From ca9bc12b90fbc4e2b1f81360f63842c9da54bb3c Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Tue, 11 Jan 2011 13:47:24 +0100
Subject: drbd: Get rid of BE_DRBD_MAGIC and BE_DRBD_MAGIC_BIG

Converting the constants happens at compile time.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 9e5f5607eba3..d28202811672 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -334,9 +334,7 @@ enum drbd_timeout_flag {
 #define UUID_JUST_CREATED ((__u64)4)
 
 #define DRBD_MAGIC 0x83740267
-#define BE_DRBD_MAGIC __constant_cpu_to_be32(DRBD_MAGIC)
 #define DRBD_MAGIC_BIG 0x835a
-#define BE_DRBD_MAGIC_BIG __constant_cpu_to_be16(DRBD_MAGIC_BIG)
 
 /* these are of type "int" */
 #define DRBD_MD_INDEX_INTERNAL -1
-- 
cgit v1.2.3-55-g7522


From 9749f30f1a387070e6e8351f35aeb829eacc3ab6 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Wed, 20 Jul 2011 14:59:37 +0200
Subject: idr: idr_for_each_entry() macro

Inspired by the list_for_each_entry() macro
---
 include/linux/idr.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index 255491cf522e..52a9da295296 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -152,4 +152,15 @@ void ida_simple_remove(struct ida *ida, unsigned int id);
 
 void __init idr_init_cache(void);
 
+/**
+ * idr_for_each_entry - iterate over an idr's elements of a given type
+ * @idp:     idr handle
+ * @entry:   the type * to use as cursor
+ * @id:      id entry's key
+ */
+#define idr_for_each_entry(idp, entry, id)				\
+	for (id = 0, entry = (typeof(entry))idr_get_next((idp), &(id)); \
+	     entry != NULL;                                             \
+	     ++id, entry = (typeof(entry))idr_get_next((idp), &(id)))
+
 #endif /* __IDR_H__ */
-- 
cgit v1.2.3-55-g7522


From fd340c12c98b57ec0751ebb317057eee41be0c3d Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Wed, 19 Jan 2011 16:57:39 +0100
Subject: drbd: Use new header layout

The new header layout will only be used if the peer supports
it of course.

For the first packet and the handshake packet the old (h80)
layout is used for compatibility reasons.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h      |  1 -
 drivers/block/drbd/drbd_main.c     | 82 +++++++++++++++++---------------------
 drivers/block/drbd/drbd_receiver.c |  7 +++-
 include/linux/drbd.h               |  2 +-
 4 files changed, 42 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index dc669dfe5b0d..4de43481bcb9 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -345,7 +345,6 @@ struct p_header95 {
 	u16	  magic;	/* use DRBD_MAGIC_BIG here */
 	u16	  command;
 	u32	  length;	/* Use only 24 bits of that. Ignore the highest 8 bit. */
-	u8	  payload[0];
 } __packed;
 
 struct p_header {
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 55ce48e24b8e..f8cb15c84ed8 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1820,12 +1820,36 @@ void drbd_thread_current_set_cpu(struct drbd_conf *mdev)
 }
 #endif
 
+static void prepare_header80(struct drbd_conf *mdev, struct p_header80 *h,
+			     enum drbd_packets cmd, int size)
+{
+	h->magic   = cpu_to_be32(DRBD_MAGIC);
+	h->command = cpu_to_be16(cmd);
+	h->length  = cpu_to_be16(size);
+}
+
+static void prepare_header95(struct drbd_conf *mdev, struct p_header95 *h,
+			     enum drbd_packets cmd, int size)
+{
+	h->magic   = cpu_to_be16(DRBD_MAGIC_BIG);
+	h->command = cpu_to_be16(cmd);
+	h->length  = cpu_to_be32(size);
+}
+
+static void prepare_header(struct drbd_conf *mdev, struct p_header *h,
+			   enum drbd_packets cmd, int size)
+{
+	if (mdev->tconn->agreed_pro_version >= 100 || size > DRBD_MAX_SIZE_H80_PACKET)
+		prepare_header95(mdev, &h->h95, cmd, size);
+	else
+		prepare_header80(mdev, &h->h80, cmd, size);
+}
+
 /* the appropriate socket mutex must be held already */
 int _drbd_send_cmd(struct drbd_conf *mdev, struct socket *sock,
-			  enum drbd_packets cmd, struct p_header *hg,
+			  enum drbd_packets cmd, struct p_header *h,
 			  size_t size, unsigned msg_flags)
 {
-	struct p_header80 *h = (struct p_header80 *)hg;
 	int sent, ok;
 
 	if (!expect(h))
@@ -1833,9 +1857,7 @@ int _drbd_send_cmd(struct drbd_conf *mdev, struct socket *sock,
 	if (!expect(size))
 		return false;
 
-	h->magic   = cpu_to_be32(DRBD_MAGIC);
-	h->command = cpu_to_be16(cmd);
-	h->length  = cpu_to_be16(size-sizeof(struct p_header80));
+	prepare_header(mdev, h, cmd, size - sizeof(struct p_header));
 
 	sent = drbd_send(mdev, sock, h, size, msg_flags);
 
@@ -1878,12 +1900,10 @@ int drbd_send_cmd(struct drbd_conf *mdev, int use_data_socket,
 int drbd_send_cmd2(struct drbd_conf *mdev, enum drbd_packets cmd, char *data,
 		   size_t size)
 {
-	struct p_header80 h;
+	struct p_header h;
 	int ok;
 
-	h.magic   = cpu_to_be32(DRBD_MAGIC);
-	h.command = cpu_to_be16(cmd);
-	h.length  = cpu_to_be16(size);
+	prepare_header(mdev, &h, cmd, size);
 
 	if (!drbd_get_data_sock(mdev))
 		return 0;
@@ -2456,14 +2476,11 @@ int drbd_send_drequest_csum(struct drbd_conf *mdev,
 	int ok;
 	struct p_block_req p;
 
+	prepare_header(mdev, &p.head, cmd, sizeof(p) - sizeof(struct p_header) + digest_size);
 	p.sector   = cpu_to_be64(sector);
 	p.block_id = ID_SYNCER /* unused */;
 	p.blksize  = cpu_to_be32(size);
 
-	p.head.h80.magic   = cpu_to_be32(DRBD_MAGIC);
-	p.head.h80.command = cpu_to_be16(cmd);
-	p.head.h80.length  = cpu_to_be16(sizeof(p) - sizeof(struct p_header80) + digest_size);
-
 	mutex_lock(&mdev->tconn->data.mutex);
 
 	ok = (sizeof(p) == drbd_send(mdev, mdev->tconn->data.socket, &p, sizeof(p), 0));
@@ -2663,22 +2680,10 @@ int drbd_send_dblock(struct drbd_conf *mdev, struct drbd_request *req)
 	dgs = (mdev->tconn->agreed_pro_version >= 87 && mdev->tconn->integrity_w_tfm) ?
 		crypto_hash_digestsize(mdev->tconn->integrity_w_tfm) : 0;
 
-	if (req->i.size <= DRBD_MAX_SIZE_H80_PACKET) {
-		p.head.h80.magic   = cpu_to_be32(DRBD_MAGIC);
-		p.head.h80.command = cpu_to_be16(P_DATA);
-		p.head.h80.length  =
-			cpu_to_be16(sizeof(p) - sizeof(struct p_header) + dgs + req->i.size);
-	} else {
-		p.head.h95.magic   = cpu_to_be16(DRBD_MAGIC_BIG);
-		p.head.h95.command = cpu_to_be16(P_DATA);
-		p.head.h95.length  =
-			cpu_to_be32(sizeof(p) - sizeof(struct p_header) + dgs + req->i.size);
-	}
-
+	prepare_header(mdev, &p.head, P_DATA, sizeof(p) - sizeof(struct p_header) + dgs + req->i.size);
 	p.sector   = cpu_to_be64(req->i.sector);
 	p.block_id = (unsigned long)req;
-	p.seq_num  = cpu_to_be32(req->seq_num =
-				 atomic_add_return(1, &mdev->packet_seq));
+	p.seq_num  = cpu_to_be32(req->seq_num = atomic_add_return(1, &mdev->packet_seq));
 
 	dp_flags = bio_flags_to_wire(mdev, req->master_bio->bi_rw);
 
@@ -2748,18 +2753,7 @@ int drbd_send_block(struct drbd_conf *mdev, enum drbd_packets cmd,
 	dgs = (mdev->tconn->agreed_pro_version >= 87 && mdev->tconn->integrity_w_tfm) ?
 		crypto_hash_digestsize(mdev->tconn->integrity_w_tfm) : 0;
 
-	if (e->i.size <= DRBD_MAX_SIZE_H80_PACKET) {
-		p.head.h80.magic   = cpu_to_be32(DRBD_MAGIC);
-		p.head.h80.command = cpu_to_be16(cmd);
-		p.head.h80.length  =
-			cpu_to_be16(sizeof(p) - sizeof(struct p_header80) + dgs + e->i.size);
-	} else {
-		p.head.h95.magic   = cpu_to_be16(DRBD_MAGIC_BIG);
-		p.head.h95.command = cpu_to_be16(cmd);
-		p.head.h95.length  =
-			cpu_to_be32(sizeof(p) - sizeof(struct p_header80) + dgs + e->i.size);
-	}
-
+	prepare_header(mdev, &p.head, cmd, sizeof(p) - sizeof(struct p_header80) + dgs + e->i.size);
 	p.sector   = cpu_to_be64(e->i.sector);
 	p.block_id = e->block_id;
 	/* p.seq_num  = 0;    No sequence numbers here.. */
@@ -3028,7 +3022,7 @@ void drbd_init_set_defaults(struct drbd_conf *mdev)
 	drbd_thread_init(mdev, &mdev->tconn->worker, drbd_worker);
 	drbd_thread_init(mdev, &mdev->tconn->asender, drbd_asender);
 
-	mdev->tconn->agreed_pro_version = PRO_VERSION_MAX;
+	/* mdev->tconn->agreed_pro_version gets initialized in drbd_connect() */
 	mdev->write_ordering = WO_bdev_flush;
 	mdev->resync_wenr = LC_FREE;
 	mdev->peer_max_bio_size = DRBD_MAX_BIO_SIZE_SAFE;
@@ -3506,12 +3500,8 @@ int __init drbd_init(void)
 {
 	int err;
 
-	if (sizeof(struct p_handshake) != 80) {
-		printk(KERN_ERR
-		       "drbd: never change the size or layout "
-		       "of the HandShake packet.\n");
-		return -EINVAL;
-	}
+	BUILD_BUG_ON(sizeof(struct p_header80) != sizeof(struct p_header95));
+	BUILD_BUG_ON(sizeof(struct p_handshake) != 80);
 
 	if (minor_count < DRBD_MINOR_COUNT_MIN || minor_count > DRBD_MINOR_COUNT_MAX) {
 		printk(KERN_ERR
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 9393fe482efc..8f5a241fe20a 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -761,6 +761,9 @@ static int drbd_connect(struct drbd_conf *mdev)
 		return -2;
 
 	clear_bit(DISCARD_CONCURRENT, &mdev->flags);
+	mdev->tconn->agreed_pro_version = 99;
+	/* agreed_pro_version must be smaller than 100 so we send the old
+	   header (h80) in the first packet and in the handshake packet. */
 
 	sock  = NULL;
 	msock = NULL;
@@ -935,12 +938,12 @@ static int drbd_recv_header(struct drbd_conf *mdev, enum drbd_packets *cmd, unsi
 		return false;
 	}
 
-	if (likely(h->h80.magic == cpu_to_be32(DRBD_MAGIC))) {
+	if (h->h80.magic == cpu_to_be32(DRBD_MAGIC)) {
 		*cmd = be16_to_cpu(h->h80.command);
 		*packet_size = be16_to_cpu(h->h80.length);
 	} else if (h->h95.magic == cpu_to_be16(DRBD_MAGIC_BIG)) {
 		*cmd = be16_to_cpu(h->h95.command);
-		*packet_size = be32_to_cpu(h->h95.length);
+		*packet_size = be32_to_cpu(h->h95.length) & 0x00ffffff;
 	} else {
 		dev_err(DEV, "magic?? on data m: 0x%08x c: %d l: %d\n",
 		    be32_to_cpu(h->h80.magic),
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index d28202811672..35fc08a0a552 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -56,7 +56,7 @@ extern const char *drbd_buildtag(void);
 #define REL_VERSION "8.3.11"
 #define API_VERSION 88
 #define PRO_VERSION_MIN 86
-#define PRO_VERSION_MAX 96
+#define PRO_VERSION_MAX 100
 
 
 enum drbd_io_error_p {
-- 
cgit v1.2.3-55-g7522


From 4738fa16907a933d72bbcae1b8922dc9330fde92 Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Mon, 21 Feb 2011 13:20:55 +0100
Subject: drbd: use clear_bit_unlock() where appropriate

Some open-coded clear_bit(); smp_mb__after_clear_bit();
should in fact have been smp_mb__before_clear_bit(); clear_bit();

Instead, use clear_bit_unlock() to annotate the intention,
and have it do the right thing.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_bitmap.c |  3 +--
 drivers/block/drbd/drbd_main.c   |  3 +--
 include/linux/lru_cache.h        |  3 +--
 lib/lru_cache.c                  | 10 ++++------
 4 files changed, 7 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index e8d652f197c3..4be737055718 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -219,8 +219,7 @@ static void bm_page_unlock_io(struct drbd_conf *mdev, int page_nr)
 {
 	struct drbd_bitmap *b = mdev->bitmap;
 	void *addr = &page_private(b->bm_pages[page_nr]);
-	clear_bit(BM_PAGE_IO_LOCK, addr);
-	smp_mb__after_clear_bit();
+	clear_bit_unlock(BM_PAGE_IO_LOCK, addr);
 	wake_up(&mdev->bitmap->bm_io_wait);
 }
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 592f0c949fd0..c77e51a40926 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2818,8 +2818,7 @@ static int w_bitmap_io(struct drbd_work *w, int unused)
 		put_ldev(mdev);
 	}
 
-	clear_bit(BITMAP_IO, &mdev->flags);
-	smp_mb__after_clear_bit();
+	clear_bit_unlock(BITMAP_IO, &mdev->flags);
 	wake_up(&mdev->misc_wait);
 
 	if (work->done)
diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h
index 7a71ffad037c..4cceafb0732d 100644
--- a/include/linux/lru_cache.h
+++ b/include/linux/lru_cache.h
@@ -275,8 +275,7 @@ static inline int lc_try_lock(struct lru_cache *lc)
  */
 static inline void lc_unlock(struct lru_cache *lc)
 {
-	clear_bit(__LC_DIRTY, &lc->flags);
-	smp_mb__after_clear_bit();
+	clear_bit_unlock(__LC_DIRTY, &lc->flags);
 }
 
 static inline int lc_is_used(struct lru_cache *lc, unsigned int enr)
diff --git a/lib/lru_cache.c b/lib/lru_cache.c
index a07e7268d7ed..9f353f7f41ca 100644
--- a/lib/lru_cache.c
+++ b/lib/lru_cache.c
@@ -44,8 +44,8 @@ MODULE_LICENSE("GPL");
 } while (0)
 
 #define RETURN(x...)     do { \
-	clear_bit(__LC_PARANOIA, &lc->flags); \
-	smp_mb__after_clear_bit(); return x ; } while (0)
+	clear_bit_unlock(__LC_PARANOIA, &lc->flags); \
+	return x ; } while (0)
 
 /* BUG() if e is not one of the elements tracked by lc */
 #define PARANOIA_LC_ELEMENT(lc, e) do {	\
@@ -438,8 +438,7 @@ void lc_changed(struct lru_cache *lc, struct lc_element *e)
 	hlist_add_head(&e->colision, lc_hash_slot(lc, lc->new_number));
 	lc->changing_element = NULL;
 	lc->new_number = LC_FREE;
-	clear_bit(__LC_DIRTY, &lc->flags);
-	smp_mb__after_clear_bit();
+	clear_bit_unlock(__LC_DIRTY, &lc->flags);
 	RETURN();
 }
 
@@ -463,8 +462,7 @@ unsigned int lc_put(struct lru_cache *lc, struct lc_element *e)
 		/* move it to the front of LRU. */
 		list_move(&e->list, &lc->lru);
 		lc->used--;
-		clear_bit(__LC_STARVING, &lc->flags);
-		smp_mb__after_clear_bit();
+		clear_bit_unlock(__LC_STARVING, &lc->flags);
 	}
 	RETURN(e->refcnt);
 }
-- 
cgit v1.2.3-55-g7522


From 46a15bc3ec425b546d140581c28192ab7877ddc4 Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Mon, 21 Feb 2011 13:21:01 +0100
Subject: lru_cache: allow multiple changes per transaction

Allow multiple changes to the active set of elements in lru_cache.
The only current user of lru_cache, drbd, is driving this generalisation.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_actlog.c |  50 ++------
 drivers/block/drbd/drbd_nl.c     |   4 +-
 include/linux/lru_cache.h        |  68 +++++++----
 lib/lru_cache.c                  | 243 +++++++++++++++++++++++++++------------
 4 files changed, 225 insertions(+), 140 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 1ce3de6eed1b..44097c87fed7 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -175,7 +175,6 @@ static struct lc_element *_al_get(struct drbd_conf *mdev, unsigned int enr)
 {
 	struct lc_element *al_ext;
 	struct lc_element *tmp;
-	unsigned long     al_flags = 0;
 	int wake;
 
 	spin_lock_irq(&mdev->al_lock);
@@ -190,19 +189,8 @@ static struct lc_element *_al_get(struct drbd_conf *mdev, unsigned int enr)
 			return NULL;
 		}
 	}
-	al_ext   = lc_get(mdev->act_log, enr);
-	al_flags = mdev->act_log->flags;
+	al_ext = lc_get(mdev->act_log, enr);
 	spin_unlock_irq(&mdev->al_lock);
-
-	/*
-	if (!al_ext) {
-		if (al_flags & LC_STARVING)
-			dev_warn(DEV, "Have to wait for LRU element (AL too small?)\n");
-		if (al_flags & LC_DIRTY)
-			dev_warn(DEV, "Ongoing AL update (AL device too slow?)\n");
-	}
-	*/
-
 	return al_ext;
 }
 
@@ -235,7 +223,7 @@ void drbd_al_begin_io(struct drbd_conf *mdev, sector_t sector)
 		mdev->al_writ_cnt++;
 
 		spin_lock_irq(&mdev->al_lock);
-		lc_changed(mdev->act_log, al_ext);
+		lc_committed(mdev->act_log);
 		spin_unlock_irq(&mdev->al_lock);
 		wake_up(&mdev->al_wait);
 	}
@@ -601,7 +589,7 @@ void drbd_al_shrink(struct drbd_conf *mdev)
 	struct lc_element *al_ext;
 	int i;
 
-	D_ASSERT(test_bit(__LC_DIRTY, &mdev->act_log->flags));
+	D_ASSERT(test_bit(__LC_LOCKED, &mdev->act_log->flags));
 
 	for (i = 0; i < mdev->act_log->nr_elements; i++) {
 		al_ext = lc_element_by_index(mdev->act_log, i);
@@ -708,7 +696,9 @@ static void drbd_try_clear_on_disk_bm(struct drbd_conf *mdev, sector_t sector,
 			}
 			ext->rs_left = rs_left;
 			ext->rs_failed = success ? 0 : count;
-			lc_changed(mdev->resync, &ext->lce);
+			/* we don't keep a persistent log of the resync lru,
+			 * we can commit any change right away. */
+			lc_committed(mdev->resync);
 		}
 		lc_put(mdev->resync, &ext->lce);
 		/* no race, we are within the al_lock! */
@@ -892,7 +882,7 @@ struct bm_extent *_bme_get(struct drbd_conf *mdev, unsigned int enr)
 		if (bm_ext->lce.lc_number != enr) {
 			bm_ext->rs_left = drbd_bm_e_weight(mdev, enr);
 			bm_ext->rs_failed = 0;
-			lc_changed(mdev->resync, &bm_ext->lce);
+			lc_committed(mdev->resync);
 			wakeup = 1;
 		}
 		if (bm_ext->lce.refcnt == 1)
@@ -908,7 +898,7 @@ struct bm_extent *_bme_get(struct drbd_conf *mdev, unsigned int enr)
 		if (rs_flags & LC_STARVING)
 			dev_warn(DEV, "Have to wait for element"
 			     " (resync LRU too small?)\n");
-		BUG_ON(rs_flags & LC_DIRTY);
+		BUG_ON(rs_flags & LC_LOCKED);
 	}
 
 	return bm_ext;
@@ -916,26 +906,12 @@ struct bm_extent *_bme_get(struct drbd_conf *mdev, unsigned int enr)
 
 static int _is_in_al(struct drbd_conf *mdev, unsigned int enr)
 {
-	struct lc_element *al_ext;
-	int rv = 0;
+	int rv;
 
 	spin_lock_irq(&mdev->al_lock);
-	if (unlikely(enr == mdev->act_log->new_number))
-		rv = 1;
-	else {
-		al_ext = lc_find(mdev->act_log, enr);
-		if (al_ext) {
-			if (al_ext->refcnt)
-				rv = 1;
-		}
-	}
+	rv = lc_is_used(mdev->act_log, enr);
 	spin_unlock_irq(&mdev->al_lock);
 
-	/*
-	if (unlikely(rv)) {
-		dev_info(DEV, "Delaying sync read until app's write is done\n");
-	}
-	*/
 	return rv;
 }
 
@@ -1065,13 +1041,13 @@ int drbd_try_rs_begin_io(struct drbd_conf *mdev, sector_t sector)
 			if (rs_flags & LC_STARVING)
 				dev_warn(DEV, "Have to wait for element"
 				     " (resync LRU too small?)\n");
-			BUG_ON(rs_flags & LC_DIRTY);
+			BUG_ON(rs_flags & LC_LOCKED);
 			goto try_again;
 		}
 		if (bm_ext->lce.lc_number != enr) {
 			bm_ext->rs_left = drbd_bm_e_weight(mdev, enr);
 			bm_ext->rs_failed = 0;
-			lc_changed(mdev->resync, &bm_ext->lce);
+			lc_committed(mdev->resync);
 			wake_up(&mdev->al_wait);
 			D_ASSERT(test_bit(BME_LOCKED, &bm_ext->flags) == 0);
 		}
@@ -1082,8 +1058,6 @@ int drbd_try_rs_begin_io(struct drbd_conf *mdev, sector_t sector)
 	}
 check_al:
 	for (i = 0; i < AL_EXT_PER_BM_SECT; i++) {
-		if (unlikely(al_enr+i == mdev->act_log->new_number))
-			goto try_again;
 		if (lc_is_used(mdev->act_log, al_enr+i))
 			goto try_again;
 	}
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index ae8f42e38e4f..0a92f5226c2a 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -760,7 +760,7 @@ static int drbd_check_al_size(struct drbd_conf *mdev)
 
 	in_use = 0;
 	t = mdev->act_log;
-	n = lc_create("act_log", drbd_al_ext_cache,
+	n = lc_create("act_log", drbd_al_ext_cache, 1,
 		mdev->sync_conf.al_extents, sizeof(struct lc_element), 0);
 
 	if (n == NULL) {
@@ -1016,7 +1016,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	}
 
 	resync_lru = lc_create("resync", drbd_bm_ext_cache,
-			61, sizeof(struct bm_extent),
+			1, 61, sizeof(struct bm_extent),
 			offsetof(struct bm_extent, lce));
 	if (!resync_lru) {
 		retcode = ERR_NOMEM;
diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h
index 4cceafb0732d..cbafae40c649 100644
--- a/include/linux/lru_cache.h
+++ b/include/linux/lru_cache.h
@@ -166,9 +166,11 @@ struct lc_element {
 	/* if we want to track a larger set of objects,
 	 * it needs to become arch independend u64 */
 	unsigned lc_number;
-
 	/* special label when on free list */
 #define LC_FREE (~0U)
+
+	/* for pending changes */
+	unsigned lc_new_number;
 };
 
 struct lru_cache {
@@ -176,6 +178,7 @@ struct lru_cache {
 	struct list_head lru;
 	struct list_head free;
 	struct list_head in_use;
+	struct list_head to_be_changed;
 
 	/* the pre-created kmem cache to allocate the objects from */
 	struct kmem_cache *lc_cache;
@@ -186,7 +189,7 @@ struct lru_cache {
 	size_t element_off;
 
 	/* number of elements (indices) */
-	unsigned int  nr_elements;
+	unsigned int nr_elements;
 	/* Arbitrary limit on maximum tracked objects. Practical limit is much
 	 * lower due to allocation failures, probably. For typical use cases,
 	 * nr_elements should be a few thousand at most.
@@ -194,18 +197,19 @@ struct lru_cache {
 	 * 8 high bits of .lc_index to be overloaded with flags in the future. */
 #define LC_MAX_ACTIVE	(1<<24)
 
+	/* allow to accumulate a few (index:label) changes,
+	 * but no more than max_pending_changes */
+	unsigned int max_pending_changes;
+	/* number of elements currently on to_be_changed list */
+	unsigned int pending_changes;
+
 	/* statistics */
-	unsigned used; /* number of lelements currently on in_use list */
-	unsigned long hits, misses, starving, dirty, changed;
+	unsigned used; /* number of elements currently on in_use list */
+	unsigned long hits, misses, starving, locked, changed;
 
 	/* see below: flag-bits for lru_cache */
 	unsigned long flags;
 
-	/* when changing the label of an index element */
-	unsigned int  new_number;
-
-	/* for paranoia when changing the label of an index element */
-	struct lc_element *changing_element;
 
 	void  *lc_private;
 	const char *name;
@@ -221,10 +225,15 @@ enum {
 	/* debugging aid, to catch concurrent access early.
 	 * user needs to guarantee exclusive access by proper locking! */
 	__LC_PARANOIA,
-	/* if we need to change the set, but currently there is a changing
-	 * transaction pending, we are "dirty", and must deferr further
-	 * changing requests */
+
+	/* annotate that the set is "dirty", possibly accumulating further
+	 * changes, until a transaction is finally triggered */
 	__LC_DIRTY,
+
+	/* Locked, no further changes allowed.
+	 * Also used to serialize changing transactions. */
+	__LC_LOCKED,
+
 	/* if we need to change the set, but currently there is no free nor
 	 * unused element available, we are "starving", and must not give out
 	 * further references, to guarantee that eventually some refcnt will
@@ -236,9 +245,11 @@ enum {
 };
 #define LC_PARANOIA (1<<__LC_PARANOIA)
 #define LC_DIRTY    (1<<__LC_DIRTY)
+#define LC_LOCKED   (1<<__LC_LOCKED)
 #define LC_STARVING (1<<__LC_STARVING)
 
 extern struct lru_cache *lc_create(const char *name, struct kmem_cache *cache,
+		unsigned max_pending_changes,
 		unsigned e_count, size_t e_size, size_t e_off);
 extern void lc_reset(struct lru_cache *lc);
 extern void lc_destroy(struct lru_cache *lc);
@@ -249,7 +260,7 @@ extern struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr);
 extern struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr);
 extern struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr);
 extern unsigned int lc_put(struct lru_cache *lc, struct lc_element *e);
-extern void lc_changed(struct lru_cache *lc, struct lc_element *e);
+extern void lc_committed(struct lru_cache *lc);
 
 struct seq_file;
 extern size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc);
@@ -258,31 +269,40 @@ extern void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char
 				void (*detail) (struct seq_file *, struct lc_element *));
 
 /**
- * lc_try_lock - can be used to stop lc_get() from changing the tracked set
+ * lc_try_lock_for_transaction - can be used to stop lc_get() from changing the tracked set
  * @lc: the lru cache to operate on
  *
- * Note that the reference counts and order on the active and lru lists may
- * still change.  Returns true if we acquired the lock.
+ * Allows (expects) the set to be "dirty".  Note that the reference counts and
+ * order on the active and lru lists may still change.  Used to serialize
+ * changing transactions.  Returns true if we aquired the lock.
  */
-static inline int lc_try_lock(struct lru_cache *lc)
+static inline int lc_try_lock_for_transaction(struct lru_cache *lc)
 {
-	return !test_and_set_bit(__LC_DIRTY, &lc->flags);
+	return !test_and_set_bit(__LC_LOCKED, &lc->flags);
 }
 
+/**
+ * lc_try_lock - variant to stop lc_get() from changing the tracked set
+ * @lc: the lru cache to operate on
+ *
+ * Note that the reference counts and order on the active and lru lists may
+ * still change.  Only works on a "clean" set.  Returns true if we aquired the
+ * lock, which means there are no pending changes, and any further attempt to
+ * change the set will not succeed until the next lc_unlock().
+ */
+extern int lc_try_lock(struct lru_cache *lc);
+
 /**
  * lc_unlock - unlock @lc, allow lc_get() to change the set again
  * @lc: the lru cache to operate on
  */
 static inline void lc_unlock(struct lru_cache *lc)
 {
-	clear_bit_unlock(__LC_DIRTY, &lc->flags);
+	clear_bit(__LC_DIRTY, &lc->flags);
+	clear_bit_unlock(__LC_LOCKED, &lc->flags);
 }
 
-static inline int lc_is_used(struct lru_cache *lc, unsigned int enr)
-{
-	struct lc_element *e = lc_find(lc, enr);
-	return e && e->refcnt;
-}
+extern bool lc_is_used(struct lru_cache *lc, unsigned int enr);
 
 #define lc_entry(ptr, type, member) \
 	container_of(ptr, type, member)
diff --git a/lib/lru_cache.c b/lib/lru_cache.c
index 17621684758a..d71d89498943 100644
--- a/lib/lru_cache.c
+++ b/lib/lru_cache.c
@@ -55,9 +55,40 @@ MODULE_LICENSE("GPL");
 	BUG_ON(i >= lc_->nr_elements);	\
 	BUG_ON(lc_->lc_element[i] != e_); } while (0)
 
+
+/* We need to atomically
+ *  - try to grab the lock (set LC_LOCKED)
+ *  - only if there is no pending transaction
+ *    (neither LC_DIRTY nor LC_STARVING is set)
+ * Because of PARANOIA_ENTRY() above abusing lc->flags as well,
+ * it is not sufficient to just say
+ *	return 0 == cmpxchg(&lc->flags, 0, LC_LOCKED);
+ */
+int lc_try_lock(struct lru_cache *lc)
+{
+	unsigned long val;
+	do {
+		val = cmpxchg(&lc->flags, 0, LC_LOCKED);
+	} while (unlikely (val == LC_PARANOIA));
+	/* Spin until no-one is inside a PARANOIA_ENTRY()/RETURN() section. */
+	return 0 == val;
+#if 0
+	/* Alternative approach, spin in case someone enters or leaves a
+	 * PARANOIA_ENTRY()/RETURN() section. */
+	unsigned long old, new, val;
+	do {
+		old = lc->flags & LC_PARANOIA;
+		new = old | LC_LOCKED;
+		val = cmpxchg(&lc->flags, old, new);
+	} while (unlikely (val == (old ^ LC_PARANOIA)));
+	return old == val;
+#endif
+}
+
 /**
  * lc_create - prepares to track objects in an active set
  * @name: descriptive name only used in lc_seq_printf_stats and lc_seq_dump_details
+ * @max_pending_changes: maximum changes to accumulate until a transaction is required
  * @e_count: number of elements allowed to be active simultaneously
  * @e_size: size of the tracked objects
  * @e_off: offset to the &struct lc_element member in a tracked object
@@ -66,6 +97,7 @@ MODULE_LICENSE("GPL");
  * or NULL on (allocation) failure.
  */
 struct lru_cache *lc_create(const char *name, struct kmem_cache *cache,
+		unsigned max_pending_changes,
 		unsigned e_count, size_t e_size, size_t e_off)
 {
 	struct hlist_head *slot = NULL;
@@ -98,12 +130,13 @@ struct lru_cache *lc_create(const char *name, struct kmem_cache *cache,
 	INIT_LIST_HEAD(&lc->in_use);
 	INIT_LIST_HEAD(&lc->lru);
 	INIT_LIST_HEAD(&lc->free);
+	INIT_LIST_HEAD(&lc->to_be_changed);
 
 	lc->name = name;
 	lc->element_size = e_size;
 	lc->element_off = e_off;
 	lc->nr_elements = e_count;
-	lc->new_number = LC_FREE;
+	lc->max_pending_changes = max_pending_changes;
 	lc->lc_cache = cache;
 	lc->lc_element = element;
 	lc->lc_slot = slot;
@@ -117,6 +150,7 @@ struct lru_cache *lc_create(const char *name, struct kmem_cache *cache,
 		e = p + e_off;
 		e->lc_index = i;
 		e->lc_number = LC_FREE;
+		e->lc_new_number = LC_FREE;
 		list_add(&e->list, &lc->free);
 		element[i] = e;
 	}
@@ -175,15 +209,15 @@ void lc_reset(struct lru_cache *lc)
 	INIT_LIST_HEAD(&lc->in_use);
 	INIT_LIST_HEAD(&lc->lru);
 	INIT_LIST_HEAD(&lc->free);
+	INIT_LIST_HEAD(&lc->to_be_changed);
 	lc->used = 0;
 	lc->hits = 0;
 	lc->misses = 0;
 	lc->starving = 0;
-	lc->dirty = 0;
+	lc->locked = 0;
 	lc->changed = 0;
+	lc->pending_changes = 0;
 	lc->flags = 0;
-	lc->changing_element = NULL;
-	lc->new_number = LC_FREE;
 	memset(lc->lc_slot, 0, sizeof(struct hlist_head) * lc->nr_elements);
 
 	for (i = 0; i < lc->nr_elements; i++) {
@@ -194,6 +228,7 @@ void lc_reset(struct lru_cache *lc)
 		/* re-init it */
 		e->lc_index = i;
 		e->lc_number = LC_FREE;
+		e->lc_new_number = LC_FREE;
 		list_add(&e->list, &lc->free);
 	}
 }
@@ -208,14 +243,14 @@ size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc)
 	/* NOTE:
 	 * total calls to lc_get are
 	 * (starving + hits + misses)
-	 * misses include "dirty" count (update from an other thread in
+	 * misses include "locked" count (update from an other thread in
 	 * progress) and "changed", when this in fact lead to an successful
 	 * update of the cache.
 	 */
 	return seq_printf(seq, "\t%s: used:%u/%u "
-		"hits:%lu misses:%lu starving:%lu dirty:%lu changed:%lu\n",
+		"hits:%lu misses:%lu starving:%lu locked:%lu changed:%lu\n",
 		lc->name, lc->used, lc->nr_elements,
-		lc->hits, lc->misses, lc->starving, lc->dirty, lc->changed);
+		lc->hits, lc->misses, lc->starving, lc->locked, lc->changed);
 }
 
 static struct hlist_head *lc_hash_slot(struct lru_cache *lc, unsigned int enr)
@@ -224,16 +259,8 @@ static struct hlist_head *lc_hash_slot(struct lru_cache *lc, unsigned int enr)
 }
 
 
-/**
- * lc_find - find element by label, if present in the hash table
- * @lc: The lru_cache object
- * @enr: element number
- *
- * Returns the pointer to an element, if the element with the requested
- * "label" or element number is present in the hash table,
- * or NULL if not found. Does not change the refcnt.
- */
-struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr)
+static struct lc_element *__lc_find(struct lru_cache *lc, unsigned int enr,
+		bool include_changing)
 {
 	struct hlist_node *n;
 	struct lc_element *e;
@@ -241,29 +268,48 @@ struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr)
 	BUG_ON(!lc);
 	BUG_ON(!lc->nr_elements);
 	hlist_for_each_entry(e, n, lc_hash_slot(lc, enr), colision) {
-		if (e->lc_number == enr)
+		/* "about to be changed" elements, pending transaction commit,
+		 * are hashed by their "new number". "Normal" elements have
+		 * lc_number == lc_new_number. */
+		if (e->lc_new_number != enr)
+			continue;
+		if (e->lc_new_number == e->lc_number || include_changing)
 			return e;
+		break;
 	}
 	return NULL;
 }
 
-/* returned element will be "recycled" immediately */
-static struct lc_element *lc_evict(struct lru_cache *lc)
+/**
+ * lc_find - find element by label, if present in the hash table
+ * @lc: The lru_cache object
+ * @enr: element number
+ *
+ * Returns the pointer to an element, if the element with the requested
+ * "label" or element number is present in the hash table,
+ * or NULL if not found. Does not change the refcnt.
+ * Ignores elements that are "about to be used", i.e. not yet in the active
+ * set, but still pending transaction commit.
+ */
+struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr)
 {
-	struct list_head  *n;
-	struct lc_element *e;
-
-	if (list_empty(&lc->lru))
-		return NULL;
-
-	n = lc->lru.prev;
-	e = list_entry(n, struct lc_element, list);
-
-	PARANOIA_LC_ELEMENT(lc, e);
+	return __lc_find(lc, enr, 0);
+}
 
-	list_del(&e->list);
-	hlist_del(&e->colision);
-	return e;
+/**
+ * lc_is_used - find element by label
+ * @lc: The lru_cache object
+ * @enr: element number
+ *
+ * Returns true, if the element with the requested "label" or element number is
+ * present in the hash table, and is used (refcnt > 0).
+ * Also finds elements that are not _currently_ used but only "about to be
+ * used", i.e. on the "to_be_changed" list, pending transaction commit.
+ */
+bool lc_is_used(struct lru_cache *lc, unsigned int enr)
+{
+	struct lc_element *e = __lc_find(lc, enr, 1);
+	return e && e->refcnt;
 }
 
 /**
@@ -280,22 +326,34 @@ void lc_del(struct lru_cache *lc, struct lc_element *e)
 	PARANOIA_LC_ELEMENT(lc, e);
 	BUG_ON(e->refcnt);
 
-	e->lc_number = LC_FREE;
+	e->lc_number = e->lc_new_number = LC_FREE;
 	hlist_del_init(&e->colision);
 	list_move(&e->list, &lc->free);
 	RETURN();
 }
 
-static struct lc_element *lc_get_unused_element(struct lru_cache *lc)
+static struct lc_element *lc_prepare_for_change(struct lru_cache *lc, unsigned new_number)
 {
 	struct list_head *n;
+	struct lc_element *e;
+
+	if (!list_empty(&lc->free))
+		n = lc->free.next;
+	else if (!list_empty(&lc->lru))
+		n = lc->lru.prev;
+	else
+		return NULL;
+
+	e = list_entry(n, struct lc_element, list);
+	PARANOIA_LC_ELEMENT(lc, e);
 
-	if (list_empty(&lc->free))
-		return lc_evict(lc);
+	e->lc_new_number = new_number;
+	if (!hlist_unhashed(&e->colision))
+		__hlist_del(&e->colision);
+	hlist_add_head(&e->colision, lc_hash_slot(lc, new_number));
+	list_move(&e->list, &lc->to_be_changed);
 
-	n = lc->free.next;
-	list_del(n);
-	return list_entry(n, struct lc_element, list);
+	return e;
 }
 
 static int lc_unused_element_available(struct lru_cache *lc)
@@ -318,8 +376,12 @@ static struct lc_element *__lc_get(struct lru_cache *lc, unsigned int enr, bool
 		RETURN(NULL);
 	}
 
-	e = lc_find(lc, enr);
-	if (e) {
+	e = __lc_find(lc, enr, 1);
+	/* if lc_new_number != lc_number,
+	 * this enr is currently being pulled in already,
+	 * and will be available once the pending transaction
+	 * has been committed. */
+	if (e && e->lc_new_number == e->lc_number) {
 		++lc->hits;
 		if (e->refcnt++ == 0)
 			lc->used++;
@@ -331,6 +393,24 @@ static struct lc_element *__lc_get(struct lru_cache *lc, unsigned int enr, bool
 	if (!may_change)
 		RETURN(NULL);
 
+	/* It has been found above, but on the "to_be_changed" list, not yet
+	 * committed.  Don't pull it in twice, wait for the transaction, then
+	 * try again */
+	if (e)
+		RETURN(NULL);
+
+	/* To avoid races with lc_try_lock(), first, mark us dirty
+	 * (using test_and_set_bit, as it implies memory barriers), ... */
+	test_and_set_bit(__LC_DIRTY, &lc->flags);
+
+	/* ... only then check if it is locked anyways. If lc_unlock clears
+	 * the dirty bit again, that's not a problem, we will come here again.
+	 */
+	if (test_bit(__LC_LOCKED, &lc->flags)) {
+		++lc->locked;
+		RETURN(NULL);
+	}
+
 	/* In case there is nothing available and we can not kick out
 	 * the LRU element, we have to wait ...
 	 */
@@ -339,24 +419,19 @@ static struct lc_element *__lc_get(struct lru_cache *lc, unsigned int enr, bool
 		RETURN(NULL);
 	}
 
-	/* it was not present in the active set.
-	 * we are going to recycle an unused (or even "free") element.
-	 * user may need to commit a transaction to record that change.
-	 * we serialize on flags & LC_DIRTY */
-	if (test_and_set_bit(__LC_DIRTY, &lc->flags)) {
-		++lc->dirty;
+	/* It was not present in the active set.  We are going to recycle an
+	 * unused (or even "free") element, but we won't accumulate more than
+	 * max_pending_changes changes.  */
+	if (lc->pending_changes >= lc->max_pending_changes)
 		RETURN(NULL);
-	}
 
-	e = lc_get_unused_element(lc);
+	e = lc_prepare_for_change(lc, enr);
 	BUG_ON(!e);
 
 	clear_bit(__LC_STARVING, &lc->flags);
 	BUG_ON(++e->refcnt != 1);
 	lc->used++;
-
-	lc->changing_element = e;
-	lc->new_number = enr;
+	lc->pending_changes++;
 
 	RETURN(e);
 }
@@ -388,12 +463,15 @@ static struct lc_element *__lc_get(struct lru_cache *lc, unsigned int enr, bool
  *  pointer to an UNUSED element with some different element number,
  *          where that different number may also be %LC_FREE.
  *
- *          In this case, the cache is marked %LC_DIRTY (blocking further changes),
- *          and the returned element pointer is removed from the lru list and
- *          hash collision chains.  The user now should do whatever housekeeping
- *          is necessary.
- *          Then he must call lc_changed(lc,element_pointer), to finish
- *          the change.
+ *          In this case, the cache is marked %LC_DIRTY,
+ *          so lc_try_lock() will no longer succeed.
+ *          The returned element pointer is moved to the "to_be_changed" list,
+ *          and registered with the new element number on the hash collision chains,
+ *          so it is possible to pick it up from lc_is_used().
+ *          Up to "max_pending_changes" (see lc_create()) can be accumulated.
+ *          The user now should do whatever housekeeping is necessary,
+ *          typically serialize on lc_try_lock_for_transaction(), then call
+ *          lc_committed(lc) and lc_unlock(), to finish the change.
  *
  * NOTE: The user needs to check the lc_number on EACH use, so he recognizes
  *       any cache set change.
@@ -425,22 +503,25 @@ struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr)
 }
 
 /**
- * lc_changed - tell @lc that the change has been recorded
+ * lc_committed - tell @lc that pending changes have been recorded
  * @lc: the lru cache to operate on
- * @e: the element pending label change
+ *
+ * User is expected to serialize on explicit lc_try_lock_for_transaction()
+ * before the transaction is started, and later needs to lc_unlock() explicitly
+ * as well.
  */
-void lc_changed(struct lru_cache *lc, struct lc_element *e)
+void lc_committed(struct lru_cache *lc)
 {
+	struct lc_element *e, *tmp;
+
 	PARANOIA_ENTRY();
-	BUG_ON(e != lc->changing_element);
-	PARANOIA_LC_ELEMENT(lc, e);
-	++lc->changed;
-	e->lc_number = lc->new_number;
-	list_add(&e->list, &lc->in_use);
-	hlist_add_head(&e->colision, lc_hash_slot(lc, lc->new_number));
-	lc->changing_element = NULL;
-	lc->new_number = LC_FREE;
-	clear_bit_unlock(__LC_DIRTY, &lc->flags);
+	list_for_each_entry_safe(e, tmp, &lc->to_be_changed, list) {
+		/* count number of changes, not number of transactions */
+		++lc->changed;
+		e->lc_number = e->lc_new_number;
+		list_move(&e->list, &lc->in_use);
+	}
+	lc->pending_changes = 0;
 	RETURN();
 }
 
@@ -459,7 +540,7 @@ unsigned int lc_put(struct lru_cache *lc, struct lc_element *e)
 	PARANOIA_ENTRY();
 	PARANOIA_LC_ELEMENT(lc, e);
 	BUG_ON(e->refcnt == 0);
-	BUG_ON(e == lc->changing_element);
+	BUG_ON(e->lc_number != e->lc_new_number);
 	if (--e->refcnt == 0) {
 		/* move it to the front of LRU. */
 		list_move(&e->list, &lc->lru);
@@ -504,16 +585,24 @@ unsigned int lc_index_of(struct lru_cache *lc, struct lc_element *e)
 void lc_set(struct lru_cache *lc, unsigned int enr, int index)
 {
 	struct lc_element *e;
+	struct list_head *lh;
 
 	if (index < 0 || index >= lc->nr_elements)
 		return;
 
 	e = lc_element_by_index(lc, index);
-	e->lc_number = enr;
+	BUG_ON(e->lc_number != e->lc_new_number);
+	BUG_ON(e->refcnt != 0);
 
+	e->lc_number = e->lc_new_number = enr;
 	hlist_del_init(&e->colision);
-	hlist_add_head(&e->colision, lc_hash_slot(lc, enr));
-	list_move(&e->list, e->refcnt ? &lc->in_use : &lc->lru);
+	if (enr == LC_FREE)
+		lh = &lc->free;
+	else {
+		hlist_add_head(&e->colision, lc_hash_slot(lc, enr));
+		lh = &lc->lru;
+	}
+	list_move(&e->list, lh);
 }
 
 /**
@@ -553,8 +642,10 @@ EXPORT_SYMBOL(lc_try_get);
 EXPORT_SYMBOL(lc_find);
 EXPORT_SYMBOL(lc_get);
 EXPORT_SYMBOL(lc_put);
-EXPORT_SYMBOL(lc_changed);
+EXPORT_SYMBOL(lc_committed);
 EXPORT_SYMBOL(lc_element_by_index);
 EXPORT_SYMBOL(lc_index_of);
 EXPORT_SYMBOL(lc_seq_printf_stats);
 EXPORT_SYMBOL(lc_seq_dump_details);
+EXPORT_SYMBOL(lc_try_lock);
+EXPORT_SYMBOL(lc_is_used);
-- 
cgit v1.2.3-55-g7522


From 7ad651b52218eea3f9280dbb353dfe0c42742d85 Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Mon, 21 Feb 2011 13:21:03 +0100
Subject: drbd: new on-disk activity log transaction format

Use a new on-disk transaction format for the activity log, which allows
for multiple changes to the active set per transaction.

Using 4k transaction blocks, we can now get rid of the work-around code
to deal with devices not supporting 512 byte logical block size.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_actlog.c | 409 ++++++++++++++++++++++++---------------
 drivers/block/drbd/drbd_int.h    |  44 +++--
 drivers/block/drbd/drbd_main.c   |   4 -
 drivers/block/drbd/drbd_nl.c     |  42 +---
 include/linux/drbd.h             |   4 +
 include/linux/drbd_limits.h      |   8 +-
 6 files changed, 302 insertions(+), 209 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 44097c87fed7..ea3895de4e6d 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -24,21 +24,67 @@
  */
 
 #include <linux/slab.h>
+#include <linux/crc32c.h>
 #include <linux/drbd.h>
+#include <linux/drbd_limits.h>
+#include <linux/dynamic_debug.h>
 #include "drbd_int.h"
 #include "drbd_wrappers.h"
 
-/* We maintain a trivial checksum in our on disk activity log.
- * With that we can ensure correct operation even when the storage
- * device might do a partial (last) sector write while losing power.
- */
-struct __packed al_transaction {
-	u32       magic;
-	u32       tr_number;
-	struct __packed {
-		u32 pos;
-		u32 extent; } updates[1 + AL_EXTENTS_PT];
-	u32       xor_sum;
+/* all fields on disc in big endian */
+struct __packed al_transaction_on_disk {
+	/* don't we all like magic */
+	__be32	magic;
+
+	/* to identify the most recent transaction block
+	 * in the on disk ring buffer */
+	__be32	tr_number;
+
+	/* checksum on the full 4k block, with this field set to 0. */
+	__be32	crc32c;
+
+	/* type of transaction, special transaction types like:
+	 * purge-all, set-all-idle, set-all-active, ... to-be-defined */
+	__be16	transaction_type;
+
+	/* we currently allow only a few thousand extents,
+	 * so 16bit will be enough for the slot number. */
+
+	/* how many updates in this transaction */
+	__be16	n_updates;
+
+	/* maximum slot number, "al-extents" in drbd.conf speak.
+	 * Having this in each transaction should make reconfiguration
+	 * of that parameter easier. */
+	__be16	context_size;
+
+	/* slot number the context starts with */
+	__be16	context_start_slot_nr;
+
+	/* Some reserved bytes.  Expected usage is a 64bit counter of
+	 * sectors-written since device creation, and other data generation tag
+	 * supporting usage */
+	__be32	__reserved[4];
+
+	/* --- 36 byte used --- */
+
+	/* Reserve space for up to AL_UPDATES_PER_TRANSACTION changes
+	 * in one transaction, then use the remaining byte in the 4k block for
+	 * context information.  "Flexible" number of updates per transaction
+	 * does not help, as we have to account for the case when all update
+	 * slots are used anyways, so it would only complicate code without
+	 * additional benefit.
+	 */
+	__be16	update_slot_nr[AL_UPDATES_PER_TRANSACTION];
+
+	/* but the extent number is 32bit, which at an extent size of 4 MiB
+	 * allows to cover device sizes of up to 2**54 Byte (16 PiB) */
+	__be32	update_extent_nr[AL_UPDATES_PER_TRANSACTION];
+
+	/* --- 420 bytes used (36 + 64*6) --- */
+
+	/* 4096 - 420 = 3676 = 919 * 4 */
+	__be32	context[AL_CONTEXT_PER_TRANSACTION];
 };
 
 struct update_odbm_work {
@@ -48,11 +94,8 @@ struct update_odbm_work {
 
 struct update_al_work {
 	struct drbd_work w;
-	struct lc_element *al_ext;
 	struct completion event;
-	unsigned int enr;
-	/* if old_enr != LC_FREE, write corresponding bitmap sector, too */
-	unsigned int old_enr;
+	int err;
 };
 
 struct drbd_atodb_wait {
@@ -107,67 +150,30 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
 int drbd_md_sync_page_io(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
 			 sector_t sector, int rw)
 {
-	int logical_block_size, mask, ok;
-	int offset = 0;
+	int ok;
 	struct page *iop = mdev->md_io_page;
 
 	D_ASSERT(mutex_is_locked(&mdev->md_io_mutex));
 
 	BUG_ON(!bdev->md_bdev);
 
-	logical_block_size = bdev_logical_block_size(bdev->md_bdev);
-	if (logical_block_size == 0)
-		logical_block_size = MD_SECTOR_SIZE;
-
-	/* in case logical_block_size != 512 [ s390 only? ] */
-	if (logical_block_size != MD_SECTOR_SIZE) {
-		mask = (logical_block_size / MD_SECTOR_SIZE) - 1;
-		D_ASSERT(mask == 1 || mask == 3 || mask == 7);
-		D_ASSERT(logical_block_size == (mask+1) * MD_SECTOR_SIZE);
-		offset = sector & mask;
-		sector = sector & ~mask;
-		iop = mdev->md_io_tmpp;
-
-		if (rw & WRITE) {
-			/* these are GFP_KERNEL pages, pre-allocated
-			 * on device initialization */
-			void *p = page_address(mdev->md_io_page);
-			void *hp = page_address(mdev->md_io_tmpp);
-
-			ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector,
-					READ, logical_block_size);
-
-			if (unlikely(!ok)) {
-				dev_err(DEV, "drbd_md_sync_page_io(,%llus,"
-				    "READ [logical_block_size!=512]) failed!\n",
-				    (unsigned long long)sector);
-				return 0;
-			}
-
-			memcpy(hp + offset*MD_SECTOR_SIZE, p, MD_SECTOR_SIZE);
-		}
-	}
+	dev_dbg(DEV, "meta_data io: %s [%d]:%s(,%llus,%s)\n",
+	     current->comm, current->pid, __func__,
+	     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
 
 	if (sector < drbd_md_first_sector(bdev) ||
-	    sector > drbd_md_last_sector(bdev))
+	    sector + 7 > drbd_md_last_sector(bdev))
 		dev_alert(DEV, "%s [%d]:%s(,%llus,%s) out of range md access!\n",
 		     current->comm, current->pid, __func__,
 		     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
 
-	ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector, rw, logical_block_size);
+	ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector, rw, MD_BLOCK_SIZE);
 	if (unlikely(!ok)) {
 		dev_err(DEV, "drbd_md_sync_page_io(,%llus,%s) failed!\n",
 		    (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
 		return 0;
 	}
 
-	if (logical_block_size != MD_SECTOR_SIZE && !(rw & WRITE)) {
-		void *p = page_address(mdev->md_io_page);
-		void *hp = page_address(mdev->md_io_tmpp);
-
-		memcpy(p, hp + offset*MD_SECTOR_SIZE, MD_SECTOR_SIZE);
-	}
-
 	return ok;
 }
 
@@ -211,20 +217,34 @@ void drbd_al_begin_io(struct drbd_conf *mdev, sector_t sector)
 		 * current->bio_tail list now.
 		 * we have to delegate updates to the activity log
 		 * to the worker thread. */
-		init_completion(&al_work.event);
-		al_work.al_ext = al_ext;
-		al_work.enr = enr;
-		al_work.old_enr = al_ext->lc_number;
-		al_work.w.cb = w_al_write_transaction;
-		al_work.w.mdev = mdev;
-		drbd_queue_work_front(&mdev->tconn->data.work, &al_work.w);
-		wait_for_completion(&al_work.event);
 
-		mdev->al_writ_cnt++;
+		/* Serialize multiple transactions.
+		 * This uses test_and_set_bit, memory barrier is implicit.
+		 * Optimization potential:
+		 * first check for transaction number > old transaction number,
+		 * so not all waiters have to lock/unlock.  */
+		wait_event(mdev->al_wait, lc_try_lock_for_transaction(mdev->act_log));
 
-		spin_lock_irq(&mdev->al_lock);
-		lc_committed(mdev->act_log);
-		spin_unlock_irq(&mdev->al_lock);
+		/* Double check: it may have been committed by someone else,
+		 * while we have been waiting for the lock. */
+		if (al_ext->lc_number != enr) {
+			init_completion(&al_work.event);
+			al_work.w.cb = w_al_write_transaction;
+			al_work.w.mdev = mdev;
+			drbd_queue_work_front(&mdev->tconn->data.work, &al_work.w);
+			wait_for_completion(&al_work.event);
+
+			mdev->al_writ_cnt++;
+
+			spin_lock_irq(&mdev->al_lock);
+			/* FIXME
+			if (al_work.err)
+				we need an "lc_cancel" here;
+			*/
+			lc_committed(mdev->act_log);
+			spin_unlock_irq(&mdev->al_lock);
+		}
+		lc_unlock(mdev->act_log);
 		wake_up(&mdev->al_wait);
 	}
 }
@@ -283,95 +303,118 @@ w_al_write_transaction(struct drbd_work *w, int unused)
 {
 	struct update_al_work *aw = container_of(w, struct update_al_work, w);
 	struct drbd_conf *mdev = w->mdev;
-	struct lc_element *updated = aw->al_ext;
-	const unsigned int new_enr = aw->enr;
-	const unsigned int evicted = aw->old_enr;
-	struct al_transaction *buffer;
+	struct al_transaction_on_disk *buffer;
+	struct lc_element *e;
 	sector_t sector;
-	int i, n, mx;
-	unsigned int extent_nr;
-	u32 xor_sum = 0;
+	int i, mx;
+	unsigned extent_nr;
+	unsigned crc = 0;
 
 	if (!get_ldev(mdev)) {
-		dev_err(DEV,
-			"disk is %s, cannot start al transaction (-%d +%d)\n",
-			drbd_disk_str(mdev->state.disk), evicted, new_enr);
+		dev_err(DEV, "disk is %s, cannot start al transaction\n",
+			drbd_disk_str(mdev->state.disk));
+		aw->err = -EIO;
 		complete(&((struct update_al_work *)w)->event);
 		return 1;
 	}
-	/* do we have to do a bitmap write, first?
-	 * TODO reduce maximum latency:
-	 * submit both bios, then wait for both,
-	 * instead of doing two synchronous sector writes.
-	 * For now, we must not write the transaction,
-	 * if we cannot write out the bitmap of the evicted extent. */
-	if (mdev->state.conn < C_CONNECTED && evicted != LC_FREE)
-		drbd_bm_write_page(mdev, al_extent_to_bm_page(evicted));
 
 	/* The bitmap write may have failed, causing a state change. */
 	if (mdev->state.disk < D_INCONSISTENT) {
 		dev_err(DEV,
-			"disk is %s, cannot write al transaction (-%d +%d)\n",
-			drbd_disk_str(mdev->state.disk), evicted, new_enr);
+			"disk is %s, cannot write al transaction\n",
+			drbd_disk_str(mdev->state.disk));
+		aw->err = -EIO;
 		complete(&((struct update_al_work *)w)->event);
 		put_ldev(mdev);
 		return 1;
 	}
 
 	mutex_lock(&mdev->md_io_mutex); /* protects md_io_buffer, al_tr_cycle, ... */
-	buffer = (struct al_transaction *)page_address(mdev->md_io_page);
+	buffer = page_address(mdev->md_io_page);
 
-	buffer->magic = __constant_cpu_to_be32(DRBD_MAGIC);
+	memset(buffer, 0, sizeof(*buffer));
+	buffer->magic = cpu_to_be32(DRBD_AL_MAGIC);
 	buffer->tr_number = cpu_to_be32(mdev->al_tr_number);
 
-	n = lc_index_of(mdev->act_log, updated);
+	i = 0;
+
+	/* Even though no one can start to change this list
+	 * once we set the LC_LOCKED -- from drbd_al_begin_io(),
+	 * lc_try_lock_for_transaction() --, someone may still
+	 * be in the process of changing it. */
+	spin_lock_irq(&mdev->al_lock);
+	list_for_each_entry(e, &mdev->act_log->to_be_changed, list) {
+		if (i == AL_UPDATES_PER_TRANSACTION) {
+			i++;
+			break;
+		}
+		buffer->update_slot_nr[i] = cpu_to_be16(e->lc_index);
+		buffer->update_extent_nr[i] = cpu_to_be32(e->lc_new_number);
+		if (e->lc_number != LC_FREE)
+			drbd_bm_mark_for_writeout(mdev,
+					al_extent_to_bm_page(e->lc_number));
+		i++;
+	}
+	spin_unlock_irq(&mdev->al_lock);
+	BUG_ON(i > AL_UPDATES_PER_TRANSACTION);
 
-	buffer->updates[0].pos = cpu_to_be32(n);
-	buffer->updates[0].extent = cpu_to_be32(new_enr);
+	buffer->n_updates = cpu_to_be16(i);
+	for ( ; i < AL_UPDATES_PER_TRANSACTION; i++) {
+		buffer->update_slot_nr[i] = cpu_to_be16(-1);
+		buffer->update_extent_nr[i] = cpu_to_be32(LC_FREE);
+	}
 
-	xor_sum ^= new_enr;
+	buffer->context_size = cpu_to_be16(mdev->act_log->nr_elements);
+	buffer->context_start_slot_nr = cpu_to_be16(mdev->al_tr_cycle);
 
-	mx = min_t(int, AL_EXTENTS_PT,
+	mx = min_t(int, AL_CONTEXT_PER_TRANSACTION,
 		   mdev->act_log->nr_elements - mdev->al_tr_cycle);
 	for (i = 0; i < mx; i++) {
 		unsigned idx = mdev->al_tr_cycle + i;
 		extent_nr = lc_element_by_index(mdev->act_log, idx)->lc_number;
-		buffer->updates[i+1].pos = cpu_to_be32(idx);
-		buffer->updates[i+1].extent = cpu_to_be32(extent_nr);
-		xor_sum ^= extent_nr;
+		buffer->context[i] = cpu_to_be32(extent_nr);
 	}
-	for (; i < AL_EXTENTS_PT; i++) {
-		buffer->updates[i+1].pos = __constant_cpu_to_be32(-1);
-		buffer->updates[i+1].extent = __constant_cpu_to_be32(LC_FREE);
-		xor_sum ^= LC_FREE;
-	}
-	mdev->al_tr_cycle += AL_EXTENTS_PT;
+	for (; i < AL_CONTEXT_PER_TRANSACTION; i++)
+		buffer->context[i] = cpu_to_be32(LC_FREE);
+
+	mdev->al_tr_cycle += AL_CONTEXT_PER_TRANSACTION;
 	if (mdev->al_tr_cycle >= mdev->act_log->nr_elements)
 		mdev->al_tr_cycle = 0;
 
-	buffer->xor_sum = cpu_to_be32(xor_sum);
-
 	sector =  mdev->ldev->md.md_offset
-		+ mdev->ldev->md.al_offset + mdev->al_tr_pos;
-
-	if (!drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE))
-		drbd_chk_io_error(mdev, 1, true);
+		+ mdev->ldev->md.al_offset
+		+ mdev->al_tr_pos * (MD_BLOCK_SIZE>>9);
 
-	if (++mdev->al_tr_pos >
-	    div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT))
-		mdev->al_tr_pos = 0;
+	crc = crc32c(0, buffer, 4096);
+	buffer->crc32c = cpu_to_be32(crc);
 
-	D_ASSERT(mdev->al_tr_pos < MD_AL_MAX_SIZE);
-	mdev->al_tr_number++;
+	if (drbd_bm_write_hinted(mdev))
+		aw->err = -EIO;
+		/* drbd_chk_io_error done already */
+	else if (!drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) {
+		aw->err = -EIO;
+		drbd_chk_io_error(mdev, 1, true);
+	} else {
+		/* advance ringbuffer position and transaction counter */
+		mdev->al_tr_pos = (mdev->al_tr_pos + 1) % (MD_AL_SECTORS*512/MD_BLOCK_SIZE);
+		mdev->al_tr_number++;
+	}
 
 	mutex_unlock(&mdev->md_io_mutex);
-
 	complete(&((struct update_al_work *)w)->event);
 	put_ldev(mdev);
 
 	return 1;
 }
 
+/* FIXME
+ * reading of the activity log,
+ * and potentially dirtying of the affected bitmap regions,
+ * should be done from userland only.
+ * DRBD would simply always attach with an empty activity log,
+ * and refuse to attach to something that looks like a crashed primary.
+ */
+
 /**
  * drbd_al_read_tr() - Read a single transaction from the on disk activity log
  * @mdev:	DRBD device.
@@ -383,27 +426,39 @@ w_al_write_transaction(struct drbd_work *w, int unused)
  */
 static int drbd_al_read_tr(struct drbd_conf *mdev,
 			   struct drbd_backing_dev *bdev,
-			   struct al_transaction *b,
 			   int index)
 {
+	struct al_transaction_on_disk *b = page_address(mdev->md_io_page);
 	sector_t sector;
-	int rv, i;
-	u32 xor_sum = 0;
+	u32 crc;
 
-	sector = bdev->md.md_offset + bdev->md.al_offset + index;
+	sector =  bdev->md.md_offset
+		+ bdev->md.al_offset
+		+ index * (MD_BLOCK_SIZE>>9);
 
 	/* Dont process error normally,
 	 * as this is done before disk is attached! */
 	if (!drbd_md_sync_page_io(mdev, bdev, sector, READ))
 		return -1;
 
-	rv = (b->magic == cpu_to_be32(DRBD_MAGIC));
+	if (!expect(b->magic == cpu_to_be32(DRBD_AL_MAGIC)))
+		return 0;
+
+	if (!expect(be16_to_cpu(b->n_updates) <= AL_UPDATES_PER_TRANSACTION))
+		return 0;
 
-	for (i = 0; i < AL_EXTENTS_PT + 1; i++)
-		xor_sum ^= be32_to_cpu(b->updates[i].extent);
-	rv &= (xor_sum == be32_to_cpu(b->xor_sum));
+	if (!expect(be16_to_cpu(b->context_size) <= DRBD_AL_EXTENTS_MAX))
+		return 0;
 
-	return rv;
+	if (!expect(be16_to_cpu(b->context_start_slot_nr) < DRBD_AL_EXTENTS_MAX))
+		return 0;
+
+	crc = be32_to_cpu(b->crc32c);
+	b->crc32c = 0;
+	if (!expect(crc == crc32c(0, b, 4096)))
+		return 0;
+
+	return 1;
 }
 
 /**
@@ -415,7 +470,7 @@ static int drbd_al_read_tr(struct drbd_conf *mdev,
  */
 int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 {
-	struct al_transaction *buffer;
+	struct al_transaction_on_disk *b;
 	int i;
 	int rv;
 	int mx;
@@ -428,25 +483,36 @@ int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 	u32 to_tnr = 0;
 	u32 cnr;
 
-	mx = div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT);
+	/* Note that this is expected to be called with a newly created,
+	 * clean and all unused activity log of the "expected size".
+	 */
 
 	/* lock out all other meta data io for now,
 	 * and make sure the page is mapped.
 	 */
 	mutex_lock(&mdev->md_io_mutex);
-	buffer = page_address(mdev->md_io_page);
+	b = page_address(mdev->md_io_page);
+
+	/* Always use the full ringbuffer space for now.
+	 * possible optimization: read in all of it,
+	 * then scan the in-memory pages. */
+
+	mx = (MD_AL_SECTORS*512/MD_BLOCK_SIZE);
 
 	/* Find the valid transaction in the log */
-	for (i = 0; i <= mx; i++) {
-		rv = drbd_al_read_tr(mdev, bdev, buffer, i);
+	for (i = 0; i < mx; i++) {
+		rv = drbd_al_read_tr(mdev, bdev, i);
+		/* invalid data in that block */
 		if (rv == 0)
 			continue;
+
+		/* IO error */
 		if (rv == -1) {
 			mutex_unlock(&mdev->md_io_mutex);
 			return 0;
 		}
-		cnr = be32_to_cpu(buffer->tr_number);
 
+		cnr = be32_to_cpu(b->tr_number);
 		if (++found_valid == 1) {
 			from = i;
 			to = i;
@@ -454,8 +520,11 @@ int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 			to_tnr = cnr;
 			continue;
 		}
+
+		D_ASSERT(cnr != to_tnr);
+		D_ASSERT(cnr != from_tnr);
 		if ((int)cnr - (int)from_tnr < 0) {
-			D_ASSERT(from_tnr - cnr + i - from == mx+1);
+			D_ASSERT(from_tnr - cnr + i - from == mx);
 			from = i;
 			from_tnr = cnr;
 		}
@@ -476,11 +545,10 @@ int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 	 * dev_info(DEV, "Reading from %d to %d.\n",from,to); */
 	i = from;
 	while (1) {
-		int j, pos;
-		unsigned int extent_nr;
-		unsigned int trn;
+		struct lc_element *e;
+		unsigned j, n, slot, extent_nr;
 
-		rv = drbd_al_read_tr(mdev, bdev, buffer, i);
+		rv = drbd_al_read_tr(mdev, bdev, i);
 		if (!expect(rv != 0))
 			goto cancel;
 		if (rv == -1) {
@@ -488,23 +556,55 @@ int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 			return 0;
 		}
 
-		trn = be32_to_cpu(buffer->tr_number);
+		/* deal with different transaction types.
+		 * not yet implemented */
+		if (!expect(b->transaction_type == 0))
+			goto cancel;
 
-		spin_lock_irq(&mdev->al_lock);
+		/* on the fly re-create/resize activity log?
+		 * will be a special transaction type flag. */
+		if (!expect(be16_to_cpu(b->context_size) == mdev->act_log->nr_elements))
+			goto cancel;
+		if (!expect(be16_to_cpu(b->context_start_slot_nr) < mdev->act_log->nr_elements))
+			goto cancel;
 
-		/* This loop runs backwards because in the cyclic
-		   elements there might be an old version of the
-		   updated element (in slot 0). So the element in slot 0
-		   can overwrite old versions. */
-		for (j = AL_EXTENTS_PT; j >= 0; j--) {
-			pos = be32_to_cpu(buffer->updates[j].pos);
-			extent_nr = be32_to_cpu(buffer->updates[j].extent);
+		/* We are the only user of the activity log right now,
+		 * don't actually need to take that lock. */
+		spin_lock_irq(&mdev->al_lock);
 
-			if (extent_nr == LC_FREE)
-				continue;
+		/* first, apply the context, ... */
+		for (j = 0, slot = be16_to_cpu(b->context_start_slot_nr);
+		     j < AL_CONTEXT_PER_TRANSACTION &&
+		     slot < mdev->act_log->nr_elements; j++, slot++) {
+			extent_nr = be32_to_cpu(b->context[j]);
+			e = lc_element_by_index(mdev->act_log, slot);
+			if (e->lc_number != extent_nr) {
+				if (extent_nr != LC_FREE)
+					active_extents++;
+				else
+					active_extents--;
+			}
+			lc_set(mdev->act_log, extent_nr, slot);
+		}
 
-			lc_set(mdev->act_log, extent_nr, pos);
-			active_extents++;
+		/* ... then apply the updates,
+		 * which override the context information.
+		 * drbd_al_read_tr already did the rangecheck
+		 * on n <= AL_UPDATES_PER_TRANSACTION */
+		n = be16_to_cpu(b->n_updates);
+		for (j = 0; j < n; j++) {
+			slot = be16_to_cpu(b->update_slot_nr[j]);
+			extent_nr = be32_to_cpu(b->update_extent_nr[j]);
+			if (!expect(slot < mdev->act_log->nr_elements))
+				break;
+			e = lc_element_by_index(mdev->act_log, slot);
+			if (e->lc_number != extent_nr) {
+				if (extent_nr != LC_FREE)
+					active_extents++;
+				else
+					active_extents--;
+			}
+			lc_set(mdev->act_log, extent_nr, slot);
 		}
 		spin_unlock_irq(&mdev->al_lock);
 
@@ -514,15 +614,12 @@ cancel:
 		if (i == to)
 			break;
 		i++;
-		if (i > mx)
+		if (i >= mx)
 			i = 0;
 	}
 
 	mdev->al_tr_number = to_tnr+1;
-	mdev->al_tr_pos = to;
-	if (++mdev->al_tr_pos >
-	    div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT))
-		mdev->al_tr_pos = 0;
+	mdev->al_tr_pos = (to + 1) % (MD_AL_SECTORS*512/MD_BLOCK_SIZE);
 
 	/* ok, we are done with it */
 	mutex_unlock(&mdev->md_io_mutex);
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index edfdeb62c18f..3213808a898a 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1069,7 +1069,6 @@ struct drbd_conf {
 	atomic_t pp_in_use_by_net;	/* sendpage()d, still referenced by tcp */
 	wait_queue_head_t ee_wait;
 	struct page *md_io_page;	/* one page buffer for md_io */
-	struct page *md_io_tmpp;	/* for logical_block_size != 512 */
 	struct mutex md_io_mutex;	/* protects the md_io_buffer */
 	spinlock_t al_lock;
 	wait_queue_head_t al_wait;
@@ -1259,22 +1258,39 @@ extern void drbd_ldev_destroy(struct drbd_conf *mdev);
    * either at the end of the backing device
    * or on a separate meta data device. */
 
-#define MD_RESERVED_SECT (128LU << 11)  /* 128 MB, unit sectors */
 /* The following numbers are sectors */
-#define MD_AL_OFFSET 8	    /* 8 Sectors after start of meta area */
-#define MD_AL_MAX_SIZE 64   /* = 32 kb LOG  ~ 3776 extents ~ 14 GB Storage */
-/* Allows up to about 3.8TB */
-#define MD_BM_OFFSET (MD_AL_OFFSET + MD_AL_MAX_SIZE)
-
-/* Since the smalles IO unit is usually 512 byte */
-#define MD_SECTOR_SHIFT	 9
-#define MD_SECTOR_SIZE	 (1<<MD_SECTOR_SHIFT)
-
-/* activity log */
-#define AL_EXTENTS_PT ((MD_SECTOR_SIZE-12)/8-1) /* 61 ; Extents per 512B sector */
-#define AL_EXTENT_SHIFT 22		 /* One extent represents 4M Storage */
+/* Allows up to about 3.8TB, so if you want more,
+ * you need to use the "flexible" meta data format. */
+#define MD_RESERVED_SECT (128LU << 11)  /* 128 MB, unit sectors */
+#define MD_AL_OFFSET	8    /* 8 Sectors after start of meta area */
+#define MD_AL_SECTORS	64   /* = 32 kB on disk activity log ring buffer */
+#define MD_BM_OFFSET (MD_AL_OFFSET + MD_AL_SECTORS)
+
+/* we do all meta data IO in 4k blocks */
+#define MD_BLOCK_SHIFT	12
+#define MD_BLOCK_SIZE	(1<<MD_BLOCK_SHIFT)
+
+/* One activity log extent represents 4M of storage */
+#define AL_EXTENT_SHIFT 22
 #define AL_EXTENT_SIZE (1<<AL_EXTENT_SHIFT)
 
+/* We could make these currently hardcoded constants configurable
+ * variables at create-md time (or even re-configurable at runtime?).
+ * Which will require some more changes to the DRBD "super block"
+ * and attach code.
+ *
+ * updates per transaction:
+ *   This many changes to the active set can be logged with one transaction.
+ *   This number is arbitrary.
+ * context per transaction:
+ *   This many context extent numbers are logged with each transaction.
+ *   This number is resulting from the transaction block size (4k), the layout
+ *   of the transaction header, and the number of updates per transaction.
+ *   See drbd_actlog.c:struct al_transaction_on_disk
+ * */
+#define AL_UPDATES_PER_TRANSACTION	 64	// arbitrary
+#define AL_CONTEXT_PER_TRANSACTION	919	// (4096 - 36 - 6*64)/4
+
 #if BITS_PER_LONG == 32
 #define LN2_BPL 5
 #define cpu_to_lel(A) cpu_to_le32(A)
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index c77e51a40926..efedfbc06198 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2841,10 +2841,6 @@ void drbd_ldev_destroy(struct drbd_conf *mdev)
 		drbd_free_bc(mdev->ldev);
 		mdev->ldev = NULL;);
 
-	if (mdev->md_io_tmpp) {
-		__free_page(mdev->md_io_tmpp);
-		mdev->md_io_tmpp = NULL;
-	}
 	clear_bit(GO_DISKLESS, &mdev->flags);
 }
 
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 0a92f5226c2a..90d731723205 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -527,7 +527,7 @@ static void drbd_md_set_sector_offsets(struct drbd_conf *mdev,
 	case DRBD_MD_INDEX_FLEX_INT:
 		bdev->md.md_offset = drbd_md_ss__(mdev, bdev);
 		/* al size is still fixed */
-		bdev->md.al_offset = -MD_AL_MAX_SIZE;
+		bdev->md.al_offset = -MD_AL_SECTORS;
 		/* we need (slightly less than) ~ this much bitmap sectors: */
 		md_size_sect = drbd_get_capacity(bdev->backing_bdev);
 		md_size_sect = ALIGN(md_size_sect, BM_SECT_PER_EXT);
@@ -751,8 +751,8 @@ static int drbd_check_al_size(struct drbd_conf *mdev)
 	unsigned int in_use;
 	int i;
 
-	if (!expect(mdev->sync_conf.al_extents >= 7))
-		mdev->sync_conf.al_extents = 127;
+	if (!expect(mdev->sync_conf.al_extents >= DRBD_AL_EXTENTS_MIN))
+		mdev->sync_conf.al_extents = DRBD_AL_EXTENTS_MIN;
 
 	if (mdev->act_log &&
 	    mdev->act_log->nr_elements == mdev->sync_conf.al_extents)
@@ -760,7 +760,7 @@ static int drbd_check_al_size(struct drbd_conf *mdev)
 
 	in_use = 0;
 	t = mdev->act_log;
-	n = lc_create("act_log", drbd_al_ext_cache, 1,
+	n = lc_create("act_log", drbd_al_ext_cache, AL_UPDATES_PER_TRANSACTION,
 		mdev->sync_conf.al_extents, sizeof(struct lc_element), 0);
 
 	if (n == NULL) {
@@ -932,7 +932,6 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	union drbd_state ns, os;
 	enum drbd_state_rv rv;
 	int cp_discovered = 0;
-	int logical_block_size;
 
 	drbd_reconfig_start(mdev);
 
@@ -1087,25 +1086,6 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 
 	drbd_md_set_sector_offsets(mdev, nbc);
 
-	/* allocate a second IO page if logical_block_size != 512 */
-	logical_block_size = bdev_logical_block_size(nbc->md_bdev);
-	if (logical_block_size == 0)
-		logical_block_size = MD_SECTOR_SIZE;
-
-	if (logical_block_size != MD_SECTOR_SIZE) {
-		if (!mdev->md_io_tmpp) {
-			struct page *page = alloc_page(GFP_NOIO);
-			if (!page)
-				goto force_diskless_dec;
-
-			dev_warn(DEV, "Meta data's bdev logical_block_size = %d != %d\n",
-			     logical_block_size, MD_SECTOR_SIZE);
-			dev_warn(DEV, "Workaround engaged (has performance impact).\n");
-
-			mdev->md_io_tmpp = page;
-		}
-	}
-
 	if (!mdev->bitmap) {
 		if (drbd_bm_init(mdev)) {
 			retcode = ERR_NOMEM;
@@ -1804,14 +1784,12 @@ static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *n
 
 	if (!expect(sc.rate >= 1))
 		sc.rate = 1;
-	if (!expect(sc.al_extents >= 7))
-		sc.al_extents = 127; /* arbitrary minimum */
-#define AL_MAX ((MD_AL_MAX_SIZE-1) * AL_EXTENTS_PT)
-	if (sc.al_extents > AL_MAX) {
-		dev_err(DEV, "sc.al_extents > %d\n", AL_MAX);
-		sc.al_extents = AL_MAX;
-	}
-#undef AL_MAX
+
+	/* clip to allowed range */
+	if (!expect(sc.al_extents >= DRBD_AL_EXTENTS_MIN))
+		sc.al_extents = DRBD_AL_EXTENTS_MIN;
+	if (!expect(sc.al_extents <= DRBD_AL_EXTENTS_MAX))
+		sc.al_extents = DRBD_AL_EXTENTS_MAX;
 
 	/* to avoid spurious errors when configuring minors before configuring
 	 * the minors they depend on: if necessary, first create the minor we
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 35fc08a0a552..70a688b92c1b 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -336,6 +336,10 @@ enum drbd_timeout_flag {
 #define DRBD_MAGIC 0x83740267
 #define DRBD_MAGIC_BIG 0x835a
 
+/* how I came up with this magic?
+ * base64 decode "actlog==" ;) */
+#define DRBD_AL_MAGIC 0x69cb65a2
+
 /* these are of type "int" */
 #define DRBD_MD_INDEX_INTERNAL -1
 #define DRBD_MD_INDEX_FLEX_EXT -2
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 447c36752385..75f05af33725 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -102,10 +102,12 @@
 #define DRBD_RATE_DEF 250  /* kb/second */
 
   /* less than 7 would hit performance unnecessarily.
-   * 3833 is the largest prime that still does fit
-   * into 64 sectors of activity log */
+   * 919 slots context information per transaction,
+   * 32k activity log, 4k transaction size,
+   * one transaction in flight:
+   * 919 * 7 = 6433 */
 #define DRBD_AL_EXTENTS_MIN  7
-#define DRBD_AL_EXTENTS_MAX  3833
+#define DRBD_AL_EXTENTS_MAX  6433
 #define DRBD_AL_EXTENTS_DEF  127
 
 #define DRBD_AFTER_MIN  -1
-- 
cgit v1.2.3-55-g7522


From 1aba4d7fcfabe999e0c99683b394aa76d5c42842 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Mon, 21 Feb 2011 15:38:08 +0100
Subject: drbd: Preparing the connector interface to operator on connections

Up to now it only operated on minor numbers. Now it can work also
on named connections.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h  |  1 +
 drivers/block/drbd/drbd_main.c | 15 +++++++
 drivers/block/drbd/drbd_nl.c   | 96 +++++++++++++++++++++++++++---------------
 include/linux/drbd.h           | 19 +++++++--
 4 files changed, 94 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 48367e53a7a5..033af1995867 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1479,6 +1479,7 @@ extern void drbd_free_mdev(struct drbd_conf *mdev);
 
 struct drbd_tconn *drbd_new_tconn(char *name);
 extern void drbd_free_tconn(struct drbd_tconn *tconn);
+struct drbd_tconn *conn_by_name(const char *name);
 
 extern int proc_details;
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index cbec5ff2cc74..4761426f9ad7 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2196,6 +2196,21 @@ static void drbd_init_workqueue(struct drbd_work_queue* wq)
 	INIT_LIST_HEAD(&wq->q);
 }
 
+struct drbd_tconn *conn_by_name(const char *name)
+{
+	struct drbd_tconn *tconn;
+
+	write_lock_irq(&global_state_lock);
+	list_for_each_entry(tconn, &drbd_tconns, all_tconn) {
+		if (!strcmp(tconn->name, name))
+			goto found;
+	}
+	tconn = NULL;
+found:
+	write_unlock_irq(&global_state_lock);
+	return tconn;
+}
+
 struct drbd_tconn *drbd_new_tconn(char *name)
 {
 	struct drbd_tconn *tconn;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index b141f891f643..27a43d138f6b 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2184,42 +2184,57 @@ out:
 	return 0;
 }
 
+enum cn_handler_type {
+	CHT_MINOR,
+	CHT_CONN,
+	CHT_CTOR,
+	/* CHT_RES, later */
+};
+
 struct cn_handler_struct {
-	int (*function)(struct drbd_conf *,
-			 struct drbd_nl_cfg_req *,
-			 struct drbd_nl_cfg_reply *);
+	enum cn_handler_type type;
+	union {
+		int (*minor_based)(struct drbd_conf *,
+				   struct drbd_nl_cfg_req *,
+				   struct drbd_nl_cfg_reply *);
+		int (*conn_based)(struct drbd_tconn *,
+				  struct drbd_nl_cfg_req *,
+				  struct drbd_nl_cfg_reply *);
+		int (*constructor)(struct drbd_nl_cfg_req *,
+				   struct drbd_nl_cfg_reply *);
+	};
 	int reply_body_size;
 };
 
 static struct cn_handler_struct cnd_table[] = {
-	[ P_primary ]		= { &drbd_nl_primary,		0 },
-	[ P_secondary ]		= { &drbd_nl_secondary,		0 },
-	[ P_disk_conf ]		= { &drbd_nl_disk_conf,		0 },
-	[ P_detach ]		= { &drbd_nl_detach,		0 },
-	[ P_net_conf ]		= { &drbd_nl_net_conf,		0 },
-	[ P_disconnect ]	= { &drbd_nl_disconnect,	0 },
-	[ P_resize ]		= { &drbd_nl_resize,		0 },
-	[ P_syncer_conf ]	= { &drbd_nl_syncer_conf,	0 },
-	[ P_invalidate ]	= { &drbd_nl_invalidate,	0 },
-	[ P_invalidate_peer ]	= { &drbd_nl_invalidate_peer,	0 },
-	[ P_pause_sync ]	= { &drbd_nl_pause_sync,	0 },
-	[ P_resume_sync ]	= { &drbd_nl_resume_sync,	0 },
-	[ P_suspend_io ]	= { &drbd_nl_suspend_io,	0 },
-	[ P_resume_io ]		= { &drbd_nl_resume_io,		0 },
-	[ P_outdate ]		= { &drbd_nl_outdate,		0 },
-	[ P_get_config ]	= { &drbd_nl_get_config,
+	[ P_primary ]		= { CHT_MINOR, { &drbd_nl_primary },	0 },
+	[ P_secondary ]		= { CHT_MINOR, { &drbd_nl_secondary },	0 },
+	[ P_disk_conf ]		= { CHT_MINOR, { &drbd_nl_disk_conf },	0 },
+	[ P_detach ]		= { CHT_MINOR, { &drbd_nl_detach },	0 },
+	[ P_net_conf ]		= { CHT_MINOR, { &drbd_nl_net_conf },	0 },
+	[ P_disconnect ]	= { CHT_MINOR, { &drbd_nl_disconnect },	0 },
+	[ P_resize ]		= { CHT_MINOR, { &drbd_nl_resize },	0 },
+	[ P_syncer_conf ]	= { CHT_MINOR, { &drbd_nl_syncer_conf },0 },
+	[ P_invalidate ]	= { CHT_MINOR, { &drbd_nl_invalidate },	0 },
+	[ P_invalidate_peer ]	= { CHT_MINOR, { &drbd_nl_invalidate_peer },0 },
+	[ P_pause_sync ]	= { CHT_MINOR, { &drbd_nl_pause_sync },	0 },
+	[ P_resume_sync ]	= { CHT_MINOR, { &drbd_nl_resume_sync },0 },
+	[ P_suspend_io ]	= { CHT_MINOR, { &drbd_nl_suspend_io },	0 },
+	[ P_resume_io ]		= { CHT_MINOR, { &drbd_nl_resume_io },	0 },
+	[ P_outdate ]		= { CHT_MINOR, { &drbd_nl_outdate },	0 },
+	[ P_get_config ]	= { CHT_MINOR, { &drbd_nl_get_config },
 				    sizeof(struct syncer_conf_tag_len_struct) +
 				    sizeof(struct disk_conf_tag_len_struct) +
 				    sizeof(struct net_conf_tag_len_struct) },
-	[ P_get_state ]		= { &drbd_nl_get_state,
+	[ P_get_state ]		= { CHT_MINOR, { &drbd_nl_get_state },
 				    sizeof(struct get_state_tag_len_struct) +
 				    sizeof(struct sync_progress_tag_len_struct)	},
-	[ P_get_uuids ]		= { &drbd_nl_get_uuids,
+	[ P_get_uuids ]		= { CHT_MINOR, { &drbd_nl_get_uuids },
 				    sizeof(struct get_uuids_tag_len_struct) },
-	[ P_get_timeout_flag ]	= { &drbd_nl_get_timeout_flag,
+	[ P_get_timeout_flag ]	= { CHT_MINOR, { &drbd_nl_get_timeout_flag },
 				    sizeof(struct get_timeout_flag_tag_len_struct)},
-	[ P_start_ov ]		= { &drbd_nl_start_ov,		0 },
-	[ P_new_c_uuid ]	= { &drbd_nl_new_c_uuid,	0 },
+	[ P_start_ov ]		= { CHT_MINOR, { &drbd_nl_start_ov },	0 },
+	[ P_new_c_uuid ]	= { CHT_MINOR, { &drbd_nl_new_c_uuid },	0 },
 };
 
 static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms *nsp)
@@ -2229,6 +2244,7 @@ static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms
 	struct cn_msg *cn_reply;
 	struct drbd_nl_cfg_reply *reply;
 	struct drbd_conf *mdev;
+	struct drbd_tconn *tconn;
 	int retcode, rr;
 	int reply_size = sizeof(struct cn_msg)
 		+ sizeof(struct drbd_nl_cfg_reply)
@@ -2244,13 +2260,6 @@ static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms
 		goto fail;
 	}
 
-	mdev = ensure_mdev(nlp->drbd_minor,
-			(nlp->flags & DRBD_NL_CREATE_DEVICE));
-	if (!mdev) {
-		retcode = ERR_MINOR_INVALID;
-		goto fail;
-	}
-
 	if (nlp->packet_type >= P_nl_after_last_packet ||
 	    nlp->packet_type == P_return_code_only) {
 		retcode = ERR_PACKET_NR;
@@ -2260,7 +2269,7 @@ static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms
 	cm = cnd_table + nlp->packet_type;
 
 	/* This may happen if packet number is 0: */
-	if (cm->function == NULL) {
+	if (cm->minor_based == NULL) {
 		retcode = ERR_PACKET_NR;
 		goto fail;
 	}
@@ -2281,7 +2290,28 @@ static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms
 	reply->ret_code = NO_ERROR; /* Might by modified by cm->function. */
 	/* reply->tag_list; might be modified by cm->function. */
 
-	rr = cm->function(mdev, nlp, reply);
+	retcode = ERR_MINOR_INVALID;
+	rr = 0;
+	switch (cm->type) {
+	case CHT_MINOR:
+		mdev = minor_to_mdev(nlp->drbd_minor);
+		if (!mdev)
+			goto fail;
+		rr = cm->minor_based(mdev, nlp, reply);
+		break;
+	case CHT_CONN:
+		tconn = conn_by_name(nlp->obj_name);
+		if (!tconn) {
+			retcode = ERR_CONN_NOT_KNOWN;
+			goto fail;
+		}
+		rr = cm->conn_based(tconn, nlp, reply);
+		break;
+	case CHT_CTOR:
+		rr = cm->constructor(nlp, reply);
+		break;
+	/* case CHT_RES: */
+	}
 
 	cn_reply->id = req->id;
 	cn_reply->seq = req->seq;
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 70a688b92c1b..7683b4ab6583 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -155,6 +155,7 @@ enum drbd_ret_code {
 	ERR_CONG_NOT_PROTO_A	= 155,
 	ERR_PIC_AFTER_DEP	= 156,
 	ERR_PIC_PEER_DEP	= 157,
+	ERR_CONN_NOT_KNOWN      = 158,
 
 	/* insert new ones above this line */
 	AFTER_LAST_ERR_CODE
@@ -347,8 +348,11 @@ enum drbd_timeout_flag {
 
 /* Start of the new netlink/connector stuff */
 
-#define DRBD_NL_CREATE_DEVICE 0x01
-#define DRBD_NL_SET_DEFAULTS  0x02
+enum drbd_ncr_flags {
+	DRBD_NL_CREATE_DEVICE = 0x01,
+	DRBD_NL_SET_DEFAULTS =  0x02,
+};
+#define DRBD_NL_OBJ_NAME_LEN 32
 
 
 /* For searching a vacant cn_idx value */
@@ -356,8 +360,15 @@ enum drbd_timeout_flag {
 
 struct drbd_nl_cfg_req {
 	int packet_type;
-	unsigned int drbd_minor;
-	int flags;
+	union {
+		struct {
+			unsigned int drbd_minor;
+			enum drbd_ncr_flags flags;
+		};
+		struct {
+			char obj_name[DRBD_NL_OBJ_NAME_LEN];
+		};
+	};
 	unsigned short tag_list[];
 };
 
-- 
cgit v1.2.3-55-g7522


From 774b305518a68a50df4f479bcf79da2add724e6e Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Tue, 22 Feb 2011 02:07:03 -0500
Subject: drbd: Implemented new commands to create/delete connections/minors

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h  |   4 +-
 drivers/block/drbd/drbd_main.c |  68 ++++++++++++++------------
 drivers/block/drbd/drbd_nl.c   | 106 +++++++++++++++++++++++++----------------
 include/linux/drbd.h           |   3 ++
 include/linux/drbd_nl.h        |  12 +++++
 5 files changed, 120 insertions(+), 73 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index a27e2a4e038d..535d503886d8 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1258,7 +1258,6 @@ extern int drbd_bmio_clear_n_write(struct drbd_conf *mdev);
 extern void drbd_go_diskless(struct drbd_conf *mdev);
 extern void drbd_ldev_destroy(struct drbd_conf *mdev);
 
-
 /* Meta data layout
    We reserve a 128MB Block (4k aligned)
    * either at the end of the backing device
@@ -1476,8 +1475,9 @@ extern wait_queue_head_t drbd_pp_wait;
 extern rwlock_t global_state_lock;
 
 extern int conn_lowest_minor(struct drbd_tconn *tconn);
-extern struct drbd_conf *drbd_new_device(unsigned int minor);
+enum drbd_ret_code conn_new_minor(struct drbd_tconn *tconn, unsigned int minor, int vnr);
 extern void drbd_free_mdev(struct drbd_conf *mdev);
+extern void drbd_delete_device(unsigned int minor);
 
 struct drbd_tconn *drbd_new_tconn(char *name);
 extern void drbd_free_tconn(struct drbd_tconn *tconn);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 2bfd63058f40..ec7d0d98657c 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -614,13 +614,16 @@ char *drbd_task_to_thread_name(struct drbd_tconn *tconn, struct task_struct *tas
 	return thi ? thi->name : task->comm;
 }
 
-#ifdef CONFIG_SMP
 int conn_lowest_minor(struct drbd_tconn *tconn)
 {
 	int minor = 0;
-	idr_get_next(&tconn->volumes, &minor);
+
+	if (!idr_get_next(&tconn->volumes, &minor))
+		return -1;
 	return minor;
 }
+
+#ifdef CONFIG_SMP
 /**
  * drbd_calc_cpu_mask() - Generate CPU masks, spread over all CPUs
  * @mdev:	DRBD device.
@@ -2078,15 +2081,16 @@ static void drbd_release_ee_lists(struct drbd_conf *mdev)
 		dev_err(DEV, "%d EEs in net list found!\n", rr);
 }
 
-/* caution. no locking.
- * currently only used from module cleanup code. */
-static void drbd_delete_device(unsigned int minor)
+/* caution. no locking. */
+void drbd_delete_device(unsigned int minor)
 {
 	struct drbd_conf *mdev = minor_to_mdev(minor);
 
 	if (!mdev)
 		return;
 
+	idr_remove(&mdev->tconn->volumes, minor);
+
 	/* paranoia asserts */
 	D_ASSERT(mdev->open_cnt == 0);
 	D_ASSERT(list_empty(&mdev->tconn->data.work.q));
@@ -2101,7 +2105,6 @@ static void drbd_delete_device(unsigned int minor)
 		bdput(mdev->this_bdev);
 
 	drbd_free_resources(mdev);
-	drbd_free_tconn(mdev->tconn);
 
 	drbd_release_ee_lists(mdev);
 
@@ -2223,6 +2226,9 @@ struct drbd_tconn *drbd_new_tconn(char *name)
 	if (!tconn->name)
 		goto fail;
 
+	if (!zalloc_cpumask_var(&tconn->cpu_mask, GFP_KERNEL))
+		goto fail;
+
 	if (!tl_init(tconn))
 		goto fail;
 
@@ -2252,6 +2258,7 @@ struct drbd_tconn *drbd_new_tconn(char *name)
 
 fail:
 	tl_cleanup(tconn);
+	free_cpumask_var(tconn->cpu_mask);
 	kfree(tconn->name);
 	kfree(tconn);
 
@@ -2265,6 +2272,7 @@ void drbd_free_tconn(struct drbd_tconn *tconn)
 	write_unlock_irq(&global_state_lock);
 	idr_destroy(&tconn->volumes);
 
+	free_cpumask_var(tconn->cpu_mask);
 	kfree(tconn->name);
 	kfree(tconn->int_dig_out);
 	kfree(tconn->int_dig_in);
@@ -2272,32 +2280,31 @@ void drbd_free_tconn(struct drbd_tconn *tconn)
 	kfree(tconn);
 }
 
-struct drbd_conf *drbd_new_device(unsigned int minor)
+enum drbd_ret_code conn_new_minor(struct drbd_tconn *tconn, unsigned int minor, int vnr)
 {
 	struct drbd_conf *mdev;
 	struct gendisk *disk;
 	struct request_queue *q;
-	char conn_name[9]; /* drbd1234N */
-	int vnr;
+	int vnr_got = vnr;
+
+	mdev = minor_to_mdev(minor);
+	if (mdev)
+		return ERR_MINOR_EXISTS;
 
 	/* GFP_KERNEL, we are outside of all write-out paths */
 	mdev = kzalloc(sizeof(struct drbd_conf), GFP_KERNEL);
 	if (!mdev)
-		return NULL;
-	sprintf(conn_name, "drbd%d", minor);
-	mdev->tconn = drbd_new_tconn(conn_name);
-	if (!mdev->tconn)
-		goto out_no_tconn;
-	if (!idr_pre_get(&mdev->tconn->volumes, GFP_KERNEL))
-		goto out_no_cpumask;
-	if (idr_get_new(&mdev->tconn->volumes, mdev, &vnr))
-		goto out_no_cpumask;
-	if (vnr != 0) {
-		dev_err(DEV, "vnr = %d\n", vnr);
-		goto out_no_cpumask;
-	}
-	if (!zalloc_cpumask_var(&mdev->tconn->cpu_mask, GFP_KERNEL))
-		goto out_no_cpumask;
+		return ERR_NOMEM;
+
+	mdev->tconn = tconn;
+	if (!idr_pre_get(&tconn->volumes, GFP_KERNEL))
+		goto out_no_idr;
+	if (idr_get_new(&tconn->volumes, mdev, &vnr_got))
+		goto out_no_idr;
+	if (vnr_got != vnr) {
+		dev_err(DEV, "vnr_got (%d) != vnr (%d)\n", vnr_got, vnr);
+		goto out_no_q;
+	}
 
 	mdev->minor = minor;
 
@@ -2354,7 +2361,10 @@ struct drbd_conf *drbd_new_device(unsigned int minor)
 	INIT_LIST_HEAD(&mdev->current_epoch->list);
 	mdev->epochs = 1;
 
-	return mdev;
+	minor_table[minor] = mdev;
+	add_disk(disk);
+
+	return NO_ERROR;
 
 /* out_whatever_else:
 	kfree(mdev->current_epoch); */
@@ -2367,12 +2377,10 @@ out_no_io_page:
 out_no_disk:
 	blk_cleanup_queue(q);
 out_no_q:
-	free_cpumask_var(mdev->tconn->cpu_mask);
-out_no_cpumask:
-	drbd_free_tconn(mdev->tconn);
-out_no_tconn:
+	idr_remove(&tconn->volumes, vnr_got);
+out_no_idr:
 	kfree(mdev);
-	return NULL;
+	return ERR_NOMEM;
 }
 
 /* counterpart of drbd_new_device.
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 455a51dd364d..f2739fd188a0 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -443,40 +443,6 @@ drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force)
 	return rv;
 }
 
-static struct drbd_conf *ensure_mdev(int minor, int create)
-{
-	struct drbd_conf *mdev;
-
-	if (minor >= minor_count)
-		return NULL;
-
-	mdev = minor_to_mdev(minor);
-
-	if (!mdev && create) {
-		struct gendisk *disk = NULL;
-		mdev = drbd_new_device(minor);
-
-		spin_lock_irq(&drbd_pp_lock);
-		if (minor_table[minor] == NULL) {
-			minor_table[minor] = mdev;
-			disk = mdev->vdisk;
-			mdev = NULL;
-		} /* else: we lost the race */
-		spin_unlock_irq(&drbd_pp_lock);
-
-		if (disk) /* we won the race above */
-			/* in case we ever add a drbd_delete_device(),
-			 * don't forget the del_gendisk! */
-			add_disk(disk);
-		else /* we lost the race above */
-			drbd_free_mdev(mdev);
-
-		mdev = minor_to_mdev(minor);
-	}
-
-	return mdev;
-}
-
 static int drbd_nl_primary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
 			   struct drbd_nl_cfg_reply *reply)
 {
@@ -1789,12 +1755,6 @@ static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *n
 	if (!expect(sc.al_extents <= DRBD_AL_EXTENTS_MAX))
 		sc.al_extents = DRBD_AL_EXTENTS_MAX;
 
-	/* to avoid spurious errors when configuring minors before configuring
-	 * the minors they depend on: if necessary, first create the minor we
-	 * depend on */
-	if (sc.after >= 0)
-		ensure_mdev(sc.after, 1);
-
 	/* most sanity checks done, try to assign the new sync-after
 	 * dependency.  need to hold the global lock in there,
 	 * to avoid a race in the dependency loop check. */
@@ -2184,13 +2144,73 @@ out:
 	return 0;
 }
 
+static int drbd_nl_new_conn(struct drbd_nl_cfg_req *nlp, struct drbd_nl_cfg_reply *reply)
+{
+	struct new_connection args;
+
+	if (!new_connection_from_tags(nlp->tag_list, &args)) {
+		reply->ret_code = ERR_MANDATORY_TAG;
+		return 0;
+	}
+
+	reply->ret_code = NO_ERROR;
+	if (!drbd_new_tconn(args.name))
+		reply->ret_code = ERR_NOMEM;
+
+	return 0;
+}
+
+static int drbd_nl_new_minor(struct drbd_tconn *tconn,
+		      struct drbd_nl_cfg_req *nlp, struct drbd_nl_cfg_reply *reply)
+{
+	struct new_minor args;
+
+	args.vol_nr = 0;
+	args.minor = 0;
+
+	if (!new_minor_from_tags(nlp->tag_list, &args)) {
+		reply->ret_code = ERR_MANDATORY_TAG;
+		return 0;
+	}
+
+	reply->ret_code = conn_new_minor(tconn, args.minor, args.vol_nr);
+
+	return 0;
+}
+
+static int drbd_nl_del_minor(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
+			     struct drbd_nl_cfg_reply *reply)
+{
+	if (mdev->state.disk == D_DISKLESS &&
+	    mdev->state.conn == C_STANDALONE &&
+	    mdev->state.role == R_SECONDARY) {
+		drbd_delete_device(mdev_to_minor(mdev));
+		reply->ret_code = NO_ERROR;
+	} else {
+		reply->ret_code = ERR_MINOR_CONFIGURED;
+	}
+	return 0;
+}
+
+static int drbd_nl_del_conn(struct drbd_tconn *tconn,
+			    struct drbd_nl_cfg_req *nlp, struct drbd_nl_cfg_reply *reply)
+{
+	if (conn_lowest_minor(tconn) < 0) {
+		drbd_free_tconn(tconn);
+		reply->ret_code = NO_ERROR;
+	} else {
+		reply->ret_code = ERR_CONN_IN_USE;
+	}
+
+	return 0;
+}
+
 enum cn_handler_type {
 	CHT_MINOR,
 	CHT_CONN,
 	CHT_CTOR,
 	/* CHT_RES, later */
 };
-
 struct cn_handler_struct {
 	enum cn_handler_type type;
 	union {
@@ -2235,6 +2255,10 @@ static struct cn_handler_struct cnd_table[] = {
 				    sizeof(struct get_timeout_flag_tag_len_struct)},
 	[ P_start_ov ]		= { CHT_MINOR, { &drbd_nl_start_ov },	0 },
 	[ P_new_c_uuid ]	= { CHT_MINOR, { &drbd_nl_new_c_uuid },	0 },
+	[ P_new_connection ]	= { CHT_CTOR,  { .constructor = &drbd_nl_new_conn }, 0 },
+	[ P_new_minor ]		= { CHT_CONN,  { .conn_based = &drbd_nl_new_minor }, 0 },
+	[ P_del_minor ]		= { CHT_MINOR, { &drbd_nl_del_minor },	0 },
+	[ P_del_connection ]    = { CHT_CONN,  { .conn_based = &drbd_nl_del_conn }, 0 },
 };
 
 static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms *nsp)
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 7683b4ab6583..e192167e6145 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -156,6 +156,9 @@ enum drbd_ret_code {
 	ERR_PIC_AFTER_DEP	= 156,
 	ERR_PIC_PEER_DEP	= 157,
 	ERR_CONN_NOT_KNOWN      = 158,
+	ERR_CONN_IN_USE         = 159,
+	ERR_MINOR_CONFIGURED    = 160,
+	ERR_MINOR_EXISTS	= 161,
 
 	/* insert new ones above this line */
 	AFTER_LAST_ERR_CODE
diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h
index ab6159e4fcf0..1216c7a432c5 100644
--- a/include/linux/drbd_nl.h
+++ b/include/linux/drbd_nl.h
@@ -152,6 +152,18 @@ NL_PACKET(new_c_uuid, 26,
 NL_RESPONSE(return_code_only, 27)
 #endif
 
+NL_PACKET(new_connection, 28, /* CHT_CTOR */
+	NL_STRING(	85,	T_MANDATORY,	name, DRBD_NL_OBJ_NAME_LEN)
+)
+
+NL_PACKET(new_minor, 29, /* CHT_CONN */
+	NL_INTEGER(	86,	T_MANDATORY,	minor)
+	NL_INTEGER(	87,	T_MANDATORY,	vol_nr)
+)
+
+NL_PACKET(del_minor, 30, ) /* CHT_MINOR */
+NL_PACKET(del_connection, 31, ) /* CHT_CONN */
+
 #undef NL_PACKET
 #undef NL_INTEGER
 #undef NL_INT64
-- 
cgit v1.2.3-55-g7522


From a5df0e199cf6b31400fa86f6c3f73fa6e127e9ed Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Wed, 23 Feb 2011 12:51:43 +0100
Subject: drbd: default to detach on-io-error

Old default behaviour was "pass-on",
which is not useful in production at all.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_limits.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 75f05af33725..22920a8af4e2 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -125,7 +125,7 @@
 #define DRBD_DISK_SIZE_SECT_MAX  (1 * (2LLU << 40))
 #define DRBD_DISK_SIZE_SECT_DEF  0 /* = disabled = no user size... */
 
-#define DRBD_ON_IO_ERROR_DEF EP_PASS_ON
+#define DRBD_ON_IO_ERROR_DEF EP_DETACH
 #define DRBD_FENCING_DEF FP_DONT_CARE
 #define DRBD_AFTER_SB_0P_DEF ASB_DISCONNECT
 #define DRBD_AFTER_SB_1P_DEF ASB_DISCONNECT
-- 
cgit v1.2.3-55-g7522


From ec2c35ac1ea288f5c931e32452ecea50068e8450 Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Mon, 7 Mar 2011 10:20:08 +0100
Subject: drbd: prepare the transition from connector to genetlink

This adds the new API header and helper files.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_genl.h         | 349 +++++++++++++++++++++++++++++++
 include/linux/drbd_genl_api.h     |  55 +++++
 include/linux/genl_magic_func.h   | 417 ++++++++++++++++++++++++++++++++++++++
 include/linux/genl_magic_struct.h | 260 ++++++++++++++++++++++++
 4 files changed, 1081 insertions(+)
 create mode 100644 include/linux/drbd_genl.h
 create mode 100644 include/linux/drbd_genl_api.h
 create mode 100644 include/linux/genl_magic_func.h
 create mode 100644 include/linux/genl_magic_struct.h

(limited to 'include')

diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
new file mode 100644
index 000000000000..84e16848f7a1
--- /dev/null
+++ b/include/linux/drbd_genl.h
@@ -0,0 +1,349 @@
+/*
+ * General overview:
+ * full generic netlink message:
+ * |nlmsghdr|genlmsghdr|<payload>
+ *
+ * payload:
+ * |optional fixed size family header|<sequence of netlink attributes>
+ *
+ * sequence of netlink attributes:
+ * I chose to have all "top level" attributes NLA_NESTED,
+ * corresponding to some real struct.
+ * So we have a sequence of |tla, len|<nested nla sequence>
+ *
+ * nested nla sequence:
+ * may be empty, or contain a sequence of netlink attributes
+ * representing the struct fields.
+ *
+ * The tag number of any field (regardless of containing struct)
+ * will be available as T_ ## field_name,
+ * so you cannot have the same field name in two differnt structs.
+ *
+ * The tag numbers themselves are per struct, though,
+ * so should always begin at 1 (not 0, that is the special "NLA_UNSPEC" type,
+ * which we won't use here).
+ * The tag numbers are used as index in the respective nla_policy array.
+ *
+ * GENL_struct(tag_name, tag_number, struct name, struct fields) - struct and policy
+ *	genl_magic_struct.h
+ *		generates the struct declaration,
+ *		generates an entry in the tla enum,
+ *	genl_magic_func.h
+ *		generates an entry in the static tla policy
+ *		with .type = NLA_NESTED
+ *		generates the static <struct_name>_nl_policy definition,
+ *		and static conversion functions
+ *
+ *	genl_magic_func.h
+ *
+ * GENL_mc_group(group)
+ *	genl_magic_struct.h
+ *		does nothing
+ *	genl_magic_func.h
+ *		defines and registers the mcast group,
+ *		and provides a send helper
+ *
+ * GENL_notification(op_name, op_num, mcast_group, tla list)
+ *	These are notifications to userspace.
+ *
+ *	genl_magic_struct.h
+ *		generates an entry in the genl_ops enum,
+ *	genl_magic_func.h
+ *		does nothing
+ *
+ *	mcast group: the name of the mcast group this notification should be
+ *	expected on
+ *	tla list: the list of expected top level attributes,
+ *	for documentation and sanity checking.
+ *
+ * GENL_op(op_name, op_num, flags and handler, tla list) - "genl operations"
+ *	These are requests from userspace.
+ *
+ *	_op and _notification share the same "number space",
+ *	op_nr will be assigned to "genlmsghdr->cmd"
+ *
+ *	genl_magic_struct.h
+ *		generates an entry in the genl_ops enum,
+ *	genl_magic_func.h
+ *		generates an entry in the static genl_ops array,
+ *		and static register/unregister functions to
+ *		genl_register_family_with_ops().
+ *
+ *	flags and handler:
+ *		GENL_op_init( .doit = x, .dumpit = y, .flags = something)
+ *		GENL_doit(x) => .dumpit = NULL, .flags = GENL_ADMIN_PERM
+ *	tla list: the list of expected top level attributes,
+ *	for documentation and sanity checking.
+ */
+
+/*
+ * STRUCTS
+ */
+
+/* this is sent kernel -> userland on various error conditions, and contains
+ * informational textual info, which is supposedly human readable.
+ * The computer relevant return code is in the drbd_genlmsghdr.
+ */
+GENL_struct(DRBD_NLA_CFG_REPLY, 1, drbd_cfg_reply,
+		/* "arbitrary" size strings, nla_policy.len = 0 */
+	__str_field(1, GENLA_F_MANDATORY,	info_text, 0)
+)
+
+/* Configuration requests typically need a context to operate on.
+ * Possible keys are device minor (fits in the drbd_genlmsghdr),
+ * the replication link (aka connection) name,
+ * and/or the replication group (aka resource) name,
+ * and the volume id within the resource. */
+GENL_struct(DRBD_NLA_CFG_CONTEXT, 2, drbd_cfg_context,
+		/* currently only 256 volumes per group,
+		 * but maybe we still change that */
+	__u32_field(1, GENLA_F_MANDATORY,	ctx_volume)
+	__str_field(2, GENLA_F_MANDATORY,	ctx_conn_name, 128)
+)
+
+GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
+	__u64_field(1, GENLA_F_MANDATORY,	disk_size)
+	__str_field(2, GENLA_F_REQUIRED,	backing_dev,	128)
+	__str_field(3, GENLA_F_REQUIRED,	meta_dev,	128)
+	__u32_field(4, GENLA_F_REQUIRED,	meta_dev_idx)
+	__u32_field(5, GENLA_F_MANDATORY,	max_bio_bvecs)
+	__u32_field(6, GENLA_F_MANDATORY,	on_io_error)
+	__u32_field(7, GENLA_F_MANDATORY,	fencing)
+	__flg_field(8, GENLA_F_MANDATORY,	no_disk_barrier)
+	__flg_field(9, GENLA_F_MANDATORY,	no_disk_flush)
+	__flg_field(10, GENLA_F_MANDATORY,	no_disk_drain)
+	__flg_field(11, GENLA_F_MANDATORY,	no_md_flush)
+	__flg_field(12, GENLA_F_MANDATORY,	use_bmbv)
+)
+
+GENL_struct(DRBD_NLA_SYNCER_CONF, 4, syncer_conf,
+	__u32_field(1,	GENLA_F_MANDATORY,	rate)
+	__u32_field(2,	GENLA_F_MANDATORY,	after)
+	__u32_field(3,	GENLA_F_MANDATORY,	al_extents)
+	__str_field(4,	GENLA_F_MANDATORY,	cpu_mask,       32)
+	__str_field(5,	GENLA_F_MANDATORY,	verify_alg,     SHARED_SECRET_MAX)
+	__str_field(6,	GENLA_F_MANDATORY,	csums_alg,	SHARED_SECRET_MAX)
+	__flg_field(7,	GENLA_F_MANDATORY,	use_rle)
+	__u32_field(8,	GENLA_F_MANDATORY,	on_no_data)
+	__u32_field(9,	GENLA_F_MANDATORY,	c_plan_ahead)
+	__u32_field(10,	GENLA_F_MANDATORY,	c_delay_target)
+	__u32_field(11,	GENLA_F_MANDATORY,	c_fill_target)
+	__u32_field(12,	GENLA_F_MANDATORY,	c_max_rate)
+	__u32_field(13,	GENLA_F_MANDATORY,	c_min_rate)
+)
+
+GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
+	__str_field(1,	GENLA_F_MANDATORY | GENLA_F_SENSITIVE,
+						shared_secret,	SHARED_SECRET_MAX)
+	__str_field(2,	GENLA_F_MANDATORY,	cram_hmac_alg,	SHARED_SECRET_MAX)
+	__str_field(3,	GENLA_F_MANDATORY,	integrity_alg,	SHARED_SECRET_MAX)
+	__str_field(4,	GENLA_F_REQUIRED,	my_addr,	128)
+	__str_field(5,	GENLA_F_REQUIRED,	peer_addr,	128)
+	__u32_field(6,	GENLA_F_REQUIRED,	wire_protocol)
+	__u32_field(7,	GENLA_F_MANDATORY,	try_connect_int)
+	__u32_field(8,	GENLA_F_MANDATORY,	timeout)
+	__u32_field(9,	GENLA_F_MANDATORY,	ping_int)
+	__u32_field(10,	GENLA_F_MANDATORY,	ping_timeo)
+	__u32_field(11,	GENLA_F_MANDATORY,	sndbuf_size)
+	__u32_field(12,	GENLA_F_MANDATORY,	rcvbuf_size)
+	__u32_field(13,	GENLA_F_MANDATORY,	ko_count)
+	__u32_field(14,	GENLA_F_MANDATORY,	max_buffers)
+	__u32_field(15,	GENLA_F_MANDATORY,	max_epoch_size)
+	__u32_field(16,	GENLA_F_MANDATORY,	unplug_watermark)
+	__u32_field(17,	GENLA_F_MANDATORY,	after_sb_0p)
+	__u32_field(18,	GENLA_F_MANDATORY,	after_sb_1p)
+	__u32_field(19,	GENLA_F_MANDATORY,	after_sb_2p)
+	__u32_field(20,	GENLA_F_MANDATORY,	rr_conflict)
+	__u32_field(21,	GENLA_F_MANDATORY,	on_congestion)
+	__u32_field(22,	GENLA_F_MANDATORY,	cong_fill)
+	__u32_field(23,	GENLA_F_MANDATORY,	cong_extents)
+	__flg_field(24, GENLA_F_MANDATORY,	two_primaries)
+	__flg_field(25, GENLA_F_MANDATORY,	want_lose)
+	__flg_field(26, GENLA_F_MANDATORY,	no_cork)
+	__flg_field(27, GENLA_F_MANDATORY,	always_asbp)
+	__flg_field(28, GENLA_F_MANDATORY,	dry_run)
+)
+
+GENL_struct(DRBD_NLA_SET_ROLE_PARMS, 6, set_role_parms,
+	__flg_field(1, GENLA_F_MANDATORY,	assume_uptodate)
+)
+
+GENL_struct(DRBD_NLA_RESIZE_PARMS, 7, resize_parms,
+	__u64_field(1, GENLA_F_MANDATORY,	resize_size)
+	__flg_field(2, GENLA_F_MANDATORY,	resize_force)
+	__flg_field(3, GENLA_F_MANDATORY,	no_resync)
+)
+
+GENL_struct(DRBD_NLA_STATE_INFO, 8, state_info,
+	/* the reason of the broadcast,
+	 * if this is an event triggered broadcast. */
+	__u32_field(1, GENLA_F_MANDATORY,	sib_reason)
+	__u32_field(2, GENLA_F_REQUIRED,	current_state)
+	__u64_field(3, GENLA_F_MANDATORY,	capacity)
+	__u64_field(4, GENLA_F_MANDATORY,	ed_uuid)
+
+	/* These are for broadcast from after state change work.
+	 * prev_state and new_state are from the moment the state change took
+	 * place, new_state is not neccessarily the same as current_state,
+	 * there may have been more state changes since.  Which will be
+	 * broadcasted soon, in their respective after state change work.  */
+	__u32_field(5, GENLA_F_MANDATORY,	prev_state)
+	__u32_field(6, GENLA_F_MANDATORY,	new_state)
+
+	/* if we have a local disk: */
+	__bin_field(7, GENLA_F_MANDATORY,	uuids, (UI_SIZE*sizeof(__u64)))
+	__u32_field(8, GENLA_F_MANDATORY,	disk_flags)
+	__u64_field(9, GENLA_F_MANDATORY,	bits_total)
+	__u64_field(10, GENLA_F_MANDATORY,	bits_oos)
+	/* and in case resync or online verify is active */
+	__u64_field(11, GENLA_F_MANDATORY,	bits_rs_total)
+	__u64_field(12, GENLA_F_MANDATORY,	bits_rs_failed)
+
+	/* for pre and post notifications of helper execution */
+	__str_field(13, GENLA_F_MANDATORY,	helper, 32)
+	__u32_field(14, GENLA_F_MANDATORY,	helper_exit_code)
+)
+
+GENL_struct(DRBD_NLA_START_OV_PARMS, 9, start_ov_parms,
+	__u64_field(1, GENLA_F_MANDATORY,	ov_start_sector)
+)
+
+GENL_struct(DRBD_NLA_NEW_C_UUID_PARMS, 10, new_c_uuid_parms,
+	__flg_field(1, GENLA_F_MANDATORY, clear_bm)
+)
+
+GENL_struct(DRBD_NLA_TIMEOUT_PARMS, 11, timeout_parms,
+	__u32_field(1,	GENLA_F_REQUIRED,	timeout_type)
+)
+
+GENL_struct(DRBD_NLA_DISCONNECT_PARMS, 12, disconnect_parms,
+	__flg_field(1, GENLA_F_MANDATORY,	force_disconnect)
+)
+
+/*
+ * Notifications and commands (genlmsghdr->cmd)
+ */
+GENL_mc_group(events)
+
+	/* kernel -> userspace announcement of changes */
+GENL_notification(
+	DRBD_EVENT, 1, events,
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_STATE_INFO, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NET_CONF, GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_DISK_CONF, GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_SYNCER_CONF, GENLA_F_MANDATORY)
+)
+
+	/* query kernel for specific or all info */
+GENL_op(
+	DRBD_ADM_GET_STATUS, 2,
+	GENL_op_init(
+		.doit = drbd_adm_get_status,
+		.dumpit = drbd_adm_get_status_all,
+		/* anyone may ask for the status,
+		 * it is broadcasted anyways */
+	),
+	/* To select the object .doit.
+	 * Or a subset of objects in .dumpit. */
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_MANDATORY)
+)
+
+#if 0
+	/* TO BE DONE */
+	/* create or destroy resources, aka replication groups */
+GENL_op(DRBD_ADM_CREATE_RESOURCE, 3, GENL_doit(drbd_adm_create_resource),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_DELETE_RESOURCE, 4, GENL_doit(drbd_adm_delete_resource),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+#endif
+
+	/* add DRBD minor devices as volumes to resources */
+GENL_op(DRBD_ADM_ADD_MINOR, 5, GENL_doit(drbd_adm_add_minor),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_DEL_MINOR, 6, GENL_doit(drbd_adm_delete_minor),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+
+	/* add or delete replication links to resources */
+GENL_op(DRBD_ADM_ADD_LINK, 7, GENL_doit(drbd_adm_create_connection),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_DEL_LINK, 8, GENL_doit(drbd_adm_delete_connection),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+
+	/* operates on replication links */
+GENL_op(DRBD_ADM_SYNCER, 9,
+	GENL_doit(drbd_adm_syncer),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_SYNCER_CONF, GENLA_F_MANDATORY)
+)
+
+GENL_op(
+	DRBD_ADM_CONNECT, 10,
+	GENL_doit(drbd_adm_connect),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NET_CONF, GENLA_F_REQUIRED)
+)
+
+GENL_op(DRBD_ADM_DISCONNECT, 11, GENL_doit(drbd_adm_disconnect),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+
+	/* operates on minors */
+GENL_op(DRBD_ADM_ATTACH, 12,
+	GENL_doit(drbd_adm_attach),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_DISK_CONF, GENLA_F_REQUIRED)
+)
+
+GENL_op(
+	DRBD_ADM_RESIZE, 13,
+	GENL_doit(drbd_adm_resize),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_RESIZE_PARMS, GENLA_F_MANDATORY)
+)
+
+	/* operates on all volumes within a resource */
+GENL_op(
+	DRBD_ADM_PRIMARY, 14,
+	GENL_doit(drbd_adm_set_role),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_SET_ROLE_PARMS, GENLA_F_REQUIRED)
+)
+
+GENL_op(
+	DRBD_ADM_SECONDARY, 15,
+	GENL_doit(drbd_adm_set_role),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_SET_ROLE_PARMS, GENLA_F_REQUIRED)
+)
+
+GENL_op(
+	DRBD_ADM_NEW_C_UUID, 16,
+	GENL_doit(drbd_adm_new_c_uuid),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NEW_C_UUID_PARMS, GENLA_F_MANDATORY)
+)
+
+GENL_op(
+	DRBD_ADM_START_OV, 17,
+	GENL_doit(drbd_adm_start_ov),
+	GENL_tla_expected(DRBD_NLA_START_OV_PARMS, GENLA_F_MANDATORY)
+)
+
+GENL_op(DRBD_ADM_DETACH,	18, GENL_doit(drbd_adm_detach),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_INVALIDATE,	19, GENL_doit(drbd_adm_invalidate),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_INVAL_PEER,	20, GENL_doit(drbd_adm_invalidate_peer),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_PAUSE_SYNC,	21, GENL_doit(drbd_adm_pause_sync),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_RESUME_SYNC,	22, GENL_doit(drbd_adm_resume_sync),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_SUSPEND_IO,	23, GENL_doit(drbd_adm_suspend_io),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_RESUME_IO,	24, GENL_doit(drbd_adm_resume_io),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_OUTDATE,	25, GENL_doit(drbd_adm_outdate),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_GET_TIMEOUT_TYPE, 26, GENL_doit(drbd_adm_get_timeout_type),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
diff --git a/include/linux/drbd_genl_api.h b/include/linux/drbd_genl_api.h
new file mode 100644
index 000000000000..9ef50d51e34e
--- /dev/null
+++ b/include/linux/drbd_genl_api.h
@@ -0,0 +1,55 @@
+#ifndef DRBD_GENL_STRUCT_H
+#define DRBD_GENL_STRUCT_H
+
+/**
+ * struct drbd_genlmsghdr - DRBD specific header used in NETLINK_GENERIC requests
+ * @minor:
+ *     For admin requests (user -> kernel): which minor device to operate on.
+ *     For (unicast) replies or informational (broadcast) messages
+ *     (kernel -> user): which minor device the information is about.
+ *     If we do not operate on minors, but on connections or resources,
+ *     the minor value shall be (~0), and the attribute DRBD_NLA_CFG_CONTEXT
+ *     is used instead.
+ * @flags: possible operation modifiers (relevant only for user->kernel):
+ *     DRBD_GENL_F_SET_DEFAULTS
+ * @volume:
+ *     When creating a new minor (adding it to a resource), the resource needs
+ *     to know which volume number within the resource this is supposed to be.
+ *     The volume number corresponds to the same volume number on the remote side,
+ *     whereas the minor number on the remote side may be different
+ *     (union with flags).
+ * @ret_code: kernel->userland unicast cfg reply return code (union with flags);
+ */
+struct drbd_genlmsghdr {
+	__u32 minor;
+	union {
+	__u32 flags;
+	__s32 ret_code;
+	};
+};
+
+/* To be used in drbd_genlmsghdr.flags */
+enum {
+	DRBD_GENL_F_SET_DEFAULTS = 1,
+};
+
+enum drbd_state_info_bcast_reason {
+	SIB_GET_STATUS_REPLY = 1,
+	SIB_STATE_CHANGE = 2,
+	SIB_HELPER_PRE = 3,
+	SIB_HELPER_POST = 4,
+	SIB_SYNC_PROGRESS = 5,
+};
+
+/* hack around predefined gcc/cpp "linux=1",
+ * we cannot possibly include <1/drbd_genl.h> */
+#undef linux
+
+#include <linux/drbd.h>
+#define GENL_MAGIC_VERSION	API_VERSION
+#define GENL_MAGIC_FAMILY	drbd
+#define GENL_MAGIC_FAMILY_HDRSZ	sizeof(struct drbd_genlmsghdr)
+#define GENL_MAGIC_INCLUDE_FILE <linux/drbd_genl.h>
+#include <linux/genl_magic_struct.h>
+
+#endif
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
new file mode 100644
index 000000000000..8a86f659d363
--- /dev/null
+++ b/include/linux/genl_magic_func.h
@@ -0,0 +1,417 @@
+#ifndef GENL_MAGIC_FUNC_H
+#define GENL_MAGIC_FUNC_H
+
+#include <linux/genl_magic_struct.h>
+
+/*
+ * Extension of genl attribute validation policies			{{{1
+ *									{{{2
+ */
+
+/**
+ * nla_is_required - return true if this attribute is required
+ * @nla: netlink attribute
+ */
+static inline int nla_is_required(const struct nlattr *nla)
+{
+        return nla->nla_type & GENLA_F_REQUIRED;
+}
+
+/**
+ * nla_is_mandatory - return true if understanding this attribute is mandatory
+ * @nla: netlink attribute
+ * Note: REQUIRED attributes are implicitly MANDATORY as well
+ */
+static inline int nla_is_mandatory(const struct nlattr *nla)
+{
+        return nla->nla_type & (GENLA_F_MANDATORY | GENLA_F_REQUIRED);
+}
+
+/* Functionality to be integrated into nla_parse(), and validate_nla(),
+ * respectively.
+ *
+ * Enforcing the "mandatory" bit is done here,
+ * by rejecting unknown mandatory attributes.
+ *
+ * Part of enforcing the "required" flag would mean to embed it into
+ * nla_policy.type, and extending validate_nla(), which currently does
+ * BUG_ON(pt->type > NLA_TYPE_MAX); we have to work on existing kernels,
+ * so we cannot do that.  Thats why enforcing "required" is done in the
+ * generated assignment functions below. */
+static int nla_check_unknown(int maxtype, struct nlattr *head, int len)
+{
+	struct nlattr *nla;
+	int rem;
+        nla_for_each_attr(nla, head, len, rem) {
+		__u16 type = nla_type(nla);
+		if (type > maxtype && nla_is_mandatory(nla))
+			return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+/*
+ * Magic: declare tla policy						{{{1
+ * Magic: declare nested policies
+ *									{{{2
+ */
+#undef GENL_mc_group
+#define GENL_mc_group(group)
+
+#undef GENL_notification
+#define GENL_notification(op_name, op_num, mcast_group, tla_list)
+
+#undef GENL_op
+#define GENL_op(op_name, op_num, handler, tla_list)
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
+	[tag_name] = { .type = NLA_NESTED },
+
+static struct nla_policy CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy)[] = {
+#include GENL_MAGIC_INCLUDE_FILE
+};
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
+static struct nla_policy s_name ## _nl_policy[] __read_mostly =		\
+{ s_fields };
+
+#undef __field
+#define __field(attr_nr, attr_flag, name, nla_type, _type, __get, __put) \
+	[__nla_type(attr_nr)] = { .type = nla_type },
+
+#undef __array
+#define __array(attr_nr, attr_flag, name, nla_type, _type, maxlen,	\
+		__get, __put)						\
+	[__nla_type(attr_nr)] = { .type = nla_type,			\
+		.len = maxlen - (nla_type == NLA_NUL_STRING) },
+
+#include GENL_MAGIC_INCLUDE_FILE
+
+#ifndef __KERNEL__
+#ifndef pr_info
+#define pr_info(args...)	fprintf(stderr, args);
+#endif
+#endif
+
+#if 1
+static void dprint_field(const char *dir, int nla_type,
+		const char *name, void *valp)
+{
+	__u64 val = valp ? *(__u32 *)valp : 1;
+	switch (nla_type) {
+	case NLA_U8:  val = (__u8)val;
+	case NLA_U16: val = (__u16)val;
+	case NLA_U32: val = (__u32)val;
+		pr_info("%s attr %s: %d 0x%08x\n", dir,
+			name, (int)val, (unsigned)val);
+		break;
+	case NLA_U64:
+		val = *(__u64*)valp;
+		pr_info("%s attr %s: %lld 0x%08llx\n", dir,
+			name, (long long)val, (unsigned long long)val);
+		break;
+	case NLA_FLAG:
+		if (val)
+			pr_info("%s attr %s: set\n", dir, name);
+		break;
+	}
+}
+
+static void dprint_array(const char *dir, int nla_type,
+		const char *name, const char *val, unsigned len)
+{
+	switch (nla_type) {
+	case NLA_NUL_STRING:
+		if (len && val[len-1] == '\0')
+			len--;
+		pr_info("%s attr %s: [len:%u] '%s'\n", dir, name, len, val);
+		break;
+	default:
+		/* we can always show 4 byte,
+		 * thats what nlattr are aligned to. */
+		pr_info("%s attr %s: [len:%u] %02x%02x%02x%02x ...\n",
+			dir, name, len, val[0], val[1], val[2], val[3]);
+	}
+}
+
+#define DPRINT_TLA(a, op, b) pr_info("%s %s %s\n", a, op, b);
+
+/* Name is a member field name of the struct s.
+ * If s is NULL (only parsing, no copy requested in *_from_attrs()),
+ * nla is supposed to point to the attribute containing the information
+ * corresponding to that struct member. */
+#define DPRINT_FIELD(dir, nla_type, name, s, nla)			\
+	do {								\
+		if (s)							\
+			dprint_field(dir, nla_type, #name, &s->name);	\
+		else if (nla)						\
+			dprint_field(dir, nla_type, #name,		\
+				(nla_type == NLA_FLAG) ? NULL		\
+						: nla_data(nla));	\
+	} while (0)
+
+#define	DPRINT_ARRAY(dir, nla_type, name, s, nla)			\
+	do {								\
+		if (s)							\
+			dprint_array(dir, nla_type, #name,		\
+					s->name, s->name ## _len);	\
+		else if (nla)						\
+			dprint_array(dir, nla_type, #name,		\
+					nla_data(nla), nla_len(nla));	\
+	} while (0)
+#else
+#define DPRINT_TLA(a, op, b) do {} while (0)
+#define DPRINT_FIELD(dir, nla_type, name, s, nla) do {} while (0)
+#define	DPRINT_ARRAY(dir, nla_type, name, s, nla) do {} while (0)
+#endif
+
+/*
+ * Magic: provide conversion functions					{{{1
+ * populate struct from attribute table:
+ *									{{{2
+ */
+
+/* processing of generic netlink messages is serialized.
+ * use one static buffer for parsing of nested attributes */
+static struct nlattr *nested_attr_tb[128];
+
+#ifndef BUILD_BUG_ON
+/* Force a compilation error if condition is true */
+#define BUILD_BUG_ON(condition) ((void)BUILD_BUG_ON_ZERO(condition))
+/* Force a compilation error if condition is true, but also produce a
+   result (of value 0 and type size_t), so the expression can be used
+   e.g. in a structure initializer (or where-ever else comma expressions
+   aren't permitted). */
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); }))
+#endif
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
+	/* static, potentially unused */				\
+int s_name ## _from_attrs(struct s_name *s, struct nlattr *tb[])	\
+{									\
+	const int maxtype = ARRAY_SIZE(s_name ## _nl_policy)-1;		\
+	struct nlattr *tla = tb[tag_number];				\
+	struct nlattr **ntb = nested_attr_tb;				\
+	struct nlattr *nla;						\
+	int err;							\
+	BUILD_BUG_ON(ARRAY_SIZE(s_name ## _nl_policy) > ARRAY_SIZE(nested_attr_tb));	\
+	if (!tla)							\
+		return -ENOMSG;						\
+	DPRINT_TLA(#s_name, "<=-", #tag_name);				\
+	err = nla_parse_nested(ntb, maxtype, tla, s_name ## _nl_policy); \
+	if (err)							\
+		return err;						\
+	err = nla_check_unknown(maxtype, nla_data(tla), nla_len(tla));	\
+	if (err)							\
+	      return err;						\
+									\
+	s_fields							\
+	return 0;							\
+}
+
+#undef __field
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)	\
+		nla = ntb[__nla_type(attr_nr)];				\
+		if (nla) {						\
+			if (s)						\
+				s->name = __get(nla);			\
+			DPRINT_FIELD("<<", nla_type, name, s, nla);	\
+		} else if ((attr_flag) & GENLA_F_REQUIRED) {		\
+			pr_info("<< missing attr: %s\n", #name);	\
+			return -ENOMSG;					\
+		}
+
+/* validate_nla() already checked nla_len <= maxlen appropriately. */
+#undef __array
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
+		nla = ntb[__nla_type(attr_nr)];				\
+		if (nla) {						\
+			if (s)						\
+				s->name ## _len =			\
+					__get(s->name, nla, maxlen);	\
+			DPRINT_ARRAY("<<", nla_type, name, s, nla);	\
+		} else if ((attr_flag) & GENLA_F_REQUIRED) {		\
+			pr_info("<< missing attr: %s\n", #name);	\
+			return -ENOMSG;					\
+		}							\
+
+#include GENL_MAGIC_INCLUDE_FILE
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)
+
+/*
+ * Magic: define op number to op name mapping				{{{1
+ *									{{{2
+ */
+const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd)
+{
+	switch (cmd) {
+#undef GENL_op
+#define GENL_op(op_name, op_num, handler, tla_list)		\
+	case op_num: return #op_name;
+#include GENL_MAGIC_INCLUDE_FILE
+	default:
+		     return "unknown";
+	}
+}
+
+#ifdef __KERNEL__
+#include <linux/stringify.h>
+/*
+ * Magic: define genl_ops						{{{1
+ *									{{{2
+ */
+
+#undef GENL_op
+#define GENL_op(op_name, op_num, handler, tla_list)		\
+{								\
+	handler							\
+	.cmd = op_name,						\
+	.policy	= CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy),	\
+},
+
+#define ZZZ_genl_ops		CONCAT_(GENL_MAGIC_FAMILY, _genl_ops)
+static struct genl_ops ZZZ_genl_ops[] __read_mostly = {
+#include GENL_MAGIC_INCLUDE_FILE
+};
+
+#undef GENL_op
+#define GENL_op(op_name, op_num, handler, tla_list)
+
+/*
+ * Define the genl_family, multicast groups,				{{{1
+ * and provide register/unregister functions.
+ *									{{{2
+ */
+#define ZZZ_genl_family		CONCAT_(GENL_MAGIC_FAMILY, _genl_family)
+static struct genl_family ZZZ_genl_family __read_mostly = {
+	.id = GENL_ID_GENERATE,
+	.name = __stringify(GENL_MAGIC_FAMILY),
+	.version = GENL_MAGIC_VERSION,
+#ifdef GENL_MAGIC_FAMILY_HDRSZ
+	.hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ),
+#endif
+	.maxattr = ARRAY_SIZE(drbd_tla_nl_policy)-1,
+};
+
+/*
+ * Magic: define multicast groups
+ * Magic: define multicast group registration helper
+ */
+#undef GENL_mc_group
+#define GENL_mc_group(group)						\
+static struct genl_multicast_group					\
+CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group) __read_mostly = {		\
+	.name = #group,							\
+};									\
+static int CONCAT_(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)(	\
+	struct sk_buff *skb, gfp_t flags)				\
+{									\
+	unsigned int group_id =						\
+		CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group).id;	\
+	if (!group_id)							\
+		return -EINVAL;						\
+	return genlmsg_multicast(skb, 0, group_id, flags);		\
+}
+
+#include GENL_MAGIC_INCLUDE_FILE
+
+int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void)
+{
+	int err = genl_register_family_with_ops(&ZZZ_genl_family,
+		ZZZ_genl_ops, ARRAY_SIZE(ZZZ_genl_ops));
+	if (err)
+		return err;
+#undef GENL_mc_group
+#define GENL_mc_group(group)						\
+	err = genl_register_mc_group(&ZZZ_genl_family,			\
+		&CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group));		\
+	if (err)							\
+		goto fail;						\
+	else								\
+		pr_info("%s: mcg %s: %u\n", #group,			\
+			__stringify(GENL_MAGIC_FAMILY),			\
+			CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group).id);
+
+#include GENL_MAGIC_INCLUDE_FILE
+
+#undef GENL_mc_group
+#define GENL_mc_group(group)
+	return 0;
+fail:
+	genl_unregister_family(&ZZZ_genl_family);
+	return err;
+}
+
+void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void)
+{
+	genl_unregister_family(&ZZZ_genl_family);
+}
+
+/*
+ * Magic: provide conversion functions					{{{1
+ * populate skb from struct.
+ *									{{{2
+ */
+
+#undef GENL_op
+#define GENL_op(op_name, op_num, handler, tla_list)
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
+static int s_name ## _to_skb(struct sk_buff *skb, struct s_name *s,	\
+		const bool exclude_sensitive)				\
+{									\
+	struct nlattr *tla = nla_nest_start(skb, tag_number);		\
+	if (!tla)							\
+		goto nla_put_failure;					\
+	DPRINT_TLA(#s_name, "-=>", #tag_name);				\
+	s_fields							\
+	nla_nest_end(skb, tla);						\
+	return 0;							\
+									\
+nla_put_failure:							\
+	if (tla)							\
+		nla_nest_cancel(skb, tla);				\
+        return -EMSGSIZE;						\
+}									\
+static inline int s_name ## _to_priv_skb(struct sk_buff *skb,		\
+		struct s_name *s)					\
+{									\
+	return s_name ## _to_skb(skb, s, 0);				\
+}									\
+static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb,		\
+		struct s_name *s)					\
+{									\
+	return s_name ## _to_skb(skb, s, 1);				\
+}
+
+
+#undef __field
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)	\
+	if (!exclude_sensitive || !((attr_flag) & GENLA_F_SENSITIVE)) {	\
+		DPRINT_FIELD(">>", nla_type, name, s, NULL);		\
+		__put(skb, attr_nr, s->name);				\
+	}
+
+#undef __array
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
+	if (!exclude_sensitive || !((attr_flag) & GENLA_F_SENSITIVE)) {	\
+		DPRINT_ARRAY(">>",nla_type, name, s, NULL);		\
+		__put(skb, attr_nr, min_t(int, maxlen,			\
+			s->name ## _len + (nla_type == NLA_NUL_STRING)),\
+						s->name);		\
+	}
+
+#include GENL_MAGIC_INCLUDE_FILE
+
+#endif /* __KERNEL__ */
+
+/* }}}1 */
+#endif /* GENL_MAGIC_FUNC_H */
+/* vim: set foldmethod=marker foldlevel=1 nofoldenable : */
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
new file mode 100644
index 000000000000..745ebfd6c7e5
--- /dev/null
+++ b/include/linux/genl_magic_struct.h
@@ -0,0 +1,260 @@
+#ifndef GENL_MAGIC_STRUCT_H
+#define GENL_MAGIC_STRUCT_H
+
+#ifndef GENL_MAGIC_FAMILY
+# error "you need to define GENL_MAGIC_FAMILY before inclusion"
+#endif
+
+#ifndef GENL_MAGIC_VERSION
+# error "you need to define GENL_MAGIC_VERSION before inclusion"
+#endif
+
+#ifndef GENL_MAGIC_INCLUDE_FILE
+# error "you need to define GENL_MAGIC_INCLUDE_FILE before inclusion"
+#endif
+
+#include <linux/genetlink.h>
+#include <linux/types.h>
+
+#define CONCAT__(a,b)	a ## b
+#define CONCAT_(a,b)	CONCAT__(a,b)
+
+extern int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void);
+extern void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void);
+
+/*
+ * Extension of genl attribute validation policies			{{{2
+ */
+
+/**
+ * GENLA_F_FLAGS - policy type flags to ease compatible ABI evolvement
+ *
+ * @GENLA_F_REQUIRED: attribute has to be present, or message is considered invalid.
+ * Adding new REQUIRED attributes breaks ABI compatibility, so don't do that.
+ *
+ * @GENLA_F_MANDATORY: if present, receiver _must_ understand it.
+ * Without this, unknown attributes (> maxtype) are _silently_ ignored
+ * by validate_nla().
+ *
+ * To be used for API extensions, so older kernel can reject requests for not
+ * yet implemented features, if newer userland tries to use them even though
+ * the genl_family version clearly indicates they are not available.
+ *
+ * @GENLA_F_MAY_IGNORE: To clearly document the fact, for good measure.
+ * To be used for API extensions for things that have sane defaults,
+ * so newer userland can still talk to older kernel, knowing it will
+ * silently ignore these attributes if not yet known.
+ *
+ * NOTE: These flags overload
+ *   NLA_F_NESTED		(1 << 15)
+ *   NLA_F_NET_BYTEORDER	(1 << 14)
+ * from linux/netlink.h, which are not useful for validate_nla():
+ * NET_BYTEORDER is not used anywhere, and NESTED would be specified by setting
+ * .type = NLA_NESTED in the appropriate policy.
+ *
+ * See also: nla_type()
+ */
+enum {
+	GENLA_F_MAY_IGNORE	= 0,
+	GENLA_F_MANDATORY	= 1 << 14,
+	GENLA_F_REQUIRED	= 1 << 15,
+
+	/* This will not be present in the __u16 .nla_type, but can be
+	 * triggered on in <struct>_to_skb, to exclude "sensitive"
+	 * information from broadcasts, or on unpriviledged get requests.
+	 * This is useful because genetlink multicast groups can be listened in
+	 * on by anyone.  */
+	GENLA_F_SENSITIVE	= 1 << 16,
+};
+
+#define __nla_type(x)	((__u16)((__u16)(x) & (__u16)NLA_TYPE_MASK))
+
+/*									}}}1
+ * MAGIC
+ * multi-include macro expansion magic starts here
+ */
+
+/* MAGIC helpers							{{{2 */
+
+/* possible field types */
+#define __flg_field(attr_nr, attr_flag, name) \
+	__field(attr_nr, attr_flag, name, NLA_FLAG, char, \
+			nla_get_flag, __nla_put_flag)
+#define __u8_field(attr_nr, attr_flag, name)	\
+	__field(attr_nr, attr_flag, name, NLA_U8, unsigned char, \
+			nla_get_u8, NLA_PUT_U8)
+#define __u16_field(attr_nr, attr_flag, name)	\
+	__field(attr_nr, attr_flag, name, NLA_U16, __u16, \
+			nla_get_u16, NLA_PUT_U16)
+#define __u32_field(attr_nr, attr_flag, name)	\
+	__field(attr_nr, attr_flag, name, NLA_U32, __u32, \
+			nla_get_u32, NLA_PUT_U32)
+#define __u64_field(attr_nr, attr_flag, name)	\
+	__field(attr_nr, attr_flag, name, NLA_U64, __u64, \
+			nla_get_u64, NLA_PUT_U64)
+#define __str_field(attr_nr, attr_flag, name, maxlen) \
+	__array(attr_nr, attr_flag, name, NLA_NUL_STRING, char, maxlen, \
+			nla_strlcpy, NLA_PUT)
+#define __bin_field(attr_nr, attr_flag, name, maxlen) \
+	__array(attr_nr, attr_flag, name, NLA_BINARY, char, maxlen, \
+			nla_memcpy, NLA_PUT)
+
+#define __nla_put_flag(skb, attrtype, value)		\
+	do {						\
+		if (value)				\
+			NLA_PUT_FLAG(skb, attrtype);	\
+	} while (0)
+
+#define GENL_op_init(args...)	args
+#define GENL_doit(handler)		\
+	.doit = handler,		\
+	.flags = GENL_ADMIN_PERM,
+#define GENL_dumpit(handler)		\
+	.dumpit = handler,		\
+	.flags = GENL_ADMIN_PERM,
+
+/*									}}}1
+ * Magic: define the enum symbols for genl_ops
+ * Magic: define the enum symbols for top level attributes
+ * Magic: define the enum symbols for nested attributes
+ *									{{{2
+ */
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)
+
+#undef GENL_mc_group
+#define GENL_mc_group(group)
+
+#undef GENL_notification
+#define GENL_notification(op_name, op_num, mcast_group, tla_list)	\
+	op_name = op_num,
+
+#undef GENL_op
+#define GENL_op(op_name, op_num, handler, tla_list)			\
+	op_name = op_num,
+
+enum {
+#include GENL_MAGIC_INCLUDE_FILE
+};
+
+#undef GENL_notification
+#define GENL_notification(op_name, op_num, mcast_group, tla_list)
+
+#undef GENL_op
+#define GENL_op(op_name, op_num, handler, attr_list)
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields) \
+		tag_name = tag_number,
+
+enum {
+#include GENL_MAGIC_INCLUDE_FILE
+};
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)	\
+enum {								\
+	s_fields						\
+};
+
+#undef __field
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)	\
+	T_ ## name = (__u16)(attr_nr | attr_flag),
+
+#undef __array
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
+	T_ ## name = (__u16)(attr_nr | attr_flag),
+
+#include GENL_MAGIC_INCLUDE_FILE
+
+/*									}}}1
+ * Magic: compile time assert unique numbers for operations
+ * Magic: -"- unique numbers for top level attributes
+ * Magic: -"- unique numbers for nested attributes
+ *									{{{2
+ */
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)
+
+#undef GENL_op
+#define GENL_op(op_name, op_num, handler, attr_list)	\
+	case op_name:
+
+#undef GENL_notification
+#define GENL_notification(op_name, op_num, mcast_group, tla_list)	\
+	case op_name:
+
+static inline void ct_assert_unique_operations(void)
+{
+	switch (0) {
+#include GENL_MAGIC_INCLUDE_FILE
+		;
+	}
+}
+
+#undef GENL_op
+#define GENL_op(op_name, op_num, handler, attr_list)
+
+#undef GENL_notification
+#define GENL_notification(op_name, op_num, mcast_group, tla_list)
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
+		case tag_number:
+
+static inline void ct_assert_unique_top_level_attributes(void)
+{
+	switch (0) {
+#include GENL_MAGIC_INCLUDE_FILE
+		;
+	}
+}
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
+static inline void ct_assert_unique_ ## s_name ## _attributes(void)	\
+{									\
+	switch (0) {							\
+		s_fields						\
+			;						\
+	}								\
+}
+
+#undef __field
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)	\
+	case attr_nr:
+
+#undef __array
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
+	case attr_nr:
+
+#include GENL_MAGIC_INCLUDE_FILE
+
+/*									}}}1
+ * Magic: declare structs
+ * struct <name> {
+ *	fields
+ * };
+ *									{{{2
+ */
+
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
+struct s_name { s_fields };
+
+#undef __field
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put) \
+	type name;
+
+#undef __array
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
+	type name[maxlen];	\
+	__u32 name ## _len;
+
+#include GENL_MAGIC_INCLUDE_FILE
+
+/* }}}1 */
+#endif /* GENL_MAGIC_STRUCT_H */
+/* vim: set foldmethod=marker nofoldenable : */
-- 
cgit v1.2.3-55-g7522


From d4f65b5d2497b2fd9c45f06b71deb4ab084a5b66 Mon Sep 17 00:00:00 2001
From: David Howells
Date: Thu, 13 Sep 2012 13:06:29 +0100
Subject: KEYS: Add payload preparsing opportunity prior to key instantiate or
 update

Give the key type the opportunity to preparse the payload prior to the
instantiation and update routines being called.  This is done with the
provision of two new key type operations:

	int (*preparse)(struct key_preparsed_payload *prep);
	void (*free_preparse)(struct key_preparsed_payload *prep);

If the first operation is present, then it is called before key creation (in
the add/update case) or before the key semaphore is taken (in the update and
instantiate cases).  The second operation is called to clean up if the first
was called.

preparse() is given the opportunity to fill in the following structure:

	struct key_preparsed_payload {
		char		*description;
		void		*type_data[2];
		void		*payload;
		const void	*data;
		size_t		datalen;
		size_t		quotalen;
	};

Before the preparser is called, the first three fields will have been cleared,
the payload pointer and size will be stored in data and datalen and the default
quota size from the key_type struct will be stored into quotalen.

The preparser may parse the payload in any way it likes and may store data in
the type_data[] and payload fields for use by the instantiate() and update()
ops.

The preparser may also propose a description for the key by attaching it as a
string to the description field.  This can be used by passing a NULL or ""
description to the add_key() system call or the key_create_or_update()
function.  This cannot work with request_key() as that required the description
to tell the upcall about the key to be created.

This, for example permits keys that store PGP public keys to generate their own
name from the user ID and public key fingerprint in the key.

The instantiate() and update() operations are then modified to look like this:

	int (*instantiate)(struct key *key, struct key_preparsed_payload *prep);
	int (*update)(struct key *key, struct key_preparsed_payload *prep);

and the new payload data is passed in *prep, whether or not it was preparsed.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 Documentation/security/keys.txt          |  50 +++++++++++++-
 fs/cifs/cifs_spnego.c                    |   6 +-
 fs/cifs/cifsacl.c                        |   8 +--
 include/keys/user-type.h                 |   6 +-
 include/linux/key-type.h                 |  35 +++++++++-
 net/ceph/crypto.c                        |   9 +--
 net/dns_resolver/dns_key.c               |   6 +-
 net/rxrpc/ar-key.c                       |  40 +++++------
 security/keys/encrypted-keys/encrypted.c |  16 +++--
 security/keys/key.c                      | 114 ++++++++++++++++++++++---------
 security/keys/keyctl.c                   |  18 +++--
 security/keys/keyring.c                  |   6 +-
 security/keys/request_key_auth.c         |   8 +--
 security/keys/trusted.c                  |  16 +++--
 security/keys/user_defined.c             |  14 ++--
 15 files changed, 250 insertions(+), 102 deletions(-)

(limited to 'include')

diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index aa0dbd74b71b..7d9ca92022d8 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -412,6 +412,10 @@ The main syscalls are:
      to the keyring. In this case, an error will be generated if the process
      does not have permission to write to the keyring.
 
+     If the key type supports it, if the description is NULL or an empty
+     string, the key type will try and generate a description from the content
+     of the payload.
+
      The payload is optional, and the pointer can be NULL if not required by
      the type. The payload is plen in size, and plen can be zero for an empty
      payload.
@@ -1114,12 +1118,53 @@ The structure has a number of fields, some of which are mandatory:
      it should return 0.
 
 
- (*) int (*instantiate)(struct key *key, const void *data, size_t datalen);
+ (*) int (*preparse)(struct key_preparsed_payload *prep);
+
+     This optional method permits the key type to attempt to parse payload
+     before a key is created (add key) or the key semaphore is taken (update or
+     instantiate key).  The structure pointed to by prep looks like:
+
+	struct key_preparsed_payload {
+		char		*description;
+		void		*type_data[2];
+		void		*payload;
+		const void	*data;
+		size_t		datalen;
+		size_t		quotalen;
+	};
+
+     Before calling the method, the caller will fill in data and datalen with
+     the payload blob parameters; quotalen will be filled in with the default
+     quota size from the key type and the rest will be cleared.
+
+     If a description can be proposed from the payload contents, that should be
+     attached as a string to the description field.  This will be used for the
+     key description if the caller of add_key() passes NULL or "".
+
+     The method can attach anything it likes to type_data[] and payload.  These
+     are merely passed along to the instantiate() or update() operations.
+
+     The method should return 0 if success ful or a negative error code
+     otherwise.
+
+     
+ (*) void (*free_preparse)(struct key_preparsed_payload *prep);
+
+     This method is only required if the preparse() method is provided,
+     otherwise it is unused.  It cleans up anything attached to the
+     description, type_data and payload fields of the key_preparsed_payload
+     struct as filled in by the preparse() method.
+
+
+ (*) int (*instantiate)(struct key *key, struct key_preparsed_payload *prep);
 
      This method is called to attach a payload to a key during construction.
      The payload attached need not bear any relation to the data passed to this
      function.
 
+     The prep->data and prep->datalen fields will define the original payload
+     blob.  If preparse() was supplied then other fields may be filled in also.
+
      If the amount of data attached to the key differs from the size in
      keytype->def_datalen, then key_payload_reserve() should be called.
 
@@ -1135,6 +1180,9 @@ The structure has a number of fields, some of which are mandatory:
      If this type of key can be updated, then this method should be provided.
      It is called to update a key's payload from the blob of data provided.
 
+     The prep->data and prep->datalen fields will define the original payload
+     blob.  If preparse() was supplied then other fields may be filled in also.
+
      key_payload_reserve() should be called if the data length might change
      before any changes are actually made. Note that if this succeeds, the type
      is committed to changing the key because it's already been altered, so all
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index e622863b292f..086f381d6489 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -31,18 +31,18 @@
 
 /* create a new cifs key */
 static int
-cifs_spnego_key_instantiate(struct key *key, const void *data, size_t datalen)
+cifs_spnego_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	char *payload;
 	int ret;
 
 	ret = -ENOMEM;
-	payload = kmalloc(datalen, GFP_KERNEL);
+	payload = kmalloc(prep->datalen, GFP_KERNEL);
 	if (!payload)
 		goto error;
 
 	/* attach the data */
-	memcpy(payload, data, datalen);
+	memcpy(payload, prep->data, prep->datalen);
 	key->payload.data = payload;
 	ret = 0;
 
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 05f4dc263a23..f3c60e264ca8 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -167,17 +167,17 @@ static struct shrinker cifs_shrinker = {
 };
 
 static int
-cifs_idmap_key_instantiate(struct key *key, const void *data, size_t datalen)
+cifs_idmap_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	char *payload;
 
-	payload = kmalloc(datalen, GFP_KERNEL);
+	payload = kmalloc(prep->datalen, GFP_KERNEL);
 	if (!payload)
 		return -ENOMEM;
 
-	memcpy(payload, data, datalen);
+	memcpy(payload, prep->data, prep->datalen);
 	key->payload.data = payload;
-	key->datalen = datalen;
+	key->datalen = prep->datalen;
 	return 0;
 }
 
diff --git a/include/keys/user-type.h b/include/keys/user-type.h
index bc9ec1d7698c..5e452c84f1e6 100644
--- a/include/keys/user-type.h
+++ b/include/keys/user-type.h
@@ -35,8 +35,10 @@ struct user_key_payload {
 extern struct key_type key_type_user;
 extern struct key_type key_type_logon;
 
-extern int user_instantiate(struct key *key, const void *data, size_t datalen);
-extern int user_update(struct key *key, const void *data, size_t datalen);
+struct key_preparsed_payload;
+
+extern int user_instantiate(struct key *key, struct key_preparsed_payload *prep);
+extern int user_update(struct key *key, struct key_preparsed_payload *prep);
 extern int user_match(const struct key *key, const void *criterion);
 extern void user_revoke(struct key *key);
 extern void user_destroy(struct key *key);
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index f0c651cda7b0..518a53afb9ea 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -26,6 +26,27 @@ struct key_construction {
 	struct key	*authkey;/* authorisation for key being constructed */
 };
 
+/*
+ * Pre-parsed payload, used by key add, update and instantiate.
+ *
+ * This struct will be cleared and data and datalen will be set with the data
+ * and length parameters from the caller and quotalen will be set from
+ * def_datalen from the key type.  Then if the preparse() op is provided by the
+ * key type, that will be called.  Then the struct will be passed to the
+ * instantiate() or the update() op.
+ *
+ * If the preparse() op is given, the free_preparse() op will be called to
+ * clear the contents.
+ */
+struct key_preparsed_payload {
+	char		*description;	/* Proposed key description (or NULL) */
+	void		*type_data[2];	/* Private key-type data */
+	void		*payload;	/* Proposed payload */
+	const void	*data;		/* Raw data */
+	size_t		datalen;	/* Raw datalen */
+	size_t		quotalen;	/* Quota length for proposed payload */
+};
+
 typedef int (*request_key_actor_t)(struct key_construction *key,
 				   const char *op, void *aux);
 
@@ -45,18 +66,28 @@ struct key_type {
 	/* vet a description */
 	int (*vet_description)(const char *description);
 
+	/* Preparse the data blob from userspace that is to be the payload,
+	 * generating a proposed description and payload that will be handed to
+	 * the instantiate() and update() ops.
+	 */
+	int (*preparse)(struct key_preparsed_payload *prep);
+
+	/* Free a preparse data structure.
+	 */
+	void (*free_preparse)(struct key_preparsed_payload *prep);
+
 	/* instantiate a key of this type
 	 * - this method should call key_payload_reserve() to determine if the
 	 *   user's quota will hold the payload
 	 */
-	int (*instantiate)(struct key *key, const void *data, size_t datalen);
+	int (*instantiate)(struct key *key, struct key_preparsed_payload *prep);
 
 	/* update a key of this type (optional)
 	 * - this method should call key_payload_reserve() to recalculate the
 	 *   quota consumption
 	 * - the key must be locked against read when modifying
 	 */
-	int (*update)(struct key *key, const void *data, size_t datalen);
+	int (*update)(struct key *key, struct key_preparsed_payload *prep);
 
 	/* match a key against a description */
 	int (*match)(const struct key *key, const void *desc);
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 9da7fdd3cd8a..af14cb425164 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -423,14 +423,15 @@ int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len,
 	}
 }
 
-int ceph_key_instantiate(struct key *key, const void *data, size_t datalen)
+int ceph_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	struct ceph_crypto_key *ckey;
+	size_t datalen = prep->datalen;
 	int ret;
 	void *p;
 
 	ret = -EINVAL;
-	if (datalen <= 0 || datalen > 32767 || !data)
+	if (datalen <= 0 || datalen > 32767 || !prep->data)
 		goto err;
 
 	ret = key_payload_reserve(key, datalen);
@@ -443,8 +444,8 @@ int ceph_key_instantiate(struct key *key, const void *data, size_t datalen)
 		goto err;
 
 	/* TODO ceph_crypto_key_decode should really take const input */
-	p = (void *)data;
-	ret = ceph_crypto_key_decode(ckey, &p, (char*)data+datalen);
+	p = (void *)prep->data;
+	ret = ceph_crypto_key_decode(ckey, &p, (char*)prep->data+datalen);
 	if (ret < 0)
 		goto err_ckey;
 
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index d9507dd05818..859ab8b6ec34 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -59,13 +59,13 @@ const struct cred *dns_resolver_cache;
  *        "ip1,ip2,...#foo=bar"
  */
 static int
-dns_resolver_instantiate(struct key *key, const void *_data, size_t datalen)
+dns_resolver_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	struct user_key_payload *upayload;
 	unsigned long derrno;
 	int ret;
-	size_t result_len = 0;
-	const char *data = _data, *end, *opt;
+	size_t datalen = prep->datalen, result_len = 0;
+	const char *data = prep->data, *end, *opt;
 
 	kenter("%%%d,%s,'%*.*s',%zu",
 	       key->serial, key->description,
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index 8b1f9f49960f..106c5a6b1ab2 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -26,8 +26,8 @@
 #include "ar-internal.h"
 
 static int rxrpc_vet_description_s(const char *);
-static int rxrpc_instantiate(struct key *, const void *, size_t);
-static int rxrpc_instantiate_s(struct key *, const void *, size_t);
+static int rxrpc_instantiate(struct key *, struct key_preparsed_payload *);
+static int rxrpc_instantiate_s(struct key *, struct key_preparsed_payload *);
 static void rxrpc_destroy(struct key *);
 static void rxrpc_destroy_s(struct key *);
 static void rxrpc_describe(const struct key *, struct seq_file *);
@@ -678,7 +678,7 @@ error:
  *
  * if no data is provided, then a no-security key is made
  */
-static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen)
+static int rxrpc_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	const struct rxrpc_key_data_v1 *v1;
 	struct rxrpc_key_token *token, **pp;
@@ -686,26 +686,26 @@ static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen)
 	u32 kver;
 	int ret;
 
-	_enter("{%x},,%zu", key_serial(key), datalen);
+	_enter("{%x},,%zu", key_serial(key), prep->datalen);
 
 	/* handle a no-security key */
-	if (!data && datalen == 0)
+	if (!prep->data && prep->datalen == 0)
 		return 0;
 
 	/* determine if the XDR payload format is being used */
-	if (datalen > 7 * 4) {
-		ret = rxrpc_instantiate_xdr(key, data, datalen);
+	if (prep->datalen > 7 * 4) {
+		ret = rxrpc_instantiate_xdr(key, prep->data, prep->datalen);
 		if (ret != -EPROTO)
 			return ret;
 	}
 
 	/* get the key interface version number */
 	ret = -EINVAL;
-	if (datalen <= 4 || !data)
+	if (prep->datalen <= 4 || !prep->data)
 		goto error;
-	memcpy(&kver, data, sizeof(kver));
-	data += sizeof(kver);
-	datalen -= sizeof(kver);
+	memcpy(&kver, prep->data, sizeof(kver));
+	prep->data += sizeof(kver);
+	prep->datalen -= sizeof(kver);
 
 	_debug("KEY I/F VERSION: %u", kver);
 
@@ -715,11 +715,11 @@ static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen)
 
 	/* deal with a version 1 key */
 	ret = -EINVAL;
-	if (datalen < sizeof(*v1))
+	if (prep->datalen < sizeof(*v1))
 		goto error;
 
-	v1 = data;
-	if (datalen != sizeof(*v1) + v1->ticket_length)
+	v1 = prep->data;
+	if (prep->datalen != sizeof(*v1) + v1->ticket_length)
 		goto error;
 
 	_debug("SCIX: %u", v1->security_index);
@@ -784,17 +784,17 @@ error:
  * instantiate a server secret key
  * data should be a pointer to the 8-byte secret key
  */
-static int rxrpc_instantiate_s(struct key *key, const void *data,
-			       size_t datalen)
+static int rxrpc_instantiate_s(struct key *key,
+			       struct key_preparsed_payload *prep)
 {
 	struct crypto_blkcipher *ci;
 
-	_enter("{%x},,%zu", key_serial(key), datalen);
+	_enter("{%x},,%zu", key_serial(key), prep->datalen);
 
-	if (datalen != 8)
+	if (prep->datalen != 8)
 		return -EINVAL;
 
-	memcpy(&key->type_data, data, 8);
+	memcpy(&key->type_data, prep->data, 8);
 
 	ci = crypto_alloc_blkcipher("pcbc(des)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(ci)) {
@@ -802,7 +802,7 @@ static int rxrpc_instantiate_s(struct key *key, const void *data,
 		return PTR_ERR(ci);
 	}
 
-	if (crypto_blkcipher_setkey(ci, data, 8) < 0)
+	if (crypto_blkcipher_setkey(ci, prep->data, 8) < 0)
 		BUG();
 
 	key->payload.data = ci;
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 2d1bb8af7696..9e1e005c7596 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -773,8 +773,8 @@ static int encrypted_init(struct encrypted_key_payload *epayload,
  *
  * On success, return 0. Otherwise return errno.
  */
-static int encrypted_instantiate(struct key *key, const void *data,
-				 size_t datalen)
+static int encrypted_instantiate(struct key *key,
+				 struct key_preparsed_payload *prep)
 {
 	struct encrypted_key_payload *epayload = NULL;
 	char *datablob = NULL;
@@ -782,16 +782,17 @@ static int encrypted_instantiate(struct key *key, const void *data,
 	char *master_desc = NULL;
 	char *decrypted_datalen = NULL;
 	char *hex_encoded_iv = NULL;
+	size_t datalen = prep->datalen;
 	int ret;
 
-	if (datalen <= 0 || datalen > 32767 || !data)
+	if (datalen <= 0 || datalen > 32767 || !prep->data)
 		return -EINVAL;
 
 	datablob = kmalloc(datalen + 1, GFP_KERNEL);
 	if (!datablob)
 		return -ENOMEM;
 	datablob[datalen] = 0;
-	memcpy(datablob, data, datalen);
+	memcpy(datablob, prep->data, datalen);
 	ret = datablob_parse(datablob, &format, &master_desc,
 			     &decrypted_datalen, &hex_encoded_iv);
 	if (ret < 0)
@@ -834,16 +835,17 @@ static void encrypted_rcu_free(struct rcu_head *rcu)
  *
  * On success, return 0. Otherwise return errno.
  */
-static int encrypted_update(struct key *key, const void *data, size_t datalen)
+static int encrypted_update(struct key *key, struct key_preparsed_payload *prep)
 {
 	struct encrypted_key_payload *epayload = key->payload.data;
 	struct encrypted_key_payload *new_epayload;
 	char *buf;
 	char *new_master_desc = NULL;
 	const char *format = NULL;
+	size_t datalen = prep->datalen;
 	int ret = 0;
 
-	if (datalen <= 0 || datalen > 32767 || !data)
+	if (datalen <= 0 || datalen > 32767 || !prep->data)
 		return -EINVAL;
 
 	buf = kmalloc(datalen + 1, GFP_KERNEL);
@@ -851,7 +853,7 @@ static int encrypted_update(struct key *key, const void *data, size_t datalen)
 		return -ENOMEM;
 
 	buf[datalen] = 0;
-	memcpy(buf, data, datalen);
+	memcpy(buf, prep->data, datalen);
 	ret = datablob_parse(buf, &format, &new_master_desc, NULL, NULL);
 	if (ret < 0)
 		goto out;
diff --git a/security/keys/key.c b/security/keys/key.c
index 50d96d4e06f2..1d039af99f50 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -412,8 +412,7 @@ EXPORT_SYMBOL(key_payload_reserve);
  * key_construction_mutex.
  */
 static int __key_instantiate_and_link(struct key *key,
-				      const void *data,
-				      size_t datalen,
+				      struct key_preparsed_payload *prep,
 				      struct key *keyring,
 				      struct key *authkey,
 				      unsigned long *_prealloc)
@@ -431,7 +430,7 @@ static int __key_instantiate_and_link(struct key *key,
 	/* can't instantiate twice */
 	if (!test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) {
 		/* instantiate the key */
-		ret = key->type->instantiate(key, data, datalen);
+		ret = key->type->instantiate(key, prep);
 
 		if (ret == 0) {
 			/* mark the key as being instantiated */
@@ -482,22 +481,37 @@ int key_instantiate_and_link(struct key *key,
 			     struct key *keyring,
 			     struct key *authkey)
 {
+	struct key_preparsed_payload prep;
 	unsigned long prealloc;
 	int ret;
 
+	memset(&prep, 0, sizeof(prep));
+	prep.data = data;
+	prep.datalen = datalen;
+	prep.quotalen = key->type->def_datalen;
+	if (key->type->preparse) {
+		ret = key->type->preparse(&prep);
+		if (ret < 0)
+			goto error;
+	}
+
 	if (keyring) {
 		ret = __key_link_begin(keyring, key->type, key->description,
 				       &prealloc);
 		if (ret < 0)
-			return ret;
+			goto error_free_preparse;
 	}
 
-	ret = __key_instantiate_and_link(key, data, datalen, keyring, authkey,
+	ret = __key_instantiate_and_link(key, &prep, keyring, authkey,
 					 &prealloc);
 
 	if (keyring)
 		__key_link_end(keyring, key->type, prealloc);
 
+error_free_preparse:
+	if (key->type->preparse)
+		key->type->free_preparse(&prep);
+error:
 	return ret;
 }
 
@@ -706,7 +720,7 @@ void key_type_put(struct key_type *ktype)
  * if we get an error.
  */
 static inline key_ref_t __key_update(key_ref_t key_ref,
-				     const void *payload, size_t plen)
+				     struct key_preparsed_payload *prep)
 {
 	struct key *key = key_ref_to_ptr(key_ref);
 	int ret;
@@ -722,7 +736,7 @@ static inline key_ref_t __key_update(key_ref_t key_ref,
 
 	down_write(&key->sem);
 
-	ret = key->type->update(key, payload, plen);
+	ret = key->type->update(key, prep);
 	if (ret == 0)
 		/* updating a negative key instantiates it */
 		clear_bit(KEY_FLAG_NEGATIVE, &key->flags);
@@ -774,6 +788,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 			       unsigned long flags)
 {
 	unsigned long prealloc;
+	struct key_preparsed_payload prep;
 	const struct cred *cred = current_cred();
 	struct key_type *ktype;
 	struct key *keyring, *key = NULL;
@@ -789,8 +804,9 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	}
 
 	key_ref = ERR_PTR(-EINVAL);
-	if (!ktype->match || !ktype->instantiate)
-		goto error_2;
+	if (!ktype->match || !ktype->instantiate ||
+	    (!description && !ktype->preparse))
+		goto error_put_type;
 
 	keyring = key_ref_to_ptr(keyring_ref);
 
@@ -798,18 +814,37 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 
 	key_ref = ERR_PTR(-ENOTDIR);
 	if (keyring->type != &key_type_keyring)
-		goto error_2;
+		goto error_put_type;
+
+	memset(&prep, 0, sizeof(prep));
+	prep.data = payload;
+	prep.datalen = plen;
+	prep.quotalen = ktype->def_datalen;
+	if (ktype->preparse) {
+		ret = ktype->preparse(&prep);
+		if (ret < 0) {
+			key_ref = ERR_PTR(ret);
+			goto error_put_type;
+		}
+		if (!description)
+			description = prep.description;
+		key_ref = ERR_PTR(-EINVAL);
+		if (!description)
+			goto error_free_prep;
+	}
 
 	ret = __key_link_begin(keyring, ktype, description, &prealloc);
-	if (ret < 0)
-		goto error_2;
+	if (ret < 0) {
+		key_ref = ERR_PTR(ret);
+		goto error_free_prep;
+	}
 
 	/* if we're going to allocate a new key, we're going to have
 	 * to modify the keyring */
 	ret = key_permission(keyring_ref, KEY_WRITE);
 	if (ret < 0) {
 		key_ref = ERR_PTR(ret);
-		goto error_3;
+		goto error_link_end;
 	}
 
 	/* if it's possible to update this type of key, search for an existing
@@ -840,25 +875,27 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 			perm, flags);
 	if (IS_ERR(key)) {
 		key_ref = ERR_CAST(key);
-		goto error_3;
+		goto error_link_end;
 	}
 
 	/* instantiate it and link it into the target keyring */
-	ret = __key_instantiate_and_link(key, payload, plen, keyring, NULL,
-					 &prealloc);
+	ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &prealloc);
 	if (ret < 0) {
 		key_put(key);
 		key_ref = ERR_PTR(ret);
-		goto error_3;
+		goto error_link_end;
 	}
 
 	key_ref = make_key_ref(key, is_key_possessed(keyring_ref));
 
- error_3:
+error_link_end:
 	__key_link_end(keyring, ktype, prealloc);
- error_2:
+error_free_prep:
+	if (ktype->preparse)
+		ktype->free_preparse(&prep);
+error_put_type:
 	key_type_put(ktype);
- error:
+error:
 	return key_ref;
 
  found_matching_key:
@@ -866,10 +903,9 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	 * - we can drop the locks first as we have the key pinned
 	 */
 	__key_link_end(keyring, ktype, prealloc);
-	key_type_put(ktype);
 
-	key_ref = __key_update(key_ref, payload, plen);
-	goto error;
+	key_ref = __key_update(key_ref, &prep);
+	goto error_free_prep;
 }
 EXPORT_SYMBOL(key_create_or_update);
 
@@ -888,6 +924,7 @@ EXPORT_SYMBOL(key_create_or_update);
  */
 int key_update(key_ref_t key_ref, const void *payload, size_t plen)
 {
+	struct key_preparsed_payload prep;
 	struct key *key = key_ref_to_ptr(key_ref);
 	int ret;
 
@@ -900,18 +937,31 @@ int key_update(key_ref_t key_ref, const void *payload, size_t plen)
 
 	/* attempt to update it if supported */
 	ret = -EOPNOTSUPP;
-	if (key->type->update) {
-		down_write(&key->sem);
-
-		ret = key->type->update(key, payload, plen);
-		if (ret == 0)
-			/* updating a negative key instantiates it */
-			clear_bit(KEY_FLAG_NEGATIVE, &key->flags);
+	if (!key->type->update)
+		goto error;
 
-		up_write(&key->sem);
+	memset(&prep, 0, sizeof(prep));
+	prep.data = payload;
+	prep.datalen = plen;
+	prep.quotalen = key->type->def_datalen;
+	if (key->type->preparse) {
+		ret = key->type->preparse(&prep);
+		if (ret < 0)
+			goto error;
 	}
 
- error:
+	down_write(&key->sem);
+
+	ret = key->type->update(key, &prep);
+	if (ret == 0)
+		/* updating a negative key instantiates it */
+		clear_bit(KEY_FLAG_NEGATIVE, &key->flags);
+
+	up_write(&key->sem);
+
+	if (key->type->preparse)
+		key->type->free_preparse(&prep);
+error:
 	return ret;
 }
 EXPORT_SYMBOL(key_update);
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 3364fbf46807..505d40be196c 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -46,6 +46,9 @@ static int key_get_type_from_user(char *type,
  * Extract the description of a new key from userspace and either add it as a
  * new key to the specified keyring or update a matching key in that keyring.
  *
+ * If the description is NULL or an empty string, the key type is asked to
+ * generate one from the payload.
+ *
  * The keyring must be writable so that we can attach the key to it.
  *
  * If successful, the new key's serial number is returned, otherwise an error
@@ -72,10 +75,17 @@ SYSCALL_DEFINE5(add_key, const char __user *, _type,
 	if (ret < 0)
 		goto error;
 
-	description = strndup_user(_description, PAGE_SIZE);
-	if (IS_ERR(description)) {
-		ret = PTR_ERR(description);
-		goto error;
+	description = NULL;
+	if (_description) {
+		description = strndup_user(_description, PAGE_SIZE);
+		if (IS_ERR(description)) {
+			ret = PTR_ERR(description);
+			goto error;
+		}
+		if (!*description) {
+			kfree(description);
+			description = NULL;
+		}
 	}
 
 	/* pull the payload in if one was supplied */
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 81e7852d281d..f04d8cf81f3c 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -66,7 +66,7 @@ static inline unsigned keyring_hash(const char *desc)
  * operations.
  */
 static int keyring_instantiate(struct key *keyring,
-			       const void *data, size_t datalen);
+			       struct key_preparsed_payload *prep);
 static int keyring_match(const struct key *keyring, const void *criterion);
 static void keyring_revoke(struct key *keyring);
 static void keyring_destroy(struct key *keyring);
@@ -121,12 +121,12 @@ static void keyring_publish_name(struct key *keyring)
  * Returns 0 on success, -EINVAL if given any data.
  */
 static int keyring_instantiate(struct key *keyring,
-			       const void *data, size_t datalen)
+			       struct key_preparsed_payload *prep)
 {
 	int ret;
 
 	ret = -EINVAL;
-	if (datalen == 0) {
+	if (prep->datalen == 0) {
 		/* make the keyring available by name if it has one */
 		keyring_publish_name(keyring);
 		ret = 0;
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 60d4e3f5e4bb..85730d5a5a59 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -19,7 +19,8 @@
 #include <asm/uaccess.h>
 #include "internal.h"
 
-static int request_key_auth_instantiate(struct key *, const void *, size_t);
+static int request_key_auth_instantiate(struct key *,
+					struct key_preparsed_payload *);
 static void request_key_auth_describe(const struct key *, struct seq_file *);
 static void request_key_auth_revoke(struct key *);
 static void request_key_auth_destroy(struct key *);
@@ -42,10 +43,9 @@ struct key_type key_type_request_key_auth = {
  * Instantiate a request-key authorisation key.
  */
 static int request_key_auth_instantiate(struct key *key,
-					const void *data,
-					size_t datalen)
+					struct key_preparsed_payload *prep)
 {
-	key->payload.data = (struct request_key_auth *) data;
+	key->payload.data = (struct request_key_auth *)prep->data;
 	return 0;
 }
 
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index 2d5d041f2049..42036c7a0856 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -927,22 +927,23 @@ static struct trusted_key_payload *trusted_payload_alloc(struct key *key)
  *
  * On success, return 0. Otherwise return errno.
  */
-static int trusted_instantiate(struct key *key, const void *data,
-			       size_t datalen)
+static int trusted_instantiate(struct key *key,
+			       struct key_preparsed_payload *prep)
 {
 	struct trusted_key_payload *payload = NULL;
 	struct trusted_key_options *options = NULL;
+	size_t datalen = prep->datalen;
 	char *datablob;
 	int ret = 0;
 	int key_cmd;
 
-	if (datalen <= 0 || datalen > 32767 || !data)
+	if (datalen <= 0 || datalen > 32767 || !prep->data)
 		return -EINVAL;
 
 	datablob = kmalloc(datalen + 1, GFP_KERNEL);
 	if (!datablob)
 		return -ENOMEM;
-	memcpy(datablob, data, datalen);
+	memcpy(datablob, prep->data, datalen);
 	datablob[datalen] = '\0';
 
 	options = trusted_options_alloc();
@@ -1011,17 +1012,18 @@ static void trusted_rcu_free(struct rcu_head *rcu)
 /*
  * trusted_update - reseal an existing key with new PCR values
  */
-static int trusted_update(struct key *key, const void *data, size_t datalen)
+static int trusted_update(struct key *key, struct key_preparsed_payload *prep)
 {
 	struct trusted_key_payload *p = key->payload.data;
 	struct trusted_key_payload *new_p;
 	struct trusted_key_options *new_o;
+	size_t datalen = prep->datalen;
 	char *datablob;
 	int ret = 0;
 
 	if (!p->migratable)
 		return -EPERM;
-	if (datalen <= 0 || datalen > 32767 || !data)
+	if (datalen <= 0 || datalen > 32767 || !prep->data)
 		return -EINVAL;
 
 	datablob = kmalloc(datalen + 1, GFP_KERNEL);
@@ -1038,7 +1040,7 @@ static int trusted_update(struct key *key, const void *data, size_t datalen)
 		goto out;
 	}
 
-	memcpy(datablob, data, datalen);
+	memcpy(datablob, prep->data, datalen);
 	datablob[datalen] = '\0';
 	ret = datablob_parse(datablob, new_p, new_o);
 	if (ret != Opt_update) {
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index c7660a25a3e4..55dc88939185 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -58,13 +58,14 @@ EXPORT_SYMBOL_GPL(key_type_logon);
 /*
  * instantiate a user defined key
  */
-int user_instantiate(struct key *key, const void *data, size_t datalen)
+int user_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	struct user_key_payload *upayload;
+	size_t datalen = prep->datalen;
 	int ret;
 
 	ret = -EINVAL;
-	if (datalen <= 0 || datalen > 32767 || !data)
+	if (datalen <= 0 || datalen > 32767 || !prep->data)
 		goto error;
 
 	ret = key_payload_reserve(key, datalen);
@@ -78,7 +79,7 @@ int user_instantiate(struct key *key, const void *data, size_t datalen)
 
 	/* attach the data */
 	upayload->datalen = datalen;
-	memcpy(upayload->data, data, datalen);
+	memcpy(upayload->data, prep->data, datalen);
 	rcu_assign_keypointer(key, upayload);
 	ret = 0;
 
@@ -92,13 +93,14 @@ EXPORT_SYMBOL_GPL(user_instantiate);
  * update a user defined key
  * - the key's semaphore is write-locked
  */
-int user_update(struct key *key, const void *data, size_t datalen)
+int user_update(struct key *key, struct key_preparsed_payload *prep)
 {
 	struct user_key_payload *upayload, *zap;
+	size_t datalen = prep->datalen;
 	int ret;
 
 	ret = -EINVAL;
-	if (datalen <= 0 || datalen > 32767 || !data)
+	if (datalen <= 0 || datalen > 32767 || !prep->data)
 		goto error;
 
 	/* construct a replacement payload */
@@ -108,7 +110,7 @@ int user_update(struct key *key, const void *data, size_t datalen)
 		goto error;
 
 	upayload->datalen = datalen;
-	memcpy(upayload->data, data, datalen);
+	memcpy(upayload->data, prep->data, datalen);
 
 	/* check the quota and attach the new data */
 	zap = upayload;
-- 
cgit v1.2.3-55-g7522


From 015b85a067bd9949756e49b01b70c820d31316d7 Mon Sep 17 00:00:00 2001
From: Adam Jackson
Date: Tue, 18 Sep 2012 10:58:47 -0400
Subject: drm: Export drm_probe_ddc()

Tested-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Adam Jackson <ajax@redhat.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_edid.c | 3 ++-
 include/drm/drm_crtc.h     | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 289c9b18c0d3..d738a38e2329 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -395,13 +395,14 @@ out:
  * \param adapter : i2c device adaptor
  * \return 1 on success
  */
-static bool
+bool
 drm_probe_ddc(struct i2c_adapter *adapter)
 {
 	unsigned char out;
 
 	return (drm_do_probe_ddc_edid(adapter, &out, 0, 1) == 0);
 }
+EXPORT_SYMBOL(drm_probe_ddc);
 
 /**
  * drm_get_edid - get EDID data, if available
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index eb91d520ce0b..07e2956d9644 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -861,6 +861,7 @@ extern char *drm_get_tv_subconnector_name(int val);
 extern char *drm_get_tv_select_name(int val);
 extern void drm_fb_release(struct drm_file *file_priv);
 extern int drm_mode_group_init_legacy_group(struct drm_device *dev, struct drm_mode_group *group);
+extern bool drm_probe_ddc(struct i2c_adapter *adapter);
 extern struct edid *drm_get_edid(struct drm_connector *connector,
 				 struct i2c_adapter *adapter);
 extern int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid);
-- 
cgit v1.2.3-55-g7522


From e89861dfa3ed0d8e9d184becf25aebea14e98372 Mon Sep 17 00:00:00 2001
From: Adam Jackson
Date: Tue, 18 Sep 2012 10:58:48 -0400
Subject: drm/dp: Update DPCD defines

Sources: DP, eDP, and DP interop specs, and a VESA slideshow about DP
1.2 for the MST bits.

Tested-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Adam Jackson <ajax@redhat.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_dp_helper.h | 60 ++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 56 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 1744b18c06b3..f9888c3cb955 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -69,16 +69,30 @@
 /* 10b = TMDS or HDMI */
 /* 11b = Other */
 # define DP_FORMAT_CONVERSION               (1 << 3)
+# define DP_DETAILED_CAP_INFO_AVAILABLE	    (1 << 4)
 
 #define DP_MAIN_LINK_CHANNEL_CODING         0x006
 
 #define DP_DOWN_STREAM_PORT_COUNT	    0x007
-#define  DP_PORT_COUNT_MASK		    0x0f
-#define  DP_OUI_SUPPORT			    (1 << 7)
+# define DP_PORT_COUNT_MASK		    0x0f
+# define DP_MSA_TIMING_PAR_IGNORED	    (1 << 6)
+# define DP_OUI_SUPPORT			    (1 << 7)
+
+#define DP_I2C_SPEED_CAP		    0x00c
+# define DP_I2C_SPEED_1K		    0x01
+# define DP_I2C_SPEED_5K		    0x02
+# define DP_I2C_SPEED_10K		    0x04
+# define DP_I2C_SPEED_100K		    0x08
+# define DP_I2C_SPEED_400K		    0x10
+# define DP_I2C_SPEED_1M		    0x20
 
 #define DP_EDP_CONFIGURATION_CAP            0x00d
 #define DP_TRAINING_AUX_RD_INTERVAL         0x00e
 
+/* Multiple stream transport */
+#define DP_MSTM_CAP			    0x021
+# define DP_MST_CAP			    (1 << 0)
+
 #define DP_PSR_SUPPORT                      0x070
 # define DP_PSR_IS_SUPPORTED                1
 #define DP_PSR_CAPS                         0x071
@@ -93,6 +107,31 @@
 # define DP_PSR_SETUP_TIME_MASK             (7 << 1)
 # define DP_PSR_SETUP_TIME_SHIFT            1
 
+/*
+ * 0x80-0x8f describe downstream port capabilities, but there are two layouts
+ * based on whether DP_DETAILED_CAP_INFO_AVAILABLE was set.  If it was not,
+ * each port's descriptor is one byte wide.  If it was set, each port's is
+ * four bytes wide, starting with the one byte from the base info.  As of
+ * DP interop v1.1a only VGA defines additional detail.
+ */
+
+/* offset 0 */
+#define DP_DOWNSTREAM_PORT_0		    0x80
+# define DP_DS_PORT_TYPE_MASK		    (7 << 0)
+# define DP_DS_PORT_TYPE_DP		    0
+# define DP_DS_PORT_TYPE_VGA		    1
+# define DP_DS_PORT_TYPE_DVI		    2
+# define DP_DS_PORT_TYPE_HDMI		    3
+# define DP_DS_PORT_TYPE_NON_EDID	    4
+# define DP_DS_PORT_HPD			    (1 << 3)
+/* offset 1 for VGA is maximum megapixels per second / 8 */
+/* offset 2 */
+# define DP_DS_VGA_MAX_BPC_MASK		    (3 << 0)
+# define DP_DS_VGA_8BPC			    0
+# define DP_DS_VGA_10BPC		    1
+# define DP_DS_VGA_12BPC		    2
+# define DP_DS_VGA_16BPC		    3
+
 /* link configuration */
 #define	DP_LINK_BW_SET		            0x100
 # define DP_LINK_BW_1_62		    0x06
@@ -148,24 +187,37 @@
 
 #define DP_DOWNSPREAD_CTRL		    0x107
 # define DP_SPREAD_AMP_0_5		    (1 << 4)
+# define DP_MSA_TIMING_PAR_IGNORE_EN	    (1 << 7)
 
 #define DP_MAIN_LINK_CHANNEL_CODING_SET	    0x108
 # define DP_SET_ANSI_8B10B		    (1 << 0)
 
+#define DP_I2C_SPEED_CONTROL_STATUS	    0x109
+/* bitmask as for DP_I2C_SPEED_CAP */
+
+#define DP_EDP_CONFIGURATION_SET            0x10a
+
+#define DP_MSTM_CTRL			    0x111
+# define DP_MST_EN			    (1 << 0)
+# define DP_UP_REQ_EN			    (1 << 1)
+# define DP_UPSTREAM_IS_SRC		    (1 << 2)
+
 #define DP_PSR_EN_CFG			    0x170
 # define DP_PSR_ENABLE			    (1 << 0)
 # define DP_PSR_MAIN_LINK_ACTIVE	    (1 << 1)
 # define DP_PSR_CRC_VERIFICATION	    (1 << 2)
 # define DP_PSR_FRAME_CAPTURE		    (1 << 3)
 
+#define DP_SINK_COUNT			    0x200
+# define DP_SINK_COUNT_MASK		    (31 << 0)
+# define DP_SINK_CP_READY		    (1 << 6)
+
 #define DP_DEVICE_SERVICE_IRQ_VECTOR	    0x201
 # define DP_REMOTE_CONTROL_COMMAND_PENDING  (1 << 0)
 # define DP_AUTOMATED_TEST_REQUEST	    (1 << 1)
 # define DP_CP_IRQ			    (1 << 2)
 # define DP_SINK_SPECIFIC_IRQ		    (1 << 6)
 
-#define DP_EDP_CONFIGURATION_SET            0x10a
-
 #define DP_LANE0_1_STATUS		    0x202
 #define DP_LANE2_3_STATUS		    0x203
 # define DP_LANE_CR_DONE		    (1 << 0)
-- 
cgit v1.2.3-55-g7522


From a477f4fcbdd48837610974b0d025af1d46051a57 Mon Sep 17 00:00:00 2001
From: Adam Jackson
Date: Thu, 20 Sep 2012 16:42:44 -0400
Subject: drm/dp: Document DP spec versions for various DPCD registers

Note with a comment anything newer than DP 1.1a.

Obviously this needs some work still...

Signed-off-by: Adam Jackson <ajax@redhat.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_dp_helper.h | 52 ++++++++++++++++++++++++++++-----------------
 1 file changed, 32 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index f9888c3cb955..38ffcb4332aa 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -26,7 +26,19 @@
 #include <linux/types.h>
 #include <linux/i2c.h>
 
-/* From the VESA DisplayPort spec */
+/*
+ * Unless otherwise noted, all values are from the DP 1.1a spec.  Note that
+ * DP and DPCD versions are independent.  Differences from 1.0 are not noted,
+ * 1.0 devices basically don't exist in the wild.
+ *
+ * Abbreviations, in chronological order:
+ *
+ * eDP: Embedded DisplayPort version 1
+ * DPI: DisplayPort Interoperability Guideline v1.1a
+ * 1.2: DisplayPort 1.2
+ *
+ * 1.2 formally includes both eDP and DPI definitions.
+ */
 
 #define AUX_NATIVE_WRITE	0x8
 #define AUX_NATIVE_READ		0x9
@@ -53,7 +65,7 @@
 
 #define DP_MAX_LANE_COUNT                   0x002
 # define DP_MAX_LANE_COUNT_MASK		    0x1f
-# define DP_TPS3_SUPPORTED		    (1 << 6)
+# define DP_TPS3_SUPPORTED		    (1 << 6) /* 1.2 */
 # define DP_ENHANCED_FRAME_CAP		    (1 << 7)
 
 #define DP_MAX_DOWNSPREAD                   0x003
@@ -69,16 +81,16 @@
 /* 10b = TMDS or HDMI */
 /* 11b = Other */
 # define DP_FORMAT_CONVERSION               (1 << 3)
-# define DP_DETAILED_CAP_INFO_AVAILABLE	    (1 << 4)
+# define DP_DETAILED_CAP_INFO_AVAILABLE	    (1 << 4) /* DPI */
 
 #define DP_MAIN_LINK_CHANNEL_CODING         0x006
 
 #define DP_DOWN_STREAM_PORT_COUNT	    0x007
 # define DP_PORT_COUNT_MASK		    0x0f
-# define DP_MSA_TIMING_PAR_IGNORED	    (1 << 6)
+# define DP_MSA_TIMING_PAR_IGNORED	    (1 << 6) /* eDP */
 # define DP_OUI_SUPPORT			    (1 << 7)
 
-#define DP_I2C_SPEED_CAP		    0x00c
+#define DP_I2C_SPEED_CAP		    0x00c    /* DPI */
 # define DP_I2C_SPEED_1K		    0x01
 # define DP_I2C_SPEED_5K		    0x02
 # define DP_I2C_SPEED_10K		    0x04
@@ -86,16 +98,16 @@
 # define DP_I2C_SPEED_400K		    0x10
 # define DP_I2C_SPEED_1M		    0x20
 
-#define DP_EDP_CONFIGURATION_CAP            0x00d
-#define DP_TRAINING_AUX_RD_INTERVAL         0x00e
+#define DP_EDP_CONFIGURATION_CAP            0x00d   /* XXX 1.2? */
+#define DP_TRAINING_AUX_RD_INTERVAL         0x00e   /* XXX 1.2? */
 
 /* Multiple stream transport */
-#define DP_MSTM_CAP			    0x021
+#define DP_MSTM_CAP			    0x021   /* 1.2 */
 # define DP_MST_CAP			    (1 << 0)
 
-#define DP_PSR_SUPPORT                      0x070
+#define DP_PSR_SUPPORT                      0x070   /* XXX 1.2? */
 # define DP_PSR_IS_SUPPORTED                1
-#define DP_PSR_CAPS                         0x071
+#define DP_PSR_CAPS                         0x071   /* XXX 1.2? */
 # define DP_PSR_NO_TRAIN_ON_EXIT            1
 # define DP_PSR_SETUP_TIME_330              (0 << 1)
 # define DP_PSR_SETUP_TIME_275              (1 << 1)
@@ -136,7 +148,7 @@
 #define	DP_LINK_BW_SET		            0x100
 # define DP_LINK_BW_1_62		    0x06
 # define DP_LINK_BW_2_7			    0x0a
-# define DP_LINK_BW_5_4			    0x14
+# define DP_LINK_BW_5_4			    0x14    /* 1.2 */
 
 #define DP_LANE_COUNT_SET	            0x101
 # define DP_LANE_COUNT_MASK		    0x0f
@@ -146,7 +158,7 @@
 # define DP_TRAINING_PATTERN_DISABLE	    0
 # define DP_TRAINING_PATTERN_1		    1
 # define DP_TRAINING_PATTERN_2		    2
-# define DP_TRAINING_PATTERN_3		    3
+# define DP_TRAINING_PATTERN_3		    3	    /* 1.2 */
 # define DP_TRAINING_PATTERN_MASK	    0x3
 
 # define DP_LINK_QUAL_PATTERN_DISABLE	    (0 << 2)
@@ -187,22 +199,22 @@
 
 #define DP_DOWNSPREAD_CTRL		    0x107
 # define DP_SPREAD_AMP_0_5		    (1 << 4)
-# define DP_MSA_TIMING_PAR_IGNORE_EN	    (1 << 7)
+# define DP_MSA_TIMING_PAR_IGNORE_EN	    (1 << 7) /* eDP */
 
 #define DP_MAIN_LINK_CHANNEL_CODING_SET	    0x108
 # define DP_SET_ANSI_8B10B		    (1 << 0)
 
-#define DP_I2C_SPEED_CONTROL_STATUS	    0x109
+#define DP_I2C_SPEED_CONTROL_STATUS	    0x109   /* DPI */
 /* bitmask as for DP_I2C_SPEED_CAP */
 
-#define DP_EDP_CONFIGURATION_SET            0x10a
+#define DP_EDP_CONFIGURATION_SET            0x10a   /* XXX 1.2? */
 
-#define DP_MSTM_CTRL			    0x111
+#define DP_MSTM_CTRL			    0x111   /* 1.2 */
 # define DP_MST_EN			    (1 << 0)
 # define DP_UP_REQ_EN			    (1 << 1)
 # define DP_UPSTREAM_IS_SRC		    (1 << 2)
 
-#define DP_PSR_EN_CFG			    0x170
+#define DP_PSR_EN_CFG			    0x170   /* XXX 1.2? */
 # define DP_PSR_ENABLE			    (1 << 0)
 # define DP_PSR_MAIN_LINK_ACTIVE	    (1 << 1)
 # define DP_PSR_CRC_VERIFICATION	    (1 << 2)
@@ -277,14 +289,14 @@
 # define DP_SET_POWER_D0                    0x1
 # define DP_SET_POWER_D3                    0x2
 
-#define DP_PSR_ERROR_STATUS                 0x2006
+#define DP_PSR_ERROR_STATUS                 0x2006  /* XXX 1.2? */
 # define DP_PSR_LINK_CRC_ERROR              (1 << 0)
 # define DP_PSR_RFB_STORAGE_ERROR           (1 << 1)
 
-#define DP_PSR_ESI                          0x2007
+#define DP_PSR_ESI                          0x2007  /* XXX 1.2? */
 # define DP_PSR_CAPS_CHANGE                 (1 << 0)
 
-#define DP_PSR_STATUS                       0x2008
+#define DP_PSR_STATUS                       0x2008  /* XXX 1.2? */
 # define DP_PSR_SINK_INACTIVE               0
 # define DP_PSR_SINK_ACTIVE_SRC_SYNCED      1
 # define DP_PSR_SINK_ACTIVE_RFB             2
-- 
cgit v1.2.3-55-g7522


From da131a46268bf2a67e7b7fa137a90a1279866367 Mon Sep 17 00:00:00 2001
From: Adam Jackson
Date: Thu, 20 Sep 2012 16:42:45 -0400
Subject: drm/dp: Make sink count DP 1.2 aware

Signed-off-by: Adam Jackson <ajax@redhat.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_dp.c | 9 ++++-----
 include/drm/drm_dp_helper.h     | 3 ++-
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 4f2a38181491..c63f54e84847 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -2101,13 +2101,12 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp)
 	/* If we're HPD-aware, SINK_COUNT changes dynamically */
 	hpd = !!(intel_dp->downstream_ports[0] & DP_DS_PORT_HPD);
 	if (hpd) {
-		uint8_t sink_count;
+		uint8_t reg;
 		if (!intel_dp_aux_native_read_retry(intel_dp, DP_SINK_COUNT,
-						    &sink_count, 1))
+						    &reg, 1))
 			return connector_status_unknown;
-		sink_count &= DP_SINK_COUNT_MASK;
-		return sink_count ? connector_status_connected
-				  : connector_status_disconnected;
+		return DP_GET_SINK_COUNT(reg) ? connector_status_connected
+					      : connector_status_disconnected;
 	}
 
 	/* If no HPD, poke DDC gently */
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 38ffcb4332aa..fe061489f91f 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -221,7 +221,8 @@
 # define DP_PSR_FRAME_CAPTURE		    (1 << 3)
 
 #define DP_SINK_COUNT			    0x200
-# define DP_SINK_COUNT_MASK		    (31 << 0)
+/* prior to 1.2 bit 7 was reserved mbz */
+# define DP_GET_SINK_COUNT(x)		    ((((x) & 0x80) >> 1) | ((x) & 0x3f))
 # define DP_SINK_CP_READY		    (1 << 6)
 
 #define DP_DEVICE_SERVICE_IRQ_VECTOR	    0x201
-- 
cgit v1.2.3-55-g7522


From b078b564292ab87cdf4a58de3c2f86d4300a161c Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:06 +0300
Subject: Bluetooth: Add HCI logical link cmds definitions

Add a few definitions to hci.h

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h | 36 +++++++++++++++++++++++++++++++++++-
 1 file changed, 35 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 76b2b6bdcf36..4be26abf6dad 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -556,12 +556,46 @@ struct hci_cp_accept_phy_link {
 	__u8     key[HCI_AMP_LINK_KEY_SIZE];
 } __packed;
 
-#define HCI_OP_DISCONN_PHY_LINK	0x0437
+#define HCI_OP_DISCONN_PHY_LINK		0x0437
 struct hci_cp_disconn_phy_link {
 	__u8     phy_handle;
 	__u8     reason;
 } __packed;
 
+struct ext_flow_spec {
+	__u8       id;
+	__u8       stype;
+	__le16     msdu;
+	__le32     sdu_itime;
+	__le32     acc_lat;
+	__le32     flush_to;
+} __packed;
+
+#define HCI_OP_CREATE_LOGICAL_LINK	0x0438
+#define HCI_OP_ACCEPT_LOGICAL_LINK	0x0439
+struct hci_cp_create_accept_logical_link {
+	__u8                  phy_handle;
+	struct ext_flow_spec  tx_flow_spec;
+	struct ext_flow_spec  rx_flow_spec;
+} __packed;
+
+#define HCI_OP_DISCONN_LOGICAL_LINK	0x043a
+struct hci_cp_disconn_logical_link {
+	__le16   log_handle;
+} __packed;
+
+#define HCI_OP_LOGICAL_LINK_CANCEL	0x043b
+struct hci_cp_logical_link_cancel {
+	__u8     phy_handle;
+	__u8     flow_spec_id;
+} __packed;
+
+struct hci_rp_logical_link_cancel {
+	__u8     status;
+	__u8     phy_handle;
+	__u8     flow_spec_id;
+} __packed;
+
 #define HCI_OP_SNIFF_MODE		0x0803
 struct hci_cp_sniff_mode {
 	__le16   handle;
-- 
cgit v1.2.3-55-g7522


From f97268fccdd4e76462195216fcab621b8d4a6cd1 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:07 +0300
Subject: Bluetooth: A2MP: Create amp_mgr global list

Create amp_mgr_list global list which will be used by different
hci devices to find amp_mgr.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/a2mp.h | 10 ++++++++++
 net/bluetooth/a2mp.c         | 29 +++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/a2mp.h b/include/net/bluetooth/a2mp.h
index 6a76e0a0705e..316c1c803676 100644
--- a/include/net/bluetooth/a2mp.h
+++ b/include/net/bluetooth/a2mp.h
@@ -19,12 +19,18 @@
 
 #define A2MP_FEAT_EXT	0x8000
 
+enum amp_mgr_state {
+	READ_LOC_AMP_INFO,
+};
+
 struct amp_mgr {
+	struct list_head	list;
 	struct l2cap_conn	*l2cap_conn;
 	struct l2cap_chan	*a2mp_chan;
 	struct kref		kref;
 	__u8			ident;
 	__u8			handle;
+	enum amp_mgr_state	state;
 	unsigned long		flags;
 };
 
@@ -118,9 +124,13 @@ struct a2mp_physlink_rsp {
 #define A2MP_STATUS_PHYS_LINK_EXISTS		0x05
 #define A2MP_STATUS_SECURITY_VIOLATION		0x06
 
+extern struct list_head amp_mgr_list;
+extern struct mutex amp_mgr_list_lock;
+
 void amp_mgr_get(struct amp_mgr *mgr);
 int amp_mgr_put(struct amp_mgr *mgr);
 struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
 				       struct sk_buff *skb);
+struct amp_mgr *amp_mgr_lookup_by_state(u8 state);
 
 #endif /* __A2MP_H */
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 0760d1fed6f0..3f930608ecfa 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -17,6 +17,10 @@
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/a2mp.h>
 
+/* Global AMP Manager list */
+LIST_HEAD(amp_mgr_list);
+DEFINE_MUTEX(amp_mgr_list_lock);
+
 /* A2MP build & send command helper functions */
 static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data)
 {
@@ -516,6 +520,10 @@ static void amp_mgr_destroy(struct kref *kref)
 
 	BT_DBG("mgr %p", mgr);
 
+	mutex_lock(&amp_mgr_list_lock);
+	list_del(&mgr->list);
+	mutex_unlock(&amp_mgr_list_lock);
+
 	kfree(mgr);
 }
 
@@ -552,6 +560,10 @@ static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn)
 
 	kref_init(&mgr->kref);
 
+	mutex_lock(&amp_mgr_list_lock);
+	list_add(&mgr->list, &amp_mgr_list);
+	mutex_unlock(&amp_mgr_list_lock);
+
 	return mgr;
 }
 
@@ -570,3 +582,20 @@ struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
 
 	return mgr->a2mp_chan;
 }
+
+struct amp_mgr *amp_mgr_lookup_by_state(u8 state)
+{
+	struct amp_mgr *mgr;
+
+	mutex_lock(&amp_mgr_list_lock);
+	list_for_each_entry(mgr, &amp_mgr_list, list) {
+		if (mgr->state == state) {
+			amp_mgr_get(mgr);
+			mutex_unlock(&amp_mgr_list_lock);
+			return mgr;
+		}
+	}
+	mutex_unlock(&amp_mgr_list_lock);
+
+	return NULL;
+}
-- 
cgit v1.2.3-55-g7522


From 8e2a0d92c56ec6955526a8b60838c9b00f70540d Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:08 +0300
Subject: Bluetooth: AMP: Use HCI cmd to Read AMP Info

When receiving A2MP Get Info Request execute Read Local AMP Info HCI
command to AMP controller with function to be executed upon receiving
command complete event. Function will handle A2MP Get Info Response.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/a2mp.h |  2 ++
 net/bluetooth/a2mp.c         | 57 +++++++++++++++++++++++++++++++-------------
 net/bluetooth/hci_event.c    |  6 ++++-
 3 files changed, 48 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/a2mp.h b/include/net/bluetooth/a2mp.h
index 316c1c803676..af594685112e 100644
--- a/include/net/bluetooth/a2mp.h
+++ b/include/net/bluetooth/a2mp.h
@@ -132,5 +132,7 @@ int amp_mgr_put(struct amp_mgr *mgr);
 struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
 				       struct sk_buff *skb);
 struct amp_mgr *amp_mgr_lookup_by_state(u8 state);
+void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data);
+void a2mp_send_getinfo_rsp(struct hci_dev *hdev);
 
 #endif /* __A2MP_H */
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 3f930608ecfa..0e97b3b42ab1 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -41,8 +41,7 @@ static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data)
 	return cmd;
 }
 
-static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len,
-		      void *data)
+void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data)
 {
 	struct l2cap_chan *chan = mgr->a2mp_chan;
 	struct a2mp_cmd *cmd;
@@ -185,7 +184,6 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb,
 			    struct a2mp_cmd *hdr)
 {
 	struct a2mp_info_req *req  = (void *) skb->data;
-	struct a2mp_info_rsp rsp;
 	struct hci_dev *hdev;
 
 	if (le16_to_cpu(hdr->len) < sizeof(*req))
@@ -193,23 +191,23 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	BT_DBG("id %d", req->id);
 
-	rsp.id = req->id;
-	rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
-
 	hdev = hci_dev_get(req->id);
-	if (hdev && hdev->amp_type != HCI_BREDR) {
-		rsp.status = 0;
-		rsp.total_bw = cpu_to_le32(hdev->amp_total_bw);
-		rsp.max_bw = cpu_to_le32(hdev->amp_max_bw);
-		rsp.min_latency = cpu_to_le32(hdev->amp_min_latency);
-		rsp.pal_cap = cpu_to_le16(hdev->amp_pal_cap);
-		rsp.assoc_size = cpu_to_le16(hdev->amp_assoc_size);
+	if (!hdev) {
+		struct a2mp_info_rsp rsp;
+
+		rsp.id = req->id;
+		rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
+
+		a2mp_send(mgr, A2MP_GETINFO_RSP, hdr->ident, sizeof(rsp),
+			  &rsp);
 	}
 
-	if (hdev)
-		hci_dev_put(hdev);
+	if (hdev->dev_type != HCI_BREDR) {
+		mgr->state = READ_LOC_AMP_INFO;
+		hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL);
+	}
 
-	a2mp_send(mgr, A2MP_GETINFO_RSP, hdr->ident, sizeof(rsp), &rsp);
+	hci_dev_put(hdev);
 
 	skb_pull(skb, sizeof(*req));
 	return 0;
@@ -599,3 +597,30 @@ struct amp_mgr *amp_mgr_lookup_by_state(u8 state)
 
 	return NULL;
 }
+
+void a2mp_send_getinfo_rsp(struct hci_dev *hdev)
+{
+	struct amp_mgr *mgr;
+	struct a2mp_info_rsp rsp;
+
+	mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_INFO);
+	if (!mgr)
+		return;
+
+	BT_DBG("%s mgr %p", hdev->name, mgr);
+
+	rsp.id = hdev->id;
+	rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
+
+	if (hdev->amp_type != HCI_BREDR) {
+		rsp.status = 0;
+		rsp.total_bw = cpu_to_le32(hdev->amp_total_bw);
+		rsp.max_bw = cpu_to_le32(hdev->amp_max_bw);
+		rsp.min_latency = cpu_to_le32(hdev->amp_min_latency);
+		rsp.pal_cap = cpu_to_le16(hdev->amp_pal_cap);
+		rsp.assoc_size = cpu_to_le16(hdev->amp_assoc_size);
+	}
+
+	a2mp_send(mgr, A2MP_GETINFO_RSP, mgr->ident, sizeof(rsp), &rsp);
+	amp_mgr_put(mgr);
+}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 2022b43c7353..eb45774165f4 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -30,6 +30,7 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/mgmt.h>
+#include <net/bluetooth/a2mp.h>
 
 /* Handle HCI Event packets */
 
@@ -846,7 +847,7 @@ static void hci_cc_read_local_amp_info(struct hci_dev *hdev,
 	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
 
 	if (rp->status)
-		return;
+		goto a2mp_rsp;
 
 	hdev->amp_status = rp->amp_status;
 	hdev->amp_total_bw = __le32_to_cpu(rp->total_bw);
@@ -860,6 +861,9 @@ static void hci_cc_read_local_amp_info(struct hci_dev *hdev,
 	hdev->amp_max_flush_to = __le32_to_cpu(rp->max_flush_to);
 
 	hci_req_complete(hdev, HCI_OP_READ_LOCAL_AMP_INFO, rp->status);
+
+a2mp_rsp:
+	a2mp_send_getinfo_rsp(hdev);
 }
 
 static void hci_cc_delete_stored_link_key(struct hci_dev *hdev,
-- 
cgit v1.2.3-55-g7522


From 903e45411099ae8292f5ce637ad0c72f6fef61db Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:09 +0300
Subject: Bluetooth: AMP: Use HCI cmd to Read Loc AMP Assoc

When receiving A2MP Get AMP Assoc Request execute Read Local AMP Assoc
HCI command to AMP controller. If the AMP Assoc data is larger than it
can fit to HCI event only fragment is read. When all fragments are read
send A2MP Get AMP Assoc Response.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/a2mp.h     |  2 ++
 include/net/bluetooth/amp.h      | 21 +++++++++++++++
 include/net/bluetooth/hci.h      |  2 ++
 include/net/bluetooth/hci_core.h |  8 ++++++
 net/bluetooth/Makefile           |  2 +-
 net/bluetooth/a2mp.c             | 56 ++++++++++++++++++++++++++++++++++++----
 net/bluetooth/amp.c              | 45 ++++++++++++++++++++++++++++++++
 net/bluetooth/hci_event.c        | 41 +++++++++++++++++++++++++++++
 8 files changed, 171 insertions(+), 6 deletions(-)
 create mode 100644 include/net/bluetooth/amp.h
 create mode 100644 net/bluetooth/amp.c

(limited to 'include')

diff --git a/include/net/bluetooth/a2mp.h b/include/net/bluetooth/a2mp.h
index af594685112e..d5476719fa4c 100644
--- a/include/net/bluetooth/a2mp.h
+++ b/include/net/bluetooth/a2mp.h
@@ -21,6 +21,7 @@
 
 enum amp_mgr_state {
 	READ_LOC_AMP_INFO,
+	READ_LOC_AMP_ASSOC,
 };
 
 struct amp_mgr {
@@ -134,5 +135,6 @@ struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
 struct amp_mgr *amp_mgr_lookup_by_state(u8 state);
 void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data);
 void a2mp_send_getinfo_rsp(struct hci_dev *hdev);
+void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status);
 
 #endif /* __A2MP_H */
diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
new file mode 100644
index 000000000000..e8616751bc81
--- /dev/null
+++ b/include/net/bluetooth/amp.h
@@ -0,0 +1,21 @@
+/*
+   Copyright (c) 2011,2012 Intel Corp.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 2 and
+   only version 2 as published by the Free Software Foundation.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+*/
+
+#ifndef __AMP_H
+#define __AMP_H
+
+void amp_read_loc_info(struct hci_dev *hdev, struct amp_mgr *mgr);
+void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle);
+void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr);
+
+#endif /* __AMP_H */
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 4be26abf6dad..ccc08e57c107 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -33,6 +33,8 @@
 #define HCI_LINK_KEY_SIZE	16
 #define HCI_AMP_LINK_KEY_SIZE	(2 * HCI_LINK_KEY_SIZE)
 
+#define HCI_MAX_AMP_ASSOC_SIZE	672
+
 /* HCI dev events */
 #define HCI_DEV_REG			1
 #define HCI_DEV_UNREG			2
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index e7d454609881..b1c7d0607244 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -124,6 +124,12 @@ struct le_scan_params {
 
 #define HCI_MAX_SHORT_NAME_LENGTH	10
 
+struct amp_assoc {
+	__u16	len;
+	__u16	offset;
+	__u8	data[HCI_MAX_AMP_ASSOC_SIZE];
+};
+
 #define NUM_REASSEMBLY 4
 struct hci_dev {
 	struct list_head list;
@@ -177,6 +183,8 @@ struct hci_dev {
 	__u32		amp_max_flush_to;
 	__u32		amp_be_flush_to;
 
+	struct amp_assoc	loc_assoc;
+
 	__u8		flow_ctl_mode;
 
 	unsigned int	auto_accept_delay;
diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile
index fa6d94a4602a..dea6a287daca 100644
--- a/net/bluetooth/Makefile
+++ b/net/bluetooth/Makefile
@@ -10,4 +10,4 @@ obj-$(CONFIG_BT_HIDP)	+= hidp/
 
 bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \
 	hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o sco.o lib.o \
-	a2mp.o
+	a2mp.o amp.o
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 0e97b3b42ab1..71400612843d 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -16,6 +16,7 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/a2mp.h>
+#include <net/bluetooth/amp.h>
 
 /* Global AMP Manager list */
 LIST_HEAD(amp_mgr_list);
@@ -218,26 +219,37 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb,
 {
 	struct a2mp_amp_assoc_req *req = (void *) skb->data;
 	struct hci_dev *hdev;
+	struct amp_mgr *tmp;
 
 	if (le16_to_cpu(hdr->len) < sizeof(*req))
 		return -EINVAL;
 
 	BT_DBG("id %d", req->id);
 
+	/* Make sure that other request is not processed */
+	tmp = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC);
+
 	hdev = hci_dev_get(req->id);
-	if (!hdev || hdev->amp_type == HCI_BREDR) {
+	if (!hdev || hdev->amp_type == HCI_BREDR || tmp) {
 		struct a2mp_amp_assoc_rsp rsp;
 		rsp.id = req->id;
-		rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
+
+		if (tmp) {
+			rsp.status = A2MP_STATUS_COLLISION_OCCURED;
+			amp_mgr_put(tmp);
+		} else {
+			rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
+		}
 
 		a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, hdr->ident, sizeof(rsp),
 			  &rsp);
-		goto clean;
+
+		goto done;
 	}
 
-	/* Placeholder for HCI Read AMP Assoc */
+	amp_read_loc_assoc(hdev, mgr);
 
-clean:
+done:
 	if (hdev)
 		hci_dev_put(hdev);
 
@@ -624,3 +636,37 @@ void a2mp_send_getinfo_rsp(struct hci_dev *hdev)
 	a2mp_send(mgr, A2MP_GETINFO_RSP, mgr->ident, sizeof(rsp), &rsp);
 	amp_mgr_put(mgr);
 }
+
+void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status)
+{
+	struct amp_mgr *mgr;
+	struct amp_assoc *loc_assoc = &hdev->loc_assoc;
+	struct a2mp_amp_assoc_rsp *rsp;
+	size_t len;
+
+	mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC);
+	if (!mgr)
+		return;
+
+	BT_DBG("%s mgr %p", hdev->name, mgr);
+
+	len = sizeof(struct a2mp_amp_assoc_rsp) + loc_assoc->len;
+	rsp = kzalloc(len, GFP_KERNEL);
+	if (!rsp) {
+		amp_mgr_put(mgr);
+		return;
+	}
+
+	rsp->id = hdev->id;
+
+	if (status) {
+		rsp->status = A2MP_STATUS_INVALID_CTRL_ID;
+	} else {
+		rsp->status = A2MP_STATUS_SUCCESS;
+		memcpy(rsp->amp_assoc, loc_assoc->data, loc_assoc->len);
+	}
+
+	a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, mgr->ident, len, rsp);
+	amp_mgr_put(mgr);
+	kfree(rsp);
+}
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
new file mode 100644
index 000000000000..2d4e79ee06a5
--- /dev/null
+++ b/net/bluetooth/amp.c
@@ -0,0 +1,45 @@
+/*
+   Copyright (c) 2011,2012 Intel Corp.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 2 and
+   only version 2 as published by the Free Software Foundation.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+*/
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci.h>
+#include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/a2mp.h>
+#include <net/bluetooth/amp.h>
+
+void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle)
+{
+	struct hci_cp_read_local_amp_assoc cp;
+	struct amp_assoc *loc_assoc = &hdev->loc_assoc;
+
+	BT_DBG("%s handle %d", hdev->name, phy_handle);
+
+	cp.phy_handle = phy_handle;
+	cp.max_len = cpu_to_le16(hdev->amp_assoc_size);
+	cp.len_so_far = cpu_to_le16(loc_assoc->offset);
+
+	hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp);
+}
+
+void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr)
+{
+	struct hci_cp_read_local_amp_assoc cp;
+
+	memset(&hdev->loc_assoc, 0, sizeof(struct amp_assoc));
+	memset(&cp, 0, sizeof(cp));
+
+	cp.max_len = cpu_to_le16(hdev->amp_assoc_size);
+
+	mgr->state = READ_LOC_AMP_ASSOC;
+	hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp);
+}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index eb45774165f4..a4240f7a142e 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -31,6 +31,7 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/mgmt.h>
 #include <net/bluetooth/a2mp.h>
+#include <net/bluetooth/amp.h>
 
 /* Handle HCI Event packets */
 
@@ -866,6 +867,42 @@ a2mp_rsp:
 	a2mp_send_getinfo_rsp(hdev);
 }
 
+static void hci_cc_read_local_amp_assoc(struct hci_dev *hdev,
+					struct sk_buff *skb)
+{
+	struct hci_rp_read_local_amp_assoc *rp = (void *) skb->data;
+	struct amp_assoc *assoc = &hdev->loc_assoc;
+	size_t rem_len, frag_len;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		goto a2mp_rsp;
+
+	frag_len = skb->len - sizeof(*rp);
+	rem_len = __le16_to_cpu(rp->rem_len);
+
+	if (rem_len > frag_len) {
+		BT_DBG("frag_len %d rem_len %d", frag_len, rem_len);
+
+		memcpy(assoc->data + assoc->offset, rp->frag, frag_len);
+		assoc->offset += frag_len;
+
+		/* Read other fragments */
+		amp_read_loc_assoc_frag(hdev, rp->phy_handle);
+
+		return;
+	}
+
+	memcpy(assoc->data + assoc->offset, rp->frag, rem_len);
+	assoc->len = assoc->offset + rem_len;
+	assoc->offset = 0;
+
+a2mp_rsp:
+	/* Send A2MP Rsp when all fragments are received */
+	a2mp_send_getampassoc_rsp(hdev, rp->status);
+}
+
 static void hci_cc_delete_stored_link_key(struct hci_dev *hdev,
 					  struct sk_buff *skb)
 {
@@ -2318,6 +2355,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_read_local_amp_info(hdev, skb);
 		break;
 
+	case HCI_OP_READ_LOCAL_AMP_ASSOC:
+		hci_cc_read_local_amp_assoc(hdev, skb);
+		break;
+
 	case HCI_OP_DELETE_STORED_LINK_KEY:
 		hci_cc_delete_stored_link_key(hdev, skb);
 		break;
-- 
cgit v1.2.3-55-g7522


From 3161ae1c72f03b021bc67504c13025626c26d30c Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:11 +0300
Subject: Bluetooth: AMP: Physical link struct and helpers

Define physical link structures. Physical links are represented by
hci_conn structure. For BR/EDR we use type ACL_LINK and for AMP
we use AMP_LINK.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h      |  3 +++
 include/net/bluetooth/hci.h      |  1 +
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/amp.c              | 29 +++++++++++++++++++++++++++++
 4 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index e8616751bc81..3414dfdc404c 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -14,6 +14,9 @@
 #ifndef __AMP_H
 #define __AMP_H
 
+struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
+			     u8 remote_id);
+
 void amp_read_loc_info(struct hci_dev *hdev, struct amp_mgr *mgr);
 void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle);
 void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr);
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index ccc08e57c107..77b6a197a6f6 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -207,6 +207,7 @@ enum {
 #define ESCO_LINK	0x02
 /* Low Energy links do not have defined link type. Use invented one */
 #define LE_LINK		0x80
+#define AMP_LINK	0x81
 
 /* LMP features */
 #define LMP_3SLOT	0x01
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index b1c7d0607244..464eae340419 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -318,6 +318,7 @@ struct hci_conn {
 
 	__u8		remote_cap;
 	__u8		remote_auth;
+	__u8		remote_id;
 	bool		flush_key;
 
 	unsigned int	sent;
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 2d4e79ee06a5..50a7b2fb8bf3 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -17,6 +17,35 @@
 #include <net/bluetooth/a2mp.h>
 #include <net/bluetooth/amp.h>
 
+/* Physical Link interface */
+static u8 __next_handle(struct amp_mgr *mgr)
+{
+	if (++mgr->handle == 0)
+		mgr->handle = 1;
+
+	return mgr->handle;
+}
+
+struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
+			     u8 remote_id)
+{
+	bdaddr_t *dst = mgr->l2cap_conn->dst;
+	struct hci_conn *hcon;
+
+	hcon = hci_conn_add(hdev, AMP_LINK, dst);
+	if (!hcon)
+		return NULL;
+
+	hcon->state = BT_CONNECT;
+	hcon->out = true;
+	hcon->attempt++;
+	hcon->handle = __next_handle(mgr);
+	hcon->remote_id = remote_id;
+	hcon->amp_mgr = mgr;
+
+	return hcon;
+}
+
 void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle)
 {
 	struct hci_cp_read_local_amp_assoc cp;
-- 
cgit v1.2.3-55-g7522


From 52c0d6e56b634b195e377192182391d526cdd5e4 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:12 +0300
Subject: Bluetooth: AMP: Remote AMP ctrl definitions

Create remote AMP controllers structure. It is used to keep information
about discovered remote AMP controllers by A2MP protocol.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/a2mp.h |  3 ++
 include/net/bluetooth/amp.h  | 15 +++++++++
 net/bluetooth/a2mp.c         |  5 +++
 net/bluetooth/amp.c          | 79 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 102 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/a2mp.h b/include/net/bluetooth/a2mp.h
index d5476719fa4c..99c7389b9189 100644
--- a/include/net/bluetooth/a2mp.h
+++ b/include/net/bluetooth/a2mp.h
@@ -33,6 +33,9 @@ struct amp_mgr {
 	__u8			handle;
 	enum amp_mgr_state	state;
 	unsigned long		flags;
+
+	struct list_head	amp_ctrls;
+	struct mutex		amp_ctrls_lock;
 };
 
 struct a2mp_cmd {
diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index 3414dfdc404c..f57854f0786d 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -14,6 +14,21 @@
 #ifndef __AMP_H
 #define __AMP_H
 
+struct amp_ctrl {
+	struct list_head	list;
+	struct kref		kref;
+	__u8			id;
+	__u16			assoc_len_so_far;
+	__u16			assoc_rem_len;
+	__u16			assoc_len;
+	__u8			*assoc;
+};
+
+int amp_ctrl_put(struct amp_ctrl *ctrl);
+struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr);
+struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id);
+void amp_ctrl_list_flush(struct amp_mgr *mgr);
+
 struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
 			     u8 remote_id);
 
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index f04c44146663..35e188c7a441 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -594,6 +594,7 @@ static void amp_mgr_destroy(struct kref *kref)
 	list_del(&mgr->list);
 	mutex_unlock(&amp_mgr_list_lock);
 
+	amp_ctrl_list_flush(mgr);
 	kfree(mgr);
 }
 
@@ -630,6 +631,10 @@ static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn)
 
 	kref_init(&mgr->kref);
 
+	/* Remote AMP ctrl list initialization */
+	INIT_LIST_HEAD(&mgr->amp_ctrls);
+	mutex_init(&mgr->amp_ctrls_lock);
+
 	mutex_lock(&amp_mgr_list_lock);
 	list_add(&mgr->list, &amp_mgr_list);
 	mutex_unlock(&amp_mgr_list_lock);
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 50a7b2fb8bf3..8ef912c36224 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -17,6 +17,85 @@
 #include <net/bluetooth/a2mp.h>
 #include <net/bluetooth/amp.h>
 
+/* Remote AMP Controllers interface */
+static void amp_ctrl_get(struct amp_ctrl *ctrl)
+{
+	BT_DBG("ctrl %p orig refcnt %d", ctrl,
+	       atomic_read(&ctrl->kref.refcount));
+
+	kref_get(&ctrl->kref);
+}
+
+static void amp_ctrl_destroy(struct kref *kref)
+{
+	struct amp_ctrl *ctrl = container_of(kref, struct amp_ctrl, kref);
+
+	BT_DBG("ctrl %p", ctrl);
+
+	kfree(ctrl->assoc);
+	kfree(ctrl);
+}
+
+int amp_ctrl_put(struct amp_ctrl *ctrl)
+{
+	BT_DBG("ctrl %p orig refcnt %d", ctrl,
+	       atomic_read(&ctrl->kref.refcount));
+
+	return kref_put(&ctrl->kref, &amp_ctrl_destroy);
+}
+
+struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr)
+{
+	struct amp_ctrl *ctrl;
+
+	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		return NULL;
+
+	mutex_lock(&mgr->amp_ctrls_lock);
+	list_add(&ctrl->list, &mgr->amp_ctrls);
+	mutex_unlock(&mgr->amp_ctrls_lock);
+
+	kref_init(&ctrl->kref);
+
+	BT_DBG("mgr %p ctrl %p", mgr, ctrl);
+
+	return ctrl;
+}
+
+void amp_ctrl_list_flush(struct amp_mgr *mgr)
+{
+	struct amp_ctrl *ctrl, *n;
+
+	BT_DBG("mgr %p", mgr);
+
+	mutex_lock(&mgr->amp_ctrls_lock);
+	list_for_each_entry_safe(ctrl, n, &mgr->amp_ctrls, list) {
+		list_del(&ctrl->list);
+		amp_ctrl_put(ctrl);
+	}
+	mutex_unlock(&mgr->amp_ctrls_lock);
+}
+
+struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id)
+{
+	struct amp_ctrl *ctrl;
+
+	BT_DBG("mgr %p id %d", mgr, id);
+
+	mutex_lock(&mgr->amp_ctrls_lock);
+	list_for_each_entry(ctrl, &mgr->amp_ctrls, list) {
+		if (ctrl->id == id) {
+			amp_ctrl_get(ctrl);
+			mutex_unlock(&mgr->amp_ctrls_lock);
+			return ctrl;
+		}
+	}
+	mutex_unlock(&mgr->amp_ctrls_lock);
+
+	return NULL;
+}
+
 /* Physical Link interface */
 static u8 __next_handle(struct amp_mgr *mgr)
 {
-- 
cgit v1.2.3-55-g7522


From 93c3e8f5c9a0e4dc6b6c93108dcf3ec54ab1191a Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:16 +0300
Subject: Bluetooth: Choose connection based on capabilities

Choose which L2CAP connection to establish by checking support
for HS and remote side supported features.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/a2mp.h  |  2 ++
 include/net/bluetooth/l2cap.h |  1 +
 net/bluetooth/a2mp.c          | 34 +++++++++++++++++++++++++++++-----
 net/bluetooth/l2cap_core.c    | 33 ++++++++++++++++++++++++++++-----
 4 files changed, 60 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/a2mp.h b/include/net/bluetooth/a2mp.h
index 99c7389b9189..9fda7c94913f 100644
--- a/include/net/bluetooth/a2mp.h
+++ b/include/net/bluetooth/a2mp.h
@@ -28,6 +28,7 @@ struct amp_mgr {
 	struct list_head	list;
 	struct l2cap_conn	*l2cap_conn;
 	struct l2cap_chan	*a2mp_chan;
+	struct l2cap_chan	*bredr_chan;
 	struct kref		kref;
 	__u8			ident;
 	__u8			handle;
@@ -137,6 +138,7 @@ struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
 				       struct sk_buff *skb);
 struct amp_mgr *amp_mgr_lookup_by_state(u8 state);
 void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data);
+void a2mp_discover_amp(struct l2cap_chan *chan);
 void a2mp_send_getinfo_rsp(struct hci_dev *hdev);
 void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status);
 
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 7ed8e356425a..aba830fc762f 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -767,6 +767,7 @@ int l2cap_chan_check_security(struct l2cap_chan *chan);
 void l2cap_chan_set_defaults(struct l2cap_chan *chan);
 int l2cap_ertm_init(struct l2cap_chan *chan);
 void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
+void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
 void l2cap_chan_del(struct l2cap_chan *chan, int err);
 
 #endif /* __L2CAP_H */
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index d0fde05e8b17..93adaad782ed 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -638,7 +638,7 @@ static struct l2cap_ops a2mp_chan_ops = {
 	.ready = l2cap_chan_no_ready,
 };
 
-static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn)
+static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked)
 {
 	struct l2cap_chan *chan;
 	int err;
@@ -673,7 +673,10 @@ static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn)
 
 	chan->conf_state = 0;
 
-	l2cap_chan_add(conn, chan);
+	if (locked)
+		__l2cap_chan_add(conn, chan);
+	else
+		l2cap_chan_add(conn, chan);
 
 	chan->remote_mps = chan->omtu;
 	chan->mps = chan->omtu;
@@ -712,7 +715,7 @@ int amp_mgr_put(struct amp_mgr *mgr)
 	return kref_put(&mgr->kref, &amp_mgr_destroy);
 }
 
-static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn)
+static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn, bool locked)
 {
 	struct amp_mgr *mgr;
 	struct l2cap_chan *chan;
@@ -725,7 +728,7 @@ static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn)
 
 	mgr->l2cap_conn = conn;
 
-	chan = a2mp_chan_open(conn);
+	chan = a2mp_chan_open(conn, locked);
 	if (!chan) {
 		kfree(mgr);
 		return NULL;
@@ -754,7 +757,7 @@ struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
 {
 	struct amp_mgr *mgr;
 
-	mgr = amp_mgr_create(conn);
+	mgr = amp_mgr_create(conn, false);
 	if (!mgr) {
 		BT_ERR("Could not create AMP manager");
 		return NULL;
@@ -842,3 +845,24 @@ void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status)
 	amp_mgr_put(mgr);
 	kfree(rsp);
 }
+
+void a2mp_discover_amp(struct l2cap_chan *chan)
+{
+	struct l2cap_conn *conn = chan->conn;
+	struct amp_mgr *mgr = conn->hcon->amp_mgr;
+	struct a2mp_discov_req req;
+
+	BT_DBG("chan %p conn %p mgr %p", chan, conn, mgr);
+
+	if (!mgr) {
+		mgr = amp_mgr_create(conn, true);
+		if (!mgr)
+			return;
+	}
+
+	mgr->bredr_chan = chan;
+
+	req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU);
+	req.ext_feat = 0;
+	a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req);
+}
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 7a59e929febc..781a085ae5bc 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -455,7 +455,7 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan)
 	set_bit(FLAG_FORCE_ACTIVE, &chan->flags);
 }
 
-static void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
+void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
 {
 	BT_DBG("conn %p, psm 0x%2.2x, dcid 0x%4.4x", conn,
 	       __le16_to_cpu(chan->psm), chan->dcid);
@@ -946,6 +946,18 @@ static inline int __l2cap_no_conn_pending(struct l2cap_chan *chan)
 	return !test_bit(CONF_CONNECT_PEND, &chan->conf_state);
 }
 
+static bool __amp_capable(struct l2cap_chan *chan)
+{
+	struct l2cap_conn *conn = chan->conn;
+
+	if (enable_hs &&
+	    chan->chan_policy == BT_CHANNEL_POLICY_AMP_PREFERRED &&
+	    conn->fixed_chan_mask & L2CAP_FC_A2MP)
+		return true;
+	else
+		return false;
+}
+
 static void l2cap_send_conn_req(struct l2cap_chan *chan)
 {
 	struct l2cap_conn *conn = chan->conn;
@@ -972,6 +984,16 @@ static void l2cap_chan_ready(struct l2cap_chan *chan)
 	chan->ops->ready(chan);
 }
 
+static void l2cap_start_connection(struct l2cap_chan *chan)
+{
+	if (__amp_capable(chan)) {
+		BT_DBG("chan %p AMP capable: discover AMPs", chan);
+		a2mp_discover_amp(chan);
+	} else {
+		l2cap_send_conn_req(chan);
+	}
+}
+
 static void l2cap_do_start(struct l2cap_chan *chan)
 {
 	struct l2cap_conn *conn = chan->conn;
@@ -986,8 +1008,9 @@ static void l2cap_do_start(struct l2cap_chan *chan)
 			return;
 
 		if (l2cap_chan_check_security(chan) &&
-				__l2cap_no_conn_pending(chan))
-			l2cap_send_conn_req(chan);
+				__l2cap_no_conn_pending(chan)) {
+			l2cap_start_connection(chan);
+		}
 	} else {
 		struct l2cap_info_req req;
 		req.type = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK);
@@ -1082,7 +1105,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
 				continue;
 			}
 
-			l2cap_send_conn_req(chan);
+			l2cap_start_connection(chan);
 
 		} else if (chan->state == BT_CONNECT2) {
 			struct l2cap_conn_rsp rsp;
@@ -5456,7 +5479,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 
 		if (chan->state == BT_CONNECT) {
 			if (!status) {
-				l2cap_send_conn_req(chan);
+				l2cap_start_connection(chan);
 			} else {
 				__set_chan_timer(chan, L2CAP_DISC_TIMEOUT);
 			}
-- 
cgit v1.2.3-55-g7522


From 5a349186692950b13896abc3fb2f491d023f95a1 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:18 +0300
Subject: Bluetooth: AMP: Add AMP key calculation

Function calculates AMP keys using hmac_sha256 helper. Calculated keys
are Generic AMP Link Key (gamp) and Dedicated AMP Link Key with
keyID "802b" for 802.11 PAL.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h |  2 ++
 net/bluetooth/Kconfig       |  1 +
 net/bluetooth/amp.c         | 45 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 48 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index f57854f0786d..763b4635c304 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -32,6 +32,8 @@ void amp_ctrl_list_flush(struct amp_mgr *mgr);
 struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
 			     u8 remote_id);
 
+int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type);
+
 void amp_read_loc_info(struct hci_dev *hdev, struct amp_mgr *mgr);
 void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle);
 void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr);
diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig
index 3537d385035e..1c11d0dcd863 100644
--- a/net/bluetooth/Kconfig
+++ b/net/bluetooth/Kconfig
@@ -11,6 +11,7 @@ menuconfig BT
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_AES
 	select CRYPTO_ECB
+	select CRYPTO_SHA256
 	help
 	  Bluetooth is low-cost, low-power, short-range wireless technology.
 	  It was designed as a replacement for cables and other short-range
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index ea4d5ffc1151..67bc2c2f8783 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -161,6 +161,51 @@ static int hmac_sha256(u8 *key, u8 ksize, char *plaintext, u8 psize, u8 *output)
 	return ret;
 }
 
+int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type)
+{
+	struct hci_dev *hdev = conn->hdev;
+	struct link_key *key;
+	u8 keybuf[HCI_AMP_LINK_KEY_SIZE];
+	u8 gamp_key[HCI_AMP_LINK_KEY_SIZE];
+	int err;
+
+	if (!hci_conn_check_link_mode(conn))
+		return -EACCES;
+
+	BT_DBG("conn %p key_type %d", conn, conn->key_type);
+
+	/* Legacy key */
+	if (conn->key_type < 3) {
+		BT_ERR("Legacy key type %d", conn->key_type);
+		return -EACCES;
+	}
+
+	*type = conn->key_type;
+	*len = HCI_AMP_LINK_KEY_SIZE;
+
+	key = hci_find_link_key(hdev, &conn->dst);
+
+	/* BR/EDR Link Key concatenated together with itself */
+	memcpy(&keybuf[0], key->val, HCI_LINK_KEY_SIZE);
+	memcpy(&keybuf[HCI_LINK_KEY_SIZE], key->val, HCI_LINK_KEY_SIZE);
+
+	/* Derive Generic AMP Link Key (gamp) */
+	err = hmac_sha256(keybuf, HCI_AMP_LINK_KEY_SIZE, "gamp", 4, gamp_key);
+	if (err) {
+		BT_ERR("Could not derive Generic AMP Key: err %d", err);
+		return err;
+	}
+
+	if (conn->key_type == HCI_LK_DEBUG_COMBINATION) {
+		BT_DBG("Use Generic AMP Key (gamp)");
+		memcpy(data, gamp_key, HCI_AMP_LINK_KEY_SIZE);
+		return err;
+	}
+
+	/* Derive Dedicated AMP Link Key: "802b" is 802.11 PAL keyID */
+	return hmac_sha256(gamp_key, HCI_AMP_LINK_KEY_SIZE, "802b", 4, data);
+}
+
 void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle)
 {
 	struct hci_cp_read_local_amp_assoc cp;
-- 
cgit v1.2.3-55-g7522


From a02226d6ff5098e6b97590cc55aabe7faf0860ed Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:19 +0300
Subject: Bluetooth: AMP: Create Physical Link

When receiving A2MP Get AMP Assoc Response execute HCI Create Physical
Link to AMP controller. Define function which will run when receiving
HCI Command Status.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h |  2 ++
 net/bluetooth/a2mp.c        |  2 ++
 net/bluetooth/amp.c         | 19 +++++++++++++++++++
 net/bluetooth/hci_event.c   |  9 +++++++++
 4 files changed, 32 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index 763b4635c304..cadb3d032856 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -37,5 +37,7 @@ int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type);
 void amp_read_loc_info(struct hci_dev *hdev, struct amp_mgr *mgr);
 void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle);
 void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr);
+void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
+			struct hci_conn *hcon);
 
 #endif /* __AMP_H */
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 93adaad782ed..773e8fc41670 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -392,6 +392,8 @@ static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	BT_DBG("Created hcon %p: loc:%d -> rem:%d", hcon, hdev->id, rsp->id);
 
+	amp_create_phylink(hdev, mgr, hcon);
+
 done:
 	hci_dev_put(hdev);
 	skb_pull(skb, len);
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 67bc2c2f8783..657ec736bbc6 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -232,3 +232,22 @@ void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr)
 	mgr->state = READ_LOC_AMP_ASSOC;
 	hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp);
 }
+
+void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
+			struct hci_conn *hcon)
+{
+	struct hci_cp_create_phy_link cp;
+
+	cp.phy_handle = hcon->handle;
+
+	BT_DBG("%s hcon %p phy handle 0x%2.2x", hdev->name, hcon,
+	       hcon->handle);
+
+	if (phylink_gen_key(mgr->l2cap_conn->hcon, cp.key, &cp.key_len,
+			    &cp.key_type)) {
+		BT_DBG("Cannot create link key");
+		return;
+	}
+
+	hci_send_cmd(hdev, HCI_OP_CREATE_PHY_LINK, sizeof(cp), &cp);
+}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index a4240f7a142e..bd06ef95693d 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1698,6 +1698,11 @@ static void hci_cs_le_start_enc(struct hci_dev *hdev, u8 status)
 	BT_DBG("%s status 0x%2.2x", hdev->name, status);
 }
 
+static void hci_cs_create_phylink(struct hci_dev *hdev, u8 status)
+{
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+}
+
 static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 status = *((__u8 *) skb->data);
@@ -2512,6 +2517,10 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cs_le_start_enc(hdev, ev->status);
 		break;
 
+	case HCI_OP_CREATE_PHY_LINK:
+		hci_cs_create_phylink(hdev, ev->status);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode);
 		break;
-- 
cgit v1.2.3-55-g7522


From 93c284ee901f7d7bdd09087e92abefb7496c3777 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:20 +0300
Subject: Bluetooth: AMP: Write remote AMP Assoc

When receiving HCI Command Status after HCI Create Physical Link
execute HCI Write Remote AMP Assoc command to AMP controller.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h      |  2 +
 include/net/bluetooth/hci_core.h |  2 +
 net/bluetooth/amp.c              | 80 ++++++++++++++++++++++++++++++++++++++++
 net/bluetooth/hci_event.c        | 29 +++++++++++++++
 4 files changed, 113 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index cadb3d032856..8f8032965eaf 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -39,5 +39,7 @@ void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle);
 void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr);
 void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 			struct hci_conn *hcon);
+void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle);
+void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle);
 
 #endif /* __AMP_H */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 464eae340419..ea1f9340324d 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -127,6 +127,8 @@ struct le_scan_params {
 struct amp_assoc {
 	__u16	len;
 	__u16	offset;
+	__u16	rem_len;
+	__u16	len_so_far;
 	__u8	data[HCI_MAX_AMP_ASSOC_SIZE];
 };
 
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 657ec736bbc6..5895ad0d2ac9 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -233,6 +233,86 @@ void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr)
 	hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp);
 }
 
+
+/* Write AMP Assoc data fragments, returns true with last fragment written*/
+static bool amp_write_rem_assoc_frag(struct hci_dev *hdev,
+				     struct hci_conn *hcon)
+{
+	struct hci_cp_write_remote_amp_assoc *cp;
+	struct amp_mgr *mgr = hcon->amp_mgr;
+	struct amp_ctrl *ctrl;
+	u16 frag_len, len;
+
+	ctrl = amp_ctrl_lookup(mgr, hcon->remote_id);
+	if (!ctrl)
+		return false;
+
+	if (!ctrl->assoc_rem_len) {
+		BT_DBG("all fragments are written");
+		ctrl->assoc_rem_len = ctrl->assoc_len;
+		ctrl->assoc_len_so_far = 0;
+
+		amp_ctrl_put(ctrl);
+		return true;
+	}
+
+	frag_len = min_t(u16, 248, ctrl->assoc_rem_len);
+	len = frag_len + sizeof(*cp);
+
+	cp = kzalloc(len, GFP_KERNEL);
+	if (!cp) {
+		amp_ctrl_put(ctrl);
+		return false;
+	}
+
+	BT_DBG("hcon %p ctrl %p frag_len %u assoc_len %u rem_len %u",
+	       hcon, ctrl, frag_len, ctrl->assoc_len, ctrl->assoc_rem_len);
+
+	cp->phy_handle = hcon->handle;
+	cp->len_so_far = cpu_to_le16(ctrl->assoc_len_so_far);
+	cp->rem_len = cpu_to_le16(ctrl->assoc_rem_len);
+	memcpy(cp->frag, ctrl->assoc, frag_len);
+
+	ctrl->assoc_len_so_far += frag_len;
+	ctrl->assoc_rem_len -= frag_len;
+
+	amp_ctrl_put(ctrl);
+
+	hci_send_cmd(hdev, HCI_OP_WRITE_REMOTE_AMP_ASSOC, len, cp);
+
+	kfree(cp);
+
+	return false;
+}
+
+void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle)
+{
+	struct hci_conn *hcon;
+
+	BT_DBG("%s phy handle 0x%2.2x", hdev->name, handle);
+
+	hcon = hci_conn_hash_lookup_handle(hdev, handle);
+	if (!hcon)
+		return;
+
+	amp_write_rem_assoc_frag(hdev, hcon);
+}
+
+void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle)
+{
+	struct hci_conn *hcon;
+
+	BT_DBG("%s phy handle 0x%2.2x", hdev->name, handle);
+
+	hcon = hci_conn_hash_lookup_handle(hdev, handle);
+	if (!hcon)
+		return;
+
+	BT_DBG("%s phy handle 0x%2.2x hcon %p", hdev->name, handle, hcon);
+
+	amp_write_rem_assoc_frag(hdev, hcon);
+}
+
 void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 			struct hci_conn *hcon)
 {
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index bd06ef95693d..0b7ba1e39d45 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1215,6 +1215,20 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev,
 	hci_req_complete(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, status);
 }
 
+static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev,
+					  struct sk_buff *skb)
+{
+	struct hci_rp_write_remote_amp_assoc *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x phy_handle 0x%2.2x",
+	       hdev->name, rp->status, rp->phy_handle);
+
+	if (rp->status)
+		return;
+
+	amp_write_rem_assoc_continue(hdev, rp->phy_handle);
+}
+
 static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 {
 	BT_DBG("%s status 0x%2.2x", hdev->name, status);
@@ -1700,7 +1714,18 @@ static void hci_cs_le_start_enc(struct hci_dev *hdev, u8 status)
 
 static void hci_cs_create_phylink(struct hci_dev *hdev, u8 status)
 {
+	struct hci_cp_create_phy_link *cp;
+
 	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_PHY_LINK);
+	if (!cp)
+		return;
+
+	amp_write_remote_assoc(hdev, cp->phy_handle);
 }
 
 static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
@@ -2436,6 +2461,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_write_le_host_supported(hdev, skb);
 		break;
 
+	case HCI_OP_WRITE_REMOTE_AMP_ASSOC:
+		hci_cc_write_remote_amp_assoc(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode);
 		break;
-- 
cgit v1.2.3-55-g7522


From 2766be48a7181d7f2a84831ca7e7be248fb6fdb5 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:21 +0300
Subject: Bluetooth: A2MP: Add fallback to normal l2cap init sequence

When there is no remote AMP controller found fallback to normal
L2CAP sequence.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h |  1 +
 net/bluetooth/a2mp.c          | 28 ++++++++++++++++++++++++++++
 net/bluetooth/l2cap_core.c    |  2 +-
 3 files changed, 30 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index aba830fc762f..0967f9e33750 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -769,5 +769,6 @@ int l2cap_ertm_init(struct l2cap_chan *chan);
 void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
 void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
 void l2cap_chan_del(struct l2cap_chan *chan, int err);
+void l2cap_send_conn_req(struct l2cap_chan *chan);
 
 #endif /* __L2CAP_H */
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 773e8fc41670..28d1246958be 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -180,6 +180,7 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 	u16 len = le16_to_cpu(hdr->len);
 	struct a2mp_cl *cl;
 	u16 ext_feat;
+	bool found = false;
 
 	if (len < sizeof(*rsp))
 		return -EINVAL;
@@ -210,6 +211,7 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 		if (cl->id != HCI_BREDR_ID && cl->type == HCI_AMP) {
 			struct a2mp_info_req req;
 
+			found = true;
 			req.id = cl->id;
 			a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr),
 				  sizeof(req), &req);
@@ -219,6 +221,32 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 		cl = (void *) skb_pull(skb, sizeof(*cl));
 	}
 
+	/* Fall back to L2CAP init sequence */
+	if (!found) {
+		struct l2cap_conn *conn = mgr->l2cap_conn;
+		struct l2cap_chan *chan;
+
+		mutex_lock(&conn->chan_lock);
+
+		list_for_each_entry(chan, &conn->chan_l, list) {
+
+			BT_DBG("chan %p state %s", chan,
+			       state_to_string(chan->state));
+
+			if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP)
+				continue;
+
+			l2cap_chan_lock(chan);
+
+			if (chan->state == BT_CONNECT)
+				l2cap_send_conn_req(chan);
+
+			l2cap_chan_unlock(chan);
+		}
+
+		mutex_unlock(&conn->chan_lock);
+	}
+
 	return 0;
 }
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 781a085ae5bc..a347522b2144 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -958,7 +958,7 @@ static bool __amp_capable(struct l2cap_chan *chan)
 		return false;
 }
 
-static void l2cap_send_conn_req(struct l2cap_chan *chan)
+void l2cap_send_conn_req(struct l2cap_chan *chan)
 {
 	struct l2cap_conn *conn = chan->conn;
 	struct l2cap_conn_req req;
-- 
cgit v1.2.3-55-g7522


From 9495b2ee757f7747d7c28f9ba8d7edc53005ec2d Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:22 +0300
Subject: Bluetooth: AMP: Process Chan Selected event

Channel Selected event indicates that link information data is available.
Read it with Read Local AMP Assoc command. The data shall be sent in the
A2MP Create Physical Link Request.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/a2mp.h  |  3 +++
 include/net/bluetooth/amp.h   |  2 ++
 include/net/bluetooth/l2cap.h |  2 ++
 net/bluetooth/a2mp.c          | 41 ++++++++++++++++++++++++++++++++++++++++-
 net/bluetooth/amp.c           | 15 +++++++++++++++
 net/bluetooth/hci_event.c     | 21 +++++++++++++++++++++
 6 files changed, 83 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/a2mp.h b/include/net/bluetooth/a2mp.h
index 9fda7c94913f..e776ab2dc572 100644
--- a/include/net/bluetooth/a2mp.h
+++ b/include/net/bluetooth/a2mp.h
@@ -22,6 +22,7 @@
 enum amp_mgr_state {
 	READ_LOC_AMP_INFO,
 	READ_LOC_AMP_ASSOC,
+	READ_LOC_AMP_ASSOC_FINAL,
 };
 
 struct amp_mgr {
@@ -134,6 +135,7 @@ extern struct mutex amp_mgr_list_lock;
 
 void amp_mgr_get(struct amp_mgr *mgr);
 int amp_mgr_put(struct amp_mgr *mgr);
+u8 __next_ident(struct amp_mgr *mgr);
 struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
 				       struct sk_buff *skb);
 struct amp_mgr *amp_mgr_lookup_by_state(u8 state);
@@ -141,5 +143,6 @@ void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data);
 void a2mp_discover_amp(struct l2cap_chan *chan);
 void a2mp_send_getinfo_rsp(struct hci_dev *hdev);
 void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status);
+void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status);
 
 #endif /* __A2MP_H */
diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index 8f8032965eaf..70496c07afaa 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -37,6 +37,8 @@ int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type);
 void amp_read_loc_info(struct hci_dev *hdev, struct amp_mgr *mgr);
 void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle);
 void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr);
+void amp_read_loc_assoc_final_data(struct hci_dev *hdev,
+				   struct hci_conn *hcon);
 void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 			struct hci_conn *hcon);
 void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle);
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 0967f9e33750..ab58b81fb7c5 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -508,6 +508,8 @@ struct l2cap_chan {
 	__u32		remote_acc_lat;
 	__u32		remote_flush_to;
 
+	__u8		ctrl_id;
+
 	struct delayed_work	chan_timer;
 	struct delayed_work	retrans_timer;
 	struct delayed_work	monitor_timer;
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 28d1246958be..375a67f501d0 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -67,7 +67,7 @@ void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data)
 	kfree(cmd);
 }
 
-static u8 __next_ident(struct amp_mgr *mgr)
+u8 __next_ident(struct amp_mgr *mgr)
 {
 	if (++mgr->ident == 0)
 		mgr->ident = 1;
@@ -420,6 +420,8 @@ static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	BT_DBG("Created hcon %p: loc:%d -> rem:%d", hcon, hdev->id, rsp->id);
 
+	mgr->bredr_chan->ctrl_id = rsp->id;
+
 	amp_create_phylink(hdev, mgr, hcon);
 
 done:
@@ -876,6 +878,43 @@ void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status)
 	kfree(rsp);
 }
 
+void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status)
+{
+	struct amp_mgr *mgr;
+	struct amp_assoc *loc_assoc = &hdev->loc_assoc;
+	struct a2mp_physlink_req *req;
+	struct l2cap_chan *bredr_chan;
+	size_t len;
+
+	mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC_FINAL);
+	if (!mgr)
+		return;
+
+	len = sizeof(*req) + loc_assoc->len;
+
+	BT_DBG("%s mgr %p assoc_len %zu", hdev->name, mgr, len);
+
+	req = kzalloc(len, GFP_KERNEL);
+	if (!req) {
+		amp_mgr_put(mgr);
+		return;
+	}
+
+	bredr_chan = mgr->bredr_chan;
+	if (!bredr_chan)
+		goto clean;
+
+	req->local_id = hdev->id;
+	req->remote_id = bredr_chan->ctrl_id;
+	memcpy(req->amp_assoc, loc_assoc->data, loc_assoc->len);
+
+	a2mp_send(mgr, A2MP_CREATEPHYSLINK_REQ, __next_ident(mgr), len, req);
+
+clean:
+	amp_mgr_put(mgr);
+	kfree(req);
+}
+
 void a2mp_discover_amp(struct l2cap_chan *chan)
 {
 	struct l2cap_conn *conn = chan->conn;
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 5895ad0d2ac9..4f7b2647d5e9 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -233,6 +233,21 @@ void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr)
 	hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp);
 }
 
+void amp_read_loc_assoc_final_data(struct hci_dev *hdev,
+				   struct hci_conn *hcon)
+{
+	struct hci_cp_read_local_amp_assoc cp;
+	struct amp_mgr *mgr = hcon->amp_mgr;
+
+	cp.phy_handle = hcon->handle;
+	cp.len_so_far = cpu_to_le16(0);
+	cp.max_len = cpu_to_le16(hdev->amp_assoc_size);
+
+	mgr->state = READ_LOC_AMP_ASSOC_FINAL;
+
+	/* Read Local AMP Assoc final link information data */
+	hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp);
+}
 
 /* Write AMP Assoc data fragments, returns true with last fragment written*/
 static bool amp_write_rem_assoc_frag(struct hci_dev *hdev,
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0b7ba1e39d45..d702ba1c171c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -901,6 +901,7 @@ static void hci_cc_read_local_amp_assoc(struct hci_dev *hdev,
 a2mp_rsp:
 	/* Send A2MP Rsp when all fragments are received */
 	a2mp_send_getampassoc_rsp(hdev, rp->status);
+	a2mp_send_create_phy_link_req(hdev, rp->status);
 }
 
 static void hci_cc_delete_stored_link_key(struct hci_dev *hdev,
@@ -3641,6 +3642,22 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 }
 
+static void hci_chan_selected_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_ev_channel_selected *ev = (void *) skb->data;
+	struct hci_conn *hcon;
+
+	BT_DBG("%s handle 0x%2.2x", hdev->name, ev->phy_handle);
+
+	skb_pull(skb, sizeof(*ev));
+
+	hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle);
+	if (!hcon)
+		return;
+
+	amp_read_loc_assoc_final_data(hdev, hcon);
+}
+
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_event_hdr *hdr = (void *) skb->data;
@@ -3805,6 +3822,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_le_meta_evt(hdev, skb);
 		break;
 
+	case HCI_EV_CHANNEL_SELECTED:
+		hci_chan_selected_evt(hdev, skb);
+		break;
+
 	case HCI_EV_REMOTE_OOB_DATA_REQUEST:
 		hci_remote_oob_data_request_evt(hdev, skb);
 		break;
-- 
cgit v1.2.3-55-g7522


From dffa387110025801862d7ad09f4e850d06ff55a9 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:23 +0300
Subject: Bluetooth: AMP: Accept Physical Link

When receiving A2MP Create Physical Link message execute HCI
Accept Physical Link command to AMP controller.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h |  2 ++
 net/bluetooth/a2mp.c        |  5 +----
 net/bluetooth/amp.c         | 19 +++++++++++++++++++
 3 files changed, 22 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index 70496c07afaa..1b06d7b01359 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -41,6 +41,8 @@ void amp_read_loc_assoc_final_data(struct hci_dev *hdev,
 				   struct hci_conn *hcon);
 void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 			struct hci_conn *hcon);
+void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
+			struct hci_conn *hcon);
 void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle);
 void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle);
 
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 375a67f501d0..dbfdbbb9707c 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -453,12 +453,9 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 		goto send_rsp;
 	}
 
-	/* TODO process physlink create */
-
 	hcon = phylink_add(hdev, mgr, req->local_id);
 	if (hcon) {
-		BT_DBG("hcon %p", hcon);
-
+		amp_accept_phylink(hdev, mgr, hcon);
 		rsp.status = A2MP_STATUS_SUCCESS;
 	} else {
 		rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION;
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 4f7b2647d5e9..845e43073c40 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -346,3 +346,22 @@ void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 
 	hci_send_cmd(hdev, HCI_OP_CREATE_PHY_LINK, sizeof(cp), &cp);
 }
+
+void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
+			struct hci_conn *hcon)
+{
+	struct hci_cp_accept_phy_link cp;
+
+	cp.phy_handle = hcon->handle;
+
+	BT_DBG("%s hcon %p phy handle 0x%2.2x", hdev->name, hcon,
+	       hcon->handle);
+
+	if (phylink_gen_key(mgr->l2cap_conn->hcon, cp.key, &cp.key_len,
+			    &cp.key_type)) {
+		BT_DBG("Cannot create link key");
+		return;
+	}
+
+	hci_send_cmd(hdev, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp);
+}
-- 
cgit v1.2.3-55-g7522


From 0b26ab9dce74f8ac77d7eef0d683ab1d527e45b1 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 27 Sep 2012 17:26:24 +0300
Subject: Bluetooth: AMP: Handle Accept phylink command status evt

When receiving HCI Command Status event for Accept Physical Link
execute HCI Write Remote AMP Assoc with data saved from A2MP Create
Physical Link Request.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h |  1 +
 net/bluetooth/a2mp.c        | 32 ++++++++++++++++++++++++++++++++
 net/bluetooth/amp.c         |  2 +-
 net/bluetooth/hci_event.c   | 20 ++++++++++++++++++++
 4 files changed, 54 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index 1b06d7b01359..b1e54903dd42 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -25,6 +25,7 @@ struct amp_ctrl {
 };
 
 int amp_ctrl_put(struct amp_ctrl *ctrl);
+void amp_ctrl_get(struct amp_ctrl *ctrl);
 struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr);
 struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id);
 void amp_ctrl_list_flush(struct amp_mgr *mgr);
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index dbfdbbb9707c..47565d28b27f 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -438,6 +438,7 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 	struct a2mp_physlink_rsp rsp;
 	struct hci_dev *hdev;
 	struct hci_conn *hcon;
+	struct amp_ctrl *ctrl;
 
 	if (le16_to_cpu(hdr->len) < sizeof(*req))
 		return -EINVAL;
@@ -453,6 +454,37 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 		goto send_rsp;
 	}
 
+	ctrl = amp_ctrl_lookup(mgr, rsp.remote_id);
+	if (!ctrl) {
+		ctrl = amp_ctrl_add(mgr);
+		if (ctrl) {
+			amp_ctrl_get(ctrl);
+		} else {
+			rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION;
+			goto send_rsp;
+		}
+	}
+
+	if (ctrl) {
+		u8 *assoc, assoc_len = le16_to_cpu(hdr->len) - sizeof(*req);
+
+		ctrl->id = rsp.remote_id;
+
+		assoc = kzalloc(assoc_len, GFP_KERNEL);
+		if (!assoc) {
+			amp_ctrl_put(ctrl);
+			return -ENOMEM;
+		}
+
+		memcpy(assoc, req->amp_assoc, assoc_len);
+		ctrl->assoc = assoc;
+		ctrl->assoc_len = assoc_len;
+		ctrl->assoc_rem_len = assoc_len;
+		ctrl->assoc_len_so_far = 0;
+
+		amp_ctrl_put(ctrl);
+	}
+
 	hcon = phylink_add(hdev, mgr, req->local_id);
 	if (hcon) {
 		amp_accept_phylink(hdev, mgr, hcon);
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 845e43073c40..5dab2d1c7c82 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -19,7 +19,7 @@
 #include <crypto/hash.h>
 
 /* Remote AMP Controllers interface */
-static void amp_ctrl_get(struct amp_ctrl *ctrl)
+void amp_ctrl_get(struct amp_ctrl *ctrl)
 {
 	BT_DBG("ctrl %p orig refcnt %d", ctrl,
 	       atomic_read(&ctrl->kref.refcount));
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index d702ba1c171c..7e716698fe64 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1729,6 +1729,22 @@ static void hci_cs_create_phylink(struct hci_dev *hdev, u8 status)
 	amp_write_remote_assoc(hdev, cp->phy_handle);
 }
 
+static void hci_cs_accept_phylink(struct hci_dev *hdev, u8 status)
+{
+	struct hci_cp_accept_phy_link *cp;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_ACCEPT_PHY_LINK);
+	if (!cp)
+		return;
+
+	amp_write_remote_assoc(hdev, cp->phy_handle);
+}
+
 static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 status = *((__u8 *) skb->data);
@@ -2551,6 +2567,10 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cs_create_phylink(hdev, ev->status);
 		break;
 
+	case HCI_OP_ACCEPT_PHY_LINK:
+		hci_cs_accept_phylink(hdev, ev->status);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode);
 		break;
-- 
cgit v1.2.3-55-g7522


From d945df256a7b2446227fafae2f89db85597412ef Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Tue, 25 Sep 2012 12:49:46 +0300
Subject: bluetooth: Remove unneeded batostr function

batostr is not needed anymore since for printing Bluetooth
addresses we use %pMR specifier.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/bluetooth.h |  1 -
 net/bluetooth/lib.c               | 14 --------------
 2 files changed, 15 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index ede036977ae8..2554b3f5222a 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -180,7 +180,6 @@ static inline void bacpy(bdaddr_t *dst, bdaddr_t *src)
 }
 
 void baswap(bdaddr_t *dst, bdaddr_t *src);
-char *batostr(bdaddr_t *ba);
 
 /* Common socket structures and functions */
 
diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c
index e1c97527e16c..b3fbc73516c4 100644
--- a/net/bluetooth/lib.c
+++ b/net/bluetooth/lib.c
@@ -41,20 +41,6 @@ void baswap(bdaddr_t *dst, bdaddr_t *src)
 }
 EXPORT_SYMBOL(baswap);
 
-char *batostr(bdaddr_t *ba)
-{
-	static char str[2][18];
-	static int i = 1;
-
-	i ^= 1;
-	sprintf(str[i], "%2.2X:%2.2X:%2.2X:%2.2X:%2.2X:%2.2X",
-		ba->b[5], ba->b[4], ba->b[3],
-		ba->b[2], ba->b[1], ba->b[0]);
-
-	return str[i];
-}
-EXPORT_SYMBOL(batostr);
-
 /* Bluetooth error codes to Unix errno mapping */
 int bt_to_errno(__u16 code)
 {
-- 
cgit v1.2.3-55-g7522


From 120b9c14f464c445b20c05e81221ef83fdb5e55e Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer
Date: Wed, 26 Sep 2012 14:05:53 +0200
Subject: ipvs: Trivial changes, use compressed IPv6 address in output

Have not converted the proc file output to compressed IPv6 addresses.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h              |  2 +-
 net/netfilter/ipvs/ip_vs_core.c  |  2 +-
 net/netfilter/ipvs/ip_vs_proto.c |  6 +++---
 net/netfilter/ipvs/ip_vs_sched.c |  2 +-
 net/netfilter/ipvs/ip_vs_xmit.c  | 10 +++++-----
 5 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index ee75ccdf5188..aba0bb2da92d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -165,7 +165,7 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len,
 	int len;
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
-		len = snprintf(&buf[*idx], buf_len - *idx, "[%pI6]",
+		len = snprintf(&buf[*idx], buf_len - *idx, "[%pI6c]",
 			       &addr->in6) + 1;
 	else
 #endif
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 58918e20f9d5..4edb65462abe 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1487,7 +1487,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	if (ic == NULL)
 		return NF_DROP;
 
-	IP_VS_DBG(12, "Incoming ICMPv6 (%d,%d) %pI6->%pI6\n",
+	IP_VS_DBG(12, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n",
 		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
 		  &iph->saddr, &iph->daddr);
 
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 50d82186da87..939f7fbe9b46 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -280,17 +280,17 @@ ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp,
 	if (ih == NULL)
 		sprintf(buf, "TRUNCATED");
 	else if (ih->nexthdr == IPPROTO_FRAGMENT)
-		sprintf(buf, "%pI6->%pI6 frag",	&ih->saddr, &ih->daddr);
+		sprintf(buf, "%pI6c->%pI6c frag", &ih->saddr, &ih->daddr);
 	else {
 		__be16 _ports[2], *pptr;
 
 		pptr = skb_header_pointer(skb, offset + sizeof(struct ipv6hdr),
 					  sizeof(_ports), _ports);
 		if (pptr == NULL)
-			sprintf(buf, "TRUNCATED %pI6->%pI6",
+			sprintf(buf, "TRUNCATED %pI6c->%pI6c",
 				&ih->saddr, &ih->daddr);
 		else
-			sprintf(buf, "%pI6:%u->%pI6:%u",
+			sprintf(buf, "%pI6c:%u->%pI6c:%u",
 				&ih->saddr, ntohs(pptr[0]),
 				&ih->daddr, ntohs(pptr[1]));
 	}
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 08dbdd5bc18f..d6bf20d6cdbe 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -159,7 +159,7 @@ void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
 			     svc->fwmark, msg);
 #ifdef CONFIG_IP_VS_IPV6
 	} else if (svc->af == AF_INET6) {
-		IP_VS_ERR_RL("%s: %s [%pI6]:%d - %s\n",
+		IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n",
 			     svc->scheduler->name,
 			     ip_vs_proto_name(svc->protocol),
 			     &svc->addr.in6, ntohs(svc->port), msg);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 56f6d5d81a77..1060bd52a165 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -335,7 +335,7 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
 	local = __ip_vs_is_local_route6(rt);
 	if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
 	      rt_mode)) {
-		IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n",
+		IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6c\n",
 			     local ? "local":"non-local", daddr);
 		dst_release(&rt->dst);
 		return NULL;
@@ -343,8 +343,8 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
 	if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
 	    !((ort = (struct rt6_info *) skb_dst(skb)) &&
 	      __ip_vs_is_local_route6(ort))) {
-		IP_VS_DBG_RL("Redirect from non-local address %pI6 to local "
-			     "requires NAT method, dest: %pI6\n",
+		IP_VS_DBG_RL("Redirect from non-local address %pI6c to local "
+			     "requires NAT method, dest: %pI6c\n",
 			     &ipv6_hdr(skb)->daddr, daddr);
 		dst_release(&rt->dst);
 		return NULL;
@@ -352,8 +352,8 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
 	if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
 		     ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
 				    IPV6_ADDR_LOOPBACK)) {
-		IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 "
-			     "to non-local address, dest: %pI6\n",
+		IP_VS_DBG_RL("Stopping traffic from loopback address %pI6c "
+			     "to non-local address, dest: %pI6c\n",
 			     &ipv6_hdr(skb)->saddr, daddr);
 		dst_release(&rt->dst);
 		return NULL;
-- 
cgit v1.2.3-55-g7522


From a638e51437f5efd00c4579df56cfd4d497ed51a8 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer
Date: Wed, 26 Sep 2012 14:06:20 +0200
Subject: ipvs: Use config macro IS_ENABLED()

Cleanup patch.

Use the IS_ENABLED macro, instead of having to check
both the build and the module CONFIG_ option.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index aba0bb2da92d..c8b2bdbaf91b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -22,7 +22,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>			/* for struct ipv6hdr */
 #include <net/ipv6.h>
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <net/netfilter/nf_conntrack.h>
 #endif
 #include <net/net_namespace.h>		/* Netw namespace */
-- 
cgit v1.2.3-55-g7522


From 63dca2c0b0e7a92cb39d1b1ecefa32ffda201975 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer
Date: Wed, 26 Sep 2012 14:06:41 +0200
Subject: ipvs: Fix faulty IPv6 extension header handling in IPVS

IPv6 packets can contain extension headers, thus its wrong to assume
that the transport/upper-layer header, starts right after (struct
ipv6hdr) the IPv6 header.  IPVS uses this false assumption, and will
write SNAT & DNAT modifications at a fixed pos which will corrupt the
message.

To fix this, proper header position must be found before modifying
packets.  Introducing ip_vs_fill_iph_skb(), which uses ipv6_find_hdr()
to skip the exthdrs. It finds (1) the transport header offset, (2) the
protocol, and (3) detects if the packet is a fragment.

Note, that fragments in IPv6 is represented via an exthdr.  Thus, this
is detected while skipping through the exthdrs.

This patch depends on commit 84018f55a:
 "netfilter: ip6_tables: add flags parameter to ipv6_find_hdr()"
This also adds a dependency to ip6_tables.

Originally based on patch from: Hans Schillstrom

kABI notes:
Changing struct ip_vs_iphdr is a potential minor kABI breaker,
because external modules can be compiled with another version of
this struct.  This should not matter, as they would most-likely
be using a compiled-in version of ip_vs_fill_iphdr().  When
recompiled, they will notice ip_vs_fill_iphdr() no longer exists,
and they have to used ip_vs_fill_iph_skb() instead.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                   |  72 ++++++++++--
 net/netfilter/ipvs/Kconfig            |   1 +
 net/netfilter/ipvs/ip_vs_core.c       | 211 +++++++++++++++++-----------------
 net/netfilter/ipvs/ip_vs_dh.c         |   2 +-
 net/netfilter/ipvs/ip_vs_lblc.c       |   2 +-
 net/netfilter/ipvs/ip_vs_lblcr.c      |   2 +-
 net/netfilter/ipvs/ip_vs_pe_sip.c     |   2 +-
 net/netfilter/ipvs/ip_vs_proto_sctp.c |  22 ++--
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |  22 ++--
 net/netfilter/ipvs/ip_vs_proto_udp.c  |  22 ++--
 net/netfilter/ipvs/ip_vs_sh.c         |   2 +-
 net/netfilter/ipvs/ip_vs_xmit.c       |   5 +-
 net/netfilter/xt_ipvs.c               |   2 +-
 13 files changed, 214 insertions(+), 153 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index c8b2bdbaf91b..29265bf4153e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -22,6 +22,9 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>			/* for struct ipv6hdr */
 #include <net/ipv6.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#endif
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <net/netfilter/nf_conntrack.h>
 #endif
@@ -103,30 +106,79 @@ static inline struct net *seq_file_single_net(struct seq_file *seq)
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
 
-
 struct ip_vs_iphdr {
-	int len;
-	__u8 protocol;
+	__u32 len;	/* IPv4 simply where L4 starts
+			   IPv6 where L4 Transport Header starts */
+	__u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
+	__s16 protocol;
+	__s32 flags;
 	union nf_inet_addr saddr;
 	union nf_inet_addr daddr;
 };
 
 static inline void
-ip_vs_fill_iphdr(int af, const void *nh, struct ip_vs_iphdr *iphdr)
+ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr)
+{
+	const struct iphdr *iph = nh;
+
+	iphdr->len	= iph->ihl * 4;
+	iphdr->fragoffs	= 0;
+	iphdr->protocol	= iph->protocol;
+	iphdr->saddr.ip	= iph->saddr;
+	iphdr->daddr.ip	= iph->daddr;
+}
+
+/* This function handles filling *ip_vs_iphdr, both for IPv4 and IPv6.
+ * IPv6 requires some extra work, as finding proper header position,
+ * depend on the IPv6 extension headers.
+ */
+static inline void
+ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr)
 {
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		const struct ipv6hdr *iph = nh;
-		iphdr->len = sizeof(struct ipv6hdr);
-		iphdr->protocol = iph->nexthdr;
+		const struct ipv6hdr *iph =
+			(struct ipv6hdr *)skb_network_header(skb);
 		iphdr->saddr.in6 = iph->saddr;
 		iphdr->daddr.in6 = iph->daddr;
+		/* ipv6_find_hdr() updates len, flags */
+		iphdr->len	 = 0;
+		iphdr->flags	 = 0;
+		iphdr->protocol  = ipv6_find_hdr(skb, &iphdr->len, -1,
+						 &iphdr->fragoffs,
+						 &iphdr->flags);
 	} else
 #endif
 	{
-		const struct iphdr *iph = nh;
-		iphdr->len = iph->ihl * 4;
-		iphdr->protocol = iph->protocol;
+		const struct iphdr *iph =
+			(struct iphdr *)skb_network_header(skb);
+		iphdr->len	= iph->ihl * 4;
+		iphdr->fragoffs	= 0;
+		iphdr->protocol	= iph->protocol;
+		iphdr->saddr.ip	= iph->saddr;
+		iphdr->daddr.ip	= iph->daddr;
+	}
+}
+
+/* This function is a faster version of ip_vs_fill_iph_skb().
+ * Where we only populate {s,d}addr (and avoid calling ipv6_find_hdr()).
+ * This is used by the some of the ip_vs_*_schedule() functions.
+ * (Mostly done to avoid ABI breakage of external schedulers)
+ */
+static inline void
+ip_vs_fill_iph_addr_only(int af, const struct sk_buff *skb,
+			 struct ip_vs_iphdr *iphdr)
+{
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6) {
+		const struct ipv6hdr *iph =
+			(struct ipv6hdr *)skb_network_header(skb);
+		iphdr->saddr.in6 = iph->saddr;
+		iphdr->daddr.in6 = iph->daddr;
+	} else {
+#endif
+		const struct iphdr *iph =
+			(struct iphdr *)skb_network_header(skb);
 		iphdr->saddr.ip = iph->saddr;
 		iphdr->daddr.ip = iph->daddr;
 	}
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 8b2cffdfdd99..a97ae5328ae4 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -28,6 +28,7 @@ if IP_VS
 config	IP_VS_IPV6
 	bool "IPv6 support for IPVS"
 	depends on IPV6 = y || IP_VS = IPV6
+	select IP6_NF_IPTABLES
 	---help---
 	  Add IPv6 support to IPVS. This is incomplete and might be dangerous.
 
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index ebd105c4e0c6..19c08425e137 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -236,7 +236,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	union nf_inet_addr snet;	/* source network of the client,
 					   after masking */
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(svc->af, skb, &iph);
 
 	/* Mask saddr with the netmask to adjust template granularity */
 #ifdef CONFIG_IP_VS_IPV6
@@ -402,7 +402,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	unsigned int flags;
 
 	*ignored = 1;
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(svc->af, skb, &iph);
 	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
 	if (pptr == NULL)
 		return NULL;
@@ -506,7 +506,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 	int unicast;
 #endif
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(svc->af, skb, &iph);
 
 	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
 	if (pptr == NULL) {
@@ -732,10 +732,19 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		    struct ip_vs_conn *cp, int inout)
 {
 	struct ipv6hdr *iph	 = ipv6_hdr(skb);
-	unsigned int icmp_offset = sizeof(struct ipv6hdr);
-	struct icmp6hdr *icmph	 = (struct icmp6hdr *)(skb_network_header(skb) +
-						      icmp_offset);
-	struct ipv6hdr *ciph	 = (struct ipv6hdr *)(icmph + 1);
+	unsigned int icmp_offset = 0;
+	unsigned int offs	 = 0; /* header offset*/
+	int protocol;
+	struct icmp6hdr *icmph;
+	struct ipv6hdr *ciph;
+	unsigned short fragoffs;
+
+	ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL);
+	icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset);
+	offs = icmp_offset + sizeof(struct icmp6hdr);
+	ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs);
+
+	protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL);
 
 	if (inout) {
 		iph->saddr = cp->vaddr.in6;
@@ -746,10 +755,13 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
 	}
 
 	/* the TCP/UDP/SCTP port */
-	if (IPPROTO_TCP == ciph->nexthdr || IPPROTO_UDP == ciph->nexthdr ||
-	    IPPROTO_SCTP == ciph->nexthdr) {
-		__be16 *ports = (void *)ciph + sizeof(struct ipv6hdr);
+	if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol ||
+			  IPPROTO_SCTP == protocol)) {
+		__be16 *ports = (void *)(skb_network_header(skb) + offs);
 
+		IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__,
+			      ntohs(inout ? ports[1] : ports[0]),
+			      ntohs(inout ? cp->vport : cp->dport));
 		if (inout)
 			ports[1] = cp->vport;
 		else
@@ -898,9 +910,8 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
 	IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
 		      "Checking outgoing ICMP for");
 
-	offset += cih->ihl * 4;
-
-	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
+	ip_vs_fill_ip4hdr(cih, &ciph);
+	ciph.len += offset;
 	/* The embedded headers contain source and dest in reverse order */
 	cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1);
 	if (!cp)
@@ -908,41 +919,31 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
 
 	snet.ip = iph->saddr;
 	return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp,
-				    pp, offset, ihl);
+				    pp, ciph.len, ihl);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
 static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 			     unsigned int hooknum)
 {
-	struct ipv6hdr *iph;
 	struct icmp6hdr	_icmph, *ic;
-	struct ipv6hdr	_ciph, *cih;	/* The ip header contained
-					   within the ICMP */
-	struct ip_vs_iphdr ciph;
+	struct ipv6hdr _ip6h, *ip6h; /* The ip header contained within ICMP */
+	struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
-	unsigned int offset;
 	union nf_inet_addr snet;
+	unsigned int writable;
 
-	*related = 1;
+	struct ip_vs_iphdr ipvsh_stack;
+	struct ip_vs_iphdr *ipvsh = &ipvsh_stack;
+	ip_vs_fill_iph_skb(AF_INET6, skb, ipvsh);
 
-	/* reassemble IP fragments */
-	if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) {
-		if (ip_vs_gather_frags_v6(skb, ip_vs_defrag_user(hooknum)))
-			return NF_STOLEN;
-	}
+	*related = 1;
 
-	iph = ipv6_hdr(skb);
-	offset = sizeof(struct ipv6hdr);
-	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
+	ic = skb_header_pointer(skb, ipvsh->len, sizeof(_icmph), &_icmph);
 	if (ic == NULL)
 		return NF_DROP;
 
-	IP_VS_DBG(12, "Outgoing ICMPv6 (%d,%d) %pI6->%pI6\n",
-		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
-		  &iph->saddr, &iph->daddr);
-
 	/*
 	 * Work through seeing if this is for us.
 	 * These checks are supposed to be in an order that means easy
@@ -955,35 +956,35 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 		return NF_ACCEPT;
 	}
 
+	IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n",
+		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
+		  &ipvsh->saddr, &ipvsh->daddr);
+
 	/* Now find the contained IP header */
-	offset += sizeof(_icmph);
-	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
-	if (cih == NULL)
+	ciph.len = ipvsh->len + sizeof(_icmph);
+	ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h);
+	if (ip6h == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
-
-	pp = ip_vs_proto_get(cih->nexthdr);
+	ciph.saddr.in6 = ip6h->saddr; /* conn_out_get() handles reverse order */
+	ciph.daddr.in6 = ip6h->daddr;
+	/* skip possible IPv6 exthdrs of contained IPv6 packet */
+	ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL);
+	if (ciph.protocol < 0)
+		return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */
+
+	pp = ip_vs_proto_get(ciph.protocol);
 	if (!pp)
 		return NF_ACCEPT;
 
-	/* Is the embedded protocol header present? */
-	/* TODO: we don't support fragmentation at the moment anyways */
-	if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag))
-		return NF_ACCEPT;
-
-	IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset,
-		      "Checking outgoing ICMPv6 for");
-
-	offset += sizeof(struct ipv6hdr);
-
-	ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1);
+	cp = pp->conn_out_get(AF_INET6, skb, &ciph, ciph.len, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
-	snet.in6 = iph->saddr;
-	return handle_response_icmp(AF_INET6, skb, &snet, cih->nexthdr, cp,
-				    pp, offset, sizeof(struct ipv6hdr));
+	snet.in6 = ciph.saddr.in6;
+	writable = ciph.len;
+	return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
+				    pp, writable, sizeof(struct ipv6hdr));
 }
 #endif
 
@@ -1113,7 +1114,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (!net_ipvs(net)->enable)
 		return NF_ACCEPT;
 
-	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(af, skb, &iph);
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
@@ -1123,7 +1124,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 
 			if (related)
 				return verdict;
-			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+			ip_vs_fill_iph_skb(af, skb, &iph);
 		}
 	} else
 #endif
@@ -1133,7 +1134,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 
 			if (related)
 				return verdict;
-			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+			ip_vs_fill_ip4hdr(skb_network_header(skb), &iph);
 		}
 
 	pd = ip_vs_proto_data_get(net, iph.protocol);
@@ -1143,22 +1144,14 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 
 	/* reassemble IP fragments */
 #ifdef CONFIG_IP_VS_IPV6
-	if (af == AF_INET6) {
-		if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) {
-			if (ip_vs_gather_frags_v6(skb,
-						  ip_vs_defrag_user(hooknum)))
-				return NF_STOLEN;
-		}
-
-		ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
-	} else
+	if (af == AF_INET)
 #endif
 		if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) {
 			if (ip_vs_gather_frags(skb,
 					       ip_vs_defrag_user(hooknum)))
 				return NF_STOLEN;
 
-			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+			ip_vs_fill_ip4hdr(skb_network_header(skb), &iph);
 		}
 
 	/*
@@ -1373,9 +1366,9 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 		      "Checking incoming ICMP for");
 
 	offset2 = offset;
-	offset += cih->ihl * 4;
-
-	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
+	ip_vs_fill_ip4hdr(cih, &ciph);
+	ciph.len += offset;
+	offset = ciph.len;
 	/* The embedded headers contain source and dest in reverse order.
 	 * For IPIP this is error for request, not for reply.
 	 */
@@ -1461,34 +1454,24 @@ static int
 ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 {
 	struct net *net = NULL;
-	struct ipv6hdr *iph;
+	struct ipv6hdr _ip6h, *ip6h;
 	struct icmp6hdr	_icmph, *ic;
-	struct ipv6hdr	_ciph, *cih;	/* The ip header contained
-					   within the ICMP */
-	struct ip_vs_iphdr ciph;
+	struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
 	struct ip_vs_proto_data *pd;
-	unsigned int offset, verdict;
+	unsigned int offs_ciph, writable, verdict;
 
-	*related = 1;
+	struct ip_vs_iphdr iph_stack;
+	struct ip_vs_iphdr *iph = &iph_stack;
+	ip_vs_fill_iph_skb(AF_INET6, skb, iph);
 
-	/* reassemble IP fragments */
-	if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) {
-		if (ip_vs_gather_frags_v6(skb, ip_vs_defrag_user(hooknum)))
-			return NF_STOLEN;
-	}
+	*related = 1;
 
-	iph = ipv6_hdr(skb);
-	offset = sizeof(struct ipv6hdr);
-	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
+	ic = skb_header_pointer(skb, iph->len, sizeof(_icmph), &_icmph);
 	if (ic == NULL)
 		return NF_DROP;
 
-	IP_VS_DBG(12, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n",
-		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
-		  &iph->saddr, &iph->daddr);
-
 	/*
 	 * Work through seeing if this is for us.
 	 * These checks are supposed to be in an order that means easy
@@ -1501,40 +1484,51 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 		return NF_ACCEPT;
 	}
 
+	IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n",
+		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
+		  &iph->saddr, &iph->daddr);
+
 	/* Now find the contained IP header */
-	offset += sizeof(_icmph);
-	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
-	if (cih == NULL)
+	ciph.len = iph->len + sizeof(_icmph);
+	offs_ciph = ciph.len; /* Save ip header offset */
+	ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h);
+	if (ip6h == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
+	ciph.saddr.in6 = ip6h->saddr; /* conn_in_get() handles reverse order */
+	ciph.daddr.in6 = ip6h->daddr;
+	/* skip possible IPv6 exthdrs of contained IPv6 packet */
+	ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL);
+	if (ciph.protocol < 0)
+		return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */
 
 	net = skb_net(skb);
-	pd = ip_vs_proto_data_get(net, cih->nexthdr);
+	pd = ip_vs_proto_data_get(net, ciph.protocol);
 	if (!pd)
 		return NF_ACCEPT;
 	pp = pd->pp;
 
-	/* Is the embedded protocol header present? */
-	/* TODO: we don't support fragmentation at the moment anyways */
-	if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag))
+	/* Cannot handle fragmented embedded protocol */
+	if (ciph.fragoffs)
 		return NF_ACCEPT;
 
-	IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset,
+	IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offs_ciph,
 		      "Checking incoming ICMPv6 for");
 
-	offset += sizeof(struct ipv6hdr);
-
-	ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET6, skb, &ciph, offset, 1);
+	cp = pp->conn_in_get(AF_INET6, skb, &ciph, ciph.len, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
 	/* do the statistics and put it back */
 	ip_vs_in_stats(cp, skb);
-	if (IPPROTO_TCP == cih->nexthdr || IPPROTO_UDP == cih->nexthdr ||
-	    IPPROTO_SCTP == cih->nexthdr)
-		offset += 2 * sizeof(__u16);
-	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum);
+
+	/* Need to mangle contained IPv6 header in ICMPv6 packet */
+	writable = ciph.len;
+	if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol ||
+	    IPPROTO_SCTP == ciph.protocol)
+		writable += 2 * sizeof(__u16); /* Also mangle ports */
+
+	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, writable, hooknum);
 
 	__ip_vs_conn_put(cp);
 
@@ -1570,7 +1564,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (unlikely((skb->pkt_type != PACKET_HOST &&
 		      hooknum != NF_INET_LOCAL_OUT) ||
 		     !skb_dst(skb))) {
-		ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+		ip_vs_fill_iph_skb(af, skb, &iph);
 		IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s"
 			      " ignored in hook %u\n",
 			      skb->pkt_type, iph.protocol,
@@ -1582,7 +1576,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (!net_ipvs(net)->enable)
 		return NF_ACCEPT;
 
-	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(af, skb, &iph);
 
 	/* Bad... Do not break raw sockets */
 	if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT &&
@@ -1602,7 +1596,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 
 			if (related)
 				return verdict;
-			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 	} else
 #endif
@@ -1612,7 +1605,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 
 			if (related)
 				return verdict;
-			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 
 	/* Protocol supported? */
@@ -1622,10 +1614,11 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	pp = pd->pp;
 	/*
 	 * Check if the packet belongs to an existing connection entry
+	 * Only sched first IPv6 fragment.
 	 */
 	cp = pp->conn_in_get(af, skb, &iph, iph.len, 0);
 
-	if (unlikely(!cp)) {
+	if (unlikely(!cp) && !iph.fragoffs) {
 		int v;
 
 		if (!pp->conn_schedule(af, skb, pd, &v, &cp))
@@ -1789,8 +1782,10 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
 {
 	int r;
 	struct net *net;
+	struct ip_vs_iphdr iphdr;
 
-	if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6)
+	ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr);
+	if (iphdr.protocol != IPPROTO_ICMPV6)
 		return NF_ACCEPT;
 
 	/* ipvs enabled in this netns ? */
diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index 8b7dca9ea422..7f3b0cc00b7a 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -215,7 +215,7 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	struct ip_vs_dh_bucket *tbl;
 	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
 
 	IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
 
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index df646ccf08a7..cbd37489ac77 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -479,7 +479,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	struct ip_vs_dest *dest = NULL;
 	struct ip_vs_lblc_entry *en;
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
 
 	IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
 
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 570e31ea427a..161b67972e3f 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -649,7 +649,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	struct ip_vs_dest *dest = NULL;
 	struct ip_vs_lblcr_entry *en;
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
 
 	IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
 
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 1aa5cac748c4..ee4e2e3cc086 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -73,7 +73,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	const char *dptr;
 	int retc;
 
-	ip_vs_fill_iphdr(p->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(p->af, skb, &iph);
 
 	/* Only useful with UDP */
 	if (iph.protocol != IPPROTO_UDP)
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 9f3fb751c491..b903db60341e 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -18,7 +18,7 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	sctp_sctphdr_t *sh, _sctph;
 	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(af, skb, &iph);
 
 	sh = skb_header_pointer(skb, iph.len, sizeof(_sctph), &_sctph);
 	if (sh == NULL)
@@ -72,12 +72,14 @@ sctp_snat_handler(struct sk_buff *skb,
 	struct sk_buff *iter;
 	__be32 crc32;
 
+	struct ip_vs_iphdr iph;
+	ip_vs_fill_iph_skb(cp->af, skb, &iph);
+	sctphoff = iph.len;
+
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		sctphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph.fragoffs)
+		return 1;
 #endif
-		sctphoff = ip_hdrlen(skb);
 
 	/* csum_check requires unshared skb */
 	if (!skb_make_writable(skb, sctphoff + sizeof(*sctph)))
@@ -116,12 +118,14 @@ sctp_dnat_handler(struct sk_buff *skb,
 	struct sk_buff *iter;
 	__be32 crc32;
 
+	struct ip_vs_iphdr iph;
+	ip_vs_fill_iph_skb(cp->af, skb, &iph);
+	sctphoff = iph.len;
+
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		sctphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph.fragoffs)
+		return 1;
 #endif
-		sctphoff = ip_hdrlen(skb);
 
 	/* csum_check requires unshared skb */
 	if (!skb_make_writable(skb, sctphoff + sizeof(*sctph)))
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index cd609cc62721..8a96069c0023 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -40,7 +40,7 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	struct tcphdr _tcph, *th;
 	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(af, skb, &iph);
 
 	th = skb_header_pointer(skb, iph.len, sizeof(_tcph), &_tcph);
 	if (th == NULL) {
@@ -136,12 +136,14 @@ tcp_snat_handler(struct sk_buff *skb,
 	int oldlen;
 	int payload_csum = 0;
 
+	struct ip_vs_iphdr iph;
+	ip_vs_fill_iph_skb(cp->af, skb, &iph);
+	tcphoff = iph.len;
+
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		tcphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph.fragoffs)
+		return 1;
 #endif
-		tcphoff = ip_hdrlen(skb);
 	oldlen = skb->len - tcphoff;
 
 	/* csum_check requires unshared skb */
@@ -216,12 +218,14 @@ tcp_dnat_handler(struct sk_buff *skb,
 	int oldlen;
 	int payload_csum = 0;
 
+	struct ip_vs_iphdr iph;
+	ip_vs_fill_iph_skb(cp->af, skb, &iph);
+	tcphoff = iph.len;
+
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		tcphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph.fragoffs)
+		return 1;
 #endif
-		tcphoff = ip_hdrlen(skb);
 	oldlen = skb->len - tcphoff;
 
 	/* csum_check requires unshared skb */
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 2fedb2dcb3d1..d6f4eeec8b71 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -37,7 +37,7 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	struct udphdr _udph, *uh;
 	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(af, skb, &iph);
 
 	uh = skb_header_pointer(skb, iph.len, sizeof(_udph), &_udph);
 	if (uh == NULL) {
@@ -133,12 +133,14 @@ udp_snat_handler(struct sk_buff *skb,
 	int oldlen;
 	int payload_csum = 0;
 
+	struct ip_vs_iphdr iph;
+	ip_vs_fill_iph_skb(cp->af, skb, &iph);
+	udphoff = iph.len;
+
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		udphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph.fragoffs)
+		return 1;
 #endif
-		udphoff = ip_hdrlen(skb);
 	oldlen = skb->len - udphoff;
 
 	/* csum_check requires unshared skb */
@@ -218,12 +220,14 @@ udp_dnat_handler(struct sk_buff *skb,
 	int oldlen;
 	int payload_csum = 0;
 
+	struct ip_vs_iphdr iph;
+	ip_vs_fill_iph_skb(cp->af, skb, &iph);
+	udphoff = iph.len;
+
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6)
-		udphoff = sizeof(struct ipv6hdr);
-	else
+	if (cp->af == AF_INET6 && iph.fragoffs)
+		return 1;
 #endif
-		udphoff = ip_hdrlen(skb);
 	oldlen = skb->len - udphoff;
 
 	/* csum_check requires unshared skb */
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index 05126521743e..e33126994628 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -228,7 +228,7 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	struct ip_vs_sh_bucket *tbl;
 	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
 
 	IP_VS_DBG(6, "ip_vs_sh_schedule(): Scheduling...\n");
 
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 1060bd52a165..428de7579577 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -679,14 +679,15 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	struct rt6_info *rt;		/* Route to the other host */
 	int mtu;
 	int local;
+	struct ip_vs_iphdr iph;
 
 	EnterFunction(10);
+	ip_vs_fill_iph_skb(cp->af, skb, &iph);
 
 	/* check if it is a connection of no-client-port */
 	if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
 		__be16 _pt, *p;
-		p = skb_header_pointer(skb, sizeof(struct ipv6hdr),
-				       sizeof(_pt), &_pt);
+		p = skb_header_pointer(skb, iph.len, sizeof(_pt), &_pt);
 		if (p == NULL)
 			goto tx_error;
 		ip_vs_conn_fill_cport(cp, *p);
diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c
index bb10b0717f1b..3f9b8cde2450 100644
--- a/net/netfilter/xt_ipvs.c
+++ b/net/netfilter/xt_ipvs.c
@@ -67,7 +67,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		goto out;
 	}
 
-	ip_vs_fill_iphdr(family, skb_network_header(skb), &iph);
+	ip_vs_fill_iph_skb(family, skb, &iph);
 
 	if (data->bitmask & XT_IPVS_PROTO)
 		if ((iph.protocol == data->l4proto) ^
-- 
cgit v1.2.3-55-g7522


From 2f74713d1436b7d2d0506ba1bc5f10915a73bbec Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer
Date: Wed, 26 Sep 2012 14:06:59 +0200
Subject: ipvs: Complete IPv6 fragment handling for IPVS

IPVS now supports fragmented packets, with support from nf_conntrack_reasm.c

Based on patch from: Hans Schillstrom.

IPVS do like conntrack i.e. use the skb->nfct_reasm
(i.e. when all fragments is collected, nf_ct_frag6_output()
starts a "re-play" of all fragments into the interrupted
PREROUTING chain at prio -399 (NF_IP6_PRI_CONNTRACK_DEFRAG+1)
with nfct_reasm pointing to the assembled packet.)

Notice, module nf_defrag_ipv6 must be loaded for this to work.
Report unhandled fragments, and recommend user to load nf_defrag_ipv6.

To handle fw-mark for fragments.  Add a new IPVS hook into prerouting
chain at prio -99 (NF_IP6_PRI_NAT_DST+1) to catch fragments, and copy
fw-mark info from the first packet with an upper layer header.

IPv6 fragment handling should be the last thing on the IPVS IPv6
missing support list.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |  39 +++++++++++++-
 net/netfilter/ipvs/Kconfig      |   6 +--
 net/netfilter/ipvs/ip_vs_conn.c |   2 +-
 net/netfilter/ipvs/ip_vs_core.c | 117 ++++++++++++++++++++++++++++++++--------
 net/netfilter/ipvs/ip_vs_xmit.c |  36 +++++++++----
 5 files changed, 164 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 29265bf4153e..98806b64bef3 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -109,6 +109,7 @@ extern int ip_vs_conn_tab_size;
 struct ip_vs_iphdr {
 	__u32 len;	/* IPv4 simply where L4 starts
 			   IPv6 where L4 Transport Header starts */
+	__u32 thoff_reasm; /* Transport Header Offset in nfct_reasm skb */
 	__u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
 	__s16 protocol;
 	__s32 flags;
@@ -116,6 +117,35 @@ struct ip_vs_iphdr {
 	union nf_inet_addr daddr;
 };
 
+/* Dependency to module: nf_defrag_ipv6 */
+#if defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
+static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
+{
+	return skb->nfct_reasm;
+}
+static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
+				      int len, void *buffer,
+				      const struct ip_vs_iphdr *ipvsh)
+{
+	if (unlikely(ipvsh->fragoffs && skb_nfct_reasm(skb)))
+		return skb_header_pointer(skb_nfct_reasm(skb),
+					  ipvsh->thoff_reasm, len, buffer);
+
+	return skb_header_pointer(skb, offset, len, buffer);
+}
+#else
+static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
+{
+	return NULL;
+}
+static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
+				      int len, void *buffer,
+				      const struct ip_vs_iphdr *ipvsh)
+{
+	return skb_header_pointer(skb, offset, len, buffer);
+}
+#endif
+
 static inline void
 ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr)
 {
@@ -141,12 +171,19 @@ ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr)
 			(struct ipv6hdr *)skb_network_header(skb);
 		iphdr->saddr.in6 = iph->saddr;
 		iphdr->daddr.in6 = iph->daddr;
-		/* ipv6_find_hdr() updates len, flags */
+		/* ipv6_find_hdr() updates len, flags, thoff_reasm */
+		iphdr->thoff_reasm = 0;
 		iphdr->len	 = 0;
 		iphdr->flags	 = 0;
 		iphdr->protocol  = ipv6_find_hdr(skb, &iphdr->len, -1,
 						 &iphdr->fragoffs,
 						 &iphdr->flags);
+		/* get proto from re-assembled packet and it's offset */
+		if (skb_nfct_reasm(skb))
+			iphdr->protocol = ipv6_find_hdr(skb_nfct_reasm(skb),
+							&iphdr->thoff_reasm,
+							-1, NULL, NULL);
+
 	} else
 #endif
 	{
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index a97ae5328ae4..0c3b1670b0d1 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -30,11 +30,9 @@ config	IP_VS_IPV6
 	depends on IPV6 = y || IP_VS = IPV6
 	select IP6_NF_IPTABLES
 	---help---
-	  Add IPv6 support to IPVS. This is incomplete and might be dangerous.
+	  Add IPv6 support to IPVS.
 
-	  See http://www.mindbasket.com/ipvs for more information.
-
-	  Say N if unsure.
+	  Say Y if unsure.
 
 config	IP_VS_DEBUG
 	bool "IP virtual server debugging"
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 1548df9a7524..d6c1c2636dd0 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -314,7 +314,7 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
 	__be16 _ports[2], *pptr;
 	struct net *net = skb_net(skb);
 
-	pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
+	pptr = frag_safe_skb_hp(skb, proto_off, sizeof(_ports), _ports, iph);
 	if (pptr == NULL)
 		return 1;
 
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 19c08425e137..19b89ff94cd5 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -402,8 +402,12 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	unsigned int flags;
 
 	*ignored = 1;
+
+	/*
+	 * IPv6 frags, only the first hit here.
+	 */
 	ip_vs_fill_iph_skb(svc->af, skb, &iph);
-	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
+	pptr = frag_safe_skb_hp(skb, iph.len, sizeof(_ports), _ports, &iph);
 	if (pptr == NULL)
 		return NULL;
 
@@ -507,8 +511,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 #endif
 
 	ip_vs_fill_iph_skb(svc->af, skb, &iph);
-
-	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
+	pptr = frag_safe_skb_hp(skb, iph.len, sizeof(_ports), _ports, &iph);
 	if (pptr == NULL) {
 		ip_vs_service_put(svc);
 		return NF_DROP;
@@ -654,14 +657,6 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
 	return err;
 }
 
-#ifdef CONFIG_IP_VS_IPV6
-static inline int ip_vs_gather_frags_v6(struct sk_buff *skb, u_int32_t user)
-{
-	/* TODO IPv6: Find out what to do here for IPv6 */
-	return 0;
-}
-#endif
-
 static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
 {
 #ifdef CONFIG_IP_VS_IPV6
@@ -939,8 +934,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 	ip_vs_fill_iph_skb(AF_INET6, skb, ipvsh);
 
 	*related = 1;
-
-	ic = skb_header_pointer(skb, ipvsh->len, sizeof(_icmph), &_icmph);
+	ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph, ipvsh);
 	if (ic == NULL)
 		return NF_DROP;
 
@@ -955,6 +949,11 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 		*related = 0;
 		return NF_ACCEPT;
 	}
+	/* Fragment header that is before ICMP header tells us that:
+	 * it's not an error message since they can't be fragmented.
+	 */
+	if (ipvsh->flags & IP6T_FH_F_FRAG)
+		return NF_DROP;
 
 	IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n",
 		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
@@ -1117,6 +1116,12 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	ip_vs_fill_iph_skb(af, skb, &iph);
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
+		if (!iph.fragoffs && skb_nfct_reasm(skb)) {
+			struct sk_buff *reasm = skb_nfct_reasm(skb);
+			/* Save fw mark for coming frags */
+			reasm->ipvs_property = 1;
+			reasm->mark = skb->mark;
+		}
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
 			int related;
 			int verdict = ip_vs_out_icmp_v6(skb, &related,
@@ -1124,7 +1129,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 
 			if (related)
 				return verdict;
-			ip_vs_fill_iph_skb(af, skb, &iph);
 		}
 	} else
 #endif
@@ -1134,7 +1138,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 
 			if (related)
 				return verdict;
-			ip_vs_fill_ip4hdr(skb_network_header(skb), &iph);
 		}
 
 	pd = ip_vs_proto_data_get(net, iph.protocol);
@@ -1167,8 +1170,8 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	     pp->protocol == IPPROTO_SCTP)) {
 		__be16 _ports[2], *pptr;
 
-		pptr = skb_header_pointer(skb, iph.len,
-					  sizeof(_ports), _ports);
+		pptr = frag_safe_skb_hp(skb, iph.len,
+					 sizeof(_ports), _ports, &iph);
 		if (pptr == NULL)
 			return NF_ACCEPT;	/* Not for me */
 		if (ip_vs_lookup_real_service(net, af, iph.protocol,
@@ -1468,7 +1471,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	*related = 1;
 
-	ic = skb_header_pointer(skb, iph->len, sizeof(_icmph), &_icmph);
+	ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph, iph);
 	if (ic == NULL)
 		return NF_DROP;
 
@@ -1483,6 +1486,11 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 		*related = 0;
 		return NF_ACCEPT;
 	}
+	/* Fragment header that is before ICMP header tells us that:
+	 * it's not an error message since they can't be fragmented.
+	 */
+	if (iph->flags & IP6T_FH_F_FRAG)
+		return NF_DROP;
 
 	IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n",
 		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
@@ -1514,10 +1522,20 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offs_ciph,
 		      "Checking incoming ICMPv6 for");
 
-	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET6, skb, &ciph, ciph.len, 1);
+	/* The embedded headers contain source and dest in reverse order
+	 * if not from localhost
+	 */
+	cp = pp->conn_in_get(AF_INET6, skb, &ciph, ciph.len,
+			     (hooknum == NF_INET_LOCAL_OUT) ? 0 : 1);
+
 	if (!cp)
 		return NF_ACCEPT;
+	/* VS/TUN, VS/DR and LOCALNODE just let it go */
+	if ((hooknum == NF_INET_LOCAL_OUT) &&
+	    (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) {
+		__ip_vs_conn_put(cp);
+		return NF_ACCEPT;
+	}
 
 	/* do the statistics and put it back */
 	ip_vs_in_stats(cp, skb);
@@ -1590,6 +1608,12 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
+		if (!iph.fragoffs && skb_nfct_reasm(skb)) {
+			struct sk_buff *reasm = skb_nfct_reasm(skb);
+			/* Save fw mark for coming frags. */
+			reasm->ipvs_property = 1;
+			reasm->mark = skb->mark;
+		}
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
 			int related;
 			int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum);
@@ -1614,13 +1638,16 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	pp = pd->pp;
 	/*
 	 * Check if the packet belongs to an existing connection entry
-	 * Only sched first IPv6 fragment.
 	 */
 	cp = pp->conn_in_get(af, skb, &iph, iph.len, 0);
 
 	if (unlikely(!cp) && !iph.fragoffs) {
+		/* No (second) fragments need to enter here, as nf_defrag_ipv6
+		 * replayed fragment zero will already have created the cp
+		 */
 		int v;
 
+		/* Schedule and create new connection entry into &cp */
 		if (!pp->conn_schedule(af, skb, pd, &v, &cp))
 			return v;
 	}
@@ -1629,6 +1656,14 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 		/* sorry, all this trouble for a no-hit :) */
 		IP_VS_DBG_PKT(12, af, pp, skb, 0,
 			      "ip_vs_in: packet continues traversal as normal");
+		if (iph.fragoffs && !skb_nfct_reasm(skb)) {
+			/* Fragment that couldn't be mapped to a conn entry
+			 * and don't have any pointer to a reasm skb
+			 * is missing module nf_defrag_ipv6
+			 */
+			IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
+			IP_VS_DBG_PKT(7, af, pp, skb, 0, "unhandled fragment");
+		}
 		return NF_ACCEPT;
 	}
 
@@ -1712,6 +1747,38 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb,
 
 #ifdef CONFIG_IP_VS_IPV6
 
+/*
+ * AF_INET6 fragment handling
+ * Copy info from first fragment, to the rest of them.
+ */
+static unsigned int
+ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb,
+		     const struct net_device *in,
+		     const struct net_device *out,
+		     int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *reasm = skb_nfct_reasm(skb);
+	struct net *net;
+
+	/* Skip if not a "replay" from nf_ct_frag6_output or first fragment.
+	 * ipvs_property is set when checking first fragment
+	 * in ip_vs_in() and ip_vs_out().
+	 */
+	if (reasm)
+		IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property);
+	if (!reasm || !reasm->ipvs_property)
+		return NF_ACCEPT;
+
+	net = skb_net(skb);
+	if (!net_ipvs(net)->enable)
+		return NF_ACCEPT;
+
+	/* Copy stored fw mark, saved in ip_vs_{in,out} */
+	skb->mark = reasm->mark;
+
+	return NF_ACCEPT;
+}
+
 /*
  *	AF_INET6 handler in NF_INET_LOCAL_IN chain
  *	Schedule and forward packets from remote clients
@@ -1851,6 +1918,14 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.priority	= 100,
 	},
 #ifdef CONFIG_IP_VS_IPV6
+	/* After mangle & nat fetch 2:nd fragment and following */
+	{
+		.hook		= ip_vs_preroute_frag6,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP6_PRI_NAT_DST + 1,
+	},
 	/* After packet filtering, change source only for VS/NAT */
 	{
 		.hook		= ip_vs_reply6,
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 428de7579577..a8b75fc8e6a8 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -496,13 +496,15 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		     struct ip_vs_protocol *pp)
 {
 	struct rt6_info *rt;			/* Route to the other host */
-	struct ipv6hdr  *iph = ipv6_hdr(skb);
+	struct ip_vs_iphdr iph;
 	int    mtu;
 
 	EnterFunction(10);
+	ip_vs_fill_iph_skb(cp->af, skb, &iph);
 
-	if (!(rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr, NULL, 0,
-					 IP_VS_RT_MODE_NON_LOCAL)))
+	rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph.daddr.in6, NULL, 0,
+				   IP_VS_RT_MODE_NON_LOCAL);
+	if (!rt)
 		goto tx_error_icmp;
 
 	/* MTU checking */
@@ -513,7 +515,9 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		/* only send ICMP too big on first fragment */
+		if (!iph.fragoffs)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		dst_release(&rt->dst);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error;
@@ -685,7 +689,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	ip_vs_fill_iph_skb(cp->af, skb, &iph);
 
 	/* check if it is a connection of no-client-port */
-	if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
+	if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !iph.fragoffs)) {
 		__be16 _pt, *p;
 		p = skb_header_pointer(skb, iph.len, sizeof(_pt), &_pt);
 		if (p == NULL)
@@ -735,7 +739,9 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		/* only send ICMP too big on first fragment */
+		if (!iph.fragoffs)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0,
 				 "ip_vs_nat_xmit_v6(): frag needed for");
 		goto tx_error_put;
@@ -940,8 +946,10 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	unsigned int max_headroom;	/* The extra header space needed */
 	int    mtu;
 	int ret;
+	struct ip_vs_iphdr ipvsh;
 
 	EnterFunction(10);
+	ip_vs_fill_iph_skb(cp->af, skb, &ipvsh);
 
 	if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6,
 					 &saddr, 1, (IP_VS_RT_MODE_LOCAL |
@@ -970,7 +978,9 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		/* only send ICMP too big on first fragment */
+		if (!ipvsh.fragoffs)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;
 	}
@@ -1116,8 +1126,10 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 {
 	struct rt6_info *rt;			/* Route to the other host */
 	int    mtu;
+	struct ip_vs_iphdr iph;
 
 	EnterFunction(10);
+	ip_vs_fill_iph_skb(cp->af, skb, &iph);
 
 	if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
 					 0, (IP_VS_RT_MODE_LOCAL |
@@ -1136,7 +1148,9 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		/* only send ICMP too big on first fragment */
+		if (!iph.fragoffs)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		dst_release(&rt->dst);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error;
@@ -1308,8 +1322,10 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	int rc;
 	int local;
 	int rt_mode;
+	struct ip_vs_iphdr iph;
 
 	EnterFunction(10);
+	ip_vs_fill_iph_skb(cp->af, skb, &iph);
 
 	/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
 	   forwarded directly here, because there is no need to
@@ -1372,7 +1388,9 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 			skb->dev = net->loopback_dev;
 		}
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		/* only send ICMP too big on first fragment */
+		if (!iph.fragoffs)
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;
 	}
-- 
cgit v1.2.3-55-g7522


From d4383f04d145cce8b855c463f40020639ef83ea0 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer
Date: Wed, 26 Sep 2012 14:07:17 +0200
Subject: ipvs: API change to avoid rescan of IPv6 exthdr

Reduce the number of times we scan/skip the IPv6 exthdrs.

This patch contains a lot of API changes.  This is done, to avoid
repeating the scan of finding the IPv6 headers, via ipv6_find_hdr(),
which is called by ip_vs_fill_iph_skb().

Finding the IPv6 headers is done as early as possible, and passed on
as a pointer "struct ip_vs_iphdr *" to the affected functions.

This patch reduce/removes 19 calls to ip_vs_fill_iph_skb().

Notice, I have choosen, not to change the API of function
pointer "(*schedule)" (in struct ip_vs_scheduler) as it can be
used by external schedulers, via {un,}register_ip_vs_scheduler.
Only 4 out of 10 schedulers use info from ip_vs_iphdr*, and when
they do, they are only interested in iph->{s,d}addr.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                     |  81 +++++++++++-----------
 net/netfilter/ipvs/ip_vs_conn.c         |  15 ++---
 net/netfilter/ipvs/ip_vs_core.c         | 116 ++++++++++++++------------------
 net/netfilter/ipvs/ip_vs_proto_ah_esp.c |   9 ++-
 net/netfilter/ipvs/ip_vs_proto_sctp.c   |  42 +++++-------
 net/netfilter/ipvs/ip_vs_proto_tcp.c    |  40 +++++------
 net/netfilter/ipvs/ip_vs_proto_udp.c    |  41 +++++------
 net/netfilter/ipvs/ip_vs_xmit.c         |  58 +++++++---------
 net/netfilter/xt_ipvs.c                 |   2 +-
 9 files changed, 175 insertions(+), 229 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 98806b64bef3..a681ad65b735 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -487,27 +487,26 @@ struct ip_vs_protocol {
 
 	int (*conn_schedule)(int af, struct sk_buff *skb,
 			     struct ip_vs_proto_data *pd,
-			     int *verdict, struct ip_vs_conn **cpp);
+			     int *verdict, struct ip_vs_conn **cpp,
+			     struct ip_vs_iphdr *iph);
 
 	struct ip_vs_conn *
 	(*conn_in_get)(int af,
 		       const struct sk_buff *skb,
 		       const struct ip_vs_iphdr *iph,
-		       unsigned int proto_off,
 		       int inverse);
 
 	struct ip_vs_conn *
 	(*conn_out_get)(int af,
 			const struct sk_buff *skb,
 			const struct ip_vs_iphdr *iph,
-			unsigned int proto_off,
 			int inverse);
 
-	int (*snat_handler)(struct sk_buff *skb,
-			    struct ip_vs_protocol *pp, struct ip_vs_conn *cp);
+	int (*snat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp,
+			    struct ip_vs_conn *cp, struct ip_vs_iphdr *iph);
 
-	int (*dnat_handler)(struct sk_buff *skb,
-			    struct ip_vs_protocol *pp, struct ip_vs_conn *cp);
+	int (*dnat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp,
+			    struct ip_vs_conn *cp, struct ip_vs_iphdr *iph);
 
 	int (*csum_check)(int af, struct sk_buff *skb,
 			  struct ip_vs_protocol *pp);
@@ -607,7 +606,7 @@ struct ip_vs_conn {
 	   NF_ACCEPT can be returned when destination is local.
 	 */
 	int (*packet_xmit)(struct sk_buff *skb, struct ip_vs_conn *cp,
-			   struct ip_vs_protocol *pp);
+			   struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 
 	/* Note: we can group the following members into a structure,
 	   in order to save more space, and the following members are
@@ -858,13 +857,11 @@ struct ip_vs_app {
 
 	struct ip_vs_conn *
 	(*conn_in_get)(const struct sk_buff *skb, struct ip_vs_app *app,
-		       const struct iphdr *iph, unsigned int proto_off,
-		       int inverse);
+		       const struct iphdr *iph, int inverse);
 
 	struct ip_vs_conn *
 	(*conn_out_get)(const struct sk_buff *skb, struct ip_vs_app *app,
-			const struct iphdr *iph, unsigned int proto_off,
-			int inverse);
+			const struct iphdr *iph, int inverse);
 
 	int (*state_transition)(struct ip_vs_conn *cp, int direction,
 				const struct sk_buff *skb,
@@ -1163,14 +1160,12 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p);
 
 struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
 					    const struct ip_vs_iphdr *iph,
-					    unsigned int proto_off,
 					    int inverse);
 
 struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p);
 
 struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
 					     const struct ip_vs_iphdr *iph,
-					     unsigned int proto_off,
 					     int inverse);
 
 /* put back the conn without restarting its timer */
@@ -1343,9 +1338,10 @@ extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
 extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
 extern struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
-	       struct ip_vs_proto_data *pd, int *ignored);
+	       struct ip_vs_proto_data *pd, int *ignored,
+	       struct ip_vs_iphdr *iph);
 extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-			struct ip_vs_proto_data *pd);
+			struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph);
 
 extern void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);
 
@@ -1404,33 +1400,38 @@ extern void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
 /*
  *	Various IPVS packet transmitters (from ip_vs_xmit.c)
  */
-extern int ip_vs_null_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_bypass_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_nat_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_tunnel_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_dr_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_icmp_xmit
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp,
- int offset, unsigned int hooknum);
+extern int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			   struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+extern int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			     struct ip_vs_protocol *pp,
+			     struct ip_vs_iphdr *iph);
+extern int ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			  struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+extern int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			     struct ip_vs_protocol *pp,
+			     struct ip_vs_iphdr *iph);
+extern int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			 struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+extern int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+			   struct ip_vs_protocol *pp, int offset,
+			   unsigned int hooknum, struct ip_vs_iphdr *iph);
 extern void ip_vs_dst_reset(struct ip_vs_dest *dest);
 
 #ifdef CONFIG_IP_VS_IPV6
-extern int ip_vs_bypass_xmit_v6
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_nat_xmit_v6
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_tunnel_xmit_v6
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_dr_xmit_v6
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern int ip_vs_icmp_xmit_v6
-(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp,
- int offset, unsigned int hooknum);
+extern int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+				struct ip_vs_protocol *pp,
+				struct ip_vs_iphdr *iph);
+extern int ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+			     struct ip_vs_protocol *pp,
+			     struct ip_vs_iphdr *iph);
+extern int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+				struct ip_vs_protocol *pp,
+				struct ip_vs_iphdr *iph);
+extern int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+			    struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+extern int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+			      struct ip_vs_protocol *pp, int offset,
+			      unsigned int hooknum, struct ip_vs_iphdr *iph);
 #endif
 
 #ifdef CONFIG_SYSCTL
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index d6c1c2636dd0..30e764ad021f 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -308,13 +308,12 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
 static int
 ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
 			    const struct ip_vs_iphdr *iph,
-			    unsigned int proto_off, int inverse,
-			    struct ip_vs_conn_param *p)
+			    int inverse, struct ip_vs_conn_param *p)
 {
 	__be16 _ports[2], *pptr;
 	struct net *net = skb_net(skb);
 
-	pptr = frag_safe_skb_hp(skb, proto_off, sizeof(_ports), _ports, iph);
+	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
 	if (pptr == NULL)
 		return 1;
 
@@ -329,12 +328,11 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
 
 struct ip_vs_conn *
 ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
-			const struct ip_vs_iphdr *iph,
-			unsigned int proto_off, int inverse)
+			const struct ip_vs_iphdr *iph, int inverse)
 {
 	struct ip_vs_conn_param p;
 
-	if (ip_vs_conn_fill_param_proto(af, skb, iph, proto_off, inverse, &p))
+	if (ip_vs_conn_fill_param_proto(af, skb, iph, inverse, &p))
 		return NULL;
 
 	return ip_vs_conn_in_get(&p);
@@ -432,12 +430,11 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 
 struct ip_vs_conn *
 ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
-			 const struct ip_vs_iphdr *iph,
-			 unsigned int proto_off, int inverse)
+			 const struct ip_vs_iphdr *iph, int inverse)
 {
 	struct ip_vs_conn_param p;
 
-	if (ip_vs_conn_fill_param_proto(af, skb, iph, proto_off, inverse, &p))
+	if (ip_vs_conn_fill_param_proto(af, skb, iph, inverse, &p))
 		return NULL;
 
 	return ip_vs_conn_out_get(&p);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 19b89ff94cd5..fb45640dc1fb 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -222,11 +222,10 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
  */
 static struct ip_vs_conn *
 ip_vs_sched_persist(struct ip_vs_service *svc,
-		    struct sk_buff *skb,
-		    __be16 src_port, __be16 dst_port, int *ignored)
+		    struct sk_buff *skb, __be16 src_port, __be16 dst_port,
+		    int *ignored, struct ip_vs_iphdr *iph)
 {
 	struct ip_vs_conn *cp = NULL;
-	struct ip_vs_iphdr iph;
 	struct ip_vs_dest *dest;
 	struct ip_vs_conn *ct;
 	__be16 dport = 0;		/* destination port to forward */
@@ -236,20 +235,18 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	union nf_inet_addr snet;	/* source network of the client,
 					   after masking */
 
-	ip_vs_fill_iph_skb(svc->af, skb, &iph);
-
 	/* Mask saddr with the netmask to adjust template granularity */
 #ifdef CONFIG_IP_VS_IPV6
 	if (svc->af == AF_INET6)
-		ipv6_addr_prefix(&snet.in6, &iph.saddr.in6, svc->netmask);
+		ipv6_addr_prefix(&snet.in6, &iph->saddr.in6, svc->netmask);
 	else
 #endif
-		snet.ip = iph.saddr.ip & svc->netmask;
+		snet.ip = iph->saddr.ip & svc->netmask;
 
 	IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u "
 		      "mnet %s\n",
-		      IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(src_port),
-		      IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(dst_port),
+		      IP_VS_DBG_ADDR(svc->af, &iph->saddr), ntohs(src_port),
+		      IP_VS_DBG_ADDR(svc->af, &iph->daddr), ntohs(dst_port),
 		      IP_VS_DBG_ADDR(svc->af, &snet));
 
 	/*
@@ -266,8 +263,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	 * is created for other persistent services.
 	 */
 	{
-		int protocol = iph.protocol;
-		const union nf_inet_addr *vaddr = &iph.daddr;
+		int protocol = iph->protocol;
+		const union nf_inet_addr *vaddr = &iph->daddr;
 		__be16 vport = 0;
 
 		if (dst_port == svc->port) {
@@ -342,14 +339,14 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		dport = dest->port;
 
 	flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
-		 && iph.protocol == IPPROTO_UDP)?
+		 && iph->protocol == IPPROTO_UDP) ?
 		IP_VS_CONN_F_ONE_PACKET : 0;
 
 	/*
 	 *    Create a new connection according to the template
 	 */
-	ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr,
-			      src_port, &iph.daddr, dst_port, &param);
+	ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, &iph->saddr,
+			      src_port, &iph->daddr, dst_port, &param);
 
 	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
 	if (cp == NULL) {
@@ -392,22 +389,20 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
  */
 struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
-	       struct ip_vs_proto_data *pd, int *ignored)
+	       struct ip_vs_proto_data *pd, int *ignored,
+	       struct ip_vs_iphdr *iph)
 {
 	struct ip_vs_protocol *pp = pd->pp;
 	struct ip_vs_conn *cp = NULL;
-	struct ip_vs_iphdr iph;
 	struct ip_vs_dest *dest;
 	__be16 _ports[2], *pptr;
 	unsigned int flags;
 
 	*ignored = 1;
-
 	/*
 	 * IPv6 frags, only the first hit here.
 	 */
-	ip_vs_fill_iph_skb(svc->af, skb, &iph);
-	pptr = frag_safe_skb_hp(skb, iph.len, sizeof(_ports), _ports, &iph);
+	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
 	if (pptr == NULL)
 		return NULL;
 
@@ -427,7 +422,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	 *    Do not schedule replies from local real server.
 	 */
 	if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
-	    (cp = pp->conn_in_get(svc->af, skb, &iph, iph.len, 1))) {
+	    (cp = pp->conn_in_get(svc->af, skb, iph, 1))) {
 		IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
 			      "Not scheduling reply for existing connection");
 		__ip_vs_conn_put(cp);
@@ -438,7 +433,8 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	 *    Persistent service
 	 */
 	if (svc->flags & IP_VS_SVC_F_PERSISTENT)
-		return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored);
+		return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored,
+					   iph);
 
 	*ignored = 0;
 
@@ -460,7 +456,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	}
 
 	flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
-		 && iph.protocol == IPPROTO_UDP)?
+		 && iph->protocol == IPPROTO_UDP) ?
 		IP_VS_CONN_F_ONE_PACKET : 0;
 
 	/*
@@ -469,9 +465,9 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	{
 		struct ip_vs_conn_param p;
 
-		ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
-				      &iph.saddr, pptr[0], &iph.daddr, pptr[1],
-				      &p);
+		ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
+				      &iph->saddr, pptr[0], &iph->daddr,
+				      pptr[1], &p);
 		cp = ip_vs_conn_new(&p, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
 				    flags, dest, skb->mark);
@@ -500,18 +496,16 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
  *  no destination is available for a new connection.
  */
 int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-		struct ip_vs_proto_data *pd)
+		struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph)
 {
 	__be16 _ports[2], *pptr;
-	struct ip_vs_iphdr iph;
 #ifdef CONFIG_SYSCTL
 	struct net *net;
 	struct netns_ipvs *ipvs;
 	int unicast;
 #endif
 
-	ip_vs_fill_iph_skb(svc->af, skb, &iph);
-	pptr = frag_safe_skb_hp(skb, iph.len, sizeof(_ports), _ports, &iph);
+	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
 	if (pptr == NULL) {
 		ip_vs_service_put(svc);
 		return NF_DROP;
@@ -522,10 +516,10 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (svc->af == AF_INET6)
-		unicast = ipv6_addr_type(&iph.daddr.in6) & IPV6_ADDR_UNICAST;
+		unicast = ipv6_addr_type(&iph->daddr.in6) & IPV6_ADDR_UNICAST;
 	else
 #endif
-		unicast = (inet_addr_type(net, iph.daddr.ip) == RTN_UNICAST);
+		unicast = (inet_addr_type(net, iph->daddr.ip) == RTN_UNICAST);
 
 	/* if it is fwmark-based service, the cache_bypass sysctl is up
 	   and the destination is a non-local unicast, then create
@@ -535,7 +529,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		int ret;
 		struct ip_vs_conn *cp;
 		unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
-				      iph.protocol == IPPROTO_UDP)?
+				      iph->protocol == IPPROTO_UDP) ?
 				      IP_VS_CONN_F_ONE_PACKET : 0;
 		union nf_inet_addr daddr =  { .all = { 0, 0, 0, 0 } };
 
@@ -545,9 +539,9 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
 		{
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
-					      &iph.saddr, pptr[0],
-					      &iph.daddr, pptr[1], &p);
+			ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
+					      &iph->saddr, pptr[0],
+					      &iph->daddr, pptr[1], &p);
 			cp = ip_vs_conn_new(&p, &daddr, 0,
 					    IP_VS_CONN_F_BYPASS | flags,
 					    NULL, skb->mark);
@@ -562,7 +556,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 
 		/* transmit the first SYN packet */
-		ret = cp->packet_xmit(skb, cp, pd->pp);
+		ret = cp->packet_xmit(skb, cp, pd->pp, iph);
 		/* do not touch skb anymore */
 
 		atomic_inc(&cp->in_pkts);
@@ -908,7 +902,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
 	ip_vs_fill_ip4hdr(cih, &ciph);
 	ciph.len += offset;
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1);
+	cp = pp->conn_out_get(AF_INET, skb, &ciph, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -919,7 +913,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
 
 #ifdef CONFIG_IP_VS_IPV6
 static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
-			     unsigned int hooknum)
+			     unsigned int hooknum, struct ip_vs_iphdr *ipvsh)
 {
 	struct icmp6hdr	_icmph, *ic;
 	struct ipv6hdr _ip6h, *ip6h; /* The ip header contained within ICMP */
@@ -929,10 +923,6 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 	union nf_inet_addr snet;
 	unsigned int writable;
 
-	struct ip_vs_iphdr ipvsh_stack;
-	struct ip_vs_iphdr *ipvsh = &ipvsh_stack;
-	ip_vs_fill_iph_skb(AF_INET6, skb, ipvsh);
-
 	*related = 1;
 	ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph, ipvsh);
 	if (ic == NULL)
@@ -976,7 +966,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 		return NF_ACCEPT;
 
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET6, skb, &ciph, ciph.len, 1);
+	cp = pp->conn_out_get(AF_INET6, skb, &ciph, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -1016,17 +1006,17 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len)
  */
 static unsigned int
 handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		struct ip_vs_conn *cp, int ihl)
+		struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	struct ip_vs_protocol *pp = pd->pp;
 
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");
 
-	if (!skb_make_writable(skb, ihl))
+	if (!skb_make_writable(skb, iph->len))
 		goto drop;
 
 	/* mangle the packet */
-	if (pp->snat_handler && !pp->snat_handler(skb, pp, cp))
+	if (pp->snat_handler && !pp->snat_handler(skb, pp, cp, iph))
 		goto drop;
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1125,7 +1115,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
 			int related;
 			int verdict = ip_vs_out_icmp_v6(skb, &related,
-							hooknum);
+							hooknum, &iph);
 
 			if (related)
 				return verdict;
@@ -1160,10 +1150,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	/*
 	 * Check if the packet belongs to an existing entry
 	 */
-	cp = pp->conn_out_get(af, skb, &iph, iph.len, 0);
+	cp = pp->conn_out_get(af, skb, &iph, 0);
 
 	if (likely(cp))
-		return handle_response(af, skb, pd, cp, iph.len);
+		return handle_response(af, skb, pd, cp, &iph);
 	if (sysctl_nat_icmp_send(net) &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
@@ -1375,7 +1365,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 	/* The embedded headers contain source and dest in reverse order.
 	 * For IPIP this is error for request, not for reply.
 	 */
-	cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, ipip ? 0 : 1);
+	cp = pp->conn_in_get(AF_INET, skb, &ciph, ipip ? 0 : 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -1444,7 +1434,7 @@ ignore_ipip:
 	ip_vs_in_stats(cp, skb);
 	if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
 		offset += 2 * sizeof(__u16);
-	verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum);
+	verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph);
 
 out:
 	__ip_vs_conn_put(cp);
@@ -1453,8 +1443,8 @@ out:
 }
 
 #ifdef CONFIG_IP_VS_IPV6
-static int
-ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
+static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related,
+			    unsigned int hooknum, struct ip_vs_iphdr *iph)
 {
 	struct net *net = NULL;
 	struct ipv6hdr _ip6h, *ip6h;
@@ -1465,10 +1455,6 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	struct ip_vs_proto_data *pd;
 	unsigned int offs_ciph, writable, verdict;
 
-	struct ip_vs_iphdr iph_stack;
-	struct ip_vs_iphdr *iph = &iph_stack;
-	ip_vs_fill_iph_skb(AF_INET6, skb, iph);
-
 	*related = 1;
 
 	ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph, iph);
@@ -1525,7 +1511,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	/* The embedded headers contain source and dest in reverse order
 	 * if not from localhost
 	 */
-	cp = pp->conn_in_get(AF_INET6, skb, &ciph, ciph.len,
+	cp = pp->conn_in_get(AF_INET6, skb, &ciph,
 			     (hooknum == NF_INET_LOCAL_OUT) ? 0 : 1);
 
 	if (!cp)
@@ -1546,7 +1532,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	    IPPROTO_SCTP == ciph.protocol)
 		writable += 2 * sizeof(__u16); /* Also mangle ports */
 
-	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, writable, hooknum);
+	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, writable, hooknum, &ciph);
 
 	__ip_vs_conn_put(cp);
 
@@ -1616,7 +1602,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 		}
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
 			int related;
-			int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum);
+			int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum,
+						       &iph);
 
 			if (related)
 				return verdict;
@@ -1639,8 +1626,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	/*
 	 * Check if the packet belongs to an existing connection entry
 	 */
-	cp = pp->conn_in_get(af, skb, &iph, iph.len, 0);
-
+	cp = pp->conn_in_get(af, skb, &iph, 0);
 	if (unlikely(!cp) && !iph.fragoffs) {
 		/* No (second) fragments need to enter here, as nf_defrag_ipv6
 		 * replayed fragment zero will already have created the cp
@@ -1648,7 +1634,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 		int v;
 
 		/* Schedule and create new connection entry into &cp */
-		if (!pp->conn_schedule(af, skb, pd, &v, &cp))
+		if (!pp->conn_schedule(af, skb, pd, &v, &cp, &iph))
 			return v;
 	}
 
@@ -1686,7 +1672,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	ip_vs_in_stats(cp, skb);
 	ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 	if (cp->packet_xmit)
-		ret = cp->packet_xmit(skb, cp, pp);
+		ret = cp->packet_xmit(skb, cp, pp, &iph);
 		/* do not touch skb anymore */
 	else {
 		IP_VS_DBG_RL("warning: packet_xmit is null");
@@ -1860,7 +1846,7 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
 	if (!net_ipvs(net)->enable)
 		return NF_ACCEPT;
 
-	return ip_vs_in_icmp_v6(skb, &r, hooknum);
+	return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr);
 }
 #endif
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
index 5b8eb8b12c3e..5de3dd312c0f 100644
--- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
@@ -57,7 +57,7 @@ ah_esp_conn_fill_param_proto(struct net *net, int af,
 
 static struct ip_vs_conn *
 ah_esp_conn_in_get(int af, const struct sk_buff *skb,
-		   const struct ip_vs_iphdr *iph, unsigned int proto_off,
+		   const struct ip_vs_iphdr *iph,
 		   int inverse)
 {
 	struct ip_vs_conn *cp;
@@ -85,9 +85,7 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb,
 
 static struct ip_vs_conn *
 ah_esp_conn_out_get(int af, const struct sk_buff *skb,
-		    const struct ip_vs_iphdr *iph,
-		    unsigned int proto_off,
-		    int inverse)
+		    const struct ip_vs_iphdr *iph, int inverse)
 {
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
@@ -110,7 +108,8 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
 
 static int
 ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		     int *verdict, struct ip_vs_conn **cpp)
+		     int *verdict, struct ip_vs_conn **cpp,
+		     struct ip_vs_iphdr *iph)
 {
 	/*
 	 * AH/ESP is only related traffic. Pass the packet to IP stack.
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index b903db60341e..746048b13ef3 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -10,28 +10,26 @@
 
 static int
 sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		   int *verdict, struct ip_vs_conn **cpp)
+		   int *verdict, struct ip_vs_conn **cpp,
+		   struct ip_vs_iphdr *iph)
 {
 	struct net *net;
 	struct ip_vs_service *svc;
 	sctp_chunkhdr_t _schunkh, *sch;
 	sctp_sctphdr_t *sh, _sctph;
-	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iph_skb(af, skb, &iph);
-
-	sh = skb_header_pointer(skb, iph.len, sizeof(_sctph), &_sctph);
+	sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph);
 	if (sh == NULL)
 		return 0;
 
-	sch = skb_header_pointer(skb, iph.len + sizeof(sctp_sctphdr_t),
+	sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t),
 				 sizeof(_schunkh), &_schunkh);
 	if (sch == NULL)
 		return 0;
 	net = skb_net(skb);
 	if ((sch->type == SCTP_CID_INIT) &&
-	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
-				     &iph.daddr, sh->dest))) {
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
+				     &iph->daddr, sh->dest))) {
 		int ignored;
 
 		if (ip_vs_todrop(net_ipvs(net))) {
@@ -47,10 +45,10 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pd);
+				*verdict = ip_vs_leave(svc, skb, pd, iph);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -64,20 +62,16 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 }
 
 static int
-sctp_snat_handler(struct sk_buff *skb,
-		  struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		  struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	sctp_sctphdr_t *sctph;
-	unsigned int sctphoff;
+	unsigned int sctphoff = iph->len;
 	struct sk_buff *iter;
 	__be32 crc32;
 
-	struct ip_vs_iphdr iph;
-	ip_vs_fill_iph_skb(cp->af, skb, &iph);
-	sctphoff = iph.len;
-
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6 && iph.fragoffs)
+	if (cp->af == AF_INET6 && iph->fragoffs)
 		return 1;
 #endif
 
@@ -110,20 +104,16 @@ sctp_snat_handler(struct sk_buff *skb,
 }
 
 static int
-sctp_dnat_handler(struct sk_buff *skb,
-		  struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		  struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	sctp_sctphdr_t *sctph;
-	unsigned int sctphoff;
+	unsigned int sctphoff = iph->len;
 	struct sk_buff *iter;
 	__be32 crc32;
 
-	struct ip_vs_iphdr iph;
-	ip_vs_fill_iph_skb(cp->af, skb, &iph);
-	sctphoff = iph.len;
-
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6 && iph.fragoffs)
+	if (cp->af == AF_INET6 && iph->fragoffs)
 		return 1;
 #endif
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 8a96069c0023..9af653a75825 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -33,16 +33,14 @@
 
 static int
 tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		  int *verdict, struct ip_vs_conn **cpp)
+		  int *verdict, struct ip_vs_conn **cpp,
+		  struct ip_vs_iphdr *iph)
 {
 	struct net *net;
 	struct ip_vs_service *svc;
 	struct tcphdr _tcph, *th;
-	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iph_skb(af, skb, &iph);
-
-	th = skb_header_pointer(skb, iph.len, sizeof(_tcph), &_tcph);
+	th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
 	if (th == NULL) {
 		*verdict = NF_DROP;
 		return 0;
@@ -50,8 +48,8 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	net = skb_net(skb);
 	/* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */
 	if (th->syn &&
-	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
-				     &iph.daddr, th->dest))) {
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
+				     &iph->daddr, th->dest))) {
 		int ignored;
 
 		if (ip_vs_todrop(net_ipvs(net))) {
@@ -68,10 +66,10 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pd);
+				*verdict = ip_vs_leave(svc, skb, pd, iph);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -128,20 +126,16 @@ tcp_partial_csum_update(int af, struct tcphdr *tcph,
 
 
 static int
-tcp_snat_handler(struct sk_buff *skb,
-		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		 struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	struct tcphdr *tcph;
-	unsigned int tcphoff;
+	unsigned int tcphoff = iph->len;
 	int oldlen;
 	int payload_csum = 0;
 
-	struct ip_vs_iphdr iph;
-	ip_vs_fill_iph_skb(cp->af, skb, &iph);
-	tcphoff = iph.len;
-
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6 && iph.fragoffs)
+	if (cp->af == AF_INET6 && iph->fragoffs)
 		return 1;
 #endif
 	oldlen = skb->len - tcphoff;
@@ -210,20 +204,16 @@ tcp_snat_handler(struct sk_buff *skb,
 
 
 static int
-tcp_dnat_handler(struct sk_buff *skb,
-		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		 struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	struct tcphdr *tcph;
-	unsigned int tcphoff;
+	unsigned int tcphoff = iph->len;
 	int oldlen;
 	int payload_csum = 0;
 
-	struct ip_vs_iphdr iph;
-	ip_vs_fill_iph_skb(cp->af, skb, &iph);
-	tcphoff = iph.len;
-
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6 && iph.fragoffs)
+	if (cp->af == AF_INET6 && iph->fragoffs)
 		return 1;
 #endif
 	oldlen = skb->len - tcphoff;
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index d6f4eeec8b71..503a842c90d2 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -30,23 +30,22 @@
 
 static int
 udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		  int *verdict, struct ip_vs_conn **cpp)
+		  int *verdict, struct ip_vs_conn **cpp,
+		  struct ip_vs_iphdr *iph)
 {
 	struct net *net;
 	struct ip_vs_service *svc;
 	struct udphdr _udph, *uh;
-	struct ip_vs_iphdr iph;
 
-	ip_vs_fill_iph_skb(af, skb, &iph);
-
-	uh = skb_header_pointer(skb, iph.len, sizeof(_udph), &_udph);
+	/* IPv6 fragments, only first fragment will hit this */
+	uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph);
 	if (uh == NULL) {
 		*verdict = NF_DROP;
 		return 0;
 	}
 	net = skb_net(skb);
-	svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
-				&iph.daddr, uh->dest);
+	svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
+				&iph->daddr, uh->dest);
 	if (svc) {
 		int ignored;
 
@@ -64,10 +63,10 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pd);
+				*verdict = ip_vs_leave(svc, skb, pd, iph);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -125,20 +124,16 @@ udp_partial_csum_update(int af, struct udphdr *uhdr,
 
 
 static int
-udp_snat_handler(struct sk_buff *skb,
-		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		 struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	struct udphdr *udph;
-	unsigned int udphoff;
+	unsigned int udphoff = iph->len;
 	int oldlen;
 	int payload_csum = 0;
 
-	struct ip_vs_iphdr iph;
-	ip_vs_fill_iph_skb(cp->af, skb, &iph);
-	udphoff = iph.len;
-
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6 && iph.fragoffs)
+	if (cp->af == AF_INET6 && iph->fragoffs)
 		return 1;
 #endif
 	oldlen = skb->len - udphoff;
@@ -212,20 +207,16 @@ udp_snat_handler(struct sk_buff *skb,
 
 
 static int
-udp_dnat_handler(struct sk_buff *skb,
-		 struct ip_vs_protocol *pp, struct ip_vs_conn *cp)
+udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		 struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	struct udphdr *udph;
-	unsigned int udphoff;
+	unsigned int udphoff = iph->len;
 	int oldlen;
 	int payload_csum = 0;
 
-	struct ip_vs_iphdr iph;
-	ip_vs_fill_iph_skb(cp->af, skb, &iph);
-	udphoff = iph.len;
-
 #ifdef CONFIG_IP_VS_IPV6
-	if (cp->af == AF_INET6 && iph.fragoffs)
+	if (cp->af == AF_INET6 && iph->fragoffs)
 		return 1;
 #endif
 	oldlen = skb->len - udphoff;
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index a8b75fc8e6a8..90122eb0b043 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -424,7 +424,7 @@ do {							\
  */
 int
 ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		struct ip_vs_protocol *pp)
+		struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	/* we do not touch skb and do not need pskb ptr */
 	IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
@@ -438,7 +438,7 @@ ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
  */
 int
 ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		  struct ip_vs_protocol *pp)
+		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	struct rtable *rt;			/* Route to the other host */
 	struct iphdr  *iph = ip_hdr(skb);
@@ -493,16 +493,14 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		     struct ip_vs_protocol *pp)
+		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph)
 {
 	struct rt6_info *rt;			/* Route to the other host */
-	struct ip_vs_iphdr iph;
 	int    mtu;
 
 	EnterFunction(10);
-	ip_vs_fill_iph_skb(cp->af, skb, &iph);
 
-	rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph.daddr.in6, NULL, 0,
+	rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr.in6, NULL, 0,
 				   IP_VS_RT_MODE_NON_LOCAL);
 	if (!rt)
 		goto tx_error_icmp;
@@ -516,7 +514,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 			skb->dev = net->loopback_dev;
 		}
 		/* only send ICMP too big on first fragment */
-		if (!iph.fragoffs)
+		if (!iph->fragoffs)
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		dst_release(&rt->dst);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
@@ -560,7 +558,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
  */
 int
 ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-	       struct ip_vs_protocol *pp)
+	       struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	struct rtable *rt;		/* Route to the other host */
 	int mtu;
@@ -630,7 +628,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error_put;
 
 	/* mangle the packet */
-	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
+	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, ipvsh))
 		goto tx_error_put;
 	ip_hdr(skb)->daddr = cp->daddr.ip;
 	ip_send_check(ip_hdr(skb));
@@ -678,20 +676,18 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		  struct ip_vs_protocol *pp)
+		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph)
 {
 	struct rt6_info *rt;		/* Route to the other host */
 	int mtu;
 	int local;
-	struct ip_vs_iphdr iph;
 
 	EnterFunction(10);
-	ip_vs_fill_iph_skb(cp->af, skb, &iph);
 
 	/* check if it is a connection of no-client-port */
-	if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !iph.fragoffs)) {
+	if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !iph->fragoffs)) {
 		__be16 _pt, *p;
-		p = skb_header_pointer(skb, iph.len, sizeof(_pt), &_pt);
+		p = skb_header_pointer(skb, iph->len, sizeof(_pt), &_pt);
 		if (p == NULL)
 			goto tx_error;
 		ip_vs_conn_fill_cport(cp, *p);
@@ -740,7 +736,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 			skb->dev = net->loopback_dev;
 		}
 		/* only send ICMP too big on first fragment */
-		if (!iph.fragoffs)
+		if (!iph->fragoffs)
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0,
 				 "ip_vs_nat_xmit_v6(): frag needed for");
@@ -755,7 +751,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error_put;
 
 	/* mangle the packet */
-	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
+	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, iph))
 		goto tx_error;
 	ipv6_hdr(skb)->daddr = cp->daddr.in6;
 
@@ -816,7 +812,7 @@ tx_error_put:
  */
 int
 ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		  struct ip_vs_protocol *pp)
+		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
 	struct rtable *rt;			/* Route to the other host */
@@ -936,7 +932,7 @@ tx_error_put:
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		     struct ip_vs_protocol *pp)
+		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	struct rt6_info *rt;		/* Route to the other host */
 	struct in6_addr saddr;		/* Source for tunnel */
@@ -946,10 +942,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	unsigned int max_headroom;	/* The extra header space needed */
 	int    mtu;
 	int ret;
-	struct ip_vs_iphdr ipvsh;
 
 	EnterFunction(10);
-	ip_vs_fill_iph_skb(cp->af, skb, &ipvsh);
 
 	if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6,
 					 &saddr, 1, (IP_VS_RT_MODE_LOCAL |
@@ -979,7 +973,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 			skb->dev = net->loopback_dev;
 		}
 		/* only send ICMP too big on first fragment */
-		if (!ipvsh.fragoffs)
+		if (!ipvsh->fragoffs)
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;
@@ -1061,7 +1055,7 @@ tx_error_put:
  */
 int
 ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-	      struct ip_vs_protocol *pp)
+	      struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
 	struct rtable *rt;			/* Route to the other host */
 	struct iphdr  *iph = ip_hdr(skb);
@@ -1122,14 +1116,12 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		 struct ip_vs_protocol *pp)
+		 struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph)
 {
 	struct rt6_info *rt;			/* Route to the other host */
 	int    mtu;
-	struct ip_vs_iphdr iph;
 
 	EnterFunction(10);
-	ip_vs_fill_iph_skb(cp->af, skb, &iph);
 
 	if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
 					 0, (IP_VS_RT_MODE_LOCAL |
@@ -1149,7 +1141,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 			skb->dev = net->loopback_dev;
 		}
 		/* only send ICMP too big on first fragment */
-		if (!iph.fragoffs)
+		if (!iph->fragoffs)
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		dst_release(&rt->dst);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
@@ -1194,7 +1186,8 @@ tx_error:
  */
 int
 ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		struct ip_vs_protocol *pp, int offset, unsigned int hooknum)
+		struct ip_vs_protocol *pp, int offset, unsigned int hooknum,
+		struct ip_vs_iphdr *iph)
 {
 	struct rtable	*rt;	/* Route to the other host */
 	int mtu;
@@ -1209,7 +1202,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	   translate address/port back */
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
 		if (cp->packet_xmit)
-			rc = cp->packet_xmit(skb, cp, pp);
+			rc = cp->packet_xmit(skb, cp, pp, iph);
 		else
 			rc = NF_ACCEPT;
 		/* do not touch skb anymore */
@@ -1315,24 +1308,23 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #ifdef CONFIG_IP_VS_IPV6
 int
 ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		struct ip_vs_protocol *pp, int offset, unsigned int hooknum)
+		struct ip_vs_protocol *pp, int offset, unsigned int hooknum,
+		struct ip_vs_iphdr *iph)
 {
 	struct rt6_info	*rt;	/* Route to the other host */
 	int mtu;
 	int rc;
 	int local;
 	int rt_mode;
-	struct ip_vs_iphdr iph;
 
 	EnterFunction(10);
-	ip_vs_fill_iph_skb(cp->af, skb, &iph);
 
 	/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
 	   forwarded directly here, because there is no need to
 	   translate address/port back */
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
 		if (cp->packet_xmit)
-			rc = cp->packet_xmit(skb, cp, pp);
+			rc = cp->packet_xmit(skb, cp, pp, iph);
 		else
 			rc = NF_ACCEPT;
 		/* do not touch skb anymore */
@@ -1389,7 +1381,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 			skb->dev = net->loopback_dev;
 		}
 		/* only send ICMP too big on first fragment */
-		if (!iph.fragoffs)
+		if (!iph->fragoffs)
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;
diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c
index 3f9b8cde2450..8d47c3780fda 100644
--- a/net/netfilter/xt_ipvs.c
+++ b/net/netfilter/xt_ipvs.c
@@ -85,7 +85,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	/*
 	 * Check if the packet belongs to an existing entry
 	 */
-	cp = pp->conn_out_get(family, skb, &iph, iph.len, 1 /* inverse */);
+	cp = pp->conn_out_get(family, skb, &iph, 1 /* inverse */);
 	if (unlikely(cp == NULL)) {
 		match = false;
 		goto out;
-- 
cgit v1.2.3-55-g7522


From e6459606b04e6385ccd3c2060fc10f78a92c7700 Mon Sep 17 00:00:00 2001
From: H. Peter Anvin
Date: Mon, 1 Oct 2012 00:23:52 +0200
Subject: lib: Add early cpio decoder

Add a simple cpio decoder without library dependencies for the purpose
of extracting components from the initramfs blob for early kernel
uses.  Intended consumers so far are microcode and ACPI override.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1349043837-22659-2-git-send-email-trenn@suse.de
Cc: Len Brown <lenb@kernel.org>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 include/linux/earlycpio.h |  17 ++++++
 lib/Makefile              |   2 +-
 lib/earlycpio.c           | 145 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 163 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/earlycpio.h
 create mode 100644 lib/earlycpio.c

(limited to 'include')

diff --git a/include/linux/earlycpio.h b/include/linux/earlycpio.h
new file mode 100644
index 000000000000..111f46d83d00
--- /dev/null
+++ b/include/linux/earlycpio.h
@@ -0,0 +1,17 @@
+#ifndef _LINUX_EARLYCPIO_H
+#define _LINUX_EARLYCPIO_H
+
+#include <linux/types.h>
+
+#define MAX_CPIO_FILE_NAME 18
+
+struct cpio_data {
+	void *data;
+	size_t size;
+	char name[MAX_CPIO_FILE_NAME];
+};
+
+struct cpio_data find_cpio_data(const char *path, void *data, size_t len,
+				long *offset);
+
+#endif /* _LINUX_EARLYCPIO_H */
diff --git a/lib/Makefile b/lib/Makefile
index 42d283edc4d3..0924041b6959 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -12,7 +12,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 idr.o int_sqrt.o extable.o prio_tree.o \
 	 sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
 	 proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
-	 is_single_threaded.o plist.o decompress.o
+	 is_single_threaded.o plist.o decompress.o earlycpio.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
diff --git a/lib/earlycpio.c b/lib/earlycpio.c
new file mode 100644
index 000000000000..8078ef49cb79
--- /dev/null
+++ b/lib/earlycpio.c
@@ -0,0 +1,145 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright 2012 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available
+ *   under the terms of the GNU General Public License version 2, as
+ *   published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *   General Public License for more details.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * earlycpio.c
+ *
+ * Find a specific cpio member; must precede any compressed content.
+ * This is used to locate data items in the initramfs used by the
+ * kernel itself during early boot (before the main initramfs is
+ * decompressed.)  It is the responsibility of the initramfs creator
+ * to ensure that these items are uncompressed at the head of the
+ * blob.  Depending on the boot loader or package tool that may be a
+ * separate file or part of the same file.
+ */
+
+#include <linux/earlycpio.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+enum cpio_fields {
+	C_MAGIC,
+	C_INO,
+	C_MODE,
+	C_UID,
+	C_GID,
+	C_NLINK,
+	C_MTIME,
+	C_FILESIZE,
+	C_MAJ,
+	C_MIN,
+	C_RMAJ,
+	C_RMIN,
+	C_NAMESIZE,
+	C_CHKSUM,
+	C_NFIELDS
+};
+
+/**
+ * cpio_data find_cpio_data - Search for files in an uncompressed cpio
+ * @path:   The directory to search for, including a slash at the end
+ * @data:   Pointer to the the cpio archive or a header inside
+ * @len:    Remaining length of the cpio based on data pointer
+ * @offset: When a matching file is found, this is the offset to the
+ *          beginning of the cpio. It can be used to iterate through
+ *          the cpio to find all files inside of a directory path
+ *
+ * @return: struct cpio_data containing the address, length and
+ *          filename (with the directory path cut off) of the found file.
+ *          If you search for a filename and not for files in a directory,
+ *          pass the absolute path of the filename in the cpio and make sure
+ *          the match returned an empty filename string.
+ */
+
+struct cpio_data __cpuinit find_cpio_data(const char *path, void *data,
+					  size_t len,  long *offset)
+{
+	const size_t cpio_header_len = 8*C_NFIELDS - 2;
+	struct cpio_data cd = { NULL, 0, "" };
+	const char *p, *dptr, *nptr;
+	unsigned int ch[C_NFIELDS], *chp, v;
+	unsigned char c, x;
+	size_t mypathsize = strlen(path);
+	int i, j;
+
+	p = data;
+
+	while (len > cpio_header_len) {
+		if (!*p) {
+			/* All cpio headers need to be 4-byte aligned */
+			p += 4;
+			len -= 4;
+			continue;
+		}
+
+		j = 6;		/* The magic field is only 6 characters */
+		chp = ch;
+		for (i = C_NFIELDS; i; i--) {
+			v = 0;
+			while (j--) {
+				v <<= 4;
+				c = *p++;
+
+				x = c - '0';
+				if (x < 10) {
+					v += x;
+					continue;
+				}
+
+				x = (c | 0x20) - 'a';
+				if (x < 6) {
+					v += x + 10;
+					continue;
+				}
+
+				goto quit; /* Invalid hexadecimal */
+			}
+			*chp++ = v;
+			j = 8;	/* All other fields are 8 characters */
+		}
+
+		if ((ch[C_MAGIC] - 0x070701) > 1)
+			goto quit; /* Invalid magic */
+
+		len -= cpio_header_len;
+
+		dptr = PTR_ALIGN(p + ch[C_NAMESIZE], 4);
+		nptr = PTR_ALIGN(dptr + ch[C_FILESIZE], 4);
+
+		if (nptr > p + len || dptr < p || nptr < dptr)
+			goto quit; /* Buffer overrun */
+
+		if ((ch[C_MODE] & 0170000) == 0100000 &&
+		    ch[C_NAMESIZE] >= mypathsize &&
+		    !memcmp(p, path, mypathsize)) {
+			*offset = (long)nptr - (long)data;
+			if (ch[C_NAMESIZE] - mypathsize >= MAX_CPIO_FILE_NAME) {
+				pr_warn(
+				"File %s exceeding MAX_CPIO_FILE_NAME [%d]\n",
+				p, MAX_CPIO_FILE_NAME);
+			}
+			strlcpy(cd.name, p + mypathsize, MAX_CPIO_FILE_NAME);
+
+			cd.data = (void *)dptr;
+			cd.size = ch[C_FILESIZE];
+			return cd; /* Found it! */
+		}
+		len -= (nptr - p);
+		p = nptr;
+	}
+
+quit:
+	return cd;
+}
-- 
cgit v1.2.3-55-g7522


From 8e30524dcc0d0ac1a18a5cee482b9d9cde3cb332 Mon Sep 17 00:00:00 2001
From: Thomas Renninger
Date: Mon, 1 Oct 2012 00:23:53 +0200
Subject: x86, acpi: Introduce x86 arch specific arch_reserve_mem_area() for
 e820 handling

This is needed for ACPI table overriding via initrd. Beside reserving
memblocks, X86 also requires to flag the memory area to E820_RESERVED or
E820_ACPI in the e820 mappings to be able to io(re)map it later.

Signed-off-by: Thomas Renninger <trenn@suse.de>
Link: http://lkml.kernel.org/r/1349043837-22659-3-git-send-email-trenn@suse.de
Cc: Len Brown <lenb@kernel.org>
Cc: Robert Moore <robert.moore@intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Eric Piel <eric.piel@tremplin-utc.net>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/x86/kernel/acpi/boot.c | 6 ++++++
 include/linux/acpi.h        | 8 ++++++++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index b2297e58c6ed..6b75777c0a8d 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1700,3 +1700,9 @@ int __acpi_release_global_lock(unsigned int *lock)
 	} while (unlikely (val != old));
 	return old & 0x1;
 }
+
+void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size)
+{
+	e820_add_region(addr, size, E820_ACPI);
+	update_e820();
+}
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4f2a76224509..946fd1ea79ff 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -426,6 +426,14 @@ void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
 
 acpi_status acpi_os_prepare_sleep(u8 sleep_state,
 				  u32 pm1a_control, u32 pm1b_control);
+#if CONFIG_X86
+void arch_reserve_mem_area(acpi_physical_address addr, size_t size);
+#else
+static inline void arch_reserve_mem_area(acpi_physical_address addr,
+					  size_t size)
+{
+}
+#endif /* CONFIG_X86 */
 #else
 #define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0)
 #endif
-- 
cgit v1.2.3-55-g7522


From 53aac44c904abbad9f474f652f099de13b5c3563 Mon Sep 17 00:00:00 2001
From: Thomas Renninger
Date: Mon, 1 Oct 2012 00:23:54 +0200
Subject: ACPI: Store valid ACPI tables passed via early initrd in reserved
 memblock areas

A later patch will compare them with ACPI tables that get loaded at boot or
runtime and if criteria match, a stored one is loaded.

Signed-off-by: Thomas Renninger <trenn@suse.de>
Link: http://lkml.kernel.org/r/1349043837-22659-4-git-send-email-trenn@suse.de
Cc: Len Brown <lenb@kernel.org>
Cc: Robert Moore <robert.moore@intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Eric Piel <eric.piel@tremplin-utc.net>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/x86/kernel/setup.c |   2 +
 drivers/acpi/Kconfig    |   9 ++++
 drivers/acpi/osl.c      | 122 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/acpi.h    |   8 ++++
 4 files changed, 141 insertions(+)

(limited to 'include')

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f4b9b80e1b95..764e543b2297 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -941,6 +941,8 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_initrd();
 
+	acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start);
+
 	reserve_crashkernel();
 
 	vsmp_init();
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 80998958cf45..8cf719547b51 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -261,6 +261,15 @@ config ACPI_CUSTOM_DSDT
 	bool
 	default ACPI_CUSTOM_DSDT_FILE != ""
 
+config ACPI_INITRD_TABLE_OVERRIDE
+	bool "ACPI tables can be passed via uncompressed cpio in initrd"
+	default n
+	help
+	  This option provides functionality to override arbitrary ACPI tables
+	  via initrd. No functional change if no ACPI tables are passed via
+	  initrd, therefore it's safe to say Y.
+	  See Documentation/acpi/initrd_table_override.txt for details
+
 config ACPI_BLACKLIST_YEAR
 	int "Disable ACPI for systems before Jan 1st this year" if X86_32
 	default 0
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 9eaf708f5885..b20b07903218 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -534,6 +534,128 @@ acpi_os_predefined_override(const struct acpi_predefined_names *init_val,
 	return AE_OK;
 }
 
+#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
+#include <linux/earlycpio.h>
+#include <linux/memblock.h>
+
+static u64 acpi_tables_addr;
+static int all_tables_size;
+
+/* Copied from acpica/tbutils.c:acpi_tb_checksum() */
+u8 __init acpi_table_checksum(u8 *buffer, u32 length)
+{
+	u8 sum = 0;
+	u8 *end = buffer + length;
+
+	while (buffer < end)
+		sum = (u8) (sum + *(buffer++));
+	return sum;
+}
+
+/* All but ACPI_SIG_RSDP and ACPI_SIG_FACS: */
+static const char * const table_sigs[] = {
+	ACPI_SIG_BERT, ACPI_SIG_CPEP, ACPI_SIG_ECDT, ACPI_SIG_EINJ,
+	ACPI_SIG_ERST, ACPI_SIG_HEST, ACPI_SIG_MADT, ACPI_SIG_MSCT,
+	ACPI_SIG_SBST, ACPI_SIG_SLIT, ACPI_SIG_SRAT, ACPI_SIG_ASF,
+	ACPI_SIG_BOOT, ACPI_SIG_DBGP, ACPI_SIG_DMAR, ACPI_SIG_HPET,
+	ACPI_SIG_IBFT, ACPI_SIG_IVRS, ACPI_SIG_MCFG, ACPI_SIG_MCHI,
+	ACPI_SIG_SLIC, ACPI_SIG_SPCR, ACPI_SIG_SPMI, ACPI_SIG_TCPA,
+	ACPI_SIG_UEFI, ACPI_SIG_WAET, ACPI_SIG_WDAT, ACPI_SIG_WDDT,
+	ACPI_SIG_WDRT, ACPI_SIG_DSDT, ACPI_SIG_FADT, ACPI_SIG_PSDT,
+	ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT, NULL };
+
+/* Non-fatal errors: Affected tables/files are ignored */
+#define INVALID_TABLE(x, path, name)					\
+	{ pr_err("ACPI OVERRIDE: " x " [%s%s]\n", path, name); continue; }
+
+#define ACPI_HEADER_SIZE sizeof(struct acpi_table_header)
+
+/* Must not increase 10 or needs code modification below */
+#define ACPI_OVERRIDE_TABLES 10
+
+void __init acpi_initrd_override(void *data, size_t size)
+{
+	int sig, no, table_nr = 0, total_offset = 0;
+	long offset = 0;
+	struct acpi_table_header *table;
+	char cpio_path[32] = "kernel/firmware/acpi/";
+	struct cpio_data file;
+	struct cpio_data early_initrd_files[ACPI_OVERRIDE_TABLES];
+	char *p;
+
+	if (data == NULL || size == 0)
+		return;
+
+	for (no = 0; no < ACPI_OVERRIDE_TABLES; no++) {
+		file = find_cpio_data(cpio_path, data, size, &offset);
+		if (!file.data)
+			break;
+
+		data += offset;
+		size -= offset;
+
+		if (file.size < sizeof(struct acpi_table_header))
+			INVALID_TABLE("Table smaller than ACPI header",
+				      cpio_path, file.name);
+
+		table = file.data;
+
+		for (sig = 0; table_sigs[sig]; sig++)
+			if (!memcmp(table->signature, table_sigs[sig], 4))
+				break;
+
+		if (!table_sigs[sig])
+			INVALID_TABLE("Unknown signature",
+				      cpio_path, file.name);
+		if (file.size != table->length)
+			INVALID_TABLE("File length does not match table length",
+				      cpio_path, file.name);
+		if (acpi_table_checksum(file.data, table->length))
+			INVALID_TABLE("Bad table checksum",
+				      cpio_path, file.name);
+
+		pr_info("%4.4s ACPI table found in initrd [%s%s][0x%x]\n",
+			table->signature, cpio_path, file.name, table->length);
+
+		all_tables_size += table->length;
+		early_initrd_files[table_nr].data = file.data;
+		early_initrd_files[table_nr].size = file.size;
+		table_nr++;
+	}
+	if (table_nr == 0)
+		return;
+
+	acpi_tables_addr =
+		memblock_find_in_range(0, max_low_pfn_mapped << PAGE_SHIFT,
+				       all_tables_size, PAGE_SIZE);
+	if (!acpi_tables_addr) {
+		WARN_ON(1);
+		return;
+	}
+	/*
+	 * Only calling e820_add_reserve does not work and the
+	 * tables are invalid (memory got used) later.
+	 * memblock_reserve works as expected and the tables won't get modified.
+	 * But it's not enough on X86 because ioremap will
+	 * complain later (used by acpi_os_map_memory) that the pages
+	 * that should get mapped are not marked "reserved".
+	 * Both memblock_reserve and e820_add_region (via arch_reserve_mem_area)
+	 * works fine.
+	 */
+	memblock_reserve(acpi_tables_addr, acpi_tables_addr + all_tables_size);
+	arch_reserve_mem_area(acpi_tables_addr, all_tables_size);
+
+	p = early_ioremap(acpi_tables_addr, all_tables_size);
+
+	for (no = 0; no < table_nr; no++) {
+		memcpy(p + total_offset, early_initrd_files[no].data,
+		       early_initrd_files[no].size);
+		total_offset += early_initrd_files[no].size;
+	}
+	early_iounmap(p, all_tables_size);
+}
+#endif /* CONFIG_ACPI_INITRD_TABLE_OVERRIDE */
+
 acpi_status
 acpi_os_table_override(struct acpi_table_header * existing_table,
 		       struct acpi_table_header ** new_table)
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 946fd1ea79ff..d14081c10c17 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -76,6 +76,14 @@ typedef int (*acpi_table_handler) (struct acpi_table_header *table);
 
 typedef int (*acpi_table_entry_handler) (struct acpi_subtable_header *header, const unsigned long end);
 
+#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
+void acpi_initrd_override(void *data, size_t size);
+#else
+static inline void acpi_initrd_override(void *data, size_t size)
+{
+}
+#endif
+
 char * __acpi_map_table (unsigned long phys_addr, unsigned long size);
 void __acpi_unmap_table(char *map, unsigned long size);
 int early_acpi_boot_init(void);
-- 
cgit v1.2.3-55-g7522


From dfee1ebc0e363ff1dc233c4a5246bf3e7f5c5ca6 Mon Sep 17 00:00:00 2001
From: Rami Rosen
Date: Mon, 1 Oct 2012 19:37:31 +0200
Subject: Bluetooth: remove unused member of hci_dev.

This patch removes core_data member from hci_dev struct as it is unused.

Signed-off-by: Rami Rosen <ramirose@gmail.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ea1f9340324d..90ae4f0a4fdc 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -262,8 +262,6 @@ struct hci_dev {
 
 	struct sk_buff_head	driver_init;
 
-	void			*core_data;
-
 	atomic_t		promisc;
 
 	struct dentry		*debugfs;
-- 
cgit v1.2.3-55-g7522


From 3a50597de8635cd05133bd12c95681c82fe7b878 Mon Sep 17 00:00:00 2001
From: David Howells
Date: Tue, 2 Oct 2012 19:24:29 +0100
Subject: KEYS: Make the session and process keyrings per-thread

Make the session keyring per-thread rather than per-process, but still
inherited from the parent thread to solve a problem with PAM and gdm.

The problem is that join_session_keyring() will reject attempts to change the
session keyring of a multithreaded program but gdm is now multithreaded before
it gets to the point of starting PAM and running pam_keyinit to create the
session keyring.  See:

	https://bugs.freedesktop.org/show_bug.cgi?id=49211

The reason that join_session_keyring() will only change the session keyring
under a single-threaded environment is that it's hard to alter the other
thread's credentials to effect the change in a multi-threaded program.  The
problems are such as:

 (1) How to prevent two threads both running join_session_keyring() from
     racing.

 (2) Another thread's credentials may not be modified directly by this process.

 (3) The number of threads is uncertain whilst we're not holding the
     appropriate spinlock, making preallocation slightly tricky.

 (4) We could use TIF_NOTIFY_RESUME and key_replace_session_keyring() to get
     another thread to replace its keyring, but that means preallocating for
     each thread.

A reasonable way around this is to make the session keyring per-thread rather
than per-process and just document that if you want a common session keyring,
you must get it before you spawn any threads - which is the current situation
anyway.

Whilst we're at it, we can the process keyring behave in the same way.  This
means we can clean up some of the ickyness in the creds code.

Basically, after this patch, the session, process and thread keyrings are about
inheritance rules only and not about sharing changes of keyring.

Reported-by: Mantas M. <grawity@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Ray Strode <rstrode@redhat.com>
---
 include/linux/cred.h         |  17 +-----
 kernel/cred.c                | 127 +++++--------------------------------------
 security/keys/keyctl.c       |  11 ++--
 security/keys/process_keys.c |  66 ++++++++--------------
 security/keys/request_key.c  |  10 ++--
 5 files changed, 50 insertions(+), 181 deletions(-)

(limited to 'include')

diff --git a/include/linux/cred.h b/include/linux/cred.h
index ebbed2ce6637..0142aacb70b7 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -76,21 +76,6 @@ extern int groups_search(const struct group_info *, kgid_t);
 extern int in_group_p(kgid_t);
 extern int in_egroup_p(kgid_t);
 
-/*
- * The common credentials for a thread group
- * - shared by CLONE_THREAD
- */
-#ifdef CONFIG_KEYS
-struct thread_group_cred {
-	atomic_t	usage;
-	pid_t		tgid;			/* thread group process ID */
-	spinlock_t	lock;
-	struct key __rcu *session_keyring;	/* keyring inherited over fork */
-	struct key	*process_keyring;	/* keyring private to this process */
-	struct rcu_head	rcu;			/* RCU deletion hook */
-};
-#endif
-
 /*
  * The security context of a task
  *
@@ -139,6 +124,8 @@ struct cred {
 #ifdef CONFIG_KEYS
 	unsigned char	jit_keyring;	/* default keyring to attach requested
 					 * keys to */
+	struct key __rcu *session_keyring; /* keyring inherited over fork */
+	struct key	*process_keyring; /* keyring private to this process */
 	struct key	*thread_keyring; /* keyring private to this thread */
 	struct key	*request_key_auth; /* assumed request_key authority */
 	struct thread_group_cred *tgcred; /* thread-group shared credentials */
diff --git a/kernel/cred.c b/kernel/cred.c
index de728ac50d82..3f7ad1ec2ae4 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -29,17 +29,6 @@
 
 static struct kmem_cache *cred_jar;
 
-/*
- * The common credentials for the initial task's thread group
- */
-#ifdef CONFIG_KEYS
-static struct thread_group_cred init_tgcred = {
-	.usage	= ATOMIC_INIT(2),
-	.tgid	= 0,
-	.lock	= __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock),
-};
-#endif
-
 /*
  * The initial credentials for the initial task
  */
@@ -65,9 +54,6 @@ struct cred init_cred = {
 	.user			= INIT_USER,
 	.user_ns		= &init_user_ns,
 	.group_info		= &init_groups,
-#ifdef CONFIG_KEYS
-	.tgcred			= &init_tgcred,
-#endif
 };
 
 static inline void set_cred_subscribers(struct cred *cred, int n)
@@ -95,36 +81,6 @@ static inline void alter_cred_subscribers(const struct cred *_cred, int n)
 #endif
 }
 
-/*
- * Dispose of the shared task group credentials
- */
-#ifdef CONFIG_KEYS
-static void release_tgcred_rcu(struct rcu_head *rcu)
-{
-	struct thread_group_cred *tgcred =
-		container_of(rcu, struct thread_group_cred, rcu);
-
-	BUG_ON(atomic_read(&tgcred->usage) != 0);
-
-	key_put(tgcred->session_keyring);
-	key_put(tgcred->process_keyring);
-	kfree(tgcred);
-}
-#endif
-
-/*
- * Release a set of thread group credentials.
- */
-static void release_tgcred(struct cred *cred)
-{
-#ifdef CONFIG_KEYS
-	struct thread_group_cred *tgcred = cred->tgcred;
-
-	if (atomic_dec_and_test(&tgcred->usage))
-		call_rcu(&tgcred->rcu, release_tgcred_rcu);
-#endif
-}
-
 /*
  * The RCU callback to actually dispose of a set of credentials
  */
@@ -150,9 +106,10 @@ static void put_cred_rcu(struct rcu_head *rcu)
 #endif
 
 	security_cred_free(cred);
+	key_put(cred->session_keyring);
+	key_put(cred->process_keyring);
 	key_put(cred->thread_keyring);
 	key_put(cred->request_key_auth);
-	release_tgcred(cred);
 	if (cred->group_info)
 		put_group_info(cred->group_info);
 	free_uid(cred->user);
@@ -246,15 +203,6 @@ struct cred *cred_alloc_blank(void)
 	if (!new)
 		return NULL;
 
-#ifdef CONFIG_KEYS
-	new->tgcred = kzalloc(sizeof(*new->tgcred), GFP_KERNEL);
-	if (!new->tgcred) {
-		kmem_cache_free(cred_jar, new);
-		return NULL;
-	}
-	atomic_set(&new->tgcred->usage, 1);
-#endif
-
 	atomic_set(&new->usage, 1);
 #ifdef CONFIG_DEBUG_CREDENTIALS
 	new->magic = CRED_MAGIC;
@@ -308,9 +256,10 @@ struct cred *prepare_creds(void)
 	get_user_ns(new->user_ns);
 
 #ifdef CONFIG_KEYS
+	key_get(new->session_keyring);
+	key_get(new->process_keyring);
 	key_get(new->thread_keyring);
 	key_get(new->request_key_auth);
-	atomic_inc(&new->tgcred->usage);
 #endif
 
 #ifdef CONFIG_SECURITY
@@ -334,39 +283,20 @@ EXPORT_SYMBOL(prepare_creds);
  */
 struct cred *prepare_exec_creds(void)
 {
-	struct thread_group_cred *tgcred = NULL;
 	struct cred *new;
 
-#ifdef CONFIG_KEYS
-	tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL);
-	if (!tgcred)
-		return NULL;
-#endif
-
 	new = prepare_creds();
-	if (!new) {
-		kfree(tgcred);
+	if (!new)
 		return new;
-	}
 
 #ifdef CONFIG_KEYS
 	/* newly exec'd tasks don't get a thread keyring */
 	key_put(new->thread_keyring);
 	new->thread_keyring = NULL;
 
-	/* create a new per-thread-group creds for all this set of threads to
-	 * share */
-	memcpy(tgcred, new->tgcred, sizeof(struct thread_group_cred));
-
-	atomic_set(&tgcred->usage, 1);
-	spin_lock_init(&tgcred->lock);
-
 	/* inherit the session keyring; new process keyring */
-	key_get(tgcred->session_keyring);
-	tgcred->process_keyring = NULL;
-
-	release_tgcred(new);
-	new->tgcred = tgcred;
+	key_put(new->process_keyring);
+	new->process_keyring = NULL;
 #endif
 
 	return new;
@@ -383,9 +313,6 @@ struct cred *prepare_exec_creds(void)
  */
 int copy_creds(struct task_struct *p, unsigned long clone_flags)
 {
-#ifdef CONFIG_KEYS
-	struct thread_group_cred *tgcred;
-#endif
 	struct cred *new;
 	int ret;
 
@@ -425,22 +352,12 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 			install_thread_keyring_to_cred(new);
 	}
 
-	/* we share the process and session keyrings between all the threads in
-	 * a process - this is slightly icky as we violate COW credentials a
-	 * bit */
+	/* The process keyring is only shared between the threads in a process;
+	 * anything outside of those threads doesn't inherit.
+	 */
 	if (!(clone_flags & CLONE_THREAD)) {
-		tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL);
-		if (!tgcred) {
-			ret = -ENOMEM;
-			goto error_put;
-		}
-		atomic_set(&tgcred->usage, 1);
-		spin_lock_init(&tgcred->lock);
-		tgcred->process_keyring = NULL;
-		tgcred->session_keyring = key_get(new->tgcred->session_keyring);
-
-		release_tgcred(new);
-		new->tgcred = tgcred;
+		key_put(new->process_keyring);
+		new->process_keyring = NULL;
 	}
 #endif
 
@@ -643,9 +560,6 @@ void __init cred_init(void)
  */
 struct cred *prepare_kernel_cred(struct task_struct *daemon)
 {
-#ifdef CONFIG_KEYS
-	struct thread_group_cred *tgcred;
-#endif
 	const struct cred *old;
 	struct cred *new;
 
@@ -653,14 +567,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	if (!new)
 		return NULL;
 
-#ifdef CONFIG_KEYS
-	tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL);
-	if (!tgcred) {
-		kmem_cache_free(cred_jar, new);
-		return NULL;
-	}
-#endif
-
 	kdebug("prepare_kernel_cred() alloc %p", new);
 
 	if (daemon)
@@ -678,13 +584,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	get_group_info(new->group_info);
 
 #ifdef CONFIG_KEYS
-	atomic_set(&tgcred->usage, 1);
-	spin_lock_init(&tgcred->lock);
-	tgcred->process_keyring = NULL;
-	tgcred->session_keyring = NULL;
-	new->tgcred = tgcred;
-	new->request_key_auth = NULL;
+	new->session_keyring = NULL;
+	new->process_keyring = NULL;
 	new->thread_keyring = NULL;
+	new->request_key_auth = NULL;
 	new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
 #endif
 
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index a0d373f76815..65b38417c211 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1475,7 +1475,8 @@ long keyctl_session_to_parent(void)
 		goto error_keyring;
 	newwork = &cred->rcu;
 
-	cred->tgcred->session_keyring = key_ref_to_ptr(keyring_r);
+	cred->session_keyring = key_ref_to_ptr(keyring_r);
+	keyring_r = NULL;
 	init_task_work(newwork, key_change_session_keyring);
 
 	me = current;
@@ -1500,7 +1501,7 @@ long keyctl_session_to_parent(void)
 	mycred = current_cred();
 	pcred = __task_cred(parent);
 	if (mycred == pcred ||
-	    mycred->tgcred->session_keyring == pcred->tgcred->session_keyring) {
+	    mycred->session_keyring == pcred->session_keyring) {
 		ret = 0;
 		goto unlock;
 	}
@@ -1516,9 +1517,9 @@ long keyctl_session_to_parent(void)
 		goto unlock;
 
 	/* the keyrings must have the same UID */
-	if ((pcred->tgcred->session_keyring &&
-	     pcred->tgcred->session_keyring->uid != mycred->euid) ||
-	    mycred->tgcred->session_keyring->uid != mycred->euid)
+	if ((pcred->session_keyring &&
+	     pcred->session_keyring->uid != mycred->euid) ||
+	    mycred->session_keyring->uid != mycred->euid)
 		goto unlock;
 
 	/* cancel an already pending keyring replacement */
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 178b8c3b130a..9de5dc598276 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -169,9 +169,8 @@ static int install_thread_keyring(void)
 int install_process_keyring_to_cred(struct cred *new)
 {
 	struct key *keyring;
-	int ret;
 
-	if (new->tgcred->process_keyring)
+	if (new->process_keyring)
 		return -EEXIST;
 
 	keyring = keyring_alloc("_pid", new->uid, new->gid,
@@ -179,17 +178,8 @@ int install_process_keyring_to_cred(struct cred *new)
 	if (IS_ERR(keyring))
 		return PTR_ERR(keyring);
 
-	spin_lock_irq(&new->tgcred->lock);
-	if (!new->tgcred->process_keyring) {
-		new->tgcred->process_keyring = keyring;
-		keyring = NULL;
-		ret = 0;
-	} else {
-		ret = -EEXIST;
-	}
-	spin_unlock_irq(&new->tgcred->lock);
-	key_put(keyring);
-	return ret;
+	new->process_keyring = keyring;
+	return 0;
 }
 
 /*
@@ -230,7 +220,7 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
 	/* create an empty session keyring */
 	if (!keyring) {
 		flags = KEY_ALLOC_QUOTA_OVERRUN;
-		if (cred->tgcred->session_keyring)
+		if (cred->session_keyring)
 			flags = KEY_ALLOC_IN_QUOTA;
 
 		keyring = keyring_alloc("_ses", cred->uid, cred->gid,
@@ -242,17 +232,11 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
 	}
 
 	/* install the keyring */
-	spin_lock_irq(&cred->tgcred->lock);
-	old = cred->tgcred->session_keyring;
-	rcu_assign_pointer(cred->tgcred->session_keyring, keyring);
-	spin_unlock_irq(&cred->tgcred->lock);
-
-	/* we're using RCU on the pointer, but there's no point synchronising
-	 * on it if it didn't previously point to anything */
-	if (old) {
-		synchronize_rcu();
+	old = cred->session_keyring;
+	rcu_assign_pointer(cred->session_keyring, keyring);
+
+	if (old)
 		key_put(old);
-	}
 
 	return 0;
 }
@@ -367,9 +351,9 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 	}
 
 	/* search the process keyring second */
-	if (cred->tgcred->process_keyring) {
+	if (cred->process_keyring) {
 		key_ref = keyring_search_aux(
-			make_key_ref(cred->tgcred->process_keyring, 1),
+			make_key_ref(cred->process_keyring, 1),
 			cred, type, description, match, no_state_check);
 		if (!IS_ERR(key_ref))
 			goto found;
@@ -388,12 +372,10 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 	}
 
 	/* search the session keyring */
-	if (cred->tgcred->session_keyring) {
+	if (cred->session_keyring) {
 		rcu_read_lock();
 		key_ref = keyring_search_aux(
-			make_key_ref(rcu_dereference(
-					     cred->tgcred->session_keyring),
-				     1),
+			make_key_ref(rcu_dereference(cred->session_keyring), 1),
 			cred, type, description, match, no_state_check);
 		rcu_read_unlock();
 
@@ -563,7 +545,7 @@ try_again:
 		break;
 
 	case KEY_SPEC_PROCESS_KEYRING:
-		if (!cred->tgcred->process_keyring) {
+		if (!cred->process_keyring) {
 			if (!(lflags & KEY_LOOKUP_CREATE))
 				goto error;
 
@@ -575,13 +557,13 @@ try_again:
 			goto reget_creds;
 		}
 
-		key = cred->tgcred->process_keyring;
+		key = cred->process_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
 		break;
 
 	case KEY_SPEC_SESSION_KEYRING:
-		if (!cred->tgcred->session_keyring) {
+		if (!cred->session_keyring) {
 			/* always install a session keyring upon access if one
 			 * doesn't exist yet */
 			ret = install_user_keyrings();
@@ -596,7 +578,7 @@ try_again:
 			if (ret < 0)
 				goto error;
 			goto reget_creds;
-		} else if (cred->tgcred->session_keyring ==
+		} else if (cred->session_keyring ==
 			   cred->user->session_keyring &&
 			   lflags & KEY_LOOKUP_CREATE) {
 			ret = join_session_keyring(NULL);
@@ -606,7 +588,7 @@ try_again:
 		}
 
 		rcu_read_lock();
-		key = rcu_dereference(cred->tgcred->session_keyring);
+		key = rcu_dereference(cred->session_keyring);
 		atomic_inc(&key->usage);
 		rcu_read_unlock();
 		key_ref = make_key_ref(key, 1);
@@ -766,12 +748,6 @@ long join_session_keyring(const char *name)
 	struct key *keyring;
 	long ret, serial;
 
-	/* only permit this if there's a single thread in the thread group -
-	 * this avoids us having to adjust the creds on all threads and risking
-	 * ENOMEM */
-	if (!current_is_single_threaded())
-		return -EMLINK;
-
 	new = prepare_creds();
 	if (!new)
 		return -ENOMEM;
@@ -783,7 +759,7 @@ long join_session_keyring(const char *name)
 		if (ret < 0)
 			goto error;
 
-		serial = new->tgcred->session_keyring->serial;
+		serial = new->session_keyring->serial;
 		ret = commit_creds(new);
 		if (ret == 0)
 			ret = serial;
@@ -806,6 +782,9 @@ long join_session_keyring(const char *name)
 	} else if (IS_ERR(keyring)) {
 		ret = PTR_ERR(keyring);
 		goto error2;
+	} else if (keyring == new->session_keyring) {
+		ret = 0;
+		goto error2;
 	}
 
 	/* we've got a keyring - now to install it */
@@ -862,8 +841,7 @@ void key_change_session_keyring(struct callback_head *twork)
 
 	new->jit_keyring	= old->jit_keyring;
 	new->thread_keyring	= key_get(old->thread_keyring);
-	new->tgcred->tgid	= old->tgcred->tgid;
-	new->tgcred->process_keyring = key_get(old->tgcred->process_keyring);
+	new->process_keyring	= key_get(old->process_keyring);
 
 	security_transfer_creds(new, old);
 
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 000e75017520..275c4f9e4b8c 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -150,12 +150,12 @@ static int call_sbin_request_key(struct key_construction *cons,
 		cred->thread_keyring ? cred->thread_keyring->serial : 0);
 
 	prkey = 0;
-	if (cred->tgcred->process_keyring)
-		prkey = cred->tgcred->process_keyring->serial;
+	if (cred->process_keyring)
+		prkey = cred->process_keyring->serial;
 	sprintf(keyring_str[1], "%d", prkey);
 
 	rcu_read_lock();
-	session = rcu_dereference(cred->tgcred->session_keyring);
+	session = rcu_dereference(cred->session_keyring);
 	if (!session)
 		session = cred->user->session_keyring;
 	sskey = session->serial;
@@ -297,14 +297,14 @@ static void construct_get_dest_keyring(struct key **_dest_keyring)
 				break;
 
 		case KEY_REQKEY_DEFL_PROCESS_KEYRING:
-			dest_keyring = key_get(cred->tgcred->process_keyring);
+			dest_keyring = key_get(cred->process_keyring);
 			if (dest_keyring)
 				break;
 
 		case KEY_REQKEY_DEFL_SESSION_KEYRING:
 			rcu_read_lock();
 			dest_keyring = key_get(
-				rcu_dereference(cred->tgcred->session_keyring));
+				rcu_dereference(cred->session_keyring));
 			rcu_read_unlock();
 
 			if (dest_keyring)
-- 
cgit v1.2.3-55-g7522


From 96b5c8fea6c0861621051290d705ec2e971963f1 Mon Sep 17 00:00:00 2001
From: David Howells
Date: Tue, 2 Oct 2012 19:24:56 +0100
Subject: KEYS: Reduce initial permissions on keys

Reduce the initial permissions on new keys to grant the possessor everything,
view permission only to the user (so the keys can be seen in /proc/keys) and
nothing else.

This gives the creator a chance to adjust the permissions mask before other
processes can access the new key or create a link to it.

To aid with this, keyring_alloc() now takes a permission argument rather than
setting the permissions itself.

The following permissions are now set:

 (1) The user and user-session keyrings grant the user that owns them full
     permissions and grant a possessor everything bar SETATTR.

 (2) The process and thread keyrings grant the possessor full permissions but
     only grant the user VIEW.  This permits the user to see them in
     /proc/keys, but not to do anything with them.

 (3) Anonymous session keyrings grant the possessor full permissions, but only
     grant the user VIEW and READ.  This means that the user can see them in
     /proc/keys and can list them, but nothing else.  Possibly READ shouldn't
     be provided either.

 (4) Named session keyrings grant everything an anonymous session keyring does,
     plus they grant the user LINK permission.  The whole point of named
     session keyrings is that others can also subscribe to them.  Possibly this
     should be a separate permission to LINK.

 (5) The temporary session keyring created by call_sbin_request_key() gets the
     same permissions as an anonymous session keyring.

 (6) Keys created by add_key() get VIEW, SEARCH, LINK and SETATTR for the
     possessor, plus READ and/or WRITE if the key type supports them.  The used
     only gets VIEW now.

 (7) Keys created by request_key() now get the same as those created by
     add_key().

Reported-by: Lennart Poettering <lennart@poettering.net>
Reported-by: Stef Walter <stefw@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/linux/key.h          |  1 +
 security/keys/key.c          |  6 +++---
 security/keys/keyring.c      |  9 +++------
 security/keys/process_keys.c | 26 +++++++++++++++++---------
 security/keys/request_key.c  | 11 ++++++++++-
 5 files changed, 34 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/key.h b/include/linux/key.h
index cef3b315ba7c..890699815212 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -264,6 +264,7 @@ extern int key_unlink(struct key *keyring,
 
 extern struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid,
 				 const struct cred *cred,
+				 key_perm_t perm,
 				 unsigned long flags,
 				 struct key *dest);
 
diff --git a/security/keys/key.c b/security/keys/key.c
index 50d96d4e06f2..bebeca3a78e4 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -826,13 +826,13 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	/* if the client doesn't provide, decide on the permissions we want */
 	if (perm == KEY_PERM_UNDEF) {
 		perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
-		perm |= KEY_USR_VIEW | KEY_USR_SEARCH | KEY_USR_LINK | KEY_USR_SETATTR;
+		perm |= KEY_USR_VIEW;
 
 		if (ktype->read)
-			perm |= KEY_POS_READ | KEY_USR_READ;
+			perm |= KEY_POS_READ;
 
 		if (ktype == &key_type_keyring || ktype->update)
-			perm |= KEY_USR_WRITE;
+			perm |= KEY_POS_WRITE;
 	}
 
 	/* allocate a new key */
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 81e7852d281d..cf704a92083f 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -257,17 +257,14 @@ error:
  * Allocate a keyring and link into the destination keyring.
  */
 struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid,
-			  const struct cred *cred, unsigned long flags,
-			  struct key *dest)
+			  const struct cred *cred, key_perm_t perm,
+			  unsigned long flags, struct key *dest)
 {
 	struct key *keyring;
 	int ret;
 
 	keyring = key_alloc(&key_type_keyring, description,
-			    uid, gid, cred,
-			    (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_ALL,
-			    flags);
-
+			    uid, gid, cred, perm, flags);
 	if (!IS_ERR(keyring)) {
 		ret = key_instantiate_and_link(keyring, NULL, 0, dest, NULL);
 		if (ret < 0) {
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 9de5dc598276..b58d93892740 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -46,9 +46,11 @@ int install_user_keyrings(void)
 	struct user_struct *user;
 	const struct cred *cred;
 	struct key *uid_keyring, *session_keyring;
+	key_perm_t user_keyring_perm;
 	char buf[20];
 	int ret;
 
+	user_keyring_perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_ALL;
 	cred = current_cred();
 	user = cred->user;
 
@@ -72,8 +74,8 @@ int install_user_keyrings(void)
 		uid_keyring = find_keyring_by_name(buf, true);
 		if (IS_ERR(uid_keyring)) {
 			uid_keyring = keyring_alloc(buf, user->uid, (gid_t) -1,
-						    cred, KEY_ALLOC_IN_QUOTA,
-						    NULL);
+						    cred, user_keyring_perm,
+						    KEY_ALLOC_IN_QUOTA, NULL);
 			if (IS_ERR(uid_keyring)) {
 				ret = PTR_ERR(uid_keyring);
 				goto error;
@@ -88,7 +90,8 @@ int install_user_keyrings(void)
 		if (IS_ERR(session_keyring)) {
 			session_keyring =
 				keyring_alloc(buf, user->uid, (gid_t) -1,
-					      cred, KEY_ALLOC_IN_QUOTA, NULL);
+					      cred, user_keyring_perm,
+					      KEY_ALLOC_IN_QUOTA, NULL);
 			if (IS_ERR(session_keyring)) {
 				ret = PTR_ERR(session_keyring);
 				goto error_release;
@@ -129,6 +132,7 @@ int install_thread_keyring_to_cred(struct cred *new)
 	struct key *keyring;
 
 	keyring = keyring_alloc("_tid", new->uid, new->gid, new,
+				KEY_POS_ALL | KEY_USR_VIEW,
 				KEY_ALLOC_QUOTA_OVERRUN, NULL);
 	if (IS_ERR(keyring))
 		return PTR_ERR(keyring);
@@ -173,8 +177,9 @@ int install_process_keyring_to_cred(struct cred *new)
 	if (new->process_keyring)
 		return -EEXIST;
 
-	keyring = keyring_alloc("_pid", new->uid, new->gid,
-				new, KEY_ALLOC_QUOTA_OVERRUN, NULL);
+	keyring = keyring_alloc("_pid", new->uid, new->gid, new,
+				KEY_POS_ALL | KEY_USR_VIEW,
+				KEY_ALLOC_QUOTA_OVERRUN, NULL);
 	if (IS_ERR(keyring))
 		return PTR_ERR(keyring);
 
@@ -223,8 +228,9 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
 		if (cred->session_keyring)
 			flags = KEY_ALLOC_IN_QUOTA;
 
-		keyring = keyring_alloc("_ses", cred->uid, cred->gid,
-					cred, flags, NULL);
+		keyring = keyring_alloc("_ses", cred->uid, cred->gid, cred,
+					KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ,
+					flags, NULL);
 		if (IS_ERR(keyring))
 			return PTR_ERR(keyring);
 	} else {
@@ -773,8 +779,10 @@ long join_session_keyring(const char *name)
 	keyring = find_keyring_by_name(name, false);
 	if (PTR_ERR(keyring) == -ENOKEY) {
 		/* not found - try and create a new one */
-		keyring = keyring_alloc(name, old->uid, old->gid, old,
-					KEY_ALLOC_IN_QUOTA, NULL);
+		keyring = keyring_alloc(
+			name, old->uid, old->gid, old,
+			KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_LINK,
+			KEY_ALLOC_IN_QUOTA, NULL);
 		if (IS_ERR(keyring)) {
 			ret = PTR_ERR(keyring);
 			goto error2;
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 275c4f9e4b8c..0ae3a2202771 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -126,6 +126,7 @@ static int call_sbin_request_key(struct key_construction *cons,
 
 	cred = get_current_cred();
 	keyring = keyring_alloc(desc, cred->fsuid, cred->fsgid, cred,
+				KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ,
 				KEY_ALLOC_QUOTA_OVERRUN, NULL);
 	put_cred(cred);
 	if (IS_ERR(keyring)) {
@@ -347,6 +348,7 @@ static int construct_alloc_key(struct key_type *type,
 	const struct cred *cred = current_cred();
 	unsigned long prealloc;
 	struct key *key;
+	key_perm_t perm;
 	key_ref_t key_ref;
 	int ret;
 
@@ -355,8 +357,15 @@ static int construct_alloc_key(struct key_type *type,
 	*_key = NULL;
 	mutex_lock(&user->cons_lock);
 
+	perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
+	perm |= KEY_USR_VIEW;
+	if (type->read)
+		perm |= KEY_POS_READ;
+	if (type == &key_type_keyring || type->update)
+		perm |= KEY_POS_WRITE;
+
 	key = key_alloc(type, description, cred->fsuid, cred->fsgid, cred,
-			KEY_POS_ALL, flags);
+			perm, flags);
 	if (IS_ERR(key))
 		goto alloc_failed;
 
-- 
cgit v1.2.3-55-g7522


From 9202e07636f0c4858ba6c30773a3f160b2b5659a Mon Sep 17 00:00:00 2001
From: Liu Yu-B13201
Date: Tue, 3 Jul 2012 05:48:52 +0000
Subject: KVM: PPC: Add support for ePAPR idle hcall in host kernel

And add a new flag definition in kvm_ppc_pvinfo to indicate
whether the host supports the EV_IDLE hcall.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
[stuart.yoder@freescale.com: cleanup,fixes for conditions allowing idle]
Signed-off-by: Stuart Yoder <stuart.yoder@freescale.com>
[agraf: fix typo]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt |  7 +++++--
 arch/powerpc/include/asm/Kbuild   |  1 +
 arch/powerpc/kvm/powerpc.c        | 10 ++++++++--
 include/linux/kvm.h               |  2 ++
 4 files changed, 16 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index f6ec3a92e621..170afb1fbc2e 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1194,12 +1194,15 @@ struct kvm_ppc_pvinfo {
 This ioctl fetches PV specific information that need to be passed to the guest
 using the device tree or other means from vm context.
 
-For now the only implemented piece of information distributed here is an array
-of 4 instructions that make up a hypercall.
+The hcall array defines 4 instructions that make up a hypercall.
 
 If any additional field gets added to this structure later on, a bit for that
 additional piece of information will be set in the flags bitmap.
 
+The flags bitmap is defined as:
+
+   /* the host supports the ePAPR idle hcall
+   #define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
 
 4.48 KVM_ASSIGN_PCI_DEVICE
 
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 7e313f1ed183..13d6b7bf3b69 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -34,5 +34,6 @@ header-y += termios.h
 header-y += types.h
 header-y += ucontext.h
 header-y += unistd.h
+header-y += epapr_hcalls.h
 
 generic-y += rwsem.h
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index a478e662b2bc..dbf56e173c25 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -38,8 +38,7 @@
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return !(v->arch.shared->msr & MSR_WE) ||
-	       !!(v->arch.pending_exceptions) ||
+	return !!(v->arch.pending_exceptions) ||
 	       v->requests;
 }
 
@@ -86,6 +85,11 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 
 		/* Second return value is in r4 */
 		break;
+	case EV_HCALL_TOKEN(EV_IDLE):
+		r = EV_SUCCESS;
+		kvm_vcpu_block(vcpu);
+		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
+		break;
 	default:
 		r = EV_UNIMPLEMENTED;
 		break;
@@ -779,6 +783,8 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
 	pvinfo->hcall[3] = inst_nop;
 #endif
 
+	pvinfo->flags = KVM_PPC_PVINFO_FLAGS_EV_IDLE;
+
 	return 0;
 }
 
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 0a6d6ba44c85..4cb3761bebae 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -477,6 +477,8 @@ struct kvm_ppc_smmu_info {
 	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
 };
 
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
+
 #define KVMIO 0xAE
 
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
-- 
cgit v1.2.3-55-g7522


From f61c94bb99ca4253ac5dd57750e1af209a4beb7a Mon Sep 17 00:00:00 2001
From: Bharat Bhushan
Date: Wed, 8 Aug 2012 20:38:19 +0000
Subject: KVM: PPC: booke: Add watchdog emulation

This patch adds the watchdog emulation in KVM. The watchdog
emulation is enabled by KVM_ENABLE_CAP(KVM_CAP_PPC_BOOKE_WATCHDOG) ioctl.
The kernel timer are used for watchdog emulation and emulates
h/w watchdog state machine. On watchdog timer expiry, it exit to QEMU
if TCR.WRC is non ZERO. QEMU can reset/shutdown etc depending upon how
it is configured.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
[bharat.bhushan@freescale.com: reworked patch]
Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
[agraf: adjust to new request framework]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_host.h  |   3 +
 arch/powerpc/include/asm/kvm_ppc.h   |   2 +
 arch/powerpc/include/asm/reg_booke.h |   7 ++
 arch/powerpc/kvm/book3s.c            |   9 ++
 arch/powerpc/kvm/booke.c             | 155 +++++++++++++++++++++++++++++++++++
 arch/powerpc/kvm/booke_emulate.c     |   8 ++
 arch/powerpc/kvm/powerpc.c           |  14 +++-
 include/linux/kvm.h                  |   2 +
 include/linux/kvm_host.h             |   1 +
 9 files changed, 199 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 4a5ec8f573c7..51b0ccd56769 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -471,6 +471,8 @@ struct kvm_vcpu_arch {
 	ulong fault_esr;
 	ulong queued_dear;
 	ulong queued_esr;
+	spinlock_t wdt_lock;
+	struct timer_list wdt_timer;
 	u32 tlbcfg[4];
 	u32 mmucfg;
 	u32 epr;
@@ -486,6 +488,7 @@ struct kvm_vcpu_arch {
 	u8 osi_needed;
 	u8 osi_enabled;
 	u8 papr_enabled;
+	u8 watchdog_enabled;
 	u8 sane;
 	u8 cpu_type;
 	u8 hcall_needed;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 3dfc437fb9d9..c06a64b53362 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -68,6 +68,8 @@ extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu);
 extern u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb);
 extern void kvmppc_decrementer_func(unsigned long data);
 extern int kvmppc_sanity_check(struct kvm_vcpu *vcpu);
+extern int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu);
+extern void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu);
 
 /* Core-specific hooks */
 
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 2d916c4982c5..e07e6af5e1ff 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -539,6 +539,13 @@
 #define TCR_FIE		0x00800000	/* FIT Interrupt Enable */
 #define TCR_ARE		0x00400000	/* Auto Reload Enable */
 
+#ifdef CONFIG_E500
+#define TCR_GET_WP(tcr)  ((((tcr) & 0xC0000000) >> 30) | \
+			      (((tcr) & 0x1E0000) >> 15))
+#else
+#define TCR_GET_WP(tcr)  (((tcr) & 0xC0000000) >> 30)
+#endif
+
 /* Bit definitions for the TSR. */
 #define TSR_ENW		0x80000000	/* Enable Next Watchdog */
 #define TSR_WIS		0x40000000	/* WDT Interrupt Status */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 3f2a8360c857..e94666566fa9 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -411,6 +411,15 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+}
+
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index c36493087dbf..09e8bf33a8c9 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -209,6 +209,16 @@ void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
 	clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
 }
 
+static void kvmppc_core_queue_watchdog(struct kvm_vcpu *vcpu)
+{
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_WATCHDOG);
+}
+
+static void kvmppc_core_dequeue_watchdog(struct kvm_vcpu *vcpu)
+{
+	clear_bit(BOOKE_IRQPRIO_WATCHDOG, &vcpu->arch.pending_exceptions);
+}
+
 static void set_guest_srr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
 {
 #ifdef CONFIG_KVM_BOOKE_HV
@@ -328,6 +338,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		msr_mask = MSR_CE | MSR_ME | MSR_DE;
 		int_class = INT_CLASS_NONCRIT;
 		break;
+	case BOOKE_IRQPRIO_WATCHDOG:
 	case BOOKE_IRQPRIO_CRITICAL:
 	case BOOKE_IRQPRIO_DBELL_CRIT:
 		allowed = vcpu->arch.shared->msr & MSR_CE;
@@ -407,12 +418,121 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	return allowed;
 }
 
+/*
+ * Return the number of jiffies until the next timeout.  If the timeout is
+ * longer than the NEXT_TIMER_MAX_DELTA, then return NEXT_TIMER_MAX_DELTA
+ * because the larger value can break the timer APIs.
+ */
+static unsigned long watchdog_next_timeout(struct kvm_vcpu *vcpu)
+{
+	u64 tb, wdt_tb, wdt_ticks = 0;
+	u64 nr_jiffies = 0;
+	u32 period = TCR_GET_WP(vcpu->arch.tcr);
+
+	wdt_tb = 1ULL << (63 - period);
+	tb = get_tb();
+	/*
+	 * The watchdog timeout will hapeen when TB bit corresponding
+	 * to watchdog will toggle from 0 to 1.
+	 */
+	if (tb & wdt_tb)
+		wdt_ticks = wdt_tb;
+
+	wdt_ticks += wdt_tb - (tb & (wdt_tb - 1));
+
+	/* Convert timebase ticks to jiffies */
+	nr_jiffies = wdt_ticks;
+
+	if (do_div(nr_jiffies, tb_ticks_per_jiffy))
+		nr_jiffies++;
+
+	return min_t(unsigned long long, nr_jiffies, NEXT_TIMER_MAX_DELTA);
+}
+
+static void arm_next_watchdog(struct kvm_vcpu *vcpu)
+{
+	unsigned long nr_jiffies;
+	unsigned long flags;
+
+	/*
+	 * If TSR_ENW and TSR_WIS are not set then no need to exit to
+	 * userspace, so clear the KVM_REQ_WATCHDOG request.
+	 */
+	if ((vcpu->arch.tsr & (TSR_ENW | TSR_WIS)) != (TSR_ENW | TSR_WIS))
+		clear_bit(KVM_REQ_WATCHDOG, &vcpu->requests);
+
+	spin_lock_irqsave(&vcpu->arch.wdt_lock, flags);
+	nr_jiffies = watchdog_next_timeout(vcpu);
+	/*
+	 * If the number of jiffies of watchdog timer >= NEXT_TIMER_MAX_DELTA
+	 * then do not run the watchdog timer as this can break timer APIs.
+	 */
+	if (nr_jiffies < NEXT_TIMER_MAX_DELTA)
+		mod_timer(&vcpu->arch.wdt_timer, jiffies + nr_jiffies);
+	else
+		del_timer(&vcpu->arch.wdt_timer);
+	spin_unlock_irqrestore(&vcpu->arch.wdt_lock, flags);
+}
+
+void kvmppc_watchdog_func(unsigned long data)
+{
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+	u32 tsr, new_tsr;
+	int final;
+
+	do {
+		new_tsr = tsr = vcpu->arch.tsr;
+		final = 0;
+
+		/* Time out event */
+		if (tsr & TSR_ENW) {
+			if (tsr & TSR_WIS)
+				final = 1;
+			else
+				new_tsr = tsr | TSR_WIS;
+		} else {
+			new_tsr = tsr | TSR_ENW;
+		}
+	} while (cmpxchg(&vcpu->arch.tsr, tsr, new_tsr) != tsr);
+
+	if (new_tsr & TSR_WIS) {
+		smp_wmb();
+		kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+		kvm_vcpu_kick(vcpu);
+	}
+
+	/*
+	 * If this is final watchdog expiry and some action is required
+	 * then exit to userspace.
+	 */
+	if (final && (vcpu->arch.tcr & TCR_WRC_MASK) &&
+	    vcpu->arch.watchdog_enabled) {
+		smp_wmb();
+		kvm_make_request(KVM_REQ_WATCHDOG, vcpu);
+		kvm_vcpu_kick(vcpu);
+	}
+
+	/*
+	 * Stop running the watchdog timer after final expiration to
+	 * prevent the host from being flooded with timers if the
+	 * guest sets a short period.
+	 * Timers will resume when TSR/TCR is updated next time.
+	 */
+	if (!final)
+		arm_next_watchdog(vcpu);
+}
+
 static void update_timer_ints(struct kvm_vcpu *vcpu)
 {
 	if ((vcpu->arch.tcr & TCR_DIE) && (vcpu->arch.tsr & TSR_DIS))
 		kvmppc_core_queue_dec(vcpu);
 	else
 		kvmppc_core_dequeue_dec(vcpu);
+
+	if ((vcpu->arch.tcr & TCR_WIE) && (vcpu->arch.tsr & TSR_WIS))
+		kvmppc_core_queue_watchdog(vcpu);
+	else
+		kvmppc_core_dequeue_watchdog(vcpu);
 }
 
 static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
@@ -466,6 +586,11 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 		kvmppc_core_flush_tlb(vcpu);
 #endif
 
+	if (kvm_check_request(KVM_REQ_WATCHDOG, vcpu)) {
+		vcpu->run->exit_reason = KVM_EXIT_WATCHDOG;
+		r = 0;
+	}
+
 	return r;
 }
 
@@ -995,6 +1120,21 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	return r;
 }
 
+int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	/* setup watchdog timer once */
+	spin_lock_init(&vcpu->arch.wdt_lock);
+	setup_timer(&vcpu->arch.wdt_timer, kvmppc_watchdog_func,
+		    (unsigned long)vcpu);
+
+	return 0;
+}
+
+void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+	del_timer_sync(&vcpu->arch.wdt_timer);
+}
+
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
@@ -1090,7 +1230,13 @@ static int set_sregs_base(struct kvm_vcpu *vcpu,
 	}
 
 	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) {
+		u32 old_tsr = vcpu->arch.tsr;
+
 		vcpu->arch.tsr = sregs->u.e.tsr;
+
+		if ((old_tsr ^ vcpu->arch.tsr) & (TSR_ENW | TSR_WIS))
+			arm_next_watchdog(vcpu);
+
 		update_timer_ints(vcpu);
 	}
 
@@ -1251,6 +1397,7 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr)
 {
 	vcpu->arch.tcr = new_tcr;
+	arm_next_watchdog(vcpu);
 	update_timer_ints(vcpu);
 }
 
@@ -1265,6 +1412,14 @@ void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
 void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
 {
 	clear_bits(tsr_bits, &vcpu->arch.tsr);
+
+	/*
+	 * We may have stopped the watchdog due to
+	 * being stuck on final expiration.
+	 */
+	if (tsr_bits & (TSR_ENW | TSR_WIS))
+		arm_next_watchdog(vcpu);
+
 	update_timer_ints(vcpu);
 }
 
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 12834bb608ab..5a66ade7fd17 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -145,6 +145,14 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 		kvmppc_clr_tsr_bits(vcpu, spr_val);
 		break;
 	case SPRN_TCR:
+		/*
+		 * WRC is a 2-bit field that is supposed to preserve its
+		 * value once written to non-zero.
+		 */
+		if (vcpu->arch.tcr & TCR_WRC_MASK) {
+			spr_val &= ~TCR_WRC_MASK;
+			spr_val |= vcpu->arch.tcr & TCR_WRC_MASK;
+		}
 		kvmppc_set_tcr(vcpu, spr_val);
 		break;
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 54b12af577d0..0ffd7d17adc7 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -300,6 +300,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	switch (ext) {
 #ifdef CONFIG_BOOKE
 	case KVM_CAP_PPC_BOOKE_SREGS:
+	case KVM_CAP_PPC_BOOKE_WATCHDOG:
 #else
 	case KVM_CAP_PPC_SEGSTATE:
 	case KVM_CAP_PPC_HIOR:
@@ -476,6 +477,8 @@ enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
+	int ret;
+
 	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
 	tasklet_init(&vcpu->arch.tasklet, kvmppc_decrementer_func, (ulong)vcpu);
 	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
@@ -484,13 +487,14 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_KVM_EXIT_TIMING
 	mutex_init(&vcpu->arch.exit_timing_lock);
 #endif
-
-	return 0;
+	ret = kvmppc_subarch_vcpu_init(vcpu);
+	return ret;
 }
 
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 	kvmppc_mmu_destroy(vcpu);
+	kvmppc_subarch_vcpu_uninit(vcpu);
 }
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -735,6 +739,12 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		r = 0;
 		vcpu->arch.papr_enabled = true;
 		break;
+#ifdef CONFIG_BOOKE
+	case KVM_CAP_PPC_BOOKE_WATCHDOG:
+		r = 0;
+		vcpu->arch.watchdog_enabled = true;
+		break;
+#endif
 #if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
 	case KVM_CAP_SW_TLB: {
 		struct kvm_config_tlb cfg;
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 4cb3761bebae..1649d4b57e1f 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -167,6 +167,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_OSI              18
 #define KVM_EXIT_PAPR_HCALL	  19
 #define KVM_EXIT_S390_UCONTROL	  20
+#define KVM_EXIT_WATCHDOG         21
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 #define KVM_INTERNAL_ERROR_EMULATION 1
@@ -628,6 +629,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_READONLY_MEM 81
 #endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
+#define KVM_CAP_PPC_BOOKE_WATCHDOG 83
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2850656e2e96..0ca3663206f8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -118,6 +118,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_IMMEDIATE_EXIT    15
 #define KVM_REQ_PMU               16
 #define KVM_REQ_PMI               17
+#define KVM_REQ_WATCHDOG          18
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
-- 
cgit v1.2.3-55-g7522


From ed7a8d7a3c5dd4adedb271112b6faba45c7037f9 Mon Sep 17 00:00:00 2001
From: Paul Mackerras
Date: Thu, 13 Sep 2012 21:44:30 +0000
Subject: KVM: Move some PPC ioctl definitions to the correct place

This moves the definitions of KVM_CREATE_SPAPR_TCE and
KVM_ALLOCATE_RMA in include/linux/kvm.h from the section listing the
vcpu ioctls to the section listing VM ioctls, as these are both
implemented and documented as VM ioctls.

Fortunately there is no actual collision of ioctl numbers at this
point.  Moving these to the correct section will reduce the
probability of a future collision.  This does not change the
user/kernel ABI at all.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 include/linux/kvm.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 1649d4b57e1f..65ad5c624c70 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -852,6 +852,9 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_GET_SMMU_INFO	  _IOR(KVMIO,  0xa6, struct kvm_ppc_smmu_info)
 /* Available with KVM_CAP_PPC_ALLOC_HTAB */
 #define KVM_PPC_ALLOCATE_HTAB	  _IOWR(KVMIO, 0xa7, __u32)
+#define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
+/* Available with KVM_CAP_RMA */
+#define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
 
 /*
  * ioctls for vcpu fds
@@ -915,9 +918,6 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_XCRS */
 #define KVM_GET_XCRS		  _IOR(KVMIO,  0xa6, struct kvm_xcrs)
 #define KVM_SET_XCRS		  _IOW(KVMIO,  0xa7, struct kvm_xcrs)
-#define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
-/* Available with KVM_CAP_RMA */
-#define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
 /* Available with KVM_CAP_SW_TLB */
 #define KVM_DIRTY_TLB		  _IOW(KVMIO,  0xaa, struct kvm_dirty_tlb)
 /* Available with KVM_CAP_ONE_REG */
-- 
cgit v1.2.3-55-g7522


From 385ddeac7ed99cf7dc62d76274d55fbd7cae1b5a Mon Sep 17 00:00:00 2001
From: Luck, Tony
Date: Fri, 5 Oct 2012 15:05:34 -0700
Subject: X86 ACPI: Use #ifdef not #if for CONFIG_X86 check

Fix a build warning on ia64:

include/linux/acpi.h:437:5: warning: "CONFIG_X86" is not defined

Signed-off-by: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/506f59ae9600b36a4@agluck-desktop.sc.intel.com
Cc: Len Brown <lenb@kernel.org>
Cc: Thomas Renninger <trenn@suse.de>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 include/linux/acpi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d14081c10c17..49fe586e3b1e 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -434,7 +434,7 @@ void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
 
 acpi_status acpi_os_prepare_sleep(u8 sleep_state,
 				  u32 pm1a_control, u32 pm1b_control);
-#if CONFIG_X86
+#ifdef CONFIG_X86
 void arch_reserve_mem_area(acpi_physical_address addr, size_t size);
 #else
 static inline void arch_reserve_mem_area(acpi_physical_address addr,
-- 
cgit v1.2.3-55-g7522


From fa4ebc66c432d0e0ec947cb754d4144c4a681f28 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Fri, 5 Oct 2012 16:56:55 +0300
Subject: Bluetooth: AMP: Factor out amp_ctrl_add

Add ctrl_id parameter to amp_ctrl_add since we always set it
after function ctrl is created.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h | 2 +-
 net/bluetooth/a2mp.c        | 8 ++------
 net/bluetooth/amp.c         | 7 ++++---
 3 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index b1e54903dd42..ae2c3e536473 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -26,7 +26,7 @@ struct amp_ctrl {
 
 int amp_ctrl_put(struct amp_ctrl *ctrl);
 void amp_ctrl_get(struct amp_ctrl *ctrl);
-struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr);
+struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id);
 struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id);
 void amp_ctrl_list_flush(struct amp_mgr *mgr);
 
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index d4946b591b71..88a4b583d218 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -316,12 +316,10 @@ static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 	if (rsp->status)
 		return -EINVAL;
 
-	ctrl = amp_ctrl_add(mgr);
+	ctrl = amp_ctrl_add(mgr, rsp->id);
 	if (!ctrl)
 		return -ENOMEM;
 
-	ctrl->id = rsp->id;
-
 	req.id = rsp->id;
 	a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req),
 		  &req);
@@ -461,7 +459,7 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	ctrl = amp_ctrl_lookup(mgr, rsp.remote_id);
 	if (!ctrl) {
-		ctrl = amp_ctrl_add(mgr);
+		ctrl = amp_ctrl_add(mgr, rsp.remote_id);
 		if (ctrl) {
 			amp_ctrl_get(ctrl);
 		} else {
@@ -474,8 +472,6 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 		size_t assoc_len = le16_to_cpu(hdr->len) - sizeof(*req);
 		u8 *assoc;
 
-		ctrl->id = rsp.remote_id;
-
 		assoc = kzalloc(assoc_len, GFP_KERNEL);
 		if (!assoc) {
 			amp_ctrl_put(ctrl);
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index b6e1c3ac74f1..2fc5562a84b9 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -45,7 +45,7 @@ int amp_ctrl_put(struct amp_ctrl *ctrl)
 	return kref_put(&ctrl->kref, &amp_ctrl_destroy);
 }
 
-struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr)
+struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id)
 {
 	struct amp_ctrl *ctrl;
 
@@ -53,12 +53,13 @@ struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr)
 	if (!ctrl)
 		return NULL;
 
+	kref_init(&ctrl->kref);
+	ctrl->id = id;
+
 	mutex_lock(&mgr->amp_ctrls_lock);
 	list_add(&ctrl->list, &mgr->amp_ctrls);
 	mutex_unlock(&mgr->amp_ctrls_lock);
 
-	kref_init(&ctrl->kref);
-
 	BT_DBG("mgr %p ctrl %p", mgr, ctrl);
 
 	return ctrl;
-- 
cgit v1.2.3-55-g7522


From a0c234fe8972aa6a5afe2db6c27a3f5d5fbd88e7 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Fri, 5 Oct 2012 16:56:56 +0300
Subject: Bluetooth: AMP: Factor out phylink_add

Add direction parameter to phylink_add since it is anyway set later.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h | 2 +-
 net/bluetooth/a2mp.c        | 4 ++--
 net/bluetooth/amp.c         | 6 ++++--
 3 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index ae2c3e536473..2e7c79ea0463 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -31,7 +31,7 @@ struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id);
 void amp_ctrl_list_flush(struct amp_mgr *mgr);
 
 struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
-			     u8 remote_id);
+			     u8 remote_id, bool out);
 
 int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type);
 
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 88a4b583d218..3ff4dc928bf5 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -417,7 +417,7 @@ static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 	if (!hdev)
 		return -EINVAL;
 
-	hcon = phylink_add(hdev, mgr, rsp->id);
+	hcon = phylink_add(hdev, mgr, rsp->id, true);
 	if (!hcon)
 		goto done;
 
@@ -487,7 +487,7 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 		amp_ctrl_put(ctrl);
 	}
 
-	hcon = phylink_add(hdev, mgr, req->local_id);
+	hcon = phylink_add(hdev, mgr, req->local_id, false);
 	if (hcon) {
 		amp_accept_phylink(hdev, mgr, hcon);
 		rsp.status = A2MP_STATUS_SUCCESS;
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 2fc5562a84b9..59da0f15818e 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -108,7 +108,7 @@ static u8 __next_handle(struct amp_mgr *mgr)
 }
 
 struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
-			     u8 remote_id)
+			     u8 remote_id, bool out)
 {
 	bdaddr_t *dst = mgr->l2cap_conn->dst;
 	struct hci_conn *hcon;
@@ -117,12 +117,14 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
 	if (!hcon)
 		return NULL;
 
+	BT_DBG("hcon %p dst %pMR", hcon, dst);
+
 	hcon->state = BT_CONNECT;
-	hcon->out = true;
 	hcon->attempt++;
 	hcon->handle = __next_handle(mgr);
 	hcon->remote_id = remote_id;
 	hcon->amp_mgr = mgr;
+	hcon->out = out;
 
 	return hcon;
 }
-- 
cgit v1.2.3-55-g7522


From 0b4558e388e72b6d088a057833bafb816ff8af85 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Fri, 5 Oct 2012 16:56:58 +0300
Subject: Bluetooth: Adjust L2CAP Max PDU size for AMP packets

Maximum PDU size is defined by new BT Spec as 1492 octets.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Reviewed-by: Mat Martineau <mathewm@codeaurora.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index ab58b81fb7c5..7002f0d656ed 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -38,7 +38,7 @@
 #define L2CAP_DEFAULT_MAX_TX		3
 #define L2CAP_DEFAULT_RETRANS_TO	2000    /* 2 seconds */
 #define L2CAP_DEFAULT_MONITOR_TO	12000   /* 12 seconds */
-#define L2CAP_DEFAULT_MAX_PDU_SIZE	1009    /* Sized for 3-DH5 packet */
+#define L2CAP_DEFAULT_MAX_PDU_SIZE	1492    /* Sized for AMP packet */
 #define L2CAP_DEFAULT_ACK_TO		200
 #define L2CAP_DEFAULT_MAX_SDU_SIZE	0xFFFF
 #define L2CAP_DEFAULT_SDU_ITIME		0xFFFFFFFF
-- 
cgit v1.2.3-55-g7522


From 8936fa6d1c202abeb94c51c68897342e8714dd69 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Mon, 8 Oct 2012 11:14:41 +0300
Subject: Bluetooth: L2CAP: Fix using default Flush Timeout for EFS

There are two Flush Timeouts: one is old Flush Timeot Option
which is 2 octets and the second is Flush Timeout inside EFS
which is 4 octets long.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h | 3 ++-
 net/bluetooth/l2cap_core.c    | 6 +++---
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 7002f0d656ed..caab98c45121 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -32,7 +32,8 @@
 /* L2CAP defaults */
 #define L2CAP_DEFAULT_MTU		672
 #define L2CAP_DEFAULT_MIN_MTU		48
-#define L2CAP_DEFAULT_FLUSH_TO		0xffff
+#define L2CAP_DEFAULT_FLUSH_TO		0xFFFF
+#define L2CAP_EFS_DEFAULT_FLUSH_TO	0xFFFFFFFF
 #define L2CAP_DEFAULT_TX_WINDOW		63
 #define L2CAP_DEFAULT_EXT_WINDOW	0x3FFF
 #define L2CAP_DEFAULT_MAX_TX		3
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index d605bbfddec1..d42cdb145c6d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -504,7 +504,7 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
 	chan->local_msdu	= L2CAP_DEFAULT_MAX_SDU_SIZE;
 	chan->local_sdu_itime	= L2CAP_DEFAULT_SDU_ITIME;
 	chan->local_acc_lat	= L2CAP_DEFAULT_ACC_LAT;
-	chan->local_flush_to	= L2CAP_DEFAULT_FLUSH_TO;
+	chan->local_flush_to	= L2CAP_EFS_DEFAULT_FLUSH_TO;
 
 	l2cap_chan_hold(chan);
 
@@ -2727,7 +2727,7 @@ static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan)
 		efs.msdu	= cpu_to_le16(chan->local_msdu);
 		efs.sdu_itime	= cpu_to_le32(chan->local_sdu_itime);
 		efs.acc_lat	= __constant_cpu_to_le32(L2CAP_DEFAULT_ACC_LAT);
-		efs.flush_to	= __constant_cpu_to_le32(L2CAP_DEFAULT_FLUSH_TO);
+		efs.flush_to	= __constant_cpu_to_le32(L2CAP_EFS_DEFAULT_FLUSH_TO);
 		break;
 
 	case L2CAP_MODE_STREAMING:
@@ -2744,7 +2744,7 @@ static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan)
 	}
 
 	l2cap_add_conf_opt(ptr, L2CAP_CONF_EFS, sizeof(efs),
-							(unsigned long) &efs);
+			   (unsigned long) &efs);
 }
 
 static void l2cap_ack_timeout(struct work_struct *work)
-- 
cgit v1.2.3-55-g7522


From 8b6e4547e0e4b6aac11df6d8d4e71ea2ab159b5e Mon Sep 17 00:00:00 2001
From: Jan Kiszka
Date: Thu, 20 Sep 2012 07:43:08 +0200
Subject: KVM: x86: Convert kvm_arch_vcpu_reset into private kvm_vcpu_reset

There are no external callers of this function as there is no concept of
resetting a vcpu from generic code.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/x86.c       | 8 +++++---
 include/linux/kvm_host.h | 1 -
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1eefebe5d727..dfed7ca2d27a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -160,6 +160,8 @@ u64 __read_mostly host_xcr0;
 
 int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt);
 
+static int kvm_vcpu_reset(struct kvm_vcpu *vcpu);
+
 static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
 {
 	int i;
@@ -5426,7 +5428,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		pr_debug("vcpu %d received sipi with vector # %x\n",
 			 vcpu->vcpu_id, vcpu->arch.sipi_vector);
 		kvm_lapic_reset(vcpu);
-		r = kvm_arch_vcpu_reset(vcpu);
+		r = kvm_vcpu_reset(vcpu);
 		if (r)
 			return r;
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -6036,7 +6038,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	r = vcpu_load(vcpu);
 	if (r)
 		return r;
-	r = kvm_arch_vcpu_reset(vcpu);
+	r = kvm_vcpu_reset(vcpu);
 	if (r == 0)
 		r = kvm_mmu_setup(vcpu);
 	vcpu_put(vcpu);
@@ -6058,7 +6060,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->vcpu_free(vcpu);
 }
 
-int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
+static int kvm_vcpu_reset(struct kvm_vcpu *vcpu)
 {
 	atomic_set(&vcpu->arch.nmi_queued, 0);
 	vcpu->arch.nmi_pending = 0;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 93bfc9f9815c..c35b1c08c004 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -582,7 +582,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id);
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
-int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu);
 int kvm_arch_hardware_enable(void *garbage);
 void kvm_arch_hardware_disable(void *garbage);
 int kvm_arch_hardware_setup(void);
-- 
cgit v1.2.3-55-g7522


From 674e95ca446369e9ca40e4e92b214a616a52bcd6 Mon Sep 17 00:00:00 2001
From: David Howells
Date: Tue, 9 Oct 2012 09:49:13 +0100
Subject: UAPI: (Scripted) Disintegrate include/sound

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Dave Jones <davej@redhat.com>
---
 include/sound/Kbuild                  |  10 -
 include/sound/asequencer.h            | 594 +--------------------
 include/sound/asound.h                | 935 +--------------------------------
 include/sound/asound_fm.h             | 134 -----
 include/sound/compress_offload.h      | 161 ------
 include/sound/compress_params.h       | 400 --------------
 include/sound/emu10k1.h               | 355 +------------
 include/sound/hdsp.h                  | 110 ----
 include/sound/hdspm.h                 | 229 --------
 include/sound/sb16_csp.h              | 104 +---
 include/sound/sfnt_info.h             | 212 --------
 include/uapi/sound/Kbuild             |  10 +
 include/uapi/sound/asequencer.h       | 614 ++++++++++++++++++++++
 include/uapi/sound/asound.h           | 957 ++++++++++++++++++++++++++++++++++
 include/uapi/sound/asound_fm.h        | 134 +++++
 include/uapi/sound/compress_offload.h | 161 ++++++
 include/uapi/sound/compress_params.h  | 400 ++++++++++++++
 include/uapi/sound/emu10k1.h          | 373 +++++++++++++
 include/uapi/sound/hdsp.h             | 110 ++++
 include/uapi/sound/hdspm.h            | 229 ++++++++
 include/uapi/sound/sb16_csp.h         | 122 +++++
 include/uapi/sound/sfnt_info.h        | 212 ++++++++
 22 files changed, 3330 insertions(+), 3236 deletions(-)
 delete mode 100644 include/sound/asound_fm.h
 delete mode 100644 include/sound/compress_offload.h
 delete mode 100644 include/sound/compress_params.h
 delete mode 100644 include/sound/hdsp.h
 delete mode 100644 include/sound/hdspm.h
 delete mode 100644 include/sound/sfnt_info.h
 create mode 100644 include/uapi/sound/asequencer.h
 create mode 100644 include/uapi/sound/asound.h
 create mode 100644 include/uapi/sound/asound_fm.h
 create mode 100644 include/uapi/sound/compress_offload.h
 create mode 100644 include/uapi/sound/compress_params.h
 create mode 100644 include/uapi/sound/emu10k1.h
 create mode 100644 include/uapi/sound/hdsp.h
 create mode 100644 include/uapi/sound/hdspm.h
 create mode 100644 include/uapi/sound/sb16_csp.h
 create mode 100644 include/uapi/sound/sfnt_info.h

(limited to 'include')

diff --git a/include/sound/Kbuild b/include/sound/Kbuild
index 6df30ed1581c..e69de29bb2d1 100644
--- a/include/sound/Kbuild
+++ b/include/sound/Kbuild
@@ -1,10 +0,0 @@
-header-y += asequencer.h
-header-y += asound.h
-header-y += asound_fm.h
-header-y += emu10k1.h
-header-y += hdsp.h
-header-y += hdspm.h
-header-y += sb16_csp.h
-header-y += sfnt_info.h
-header-y += compress_params.h
-header-y += compress_offload.h
diff --git a/include/sound/asequencer.h b/include/sound/asequencer.h
index 1505e6d5ef82..75935ce739c5 100644
--- a/include/sound/asequencer.h
+++ b/include/sound/asequencer.h
@@ -22,294 +22,9 @@
 #ifndef __SOUND_ASEQUENCER_H
 #define __SOUND_ASEQUENCER_H
 
-#ifdef __KERNEL__
 #include <linux/ioctl.h>
 #include <sound/asound.h>
-#endif
-
-/** version of the sequencer */
-#define SNDRV_SEQ_VERSION SNDRV_PROTOCOL_VERSION (1, 0, 1)
-
-/**
- * definition of sequencer event types
- */
-
-/** system messages
- * event data type = #snd_seq_result
- */
-#define SNDRV_SEQ_EVENT_SYSTEM		0
-#define SNDRV_SEQ_EVENT_RESULT		1
-
-/** note messages (channel specific)
- * event data type = #snd_seq_ev_note
- */
-#define SNDRV_SEQ_EVENT_NOTE		5
-#define SNDRV_SEQ_EVENT_NOTEON		6
-#define SNDRV_SEQ_EVENT_NOTEOFF		7
-#define SNDRV_SEQ_EVENT_KEYPRESS	8
-	
-/** control messages (channel specific)
- * event data type = #snd_seq_ev_ctrl
- */
-#define SNDRV_SEQ_EVENT_CONTROLLER	10
-#define SNDRV_SEQ_EVENT_PGMCHANGE	11
-#define SNDRV_SEQ_EVENT_CHANPRESS	12
-#define SNDRV_SEQ_EVENT_PITCHBEND	13	/**< from -8192 to 8191 */
-#define SNDRV_SEQ_EVENT_CONTROL14	14	/**< 14 bit controller value */
-#define SNDRV_SEQ_EVENT_NONREGPARAM	15	/**< 14 bit NRPN address + 14 bit unsigned value */
-#define SNDRV_SEQ_EVENT_REGPARAM	16	/**< 14 bit RPN address + 14 bit unsigned value */
-
-/** synchronisation messages
- * event data type = #snd_seq_ev_ctrl
- */
-#define SNDRV_SEQ_EVENT_SONGPOS		20	/* Song Position Pointer with LSB and MSB values */
-#define SNDRV_SEQ_EVENT_SONGSEL		21	/* Song Select with song ID number */
-#define SNDRV_SEQ_EVENT_QFRAME		22	/* midi time code quarter frame */
-#define SNDRV_SEQ_EVENT_TIMESIGN	23	/* SMF Time Signature event */
-#define SNDRV_SEQ_EVENT_KEYSIGN		24	/* SMF Key Signature event */
-	        
-/** timer messages
- * event data type = snd_seq_ev_queue_control
- */
-#define SNDRV_SEQ_EVENT_START		30	/* midi Real Time Start message */
-#define SNDRV_SEQ_EVENT_CONTINUE	31	/* midi Real Time Continue message */
-#define SNDRV_SEQ_EVENT_STOP		32	/* midi Real Time Stop message */	
-#define	SNDRV_SEQ_EVENT_SETPOS_TICK	33	/* set tick queue position */
-#define SNDRV_SEQ_EVENT_SETPOS_TIME	34	/* set realtime queue position */
-#define SNDRV_SEQ_EVENT_TEMPO		35	/* (SMF) Tempo event */
-#define SNDRV_SEQ_EVENT_CLOCK		36	/* midi Real Time Clock message */
-#define SNDRV_SEQ_EVENT_TICK		37	/* midi Real Time Tick message */
-#define SNDRV_SEQ_EVENT_QUEUE_SKEW	38	/* skew queue tempo */
-
-/** others
- * event data type = none
- */
-#define SNDRV_SEQ_EVENT_TUNE_REQUEST	40	/* tune request */
-#define SNDRV_SEQ_EVENT_RESET		41	/* reset to power-on state */
-#define SNDRV_SEQ_EVENT_SENSING		42	/* "active sensing" event */
-
-/** echo back, kernel private messages
- * event data type = any type
- */
-#define SNDRV_SEQ_EVENT_ECHO		50	/* echo event */
-#define SNDRV_SEQ_EVENT_OSS		51	/* OSS raw event */
-
-/** system status messages (broadcast for subscribers)
- * event data type = snd_seq_addr
- */
-#define SNDRV_SEQ_EVENT_CLIENT_START	60	/* new client has connected */
-#define SNDRV_SEQ_EVENT_CLIENT_EXIT	61	/* client has left the system */
-#define SNDRV_SEQ_EVENT_CLIENT_CHANGE	62	/* client status/info has changed */
-#define SNDRV_SEQ_EVENT_PORT_START	63	/* new port was created */
-#define SNDRV_SEQ_EVENT_PORT_EXIT	64	/* port was deleted from system */
-#define SNDRV_SEQ_EVENT_PORT_CHANGE	65	/* port status/info has changed */
-
-/** port connection changes
- * event data type = snd_seq_connect
- */
-#define SNDRV_SEQ_EVENT_PORT_SUBSCRIBED	66	/* ports connected */
-#define SNDRV_SEQ_EVENT_PORT_UNSUBSCRIBED 67	/* ports disconnected */
-
-/* 70-89:  synthesizer events - obsoleted */
-
-/** user-defined events with fixed length
- * event data type = any
- */
-#define SNDRV_SEQ_EVENT_USR0		90
-#define SNDRV_SEQ_EVENT_USR1		91
-#define SNDRV_SEQ_EVENT_USR2		92
-#define SNDRV_SEQ_EVENT_USR3		93
-#define SNDRV_SEQ_EVENT_USR4		94
-#define SNDRV_SEQ_EVENT_USR5		95
-#define SNDRV_SEQ_EVENT_USR6		96
-#define SNDRV_SEQ_EVENT_USR7		97
-#define SNDRV_SEQ_EVENT_USR8		98
-#define SNDRV_SEQ_EVENT_USR9		99
-
-/* 100-118: instrument layer - obsoleted */
-/* 119-129: reserved */
-
-/* 130-139: variable length events
- * event data type = snd_seq_ev_ext
- * (SNDRV_SEQ_EVENT_LENGTH_VARIABLE must be set)
- */
-#define SNDRV_SEQ_EVENT_SYSEX		130	/* system exclusive data (variable length) */
-#define SNDRV_SEQ_EVENT_BOUNCE		131	/* error event */
-/* 132-134: reserved */
-#define SNDRV_SEQ_EVENT_USR_VAR0	135
-#define SNDRV_SEQ_EVENT_USR_VAR1	136
-#define SNDRV_SEQ_EVENT_USR_VAR2	137
-#define SNDRV_SEQ_EVENT_USR_VAR3	138
-#define SNDRV_SEQ_EVENT_USR_VAR4	139
-
-/* 150-151: kernel events with quote - DO NOT use in user clients */
-#define SNDRV_SEQ_EVENT_KERNEL_ERROR	150
-#define SNDRV_SEQ_EVENT_KERNEL_QUOTE	151	/* obsolete */
-
-/* 152-191: reserved */
-
-/* 192-254: hardware specific events */
-
-/* 255: special event */
-#define SNDRV_SEQ_EVENT_NONE		255
-
-
-typedef unsigned char snd_seq_event_type_t;
-
-/** event address */
-struct snd_seq_addr {
-	unsigned char client;	/**< Client number:         0..255, 255 = broadcast to all clients */
-	unsigned char port;	/**< Port within client:    0..255, 255 = broadcast to all ports */
-};
-
-/** port connection */
-struct snd_seq_connect {
-	struct snd_seq_addr sender;
-	struct snd_seq_addr dest;
-};
-
-
-#define SNDRV_SEQ_ADDRESS_UNKNOWN	253	/* unknown source */
-#define SNDRV_SEQ_ADDRESS_SUBSCRIBERS	254	/* send event to all subscribed ports */
-#define SNDRV_SEQ_ADDRESS_BROADCAST	255	/* send event to all queues/clients/ports/channels */
-#define SNDRV_SEQ_QUEUE_DIRECT		253	/* direct dispatch */
-
-	/* event mode flag - NOTE: only 8 bits available! */
-#define SNDRV_SEQ_TIME_STAMP_TICK	(0<<0) /* timestamp in clock ticks */
-#define SNDRV_SEQ_TIME_STAMP_REAL	(1<<0) /* timestamp in real time */
-#define SNDRV_SEQ_TIME_STAMP_MASK	(1<<0)
-
-#define SNDRV_SEQ_TIME_MODE_ABS		(0<<1)	/* absolute timestamp */
-#define SNDRV_SEQ_TIME_MODE_REL		(1<<1)	/* relative to current time */
-#define SNDRV_SEQ_TIME_MODE_MASK	(1<<1)
-
-#define SNDRV_SEQ_EVENT_LENGTH_FIXED	(0<<2)	/* fixed event size */
-#define SNDRV_SEQ_EVENT_LENGTH_VARIABLE	(1<<2)	/* variable event size */
-#define SNDRV_SEQ_EVENT_LENGTH_VARUSR	(2<<2)	/* variable event size - user memory space */
-#define SNDRV_SEQ_EVENT_LENGTH_MASK	(3<<2)
-
-#define SNDRV_SEQ_PRIORITY_NORMAL	(0<<4)	/* normal priority */
-#define SNDRV_SEQ_PRIORITY_HIGH		(1<<4)	/* event should be processed before others */
-#define SNDRV_SEQ_PRIORITY_MASK		(1<<4)
-
-
-	/* note event */
-struct snd_seq_ev_note {
-	unsigned char channel;
-	unsigned char note;
-	unsigned char velocity;
-	unsigned char off_velocity;	/* only for SNDRV_SEQ_EVENT_NOTE */
-	unsigned int duration;		/* only for SNDRV_SEQ_EVENT_NOTE */
-};
-
-	/* controller event */
-struct snd_seq_ev_ctrl {
-	unsigned char channel;
-	unsigned char unused1, unused2, unused3;	/* pad */
-	unsigned int param;
-	signed int value;
-};
-
-	/* generic set of bytes (12x8 bit) */
-struct snd_seq_ev_raw8 {
-	unsigned char d[12];	/* 8 bit value */
-};
-
-	/* generic set of integers (3x32 bit) */
-struct snd_seq_ev_raw32 {
-	unsigned int d[3];	/* 32 bit value */
-};
-
-	/* external stored data */
-struct snd_seq_ev_ext {
-	unsigned int len;	/* length of data */
-	void *ptr;		/* pointer to data (note: maybe 64-bit) */
-} __attribute__((packed));
-
-struct snd_seq_result {
-	int event;		/* processed event type */
-	int result;
-};
-
-
-struct snd_seq_real_time {
-	unsigned int tv_sec;	/* seconds */
-	unsigned int tv_nsec;	/* nanoseconds */
-};
-
-typedef unsigned int snd_seq_tick_time_t;	/* midi ticks */
-
-union snd_seq_timestamp {
-	snd_seq_tick_time_t tick;
-	struct snd_seq_real_time time;
-};
-
-struct snd_seq_queue_skew {
-	unsigned int value;
-	unsigned int base;
-};
-
-	/* queue timer control */
-struct snd_seq_ev_queue_control {
-	unsigned char queue;			/* affected queue */
-	unsigned char pad[3];			/* reserved */
-	union {
-		signed int value;		/* affected value (e.g. tempo) */
-		union snd_seq_timestamp time;	/* time */
-		unsigned int position;		/* sync position */
-		struct snd_seq_queue_skew skew;
-		unsigned int d32[2];
-		unsigned char d8[8];
-	} param;
-};
-
-	/* quoted event - inside the kernel only */
-struct snd_seq_ev_quote {
-	struct snd_seq_addr origin;		/* original sender */
-	unsigned short value;		/* optional data */
-	struct snd_seq_event *event;		/* quoted event */
-} __attribute__((packed));
-
-
-	/* sequencer event */
-struct snd_seq_event {
-	snd_seq_event_type_t type;	/* event type */
-	unsigned char flags;		/* event flags */
-	char tag;
-	
-	unsigned char queue;		/* schedule queue */
-	union snd_seq_timestamp time;	/* schedule time */
-
-
-	struct snd_seq_addr source;	/* source address */
-	struct snd_seq_addr dest;	/* destination address */
-
-	union {				/* event data... */
-		struct snd_seq_ev_note note;
-		struct snd_seq_ev_ctrl control;
-		struct snd_seq_ev_raw8 raw8;
-		struct snd_seq_ev_raw32 raw32;
-		struct snd_seq_ev_ext ext;
-		struct snd_seq_ev_queue_control queue;
-		union snd_seq_timestamp time;
-		struct snd_seq_addr addr;
-		struct snd_seq_connect connect;
-		struct snd_seq_result result;
-		struct snd_seq_ev_quote quote;
-	} data;
-};
-
-
-/*
- * bounce event - stored as variable size data
- */
-struct snd_seq_event_bounce {
-	int err;
-	struct snd_seq_event event;
-	/* external data follows here. */
-};
-
-#ifdef __KERNEL__
+#include <uapi/sound/asequencer.h>
 
 /* helper macro */
 #define snd_seq_event_bounce_ext_data(ev) ((void*)((char *)(ev)->data.ext.ptr + sizeof(struct snd_seq_event_bounce)))
@@ -368,311 +83,4 @@ struct snd_seq_event_bounce {
 /* queue sync port */
 #define snd_seq_queue_sync_port(q)	((q) + 16)
 
-#endif /* __KERNEL__ */
-
-	/* system information */
-struct snd_seq_system_info {
-	int queues;			/* maximum queues count */
-	int clients;			/* maximum clients count */
-	int ports;			/* maximum ports per client */
-	int channels;			/* maximum channels per port */
-	int cur_clients;		/* current clients */
-	int cur_queues;			/* current queues */
-	char reserved[24];
-};
-
-
-	/* system running information */
-struct snd_seq_running_info {
-	unsigned char client;		/* client id */
-	unsigned char big_endian;	/* 1 = big-endian */
-	unsigned char cpu_mode;		/* 4 = 32bit, 8 = 64bit */
-	unsigned char pad;		/* reserved */
-	unsigned char reserved[12];
-};
-
-
-	/* known client numbers */
-#define SNDRV_SEQ_CLIENT_SYSTEM		0
-	/* internal client numbers */
-#define SNDRV_SEQ_CLIENT_DUMMY		14	/* midi through */
-#define SNDRV_SEQ_CLIENT_OSS		15	/* oss sequencer emulator */
-
-
-	/* client types */
-typedef int __bitwise snd_seq_client_type_t;
-#define	NO_CLIENT	((__force snd_seq_client_type_t) 0)
-#define	USER_CLIENT	((__force snd_seq_client_type_t) 1)
-#define	KERNEL_CLIENT	((__force snd_seq_client_type_t) 2)
-                        
-	/* event filter flags */
-#define SNDRV_SEQ_FILTER_BROADCAST	(1<<0)	/* accept broadcast messages */
-#define SNDRV_SEQ_FILTER_MULTICAST	(1<<1)	/* accept multicast messages */
-#define SNDRV_SEQ_FILTER_BOUNCE		(1<<2)	/* accept bounce event in error */
-#define SNDRV_SEQ_FILTER_USE_EVENT	(1<<31)	/* use event filter */
-
-struct snd_seq_client_info {
-	int client;			/* client number to inquire */
-	snd_seq_client_type_t type;	/* client type */
-	char name[64];			/* client name */
-	unsigned int filter;		/* filter flags */
-	unsigned char multicast_filter[8]; /* multicast filter bitmap */
-	unsigned char event_filter[32];	/* event filter bitmap */
-	int num_ports;			/* RO: number of ports */
-	int event_lost;			/* number of lost events */
-	char reserved[64];		/* for future use */
-};
-
-
-/* client pool size */
-struct snd_seq_client_pool {
-	int client;			/* client number to inquire */
-	int output_pool;		/* outgoing (write) pool size */
-	int input_pool;			/* incoming (read) pool size */
-	int output_room;		/* minimum free pool size for select/blocking mode */
-	int output_free;		/* unused size */
-	int input_free;			/* unused size */
-	char reserved[64];
-};
-
-
-/* Remove events by specified criteria */
-
-#define SNDRV_SEQ_REMOVE_INPUT		(1<<0)	/* Flush input queues */
-#define SNDRV_SEQ_REMOVE_OUTPUT		(1<<1)	/* Flush output queues */
-#define SNDRV_SEQ_REMOVE_DEST		(1<<2)	/* Restrict by destination q:client:port */
-#define SNDRV_SEQ_REMOVE_DEST_CHANNEL	(1<<3)	/* Restrict by channel */
-#define SNDRV_SEQ_REMOVE_TIME_BEFORE	(1<<4)	/* Restrict to before time */
-#define SNDRV_SEQ_REMOVE_TIME_AFTER	(1<<5)	/* Restrict to time or after */
-#define SNDRV_SEQ_REMOVE_TIME_TICK	(1<<6)	/* Time is in ticks */
-#define SNDRV_SEQ_REMOVE_EVENT_TYPE	(1<<7)	/* Restrict to event type */
-#define SNDRV_SEQ_REMOVE_IGNORE_OFF 	(1<<8)	/* Do not flush off events */
-#define SNDRV_SEQ_REMOVE_TAG_MATCH 	(1<<9)	/* Restrict to events with given tag */
-
-struct snd_seq_remove_events {
-	unsigned int  remove_mode;	/* Flags that determine what gets removed */
-
-	union snd_seq_timestamp time;
-
-	unsigned char queue;	/* Queue for REMOVE_DEST */
-	struct snd_seq_addr dest;	/* Address for REMOVE_DEST */
-	unsigned char channel;	/* Channel for REMOVE_DEST */
-
-	int  type;	/* For REMOVE_EVENT_TYPE */
-	char  tag;	/* Tag for REMOVE_TAG */
-
-	int  reserved[10];	/* To allow for future binary compatibility */
-
-};
-
-
-	/* known port numbers */
-#define SNDRV_SEQ_PORT_SYSTEM_TIMER	0
-#define SNDRV_SEQ_PORT_SYSTEM_ANNOUNCE	1
-
-	/* port capabilities (32 bits) */
-#define SNDRV_SEQ_PORT_CAP_READ		(1<<0)	/* readable from this port */
-#define SNDRV_SEQ_PORT_CAP_WRITE	(1<<1)	/* writable to this port */
-
-#define SNDRV_SEQ_PORT_CAP_SYNC_READ	(1<<2)
-#define SNDRV_SEQ_PORT_CAP_SYNC_WRITE	(1<<3)
-
-#define SNDRV_SEQ_PORT_CAP_DUPLEX	(1<<4)
-
-#define SNDRV_SEQ_PORT_CAP_SUBS_READ	(1<<5)	/* allow read subscription */
-#define SNDRV_SEQ_PORT_CAP_SUBS_WRITE	(1<<6)	/* allow write subscription */
-#define SNDRV_SEQ_PORT_CAP_NO_EXPORT	(1<<7)	/* routing not allowed */
-
-	/* port type */
-#define SNDRV_SEQ_PORT_TYPE_SPECIFIC	(1<<0)	/* hardware specific */
-#define SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC (1<<1)	/* generic MIDI device */
-#define SNDRV_SEQ_PORT_TYPE_MIDI_GM	(1<<2)	/* General MIDI compatible device */
-#define SNDRV_SEQ_PORT_TYPE_MIDI_GS	(1<<3)	/* GS compatible device */
-#define SNDRV_SEQ_PORT_TYPE_MIDI_XG	(1<<4)	/* XG compatible device */
-#define SNDRV_SEQ_PORT_TYPE_MIDI_MT32	(1<<5)	/* MT-32 compatible device */
-#define SNDRV_SEQ_PORT_TYPE_MIDI_GM2	(1<<6)	/* General MIDI 2 compatible device */
-
-/* other standards...*/
-#define SNDRV_SEQ_PORT_TYPE_SYNTH	(1<<10)	/* Synth device (no MIDI compatible - direct wavetable) */
-#define SNDRV_SEQ_PORT_TYPE_DIRECT_SAMPLE (1<<11)	/* Sampling device (support sample download) */
-#define SNDRV_SEQ_PORT_TYPE_SAMPLE	(1<<12)	/* Sampling device (sample can be downloaded at any time) */
-/*...*/
-#define SNDRV_SEQ_PORT_TYPE_HARDWARE	(1<<16)	/* driver for a hardware device */
-#define SNDRV_SEQ_PORT_TYPE_SOFTWARE	(1<<17)	/* implemented in software */
-#define SNDRV_SEQ_PORT_TYPE_SYNTHESIZER	(1<<18)	/* generates sound */
-#define SNDRV_SEQ_PORT_TYPE_PORT	(1<<19)	/* connects to other device(s) */
-#define SNDRV_SEQ_PORT_TYPE_APPLICATION	(1<<20)	/* application (sequencer/editor) */
-
-/* misc. conditioning flags */
-#define SNDRV_SEQ_PORT_FLG_GIVEN_PORT	(1<<0)
-#define SNDRV_SEQ_PORT_FLG_TIMESTAMP	(1<<1)
-#define SNDRV_SEQ_PORT_FLG_TIME_REAL	(1<<2)
-
-struct snd_seq_port_info {
-	struct snd_seq_addr addr;	/* client/port numbers */
-	char name[64];			/* port name */
-
-	unsigned int capability;	/* port capability bits */
-	unsigned int type;		/* port type bits */
-	int midi_channels;		/* channels per MIDI port */
-	int midi_voices;		/* voices per MIDI port */
-	int synth_voices;		/* voices per SYNTH port */
-
-	int read_use;			/* R/O: subscribers for output (from this port) */
-	int write_use;			/* R/O: subscribers for input (to this port) */
-
-	void *kernel;			/* reserved for kernel use (must be NULL) */
-	unsigned int flags;		/* misc. conditioning */
-	unsigned char time_queue;	/* queue # for timestamping */
-	char reserved[59];		/* for future use */
-};
-
-
-/* queue flags */
-#define SNDRV_SEQ_QUEUE_FLG_SYNC	(1<<0)	/* sync enabled */
-
-/* queue information */
-struct snd_seq_queue_info {
-	int queue;		/* queue id */
-
-	/*
-	 *  security settings, only owner of this queue can start/stop timer
-	 *  etc. if the queue is locked for other clients
-	 */
-	int owner;		/* client id for owner of the queue */
-	unsigned locked:1;	/* timing queue locked for other queues */
-	char name[64];		/* name of this queue */
-	unsigned int flags;	/* flags */
-	char reserved[60];	/* for future use */
-
-};
-
-/* queue info/status */
-struct snd_seq_queue_status {
-	int queue;			/* queue id */
-	int events;			/* read-only - queue size */
-	snd_seq_tick_time_t tick;	/* current tick */
-	struct snd_seq_real_time time;	/* current time */
-	int running;			/* running state of queue */
-	int flags;			/* various flags */
-	char reserved[64];		/* for the future */
-};
-
-
-/* queue tempo */
-struct snd_seq_queue_tempo {
-	int queue;			/* sequencer queue */
-	unsigned int tempo;		/* current tempo, us/tick */
-	int ppq;			/* time resolution, ticks/quarter */
-	unsigned int skew_value;	/* queue skew */
-	unsigned int skew_base;		/* queue skew base */
-	char reserved[24];		/* for the future */
-};
-
-
-/* sequencer timer sources */
-#define SNDRV_SEQ_TIMER_ALSA		0	/* ALSA timer */
-#define SNDRV_SEQ_TIMER_MIDI_CLOCK	1	/* Midi Clock (CLOCK event) */
-#define SNDRV_SEQ_TIMER_MIDI_TICK	2	/* Midi Timer Tick (TICK event) */
-
-/* queue timer info */
-struct snd_seq_queue_timer {
-	int queue;			/* sequencer queue */
-	int type;			/* source timer type */
-	union {
-		struct {
-			struct snd_timer_id id;	/* ALSA's timer ID */
-			unsigned int resolution;	/* resolution in Hz */
-		} alsa;
-	} u;
-	char reserved[64];		/* for the future use */
-};
-
-
-struct snd_seq_queue_client {
-	int queue;		/* sequencer queue */
-	int client;		/* sequencer client */
-	int used;		/* queue is used with this client
-				   (must be set for accepting events) */
-	/* per client watermarks */
-	char reserved[64];	/* for future use */
-};
-
-
-#define SNDRV_SEQ_PORT_SUBS_EXCLUSIVE	(1<<0)	/* exclusive connection */
-#define SNDRV_SEQ_PORT_SUBS_TIMESTAMP	(1<<1)
-#define SNDRV_SEQ_PORT_SUBS_TIME_REAL	(1<<2)
-
-struct snd_seq_port_subscribe {
-	struct snd_seq_addr sender;	/* sender address */
-	struct snd_seq_addr dest;	/* destination address */
-	unsigned int voices;		/* number of voices to be allocated (0 = don't care) */
-	unsigned int flags;		/* modes */
-	unsigned char queue;		/* input time-stamp queue (optional) */
-	unsigned char pad[3];		/* reserved */
-	char reserved[64];
-};
-
-/* type of query subscription */
-#define SNDRV_SEQ_QUERY_SUBS_READ	0
-#define SNDRV_SEQ_QUERY_SUBS_WRITE	1
-
-struct snd_seq_query_subs {
-	struct snd_seq_addr root;	/* client/port id to be searched */
-	int type;		/* READ or WRITE */
-	int index;		/* 0..N-1 */
-	int num_subs;		/* R/O: number of subscriptions on this port */
-	struct snd_seq_addr addr;	/* R/O: result */
-	unsigned char queue;	/* R/O: result */
-	unsigned int flags;	/* R/O: result */
-	char reserved[64];	/* for future use */
-};
-
-
-/*
- *  IOCTL commands
- */
-
-#define SNDRV_SEQ_IOCTL_PVERSION	_IOR ('S', 0x00, int)
-#define SNDRV_SEQ_IOCTL_CLIENT_ID	_IOR ('S', 0x01, int)
-#define SNDRV_SEQ_IOCTL_SYSTEM_INFO	_IOWR('S', 0x02, struct snd_seq_system_info)
-#define SNDRV_SEQ_IOCTL_RUNNING_MODE	_IOWR('S', 0x03, struct snd_seq_running_info)
-
-#define SNDRV_SEQ_IOCTL_GET_CLIENT_INFO	_IOWR('S', 0x10, struct snd_seq_client_info)
-#define SNDRV_SEQ_IOCTL_SET_CLIENT_INFO	_IOW ('S', 0x11, struct snd_seq_client_info)
-
-#define SNDRV_SEQ_IOCTL_CREATE_PORT	_IOWR('S', 0x20, struct snd_seq_port_info)
-#define SNDRV_SEQ_IOCTL_DELETE_PORT	_IOW ('S', 0x21, struct snd_seq_port_info)
-#define SNDRV_SEQ_IOCTL_GET_PORT_INFO	_IOWR('S', 0x22, struct snd_seq_port_info)
-#define SNDRV_SEQ_IOCTL_SET_PORT_INFO	_IOW ('S', 0x23, struct snd_seq_port_info)
-
-#define SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT	_IOW ('S', 0x30, struct snd_seq_port_subscribe)
-#define SNDRV_SEQ_IOCTL_UNSUBSCRIBE_PORT _IOW ('S', 0x31, struct snd_seq_port_subscribe)
-
-#define SNDRV_SEQ_IOCTL_CREATE_QUEUE	_IOWR('S', 0x32, struct snd_seq_queue_info)
-#define SNDRV_SEQ_IOCTL_DELETE_QUEUE	_IOW ('S', 0x33, struct snd_seq_queue_info)
-#define SNDRV_SEQ_IOCTL_GET_QUEUE_INFO	_IOWR('S', 0x34, struct snd_seq_queue_info)
-#define SNDRV_SEQ_IOCTL_SET_QUEUE_INFO	_IOWR('S', 0x35, struct snd_seq_queue_info)
-#define SNDRV_SEQ_IOCTL_GET_NAMED_QUEUE	_IOWR('S', 0x36, struct snd_seq_queue_info)
-#define SNDRV_SEQ_IOCTL_GET_QUEUE_STATUS _IOWR('S', 0x40, struct snd_seq_queue_status)
-#define SNDRV_SEQ_IOCTL_GET_QUEUE_TEMPO	_IOWR('S', 0x41, struct snd_seq_queue_tempo)
-#define SNDRV_SEQ_IOCTL_SET_QUEUE_TEMPO	_IOW ('S', 0x42, struct snd_seq_queue_tempo)
-#define SNDRV_SEQ_IOCTL_GET_QUEUE_OWNER	_IOWR('S', 0x43, struct snd_seq_queue_owner)
-#define SNDRV_SEQ_IOCTL_SET_QUEUE_OWNER	_IOW ('S', 0x44, struct snd_seq_queue_owner)
-#define SNDRV_SEQ_IOCTL_GET_QUEUE_TIMER	_IOWR('S', 0x45, struct snd_seq_queue_timer)
-#define SNDRV_SEQ_IOCTL_SET_QUEUE_TIMER	_IOW ('S', 0x46, struct snd_seq_queue_timer)
-/* XXX
-#define SNDRV_SEQ_IOCTL_GET_QUEUE_SYNC	_IOWR('S', 0x53, struct snd_seq_queue_sync)
-#define SNDRV_SEQ_IOCTL_SET_QUEUE_SYNC	_IOW ('S', 0x54, struct snd_seq_queue_sync)
-*/
-#define SNDRV_SEQ_IOCTL_GET_QUEUE_CLIENT	_IOWR('S', 0x49, struct snd_seq_queue_client)
-#define SNDRV_SEQ_IOCTL_SET_QUEUE_CLIENT	_IOW ('S', 0x4a, struct snd_seq_queue_client)
-#define SNDRV_SEQ_IOCTL_GET_CLIENT_POOL	_IOWR('S', 0x4b, struct snd_seq_client_pool)
-#define SNDRV_SEQ_IOCTL_SET_CLIENT_POOL	_IOW ('S', 0x4c, struct snd_seq_client_pool)
-#define SNDRV_SEQ_IOCTL_REMOVE_EVENTS	_IOW ('S', 0x4e, struct snd_seq_remove_events)
-#define SNDRV_SEQ_IOCTL_QUERY_SUBS	_IOWR('S', 0x4f, struct snd_seq_query_subs)
-#define SNDRV_SEQ_IOCTL_GET_SUBSCRIPTION	_IOWR('S', 0x50, struct snd_seq_port_subscribe)
-#define SNDRV_SEQ_IOCTL_QUERY_NEXT_CLIENT	_IOWR('S', 0x51, struct snd_seq_client_info)
-#define SNDRV_SEQ_IOCTL_QUERY_NEXT_PORT	_IOWR('S', 0x52, struct snd_seq_port_info)
-
 #endif /* __SOUND_ASEQUENCER_H */
diff --git a/include/sound/asound.h b/include/sound/asound.h
index dfe7d441748c..c2dff5369d33 100644
--- a/include/sound/asound.h
+++ b/include/sound/asound.h
@@ -19,13 +19,9 @@
  *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  *
  */
-
 #ifndef __SOUND_ASOUND_H
 #define __SOUND_ASOUND_H
 
-#include <linux/types.h>
-
-#ifdef __KERNEL__
 #include <linux/ioctl.h>
 #include <linux/time.h>
 #include <asm/byteorder.h>
@@ -40,934 +36,5 @@
 #endif
 #endif
 
-#endif /* __KERNEL__ **/
-
-/*
- *  protocol version
- */
-
-#define SNDRV_PROTOCOL_VERSION(major, minor, subminor) (((major)<<16)|((minor)<<8)|(subminor))
-#define SNDRV_PROTOCOL_MAJOR(version) (((version)>>16)&0xffff)
-#define SNDRV_PROTOCOL_MINOR(version) (((version)>>8)&0xff)
-#define SNDRV_PROTOCOL_MICRO(version) ((version)&0xff)
-#define SNDRV_PROTOCOL_INCOMPATIBLE(kversion, uversion) \
-	(SNDRV_PROTOCOL_MAJOR(kversion) != SNDRV_PROTOCOL_MAJOR(uversion) || \
-	 (SNDRV_PROTOCOL_MAJOR(kversion) == SNDRV_PROTOCOL_MAJOR(uversion) && \
-	   SNDRV_PROTOCOL_MINOR(kversion) != SNDRV_PROTOCOL_MINOR(uversion)))
-
-/****************************************************************************
- *                                                                          *
- *        Digital audio interface					    *
- *                                                                          *
- ****************************************************************************/
-
-struct snd_aes_iec958 {
-	unsigned char status[24];	/* AES/IEC958 channel status bits */
-	unsigned char subcode[147];	/* AES/IEC958 subcode bits */
-	unsigned char pad;		/* nothing */
-	unsigned char dig_subframe[4];	/* AES/IEC958 subframe bits */
-};
-
-/****************************************************************************
- *                                                                          *
- *        CEA-861 Audio InfoFrame. Used in HDMI and DisplayPort		    *
- *                                                                          *
- ****************************************************************************/
-
-struct snd_cea_861_aud_if {
-	unsigned char db1_ct_cc; /* coding type and channel count */
-	unsigned char db2_sf_ss; /* sample frequency and size */
-	unsigned char db3; /* not used, all zeros */
-	unsigned char db4_ca; /* channel allocation code */
-	unsigned char db5_dminh_lsv; /* downmix inhibit & level-shit values */
-};
-
-/****************************************************************************
- *                                                                          *
- *      Section for driver hardware dependent interface - /dev/snd/hw?      *
- *                                                                          *
- ****************************************************************************/
-
-#define SNDRV_HWDEP_VERSION		SNDRV_PROTOCOL_VERSION(1, 0, 1)
-
-enum {
-	SNDRV_HWDEP_IFACE_OPL2 = 0,
-	SNDRV_HWDEP_IFACE_OPL3,
-	SNDRV_HWDEP_IFACE_OPL4,
-	SNDRV_HWDEP_IFACE_SB16CSP,	/* Creative Signal Processor */
-	SNDRV_HWDEP_IFACE_EMU10K1,	/* FX8010 processor in EMU10K1 chip */
-	SNDRV_HWDEP_IFACE_YSS225,	/* Yamaha FX processor */
-	SNDRV_HWDEP_IFACE_ICS2115,	/* Wavetable synth */
-	SNDRV_HWDEP_IFACE_SSCAPE,	/* Ensoniq SoundScape ISA card (MC68EC000) */
-	SNDRV_HWDEP_IFACE_VX,		/* Digigram VX cards */
-	SNDRV_HWDEP_IFACE_MIXART,	/* Digigram miXart cards */
-	SNDRV_HWDEP_IFACE_USX2Y,	/* Tascam US122, US224 & US428 usb */
-	SNDRV_HWDEP_IFACE_EMUX_WAVETABLE, /* EmuX wavetable */	
-	SNDRV_HWDEP_IFACE_BLUETOOTH,	/* Bluetooth audio */
-	SNDRV_HWDEP_IFACE_USX2Y_PCM,	/* Tascam US122, US224 & US428 rawusb pcm */
-	SNDRV_HWDEP_IFACE_PCXHR,	/* Digigram PCXHR */
-	SNDRV_HWDEP_IFACE_SB_RC,	/* SB Extigy/Audigy2NX remote control */
-	SNDRV_HWDEP_IFACE_HDA,		/* HD-audio */
-	SNDRV_HWDEP_IFACE_USB_STREAM,	/* direct access to usb stream */
-
-	/* Don't forget to change the following: */
-	SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_USB_STREAM
-};
-
-struct snd_hwdep_info {
-	unsigned int device;		/* WR: device number */
-	int card;			/* R: card number */
-	unsigned char id[64];		/* ID (user selectable) */
-	unsigned char name[80];		/* hwdep name */
-	int iface;			/* hwdep interface */
-	unsigned char reserved[64];	/* reserved for future */
-};
-
-/* generic DSP loader */
-struct snd_hwdep_dsp_status {
-	unsigned int version;		/* R: driver-specific version */
-	unsigned char id[32];		/* R: driver-specific ID string */
-	unsigned int num_dsps;		/* R: number of DSP images to transfer */
-	unsigned int dsp_loaded;	/* R: bit flags indicating the loaded DSPs */
-	unsigned int chip_ready;	/* R: 1 = initialization finished */
-	unsigned char reserved[16];	/* reserved for future use */
-};
-
-struct snd_hwdep_dsp_image {
-	unsigned int index;		/* W: DSP index */
-	unsigned char name[64];		/* W: ID (e.g. file name) */
-	unsigned char __user *image;	/* W: binary image */
-	size_t length;			/* W: size of image in bytes */
-	unsigned long driver_data;	/* W: driver-specific data */
-};
-
-#define SNDRV_HWDEP_IOCTL_PVERSION	_IOR ('H', 0x00, int)
-#define SNDRV_HWDEP_IOCTL_INFO		_IOR ('H', 0x01, struct snd_hwdep_info)
-#define SNDRV_HWDEP_IOCTL_DSP_STATUS	_IOR('H', 0x02, struct snd_hwdep_dsp_status)
-#define SNDRV_HWDEP_IOCTL_DSP_LOAD	_IOW('H', 0x03, struct snd_hwdep_dsp_image)
-
-/*****************************************************************************
- *                                                                           *
- *             Digital Audio (PCM) interface - /dev/snd/pcm??                *
- *                                                                           *
- *****************************************************************************/
-
-#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 10)
-
-typedef unsigned long snd_pcm_uframes_t;
-typedef signed long snd_pcm_sframes_t;
-
-enum {
-	SNDRV_PCM_CLASS_GENERIC = 0,	/* standard mono or stereo device */
-	SNDRV_PCM_CLASS_MULTI,		/* multichannel device */
-	SNDRV_PCM_CLASS_MODEM,		/* software modem class */
-	SNDRV_PCM_CLASS_DIGITIZER,	/* digitizer class */
-	/* Don't forget to change the following: */
-	SNDRV_PCM_CLASS_LAST = SNDRV_PCM_CLASS_DIGITIZER,
-};
-
-enum {
-	SNDRV_PCM_SUBCLASS_GENERIC_MIX = 0, /* mono or stereo subdevices are mixed together */
-	SNDRV_PCM_SUBCLASS_MULTI_MIX,	/* multichannel subdevices are mixed together */
-	/* Don't forget to change the following: */
-	SNDRV_PCM_SUBCLASS_LAST = SNDRV_PCM_SUBCLASS_MULTI_MIX,
-};
-
-enum {
-	SNDRV_PCM_STREAM_PLAYBACK = 0,
-	SNDRV_PCM_STREAM_CAPTURE,
-	SNDRV_PCM_STREAM_LAST = SNDRV_PCM_STREAM_CAPTURE,
-};
-
-typedef int __bitwise snd_pcm_access_t;
-#define	SNDRV_PCM_ACCESS_MMAP_INTERLEAVED	((__force snd_pcm_access_t) 0) /* interleaved mmap */
-#define	SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED	((__force snd_pcm_access_t) 1) /* noninterleaved mmap */
-#define	SNDRV_PCM_ACCESS_MMAP_COMPLEX		((__force snd_pcm_access_t) 2) /* complex mmap */
-#define	SNDRV_PCM_ACCESS_RW_INTERLEAVED		((__force snd_pcm_access_t) 3) /* readi/writei */
-#define	SNDRV_PCM_ACCESS_RW_NONINTERLEAVED	((__force snd_pcm_access_t) 4) /* readn/writen */
-#define	SNDRV_PCM_ACCESS_LAST		SNDRV_PCM_ACCESS_RW_NONINTERLEAVED
-
-typedef int __bitwise snd_pcm_format_t;
-#define	SNDRV_PCM_FORMAT_S8	((__force snd_pcm_format_t) 0)
-#define	SNDRV_PCM_FORMAT_U8	((__force snd_pcm_format_t) 1)
-#define	SNDRV_PCM_FORMAT_S16_LE	((__force snd_pcm_format_t) 2)
-#define	SNDRV_PCM_FORMAT_S16_BE	((__force snd_pcm_format_t) 3)
-#define	SNDRV_PCM_FORMAT_U16_LE	((__force snd_pcm_format_t) 4)
-#define	SNDRV_PCM_FORMAT_U16_BE	((__force snd_pcm_format_t) 5)
-#define	SNDRV_PCM_FORMAT_S24_LE	((__force snd_pcm_format_t) 6) /* low three bytes */
-#define	SNDRV_PCM_FORMAT_S24_BE	((__force snd_pcm_format_t) 7) /* low three bytes */
-#define	SNDRV_PCM_FORMAT_U24_LE	((__force snd_pcm_format_t) 8) /* low three bytes */
-#define	SNDRV_PCM_FORMAT_U24_BE	((__force snd_pcm_format_t) 9) /* low three bytes */
-#define	SNDRV_PCM_FORMAT_S32_LE	((__force snd_pcm_format_t) 10)
-#define	SNDRV_PCM_FORMAT_S32_BE	((__force snd_pcm_format_t) 11)
-#define	SNDRV_PCM_FORMAT_U32_LE	((__force snd_pcm_format_t) 12)
-#define	SNDRV_PCM_FORMAT_U32_BE	((__force snd_pcm_format_t) 13)
-#define	SNDRV_PCM_FORMAT_FLOAT_LE	((__force snd_pcm_format_t) 14) /* 4-byte float, IEEE-754 32-bit, range -1.0 to 1.0 */
-#define	SNDRV_PCM_FORMAT_FLOAT_BE	((__force snd_pcm_format_t) 15) /* 4-byte float, IEEE-754 32-bit, range -1.0 to 1.0 */
-#define	SNDRV_PCM_FORMAT_FLOAT64_LE	((__force snd_pcm_format_t) 16) /* 8-byte float, IEEE-754 64-bit, range -1.0 to 1.0 */
-#define	SNDRV_PCM_FORMAT_FLOAT64_BE	((__force snd_pcm_format_t) 17) /* 8-byte float, IEEE-754 64-bit, range -1.0 to 1.0 */
-#define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE ((__force snd_pcm_format_t) 18) /* IEC-958 subframe, Little Endian */
-#define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE ((__force snd_pcm_format_t) 19) /* IEC-958 subframe, Big Endian */
-#define	SNDRV_PCM_FORMAT_MU_LAW		((__force snd_pcm_format_t) 20)
-#define	SNDRV_PCM_FORMAT_A_LAW		((__force snd_pcm_format_t) 21)
-#define	SNDRV_PCM_FORMAT_IMA_ADPCM	((__force snd_pcm_format_t) 22)
-#define	SNDRV_PCM_FORMAT_MPEG		((__force snd_pcm_format_t) 23)
-#define	SNDRV_PCM_FORMAT_GSM		((__force snd_pcm_format_t) 24)
-#define	SNDRV_PCM_FORMAT_SPECIAL	((__force snd_pcm_format_t) 31)
-#define	SNDRV_PCM_FORMAT_S24_3LE	((__force snd_pcm_format_t) 32)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_S24_3BE	((__force snd_pcm_format_t) 33)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_U24_3LE	((__force snd_pcm_format_t) 34)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_U24_3BE	((__force snd_pcm_format_t) 35)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_S20_3LE	((__force snd_pcm_format_t) 36)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_S20_3BE	((__force snd_pcm_format_t) 37)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_U20_3LE	((__force snd_pcm_format_t) 38)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_U20_3BE	((__force snd_pcm_format_t) 39)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_S18_3LE	((__force snd_pcm_format_t) 40)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_S18_3BE	((__force snd_pcm_format_t) 41)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_U18_3LE	((__force snd_pcm_format_t) 42)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_U18_3BE	((__force snd_pcm_format_t) 43)	/* in three bytes */
-#define	SNDRV_PCM_FORMAT_G723_24	((__force snd_pcm_format_t) 44) /* 8 samples in 3 bytes */
-#define	SNDRV_PCM_FORMAT_G723_24_1B	((__force snd_pcm_format_t) 45) /* 1 sample in 1 byte */
-#define	SNDRV_PCM_FORMAT_G723_40	((__force snd_pcm_format_t) 46) /* 8 Samples in 5 bytes */
-#define	SNDRV_PCM_FORMAT_G723_40_1B	((__force snd_pcm_format_t) 47) /* 1 sample in 1 byte */
-#define	SNDRV_PCM_FORMAT_LAST		SNDRV_PCM_FORMAT_G723_40_1B
-
-#ifdef SNDRV_LITTLE_ENDIAN
-#define	SNDRV_PCM_FORMAT_S16		SNDRV_PCM_FORMAT_S16_LE
-#define	SNDRV_PCM_FORMAT_U16		SNDRV_PCM_FORMAT_U16_LE
-#define	SNDRV_PCM_FORMAT_S24		SNDRV_PCM_FORMAT_S24_LE
-#define	SNDRV_PCM_FORMAT_U24		SNDRV_PCM_FORMAT_U24_LE
-#define	SNDRV_PCM_FORMAT_S32		SNDRV_PCM_FORMAT_S32_LE
-#define	SNDRV_PCM_FORMAT_U32		SNDRV_PCM_FORMAT_U32_LE
-#define	SNDRV_PCM_FORMAT_FLOAT		SNDRV_PCM_FORMAT_FLOAT_LE
-#define	SNDRV_PCM_FORMAT_FLOAT64	SNDRV_PCM_FORMAT_FLOAT64_LE
-#define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE
-#endif
-#ifdef SNDRV_BIG_ENDIAN
-#define	SNDRV_PCM_FORMAT_S16		SNDRV_PCM_FORMAT_S16_BE
-#define	SNDRV_PCM_FORMAT_U16		SNDRV_PCM_FORMAT_U16_BE
-#define	SNDRV_PCM_FORMAT_S24		SNDRV_PCM_FORMAT_S24_BE
-#define	SNDRV_PCM_FORMAT_U24		SNDRV_PCM_FORMAT_U24_BE
-#define	SNDRV_PCM_FORMAT_S32		SNDRV_PCM_FORMAT_S32_BE
-#define	SNDRV_PCM_FORMAT_U32		SNDRV_PCM_FORMAT_U32_BE
-#define	SNDRV_PCM_FORMAT_FLOAT		SNDRV_PCM_FORMAT_FLOAT_BE
-#define	SNDRV_PCM_FORMAT_FLOAT64	SNDRV_PCM_FORMAT_FLOAT64_BE
-#define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE
-#endif
-
-typedef int __bitwise snd_pcm_subformat_t;
-#define	SNDRV_PCM_SUBFORMAT_STD		((__force snd_pcm_subformat_t) 0)
-#define	SNDRV_PCM_SUBFORMAT_LAST	SNDRV_PCM_SUBFORMAT_STD
-
-#define SNDRV_PCM_INFO_MMAP		0x00000001	/* hardware supports mmap */
-#define SNDRV_PCM_INFO_MMAP_VALID	0x00000002	/* period data are valid during transfer */
-#define SNDRV_PCM_INFO_DOUBLE		0x00000004	/* Double buffering needed for PCM start/stop */
-#define SNDRV_PCM_INFO_BATCH		0x00000010	/* double buffering */
-#define SNDRV_PCM_INFO_INTERLEAVED	0x00000100	/* channels are interleaved */
-#define SNDRV_PCM_INFO_NONINTERLEAVED	0x00000200	/* channels are not interleaved */
-#define SNDRV_PCM_INFO_COMPLEX		0x00000400	/* complex frame organization (mmap only) */
-#define SNDRV_PCM_INFO_BLOCK_TRANSFER	0x00010000	/* hardware transfer block of samples */
-#define SNDRV_PCM_INFO_OVERRANGE	0x00020000	/* hardware supports ADC (capture) overrange detection */
-#define SNDRV_PCM_INFO_RESUME		0x00040000	/* hardware supports stream resume after suspend */
-#define SNDRV_PCM_INFO_PAUSE		0x00080000	/* pause ioctl is supported */
-#define SNDRV_PCM_INFO_HALF_DUPLEX	0x00100000	/* only half duplex */
-#define SNDRV_PCM_INFO_JOINT_DUPLEX	0x00200000	/* playback and capture stream are somewhat correlated */
-#define SNDRV_PCM_INFO_SYNC_START	0x00400000	/* pcm support some kind of sync go */
-#define SNDRV_PCM_INFO_NO_PERIOD_WAKEUP	0x00800000	/* period wakeup can be disabled */
-#define SNDRV_PCM_INFO_FIFO_IN_FRAMES	0x80000000	/* internal kernel flag - FIFO size is in frames */
-
-typedef int __bitwise snd_pcm_state_t;
-#define	SNDRV_PCM_STATE_OPEN		((__force snd_pcm_state_t) 0) /* stream is open */
-#define	SNDRV_PCM_STATE_SETUP		((__force snd_pcm_state_t) 1) /* stream has a setup */
-#define	SNDRV_PCM_STATE_PREPARED	((__force snd_pcm_state_t) 2) /* stream is ready to start */
-#define	SNDRV_PCM_STATE_RUNNING		((__force snd_pcm_state_t) 3) /* stream is running */
-#define	SNDRV_PCM_STATE_XRUN		((__force snd_pcm_state_t) 4) /* stream reached an xrun */
-#define	SNDRV_PCM_STATE_DRAINING	((__force snd_pcm_state_t) 5) /* stream is draining */
-#define	SNDRV_PCM_STATE_PAUSED		((__force snd_pcm_state_t) 6) /* stream is paused */
-#define	SNDRV_PCM_STATE_SUSPENDED	((__force snd_pcm_state_t) 7) /* hardware is suspended */
-#define	SNDRV_PCM_STATE_DISCONNECTED	((__force snd_pcm_state_t) 8) /* hardware is disconnected */
-#define	SNDRV_PCM_STATE_LAST		SNDRV_PCM_STATE_DISCONNECTED
-
-enum {
-	SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000,
-	SNDRV_PCM_MMAP_OFFSET_STATUS = 0x80000000,
-	SNDRV_PCM_MMAP_OFFSET_CONTROL = 0x81000000,
-};
-
-union snd_pcm_sync_id {
-	unsigned char id[16];
-	unsigned short id16[8];
-	unsigned int id32[4];
-};
-
-struct snd_pcm_info {
-	unsigned int device;		/* RO/WR (control): device number */
-	unsigned int subdevice;		/* RO/WR (control): subdevice number */
-	int stream;			/* RO/WR (control): stream direction */
-	int card;			/* R: card number */
-	unsigned char id[64];		/* ID (user selectable) */
-	unsigned char name[80];		/* name of this device */
-	unsigned char subname[32];	/* subdevice name */
-	int dev_class;			/* SNDRV_PCM_CLASS_* */
-	int dev_subclass;		/* SNDRV_PCM_SUBCLASS_* */
-	unsigned int subdevices_count;
-	unsigned int subdevices_avail;
-	union snd_pcm_sync_id sync;	/* hardware synchronization ID */
-	unsigned char reserved[64];	/* reserved for future... */
-};
-
-typedef int snd_pcm_hw_param_t;
-#define	SNDRV_PCM_HW_PARAM_ACCESS	0	/* Access type */
-#define	SNDRV_PCM_HW_PARAM_FORMAT	1	/* Format */
-#define	SNDRV_PCM_HW_PARAM_SUBFORMAT	2	/* Subformat */
-#define	SNDRV_PCM_HW_PARAM_FIRST_MASK	SNDRV_PCM_HW_PARAM_ACCESS
-#define	SNDRV_PCM_HW_PARAM_LAST_MASK	SNDRV_PCM_HW_PARAM_SUBFORMAT
-
-#define	SNDRV_PCM_HW_PARAM_SAMPLE_BITS	8	/* Bits per sample */
-#define	SNDRV_PCM_HW_PARAM_FRAME_BITS	9	/* Bits per frame */
-#define	SNDRV_PCM_HW_PARAM_CHANNELS	10	/* Channels */
-#define	SNDRV_PCM_HW_PARAM_RATE		11	/* Approx rate */
-#define	SNDRV_PCM_HW_PARAM_PERIOD_TIME	12	/* Approx distance between
-						 * interrupts in us
-						 */
-#define	SNDRV_PCM_HW_PARAM_PERIOD_SIZE	13	/* Approx frames between
-						 * interrupts
-						 */
-#define	SNDRV_PCM_HW_PARAM_PERIOD_BYTES	14	/* Approx bytes between
-						 * interrupts
-						 */
-#define	SNDRV_PCM_HW_PARAM_PERIODS	15	/* Approx interrupts per
-						 * buffer
-						 */
-#define	SNDRV_PCM_HW_PARAM_BUFFER_TIME	16	/* Approx duration of buffer
-						 * in us
-						 */
-#define	SNDRV_PCM_HW_PARAM_BUFFER_SIZE	17	/* Size of buffer in frames */
-#define	SNDRV_PCM_HW_PARAM_BUFFER_BYTES	18	/* Size of buffer in bytes */
-#define	SNDRV_PCM_HW_PARAM_TICK_TIME	19	/* Approx tick duration in us */
-#define	SNDRV_PCM_HW_PARAM_FIRST_INTERVAL	SNDRV_PCM_HW_PARAM_SAMPLE_BITS
-#define	SNDRV_PCM_HW_PARAM_LAST_INTERVAL	SNDRV_PCM_HW_PARAM_TICK_TIME
-
-#define SNDRV_PCM_HW_PARAMS_NORESAMPLE	(1<<0)	/* avoid rate resampling */
-#define SNDRV_PCM_HW_PARAMS_EXPORT_BUFFER	(1<<1)	/* export buffer */
-#define SNDRV_PCM_HW_PARAMS_NO_PERIOD_WAKEUP	(1<<2)	/* disable period wakeups */
-
-struct snd_interval {
-	unsigned int min, max;
-	unsigned int openmin:1,
-		     openmax:1,
-		     integer:1,
-		     empty:1;
-};
-
-#define SNDRV_MASK_MAX	256
-
-struct snd_mask {
-	__u32 bits[(SNDRV_MASK_MAX+31)/32];
-};
-
-struct snd_pcm_hw_params {
-	unsigned int flags;
-	struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK - 
-			       SNDRV_PCM_HW_PARAM_FIRST_MASK + 1];
-	struct snd_mask mres[5];	/* reserved masks */
-	struct snd_interval intervals[SNDRV_PCM_HW_PARAM_LAST_INTERVAL -
-				        SNDRV_PCM_HW_PARAM_FIRST_INTERVAL + 1];
-	struct snd_interval ires[9];	/* reserved intervals */
-	unsigned int rmask;		/* W: requested masks */
-	unsigned int cmask;		/* R: changed masks */
-	unsigned int info;		/* R: Info flags for returned setup */
-	unsigned int msbits;		/* R: used most significant bits */
-	unsigned int rate_num;		/* R: rate numerator */
-	unsigned int rate_den;		/* R: rate denominator */
-	snd_pcm_uframes_t fifo_size;	/* R: chip FIFO size in frames */
-	unsigned char reserved[64];	/* reserved for future */
-};
-
-enum {
-	SNDRV_PCM_TSTAMP_NONE = 0,
-	SNDRV_PCM_TSTAMP_ENABLE,
-	SNDRV_PCM_TSTAMP_LAST = SNDRV_PCM_TSTAMP_ENABLE,
-};
-
-struct snd_pcm_sw_params {
-	int tstamp_mode;			/* timestamp mode */
-	unsigned int period_step;
-	unsigned int sleep_min;			/* min ticks to sleep */
-	snd_pcm_uframes_t avail_min;		/* min avail frames for wakeup */
-	snd_pcm_uframes_t xfer_align;		/* obsolete: xfer size need to be a multiple */
-	snd_pcm_uframes_t start_threshold;	/* min hw_avail frames for automatic start */
-	snd_pcm_uframes_t stop_threshold;	/* min avail frames for automatic stop */
-	snd_pcm_uframes_t silence_threshold;	/* min distance from noise for silence filling */
-	snd_pcm_uframes_t silence_size;		/* silence block size */
-	snd_pcm_uframes_t boundary;		/* pointers wrap point */
-	unsigned char reserved[64];		/* reserved for future */
-};
-
-struct snd_pcm_channel_info {
-	unsigned int channel;
-	__kernel_off_t offset;		/* mmap offset */
-	unsigned int first;		/* offset to first sample in bits */
-	unsigned int step;		/* samples distance in bits */
-};
-
-struct snd_pcm_status {
-	snd_pcm_state_t state;		/* stream state */
-	struct timespec trigger_tstamp;	/* time when stream was started/stopped/paused */
-	struct timespec tstamp;		/* reference timestamp */
-	snd_pcm_uframes_t appl_ptr;	/* appl ptr */
-	snd_pcm_uframes_t hw_ptr;	/* hw ptr */
-	snd_pcm_sframes_t delay;	/* current delay in frames */
-	snd_pcm_uframes_t avail;	/* number of frames available */
-	snd_pcm_uframes_t avail_max;	/* max frames available on hw since last status */
-	snd_pcm_uframes_t overrange;	/* count of ADC (capture) overrange detections from last status */
-	snd_pcm_state_t suspended_state; /* suspended stream state */
-	unsigned char reserved[60];	/* must be filled with zero */
-};
-
-struct snd_pcm_mmap_status {
-	snd_pcm_state_t state;		/* RO: state - SNDRV_PCM_STATE_XXXX */
-	int pad1;			/* Needed for 64 bit alignment */
-	snd_pcm_uframes_t hw_ptr;	/* RO: hw ptr (0...boundary-1) */
-	struct timespec tstamp;		/* Timestamp */
-	snd_pcm_state_t suspended_state; /* RO: suspended stream state */
-};
-
-struct snd_pcm_mmap_control {
-	snd_pcm_uframes_t appl_ptr;	/* RW: appl ptr (0...boundary-1) */
-	snd_pcm_uframes_t avail_min;	/* RW: min available frames for wakeup */
-};
-
-#define SNDRV_PCM_SYNC_PTR_HWSYNC	(1<<0)	/* execute hwsync */
-#define SNDRV_PCM_SYNC_PTR_APPL		(1<<1)	/* get appl_ptr from driver (r/w op) */
-#define SNDRV_PCM_SYNC_PTR_AVAIL_MIN	(1<<2)	/* get avail_min from driver */
-
-struct snd_pcm_sync_ptr {
-	unsigned int flags;
-	union {
-		struct snd_pcm_mmap_status status;
-		unsigned char reserved[64];
-	} s;
-	union {
-		struct snd_pcm_mmap_control control;
-		unsigned char reserved[64];
-	} c;
-};
-
-struct snd_xferi {
-	snd_pcm_sframes_t result;
-	void __user *buf;
-	snd_pcm_uframes_t frames;
-};
-
-struct snd_xfern {
-	snd_pcm_sframes_t result;
-	void __user * __user *bufs;
-	snd_pcm_uframes_t frames;
-};
-
-enum {
-	SNDRV_PCM_TSTAMP_TYPE_GETTIMEOFDAY = 0,	/* gettimeofday equivalent */
-	SNDRV_PCM_TSTAMP_TYPE_MONOTONIC,	/* posix_clock_monotonic equivalent */
-	SNDRV_PCM_TSTAMP_TYPE_LAST = SNDRV_PCM_TSTAMP_TYPE_MONOTONIC,
-};
-
-/* channel positions */
-enum {
-	SNDRV_CHMAP_UNKNOWN = 0,
-	SNDRV_CHMAP_NA,		/* N/A, silent */
-	SNDRV_CHMAP_MONO,	/* mono stream */
-	/* this follows the alsa-lib mixer channel value + 3 */
-	SNDRV_CHMAP_FL,		/* front left */
-	SNDRV_CHMAP_FR,		/* front right */
-	SNDRV_CHMAP_RL,		/* rear left */
-	SNDRV_CHMAP_RR,		/* rear right */
-	SNDRV_CHMAP_FC,		/* front center */
-	SNDRV_CHMAP_LFE,	/* LFE */
-	SNDRV_CHMAP_SL,		/* side left */
-	SNDRV_CHMAP_SR,		/* side right */
-	SNDRV_CHMAP_RC,		/* rear center */
-	/* new definitions */
-	SNDRV_CHMAP_FLC,	/* front left center */
-	SNDRV_CHMAP_FRC,	/* front right center */
-	SNDRV_CHMAP_RLC,	/* rear left center */
-	SNDRV_CHMAP_RRC,	/* rear right center */
-	SNDRV_CHMAP_FLW,	/* front left wide */
-	SNDRV_CHMAP_FRW,	/* front right wide */
-	SNDRV_CHMAP_FLH,	/* front left high */
-	SNDRV_CHMAP_FCH,	/* front center high */
-	SNDRV_CHMAP_FRH,	/* front right high */
-	SNDRV_CHMAP_TC,		/* top center */
-	SNDRV_CHMAP_TFL,	/* top front left */
-	SNDRV_CHMAP_TFR,	/* top front right */
-	SNDRV_CHMAP_TFC,	/* top front center */
-	SNDRV_CHMAP_TRL,	/* top rear left */
-	SNDRV_CHMAP_TRR,	/* top rear right */
-	SNDRV_CHMAP_TRC,	/* top rear center */
-	SNDRV_CHMAP_LAST = SNDRV_CHMAP_TRC,
-};
-
-#define SNDRV_CHMAP_POSITION_MASK	0xffff
-#define SNDRV_CHMAP_PHASE_INVERSE	(0x01 << 16)
-#define SNDRV_CHMAP_DRIVER_SPEC		(0x02 << 16)
-
-#define SNDRV_PCM_IOCTL_PVERSION	_IOR('A', 0x00, int)
-#define SNDRV_PCM_IOCTL_INFO		_IOR('A', 0x01, struct snd_pcm_info)
-#define SNDRV_PCM_IOCTL_TSTAMP		_IOW('A', 0x02, int)
-#define SNDRV_PCM_IOCTL_TTSTAMP		_IOW('A', 0x03, int)
-#define SNDRV_PCM_IOCTL_HW_REFINE	_IOWR('A', 0x10, struct snd_pcm_hw_params)
-#define SNDRV_PCM_IOCTL_HW_PARAMS	_IOWR('A', 0x11, struct snd_pcm_hw_params)
-#define SNDRV_PCM_IOCTL_HW_FREE		_IO('A', 0x12)
-#define SNDRV_PCM_IOCTL_SW_PARAMS	_IOWR('A', 0x13, struct snd_pcm_sw_params)
-#define SNDRV_PCM_IOCTL_STATUS		_IOR('A', 0x20, struct snd_pcm_status)
-#define SNDRV_PCM_IOCTL_DELAY		_IOR('A', 0x21, snd_pcm_sframes_t)
-#define SNDRV_PCM_IOCTL_HWSYNC		_IO('A', 0x22)
-#define SNDRV_PCM_IOCTL_SYNC_PTR	_IOWR('A', 0x23, struct snd_pcm_sync_ptr)
-#define SNDRV_PCM_IOCTL_CHANNEL_INFO	_IOR('A', 0x32, struct snd_pcm_channel_info)
-#define SNDRV_PCM_IOCTL_PREPARE		_IO('A', 0x40)
-#define SNDRV_PCM_IOCTL_RESET		_IO('A', 0x41)
-#define SNDRV_PCM_IOCTL_START		_IO('A', 0x42)
-#define SNDRV_PCM_IOCTL_DROP		_IO('A', 0x43)
-#define SNDRV_PCM_IOCTL_DRAIN		_IO('A', 0x44)
-#define SNDRV_PCM_IOCTL_PAUSE		_IOW('A', 0x45, int)
-#define SNDRV_PCM_IOCTL_REWIND		_IOW('A', 0x46, snd_pcm_uframes_t)
-#define SNDRV_PCM_IOCTL_RESUME		_IO('A', 0x47)
-#define SNDRV_PCM_IOCTL_XRUN		_IO('A', 0x48)
-#define SNDRV_PCM_IOCTL_FORWARD		_IOW('A', 0x49, snd_pcm_uframes_t)
-#define SNDRV_PCM_IOCTL_WRITEI_FRAMES	_IOW('A', 0x50, struct snd_xferi)
-#define SNDRV_PCM_IOCTL_READI_FRAMES	_IOR('A', 0x51, struct snd_xferi)
-#define SNDRV_PCM_IOCTL_WRITEN_FRAMES	_IOW('A', 0x52, struct snd_xfern)
-#define SNDRV_PCM_IOCTL_READN_FRAMES	_IOR('A', 0x53, struct snd_xfern)
-#define SNDRV_PCM_IOCTL_LINK		_IOW('A', 0x60, int)
-#define SNDRV_PCM_IOCTL_UNLINK		_IO('A', 0x61)
-
-/*****************************************************************************
- *                                                                           *
- *                            MIDI v1.0 interface                            *
- *                                                                           *
- *****************************************************************************/
-
-/*
- *  Raw MIDI section - /dev/snd/midi??
- */
-
-#define SNDRV_RAWMIDI_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 0)
-
-enum {
-	SNDRV_RAWMIDI_STREAM_OUTPUT = 0,
-	SNDRV_RAWMIDI_STREAM_INPUT,
-	SNDRV_RAWMIDI_STREAM_LAST = SNDRV_RAWMIDI_STREAM_INPUT,
-};
-
-#define SNDRV_RAWMIDI_INFO_OUTPUT		0x00000001
-#define SNDRV_RAWMIDI_INFO_INPUT		0x00000002
-#define SNDRV_RAWMIDI_INFO_DUPLEX		0x00000004
-
-struct snd_rawmidi_info {
-	unsigned int device;		/* RO/WR (control): device number */
-	unsigned int subdevice;		/* RO/WR (control): subdevice number */
-	int stream;			/* WR: stream */
-	int card;			/* R: card number */
-	unsigned int flags;		/* SNDRV_RAWMIDI_INFO_XXXX */
-	unsigned char id[64];		/* ID (user selectable) */
-	unsigned char name[80];		/* name of device */
-	unsigned char subname[32];	/* name of active or selected subdevice */
-	unsigned int subdevices_count;
-	unsigned int subdevices_avail;
-	unsigned char reserved[64];	/* reserved for future use */
-};
-
-struct snd_rawmidi_params {
-	int stream;
-	size_t buffer_size;		/* queue size in bytes */
-	size_t avail_min;		/* minimum avail bytes for wakeup */
-	unsigned int no_active_sensing: 1; /* do not send active sensing byte in close() */
-	unsigned char reserved[16];	/* reserved for future use */
-};
-
-struct snd_rawmidi_status {
-	int stream;
-	struct timespec tstamp;		/* Timestamp */
-	size_t avail;			/* available bytes */
-	size_t xruns;			/* count of overruns since last status (in bytes) */
-	unsigned char reserved[16];	/* reserved for future use */
-};
-
-#define SNDRV_RAWMIDI_IOCTL_PVERSION	_IOR('W', 0x00, int)
-#define SNDRV_RAWMIDI_IOCTL_INFO	_IOR('W', 0x01, struct snd_rawmidi_info)
-#define SNDRV_RAWMIDI_IOCTL_PARAMS	_IOWR('W', 0x10, struct snd_rawmidi_params)
-#define SNDRV_RAWMIDI_IOCTL_STATUS	_IOWR('W', 0x20, struct snd_rawmidi_status)
-#define SNDRV_RAWMIDI_IOCTL_DROP	_IOW('W', 0x30, int)
-#define SNDRV_RAWMIDI_IOCTL_DRAIN	_IOW('W', 0x31, int)
-
-/*
- *  Timer section - /dev/snd/timer
- */
-
-#define SNDRV_TIMER_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 6)
-
-enum {
-	SNDRV_TIMER_CLASS_NONE = -1,
-	SNDRV_TIMER_CLASS_SLAVE = 0,
-	SNDRV_TIMER_CLASS_GLOBAL,
-	SNDRV_TIMER_CLASS_CARD,
-	SNDRV_TIMER_CLASS_PCM,
-	SNDRV_TIMER_CLASS_LAST = SNDRV_TIMER_CLASS_PCM,
-};
-
-/* slave timer classes */
-enum {
-	SNDRV_TIMER_SCLASS_NONE = 0,
-	SNDRV_TIMER_SCLASS_APPLICATION,
-	SNDRV_TIMER_SCLASS_SEQUENCER,		/* alias */
-	SNDRV_TIMER_SCLASS_OSS_SEQUENCER,	/* alias */
-	SNDRV_TIMER_SCLASS_LAST = SNDRV_TIMER_SCLASS_OSS_SEQUENCER,
-};
-
-/* global timers (device member) */
-#define SNDRV_TIMER_GLOBAL_SYSTEM	0
-#define SNDRV_TIMER_GLOBAL_RTC		1
-#define SNDRV_TIMER_GLOBAL_HPET		2
-#define SNDRV_TIMER_GLOBAL_HRTIMER	3
-
-/* info flags */
-#define SNDRV_TIMER_FLG_SLAVE		(1<<0)	/* cannot be controlled */
-
-struct snd_timer_id {
-	int dev_class;
-	int dev_sclass;
-	int card;
-	int device;
-	int subdevice;
-};
-
-struct snd_timer_ginfo {
-	struct snd_timer_id tid;	/* requested timer ID */
-	unsigned int flags;		/* timer flags - SNDRV_TIMER_FLG_* */
-	int card;			/* card number */
-	unsigned char id[64];		/* timer identification */
-	unsigned char name[80];		/* timer name */
-	unsigned long reserved0;	/* reserved for future use */
-	unsigned long resolution;	/* average period resolution in ns */
-	unsigned long resolution_min;	/* minimal period resolution in ns */
-	unsigned long resolution_max;	/* maximal period resolution in ns */
-	unsigned int clients;		/* active timer clients */
-	unsigned char reserved[32];
-};
-
-struct snd_timer_gparams {
-	struct snd_timer_id tid;	/* requested timer ID */
-	unsigned long period_num;	/* requested precise period duration (in seconds) - numerator */
-	unsigned long period_den;	/* requested precise period duration (in seconds) - denominator */
-	unsigned char reserved[32];
-};
-
-struct snd_timer_gstatus {
-	struct snd_timer_id tid;	/* requested timer ID */
-	unsigned long resolution;	/* current period resolution in ns */
-	unsigned long resolution_num;	/* precise current period resolution (in seconds) - numerator */
-	unsigned long resolution_den;	/* precise current period resolution (in seconds) - denominator */
-	unsigned char reserved[32];
-};
-
-struct snd_timer_select {
-	struct snd_timer_id id;	/* bind to timer ID */
-	unsigned char reserved[32];	/* reserved */
-};
-
-struct snd_timer_info {
-	unsigned int flags;		/* timer flags - SNDRV_TIMER_FLG_* */
-	int card;			/* card number */
-	unsigned char id[64];		/* timer identificator */
-	unsigned char name[80];		/* timer name */
-	unsigned long reserved0;	/* reserved for future use */
-	unsigned long resolution;	/* average period resolution in ns */
-	unsigned char reserved[64];	/* reserved */
-};
-
-#define SNDRV_TIMER_PSFLG_AUTO		(1<<0)	/* auto start, otherwise one-shot */
-#define SNDRV_TIMER_PSFLG_EXCLUSIVE	(1<<1)	/* exclusive use, precise start/stop/pause/continue */
-#define SNDRV_TIMER_PSFLG_EARLY_EVENT	(1<<2)	/* write early event to the poll queue */
-
-struct snd_timer_params {
-	unsigned int flags;		/* flags - SNDRV_MIXER_PSFLG_* */
-	unsigned int ticks;		/* requested resolution in ticks */
-	unsigned int queue_size;	/* total size of queue (32-1024) */
-	unsigned int reserved0;		/* reserved, was: failure locations */
-	unsigned int filter;		/* event filter (bitmask of SNDRV_TIMER_EVENT_*) */
-	unsigned char reserved[60];	/* reserved */
-};
-
-struct snd_timer_status {
-	struct timespec tstamp;		/* Timestamp - last update */
-	unsigned int resolution;	/* current period resolution in ns */
-	unsigned int lost;		/* counter of master tick lost */
-	unsigned int overrun;		/* count of read queue overruns */
-	unsigned int queue;		/* used queue size */
-	unsigned char reserved[64];	/* reserved */
-};
-
-#define SNDRV_TIMER_IOCTL_PVERSION	_IOR('T', 0x00, int)
-#define SNDRV_TIMER_IOCTL_NEXT_DEVICE	_IOWR('T', 0x01, struct snd_timer_id)
-#define SNDRV_TIMER_IOCTL_TREAD		_IOW('T', 0x02, int)
-#define SNDRV_TIMER_IOCTL_GINFO		_IOWR('T', 0x03, struct snd_timer_ginfo)
-#define SNDRV_TIMER_IOCTL_GPARAMS	_IOW('T', 0x04, struct snd_timer_gparams)
-#define SNDRV_TIMER_IOCTL_GSTATUS	_IOWR('T', 0x05, struct snd_timer_gstatus)
-#define SNDRV_TIMER_IOCTL_SELECT	_IOW('T', 0x10, struct snd_timer_select)
-#define SNDRV_TIMER_IOCTL_INFO		_IOR('T', 0x11, struct snd_timer_info)
-#define SNDRV_TIMER_IOCTL_PARAMS	_IOW('T', 0x12, struct snd_timer_params)
-#define SNDRV_TIMER_IOCTL_STATUS	_IOR('T', 0x14, struct snd_timer_status)
-/* The following four ioctls are changed since 1.0.9 due to confliction */
-#define SNDRV_TIMER_IOCTL_START		_IO('T', 0xa0)
-#define SNDRV_TIMER_IOCTL_STOP		_IO('T', 0xa1)
-#define SNDRV_TIMER_IOCTL_CONTINUE	_IO('T', 0xa2)
-#define SNDRV_TIMER_IOCTL_PAUSE		_IO('T', 0xa3)
-
-struct snd_timer_read {
-	unsigned int resolution;
-	unsigned int ticks;
-};
-
-enum {
-	SNDRV_TIMER_EVENT_RESOLUTION = 0,	/* val = resolution in ns */
-	SNDRV_TIMER_EVENT_TICK,			/* val = ticks */
-	SNDRV_TIMER_EVENT_START,		/* val = resolution in ns */
-	SNDRV_TIMER_EVENT_STOP,			/* val = 0 */
-	SNDRV_TIMER_EVENT_CONTINUE,		/* val = resolution in ns */
-	SNDRV_TIMER_EVENT_PAUSE,		/* val = 0 */
-	SNDRV_TIMER_EVENT_EARLY,		/* val = 0, early event */
-	SNDRV_TIMER_EVENT_SUSPEND,		/* val = 0 */
-	SNDRV_TIMER_EVENT_RESUME,		/* val = resolution in ns */
-	/* master timer events for slave timer instances */
-	SNDRV_TIMER_EVENT_MSTART = SNDRV_TIMER_EVENT_START + 10,
-	SNDRV_TIMER_EVENT_MSTOP = SNDRV_TIMER_EVENT_STOP + 10,
-	SNDRV_TIMER_EVENT_MCONTINUE = SNDRV_TIMER_EVENT_CONTINUE + 10,
-	SNDRV_TIMER_EVENT_MPAUSE = SNDRV_TIMER_EVENT_PAUSE + 10,
-	SNDRV_TIMER_EVENT_MSUSPEND = SNDRV_TIMER_EVENT_SUSPEND + 10,
-	SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10,
-};
-
-struct snd_timer_tread {
-	int event;
-	struct timespec tstamp;
-	unsigned int val;
-};
-
-/****************************************************************************
- *                                                                          *
- *        Section for driver control interface - /dev/snd/control?          *
- *                                                                          *
- ****************************************************************************/
-
-#define SNDRV_CTL_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 7)
-
-struct snd_ctl_card_info {
-	int card;			/* card number */
-	int pad;			/* reserved for future (was type) */
-	unsigned char id[16];		/* ID of card (user selectable) */
-	unsigned char driver[16];	/* Driver name */
-	unsigned char name[32];		/* Short name of soundcard */
-	unsigned char longname[80];	/* name + info text about soundcard */
-	unsigned char reserved_[16];	/* reserved for future (was ID of mixer) */
-	unsigned char mixername[80];	/* visual mixer identification */
-	unsigned char components[128];	/* card components / fine identification, delimited with one space (AC97 etc..) */
-};
-
-typedef int __bitwise snd_ctl_elem_type_t;
-#define	SNDRV_CTL_ELEM_TYPE_NONE	((__force snd_ctl_elem_type_t) 0) /* invalid */
-#define	SNDRV_CTL_ELEM_TYPE_BOOLEAN	((__force snd_ctl_elem_type_t) 1) /* boolean type */
-#define	SNDRV_CTL_ELEM_TYPE_INTEGER	((__force snd_ctl_elem_type_t) 2) /* integer type */
-#define	SNDRV_CTL_ELEM_TYPE_ENUMERATED	((__force snd_ctl_elem_type_t) 3) /* enumerated type */
-#define	SNDRV_CTL_ELEM_TYPE_BYTES	((__force snd_ctl_elem_type_t) 4) /* byte array */
-#define	SNDRV_CTL_ELEM_TYPE_IEC958	((__force snd_ctl_elem_type_t) 5) /* IEC958 (S/PDIF) setup */
-#define	SNDRV_CTL_ELEM_TYPE_INTEGER64	((__force snd_ctl_elem_type_t) 6) /* 64-bit integer type */
-#define	SNDRV_CTL_ELEM_TYPE_LAST	SNDRV_CTL_ELEM_TYPE_INTEGER64
-
-typedef int __bitwise snd_ctl_elem_iface_t;
-#define	SNDRV_CTL_ELEM_IFACE_CARD	((__force snd_ctl_elem_iface_t) 0) /* global control */
-#define	SNDRV_CTL_ELEM_IFACE_HWDEP	((__force snd_ctl_elem_iface_t) 1) /* hardware dependent device */
-#define	SNDRV_CTL_ELEM_IFACE_MIXER	((__force snd_ctl_elem_iface_t) 2) /* virtual mixer device */
-#define	SNDRV_CTL_ELEM_IFACE_PCM	((__force snd_ctl_elem_iface_t) 3) /* PCM device */
-#define	SNDRV_CTL_ELEM_IFACE_RAWMIDI	((__force snd_ctl_elem_iface_t) 4) /* RawMidi device */
-#define	SNDRV_CTL_ELEM_IFACE_TIMER	((__force snd_ctl_elem_iface_t) 5) /* timer device */
-#define	SNDRV_CTL_ELEM_IFACE_SEQUENCER	((__force snd_ctl_elem_iface_t) 6) /* sequencer client */
-#define	SNDRV_CTL_ELEM_IFACE_LAST	SNDRV_CTL_ELEM_IFACE_SEQUENCER
-
-#define SNDRV_CTL_ELEM_ACCESS_READ		(1<<0)
-#define SNDRV_CTL_ELEM_ACCESS_WRITE		(1<<1)
-#define SNDRV_CTL_ELEM_ACCESS_READWRITE		(SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
-#define SNDRV_CTL_ELEM_ACCESS_VOLATILE		(1<<2)	/* control value may be changed without a notification */
-#define SNDRV_CTL_ELEM_ACCESS_TIMESTAMP		(1<<3)	/* when was control changed */
-#define SNDRV_CTL_ELEM_ACCESS_TLV_READ		(1<<4)	/* TLV read is possible */
-#define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE		(1<<5)	/* TLV write is possible */
-#define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE	(SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)
-#define SNDRV_CTL_ELEM_ACCESS_TLV_COMMAND	(1<<6)	/* TLV command is possible */
-#define SNDRV_CTL_ELEM_ACCESS_INACTIVE		(1<<8)	/* control does actually nothing, but may be updated */
-#define SNDRV_CTL_ELEM_ACCESS_LOCK		(1<<9)	/* write lock */
-#define SNDRV_CTL_ELEM_ACCESS_OWNER		(1<<10)	/* write lock owner */
-#define SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK	(1<<28)	/* kernel use a TLV callback */ 
-#define SNDRV_CTL_ELEM_ACCESS_USER		(1<<29) /* user space element */
-/* bits 30 and 31 are obsoleted (for indirect access) */
-
-/* for further details see the ACPI and PCI power management specification */
-#define SNDRV_CTL_POWER_D0		0x0000	/* full On */
-#define SNDRV_CTL_POWER_D1		0x0100	/* partial On */
-#define SNDRV_CTL_POWER_D2		0x0200	/* partial On */
-#define SNDRV_CTL_POWER_D3		0x0300	/* Off */
-#define SNDRV_CTL_POWER_D3hot		(SNDRV_CTL_POWER_D3|0x0000)	/* Off, with power */
-#define SNDRV_CTL_POWER_D3cold		(SNDRV_CTL_POWER_D3|0x0001)	/* Off, without power */
-
-struct snd_ctl_elem_id {
-	unsigned int numid;		/* numeric identifier, zero = invalid */
-	snd_ctl_elem_iface_t iface;	/* interface identifier */
-	unsigned int device;		/* device/client number */
-	unsigned int subdevice;		/* subdevice (substream) number */
-	unsigned char name[44];		/* ASCII name of item */
-	unsigned int index;		/* index of item */
-};
-
-struct snd_ctl_elem_list {
-	unsigned int offset;		/* W: first element ID to get */
-	unsigned int space;		/* W: count of element IDs to get */
-	unsigned int used;		/* R: count of element IDs set */
-	unsigned int count;		/* R: count of all elements */
-	struct snd_ctl_elem_id __user *pids; /* R: IDs */
-	unsigned char reserved[50];
-};
-
-struct snd_ctl_elem_info {
-	struct snd_ctl_elem_id id;	/* W: element ID */
-	snd_ctl_elem_type_t type;	/* R: value type - SNDRV_CTL_ELEM_TYPE_* */
-	unsigned int access;		/* R: value access (bitmask) - SNDRV_CTL_ELEM_ACCESS_* */
-	unsigned int count;		/* count of values */
-	__kernel_pid_t owner;		/* owner's PID of this control */
-	union {
-		struct {
-			long min;		/* R: minimum value */
-			long max;		/* R: maximum value */
-			long step;		/* R: step (0 variable) */
-		} integer;
-		struct {
-			long long min;		/* R: minimum value */
-			long long max;		/* R: maximum value */
-			long long step;		/* R: step (0 variable) */
-		} integer64;
-		struct {
-			unsigned int items;	/* R: number of items */
-			unsigned int item;	/* W: item number */
-			char name[64];		/* R: value name */
-			__u64 names_ptr;	/* W: names list (ELEM_ADD only) */
-			unsigned int names_length;
-		} enumerated;
-		unsigned char reserved[128];
-	} value;
-	union {
-		unsigned short d[4];		/* dimensions */
-		unsigned short *d_ptr;		/* indirect - obsoleted */
-	} dimen;
-	unsigned char reserved[64-4*sizeof(unsigned short)];
-};
-
-struct snd_ctl_elem_value {
-	struct snd_ctl_elem_id id;	/* W: element ID */
-	unsigned int indirect: 1;	/* W: indirect access - obsoleted */
-	union {
-		union {
-			long value[128];
-			long *value_ptr;	/* obsoleted */
-		} integer;
-		union {
-			long long value[64];
-			long long *value_ptr;	/* obsoleted */
-		} integer64;
-		union {
-			unsigned int item[128];
-			unsigned int *item_ptr;	/* obsoleted */
-		} enumerated;
-		union {
-			unsigned char data[512];
-			unsigned char *data_ptr;	/* obsoleted */
-		} bytes;
-		struct snd_aes_iec958 iec958;
-	} value;		/* RO */
-	struct timespec tstamp;
-	unsigned char reserved[128-sizeof(struct timespec)];
-};
-
-struct snd_ctl_tlv {
-	unsigned int numid;	/* control element numeric identification */
-	unsigned int length;	/* in bytes aligned to 4 */
-	unsigned int tlv[0];	/* first TLV */
-};
-
-#define SNDRV_CTL_IOCTL_PVERSION	_IOR('U', 0x00, int)
-#define SNDRV_CTL_IOCTL_CARD_INFO	_IOR('U', 0x01, struct snd_ctl_card_info)
-#define SNDRV_CTL_IOCTL_ELEM_LIST	_IOWR('U', 0x10, struct snd_ctl_elem_list)
-#define SNDRV_CTL_IOCTL_ELEM_INFO	_IOWR('U', 0x11, struct snd_ctl_elem_info)
-#define SNDRV_CTL_IOCTL_ELEM_READ	_IOWR('U', 0x12, struct snd_ctl_elem_value)
-#define SNDRV_CTL_IOCTL_ELEM_WRITE	_IOWR('U', 0x13, struct snd_ctl_elem_value)
-#define SNDRV_CTL_IOCTL_ELEM_LOCK	_IOW('U', 0x14, struct snd_ctl_elem_id)
-#define SNDRV_CTL_IOCTL_ELEM_UNLOCK	_IOW('U', 0x15, struct snd_ctl_elem_id)
-#define SNDRV_CTL_IOCTL_SUBSCRIBE_EVENTS _IOWR('U', 0x16, int)
-#define SNDRV_CTL_IOCTL_ELEM_ADD	_IOWR('U', 0x17, struct snd_ctl_elem_info)
-#define SNDRV_CTL_IOCTL_ELEM_REPLACE	_IOWR('U', 0x18, struct snd_ctl_elem_info)
-#define SNDRV_CTL_IOCTL_ELEM_REMOVE	_IOWR('U', 0x19, struct snd_ctl_elem_id)
-#define SNDRV_CTL_IOCTL_TLV_READ	_IOWR('U', 0x1a, struct snd_ctl_tlv)
-#define SNDRV_CTL_IOCTL_TLV_WRITE	_IOWR('U', 0x1b, struct snd_ctl_tlv)
-#define SNDRV_CTL_IOCTL_TLV_COMMAND	_IOWR('U', 0x1c, struct snd_ctl_tlv)
-#define SNDRV_CTL_IOCTL_HWDEP_NEXT_DEVICE _IOWR('U', 0x20, int)
-#define SNDRV_CTL_IOCTL_HWDEP_INFO	_IOR('U', 0x21, struct snd_hwdep_info)
-#define SNDRV_CTL_IOCTL_PCM_NEXT_DEVICE	_IOR('U', 0x30, int)
-#define SNDRV_CTL_IOCTL_PCM_INFO	_IOWR('U', 0x31, struct snd_pcm_info)
-#define SNDRV_CTL_IOCTL_PCM_PREFER_SUBDEVICE _IOW('U', 0x32, int)
-#define SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE _IOWR('U', 0x40, int)
-#define SNDRV_CTL_IOCTL_RAWMIDI_INFO	_IOWR('U', 0x41, struct snd_rawmidi_info)
-#define SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE _IOW('U', 0x42, int)
-#define SNDRV_CTL_IOCTL_POWER		_IOWR('U', 0xd0, int)
-#define SNDRV_CTL_IOCTL_POWER_STATE	_IOR('U', 0xd1, int)
-
-/*
- *  Read interface.
- */
-
-enum sndrv_ctl_event_type {
-	SNDRV_CTL_EVENT_ELEM = 0,
-	SNDRV_CTL_EVENT_LAST = SNDRV_CTL_EVENT_ELEM,
-};
-
-#define SNDRV_CTL_EVENT_MASK_VALUE	(1<<0)	/* element value was changed */
-#define SNDRV_CTL_EVENT_MASK_INFO	(1<<1)	/* element info was changed */
-#define SNDRV_CTL_EVENT_MASK_ADD	(1<<2)	/* element was added */
-#define SNDRV_CTL_EVENT_MASK_TLV	(1<<3)	/* element TLV tree was changed */
-#define SNDRV_CTL_EVENT_MASK_REMOVE	(~0U)	/* element was removed */
-
-struct snd_ctl_event {
-	int type;	/* event type - SNDRV_CTL_EVENT_* */
-	union {
-		struct {
-			unsigned int mask;
-			struct snd_ctl_elem_id id;
-		} elem;
-		unsigned char data8[60];
-	} data;
-};
-
-/*
- *  Control names
- */
-
-#define SNDRV_CTL_NAME_NONE				""
-#define SNDRV_CTL_NAME_PLAYBACK				"Playback "
-#define SNDRV_CTL_NAME_CAPTURE				"Capture "
-
-#define SNDRV_CTL_NAME_IEC958_NONE			""
-#define SNDRV_CTL_NAME_IEC958_SWITCH			"Switch"
-#define SNDRV_CTL_NAME_IEC958_VOLUME			"Volume"
-#define SNDRV_CTL_NAME_IEC958_DEFAULT			"Default"
-#define SNDRV_CTL_NAME_IEC958_MASK			"Mask"
-#define SNDRV_CTL_NAME_IEC958_CON_MASK			"Con Mask"
-#define SNDRV_CTL_NAME_IEC958_PRO_MASK			"Pro Mask"
-#define SNDRV_CTL_NAME_IEC958_PCM_STREAM		"PCM Stream"
-#define SNDRV_CTL_NAME_IEC958(expl,direction,what)	"IEC958 " expl SNDRV_CTL_NAME_##direction SNDRV_CTL_NAME_IEC958_##what
-
+#include <uapi/sound/asound.h>
 #endif /* __SOUND_ASOUND_H */
diff --git a/include/sound/asound_fm.h b/include/sound/asound_fm.h
deleted file mode 100644
index c2a4b967d5be..000000000000
--- a/include/sound/asound_fm.h
+++ /dev/null
@@ -1,134 +0,0 @@
-#ifndef __SOUND_ASOUND_FM_H
-#define __SOUND_ASOUND_FM_H
-
-/*
- *  Advanced Linux Sound Architecture - ALSA
- *
- *  Interface file between ALSA driver & user space
- *  Copyright (c) 1994-98 by Jaroslav Kysela <perex@perex.cz>,
- *                           4Front Technologies
- *
- *  Direct FM control
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program; if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
- */
-
-#define SNDRV_DM_FM_MODE_OPL2	0x00
-#define SNDRV_DM_FM_MODE_OPL3	0x01
-
-struct snd_dm_fm_info {
-	unsigned char fm_mode;		/* OPL mode, see SNDRV_DM_FM_MODE_XXX */
-	unsigned char rhythm;		/* percussion mode flag */
-};
-
-/*
- *  Data structure composing an FM "note" or sound event.
- */
-
-struct snd_dm_fm_voice {
-	unsigned char op;		/* operator cell (0 or 1) */
-	unsigned char voice;		/* FM voice (0 to 17) */
-
-	unsigned char am;		/* amplitude modulation */
-	unsigned char vibrato;		/* vibrato effect */
-	unsigned char do_sustain;	/* sustain phase */
-	unsigned char kbd_scale;	/* keyboard scaling */
-	unsigned char harmonic;		/* 4 bits: harmonic and multiplier */
-	unsigned char scale_level;	/* 2 bits: decrease output freq rises */
-	unsigned char volume;		/* 6 bits: volume */
-
-	unsigned char attack;		/* 4 bits: attack rate */
-	unsigned char decay;		/* 4 bits: decay rate */
-	unsigned char sustain;		/* 4 bits: sustain level */
-	unsigned char release;		/* 4 bits: release rate */
-
-	unsigned char feedback;		/* 3 bits: feedback for op0 */
-	unsigned char connection;	/* 0 for serial, 1 for parallel */
-	unsigned char left;		/* stereo left */
-	unsigned char right;		/* stereo right */
-	unsigned char waveform;		/* 3 bits: waveform shape */
-};
-
-/*
- *  This describes an FM note by its voice, octave, frequency number (10bit)
- *  and key on/off.
- */
-
-struct snd_dm_fm_note {
-	unsigned char voice;	/* 0-17 voice channel */
-	unsigned char octave;	/* 3 bits: what octave to play */
-	unsigned int fnum;	/* 10 bits: frequency number */
-	unsigned char key_on;	/* set for active, clear for silent */
-};
-
-/*
- *  FM parameters that apply globally to all voices, and thus are not "notes"
- */
-
-struct snd_dm_fm_params {
-	unsigned char am_depth;		/* amplitude modulation depth (1=hi) */
-	unsigned char vib_depth;	/* vibrato depth (1=hi) */
-	unsigned char kbd_split;	/* keyboard split */
-	unsigned char rhythm;		/* percussion mode select */
-
-	/* This block is the percussion instrument data */
-	unsigned char bass;
-	unsigned char snare;
-	unsigned char tomtom;
-	unsigned char cymbal;
-	unsigned char hihat;
-};
-
-/*
- *  FM mode ioctl settings
- */
-
-#define SNDRV_DM_FM_IOCTL_INFO		_IOR('H', 0x20, struct snd_dm_fm_info)
-#define SNDRV_DM_FM_IOCTL_RESET		_IO ('H', 0x21)
-#define SNDRV_DM_FM_IOCTL_PLAY_NOTE	_IOW('H', 0x22, struct snd_dm_fm_note)
-#define SNDRV_DM_FM_IOCTL_SET_VOICE	_IOW('H', 0x23, struct snd_dm_fm_voice)
-#define SNDRV_DM_FM_IOCTL_SET_PARAMS	_IOW('H', 0x24, struct snd_dm_fm_params)
-#define SNDRV_DM_FM_IOCTL_SET_MODE	_IOW('H', 0x25, int)
-/* for OPL3 only */
-#define SNDRV_DM_FM_IOCTL_SET_CONNECTION	_IOW('H', 0x26, int)
-/* SBI patch management */
-#define SNDRV_DM_FM_IOCTL_CLEAR_PATCHES	_IO ('H', 0x40)
-
-#define SNDRV_DM_FM_OSS_IOCTL_RESET		0x20
-#define SNDRV_DM_FM_OSS_IOCTL_PLAY_NOTE		0x21
-#define SNDRV_DM_FM_OSS_IOCTL_SET_VOICE		0x22
-#define SNDRV_DM_FM_OSS_IOCTL_SET_PARAMS	0x23
-#define SNDRV_DM_FM_OSS_IOCTL_SET_MODE		0x24
-#define SNDRV_DM_FM_OSS_IOCTL_SET_OPL		0x25
-
-/*
- * Patch Record - fixed size for write
- */
-
-#define FM_KEY_SBI	"SBI\032"
-#define FM_KEY_2OP	"2OP\032"
-#define FM_KEY_4OP	"4OP\032"
-
-struct sbi_patch {
-	unsigned char prog;
-	unsigned char bank;
-	char key[4];
-	char name[25];
-	char extension[7];
-	unsigned char data[32];
-};
-
-#endif /* __SOUND_ASOUND_FM_H */
diff --git a/include/sound/compress_offload.h b/include/sound/compress_offload.h
deleted file mode 100644
index 05341a43fedf..000000000000
--- a/include/sound/compress_offload.h
+++ /dev/null
@@ -1,161 +0,0 @@
-/*
- *  compress_offload.h - compress offload header definations
- *
- *  Copyright (C) 2011 Intel Corporation
- *  Authors:	Vinod Koul <vinod.koul@linux.intel.com>
- *		Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
- *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; version 2 of the License.
- *
- *  This program is distributed in the hope that it will be useful, but
- *  WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- */
-#ifndef __COMPRESS_OFFLOAD_H
-#define __COMPRESS_OFFLOAD_H
-
-#include <linux/types.h>
-#include <sound/asound.h>
-#include <sound/compress_params.h>
-
-
-#define SNDRV_COMPRESS_VERSION SNDRV_PROTOCOL_VERSION(0, 1, 0)
-/**
- * struct snd_compressed_buffer: compressed buffer
- * @fragment_size: size of buffer fragment in bytes
- * @fragments: number of such fragments
- */
-struct snd_compressed_buffer {
-	__u32 fragment_size;
-	__u32 fragments;
-};
-
-/**
- * struct snd_compr_params: compressed stream params
- * @buffer: buffer description
- * @codec: codec parameters
- * @no_wake_mode: dont wake on fragment elapsed
- */
-struct snd_compr_params {
-	struct snd_compressed_buffer buffer;
-	struct snd_codec codec;
-	__u8 no_wake_mode;
-};
-
-/**
- * struct snd_compr_tstamp: timestamp descriptor
- * @byte_offset: Byte offset in ring buffer to DSP
- * @copied_total: Total number of bytes copied from/to ring buffer to/by DSP
- * @pcm_frames: Frames decoded or encoded by DSP. This field will evolve by
- *	large steps and should only be used to monitor encoding/decoding
- *	progress. It shall not be used for timing estimates.
- * @pcm_io_frames: Frames rendered or received by DSP into a mixer or an audio
- * output/input. This field should be used for A/V sync or time estimates.
- * @sampling_rate: sampling rate of audio
- */
-struct snd_compr_tstamp {
-	__u32 byte_offset;
-	__u32 copied_total;
-	snd_pcm_uframes_t pcm_frames;
-	snd_pcm_uframes_t pcm_io_frames;
-	__u32 sampling_rate;
-};
-
-/**
- * struct snd_compr_avail: avail descriptor
- * @avail: Number of bytes available in ring buffer for writing/reading
- * @tstamp: timestamp infomation
- */
-struct snd_compr_avail {
-	__u64 avail;
-	struct snd_compr_tstamp tstamp;
-};
-
-enum snd_compr_direction {
-	SND_COMPRESS_PLAYBACK = 0,
-	SND_COMPRESS_CAPTURE
-};
-
-/**
- * struct snd_compr_caps: caps descriptor
- * @codecs: pointer to array of codecs
- * @direction: direction supported. Of type snd_compr_direction
- * @min_fragment_size: minimum fragment supported by DSP
- * @max_fragment_size: maximum fragment supported by DSP
- * @min_fragments: min fragments supported by DSP
- * @max_fragments: max fragments supported by DSP
- * @num_codecs: number of codecs supported
- * @reserved: reserved field
- */
-struct snd_compr_caps {
-	__u32 num_codecs;
-	__u32 direction;
-	__u32 min_fragment_size;
-	__u32 max_fragment_size;
-	__u32 min_fragments;
-	__u32 max_fragments;
-	__u32 codecs[MAX_NUM_CODECS];
-	__u32 reserved[11];
-};
-
-/**
- * struct snd_compr_codec_caps: query capability of codec
- * @codec: codec for which capability is queried
- * @num_descriptors: number of codec descriptors
- * @descriptor: array of codec capability descriptor
- */
-struct snd_compr_codec_caps {
-	__u32 codec;
-	__u32 num_descriptors;
-	struct snd_codec_desc descriptor[MAX_NUM_CODEC_DESCRIPTORS];
-};
-
-/**
- * compress path ioctl definitions
- * SNDRV_COMPRESS_GET_CAPS: Query capability of DSP
- * SNDRV_COMPRESS_GET_CODEC_CAPS: Query capability of a codec
- * SNDRV_COMPRESS_SET_PARAMS: Set codec and stream parameters
- * Note: only codec params can be changed runtime and stream params cant be
- * SNDRV_COMPRESS_GET_PARAMS: Query codec params
- * SNDRV_COMPRESS_TSTAMP: get the current timestamp value
- * SNDRV_COMPRESS_AVAIL: get the current buffer avail value.
- * This also queries the tstamp properties
- * SNDRV_COMPRESS_PAUSE: Pause the running stream
- * SNDRV_COMPRESS_RESUME: resume a paused stream
- * SNDRV_COMPRESS_START: Start a stream
- * SNDRV_COMPRESS_STOP: stop a running stream, discarding ring buffer content
- * and the buffers currently with DSP
- * SNDRV_COMPRESS_DRAIN: Play till end of buffers and stop after that
- * SNDRV_COMPRESS_IOCTL_VERSION: Query the API version
- */
-#define SNDRV_COMPRESS_IOCTL_VERSION	_IOR('C', 0x00, int)
-#define SNDRV_COMPRESS_GET_CAPS		_IOWR('C', 0x10, struct snd_compr_caps)
-#define SNDRV_COMPRESS_GET_CODEC_CAPS	_IOWR('C', 0x11,\
-						struct snd_compr_codec_caps)
-#define SNDRV_COMPRESS_SET_PARAMS	_IOW('C', 0x12, struct snd_compr_params)
-#define SNDRV_COMPRESS_GET_PARAMS	_IOR('C', 0x13, struct snd_codec)
-#define SNDRV_COMPRESS_TSTAMP		_IOR('C', 0x20, struct snd_compr_tstamp)
-#define SNDRV_COMPRESS_AVAIL		_IOR('C', 0x21, struct snd_compr_avail)
-#define SNDRV_COMPRESS_PAUSE		_IO('C', 0x30)
-#define SNDRV_COMPRESS_RESUME		_IO('C', 0x31)
-#define SNDRV_COMPRESS_START		_IO('C', 0x32)
-#define SNDRV_COMPRESS_STOP		_IO('C', 0x33)
-#define SNDRV_COMPRESS_DRAIN		_IO('C', 0x34)
-/*
- * TODO
- * 1. add mmap support
- *
- */
-#define SND_COMPR_TRIGGER_DRAIN 7 /*FIXME move this to pcm.h */
-#endif
diff --git a/include/sound/compress_params.h b/include/sound/compress_params.h
deleted file mode 100644
index 602dc6c45d1a..000000000000
--- a/include/sound/compress_params.h
+++ /dev/null
@@ -1,400 +0,0 @@
-/*
- *  compress_params.h - codec types and parameters for compressed data
- *  streaming interface
- *
- *  Copyright (C) 2011 Intel Corporation
- *  Authors:	Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
- *              Vinod Koul <vinod.koul@linux.intel.com>
- *
- *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; version 2 of the License.
- *
- *  This program is distributed in the hope that it will be useful, but
- *  WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- * The definitions in this file are derived from the OpenMAX AL version 1.1
- * and OpenMAX IL v 1.1.2 header files which contain the copyright notice below.
- *
- * Copyright (c) 2007-2010 The Khronos Group Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining
- * a copy of this software and/or associated documentation files (the
- * "Materials "), to deal in the Materials without restriction, including
- * without limitation the rights to use, copy, modify, merge, publish,
- * distribute, sublicense, and/or sell copies of the Materials, and to
- * permit persons to whom the Materials are furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice shall be included
- * in all copies or substantial portions of the Materials.
- *
- * THE MATERIALS ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
- * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
- * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
- * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
- * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
- * MATERIALS OR THE USE OR OTHER DEALINGS IN THE MATERIALS.
- *
- */
-#ifndef __SND_COMPRESS_PARAMS_H
-#define __SND_COMPRESS_PARAMS_H
-
-#include <linux/types.h>
-
-/* AUDIO CODECS SUPPORTED */
-#define MAX_NUM_CODECS 32
-#define MAX_NUM_CODEC_DESCRIPTORS 32
-#define MAX_NUM_BITRATES 32
-
-/* Codecs are listed linearly to allow for extensibility */
-#define SND_AUDIOCODEC_PCM                   ((__u32) 0x00000001)
-#define SND_AUDIOCODEC_MP3                   ((__u32) 0x00000002)
-#define SND_AUDIOCODEC_AMR                   ((__u32) 0x00000003)
-#define SND_AUDIOCODEC_AMRWB                 ((__u32) 0x00000004)
-#define SND_AUDIOCODEC_AMRWBPLUS             ((__u32) 0x00000005)
-#define SND_AUDIOCODEC_AAC                   ((__u32) 0x00000006)
-#define SND_AUDIOCODEC_WMA                   ((__u32) 0x00000007)
-#define SND_AUDIOCODEC_REAL                  ((__u32) 0x00000008)
-#define SND_AUDIOCODEC_VORBIS                ((__u32) 0x00000009)
-#define SND_AUDIOCODEC_FLAC                  ((__u32) 0x0000000A)
-#define SND_AUDIOCODEC_IEC61937              ((__u32) 0x0000000B)
-#define SND_AUDIOCODEC_G723_1                ((__u32) 0x0000000C)
-#define SND_AUDIOCODEC_G729                  ((__u32) 0x0000000D)
-#define SND_AUDIOCODEC_MAX                   SND_AUDIOCODEC_G729
-
-/*
- * Profile and modes are listed with bit masks. This allows for a
- * more compact representation of fields that will not evolve
- * (in contrast to the list of codecs)
- */
-
-#define SND_AUDIOPROFILE_PCM                 ((__u32) 0x00000001)
-
-/* MP3 modes are only useful for encoders */
-#define SND_AUDIOCHANMODE_MP3_MONO           ((__u32) 0x00000001)
-#define SND_AUDIOCHANMODE_MP3_STEREO         ((__u32) 0x00000002)
-#define SND_AUDIOCHANMODE_MP3_JOINTSTEREO    ((__u32) 0x00000004)
-#define SND_AUDIOCHANMODE_MP3_DUAL           ((__u32) 0x00000008)
-
-#define SND_AUDIOPROFILE_AMR                 ((__u32) 0x00000001)
-
-/* AMR modes are only useful for encoders */
-#define SND_AUDIOMODE_AMR_DTX_OFF            ((__u32) 0x00000001)
-#define SND_AUDIOMODE_AMR_VAD1               ((__u32) 0x00000002)
-#define SND_AUDIOMODE_AMR_VAD2               ((__u32) 0x00000004)
-
-#define SND_AUDIOSTREAMFORMAT_UNDEFINED	     ((__u32) 0x00000000)
-#define SND_AUDIOSTREAMFORMAT_CONFORMANCE    ((__u32) 0x00000001)
-#define SND_AUDIOSTREAMFORMAT_IF1            ((__u32) 0x00000002)
-#define SND_AUDIOSTREAMFORMAT_IF2            ((__u32) 0x00000004)
-#define SND_AUDIOSTREAMFORMAT_FSF            ((__u32) 0x00000008)
-#define SND_AUDIOSTREAMFORMAT_RTPPAYLOAD     ((__u32) 0x00000010)
-#define SND_AUDIOSTREAMFORMAT_ITU            ((__u32) 0x00000020)
-
-#define SND_AUDIOPROFILE_AMRWB               ((__u32) 0x00000001)
-
-/* AMRWB modes are only useful for encoders */
-#define SND_AUDIOMODE_AMRWB_DTX_OFF          ((__u32) 0x00000001)
-#define SND_AUDIOMODE_AMRWB_VAD1             ((__u32) 0x00000002)
-#define SND_AUDIOMODE_AMRWB_VAD2             ((__u32) 0x00000004)
-
-#define SND_AUDIOPROFILE_AMRWBPLUS           ((__u32) 0x00000001)
-
-#define SND_AUDIOPROFILE_AAC                 ((__u32) 0x00000001)
-
-/* AAC modes are required for encoders and decoders */
-#define SND_AUDIOMODE_AAC_MAIN               ((__u32) 0x00000001)
-#define SND_AUDIOMODE_AAC_LC                 ((__u32) 0x00000002)
-#define SND_AUDIOMODE_AAC_SSR                ((__u32) 0x00000004)
-#define SND_AUDIOMODE_AAC_LTP                ((__u32) 0x00000008)
-#define SND_AUDIOMODE_AAC_HE                 ((__u32) 0x00000010)
-#define SND_AUDIOMODE_AAC_SCALABLE           ((__u32) 0x00000020)
-#define SND_AUDIOMODE_AAC_ERLC               ((__u32) 0x00000040)
-#define SND_AUDIOMODE_AAC_LD                 ((__u32) 0x00000080)
-#define SND_AUDIOMODE_AAC_HE_PS              ((__u32) 0x00000100)
-#define SND_AUDIOMODE_AAC_HE_MPS             ((__u32) 0x00000200)
-
-/* AAC formats are required for encoders and decoders */
-#define SND_AUDIOSTREAMFORMAT_MP2ADTS        ((__u32) 0x00000001)
-#define SND_AUDIOSTREAMFORMAT_MP4ADTS        ((__u32) 0x00000002)
-#define SND_AUDIOSTREAMFORMAT_MP4LOAS        ((__u32) 0x00000004)
-#define SND_AUDIOSTREAMFORMAT_MP4LATM        ((__u32) 0x00000008)
-#define SND_AUDIOSTREAMFORMAT_ADIF           ((__u32) 0x00000010)
-#define SND_AUDIOSTREAMFORMAT_MP4FF          ((__u32) 0x00000020)
-#define SND_AUDIOSTREAMFORMAT_RAW            ((__u32) 0x00000040)
-
-#define SND_AUDIOPROFILE_WMA7                ((__u32) 0x00000001)
-#define SND_AUDIOPROFILE_WMA8                ((__u32) 0x00000002)
-#define SND_AUDIOPROFILE_WMA9                ((__u32) 0x00000004)
-#define SND_AUDIOPROFILE_WMA10               ((__u32) 0x00000008)
-
-#define SND_AUDIOMODE_WMA_LEVEL1             ((__u32) 0x00000001)
-#define SND_AUDIOMODE_WMA_LEVEL2             ((__u32) 0x00000002)
-#define SND_AUDIOMODE_WMA_LEVEL3             ((__u32) 0x00000004)
-#define SND_AUDIOMODE_WMA_LEVEL4             ((__u32) 0x00000008)
-#define SND_AUDIOMODE_WMAPRO_LEVELM0         ((__u32) 0x00000010)
-#define SND_AUDIOMODE_WMAPRO_LEVELM1         ((__u32) 0x00000020)
-#define SND_AUDIOMODE_WMAPRO_LEVELM2         ((__u32) 0x00000040)
-#define SND_AUDIOMODE_WMAPRO_LEVELM3         ((__u32) 0x00000080)
-
-#define SND_AUDIOSTREAMFORMAT_WMA_ASF        ((__u32) 0x00000001)
-/*
- * Some implementations strip the ASF header and only send ASF packets
- * to the DSP
- */
-#define SND_AUDIOSTREAMFORMAT_WMA_NOASF_HDR  ((__u32) 0x00000002)
-
-#define SND_AUDIOPROFILE_REALAUDIO           ((__u32) 0x00000001)
-
-#define SND_AUDIOMODE_REALAUDIO_G2           ((__u32) 0x00000001)
-#define SND_AUDIOMODE_REALAUDIO_8            ((__u32) 0x00000002)
-#define SND_AUDIOMODE_REALAUDIO_10           ((__u32) 0x00000004)
-#define SND_AUDIOMODE_REALAUDIO_SURROUND     ((__u32) 0x00000008)
-
-#define SND_AUDIOPROFILE_VORBIS              ((__u32) 0x00000001)
-
-#define SND_AUDIOMODE_VORBIS                 ((__u32) 0x00000001)
-
-#define SND_AUDIOPROFILE_FLAC                ((__u32) 0x00000001)
-
-/*
- * Define quality levels for FLAC encoders, from LEVEL0 (fast)
- * to LEVEL8 (best)
- */
-#define SND_AUDIOMODE_FLAC_LEVEL0            ((__u32) 0x00000001)
-#define SND_AUDIOMODE_FLAC_LEVEL1            ((__u32) 0x00000002)
-#define SND_AUDIOMODE_FLAC_LEVEL2            ((__u32) 0x00000004)
-#define SND_AUDIOMODE_FLAC_LEVEL3            ((__u32) 0x00000008)
-#define SND_AUDIOMODE_FLAC_LEVEL4            ((__u32) 0x00000010)
-#define SND_AUDIOMODE_FLAC_LEVEL5            ((__u32) 0x00000020)
-#define SND_AUDIOMODE_FLAC_LEVEL6            ((__u32) 0x00000040)
-#define SND_AUDIOMODE_FLAC_LEVEL7            ((__u32) 0x00000080)
-#define SND_AUDIOMODE_FLAC_LEVEL8            ((__u32) 0x00000100)
-
-#define SND_AUDIOSTREAMFORMAT_FLAC           ((__u32) 0x00000001)
-#define SND_AUDIOSTREAMFORMAT_FLAC_OGG       ((__u32) 0x00000002)
-
-/* IEC61937 payloads without CUVP and preambles */
-#define SND_AUDIOPROFILE_IEC61937            ((__u32) 0x00000001)
-/* IEC61937 with S/PDIF preambles+CUVP bits in 32-bit containers */
-#define SND_AUDIOPROFILE_IEC61937_SPDIF      ((__u32) 0x00000002)
-
-/*
- * IEC modes are mandatory for decoders. Format autodetection
- * will only happen on the DSP side with mode 0. The PCM mode should
- * not be used, the PCM codec should be used instead.
- */
-#define SND_AUDIOMODE_IEC_REF_STREAM_HEADER  ((__u32) 0x00000000)
-#define SND_AUDIOMODE_IEC_LPCM		     ((__u32) 0x00000001)
-#define SND_AUDIOMODE_IEC_AC3		     ((__u32) 0x00000002)
-#define SND_AUDIOMODE_IEC_MPEG1		     ((__u32) 0x00000004)
-#define SND_AUDIOMODE_IEC_MP3		     ((__u32) 0x00000008)
-#define SND_AUDIOMODE_IEC_MPEG2		     ((__u32) 0x00000010)
-#define SND_AUDIOMODE_IEC_AACLC		     ((__u32) 0x00000020)
-#define SND_AUDIOMODE_IEC_DTS		     ((__u32) 0x00000040)
-#define SND_AUDIOMODE_IEC_ATRAC		     ((__u32) 0x00000080)
-#define SND_AUDIOMODE_IEC_SACD		     ((__u32) 0x00000100)
-#define SND_AUDIOMODE_IEC_EAC3		     ((__u32) 0x00000200)
-#define SND_AUDIOMODE_IEC_DTS_HD	     ((__u32) 0x00000400)
-#define SND_AUDIOMODE_IEC_MLP		     ((__u32) 0x00000800)
-#define SND_AUDIOMODE_IEC_DST		     ((__u32) 0x00001000)
-#define SND_AUDIOMODE_IEC_WMAPRO	     ((__u32) 0x00002000)
-#define SND_AUDIOMODE_IEC_REF_CXT            ((__u32) 0x00004000)
-#define SND_AUDIOMODE_IEC_HE_AAC	     ((__u32) 0x00008000)
-#define SND_AUDIOMODE_IEC_HE_AAC2	     ((__u32) 0x00010000)
-#define SND_AUDIOMODE_IEC_MPEG_SURROUND	     ((__u32) 0x00020000)
-
-#define SND_AUDIOPROFILE_G723_1              ((__u32) 0x00000001)
-
-#define SND_AUDIOMODE_G723_1_ANNEX_A         ((__u32) 0x00000001)
-#define SND_AUDIOMODE_G723_1_ANNEX_B         ((__u32) 0x00000002)
-#define SND_AUDIOMODE_G723_1_ANNEX_C         ((__u32) 0x00000004)
-
-#define SND_AUDIOPROFILE_G729                ((__u32) 0x00000001)
-
-#define SND_AUDIOMODE_G729_ANNEX_A           ((__u32) 0x00000001)
-#define SND_AUDIOMODE_G729_ANNEX_B           ((__u32) 0x00000002)
-
-/* <FIXME: multichannel encoders aren't supported for now. Would need
-   an additional definition of channel arrangement> */
-
-/* VBR/CBR definitions */
-#define SND_RATECONTROLMODE_CONSTANTBITRATE  ((__u32) 0x00000001)
-#define SND_RATECONTROLMODE_VARIABLEBITRATE  ((__u32) 0x00000002)
-
-/* Encoder options */
-
-struct snd_enc_wma {
-	__u32 super_block_align; /* WMA Type-specific data */
-};
-
-
-/**
- * struct snd_enc_vorbis
- * @quality: Sets encoding quality to n, between -1 (low) and 10 (high).
- * In the default mode of operation, the quality level is 3.
- * Normal quality range is 0 - 10.
- * @managed: Boolean. Set  bitrate  management  mode. This turns off the
- * normal VBR encoding, but allows hard or soft bitrate constraints to be
- * enforced by the encoder. This mode can be slower, and may also be
- * lower quality. It is primarily useful for streaming.
- * @max_bit_rate: Enabled only if managed is TRUE
- * @min_bit_rate: Enabled only if managed is TRUE
- * @downmix: Boolean. Downmix input from stereo to mono (has no effect on
- * non-stereo streams). Useful for lower-bitrate encoding.
- *
- * These options were extracted from the OpenMAX IL spec and Gstreamer vorbisenc
- * properties
- *
- * For best quality users should specify VBR mode and set quality levels.
- */
-
-struct snd_enc_vorbis {
-	__s32 quality;
-	__u32 managed;
-	__u32 max_bit_rate;
-	__u32 min_bit_rate;
-	__u32 downmix;
-};
-
-
-/**
- * struct snd_enc_real
- * @quant_bits: number of coupling quantization bits in the stream
- * @start_region: coupling start region in the stream
- * @num_regions: number of regions value
- *
- * These options were extracted from the OpenMAX IL spec
- */
-
-struct snd_enc_real {
-	__u32 quant_bits;
-	__u32 start_region;
-	__u32 num_regions;
-};
-
-/**
- * struct snd_enc_flac
- * @num: serial number, valid only for OGG formats
- *	needs to be set by application
- * @gain: Add replay gain tags
- *
- * These options were extracted from the FLAC online documentation
- * at http://flac.sourceforge.net/documentation_tools_flac.html
- *
- * To make the API simpler, it is assumed that the user will select quality
- * profiles. Additional options that affect encoding quality and speed can
- * be added at a later stage if needed.
- *
- * By default the Subset format is used by encoders.
- *
- * TAGS such as pictures, etc, cannot be handled by an offloaded encoder and are
- * not supported in this API.
- */
-
-struct snd_enc_flac {
-	__u32 num;
-	__u32 gain;
-};
-
-struct snd_enc_generic {
-	__u32 bw;	/* encoder bandwidth */
-	__s32 reserved[15];
-};
-
-union snd_codec_options {
-	struct snd_enc_wma wma;
-	struct snd_enc_vorbis vorbis;
-	struct snd_enc_real real;
-	struct snd_enc_flac flac;
-	struct snd_enc_generic generic;
-};
-
-/** struct snd_codec_desc - description of codec capabilities
- * @max_ch: Maximum number of audio channels
- * @sample_rates: Sampling rates in Hz, use SNDRV_PCM_RATE_xxx for this
- * @bit_rate: Indexed array containing supported bit rates
- * @num_bitrates: Number of valid values in bit_rate array
- * @rate_control: value is specified by SND_RATECONTROLMODE defines.
- * @profiles: Supported profiles. See SND_AUDIOPROFILE defines.
- * @modes: Supported modes. See SND_AUDIOMODE defines
- * @formats: Supported formats. See SND_AUDIOSTREAMFORMAT defines
- * @min_buffer: Minimum buffer size handled by codec implementation
- * @reserved: reserved for future use
- *
- * This structure provides a scalar value for profiles, modes and stream
- * format fields.
- * If an implementation supports multiple combinations, they will be listed as
- * codecs with different descriptors, for example there would be 2 descriptors
- * for AAC-RAW and AAC-ADTS.
- * This entails some redundancy but makes it easier to avoid invalid
- * configurations.
- *
- */
-
-struct snd_codec_desc {
-	__u32 max_ch;
-	__u32 sample_rates;
-	__u32 bit_rate[MAX_NUM_BITRATES];
-	__u32 num_bitrates;
-	__u32 rate_control;
-	__u32 profiles;
-	__u32 modes;
-	__u32 formats;
-	__u32 min_buffer;
-	__u32 reserved[15];
-};
-
-/** struct snd_codec
- * @id: Identifies the supported audio encoder/decoder.
- *		See SND_AUDIOCODEC macros.
- * @ch_in: Number of input audio channels
- * @ch_out: Number of output channels. In case of contradiction between
- *		this field and the channelMode field, the channelMode field
- *		overrides.
- * @sample_rate: Audio sample rate of input data
- * @bit_rate: Bitrate of encoded data. May be ignored by decoders
- * @rate_control: Encoding rate control. See SND_RATECONTROLMODE defines.
- *               Encoders may rely on profiles for quality levels.
- *		 May be ignored by decoders.
- * @profile: Mandatory for encoders, can be mandatory for specific
- *		decoders as well. See SND_AUDIOPROFILE defines.
- * @level: Supported level (Only used by WMA at the moment)
- * @ch_mode: Channel mode for encoder. See SND_AUDIOCHANMODE defines
- * @format: Format of encoded bistream. Mandatory when defined.
- *		See SND_AUDIOSTREAMFORMAT defines.
- * @align: Block alignment in bytes of an audio sample.
- *		Only required for PCM or IEC formats.
- * @options: encoder-specific settings
- * @reserved: reserved for future use
- */
-
-struct snd_codec {
-	__u32 id;
-	__u32 ch_in;
-	__u32 ch_out;
-	__u32 sample_rate;
-	__u32 bit_rate;
-	__u32 rate_control;
-	__u32 profile;
-	__u32 level;
-	__u32 ch_mode;
-	__u32 format;
-	__u32 align;
-	union snd_codec_options options;
-	__u32 reserved[3];
-};
-
-#endif
diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h
index 1a33f48ebe78..3707288ae9bf 100644
--- a/include/sound/emu10k1.h
+++ b/include/sound/emu10k1.h
@@ -1,8 +1,3 @@
-#ifndef __SOUND_EMU10K1_H
-#define __SOUND_EMU10K1_H
-
-#include <linux/types.h>
-
 /*
  *  Copyright (c) by Jaroslav Kysela <perex@perex.cz>,
  *		     Creative Labs, Inc.
@@ -24,8 +19,9 @@
  *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  *
  */
+#ifndef __SOUND_EMU10K1_H
+#define __SOUND_EMU10K1_H
 
-#ifdef __KERNEL__
 
 #include <sound/pcm.h>
 #include <sound/rawmidi.h>
@@ -38,6 +34,7 @@
 #include <linux/mutex.h>
 
 #include <asm/io.h>
+#include <uapi/sound/emu10k1.h>
 
 /* ------------------- DEFINES -------------------- */
 
@@ -1899,350 +1896,4 @@ int snd_emu10k1_fx8010_register_irq_handler(struct snd_emu10k1 *emu,
 int snd_emu10k1_fx8010_unregister_irq_handler(struct snd_emu10k1 *emu,
 					      struct snd_emu10k1_fx8010_irq *irq);
 
-#endif /* __KERNEL__ */
-
-/*
- * ---- FX8010 ----
- */
-
-#define EMU10K1_CARD_CREATIVE			0x00000000
-#define EMU10K1_CARD_EMUAPS			0x00000001
-
-#define EMU10K1_FX8010_PCM_COUNT		8
-
-/* instruction set */
-#define iMAC0	 0x00	/* R = A + (X * Y >> 31)   ; saturation */
-#define iMAC1	 0x01	/* R = A + (-X * Y >> 31)  ; saturation */
-#define iMAC2	 0x02	/* R = A + (X * Y >> 31)   ; wraparound */
-#define iMAC3	 0x03	/* R = A + (-X * Y >> 31)  ; wraparound */
-#define iMACINT0 0x04	/* R = A + X * Y	   ; saturation */
-#define iMACINT1 0x05	/* R = A + X * Y	   ; wraparound (31-bit) */
-#define iACC3	 0x06	/* R = A + X + Y	   ; saturation */
-#define iMACMV   0x07	/* R = A, acc += X * Y >> 31 */
-#define iANDXOR  0x08	/* R = (A & X) ^ Y */
-#define iTSTNEG  0x09	/* R = (A >= Y) ? X : ~X */
-#define iLIMITGE 0x0a	/* R = (A >= Y) ? X : Y */
-#define iLIMITLT 0x0b	/* R = (A < Y) ? X : Y */
-#define iLOG	 0x0c	/* R = linear_data, A (log_data), X (max_exp), Y (format_word) */
-#define iEXP	 0x0d	/* R = log_data, A (linear_data), X (max_exp), Y (format_word) */
-#define iINTERP  0x0e	/* R = A + (X * (Y - A) >> 31)  ; saturation */
-#define iSKIP    0x0f	/* R = A (cc_reg), X (count), Y (cc_test) */
-
-/* GPRs */
-#define FXBUS(x)	(0x00 + (x))	/* x = 0x00 - 0x0f */
-#define EXTIN(x)	(0x10 + (x))	/* x = 0x00 - 0x0f */
-#define EXTOUT(x)	(0x20 + (x))	/* x = 0x00 - 0x0f physical outs -> FXWC low 16 bits */
-#define FXBUS2(x)	(0x30 + (x))	/* x = 0x00 - 0x0f copies of fx buses for capture -> FXWC high 16 bits */
-					/* NB: 0x31 and 0x32 are shared with Center/LFE on SB live 5.1 */
-
-#define C_00000000	0x40
-#define C_00000001	0x41
-#define C_00000002	0x42
-#define C_00000003	0x43
-#define C_00000004	0x44
-#define C_00000008	0x45
-#define C_00000010	0x46
-#define C_00000020	0x47
-#define C_00000100	0x48
-#define C_00010000	0x49
-#define C_00080000	0x4a
-#define C_10000000	0x4b
-#define C_20000000	0x4c
-#define C_40000000	0x4d
-#define C_80000000	0x4e
-#define C_7fffffff	0x4f
-#define C_ffffffff	0x50
-#define C_fffffffe	0x51
-#define C_c0000000	0x52
-#define C_4f1bbcdc	0x53
-#define C_5a7ef9db	0x54
-#define C_00100000	0x55		/* ?? */
-#define GPR_ACCU	0x56		/* ACCUM, accumulator */
-#define GPR_COND	0x57		/* CCR, condition register */
-#define GPR_NOISE0	0x58		/* noise source */
-#define GPR_NOISE1	0x59		/* noise source */
-#define GPR_IRQ		0x5a		/* IRQ register */
-#define GPR_DBAC	0x5b		/* TRAM Delay Base Address Counter */
-#define GPR(x)		(FXGPREGBASE + (x)) /* free GPRs: x = 0x00 - 0xff */
-#define ITRAM_DATA(x)	(TANKMEMDATAREGBASE + 0x00 + (x)) /* x = 0x00 - 0x7f */
-#define ETRAM_DATA(x)	(TANKMEMDATAREGBASE + 0x80 + (x)) /* x = 0x00 - 0x1f */
-#define ITRAM_ADDR(x)	(TANKMEMADDRREGBASE + 0x00 + (x)) /* x = 0x00 - 0x7f */
-#define ETRAM_ADDR(x)	(TANKMEMADDRREGBASE + 0x80 + (x)) /* x = 0x00 - 0x1f */
-
-#define A_ITRAM_DATA(x)	(TANKMEMDATAREGBASE + 0x00 + (x)) /* x = 0x00 - 0xbf */
-#define A_ETRAM_DATA(x)	(TANKMEMDATAREGBASE + 0xc0 + (x)) /* x = 0x00 - 0x3f */
-#define A_ITRAM_ADDR(x)	(TANKMEMADDRREGBASE + 0x00 + (x)) /* x = 0x00 - 0xbf */
-#define A_ETRAM_ADDR(x)	(TANKMEMADDRREGBASE + 0xc0 + (x)) /* x = 0x00 - 0x3f */
-#define A_ITRAM_CTL(x)	(A_TANKMEMCTLREGBASE + 0x00 + (x)) /* x = 0x00 - 0xbf */
-#define A_ETRAM_CTL(x)	(A_TANKMEMCTLREGBASE + 0xc0 + (x)) /* x = 0x00 - 0x3f */
-
-#define A_FXBUS(x)	(0x00 + (x))	/* x = 0x00 - 0x3f FX buses */
-#define A_EXTIN(x)	(0x40 + (x))	/* x = 0x00 - 0x0f physical ins */
-#define A_P16VIN(x)	(0x50 + (x))	/* x = 0x00 - 0x0f p16v ins (A2 only) "EMU32 inputs" */
-#define A_EXTOUT(x)	(0x60 + (x))	/* x = 0x00 - 0x1f physical outs -> A_FXWC1 0x79-7f unknown   */
-#define A_FXBUS2(x)	(0x80 + (x))	/* x = 0x00 - 0x1f extra outs used for EFX capture -> A_FXWC2 */
-#define A_EMU32OUTH(x)	(0xa0 + (x))	/* x = 0x00 - 0x0f "EMU32_OUT_10 - _1F" - ??? */
-#define A_EMU32OUTL(x)	(0xb0 + (x))	/* x = 0x00 - 0x0f "EMU32_OUT_1 - _F" - ??? */
-#define A3_EMU32IN(x)	(0x160 + (x))	/* x = 0x00 - 0x3f "EMU32_IN_00 - _3F" - Only when .device = 0x0008 */
-#define A3_EMU32OUT(x)	(0x1E0 + (x))	/* x = 0x00 - 0x0f "EMU32_OUT_00 - _3F" - Only when .device = 0x0008 */
-#define A_GPR(x)	(A_FXGPREGBASE + (x))
-
-/* cc_reg constants */
-#define CC_REG_NORMALIZED C_00000001
-#define CC_REG_BORROW	C_00000002
-#define CC_REG_MINUS	C_00000004
-#define CC_REG_ZERO	C_00000008
-#define CC_REG_SATURATE	C_00000010
-#define CC_REG_NONZERO	C_00000100
-
-/* FX buses */
-#define FXBUS_PCM_LEFT		0x00
-#define FXBUS_PCM_RIGHT		0x01
-#define FXBUS_PCM_LEFT_REAR	0x02
-#define FXBUS_PCM_RIGHT_REAR	0x03
-#define FXBUS_MIDI_LEFT		0x04
-#define FXBUS_MIDI_RIGHT	0x05
-#define FXBUS_PCM_CENTER	0x06
-#define FXBUS_PCM_LFE		0x07
-#define FXBUS_PCM_LEFT_FRONT	0x08
-#define FXBUS_PCM_RIGHT_FRONT	0x09
-#define FXBUS_MIDI_REVERB	0x0c
-#define FXBUS_MIDI_CHORUS	0x0d
-#define FXBUS_PCM_LEFT_SIDE	0x0e
-#define FXBUS_PCM_RIGHT_SIDE	0x0f
-#define FXBUS_PT_LEFT		0x14
-#define FXBUS_PT_RIGHT		0x15
-
-/* Inputs */
-#define EXTIN_AC97_L	   0x00	/* AC'97 capture channel - left */
-#define EXTIN_AC97_R	   0x01	/* AC'97 capture channel - right */
-#define EXTIN_SPDIF_CD_L   0x02	/* internal S/PDIF CD - onboard - left */
-#define EXTIN_SPDIF_CD_R   0x03	/* internal S/PDIF CD - onboard - right */
-#define EXTIN_ZOOM_L	   0x04	/* Zoom Video I2S - left */
-#define EXTIN_ZOOM_R	   0x05	/* Zoom Video I2S - right */
-#define EXTIN_TOSLINK_L	   0x06	/* LiveDrive - TOSLink Optical - left */
-#define EXTIN_TOSLINK_R    0x07	/* LiveDrive - TOSLink Optical - right */
-#define EXTIN_LINE1_L	   0x08	/* LiveDrive - Line/Mic 1 - left */
-#define EXTIN_LINE1_R	   0x09	/* LiveDrive - Line/Mic 1 - right */
-#define EXTIN_COAX_SPDIF_L 0x0a	/* LiveDrive - Coaxial S/PDIF - left */
-#define EXTIN_COAX_SPDIF_R 0x0b /* LiveDrive - Coaxial S/PDIF - right */
-#define EXTIN_LINE2_L	   0x0c	/* LiveDrive - Line/Mic 2 - left */
-#define EXTIN_LINE2_R	   0x0d	/* LiveDrive - Line/Mic 2 - right */
-
-/* Outputs */
-#define EXTOUT_AC97_L	   0x00	/* AC'97 playback channel - left */
-#define EXTOUT_AC97_R	   0x01	/* AC'97 playback channel - right */
-#define EXTOUT_TOSLINK_L   0x02	/* LiveDrive - TOSLink Optical - left */
-#define EXTOUT_TOSLINK_R   0x03	/* LiveDrive - TOSLink Optical - right */
-#define EXTOUT_AC97_CENTER 0x04	/* SB Live 5.1 - center */
-#define EXTOUT_AC97_LFE	   0x05 /* SB Live 5.1 - LFE */
-#define EXTOUT_HEADPHONE_L 0x06	/* LiveDrive - Headphone - left */
-#define EXTOUT_HEADPHONE_R 0x07	/* LiveDrive - Headphone - right */
-#define EXTOUT_REAR_L	   0x08	/* Rear channel - left */
-#define EXTOUT_REAR_R	   0x09	/* Rear channel - right */
-#define EXTOUT_ADC_CAP_L   0x0a	/* ADC Capture buffer - left */
-#define EXTOUT_ADC_CAP_R   0x0b	/* ADC Capture buffer - right */
-#define EXTOUT_MIC_CAP	   0x0c	/* MIC Capture buffer */
-#define EXTOUT_AC97_REAR_L 0x0d	/* SB Live 5.1 (c) 2003 - Rear Left */
-#define EXTOUT_AC97_REAR_R 0x0e	/* SB Live 5.1 (c) 2003 - Rear Right */
-#define EXTOUT_ACENTER	   0x11 /* Analog Center */
-#define EXTOUT_ALFE	   0x12 /* Analog LFE */
-
-/* Audigy Inputs */
-#define A_EXTIN_AC97_L		0x00	/* AC'97 capture channel - left */
-#define A_EXTIN_AC97_R		0x01	/* AC'97 capture channel - right */
-#define A_EXTIN_SPDIF_CD_L	0x02	/* digital CD left */
-#define A_EXTIN_SPDIF_CD_R	0x03	/* digital CD left */
-#define A_EXTIN_OPT_SPDIF_L     0x04    /* audigy drive Optical SPDIF - left */
-#define A_EXTIN_OPT_SPDIF_R     0x05    /*                              right */ 
-#define A_EXTIN_LINE2_L		0x08	/* audigy drive line2/mic2 - left */
-#define A_EXTIN_LINE2_R		0x09	/*                           right */
-#define A_EXTIN_ADC_L		0x0a    /* Philips ADC - left */
-#define A_EXTIN_ADC_R		0x0b    /*               right */
-#define A_EXTIN_AUX2_L		0x0c	/* audigy drive aux2 - left */
-#define A_EXTIN_AUX2_R		0x0d	/*                   - right */
-
-/* Audigiy Outputs */
-#define A_EXTOUT_FRONT_L	0x00	/* digital front left */
-#define A_EXTOUT_FRONT_R	0x01	/*               right */
-#define A_EXTOUT_CENTER		0x02	/* digital front center */
-#define A_EXTOUT_LFE		0x03	/* digital front lfe */
-#define A_EXTOUT_HEADPHONE_L	0x04	/* headphone audigy drive left */
-#define A_EXTOUT_HEADPHONE_R	0x05	/*                        right */
-#define A_EXTOUT_REAR_L		0x06	/* digital rear left */
-#define A_EXTOUT_REAR_R		0x07	/*              right */
-#define A_EXTOUT_AFRONT_L	0x08	/* analog front left */
-#define A_EXTOUT_AFRONT_R	0x09	/*              right */
-#define A_EXTOUT_ACENTER	0x0a	/* analog center */
-#define A_EXTOUT_ALFE		0x0b	/* analog LFE */
-#define A_EXTOUT_ASIDE_L	0x0c	/* analog side left  - Audigy 2 ZS */
-#define A_EXTOUT_ASIDE_R	0x0d	/*             right - Audigy 2 ZS */
-#define A_EXTOUT_AREAR_L	0x0e	/* analog rear left */
-#define A_EXTOUT_AREAR_R	0x0f	/*             right */
-#define A_EXTOUT_AC97_L		0x10	/* AC97 left (front) */
-#define A_EXTOUT_AC97_R		0x11	/*      right */
-#define A_EXTOUT_ADC_CAP_L	0x16	/* ADC capture buffer left */
-#define A_EXTOUT_ADC_CAP_R	0x17	/*                    right */
-#define A_EXTOUT_MIC_CAP	0x18	/* Mic capture buffer */
-
-/* Audigy constants */
-#define A_C_00000000	0xc0
-#define A_C_00000001	0xc1
-#define A_C_00000002	0xc2
-#define A_C_00000003	0xc3
-#define A_C_00000004	0xc4
-#define A_C_00000008	0xc5
-#define A_C_00000010	0xc6
-#define A_C_00000020	0xc7
-#define A_C_00000100	0xc8
-#define A_C_00010000	0xc9
-#define A_C_00000800	0xca
-#define A_C_10000000	0xcb
-#define A_C_20000000	0xcc
-#define A_C_40000000	0xcd
-#define A_C_80000000	0xce
-#define A_C_7fffffff	0xcf
-#define A_C_ffffffff	0xd0
-#define A_C_fffffffe	0xd1
-#define A_C_c0000000	0xd2
-#define A_C_4f1bbcdc	0xd3
-#define A_C_5a7ef9db	0xd4
-#define A_C_00100000	0xd5
-#define A_GPR_ACCU	0xd6		/* ACCUM, accumulator */
-#define A_GPR_COND	0xd7		/* CCR, condition register */
-#define A_GPR_NOISE0	0xd8		/* noise source */
-#define A_GPR_NOISE1	0xd9		/* noise source */
-#define A_GPR_IRQ	0xda		/* IRQ register */
-#define A_GPR_DBAC	0xdb		/* TRAM Delay Base Address Counter - internal */
-#define A_GPR_DBACE	0xde		/* TRAM Delay Base Address Counter - external */
-
-/* definitions for debug register */
-#define EMU10K1_DBG_ZC			0x80000000	/* zero tram counter */
-#define EMU10K1_DBG_SATURATION_OCCURED	0x02000000	/* saturation control */
-#define EMU10K1_DBG_SATURATION_ADDR	0x01ff0000	/* saturation address */
-#define EMU10K1_DBG_SINGLE_STEP		0x00008000	/* single step mode */
-#define EMU10K1_DBG_STEP		0x00004000	/* start single step */
-#define EMU10K1_DBG_CONDITION_CODE	0x00003e00	/* condition code */
-#define EMU10K1_DBG_SINGLE_STEP_ADDR	0x000001ff	/* single step address */
-
-/* tank memory address line */
-#ifndef __KERNEL__
-#define TANKMEMADDRREG_ADDR_MASK 0x000fffff	/* 20 bit tank address field			*/
-#define TANKMEMADDRREG_CLEAR	 0x00800000	/* Clear tank memory				*/
-#define TANKMEMADDRREG_ALIGN	 0x00400000	/* Align read or write relative to tank access	*/
-#define TANKMEMADDRREG_WRITE	 0x00200000	/* Write to tank memory				*/
-#define TANKMEMADDRREG_READ	 0x00100000	/* Read from tank memory			*/
-#endif
-
-struct snd_emu10k1_fx8010_info {
-	unsigned int internal_tram_size;	/* in samples */
-	unsigned int external_tram_size;	/* in samples */
-	char fxbus_names[16][32];		/* names of FXBUSes */
-	char extin_names[16][32];		/* names of external inputs */
-	char extout_names[32][32];		/* names of external outputs */
-	unsigned int gpr_controls;		/* count of GPR controls */
-};
-
-#define EMU10K1_GPR_TRANSLATION_NONE		0
-#define EMU10K1_GPR_TRANSLATION_TABLE100	1
-#define EMU10K1_GPR_TRANSLATION_BASS		2
-#define EMU10K1_GPR_TRANSLATION_TREBLE		3
-#define EMU10K1_GPR_TRANSLATION_ONOFF		4
-
-struct snd_emu10k1_fx8010_control_gpr {
-	struct snd_ctl_elem_id id;		/* full control ID definition */
-	unsigned int vcount;		/* visible count */
-	unsigned int count;		/* count of GPR (1..16) */
-	unsigned short gpr[32];		/* GPR number(s) */
-	unsigned int value[32];		/* initial values */
-	unsigned int min;		/* minimum range */
-	unsigned int max;		/* maximum range */
-	unsigned int translation;	/* translation type (EMU10K1_GPR_TRANSLATION*) */
-	const unsigned int *tlv;
-};
-
-/* old ABI without TLV support */
-struct snd_emu10k1_fx8010_control_old_gpr {
-	struct snd_ctl_elem_id id;
-	unsigned int vcount;
-	unsigned int count;
-	unsigned short gpr[32];
-	unsigned int value[32];
-	unsigned int min;
-	unsigned int max;
-	unsigned int translation;
-};
-
-struct snd_emu10k1_fx8010_code {
-	char name[128];
-
-	DECLARE_BITMAP(gpr_valid, 0x200); /* bitmask of valid initializers */
-	__u32 __user *gpr_map;		/* initializers */
-
-	unsigned int gpr_add_control_count; /* count of GPR controls to add/replace */
-	struct snd_emu10k1_fx8010_control_gpr __user *gpr_add_controls; /* GPR controls to add/replace */
-
-	unsigned int gpr_del_control_count; /* count of GPR controls to remove */
-	struct snd_ctl_elem_id __user *gpr_del_controls; /* IDs of GPR controls to remove */
-
-	unsigned int gpr_list_control_count; /* count of GPR controls to list */
-	unsigned int gpr_list_control_total; /* total count of GPR controls */
-	struct snd_emu10k1_fx8010_control_gpr __user *gpr_list_controls; /* listed GPR controls */
-
-	DECLARE_BITMAP(tram_valid, 0x100); /* bitmask of valid initializers */
-	__u32 __user *tram_data_map;	  /* data initializers */
-	__u32 __user *tram_addr_map;	  /* map initializers */
-
-	DECLARE_BITMAP(code_valid, 1024); /* bitmask of valid instructions */
-	__u32 __user *code;		  /* one instruction - 64 bits */
-};
-
-struct snd_emu10k1_fx8010_tram {
-	unsigned int address;		/* 31.bit == 1 -> external TRAM */
-	unsigned int size;		/* size in samples (4 bytes) */
-	unsigned int *samples;		/* pointer to samples (20-bit) */
-					/* NULL->clear memory */
-};
-
-struct snd_emu10k1_fx8010_pcm_rec {
-	unsigned int substream;		/* substream number */
-	unsigned int res1;		/* reserved */
-	unsigned int channels;		/* 16-bit channels count, zero = remove this substream */
-	unsigned int tram_start;	/* ring buffer position in TRAM (in samples) */
-	unsigned int buffer_size;	/* count of buffered samples */
-	unsigned short gpr_size;		/* GPR containing size of ringbuffer in samples (host) */
-	unsigned short gpr_ptr;		/* GPR containing current pointer in the ring buffer (host = reset, FX8010) */
-	unsigned short gpr_count;	/* GPR containing count of samples between two interrupts (host) */
-	unsigned short gpr_tmpcount;	/* GPR containing current count of samples to interrupt (host = set, FX8010) */
-	unsigned short gpr_trigger;	/* GPR containing trigger (activate) information (host) */
-	unsigned short gpr_running;	/* GPR containing info if PCM is running (FX8010) */
-	unsigned char pad;		/* reserved */
-	unsigned char etram[32];	/* external TRAM address & data (one per channel) */
-	unsigned int res2;		/* reserved */
-};
-
-#define SNDRV_EMU10K1_VERSION		SNDRV_PROTOCOL_VERSION(1, 0, 1)
-
-#define SNDRV_EMU10K1_IOCTL_INFO	_IOR ('H', 0x10, struct snd_emu10k1_fx8010_info)
-#define SNDRV_EMU10K1_IOCTL_CODE_POKE	_IOW ('H', 0x11, struct snd_emu10k1_fx8010_code)
-#define SNDRV_EMU10K1_IOCTL_CODE_PEEK	_IOWR('H', 0x12, struct snd_emu10k1_fx8010_code)
-#define SNDRV_EMU10K1_IOCTL_TRAM_SETUP	_IOW ('H', 0x20, int)
-#define SNDRV_EMU10K1_IOCTL_TRAM_POKE	_IOW ('H', 0x21, struct snd_emu10k1_fx8010_tram)
-#define SNDRV_EMU10K1_IOCTL_TRAM_PEEK	_IOWR('H', 0x22, struct snd_emu10k1_fx8010_tram)
-#define SNDRV_EMU10K1_IOCTL_PCM_POKE	_IOW ('H', 0x30, struct snd_emu10k1_fx8010_pcm_rec)
-#define SNDRV_EMU10K1_IOCTL_PCM_PEEK	_IOWR('H', 0x31, struct snd_emu10k1_fx8010_pcm_rec)
-#define SNDRV_EMU10K1_IOCTL_PVERSION	_IOR ('H', 0x40, int)
-#define SNDRV_EMU10K1_IOCTL_STOP	_IO  ('H', 0x80)
-#define SNDRV_EMU10K1_IOCTL_CONTINUE	_IO  ('H', 0x81)
-#define SNDRV_EMU10K1_IOCTL_ZERO_TRAM_COUNTER _IO ('H', 0x82)
-#define SNDRV_EMU10K1_IOCTL_SINGLE_STEP	_IOW ('H', 0x83, int)
-#define SNDRV_EMU10K1_IOCTL_DBG_READ	_IOR ('H', 0x84, int)
-
-/* typedefs for compatibility to user-space */
-typedef struct snd_emu10k1_fx8010_info emu10k1_fx8010_info_t;
-typedef struct snd_emu10k1_fx8010_control_gpr emu10k1_fx8010_control_gpr_t;
-typedef struct snd_emu10k1_fx8010_code emu10k1_fx8010_code_t;
-typedef struct snd_emu10k1_fx8010_tram emu10k1_fx8010_tram_t;
-typedef struct snd_emu10k1_fx8010_pcm_rec emu10k1_fx8010_pcm_t;
-
 #endif	/* __SOUND_EMU10K1_H */
diff --git a/include/sound/hdsp.h b/include/sound/hdsp.h
deleted file mode 100644
index 0909a3843479..000000000000
--- a/include/sound/hdsp.h
+++ /dev/null
@@ -1,110 +0,0 @@
-#ifndef __SOUND_HDSP_H
-#define __SOUND_HDSP_H
-
-/*
- *   Copyright (C) 2003 Thomas Charbonnel (thomas@undata.org)
- *    
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program; if not, write to the Free Software
- *   Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/types.h>
-
-#define HDSP_MATRIX_MIXER_SIZE 2048
-
-enum HDSP_IO_Type {
-	Digiface,
-	Multiface,
-	H9652,
-	H9632,
-	RPM,
-	Undefined,
-};
-
-struct hdsp_peak_rms {
-	__u32 input_peaks[26];
-	__u32 playback_peaks[26];
-	__u32 output_peaks[28];
-	__u64 input_rms[26];
-	__u64 playback_rms[26];
-	/* These are only used for H96xx cards */
-	__u64 output_rms[26];
-};
-
-#define SNDRV_HDSP_IOCTL_GET_PEAK_RMS _IOR('H', 0x40, struct hdsp_peak_rms)
-
-struct hdsp_config_info {
-	unsigned char pref_sync_ref;
-	unsigned char wordclock_sync_check;
-	unsigned char spdif_sync_check;
-	unsigned char adatsync_sync_check;
-	unsigned char adat_sync_check[3];
-	unsigned char spdif_in;
-	unsigned char spdif_out;
-	unsigned char spdif_professional;
-	unsigned char spdif_emphasis;
-	unsigned char spdif_nonaudio;
-	unsigned int spdif_sample_rate;
-	unsigned int system_sample_rate;
-	unsigned int autosync_sample_rate;
-	unsigned char system_clock_mode;
-	unsigned char clock_source;
-	unsigned char autosync_ref;
-	unsigned char line_out;
-	unsigned char passthru; 
-	unsigned char da_gain;
-	unsigned char ad_gain;
-	unsigned char phone_gain;
-	unsigned char xlr_breakout_cable;
-	unsigned char analog_extension_board;
-};
-
-#define SNDRV_HDSP_IOCTL_GET_CONFIG_INFO _IOR('H', 0x41, struct hdsp_config_info)
-
-struct hdsp_firmware {
-	void __user *firmware_data;	/* 24413 x 4 bytes */
-};
-
-#define SNDRV_HDSP_IOCTL_UPLOAD_FIRMWARE _IOW('H', 0x42, struct hdsp_firmware)
-
-struct hdsp_version {
-	enum HDSP_IO_Type io_type;
-	unsigned short firmware_rev;
-};
-
-#define SNDRV_HDSP_IOCTL_GET_VERSION _IOR('H', 0x43, struct hdsp_version)
-
-struct hdsp_mixer {
-	unsigned short matrix[HDSP_MATRIX_MIXER_SIZE];
-};
-
-#define SNDRV_HDSP_IOCTL_GET_MIXER _IOR('H', 0x44, struct hdsp_mixer)
-
-struct hdsp_9632_aeb {
-	int aebi;
-	int aebo;
-};
-
-#define SNDRV_HDSP_IOCTL_GET_9632_AEB _IOR('H', 0x45, struct hdsp_9632_aeb)
-
-/* typedefs for compatibility to user-space */
-typedef enum HDSP_IO_Type HDSP_IO_Type;
-typedef struct hdsp_peak_rms hdsp_peak_rms_t;
-typedef struct hdsp_config_info hdsp_config_info_t;
-typedef struct hdsp_firmware hdsp_firmware_t;
-typedef struct hdsp_version hdsp_version_t;
-typedef struct hdsp_mixer hdsp_mixer_t;
-typedef struct hdsp_9632_aeb hdsp_9632_aeb_t;
-
-#endif /* __SOUND_HDSP_H */
diff --git a/include/sound/hdspm.h b/include/sound/hdspm.h
deleted file mode 100644
index 1f59ea2a4a76..000000000000
--- a/include/sound/hdspm.h
+++ /dev/null
@@ -1,229 +0,0 @@
-#ifndef __SOUND_HDSPM_H
-#define __SOUND_HDSPM_H
-/*
- *   Copyright (C) 2003 Winfried Ritsch (IEM)
- *   based on hdsp.h from Thomas Charbonnel (thomas@undata.org)
- *
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program; if not, write to the Free Software
- *   Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-/* Maximum channels is 64 even on 56Mode you have 64playbacks to matrix */
-#define HDSPM_MAX_CHANNELS      64
-
-enum hdspm_io_type {
-	MADI,
-	MADIface,
-	AIO,
-	AES32,
-	RayDAT
-};
-
-enum hdspm_speed {
-	ss,
-	ds,
-	qs
-};
-
-/* -------------------- IOCTL Peak/RMS Meters -------------------- */
-
-struct hdspm_peak_rms {
-	uint32_t input_peaks[64];
-	uint32_t playback_peaks[64];
-	uint32_t output_peaks[64];
-
-	uint64_t input_rms[64];
-	uint64_t playback_rms[64];
-	uint64_t output_rms[64];
-
-	uint8_t speed; /* enum {ss, ds, qs} */
-	int status2;
-};
-
-#define SNDRV_HDSPM_IOCTL_GET_PEAK_RMS \
-	_IOR('H', 0x42, struct hdspm_peak_rms)
-
-/* ------------ CONFIG block IOCTL ---------------------- */
-
-struct hdspm_config {
-	unsigned char pref_sync_ref;
-	unsigned char wordclock_sync_check;
-	unsigned char madi_sync_check;
-	unsigned int system_sample_rate;
-	unsigned int autosync_sample_rate;
-	unsigned char system_clock_mode;
-	unsigned char clock_source;
-	unsigned char autosync_ref;
-	unsigned char line_out;
-	unsigned int passthru;
-	unsigned int analog_out;
-};
-
-#define SNDRV_HDSPM_IOCTL_GET_CONFIG \
-	_IOR('H', 0x41, struct hdspm_config)
-
-/**
- * If there's a TCO (TimeCode Option) board installed,
- * there are further options and status data available.
- * The hdspm_ltc structure contains the current SMPTE
- * timecode and some status information and can be
- * obtained via SNDRV_HDSPM_IOCTL_GET_LTC or in the
- * hdspm_status struct.
- **/
-
-enum hdspm_ltc_format {
-	format_invalid,
-	fps_24,
-	fps_25,
-	fps_2997,
-	fps_30
-};
-
-enum hdspm_ltc_frame {
-	frame_invalid,
-	drop_frame,
-	full_frame
-};
-
-enum hdspm_ltc_input_format {
-	ntsc,
-	pal,
-	no_video
-};
-
-struct hdspm_ltc {
-	unsigned int ltc;
-
-	enum hdspm_ltc_format format;
-	enum hdspm_ltc_frame frame;
-	enum hdspm_ltc_input_format input_format;
-};
-
-#define SNDRV_HDSPM_IOCTL_GET_LTC _IOR('H', 0x46, struct hdspm_mixer_ioctl)
-
-/**
- * The status data reflects the device's current state
- * as determined by the card's configuration and
- * connection status.
- **/
-
-enum hdspm_sync {
-	hdspm_sync_no_lock = 0,
-	hdspm_sync_lock = 1,
-	hdspm_sync_sync = 2
-};
-
-enum hdspm_madi_input {
-	hdspm_input_optical = 0,
-	hdspm_input_coax = 1
-};
-
-enum hdspm_madi_channel_format {
-	hdspm_format_ch_64 = 0,
-	hdspm_format_ch_56 = 1
-};
-
-enum hdspm_madi_frame_format {
-	hdspm_frame_48 = 0,
-	hdspm_frame_96 = 1
-};
-
-enum hdspm_syncsource {
-	syncsource_wc = 0,
-	syncsource_madi = 1,
-	syncsource_tco = 2,
-	syncsource_sync = 3,
-	syncsource_none = 4
-};
-
-struct hdspm_status {
-	uint8_t card_type; /* enum hdspm_io_type */
-	enum hdspm_syncsource autosync_source;
-
-	uint64_t card_clock;
-	uint32_t master_period;
-
-	union {
-		struct {
-			uint8_t sync_wc; /* enum hdspm_sync */
-			uint8_t sync_madi; /* enum hdspm_sync */
-			uint8_t sync_tco; /* enum hdspm_sync */
-			uint8_t sync_in; /* enum hdspm_sync */
-			uint8_t madi_input; /* enum hdspm_madi_input */
-			uint8_t channel_format; /* enum hdspm_madi_channel_format */
-			uint8_t frame_format; /* enum hdspm_madi_frame_format */
-		} madi;
-	} card_specific;
-};
-
-#define SNDRV_HDSPM_IOCTL_GET_STATUS \
-	_IOR('H', 0x47, struct hdspm_status)
-
-/**
- * Get information about the card and its add-ons.
- **/
-
-#define HDSPM_ADDON_TCO 1
-
-struct hdspm_version {
-	uint8_t card_type; /* enum hdspm_io_type */
-	char cardname[20];
-	unsigned int serial;
-	unsigned short firmware_rev;
-	int addons;
-};
-
-#define SNDRV_HDSPM_IOCTL_GET_VERSION _IOR('H', 0x48, struct hdspm_version)
-
-/* ------------- get Matrix Mixer IOCTL --------------- */
-
-/* MADI mixer: 64inputs+64playback in 64outputs = 8192 => *4Byte =
- * 32768 Bytes
- */
-
-/* organisation is 64 channelfader in a continuous memory block */
-/* equivalent to hardware definition, maybe for future feature of mmap of
- * them
- */
-/* each of 64 outputs has 64 infader and 64 outfader:
-   Ins to Outs mixer[out].in[in], Outstreams to Outs mixer[out].pb[pb] */
-
-#define HDSPM_MIXER_CHANNELS HDSPM_MAX_CHANNELS
-
-struct hdspm_channelfader {
-	unsigned int in[HDSPM_MIXER_CHANNELS];
-	unsigned int pb[HDSPM_MIXER_CHANNELS];
-};
-
-struct hdspm_mixer {
-	struct hdspm_channelfader ch[HDSPM_MIXER_CHANNELS];
-};
-
-struct hdspm_mixer_ioctl {
-	struct hdspm_mixer *mixer;
-};
-
-/* use indirect access due to the limit of ioctl bit size */
-#define SNDRV_HDSPM_IOCTL_GET_MIXER _IOR('H', 0x44, struct hdspm_mixer_ioctl)
-
-/* typedefs for compatibility to user-space */
-typedef struct hdspm_peak_rms hdspm_peak_rms_t;
-typedef struct hdspm_config_info hdspm_config_info_t;
-typedef struct hdspm_version hdspm_version_t;
-typedef struct hdspm_channelfader snd_hdspm_channelfader_t;
-typedef struct hdspm_mixer hdspm_mixer_t;
-
-
-#endif
diff --git a/include/sound/sb16_csp.h b/include/sound/sb16_csp.h
index 7e950560e591..c7c7788005e4 100644
--- a/include/sound/sb16_csp.h
+++ b/include/sound/sb16_csp.h
@@ -1,6 +1,3 @@
-#ifndef __SOUND_SB16_CSP_H
-#define __SOUND_SB16_CSP_H
-
 /*
  *  Copyright (c) 1999 by Uros Bizjak <uros@kss-loka.si>
  *                        Takashi Iwai <tiwai@suse.de>
@@ -22,106 +19,13 @@
  *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  *
  */
+#ifndef __SOUND_SB16_CSP_H
+#define __SOUND_SB16_CSP_H
 
-/* CSP modes */
-#define SNDRV_SB_CSP_MODE_NONE		0x00
-#define SNDRV_SB_CSP_MODE_DSP_READ	0x01	/* Record from DSP */
-#define SNDRV_SB_CSP_MODE_DSP_WRITE	0x02	/* Play to DSP */
-#define SNDRV_SB_CSP_MODE_QSOUND		0x04	/* QSound */
-
-/* CSP load flags */
-#define SNDRV_SB_CSP_LOAD_FROMUSER	0x01
-#define SNDRV_SB_CSP_LOAD_INITBLOCK	0x02
-
-/* CSP sample width */
-#define SNDRV_SB_CSP_SAMPLE_8BIT		0x01
-#define SNDRV_SB_CSP_SAMPLE_16BIT		0x02
-
-/* CSP channels */
-#define SNDRV_SB_CSP_MONO			0x01
-#define SNDRV_SB_CSP_STEREO		0x02
-
-/* CSP rates */
-#define SNDRV_SB_CSP_RATE_8000		0x01
-#define SNDRV_SB_CSP_RATE_11025		0x02
-#define SNDRV_SB_CSP_RATE_22050		0x04
-#define SNDRV_SB_CSP_RATE_44100		0x08
-#define SNDRV_SB_CSP_RATE_ALL		0x0f
-
-/* CSP running state */
-#define SNDRV_SB_CSP_ST_IDLE		0x00
-#define SNDRV_SB_CSP_ST_LOADED		0x01
-#define SNDRV_SB_CSP_ST_RUNNING		0x02
-#define SNDRV_SB_CSP_ST_PAUSED		0x04
-#define SNDRV_SB_CSP_ST_AUTO		0x08
-#define SNDRV_SB_CSP_ST_QSOUND		0x10
-
-/* maximum QSound value (180 degrees right) */
-#define SNDRV_SB_CSP_QSOUND_MAX_RIGHT	0x20
-
-/* maximum microcode RIFF file size */
-#define SNDRV_SB_CSP_MAX_MICROCODE_FILE_SIZE	0x3000
-
-/* microcode header */
-struct snd_sb_csp_mc_header {
-	char codec_name[16];		/* id name of codec */
-	unsigned short func_req;	/* requested function */
-};
-
-/* microcode to be loaded */
-struct snd_sb_csp_microcode {
-	struct snd_sb_csp_mc_header info;
-	unsigned char data[SNDRV_SB_CSP_MAX_MICROCODE_FILE_SIZE];
-};
-
-/* start CSP with sample_width in mono/stereo */
-struct snd_sb_csp_start {
-	int sample_width;	/* sample width, look above */
-	int channels;		/* channels, look above */
-};
-
-/* CSP information */
-struct snd_sb_csp_info {
-	char codec_name[16];		/* id name of codec */
-	unsigned short func_nr;		/* function number */
-	unsigned int acc_format;	/* accepted PCM formats */
-	unsigned short acc_channels;	/* accepted channels */
-	unsigned short acc_width;	/* accepted sample width */
-	unsigned short acc_rates;	/* accepted sample rates */
-	unsigned short csp_mode;	/* CSP mode, see above */
-	unsigned short run_channels;	/* current channels  */
-	unsigned short run_width;	/* current sample width */
-	unsigned short version;		/* version id: 0x10 - 0x1f */
-	unsigned short state;		/* state bits */
-};
-
-/* HWDEP controls */
-/* get CSP information */
-#define SNDRV_SB_CSP_IOCTL_INFO		_IOR('H', 0x10, struct snd_sb_csp_info)
-/* load microcode to CSP */
-/* NOTE: struct snd_sb_csp_microcode overflows the max size (13 bits)
- * defined for some architectures like MIPS, and it leads to build errors.
- * (x86 and co have 14-bit size, thus it's valid, though.)
- * As a workaround for skipping the size-limit check, here we don't use the
- * normal _IOW() macro but _IOC() with the manual argument.
- */
-#define SNDRV_SB_CSP_IOCTL_LOAD_CODE	\
-	_IOC(_IOC_WRITE, 'H', 0x11, sizeof(struct snd_sb_csp_microcode))
-/* unload microcode from CSP */
-#define SNDRV_SB_CSP_IOCTL_UNLOAD_CODE	_IO('H', 0x12)
-/* start CSP */
-#define SNDRV_SB_CSP_IOCTL_START		_IOW('H', 0x13, struct snd_sb_csp_start)
-/* stop CSP */
-#define SNDRV_SB_CSP_IOCTL_STOP		_IO('H', 0x14)
-/* pause CSP and DMA transfer */
-#define SNDRV_SB_CSP_IOCTL_PAUSE		_IO('H', 0x15)
-/* restart CSP and DMA transfer */
-#define SNDRV_SB_CSP_IOCTL_RESTART	_IO('H', 0x16)
-
-#ifdef __KERNEL__
 #include <sound/sb.h>
 #include <sound/hwdep.h>
 #include <linux/firmware.h>
+#include <uapi/sound/sb16_csp.h>
 
 struct snd_sb_csp;
 
@@ -183,6 +87,4 @@ struct snd_sb_csp {
 };
 
 int snd_sb_csp_new(struct snd_sb *chip, int device, struct snd_hwdep ** rhwdep);
-#endif
-
 #endif /* __SOUND_SB16_CSP */
diff --git a/include/sound/sfnt_info.h b/include/sound/sfnt_info.h
deleted file mode 100644
index 1bce7fd1725f..000000000000
--- a/include/sound/sfnt_info.h
+++ /dev/null
@@ -1,212 +0,0 @@
-#ifndef __SOUND_SFNT_INFO_H
-#define __SOUND_SFNT_INFO_H
-
-/*
- *  Patch record compatible with AWE driver on OSS
- *
- *  Copyright (C) 1999-2000 Takashi Iwai
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program; if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
- */
-
-#include <sound/asound.h>
-
-/*
- * patch information record
- */
-
-#ifdef SNDRV_BIG_ENDIAN
-#define SNDRV_OSS_PATCHKEY(id) (0xfd00|id)
-#else
-#define SNDRV_OSS_PATCHKEY(id) ((id<<8)|0xfd)
-#endif
-
-/* patch interface header: 16 bytes */
-struct soundfont_patch_info {
-	unsigned short key;		/* use the key below */
-#define SNDRV_OSS_SOUNDFONT_PATCH		SNDRV_OSS_PATCHKEY(0x07)
-
-	short device_no;		/* synthesizer number */
-	unsigned short sf_id;		/* file id (should be zero) */
-	short optarg;			/* optional argument */
-	int len;			/* data length (without this header) */
-
-	short type;			/* patch operation type */
-#define SNDRV_SFNT_LOAD_INFO		0	/* awe_voice_rec */
-#define SNDRV_SFNT_LOAD_DATA		1	/* awe_sample_info */
-#define SNDRV_SFNT_OPEN_PATCH	2	/* awe_open_parm */
-#define SNDRV_SFNT_CLOSE_PATCH	3	/* none */
-	/* 4 is obsolete */
-#define SNDRV_SFNT_REPLACE_DATA	5	/* awe_sample_info (optarg=#channels)*/
-#define SNDRV_SFNT_MAP_PRESET	6	/* awe_voice_map */
-	/* 7 is not used */
-#define SNDRV_SFNT_PROBE_DATA		8	/* optarg=sample */
-#define SNDRV_SFNT_REMOVE_INFO		9	/* optarg=(bank<<8)|instr */
-
-	short reserved;			/* word alignment data */
-
-	/* the actual patch data begins after this */
-};
-
-
-/*
- * open patch
- */
-
-#define SNDRV_SFNT_PATCH_NAME_LEN	32
-
-struct soundfont_open_parm {
-	unsigned short type;		/* sample type */
-#define SNDRV_SFNT_PAT_TYPE_MISC	0
-#define SNDRV_SFNT_PAT_TYPE_GUS	6
-#define SNDRV_SFNT_PAT_TYPE_MAP	7
-#define SNDRV_SFNT_PAT_LOCKED	0x100	/* lock the samples */
-#define SNDRV_SFNT_PAT_SHARED	0x200	/* sample is shared */
-
-	short reserved;
-	char name[SNDRV_SFNT_PATCH_NAME_LEN];
-};
-
-
-/*
- * raw voice information record
- */
-
-/* wave table envelope & effect parameters to control EMU8000 */
-struct soundfont_voice_parm {
-	unsigned short moddelay;	/* modulation delay (0x8000) */
-	unsigned short modatkhld;	/* modulation attack & hold time (0x7f7f) */
-	unsigned short moddcysus;	/* modulation decay & sustain (0x7f7f) */
-	unsigned short modrelease;	/* modulation release time (0x807f) */
-	short modkeyhold, modkeydecay;	/* envelope change per key (not used) */
-	unsigned short voldelay;	/* volume delay (0x8000) */
-	unsigned short volatkhld;	/* volume attack & hold time (0x7f7f) */
-	unsigned short voldcysus;	/* volume decay & sustain (0x7f7f) */
-	unsigned short volrelease;	/* volume release time (0x807f) */
-	short volkeyhold, volkeydecay;	/* envelope change per key (not used) */
-	unsigned short lfo1delay;	/* LFO1 delay (0x8000) */
-	unsigned short lfo2delay;	/* LFO2 delay (0x8000) */
-	unsigned short pefe;		/* modulation pitch & cutoff (0x0000) */
-	unsigned short fmmod;		/* LFO1 pitch & cutoff (0x0000) */
-	unsigned short tremfrq;		/* LFO1 volume & freq (0x0000) */
-	unsigned short fm2frq2;		/* LFO2 pitch & freq (0x0000) */
-	unsigned char cutoff;		/* initial cutoff (0xff) */
-	unsigned char filterQ;		/* initial filter Q [0-15] (0x0) */
-	unsigned char chorus;		/* chorus send (0x00) */
-	unsigned char reverb;		/* reverb send (0x00) */
-	unsigned short reserved[4];	/* not used */
-};
-
-
-/* wave table parameters: 92 bytes */
-struct soundfont_voice_info {
-	unsigned short sf_id;		/* file id (should be zero) */
-	unsigned short sample;		/* sample id */
-	int start, end;			/* sample offset correction */
-	int loopstart, loopend;		/* loop offset correction */
-	short rate_offset;		/* sample rate pitch offset */
-	unsigned short mode;		/* sample mode */
-#define SNDRV_SFNT_MODE_ROMSOUND		0x8000
-#define SNDRV_SFNT_MODE_STEREO		1
-#define SNDRV_SFNT_MODE_LOOPING		2
-#define SNDRV_SFNT_MODE_NORELEASE		4	/* obsolete */
-#define SNDRV_SFNT_MODE_INIT_PARM		8
-
-	short root;			/* midi root key */
-	short tune;			/* pitch tuning (in cents) */
-	unsigned char low, high;	/* key note range */
-	unsigned char vellow, velhigh;	/* velocity range */
-	signed char fixkey, fixvel;	/* fixed key, velocity */
-	signed char pan, fixpan;	/* panning, fixed panning */
-	short exclusiveClass;		/* exclusive class (0 = none) */
-	unsigned char amplitude;	/* sample volume (127 max) */
-	unsigned char attenuation;	/* attenuation (0.375dB) */
-	short scaleTuning;		/* pitch scale tuning(%), normally 100 */
-	struct soundfont_voice_parm parm;	/* voice envelope parameters */
-	unsigned short sample_mode;	/* sample mode_flag (set by driver) */
-};
-
-
-/* instrument info header: 4 bytes */
-struct soundfont_voice_rec_hdr {
-	unsigned char bank;		/* midi bank number */
-	unsigned char instr;		/* midi preset number */
-	char nvoices;			/* number of voices */
-	char write_mode;		/* write mode; normally 0 */
-#define SNDRV_SFNT_WR_APPEND		0	/* append anyway */
-#define SNDRV_SFNT_WR_EXCLUSIVE		1	/* skip if already exists */
-#define SNDRV_SFNT_WR_REPLACE		2	/* replace if already exists */
-};
-
-
-/*
- * sample wave information
- */
-
-/* wave table sample header: 32 bytes */
-struct soundfont_sample_info {
-	unsigned short sf_id;		/* file id (should be zero) */
-	unsigned short sample;		/* sample id */
-	int start, end;			/* start & end offset */
-	int loopstart, loopend;		/* loop start & end offset */
-	int size;			/* size (0 = ROM) */
-	short dummy;			/* not used */
-	unsigned short mode_flags;	/* mode flags */
-#define SNDRV_SFNT_SAMPLE_8BITS		1	/* wave data is 8bits */
-#define SNDRV_SFNT_SAMPLE_UNSIGNED	2	/* wave data is unsigned */
-#define SNDRV_SFNT_SAMPLE_NO_BLANK	4	/* no blank loop is attached */
-#define SNDRV_SFNT_SAMPLE_SINGLESHOT	8	/* single-shot w/o loop */
-#define SNDRV_SFNT_SAMPLE_BIDIR_LOOP	16	/* bidirectional looping */
-#define SNDRV_SFNT_SAMPLE_STEREO_LEFT	32	/* stereo left sound */
-#define SNDRV_SFNT_SAMPLE_STEREO_RIGHT	64	/* stereo right sound */
-#define SNDRV_SFNT_SAMPLE_REVERSE_LOOP	128	/* reverse looping */
-	unsigned int truesize;		/* used memory size (set by driver) */
-};
-
-
-/*
- * voice preset mapping (aliasing)
- */
-
-struct soundfont_voice_map {
-	int map_bank, map_instr, map_key;	/* key = -1 means all keys */
-	int src_bank, src_instr, src_key;
-};
-
-
-/*
- * ioctls for hwdep
- */
-
-#define SNDRV_EMUX_HWDEP_NAME	"Emux WaveTable"
-
-#define SNDRV_EMUX_VERSION	((1 << 16) | (0 << 8) | 0)	/* 1.0.0 */
-
-struct snd_emux_misc_mode {
-	int port;	/* -1 = all */
-	int mode;
-	int value;
-	int value2;	/* reserved */
-};
-
-#define SNDRV_EMUX_IOCTL_VERSION	_IOR('H', 0x80, unsigned int)
-#define SNDRV_EMUX_IOCTL_LOAD_PATCH	_IOWR('H', 0x81, struct soundfont_patch_info)
-#define SNDRV_EMUX_IOCTL_RESET_SAMPLES	_IO('H', 0x82)
-#define SNDRV_EMUX_IOCTL_REMOVE_LAST_SAMPLES _IO('H', 0x83)
-#define SNDRV_EMUX_IOCTL_MEM_AVAIL	_IOW('H', 0x84, int)
-#define SNDRV_EMUX_IOCTL_MISC_MODE	_IOWR('H', 0x84, struct snd_emux_misc_mode)
-
-#endif /* __SOUND_SFNT_INFO_H */
diff --git a/include/uapi/sound/Kbuild b/include/uapi/sound/Kbuild
index aafaa5aa54d4..0f7d279ebde3 100644
--- a/include/uapi/sound/Kbuild
+++ b/include/uapi/sound/Kbuild
@@ -1 +1,11 @@
 # UAPI Header export list
+header-y += asequencer.h
+header-y += asound.h
+header-y += asound_fm.h
+header-y += compress_offload.h
+header-y += compress_params.h
+header-y += emu10k1.h
+header-y += hdsp.h
+header-y += hdspm.h
+header-y += sb16_csp.h
+header-y += sfnt_info.h
diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h
new file mode 100644
index 000000000000..09c8a00ea503
--- /dev/null
+++ b/include/uapi/sound/asequencer.h
@@ -0,0 +1,614 @@
+/*
+ *  Main header file for the ALSA sequencer
+ *  Copyright (c) 1998-1999 by Frank van de Pol <fvdpol@coil.demon.nl>
+ *            (c) 1998-1999 by Jaroslav Kysela <perex@perex.cz>
+ *
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program; if not, write to the Free Software
+ *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ */
+#ifndef _UAPI__SOUND_ASEQUENCER_H
+#define _UAPI__SOUND_ASEQUENCER_H
+
+
+/** version of the sequencer */
+#define SNDRV_SEQ_VERSION SNDRV_PROTOCOL_VERSION (1, 0, 1)
+
+/**
+ * definition of sequencer event types
+ */
+
+/** system messages
+ * event data type = #snd_seq_result
+ */
+#define SNDRV_SEQ_EVENT_SYSTEM		0
+#define SNDRV_SEQ_EVENT_RESULT		1
+
+/** note messages (channel specific)
+ * event data type = #snd_seq_ev_note
+ */
+#define SNDRV_SEQ_EVENT_NOTE		5
+#define SNDRV_SEQ_EVENT_NOTEON		6
+#define SNDRV_SEQ_EVENT_NOTEOFF		7
+#define SNDRV_SEQ_EVENT_KEYPRESS	8
+	
+/** control messages (channel specific)
+ * event data type = #snd_seq_ev_ctrl
+ */
+#define SNDRV_SEQ_EVENT_CONTROLLER	10
+#define SNDRV_SEQ_EVENT_PGMCHANGE	11
+#define SNDRV_SEQ_EVENT_CHANPRESS	12
+#define SNDRV_SEQ_EVENT_PITCHBEND	13	/**< from -8192 to 8191 */
+#define SNDRV_SEQ_EVENT_CONTROL14	14	/**< 14 bit controller value */
+#define SNDRV_SEQ_EVENT_NONREGPARAM	15	/**< 14 bit NRPN address + 14 bit unsigned value */
+#define SNDRV_SEQ_EVENT_REGPARAM	16	/**< 14 bit RPN address + 14 bit unsigned value */
+
+/** synchronisation messages
+ * event data type = #snd_seq_ev_ctrl
+ */
+#define SNDRV_SEQ_EVENT_SONGPOS		20	/* Song Position Pointer with LSB and MSB values */
+#define SNDRV_SEQ_EVENT_SONGSEL		21	/* Song Select with song ID number */
+#define SNDRV_SEQ_EVENT_QFRAME		22	/* midi time code quarter frame */
+#define SNDRV_SEQ_EVENT_TIMESIGN	23	/* SMF Time Signature event */
+#define SNDRV_SEQ_EVENT_KEYSIGN		24	/* SMF Key Signature event */
+	        
+/** timer messages
+ * event data type = snd_seq_ev_queue_control
+ */
+#define SNDRV_SEQ_EVENT_START		30	/* midi Real Time Start message */
+#define SNDRV_SEQ_EVENT_CONTINUE	31	/* midi Real Time Continue message */
+#define SNDRV_SEQ_EVENT_STOP		32	/* midi Real Time Stop message */	
+#define	SNDRV_SEQ_EVENT_SETPOS_TICK	33	/* set tick queue position */
+#define SNDRV_SEQ_EVENT_SETPOS_TIME	34	/* set realtime queue position */
+#define SNDRV_SEQ_EVENT_TEMPO		35	/* (SMF) Tempo event */
+#define SNDRV_SEQ_EVENT_CLOCK		36	/* midi Real Time Clock message */
+#define SNDRV_SEQ_EVENT_TICK		37	/* midi Real Time Tick message */
+#define SNDRV_SEQ_EVENT_QUEUE_SKEW	38	/* skew queue tempo */
+
+/** others
+ * event data type = none
+ */
+#define SNDRV_SEQ_EVENT_TUNE_REQUEST	40	/* tune request */
+#define SNDRV_SEQ_EVENT_RESET		41	/* reset to power-on state */
+#define SNDRV_SEQ_EVENT_SENSING		42	/* "active sensing" event */
+
+/** echo back, kernel private messages
+ * event data type = any type
+ */
+#define SNDRV_SEQ_EVENT_ECHO		50	/* echo event */
+#define SNDRV_SEQ_EVENT_OSS		51	/* OSS raw event */
+
+/** system status messages (broadcast for subscribers)
+ * event data type = snd_seq_addr
+ */
+#define SNDRV_SEQ_EVENT_CLIENT_START	60	/* new client has connected */
+#define SNDRV_SEQ_EVENT_CLIENT_EXIT	61	/* client has left the system */
+#define SNDRV_SEQ_EVENT_CLIENT_CHANGE	62	/* client status/info has changed */
+#define SNDRV_SEQ_EVENT_PORT_START	63	/* new port was created */
+#define SNDRV_SEQ_EVENT_PORT_EXIT	64	/* port was deleted from system */
+#define SNDRV_SEQ_EVENT_PORT_CHANGE	65	/* port status/info has changed */
+
+/** port connection changes
+ * event data type = snd_seq_connect
+ */
+#define SNDRV_SEQ_EVENT_PORT_SUBSCRIBED	66	/* ports connected */
+#define SNDRV_SEQ_EVENT_PORT_UNSUBSCRIBED 67	/* ports disconnected */
+
+/* 70-89:  synthesizer events - obsoleted */
+
+/** user-defined events with fixed length
+ * event data type = any
+ */
+#define SNDRV_SEQ_EVENT_USR0		90
+#define SNDRV_SEQ_EVENT_USR1		91
+#define SNDRV_SEQ_EVENT_USR2		92
+#define SNDRV_SEQ_EVENT_USR3		93
+#define SNDRV_SEQ_EVENT_USR4		94
+#define SNDRV_SEQ_EVENT_USR5		95
+#define SNDRV_SEQ_EVENT_USR6		96
+#define SNDRV_SEQ_EVENT_USR7		97
+#define SNDRV_SEQ_EVENT_USR8		98
+#define SNDRV_SEQ_EVENT_USR9		99
+
+/* 100-118: instrument layer - obsoleted */
+/* 119-129: reserved */
+
+/* 130-139: variable length events
+ * event data type = snd_seq_ev_ext
+ * (SNDRV_SEQ_EVENT_LENGTH_VARIABLE must be set)
+ */
+#define SNDRV_SEQ_EVENT_SYSEX		130	/* system exclusive data (variable length) */
+#define SNDRV_SEQ_EVENT_BOUNCE		131	/* error event */
+/* 132-134: reserved */
+#define SNDRV_SEQ_EVENT_USR_VAR0	135
+#define SNDRV_SEQ_EVENT_USR_VAR1	136
+#define SNDRV_SEQ_EVENT_USR_VAR2	137
+#define SNDRV_SEQ_EVENT_USR_VAR3	138
+#define SNDRV_SEQ_EVENT_USR_VAR4	139
+
+/* 150-151: kernel events with quote - DO NOT use in user clients */
+#define SNDRV_SEQ_EVENT_KERNEL_ERROR	150
+#define SNDRV_SEQ_EVENT_KERNEL_QUOTE	151	/* obsolete */
+
+/* 152-191: reserved */
+
+/* 192-254: hardware specific events */
+
+/* 255: special event */
+#define SNDRV_SEQ_EVENT_NONE		255
+
+
+typedef unsigned char snd_seq_event_type_t;
+
+/** event address */
+struct snd_seq_addr {
+	unsigned char client;	/**< Client number:         0..255, 255 = broadcast to all clients */
+	unsigned char port;	/**< Port within client:    0..255, 255 = broadcast to all ports */
+};
+
+/** port connection */
+struct snd_seq_connect {
+	struct snd_seq_addr sender;
+	struct snd_seq_addr dest;
+};
+
+
+#define SNDRV_SEQ_ADDRESS_UNKNOWN	253	/* unknown source */
+#define SNDRV_SEQ_ADDRESS_SUBSCRIBERS	254	/* send event to all subscribed ports */
+#define SNDRV_SEQ_ADDRESS_BROADCAST	255	/* send event to all queues/clients/ports/channels */
+#define SNDRV_SEQ_QUEUE_DIRECT		253	/* direct dispatch */
+
+	/* event mode flag - NOTE: only 8 bits available! */
+#define SNDRV_SEQ_TIME_STAMP_TICK	(0<<0) /* timestamp in clock ticks */
+#define SNDRV_SEQ_TIME_STAMP_REAL	(1<<0) /* timestamp in real time */
+#define SNDRV_SEQ_TIME_STAMP_MASK	(1<<0)
+
+#define SNDRV_SEQ_TIME_MODE_ABS		(0<<1)	/* absolute timestamp */
+#define SNDRV_SEQ_TIME_MODE_REL		(1<<1)	/* relative to current time */
+#define SNDRV_SEQ_TIME_MODE_MASK	(1<<1)
+
+#define SNDRV_SEQ_EVENT_LENGTH_FIXED	(0<<2)	/* fixed event size */
+#define SNDRV_SEQ_EVENT_LENGTH_VARIABLE	(1<<2)	/* variable event size */
+#define SNDRV_SEQ_EVENT_LENGTH_VARUSR	(2<<2)	/* variable event size - user memory space */
+#define SNDRV_SEQ_EVENT_LENGTH_MASK	(3<<2)
+
+#define SNDRV_SEQ_PRIORITY_NORMAL	(0<<4)	/* normal priority */
+#define SNDRV_SEQ_PRIORITY_HIGH		(1<<4)	/* event should be processed before others */
+#define SNDRV_SEQ_PRIORITY_MASK		(1<<4)
+
+
+	/* note event */
+struct snd_seq_ev_note {
+	unsigned char channel;
+	unsigned char note;
+	unsigned char velocity;
+	unsigned char off_velocity;	/* only for SNDRV_SEQ_EVENT_NOTE */
+	unsigned int duration;		/* only for SNDRV_SEQ_EVENT_NOTE */
+};
+
+	/* controller event */
+struct snd_seq_ev_ctrl {
+	unsigned char channel;
+	unsigned char unused1, unused2, unused3;	/* pad */
+	unsigned int param;
+	signed int value;
+};
+
+	/* generic set of bytes (12x8 bit) */
+struct snd_seq_ev_raw8 {
+	unsigned char d[12];	/* 8 bit value */
+};
+
+	/* generic set of integers (3x32 bit) */
+struct snd_seq_ev_raw32 {
+	unsigned int d[3];	/* 32 bit value */
+};
+
+	/* external stored data */
+struct snd_seq_ev_ext {
+	unsigned int len;	/* length of data */
+	void *ptr;		/* pointer to data (note: maybe 64-bit) */
+} __attribute__((packed));
+
+struct snd_seq_result {
+	int event;		/* processed event type */
+	int result;
+};
+
+
+struct snd_seq_real_time {
+	unsigned int tv_sec;	/* seconds */
+	unsigned int tv_nsec;	/* nanoseconds */
+};
+
+typedef unsigned int snd_seq_tick_time_t;	/* midi ticks */
+
+union snd_seq_timestamp {
+	snd_seq_tick_time_t tick;
+	struct snd_seq_real_time time;
+};
+
+struct snd_seq_queue_skew {
+	unsigned int value;
+	unsigned int base;
+};
+
+	/* queue timer control */
+struct snd_seq_ev_queue_control {
+	unsigned char queue;			/* affected queue */
+	unsigned char pad[3];			/* reserved */
+	union {
+		signed int value;		/* affected value (e.g. tempo) */
+		union snd_seq_timestamp time;	/* time */
+		unsigned int position;		/* sync position */
+		struct snd_seq_queue_skew skew;
+		unsigned int d32[2];
+		unsigned char d8[8];
+	} param;
+};
+
+	/* quoted event - inside the kernel only */
+struct snd_seq_ev_quote {
+	struct snd_seq_addr origin;		/* original sender */
+	unsigned short value;		/* optional data */
+	struct snd_seq_event *event;		/* quoted event */
+} __attribute__((packed));
+
+
+	/* sequencer event */
+struct snd_seq_event {
+	snd_seq_event_type_t type;	/* event type */
+	unsigned char flags;		/* event flags */
+	char tag;
+	
+	unsigned char queue;		/* schedule queue */
+	union snd_seq_timestamp time;	/* schedule time */
+
+
+	struct snd_seq_addr source;	/* source address */
+	struct snd_seq_addr dest;	/* destination address */
+
+	union {				/* event data... */
+		struct snd_seq_ev_note note;
+		struct snd_seq_ev_ctrl control;
+		struct snd_seq_ev_raw8 raw8;
+		struct snd_seq_ev_raw32 raw32;
+		struct snd_seq_ev_ext ext;
+		struct snd_seq_ev_queue_control queue;
+		union snd_seq_timestamp time;
+		struct snd_seq_addr addr;
+		struct snd_seq_connect connect;
+		struct snd_seq_result result;
+		struct snd_seq_ev_quote quote;
+	} data;
+};
+
+
+/*
+ * bounce event - stored as variable size data
+ */
+struct snd_seq_event_bounce {
+	int err;
+	struct snd_seq_event event;
+	/* external data follows here. */
+};
+
+
+	/* system information */
+struct snd_seq_system_info {
+	int queues;			/* maximum queues count */
+	int clients;			/* maximum clients count */
+	int ports;			/* maximum ports per client */
+	int channels;			/* maximum channels per port */
+	int cur_clients;		/* current clients */
+	int cur_queues;			/* current queues */
+	char reserved[24];
+};
+
+
+	/* system running information */
+struct snd_seq_running_info {
+	unsigned char client;		/* client id */
+	unsigned char big_endian;	/* 1 = big-endian */
+	unsigned char cpu_mode;		/* 4 = 32bit, 8 = 64bit */
+	unsigned char pad;		/* reserved */
+	unsigned char reserved[12];
+};
+
+
+	/* known client numbers */
+#define SNDRV_SEQ_CLIENT_SYSTEM		0
+	/* internal client numbers */
+#define SNDRV_SEQ_CLIENT_DUMMY		14	/* midi through */
+#define SNDRV_SEQ_CLIENT_OSS		15	/* oss sequencer emulator */
+
+
+	/* client types */
+typedef int __bitwise snd_seq_client_type_t;
+#define	NO_CLIENT	((__force snd_seq_client_type_t) 0)
+#define	USER_CLIENT	((__force snd_seq_client_type_t) 1)
+#define	KERNEL_CLIENT	((__force snd_seq_client_type_t) 2)
+                        
+	/* event filter flags */
+#define SNDRV_SEQ_FILTER_BROADCAST	(1<<0)	/* accept broadcast messages */
+#define SNDRV_SEQ_FILTER_MULTICAST	(1<<1)	/* accept multicast messages */
+#define SNDRV_SEQ_FILTER_BOUNCE		(1<<2)	/* accept bounce event in error */
+#define SNDRV_SEQ_FILTER_USE_EVENT	(1<<31)	/* use event filter */
+
+struct snd_seq_client_info {
+	int client;			/* client number to inquire */
+	snd_seq_client_type_t type;	/* client type */
+	char name[64];			/* client name */
+	unsigned int filter;		/* filter flags */
+	unsigned char multicast_filter[8]; /* multicast filter bitmap */
+	unsigned char event_filter[32];	/* event filter bitmap */
+	int num_ports;			/* RO: number of ports */
+	int event_lost;			/* number of lost events */
+	char reserved[64];		/* for future use */
+};
+
+
+/* client pool size */
+struct snd_seq_client_pool {
+	int client;			/* client number to inquire */
+	int output_pool;		/* outgoing (write) pool size */
+	int input_pool;			/* incoming (read) pool size */
+	int output_room;		/* minimum free pool size for select/blocking mode */
+	int output_free;		/* unused size */
+	int input_free;			/* unused size */
+	char reserved[64];
+};
+
+
+/* Remove events by specified criteria */
+
+#define SNDRV_SEQ_REMOVE_INPUT		(1<<0)	/* Flush input queues */
+#define SNDRV_SEQ_REMOVE_OUTPUT		(1<<1)	/* Flush output queues */
+#define SNDRV_SEQ_REMOVE_DEST		(1<<2)	/* Restrict by destination q:client:port */
+#define SNDRV_SEQ_REMOVE_DEST_CHANNEL	(1<<3)	/* Restrict by channel */
+#define SNDRV_SEQ_REMOVE_TIME_BEFORE	(1<<4)	/* Restrict to before time */
+#define SNDRV_SEQ_REMOVE_TIME_AFTER	(1<<5)	/* Restrict to time or after */
+#define SNDRV_SEQ_REMOVE_TIME_TICK	(1<<6)	/* Time is in ticks */
+#define SNDRV_SEQ_REMOVE_EVENT_TYPE	(1<<7)	/* Restrict to event type */
+#define SNDRV_SEQ_REMOVE_IGNORE_OFF 	(1<<8)	/* Do not flush off events */
+#define SNDRV_SEQ_REMOVE_TAG_MATCH 	(1<<9)	/* Restrict to events with given tag */
+
+struct snd_seq_remove_events {
+	unsigned int  remove_mode;	/* Flags that determine what gets removed */
+
+	union snd_seq_timestamp time;
+
+	unsigned char queue;	/* Queue for REMOVE_DEST */
+	struct snd_seq_addr dest;	/* Address for REMOVE_DEST */
+	unsigned char channel;	/* Channel for REMOVE_DEST */
+
+	int  type;	/* For REMOVE_EVENT_TYPE */
+	char  tag;	/* Tag for REMOVE_TAG */
+
+	int  reserved[10];	/* To allow for future binary compatibility */
+
+};
+
+
+	/* known port numbers */
+#define SNDRV_SEQ_PORT_SYSTEM_TIMER	0
+#define SNDRV_SEQ_PORT_SYSTEM_ANNOUNCE	1
+
+	/* port capabilities (32 bits) */
+#define SNDRV_SEQ_PORT_CAP_READ		(1<<0)	/* readable from this port */
+#define SNDRV_SEQ_PORT_CAP_WRITE	(1<<1)	/* writable to this port */
+
+#define SNDRV_SEQ_PORT_CAP_SYNC_READ	(1<<2)
+#define SNDRV_SEQ_PORT_CAP_SYNC_WRITE	(1<<3)
+
+#define SNDRV_SEQ_PORT_CAP_DUPLEX	(1<<4)
+
+#define SNDRV_SEQ_PORT_CAP_SUBS_READ	(1<<5)	/* allow read subscription */
+#define SNDRV_SEQ_PORT_CAP_SUBS_WRITE	(1<<6)	/* allow write subscription */
+#define SNDRV_SEQ_PORT_CAP_NO_EXPORT	(1<<7)	/* routing not allowed */
+
+	/* port type */
+#define SNDRV_SEQ_PORT_TYPE_SPECIFIC	(1<<0)	/* hardware specific */
+#define SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC (1<<1)	/* generic MIDI device */
+#define SNDRV_SEQ_PORT_TYPE_MIDI_GM	(1<<2)	/* General MIDI compatible device */
+#define SNDRV_SEQ_PORT_TYPE_MIDI_GS	(1<<3)	/* GS compatible device */
+#define SNDRV_SEQ_PORT_TYPE_MIDI_XG	(1<<4)	/* XG compatible device */
+#define SNDRV_SEQ_PORT_TYPE_MIDI_MT32	(1<<5)	/* MT-32 compatible device */
+#define SNDRV_SEQ_PORT_TYPE_MIDI_GM2	(1<<6)	/* General MIDI 2 compatible device */
+
+/* other standards...*/
+#define SNDRV_SEQ_PORT_TYPE_SYNTH	(1<<10)	/* Synth device (no MIDI compatible - direct wavetable) */
+#define SNDRV_SEQ_PORT_TYPE_DIRECT_SAMPLE (1<<11)	/* Sampling device (support sample download) */
+#define SNDRV_SEQ_PORT_TYPE_SAMPLE	(1<<12)	/* Sampling device (sample can be downloaded at any time) */
+/*...*/
+#define SNDRV_SEQ_PORT_TYPE_HARDWARE	(1<<16)	/* driver for a hardware device */
+#define SNDRV_SEQ_PORT_TYPE_SOFTWARE	(1<<17)	/* implemented in software */
+#define SNDRV_SEQ_PORT_TYPE_SYNTHESIZER	(1<<18)	/* generates sound */
+#define SNDRV_SEQ_PORT_TYPE_PORT	(1<<19)	/* connects to other device(s) */
+#define SNDRV_SEQ_PORT_TYPE_APPLICATION	(1<<20)	/* application (sequencer/editor) */
+
+/* misc. conditioning flags */
+#define SNDRV_SEQ_PORT_FLG_GIVEN_PORT	(1<<0)
+#define SNDRV_SEQ_PORT_FLG_TIMESTAMP	(1<<1)
+#define SNDRV_SEQ_PORT_FLG_TIME_REAL	(1<<2)
+
+struct snd_seq_port_info {
+	struct snd_seq_addr addr;	/* client/port numbers */
+	char name[64];			/* port name */
+
+	unsigned int capability;	/* port capability bits */
+	unsigned int type;		/* port type bits */
+	int midi_channels;		/* channels per MIDI port */
+	int midi_voices;		/* voices per MIDI port */
+	int synth_voices;		/* voices per SYNTH port */
+
+	int read_use;			/* R/O: subscribers for output (from this port) */
+	int write_use;			/* R/O: subscribers for input (to this port) */
+
+	void *kernel;			/* reserved for kernel use (must be NULL) */
+	unsigned int flags;		/* misc. conditioning */
+	unsigned char time_queue;	/* queue # for timestamping */
+	char reserved[59];		/* for future use */
+};
+
+
+/* queue flags */
+#define SNDRV_SEQ_QUEUE_FLG_SYNC	(1<<0)	/* sync enabled */
+
+/* queue information */
+struct snd_seq_queue_info {
+	int queue;		/* queue id */
+
+	/*
+	 *  security settings, only owner of this queue can start/stop timer
+	 *  etc. if the queue is locked for other clients
+	 */
+	int owner;		/* client id for owner of the queue */
+	unsigned locked:1;	/* timing queue locked for other queues */
+	char name[64];		/* name of this queue */
+	unsigned int flags;	/* flags */
+	char reserved[60];	/* for future use */
+
+};
+
+/* queue info/status */
+struct snd_seq_queue_status {
+	int queue;			/* queue id */
+	int events;			/* read-only - queue size */
+	snd_seq_tick_time_t tick;	/* current tick */
+	struct snd_seq_real_time time;	/* current time */
+	int running;			/* running state of queue */
+	int flags;			/* various flags */
+	char reserved[64];		/* for the future */
+};
+
+
+/* queue tempo */
+struct snd_seq_queue_tempo {
+	int queue;			/* sequencer queue */
+	unsigned int tempo;		/* current tempo, us/tick */
+	int ppq;			/* time resolution, ticks/quarter */
+	unsigned int skew_value;	/* queue skew */
+	unsigned int skew_base;		/* queue skew base */
+	char reserved[24];		/* for the future */
+};
+
+
+/* sequencer timer sources */
+#define SNDRV_SEQ_TIMER_ALSA		0	/* ALSA timer */
+#define SNDRV_SEQ_TIMER_MIDI_CLOCK	1	/* Midi Clock (CLOCK event) */
+#define SNDRV_SEQ_TIMER_MIDI_TICK	2	/* Midi Timer Tick (TICK event) */
+
+/* queue timer info */
+struct snd_seq_queue_timer {
+	int queue;			/* sequencer queue */
+	int type;			/* source timer type */
+	union {
+		struct {
+			struct snd_timer_id id;	/* ALSA's timer ID */
+			unsigned int resolution;	/* resolution in Hz */
+		} alsa;
+	} u;
+	char reserved[64];		/* for the future use */
+};
+
+
+struct snd_seq_queue_client {
+	int queue;		/* sequencer queue */
+	int client;		/* sequencer client */
+	int used;		/* queue is used with this client
+				   (must be set for accepting events) */
+	/* per client watermarks */
+	char reserved[64];	/* for future use */
+};
+
+
+#define SNDRV_SEQ_PORT_SUBS_EXCLUSIVE	(1<<0)	/* exclusive connection */
+#define SNDRV_SEQ_PORT_SUBS_TIMESTAMP	(1<<1)
+#define SNDRV_SEQ_PORT_SUBS_TIME_REAL	(1<<2)
+
+struct snd_seq_port_subscribe {
+	struct snd_seq_addr sender;	/* sender address */
+	struct snd_seq_addr dest;	/* destination address */
+	unsigned int voices;		/* number of voices to be allocated (0 = don't care) */
+	unsigned int flags;		/* modes */
+	unsigned char queue;		/* input time-stamp queue (optional) */
+	unsigned char pad[3];		/* reserved */
+	char reserved[64];
+};
+
+/* type of query subscription */
+#define SNDRV_SEQ_QUERY_SUBS_READ	0
+#define SNDRV_SEQ_QUERY_SUBS_WRITE	1
+
+struct snd_seq_query_subs {
+	struct snd_seq_addr root;	/* client/port id to be searched */
+	int type;		/* READ or WRITE */
+	int index;		/* 0..N-1 */
+	int num_subs;		/* R/O: number of subscriptions on this port */
+	struct snd_seq_addr addr;	/* R/O: result */
+	unsigned char queue;	/* R/O: result */
+	unsigned int flags;	/* R/O: result */
+	char reserved[64];	/* for future use */
+};
+
+
+/*
+ *  IOCTL commands
+ */
+
+#define SNDRV_SEQ_IOCTL_PVERSION	_IOR ('S', 0x00, int)
+#define SNDRV_SEQ_IOCTL_CLIENT_ID	_IOR ('S', 0x01, int)
+#define SNDRV_SEQ_IOCTL_SYSTEM_INFO	_IOWR('S', 0x02, struct snd_seq_system_info)
+#define SNDRV_SEQ_IOCTL_RUNNING_MODE	_IOWR('S', 0x03, struct snd_seq_running_info)
+
+#define SNDRV_SEQ_IOCTL_GET_CLIENT_INFO	_IOWR('S', 0x10, struct snd_seq_client_info)
+#define SNDRV_SEQ_IOCTL_SET_CLIENT_INFO	_IOW ('S', 0x11, struct snd_seq_client_info)
+
+#define SNDRV_SEQ_IOCTL_CREATE_PORT	_IOWR('S', 0x20, struct snd_seq_port_info)
+#define SNDRV_SEQ_IOCTL_DELETE_PORT	_IOW ('S', 0x21, struct snd_seq_port_info)
+#define SNDRV_SEQ_IOCTL_GET_PORT_INFO	_IOWR('S', 0x22, struct snd_seq_port_info)
+#define SNDRV_SEQ_IOCTL_SET_PORT_INFO	_IOW ('S', 0x23, struct snd_seq_port_info)
+
+#define SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT	_IOW ('S', 0x30, struct snd_seq_port_subscribe)
+#define SNDRV_SEQ_IOCTL_UNSUBSCRIBE_PORT _IOW ('S', 0x31, struct snd_seq_port_subscribe)
+
+#define SNDRV_SEQ_IOCTL_CREATE_QUEUE	_IOWR('S', 0x32, struct snd_seq_queue_info)
+#define SNDRV_SEQ_IOCTL_DELETE_QUEUE	_IOW ('S', 0x33, struct snd_seq_queue_info)
+#define SNDRV_SEQ_IOCTL_GET_QUEUE_INFO	_IOWR('S', 0x34, struct snd_seq_queue_info)
+#define SNDRV_SEQ_IOCTL_SET_QUEUE_INFO	_IOWR('S', 0x35, struct snd_seq_queue_info)
+#define SNDRV_SEQ_IOCTL_GET_NAMED_QUEUE	_IOWR('S', 0x36, struct snd_seq_queue_info)
+#define SNDRV_SEQ_IOCTL_GET_QUEUE_STATUS _IOWR('S', 0x40, struct snd_seq_queue_status)
+#define SNDRV_SEQ_IOCTL_GET_QUEUE_TEMPO	_IOWR('S', 0x41, struct snd_seq_queue_tempo)
+#define SNDRV_SEQ_IOCTL_SET_QUEUE_TEMPO	_IOW ('S', 0x42, struct snd_seq_queue_tempo)
+#define SNDRV_SEQ_IOCTL_GET_QUEUE_OWNER	_IOWR('S', 0x43, struct snd_seq_queue_owner)
+#define SNDRV_SEQ_IOCTL_SET_QUEUE_OWNER	_IOW ('S', 0x44, struct snd_seq_queue_owner)
+#define SNDRV_SEQ_IOCTL_GET_QUEUE_TIMER	_IOWR('S', 0x45, struct snd_seq_queue_timer)
+#define SNDRV_SEQ_IOCTL_SET_QUEUE_TIMER	_IOW ('S', 0x46, struct snd_seq_queue_timer)
+/* XXX
+#define SNDRV_SEQ_IOCTL_GET_QUEUE_SYNC	_IOWR('S', 0x53, struct snd_seq_queue_sync)
+#define SNDRV_SEQ_IOCTL_SET_QUEUE_SYNC	_IOW ('S', 0x54, struct snd_seq_queue_sync)
+*/
+#define SNDRV_SEQ_IOCTL_GET_QUEUE_CLIENT	_IOWR('S', 0x49, struct snd_seq_queue_client)
+#define SNDRV_SEQ_IOCTL_SET_QUEUE_CLIENT	_IOW ('S', 0x4a, struct snd_seq_queue_client)
+#define SNDRV_SEQ_IOCTL_GET_CLIENT_POOL	_IOWR('S', 0x4b, struct snd_seq_client_pool)
+#define SNDRV_SEQ_IOCTL_SET_CLIENT_POOL	_IOW ('S', 0x4c, struct snd_seq_client_pool)
+#define SNDRV_SEQ_IOCTL_REMOVE_EVENTS	_IOW ('S', 0x4e, struct snd_seq_remove_events)
+#define SNDRV_SEQ_IOCTL_QUERY_SUBS	_IOWR('S', 0x4f, struct snd_seq_query_subs)
+#define SNDRV_SEQ_IOCTL_GET_SUBSCRIPTION	_IOWR('S', 0x50, struct snd_seq_port_subscribe)
+#define SNDRV_SEQ_IOCTL_QUERY_NEXT_CLIENT	_IOWR('S', 0x51, struct snd_seq_client_info)
+#define SNDRV_SEQ_IOCTL_QUERY_NEXT_PORT	_IOWR('S', 0x52, struct snd_seq_port_info)
+
+#endif /* _UAPI__SOUND_ASEQUENCER_H */
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
new file mode 100644
index 000000000000..92b104e496b5
--- /dev/null
+++ b/include/uapi/sound/asound.h
@@ -0,0 +1,957 @@
+/*
+ *  Advanced Linux Sound Architecture - ALSA - Driver
+ *  Copyright (c) 1994-2003 by Jaroslav Kysela <perex@perex.cz>,
+ *                             Abramo Bagnara <abramo@alsa-project.org>
+ *
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program; if not, write to the Free Software
+ *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ */
+
+#ifndef _UAPI__SOUND_ASOUND_H
+#define _UAPI__SOUND_ASOUND_H
+
+#include <linux/types.h>
+
+
+/*
+ *  protocol version
+ */
+
+#define SNDRV_PROTOCOL_VERSION(major, minor, subminor) (((major)<<16)|((minor)<<8)|(subminor))
+#define SNDRV_PROTOCOL_MAJOR(version) (((version)>>16)&0xffff)
+#define SNDRV_PROTOCOL_MINOR(version) (((version)>>8)&0xff)
+#define SNDRV_PROTOCOL_MICRO(version) ((version)&0xff)
+#define SNDRV_PROTOCOL_INCOMPATIBLE(kversion, uversion) \
+	(SNDRV_PROTOCOL_MAJOR(kversion) != SNDRV_PROTOCOL_MAJOR(uversion) || \
+	 (SNDRV_PROTOCOL_MAJOR(kversion) == SNDRV_PROTOCOL_MAJOR(uversion) && \
+	   SNDRV_PROTOCOL_MINOR(kversion) != SNDRV_PROTOCOL_MINOR(uversion)))
+
+/****************************************************************************
+ *                                                                          *
+ *        Digital audio interface					    *
+ *                                                                          *
+ ****************************************************************************/
+
+struct snd_aes_iec958 {
+	unsigned char status[24];	/* AES/IEC958 channel status bits */
+	unsigned char subcode[147];	/* AES/IEC958 subcode bits */
+	unsigned char pad;		/* nothing */
+	unsigned char dig_subframe[4];	/* AES/IEC958 subframe bits */
+};
+
+/****************************************************************************
+ *                                                                          *
+ *        CEA-861 Audio InfoFrame. Used in HDMI and DisplayPort		    *
+ *                                                                          *
+ ****************************************************************************/
+
+struct snd_cea_861_aud_if {
+	unsigned char db1_ct_cc; /* coding type and channel count */
+	unsigned char db2_sf_ss; /* sample frequency and size */
+	unsigned char db3; /* not used, all zeros */
+	unsigned char db4_ca; /* channel allocation code */
+	unsigned char db5_dminh_lsv; /* downmix inhibit & level-shit values */
+};
+
+/****************************************************************************
+ *                                                                          *
+ *      Section for driver hardware dependent interface - /dev/snd/hw?      *
+ *                                                                          *
+ ****************************************************************************/
+
+#define SNDRV_HWDEP_VERSION		SNDRV_PROTOCOL_VERSION(1, 0, 1)
+
+enum {
+	SNDRV_HWDEP_IFACE_OPL2 = 0,
+	SNDRV_HWDEP_IFACE_OPL3,
+	SNDRV_HWDEP_IFACE_OPL4,
+	SNDRV_HWDEP_IFACE_SB16CSP,	/* Creative Signal Processor */
+	SNDRV_HWDEP_IFACE_EMU10K1,	/* FX8010 processor in EMU10K1 chip */
+	SNDRV_HWDEP_IFACE_YSS225,	/* Yamaha FX processor */
+	SNDRV_HWDEP_IFACE_ICS2115,	/* Wavetable synth */
+	SNDRV_HWDEP_IFACE_SSCAPE,	/* Ensoniq SoundScape ISA card (MC68EC000) */
+	SNDRV_HWDEP_IFACE_VX,		/* Digigram VX cards */
+	SNDRV_HWDEP_IFACE_MIXART,	/* Digigram miXart cards */
+	SNDRV_HWDEP_IFACE_USX2Y,	/* Tascam US122, US224 & US428 usb */
+	SNDRV_HWDEP_IFACE_EMUX_WAVETABLE, /* EmuX wavetable */	
+	SNDRV_HWDEP_IFACE_BLUETOOTH,	/* Bluetooth audio */
+	SNDRV_HWDEP_IFACE_USX2Y_PCM,	/* Tascam US122, US224 & US428 rawusb pcm */
+	SNDRV_HWDEP_IFACE_PCXHR,	/* Digigram PCXHR */
+	SNDRV_HWDEP_IFACE_SB_RC,	/* SB Extigy/Audigy2NX remote control */
+	SNDRV_HWDEP_IFACE_HDA,		/* HD-audio */
+	SNDRV_HWDEP_IFACE_USB_STREAM,	/* direct access to usb stream */
+
+	/* Don't forget to change the following: */
+	SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_USB_STREAM
+};
+
+struct snd_hwdep_info {
+	unsigned int device;		/* WR: device number */
+	int card;			/* R: card number */
+	unsigned char id[64];		/* ID (user selectable) */
+	unsigned char name[80];		/* hwdep name */
+	int iface;			/* hwdep interface */
+	unsigned char reserved[64];	/* reserved for future */
+};
+
+/* generic DSP loader */
+struct snd_hwdep_dsp_status {
+	unsigned int version;		/* R: driver-specific version */
+	unsigned char id[32];		/* R: driver-specific ID string */
+	unsigned int num_dsps;		/* R: number of DSP images to transfer */
+	unsigned int dsp_loaded;	/* R: bit flags indicating the loaded DSPs */
+	unsigned int chip_ready;	/* R: 1 = initialization finished */
+	unsigned char reserved[16];	/* reserved for future use */
+};
+
+struct snd_hwdep_dsp_image {
+	unsigned int index;		/* W: DSP index */
+	unsigned char name[64];		/* W: ID (e.g. file name) */
+	unsigned char __user *image;	/* W: binary image */
+	size_t length;			/* W: size of image in bytes */
+	unsigned long driver_data;	/* W: driver-specific data */
+};
+
+#define SNDRV_HWDEP_IOCTL_PVERSION	_IOR ('H', 0x00, int)
+#define SNDRV_HWDEP_IOCTL_INFO		_IOR ('H', 0x01, struct snd_hwdep_info)
+#define SNDRV_HWDEP_IOCTL_DSP_STATUS	_IOR('H', 0x02, struct snd_hwdep_dsp_status)
+#define SNDRV_HWDEP_IOCTL_DSP_LOAD	_IOW('H', 0x03, struct snd_hwdep_dsp_image)
+
+/*****************************************************************************
+ *                                                                           *
+ *             Digital Audio (PCM) interface - /dev/snd/pcm??                *
+ *                                                                           *
+ *****************************************************************************/
+
+#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 10)
+
+typedef unsigned long snd_pcm_uframes_t;
+typedef signed long snd_pcm_sframes_t;
+
+enum {
+	SNDRV_PCM_CLASS_GENERIC = 0,	/* standard mono or stereo device */
+	SNDRV_PCM_CLASS_MULTI,		/* multichannel device */
+	SNDRV_PCM_CLASS_MODEM,		/* software modem class */
+	SNDRV_PCM_CLASS_DIGITIZER,	/* digitizer class */
+	/* Don't forget to change the following: */
+	SNDRV_PCM_CLASS_LAST = SNDRV_PCM_CLASS_DIGITIZER,
+};
+
+enum {
+	SNDRV_PCM_SUBCLASS_GENERIC_MIX = 0, /* mono or stereo subdevices are mixed together */
+	SNDRV_PCM_SUBCLASS_MULTI_MIX,	/* multichannel subdevices are mixed together */
+	/* Don't forget to change the following: */
+	SNDRV_PCM_SUBCLASS_LAST = SNDRV_PCM_SUBCLASS_MULTI_MIX,
+};
+
+enum {
+	SNDRV_PCM_STREAM_PLAYBACK = 0,
+	SNDRV_PCM_STREAM_CAPTURE,
+	SNDRV_PCM_STREAM_LAST = SNDRV_PCM_STREAM_CAPTURE,
+};
+
+typedef int __bitwise snd_pcm_access_t;
+#define	SNDRV_PCM_ACCESS_MMAP_INTERLEAVED	((__force snd_pcm_access_t) 0) /* interleaved mmap */
+#define	SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED	((__force snd_pcm_access_t) 1) /* noninterleaved mmap */
+#define	SNDRV_PCM_ACCESS_MMAP_COMPLEX		((__force snd_pcm_access_t) 2) /* complex mmap */
+#define	SNDRV_PCM_ACCESS_RW_INTERLEAVED		((__force snd_pcm_access_t) 3) /* readi/writei */
+#define	SNDRV_PCM_ACCESS_RW_NONINTERLEAVED	((__force snd_pcm_access_t) 4) /* readn/writen */
+#define	SNDRV_PCM_ACCESS_LAST		SNDRV_PCM_ACCESS_RW_NONINTERLEAVED
+
+typedef int __bitwise snd_pcm_format_t;
+#define	SNDRV_PCM_FORMAT_S8	((__force snd_pcm_format_t) 0)
+#define	SNDRV_PCM_FORMAT_U8	((__force snd_pcm_format_t) 1)
+#define	SNDRV_PCM_FORMAT_S16_LE	((__force snd_pcm_format_t) 2)
+#define	SNDRV_PCM_FORMAT_S16_BE	((__force snd_pcm_format_t) 3)
+#define	SNDRV_PCM_FORMAT_U16_LE	((__force snd_pcm_format_t) 4)
+#define	SNDRV_PCM_FORMAT_U16_BE	((__force snd_pcm_format_t) 5)
+#define	SNDRV_PCM_FORMAT_S24_LE	((__force snd_pcm_format_t) 6) /* low three bytes */
+#define	SNDRV_PCM_FORMAT_S24_BE	((__force snd_pcm_format_t) 7) /* low three bytes */
+#define	SNDRV_PCM_FORMAT_U24_LE	((__force snd_pcm_format_t) 8) /* low three bytes */
+#define	SNDRV_PCM_FORMAT_U24_BE	((__force snd_pcm_format_t) 9) /* low three bytes */
+#define	SNDRV_PCM_FORMAT_S32_LE	((__force snd_pcm_format_t) 10)
+#define	SNDRV_PCM_FORMAT_S32_BE	((__force snd_pcm_format_t) 11)
+#define	SNDRV_PCM_FORMAT_U32_LE	((__force snd_pcm_format_t) 12)
+#define	SNDRV_PCM_FORMAT_U32_BE	((__force snd_pcm_format_t) 13)
+#define	SNDRV_PCM_FORMAT_FLOAT_LE	((__force snd_pcm_format_t) 14) /* 4-byte float, IEEE-754 32-bit, range -1.0 to 1.0 */
+#define	SNDRV_PCM_FORMAT_FLOAT_BE	((__force snd_pcm_format_t) 15) /* 4-byte float, IEEE-754 32-bit, range -1.0 to 1.0 */
+#define	SNDRV_PCM_FORMAT_FLOAT64_LE	((__force snd_pcm_format_t) 16) /* 8-byte float, IEEE-754 64-bit, range -1.0 to 1.0 */
+#define	SNDRV_PCM_FORMAT_FLOAT64_BE	((__force snd_pcm_format_t) 17) /* 8-byte float, IEEE-754 64-bit, range -1.0 to 1.0 */
+#define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE ((__force snd_pcm_format_t) 18) /* IEC-958 subframe, Little Endian */
+#define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE ((__force snd_pcm_format_t) 19) /* IEC-958 subframe, Big Endian */
+#define	SNDRV_PCM_FORMAT_MU_LAW		((__force snd_pcm_format_t) 20)
+#define	SNDRV_PCM_FORMAT_A_LAW		((__force snd_pcm_format_t) 21)
+#define	SNDRV_PCM_FORMAT_IMA_ADPCM	((__force snd_pcm_format_t) 22)
+#define	SNDRV_PCM_FORMAT_MPEG		((__force snd_pcm_format_t) 23)
+#define	SNDRV_PCM_FORMAT_GSM		((__force snd_pcm_format_t) 24)
+#define	SNDRV_PCM_FORMAT_SPECIAL	((__force snd_pcm_format_t) 31)
+#define	SNDRV_PCM_FORMAT_S24_3LE	((__force snd_pcm_format_t) 32)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_S24_3BE	((__force snd_pcm_format_t) 33)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_U24_3LE	((__force snd_pcm_format_t) 34)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_U24_3BE	((__force snd_pcm_format_t) 35)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_S20_3LE	((__force snd_pcm_format_t) 36)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_S20_3BE	((__force snd_pcm_format_t) 37)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_U20_3LE	((__force snd_pcm_format_t) 38)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_U20_3BE	((__force snd_pcm_format_t) 39)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_S18_3LE	((__force snd_pcm_format_t) 40)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_S18_3BE	((__force snd_pcm_format_t) 41)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_U18_3LE	((__force snd_pcm_format_t) 42)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_U18_3BE	((__force snd_pcm_format_t) 43)	/* in three bytes */
+#define	SNDRV_PCM_FORMAT_G723_24	((__force snd_pcm_format_t) 44) /* 8 samples in 3 bytes */
+#define	SNDRV_PCM_FORMAT_G723_24_1B	((__force snd_pcm_format_t) 45) /* 1 sample in 1 byte */
+#define	SNDRV_PCM_FORMAT_G723_40	((__force snd_pcm_format_t) 46) /* 8 Samples in 5 bytes */
+#define	SNDRV_PCM_FORMAT_G723_40_1B	((__force snd_pcm_format_t) 47) /* 1 sample in 1 byte */
+#define	SNDRV_PCM_FORMAT_LAST		SNDRV_PCM_FORMAT_G723_40_1B
+
+#ifdef SNDRV_LITTLE_ENDIAN
+#define	SNDRV_PCM_FORMAT_S16		SNDRV_PCM_FORMAT_S16_LE
+#define	SNDRV_PCM_FORMAT_U16		SNDRV_PCM_FORMAT_U16_LE
+#define	SNDRV_PCM_FORMAT_S24		SNDRV_PCM_FORMAT_S24_LE
+#define	SNDRV_PCM_FORMAT_U24		SNDRV_PCM_FORMAT_U24_LE
+#define	SNDRV_PCM_FORMAT_S32		SNDRV_PCM_FORMAT_S32_LE
+#define	SNDRV_PCM_FORMAT_U32		SNDRV_PCM_FORMAT_U32_LE
+#define	SNDRV_PCM_FORMAT_FLOAT		SNDRV_PCM_FORMAT_FLOAT_LE
+#define	SNDRV_PCM_FORMAT_FLOAT64	SNDRV_PCM_FORMAT_FLOAT64_LE
+#define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE
+#endif
+#ifdef SNDRV_BIG_ENDIAN
+#define	SNDRV_PCM_FORMAT_S16		SNDRV_PCM_FORMAT_S16_BE
+#define	SNDRV_PCM_FORMAT_U16		SNDRV_PCM_FORMAT_U16_BE
+#define	SNDRV_PCM_FORMAT_S24		SNDRV_PCM_FORMAT_S24_BE
+#define	SNDRV_PCM_FORMAT_U24		SNDRV_PCM_FORMAT_U24_BE
+#define	SNDRV_PCM_FORMAT_S32		SNDRV_PCM_FORMAT_S32_BE
+#define	SNDRV_PCM_FORMAT_U32		SNDRV_PCM_FORMAT_U32_BE
+#define	SNDRV_PCM_FORMAT_FLOAT		SNDRV_PCM_FORMAT_FLOAT_BE
+#define	SNDRV_PCM_FORMAT_FLOAT64	SNDRV_PCM_FORMAT_FLOAT64_BE
+#define	SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE
+#endif
+
+typedef int __bitwise snd_pcm_subformat_t;
+#define	SNDRV_PCM_SUBFORMAT_STD		((__force snd_pcm_subformat_t) 0)
+#define	SNDRV_PCM_SUBFORMAT_LAST	SNDRV_PCM_SUBFORMAT_STD
+
+#define SNDRV_PCM_INFO_MMAP		0x00000001	/* hardware supports mmap */
+#define SNDRV_PCM_INFO_MMAP_VALID	0x00000002	/* period data are valid during transfer */
+#define SNDRV_PCM_INFO_DOUBLE		0x00000004	/* Double buffering needed for PCM start/stop */
+#define SNDRV_PCM_INFO_BATCH		0x00000010	/* double buffering */
+#define SNDRV_PCM_INFO_INTERLEAVED	0x00000100	/* channels are interleaved */
+#define SNDRV_PCM_INFO_NONINTERLEAVED	0x00000200	/* channels are not interleaved */
+#define SNDRV_PCM_INFO_COMPLEX		0x00000400	/* complex frame organization (mmap only) */
+#define SNDRV_PCM_INFO_BLOCK_TRANSFER	0x00010000	/* hardware transfer block of samples */
+#define SNDRV_PCM_INFO_OVERRANGE	0x00020000	/* hardware supports ADC (capture) overrange detection */
+#define SNDRV_PCM_INFO_RESUME		0x00040000	/* hardware supports stream resume after suspend */
+#define SNDRV_PCM_INFO_PAUSE		0x00080000	/* pause ioctl is supported */
+#define SNDRV_PCM_INFO_HALF_DUPLEX	0x00100000	/* only half duplex */
+#define SNDRV_PCM_INFO_JOINT_DUPLEX	0x00200000	/* playback and capture stream are somewhat correlated */
+#define SNDRV_PCM_INFO_SYNC_START	0x00400000	/* pcm support some kind of sync go */
+#define SNDRV_PCM_INFO_NO_PERIOD_WAKEUP	0x00800000	/* period wakeup can be disabled */
+#define SNDRV_PCM_INFO_FIFO_IN_FRAMES	0x80000000	/* internal kernel flag - FIFO size is in frames */
+
+typedef int __bitwise snd_pcm_state_t;
+#define	SNDRV_PCM_STATE_OPEN		((__force snd_pcm_state_t) 0) /* stream is open */
+#define	SNDRV_PCM_STATE_SETUP		((__force snd_pcm_state_t) 1) /* stream has a setup */
+#define	SNDRV_PCM_STATE_PREPARED	((__force snd_pcm_state_t) 2) /* stream is ready to start */
+#define	SNDRV_PCM_STATE_RUNNING		((__force snd_pcm_state_t) 3) /* stream is running */
+#define	SNDRV_PCM_STATE_XRUN		((__force snd_pcm_state_t) 4) /* stream reached an xrun */
+#define	SNDRV_PCM_STATE_DRAINING	((__force snd_pcm_state_t) 5) /* stream is draining */
+#define	SNDRV_PCM_STATE_PAUSED		((__force snd_pcm_state_t) 6) /* stream is paused */
+#define	SNDRV_PCM_STATE_SUSPENDED	((__force snd_pcm_state_t) 7) /* hardware is suspended */
+#define	SNDRV_PCM_STATE_DISCONNECTED	((__force snd_pcm_state_t) 8) /* hardware is disconnected */
+#define	SNDRV_PCM_STATE_LAST		SNDRV_PCM_STATE_DISCONNECTED
+
+enum {
+	SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000,
+	SNDRV_PCM_MMAP_OFFSET_STATUS = 0x80000000,
+	SNDRV_PCM_MMAP_OFFSET_CONTROL = 0x81000000,
+};
+
+union snd_pcm_sync_id {
+	unsigned char id[16];
+	unsigned short id16[8];
+	unsigned int id32[4];
+};
+
+struct snd_pcm_info {
+	unsigned int device;		/* RO/WR (control): device number */
+	unsigned int subdevice;		/* RO/WR (control): subdevice number */
+	int stream;			/* RO/WR (control): stream direction */
+	int card;			/* R: card number */
+	unsigned char id[64];		/* ID (user selectable) */
+	unsigned char name[80];		/* name of this device */
+	unsigned char subname[32];	/* subdevice name */
+	int dev_class;			/* SNDRV_PCM_CLASS_* */
+	int dev_subclass;		/* SNDRV_PCM_SUBCLASS_* */
+	unsigned int subdevices_count;
+	unsigned int subdevices_avail;
+	union snd_pcm_sync_id sync;	/* hardware synchronization ID */
+	unsigned char reserved[64];	/* reserved for future... */
+};
+
+typedef int snd_pcm_hw_param_t;
+#define	SNDRV_PCM_HW_PARAM_ACCESS	0	/* Access type */
+#define	SNDRV_PCM_HW_PARAM_FORMAT	1	/* Format */
+#define	SNDRV_PCM_HW_PARAM_SUBFORMAT	2	/* Subformat */
+#define	SNDRV_PCM_HW_PARAM_FIRST_MASK	SNDRV_PCM_HW_PARAM_ACCESS
+#define	SNDRV_PCM_HW_PARAM_LAST_MASK	SNDRV_PCM_HW_PARAM_SUBFORMAT
+
+#define	SNDRV_PCM_HW_PARAM_SAMPLE_BITS	8	/* Bits per sample */
+#define	SNDRV_PCM_HW_PARAM_FRAME_BITS	9	/* Bits per frame */
+#define	SNDRV_PCM_HW_PARAM_CHANNELS	10	/* Channels */
+#define	SNDRV_PCM_HW_PARAM_RATE		11	/* Approx rate */
+#define	SNDRV_PCM_HW_PARAM_PERIOD_TIME	12	/* Approx distance between
+						 * interrupts in us
+						 */
+#define	SNDRV_PCM_HW_PARAM_PERIOD_SIZE	13	/* Approx frames between
+						 * interrupts
+						 */
+#define	SNDRV_PCM_HW_PARAM_PERIOD_BYTES	14	/* Approx bytes between
+						 * interrupts
+						 */
+#define	SNDRV_PCM_HW_PARAM_PERIODS	15	/* Approx interrupts per
+						 * buffer
+						 */
+#define	SNDRV_PCM_HW_PARAM_BUFFER_TIME	16	/* Approx duration of buffer
+						 * in us
+						 */
+#define	SNDRV_PCM_HW_PARAM_BUFFER_SIZE	17	/* Size of buffer in frames */
+#define	SNDRV_PCM_HW_PARAM_BUFFER_BYTES	18	/* Size of buffer in bytes */
+#define	SNDRV_PCM_HW_PARAM_TICK_TIME	19	/* Approx tick duration in us */
+#define	SNDRV_PCM_HW_PARAM_FIRST_INTERVAL	SNDRV_PCM_HW_PARAM_SAMPLE_BITS
+#define	SNDRV_PCM_HW_PARAM_LAST_INTERVAL	SNDRV_PCM_HW_PARAM_TICK_TIME
+
+#define SNDRV_PCM_HW_PARAMS_NORESAMPLE	(1<<0)	/* avoid rate resampling */
+#define SNDRV_PCM_HW_PARAMS_EXPORT_BUFFER	(1<<1)	/* export buffer */
+#define SNDRV_PCM_HW_PARAMS_NO_PERIOD_WAKEUP	(1<<2)	/* disable period wakeups */
+
+struct snd_interval {
+	unsigned int min, max;
+	unsigned int openmin:1,
+		     openmax:1,
+		     integer:1,
+		     empty:1;
+};
+
+#define SNDRV_MASK_MAX	256
+
+struct snd_mask {
+	__u32 bits[(SNDRV_MASK_MAX+31)/32];
+};
+
+struct snd_pcm_hw_params {
+	unsigned int flags;
+	struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK - 
+			       SNDRV_PCM_HW_PARAM_FIRST_MASK + 1];
+	struct snd_mask mres[5];	/* reserved masks */
+	struct snd_interval intervals[SNDRV_PCM_HW_PARAM_LAST_INTERVAL -
+				        SNDRV_PCM_HW_PARAM_FIRST_INTERVAL + 1];
+	struct snd_interval ires[9];	/* reserved intervals */
+	unsigned int rmask;		/* W: requested masks */
+	unsigned int cmask;		/* R: changed masks */
+	unsigned int info;		/* R: Info flags for returned setup */
+	unsigned int msbits;		/* R: used most significant bits */
+	unsigned int rate_num;		/* R: rate numerator */
+	unsigned int rate_den;		/* R: rate denominator */
+	snd_pcm_uframes_t fifo_size;	/* R: chip FIFO size in frames */
+	unsigned char reserved[64];	/* reserved for future */
+};
+
+enum {
+	SNDRV_PCM_TSTAMP_NONE = 0,
+	SNDRV_PCM_TSTAMP_ENABLE,
+	SNDRV_PCM_TSTAMP_LAST = SNDRV_PCM_TSTAMP_ENABLE,
+};
+
+struct snd_pcm_sw_params {
+	int tstamp_mode;			/* timestamp mode */
+	unsigned int period_step;
+	unsigned int sleep_min;			/* min ticks to sleep */
+	snd_pcm_uframes_t avail_min;		/* min avail frames for wakeup */
+	snd_pcm_uframes_t xfer_align;		/* obsolete: xfer size need to be a multiple */
+	snd_pcm_uframes_t start_threshold;	/* min hw_avail frames for automatic start */
+	snd_pcm_uframes_t stop_threshold;	/* min avail frames for automatic stop */
+	snd_pcm_uframes_t silence_threshold;	/* min distance from noise for silence filling */
+	snd_pcm_uframes_t silence_size;		/* silence block size */
+	snd_pcm_uframes_t boundary;		/* pointers wrap point */
+	unsigned char reserved[64];		/* reserved for future */
+};
+
+struct snd_pcm_channel_info {
+	unsigned int channel;
+	__kernel_off_t offset;		/* mmap offset */
+	unsigned int first;		/* offset to first sample in bits */
+	unsigned int step;		/* samples distance in bits */
+};
+
+struct snd_pcm_status {
+	snd_pcm_state_t state;		/* stream state */
+	struct timespec trigger_tstamp;	/* time when stream was started/stopped/paused */
+	struct timespec tstamp;		/* reference timestamp */
+	snd_pcm_uframes_t appl_ptr;	/* appl ptr */
+	snd_pcm_uframes_t hw_ptr;	/* hw ptr */
+	snd_pcm_sframes_t delay;	/* current delay in frames */
+	snd_pcm_uframes_t avail;	/* number of frames available */
+	snd_pcm_uframes_t avail_max;	/* max frames available on hw since last status */
+	snd_pcm_uframes_t overrange;	/* count of ADC (capture) overrange detections from last status */
+	snd_pcm_state_t suspended_state; /* suspended stream state */
+	unsigned char reserved[60];	/* must be filled with zero */
+};
+
+struct snd_pcm_mmap_status {
+	snd_pcm_state_t state;		/* RO: state - SNDRV_PCM_STATE_XXXX */
+	int pad1;			/* Needed for 64 bit alignment */
+	snd_pcm_uframes_t hw_ptr;	/* RO: hw ptr (0...boundary-1) */
+	struct timespec tstamp;		/* Timestamp */
+	snd_pcm_state_t suspended_state; /* RO: suspended stream state */
+};
+
+struct snd_pcm_mmap_control {
+	snd_pcm_uframes_t appl_ptr;	/* RW: appl ptr (0...boundary-1) */
+	snd_pcm_uframes_t avail_min;	/* RW: min available frames for wakeup */
+};
+
+#define SNDRV_PCM_SYNC_PTR_HWSYNC	(1<<0)	/* execute hwsync */
+#define SNDRV_PCM_SYNC_PTR_APPL		(1<<1)	/* get appl_ptr from driver (r/w op) */
+#define SNDRV_PCM_SYNC_PTR_AVAIL_MIN	(1<<2)	/* get avail_min from driver */
+
+struct snd_pcm_sync_ptr {
+	unsigned int flags;
+	union {
+		struct snd_pcm_mmap_status status;
+		unsigned char reserved[64];
+	} s;
+	union {
+		struct snd_pcm_mmap_control control;
+		unsigned char reserved[64];
+	} c;
+};
+
+struct snd_xferi {
+	snd_pcm_sframes_t result;
+	void __user *buf;
+	snd_pcm_uframes_t frames;
+};
+
+struct snd_xfern {
+	snd_pcm_sframes_t result;
+	void __user * __user *bufs;
+	snd_pcm_uframes_t frames;
+};
+
+enum {
+	SNDRV_PCM_TSTAMP_TYPE_GETTIMEOFDAY = 0,	/* gettimeofday equivalent */
+	SNDRV_PCM_TSTAMP_TYPE_MONOTONIC,	/* posix_clock_monotonic equivalent */
+	SNDRV_PCM_TSTAMP_TYPE_LAST = SNDRV_PCM_TSTAMP_TYPE_MONOTONIC,
+};
+
+/* channel positions */
+enum {
+	SNDRV_CHMAP_UNKNOWN = 0,
+	SNDRV_CHMAP_NA,		/* N/A, silent */
+	SNDRV_CHMAP_MONO,	/* mono stream */
+	/* this follows the alsa-lib mixer channel value + 3 */
+	SNDRV_CHMAP_FL,		/* front left */
+	SNDRV_CHMAP_FR,		/* front right */
+	SNDRV_CHMAP_RL,		/* rear left */
+	SNDRV_CHMAP_RR,		/* rear right */
+	SNDRV_CHMAP_FC,		/* front center */
+	SNDRV_CHMAP_LFE,	/* LFE */
+	SNDRV_CHMAP_SL,		/* side left */
+	SNDRV_CHMAP_SR,		/* side right */
+	SNDRV_CHMAP_RC,		/* rear center */
+	/* new definitions */
+	SNDRV_CHMAP_FLC,	/* front left center */
+	SNDRV_CHMAP_FRC,	/* front right center */
+	SNDRV_CHMAP_RLC,	/* rear left center */
+	SNDRV_CHMAP_RRC,	/* rear right center */
+	SNDRV_CHMAP_FLW,	/* front left wide */
+	SNDRV_CHMAP_FRW,	/* front right wide */
+	SNDRV_CHMAP_FLH,	/* front left high */
+	SNDRV_CHMAP_FCH,	/* front center high */
+	SNDRV_CHMAP_FRH,	/* front right high */
+	SNDRV_CHMAP_TC,		/* top center */
+	SNDRV_CHMAP_TFL,	/* top front left */
+	SNDRV_CHMAP_TFR,	/* top front right */
+	SNDRV_CHMAP_TFC,	/* top front center */
+	SNDRV_CHMAP_TRL,	/* top rear left */
+	SNDRV_CHMAP_TRR,	/* top rear right */
+	SNDRV_CHMAP_TRC,	/* top rear center */
+	SNDRV_CHMAP_LAST = SNDRV_CHMAP_TRC,
+};
+
+#define SNDRV_CHMAP_POSITION_MASK	0xffff
+#define SNDRV_CHMAP_PHASE_INVERSE	(0x01 << 16)
+#define SNDRV_CHMAP_DRIVER_SPEC		(0x02 << 16)
+
+#define SNDRV_PCM_IOCTL_PVERSION	_IOR('A', 0x00, int)
+#define SNDRV_PCM_IOCTL_INFO		_IOR('A', 0x01, struct snd_pcm_info)
+#define SNDRV_PCM_IOCTL_TSTAMP		_IOW('A', 0x02, int)
+#define SNDRV_PCM_IOCTL_TTSTAMP		_IOW('A', 0x03, int)
+#define SNDRV_PCM_IOCTL_HW_REFINE	_IOWR('A', 0x10, struct snd_pcm_hw_params)
+#define SNDRV_PCM_IOCTL_HW_PARAMS	_IOWR('A', 0x11, struct snd_pcm_hw_params)
+#define SNDRV_PCM_IOCTL_HW_FREE		_IO('A', 0x12)
+#define SNDRV_PCM_IOCTL_SW_PARAMS	_IOWR('A', 0x13, struct snd_pcm_sw_params)
+#define SNDRV_PCM_IOCTL_STATUS		_IOR('A', 0x20, struct snd_pcm_status)
+#define SNDRV_PCM_IOCTL_DELAY		_IOR('A', 0x21, snd_pcm_sframes_t)
+#define SNDRV_PCM_IOCTL_HWSYNC		_IO('A', 0x22)
+#define SNDRV_PCM_IOCTL_SYNC_PTR	_IOWR('A', 0x23, struct snd_pcm_sync_ptr)
+#define SNDRV_PCM_IOCTL_CHANNEL_INFO	_IOR('A', 0x32, struct snd_pcm_channel_info)
+#define SNDRV_PCM_IOCTL_PREPARE		_IO('A', 0x40)
+#define SNDRV_PCM_IOCTL_RESET		_IO('A', 0x41)
+#define SNDRV_PCM_IOCTL_START		_IO('A', 0x42)
+#define SNDRV_PCM_IOCTL_DROP		_IO('A', 0x43)
+#define SNDRV_PCM_IOCTL_DRAIN		_IO('A', 0x44)
+#define SNDRV_PCM_IOCTL_PAUSE		_IOW('A', 0x45, int)
+#define SNDRV_PCM_IOCTL_REWIND		_IOW('A', 0x46, snd_pcm_uframes_t)
+#define SNDRV_PCM_IOCTL_RESUME		_IO('A', 0x47)
+#define SNDRV_PCM_IOCTL_XRUN		_IO('A', 0x48)
+#define SNDRV_PCM_IOCTL_FORWARD		_IOW('A', 0x49, snd_pcm_uframes_t)
+#define SNDRV_PCM_IOCTL_WRITEI_FRAMES	_IOW('A', 0x50, struct snd_xferi)
+#define SNDRV_PCM_IOCTL_READI_FRAMES	_IOR('A', 0x51, struct snd_xferi)
+#define SNDRV_PCM_IOCTL_WRITEN_FRAMES	_IOW('A', 0x52, struct snd_xfern)
+#define SNDRV_PCM_IOCTL_READN_FRAMES	_IOR('A', 0x53, struct snd_xfern)
+#define SNDRV_PCM_IOCTL_LINK		_IOW('A', 0x60, int)
+#define SNDRV_PCM_IOCTL_UNLINK		_IO('A', 0x61)
+
+/*****************************************************************************
+ *                                                                           *
+ *                            MIDI v1.0 interface                            *
+ *                                                                           *
+ *****************************************************************************/
+
+/*
+ *  Raw MIDI section - /dev/snd/midi??
+ */
+
+#define SNDRV_RAWMIDI_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 0)
+
+enum {
+	SNDRV_RAWMIDI_STREAM_OUTPUT = 0,
+	SNDRV_RAWMIDI_STREAM_INPUT,
+	SNDRV_RAWMIDI_STREAM_LAST = SNDRV_RAWMIDI_STREAM_INPUT,
+};
+
+#define SNDRV_RAWMIDI_INFO_OUTPUT		0x00000001
+#define SNDRV_RAWMIDI_INFO_INPUT		0x00000002
+#define SNDRV_RAWMIDI_INFO_DUPLEX		0x00000004
+
+struct snd_rawmidi_info {
+	unsigned int device;		/* RO/WR (control): device number */
+	unsigned int subdevice;		/* RO/WR (control): subdevice number */
+	int stream;			/* WR: stream */
+	int card;			/* R: card number */
+	unsigned int flags;		/* SNDRV_RAWMIDI_INFO_XXXX */
+	unsigned char id[64];		/* ID (user selectable) */
+	unsigned char name[80];		/* name of device */
+	unsigned char subname[32];	/* name of active or selected subdevice */
+	unsigned int subdevices_count;
+	unsigned int subdevices_avail;
+	unsigned char reserved[64];	/* reserved for future use */
+};
+
+struct snd_rawmidi_params {
+	int stream;
+	size_t buffer_size;		/* queue size in bytes */
+	size_t avail_min;		/* minimum avail bytes for wakeup */
+	unsigned int no_active_sensing: 1; /* do not send active sensing byte in close() */
+	unsigned char reserved[16];	/* reserved for future use */
+};
+
+struct snd_rawmidi_status {
+	int stream;
+	struct timespec tstamp;		/* Timestamp */
+	size_t avail;			/* available bytes */
+	size_t xruns;			/* count of overruns since last status (in bytes) */
+	unsigned char reserved[16];	/* reserved for future use */
+};
+
+#define SNDRV_RAWMIDI_IOCTL_PVERSION	_IOR('W', 0x00, int)
+#define SNDRV_RAWMIDI_IOCTL_INFO	_IOR('W', 0x01, struct snd_rawmidi_info)
+#define SNDRV_RAWMIDI_IOCTL_PARAMS	_IOWR('W', 0x10, struct snd_rawmidi_params)
+#define SNDRV_RAWMIDI_IOCTL_STATUS	_IOWR('W', 0x20, struct snd_rawmidi_status)
+#define SNDRV_RAWMIDI_IOCTL_DROP	_IOW('W', 0x30, int)
+#define SNDRV_RAWMIDI_IOCTL_DRAIN	_IOW('W', 0x31, int)
+
+/*
+ *  Timer section - /dev/snd/timer
+ */
+
+#define SNDRV_TIMER_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 6)
+
+enum {
+	SNDRV_TIMER_CLASS_NONE = -1,
+	SNDRV_TIMER_CLASS_SLAVE = 0,
+	SNDRV_TIMER_CLASS_GLOBAL,
+	SNDRV_TIMER_CLASS_CARD,
+	SNDRV_TIMER_CLASS_PCM,
+	SNDRV_TIMER_CLASS_LAST = SNDRV_TIMER_CLASS_PCM,
+};
+
+/* slave timer classes */
+enum {
+	SNDRV_TIMER_SCLASS_NONE = 0,
+	SNDRV_TIMER_SCLASS_APPLICATION,
+	SNDRV_TIMER_SCLASS_SEQUENCER,		/* alias */
+	SNDRV_TIMER_SCLASS_OSS_SEQUENCER,	/* alias */
+	SNDRV_TIMER_SCLASS_LAST = SNDRV_TIMER_SCLASS_OSS_SEQUENCER,
+};
+
+/* global timers (device member) */
+#define SNDRV_TIMER_GLOBAL_SYSTEM	0
+#define SNDRV_TIMER_GLOBAL_RTC		1
+#define SNDRV_TIMER_GLOBAL_HPET		2
+#define SNDRV_TIMER_GLOBAL_HRTIMER	3
+
+/* info flags */
+#define SNDRV_TIMER_FLG_SLAVE		(1<<0)	/* cannot be controlled */
+
+struct snd_timer_id {
+	int dev_class;
+	int dev_sclass;
+	int card;
+	int device;
+	int subdevice;
+};
+
+struct snd_timer_ginfo {
+	struct snd_timer_id tid;	/* requested timer ID */
+	unsigned int flags;		/* timer flags - SNDRV_TIMER_FLG_* */
+	int card;			/* card number */
+	unsigned char id[64];		/* timer identification */
+	unsigned char name[80];		/* timer name */
+	unsigned long reserved0;	/* reserved for future use */
+	unsigned long resolution;	/* average period resolution in ns */
+	unsigned long resolution_min;	/* minimal period resolution in ns */
+	unsigned long resolution_max;	/* maximal period resolution in ns */
+	unsigned int clients;		/* active timer clients */
+	unsigned char reserved[32];
+};
+
+struct snd_timer_gparams {
+	struct snd_timer_id tid;	/* requested timer ID */
+	unsigned long period_num;	/* requested precise period duration (in seconds) - numerator */
+	unsigned long period_den;	/* requested precise period duration (in seconds) - denominator */
+	unsigned char reserved[32];
+};
+
+struct snd_timer_gstatus {
+	struct snd_timer_id tid;	/* requested timer ID */
+	unsigned long resolution;	/* current period resolution in ns */
+	unsigned long resolution_num;	/* precise current period resolution (in seconds) - numerator */
+	unsigned long resolution_den;	/* precise current period resolution (in seconds) - denominator */
+	unsigned char reserved[32];
+};
+
+struct snd_timer_select {
+	struct snd_timer_id id;	/* bind to timer ID */
+	unsigned char reserved[32];	/* reserved */
+};
+
+struct snd_timer_info {
+	unsigned int flags;		/* timer flags - SNDRV_TIMER_FLG_* */
+	int card;			/* card number */
+	unsigned char id[64];		/* timer identificator */
+	unsigned char name[80];		/* timer name */
+	unsigned long reserved0;	/* reserved for future use */
+	unsigned long resolution;	/* average period resolution in ns */
+	unsigned char reserved[64];	/* reserved */
+};
+
+#define SNDRV_TIMER_PSFLG_AUTO		(1<<0)	/* auto start, otherwise one-shot */
+#define SNDRV_TIMER_PSFLG_EXCLUSIVE	(1<<1)	/* exclusive use, precise start/stop/pause/continue */
+#define SNDRV_TIMER_PSFLG_EARLY_EVENT	(1<<2)	/* write early event to the poll queue */
+
+struct snd_timer_params {
+	unsigned int flags;		/* flags - SNDRV_MIXER_PSFLG_* */
+	unsigned int ticks;		/* requested resolution in ticks */
+	unsigned int queue_size;	/* total size of queue (32-1024) */
+	unsigned int reserved0;		/* reserved, was: failure locations */
+	unsigned int filter;		/* event filter (bitmask of SNDRV_TIMER_EVENT_*) */
+	unsigned char reserved[60];	/* reserved */
+};
+
+struct snd_timer_status {
+	struct timespec tstamp;		/* Timestamp - last update */
+	unsigned int resolution;	/* current period resolution in ns */
+	unsigned int lost;		/* counter of master tick lost */
+	unsigned int overrun;		/* count of read queue overruns */
+	unsigned int queue;		/* used queue size */
+	unsigned char reserved[64];	/* reserved */
+};
+
+#define SNDRV_TIMER_IOCTL_PVERSION	_IOR('T', 0x00, int)
+#define SNDRV_TIMER_IOCTL_NEXT_DEVICE	_IOWR('T', 0x01, struct snd_timer_id)
+#define SNDRV_TIMER_IOCTL_TREAD		_IOW('T', 0x02, int)
+#define SNDRV_TIMER_IOCTL_GINFO		_IOWR('T', 0x03, struct snd_timer_ginfo)
+#define SNDRV_TIMER_IOCTL_GPARAMS	_IOW('T', 0x04, struct snd_timer_gparams)
+#define SNDRV_TIMER_IOCTL_GSTATUS	_IOWR('T', 0x05, struct snd_timer_gstatus)
+#define SNDRV_TIMER_IOCTL_SELECT	_IOW('T', 0x10, struct snd_timer_select)
+#define SNDRV_TIMER_IOCTL_INFO		_IOR('T', 0x11, struct snd_timer_info)
+#define SNDRV_TIMER_IOCTL_PARAMS	_IOW('T', 0x12, struct snd_timer_params)
+#define SNDRV_TIMER_IOCTL_STATUS	_IOR('T', 0x14, struct snd_timer_status)
+/* The following four ioctls are changed since 1.0.9 due to confliction */
+#define SNDRV_TIMER_IOCTL_START		_IO('T', 0xa0)
+#define SNDRV_TIMER_IOCTL_STOP		_IO('T', 0xa1)
+#define SNDRV_TIMER_IOCTL_CONTINUE	_IO('T', 0xa2)
+#define SNDRV_TIMER_IOCTL_PAUSE		_IO('T', 0xa3)
+
+struct snd_timer_read {
+	unsigned int resolution;
+	unsigned int ticks;
+};
+
+enum {
+	SNDRV_TIMER_EVENT_RESOLUTION = 0,	/* val = resolution in ns */
+	SNDRV_TIMER_EVENT_TICK,			/* val = ticks */
+	SNDRV_TIMER_EVENT_START,		/* val = resolution in ns */
+	SNDRV_TIMER_EVENT_STOP,			/* val = 0 */
+	SNDRV_TIMER_EVENT_CONTINUE,		/* val = resolution in ns */
+	SNDRV_TIMER_EVENT_PAUSE,		/* val = 0 */
+	SNDRV_TIMER_EVENT_EARLY,		/* val = 0, early event */
+	SNDRV_TIMER_EVENT_SUSPEND,		/* val = 0 */
+	SNDRV_TIMER_EVENT_RESUME,		/* val = resolution in ns */
+	/* master timer events for slave timer instances */
+	SNDRV_TIMER_EVENT_MSTART = SNDRV_TIMER_EVENT_START + 10,
+	SNDRV_TIMER_EVENT_MSTOP = SNDRV_TIMER_EVENT_STOP + 10,
+	SNDRV_TIMER_EVENT_MCONTINUE = SNDRV_TIMER_EVENT_CONTINUE + 10,
+	SNDRV_TIMER_EVENT_MPAUSE = SNDRV_TIMER_EVENT_PAUSE + 10,
+	SNDRV_TIMER_EVENT_MSUSPEND = SNDRV_TIMER_EVENT_SUSPEND + 10,
+	SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10,
+};
+
+struct snd_timer_tread {
+	int event;
+	struct timespec tstamp;
+	unsigned int val;
+};
+
+/****************************************************************************
+ *                                                                          *
+ *        Section for driver control interface - /dev/snd/control?          *
+ *                                                                          *
+ ****************************************************************************/
+
+#define SNDRV_CTL_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 7)
+
+struct snd_ctl_card_info {
+	int card;			/* card number */
+	int pad;			/* reserved for future (was type) */
+	unsigned char id[16];		/* ID of card (user selectable) */
+	unsigned char driver[16];	/* Driver name */
+	unsigned char name[32];		/* Short name of soundcard */
+	unsigned char longname[80];	/* name + info text about soundcard */
+	unsigned char reserved_[16];	/* reserved for future (was ID of mixer) */
+	unsigned char mixername[80];	/* visual mixer identification */
+	unsigned char components[128];	/* card components / fine identification, delimited with one space (AC97 etc..) */
+};
+
+typedef int __bitwise snd_ctl_elem_type_t;
+#define	SNDRV_CTL_ELEM_TYPE_NONE	((__force snd_ctl_elem_type_t) 0) /* invalid */
+#define	SNDRV_CTL_ELEM_TYPE_BOOLEAN	((__force snd_ctl_elem_type_t) 1) /* boolean type */
+#define	SNDRV_CTL_ELEM_TYPE_INTEGER	((__force snd_ctl_elem_type_t) 2) /* integer type */
+#define	SNDRV_CTL_ELEM_TYPE_ENUMERATED	((__force snd_ctl_elem_type_t) 3) /* enumerated type */
+#define	SNDRV_CTL_ELEM_TYPE_BYTES	((__force snd_ctl_elem_type_t) 4) /* byte array */
+#define	SNDRV_CTL_ELEM_TYPE_IEC958	((__force snd_ctl_elem_type_t) 5) /* IEC958 (S/PDIF) setup */
+#define	SNDRV_CTL_ELEM_TYPE_INTEGER64	((__force snd_ctl_elem_type_t) 6) /* 64-bit integer type */
+#define	SNDRV_CTL_ELEM_TYPE_LAST	SNDRV_CTL_ELEM_TYPE_INTEGER64
+
+typedef int __bitwise snd_ctl_elem_iface_t;
+#define	SNDRV_CTL_ELEM_IFACE_CARD	((__force snd_ctl_elem_iface_t) 0) /* global control */
+#define	SNDRV_CTL_ELEM_IFACE_HWDEP	((__force snd_ctl_elem_iface_t) 1) /* hardware dependent device */
+#define	SNDRV_CTL_ELEM_IFACE_MIXER	((__force snd_ctl_elem_iface_t) 2) /* virtual mixer device */
+#define	SNDRV_CTL_ELEM_IFACE_PCM	((__force snd_ctl_elem_iface_t) 3) /* PCM device */
+#define	SNDRV_CTL_ELEM_IFACE_RAWMIDI	((__force snd_ctl_elem_iface_t) 4) /* RawMidi device */
+#define	SNDRV_CTL_ELEM_IFACE_TIMER	((__force snd_ctl_elem_iface_t) 5) /* timer device */
+#define	SNDRV_CTL_ELEM_IFACE_SEQUENCER	((__force snd_ctl_elem_iface_t) 6) /* sequencer client */
+#define	SNDRV_CTL_ELEM_IFACE_LAST	SNDRV_CTL_ELEM_IFACE_SEQUENCER
+
+#define SNDRV_CTL_ELEM_ACCESS_READ		(1<<0)
+#define SNDRV_CTL_ELEM_ACCESS_WRITE		(1<<1)
+#define SNDRV_CTL_ELEM_ACCESS_READWRITE		(SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
+#define SNDRV_CTL_ELEM_ACCESS_VOLATILE		(1<<2)	/* control value may be changed without a notification */
+#define SNDRV_CTL_ELEM_ACCESS_TIMESTAMP		(1<<3)	/* when was control changed */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_READ		(1<<4)	/* TLV read is possible */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE		(1<<5)	/* TLV write is possible */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE	(SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)
+#define SNDRV_CTL_ELEM_ACCESS_TLV_COMMAND	(1<<6)	/* TLV command is possible */
+#define SNDRV_CTL_ELEM_ACCESS_INACTIVE		(1<<8)	/* control does actually nothing, but may be updated */
+#define SNDRV_CTL_ELEM_ACCESS_LOCK		(1<<9)	/* write lock */
+#define SNDRV_CTL_ELEM_ACCESS_OWNER		(1<<10)	/* write lock owner */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK	(1<<28)	/* kernel use a TLV callback */ 
+#define SNDRV_CTL_ELEM_ACCESS_USER		(1<<29) /* user space element */
+/* bits 30 and 31 are obsoleted (for indirect access) */
+
+/* for further details see the ACPI and PCI power management specification */
+#define SNDRV_CTL_POWER_D0		0x0000	/* full On */
+#define SNDRV_CTL_POWER_D1		0x0100	/* partial On */
+#define SNDRV_CTL_POWER_D2		0x0200	/* partial On */
+#define SNDRV_CTL_POWER_D3		0x0300	/* Off */
+#define SNDRV_CTL_POWER_D3hot		(SNDRV_CTL_POWER_D3|0x0000)	/* Off, with power */
+#define SNDRV_CTL_POWER_D3cold		(SNDRV_CTL_POWER_D3|0x0001)	/* Off, without power */
+
+struct snd_ctl_elem_id {
+	unsigned int numid;		/* numeric identifier, zero = invalid */
+	snd_ctl_elem_iface_t iface;	/* interface identifier */
+	unsigned int device;		/* device/client number */
+	unsigned int subdevice;		/* subdevice (substream) number */
+	unsigned char name[44];		/* ASCII name of item */
+	unsigned int index;		/* index of item */
+};
+
+struct snd_ctl_elem_list {
+	unsigned int offset;		/* W: first element ID to get */
+	unsigned int space;		/* W: count of element IDs to get */
+	unsigned int used;		/* R: count of element IDs set */
+	unsigned int count;		/* R: count of all elements */
+	struct snd_ctl_elem_id __user *pids; /* R: IDs */
+	unsigned char reserved[50];
+};
+
+struct snd_ctl_elem_info {
+	struct snd_ctl_elem_id id;	/* W: element ID */
+	snd_ctl_elem_type_t type;	/* R: value type - SNDRV_CTL_ELEM_TYPE_* */
+	unsigned int access;		/* R: value access (bitmask) - SNDRV_CTL_ELEM_ACCESS_* */
+	unsigned int count;		/* count of values */
+	__kernel_pid_t owner;		/* owner's PID of this control */
+	union {
+		struct {
+			long min;		/* R: minimum value */
+			long max;		/* R: maximum value */
+			long step;		/* R: step (0 variable) */
+		} integer;
+		struct {
+			long long min;		/* R: minimum value */
+			long long max;		/* R: maximum value */
+			long long step;		/* R: step (0 variable) */
+		} integer64;
+		struct {
+			unsigned int items;	/* R: number of items */
+			unsigned int item;	/* W: item number */
+			char name[64];		/* R: value name */
+			__u64 names_ptr;	/* W: names list (ELEM_ADD only) */
+			unsigned int names_length;
+		} enumerated;
+		unsigned char reserved[128];
+	} value;
+	union {
+		unsigned short d[4];		/* dimensions */
+		unsigned short *d_ptr;		/* indirect - obsoleted */
+	} dimen;
+	unsigned char reserved[64-4*sizeof(unsigned short)];
+};
+
+struct snd_ctl_elem_value {
+	struct snd_ctl_elem_id id;	/* W: element ID */
+	unsigned int indirect: 1;	/* W: indirect access - obsoleted */
+	union {
+		union {
+			long value[128];
+			long *value_ptr;	/* obsoleted */
+		} integer;
+		union {
+			long long value[64];
+			long long *value_ptr;	/* obsoleted */
+		} integer64;
+		union {
+			unsigned int item[128];
+			unsigned int *item_ptr;	/* obsoleted */
+		} enumerated;
+		union {
+			unsigned char data[512];
+			unsigned char *data_ptr;	/* obsoleted */
+		} bytes;
+		struct snd_aes_iec958 iec958;
+	} value;		/* RO */
+	struct timespec tstamp;
+	unsigned char reserved[128-sizeof(struct timespec)];
+};
+
+struct snd_ctl_tlv {
+	unsigned int numid;	/* control element numeric identification */
+	unsigned int length;	/* in bytes aligned to 4 */
+	unsigned int tlv[0];	/* first TLV */
+};
+
+#define SNDRV_CTL_IOCTL_PVERSION	_IOR('U', 0x00, int)
+#define SNDRV_CTL_IOCTL_CARD_INFO	_IOR('U', 0x01, struct snd_ctl_card_info)
+#define SNDRV_CTL_IOCTL_ELEM_LIST	_IOWR('U', 0x10, struct snd_ctl_elem_list)
+#define SNDRV_CTL_IOCTL_ELEM_INFO	_IOWR('U', 0x11, struct snd_ctl_elem_info)
+#define SNDRV_CTL_IOCTL_ELEM_READ	_IOWR('U', 0x12, struct snd_ctl_elem_value)
+#define SNDRV_CTL_IOCTL_ELEM_WRITE	_IOWR('U', 0x13, struct snd_ctl_elem_value)
+#define SNDRV_CTL_IOCTL_ELEM_LOCK	_IOW('U', 0x14, struct snd_ctl_elem_id)
+#define SNDRV_CTL_IOCTL_ELEM_UNLOCK	_IOW('U', 0x15, struct snd_ctl_elem_id)
+#define SNDRV_CTL_IOCTL_SUBSCRIBE_EVENTS _IOWR('U', 0x16, int)
+#define SNDRV_CTL_IOCTL_ELEM_ADD	_IOWR('U', 0x17, struct snd_ctl_elem_info)
+#define SNDRV_CTL_IOCTL_ELEM_REPLACE	_IOWR('U', 0x18, struct snd_ctl_elem_info)
+#define SNDRV_CTL_IOCTL_ELEM_REMOVE	_IOWR('U', 0x19, struct snd_ctl_elem_id)
+#define SNDRV_CTL_IOCTL_TLV_READ	_IOWR('U', 0x1a, struct snd_ctl_tlv)
+#define SNDRV_CTL_IOCTL_TLV_WRITE	_IOWR('U', 0x1b, struct snd_ctl_tlv)
+#define SNDRV_CTL_IOCTL_TLV_COMMAND	_IOWR('U', 0x1c, struct snd_ctl_tlv)
+#define SNDRV_CTL_IOCTL_HWDEP_NEXT_DEVICE _IOWR('U', 0x20, int)
+#define SNDRV_CTL_IOCTL_HWDEP_INFO	_IOR('U', 0x21, struct snd_hwdep_info)
+#define SNDRV_CTL_IOCTL_PCM_NEXT_DEVICE	_IOR('U', 0x30, int)
+#define SNDRV_CTL_IOCTL_PCM_INFO	_IOWR('U', 0x31, struct snd_pcm_info)
+#define SNDRV_CTL_IOCTL_PCM_PREFER_SUBDEVICE _IOW('U', 0x32, int)
+#define SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE _IOWR('U', 0x40, int)
+#define SNDRV_CTL_IOCTL_RAWMIDI_INFO	_IOWR('U', 0x41, struct snd_rawmidi_info)
+#define SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE _IOW('U', 0x42, int)
+#define SNDRV_CTL_IOCTL_POWER		_IOWR('U', 0xd0, int)
+#define SNDRV_CTL_IOCTL_POWER_STATE	_IOR('U', 0xd1, int)
+
+/*
+ *  Read interface.
+ */
+
+enum sndrv_ctl_event_type {
+	SNDRV_CTL_EVENT_ELEM = 0,
+	SNDRV_CTL_EVENT_LAST = SNDRV_CTL_EVENT_ELEM,
+};
+
+#define SNDRV_CTL_EVENT_MASK_VALUE	(1<<0)	/* element value was changed */
+#define SNDRV_CTL_EVENT_MASK_INFO	(1<<1)	/* element info was changed */
+#define SNDRV_CTL_EVENT_MASK_ADD	(1<<2)	/* element was added */
+#define SNDRV_CTL_EVENT_MASK_TLV	(1<<3)	/* element TLV tree was changed */
+#define SNDRV_CTL_EVENT_MASK_REMOVE	(~0U)	/* element was removed */
+
+struct snd_ctl_event {
+	int type;	/* event type - SNDRV_CTL_EVENT_* */
+	union {
+		struct {
+			unsigned int mask;
+			struct snd_ctl_elem_id id;
+		} elem;
+		unsigned char data8[60];
+	} data;
+};
+
+/*
+ *  Control names
+ */
+
+#define SNDRV_CTL_NAME_NONE				""
+#define SNDRV_CTL_NAME_PLAYBACK				"Playback "
+#define SNDRV_CTL_NAME_CAPTURE				"Capture "
+
+#define SNDRV_CTL_NAME_IEC958_NONE			""
+#define SNDRV_CTL_NAME_IEC958_SWITCH			"Switch"
+#define SNDRV_CTL_NAME_IEC958_VOLUME			"Volume"
+#define SNDRV_CTL_NAME_IEC958_DEFAULT			"Default"
+#define SNDRV_CTL_NAME_IEC958_MASK			"Mask"
+#define SNDRV_CTL_NAME_IEC958_CON_MASK			"Con Mask"
+#define SNDRV_CTL_NAME_IEC958_PRO_MASK			"Pro Mask"
+#define SNDRV_CTL_NAME_IEC958_PCM_STREAM		"PCM Stream"
+#define SNDRV_CTL_NAME_IEC958(expl,direction,what)	"IEC958 " expl SNDRV_CTL_NAME_##direction SNDRV_CTL_NAME_IEC958_##what
+
+#endif /* _UAPI__SOUND_ASOUND_H */
diff --git a/include/uapi/sound/asound_fm.h b/include/uapi/sound/asound_fm.h
new file mode 100644
index 000000000000..c2a4b967d5be
--- /dev/null
+++ b/include/uapi/sound/asound_fm.h
@@ -0,0 +1,134 @@
+#ifndef __SOUND_ASOUND_FM_H
+#define __SOUND_ASOUND_FM_H
+
+/*
+ *  Advanced Linux Sound Architecture - ALSA
+ *
+ *  Interface file between ALSA driver & user space
+ *  Copyright (c) 1994-98 by Jaroslav Kysela <perex@perex.cz>,
+ *                           4Front Technologies
+ *
+ *  Direct FM control
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program; if not, write to the Free Software
+ *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ */
+
+#define SNDRV_DM_FM_MODE_OPL2	0x00
+#define SNDRV_DM_FM_MODE_OPL3	0x01
+
+struct snd_dm_fm_info {
+	unsigned char fm_mode;		/* OPL mode, see SNDRV_DM_FM_MODE_XXX */
+	unsigned char rhythm;		/* percussion mode flag */
+};
+
+/*
+ *  Data structure composing an FM "note" or sound event.
+ */
+
+struct snd_dm_fm_voice {
+	unsigned char op;		/* operator cell (0 or 1) */
+	unsigned char voice;		/* FM voice (0 to 17) */
+
+	unsigned char am;		/* amplitude modulation */
+	unsigned char vibrato;		/* vibrato effect */
+	unsigned char do_sustain;	/* sustain phase */
+	unsigned char kbd_scale;	/* keyboard scaling */
+	unsigned char harmonic;		/* 4 bits: harmonic and multiplier */
+	unsigned char scale_level;	/* 2 bits: decrease output freq rises */
+	unsigned char volume;		/* 6 bits: volume */
+
+	unsigned char attack;		/* 4 bits: attack rate */
+	unsigned char decay;		/* 4 bits: decay rate */
+	unsigned char sustain;		/* 4 bits: sustain level */
+	unsigned char release;		/* 4 bits: release rate */
+
+	unsigned char feedback;		/* 3 bits: feedback for op0 */
+	unsigned char connection;	/* 0 for serial, 1 for parallel */
+	unsigned char left;		/* stereo left */
+	unsigned char right;		/* stereo right */
+	unsigned char waveform;		/* 3 bits: waveform shape */
+};
+
+/*
+ *  This describes an FM note by its voice, octave, frequency number (10bit)
+ *  and key on/off.
+ */
+
+struct snd_dm_fm_note {
+	unsigned char voice;	/* 0-17 voice channel */
+	unsigned char octave;	/* 3 bits: what octave to play */
+	unsigned int fnum;	/* 10 bits: frequency number */
+	unsigned char key_on;	/* set for active, clear for silent */
+};
+
+/*
+ *  FM parameters that apply globally to all voices, and thus are not "notes"
+ */
+
+struct snd_dm_fm_params {
+	unsigned char am_depth;		/* amplitude modulation depth (1=hi) */
+	unsigned char vib_depth;	/* vibrato depth (1=hi) */
+	unsigned char kbd_split;	/* keyboard split */
+	unsigned char rhythm;		/* percussion mode select */
+
+	/* This block is the percussion instrument data */
+	unsigned char bass;
+	unsigned char snare;
+	unsigned char tomtom;
+	unsigned char cymbal;
+	unsigned char hihat;
+};
+
+/*
+ *  FM mode ioctl settings
+ */
+
+#define SNDRV_DM_FM_IOCTL_INFO		_IOR('H', 0x20, struct snd_dm_fm_info)
+#define SNDRV_DM_FM_IOCTL_RESET		_IO ('H', 0x21)
+#define SNDRV_DM_FM_IOCTL_PLAY_NOTE	_IOW('H', 0x22, struct snd_dm_fm_note)
+#define SNDRV_DM_FM_IOCTL_SET_VOICE	_IOW('H', 0x23, struct snd_dm_fm_voice)
+#define SNDRV_DM_FM_IOCTL_SET_PARAMS	_IOW('H', 0x24, struct snd_dm_fm_params)
+#define SNDRV_DM_FM_IOCTL_SET_MODE	_IOW('H', 0x25, int)
+/* for OPL3 only */
+#define SNDRV_DM_FM_IOCTL_SET_CONNECTION	_IOW('H', 0x26, int)
+/* SBI patch management */
+#define SNDRV_DM_FM_IOCTL_CLEAR_PATCHES	_IO ('H', 0x40)
+
+#define SNDRV_DM_FM_OSS_IOCTL_RESET		0x20
+#define SNDRV_DM_FM_OSS_IOCTL_PLAY_NOTE		0x21
+#define SNDRV_DM_FM_OSS_IOCTL_SET_VOICE		0x22
+#define SNDRV_DM_FM_OSS_IOCTL_SET_PARAMS	0x23
+#define SNDRV_DM_FM_OSS_IOCTL_SET_MODE		0x24
+#define SNDRV_DM_FM_OSS_IOCTL_SET_OPL		0x25
+
+/*
+ * Patch Record - fixed size for write
+ */
+
+#define FM_KEY_SBI	"SBI\032"
+#define FM_KEY_2OP	"2OP\032"
+#define FM_KEY_4OP	"4OP\032"
+
+struct sbi_patch {
+	unsigned char prog;
+	unsigned char bank;
+	char key[4];
+	char name[25];
+	char extension[7];
+	unsigned char data[32];
+};
+
+#endif /* __SOUND_ASOUND_FM_H */
diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h
new file mode 100644
index 000000000000..05341a43fedf
--- /dev/null
+++ b/include/uapi/sound/compress_offload.h
@@ -0,0 +1,161 @@
+/*
+ *  compress_offload.h - compress offload header definations
+ *
+ *  Copyright (C) 2011 Intel Corporation
+ *  Authors:	Vinod Koul <vinod.koul@linux.intel.com>
+ *		Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
+ *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ */
+#ifndef __COMPRESS_OFFLOAD_H
+#define __COMPRESS_OFFLOAD_H
+
+#include <linux/types.h>
+#include <sound/asound.h>
+#include <sound/compress_params.h>
+
+
+#define SNDRV_COMPRESS_VERSION SNDRV_PROTOCOL_VERSION(0, 1, 0)
+/**
+ * struct snd_compressed_buffer: compressed buffer
+ * @fragment_size: size of buffer fragment in bytes
+ * @fragments: number of such fragments
+ */
+struct snd_compressed_buffer {
+	__u32 fragment_size;
+	__u32 fragments;
+};
+
+/**
+ * struct snd_compr_params: compressed stream params
+ * @buffer: buffer description
+ * @codec: codec parameters
+ * @no_wake_mode: dont wake on fragment elapsed
+ */
+struct snd_compr_params {
+	struct snd_compressed_buffer buffer;
+	struct snd_codec codec;
+	__u8 no_wake_mode;
+};
+
+/**
+ * struct snd_compr_tstamp: timestamp descriptor
+ * @byte_offset: Byte offset in ring buffer to DSP
+ * @copied_total: Total number of bytes copied from/to ring buffer to/by DSP
+ * @pcm_frames: Frames decoded or encoded by DSP. This field will evolve by
+ *	large steps and should only be used to monitor encoding/decoding
+ *	progress. It shall not be used for timing estimates.
+ * @pcm_io_frames: Frames rendered or received by DSP into a mixer or an audio
+ * output/input. This field should be used for A/V sync or time estimates.
+ * @sampling_rate: sampling rate of audio
+ */
+struct snd_compr_tstamp {
+	__u32 byte_offset;
+	__u32 copied_total;
+	snd_pcm_uframes_t pcm_frames;
+	snd_pcm_uframes_t pcm_io_frames;
+	__u32 sampling_rate;
+};
+
+/**
+ * struct snd_compr_avail: avail descriptor
+ * @avail: Number of bytes available in ring buffer for writing/reading
+ * @tstamp: timestamp infomation
+ */
+struct snd_compr_avail {
+	__u64 avail;
+	struct snd_compr_tstamp tstamp;
+};
+
+enum snd_compr_direction {
+	SND_COMPRESS_PLAYBACK = 0,
+	SND_COMPRESS_CAPTURE
+};
+
+/**
+ * struct snd_compr_caps: caps descriptor
+ * @codecs: pointer to array of codecs
+ * @direction: direction supported. Of type snd_compr_direction
+ * @min_fragment_size: minimum fragment supported by DSP
+ * @max_fragment_size: maximum fragment supported by DSP
+ * @min_fragments: min fragments supported by DSP
+ * @max_fragments: max fragments supported by DSP
+ * @num_codecs: number of codecs supported
+ * @reserved: reserved field
+ */
+struct snd_compr_caps {
+	__u32 num_codecs;
+	__u32 direction;
+	__u32 min_fragment_size;
+	__u32 max_fragment_size;
+	__u32 min_fragments;
+	__u32 max_fragments;
+	__u32 codecs[MAX_NUM_CODECS];
+	__u32 reserved[11];
+};
+
+/**
+ * struct snd_compr_codec_caps: query capability of codec
+ * @codec: codec for which capability is queried
+ * @num_descriptors: number of codec descriptors
+ * @descriptor: array of codec capability descriptor
+ */
+struct snd_compr_codec_caps {
+	__u32 codec;
+	__u32 num_descriptors;
+	struct snd_codec_desc descriptor[MAX_NUM_CODEC_DESCRIPTORS];
+};
+
+/**
+ * compress path ioctl definitions
+ * SNDRV_COMPRESS_GET_CAPS: Query capability of DSP
+ * SNDRV_COMPRESS_GET_CODEC_CAPS: Query capability of a codec
+ * SNDRV_COMPRESS_SET_PARAMS: Set codec and stream parameters
+ * Note: only codec params can be changed runtime and stream params cant be
+ * SNDRV_COMPRESS_GET_PARAMS: Query codec params
+ * SNDRV_COMPRESS_TSTAMP: get the current timestamp value
+ * SNDRV_COMPRESS_AVAIL: get the current buffer avail value.
+ * This also queries the tstamp properties
+ * SNDRV_COMPRESS_PAUSE: Pause the running stream
+ * SNDRV_COMPRESS_RESUME: resume a paused stream
+ * SNDRV_COMPRESS_START: Start a stream
+ * SNDRV_COMPRESS_STOP: stop a running stream, discarding ring buffer content
+ * and the buffers currently with DSP
+ * SNDRV_COMPRESS_DRAIN: Play till end of buffers and stop after that
+ * SNDRV_COMPRESS_IOCTL_VERSION: Query the API version
+ */
+#define SNDRV_COMPRESS_IOCTL_VERSION	_IOR('C', 0x00, int)
+#define SNDRV_COMPRESS_GET_CAPS		_IOWR('C', 0x10, struct snd_compr_caps)
+#define SNDRV_COMPRESS_GET_CODEC_CAPS	_IOWR('C', 0x11,\
+						struct snd_compr_codec_caps)
+#define SNDRV_COMPRESS_SET_PARAMS	_IOW('C', 0x12, struct snd_compr_params)
+#define SNDRV_COMPRESS_GET_PARAMS	_IOR('C', 0x13, struct snd_codec)
+#define SNDRV_COMPRESS_TSTAMP		_IOR('C', 0x20, struct snd_compr_tstamp)
+#define SNDRV_COMPRESS_AVAIL		_IOR('C', 0x21, struct snd_compr_avail)
+#define SNDRV_COMPRESS_PAUSE		_IO('C', 0x30)
+#define SNDRV_COMPRESS_RESUME		_IO('C', 0x31)
+#define SNDRV_COMPRESS_START		_IO('C', 0x32)
+#define SNDRV_COMPRESS_STOP		_IO('C', 0x33)
+#define SNDRV_COMPRESS_DRAIN		_IO('C', 0x34)
+/*
+ * TODO
+ * 1. add mmap support
+ *
+ */
+#define SND_COMPR_TRIGGER_DRAIN 7 /*FIXME move this to pcm.h */
+#endif
diff --git a/include/uapi/sound/compress_params.h b/include/uapi/sound/compress_params.h
new file mode 100644
index 000000000000..602dc6c45d1a
--- /dev/null
+++ b/include/uapi/sound/compress_params.h
@@ -0,0 +1,400 @@
+/*
+ *  compress_params.h - codec types and parameters for compressed data
+ *  streaming interface
+ *
+ *  Copyright (C) 2011 Intel Corporation
+ *  Authors:	Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
+ *              Vinod Koul <vinod.koul@linux.intel.com>
+ *
+ *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * The definitions in this file are derived from the OpenMAX AL version 1.1
+ * and OpenMAX IL v 1.1.2 header files which contain the copyright notice below.
+ *
+ * Copyright (c) 2007-2010 The Khronos Group Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining
+ * a copy of this software and/or associated documentation files (the
+ * "Materials "), to deal in the Materials without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sublicense, and/or sell copies of the Materials, and to
+ * permit persons to whom the Materials are furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Materials.
+ *
+ * THE MATERIALS ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+ * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ * MATERIALS OR THE USE OR OTHER DEALINGS IN THE MATERIALS.
+ *
+ */
+#ifndef __SND_COMPRESS_PARAMS_H
+#define __SND_COMPRESS_PARAMS_H
+
+#include <linux/types.h>
+
+/* AUDIO CODECS SUPPORTED */
+#define MAX_NUM_CODECS 32
+#define MAX_NUM_CODEC_DESCRIPTORS 32
+#define MAX_NUM_BITRATES 32
+
+/* Codecs are listed linearly to allow for extensibility */
+#define SND_AUDIOCODEC_PCM                   ((__u32) 0x00000001)
+#define SND_AUDIOCODEC_MP3                   ((__u32) 0x00000002)
+#define SND_AUDIOCODEC_AMR                   ((__u32) 0x00000003)
+#define SND_AUDIOCODEC_AMRWB                 ((__u32) 0x00000004)
+#define SND_AUDIOCODEC_AMRWBPLUS             ((__u32) 0x00000005)
+#define SND_AUDIOCODEC_AAC                   ((__u32) 0x00000006)
+#define SND_AUDIOCODEC_WMA                   ((__u32) 0x00000007)
+#define SND_AUDIOCODEC_REAL                  ((__u32) 0x00000008)
+#define SND_AUDIOCODEC_VORBIS                ((__u32) 0x00000009)
+#define SND_AUDIOCODEC_FLAC                  ((__u32) 0x0000000A)
+#define SND_AUDIOCODEC_IEC61937              ((__u32) 0x0000000B)
+#define SND_AUDIOCODEC_G723_1                ((__u32) 0x0000000C)
+#define SND_AUDIOCODEC_G729                  ((__u32) 0x0000000D)
+#define SND_AUDIOCODEC_MAX                   SND_AUDIOCODEC_G729
+
+/*
+ * Profile and modes are listed with bit masks. This allows for a
+ * more compact representation of fields that will not evolve
+ * (in contrast to the list of codecs)
+ */
+
+#define SND_AUDIOPROFILE_PCM                 ((__u32) 0x00000001)
+
+/* MP3 modes are only useful for encoders */
+#define SND_AUDIOCHANMODE_MP3_MONO           ((__u32) 0x00000001)
+#define SND_AUDIOCHANMODE_MP3_STEREO         ((__u32) 0x00000002)
+#define SND_AUDIOCHANMODE_MP3_JOINTSTEREO    ((__u32) 0x00000004)
+#define SND_AUDIOCHANMODE_MP3_DUAL           ((__u32) 0x00000008)
+
+#define SND_AUDIOPROFILE_AMR                 ((__u32) 0x00000001)
+
+/* AMR modes are only useful for encoders */
+#define SND_AUDIOMODE_AMR_DTX_OFF            ((__u32) 0x00000001)
+#define SND_AUDIOMODE_AMR_VAD1               ((__u32) 0x00000002)
+#define SND_AUDIOMODE_AMR_VAD2               ((__u32) 0x00000004)
+
+#define SND_AUDIOSTREAMFORMAT_UNDEFINED	     ((__u32) 0x00000000)
+#define SND_AUDIOSTREAMFORMAT_CONFORMANCE    ((__u32) 0x00000001)
+#define SND_AUDIOSTREAMFORMAT_IF1            ((__u32) 0x00000002)
+#define SND_AUDIOSTREAMFORMAT_IF2            ((__u32) 0x00000004)
+#define SND_AUDIOSTREAMFORMAT_FSF            ((__u32) 0x00000008)
+#define SND_AUDIOSTREAMFORMAT_RTPPAYLOAD     ((__u32) 0x00000010)
+#define SND_AUDIOSTREAMFORMAT_ITU            ((__u32) 0x00000020)
+
+#define SND_AUDIOPROFILE_AMRWB               ((__u32) 0x00000001)
+
+/* AMRWB modes are only useful for encoders */
+#define SND_AUDIOMODE_AMRWB_DTX_OFF          ((__u32) 0x00000001)
+#define SND_AUDIOMODE_AMRWB_VAD1             ((__u32) 0x00000002)
+#define SND_AUDIOMODE_AMRWB_VAD2             ((__u32) 0x00000004)
+
+#define SND_AUDIOPROFILE_AMRWBPLUS           ((__u32) 0x00000001)
+
+#define SND_AUDIOPROFILE_AAC                 ((__u32) 0x00000001)
+
+/* AAC modes are required for encoders and decoders */
+#define SND_AUDIOMODE_AAC_MAIN               ((__u32) 0x00000001)
+#define SND_AUDIOMODE_AAC_LC                 ((__u32) 0x00000002)
+#define SND_AUDIOMODE_AAC_SSR                ((__u32) 0x00000004)
+#define SND_AUDIOMODE_AAC_LTP                ((__u32) 0x00000008)
+#define SND_AUDIOMODE_AAC_HE                 ((__u32) 0x00000010)
+#define SND_AUDIOMODE_AAC_SCALABLE           ((__u32) 0x00000020)
+#define SND_AUDIOMODE_AAC_ERLC               ((__u32) 0x00000040)
+#define SND_AUDIOMODE_AAC_LD                 ((__u32) 0x00000080)
+#define SND_AUDIOMODE_AAC_HE_PS              ((__u32) 0x00000100)
+#define SND_AUDIOMODE_AAC_HE_MPS             ((__u32) 0x00000200)
+
+/* AAC formats are required for encoders and decoders */
+#define SND_AUDIOSTREAMFORMAT_MP2ADTS        ((__u32) 0x00000001)
+#define SND_AUDIOSTREAMFORMAT_MP4ADTS        ((__u32) 0x00000002)
+#define SND_AUDIOSTREAMFORMAT_MP4LOAS        ((__u32) 0x00000004)
+#define SND_AUDIOSTREAMFORMAT_MP4LATM        ((__u32) 0x00000008)
+#define SND_AUDIOSTREAMFORMAT_ADIF           ((__u32) 0x00000010)
+#define SND_AUDIOSTREAMFORMAT_MP4FF          ((__u32) 0x00000020)
+#define SND_AUDIOSTREAMFORMAT_RAW            ((__u32) 0x00000040)
+
+#define SND_AUDIOPROFILE_WMA7                ((__u32) 0x00000001)
+#define SND_AUDIOPROFILE_WMA8                ((__u32) 0x00000002)
+#define SND_AUDIOPROFILE_WMA9                ((__u32) 0x00000004)
+#define SND_AUDIOPROFILE_WMA10               ((__u32) 0x00000008)
+
+#define SND_AUDIOMODE_WMA_LEVEL1             ((__u32) 0x00000001)
+#define SND_AUDIOMODE_WMA_LEVEL2             ((__u32) 0x00000002)
+#define SND_AUDIOMODE_WMA_LEVEL3             ((__u32) 0x00000004)
+#define SND_AUDIOMODE_WMA_LEVEL4             ((__u32) 0x00000008)
+#define SND_AUDIOMODE_WMAPRO_LEVELM0         ((__u32) 0x00000010)
+#define SND_AUDIOMODE_WMAPRO_LEVELM1         ((__u32) 0x00000020)
+#define SND_AUDIOMODE_WMAPRO_LEVELM2         ((__u32) 0x00000040)
+#define SND_AUDIOMODE_WMAPRO_LEVELM3         ((__u32) 0x00000080)
+
+#define SND_AUDIOSTREAMFORMAT_WMA_ASF        ((__u32) 0x00000001)
+/*
+ * Some implementations strip the ASF header and only send ASF packets
+ * to the DSP
+ */
+#define SND_AUDIOSTREAMFORMAT_WMA_NOASF_HDR  ((__u32) 0x00000002)
+
+#define SND_AUDIOPROFILE_REALAUDIO           ((__u32) 0x00000001)
+
+#define SND_AUDIOMODE_REALAUDIO_G2           ((__u32) 0x00000001)
+#define SND_AUDIOMODE_REALAUDIO_8            ((__u32) 0x00000002)
+#define SND_AUDIOMODE_REALAUDIO_10           ((__u32) 0x00000004)
+#define SND_AUDIOMODE_REALAUDIO_SURROUND     ((__u32) 0x00000008)
+
+#define SND_AUDIOPROFILE_VORBIS              ((__u32) 0x00000001)
+
+#define SND_AUDIOMODE_VORBIS                 ((__u32) 0x00000001)
+
+#define SND_AUDIOPROFILE_FLAC                ((__u32) 0x00000001)
+
+/*
+ * Define quality levels for FLAC encoders, from LEVEL0 (fast)
+ * to LEVEL8 (best)
+ */
+#define SND_AUDIOMODE_FLAC_LEVEL0            ((__u32) 0x00000001)
+#define SND_AUDIOMODE_FLAC_LEVEL1            ((__u32) 0x00000002)
+#define SND_AUDIOMODE_FLAC_LEVEL2            ((__u32) 0x00000004)
+#define SND_AUDIOMODE_FLAC_LEVEL3            ((__u32) 0x00000008)
+#define SND_AUDIOMODE_FLAC_LEVEL4            ((__u32) 0x00000010)
+#define SND_AUDIOMODE_FLAC_LEVEL5            ((__u32) 0x00000020)
+#define SND_AUDIOMODE_FLAC_LEVEL6            ((__u32) 0x00000040)
+#define SND_AUDIOMODE_FLAC_LEVEL7            ((__u32) 0x00000080)
+#define SND_AUDIOMODE_FLAC_LEVEL8            ((__u32) 0x00000100)
+
+#define SND_AUDIOSTREAMFORMAT_FLAC           ((__u32) 0x00000001)
+#define SND_AUDIOSTREAMFORMAT_FLAC_OGG       ((__u32) 0x00000002)
+
+/* IEC61937 payloads without CUVP and preambles */
+#define SND_AUDIOPROFILE_IEC61937            ((__u32) 0x00000001)
+/* IEC61937 with S/PDIF preambles+CUVP bits in 32-bit containers */
+#define SND_AUDIOPROFILE_IEC61937_SPDIF      ((__u32) 0x00000002)
+
+/*
+ * IEC modes are mandatory for decoders. Format autodetection
+ * will only happen on the DSP side with mode 0. The PCM mode should
+ * not be used, the PCM codec should be used instead.
+ */
+#define SND_AUDIOMODE_IEC_REF_STREAM_HEADER  ((__u32) 0x00000000)
+#define SND_AUDIOMODE_IEC_LPCM		     ((__u32) 0x00000001)
+#define SND_AUDIOMODE_IEC_AC3		     ((__u32) 0x00000002)
+#define SND_AUDIOMODE_IEC_MPEG1		     ((__u32) 0x00000004)
+#define SND_AUDIOMODE_IEC_MP3		     ((__u32) 0x00000008)
+#define SND_AUDIOMODE_IEC_MPEG2		     ((__u32) 0x00000010)
+#define SND_AUDIOMODE_IEC_AACLC		     ((__u32) 0x00000020)
+#define SND_AUDIOMODE_IEC_DTS		     ((__u32) 0x00000040)
+#define SND_AUDIOMODE_IEC_ATRAC		     ((__u32) 0x00000080)
+#define SND_AUDIOMODE_IEC_SACD		     ((__u32) 0x00000100)
+#define SND_AUDIOMODE_IEC_EAC3		     ((__u32) 0x00000200)
+#define SND_AUDIOMODE_IEC_DTS_HD	     ((__u32) 0x00000400)
+#define SND_AUDIOMODE_IEC_MLP		     ((__u32) 0x00000800)
+#define SND_AUDIOMODE_IEC_DST		     ((__u32) 0x00001000)
+#define SND_AUDIOMODE_IEC_WMAPRO	     ((__u32) 0x00002000)
+#define SND_AUDIOMODE_IEC_REF_CXT            ((__u32) 0x00004000)
+#define SND_AUDIOMODE_IEC_HE_AAC	     ((__u32) 0x00008000)
+#define SND_AUDIOMODE_IEC_HE_AAC2	     ((__u32) 0x00010000)
+#define SND_AUDIOMODE_IEC_MPEG_SURROUND	     ((__u32) 0x00020000)
+
+#define SND_AUDIOPROFILE_G723_1              ((__u32) 0x00000001)
+
+#define SND_AUDIOMODE_G723_1_ANNEX_A         ((__u32) 0x00000001)
+#define SND_AUDIOMODE_G723_1_ANNEX_B         ((__u32) 0x00000002)
+#define SND_AUDIOMODE_G723_1_ANNEX_C         ((__u32) 0x00000004)
+
+#define SND_AUDIOPROFILE_G729                ((__u32) 0x00000001)
+
+#define SND_AUDIOMODE_G729_ANNEX_A           ((__u32) 0x00000001)
+#define SND_AUDIOMODE_G729_ANNEX_B           ((__u32) 0x00000002)
+
+/* <FIXME: multichannel encoders aren't supported for now. Would need
+   an additional definition of channel arrangement> */
+
+/* VBR/CBR definitions */
+#define SND_RATECONTROLMODE_CONSTANTBITRATE  ((__u32) 0x00000001)
+#define SND_RATECONTROLMODE_VARIABLEBITRATE  ((__u32) 0x00000002)
+
+/* Encoder options */
+
+struct snd_enc_wma {
+	__u32 super_block_align; /* WMA Type-specific data */
+};
+
+
+/**
+ * struct snd_enc_vorbis
+ * @quality: Sets encoding quality to n, between -1 (low) and 10 (high).
+ * In the default mode of operation, the quality level is 3.
+ * Normal quality range is 0 - 10.
+ * @managed: Boolean. Set  bitrate  management  mode. This turns off the
+ * normal VBR encoding, but allows hard or soft bitrate constraints to be
+ * enforced by the encoder. This mode can be slower, and may also be
+ * lower quality. It is primarily useful for streaming.
+ * @max_bit_rate: Enabled only if managed is TRUE
+ * @min_bit_rate: Enabled only if managed is TRUE
+ * @downmix: Boolean. Downmix input from stereo to mono (has no effect on
+ * non-stereo streams). Useful for lower-bitrate encoding.
+ *
+ * These options were extracted from the OpenMAX IL spec and Gstreamer vorbisenc
+ * properties
+ *
+ * For best quality users should specify VBR mode and set quality levels.
+ */
+
+struct snd_enc_vorbis {
+	__s32 quality;
+	__u32 managed;
+	__u32 max_bit_rate;
+	__u32 min_bit_rate;
+	__u32 downmix;
+};
+
+
+/**
+ * struct snd_enc_real
+ * @quant_bits: number of coupling quantization bits in the stream
+ * @start_region: coupling start region in the stream
+ * @num_regions: number of regions value
+ *
+ * These options were extracted from the OpenMAX IL spec
+ */
+
+struct snd_enc_real {
+	__u32 quant_bits;
+	__u32 start_region;
+	__u32 num_regions;
+};
+
+/**
+ * struct snd_enc_flac
+ * @num: serial number, valid only for OGG formats
+ *	needs to be set by application
+ * @gain: Add replay gain tags
+ *
+ * These options were extracted from the FLAC online documentation
+ * at http://flac.sourceforge.net/documentation_tools_flac.html
+ *
+ * To make the API simpler, it is assumed that the user will select quality
+ * profiles. Additional options that affect encoding quality and speed can
+ * be added at a later stage if needed.
+ *
+ * By default the Subset format is used by encoders.
+ *
+ * TAGS such as pictures, etc, cannot be handled by an offloaded encoder and are
+ * not supported in this API.
+ */
+
+struct snd_enc_flac {
+	__u32 num;
+	__u32 gain;
+};
+
+struct snd_enc_generic {
+	__u32 bw;	/* encoder bandwidth */
+	__s32 reserved[15];
+};
+
+union snd_codec_options {
+	struct snd_enc_wma wma;
+	struct snd_enc_vorbis vorbis;
+	struct snd_enc_real real;
+	struct snd_enc_flac flac;
+	struct snd_enc_generic generic;
+};
+
+/** struct snd_codec_desc - description of codec capabilities
+ * @max_ch: Maximum number of audio channels
+ * @sample_rates: Sampling rates in Hz, use SNDRV_PCM_RATE_xxx for this
+ * @bit_rate: Indexed array containing supported bit rates
+ * @num_bitrates: Number of valid values in bit_rate array
+ * @rate_control: value is specified by SND_RATECONTROLMODE defines.
+ * @profiles: Supported profiles. See SND_AUDIOPROFILE defines.
+ * @modes: Supported modes. See SND_AUDIOMODE defines
+ * @formats: Supported formats. See SND_AUDIOSTREAMFORMAT defines
+ * @min_buffer: Minimum buffer size handled by codec implementation
+ * @reserved: reserved for future use
+ *
+ * This structure provides a scalar value for profiles, modes and stream
+ * format fields.
+ * If an implementation supports multiple combinations, they will be listed as
+ * codecs with different descriptors, for example there would be 2 descriptors
+ * for AAC-RAW and AAC-ADTS.
+ * This entails some redundancy but makes it easier to avoid invalid
+ * configurations.
+ *
+ */
+
+struct snd_codec_desc {
+	__u32 max_ch;
+	__u32 sample_rates;
+	__u32 bit_rate[MAX_NUM_BITRATES];
+	__u32 num_bitrates;
+	__u32 rate_control;
+	__u32 profiles;
+	__u32 modes;
+	__u32 formats;
+	__u32 min_buffer;
+	__u32 reserved[15];
+};
+
+/** struct snd_codec
+ * @id: Identifies the supported audio encoder/decoder.
+ *		See SND_AUDIOCODEC macros.
+ * @ch_in: Number of input audio channels
+ * @ch_out: Number of output channels. In case of contradiction between
+ *		this field and the channelMode field, the channelMode field
+ *		overrides.
+ * @sample_rate: Audio sample rate of input data
+ * @bit_rate: Bitrate of encoded data. May be ignored by decoders
+ * @rate_control: Encoding rate control. See SND_RATECONTROLMODE defines.
+ *               Encoders may rely on profiles for quality levels.
+ *		 May be ignored by decoders.
+ * @profile: Mandatory for encoders, can be mandatory for specific
+ *		decoders as well. See SND_AUDIOPROFILE defines.
+ * @level: Supported level (Only used by WMA at the moment)
+ * @ch_mode: Channel mode for encoder. See SND_AUDIOCHANMODE defines
+ * @format: Format of encoded bistream. Mandatory when defined.
+ *		See SND_AUDIOSTREAMFORMAT defines.
+ * @align: Block alignment in bytes of an audio sample.
+ *		Only required for PCM or IEC formats.
+ * @options: encoder-specific settings
+ * @reserved: reserved for future use
+ */
+
+struct snd_codec {
+	__u32 id;
+	__u32 ch_in;
+	__u32 ch_out;
+	__u32 sample_rate;
+	__u32 bit_rate;
+	__u32 rate_control;
+	__u32 profile;
+	__u32 level;
+	__u32 ch_mode;
+	__u32 format;
+	__u32 align;
+	union snd_codec_options options;
+	__u32 reserved[3];
+};
+
+#endif
diff --git a/include/uapi/sound/emu10k1.h b/include/uapi/sound/emu10k1.h
new file mode 100644
index 000000000000..d1bbaf78457a
--- /dev/null
+++ b/include/uapi/sound/emu10k1.h
@@ -0,0 +1,373 @@
+/*
+ *  Copyright (c) by Jaroslav Kysela <perex@perex.cz>,
+ *		     Creative Labs, Inc.
+ *  Definitions for EMU10K1 (SB Live!) chips
+ *
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program; if not, write to the Free Software
+ *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ */
+#ifndef _UAPI__SOUND_EMU10K1_H
+#define _UAPI__SOUND_EMU10K1_H
+
+#include <linux/types.h>
+
+
+
+/*
+ * ---- FX8010 ----
+ */
+
+#define EMU10K1_CARD_CREATIVE			0x00000000
+#define EMU10K1_CARD_EMUAPS			0x00000001
+
+#define EMU10K1_FX8010_PCM_COUNT		8
+
+/* instruction set */
+#define iMAC0	 0x00	/* R = A + (X * Y >> 31)   ; saturation */
+#define iMAC1	 0x01	/* R = A + (-X * Y >> 31)  ; saturation */
+#define iMAC2	 0x02	/* R = A + (X * Y >> 31)   ; wraparound */
+#define iMAC3	 0x03	/* R = A + (-X * Y >> 31)  ; wraparound */
+#define iMACINT0 0x04	/* R = A + X * Y	   ; saturation */
+#define iMACINT1 0x05	/* R = A + X * Y	   ; wraparound (31-bit) */
+#define iACC3	 0x06	/* R = A + X + Y	   ; saturation */
+#define iMACMV   0x07	/* R = A, acc += X * Y >> 31 */
+#define iANDXOR  0x08	/* R = (A & X) ^ Y */
+#define iTSTNEG  0x09	/* R = (A >= Y) ? X : ~X */
+#define iLIMITGE 0x0a	/* R = (A >= Y) ? X : Y */
+#define iLIMITLT 0x0b	/* R = (A < Y) ? X : Y */
+#define iLOG	 0x0c	/* R = linear_data, A (log_data), X (max_exp), Y (format_word) */
+#define iEXP	 0x0d	/* R = log_data, A (linear_data), X (max_exp), Y (format_word) */
+#define iINTERP  0x0e	/* R = A + (X * (Y - A) >> 31)  ; saturation */
+#define iSKIP    0x0f	/* R = A (cc_reg), X (count), Y (cc_test) */
+
+/* GPRs */
+#define FXBUS(x)	(0x00 + (x))	/* x = 0x00 - 0x0f */
+#define EXTIN(x)	(0x10 + (x))	/* x = 0x00 - 0x0f */
+#define EXTOUT(x)	(0x20 + (x))	/* x = 0x00 - 0x0f physical outs -> FXWC low 16 bits */
+#define FXBUS2(x)	(0x30 + (x))	/* x = 0x00 - 0x0f copies of fx buses for capture -> FXWC high 16 bits */
+					/* NB: 0x31 and 0x32 are shared with Center/LFE on SB live 5.1 */
+
+#define C_00000000	0x40
+#define C_00000001	0x41
+#define C_00000002	0x42
+#define C_00000003	0x43
+#define C_00000004	0x44
+#define C_00000008	0x45
+#define C_00000010	0x46
+#define C_00000020	0x47
+#define C_00000100	0x48
+#define C_00010000	0x49
+#define C_00080000	0x4a
+#define C_10000000	0x4b
+#define C_20000000	0x4c
+#define C_40000000	0x4d
+#define C_80000000	0x4e
+#define C_7fffffff	0x4f
+#define C_ffffffff	0x50
+#define C_fffffffe	0x51
+#define C_c0000000	0x52
+#define C_4f1bbcdc	0x53
+#define C_5a7ef9db	0x54
+#define C_00100000	0x55		/* ?? */
+#define GPR_ACCU	0x56		/* ACCUM, accumulator */
+#define GPR_COND	0x57		/* CCR, condition register */
+#define GPR_NOISE0	0x58		/* noise source */
+#define GPR_NOISE1	0x59		/* noise source */
+#define GPR_IRQ		0x5a		/* IRQ register */
+#define GPR_DBAC	0x5b		/* TRAM Delay Base Address Counter */
+#define GPR(x)		(FXGPREGBASE + (x)) /* free GPRs: x = 0x00 - 0xff */
+#define ITRAM_DATA(x)	(TANKMEMDATAREGBASE + 0x00 + (x)) /* x = 0x00 - 0x7f */
+#define ETRAM_DATA(x)	(TANKMEMDATAREGBASE + 0x80 + (x)) /* x = 0x00 - 0x1f */
+#define ITRAM_ADDR(x)	(TANKMEMADDRREGBASE + 0x00 + (x)) /* x = 0x00 - 0x7f */
+#define ETRAM_ADDR(x)	(TANKMEMADDRREGBASE + 0x80 + (x)) /* x = 0x00 - 0x1f */
+
+#define A_ITRAM_DATA(x)	(TANKMEMDATAREGBASE + 0x00 + (x)) /* x = 0x00 - 0xbf */
+#define A_ETRAM_DATA(x)	(TANKMEMDATAREGBASE + 0xc0 + (x)) /* x = 0x00 - 0x3f */
+#define A_ITRAM_ADDR(x)	(TANKMEMADDRREGBASE + 0x00 + (x)) /* x = 0x00 - 0xbf */
+#define A_ETRAM_ADDR(x)	(TANKMEMADDRREGBASE + 0xc0 + (x)) /* x = 0x00 - 0x3f */
+#define A_ITRAM_CTL(x)	(A_TANKMEMCTLREGBASE + 0x00 + (x)) /* x = 0x00 - 0xbf */
+#define A_ETRAM_CTL(x)	(A_TANKMEMCTLREGBASE + 0xc0 + (x)) /* x = 0x00 - 0x3f */
+
+#define A_FXBUS(x)	(0x00 + (x))	/* x = 0x00 - 0x3f FX buses */
+#define A_EXTIN(x)	(0x40 + (x))	/* x = 0x00 - 0x0f physical ins */
+#define A_P16VIN(x)	(0x50 + (x))	/* x = 0x00 - 0x0f p16v ins (A2 only) "EMU32 inputs" */
+#define A_EXTOUT(x)	(0x60 + (x))	/* x = 0x00 - 0x1f physical outs -> A_FXWC1 0x79-7f unknown   */
+#define A_FXBUS2(x)	(0x80 + (x))	/* x = 0x00 - 0x1f extra outs used for EFX capture -> A_FXWC2 */
+#define A_EMU32OUTH(x)	(0xa0 + (x))	/* x = 0x00 - 0x0f "EMU32_OUT_10 - _1F" - ??? */
+#define A_EMU32OUTL(x)	(0xb0 + (x))	/* x = 0x00 - 0x0f "EMU32_OUT_1 - _F" - ??? */
+#define A3_EMU32IN(x)	(0x160 + (x))	/* x = 0x00 - 0x3f "EMU32_IN_00 - _3F" - Only when .device = 0x0008 */
+#define A3_EMU32OUT(x)	(0x1E0 + (x))	/* x = 0x00 - 0x0f "EMU32_OUT_00 - _3F" - Only when .device = 0x0008 */
+#define A_GPR(x)	(A_FXGPREGBASE + (x))
+
+/* cc_reg constants */
+#define CC_REG_NORMALIZED C_00000001
+#define CC_REG_BORROW	C_00000002
+#define CC_REG_MINUS	C_00000004
+#define CC_REG_ZERO	C_00000008
+#define CC_REG_SATURATE	C_00000010
+#define CC_REG_NONZERO	C_00000100
+
+/* FX buses */
+#define FXBUS_PCM_LEFT		0x00
+#define FXBUS_PCM_RIGHT		0x01
+#define FXBUS_PCM_LEFT_REAR	0x02
+#define FXBUS_PCM_RIGHT_REAR	0x03
+#define FXBUS_MIDI_LEFT		0x04
+#define FXBUS_MIDI_RIGHT	0x05
+#define FXBUS_PCM_CENTER	0x06
+#define FXBUS_PCM_LFE		0x07
+#define FXBUS_PCM_LEFT_FRONT	0x08
+#define FXBUS_PCM_RIGHT_FRONT	0x09
+#define FXBUS_MIDI_REVERB	0x0c
+#define FXBUS_MIDI_CHORUS	0x0d
+#define FXBUS_PCM_LEFT_SIDE	0x0e
+#define FXBUS_PCM_RIGHT_SIDE	0x0f
+#define FXBUS_PT_LEFT		0x14
+#define FXBUS_PT_RIGHT		0x15
+
+/* Inputs */
+#define EXTIN_AC97_L	   0x00	/* AC'97 capture channel - left */
+#define EXTIN_AC97_R	   0x01	/* AC'97 capture channel - right */
+#define EXTIN_SPDIF_CD_L   0x02	/* internal S/PDIF CD - onboard - left */
+#define EXTIN_SPDIF_CD_R   0x03	/* internal S/PDIF CD - onboard - right */
+#define EXTIN_ZOOM_L	   0x04	/* Zoom Video I2S - left */
+#define EXTIN_ZOOM_R	   0x05	/* Zoom Video I2S - right */
+#define EXTIN_TOSLINK_L	   0x06	/* LiveDrive - TOSLink Optical - left */
+#define EXTIN_TOSLINK_R    0x07	/* LiveDrive - TOSLink Optical - right */
+#define EXTIN_LINE1_L	   0x08	/* LiveDrive - Line/Mic 1 - left */
+#define EXTIN_LINE1_R	   0x09	/* LiveDrive - Line/Mic 1 - right */
+#define EXTIN_COAX_SPDIF_L 0x0a	/* LiveDrive - Coaxial S/PDIF - left */
+#define EXTIN_COAX_SPDIF_R 0x0b /* LiveDrive - Coaxial S/PDIF - right */
+#define EXTIN_LINE2_L	   0x0c	/* LiveDrive - Line/Mic 2 - left */
+#define EXTIN_LINE2_R	   0x0d	/* LiveDrive - Line/Mic 2 - right */
+
+/* Outputs */
+#define EXTOUT_AC97_L	   0x00	/* AC'97 playback channel - left */
+#define EXTOUT_AC97_R	   0x01	/* AC'97 playback channel - right */
+#define EXTOUT_TOSLINK_L   0x02	/* LiveDrive - TOSLink Optical - left */
+#define EXTOUT_TOSLINK_R   0x03	/* LiveDrive - TOSLink Optical - right */
+#define EXTOUT_AC97_CENTER 0x04	/* SB Live 5.1 - center */
+#define EXTOUT_AC97_LFE	   0x05 /* SB Live 5.1 - LFE */
+#define EXTOUT_HEADPHONE_L 0x06	/* LiveDrive - Headphone - left */
+#define EXTOUT_HEADPHONE_R 0x07	/* LiveDrive - Headphone - right */
+#define EXTOUT_REAR_L	   0x08	/* Rear channel - left */
+#define EXTOUT_REAR_R	   0x09	/* Rear channel - right */
+#define EXTOUT_ADC_CAP_L   0x0a	/* ADC Capture buffer - left */
+#define EXTOUT_ADC_CAP_R   0x0b	/* ADC Capture buffer - right */
+#define EXTOUT_MIC_CAP	   0x0c	/* MIC Capture buffer */
+#define EXTOUT_AC97_REAR_L 0x0d	/* SB Live 5.1 (c) 2003 - Rear Left */
+#define EXTOUT_AC97_REAR_R 0x0e	/* SB Live 5.1 (c) 2003 - Rear Right */
+#define EXTOUT_ACENTER	   0x11 /* Analog Center */
+#define EXTOUT_ALFE	   0x12 /* Analog LFE */
+
+/* Audigy Inputs */
+#define A_EXTIN_AC97_L		0x00	/* AC'97 capture channel - left */
+#define A_EXTIN_AC97_R		0x01	/* AC'97 capture channel - right */
+#define A_EXTIN_SPDIF_CD_L	0x02	/* digital CD left */
+#define A_EXTIN_SPDIF_CD_R	0x03	/* digital CD left */
+#define A_EXTIN_OPT_SPDIF_L     0x04    /* audigy drive Optical SPDIF - left */
+#define A_EXTIN_OPT_SPDIF_R     0x05    /*                              right */ 
+#define A_EXTIN_LINE2_L		0x08	/* audigy drive line2/mic2 - left */
+#define A_EXTIN_LINE2_R		0x09	/*                           right */
+#define A_EXTIN_ADC_L		0x0a    /* Philips ADC - left */
+#define A_EXTIN_ADC_R		0x0b    /*               right */
+#define A_EXTIN_AUX2_L		0x0c	/* audigy drive aux2 - left */
+#define A_EXTIN_AUX2_R		0x0d	/*                   - right */
+
+/* Audigiy Outputs */
+#define A_EXTOUT_FRONT_L	0x00	/* digital front left */
+#define A_EXTOUT_FRONT_R	0x01	/*               right */
+#define A_EXTOUT_CENTER		0x02	/* digital front center */
+#define A_EXTOUT_LFE		0x03	/* digital front lfe */
+#define A_EXTOUT_HEADPHONE_L	0x04	/* headphone audigy drive left */
+#define A_EXTOUT_HEADPHONE_R	0x05	/*                        right */
+#define A_EXTOUT_REAR_L		0x06	/* digital rear left */
+#define A_EXTOUT_REAR_R		0x07	/*              right */
+#define A_EXTOUT_AFRONT_L	0x08	/* analog front left */
+#define A_EXTOUT_AFRONT_R	0x09	/*              right */
+#define A_EXTOUT_ACENTER	0x0a	/* analog center */
+#define A_EXTOUT_ALFE		0x0b	/* analog LFE */
+#define A_EXTOUT_ASIDE_L	0x0c	/* analog side left  - Audigy 2 ZS */
+#define A_EXTOUT_ASIDE_R	0x0d	/*             right - Audigy 2 ZS */
+#define A_EXTOUT_AREAR_L	0x0e	/* analog rear left */
+#define A_EXTOUT_AREAR_R	0x0f	/*             right */
+#define A_EXTOUT_AC97_L		0x10	/* AC97 left (front) */
+#define A_EXTOUT_AC97_R		0x11	/*      right */
+#define A_EXTOUT_ADC_CAP_L	0x16	/* ADC capture buffer left */
+#define A_EXTOUT_ADC_CAP_R	0x17	/*                    right */
+#define A_EXTOUT_MIC_CAP	0x18	/* Mic capture buffer */
+
+/* Audigy constants */
+#define A_C_00000000	0xc0
+#define A_C_00000001	0xc1
+#define A_C_00000002	0xc2
+#define A_C_00000003	0xc3
+#define A_C_00000004	0xc4
+#define A_C_00000008	0xc5
+#define A_C_00000010	0xc6
+#define A_C_00000020	0xc7
+#define A_C_00000100	0xc8
+#define A_C_00010000	0xc9
+#define A_C_00000800	0xca
+#define A_C_10000000	0xcb
+#define A_C_20000000	0xcc
+#define A_C_40000000	0xcd
+#define A_C_80000000	0xce
+#define A_C_7fffffff	0xcf
+#define A_C_ffffffff	0xd0
+#define A_C_fffffffe	0xd1
+#define A_C_c0000000	0xd2
+#define A_C_4f1bbcdc	0xd3
+#define A_C_5a7ef9db	0xd4
+#define A_C_00100000	0xd5
+#define A_GPR_ACCU	0xd6		/* ACCUM, accumulator */
+#define A_GPR_COND	0xd7		/* CCR, condition register */
+#define A_GPR_NOISE0	0xd8		/* noise source */
+#define A_GPR_NOISE1	0xd9		/* noise source */
+#define A_GPR_IRQ	0xda		/* IRQ register */
+#define A_GPR_DBAC	0xdb		/* TRAM Delay Base Address Counter - internal */
+#define A_GPR_DBACE	0xde		/* TRAM Delay Base Address Counter - external */
+
+/* definitions for debug register */
+#define EMU10K1_DBG_ZC			0x80000000	/* zero tram counter */
+#define EMU10K1_DBG_SATURATION_OCCURED	0x02000000	/* saturation control */
+#define EMU10K1_DBG_SATURATION_ADDR	0x01ff0000	/* saturation address */
+#define EMU10K1_DBG_SINGLE_STEP		0x00008000	/* single step mode */
+#define EMU10K1_DBG_STEP		0x00004000	/* start single step */
+#define EMU10K1_DBG_CONDITION_CODE	0x00003e00	/* condition code */
+#define EMU10K1_DBG_SINGLE_STEP_ADDR	0x000001ff	/* single step address */
+
+/* tank memory address line */
+#ifndef __KERNEL__
+#define TANKMEMADDRREG_ADDR_MASK 0x000fffff	/* 20 bit tank address field			*/
+#define TANKMEMADDRREG_CLEAR	 0x00800000	/* Clear tank memory				*/
+#define TANKMEMADDRREG_ALIGN	 0x00400000	/* Align read or write relative to tank access	*/
+#define TANKMEMADDRREG_WRITE	 0x00200000	/* Write to tank memory				*/
+#define TANKMEMADDRREG_READ	 0x00100000	/* Read from tank memory			*/
+#endif
+
+struct snd_emu10k1_fx8010_info {
+	unsigned int internal_tram_size;	/* in samples */
+	unsigned int external_tram_size;	/* in samples */
+	char fxbus_names[16][32];		/* names of FXBUSes */
+	char extin_names[16][32];		/* names of external inputs */
+	char extout_names[32][32];		/* names of external outputs */
+	unsigned int gpr_controls;		/* count of GPR controls */
+};
+
+#define EMU10K1_GPR_TRANSLATION_NONE		0
+#define EMU10K1_GPR_TRANSLATION_TABLE100	1
+#define EMU10K1_GPR_TRANSLATION_BASS		2
+#define EMU10K1_GPR_TRANSLATION_TREBLE		3
+#define EMU10K1_GPR_TRANSLATION_ONOFF		4
+
+struct snd_emu10k1_fx8010_control_gpr {
+	struct snd_ctl_elem_id id;		/* full control ID definition */
+	unsigned int vcount;		/* visible count */
+	unsigned int count;		/* count of GPR (1..16) */
+	unsigned short gpr[32];		/* GPR number(s) */
+	unsigned int value[32];		/* initial values */
+	unsigned int min;		/* minimum range */
+	unsigned int max;		/* maximum range */
+	unsigned int translation;	/* translation type (EMU10K1_GPR_TRANSLATION*) */
+	const unsigned int *tlv;
+};
+
+/* old ABI without TLV support */
+struct snd_emu10k1_fx8010_control_old_gpr {
+	struct snd_ctl_elem_id id;
+	unsigned int vcount;
+	unsigned int count;
+	unsigned short gpr[32];
+	unsigned int value[32];
+	unsigned int min;
+	unsigned int max;
+	unsigned int translation;
+};
+
+struct snd_emu10k1_fx8010_code {
+	char name[128];
+
+	DECLARE_BITMAP(gpr_valid, 0x200); /* bitmask of valid initializers */
+	__u32 __user *gpr_map;		/* initializers */
+
+	unsigned int gpr_add_control_count; /* count of GPR controls to add/replace */
+	struct snd_emu10k1_fx8010_control_gpr __user *gpr_add_controls; /* GPR controls to add/replace */
+
+	unsigned int gpr_del_control_count; /* count of GPR controls to remove */
+	struct snd_ctl_elem_id __user *gpr_del_controls; /* IDs of GPR controls to remove */
+
+	unsigned int gpr_list_control_count; /* count of GPR controls to list */
+	unsigned int gpr_list_control_total; /* total count of GPR controls */
+	struct snd_emu10k1_fx8010_control_gpr __user *gpr_list_controls; /* listed GPR controls */
+
+	DECLARE_BITMAP(tram_valid, 0x100); /* bitmask of valid initializers */
+	__u32 __user *tram_data_map;	  /* data initializers */
+	__u32 __user *tram_addr_map;	  /* map initializers */
+
+	DECLARE_BITMAP(code_valid, 1024); /* bitmask of valid instructions */
+	__u32 __user *code;		  /* one instruction - 64 bits */
+};
+
+struct snd_emu10k1_fx8010_tram {
+	unsigned int address;		/* 31.bit == 1 -> external TRAM */
+	unsigned int size;		/* size in samples (4 bytes) */
+	unsigned int *samples;		/* pointer to samples (20-bit) */
+					/* NULL->clear memory */
+};
+
+struct snd_emu10k1_fx8010_pcm_rec {
+	unsigned int substream;		/* substream number */
+	unsigned int res1;		/* reserved */
+	unsigned int channels;		/* 16-bit channels count, zero = remove this substream */
+	unsigned int tram_start;	/* ring buffer position in TRAM (in samples) */
+	unsigned int buffer_size;	/* count of buffered samples */
+	unsigned short gpr_size;		/* GPR containing size of ringbuffer in samples (host) */
+	unsigned short gpr_ptr;		/* GPR containing current pointer in the ring buffer (host = reset, FX8010) */
+	unsigned short gpr_count;	/* GPR containing count of samples between two interrupts (host) */
+	unsigned short gpr_tmpcount;	/* GPR containing current count of samples to interrupt (host = set, FX8010) */
+	unsigned short gpr_trigger;	/* GPR containing trigger (activate) information (host) */
+	unsigned short gpr_running;	/* GPR containing info if PCM is running (FX8010) */
+	unsigned char pad;		/* reserved */
+	unsigned char etram[32];	/* external TRAM address & data (one per channel) */
+	unsigned int res2;		/* reserved */
+};
+
+#define SNDRV_EMU10K1_VERSION		SNDRV_PROTOCOL_VERSION(1, 0, 1)
+
+#define SNDRV_EMU10K1_IOCTL_INFO	_IOR ('H', 0x10, struct snd_emu10k1_fx8010_info)
+#define SNDRV_EMU10K1_IOCTL_CODE_POKE	_IOW ('H', 0x11, struct snd_emu10k1_fx8010_code)
+#define SNDRV_EMU10K1_IOCTL_CODE_PEEK	_IOWR('H', 0x12, struct snd_emu10k1_fx8010_code)
+#define SNDRV_EMU10K1_IOCTL_TRAM_SETUP	_IOW ('H', 0x20, int)
+#define SNDRV_EMU10K1_IOCTL_TRAM_POKE	_IOW ('H', 0x21, struct snd_emu10k1_fx8010_tram)
+#define SNDRV_EMU10K1_IOCTL_TRAM_PEEK	_IOWR('H', 0x22, struct snd_emu10k1_fx8010_tram)
+#define SNDRV_EMU10K1_IOCTL_PCM_POKE	_IOW ('H', 0x30, struct snd_emu10k1_fx8010_pcm_rec)
+#define SNDRV_EMU10K1_IOCTL_PCM_PEEK	_IOWR('H', 0x31, struct snd_emu10k1_fx8010_pcm_rec)
+#define SNDRV_EMU10K1_IOCTL_PVERSION	_IOR ('H', 0x40, int)
+#define SNDRV_EMU10K1_IOCTL_STOP	_IO  ('H', 0x80)
+#define SNDRV_EMU10K1_IOCTL_CONTINUE	_IO  ('H', 0x81)
+#define SNDRV_EMU10K1_IOCTL_ZERO_TRAM_COUNTER _IO ('H', 0x82)
+#define SNDRV_EMU10K1_IOCTL_SINGLE_STEP	_IOW ('H', 0x83, int)
+#define SNDRV_EMU10K1_IOCTL_DBG_READ	_IOR ('H', 0x84, int)
+
+/* typedefs for compatibility to user-space */
+typedef struct snd_emu10k1_fx8010_info emu10k1_fx8010_info_t;
+typedef struct snd_emu10k1_fx8010_control_gpr emu10k1_fx8010_control_gpr_t;
+typedef struct snd_emu10k1_fx8010_code emu10k1_fx8010_code_t;
+typedef struct snd_emu10k1_fx8010_tram emu10k1_fx8010_tram_t;
+typedef struct snd_emu10k1_fx8010_pcm_rec emu10k1_fx8010_pcm_t;
+
+#endif /* _UAPI__SOUND_EMU10K1_H */
diff --git a/include/uapi/sound/hdsp.h b/include/uapi/sound/hdsp.h
new file mode 100644
index 000000000000..0909a3843479
--- /dev/null
+++ b/include/uapi/sound/hdsp.h
@@ -0,0 +1,110 @@
+#ifndef __SOUND_HDSP_H
+#define __SOUND_HDSP_H
+
+/*
+ *   Copyright (C) 2003 Thomas Charbonnel (thomas@undata.org)
+ *    
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program; if not, write to the Free Software
+ *   Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/types.h>
+
+#define HDSP_MATRIX_MIXER_SIZE 2048
+
+enum HDSP_IO_Type {
+	Digiface,
+	Multiface,
+	H9652,
+	H9632,
+	RPM,
+	Undefined,
+};
+
+struct hdsp_peak_rms {
+	__u32 input_peaks[26];
+	__u32 playback_peaks[26];
+	__u32 output_peaks[28];
+	__u64 input_rms[26];
+	__u64 playback_rms[26];
+	/* These are only used for H96xx cards */
+	__u64 output_rms[26];
+};
+
+#define SNDRV_HDSP_IOCTL_GET_PEAK_RMS _IOR('H', 0x40, struct hdsp_peak_rms)
+
+struct hdsp_config_info {
+	unsigned char pref_sync_ref;
+	unsigned char wordclock_sync_check;
+	unsigned char spdif_sync_check;
+	unsigned char adatsync_sync_check;
+	unsigned char adat_sync_check[3];
+	unsigned char spdif_in;
+	unsigned char spdif_out;
+	unsigned char spdif_professional;
+	unsigned char spdif_emphasis;
+	unsigned char spdif_nonaudio;
+	unsigned int spdif_sample_rate;
+	unsigned int system_sample_rate;
+	unsigned int autosync_sample_rate;
+	unsigned char system_clock_mode;
+	unsigned char clock_source;
+	unsigned char autosync_ref;
+	unsigned char line_out;
+	unsigned char passthru; 
+	unsigned char da_gain;
+	unsigned char ad_gain;
+	unsigned char phone_gain;
+	unsigned char xlr_breakout_cable;
+	unsigned char analog_extension_board;
+};
+
+#define SNDRV_HDSP_IOCTL_GET_CONFIG_INFO _IOR('H', 0x41, struct hdsp_config_info)
+
+struct hdsp_firmware {
+	void __user *firmware_data;	/* 24413 x 4 bytes */
+};
+
+#define SNDRV_HDSP_IOCTL_UPLOAD_FIRMWARE _IOW('H', 0x42, struct hdsp_firmware)
+
+struct hdsp_version {
+	enum HDSP_IO_Type io_type;
+	unsigned short firmware_rev;
+};
+
+#define SNDRV_HDSP_IOCTL_GET_VERSION _IOR('H', 0x43, struct hdsp_version)
+
+struct hdsp_mixer {
+	unsigned short matrix[HDSP_MATRIX_MIXER_SIZE];
+};
+
+#define SNDRV_HDSP_IOCTL_GET_MIXER _IOR('H', 0x44, struct hdsp_mixer)
+
+struct hdsp_9632_aeb {
+	int aebi;
+	int aebo;
+};
+
+#define SNDRV_HDSP_IOCTL_GET_9632_AEB _IOR('H', 0x45, struct hdsp_9632_aeb)
+
+/* typedefs for compatibility to user-space */
+typedef enum HDSP_IO_Type HDSP_IO_Type;
+typedef struct hdsp_peak_rms hdsp_peak_rms_t;
+typedef struct hdsp_config_info hdsp_config_info_t;
+typedef struct hdsp_firmware hdsp_firmware_t;
+typedef struct hdsp_version hdsp_version_t;
+typedef struct hdsp_mixer hdsp_mixer_t;
+typedef struct hdsp_9632_aeb hdsp_9632_aeb_t;
+
+#endif /* __SOUND_HDSP_H */
diff --git a/include/uapi/sound/hdspm.h b/include/uapi/sound/hdspm.h
new file mode 100644
index 000000000000..1f59ea2a4a76
--- /dev/null
+++ b/include/uapi/sound/hdspm.h
@@ -0,0 +1,229 @@
+#ifndef __SOUND_HDSPM_H
+#define __SOUND_HDSPM_H
+/*
+ *   Copyright (C) 2003 Winfried Ritsch (IEM)
+ *   based on hdsp.h from Thomas Charbonnel (thomas@undata.org)
+ *
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program; if not, write to the Free Software
+ *   Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/* Maximum channels is 64 even on 56Mode you have 64playbacks to matrix */
+#define HDSPM_MAX_CHANNELS      64
+
+enum hdspm_io_type {
+	MADI,
+	MADIface,
+	AIO,
+	AES32,
+	RayDAT
+};
+
+enum hdspm_speed {
+	ss,
+	ds,
+	qs
+};
+
+/* -------------------- IOCTL Peak/RMS Meters -------------------- */
+
+struct hdspm_peak_rms {
+	uint32_t input_peaks[64];
+	uint32_t playback_peaks[64];
+	uint32_t output_peaks[64];
+
+	uint64_t input_rms[64];
+	uint64_t playback_rms[64];
+	uint64_t output_rms[64];
+
+	uint8_t speed; /* enum {ss, ds, qs} */
+	int status2;
+};
+
+#define SNDRV_HDSPM_IOCTL_GET_PEAK_RMS \
+	_IOR('H', 0x42, struct hdspm_peak_rms)
+
+/* ------------ CONFIG block IOCTL ---------------------- */
+
+struct hdspm_config {
+	unsigned char pref_sync_ref;
+	unsigned char wordclock_sync_check;
+	unsigned char madi_sync_check;
+	unsigned int system_sample_rate;
+	unsigned int autosync_sample_rate;
+	unsigned char system_clock_mode;
+	unsigned char clock_source;
+	unsigned char autosync_ref;
+	unsigned char line_out;
+	unsigned int passthru;
+	unsigned int analog_out;
+};
+
+#define SNDRV_HDSPM_IOCTL_GET_CONFIG \
+	_IOR('H', 0x41, struct hdspm_config)
+
+/**
+ * If there's a TCO (TimeCode Option) board installed,
+ * there are further options and status data available.
+ * The hdspm_ltc structure contains the current SMPTE
+ * timecode and some status information and can be
+ * obtained via SNDRV_HDSPM_IOCTL_GET_LTC or in the
+ * hdspm_status struct.
+ **/
+
+enum hdspm_ltc_format {
+	format_invalid,
+	fps_24,
+	fps_25,
+	fps_2997,
+	fps_30
+};
+
+enum hdspm_ltc_frame {
+	frame_invalid,
+	drop_frame,
+	full_frame
+};
+
+enum hdspm_ltc_input_format {
+	ntsc,
+	pal,
+	no_video
+};
+
+struct hdspm_ltc {
+	unsigned int ltc;
+
+	enum hdspm_ltc_format format;
+	enum hdspm_ltc_frame frame;
+	enum hdspm_ltc_input_format input_format;
+};
+
+#define SNDRV_HDSPM_IOCTL_GET_LTC _IOR('H', 0x46, struct hdspm_mixer_ioctl)
+
+/**
+ * The status data reflects the device's current state
+ * as determined by the card's configuration and
+ * connection status.
+ **/
+
+enum hdspm_sync {
+	hdspm_sync_no_lock = 0,
+	hdspm_sync_lock = 1,
+	hdspm_sync_sync = 2
+};
+
+enum hdspm_madi_input {
+	hdspm_input_optical = 0,
+	hdspm_input_coax = 1
+};
+
+enum hdspm_madi_channel_format {
+	hdspm_format_ch_64 = 0,
+	hdspm_format_ch_56 = 1
+};
+
+enum hdspm_madi_frame_format {
+	hdspm_frame_48 = 0,
+	hdspm_frame_96 = 1
+};
+
+enum hdspm_syncsource {
+	syncsource_wc = 0,
+	syncsource_madi = 1,
+	syncsource_tco = 2,
+	syncsource_sync = 3,
+	syncsource_none = 4
+};
+
+struct hdspm_status {
+	uint8_t card_type; /* enum hdspm_io_type */
+	enum hdspm_syncsource autosync_source;
+
+	uint64_t card_clock;
+	uint32_t master_period;
+
+	union {
+		struct {
+			uint8_t sync_wc; /* enum hdspm_sync */
+			uint8_t sync_madi; /* enum hdspm_sync */
+			uint8_t sync_tco; /* enum hdspm_sync */
+			uint8_t sync_in; /* enum hdspm_sync */
+			uint8_t madi_input; /* enum hdspm_madi_input */
+			uint8_t channel_format; /* enum hdspm_madi_channel_format */
+			uint8_t frame_format; /* enum hdspm_madi_frame_format */
+		} madi;
+	} card_specific;
+};
+
+#define SNDRV_HDSPM_IOCTL_GET_STATUS \
+	_IOR('H', 0x47, struct hdspm_status)
+
+/**
+ * Get information about the card and its add-ons.
+ **/
+
+#define HDSPM_ADDON_TCO 1
+
+struct hdspm_version {
+	uint8_t card_type; /* enum hdspm_io_type */
+	char cardname[20];
+	unsigned int serial;
+	unsigned short firmware_rev;
+	int addons;
+};
+
+#define SNDRV_HDSPM_IOCTL_GET_VERSION _IOR('H', 0x48, struct hdspm_version)
+
+/* ------------- get Matrix Mixer IOCTL --------------- */
+
+/* MADI mixer: 64inputs+64playback in 64outputs = 8192 => *4Byte =
+ * 32768 Bytes
+ */
+
+/* organisation is 64 channelfader in a continuous memory block */
+/* equivalent to hardware definition, maybe for future feature of mmap of
+ * them
+ */
+/* each of 64 outputs has 64 infader and 64 outfader:
+   Ins to Outs mixer[out].in[in], Outstreams to Outs mixer[out].pb[pb] */
+
+#define HDSPM_MIXER_CHANNELS HDSPM_MAX_CHANNELS
+
+struct hdspm_channelfader {
+	unsigned int in[HDSPM_MIXER_CHANNELS];
+	unsigned int pb[HDSPM_MIXER_CHANNELS];
+};
+
+struct hdspm_mixer {
+	struct hdspm_channelfader ch[HDSPM_MIXER_CHANNELS];
+};
+
+struct hdspm_mixer_ioctl {
+	struct hdspm_mixer *mixer;
+};
+
+/* use indirect access due to the limit of ioctl bit size */
+#define SNDRV_HDSPM_IOCTL_GET_MIXER _IOR('H', 0x44, struct hdspm_mixer_ioctl)
+
+/* typedefs for compatibility to user-space */
+typedef struct hdspm_peak_rms hdspm_peak_rms_t;
+typedef struct hdspm_config_info hdspm_config_info_t;
+typedef struct hdspm_version hdspm_version_t;
+typedef struct hdspm_channelfader snd_hdspm_channelfader_t;
+typedef struct hdspm_mixer hdspm_mixer_t;
+
+
+#endif
diff --git a/include/uapi/sound/sb16_csp.h b/include/uapi/sound/sb16_csp.h
new file mode 100644
index 000000000000..3b96907e2afb
--- /dev/null
+++ b/include/uapi/sound/sb16_csp.h
@@ -0,0 +1,122 @@
+/*
+ *  Copyright (c) 1999 by Uros Bizjak <uros@kss-loka.si>
+ *                        Takashi Iwai <tiwai@suse.de>
+ *
+ *  SB16ASP/AWE32 CSP control
+ *
+ *   This program is free software; you can redistribute it and/or modify 
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program; if not, write to the Free Software
+ *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ */
+#ifndef _UAPI__SOUND_SB16_CSP_H
+#define _UAPI__SOUND_SB16_CSP_H
+
+
+/* CSP modes */
+#define SNDRV_SB_CSP_MODE_NONE		0x00
+#define SNDRV_SB_CSP_MODE_DSP_READ	0x01	/* Record from DSP */
+#define SNDRV_SB_CSP_MODE_DSP_WRITE	0x02	/* Play to DSP */
+#define SNDRV_SB_CSP_MODE_QSOUND		0x04	/* QSound */
+
+/* CSP load flags */
+#define SNDRV_SB_CSP_LOAD_FROMUSER	0x01
+#define SNDRV_SB_CSP_LOAD_INITBLOCK	0x02
+
+/* CSP sample width */
+#define SNDRV_SB_CSP_SAMPLE_8BIT		0x01
+#define SNDRV_SB_CSP_SAMPLE_16BIT		0x02
+
+/* CSP channels */
+#define SNDRV_SB_CSP_MONO			0x01
+#define SNDRV_SB_CSP_STEREO		0x02
+
+/* CSP rates */
+#define SNDRV_SB_CSP_RATE_8000		0x01
+#define SNDRV_SB_CSP_RATE_11025		0x02
+#define SNDRV_SB_CSP_RATE_22050		0x04
+#define SNDRV_SB_CSP_RATE_44100		0x08
+#define SNDRV_SB_CSP_RATE_ALL		0x0f
+
+/* CSP running state */
+#define SNDRV_SB_CSP_ST_IDLE		0x00
+#define SNDRV_SB_CSP_ST_LOADED		0x01
+#define SNDRV_SB_CSP_ST_RUNNING		0x02
+#define SNDRV_SB_CSP_ST_PAUSED		0x04
+#define SNDRV_SB_CSP_ST_AUTO		0x08
+#define SNDRV_SB_CSP_ST_QSOUND		0x10
+
+/* maximum QSound value (180 degrees right) */
+#define SNDRV_SB_CSP_QSOUND_MAX_RIGHT	0x20
+
+/* maximum microcode RIFF file size */
+#define SNDRV_SB_CSP_MAX_MICROCODE_FILE_SIZE	0x3000
+
+/* microcode header */
+struct snd_sb_csp_mc_header {
+	char codec_name[16];		/* id name of codec */
+	unsigned short func_req;	/* requested function */
+};
+
+/* microcode to be loaded */
+struct snd_sb_csp_microcode {
+	struct snd_sb_csp_mc_header info;
+	unsigned char data[SNDRV_SB_CSP_MAX_MICROCODE_FILE_SIZE];
+};
+
+/* start CSP with sample_width in mono/stereo */
+struct snd_sb_csp_start {
+	int sample_width;	/* sample width, look above */
+	int channels;		/* channels, look above */
+};
+
+/* CSP information */
+struct snd_sb_csp_info {
+	char codec_name[16];		/* id name of codec */
+	unsigned short func_nr;		/* function number */
+	unsigned int acc_format;	/* accepted PCM formats */
+	unsigned short acc_channels;	/* accepted channels */
+	unsigned short acc_width;	/* accepted sample width */
+	unsigned short acc_rates;	/* accepted sample rates */
+	unsigned short csp_mode;	/* CSP mode, see above */
+	unsigned short run_channels;	/* current channels  */
+	unsigned short run_width;	/* current sample width */
+	unsigned short version;		/* version id: 0x10 - 0x1f */
+	unsigned short state;		/* state bits */
+};
+
+/* HWDEP controls */
+/* get CSP information */
+#define SNDRV_SB_CSP_IOCTL_INFO		_IOR('H', 0x10, struct snd_sb_csp_info)
+/* load microcode to CSP */
+/* NOTE: struct snd_sb_csp_microcode overflows the max size (13 bits)
+ * defined for some architectures like MIPS, and it leads to build errors.
+ * (x86 and co have 14-bit size, thus it's valid, though.)
+ * As a workaround for skipping the size-limit check, here we don't use the
+ * normal _IOW() macro but _IOC() with the manual argument.
+ */
+#define SNDRV_SB_CSP_IOCTL_LOAD_CODE	\
+	_IOC(_IOC_WRITE, 'H', 0x11, sizeof(struct snd_sb_csp_microcode))
+/* unload microcode from CSP */
+#define SNDRV_SB_CSP_IOCTL_UNLOAD_CODE	_IO('H', 0x12)
+/* start CSP */
+#define SNDRV_SB_CSP_IOCTL_START		_IOW('H', 0x13, struct snd_sb_csp_start)
+/* stop CSP */
+#define SNDRV_SB_CSP_IOCTL_STOP		_IO('H', 0x14)
+/* pause CSP and DMA transfer */
+#define SNDRV_SB_CSP_IOCTL_PAUSE		_IO('H', 0x15)
+/* restart CSP and DMA transfer */
+#define SNDRV_SB_CSP_IOCTL_RESTART	_IO('H', 0x16)
+
+
+#endif /* _UAPI__SOUND_SB16_CSP_H */
diff --git a/include/uapi/sound/sfnt_info.h b/include/uapi/sound/sfnt_info.h
new file mode 100644
index 000000000000..1bce7fd1725f
--- /dev/null
+++ b/include/uapi/sound/sfnt_info.h
@@ -0,0 +1,212 @@
+#ifndef __SOUND_SFNT_INFO_H
+#define __SOUND_SFNT_INFO_H
+
+/*
+ *  Patch record compatible with AWE driver on OSS
+ *
+ *  Copyright (C) 1999-2000 Takashi Iwai
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program; if not, write to the Free Software
+ *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ */
+
+#include <sound/asound.h>
+
+/*
+ * patch information record
+ */
+
+#ifdef SNDRV_BIG_ENDIAN
+#define SNDRV_OSS_PATCHKEY(id) (0xfd00|id)
+#else
+#define SNDRV_OSS_PATCHKEY(id) ((id<<8)|0xfd)
+#endif
+
+/* patch interface header: 16 bytes */
+struct soundfont_patch_info {
+	unsigned short key;		/* use the key below */
+#define SNDRV_OSS_SOUNDFONT_PATCH		SNDRV_OSS_PATCHKEY(0x07)
+
+	short device_no;		/* synthesizer number */
+	unsigned short sf_id;		/* file id (should be zero) */
+	short optarg;			/* optional argument */
+	int len;			/* data length (without this header) */
+
+	short type;			/* patch operation type */
+#define SNDRV_SFNT_LOAD_INFO		0	/* awe_voice_rec */
+#define SNDRV_SFNT_LOAD_DATA		1	/* awe_sample_info */
+#define SNDRV_SFNT_OPEN_PATCH	2	/* awe_open_parm */
+#define SNDRV_SFNT_CLOSE_PATCH	3	/* none */
+	/* 4 is obsolete */
+#define SNDRV_SFNT_REPLACE_DATA	5	/* awe_sample_info (optarg=#channels)*/
+#define SNDRV_SFNT_MAP_PRESET	6	/* awe_voice_map */
+	/* 7 is not used */
+#define SNDRV_SFNT_PROBE_DATA		8	/* optarg=sample */
+#define SNDRV_SFNT_REMOVE_INFO		9	/* optarg=(bank<<8)|instr */
+
+	short reserved;			/* word alignment data */
+
+	/* the actual patch data begins after this */
+};
+
+
+/*
+ * open patch
+ */
+
+#define SNDRV_SFNT_PATCH_NAME_LEN	32
+
+struct soundfont_open_parm {
+	unsigned short type;		/* sample type */
+#define SNDRV_SFNT_PAT_TYPE_MISC	0
+#define SNDRV_SFNT_PAT_TYPE_GUS	6
+#define SNDRV_SFNT_PAT_TYPE_MAP	7
+#define SNDRV_SFNT_PAT_LOCKED	0x100	/* lock the samples */
+#define SNDRV_SFNT_PAT_SHARED	0x200	/* sample is shared */
+
+	short reserved;
+	char name[SNDRV_SFNT_PATCH_NAME_LEN];
+};
+
+
+/*
+ * raw voice information record
+ */
+
+/* wave table envelope & effect parameters to control EMU8000 */
+struct soundfont_voice_parm {
+	unsigned short moddelay;	/* modulation delay (0x8000) */
+	unsigned short modatkhld;	/* modulation attack & hold time (0x7f7f) */
+	unsigned short moddcysus;	/* modulation decay & sustain (0x7f7f) */
+	unsigned short modrelease;	/* modulation release time (0x807f) */
+	short modkeyhold, modkeydecay;	/* envelope change per key (not used) */
+	unsigned short voldelay;	/* volume delay (0x8000) */
+	unsigned short volatkhld;	/* volume attack & hold time (0x7f7f) */
+	unsigned short voldcysus;	/* volume decay & sustain (0x7f7f) */
+	unsigned short volrelease;	/* volume release time (0x807f) */
+	short volkeyhold, volkeydecay;	/* envelope change per key (not used) */
+	unsigned short lfo1delay;	/* LFO1 delay (0x8000) */
+	unsigned short lfo2delay;	/* LFO2 delay (0x8000) */
+	unsigned short pefe;		/* modulation pitch & cutoff (0x0000) */
+	unsigned short fmmod;		/* LFO1 pitch & cutoff (0x0000) */
+	unsigned short tremfrq;		/* LFO1 volume & freq (0x0000) */
+	unsigned short fm2frq2;		/* LFO2 pitch & freq (0x0000) */
+	unsigned char cutoff;		/* initial cutoff (0xff) */
+	unsigned char filterQ;		/* initial filter Q [0-15] (0x0) */
+	unsigned char chorus;		/* chorus send (0x00) */
+	unsigned char reverb;		/* reverb send (0x00) */
+	unsigned short reserved[4];	/* not used */
+};
+
+
+/* wave table parameters: 92 bytes */
+struct soundfont_voice_info {
+	unsigned short sf_id;		/* file id (should be zero) */
+	unsigned short sample;		/* sample id */
+	int start, end;			/* sample offset correction */
+	int loopstart, loopend;		/* loop offset correction */
+	short rate_offset;		/* sample rate pitch offset */
+	unsigned short mode;		/* sample mode */
+#define SNDRV_SFNT_MODE_ROMSOUND		0x8000
+#define SNDRV_SFNT_MODE_STEREO		1
+#define SNDRV_SFNT_MODE_LOOPING		2
+#define SNDRV_SFNT_MODE_NORELEASE		4	/* obsolete */
+#define SNDRV_SFNT_MODE_INIT_PARM		8
+
+	short root;			/* midi root key */
+	short tune;			/* pitch tuning (in cents) */
+	unsigned char low, high;	/* key note range */
+	unsigned char vellow, velhigh;	/* velocity range */
+	signed char fixkey, fixvel;	/* fixed key, velocity */
+	signed char pan, fixpan;	/* panning, fixed panning */
+	short exclusiveClass;		/* exclusive class (0 = none) */
+	unsigned char amplitude;	/* sample volume (127 max) */
+	unsigned char attenuation;	/* attenuation (0.375dB) */
+	short scaleTuning;		/* pitch scale tuning(%), normally 100 */
+	struct soundfont_voice_parm parm;	/* voice envelope parameters */
+	unsigned short sample_mode;	/* sample mode_flag (set by driver) */
+};
+
+
+/* instrument info header: 4 bytes */
+struct soundfont_voice_rec_hdr {
+	unsigned char bank;		/* midi bank number */
+	unsigned char instr;		/* midi preset number */
+	char nvoices;			/* number of voices */
+	char write_mode;		/* write mode; normally 0 */
+#define SNDRV_SFNT_WR_APPEND		0	/* append anyway */
+#define SNDRV_SFNT_WR_EXCLUSIVE		1	/* skip if already exists */
+#define SNDRV_SFNT_WR_REPLACE		2	/* replace if already exists */
+};
+
+
+/*
+ * sample wave information
+ */
+
+/* wave table sample header: 32 bytes */
+struct soundfont_sample_info {
+	unsigned short sf_id;		/* file id (should be zero) */
+	unsigned short sample;		/* sample id */
+	int start, end;			/* start & end offset */
+	int loopstart, loopend;		/* loop start & end offset */
+	int size;			/* size (0 = ROM) */
+	short dummy;			/* not used */
+	unsigned short mode_flags;	/* mode flags */
+#define SNDRV_SFNT_SAMPLE_8BITS		1	/* wave data is 8bits */
+#define SNDRV_SFNT_SAMPLE_UNSIGNED	2	/* wave data is unsigned */
+#define SNDRV_SFNT_SAMPLE_NO_BLANK	4	/* no blank loop is attached */
+#define SNDRV_SFNT_SAMPLE_SINGLESHOT	8	/* single-shot w/o loop */
+#define SNDRV_SFNT_SAMPLE_BIDIR_LOOP	16	/* bidirectional looping */
+#define SNDRV_SFNT_SAMPLE_STEREO_LEFT	32	/* stereo left sound */
+#define SNDRV_SFNT_SAMPLE_STEREO_RIGHT	64	/* stereo right sound */
+#define SNDRV_SFNT_SAMPLE_REVERSE_LOOP	128	/* reverse looping */
+	unsigned int truesize;		/* used memory size (set by driver) */
+};
+
+
+/*
+ * voice preset mapping (aliasing)
+ */
+
+struct soundfont_voice_map {
+	int map_bank, map_instr, map_key;	/* key = -1 means all keys */
+	int src_bank, src_instr, src_key;
+};
+
+
+/*
+ * ioctls for hwdep
+ */
+
+#define SNDRV_EMUX_HWDEP_NAME	"Emux WaveTable"
+
+#define SNDRV_EMUX_VERSION	((1 << 16) | (0 << 8) | 0)	/* 1.0.0 */
+
+struct snd_emux_misc_mode {
+	int port;	/* -1 = all */
+	int mode;
+	int value;
+	int value2;	/* reserved */
+};
+
+#define SNDRV_EMUX_IOCTL_VERSION	_IOR('H', 0x80, unsigned int)
+#define SNDRV_EMUX_IOCTL_LOAD_PATCH	_IOWR('H', 0x81, struct soundfont_patch_info)
+#define SNDRV_EMUX_IOCTL_RESET_SAMPLES	_IO('H', 0x82)
+#define SNDRV_EMUX_IOCTL_REMOVE_LAST_SAMPLES _IO('H', 0x83)
+#define SNDRV_EMUX_IOCTL_MEM_AVAIL	_IOW('H', 0x84, int)
+#define SNDRV_EMUX_IOCTL_MISC_MODE	_IOWR('H', 0x84, struct snd_emux_misc_mode)
+
+#endif /* __SOUND_SFNT_INFO_H */
-- 
cgit v1.2.3-55-g7522


From 53502d69be49e3dd5bc95ab0f2deeaea260bd617 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Wed, 10 Oct 2012 17:38:27 +0300
Subject: Bluetooth: AMP: Handle AMP_LINK timeout

When AMP_LINK timeouts execute HCI_OP_DISCONN_PHY_LINK as analog to
HCI_OP_DISCONNECT for ACL_LINK.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  2 ++
 net/bluetooth/hci_conn.c         | 32 +++++++++++++++++++++++++++++---
 2 files changed, 31 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 90ae4f0a4fdc..dfa108c4abec 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -285,6 +285,8 @@ struct hci_dev {
 	int (*ioctl)(struct hci_dev *hdev, unsigned int cmd, unsigned long arg);
 };
 
+#define HCI_PHY_HANDLE(handle)	(handle & 0xff)
+
 struct hci_conn {
 	struct list_head list;
 
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 53202f6733ae..64875794dd9b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -130,6 +130,20 @@ void hci_acl_disconn(struct hci_conn *conn, __u8 reason)
 	hci_send_cmd(conn->hdev, HCI_OP_DISCONNECT, sizeof(cp), &cp);
 }
 
+static void hci_amp_disconn(struct hci_conn *conn, __u8 reason)
+{
+	struct hci_cp_disconn_phy_link cp;
+
+	BT_DBG("hcon %p", conn);
+
+	conn->state = BT_DISCONN;
+
+	cp.phy_handle = HCI_PHY_HANDLE(conn->handle);
+	cp.reason = reason;
+	hci_send_cmd(conn->hdev, HCI_OP_DISCONN_PHY_LINK,
+		     sizeof(cp), &cp);
+}
+
 static void hci_add_sco(struct hci_conn *conn, __u16 handle)
 {
 	struct hci_dev *hdev = conn->hdev;
@@ -230,11 +244,24 @@ void hci_sco_setup(struct hci_conn *conn, __u8 status)
 	}
 }
 
+static void hci_conn_disconnect(struct hci_conn *conn)
+{
+	__u8 reason = hci_proto_disconn_ind(conn);
+
+	switch (conn->type) {
+	case ACL_LINK:
+		hci_acl_disconn(conn, reason);
+		break;
+	case AMP_LINK:
+		hci_amp_disconn(conn, reason);
+		break;
+	}
+}
+
 static void hci_conn_timeout(struct work_struct *work)
 {
 	struct hci_conn *conn = container_of(work, struct hci_conn,
 					     disc_work.work);
-	__u8 reason;
 
 	BT_DBG("hcon %p state %s", conn, state_to_string(conn->state));
 
@@ -253,8 +280,7 @@ static void hci_conn_timeout(struct work_struct *work)
 		break;
 	case BT_CONFIG:
 	case BT_CONNECTED:
-		reason = hci_proto_disconn_ind(conn);
-		hci_acl_disconn(conn, reason);
+		hci_conn_disconnect(conn);
 		break;
 	default:
 		conn->state = BT_CLOSED;
-- 
cgit v1.2.3-55-g7522


From 42c4e53e7ac3d4069105e852d1ee24e6ee9e57b8 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Wed, 10 Oct 2012 17:38:28 +0300
Subject: Bluetooth: AMP: Add handle to hci_chan structure

hci_chan will be identified by handle used in logical link creation
process. This handle is used in AMP ACL-U packet handle field.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  3 ++-
 net/bluetooth/hci_conn.c         | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index dfa108c4abec..b697ef342020 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -350,7 +350,7 @@ struct hci_conn {
 
 struct hci_chan {
 	struct list_head list;
-
+	__u16 handle;
 	struct hci_conn *conn;
 	struct sk_buff_head data_q;
 	unsigned int	sent;
@@ -567,6 +567,7 @@ void hci_conn_check_pending(struct hci_dev *hdev);
 struct hci_chan *hci_chan_create(struct hci_conn *conn);
 void hci_chan_del(struct hci_chan *chan);
 void hci_chan_list_flush(struct hci_conn *conn);
+struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle);
 
 struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst,
 			     __u8 dst_type, __u8 sec_level, __u8 auth_type);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 64875794dd9b..fe646211c61f 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -989,3 +989,35 @@ void hci_chan_list_flush(struct hci_conn *conn)
 	list_for_each_entry_safe(chan, n, &conn->chan_list, list)
 		hci_chan_del(chan);
 }
+
+static struct hci_chan *__hci_chan_lookup_handle(struct hci_conn *hcon,
+						 __u16 handle)
+{
+	struct hci_chan *hchan;
+
+	list_for_each_entry(hchan, &hcon->chan_list, list) {
+		if (hchan->handle == handle)
+			return hchan;
+	}
+
+	return NULL;
+}
+
+struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle)
+{
+	struct hci_conn_hash *h = &hdev->conn_hash;
+	struct hci_conn *hcon;
+	struct hci_chan *hchan = NULL;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(hcon, &h->list, list) {
+		hchan = __hci_chan_lookup_handle(hcon, handle);
+		if (hchan)
+			break;
+	}
+
+	rcu_read_unlock();
+
+	return hchan;
+}
-- 
cgit v1.2.3-55-g7522


From bd1eb66ba4eee21de3be24212b135f57101ad930 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Wed, 10 Oct 2012 17:38:30 +0300
Subject: Bluetooth: AMP: Handle AMP_LINK connection

AMP_LINK represents physical link between AMP controllers.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 13 +++++++++++++
 net/bluetooth/hci_core.c         | 22 +++++++++++++++++++---
 net/bluetooth/hci_event.c        |  1 +
 3 files changed, 33 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index b697ef342020..d5ed054d77cf 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -73,6 +73,7 @@ struct discovery_state {
 struct hci_conn_hash {
 	struct list_head list;
 	unsigned int     acl_num;
+	unsigned int     amp_num;
 	unsigned int     sco_num;
 	unsigned int     le_num;
 };
@@ -449,6 +450,9 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c)
 	case ACL_LINK:
 		h->acl_num++;
 		break;
+	case AMP_LINK:
+		h->amp_num++;
+		break;
 	case LE_LINK:
 		h->le_num++;
 		break;
@@ -470,6 +474,9 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c)
 	case ACL_LINK:
 		h->acl_num--;
 		break;
+	case AMP_LINK:
+		h->amp_num--;
+		break;
 	case LE_LINK:
 		h->le_num--;
 		break;
@@ -486,6 +493,8 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type)
 	switch (type) {
 	case ACL_LINK:
 		return h->acl_num;
+	case AMP_LINK:
+		return h->amp_num;
 	case LE_LINK:
 		return h->le_num;
 	case SCO_LINK:
@@ -801,6 +810,10 @@ static inline void hci_proto_disconn_cfm(struct hci_conn *conn, __u8 reason)
 		sco_disconn_cfm(conn, reason);
 		break;
 
+	/* L2CAP would be handled for BREDR chan */
+	case AMP_LINK:
+		break;
+
 	default:
 		BT_ERR("unknown link type %d", conn->type);
 		break;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index bd26cb52aaa9..2e72c410fb47 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2379,6 +2379,9 @@ static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type,
 	case ACL_LINK:
 		cnt = hdev->acl_cnt;
 		break;
+	case AMP_LINK:
+		cnt = hdev->block_cnt;
+		break;
 	case SCO_LINK:
 	case ESCO_LINK:
 		cnt = hdev->sco_cnt;
@@ -2508,11 +2511,19 @@ static void hci_sched_acl_blk(struct hci_dev *hdev)
 	struct hci_chan *chan;
 	struct sk_buff *skb;
 	int quote;
+	u8 type;
 
 	__check_timeout(hdev, cnt);
 
+	BT_DBG("%s", hdev->name);
+
+	if (hdev->dev_type == HCI_AMP)
+		type = AMP_LINK;
+	else
+		type = ACL_LINK;
+
 	while (hdev->block_cnt > 0 &&
-	       (chan = hci_chan_sent(hdev, ACL_LINK, &quote))) {
+	       (chan = hci_chan_sent(hdev, type, &quote))) {
 		u32 priority = (skb_peek(&chan->data_q))->priority;
 		while (quote > 0 && (skb = skb_peek(&chan->data_q))) {
 			int blocks;
@@ -2545,14 +2556,19 @@ static void hci_sched_acl_blk(struct hci_dev *hdev)
 	}
 
 	if (cnt != hdev->block_cnt)
-		hci_prio_recalculate(hdev, ACL_LINK);
+		hci_prio_recalculate(hdev, type);
 }
 
 static void hci_sched_acl(struct hci_dev *hdev)
 {
 	BT_DBG("%s", hdev->name);
 
-	if (!hci_conn_num(hdev, ACL_LINK))
+	/* No ACL link over BR/EDR controller */
+	if (!hci_conn_num(hdev, ACL_LINK) && hdev->dev_type == HCI_BREDR)
+		return;
+
+	/* No AMP link over AMP controller */
+	if (!hci_conn_num(hdev, AMP_LINK) && hdev->dev_type == HCI_AMP)
 		return;
 
 	switch (hdev->flow_ctl_mode) {
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 5c0b6c161a01..0383635f91fb 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2733,6 +2733,7 @@ static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 		switch (conn->type) {
 		case ACL_LINK:
+		case AMP_LINK:
 			hdev->block_cnt += block_count;
 			if (hdev->block_cnt > hdev->num_blocks)
 				hdev->block_cnt = hdev->num_blocks;
-- 
cgit v1.2.3-55-g7522


From 716e4ab5c966327988e21e6137c14e457cfca690 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Wed, 10 Oct 2012 17:38:31 +0300
Subject: Bluetooth: AMP: Hanlde AMP_LINK case in conn_put

Handle AMP link when setting up disconnect timeout.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d5ed054d77cf..9fe8e2dec870 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -605,7 +605,10 @@ static inline void hci_conn_put(struct hci_conn *conn)
 
 	if (atomic_dec_and_test(&conn->refcnt)) {
 		unsigned long timeo;
-		if (conn->type == ACL_LINK || conn->type == LE_LINK) {
+
+		switch (conn->type) {
+		case ACL_LINK:
+		case LE_LINK:
 			del_timer(&conn->idle_timer);
 			if (conn->state == BT_CONNECTED) {
 				timeo = conn->disc_timeout;
@@ -614,12 +617,20 @@ static inline void hci_conn_put(struct hci_conn *conn)
 			} else {
 				timeo = msecs_to_jiffies(10);
 			}
-		} else {
+			break;
+
+		case AMP_LINK:
+			timeo = conn->disc_timeout;
+			break;
+
+		default:
 			timeo = msecs_to_jiffies(10);
+			break;
 		}
+
 		cancel_delayed_work(&conn->disc_work);
 		queue_delayed_work(conn->hdev->workqueue,
-					&conn->disc_work, timeo);
+				   &conn->disc_work, timeo);
 	}
 }
 
-- 
cgit v1.2.3-55-g7522


From 90f790d2dc96f5a61855ae65b90e30c40c893a20 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Mon, 20 Aug 2012 21:45:05 +0100
Subject: regmap: irq: Allow users to retrieve the irq_domain

This is useful for integration with other subsystems, especially MFD,
and provides an alternative API for users that request their own IRQs.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/base/regmap/regmap-irq.c | 19 +++++++++++++++++++
 include/linux/regmap.h           |  2 ++
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 5b6b1d8e6cc0..5972ad958544 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -458,3 +458,22 @@ int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq)
 	return irq_create_mapping(data->domain, irq);
 }
 EXPORT_SYMBOL_GPL(regmap_irq_get_virq);
+
+/**
+ * regmap_irq_get_domain(): Retrieve the irq_domain for the chip
+ *
+ * Useful for drivers to request their own IRQs and for integration
+ * with subsystems.  For ease of integration NULL is accepted as a
+ * domain, allowing devices to just call this even if no domain is
+ * allocated.
+ *
+ * @data: regmap_irq controller to operate on.
+ */
+struct irq_domain *regmap_irq_get_domain(struct regmap_irq_chip_data *data)
+{
+	if (data)
+		return data->domain;
+	else
+		return NULL;
+}
+EXPORT_SYMBOL_GPL(regmap_irq_get_domain);
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index e3bcc3f4dcb8..b9e99799965d 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -19,6 +19,7 @@
 struct module;
 struct device;
 struct i2c_client;
+struct irq_domain;
 struct spi_device;
 struct regmap;
 struct regmap_range_cfg;
@@ -317,6 +318,7 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
 void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data);
 int regmap_irq_chip_get_base(struct regmap_irq_chip_data *data);
 int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq);
+struct irq_domain *regmap_irq_get_domain(struct regmap_irq_chip_data *data);
 
 #else
 
-- 
cgit v1.2.3-55-g7522


From e3549cd01347ef211d01353bdf2572b086574007 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 2 Oct 2012 20:17:15 +0100
Subject: regmap: Rename n_ranges to num_ranges

This makes things consistent with the rest of the API and is actually what
the documentation says. We don't currently have any in tree users so low
cost.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/base/regmap/regmap.c | 4 ++--
 include/linux/regmap.h       | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 52069d29ff12..ea9d6eb826bd 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -519,7 +519,7 @@ struct regmap *regmap_init(struct device *dev,
 	}
 
 	map->range_tree = RB_ROOT;
-	for (i = 0; i < config->n_ranges; i++) {
+	for (i = 0; i < config->num_ranges; i++) {
 		const struct regmap_range_cfg *range_cfg = &config->ranges[i];
 		struct regmap_range_node *new;
 
@@ -532,7 +532,7 @@ struct regmap *regmap_init(struct device *dev,
 
 		/* Make sure, that this register range has no selector
 		   or data window within its boundary */
-		for (j = 0; j < config->n_ranges; j++) {
+		for (j = 0; j < config->num_ranges; j++) {
 			unsigned sel_reg = config->ranges[j].selector_reg;
 			unsigned win_min = config->ranges[j].window_start;
 			unsigned win_max = win_min +
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index e3bcc3f4dcb8..afc8e1a2cd1b 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -133,7 +133,7 @@ struct regmap_config {
 	enum regmap_endian val_format_endian;
 
 	const struct regmap_range_cfg *ranges;
-	unsigned int n_ranges;
+	unsigned int num_ranges;
 };
 
 /**
-- 
cgit v1.2.3-55-g7522


From d058bb49618482f2eff0db57618c9a7352916dd5 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Wed, 3 Oct 2012 12:40:47 +0100
Subject: regmap: Allow ranges to be named

For more useful diagnostics.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/base/regmap/internal.h | 1 +
 drivers/base/regmap/regmap.c   | 1 +
 include/linux/regmap.h         | 4 ++++
 3 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 80f9ab9c3aa4..27e66c3e7a59 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -120,6 +120,7 @@ int _regmap_write(struct regmap *map, unsigned int reg,
 
 struct regmap_range_node {
 	struct rb_node node;
+	const char *name;
 
 	unsigned int range_min;
 	unsigned int range_max;
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 0544f63ecd31..ce5129df4406 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -579,6 +579,7 @@ struct regmap *regmap_init(struct device *dev,
 			goto err_range;
 		}
 
+		new->name = range_cfg->name;
 		new->range_min = range_cfg->range_min;
 		new->range_max = range_cfg->range_max;
 		new->selector_reg = range_cfg->selector_reg;
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index afc8e1a2cd1b..9f228d7f7ac4 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -142,6 +142,8 @@ struct regmap_config {
  *     1. page selector register update;
  *     2. access through data window registers.
  *
+ * @name: Descriptive name for diagnostics
+ *
  * @range_min: Address of the lowest register address in virtual range.
  * @range_max: Address of the highest register in virtual range.
  *
@@ -153,6 +155,8 @@ struct regmap_config {
  * @window_len: Number of registers in data window.
  */
 struct regmap_range_cfg {
+	const char *name;
+
 	/* Registers of virtual address range */
 	unsigned int range_min;
 	unsigned int range_max;
-- 
cgit v1.2.3-55-g7522


From 293750f9bcb3368d5298ed1a091b5402de359d3b Mon Sep 17 00:00:00 2001
From: Daniel Mack
Date: Thu, 4 Oct 2012 14:03:23 +0200
Subject: ASoC: cs4271: add support for AMUTEB=BMUTEC feature

The CS4271 has a feature to sync its analog mute flags, so one mute
circuitry can be used for both channels.

Give users access to this feature with a new DT property and a flag in
the platform data.

Signed-off-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 Documentation/devicetree/bindings/sound/cs4271.txt |  2 ++
 include/sound/cs4271.h                             |  1 +
 sound/soc/codecs/cs4271.c                          | 21 ++++++++++++++++++---
 3 files changed, 21 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/sound/cs4271.txt b/Documentation/devicetree/bindings/sound/cs4271.txt
index c81b5fd5a5bc..a850fb9c88ea 100644
--- a/Documentation/devicetree/bindings/sound/cs4271.txt
+++ b/Documentation/devicetree/bindings/sound/cs4271.txt
@@ -18,6 +18,8 @@ Optional properties:
 
  - reset-gpio: 	a GPIO spec to define which pin is connected to the chip's
 		!RESET pin
+ - cirrus,amuteb-eq-bmutec:	When given, the Codec's AMUTEB=BMUTEC flag
+				is enabled.
 
 Examples:
 
diff --git a/include/sound/cs4271.h b/include/sound/cs4271.h
index 50a059e7d116..6d9e15ed1dcf 100644
--- a/include/sound/cs4271.h
+++ b/include/sound/cs4271.h
@@ -19,6 +19,7 @@
 
 struct cs4271_platform_data {
 	int gpio_nreset;	/* GPIO driving Reset pin, if any */
+	int amutec_eq_bmutec:1;	/* flag to enable AMUTEC=BMUTEC */
 };
 
 #endif /* __CS4271_H */
diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c
index f994af34f552..2ac5fe61a96c 100644
--- a/sound/soc/codecs/cs4271.c
+++ b/sound/soc/codecs/cs4271.c
@@ -474,15 +474,25 @@ static int cs4271_probe(struct snd_soc_codec *codec)
 	struct cs4271_platform_data *cs4271plat = codec->dev->platform_data;
 	int ret;
 	int gpio_nreset = -EINVAL;
+	int amutec_eq_bmutec = 0;
 
 #ifdef CONFIG_OF
-	if (of_match_device(cs4271_dt_ids, codec->dev))
+	if (of_match_device(cs4271_dt_ids, codec->dev)) {
 		gpio_nreset = of_get_named_gpio(codec->dev->of_node,
 						"reset-gpio", 0);
+
+		if (!of_get_property(codec->dev->of_node,
+				     "cirrus,amutec-eq-bmutec", NULL))
+			amutec_eq_bmutec = 1;
+	}
 #endif
 
-	if (cs4271plat && gpio_is_valid(cs4271plat->gpio_nreset))
-		gpio_nreset = cs4271plat->gpio_nreset;
+	if (cs4271plat) {
+		if (gpio_is_valid(cs4271plat->gpio_nreset))
+			gpio_nreset = cs4271plat->gpio_nreset;
+
+		amutec_eq_bmutec = cs4271plat->amutec_eq_bmutec;
+	}
 
 	if (gpio_nreset >= 0)
 		if (gpio_request(gpio_nreset, "CS4271 Reset"))
@@ -528,6 +538,11 @@ static int cs4271_probe(struct snd_soc_codec *codec)
 	/* Power-up sequence requires 85 uS */
 	udelay(85);
 
+	if (amutec_eq_bmutec)
+		snd_soc_update_bits(codec, CS4271_MODE2,
+				    CS4271_MODE2_MUTECAEQUB,
+				    CS4271_MODE2_MUTECAEQUB);
+
 	return snd_soc_add_codec_controls(codec, cs4271_snd_controls,
 		ARRAY_SIZE(cs4271_snd_controls));
 }
-- 
cgit v1.2.3-55-g7522


From b8a6d9980f75cf5401a5ab23834eace1cb23c4f1 Mon Sep 17 00:00:00 2001
From: Shawn Guo
Date: Fri, 14 Sep 2012 10:35:54 +0800
Subject: dma: ipu: rename mach/ipu.h to include/linux/dma/ipu-dma.h

The header ipu.h really belongs to dma subsystem rather than imx
platform.  Rename it to ipu-dma.h and put it into include/linux/dma/.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Acked-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Acked-by: Sascha Hauer <s.hauer@pengutronix.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Cc: Vinod Koul <vinod.koul@intel.com>
Cc: Florian Tobias Schandinat <FlorianSchandinat@gmx.de>
Cc: linux-media@vger.kernel.org
Cc: linux-fbdev@vger.kernel.org
---
 arch/arm/mach-imx/include/mach/ipu.h           | 177 -------------------------
 drivers/dma/ipu/ipu_idmac.c                    |   3 +-
 drivers/dma/ipu/ipu_irq.c                      |   3 +-
 drivers/media/platform/soc_camera/mx3_camera.c |   2 +-
 drivers/video/mx3fb.c                          |   2 +-
 include/linux/dma/ipu-dma.h                    | 177 +++++++++++++++++++++++++
 6 files changed, 181 insertions(+), 183 deletions(-)
 delete mode 100644 arch/arm/mach-imx/include/mach/ipu.h
 create mode 100644 include/linux/dma/ipu-dma.h

(limited to 'include')

diff --git a/arch/arm/mach-imx/include/mach/ipu.h b/arch/arm/mach-imx/include/mach/ipu.h
deleted file mode 100644
index 539e559d18b2..000000000000
--- a/arch/arm/mach-imx/include/mach/ipu.h
+++ /dev/null
@@ -1,177 +0,0 @@
-/*
- * Copyright (C) 2008
- * Guennadi Liakhovetski, DENX Software Engineering, <lg@denx.de>
- *
- * Copyright (C) 2005-2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _IPU_H_
-#define _IPU_H_
-
-#include <linux/types.h>
-#include <linux/dmaengine.h>
-
-/* IPU DMA Controller channel definitions. */
-enum ipu_channel {
-	IDMAC_IC_0 = 0,		/* IC (encoding task) to memory */
-	IDMAC_IC_1 = 1,		/* IC (viewfinder task) to memory */
-	IDMAC_ADC_0 = 1,
-	IDMAC_IC_2 = 2,
-	IDMAC_ADC_1 = 2,
-	IDMAC_IC_3 = 3,
-	IDMAC_IC_4 = 4,
-	IDMAC_IC_5 = 5,
-	IDMAC_IC_6 = 6,
-	IDMAC_IC_7 = 7,		/* IC (sensor data) to memory */
-	IDMAC_IC_8 = 8,
-	IDMAC_IC_9 = 9,
-	IDMAC_IC_10 = 10,
-	IDMAC_IC_11 = 11,
-	IDMAC_IC_12 = 12,
-	IDMAC_IC_13 = 13,
-	IDMAC_SDC_0 = 14,	/* Background synchronous display data */
-	IDMAC_SDC_1 = 15,	/* Foreground data (overlay) */
-	IDMAC_SDC_2 = 16,
-	IDMAC_SDC_3 = 17,
-	IDMAC_ADC_2 = 18,
-	IDMAC_ADC_3 = 19,
-	IDMAC_ADC_4 = 20,
-	IDMAC_ADC_5 = 21,
-	IDMAC_ADC_6 = 22,
-	IDMAC_ADC_7 = 23,
-	IDMAC_PF_0 = 24,
-	IDMAC_PF_1 = 25,
-	IDMAC_PF_2 = 26,
-	IDMAC_PF_3 = 27,
-	IDMAC_PF_4 = 28,
-	IDMAC_PF_5 = 29,
-	IDMAC_PF_6 = 30,
-	IDMAC_PF_7 = 31,
-};
-
-/* Order significant! */
-enum ipu_channel_status {
-	IPU_CHANNEL_FREE,
-	IPU_CHANNEL_INITIALIZED,
-	IPU_CHANNEL_READY,
-	IPU_CHANNEL_ENABLED,
-};
-
-#define IPU_CHANNELS_NUM 32
-
-enum pixel_fmt {
-	/* 1 byte */
-	IPU_PIX_FMT_GENERIC,
-	IPU_PIX_FMT_RGB332,
-	IPU_PIX_FMT_YUV420P,
-	IPU_PIX_FMT_YUV422P,
-	IPU_PIX_FMT_YUV420P2,
-	IPU_PIX_FMT_YVU422P,
-	/* 2 bytes */
-	IPU_PIX_FMT_RGB565,
-	IPU_PIX_FMT_RGB666,
-	IPU_PIX_FMT_BGR666,
-	IPU_PIX_FMT_YUYV,
-	IPU_PIX_FMT_UYVY,
-	/* 3 bytes */
-	IPU_PIX_FMT_RGB24,
-	IPU_PIX_FMT_BGR24,
-	/* 4 bytes */
-	IPU_PIX_FMT_GENERIC_32,
-	IPU_PIX_FMT_RGB32,
-	IPU_PIX_FMT_BGR32,
-	IPU_PIX_FMT_ABGR32,
-	IPU_PIX_FMT_BGRA32,
-	IPU_PIX_FMT_RGBA32,
-};
-
-enum ipu_color_space {
-	IPU_COLORSPACE_RGB,
-	IPU_COLORSPACE_YCBCR,
-	IPU_COLORSPACE_YUV
-};
-
-/*
- * Enumeration of IPU rotation modes
- */
-enum ipu_rotate_mode {
-	/* Note the enum values correspond to BAM value */
-	IPU_ROTATE_NONE = 0,
-	IPU_ROTATE_VERT_FLIP = 1,
-	IPU_ROTATE_HORIZ_FLIP = 2,
-	IPU_ROTATE_180 = 3,
-	IPU_ROTATE_90_RIGHT = 4,
-	IPU_ROTATE_90_RIGHT_VFLIP = 5,
-	IPU_ROTATE_90_RIGHT_HFLIP = 6,
-	IPU_ROTATE_90_LEFT = 7,
-};
-
-/*
- * Enumeration of DI ports for ADC.
- */
-enum display_port {
-	DISP0,
-	DISP1,
-	DISP2,
-	DISP3
-};
-
-struct idmac_video_param {
-	unsigned short		in_width;
-	unsigned short		in_height;
-	uint32_t		in_pixel_fmt;
-	unsigned short		out_width;
-	unsigned short		out_height;
-	uint32_t		out_pixel_fmt;
-	unsigned short		out_stride;
-	bool			graphics_combine_en;
-	bool			global_alpha_en;
-	bool			key_color_en;
-	enum display_port	disp;
-	unsigned short		out_left;
-	unsigned short		out_top;
-};
-
-/*
- * Union of initialization parameters for a logical channel. So far only video
- * parameters are used.
- */
-union ipu_channel_param {
-	struct idmac_video_param video;
-};
-
-struct idmac_tx_desc {
-	struct dma_async_tx_descriptor	txd;
-	struct scatterlist		*sg;	/* scatterlist for this */
-	unsigned int			sg_len;	/* tx-descriptor. */
-	struct list_head		list;
-};
-
-struct idmac_channel {
-	struct dma_chan		dma_chan;
-	dma_cookie_t		completed;	/* last completed cookie	   */
-	union ipu_channel_param	params;
-	enum ipu_channel	link;	/* input channel, linked to the output	   */
-	enum ipu_channel_status	status;
-	void			*client;	/* Only one client per channel	   */
-	unsigned int		n_tx_desc;
-	struct idmac_tx_desc	*desc;		/* allocated tx-descriptors	   */
-	struct scatterlist	*sg[2];	/* scatterlist elements in buffer-0 and -1 */
-	struct list_head	free_list;	/* free tx-descriptors		   */
-	struct list_head	queue;		/* queued tx-descriptors	   */
-	spinlock_t		lock;		/* protects sg[0,1], queue	   */
-	struct mutex		chan_mutex; /* protects status, cookie, free_list  */
-	bool			sec_chan_en;
-	int			active_buffer;
-	unsigned int		eof_irq;
-	char			eof_name[16];	/* EOF IRQ name for request_irq()  */
-};
-
-#define to_tx_desc(tx) container_of(tx, struct idmac_tx_desc, txd)
-#define to_idmac_chan(c) container_of(c, struct idmac_channel, dma_chan)
-
-#endif
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index c7573e50aa14..65855373cee6 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -22,8 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
-
-#include <mach/ipu.h>
+#include <linux/dma/ipu-dma.h>
 
 #include "../dmaengine.h"
 #include "ipu_intern.h"
diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c
index fa95bcc3de1f..a5ee37d5320f 100644
--- a/drivers/dma/ipu/ipu_irq.c
+++ b/drivers/dma/ipu/ipu_irq.c
@@ -15,8 +15,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/module.h>
-
-#include <mach/ipu.h>
+#include <linux/dma/ipu-dma.h>
 
 #include "ipu_intern.h"
 
diff --git a/drivers/media/platform/soc_camera/mx3_camera.c b/drivers/media/platform/soc_camera/mx3_camera.c
index 3557ac97e430..64d39b1b5582 100644
--- a/drivers/media/platform/soc_camera/mx3_camera.c
+++ b/drivers/media/platform/soc_camera/mx3_camera.c
@@ -17,6 +17,7 @@
 #include <linux/vmalloc.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/dma/ipu-dma.h>
 
 #include <media/v4l2-common.h>
 #include <media/v4l2-dev.h>
@@ -24,7 +25,6 @@
 #include <media/soc_camera.h>
 #include <media/soc_mediabus.h>
 
-#include <mach/ipu.h>
 #include <linux/platform_data/camera-mx3.h>
 #include <linux/platform_data/dma-imx.h>
 
diff --git a/drivers/video/mx3fb.c b/drivers/video/mx3fb.c
index ce1d452464ed..0324c07be895 100644
--- a/drivers/video/mx3fb.c
+++ b/drivers/video/mx3fb.c
@@ -26,10 +26,10 @@
 #include <linux/console.h>
 #include <linux/clk.h>
 #include <linux/mutex.h>
+#include <linux/dma/ipu-dma.h>
 
 #include <linux/platform_data/dma-imx.h>
 #include <mach/hardware.h>
-#include <mach/ipu.h>
 #include <linux/platform_data/video-mx3fb.h>
 
 #include <asm/io.h>
diff --git a/include/linux/dma/ipu-dma.h b/include/linux/dma/ipu-dma.h
new file mode 100644
index 000000000000..18031115c668
--- /dev/null
+++ b/include/linux/dma/ipu-dma.h
@@ -0,0 +1,177 @@
+/*
+ * Copyright (C) 2008
+ * Guennadi Liakhovetski, DENX Software Engineering, <lg@denx.de>
+ *
+ * Copyright (C) 2005-2007 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_DMA_IPU_DMA_H
+#define __LINUX_DMA_IPU_DMA_H
+
+#include <linux/types.h>
+#include <linux/dmaengine.h>
+
+/* IPU DMA Controller channel definitions. */
+enum ipu_channel {
+	IDMAC_IC_0 = 0,		/* IC (encoding task) to memory */
+	IDMAC_IC_1 = 1,		/* IC (viewfinder task) to memory */
+	IDMAC_ADC_0 = 1,
+	IDMAC_IC_2 = 2,
+	IDMAC_ADC_1 = 2,
+	IDMAC_IC_3 = 3,
+	IDMAC_IC_4 = 4,
+	IDMAC_IC_5 = 5,
+	IDMAC_IC_6 = 6,
+	IDMAC_IC_7 = 7,		/* IC (sensor data) to memory */
+	IDMAC_IC_8 = 8,
+	IDMAC_IC_9 = 9,
+	IDMAC_IC_10 = 10,
+	IDMAC_IC_11 = 11,
+	IDMAC_IC_12 = 12,
+	IDMAC_IC_13 = 13,
+	IDMAC_SDC_0 = 14,	/* Background synchronous display data */
+	IDMAC_SDC_1 = 15,	/* Foreground data (overlay) */
+	IDMAC_SDC_2 = 16,
+	IDMAC_SDC_3 = 17,
+	IDMAC_ADC_2 = 18,
+	IDMAC_ADC_3 = 19,
+	IDMAC_ADC_4 = 20,
+	IDMAC_ADC_5 = 21,
+	IDMAC_ADC_6 = 22,
+	IDMAC_ADC_7 = 23,
+	IDMAC_PF_0 = 24,
+	IDMAC_PF_1 = 25,
+	IDMAC_PF_2 = 26,
+	IDMAC_PF_3 = 27,
+	IDMAC_PF_4 = 28,
+	IDMAC_PF_5 = 29,
+	IDMAC_PF_6 = 30,
+	IDMAC_PF_7 = 31,
+};
+
+/* Order significant! */
+enum ipu_channel_status {
+	IPU_CHANNEL_FREE,
+	IPU_CHANNEL_INITIALIZED,
+	IPU_CHANNEL_READY,
+	IPU_CHANNEL_ENABLED,
+};
+
+#define IPU_CHANNELS_NUM 32
+
+enum pixel_fmt {
+	/* 1 byte */
+	IPU_PIX_FMT_GENERIC,
+	IPU_PIX_FMT_RGB332,
+	IPU_PIX_FMT_YUV420P,
+	IPU_PIX_FMT_YUV422P,
+	IPU_PIX_FMT_YUV420P2,
+	IPU_PIX_FMT_YVU422P,
+	/* 2 bytes */
+	IPU_PIX_FMT_RGB565,
+	IPU_PIX_FMT_RGB666,
+	IPU_PIX_FMT_BGR666,
+	IPU_PIX_FMT_YUYV,
+	IPU_PIX_FMT_UYVY,
+	/* 3 bytes */
+	IPU_PIX_FMT_RGB24,
+	IPU_PIX_FMT_BGR24,
+	/* 4 bytes */
+	IPU_PIX_FMT_GENERIC_32,
+	IPU_PIX_FMT_RGB32,
+	IPU_PIX_FMT_BGR32,
+	IPU_PIX_FMT_ABGR32,
+	IPU_PIX_FMT_BGRA32,
+	IPU_PIX_FMT_RGBA32,
+};
+
+enum ipu_color_space {
+	IPU_COLORSPACE_RGB,
+	IPU_COLORSPACE_YCBCR,
+	IPU_COLORSPACE_YUV
+};
+
+/*
+ * Enumeration of IPU rotation modes
+ */
+enum ipu_rotate_mode {
+	/* Note the enum values correspond to BAM value */
+	IPU_ROTATE_NONE = 0,
+	IPU_ROTATE_VERT_FLIP = 1,
+	IPU_ROTATE_HORIZ_FLIP = 2,
+	IPU_ROTATE_180 = 3,
+	IPU_ROTATE_90_RIGHT = 4,
+	IPU_ROTATE_90_RIGHT_VFLIP = 5,
+	IPU_ROTATE_90_RIGHT_HFLIP = 6,
+	IPU_ROTATE_90_LEFT = 7,
+};
+
+/*
+ * Enumeration of DI ports for ADC.
+ */
+enum display_port {
+	DISP0,
+	DISP1,
+	DISP2,
+	DISP3
+};
+
+struct idmac_video_param {
+	unsigned short		in_width;
+	unsigned short		in_height;
+	uint32_t		in_pixel_fmt;
+	unsigned short		out_width;
+	unsigned short		out_height;
+	uint32_t		out_pixel_fmt;
+	unsigned short		out_stride;
+	bool			graphics_combine_en;
+	bool			global_alpha_en;
+	bool			key_color_en;
+	enum display_port	disp;
+	unsigned short		out_left;
+	unsigned short		out_top;
+};
+
+/*
+ * Union of initialization parameters for a logical channel. So far only video
+ * parameters are used.
+ */
+union ipu_channel_param {
+	struct idmac_video_param video;
+};
+
+struct idmac_tx_desc {
+	struct dma_async_tx_descriptor	txd;
+	struct scatterlist		*sg;	/* scatterlist for this */
+	unsigned int			sg_len;	/* tx-descriptor. */
+	struct list_head		list;
+};
+
+struct idmac_channel {
+	struct dma_chan		dma_chan;
+	dma_cookie_t		completed;	/* last completed cookie	   */
+	union ipu_channel_param	params;
+	enum ipu_channel	link;	/* input channel, linked to the output	   */
+	enum ipu_channel_status	status;
+	void			*client;	/* Only one client per channel	   */
+	unsigned int		n_tx_desc;
+	struct idmac_tx_desc	*desc;		/* allocated tx-descriptors	   */
+	struct scatterlist	*sg[2];	/* scatterlist elements in buffer-0 and -1 */
+	struct list_head	free_list;	/* free tx-descriptors		   */
+	struct list_head	queue;		/* queued tx-descriptors	   */
+	spinlock_t		lock;		/* protects sg[0,1], queue	   */
+	struct mutex		chan_mutex; /* protects status, cookie, free_list  */
+	bool			sec_chan_en;
+	int			active_buffer;
+	unsigned int		eof_irq;
+	char			eof_name[16];	/* EOF IRQ name for request_irq()  */
+};
+
+#define to_tx_desc(tx) container_of(tx, struct idmac_tx_desc, txd)
+#define to_idmac_chan(c) container_of(c, struct idmac_channel, dma_chan)
+
+#endif /* __LINUX_DMA_IPU_DMA_H */
-- 
cgit v1.2.3-55-g7522


From e51d0f0ac4b7f513808743c6a62f0387eebd0144 Mon Sep 17 00:00:00 2001
From: Shawn Guo
Date: Sat, 15 Sep 2012 21:11:28 +0800
Subject: dma: imx-dma: remove cpu_is_xxx by using platform_device_id

It changes the driver to use platform_device_id rather than cpu_is_xxx
to determine the controller type, and updates the platform code
accordingly.

As the result, mach/hardware.h inclusion gets removed from the driver.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Javier Martin <javier.martin@vista-silicon.com>
Cc: Vinod Koul <vinod.koul@linux.intel.com>
---
 arch/arm/mach-imx/clk-imx1.c                 |  3 +-
 arch/arm/mach-imx/clk-imx21.c                |  4 +--
 arch/arm/mach-imx/clk-imx27.c                |  4 +--
 arch/arm/mach-imx/devices/devices-common.h   |  2 +-
 arch/arm/mach-imx/devices/platform-imx-dma.c |  4 +--
 arch/arm/mach-imx/mm-imx1.c                  |  3 +-
 arch/arm/mach-imx/mm-imx21.c                 |  3 +-
 arch/arm/mach-imx/mm-imx27.c                 |  3 +-
 drivers/dma/imx-dma.c                        | 54 ++++++++++++++++++++++++----
 include/linux/platform_data/dma-imx.h        |  4 ++-
 10 files changed, 66 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-imx1.c b/arch/arm/mach-imx/clk-imx1.c
index 1cc7a735ed19..49a74440bc48 100644
--- a/arch/arm/mach-imx/clk-imx1.c
+++ b/arch/arm/mach-imx/clk-imx1.c
@@ -83,7 +83,8 @@ int __init mx1_clocks_init(unsigned long fref)
 			pr_err("imx1 clk %d: register failed with %ld\n",
 				i, PTR_ERR(clk[i]));
 
-	clk_register_clkdev(clk[dma_gate], "ahb", "imx-dma");
+	clk_register_clkdev(clk[dma_gate], "ahb", "imx1-dma");
+	clk_register_clkdev(clk[hclk], "ipg", "imx1-dma");
 	clk_register_clkdev(clk[csi_gate], NULL, "mx1-camera.0");
 	clk_register_clkdev(clk[mma_gate], "mma", NULL);
 	clk_register_clkdev(clk[usbd_gate], NULL, "imx_udc.0");
diff --git a/arch/arm/mach-imx/clk-imx21.c b/arch/arm/mach-imx/clk-imx21.c
index 96a4788032d1..8aec572f84fe 100644
--- a/arch/arm/mach-imx/clk-imx21.c
+++ b/arch/arm/mach-imx/clk-imx21.c
@@ -163,8 +163,8 @@ int __init mx21_clocks_init(unsigned long lref, unsigned long href)
 	clk_register_clkdev(clk[usb_gate], "per", "imx21-hcd.0");
 	clk_register_clkdev(clk[usb_hclk_gate], "ahb", "imx21-hcd.0");
 	clk_register_clkdev(clk[nfc_gate], NULL, "imx21-nand.0");
-	clk_register_clkdev(clk[dma_hclk_gate], "ahb", "imx-dma");
-	clk_register_clkdev(clk[dma_gate], "ipg", "imx-dma");
+	clk_register_clkdev(clk[dma_hclk_gate], "ahb", "imx21-dma");
+	clk_register_clkdev(clk[dma_gate], "ipg", "imx21-dma");
 	clk_register_clkdev(clk[wdog_gate], NULL, "imx2-wdt.0");
 	clk_register_clkdev(clk[i2c_gate], NULL, "imx21-i2c.0");
 	clk_register_clkdev(clk[kpp_gate], NULL, "mxc-keypad");
diff --git a/arch/arm/mach-imx/clk-imx27.c b/arch/arm/mach-imx/clk-imx27.c
index 86a0c4262471..a5f0e3b6dec6 100644
--- a/arch/arm/mach-imx/clk-imx27.c
+++ b/arch/arm/mach-imx/clk-imx27.c
@@ -242,8 +242,8 @@ int __init mx27_clocks_init(unsigned long fref)
 	clk_register_clkdev(clk[nfc_baud_gate], NULL, "imx27-nand.0");
 	clk_register_clkdev(clk[vpu_baud_gate], "per", "coda-imx27.0");
 	clk_register_clkdev(clk[vpu_ahb_gate], "ahb", "coda-imx27.0");
-	clk_register_clkdev(clk[dma_ahb_gate], "ahb", "imx-dma");
-	clk_register_clkdev(clk[dma_ipg_gate], "ipg", "imx-dma");
+	clk_register_clkdev(clk[dma_ahb_gate], "ahb", "imx27-dma");
+	clk_register_clkdev(clk[dma_ipg_gate], "ipg", "imx27-dma");
 	clk_register_clkdev(clk[fec_ipg_gate], "ipg", "imx27-fec.0");
 	clk_register_clkdev(clk[fec_ahb_gate], "ahb", "imx27-fec.0");
 	clk_register_clkdev(clk[wdog_ipg_gate], NULL, "imx2-wdt.0");
diff --git a/arch/arm/mach-imx/devices/devices-common.h b/arch/arm/mach-imx/devices/devices-common.h
index e4368f6c5fb4..36eb3f09f5d7 100644
--- a/arch/arm/mach-imx/devices/devices-common.h
+++ b/arch/arm/mach-imx/devices/devices-common.h
@@ -329,7 +329,7 @@ struct platform_device *__init imx_add_spi_imx(
 		const struct imx_spi_imx_data *data,
 		const struct spi_imx_master *pdata);
 
-struct platform_device *imx_add_imx_dma(resource_size_t iobase,
+struct platform_device *imx_add_imx_dma(char *name, resource_size_t iobase,
 					int irq, int irq_err);
 struct platform_device *imx_add_imx_sdma(char *name,
 	resource_size_t iobase, int irq, struct sdma_platform_data *pdata);
diff --git a/arch/arm/mach-imx/devices/platform-imx-dma.c b/arch/arm/mach-imx/devices/platform-imx-dma.c
index f9003e4d0f57..ccdb5dc4ddbd 100644
--- a/arch/arm/mach-imx/devices/platform-imx-dma.c
+++ b/arch/arm/mach-imx/devices/platform-imx-dma.c
@@ -8,7 +8,7 @@
  */
 #include "devices-common.h"
 
-struct platform_device __init __maybe_unused *imx_add_imx_dma(
+struct platform_device __init __maybe_unused *imx_add_imx_dma(char *name,
 	resource_size_t iobase, int irq, int irq_err)
 {
 	struct resource res[] = {
@@ -28,7 +28,7 @@ struct platform_device __init __maybe_unused *imx_add_imx_dma(
 	};
 
 	return platform_device_register_resndata(&mxc_ahb_bus,
-			"imx-dma", -1, res, ARRAY_SIZE(res), NULL, 0);
+			name, -1, res, ARRAY_SIZE(res), NULL, 0);
 }
 
 struct platform_device __init __maybe_unused *imx_add_imx_sdma(char *name,
diff --git a/arch/arm/mach-imx/mm-imx1.c b/arch/arm/mach-imx/mm-imx1.c
index 9de81bf6de96..79f6c0b8f69f 100644
--- a/arch/arm/mach-imx/mm-imx1.c
+++ b/arch/arm/mach-imx/mm-imx1.c
@@ -60,6 +60,7 @@ void __init imx1_soc_init(void)
 						MX1_GPIO_INT_PORTC, 0);
 	mxc_register_gpio("imx1-gpio", 3, MX1_GPIO4_BASE_ADDR, SZ_256,
 						MX1_GPIO_INT_PORTD, 0);
-	imx_add_imx_dma(MX1_DMA_BASE_ADDR, MX1_DMA_INT, MX1_DMA_ERR);
+	imx_add_imx_dma("imx1-dma", MX1_DMA_BASE_ADDR,
+			MX1_DMA_INT, MX1_DMA_ERR);
 	pinctrl_provide_dummies();
 }
diff --git a/arch/arm/mach-imx/mm-imx21.c b/arch/arm/mach-imx/mm-imx21.c
index 1c295154c296..3b97ea63b5fb 100644
--- a/arch/arm/mach-imx/mm-imx21.c
+++ b/arch/arm/mach-imx/mm-imx21.c
@@ -90,7 +90,8 @@ void __init imx21_soc_init(void)
 	mxc_register_gpio("imx21-gpio", 5, MX21_GPIO6_BASE_ADDR, SZ_256, MX21_INT_GPIO, 0);
 
 	pinctrl_provide_dummies();
-	imx_add_imx_dma(MX21_DMA_BASE_ADDR, MX21_INT_DMACH0, 0); /* No ERR irq */
+	imx_add_imx_dma("imx21-dma", MX21_DMA_BASE_ADDR,
+			MX21_INT_DMACH0, 0); /* No ERR irq */
 	platform_device_register_simple("imx21-audmux", 0, imx21_audmux_res,
 					ARRAY_SIZE(imx21_audmux_res));
 }
diff --git a/arch/arm/mach-imx/mm-imx27.c b/arch/arm/mach-imx/mm-imx27.c
index d389f4af33c0..91e8da832810 100644
--- a/arch/arm/mach-imx/mm-imx27.c
+++ b/arch/arm/mach-imx/mm-imx27.c
@@ -91,7 +91,8 @@ void __init imx27_soc_init(void)
 	mxc_register_gpio("imx21-gpio", 5, MX27_GPIO6_BASE_ADDR, SZ_256, MX27_INT_GPIO, 0);
 
 	pinctrl_provide_dummies();
-	imx_add_imx_dma(MX27_DMA_BASE_ADDR, MX27_INT_DMACH0, 0); /* No ERR irq */
+	imx_add_imx_dma("imx27-dma", MX27_DMA_BASE_ADDR,
+			MX27_INT_DMACH0, 0); /* No ERR irq */
 	/* imx27 has the imx21 type audmux */
 	platform_device_register_simple("imx21-audmux", 0, imx27_audmux_res,
 					ARRAY_SIZE(imx27_audmux_res));
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 88e8a8d89b56..a3a8270e76fb 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -29,7 +29,6 @@
 
 #include <asm/irq.h>
 #include <linux/platform_data/dma-imx.h>
-#include <mach/hardware.h>
 
 #include "dmaengine.h"
 #define IMXDMA_MAX_CHAN_DESCRIPTORS	16
@@ -167,6 +166,12 @@ struct imxdma_channel {
 	int				slot_2d;
 };
 
+enum imx_dma_type {
+	IMX1_DMA,
+	IMX21_DMA,
+	IMX27_DMA,
+};
+
 struct imxdma_engine {
 	struct device			*dev;
 	struct device_dma_parameters	dma_parms;
@@ -177,8 +182,40 @@ struct imxdma_engine {
 	spinlock_t			lock;
 	struct imx_dma_2d_config	slots_2d[IMX_DMA_2D_SLOTS];
 	struct imxdma_channel		channel[IMX_DMA_CHANNELS];
+	enum imx_dma_type		devtype;
 };
 
+static struct platform_device_id imx_dma_devtype[] = {
+	{
+		.name = "imx1-dma",
+		.driver_data = IMX1_DMA,
+	}, {
+		.name = "imx21-dma",
+		.driver_data = IMX21_DMA,
+	}, {
+		.name = "imx27-dma",
+		.driver_data = IMX27_DMA,
+	}, {
+		/* sentinel */
+	}
+};
+MODULE_DEVICE_TABLE(platform, imx_dma_devtype);
+
+static inline int is_imx1_dma(struct imxdma_engine *imxdma)
+{
+	return imxdma->devtype == IMX1_DMA;
+}
+
+static inline int is_imx21_dma(struct imxdma_engine *imxdma)
+{
+	return imxdma->devtype == IMX21_DMA;
+}
+
+static inline int is_imx27_dma(struct imxdma_engine *imxdma)
+{
+	return imxdma->devtype == IMX27_DMA;
+}
+
 static struct imxdma_channel *to_imxdma_chan(struct dma_chan *chan)
 {
 	return container_of(chan, struct imxdma_channel, chan);
@@ -212,7 +249,9 @@ static unsigned imx_dmav1_readl(struct imxdma_engine *imxdma, unsigned offset)
 
 static int imxdma_hw_chain(struct imxdma_channel *imxdmac)
 {
-	if (cpu_is_mx27())
+	struct imxdma_engine *imxdma = imxdmac->imxdma;
+
+	if (is_imx27_dma(imxdma))
 		return imxdmac->hw_chaining;
 	else
 		return 0;
@@ -267,7 +306,7 @@ static void imxdma_enable_hw(struct imxdma_desc *d)
 	imx_dmav1_writel(imxdma, imx_dmav1_readl(imxdma, DMA_CCR(channel)) |
 			 CCR_CEN | CCR_ACRPT, DMA_CCR(channel));
 
-	if ((cpu_is_mx21() || cpu_is_mx27()) &&
+	if (!is_imx1_dma(imxdma) &&
 			d->sg && imxdma_hw_chain(imxdmac)) {
 		d->sg = sg_next(d->sg);
 		if (d->sg) {
@@ -436,7 +475,7 @@ static irqreturn_t dma_irq_handler(int irq, void *dev_id)
 	struct imxdma_engine *imxdma = dev_id;
 	int i, disr;
 
-	if (cpu_is_mx21() || cpu_is_mx27())
+	if (!is_imx1_dma(imxdma))
 		imxdma_err_handler(irq, dev_id);
 
 	disr = imx_dmav1_readl(imxdma, DMA_DISR);
@@ -967,6 +1006,8 @@ static int __init imxdma_probe(struct platform_device *pdev)
 	if (!imxdma)
 		return -ENOMEM;
 
+	imxdma->devtype = pdev->id_entry->driver_data;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	imxdma->base = devm_request_and_ioremap(&pdev->dev, res);
 	if (!imxdma->base)
@@ -990,7 +1031,7 @@ static int __init imxdma_probe(struct platform_device *pdev)
 	/* reset DMA module */
 	imx_dmav1_writel(imxdma, DCR_DRST, DMA_DCR);
 
-	if (cpu_is_mx1()) {
+	if (is_imx1_dma(imxdma)) {
 		ret = devm_request_irq(&pdev->dev, irq,
 				       dma_irq_handler, 0, "DMA", imxdma);
 		if (ret) {
@@ -1038,7 +1079,7 @@ static int __init imxdma_probe(struct platform_device *pdev)
 	for (i = 0; i < IMX_DMA_CHANNELS; i++) {
 		struct imxdma_channel *imxdmac = &imxdma->channel[i];
 
-		if (cpu_is_mx21() || cpu_is_mx27()) {
+		if (!is_imx1_dma(imxdma)) {
 			ret = devm_request_irq(&pdev->dev, irq + i,
 					dma_irq_handler, 0, "DMA", imxdma);
 			if (ret) {
@@ -1118,6 +1159,7 @@ static struct platform_driver imxdma_driver = {
 	.driver		= {
 		.name	= "imx-dma",
 	},
+	.id_table	= imx_dma_devtype,
 	.remove		= __exit_p(imxdma_remove),
 };
 
diff --git a/include/linux/platform_data/dma-imx.h b/include/linux/platform_data/dma-imx.h
index 1b9080385b46..f6d30cc1cb77 100644
--- a/include/linux/platform_data/dma-imx.h
+++ b/include/linux/platform_data/dma-imx.h
@@ -61,7 +61,9 @@ static inline int imx_dma_is_ipu(struct dma_chan *chan)
 static inline int imx_dma_is_general_purpose(struct dma_chan *chan)
 {
 	return strstr(dev_name(chan->device->dev), "sdma") ||
-		!strcmp(dev_name(chan->device->dev), "imx-dma");
+		!strcmp(dev_name(chan->device->dev), "imx1-dma") ||
+		!strcmp(dev_name(chan->device->dev), "imx21-dma") ||
+		!strcmp(dev_name(chan->device->dev), "imx27-dma");
 }
 
 #endif
-- 
cgit v1.2.3-55-g7522


From 1e66210a3135b544713a9455e78e36f6f8d1bf77 Mon Sep 17 00:00:00 2001
From: Shawn Guo
Date: Sun, 16 Sep 2012 22:16:44 +0800
Subject: ARM: imx: remove header file mach/irqs.h

The only mach/irqs.h user outside arch/arm/mach-imx is
sound/soc/fsl/imx-pcm-fiq.c, which refers to mxc_set_irq_fiq().
Move the declaration into include/linux/platform_data/asoc-imx-ssi.h,
so that we can remove mach/irqs.h includsion from imx-pcm-fiq.c.

Inside arch/arm/mach-imx, the only users to mach/irqs.h are avic.c
and tzic.c for referring to macro FIQ_START.  Let's move the macro
into irq-common.h and get rid of mach/irqs.h completely.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Acked-by: Sascha Hauer <s.hauer@pengutronix.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: alsa-devel@alsa-project.org
---
 arch/arm/mach-imx/avic.c                   |  1 -
 arch/arm/mach-imx/include/mach/irqs.h      | 21 ---------------------
 arch/arm/mach-imx/irq-common.h             |  3 +++
 arch/arm/mach-imx/tzic.c                   |  2 --
 include/linux/platform_data/asoc-imx-ssi.h |  2 ++
 sound/soc/fsl/imx-pcm-fiq.c                |  1 -
 6 files changed, 5 insertions(+), 25 deletions(-)
 delete mode 100644 arch/arm/mach-imx/include/mach/irqs.h

(limited to 'include')

diff --git a/arch/arm/mach-imx/avic.c b/arch/arm/mach-imx/avic.c
index adc64bc5b343..0eff23ed92b9 100644
--- a/arch/arm/mach-imx/avic.c
+++ b/arch/arm/mach-imx/avic.c
@@ -24,7 +24,6 @@
 #include <linux/of.h>
 #include <asm/mach/irq.h>
 #include <asm/exception.h>
-#include <mach/irqs.h>
 
 #include "common.h"
 #include "hardware.h"
diff --git a/arch/arm/mach-imx/include/mach/irqs.h b/arch/arm/mach-imx/include/mach/irqs.h
deleted file mode 100644
index d73f5e8ea9cb..000000000000
--- a/arch/arm/mach-imx/include/mach/irqs.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- *  Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
- */
-
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ASM_ARCH_MXC_IRQS_H__
-#define __ASM_ARCH_MXC_IRQS_H__
-
-extern int imx_irq_set_priority(unsigned char irq, unsigned char prio);
-
-/* all normal IRQs can be FIQs */
-#define FIQ_START	0
-/* switch between IRQ and FIQ */
-extern int mxc_set_irq_fiq(unsigned int irq, unsigned int type);
-
-#endif /* __ASM_ARCH_MXC_IRQS_H__ */
diff --git a/arch/arm/mach-imx/irq-common.h b/arch/arm/mach-imx/irq-common.h
index 6ccb3a14c693..5b2dabba330f 100644
--- a/arch/arm/mach-imx/irq-common.h
+++ b/arch/arm/mach-imx/irq-common.h
@@ -19,6 +19,9 @@
 #ifndef __PLAT_MXC_IRQ_COMMON_H__
 #define __PLAT_MXC_IRQ_COMMON_H__
 
+/* all normal IRQs can be FIQs */
+#define FIQ_START	0
+
 struct mxc_extra_irq
 {
 	int (*set_priority)(unsigned char irq, unsigned char prio);
diff --git a/arch/arm/mach-imx/tzic.c b/arch/arm/mach-imx/tzic.c
index c7625b4a916b..9721161f208f 100644
--- a/arch/arm/mach-imx/tzic.c
+++ b/arch/arm/mach-imx/tzic.c
@@ -21,8 +21,6 @@
 #include <asm/mach/irq.h>
 #include <asm/exception.h>
 
-#include <mach/irqs.h>
-
 #include "common.h"
 #include "hardware.h"
 #include "irq-common.h"
diff --git a/include/linux/platform_data/asoc-imx-ssi.h b/include/linux/platform_data/asoc-imx-ssi.h
index 63f3c2804239..92c7fd72f636 100644
--- a/include/linux/platform_data/asoc-imx-ssi.h
+++ b/include/linux/platform_data/asoc-imx-ssi.h
@@ -17,5 +17,7 @@ struct imx_ssi_platform_data {
 	void (*ac97_warm_reset)(struct snd_ac97 *ac97);
 };
 
+extern int mxc_set_irq_fiq(unsigned int irq, unsigned int type);
+
 #endif /* __MACH_SSI_H */
 
diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c
index 22c6130957ba..9ffc9e66308f 100644
--- a/sound/soc/fsl/imx-pcm-fiq.c
+++ b/sound/soc/fsl/imx-pcm-fiq.c
@@ -29,7 +29,6 @@
 
 #include <asm/fiq.h>
 
-#include <mach/irqs.h>
 #include <linux/platform_data/asoc-imx-ssi.h>
 
 #include "imx-ssi.h"
-- 
cgit v1.2.3-55-g7522


From c0cc3f1665256b7cfdc1d581f997dcea1af71405 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Fri, 28 Sep 2012 16:50:15 +0100
Subject: ASoC: wm8994: Allow a delay between jack insertion and microphone
 detect

This can be used to provide some additional settling time to ensure that
we don't start microphone detection while the microphone pin is connected
to one of the headphone pins.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/linux/mfd/wm8994/pdata.h |  5 +++
 sound/soc/codecs/wm8994.c        | 74 +++++++++++++++++++++++++++++-----------
 2 files changed, 60 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/wm8994/pdata.h b/include/linux/mfd/wm8994/pdata.h
index fc87be4fdc25..8e21a094836d 100644
--- a/include/linux/mfd/wm8994/pdata.h
+++ b/include/linux/mfd/wm8994/pdata.h
@@ -176,6 +176,11 @@ struct wm8994_pdata {
         unsigned int lineout1fb:1;
         unsigned int lineout2fb:1;
 
+	/* Delay between detecting a jack and starting microphone
+	 * detect (specified in ms)
+	 */
+	int micdet_delay;
+
 	/* IRQ for microphone detection if brought out directly as a
 	 * signal.
 	 */
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 2b2dadc54dac..07095a9ca9a6 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -3470,11 +3470,46 @@ static void wm8958_default_micdet(u16 status, void *data)
 	}
 }
 
+/* Deferred mic detection to allow for extra settling time */
+static void wm1811_mic_work(struct work_struct *work)
+{
+	struct wm8994_priv *wm8994 = container_of(work, struct wm8994_priv,
+						  mic_work.work);
+	struct snd_soc_codec *codec = wm8994->hubs.codec;
+
+	pm_runtime_get_sync(codec->dev);
+
+	/* If required for an external cap force MICBIAS on */
+	if (wm8994->pdata->jd_ext_cap) {
+		snd_soc_dapm_force_enable_pin(&codec->dapm,
+					      "MICBIAS2");
+		snd_soc_dapm_sync(&codec->dapm);
+	}
+
+	mutex_lock(&wm8994->accdet_lock);
+
+	dev_dbg(codec->dev, "Starting mic detection\n");
+
+	/*
+	 * Start off measument of microphone impedence to find out
+	 * what's actually there.
+	 */
+	wm8994->mic_detecting = true;
+	wm1811_jackdet_set_mode(codec, WM1811_JACKDET_MODE_MIC);
+
+	snd_soc_update_bits(codec, WM8958_MIC_DETECT_1,
+			    WM8958_MICD_ENA, WM8958_MICD_ENA);
+
+	mutex_unlock(&wm8994->accdet_lock);
+
+	pm_runtime_put(codec->dev);
+}
+
 static irqreturn_t wm1811_jackdet_irq(int irq, void *data)
 {
 	struct wm8994_priv *wm8994 = data;
 	struct snd_soc_codec *codec = wm8994->hubs.codec;
-	int reg;
+	int reg, delay;
 	bool present;
 
 	pm_runtime_get_sync(codec->dev);
@@ -3505,18 +3540,14 @@ static irqreturn_t wm1811_jackdet_irq(int irq, void *data)
 		snd_soc_update_bits(codec, WM1811_JACKDET_CTRL,
 				    WM1811_JACKDET_DB, 0);
 
-		/*
-		 * Start off measument of microphone impedence to find
-		 * out what's actually there.
-		 */
-		wm8994->mic_detecting = true;
-		wm1811_jackdet_set_mode(codec, WM1811_JACKDET_MODE_MIC);
-
-		snd_soc_update_bits(codec, WM8958_MIC_DETECT_1,
-				    WM8958_MICD_ENA, WM8958_MICD_ENA);
+		delay = wm8994->pdata->micdet_delay;
+		schedule_delayed_work(&wm8994->mic_work,
+				      msecs_to_jiffies(delay));
 	} else {
 		dev_dbg(codec->dev, "Jack not detected\n");
 
+		cancel_delayed_work_sync(&wm8994->mic_work);
+
 		snd_soc_update_bits(codec, WM8958_MICBIAS2,
 				    WM8958_MICB2_DISCH, WM8958_MICB2_DISCH);
 
@@ -3533,14 +3564,9 @@ static irqreturn_t wm1811_jackdet_irq(int irq, void *data)
 
 	mutex_unlock(&wm8994->accdet_lock);
 
-	/* If required for an external cap force MICBIAS on */
-	if (wm8994->pdata->jd_ext_cap) {
-		if (present)
-			snd_soc_dapm_force_enable_pin(&codec->dapm,
-						      "MICBIAS2");
-		else
-			snd_soc_dapm_disable_pin(&codec->dapm, "MICBIAS2");
-	}
+	/* Turn off MICBIAS if it was on for an external cap */
+	if (wm8994->pdata->jd_ext_cap && !present)
+		snd_soc_dapm_disable_pin(&codec->dapm, "MICBIAS2");
 
 	if (present)
 		snd_soc_jack_report(wm8994->micdet[0].jack,
@@ -3763,10 +3789,20 @@ static int wm8994_codec_probe(struct snd_soc_codec *codec)
 	snd_soc_codec_set_cache_io(codec, 16, 16, SND_SOC_REGMAP);
 
 	mutex_init(&wm8994->accdet_lock);
-	INIT_DELAYED_WORK(&wm8994->mic_work, wm8994_mic_work);
 	INIT_DELAYED_WORK(&wm8994->jackdet_bootstrap,
 			  wm1811_jackdet_bootstrap);
 
+	switch (control->type) {
+	case WM8994:
+		INIT_DELAYED_WORK(&wm8994->mic_work, wm8994_mic_work);
+		break;
+	case WM1811:
+		INIT_DELAYED_WORK(&wm8994->mic_work, wm1811_mic_work);
+		break;
+	default:
+		break;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(wm8994->fll_locked); i++)
 		init_completion(&wm8994->fll_locked[i]);
 
-- 
cgit v1.2.3-55-g7522


From 0c57067430a2b729bc08c92b17eb4f29d9bbfaae Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Sat, 6 Oct 2012 20:47:46 +0530
Subject: regulator: tps51632: Add tps51632 regulator driver

The TPS51632 is a driverless step down controller with
serial control. Advanced features such as D-Cap+
architecture with overlapping pulse support and OSR
overshoot reduction provide fast transient response,
lowest output capacitance and high efficiency.
The TPS51632 supports both I2C and DVFS interfaces
(through PWM) for dynamic control of the output voltage
and current monitor telemetry.
Add regulator driver for TPS51632.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/regulator/Kconfig                    |  11 +
 drivers/regulator/Makefile                   |   1 +
 drivers/regulator/tps51632-regulator.c       | 332 +++++++++++++++++++++++++++
 include/linux/regulator/tps51632-regulator.h |  47 ++++
 4 files changed, 391 insertions(+)
 create mode 100644 drivers/regulator/tps51632-regulator.c
 create mode 100644 include/linux/regulator/tps51632-regulator.h

(limited to 'include')

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 67d47b59a66d..aa9e8a18262d 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -335,6 +335,17 @@ config REGULATOR_PALMAS
 	  on the muxing. This is handled automatically in the driver by
 	  reading the mux info from OTP.
 
+config REGULATOR_TPS51632
+	tristate "TI TPS51632 Power Regulator"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  This driver supports TPS51632 voltage regulator chip.
+	  The TPS52632 is 3-2-1 Phase D-Cap+ Step Down Driverless Controller
+	  with Serial VID control and DVFS.
+	  The voltage output can be configure through I2C interface or PWM
+	  interface.
+
 config REGULATOR_TPS6105X
 	tristate "TI TPS6105X Power regulators"
 	depends on TPS6105X
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index e431eed8a878..ec1aec460bf6 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_REGULATOR_MC13783) += mc13783-regulator.o
 obj-$(CONFIG_REGULATOR_MC13892) += mc13892-regulator.o
 obj-$(CONFIG_REGULATOR_MC13XXX_CORE) +=  mc13xxx-regulator-core.o
 obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o
+obj-$(CONFIG_REGULATOR_TPS51632) += tps51632-regulator.o
 obj-$(CONFIG_REGULATOR_PCAP) += pcap-regulator.o
 obj-$(CONFIG_REGULATOR_PCF50633) += pcf50633-regulator.o
 obj-$(CONFIG_REGULATOR_RC5T583)  += rc5t583-regulator.o
diff --git a/drivers/regulator/tps51632-regulator.c b/drivers/regulator/tps51632-regulator.c
new file mode 100644
index 000000000000..34603640d6d9
--- /dev/null
+++ b/drivers/regulator/tps51632-regulator.c
@@ -0,0 +1,332 @@
+/*
+ * tps51632-regulator.c -- TI TPS51632
+ *
+ * Regulator driver for TPS51632 3-2-1 Phase D-Cap Step Down Driverless
+ * Controller with serial VID control and DVFS.
+ *
+ * Copyright (c) 2012, NVIDIA Corporation.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind,
+ * whether express or implied; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ * 02111-1307, USA
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/tps51632-regulator.h>
+#include <linux/slab.h>
+
+/* Register definitions */
+#define TPS51632_VOLTAGE_SELECT_REG		0x0
+#define TPS51632_VOLTAGE_BASE_REG		0x1
+#define TPS51632_OFFSET_REG			0x2
+#define TPS51632_IMON_REG			0x3
+#define TPS51632_VMAX_REG			0x4
+#define TPS51632_DVFS_CONTROL_REG		0x5
+#define TPS51632_POWER_STATE_REG		0x6
+#define TPS51632_SLEW_REGS			0x7
+#define TPS51632_FAULT_REG			0x14
+
+#define TPS51632_MAX_REG			0x15
+
+#define TPS51632_VOUT_MASK			0x7F
+#define TPS51632_VOUT_OFFSET_MASK		0x1F
+#define TPS51632_VMAX_MASK			0x7F
+#define TPS51632_VMAX_LOCK			0x80
+
+/* TPS51632_DVFS_CONTROL_REG */
+#define TPS51632_DVFS_PWMEN			0x1
+#define TPS51632_DVFS_STEP_20			0x2
+#define TPS51632_DVFS_VMAX_PG			0x4
+#define TPS51632_DVFS_PWMRST			0x8
+#define TPS51632_DVFS_OCA_EN			0x10
+#define TPS51632_DVFS_FCCM			0x20
+
+/* TPS51632_POWER_STATE_REG */
+#define TPS51632_POWER_STATE_MASK		0x03
+#define TPS51632_POWER_STATE_MULTI_PHASE_CCM	0x0
+#define TPS51632_POWER_STATE_SINGLE_PHASE_CCM	0x1
+#define TPS51632_POWER_STATE_SINGLE_PHASE_DCM	0x2
+
+#define TPS51632_MIN_VOLATGE			500000
+#define TPS51632_MAX_VOLATGE			1520000
+#define TPS51632_VOLATGE_STEP_10mV		10000
+#define TPS51632_VOLATGE_STEP_20mV		20000
+#define TPS51632_MAX_VSEL			0x7F
+#define TPS51632_MIN_VSEL			0x19
+#define TPS51632_DEFAULT_RAMP_DELAY		6000
+#define TPS51632_VOLT_VSEL(uV)					\
+		(DIV_ROUND_UP(uV - TPS51632_MIN_VOLATGE,	\
+			TPS51632_VOLATGE_STEP_10mV) +		\
+			TPS51632_MIN_VSEL)
+
+/* TPS51632 chip information */
+struct tps51632_chip {
+	struct device *dev;
+	struct regulator_desc desc;
+	struct regulator_dev *rdev;
+	struct regmap *regmap;
+	bool enable_pwm_dvfs;
+};
+
+static int tps51632_dcdc_get_voltage_sel(struct regulator_dev *rdev)
+{
+	struct tps51632_chip *tps = rdev_get_drvdata(rdev);
+	unsigned int data;
+	int ret;
+	unsigned int reg = TPS51632_VOLTAGE_SELECT_REG;
+	int vsel;
+
+	if (tps->enable_pwm_dvfs)
+		reg = TPS51632_VOLTAGE_BASE_REG;
+
+	ret = regmap_read(tps->regmap, reg, &data);
+	if (ret < 0) {
+		dev_err(tps->dev, "reg read failed, err %d\n", ret);
+		return ret;
+	}
+
+	vsel = data & TPS51632_VOUT_MASK;
+
+	if (vsel < TPS51632_MIN_VSEL)
+		return 0;
+	else
+		return vsel - TPS51632_MIN_VSEL;
+}
+
+static int tps51632_dcdc_set_voltage_sel(struct regulator_dev *rdev,
+		unsigned selector)
+{
+	struct tps51632_chip *tps = rdev_get_drvdata(rdev);
+	int vsel;
+	int ret;
+	unsigned int reg = TPS51632_VOLTAGE_SELECT_REG;
+
+	if (tps->enable_pwm_dvfs)
+		reg = TPS51632_VOLTAGE_BASE_REG;
+
+	vsel = selector + TPS51632_MIN_VSEL;
+	if (vsel > TPS51632_MAX_VSEL)
+		return -EINVAL;
+
+	ret = regmap_write(tps->regmap, TPS51632_VOLTAGE_SELECT_REG, vsel);
+	if (ret < 0)
+		dev_err(tps->dev, "reg write failed, err %d\n", ret);
+	return ret;
+}
+
+static int tps51632_dcdc_set_ramp_delay(struct regulator_dev *rdev,
+		int ramp_delay)
+{
+	struct tps51632_chip *tps = rdev_get_drvdata(rdev);
+	int bit = ramp_delay/6000;
+	int ret;
+
+	if (bit)
+		bit--;
+	ret = regmap_write(tps->regmap, TPS51632_SLEW_REGS, BIT(bit));
+	if (ret < 0)
+		dev_err(tps->dev, "SLEW reg write failed, err %d\n", ret);
+	return ret;
+}
+
+static struct regulator_ops tps51632_dcdc_ops = {
+	.get_voltage_sel	= tps51632_dcdc_get_voltage_sel,
+	.set_voltage_sel	= tps51632_dcdc_set_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear,
+	.set_voltage_time_sel	= regulator_set_voltage_time_sel,
+	.set_ramp_delay		= tps51632_dcdc_set_ramp_delay,
+};
+
+static int __devinit tps51632_init_dcdc(struct tps51632_chip *tps,
+		struct tps51632_regulator_platform_data *pdata)
+{
+	int ret;
+	uint8_t	control = 0;
+	int vsel;
+
+	if (!pdata->enable_pwm_dvfs)
+		goto skip_pwm_config;
+
+	control |= TPS51632_DVFS_PWMEN;
+	tps->enable_pwm_dvfs = pdata->enable_pwm_dvfs;
+	vsel = TPS51632_VOLT_VSEL(pdata->base_voltage_uV);
+	ret = regmap_write(tps->regmap, TPS51632_VOLTAGE_BASE_REG, vsel);
+	if (ret < 0) {
+		dev_err(tps->dev, "BASE reg write failed, err %d\n", ret);
+		return ret;
+	}
+
+	if (pdata->dvfs_step_20mV)
+		control |= TPS51632_DVFS_STEP_20;
+
+	if (pdata->max_voltage_uV) {
+		unsigned int vmax;
+		/**
+		 * TPS51632 hw behavior: VMAX register can be write only
+		 * once as it get locked after first write. The lock get
+		 * reset only when device is power-reset.
+		 * Write register only when lock bit is not enabled.
+		 */
+		ret = regmap_read(tps->regmap, TPS51632_VMAX_REG, &vmax);
+		if (ret < 0) {
+			dev_err(tps->dev, "VMAX read failed, err %d\n", ret);
+			return ret;
+		}
+		if (!(vmax & TPS51632_VMAX_LOCK)) {
+			vsel = TPS51632_VOLT_VSEL(pdata->max_voltage_uV);
+			ret = regmap_write(tps->regmap, TPS51632_VMAX_REG,
+					vsel);
+			if (ret < 0) {
+				dev_err(tps->dev,
+					"VMAX write failed, err %d\n", ret);
+				return ret;
+			}
+		}
+	}
+
+skip_pwm_config:
+	ret = regmap_write(tps->regmap, TPS51632_DVFS_CONTROL_REG, control);
+	if (ret < 0)
+		dev_err(tps->dev, "DVFS reg write failed, err %d\n", ret);
+	return ret;
+}
+
+static bool rd_wr_reg(struct device *dev, unsigned int reg)
+{
+	if ((reg >= 0x8) && (reg <= 0x10))
+		return false;
+	return true;
+}
+
+static const struct regmap_config tps51632_regmap_config = {
+	.reg_bits		= 8,
+	.val_bits		= 8,
+	.writeable_reg		= rd_wr_reg,
+	.readable_reg		= rd_wr_reg,
+	.max_register		= TPS51632_MAX_REG - 1,
+	.cache_type		= REGCACHE_RBTREE,
+};
+
+static int __devinit tps51632_probe(struct i2c_client *client,
+				const struct i2c_device_id *id)
+{
+	struct tps51632_regulator_platform_data *pdata;
+	struct regulator_dev *rdev;
+	struct tps51632_chip *tps;
+	int ret;
+	struct regulator_config config = { };
+
+	pdata = client->dev.platform_data;
+	if (!pdata) {
+		dev_err(&client->dev, "No Platform data\n");
+		return -EINVAL;
+	}
+
+	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
+	if (!tps) {
+		dev_err(&client->dev, "Memory allocation failed\n");
+		return -ENOMEM;
+	}
+
+	tps->dev = &client->dev;
+	tps->desc.name = id->name;
+	tps->desc.id = 0;
+	tps->desc.ramp_delay = TPS51632_DEFAULT_RAMP_DELAY;
+	tps->desc.min_uV = TPS51632_MIN_VOLATGE;
+	tps->desc.uV_step = TPS51632_VOLATGE_STEP_10mV;
+	tps->desc.n_voltages = (TPS51632_MAX_VSEL - TPS51632_MIN_VSEL) + 1;
+	tps->desc.ops = &tps51632_dcdc_ops;
+	tps->desc.type = REGULATOR_VOLTAGE;
+	tps->desc.owner = THIS_MODULE;
+
+	tps->regmap = devm_regmap_init_i2c(client, &tps51632_regmap_config);
+	if (IS_ERR(tps->regmap)) {
+		ret = PTR_ERR(tps->regmap);
+		dev_err(&client->dev, "regmap init failed, err %d\n", ret);
+		return ret;
+	}
+	i2c_set_clientdata(client, tps);
+
+	ret = tps51632_init_dcdc(tps, pdata);
+	if (ret < 0) {
+		dev_err(tps->dev, "Init failed, err = %d\n", ret);
+		return ret;
+	}
+
+	/* Register the regulators */
+	config.dev = &client->dev;
+	config.init_data = pdata->reg_init_data;
+	config.driver_data = tps;
+	config.regmap = tps->regmap;
+	config.of_node = client->dev.of_node;
+
+	rdev = regulator_register(&tps->desc, &config);
+	if (IS_ERR(rdev)) {
+		dev_err(tps->dev, "regulator register failed\n");
+		return PTR_ERR(rdev);
+	}
+
+	tps->rdev = rdev;
+	return 0;
+}
+
+static int __devexit tps51632_remove(struct i2c_client *client)
+{
+	struct tps51632_chip *tps = i2c_get_clientdata(client);
+
+	regulator_unregister(tps->rdev);
+	return 0;
+}
+
+static const struct i2c_device_id tps51632_id[] = {
+	{.name = "tps51632",},
+	{},
+};
+
+MODULE_DEVICE_TABLE(i2c, tps51632_id);
+
+static struct i2c_driver tps51632_i2c_driver = {
+	.driver = {
+		.name = "tps51632",
+		.owner = THIS_MODULE,
+	},
+	.probe = tps51632_probe,
+	.remove = __devexit_p(tps51632_remove),
+	.id_table = tps51632_id,
+};
+
+static int __init tps51632_init(void)
+{
+	return i2c_add_driver(&tps51632_i2c_driver);
+}
+subsys_initcall(tps51632_init);
+
+static void __exit tps51632_cleanup(void)
+{
+	i2c_del_driver(&tps51632_i2c_driver);
+}
+module_exit(tps51632_cleanup);
+
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_DESCRIPTION("TPS51632 voltage regulator driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/regulator/tps51632-regulator.h b/include/linux/regulator/tps51632-regulator.h
new file mode 100644
index 000000000000..d00841e1a75a
--- /dev/null
+++ b/include/linux/regulator/tps51632-regulator.h
@@ -0,0 +1,47 @@
+/*
+ * tps51632-regulator.h -- TPS51632 regulator
+ *
+ * Interface for regulator driver for TPS51632 3-2-1 Phase D-Cap Step Down
+ * Driverless Controller with serial VID control and DVFS.
+ *
+ * Copyright (C) 2012 NVIDIA Corporation
+
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA	02110-1301, USA.
+ *
+ */
+
+#ifndef __LINUX_REGULATOR_TPS51632_H
+#define __LINUX_REGULATOR_TPS51632_H
+
+/*
+ * struct tps51632_regulator_platform_data - tps51632 regulator platform data.
+ *
+ * @reg_init_data: The regulator init data.
+ * @enable_pwm_dvfs: Enable PWM DVFS or not.
+ * @dvfs_step_20mV: Step for DVFS is 20mV or 10mV.
+ * @max_voltage_uV: Maximum possible voltage in PWM-DVFS mode.
+ * @base_voltage_uV: Base voltage when PWM-DVFS enabled.
+ */
+struct tps51632_regulator_platform_data {
+	struct regulator_init_data *reg_init_data;
+	bool enable_pwm_dvfs;
+	bool dvfs_step_20mV;
+	int max_voltage_uV;
+	int base_voltage_uV;
+};
+
+#endif /* __LINUX_REGULATOR_TPS51632_H */
-- 
cgit v1.2.3-55-g7522


From bd7a2b600ace90c8819495b639a744c8f5c68feb Mon Sep 17 00:00:00 2001
From: Pawel Moll
Date: Mon, 24 Sep 2012 18:56:53 +0100
Subject: regulator: core: Support for continuous voltage range

Some regulators can set any voltage within the constraints range,
not being limited to specified operating points.

This patch makes it possible to describe such regulator and makes
the regulator_is_supported_voltage() function behave correctly.

Signed-off-by: Pawel Moll <pawel.moll@arm.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/regulator/core.c         | 5 +++++
 include/linux/regulator/driver.h | 3 +++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 5c4829cba6a6..f7c74db7465c 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1979,6 +1979,11 @@ int regulator_is_supported_voltage(struct regulator *regulator,
 			return ret;
 	}
 
+	/* Any voltage within constrains range is fine? */
+	if (rdev->desc->continuous_voltage_range)
+		return min_uV >= rdev->constraints->min_uV &&
+				max_uV <= rdev->constraints->max_uV;
+
 	ret = regulator_count_voltages(regulator);
 	if (ret < 0)
 		return ret;
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 7932a3bf21bd..f2b72b230b9b 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -181,6 +181,8 @@ enum regulator_type {
  * @type: Indicates if the regulator is a voltage or current regulator.
  * @owner: Module providing the regulator, used for refcounting.
  *
+ * @continuous_voltage_range: Indicates if the regulator can set any
+ *                            voltage within constrains range.
  * @n_voltages: Number of selectors available for ops.list_voltage().
  *
  * @min_uV: Voltage given by the lowest selector (if linear mapping)
@@ -199,6 +201,7 @@ struct regulator_desc {
 	const char *name;
 	const char *supply_name;
 	int id;
+	bool continuous_voltage_range;
 	unsigned n_voltages;
 	struct regulator_ops *ops;
 	int irq;
-- 
cgit v1.2.3-55-g7522


From 757ef79188657087f96f6f12c003b682860fede2 Mon Sep 17 00:00:00 2001
From: Jon Hunter
Date: Thu, 28 Jun 2012 13:41:29 -0500
Subject: ARM: OMAP2+: GPMC: Remove unused OneNAND get_freq() platform function

A platform function pointer for getting the frequency of a OneNAND device
was added so that a platform could specify a custom function for returning
the frequency and not just rely on the OneNAND version to determine the
frequency. However, this platform function pointer is not currently being
used and I am not sure if it ever has.

OneNAND devices are not so common these days and as far as I know not being
used with new devices. Therefore, it is most likely that this get_freq()
function pointer will not be used and so remove it.

Given that the get_freq() function pointer is not used, neither is the
clk_dep variable and so all references to it can also be removed.

Signed-off-by: Jon Hunter <jon-hunter@ti.com>
Signed-off-by: Afzal Mohammed <afzal@ti.com>
---
 arch/arm/mach-omap2/gpmc-onenand.c              | 39 ++++---------------------
 include/linux/platform_data/mtd-onenand-omap2.h |  8 -----
 2 files changed, 5 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 29d391b273fc..50165aa4205a 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -140,21 +140,10 @@ static void set_onenand_cfg(void __iomem *onenand_base)
 }
 
 static int omap2_onenand_get_freq(struct omap_onenand_platform_data *cfg,
-				  void __iomem *onenand_base, bool *clk_dep)
+				  void __iomem *onenand_base)
 {
 	u16 ver = readw(onenand_base + ONENAND_REG_VERSION_ID);
-	int freq = 0;
-
-	if (cfg->get_freq) {
-		struct onenand_freq_info fi;
-
-		fi.maf_id = readw(onenand_base + ONENAND_REG_MANUFACTURER_ID);
-		fi.dev_id = readw(onenand_base + ONENAND_REG_DEVICE_ID);
-		fi.ver_id = ver;
-		freq = cfg->get_freq(&fi, clk_dep);
-		if (freq)
-			return freq;
-	}
+	int freq;
 
 	switch ((ver >> 4) & 0xf) {
 	case 0:
@@ -182,7 +171,7 @@ static int omap2_onenand_get_freq(struct omap_onenand_platform_data *cfg,
 
 static struct gpmc_timings
 omap2_onenand_calc_sync_timings(struct omap_onenand_platform_data *cfg,
-				int freq, bool clk_dep)
+				int freq)
 {
 	struct gpmc_timings t;
 	const int t_cer  = 15;
@@ -261,22 +250,6 @@ omap2_onenand_calc_sync_timings(struct omap_onenand_platform_data *cfg,
 	else
 		latency = 4;
 
-	if (clk_dep) {
-		if (gpmc_clk_ns < 12) { /* >83Mhz */
-			t_ces   = 3;
-			t_avds  = 4;
-		} else if (gpmc_clk_ns < 15) { /* >66Mhz */
-			t_ces   = 5;
-			t_avds  = 4;
-		} else if (gpmc_clk_ns < 25) { /* >40Mhz */
-			t_ces   = 6;
-			t_avds  = 5;
-		} else {
-			t_ces   = 7;
-			t_avds  = 7;
-		}
-	}
-
 	/* Set synchronous read timings */
 	memset(&t, 0, sizeof(t));
 
@@ -399,16 +372,14 @@ static int omap2_onenand_setup_sync(void __iomem *onenand_base, int *freq_ptr)
 {
 	int ret, freq = *freq_ptr;
 	struct gpmc_timings t;
-	bool clk_dep = false;
 
 	if (!freq) {
 		/* Very first call freq is not known */
-		freq = omap2_onenand_get_freq(gpmc_onenand_data,
-						onenand_base, &clk_dep);
+		freq = omap2_onenand_get_freq(gpmc_onenand_data, onenand_base);
 		set_onenand_cfg(onenand_base);
 	}
 
-	t = omap2_onenand_calc_sync_timings(gpmc_onenand_data, freq, clk_dep);
+	t = omap2_onenand_calc_sync_timings(gpmc_onenand_data, freq);
 
 	ret = gpmc_set_sync_mode(gpmc_onenand_data->cs, &t);
 	if (IS_ERR_VALUE(ret))
diff --git a/include/linux/platform_data/mtd-onenand-omap2.h b/include/linux/platform_data/mtd-onenand-omap2.h
index 2858667d2e4f..21bb0ff4052e 100644
--- a/include/linux/platform_data/mtd-onenand-omap2.h
+++ b/include/linux/platform_data/mtd-onenand-omap2.h
@@ -15,20 +15,12 @@
 #define ONENAND_SYNC_READ	(1 << 0)
 #define ONENAND_SYNC_READWRITE	(1 << 1)
 
-struct onenand_freq_info {
-	u16			maf_id;
-	u16			dev_id;
-	u16			ver_id;
-};
-
 struct omap_onenand_platform_data {
 	int			cs;
 	int			gpio_irq;
 	struct mtd_partition	*parts;
 	int			nr_parts;
 	int			(*onenand_setup)(void __iomem *, int *freq_ptr);
-	int		(*get_freq)(const struct onenand_freq_info *freq_info,
-				    bool *clk_dep);
 	int			dma_channel;
 	u8			flags;
 	u8			regulator_can_sleep;
-- 
cgit v1.2.3-55-g7522


From eb77b6a78ac7f63985a3f592baf80ff33d213c48 Mon Sep 17 00:00:00 2001
From: Afzal Mohammed
Date: Fri, 5 Oct 2012 11:39:54 +0530
Subject: ARM: OMAP2+: onenand: connected soc info in pdata

onenand driver needs to know whether soc is falling under
34xx family to properly handle onenand. But driver is not
supposed to do cpu_is_* check, hence educate platform data
with this information. Driver can make use of it to avoid
cpu_is_* check.

Signed-off-by: Afzal Mohammed <afzal@ti.com>
---
 arch/arm/mach-omap2/gpmc-onenand.c              | 5 +++++
 include/linux/platform_data/mtd-onenand-omap2.h | 1 +
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 06fd84657218..4a1c0b7ab432 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -428,6 +428,11 @@ void __init gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
 		gpmc_onenand_data->flags |= ONENAND_SYNC_READ;
 	}
 
+	if (cpu_is_omap34xx())
+		gpmc_onenand_data->flags |= ONENAND_IN_OMAP34XX;
+	else
+		gpmc_onenand_data->flags &= ~ONENAND_IN_OMAP34XX;
+
 	err = gpmc_cs_request(gpmc_onenand_data->cs, ONENAND_IO_SIZE,
 				(unsigned long *)&gpmc_onenand_resource.start);
 	if (err < 0) {
diff --git a/include/linux/platform_data/mtd-onenand-omap2.h b/include/linux/platform_data/mtd-onenand-omap2.h
index 21bb0ff4052e..ef9c60d4b29b 100644
--- a/include/linux/platform_data/mtd-onenand-omap2.h
+++ b/include/linux/platform_data/mtd-onenand-omap2.h
@@ -14,6 +14,7 @@
 
 #define ONENAND_SYNC_READ	(1 << 0)
 #define ONENAND_SYNC_READWRITE	(1 << 1)
+#define	ONENAND_IN_OMAP34XX	(1 << 2)
 
 struct omap_onenand_platform_data {
 	int			cs;
-- 
cgit v1.2.3-55-g7522


From b6ab13e7d6d2778702baea7433d0bd9f234d5083 Mon Sep 17 00:00:00 2001
From: Afzal Mohammed
Date: Sat, 29 Sep 2012 10:32:42 +0530
Subject: ARM: OMAP2+: onenand: header cleanup

For common arm zImage existing onenand header file
in platform specific location was moved to generic
platform data location, but it contained more than
platform data, remove it. New local header has been
created for exposing functions.

Signed-off-by: Afzal Mohammed <afzal@ti.com>
---
 arch/arm/mach-omap2/board-flash.c               |  1 +
 arch/arm/mach-omap2/board-igep0020.c            |  1 +
 arch/arm/mach-omap2/board-n8x0.c                |  1 +
 arch/arm/mach-omap2/board-rm680.c               |  1 +
 arch/arm/mach-omap2/board-rx51-peripherals.c    |  1 +
 arch/arm/mach-omap2/gpmc-onenand.c              |  1 +
 arch/arm/mach-omap2/gpmc-onenand.h              | 24 ++++++++++++++++++++++++
 include/linux/platform_data/mtd-onenand-omap2.h | 19 +++----------------
 8 files changed, 33 insertions(+), 16 deletions(-)
 create mode 100644 arch/arm/mach-omap2/gpmc-onenand.h

(limited to 'include')

diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c
index d4ac5352a71c..f438d511ba11 100644
--- a/arch/arm/mach-omap2/board-flash.c
+++ b/arch/arm/mach-omap2/board-flash.c
@@ -25,6 +25,7 @@
 
 #include "common.h"
 #include "board-flash.h"
+#include "gpmc-onenand.h"
 
 #define REG_FPGA_REV			0x10
 #define REG_FPGA_DIP_SWITCH_INPUT2	0x60
diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c
index f6b3ed0e5c94..83c6efaf4226 100644
--- a/arch/arm/mach-omap2/board-igep0020.c
+++ b/arch/arm/mach-omap2/board-igep0020.c
@@ -43,6 +43,7 @@
 #include "common-board-devices.h"
 #include "board-flash.h"
 #include "control.h"
+#include "gpmc-onenand.h"
 
 #define IGEP2_SMSC911X_CS       5
 #define IGEP2_SMSC911X_GPIO     176
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index d95f727ca39a..92b19166aac8 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -32,6 +32,7 @@
 #include <plat/mmc.h>
 
 #include "mux.h"
+#include "gpmc-onenand.h"
 
 #define TUSB6010_ASYNC_CS	1
 #define TUSB6010_SYNC_CS	4
diff --git a/arch/arm/mach-omap2/board-rm680.c b/arch/arm/mach-omap2/board-rm680.c
index 45997bfbcbd2..154cf337c0c7 100644
--- a/arch/arm/mach-omap2/board-rm680.c
+++ b/arch/arm/mach-omap2/board-rm680.c
@@ -33,6 +33,7 @@
 #include "hsmmc.h"
 #include "sdram-nokia.h"
 #include "common-board-devices.h"
+#include "gpmc-onenand.h"
 
 static struct regulator_consumer_supply rm680_vemmc_consumers[] = {
 	REGULATOR_SUPPLY("vmmc", "omap_hsmmc.1"),
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 020e03c95bfe..45760044b2bd 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -54,6 +54,7 @@
 #include "mux.h"
 #include "hsmmc.h"
 #include "common-board-devices.h"
+#include "gpmc-onenand.h"
 
 #define SYSTEM_REV_B_USES_VAUX3	0x1699
 #define SYSTEM_REV_S_USES_VAUX3 0x8
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 4a1c0b7ab432..f318f11da2fa 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -23,6 +23,7 @@
 #include <plat/gpmc.h>
 
 #include "soc.h"
+#include "gpmc-onenand.h"
 
 #define	ONENAND_IO_SIZE	SZ_128K
 
diff --git a/arch/arm/mach-omap2/gpmc-onenand.h b/arch/arm/mach-omap2/gpmc-onenand.h
new file mode 100644
index 000000000000..216f23a8b45c
--- /dev/null
+++ b/arch/arm/mach-omap2/gpmc-onenand.h
@@ -0,0 +1,24 @@
+/*
+ *  arch/arm/mach-omap2/gpmc-onenand.h
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+#ifndef	__OMAP2_GPMC_ONENAND_H
+#define	__OMAP2_GPMC_ONENAND_H
+
+#include <linux/platform_data/mtd-onenand-omap2.h>
+
+#if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2)
+extern void gpmc_onenand_init(struct omap_onenand_platform_data *d);
+#else
+#define board_onenand_data	NULL
+static inline void gpmc_onenand_init(struct omap_onenand_platform_data *d)
+{
+}
+#endif
+
+#endif
diff --git a/include/linux/platform_data/mtd-onenand-omap2.h b/include/linux/platform_data/mtd-onenand-omap2.h
index ef9c60d4b29b..685af7e8b120 100644
--- a/include/linux/platform_data/mtd-onenand-omap2.h
+++ b/include/linux/platform_data/mtd-onenand-omap2.h
@@ -9,6 +9,9 @@
  * published by the Free Software Foundation.
  */
 
+#ifndef	__MTD_ONENAND_OMAP2_H
+#define	__MTD_ONENAND_OMAP2_H
+
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 
@@ -27,20 +30,4 @@ struct omap_onenand_platform_data {
 	u8			regulator_can_sleep;
 	u8			skip_initial_unlocking;
 };
-
-#define ONENAND_MAX_PARTITIONS 8
-
-#if defined(CONFIG_MTD_ONENAND_OMAP2) || \
-	defined(CONFIG_MTD_ONENAND_OMAP2_MODULE)
-
-extern void gpmc_onenand_init(struct omap_onenand_platform_data *d);
-
-#else
-
-#define board_onenand_data	NULL
-
-static inline void gpmc_onenand_init(struct omap_onenand_platform_data *d)
-{
-}
-
 #endif
-- 
cgit v1.2.3-55-g7522


From bc3668ea046be9e841eecfab04bddfa759e765d6 Mon Sep 17 00:00:00 2001
From: Afzal Mohammed
Date: Sat, 29 Sep 2012 12:26:13 +0530
Subject: ARM: OMAP2+: nand: header cleanup

For common arm zImage existing nand header file
in platform specific location was moved to generic
platform data location, but it contained more than
platform data, remove it. New local header has been
created for exposing functions.

Also move gpmc-nand platform data to platform header
meant for nand from gpmc header file

Signed-off-by: Afzal Mohammed <afzal@ti.com>
---
 arch/arm/mach-omap2/board-cm-t35.c           |  3 +-
 arch/arm/mach-omap2/board-cm-t3517.c         |  3 +-
 arch/arm/mach-omap2/board-flash.c            |  4 +-
 arch/arm/mach-omap2/board-omap3pandora.c     |  3 +-
 arch/arm/mach-omap2/common-board-devices.c   |  1 -
 arch/arm/mach-omap2/gpmc-nand.c              | 58 ++++++++++++++--------------
 arch/arm/mach-omap2/gpmc-nand.h              | 27 +++++++++++++
 arch/arm/mach-omap2/gpmc.c                   |  2 +
 arch/arm/plat-omap/include/plat/gpmc.h       | 28 +-------------
 include/linux/platform_data/mtd-nand-omap2.h | 41 ++++++++++++++------
 10 files changed, 98 insertions(+), 72 deletions(-)
 create mode 100644 arch/arm/mach-omap2/gpmc-nand.h

(limited to 'include')

diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index 376d26eb601c..fef68de716b5 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -53,6 +53,7 @@
 #include "sdram-micron-mt46h32m32lf-6.h"
 #include "hsmmc.h"
 #include "common-board-devices.h"
+#include "gpmc-nand.h"
 
 #define CM_T35_GPIO_PENDOWN		57
 #define SB_T35_USB_HUB_RESET_GPIO	167
@@ -181,7 +182,7 @@ static struct omap_nand_platform_data cm_t35_nand_data = {
 
 static void __init cm_t35_init_nand(void)
 {
-	if (gpmc_nand_init(&cm_t35_nand_data) < 0)
+	if (gpmc_nand_init(&cm_t35_nand_data, NULL) < 0)
 		pr_err("CM-T35: Unable to register NAND device\n");
 }
 #else
diff --git a/arch/arm/mach-omap2/board-cm-t3517.c b/arch/arm/mach-omap2/board-cm-t3517.c
index 59c0a45f75b0..3a19e80e0005 100644
--- a/arch/arm/mach-omap2/board-cm-t3517.c
+++ b/arch/arm/mach-omap2/board-cm-t3517.c
@@ -49,6 +49,7 @@
 #include "control.h"
 #include "common-board-devices.h"
 #include "am35xx-emac.h"
+#include "gpmc-nand.h"
 
 #if defined(CONFIG_LEDS_GPIO) || defined(CONFIG_LEDS_GPIO_MODULE)
 static struct gpio_led cm_t3517_leds[] = {
@@ -240,7 +241,7 @@ static struct omap_nand_platform_data cm_t3517_nand_data = {
 
 static void __init cm_t3517_init_nand(void)
 {
-	if (gpmc_nand_init(&cm_t3517_nand_data) < 0)
+	if (gpmc_nand_init(&cm_t3517_nand_data, NULL) < 0)
 		pr_err("CM-T3517: NAND initialization failed\n");
 }
 #else
diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c
index f438d511ba11..ba9fa86a10aa 100644
--- a/arch/arm/mach-omap2/board-flash.c
+++ b/arch/arm/mach-omap2/board-flash.c
@@ -26,6 +26,7 @@
 #include "common.h"
 #include "board-flash.h"
 #include "gpmc-onenand.h"
+#include "gpmc-nand.h"
 
 #define REG_FPGA_REV			0x10
 #define REG_FPGA_DIP_SWITCH_INPUT2	0x60
@@ -139,10 +140,9 @@ __init board_nand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs,
 	board_nand_data.parts		= nand_parts;
 	board_nand_data.nr_parts	= nr_parts;
 	board_nand_data.devsize		= nand_type;
-	board_nand_data.gpmc_t		= gpmc_t;
 
 	board_nand_data.ecc_opt = OMAP_ECC_HAMMING_CODE_DEFAULT;
-	gpmc_nand_init(&board_nand_data);
+	gpmc_nand_init(&board_nand_data, gpmc_t);
 }
 #endif /* CONFIG_MTD_NAND_OMAP2 || CONFIG_MTD_NAND_OMAP2_MODULE */
 
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index 00a1f4ae6e44..f286b4b4bd5b 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -50,6 +50,7 @@
 #include "sdram-micron-mt46h32m32lf-6.h"
 #include "hsmmc.h"
 #include "common-board-devices.h"
+#include "gpmc-nand.h"
 
 #define PANDORA_WIFI_IRQ_GPIO		21
 #define PANDORA_WIFI_NRESET_GPIO	23
@@ -602,7 +603,7 @@ static void __init omap3pandora_init(void)
 	omap_ads7846_init(1, OMAP3_PANDORA_TS_GPIO, 0, NULL);
 	usbhs_init(&usbhs_bdata);
 	usb_musb_init(NULL);
-	gpmc_nand_init(&pandora_nand_data);
+	gpmc_nand_init(&pandora_nand_data, NULL);
 
 	/* Ensure SDRC pins are mux'd for self-refresh */
 	omap_mux_init_signal("sdrc_cke0", OMAP_PIN_OUTPUT);
diff --git a/arch/arm/mach-omap2/common-board-devices.c b/arch/arm/mach-omap2/common-board-devices.c
index 90e0597667b9..ad856092c06a 100644
--- a/arch/arm/mach-omap2/common-board-devices.c
+++ b/arch/arm/mach-omap2/common-board-devices.c
@@ -25,7 +25,6 @@
 #include <linux/spi/ads7846.h>
 
 #include <linux/platform_data/spi-omap2-mcspi.h>
-#include <linux/platform_data/mtd-nand-omap2.h>
 
 #include "common.h"
 #include "common-board-devices.h"
diff --git a/arch/arm/mach-omap2/gpmc-nand.c b/arch/arm/mach-omap2/gpmc-nand.c
index 4acf497faeb3..abdb78a95a94 100644
--- a/arch/arm/mach-omap2/gpmc-nand.c
+++ b/arch/arm/mach-omap2/gpmc-nand.c
@@ -20,6 +20,10 @@
 #include <plat/gpmc.h>
 
 #include "soc.h"
+#include "gpmc-nand.h"
+
+/* minimum size for IO mapping */
+#define	NAND_IO_SIZE	4
 
 static struct resource gpmc_nand_resource[] = {
 	{
@@ -40,41 +44,36 @@ static struct platform_device gpmc_nand_device = {
 	.resource	= gpmc_nand_resource,
 };
 
-static int omap2_nand_gpmc_retime(struct omap_nand_platform_data *gpmc_nand_data)
+static int omap2_nand_gpmc_retime(
+				struct omap_nand_platform_data *gpmc_nand_data,
+				struct gpmc_timings *gpmc_t)
 {
 	struct gpmc_timings t;
 	int err;
 
-	if (!gpmc_nand_data->gpmc_t)
-		return 0;
-
 	memset(&t, 0, sizeof(t));
-	t.sync_clk = gpmc_nand_data->gpmc_t->sync_clk;
-	t.cs_on = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->cs_on);
-	t.adv_on = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->adv_on);
+	t.sync_clk = gpmc_t->sync_clk;
+	t.cs_on = gpmc_round_ns_to_ticks(gpmc_t->cs_on);
+	t.adv_on = gpmc_round_ns_to_ticks(gpmc_t->adv_on);
 
 	/* Read */
-	t.adv_rd_off = gpmc_round_ns_to_ticks(
-				gpmc_nand_data->gpmc_t->adv_rd_off);
+	t.adv_rd_off = gpmc_round_ns_to_ticks(gpmc_t->adv_rd_off);
 	t.oe_on  = t.adv_on;
-	t.access = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->access);
-	t.oe_off = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->oe_off);
-	t.cs_rd_off = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->cs_rd_off);
-	t.rd_cycle  = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->rd_cycle);
+	t.access = gpmc_round_ns_to_ticks(gpmc_t->access);
+	t.oe_off = gpmc_round_ns_to_ticks(gpmc_t->oe_off);
+	t.cs_rd_off = gpmc_round_ns_to_ticks(gpmc_t->cs_rd_off);
+	t.rd_cycle  = gpmc_round_ns_to_ticks(gpmc_t->rd_cycle);
 
 	/* Write */
-	t.adv_wr_off = gpmc_round_ns_to_ticks(
-				gpmc_nand_data->gpmc_t->adv_wr_off);
+	t.adv_wr_off = gpmc_round_ns_to_ticks(gpmc_t->adv_wr_off);
 	t.we_on  = t.oe_on;
 	if (cpu_is_omap34xx()) {
-	    t.wr_data_mux_bus =	gpmc_round_ns_to_ticks(
-				gpmc_nand_data->gpmc_t->wr_data_mux_bus);
-	    t.wr_access = gpmc_round_ns_to_ticks(
-				gpmc_nand_data->gpmc_t->wr_access);
+	    t.wr_data_mux_bus =	gpmc_round_ns_to_ticks(gpmc_t->wr_data_mux_bus);
+	    t.wr_access = gpmc_round_ns_to_ticks(gpmc_t->wr_access);
 	}
-	t.we_off = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->we_off);
-	t.cs_wr_off = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->cs_wr_off);
-	t.wr_cycle  = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->wr_cycle);
+	t.we_off = gpmc_round_ns_to_ticks(gpmc_t->we_off);
+	t.cs_wr_off = gpmc_round_ns_to_ticks(gpmc_t->cs_wr_off);
+	t.wr_cycle  = gpmc_round_ns_to_ticks(gpmc_t->wr_cycle);
 
 	/* Configure GPMC */
 	if (gpmc_nand_data->devsize == NAND_BUSWIDTH_16)
@@ -91,7 +90,8 @@ static int omap2_nand_gpmc_retime(struct omap_nand_platform_data *gpmc_nand_data
 	return 0;
 }
 
-int __init gpmc_nand_init(struct omap_nand_platform_data *gpmc_nand_data)
+int __init gpmc_nand_init(struct omap_nand_platform_data *gpmc_nand_data,
+			  struct gpmc_timings *gpmc_t)
 {
 	int err	= 0;
 	struct device *dev = &gpmc_nand_device.dev;
@@ -112,11 +112,13 @@ int __init gpmc_nand_init(struct omap_nand_platform_data *gpmc_nand_data)
 				gpmc_get_client_irq(GPMC_IRQ_FIFOEVENTENABLE);
 	gpmc_nand_resource[2].start =
 				gpmc_get_client_irq(GPMC_IRQ_COUNT_EVENT);
-	 /* Set timings in GPMC */
-	err = omap2_nand_gpmc_retime(gpmc_nand_data);
-	if (err < 0) {
-		dev_err(dev, "Unable to set gpmc timings: %d\n", err);
-		return err;
+
+	if (gpmc_t) {
+		err = omap2_nand_gpmc_retime(gpmc_nand_data, gpmc_t);
+		if (err < 0) {
+			dev_err(dev, "Unable to set gpmc timings: %d\n", err);
+			return err;
+		}
 	}
 
 	/* Enable RD PIN Monitoring Reg */
diff --git a/arch/arm/mach-omap2/gpmc-nand.h b/arch/arm/mach-omap2/gpmc-nand.h
new file mode 100644
index 000000000000..11a377f0e6f0
--- /dev/null
+++ b/arch/arm/mach-omap2/gpmc-nand.h
@@ -0,0 +1,27 @@
+/*
+ *  arch/arm/mach-omap2/gpmc-nand.h
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+#ifndef	__OMAP2_GPMC_NAND_H
+#define	__OMAP2_GPMC_NAND_H
+
+#include <plat/gpmc.h>
+#include <linux/platform_data/mtd-nand-omap2.h>
+
+#if IS_ENABLED(CONFIG_MTD_NAND_OMAP2)
+extern int gpmc_nand_init(struct omap_nand_platform_data *d,
+			  struct gpmc_timings *gpmc_t);
+#else
+static inline int gpmc_nand_init(struct omap_nand_platform_data *d,
+				 struct gpmc_timings *gpmc_t)
+{
+	return 0;
+}
+#endif
+
+#endif
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index 91af5aefeaae..34823b3092f3 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -26,6 +26,8 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 
+#include <linux/platform_data/mtd-nand-omap2.h>
+
 #include <asm/mach-types.h>
 #include <plat/gpmc.h>
 
diff --git a/arch/arm/plat-omap/include/plat/gpmc.h b/arch/arm/plat-omap/include/plat/gpmc.h
index f7e0990eaf37..4b06bb4531a2 100644
--- a/arch/arm/plat-omap/include/plat/gpmc.h
+++ b/arch/arm/plat-omap/include/plat/gpmc.h
@@ -11,6 +11,8 @@
 #ifndef __OMAP2_GPMC_H
 #define __OMAP2_GPMC_H
 
+#include <linux/platform_data/mtd-nand-omap2.h>
+
 /* Maximum Number of Chip Selects */
 #define GPMC_CS_NUM		8
 
@@ -86,16 +88,6 @@
 #define PREFETCH_FIFOTHRESHOLD_MAX	0x40
 #define PREFETCH_FIFOTHRESHOLD(val)	((val) << 8)
 
-enum omap_ecc {
-		/* 1-bit ecc: stored at end of spare area */
-	OMAP_ECC_HAMMING_CODE_DEFAULT = 0, /* Default, s/w method */
-	OMAP_ECC_HAMMING_CODE_HW, /* gpmc to detect the error */
-		/* 1-bit ecc: stored at beginning of spare area as romcode */
-	OMAP_ECC_HAMMING_CODE_HW_ROMCODE, /* gpmc method & romcode layout */
-	OMAP_ECC_BCH4_CODE_HW, /* 4-bit BCH ecc code */
-	OMAP_ECC_BCH8_CODE_HW, /* 8-bit BCH ecc code */
-};
-
 /*
  * Note that all values in this struct are in nanoseconds except sync_clk
  * (which is in picoseconds), while the register values are in gpmc_fck cycles.
@@ -133,22 +125,6 @@ struct gpmc_timings {
 	u16 wr_data_mux_bus;	/* WRDATAONADMUXBUS */
 };
 
-struct gpmc_nand_regs {
-	void __iomem	*gpmc_status;
-	void __iomem	*gpmc_nand_command;
-	void __iomem	*gpmc_nand_address;
-	void __iomem	*gpmc_nand_data;
-	void __iomem	*gpmc_prefetch_config1;
-	void __iomem	*gpmc_prefetch_config2;
-	void __iomem	*gpmc_prefetch_control;
-	void __iomem	*gpmc_prefetch_status;
-	void __iomem	*gpmc_ecc_config;
-	void __iomem	*gpmc_ecc_control;
-	void __iomem	*gpmc_ecc_size_config;
-	void __iomem	*gpmc_ecc1_result;
-	void __iomem	*gpmc_bch_result0;
-};
-
 extern void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs);
 extern int gpmc_get_client_irq(unsigned irq_config);
 
diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h
index 1a68c1e5fe53..e1965fe581d1 100644
--- a/include/linux/platform_data/mtd-nand-omap2.h
+++ b/include/linux/platform_data/mtd-nand-omap2.h
@@ -8,7 +8,9 @@
  * published by the Free Software Foundation.
  */
 
-#include <plat/gpmc.h>
+#ifndef	_MTD_NAND_OMAP2_H
+#define	_MTD_NAND_OMAP2_H
+
 #include <linux/mtd/partitions.h>
 
 enum nand_io {
@@ -18,10 +20,35 @@ enum nand_io {
 	NAND_OMAP_PREFETCH_IRQ		/* prefetch enabled irq mode */
 };
 
+enum omap_ecc {
+		/* 1-bit ecc: stored at end of spare area */
+	OMAP_ECC_HAMMING_CODE_DEFAULT = 0, /* Default, s/w method */
+	OMAP_ECC_HAMMING_CODE_HW, /* gpmc to detect the error */
+		/* 1-bit ecc: stored at beginning of spare area as romcode */
+	OMAP_ECC_HAMMING_CODE_HW_ROMCODE, /* gpmc method & romcode layout */
+	OMAP_ECC_BCH4_CODE_HW, /* 4-bit BCH ecc code */
+	OMAP_ECC_BCH8_CODE_HW, /* 8-bit BCH ecc code */
+};
+
+struct gpmc_nand_regs {
+	void __iomem	*gpmc_status;
+	void __iomem	*gpmc_nand_command;
+	void __iomem	*gpmc_nand_address;
+	void __iomem	*gpmc_nand_data;
+	void __iomem	*gpmc_prefetch_config1;
+	void __iomem	*gpmc_prefetch_config2;
+	void __iomem	*gpmc_prefetch_control;
+	void __iomem	*gpmc_prefetch_status;
+	void __iomem	*gpmc_ecc_config;
+	void __iomem	*gpmc_ecc_control;
+	void __iomem	*gpmc_ecc_size_config;
+	void __iomem	*gpmc_ecc1_result;
+	void __iomem	*gpmc_bch_result0;
+};
+
 struct omap_nand_platform_data {
 	int			cs;
 	struct mtd_partition	*parts;
-	struct gpmc_timings	*gpmc_t;
 	int			nr_parts;
 	bool			dev_ready;
 	enum nand_io		xfer_type;
@@ -30,14 +57,4 @@ struct omap_nand_platform_data {
 	struct gpmc_nand_regs	reg;
 };
 
-/* minimum size for IO mapping */
-#define	NAND_IO_SIZE	4
-
-#if defined(CONFIG_MTD_NAND_OMAP2) || defined(CONFIG_MTD_NAND_OMAP2_MODULE)
-extern int gpmc_nand_init(struct omap_nand_platform_data *d);
-#else
-static inline int gpmc_nand_init(struct omap_nand_platform_data *d)
-{
-	return 0;
-}
 #endif
-- 
cgit v1.2.3-55-g7522


From 2fdf0c98969fdac8f7b191d4988e2e436717c857 Mon Sep 17 00:00:00 2001
From: Afzal Mohammed
Date: Thu, 4 Oct 2012 15:49:04 +0530
Subject: ARM: OMAP2+: gpmc: nand register helper bch update

Update helper function that provides gpmc-nand register
details for nand driver with bch register information.
Using this nand driver can be made self sufficient to
handle remaining gpmc-nand operations by itself instead
of relying on gpmc exported nand functions.

Signed-off-by: Afzal Mohammed <afzal@ti.com>
---
 arch/arm/mach-omap2/gpmc.c                   | 18 +++++++++++++++++-
 include/linux/platform_data/mtd-nand-omap2.h |  7 ++++++-
 2 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index 34823b3092f3..f5cde49854a5 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -61,6 +61,9 @@
 #define GPMC_ECC_SIZE_CONFIG	0x1fc
 #define GPMC_ECC1_RESULT        0x200
 #define GPMC_ECC_BCH_RESULT_0   0x240   /* not available on OMAP2 */
+#define	GPMC_ECC_BCH_RESULT_1	0x244	/* not available on OMAP2 */
+#define	GPMC_ECC_BCH_RESULT_2	0x248	/* not available on OMAP2 */
+#define	GPMC_ECC_BCH_RESULT_3	0x24c	/* not available on OMAP2 */
 
 /* GPMC ECC control settings */
 #define GPMC_ECC_CTRL_ECCCLEAR		0x100
@@ -77,6 +80,7 @@
 
 #define GPMC_CS0_OFFSET		0x60
 #define GPMC_CS_SIZE		0x30
+#define	GPMC_BCH_SIZE		0x10
 
 #define GPMC_MEM_START		0x00000000
 #define GPMC_MEM_END		0x3FFFFFFF
@@ -731,6 +735,8 @@ EXPORT_SYMBOL(gpmc_prefetch_reset);
 
 void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs)
 {
+	int i;
+
 	reg->gpmc_status = gpmc_base + GPMC_STATUS;
 	reg->gpmc_nand_command = gpmc_base + GPMC_CS0_OFFSET +
 				GPMC_CS_NAND_COMMAND + GPMC_CS_SIZE * cs;
@@ -746,7 +752,17 @@ void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs)
 	reg->gpmc_ecc_control = gpmc_base + GPMC_ECC_CONTROL;
 	reg->gpmc_ecc_size_config = gpmc_base + GPMC_ECC_SIZE_CONFIG;
 	reg->gpmc_ecc1_result = gpmc_base + GPMC_ECC1_RESULT;
-	reg->gpmc_bch_result0 = gpmc_base + GPMC_ECC_BCH_RESULT_0;
+
+	for (i = 0; i < GPMC_BCH_NUM_REMAINDER; i++) {
+		reg->gpmc_bch_result0[i] = gpmc_base + GPMC_ECC_BCH_RESULT_0 +
+					   GPMC_BCH_SIZE * i;
+		reg->gpmc_bch_result1[i] = gpmc_base + GPMC_ECC_BCH_RESULT_1 +
+					   GPMC_BCH_SIZE * i;
+		reg->gpmc_bch_result2[i] = gpmc_base + GPMC_ECC_BCH_RESULT_2 +
+					   GPMC_BCH_SIZE * i;
+		reg->gpmc_bch_result3[i] = gpmc_base + GPMC_ECC_BCH_RESULT_3 +
+					   GPMC_BCH_SIZE * i;
+	}
 }
 
 int gpmc_get_client_irq(unsigned irq_config)
diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h
index e1965fe581d1..24d32ca34bef 100644
--- a/include/linux/platform_data/mtd-nand-omap2.h
+++ b/include/linux/platform_data/mtd-nand-omap2.h
@@ -13,6 +13,8 @@
 
 #include <linux/mtd/partitions.h>
 
+#define	GPMC_BCH_NUM_REMAINDER	8
+
 enum nand_io {
 	NAND_OMAP_PREFETCH_POLLED = 0,	/* prefetch polled mode, default */
 	NAND_OMAP_POLLED,		/* polled mode, without prefetch */
@@ -43,7 +45,10 @@ struct gpmc_nand_regs {
 	void __iomem	*gpmc_ecc_control;
 	void __iomem	*gpmc_ecc_size_config;
 	void __iomem	*gpmc_ecc1_result;
-	void __iomem	*gpmc_bch_result0;
+	void __iomem	*gpmc_bch_result0[GPMC_BCH_NUM_REMAINDER];
+	void __iomem	*gpmc_bch_result1[GPMC_BCH_NUM_REMAINDER];
+	void __iomem	*gpmc_bch_result2[GPMC_BCH_NUM_REMAINDER];
+	void __iomem	*gpmc_bch_result3[GPMC_BCH_NUM_REMAINDER];
 };
 
 struct omap_nand_platform_data {
-- 
cgit v1.2.3-55-g7522


From 2dc4e5105f012bda7eef2f459ed3d5299ded9672 Mon Sep 17 00:00:00 2001
From: Gustavo Padovan
Date: Fri, 12 Oct 2012 19:35:24 +0800
Subject: Bluetooth: Add chan->ops->defer()

When DEFER_SETUP is set defer() will trigger an authorization
request to the userspace.

l2cap_chan_no_defer() is meant to be used when one does not want to
support DEFER_SETUP (A2MP for example).

Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h |  5 +++++
 net/bluetooth/a2mp.c          |  1 +
 net/bluetooth/l2cap_core.c    | 10 +++-------
 net/bluetooth/l2cap_sock.c    | 10 ++++++++++
 4 files changed, 19 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index caab98c45121..6e23afdf65c1 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -541,6 +541,7 @@ struct l2cap_ops {
 	void			(*state_change) (struct l2cap_chan *chan,
 						 int state);
 	void			(*ready) (struct l2cap_chan *chan);
+	void			(*defer) (struct l2cap_chan *chan);
 	struct sk_buff		*(*alloc_skb) (struct l2cap_chan *chan,
 					       unsigned long len, int nb);
 };
@@ -748,6 +749,10 @@ static inline void l2cap_chan_no_ready(struct l2cap_chan *chan)
 {
 }
 
+static inline void l2cap_chan_no_defer(struct l2cap_chan *chan)
+{
+}
+
 extern bool disable_ertm;
 
 int l2cap_init_sockets(void);
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 3ff4dc928bf5..7bf9a10d8e46 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -699,6 +699,7 @@ static struct l2cap_ops a2mp_chan_ops = {
 	.new_connection = l2cap_chan_no_new_connection,
 	.teardown = l2cap_chan_no_teardown,
 	.ready = l2cap_chan_no_ready,
+	.defer = l2cap_chan_no_defer,
 };
 
 static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked)
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 9d84050bed2c..314d95580d73 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1120,11 +1120,9 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
 				lock_sock(sk);
 				if (test_bit(BT_SK_DEFER_SETUP,
 					     &bt_sk(sk)->flags)) {
-					struct sock *parent = bt_sk(sk)->parent;
 					rsp.result = __constant_cpu_to_le16(L2CAP_CR_PEND);
 					rsp.status = __constant_cpu_to_le16(L2CAP_CS_AUTHOR_PEND);
-					if (parent)
-						parent->sk_data_ready(parent, 0);
+					chan->ops->defer(chan);
 
 				} else {
 					__l2cap_state_change(chan, BT_CONFIG);
@@ -3460,7 +3458,7 @@ static void __l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd,
 				__l2cap_state_change(chan, BT_CONNECT2);
 				result = L2CAP_CR_PEND;
 				status = L2CAP_CS_AUTHOR_PEND;
-				parent->sk_data_ready(parent, 0);
+				chan->ops->defer(chan);
 			} else {
 				__l2cap_state_change(chan, BT_CONFIG);
 				result = L2CAP_CR_SUCCESS;
@@ -5523,11 +5521,9 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 			if (!status) {
 				if (test_bit(BT_SK_DEFER_SETUP,
 					     &bt_sk(sk)->flags)) {
-					struct sock *parent = bt_sk(sk)->parent;
 					res = L2CAP_CR_PEND;
 					stat = L2CAP_CS_AUTHOR_PEND;
-					if (parent)
-						parent->sk_data_ready(parent, 0);
+					chan->ops->defer(chan);
 				} else {
 					__l2cap_state_change(chan, BT_CONFIG);
 					res = L2CAP_CR_SUCCESS;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index d5093b853b05..5fae2bd879a1 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1081,6 +1081,15 @@ static void l2cap_sock_ready_cb(struct l2cap_chan *chan)
 	release_sock(sk);
 }
 
+static void l2cap_sock_defer_cb(struct l2cap_chan *chan)
+{
+	struct sock *sk = chan->data;
+	struct sock *parent = bt_sk(sk)->parent;
+
+	if (parent)
+		parent->sk_data_ready(parent, 0);
+}
+
 static struct l2cap_ops l2cap_chan_ops = {
 	.name		= "L2CAP Socket Interface",
 	.new_connection	= l2cap_sock_new_connection_cb,
@@ -1089,6 +1098,7 @@ static struct l2cap_ops l2cap_chan_ops = {
 	.teardown	= l2cap_sock_teardown_cb,
 	.state_change	= l2cap_sock_state_change_cb,
 	.ready		= l2cap_sock_ready_cb,
+	.defer		= l2cap_sock_defer_cb,
 	.alloc_skb	= l2cap_sock_alloc_skb_cb,
 };
 
-- 
cgit v1.2.3-55-g7522


From d73a098804b4d1d254b1caf1d114e5b707dee060 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Mon, 15 Oct 2012 11:58:40 +0300
Subject: Bluetooth: AMP: Handle complete frames in l2cap

Check flags type in switch statement and handle new frame
type ACL_COMPLETE used for High Speed data over AMP.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h |  1 +
 net/bluetooth/l2cap_core.c  | 15 ++++++++++-----
 2 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 77b6a197a6f6..88cbbda61027 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -198,6 +198,7 @@ enum {
 #define ACL_START_NO_FLUSH	0x00
 #define ACL_CONT		0x01
 #define ACL_START		0x02
+#define ACL_COMPLETE		0x03
 #define ACL_ACTIVE_BCAST	0x04
 #define ACL_PICO_BCAST		0x08
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index fca407e17f16..8faa3121bb44 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5568,6 +5568,8 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
 {
 	struct l2cap_conn *conn = hcon->l2cap_data;
+	struct l2cap_hdr *hdr;
+	int len;
 
 	if (!conn)
 		conn = l2cap_conn_add(hcon, 0);
@@ -5577,10 +5579,10 @@ int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
 
 	BT_DBG("conn %p len %d flags 0x%x", conn, skb->len, flags);
 
-	if (!(flags & ACL_CONT)) {
-		struct l2cap_hdr *hdr;
-		int len;
-
+	switch (flags) {
+	case ACL_START:
+	case ACL_START_NO_FLUSH:
+	case ACL_COMPLETE:
 		if (conn->rx_len) {
 			BT_ERR("Unexpected start frame (len %d)", skb->len);
 			kfree_skb(conn->rx_skb);
@@ -5622,7 +5624,9 @@ int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
 		skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len),
 					  skb->len);
 		conn->rx_len = len - skb->len;
-	} else {
+		break;
+
+	case ACL_CONT:
 		BT_DBG("Cont: frag len %d (expecting %d)", skb->len, conn->rx_len);
 
 		if (!conn->rx_len) {
@@ -5650,6 +5654,7 @@ int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
 			l2cap_recv_frame(conn, conn->rx_skb);
 			conn->rx_skb = NULL;
 		}
+		break;
 	}
 
 drop:
-- 
cgit v1.2.3-55-g7522


From ba1ee070909fae01248b8117da1706f3cf2bfd1b Mon Sep 17 00:00:00 2001
From: Salman Qazi
Date: Fri, 5 Oct 2012 14:24:14 -0700
Subject: crypto: vmac - Make VMAC work when blocks aren't aligned

VMAC implementation, as it is, does not work with blocks that
are not multiples of 128-bytes.  Furthermore, this is a problem
when using the implementation on scatterlists, even
when the complete plain text is 128-byte multiple, as the pieces
that get passed to vmac_update can be pretty much any size.

I also added test cases for unaligned blocks.

Signed-off-by: Salman Qazi <sqazi@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/testmgr.h      | 33 ++++++++++++++++++++++++++++++++-
 crypto/vmac.c         | 47 +++++++++++++++++++++++++++++++++++++++++++----
 include/crypto/vmac.h |  2 ++
 3 files changed, 77 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 76d7f6cc82f5..f8365e913de9 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -1707,7 +1707,7 @@ static struct hash_testvec aes_xcbc128_tv_template[] = {
 	}
 };
 
-#define VMAC_AES_TEST_VECTORS	8
+#define VMAC_AES_TEST_VECTORS	11
 static char vmac_string1[128] = {'\x01', '\x01', '\x01', '\x01',
 				'\x02', '\x03', '\x02', '\x02',
 				'\x02', '\x04', '\x01', '\x07',
@@ -1723,6 +1723,19 @@ static char vmac_string3[128] = {'a', 'b', 'c', 'a', 'b', 'c',
 				'a', 'b', 'c', 'a', 'b', 'c',
 				};
 
+static char vmac_string4[17] = {'b', 'c', 'e', 'f',
+				'i', 'j', 'l', 'm',
+				'o', 'p', 'r', 's',
+				't', 'u', 'w', 'x', 'z'};
+
+static char vmac_string5[127] = {'r', 'm', 'b', 't', 'c',
+				 'o', 'l', 'k', ']', '%',
+				 '9', '2', '7', '!', 'A'};
+
+static char vmac_string6[129] = {'p', 't', '*', '7', 'l',
+				 'i', '!', '#', 'w', '0',
+				 'z', '/', '4', 'A', 'n'};
+
 static struct hash_testvec aes_vmac128_tv_template[] = {
 	{
 		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
@@ -1776,6 +1789,24 @@ static struct hash_testvec aes_vmac128_tv_template[] = {
 		.digest = "\x8b\x32\x8f\xe1\xed\x8f\xfa\xd4",
 		.psize  = 128,
 		.ksize  = 16,
+	}, {
+		.key = "a09b5cd!f#07K\x00\x00\x00",
+		.plaintext = vmac_string4,
+		.digest = "\xab\xa5\x0f\xea\x42\x4e\xa1\x5f",
+		.psize = sizeof(vmac_string4),
+		.ksize = 16,
+	}, {
+		.key = "a09b5cd!f#07K\x00\x00\x00",
+		.plaintext = vmac_string5,
+		.digest = "\x25\x31\x98\xbc\x1d\xe8\x67\x60",
+		.psize = sizeof(vmac_string5),
+		.ksize = 16,
+	}, {
+		.key = "a09b5cd!f#07K\x00\x00\x00",
+		.plaintext = vmac_string6,
+		.digest = "\xc4\xae\x9b\x47\x95\x65\xeb\x41",
+		.psize = sizeof(vmac_string6),
+		.ksize = 16,
 	},
 };
 
diff --git a/crypto/vmac.c b/crypto/vmac.c
index f2338ca98368..2eb11a30c29c 100644
--- a/crypto/vmac.c
+++ b/crypto/vmac.c
@@ -375,6 +375,11 @@ static void vhash_update(const unsigned char *m,
 	u64 pkh = ctx->polykey[0];
 	u64 pkl = ctx->polykey[1];
 
+	if (!mbytes)
+		return;
+
+	BUG_ON(mbytes % VMAC_NHBYTES);
+
 	mptr = (u64 *)m;
 	i = mbytes / VMAC_NHBYTES;  /* Must be non-zero */
 
@@ -454,7 +459,7 @@ do_l3:
 }
 
 static u64 vmac(unsigned char m[], unsigned int mbytes,
-			unsigned char n[16], u64 *tagl,
+			const unsigned char n[16], u64 *tagl,
 			struct vmac_ctx_t *ctx)
 {
 	u64 *in_n, *out_p;
@@ -559,8 +564,33 @@ static int vmac_update(struct shash_desc *pdesc, const u8 *p,
 {
 	struct crypto_shash *parent = pdesc->tfm;
 	struct vmac_ctx_t *ctx = crypto_shash_ctx(parent);
+	int expand;
+	int min;
+
+	expand = VMAC_NHBYTES - ctx->partial_size > 0 ?
+			VMAC_NHBYTES - ctx->partial_size : 0;
+
+	min = len < expand ? len : expand;
+
+	memcpy(ctx->partial + ctx->partial_size, p, min);
+	ctx->partial_size += min;
+
+	if (len < expand)
+		return 0;
 
-	vhash_update(p, len, &ctx->__vmac_ctx);
+	vhash_update(ctx->partial, VMAC_NHBYTES, &ctx->__vmac_ctx);
+	ctx->partial_size = 0;
+
+	len -= expand;
+	p += expand;
+
+	if (len % VMAC_NHBYTES) {
+		memcpy(ctx->partial, p + len - (len % VMAC_NHBYTES),
+			len % VMAC_NHBYTES);
+		ctx->partial_size = len % VMAC_NHBYTES;
+	}
+
+	vhash_update(p, len - len % VMAC_NHBYTES, &ctx->__vmac_ctx);
 
 	return 0;
 }
@@ -572,10 +602,20 @@ static int vmac_final(struct shash_desc *pdesc, u8 *out)
 	vmac_t mac;
 	u8 nonce[16] = {};
 
-	mac = vmac(NULL, 0, nonce, NULL, ctx);
+	/* vmac() ends up accessing outside the array bounds that
+	 * we specify.  In appears to access up to the next 2-word
+	 * boundary.  We'll just be uber cautious and zero the
+	 * unwritten bytes in the buffer.
+	 */
+	if (ctx->partial_size) {
+		memset(ctx->partial + ctx->partial_size, 0,
+			VMAC_NHBYTES - ctx->partial_size);
+	}
+	mac = vmac(ctx->partial, ctx->partial_size, nonce, NULL, ctx);
 	memcpy(out, &mac, sizeof(vmac_t));
 	memset(&mac, 0, sizeof(vmac_t));
 	memset(&ctx->__vmac_ctx, 0, sizeof(struct vmac_ctx));
+	ctx->partial_size = 0;
 	return 0;
 }
 
@@ -673,4 +713,3 @@ module_exit(vmac_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("VMAC hash algorithm");
-
diff --git a/include/crypto/vmac.h b/include/crypto/vmac.h
index c4467c55df1e..6b700c7b2fe1 100644
--- a/include/crypto/vmac.h
+++ b/include/crypto/vmac.h
@@ -56,6 +56,8 @@ typedef u64 vmac_t;
 struct vmac_ctx_t {
 	struct crypto_cipher *child;
 	struct vmac_ctx __vmac_ctx;
+	u8 partial[VMAC_NHBYTES];	/* partial block */
+	int partial_size;		/* size of the partial block */
 };
 
 #endif /* __CRYPTO_VMAC_H */
-- 
cgit v1.2.3-55-g7522


From 68f39e74fbc3e58ad52d008072bddacc9eee1c7e Mon Sep 17 00:00:00 2001
From: Tony Lindgren
Date: Mon, 15 Oct 2012 12:09:43 -0700
Subject: ARM: OMAP: Split plat/mmc.h into local headers and platform_data

We need to remove this from plat for ARM common zImage
support.

Also remove includes not needed by the omap_hsmmc.c driver.

Cc: linux-mmc@vger.kernel.org
Acked-by: Chris Ball <cjb@laptop.org>
Acked-by: Venkatraman S <svenkatr@ti.com>
[tony@atomide.com: fold in removal of unused driver includes]
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap1/board-h2-mmc.c         |   5 +-
 arch/arm/mach-omap1/board-h3-mmc.c         |   3 +-
 arch/arm/mach-omap1/board-htcherald.c      |   2 +-
 arch/arm/mach-omap1/board-innovator.c      |   2 +-
 arch/arm/mach-omap1/board-nokia770.c       |   2 +-
 arch/arm/mach-omap1/board-sx1-mmc.c        |   3 +-
 arch/arm/mach-omap1/devices.c              |   2 +-
 arch/arm/mach-omap1/mmc.h                  |  18 +++
 arch/arm/mach-omap2/board-4430sdp.c        |   2 +-
 arch/arm/mach-omap2/board-n8x0.c           |   2 +-
 arch/arm/mach-omap2/board-omap4panda.c     |   2 +-
 arch/arm/mach-omap2/board-rm680.c          |   2 +-
 arch/arm/mach-omap2/hsmmc.c                |   2 +-
 arch/arm/mach-omap2/mmc.h                  |  23 ++++
 arch/arm/mach-omap2/msdi.c                 |   2 +-
 arch/arm/mach-omap2/omap4-common.c         |   2 +-
 arch/arm/mach-omap2/omap_hwmod_2420_data.c |   2 +-
 arch/arm/mach-omap2/omap_hwmod_2430_data.c |   2 +-
 arch/arm/mach-omap2/omap_hwmod_33xx_data.c |   2 +-
 arch/arm/mach-omap2/omap_hwmod_3xxx_data.c |   2 +-
 arch/arm/mach-omap2/omap_hwmod_44xx_data.c |   2 +-
 arch/arm/plat-omap/include/plat/mmc.h      | 188 -----------------------------
 drivers/mmc/host/omap.c                    |   3 +-
 drivers/mmc/host/omap_hsmmc.c              |   4 +-
 include/linux/platform_data/mmc-omap.h     | 147 ++++++++++++++++++++++
 25 files changed, 212 insertions(+), 214 deletions(-)
 create mode 100644 arch/arm/mach-omap1/mmc.h
 create mode 100644 arch/arm/mach-omap2/mmc.h
 delete mode 100644 arch/arm/plat-omap/include/plat/mmc.h
 create mode 100644 include/linux/platform_data/mmc-omap.h

(limited to 'include')

diff --git a/arch/arm/mach-omap1/board-h2-mmc.c b/arch/arm/mach-omap1/board-h2-mmc.c
index e1362ce48497..7119ef28e0ad 100644
--- a/arch/arm/mach-omap1/board-h2-mmc.c
+++ b/arch/arm/mach-omap1/board-h2-mmc.c
@@ -13,12 +13,11 @@
  */
 #include <linux/gpio.h>
 #include <linux/platform_device.h>
-
+#include <linux/platform_data/gpio-omap.h>
 #include <linux/i2c/tps65010.h>
 
-#include <plat/mmc.h>
-
 #include "board-h2.h"
+#include "mmc.h"
 
 #if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE)
 
diff --git a/arch/arm/mach-omap1/board-h3-mmc.c b/arch/arm/mach-omap1/board-h3-mmc.c
index c74daace8cd6..17d77914d769 100644
--- a/arch/arm/mach-omap1/board-h3-mmc.c
+++ b/arch/arm/mach-omap1/board-h3-mmc.c
@@ -16,9 +16,8 @@
 
 #include <linux/i2c/tps65010.h>
 
-#include <plat/mmc.h>
-
 #include "board-h3.h"
+#include "mmc.h"
 
 #if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE)
 
diff --git a/arch/arm/mach-omap1/board-htcherald.c b/arch/arm/mach-omap1/board-htcherald.c
index 87ab2086ef96..f23200ceb43d 100644
--- a/arch/arm/mach-omap1/board-htcherald.c
+++ b/arch/arm/mach-omap1/board-htcherald.c
@@ -43,7 +43,7 @@
 #include <asm/mach/arch.h>
 
 #include <mach/omap7xx.h>
-#include <plat/mmc.h>
+#include "mmc.h"
 
 #include <mach/irqs.h>
 #include <mach/usb.h>
diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index db5f7d2976e7..411cc5b14ce3 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -36,13 +36,13 @@
 #include <plat/fpga.h>
 #include <plat/tc.h>
 #include <linux/platform_data/keypad-omap.h>
-#include <plat/mmc.h>
 
 #include <mach/hardware.h>
 #include <mach/usb.h>
 
 #include "iomap.h"
 #include "common.h"
+#include "mmc.h"
 
 /* At OMAP1610 Innovator the Ethernet is directly connected to CS1 */
 #define INNOVATOR1610_ETHR_START	0x04000300
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index 7d5c06d6a52a..cb72f2474430 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -29,13 +29,13 @@
 #include <asm/mach/map.h>
 
 #include <mach/mux.h>
-#include <plat/mmc.h>
 #include <plat/clock.h>
 
 #include <mach/hardware.h>
 #include <mach/usb.h>
 
 #include "common.h"
+#include "mmc.h"
 
 #define ADS7846_PENDOWN_GPIO	15
 
diff --git a/arch/arm/mach-omap1/board-sx1-mmc.c b/arch/arm/mach-omap1/board-sx1-mmc.c
index 5932d56e17bf..4fcf19c78a08 100644
--- a/arch/arm/mach-omap1/board-sx1-mmc.c
+++ b/arch/arm/mach-omap1/board-sx1-mmc.c
@@ -16,9 +16,10 @@
 #include <linux/platform_device.h>
 
 #include <mach/hardware.h>
-#include <plat/mmc.h>
 #include <mach/board-sx1.h>
 
+#include "mmc.h"
+
 #if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE)
 
 static int mmc_set_power(struct device *dev, int slot, int power_on,
diff --git a/arch/arm/mach-omap1/devices.c b/arch/arm/mach-omap1/devices.c
index d3fec92c54cb..f85836ae6691 100644
--- a/arch/arm/mach-omap1/devices.c
+++ b/arch/arm/mach-omap1/devices.c
@@ -22,7 +22,6 @@
 #include <plat/tc.h>
 #include <mach/mux.h>
 #include <plat/dma.h>
-#include <plat/mmc.h>
 
 #include <mach/omap7xx.h>
 #include <mach/camera.h>
@@ -30,6 +29,7 @@
 
 #include "common.h"
 #include "clock.h"
+#include "mmc.h"
 
 #if defined(CONFIG_SND_SOC) || defined(CONFIG_SND_SOC_MODULE)
 
diff --git a/arch/arm/mach-omap1/mmc.h b/arch/arm/mach-omap1/mmc.h
new file mode 100644
index 000000000000..39c2b13de884
--- /dev/null
+++ b/arch/arm/mach-omap1/mmc.h
@@ -0,0 +1,18 @@
+#include <linux/mmc/host.h>
+#include <linux/platform_data/mmc-omap.h>
+
+#define OMAP15XX_NR_MMC		1
+#define OMAP16XX_NR_MMC		2
+#define OMAP1_MMC_SIZE		0x080
+#define OMAP1_MMC1_BASE		0xfffb7800
+#define OMAP1_MMC2_BASE		0xfffb7c00	/* omap16xx only */
+
+#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE)
+void omap1_init_mmc(struct omap_mmc_platform_data **mmc_data,
+				int nr_controllers);
+#else
+static inline void omap1_init_mmc(struct omap_mmc_platform_data **mmc_data,
+				int nr_controllers)
+{
+}
+#endif
diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c
index 3669c120c7e8..2ab267ec3b75 100644
--- a/arch/arm/mach-omap2/board-4430sdp.c
+++ b/arch/arm/mach-omap2/board-4430sdp.c
@@ -35,7 +35,6 @@
 
 #include "common.h"
 #include <plat/usb.h>
-#include <plat/mmc.h>
 #include "omap4-keypad.h"
 #include <video/omapdss.h>
 #include <video/omap-panel-nokia-dsi.h>
@@ -45,6 +44,7 @@
 
 #include "soc.h"
 #include "mux.h"
+#include "mmc.h"
 #include "hsmmc.h"
 #include "control.h"
 #include "common-board-devices.h"
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index d95f727ca39a..f865ace5cf85 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -29,7 +29,7 @@
 
 #include "common.h"
 #include <plat/menelaus.h>
-#include <plat/mmc.h>
+#include "mmc.h"
 
 #include "mux.h"
 
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index bfcd397e233c..e9ce9fb9ffac 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -40,10 +40,10 @@
 
 #include "common.h"
 #include <plat/usb.h>
-#include <plat/mmc.h>
 #include <video/omap-panel-tfp410.h>
 
 #include "soc.h"
+#include "mmc.h"
 #include "hsmmc.h"
 #include "control.h"
 #include "mux.h"
diff --git a/arch/arm/mach-omap2/board-rm680.c b/arch/arm/mach-omap2/board-rm680.c
index 45997bfbcbd2..f4b3c288e16b 100644
--- a/arch/arm/mach-omap2/board-rm680.c
+++ b/arch/arm/mach-omap2/board-rm680.c
@@ -23,13 +23,13 @@
 #include <asm/mach-types.h>
 
 #include <plat/i2c.h>
-#include <plat/mmc.h>
 #include <plat/usb.h>
 #include <plat/gpmc.h>
 #include "common.h"
 #include <plat/serial.h>
 
 #include "mux.h"
+#include "mmc.h"
 #include "hsmmc.h"
 #include "sdram-nokia.h"
 #include "common-board-devices.h"
diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index 4d3a6324155f..ec6c2230cb38 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -17,11 +17,11 @@
 #include <mach/hardware.h>
 #include <linux/platform_data/gpio-omap.h>
 
-#include <plat/mmc.h>
 #include <plat/omap-pm.h>
 #include <plat/omap_device.h>
 
 #include "mux.h"
+#include "mmc.h"
 #include "hsmmc.h"
 #include "control.h"
 
diff --git a/arch/arm/mach-omap2/mmc.h b/arch/arm/mach-omap2/mmc.h
new file mode 100644
index 000000000000..0cd4b089da9c
--- /dev/null
+++ b/arch/arm/mach-omap2/mmc.h
@@ -0,0 +1,23 @@
+#include <linux/mmc/host.h>
+#include <linux/platform_data/mmc-omap.h>
+
+#define OMAP24XX_NR_MMC		2
+#define OMAP2420_MMC_SIZE	OMAP1_MMC_SIZE
+#define OMAP2_MMC1_BASE		0x4809c000
+
+#define OMAP4_MMC_REG_OFFSET	0x100
+
+#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE)
+void omap242x_init_mmc(struct omap_mmc_platform_data **mmc_data);
+#else
+static inline void omap242x_init_mmc(struct omap_mmc_platform_data **mmc_data)
+{
+}
+#endif
+
+struct omap_hwmod;
+int omap_msdi_reset(struct omap_hwmod *oh);
+
+/* called from board-specific card detection service routine */
+extern void omap_mmc_notify_cover_event(struct device *dev, int slot,
+					int is_closed);
diff --git a/arch/arm/mach-omap2/msdi.c b/arch/arm/mach-omap2/msdi.c
index 9e57b4aadb06..a6020d750431 100644
--- a/arch/arm/mach-omap2/msdi.c
+++ b/arch/arm/mach-omap2/msdi.c
@@ -27,11 +27,11 @@
 
 #include <plat/omap_hwmod.h>
 #include <plat/omap_device.h>
-#include <plat/mmc.h>
 
 #include "common.h"
 #include "control.h"
 #include "mux.h"
+#include "mmc.h"
 
 /*
  * MSDI_CON_OFFSET: offset in bytes of the MSDI IP block's CON register
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index e1f289748c5d..de89d382f52c 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -27,12 +27,12 @@
 
 #include <plat/sram.h>
 #include <plat/omap-secure.h>
-#include <plat/mmc.h>
 
 #include "omap-wakeupgen.h"
 
 #include "soc.h"
 #include "common.h"
+#include "mmc.h"
 #include "hsmmc.h"
 #include "omap4-sar-layout.h"
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_2420_data.c b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
index b5db6007c523..82ad9a57661e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2420_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
@@ -21,12 +21,12 @@
 #include <plat/dmtimer.h>
 #include "l3_2xxx.h"
 #include "l4_2xxx.h"
-#include <plat/mmc.h>
 
 #include "omap_hwmod_common_data.h"
 
 #include "cm-regbits-24xx.h"
 #include "prm-regbits-24xx.h"
+#include "mmc.h"
 #include "wd_timer.h"
 
 /*
diff --git a/arch/arm/mach-omap2/omap_hwmod_2430_data.c b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
index c455e41b0237..5c833fb35d21 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2430_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
@@ -20,7 +20,7 @@
 #include <plat/serial.h>
 #include <plat/i2c.h>
 #include <plat/dmtimer.h>
-#include <plat/mmc.h>
+#include "mmc.h"
 #include "l3_2xxx.h"
 
 #include "soc.h"
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
index 59d5c1cd316d..d023a99cfd7a 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
@@ -19,7 +19,6 @@
 #include <linux/platform_data/gpio-omap.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 #include <plat/dma.h>
-#include <plat/mmc.h>
 #include <plat/i2c.h>
 
 #include "omap_hwmod_common_data.h"
@@ -28,6 +27,7 @@
 #include "cm33xx.h"
 #include "prm33xx.h"
 #include "prm-regbits-33xx.h"
+#include "mmc.h"
 
 /*
  * IP blocks
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index f67b7ee07dd4..509e8ba3fe75 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -23,7 +23,6 @@
 #include "l3_3xxx.h"
 #include "l4_3xxx.h"
 #include <plat/i2c.h>
-#include <plat/mmc.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 #include <plat/dmtimer.h>
@@ -35,6 +34,7 @@
 #include "omap_hwmod_common_data.h"
 #include "prm-regbits-34xx.h"
 #include "cm-regbits-34xx.h"
+#include "mmc.h"
 #include "wd_timer.h"
 
 /*
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 652d0285bd6d..f87d781c4ebb 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -27,7 +27,6 @@
 #include <plat/dma.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
-#include <plat/mmc.h>
 #include <plat/dmtimer.h>
 #include <plat/common.h>
 #include <plat/iommu.h>
@@ -37,6 +36,7 @@
 #include "cm2_44xx.h"
 #include "prm44xx.h"
 #include "prm-regbits-44xx.h"
+#include "mmc.h"
 #include "wd_timer.h"
 
 /* Base offset for all OMAP4 interrupts external to MPUSS */
diff --git a/arch/arm/plat-omap/include/plat/mmc.h b/arch/arm/plat-omap/include/plat/mmc.h
deleted file mode 100644
index 8b4e4f2da2f5..000000000000
--- a/arch/arm/plat-omap/include/plat/mmc.h
+++ /dev/null
@@ -1,188 +0,0 @@
-/*
- * MMC definitions for OMAP2
- *
- * Copyright (C) 2006 Nokia Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __OMAP2_MMC_H
-#define __OMAP2_MMC_H
-
-#include <linux/types.h>
-#include <linux/device.h>
-#include <linux/mmc/host.h>
-
-#include <plat/omap_hwmod.h>
-
-#define OMAP15XX_NR_MMC		1
-#define OMAP16XX_NR_MMC		2
-#define OMAP1_MMC_SIZE		0x080
-#define OMAP1_MMC1_BASE		0xfffb7800
-#define OMAP1_MMC2_BASE		0xfffb7c00	/* omap16xx only */
-
-#define OMAP24XX_NR_MMC		2
-#define OMAP2420_MMC_SIZE	OMAP1_MMC_SIZE
-#define OMAP2_MMC1_BASE		0x4809c000
-
-#define OMAP4_MMC_REG_OFFSET	0x100
-
-#define OMAP_MMC_MAX_SLOTS	2
-
-/*
- * struct omap_mmc_dev_attr.flags possibilities
- *
- * OMAP_HSMMC_SUPPORTS_DUAL_VOLT: Some HSMMC controller instances can
- *    operate with either 1.8Vdc or 3.0Vdc card voltages; this flag
- *    should be set if this is the case.  See for example Section 22.5.3
- *    "MMC/SD/SDIO1 Bus Voltage Selection" of the OMAP34xx Multimedia
- *    Device Silicon Revision 3.1.x Revision ZR (July 2011) (SWPU223R).
- *
- * OMAP_HSMMC_BROKEN_MULTIBLOCK_READ: Multiple-block read transfers
- *    don't work correctly on some MMC controller instances on some
- *    OMAP3 SoCs; this flag should be set if this is the case.  See
- *    for example Advisory 2.1.1.128 "MMC: Multiple Block Read
- *    Operation Issue" in _OMAP3530/3525/3515/3503 Silicon Errata_
- *    Revision F (October 2010) (SPRZ278F).
- */
-#define OMAP_HSMMC_SUPPORTS_DUAL_VOLT		BIT(0)
-#define OMAP_HSMMC_BROKEN_MULTIBLOCK_READ	BIT(1)
-
-struct omap_mmc_dev_attr {
-	u8 flags;
-};
-
-struct omap_mmc_platform_data {
-	/* back-link to device */
-	struct device *dev;
-
-	/* number of slots per controller */
-	unsigned nr_slots:2;
-
-	/* set if your board has components or wiring that limits the
-	 * maximum frequency on the MMC bus */
-	unsigned int max_freq;
-
-	/* switch the bus to a new slot */
-	int (*switch_slot)(struct device *dev, int slot);
-	/* initialize board-specific MMC functionality, can be NULL if
-	 * not supported */
-	int (*init)(struct device *dev);
-	void (*cleanup)(struct device *dev);
-	void (*shutdown)(struct device *dev);
-
-	/* To handle board related suspend/resume functionality for MMC */
-	int (*suspend)(struct device *dev, int slot);
-	int (*resume)(struct device *dev, int slot);
-
-	/* Return context loss count due to PM states changing */
-	int (*get_context_loss_count)(struct device *dev);
-
-	/* Integrating attributes from the omap_hwmod layer */
-	u8 controller_flags;
-
-	/* Register offset deviation */
-	u16 reg_offset;
-
-	struct omap_mmc_slot_data {
-
-		/*
-		 * 4/8 wires and any additional host capabilities
-		 * need to OR'd all capabilities (ref. linux/mmc/host.h)
-		 */
-		u8  wires;	/* Used for the MMC driver on omap1 and 2420 */
-		u32 caps;	/* Used for the MMC driver on 2430 and later */
-		u32 pm_caps;	/* PM capabilities of the mmc */
-
-		/*
-		 * nomux means "standard" muxing is wrong on this board, and
-		 * that board-specific code handled it before common init logic.
-		 */
-		unsigned nomux:1;
-
-		/* switch pin can be for card detect (default) or card cover */
-		unsigned cover:1;
-
-		/* use the internal clock */
-		unsigned internal_clock:1;
-
-		/* nonremovable e.g. eMMC */
-		unsigned nonremovable:1;
-
-		/* Try to sleep or power off when possible */
-		unsigned power_saving:1;
-
-		/* If using power_saving and the MMC power is not to go off */
-		unsigned no_off:1;
-
-		/* eMMC does not handle power off when not in sleep state */
-		unsigned no_regulator_off_init:1;
-
-		/* Regulator off remapped to sleep */
-		unsigned vcc_aux_disable_is_sleep:1;
-
-		/* we can put the features above into this variable */
-#define HSMMC_HAS_PBIAS		(1 << 0)
-#define HSMMC_HAS_UPDATED_RESET	(1 << 1)
-		unsigned features;
-
-		int switch_pin;			/* gpio (card detect) */
-		int gpio_wp;			/* gpio (write protect) */
-
-		int (*set_bus_mode)(struct device *dev, int slot, int bus_mode);
-		int (*set_power)(struct device *dev, int slot,
-				 int power_on, int vdd);
-		int (*get_ro)(struct device *dev, int slot);
-		void (*remux)(struct device *dev, int slot, int power_on);
-		/* Call back before enabling / disabling regulators */
-		void (*before_set_reg)(struct device *dev, int slot,
-				       int power_on, int vdd);
-		/* Call back after enabling / disabling regulators */
-		void (*after_set_reg)(struct device *dev, int slot,
-				      int power_on, int vdd);
-		/* if we have special card, init it using this callback */
-		void (*init_card)(struct mmc_card *card);
-
-		/* return MMC cover switch state, can be NULL if not supported.
-		 *
-		 * possible return values:
-		 *   0 - closed
-		 *   1 - open
-		 */
-		int (*get_cover_state)(struct device *dev, int slot);
-
-		const char *name;
-		u32 ocr_mask;
-
-		/* Card detection IRQs */
-		int card_detect_irq;
-		int (*card_detect)(struct device *dev, int slot);
-
-		unsigned int ban_openended:1;
-
-	} slots[OMAP_MMC_MAX_SLOTS];
-};
-
-/* called from board-specific card detection service routine */
-extern void omap_mmc_notify_cover_event(struct device *dev, int slot,
-					int is_closed);
-
-#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE)
-void omap1_init_mmc(struct omap_mmc_platform_data **mmc_data,
-				int nr_controllers);
-void omap242x_init_mmc(struct omap_mmc_platform_data **mmc_data);
-#else
-static inline void omap1_init_mmc(struct omap_mmc_platform_data **mmc_data,
-				int nr_controllers)
-{
-}
-static inline void omap242x_init_mmc(struct omap_mmc_platform_data **mmc_data)
-{
-}
-#endif
-
-extern int omap_msdi_reset(struct omap_hwmod *oh);
-
-#endif
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index 48ad361613ef..e7c61b9b044c 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -28,8 +28,9 @@
 #include <linux/clk.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
+#include <linux/platform_data/mmc-omap.h>
 
-#include <plat/mmc.h>
+#include <plat/cpu.h>
 #include <plat/dma.h>
 
 #define	OMAP_MMC_REG_CMD	0x00
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 54bfd0cc106b..9b24bd46aad3 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -38,9 +38,7 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/pm_runtime.h>
-#include <mach/hardware.h>
-#include <plat/mmc.h>
-#include <plat/cpu.h>
+#include <linux/platform_data/mmc-omap.h>
 
 /* OMAP HSMMC Host Controller Registers */
 #define OMAP_HSMMC_SYSSTATUS	0x0014
diff --git a/include/linux/platform_data/mmc-omap.h b/include/linux/platform_data/mmc-omap.h
new file mode 100644
index 000000000000..39a7abc5604c
--- /dev/null
+++ b/include/linux/platform_data/mmc-omap.h
@@ -0,0 +1,147 @@
+/*
+ * MMC definitions for OMAP2
+ *
+ * Copyright (C) 2006 Nokia Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define OMAP_MMC_MAX_SLOTS	2
+
+/*
+ * struct omap_mmc_dev_attr.flags possibilities
+ *
+ * OMAP_HSMMC_SUPPORTS_DUAL_VOLT: Some HSMMC controller instances can
+ *    operate with either 1.8Vdc or 3.0Vdc card voltages; this flag
+ *    should be set if this is the case.  See for example Section 22.5.3
+ *    "MMC/SD/SDIO1 Bus Voltage Selection" of the OMAP34xx Multimedia
+ *    Device Silicon Revision 3.1.x Revision ZR (July 2011) (SWPU223R).
+ *
+ * OMAP_HSMMC_BROKEN_MULTIBLOCK_READ: Multiple-block read transfers
+ *    don't work correctly on some MMC controller instances on some
+ *    OMAP3 SoCs; this flag should be set if this is the case.  See
+ *    for example Advisory 2.1.1.128 "MMC: Multiple Block Read
+ *    Operation Issue" in _OMAP3530/3525/3515/3503 Silicon Errata_
+ *    Revision F (October 2010) (SPRZ278F).
+ */
+#define OMAP_HSMMC_SUPPORTS_DUAL_VOLT		BIT(0)
+#define OMAP_HSMMC_BROKEN_MULTIBLOCK_READ	BIT(1)
+
+struct mmc_card;
+
+struct omap_mmc_dev_attr {
+	u8 flags;
+};
+
+struct omap_mmc_platform_data {
+	/* back-link to device */
+	struct device *dev;
+
+	/* number of slots per controller */
+	unsigned nr_slots:2;
+
+	/* set if your board has components or wiring that limits the
+	 * maximum frequency on the MMC bus */
+	unsigned int max_freq;
+
+	/* switch the bus to a new slot */
+	int (*switch_slot)(struct device *dev, int slot);
+	/* initialize board-specific MMC functionality, can be NULL if
+	 * not supported */
+	int (*init)(struct device *dev);
+	void (*cleanup)(struct device *dev);
+	void (*shutdown)(struct device *dev);
+
+	/* To handle board related suspend/resume functionality for MMC */
+	int (*suspend)(struct device *dev, int slot);
+	int (*resume)(struct device *dev, int slot);
+
+	/* Return context loss count due to PM states changing */
+	int (*get_context_loss_count)(struct device *dev);
+
+	/* Integrating attributes from the omap_hwmod layer */
+	u8 controller_flags;
+
+	/* Register offset deviation */
+	u16 reg_offset;
+
+	struct omap_mmc_slot_data {
+
+		/*
+		 * 4/8 wires and any additional host capabilities
+		 * need to OR'd all capabilities (ref. linux/mmc/host.h)
+		 */
+		u8  wires;	/* Used for the MMC driver on omap1 and 2420 */
+		u32 caps;	/* Used for the MMC driver on 2430 and later */
+		u32 pm_caps;	/* PM capabilities of the mmc */
+
+		/*
+		 * nomux means "standard" muxing is wrong on this board, and
+		 * that board-specific code handled it before common init logic.
+		 */
+		unsigned nomux:1;
+
+		/* switch pin can be for card detect (default) or card cover */
+		unsigned cover:1;
+
+		/* use the internal clock */
+		unsigned internal_clock:1;
+
+		/* nonremovable e.g. eMMC */
+		unsigned nonremovable:1;
+
+		/* Try to sleep or power off when possible */
+		unsigned power_saving:1;
+
+		/* If using power_saving and the MMC power is not to go off */
+		unsigned no_off:1;
+
+		/* eMMC does not handle power off when not in sleep state */
+		unsigned no_regulator_off_init:1;
+
+		/* Regulator off remapped to sleep */
+		unsigned vcc_aux_disable_is_sleep:1;
+
+		/* we can put the features above into this variable */
+#define HSMMC_HAS_PBIAS		(1 << 0)
+#define HSMMC_HAS_UPDATED_RESET	(1 << 1)
+		unsigned features;
+
+		int switch_pin;			/* gpio (card detect) */
+		int gpio_wp;			/* gpio (write protect) */
+
+		int (*set_bus_mode)(struct device *dev, int slot, int bus_mode);
+		int (*set_power)(struct device *dev, int slot,
+				 int power_on, int vdd);
+		int (*get_ro)(struct device *dev, int slot);
+		void (*remux)(struct device *dev, int slot, int power_on);
+		/* Call back before enabling / disabling regulators */
+		void (*before_set_reg)(struct device *dev, int slot,
+				       int power_on, int vdd);
+		/* Call back after enabling / disabling regulators */
+		void (*after_set_reg)(struct device *dev, int slot,
+				      int power_on, int vdd);
+		/* if we have special card, init it using this callback */
+		void (*init_card)(struct mmc_card *card);
+
+		/* return MMC cover switch state, can be NULL if not supported.
+		 *
+		 * possible return values:
+		 *   0 - closed
+		 *   1 - open
+		 */
+		int (*get_cover_state)(struct device *dev, int slot);
+
+		const char *name;
+		u32 ocr_mask;
+
+		/* Card detection IRQs */
+		int card_detect_irq;
+		int (*card_detect)(struct device *dev, int slot);
+
+		unsigned int ban_openended:1;
+
+	} slots[OMAP_MMC_MAX_SLOTS];
+};
-- 
cgit v1.2.3-55-g7522


From 53db20d123f7a1bf44e46b727775403672655fde Mon Sep 17 00:00:00 2001
From: Tony Lindgren
Date: Mon, 15 Oct 2012 12:10:33 -0700
Subject: mmc: omap: Remove cpu_is_omap usage from the driver

This is needed for the ARM common zImage support.

We can use the existing slot features to pass omap1
specific options to the driver. For omap2 we don't
want to pass anything new as that will be eventually
moved to use device tree based init.

Note that this patch depends on earlier patch that
moves plat/mmc.h into include/linux/platform_data.

Cc: linux-mmc@vger.kernel.org
Cc: Venkatraman S <svenkatr@ti.com>
Acked-by: Chris Ball <cjb@laptop.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap1/devices.c          |  7 +++++++
 drivers/mmc/host/omap.c                | 23 +++++++++++++++--------
 include/linux/platform_data/mmc-omap.h |  3 +++
 3 files changed, 25 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap1/devices.c b/arch/arm/mach-omap1/devices.c
index f85836ae6691..d807d949913d 100644
--- a/arch/arm/mach-omap1/devices.c
+++ b/arch/arm/mach-omap1/devices.c
@@ -175,6 +175,13 @@ static int __init omap_mmc_add(const char *name, int id, unsigned long base,
 	res[3].name = "tx";
 	res[3].flags = IORESOURCE_DMA;
 
+	if (cpu_is_omap7xx())
+		data->slots[0].features = MMC_OMAP7XX;
+	if (cpu_is_omap15xx())
+		data->slots[0].features = MMC_OMAP15XX;
+	if (cpu_is_omap16xx())
+		data->slots[0].features = MMC_OMAP16XX;
+
 	ret = platform_device_add_resources(pdev, res, ARRAY_SIZE(res));
 	if (ret == 0)
 		ret = platform_device_add_data(pdev, data, sizeof(*data));
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index e7c61b9b044c..9f0e26fffaea 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -30,7 +30,6 @@
 #include <linux/slab.h>
 #include <linux/platform_data/mmc-omap.h>
 
-#include <plat/cpu.h>
 #include <plat/dma.h>
 
 #define	OMAP_MMC_REG_CMD	0x00
@@ -73,6 +72,13 @@
 #define	OMAP_MMC_STAT_CARD_BUSY		(1 <<  2)
 #define	OMAP_MMC_STAT_END_OF_CMD	(1 <<  0)
 
+#define mmc_omap7xx()	(host->features & MMC_OMAP7XX)
+#define mmc_omap15xx()	(host->features & MMC_OMAP15XX)
+#define mmc_omap16xx()	(host->features & MMC_OMAP16XX)
+#define MMC_OMAP1_MASK	(MMC_OMAP7XX | MMC_OMAP15XX | MMC_OMAP16XX)
+#define mmc_omap1()	(host->features & MMC_OMAP1_MASK)
+#define mmc_omap2()	(!mmc_omap1())
+
 #define OMAP_MMC_REG(host, reg)		(OMAP_MMC_REG_##reg << (host)->reg_shift)
 #define OMAP_MMC_READ(host, reg)	__raw_readw((host)->virt_base + OMAP_MMC_REG(host, reg))
 #define OMAP_MMC_WRITE(host, reg, val)	__raw_writew((val), (host)->virt_base + OMAP_MMC_REG(host, reg))
@@ -148,6 +154,7 @@ struct mmc_omap_host {
 	u32			buffer_bytes_left;
 	u32			total_bytes_left;
 
+	unsigned		features;
 	unsigned		use_dma:1;
 	unsigned		brs_received:1, dma_done:1;
 	unsigned		dma_in_use:1;
@@ -989,7 +996,7 @@ mmc_omap_prepare_data(struct mmc_omap_host *host, struct mmc_request *req)
 		 * blocksize is at least that large. Blocksize is
 		 * usually 512 bytes; but not for some SD reads.
 		 */
-		burst = cpu_is_omap15xx() ? 32 : 64;
+		burst = mmc_omap15xx() ? 32 : 64;
 		if (burst > data->blksz)
 			burst = data->blksz;
 
@@ -1105,8 +1112,7 @@ static void mmc_omap_set_power(struct mmc_omap_slot *slot, int power_on,
 	if (slot->pdata->set_power != NULL)
 		slot->pdata->set_power(mmc_dev(slot->mmc), slot->id, power_on,
 					vdd);
-
-	if (cpu_is_omap24xx()) {
+	if (mmc_omap2()) {
 		u16 w;
 
 		if (power_on) {
@@ -1240,7 +1246,7 @@ static int __devinit mmc_omap_new_slot(struct mmc_omap_host *host, int id)
 	mmc->ops = &mmc_omap_ops;
 	mmc->f_min = 400000;
 
-	if (cpu_class_is_omap2())
+	if (mmc_omap2())
 		mmc->f_max = 48000000;
 	else
 		mmc->f_max = 24000000;
@@ -1360,6 +1366,7 @@ static int __devinit mmc_omap_probe(struct platform_device *pdev)
 	init_waitqueue_head(&host->slot_wq);
 
 	host->pdata = pdata;
+	host->features = host->pdata->slots[0].features;
 	host->dev = &pdev->dev;
 	platform_set_drvdata(pdev, host);
 
@@ -1392,7 +1399,7 @@ static int __devinit mmc_omap_probe(struct platform_device *pdev)
 	host->dma_tx_burst = -1;
 	host->dma_rx_burst = -1;
 
-	if (cpu_is_omap24xx())
+	if (mmc_omap2())
 		sig = host->id == 0 ? OMAP24XX_DMA_MMC1_TX : OMAP24XX_DMA_MMC2_TX;
 	else
 		sig = host->id == 0 ? OMAP_DMA_MMC_TX : OMAP_DMA_MMC2_TX;
@@ -1408,7 +1415,7 @@ static int __devinit mmc_omap_probe(struct platform_device *pdev)
 		dev_warn(host->dev, "unable to obtain TX DMA engine channel %u\n",
 			sig);
 #endif
-	if (cpu_is_omap24xx())
+	if (mmc_omap2())
 		sig = host->id == 0 ? OMAP24XX_DMA_MMC1_RX : OMAP24XX_DMA_MMC2_RX;
 	else
 		sig = host->id == 0 ? OMAP_DMA_MMC_RX : OMAP_DMA_MMC2_RX;
@@ -1436,7 +1443,7 @@ static int __devinit mmc_omap_probe(struct platform_device *pdev)
 	}
 
 	host->nr_slots = pdata->nr_slots;
-	host->reg_shift = (cpu_is_omap7xx() ? 1 : 2);
+	host->reg_shift = (mmc_omap7xx() ? 1 : 2);
 
 	host->mmc_omap_wq = alloc_workqueue("mmc_omap", 0, 0);
 	if (!host->mmc_omap_wq)
diff --git a/include/linux/platform_data/mmc-omap.h b/include/linux/platform_data/mmc-omap.h
index 39a7abc5604c..2bf6ea82ff94 100644
--- a/include/linux/platform_data/mmc-omap.h
+++ b/include/linux/platform_data/mmc-omap.h
@@ -107,6 +107,9 @@ struct omap_mmc_platform_data {
 		/* we can put the features above into this variable */
 #define HSMMC_HAS_PBIAS		(1 << 0)
 #define HSMMC_HAS_UPDATED_RESET	(1 << 1)
+#define MMC_OMAP7XX		(1 << 2)
+#define MMC_OMAP15XX		(1 << 3)
+#define MMC_OMAP16XX		(1 << 4)
 		unsigned features;
 
 		int switch_pin;			/* gpio (card detect) */
-- 
cgit v1.2.3-55-g7522


From 1b61810d196b84bfdc14c289126d98de765b7f97 Mon Sep 17 00:00:00 2001
From: Chad Reese
Date: Mon, 8 Oct 2012 17:38:32 -0700
Subject: RapidIO: Fix comment error.

The resource index for the mailboxes was incorrect.

Signed-off-by: Chad Reese <kreese@caviumnetworks.com>
Acked-by: Alexandre Bounine <alexandre.bounine@idt.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/rio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rio.h b/include/linux/rio.h
index a90ebadd9da0..abddba9db130 100644
--- a/include/linux/rio.h
+++ b/include/linux/rio.h
@@ -62,7 +62,7 @@
  *
  *	0	RapidIO inbound doorbells
  *	1	RapidIO inbound mailboxes
- *	1	RapidIO outbound mailboxes
+ *	2	RapidIO outbound mailboxes
  */
 #define RIO_DOORBELL_RESOURCE	0
 #define RIO_INB_MBOX_RESOURCE	1
-- 
cgit v1.2.3-55-g7522


From 7bd3b61853da6d2fc579e27c7a1ac1e9fc968d1a Mon Sep 17 00:00:00 2001
From: Tony Lindgren
Date: Mon, 15 Oct 2012 13:53:41 -0700
Subject: ARM: OMAP2: Move plat/menelaus.h to linux/mfd/menelaus.h

We can move menelaus.h to live with other mfd headers to
get it out of plat for ARM common zImage support.

Acked-by: Samuel Ortiz <sameo@linux.intel.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/board-h4.c             |  2 +-
 arch/arm/mach-omap2/board-n8x0.c           |  2 +-
 arch/arm/plat-omap/include/plat/menelaus.h | 49 ------------------------------
 drivers/mfd/menelaus.c                     |  2 +-
 include/linux/mfd/menelaus.h               | 47 ++++++++++++++++++++++++++++
 5 files changed, 50 insertions(+), 52 deletions(-)
 delete mode 100644 arch/arm/plat-omap/include/plat/menelaus.h
 create mode 100644 include/linux/mfd/menelaus.h

(limited to 'include')

diff --git a/arch/arm/mach-omap2/board-h4.c b/arch/arm/mach-omap2/board-h4.c
index 8d04bf851af4..3977a0276b4c 100644
--- a/arch/arm/mach-omap2/board-h4.c
+++ b/arch/arm/mach-omap2/board-h4.c
@@ -26,12 +26,12 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/input/matrix_keypad.h>
+#include <linux/mfd/menelaus.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <plat/menelaus.h>
 #include <plat/dma.h>
 #include <plat/gpmc.h>
 #include "debug-devices.h"
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index d95f727ca39a..e3e8325054b2 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -22,13 +22,13 @@
 #include <linux/usb/musb.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 #include <linux/platform_data/mtd-onenand-omap2.h>
+#include <linux/mfd/menelaus.h>
 #include <sound/tlv320aic3x.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach-types.h>
 
 #include "common.h"
-#include <plat/menelaus.h>
 #include <plat/mmc.h>
 
 #include "mux.h"
diff --git a/arch/arm/plat-omap/include/plat/menelaus.h b/arch/arm/plat-omap/include/plat/menelaus.h
deleted file mode 100644
index 4a970ec62dd1..000000000000
--- a/arch/arm/plat-omap/include/plat/menelaus.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * arch/arm/plat-omap/include/mach/menelaus.h
- *
- * Functions to access Menelaus power management chip
- */
-
-#ifndef __ASM_ARCH_MENELAUS_H
-#define __ASM_ARCH_MENELAUS_H
-
-struct device;
-
-struct menelaus_platform_data {
-	int (* late_init)(struct device *dev);
-};
-
-extern int menelaus_register_mmc_callback(void (*callback)(void *data, u8 card_mask),
-					  void *data);
-extern void menelaus_unregister_mmc_callback(void);
-extern int menelaus_set_mmc_opendrain(int slot, int enable);
-extern int menelaus_set_mmc_slot(int slot, int enable, int power, int cd_on);
-
-extern int menelaus_set_vmem(unsigned int mV);
-extern int menelaus_set_vio(unsigned int mV);
-extern int menelaus_set_vmmc(unsigned int mV);
-extern int menelaus_set_vaux(unsigned int mV);
-extern int menelaus_set_vdcdc(int dcdc, unsigned int mV);
-extern int menelaus_set_slot_sel(int enable);
-extern int menelaus_get_slot_pin_states(void);
-extern int menelaus_set_vcore_sw(unsigned int mV);
-extern int menelaus_set_vcore_hw(unsigned int roof_mV, unsigned int floor_mV);
-
-#define EN_VPLL_SLEEP	(1 << 7)
-#define EN_VMMC_SLEEP	(1 << 6)
-#define EN_VAUX_SLEEP	(1 << 5)
-#define EN_VIO_SLEEP	(1 << 4)
-#define EN_VMEM_SLEEP	(1 << 3)
-#define EN_DC3_SLEEP	(1 << 2)
-#define EN_DC2_SLEEP	(1 << 1)
-#define EN_VC_SLEEP	(1 << 0)
-
-extern int menelaus_set_regulator_sleep(int enable, u32 val);
-
-#if defined(CONFIG_ARCH_OMAP2) && defined(CONFIG_MENELAUS)
-#define omap_has_menelaus()	1
-#else
-#define omap_has_menelaus()	0
-#endif
-
-#endif
diff --git a/drivers/mfd/menelaus.c b/drivers/mfd/menelaus.c
index 55d589981412..998ce8cb3065 100644
--- a/drivers/mfd/menelaus.c
+++ b/drivers/mfd/menelaus.c
@@ -41,11 +41,11 @@
 #include <linux/rtc.h>
 #include <linux/bcd.h>
 #include <linux/slab.h>
+#include <linux/mfd/menelaus.h>
 
 #include <asm/mach/irq.h>
 
 #include <asm/gpio.h>
-#include <plat/menelaus.h>
 
 #define DRIVER_NAME			"menelaus"
 
diff --git a/include/linux/mfd/menelaus.h b/include/linux/mfd/menelaus.h
new file mode 100644
index 000000000000..f097e89134cb
--- /dev/null
+++ b/include/linux/mfd/menelaus.h
@@ -0,0 +1,47 @@
+/*
+ * Functions to access Menelaus power management chip
+ */
+
+#ifndef __ASM_ARCH_MENELAUS_H
+#define __ASM_ARCH_MENELAUS_H
+
+struct device;
+
+struct menelaus_platform_data {
+	int (* late_init)(struct device *dev);
+};
+
+extern int menelaus_register_mmc_callback(void (*callback)(void *data, u8 card_mask),
+					  void *data);
+extern void menelaus_unregister_mmc_callback(void);
+extern int menelaus_set_mmc_opendrain(int slot, int enable);
+extern int menelaus_set_mmc_slot(int slot, int enable, int power, int cd_on);
+
+extern int menelaus_set_vmem(unsigned int mV);
+extern int menelaus_set_vio(unsigned int mV);
+extern int menelaus_set_vmmc(unsigned int mV);
+extern int menelaus_set_vaux(unsigned int mV);
+extern int menelaus_set_vdcdc(int dcdc, unsigned int mV);
+extern int menelaus_set_slot_sel(int enable);
+extern int menelaus_get_slot_pin_states(void);
+extern int menelaus_set_vcore_sw(unsigned int mV);
+extern int menelaus_set_vcore_hw(unsigned int roof_mV, unsigned int floor_mV);
+
+#define EN_VPLL_SLEEP	(1 << 7)
+#define EN_VMMC_SLEEP	(1 << 6)
+#define EN_VAUX_SLEEP	(1 << 5)
+#define EN_VIO_SLEEP	(1 << 4)
+#define EN_VMEM_SLEEP	(1 << 3)
+#define EN_DC3_SLEEP	(1 << 2)
+#define EN_DC2_SLEEP	(1 << 1)
+#define EN_VC_SLEEP	(1 << 0)
+
+extern int menelaus_set_regulator_sleep(int enable, u32 val);
+
+#if defined(CONFIG_ARCH_OMAP2) && defined(CONFIG_MENELAUS)
+#define omap_has_menelaus()	1
+#else
+#define omap_has_menelaus()	0
+#endif
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 98aed08e16c5f18d0c31fc07127bc163ccd0d04c Mon Sep 17 00:00:00 2001
From: Jean Pihet
Date: Thu, 4 Oct 2012 18:47:11 +0200
Subject: ARM: OMAP: SmartReflex: pass device dependent data via platform data

Remove the device dependent code (ex. cpu_is_xxx()) and settings
from the driver code and instead pass them via the platform
data. This allows a clean separation of the driver code and the platform
code, as required by the move of the platform header files to
include/linux/platform_data.

Note about the smartreflex functional clocks: the smartreflex fclks
are derived from sys_clk and have the same name as the main_clk from
the hwmod entry, in order for the SmartReflex driver to request the
fclk (using clk_get(dev, "fck")).

Signed-off-by: Jean Pihet <j-pihet@ti.com>
Signed-off-by: Kevin Hilman <khilman@ti.com>
---
 arch/arm/mach-omap2/sr_device.c   | 13 ++++++++++
 drivers/power/avs/smartreflex.c   | 54 ++++++++++++---------------------------
 include/linux/power/smartreflex.h | 14 ++++++++--
 3 files changed, 42 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/sr_device.c b/arch/arm/mach-omap2/sr_device.c
index f8217a5a4a26..a04bc25a1d26 100644
--- a/arch/arm/mach-omap2/sr_device.c
+++ b/arch/arm/mach-omap2/sr_device.c
@@ -121,6 +121,19 @@ static int __init sr_dev_init(struct omap_hwmod *oh, void *user)
 	sr_data->senn_mod = 0x1;
 	sr_data->senp_mod = 0x1;
 
+	if (cpu_is_omap34xx() || cpu_is_omap44xx()) {
+		sr_data->err_weight = OMAP3430_SR_ERRWEIGHT;
+		sr_data->err_maxlimit = OMAP3430_SR_ERRMAXLIMIT;
+		sr_data->accum_data = OMAP3430_SR_ACCUMDATA;
+		if (!(strcmp(sr_data->name, "smartreflex_mpu"))) {
+			sr_data->senn_avgweight = OMAP3430_SR1_SENNAVGWEIGHT;
+			sr_data->senp_avgweight = OMAP3430_SR1_SENPAVGWEIGHT;
+		} else {
+			sr_data->senn_avgweight = OMAP3430_SR2_SENNAVGWEIGHT;
+			sr_data->senp_avgweight = OMAP3430_SR2_SENPAVGWEIGHT;
+		}
+	}
+
 	sr_data->voltdm = voltdm_lookup(sr_dev_attr->sensor_voltdm_name);
 	if (!sr_data->voltdm) {
 		pr_err("%s: Unable to get voltage domain pointer for VDD %s\n",
diff --git a/drivers/power/avs/smartreflex.c b/drivers/power/avs/smartreflex.c
index 24768a27e1d8..4c4519e59be4 100644
--- a/drivers/power/avs/smartreflex.c
+++ b/drivers/power/avs/smartreflex.c
@@ -130,24 +130,21 @@ static irqreturn_t sr_interrupt(int irq, void *data)
 
 static void sr_set_clk_length(struct omap_sr *sr)
 {
-	struct clk *sys_ck;
-	u32 sys_clk_speed;
+	struct clk *fck;
+	u32 fclk_speed;
 
-	if (cpu_is_omap34xx())
-		sys_ck = clk_get(NULL, "sys_ck");
-	else
-		sys_ck = clk_get(NULL, "sys_clkin_ck");
+	fck = clk_get(&sr->pdev->dev, "fck");
 
-	if (IS_ERR(sys_ck)) {
-		dev_err(&sr->pdev->dev, "%s: unable to get sys clk\n",
-			__func__);
+	if (IS_ERR(fck)) {
+		dev_err(&sr->pdev->dev, "%s: unable to get fck for device %s\n",
+				__func__, dev_name(&sr->pdev->dev));
 		return;
 	}
 
-	sys_clk_speed = clk_get_rate(sys_ck);
-	clk_put(sys_ck);
+	fclk_speed = clk_get_rate(fck);
+	clk_put(fck);
 
-	switch (sys_clk_speed) {
+	switch (fclk_speed) {
 	case 12000000:
 		sr->clk_length = SRCLKLENGTH_12MHZ_SYSCLK;
 		break;
@@ -164,34 +161,12 @@ static void sr_set_clk_length(struct omap_sr *sr)
 		sr->clk_length = SRCLKLENGTH_38MHZ_SYSCLK;
 		break;
 	default:
-		dev_err(&sr->pdev->dev, "%s: Invalid sysclk value: %d\n",
-			__func__, sys_clk_speed);
+		dev_err(&sr->pdev->dev, "%s: Invalid fclk rate: %d\n",
+			__func__, fclk_speed);
 		break;
 	}
 }
 
-static void sr_set_regfields(struct omap_sr *sr)
-{
-	/*
-	 * For time being these values are defined in smartreflex.h
-	 * and populated during init. May be they can be moved to board
-	 * file or pmic specific data structure. In that case these structure
-	 * fields will have to be populated using the pdata or pmic structure.
-	 */
-	if (cpu_is_omap34xx() || cpu_is_omap44xx()) {
-		sr->err_weight = OMAP3430_SR_ERRWEIGHT;
-		sr->err_maxlimit = OMAP3430_SR_ERRMAXLIMIT;
-		sr->accum_data = OMAP3430_SR_ACCUMDATA;
-		if (!(strcmp(sr->name, "smartreflex_mpu_iva"))) {
-			sr->senn_avgweight = OMAP3430_SR1_SENNAVGWEIGHT;
-			sr->senp_avgweight = OMAP3430_SR1_SENPAVGWEIGHT;
-		} else {
-			sr->senn_avgweight = OMAP3430_SR2_SENNAVGWEIGHT;
-			sr->senp_avgweight = OMAP3430_SR2_SENPAVGWEIGHT;
-		}
-	}
-}
-
 static void sr_start_vddautocomp(struct omap_sr *sr)
 {
 	if (!sr_class || !(sr_class->enable) || !(sr_class->configure)) {
@@ -924,8 +899,14 @@ static int __init omap_sr_probe(struct platform_device *pdev)
 	sr_info->nvalue_count = pdata->nvalue_count;
 	sr_info->senn_mod = pdata->senn_mod;
 	sr_info->senp_mod = pdata->senp_mod;
+	sr_info->err_weight = pdata->err_weight;
+	sr_info->err_maxlimit = pdata->err_maxlimit;
+	sr_info->accum_data = pdata->accum_data;
+	sr_info->senn_avgweight = pdata->senn_avgweight;
+	sr_info->senp_avgweight = pdata->senp_avgweight;
 	sr_info->autocomp_active = false;
 	sr_info->ip_type = pdata->ip_type;
+
 	sr_info->base = ioremap(mem->start, resource_size(mem));
 	if (!sr_info->base) {
 		dev_err(&pdev->dev, "%s: ioremap fail\n", __func__);
@@ -937,7 +918,6 @@ static int __init omap_sr_probe(struct platform_device *pdev)
 		sr_info->irq = irq->start;
 
 	sr_set_clk_length(sr_info);
-	sr_set_regfields(sr_info);
 
 	list_add(&sr_info->node, &sr_list);
 
diff --git a/include/linux/power/smartreflex.h b/include/linux/power/smartreflex.h
index 4a496ebc7d73..c0f44c2b006d 100644
--- a/include/linux/power/smartreflex.h
+++ b/include/linux/power/smartreflex.h
@@ -260,8 +260,13 @@ struct omap_sr_nvalue_table {
  *
  * @name:		instance name
  * @ip_type:		Smartreflex IP type.
- * @senp_mod:		SENPENABLE value for the sr
- * @senn_mod:		SENNENABLE value for sr
+ * @senp_mod:		SENPENABLE value of the sr CONFIG register
+ * @senn_mod:		SENNENABLE value for sr CONFIG register
+ * @err_weight		ERRWEIGHT value of the sr ERRCONFIG register
+ * @err_maxlimit	ERRMAXLIMIT value of the sr ERRCONFIG register
+ * @accum_data		ACCUMDATA value of the sr CONFIG register
+ * @senn_avgweight	SENNAVGWEIGHT value of the sr AVGWEIGHT register
+ * @senp_avgweight	SENPAVGWEIGHT value of the sr AVGWEIGHT register
  * @nvalue_count:	Number of distinct nvalues in the nvalue table
  * @enable_on_init:	whether this sr module needs to enabled at
  *			boot up or not.
@@ -274,6 +279,11 @@ struct omap_sr_data {
 	int				ip_type;
 	u32				senp_mod;
 	u32				senn_mod;
+	u32				err_weight;
+	u32				err_maxlimit;
+	u32				accum_data;
+	u32				senn_avgweight;
+	u32				senp_avgweight;
 	int				nvalue_count;
 	bool				enable_on_init;
 	struct omap_sr_nvalue_table	*nvalue_table;
-- 
cgit v1.2.3-55-g7522


From acd18af93ad3b99e6769b917fe5b549dc1bfc468 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Fri, 28 Sep 2012 12:42:28 +0300
Subject: OMAPDSS: add omapdss_version

Add new enum, omapdss_version, that is used to tell which DSS hardware
version the SoC has. This enum is initialized during platform init, and
passed in the platform data to omapdss driver.

Note that the versions are not "continuous", that is, you cannot check
if the version is less or greater than something, but you need to check
for exact version match. In other words, this is invalid:

/* test if DSS is 3630 or earlier */
if (ver <= OMAPDSS_VER_OMAP3630)
	...

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 arch/arm/mach-omap2/display.c | 38 ++++++++++++++++++++++++++++++++++++++
 include/video/omapdss.h       | 14 ++++++++++++++
 2 files changed, 52 insertions(+)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 1011995f150a..28f508724a56 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -284,6 +284,35 @@ err:
 	return ERR_PTR(r);
 }
 
+static enum omapdss_version __init omap_display_get_version(void)
+{
+	if (cpu_is_omap24xx())
+		return OMAPDSS_VER_OMAP24xx;
+	else if (cpu_is_omap3630())
+		return OMAPDSS_VER_OMAP3630;
+	else if (cpu_is_omap34xx()) {
+		if (soc_is_am35xx()) {
+			return OMAPDSS_VER_AM35xx;
+		} else {
+			if (omap_rev() < OMAP3430_REV_ES3_0)
+				return OMAPDSS_VER_OMAP34xx_ES1;
+			else
+				return OMAPDSS_VER_OMAP34xx_ES3;
+		}
+	} else if (omap_rev() == OMAP4430_REV_ES1_0)
+		return OMAPDSS_VER_OMAP4430_ES1;
+	else if (omap_rev() == OMAP4430_REV_ES2_0 ||
+			omap_rev() == OMAP4430_REV_ES2_1 ||
+			omap_rev() == OMAP4430_REV_ES2_2)
+		return OMAPDSS_VER_OMAP4430_ES2;
+	else if (cpu_is_omap44xx())
+		return OMAPDSS_VER_OMAP4;
+	else if (soc_is_omap54xx())
+		return OMAPDSS_VER_OMAP5;
+	else
+		return OMAPDSS_VER_UNKNOWN;
+}
+
 int __init omap_display_init(struct omap_dss_board_info *board_data)
 {
 	int r = 0;
@@ -291,9 +320,18 @@ int __init omap_display_init(struct omap_dss_board_info *board_data)
 	int i, oh_count;
 	const struct omap_dss_hwmod_data *curr_dss_hwmod;
 	struct platform_device *dss_pdev;
+	enum omapdss_version ver;
 
 	/* create omapdss device */
 
+	ver = omap_display_get_version();
+
+	if (ver == OMAPDSS_VER_UNKNOWN) {
+		pr_err("DSS not supported on this SoC\n");
+		return -ENODEV;
+	}
+
+	board_data->version = ver;
 	board_data->dsi_enable_pads = omap_dsi_enable_pads;
 	board_data->dsi_disable_pads = omap_dsi_disable_pads;
 	board_data->get_context_loss_count = omap_pm_get_dev_context_loss_count;
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index 3729173b7fbc..88c829466fc1 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -314,6 +314,19 @@ int dsi_vc_send_bta_sync(struct omap_dss_device *dssdev, int channel);
 int dsi_enable_video_output(struct omap_dss_device *dssdev, int channel);
 void dsi_disable_video_output(struct omap_dss_device *dssdev, int channel);
 
+enum omapdss_version {
+	OMAPDSS_VER_UNKNOWN = 0,
+	OMAPDSS_VER_OMAP24xx,
+	OMAPDSS_VER_OMAP34xx_ES1,	/* OMAP3430 ES1.0, 2.0 */
+	OMAPDSS_VER_OMAP34xx_ES3,	/* OMAP3430 ES3.0+ */
+	OMAPDSS_VER_OMAP3630,
+	OMAPDSS_VER_AM35xx,
+	OMAPDSS_VER_OMAP4430_ES1,	/* OMAP4430 ES1.0 */
+	OMAPDSS_VER_OMAP4430_ES2,	/* OMAP4430 ES2.0, 2.1, 2.2 */
+	OMAPDSS_VER_OMAP4,		/* All other OMAP4s */
+	OMAPDSS_VER_OMAP5,
+};
+
 /* Board specific data */
 struct omap_dss_board_info {
 	int (*get_context_loss_count)(struct device *dev);
@@ -323,6 +336,7 @@ struct omap_dss_board_info {
 	int (*dsi_enable_pads)(int dsi_id, unsigned lane_mask);
 	void (*dsi_disable_pads)(int dsi_id, unsigned lane_mask);
 	int (*set_min_bus_tput)(struct device *dev, unsigned long r);
+	enum omapdss_version version;
 };
 
 /* Init with the board info */
-- 
cgit v1.2.3-55-g7522


From d01a1e658606a0a69100f49c2ef09aacaf74d3e7 Mon Sep 17 00:00:00 2001
From: Michal Kazior
Date: Tue, 26 Jun 2012 14:37:16 +0200
Subject: mac80211: introduce channel context skeleton code

Channel context are the foundation for multi-channel
operation. They are are immutable and are re-created
(or re-used if other interfaces are bound to a certain
channel and a compatible channel type) on channel
switching.

This is an initial implementation and more features
will come in separate patches.

Signed-off-by: Michal Kazior <michal.kazior@tieto.com>
[some changes including RCU protection]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  36 +++++++++++
 net/mac80211/chan.c        | 147 +++++++++++++++++++++++++++++++++++++++++++++
 net/mac80211/ieee80211_i.h |  35 +++++++++++
 net/mac80211/main.c        |   3 +
 4 files changed, 221 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 82558c8decf8..ab1b5bafb568 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -143,6 +143,32 @@ struct ieee80211_low_level_stats {
 	unsigned int dot11RTSSuccessCount;
 };
 
+/**
+ * enum ieee80211_chanctx_change - change flag for channel context
+ * @IEEE80211_CHANCTX_CHANGE_CHANNEL_TYPE: The channel type was changed
+ */
+enum ieee80211_chanctx_change {
+	IEEE80211_CHANCTX_CHANGE_CHANNEL_TYPE	= BIT(0),
+};
+
+/**
+ * struct ieee80211_chanctx_conf - channel context that vifs may be tuned to
+ *
+ * This is the driver-visible part. The ieee80211_chanctx
+ * that contains it is visible in mac80211 only.
+ *
+ * @channel: the channel to tune to
+ * @channel_type: the channel (HT) type
+ * @drv_priv: data area for driver use, will always be aligned to
+ *	sizeof(void *), size is determined in hw information.
+ */
+struct ieee80211_chanctx_conf {
+	struct ieee80211_channel *channel;
+	enum nl80211_channel_type channel_type;
+
+	u8 drv_priv[0] __attribute__((__aligned__(sizeof(void *))));
+};
+
 /**
  * enum ieee80211_bss_change - BSS change notification flags
  *
@@ -931,6 +957,11 @@ enum ieee80211_vif_flags {
  *	at runtime, mac80211 will never touch this field
  * @hw_queue: hardware queue for each AC
  * @cab_queue: content-after-beacon (DTIM beacon really) queue, AP mode only
+ * @chanctx_conf: The channel context this interface is assigned to, or %NULL
+ *	when it is not assigned. This pointer is RCU-protected due to the TX
+ *	path needing to access it; even though the netdev carrier will always
+ *	be off when it is %NULL there can still be races and packets could be
+ *	processed after it switches back to %NULL.
  * @drv_priv: data area for driver use, will always be aligned to
  *	sizeof(void *).
  */
@@ -943,6 +974,8 @@ struct ieee80211_vif {
 	u8 cab_queue;
 	u8 hw_queue[IEEE80211_NUM_ACS];
 
+	struct ieee80211_chanctx_conf __rcu *chanctx_conf;
+
 	u32 driver_flags;
 
 	/* must be last */
@@ -1325,6 +1358,8 @@ enum ieee80211_hw_flags {
  *	within &struct ieee80211_vif.
  * @sta_data_size: size (in bytes) of the drv_priv data area
  *	within &struct ieee80211_sta.
+ * @chanctx_data_size: size (in bytes) of the drv_priv data area
+ *	within &struct ieee80211_chanctx_conf.
  *
  * @max_rates: maximum number of alternate rate retry stages the hw
  *	can handle.
@@ -1369,6 +1404,7 @@ struct ieee80211_hw {
 	int channel_change_time;
 	int vif_data_size;
 	int sta_data_size;
+	int chanctx_data_size;
 	int napi_weight;
 	u16 queues;
 	u16 max_listen_interval;
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 0bfc914ddd15..4ae94860a161 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -168,3 +168,150 @@ bool ieee80211_set_channel_type(struct ieee80211_local *local,
 	return true;
 
 }
+
+static struct ieee80211_chanctx *
+ieee80211_find_chanctx(struct ieee80211_local *local,
+		       struct ieee80211_channel *channel,
+		       enum nl80211_channel_type channel_type,
+		       enum ieee80211_chanctx_mode mode)
+{
+	struct ieee80211_chanctx *ctx;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	if (mode == IEEE80211_CHANCTX_EXCLUSIVE)
+		return NULL;
+	if (WARN_ON(!channel))
+		return NULL;
+
+	list_for_each_entry(ctx, &local->chanctx_list, list) {
+		if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE)
+			continue;
+		if (ctx->conf.channel != channel)
+			continue;
+		if (ctx->conf.channel_type != channel_type)
+			continue;
+
+		return ctx;
+	}
+
+	return NULL;
+}
+
+static struct ieee80211_chanctx *
+ieee80211_new_chanctx(struct ieee80211_local *local,
+		      struct ieee80211_channel *channel,
+		      enum nl80211_channel_type channel_type,
+		      enum ieee80211_chanctx_mode mode)
+{
+	struct ieee80211_chanctx *ctx;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	ctx = kzalloc(sizeof(*ctx) + local->hw.chanctx_data_size, GFP_KERNEL);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
+
+	ctx->conf.channel = channel;
+	ctx->conf.channel_type = channel_type;
+	ctx->mode = mode;
+
+	list_add(&ctx->list, &local->chanctx_list);
+
+	return ctx;
+}
+
+static void ieee80211_free_chanctx(struct ieee80211_local *local,
+				   struct ieee80211_chanctx *ctx)
+{
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	WARN_ON_ONCE(ctx->refcount != 0);
+
+	list_del(&ctx->list);
+	kfree_rcu(ctx, rcu_head);
+}
+
+static int ieee80211_assign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
+					struct ieee80211_chanctx *ctx)
+{
+	struct ieee80211_local *local __maybe_unused = sdata->local;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	rcu_assign_pointer(sdata->vif.chanctx_conf, &ctx->conf);
+	ctx->refcount++;
+
+	return 0;
+}
+
+static void ieee80211_unassign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
+					   struct ieee80211_chanctx *ctx)
+{
+	struct ieee80211_local *local __maybe_unused = sdata->local;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	ctx->refcount--;
+	rcu_assign_pointer(sdata->vif.chanctx_conf, NULL);
+}
+
+static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx_conf *conf;
+	struct ieee80211_chanctx *ctx;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
+	if (!conf)
+		return;
+
+	ctx = container_of(conf, struct ieee80211_chanctx, conf);
+
+	ieee80211_unassign_vif_chanctx(sdata, ctx);
+	if (ctx->refcount == 0)
+		ieee80211_free_chanctx(local, ctx);
+}
+
+int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
+			      struct ieee80211_channel *channel,
+			      enum nl80211_channel_type channel_type,
+			      enum ieee80211_chanctx_mode mode)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx *ctx;
+	int ret;
+
+	mutex_lock(&local->chanctx_mtx);
+	__ieee80211_vif_release_channel(sdata);
+
+	ctx = ieee80211_find_chanctx(local, channel, channel_type, mode);
+	if (!ctx)
+		ctx = ieee80211_new_chanctx(local, channel, channel_type, mode);
+	if (IS_ERR(ctx)) {
+		ret = PTR_ERR(ctx);
+		goto out;
+	}
+
+	ret = ieee80211_assign_vif_chanctx(sdata, ctx);
+	if (ret) {
+		/* if assign fails refcount stays the same */
+		if (ctx->refcount == 0)
+			ieee80211_free_chanctx(local, ctx);
+		goto out;
+	}
+
+ out:
+	mutex_unlock(&local->chanctx_mtx);
+	return ret;
+}
+
+void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
+{
+	mutex_lock(&sdata->local->chanctx_mtx);
+	__ieee80211_vif_release_channel(sdata);
+	mutex_unlock(&sdata->local->chanctx_mtx);
+}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 8c804550465b..9a058e58d53e 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -658,6 +658,30 @@ enum ieee80211_sdata_state_bits {
 	SDATA_STATE_OFFCHANNEL,
 };
 
+/**
+ * enum ieee80211_chanctx_mode - channel context configuration mode
+ *
+ * @IEEE80211_CHANCTX_SHARED: channel context may be used by
+ *	multiple interfaces
+ * @IEEE80211_CHANCTX_EXCLUSIVE: channel context can be used
+ *	only by a single interface. This can be used for example for
+ *	non-fixed channel IBSS.
+ */
+enum ieee80211_chanctx_mode {
+	IEEE80211_CHANCTX_SHARED,
+	IEEE80211_CHANCTX_EXCLUSIVE
+};
+
+struct ieee80211_chanctx {
+	struct list_head list;
+	struct rcu_head rcu_head;
+
+	enum ieee80211_chanctx_mode mode;
+	int refcount;
+
+	struct ieee80211_chanctx_conf conf;
+};
+
 struct ieee80211_sub_if_data {
 	struct list_head list;
 
@@ -987,6 +1011,10 @@ struct ieee80211_local {
 	struct ieee80211_channel *tmp_channel;
 	enum nl80211_channel_type tmp_channel_type;
 
+	/* channel contexts */
+	struct list_head chanctx_list;
+	struct mutex chanctx_mtx;
+
 	/* SNMP counters */
 	/* dot11CountersTable */
 	u32 dot11TransmittedFragmentCount;
@@ -1510,6 +1538,13 @@ bool ieee80211_set_channel_type(struct ieee80211_local *local,
 enum nl80211_channel_type
 ieee80211_ht_oper_to_channel_type(struct ieee80211_ht_operation *ht_oper);
 
+int __must_check
+ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
+			  struct ieee80211_channel *channel,
+			  enum nl80211_channel_type channel_type,
+			  enum ieee80211_chanctx_mode mode);
+void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata);
+
 #ifdef CONFIG_MAC80211_NOINLINE
 #define debug_noinline noinline
 #else
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index c80c4490351c..9be3ef1d2e86 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -626,6 +626,9 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	spin_lock_init(&local->filter_lock);
 	spin_lock_init(&local->queue_stop_reason_lock);
 
+	INIT_LIST_HEAD(&local->chanctx_list);
+	mutex_init(&local->chanctx_mtx);
+
 	/*
 	 * The rx_skb_queue is only accessed from tasklets,
 	 * but other SKB queues are used from within IRQ
-- 
cgit v1.2.3-55-g7522


From c3645eac479d9aaac9f8099c94bf681dc695dd34 Mon Sep 17 00:00:00 2001
From: Michal Kazior
Date: Tue, 26 Jun 2012 14:37:17 +0200
Subject: mac80211: introduce new ieee80211_ops

Introduce channel context driver methods. The channel
on a context channel is immutable, but the channel type
and other properties can change.

Signed-off-by: Michal Kazior <michal.kazior@tieto.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    |  24 +++++++++++
 net/mac80211/driver-ops.h |  65 ++++++++++++++++++++++++++++
 net/mac80211/trace.h      | 107 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 196 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index ab1b5bafb568..d9d2119f0828 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2353,6 +2353,16 @@ enum ieee80211_rate_control_changed {
  *	The callback will be called before each transmission and upon return
  *	mac80211 will transmit the frame right away.
  *	The callback is optional and can (should!) sleep.
+ *
+ * @add_chanctx: Notifies device driver about new channel context creation.
+ * @remove_chanctx: Notifies device driver about channel context destruction.
+ * @change_chanctx: Notifies device driver about channel context changes that
+ *	may happen when combining different virtual interfaces on the same
+ *	channel context with different settings
+ * @assign_vif_chanctx: Notifies device driver about channel context being bound
+ *	to vif. Possible use is for hw queue remapping.
+ * @unassign_vif_chanctx: Notifies device driver about channel context being
+ *	unbound from vif.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -2497,6 +2507,20 @@ struct ieee80211_ops {
 
 	void	(*mgd_prepare_tx)(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif);
+
+	int (*add_chanctx)(struct ieee80211_hw *hw,
+			   struct ieee80211_chanctx_conf *ctx);
+	void (*remove_chanctx)(struct ieee80211_hw *hw,
+			       struct ieee80211_chanctx_conf *ctx);
+	void (*change_chanctx)(struct ieee80211_hw *hw,
+			       struct ieee80211_chanctx_conf *ctx,
+			       u32 changed);
+	int (*assign_vif_chanctx)(struct ieee80211_hw *hw,
+				  struct ieee80211_vif *vif,
+				  struct ieee80211_chanctx_conf *ctx);
+	void (*unassign_vif_chanctx)(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif,
+				     struct ieee80211_chanctx_conf *ctx);
 };
 
 /**
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index da9003b20004..77407b31e1ff 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -871,4 +871,69 @@ static inline void drv_mgd_prepare_tx(struct ieee80211_local *local,
 		local->ops->mgd_prepare_tx(&local->hw, &sdata->vif);
 	trace_drv_return_void(local);
 }
+
+static inline int drv_add_chanctx(struct ieee80211_local *local,
+				  struct ieee80211_chanctx *ctx)
+{
+	int ret = -EOPNOTSUPP;
+
+	trace_drv_add_chanctx(local, ctx);
+	if (local->ops->add_chanctx)
+		ret = local->ops->add_chanctx(&local->hw, &ctx->conf);
+	trace_drv_return_int(local, ret);
+
+	return ret;
+}
+
+static inline void drv_remove_chanctx(struct ieee80211_local *local,
+				      struct ieee80211_chanctx *ctx)
+{
+	trace_drv_remove_chanctx(local, ctx);
+	if (local->ops->remove_chanctx)
+		local->ops->remove_chanctx(&local->hw, &ctx->conf);
+	trace_drv_return_void(local);
+}
+
+static inline void drv_change_chanctx(struct ieee80211_local *local,
+				      struct ieee80211_chanctx *ctx,
+				      u32 changed)
+{
+	trace_drv_change_chanctx(local, ctx, changed);
+	if (local->ops->change_chanctx)
+		local->ops->change_chanctx(&local->hw, &ctx->conf, changed);
+	trace_drv_return_void(local);
+}
+
+static inline int drv_assign_vif_chanctx(struct ieee80211_local *local,
+					 struct ieee80211_sub_if_data *sdata,
+					 struct ieee80211_chanctx *ctx)
+{
+	int ret = 0;
+
+	check_sdata_in_driver(sdata);
+
+	trace_drv_assign_vif_chanctx(local, sdata, ctx);
+	if (local->ops->assign_vif_chanctx)
+		ret = local->ops->assign_vif_chanctx(&local->hw,
+						     &sdata->vif,
+						     &ctx->conf);
+	trace_drv_return_int(local, ret);
+
+	return ret;
+}
+
+static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local,
+					    struct ieee80211_sub_if_data *sdata,
+					    struct ieee80211_chanctx *ctx)
+{
+	check_sdata_in_driver(sdata);
+
+	trace_drv_unassign_vif_chanctx(local, sdata, ctx);
+	if (local->ops->unassign_vif_chanctx)
+		local->ops->unassign_vif_chanctx(&local->hw,
+						 &sdata->vif,
+						 &ctx->conf);
+	trace_drv_return_void(local);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 18d9c8a52e9e..a3f5fe2a84a8 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -28,6 +28,15 @@
 #define VIF_PR_FMT	" vif:%s(%d%s)"
 #define VIF_PR_ARG	__get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : ""
 
+#define CHANCTX_ENTRY	__field(int, freq)					\
+			__field(int, chantype)
+#define CHANCTX_ASSIGN	__entry->freq = ctx->conf.channel->center_freq;		\
+			__entry->chantype = ctx->conf.channel_type
+#define CHANCTX_PR_FMT	" freq:%d MHz chantype:%d"
+#define CHANCTX_PR_ARG	__entry->freq, __entry->chantype
+
+
+
 /*
  * Tracing for driver callbacks.
  */
@@ -1256,6 +1265,104 @@ DEFINE_EVENT(local_sdata_evt, drv_mgd_prepare_tx,
 	TP_ARGS(local, sdata)
 );
 
+DECLARE_EVENT_CLASS(local_chanctx,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_chanctx *ctx),
+
+	TP_ARGS(local, ctx),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		CHANCTX_ENTRY
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		CHANCTX_ASSIGN;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT CHANCTX_PR_FMT,
+		LOCAL_PR_ARG, CHANCTX_PR_ARG
+	)
+);
+
+DEFINE_EVENT(local_chanctx, drv_add_chanctx,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_chanctx *ctx),
+	TP_ARGS(local, ctx)
+);
+
+DEFINE_EVENT(local_chanctx, drv_remove_chanctx,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_chanctx *ctx),
+	TP_ARGS(local, ctx)
+);
+
+TRACE_EVENT(drv_change_chanctx,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_chanctx *ctx,
+		 u32 changed),
+
+	TP_ARGS(local, ctx, changed),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		CHANCTX_ENTRY
+		__field(u32, changed)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		CHANCTX_ASSIGN;
+		__entry->changed = changed;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT CHANCTX_PR_FMT " changed:%#x",
+		LOCAL_PR_ARG, CHANCTX_PR_ARG, __entry->changed
+	)
+);
+
+DECLARE_EVENT_CLASS(local_sdata_chanctx,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_chanctx *ctx),
+
+	TP_ARGS(local, sdata, ctx),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		CHANCTX_ENTRY
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		CHANCTX_ASSIGN;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT CHANCTX_PR_FMT,
+		LOCAL_PR_ARG, VIF_PR_ARG, CHANCTX_PR_ARG
+	)
+);
+
+DEFINE_EVENT(local_sdata_chanctx, drv_assign_vif_chanctx,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_chanctx *ctx),
+	TP_ARGS(local, sdata, ctx)
+);
+
+DEFINE_EVENT(local_sdata_chanctx, drv_unassign_vif_chanctx,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_chanctx *ctx),
+	TP_ARGS(local, sdata, ctx)
+);
+
 /*
  * Tracing for API calls that drivers call.
  */
-- 
cgit v1.2.3-55-g7522


From 5edee61edeaaebafe584f8fb7074c1ef4658596b Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Tue, 16 Oct 2012 15:03:14 -0700
Subject: cgroup: cgroup_subsys->fork() should be called after the task is
 added to css_set

cgroup core has a bug which violates a basic rule about event
notifications - when a new entity needs to be added, you add that to
the notification list first and then make the new entity conform to
the current state.  If done in the reverse order, an event happening
inbetween will be lost.

cgroup_subsys->fork() is invoked way before the new task is added to
the css_set.  Currently, cgroup_freezer is the only user of ->fork()
and uses it to make new tasks conform to the current state of the
freezer.  If FROZEN state is requested while fork is in progress
between cgroup_fork_callbacks() and cgroup_post_fork(), the child
could escape freezing - the cgroup isn't frozen when ->fork() is
called and the freezer couldn't see the new task on the css_set.

This patch moves cgroup_subsys->fork() invocation to
cgroup_post_fork() after the new task is added to the css_set.
cgroup_fork_callbacks() is removed.

Because now a task may be migrated during cgroup_subsys->fork(),
freezer_fork() is updated so that it adheres to the usual RCU locking
and the rather pointless comment on why locking can be different there
is removed (if it doesn't make anything simpler, why even bother?).

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: stable@vger.kernel.org
---
 include/linux/cgroup.h  |  1 -
 kernel/cgroup.c         | 62 ++++++++++++++++++++++++-------------------------
 kernel/cgroup_freezer.c | 13 ++++-------
 kernel/fork.c           |  9 +------
 4 files changed, 35 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f8a030ced0c7..4cd1d0fd2542 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -34,7 +34,6 @@ extern int cgroup_lock_is_held(void);
 extern bool cgroup_lock_live_group(struct cgroup *cgrp);
 extern void cgroup_unlock(void);
 extern void cgroup_fork(struct task_struct *p);
-extern void cgroup_fork_callbacks(struct task_struct *p);
 extern void cgroup_post_fork(struct task_struct *p);
 extern void cgroup_exit(struct task_struct *p, int run_callbacks);
 extern int cgroupstats_build(struct cgroupstats *stats,
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 13774b3b39aa..b7a0171067ea 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4843,45 +4843,20 @@ void cgroup_fork(struct task_struct *child)
 	INIT_LIST_HEAD(&child->cg_list);
 }
 
-/**
- * cgroup_fork_callbacks - run fork callbacks
- * @child: the new task
- *
- * Called on a new task very soon before adding it to the
- * tasklist. No need to take any locks since no-one can
- * be operating on this task.
- */
-void cgroup_fork_callbacks(struct task_struct *child)
-{
-	if (need_forkexit_callback) {
-		int i;
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-			struct cgroup_subsys *ss = subsys[i];
-
-			/*
-			 * forkexit callbacks are only supported for
-			 * builtin subsystems.
-			 */
-			if (!ss || ss->module)
-				continue;
-
-			if (ss->fork)
-				ss->fork(child);
-		}
-	}
-}
-
 /**
  * cgroup_post_fork - called on a new task after adding it to the task list
  * @child: the task in question
  *
- * Adds the task to the list running through its css_set if necessary.
- * Has to be after the task is visible on the task list in case we race
- * with the first call to cgroup_iter_start() - to guarantee that the
- * new task ends up on its list.
+ * Adds the task to the list running through its css_set if necessary and
+ * call the subsystem fork() callbacks.  Has to be after the task is
+ * visible on the task list in case we race with the first call to
+ * cgroup_iter_start() - to guarantee that the new task ends up on its
+ * list.
  */
 void cgroup_post_fork(struct task_struct *child)
 {
+	int i;
+
 	/*
 	 * use_task_css_set_links is set to 1 before we walk the tasklist
 	 * under the tasklist_lock and we read it here after we added the child
@@ -4910,7 +4885,30 @@ void cgroup_post_fork(struct task_struct *child)
 		}
 		write_unlock(&css_set_lock);
 	}
+
+	/*
+	 * Call ss->fork().  This must happen after @child is linked on
+	 * css_set; otherwise, @child might change state between ->fork()
+	 * and addition to css_set.
+	 */
+	if (need_forkexit_callback) {
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+
+			/*
+			 * fork/exit callbacks are supported only for
+			 * builtin subsystems and we don't need further
+			 * synchronization as they never go away.
+			 */
+			if (!ss || ss->module)
+				continue;
+
+			if (ss->fork)
+				ss->fork(child);
+		}
+	}
 }
+
 /**
  * cgroup_exit - detach cgroup from exiting task
  * @tsk: pointer to task_struct of exiting process
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index b1724ce98981..12bfedb598c2 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -186,23 +186,15 @@ static void freezer_fork(struct task_struct *task)
 {
 	struct freezer *freezer;
 
-	/*
-	 * No lock is needed, since the task isn't on tasklist yet,
-	 * so it can't be moved to another cgroup, which means the
-	 * freezer won't be removed and will be valid during this
-	 * function call.  Nevertheless, apply RCU read-side critical
-	 * section to suppress RCU lockdep false positives.
-	 */
 	rcu_read_lock();
 	freezer = task_freezer(task);
-	rcu_read_unlock();
 
 	/*
 	 * The root cgroup is non-freezable, so we can skip the
 	 * following check.
 	 */
 	if (!freezer->css.cgroup->parent)
-		return;
+		goto out;
 
 	spin_lock_irq(&freezer->lock);
 	BUG_ON(freezer->state == CGROUP_FROZEN);
@@ -210,7 +202,10 @@ static void freezer_fork(struct task_struct *task)
 	/* Locking avoids race with FREEZING -> THAWED transitions. */
 	if (freezer->state == CGROUP_FREEZING)
 		freeze_task(task);
+
 	spin_unlock_irq(&freezer->lock);
+out:
+	rcu_read_unlock();
 }
 
 /*
diff --git a/kernel/fork.c b/kernel/fork.c
index 8b20ab7d3aa2..acc4cb62f32f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1135,7 +1135,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 {
 	int retval;
 	struct task_struct *p;
-	int cgroup_callbacks_done = 0;
 
 	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
 		return ERR_PTR(-EINVAL);
@@ -1393,12 +1392,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
-	/* Now that the task is set up, run cgroup callbacks if
-	 * necessary. We need to run them before the task is visible
-	 * on the tasklist. */
-	cgroup_fork_callbacks(p);
-	cgroup_callbacks_done = 1;
-
 	/* Need tasklist lock for parent etc handling! */
 	write_lock_irq(&tasklist_lock);
 
@@ -1503,7 +1496,7 @@ bad_fork_cleanup_cgroup:
 #endif
 	if (clone_flags & CLONE_THREAD)
 		threadgroup_change_end(current);
-	cgroup_exit(p, cgroup_callbacks_done);
+	cgroup_exit(p, 0);
 	delayacct_tsk_free(p);
 	module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
-- 
cgit v1.2.3-55-g7522


From dd67d32dbc5de299d70cc9e10c6c1e29ffa56b92 Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Tue, 16 Oct 2012 15:03:14 -0700
Subject: freezer: add missing mb's to freezer_count() and
 freezer_should_skip()

A task is considered frozen enough between freezer_do_not_count() and
freezer_count() and freezers use freezer_should_skip() to test this
condition.  This supposedly works because freezer_count() always calls
try_to_freezer() after clearing %PF_FREEZER_SKIP.

However, there currently is nothing which guarantees that
freezer_count() sees %true freezing() after clearing %PF_FREEZER_SKIP
when freezing is in progress, and vice-versa.  A task can escape the
freezing condition in effect by freezer_count() seeing !freezing() and
freezer_should_skip() seeing %PF_FREEZER_SKIP.

This patch adds smp_mb()'s to freezer_count() and
freezer_should_skip() such that either %true freezing() is visible to
freezer_count() or !PF_FREEZER_SKIP is visible to
freezer_should_skip().

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: stable@vger.kernel.org
---
 include/linux/freezer.h | 50 +++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 42 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index d09af4b67cf1..ee899329e65a 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -75,28 +75,62 @@ static inline bool cgroup_freezing(struct task_struct *task)
  */
 
 
-/* Tell the freezer not to count the current task as freezable. */
+/**
+ * freezer_do_not_count - tell freezer to ignore %current
+ *
+ * Tell freezers to ignore the current task when determining whether the
+ * target frozen state is reached.  IOW, the current task will be
+ * considered frozen enough by freezers.
+ *
+ * The caller shouldn't do anything which isn't allowed for a frozen task
+ * until freezer_cont() is called.  Usually, freezer[_do_not]_count() pair
+ * wrap a scheduling operation and nothing much else.
+ */
 static inline void freezer_do_not_count(void)
 {
 	current->flags |= PF_FREEZER_SKIP;
 }
 
-/*
- * Tell the freezer to count the current task as freezable again and try to
- * freeze it.
+/**
+ * freezer_count - tell freezer to stop ignoring %current
+ *
+ * Undo freezer_do_not_count().  It tells freezers that %current should be
+ * considered again and tries to freeze if freezing condition is already in
+ * effect.
  */
 static inline void freezer_count(void)
 {
 	current->flags &= ~PF_FREEZER_SKIP;
+	/*
+	 * If freezing is in progress, the following paired with smp_mb()
+	 * in freezer_should_skip() ensures that either we see %true
+	 * freezing() or freezer_should_skip() sees !PF_FREEZER_SKIP.
+	 */
+	smp_mb();
 	try_to_freeze();
 }
 
-/*
- * Check if the task should be counted as freezable by the freezer
+/**
+ * freezer_should_skip - whether to skip a task when determining frozen
+ *			 state is reached
+ * @p: task in quesion
+ *
+ * This function is used by freezers after establishing %true freezing() to
+ * test whether a task should be skipped when determining the target frozen
+ * state is reached.  IOW, if this function returns %true, @p is considered
+ * frozen enough.
  */
-static inline int freezer_should_skip(struct task_struct *p)
+static inline bool freezer_should_skip(struct task_struct *p)
 {
-	return !!(p->flags & PF_FREEZER_SKIP);
+	/*
+	 * The following smp_mb() paired with the one in freezer_count()
+	 * ensures that either freezer_count() sees %true freezing() or we
+	 * see cleared %PF_FREEZER_SKIP and return %false.  This makes it
+	 * impossible for a task to slip frozen state testing after
+	 * clearing %PF_FREEZER_SKIP.
+	 */
+	smp_mb();
+	return p->flags & PF_FREEZER_SKIP;
 }
 
 /*
-- 
cgit v1.2.3-55-g7522


From 0384e90b853357d24935c65ba0e1bdd27faa6e58 Mon Sep 17 00:00:00 2001
From: Daniel Mack
Date: Sun, 7 Oct 2012 18:19:44 +0200
Subject: spi/mcspi: allow configuration of pin directions

Allow D0 to be an input and D1 to be an output, configurable via
platform data and a new DT property.

Based on a patch from  Matus Ujhelyi <matus.ujhelyi@streamunlimited.com>

Signed-off-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 Documentation/devicetree/bindings/spi/omap-spi.txt |  4 +++-
 drivers/spi/spi-omap2-mcspi.c                      | 25 ++++++++++++++++------
 include/linux/platform_data/spi-omap2-mcspi.h      |  4 ++++
 3 files changed, 25 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/spi/omap-spi.txt b/Documentation/devicetree/bindings/spi/omap-spi.txt
index 81df374adbb9..2ef0a6b85653 100644
--- a/Documentation/devicetree/bindings/spi/omap-spi.txt
+++ b/Documentation/devicetree/bindings/spi/omap-spi.txt
@@ -6,7 +6,9 @@ Required properties:
   - "ti,omap4-spi" for OMAP4+.
 - ti,spi-num-cs : Number of chipselect supported  by the instance.
 - ti,hwmods: Name of the hwmod associated to the McSPI
-
+- ti,pindir-d0-in-d1-out: Select the D0 pin as input and D1 as
+			  output. The default is D0 as output and
+			  D1 as input.
 
 Example:
 
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 3542fdc664b1..51046332677c 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -130,6 +130,7 @@ struct omap2_mcspi {
 	struct omap2_mcspi_dma	*dma_channels;
 	struct device		*dev;
 	struct omap2_mcspi_regs ctx;
+	unsigned int		pin_dir:1;
 };
 
 struct omap2_mcspi_cs {
@@ -765,8 +766,15 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi,
 	/* standard 4-wire master mode:  SCK, MOSI/out, MISO/in, nCS
 	 * REVISIT: this controller could support SPI_3WIRE mode.
 	 */
-	l &= ~(OMAP2_MCSPI_CHCONF_IS|OMAP2_MCSPI_CHCONF_DPE1);
-	l |= OMAP2_MCSPI_CHCONF_DPE0;
+	if (mcspi->pin_dir == MCSPI_PINDIR_D0_OUT_D1_IN) {
+		l &= ~OMAP2_MCSPI_CHCONF_IS;
+		l &= ~OMAP2_MCSPI_CHCONF_DPE1;
+		l |= OMAP2_MCSPI_CHCONF_DPE0;
+	} else {
+		l |= OMAP2_MCSPI_CHCONF_IS;
+		l |= OMAP2_MCSPI_CHCONF_DPE1;
+		l &= ~OMAP2_MCSPI_CHCONF_DPE0;
+	}
 
 	/* wordlength */
 	l &= ~OMAP2_MCSPI_CHCONF_WL_MASK;
@@ -1167,6 +1175,11 @@ static int __devinit omap2_mcspi_probe(struct platform_device *pdev)
 	master->cleanup = omap2_mcspi_cleanup;
 	master->dev.of_node = node;
 
+	dev_set_drvdata(&pdev->dev, master);
+
+	mcspi = spi_master_get_devdata(master);
+	mcspi->master = master;
+
 	match = of_match_device(omap_mcspi_of_match, &pdev->dev);
 	if (match) {
 		u32 num_cs = 1; /* default number of chipselect */
@@ -1175,19 +1188,17 @@ static int __devinit omap2_mcspi_probe(struct platform_device *pdev)
 		of_property_read_u32(node, "ti,spi-num-cs", &num_cs);
 		master->num_chipselect = num_cs;
 		master->bus_num = bus_num++;
+		if (of_get_property(node, "ti,pindir-d0-in-d1-out", NULL))
+			mcspi->pin_dir = MCSPI_PINDIR_D0_IN_D1_OUT;
 	} else {
 		pdata = pdev->dev.platform_data;
 		master->num_chipselect = pdata->num_cs;
 		if (pdev->id != -1)
 			master->bus_num = pdev->id;
+		mcspi->pin_dir = pdata->pin_dir;
 	}
 	regs_offset = pdata->regs_offset;
 
-	dev_set_drvdata(&pdev->dev, master);
-
-	mcspi = spi_master_get_devdata(master);
-	mcspi->master = master;
-
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (r == NULL) {
 		status = -ENODEV;
diff --git a/include/linux/platform_data/spi-omap2-mcspi.h b/include/linux/platform_data/spi-omap2-mcspi.h
index a357eb26bd25..ce70f7b5a8e1 100644
--- a/include/linux/platform_data/spi-omap2-mcspi.h
+++ b/include/linux/platform_data/spi-omap2-mcspi.h
@@ -7,9 +7,13 @@
 
 #define OMAP4_MCSPI_REG_OFFSET 0x100
 
+#define MCSPI_PINDIR_D0_OUT_D1_IN	0
+#define MCSPI_PINDIR_D0_IN_D1_OUT	1
+
 struct omap2_mcspi_platform_config {
 	unsigned short	num_cs;
 	unsigned int regs_offset;
+	unsigned int pin_dir:1;
 };
 
 struct omap2_mcspi_dev_attr {
-- 
cgit v1.2.3-55-g7522


From 0d4529c534c1c664f25088eb5f5b4d7ce0ee2510 Mon Sep 17 00:00:00 2001
From: Davide Ciminaghi
Date: Tue, 16 Oct 2012 15:56:59 +0200
Subject: regmap: make lock/unlock functions customizable

It is sometimes convenient for a regmap user to override the standard
regmap lock/unlock functions with custom functions.
For instance this can be useful in case an already existing spinlock
or mutex has to be used for locking a set of registers instead of the
internal regmap spinlock/mutex.
Note that the fast_io field of struct regmap_bus is ignored in case
custom locking functions are used.

Signed-off-by: Davide Ciminaghi <ciminaghi@gnudd.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/base/regmap/internal.h |  4 +--
 drivers/base/regmap/regmap.c   | 65 ++++++++++++++++++++++++------------------
 include/linux/regmap.h         | 16 ++++++++++-
 3 files changed, 54 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 80f9ab9c3aa4..b1ee824e2a5f 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -31,14 +31,12 @@ struct regmap_format {
 	unsigned int (*parse_val)(void *buf);
 };
 
-typedef void (*regmap_lock)(struct regmap *map);
-typedef void (*regmap_unlock)(struct regmap *map);
-
 struct regmap {
 	struct mutex mutex;
 	spinlock_t spinlock;
 	regmap_lock lock;
 	regmap_unlock unlock;
+	void *lock_arg; /* This is passed to lock/unlock functions */
 
 	struct device *dev; /* Device we do I/O on */
 	void *work_buf;     /* Scratch buffer used to format I/O */
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 52069d29ff12..5d8b75255b50 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -214,23 +214,27 @@ static unsigned int regmap_parse_32_native(void *buf)
 	return *(u32 *)buf;
 }
 
-static void regmap_lock_mutex(struct regmap *map)
+static void regmap_lock_mutex(void *__map)
 {
+	struct regmap *map = __map;
 	mutex_lock(&map->mutex);
 }
 
-static void regmap_unlock_mutex(struct regmap *map)
+static void regmap_unlock_mutex(void *__map)
 {
+	struct regmap *map = __map;
 	mutex_unlock(&map->mutex);
 }
 
-static void regmap_lock_spinlock(struct regmap *map)
+static void regmap_lock_spinlock(void *__map)
 {
+	struct regmap *map = __map;
 	spin_lock(&map->spinlock);
 }
 
-static void regmap_unlock_spinlock(struct regmap *map)
+static void regmap_unlock_spinlock(void *__map)
 {
+	struct regmap *map = __map;
 	spin_unlock(&map->spinlock);
 }
 
@@ -335,14 +339,21 @@ struct regmap *regmap_init(struct device *dev,
 		goto err;
 	}
 
-	if (bus->fast_io) {
-		spin_lock_init(&map->spinlock);
-		map->lock = regmap_lock_spinlock;
-		map->unlock = regmap_unlock_spinlock;
+	if (config->lock && config->unlock) {
+		map->lock = config->lock;
+		map->unlock = config->unlock;
+		map->lock_arg = config->lock_arg;
 	} else {
-		mutex_init(&map->mutex);
-		map->lock = regmap_lock_mutex;
-		map->unlock = regmap_unlock_mutex;
+		if (bus->fast_io) {
+			spin_lock_init(&map->spinlock);
+			map->lock = regmap_lock_spinlock;
+			map->unlock = regmap_unlock_spinlock;
+		} else {
+			mutex_init(&map->mutex);
+			map->lock = regmap_lock_mutex;
+			map->unlock = regmap_unlock_mutex;
+		}
+		map->lock_arg = map;
 	}
 	map->format.reg_bytes = DIV_ROUND_UP(config->reg_bits, 8);
 	map->format.pad_bytes = config->pad_bits / 8;
@@ -939,11 +950,11 @@ int regmap_write(struct regmap *map, unsigned int reg, unsigned int val)
 	if (reg % map->reg_stride)
 		return -EINVAL;
 
-	map->lock(map);
+	map->lock(map->lock_arg);
 
 	ret = _regmap_write(map, reg, val);
 
-	map->unlock(map);
+	map->unlock(map->lock_arg);
 
 	return ret;
 }
@@ -975,11 +986,11 @@ int regmap_raw_write(struct regmap *map, unsigned int reg,
 	if (reg % map->reg_stride)
 		return -EINVAL;
 
-	map->lock(map);
+	map->lock(map->lock_arg);
 
 	ret = _regmap_raw_write(map, reg, val, val_len);
 
-	map->unlock(map);
+	map->unlock(map->lock_arg);
 
 	return ret;
 }
@@ -1011,7 +1022,7 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 	if (reg % map->reg_stride)
 		return -EINVAL;
 
-	map->lock(map);
+	map->lock(map->lock_arg);
 
 	/* No formatting is require if val_byte is 1 */
 	if (val_bytes == 1) {
@@ -1047,7 +1058,7 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 		kfree(wval);
 
 out:
-	map->unlock(map);
+	map->unlock(map->lock_arg);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(regmap_bulk_write);
@@ -1137,11 +1148,11 @@ int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val)
 	if (reg % map->reg_stride)
 		return -EINVAL;
 
-	map->lock(map);
+	map->lock(map->lock_arg);
 
 	ret = _regmap_read(map, reg, val);
 
-	map->unlock(map);
+	map->unlock(map->lock_arg);
 
 	return ret;
 }
@@ -1171,7 +1182,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 	if (reg % map->reg_stride)
 		return -EINVAL;
 
-	map->lock(map);
+	map->lock(map->lock_arg);
 
 	if (regmap_volatile_range(map, reg, val_count) || map->cache_bypass ||
 	    map->cache_type == REGCACHE_NONE) {
@@ -1193,7 +1204,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 	}
 
  out:
-	map->unlock(map);
+	map->unlock(map->lock_arg);
 
 	return ret;
 }
@@ -1300,9 +1311,9 @@ int regmap_update_bits(struct regmap *map, unsigned int reg,
 	bool change;
 	int ret;
 
-	map->lock(map);
+	map->lock(map->lock_arg);
 	ret = _regmap_update_bits(map, reg, mask, val, &change);
-	map->unlock(map);
+	map->unlock(map->lock_arg);
 
 	return ret;
 }
@@ -1326,9 +1337,9 @@ int regmap_update_bits_check(struct regmap *map, unsigned int reg,
 {
 	int ret;
 
-	map->lock(map);
+	map->lock(map->lock_arg);
 	ret = _regmap_update_bits(map, reg, mask, val, change);
-	map->unlock(map);
+	map->unlock(map->lock_arg);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(regmap_update_bits_check);
@@ -1357,7 +1368,7 @@ int regmap_register_patch(struct regmap *map, const struct reg_default *regs,
 	if (map->patch)
 		return -EBUSY;
 
-	map->lock(map);
+	map->lock(map->lock_arg);
 
 	bypass = map->cache_bypass;
 
@@ -1385,7 +1396,7 @@ int regmap_register_patch(struct regmap *map, const struct reg_default *regs,
 out:
 	map->cache_bypass = bypass;
 
-	map->unlock(map);
+	map->unlock(map->lock_arg);
 
 	return ret;
 }
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index e3bcc3f4dcb8..5d243786f254 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -53,6 +53,9 @@ enum regmap_endian {
 	REGMAP_ENDIAN_NATIVE,
 };
 
+typedef void (*regmap_lock)(void *);
+typedef void (*regmap_unlock)(void *);
+
 /**
  * Configuration for the register map of a device.
  *
@@ -75,6 +78,12 @@ enum regmap_endian {
  * @precious_reg: Optional callback returning true if the rgister
  *                should not be read outside of a call from the driver
  *                (eg, a clear on read interrupt status register).
+ * @lock:         Optional lock callback (overrides regmap's default lock
+ *                function, based on spinlock or mutex).
+ * @unlock:       As above for unlocking.
+ * @lock_arg:     this field is passed as the only argument of lock/unlock
+ *                functions (ignored in case regular lock/unlock functions
+ *                are not overridden).
  *
  * @max_register: Optional, specifies the maximum valid register index.
  * @reg_defaults: Power on reset values for registers (for use with
@@ -116,6 +125,9 @@ struct regmap_config {
 	bool (*readable_reg)(struct device *dev, unsigned int reg);
 	bool (*volatile_reg)(struct device *dev, unsigned int reg);
 	bool (*precious_reg)(struct device *dev, unsigned int reg);
+	regmap_lock lock;
+	regmap_unlock unlock;
+	void *lock_arg;
 
 	unsigned int max_register;
 	const struct reg_default *reg_defaults;
@@ -181,7 +193,9 @@ typedef void (*regmap_hw_free_context)(void *context);
  * Description of a hardware bus for the register map infrastructure.
  *
  * @fast_io: Register IO is fast. Use a spinlock instead of a mutex
- *           to perform locking.
+ *	     to perform locking. This field is ignored if custom lock/unlock
+ *	     functions are used (see fields lock/unlock of
+ *	     struct regmap_config).
  * @write: Write operation.
  * @gather_write: Write operation with split register/value, return -ENOTSUPP
  *                if not implemented  on a given device.
-- 
cgit v1.2.3-55-g7522


From 04ecd2578e712c301fa1369d2a8f298a2b4b146a Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Tue, 11 Sep 2012 14:34:12 +0200
Subject: mac80211: track needed RX chains for channel contexts

On each channel that the device is operating on, it
may need to listen using one or more chains depending
on the SMPS settings of the interfaces using it. The
previous channel context changes completely removed
this ability (before, it was available as the SMPS
mode).

Add per-context tracking of the required static and
dynamic RX chains and notify the driver on changes.
To achieve this, track the chains and SMPS mode used
on each virtual interface and update the channel
context whenever this changes.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h        | 15 +++++++-
 net/mac80211/cfg.c            | 15 ++++++--
 net/mac80211/chan.c           | 90 ++++++++++++++++++++++++++++++++++++++++++-
 net/mac80211/debugfs_netdev.c |  2 +-
 net/mac80211/ibss.c           |  3 ++
 net/mac80211/ieee80211_i.h    | 20 +++++++---
 net/mac80211/iface.c          | 10 +++++
 net/mac80211/main.c           | 18 ++++-----
 net/mac80211/mlme.c           | 28 +++++++++++---
 net/mac80211/status.c         | 15 ++++----
 net/mac80211/trace.h          | 13 +++++--
 net/mac80211/util.c           | 82 +++++++++++++--------------------------
 12 files changed, 219 insertions(+), 92 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d9d2119f0828..3560881d17ee 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -146,9 +146,11 @@ struct ieee80211_low_level_stats {
 /**
  * enum ieee80211_chanctx_change - change flag for channel context
  * @IEEE80211_CHANCTX_CHANGE_CHANNEL_TYPE: The channel type was changed
+ * @IEEE80211_CHANCTX_CHANGE_RX_CHAINS: The number of RX chains changed
  */
 enum ieee80211_chanctx_change {
 	IEEE80211_CHANCTX_CHANGE_CHANNEL_TYPE	= BIT(0),
+	IEEE80211_CHANCTX_CHANGE_RX_CHAINS	= BIT(1),
 };
 
 /**
@@ -159,6 +161,11 @@ enum ieee80211_chanctx_change {
  *
  * @channel: the channel to tune to
  * @channel_type: the channel (HT) type
+ * @rx_chains_static: The number of RX chains that must always be
+ *	active on the channel to receive MIMO transmissions
+ * @rx_chains_dynamic: The number of RX chains that must be enabled
+ *	after RTS/CTS handshake to receive SMPS MIMO transmissions;
+ *	this will always be >= @rx_chains_always.
  * @drv_priv: data area for driver use, will always be aligned to
  *	sizeof(void *), size is determined in hw information.
  */
@@ -166,6 +173,8 @@ struct ieee80211_chanctx_conf {
 	struct ieee80211_channel *channel;
 	enum nl80211_channel_type channel_type;
 
+	u8 rx_chains_static, rx_chains_dynamic;
+
 	u8 drv_priv[0] __attribute__((__aligned__(sizeof(void *))));
 };
 
@@ -820,6 +829,8 @@ enum ieee80211_conf_flags {
  * @IEEE80211_CONF_CHANGE_RETRY_LIMITS: retry limits changed
  * @IEEE80211_CONF_CHANGE_IDLE: Idle flag changed
  * @IEEE80211_CONF_CHANGE_SMPS: Spatial multiplexing powersave mode changed
+ *	Note that this is only valid if channel contexts are not used,
+ *	otherwise each channel context has the number of chains listed.
  */
 enum ieee80211_conf_changed {
 	IEEE80211_CONF_CHANGE_SMPS		= BIT(1),
@@ -885,7 +896,9 @@ enum ieee80211_smps_mode {
  *
  * @smps_mode: spatial multiplexing powersave mode; note that
  *	%IEEE80211_SMPS_STATIC is used when the device is not
- *	configured for an HT channel
+ *	configured for an HT channel.
+ *	Note that this is only valid if channel contexts are not used,
+ *	otherwise each channel context has the number of chains listed.
  */
 struct ieee80211_conf {
 	u32 flags;
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 09c90627fd19..03216b0408c7 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -884,6 +884,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	if (old)
 		return -EALREADY;
 
+	/* TODO: make hostapd tell us what it wants */
+	sdata->smps_mode = IEEE80211_SMPS_OFF;
+	sdata->needed_rx_chains = sdata->local->rx_chains;
+
 	err = ieee80211_vif_use_channel(sdata, params->channel,
 					params->channel_type,
 					IEEE80211_CHANCTX_SHARED);
@@ -1673,6 +1677,10 @@ static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev,
 	if (err)
 		return err;
 
+	/* can mesh use other SMPS modes? */
+	sdata->smps_mode = IEEE80211_SMPS_OFF;
+	sdata->needed_rx_chains = sdata->local->rx_chains;
+
 	err = ieee80211_vif_use_channel(sdata, setup->channel,
 					setup->channel_type,
 					IEEE80211_CHANCTX_SHARED);
@@ -2052,13 +2060,12 @@ int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata,
 
 	/*
 	 * If not associated, or current association is not an HT
-	 * association, there's no need to send an action frame.
+	 * association, there's no need to do anything, just store
+	 * the new value until we associate.
 	 */
 	if (!sdata->u.mgd.associated ||
-	    sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT) {
-		ieee80211_recalc_smps(sdata->local);
+	    sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT)
 		return 0;
-	}
 
 	ap = sdata->u.mgd.associated->bssid;
 
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 41e1aa69f7aa..bfaa486d928c 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -118,6 +118,8 @@ ieee80211_new_chanctx(struct ieee80211_local *local,
 
 	ctx->conf.channel = channel;
 	ctx->conf.channel_type = channel_type;
+	ctx->conf.rx_chains_static = 1;
+	ctx->conf.rx_chains_dynamic = 1;
 	ctx->mode = mode;
 
 	if (!local->use_chanctx) {
@@ -222,8 +224,10 @@ static void ieee80211_unassign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
 
 	drv_unassign_vif_chanctx(local, sdata, ctx);
 
-	if (ctx->refcount > 0)
+	if (ctx->refcount > 0) {
 		ieee80211_recalc_chanctx_chantype(sdata->local, ctx);
+		ieee80211_recalc_smps_chanctx(local, ctx);
+	}
 }
 
 static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
@@ -246,6 +250,89 @@ static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
 		ieee80211_free_chanctx(local, ctx);
 }
 
+void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
+				   struct ieee80211_chanctx *chanctx)
+{
+	struct ieee80211_sub_if_data *sdata;
+	u8 rx_chains_static, rx_chains_dynamic;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	rx_chains_static = 1;
+	rx_chains_dynamic = 1;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		u8 needed_static, needed_dynamic;
+
+		if (!ieee80211_sdata_running(sdata))
+			continue;
+
+		if (rcu_access_pointer(sdata->vif.chanctx_conf) !=
+						&chanctx->conf)
+			continue;
+
+		switch (sdata->vif.type) {
+		case NL80211_IFTYPE_P2P_DEVICE:
+			continue;
+		case NL80211_IFTYPE_STATION:
+			if (!sdata->u.mgd.associated)
+				continue;
+			break;
+		case NL80211_IFTYPE_AP_VLAN:
+			continue;
+		case NL80211_IFTYPE_AP:
+		case NL80211_IFTYPE_ADHOC:
+		case NL80211_IFTYPE_WDS:
+		case NL80211_IFTYPE_MESH_POINT:
+			break;
+		default:
+			WARN_ON_ONCE(1);
+		}
+
+		switch (sdata->smps_mode) {
+		default:
+			WARN_ONCE(1, "Invalid SMPS mode %d\n",
+				  sdata->smps_mode);
+			/* fall through */
+		case IEEE80211_SMPS_OFF:
+			needed_static = sdata->needed_rx_chains;
+			needed_dynamic = sdata->needed_rx_chains;
+			break;
+		case IEEE80211_SMPS_DYNAMIC:
+			needed_static = 1;
+			needed_dynamic = sdata->needed_rx_chains;
+			break;
+		case IEEE80211_SMPS_STATIC:
+			needed_static = 1;
+			needed_dynamic = 1;
+			break;
+		}
+
+		rx_chains_static = max(rx_chains_static, needed_static);
+		rx_chains_dynamic = max(rx_chains_dynamic, needed_dynamic);
+	}
+	rcu_read_unlock();
+
+	if (!local->use_chanctx) {
+		if (rx_chains_static > 1)
+			local->smps_mode = IEEE80211_SMPS_OFF;
+		else if (rx_chains_dynamic > 1)
+			local->smps_mode = IEEE80211_SMPS_DYNAMIC;
+		else
+			local->smps_mode = IEEE80211_SMPS_STATIC;
+		ieee80211_hw_config(local, 0);
+	}
+
+	if (rx_chains_static == chanctx->conf.rx_chains_static &&
+	    rx_chains_dynamic == chanctx->conf.rx_chains_dynamic)
+		return;
+
+	chanctx->conf.rx_chains_static = rx_chains_static;
+	chanctx->conf.rx_chains_dynamic = rx_chains_dynamic;
+	drv_change_chanctx(local, chanctx, IEEE80211_CHANCTX_CHANGE_RX_CHAINS);
+}
+
 int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 			      struct ieee80211_channel *channel,
 			      enum nl80211_channel_type channel_type,
@@ -278,6 +365,7 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	}
 
+	ieee80211_recalc_smps_chanctx(local, ctx);
  out:
 	mutex_unlock(&local->chanctx_mtx);
 	return ret;
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 6d5aec9418ee..34e173976573 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -217,7 +217,7 @@ static ssize_t ieee80211_if_fmt_smps(const struct ieee80211_sub_if_data *sdata,
 
 	return snprintf(buf, buflen, "request: %s\nused: %s\n",
 			smps_modes[sdata->u.mgd.req_smps],
-			smps_modes[sdata->u.mgd.ap_smps]);
+			smps_modes[sdata->smps_mode]);
 }
 
 static ssize_t ieee80211_if_parse_smps(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 34d9235117d9..291c9e07f1bd 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -1132,6 +1132,9 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 	changed |= BSS_CHANGED_HT;
 	ieee80211_bss_info_change_notify(sdata, changed);
 
+	sdata->smps_mode = IEEE80211_SMPS_OFF;
+	sdata->needed_rx_chains = sdata->local->rx_chains;
+
 	ieee80211_queue_work(&sdata->local->hw, &sdata->work);
 
 	return 0;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 6660118b46b3..132577d22928 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -433,7 +433,6 @@ struct ieee80211_if_managed {
 	bool powersave; /* powersave requested for this iface */
 	bool broken_ap; /* AP is broken -- turn off powersave */
 	enum ieee80211_smps_mode req_smps, /* requested smps mode */
-				 ap_smps, /* smps mode AP thinks we're in */
 				 driver_smps_mode; /* smps mode request */
 
 	struct work_struct request_smps_work;
@@ -728,11 +727,17 @@ struct ieee80211_sub_if_data {
 
 	struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS];
 
+	/* used to reconfigure hardware SM PS */
+	struct work_struct recalc_smps;
+
 	struct work_struct work;
 	struct sk_buff_head skb_queue;
 
 	bool arp_filter_state;
 
+	u8 needed_rx_chains;
+	enum ieee80211_smps_mode smps_mode;
+
 	/*
 	 * AP this belongs to: self in AP mode and
 	 * corresponding AP in VLAN mode, NULL for
@@ -905,9 +910,6 @@ struct ieee80211_local {
 	/* used for uploading changed mc list */
 	struct work_struct reconfig_filter;
 
-	/* used to reconfigure hardware SM PS */
-	struct work_struct recalc_smps;
-
 	/* aggregated multicast list */
 	struct netdev_hw_addr_list mc_list;
 
@@ -944,6 +946,9 @@ struct ieee80211_local {
 	/* wowlan is enabled -- don't reconfig on resume */
 	bool wowlan;
 
+	/* number of RX chains the hardware has */
+	u8 rx_chains;
+
 	int tx_headroom; /* required headroom for hardware/radiotap */
 
 	/* Tasklet and skb queue to process calls from IRQ mode. All frames
@@ -1408,6 +1413,8 @@ void ieee80211_ba_session_work(struct work_struct *work);
 void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid);
 void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid);
 
+u8 ieee80211_mcs_to_chains(const struct ieee80211_mcs_info *mcs);
+
 /* Spectrum management */
 void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata,
 				       struct ieee80211_mgmt *mgmt,
@@ -1554,7 +1561,7 @@ u32 ieee80211_sta_get_rates(struct ieee80211_local *local,
 			    enum ieee80211_band band, u32 *basic_rates);
 int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata,
 			     enum ieee80211_smps_mode smps_mode);
-void ieee80211_recalc_smps(struct ieee80211_local *local);
+void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata);
 
 size_t ieee80211_ie_split(const u8 *ies, size_t ielen,
 			  const u8 *ids, int n_ids, size_t offset);
@@ -1585,6 +1592,9 @@ ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 			  enum ieee80211_chanctx_mode mode);
 void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata);
 
+void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
+				   struct ieee80211_chanctx *chanctx);
+
 #ifdef CONFIG_MAC80211_NOINLINE
 #define debug_noinline noinline
 #else
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 7cb8382b19e5..99f2b19c8f0d 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -739,6 +739,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	del_timer_sync(&local->dynamic_ps_timer);
 	cancel_work_sync(&local->dynamic_ps_enable_work);
 
+	cancel_work_sync(&sdata->recalc_smps);
+
 	/* APs need special treatment */
 	if (sdata->vif.type == NL80211_IFTYPE_AP) {
 		struct ieee80211_sub_if_data *vlan, *tmpsdata;
@@ -1125,6 +1127,13 @@ static void ieee80211_iface_work(struct work_struct *work)
 	}
 }
 
+static void ieee80211_recalc_smps_work(struct work_struct *work)
+{
+	struct ieee80211_sub_if_data *sdata =
+		container_of(work, struct ieee80211_sub_if_data, recalc_smps);
+
+	ieee80211_recalc_smps(sdata);
+}
 
 /*
  * Helper function to initialise an interface to a specific type.
@@ -1153,6 +1162,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 
 	skb_queue_head_init(&sdata->skb_queue);
 	INIT_WORK(&sdata->work, ieee80211_iface_work);
+	INIT_WORK(&sdata->recalc_smps, ieee80211_recalc_smps_work);
 
 	switch (type) {
 	case NL80211_IFTYPE_P2P_GO:
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 9cb6280aa2f2..2c8969b67851 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -372,14 +372,6 @@ void ieee80211_restart_hw(struct ieee80211_hw *hw)
 }
 EXPORT_SYMBOL(ieee80211_restart_hw);
 
-static void ieee80211_recalc_smps_work(struct work_struct *work)
-{
-	struct ieee80211_local *local =
-		container_of(work, struct ieee80211_local, recalc_smps);
-
-	ieee80211_recalc_smps(local);
-}
-
 #ifdef CONFIG_INET
 static int ieee80211_ifa_changed(struct notifier_block *nb,
 				 unsigned long data, void *arg)
@@ -667,7 +659,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	INIT_WORK(&local->restart_work, ieee80211_restart_work);
 
 	INIT_WORK(&local->reconfig_filter, ieee80211_reconfig_filter);
-	INIT_WORK(&local->recalc_smps, ieee80211_recalc_smps_work);
 	local->smps_mode = IEEE80211_SMPS_OFF;
 
 	INIT_WORK(&local->dynamic_ps_enable_work,
@@ -773,6 +764,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	if (hw->max_report_rates == 0)
 		hw->max_report_rates = hw->max_rates;
 
+	local->rx_chains = 1;
+
 	/*
 	 * generic code guarantees at least one band,
 	 * set this very early because much code assumes
@@ -804,6 +797,13 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 			max_bitrates = sband->n_bitrates;
 		supp_ht = supp_ht || sband->ht_cap.ht_supported;
 		supp_vht = supp_vht || sband->vht_cap.vht_supported;
+
+		if (sband->ht_cap.ht_supported)
+			local->rx_chains =
+				max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs),
+				    local->rx_chains);
+
+		/* TODO: consider VHT for RX chains, hopefully it's the same */
 	}
 
 	local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) +
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 4add50063161..f3f338541b01 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -543,7 +543,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_11N))
 		ieee80211_add_ht_ie(sdata, skb, assoc_data->ap_ht_param,
-				    sband, chan, ifmgd->ap_smps);
+				    sband, chan, sdata->smps_mode);
 
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
 		ieee80211_add_vht_ie(sdata, skb, sband);
@@ -1392,7 +1392,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata,
 	ieee80211_recalc_ps(local, -1);
 	mutex_unlock(&local->iflist_mtx);
 
-	ieee80211_recalc_smps(local);
+	ieee80211_recalc_smps(sdata);
 	ieee80211_recalc_ps_vif(sdata);
 
 	netif_tx_start_all_queues(sdata->dev);
@@ -3157,6 +3157,10 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (ht_oper) {
+		const u8 *ht_cap_ie;
+		const struct ieee80211_ht_cap *ht_cap;
+		u8 chains = 1;
+
 		channel_type = NL80211_CHAN_HT20;
 
 		if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) {
@@ -3170,8 +3174,22 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 				break;
 			}
 		}
+
+		ht_cap_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY,
+					     cbss->information_elements,
+					     cbss->len_information_elements);
+		if (ht_cap_ie && ht_cap_ie[1] >= sizeof(*ht_cap)) {
+			ht_cap = (void *)(ht_cap_ie + 2);
+			chains = ieee80211_mcs_to_chains(&ht_cap->mcs);
+		}
+		sdata->needed_rx_chains = min(chains, local->rx_chains);
+	} else {
+		sdata->needed_rx_chains = 1;
 	}
 
+	/* will change later if needed */
+	sdata->smps_mode = IEEE80211_SMPS_OFF;
+
 	ieee80211_vif_release_channel(sdata);
 	return ieee80211_vif_use_channel(sdata, cbss->channel, channel_type,
 					 IEEE80211_CHANCTX_SHARED);
@@ -3485,11 +3503,11 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 
 	if (ifmgd->req_smps == IEEE80211_SMPS_AUTOMATIC) {
 		if (ifmgd->powersave)
-			ifmgd->ap_smps = IEEE80211_SMPS_DYNAMIC;
+			sdata->smps_mode = IEEE80211_SMPS_DYNAMIC;
 		else
-			ifmgd->ap_smps = IEEE80211_SMPS_OFF;
+			sdata->smps_mode = IEEE80211_SMPS_OFF;
 	} else
-		ifmgd->ap_smps = ifmgd->req_smps;
+		sdata->smps_mode = ifmgd->req_smps;
 
 	assoc_data->capability = req->bss->capability;
 	assoc_data->wmm = bss->wmm_used &&
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 3af0cc4130f1..21fa5c72ea14 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -189,30 +189,31 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb)
 	}
 
 	if (ieee80211_is_action(mgmt->frame_control) &&
-	    sdata->vif.type == NL80211_IFTYPE_STATION &&
 	    mgmt->u.action.category == WLAN_CATEGORY_HT &&
-	    mgmt->u.action.u.ht_smps.action == WLAN_HT_ACTION_SMPS) {
+	    mgmt->u.action.u.ht_smps.action == WLAN_HT_ACTION_SMPS &&
+	    sdata->vif.type == NL80211_IFTYPE_STATION &&
+	    ieee80211_sdata_running(sdata)) {
 		/*
 		 * This update looks racy, but isn't -- if we come
 		 * here we've definitely got a station that we're
 		 * talking to, and on a managed interface that can
 		 * only be the AP. And the only other place updating
-		 * this variable is before we're associated.
+		 * this variable in managed mode is before association.
 		 */
 		switch (mgmt->u.action.u.ht_smps.smps_control) {
 		case WLAN_HT_SMPS_CONTROL_DYNAMIC:
-			sta->sdata->u.mgd.ap_smps = IEEE80211_SMPS_DYNAMIC;
+			sdata->smps_mode = IEEE80211_SMPS_DYNAMIC;
 			break;
 		case WLAN_HT_SMPS_CONTROL_STATIC:
-			sta->sdata->u.mgd.ap_smps = IEEE80211_SMPS_STATIC;
+			sdata->smps_mode = IEEE80211_SMPS_STATIC;
 			break;
 		case WLAN_HT_SMPS_CONTROL_DISABLED:
 		default: /* shouldn't happen since we don't send that */
-			sta->sdata->u.mgd.ap_smps = IEEE80211_SMPS_OFF;
+			sdata->smps_mode = IEEE80211_SMPS_OFF;
 			break;
 		}
 
-		ieee80211_queue_work(&local->hw, &local->recalc_smps);
+		ieee80211_queue_work(&local->hw, &sdata->recalc_smps);
 	}
 }
 
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index a3f5fe2a84a8..629364705f7b 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -29,11 +29,16 @@
 #define VIF_PR_ARG	__get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : ""
 
 #define CHANCTX_ENTRY	__field(int, freq)					\
-			__field(int, chantype)
+			__field(int, chantype)					\
+			__field(u8, rx_chains_static)				\
+			__field(u8, rx_chains_dynamic)
 #define CHANCTX_ASSIGN	__entry->freq = ctx->conf.channel->center_freq;		\
-			__entry->chantype = ctx->conf.channel_type
-#define CHANCTX_PR_FMT	" freq:%d MHz chantype:%d"
-#define CHANCTX_PR_ARG	__entry->freq, __entry->chantype
+			__entry->chantype = ctx->conf.channel_type;		\
+			__entry->rx_chains_static = ctx->conf.rx_chains_static;	\
+			__entry->rx_chains_dynamic = ctx->conf.rx_chains_dynamic
+#define CHANCTX_PR_FMT	" freq:%d MHz chantype:%d chains:%d/%d"
+#define CHANCTX_PR_ARG	__entry->freq, __entry->chantype,			\
+			__entry->rx_chains_static, __entry->rx_chains_dynamic
 
 
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 7d737071dedb..b732e219b107 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1618,68 +1618,24 @@ void ieee80211_resume_disconnect(struct ieee80211_vif *vif)
 }
 EXPORT_SYMBOL_GPL(ieee80211_resume_disconnect);
 
-static int check_mgd_smps(struct ieee80211_if_managed *ifmgd,
-			  enum ieee80211_smps_mode *smps_mode)
+void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata)
 {
-	if (ifmgd->associated) {
-		*smps_mode = ifmgd->ap_smps;
-
-		if (*smps_mode == IEEE80211_SMPS_AUTOMATIC) {
-			if (ifmgd->powersave)
-				*smps_mode = IEEE80211_SMPS_DYNAMIC;
-			else
-				*smps_mode = IEEE80211_SMPS_OFF;
-		}
-
-		return 1;
-	}
-
-	return 0;
-}
-
-void ieee80211_recalc_smps(struct ieee80211_local *local)
-{
-	struct ieee80211_sub_if_data *sdata;
-	enum ieee80211_smps_mode smps_mode = IEEE80211_SMPS_OFF;
-	int count = 0;
-
-	mutex_lock(&local->iflist_mtx);
-
-	/*
-	 * This function could be improved to handle multiple
-	 * interfaces better, but right now it makes any
-	 * non-station interfaces force SM PS to be turned
-	 * off. If there are multiple station interfaces it
-	 * could also use the best possible mode, e.g. if
-	 * one is in static and the other in dynamic then
-	 * dynamic is ok.
-	 */
-
-	list_for_each_entry(sdata, &local->interfaces, list) {
-		if (!ieee80211_sdata_running(sdata))
-			continue;
-		if (sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE)
-			continue;
-		if (sdata->vif.type != NL80211_IFTYPE_STATION)
-			goto set;
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx_conf *chanctx_conf;
+	struct ieee80211_chanctx *chanctx;
 
-		count += check_mgd_smps(&sdata->u.mgd, &smps_mode);
+	mutex_lock(&local->chanctx_mtx);
 
-		if (count > 1) {
-			smps_mode = IEEE80211_SMPS_OFF;
-			break;
-		}
-	}
+	chanctx_conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					lockdep_is_held(&local->chanctx_mtx));
 
-	if (smps_mode == local->smps_mode)
+	if (WARN_ON_ONCE(!chanctx_conf))
 		goto unlock;
 
- set:
-	local->smps_mode = smps_mode;
-	/* changed flag is auto-detected for this */
-	ieee80211_hw_config(local, 0);
+	chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf);
+	ieee80211_recalc_smps_chanctx(local, chanctx);
  unlock:
-	mutex_unlock(&local->iflist_mtx);
+	mutex_unlock(&local->chanctx_mtx);
 }
 
 static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id)
@@ -1978,3 +1934,19 @@ int ieee80211_ave_rssi(struct ieee80211_vif *vif)
 	return ifmgd->ave_beacon_signal;
 }
 EXPORT_SYMBOL_GPL(ieee80211_ave_rssi);
+
+u8 ieee80211_mcs_to_chains(const struct ieee80211_mcs_info *mcs)
+{
+	if (!mcs)
+		return 1;
+
+	/* TODO: consider rx_highest */
+
+	if (mcs->rx_mask[3])
+		return 4;
+	if (mcs->rx_mask[2])
+		return 3;
+	if (mcs->rx_mask[1])
+		return 2;
+	return 1;
+}
-- 
cgit v1.2.3-55-g7522


From 3448c0058327356049f140116fc6632bbfd0c122 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Tue, 11 Sep 2012 17:57:42 +0200
Subject: mac80211: add channel context iterator

Drivers may need to iterate the active channel
contexts, export an iterator function to allow
that. To make it possible, use RCU-safe list
functions.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 21 +++++++++++++++++++++
 net/mac80211/chan.c    | 22 ++++++++++++++++++++--
 2 files changed, 41 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 3560881d17ee..f12df5bb529f 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3596,6 +3596,27 @@ void ieee80211_iter_keys(struct ieee80211_hw *hw,
 				      void *data),
 			 void *iter_data);
 
+/**
+ * ieee80211_iter_chan_contexts_atomic - iterate channel contexts
+ * @hw: pointre obtained from ieee80211_alloc_hw().
+ * @iter: iterator function
+ * @iter_data: data passed to iterator function
+ *
+ * Iterate all active channel contexts. This function is atomic and
+ * doesn't acquire any locks internally that might be held in other
+ * places while calling into the driver.
+ *
+ * The iterator will not find a context that's being added (during
+ * the driver callback to add it) but will find it while it's being
+ * removed.
+ */
+void ieee80211_iter_chan_contexts_atomic(
+	struct ieee80211_hw *hw,
+	void (*iter)(struct ieee80211_hw *hw,
+		     struct ieee80211_chanctx_conf *chanctx_conf,
+		     void *data),
+	void *iter_data);
+
 /**
  * ieee80211_ap_probereq_get - retrieve a Probe Request template
  * @hw: pointer obtained from ieee80211_alloc_hw().
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index bfaa486d928c..f84b86028a9c 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -3,6 +3,7 @@
  */
 
 #include <linux/nl80211.h>
+#include <linux/export.h>
 #include <net/cfg80211.h>
 #include "ieee80211_i.h"
 #include "driver-ops.h"
@@ -134,7 +135,7 @@ ieee80211_new_chanctx(struct ieee80211_local *local,
 		}
 	}
 
-	list_add(&ctx->list, &local->chanctx_list);
+	list_add_rcu(&ctx->list, &local->chanctx_list);
 
 	return ctx;
 }
@@ -153,7 +154,7 @@ static void ieee80211_free_chanctx(struct ieee80211_local *local,
 		drv_remove_chanctx(local, ctx);
 	}
 
-	list_del(&ctx->list);
+	list_del_rcu(&ctx->list);
 	kfree_rcu(ctx, rcu_head);
 }
 
@@ -379,3 +380,20 @@ void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
 	__ieee80211_vif_release_channel(sdata);
 	mutex_unlock(&sdata->local->chanctx_mtx);
 }
+
+void ieee80211_iter_chan_contexts_atomic(
+	struct ieee80211_hw *hw,
+	void (*iter)(struct ieee80211_hw *hw,
+		     struct ieee80211_chanctx_conf *chanctx_conf,
+		     void *data),
+	void *iter_data)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_chanctx *ctx;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ctx, &local->chanctx_list, list)
+		iter(hw, &ctx->conf, iter_data);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(ieee80211_iter_chan_contexts_atomic);
-- 
cgit v1.2.3-55-g7522


From e39e5b5e7206767a0f1be0e5cb7acbd0db87ae60 Mon Sep 17 00:00:00 2001
From: Jouni Malinen
Date: Sun, 30 Sep 2012 19:29:39 +0300
Subject: cfg80211: Allow user space to specify non-IEs to SAE Authentication

SAE extends Authentication frames with fields that are not information
elements. NL80211_ATTR_IE is not suitable for these, so introduce a new
attribute that can be used to specify the fields needed for SAE in
station mode.

Signed-off-by: Jouni Malinen <j@w1.fi>
[change to verify that SAE is only used with authenticate command]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  5 ++++
 include/uapi/linux/nl80211.h | 11 ++++++++
 net/wireless/core.h          |  6 +++--
 net/wireless/mlme.c          | 11 +++++---
 net/wireless/nl80211.c       | 60 +++++++++++++++++++++++++++++++++++---------
 net/wireless/sme.c           |  2 +-
 6 files changed, 77 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 1b4989082244..60cebfac3e3c 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1152,6 +1152,9 @@ const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 ie);
  * @key_len: length of WEP key for shared key authentication
  * @key_idx: index of WEP key for shared key authentication
  * @key: WEP key for shared key authentication
+ * @sae_data: Non-IE data to use with SAE or %NULL. This starts with
+ *	Authentication transaction sequence number field.
+ * @sae_data_len: Length of sae_data buffer in octets
  */
 struct cfg80211_auth_request {
 	struct cfg80211_bss *bss;
@@ -1160,6 +1163,8 @@ struct cfg80211_auth_request {
 	enum nl80211_auth_type auth_type;
 	const u8 *key;
 	u8 key_len, key_idx;
+	const u8 *sae_data;
+	size_t sae_data_len;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 7df9b500c804..179a0c2e2f61 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1273,6 +1273,9 @@ enum nl80211_commands {
  *	the connection request from a station. nl80211_connect_failed_reason
  *	enum has different reasons of connection failure.
  *
+ * @NL80211_ATTR_SAE_DATA: SAE elements in Authentication frames. This starts
+ *	with the Authentication transaction sequence number field.
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1530,6 +1533,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_CONN_FAILED_REASON,
 
+	NL80211_ATTR_SAE_DATA,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -2489,6 +2494,7 @@ enum nl80211_bss_status {
  * @NL80211_AUTHTYPE_SHARED_KEY: Shared Key authentication (WEP only)
  * @NL80211_AUTHTYPE_FT: Fast BSS Transition (IEEE 802.11r)
  * @NL80211_AUTHTYPE_NETWORK_EAP: Network EAP (some Cisco APs and mainly LEAP)
+ * @NL80211_AUTHTYPE_SAE: Simultaneous authentication of equals
  * @__NL80211_AUTHTYPE_NUM: internal
  * @NL80211_AUTHTYPE_MAX: maximum valid auth algorithm
  * @NL80211_AUTHTYPE_AUTOMATIC: determine automatically (if necessary by
@@ -2500,6 +2506,7 @@ enum nl80211_auth_type {
 	NL80211_AUTHTYPE_SHARED_KEY,
 	NL80211_AUTHTYPE_FT,
 	NL80211_AUTHTYPE_NETWORK_EAP,
+	NL80211_AUTHTYPE_SAE,
 
 	/* keep last */
 	__NL80211_AUTHTYPE_NUM,
@@ -3028,6 +3035,9 @@ enum nl80211_ap_sme_features {
  *	in the interface combinations, even when it's only used for scan
  *	and remain-on-channel. This could be due to, for example, the
  *	remain-on-channel implementation requiring a channel context.
+ * @NL80211_FEATURE_SAE: This driver supports simultaneous authentication of
+ *	equals (SAE) with user space SME (NL80211_CMD_AUTHENTICATE) in station
+ *	mode
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -3035,6 +3045,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_INACTIVITY_TIMER		= 1 << 2,
 	NL80211_FEATURE_CELL_BASE_REG_HINTS		= 1 << 3,
 	NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL	= 1 << 4,
+	NL80211_FEATURE_SAE				= 1 << 5,
 };
 
 /**
diff --git a/net/wireless/core.h b/net/wireless/core.h
index a343be4a52bd..b8eb743fe7da 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -320,13 +320,15 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
 			 const u8 *bssid,
 			 const u8 *ssid, int ssid_len,
 			 const u8 *ie, int ie_len,
-			 const u8 *key, int key_len, int key_idx);
+			 const u8 *key, int key_len, int key_idx,
+			 const u8 *sae_data, int sae_data_len);
 int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
 		       struct net_device *dev, struct ieee80211_channel *chan,
 		       enum nl80211_auth_type auth_type, const u8 *bssid,
 		       const u8 *ssid, int ssid_len,
 		       const u8 *ie, int ie_len,
-		       const u8 *key, int key_len, int key_idx);
+		       const u8 *key, int key_len, int key_idx,
+		       const u8 *sae_data, int sae_data_len);
 int __cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev,
 			  struct net_device *dev,
 			  struct ieee80211_channel *chan,
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 8016fee0752b..460d49325741 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -273,7 +273,8 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
 			 const u8 *bssid,
 			 const u8 *ssid, int ssid_len,
 			 const u8 *ie, int ie_len,
-			 const u8 *key, int key_len, int key_idx)
+			 const u8 *key, int key_len, int key_idx,
+			 const u8 *sae_data, int sae_data_len)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_auth_request req;
@@ -293,6 +294,8 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
 
 	req.ie = ie;
 	req.ie_len = ie_len;
+	req.sae_data = sae_data;
+	req.sae_data_len = sae_data_len;
 	req.auth_type = auth_type;
 	req.bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len,
 				   WLAN_CAPABILITY_ESS, WLAN_CAPABILITY_ESS);
@@ -319,7 +322,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
 		       enum nl80211_auth_type auth_type, const u8 *bssid,
 		       const u8 *ssid, int ssid_len,
 		       const u8 *ie, int ie_len,
-		       const u8 *key, int key_len, int key_idx)
+		       const u8 *key, int key_len, int key_idx,
+		       const u8 *sae_data, int sae_data_len)
 {
 	int err;
 
@@ -327,7 +331,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
 	wdev_lock(dev->ieee80211_ptr);
 	err = __cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid,
 				   ssid, ssid_len, ie, ie_len,
-				   key, key_len, key_idx);
+				   key, key_len, key_idx,
+				   sae_data, sae_data_len);
 	wdev_unlock(dev->ieee80211_ptr);
 	mutex_unlock(&rdev->devlist_mtx);
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0418a6d5c1a6..74d8123ada77 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -23,7 +23,6 @@
 #include "nl80211.h"
 #include "reg.h"
 
-static bool nl80211_valid_auth_type(enum nl80211_auth_type auth_type);
 static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 				   struct genl_info *info,
 				   struct cfg80211_crypto_settings *settings,
@@ -355,6 +354,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 },
 	[NL80211_ATTR_WDEV] = { .type = NLA_U64 },
 	[NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 },
+	[NL80211_ATTR_SAE_DATA] = { .type = NLA_BINARY, },
 };
 
 /* policy for the key attributes */
@@ -2490,6 +2490,30 @@ static bool nl80211_get_ap_channel(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev,
+				    enum nl80211_auth_type auth_type,
+				    enum nl80211_commands cmd)
+{
+	if (auth_type > NL80211_AUTHTYPE_MAX)
+		return false;
+
+	switch (cmd) {
+	case NL80211_CMD_AUTHENTICATE:
+		if (!(rdev->wiphy.features & NL80211_FEATURE_SAE) &&
+		    auth_type == NL80211_AUTHTYPE_SAE)
+			return false;
+		return true;
+	case NL80211_CMD_CONNECT:
+	case NL80211_CMD_START_AP:
+		/* SAE not supported yet */
+		if (auth_type == NL80211_AUTHTYPE_SAE)
+			return false;
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -2559,7 +2583,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_AUTH_TYPE]) {
 		params.auth_type = nla_get_u32(
 			info->attrs[NL80211_ATTR_AUTH_TYPE]);
-		if (!nl80211_valid_auth_type(params.auth_type))
+		if (!nl80211_valid_auth_type(rdev, params.auth_type,
+					     NL80211_CMD_START_AP))
 			return -EINVAL;
 	} else
 		params.auth_type = NL80211_AUTHTYPE_AUTOMATIC;
@@ -4852,11 +4877,6 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 	return res;
 }
 
-static bool nl80211_valid_auth_type(enum nl80211_auth_type auth_type)
-{
-	return auth_type <= NL80211_AUTHTYPE_MAX;
-}
-
 static bool nl80211_valid_wpa_versions(u32 wpa_versions)
 {
 	return !(wpa_versions & ~(NL80211_WPA_VERSION_1 |
@@ -4868,8 +4888,8 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info)
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
 	struct ieee80211_channel *chan;
-	const u8 *bssid, *ssid, *ie = NULL;
-	int err, ssid_len, ie_len = 0;
+	const u8 *bssid, *ssid, *ie = NULL, *sae_data = NULL;
+	int err, ssid_len, ie_len = 0, sae_data_len = 0;
 	enum nl80211_auth_type auth_type;
 	struct key_parse key;
 	bool local_state_change;
@@ -4945,9 +4965,23 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	auth_type = nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]);
-	if (!nl80211_valid_auth_type(auth_type))
+	if (!nl80211_valid_auth_type(rdev, auth_type, NL80211_CMD_AUTHENTICATE))
 		return -EINVAL;
 
+	if (auth_type == NL80211_AUTHTYPE_SAE &&
+	    !info->attrs[NL80211_ATTR_SAE_DATA])
+		return -EINVAL;
+
+	if (info->attrs[NL80211_ATTR_SAE_DATA]) {
+		if (auth_type != NL80211_AUTHTYPE_SAE)
+			return -EINVAL;
+		sae_data = nla_data(info->attrs[NL80211_ATTR_SAE_DATA]);
+		sae_data_len = nla_len(info->attrs[NL80211_ATTR_SAE_DATA]);
+		/* need to include at least Auth Transaction and Status Code */
+		if (sae_data_len < 4)
+			return -EINVAL;
+	}
+
 	local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE];
 
 	/*
@@ -4959,7 +4993,8 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info)
 
 	return cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid,
 				  ssid, ssid_len, ie, ie_len,
-				  key.p.key, key.p.key_len, key.idx);
+				  key.p.key, key.p.key_len, key.idx,
+				  sae_data, sae_data_len);
 }
 
 static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
@@ -5596,7 +5631,8 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_AUTH_TYPE]) {
 		connect.auth_type =
 			nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]);
-		if (!nl80211_valid_auth_type(connect.auth_type))
+		if (!nl80211_valid_auth_type(rdev, connect.auth_type,
+					     NL80211_CMD_CONNECT))
 			return -EINVAL;
 	} else
 		connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC;
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 6f39cb808302..055d59643616 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -179,7 +179,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev)
 					    params->ssid, params->ssid_len,
 					    NULL, 0,
 					    params->key, params->key_len,
-					    params->key_idx);
+					    params->key_idx, NULL, 0);
 	case CFG80211_CONN_ASSOCIATE_NEXT:
 		BUG_ON(!rdev->ops->assoc);
 		wdev->conn->state = CFG80211_CONN_ASSOCIATING;
-- 
cgit v1.2.3-55-g7522


From d4950281d72d8845225e3a39dbeb366c40c824c9 Mon Sep 17 00:00:00 2001
From: Mahesh Palivela
Date: Wed, 10 Oct 2012 11:25:40 +0000
Subject: ieee80211: Rename VHT cap struct

Rename struct ieee80211_vht_capabilities to ieee80211_vht_cap
and renamed its member vht_capabilities_info to vht_cap_info.

Signed-off-by: Mahesh Palivela <maheshp@posedge.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 45 +++++++++++++++++++++++++++++++--------------
 net/mac80211/main.c       |  2 +-
 net/mac80211/mlme.c       |  4 ++--
 net/mac80211/util.c       |  4 ++--
 4 files changed, 36 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 2385119f8bb0..8c803f0e4925 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1107,20 +1107,6 @@ struct ieee80211_ht_operation {
 #define WLAN_HT_SMPS_CONTROL_STATIC	1
 #define WLAN_HT_SMPS_CONTROL_DYNAMIC	3
 
-#define VHT_MCS_SUPPORTED_SET_SIZE      8
-
-struct ieee80211_vht_capabilities {
-	__le32 vht_capabilities_info;
-	u8 vht_supported_mcs_set[VHT_MCS_SUPPORTED_SET_SIZE];
-} __packed;
-
-struct ieee80211_vht_operation {
-	u8 vht_op_info_chwidth;
-	u8 vht_op_info_chan_center_freq_seg1_idx;
-	u8 vht_op_info_chan_center_freq_seg2_idx;
-	__le16 vht_basic_mcs_set;
-} __packed;
-
 /**
  * struct ieee80211_vht_mcs_info - VHT MCS information
  * @rx_mcs_map: RX MCS map 2 bits for each stream, total 8 streams
@@ -1141,6 +1127,37 @@ struct ieee80211_vht_mcs_info {
 	__le16 tx_highest;
 } __packed;
 
+/**
+ * struct ieee80211_vht_cap - VHT capabilities
+ *
+ * This structure is the "VHT capabilities element" as
+ * described in 802.11ac D3.0 8.4.2.160
+ * @vht_cap_info: VHT capability info
+ * @supp_mcs: VHT MCS supported rates
+ */
+struct ieee80211_vht_cap {
+	__le32 vht_cap_info;
+	struct ieee80211_vht_mcs_info supp_mcs;
+} __packed;
+
+/**
+ * struct ieee80211_vht_operation - VHT operation IE
+ *
+ * This structure is the "VHT operation element" as
+ * described in 802.11ac D3.0 8.4.2.161
+ * @chan_width: Operating channel width
+ * @center_freq_seg1_idx: center freq segment 1 index
+ * @center_freq_seg2_idx: center freq segment 2 index
+ * @basic_mcs_set: VHT Basic MCS rate set
+ */
+struct ieee80211_vht_operation {
+	u8 chan_width;
+	u8 center_freq_seg1_idx;
+	u8 center_freq_seg2_idx;
+	__le16 basic_mcs_set;
+} __packed;
+
+
 #define IEEE80211_VHT_MCS_ZERO_TO_SEVEN_SUPPORT 0
 #define IEEE80211_VHT_MCS_ZERO_TO_EIGHT_SUPPORT 1
 #define IEEE80211_VHT_MCS_ZERO_TO_NINE_SUPPORT  2
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 473b755b349f..620f427069c8 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -876,7 +876,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 
 	if (supp_vht)
 		local->scan_ies_len +=
-			2 + sizeof(struct ieee80211_vht_capabilities);
+			2 + sizeof(struct ieee80211_vht_cap);
 
 	if (!local->ops->hw_scan) {
 		/* For hw_scan, driver needs to set these up. */
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f24884a60614..4af5a3eb892e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -353,7 +353,7 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata,
 	cap = vht_cap.cap;
 
 	/* reserve and fill IE */
-	pos = skb_put(skb, sizeof(struct ieee80211_vht_capabilities) + 2);
+	pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2);
 	ieee80211_ie_build_vht_cap(pos, &vht_cap, cap);
 }
 
@@ -412,7 +412,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 			4 + /* power capability */
 			2 + 2 * sband->n_channels + /* supported channels */
 			2 + sizeof(struct ieee80211_ht_cap) + /* HT */
-			2 + sizeof(struct ieee80211_vht_capabilities) + /* VHT */
+			2 + sizeof(struct ieee80211_vht_cap) + /* VHT */
 			assoc_data->ie_len + /* extra IEs */
 			9, /* WMM */
 			GFP_KERNEL);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 558412d75ac3..3dca9827624a 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1775,8 +1775,8 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 	__le32 tmp;
 
 	*pos++ = WLAN_EID_VHT_CAPABILITY;
-	*pos++ = sizeof(struct ieee80211_vht_capabilities);
-	memset(pos, 0, sizeof(struct ieee80211_vht_capabilities));
+	*pos++ = sizeof(struct ieee80211_vht_cap);
+	memset(pos, 0, sizeof(struct ieee80211_vht_cap));
 
 	/* capability flags */
 	tmp = cpu_to_le32(cap);
-- 
cgit v1.2.3-55-g7522


From 818255ea47709065c53c86ca47fce96d8580bee1 Mon Sep 17 00:00:00 2001
From: Mahesh Palivela
Date: Wed, 10 Oct 2012 11:33:04 +0000
Subject: mac80211: VHT peer STA caps

Save the AP's VHT capabilities (in managed
mode) and make them available to the driver
in the station information.

Unlike HT capabilities, they aren't restricted
to the common capabilities, so drivers must be
aware of their own capabilities.

Signed-off-by: Mahesh Palivela <maheshp@posedge.com>
[fix endian conversion bug ...]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  3 +++
 net/mac80211/Makefile      |  1 +
 net/mac80211/ieee80211_i.h |  7 +++++++
 net/mac80211/mlme.c        |  5 +++++
 net/mac80211/util.c        | 12 ++++++++++++
 net/mac80211/vht.c         | 35 +++++++++++++++++++++++++++++++++++
 6 files changed, 63 insertions(+)
 create mode 100644 net/mac80211/vht.c

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index f12df5bb529f..89d5bba28e05 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1122,6 +1122,8 @@ enum ieee80211_sta_state {
  * @aid: AID we assigned to the station if we're an AP
  * @supp_rates: Bitmap of supported rates (per band)
  * @ht_cap: HT capabilities of this STA; restricted to our own TX capabilities
+ * @vht_cap: VHT capabilities of this STA; Not restricting any capabilities
+ * 	of remote STA. Taking as is.
  * @wme: indicates whether the STA supports WME. Only valid during AP-mode.
  * @drv_priv: data area for driver use, will always be aligned to
  *	sizeof(void *), size is determined in hw information.
@@ -1134,6 +1136,7 @@ struct ieee80211_sta {
 	u8 addr[ETH_ALEN];
 	u16 aid;
 	struct ieee80211_sta_ht_cap ht_cap;
+	struct ieee80211_sta_vht_cap vht_cap;
 	bool wme;
 	u8 uapsd_queues;
 	u8 max_sp;
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index a7dd110faafa..4911202334d9 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -8,6 +8,7 @@ mac80211-y := \
 	wpa.o \
 	scan.o offchannel.o \
 	ht.o agg-tx.o agg-rx.o \
+	vht.o \
 	ibss.o \
 	iface.o \
 	rate.o \
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index b7382454d0a6..6327816790e6 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1188,6 +1188,8 @@ struct ieee802_11_elems {
 	u8 *wmm_param;
 	struct ieee80211_ht_cap *ht_cap_elem;
 	struct ieee80211_ht_operation *ht_operation;
+	struct ieee80211_vht_cap *vht_cap_elem;
+	struct ieee80211_vht_operation *vht_operation;
 	struct ieee80211_meshconf_ie *mesh_config;
 	u8 *mesh_id;
 	u8 *peering;
@@ -1416,6 +1418,11 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid);
 
 u8 ieee80211_mcs_to_chains(const struct ieee80211_mcs_info *mcs);
 
+/* VHT */
+void ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
+					 struct ieee80211_supported_band *sband,
+					 struct ieee80211_vht_cap *vht_cap_ie,
+					 struct ieee80211_sta_vht_cap *vht_cap);
 /* Spectrum management */
 void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata,
 				       struct ieee80211_mgmt *mgmt,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 4af5a3eb892e..ab39c4f44e5c 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2156,6 +2156,11 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	sta->supports_40mhz =
 		sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40;
 
+	if (elems.vht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
+		ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
+						    elems.vht_cap_elem,
+						    &sta->sta.vht_cap);
+
 	rate_control_rate_init(sta);
 
 	if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED)
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 3dca9827624a..51a4a2516233 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -741,6 +741,18 @@ u32 ieee802_11_parse_elems_crc(u8 *start, size_t len,
 			else
 				elem_parse_failed = true;
 			break;
+		case WLAN_EID_VHT_CAPABILITY:
+			if (elen >= sizeof(struct ieee80211_vht_cap))
+				elems->vht_cap_elem = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
+		case WLAN_EID_VHT_OPERATION:
+			if (elen >= sizeof(struct ieee80211_vht_operation))
+				elems->vht_operation = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
 		case WLAN_EID_MESH_ID:
 			elems->mesh_id = pos;
 			elems->mesh_id_len = elen;
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
new file mode 100644
index 000000000000..f311388aeedf
--- /dev/null
+++ b/net/mac80211/vht.c
@@ -0,0 +1,35 @@
+/*
+ * VHT handling
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ieee80211.h>
+#include <linux/export.h>
+#include <net/mac80211.h>
+#include "ieee80211_i.h"
+
+
+void ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
+					 struct ieee80211_supported_band *sband,
+					 struct ieee80211_vht_cap *vht_cap_ie,
+					 struct ieee80211_sta_vht_cap *vht_cap)
+{
+	if (WARN_ON_ONCE(!vht_cap))
+		return;
+
+	memset(vht_cap, 0, sizeof(*vht_cap));
+
+	if (!vht_cap_ie || !sband->vht_cap.vht_supported)
+		return;
+
+	vht_cap->vht_supported = true;
+
+	vht_cap->cap = le32_to_cpu(vht_cap_ie->vht_cap_info);
+
+	/* Copy peer MCS info, the driver might need them. */
+	memcpy(&vht_cap->vht_mcs, &vht_cap_ie->supp_mcs,
+	       sizeof(struct ieee80211_vht_mcs_info));
+}
-- 
cgit v1.2.3-55-g7522


From f461be3eff662f01a177ecea8c1d7b040bb6bfbe Mon Sep 17 00:00:00 2001
From: Mahesh Palivela
Date: Thu, 11 Oct 2012 08:04:52 +0000
Subject: {nl,cfg}80211: Peer STA VHT caps

To save STAs VHT caps in AP mode

Signed-off-by: Mahesh Palivela <maheshp@posedge.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 2 ++
 include/uapi/linux/nl80211.h | 6 ++++++
 net/mac80211/cfg.c           | 5 +++++
 net/wireless/nl80211.c       | 5 +++++
 4 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 60cebfac3e3c..607b5c02f740 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -498,6 +498,7 @@ enum station_parameters_apply_mask {
  * @plink_action: plink action to take
  * @plink_state: set the peer link state for a station
  * @ht_capa: HT capabilities of station
+ * @vht_capa: VHT capabilities of station
  * @uapsd_queues: bitmap of queues configured for uapsd. same format
  *	as the AC bitmap in the QoS info field
  * @max_sp: max Service Period. same format as the MAX_SP in the
@@ -517,6 +518,7 @@ struct station_parameters {
 	u8 plink_action;
 	u8 plink_state;
 	struct ieee80211_ht_cap *ht_capa;
+	struct ieee80211_vht_cap *vht_capa;
 	u8 uapsd_queues;
 	u8 max_sp;
 };
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 179a0c2e2f61..71ab23b0356d 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1276,6 +1276,9 @@ enum nl80211_commands {
  * @NL80211_ATTR_SAE_DATA: SAE elements in Authentication frames. This starts
  *	with the Authentication transaction sequence number field.
  *
+ * @NL80211_ATTR_VHT_CAPABILITY: VHT Capability information element (from
+ *	association request when used with NL80211_CMD_NEW_STATION)
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1535,6 +1538,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_SAE_DATA,
 
+	NL80211_ATTR_VHT_CAPABILITY,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -1578,6 +1583,7 @@ enum nl80211_attrs {
 #define NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY	16
 #define NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY	24
 #define NL80211_HT_CAPABILITY_LEN		26
+#define NL80211_VHT_CAPABILITY_LEN		12
 
 #define NL80211_MAX_NR_CIPHER_SUITES		5
 #define NL80211_MAX_NR_AKM_SUITES		2
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 03216b0408c7..ed27988f9d35 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1157,6 +1157,11 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 						  params->ht_capa,
 						  &sta->sta.ht_cap);
 
+	if (params->vht_capa)
+		ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
+						    params->vht_capa,
+						    &sta->sta.vht_cap);
+
 	if (ieee80211_vif_is_mesh(&sdata->vif)) {
 #ifdef CONFIG_MAC80211_MESH
 		if (sdata->u.mesh.security & IEEE80211_MESH_SEC_SECURED)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 74d8123ada77..ef170e982f91 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -355,6 +355,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_WDEV] = { .type = NLA_U64 },
 	[NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 },
 	[NL80211_ATTR_SAE_DATA] = { .type = NLA_BINARY, },
+	[NL80211_ATTR_VHT_CAPABILITY] = { .len = NL80211_VHT_CAPABILITY_LEN },
 };
 
 /* policy for the key attributes */
@@ -3223,6 +3224,10 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 		params.ht_capa =
 			nla_data(info->attrs[NL80211_ATTR_HT_CAPABILITY]);
 
+	if (info->attrs[NL80211_ATTR_VHT_CAPABILITY])
+		params.vht_capa =
+			nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]);
+
 	if (info->attrs[NL80211_ATTR_STA_PLINK_ACTION])
 		params.plink_action =
 		    nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_ACTION]);
-- 
cgit v1.2.3-55-g7522


From 6a1c9f6d19180cdbb603e5b77bd7b57d01260664 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Mon, 8 Oct 2012 14:52:24 +0300
Subject: OMAP: move arch/arm/plat-omap/include/plat/vrfb.h

Now that vrfb driver is not omap dependent anymore, we can move vrfb.h
from arch/arm/plat-omap/include/plat to include/video/omapvrfb.h.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Vaibhav Hiremath <hvaibhav@ti.com>
---
 arch/arm/plat-omap/include/plat/vrfb.h       | 66 ----------------------------
 drivers/media/platform/omap/omap_vout.c      |  2 +-
 drivers/media/platform/omap/omap_vout_vrfb.c |  2 +-
 drivers/media/platform/omap/omap_voutdef.h   |  2 +-
 drivers/video/omap2/omapfb/omapfb-ioctl.c    |  2 +-
 drivers/video/omap2/omapfb/omapfb-main.c     |  2 +-
 drivers/video/omap2/omapfb/omapfb-sysfs.c    |  2 +-
 drivers/video/omap2/vrfb.c                   |  2 +-
 include/video/omapvrfb.h                     | 66 ++++++++++++++++++++++++++++
 9 files changed, 73 insertions(+), 73 deletions(-)
 delete mode 100644 arch/arm/plat-omap/include/plat/vrfb.h
 create mode 100644 include/video/omapvrfb.h

(limited to 'include')

diff --git a/arch/arm/plat-omap/include/plat/vrfb.h b/arch/arm/plat-omap/include/plat/vrfb.h
deleted file mode 100644
index 3792bdea2f6d..000000000000
--- a/arch/arm/plat-omap/include/plat/vrfb.h
+++ /dev/null
@@ -1,66 +0,0 @@
-/*
- * VRFB Rotation Engine
- *
- * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- */
-
-#ifndef __OMAP_VRFB_H__
-#define __OMAP_VRFB_H__
-
-#define OMAP_VRFB_LINE_LEN 2048
-
-struct vrfb {
-	u8 context;
-	void __iomem *vaddr[4];
-	unsigned long paddr[4];
-	u16 xres;
-	u16 yres;
-	u16 xoffset;
-	u16 yoffset;
-	u8 bytespp;
-	bool yuv_mode;
-};
-
-#ifdef CONFIG_OMAP2_VRFB
-extern int omap_vrfb_request_ctx(struct vrfb *vrfb);
-extern void omap_vrfb_release_ctx(struct vrfb *vrfb);
-extern void omap_vrfb_adjust_size(u16 *width, u16 *height,
-		u8 bytespp);
-extern u32 omap_vrfb_min_phys_size(u16 width, u16 height, u8 bytespp);
-extern u16 omap_vrfb_max_height(u32 phys_size, u16 width, u8 bytespp);
-extern void omap_vrfb_setup(struct vrfb *vrfb, unsigned long paddr,
-		u16 width, u16 height,
-		unsigned bytespp, bool yuv_mode);
-extern int omap_vrfb_map_angle(struct vrfb *vrfb, u16 height, u8 rot);
-extern void omap_vrfb_restore_context(void);
-
-#else
-static inline int omap_vrfb_request_ctx(struct vrfb *vrfb) { return 0; }
-static inline void omap_vrfb_release_ctx(struct vrfb *vrfb) {}
-static inline void omap_vrfb_adjust_size(u16 *width, u16 *height,
-		u8 bytespp) {}
-static inline u32 omap_vrfb_min_phys_size(u16 width, u16 height, u8 bytespp)
-		{ return 0; }
-static inline u16 omap_vrfb_max_height(u32 phys_size, u16 width, u8 bytespp)
-		{ return 0; }
-static inline void omap_vrfb_setup(struct vrfb *vrfb, unsigned long paddr,
-		u16 width, u16 height, unsigned bytespp, bool yuv_mode) {}
-static inline int omap_vrfb_map_angle(struct vrfb *vrfb, u16 height, u8 rot)
-		{ return 0; }
-static inline void omap_vrfb_restore_context(void) {}
-#endif
-#endif /* __VRFB_H */
diff --git a/drivers/media/platform/omap/omap_vout.c b/drivers/media/platform/omap/omap_vout.c
index a3b1a34c896d..3ff94a30fde4 100644
--- a/drivers/media/platform/omap/omap_vout.c
+++ b/drivers/media/platform/omap/omap_vout.c
@@ -46,7 +46,7 @@
 
 #include <plat/cpu.h>
 #include <plat/dma.h>
-#include <plat/vrfb.h>
+#include <video/omapvrfb.h>
 #include <video/omapdss.h>
 
 #include "omap_voutlib.h"
diff --git a/drivers/media/platform/omap/omap_vout_vrfb.c b/drivers/media/platform/omap/omap_vout_vrfb.c
index 4be26abf6cea..6c37f9240ddf 100644
--- a/drivers/media/platform/omap/omap_vout_vrfb.c
+++ b/drivers/media/platform/omap/omap_vout_vrfb.c
@@ -17,7 +17,7 @@
 #include <media/v4l2-device.h>
 
 #include <plat/dma.h>
-#include <plat/vrfb.h>
+#include <video/omapvrfb.h>
 
 #include "omap_voutdef.h"
 #include "omap_voutlib.h"
diff --git a/drivers/media/platform/omap/omap_voutdef.h b/drivers/media/platform/omap/omap_voutdef.h
index 27a95d23b913..9ccfe1f475a4 100644
--- a/drivers/media/platform/omap/omap_voutdef.h
+++ b/drivers/media/platform/omap/omap_voutdef.h
@@ -12,7 +12,7 @@
 #define OMAP_VOUTDEF_H
 
 #include <video/omapdss.h>
-#include <plat/vrfb.h>
+#include <video/omapvrfb.h>
 
 #define YUYV_BPP        2
 #define RGB565_BPP      2
diff --git a/drivers/video/omap2/omapfb/omapfb-ioctl.c b/drivers/video/omap2/omapfb/omapfb-ioctl.c
index 606b89f12351..55a39be694a5 100644
--- a/drivers/video/omap2/omapfb/omapfb-ioctl.c
+++ b/drivers/video/omap2/omapfb/omapfb-ioctl.c
@@ -30,7 +30,7 @@
 #include <linux/export.h>
 
 #include <video/omapdss.h>
-#include <plat/vrfb.h>
+#include <video/omapvrfb.h>
 #include <plat/vram.h>
 
 #include "omapfb.h"
diff --git a/drivers/video/omap2/omapfb/omapfb-main.c b/drivers/video/omap2/omapfb/omapfb-main.c
index 16db1589bd91..5943b3a5d55a 100644
--- a/drivers/video/omap2/omapfb/omapfb-main.c
+++ b/drivers/video/omap2/omapfb/omapfb-main.c
@@ -33,7 +33,7 @@
 #include <video/omapdss.h>
 #include <plat/cpu.h>
 #include <plat/vram.h>
-#include <plat/vrfb.h>
+#include <video/omapvrfb.h>
 
 #include "omapfb.h"
 
diff --git a/drivers/video/omap2/omapfb/omapfb-sysfs.c b/drivers/video/omap2/omapfb/omapfb-sysfs.c
index e8d8cc76a435..17aa174e187c 100644
--- a/drivers/video/omap2/omapfb/omapfb-sysfs.c
+++ b/drivers/video/omap2/omapfb/omapfb-sysfs.c
@@ -30,7 +30,7 @@
 #include <linux/omapfb.h>
 
 #include <video/omapdss.h>
-#include <plat/vrfb.h>
+#include <video/omapvrfb.h>
 
 #include "omapfb.h"
 
diff --git a/drivers/video/omap2/vrfb.c b/drivers/video/omap2/vrfb.c
index fda45cc10d48..e4a0450a39a1 100644
--- a/drivers/video/omap2/vrfb.c
+++ b/drivers/video/omap2/vrfb.c
@@ -28,7 +28,7 @@
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
 
-#include <plat/vrfb.h>
+#include <video/omapvrfb.h>
 
 #ifdef DEBUG
 #define DBG(format, ...) pr_debug("VRFB: " format, ## __VA_ARGS__)
diff --git a/include/video/omapvrfb.h b/include/video/omapvrfb.h
new file mode 100644
index 000000000000..3792bdea2f6d
--- /dev/null
+++ b/include/video/omapvrfb.h
@@ -0,0 +1,66 @@
+/*
+ * VRFB Rotation Engine
+ *
+ * Copyright (C) 2009 Nokia Corporation
+ * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+
+#ifndef __OMAP_VRFB_H__
+#define __OMAP_VRFB_H__
+
+#define OMAP_VRFB_LINE_LEN 2048
+
+struct vrfb {
+	u8 context;
+	void __iomem *vaddr[4];
+	unsigned long paddr[4];
+	u16 xres;
+	u16 yres;
+	u16 xoffset;
+	u16 yoffset;
+	u8 bytespp;
+	bool yuv_mode;
+};
+
+#ifdef CONFIG_OMAP2_VRFB
+extern int omap_vrfb_request_ctx(struct vrfb *vrfb);
+extern void omap_vrfb_release_ctx(struct vrfb *vrfb);
+extern void omap_vrfb_adjust_size(u16 *width, u16 *height,
+		u8 bytespp);
+extern u32 omap_vrfb_min_phys_size(u16 width, u16 height, u8 bytespp);
+extern u16 omap_vrfb_max_height(u32 phys_size, u16 width, u8 bytespp);
+extern void omap_vrfb_setup(struct vrfb *vrfb, unsigned long paddr,
+		u16 width, u16 height,
+		unsigned bytespp, bool yuv_mode);
+extern int omap_vrfb_map_angle(struct vrfb *vrfb, u16 height, u8 rot);
+extern void omap_vrfb_restore_context(void);
+
+#else
+static inline int omap_vrfb_request_ctx(struct vrfb *vrfb) { return 0; }
+static inline void omap_vrfb_release_ctx(struct vrfb *vrfb) {}
+static inline void omap_vrfb_adjust_size(u16 *width, u16 *height,
+		u8 bytespp) {}
+static inline u32 omap_vrfb_min_phys_size(u16 width, u16 height, u8 bytespp)
+		{ return 0; }
+static inline u16 omap_vrfb_max_height(u32 phys_size, u16 width, u8 bytespp)
+		{ return 0; }
+static inline void omap_vrfb_setup(struct vrfb *vrfb, unsigned long paddr,
+		u16 width, u16 height, unsigned bytespp, bool yuv_mode) {}
+static inline int omap_vrfb_map_angle(struct vrfb *vrfb, u16 height, u8 rot)
+		{ return 0; }
+static inline void omap_vrfb_restore_context(void) {}
+#endif
+#endif /* __VRFB_H */
-- 
cgit v1.2.3-55-g7522


From aa1e49a3752f09b3d2ab706f6d48916a04acf557 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Wed, 17 Oct 2012 12:15:31 +0300
Subject: OMAPDSS: VRFB: add omap_vrfb_supported()

Add an exported function omap_vrfb_supported() which returns true if the
vrfb driver has been loaded succesfully. This can be used to decide if
VRFB can be used or not.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/omap2/vrfb.c | 16 ++++++++++++++++
 include/video/omapvrfb.h   |  2 ++
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/drivers/video/omap2/vrfb.c b/drivers/video/omap2/vrfb.c
index e4a0450a39a1..5d8fdac3b800 100644
--- a/drivers/video/omap2/vrfb.c
+++ b/drivers/video/omap2/vrfb.c
@@ -77,6 +77,8 @@ static void __iomem *vrfb_base;
 static int num_ctxs;
 static struct vrfb_ctx *ctxs;
 
+static bool vrfb_loaded;
+
 static void omap2_sms_write_rot_control(u32 val, unsigned ctx)
 {
 	__raw_writel(val, vrfb_base + SMS_ROT_CONTROL(ctx));
@@ -336,6 +338,12 @@ out:
 }
 EXPORT_SYMBOL(omap_vrfb_request_ctx);
 
+bool omap_vrfb_supported(void)
+{
+	return vrfb_loaded;
+}
+EXPORT_SYMBOL(omap_vrfb_supported);
+
 static int __init vrfb_probe(struct platform_device *pdev)
 {
 	struct resource *mem;
@@ -375,11 +383,19 @@ static int __init vrfb_probe(struct platform_device *pdev)
 		ctxs[i].base = mem->start;
 	}
 
+	vrfb_loaded = true;
+
 	return 0;
 }
 
+static void __exit vrfb_remove(struct platform_device *pdev)
+{
+	vrfb_loaded = false;
+}
+
 static struct platform_driver vrfb_driver = {
 	.driver.name	= "omapvrfb",
+	.remove		= __exit_p(vrfb_remove),
 };
 
 static int __init vrfb_init(void)
diff --git a/include/video/omapvrfb.h b/include/video/omapvrfb.h
index 3792bdea2f6d..bb0bd89f8bc6 100644
--- a/include/video/omapvrfb.h
+++ b/include/video/omapvrfb.h
@@ -36,6 +36,7 @@ struct vrfb {
 };
 
 #ifdef CONFIG_OMAP2_VRFB
+extern bool omap_vrfb_supported(void);
 extern int omap_vrfb_request_ctx(struct vrfb *vrfb);
 extern void omap_vrfb_release_ctx(struct vrfb *vrfb);
 extern void omap_vrfb_adjust_size(u16 *width, u16 *height,
@@ -49,6 +50,7 @@ extern int omap_vrfb_map_angle(struct vrfb *vrfb, u16 height, u8 rot);
 extern void omap_vrfb_restore_context(void);
 
 #else
+static inline bool omap_vrfb_supported(void) { return false; }
 static inline int omap_vrfb_request_ctx(struct vrfb *vrfb) { return 0; }
 static inline void omap_vrfb_release_ctx(struct vrfb *vrfb) {}
 static inline void omap_vrfb_adjust_size(u16 *width, u16 *height,
-- 
cgit v1.2.3-55-g7522


From 24282a1ca33b4a2cdfb907fb7a3ba4d0f6e93311 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 9 Oct 2012 15:18:59 +0530
Subject: regulator: tps65090: Register all regulators in single probe call

MFD driver registers the regulator driver once per device and
hence it is require to register all regulators in single probe
call.
Following are details of changes done to achieve this:
- Move the regulator enums to mfd header and remove the
  tps65090-regulator.h as it does not contain more info.
- Add max regulator and register all regulators even if there
  is no regulator init data from platform.
- Convert regulator init data to pointer type in platform data.
- Add input supply name in regulator desc to provide input supply.
- Separate desc information from driver information.
- Disable external control bit to have control through register write.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/regulator/tps65090-regulator.c       | 195 +++++++++++++++++++--------
 include/linux/mfd/tps65090.h                 |  28 ++++
 include/linux/regulator/tps65090-regulator.h |  50 -------
 3 files changed, 165 insertions(+), 108 deletions(-)
 delete mode 100644 include/linux/regulator/tps65090-regulator.h

(limited to 'include')

diff --git a/drivers/regulator/tps65090-regulator.c b/drivers/regulator/tps65090-regulator.c
index 001ad554ac62..5f7f9311024e 100644
--- a/drivers/regulator/tps65090-regulator.c
+++ b/drivers/regulator/tps65090-regulator.c
@@ -24,15 +24,11 @@
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
 #include <linux/mfd/tps65090.h>
-#include <linux/regulator/tps65090-regulator.h>
 
 struct tps65090_regulator {
-	int		id;
-	/* used by regulator core */
-	struct regulator_desc	desc;
-
-	/* Device */
 	struct device		*dev;
+	struct regulator_desc	*desc;
+	struct regulator_dev	*rdev;
 };
 
 static struct regulator_ops tps65090_ops = {
@@ -41,44 +37,80 @@ static struct regulator_ops tps65090_ops = {
 	.is_enabled = regulator_is_enabled_regmap,
 };
 
-#define tps65090_REG(_id)				\
+#define tps65090_REG_DESC(_id, _sname, _en_reg, _ops)	\
 {							\
-	.id		= TPS65090_ID_##_id,		\
-	.desc = {					\
-		.name = tps65090_rails(_id),		\
-		.id = TPS65090_ID_##_id,		\
-		.ops = &tps65090_ops,			\
-		.type = REGULATOR_VOLTAGE,		\
-		.owner = THIS_MODULE,			\
-		.enable_reg = (TPS65090_ID_##_id) + 12,	\
-		.enable_mask = BIT(0),			\
-	},						\
+	.name = "TPS65090_RAILS"#_id,			\
+	.supply_name = _sname,				\
+	.id = TPS65090_ID_##_id,			\
+	.ops = &_ops,					\
+	.enable_reg = _en_reg,				\
+	.enable_mask = BIT(0),				\
+	.type = REGULATOR_VOLTAGE,			\
+	.owner = THIS_MODULE,				\
 }
 
-static struct tps65090_regulator TPS65090_regulator[] = {
-	tps65090_REG(DCDC1),
-	tps65090_REG(DCDC2),
-	tps65090_REG(DCDC3),
-	tps65090_REG(FET1),
-	tps65090_REG(FET2),
-	tps65090_REG(FET3),
-	tps65090_REG(FET4),
-	tps65090_REG(FET5),
-	tps65090_REG(FET6),
-	tps65090_REG(FET7),
+static struct regulator_desc tps65090_regulator_desc[] = {
+	tps65090_REG_DESC(DCDC1, "vsys1",   0x0C, tps65090_ops),
+	tps65090_REG_DESC(DCDC2, "vsys2",   0x0D, tps65090_ops),
+	tps65090_REG_DESC(DCDC3, "vsys3",   0x0E, tps65090_ops),
+	tps65090_REG_DESC(FET1,  "infet1",  0x0F, tps65090_ops),
+	tps65090_REG_DESC(FET2,  "infet2",  0x10, tps65090_ops),
+	tps65090_REG_DESC(FET3,  "infet3",  0x11, tps65090_ops),
+	tps65090_REG_DESC(FET4,  "infet4",  0x12, tps65090_ops),
+	tps65090_REG_DESC(FET5,  "infet5",  0x13, tps65090_ops),
+	tps65090_REG_DESC(FET6,  "infet6",  0x14, tps65090_ops),
+	tps65090_REG_DESC(FET7,  "infet7",  0x15, tps65090_ops),
 };
 
-static inline struct tps65090_regulator *find_regulator_info(int id)
+static inline bool is_dcdc(int id)
 {
-	struct tps65090_regulator *ri;
-	int i;
+	switch (id) {
+	case TPS65090_ID_DCDC1:
+	case TPS65090_ID_DCDC2:
+	case TPS65090_ID_DCDC3:
+		return true;
+	default:
+		return false;
+	}
+}
 
-	for (i = 0; i < ARRAY_SIZE(TPS65090_regulator); i++) {
-		ri = &TPS65090_regulator[i];
-		if (ri->desc.id == id)
-			return ri;
+static int __devinit tps65090_config_ext_control(
+	struct tps65090_regulator *ri, bool enable)
+{
+	int ret;
+	struct device *parent = ri->dev->parent;
+	unsigned int reg_en_reg = ri->desc->enable_reg;
+
+	if (enable)
+		ret = tps65090_set_bits(parent, reg_en_reg, 1);
+	else
+		ret =  tps65090_clr_bits(parent, reg_en_reg, 1);
+	if (ret < 0)
+		dev_err(ri->dev, "Error in updating reg 0x%x\n", reg_en_reg);
+	return ret;
+}
+
+static int __devinit tps65090_regulator_disable_ext_control(
+		struct tps65090_regulator *ri,
+		struct tps65090_regulator_plat_data *tps_pdata)
+{
+	int ret = 0;
+	struct device *parent = ri->dev->parent;
+	unsigned int reg_en_reg = ri->desc->enable_reg;
+
+	/*
+	 * First enable output for internal control if require.
+	 * And then disable external control.
+	 */
+	if (tps_pdata->reg_init_data->constraints.always_on ||
+			tps_pdata->reg_init_data->constraints.boot_on) {
+		ret =  tps65090_set_bits(parent, reg_en_reg, 0);
+		if (ret < 0) {
+			dev_err(ri->dev, "Error in set reg 0x%x\n", reg_en_reg);
+			return ret;
+		}
 	}
-	return NULL;
+	return tps65090_config_ext_control(ri, false);
 }
 
 static int __devinit tps65090_regulator_probe(struct platform_device *pdev)
@@ -87,40 +119,87 @@ static int __devinit tps65090_regulator_probe(struct platform_device *pdev)
 	struct tps65090_regulator *ri = NULL;
 	struct regulator_config config = { };
 	struct regulator_dev *rdev;
-	struct tps65090_regulator_platform_data *tps_pdata;
-	int id = pdev->id;
+	struct tps65090_regulator_plat_data *tps_pdata;
+	struct tps65090_regulator *pmic;
+	struct tps65090_platform_data *tps65090_pdata;
+	int num;
+	int ret;
 
-	dev_dbg(&pdev->dev, "Probing regulator %d\n", id);
+	dev_dbg(&pdev->dev, "Probing regulator\n");
 
-	ri = find_regulator_info(id);
-	if (ri == NULL) {
-		dev_err(&pdev->dev, "invalid regulator ID specified\n");
+	tps65090_pdata = dev_get_platdata(pdev->dev.parent);
+	if (!tps65090_pdata) {
+		dev_err(&pdev->dev, "Platform data missing\n");
 		return -EINVAL;
 	}
-	tps_pdata = pdev->dev.platform_data;
-	ri->dev = &pdev->dev;
-
-	config.dev = &pdev->dev;
-	config.init_data = &tps_pdata->regulator;
-	config.driver_data = ri;
-	config.regmap = tps65090_mfd->rmap;
-
-	rdev = regulator_register(&ri->desc, &config);
-	if (IS_ERR(rdev)) {
-		dev_err(&pdev->dev, "failed to register regulator %s\n",
-				ri->desc.name);
-		return PTR_ERR(rdev);
+
+	pmic = devm_kzalloc(&pdev->dev, TPS65090_ID_MAX * sizeof(*pmic),
+			GFP_KERNEL);
+	if (!pmic) {
+		dev_err(&pdev->dev, "mem alloc for pmic failed\n");
+		return -ENOMEM;
+	}
+
+	for (num = 0; num < TPS65090_ID_MAX; num++) {
+		tps_pdata = tps65090_pdata->reg_pdata[num];
+
+		ri = &pmic[num];
+		ri->dev = &pdev->dev;
+		ri->desc = &tps65090_regulator_desc[num];
+
+		/*
+		 * TPS5090 DCDC support the control from external digital input.
+		 * It may be possible that during boot, the external control is
+		 * enabled. Disabling external control for DCDC.
+		 */
+		if (tps_pdata && is_dcdc(num) && tps_pdata->reg_init_data) {
+			ret = tps65090_regulator_disable_ext_control(
+						ri, tps_pdata);
+			if (ret < 0) {
+				dev_err(&pdev->dev,
+						"failed disable ext control\n");
+				goto scrub;
+			}
+		}
+		config.dev = &pdev->dev;
+		config.driver_data = ri;
+		config.regmap = tps65090_mfd->rmap;
+		if (tps_pdata)
+			config.init_data = tps_pdata->reg_init_data;
+		else
+			config.init_data = NULL;
+
+		rdev = regulator_register(ri->desc, &config);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "failed to register regulator %s\n",
+				ri->desc->name);
+			ret = PTR_ERR(rdev);
+			goto scrub;
+		}
+		ri->rdev = rdev;
 	}
 
-	platform_set_drvdata(pdev, rdev);
+	platform_set_drvdata(pdev, pmic);
 	return 0;
+
+scrub:
+	while (--num >= 0) {
+		ri = &pmic[num];
+		regulator_unregister(ri->rdev);
+	}
+	return ret;
 }
 
 static int __devexit tps65090_regulator_remove(struct platform_device *pdev)
 {
-	struct regulator_dev *rdev = platform_get_drvdata(pdev);
+	struct tps65090_regulator *pmic = platform_get_drvdata(pdev);
+	struct tps65090_regulator *ri;
+	int num;
 
-	regulator_unregister(rdev);
+	for (num = 0; num < TPS65090_ID_MAX; ++num) {
+		ri = &pmic[num];
+		regulator_unregister(ri->rdev);
+	}
 	return 0;
 }
 
diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h
index 6bc31d854626..d06c63335a2a 100644
--- a/include/linux/mfd/tps65090.h
+++ b/include/linux/mfd/tps65090.h
@@ -24,6 +24,23 @@
 
 #include <linux/irq.h>
 
+/* TPS65090 Regulator ID */
+enum {
+	TPS65090_ID_DCDC1,
+	TPS65090_ID_DCDC2,
+	TPS65090_ID_DCDC3,
+	TPS65090_ID_FET1,
+	TPS65090_ID_FET2,
+	TPS65090_ID_FET3,
+	TPS65090_ID_FET4,
+	TPS65090_ID_FET5,
+	TPS65090_ID_FET6,
+	TPS65090_ID_FET7,
+
+	/* Last entry for maximum ID */
+	TPS65090_ID_MAX,
+};
+
 struct tps65090 {
 	struct mutex		lock;
 	struct device		*dev;
@@ -41,10 +58,21 @@ struct tps65090_subdev_info {
 	void		*platform_data;
 };
 
+/*
+ * struct tps65090_regulator_plat_data
+ *
+ * @reg_init_data: The regulator init data.
+ */
+
+struct tps65090_regulator_plat_data {
+	struct regulator_init_data *reg_init_data;
+};
+
 struct tps65090_platform_data {
 	int irq_base;
 	int num_subdevs;
 	struct tps65090_subdev_info *subdevs;
+	struct tps65090_regulator_plat_data *reg_pdata[TPS65090_ID_MAX];
 };
 
 /*
diff --git a/include/linux/regulator/tps65090-regulator.h b/include/linux/regulator/tps65090-regulator.h
deleted file mode 100644
index 0fa04b64db3e..000000000000
--- a/include/linux/regulator/tps65090-regulator.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Regulator driver interface for TI TPS65090 PMIC family
- *
- * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
-
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
-
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
-
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __REGULATOR_TPS65090_H
-#define __REGULATOR_TPS65090_H
-
-#include <linux/regulator/machine.h>
-
-#define tps65090_rails(_name) "tps65090_"#_name
-
-enum {
-	TPS65090_ID_DCDC1,
-	TPS65090_ID_DCDC2,
-	TPS65090_ID_DCDC3,
-	TPS65090_ID_FET1,
-	TPS65090_ID_FET2,
-	TPS65090_ID_FET3,
-	TPS65090_ID_FET4,
-	TPS65090_ID_FET5,
-	TPS65090_ID_FET6,
-	TPS65090_ID_FET7,
-};
-
-/*
- * struct tps65090_regulator_platform_data
- *
- * @regulator: The regulator init data.
- * @slew_rate_uV_per_us: Slew rate microvolt per microsec.
- */
-
-struct tps65090_regulator_platform_data {
-	struct regulator_init_data regulator;
-};
-
-#endif	/* __REGULATOR_TPS65090_H */
-- 
cgit v1.2.3-55-g7522


From 8620ca9f77b71a0069a6151e859b988117ef1fa5 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 9 Oct 2012 15:19:00 +0530
Subject: regulator: tps65090: rename driver name and regulator name

To make the names proper and more appropriate:
Rename the driver name from tps65090-regulator to tps65090-pmic.
Rename the regulators from TPS65090_ID_* to TPS65090_REGULATOR_*

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/regulator/tps65090-regulator.c | 16 ++++++++--------
 include/linux/mfd/tps65090.h           | 24 ++++++++++++------------
 2 files changed, 20 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/tps65090-regulator.c b/drivers/regulator/tps65090-regulator.c
index 5f7f9311024e..584a185f89e1 100644
--- a/drivers/regulator/tps65090-regulator.c
+++ b/drivers/regulator/tps65090-regulator.c
@@ -41,7 +41,7 @@ static struct regulator_ops tps65090_ops = {
 {							\
 	.name = "TPS65090_RAILS"#_id,			\
 	.supply_name = _sname,				\
-	.id = TPS65090_ID_##_id,			\
+	.id = TPS65090_REGULATOR_##_id,			\
 	.ops = &_ops,					\
 	.enable_reg = _en_reg,				\
 	.enable_mask = BIT(0),				\
@@ -65,9 +65,9 @@ static struct regulator_desc tps65090_regulator_desc[] = {
 static inline bool is_dcdc(int id)
 {
 	switch (id) {
-	case TPS65090_ID_DCDC1:
-	case TPS65090_ID_DCDC2:
-	case TPS65090_ID_DCDC3:
+	case TPS65090_REGULATOR_DCDC1:
+	case TPS65090_REGULATOR_DCDC2:
+	case TPS65090_REGULATOR_DCDC3:
 		return true;
 	default:
 		return false;
@@ -133,14 +133,14 @@ static int __devinit tps65090_regulator_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	pmic = devm_kzalloc(&pdev->dev, TPS65090_ID_MAX * sizeof(*pmic),
+	pmic = devm_kzalloc(&pdev->dev, TPS65090_REGULATOR_MAX * sizeof(*pmic),
 			GFP_KERNEL);
 	if (!pmic) {
 		dev_err(&pdev->dev, "mem alloc for pmic failed\n");
 		return -ENOMEM;
 	}
 
-	for (num = 0; num < TPS65090_ID_MAX; num++) {
+	for (num = 0; num < TPS65090_REGULATOR_MAX; num++) {
 		tps_pdata = tps65090_pdata->reg_pdata[num];
 
 		ri = &pmic[num];
@@ -196,7 +196,7 @@ static int __devexit tps65090_regulator_remove(struct platform_device *pdev)
 	struct tps65090_regulator *ri;
 	int num;
 
-	for (num = 0; num < TPS65090_ID_MAX; ++num) {
+	for (num = 0; num < TPS65090_REGULATOR_MAX; ++num) {
 		ri = &pmic[num];
 		regulator_unregister(ri->rdev);
 	}
@@ -205,7 +205,7 @@ static int __devexit tps65090_regulator_remove(struct platform_device *pdev)
 
 static struct platform_driver tps65090_regulator_driver = {
 	.driver	= {
-		.name	= "tps65090-regulator",
+		.name	= "tps65090-pmic",
 		.owner	= THIS_MODULE,
 	},
 	.probe		= tps65090_regulator_probe,
diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h
index d06c63335a2a..958bf155097c 100644
--- a/include/linux/mfd/tps65090.h
+++ b/include/linux/mfd/tps65090.h
@@ -26,19 +26,19 @@
 
 /* TPS65090 Regulator ID */
 enum {
-	TPS65090_ID_DCDC1,
-	TPS65090_ID_DCDC2,
-	TPS65090_ID_DCDC3,
-	TPS65090_ID_FET1,
-	TPS65090_ID_FET2,
-	TPS65090_ID_FET3,
-	TPS65090_ID_FET4,
-	TPS65090_ID_FET5,
-	TPS65090_ID_FET6,
-	TPS65090_ID_FET7,
+	TPS65090_REGULATOR_DCDC1,
+	TPS65090_REGULATOR_DCDC2,
+	TPS65090_REGULATOR_DCDC3,
+	TPS65090_REGULATOR_FET1,
+	TPS65090_REGULATOR_FET2,
+	TPS65090_REGULATOR_FET3,
+	TPS65090_REGULATOR_FET4,
+	TPS65090_REGULATOR_FET5,
+	TPS65090_REGULATOR_FET6,
+	TPS65090_REGULATOR_FET7,
 
 	/* Last entry for maximum ID */
-	TPS65090_ID_MAX,
+	TPS65090_REGULATOR_MAX,
 };
 
 struct tps65090 {
@@ -72,7 +72,7 @@ struct tps65090_platform_data {
 	int irq_base;
 	int num_subdevs;
 	struct tps65090_subdev_info *subdevs;
-	struct tps65090_regulator_plat_data *reg_pdata[TPS65090_ID_MAX];
+	struct tps65090_regulator_plat_data *reg_pdata[TPS65090_REGULATOR_MAX];
 };
 
 /*
-- 
cgit v1.2.3-55-g7522


From 3a81ef8c27cea5c749a45765da4e06a7af75be2b Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 9 Oct 2012 15:19:01 +0530
Subject: regulator: tps65090: Add support for LDO regulators

TPS65090 supports the two LDOs, LDO1 and LDO2. These are
always ON regulators. The output on these LDOs are available
once the input voltage available for these LDOs.
Add support for these LDOs regulators.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/regulator/tps65090-regulator.c | 5 +++++
 include/linux/mfd/tps65090.h           | 2 ++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/drivers/regulator/tps65090-regulator.c b/drivers/regulator/tps65090-regulator.c
index 584a185f89e1..0732d9ba3f40 100644
--- a/drivers/regulator/tps65090-regulator.c
+++ b/drivers/regulator/tps65090-regulator.c
@@ -37,6 +37,9 @@ static struct regulator_ops tps65090_ops = {
 	.is_enabled = regulator_is_enabled_regmap,
 };
 
+static struct regulator_ops tps65090_ldo_ops = {
+};
+
 #define tps65090_REG_DESC(_id, _sname, _en_reg, _ops)	\
 {							\
 	.name = "TPS65090_RAILS"#_id,			\
@@ -60,6 +63,8 @@ static struct regulator_desc tps65090_regulator_desc[] = {
 	tps65090_REG_DESC(FET5,  "infet5",  0x13, tps65090_ops),
 	tps65090_REG_DESC(FET6,  "infet6",  0x14, tps65090_ops),
 	tps65090_REG_DESC(FET7,  "infet7",  0x15, tps65090_ops),
+	tps65090_REG_DESC(LDO1,  "vsys_l1", 0,    tps65090_ldo_ops),
+	tps65090_REG_DESC(LDO2,  "vsys_l2", 0,    tps65090_ldo_ops),
 };
 
 static inline bool is_dcdc(int id)
diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h
index 958bf155097c..598921221ff0 100644
--- a/include/linux/mfd/tps65090.h
+++ b/include/linux/mfd/tps65090.h
@@ -36,6 +36,8 @@ enum {
 	TPS65090_REGULATOR_FET5,
 	TPS65090_REGULATOR_FET6,
 	TPS65090_REGULATOR_FET7,
+	TPS65090_REGULATOR_LDO1,
+	TPS65090_REGULATOR_LDO2,
 
 	/* Last entry for maximum ID */
 	TPS65090_REGULATOR_MAX,
-- 
cgit v1.2.3-55-g7522


From f329b1755b475f64f0472cda1ae9602e092f6f05 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 9 Oct 2012 15:19:02 +0530
Subject: regulator: tps65090: add external control support for DCDC

The TPS65090's DCDC output can also be enable/disable through the
external digital input signal. Add support for enable/disable
either through register access via I2C or through external
control inputs. The external control inputs can be driven through
GPIOs also and hence adding support for passing the GPIO number.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/regulator/tps65090-regulator.c | 77 +++++++++++++++++++++++++---------
 include/linux/mfd/tps65090.h           |  7 +++-
 2 files changed, 63 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/tps65090-regulator.c b/drivers/regulator/tps65090-regulator.c
index 0732d9ba3f40..412413838e12 100644
--- a/drivers/regulator/tps65090-regulator.c
+++ b/drivers/regulator/tps65090-regulator.c
@@ -18,6 +18,7 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/gpio.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/platform_device.h>
@@ -31,10 +32,13 @@ struct tps65090_regulator {
 	struct regulator_dev	*rdev;
 };
 
-static struct regulator_ops tps65090_ops = {
-	.enable = regulator_enable_regmap,
-	.disable = regulator_disable_regmap,
-	.is_enabled = regulator_is_enabled_regmap,
+static struct regulator_ops tps65090_ext_control_ops = {
+};
+
+static struct regulator_ops tps65090_reg_contol_ops = {
+	.enable		= regulator_enable_regmap,
+	.disable	= regulator_disable_regmap,
+	.is_enabled	= regulator_is_enabled_regmap,
 };
 
 static struct regulator_ops tps65090_ldo_ops = {
@@ -53,16 +57,16 @@ static struct regulator_ops tps65090_ldo_ops = {
 }
 
 static struct regulator_desc tps65090_regulator_desc[] = {
-	tps65090_REG_DESC(DCDC1, "vsys1",   0x0C, tps65090_ops),
-	tps65090_REG_DESC(DCDC2, "vsys2",   0x0D, tps65090_ops),
-	tps65090_REG_DESC(DCDC3, "vsys3",   0x0E, tps65090_ops),
-	tps65090_REG_DESC(FET1,  "infet1",  0x0F, tps65090_ops),
-	tps65090_REG_DESC(FET2,  "infet2",  0x10, tps65090_ops),
-	tps65090_REG_DESC(FET3,  "infet3",  0x11, tps65090_ops),
-	tps65090_REG_DESC(FET4,  "infet4",  0x12, tps65090_ops),
-	tps65090_REG_DESC(FET5,  "infet5",  0x13, tps65090_ops),
-	tps65090_REG_DESC(FET6,  "infet6",  0x14, tps65090_ops),
-	tps65090_REG_DESC(FET7,  "infet7",  0x15, tps65090_ops),
+	tps65090_REG_DESC(DCDC1, "vsys1",   0x0C, tps65090_reg_contol_ops),
+	tps65090_REG_DESC(DCDC2, "vsys2",   0x0D, tps65090_reg_contol_ops),
+	tps65090_REG_DESC(DCDC3, "vsys3",   0x0E, tps65090_reg_contol_ops),
+	tps65090_REG_DESC(FET1,  "infet1",  0x0F, tps65090_reg_contol_ops),
+	tps65090_REG_DESC(FET2,  "infet2",  0x10, tps65090_reg_contol_ops),
+	tps65090_REG_DESC(FET3,  "infet3",  0x11, tps65090_reg_contol_ops),
+	tps65090_REG_DESC(FET4,  "infet4",  0x12, tps65090_reg_contol_ops),
+	tps65090_REG_DESC(FET5,  "infet5",  0x13, tps65090_reg_contol_ops),
+	tps65090_REG_DESC(FET6,  "infet6",  0x14, tps65090_reg_contol_ops),
+	tps65090_REG_DESC(FET7,  "infet7",  0x15, tps65090_reg_contol_ops),
 	tps65090_REG_DESC(LDO1,  "vsys_l1", 0,    tps65090_ldo_ops),
 	tps65090_REG_DESC(LDO2,  "vsys_l2", 0,    tps65090_ldo_ops),
 };
@@ -118,6 +122,22 @@ static int __devinit tps65090_regulator_disable_ext_control(
 	return tps65090_config_ext_control(ri, false);
 }
 
+static void __devinit tps65090_configure_regulator_config(
+		struct tps65090_regulator_plat_data *tps_pdata,
+		struct regulator_config *config)
+{
+	if (gpio_is_valid(tps_pdata->gpio)) {
+		int gpio_flag = GPIOF_OUT_INIT_LOW;
+
+		if (tps_pdata->reg_init_data->constraints.always_on ||
+				tps_pdata->reg_init_data->constraints.boot_on)
+			gpio_flag = GPIOF_OUT_INIT_HIGH;
+
+		config->ena_gpio = tps_pdata->gpio;
+		config->ena_gpio_flags = gpio_flag;
+	}
+}
+
 static int __devinit tps65090_regulator_probe(struct platform_device *pdev)
 {
 	struct tps65090 *tps65090_mfd = dev_get_drvdata(pdev->dev.parent);
@@ -154,18 +174,24 @@ static int __devinit tps65090_regulator_probe(struct platform_device *pdev)
 
 		/*
 		 * TPS5090 DCDC support the control from external digital input.
-		 * It may be possible that during boot, the external control is
-		 * enabled. Disabling external control for DCDC.
+		 * Configure it as per platform data.
 		 */
 		if (tps_pdata && is_dcdc(num) && tps_pdata->reg_init_data) {
-			ret = tps65090_regulator_disable_ext_control(
+			if (tps_pdata->enable_ext_control) {
+				tps65090_configure_regulator_config(
+						tps_pdata, &config);
+				ri->desc->ops = &tps65090_ext_control_ops;
+			} else {
+				ret = tps65090_regulator_disable_ext_control(
 						ri, tps_pdata);
-			if (ret < 0) {
-				dev_err(&pdev->dev,
+				if (ret < 0) {
+					dev_err(&pdev->dev,
 						"failed disable ext control\n");
-				goto scrub;
+					goto scrub;
+				}
 			}
 		}
+
 		config.dev = &pdev->dev;
 		config.driver_data = ri;
 		config.regmap = tps65090_mfd->rmap;
@@ -182,6 +208,17 @@ static int __devinit tps65090_regulator_probe(struct platform_device *pdev)
 			goto scrub;
 		}
 		ri->rdev = rdev;
+
+		/* Enable external control if it is require */
+		if (tps_pdata && is_dcdc(num) && tps_pdata->reg_init_data &&
+				tps_pdata->enable_ext_control) {
+			ret = tps65090_config_ext_control(ri, true);
+			if (ret < 0) {
+				/* Increment num to get unregister rdev */
+				num++;
+				goto scrub;
+			}
+		}
 	}
 
 	platform_set_drvdata(pdev, pmic);
diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h
index 598921221ff0..804e280c1e1d 100644
--- a/include/linux/mfd/tps65090.h
+++ b/include/linux/mfd/tps65090.h
@@ -64,10 +64,15 @@ struct tps65090_subdev_info {
  * struct tps65090_regulator_plat_data
  *
  * @reg_init_data: The regulator init data.
+ * @enable_ext_control: Enable extrenal control or not. Only available for
+ *     DCDC1, DCDC2 and DCDC3.
+ * @gpio: Gpio number if external control is enabled and controlled through
+ *     gpio.
  */
-
 struct tps65090_regulator_plat_data {
 	struct regulator_init_data *reg_init_data;
+	bool enable_ext_control;
+	int gpio;
 };
 
 struct tps65090_platform_data {
-- 
cgit v1.2.3-55-g7522


From a8f7445c7b0d2b7a523e521e2d14974804910ad0 Mon Sep 17 00:00:00 2001
From: Tony Lindgren
Date: Tue, 2 Oct 2012 14:12:31 -0700
Subject: ARM: OMAP: Move plat/led.h to include/linux/platform_data

We need to move this away from plat for ARM common
zImage support.

Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap1/board-palmtt.c      |  2 +-
 arch/arm/mach-omap2/board-apollon.c     |  2 +-
 arch/arm/plat-omap/include/plat/led.h   | 24 ------------------------
 include/linux/platform_data/leds-omap.h | 22 ++++++++++++++++++++++
 4 files changed, 24 insertions(+), 26 deletions(-)
 delete mode 100644 arch/arm/plat-omap/include/plat/led.h
 create mode 100644 include/linux/platform_data/leds-omap.h

(limited to 'include')

diff --git a/arch/arm/mach-omap1/board-palmtt.c b/arch/arm/mach-omap1/board-palmtt.c
index b1d2e802fec0..09c2418e947d 100644
--- a/arch/arm/mach-omap1/board-palmtt.c
+++ b/arch/arm/mach-omap1/board-palmtt.c
@@ -28,12 +28,12 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
 #include <linux/platform_data/omap1_bl.h>
+#include <linux/platform_data/leds-omap.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <plat/led.h>
 #include <mach/flash.h>
 #include <mach/mux.h>
 #include <plat-omap/dma-omap.h>
diff --git a/arch/arm/mach-omap2/board-apollon.c b/arch/arm/mach-omap2/board-apollon.c
index 8cdd18699de6..64cf1bde0f3b 100644
--- a/arch/arm/mach-omap2/board-apollon.c
+++ b/arch/arm/mach-omap2/board-apollon.c
@@ -28,12 +28,12 @@
 #include <linux/clk.h>
 #include <linux/smc91x.h>
 #include <linux/gpio.h>
+#include <linux/platform_data/leds-omap.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 
-#include <plat/led.h>
 #include "common.h"
 #include "gpmc.h"
 
diff --git a/arch/arm/plat-omap/include/plat/led.h b/arch/arm/plat-omap/include/plat/led.h
deleted file mode 100644
index 25e451e7e2fd..000000000000
--- a/arch/arm/plat-omap/include/plat/led.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- *  arch/arm/plat-omap/include/mach/led.h
- *
- *  Copyright (C) 2006 Samsung Electronics
- *  Kyungmin Park <kyungmin.park@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef ASMARM_ARCH_LED_H
-#define ASMARM_ARCH_LED_H
-
-struct omap_led_config {
-	struct led_classdev	cdev;
-	s16			gpio;
-};
-
-struct omap_led_platform_data {
-	s16			nr_leds;
-	struct omap_led_config	*leds;
-};
-
-#endif
diff --git a/include/linux/platform_data/leds-omap.h b/include/linux/platform_data/leds-omap.h
new file mode 100644
index 000000000000..56c9b2a0ada5
--- /dev/null
+++ b/include/linux/platform_data/leds-omap.h
@@ -0,0 +1,22 @@
+/*
+ *  Copyright (C) 2006 Samsung Electronics
+ *  Kyungmin Park <kyungmin.park@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ASMARM_ARCH_LED_H
+#define ASMARM_ARCH_LED_H
+
+struct omap_led_config {
+	struct led_classdev	cdev;
+	s16			gpio;
+};
+
+struct omap_led_platform_data {
+	s16			nr_leds;
+	struct omap_led_config	*leds;
+};
+
+#endif
-- 
cgit v1.2.3-55-g7522


From d7d4eeddb8f72342f70621c4b3cb718af9361712 Mon Sep 17 00:00:00 2001
From: Chris Wilson
Date: Wed, 17 Oct 2012 12:09:54 +0100
Subject: drm/i915: Allow DRM_ROOT_ONLY|DRM_MASTER to submit privileged
 batchbuffers

With the introduction of per-process GTT space, the hardware designers
thought it wise to also limit the ability to write to MMIO space to only
a "secure" batch buffer. The ability to rewrite registers is the only
way to program the hardware to perform certain operations like scanline
waits (required for tear-free windowed updates). So we either have a
choice of adding an interface to perform those synchronized updates
inside the kernel, or we permit certain processes the ability to write
to the "safe" registers from within its command stream. This patch
exposes the ability to submit a SECURE batch buffer to
DRM_ROOT_ONLY|DRM_MASTER processes.

v2: Haswell split up bit8 into a ppgtt bit (still bit8) and a security
bit (bit 13, accidentally not set). Also add a comment explaining why
secure batches need a global gtt binding.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> (v1)
[danvet: added hsw fixup.]
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c            |  3 ++
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 25 ++++++++++++++--
 drivers/gpu/drm/i915/i915_reg.h            |  7 +++--
 drivers/gpu/drm/i915/i915_trace.h          | 10 ++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c    | 48 ++++++++++++++++++++++++------
 drivers/gpu/drm/i915/intel_ringbuffer.h    |  4 ++-
 include/drm/i915_drm.h                     |  6 ++++
 7 files changed, 84 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 491394fd94cd..14271aab72bb 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1015,6 +1015,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_PRIME_VMAP_FLUSH:
 		value = 1;
 		break;
+	case I915_PARAM_HAS_SECURE_BATCHES:
+		value = capable(CAP_SYS_ADMIN);
+		break;
 	default:
 		DRM_DEBUG_DRIVER("Unknown parameter %d\n",
 				 param->param);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 6a2f3e50c714..afbc9240a992 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -801,6 +801,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	u32 exec_start, exec_len;
 	u32 seqno;
 	u32 mask;
+	u32 flags;
 	int ret, mode, i;
 
 	if (!i915_gem_check_execbuffer(args)) {
@@ -812,6 +813,14 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	if (ret)
 		return ret;
 
+	flags = 0;
+	if (args->flags & I915_EXEC_SECURE) {
+		if (!file->is_master || !capable(CAP_SYS_ADMIN))
+		    return -EPERM;
+
+		flags |= I915_DISPATCH_SECURE;
+	}
+
 	switch (args->flags & I915_EXEC_RING_MASK) {
 	case I915_EXEC_DEFAULT:
 	case I915_EXEC_RENDER:
@@ -984,6 +993,13 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	}
 	batch_obj->base.pending_read_domains |= I915_GEM_DOMAIN_COMMAND;
 
+	/* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
+	 * batch" bit. Hence we need to pin secure batches into the global gtt.
+	 * hsw should have this fixed, but let's be paranoid and do it
+	 * unconditionally for now. */
+	if (flags & I915_DISPATCH_SECURE && !batch_obj->has_global_gtt_mapping)
+		i915_gem_gtt_bind_object(batch_obj, batch_obj->cache_level);
+
 	ret = i915_gem_execbuffer_move_to_gpu(ring, &objects);
 	if (ret)
 		goto err;
@@ -1029,7 +1045,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			goto err;
 	}
 
-	trace_i915_gem_ring_dispatch(ring, seqno);
+	trace_i915_gem_ring_dispatch(ring, seqno, flags);
 
 	exec_start = batch_obj->gtt_offset + args->batch_start_offset;
 	exec_len = args->batch_len;
@@ -1041,12 +1057,15 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 				goto err;
 
 			ret = ring->dispatch_execbuffer(ring,
-							exec_start, exec_len);
+							exec_start, exec_len,
+							flags);
 			if (ret)
 				goto err;
 		}
 	} else {
-		ret = ring->dispatch_execbuffer(ring, exec_start, exec_len);
+		ret = ring->dispatch_execbuffer(ring,
+						exec_start, exec_len,
+						flags);
 		if (ret)
 			goto err;
 	}
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index d7f516c4855a..455beb4f690f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -244,8 +244,11 @@
 #define   MI_INVALIDATE_TLB	(1<<18)
 #define   MI_INVALIDATE_BSD	(1<<7)
 #define MI_BATCH_BUFFER		MI_INSTR(0x30, 1)
-#define   MI_BATCH_NON_SECURE	(1)
-#define   MI_BATCH_NON_SECURE_I965 (1<<8)
+#define   MI_BATCH_NON_SECURE		(1)
+/* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */
+#define   MI_BATCH_NON_SECURE_I965 	(1<<8)
+#define   MI_BATCH_PPGTT_HSW		(1<<8)
+#define   MI_BATCH_NON_SECURE_HSW 	(1<<13)
 #define MI_BATCH_BUFFER_START	MI_INSTR(0x31, 0)
 #define   MI_BATCH_GTT		    (2<<6) /* aliased with (1<<7) on gen4 */
 #define MI_SEMAPHORE_MBOX	MI_INSTR(0x16, 1) /* gen6+ */
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 8134421b89a6..3db4a6817713 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -229,24 +229,26 @@ TRACE_EVENT(i915_gem_evict_everything,
 );
 
 TRACE_EVENT(i915_gem_ring_dispatch,
-	    TP_PROTO(struct intel_ring_buffer *ring, u32 seqno),
-	    TP_ARGS(ring, seqno),
+	    TP_PROTO(struct intel_ring_buffer *ring, u32 seqno, u32 flags),
+	    TP_ARGS(ring, seqno, flags),
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, ring)
 			     __field(u32, seqno)
+			     __field(u32, flags)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->dev = ring->dev->primary->index;
 			   __entry->ring = ring->id;
 			   __entry->seqno = seqno;
+			   __entry->flags = flags;
 			   i915_trace_irq_get(ring, seqno);
 			   ),
 
-	    TP_printk("dev=%u, ring=%u, seqno=%u",
-		      __entry->dev, __entry->ring, __entry->seqno)
+	    TP_printk("dev=%u, ring=%u, seqno=%u, flags=%x",
+		      __entry->dev, __entry->ring, __entry->seqno, __entry->flags)
 );
 
 TRACE_EVENT(i915_gem_ring_flush,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 984a0c5fbf5d..6c6f95a534b1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -965,7 +965,9 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 }
 
 static int
-i965_dispatch_execbuffer(struct intel_ring_buffer *ring, u32 offset, u32 length)
+i965_dispatch_execbuffer(struct intel_ring_buffer *ring,
+			 u32 offset, u32 length,
+			 unsigned flags)
 {
 	int ret;
 
@@ -976,7 +978,7 @@ i965_dispatch_execbuffer(struct intel_ring_buffer *ring, u32 offset, u32 length)
 	intel_ring_emit(ring,
 			MI_BATCH_BUFFER_START |
 			MI_BATCH_GTT |
-			MI_BATCH_NON_SECURE_I965);
+			(flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE_I965));
 	intel_ring_emit(ring, offset);
 	intel_ring_advance(ring);
 
@@ -985,7 +987,8 @@ i965_dispatch_execbuffer(struct intel_ring_buffer *ring, u32 offset, u32 length)
 
 static int
 i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
-				u32 offset, u32 len)
+				u32 offset, u32 len,
+				unsigned flags)
 {
 	int ret;
 
@@ -994,7 +997,7 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 		return ret;
 
 	intel_ring_emit(ring, MI_BATCH_BUFFER);
-	intel_ring_emit(ring, offset | MI_BATCH_NON_SECURE);
+	intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
 	intel_ring_emit(ring, offset + len - 8);
 	intel_ring_emit(ring, 0);
 	intel_ring_advance(ring);
@@ -1004,7 +1007,8 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 
 static int
 i915_dispatch_execbuffer(struct intel_ring_buffer *ring,
-				u32 offset, u32 len)
+			 u32 offset, u32 len,
+			 unsigned flags)
 {
 	int ret;
 
@@ -1013,7 +1017,7 @@ i915_dispatch_execbuffer(struct intel_ring_buffer *ring,
 		return ret;
 
 	intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_GTT);
-	intel_ring_emit(ring, offset | MI_BATCH_NON_SECURE);
+	intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
 	intel_ring_advance(ring);
 
 	return 0;
@@ -1402,9 +1406,31 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring,
 	return 0;
 }
 
+static int
+hsw_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
+			      u32 offset, u32 len,
+			      unsigned flags)
+{
+	int ret;
+
+	ret = intel_ring_begin(ring, 2);
+	if (ret)
+		return ret;
+
+	intel_ring_emit(ring,
+			MI_BATCH_BUFFER_START | MI_BATCH_PPGTT_HSW |
+			(flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE_HSW));
+	/* bit0-7 is the length on GEN6+ */
+	intel_ring_emit(ring, offset);
+	intel_ring_advance(ring);
+
+	return 0;
+}
+
 static int
 gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			      u32 offset, u32 len)
+			      u32 offset, u32 len,
+			      unsigned flags)
 {
 	int ret;
 
@@ -1412,7 +1438,9 @@ gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 	if (ret)
 		return ret;
 
-	intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_NON_SECURE_I965);
+	intel_ring_emit(ring,
+			MI_BATCH_BUFFER_START |
+			(flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE_I965));
 	/* bit0-7 is the length on GEN6+ */
 	intel_ring_emit(ring, offset);
 	intel_ring_advance(ring);
@@ -1491,7 +1519,9 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->irq_enable_mask = I915_USER_INTERRUPT;
 	}
 	ring->write_tail = ring_write_tail;
-	if (INTEL_INFO(dev)->gen >= 6)
+	if (IS_HASWELL(dev))
+		ring->dispatch_execbuffer = hsw_ring_dispatch_execbuffer;
+	else if (INTEL_INFO(dev)->gen >= 6)
 		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 	else if (INTEL_INFO(dev)->gen >= 4)
 		ring->dispatch_execbuffer = i965_dispatch_execbuffer;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 2ea7a311a1f0..3745d1dc1fa1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -81,7 +81,9 @@ struct  intel_ring_buffer {
 	u32		(*get_seqno)(struct intel_ring_buffer *ring,
 				     bool lazy_coherency);
 	int		(*dispatch_execbuffer)(struct intel_ring_buffer *ring,
-					       u32 offset, u32 length);
+					       u32 offset, u32 length,
+					       unsigned flags);
+#define I915_DISPATCH_SECURE 0x1
 	void		(*cleanup)(struct intel_ring_buffer *ring);
 	int		(*sync_to)(struct intel_ring_buffer *ring,
 				   struct intel_ring_buffer *to,
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index c8833009f37b..0e6e135f5397 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -314,6 +314,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_SEMAPHORES	 20
 #define I915_PARAM_HAS_PRIME_VMAP_FLUSH	 21
 #define I915_PARAM_RSVD_FOR_FUTURE_USE	 22
+#define I915_PARAM_HAS_SECURE_BATCHES	 23
 
 typedef struct drm_i915_getparam {
 	int param;
@@ -679,6 +680,11 @@ struct drm_i915_gem_execbuffer2 {
 /** Resets the SO write offset registers for transform feedback on gen7. */
 #define I915_EXEC_GEN7_SOL_RESET	(1<<8)
 
+/** Request a privileged ("secure") batch buffer. Note only available for
+ * DRM_ROOT_ONLY | DRM_MASTER processes.
+ */
+#define I915_EXEC_SECURE		(1<<9)
+
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
 	(eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK
-- 
cgit v1.2.3-55-g7522


From ed47377154310fd2fd59d75fcdeb3d022344fb31 Mon Sep 17 00:00:00 2001
From: Sam Leffler
Date: Thu, 11 Oct 2012 21:03:31 -0700
Subject: {nl,cfg}80211: add a flags word to scan requests

Add a flags word to direct and scheduled scan requests; it will
be used for control of optional behaviours such as flushing the
bss cache prior to doing a scan.

Signed-off-by: Sam Leffler <sleffler@chromium.org>
Tested-by: Amitkumar Karwar <akarwar@marvell.com>
Signed-off-by: Amitkumar Karwar <akarwar@marvell.com>
Signed-off-by: Bing Zhao <bzhao@marvell.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  4 ++++
 include/uapi/linux/nl80211.h | 15 +++++++++++++++
 net/wireless/nl80211.c       | 12 ++++++++++++
 3 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 607b5c02f740..d95da8f55f6e 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1002,6 +1002,7 @@ struct cfg80211_ssid {
  * @n_channels: total number of channels to scan
  * @ie: optional information element(s) to add into Probe Request or %NULL
  * @ie_len: length of ie in octets
+ * @flags: bit field of flags controlling operation
  * @rates: bitmap of rates to advertise for each band
  * @wiphy: the wiphy this was for
  * @wdev: the wireless device to scan for
@@ -1014,6 +1015,7 @@ struct cfg80211_scan_request {
 	u32 n_channels;
 	const u8 *ie;
 	size_t ie_len;
+	u32 flags;
 
 	u32 rates[IEEE80211_NUM_BANDS];
 
@@ -1046,6 +1048,7 @@ struct cfg80211_match_set {
  * @interval: interval between each scheduled scan cycle
  * @ie: optional information element(s) to add into Probe Request or %NULL
  * @ie_len: length of ie in octets
+ * @flags: bit field of flags controlling operation
  * @match_sets: sets of parameters to be matched for a scan result
  * 	entry to be considered valid and to be passed to the host
  * 	(others are filtered out).
@@ -1063,6 +1066,7 @@ struct cfg80211_sched_scan_request {
 	u32 interval;
 	const u8 *ie;
 	size_t ie_len;
+	u32 flags;
 	struct cfg80211_match_set *match_sets;
 	int n_match_sets;
 	s32 rssi_thold;
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 71ab23b0356d..4d0b49ee4c2c 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1279,6 +1279,8 @@ enum nl80211_commands {
  * @NL80211_ATTR_VHT_CAPABILITY: VHT Capability information element (from
  *	association request when used with NL80211_CMD_NEW_STATION)
  *
+ * @NL80211_ATTR_SCAN_FLAGS: scan request control flags (u32)
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1540,6 +1542,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_VHT_CAPABILITY,
 
+	NL80211_ATTR_SCAN_FLAGS,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -3086,4 +3090,15 @@ enum nl80211_connect_failed_reason {
 	NL80211_CONN_FAIL_BLOCKED_CLIENT,
 };
 
+/**
+ * enum nl80211_scan_flags -  scan request control flags
+ *
+ * Scan request control flags are used to control the handling
+ * of NL80211_CMD_TRIGGER_SCAN and NL80211_CMD_START_SCHED_SCAN
+ * requests.
+ * (will be filled)
+enum nl80211_scan_flags {
+};
+ */
+
 #endif /* __LINUX_NL80211_H */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ef170e982f91..dc08211c6c6b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -356,6 +356,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 },
 	[NL80211_ATTR_SAE_DATA] = { .type = NLA_BINARY, },
 	[NL80211_ATTR_VHT_CAPABILITY] = { .len = NL80211_VHT_CAPABILITY_LEN },
+	[NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 },
 };
 
 /* policy for the key attributes */
@@ -4367,6 +4368,10 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
+	if (info->attrs[NL80211_ATTR_SCAN_FLAGS])
+		request->flags = nla_get_u32(
+			info->attrs[NL80211_ATTR_SCAN_FLAGS]);
+
 	request->no_cck =
 		nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]);
 
@@ -4598,6 +4603,10 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 		       request->ie_len);
 	}
 
+	if (info->attrs[NL80211_ATTR_SCAN_FLAGS])
+		request->flags = nla_get_u32(
+			info->attrs[NL80211_ATTR_SCAN_FLAGS]);
+
 	request->dev = dev;
 	request->wiphy = &rdev->wiphy;
 	request->interval = interval;
@@ -7663,6 +7672,9 @@ static int nl80211_add_scan_req(struct sk_buff *msg,
 	    nla_put(msg, NL80211_ATTR_IE, req->ie_len, req->ie))
 		goto nla_put_failure;
 
+	if (req->flags)
+		nla_put_u32(msg, NL80211_ATTR_SCAN_FLAGS, req->flags);
+
 	return 0;
  nla_put_failure:
 	return -ENOBUFS;
-- 
cgit v1.2.3-55-g7522


From 46856bbf0f0412c12e9674df68822cb531d49327 Mon Sep 17 00:00:00 2001
From: Sam Leffler
Date: Thu, 11 Oct 2012 21:03:32 -0700
Subject: cfg80211: add scan flag to indicate its priority

Add NL80211_SCAN_FLAG_LOW_PRIORITY flag support. It tells drivers
that this is a low priority scan request, so that they can take
necessary action.
Drivers need to advertise low priority scan capability during
registration.

Signed-off-by: Sam Leffler <sleffler@chromium.org>
Tested-by: Amitkumar Karwar <akarwar@marvell.com>
Signed-off-by: Amitkumar Karwar <akarwar@marvell.com>
Signed-off-by: Bing Zhao <bzhao@marvell.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h |  8 ++++++--
 net/wireless/nl80211.c       | 16 ++++++++++++++--
 2 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 4d0b49ee4c2c..c68e15e41321 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3048,6 +3048,7 @@ enum nl80211_ap_sme_features {
  * @NL80211_FEATURE_SAE: This driver supports simultaneous authentication of
  *	equals (SAE) with user space SME (NL80211_CMD_AUTHENTICATE) in station
  *	mode
+ * @NL80211_FEATURE_LOW_PRIORITY_SCAN: This driver supports low priority scan
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -3056,6 +3057,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_CELL_BASE_REG_HINTS		= 1 << 3,
 	NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL	= 1 << 4,
 	NL80211_FEATURE_SAE				= 1 << 5,
+	NL80211_FEATURE_LOW_PRIORITY_SCAN		= 1 << 6,
 };
 
 /**
@@ -3096,9 +3098,11 @@ enum nl80211_connect_failed_reason {
  * Scan request control flags are used to control the handling
  * of NL80211_CMD_TRIGGER_SCAN and NL80211_CMD_START_SCHED_SCAN
  * requests.
- * (will be filled)
+ *
+ * @NL80211_SCAN_FLAG_LOW_PRIORITY: scan request has low priority
+ */
 enum nl80211_scan_flags {
+	NL80211_SCAN_FLAG_LOW_PRIORITY			= 1<<0,
 };
- */
 
 #endif /* __LINUX_NL80211_H */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index dc08211c6c6b..aee252d65b8f 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4368,9 +4368,15 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	if (info->attrs[NL80211_ATTR_SCAN_FLAGS])
+	if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) {
 		request->flags = nla_get_u32(
 			info->attrs[NL80211_ATTR_SCAN_FLAGS]);
+		if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
+		    !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) {
+			err = -EOPNOTSUPP;
+			goto out_free;
+		}
+	}
 
 	request->no_cck =
 		nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]);
@@ -4603,9 +4609,15 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 		       request->ie_len);
 	}
 
-	if (info->attrs[NL80211_ATTR_SCAN_FLAGS])
+	if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) {
 		request->flags = nla_get_u32(
 			info->attrs[NL80211_ATTR_SCAN_FLAGS]);
+		if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
+		    !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) {
+			err = -EOPNOTSUPP;
+			goto out_free;
+		}
+	}
 
 	request->dev = dev;
 	request->wiphy = &rdev->wiphy;
-- 
cgit v1.2.3-55-g7522


From 15d6030b4bec618742b8b9ccae9209c8f9e4a916 Mon Sep 17 00:00:00 2001
From: Sam Leffler
Date: Thu, 11 Oct 2012 21:03:34 -0700
Subject: cfg80211: add support for flushing old scan results

Add an NL80211_SCAN_FLAG_FLUSH flag that causes old bss cache
entries to be flushed on scan completion. This is useful for
collecting guaranteed fresh scan/survey result (e.g. on resume).

For normal scan, flushing only happens on successful completion
of a scan; i.e. it does not happen if the scan is aborted.
For scheduled scan, previous scan results are flushed everytime
when we get new scan results.

This feature is enabled by default. Drivers can disable it by
unsetting the NL80211_FEATURE_SCAN_FLUSH flag.

Signed-off-by: Sam Leffler <sleffler@chromium.org>
Tested-by: Amitkumar Karwar <akarwar@marvell.com>
Signed-off-by: Amitkumar Karwar <akarwar@marvell.com>
Signed-off-by: Bing Zhao <bzhao@marvell.com>
[invert polarity of feature flag to account for old kernels]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  3 ++
 include/uapi/linux/nl80211.h |  4 +++
 net/wireless/core.c          |  2 ++
 net/wireless/nl80211.c       | 14 +++++++---
 net/wireless/scan.c          | 66 ++++++++++++++++++++++++++++++--------------
 net/wireless/sme.c           |  1 +
 6 files changed, 66 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index d95da8f55f6e..aa0e4a12308c 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1005,6 +1005,7 @@ struct cfg80211_ssid {
  * @flags: bit field of flags controlling operation
  * @rates: bitmap of rates to advertise for each band
  * @wiphy: the wiphy this was for
+ * @scan_start: time (in jiffies) when the scan started
  * @wdev: the wireless device to scan for
  * @aborted: (internal) scan request was notified as aborted
  * @no_cck: used to send probe requests at non CCK rate in 2GHz band
@@ -1023,6 +1024,7 @@ struct cfg80211_scan_request {
 
 	/* internal */
 	struct wiphy *wiphy;
+	unsigned long scan_start;
 	bool aborted;
 	bool no_cck;
 
@@ -1074,6 +1076,7 @@ struct cfg80211_sched_scan_request {
 	/* internal */
 	struct wiphy *wiphy;
 	struct net_device *dev;
+	unsigned long scan_start;
 
 	/* keep last */
 	struct ieee80211_channel *channels[0];
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index c68e15e41321..0e6277a06c29 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3049,6 +3049,7 @@ enum nl80211_ap_sme_features {
  *	equals (SAE) with user space SME (NL80211_CMD_AUTHENTICATE) in station
  *	mode
  * @NL80211_FEATURE_LOW_PRIORITY_SCAN: This driver supports low priority scan
+ * @NL80211_FEATURE_SCAN_FLUSH: Scan flush is supported
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -3058,6 +3059,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL	= 1 << 4,
 	NL80211_FEATURE_SAE				= 1 << 5,
 	NL80211_FEATURE_LOW_PRIORITY_SCAN		= 1 << 6,
+	NL80211_FEATURE_SCAN_FLUSH			= 1 << 7,
 };
 
 /**
@@ -3100,9 +3102,11 @@ enum nl80211_connect_failed_reason {
  * requests.
  *
  * @NL80211_SCAN_FLAG_LOW_PRIORITY: scan request has low priority
+ * @NL80211_SCAN_FLAG_FLUSH: flush cache before scanning
  */
 enum nl80211_scan_flags {
 	NL80211_SCAN_FLAG_LOW_PRIORITY			= 1<<0,
+	NL80211_SCAN_FLAG_FLUSH				= 1<<1,
 };
 
 #endif /* __LINUX_NL80211_H */
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 443d4d7deea2..48c2ea4712e9 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -370,6 +370,8 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 	rdev->wiphy.rts_threshold = (u32) -1;
 	rdev->wiphy.coverage_class = 0;
 
+	rdev->wiphy.features = NL80211_FEATURE_SCAN_FLUSH;
+
 	return &rdev->wiphy;
 }
 EXPORT_SYMBOL(wiphy_new);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index aee252d65b8f..9e5a7206b0b4 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4371,8 +4371,10 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) {
 		request->flags = nla_get_u32(
 			info->attrs[NL80211_ATTR_SCAN_FLAGS]);
-		if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
-		    !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) {
+		if (((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
+		     !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) ||
+		    ((request->flags & NL80211_SCAN_FLAG_FLUSH) &&
+		     !(wiphy->features & NL80211_FEATURE_SCAN_FLUSH))) {
 			err = -EOPNOTSUPP;
 			goto out_free;
 		}
@@ -4383,6 +4385,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 
 	request->wdev = wdev;
 	request->wiphy = &rdev->wiphy;
+	request->scan_start = jiffies;
 
 	rdev->scan_req = request;
 	err = rdev->ops->scan(&rdev->wiphy, request);
@@ -4612,8 +4615,10 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) {
 		request->flags = nla_get_u32(
 			info->attrs[NL80211_ATTR_SCAN_FLAGS]);
-		if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
-		    !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) {
+		if (((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
+		     !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) ||
+		    ((request->flags & NL80211_SCAN_FLAG_FLUSH) &&
+		     !(wiphy->features & NL80211_FEATURE_SCAN_FLUSH))) {
 			err = -EOPNOTSUPP;
 			goto out_free;
 		}
@@ -4622,6 +4627,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	request->dev = dev;
 	request->wiphy = &rdev->wiphy;
 	request->interval = interval;
+	request->scan_start = jiffies;
 
 	err = rdev->ops->sched_scan_start(&rdev->wiphy, dev, request);
 	if (!err) {
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 20050965abca..a8d5a9a07e49 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -47,6 +47,27 @@ static void __cfg80211_unlink_bss(struct cfg80211_registered_device *dev,
 	kref_put(&bss->ref, bss_release);
 }
 
+/* must hold dev->bss_lock! */
+static void __cfg80211_bss_expire(struct cfg80211_registered_device *dev,
+				  unsigned long expire_time)
+{
+	struct cfg80211_internal_bss *bss, *tmp;
+	bool expired = false;
+
+	list_for_each_entry_safe(bss, tmp, &dev->bss_list, list) {
+		if (atomic_read(&bss->hold))
+			continue;
+		if (!time_after(expire_time, bss->ts))
+			continue;
+
+		__cfg80211_unlink_bss(dev, bss);
+		expired = true;
+	}
+
+	if (expired)
+		dev->bss_generation++;
+}
+
 void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak)
 {
 	struct cfg80211_scan_request *request;
@@ -72,10 +93,17 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak)
 	if (wdev->netdev)
 		cfg80211_sme_scan_done(wdev->netdev);
 
-	if (request->aborted)
+	if (request->aborted) {
 		nl80211_send_scan_aborted(rdev, wdev);
-	else
+	} else {
+		if (request->flags & NL80211_SCAN_FLAG_FLUSH) {
+			/* flush entries from previous scans */
+			spin_lock_bh(&rdev->bss_lock);
+			__cfg80211_bss_expire(rdev, request->scan_start);
+			spin_unlock_bh(&rdev->bss_lock);
+		}
 		nl80211_send_scan_done(rdev, wdev);
+	}
 
 #ifdef CONFIG_CFG80211_WEXT
 	if (wdev->netdev && !request->aborted) {
@@ -126,16 +154,27 @@ EXPORT_SYMBOL(cfg80211_scan_done);
 void __cfg80211_sched_scan_results(struct work_struct *wk)
 {
 	struct cfg80211_registered_device *rdev;
+	struct cfg80211_sched_scan_request *request;
 
 	rdev = container_of(wk, struct cfg80211_registered_device,
 			    sched_scan_results_wk);
 
+	request = rdev->sched_scan_req;
+
 	mutex_lock(&rdev->sched_scan_mtx);
 
 	/* we don't have sched_scan_req anymore if the scan is stopping */
-	if (rdev->sched_scan_req)
-		nl80211_send_sched_scan_results(rdev,
-						rdev->sched_scan_req->dev);
+	if (request) {
+		if (request->flags & NL80211_SCAN_FLAG_FLUSH) {
+			/* flush entries from previous scans */
+			spin_lock_bh(&rdev->bss_lock);
+			__cfg80211_bss_expire(rdev, request->scan_start);
+			spin_unlock_bh(&rdev->bss_lock);
+			request->scan_start =
+				jiffies + msecs_to_jiffies(request->interval);
+		}
+		nl80211_send_sched_scan_results(rdev, request->dev);
+	}
 
 	mutex_unlock(&rdev->sched_scan_mtx);
 }
@@ -197,23 +236,9 @@ void cfg80211_bss_age(struct cfg80211_registered_device *dev,
 	}
 }
 
-/* must hold dev->bss_lock! */
 void cfg80211_bss_expire(struct cfg80211_registered_device *dev)
 {
-	struct cfg80211_internal_bss *bss, *tmp;
-	bool expired = false;
-
-	list_for_each_entry_safe(bss, tmp, &dev->bss_list, list) {
-		if (atomic_read(&bss->hold))
-			continue;
-		if (!time_after(jiffies, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE))
-			continue;
-		__cfg80211_unlink_bss(dev, bss);
-		expired = true;
-	}
-
-	if (expired)
-		dev->bss_generation++;
+	__cfg80211_bss_expire(dev, jiffies - IEEE80211_SCAN_RESULT_EXPIRE);
 }
 
 const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len)
@@ -962,6 +987,7 @@ int cfg80211_wext_siwscan(struct net_device *dev,
 	creq->ssids = (void *)&creq->channels[n_channels];
 	creq->n_channels = n_channels;
 	creq->n_ssids = 1;
+	creq->scan_start = jiffies;
 
 	/* translate "Scan on frequencies" request */
 	i = 0;
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 055d59643616..07d717eb9e2a 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -138,6 +138,7 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev)
 
 	request->wdev = wdev;
 	request->wiphy = &rdev->wiphy;
+	request->scan_start = jiffies;
 
 	rdev->scan_req = request;
 
-- 
cgit v1.2.3-55-g7522


From c13a765bd96f4e2f52d218ee6e5c0715380eeeb8 Mon Sep 17 00:00:00 2001
From: Sujith Manoharan
Date: Fri, 12 Oct 2012 17:35:45 +0530
Subject: mac80211: Notify new IBSS network creation

Initialization of beacon transmission in IBSS mode depends
on whether a new BSS is being created or joined. When joining
an existing IBSS network, beaconing has to start only after
a TSF-sync has happened - this is explained in 11.1.4.

Introduce a new parameter in the BSS information structure to
indicate creator/joiner mode.

Signed-off-by: Sujith Manoharan <c_manoha@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  2 ++
 net/mac80211/ibss.c    | 11 ++++++++---
 2 files changed, 10 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 89d5bba28e05..71c2f9c2f5be 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -258,6 +258,7 @@ enum ieee80211_rssi_event {
  * @assoc: association status
  * @ibss_joined: indicates whether this station is part of an IBSS
  *	or not
+ * @ibss_creator: indicates if a new IBSS network is being created
  * @aid: association ID number, valid only when @assoc is true
  * @use_cts_prot: use CTS protection
  * @use_short_preamble: use 802.11b short preamble;
@@ -313,6 +314,7 @@ struct ieee80211_bss_conf {
 	const u8 *bssid;
 	/* association related data */
 	bool assoc, ibss_joined;
+	bool ibss_creator;
 	u16 aid;
 	/* erp related data */
 	bool use_cts_prot;
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index c6b1448224f2..3d5332e367f8 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -38,7 +38,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 				      const u8 *bssid, const int beacon_int,
 				      struct ieee80211_channel *chan,
 				      const u32 basic_rates,
-				      const u16 capability, u64 tsf)
+				      const u16 capability, u64 tsf,
+				      bool creator)
 {
 	struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
 	struct ieee80211_local *local = sdata->local;
@@ -71,6 +72,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	/* if merging, indicate to driver that we leave the old IBSS */
 	if (sdata->vif.bss_conf.ibss_joined) {
 		sdata->vif.bss_conf.ibss_joined = false;
+		sdata->vif.bss_conf.ibss_creator = false;
 		netif_carrier_off(sdata->dev);
 		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IBSS);
 	}
@@ -197,6 +199,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	bss_change |= BSS_CHANGED_HT;
 	bss_change |= BSS_CHANGED_IBSS;
 	sdata->vif.bss_conf.ibss_joined = true;
+	sdata->vif.bss_conf.ibss_creator = creator;
 	ieee80211_bss_info_change_notify(sdata, bss_change);
 
 	ieee80211_sta_def_wmm_params(sdata, sband->n_bitrates, supp_rates);
@@ -249,7 +252,8 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 				  cbss->channel,
 				  basic_rates,
 				  cbss->capability,
-				  cbss->tsf);
+				  cbss->tsf,
+				  false);
 }
 
 static struct sta_info *ieee80211_ibss_finish_sta(struct sta_info *sta,
@@ -734,7 +738,7 @@ static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata)
 
 	__ieee80211_sta_join_ibss(sdata, bssid, sdata->vif.bss_conf.beacon_int,
 				  ifibss->channel, ifibss->basic_rates,
-				  capability, 0);
+				  capability, 0, true);
 }
 
 /*
@@ -1198,6 +1202,7 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata)
 					lockdep_is_held(&sdata->u.ibss.mtx));
 	RCU_INIT_POINTER(sdata->u.ibss.presp, NULL);
 	sdata->vif.bss_conf.ibss_joined = false;
+	sdata->vif.bss_conf.ibss_creator = false;
 	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED |
 						BSS_CHANGED_IBSS);
 	synchronize_rcu();
-- 
cgit v1.2.3-55-g7522


From 3821b4247b40d6b95a59a2895ea6e9bd3f983f04 Mon Sep 17 00:00:00 2001
From: Arend van Spriel
Date: Fri, 12 Oct 2012 12:28:16 +0200
Subject: wireless: remove duplicate enum ieee80211_eid definitions

WLAN_EID_WPA and WLAN_EID_GENERIC mapped to the same value
as WLAN_EID_VENDOR_SPECIFIC. The last one being more in line
with the standard specification. Removing WLAN_EID_WPA and
WLAN_EID_GENERIC as there are no longer drivers using these.

Cc: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Arend van Spriel <arend@broadcom.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 8c803f0e4925..85764a900731 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1457,8 +1457,6 @@ enum ieee80211_eid {
 
 	WLAN_EID_RSN = 48,
 	WLAN_EID_MMIE = 76,
-	WLAN_EID_WPA = 221,
-	WLAN_EID_GENERIC = 221,
 	WLAN_EID_VENDOR_SPECIFIC = 221,
 	WLAN_EID_QOS_PARAMETER = 222,
 
-- 
cgit v1.2.3-55-g7522


From f706adfeade767d2194c9f39c0f75e944b0bdd23 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 18 Oct 2012 13:16:19 +0300
Subject: Bluetooth: AMP: Get amp_mgr reference in HS hci_conn

When assigning amp_mgr in hci_conn (type AMP_LINK) get also reference.
In hci_conn_del those references would be put for both conn types
AMP_LINK and ACL_LINK associated with amp_mgr.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/a2mp.h | 2 +-
 net/bluetooth/a2mp.c         | 4 +++-
 net/bluetooth/amp.c          | 2 +-
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/a2mp.h b/include/net/bluetooth/a2mp.h
index e776ab2dc572..42f21766c538 100644
--- a/include/net/bluetooth/a2mp.h
+++ b/include/net/bluetooth/a2mp.h
@@ -133,7 +133,7 @@ struct a2mp_physlink_rsp {
 extern struct list_head amp_mgr_list;
 extern struct mutex amp_mgr_list_lock;
 
-void amp_mgr_get(struct amp_mgr *mgr);
+struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr);
 int amp_mgr_put(struct amp_mgr *mgr);
 u8 __next_ident(struct amp_mgr *mgr);
 struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 7bf9a10d8e46..d5136cfb57e2 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -751,11 +751,13 @@ static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked)
 }
 
 /* AMP Manager functions */
-void amp_mgr_get(struct amp_mgr *mgr)
+struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr)
 {
 	BT_DBG("mgr %p orig refcnt %d", mgr, atomic_read(&mgr->kref.refcount));
 
 	kref_get(&mgr->kref);
+
+	return mgr;
 }
 
 static void amp_mgr_destroy(struct kref *kref)
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 59da0f15818e..231d7ef53ecb 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -123,7 +123,7 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
 	hcon->attempt++;
 	hcon->handle = __next_handle(mgr);
 	hcon->remote_id = remote_id;
-	hcon->amp_mgr = mgr;
+	hcon->amp_mgr = amp_mgr_get(mgr);
 	hcon->out = out;
 
 	return hcon;
-- 
cgit v1.2.3-55-g7522


From b9bf6882c1f9451ce1e80aaed32107673a735613 Mon Sep 17 00:00:00 2001
From: Xiao Guangrong
Date: Wed, 17 Oct 2012 13:46:52 +0800
Subject: KVM: VMX: report internal error for the unhandleable event

VM exits during Event Delivery is really unexpected if it is not caused
by Exceptions/EPT-VIOLATION/TASK_SWITCH, we'd better to report an internal
and freeze the guest, the VMM has the chance to check the guest

Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/vmx.c  | 19 +++++++++++++++----
 include/linux/kvm.h |  8 ++++++--
 2 files changed, 21 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ad6b1dd06f8b..b8a0841dfe7d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5979,13 +5979,24 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
+	/*
+	 * Note:
+	 * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by
+	 * delivery event since it indicates guest is accessing MMIO.
+	 * The vm-exit can be triggered again after return to guest that
+	 * will cause infinite loop.
+	 */
 	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
-			exit_reason != EXIT_REASON_TASK_SWITCH))
-		printk(KERN_WARNING "%s: unexpected, valid vectoring info "
-		       "(0x%x) and exit reason is 0x%x\n",
-		       __func__, vectoring_info, exit_reason);
+			exit_reason != EXIT_REASON_TASK_SWITCH)) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
+		vcpu->run->internal.ndata = 2;
+		vcpu->run->internal.data[0] = vectoring_info;
+		vcpu->run->internal.data[1] = exit_reason;
+		return 0;
+	}
 
 	if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked &&
 	    !(is_guest_mode(vcpu) && nested_cpu_has_virtual_nmis(
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 65ad5c624c70..494a84c37c3e 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -170,8 +170,12 @@ struct kvm_pit_config {
 #define KVM_EXIT_WATCHDOG         21
 
 /* For KVM_EXIT_INTERNAL_ERROR */
-#define KVM_INTERNAL_ERROR_EMULATION 1
-#define KVM_INTERNAL_ERROR_SIMUL_EX 2
+/* Emulate instruction failed. */
+#define KVM_INTERNAL_ERROR_EMULATION	1
+/* Encounter unexpected simultaneous exceptions. */
+#define KVM_INTERNAL_ERROR_SIMUL_EX	2
+/* Encounter unexpected vm-exit due to delivery event. */
+#define KVM_INTERNAL_ERROR_DELIVERY_EV	3
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
-- 
cgit v1.2.3-55-g7522


From 5c95b940bd97e744267249e3b0780e6ef04b029c Mon Sep 17 00:00:00 2001
From: Antonio Quartulli
Date: Tue, 16 Oct 2012 08:39:22 +0200
Subject: nl/cfg80211: force scan using an AP vif if requested

If the user wants to scan using a vif configured as AP,
cfg80211 must give him a chance to do it, even if this
will disrupt the stations performance due to off-channel
scanning. To do so, this patch adds a 'force' flag to the
SCAN_TRIGGER command which tells cfg80211 to perform the
scanning operation even if the vif is an AP and the
beaconing has already started.

Signed-off-by: Antonio Quartulli <ordex@autistici.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h |  8 ++++++++
 net/mac80211/cfg.c           | 11 ++++++++++-
 net/mac80211/main.c          |  4 +++-
 3 files changed, 21 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 0e6277a06c29..617d0fbfc96f 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3050,6 +3050,7 @@ enum nl80211_ap_sme_features {
  *	mode
  * @NL80211_FEATURE_LOW_PRIORITY_SCAN: This driver supports low priority scan
  * @NL80211_FEATURE_SCAN_FLUSH: Scan flush is supported
+ * @NL80211_FEATURE_AP_SCAN: Support scanning using an AP vif
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -3060,6 +3061,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_SAE				= 1 << 5,
 	NL80211_FEATURE_LOW_PRIORITY_SCAN		= 1 << 6,
 	NL80211_FEATURE_SCAN_FLUSH			= 1 << 7,
+	NL80211_FEATURE_AP_SCAN				= 1 << 8,
 };
 
 /**
@@ -3103,10 +3105,16 @@ enum nl80211_connect_failed_reason {
  *
  * @NL80211_SCAN_FLAG_LOW_PRIORITY: scan request has low priority
  * @NL80211_SCAN_FLAG_FLUSH: flush cache before scanning
+ * @NL80211_SCAN_FLAG_AP: force a scan even if the interface is configured
+ *	as AP and the beaconing has already been configured. This attribute is
+ *	dangerous because will destroy stations performance as a lot of frames
+ *	will be lost while scanning off-channel, therefore it must be used only
+ *	when really needed
  */
 enum nl80211_scan_flags {
 	NL80211_SCAN_FLAG_LOW_PRIORITY			= 1<<0,
 	NL80211_SCAN_FLAG_FLUSH				= 1<<1,
+	NL80211_SCAN_FLAG_AP				= 1<<2,
 };
 
 #endif /* __LINUX_NL80211_H */
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 5739bfbf2999..5eab1325a0f6 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1855,7 +1855,16 @@ static int ieee80211_scan(struct wiphy *wiphy,
 		 * beaconing hasn't been configured yet
 		 */
 	case NL80211_IFTYPE_AP:
-		if (sdata->u.ap.beacon)
+		/*
+		 * If the scan has been forced (and the driver supports
+		 * forcing), don't care about being beaconing already.
+		 * This will create problems to the attached stations (e.g. all
+		 * the  frames sent while scanning on other channel will be
+		 * lost)
+		 */
+		if (sdata->u.ap.beacon &&
+		    (!(wiphy->features & NL80211_FEATURE_AP_SCAN) ||
+		     !(req->flags & NL80211_SCAN_FLAG_AP)))
 			return -EOPNOTSUPP;
 		break;
 	default:
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index ba5a23249771..c42094be2f0b 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -603,7 +603,9 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 			   NL80211_FEATURE_HT_IBSS;
 
 	if (!ops->hw_scan)
-		wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN;
+		wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN |
+				   NL80211_FEATURE_AP_SCAN;
+
 
 	if (!ops->set_key)
 		wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
-- 
cgit v1.2.3-55-g7522


From b2409b65d9401f7e3c572fc59db6a920fc7a163e Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab
Date: Fri, 19 Oct 2012 07:29:17 -0300
Subject: [media] remove include/linux/dvb/dmx.h

The only reason for this header is to make sure that include
linux/time.h were added before uapi/*/dmx.h. Just push down the
time.h header on the few places where this is used, and drop
this new header.

Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/dvb-core/dmxdev.h    |  1 +
 drivers/media/firewire/firedtv.h   |  1 +
 drivers/media/pci/ttpci/av7110.h   |  1 +
 drivers/media/usb/tlg2300/pd-dvb.c |  1 +
 include/linux/dvb/dmx.h            | 29 -----------------------------
 5 files changed, 4 insertions(+), 29 deletions(-)
 delete mode 100644 include/linux/dvb/dmx.h

(limited to 'include')

diff --git a/drivers/media/dvb-core/dmxdev.h b/drivers/media/dvb-core/dmxdev.h
index 02ebe28f830d..48c6cf92ab99 100644
--- a/drivers/media/dvb-core/dmxdev.h
+++ b/drivers/media/dvb-core/dmxdev.h
@@ -26,6 +26,7 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/kernel.h>
+#include <linux/time.h>
 #include <linux/timer.h>
 #include <linux/wait.h>
 #include <linux/fs.h>
diff --git a/drivers/media/firewire/firedtv.h b/drivers/media/firewire/firedtv.h
index 4fdcd8cb7530..c2ba085e0d20 100644
--- a/drivers/media/firewire/firedtv.h
+++ b/drivers/media/firewire/firedtv.h
@@ -13,6 +13,7 @@
 #ifndef _FIREDTV_H
 #define _FIREDTV_H
 
+#include <linux/time.h>
 #include <linux/dvb/dmx.h>
 #include <linux/dvb/frontend.h>
 #include <linux/list.h>
diff --git a/drivers/media/pci/ttpci/av7110.h b/drivers/media/pci/ttpci/av7110.h
index 88b3b2d6cc0e..a378662b1dcf 100644
--- a/drivers/media/pci/ttpci/av7110.h
+++ b/drivers/media/pci/ttpci/av7110.h
@@ -6,6 +6,7 @@
 #include <linux/netdevice.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
+#include <linux/time.h>
 
 #include <linux/dvb/video.h>
 #include <linux/dvb/audio.h>
diff --git a/drivers/media/usb/tlg2300/pd-dvb.c b/drivers/media/usb/tlg2300/pd-dvb.c
index 30fcb117e898..ca4994a5190c 100644
--- a/drivers/media/usb/tlg2300/pd-dvb.c
+++ b/drivers/media/usb/tlg2300/pd-dvb.c
@@ -1,6 +1,7 @@
 #include "pd-common.h"
 #include <linux/kernel.h>
 #include <linux/usb.h>
+#include <linux/time.h>
 #include <linux/dvb/dmx.h>
 #include <linux/delay.h>
 #include <linux/gfp.h>
diff --git a/include/linux/dvb/dmx.h b/include/linux/dvb/dmx.h
deleted file mode 100644
index 0be6d8f2b52b..000000000000
--- a/include/linux/dvb/dmx.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * dmx.h
- *
- * Copyright (C) 2000 Marcus Metzler <marcus@convergence.de>
- *                  & Ralph  Metzler <ralph@convergence.de>
- *                    for convergence integrated media GmbH
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public License
- * as published by the Free Software Foundation; either version 2.1
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- */
-#ifndef _DVBDMX_H_
-#define _DVBDMX_H_
-
-#include <linux/time.h>
-#include <uapi/linux/dvb/dmx.h>
-
-#endif /*_DVBDMX_H_*/
-- 
cgit v1.2.3-55-g7522


From 74df06daf632ce2d321d01cb046004768352efc4 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab
Date: Fri, 19 Oct 2012 07:41:50 -0300
Subject: [media] Remove include/linux/dvb/ stuff

The only file left there is include/linux/dvb/video.h. The
only function for it is to include linux/compiler.h, but this
is already indirectly included. So, get rid of it.

Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 include/linux/dvb/Kbuild  |  0
 include/linux/dvb/video.h | 29 -----------------------------
 2 files changed, 29 deletions(-)
 delete mode 100644 include/linux/dvb/Kbuild
 delete mode 100644 include/linux/dvb/video.h

(limited to 'include')

diff --git a/include/linux/dvb/Kbuild b/include/linux/dvb/Kbuild
deleted file mode 100644
index e69de29bb2d1..000000000000
diff --git a/include/linux/dvb/video.h b/include/linux/dvb/video.h
deleted file mode 100644
index 85c20d925696..000000000000
--- a/include/linux/dvb/video.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * video.h
- *
- * Copyright (C) 2000 Marcus Metzler <marcus@convergence.de>
- *                  & Ralph  Metzler <ralph@convergence.de>
- *                    for convergence integrated media GmbH
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public License
- * as published by the Free Software Foundation; either version 2.1
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- */
-#ifndef _DVBVIDEO_H_
-#define _DVBVIDEO_H_
-
-#include <linux/compiler.h>
-#include <uapi/linux/dvb/video.h>
-
-#endif /*_DVBVIDEO_H_*/
-- 
cgit v1.2.3-55-g7522


From 103d9fb907058e4eb052f4f7302d1b07eb6a7792 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Tue, 16 Oct 2012 17:29:00 +0100
Subject: iio: Add a logarithmic fractional value type

For ADCs or DACs the denominator for fractional types often is a power of two.
In this case we can use a shift operation instead of the rather expensive 64 bit
division. This patch adds a new fractional type which expects the denominator to
be specified as the log2 of the actual denominator. E.g. for ADCs and DACs this
will usually be the number of significant bits.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/industrialio-core.c | 5 +++++
 drivers/iio/inkern.c            | 3 +++
 include/linux/iio/types.h       | 1 +
 3 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 6eb24dbc081e..37650a72b31f 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -397,6 +397,11 @@ static ssize_t iio_read_channel_info(struct device *dev,
 		val2 = do_div(tmp, 1000000000LL);
 		val = tmp;
 		return sprintf(buf, "%d.%09u\n", val, val2);
+	case IIO_VAL_FRACTIONAL_LOG2:
+		tmp = (s64)val * 1000000000LL >> val2;
+		val2 = do_div(tmp, 1000000000LL);
+		val = tmp;
+		return sprintf(buf, "%d.%09u\n", val, val2);
 	default:
 		return 0;
 	}
diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c
index 5230a33886c0..b394621d362c 100644
--- a/drivers/iio/inkern.c
+++ b/drivers/iio/inkern.c
@@ -314,6 +314,9 @@ static int iio_convert_raw_to_processed_unlocked(struct iio_channel *chan,
 		*processed = div_s64(raw64 * (s64)scale_val * scale,
 				     scale_val2);
 		break;
+	case IIO_VAL_FRACTIONAL_LOG2:
+		*processed = (raw64 * (s64)scale_val * scale) >> scale_val2;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index 5c647ecfd5ba..87b196a2d698 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -58,5 +58,6 @@ enum iio_modifier {
 #define IIO_VAL_INT_PLUS_NANO 3
 #define IIO_VAL_INT_PLUS_MICRO_DB 4
 #define IIO_VAL_FRACTIONAL 10
+#define IIO_VAL_FRACTIONAL_LOG2 11
 
 #endif /* _IIO_TYPES_H_ */
-- 
cgit v1.2.3-55-g7522


From 8341dc04dfb33fbae71727ae648e20c51abc40e3 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Tue, 16 Oct 2012 17:29:00 +0100
Subject: iio:dac: Add support for the ad5449

This patch adds support for the AD5415, AD5426, AD5429, AD5432, AD5439, AD5443
and AD5449 single and dual channel DACs.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/dac/Kconfig              |  10 +
 drivers/iio/dac/Makefile             |   1 +
 drivers/iio/dac/ad5449.c             | 375 +++++++++++++++++++++++++++++++++++
 include/linux/platform_data/ad5449.h |  40 ++++
 4 files changed, 426 insertions(+)
 create mode 100644 drivers/iio/dac/ad5449.c
 create mode 100644 include/linux/platform_data/ad5449.h

(limited to 'include')

diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig
index b1c0ee5294ca..f68756e6dd62 100644
--- a/drivers/iio/dac/Kconfig
+++ b/drivers/iio/dac/Kconfig
@@ -67,6 +67,16 @@ config AD5446
 	  To compile this driver as a module, choose M here: the
 	  module will be called ad5446.
 
+config AD5449
+	tristate "Analog Device AD5449 and similar DACs driver"
+	depends on SPI_MASTER
+	help
+	  Say yes here to build support for Analog Devices AD5415, AD5426, AD5429,
+	  AD5432, AD5439, AD5443, AD5449 Digital to Analog Converters.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ad5449.
+
 config AD5504
 	tristate "Analog Devices AD5504/AD5501 DAC SPI driver"
 	depends on SPI
diff --git a/drivers/iio/dac/Makefile b/drivers/iio/dac/Makefile
index c0d333b23ba3..5b528ebb3343 100644
--- a/drivers/iio/dac/Makefile
+++ b/drivers/iio/dac/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_AD5624R_SPI) += ad5624r_spi.o
 obj-$(CONFIG_AD5064) += ad5064.o
 obj-$(CONFIG_AD5504) += ad5504.o
 obj-$(CONFIG_AD5446) += ad5446.o
+obj-$(CONFIG_AD5449) += ad5449.o
 obj-$(CONFIG_AD5755) += ad5755.o
 obj-$(CONFIG_AD5764) += ad5764.o
 obj-$(CONFIG_AD5791) += ad5791.o
diff --git a/drivers/iio/dac/ad5449.c b/drivers/iio/dac/ad5449.c
new file mode 100644
index 000000000000..5b43030fe6e3
--- /dev/null
+++ b/drivers/iio/dac/ad5449.c
@@ -0,0 +1,375 @@
+/*
+ * AD5415, AD5426, AD5429, AD5432, AD5439, AD5443, AD5449 Digital to Analog
+ * Converter driver.
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/spi/spi.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/regulator/consumer.h>
+#include <asm/unaligned.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+
+#include <linux/platform_data/ad5449.h>
+
+#define AD5449_MAX_CHANNELS		2
+#define AD5449_MAX_VREFS		2
+
+#define AD5449_CMD_NOOP			0x0
+#define AD5449_CMD_LOAD_AND_UPDATE(x)	(0x1 + (x) * 3)
+#define AD5449_CMD_READ(x)		(0x2 + (x) * 3)
+#define AD5449_CMD_LOAD(x)		(0x3 + (x) * 3)
+#define AD5449_CMD_CTRL			13
+
+#define AD5449_CTRL_SDO_OFFSET		10
+#define AD5449_CTRL_DAISY_CHAIN		BIT(9)
+#define AD5449_CTRL_HCLR_TO_MIDSCALE	BIT(8)
+#define AD5449_CTRL_SAMPLE_RISING	BIT(7)
+
+/**
+ * struct ad5449_chip_info - chip specific information
+ * @channels:		Channel specification
+ * @num_channels:	Number of channels
+ * @has_ctrl:		Chip has a control register
+ */
+struct ad5449_chip_info {
+	const struct iio_chan_spec *channels;
+	unsigned int num_channels;
+	bool has_ctrl;
+};
+
+/**
+ * struct ad5449 - driver instance specific data
+ * @spi:		the SPI device for this driver instance
+ * @chip_info:		chip model specific constants, available modes etc
+ * @vref_reg:		vref supply regulators
+ * @has_sdo:		whether the SDO line is connected
+ * @dac_cache:		Cache for the DAC values
+ * @data:		spi transfer buffers
+ */
+struct ad5449 {
+	struct spi_device		*spi;
+	const struct ad5449_chip_info	*chip_info;
+	struct regulator_bulk_data	vref_reg[AD5449_MAX_VREFS];
+
+	bool has_sdo;
+	uint16_t dac_cache[AD5449_MAX_CHANNELS];
+
+	/*
+	 * DMA (thus cache coherency maintenance) requires the
+	 * transfer buffers to live in their own cache lines.
+	 */
+	__be16 data[2] ____cacheline_aligned;
+};
+
+enum ad5449_type {
+	ID_AD5426,
+	ID_AD5429,
+	ID_AD5432,
+	ID_AD5439,
+	ID_AD5443,
+	ID_AD5449,
+};
+
+static int ad5449_write(struct iio_dev *indio_dev, unsigned int addr,
+	unsigned int val)
+{
+	struct ad5449 *st = iio_priv(indio_dev);
+	int ret;
+
+	mutex_lock(&indio_dev->mlock);
+	st->data[0] = cpu_to_be16((addr << 12) | val);
+	ret = spi_write(st->spi, st->data, 2);
+	mutex_unlock(&indio_dev->mlock);
+
+	return ret;
+}
+
+static int ad5449_read(struct iio_dev *indio_dev, unsigned int addr,
+	unsigned int *val)
+{
+	struct ad5449 *st = iio_priv(indio_dev);
+	int ret;
+	struct spi_message msg;
+	struct spi_transfer t[] = {
+		{
+			.tx_buf = &st->data[0],
+			.len = 2,
+			.cs_change = 1,
+		}, {
+			.tx_buf = &st->data[1],
+			.rx_buf = &st->data[1],
+			.len = 2,
+		},
+	};
+
+	spi_message_init(&msg);
+	spi_message_add_tail(&t[0], &msg);
+	spi_message_add_tail(&t[1], &msg);
+
+	mutex_lock(&indio_dev->mlock);
+	st->data[0] = cpu_to_be16(addr << 12);
+	st->data[1] = cpu_to_be16(AD5449_CMD_NOOP);
+
+	ret = spi_sync(st->spi, &msg);
+	if (ret < 0)
+		return ret;
+
+	*val = be16_to_cpu(st->data[1]);
+	mutex_unlock(&indio_dev->mlock);
+
+	return 0;
+}
+
+static int ad5449_read_raw(struct iio_dev *indio_dev,
+	struct iio_chan_spec const *chan, int *val, int *val2, long info)
+{
+	struct ad5449 *st = iio_priv(indio_dev);
+	struct regulator_bulk_data *reg;
+	int scale_uv;
+	int ret;
+
+	switch (info) {
+	case IIO_CHAN_INFO_RAW:
+		if (st->has_sdo) {
+			ret = ad5449_read(indio_dev,
+				AD5449_CMD_READ(chan->address), val);
+			if (ret)
+				return ret;
+			*val &= 0xfff;
+		} else {
+			*val = st->dac_cache[chan->address];
+		}
+
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		reg = &st->vref_reg[chan->channel];
+		scale_uv = regulator_get_voltage(reg->consumer);
+		if (scale_uv < 0)
+			return scale_uv;
+
+		*val = scale_uv / 1000;
+		*val2 = chan->scan_type.realbits;
+
+		return IIO_VAL_FRACTIONAL_LOG2;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static int ad5449_write_raw(struct iio_dev *indio_dev,
+	struct iio_chan_spec const *chan, int val, int val2, long info)
+{
+	struct ad5449 *st = iio_priv(indio_dev);
+	int ret;
+
+	switch (info) {
+	case IIO_CHAN_INFO_RAW:
+		if (val < 0 || val >= (1 << chan->scan_type.realbits))
+			return -EINVAL;
+
+		ret = ad5449_write(indio_dev,
+			AD5449_CMD_LOAD_AND_UPDATE(chan->address),
+			val << chan->scan_type.shift);
+		if (ret == 0)
+			st->dac_cache[chan->address] = val;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static const struct iio_info ad5449_info = {
+	.read_raw = ad5449_read_raw,
+	.write_raw = ad5449_write_raw,
+	.driver_module = THIS_MODULE,
+};
+
+#define AD5449_CHANNEL(chan, bits) {				\
+	.type = IIO_VOLTAGE,					\
+	.indexed = 1,						\
+	.output = 1,						\
+	.channel = (chan),					\
+	.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT |		\
+		IIO_CHAN_INFO_SCALE_SEPARATE_BIT,		\
+	.address = (chan),					\
+	.scan_type = IIO_ST('u', (bits), 16, 12 - (bits)),	\
+}
+
+#define DECLARE_AD5449_CHANNELS(name, bits) \
+const struct iio_chan_spec name[] = { \
+	AD5449_CHANNEL(0, bits), \
+	AD5449_CHANNEL(1, bits), \
+}
+
+static DECLARE_AD5449_CHANNELS(ad5429_channels, 8);
+static DECLARE_AD5449_CHANNELS(ad5439_channels, 10);
+static DECLARE_AD5449_CHANNELS(ad5449_channels, 12);
+
+static const struct ad5449_chip_info ad5449_chip_info[] = {
+	[ID_AD5426] = {
+		.channels = ad5429_channels,
+		.num_channels = 1,
+		.has_ctrl = false,
+	},
+	[ID_AD5429] = {
+		.channels = ad5429_channels,
+		.num_channels = 2,
+		.has_ctrl = true,
+	},
+	[ID_AD5432] = {
+		.channels = ad5439_channels,
+		.num_channels = 1,
+		.has_ctrl = false,
+	},
+	[ID_AD5439] = {
+		.channels = ad5439_channels,
+		.num_channels = 2,
+		.has_ctrl = true,
+	},
+	[ID_AD5443] = {
+		.channels = ad5449_channels,
+		.num_channels = 1,
+		.has_ctrl = false,
+	},
+	[ID_AD5449] = {
+		.channels = ad5449_channels,
+		.num_channels = 2,
+		.has_ctrl = true,
+	},
+};
+
+static const char *ad5449_vref_name(struct ad5449 *st, int n)
+{
+	if (st->chip_info->num_channels == 1)
+		return "VREF";
+
+	if (n == 0)
+		return "VREFA";
+	else
+		return "VREFB";
+}
+
+static int __devinit ad5449_spi_probe(struct spi_device *spi)
+{
+	struct ad5449_platform_data *pdata = spi->dev.platform_data;
+	const struct spi_device_id *id = spi_get_device_id(spi);
+	struct iio_dev *indio_dev;
+	struct ad5449 *st;
+	unsigned int i;
+	int ret;
+
+	indio_dev = iio_device_alloc(sizeof(*st));
+	if (indio_dev == NULL)
+		return -ENOMEM;
+
+	st = iio_priv(indio_dev);
+	spi_set_drvdata(spi, indio_dev);
+
+	st->chip_info = &ad5449_chip_info[id->driver_data];
+	st->spi = spi;
+
+	for (i = 0; i < st->chip_info->num_channels; ++i)
+		st->vref_reg[i].supply = ad5449_vref_name(st, i);
+
+	ret = regulator_bulk_get(&spi->dev, st->chip_info->num_channels,
+				st->vref_reg);
+	if (ret)
+		goto error_free;
+
+	ret = regulator_bulk_enable(st->chip_info->num_channels, st->vref_reg);
+	if (ret)
+		goto error_free_reg;
+
+	indio_dev->dev.parent = &spi->dev;
+	indio_dev->name = id->name;
+	indio_dev->info = &ad5449_info;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = st->chip_info->channels;
+	indio_dev->num_channels = st->chip_info->num_channels;
+
+	if (st->chip_info->has_ctrl) {
+		unsigned int ctrl = 0x00;
+		if (pdata) {
+			if (pdata->hardware_clear_to_midscale)
+				ctrl |= AD5449_CTRL_HCLR_TO_MIDSCALE;
+			ctrl |= pdata->sdo_mode << AD5449_CTRL_SDO_OFFSET;
+			st->has_sdo = pdata->sdo_mode != AD5449_SDO_DISABLED;
+		} else {
+			st->has_sdo = true;
+		}
+		ad5449_write(indio_dev, AD5449_CMD_CTRL, ctrl);
+	}
+
+	ret = iio_device_register(indio_dev);
+	if (ret)
+		goto error_disable_reg;
+
+	return 0;
+
+error_disable_reg:
+	regulator_bulk_disable(st->chip_info->num_channels, st->vref_reg);
+error_free_reg:
+	regulator_bulk_free(st->chip_info->num_channels, st->vref_reg);
+error_free:
+	iio_device_free(indio_dev);
+
+	return ret;
+}
+
+static int __devexit ad5449_spi_remove(struct spi_device *spi)
+{
+	struct iio_dev *indio_dev = spi_get_drvdata(spi);
+	struct ad5449 *st = iio_priv(indio_dev);
+
+	iio_device_unregister(indio_dev);
+
+	regulator_bulk_disable(st->chip_info->num_channels, st->vref_reg);
+	regulator_bulk_free(st->chip_info->num_channels, st->vref_reg);
+
+	iio_device_free(indio_dev);
+
+	return 0;
+}
+
+static const struct spi_device_id ad5449_spi_ids[] = {
+	{ "ad5415", ID_AD5449 },
+	{ "ad5426", ID_AD5426 },
+	{ "ad5429", ID_AD5429 },
+	{ "ad5432", ID_AD5432 },
+	{ "ad5439", ID_AD5439 },
+	{ "ad5443", ID_AD5443 },
+	{ "ad5449", ID_AD5449 },
+	{}
+};
+MODULE_DEVICE_TABLE(spi, ad5449_spi_ids);
+
+static struct spi_driver ad5449_spi_driver = {
+	.driver = {
+		.name = "ad5449",
+		.owner = THIS_MODULE,
+	},
+	.probe = ad5449_spi_probe,
+	.remove = __devexit_p(ad5449_spi_remove),
+	.id_table = ad5449_spi_ids,
+};
+module_spi_driver(ad5449_spi_driver);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("Analog Devices AD5449 and similar DACs");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/platform_data/ad5449.h b/include/linux/platform_data/ad5449.h
new file mode 100644
index 000000000000..bd712bd4b94e
--- /dev/null
+++ b/include/linux/platform_data/ad5449.h
@@ -0,0 +1,40 @@
+/*
+ * AD5415, AD5426, AD5429, AD5432, AD5439, AD5443, AD5449 Digital to Analog
+ * Converter driver.
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#ifndef __LINUX_PLATFORM_DATA_AD5449_H__
+#define __LINUX_PLATFORM_DATA_AD5449_H__
+
+/**
+ * enum ad5449_sdo_mode - AD5449 SDO pin configuration
+ * @AD5449_SDO_DRIVE_FULL: Drive the SDO pin with full strength.
+ * @AD5449_SDO_DRIVE_WEAK: Drive the SDO pin with not full strength.
+ * @AD5449_SDO_OPEN_DRAIN: Operate the SDO pin in open-drain mode.
+ * @AD5449_SDO_DISABLED: Disable the SDO pin, in this mode it is not possible to
+ *			read back from the device.
+ */
+enum ad5449_sdo_mode {
+	AD5449_SDO_DRIVE_FULL = 0x0,
+	AD5449_SDO_DRIVE_WEAK = 0x1,
+	AD5449_SDO_OPEN_DRAIN = 0x2,
+	AD5449_SDO_DISABLED = 0x3,
+};
+
+/**
+ * struct ad5449_platform_data - Platform data for the ad5449 DAC driver
+ * @sdo_mode: SDO pin mode
+ * @hardware_clear_to_midscale: Whether asserting the hardware CLR pin sets the
+ *			outputs to midscale (true) or to zero scale(false).
+ */
+struct ad5449_platform_data {
+	enum ad5449_sdo_mode sdo_mode;
+	bool hardware_clear_to_midscale;
+};
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 49655bb8a51565f0375a4f783334c9de78134be5 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Sat, 29 Sep 2012 20:29:49 +0200
Subject: bcma: just do the necessary things in early register on SoCs

Some parts of the initialization for chip common and the pcie core are
accessing the sprom struct, but it is not initialized at that stage.
Just do the necessary thing in the early register on SoCs and not the
complete initialization to read out the nvram from the flash chip.
After it is possible to read out the nvram, the sprom should be parsed
from it and the full initialization of the cores should be run.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/driver_chipcommon.c            | 23 ++++++++++++++++++-----
 drivers/bcma/driver_chipcommon_pmu.c        |  5 ++++-
 drivers/bcma/driver_mips.c                  | 26 +++++++++++++++++++-------
 drivers/bcma/main.c                         |  8 ++++----
 include/linux/bcma/bcma_driver_chipcommon.h |  3 +++
 include/linux/bcma/bcma_driver_mips.h       |  3 +++
 6 files changed, 51 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c
index a4c3ebcc4c86..ffd74e51f02d 100644
--- a/drivers/bcma/driver_chipcommon.c
+++ b/drivers/bcma/driver_chipcommon.c
@@ -22,12 +22,9 @@ static inline u32 bcma_cc_write32_masked(struct bcma_drv_cc *cc, u16 offset,
 	return value;
 }
 
-void bcma_core_chipcommon_init(struct bcma_drv_cc *cc)
+void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc)
 {
-	u32 leddc_on = 10;
-	u32 leddc_off = 90;
-
-	if (cc->setup_done)
+	if (cc->early_setup_done)
 		return;
 
 	if (cc->core->id.rev >= 11)
@@ -36,6 +33,22 @@ void bcma_core_chipcommon_init(struct bcma_drv_cc *cc)
 	if (cc->core->id.rev >= 35)
 		cc->capabilities_ext = bcma_cc_read32(cc, BCMA_CC_CAP_EXT);
 
+	if (cc->capabilities & BCMA_CC_CAP_PMU)
+		bcma_pmu_early_init(cc);
+
+	cc->early_setup_done = true;
+}
+
+void bcma_core_chipcommon_init(struct bcma_drv_cc *cc)
+{
+	u32 leddc_on = 10;
+	u32 leddc_off = 90;
+
+	if (cc->setup_done)
+		return;
+
+	bcma_core_chipcommon_early_init(cc);
+
 	if (cc->core->id.rev >= 20) {
 		bcma_cc_write32(cc, BCMA_CC_GPIOPULLUP, 0);
 		bcma_cc_write32(cc, BCMA_CC_GPIOPULLDOWN, 0);
diff --git a/drivers/bcma/driver_chipcommon_pmu.c b/drivers/bcma/driver_chipcommon_pmu.c
index 201faf106b3f..a63ddd9c70eb 100644
--- a/drivers/bcma/driver_chipcommon_pmu.c
+++ b/drivers/bcma/driver_chipcommon_pmu.c
@@ -144,7 +144,7 @@ static void bcma_pmu_workarounds(struct bcma_drv_cc *cc)
 	}
 }
 
-void bcma_pmu_init(struct bcma_drv_cc *cc)
+void bcma_pmu_early_init(struct bcma_drv_cc *cc)
 {
 	u32 pmucap;
 
@@ -153,7 +153,10 @@ void bcma_pmu_init(struct bcma_drv_cc *cc)
 
 	bcma_debug(cc->core->bus, "Found rev %u PMU (capabilities 0x%08X)\n",
 		   cc->pmu.rev, pmucap);
+}
 
+void bcma_pmu_init(struct bcma_drv_cc *cc)
+{
 	if (cc->pmu.rev == 1)
 		bcma_cc_mask32(cc, BCMA_CC_PMU_CTL,
 			      ~BCMA_CC_PMU_CTL_NOILPONW);
diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c
index cc65b45b4368..f44f1fb67011 100644
--- a/drivers/bcma/driver_mips.c
+++ b/drivers/bcma/driver_mips.c
@@ -212,16 +212,33 @@ static void bcma_core_mips_flash_detect(struct bcma_drv_mips *mcore)
 	}
 }
 
+void bcma_core_mips_early_init(struct bcma_drv_mips *mcore)
+{
+	struct bcma_bus *bus = mcore->core->bus;
+
+	if (mcore->early_setup_done)
+		return;
+
+	bcma_chipco_serial_init(&bus->drv_cc);
+	bcma_core_mips_flash_detect(mcore);
+
+	mcore->early_setup_done = true;
+}
+
 void bcma_core_mips_init(struct bcma_drv_mips *mcore)
 {
 	struct bcma_bus *bus;
 	struct bcma_device *core;
 	bus = mcore->core->bus;
 
+	if (mcore->setup_done)
+		return;
+
 	bcma_info(bus, "Initializing MIPS core...\n");
 
-	if (!mcore->setup_done)
-		mcore->assigned_irqs = 1;
+	bcma_core_mips_early_init(mcore);
+
+	mcore->assigned_irqs = 1;
 
 	/* Assign IRQs to all cores on the bus */
 	list_for_each_entry(core, &bus->cores, list) {
@@ -256,10 +273,5 @@ void bcma_core_mips_init(struct bcma_drv_mips *mcore)
 	bcma_info(bus, "IRQ reconfiguration done\n");
 	bcma_core_mips_dump_irq(bus);
 
-	if (mcore->setup_done)
-		return;
-
-	bcma_chipco_serial_init(&bus->drv_cc);
-	bcma_core_mips_flash_detect(mcore);
 	mcore->setup_done = true;
 }
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 432aeeedfd5e..bea2d7cfa6c2 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -274,18 +274,18 @@ int __init bcma_bus_early_register(struct bcma_bus *bus,
 		return -1;
 	}
 
-	/* Init CC core */
+	/* Early init CC core */
 	core = bcma_find_core(bus, bcma_cc_core_id(bus));
 	if (core) {
 		bus->drv_cc.core = core;
-		bcma_core_chipcommon_init(&bus->drv_cc);
+		bcma_core_chipcommon_early_init(&bus->drv_cc);
 	}
 
-	/* Init MIPS core */
+	/* Early init MIPS core */
 	core = bcma_find_core(bus, BCMA_CORE_MIPS_74K);
 	if (core) {
 		bus->drv_mips.core = core;
-		bcma_core_mips_init(&bus->drv_mips);
+		bcma_core_mips_early_init(&bus->drv_mips);
 	}
 
 	bcma_info(bus, "Early bus registered\n");
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index 1cf1749440ac..fbde7cbd2d7d 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -552,6 +552,7 @@ struct bcma_drv_cc {
 	u32 capabilities;
 	u32 capabilities_ext;
 	u8 setup_done:1;
+	u8 early_setup_done:1;
 	/* Fast Powerup Delay constant */
 	u16 fast_pwrup_delay;
 	struct bcma_chipcommon_pmu pmu;
@@ -583,6 +584,7 @@ struct bcma_drv_cc {
 	bcma_cc_write32(cc, offset, (bcma_cc_read32(cc, offset) & (mask)) | (set))
 
 extern void bcma_core_chipcommon_init(struct bcma_drv_cc *cc);
+extern void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc);
 
 extern void bcma_chipco_suspend(struct bcma_drv_cc *cc);
 extern void bcma_chipco_resume(struct bcma_drv_cc *cc);
@@ -606,6 +608,7 @@ u32 bcma_chipco_gpio_polarity(struct bcma_drv_cc *cc, u32 mask, u32 value);
 
 /* PMU support */
 extern void bcma_pmu_init(struct bcma_drv_cc *cc);
+extern void bcma_pmu_early_init(struct bcma_drv_cc *cc);
 
 extern void bcma_chipco_pll_write(struct bcma_drv_cc *cc, u32 offset,
 				  u32 value);
diff --git a/include/linux/bcma/bcma_driver_mips.h b/include/linux/bcma/bcma_driver_mips.h
index c0043645cdcb..0baf8a56b794 100644
--- a/include/linux/bcma/bcma_driver_mips.h
+++ b/include/linux/bcma/bcma_driver_mips.h
@@ -35,13 +35,16 @@ struct bcma_device;
 struct bcma_drv_mips {
 	struct bcma_device *core;
 	u8 setup_done:1;
+	u8 early_setup_done:1;
 	unsigned int assigned_irqs;
 };
 
 #ifdef CONFIG_BCMA_DRIVER_MIPS
 extern void bcma_core_mips_init(struct bcma_drv_mips *mcore);
+extern void bcma_core_mips_early_init(struct bcma_drv_mips *mcore);
 #else
 static inline void bcma_core_mips_init(struct bcma_drv_mips *mcore) { }
+static inline void bcma_core_mips_early_init(struct bcma_drv_mips *mcore) { }
 #endif
 
 extern u32 bcma_cpu_clock(struct bcma_drv_mips *mcore);
-- 
cgit v1.2.3-55-g7522


From 360dc31e9cc3f74d0d91a9d19b154c12592f4ffc Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Sat, 29 Sep 2012 20:33:49 +0200
Subject: bcma: mark pflash as present when available

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/driver_mips.c                  | 1 +
 include/linux/bcma/bcma_driver_chipcommon.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c
index f44f1fb67011..c0fb1d45c6db 100644
--- a/drivers/bcma/driver_mips.c
+++ b/drivers/bcma/driver_mips.c
@@ -190,6 +190,7 @@ static void bcma_core_mips_flash_detect(struct bcma_drv_mips *mcore)
 		break;
 	case BCMA_CC_FLASHT_PARA:
 		bcma_debug(bus, "Found parallel flash\n");
+		bus->drv_cc.pflash.present = true;
 		bus->drv_cc.pflash.window = 0x1c000000;
 		bus->drv_cc.pflash.window_size = 0x02000000;
 
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index fbde7cbd2d7d..79993969953a 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -510,6 +510,7 @@ struct bcma_chipcommon_pmu {
 
 #ifdef CONFIG_BCMA_DRIVER_MIPS
 struct bcma_pflash {
+	bool present;
 	u8 buswidth;
 	u32 window;
 	u32 window_size;
-- 
cgit v1.2.3-55-g7522


From cc787081bcab5a83051c2a936927634d066e7284 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Sat, 29 Sep 2012 20:33:50 +0200
Subject: bcma: add and use constants for the flash windows

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/driver_chipcommon_sflash.c | 4 ++--
 drivers/bcma/driver_mips.c              | 4 ++--
 include/linux/bcma/bcma_regs.h          | 5 ++++-
 3 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/driver_chipcommon_sflash.c b/drivers/bcma/driver_chipcommon_sflash.c
index 2c4eec2ca5a0..a0993fcd13c2 100644
--- a/drivers/bcma/driver_chipcommon_sflash.c
+++ b/drivers/bcma/driver_chipcommon_sflash.c
@@ -12,7 +12,7 @@
 
 static struct resource bcma_sflash_resource = {
 	.name	= "bcma_sflash",
-	.start	= BCMA_SFLASH,
+	.start	= BCMA_SOC_FLASH2,
 	.end	= 0,
 	.flags  = IORESOURCE_MEM | IORESOURCE_READONLY,
 };
@@ -116,7 +116,7 @@ int bcma_sflash_init(struct bcma_drv_cc *cc)
 		return -ENOTSUPP;
 	}
 
-	sflash->window = BCMA_SFLASH;
+	sflash->window = BCMA_SOC_FLASH2;
 	sflash->blocksize = e->blocksize;
 	sflash->numblocks = e->numblocks;
 	sflash->size = sflash->blocksize * sflash->numblocks;
diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c
index c0fb1d45c6db..d8e2fba482e6 100644
--- a/drivers/bcma/driver_mips.c
+++ b/drivers/bcma/driver_mips.c
@@ -191,8 +191,8 @@ static void bcma_core_mips_flash_detect(struct bcma_drv_mips *mcore)
 	case BCMA_CC_FLASHT_PARA:
 		bcma_debug(bus, "Found parallel flash\n");
 		bus->drv_cc.pflash.present = true;
-		bus->drv_cc.pflash.window = 0x1c000000;
-		bus->drv_cc.pflash.window_size = 0x02000000;
+		bus->drv_cc.pflash.window = BCMA_SOC_FLASH2;
+		bus->drv_cc.pflash.window_size = BCMA_SOC_FLASH2_SZ;
 
 		if ((bcma_read32(bus->drv_cc.core, BCMA_CC_FLASH_CFG) &
 		     BCMA_CC_FLASH_CFG_DS) == 0)
diff --git a/include/linux/bcma/bcma_regs.h b/include/linux/bcma/bcma_regs.h
index 6c9cb93ae3de..7e8104bb7a7e 100644
--- a/include/linux/bcma/bcma_regs.h
+++ b/include/linux/bcma/bcma_regs.h
@@ -85,6 +85,9 @@
 							 * (2 ZettaBytes), high 32 bits
 							 */
 
-#define BCMA_SFLASH			0x1c000000
+#define BCMA_SOC_FLASH1			0x1fc00000	/* MIPS Flash Region 1 */
+#define BCMA_SOC_FLASH1_SZ		0x00400000	/* MIPS Size of Flash Region 1 */
+#define BCMA_SOC_FLASH2			0x1c000000	/* Flash Region 2 (region 1 shadowed here) */
+#define BCMA_SOC_FLASH2_SZ		0x02000000	/* Size of Flash Region 2 */
 
 #endif /* LINUX_BCMA_REGS_H_ */
-- 
cgit v1.2.3-55-g7522


From e661b75a44cc811426ea005c3cb858e45bd73d57 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Sat, 29 Sep 2012 20:33:51 +0200
Subject: bcma: mark nflash if it is the boot flash

There are some devices which are able to boot from nand flash and other
are using a serial flash for booting. Add a bool to indicate that the
device is booted from that flash chip and not from some other chip also
connected to the SoC. This is needed to find the nvram, as it is stored
on the flash the devices booted from.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/driver_chipcommon_nflash.c     | 3 +++
 include/linux/bcma/bcma_driver_chipcommon.h | 1 +
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/bcma/driver_chipcommon_nflash.c b/drivers/bcma/driver_chipcommon_nflash.c
index 9042781edec3..dbda91e4dff5 100644
--- a/drivers/bcma/driver_chipcommon_nflash.c
+++ b/drivers/bcma/driver_chipcommon_nflash.c
@@ -32,6 +32,9 @@ int bcma_nflash_init(struct bcma_drv_cc *cc)
 	}
 
 	cc->nflash.present = true;
+	if (cc->core->id.rev == 38 &&
+	    (cc->status & BCMA_CC_CHIPST_5357_NAND_BOOT))
+		cc->nflash.boot = true;
 
 	/* Prepare platform device, but don't register it yet. It's too early,
 	 * malloc (required by device_private_init) is not available yet. */
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index 79993969953a..145f3c56227f 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -533,6 +533,7 @@ struct mtd_info;
 
 struct bcma_nflash {
 	bool present;
+	bool boot;		/* This is the flash the SoC boots from */
 
 	struct mtd_info *mtd;
 };
-- 
cgit v1.2.3-55-g7522


From 54c974984e8840c9e20390ce16e3d9f4ea674499 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Sat, 29 Sep 2012 20:36:17 +0200
Subject: ssb: move parallel flash config into an own struct

This is a preparing step for adding serial flash support.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 arch/mips/bcm47xx/nvram.c           |  4 ++--
 arch/mips/bcm47xx/wgt634u.c         |  8 ++++----
 drivers/ssb/driver_mipscore.c       | 14 +++++++-------
 include/linux/ssb/ssb_driver_mips.h |  9 ++++++---
 4 files changed, 19 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/mips/bcm47xx/nvram.c b/arch/mips/bcm47xx/nvram.c
index d43ceff5be47..48a4c70b3842 100644
--- a/arch/mips/bcm47xx/nvram.c
+++ b/arch/mips/bcm47xx/nvram.c
@@ -43,8 +43,8 @@ static void early_nvram_init(void)
 #ifdef CONFIG_BCM47XX_SSB
 	case BCM47XX_BUS_TYPE_SSB:
 		mcore_ssb = &bcm47xx_bus.ssb.mipscore;
-		base = mcore_ssb->flash_window;
-		lim = mcore_ssb->flash_window_size;
+		base = mcore_ssb->pflash.window;
+		lim = mcore_ssb->pflash.window_size;
 		break;
 #endif
 #ifdef CONFIG_BCM47XX_BCMA
diff --git a/arch/mips/bcm47xx/wgt634u.c b/arch/mips/bcm47xx/wgt634u.c
index e9f9ec8d443b..e80d585731aa 100644
--- a/arch/mips/bcm47xx/wgt634u.c
+++ b/arch/mips/bcm47xx/wgt634u.c
@@ -156,10 +156,10 @@ static int __init wgt634u_init(void)
 					    SSB_CHIPCO_IRQ_GPIO);
 		}
 
-		wgt634u_flash_data.width = mcore->flash_buswidth;
-		wgt634u_flash_resource.start = mcore->flash_window;
-		wgt634u_flash_resource.end = mcore->flash_window
-					   + mcore->flash_window_size
+		wgt634u_flash_data.width = mcore->pflash.buswidth;
+		wgt634u_flash_resource.start = mcore->pflash.window;
+		wgt634u_flash_resource.end = mcore->pflash.window
+					   + mcore->pflash.window_size
 					   - 1;
 		return platform_add_devices(wgt634u_devices,
 					    ARRAY_SIZE(wgt634u_devices));
diff --git a/drivers/ssb/driver_mipscore.c b/drivers/ssb/driver_mipscore.c
index c6250867a95d..dcad2c40836e 100644
--- a/drivers/ssb/driver_mipscore.c
+++ b/drivers/ssb/driver_mipscore.c
@@ -192,9 +192,9 @@ static void ssb_mips_flash_detect(struct ssb_mipscore *mcore)
 
 	/* When there is no chipcommon on the bus there is 4MB flash */
 	if (!bus->chipco.dev) {
-		mcore->flash_buswidth = 2;
-		mcore->flash_window = SSB_FLASH1;
-		mcore->flash_window_size = SSB_FLASH1_SZ;
+		mcore->pflash.buswidth = 2;
+		mcore->pflash.window = SSB_FLASH1;
+		mcore->pflash.window_size = SSB_FLASH1_SZ;
 		return;
 	}
 
@@ -206,13 +206,13 @@ static void ssb_mips_flash_detect(struct ssb_mipscore *mcore)
 		break;
 	case SSB_CHIPCO_FLASHT_PARA:
 		pr_debug("Found parallel flash\n");
-		mcore->flash_window = SSB_FLASH2;
-		mcore->flash_window_size = SSB_FLASH2_SZ;
+		mcore->pflash.window = SSB_FLASH2;
+		mcore->pflash.window_size = SSB_FLASH2_SZ;
 		if ((ssb_read32(bus->chipco.dev, SSB_CHIPCO_FLASH_CFG)
 		               & SSB_CHIPCO_CFG_DS16) == 0)
-			mcore->flash_buswidth = 1;
+			mcore->pflash.buswidth = 1;
 		else
-			mcore->flash_buswidth = 2;
+			mcore->pflash.buswidth = 2;
 		break;
 	}
 }
diff --git a/include/linux/ssb/ssb_driver_mips.h b/include/linux/ssb/ssb_driver_mips.h
index 5f44e9740cd2..5d057db53071 100644
--- a/include/linux/ssb/ssb_driver_mips.h
+++ b/include/linux/ssb/ssb_driver_mips.h
@@ -13,6 +13,11 @@ struct ssb_serial_port {
 	unsigned int reg_shift;
 };
 
+struct ssb_pflash {
+	u8 buswidth;
+	u32 window;
+	u32 window_size;
+};
 
 struct ssb_mipscore {
 	struct ssb_device *dev;
@@ -20,9 +25,7 @@ struct ssb_mipscore {
 	int nr_serial_ports;
 	struct ssb_serial_port serial_ports[4];
 
-	u8 flash_buswidth;
-	u32 flash_window;
-	u32 flash_window_size;
+	struct ssb_pflash pflash;
 };
 
 extern void ssb_mipscore_init(struct ssb_mipscore *mcore);
-- 
cgit v1.2.3-55-g7522


From d954162c54ea81cee12acec1ee5fa19214d0de96 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Sat, 29 Sep 2012 20:36:18 +0200
Subject: ssb: add attribute to indicate a parallel flash is available

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/ssb/driver_mipscore.c       | 2 ++
 include/linux/ssb/ssb_driver_mips.h | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/drivers/ssb/driver_mipscore.c b/drivers/ssb/driver_mipscore.c
index dcad2c40836e..b918ba922306 100644
--- a/drivers/ssb/driver_mipscore.c
+++ b/drivers/ssb/driver_mipscore.c
@@ -192,6 +192,7 @@ static void ssb_mips_flash_detect(struct ssb_mipscore *mcore)
 
 	/* When there is no chipcommon on the bus there is 4MB flash */
 	if (!bus->chipco.dev) {
+		mcore->pflash.present = true;
 		mcore->pflash.buswidth = 2;
 		mcore->pflash.window = SSB_FLASH1;
 		mcore->pflash.window_size = SSB_FLASH1_SZ;
@@ -206,6 +207,7 @@ static void ssb_mips_flash_detect(struct ssb_mipscore *mcore)
 		break;
 	case SSB_CHIPCO_FLASHT_PARA:
 		pr_debug("Found parallel flash\n");
+		mcore->pflash.present = true;
 		mcore->pflash.window = SSB_FLASH2;
 		mcore->pflash.window_size = SSB_FLASH2_SZ;
 		if ((ssb_read32(bus->chipco.dev, SSB_CHIPCO_FLASH_CFG)
diff --git a/include/linux/ssb/ssb_driver_mips.h b/include/linux/ssb/ssb_driver_mips.h
index 5d057db53071..07a9c7a2e088 100644
--- a/include/linux/ssb/ssb_driver_mips.h
+++ b/include/linux/ssb/ssb_driver_mips.h
@@ -14,6 +14,7 @@ struct ssb_serial_port {
 };
 
 struct ssb_pflash {
+	bool present;
 	u8 buswidth;
 	u32 window;
 	u32 window_size;
-- 
cgit v1.2.3-55-g7522


From dfae714361ba75323914da19eb411aaae53d6af0 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Sat, 29 Sep 2012 20:40:18 +0200
Subject: bcma: add an extra pcie core struct

The BCM4706 has two PCIe host controller on the bcma bus. For PCIe
client mode it is assumed that there is only one PCIe controller so the
PCIe driver, like b43 and brcmsmac are accessing the first PCIe
controller when they want to issue a operation on the host controller.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/driver_pci_host.c                    |  4 ++++
 drivers/bcma/main.c                               | 25 ++++++++++++++++++++---
 drivers/net/wireless/b43/main.c                   |  2 +-
 drivers/net/wireless/brcm80211/brcmsmac/aiutils.c |  4 ++--
 drivers/net/wireless/brcm80211/brcmsmac/main.c    |  2 +-
 include/linux/bcma/bcma.h                         |  2 +-
 6 files changed, 31 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/driver_pci_host.c b/drivers/bcma/driver_pci_host.c
index 9baf886e82df..63172c9f871a 100644
--- a/drivers/bcma/driver_pci_host.c
+++ b/drivers/bcma/driver_pci_host.c
@@ -452,6 +452,8 @@ void __devinit bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc)
 			pc_host->mem_resource.start = BCMA_SOC_PCI_MEM;
 			pc_host->mem_resource.end = BCMA_SOC_PCI_MEM +
 						    BCMA_SOC_PCI_MEM_SZ - 1;
+			pc_host->io_resource.start = 0x100;
+			pc_host->io_resource.end = 0x47F;
 			pci_membase_1G = BCMA_SOC_PCIE_DMA_H32;
 			pcicore_write32(pc, BCMA_CORE_PCI_SBTOPCI0,
 					tmp | BCMA_SOC_PCI_MEM);
@@ -459,6 +461,8 @@ void __devinit bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc)
 			pc_host->mem_resource.start = BCMA_SOC_PCI1_MEM;
 			pc_host->mem_resource.end = BCMA_SOC_PCI1_MEM +
 						    BCMA_SOC_PCI_MEM_SZ - 1;
+			pc_host->io_resource.start = 0x480;
+			pc_host->io_resource.end = 0x7FF;
 			pci_membase_1G = BCMA_SOC_PCIE1_DMA_H32;
 			pc_host->host_cfg_addr = BCMA_SOC_PCI1_CFG;
 			pcicore_write32(pc, BCMA_CORE_PCI_SBTOPCI0,
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index d6b5c4ca4c43..7f473cf0469e 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -81,6 +81,18 @@ struct bcma_device *bcma_find_core(struct bcma_bus *bus, u16 coreid)
 }
 EXPORT_SYMBOL_GPL(bcma_find_core);
 
+static struct bcma_device *bcma_find_core_unit(struct bcma_bus *bus, u16 coreid,
+					       u8 unit)
+{
+	struct bcma_device *core;
+
+	list_for_each_entry(core, &bus->cores, list) {
+		if (core->id.id == coreid && core->core_unit == unit)
+			return core;
+	}
+	return NULL;
+}
+
 static void bcma_release_core_dev(struct device *dev)
 {
 	struct bcma_device *core = container_of(dev, struct bcma_device, dev);
@@ -211,10 +223,17 @@ int __devinit bcma_bus_register(struct bcma_bus *bus)
 	}
 
 	/* Init PCIE core */
-	core = bcma_find_core(bus, BCMA_CORE_PCIE);
+	core = bcma_find_core_unit(bus, BCMA_CORE_PCIE, 0);
+	if (core) {
+		bus->drv_pci[0].core = core;
+		bcma_core_pci_init(&bus->drv_pci[0]);
+	}
+
+	/* Init PCIE core */
+	core = bcma_find_core_unit(bus, BCMA_CORE_PCIE, 1);
 	if (core) {
-		bus->drv_pci.core = core;
-		bcma_core_pci_init(&bus->drv_pci);
+		bus->drv_pci[1].core = core;
+		bcma_core_pci_init(&bus->drv_pci[1]);
 	}
 
 	/* Init GBIT MAC COMMON core */
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index 73730e94e0ac..7358ea2eb576 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -4652,7 +4652,7 @@ static int b43_wireless_core_init(struct b43_wldev *dev)
 	switch (dev->dev->bus_type) {
 #ifdef CONFIG_B43_BCMA
 	case B43_BUS_BCMA:
-		bcma_core_pci_irq_ctl(&dev->dev->bdev->bus->drv_pci,
+		bcma_core_pci_irq_ctl(&dev->dev->bdev->bus->drv_pci[0],
 				      dev->dev->bdev, true);
 		break;
 #endif
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/aiutils.c b/drivers/net/wireless/brcm80211/brcmsmac/aiutils.c
index b89f1272b93f..de96290f5ccd 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/aiutils.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/aiutils.c
@@ -692,7 +692,7 @@ void ai_pci_up(struct si_pub *sih)
 	sii = container_of(sih, struct si_info, pub);
 
 	if (sii->icbus->hosttype == BCMA_HOSTTYPE_PCI)
-		bcma_core_pci_extend_L1timer(&sii->icbus->drv_pci, true);
+		bcma_core_pci_extend_L1timer(&sii->icbus->drv_pci[0], true);
 }
 
 /* Unconfigure and/or apply various WARs when going down */
@@ -703,7 +703,7 @@ void ai_pci_down(struct si_pub *sih)
 	sii = container_of(sih, struct si_info, pub);
 
 	if (sii->icbus->hosttype == BCMA_HOSTTYPE_PCI)
-		bcma_core_pci_extend_L1timer(&sii->icbus->drv_pci, false);
+		bcma_core_pci_extend_L1timer(&sii->icbus->drv_pci[0], false);
 }
 
 /* Enable BT-COEX & Ex-PA for 4313 */
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/main.c b/drivers/net/wireless/brcm80211/brcmsmac/main.c
index 75086b37c817..565c15abbed5 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/main.c
@@ -5077,7 +5077,7 @@ static int brcms_b_up_prep(struct brcms_hardware *wlc_hw)
 	 * Configure pci/pcmcia here instead of in brcms_c_attach()
 	 * to allow mfg hotswap:  down, hotswap (chip power cycle), up.
 	 */
-	bcma_core_pci_irq_ctl(&wlc_hw->d11core->bus->drv_pci, wlc_hw->d11core,
+	bcma_core_pci_irq_ctl(&wlc_hw->d11core->bus->drv_pci[0], wlc_hw->d11core,
 			      true);
 
 	/*
diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index 4180eb78d575..fd15d9829705 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -251,7 +251,7 @@ struct bcma_bus {
 	u8 num;
 
 	struct bcma_drv_cc drv_cc;
-	struct bcma_drv_pci drv_pci;
+	struct bcma_drv_pci drv_pci[2];
 	struct bcma_drv_mips drv_mips;
 	struct bcma_drv_gmac_cmn drv_gmac_cmn;
 
-- 
cgit v1.2.3-55-g7522


From 733deca197143857f938b41d671cd7ce9c53c4bc Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Sat, 20 Oct 2012 13:13:11 -0400
Subject: Drop struct pt_regs * argument in compat_sys_execve()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/tile/include/asm/compat.h    | 6 ------
 arch/tile/include/asm/processor.h | 3 +++
 arch/tile/kernel/compat.c         | 1 -
 arch/tile/kernel/intvec_64.S      | 1 -
 arch/tile/kernel/process.c        | 6 +++---
 include/linux/compat.h            | 2 --
 6 files changed, 6 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index 3063e6fc8daa..3bcf1b94b563 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -275,9 +275,6 @@ extern int compat_setup_rt_frame(int sig, struct k_sigaction *ka,
 struct compat_sigaction;
 struct compat_siginfo;
 struct compat_sigaltstack;
-long compat_sys_execve(const char __user *path,
-		       compat_uptr_t __user *argv,
-		       compat_uptr_t __user *envp, struct pt_regs *);
 long compat_sys_rt_sigaction(int sig, struct compat_sigaction __user *act,
 			     struct compat_sigaction __user *oact,
 			     size_t sigsetsize);
@@ -304,9 +301,6 @@ long compat_sys_sched_rr_get_interval(compat_pid_t pid,
 				      struct compat_timespec __user *interval);
 
 /* These are the intvec_64.S trampolines. */
-long _compat_sys_execve(const char __user *path,
-			const compat_uptr_t __user *argv,
-			const compat_uptr_t __user *envp);
 long _compat_sys_sigaltstack(const struct compat_sigaltstack __user *uss_ptr,
 			    struct compat_sigaltstack __user *uoss_ptr);
 long _compat_sys_rt_sigreturn(void);
diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h
index 8c4dd9ff91eb..9a83e531e843 100644
--- a/arch/tile/include/asm/processor.h
+++ b/arch/tile/include/asm/processor.h
@@ -239,6 +239,9 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_TOP(task)	(task_ksp0(task) - STACK_TOP_DELTA)
 #define task_pt_regs(task) \
   ((struct pt_regs *)(task_ksp0(task) - KSTK_PTREGS_GAP) - 1)
+#define current_pt_regs()                                   \
+  ((struct pt_regs *)((stack_pointer | (THREAD_SIZE - 1)) - \
+                      (KSTK_PTREGS_GAP - 1)) - 1)
 #define task_sp(task)	(task_pt_regs(task)->sp)
 #define task_pc(task)	(task_pt_regs(task)->pc)
 /* Aliases for pc and sp (used in fs/proc/array.c) */
diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c
index d67459b9ac2a..a8e5a847037c 100644
--- a/arch/tile/kernel/compat.c
+++ b/arch/tile/kernel/compat.c
@@ -103,7 +103,6 @@ long compat_sys_sched_rr_get_interval(compat_pid_t pid,
 #define compat_sys_readahead sys32_readahead
 
 /* Call the trampolines to manage pt_regs where necessary. */
-#define compat_sys_execve _compat_sys_execve
 #define compat_sys_sigaltstack _compat_sys_sigaltstack
 #define compat_sys_rt_sigreturn _compat_sys_rt_sigreturn
 #define sys_clone _sys_clone
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index 7c06d597ffd0..73f6c0a648c4 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -1194,7 +1194,6 @@ PTREGS_SYSCALL(sys_execve, r3)
 PTREGS_SYSCALL(sys_sigaltstack, r2)
 PTREGS_SYSCALL_SIGRETURN(sys_rt_sigreturn, r0)
 #ifdef CONFIG_COMPAT
-PTREGS_SYSCALL(compat_sys_execve, r3)
 PTREGS_SYSCALL(compat_sys_sigaltstack, r2)
 PTREGS_SYSCALL_SIGRETURN(compat_sys_rt_sigreturn, r0)
 #endif
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 307d010696c9..9dc139127f86 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -614,8 +614,7 @@ out:
 #ifdef CONFIG_COMPAT
 long compat_sys_execve(const char __user *path,
 		       compat_uptr_t __user *argv,
-		       compat_uptr_t __user *envp,
-		       struct pt_regs *regs)
+		       compat_uptr_t __user *envp)
 {
 	long error;
 	struct filename *filename;
@@ -624,7 +623,8 @@ long compat_sys_execve(const char __user *path,
 	error = PTR_ERR(filename);
 	if (IS_ERR(filename))
 		goto out;
-	error = compat_do_execve(filename->name, argv, envp, regs);
+	error = compat_do_execve(filename->name, argv, envp,
+				 current_pt_regs());
 	putname(filename);
 	if (error == 0)
 		single_step_execve();
diff --git a/include/linux/compat.h b/include/linux/compat.h
index d0ced1011f2f..d2db71077d93 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -286,10 +286,8 @@ asmlinkage ssize_t compat_sys_pwritev(unsigned long fd,
 
 int compat_do_execve(const char *filename, const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp, struct pt_regs *regs);
-#ifdef __ARCH_WANT_SYS_EXECVE
 asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp);
-#endif
 
 asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 		compat_ulong_t __user *outp, compat_ulong_t __user *exp,
-- 
cgit v1.2.3-55-g7522


From 0da5f7c6d2a2653e3c8867df5f226e62377a141f Mon Sep 17 00:00:00 2001
From: Pavel Emelyanov
Date: Thu, 18 Oct 2012 20:28:28 +0000
Subject: unix: Remove unused field from unix_sock

The struct sock *other one seem to be unused. Grep and make do not object.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index b5f8988e4283..0a996a3517ed 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -53,7 +53,6 @@ struct unix_sock {
 	struct path		path;
 	struct mutex		readlock;
 	struct sock		*peer;
-	struct sock		*other;
 	struct list_head	link;
 	atomic_long_t		inflight;
 	spinlock_t		lock;
-- 
cgit v1.2.3-55-g7522


From 5028ea04c8a8a67fe73f18f5f34386730c9c1bf2 Mon Sep 17 00:00:00 2001
From: Archit Taneja
Date: Thu, 18 Oct 2012 16:51:57 +0530
Subject: OMAPDSS: Remove acb and acbi fields from omap_dss_device

acbi and acb fields were meant for passive matrix panels which omapdss
doesn't support any longer. Remove these fields from omap_dss_device
struct.

Signed-off-by: Archit Taneja <archit@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 include/video/omapdss.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index 88c829466fc1..f39e6aabce21 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -621,10 +621,6 @@ struct omap_dss_device {
 	struct {
 		struct omap_video_timings timings;
 
-		int acbi;	/* ac-bias pin transitions per interrupt */
-		/* Unit: line clocks */
-		int acb;	/* ac-bias pin frequency */
-
 		enum omap_dss_dsi_pixel_format dsi_pix_fmt;
 		enum omap_dss_dsi_mode dsi_mode;
 		struct omap_dss_dsi_videomode_timings dsi_vm_timings;
-- 
cgit v1.2.3-55-g7522


From 7e05484f02e1ea05a3aae0724d4df1e8a5a1920f Mon Sep 17 00:00:00 2001
From: Bryan Venteicher
Date: Tue, 16 Oct 2012 23:55:54 +1030
Subject: virtio-scsi: Add real 2-clause BSD license to header

This is analogous to commit a1b383870a made by Rusty Russell to all
the VirtIO headers at the time. This eases the use of the header as
is by other OSes.

Signed-off-by: Bryan Venteicher <bryanv@daemoninthecloset.org>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/virtio_scsi.h | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/virtio_scsi.h b/include/linux/virtio_scsi.h
index d6b4440387b7..4195b97a3def 100644
--- a/include/linux/virtio_scsi.h
+++ b/include/linux/virtio_scsi.h
@@ -1,7 +1,31 @@
+/*
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
 #ifndef _LINUX_VIRTIO_SCSI_H
 #define _LINUX_VIRTIO_SCSI_H
-/* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
 
 #define VIRTIO_SCSI_CDB_SIZE   32
 #define VIRTIO_SCSI_SENSE_SIZE 96
-- 
cgit v1.2.3-55-g7522


From b8ec56d8eabc6382bd6586024138d9f1d1121ceb Mon Sep 17 00:00:00 2001
From: Matt Porter
Date: Wed, 17 Oct 2012 16:08:03 +0200
Subject: ASoC: davinci: replace private sram api with genalloc

Removes the DaVinci private SRAM API and replaces it with
the genalloc API. The SRAM gen_pool is passed in pdata since
DaVinci is in the early stages of DT conversion.

[zonque@gmail.com: stub out gen_pool functions for
		   !CONFIG_GENERIC_ALLOCATOR]

Signed-off-by: Matt Porter <mporter@ti.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/linux/platform_data/davinci_asp.h |  3 +++
 sound/soc/davinci/davinci-mcasp.c         |  2 ++
 sound/soc/davinci/davinci-pcm.c           | 37 ++++++++++++++++++++++++++-----
 sound/soc/davinci/davinci-pcm.h           |  2 ++
 4 files changed, 38 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h
index d0c5825876f8..f3d6e4f20962 100644
--- a/include/linux/platform_data/davinci_asp.h
+++ b/include/linux/platform_data/davinci_asp.h
@@ -16,6 +16,8 @@
 #ifndef __DAVINCI_ASP_H
 #define __DAVINCI_ASP_H
 
+#include <linux/genalloc.h>
+
 struct snd_platform_data {
 	u32 tx_dma_offset;
 	u32 rx_dma_offset;
@@ -30,6 +32,7 @@ struct snd_platform_data {
 	unsigned enable_channel_combine:1;
 	unsigned sram_size_playback;
 	unsigned sram_size_capture;
+	struct gen_pool *sram_pool;
 
 	/*
 	 * If McBSP peripheral gets the clock from an external pin,
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 4fd149bb1ae7..571559501b0b 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -1167,6 +1167,7 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 	dma_data = &dev->dma_params[SNDRV_PCM_STREAM_PLAYBACK];
 	dma_data->asp_chan_q = pdata->asp_chan_q;
 	dma_data->ram_chan_q = pdata->ram_chan_q;
+	dma_data->sram_pool = pdata->sram_pool;
 	dma_data->sram_size = pdata->sram_size_playback;
 	dma_data->dma_addr = (dma_addr_t) (pdata->tx_dma_offset +
 							mem->start);
@@ -1184,6 +1185,7 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 	dma_data = &dev->dma_params[SNDRV_PCM_STREAM_CAPTURE];
 	dma_data->asp_chan_q = pdata->asp_chan_q;
 	dma_data->ram_chan_q = pdata->ram_chan_q;
+	dma_data->sram_pool = pdata->sram_pool;
 	dma_data->sram_size = pdata->sram_size_capture;
 	dma_data->dma_addr = (dma_addr_t)(pdata->rx_dma_offset +
 							mem->start);
diff --git a/sound/soc/davinci/davinci-pcm.c b/sound/soc/davinci/davinci-pcm.c
index 6ebbc8885518..afab81f844ae 100644
--- a/sound/soc/davinci/davinci-pcm.c
+++ b/sound/soc/davinci/davinci-pcm.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
 #include <linux/kernel.h>
+#include <linux/genalloc.h>
 
 #include <sound/core.h>
 #include <sound/pcm.h>
@@ -23,7 +24,6 @@
 #include <sound/soc.h>
 
 #include <asm/dma.h>
-#include <mach/sram.h>
 
 #include "davinci-pcm.h"
 
@@ -251,7 +251,9 @@ static void davinci_pcm_dma_irq(unsigned link, u16 ch_status, void *data)
 	}
 }
 
-static int allocate_sram(struct snd_pcm_substream *substream, unsigned size,
+#ifdef CONFIG_GENERIC_ALLOCATOR
+static int allocate_sram(struct snd_pcm_substream *substream,
+		struct gen_pool *sram_pool, unsigned size,
 		struct snd_pcm_hardware *ppcm)
 {
 	struct snd_dma_buffer *buf = &substream->dma_buffer;
@@ -263,9 +265,10 @@ static int allocate_sram(struct snd_pcm_substream *substream, unsigned size,
 		return 0;
 
 	ppcm->period_bytes_max = size;
-	iram_virt = sram_alloc(size, &iram_phys);
+	iram_virt = (void *)gen_pool_alloc(sram_pool, size);
 	if (!iram_virt)
 		goto exit1;
+	iram_phys = gen_pool_virt_to_phys(sram_pool, (unsigned)iram_virt);
 	iram_dma = kzalloc(sizeof(*iram_dma), GFP_KERNEL);
 	if (!iram_dma)
 		goto exit2;
@@ -277,11 +280,33 @@ static int allocate_sram(struct snd_pcm_substream *substream, unsigned size,
 	return 0;
 exit2:
 	if (iram_virt)
-		sram_free(iram_virt, size);
+		gen_pool_free(sram_pool, (unsigned)iram_virt, size);
 exit1:
 	return -ENOMEM;
 }
 
+static void davinci_free_sram(struct snd_pcm_substream *substream,
+			      struct snd_dma_buffer *iram_dma)
+{
+	struct davinci_runtime_data *prtd = substream->runtime->private_data;
+	struct gen_pool *sram_pool = prtd->params->sram_pool;
+
+	gen_pool_free(sram_pool, (unsigned) iram_dma->area, iram_dma->bytes);
+}
+#else
+static int allocate_sram(struct snd_pcm_substream *substream,
+		struct gen_pool *sram_pool, unsigned size,
+		struct snd_pcm_hardware *ppcm)
+{
+	return 0;
+}
+
+static void davinci_free_sram(struct snd_pcm_substream *substream,
+			      struct snd_dma_buffer *iram_dma)
+{
+}
+#endif
+
 /*
  * Only used with ping/pong.
  * This is called after runtime->dma_addr, period_bytes and data_type are valid
@@ -668,7 +693,7 @@ static int davinci_pcm_open(struct snd_pcm_substream *substream)
 
 	ppcm = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
 			&pcm_hardware_playback : &pcm_hardware_capture;
-	allocate_sram(substream, params->sram_size, ppcm);
+	allocate_sram(substream, params->sram_pool, params->sram_size, ppcm);
 	snd_soc_set_runtime_hwparams(substream, ppcm);
 	/* ensure that buffer size is a multiple of period size */
 	ret = snd_pcm_hw_constraint_integer(runtime,
@@ -811,7 +836,7 @@ static void davinci_pcm_free(struct snd_pcm *pcm)
 		buf->area = NULL;
 		iram_dma = buf->private_data;
 		if (iram_dma) {
-			sram_free(iram_dma->area, iram_dma->bytes);
+			davinci_free_sram(substream, iram_dma);
 			kfree(iram_dma);
 		}
 	}
diff --git a/sound/soc/davinci/davinci-pcm.h b/sound/soc/davinci/davinci-pcm.h
index fc4d01cdd8c9..b6ef7039dd09 100644
--- a/sound/soc/davinci/davinci-pcm.h
+++ b/sound/soc/davinci/davinci-pcm.h
@@ -12,6 +12,7 @@
 #ifndef _DAVINCI_PCM_H
 #define _DAVINCI_PCM_H
 
+#include <linux/genalloc.h>
 #include <linux/platform_data/davinci_asp.h>
 #include <mach/edma.h>
 
@@ -20,6 +21,7 @@ struct davinci_pcm_dma_params {
 	unsigned short acnt;
 	dma_addr_t dma_addr;		/* device physical address for DMA */
 	unsigned sram_size;
+	struct gen_pool *sram_pool;	/* SRAM gen_pool for ping pong */
 	enum dma_event_q asp_chan_q;	/* event queue number for ASP channel */
 	enum dma_event_q ram_chan_q;	/* event queue number for RAM channel */
 	unsigned char data_type;	/* xfer data type */
-- 
cgit v1.2.3-55-g7522


From a03bede5c73a6876fa891cfe82a65460dc9f4698 Mon Sep 17 00:00:00 2001
From: Alan Stern
Date: Mon, 1 Oct 2012 10:31:53 -0400
Subject: USB: update documentation for URB_ISO_ASAP

This patch (as1611) updates the USB documentation and kerneldoc to
give a more precise meaning for the URB_ISO_ASAP flag and to explain
more of the details of scheduling for isochronous URBs.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/usb/error-codes.txt |  5 ++---
 drivers/usb/core/urb.c            | 22 +++++++++++++++++++---
 include/linux/usb.h               | 27 ++++++++++++++++-----------
 3 files changed, 37 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/Documentation/usb/error-codes.txt b/Documentation/usb/error-codes.txt
index b3f606b81a03..8d1e2a9ebbba 100644
--- a/Documentation/usb/error-codes.txt
+++ b/Documentation/usb/error-codes.txt
@@ -35,9 +35,8 @@ USB-specific:
 		d) ISO: number_of_packets is < 0
 		e) various other cases
 
--EAGAIN		a) specified ISO start frame too early
-		b) (using ISO-ASAP) too much scheduled for the future
-		   wait some time and try again.
+-EXDEV		ISO: URB_ISO_ASAP wasn't specified and all the frames
+		the URB would be scheduled in have already expired.
 
 -EFBIG		Host controller driver can't schedule that many ISO frames.
 
diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index 9d912bfdcffe..3662287e2f4f 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -214,9 +214,25 @@ EXPORT_SYMBOL_GPL(usb_unanchor_urb);
  * urb->interval is modified to reflect the actual transfer period used
  * (normally some power of two units).  And for isochronous urbs,
  * urb->start_frame is modified to reflect when the URB's transfers were
- * scheduled to start.  Not all isochronous transfer scheduling policies
- * will work, but most host controller drivers should easily handle ISO
- * queues going from now until 10-200 msec into the future.
+ * scheduled to start.
+ *
+ * Not all isochronous transfer scheduling policies will work, but most
+ * host controller drivers should easily handle ISO queues going from now
+ * until 10-200 msec into the future.  Drivers should try to keep at
+ * least one or two msec of data in the queue; many controllers require
+ * that new transfers start at least 1 msec in the future when they are
+ * added.  If the driver is unable to keep up and the queue empties out,
+ * the behavior for new submissions is governed by the URB_ISO_ASAP flag.
+ * If the flag is set, or if the queue is idle, then the URB is always
+ * assigned to the first available (and not yet expired) slot in the
+ * endpoint's schedule.  If the flag is not set and the queue is active
+ * then the URB is always assigned to the next slot in the schedule
+ * following the end of the endpoint's previous URB, even if that slot is
+ * in the past.  When a packet is assigned in this way to a slot that has
+ * already expired, the packet is not transmitted and the corresponding
+ * usb_iso_packet_descriptor's status field will return -EXDEV.  If this
+ * would happen to all the packets in the URB, submission fails with a
+ * -EXDEV error code.
  *
  * For control endpoints, the synchronous usb_control_msg() call is
  * often used (in non-interrupt context) instead of this call.
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 10278d18709c..f92cdf0c1457 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1129,8 +1129,8 @@ extern int usb_disabled(void);
  * Note: URB_DIR_IN/OUT is automatically set in usb_submit_urb().
  */
 #define URB_SHORT_NOT_OK	0x0001	/* report short reads as errors */
-#define URB_ISO_ASAP		0x0002	/* iso-only, urb->start_frame
-					 * ignored */
+#define URB_ISO_ASAP		0x0002	/* iso-only; use the first unexpired
+					 * slot in the schedule */
 #define URB_NO_TRANSFER_DMA_MAP	0x0004	/* urb->transfer_dma valid on submit */
 #define URB_NO_FSBR		0x0020	/* UHCI-specific */
 #define URB_ZERO_PACKET		0x0040	/* Finish bulk OUT with short packet */
@@ -1309,15 +1309,20 @@ typedef void (*usb_complete_t)(struct urb *);
  * the transfer interval in the endpoint descriptor is logarithmic.
  * Device drivers must convert that value to linear units themselves.)
  *
- * Isochronous URBs normally use the URB_ISO_ASAP transfer flag, telling
- * the host controller to schedule the transfer as soon as bandwidth
- * utilization allows, and then set start_frame to reflect the actual frame
- * selected during submission.  Otherwise drivers must specify the start_frame
- * and handle the case where the transfer can't begin then.  However, drivers
- * won't know how bandwidth is currently allocated, and while they can
- * find the current frame using usb_get_current_frame_number () they can't
- * know the range for that frame number.  (Ranges for frame counter values
- * are HC-specific, and can go from 256 to 65536 frames from "now".)
+ * If an isochronous endpoint queue isn't already running, the host
+ * controller will schedule a new URB to start as soon as bandwidth
+ * utilization allows.  If the queue is running then a new URB will be
+ * scheduled to start in the first transfer slot following the end of the
+ * preceding URB, if that slot has not already expired.  If the slot has
+ * expired (which can happen when IRQ delivery is delayed for a long time),
+ * the scheduling behavior depends on the URB_ISO_ASAP flag.  If the flag
+ * is clear then the URB will be scheduled to start in the expired slot,
+ * implying that some of its packets will not be transferred; if the flag
+ * is set then the URB will be scheduled in the first unexpired slot,
+ * breaking the queue's synchronization.  Upon URB completion, the
+ * start_frame field will be set to the (micro)frame number in which the
+ * transfer was scheduled.  Ranges for frame counter values are HC-specific
+ * and can go from as low as 256 to as high as 65536 frames.
  *
  * Isochronous URBs have a different data transfer model, in part because
  * the quality of service is only "best effort".  Callers provide specially
-- 
cgit v1.2.3-55-g7522


From 4534874a8720a361845dce47d310a98e9aac8aeb Mon Sep 17 00:00:00 2001
From: Florian Fainelli
Date: Mon, 8 Oct 2012 15:11:21 +0200
Subject: USB: EHCI: add no_io_watchdog platform_data parameter to
 ehci-platform

Enhance the ehci-platform driver to also accept no_io_watchdog as a platform
data parameter. When no_io_watchdog is set to 1, the ehci controller will set
ehci->need_io_watchdog to 0. Since most EHCI controllers do need the I/O
watchdog to be on, only let those which need it to turn the watchdog off.

Make sure that we change need_io_watchdog after the call to ehci_setup()
because ehci_setup() will unconditionnaly set need_io_watchdog to 1.

Signed-off-by: Florian Fainelli <florian@openwrt.org>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/ehci-platform.c | 2 ++
 include/linux/usb/ehci_pdriver.h | 3 +++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/host/ehci-platform.c b/drivers/usb/host/ehci-platform.c
index 764e0100b6f4..607adf9adb83 100644
--- a/drivers/usb/host/ehci-platform.c
+++ b/drivers/usb/host/ehci-platform.c
@@ -38,6 +38,8 @@ static int ehci_platform_reset(struct usb_hcd *hcd)
 	if (retval)
 		return retval;
 
+	if (pdata->no_io_watchdog)
+		ehci->need_io_watchdog = 0;
 	if (pdata->port_power_on)
 		ehci_port_power(ehci, 1);
 	if (pdata->port_power_off)
diff --git a/include/linux/usb/ehci_pdriver.h b/include/linux/usb/ehci_pdriver.h
index c9d09f8b7ff2..67ac74bde6d0 100644
--- a/include/linux/usb/ehci_pdriver.h
+++ b/include/linux/usb/ehci_pdriver.h
@@ -29,6 +29,8 @@
  *			initialization.
  * @port_power_off:	set to 1 if the controller needs to be powered down
  *			after initialization.
+ * @no_io_watchdog:	set to 1 if the controller does not need the I/O
+ *			watchdog to run.
  *
  * These are general configuration options for the EHCI controller. All of
  * these options are activating more or less workarounds for some hardware.
@@ -41,6 +43,7 @@ struct usb_ehci_pdata {
 	unsigned	big_endian_mmio:1;
 	unsigned	port_power_on:1;
 	unsigned	port_power_off:1;
+	unsigned	no_io_watchdog:1;
 
 	/* Turn on all power and clocks */
 	int (*power_on)(struct platform_device *pdev);
-- 
cgit v1.2.3-55-g7522


From 2b16e39ee0a431d6cf6e6ca33bb08ec7dc82073f Mon Sep 17 00:00:00 2001
From: Florian Fainelli
Date: Mon, 8 Oct 2012 15:11:26 +0200
Subject: USB: ohci: allow platform driver to specify the number of ports

This patch modifies the ohci platform driver to accept the num_ports
parameter to be set via platform_data. Setting the number of ports must be
done after the call to ohci_hcd_init().

Signed-off-by: Florian Fainelli <florian@openwrt.org>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/ohci-platform.c | 4 ++++
 include/linux/usb/ohci_pdriver.h | 2 ++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/host/ohci-platform.c b/drivers/usb/host/ohci-platform.c
index e24ec9f79164..1caaf657c5ea 100644
--- a/drivers/usb/host/ohci-platform.c
+++ b/drivers/usb/host/ohci-platform.c
@@ -31,6 +31,10 @@ static int ohci_platform_reset(struct usb_hcd *hcd)
 		ohci->flags |= OHCI_QUIRK_FRAME_NO;
 
 	ohci_hcd_init(ohci);
+
+	if (pdata->num_ports)
+		ohci->num_ports = pdata->num_ports;
+
 	err = ohci_init(ohci);
 
 	return err;
diff --git a/include/linux/usb/ohci_pdriver.h b/include/linux/usb/ohci_pdriver.h
index 74e7755168b7..012f2b7eb2b6 100644
--- a/include/linux/usb/ohci_pdriver.h
+++ b/include/linux/usb/ohci_pdriver.h
@@ -25,6 +25,7 @@
  * @big_endian_desc:	BE descriptors
  * @big_endian_mmio:	BE registers
  * @no_big_frame_no:	no big endian frame_no shift
+ * @num_ports:		number of ports
  *
  * These are general configuration options for the OHCI controller. All of
  * these options are activating more or less workarounds for some hardware.
@@ -33,6 +34,7 @@ struct usb_ohci_pdata {
 	unsigned	big_endian_desc:1;
 	unsigned	big_endian_mmio:1;
 	unsigned	no_big_frame_no:1;
+	unsigned int	num_ports;
 
 	/* Turn on all power and clocks */
 	int (*power_on)(struct platform_device *pdev);
-- 
cgit v1.2.3-55-g7522


From 1ffdff134eb2d943bde3e4901ac48a9656a7e7a5 Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Thu, 18 Oct 2012 10:15:24 +0200
Subject: drm: dp helper: extract drm_dp_channel_eq_ok

radeon and intel use the exact same definition.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dp_helper.c      | 50 ++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_dp.c      | 35 ++-----------------------
 drivers/gpu/drm/radeon/atombios_dp.c | 24 ++---------------
 include/drm/drm_dp_helper.h          |  5 ++++
 4 files changed, 59 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index bb4eaf60117f..1378b789bd10 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -205,3 +205,53 @@ i2c_dp_aux_add_bus(struct i2c_adapter *adapter)
 	return error;
 }
 EXPORT_SYMBOL(i2c_dp_aux_add_bus);
+
+/* Helpers for DP link training */
+static u8 dp_link_status(u8 link_status[DP_LINK_STATUS_SIZE], int r)
+{
+	return link_status[r - DP_LANE0_1_STATUS];
+}
+
+static u8 dp_get_lane_status(u8 link_status[DP_LINK_STATUS_SIZE],
+			     int lane)
+{
+	int i = DP_LANE0_1_STATUS + (lane >> 1);
+	int s = (lane & 1) * 4;
+	u8 l = dp_link_status(link_status, i);
+	return (l >> s) & 0xf;
+}
+
+bool drm_dp_channel_eq_ok(u8 link_status[DP_LINK_STATUS_SIZE],
+			  int lane_count)
+{
+	u8 lane_align;
+	u8 lane_status;
+	int lane;
+
+	lane_align = dp_link_status(link_status,
+				    DP_LANE_ALIGN_STATUS_UPDATED);
+	if ((lane_align & DP_INTERLANE_ALIGN_DONE) == 0)
+		return false;
+	for (lane = 0; lane < lane_count; lane++) {
+		lane_status = dp_get_lane_status(link_status, lane);
+		if ((lane_status & DP_CHANNEL_EQ_BITS) != DP_CHANNEL_EQ_BITS)
+			return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL(drm_dp_channel_eq_ok);
+
+bool drm_dp_clock_recovery_ok(u8 link_status[DP_LINK_STATUS_SIZE],
+			      int lane_count)
+{
+	int lane;
+	u8 lane_status;
+
+	for (lane = 0; lane < lane_count; lane++) {
+		lane_status = dp_get_lane_status(link_status, lane);
+		if ((lane_status & DP_LANE_CR_DONE) == 0)
+			return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL(drm_dp_clock_recovery_ok);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 38305c93754c..f69044b7f008 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -37,7 +37,6 @@
 #include "i915_drv.h"
 
 #define DP_RECEIVER_CAP_SIZE	0xf
-#define DP_LINK_STATUS_SIZE	6
 #define DP_LINK_CHECK_TIMEOUT	(10 * 1000)
 
 /**
@@ -1436,13 +1435,6 @@ intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_
 					      DP_LINK_STATUS_SIZE);
 }
 
-static uint8_t
-intel_dp_link_status(uint8_t link_status[DP_LINK_STATUS_SIZE],
-		     int r)
-{
-	return link_status[r - DP_LANE0_1_STATUS];
-}
-
 static uint8_t
 intel_get_adjust_request_voltage(uint8_t adjust_request[2],
 				 int lane)
@@ -1728,29 +1720,6 @@ intel_clock_recovery_ok(uint8_t link_status[DP_LINK_STATUS_SIZE], int lane_count
 	return true;
 }
 
-/* Check to see if channel eq is done on all channels */
-#define CHANNEL_EQ_BITS (DP_LANE_CR_DONE|\
-			 DP_LANE_CHANNEL_EQ_DONE|\
-			 DP_LANE_SYMBOL_LOCKED)
-static bool
-intel_channel_eq_ok(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
-{
-	uint8_t lane_align;
-	uint8_t lane_status;
-	int lane;
-
-	lane_align = intel_dp_link_status(link_status,
-					  DP_LANE_ALIGN_STATUS_UPDATED);
-	if ((lane_align & DP_INTERLANE_ALIGN_DONE) == 0)
-		return false;
-	for (lane = 0; lane < intel_dp->lane_count; lane++) {
-		lane_status = intel_get_lane_status(link_status, lane);
-		if ((lane_status & CHANNEL_EQ_BITS) != CHANNEL_EQ_BITS)
-			return false;
-	}
-	return true;
-}
-
 static bool
 intel_dp_set_link_train(struct intel_dp *intel_dp,
 			uint32_t dp_reg_value,
@@ -2004,7 +1973,7 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 			continue;
 		}
 
-		if (intel_channel_eq_ok(intel_dp, link_status)) {
+		if (drm_dp_channel_eq_ok(link_status, intel_dp->lane_count)) {
 			channel_eq = true;
 			break;
 		}
@@ -2223,7 +2192,7 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 			DRM_DEBUG_DRIVER("CP or sink specific irq unhandled\n");
 	}
 
-	if (!intel_channel_eq_ok(intel_dp, link_status)) {
+	if (!drm_dp_channel_eq_ok(link_status, intel_dp->lane_count)) {
 		DRM_DEBUG_KMS("%s: channel EQ not ok, retraining\n",
 			      drm_get_encoder_name(&intel_dp->base.base));
 		intel_dp_start_link_train(intel_dp);
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index d5699fe4f1e8..3f46bb1bb987 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -34,7 +34,6 @@
 
 /* move these to drm_dp_helper.c/h */
 #define DP_LINK_CONFIGURATION_SIZE 9
-#define DP_LINK_STATUS_SIZE	   6
 #define DP_DPCD_SIZE	           8
 
 static char *voltage_names[] = {
@@ -318,25 +317,6 @@ static bool dp_clock_recovery_ok(u8 link_status[DP_LINK_STATUS_SIZE],
 	return true;
 }
 
-static bool dp_channel_eq_ok(u8 link_status[DP_LINK_STATUS_SIZE],
-			     int lane_count)
-{
-	u8 lane_align;
-	u8 lane_status;
-	int lane;
-
-	lane_align = dp_link_status(link_status,
-				    DP_LANE_ALIGN_STATUS_UPDATED);
-	if ((lane_align & DP_INTERLANE_ALIGN_DONE) == 0)
-		return false;
-	for (lane = 0; lane < lane_count; lane++) {
-		lane_status = dp_get_lane_status(link_status, lane);
-		if ((lane_status & DP_CHANNEL_EQ_BITS) != DP_CHANNEL_EQ_BITS)
-			return false;
-	}
-	return true;
-}
-
 static u8 dp_get_adjust_request_voltage(u8 link_status[DP_LINK_STATUS_SIZE],
 					int lane)
 
@@ -664,7 +644,7 @@ bool radeon_dp_needs_link_train(struct radeon_connector *radeon_connector)
 
 	if (!radeon_dp_get_link_status(radeon_connector, link_status))
 		return false;
-	if (dp_channel_eq_ok(link_status, dig->dp_lane_count))
+	if (drm_dp_channel_eq_ok(link_status, dig->dp_lane_count))
 		return false;
 	return true;
 }
@@ -896,7 +876,7 @@ static int radeon_dp_link_train_ce(struct radeon_dp_link_train_info *dp_info)
 			break;
 		}
 
-		if (dp_channel_eq_ok(dp_info->link_status, dp_info->dp_lane_count)) {
+		if (drm_dp_channel_eq_ok(dp_info->link_status, dp_info->dp_lane_count)) {
 			channel_eq = true;
 			break;
 		}
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index fe061489f91f..9e1042073f67 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -322,4 +322,9 @@ struct i2c_algo_dp_aux_data {
 int
 i2c_dp_aux_add_bus(struct i2c_adapter *adapter);
 
+
+#define DP_LINK_STATUS_SIZE	   6
+bool drm_dp_channel_eq_ok(u8 link_status[DP_LINK_STATUS_SIZE],
+			  int lane_count);
+
 #endif /* _DRM_DP_HELPER_H_ */
-- 
cgit v1.2.3-55-g7522


From 01916270b840f7f37b7daab936add1747d6afbbf Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Thu, 18 Oct 2012 10:15:25 +0200
Subject: drm: dp helper: extract drm_dp_clock_recovery_ok

radeon and intel use the exact same definition.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Dave Airlie <airlied@gmail.com>

v2: Kill 2 more helpers in intel_dp.c that I've missed.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_dp.c      | 29 ++---------------------------
 drivers/gpu/drm/radeon/atombios_dp.c | 25 +------------------------
 include/drm/drm_dp_helper.h          |  2 ++
 3 files changed, 5 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index f69044b7f008..401db1d42da1 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1695,31 +1695,6 @@ intel_dp_signal_levels_hsw(uint8_t train_set)
 	}
 }
 
-static uint8_t
-intel_get_lane_status(uint8_t link_status[DP_LINK_STATUS_SIZE],
-		      int lane)
-{
-	int s = (lane & 1) * 4;
-	uint8_t l = link_status[lane>>1];
-
-	return (l >> s) & 0xf;
-}
-
-/* Check for clock recovery is done on all channels */
-static bool
-intel_clock_recovery_ok(uint8_t link_status[DP_LINK_STATUS_SIZE], int lane_count)
-{
-	int lane;
-	uint8_t lane_status;
-
-	for (lane = 0; lane < lane_count; lane++) {
-		lane_status = intel_get_lane_status(link_status, lane);
-		if ((lane_status & DP_LANE_CR_DONE) == 0)
-			return false;
-	}
-	return true;
-}
-
 static bool
 intel_dp_set_link_train(struct intel_dp *intel_dp,
 			uint32_t dp_reg_value,
@@ -1885,7 +1860,7 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 			break;
 		}
 
-		if (intel_clock_recovery_ok(link_status, intel_dp->lane_count)) {
+		if (drm_dp_clock_recovery_ok(link_status, intel_dp->lane_count)) {
 			DRM_DEBUG_KMS("clock recovery OK\n");
 			clock_recovery = true;
 			break;
@@ -1967,7 +1942,7 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 			break;
 
 		/* Make sure clock is still ok */
-		if (!intel_clock_recovery_ok(link_status, intel_dp->lane_count)) {
+		if (!drm_dp_clock_recovery_ok(link_status, intel_dp->lane_count)) {
 			intel_dp_start_link_train(intel_dp);
 			cr_tries++;
 			continue;
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 3f46bb1bb987..65f0c6049472 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -294,29 +294,6 @@ static u8 dp_link_status(u8 link_status[DP_LINK_STATUS_SIZE], int r)
 	return link_status[r - DP_LANE0_1_STATUS];
 }
 
-static u8 dp_get_lane_status(u8 link_status[DP_LINK_STATUS_SIZE],
-			     int lane)
-{
-	int i = DP_LANE0_1_STATUS + (lane >> 1);
-	int s = (lane & 1) * 4;
-	u8 l = dp_link_status(link_status, i);
-	return (l >> s) & 0xf;
-}
-
-static bool dp_clock_recovery_ok(u8 link_status[DP_LINK_STATUS_SIZE],
-				 int lane_count)
-{
-	int lane;
-	u8 lane_status;
-
-	for (lane = 0; lane < lane_count; lane++) {
-		lane_status = dp_get_lane_status(link_status, lane);
-		if ((lane_status & DP_LANE_CR_DONE) == 0)
-			return false;
-	}
-	return true;
-}
-
 static u8 dp_get_adjust_request_voltage(u8 link_status[DP_LINK_STATUS_SIZE],
 					int lane)
 
@@ -811,7 +788,7 @@ static int radeon_dp_link_train_cr(struct radeon_dp_link_train_info *dp_info)
 			break;
 		}
 
-		if (dp_clock_recovery_ok(dp_info->link_status, dp_info->dp_lane_count)) {
+		if (drm_dp_clock_recovery_ok(dp_info->link_status, dp_info->dp_lane_count)) {
 			clock_recovery = true;
 			break;
 		}
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 9e1042073f67..89e92c95cf86 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -326,5 +326,7 @@ i2c_dp_aux_add_bus(struct i2c_adapter *adapter);
 #define DP_LINK_STATUS_SIZE	   6
 bool drm_dp_channel_eq_ok(u8 link_status[DP_LINK_STATUS_SIZE],
 			  int lane_count);
+bool drm_dp_clock_recovery_ok(u8 link_status[DP_LINK_STATUS_SIZE],
+			      int lane_count);
 
 #endif /* _DRM_DP_HELPER_H_ */
-- 
cgit v1.2.3-55-g7522


From 0f037bdee1a12947a0c55b21a05f57793332bc07 Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Thu, 18 Oct 2012 10:15:27 +0200
Subject: drm: extract helpers to compute new training values from sink request

Safe for the minor difference that the intel versions get an offset
into the link_status as an argument, both are the same again.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dp_helper.c      | 27 +++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_dp.c      | 30 ++----------------------------
 drivers/gpu/drm/radeon/atombios_dp.c | 34 ++--------------------------------
 include/drm/drm_dp_helper.h          |  4 ++++
 4 files changed, 35 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 1378b789bd10..9461e2f27316 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -255,3 +255,30 @@ bool drm_dp_clock_recovery_ok(u8 link_status[DP_LINK_STATUS_SIZE],
 	return true;
 }
 EXPORT_SYMBOL(drm_dp_clock_recovery_ok);
+
+u8 drm_dp_get_adjust_request_voltage(u8 link_status[DP_LINK_STATUS_SIZE],
+				     int lane)
+{
+	int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
+	int s = ((lane & 1) ?
+		 DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT :
+		 DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT);
+	u8 l = dp_link_status(link_status, i);
+
+	return ((l >> s) & 0x3) << DP_TRAIN_VOLTAGE_SWING_SHIFT;
+}
+EXPORT_SYMBOL(drm_dp_get_adjust_request_voltage);
+
+u8 drm_dp_get_adjust_request_pre_emphasis(u8 link_status[DP_LINK_STATUS_SIZE],
+					  int lane)
+{
+	int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
+	int s = ((lane & 1) ?
+		 DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT :
+		 DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT);
+	u8 l = dp_link_status(link_status, i);
+
+	return ((l >> s) & 0x3) << DP_TRAIN_PRE_EMPHASIS_SHIFT;
+}
+EXPORT_SYMBOL(drm_dp_get_adjust_request_pre_emphasis);
+
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 401db1d42da1..016febc9b55e 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1435,31 +1435,6 @@ intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_
 					      DP_LINK_STATUS_SIZE);
 }
 
-static uint8_t
-intel_get_adjust_request_voltage(uint8_t adjust_request[2],
-				 int lane)
-{
-	int	    s = ((lane & 1) ?
-			 DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT :
-			 DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT);
-	uint8_t l = adjust_request[lane>>1];
-
-	return ((l >> s) & 3) << DP_TRAIN_VOLTAGE_SWING_SHIFT;
-}
-
-static uint8_t
-intel_get_adjust_request_pre_emphasis(uint8_t adjust_request[2],
-				      int lane)
-{
-	int	    s = ((lane & 1) ?
-			 DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT :
-			 DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT);
-	uint8_t l = adjust_request[lane>>1];
-
-	return ((l >> s) & 3) << DP_TRAIN_PRE_EMPHASIS_SHIFT;
-}
-
-
 #if 0
 static char	*voltage_names[] = {
 	"0.4V", "0.6V", "0.8V", "1.2V"
@@ -1538,13 +1513,12 @@ intel_get_adjust_train(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_ST
 	uint8_t v = 0;
 	uint8_t p = 0;
 	int lane;
-	uint8_t	*adjust_request = link_status + (DP_ADJUST_REQUEST_LANE0_1 - DP_LANE0_1_STATUS);
 	uint8_t voltage_max;
 	uint8_t preemph_max;
 
 	for (lane = 0; lane < intel_dp->lane_count; lane++) {
-		uint8_t this_v = intel_get_adjust_request_voltage(adjust_request, lane);
-		uint8_t this_p = intel_get_adjust_request_pre_emphasis(adjust_request, lane);
+		uint8_t this_v = drm_dp_get_adjust_request_voltage(link_status, lane);
+		uint8_t this_p = drm_dp_get_adjust_request_pre_emphasis(link_status, lane);
 
 		if (this_v > v)
 			v = this_v;
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 65f0c6049472..5ad8bfacf728 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -289,36 +289,6 @@ int radeon_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 
 /***** general DP utility functions *****/
 
-static u8 dp_link_status(u8 link_status[DP_LINK_STATUS_SIZE], int r)
-{
-	return link_status[r - DP_LANE0_1_STATUS];
-}
-
-static u8 dp_get_adjust_request_voltage(u8 link_status[DP_LINK_STATUS_SIZE],
-					int lane)
-
-{
-	int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
-	int s = ((lane & 1) ?
-		 DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT :
-		 DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT);
-	u8 l = dp_link_status(link_status, i);
-
-	return ((l >> s) & 0x3) << DP_TRAIN_VOLTAGE_SWING_SHIFT;
-}
-
-static u8 dp_get_adjust_request_pre_emphasis(u8 link_status[DP_LINK_STATUS_SIZE],
-					     int lane)
-{
-	int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
-	int s = ((lane & 1) ?
-		 DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT :
-		 DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT);
-	u8 l = dp_link_status(link_status, i);
-
-	return ((l >> s) & 0x3) << DP_TRAIN_PRE_EMPHASIS_SHIFT;
-}
-
 #define DP_VOLTAGE_MAX         DP_TRAIN_VOLTAGE_SWING_1200
 #define DP_PRE_EMPHASIS_MAX    DP_TRAIN_PRE_EMPHASIS_9_5
 
@@ -331,8 +301,8 @@ static void dp_get_adjust_train(u8 link_status[DP_LINK_STATUS_SIZE],
 	int lane;
 
 	for (lane = 0; lane < lane_count; lane++) {
-		u8 this_v = dp_get_adjust_request_voltage(link_status, lane);
-		u8 this_p = dp_get_adjust_request_pre_emphasis(link_status, lane);
+		u8 this_v = drm_dp_get_adjust_request_voltage(link_status, lane);
+		u8 this_p = drm_dp_get_adjust_request_pre_emphasis(link_status, lane);
 
 		DRM_DEBUG_KMS("requested signal parameters: lane %d voltage %s pre_emph %s\n",
 			  lane,
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 89e92c95cf86..57e6dbd0580c 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -328,5 +328,9 @@ bool drm_dp_channel_eq_ok(u8 link_status[DP_LINK_STATUS_SIZE],
 			  int lane_count);
 bool drm_dp_clock_recovery_ok(u8 link_status[DP_LINK_STATUS_SIZE],
 			      int lane_count);
+u8 drm_dp_get_adjust_request_voltage(u8 link_status[DP_LINK_STATUS_SIZE],
+				     int lane);
+u8 drm_dp_get_adjust_request_pre_emphasis(u8 link_status[DP_LINK_STATUS_SIZE],
+					  int lane);
 
 #endif /* _DRM_DP_HELPER_H_ */
-- 
cgit v1.2.3-55-g7522


From 1a644cd47ca0c40a9210db170bd0630031c3a60b Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Thu, 18 Oct 2012 15:32:40 +0200
Subject: drm: extract dp link train delay functions from radeon

This requires a few changes since that dpcd value is above the
range currently cached by radeon. I've check the dp specs, and
above 0xf there's a big gap and nothing that looks like we should
cache it while a given device is plugged in. It's also the same value
that i915.ko uses.

Hence extend the various dpcd arrays in the radeon driver, use
proper symbolic constants where applicable (one place overallocated
the dpcd array to 25 bytes). Then also drop the rd_interval cache -
radeon_dp_link_train_init re-reads the dpcd block, so the values we'll
consume in train_cr and train_ce will always be fresh.

To avoid needless diff-churn, #define the old size of dpcd as the new
one and keep it around.

v2: Alex Deucher noticed one place where I've forgotten to replace 8
with DP_RECEIVER_CAP_SIZE.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dp_helper.c      | 15 +++++++++++++++
 drivers/gpu/drm/i915/intel_dp.c      |  1 -
 drivers/gpu/drm/radeon/atombios_dp.c | 27 ++++++++++-----------------
 drivers/gpu/drm/radeon/radeon_mode.h |  2 +-
 include/drm/drm_dp_helper.h          |  5 +++++
 5 files changed, 31 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 9461e2f27316..7ecaa11f35f6 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -282,3 +282,18 @@ u8 drm_dp_get_adjust_request_pre_emphasis(u8 link_status[DP_LINK_STATUS_SIZE],
 }
 EXPORT_SYMBOL(drm_dp_get_adjust_request_pre_emphasis);
 
+void drm_dp_link_train_clock_recovery_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]) {
+	if (dpcd[DP_TRAINING_AUX_RD_INTERVAL] == 0)
+		udelay(100);
+	else
+		mdelay(dpcd[DP_TRAINING_AUX_RD_INTERVAL] * 4);
+}
+EXPORT_SYMBOL(drm_dp_link_train_clock_recovery_delay);
+
+void drm_dp_link_train_channel_eq_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]) {
+	if (dpcd[DP_TRAINING_AUX_RD_INTERVAL] == 0)
+		udelay(400);
+	else
+		mdelay(dpcd[DP_TRAINING_AUX_RD_INTERVAL] * 4);
+}
+EXPORT_SYMBOL(drm_dp_link_train_channel_eq_delay);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 016febc9b55e..cd23ffadfda1 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -36,7 +36,6 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
-#define DP_RECEIVER_CAP_SIZE	0xf
 #define DP_LINK_CHECK_TIMEOUT	(10 * 1000)
 
 /**
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 5ad8bfacf728..5e23ab27ae46 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -34,7 +34,7 @@
 
 /* move these to drm_dp_helper.c/h */
 #define DP_LINK_CONFIGURATION_SIZE 9
-#define DP_DPCD_SIZE	           8
+#define DP_DPCD_SIZE DP_RECEIVER_CAP_SIZE
 
 static char *voltage_names[] = {
         "0.4V", "0.6V", "0.8V", "1.2V"
@@ -478,14 +478,15 @@ static void radeon_dp_probe_oui(struct radeon_connector *radeon_connector)
 bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector)
 {
 	struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv;
-	u8 msg[25];
+	u8 msg[DP_DPCD_SIZE];
 	int ret, i;
 
-	ret = radeon_dp_aux_native_read(radeon_connector, DP_DPCD_REV, msg, 8, 0);
+	ret = radeon_dp_aux_native_read(radeon_connector, DP_DPCD_REV, msg,
+					DP_DPCD_SIZE, 0);
 	if (ret > 0) {
-		memcpy(dig_connector->dpcd, msg, 8);
+		memcpy(dig_connector->dpcd, msg, DP_DPCD_SIZE);
 		DRM_DEBUG_KMS("DPCD: ");
-		for (i = 0; i < 8; i++)
+		for (i = 0; i < DP_DPCD_SIZE; i++)
 			DRM_DEBUG_KMS("%02x ", msg[i]);
 		DRM_DEBUG_KMS("\n");
 
@@ -604,9 +605,8 @@ struct radeon_dp_link_train_info {
 	int enc_id;
 	int dp_clock;
 	int dp_lane_count;
-	int rd_interval;
 	bool tp3_supported;
-	u8 dpcd[8];
+	u8 dpcd[DP_RECEIVER_CAP_SIZE];
 	u8 train_set[4];
 	u8 link_status[DP_LINK_STATUS_SIZE];
 	u8 tries;
@@ -748,10 +748,7 @@ static int radeon_dp_link_train_cr(struct radeon_dp_link_train_info *dp_info)
 	dp_info->tries = 0;
 	voltage = 0xff;
 	while (1) {
-		if (dp_info->rd_interval == 0)
-			udelay(100);
-		else
-			mdelay(dp_info->rd_interval * 4);
+		drm_dp_link_train_clock_recovery_delay(dp_info->dpcd);
 
 		if (!radeon_dp_get_link_status(dp_info->radeon_connector, dp_info->link_status)) {
 			DRM_ERROR("displayport link status failed\n");
@@ -813,10 +810,7 @@ static int radeon_dp_link_train_ce(struct radeon_dp_link_train_info *dp_info)
 	dp_info->tries = 0;
 	channel_eq = false;
 	while (1) {
-		if (dp_info->rd_interval == 0)
-			udelay(400);
-		else
-			mdelay(dp_info->rd_interval * 4);
+		drm_dp_link_train_channel_eq_delay(dp_info->dpcd);
 
 		if (!radeon_dp_get_link_status(dp_info->radeon_connector, dp_info->link_status)) {
 			DRM_ERROR("displayport link status failed\n");
@@ -901,14 +895,13 @@ void radeon_dp_link_train(struct drm_encoder *encoder,
 	else
 		dp_info.enc_id |= ATOM_DP_CONFIG_LINK_A;
 
-	dp_info.rd_interval = radeon_read_dpcd_reg(radeon_connector, DP_TRAINING_AUX_RD_INTERVAL);
 	tmp = radeon_read_dpcd_reg(radeon_connector, DP_MAX_LANE_COUNT);
 	if (ASIC_IS_DCE5(rdev) && (tmp & DP_TPS3_SUPPORTED))
 		dp_info.tp3_supported = true;
 	else
 		dp_info.tp3_supported = false;
 
-	memcpy(dp_info.dpcd, dig_connector->dpcd, 8);
+	memcpy(dp_info.dpcd, dig_connector->dpcd, DP_RECEIVER_CAP_SIZE);
 	dp_info.rdev = rdev;
 	dp_info.encoder = encoder;
 	dp_info.connector = connector;
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 92c5f473cf08..d818b503b42f 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -427,7 +427,7 @@ struct radeon_connector_atom_dig {
 	uint32_t igp_lane_info;
 	/* displayport */
 	struct radeon_i2c_chan *dp_i2c_bus;
-	u8 dpcd[8];
+	u8 dpcd[DP_RECEIVER_CAP_SIZE];
 	u8 dp_sink_type;
 	int dp_clock;
 	int dp_lane_count;
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 57e6dbd0580c..60bd8d3ae6eb 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -25,6 +25,7 @@
 
 #include <linux/types.h>
 #include <linux/i2c.h>
+#include <linux/delay.h>
 
 /*
  * Unless otherwise noted, all values are from the DP 1.1a spec.  Note that
@@ -333,4 +334,8 @@ u8 drm_dp_get_adjust_request_voltage(u8 link_status[DP_LINK_STATUS_SIZE],
 u8 drm_dp_get_adjust_request_pre_emphasis(u8 link_status[DP_LINK_STATUS_SIZE],
 					  int lane);
 
+#define DP_RECEIVER_CAP_SIZE	0xf
+void drm_dp_link_train_clock_recovery_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]);
+void drm_dp_link_train_channel_eq_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]);
+
 #endif /* _DRM_DP_HELPER_H_ */
-- 
cgit v1.2.3-55-g7522


From 3b5c662e8f536ca47396116de82f08d771727076 Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Thu, 18 Oct 2012 10:15:31 +0200
Subject: drm: extract dp link bw helpers

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dp_helper.c      | 28 ++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_dp.c      |  5 +----
 drivers/gpu/drm/radeon/atombios_dp.c | 32 +++-----------------------------
 include/drm/drm_dp_helper.h          |  8 ++++++++
 4 files changed, 40 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 7ecaa11f35f6..3c4cccd0d753 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -297,3 +297,31 @@ void drm_dp_link_train_channel_eq_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]) {
 		mdelay(dpcd[DP_TRAINING_AUX_RD_INTERVAL] * 4);
 }
 EXPORT_SYMBOL(drm_dp_link_train_channel_eq_delay);
+
+u8 drm_dp_link_rate_to_bw_code(int link_rate)
+{
+	switch (link_rate) {
+	case 162000:
+	default:
+		return DP_LINK_BW_1_62;
+	case 270000:
+		return DP_LINK_BW_2_7;
+	case 540000:
+		return DP_LINK_BW_5_4;
+	}
+}
+EXPORT_SYMBOL(drm_dp_link_rate_to_bw_code);
+
+int drm_dp_bw_code_to_link_rate(u8 link_bw)
+{
+	switch (link_bw) {
+	case DP_LINK_BW_1_62:
+	default:
+		return 162000;
+	case DP_LINK_BW_2_7:
+		return 270000;
+	case DP_LINK_BW_5_4:
+		return 540000;
+	}
+}
+EXPORT_SYMBOL(drm_dp_bw_code_to_link_rate);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 3cb180e38ca1..f7b7bfc455e2 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -108,10 +108,7 @@ intel_edp_link_config(struct intel_encoder *intel_encoder,
 	struct intel_dp *intel_dp = container_of(intel_encoder, struct intel_dp, base);
 
 	*lane_num = intel_dp->lane_count;
-	if (intel_dp->link_bw == DP_LINK_BW_1_62)
-		*link_bw = 162000;
-	else if (intel_dp->link_bw == DP_LINK_BW_2_7)
-		*link_bw = 270000;
+	*link_bw = drm_dp_bw_code_to_link_rate(intel_dp->link_bw);
 }
 
 int
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 5e23ab27ae46..093e17d07574 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -347,37 +347,11 @@ static int dp_get_max_dp_pix_clock(int link_rate,
 	return (link_rate * lane_num * 8) / bpp;
 }
 
-static int dp_get_max_link_rate(u8 dpcd[DP_DPCD_SIZE])
-{
-	switch (dpcd[DP_MAX_LINK_RATE]) {
-	case DP_LINK_BW_1_62:
-	default:
-		return 162000;
-	case DP_LINK_BW_2_7:
-		return 270000;
-	case DP_LINK_BW_5_4:
-		return 540000;
-	}
-}
-
 static u8 dp_get_max_lane_number(u8 dpcd[DP_DPCD_SIZE])
 {
 	return dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK;
 }
 
-static u8 dp_get_dp_link_rate_coded(int link_rate)
-{
-	switch (link_rate) {
-	case 162000:
-	default:
-		return DP_LINK_BW_1_62;
-	case 270000:
-		return DP_LINK_BW_2_7;
-	case 540000:
-		return DP_LINK_BW_5_4;
-	}
-}
-
 /***** radeon specific DP functions *****/
 
 /* First get the min lane# when low rate is used according to pixel clock
@@ -389,7 +363,7 @@ static int radeon_dp_get_dp_lane_number(struct drm_connector *connector,
 					int pix_clock)
 {
 	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	int max_link_rate = dp_get_max_link_rate(dpcd);
+	int max_link_rate = drm_dp_max_link_rate(dpcd);
 	int max_lane_num = dp_get_max_lane_number(dpcd);
 	int lane_num;
 	int max_dp_pix_clock;
@@ -427,7 +401,7 @@ static int radeon_dp_get_dp_link_clock(struct drm_connector *connector,
 			return 540000;
 	}
 
-	return dp_get_max_link_rate(dpcd);
+	return drm_dp_max_link_rate(dpcd);
 }
 
 static u8 radeon_dp_encoder_service(struct radeon_device *rdev,
@@ -692,7 +666,7 @@ static int radeon_dp_link_train_init(struct radeon_dp_link_train_info *dp_info)
 	radeon_write_dpcd_reg(dp_info->radeon_connector, DP_LANE_COUNT_SET, tmp);
 
 	/* set the link rate on the sink */
-	tmp = dp_get_dp_link_rate_coded(dp_info->dp_clock);
+	tmp = drm_dp_link_rate_to_bw_code(dp_info->dp_clock);
 	radeon_write_dpcd_reg(dp_info->radeon_connector, DP_LINK_BW_SET, tmp);
 
 	/* start training on the source */
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 60bd8d3ae6eb..455f8e05ca3f 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -338,4 +338,12 @@ u8 drm_dp_get_adjust_request_pre_emphasis(u8 link_status[DP_LINK_STATUS_SIZE],
 void drm_dp_link_train_clock_recovery_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]);
 void drm_dp_link_train_channel_eq_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]);
 
+u8 drm_dp_link_rate_to_bw_code(int link_rate);
+int drm_dp_bw_code_to_link_rate(u8 link_bw);
+
+static inline int
+drm_dp_max_link_rate(u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	return drm_dp_bw_code_to_link_rate(dpcd[DP_MAX_LINK_RATE]);
+}
 #endif /* _DRM_DP_HELPER_H_ */
-- 
cgit v1.2.3-55-g7522


From 397fe15715ef1457d89f52666d0e249eb5eae64c Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Mon, 22 Oct 2012 22:56:43 +0200
Subject: drm: extract drm_dp_max_lane_count helper

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_dp.c      | 17 ++---------------
 drivers/gpu/drm/radeon/atombios_dp.c |  7 +------
 include/drm/drm_dp_helper.h          |  7 +++++++
 3 files changed, 10 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index f7b7bfc455e2..e0b91cb75d63 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -124,19 +124,6 @@ intel_edp_target_clock(struct intel_encoder *intel_encoder,
 		return mode->clock;
 }
 
-static int
-intel_dp_max_lane_count(struct intel_dp *intel_dp)
-{
-	int max_lane_count = intel_dp->dpcd[DP_MAX_LANE_COUNT] & 0x1f;
-	switch (max_lane_count) {
-	case 1: case 2: case 4:
-		break;
-	default:
-		max_lane_count = 4;
-	}
-	return max_lane_count;
-}
-
 static int
 intel_dp_max_link_bw(struct intel_dp *intel_dp)
 {
@@ -197,7 +184,7 @@ intel_dp_adjust_dithering(struct intel_dp *intel_dp,
 			  bool adjust_mode)
 {
 	int max_link_clock = intel_dp_link_clock(intel_dp_max_link_bw(intel_dp));
-	int max_lanes = intel_dp_max_lane_count(intel_dp);
+	int max_lanes = drm_dp_max_lane_count(intel_dp->dpcd);
 	int max_rate, mode_rate;
 
 	mode_rate = intel_dp_link_required(mode->clock, 24);
@@ -699,7 +686,7 @@ intel_dp_mode_fixup(struct drm_encoder *encoder,
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 	int lane_count, clock;
-	int max_lane_count = intel_dp_max_lane_count(intel_dp);
+	int max_lane_count = drm_dp_max_lane_count(intel_dp->dpcd);
 	int max_clock = intel_dp_max_link_bw(intel_dp) == DP_LINK_BW_2_7 ? 1 : 0;
 	int bpp, mode_rate;
 	static int bws[2] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7 };
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 093e17d07574..064023bed480 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -347,11 +347,6 @@ static int dp_get_max_dp_pix_clock(int link_rate,
 	return (link_rate * lane_num * 8) / bpp;
 }
 
-static u8 dp_get_max_lane_number(u8 dpcd[DP_DPCD_SIZE])
-{
-	return dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK;
-}
-
 /***** radeon specific DP functions *****/
 
 /* First get the min lane# when low rate is used according to pixel clock
@@ -364,7 +359,7 @@ static int radeon_dp_get_dp_lane_number(struct drm_connector *connector,
 {
 	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
 	int max_link_rate = drm_dp_max_link_rate(dpcd);
-	int max_lane_num = dp_get_max_lane_number(dpcd);
+	int max_lane_num = drm_dp_max_lane_count(dpcd);
 	int lane_num;
 	int max_dp_pix_clock;
 
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 455f8e05ca3f..c09d36741c94 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -346,4 +346,11 @@ drm_dp_max_link_rate(u8 dpcd[DP_RECEIVER_CAP_SIZE])
 {
 	return drm_dp_bw_code_to_link_rate(dpcd[DP_MAX_LINK_RATE]);
 }
+
+static inline u8
+drm_dp_max_lane_count(u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	return dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK;
+}
+
 #endif /* _DRM_DP_HELPER_H_ */
-- 
cgit v1.2.3-55-g7522


From 5f986c590fcf4284924fcda991cf14ab32bff49f Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Tue, 23 Oct 2012 01:07:27 +0200
Subject: PM / QoS: Prepare device structure for adding more constraint types

Currently struct dev_pm_info contains only one PM QoS constraints
pointer reserved for latency requirements.  Since one more device
constraints type (i.e. flags) will be necessary, introduce a new
structure, struct dev_pm_qos, that eventually will contain all of
the available device PM QoS constraints and replace the "constraints"
pointer in struct dev_pm_info with a pointer to the new structure
called "qos".

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Jean Pihet <j-pihet@ti.com>
---
 drivers/base/power/qos.c | 42 ++++++++++++++++++++++--------------------
 include/linux/pm.h       |  2 +-
 include/linux/pm_qos.h   |  4 ++++
 3 files changed, 27 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 74a67e0019a2..40ff1b02a7c5 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -55,9 +55,7 @@ static BLOCKING_NOTIFIER_HEAD(dev_pm_notifiers);
  */
 s32 __dev_pm_qos_read_value(struct device *dev)
 {
-	struct pm_qos_constraints *c = dev->power.constraints;
-
-	return c ? pm_qos_read_value(c) : 0;
+	return dev->power.qos ? pm_qos_read_value(&dev->power.qos->latency) : 0;
 }
 
 /**
@@ -91,12 +89,12 @@ static int apply_constraint(struct dev_pm_qos_request *req,
 {
 	int ret, curr_value;
 
-	ret = pm_qos_update_target(req->dev->power.constraints,
+	ret = pm_qos_update_target(&req->dev->power.qos->latency,
 				   &req->node, action, value);
 
 	if (ret) {
 		/* Call the global callbacks if needed */
-		curr_value = pm_qos_read_value(req->dev->power.constraints);
+		curr_value = pm_qos_read_value(&req->dev->power.qos->latency);
 		blocking_notifier_call_chain(&dev_pm_notifiers,
 					     (unsigned long)curr_value,
 					     req);
@@ -114,20 +112,22 @@ static int apply_constraint(struct dev_pm_qos_request *req,
  */
 static int dev_pm_qos_constraints_allocate(struct device *dev)
 {
+	struct dev_pm_qos *qos;
 	struct pm_qos_constraints *c;
 	struct blocking_notifier_head *n;
 
-	c = kzalloc(sizeof(*c), GFP_KERNEL);
-	if (!c)
+	qos = kzalloc(sizeof(*qos), GFP_KERNEL);
+	if (!qos)
 		return -ENOMEM;
 
 	n = kzalloc(sizeof(*n), GFP_KERNEL);
 	if (!n) {
-		kfree(c);
+		kfree(qos);
 		return -ENOMEM;
 	}
 	BLOCKING_INIT_NOTIFIER_HEAD(n);
 
+	c = &qos->latency;
 	plist_head_init(&c->list);
 	c->target_value = PM_QOS_DEV_LAT_DEFAULT_VALUE;
 	c->default_value = PM_QOS_DEV_LAT_DEFAULT_VALUE;
@@ -135,7 +135,7 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	c->notifiers = n;
 
 	spin_lock_irq(&dev->power.lock);
-	dev->power.constraints = c;
+	dev->power.qos = qos;
 	spin_unlock_irq(&dev->power.lock);
 
 	return 0;
@@ -151,7 +151,7 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 void dev_pm_qos_constraints_init(struct device *dev)
 {
 	mutex_lock(&dev_pm_qos_mtx);
-	dev->power.constraints = NULL;
+	dev->power.qos = NULL;
 	dev->power.power_state = PMSG_ON;
 	mutex_unlock(&dev_pm_qos_mtx);
 }
@@ -164,6 +164,7 @@ void dev_pm_qos_constraints_init(struct device *dev)
  */
 void dev_pm_qos_constraints_destroy(struct device *dev)
 {
+	struct dev_pm_qos *qos;
 	struct dev_pm_qos_request *req, *tmp;
 	struct pm_qos_constraints *c;
 
@@ -176,10 +177,11 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 	mutex_lock(&dev_pm_qos_mtx);
 
 	dev->power.power_state = PMSG_INVALID;
-	c = dev->power.constraints;
-	if (!c)
+	qos = dev->power.qos;
+	if (!qos)
 		goto out;
 
+	c = &qos->latency;
 	/* Flush the constraints list for the device */
 	plist_for_each_entry_safe(req, tmp, &c->list, node) {
 		/*
@@ -191,7 +193,7 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 	}
 
 	spin_lock_irq(&dev->power.lock);
-	dev->power.constraints = NULL;
+	dev->power.qos = NULL;
 	spin_unlock_irq(&dev->power.lock);
 
 	kfree(c->notifiers);
@@ -235,7 +237,7 @@ int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
 
 	mutex_lock(&dev_pm_qos_mtx);
 
-	if (!dev->power.constraints) {
+	if (!dev->power.qos) {
 		if (dev->power.power_state.event == PM_EVENT_INVALID) {
 			/* The device has been removed from the system. */
 			req->dev = NULL;
@@ -290,7 +292,7 @@ int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 
 	mutex_lock(&dev_pm_qos_mtx);
 
-	if (req->dev->power.constraints) {
+	if (req->dev->power.qos) {
 		if (new_value != req->node.prio)
 			ret = apply_constraint(req, PM_QOS_UPDATE_REQ,
 					       new_value);
@@ -329,7 +331,7 @@ int dev_pm_qos_remove_request(struct dev_pm_qos_request *req)
 
 	mutex_lock(&dev_pm_qos_mtx);
 
-	if (req->dev->power.constraints) {
+	if (req->dev->power.qos) {
 		ret = apply_constraint(req, PM_QOS_REMOVE_REQ,
 				       PM_QOS_DEFAULT_VALUE);
 		memset(req, 0, sizeof(*req));
@@ -362,13 +364,13 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier)
 
 	mutex_lock(&dev_pm_qos_mtx);
 
-	if (!dev->power.constraints)
+	if (!dev->power.qos)
 		ret = dev->power.power_state.event != PM_EVENT_INVALID ?
 			dev_pm_qos_constraints_allocate(dev) : -ENODEV;
 
 	if (!ret)
 		ret = blocking_notifier_chain_register(
-				dev->power.constraints->notifiers, notifier);
+				dev->power.qos->latency.notifiers, notifier);
 
 	mutex_unlock(&dev_pm_qos_mtx);
 	return ret;
@@ -393,9 +395,9 @@ int dev_pm_qos_remove_notifier(struct device *dev,
 	mutex_lock(&dev_pm_qos_mtx);
 
 	/* Silently return if the constraints object is not present. */
-	if (dev->power.constraints)
+	if (dev->power.qos)
 		retval = blocking_notifier_chain_unregister(
-				dev->power.constraints->notifiers,
+				dev->power.qos->latency.notifiers,
 				notifier);
 
 	mutex_unlock(&dev_pm_qos_mtx);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 007e687c4f69..0ce6df94221a 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -549,7 +549,7 @@ struct dev_pm_info {
 	struct dev_pm_qos_request *pq_req;
 #endif
 	struct pm_subsys_data	*subsys_data;  /* Owned by the subsystem. */
-	struct pm_qos_constraints *constraints;
+	struct dev_pm_qos	*qos;
 };
 
 extern void update_pm_runtime_accounting(struct device *dev);
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 9924ea1f22e0..30e9ad72e797 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -57,6 +57,10 @@ struct pm_qos_constraints {
 	struct blocking_notifier_head *notifiers;
 };
 
+struct dev_pm_qos {
+	struct pm_qos_constraints latency;
+};
+
 /* Action requested to pm_qos_update_target */
 enum pm_qos_req_action {
 	PM_QOS_ADD_REQ,		/* Add a new request */
-- 
cgit v1.2.3-55-g7522


From 5efbe4279f959a3f5ed26adf5f05cb78dd1ffa7e Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Tue, 23 Oct 2012 01:07:46 +0200
Subject: PM / QoS: Introduce request and constraint data types for PM QoS
 flags

Introduce struct pm_qos_flags_request and struct pm_qos_flags
representing PM QoS flags request type and PM QoS flags constraint
type, respectively.  With these definitions the data structures
will be arranged so that the list member of a struct pm_qos_flags
object will contain the head of a list of struct pm_qos_flags_request
objects representing all of the "flags" requests present for the
given device.  Then, the effective_flags member of a struct
pm_qos_flags object will contain the bitwise OR of the flags members
of all the struct pm_qos_flags_request objects in the list.

Additionally, introduce helper function pm_qos_update_flags()
allowing the caller to manage the list of struct pm_qos_flags_request
pointed to by the list member of struct pm_qos_flags.

The flags are of type s32 so that the request's "value" field
is always of the same type regardless of what kind of request it
is (latency requests already have value fields of type s32).

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Jean Pihet <j-pihet@ti.com>
Acked-by: mark gross <markgross@thegnar.org>
---
 include/linux/pm_qos.h | 17 ++++++++++++--
 kernel/power/qos.c     | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 78 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 30e9ad72e797..413ada3c7c97 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -33,6 +33,11 @@ struct pm_qos_request {
 	struct delayed_work work; /* for pm_qos_update_request_timeout */
 };
 
+struct pm_qos_flags_request {
+	struct list_head node;
+	s32 flags;	/* Do not change to 64 bit */
+};
+
 struct dev_pm_qos_request {
 	struct plist_node node;
 	struct device *dev;
@@ -45,8 +50,8 @@ enum pm_qos_type {
 };
 
 /*
- * Note: The lockless read path depends on the CPU accessing
- * target_value atomically.  Atomic access is only guaranteed on all CPU
+ * Note: The lockless read path depends on the CPU accessing target_value
+ * or effective_flags atomically.  Atomic access is only guaranteed on all CPU
  * types linux supports for 32 bit quantites
  */
 struct pm_qos_constraints {
@@ -57,6 +62,11 @@ struct pm_qos_constraints {
 	struct blocking_notifier_head *notifiers;
 };
 
+struct pm_qos_flags {
+	struct list_head list;
+	s32 effective_flags;	/* Do not change to 64 bit */
+};
+
 struct dev_pm_qos {
 	struct pm_qos_constraints latency;
 };
@@ -75,6 +85,9 @@ static inline int dev_pm_qos_request_active(struct dev_pm_qos_request *req)
 
 int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 			 enum pm_qos_req_action action, int value);
+bool pm_qos_update_flags(struct pm_qos_flags *pqf,
+			 struct pm_qos_flags_request *req,
+			 enum pm_qos_req_action action, s32 val);
 void pm_qos_add_request(struct pm_qos_request *req, int pm_qos_class,
 			s32 value);
 void pm_qos_update_request(struct pm_qos_request *req,
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 846bd42c7ed1..2ab2819aee65 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -212,6 +212,69 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 	}
 }
 
+/**
+ * pm_qos_flags_remove_req - Remove device PM QoS flags request.
+ * @pqf: Device PM QoS flags set to remove the request from.
+ * @req: Request to remove from the set.
+ */
+static void pm_qos_flags_remove_req(struct pm_qos_flags *pqf,
+				    struct pm_qos_flags_request *req)
+{
+	s32 val = 0;
+
+	list_del(&req->node);
+	list_for_each_entry(req, &pqf->list, node)
+		val |= req->flags;
+
+	pqf->effective_flags = val;
+}
+
+/**
+ * pm_qos_update_flags - Update a set of PM QoS flags.
+ * @pqf: Set of flags to update.
+ * @req: Request to add to the set, to modify, or to remove from the set.
+ * @action: Action to take on the set.
+ * @val: Value of the request to add or modify.
+ *
+ * Update the given set of PM QoS flags and call notifiers if the aggregate
+ * value has changed.  Returns 1 if the aggregate constraint value has changed,
+ * 0 otherwise.
+ */
+bool pm_qos_update_flags(struct pm_qos_flags *pqf,
+			 struct pm_qos_flags_request *req,
+			 enum pm_qos_req_action action, s32 val)
+{
+	unsigned long irqflags;
+	s32 prev_value, curr_value;
+
+	spin_lock_irqsave(&pm_qos_lock, irqflags);
+
+	prev_value = list_empty(&pqf->list) ? 0 : pqf->effective_flags;
+
+	switch (action) {
+	case PM_QOS_REMOVE_REQ:
+		pm_qos_flags_remove_req(pqf, req);
+		break;
+	case PM_QOS_UPDATE_REQ:
+		pm_qos_flags_remove_req(pqf, req);
+	case PM_QOS_ADD_REQ:
+		req->flags = val;
+		INIT_LIST_HEAD(&req->node);
+		list_add_tail(&req->node, &pqf->list);
+		pqf->effective_flags |= val;
+		break;
+	default:
+		/* no action */
+		;
+	}
+
+	curr_value = list_empty(&pqf->list) ? 0 : pqf->effective_flags;
+
+	spin_unlock_irqrestore(&pm_qos_lock, irqflags);
+
+	return prev_value != curr_value;
+}
+
 /**
  * pm_qos_request - returns current system wide qos expectation
  * @pm_qos_class: identification of which qos value is requested
-- 
cgit v1.2.3-55-g7522


From 021c870ba4ab4bc9a23d5db4e324f50f26d8ab24 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Tue, 23 Oct 2012 01:09:00 +0200
Subject: PM / QoS: Prepare struct dev_pm_qos_request for more request types

The subsequent patches will use struct dev_pm_qos_request for
representing both latency requests and flags requests.  To make that
easier, put the node member of struct dev_pm_qos_request (under the
name "pnode") into a union called "data" that will represent the
request's  value and list node depending on its type.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Jean Pihet <j-pihet@ti.com>
Reviewed-by: mark gross <markgross@thegnar.org>
---
 drivers/base/power/qos.c   | 6 +++---
 drivers/base/power/sysfs.c | 2 +-
 include/linux/pm_qos.h     | 4 +++-
 3 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 40ff1b02a7c5..96d27b821bb8 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -90,7 +90,7 @@ static int apply_constraint(struct dev_pm_qos_request *req,
 	int ret, curr_value;
 
 	ret = pm_qos_update_target(&req->dev->power.qos->latency,
-				   &req->node, action, value);
+				   &req->data.pnode, action, value);
 
 	if (ret) {
 		/* Call the global callbacks if needed */
@@ -183,7 +183,7 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 
 	c = &qos->latency;
 	/* Flush the constraints list for the device */
-	plist_for_each_entry_safe(req, tmp, &c->list, node) {
+	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
 		/*
 		 * Update constraints list and call the notification
 		 * callbacks if needed
@@ -293,7 +293,7 @@ int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 	mutex_lock(&dev_pm_qos_mtx);
 
 	if (req->dev->power.qos) {
-		if (new_value != req->node.prio)
+		if (new_value != req->data.pnode.prio)
 			ret = apply_constraint(req, PM_QOS_UPDATE_REQ,
 					       new_value);
 	} else {
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index b91dc6f1e914..54c61ffa2044 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -221,7 +221,7 @@ static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
 static ssize_t pm_qos_latency_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", dev->power.pq_req->node.prio);
+	return sprintf(buf, "%d\n", dev->power.pq_req->data.pnode.prio);
 }
 
 static ssize_t pm_qos_latency_store(struct device *dev,
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 413ada3c7c97..3b9d14964d2b 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -39,7 +39,9 @@ struct pm_qos_flags_request {
 };
 
 struct dev_pm_qos_request {
-	struct plist_node node;
+	union {
+		struct plist_node pnode;
+	} data;
 	struct device *dev;
 };
 
-- 
cgit v1.2.3-55-g7522


From ae0fb4b72c8db7e6c4ef32bc58a43a759ad414b9 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Tue, 23 Oct 2012 01:09:12 +0200
Subject: PM / QoS: Introduce PM QoS device flags support

Modify the device PM QoS core code to support PM QoS flags requests.

First, add a new field of type struct pm_qos_flags called "flags"
to struct dev_pm_qos for representing the list of PM QoS flags
requests for the given device.  Accordingly, add a new "type" field
to struct dev_pm_qos_request (along with an enum for representing
request types) and a new member called "flr" to its data union for
representig flags requests.

Second, modify dev_pm_qos_add_request(), dev_pm_qos_update_request(),
the internal routine apply_constraint() used by them and their
existing callers to cover flags requests as well as latency
requests.  In particular, dev_pm_qos_add_request() gets a new
argument called "type" for specifying the type of a request to be
added.

Finally, introduce two routines, __dev_pm_qos_flags() and
dev_pm_qos_flags(), allowing their callers to check which PM QoS
flags have been requested for the given device (the caller is
supposed to pass the mask of flags to check as the routine's
second argument and examine its return value for the result).

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Jean Pihet <j-pihet@ti.com>
Reviewed-by: mark gross <markgross@thegnar.org>
---
 Documentation/power/pm_qos_interface.txt |   2 +-
 drivers/base/power/qos.c                 | 124 ++++++++++++++++++++++++-------
 drivers/mtd/nand/sh_flctl.c              |   4 +-
 include/linux/pm_qos.h                   |  26 ++++++-
 4 files changed, 127 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt
index 17e130a80347..79a2a58425ee 100644
--- a/Documentation/power/pm_qos_interface.txt
+++ b/Documentation/power/pm_qos_interface.txt
@@ -99,7 +99,7 @@ reading the aggregated value does not require any locking mechanism.
 
 From kernel mode the use of this interface is the following:
 
-int dev_pm_qos_add_request(device, handle, value):
+int dev_pm_qos_add_request(device, handle, type, value):
 Will insert an element into the list for that identified device with the
 target value.  Upon change to this list the new target is recomputed and any
 registered notifiers are called only if the target value is now different.
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 96d27b821bb8..3c66f75d14b0 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -47,6 +47,50 @@ static DEFINE_MUTEX(dev_pm_qos_mtx);
 
 static BLOCKING_NOTIFIER_HEAD(dev_pm_notifiers);
 
+/**
+ * __dev_pm_qos_flags - Check PM QoS flags for a given device.
+ * @dev: Device to check the PM QoS flags for.
+ * @mask: Flags to check against.
+ *
+ * This routine must be called with dev->power.lock held.
+ */
+enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask)
+{
+	struct dev_pm_qos *qos = dev->power.qos;
+	struct pm_qos_flags *pqf;
+	s32 val;
+
+	if (!qos)
+		return PM_QOS_FLAGS_UNDEFINED;
+
+	pqf = &qos->flags;
+	if (list_empty(&pqf->list))
+		return PM_QOS_FLAGS_UNDEFINED;
+
+	val = pqf->effective_flags & mask;
+	if (val)
+		return (val == mask) ? PM_QOS_FLAGS_ALL : PM_QOS_FLAGS_SOME;
+
+	return PM_QOS_FLAGS_NONE;
+}
+
+/**
+ * dev_pm_qos_flags - Check PM QoS flags for a given device (locked).
+ * @dev: Device to check the PM QoS flags for.
+ * @mask: Flags to check against.
+ */
+enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask)
+{
+	unsigned long irqflags;
+	enum pm_qos_flags_status ret;
+
+	spin_lock_irqsave(&dev->power.lock, irqflags);
+	ret = __dev_pm_qos_flags(dev, mask);
+	spin_unlock_irqrestore(&dev->power.lock, irqflags);
+
+	return ret;
+}
+
 /**
  * __dev_pm_qos_read_value - Get PM QoS constraint for a given device.
  * @dev: Device to get the PM QoS constraint value for.
@@ -74,30 +118,39 @@ s32 dev_pm_qos_read_value(struct device *dev)
 	return ret;
 }
 
-/*
- * apply_constraint
- * @req: constraint request to apply
- * @action: action to perform add/update/remove, of type enum pm_qos_req_action
- * @value: defines the qos request
+/**
+ * apply_constraint - Add/modify/remove device PM QoS request.
+ * @req: Constraint request to apply
+ * @action: Action to perform (add/update/remove).
+ * @value: Value to assign to the QoS request.
  *
  * Internal function to update the constraints list using the PM QoS core
  * code and if needed call the per-device and the global notification
  * callbacks
  */
 static int apply_constraint(struct dev_pm_qos_request *req,
-			    enum pm_qos_req_action action, int value)
+			    enum pm_qos_req_action action, s32 value)
 {
-	int ret, curr_value;
-
-	ret = pm_qos_update_target(&req->dev->power.qos->latency,
-				   &req->data.pnode, action, value);
+	struct dev_pm_qos *qos = req->dev->power.qos;
+	int ret;
 
-	if (ret) {
-		/* Call the global callbacks if needed */
-		curr_value = pm_qos_read_value(&req->dev->power.qos->latency);
-		blocking_notifier_call_chain(&dev_pm_notifiers,
-					     (unsigned long)curr_value,
-					     req);
+	switch(req->type) {
+	case DEV_PM_QOS_LATENCY:
+		ret = pm_qos_update_target(&qos->latency, &req->data.pnode,
+					   action, value);
+		if (ret) {
+			value = pm_qos_read_value(&qos->latency);
+			blocking_notifier_call_chain(&dev_pm_notifiers,
+						     (unsigned long)value,
+						     req);
+		}
+		break;
+	case DEV_PM_QOS_FLAGS:
+		ret = pm_qos_update_flags(&qos->flags, &req->data.flr,
+					  action, value);
+		break;
+	default:
+		ret = -EINVAL;
 	}
 
 	return ret;
@@ -134,6 +187,8 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	c->type = PM_QOS_MIN;
 	c->notifiers = n;
 
+	INIT_LIST_HEAD(&qos->flags.list);
+
 	spin_lock_irq(&dev->power.lock);
 	dev->power.qos = qos;
 	spin_unlock_irq(&dev->power.lock);
@@ -207,6 +262,7 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
  * dev_pm_qos_add_request - inserts new qos request into the list
  * @dev: target device for the constraint
  * @req: pointer to a preallocated handle
+ * @type: type of the request
  * @value: defines the qos request
  *
  * This function inserts a new entry in the device constraints list of
@@ -222,7 +278,7 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
  * from the system.
  */
 int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
-			   s32 value)
+			   enum dev_pm_qos_req_type type, s32 value)
 {
 	int ret = 0;
 
@@ -253,8 +309,10 @@ int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
 		}
 	}
 
-	if (!ret)
+	if (!ret) {
+		req->type = type;
 		ret = apply_constraint(req, PM_QOS_ADD_REQ, value);
+	}
 
  out:
 	mutex_unlock(&dev_pm_qos_mtx);
@@ -281,6 +339,7 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_add_request);
 int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 			      s32 new_value)
 {
+	s32 curr_value;
 	int ret = 0;
 
 	if (!req) /*guard against callers passing in null */
@@ -292,15 +351,27 @@ int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 
 	mutex_lock(&dev_pm_qos_mtx);
 
-	if (req->dev->power.qos) {
-		if (new_value != req->data.pnode.prio)
-			ret = apply_constraint(req, PM_QOS_UPDATE_REQ,
-					       new_value);
-	} else {
-		/* Return if the device has been removed */
+	if (!req->dev->power.qos) {
 		ret = -ENODEV;
+		goto out;
 	}
 
+	switch(req->type) {
+	case DEV_PM_QOS_LATENCY:
+		curr_value = req->data.pnode.prio;
+		break;
+	case DEV_PM_QOS_FLAGS:
+		curr_value = req->data.flr.flags;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (curr_value != new_value)
+		ret = apply_constraint(req, PM_QOS_UPDATE_REQ, new_value);
+
+ out:
 	mutex_unlock(&dev_pm_qos_mtx);
 	return ret;
 }
@@ -451,7 +522,8 @@ int dev_pm_qos_add_ancestor_request(struct device *dev,
 		ancestor = ancestor->parent;
 
 	if (ancestor)
-		error = dev_pm_qos_add_request(ancestor, req, value);
+		error = dev_pm_qos_add_request(ancestor, req,
+					       DEV_PM_QOS_LATENCY, value);
 
 	if (error)
 		req->dev = NULL;
@@ -487,7 +559,7 @@ int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
 	if (!req)
 		return -ENOMEM;
 
-	ret = dev_pm_qos_add_request(dev, req, value);
+	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_LATENCY, value);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index 4fbfe96e37a1..f48ac5d80bbf 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -727,7 +727,9 @@ static void flctl_select_chip(struct mtd_info *mtd, int chipnr)
 
 		if (!flctl->qos_request) {
 			ret = dev_pm_qos_add_request(&flctl->pdev->dev,
-							&flctl->pm_qos, 100);
+							&flctl->pm_qos,
+							DEV_PM_QOS_LATENCY,
+							100);
 			if (ret < 0)
 				dev_err(&flctl->pdev->dev,
 					"PM QoS request failed: %d\n", ret);
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 3b9d14964d2b..3af7d8573c23 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -20,6 +20,13 @@ enum {
 	PM_QOS_NUM_CLASSES,
 };
 
+enum pm_qos_flags_status {
+	PM_QOS_FLAGS_UNDEFINED = -1,
+	PM_QOS_FLAGS_NONE,
+	PM_QOS_FLAGS_SOME,
+	PM_QOS_FLAGS_ALL,
+};
+
 #define PM_QOS_DEFAULT_VALUE -1
 
 #define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
@@ -38,9 +45,16 @@ struct pm_qos_flags_request {
 	s32 flags;	/* Do not change to 64 bit */
 };
 
+enum dev_pm_qos_req_type {
+	DEV_PM_QOS_LATENCY = 1,
+	DEV_PM_QOS_FLAGS,
+};
+
 struct dev_pm_qos_request {
+	enum dev_pm_qos_req_type type;
 	union {
 		struct plist_node pnode;
+		struct pm_qos_flags_request flr;
 	} data;
 	struct device *dev;
 };
@@ -71,6 +85,7 @@ struct pm_qos_flags {
 
 struct dev_pm_qos {
 	struct pm_qos_constraints latency;
+	struct pm_qos_flags flags;
 };
 
 /* Action requested to pm_qos_update_target */
@@ -105,10 +120,12 @@ int pm_qos_request_active(struct pm_qos_request *req);
 s32 pm_qos_read_value(struct pm_qos_constraints *c);
 
 #ifdef CONFIG_PM
+enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask);
+enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask);
 s32 __dev_pm_qos_read_value(struct device *dev);
 s32 dev_pm_qos_read_value(struct device *dev);
 int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
-			   s32 value);
+			   enum dev_pm_qos_req_type type, s32 value);
 int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value);
 int dev_pm_qos_remove_request(struct dev_pm_qos_request *req);
 int dev_pm_qos_add_notifier(struct device *dev,
@@ -122,12 +139,19 @@ void dev_pm_qos_constraints_destroy(struct device *dev);
 int dev_pm_qos_add_ancestor_request(struct device *dev,
 				    struct dev_pm_qos_request *req, s32 value);
 #else
+static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev,
+							  s32 mask)
+			{ return PM_QOS_FLAGS_UNDEFINED; }
+static inline enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev,
+							s32 mask)
+			{ return PM_QOS_FLAGS_UNDEFINED; }
 static inline s32 __dev_pm_qos_read_value(struct device *dev)
 			{ return 0; }
 static inline s32 dev_pm_qos_read_value(struct device *dev)
 			{ return 0; }
 static inline int dev_pm_qos_add_request(struct device *dev,
 					 struct dev_pm_qos_request *req,
+					 enum dev_pm_qos_req_type type,
 					 s32 value)
 			{ return 0; }
 static inline int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
-- 
cgit v1.2.3-55-g7522


From 8fcbaa2b7f5b70dba9ed1c7f91d0a270ce752e2c Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:27 +0200
Subject: TTY: devpts, don't care about TTY in devpts_get_tty

The goal is to stop setting and using tty->driver_data in devpts code.
It should be used solely by the driver's code, pty in this case.

First, here we remove TTY from devpts_get_tty and rename it to
devpts_get_priv. Note we do not remove type safety, we just shift the
[implicit] (void *) cast one layer up.

index was unused in devpts_get_tty, so remove that from the prototype
too.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/pty.c         | 2 +-
 fs/devpts/inode.c         | 9 ++++-----
 include/linux/devpts_fs.h | 7 +++----
 3 files changed, 8 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index a82b39939a9c..65f767154d12 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -547,7 +547,7 @@ static struct tty_struct *pts_unix98_lookup(struct tty_driver *driver,
 	struct tty_struct *tty;
 
 	mutex_lock(&devpts_mutex);
-	tty = devpts_get_tty(pts_inode, idx);
+	tty = devpts_get_priv(pts_inode);
 	mutex_unlock(&devpts_mutex);
 	/* Master must be open before slave */
 	if (!tty)
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 14afbabe6546..47965807884d 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -593,10 +593,10 @@ int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty)
 	return ret;
 }
 
-struct tty_struct *devpts_get_tty(struct inode *pts_inode, int number)
+void *devpts_get_priv(struct inode *pts_inode)
 {
 	struct dentry *dentry;
-	struct tty_struct *tty;
+	void *priv = NULL;
 
 	BUG_ON(pts_inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR));
 
@@ -605,13 +605,12 @@ struct tty_struct *devpts_get_tty(struct inode *pts_inode, int number)
 	if (!dentry)
 		return NULL;
 
-	tty = NULL;
 	if (pts_inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC)
-		tty = (struct tty_struct *)pts_inode->i_private;
+		priv = pts_inode->i_private;
 
 	dput(dentry);
 
-	return tty;
+	return priv;
 }
 
 void devpts_pty_kill(struct tty_struct *tty)
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 5ce0e5fd712e..de635a5505ea 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -21,8 +21,8 @@ int devpts_new_index(struct inode *ptmx_inode);
 void devpts_kill_index(struct inode *ptmx_inode, int idx);
 /* mknod in devpts */
 int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty);
-/* get tty structure */
-struct tty_struct *devpts_get_tty(struct inode *pts_inode, int number);
+/* get private structure */
+void *devpts_get_priv(struct inode *pts_inode);
 /* unlink */
 void devpts_pty_kill(struct tty_struct *tty);
 
@@ -36,8 +36,7 @@ static inline int devpts_pty_new(struct inode *ptmx_inode,
 {
 	return -EINVAL;
 }
-static inline struct tty_struct *devpts_get_tty(struct inode *pts_inode,
-		int number)
+static inline void *devpts_get_priv(struct inode *pts_inode)
 {
 	return NULL;
 }
-- 
cgit v1.2.3-55-g7522


From 162b97cfa21f816f39ede1944f2a4220e3cf8969 Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:28 +0200
Subject: TTY: devpts, return created inode from devpts_pty_new

The goal is to stop setting and using tty->driver_data in devpts code.
It should be used solely by the driver's code, pty in this case.

For the cleanup of layering, we will need the inode created in
devpts_pty_new to be stored into slave's driver_data. So we convert
devpts_pty_new to return the inode or an ERR_PTR-encoded error in case
of failure.

The move of 'inode = new_inode(sb);' from declarators to the code is
only cosmetical, but it makes the code easier to read.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/pty.c         |  7 +++++--
 fs/devpts/inode.c         | 12 ++++++------
 include/linux/devpts_fs.h |  8 ++++----
 3 files changed, 15 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 65f767154d12..9985b451e937 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -614,6 +614,7 @@ static const struct tty_operations pty_unix98_ops = {
 static int ptmx_open(struct inode *inode, struct file *filp)
 {
 	struct tty_struct *tty;
+	struct inode *slave_inode;
 	int retval;
 	int index;
 
@@ -650,9 +651,11 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 
 	tty_add_file(tty, filp);
 
-	retval = devpts_pty_new(inode, tty->link);
-	if (retval)
+	slave_inode = devpts_pty_new(inode, tty->link);
+	if (IS_ERR(slave_inode)) {
+		retval = PTR_ERR(slave_inode);
 		goto err_release;
+	}
 
 	retval = ptm_driver->ops->open(tty, filp);
 	if (retval)
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 47965807884d..ec3bab716c05 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -545,7 +545,7 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
 	mutex_unlock(&allocated_ptys_lock);
 }
 
-int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty)
+struct inode *devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty)
 {
 	/* tty layer puts index from devpts_new_index() in here */
 	int number = tty->index;
@@ -553,19 +553,19 @@ int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty)
 	dev_t device = MKDEV(driver->major, driver->minor_start+number);
 	struct dentry *dentry;
 	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
-	struct inode *inode = new_inode(sb);
+	struct inode *inode;
 	struct dentry *root = sb->s_root;
 	struct pts_fs_info *fsi = DEVPTS_SB(sb);
 	struct pts_mount_opts *opts = &fsi->mount_opts;
-	int ret = 0;
 	char s[12];
 
 	/* We're supposed to be given the slave end of a pty */
 	BUG_ON(driver->type != TTY_DRIVER_TYPE_PTY);
 	BUG_ON(driver->subtype != PTY_TYPE_SLAVE);
 
+	inode = new_inode(sb);
 	if (!inode)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	inode->i_ino = number + 3;
 	inode->i_uid = opts->setuid ? opts->uid : current_fsuid();
@@ -585,12 +585,12 @@ int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty)
 		fsnotify_create(root->d_inode, dentry);
 	} else {
 		iput(inode);
-		ret = -ENOMEM;
+		inode = ERR_PTR(-ENOMEM);
 	}
 
 	mutex_unlock(&root->d_inode->i_mutex);
 
-	return ret;
+	return inode;
 }
 
 void *devpts_get_priv(struct inode *pts_inode)
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index de635a5505ea..4ca846f16fe5 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -20,7 +20,7 @@
 int devpts_new_index(struct inode *ptmx_inode);
 void devpts_kill_index(struct inode *ptmx_inode, int idx);
 /* mknod in devpts */
-int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty);
+struct inode *devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty);
 /* get private structure */
 void *devpts_get_priv(struct inode *pts_inode);
 /* unlink */
@@ -31,10 +31,10 @@ void devpts_pty_kill(struct tty_struct *tty);
 /* Dummy stubs in the no-pty case */
 static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
 static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
-static inline int devpts_pty_new(struct inode *ptmx_inode,
-				struct tty_struct *tty)
+static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
+		struct tty_struct *tty)
 {
-	return -EINVAL;
+	return ERR_PTR(-EINVAL);
 }
 static inline void *devpts_get_priv(struct inode *pts_inode)
 {
-- 
cgit v1.2.3-55-g7522


From f11afb61247016162aa92225a337c1575556c9d9 Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:29 +0200
Subject: TTY: devpts, do not set driver_data

The goal is to stop setting and using tty->driver_data in devpts code.
It should be used solely by the driver's code, pty in this case.

Now driver_data are managed only in the pty driver. devpts_pty_new is
switched to accept what we used to dig out of tty_struct, i.e. device
node number and index.

This also removes a note about driver_data being set outside of the
driver.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/pty.c         | 10 +++++-----
 fs/devpts/inode.c         | 21 ++++++---------------
 include/linux/devpts_fs.h |  9 +++++----
 3 files changed, 16 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 9985b451e937..559e5b27941a 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -4,9 +4,6 @@
  *  Added support for a Unix98-style ptmx device.
  *    -- C. Scott Ananian <cananian@alumni.princeton.edu>, 14-Jan-1998
  *
- *  When reading this code see also fs/devpts. In particular note that the
- *  driver_data field is used by the devpts side as a binding to the devpts
- *  inode.
  */
 
 #include <linux/module.h>
@@ -59,7 +56,7 @@ static void pty_close(struct tty_struct *tty, struct file *filp)
 #ifdef CONFIG_UNIX98_PTYS
 		if (tty->driver == ptm_driver) {
 		        mutex_lock(&devpts_mutex);
-			devpts_pty_kill(tty->link);
+			devpts_pty_kill(tty->link->driver_data);
 		        mutex_unlock(&devpts_mutex);
 		}
 #endif
@@ -651,7 +648,9 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 
 	tty_add_file(tty, filp);
 
-	slave_inode = devpts_pty_new(inode, tty->link);
+	slave_inode = devpts_pty_new(inode,
+			MKDEV(UNIX98_PTY_SLAVE_MAJOR, index), index,
+			tty->link);
 	if (IS_ERR(slave_inode)) {
 		retval = PTR_ERR(slave_inode);
 		goto err_release;
@@ -662,6 +661,7 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 		goto err_release;
 
 	tty_unlock(tty);
+	tty->link->driver_data = slave_inode;
 	return 0;
 err_release:
 	tty_unlock(tty);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index ec3bab716c05..7a20d673bb8a 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -545,12 +545,9 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
 	mutex_unlock(&allocated_ptys_lock);
 }
 
-struct inode *devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty)
+struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
+		void *priv)
 {
-	/* tty layer puts index from devpts_new_index() in here */
-	int number = tty->index;
-	struct tty_driver *driver = tty->driver;
-	dev_t device = MKDEV(driver->major, driver->minor_start+number);
 	struct dentry *dentry;
 	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
 	struct inode *inode;
@@ -559,23 +556,18 @@ struct inode *devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty)
 	struct pts_mount_opts *opts = &fsi->mount_opts;
 	char s[12];
 
-	/* We're supposed to be given the slave end of a pty */
-	BUG_ON(driver->type != TTY_DRIVER_TYPE_PTY);
-	BUG_ON(driver->subtype != PTY_TYPE_SLAVE);
-
 	inode = new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
-	inode->i_ino = number + 3;
+	inode->i_ino = index + 3;
 	inode->i_uid = opts->setuid ? opts->uid : current_fsuid();
 	inode->i_gid = opts->setgid ? opts->gid : current_fsgid();
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	init_special_inode(inode, S_IFCHR|opts->mode, device);
-	inode->i_private = tty;
-	tty->driver_data = inode;
+	inode->i_private = priv;
 
-	sprintf(s, "%d", number);
+	sprintf(s, "%d", index);
 
 	mutex_lock(&root->d_inode->i_mutex);
 
@@ -613,9 +605,8 @@ void *devpts_get_priv(struct inode *pts_inode)
 	return priv;
 }
 
-void devpts_pty_kill(struct tty_struct *tty)
+void devpts_pty_kill(struct inode *inode)
 {
-	struct inode *inode = tty->driver_data;
 	struct super_block *sb = pts_sb_from_inode(inode);
 	struct dentry *root = sb->s_root;
 	struct dentry *dentry;
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 4ca846f16fe5..251a2090a554 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -20,11 +20,12 @@
 int devpts_new_index(struct inode *ptmx_inode);
 void devpts_kill_index(struct inode *ptmx_inode, int idx);
 /* mknod in devpts */
-struct inode *devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty);
+struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
+		void *priv);
 /* get private structure */
 void *devpts_get_priv(struct inode *pts_inode);
 /* unlink */
-void devpts_pty_kill(struct tty_struct *tty);
+void devpts_pty_kill(struct inode *inode);
 
 #else
 
@@ -32,7 +33,7 @@ void devpts_pty_kill(struct tty_struct *tty);
 static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
 static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
 static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
-		struct tty_struct *tty)
+		dev_t device, int index, void *priv)
 {
 	return ERR_PTR(-EINVAL);
 }
@@ -40,7 +41,7 @@ static inline void *devpts_get_priv(struct inode *pts_inode)
 {
 	return NULL;
 }
-static inline void devpts_pty_kill(struct tty_struct *tty) { }
+static inline void devpts_pty_kill(struct inode *inode) { }
 
 #endif
 
-- 
cgit v1.2.3-55-g7522


From 6c633f27ccf783e9a782b84e34aeaeb7949a3359 Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:37 +0200
Subject: TTY: audit, stop accessing tty->icount

This is a private member of n_tty. Stop accessing it. Instead, take is
as an argument.

This is needed to allow clean switch of the private members to a
separate private structure of n_tty.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/n_tty.c     |  5 +++--
 drivers/tty/tty_audit.c | 15 ++++++++-------
 include/linux/tty.h     |  4 ++--
 3 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index ceae0744cbb8..3ebab0cfceb2 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -76,7 +76,7 @@
 static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
 			       unsigned char __user *ptr)
 {
-	tty_audit_add_data(tty, &x, 1);
+	tty_audit_add_data(tty, &x, 1, tty->icanon);
 	return put_user(x, ptr);
 }
 
@@ -1644,7 +1644,8 @@ static int copy_from_read_buf(struct tty_struct *tty,
 		n -= retval;
 		is_eof = n == 1 &&
 			tty->read_buf[tty->read_tail] == EOF_CHAR(tty);
-		tty_audit_add_data(tty, &tty->read_buf[tty->read_tail], n);
+		tty_audit_add_data(tty, &tty->read_buf[tty->read_tail], n,
+				tty->icanon);
 		spin_lock_irqsave(&tty->read_lock, flags);
 		tty->read_tail = (tty->read_tail + n) & (N_TTY_BUF_SIZE-1);
 		tty->read_cnt -= n;
diff --git a/drivers/tty/tty_audit.c b/drivers/tty/tty_audit.c
index b0b39b823ccf..6953dc82850c 100644
--- a/drivers/tty/tty_audit.c
+++ b/drivers/tty/tty_audit.c
@@ -23,7 +23,7 @@ struct tty_audit_buf {
 };
 
 static struct tty_audit_buf *tty_audit_buf_alloc(int major, int minor,
-						 int icanon)
+						 unsigned icanon)
 {
 	struct tty_audit_buf *buf;
 
@@ -239,7 +239,8 @@ int tty_audit_push_task(struct task_struct *tsk, kuid_t loginuid, u32 sessionid)
  *	if TTY auditing is disabled or out of memory.  Otherwise, return a new
  *	reference to the buffer.
  */
-static struct tty_audit_buf *tty_audit_buf_get(struct tty_struct *tty)
+static struct tty_audit_buf *tty_audit_buf_get(struct tty_struct *tty,
+		unsigned icanon)
 {
 	struct tty_audit_buf *buf, *buf2;
 
@@ -257,7 +258,7 @@ static struct tty_audit_buf *tty_audit_buf_get(struct tty_struct *tty)
 
 	buf2 = tty_audit_buf_alloc(tty->driver->major,
 				   tty->driver->minor_start + tty->index,
-				   tty->icanon);
+				   icanon);
 	if (buf2 == NULL) {
 		audit_log_lost("out of memory in TTY auditing");
 		return NULL;
@@ -287,7 +288,7 @@ static struct tty_audit_buf *tty_audit_buf_get(struct tty_struct *tty)
  *	Audit @data of @size from @tty, if necessary.
  */
 void tty_audit_add_data(struct tty_struct *tty, unsigned char *data,
-			size_t size)
+			size_t size, unsigned icanon)
 {
 	struct tty_audit_buf *buf;
 	int major, minor;
@@ -299,7 +300,7 @@ void tty_audit_add_data(struct tty_struct *tty, unsigned char *data,
 	    && tty->driver->subtype == PTY_TYPE_MASTER)
 		return;
 
-	buf = tty_audit_buf_get(tty);
+	buf = tty_audit_buf_get(tty, icanon);
 	if (!buf)
 		return;
 
@@ -307,11 +308,11 @@ void tty_audit_add_data(struct tty_struct *tty, unsigned char *data,
 	major = tty->driver->major;
 	minor = tty->driver->minor_start + tty->index;
 	if (buf->major != major || buf->minor != minor
-	    || buf->icanon != tty->icanon) {
+	    || buf->icanon != icanon) {
 		tty_audit_buf_push_current(buf);
 		buf->major = major;
 		buf->minor = minor;
-		buf->icanon = tty->icanon;
+		buf->icanon = icanon;
 	}
 	do {
 		size_t run;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index f0b4eb47297c..f02712da5d85 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -535,7 +535,7 @@ extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops);
 /* tty_audit.c */
 #ifdef CONFIG_AUDIT
 extern void tty_audit_add_data(struct tty_struct *tty, unsigned char *data,
-			       size_t size);
+			       size_t size, unsigned icanon);
 extern void tty_audit_exit(void);
 extern void tty_audit_fork(struct signal_struct *sig);
 extern void tty_audit_tiocsti(struct tty_struct *tty, char ch);
@@ -544,7 +544,7 @@ extern int tty_audit_push_task(struct task_struct *tsk,
 			       kuid_t loginuid, u32 sessionid);
 #else
 static inline void tty_audit_add_data(struct tty_struct *tty,
-				      unsigned char *data, size_t size)
+		unsigned char *data, size_t size, unsigned icanon)
 {
 }
 static inline void tty_audit_tiocsti(struct tty_struct *tty, char ch)
-- 
cgit v1.2.3-55-g7522


From 53c5ee2cfb4dadc4f5c24fe671e2fbfc034c875e Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:39 +0200
Subject: TTY: move ldisc data from tty_struct: simple members

Here we start moving all the n_tty related bits from tty_struct to
the newly defined n_tty_data struct in n_tty proper.

In this patch primitive members and bits are moved. The rest will be
done per-partes in the next patches.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/n_tty.c  | 160 ++++++++++++++++++++++++++++++---------------------
 drivers/tty/tty_io.c |   1 -
 include/linux/tty.h  |   5 --
 3 files changed, 93 insertions(+), 73 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 3d1594e10d00..bd775a7c0629 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -74,13 +74,20 @@
 #define ECHO_OP_ERASE_TAB 0x82
 
 struct n_tty_data {
-	char dummy;
+	unsigned int column;
+	unsigned long overrun_time;
+	int num_overrun;
+
+	unsigned char lnext:1, erasing:1, raw:1, real_raw:1, icanon:1;
+	unsigned char echo_overrun:1;
 };
 
 static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
 			       unsigned char __user *ptr)
 {
-	tty_audit_add_data(tty, &x, 1, tty->icanon);
+	struct n_tty_data *ldata = tty->disc_data;
+
+	tty_audit_add_data(tty, &x, 1, ldata->icanon);
 	return put_user(x, ptr);
 }
 
@@ -96,6 +103,7 @@ static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
 
 static void n_tty_set_room(struct tty_struct *tty)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	int left;
 	int old_left;
 
@@ -115,7 +123,7 @@ static void n_tty_set_room(struct tty_struct *tty)
 	 * characters will be beeped.
 	 */
 	if (left <= 0)
-		left = tty->icanon && !tty->canon_data;
+		left = ldata->icanon && !tty->canon_data;
 	old_left = tty->receive_room;
 	tty->receive_room = left;
 
@@ -183,6 +191,7 @@ static void check_unthrottle(struct tty_struct *tty)
 
 static void reset_buffer_flags(struct tty_struct *tty)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	unsigned long flags;
 
 	spin_lock_irqsave(&tty->read_lock, flags);
@@ -190,10 +199,10 @@ static void reset_buffer_flags(struct tty_struct *tty)
 	spin_unlock_irqrestore(&tty->read_lock, flags);
 
 	mutex_lock(&tty->echo_lock);
-	tty->echo_pos = tty->echo_cnt = tty->echo_overrun = 0;
+	tty->echo_pos = tty->echo_cnt = ldata->echo_overrun = 0;
 	mutex_unlock(&tty->echo_lock);
 
-	tty->canon_head = tty->canon_data = tty->erasing = 0;
+	tty->canon_head = tty->canon_data = ldata->erasing = 0;
 	memset(&tty->read_flags, 0, sizeof tty->read_flags);
 	n_tty_set_room(tty);
 }
@@ -239,11 +248,12 @@ static void n_tty_flush_buffer(struct tty_struct *tty)
 
 static ssize_t n_tty_chars_in_buffer(struct tty_struct *tty)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	unsigned long flags;
 	ssize_t n = 0;
 
 	spin_lock_irqsave(&tty->read_lock, flags);
-	if (!tty->icanon) {
+	if (!ldata->icanon) {
 		n = tty->read_cnt;
 	} else if (tty->canon_data) {
 		n = (tty->canon_head > tty->read_tail) ?
@@ -305,6 +315,7 @@ static inline int is_continuation(unsigned char c, struct tty_struct *tty)
 
 static int do_output_char(unsigned char c, struct tty_struct *tty, int space)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	int	spaces;
 
 	if (!space)
@@ -313,48 +324,48 @@ static int do_output_char(unsigned char c, struct tty_struct *tty, int space)
 	switch (c) {
 	case '\n':
 		if (O_ONLRET(tty))
-			tty->column = 0;
+			ldata->column = 0;
 		if (O_ONLCR(tty)) {
 			if (space < 2)
 				return -1;
-			tty->canon_column = tty->column = 0;
+			tty->canon_column = ldata->column = 0;
 			tty->ops->write(tty, "\r\n", 2);
 			return 2;
 		}
-		tty->canon_column = tty->column;
+		tty->canon_column = ldata->column;
 		break;
 	case '\r':
-		if (O_ONOCR(tty) && tty->column == 0)
+		if (O_ONOCR(tty) && ldata->column == 0)
 			return 0;
 		if (O_OCRNL(tty)) {
 			c = '\n';
 			if (O_ONLRET(tty))
-				tty->canon_column = tty->column = 0;
+				tty->canon_column = ldata->column = 0;
 			break;
 		}
-		tty->canon_column = tty->column = 0;
+		tty->canon_column = ldata->column = 0;
 		break;
 	case '\t':
-		spaces = 8 - (tty->column & 7);
+		spaces = 8 - (ldata->column & 7);
 		if (O_TABDLY(tty) == XTABS) {
 			if (space < spaces)
 				return -1;
-			tty->column += spaces;
+			ldata->column += spaces;
 			tty->ops->write(tty, "        ", spaces);
 			return spaces;
 		}
-		tty->column += spaces;
+		ldata->column += spaces;
 		break;
 	case '\b':
-		if (tty->column > 0)
-			tty->column--;
+		if (ldata->column > 0)
+			ldata->column--;
 		break;
 	default:
 		if (!iscntrl(c)) {
 			if (O_OLCUC(tty))
 				c = toupper(c);
 			if (!is_continuation(c, tty))
-				tty->column++;
+				ldata->column++;
 		}
 		break;
 	}
@@ -415,6 +426,7 @@ static int process_output(unsigned char c, struct tty_struct *tty)
 static ssize_t process_output_block(struct tty_struct *tty,
 				    const unsigned char *buf, unsigned int nr)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	int	space;
 	int	i;
 	const unsigned char *cp;
@@ -435,30 +447,30 @@ static ssize_t process_output_block(struct tty_struct *tty,
 		switch (c) {
 		case '\n':
 			if (O_ONLRET(tty))
-				tty->column = 0;
+				ldata->column = 0;
 			if (O_ONLCR(tty))
 				goto break_out;
-			tty->canon_column = tty->column;
+			tty->canon_column = ldata->column;
 			break;
 		case '\r':
-			if (O_ONOCR(tty) && tty->column == 0)
+			if (O_ONOCR(tty) && ldata->column == 0)
 				goto break_out;
 			if (O_OCRNL(tty))
 				goto break_out;
-			tty->canon_column = tty->column = 0;
+			tty->canon_column = ldata->column = 0;
 			break;
 		case '\t':
 			goto break_out;
 		case '\b':
-			if (tty->column > 0)
-				tty->column--;
+			if (ldata->column > 0)
+				ldata->column--;
 			break;
 		default:
 			if (!iscntrl(c)) {
 				if (O_OLCUC(tty))
 					goto break_out;
 				if (!is_continuation(c, tty))
-					tty->column++;
+					ldata->column++;
 			}
 			break;
 		}
@@ -498,6 +510,7 @@ break_out:
 
 static void process_echoes(struct tty_struct *tty)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	int	space, nr;
 	unsigned char c;
 	unsigned char *cp, *buf_end;
@@ -559,22 +572,22 @@ static void process_echoes(struct tty_struct *tty)
 				space -= num_bs;
 				while (num_bs--) {
 					tty_put_char(tty, '\b');
-					if (tty->column > 0)
-						tty->column--;
+					if (ldata->column > 0)
+						ldata->column--;
 				}
 				cp += 3;
 				nr -= 3;
 				break;
 
 			case ECHO_OP_SET_CANON_COL:
-				tty->canon_column = tty->column;
+				tty->canon_column = ldata->column;
 				cp += 2;
 				nr -= 2;
 				break;
 
 			case ECHO_OP_MOVE_BACK_COL:
-				if (tty->column > 0)
-					tty->column--;
+				if (ldata->column > 0)
+					ldata->column--;
 				cp += 2;
 				nr -= 2;
 				break;
@@ -586,7 +599,7 @@ static void process_echoes(struct tty_struct *tty)
 					break;
 				}
 				tty_put_char(tty, ECHO_OP_START);
-				tty->column++;
+				ldata->column++;
 				space--;
 				cp += 2;
 				nr -= 2;
@@ -608,7 +621,7 @@ static void process_echoes(struct tty_struct *tty)
 				}
 				tty_put_char(tty, '^');
 				tty_put_char(tty, op ^ 0100);
-				tty->column += 2;
+				ldata->column += 2;
 				space -= 2;
 				cp += 2;
 				nr -= 2;
@@ -641,14 +654,14 @@ static void process_echoes(struct tty_struct *tty)
 	if (nr == 0) {
 		tty->echo_pos = 0;
 		tty->echo_cnt = 0;
-		tty->echo_overrun = 0;
+		ldata->echo_overrun = 0;
 	} else {
 		int num_processed = tty->echo_cnt - nr;
 		tty->echo_pos += num_processed;
 		tty->echo_pos &= N_TTY_BUF_SIZE - 1;
 		tty->echo_cnt = nr;
 		if (num_processed > 0)
-			tty->echo_overrun = 0;
+			ldata->echo_overrun = 0;
 	}
 
 	mutex_unlock(&tty->echo_lock);
@@ -670,6 +683,7 @@ static void process_echoes(struct tty_struct *tty)
 
 static void add_echo_byte(unsigned char c, struct tty_struct *tty)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	int	new_byte_pos;
 
 	if (tty->echo_cnt == N_TTY_BUF_SIZE) {
@@ -695,7 +709,7 @@ static void add_echo_byte(unsigned char c, struct tty_struct *tty)
 		}
 		tty->echo_pos &= N_TTY_BUF_SIZE - 1;
 
-		tty->echo_overrun = 1;
+		ldata->echo_overrun = 1;
 	} else {
 		new_byte_pos = tty->echo_pos + tty->echo_cnt;
 		new_byte_pos &= N_TTY_BUF_SIZE - 1;
@@ -845,9 +859,10 @@ static void echo_char(unsigned char c, struct tty_struct *tty)
 
 static inline void finish_erasing(struct tty_struct *tty)
 {
-	if (tty->erasing) {
+	struct n_tty_data *ldata = tty->disc_data;
+	if (ldata->erasing) {
 		echo_char_raw('/', tty);
-		tty->erasing = 0;
+		ldata->erasing = 0;
 	}
 }
 
@@ -865,6 +880,7 @@ static inline void finish_erasing(struct tty_struct *tty)
 
 static void eraser(unsigned char c, struct tty_struct *tty)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	enum { ERASE, WERASE, KILL } kill_type;
 	int head, seen_alnums, cnt;
 	unsigned long flags;
@@ -932,9 +948,9 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 		spin_unlock_irqrestore(&tty->read_lock, flags);
 		if (L_ECHO(tty)) {
 			if (L_ECHOPRT(tty)) {
-				if (!tty->erasing) {
+				if (!ldata->erasing) {
 					echo_char_raw('\\', tty);
-					tty->erasing = 1;
+					ldata->erasing = 1;
 				}
 				/* if cnt > 1, output a multi-byte character */
 				echo_char(c, tty);
@@ -1056,16 +1072,17 @@ static inline void n_tty_receive_break(struct tty_struct *tty)
 
 static inline void n_tty_receive_overrun(struct tty_struct *tty)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	char buf[64];
 
-	tty->num_overrun++;
-	if (time_before(tty->overrun_time, jiffies - HZ) ||
-			time_after(tty->overrun_time, jiffies)) {
+	ldata->num_overrun++;
+	if (time_after(jiffies, ldata->overrun_time + HZ) ||
+			time_after(ldata->overrun_time, jiffies)) {
 		printk(KERN_WARNING "%s: %d input overrun(s)\n",
 			tty_name(tty, buf),
-			tty->num_overrun);
-		tty->overrun_time = jiffies;
-		tty->num_overrun = 0;
+			ldata->num_overrun);
+		ldata->overrun_time = jiffies;
+		ldata->num_overrun = 0;
 	}
 }
 
@@ -1105,10 +1122,11 @@ static inline void n_tty_receive_parity_error(struct tty_struct *tty,
 
 static inline void n_tty_receive_char(struct tty_struct *tty, unsigned char c)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	unsigned long flags;
 	int parmrk;
 
-	if (tty->raw) {
+	if (ldata->raw) {
 		put_tty_queue(c, tty);
 		return;
 	}
@@ -1147,8 +1165,8 @@ static inline void n_tty_receive_char(struct tty_struct *tty, unsigned char c)
 	 * handle specially, do shortcut processing to speed things
 	 * up.
 	 */
-	if (!test_bit(c, tty->process_char_map) || tty->lnext) {
-		tty->lnext = 0;
+	if (!test_bit(c, tty->process_char_map) || ldata->lnext) {
+		ldata->lnext = 0;
 		parmrk = (c == (unsigned char) '\377' && I_PARMRK(tty)) ? 1 : 0;
 		if (tty->read_cnt >= (N_TTY_BUF_SIZE - parmrk - 1)) {
 			/* beep if no space */
@@ -1222,7 +1240,7 @@ send_signal:
 	} else if (c == '\n' && I_INLCR(tty))
 		c = '\r';
 
-	if (tty->icanon) {
+	if (ldata->icanon) {
 		if (c == ERASE_CHAR(tty) || c == KILL_CHAR(tty) ||
 		    (c == WERASE_CHAR(tty) && L_IEXTEN(tty))) {
 			eraser(c, tty);
@@ -1230,7 +1248,7 @@ send_signal:
 			return;
 		}
 		if (c == LNEXT_CHAR(tty) && L_IEXTEN(tty)) {
-			tty->lnext = 1;
+			ldata->lnext = 1;
 			if (L_ECHO(tty)) {
 				finish_erasing(tty);
 				if (L_ECHOCTL(tty)) {
@@ -1373,13 +1391,14 @@ static void n_tty_write_wakeup(struct tty_struct *tty)
 static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
 			      char *fp, int count)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	const unsigned char *p;
 	char *f, flags = TTY_NORMAL;
 	int	i;
 	char	buf[64];
 	unsigned long cpuflags;
 
-	if (tty->real_raw) {
+	if (ldata->real_raw) {
 		spin_lock_irqsave(&tty->read_lock, cpuflags);
 		i = min(N_TTY_BUF_SIZE - tty->read_cnt,
 			N_TTY_BUF_SIZE - tty->read_head);
@@ -1427,7 +1446,7 @@ static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
 
 	n_tty_set_room(tty);
 
-	if ((!tty->icanon && (tty->read_cnt >= tty->minimum_to_wake)) ||
+	if ((!ldata->icanon && (tty->read_cnt >= tty->minimum_to_wake)) ||
 		L_EXTPROC(tty)) {
 		kill_fasync(&tty->fasync, SIGIO, POLL_IN);
 		if (waitqueue_active(&tty->read_wait))
@@ -1471,6 +1490,7 @@ int is_ignored(int sig)
 
 static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	int canon_change = 1;
 
 	if (old)
@@ -1479,16 +1499,16 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
 		memset(&tty->read_flags, 0, sizeof tty->read_flags);
 		tty->canon_head = tty->read_tail;
 		tty->canon_data = 0;
-		tty->erasing = 0;
+		ldata->erasing = 0;
 	}
 
 	if (canon_change && !L_ICANON(tty) && tty->read_cnt)
 		wake_up_interruptible(&tty->read_wait);
 
-	tty->icanon = (L_ICANON(tty) != 0);
+	ldata->icanon = (L_ICANON(tty) != 0);
 	if (test_bit(TTY_HW_COOK_IN, &tty->flags)) {
-		tty->raw = 1;
-		tty->real_raw = 1;
+		ldata->raw = 1;
+		ldata->real_raw = 1;
 		n_tty_set_room(tty);
 		return;
 	}
@@ -1531,16 +1551,16 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
 			set_bit(SUSP_CHAR(tty), tty->process_char_map);
 		}
 		clear_bit(__DISABLED_CHAR, tty->process_char_map);
-		tty->raw = 0;
-		tty->real_raw = 0;
+		ldata->raw = 0;
+		ldata->real_raw = 0;
 	} else {
-		tty->raw = 1;
+		ldata->raw = 1;
 		if ((I_IGNBRK(tty) || (!I_BRKINT(tty) && !I_PARMRK(tty))) &&
 		    (I_IGNPAR(tty) || !I_INPCK(tty)) &&
 		    (tty->driver->flags & TTY_DRIVER_REAL_RAW))
-			tty->real_raw = 1;
+			ldata->real_raw = 1;
 		else
-			tty->real_raw = 0;
+			ldata->real_raw = 0;
 	}
 	n_tty_set_room(tty);
 	/* The termios change make the tty ready for I/O */
@@ -1589,6 +1609,8 @@ static int n_tty_open(struct tty_struct *tty)
 	if (!ldata)
 		goto err;
 
+	ldata->overrun_time = jiffies;
+
 	/* These are ugly. Currently a malloc failure here can panic */
 	tty->read_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
 	tty->echo_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
@@ -1598,7 +1620,7 @@ static int n_tty_open(struct tty_struct *tty)
 	tty->disc_data = ldata;
 	reset_buffer_flags(tty);
 	tty_unthrottle(tty);
-	tty->column = 0;
+	ldata->column = 0;
 	n_tty_set_termios(tty, NULL);
 	tty->minimum_to_wake = 1;
 	tty->closing = 0;
@@ -1614,8 +1636,10 @@ err:
 
 static inline int input_available_p(struct tty_struct *tty, int amt)
 {
+	struct n_tty_data *ldata = tty->disc_data;
+
 	tty_flush_to_ldisc(tty);
-	if (tty->icanon && !L_EXTPROC(tty)) {
+	if (ldata->icanon && !L_EXTPROC(tty)) {
 		if (tty->canon_data)
 			return 1;
 	} else if (tty->read_cnt >= (amt ? amt : 1))
@@ -1646,6 +1670,7 @@ static int copy_from_read_buf(struct tty_struct *tty,
 				      size_t *nr)
 
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	int retval;
 	size_t n;
 	unsigned long flags;
@@ -1662,12 +1687,12 @@ static int copy_from_read_buf(struct tty_struct *tty,
 		is_eof = n == 1 &&
 			tty->read_buf[tty->read_tail] == EOF_CHAR(tty);
 		tty_audit_add_data(tty, &tty->read_buf[tty->read_tail], n,
-				tty->icanon);
+				ldata->icanon);
 		spin_lock_irqsave(&tty->read_lock, flags);
 		tty->read_tail = (tty->read_tail + n) & (N_TTY_BUF_SIZE-1);
 		tty->read_cnt -= n;
 		/* Turn single EOF into zero-length read */
-		if (L_EXTPROC(tty) && tty->icanon && is_eof && !tty->read_cnt)
+		if (L_EXTPROC(tty) && ldata->icanon && is_eof && !tty->read_cnt)
 			n = 0;
 		spin_unlock_irqrestore(&tty->read_lock, flags);
 		*b += n;
@@ -1736,6 +1761,7 @@ static int job_control(struct tty_struct *tty, struct file *file)
 static ssize_t n_tty_read(struct tty_struct *tty, struct file *file,
 			 unsigned char __user *buf, size_t nr)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	unsigned char __user *b = buf;
 	DECLARE_WAITQUEUE(wait, current);
 	int c;
@@ -1753,7 +1779,7 @@ do_it_again:
 
 	minimum = time = 0;
 	timeout = MAX_SCHEDULE_TIMEOUT;
-	if (!tty->icanon) {
+	if (!ldata->icanon) {
 		time = (HZ / 10) * TIME_CHAR(tty);
 		minimum = MIN_CHAR(tty);
 		if (minimum) {
@@ -1846,7 +1872,7 @@ do_it_again:
 			nr--;
 		}
 
-		if (tty->icanon && !L_EXTPROC(tty)) {
+		if (ldata->icanon && !L_EXTPROC(tty)) {
 			/* N.B. avoid overrun if nr == 0 */
 			spin_lock_irqsave(&tty->read_lock, flags);
 			while (nr && tty->read_cnt) {
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index e835a5b8d089..67b024ca16ec 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2932,7 +2932,6 @@ void initialize_tty_struct(struct tty_struct *tty,
 	tty_ldisc_init(tty);
 	tty->session = NULL;
 	tty->pgrp = NULL;
-	tty->overrun_time = jiffies;
 	tty_buffer_init(tty);
 	mutex_init(&tty->legacy_mutex);
 	mutex_init(&tty->termios_mutex);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index f02712da5d85..de590cec973b 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -270,13 +270,8 @@ struct tty_struct {
 	 * historical reasons, this is included in the tty structure.
 	 * Mostly locked by the BKL.
 	 */
-	unsigned int column;
-	unsigned char lnext:1, erasing:1, raw:1, real_raw:1, icanon:1;
 	unsigned char closing:1;
-	unsigned char echo_overrun:1;
 	unsigned short minimum_to_wake;
-	unsigned long overrun_time;
-	int num_overrun;
 	unsigned long process_char_map[256/(8*sizeof(unsigned long))];
 	char *read_buf;
 	int read_head;
-- 
cgit v1.2.3-55-g7522


From 3fe780b379fac2e1eeb5907ee7c864756ce7ec83 Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:40 +0200
Subject: TTY: move ldisc data from tty_struct: bitmaps

Here we move bitmaps and use DECLARE_BITMAP to declare them in the new
structure. And instead of memset, we use bitmap_zero as it is more
appropriate.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/n_tty.c | 52 ++++++++++++++++++++++++++++------------------------
 include/linux/tty.h |  2 --
 2 files changed, 28 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index bd775a7c0629..702dd4adbdc9 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -80,6 +80,9 @@ struct n_tty_data {
 
 	unsigned char lnext:1, erasing:1, raw:1, real_raw:1, icanon:1;
 	unsigned char echo_overrun:1;
+
+	DECLARE_BITMAP(process_char_map, 256);
+	DECLARE_BITMAP(read_flags, N_TTY_BUF_SIZE);
 };
 
 static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
@@ -203,7 +206,7 @@ static void reset_buffer_flags(struct tty_struct *tty)
 	mutex_unlock(&tty->echo_lock);
 
 	tty->canon_head = tty->canon_data = ldata->erasing = 0;
-	memset(&tty->read_flags, 0, sizeof tty->read_flags);
+	bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
 	n_tty_set_room(tty);
 }
 
@@ -1165,7 +1168,7 @@ static inline void n_tty_receive_char(struct tty_struct *tty, unsigned char c)
 	 * handle specially, do shortcut processing to speed things
 	 * up.
 	 */
-	if (!test_bit(c, tty->process_char_map) || ldata->lnext) {
+	if (!test_bit(c, ldata->process_char_map) || ldata->lnext) {
 		ldata->lnext = 0;
 		parmrk = (c == (unsigned char) '\377' && I_PARMRK(tty)) ? 1 : 0;
 		if (tty->read_cnt >= (N_TTY_BUF_SIZE - parmrk - 1)) {
@@ -1321,7 +1324,7 @@ send_signal:
 
 handle_newline:
 			spin_lock_irqsave(&tty->read_lock, flags);
-			set_bit(tty->read_head, tty->read_flags);
+			set_bit(tty->read_head, ldata->read_flags);
 			put_tty_queue_nolock(c, tty);
 			tty->canon_head = tty->read_head;
 			tty->canon_data++;
@@ -1496,7 +1499,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
 	if (old)
 		canon_change = (old->c_lflag ^ tty->termios.c_lflag) & ICANON;
 	if (canon_change) {
-		memset(&tty->read_flags, 0, sizeof tty->read_flags);
+		bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
 		tty->canon_head = tty->read_tail;
 		tty->canon_data = 0;
 		ldata->erasing = 0;
@@ -1516,41 +1519,41 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
 	    I_ICRNL(tty) || I_INLCR(tty) || L_ICANON(tty) ||
 	    I_IXON(tty) || L_ISIG(tty) || L_ECHO(tty) ||
 	    I_PARMRK(tty)) {
-		memset(tty->process_char_map, 0, 256/8);
+		bitmap_zero(ldata->process_char_map, 256);
 
 		if (I_IGNCR(tty) || I_ICRNL(tty))
-			set_bit('\r', tty->process_char_map);
+			set_bit('\r', ldata->process_char_map);
 		if (I_INLCR(tty))
-			set_bit('\n', tty->process_char_map);
+			set_bit('\n', ldata->process_char_map);
 
 		if (L_ICANON(tty)) {
-			set_bit(ERASE_CHAR(tty), tty->process_char_map);
-			set_bit(KILL_CHAR(tty), tty->process_char_map);
-			set_bit(EOF_CHAR(tty), tty->process_char_map);
-			set_bit('\n', tty->process_char_map);
-			set_bit(EOL_CHAR(tty), tty->process_char_map);
+			set_bit(ERASE_CHAR(tty), ldata->process_char_map);
+			set_bit(KILL_CHAR(tty), ldata->process_char_map);
+			set_bit(EOF_CHAR(tty), ldata->process_char_map);
+			set_bit('\n', ldata->process_char_map);
+			set_bit(EOL_CHAR(tty), ldata->process_char_map);
 			if (L_IEXTEN(tty)) {
 				set_bit(WERASE_CHAR(tty),
-					tty->process_char_map);
+					ldata->process_char_map);
 				set_bit(LNEXT_CHAR(tty),
-					tty->process_char_map);
+					ldata->process_char_map);
 				set_bit(EOL2_CHAR(tty),
-					tty->process_char_map);
+					ldata->process_char_map);
 				if (L_ECHO(tty))
 					set_bit(REPRINT_CHAR(tty),
-						tty->process_char_map);
+						ldata->process_char_map);
 			}
 		}
 		if (I_IXON(tty)) {
-			set_bit(START_CHAR(tty), tty->process_char_map);
-			set_bit(STOP_CHAR(tty), tty->process_char_map);
+			set_bit(START_CHAR(tty), ldata->process_char_map);
+			set_bit(STOP_CHAR(tty), ldata->process_char_map);
 		}
 		if (L_ISIG(tty)) {
-			set_bit(INTR_CHAR(tty), tty->process_char_map);
-			set_bit(QUIT_CHAR(tty), tty->process_char_map);
-			set_bit(SUSP_CHAR(tty), tty->process_char_map);
+			set_bit(INTR_CHAR(tty), ldata->process_char_map);
+			set_bit(QUIT_CHAR(tty), ldata->process_char_map);
+			set_bit(SUSP_CHAR(tty), ldata->process_char_map);
 		}
-		clear_bit(__DISABLED_CHAR, tty->process_char_map);
+		clear_bit(__DISABLED_CHAR, ldata->process_char_map);
 		ldata->raw = 0;
 		ldata->real_raw = 0;
 	} else {
@@ -1879,7 +1882,7 @@ do_it_again:
 				int eol;
 
 				eol = test_and_clear_bit(tty->read_tail,
-						tty->read_flags);
+						ldata->read_flags);
 				c = tty->read_buf[tty->read_tail];
 				tty->read_tail = ((tty->read_tail+1) &
 						  (N_TTY_BUF_SIZE-1));
@@ -2105,6 +2108,7 @@ static unsigned int n_tty_poll(struct tty_struct *tty, struct file *file,
 
 static unsigned long inq_canon(struct tty_struct *tty)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	int nr, head, tail;
 
 	if (!tty->canon_data)
@@ -2114,7 +2118,7 @@ static unsigned long inq_canon(struct tty_struct *tty)
 	nr = (head - tail) & (N_TTY_BUF_SIZE-1);
 	/* Skip EOF-chars.. */
 	while (head != tail) {
-		if (test_bit(tail, tty->read_flags) &&
+		if (test_bit(tail, ldata->read_flags) &&
 		    tty->read_buf[tail] == __DISABLED_CHAR)
 			nr--;
 		tail = (tail+1) & (N_TTY_BUF_SIZE-1);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index de590cec973b..2161e6b5a94c 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -272,12 +272,10 @@ struct tty_struct {
 	 */
 	unsigned char closing:1;
 	unsigned short minimum_to_wake;
-	unsigned long process_char_map[256/(8*sizeof(unsigned long))];
 	char *read_buf;
 	int read_head;
 	int read_tail;
 	int read_cnt;
-	unsigned long read_flags[N_TTY_BUF_SIZE/(8*sizeof(unsigned long))];
 	unsigned char *echo_buf;
 	unsigned int echo_pos;
 	unsigned int echo_cnt;
-- 
cgit v1.2.3-55-g7522


From ba2e68ac6157004ee4922fb39ebd9459bbae883e Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:41 +0200
Subject: TTY: move ldisc data from tty_struct: read_* and echo_* and canon_*
 stuff

All the ring-buffers...

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/n_tty.c | 260 +++++++++++++++++++++++++++-------------------------
 include/linux/tty.h |  10 --
 2 files changed, 137 insertions(+), 133 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 702dd4adbdc9..4794537a50ff 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -83,6 +83,19 @@ struct n_tty_data {
 
 	DECLARE_BITMAP(process_char_map, 256);
 	DECLARE_BITMAP(read_flags, N_TTY_BUF_SIZE);
+
+	char *read_buf;
+	int read_head;
+	int read_tail;
+	int read_cnt;
+
+	unsigned char *echo_buf;
+	unsigned int echo_pos;
+	unsigned int echo_cnt;
+
+	int canon_data;
+	unsigned long canon_head;
+	unsigned int canon_column;
 };
 
 static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
@@ -110,14 +123,14 @@ static void n_tty_set_room(struct tty_struct *tty)
 	int left;
 	int old_left;
 
-	/* tty->read_cnt is not read locked ? */
+	/* ldata->read_cnt is not read locked ? */
 	if (I_PARMRK(tty)) {
 		/* Multiply read_cnt by 3, since each byte might take up to
 		 * three times as many spaces when PARMRK is set (depending on
 		 * its flags, e.g. parity error). */
-		left = N_TTY_BUF_SIZE - tty->read_cnt * 3 - 1;
+		left = N_TTY_BUF_SIZE - ldata->read_cnt * 3 - 1;
 	} else
-		left = N_TTY_BUF_SIZE - tty->read_cnt - 1;
+		left = N_TTY_BUF_SIZE - ldata->read_cnt - 1;
 
 	/*
 	 * If we are doing input canonicalization, and there are no
@@ -126,7 +139,7 @@ static void n_tty_set_room(struct tty_struct *tty)
 	 * characters will be beeped.
 	 */
 	if (left <= 0)
-		left = ldata->icanon && !tty->canon_data;
+		left = ldata->icanon && !ldata->canon_data;
 	old_left = tty->receive_room;
 	tty->receive_room = left;
 
@@ -137,10 +150,12 @@ static void n_tty_set_room(struct tty_struct *tty)
 
 static void put_tty_queue_nolock(unsigned char c, struct tty_struct *tty)
 {
-	if (tty->read_cnt < N_TTY_BUF_SIZE) {
-		tty->read_buf[tty->read_head] = c;
-		tty->read_head = (tty->read_head + 1) & (N_TTY_BUF_SIZE-1);
-		tty->read_cnt++;
+	struct n_tty_data *ldata = tty->disc_data;
+
+	if (ldata->read_cnt < N_TTY_BUF_SIZE) {
+		ldata->read_buf[ldata->read_head] = c;
+		ldata->read_head = (ldata->read_head + 1) & (N_TTY_BUF_SIZE-1);
+		ldata->read_cnt++;
 	}
 }
 
@@ -198,14 +213,14 @@ static void reset_buffer_flags(struct tty_struct *tty)
 	unsigned long flags;
 
 	spin_lock_irqsave(&tty->read_lock, flags);
-	tty->read_head = tty->read_tail = tty->read_cnt = 0;
+	ldata->read_head = ldata->read_tail = ldata->read_cnt = 0;
 	spin_unlock_irqrestore(&tty->read_lock, flags);
 
 	mutex_lock(&tty->echo_lock);
-	tty->echo_pos = tty->echo_cnt = ldata->echo_overrun = 0;
+	ldata->echo_pos = ldata->echo_cnt = ldata->echo_overrun = 0;
 	mutex_unlock(&tty->echo_lock);
 
-	tty->canon_head = tty->canon_data = ldata->erasing = 0;
+	ldata->canon_head = ldata->canon_data = ldata->erasing = 0;
 	bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
 	n_tty_set_room(tty);
 }
@@ -257,11 +272,11 @@ static ssize_t n_tty_chars_in_buffer(struct tty_struct *tty)
 
 	spin_lock_irqsave(&tty->read_lock, flags);
 	if (!ldata->icanon) {
-		n = tty->read_cnt;
-	} else if (tty->canon_data) {
-		n = (tty->canon_head > tty->read_tail) ?
-			tty->canon_head - tty->read_tail :
-			tty->canon_head + (N_TTY_BUF_SIZE - tty->read_tail);
+		n = ldata->read_cnt;
+	} else if (ldata->canon_data) {
+		n = (ldata->canon_head > ldata->read_tail) ?
+			ldata->canon_head - ldata->read_tail :
+			ldata->canon_head + (N_TTY_BUF_SIZE - ldata->read_tail);
 	}
 	spin_unlock_irqrestore(&tty->read_lock, flags);
 	return n;
@@ -331,11 +346,11 @@ static int do_output_char(unsigned char c, struct tty_struct *tty, int space)
 		if (O_ONLCR(tty)) {
 			if (space < 2)
 				return -1;
-			tty->canon_column = ldata->column = 0;
+			ldata->canon_column = ldata->column = 0;
 			tty->ops->write(tty, "\r\n", 2);
 			return 2;
 		}
-		tty->canon_column = ldata->column;
+		ldata->canon_column = ldata->column;
 		break;
 	case '\r':
 		if (O_ONOCR(tty) && ldata->column == 0)
@@ -343,10 +358,10 @@ static int do_output_char(unsigned char c, struct tty_struct *tty, int space)
 		if (O_OCRNL(tty)) {
 			c = '\n';
 			if (O_ONLRET(tty))
-				tty->canon_column = ldata->column = 0;
+				ldata->canon_column = ldata->column = 0;
 			break;
 		}
-		tty->canon_column = ldata->column = 0;
+		ldata->canon_column = ldata->column = 0;
 		break;
 	case '\t':
 		spaces = 8 - (ldata->column & 7);
@@ -453,14 +468,14 @@ static ssize_t process_output_block(struct tty_struct *tty,
 				ldata->column = 0;
 			if (O_ONLCR(tty))
 				goto break_out;
-			tty->canon_column = ldata->column;
+			ldata->canon_column = ldata->column;
 			break;
 		case '\r':
 			if (O_ONOCR(tty) && ldata->column == 0)
 				goto break_out;
 			if (O_OCRNL(tty))
 				goto break_out;
-			tty->canon_column = ldata->column = 0;
+			ldata->canon_column = ldata->column = 0;
 			break;
 		case '\t':
 			goto break_out;
@@ -518,7 +533,7 @@ static void process_echoes(struct tty_struct *tty)
 	unsigned char c;
 	unsigned char *cp, *buf_end;
 
-	if (!tty->echo_cnt)
+	if (!ldata->echo_cnt)
 		return;
 
 	mutex_lock(&tty->output_lock);
@@ -526,9 +541,9 @@ static void process_echoes(struct tty_struct *tty)
 
 	space = tty_write_room(tty);
 
-	buf_end = tty->echo_buf + N_TTY_BUF_SIZE;
-	cp = tty->echo_buf + tty->echo_pos;
-	nr = tty->echo_cnt;
+	buf_end = ldata->echo_buf + N_TTY_BUF_SIZE;
+	cp = ldata->echo_buf + ldata->echo_pos;
+	nr = ldata->echo_cnt;
 	while (nr > 0) {
 		c = *cp;
 		if (c == ECHO_OP_START) {
@@ -565,7 +580,7 @@ static void process_echoes(struct tty_struct *tty)
 				 * Otherwise, tab spacing is normal.
 				 */
 				if (!(num_chars & 0x80))
-					num_chars += tty->canon_column;
+					num_chars += ldata->canon_column;
 				num_bs = 8 - (num_chars & 7);
 
 				if (num_bs > space) {
@@ -583,7 +598,7 @@ static void process_echoes(struct tty_struct *tty)
 				break;
 
 			case ECHO_OP_SET_CANON_COL:
-				tty->canon_column = ldata->column;
+				ldata->canon_column = ldata->column;
 				cp += 2;
 				nr -= 2;
 				break;
@@ -655,14 +670,14 @@ static void process_echoes(struct tty_struct *tty)
 	}
 
 	if (nr == 0) {
-		tty->echo_pos = 0;
-		tty->echo_cnt = 0;
+		ldata->echo_pos = 0;
+		ldata->echo_cnt = 0;
 		ldata->echo_overrun = 0;
 	} else {
-		int num_processed = tty->echo_cnt - nr;
-		tty->echo_pos += num_processed;
-		tty->echo_pos &= N_TTY_BUF_SIZE - 1;
-		tty->echo_cnt = nr;
+		int num_processed = ldata->echo_cnt - nr;
+		ldata->echo_pos += num_processed;
+		ldata->echo_pos &= N_TTY_BUF_SIZE - 1;
+		ldata->echo_cnt = nr;
 		if (num_processed > 0)
 			ldata->echo_overrun = 0;
 	}
@@ -689,37 +704,37 @@ static void add_echo_byte(unsigned char c, struct tty_struct *tty)
 	struct n_tty_data *ldata = tty->disc_data;
 	int	new_byte_pos;
 
-	if (tty->echo_cnt == N_TTY_BUF_SIZE) {
+	if (ldata->echo_cnt == N_TTY_BUF_SIZE) {
 		/* Circular buffer is already at capacity */
-		new_byte_pos = tty->echo_pos;
+		new_byte_pos = ldata->echo_pos;
 
 		/*
 		 * Since the buffer start position needs to be advanced,
 		 * be sure to step by a whole operation byte group.
 		 */
-		if (tty->echo_buf[tty->echo_pos] == ECHO_OP_START) {
-			if (tty->echo_buf[(tty->echo_pos + 1) &
+		if (ldata->echo_buf[ldata->echo_pos] == ECHO_OP_START) {
+			if (ldata->echo_buf[(ldata->echo_pos + 1) &
 					  (N_TTY_BUF_SIZE - 1)] ==
 						ECHO_OP_ERASE_TAB) {
-				tty->echo_pos += 3;
-				tty->echo_cnt -= 2;
+				ldata->echo_pos += 3;
+				ldata->echo_cnt -= 2;
 			} else {
-				tty->echo_pos += 2;
-				tty->echo_cnt -= 1;
+				ldata->echo_pos += 2;
+				ldata->echo_cnt -= 1;
 			}
 		} else {
-			tty->echo_pos++;
+			ldata->echo_pos++;
 		}
-		tty->echo_pos &= N_TTY_BUF_SIZE - 1;
+		ldata->echo_pos &= N_TTY_BUF_SIZE - 1;
 
 		ldata->echo_overrun = 1;
 	} else {
-		new_byte_pos = tty->echo_pos + tty->echo_cnt;
+		new_byte_pos = ldata->echo_pos + ldata->echo_cnt;
 		new_byte_pos &= N_TTY_BUF_SIZE - 1;
-		tty->echo_cnt++;
+		ldata->echo_cnt++;
 	}
 
-	tty->echo_buf[new_byte_pos] = c;
+	ldata->echo_buf[new_byte_pos] = c;
 }
 
 /**
@@ -889,7 +904,7 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 	unsigned long flags;
 
 	/* FIXME: locking needed ? */
-	if (tty->read_head == tty->canon_head) {
+	if (ldata->read_head == ldata->canon_head) {
 		/* process_output('\a', tty); */ /* what do you think? */
 		return;
 	}
@@ -900,17 +915,17 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 	else {
 		if (!L_ECHO(tty)) {
 			spin_lock_irqsave(&tty->read_lock, flags);
-			tty->read_cnt -= ((tty->read_head - tty->canon_head) &
+			ldata->read_cnt -= ((ldata->read_head - ldata->canon_head) &
 					  (N_TTY_BUF_SIZE - 1));
-			tty->read_head = tty->canon_head;
+			ldata->read_head = ldata->canon_head;
 			spin_unlock_irqrestore(&tty->read_lock, flags);
 			return;
 		}
 		if (!L_ECHOK(tty) || !L_ECHOKE(tty) || !L_ECHOE(tty)) {
 			spin_lock_irqsave(&tty->read_lock, flags);
-			tty->read_cnt -= ((tty->read_head - tty->canon_head) &
+			ldata->read_cnt -= ((ldata->read_head - ldata->canon_head) &
 					  (N_TTY_BUF_SIZE - 1));
-			tty->read_head = tty->canon_head;
+			ldata->read_head = ldata->canon_head;
 			spin_unlock_irqrestore(&tty->read_lock, flags);
 			finish_erasing(tty);
 			echo_char(KILL_CHAR(tty), tty);
@@ -924,14 +939,14 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 
 	seen_alnums = 0;
 	/* FIXME: Locking ?? */
-	while (tty->read_head != tty->canon_head) {
-		head = tty->read_head;
+	while (ldata->read_head != ldata->canon_head) {
+		head = ldata->read_head;
 
 		/* erase a single possibly multibyte character */
 		do {
 			head = (head - 1) & (N_TTY_BUF_SIZE-1);
-			c = tty->read_buf[head];
-		} while (is_continuation(c, tty) && head != tty->canon_head);
+			c = ldata->read_buf[head];
+		} while (is_continuation(c, tty) && head != ldata->canon_head);
 
 		/* do not partially erase */
 		if (is_continuation(c, tty))
@@ -944,10 +959,10 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 			else if (seen_alnums)
 				break;
 		}
-		cnt = (tty->read_head - head) & (N_TTY_BUF_SIZE-1);
+		cnt = (ldata->read_head - head) & (N_TTY_BUF_SIZE-1);
 		spin_lock_irqsave(&tty->read_lock, flags);
-		tty->read_head = head;
-		tty->read_cnt -= cnt;
+		ldata->read_head = head;
+		ldata->read_cnt -= cnt;
 		spin_unlock_irqrestore(&tty->read_lock, flags);
 		if (L_ECHO(tty)) {
 			if (L_ECHOPRT(tty)) {
@@ -959,7 +974,7 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 				echo_char(c, tty);
 				while (--cnt > 0) {
 					head = (head+1) & (N_TTY_BUF_SIZE-1);
-					echo_char_raw(tty->read_buf[head], tty);
+					echo_char_raw(ldata->read_buf[head], tty);
 					echo_move_back_col(tty);
 				}
 			} else if (kill_type == ERASE && !L_ECHOE(tty)) {
@@ -967,7 +982,7 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 			} else if (c == '\t') {
 				unsigned int num_chars = 0;
 				int after_tab = 0;
-				unsigned long tail = tty->read_head;
+				unsigned long tail = ldata->read_head;
 
 				/*
 				 * Count the columns used for characters
@@ -976,9 +991,9 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 				 * This info is used to go back the correct
 				 * number of columns.
 				 */
-				while (tail != tty->canon_head) {
+				while (tail != ldata->canon_head) {
 					tail = (tail-1) & (N_TTY_BUF_SIZE-1);
-					c = tty->read_buf[tail];
+					c = ldata->read_buf[tail];
 					if (c == '\t') {
 						after_tab = 1;
 						break;
@@ -1006,7 +1021,7 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 		if (kill_type == ERASE)
 			break;
 	}
-	if (tty->read_head == tty->canon_head && L_ECHO(tty))
+	if (ldata->read_head == ldata->canon_head && L_ECHO(tty))
 		finish_erasing(tty);
 }
 
@@ -1171,7 +1186,7 @@ static inline void n_tty_receive_char(struct tty_struct *tty, unsigned char c)
 	if (!test_bit(c, ldata->process_char_map) || ldata->lnext) {
 		ldata->lnext = 0;
 		parmrk = (c == (unsigned char) '\377' && I_PARMRK(tty)) ? 1 : 0;
-		if (tty->read_cnt >= (N_TTY_BUF_SIZE - parmrk - 1)) {
+		if (ldata->read_cnt >= (N_TTY_BUF_SIZE - parmrk - 1)) {
 			/* beep if no space */
 			if (L_ECHO(tty))
 				process_output('\a', tty);
@@ -1180,7 +1195,7 @@ static inline void n_tty_receive_char(struct tty_struct *tty, unsigned char c)
 		if (L_ECHO(tty)) {
 			finish_erasing(tty);
 			/* Record the column of first canon char. */
-			if (tty->canon_head == tty->read_head)
+			if (ldata->canon_head == ldata->read_head)
 				echo_set_canon_col(tty);
 			echo_char(c, tty);
 			process_echoes(tty);
@@ -1264,20 +1279,20 @@ send_signal:
 		}
 		if (c == REPRINT_CHAR(tty) && L_ECHO(tty) &&
 		    L_IEXTEN(tty)) {
-			unsigned long tail = tty->canon_head;
+			unsigned long tail = ldata->canon_head;
 
 			finish_erasing(tty);
 			echo_char(c, tty);
 			echo_char_raw('\n', tty);
-			while (tail != tty->read_head) {
-				echo_char(tty->read_buf[tail], tty);
+			while (tail != ldata->read_head) {
+				echo_char(ldata->read_buf[tail], tty);
 				tail = (tail+1) & (N_TTY_BUF_SIZE-1);
 			}
 			process_echoes(tty);
 			return;
 		}
 		if (c == '\n') {
-			if (tty->read_cnt >= N_TTY_BUF_SIZE) {
+			if (ldata->read_cnt >= N_TTY_BUF_SIZE) {
 				if (L_ECHO(tty))
 					process_output('\a', tty);
 				return;
@@ -1289,9 +1304,9 @@ send_signal:
 			goto handle_newline;
 		}
 		if (c == EOF_CHAR(tty)) {
-			if (tty->read_cnt >= N_TTY_BUF_SIZE)
+			if (ldata->read_cnt >= N_TTY_BUF_SIZE)
 				return;
-			if (tty->canon_head != tty->read_head)
+			if (ldata->canon_head != ldata->read_head)
 				set_bit(TTY_PUSH, &tty->flags);
 			c = __DISABLED_CHAR;
 			goto handle_newline;
@@ -1300,7 +1315,7 @@ send_signal:
 		    (c == EOL2_CHAR(tty) && L_IEXTEN(tty))) {
 			parmrk = (c == (unsigned char) '\377' && I_PARMRK(tty))
 				 ? 1 : 0;
-			if (tty->read_cnt >= (N_TTY_BUF_SIZE - parmrk)) {
+			if (ldata->read_cnt >= (N_TTY_BUF_SIZE - parmrk)) {
 				if (L_ECHO(tty))
 					process_output('\a', tty);
 				return;
@@ -1310,7 +1325,7 @@ send_signal:
 			 */
 			if (L_ECHO(tty)) {
 				/* Record the column of first canon char. */
-				if (tty->canon_head == tty->read_head)
+				if (ldata->canon_head == ldata->read_head)
 					echo_set_canon_col(tty);
 				echo_char(c, tty);
 				process_echoes(tty);
@@ -1324,10 +1339,10 @@ send_signal:
 
 handle_newline:
 			spin_lock_irqsave(&tty->read_lock, flags);
-			set_bit(tty->read_head, ldata->read_flags);
+			set_bit(ldata->read_head, ldata->read_flags);
 			put_tty_queue_nolock(c, tty);
-			tty->canon_head = tty->read_head;
-			tty->canon_data++;
+			ldata->canon_head = ldata->read_head;
+			ldata->canon_data++;
 			spin_unlock_irqrestore(&tty->read_lock, flags);
 			kill_fasync(&tty->fasync, SIGIO, POLL_IN);
 			if (waitqueue_active(&tty->read_wait))
@@ -1337,7 +1352,7 @@ handle_newline:
 	}
 
 	parmrk = (c == (unsigned char) '\377' && I_PARMRK(tty)) ? 1 : 0;
-	if (tty->read_cnt >= (N_TTY_BUF_SIZE - parmrk - 1)) {
+	if (ldata->read_cnt >= (N_TTY_BUF_SIZE - parmrk - 1)) {
 		/* beep if no space */
 		if (L_ECHO(tty))
 			process_output('\a', tty);
@@ -1349,7 +1364,7 @@ handle_newline:
 			echo_char_raw('\n', tty);
 		else {
 			/* Record the column of first canon char. */
-			if (tty->canon_head == tty->read_head)
+			if (ldata->canon_head == ldata->read_head)
 				echo_set_canon_col(tty);
 			echo_char(c, tty);
 		}
@@ -1403,21 +1418,21 @@ static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
 
 	if (ldata->real_raw) {
 		spin_lock_irqsave(&tty->read_lock, cpuflags);
-		i = min(N_TTY_BUF_SIZE - tty->read_cnt,
-			N_TTY_BUF_SIZE - tty->read_head);
+		i = min(N_TTY_BUF_SIZE - ldata->read_cnt,
+			N_TTY_BUF_SIZE - ldata->read_head);
 		i = min(count, i);
-		memcpy(tty->read_buf + tty->read_head, cp, i);
-		tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1);
-		tty->read_cnt += i;
+		memcpy(ldata->read_buf + ldata->read_head, cp, i);
+		ldata->read_head = (ldata->read_head + i) & (N_TTY_BUF_SIZE-1);
+		ldata->read_cnt += i;
 		cp += i;
 		count -= i;
 
-		i = min(N_TTY_BUF_SIZE - tty->read_cnt,
-			N_TTY_BUF_SIZE - tty->read_head);
+		i = min(N_TTY_BUF_SIZE - ldata->read_cnt,
+			N_TTY_BUF_SIZE - ldata->read_head);
 		i = min(count, i);
-		memcpy(tty->read_buf + tty->read_head, cp, i);
-		tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1);
-		tty->read_cnt += i;
+		memcpy(ldata->read_buf + ldata->read_head, cp, i);
+		ldata->read_head = (ldata->read_head + i) & (N_TTY_BUF_SIZE-1);
+		ldata->read_cnt += i;
 		spin_unlock_irqrestore(&tty->read_lock, cpuflags);
 	} else {
 		for (i = count, p = cp, f = fp; i; i--, p++) {
@@ -1449,7 +1464,7 @@ static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
 
 	n_tty_set_room(tty);
 
-	if ((!ldata->icanon && (tty->read_cnt >= tty->minimum_to_wake)) ||
+	if ((!ldata->icanon && (ldata->read_cnt >= tty->minimum_to_wake)) ||
 		L_EXTPROC(tty)) {
 		kill_fasync(&tty->fasync, SIGIO, POLL_IN);
 		if (waitqueue_active(&tty->read_wait))
@@ -1500,12 +1515,12 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
 		canon_change = (old->c_lflag ^ tty->termios.c_lflag) & ICANON;
 	if (canon_change) {
 		bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
-		tty->canon_head = tty->read_tail;
-		tty->canon_data = 0;
+		ldata->canon_head = ldata->read_tail;
+		ldata->canon_data = 0;
 		ldata->erasing = 0;
 	}
 
-	if (canon_change && !L_ICANON(tty) && tty->read_cnt)
+	if (canon_change && !L_ICANON(tty) && ldata->read_cnt)
 		wake_up_interruptible(&tty->read_wait);
 
 	ldata->icanon = (L_ICANON(tty) != 0);
@@ -1586,11 +1601,9 @@ static void n_tty_close(struct tty_struct *tty)
 	struct n_tty_data *ldata = tty->disc_data;
 
 	n_tty_flush_buffer(tty);
-	kfree(tty->read_buf);
-	kfree(tty->echo_buf);
+	kfree(ldata->read_buf);
+	kfree(ldata->echo_buf);
 	kfree(ldata);
-	tty->read_buf = NULL;
-	tty->echo_buf = NULL;
 	tty->disc_data = NULL;
 }
 
@@ -1615,9 +1628,9 @@ static int n_tty_open(struct tty_struct *tty)
 	ldata->overrun_time = jiffies;
 
 	/* These are ugly. Currently a malloc failure here can panic */
-	tty->read_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
-	tty->echo_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
-	if (!tty->read_buf || !tty->echo_buf)
+	ldata->read_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
+	ldata->echo_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
+	if (!ldata->read_buf || !ldata->echo_buf)
 		goto err_free_bufs;
 
 	tty->disc_data = ldata;
@@ -1630,8 +1643,8 @@ static int n_tty_open(struct tty_struct *tty)
 
 	return 0;
 err_free_bufs:
-	kfree(tty->read_buf);
-	kfree(tty->echo_buf);
+	kfree(ldata->read_buf);
+	kfree(ldata->echo_buf);
 	kfree(ldata);
 err:
 	return -ENOMEM;
@@ -1643,9 +1656,9 @@ static inline int input_available_p(struct tty_struct *tty, int amt)
 
 	tty_flush_to_ldisc(tty);
 	if (ldata->icanon && !L_EXTPROC(tty)) {
-		if (tty->canon_data)
+		if (ldata->canon_data)
 			return 1;
-	} else if (tty->read_cnt >= (amt ? amt : 1))
+	} else if (ldata->read_cnt >= (amt ? amt : 1))
 		return 1;
 
 	return 0;
@@ -1681,21 +1694,21 @@ static int copy_from_read_buf(struct tty_struct *tty,
 
 	retval = 0;
 	spin_lock_irqsave(&tty->read_lock, flags);
-	n = min(tty->read_cnt, N_TTY_BUF_SIZE - tty->read_tail);
+	n = min(ldata->read_cnt, N_TTY_BUF_SIZE - ldata->read_tail);
 	n = min(*nr, n);
 	spin_unlock_irqrestore(&tty->read_lock, flags);
 	if (n) {
-		retval = copy_to_user(*b, &tty->read_buf[tty->read_tail], n);
+		retval = copy_to_user(*b, &ldata->read_buf[ldata->read_tail], n);
 		n -= retval;
 		is_eof = n == 1 &&
-			tty->read_buf[tty->read_tail] == EOF_CHAR(tty);
-		tty_audit_add_data(tty, &tty->read_buf[tty->read_tail], n,
+			ldata->read_buf[ldata->read_tail] == EOF_CHAR(tty);
+		tty_audit_add_data(tty, &ldata->read_buf[ldata->read_tail], n,
 				ldata->icanon);
 		spin_lock_irqsave(&tty->read_lock, flags);
-		tty->read_tail = (tty->read_tail + n) & (N_TTY_BUF_SIZE-1);
-		tty->read_cnt -= n;
+		ldata->read_tail = (ldata->read_tail + n) & (N_TTY_BUF_SIZE-1);
+		ldata->read_cnt -= n;
 		/* Turn single EOF into zero-length read */
-		if (L_EXTPROC(tty) && ldata->icanon && is_eof && !tty->read_cnt)
+		if (L_EXTPROC(tty) && ldata->icanon && is_eof && !ldata->read_cnt)
 			n = 0;
 		spin_unlock_irqrestore(&tty->read_lock, flags);
 		*b += n;
@@ -1878,22 +1891,22 @@ do_it_again:
 		if (ldata->icanon && !L_EXTPROC(tty)) {
 			/* N.B. avoid overrun if nr == 0 */
 			spin_lock_irqsave(&tty->read_lock, flags);
-			while (nr && tty->read_cnt) {
+			while (nr && ldata->read_cnt) {
 				int eol;
 
-				eol = test_and_clear_bit(tty->read_tail,
+				eol = test_and_clear_bit(ldata->read_tail,
 						ldata->read_flags);
-				c = tty->read_buf[tty->read_tail];
-				tty->read_tail = ((tty->read_tail+1) &
+				c = ldata->read_buf[ldata->read_tail];
+				ldata->read_tail = ((ldata->read_tail+1) &
 						  (N_TTY_BUF_SIZE-1));
-				tty->read_cnt--;
+				ldata->read_cnt--;
 				if (eol) {
 					/* this test should be redundant:
 					 * we shouldn't be reading data if
 					 * canon_data is 0
 					 */
-					if (--tty->canon_data < 0)
-						tty->canon_data = 0;
+					if (--ldata->canon_data < 0)
+						ldata->canon_data = 0;
 				}
 				spin_unlock_irqrestore(&tty->read_lock, flags);
 
@@ -2111,15 +2124,15 @@ static unsigned long inq_canon(struct tty_struct *tty)
 	struct n_tty_data *ldata = tty->disc_data;
 	int nr, head, tail;
 
-	if (!tty->canon_data)
+	if (!ldata->canon_data)
 		return 0;
-	head = tty->canon_head;
-	tail = tty->read_tail;
+	head = ldata->canon_head;
+	tail = ldata->read_tail;
 	nr = (head - tail) & (N_TTY_BUF_SIZE-1);
 	/* Skip EOF-chars.. */
 	while (head != tail) {
 		if (test_bit(tail, ldata->read_flags) &&
-		    tty->read_buf[tail] == __DISABLED_CHAR)
+		    ldata->read_buf[tail] == __DISABLED_CHAR)
 			nr--;
 		tail = (tail+1) & (N_TTY_BUF_SIZE-1);
 	}
@@ -2129,6 +2142,7 @@ static unsigned long inq_canon(struct tty_struct *tty)
 static int n_tty_ioctl(struct tty_struct *tty, struct file *file,
 		       unsigned int cmd, unsigned long arg)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	int retval;
 
 	switch (cmd) {
@@ -2136,7 +2150,7 @@ static int n_tty_ioctl(struct tty_struct *tty, struct file *file,
 		return put_user(tty_chars_in_buffer(tty), (int __user *) arg);
 	case TIOCINQ:
 		/* FIXME: Locking */
-		retval = tty->read_cnt;
+		retval = ldata->read_cnt;
 		if (L_ICANON(tty))
 			retval = inq_canon(tty);
 		return put_user(retval, (unsigned int __user *) arg);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 2161e6b5a94c..226cf20e0150 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -272,16 +272,6 @@ struct tty_struct {
 	 */
 	unsigned char closing:1;
 	unsigned short minimum_to_wake;
-	char *read_buf;
-	int read_head;
-	int read_tail;
-	int read_cnt;
-	unsigned char *echo_buf;
-	unsigned int echo_pos;
-	unsigned int echo_cnt;
-	int canon_data;
-	unsigned long canon_head;
-	unsigned int canon_column;
 	struct mutex atomic_read_lock;
 	struct mutex atomic_write_lock;
 	struct mutex output_lock;
-- 
cgit v1.2.3-55-g7522


From bddc7152f68bc1e0ee1f55a8055e33531f384101 Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:42 +0200
Subject: TTY: move ldisc data from tty_struct: locks

atomic_write_lock is not n_tty specific, so move it up in the
tty_struct.

And since these are the last ones to move, remove also the comment
saying there are some ldisc' members. There are none now.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/n_tty.c  | 123 ++++++++++++++++++++++++++++++---------------------
 drivers/tty/tty_io.c |   4 --
 include/linux/tty.h  |  11 +----
 3 files changed, 73 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 4794537a50ff..0a6fcda96152 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -96,6 +96,11 @@ struct n_tty_data {
 	int canon_data;
 	unsigned long canon_head;
 	unsigned int canon_column;
+
+	struct mutex atomic_read_lock;
+	struct mutex output_lock;
+	struct mutex echo_lock;
+	spinlock_t read_lock;
 };
 
 static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
@@ -171,14 +176,15 @@ static void put_tty_queue_nolock(unsigned char c, struct tty_struct *tty)
 
 static void put_tty_queue(unsigned char c, struct tty_struct *tty)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	unsigned long flags;
 	/*
 	 *	The problem of stomping on the buffers ends here.
 	 *	Why didn't anyone see this one coming? --AJK
 	*/
-	spin_lock_irqsave(&tty->read_lock, flags);
+	spin_lock_irqsave(&ldata->read_lock, flags);
 	put_tty_queue_nolock(c, tty);
-	spin_unlock_irqrestore(&tty->read_lock, flags);
+	spin_unlock_irqrestore(&ldata->read_lock, flags);
 }
 
 /**
@@ -212,13 +218,13 @@ static void reset_buffer_flags(struct tty_struct *tty)
 	struct n_tty_data *ldata = tty->disc_data;
 	unsigned long flags;
 
-	spin_lock_irqsave(&tty->read_lock, flags);
+	spin_lock_irqsave(&ldata->read_lock, flags);
 	ldata->read_head = ldata->read_tail = ldata->read_cnt = 0;
-	spin_unlock_irqrestore(&tty->read_lock, flags);
+	spin_unlock_irqrestore(&ldata->read_lock, flags);
 
-	mutex_lock(&tty->echo_lock);
+	mutex_lock(&ldata->echo_lock);
 	ldata->echo_pos = ldata->echo_cnt = ldata->echo_overrun = 0;
-	mutex_unlock(&tty->echo_lock);
+	mutex_unlock(&ldata->echo_lock);
 
 	ldata->canon_head = ldata->canon_data = ldata->erasing = 0;
 	bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
@@ -270,7 +276,7 @@ static ssize_t n_tty_chars_in_buffer(struct tty_struct *tty)
 	unsigned long flags;
 	ssize_t n = 0;
 
-	spin_lock_irqsave(&tty->read_lock, flags);
+	spin_lock_irqsave(&ldata->read_lock, flags);
 	if (!ldata->icanon) {
 		n = ldata->read_cnt;
 	} else if (ldata->canon_data) {
@@ -278,7 +284,7 @@ static ssize_t n_tty_chars_in_buffer(struct tty_struct *tty)
 			ldata->canon_head - ldata->read_tail :
 			ldata->canon_head + (N_TTY_BUF_SIZE - ldata->read_tail);
 	}
-	spin_unlock_irqrestore(&tty->read_lock, flags);
+	spin_unlock_irqrestore(&ldata->read_lock, flags);
 	return n;
 }
 
@@ -408,14 +414,15 @@ static int do_output_char(unsigned char c, struct tty_struct *tty, int space)
 
 static int process_output(unsigned char c, struct tty_struct *tty)
 {
+	struct n_tty_data *ldata = tty->disc_data;
 	int	space, retval;
 
-	mutex_lock(&tty->output_lock);
+	mutex_lock(&ldata->output_lock);
 
 	space = tty_write_room(tty);
 	retval = do_output_char(c, tty, space);
 
-	mutex_unlock(&tty->output_lock);
+	mutex_unlock(&ldata->output_lock);
 	if (retval < 0)
 		return -1;
 	else
@@ -449,11 +456,11 @@ static ssize_t process_output_block(struct tty_struct *tty,
 	int	i;
 	const unsigned char *cp;
 
-	mutex_lock(&tty->output_lock);
+	mutex_lock(&ldata->output_lock);
 
 	space = tty_write_room(tty);
 	if (!space) {
-		mutex_unlock(&tty->output_lock);
+		mutex_unlock(&ldata->output_lock);
 		return 0;
 	}
 	if (nr > space)
@@ -496,7 +503,7 @@ static ssize_t process_output_block(struct tty_struct *tty,
 break_out:
 	i = tty->ops->write(tty, buf, i);
 
-	mutex_unlock(&tty->output_lock);
+	mutex_unlock(&ldata->output_lock);
 	return i;
 }
 
@@ -536,8 +543,8 @@ static void process_echoes(struct tty_struct *tty)
 	if (!ldata->echo_cnt)
 		return;
 
-	mutex_lock(&tty->output_lock);
-	mutex_lock(&tty->echo_lock);
+	mutex_lock(&ldata->output_lock);
+	mutex_lock(&ldata->echo_lock);
 
 	space = tty_write_room(tty);
 
@@ -682,8 +689,8 @@ static void process_echoes(struct tty_struct *tty)
 			ldata->echo_overrun = 0;
 	}
 
-	mutex_unlock(&tty->echo_lock);
-	mutex_unlock(&tty->output_lock);
+	mutex_unlock(&ldata->echo_lock);
+	mutex_unlock(&ldata->output_lock);
 
 	if (tty->ops->flush_chars)
 		tty->ops->flush_chars(tty);
@@ -748,12 +755,14 @@ static void add_echo_byte(unsigned char c, struct tty_struct *tty)
 
 static void echo_move_back_col(struct tty_struct *tty)
 {
-	mutex_lock(&tty->echo_lock);
+	struct n_tty_data *ldata = tty->disc_data;
+
+	mutex_lock(&ldata->echo_lock);
 
 	add_echo_byte(ECHO_OP_START, tty);
 	add_echo_byte(ECHO_OP_MOVE_BACK_COL, tty);
 
-	mutex_unlock(&tty->echo_lock);
+	mutex_unlock(&ldata->echo_lock);
 }
 
 /**
@@ -768,12 +777,14 @@ static void echo_move_back_col(struct tty_struct *tty)
 
 static void echo_set_canon_col(struct tty_struct *tty)
 {
-	mutex_lock(&tty->echo_lock);
+	struct n_tty_data *ldata = tty->disc_data;
+
+	mutex_lock(&ldata->echo_lock);
 
 	add_echo_byte(ECHO_OP_START, tty);
 	add_echo_byte(ECHO_OP_SET_CANON_COL, tty);
 
-	mutex_unlock(&tty->echo_lock);
+	mutex_unlock(&ldata->echo_lock);
 }
 
 /**
@@ -796,7 +807,9 @@ static void echo_set_canon_col(struct tty_struct *tty)
 static void echo_erase_tab(unsigned int num_chars, int after_tab,
 			   struct tty_struct *tty)
 {
-	mutex_lock(&tty->echo_lock);
+	struct n_tty_data *ldata = tty->disc_data;
+
+	mutex_lock(&ldata->echo_lock);
 
 	add_echo_byte(ECHO_OP_START, tty);
 	add_echo_byte(ECHO_OP_ERASE_TAB, tty);
@@ -810,7 +823,7 @@ static void echo_erase_tab(unsigned int num_chars, int after_tab,
 
 	add_echo_byte(num_chars, tty);
 
-	mutex_unlock(&tty->echo_lock);
+	mutex_unlock(&ldata->echo_lock);
 }
 
 /**
@@ -828,7 +841,9 @@ static void echo_erase_tab(unsigned int num_chars, int after_tab,
 
 static void echo_char_raw(unsigned char c, struct tty_struct *tty)
 {
-	mutex_lock(&tty->echo_lock);
+	struct n_tty_data *ldata = tty->disc_data;
+
+	mutex_lock(&ldata->echo_lock);
 
 	if (c == ECHO_OP_START) {
 		add_echo_byte(ECHO_OP_START, tty);
@@ -837,7 +852,7 @@ static void echo_char_raw(unsigned char c, struct tty_struct *tty)
 		add_echo_byte(c, tty);
 	}
 
-	mutex_unlock(&tty->echo_lock);
+	mutex_unlock(&ldata->echo_lock);
 }
 
 /**
@@ -856,7 +871,9 @@ static void echo_char_raw(unsigned char c, struct tty_struct *tty)
 
 static void echo_char(unsigned char c, struct tty_struct *tty)
 {
-	mutex_lock(&tty->echo_lock);
+	struct n_tty_data *ldata = tty->disc_data;
+
+	mutex_lock(&ldata->echo_lock);
 
 	if (c == ECHO_OP_START) {
 		add_echo_byte(ECHO_OP_START, tty);
@@ -867,7 +884,7 @@ static void echo_char(unsigned char c, struct tty_struct *tty)
 		add_echo_byte(c, tty);
 	}
 
-	mutex_unlock(&tty->echo_lock);
+	mutex_unlock(&ldata->echo_lock);
 }
 
 /**
@@ -914,19 +931,19 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 		kill_type = WERASE;
 	else {
 		if (!L_ECHO(tty)) {
-			spin_lock_irqsave(&tty->read_lock, flags);
+			spin_lock_irqsave(&ldata->read_lock, flags);
 			ldata->read_cnt -= ((ldata->read_head - ldata->canon_head) &
 					  (N_TTY_BUF_SIZE - 1));
 			ldata->read_head = ldata->canon_head;
-			spin_unlock_irqrestore(&tty->read_lock, flags);
+			spin_unlock_irqrestore(&ldata->read_lock, flags);
 			return;
 		}
 		if (!L_ECHOK(tty) || !L_ECHOKE(tty) || !L_ECHOE(tty)) {
-			spin_lock_irqsave(&tty->read_lock, flags);
+			spin_lock_irqsave(&ldata->read_lock, flags);
 			ldata->read_cnt -= ((ldata->read_head - ldata->canon_head) &
 					  (N_TTY_BUF_SIZE - 1));
 			ldata->read_head = ldata->canon_head;
-			spin_unlock_irqrestore(&tty->read_lock, flags);
+			spin_unlock_irqrestore(&ldata->read_lock, flags);
 			finish_erasing(tty);
 			echo_char(KILL_CHAR(tty), tty);
 			/* Add a newline if ECHOK is on and ECHOKE is off. */
@@ -960,10 +977,10 @@ static void eraser(unsigned char c, struct tty_struct *tty)
 				break;
 		}
 		cnt = (ldata->read_head - head) & (N_TTY_BUF_SIZE-1);
-		spin_lock_irqsave(&tty->read_lock, flags);
+		spin_lock_irqsave(&ldata->read_lock, flags);
 		ldata->read_head = head;
 		ldata->read_cnt -= cnt;
-		spin_unlock_irqrestore(&tty->read_lock, flags);
+		spin_unlock_irqrestore(&ldata->read_lock, flags);
 		if (L_ECHO(tty)) {
 			if (L_ECHOPRT(tty)) {
 				if (!ldata->erasing) {
@@ -1338,12 +1355,12 @@ send_signal:
 				put_tty_queue(c, tty);
 
 handle_newline:
-			spin_lock_irqsave(&tty->read_lock, flags);
+			spin_lock_irqsave(&ldata->read_lock, flags);
 			set_bit(ldata->read_head, ldata->read_flags);
 			put_tty_queue_nolock(c, tty);
 			ldata->canon_head = ldata->read_head;
 			ldata->canon_data++;
-			spin_unlock_irqrestore(&tty->read_lock, flags);
+			spin_unlock_irqrestore(&ldata->read_lock, flags);
 			kill_fasync(&tty->fasync, SIGIO, POLL_IN);
 			if (waitqueue_active(&tty->read_wait))
 				wake_up_interruptible(&tty->read_wait);
@@ -1417,7 +1434,7 @@ static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
 	unsigned long cpuflags;
 
 	if (ldata->real_raw) {
-		spin_lock_irqsave(&tty->read_lock, cpuflags);
+		spin_lock_irqsave(&ldata->read_lock, cpuflags);
 		i = min(N_TTY_BUF_SIZE - ldata->read_cnt,
 			N_TTY_BUF_SIZE - ldata->read_head);
 		i = min(count, i);
@@ -1433,7 +1450,7 @@ static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
 		memcpy(ldata->read_buf + ldata->read_head, cp, i);
 		ldata->read_head = (ldata->read_head + i) & (N_TTY_BUF_SIZE-1);
 		ldata->read_cnt += i;
-		spin_unlock_irqrestore(&tty->read_lock, cpuflags);
+		spin_unlock_irqrestore(&ldata->read_lock, cpuflags);
 	} else {
 		for (i = count, p = cp, f = fp; i; i--, p++) {
 			if (f)
@@ -1626,6 +1643,10 @@ static int n_tty_open(struct tty_struct *tty)
 		goto err;
 
 	ldata->overrun_time = jiffies;
+	mutex_init(&ldata->atomic_read_lock);
+	mutex_init(&ldata->output_lock);
+	mutex_init(&ldata->echo_lock);
+	spin_lock_init(&ldata->read_lock);
 
 	/* These are ugly. Currently a malloc failure here can panic */
 	ldata->read_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
@@ -1677,7 +1698,7 @@ static inline int input_available_p(struct tty_struct *tty, int amt)
  *	buffer, and once to drain the space from the (physical) beginning of
  *	the buffer to head pointer.
  *
- *	Called under the tty->atomic_read_lock sem
+ *	Called under the ldata->atomic_read_lock sem
  *
  */
 
@@ -1693,10 +1714,10 @@ static int copy_from_read_buf(struct tty_struct *tty,
 	bool is_eof;
 
 	retval = 0;
-	spin_lock_irqsave(&tty->read_lock, flags);
+	spin_lock_irqsave(&ldata->read_lock, flags);
 	n = min(ldata->read_cnt, N_TTY_BUF_SIZE - ldata->read_tail);
 	n = min(*nr, n);
-	spin_unlock_irqrestore(&tty->read_lock, flags);
+	spin_unlock_irqrestore(&ldata->read_lock, flags);
 	if (n) {
 		retval = copy_to_user(*b, &ldata->read_buf[ldata->read_tail], n);
 		n -= retval;
@@ -1704,13 +1725,13 @@ static int copy_from_read_buf(struct tty_struct *tty,
 			ldata->read_buf[ldata->read_tail] == EOF_CHAR(tty);
 		tty_audit_add_data(tty, &ldata->read_buf[ldata->read_tail], n,
 				ldata->icanon);
-		spin_lock_irqsave(&tty->read_lock, flags);
+		spin_lock_irqsave(&ldata->read_lock, flags);
 		ldata->read_tail = (ldata->read_tail + n) & (N_TTY_BUF_SIZE-1);
 		ldata->read_cnt -= n;
 		/* Turn single EOF into zero-length read */
 		if (L_EXTPROC(tty) && ldata->icanon && is_eof && !ldata->read_cnt)
 			n = 0;
-		spin_unlock_irqrestore(&tty->read_lock, flags);
+		spin_unlock_irqrestore(&ldata->read_lock, flags);
 		*b += n;
 		*nr -= n;
 	}
@@ -1818,10 +1839,10 @@ do_it_again:
 	 *	Internal serialization of reads.
 	 */
 	if (file->f_flags & O_NONBLOCK) {
-		if (!mutex_trylock(&tty->atomic_read_lock))
+		if (!mutex_trylock(&ldata->atomic_read_lock))
 			return -EAGAIN;
 	} else {
-		if (mutex_lock_interruptible(&tty->atomic_read_lock))
+		if (mutex_lock_interruptible(&ldata->atomic_read_lock))
 			return -ERESTARTSYS;
 	}
 	packet = tty->packet;
@@ -1890,7 +1911,7 @@ do_it_again:
 
 		if (ldata->icanon && !L_EXTPROC(tty)) {
 			/* N.B. avoid overrun if nr == 0 */
-			spin_lock_irqsave(&tty->read_lock, flags);
+			spin_lock_irqsave(&ldata->read_lock, flags);
 			while (nr && ldata->read_cnt) {
 				int eol;
 
@@ -1908,25 +1929,25 @@ do_it_again:
 					if (--ldata->canon_data < 0)
 						ldata->canon_data = 0;
 				}
-				spin_unlock_irqrestore(&tty->read_lock, flags);
+				spin_unlock_irqrestore(&ldata->read_lock, flags);
 
 				if (!eol || (c != __DISABLED_CHAR)) {
 					if (tty_put_user(tty, c, b++)) {
 						retval = -EFAULT;
 						b--;
-						spin_lock_irqsave(&tty->read_lock, flags);
+						spin_lock_irqsave(&ldata->read_lock, flags);
 						break;
 					}
 					nr--;
 				}
 				if (eol) {
 					tty_audit_push(tty);
-					spin_lock_irqsave(&tty->read_lock, flags);
+					spin_lock_irqsave(&ldata->read_lock, flags);
 					break;
 				}
-				spin_lock_irqsave(&tty->read_lock, flags);
+				spin_lock_irqsave(&ldata->read_lock, flags);
 			}
-			spin_unlock_irqrestore(&tty->read_lock, flags);
+			spin_unlock_irqrestore(&ldata->read_lock, flags);
 			if (retval)
 				break;
 		} else {
@@ -1958,7 +1979,7 @@ do_it_again:
 		if (time)
 			timeout = time;
 	}
-	mutex_unlock(&tty->atomic_read_lock);
+	mutex_unlock(&ldata->atomic_read_lock);
 	remove_wait_queue(&tty->read_wait, &wait);
 
 	if (!waitqueue_active(&tty->read_wait))
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 67b024ca16ec..f90b6217b3ba 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2939,11 +2939,7 @@ void initialize_tty_struct(struct tty_struct *tty,
 	init_waitqueue_head(&tty->write_wait);
 	init_waitqueue_head(&tty->read_wait);
 	INIT_WORK(&tty->hangup_work, do_tty_hangup);
-	mutex_init(&tty->atomic_read_lock);
 	mutex_init(&tty->atomic_write_lock);
-	mutex_init(&tty->output_lock);
-	mutex_init(&tty->echo_lock);
-	spin_lock_init(&tty->read_lock);
 	spin_lock_init(&tty->ctrl_lock);
 	INIT_LIST_HEAD(&tty->tty_files);
 	INIT_WORK(&tty->SAK_work, do_SAK_work);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 226cf20e0150..08787ece3fdc 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -235,6 +235,7 @@ struct tty_struct {
 	struct mutex ldisc_mutex;
 	struct tty_ldisc *ldisc;
 
+	struct mutex atomic_write_lock;
 	struct mutex legacy_mutex;
 	struct mutex termios_mutex;
 	spinlock_t ctrl_lock;
@@ -265,20 +266,10 @@ struct tty_struct {
 
 #define N_TTY_BUF_SIZE 4096
 
-	/*
-	 * The following is data for the N_TTY line discipline.  For
-	 * historical reasons, this is included in the tty structure.
-	 * Mostly locked by the BKL.
-	 */
 	unsigned char closing:1;
 	unsigned short minimum_to_wake;
-	struct mutex atomic_read_lock;
-	struct mutex atomic_write_lock;
-	struct mutex output_lock;
-	struct mutex echo_lock;
 	unsigned char *write_buf;
 	int write_cnt;
-	spinlock_t read_lock;
 	/* If the tty has a pending do_SAK, queue it here - akpm */
 	struct work_struct SAK_work;
 	struct tty_port *port;
-- 
cgit v1.2.3-55-g7522


From 2fc20661e3171d45e8e58a61eb5c6b7d8d614fde Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:44 +0200
Subject: TTY: move TTY_FLUSH* flags to tty_port

They are only TTY buffers specific. And the buffers will go to
tty_port in the next patches. So to remove the need to have both
tty_port and tty_struct at some places, let us move the flags to
tty_port.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_buffer.c | 18 ++++++++++--------
 include/linux/tty.h      |  5 +++--
 2 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 8b00f6a34a7d..6f366f257fba 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -134,17 +134,18 @@ static void __tty_buffer_flush(struct tty_struct *tty)
 
 void tty_buffer_flush(struct tty_struct *tty)
 {
+	struct tty_port *port = tty->port;
 	unsigned long flags;
 	spin_lock_irqsave(&tty->buf.lock, flags);
 
 	/* If the data is being pushed to the tty layer then we can't
 	   process it here. Instead set a flag and the flush_to_ldisc
 	   path will process the flush request before it exits */
-	if (test_bit(TTY_FLUSHING, &tty->flags)) {
-		set_bit(TTY_FLUSHPENDING, &tty->flags);
+	if (test_bit(TTYP_FLUSHING, &port->iflags)) {
+		set_bit(TTYP_FLUSHPENDING, &port->iflags);
 		spin_unlock_irqrestore(&tty->buf.lock, flags);
 		wait_event(tty->read_wait,
-				test_bit(TTY_FLUSHPENDING, &tty->flags) == 0);
+				test_bit(TTYP_FLUSHPENDING, &port->iflags) == 0);
 		return;
 	} else
 		__tty_buffer_flush(tty);
@@ -450,6 +451,7 @@ static void flush_to_ldisc(struct work_struct *work)
 {
 	struct tty_struct *tty =
 		container_of(work, struct tty_struct, buf.work);
+	struct tty_port *port = tty->port;
 	unsigned long 	flags;
 	struct tty_ldisc *disc;
 
@@ -459,7 +461,7 @@ static void flush_to_ldisc(struct work_struct *work)
 
 	spin_lock_irqsave(&tty->buf.lock, flags);
 
-	if (!test_and_set_bit(TTY_FLUSHING, &tty->flags)) {
+	if (!test_and_set_bit(TTYP_FLUSHING, &port->iflags)) {
 		struct tty_buffer *head;
 		while ((head = tty->buf.head) != NULL) {
 			int count;
@@ -477,7 +479,7 @@ static void flush_to_ldisc(struct work_struct *work)
 			/* Ldisc or user is trying to flush the buffers
 			   we are feeding to the ldisc, stop feeding the
 			   line discipline as we want to empty the queue */
-			if (test_bit(TTY_FLUSHPENDING, &tty->flags))
+			if (test_bit(TTYP_FLUSHPENDING, &port->iflags))
 				break;
 			if (!tty->receive_room)
 				break;
@@ -491,14 +493,14 @@ static void flush_to_ldisc(struct work_struct *work)
 							flag_buf, count);
 			spin_lock_irqsave(&tty->buf.lock, flags);
 		}
-		clear_bit(TTY_FLUSHING, &tty->flags);
+		clear_bit(TTYP_FLUSHING, &port->iflags);
 	}
 
 	/* We may have a deferred request to flush the input buffer,
 	   if so pull the chain under the lock and empty the queue */
-	if (test_bit(TTY_FLUSHPENDING, &tty->flags)) {
+	if (test_bit(TTYP_FLUSHPENDING, &port->iflags)) {
 		__tty_buffer_flush(tty);
-		clear_bit(TTY_FLUSHPENDING, &tty->flags);
+		clear_bit(TTYP_FLUSHPENDING, &port->iflags);
 		wake_up(&tty->read_wait);
 	}
 	spin_unlock_irqrestore(&tty->buf.lock, flags);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 08787ece3fdc..b4b3c568d242 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -197,6 +197,9 @@ struct tty_port {
 	wait_queue_head_t	close_wait;	/* Close waiters */
 	wait_queue_head_t	delta_msr_wait;	/* Modem status change */
 	unsigned long		flags;		/* TTY flags ASY_*/
+	unsigned long		iflags;		/* TTYP_ internal flags */
+#define TTYP_FLUSHING			1  /* Flushing to ldisc in progress */
+#define TTYP_FLUSHPENDING		2  /* Queued buffer flush pending */
 	unsigned char		console:1;	/* port is a console */
 	struct mutex		mutex;		/* Locking */
 	struct mutex		buf_mutex;	/* Buffer alloc lock */
@@ -309,8 +312,6 @@ struct tty_file_private {
 #define TTY_PTY_LOCK 		16	/* pty private */
 #define TTY_NO_WRITE_SPLIT 	17	/* Preserve write boundaries to driver */
 #define TTY_HUPPED 		18	/* Post driver->hangup() */
-#define TTY_FLUSHING		19	/* Flushing to ldisc in progress */
-#define TTY_FLUSHPENDING	20	/* Queued buffer flush pending */
 #define TTY_HUPPING 		21	/* ->hangup() in progress */
 
 #define TTY_WRITE_FLUSH(tty) tty_write_flush((tty))
-- 
cgit v1.2.3-55-g7522


From 967fab6916681e5ab131fdef1226327b02454f19 Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:46 +0200
Subject: TTY: add port -> tty link

For that purpose we have to temporarily introduce a second tty back
pointer into tty_port. It is because serial layer, and maybe others,
still do not use tty_port_tty_set/get. So that we cannot set the
tty_port->tty to NULL at will now.

Yes, the fix would be to convert whole serial layer and all its users
to tty_port_tty_set/get. However we are in the process of removing the
need of tty in most of the call sites, so this would lead to a
duplicated work.

Instead we have now tty_port->itty (internal tty) which will be used
only in flush_to_ldisc. For that one it is ensured that itty is valid
wherever the work is run. IOW, the work is synchronously cancelled
before we set itty to NULL and also before hangup is processed.

After we need only tty_port and not tty_struct in most code, this
shall be changed to tty_port_tty_set/get and itty removed completely.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/pty.c    | 2 ++
 drivers/tty/tty_io.c | 3 +++
 include/linux/tty.h  | 1 +
 3 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 2728afe52eea..c32690862671 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -345,6 +345,7 @@ static int pty_common_install(struct tty_driver *driver, struct tty_struct *tty,
 	tty_port_init(ports[1]);
 	o_tty->port = ports[0];
 	tty->port = ports[1];
+	o_tty->port->itty = o_tty;
 
 	tty_driver_kref_get(driver);
 	tty->count++;
@@ -371,6 +372,7 @@ static void pty_unix98_shutdown(struct tty_struct *tty)
 
 static void pty_cleanup(struct tty_struct *tty)
 {
+	tty->port->itty = NULL;
 	kfree(tty->port);
 }
 
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index f90b6217b3ba..202008f38ca3 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1417,6 +1417,8 @@ struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx)
 			"%s: %s driver does not set tty->port. This will crash the kernel later. Fix the driver!\n",
 			__func__, tty->driver->name);
 
+	tty->port->itty = tty;
+
 	/*
 	 * Structures all installed ... call the ldisc open routines.
 	 * If we fail here just call release_tty to clean up.  No need
@@ -1552,6 +1554,7 @@ static void release_tty(struct tty_struct *tty, int idx)
 		tty->ops->shutdown(tty);
 	tty_free_termios(tty);
 	tty_driver_remove_tty(tty->driver, tty);
+	tty->port->itty = NULL;
 
 	if (tty->link)
 		tty_kref_put(tty->link);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index b4b3c568d242..9be74d649a51 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -189,6 +189,7 @@ struct tty_port_operations {
 	
 struct tty_port {
 	struct tty_struct	*tty;		/* Back pointer */
+	struct tty_struct	*itty;		/* internal back ptr */
 	const struct tty_port_operations *ops;	/* Port operations */
 	spinlock_t		lock;		/* Lock protecting tty field */
 	int			blocked_open;	/* Waiting to open */
-- 
cgit v1.2.3-55-g7522


From ecbbfd44a08fa80e0d664814efd4c187721b85f6 Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 18 Oct 2012 22:26:47 +0200
Subject: TTY: move tty buffers to tty_port

So this is it. The big step why we did all the work over the past
kernel releases. Now everything is prepared, so nothing protects us
from doing that big step.

           |  |            \  \ nnnn/^l      |  |
           |  |             \  /     /       |  |
           |  '-,.__   =>    \/   ,-`    =>  |  '-,.__
           | O __.´´)        (  .`           | O __.´´)
            ~~~   ~~          ``              ~~~   ~~
The buffers are now in the tty_port structure and we can start
teaching the buffer helpers (insert char/string, flip etc.) to use
tty_port instead of tty_struct all around.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/n_tty.c      |   7 +++-
 drivers/tty/pty.c        |   2 +-
 drivers/tty/tty_buffer.c | 102 ++++++++++++++++++++++++-----------------------
 drivers/tty/tty_io.c     |   2 -
 drivers/tty/tty_ldisc.c  |  10 ++---
 drivers/tty/tty_port.c   |   2 +
 include/linux/tty.h      |   6 +--
 include/linux/tty_flip.h |   2 +-
 8 files changed, 70 insertions(+), 63 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 531e539dbfcf..60b076cc4e20 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -149,8 +149,11 @@ static void n_tty_set_room(struct tty_struct *tty)
 	tty->receive_room = left;
 
 	/* Did this open up the receive buffer? We may need to flip */
-	if (left && !old_left)
-		schedule_work(&tty->buf.work);
+	if (left && !old_left) {
+		WARN_RATELIMIT(tty->port->itty == NULL,
+				"scheduling with invalid itty");
+		schedule_work(&tty->port->buf.work);
+	}
 }
 
 static void put_tty_queue_nolock(unsigned char c, struct n_tty_data *ldata)
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index c32690862671..4219f040adb8 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -93,7 +93,7 @@ static void pty_unthrottle(struct tty_struct *tty)
 
 static int pty_space(struct tty_struct *to)
 {
-	int n = 8192 - to->buf.memory_used;
+	int n = 8192 - to->port->buf.memory_used;
 	if (n < 0)
 		return 0;
 	return n;
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index ddd74d41cbb2..06725f5cc819 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -27,9 +27,9 @@
  *	Locking: none
  */
 
-void tty_buffer_free_all(struct tty_struct *tty)
+void tty_buffer_free_all(struct tty_port *port)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &port->buf;
 	struct tty_buffer *thead;
 
 	while ((thead = buf->head) != NULL) {
@@ -56,11 +56,11 @@ void tty_buffer_free_all(struct tty_struct *tty)
  *	Locking: Caller must hold tty->buf.lock
  */
 
-static struct tty_buffer *tty_buffer_alloc(struct tty_struct *tty, size_t size)
+static struct tty_buffer *tty_buffer_alloc(struct tty_port *port, size_t size)
 {
 	struct tty_buffer *p;
 
-	if (tty->buf.memory_used + size > 65536)
+	if (port->buf.memory_used + size > 65536)
 		return NULL;
 	p = kmalloc(sizeof(struct tty_buffer) + 2 * size, GFP_ATOMIC);
 	if (p == NULL)
@@ -72,7 +72,7 @@ static struct tty_buffer *tty_buffer_alloc(struct tty_struct *tty, size_t size)
 	p->read = 0;
 	p->char_buf_ptr = (char *)(p->data);
 	p->flag_buf_ptr = (unsigned char *)p->char_buf_ptr + size;
-	tty->buf.memory_used += size;
+	port->buf.memory_used += size;
 	return p;
 }
 
@@ -87,9 +87,9 @@ static struct tty_buffer *tty_buffer_alloc(struct tty_struct *tty, size_t size)
  *	Locking: Caller must hold tty->buf.lock
  */
 
-static void tty_buffer_free(struct tty_struct *tty, struct tty_buffer *b)
+static void tty_buffer_free(struct tty_port *port, struct tty_buffer *b)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &port->buf;
 
 	/* Dumb strategy for now - should keep some stats */
 	buf->memory_used -= b->size;
@@ -114,14 +114,14 @@ static void tty_buffer_free(struct tty_struct *tty, struct tty_buffer *b)
  *	Locking: Caller must hold tty->buf.lock
  */
 
-static void __tty_buffer_flush(struct tty_struct *tty)
+static void __tty_buffer_flush(struct tty_port *port)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &port->buf;
 	struct tty_buffer *thead;
 
 	while ((thead = buf->head) != NULL) {
 		buf->head = thead->next;
-		tty_buffer_free(tty, thead);
+		tty_buffer_free(port, thead);
 	}
 	buf->tail = NULL;
 }
@@ -140,7 +140,7 @@ static void __tty_buffer_flush(struct tty_struct *tty)
 void tty_buffer_flush(struct tty_struct *tty)
 {
 	struct tty_port *port = tty->port;
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &port->buf;
 	unsigned long flags;
 
 	spin_lock_irqsave(&buf->lock, flags);
@@ -155,7 +155,7 @@ void tty_buffer_flush(struct tty_struct *tty)
 				test_bit(TTYP_FLUSHPENDING, &port->iflags) == 0);
 		return;
 	} else
-		__tty_buffer_flush(tty);
+		__tty_buffer_flush(port);
 	spin_unlock_irqrestore(&buf->lock, flags);
 }
 
@@ -171,9 +171,9 @@ void tty_buffer_flush(struct tty_struct *tty)
  *	Locking: Caller must hold tty->buf.lock
  */
 
-static struct tty_buffer *tty_buffer_find(struct tty_struct *tty, size_t size)
+static struct tty_buffer *tty_buffer_find(struct tty_port *port, size_t size)
 {
-	struct tty_buffer **tbh = &tty->buf.free;
+	struct tty_buffer **tbh = &port->buf.free;
 	while ((*tbh) != NULL) {
 		struct tty_buffer *t = *tbh;
 		if (t->size >= size) {
@@ -182,14 +182,14 @@ static struct tty_buffer *tty_buffer_find(struct tty_struct *tty, size_t size)
 			t->used = 0;
 			t->commit = 0;
 			t->read = 0;
-			tty->buf.memory_used += t->size;
+			port->buf.memory_used += t->size;
 			return t;
 		}
 		tbh = &((*tbh)->next);
 	}
 	/* Round the buffer size out */
 	size = (size + 0xFF) & ~0xFF;
-	return tty_buffer_alloc(tty, size);
+	return tty_buffer_alloc(port, size);
 	/* Should possibly check if this fails for the largest buffer we
 	   have queued and recycle that ? */
 }
@@ -200,11 +200,11 @@ static struct tty_buffer *tty_buffer_find(struct tty_struct *tty, size_t size)
  *
  *	Make at least size bytes of linear space available for the tty
  *	buffer. If we fail return the size we managed to find.
- *      Locking: Caller must hold tty->buf.lock
+ *      Locking: Caller must hold port->buf.lock
  */
-static int __tty_buffer_request_room(struct tty_struct *tty, size_t size)
+static int __tty_buffer_request_room(struct tty_port *port, size_t size)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &port->buf;
 	struct tty_buffer *b, *n;
 	int left;
 	/* OPTIMISATION: We could keep a per tty "zero" sized buffer to
@@ -218,7 +218,7 @@ static int __tty_buffer_request_room(struct tty_struct *tty, size_t size)
 
 	if (left < size) {
 		/* This is the slow path - looking for new buffers to use */
-		if ((n = tty_buffer_find(tty, size)) != NULL) {
+		if ((n = tty_buffer_find(port, size)) != NULL) {
 			if (b != NULL) {
 				b->next = n;
 				b->commit = b->used;
@@ -241,16 +241,17 @@ static int __tty_buffer_request_room(struct tty_struct *tty, size_t size)
  *	Make at least size bytes of linear space available for the tty
  *	buffer. If we fail return the size we managed to find.
  *
- *	Locking: Takes tty->buf.lock
+ *	Locking: Takes port->buf.lock
  */
 int tty_buffer_request_room(struct tty_struct *tty, size_t size)
 {
+	struct tty_port *port = tty->port;
 	unsigned long flags;
 	int length;
 
-	spin_lock_irqsave(&tty->buf.lock, flags);
-	length = __tty_buffer_request_room(tty, size);
-	spin_unlock_irqrestore(&tty->buf.lock, flags);
+	spin_lock_irqsave(&port->buf.lock, flags);
+	length = __tty_buffer_request_room(port, size);
+	spin_unlock_irqrestore(&port->buf.lock, flags);
 	return length;
 }
 EXPORT_SYMBOL_GPL(tty_buffer_request_room);
@@ -265,13 +266,13 @@ EXPORT_SYMBOL_GPL(tty_buffer_request_room);
  *	Queue a series of bytes to the tty buffering. All the characters
  *	passed are marked with the supplied flag. Returns the number added.
  *
- *	Locking: Called functions may take tty->buf.lock
+ *	Locking: Called functions may take port->buf.lock
  */
 
 int tty_insert_flip_string_fixed_flag(struct tty_struct *tty,
 		const unsigned char *chars, char flag, size_t size)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &tty->port->buf;
 	int copied = 0;
 	do {
 		int goal = min_t(size_t, size - copied, TTY_BUFFER_PAGE);
@@ -280,7 +281,7 @@ int tty_insert_flip_string_fixed_flag(struct tty_struct *tty,
 		struct tty_buffer *tb;
 
 		spin_lock_irqsave(&buf->lock, flags);
-		space = __tty_buffer_request_room(tty, goal);
+		space = __tty_buffer_request_room(tty->port, goal);
 		tb = buf->tail;
 		/* If there is no space then tb may be NULL */
 		if (unlikely(space == 0)) {
@@ -311,13 +312,13 @@ EXPORT_SYMBOL(tty_insert_flip_string_fixed_flag);
  *	the flags array indicates the status of the character. Returns the
  *	number added.
  *
- *	Locking: Called functions may take tty->buf.lock
+ *	Locking: Called functions may take port->buf.lock
  */
 
 int tty_insert_flip_string_flags(struct tty_struct *tty,
 		const unsigned char *chars, const char *flags, size_t size)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &tty->port->buf;
 	int copied = 0;
 	do {
 		int goal = min_t(size_t, size - copied, TTY_BUFFER_PAGE);
@@ -326,7 +327,7 @@ int tty_insert_flip_string_flags(struct tty_struct *tty,
 		struct tty_buffer *tb;
 
 		spin_lock_irqsave(&buf->lock, __flags);
-		space = __tty_buffer_request_room(tty, goal);
+		space = __tty_buffer_request_room(tty->port, goal);
 		tb = buf->tail;
 		/* If there is no space then tb may be NULL */
 		if (unlikely(space == 0)) {
@@ -357,12 +358,12 @@ EXPORT_SYMBOL(tty_insert_flip_string_flags);
  *	Note that this function can only be used when the low_latency flag
  *	is unset. Otherwise the workqueue won't be flushed.
  *
- *	Locking: Takes tty->buf.lock
+ *	Locking: Takes port->buf.lock
  */
 
 void tty_schedule_flip(struct tty_struct *tty)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &tty->port->buf;
 	unsigned long flags;
 
 	spin_lock_irqsave(&buf->lock, flags);
@@ -385,19 +386,19 @@ EXPORT_SYMBOL(tty_schedule_flip);
  *	that need their own block copy routines into the buffer. There is no
  *	guarantee the buffer is a DMA target!
  *
- *	Locking: May call functions taking tty->buf.lock
+ *	Locking: May call functions taking port->buf.lock
  */
 
 int tty_prepare_flip_string(struct tty_struct *tty, unsigned char **chars,
-								size_t size)
+		size_t size)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &tty->port->buf;
 	int space;
 	unsigned long flags;
 	struct tty_buffer *tb;
 
 	spin_lock_irqsave(&buf->lock, flags);
-	space = __tty_buffer_request_room(tty, size);
+	space = __tty_buffer_request_room(tty->port, size);
 
 	tb = buf->tail;
 	if (likely(space)) {
@@ -423,19 +424,19 @@ EXPORT_SYMBOL_GPL(tty_prepare_flip_string);
  *	that need their own block copy routines into the buffer. There is no
  *	guarantee the buffer is a DMA target!
  *
- *	Locking: May call functions taking tty->buf.lock
+ *	Locking: May call functions taking port->buf.lock
  */
 
 int tty_prepare_flip_string_flags(struct tty_struct *tty,
 			unsigned char **chars, char **flags, size_t size)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &tty->port->buf;
 	int space;
 	unsigned long __flags;
 	struct tty_buffer *tb;
 
 	spin_lock_irqsave(&buf->lock, __flags);
-	space = __tty_buffer_request_room(tty, size);
+	space = __tty_buffer_request_room(tty->port, size);
 
 	tb = buf->tail;
 	if (likely(space)) {
@@ -464,13 +465,16 @@ EXPORT_SYMBOL_GPL(tty_prepare_flip_string_flags);
 
 static void flush_to_ldisc(struct work_struct *work)
 {
-	struct tty_struct *tty =
-		container_of(work, struct tty_struct, buf.work);
-	struct tty_port *port = tty->port;
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_port *port = container_of(work, struct tty_port, buf.work);
+	struct tty_bufhead *buf = &port->buf;
+	struct tty_struct *tty;
 	unsigned long 	flags;
 	struct tty_ldisc *disc;
 
+	tty = port->itty;
+	if (WARN_RATELIMIT(tty == NULL, "tty is NULL"))
+		return;
+
 	disc = tty_ldisc_ref(tty);
 	if (disc == NULL)	/*  !TTY_LDISC */
 		return;
@@ -489,7 +493,7 @@ static void flush_to_ldisc(struct work_struct *work)
 				if (head->next == NULL)
 					break;
 				buf->head = head->next;
-				tty_buffer_free(tty, head);
+				tty_buffer_free(port, head);
 				continue;
 			}
 			/* Ldisc or user is trying to flush the buffers
@@ -515,7 +519,7 @@ static void flush_to_ldisc(struct work_struct *work)
 	/* We may have a deferred request to flush the input buffer,
 	   if so pull the chain under the lock and empty the queue */
 	if (test_bit(TTYP_FLUSHPENDING, &port->iflags)) {
-		__tty_buffer_flush(tty);
+		__tty_buffer_flush(port);
 		clear_bit(TTYP_FLUSHPENDING, &port->iflags);
 		wake_up(&tty->read_wait);
 	}
@@ -535,7 +539,7 @@ static void flush_to_ldisc(struct work_struct *work)
 void tty_flush_to_ldisc(struct tty_struct *tty)
 {
 	if (!tty->low_latency)
-		flush_work(&tty->buf.work);
+		flush_work(&tty->port->buf.work);
 }
 
 /**
@@ -553,7 +557,7 @@ void tty_flush_to_ldisc(struct tty_struct *tty)
 
 void tty_flip_buffer_push(struct tty_struct *tty)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &tty->port->buf;
 	unsigned long flags;
 
 	spin_lock_irqsave(&buf->lock, flags);
@@ -578,9 +582,9 @@ EXPORT_SYMBOL(tty_flip_buffer_push);
  *	Locking: none
  */
 
-void tty_buffer_init(struct tty_struct *tty)
+void tty_buffer_init(struct tty_port *port)
 {
-	struct tty_bufhead *buf = &tty->buf;
+	struct tty_bufhead *buf = &port->buf;
 
 	spin_lock_init(&buf->lock);
 	buf->head = NULL;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 202008f38ca3..a3eba7f359ed 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -186,7 +186,6 @@ void free_tty_struct(struct tty_struct *tty)
 	if (tty->dev)
 		put_device(tty->dev);
 	kfree(tty->write_buf);
-	tty_buffer_free_all(tty);
 	tty->magic = 0xDEADDEAD;
 	kfree(tty);
 }
@@ -2935,7 +2934,6 @@ void initialize_tty_struct(struct tty_struct *tty,
 	tty_ldisc_init(tty);
 	tty->session = NULL;
 	tty->pgrp = NULL;
-	tty_buffer_init(tty);
 	mutex_init(&tty->legacy_mutex);
 	mutex_init(&tty->termios_mutex);
 	mutex_init(&tty->ldisc_mutex);
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 47e3968df10b..f4e6754525dc 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -512,7 +512,7 @@ static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old)
 static int tty_ldisc_halt(struct tty_struct *tty)
 {
 	clear_bit(TTY_LDISC, &tty->flags);
-	return cancel_work_sync(&tty->buf.work);
+	return cancel_work_sync(&tty->port->buf.work);
 }
 
 /**
@@ -525,7 +525,7 @@ static void tty_ldisc_flush_works(struct tty_struct *tty)
 {
 	flush_work(&tty->hangup_work);
 	flush_work(&tty->SAK_work);
-	flush_work(&tty->buf.work);
+	flush_work(&tty->port->buf.work);
 }
 
 /**
@@ -704,9 +704,9 @@ enable:
 	/* Restart the work queue in case no characters kick it off. Safe if
 	   already running */
 	if (work)
-		schedule_work(&tty->buf.work);
+		schedule_work(&tty->port->buf.work);
 	if (o_work)
-		schedule_work(&o_tty->buf.work);
+		schedule_work(&o_tty->port->buf.work);
 	mutex_unlock(&tty->ldisc_mutex);
 	tty_unlock(tty);
 	return retval;
@@ -817,7 +817,7 @@ void tty_ldisc_hangup(struct tty_struct *tty)
 	 */
 	clear_bit(TTY_LDISC, &tty->flags);
 	tty_unlock(tty);
-	cancel_work_sync(&tty->buf.work);
+	cancel_work_sync(&tty->port->buf.work);
 	mutex_unlock(&tty->ldisc_mutex);
 retry:
 	tty_lock(tty);
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index d7bdd8d0c23f..416b42f7c346 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -21,6 +21,7 @@
 void tty_port_init(struct tty_port *port)
 {
 	memset(port, 0, sizeof(*port));
+	tty_buffer_init(port);
 	init_waitqueue_head(&port->open_wait);
 	init_waitqueue_head(&port->close_wait);
 	init_waitqueue_head(&port->delta_msr_wait);
@@ -126,6 +127,7 @@ static void tty_port_destructor(struct kref *kref)
 	struct tty_port *port = container_of(kref, struct tty_port, kref);
 	if (port->xmit_buf)
 		free_page((unsigned long)port->xmit_buf);
+	tty_buffer_free_all(port);
 	if (port->ops->destruct)
 		port->ops->destruct(port);
 	else
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 9be74d649a51..d7ff88fb8967 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -188,6 +188,7 @@ struct tty_port_operations {
 };
 	
 struct tty_port {
+	struct tty_bufhead	buf;		/* Locked internally */
 	struct tty_struct	*tty;		/* Back pointer */
 	struct tty_struct	*itty;		/* internal back ptr */
 	const struct tty_port_operations *ops;	/* Port operations */
@@ -259,7 +260,6 @@ struct tty_struct {
 
 	struct tty_struct *link;
 	struct fasync_struct *fasync;
-	struct tty_bufhead buf;		/* Locked internally */
 	int alt_speed;		/* For magic substitution of 38400 bps */
 	wait_queue_head_t write_wait;
 	wait_queue_head_t read_wait;
@@ -388,9 +388,9 @@ extern void disassociate_ctty(int priv);
 extern void no_tty(void);
 extern void tty_flip_buffer_push(struct tty_struct *tty);
 extern void tty_flush_to_ldisc(struct tty_struct *tty);
-extern void tty_buffer_free_all(struct tty_struct *tty);
+extern void tty_buffer_free_all(struct tty_port *port);
 extern void tty_buffer_flush(struct tty_struct *tty);
-extern void tty_buffer_init(struct tty_struct *tty);
+extern void tty_buffer_init(struct tty_port *port);
 extern speed_t tty_get_baud_rate(struct tty_struct *tty);
 extern speed_t tty_termios_baud_rate(struct ktermios *termios);
 extern speed_t tty_termios_input_baud_rate(struct ktermios *termios);
diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h
index 9239d033a0a3..2002344ed36a 100644
--- a/include/linux/tty_flip.h
+++ b/include/linux/tty_flip.h
@@ -11,7 +11,7 @@ void tty_schedule_flip(struct tty_struct *tty);
 static inline int tty_insert_flip_char(struct tty_struct *tty,
 					unsigned char ch, char flag)
 {
-	struct tty_buffer *tb = tty->buf.tail;
+	struct tty_buffer *tb = tty->port->buf.tail;
 	if (tb && tb->used < tb->size) {
 		tb->flag_buf_ptr[tb->used] = flag;
 		tb->char_buf_ptr[tb->used++] = ch;
-- 
cgit v1.2.3-55-g7522


From 54d83efa44aac87983f973abb42c508a25a2b554 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer
Date: Mon, 22 Oct 2012 21:22:45 +0200
Subject: ipvs: fix build errors related to config option combinations

Fix two build error introduced by commit 63dca2c0:
 "ipvs: Fix faulty IPv6 extension header handling in IPVS"

First build error was fairly trivial and can occur, when
CONFIG_IP_VS_IPV6 is disabled.

The second build error was tricky, and can occur when deselecting
both all Netfilter and IPVS, but selecting CONFIG_IPV6.  This is
caused by "kernel/sysctl_binary.c" including "net/ip_vs.h", which
includes "linux/netfilter_ipv6/ip6_tables.h" causing include
of "include/linux/netfilter/x_tables.h" which then cannot find
the typedef nf_hookfn.

Fix this by only including "linux/netfilter_ipv6/ip6_tables.h" in
case of CONFIG_IP_VS_IPV6 as its already used to guard the usage
of ipv6_find_hdr().

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Reported-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a681ad65b735..68c69d54d392 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -22,7 +22,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>			/* for struct ipv6hdr */
 #include <net/ipv6.h>
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP_VS_IPV6)
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #endif
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
@@ -212,8 +212,9 @@ ip_vs_fill_iph_addr_only(int af, const struct sk_buff *skb,
 			(struct ipv6hdr *)skb_network_header(skb);
 		iphdr->saddr.in6 = iph->saddr;
 		iphdr->daddr.in6 = iph->daddr;
-	} else {
+	} else
 #endif
+	{
 		const struct iphdr *iph =
 			(struct iphdr *)skb_network_header(skb);
 		iphdr->saddr.ip = iph->saddr;
-- 
cgit v1.2.3-55-g7522


From 51ebd3181572af8d5076808dab2682d800f6da5d Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Mon, 22 Oct 2012 03:42:09 +0000
Subject: ipv6: add support of equal cost multipath (ECMP)

Each nexthop is added like a single route in the routing table. All routes
that have the same metric/weight and destination but not the same gateway
are considering as ECMP routes. They are linked together, through a list called
rt6i_siblings.

ECMP routes can be added in one shot, with RTA_MULTIPATH attribute or one after
the other (in both case, the flag NLM_F_EXCL should not be set).

The patch is based on a previous work from
Luc Saillard <luc.saillard@6wind.com>.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  10 ++++
 net/ipv6/ip6_fib.c    |  57 +++++++++++++++++++++
 net/ipv6/route.c      | 136 ++++++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 200 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 8a2a203eb15d..20210d79e36a 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -47,6 +47,8 @@ struct fib6_config {
 	unsigned long	fc_expires;
 	struct nlattr	*fc_mx;
 	int		fc_mx_len;
+	int		fc_mp_len;
+	struct nlattr	*fc_mp;
 
 	struct nl_info	fc_nlinfo;
 };
@@ -99,6 +101,14 @@ struct rt6_info {
 
 	struct in6_addr			rt6i_gateway;
 
+	/* Multipath routes:
+	 * siblings is a list of rt6_info that have the the same metric/weight,
+	 * destination, but not the same gateway. nsiblings is just a cache
+	 * to speed up lookup.
+	 */
+	struct list_head		rt6i_siblings;
+	unsigned int			rt6i_nsiblings;
+
 	atomic_t			rt6i_ref;
 
 	/* These are in a separate cache line. */
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 24995a93ef8c..710cafd2e1a9 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -672,6 +672,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			    iter->rt6i_idev == rt->rt6i_idev &&
 			    ipv6_addr_equal(&iter->rt6i_gateway,
 					    &rt->rt6i_gateway)) {
+				if (rt->rt6i_nsiblings)
+					rt->rt6i_nsiblings = 0;
 				if (!(iter->rt6i_flags & RTF_EXPIRES))
 					return -EEXIST;
 				if (!(rt->rt6i_flags & RTF_EXPIRES))
@@ -680,6 +682,21 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 					rt6_set_expires(iter, rt->dst.expires);
 				return -EEXIST;
 			}
+			/* If we have the same destination and the same metric,
+			 * but not the same gateway, then the route we try to
+			 * add is sibling to this route, increment our counter
+			 * of siblings, and later we will add our route to the
+			 * list.
+			 * Only static routes (which don't have flag
+			 * RTF_EXPIRES) are used for ECMPv6.
+			 *
+			 * To avoid long list, we only had siblings if the
+			 * route have a gateway.
+			 */
+			if (rt->rt6i_flags & RTF_GATEWAY &&
+			    !(rt->rt6i_flags & RTF_EXPIRES) &&
+			    !(iter->rt6i_flags & RTF_EXPIRES))
+				rt->rt6i_nsiblings++;
 		}
 
 		if (iter->rt6i_metric > rt->rt6i_metric)
@@ -692,6 +709,35 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 	if (ins == &fn->leaf)
 		fn->rr_ptr = NULL;
 
+	/* Link this route to others same route. */
+	if (rt->rt6i_nsiblings) {
+		unsigned int rt6i_nsiblings;
+		struct rt6_info *sibling, *temp_sibling;
+
+		/* Find the first route that have the same metric */
+		sibling = fn->leaf;
+		while (sibling) {
+			if (sibling->rt6i_metric == rt->rt6i_metric) {
+				list_add_tail(&rt->rt6i_siblings,
+					      &sibling->rt6i_siblings);
+				break;
+			}
+			sibling = sibling->dst.rt6_next;
+		}
+		/* For each sibling in the list, increment the counter of
+		 * siblings. BUG() if counters does not match, list of siblings
+		 * is broken!
+		 */
+		rt6i_nsiblings = 0;
+		list_for_each_entry_safe(sibling, temp_sibling,
+					 &rt->rt6i_siblings, rt6i_siblings) {
+			sibling->rt6i_nsiblings++;
+			BUG_ON(sibling->rt6i_nsiblings != rt->rt6i_nsiblings);
+			rt6i_nsiblings++;
+		}
+		BUG_ON(rt6i_nsiblings != rt->rt6i_nsiblings);
+	}
+
 	/*
 	 *	insert node
 	 */
@@ -1193,6 +1239,17 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 	if (fn->rr_ptr == rt)
 		fn->rr_ptr = NULL;
 
+	/* Remove this entry from other siblings */
+	if (rt->rt6i_nsiblings) {
+		struct rt6_info *sibling, *next_sibling;
+
+		list_for_each_entry_safe(sibling, next_sibling,
+					 &rt->rt6i_siblings, rt6i_siblings)
+			sibling->rt6i_nsiblings--;
+		rt->rt6i_nsiblings = 0;
+		list_del_init(&rt->rt6i_siblings);
+	}
+
 	/* Adjust walkers */
 	read_lock(&fib6_walker_lock);
 	FOR_WALKERS(w) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7c7e963260e1..126da562d3eb 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -57,6 +57,7 @@
 #include <net/xfrm.h>
 #include <net/netevent.h>
 #include <net/netlink.h>
+#include <net/nexthop.h>
 
 #include <asm/uaccess.h>
 
@@ -289,6 +290,8 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
 		memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
 		rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
 		rt->rt6i_genid = rt_genid(net);
+		INIT_LIST_HEAD(&rt->rt6i_siblings);
+		rt->rt6i_nsiblings = 0;
 	}
 	return rt;
 }
@@ -385,6 +388,69 @@ static bool rt6_need_strict(const struct in6_addr *daddr)
 		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
 }
 
+/* Multipath route selection:
+ *   Hash based function using packet header and flowlabel.
+ * Adapted from fib_info_hashfn()
+ */
+static int rt6_info_hash_nhsfn(unsigned int candidate_count,
+			       const struct flowi6 *fl6)
+{
+	unsigned int val = fl6->flowi6_proto;
+
+	val ^= fl6->daddr.s6_addr32[0];
+	val ^= fl6->daddr.s6_addr32[1];
+	val ^= fl6->daddr.s6_addr32[2];
+	val ^= fl6->daddr.s6_addr32[3];
+
+	val ^= fl6->saddr.s6_addr32[0];
+	val ^= fl6->saddr.s6_addr32[1];
+	val ^= fl6->saddr.s6_addr32[2];
+	val ^= fl6->saddr.s6_addr32[3];
+
+	/* Work only if this not encapsulated */
+	switch (fl6->flowi6_proto) {
+	case IPPROTO_UDP:
+	case IPPROTO_TCP:
+	case IPPROTO_SCTP:
+		val ^= fl6->fl6_sport;
+		val ^= fl6->fl6_dport;
+		break;
+
+	case IPPROTO_ICMPV6:
+		val ^= fl6->fl6_icmp_type;
+		val ^= fl6->fl6_icmp_code;
+		break;
+	}
+	/* RFC6438 recommands to use flowlabel */
+	val ^= fl6->flowlabel;
+
+	/* Perhaps, we need to tune, this function? */
+	val = val ^ (val >> 7) ^ (val >> 12);
+	return val % candidate_count;
+}
+
+static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
+					     struct flowi6 *fl6)
+{
+	struct rt6_info *sibling, *next_sibling;
+	int route_choosen;
+
+	route_choosen = rt6_info_hash_nhsfn(match->rt6i_nsiblings + 1, fl6);
+	/* Don't change the route, if route_choosen == 0
+	 * (siblings does not include ourself)
+	 */
+	if (route_choosen)
+		list_for_each_entry_safe(sibling, next_sibling,
+				&match->rt6i_siblings, rt6i_siblings) {
+			route_choosen--;
+			if (route_choosen == 0) {
+				match = sibling;
+				break;
+			}
+		}
+	return match;
+}
+
 /*
  *	Route lookup. Any table->tb6_lock is implied.
  */
@@ -702,6 +768,8 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 restart:
 	rt = fn->leaf;
 	rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags);
+	if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
+		rt = rt6_multipath_select(rt, fl6);
 	BACKTRACK(net, &fl6->saddr);
 out:
 	dst_use(&rt->dst, jiffies);
@@ -863,7 +931,8 @@ restart_2:
 
 restart:
 	rt = rt6_select(fn, oif, strict | reachable);
-
+	if (rt->rt6i_nsiblings && oif == 0)
+		rt = rt6_multipath_select(rt, fl6);
 	BACKTRACK(net, &fl6->saddr);
 	if (rt == net->ipv6.ip6_null_entry ||
 	    rt->rt6i_flags & RTF_CACHE)
@@ -2249,6 +2318,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_IIF]		= { .type = NLA_U32 },
 	[RTA_PRIORITY]          = { .type = NLA_U32 },
 	[RTA_METRICS]           = { .type = NLA_NESTED },
+	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -2326,11 +2396,65 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RTA_TABLE])
 		cfg->fc_table = nla_get_u32(tb[RTA_TABLE]);
 
+	if (tb[RTA_MULTIPATH]) {
+		cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
+		cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
+	}
+
 	err = 0;
 errout:
 	return err;
 }
 
+static int ip6_route_multipath(struct fib6_config *cfg, int add)
+{
+	struct fib6_config r_cfg;
+	struct rtnexthop *rtnh;
+	int remaining;
+	int attrlen;
+	int err = 0, last_err = 0;
+
+beginning:
+	rtnh = (struct rtnexthop *)cfg->fc_mp;
+	remaining = cfg->fc_mp_len;
+
+	/* Parse a Multipath Entry */
+	while (rtnh_ok(rtnh, remaining)) {
+		memcpy(&r_cfg, cfg, sizeof(*cfg));
+		if (rtnh->rtnh_ifindex)
+			r_cfg.fc_ifindex = rtnh->rtnh_ifindex;
+
+		attrlen = rtnh_attrlen(rtnh);
+		if (attrlen > 0) {
+			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+
+			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+			if (nla) {
+				nla_memcpy(&r_cfg.fc_gateway, nla, 16);
+				r_cfg.fc_flags |= RTF_GATEWAY;
+			}
+		}
+		err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg);
+		if (err) {
+			last_err = err;
+			/* If we are trying to remove a route, do not stop the
+			 * loop when ip6_route_del() fails (because next hop is
+			 * already gone), we should try to remove all next hops.
+			 */
+			if (add) {
+				/* If add fails, we should try to delete all
+				 * next hops that have been already added.
+				 */
+				add = 0;
+				goto beginning;
+			}
+		}
+		rtnh = rtnh_next(rtnh, &remaining);
+	}
+
+	return last_err;
+}
+
 static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 {
 	struct fib6_config cfg;
@@ -2340,7 +2464,10 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a
 	if (err < 0)
 		return err;
 
-	return ip6_route_del(&cfg);
+	if (cfg.fc_mp)
+		return ip6_route_multipath(&cfg, 0);
+	else
+		return ip6_route_del(&cfg);
 }
 
 static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
@@ -2352,7 +2479,10 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a
 	if (err < 0)
 		return err;
 
-	return ip6_route_add(&cfg);
+	if (cfg.fc_mp)
+		return ip6_route_multipath(&cfg, 1);
+	else
+		return ip6_route_add(&cfg);
 }
 
 static inline size_t rt6_nlmsg_size(void)
-- 
cgit v1.2.3-55-g7522


From 0668744f792a737872aa1904010e5fba5f95376b Mon Sep 17 00:00:00 2001
From: Joachim Eastwood
Date: Mon, 22 Oct 2012 08:45:34 +0000
Subject: net/at91_ether: add pdata flag for reverse Eth addr

This will allow us to remove the last mach include from at91_ether
and also make it easier to share address setup with macb.

Signed-off-by: Joachim Eastwood <manabian@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/mach-at91/board-csb337.c         | 2 ++
 drivers/net/ethernet/cadence/Kconfig      | 1 -
 drivers/net/ethernet/cadence/at91_ether.c | 5 ++---
 include/linux/platform_data/macb.h        | 1 +
 4 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-at91/board-csb337.c b/arch/arm/mach-at91/board-csb337.c
index 3e37437a7a61..aa9b320bad59 100644
--- a/arch/arm/mach-at91/board-csb337.c
+++ b/arch/arm/mach-at91/board-csb337.c
@@ -53,6 +53,8 @@ static void __init csb337_init_early(void)
 static struct macb_platform_data __initdata csb337_eth_data = {
 	.phy_irq_pin	= AT91_PIN_PC2,
 	.is_rmii	= 0,
+	/* The CSB337 bootloader stores the MAC the wrong-way around */
+	.rev_eth_addr	= 1,
 };
 
 static struct at91_usbh_data __initdata csb337_usbh_data = {
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index f6d0956485f1..40172d1ca605 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -21,7 +21,6 @@ if NET_CADENCE
 
 config ARM_AT91_ETHER
 	tristate "AT91RM9200 Ethernet support"
-	depends on ARM && ARCH_AT91RM9200
 	select NET_CORE
 	select MACB
 	---help---
diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c
index 375d272d1a5f..b92815aabc65 100644
--- a/drivers/net/ethernet/cadence/at91_ether.c
+++ b/drivers/net/ethernet/cadence/at91_ether.c
@@ -32,8 +32,6 @@
 #include <linux/phy.h>
 #include <linux/io.h>
 
-#include <asm/mach-types.h>
-
 #include "macb.h"
 
 #define DRV_NAME	"at91_ether"
@@ -61,9 +59,10 @@
 
 static short __init unpack_mac_address(struct net_device *dev, unsigned int hi, unsigned int lo)
 {
+	struct macb *lp = netdev_priv(dev);
 	char addr[6];
 
-	if (machine_is_csb337()) {
+	if (lp->board_data.rev_eth_addr) {
 		addr[5] = (lo & 0xff);			/* The CSB337 bootloader stores the MAC the wrong-way around */
 		addr[4] = (lo & 0xff00) >> 8;
 		addr[3] = (lo & 0xff0000) >> 16;
diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h
index b081c7245ec8..044a124bfbbc 100644
--- a/include/linux/platform_data/macb.h
+++ b/include/linux/platform_data/macb.h
@@ -12,6 +12,7 @@ struct macb_platform_data {
 	u32		phy_mask;
 	int		phy_irq_pin;	/* PHY IRQ */
 	u8		is_rmii;	/* using RMII interface? */
+	u8		rev_eth_addr;	/* reverse Ethernet address byte order */
 };
 
 #endif /* __MACB_PDATA_H__ */
-- 
cgit v1.2.3-55-g7522


From 51615edd0a41b36f69858b9be1fbbf6a3de84f82 Mon Sep 17 00:00:00 2001
From: Greg Suarez
Date: Mon, 22 Oct 2012 10:56:29 +0000
Subject: USB: cdc: add MBIM constants and structures

Based on revision 1.0 of "Universal Serial Bus Communications
Class Subclass Specification for Mobile Broadband Interface
Model" available from www.usb.org

Signed-off-by: Greg Suarez <gsuarez@smithmicro.com>
[bmork: added DSS defines]
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/usb/cdc.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

(limited to 'include')

diff --git a/include/linux/usb/cdc.h b/include/linux/usb/cdc.h
index 81a927930bfd..f35aa0a338c7 100644
--- a/include/linux/usb/cdc.h
+++ b/include/linux/usb/cdc.h
@@ -19,6 +19,7 @@
 #define USB_CDC_SUBCLASS_OBEX			0x0b
 #define USB_CDC_SUBCLASS_EEM			0x0c
 #define USB_CDC_SUBCLASS_NCM			0x0d
+#define USB_CDC_SUBCLASS_MBIM			0x0e
 
 #define USB_CDC_PROTO_NONE			0
 
@@ -33,6 +34,7 @@
 #define USB_CDC_PROTO_EEM			7
 
 #define USB_CDC_NCM_PROTO_NTB			1
+#define USB_CDC_MBIM_PROTO_NTB			2
 
 /*-------------------------------------------------------------------------*/
 
@@ -53,6 +55,7 @@
 #define USB_CDC_DMM_TYPE		0x14
 #define USB_CDC_OBEX_TYPE		0x15
 #define USB_CDC_NCM_TYPE		0x1a
+#define USB_CDC_MBIM_TYPE		0x1b
 
 /* "Header Functional Descriptor" from CDC spec  5.2.3.1 */
 struct usb_cdc_header_desc {
@@ -187,6 +190,21 @@ struct usb_cdc_ncm_desc {
 	__le16	bcdNcmVersion;
 	__u8	bmNetworkCapabilities;
 } __attribute__ ((packed));
+
+/* "MBIM Control Model Functional Descriptor" */
+struct usb_cdc_mbim_desc {
+	__u8	bLength;
+	__u8	bDescriptorType;
+	__u8	bDescriptorSubType;
+
+	__le16	bcdMBIMVersion;
+	__le16  wMaxControlMessage;
+	__u8    bNumberFilters;
+	__u8    bMaxFilterSize;
+	__le16  wMaxSegmentSize;
+	__u8    bmNetworkCapabilities;
+} __attribute__ ((packed));
+
 /*-------------------------------------------------------------------------*/
 
 /*
@@ -332,6 +350,11 @@ struct usb_cdc_ncm_nth32 {
 #define USB_CDC_NCM_NDP32_CRC_SIGN	0x316D636E /* ncm1 */
 #define USB_CDC_NCM_NDP32_NOCRC_SIGN	0x306D636E /* ncm0 */
 
+#define USB_CDC_MBIM_NDP16_IPS_SIGN     0x00535049 /* IPS<sessionID> : IPS0 for now */
+#define USB_CDC_MBIM_NDP32_IPS_SIGN     0x00737069 /* ips<sessionID> : ips0 for now */
+#define USB_CDC_MBIM_NDP16_DSS_SIGN     0x00535344 /* DSS<sessionID> */
+#define USB_CDC_MBIM_NDP32_DSS_SIGN     0x00737364 /* dss<sessionID> */
+
 /* 16-bit NCM Datagram Pointer Entry */
 struct usb_cdc_ncm_dpe16 {
 	__le16	wDatagramIndex;
-- 
cgit v1.2.3-55-g7522


From c91ce3b6bff780453283a5882ecd54f267f4682f Mon Sep 17 00:00:00 2001
From: Bjørn Mork
Date: Mon, 22 Oct 2012 10:56:35 +0000
Subject: net: cdc_ncm: export shared symbols and definitions

Move symbols and definitons which can be shared with a
MBIM driver in a new header.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c   |  97 ++++------------------------------
 include/linux/usb/cdc_ncm.h | 124 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 135 insertions(+), 86 deletions(-)
 create mode 100644 include/linux/usb/cdc_ncm.h

(limited to 'include')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 2dd27346cb39..17b4ba03cb55 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -51,90 +51,10 @@
 #include <linux/atomic.h>
 #include <linux/usb/usbnet.h>
 #include <linux/usb/cdc.h>
+#include <linux/usb/cdc_ncm.h>
 
 #define	DRIVER_VERSION				"14-Mar-2012"
 
-/* CDC NCM subclass 3.2.1 */
-#define USB_CDC_NCM_NDP16_LENGTH_MIN		0x10
-
-/* Maximum NTB length */
-#define	CDC_NCM_NTB_MAX_SIZE_TX			32768	/* bytes */
-#define	CDC_NCM_NTB_MAX_SIZE_RX			32768	/* bytes */
-
-/* Minimum value for MaxDatagramSize, ch. 6.2.9 */
-#define	CDC_NCM_MIN_DATAGRAM_SIZE		1514	/* bytes */
-
-/* Minimum value for MaxDatagramSize, ch. 8.1.3 */
-#define CDC_MBIM_MIN_DATAGRAM_SIZE              2048    /* bytes */
-
-#define	CDC_NCM_MIN_TX_PKT			512	/* bytes */
-
-/* Default value for MaxDatagramSize */
-#define	CDC_NCM_MAX_DATAGRAM_SIZE		8192	/* bytes */
-
-/*
- * Maximum amount of datagrams in NCM Datagram Pointer Table, not counting
- * the last NULL entry.
- */
-#define	CDC_NCM_DPT_DATAGRAMS_MAX		40
-
-/* Restart the timer, if amount of datagrams is less than given value */
-#define	CDC_NCM_RESTART_TIMER_DATAGRAM_CNT	3
-#define	CDC_NCM_TIMER_PENDING_CNT		2
-#define CDC_NCM_TIMER_INTERVAL			(400UL * NSEC_PER_USEC)
-
-/* The following macro defines the minimum header space */
-#define	CDC_NCM_MIN_HDR_SIZE \
-	(sizeof(struct usb_cdc_ncm_nth16) + sizeof(struct usb_cdc_ncm_ndp16) + \
-	(CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16))
-
-#define CDC_NCM_NDP_SIZE \
-	(sizeof(struct usb_cdc_ncm_ndp16) +				\
-	      (CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16))
-
-struct cdc_ncm_ctx {
-	struct usb_cdc_ncm_ntb_parameters ncm_parm;
-	struct hrtimer tx_timer;
-	struct tasklet_struct bh;
-
-	const struct usb_cdc_ncm_desc *func_desc;
-	const struct usb_cdc_mbim_desc *mbim_desc;
-	const struct usb_cdc_header_desc *header_desc;
-	const struct usb_cdc_union_desc *union_desc;
-	const struct usb_cdc_ether_desc *ether_desc;
-
-	struct net_device *netdev;
-	struct usb_device *udev;
-	struct usb_host_endpoint *in_ep;
-	struct usb_host_endpoint *out_ep;
-	struct usb_host_endpoint *status_ep;
-	struct usb_interface *intf;
-	struct usb_interface *control;
-	struct usb_interface *data;
-
-	struct sk_buff *tx_curr_skb;
-	struct sk_buff *tx_rem_skb;
-	__le32 tx_rem_sign;
-
-	spinlock_t mtx;
-	atomic_t stop;
-
-	u32 tx_timer_pending;
-	u32 tx_curr_frame_num;
-	u32 rx_speed;
-	u32 tx_speed;
-	u32 rx_max;
-	u32 tx_max;
-	u32 max_datagram_size;
-	u16 tx_max_datagrams;
-	u16 tx_remainder;
-	u16 tx_modulus;
-	u16 tx_ndp_modulus;
-	u16 tx_seq;
-	u16 rx_seq;
-	u16 connected;
-};
-
 static void cdc_ncm_txpath_bh(unsigned long param);
 static void cdc_ncm_tx_timeout_start(struct cdc_ncm_ctx *ctx);
 static enum hrtimer_restart cdc_ncm_tx_timer_cb(struct hrtimer *hr_timer);
@@ -447,7 +367,7 @@ static const struct ethtool_ops cdc_ncm_ethtool_ops = {
 	.nway_reset = usbnet_nway_reset,
 };
 
-static int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting)
+int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting)
 {
 	struct cdc_ncm_ctx *ctx;
 	struct usb_driver *driver;
@@ -605,8 +525,9 @@ error:
 	dev_info(&dev->udev->dev, "bind() failure\n");
 	return -ENODEV;
 }
+EXPORT_SYMBOL_GPL(cdc_ncm_bind_common);
 
-static void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf)
+void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf)
 {
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
 	struct usb_driver *driver = driver_of(intf);
@@ -636,6 +557,7 @@ static void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf)
 	usb_set_intfdata(ctx->intf, NULL);
 	cdc_ncm_free(ctx);
 }
+EXPORT_SYMBOL_GPL(cdc_ncm_unbind);
 
 static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 {
@@ -701,7 +623,7 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_
 	return ndp16;
 }
 
-static struct sk_buff *
+struct sk_buff *
 cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign)
 {
 	struct usb_cdc_ncm_nth16 *nth16;
@@ -858,6 +780,7 @@ exit_no_skb:
 		cdc_ncm_tx_timeout_start(ctx);
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(cdc_ncm_fill_tx_frame);
 
 static void cdc_ncm_tx_timeout_start(struct cdc_ncm_ctx *ctx)
 {
@@ -924,7 +847,7 @@ error:
 }
 
 /* verify NTB header and return offset of first NDP, or negative error */
-static int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in)
+int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in)
 {
 	struct usb_cdc_ncm_nth16 *nth16;
 	int len;
@@ -966,9 +889,10 @@ static int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_
 error:
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cdc_ncm_rx_verify_nth16);
 
 /* verify NDP header and return number of datagrams, or negative error */
-static int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset)
+int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset)
 {
 	struct usb_cdc_ncm_ndp16 *ndp16;
 	int ret = -EINVAL;
@@ -999,6 +923,7 @@ static int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset)
 error:
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cdc_ncm_rx_verify_ndp16);
 
 static int cdc_ncm_rx_fixup(struct usbnet *dev, struct sk_buff *skb_in)
 {
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
new file mode 100644
index 000000000000..d1719a72f7d2
--- /dev/null
+++ b/include/linux/usb/cdc_ncm.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) ST-Ericsson 2010-2012
+ * Contact: Alexey Orishko <alexey.orishko@stericsson.com>
+ * Original author: Hans Petter Selasky <hans.petter.selasky@stericsson.com>
+ *
+ * USB Host Driver for Network Control Model (NCM)
+ * http://www.usb.org/developers/devclass_docs/NCM10.zip
+ *
+ * The NCM encoding, decoding and initialization logic
+ * derives from FreeBSD 8.x. if_cdce.c and if_cdcereg.h
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose this file to be licensed under the terms
+ * of the GNU General Public License (GPL) Version 2 or the 2-clause
+ * BSD license listed below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+/* CDC NCM subclass 3.2.1 */
+#define USB_CDC_NCM_NDP16_LENGTH_MIN		0x10
+
+/* Maximum NTB length */
+#define	CDC_NCM_NTB_MAX_SIZE_TX			32768	/* bytes */
+#define	CDC_NCM_NTB_MAX_SIZE_RX			32768	/* bytes */
+
+/* Minimum value for MaxDatagramSize, ch. 6.2.9 */
+#define	CDC_NCM_MIN_DATAGRAM_SIZE		1514	/* bytes */
+
+/* Minimum value for MaxDatagramSize, ch. 8.1.3 */
+#define CDC_MBIM_MIN_DATAGRAM_SIZE		2048	/* bytes */
+
+#define	CDC_NCM_MIN_TX_PKT			512	/* bytes */
+
+/* Default value for MaxDatagramSize */
+#define	CDC_NCM_MAX_DATAGRAM_SIZE		8192	/* bytes */
+
+/*
+ * Maximum amount of datagrams in NCM Datagram Pointer Table, not counting
+ * the last NULL entry.
+ */
+#define	CDC_NCM_DPT_DATAGRAMS_MAX		40
+
+/* Restart the timer, if amount of datagrams is less than given value */
+#define	CDC_NCM_RESTART_TIMER_DATAGRAM_CNT	3
+#define	CDC_NCM_TIMER_PENDING_CNT		2
+#define CDC_NCM_TIMER_INTERVAL			(400UL * NSEC_PER_USEC)
+
+/* The following macro defines the minimum header space */
+#define	CDC_NCM_MIN_HDR_SIZE \
+	(sizeof(struct usb_cdc_ncm_nth16) + sizeof(struct usb_cdc_ncm_ndp16) + \
+	(CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16))
+
+#define CDC_NCM_NDP_SIZE \
+	(sizeof(struct usb_cdc_ncm_ndp16) +				\
+	      (CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16))
+
+struct cdc_ncm_ctx {
+	struct usb_cdc_ncm_ntb_parameters ncm_parm;
+	struct hrtimer tx_timer;
+	struct tasklet_struct bh;
+
+	const struct usb_cdc_ncm_desc *func_desc;
+	const struct usb_cdc_mbim_desc   *mbim_desc;
+	const struct usb_cdc_header_desc *header_desc;
+	const struct usb_cdc_union_desc *union_desc;
+	const struct usb_cdc_ether_desc *ether_desc;
+
+	struct net_device *netdev;
+	struct usb_device *udev;
+	struct usb_host_endpoint *in_ep;
+	struct usb_host_endpoint *out_ep;
+	struct usb_host_endpoint *status_ep;
+	struct usb_interface *intf;
+	struct usb_interface *control;
+	struct usb_interface *data;
+
+	struct sk_buff *tx_curr_skb;
+	struct sk_buff *tx_rem_skb;
+	__le32 tx_rem_sign;
+
+	spinlock_t mtx;
+	atomic_t stop;
+
+	u32 tx_timer_pending;
+	u32 tx_curr_frame_num;
+	u32 rx_speed;
+	u32 tx_speed;
+	u32 rx_max;
+	u32 tx_max;
+	u32 max_datagram_size;
+	u16 tx_max_datagrams;
+	u16 tx_remainder;
+	u16 tx_modulus;
+	u16 tx_ndp_modulus;
+	u16 tx_seq;
+	u16 rx_seq;
+	u16 connected;
+};
+
+extern int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting);
+extern void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
+extern struct sk_buff *cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign);
+extern int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in);
+extern int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset);
-- 
cgit v1.2.3-55-g7522


From 9bf211a30b3f158c39cf1c6adb3a9388d41740ce Mon Sep 17 00:00:00 2001
From: Greg Suarez
Date: Mon, 22 Oct 2012 10:56:36 +0000
Subject: net: cdc_mbim: adding MBIM driver

The CDC Mobile Broadband Interface Model (MBIM) specification
extends CDC NCM by
 - removing the redundant ethernet header from the point-to-point
   USB channel
 - adding support for multiple IP (v4 and/or v6) sessions multiplexed
   on the same USB channel
 - adding a MBIM control channel encapsulated in CDC
 - adding Device Service Streams (DSS), which are non IP generic data
   streams multiplexed on the same USB channel as the IP sessions

MBIM devices are managed using the dedicated control channel, and no
data will flow on the data channel until a control session has been
established.  This driver has no knowledge of MBIM control messages.
It just exports the control channel to a /dev/cdc-wdmX character
device for userspace management applications. Such an application is
therefore required to use this driver.

This patch implements basic MBIM support, reusing the NCM and WDM driver
APIs, currently limited to IP sessions with SessionID 0. DSS and
multiplexed IP sessions are not yet supported.

Signed-off-by: Greg Suarez <gsuarez@smithmicro.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_mbim.c  | 365 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/usb/cdc_ncm.h |  10 ++
 2 files changed, 375 insertions(+)
 create mode 100644 drivers/net/usb/cdc_mbim.c

(limited to 'include')

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
new file mode 100644
index 000000000000..2f21139466ec
--- /dev/null
+++ b/drivers/net/usb/cdc_mbim.c
@@ -0,0 +1,365 @@
+/*
+ * Copyright (c) 2012  Smith Micro Software, Inc.
+ * Copyright (c) 2012  Bjørn Mork <bjorn@mork.no>
+ *
+ * This driver is based on and reuse most of cdc_ncm, which is
+ * Copyright (C) ST-Ericsson 2010-2012
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/ip.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/usb/cdc.h>
+#include <linux/usb/usbnet.h>
+#include <linux/usb/cdc-wdm.h>
+#include <linux/usb/cdc_ncm.h>
+
+/* driver specific data - must match cdc_ncm usage */
+struct cdc_mbim_state {
+	struct cdc_ncm_ctx *ctx;
+	atomic_t pmcount;
+	struct usb_driver *subdriver;
+	struct usb_interface *control;
+	struct usb_interface *data;
+};
+
+/* using a counter to merge subdriver requests with our own into a combined state */
+static int cdc_mbim_manage_power(struct usbnet *dev, int on)
+{
+	struct cdc_mbim_state *info = (void *)&dev->data;
+	int rv = 0;
+
+	dev_dbg(&dev->intf->dev, "%s() pmcount=%d, on=%d\n", __func__, atomic_read(&info->pmcount), on);
+
+	if ((on && atomic_add_return(1, &info->pmcount) == 1) || (!on && atomic_dec_and_test(&info->pmcount))) {
+		/* need autopm_get/put here to ensure the usbcore sees the new value */
+		rv = usb_autopm_get_interface(dev->intf);
+		if (rv < 0)
+			goto err;
+		dev->intf->needs_remote_wakeup = on;
+		usb_autopm_put_interface(dev->intf);
+	}
+err:
+	return rv;
+}
+
+static int cdc_mbim_wdm_manage_power(struct usb_interface *intf, int status)
+{
+	struct usbnet *dev = usb_get_intfdata(intf);
+
+	/* can be called while disconnecting */
+	if (!dev)
+		return 0;
+
+	return cdc_mbim_manage_power(dev, status);
+}
+
+
+static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+	struct cdc_ncm_ctx *ctx;
+	struct usb_driver *subdriver = ERR_PTR(-ENODEV);
+	int ret = -ENODEV;
+	u8 data_altsetting = CDC_NCM_DATA_ALTSETTING_NCM;
+	struct cdc_mbim_state *info = (void *)&dev->data;
+
+	/* see if interface supports MBIM alternate setting */
+	if (intf->num_altsetting == 2) {
+		if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
+			usb_set_interface(dev->udev,
+					  intf->cur_altsetting->desc.bInterfaceNumber,
+					  CDC_NCM_COMM_ALTSETTING_MBIM);
+		data_altsetting = CDC_NCM_DATA_ALTSETTING_MBIM;
+	}
+
+	/* Probably NCM, defer for cdc_ncm_bind */
+	if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
+		goto err;
+
+	ret = cdc_ncm_bind_common(dev, intf, data_altsetting);
+	if (ret)
+		goto err;
+
+	ctx = info->ctx;
+
+	/* The MBIM descriptor and the status endpoint are required */
+	if (ctx->mbim_desc && dev->status)
+		subdriver = usb_cdc_wdm_register(ctx->control,
+						 &dev->status->desc,
+						 le16_to_cpu(ctx->mbim_desc->wMaxControlMessage),
+						 cdc_mbim_wdm_manage_power);
+	if (IS_ERR(subdriver)) {
+		ret = PTR_ERR(subdriver);
+		cdc_ncm_unbind(dev, intf);
+		goto err;
+	}
+
+	/* can't let usbnet use the interrupt endpoint */
+	dev->status = NULL;
+	info->subdriver = subdriver;
+
+	/* MBIM cannot do ARP */
+	dev->net->flags |= IFF_NOARP;
+err:
+	return ret;
+}
+
+static void cdc_mbim_unbind(struct usbnet *dev, struct usb_interface *intf)
+{
+	struct cdc_mbim_state *info = (void *)&dev->data;
+	struct cdc_ncm_ctx *ctx = info->ctx;
+
+	/* disconnect subdriver from control interface */
+	if (info->subdriver && info->subdriver->disconnect)
+		info->subdriver->disconnect(ctx->control);
+	info->subdriver = NULL;
+
+	/* let NCM unbind clean up both control and data interface */
+	cdc_ncm_unbind(dev, intf);
+}
+
+
+static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags)
+{
+	struct sk_buff *skb_out;
+	struct cdc_mbim_state *info = (void *)&dev->data;
+	struct cdc_ncm_ctx *ctx = info->ctx;
+
+	if (!ctx)
+		goto error;
+
+	if (skb) {
+		if (skb->len <= sizeof(ETH_HLEN))
+			goto error;
+
+		skb_reset_mac_header(skb);
+		switch (eth_hdr(skb)->h_proto) {
+		case htons(ETH_P_IP):
+		case htons(ETH_P_IPV6):
+			skb_pull(skb, ETH_HLEN);
+			break;
+		default:
+			goto error;
+		}
+	}
+
+	spin_lock_bh(&ctx->mtx);
+	skb_out = cdc_ncm_fill_tx_frame(ctx, skb, cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN));
+	spin_unlock_bh(&ctx->mtx);
+	return skb_out;
+
+error:
+	if (skb)
+		dev_kfree_skb_any(skb);
+
+	return NULL;
+}
+
+static struct sk_buff *cdc_mbim_process_dgram(struct usbnet *dev, u8 *buf, size_t len)
+{
+	__be16 proto;
+	struct sk_buff *skb = NULL;
+
+	switch (*buf & 0xf0) {
+	case 0x40:
+		proto = htons(ETH_P_IP);
+		break;
+	case 0x60:
+		proto = htons(ETH_P_IPV6);
+		break;
+	default:
+		goto err;
+	}
+
+	skb = netdev_alloc_skb_ip_align(dev->net,  len + ETH_HLEN);
+	if (!skb)
+		goto err;
+
+	/* add an ethernet header */
+	skb_put(skb, ETH_HLEN);
+	skb_reset_mac_header(skb);
+	eth_hdr(skb)->h_proto = proto;
+	memset(eth_hdr(skb)->h_source, 0, ETH_ALEN);
+	memcpy(eth_hdr(skb)->h_dest, dev->net->dev_addr, ETH_ALEN);
+
+	/* add datagram */
+	memcpy(skb_put(skb, len), buf, len);
+err:
+	return skb;
+}
+
+static int cdc_mbim_rx_fixup(struct usbnet *dev, struct sk_buff *skb_in)
+{
+	struct sk_buff *skb;
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	int len;
+	int nframes;
+	int x;
+	int offset;
+	struct usb_cdc_ncm_ndp16 *ndp16;
+	struct usb_cdc_ncm_dpe16 *dpe16;
+	int ndpoffset;
+	int loopcount = 50; /* arbitrary max preventing infinite loop */
+
+	ndpoffset = cdc_ncm_rx_verify_nth16(ctx, skb_in);
+	if (ndpoffset < 0)
+		goto error;
+
+next_ndp:
+	nframes = cdc_ncm_rx_verify_ndp16(skb_in, ndpoffset);
+	if (nframes < 0)
+		goto error;
+
+	ndp16 = (struct usb_cdc_ncm_ndp16 *)(skb_in->data + ndpoffset);
+
+	/* only supporting IPS Session #0 for now */
+	switch (ndp16->dwSignature) {
+	case cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN):
+		break;
+	default:
+		netif_dbg(dev, rx_err, dev->net,
+			  "unsupported NDP signature <0x%08x>\n",
+			  le32_to_cpu(ndp16->dwSignature));
+		goto err_ndp;
+
+	}
+
+	dpe16 = ndp16->dpe16;
+	for (x = 0; x < nframes; x++, dpe16++) {
+		offset = le16_to_cpu(dpe16->wDatagramIndex);
+		len = le16_to_cpu(dpe16->wDatagramLength);
+
+		/*
+		 * CDC NCM ch. 3.7
+		 * All entries after first NULL entry are to be ignored
+		 */
+		if ((offset == 0) || (len == 0)) {
+			if (!x)
+				goto err_ndp; /* empty NTB */
+			break;
+		}
+
+		/* sanity checking */
+		if (((offset + len) > skb_in->len) || (len > ctx->rx_max) ||
+		    (len < sizeof(struct iphdr))) {
+			netif_dbg(dev, rx_err, dev->net,
+				  "invalid frame detected (ignored) offset[%u]=%u, length=%u, skb=%p\n",
+				  x, offset, len, skb_in);
+			if (!x)
+				goto err_ndp;
+			break;
+		} else {
+			skb = cdc_mbim_process_dgram(dev, skb_in->data + offset, len);
+			if (!skb)
+				goto error;
+			usbnet_skb_return(dev, skb);
+		}
+	}
+err_ndp:
+	/* are there more NDPs to process? */
+	ndpoffset = le16_to_cpu(ndp16->wNextNdpIndex);
+	if (ndpoffset && loopcount--)
+		goto next_ndp;
+
+	return 1;
+error:
+	return 0;
+}
+
+static int cdc_mbim_suspend(struct usb_interface *intf, pm_message_t message)
+{
+	int ret = 0;
+	struct usbnet *dev = usb_get_intfdata(intf);
+	struct cdc_mbim_state *info = (void *)&dev->data;
+	struct cdc_ncm_ctx *ctx = info->ctx;
+
+	if (ctx == NULL) {
+		ret = -1;
+		goto error;
+	}
+
+	ret = usbnet_suspend(intf, message);
+	if (ret < 0)
+		goto error;
+
+	if (intf == ctx->control && info->subdriver && info->subdriver->suspend)
+		ret = info->subdriver->suspend(intf, message);
+	if (ret < 0)
+		usbnet_resume(intf);
+
+error:
+	return ret;
+}
+
+static int cdc_mbim_resume(struct usb_interface *intf)
+{
+	int  ret = 0;
+	struct usbnet *dev = usb_get_intfdata(intf);
+	struct cdc_mbim_state *info = (void *)&dev->data;
+	struct cdc_ncm_ctx *ctx = info->ctx;
+	bool callsub = (intf == ctx->control && info->subdriver && info->subdriver->resume);
+
+	if (callsub)
+		ret = info->subdriver->resume(intf);
+	if (ret < 0)
+		goto err;
+	ret = usbnet_resume(intf);
+	if (ret < 0 && callsub && info->subdriver->suspend)
+		info->subdriver->suspend(intf, PMSG_SUSPEND);
+err:
+	return ret;
+}
+
+static const struct driver_info cdc_mbim_info = {
+	.description = "CDC MBIM",
+	.flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN,
+	.bind = cdc_mbim_bind,
+	.unbind = cdc_mbim_unbind,
+	.manage_power = cdc_mbim_manage_power,
+	.rx_fixup = cdc_mbim_rx_fixup,
+	.tx_fixup = cdc_mbim_tx_fixup,
+};
+
+static const struct usb_device_id mbim_devs[] = {
+	/* This duplicate NCM entry is intentional. MBIM devices can
+	 * be disguised as NCM by default, and this is necessary to
+	 * allow us to bind the correct driver_info to such devices.
+	 *
+	 * bind() will sort out this for us, selecting the correct
+	 * entry and reject the other
+	 */
+	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE),
+	  .driver_info = (unsigned long)&cdc_mbim_info,
+	},
+	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
+	  .driver_info = (unsigned long)&cdc_mbim_info,
+	},
+	{
+	},
+};
+MODULE_DEVICE_TABLE(usb, mbim_devs);
+
+static struct usb_driver cdc_mbim_driver = {
+	.name = "cdc_mbim",
+	.id_table = mbim_devs,
+	.probe = usbnet_probe,
+	.disconnect = usbnet_disconnect,
+	.suspend = cdc_mbim_suspend,
+	.resume = cdc_mbim_resume,
+	.reset_resume =	cdc_mbim_resume,
+	.supports_autosuspend = 1,
+	.disable_hub_initiated_lpm = 1,
+};
+module_usb_driver(cdc_mbim_driver);
+
+MODULE_AUTHOR("Greg Suarez <gsuarez@smithmicro.com>");
+MODULE_AUTHOR("Bjørn Mork <bjorn@mork.no>");
+MODULE_DESCRIPTION("USB CDC MBIM host driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index d1719a72f7d2..3b8f9d4fc3fe 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -36,6 +36,12 @@
  * SUCH DAMAGE.
  */
 
+#define CDC_NCM_COMM_ALTSETTING_NCM		0
+#define CDC_NCM_COMM_ALTSETTING_MBIM		1
+
+#define CDC_NCM_DATA_ALTSETTING_NCM		1
+#define CDC_NCM_DATA_ALTSETTING_MBIM		2
+
 /* CDC NCM subclass 3.2.1 */
 #define USB_CDC_NCM_NDP16_LENGTH_MIN		0x10
 
@@ -74,6 +80,10 @@
 	(sizeof(struct usb_cdc_ncm_ndp16) +				\
 	      (CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16))
 
+#define cdc_ncm_comm_intf_is_mbim(x)  ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \
+				       (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE)
+#define cdc_ncm_data_intf_is_mbim(x)  ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB)
+
 struct cdc_ncm_ctx {
 	struct usb_cdc_ncm_ntb_parameters ncm_parm;
 	struct hrtimer tx_timer;
-- 
cgit v1.2.3-55-g7522


From 8ca40a70a70988c0bdea106c894843f763ca2989 Mon Sep 17 00:00:00 2001
From: Christoffer Dall
Date: Sun, 14 Oct 2012 23:10:18 -0400
Subject: KVM: Take kvm instead of vcpu to mmu_notifier_retry

The mmu_notifier_retry is not specific to any vcpu (and never will be)
so only take struct kvm as a parameter.

The motivation is the ARM mmu code that needs to call this from
somewhere where we long let go of the vcpu pointer.

Signed-off-by: Christoffer Dall <c.dall@virtualopensystems.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 +-
 arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +-
 arch/x86/kvm/mmu.c                  | 4 ++--
 arch/x86/kvm/paging_tmpl.h          | 2 +-
 include/linux/kvm_host.h            | 6 +++---
 5 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 7a4aae99ac5b..2a89a36e7263 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -710,7 +710,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	/* Check if we might have been invalidated; let the guest retry if so */
 	ret = RESUME_GUEST;
-	if (mmu_notifier_retry(vcpu, mmu_seq)) {
+	if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) {
 		unlock_rmap(rmap);
 		goto out_unlock;
 	}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 9955216477a4..5e06e3153888 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -297,7 +297,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 		lock_rmap(rmap);
 		/* Check for pending invalidations under the rmap chain lock */
 		if (kvm->arch.using_mmu_notifiers &&
-		    mmu_notifier_retry(vcpu, mmu_seq)) {
+		    mmu_notifier_retry(vcpu->kvm, mmu_seq)) {
 			/* inval in progress, write a non-present HPTE */
 			pteh |= HPTE_V_ABSENT;
 			pteh &= ~HPTE_V_VALID;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 3d5ca7939380..6f78fa3a4706 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2886,7 +2886,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 		return r;
 
 	spin_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_notifier_retry(vcpu, mmu_seq))
+	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
 	kvm_mmu_free_some_pages(vcpu);
 	if (likely(!force_pt_level))
@@ -3355,7 +3355,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 		return r;
 
 	spin_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_notifier_retry(vcpu, mmu_seq))
+	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
 	kvm_mmu_free_some_pages(vcpu);
 	if (likely(!force_pt_level))
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index f887e4cfc1fe..d17decaf1db9 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -565,7 +565,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 		return r;
 
 	spin_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_notifier_retry(vcpu, mmu_seq))
+	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
 
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 6afc5be2615e..82e2c783a21e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -841,9 +841,9 @@ extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
-static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_seq)
+static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
-	if (unlikely(vcpu->kvm->mmu_notifier_count))
+	if (unlikely(kvm->mmu_notifier_count))
 		return 1;
 	/*
 	 * Ensure the read of mmu_notifier_count happens before the read
@@ -856,7 +856,7 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se
 	 * can't rely on kvm->mmu_lock to keep things ordered.
 	 */
 	smp_rmb();
-	if (vcpu->kvm->mmu_notifier_seq != mmu_seq)
+	if (kvm->mmu_notifier_seq != mmu_seq)
 		return 1;
 	return 0;
 }
-- 
cgit v1.2.3-55-g7522


From 0e8014d772a7639f48d234b23dc4ce97335cce7f Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart
Date: Mon, 22 Oct 2012 16:42:14 -0500
Subject: ALSA: core: keep track of boundary wrap-around

Keep track of boundary crossing when hw_ptr
exceeds boundary limit and wraps-around. This
will help keep track of total number
of frames played/received at the kernel level

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h  |  1 +
 sound/core/pcm_lib.c | 25 ++++++++++++++++++++-----
 2 files changed, 21 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 6268a4192d5c..28fd9f95f9ba 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -281,6 +281,7 @@ struct snd_pcm_runtime {
 	unsigned long hw_ptr_jiffies;	/* Time when hw_ptr is updated */
 	unsigned long hw_ptr_buffer_jiffies; /* buffer time in jiffies */
 	snd_pcm_sframes_t delay;	/* extra delay; typically FIFO size */
+	u64 hw_ptr_wrap;                /* offset for hw_ptr due to boundary wrap-around */
 
 	/* -- HW params -- */
 	snd_pcm_access_t access;	/* access mode */
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index f42c10a43315..3dc029e106a2 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -316,6 +316,7 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 	unsigned long jdelta;
 	unsigned long curr_jiffies;
 	struct timespec curr_tstamp;
+	int crossed_boundary = 0;
 
 	old_hw_ptr = runtime->status->hw_ptr;
 
@@ -360,8 +361,10 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 			hdelta = curr_jiffies - runtime->hw_ptr_jiffies;
 			if (hdelta > runtime->hw_ptr_buffer_jiffies/2) {
 				hw_base += runtime->buffer_size;
-				if (hw_base >= runtime->boundary)
+				if (hw_base >= runtime->boundary) {
 					hw_base = 0;
+					crossed_boundary++;
+				}
 				new_hw_ptr = hw_base + pos;
 				goto __delta;
 			}
@@ -371,8 +374,10 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 	/* pointer crosses the end of the ring buffer */
 	if (new_hw_ptr < old_hw_ptr) {
 		hw_base += runtime->buffer_size;
-		if (hw_base >= runtime->boundary)
+		if (hw_base >= runtime->boundary) {
 			hw_base = 0;
+			crossed_boundary++;
+		}
 		new_hw_ptr = hw_base + pos;
 	}
       __delta:
@@ -410,8 +415,10 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 		while (hdelta > xrun_threshold) {
 			delta += runtime->buffer_size;
 			hw_base += runtime->buffer_size;
-			if (hw_base >= runtime->boundary)
+			if (hw_base >= runtime->boundary) {
 				hw_base = 0;
+				crossed_boundary++;
+			}
 			new_hw_ptr = hw_base + pos;
 			hdelta -= runtime->hw_ptr_buffer_jiffies;
 		}
@@ -456,8 +463,10 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 		/* the delta value is small or zero in most cases */
 		while (delta > 0) {
 			new_hw_ptr += runtime->period_size;
-			if (new_hw_ptr >= runtime->boundary)
+			if (new_hw_ptr >= runtime->boundary) {
 				new_hw_ptr -= runtime->boundary;
+				crossed_boundary--;
+			}
 			delta--;
 		}
 		/* align hw_base to buffer_size */
@@ -507,6 +516,10 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 	runtime->hw_ptr_base = hw_base;
 	runtime->status->hw_ptr = new_hw_ptr;
 	runtime->hw_ptr_jiffies = curr_jiffies;
+	if (crossed_boundary) {
+		snd_BUG_ON(crossed_boundary != 1);
+		runtime->hw_ptr_wrap += runtime->boundary;
+	}
 	if (runtime->tstamp_mode == SNDRV_PCM_TSTAMP_ENABLE)
 		runtime->status->tstamp = curr_tstamp;
 
@@ -1661,8 +1674,10 @@ static int snd_pcm_lib_ioctl_reset(struct snd_pcm_substream *substream,
 	if (snd_pcm_running(substream) &&
 	    snd_pcm_update_hw_ptr(substream) >= 0)
 		runtime->status->hw_ptr %= runtime->buffer_size;
-	else
+	else {
 		runtime->status->hw_ptr = 0;
+		runtime->hw_ptr_wrap = 0;
+	}
 	snd_pcm_stream_unlock_irqrestore(substream, flags);
 	return 0;
 }
-- 
cgit v1.2.3-55-g7522


From 4eeaaeaea1cec60a25979678182720dc91308550 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart
Date: Mon, 22 Oct 2012 16:42:15 -0500
Subject: ALSA: core: add hooks for audio timestamps

ALSA did not provide any direct means to infer the audio time for A/V
sync and system/audio time correlations (eg. PulseAudio).
Applications had to track the number of samples read/written and
add/subtract the number of samples queued in the ring buffer.  This
accounting led to small errors, typically several samples, due to the
two-step process.  Computing the audio time in the kernel is more
direct, as all the information is available in the same routines.

Also add new .audio_wallclock routine to enable fine-grain synchronization
between monotonic system time and audio hardware time.
Using the wallclock, if supported in hardware, allows for a
much better sub-microsecond precision and a common drift tracking for
all devices sharing the same wall clock (master clock).

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h         |  2 ++
 include/uapi/sound/asound.h |  7 +++++--
 sound/core/pcm_compat.c     | 19 +++++++++++--------
 sound/core/pcm_lib.c        | 32 ++++++++++++++++++++++++++++++--
 sound/core/pcm_native.c     |  2 ++
 5 files changed, 50 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 28fd9f95f9ba..45c1981c9ca2 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -71,6 +71,8 @@ struct snd_pcm_ops {
 	int (*prepare)(struct snd_pcm_substream *substream);
 	int (*trigger)(struct snd_pcm_substream *substream, int cmd);
 	snd_pcm_uframes_t (*pointer)(struct snd_pcm_substream *substream);
+	int (*wall_clock)(struct snd_pcm_substream *substream,
+			  struct timespec *audio_ts);
 	int (*copy)(struct snd_pcm_substream *substream, int channel,
 		    snd_pcm_uframes_t pos,
 		    void __user *buf, snd_pcm_uframes_t count);
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 92b104e496b5..85b2e4dde883 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -136,7 +136,7 @@ struct snd_hwdep_dsp_image {
  *                                                                           *
  *****************************************************************************/
 
-#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 10)
+#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 11)
 
 typedef unsigned long snd_pcm_uframes_t;
 typedef signed long snd_pcm_sframes_t;
@@ -258,6 +258,7 @@ typedef int __bitwise snd_pcm_subformat_t;
 #define SNDRV_PCM_INFO_JOINT_DUPLEX	0x00200000	/* playback and capture stream are somewhat correlated */
 #define SNDRV_PCM_INFO_SYNC_START	0x00400000	/* pcm support some kind of sync go */
 #define SNDRV_PCM_INFO_NO_PERIOD_WAKEUP	0x00800000	/* period wakeup can be disabled */
+#define SNDRV_PCM_INFO_HAS_WALL_CLOCK   0x01000000      /* has audio wall clock for audio/system time sync */
 #define SNDRV_PCM_INFO_FIFO_IN_FRAMES	0x80000000	/* internal kernel flag - FIFO size is in frames */
 
 typedef int __bitwise snd_pcm_state_t;
@@ -406,7 +407,8 @@ struct snd_pcm_status {
 	snd_pcm_uframes_t avail_max;	/* max frames available on hw since last status */
 	snd_pcm_uframes_t overrange;	/* count of ADC (capture) overrange detections from last status */
 	snd_pcm_state_t suspended_state; /* suspended stream state */
-	unsigned char reserved[60];	/* must be filled with zero */
+	struct timespec audio_tstamp;	/* from sample counter or wall clock */
+	unsigned char reserved[60-sizeof(struct timespec)]; /* must be filled with zero */
 };
 
 struct snd_pcm_mmap_status {
@@ -415,6 +417,7 @@ struct snd_pcm_mmap_status {
 	snd_pcm_uframes_t hw_ptr;	/* RO: hw ptr (0...boundary-1) */
 	struct timespec tstamp;		/* Timestamp */
 	snd_pcm_state_t suspended_state; /* RO: suspended stream state */
+	struct timespec audio_tstamp;	/* from sample counter or wall clock */
 };
 
 struct snd_pcm_mmap_control {
diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c
index 91cdf9435fec..af2a3fdb8828 100644
--- a/sound/core/pcm_compat.c
+++ b/sound/core/pcm_compat.c
@@ -190,7 +190,8 @@ struct snd_pcm_status32 {
 	u32 avail_max;
 	u32 overrange;
 	s32 suspended_state;
-	unsigned char reserved[60];
+	struct compat_timespec audio_tstamp;
+	unsigned char reserved[60-sizeof(struct compat_timespec)];
 } __attribute__((packed));
 
 
@@ -205,17 +206,16 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream,
 		return err;
 
 	if (put_user(status.state, &src->state) ||
-	    put_user(status.trigger_tstamp.tv_sec, &src->trigger_tstamp.tv_sec) ||
-	    put_user(status.trigger_tstamp.tv_nsec, &src->trigger_tstamp.tv_nsec) ||
-	    put_user(status.tstamp.tv_sec, &src->tstamp.tv_sec) ||
-	    put_user(status.tstamp.tv_nsec, &src->tstamp.tv_nsec) ||
+	    compat_put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) ||
+	    compat_put_timespec(&status.tstamp, &src->tstamp) ||
 	    put_user(status.appl_ptr, &src->appl_ptr) ||
 	    put_user(status.hw_ptr, &src->hw_ptr) ||
 	    put_user(status.delay, &src->delay) ||
 	    put_user(status.avail, &src->avail) ||
 	    put_user(status.avail_max, &src->avail_max) ||
 	    put_user(status.overrange, &src->overrange) ||
-	    put_user(status.suspended_state, &src->suspended_state))
+	    put_user(status.suspended_state, &src->suspended_state) ||
+	    compat_put_timespec(&status.audio_tstamp, &src->audio_tstamp))
 		return -EFAULT;
 
 	return err;
@@ -364,6 +364,7 @@ struct snd_pcm_mmap_status32 {
 	u32 hw_ptr;
 	struct compat_timespec tstamp;
 	s32 suspended_state;
+	struct compat_timespec audio_tstamp;
 } __attribute__((packed));
 
 struct snd_pcm_mmap_control32 {
@@ -426,12 +427,14 @@ static int snd_pcm_ioctl_sync_ptr_compat(struct snd_pcm_substream *substream,
 	sstatus.hw_ptr = status->hw_ptr % boundary;
 	sstatus.tstamp = status->tstamp;
 	sstatus.suspended_state = status->suspended_state;
+	sstatus.audio_tstamp = status->audio_tstamp;
 	snd_pcm_stream_unlock_irq(substream);
 	if (put_user(sstatus.state, &src->s.status.state) ||
 	    put_user(sstatus.hw_ptr, &src->s.status.hw_ptr) ||
-	    put_user(sstatus.tstamp.tv_sec, &src->s.status.tstamp.tv_sec) ||
-	    put_user(sstatus.tstamp.tv_nsec, &src->s.status.tstamp.tv_nsec) ||
+	    compat_put_timespec(&sstatus.tstamp, &src->s.status.tstamp) ||
 	    put_user(sstatus.suspended_state, &src->s.status.suspended_state) ||
+	    compat_put_timespec(&sstatus.audio_tstamp,
+		    &src->s.status.audio_tstamp) ||
 	    put_user(scontrol.appl_ptr, &src->c.control.appl_ptr) ||
 	    put_user(scontrol.avail_min, &src->c.control.avail_min))
 		return -EFAULT;
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 3dc029e106a2..c4840ff75d00 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -316,6 +316,7 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 	unsigned long jdelta;
 	unsigned long curr_jiffies;
 	struct timespec curr_tstamp;
+	struct timespec audio_tstamp;
 	int crossed_boundary = 0;
 
 	old_hw_ptr = runtime->status->hw_ptr;
@@ -328,9 +329,14 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 	 */
 	pos = substream->ops->pointer(substream);
 	curr_jiffies = jiffies;
-	if (runtime->tstamp_mode == SNDRV_PCM_TSTAMP_ENABLE)
+	if (runtime->tstamp_mode == SNDRV_PCM_TSTAMP_ENABLE) {
 		snd_pcm_gettime(runtime, (struct timespec *)&curr_tstamp);
 
+		if ((runtime->hw.info & SNDRV_PCM_INFO_HAS_WALL_CLOCK) &&
+			(substream->ops->wall_clock))
+			substream->ops->wall_clock(substream, &audio_tstamp);
+	}
+
 	if (pos == SNDRV_PCM_POS_XRUN) {
 		xrun(substream);
 		return -EPIPE;
@@ -520,9 +526,31 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 		snd_BUG_ON(crossed_boundary != 1);
 		runtime->hw_ptr_wrap += runtime->boundary;
 	}
-	if (runtime->tstamp_mode == SNDRV_PCM_TSTAMP_ENABLE)
+	if (runtime->tstamp_mode == SNDRV_PCM_TSTAMP_ENABLE) {
 		runtime->status->tstamp = curr_tstamp;
 
+		if (!(runtime->hw.info & SNDRV_PCM_INFO_HAS_WALL_CLOCK)) {
+			/*
+			 * no wall clock available, provide audio timestamp
+			 * derived from pointer position+delay
+			 */
+			u64 audio_frames, audio_nsecs;
+
+			if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+				audio_frames = runtime->hw_ptr_wrap
+					+ runtime->status->hw_ptr
+					- runtime->delay;
+			else
+				audio_frames = runtime->hw_ptr_wrap
+					+ runtime->status->hw_ptr
+					+ runtime->delay;
+			audio_nsecs = div_u64(audio_frames * 1000000000LL,
+					runtime->rate);
+			audio_tstamp = ns_to_timespec(audio_nsecs);
+		}
+		runtime->status->audio_tstamp = audio_tstamp;
+	}
+
 	return snd_pcm_update_state(substream, runtime);
 }
 
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 5e12e5bacbba..7c800012fff9 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -594,6 +594,8 @@ int snd_pcm_status(struct snd_pcm_substream *substream,
 		snd_pcm_update_hw_ptr(substream);
 		if (runtime->tstamp_mode == SNDRV_PCM_TSTAMP_ENABLE) {
 			status->tstamp = runtime->status->tstamp;
+			status->audio_tstamp =
+				runtime->status->audio_tstamp;
 			goto _tstamp_end;
 		}
 	}
-- 
cgit v1.2.3-55-g7522


From 5d0d04e477c44993f995f35b728ce9dd57a4615e Mon Sep 17 00:00:00 2001
From: Assaf Krauss
Date: Wed, 1 Aug 2012 15:12:48 +0300
Subject: mac80211: expose AES-CMAC subkey calculation

Expose a function for the AES-CMAC subkey calculation
to drivers. This is the first step of the AES-CMAC
cipher key setup and may be required for CMAC hardware
offloading.

Signed-off-by: Assaf Krauss <assaf.krauss@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h  | 13 +++++++++++++
 net/mac80211/aes_cmac.c | 17 +++++++++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 71c2f9c2f5be..00b7204708bd 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3222,6 +3222,19 @@ void ieee80211_get_tkip_rx_p1k(struct ieee80211_key_conf *keyconf,
 void ieee80211_get_tkip_p2k(struct ieee80211_key_conf *keyconf,
 			    struct sk_buff *skb, u8 *p2k);
 
+/**
+ * ieee80211_aes_cmac_calculate_k1_k2 - calculate the AES-CMAC sub keys
+ *
+ * This function computes the two AES-CMAC sub-keys, based on the
+ * previously installed master key.
+ *
+ * @keyconf: the parameter passed with the set key
+ * @k1: a buffer to be filled with the 1st sub-key
+ * @k2: a buffer to be filled with the 2nd sub-key
+ */
+void ieee80211_aes_cmac_calculate_k1_k2(struct ieee80211_key_conf *keyconf,
+					u8 *k1, u8 *k2);
+
 /**
  * struct ieee80211_key_seq - key sequence counter
  *
diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c
index a04752e91023..493353534a0f 100644
--- a/net/mac80211/aes_cmac.c
+++ b/net/mac80211/aes_cmac.c
@@ -126,3 +126,20 @@ void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm)
 {
 	crypto_free_cipher(tfm);
 }
+
+void ieee80211_aes_cmac_calculate_k1_k2(struct ieee80211_key_conf *keyconf,
+					u8 *k1, u8 *k2)
+{
+	u8 l[AES_BLOCK_SIZE] = {};
+	struct ieee80211_key *key =
+		container_of(keyconf, struct ieee80211_key, conf);
+
+	crypto_cipher_encrypt_one(key->u.aes_cmac.tfm, l, l);
+
+	memcpy(k1, l, AES_BLOCK_SIZE);
+	gf_mulx(k1);
+
+	memcpy(k2, k1, AES_BLOCK_SIZE);
+	gf_mulx(k2);
+}
+EXPORT_SYMBOL(ieee80211_aes_cmac_calculate_k1_k2);
-- 
cgit v1.2.3-55-g7522


From e4e541a84863b6a41f2427f59cc9156c644491a8 Mon Sep 17 00:00:00 2001
From: Pavel Emelyanov
Date: Tue, 23 Oct 2012 22:29:56 +0400
Subject: sock-diag: Report shutdown for inet and unix sockets (v2)

Make it simple -- just put new nlattr with just sk->sk_shutdown bits.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/inet_diag.h | 3 ++-
 include/uapi/linux/unix_diag.h | 1 +
 net/ipv4/inet_diag.c           | 3 +++
 net/unix/diag.c                | 3 +++
 4 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index 8c469af939aa..bbde90fa5838 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -109,9 +109,10 @@ enum {
 	INET_DIAG_TOS,
 	INET_DIAG_TCLASS,
 	INET_DIAG_SKMEMINFO,
+	INET_DIAG_SHUTDOWN,
 };
 
-#define INET_DIAG_MAX INET_DIAG_SKMEMINFO
+#define INET_DIAG_MAX INET_DIAG_SHUTDOWN
 
 
 /* INET_DIAG_MEM */
diff --git a/include/uapi/linux/unix_diag.h b/include/uapi/linux/unix_diag.h
index b1d2bf16b33c..b8a24941db21 100644
--- a/include/uapi/linux/unix_diag.h
+++ b/include/uapi/linux/unix_diag.h
@@ -37,6 +37,7 @@ enum {
 	UNIX_DIAG_ICONS,
 	UNIX_DIAG_RQLEN,
 	UNIX_DIAG_MEMINFO,
+	UNIX_DIAG_SHUTDOWN,
 
 	UNIX_DIAG_MAX,
 };
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 535584c00f91..e5bad82d3584 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -105,6 +105,9 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 	r->id.idiag_src[0] = inet->inet_rcv_saddr;
 	r->id.idiag_dst[0] = inet->inet_daddr;
 
+	if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
+		goto errout;
+
 	/* IPv6 dual-stack sockets use inet->tos for IPv4 connections,
 	 * hence this needs to be included regardless of socket family.
 	 */
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 06748f108a57..5ac19dc1d5e4 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -151,6 +151,9 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
 	    sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO))
 		goto out_nlmsg_trim;
 
+	if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown))
+		goto out_nlmsg_trim;
+
 	return nlmsg_end(skb, nlh);
 
 out_nlmsg_trim:
-- 
cgit v1.2.3-55-g7522


From 4d9a5d4319e22670ec6d6227e12b54f361c46d0f Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Thu, 11 Oct 2012 01:47:16 +0200
Subject: rcu: Remove rcu_switch()

It's only there to call rcu_user_hooks_switch(). Let's
just call rcu_user_hooks_switch() directly, we don't need this
function in the middle.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Richard Weinberger <richard@nod.at>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 arch/um/drivers/mconsole_kern.c | 2 +-
 include/linux/rcupdate.h        | 2 ++
 include/linux/sched.h           | 8 --------
 kernel/sched/core.c             | 2 +-
 4 files changed, 4 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 79ccfe6c7078..49e3b49e552f 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -648,7 +648,7 @@ static void stack_proc(void *arg)
 	struct task_struct *from = current, *to = arg;
 
 	to->thread.saved_task = from;
-	rcu_switch(from, to);
+	rcu_user_hooks_switch(from, to);
 	switch_to(from, to, from);
 }
 
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 7c968e4f929e..5d009def7c0c 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -204,6 +204,8 @@ static inline void rcu_user_enter(void) { }
 static inline void rcu_user_exit(void) { }
 static inline void rcu_user_enter_after_irq(void) { }
 static inline void rcu_user_exit_after_irq(void) { }
+static inline void rcu_user_hooks_switch(struct task_struct *prev,
+					 struct task_struct *next) { }
 #endif /* CONFIG_RCU_USER_QS */
 
 extern void exit_rcu(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a02df2e..432cc5e1bbee 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1844,14 +1844,6 @@ static inline void rcu_copy_process(struct task_struct *p)
 
 #endif
 
-static inline void rcu_switch(struct task_struct *prev,
-			      struct task_struct *next)
-{
-#ifdef CONFIG_RCU_USER_QS
-	rcu_user_hooks_switch(prev, next);
-#endif
-}
-
 static inline void tsk_restore_flags(struct task_struct *task,
 				unsigned long orig_flags, unsigned long flags)
 {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d8927fda712..68414fa4cd2a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1887,7 +1887,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 #endif
 
 	/* Here we just switch the register state and the stack. */
-	rcu_switch(prev, next);
+	rcu_user_hooks_switch(prev, next);
 	switch_to(prev, next, prev);
 
 	barrier();
-- 
cgit v1.2.3-55-g7522


From 4e87b2d7e887df3fe251dd7f702591a3acf369ca Mon Sep 17 00:00:00 2001
From: Lai Jiangshan
Date: Sat, 13 Oct 2012 01:14:14 +0800
Subject: srcu: Credit Lai Jiangshan with SRCU rewrite

Lai Jiangshan rewrote SRCU, so this commit ensures that he gets his
proper share of blame^Wcredit.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/srcu.h | 2 ++
 kernel/srcu.c        | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 55a5c52cbb25..a55ddb19053c 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -16,8 +16,10 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2006
+ * Copyright (C) Fujitsu, 2012
  *
  * Author: Paul McKenney <paulmck@us.ibm.com>
+ *	   Lai Jiangshan <laijs@cn.fujitsu.com>
  *
  * For detailed explanation of Read-Copy Update mechanism see -
  * 		Documentation/RCU/ *.txt
diff --git a/kernel/srcu.c b/kernel/srcu.c
index 97c465ebd844..0b99f27fa2f7 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -16,8 +16,10 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2006
+ * Copyright (C) Fujitsu, 2012
  *
  * Author: Paul McKenney <paulmck@us.ibm.com>
+ *	   Lai Jiangshan <laijs@cn.fujitsu.com>
  *
  * For detailed explanation of Read-Copy Update mechanism see -
  * 		Documentation/RCU/ *.txt
-- 
cgit v1.2.3-55-g7522


From f2ebfbc991044fd5b89d4529741d7500feb37fbd Mon Sep 17 00:00:00 2001
From: Lai Jiangshan
Date: Sat, 13 Oct 2012 01:14:15 +0800
Subject: srcu: Export process_srcu()

Because process_srcu() will be used in DEFINE_SRCU(), which is a macro
that could be expanded pretty much anywhere, it can no longer be static.
Note that process_srcu() is still internal to srcu.h.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/srcu.h | 2 ++
 kernel/srcu.c        | 6 ++----
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index a55ddb19053c..5cce128f196c 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -78,6 +78,8 @@ int init_srcu_struct(struct srcu_struct *sp);
 
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
+void process_srcu(struct work_struct *work);
+
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
  * @sp: srcu_struct in queue the callback
diff --git a/kernel/srcu.c b/kernel/srcu.c
index 0b99f27fa2f7..b363b0924561 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -94,9 +94,6 @@ static inline void rcu_batch_move(struct rcu_batch *to, struct rcu_batch *from)
 	}
 }
 
-/* single-thread state-machine */
-static void process_srcu(struct work_struct *work);
-
 static int init_srcu_struct_fields(struct srcu_struct *sp)
 {
 	sp->completed = 0;
@@ -639,7 +636,7 @@ static void srcu_reschedule(struct srcu_struct *sp)
 /*
  * This is the work-queue function that handles SRCU grace periods.
  */
-static void process_srcu(struct work_struct *work)
+void process_srcu(struct work_struct *work)
 {
 	struct srcu_struct *sp;
 
@@ -650,3 +647,4 @@ static void process_srcu(struct work_struct *work)
 	srcu_invoke_callbacks(sp);
 	srcu_reschedule(sp);
 }
+EXPORT_SYMBOL_GPL(process_srcu);
-- 
cgit v1.2.3-55-g7522


From b637a328bd4f43a0e146d1eef0142b650ba0d644 Mon Sep 17 00:00:00 2001
From: Paul E. McKenney
Date: Wed, 19 Sep 2012 16:58:38 -0700
Subject: rcu: Print remote CPU's stacks in stall warnings

The RCU CPU stall warnings rely on trigger_all_cpu_backtrace() to
do NMI-based dump of the stack traces of all CPUs.  Unfortunately, a
number of architectures do not implement trigger_all_cpu_backtrace(), in
which case RCU falls back to just dumping the stack of the running CPU.
This is unhelpful in the case where the running CPU has detected that
some other CPU has stalled.

This commit therefore makes the running CPU dump the stacks of the
tasks running on the stalled CPUs.

Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/sched.h |  2 ++
 kernel/rcutree.c      | 25 ++++++++++++++++++++++++-
 kernel/sched/core.c   |  6 ++++++
 3 files changed, 32 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a02df2e..ba69b5adea30 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -109,6 +109,8 @@ extern void update_cpu_load_nohz(void);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
+extern void dump_cpu_task(int cpu);
+
 struct seq_file;
 struct cfs_rq;
 struct task_group;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 74df86bd9204..e78538712df0 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -873,6 +873,29 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 	rsp->jiffies_stall = jiffies + jiffies_till_stall_check();
 }
 
+/*
+ * Dump stacks of all tasks running on stalled CPUs.  This is a fallback
+ * for architectures that do not implement trigger_all_cpu_backtrace().
+ * The NMI-triggered stack traces are more accurate because they are
+ * printed by the target CPU.
+ */
+static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
+{
+	int cpu;
+	unsigned long flags;
+	struct rcu_node *rnp;
+
+	rcu_for_each_leaf_node(rsp, rnp) {
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		if (rnp->qsmask != 0) {
+			for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
+				if (rnp->qsmask & (1UL << cpu))
+					dump_cpu_task(rnp->grplo + cpu);
+		}
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	}
+}
+
 static void print_other_cpu_stall(struct rcu_state *rsp)
 {
 	int cpu;
@@ -929,7 +952,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	if (ndetected == 0)
 		printk(KERN_ERR "INFO: Stall ended before state dump start\n");
 	else if (!trigger_all_cpu_backtrace())
-		dump_stack();
+		rcu_dump_cpu_stacks(rsp);
 
 	/* Complain about tasks blocking the grace period. */
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d8927fda712..59d08fb1a9e3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8076,3 +8076,9 @@ struct cgroup_subsys cpuacct_subsys = {
 	.base_cftypes = files,
 };
 #endif	/* CONFIG_CGROUP_CPUACCT */
+
+void dump_cpu_task(int cpu)
+{
+	pr_info("Task dump for CPU %d:\n", cpu);
+	sched_show_task(cpu_curr(cpu));
+}
-- 
cgit v1.2.3-55-g7522


From e39473d0b9448e770f49b0b15e514be884264438 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Wed, 24 Oct 2012 02:08:18 +0200
Subject: PM / QoS: Make it possible to expose PM QoS device flags to user
 space

Define two device PM QoS flags, PM_QOS_FLAG_NO_POWER_OFF
and PM_QOS_FLAG_REMOTE_WAKEUP, and introduce routines
dev_pm_qos_expose_flags() and dev_pm_qos_hide_flags() allowing the
caller to expose those two flags to user space or to hide them
from it, respectively.

After the flags have been exposed, user space will see two
additional sysfs attributes, pm_qos_no_power_off and
pm_qos_remote_wakeup, under the device's /sys/devices/.../power/
directory.  Then, writing 1 to one of them will update the
PM QoS flags request owned by user space so that the corresponding
flag is requested to be set.  In turn, writing 0 to one of them
will cause the corresponding flag in the user space's request to
be cleared (however, the owners of the other PM QoS flags requests
for the same device may still request the flag to be set and it
may be effectively set even if user space doesn't request that).

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Jean Pihet <j-pihet@ti.com>
Acked-by: mark gross <markgross@thegnar.org>
---
 Documentation/ABI/testing/sysfs-devices-power |  31 +++++
 drivers/base/power/power.h                    |   6 +-
 drivers/base/power/qos.c                      | 168 ++++++++++++++++++++------
 drivers/base/power/sysfs.c                    |  94 ++++++++++++--
 include/linux/pm.h                            |   1 -
 include/linux/pm_qos.h                        |  26 ++++
 6 files changed, 278 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
index 45000f0db4d4..7fc2997b23a6 100644
--- a/Documentation/ABI/testing/sysfs-devices-power
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -204,3 +204,34 @@ Description:
 
 		This attribute has no effect on system-wide suspend/resume and
 		hibernation.
+
+What:		/sys/devices/.../power/pm_qos_no_power_off
+Date:		September 2012
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../power/pm_qos_no_power_off attribute
+		is used for manipulating the PM QoS "no power off" flag.  If
+		set, this flag indicates to the kernel that power should not
+		be removed entirely from the device.
+
+		Not all drivers support this attribute.  If it isn't supported,
+		it is not present.
+
+		This attribute has no effect on system-wide suspend/resume and
+		hibernation.
+
+What:		/sys/devices/.../power/pm_qos_remote_wakeup
+Date:		September 2012
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../power/pm_qos_remote_wakeup attribute
+		is used for manipulating the PM QoS "remote wakeup required"
+		flag.  If set, this flag indicates to the kernel that the
+		device is a source of user events that have to be signaled from
+		its low-power states.
+
+		Not all drivers support this attribute.  If it isn't supported,
+		it is not present.
+
+		This attribute has no effect on system-wide suspend/resume and
+		hibernation.
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 0dbfdf4419af..b16686a0a5a2 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -93,8 +93,10 @@ extern void dpm_sysfs_remove(struct device *dev);
 extern void rpm_sysfs_remove(struct device *dev);
 extern int wakeup_sysfs_add(struct device *dev);
 extern void wakeup_sysfs_remove(struct device *dev);
-extern int pm_qos_sysfs_add(struct device *dev);
-extern void pm_qos_sysfs_remove(struct device *dev);
+extern int pm_qos_sysfs_add_latency(struct device *dev);
+extern void pm_qos_sysfs_remove_latency(struct device *dev);
+extern int pm_qos_sysfs_add_flags(struct device *dev);
+extern void pm_qos_sysfs_remove_flags(struct device *dev);
 
 #else /* CONFIG_PM */
 
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 3c66f75d14b0..167834dcc82a 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -40,6 +40,7 @@
 #include <linux/device.h>
 #include <linux/mutex.h>
 #include <linux/export.h>
+#include <linux/pm_runtime.h>
 
 #include "power.h"
 
@@ -321,6 +322,37 @@ int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
 }
 EXPORT_SYMBOL_GPL(dev_pm_qos_add_request);
 
+/**
+ * __dev_pm_qos_update_request - Modify an existing device PM QoS request.
+ * @req : PM QoS request to modify.
+ * @new_value: New value to request.
+ */
+static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req,
+				       s32 new_value)
+{
+	s32 curr_value;
+	int ret = 0;
+
+	if (!req->dev->power.qos)
+		return -ENODEV;
+
+	switch(req->type) {
+	case DEV_PM_QOS_LATENCY:
+		curr_value = req->data.pnode.prio;
+		break;
+	case DEV_PM_QOS_FLAGS:
+		curr_value = req->data.flr.flags;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (curr_value != new_value)
+		ret = apply_constraint(req, PM_QOS_UPDATE_REQ, new_value);
+
+	return ret;
+}
+
 /**
  * dev_pm_qos_update_request - modifies an existing qos request
  * @req : handle to list element holding a dev_pm_qos request to use
@@ -336,11 +368,9 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_add_request);
  * -EINVAL in case of wrong parameters, -ENODEV if the device has been
  * removed from the system
  */
-int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
-			      s32 new_value)
+int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value)
 {
-	s32 curr_value;
-	int ret = 0;
+	int ret;
 
 	if (!req) /*guard against callers passing in null */
 		return -EINVAL;
@@ -350,29 +380,9 @@ int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 		return -EINVAL;
 
 	mutex_lock(&dev_pm_qos_mtx);
-
-	if (!req->dev->power.qos) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	switch(req->type) {
-	case DEV_PM_QOS_LATENCY:
-		curr_value = req->data.pnode.prio;
-		break;
-	case DEV_PM_QOS_FLAGS:
-		curr_value = req->data.flr.flags;
-		break;
-	default:
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (curr_value != new_value)
-		ret = apply_constraint(req, PM_QOS_UPDATE_REQ, new_value);
-
- out:
+	__dev_pm_qos_update_request(req, new_value);
 	mutex_unlock(&dev_pm_qos_mtx);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_qos_update_request);
@@ -533,10 +543,19 @@ int dev_pm_qos_add_ancestor_request(struct device *dev,
 EXPORT_SYMBOL_GPL(dev_pm_qos_add_ancestor_request);
 
 #ifdef CONFIG_PM_RUNTIME
-static void __dev_pm_qos_drop_user_request(struct device *dev)
+static void __dev_pm_qos_drop_user_request(struct device *dev,
+					   enum dev_pm_qos_req_type type)
 {
-	dev_pm_qos_remove_request(dev->power.pq_req);
-	dev->power.pq_req = NULL;
+	switch(type) {
+	case DEV_PM_QOS_LATENCY:
+		dev_pm_qos_remove_request(dev->power.qos->latency_req);
+		dev->power.qos->latency_req = NULL;
+		break;
+	case DEV_PM_QOS_FLAGS:
+		dev_pm_qos_remove_request(dev->power.qos->flags_req);
+		dev->power.qos->flags_req = NULL;
+		break;
+	}
 }
 
 /**
@@ -552,7 +571,7 @@ int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
 	if (!device_is_registered(dev) || value < 0)
 		return -EINVAL;
 
-	if (dev->power.pq_req)
+	if (dev->power.qos && dev->power.qos->latency_req)
 		return -EEXIST;
 
 	req = kzalloc(sizeof(*req), GFP_KERNEL);
@@ -563,10 +582,10 @@ int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
 	if (ret < 0)
 		return ret;
 
-	dev->power.pq_req = req;
-	ret = pm_qos_sysfs_add(dev);
+	dev->power.qos->latency_req = req;
+	ret = pm_qos_sysfs_add_latency(dev);
 	if (ret)
-		__dev_pm_qos_drop_user_request(dev);
+		__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY);
 
 	return ret;
 }
@@ -578,10 +597,87 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_limit);
  */
 void dev_pm_qos_hide_latency_limit(struct device *dev)
 {
-	if (dev->power.pq_req) {
-		pm_qos_sysfs_remove(dev);
-		__dev_pm_qos_drop_user_request(dev);
+	if (dev->power.qos && dev->power.qos->latency_req) {
+		pm_qos_sysfs_remove_latency(dev);
+		__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY);
 	}
 }
 EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_limit);
+
+/**
+ * dev_pm_qos_expose_flags - Expose PM QoS flags of a device to user space.
+ * @dev: Device whose PM QoS flags are to be exposed to user space.
+ * @val: Initial values of the flags.
+ */
+int dev_pm_qos_expose_flags(struct device *dev, s32 val)
+{
+	struct dev_pm_qos_request *req;
+	int ret;
+
+	if (!device_is_registered(dev))
+		return -EINVAL;
+
+	if (dev->power.qos && dev->power.qos->flags_req)
+		return -EEXIST;
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_FLAGS, val);
+	if (ret < 0)
+		return ret;
+
+	dev->power.qos->flags_req = req;
+	ret = pm_qos_sysfs_add_flags(dev);
+	if (ret)
+		__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_expose_flags);
+
+/**
+ * dev_pm_qos_hide_flags - Hide PM QoS flags of a device from user space.
+ * @dev: Device whose PM QoS flags are to be hidden from user space.
+ */
+void dev_pm_qos_hide_flags(struct device *dev)
+{
+	if (dev->power.qos && dev->power.qos->flags_req) {
+		pm_qos_sysfs_remove_flags(dev);
+		__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS);
+	}
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_hide_flags);
+
+/**
+ * dev_pm_qos_update_flags - Update PM QoS flags request owned by user space.
+ * @dev: Device to update the PM QoS flags request for.
+ * @mask: Flags to set/clear.
+ * @set: Whether to set or clear the flags (true means set).
+ */
+int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set)
+{
+	s32 value;
+	int ret;
+
+	if (!dev->power.qos || !dev->power.qos->flags_req)
+		return -EINVAL;
+
+	pm_runtime_get_sync(dev);
+	mutex_lock(&dev_pm_qos_mtx);
+
+	value = dev_pm_qos_requested_flags(dev);
+	if (set)
+		value |= mask;
+	else
+		value &= ~mask;
+
+	ret = __dev_pm_qos_update_request(dev->power.qos->flags_req, value);
+
+	mutex_unlock(&dev_pm_qos_mtx);
+	pm_runtime_put(dev);
+
+	return ret;
+}
 #endif /* CONFIG_PM_RUNTIME */
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 54c61ffa2044..50d16e3cb0a9 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -221,7 +221,7 @@ static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
 static ssize_t pm_qos_latency_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", dev->power.pq_req->data.pnode.prio);
+	return sprintf(buf, "%d\n", dev_pm_qos_requested_latency(dev));
 }
 
 static ssize_t pm_qos_latency_store(struct device *dev,
@@ -237,12 +237,66 @@ static ssize_t pm_qos_latency_store(struct device *dev,
 	if (value < 0)
 		return -EINVAL;
 
-	ret = dev_pm_qos_update_request(dev->power.pq_req, value);
+	ret = dev_pm_qos_update_request(dev->power.qos->latency_req, value);
 	return ret < 0 ? ret : n;
 }
 
 static DEVICE_ATTR(pm_qos_resume_latency_us, 0644,
 		   pm_qos_latency_show, pm_qos_latency_store);
+
+static ssize_t pm_qos_no_power_off_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return sprintf(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev)
+					& PM_QOS_FLAG_NO_POWER_OFF));
+}
+
+static ssize_t pm_qos_no_power_off_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t n)
+{
+	int ret;
+
+	if (kstrtoint(buf, 0, &ret))
+		return -EINVAL;
+
+	if (ret != 0 && ret != 1)
+		return -EINVAL;
+
+	ret = dev_pm_qos_update_flags(dev, PM_QOS_FLAG_NO_POWER_OFF, ret);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_no_power_off, 0644,
+		   pm_qos_no_power_off_show, pm_qos_no_power_off_store);
+
+static ssize_t pm_qos_remote_wakeup_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	return sprintf(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev)
+					& PM_QOS_FLAG_REMOTE_WAKEUP));
+}
+
+static ssize_t pm_qos_remote_wakeup_store(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *buf, size_t n)
+{
+	int ret;
+
+	if (kstrtoint(buf, 0, &ret))
+		return -EINVAL;
+
+	if (ret != 0 && ret != 1)
+		return -EINVAL;
+
+	ret = dev_pm_qos_update_flags(dev, PM_QOS_FLAG_REMOTE_WAKEUP, ret);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_remote_wakeup, 0644,
+		   pm_qos_remote_wakeup_show, pm_qos_remote_wakeup_store);
 #endif /* CONFIG_PM_RUNTIME */
 
 #ifdef CONFIG_PM_SLEEP
@@ -564,15 +618,27 @@ static struct attribute_group pm_runtime_attr_group = {
 	.attrs	= runtime_attrs,
 };
 
-static struct attribute *pm_qos_attrs[] = {
+static struct attribute *pm_qos_latency_attrs[] = {
 #ifdef CONFIG_PM_RUNTIME
 	&dev_attr_pm_qos_resume_latency_us.attr,
 #endif /* CONFIG_PM_RUNTIME */
 	NULL,
 };
-static struct attribute_group pm_qos_attr_group = {
+static struct attribute_group pm_qos_latency_attr_group = {
 	.name	= power_group_name,
-	.attrs	= pm_qos_attrs,
+	.attrs	= pm_qos_latency_attrs,
+};
+
+static struct attribute *pm_qos_flags_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_pm_qos_no_power_off.attr,
+	&dev_attr_pm_qos_remote_wakeup.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	NULL,
+};
+static struct attribute_group pm_qos_flags_attr_group = {
+	.name	= power_group_name,
+	.attrs	= pm_qos_flags_attrs,
 };
 
 int dpm_sysfs_add(struct device *dev)
@@ -615,14 +681,24 @@ void wakeup_sysfs_remove(struct device *dev)
 	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
 }
 
-int pm_qos_sysfs_add(struct device *dev)
+int pm_qos_sysfs_add_latency(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj, &pm_qos_latency_attr_group);
+}
+
+void pm_qos_sysfs_remove_latency(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_attr_group);
+}
+
+int pm_qos_sysfs_add_flags(struct device *dev)
 {
-	return sysfs_merge_group(&dev->kobj, &pm_qos_attr_group);
+	return sysfs_merge_group(&dev->kobj, &pm_qos_flags_attr_group);
 }
 
-void pm_qos_sysfs_remove(struct device *dev)
+void pm_qos_sysfs_remove_flags(struct device *dev)
 {
-	sysfs_unmerge_group(&dev->kobj, &pm_qos_attr_group);
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_flags_attr_group);
 }
 
 void rpm_sysfs_remove(struct device *dev)
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 0ce6df94221a..03d7bb145311 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -546,7 +546,6 @@ struct dev_pm_info {
 	unsigned long		active_jiffies;
 	unsigned long		suspended_jiffies;
 	unsigned long		accounting_timestamp;
-	struct dev_pm_qos_request *pq_req;
 #endif
 	struct pm_subsys_data	*subsys_data;  /* Owned by the subsystem. */
 	struct dev_pm_qos	*qos;
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 3af7d8573c23..5a95013905c8 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -34,6 +34,9 @@ enum pm_qos_flags_status {
 #define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE	0
 #define PM_QOS_DEV_LAT_DEFAULT_VALUE		0
 
+#define PM_QOS_FLAG_NO_POWER_OFF	(1 << 0)
+#define PM_QOS_FLAG_REMOTE_WAKEUP	(1 << 1)
+
 struct pm_qos_request {
 	struct plist_node node;
 	int pm_qos_class;
@@ -86,6 +89,8 @@ struct pm_qos_flags {
 struct dev_pm_qos {
 	struct pm_qos_constraints latency;
 	struct pm_qos_flags flags;
+	struct dev_pm_qos_request *latency_req;
+	struct dev_pm_qos_request *flags_req;
 };
 
 /* Action requested to pm_qos_update_target */
@@ -187,10 +192,31 @@ static inline int dev_pm_qos_add_ancestor_request(struct device *dev,
 #ifdef CONFIG_PM_RUNTIME
 int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value);
 void dev_pm_qos_hide_latency_limit(struct device *dev);
+int dev_pm_qos_expose_flags(struct device *dev, s32 value);
+void dev_pm_qos_hide_flags(struct device *dev);
+int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set);
+
+static inline s32 dev_pm_qos_requested_latency(struct device *dev)
+{
+	return dev->power.qos->latency_req->data.pnode.prio;
+}
+
+static inline s32 dev_pm_qos_requested_flags(struct device *dev)
+{
+	return dev->power.qos->flags_req->data.flr.flags;
+}
 #else
 static inline int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
 			{ return 0; }
 static inline void dev_pm_qos_hide_latency_limit(struct device *dev) {}
+static inline int dev_pm_qos_expose_flags(struct device *dev, s32 value)
+			{ return 0; }
+static inline void dev_pm_qos_hide_flags(struct device *dev) {}
+static inline int dev_pm_qos_update_flags(struct device *dev, s32 m, bool set)
+			{ return 0; }
+
+static inline s32 dev_pm_qos_requested_latency(struct device *dev) { return 0; }
+static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; }
 #endif
 
 #endif
-- 
cgit v1.2.3-55-g7522


From 08333283a7347c33589f31c9b1d1b7a4f3c3f7a3 Mon Sep 17 00:00:00 2001
From: Mat Martineau
Date: Tue, 23 Oct 2012 15:24:06 -0700
Subject: Bluetooth: Add new l2cap_chan struct members for high speed channels

An L2CAP channel using high speed continues to be associated with a
BR/EDR l2cap_conn, while also tracking an additional hci_conn
(representing a physical link on a high speed controller) and hci_chan
(representing a logical link).  There may only be one physical link
between two high speed controllers.  Each physical link may contain
several logical links, with each logical link representing a channel
with specific quality of service.

During a channel move, the destination channel id, current move state,
and role (initiator vs. responder) are tracked and used by the channel
move state machine.  The ident value associated with a move request
must also be stored in order to use it in later move responses.

The active channel is stored in local_amp_id.

Signed-off-by: Mat Martineau <mathewm@codeaurora.org>
Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h | 29 +++++++++++++++++++++++++++++
 net/bluetooth/l2cap_core.c    |  5 +++++
 2 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 6e23afdf65c1..6d3615eed97c 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -434,6 +434,8 @@ struct l2cap_chan {
 	struct sock *sk;
 
 	struct l2cap_conn	*conn;
+	struct hci_conn		*hs_hcon;
+	struct hci_chan		*hs_hchan;
 	struct kref	kref;
 
 	__u8		state;
@@ -477,6 +479,11 @@ struct l2cap_chan {
 	unsigned long	conn_state;
 	unsigned long	flags;
 
+	__u8		local_amp_id;
+	__u8		move_id;
+	__u8		move_state;
+	__u8		move_role;
+
 	__u16		next_tx_seq;
 	__u16		expected_ack_seq;
 	__u16		expected_tx_seq;
@@ -644,6 +651,9 @@ enum {
 enum {
 	L2CAP_RX_STATE_RECV,
 	L2CAP_RX_STATE_SREJ_SENT,
+	L2CAP_RX_STATE_MOVE,
+	L2CAP_RX_STATE_WAIT_P,
+	L2CAP_RX_STATE_WAIT_F,
 };
 
 enum {
@@ -674,6 +684,25 @@ enum {
 	L2CAP_EV_RECV_FRAME,
 };
 
+enum {
+	L2CAP_MOVE_ROLE_NONE,
+	L2CAP_MOVE_ROLE_INITIATOR,
+	L2CAP_MOVE_ROLE_RESPONDER,
+};
+
+enum {
+	L2CAP_MOVE_STABLE,
+	L2CAP_MOVE_WAIT_REQ,
+	L2CAP_MOVE_WAIT_RSP,
+	L2CAP_MOVE_WAIT_RSP_SUCCESS,
+	L2CAP_MOVE_WAIT_CONFIRM,
+	L2CAP_MOVE_WAIT_CONFIRM_RSP,
+	L2CAP_MOVE_WAIT_LOGICAL_COMP,
+	L2CAP_MOVE_WAIT_LOGICAL_CFM,
+	L2CAP_MOVE_WAIT_LOCAL_BUSY,
+	L2CAP_MOVE_WAIT_PREPARE,
+};
+
 void l2cap_chan_hold(struct l2cap_chan *c);
 void l2cap_chan_put(struct l2cap_chan *c);
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 08efc256c931..c1b169f3ae0d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2788,6 +2788,11 @@ int l2cap_ertm_init(struct l2cap_chan *chan)
 
 	skb_queue_head_init(&chan->tx_q);
 
+	chan->local_amp_id = 0;
+	chan->move_id = 0;
+	chan->move_state = L2CAP_MOVE_STABLE;
+	chan->move_role = L2CAP_MOVE_ROLE_NONE;
+
 	if (chan->mode != L2CAP_MODE_ERTM)
 		return 0;
 
-- 
cgit v1.2.3-55-g7522


From 168df8e57e7c1afce3f86a86ae106f82ff7c18d8 Mon Sep 17 00:00:00 2001
From: Mat Martineau
Date: Tue, 23 Oct 2012 15:24:13 -0700
Subject: Bluetooth: Add state to hci_chan

On an AMP controller, hci_chan maps to a logical link.  When a channel
is being moved, the logical link may or may not be connected already.
The hci_chan->state is used to determine the existance of a useable
logical link so the link can be either used or requested.

Signed-off-by: Mat Martineau <mathewm@codeaurora.org>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Acked-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 1 +
 net/bluetooth/hci_conn.c         | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 9fe8e2dec870..00abc5246cbf 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -355,6 +355,7 @@ struct hci_chan {
 	struct hci_conn *conn;
 	struct sk_buff_head data_q;
 	unsigned int	sent;
+	__u8		state;
 };
 
 extern struct list_head hci_dev_list;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index fe646211c61f..6dcf4523df3c 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -959,6 +959,7 @@ struct hci_chan *hci_chan_create(struct hci_conn *conn)
 
 	chan->conn = conn;
 	skb_queue_head_init(&chan->data_q);
+	chan->state = BT_CONNECTED;
 
 	list_add_rcu(&chan->list, &conn->chan_list);
 
-- 
cgit v1.2.3-55-g7522


From 5b155ef960202b20a5cae43b9e675f4326e2375c Mon Sep 17 00:00:00 2001
From: Mat Martineau
Date: Tue, 23 Oct 2012 15:24:14 -0700
Subject: Bluetooth: Move channel response

The move response command includes a result code indicating
"pending", "success", or "failure" status.  A pending result is
received when the remote address is still setting up a physical link,
and will be followed by success or failure.  On success, logical link
setup will proceed.  On failure, the move is stopped.  The receiver of
a move channel response must always follow up by sending a move
channel confirm command.

Signed-off-by: Mat Martineau <mathewm@codeaurora.org>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h |   2 +
 net/bluetooth/l2cap_core.c    | 183 ++++++++++++++++++++++++++++++++++++++----
 2 files changed, 170 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 6d3615eed97c..b4c3c65c1f58 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -52,6 +52,8 @@
 #define L2CAP_ENC_TIMEOUT		msecs_to_jiffies(5000)
 #define L2CAP_CONN_TIMEOUT		msecs_to_jiffies(40000)
 #define L2CAP_INFO_TIMEOUT		msecs_to_jiffies(4000)
+#define L2CAP_MOVE_TIMEOUT		msecs_to_jiffies(4000)
+#define L2CAP_MOVE_ERTX_TIMEOUT		msecs_to_jiffies(60000)
 
 #define L2CAP_A2MP_DEFAULT_MTU		670
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index fef0394add18..2277ed504283 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -129,6 +129,20 @@ static struct l2cap_chan *__l2cap_get_chan_by_ident(struct l2cap_conn *conn,
 	return NULL;
 }
 
+static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn,
+						  u8 ident)
+{
+	struct l2cap_chan *c;
+
+	mutex_lock(&conn->chan_lock);
+	c = __l2cap_get_chan_by_ident(conn, ident);
+	if (c)
+		l2cap_chan_lock(c);
+	mutex_unlock(&conn->chan_lock);
+
+	return c;
+}
+
 static struct l2cap_chan *__l2cap_global_chan_by_addr(__le16 psm, bdaddr_t *src)
 {
 	struct l2cap_chan *c;
@@ -4185,23 +4199,34 @@ static void l2cap_send_move_chan_rsp(struct l2cap_conn *conn, u8 ident,
 	l2cap_send_cmd(conn, ident, L2CAP_MOVE_CHAN_RSP, sizeof(rsp), &rsp);
 }
 
-static void l2cap_send_move_chan_cfm(struct l2cap_conn *conn,
-				     struct l2cap_chan *chan,
-				     u16 icid, u16 result)
+static void l2cap_send_move_chan_cfm(struct l2cap_chan *chan, u16 result)
 {
 	struct l2cap_move_chan_cfm cfm;
-	u8 ident;
 
-	BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result);
+	BT_DBG("chan %p, result 0x%4.4x", chan, result);
 
-	ident = l2cap_get_ident(conn);
-	if (chan)
-		chan->ident = ident;
+	chan->ident = l2cap_get_ident(chan->conn);
 
-	cfm.icid = cpu_to_le16(icid);
+	cfm.icid = cpu_to_le16(chan->scid);
 	cfm.result = cpu_to_le16(result);
 
-	l2cap_send_cmd(conn, ident, L2CAP_MOVE_CHAN_CFM, sizeof(cfm), &cfm);
+	l2cap_send_cmd(chan->conn, chan->ident, L2CAP_MOVE_CHAN_CFM,
+		       sizeof(cfm), &cfm);
+
+	__set_chan_timer(chan, L2CAP_MOVE_TIMEOUT);
+}
+
+static void l2cap_send_move_chan_cfm_icid(struct l2cap_conn *conn, u16 icid)
+{
+	struct l2cap_move_chan_cfm cfm;
+
+	BT_DBG("conn %p, icid 0x%4.4x", conn, icid);
+
+	cfm.icid = cpu_to_le16(icid);
+	cfm.result = __constant_cpu_to_le16(L2CAP_MC_UNCONFIRMED);
+
+	l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_MOVE_CHAN_CFM,
+		       sizeof(cfm), &cfm);
 }
 
 static void l2cap_send_move_chan_cfm_rsp(struct l2cap_conn *conn, u8 ident,
@@ -4223,6 +4248,13 @@ static void __release_logical_link(struct l2cap_chan *chan)
 	/* Placeholder - release the logical link */
 }
 
+static void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
+			      u8 status)
+{
+	/* Placeholder */
+	return;
+}
+
 static inline int l2cap_move_channel_req(struct l2cap_conn *conn,
 					 struct l2cap_cmd_hdr *cmd,
 					 u16 cmd_len, void *data)
@@ -4317,9 +4349,128 @@ send_move_response:
 	return 0;
 }
 
-static inline int l2cap_move_channel_rsp(struct l2cap_conn *conn,
-					 struct l2cap_cmd_hdr *cmd,
-					 u16 cmd_len, void *data)
+static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result)
+{
+	struct l2cap_chan *chan;
+	struct hci_chan *hchan = NULL;
+
+	chan = l2cap_get_chan_by_scid(conn, icid);
+	if (!chan) {
+		l2cap_send_move_chan_cfm_icid(conn, icid);
+		return;
+	}
+
+	__clear_chan_timer(chan);
+	if (result == L2CAP_MR_PEND)
+		__set_chan_timer(chan, L2CAP_MOVE_ERTX_TIMEOUT);
+
+	switch (chan->move_state) {
+	case L2CAP_MOVE_WAIT_LOGICAL_COMP:
+		/* Move confirm will be sent when logical link
+		 * is complete.
+		 */
+		chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM;
+		break;
+	case L2CAP_MOVE_WAIT_RSP_SUCCESS:
+		if (result == L2CAP_MR_PEND) {
+			break;
+		} else if (test_bit(CONN_LOCAL_BUSY,
+				    &chan->conn_state)) {
+			chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY;
+		} else {
+			/* Logical link is up or moving to BR/EDR,
+			 * proceed with move
+			 */
+			chan->move_state = L2CAP_MOVE_WAIT_CONFIRM_RSP;
+			l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED);
+		}
+		break;
+	case L2CAP_MOVE_WAIT_RSP:
+		/* Moving to AMP */
+		if (result == L2CAP_MR_SUCCESS) {
+			/* Remote is ready, send confirm immediately
+			 * after logical link is ready
+			 */
+			chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM;
+		} else {
+			/* Both logical link and move success
+			 * are required to confirm
+			 */
+			chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_COMP;
+		}
+
+		/* Placeholder - get hci_chan for logical link */
+		if (!hchan) {
+			/* Logical link not available */
+			l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED);
+			break;
+		}
+
+		/* If the logical link is not yet connected, do not
+		 * send confirmation.
+		 */
+		if (hchan->state != BT_CONNECTED)
+			break;
+
+		/* Logical link is already ready to go */
+
+		chan->hs_hcon = hchan->conn;
+		chan->hs_hcon->l2cap_data = chan->conn;
+
+		if (result == L2CAP_MR_SUCCESS) {
+			/* Can confirm now */
+			l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED);
+		} else {
+			/* Now only need move success
+			 * to confirm
+			 */
+			chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS;
+		}
+
+		l2cap_logical_cfm(chan, hchan, L2CAP_MR_SUCCESS);
+		break;
+	default:
+		/* Any other amp move state means the move failed. */
+		chan->move_id = chan->local_amp_id;
+		l2cap_move_done(chan);
+		l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED);
+	}
+
+	l2cap_chan_unlock(chan);
+}
+
+static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid,
+			    u16 result)
+{
+	struct l2cap_chan *chan;
+
+	chan = l2cap_get_chan_by_ident(conn, ident);
+	if (!chan) {
+		/* Could not locate channel, icid is best guess */
+		l2cap_send_move_chan_cfm_icid(conn, icid);
+		return;
+	}
+
+	__clear_chan_timer(chan);
+
+	if (chan->move_role == L2CAP_MOVE_ROLE_INITIATOR) {
+		if (result == L2CAP_MR_COLLISION) {
+			chan->move_role = L2CAP_MOVE_ROLE_RESPONDER;
+		} else {
+			/* Cleanup - cancel move */
+			chan->move_id = chan->local_amp_id;
+			l2cap_move_done(chan);
+		}
+	}
+
+	l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED);
+
+	l2cap_chan_unlock(chan);
+}
+
+static int l2cap_move_channel_rsp(struct l2cap_conn *conn,
+				  struct l2cap_cmd_hdr *cmd,
+				  u16 cmd_len, void *data)
 {
 	struct l2cap_move_chan_rsp *rsp = data;
 	u16 icid, result;
@@ -4332,8 +4483,10 @@ static inline int l2cap_move_channel_rsp(struct l2cap_conn *conn,
 
 	BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result);
 
-	/* Placeholder: Always unconfirmed */
-	l2cap_send_move_chan_cfm(conn, NULL, icid, L2CAP_MC_UNCONFIRMED);
+	if (result == L2CAP_MR_SUCCESS || result == L2CAP_MR_PEND)
+		l2cap_move_continue(conn, icid, result);
+	else
+		l2cap_move_fail(conn, cmd->ident, icid, result);
 
 	return 0;
 }
-- 
cgit v1.2.3-55-g7522


From 3f7a56c4ff438f4727439cb048034f56320dd228 Mon Sep 17 00:00:00 2001
From: Mat Martineau
Date: Tue, 23 Oct 2012 15:24:23 -0700
Subject: Bluetooth: Start channel move when socket option is changed

Channel moves are triggered by changes to the BT_CHANNEL_POLICY
sockopt when an ERTM or streaming-mode channel is connected.

Moves are only started if enable_hs is true.

Signed-off-by: Mat Martineau <mathewm@codeaurora.org>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h |  1 +
 net/bluetooth/l2cap_core.c    | 19 +++++++++++++++++++
 net/bluetooth/l2cap_sock.c    |  5 +++++
 3 files changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index b4c3c65c1f58..49783e948856 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -809,5 +809,6 @@ void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
 void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
 void l2cap_chan_del(struct l2cap_chan *chan, int err);
 void l2cap_send_conn_req(struct l2cap_chan *chan);
+void l2cap_move_start(struct l2cap_chan *chan);
 
 #endif /* __L2CAP_H */
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 93f1ebbd7502..fae0c70e8e10 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4453,6 +4453,25 @@ static void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
 	}
 }
 
+void l2cap_move_start(struct l2cap_chan *chan)
+{
+	BT_DBG("chan %p", chan);
+
+	if (chan->local_amp_id == HCI_BREDR_ID) {
+		if (chan->chan_policy != BT_CHANNEL_POLICY_AMP_PREFERRED)
+			return;
+		chan->move_role = L2CAP_MOVE_ROLE_INITIATOR;
+		chan->move_state = L2CAP_MOVE_WAIT_PREPARE;
+		/* Placeholder - start physical link setup */
+	} else {
+		chan->move_role = L2CAP_MOVE_ROLE_INITIATOR;
+		chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS;
+		chan->move_id = 0;
+		l2cap_move_setup(chan);
+		l2cap_send_move_chan_req(chan, 0);
+	}
+}
+
 static void l2cap_do_create(struct l2cap_chan *chan, int result,
 			    u8 local_amp_id, u8 remote_amp_id)
 {
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 89f1472939ec..1bcfb8422fdc 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -736,6 +736,11 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 		}
 
 		chan->chan_policy = (u8) opt;
+
+		if (sk->sk_state == BT_CONNECTED &&
+		    chan->move_role == L2CAP_MOVE_ROLE_NONE)
+			l2cap_move_start(chan);
+
 		break;
 
 	default:
-- 
cgit v1.2.3-55-g7522


From 998c336d4c7183301ed6a6ca93952f63e3cf694f Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Wed, 30 May 2012 13:26:00 +0300
Subject: OMAPDSS: remove omap_dss_device's suspend/resume

The panel drivers contain enable, disable, suspend and resume calls.
The suspend and resume are effectively identical to disable and enable.

This patch removes panel suspend and enable code from omapdss and the
panel drivers, and replaces their use with enable and disable.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/omap2/displays/panel-acx565akm.c     | 23 -------
 drivers/video/omap2/displays/panel-generic-dpi.c   | 36 -----------
 .../omap2/displays/panel-lgphilips-lb035q02.c      | 34 ----------
 drivers/video/omap2/displays/panel-n8x0.c          | 50 ---------------
 .../omap2/displays/panel-nec-nl8048hl11-01b.c      | 24 --------
 drivers/video/omap2/displays/panel-picodlp.c       | 44 -------------
 .../video/omap2/displays/panel-sharp-ls037v7dw01.c | 17 -----
 drivers/video/omap2/displays/panel-taal.c          | 72 ----------------------
 drivers/video/omap2/displays/panel-tfp410.c        | 33 ----------
 .../video/omap2/displays/panel-tpo-td043mtea1.c    | 20 ------
 drivers/video/omap2/dss/display.c                  | 15 +----
 drivers/video/omap2/dss/hdmi_panel.c               | 70 +++------------------
 drivers/video/omap2/dss/venc_panel.c               | 19 ------
 drivers/video/omap2/omapfb/omapfb-main.c           |  8 +--
 include/video/omapdss.h                            |  3 -
 15 files changed, 16 insertions(+), 452 deletions(-)

(limited to 'include')

diff --git a/drivers/video/omap2/displays/panel-acx565akm.c b/drivers/video/omap2/displays/panel-acx565akm.c
index c835aa70f96f..65eb76c840a1 100644
--- a/drivers/video/omap2/displays/panel-acx565akm.c
+++ b/drivers/video/omap2/displays/panel-acx565akm.c
@@ -710,27 +710,6 @@ static void acx_panel_disable(struct omap_dss_device *dssdev)
 	dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
 }
 
-static int acx_panel_suspend(struct omap_dss_device *dssdev)
-{
-	dev_dbg(&dssdev->dev, "%s\n", __func__);
-	acx_panel_power_off(dssdev);
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-	return 0;
-}
-
-static int acx_panel_resume(struct omap_dss_device *dssdev)
-{
-	int r;
-
-	dev_dbg(&dssdev->dev, "%s\n", __func__);
-	r = acx_panel_power_on(dssdev);
-	if (r)
-		return r;
-
-	dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
-	return 0;
-}
-
 static void acx_panel_set_timings(struct omap_dss_device *dssdev,
 		struct omap_video_timings *timings)
 {
@@ -752,8 +731,6 @@ static struct omap_dss_driver acx_panel_driver = {
 
 	.enable		= acx_panel_enable,
 	.disable	= acx_panel_disable,
-	.suspend	= acx_panel_suspend,
-	.resume		= acx_panel_resume,
 
 	.set_timings	= acx_panel_set_timings,
 	.check_timings	= acx_panel_check_timings,
diff --git a/drivers/video/omap2/displays/panel-generic-dpi.c b/drivers/video/omap2/displays/panel-generic-dpi.c
index 88295c526815..54ca8ae21078 100644
--- a/drivers/video/omap2/displays/panel-generic-dpi.c
+++ b/drivers/video/omap2/displays/panel-generic-dpi.c
@@ -688,40 +688,6 @@ static void generic_dpi_panel_disable(struct omap_dss_device *dssdev)
 	mutex_unlock(&drv_data->lock);
 }
 
-static int generic_dpi_panel_suspend(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *drv_data = dev_get_drvdata(&dssdev->dev);
-
-	mutex_lock(&drv_data->lock);
-
-	generic_dpi_panel_power_off(dssdev);
-
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-
-	mutex_unlock(&drv_data->lock);
-
-	return 0;
-}
-
-static int generic_dpi_panel_resume(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *drv_data = dev_get_drvdata(&dssdev->dev);
-	int r;
-
-	mutex_lock(&drv_data->lock);
-
-	r = generic_dpi_panel_power_on(dssdev);
-	if (r)
-		goto err;
-
-	dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
-
-err:
-	mutex_unlock(&drv_data->lock);
-
-	return r;
-}
-
 static void generic_dpi_panel_set_timings(struct omap_dss_device *dssdev,
 		struct omap_video_timings *timings)
 {
@@ -769,8 +735,6 @@ static struct omap_dss_driver dpi_driver = {
 
 	.enable		= generic_dpi_panel_enable,
 	.disable	= generic_dpi_panel_disable,
-	.suspend	= generic_dpi_panel_suspend,
-	.resume		= generic_dpi_panel_resume,
 
 	.set_timings	= generic_dpi_panel_set_timings,
 	.get_timings	= generic_dpi_panel_get_timings,
diff --git a/drivers/video/omap2/displays/panel-lgphilips-lb035q02.c b/drivers/video/omap2/displays/panel-lgphilips-lb035q02.c
index 90c1cabf244e..ace419b801eb 100644
--- a/drivers/video/omap2/displays/panel-lgphilips-lb035q02.c
+++ b/drivers/video/omap2/displays/panel-lgphilips-lb035q02.c
@@ -143,46 +143,12 @@ static void lb035q02_panel_disable(struct omap_dss_device *dssdev)
 	mutex_unlock(&ld->lock);
 }
 
-static int lb035q02_panel_suspend(struct omap_dss_device *dssdev)
-{
-	struct lb035q02_data *ld = dev_get_drvdata(&dssdev->dev);
-
-	mutex_lock(&ld->lock);
-
-	lb035q02_panel_power_off(dssdev);
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-
-	mutex_unlock(&ld->lock);
-	return 0;
-}
-
-static int lb035q02_panel_resume(struct omap_dss_device *dssdev)
-{
-	struct lb035q02_data *ld = dev_get_drvdata(&dssdev->dev);
-	int r;
-
-	mutex_lock(&ld->lock);
-
-	r = lb035q02_panel_power_on(dssdev);
-	if (r)
-		goto err;
-	dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
-
-	mutex_unlock(&ld->lock);
-	return 0;
-err:
-	mutex_unlock(&ld->lock);
-	return r;
-}
-
 static struct omap_dss_driver lb035q02_driver = {
 	.probe		= lb035q02_panel_probe,
 	.remove		= lb035q02_panel_remove,
 
 	.enable		= lb035q02_panel_enable,
 	.disable	= lb035q02_panel_disable,
-	.suspend	= lb035q02_panel_suspend,
-	.resume		= lb035q02_panel_resume,
 
 	.driver         = {
 		.name   = "lgphilips_lb035q02_panel",
diff --git a/drivers/video/omap2/displays/panel-n8x0.c b/drivers/video/omap2/displays/panel-n8x0.c
index 3fc5ad081a21..265326955552 100644
--- a/drivers/video/omap2/displays/panel-n8x0.c
+++ b/drivers/video/omap2/displays/panel-n8x0.c
@@ -574,54 +574,6 @@ static void n8x0_panel_disable(struct omap_dss_device *dssdev)
 	mutex_unlock(&ddata->lock);
 }
 
-static int n8x0_panel_suspend(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = get_drv_data(dssdev);
-
-	dev_dbg(&dssdev->dev, "suspend\n");
-
-	mutex_lock(&ddata->lock);
-
-	rfbi_bus_lock();
-
-	n8x0_panel_power_off(dssdev);
-
-	rfbi_bus_unlock();
-
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-
-	mutex_unlock(&ddata->lock);
-
-	return 0;
-}
-
-static int n8x0_panel_resume(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = get_drv_data(dssdev);
-	int r;
-
-	dev_dbg(&dssdev->dev, "resume\n");
-
-	mutex_lock(&ddata->lock);
-
-	rfbi_bus_lock();
-
-	r = n8x0_panel_power_on(dssdev);
-
-	rfbi_bus_unlock();
-
-	if (r) {
-		mutex_unlock(&ddata->lock);
-		return r;
-	}
-
-	dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
-
-	mutex_unlock(&ddata->lock);
-
-	return 0;
-}
-
 static void n8x0_panel_get_resolution(struct omap_dss_device *dssdev,
 		u16 *xres, u16 *yres)
 {
@@ -683,8 +635,6 @@ static struct omap_dss_driver n8x0_panel_driver = {
 
 	.enable		= n8x0_panel_enable,
 	.disable	= n8x0_panel_disable,
-	.suspend	= n8x0_panel_suspend,
-	.resume		= n8x0_panel_resume,
 
 	.update		= n8x0_panel_update,
 	.sync		= n8x0_panel_sync,
diff --git a/drivers/video/omap2/displays/panel-nec-nl8048hl11-01b.c b/drivers/video/omap2/displays/panel-nec-nl8048hl11-01b.c
index 908fd268f3dc..2a79c283bebe 100644
--- a/drivers/video/omap2/displays/panel-nec-nl8048hl11-01b.c
+++ b/drivers/video/omap2/displays/panel-nec-nl8048hl11-01b.c
@@ -236,28 +236,6 @@ static void nec_8048_panel_disable(struct omap_dss_device *dssdev)
 	dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
 }
 
-static int nec_8048_panel_suspend(struct omap_dss_device *dssdev)
-{
-	nec_8048_panel_power_off(dssdev);
-
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-
-	return 0;
-}
-
-static int nec_8048_panel_resume(struct omap_dss_device *dssdev)
-{
-	int r;
-
-	r = nec_8048_panel_power_on(dssdev);
-	if (r)
-		return r;
-
-	dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
-
-	return 0;
-}
-
 static int nec_8048_recommended_bpp(struct omap_dss_device *dssdev)
 {
 	return 16;
@@ -268,8 +246,6 @@ static struct omap_dss_driver nec_8048_driver = {
 	.remove			= nec_8048_panel_remove,
 	.enable			= nec_8048_panel_enable,
 	.disable		= nec_8048_panel_disable,
-	.suspend		= nec_8048_panel_suspend,
-	.resume			= nec_8048_panel_resume,
 	.get_recommended_bpp	= nec_8048_recommended_bpp,
 
 	.driver		= {
diff --git a/drivers/video/omap2/displays/panel-picodlp.c b/drivers/video/omap2/displays/panel-picodlp.c
index 9df87640ddd2..e3a6c1996134 100644
--- a/drivers/video/omap2/displays/panel-picodlp.c
+++ b/drivers/video/omap2/displays/panel-picodlp.c
@@ -503,47 +503,6 @@ static void picodlp_panel_disable(struct omap_dss_device *dssdev)
 	dev_dbg(&dssdev->dev, "disabling picodlp panel\n");
 }
 
-static int picodlp_panel_suspend(struct omap_dss_device *dssdev)
-{
-	struct picodlp_data *picod = dev_get_drvdata(&dssdev->dev);
-
-	mutex_lock(&picod->lock);
-	/* Turn off DLP Power */
-	if (dssdev->state != OMAP_DSS_DISPLAY_ACTIVE) {
-		mutex_unlock(&picod->lock);
-		dev_err(&dssdev->dev, "unable to suspend picodlp panel,"
-					" panel is not ACTIVE\n");
-		return -EINVAL;
-	}
-
-	picodlp_panel_power_off(dssdev);
-
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-	mutex_unlock(&picod->lock);
-
-	dev_dbg(&dssdev->dev, "suspending picodlp panel\n");
-	return 0;
-}
-
-static int picodlp_panel_resume(struct omap_dss_device *dssdev)
-{
-	struct picodlp_data *picod = dev_get_drvdata(&dssdev->dev);
-	int r;
-
-	mutex_lock(&picod->lock);
-	if (dssdev->state != OMAP_DSS_DISPLAY_SUSPENDED) {
-		mutex_unlock(&picod->lock);
-		dev_err(&dssdev->dev, "unable to resume picodlp panel,"
-			" panel is not ACTIVE\n");
-		return -EINVAL;
-	}
-
-	r = picodlp_panel_power_on(dssdev);
-	mutex_unlock(&picod->lock);
-	dev_dbg(&dssdev->dev, "resuming picodlp panel\n");
-	return r;
-}
-
 static void picodlp_get_resolution(struct omap_dss_device *dssdev,
 					u16 *xres, u16 *yres)
 {
@@ -560,9 +519,6 @@ static struct omap_dss_driver picodlp_driver = {
 
 	.get_resolution	= picodlp_get_resolution,
 
-	.suspend	= picodlp_panel_suspend,
-	.resume		= picodlp_panel_resume,
-
 	.driver		= {
 		.name	= "picodlp_panel",
 		.owner	= THIS_MODULE,
diff --git a/drivers/video/omap2/displays/panel-sharp-ls037v7dw01.c b/drivers/video/omap2/displays/panel-sharp-ls037v7dw01.c
index 1ec3b277ff15..cada8c621e01 100644
--- a/drivers/video/omap2/displays/panel-sharp-ls037v7dw01.c
+++ b/drivers/video/omap2/displays/panel-sharp-ls037v7dw01.c
@@ -194,29 +194,12 @@ static void sharp_ls_panel_disable(struct omap_dss_device *dssdev)
 	dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
 }
 
-static int sharp_ls_panel_suspend(struct omap_dss_device *dssdev)
-{
-	sharp_ls_power_off(dssdev);
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-	return 0;
-}
-
-static int sharp_ls_panel_resume(struct omap_dss_device *dssdev)
-{
-	int r;
-	r = sharp_ls_power_on(dssdev);
-	dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
-	return r;
-}
-
 static struct omap_dss_driver sharp_ls_driver = {
 	.probe		= sharp_ls_panel_probe,
 	.remove		= __exit_p(sharp_ls_panel_remove),
 
 	.enable		= sharp_ls_panel_enable,
 	.disable	= sharp_ls_panel_disable,
-	.suspend	= sharp_ls_panel_suspend,
-	.resume		= sharp_ls_panel_resume,
 
 	.driver         = {
 		.name   = "sharp_ls_panel",
diff --git a/drivers/video/omap2/displays/panel-taal.c b/drivers/video/omap2/displays/panel-taal.c
index f2f644680ca8..a32407a5735a 100644
--- a/drivers/video/omap2/displays/panel-taal.c
+++ b/drivers/video/omap2/displays/panel-taal.c
@@ -1245,76 +1245,6 @@ static void taal_disable(struct omap_dss_device *dssdev)
 	mutex_unlock(&td->lock);
 }
 
-static int taal_suspend(struct omap_dss_device *dssdev)
-{
-	struct taal_data *td = dev_get_drvdata(&dssdev->dev);
-	int r;
-
-	dev_dbg(&dssdev->dev, "suspend\n");
-
-	mutex_lock(&td->lock);
-
-	if (dssdev->state != OMAP_DSS_DISPLAY_ACTIVE) {
-		r = -EINVAL;
-		goto err;
-	}
-
-	taal_cancel_ulps_work(dssdev);
-	taal_cancel_esd_work(dssdev);
-
-	dsi_bus_lock(dssdev);
-
-	r = taal_wake_up(dssdev);
-	if (!r)
-		taal_power_off(dssdev);
-
-	dsi_bus_unlock(dssdev);
-
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-
-	mutex_unlock(&td->lock);
-
-	return 0;
-err:
-	mutex_unlock(&td->lock);
-	return r;
-}
-
-static int taal_resume(struct omap_dss_device *dssdev)
-{
-	struct taal_data *td = dev_get_drvdata(&dssdev->dev);
-	int r;
-
-	dev_dbg(&dssdev->dev, "resume\n");
-
-	mutex_lock(&td->lock);
-
-	if (dssdev->state != OMAP_DSS_DISPLAY_SUSPENDED) {
-		r = -EINVAL;
-		goto err;
-	}
-
-	dsi_bus_lock(dssdev);
-
-	r = taal_power_on(dssdev);
-
-	dsi_bus_unlock(dssdev);
-
-	if (r) {
-		dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
-	} else {
-		dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
-		taal_queue_esd_work(dssdev);
-	}
-
-	mutex_unlock(&td->lock);
-
-	return r;
-err:
-	mutex_unlock(&td->lock);
-	return r;
-}
-
 static void taal_framedone_cb(int err, void *data)
 {
 	struct omap_dss_device *dssdev = data;
@@ -1818,8 +1748,6 @@ static struct omap_dss_driver taal_driver = {
 
 	.enable		= taal_enable,
 	.disable	= taal_disable,
-	.suspend	= taal_suspend,
-	.resume		= taal_resume,
 
 	.update		= taal_update,
 	.sync		= taal_sync,
diff --git a/drivers/video/omap2/displays/panel-tfp410.c b/drivers/video/omap2/displays/panel-tfp410.c
index 383811cf8648..8281baafe1ef 100644
--- a/drivers/video/omap2/displays/panel-tfp410.c
+++ b/drivers/video/omap2/displays/panel-tfp410.c
@@ -189,37 +189,6 @@ static void tfp410_disable(struct omap_dss_device *dssdev)
 	mutex_unlock(&ddata->lock);
 }
 
-static int tfp410_suspend(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = dev_get_drvdata(&dssdev->dev);
-
-	mutex_lock(&ddata->lock);
-
-	tfp410_power_off(dssdev);
-
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-
-	mutex_unlock(&ddata->lock);
-
-	return 0;
-}
-
-static int tfp410_resume(struct omap_dss_device *dssdev)
-{
-	struct panel_drv_data *ddata = dev_get_drvdata(&dssdev->dev);
-	int r;
-
-	mutex_lock(&ddata->lock);
-
-	r = tfp410_power_on(dssdev);
-	if (r == 0)
-		dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
-
-	mutex_unlock(&ddata->lock);
-
-	return r;
-}
-
 static void tfp410_set_timings(struct omap_dss_device *dssdev,
 		struct omap_video_timings *timings)
 {
@@ -355,8 +324,6 @@ static struct omap_dss_driver tfp410_driver = {
 
 	.enable		= tfp410_enable,
 	.disable	= tfp410_disable,
-	.suspend	= tfp410_suspend,
-	.resume		= tfp410_resume,
 
 	.set_timings	= tfp410_set_timings,
 	.get_timings	= tfp410_get_timings,
diff --git a/drivers/video/omap2/displays/panel-tpo-td043mtea1.c b/drivers/video/omap2/displays/panel-tpo-td043mtea1.c
index b5e6dbc59f0a..316b3da6d2cb 100644
--- a/drivers/video/omap2/displays/panel-tpo-td043mtea1.c
+++ b/drivers/video/omap2/displays/panel-tpo-td043mtea1.c
@@ -401,24 +401,6 @@ static void tpo_td043_disable(struct omap_dss_device *dssdev)
 	dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
 }
 
-static int tpo_td043_suspend(struct omap_dss_device *dssdev)
-{
-	dev_dbg(&dssdev->dev, "suspend\n");
-
-	tpo_td043_disable_dss(dssdev);
-
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-
-	return 0;
-}
-
-static int tpo_td043_resume(struct omap_dss_device *dssdev)
-{
-	dev_dbg(&dssdev->dev, "resume\n");
-
-	return tpo_td043_enable_dss(dssdev);
-}
-
 static int tpo_td043_probe(struct omap_dss_device *dssdev)
 {
 	struct tpo_td043_device *tpo_td043 = dev_get_drvdata(&dssdev->dev);
@@ -500,8 +482,6 @@ static struct omap_dss_driver tpo_td043_driver = {
 
 	.enable		= tpo_td043_enable,
 	.disable	= tpo_td043_disable,
-	.suspend	= tpo_td043_suspend,
-	.resume		= tpo_td043_resume,
 	.set_mirror	= tpo_td043_set_hmirror,
 	.get_mirror	= tpo_td043_get_hmirror,
 
diff --git a/drivers/video/omap2/dss/display.c b/drivers/video/omap2/dss/display.c
index ccf8550fafde..1e587306215f 100644
--- a/drivers/video/omap2/dss/display.c
+++ b/drivers/video/omap2/dss/display.c
@@ -449,7 +449,6 @@ void dss_uninit_device(struct platform_device *pdev,
 
 static int dss_suspend_device(struct device *dev, void *data)
 {
-	int r;
 	struct omap_dss_device *dssdev = to_dss_device(dev);
 
 	if (dssdev->state != OMAP_DSS_DISPLAY_ACTIVE) {
@@ -457,15 +456,7 @@ static int dss_suspend_device(struct device *dev, void *data)
 		return 0;
 	}
 
-	if (!dssdev->driver->suspend) {
-		DSSERR("display '%s' doesn't implement suspend\n",
-				dssdev->name);
-		return -ENOSYS;
-	}
-
-	r = dssdev->driver->suspend(dssdev);
-	if (r)
-		return r;
+	dssdev->driver->disable(dssdev);
 
 	dssdev->activate_after_resume = true;
 
@@ -492,8 +483,8 @@ static int dss_resume_device(struct device *dev, void *data)
 	int r;
 	struct omap_dss_device *dssdev = to_dss_device(dev);
 
-	if (dssdev->activate_after_resume && dssdev->driver->resume) {
-		r = dssdev->driver->resume(dssdev);
+	if (dssdev->activate_after_resume) {
+		r = dssdev->driver->enable(dssdev);
 		if (r)
 			return r;
 	}
diff --git a/drivers/video/omap2/dss/hdmi_panel.c b/drivers/video/omap2/dss/hdmi_panel.c
index 69fb115bab32..3f9a4b947a54 100644
--- a/drivers/video/omap2/dss/hdmi_panel.c
+++ b/drivers/video/omap2/dss/hdmi_panel.c
@@ -280,58 +280,6 @@ static void hdmi_panel_disable(struct omap_dss_device *dssdev)
 	mutex_unlock(&hdmi.lock);
 }
 
-static int hdmi_panel_suspend(struct omap_dss_device *dssdev)
-{
-	int r = 0;
-
-	mutex_lock(&hdmi.lock);
-
-	if (dssdev->state != OMAP_DSS_DISPLAY_ACTIVE) {
-		r = -EINVAL;
-		goto err;
-	}
-
-	/*
-	 * TODO: notify audio users that the display was suspended. For now,
-	 * disable audio locally to not break our audio state machine.
-	 */
-	hdmi_panel_audio_disable(dssdev);
-
-	dssdev->state = OMAP_DSS_DISPLAY_SUSPENDED;
-	omapdss_hdmi_display_disable(dssdev);
-
-err:
-	mutex_unlock(&hdmi.lock);
-
-	return r;
-}
-
-static int hdmi_panel_resume(struct omap_dss_device *dssdev)
-{
-	int r = 0;
-
-	mutex_lock(&hdmi.lock);
-
-	if (dssdev->state != OMAP_DSS_DISPLAY_SUSPENDED) {
-		r = -EINVAL;
-		goto err;
-	}
-
-	r = omapdss_hdmi_display_enable(dssdev);
-	if (r) {
-		DSSERR("failed to power on\n");
-		goto err;
-	}
-	/* TODO: notify audio users that the panel resumed. */
-
-	dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
-
-err:
-	mutex_unlock(&hdmi.lock);
-
-	return r;
-}
-
 static void hdmi_get_timings(struct omap_dss_device *dssdev,
 			struct omap_video_timings *timings)
 {
@@ -379,10 +327,13 @@ static int hdmi_check_timings(struct omap_dss_device *dssdev,
 static int hdmi_read_edid(struct omap_dss_device *dssdev, u8 *buf, int len)
 {
 	int r;
+	bool need_enable;
 
 	mutex_lock(&hdmi.lock);
 
-	if (dssdev->state != OMAP_DSS_DISPLAY_ACTIVE) {
+	need_enable = dssdev->state == OMAP_DSS_DISPLAY_DISABLED;
+
+	if (need_enable) {
 		r = omapdss_hdmi_display_enable(dssdev);
 		if (r)
 			goto err;
@@ -390,8 +341,7 @@ static int hdmi_read_edid(struct omap_dss_device *dssdev, u8 *buf, int len)
 
 	r = omapdss_hdmi_read_edid(buf, len);
 
-	if (dssdev->state == OMAP_DSS_DISPLAY_DISABLED ||
-			dssdev->state == OMAP_DSS_DISPLAY_SUSPENDED)
+	if (need_enable)
 		omapdss_hdmi_display_disable(dssdev);
 err:
 	mutex_unlock(&hdmi.lock);
@@ -402,10 +352,13 @@ err:
 static bool hdmi_detect(struct omap_dss_device *dssdev)
 {
 	int r;
+	bool need_enable;
 
 	mutex_lock(&hdmi.lock);
 
-	if (dssdev->state != OMAP_DSS_DISPLAY_ACTIVE) {
+	need_enable = dssdev->state == OMAP_DSS_DISPLAY_DISABLED;
+
+	if (need_enable) {
 		r = omapdss_hdmi_display_enable(dssdev);
 		if (r)
 			goto err;
@@ -413,8 +366,7 @@ static bool hdmi_detect(struct omap_dss_device *dssdev)
 
 	r = omapdss_hdmi_detect();
 
-	if (dssdev->state == OMAP_DSS_DISPLAY_DISABLED ||
-			dssdev->state == OMAP_DSS_DISPLAY_SUSPENDED)
+	if (need_enable)
 		omapdss_hdmi_display_disable(dssdev);
 err:
 	mutex_unlock(&hdmi.lock);
@@ -427,8 +379,6 @@ static struct omap_dss_driver hdmi_driver = {
 	.remove		= hdmi_panel_remove,
 	.enable		= hdmi_panel_enable,
 	.disable	= hdmi_panel_disable,
-	.suspend	= hdmi_panel_suspend,
-	.resume		= hdmi_panel_resume,
 	.get_timings	= hdmi_get_timings,
 	.set_timings	= hdmi_set_timings,
 	.check_timings	= hdmi_check_timings,
diff --git a/drivers/video/omap2/dss/venc_panel.c b/drivers/video/omap2/dss/venc_panel.c
index d55b8784ecfd..0d2b1a0834a0 100644
--- a/drivers/video/omap2/dss/venc_panel.c
+++ b/drivers/video/omap2/dss/venc_panel.c
@@ -157,12 +157,6 @@ static void venc_panel_disable(struct omap_dss_device *dssdev)
 	if (dssdev->state == OMAP_DSS_DISPLAY_DISABLED)
 		goto end;
 
-	if (dssdev->state == OMAP_DSS_DISPLAY_SUSPENDED) {
-		/* suspended is the same as disabled with venc */
-		dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
-		goto end;
-	}
-
 	omapdss_venc_display_disable(dssdev);
 
 	dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
@@ -170,17 +164,6 @@ end:
 	mutex_unlock(&venc_panel.lock);
 }
 
-static int venc_panel_suspend(struct omap_dss_device *dssdev)
-{
-	venc_panel_disable(dssdev);
-	return 0;
-}
-
-static int venc_panel_resume(struct omap_dss_device *dssdev)
-{
-	return venc_panel_enable(dssdev);
-}
-
 static void venc_panel_set_timings(struct omap_dss_device *dssdev,
 		struct omap_video_timings *timings)
 {
@@ -222,8 +205,6 @@ static struct omap_dss_driver venc_driver = {
 
 	.enable		= venc_panel_enable,
 	.disable	= venc_panel_disable,
-	.suspend	= venc_panel_suspend,
-	.resume		= venc_panel_resume,
 
 	.get_resolution	= omapdss_default_get_resolution,
 	.get_recommended_bpp = omapdss_default_get_recommended_bpp,
diff --git a/drivers/video/omap2/omapfb/omapfb-main.c b/drivers/video/omap2/omapfb/omapfb-main.c
index bc225e46fdd2..ba4630830e09 100644
--- a/drivers/video/omap2/omapfb/omapfb-main.c
+++ b/drivers/video/omap2/omapfb/omapfb-main.c
@@ -1258,11 +1258,10 @@ static int omapfb_blank(int blank, struct fb_info *fbi)
 
 	switch (blank) {
 	case FB_BLANK_UNBLANK:
-		if (display->state != OMAP_DSS_DISPLAY_SUSPENDED)
+		if (display->state == OMAP_DSS_DISPLAY_ACTIVE)
 			goto exit;
 
-		if (display->driver->resume)
-			r = display->driver->resume(display);
+		r = display->driver->enable(display);
 
 		if ((display->caps & OMAP_DSS_DISPLAY_CAP_MANUAL_UPDATE) &&
 				d->update_mode == OMAPFB_AUTO_UPDATE &&
@@ -1283,8 +1282,7 @@ static int omapfb_blank(int blank, struct fb_info *fbi)
 		if (d->auto_update_work_enabled)
 			omapfb_stop_auto_update(fbdev, display);
 
-		if (display->driver->suspend)
-			r = display->driver->suspend(display);
+		display->driver->disable(display);
 
 		break;
 
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index 88c829466fc1..cdfb22e7fe80 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -158,7 +158,6 @@ enum omap_display_caps {
 enum omap_dss_display_state {
 	OMAP_DSS_DISPLAY_DISABLED = 0,
 	OMAP_DSS_DISPLAY_ACTIVE,
-	OMAP_DSS_DISPLAY_SUSPENDED,
 };
 
 enum omap_dss_audio_state {
@@ -686,8 +685,6 @@ struct omap_dss_driver {
 
 	int (*enable)(struct omap_dss_device *display);
 	void (*disable)(struct omap_dss_device *display);
-	int (*suspend)(struct omap_dss_device *display);
-	int (*resume)(struct omap_dss_device *display);
 	int (*run_test)(struct omap_dss_device *display, int test);
 
 	int (*update)(struct omap_dss_device *dssdev,
-- 
cgit v1.2.3-55-g7522


From b2c7d54f72c1c588e8851c882f0465705f5e9e55 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Thu, 18 Oct 2012 13:46:29 +0300
Subject: OMAPDSS: get the dss version from core pdev

The output drivers get the omapdss hw version from the platform data for
their respective output device. This doesn't work with DT, as there's no
platform data for them.

Add a new function, omapdss_get_version(), which returns the dss version
from the core device, which will have platform data on DT also. The
function is exported so that users of omapdss can also use it.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/omap2/dss/core.c  | 9 ++++++++-
 drivers/video/omap2/dss/dispc.c | 3 +--
 drivers/video/omap2/dss/dss.c   | 3 +--
 drivers/video/omap2/dss/hdmi.c  | 3 +--
 include/video/omapdss.h         | 2 ++
 5 files changed, 13 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/video/omap2/dss/core.c b/drivers/video/omap2/dss/core.c
index 00aa026e307c..685d9a957b19 100644
--- a/drivers/video/omap2/dss/core.c
+++ b/drivers/video/omap2/dss/core.c
@@ -58,6 +58,13 @@ const char *dss_get_default_display_name(void)
 	return core.default_display_name;
 }
 
+enum omapdss_version omapdss_get_version(void)
+{
+	struct omap_dss_board_info *pdata = core.pdev->dev.platform_data;
+	return pdata->version;
+}
+EXPORT_SYMBOL(omapdss_get_version);
+
 /* REGULATORS */
 
 struct regulator *dss_get_vdds_dsi(void)
@@ -232,7 +239,7 @@ static int __init omap_dss_probe(struct platform_device *pdev)
 
 	core.pdev = pdev;
 
-	dss_features_init(pdata->version);
+	dss_features_init(omapdss_get_version());
 
 	dss_apply_init();
 
diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c
index 6dd9eb4a2c5b..817d671e2baa 100644
--- a/drivers/video/omap2/dss/dispc.c
+++ b/drivers/video/omap2/dss/dispc.c
@@ -4098,7 +4098,6 @@ static const struct dispc_features omap44xx_dispc_feats __initconst = {
 
 static int __init dispc_init_features(struct platform_device *pdev)
 {
-	struct omap_dss_board_info *pdata = pdev->dev.platform_data;
 	const struct dispc_features *src;
 	struct dispc_features *dst;
 
@@ -4108,7 +4107,7 @@ static int __init dispc_init_features(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	switch (pdata->version) {
+	switch (omapdss_get_version()) {
 	case OMAPDSS_VER_OMAP24xx:
 		src = &omap24xx_dispc_feats;
 		break;
diff --git a/drivers/video/omap2/dss/dss.c b/drivers/video/omap2/dss/dss.c
index 37ee465c1a0e..d90de37288c4 100644
--- a/drivers/video/omap2/dss/dss.c
+++ b/drivers/video/omap2/dss/dss.c
@@ -793,7 +793,6 @@ static const struct dss_features omap54xx_dss_feats __initconst = {
 
 static int __init dss_init_features(struct platform_device *pdev)
 {
-	struct omap_dss_board_info *pdata = pdev->dev.platform_data;
 	const struct dss_features *src;
 	struct dss_features *dst;
 
@@ -803,7 +802,7 @@ static int __init dss_init_features(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	switch (pdata->version) {
+	switch (omapdss_get_version()) {
 	case OMAPDSS_VER_OMAP24xx:
 		src = &omap24xx_dss_feats;
 		break;
diff --git a/drivers/video/omap2/dss/hdmi.c b/drivers/video/omap2/dss/hdmi.c
index adcc906d12f8..c1c54883fbe7 100644
--- a/drivers/video/omap2/dss/hdmi.c
+++ b/drivers/video/omap2/dss/hdmi.c
@@ -323,7 +323,6 @@ static void hdmi_runtime_put(void)
 
 static int __init hdmi_init_display(struct omap_dss_device *dssdev)
 {
-	struct omap_dss_board_info *pdata = hdmi.pdev->dev.platform_data;
 	int r;
 
 	struct gpio gpios[] = {
@@ -334,7 +333,7 @@ static int __init hdmi_init_display(struct omap_dss_device *dssdev)
 
 	DSSDBG("init_display\n");
 
-	dss_init_hdmi_ip_ops(&hdmi.ip_data, pdata->version);
+	dss_init_hdmi_ip_ops(&hdmi.ip_data, omapdss_get_version());
 
 	if (hdmi.vdda_hdmi_dac_reg == NULL) {
 		struct regulator *reg;
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index cdfb22e7fe80..eac5f2562253 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -742,6 +742,8 @@ struct omap_dss_driver {
 
 };
 
+enum omapdss_version omapdss_get_version(void);
+
 int omap_dss_register_driver(struct omap_dss_driver *);
 void omap_dss_unregister_driver(struct omap_dss_driver *);
 
-- 
cgit v1.2.3-55-g7522


From 9d85f21c94f7f7a84d0ba686c58aa6d9da58fdbb Mon Sep 17 00:00:00 2001
From: Paul Turner
Date: Thu, 4 Oct 2012 13:18:29 +0200
Subject: sched: Track the runnable average on a per-task entity basis

Instead of tracking averaging the load parented by a cfs_rq, we can track
entity load directly. With the load for a given cfs_rq then being the sum
of its children.

To do this we represent the historical contribution to runnable average
within each trailing 1024us of execution as the coefficients of a
geometric series.

We can express this for a given task t as:

  runnable_sum(t) = \Sum u_i * y^i, runnable_avg_period(t) = \Sum 1024 * y^i
  load(t) = weight_t * runnable_sum(t) / runnable_avg_period(t)

Where: u_i is the usage in the last i`th 1024us period (approximately 1ms)
~ms and y is chosen such that y^k = 1/2.  We currently choose k to be 32 which
roughly translates to about a sched period.

Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20120823141506.372695337@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  13 +++++
 kernel/sched/core.c   |   5 ++
 kernel/sched/debug.c  |   4 ++
 kernel/sched/fair.c   | 129 ++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 151 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a02df2e..418fc6d8a4da 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1095,6 +1095,16 @@ struct load_weight {
 	unsigned long weight, inv_weight;
 };
 
+struct sched_avg {
+	/*
+	 * These sums represent an infinite geometric series and so are bound
+	 * above by 1024/(1-y).  Thus we only need a u32 to store them for for all
+	 * choices of y < 1-2^(-32)*1024.
+	 */
+	u32 runnable_avg_sum, runnable_avg_period;
+	u64 last_runnable_update;
+};
+
 #ifdef CONFIG_SCHEDSTATS
 struct sched_statistics {
 	u64			wait_start;
@@ -1155,6 +1165,9 @@ struct sched_entity {
 	/* rq "owned" by this entity/group: */
 	struct cfs_rq		*my_q;
 #endif
+#ifdef CONFIG_SMP
+	struct sched_avg	avg;
+#endif
 };
 
 struct sched_rt_entity {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d8927fda712..fd9d0859350a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1524,6 +1524,11 @@ static void __sched_fork(struct task_struct *p)
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+#ifdef CONFIG_SMP
+	p->se.avg.runnable_avg_period = 0;
+	p->se.avg.runnable_avg_sum = 0;
+#endif
+
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 6f79596e0ea9..61f70979153a 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -85,6 +85,10 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	P(se->statistics.wait_count);
 #endif
 	P(se->load.weight);
+#ifdef CONFIG_SMP
+	P(se->avg.runnable_avg_sum);
+	P(se->avg.runnable_avg_period);
+#endif
 #undef PN
 #undef P
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6b800a14b990..16d67f9b6955 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -971,6 +971,126 @@ static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
+#ifdef CONFIG_SMP
+/*
+ * Approximate:
+ *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
+ */
+static __always_inline u64 decay_load(u64 val, u64 n)
+{
+	for (; n && val; n--) {
+		val *= 4008;
+		val >>= 12;
+	}
+
+	return val;
+}
+
+/*
+ * We can represent the historical contribution to runnable average as the
+ * coefficients of a geometric series.  To do this we sub-divide our runnable
+ * history into segments of approximately 1ms (1024us); label the segment that
+ * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
+ *
+ * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
+ *      p0            p1           p2
+ *     (now)       (~1ms ago)  (~2ms ago)
+ *
+ * Let u_i denote the fraction of p_i that the entity was runnable.
+ *
+ * We then designate the fractions u_i as our co-efficients, yielding the
+ * following representation of historical load:
+ *   u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
+ *
+ * We choose y based on the with of a reasonably scheduling period, fixing:
+ *   y^32 = 0.5
+ *
+ * This means that the contribution to load ~32ms ago (u_32) will be weighted
+ * approximately half as much as the contribution to load within the last ms
+ * (u_0).
+ *
+ * When a period "rolls over" and we have new u_0`, multiplying the previous
+ * sum again by y is sufficient to update:
+ *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
+ *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
+ */
+static __always_inline int __update_entity_runnable_avg(u64 now,
+							struct sched_avg *sa,
+							int runnable)
+{
+	u64 delta;
+	int delta_w, decayed = 0;
+
+	delta = now - sa->last_runnable_update;
+	/*
+	 * This should only happen when time goes backwards, which it
+	 * unfortunately does during sched clock init when we swap over to TSC.
+	 */
+	if ((s64)delta < 0) {
+		sa->last_runnable_update = now;
+		return 0;
+	}
+
+	/*
+	 * Use 1024ns as the unit of measurement since it's a reasonable
+	 * approximation of 1us and fast to compute.
+	 */
+	delta >>= 10;
+	if (!delta)
+		return 0;
+	sa->last_runnable_update = now;
+
+	/* delta_w is the amount already accumulated against our next period */
+	delta_w = sa->runnable_avg_period % 1024;
+	if (delta + delta_w >= 1024) {
+		/* period roll-over */
+		decayed = 1;
+
+		/*
+		 * Now that we know we're crossing a period boundary, figure
+		 * out how much from delta we need to complete the current
+		 * period and accrue it.
+		 */
+		delta_w = 1024 - delta_w;
+		BUG_ON(delta_w > delta);
+		do {
+			if (runnable)
+				sa->runnable_avg_sum += delta_w;
+			sa->runnable_avg_period += delta_w;
+
+			/*
+			 * Remainder of delta initiates a new period, roll over
+			 * the previous.
+			 */
+			sa->runnable_avg_sum =
+				decay_load(sa->runnable_avg_sum, 1);
+			sa->runnable_avg_period =
+				decay_load(sa->runnable_avg_period, 1);
+
+			delta -= delta_w;
+			/* New period is empty */
+			delta_w = 1024;
+		} while (delta >= 1024);
+	}
+
+	/* Remainder of delta accrued against u_0` */
+	if (runnable)
+		sa->runnable_avg_sum += delta;
+	sa->runnable_avg_period += delta;
+
+	return decayed;
+}
+
+/* Update a sched_entity's runnable average */
+static inline void update_entity_load_avg(struct sched_entity *se)
+{
+	__update_entity_runnable_avg(rq_of(cfs_rq_of(se))->clock_task, &se->avg,
+				     se->on_rq);
+}
+#else
+static inline void update_entity_load_avg(struct sched_entity *se) {}
+#endif
+
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 #ifdef CONFIG_SCHEDSTATS
@@ -1097,6 +1217,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	update_curr(cfs_rq);
 	update_cfs_load(cfs_rq, 0);
+	update_entity_load_avg(se);
 	account_entity_enqueue(cfs_rq, se);
 	update_cfs_shares(cfs_rq);
 
@@ -1171,6 +1292,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
+	update_entity_load_avg(se);
 
 	update_stats_dequeue(cfs_rq, se);
 	if (flags & DEQUEUE_SLEEP) {
@@ -1340,6 +1462,8 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 		update_stats_wait_start(cfs_rq, prev);
 		/* Put 'current' back into the tree. */
 		__enqueue_entity(cfs_rq, prev);
+		/* in !on_rq case, update occurred at dequeue */
+		update_entity_load_avg(prev);
 	}
 	cfs_rq->curr = NULL;
 }
@@ -1352,6 +1476,11 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	 */
 	update_curr(cfs_rq);
 
+	/*
+	 * Ensure that runnable average is periodically updated.
+	 */
+	update_entity_load_avg(curr);
+
 	/*
 	 * Update share accounting for long-running entities.
 	 */
-- 
cgit v1.2.3-55-g7522


From 2dac754e10a5d41d94d2d2365c0345d4f215a266 Mon Sep 17 00:00:00 2001
From: Paul Turner
Date: Thu, 4 Oct 2012 13:18:30 +0200
Subject: sched: Aggregate load contributed by task entities on parenting
 cfs_rq

For a given task t, we can compute its contribution to load as:

  task_load(t) = runnable_avg(t) * weight(t)

On a parenting cfs_rq we can then aggregate:

  runnable_load(cfs_rq) = \Sum task_load(t), for all runnable children t

Maintain this bottom up, with task entities adding their contributed load to
the parenting cfs_rq sum.  When a task entity's load changes we add the same
delta to the maintained sum.

Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20120823141506.514678907@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  1 +
 kernel/sched/debug.c  |  3 +++
 kernel/sched/fair.c   | 51 +++++++++++++++++++++++++++++++++++++++++++++++----
 kernel/sched/sched.h  | 10 +++++++++-
 4 files changed, 60 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 418fc6d8a4da..81d8b1ba4100 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1103,6 +1103,7 @@ struct sched_avg {
 	 */
 	u32 runnable_avg_sum, runnable_avg_period;
 	u64 last_runnable_update;
+	unsigned long load_avg_contrib;
 };
 
 #ifdef CONFIG_SCHEDSTATS
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 4240abce4116..c953a89f94aa 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -94,6 +94,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 #ifdef CONFIG_SMP
 	P(se->avg.runnable_avg_sum);
 	P(se->avg.runnable_avg_period);
+	P(se->avg.load_avg_contrib);
 #endif
 #undef PN
 #undef P
@@ -224,6 +225,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->load_contribution);
 	SEQ_printf(m, "  .%-30s: %d\n", "load_tg",
 			atomic_read(&cfs_rq->tg->load_weight));
+	SEQ_printf(m, "  .%-30s: %lld\n", "runnable_load_avg",
+			cfs_rq->runnable_load_avg);
 #endif
 
 	print_cfs_group_stats(m, cpu, cfs_rq->tg);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8c5468fcf10d..77af759e5675 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1081,20 +1081,63 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 	return decayed;
 }
 
+/* Compute the current contribution to load_avg by se, return any delta */
+static long __update_entity_load_avg_contrib(struct sched_entity *se)
+{
+	long old_contrib = se->avg.load_avg_contrib;
+
+	if (!entity_is_task(se))
+		return 0;
+
+	se->avg.load_avg_contrib = div64_u64(se->avg.runnable_avg_sum *
+					     se->load.weight,
+					     se->avg.runnable_avg_period + 1);
+
+	return se->avg.load_avg_contrib - old_contrib;
+}
+
 /* Update a sched_entity's runnable average */
 static inline void update_entity_load_avg(struct sched_entity *se)
 {
-	__update_entity_runnable_avg(rq_of(cfs_rq_of(se))->clock_task, &se->avg,
-				     se->on_rq);
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	long contrib_delta;
+
+	if (!__update_entity_runnable_avg(rq_of(cfs_rq)->clock_task, &se->avg,
+					  se->on_rq))
+		return;
+
+	contrib_delta = __update_entity_load_avg_contrib(se);
+	if (se->on_rq)
+		cfs_rq->runnable_load_avg += contrib_delta;
 }
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 {
 	__update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable);
 }
+
+/* Add the load generated by se into cfs_rq's child load-average */
+static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
+						  struct sched_entity *se)
+{
+	update_entity_load_avg(se);
+	cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
+}
+
+/* Remove se's load from this cfs_rq child load-average */
+static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
+						  struct sched_entity *se)
+{
+	update_entity_load_avg(se);
+	cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib;
+}
 #else
 static inline void update_entity_load_avg(struct sched_entity *se) {}
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
+static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
+						  struct sched_entity *se) {}
+static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
+						  struct sched_entity *se) {}
 #endif
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -1223,7 +1266,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	update_curr(cfs_rq);
 	update_cfs_load(cfs_rq, 0);
-	update_entity_load_avg(se);
+	enqueue_entity_load_avg(cfs_rq, se);
 	account_entity_enqueue(cfs_rq, se);
 	update_cfs_shares(cfs_rq);
 
@@ -1298,7 +1341,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
-	update_entity_load_avg(se);
+	dequeue_entity_load_avg(cfs_rq, se);
 
 	update_stats_dequeue(cfs_rq, se);
 	if (flags & DEQUEUE_SLEEP) {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 14b571968713..e6539736af58 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -222,6 +222,15 @@ struct cfs_rq {
 	unsigned int nr_spread_over;
 #endif
 
+#ifdef CONFIG_SMP
+	/*
+	 * CFS Load tracking
+	 * Under CFS, load is tracked on a per-entity basis and aggregated up.
+	 * This allows for the description of both thread and group usage (in
+	 * the FAIR_GROUP_SCHED case).
+	 */
+	u64 runnable_load_avg;
+#endif
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	struct rq *rq;	/* cpu runqueue to which this cfs_rq is attached */
 
@@ -1214,4 +1223,3 @@ static inline u64 irq_time_read(int cpu)
 }
 #endif /* CONFIG_64BIT */
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-- 
cgit v1.2.3-55-g7522


From 9ee474f55664ff63111c843099d365e7ecffb56f Mon Sep 17 00:00:00 2001
From: Paul Turner
Date: Thu, 4 Oct 2012 13:18:30 +0200
Subject: sched: Maintain the load contribution of blocked entities

We are currently maintaining:

  runnable_load(cfs_rq) = \Sum task_load(t)

For all running children t of cfs_rq.  While this can be naturally updated for
tasks in a runnable state (as they are scheduled); this does not account for
the load contributed by blocked task entities.

This can be solved by introducing a separate accounting for blocked load:

  blocked_load(cfs_rq) = \Sum runnable(b) * weight(b)

Obviously we do not want to iterate over all blocked entities to account for
their decay, we instead observe that:

  runnable_load(t) = \Sum p_i*y^i

and that to account for an additional idle period we only need to compute:

  y*runnable_load(t).

This means that we can compute all blocked entities at once by evaluating:

  blocked_load(cfs_rq)` = y * blocked_load(cfs_rq)

Finally we maintain a decay counter so that when a sleeping entity re-awakens
we can determine how much of its load should be removed from the blocked sum.

Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20120823141506.585389902@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |   1 +
 kernel/sched/core.c   |   1 -
 kernel/sched/debug.c  |   3 ++
 kernel/sched/fair.c   | 128 +++++++++++++++++++++++++++++++++++++++++++++-----
 kernel/sched/sched.h  |   4 +-
 5 files changed, 122 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 81d8b1ba4100..b1831accfd89 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1103,6 +1103,7 @@ struct sched_avg {
 	 */
 	u32 runnable_avg_sum, runnable_avg_period;
 	u64 last_runnable_update;
+	s64 decay_count;
 	unsigned long load_avg_contrib;
 };
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fd9d0859350a..00898f1fb69e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1528,7 +1528,6 @@ static void __sched_fork(struct task_struct *p)
 	p->se.avg.runnable_avg_period = 0;
 	p->se.avg.runnable_avg_sum = 0;
 #endif
-
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index c953a89f94aa..2d2e2b3c1bef 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -95,6 +95,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	P(se->avg.runnable_avg_sum);
 	P(se->avg.runnable_avg_period);
 	P(se->avg.load_avg_contrib);
+	P(se->avg.decay_count);
 #endif
 #undef PN
 #undef P
@@ -227,6 +228,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			atomic_read(&cfs_rq->tg->load_weight));
 	SEQ_printf(m, "  .%-30s: %lld\n", "runnable_load_avg",
 			cfs_rq->runnable_load_avg);
+	SEQ_printf(m, "  .%-30s: %lld\n", "blocked_load_avg",
+			cfs_rq->blocked_load_avg);
 #endif
 
 	print_cfs_group_stats(m, cpu, cfs_rq->tg);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 77af759e5675..83194175e841 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -259,6 +259,8 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
 	return grp->my_q;
 }
 
+static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq);
+
 static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	if (!cfs_rq->on_list) {
@@ -278,6 +280,8 @@ static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 		}
 
 		cfs_rq->on_list = 1;
+		/* We should have no load, but we need to update last_decay. */
+		update_cfs_rq_blocked_load(cfs_rq);
 	}
 }
 
@@ -1081,6 +1085,20 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 	return decayed;
 }
 
+/* Synchronize an entity's decay with its parenting cfs_rq.*/
+static inline void __synchronize_entity_decay(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	u64 decays = atomic64_read(&cfs_rq->decay_counter);
+
+	decays -= se->avg.decay_count;
+	if (!decays)
+		return;
+
+	se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
+	se->avg.decay_count = 0;
+}
+
 /* Compute the current contribution to load_avg by se, return any delta */
 static long __update_entity_load_avg_contrib(struct sched_entity *se)
 {
@@ -1096,8 +1114,18 @@ static long __update_entity_load_avg_contrib(struct sched_entity *se)
 	return se->avg.load_avg_contrib - old_contrib;
 }
 
+static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq,
+						 long load_contrib)
+{
+	if (likely(load_contrib < cfs_rq->blocked_load_avg))
+		cfs_rq->blocked_load_avg -= load_contrib;
+	else
+		cfs_rq->blocked_load_avg = 0;
+}
+
 /* Update a sched_entity's runnable average */
-static inline void update_entity_load_avg(struct sched_entity *se)
+static inline void update_entity_load_avg(struct sched_entity *se,
+					  int update_cfs_rq)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	long contrib_delta;
@@ -1107,8 +1135,34 @@ static inline void update_entity_load_avg(struct sched_entity *se)
 		return;
 
 	contrib_delta = __update_entity_load_avg_contrib(se);
+
+	if (!update_cfs_rq)
+		return;
+
 	if (se->on_rq)
 		cfs_rq->runnable_load_avg += contrib_delta;
+	else
+		subtract_blocked_load_contrib(cfs_rq, -contrib_delta);
+}
+
+/*
+ * Decay the load contributed by all blocked children and account this so that
+ * their contribution may appropriately discounted when they wake up.
+ */
+static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq)
+{
+	u64 now = rq_of(cfs_rq)->clock_task >> 20;
+	u64 decays;
+
+	decays = now - cfs_rq->last_decay;
+	if (!decays)
+		return;
+
+	cfs_rq->blocked_load_avg = decay_load(cfs_rq->blocked_load_avg,
+					      decays);
+	atomic64_add(decays, &cfs_rq->decay_counter);
+
+	cfs_rq->last_decay = now;
 }
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
@@ -1118,26 +1172,53 @@ static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 
 /* Add the load generated by se into cfs_rq's child load-average */
 static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
-						  struct sched_entity *se)
+						  struct sched_entity *se,
+						  int wakeup)
 {
-	update_entity_load_avg(se);
+	/* we track migrations using entity decay_count == 0 */
+	if (unlikely(!se->avg.decay_count)) {
+		se->avg.last_runnable_update = rq_of(cfs_rq)->clock_task;
+		wakeup = 0;
+	} else {
+		__synchronize_entity_decay(se);
+	}
+
+	if (wakeup)
+		subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib);
+
+	update_entity_load_avg(se, 0);
 	cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
+	update_cfs_rq_blocked_load(cfs_rq);
 }
 
-/* Remove se's load from this cfs_rq child load-average */
+/*
+ * Remove se's load from this cfs_rq child load-average, if the entity is
+ * transitioning to a blocked state we track its projected decay using
+ * blocked_load_avg.
+ */
 static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
-						  struct sched_entity *se)
+						  struct sched_entity *se,
+						  int sleep)
 {
-	update_entity_load_avg(se);
+	update_entity_load_avg(se, 1);
+
 	cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib;
+	if (sleep) {
+		cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
+		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
+	} /* migrations, e.g. sleep=0 leave decay_count == 0 */
 }
 #else
-static inline void update_entity_load_avg(struct sched_entity *se) {}
+static inline void update_entity_load_avg(struct sched_entity *se,
+					  int update_cfs_rq) {}
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
 static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
-						  struct sched_entity *se) {}
+					   struct sched_entity *se,
+					   int wakeup) {}
 static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
-						  struct sched_entity *se) {}
+					   struct sched_entity *se,
+					   int sleep) {}
+static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq) {}
 #endif
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -1266,7 +1347,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	update_curr(cfs_rq);
 	update_cfs_load(cfs_rq, 0);
-	enqueue_entity_load_avg(cfs_rq, se);
+	enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);
 	account_entity_enqueue(cfs_rq, se);
 	update_cfs_shares(cfs_rq);
 
@@ -1341,7 +1422,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
-	dequeue_entity_load_avg(cfs_rq, se);
+	dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP);
 
 	update_stats_dequeue(cfs_rq, se);
 	if (flags & DEQUEUE_SLEEP) {
@@ -1512,7 +1593,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 		/* Put 'current' back into the tree. */
 		__enqueue_entity(cfs_rq, prev);
 		/* in !on_rq case, update occurred at dequeue */
-		update_entity_load_avg(prev);
+		update_entity_load_avg(prev, 1);
 	}
 	cfs_rq->curr = NULL;
 }
@@ -1528,7 +1609,8 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	/*
 	 * Ensure that runnable average is periodically updated.
 	 */
-	update_entity_load_avg(curr);
+	update_entity_load_avg(curr, 1);
+	update_cfs_rq_blocked_load(cfs_rq);
 
 	/*
 	 * Update share accounting for long-running entities.
@@ -2387,6 +2469,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		update_cfs_load(cfs_rq, 0);
 		update_cfs_shares(cfs_rq);
+		update_entity_load_avg(se, 1);
 	}
 
 	if (!se) {
@@ -2448,6 +2531,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		update_cfs_load(cfs_rq, 0);
 		update_cfs_shares(cfs_rq);
+		update_entity_load_avg(se, 1);
 	}
 
 	if (!se) {
@@ -3498,6 +3582,7 @@ static int update_shares_cpu(struct task_group *tg, int cpu)
 
 	update_rq_clock(rq);
 	update_cfs_load(cfs_rq, 1);
+	update_cfs_rq_blocked_load(cfs_rq);
 
 	/*
 	 * We need to update shares after updating tg->load_weight in
@@ -5232,6 +5317,20 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 		place_entity(cfs_rq, se, 0);
 		se->vruntime -= cfs_rq->min_vruntime;
 	}
+
+#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
+	/*
+	* Remove our load from contribution when we leave sched_fair
+	* and ensure we don't carry in an old decay_count if we
+	* switch back.
+	*/
+	if (p->se.avg.decay_count) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(&p->se);
+		__synchronize_entity_decay(&p->se);
+		subtract_blocked_load_contrib(cfs_rq,
+				p->se.avg.load_avg_contrib);
+	}
+#endif
 }
 
 /*
@@ -5278,6 +5377,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 #ifndef CONFIG_64BIT
 	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
 #endif
+#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
+	atomic64_set(&cfs_rq->decay_counter, 1);
+#endif
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e6539736af58..664ff39195f7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -229,7 +229,9 @@ struct cfs_rq {
 	 * This allows for the description of both thread and group usage (in
 	 * the FAIR_GROUP_SCHED case).
 	 */
-	u64 runnable_load_avg;
+	u64 runnable_load_avg, blocked_load_avg;
+	atomic64_t decay_counter;
+	u64 last_decay;
 #endif
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	struct rq *rq;	/* cpu runqueue to which this cfs_rq is attached */
-- 
cgit v1.2.3-55-g7522


From 0a74bef8bed18dc6889e9bc37ea1050a50c86c89 Mon Sep 17 00:00:00 2001
From: Paul Turner
Date: Thu, 4 Oct 2012 13:18:30 +0200
Subject: sched: Add an rq migration call-back to sched_class

Since we are now doing bottom up load accumulation we need explicit
notification when a task has been re-parented so that the old hierarchy can be
updated.

Adds: migrate_task_rq(struct task_struct *p, int next_cpu)

(The alternative is to do this out of __set_task_cpu, but it was suggested that
this would be a cleaner encapsulation.)

Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20120823141506.660023400@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  1 +
 kernel/sched/core.c   |  2 ++
 kernel/sched/fair.c   | 12 ++++++++++++
 3 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b1831accfd89..e483ccb08ce6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1061,6 +1061,7 @@ struct sched_class {
 
 #ifdef CONFIG_SMP
 	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
+	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
 
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 00898f1fb69e..f26860074ef2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -952,6 +952,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	trace_sched_migrate_task(p, new_cpu);
 
 	if (task_cpu(p) != new_cpu) {
+		if (p->sched_class->migrate_task_rq)
+			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
 		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 83194175e841..5e602e6ba0c3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3047,6 +3047,17 @@ unlock:
 
 	return new_cpu;
 }
+
+/*
+ * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
+ * cfs_rq_of(p) references at time of call are still valid and identify the
+ * previous cpu.  However, the caller only guarantees p->pi_lock is held; no
+ * other assumptions, including the state of rq->lock, should be made.
+ */
+static void
+migrate_task_rq_fair(struct task_struct *p, int next_cpu)
+{
+}
 #endif /* CONFIG_SMP */
 
 static unsigned long
@@ -5607,6 +5618,7 @@ const struct sched_class fair_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_fair,
+	.migrate_task_rq	= migrate_task_rq_fair,
 
 	.rq_online		= rq_online_fair,
 	.rq_offline		= rq_offline_fair,
-- 
cgit v1.2.3-55-g7522


From f4e26b120b9de84cb627bc7361ba43cfdc51341f Mon Sep 17 00:00:00 2001
From: Paul Turner
Date: Thu, 4 Oct 2012 13:18:32 +0200
Subject: sched: Introduce temporary FAIR_GROUP_SCHED dependency for
 load-tracking

While per-entity load-tracking is generally useful, beyond computing shares
distribution, e.g. runnable based load-balance (in progress), governors,
power-management, etc.

These facilities are not yet consumers of this data.  This may be trivially
reverted when the information is required; but avoid paying the overhead for
calculations we will not use until then.

Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20120823141507.422162369@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  8 +++++++-
 kernel/sched/core.c   |  7 ++++++-
 kernel/sched/fair.c   | 13 +++++++++++--
 kernel/sched/sched.h  |  9 ++++++++-
 4 files changed, 32 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e483ccb08ce6..e1581a029e3d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1168,7 +1168,13 @@ struct sched_entity {
 	/* rq "owned" by this entity/group: */
 	struct cfs_rq		*my_q;
 #endif
-#ifdef CONFIG_SMP
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+	/* Per-entity load-tracking */
 	struct sched_avg	avg;
 #endif
 };
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f26860074ef2..5dae0d252ff7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1526,7 +1526,12 @@ static void __sched_fork(struct task_struct *p)
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
-#ifdef CONFIG_SMP
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
 	p->se.avg.runnable_avg_period = 0;
 	p->se.avg.runnable_avg_sum = 0;
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6ecf455fd95b..3e6a3531fa90 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -882,7 +882,8 @@ static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-#ifdef CONFIG_SMP
+/* Only depends on SMP, FAIR_GROUP_SCHED may be removed when useful in lb */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
 /*
  * We choose a half-life close to 1 scheduling period.
  * Note: The tables below are dependent on this value.
@@ -3173,6 +3174,12 @@ unlock:
 	return new_cpu;
 }
 
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#ifdef CONFIG_FAIR_GROUP_SCHED
 /*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
@@ -3196,6 +3203,7 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu)
 		atomic64_add(se->avg.load_avg_contrib, &cfs_rq->removed_load);
 	}
 }
+#endif
 #endif /* CONFIG_SMP */
 
 static unsigned long
@@ -5773,8 +5781,9 @@ const struct sched_class fair_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_fair,
+#ifdef CONFIG_FAIR_GROUP_SCHED
 	.migrate_task_rq	= migrate_task_rq_fair,
-
+#endif
 	.rq_online		= rq_online_fair,
 	.rq_offline		= rq_offline_fair,
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0a75a430ca77..5eca173b563f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -225,6 +225,12 @@ struct cfs_rq {
 #endif
 
 #ifdef CONFIG_SMP
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#ifdef CONFIG_FAIR_GROUP_SCHED
 	/*
 	 * CFS Load tracking
 	 * Under CFS, load is tracked on a per-entity basis and aggregated up.
@@ -234,7 +240,8 @@ struct cfs_rq {
 	u64 runnable_load_avg, blocked_load_avg;
 	atomic64_t decay_counter, removed_load;
 	u64 last_decay;
-
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+/* These always depend on CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	u32 tg_runnable_contrib;
 	u64 tg_load_contrib;
-- 
cgit v1.2.3-55-g7522


From 1b4f59e356cc94929305bd107b7f38eec62715ad Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Mon, 22 Oct 2012 18:05:36 +0400
Subject: slub: Commonize slab_cache field in struct page

Right now, slab and slub have fields in struct page to derive which
cache a page belongs to, but they do it slightly differently.

slab uses a field called slab_cache, that lives in the third double
word. slub, uses a field called "slab", living outside of the
doublewords area.

Ideally, we could use the same field for this. Since slub heavily makes
use of the doubleword region, there isn't really much room to move
slub's slab_cache field around. Since slab does not have such strict
placement restrictions, we can move it outside the doubleword area.

The naming used by slab, "slab_cache", is less confusing, and it is
preferred over slub's generic "slab".

Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Christoph Lameter <cl@linux.com>
CC: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
---
 include/linux/mm_types.h |  7 ++-----
 mm/slub.c                | 24 ++++++++++++------------
 2 files changed, 14 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 31f8a3af7d94..2fef4e720e79 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -128,10 +128,7 @@ struct page {
 		};
 
 		struct list_head list;	/* slobs list of pages */
-		struct {		/* slab fields */
-			struct kmem_cache *slab_cache;
-			struct slab *slab_page;
-		};
+		struct slab *slab_page; /* slab fields */
 	};
 
 	/* Remainder is not double word aligned */
@@ -146,7 +143,7 @@ struct page {
 #if USE_SPLIT_PTLOCKS
 		spinlock_t ptl;
 #endif
-		struct kmem_cache *slab;	/* SLUB: Pointer to slab */
+		struct kmem_cache *slab_cache;	/* SL[AU]B: Pointer to slab */
 		struct page *first_page;	/* Compound tail pages */
 	};
 
diff --git a/mm/slub.c b/mm/slub.c
index 16274b273c61..35483e0ab6bc 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1092,11 +1092,11 @@ static noinline struct kmem_cache_node *free_debug_processing(
 	if (!check_object(s, page, object, SLUB_RED_ACTIVE))
 		goto out;
 
-	if (unlikely(s != page->slab)) {
+	if (unlikely(s != page->slab_cache)) {
 		if (!PageSlab(page)) {
 			slab_err(s, page, "Attempt to free object(0x%p) "
 				"outside of slab", object);
-		} else if (!page->slab) {
+		} else if (!page->slab_cache) {
 			printk(KERN_ERR
 				"SLUB <none>: no slab for object 0x%p.\n",
 						object);
@@ -1357,7 +1357,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 		goto out;
 
 	inc_slabs_node(s, page_to_nid(page), page->objects);
-	page->slab = s;
+	page->slab_cache = s;
 	__SetPageSlab(page);
 	if (page->pfmemalloc)
 		SetPageSlabPfmemalloc(page);
@@ -1424,7 +1424,7 @@ static void rcu_free_slab(struct rcu_head *h)
 	else
 		page = container_of((struct list_head *)h, struct page, lru);
 
-	__free_slab(page->slab, page);
+	__free_slab(page->slab_cache, page);
 }
 
 static void free_slab(struct kmem_cache *s, struct page *page)
@@ -2617,9 +2617,9 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 
 	page = virt_to_head_page(x);
 
-	if (kmem_cache_debug(s) && page->slab != s) {
+	if (kmem_cache_debug(s) && page->slab_cache != s) {
 		pr_err("kmem_cache_free: Wrong slab cache. %s but object"
-			" is from  %s\n", page->slab->name, s->name);
+			" is from  %s\n", page->slab_cache->name, s->name);
 		WARN_ON_ONCE(1);
 		return;
 	}
@@ -3418,7 +3418,7 @@ size_t ksize(const void *object)
 		return PAGE_SIZE << compound_order(page);
 	}
 
-	return slab_ksize(page->slab);
+	return slab_ksize(page->slab_cache);
 }
 EXPORT_SYMBOL(ksize);
 
@@ -3443,8 +3443,8 @@ bool verify_mem_not_deleted(const void *x)
 	}
 
 	slab_lock(page);
-	if (on_freelist(page->slab, page, object)) {
-		object_err(page->slab, page, object, "Object is on free-list");
+	if (on_freelist(page->slab_cache, page, object)) {
+		object_err(page->slab_cache, page, object, "Object is on free-list");
 		rv = false;
 	} else {
 		rv = true;
@@ -3475,7 +3475,7 @@ void kfree(const void *x)
 		__free_pages(page, compound_order(page));
 		return;
 	}
-	slab_free(page->slab, page, object, _RET_IP_);
+	slab_free(page->slab_cache, page, object, _RET_IP_);
 }
 EXPORT_SYMBOL(kfree);
 
@@ -3686,11 +3686,11 @@ static void __init kmem_cache_bootstrap_fixup(struct kmem_cache *s)
 
 		if (n) {
 			list_for_each_entry(p, &n->partial, lru)
-				p->slab = s;
+				p->slab_cache = s;
 
 #ifdef CONFIG_SLUB_DEBUG
 			list_for_each_entry(p, &n->full, lru)
-				p->slab = s;
+				p->slab_cache = s;
 #endif
 		}
 	}
-- 
cgit v1.2.3-55-g7522


From 8fa19098ebc700f14b0f8d0fb957e7748e14c44b Mon Sep 17 00:00:00 2001
From: Johan Hedberg
Date: Fri, 19 Oct 2012 20:57:49 +0300
Subject: Bluetooth: Read adversiting channel TX power during init sequence

This patch adds the reading of the LE advertising channel TX power to
the HCI init sequence of LE-capable controllers. This data will be used
e.g. for inclusion in the advertising data packets when advertising is
enabled.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h      |  6 ++++++
 include/net/bluetooth/hci_core.h |  2 ++
 net/bluetooth/hci_event.c        | 20 ++++++++++++++++++++
 3 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 88cbbda61027..348f4bfeaadb 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -932,6 +932,12 @@ struct hci_rp_le_read_buffer_size {
 	__u8     le_max_pkt;
 } __packed;
 
+#define HCI_OP_LE_READ_ADV_TX_POWER	0x2007
+struct hci_rp_le_read_adv_tx_power {
+	__u8	status;
+	__s8	tx_power;
+} __packed;
+
 #define HCI_OP_LE_SET_SCAN_PARAM	0x200b
 struct hci_cp_le_set_scan_param {
 	__u8    type;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 00abc5246cbf..5ab80b7e8369 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -278,6 +278,8 @@ struct hci_dev {
 	struct work_struct	le_scan;
 	struct le_scan_params	le_scan_params;
 
+	__s8			adv_tx_power;
+
 	int (*open)(struct hci_dev *hdev);
 	int (*close)(struct hci_dev *hdev);
 	int (*flush)(struct hci_dev *hdev);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 78f1af52ed81..fd5a51ccb8e4 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -594,6 +594,9 @@ static void le_init(struct hci_dev *hdev)
 {
 	/* Read LE Buffer Size */
 	hci_send_cmd(hdev, HCI_OP_LE_READ_BUFFER_SIZE, 0, NULL);
+
+	/* Read LE Advertising Channel TX Power */
+	hci_send_cmd(hdev, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL);
 }
 
 static void hci_setup(struct hci_dev *hdev)
@@ -1073,6 +1076,19 @@ static void hci_cc_le_read_buffer_size(struct hci_dev *hdev,
 	hci_req_complete(hdev, HCI_OP_LE_READ_BUFFER_SIZE, rp->status);
 }
 
+static void hci_cc_le_read_adv_tx_power(struct hci_dev *hdev,
+					struct sk_buff *skb)
+{
+	struct hci_rp_le_read_adv_tx_power *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (!rp->status)
+		hdev->adv_tx_power = rp->tx_power;
+
+	hci_req_complete(hdev, HCI_OP_LE_READ_ADV_TX_POWER, rp->status);
+}
+
 static void hci_cc_le_set_event_mask(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 status = *((__u8 *) skb->data);
@@ -2505,6 +2521,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_le_read_buffer_size(hdev, skb);
 		break;
 
+	case HCI_OP_LE_READ_ADV_TX_POWER:
+		hci_cc_le_read_adv_tx_power(hdev, skb);
+		break;
+
 	case HCI_OP_LE_SET_EVENT_MASK:
 		hci_cc_le_set_event_mask(hdev, skb);
 		break;
-- 
cgit v1.2.3-55-g7522


From 6c9c6d6301287e369a754d628230fa6e50cdb74b Mon Sep 17 00:00:00 2001
From: Shuah Khan
Date: Mon, 8 Oct 2012 11:08:06 -0600
Subject: dma-debug: New interfaces to debug dma mapping errors

Add dma-debug interface debug_dma_mapping_error() to debug
drivers that fail to check dma mapping errors on addresses
returned by dma_map_single() and dma_map_page() interfaces.
This interface clears a flag set by debug_dma_map_page() to
indicate that dma_mapping_error() has been called by the
driver. When driver does unmap, debug_dma_unmap() checks the
flag and if this flag is still set, prints warning message
that includes call trace that leads up to the unmap. This
interface can be called from dma_mapping_error() routines to
enable dma mapping error check debugging.

Tested: Intel iommu and swiotlb (iommu=soft) on x86-64 with
        CONFIG_DMA_API_DEBUG enabled and disabled.

Signed-off-by: Shuah Khan <shuah.khan@hp.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 Documentation/DMA-API.txt          | 12 +++++++
 arch/x86/include/asm/dma-mapping.h |  1 +
 include/linux/dma-debug.h          |  7 ++++
 lib/dma-debug.c                    | 71 +++++++++++++++++++++++++++++++++++---
 4 files changed, 87 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 66bd97a95f10..78a6c569d204 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -678,3 +678,15 @@ out of dma_debug_entries. These entries are preallocated at boot. The number
 of preallocated entries is defined per architecture. If it is too low for you
 boot with 'dma_debug_entries=<your_desired_number>' to overwrite the
 architectural default.
+
+void debug_dmap_mapping_error(struct device *dev, dma_addr_t dma_addr);
+
+dma-debug interface debug_dma_mapping_error() to debug drivers that fail
+to check dma mapping errors on addresses returned by dma_map_single() and
+dma_map_page() interfaces. This interface clears a flag set by
+debug_dma_map_page() to indicate that dma_mapping_error() has been called by
+the driver. When driver does unmap, debug_dma_unmap() checks the flag and if
+this flag is still set, prints warning message that includes call trace that
+leads up to the unmap. This interface can be called from dma_mapping_error()
+routines to enable dma mapping error check debugging.
+
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index f7b4c7903e7e..808dae63eeea 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -47,6 +47,7 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
+	debug_dma_mapping_error(dev, dma_addr);
 	if (ops->mapping_error)
 		return ops->mapping_error(dev, dma_addr);
 
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
index 171ad8aedc83..fc0e34ce038f 100644
--- a/include/linux/dma-debug.h
+++ b/include/linux/dma-debug.h
@@ -39,6 +39,8 @@ extern void debug_dma_map_page(struct device *dev, struct page *page,
 			       int direction, dma_addr_t dma_addr,
 			       bool map_single);
 
+extern void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
+
 extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
 				 size_t size, int direction, bool map_single);
 
@@ -105,6 +107,11 @@ static inline void debug_dma_map_page(struct device *dev, struct page *page,
 {
 }
 
+static inline void debug_dma_mapping_error(struct device *dev,
+					  dma_addr_t dma_addr)
+{
+}
+
 static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
 					size_t size, int direction,
 					bool map_single)
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index d84beb994f36..59f4a1a8187d 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -45,6 +45,12 @@ enum {
 	dma_debug_coherent,
 };
 
+enum map_err_types {
+	MAP_ERR_CHECK_NOT_APPLICABLE,
+	MAP_ERR_NOT_CHECKED,
+	MAP_ERR_CHECKED,
+};
+
 #define DMA_DEBUG_STACKTRACE_ENTRIES 5
 
 struct dma_debug_entry {
@@ -57,6 +63,7 @@ struct dma_debug_entry {
 	int              direction;
 	int		 sg_call_ents;
 	int		 sg_mapped_ents;
+	enum map_err_types  map_err_type;
 #ifdef CONFIG_STACKTRACE
 	struct		 stack_trace stacktrace;
 	unsigned long	 st_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
@@ -114,6 +121,12 @@ static struct device_driver *current_driver                    __read_mostly;
 
 static DEFINE_RWLOCK(driver_name_lock);
 
+static const char *const maperr2str[] = {
+	[MAP_ERR_CHECK_NOT_APPLICABLE] = "dma map error check not applicable",
+	[MAP_ERR_NOT_CHECKED] = "dma map error not checked",
+	[MAP_ERR_CHECKED] = "dma map error checked",
+};
+
 static const char *type2name[4] = { "single", "page",
 				    "scather-gather", "coherent" };
 
@@ -376,11 +389,12 @@ void debug_dma_dump_mappings(struct device *dev)
 		list_for_each_entry(entry, &bucket->list, list) {
 			if (!dev || dev == entry->dev) {
 				dev_info(entry->dev,
-					 "%s idx %d P=%Lx D=%Lx L=%Lx %s\n",
+					 "%s idx %d P=%Lx D=%Lx L=%Lx %s %s\n",
 					 type2name[entry->type], idx,
 					 (unsigned long long)entry->paddr,
 					 entry->dev_addr, entry->size,
-					 dir2name[entry->direction]);
+					 dir2name[entry->direction],
+					 maperr2str[entry->map_err_type]);
 			}
 		}
 
@@ -838,13 +852,28 @@ static __init int dma_debug_entries_cmdline(char *str)
 __setup("dma_debug=", dma_debug_cmdline);
 __setup("dma_debug_entries=", dma_debug_entries_cmdline);
 
+/* Calling dma_mapping_error() from dma-debug api will result in calling
+   debug_dma_mapping_error() - need internal mapping error routine to
+   avoid debug checks */
+#ifndef DMA_ERROR_CODE
+#define DMA_ERROR_CODE 0
+#endif
+static inline int has_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	if (ops->mapping_error)
+		return ops->mapping_error(dev, dma_addr);
+
+	return (dma_addr == DMA_ERROR_CODE);
+}
+
 static void check_unmap(struct dma_debug_entry *ref)
 {
 	struct dma_debug_entry *entry;
 	struct hash_bucket *bucket;
 	unsigned long flags;
 
-	if (dma_mapping_error(ref->dev, ref->dev_addr)) {
+	if (unlikely(has_mapping_error(ref->dev, ref->dev_addr))) {
 		err_printk(ref->dev, NULL, "DMA-API: device driver tries "
 			   "to free an invalid DMA memory address\n");
 		return;
@@ -910,6 +939,15 @@ static void check_unmap(struct dma_debug_entry *ref)
 			   dir2name[ref->direction]);
 	}
 
+	if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
+		err_printk(ref->dev, entry,
+			   "DMA-API: device driver failed to check map error"
+			   "[device address=0x%016llx] [size=%llu bytes] "
+			   "[mapped as %s]",
+			   ref->dev_addr, ref->size,
+			   type2name[entry->type]);
+	}
+
 	hash_bucket_del(entry);
 	dma_entry_free(entry);
 
@@ -1017,7 +1055,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 	if (unlikely(global_disable))
 		return;
 
-	if (unlikely(dma_mapping_error(dev, dma_addr)))
+	if (unlikely(has_mapping_error(dev, dma_addr)))
 		return;
 
 	entry = dma_entry_alloc();
@@ -1030,6 +1068,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 	entry->dev_addr  = dma_addr;
 	entry->size      = size;
 	entry->direction = direction;
+	entry->map_err_type = MAP_ERR_NOT_CHECKED;
 
 	if (map_single)
 		entry->type = dma_debug_single;
@@ -1045,6 +1084,30 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 }
 EXPORT_SYMBOL(debug_dma_map_page);
 
+void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	struct dma_debug_entry ref;
+	struct dma_debug_entry *entry;
+	struct hash_bucket *bucket;
+	unsigned long flags;
+
+	if (unlikely(global_disable))
+		return;
+
+	ref.dev = dev;
+	ref.dev_addr = dma_addr;
+	bucket = get_hash_bucket(&ref, &flags);
+	entry = bucket_find_exact(bucket, &ref);
+
+	if (!entry)
+		goto out;
+
+	entry->map_err_type = MAP_ERR_CHECKED;
+out:
+	put_hash_bucket(bucket, &flags);
+}
+EXPORT_SYMBOL(debug_dma_mapping_error);
+
 void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
 			  size_t size, int direction, bool map_single)
 {
-- 
cgit v1.2.3-55-g7522


From c30186e51e537d3ae8b1134983c1a5b4db3a8840 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman
Date: Wed, 24 Oct 2012 14:19:16 -0700
Subject: USB: ezusb: unexport some functions that aren't being used

When the ezusb code was split out, support was added for the fx2 chip
type, but no one is using these functions, so comment it out.  If
someone needs it, it can be added back in the future.

Also properly include <linux/usb/ezusb.h> into the ezusb.c file, to
ensure we catch any function prototype mis-matches

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Cc: René Bürgel <rene.buergel@sohard.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/ezusb.c  | 39 ++++++++++++++++++++++-----------------
 include/linux/usb/ezusb.h |  8 --------
 2 files changed, 22 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/misc/ezusb.c b/drivers/usb/misc/ezusb.c
index 4223d761223d..0a48de91df3a 100644
--- a/drivers/usb/misc/ezusb.c
+++ b/drivers/usb/misc/ezusb.c
@@ -15,6 +15,7 @@
 #include <linux/usb.h>
 #include <linux/firmware.h>
 #include <linux/ihex.h>
+#include <linux/usb/ezusb.h>
 
 struct ezusb_fx_type {
 	/* EZ-USB Control and Status Register.  Bit 0 controls 8051 reset */
@@ -22,21 +23,16 @@ struct ezusb_fx_type {
 	unsigned short max_internal_adress;
 };
 
-struct ezusb_fx_type ezusb_fx1 = {
+static struct ezusb_fx_type ezusb_fx1 = {
 	.cpucs_reg = 0x7F92,
 	.max_internal_adress = 0x1B3F,
 };
 
-struct ezusb_fx_type ezusb_fx2 = {
-	.cpucs_reg = 0xE600,
-	.max_internal_adress = 0x3FFF,
-};
-
 /* Commands for writing to memory */
 #define WRITE_INT_RAM 0xA0
 #define WRITE_EXT_RAM 0xA3
 
-int ezusb_writememory(struct usb_device *dev, int address,
+static int ezusb_writememory(struct usb_device *dev, int address,
 				unsigned char *data, int length, __u8 request)
 {
 	int result;
@@ -58,10 +54,9 @@ int ezusb_writememory(struct usb_device *dev, int address,
 	kfree(transfer_buffer);
 	return result;
 }
-EXPORT_SYMBOL_GPL(ezusb_writememory);
 
-int ezusb_set_reset(struct usb_device *dev, unsigned short cpucs_reg,
-			 unsigned char reset_bit)
+static int ezusb_set_reset(struct usb_device *dev, unsigned short cpucs_reg,
+			   unsigned char reset_bit)
 {
 	int response = ezusb_writememory(dev, cpucs_reg, &reset_bit, 1, WRITE_INT_RAM);
 	if (response < 0)
@@ -76,12 +71,6 @@ int ezusb_fx1_set_reset(struct usb_device *dev, unsigned char reset_bit)
 }
 EXPORT_SYMBOL_GPL(ezusb_fx1_set_reset);
 
-int ezusb_fx2_set_reset(struct usb_device *dev, unsigned char reset_bit)
-{
-	return ezusb_set_reset(dev, ezusb_fx2.cpucs_reg, reset_bit);
-}
-EXPORT_SYMBOL_GPL(ezusb_fx2_set_reset);
-
 static int ezusb_ihex_firmware_download(struct usb_device *dev,
 					struct ezusb_fx_type fx,
 					const char *firmware_path)
@@ -151,10 +140,26 @@ int ezusb_fx1_ihex_firmware_download(struct usb_device *dev,
 }
 EXPORT_SYMBOL_GPL(ezusb_fx1_ihex_firmware_download);
 
+#if 0
+/*
+ * Once someone one needs these fx2 functions, uncomment them
+ * and add them to ezusb.h and all should be good.
+ */
+static struct ezusb_fx_type ezusb_fx2 = {
+	.cpucs_reg = 0xE600,
+	.max_internal_adress = 0x3FFF,
+};
+
+int ezusb_fx2_set_reset(struct usb_device *dev, unsigned char reset_bit)
+{
+	return ezusb_set_reset(dev, ezusb_fx2.cpucs_reg, reset_bit);
+}
+EXPORT_SYMBOL_GPL(ezusb_fx2_set_reset);
+
 int ezusb_fx2_ihex_firmware_download(struct usb_device *dev,
 				     const char *firmware_path)
 {
 	return ezusb_ihex_firmware_download(dev, ezusb_fx2, firmware_path);
 }
 EXPORT_SYMBOL_GPL(ezusb_fx2_ihex_firmware_download);
-
+#endif
diff --git a/include/linux/usb/ezusb.h b/include/linux/usb/ezusb.h
index fc618d8d1e92..639ee45779fb 100644
--- a/include/linux/usb/ezusb.h
+++ b/include/linux/usb/ezusb.h
@@ -1,16 +1,8 @@
 #ifndef __EZUSB_H
 #define __EZUSB_H
 
-
-extern int ezusb_writememory(struct usb_device *dev, int address,
-			     unsigned char *data, int length, __u8 bRequest);
-
 extern int ezusb_fx1_set_reset(struct usb_device *dev, unsigned char reset_bit);
-extern int ezusb_fx2_set_reset(struct usb_device *dev, unsigned char reset_bit);
-
 extern int ezusb_fx1_ihex_firmware_download(struct usb_device *dev,
 					    const char *firmware_path);
-extern int ezusb_fx2_ihex_firmware_download(struct usb_device *dev,
-					    const char *firmware_path);
 
 #endif /* __EZUSB_H */
-- 
cgit v1.2.3-55-g7522


From e8c4a7acc9ec0ee82feedcdc3c6d0ee44d67918a Mon Sep 17 00:00:00 2001
From: Felipe Balbi
Date: Wed, 24 Oct 2012 14:26:19 -0700
Subject: ARM: OMAP: move OMAP USB platform data to
 <linux/platform_data/omap-usb.h>

In order to make single zImage work for ARM architecture,
we need to make sure we don't depend on private headers.

Move USB platform_data to <linux/platform_data/omap-usb.h>
and add a minimal drivers/mfd/usb-omap.h.

Cc: Samuel Ortiz <sameo@linux.intel.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Partha Basak <parthab@india.ti.com>
Cc: Keshava Munegowda <keshava_mgowda@ti.com>
Cc: linux-usb@vger.kernel.org
Signed-off-by: Felipe Balbi <balbi@ti.com>
[tony@atomide.com: updated for local mfd/usb-omap.h]
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/board-4430sdp.c    |  1 +
 arch/arm/mach-omap2/board-am3517evm.c  |  1 +
 arch/arm/mach-omap2/board-omap3evm.c   |  1 +
 arch/arm/mach-omap2/board-omap4panda.c |  1 +
 arch/arm/mach-omap2/board-rx51.c       |  1 +
 arch/arm/mach-omap2/board-ti8168evm.c  |  2 +
 arch/arm/mach-omap2/usb-tusb6010.c     |  1 +
 arch/arm/mach-omap2/usb.h              |  2 +-
 arch/arm/plat-omap/include/plat/usb.h  | 73 -------------------------------
 drivers/mfd/omap-usb-host.c            |  5 ++-
 drivers/mfd/omap-usb-tll.c             |  2 +-
 drivers/mfd/omap-usb.h                 |  2 +
 drivers/usb/host/ehci-omap.c           |  3 +-
 drivers/usb/host/ohci-omap3.c          |  1 -
 drivers/usb/musb/am35x.c               |  3 +-
 drivers/usb/musb/musb_dsps.c           |  3 +-
 drivers/usb/musb/omap2430.h            |  2 +-
 include/linux/platform_data/usb-omap.h | 80 ++++++++++++++++++++++++++++++++++
 18 files changed, 101 insertions(+), 83 deletions(-)
 delete mode 100644 arch/arm/plat-omap/include/plat/usb.h
 create mode 100644 drivers/mfd/omap-usb.h
 create mode 100644 include/linux/platform_data/usb-omap.h

(limited to 'include')

diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c
index 5700fc5b77a2..52534ba33984 100644
--- a/arch/arm/mach-omap2/board-4430sdp.c
+++ b/arch/arm/mach-omap2/board-4430sdp.c
@@ -27,6 +27,7 @@
 #include <linux/leds.h>
 #include <linux/leds_pwm.h>
 #include <linux/platform_data/omap4-keypad.h>
+#include <linux/usb/musb.h>
 
 #include <asm/hardware/gic.h>
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-omap2/board-am3517evm.c b/arch/arm/mach-omap2/board-am3517evm.c
index 0dbeb77aad68..96d6c5ab5d4c 100644
--- a/arch/arm/mach-omap2/board-am3517evm.c
+++ b/arch/arm/mach-omap2/board-am3517evm.c
@@ -25,6 +25,7 @@
 #include <linux/can/platform/ti_hecc.h>
 #include <linux/davinci_emac.h>
 #include <linux/mmc/host.h>
+#include <linux/usb/musb.h>
 #include <linux/platform_data/gpio-omap.h>
 
 #include "am35xx.h"
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index 6e7e69bf5c7e..a22a5b61db49 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -32,6 +32,7 @@
 #include <linux/spi/ads7846.h>
 #include <linux/i2c/twl.h>
 #include <linux/usb/otg.h>
+#include <linux/usb/musb.h>
 #include <linux/usb/nop-usb-xceiv.h>
 #include <linux/smsc911x.h>
 
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index 74e39bbb3ca3..3f0b92afd957 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -29,6 +29,7 @@
 #include <linux/regulator/machine.h>
 #include <linux/regulator/fixed.h>
 #include <linux/ti_wilink_st.h>
+#include <linux/usb/musb.h>
 #include <linux/wl12xx.h>
 #include <linux/platform_data/omap-abe-twl6040.h>
 
diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c
index 8c4d27ef160b..c2f8f6c16b8f 100644
--- a/arch/arm/mach-omap2/board-rx51.c
+++ b/arch/arm/mach-omap2/board-rx51.c
@@ -17,6 +17,7 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 #include <linux/leds.h>
+#include <linux/usb/musb.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-omap2/board-ti8168evm.c b/arch/arm/mach-omap2/board-ti8168evm.c
index 4977c77ce223..5e672c2b6a43 100644
--- a/arch/arm/mach-omap2/board-ti8168evm.c
+++ b/arch/arm/mach-omap2/board-ti8168evm.c
@@ -14,6 +14,8 @@
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/usb/musb.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-omap2/usb-tusb6010.c b/arch/arm/mach-omap2/usb-tusb6010.c
index 805bea6edf17..5e2428989c13 100644
--- a/arch/arm/mach-omap2/usb-tusb6010.c
+++ b/arch/arm/mach-omap2/usb-tusb6010.c
@@ -15,6 +15,7 @@
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
 #include <linux/export.h>
+#include <linux/platform_data/usb-omap.h>
 
 #include <linux/usb/musb.h>
 
diff --git a/arch/arm/mach-omap2/usb.h b/arch/arm/mach-omap2/usb.h
index b2c4ff15557e..9b986ead7c45 100644
--- a/arch/arm/mach-omap2/usb.h
+++ b/arch/arm/mach-omap2/usb.h
@@ -1,4 +1,4 @@
-#include <plat/usb.h>
+#include <linux/platform_data/usb-omap.h>
 
 /* AM35x */
 /* USB 2.0 PHY Control */
diff --git a/arch/arm/plat-omap/include/plat/usb.h b/arch/arm/plat-omap/include/plat/usb.h
deleted file mode 100644
index 1dd6522a0edd..000000000000
--- a/arch/arm/plat-omap/include/plat/usb.h
+++ /dev/null
@@ -1,73 +0,0 @@
-// include/asm-arm/mach-omap/usb.h
-
-#ifndef	__ASM_ARCH_OMAP_USB_H
-#define	__ASM_ARCH_OMAP_USB_H
-
-#include <linux/io.h>
-#include <linux/platform_device.h>
-#include <linux/usb/musb.h>
-
-#define OMAP3_HS_USB_PORTS	3
-
-enum usbhs_omap_port_mode {
-	OMAP_USBHS_PORT_MODE_UNUSED,
-	OMAP_EHCI_PORT_MODE_PHY,
-	OMAP_EHCI_PORT_MODE_TLL,
-	OMAP_EHCI_PORT_MODE_HSIC,
-	OMAP_OHCI_PORT_MODE_PHY_6PIN_DATSE0,
-	OMAP_OHCI_PORT_MODE_PHY_6PIN_DPDM,
-	OMAP_OHCI_PORT_MODE_PHY_3PIN_DATSE0,
-	OMAP_OHCI_PORT_MODE_PHY_4PIN_DPDM,
-	OMAP_OHCI_PORT_MODE_TLL_6PIN_DATSE0,
-	OMAP_OHCI_PORT_MODE_TLL_6PIN_DPDM,
-	OMAP_OHCI_PORT_MODE_TLL_3PIN_DATSE0,
-	OMAP_OHCI_PORT_MODE_TLL_4PIN_DPDM,
-	OMAP_OHCI_PORT_MODE_TLL_2PIN_DATSE0,
-	OMAP_OHCI_PORT_MODE_TLL_2PIN_DPDM
-};
-
-#ifdef CONFIG_ARCH_OMAP2PLUS
-
-struct ehci_hcd_omap_platform_data {
-	enum usbhs_omap_port_mode	port_mode[OMAP3_HS_USB_PORTS];
-	int				reset_gpio_port[OMAP3_HS_USB_PORTS];
-	struct regulator		*regulator[OMAP3_HS_USB_PORTS];
-	unsigned			phy_reset:1;
-};
-
-struct ohci_hcd_omap_platform_data {
-	enum usbhs_omap_port_mode	port_mode[OMAP3_HS_USB_PORTS];
-	unsigned			es2_compatibility:1;
-};
-
-struct usbhs_omap_platform_data {
-	enum usbhs_omap_port_mode		port_mode[OMAP3_HS_USB_PORTS];
-
-	struct ehci_hcd_omap_platform_data	*ehci_data;
-	struct ohci_hcd_omap_platform_data	*ohci_data;
-};
-
-struct usbtll_omap_platform_data {
-	enum usbhs_omap_port_mode		port_mode[OMAP3_HS_USB_PORTS];
-};
-/*-------------------------------------------------------------------------*/
-
-struct omap_musb_board_data {
-	u8	interface_type;
-	u8	mode;
-	u16	power;
-	unsigned extvbus:1;
-	void	(*set_phy_power)(u8 on);
-	void	(*clear_irq)(void);
-	void	(*set_mode)(u8 mode);
-	void	(*reset)(void);
-};
-
-enum musb_interface    {MUSB_INTERFACE_ULPI, MUSB_INTERFACE_UTMI};
-
-extern int omap_tll_enable(void);
-extern int omap_tll_disable(void);
-
-#endif
-
-#endif	/* __ASM_ARCH_OMAP_USB_H */
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 23cec57c02ba..cebfe0a68aa7 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -26,9 +26,12 @@
 #include <linux/spinlock.h>
 #include <linux/gpio.h>
 #include <plat/cpu.h>
-#include <plat/usb.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/usb-omap.h>
 #include <linux/pm_runtime.h>
 
+#include "omap-usb.h"
+
 #define USBHS_DRIVER_NAME	"usbhs_omap"
 #define OMAP_EHCI_DEVICE	"ehci-omap"
 #define OMAP_OHCI_DEVICE	"ohci-omap3"
diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c
index 4b7757b84301..0db0dfa3d08c 100644
--- a/drivers/mfd/omap-usb-tll.c
+++ b/drivers/mfd/omap-usb-tll.c
@@ -25,8 +25,8 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/err.h>
-#include <plat/usb.h>
 #include <linux/pm_runtime.h>
+#include <linux/platform_data/usb-omap.h>
 
 #define USBTLL_DRIVER_NAME	"usbhs_tll"
 
diff --git a/drivers/mfd/omap-usb.h b/drivers/mfd/omap-usb.h
new file mode 100644
index 000000000000..972aa961b064
--- /dev/null
+++ b/drivers/mfd/omap-usb.h
@@ -0,0 +1,2 @@
+extern int omap_tll_enable(void);
+extern int omap_tll_disable(void);
diff --git a/drivers/usb/host/ehci-omap.c b/drivers/usb/host/ehci-omap.c
index d7fe287d0678..0d5ac36fdf47 100644
--- a/drivers/usb/host/ehci-omap.c
+++ b/drivers/usb/host/ehci-omap.c
@@ -39,12 +39,13 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/usb/ulpi.h>
-#include <plat/usb.h>
 #include <linux/regulator/consumer.h>
 #include <linux/pm_runtime.h>
 #include <linux/gpio.h>
 #include <linux/clk.h>
 
+#include <linux/platform_data/usb-omap.h>
+
 /* EHCI Register Set */
 #define EHCI_INSNREG04					(0xA0)
 #define EHCI_INSNREG04_DISABLE_UNSUSPEND		(1 << 5)
diff --git a/drivers/usb/host/ohci-omap3.c b/drivers/usb/host/ohci-omap3.c
index 1b8133b6e451..bd7803dce9be 100644
--- a/drivers/usb/host/ohci-omap3.c
+++ b/drivers/usb/host/ohci-omap3.c
@@ -30,7 +30,6 @@
  */
 
 #include <linux/platform_device.h>
-#include <plat/usb.h>
 #include <linux/pm_runtime.h>
 
 /*-------------------------------------------------------------------------*/
diff --git a/drivers/usb/musb/am35x.c b/drivers/usb/musb/am35x.c
index c964d6af178b..a87cdd2387cf 100644
--- a/drivers/usb/musb/am35x.c
+++ b/drivers/usb/musb/am35x.c
@@ -34,8 +34,7 @@
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/usb/nop-usb-xceiv.h>
-
-#include <plat/usb.h>
+#include <linux/platform_data/usb-omap.h>
 
 #include "musb_core.h"
 
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 444346e1e10d..a67af21c1460 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -38,13 +38,12 @@
 #include <linux/pm_runtime.h>
 #include <linux/module.h>
 #include <linux/usb/nop-usb-xceiv.h>
+#include <linux/platform_data/usb-omap.h>
 
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 
-#include <plat/usb.h>
-
 #include "musb_core.h"
 
 #ifdef CONFIG_OF
diff --git a/drivers/usb/musb/omap2430.h b/drivers/usb/musb/omap2430.h
index b85f3973e78c..8ef656659fcb 100644
--- a/drivers/usb/musb/omap2430.h
+++ b/drivers/usb/musb/omap2430.h
@@ -10,7 +10,7 @@
 #ifndef __MUSB_OMAP243X_H__
 #define __MUSB_OMAP243X_H__
 
-#include <plat/usb.h>
+#include <linux/platform_data/usb-omap.h>
 
 /*
  * OMAP2430-specific definitions
diff --git a/include/linux/platform_data/usb-omap.h b/include/linux/platform_data/usb-omap.h
new file mode 100644
index 000000000000..8570bcfe6311
--- /dev/null
+++ b/include/linux/platform_data/usb-omap.h
@@ -0,0 +1,80 @@
+/*
+ * usb-omap.h - Platform data for the various OMAP USB IPs
+ *
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * This software is distributed under the terms of the GNU General Public
+ * License ("GPL") version 2, as published by the Free Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define OMAP3_HS_USB_PORTS	3
+
+enum usbhs_omap_port_mode {
+	OMAP_USBHS_PORT_MODE_UNUSED,
+	OMAP_EHCI_PORT_MODE_PHY,
+	OMAP_EHCI_PORT_MODE_TLL,
+	OMAP_EHCI_PORT_MODE_HSIC,
+	OMAP_OHCI_PORT_MODE_PHY_6PIN_DATSE0,
+	OMAP_OHCI_PORT_MODE_PHY_6PIN_DPDM,
+	OMAP_OHCI_PORT_MODE_PHY_3PIN_DATSE0,
+	OMAP_OHCI_PORT_MODE_PHY_4PIN_DPDM,
+	OMAP_OHCI_PORT_MODE_TLL_6PIN_DATSE0,
+	OMAP_OHCI_PORT_MODE_TLL_6PIN_DPDM,
+	OMAP_OHCI_PORT_MODE_TLL_3PIN_DATSE0,
+	OMAP_OHCI_PORT_MODE_TLL_4PIN_DPDM,
+	OMAP_OHCI_PORT_MODE_TLL_2PIN_DATSE0,
+	OMAP_OHCI_PORT_MODE_TLL_2PIN_DPDM
+};
+
+struct usbtll_omap_platform_data {
+	enum usbhs_omap_port_mode		port_mode[OMAP3_HS_USB_PORTS];
+};
+
+struct ehci_hcd_omap_platform_data {
+	enum usbhs_omap_port_mode	port_mode[OMAP3_HS_USB_PORTS];
+	int				reset_gpio_port[OMAP3_HS_USB_PORTS];
+	struct regulator		*regulator[OMAP3_HS_USB_PORTS];
+	unsigned			phy_reset:1;
+};
+
+struct ohci_hcd_omap_platform_data {
+	enum usbhs_omap_port_mode	port_mode[OMAP3_HS_USB_PORTS];
+	unsigned			es2_compatibility:1;
+};
+
+struct usbhs_omap_platform_data {
+	enum usbhs_omap_port_mode		port_mode[OMAP3_HS_USB_PORTS];
+
+	struct ehci_hcd_omap_platform_data	*ehci_data;
+	struct ohci_hcd_omap_platform_data	*ohci_data;
+};
+
+/*-------------------------------------------------------------------------*/
+
+struct omap_musb_board_data {
+	u8	interface_type;
+	u8	mode;
+	u16	power;
+	unsigned extvbus:1;
+	void	(*set_phy_power)(u8 on);
+	void	(*clear_irq)(void);
+	void	(*set_mode)(u8 mode);
+	void	(*reset)(void);
+};
+
+enum musb_interface {
+	MUSB_INTERFACE_ULPI,
+	MUSB_INTERFACE_UTMI
+};
-- 
cgit v1.2.3-55-g7522


From 969ddcfc95c9a1849114fb72466d2fdea70f1d48 Mon Sep 17 00:00:00 2001
From: Alan Stern
Date: Fri, 19 Oct 2012 11:03:02 -0400
Subject: USB: hub_for_each_child should skip unconnected ports

This patch (as1619) improves the interface to the "hub_for_each_child"
macro.  The name clearly suggests that the macro iterates over child
devices; it does not suggest that the loop will also iterate over
unnconnected ports.

The patch changes the macro so that it will skip over unconnected
ports and iterate only the actual child devices.  The two existing
call sites are updated to avoid testing for a NULL child pointer,
which is now unnecessary.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/devices.c      | 18 ++++++++----------
 drivers/usb/host/r8a66597-hcd.c |  6 ++----
 include/linux/usb.h             |  5 +++--
 3 files changed, 13 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/devices.c b/drivers/usb/core/devices.c
index f460de31acee..cbacea933b18 100644
--- a/drivers/usb/core/devices.c
+++ b/drivers/usb/core/devices.c
@@ -591,16 +591,14 @@ static ssize_t usb_device_dump(char __user **buffer, size_t *nbytes,
 
 	/* Now look at all of this device's children. */
 	usb_hub_for_each_child(usbdev, chix, childdev) {
-		if (childdev) {
-			usb_lock_device(childdev);
-			ret = usb_device_dump(buffer, nbytes, skip_bytes,
-					      file_offset, childdev, bus,
-					      level + 1, chix - 1, ++cnt);
-			usb_unlock_device(childdev);
-			if (ret == -EFAULT)
-				return total_written;
-			total_written += ret;
-		}
+		usb_lock_device(childdev);
+		ret = usb_device_dump(buffer, nbytes, skip_bytes,
+				      file_offset, childdev, bus,
+				      level + 1, chix - 1, ++cnt);
+		usb_unlock_device(childdev);
+		if (ret == -EFAULT)
+			return total_written;
+		total_written += ret;
 	}
 	return total_written;
 }
diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c
index fcc09e5ec0ad..b3eea0ba97a9 100644
--- a/drivers/usb/host/r8a66597-hcd.c
+++ b/drivers/usb/host/r8a66597-hcd.c
@@ -2036,10 +2036,8 @@ static void collect_usb_address_map(struct usb_device *udev, unsigned long *map)
 	    udev->parent->descriptor.bDeviceClass == USB_CLASS_HUB)
 		map[udev->devnum/32] |= (1 << (udev->devnum % 32));
 
-	usb_hub_for_each_child(udev, chix, childdev) {
-		if (childdev)
-			collect_usb_address_map(childdev, map);
-	}
+	usb_hub_for_each_child(udev, chix, childdev)
+		collect_usb_address_map(childdev, map);
 }
 
 /* this function must be called with interrupt disabled */
diff --git a/include/linux/usb.h b/include/linux/usb.h
index f92cdf0c1457..5df7c87b277f 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -588,8 +588,9 @@ extern struct usb_device *usb_hub_find_child(struct usb_device *hdev,
  */
 #define usb_hub_for_each_child(hdev, port1, child) \
 	for (port1 = 1,	child =	usb_hub_find_child(hdev, port1); \
-		port1 <= hdev->maxchild; \
-		child = usb_hub_find_child(hdev, ++port1))
+			port1 <= hdev->maxchild; \
+			child = usb_hub_find_child(hdev, ++port1)) \
+		if (!child) continue; else
 
 /* USB device locking */
 #define usb_lock_device(udev)		device_lock(&(udev)->dev)
-- 
cgit v1.2.3-55-g7522


From bfd1e910139be73fb0783a0b3171fc79e6afa031 Mon Sep 17 00:00:00 2001
From: Alan Stern
Date: Fri, 19 Oct 2012 11:03:39 -0400
Subject: USB: speed up usb_bus_resume()

This patch (as1620) speeds up USB root-hub resumes in the common case
where every enabled port has its suspend feature set (which currently
will be true for every runtime resume of the root hub).  If all the
enabled ports are suspended then resuming the root hub won't resume
any of the downstream devices.  In this case there's no need for a
Resume Recovery delay, because that delay is meant to give devices a
chance to get ready for active use.

To keep track of the port suspend features, the patch adds a
"port_is_suspended" flag to struct usb_device.  This has to be tracked
separately from the device's state; it's entirely possible for a USB-2
device to be suspended while the suspend feature on its parent port is
clear.  The reason is that devices will go into suspend whenever their
parent hub does.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reviewed-by: Peter Chen <peter.chen@freescale.com>
Tested-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c | 19 +++++++++++++++++--
 drivers/usb/core/hub.c |  2 ++
 include/linux/usb.h    |  2 ++
 3 files changed, 21 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 1e741bca0265..eaa14514e173 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2039,8 +2039,9 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
 	status = hcd->driver->bus_resume(hcd);
 	clear_bit(HCD_FLAG_WAKEUP_PENDING, &hcd->flags);
 	if (status == 0) {
-		/* TRSMRCY = 10 msec */
-		msleep(10);
+		struct usb_device *udev;
+		int port1;
+
 		spin_lock_irq(&hcd_root_hub_lock);
 		if (!HCD_DEAD(hcd)) {
 			usb_set_device_state(rhdev, rhdev->actconfig
@@ -2050,6 +2051,20 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
 			hcd->state = HC_STATE_RUNNING;
 		}
 		spin_unlock_irq(&hcd_root_hub_lock);
+
+		/*
+		 * Check whether any of the enabled ports on the root hub are
+		 * unsuspended.  If they are then a TRSMRCY delay is needed
+		 * (this is what the USB-2 spec calls a "global resume").
+		 * Otherwise we can skip the delay.
+		 */
+		usb_hub_for_each_child(rhdev, port1, udev) {
+			if (udev->state != USB_STATE_NOTATTACHED &&
+					!udev->port_is_suspended) {
+				usleep_range(10000, 11000);	/* TRSMRCY */
+				break;
+			}
+		}
 	} else {
 		hcd->state = old_state;
 		dev_dbg(&rhdev->dev, "bus %s fail, err %d\n",
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 64854d76f529..e729e94cb751 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2876,6 +2876,7 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
 				(PMSG_IS_AUTO(msg) ? "auto-" : ""),
 				udev->do_remote_wakeup);
 		usb_set_device_state(udev, USB_STATE_SUSPENDED);
+		udev->port_is_suspended = 1;
 		msleep(10);
 	}
 	usb_mark_last_busy(hub->hdev);
@@ -3040,6 +3041,7 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 
  SuspendCleared:
 	if (status == 0) {
+		udev->port_is_suspended = 0;
 		if (hub_is_superspeed(hub->hdev)) {
 			if (portchange & USB_PORT_STAT_C_LINK_STATE)
 				clear_port_feature(hub->hdev, port1,
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 5df7c87b277f..f51f9981de1e 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -482,6 +482,7 @@ struct usb3_lpm_parameters {
  * @connect_time: time device was first connected
  * @do_remote_wakeup:  remote wakeup should be enabled
  * @reset_resume: needs reset instead of resume
+ * @port_is_suspended: the upstream port is suspended (L2 or U3)
  * @wusb_dev: if this is a Wireless USB device, link to the WUSB
  *	specific data for the device.
  * @slot_id: Slot ID assigned by xHCI
@@ -560,6 +561,7 @@ struct usb_device {
 
 	unsigned do_remote_wakeup:1;
 	unsigned reset_resume:1;
+	unsigned port_is_suspended:1;
 #endif
 	struct wusb_dev *wusb_dev;
 	int slot_id;
-- 
cgit v1.2.3-55-g7522


From 0a0c3b5a24bd802b1ebbf99e0b01296647b8199b Mon Sep 17 00:00:00 2001
From: Damian Hobson-Garcia
Date: Tue, 25 Sep 2012 15:09:11 +0900
Subject: Add new uio device for dynamic memory allocation

This device extends the uio_pdrv_genirq driver to provide limited
dynamic memory allocation for UIO devices.  This allows UIO devices
to use CMA and IOMMU allocated memory regions. This driver is based
on the uio_pdrv_genirq driver and provides the same generic interrupt
handling capabilities.  Like uio_prdv_genirq,
a fixed number of memory regions, defined in the platform device's
.resources field are exported to userpace. This driver adds the ability
to export additional regions whose number and size are known at boot time,
but whose memory is not allocated until the uio device file is opened for
the first time.  When the device file is closed, the allocated memory block
is freed.  Physical (DMA) addresses for the dynamic regions are provided to
the userspace via /sys/class/uio/uioX/maps/mapY/addr in the same way as
static addresses are when the uio device file is open, when no processes
are holding the device file open, the address returned to userspace is
DMA_ERROR_CODE.

Signed-off-by: Damian Hobson-Garcia <dhobsong@igel.co.jp>
Signed-off-by: "Hans J. Koch" <hjk@hansjkoch.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/uio/Kconfig                           |  16 ++
 drivers/uio/Makefile                          |   1 +
 drivers/uio/uio_dmem_genirq.c                 | 354 ++++++++++++++++++++++++++
 include/linux/platform_data/uio_dmem_genirq.h |  26 ++
 4 files changed, 397 insertions(+)
 create mode 100644 drivers/uio/uio_dmem_genirq.c
 create mode 100644 include/linux/platform_data/uio_dmem_genirq.h

(limited to 'include')

diff --git a/drivers/uio/Kconfig b/drivers/uio/Kconfig
index 6f3ea9bbc818..82e2b89d4480 100644
--- a/drivers/uio/Kconfig
+++ b/drivers/uio/Kconfig
@@ -44,6 +44,22 @@ config UIO_PDRV_GENIRQ
 
 	  If you don't know what to do here, say N.
 
+config UIO_DMEM_GENIRQ
+	tristate "Userspace platform driver with generic irq and dynamic memory"
+	help
+	  Platform driver for Userspace I/O devices, including generic
+	  interrupt handling code. Shared interrupts are not supported.
+
+	  Memory regions can be specified with the same platform device
+	  resources as the UIO_PDRV drivers, but dynamic regions can also
+	  be specified.
+	  The number and size of these regions is static,
+	  but the memory allocation is not performed until
+	  the associated device file is opened. The
+	  memory is freed once the uio device is closed.
+
+	  If you don't know what to do here, say N.
+
 config UIO_AEC
 	tristate "AEC video timestamp device"
 	depends on PCI
diff --git a/drivers/uio/Makefile b/drivers/uio/Makefile
index d4dd9a5552f8..b354c539507a 100644
--- a/drivers/uio/Makefile
+++ b/drivers/uio/Makefile
@@ -2,6 +2,7 @@ obj-$(CONFIG_UIO)	+= uio.o
 obj-$(CONFIG_UIO_CIF)	+= uio_cif.o
 obj-$(CONFIG_UIO_PDRV)	+= uio_pdrv.o
 obj-$(CONFIG_UIO_PDRV_GENIRQ)	+= uio_pdrv_genirq.o
+obj-$(CONFIG_UIO_DMEM_GENIRQ)	+= uio_dmem_genirq.o
 obj-$(CONFIG_UIO_AEC)	+= uio_aec.o
 obj-$(CONFIG_UIO_SERCOS3)	+= uio_sercos3.o
 obj-$(CONFIG_UIO_PCI_GENERIC)	+= uio_pci_generic.o
diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c
new file mode 100644
index 000000000000..4d4dd008c8b9
--- /dev/null
+++ b/drivers/uio/uio_dmem_genirq.c
@@ -0,0 +1,354 @@
+/*
+ * drivers/uio/uio_dmem_genirq.c
+ *
+ * Userspace I/O platform driver with generic IRQ handling code.
+ *
+ * Copyright (C) 2012 Damian Hobson-Garcia
+ *
+ * Based on uio_pdrv_genirq.c by Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/uio_driver.h>
+#include <linux/spinlock.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/platform_data/uio_dmem_genirq.h>
+#include <linux/stringify.h>
+#include <linux/pm_runtime.h>
+#include <linux/dma-mapping.h>
+#include <linux/slab.h>
+
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/of_address.h>
+
+#define DRIVER_NAME "uio_dmem_genirq"
+
+struct uio_dmem_genirq_platdata {
+	struct uio_info *uioinfo;
+	spinlock_t lock;
+	unsigned long flags;
+	struct platform_device *pdev;
+	unsigned int dmem_region_start;
+	unsigned int num_dmem_regions;
+	struct mutex alloc_lock;
+	unsigned int refcnt;
+};
+
+static int uio_dmem_genirq_open(struct uio_info *info, struct inode *inode)
+{
+	struct uio_dmem_genirq_platdata *priv = info->priv;
+	struct uio_mem *uiomem;
+	int ret = 0;
+
+	uiomem = &priv->uioinfo->mem[priv->dmem_region_start];
+
+	mutex_lock(&priv->alloc_lock);
+	while (!priv->refcnt && uiomem < &priv->uioinfo->mem[MAX_UIO_MAPS]) {
+		void *addr;
+		if (!uiomem->size)
+			break;
+
+		addr = dma_alloc_coherent(&priv->pdev->dev, uiomem->size,
+				(dma_addr_t *)&uiomem->addr, GFP_KERNEL);
+		if (!addr) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		uiomem->internal_addr = addr;
+		++uiomem;
+	}
+	priv->refcnt++;
+
+	mutex_unlock(&priv->alloc_lock);
+	/* Wait until the Runtime PM code has woken up the device */
+	pm_runtime_get_sync(&priv->pdev->dev);
+	return ret;
+}
+
+static int uio_dmem_genirq_release(struct uio_info *info, struct inode *inode)
+{
+	struct uio_dmem_genirq_platdata *priv = info->priv;
+	struct uio_mem *uiomem;
+
+	/* Tell the Runtime PM code that the device has become idle */
+	pm_runtime_put_sync(&priv->pdev->dev);
+
+	uiomem = &priv->uioinfo->mem[priv->dmem_region_start];
+
+	mutex_lock(&priv->alloc_lock);
+
+	priv->refcnt--;
+	while (!priv->refcnt && uiomem < &priv->uioinfo->mem[MAX_UIO_MAPS]) {
+		if (!uiomem->size)
+			break;
+
+		dma_free_coherent(&priv->pdev->dev, uiomem->size,
+				uiomem->internal_addr, uiomem->addr);
+		uiomem->addr = DMA_ERROR_CODE;
+		++uiomem;
+	}
+
+	mutex_unlock(&priv->alloc_lock);
+	return 0;
+}
+
+static irqreturn_t uio_dmem_genirq_handler(int irq, struct uio_info *dev_info)
+{
+	struct uio_dmem_genirq_platdata *priv = dev_info->priv;
+
+	/* Just disable the interrupt in the interrupt controller, and
+	 * remember the state so we can allow user space to enable it later.
+	 */
+
+	if (!test_and_set_bit(0, &priv->flags))
+		disable_irq_nosync(irq);
+
+	return IRQ_HANDLED;
+}
+
+static int uio_dmem_genirq_irqcontrol(struct uio_info *dev_info, s32 irq_on)
+{
+	struct uio_dmem_genirq_platdata *priv = dev_info->priv;
+	unsigned long flags;
+
+	/* Allow user space to enable and disable the interrupt
+	 * in the interrupt controller, but keep track of the
+	 * state to prevent per-irq depth damage.
+	 *
+	 * Serialize this operation to support multiple tasks.
+	 */
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (irq_on) {
+		if (test_and_clear_bit(0, &priv->flags))
+			enable_irq(dev_info->irq);
+	} else {
+		if (!test_and_set_bit(0, &priv->flags))
+			disable_irq(dev_info->irq);
+	}
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
+static int uio_dmem_genirq_probe(struct platform_device *pdev)
+{
+	struct uio_dmem_genirq_pdata *pdata = pdev->dev.platform_data;
+	struct uio_info *uioinfo = &pdata->uioinfo;
+	struct uio_dmem_genirq_platdata *priv;
+	struct uio_mem *uiomem;
+	int ret = -EINVAL;
+	int i;
+
+	if (!uioinfo) {
+		int irq;
+
+		/* alloc uioinfo for one device */
+		uioinfo = kzalloc(sizeof(*uioinfo), GFP_KERNEL);
+		if (!uioinfo) {
+			ret = -ENOMEM;
+			dev_err(&pdev->dev, "unable to kmalloc\n");
+			goto bad2;
+		}
+		uioinfo->name = pdev->dev.of_node->name;
+		uioinfo->version = "devicetree";
+
+		/* Multiple IRQs are not supported */
+		irq = platform_get_irq(pdev, 0);
+		if (irq == -ENXIO)
+			uioinfo->irq = UIO_IRQ_NONE;
+		else
+			uioinfo->irq = irq;
+	}
+
+	if (!uioinfo || !uioinfo->name || !uioinfo->version) {
+		dev_err(&pdev->dev, "missing platform_data\n");
+		goto bad0;
+	}
+
+	if (uioinfo->handler || uioinfo->irqcontrol ||
+	    uioinfo->irq_flags & IRQF_SHARED) {
+		dev_err(&pdev->dev, "interrupt configuration error\n");
+		goto bad0;
+	}
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		ret = -ENOMEM;
+		dev_err(&pdev->dev, "unable to kmalloc\n");
+		goto bad0;
+	}
+
+	dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+
+	priv->uioinfo = uioinfo;
+	spin_lock_init(&priv->lock);
+	priv->flags = 0; /* interrupt is enabled to begin with */
+	priv->pdev = pdev;
+	mutex_init(&priv->alloc_lock);
+
+	if (!uioinfo->irq) {
+		ret = platform_get_irq(pdev, 0);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to get IRQ\n");
+			goto bad0;
+		}
+		uioinfo->irq = ret;
+	}
+	uiomem = &uioinfo->mem[0];
+
+	for (i = 0; i < pdev->num_resources; ++i) {
+		struct resource *r = &pdev->resource[i];
+
+		if (r->flags != IORESOURCE_MEM)
+			continue;
+
+		if (uiomem >= &uioinfo->mem[MAX_UIO_MAPS]) {
+			dev_warn(&pdev->dev, "device has more than "
+					__stringify(MAX_UIO_MAPS)
+					" I/O memory resources.\n");
+			break;
+		}
+
+		uiomem->memtype = UIO_MEM_PHYS;
+		uiomem->addr = r->start;
+		uiomem->size = resource_size(r);
+		++uiomem;
+	}
+
+	priv->dmem_region_start = i;
+	priv->num_dmem_regions = pdata->num_dynamic_regions;
+
+	for (i = 0; i < pdata->num_dynamic_regions; ++i) {
+		if (uiomem >= &uioinfo->mem[MAX_UIO_MAPS]) {
+			dev_warn(&pdev->dev, "device has more than "
+					__stringify(MAX_UIO_MAPS)
+					" dynamic and fixed memory regions.\n");
+			break;
+		}
+		uiomem->memtype = UIO_MEM_PHYS;
+		uiomem->addr = DMA_ERROR_CODE;
+		uiomem->size = pdata->dynamic_region_sizes[i];
+		++uiomem;
+	}
+
+	while (uiomem < &uioinfo->mem[MAX_UIO_MAPS]) {
+		uiomem->size = 0;
+		++uiomem;
+	}
+
+	/* This driver requires no hardware specific kernel code to handle
+	 * interrupts. Instead, the interrupt handler simply disables the
+	 * interrupt in the interrupt controller. User space is responsible
+	 * for performing hardware specific acknowledge and re-enabling of
+	 * the interrupt in the interrupt controller.
+	 *
+	 * Interrupt sharing is not supported.
+	 */
+
+	uioinfo->handler = uio_dmem_genirq_handler;
+	uioinfo->irqcontrol = uio_dmem_genirq_irqcontrol;
+	uioinfo->open = uio_dmem_genirq_open;
+	uioinfo->release = uio_dmem_genirq_release;
+	uioinfo->priv = priv;
+
+	/* Enable Runtime PM for this device:
+	 * The device starts in suspended state to allow the hardware to be
+	 * turned off by default. The Runtime PM bus code should power on the
+	 * hardware and enable clocks at open().
+	 */
+	pm_runtime_enable(&pdev->dev);
+
+	ret = uio_register_device(&pdev->dev, priv->uioinfo);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to register uio device\n");
+		goto bad1;
+	}
+
+	platform_set_drvdata(pdev, priv);
+	return 0;
+ bad1:
+	kfree(priv);
+	pm_runtime_disable(&pdev->dev);
+ bad0:
+	/* kfree uioinfo for OF */
+	if (pdev->dev.of_node)
+		kfree(uioinfo);
+ bad2:
+	return ret;
+}
+
+static int uio_dmem_genirq_remove(struct platform_device *pdev)
+{
+	struct uio_dmem_genirq_platdata *priv = platform_get_drvdata(pdev);
+
+	uio_unregister_device(priv->uioinfo);
+	pm_runtime_disable(&pdev->dev);
+
+	priv->uioinfo->handler = NULL;
+	priv->uioinfo->irqcontrol = NULL;
+
+	/* kfree uioinfo for OF */
+	if (pdev->dev.of_node)
+		kfree(priv->uioinfo);
+
+	kfree(priv);
+	return 0;
+}
+
+static int uio_dmem_genirq_runtime_nop(struct device *dev)
+{
+	/* Runtime PM callback shared between ->runtime_suspend()
+	 * and ->runtime_resume(). Simply returns success.
+	 *
+	 * In this driver pm_runtime_get_sync() and pm_runtime_put_sync()
+	 * are used at open() and release() time. This allows the
+	 * Runtime PM code to turn off power to the device while the
+	 * device is unused, ie before open() and after release().
+	 *
+	 * This Runtime PM callback does not need to save or restore
+	 * any registers since user space is responsbile for hardware
+	 * register reinitialization after open().
+	 */
+	return 0;
+}
+
+static const struct dev_pm_ops uio_dmem_genirq_dev_pm_ops = {
+	.runtime_suspend = uio_dmem_genirq_runtime_nop,
+	.runtime_resume = uio_dmem_genirq_runtime_nop,
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id uio_of_genirq_match[] = {
+	{ /* empty for now */ },
+};
+MODULE_DEVICE_TABLE(of, uio_of_genirq_match);
+#else
+# define uio_of_genirq_match NULL
+#endif
+
+static struct platform_driver uio_dmem_genirq = {
+	.probe = uio_dmem_genirq_probe,
+	.remove = uio_dmem_genirq_remove,
+	.driver = {
+		.name = DRIVER_NAME,
+		.owner = THIS_MODULE,
+		.pm = &uio_dmem_genirq_dev_pm_ops,
+		.of_match_table = uio_of_genirq_match,
+	},
+};
+
+module_platform_driver(uio_dmem_genirq);
+
+MODULE_AUTHOR("Damian Hobson-Garcia");
+MODULE_DESCRIPTION("Userspace I/O platform driver with dynamic memory.");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/include/linux/platform_data/uio_dmem_genirq.h b/include/linux/platform_data/uio_dmem_genirq.h
new file mode 100644
index 000000000000..973c1bb32168
--- /dev/null
+++ b/include/linux/platform_data/uio_dmem_genirq.h
@@ -0,0 +1,26 @@
+/*
+ * include/linux/platform_data/uio_dmem_genirq.h
+ *
+ * Copyright (C) 2012 Damian Hobson-Garcia
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UIO_DMEM_GENIRQ_H
+#define _UIO_DMEM_GENIRQ_H
+
+#include <linux/uio_driver.h>
+
+struct uio_dmem_genirq_pdata {
+	struct uio_info	uioinfo;
+	unsigned int *dynamic_region_sizes;
+	unsigned int num_dynamic_regions;
+};
+#endif /* _UIO_DMEM_GENIRQ_H */
-- 
cgit v1.2.3-55-g7522


From 9b04ebd1584766229c58fedaa8fe4dfff575ac3a Mon Sep 17 00:00:00 2001
From: James Hogan
Date: Tue, 23 Oct 2012 10:21:57 +0100
Subject: asm-generic/io.h: remove asm/cacheflush.h include

Including <asm/cacheflush.h> from <asm-generic/io.h> prevents
cacheflush.h being able to use I/O functions like readl and writel due
to circular include dependencies. It doesn't appear as if anything from
cacheflush.h is actually used by the generic io.h, so remove the
include.

I've compile tested a defconfig compilation of blackfin, openrisc (which
needed <asm/pgtable.h> including from it's <asm/io.h> to get the PAGE_*
definitions), and xtensa.

Other architectures which use asm-generic/io.h are score and unicore32,
and looking at their io.h I don't see any obvious problems.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Acked-by: Jonas Bonn <jonas@southpole.se>
Cc: Chris Zankel <chris@zankel.net>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Chen Liqin <liqin.chen@sunplusct.com>
Cc: Lennox Wu <lennox.wu@gmail.com>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/openrisc/include/asm/io.h | 1 +
 include/asm-generic/io.h       | 1 -
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h
index 07f5299d6c28..7c691399da3f 100644
--- a/arch/openrisc/include/asm/io.h
+++ b/arch/openrisc/include/asm/io.h
@@ -30,6 +30,7 @@
 #define PIO_MASK		0
 
 #include <asm-generic/io.h>
+#include <asm/pgtable.h>
 
 extern void __iomem *__ioremap(phys_addr_t offset, unsigned long size,
 				pgprot_t prot);
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 448303bdb85f..616eea53d633 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -12,7 +12,6 @@
 #define __ASM_GENERIC_IO_H
 
 #include <asm/page.h> /* I/O is all done through memory accesses */
-#include <asm/cacheflush.h>
 #include <linux/types.h>
 
 #ifdef CONFIG_GENERIC_IOMAP
-- 
cgit v1.2.3-55-g7522


From c6298038bcfc20710430a4ad069bb1f3f069997c Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov
Date: Wed, 24 Oct 2012 23:43:21 +0400
Subject: tty, ioctls -- Add new ioctl definitions for tty flags fetching

This patch defines new ioctl codes TIOCGPKT, TIOCGPTLCK,
TIOCGEXCL for fetching pty's packet mode and locking state,
and exclusive mode of tty.

[ No real handlers for the codes though, this will be
  addressed in another patch for easier review and
  bisectability ]

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
CC: Alan Cox <alan@lxorguk.ukuu.org.uk>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Pavel Emelyanov <xemul@parallels.com>
CC: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/alpha/include/asm/ioctls.h        | 3 +++
 arch/mips/include/uapi/asm/ioctls.h    | 3 +++
 arch/parisc/include/uapi/asm/ioctls.h  | 3 +++
 arch/powerpc/include/uapi/asm/ioctls.h | 3 +++
 arch/sh/include/uapi/asm/ioctls.h      | 3 +++
 arch/sparc/include/uapi/asm/ioctls.h   | 3 +++
 arch/xtensa/include/uapi/asm/ioctls.h  | 3 +++
 fs/compat_ioctl.c                      | 3 +++
 include/uapi/asm-generic/ioctls.h      | 3 +++
 9 files changed, 27 insertions(+)

(limited to 'include')

diff --git a/arch/alpha/include/asm/ioctls.h b/arch/alpha/include/asm/ioctls.h
index 80e1cee90f1f..92c557be49fc 100644
--- a/arch/alpha/include/asm/ioctls.h
+++ b/arch/alpha/include/asm/ioctls.h
@@ -95,6 +95,9 @@
 #define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
 #define TIOCVHANGUP	0x5437
+#define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
+#define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
+#define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 
 #define TIOCSERCONFIG	0x5453
 #define TIOCSERGWILD	0x5454
diff --git a/arch/mips/include/uapi/asm/ioctls.h b/arch/mips/include/uapi/asm/ioctls.h
index 92403c3d6007..addd56b60694 100644
--- a/arch/mips/include/uapi/asm/ioctls.h
+++ b/arch/mips/include/uapi/asm/ioctls.h
@@ -86,6 +86,9 @@
 #define TIOCGDEV	_IOR('T', 0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T', 0x36, int)  /* Generate signal on Pty slave */
 #define TIOCVHANGUP	0x5437
+#define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
+#define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
+#define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 
 /* I hope the range from 0x5480 on is free ... */
 #define TIOCSCTTY	0x5480		/* become controlling tty */
diff --git a/arch/parisc/include/uapi/asm/ioctls.h b/arch/parisc/include/uapi/asm/ioctls.h
index 054ec06f9e23..66719c38a36b 100644
--- a/arch/parisc/include/uapi/asm/ioctls.h
+++ b/arch/parisc/include/uapi/asm/ioctls.h
@@ -55,6 +55,9 @@
 #define TIOCGDEV	_IOR('T',0x32, int)  /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
 #define TIOCVHANGUP	0x5437
+#define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
+#define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
+#define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 
 #define FIONCLEX	0x5450  /* these numbers need to be adjusted. */
 #define FIOCLEX		0x5451
diff --git a/arch/powerpc/include/uapi/asm/ioctls.h b/arch/powerpc/include/uapi/asm/ioctls.h
index e9b78870aaab..49a25796a61a 100644
--- a/arch/powerpc/include/uapi/asm/ioctls.h
+++ b/arch/powerpc/include/uapi/asm/ioctls.h
@@ -97,6 +97,9 @@
 #define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
 #define TIOCVHANGUP	0x5437
+#define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
+#define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
+#define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 
 #define TIOCSERCONFIG	0x5453
 #define TIOCSERGWILD	0x5454
diff --git a/arch/sh/include/uapi/asm/ioctls.h b/arch/sh/include/uapi/asm/ioctls.h
index a6769f352bf6..342241079760 100644
--- a/arch/sh/include/uapi/asm/ioctls.h
+++ b/arch/sh/include/uapi/asm/ioctls.h
@@ -88,6 +88,9 @@
 #define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
 #define TIOCVHANGUP	_IO('T', 0x37)
+#define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
+#define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
+#define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 
 #define TIOCSERCONFIG	_IO('T', 83) /* 0x5453 */
 #define TIOCSERGWILD	_IOR('T', 84,  int) /* 0x5454 */
diff --git a/arch/sparc/include/uapi/asm/ioctls.h b/arch/sparc/include/uapi/asm/ioctls.h
index 9155f7041d44..897d1723fa14 100644
--- a/arch/sparc/include/uapi/asm/ioctls.h
+++ b/arch/sparc/include/uapi/asm/ioctls.h
@@ -21,6 +21,9 @@
 #define TCSETSF2	_IOW('T', 15, struct termios2)
 #define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCVHANGUP	_IO('T', 0x37)
+#define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
+#define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
+#define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 
 /* Note that all the ioctls that are not available in Linux have a 
  * double underscore on the front to: a) avoid some programs to
diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h
index 2aa4cd9f0cec..b4cb1100c0fb 100644
--- a/arch/xtensa/include/uapi/asm/ioctls.h
+++ b/arch/xtensa/include/uapi/asm/ioctls.h
@@ -101,6 +101,9 @@
 #define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
 #define TIOCVHANGUP	_IO('T', 0x37)
+#define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
+#define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
+#define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 
 #define TIOCSERCONFIG	_IO('T', 83)
 #define TIOCSERGWILD	_IOR('T', 84,  int)
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index f5054025f9da..89cf6014a967 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -842,6 +842,9 @@ COMPATIBLE_IOCTL(TIOCGDEV)
 COMPATIBLE_IOCTL(TIOCCBRK)
 COMPATIBLE_IOCTL(TIOCGSID)
 COMPATIBLE_IOCTL(TIOCGICOUNT)
+COMPATIBLE_IOCTL(TIOCGPKT)
+COMPATIBLE_IOCTL(TIOCGPTLCK)
+COMPATIBLE_IOCTL(TIOCGEXCL)
 /* Little t */
 COMPATIBLE_IOCTL(TIOCGETD)
 COMPATIBLE_IOCTL(TIOCSETD)
diff --git a/include/uapi/asm-generic/ioctls.h b/include/uapi/asm-generic/ioctls.h
index 199975fac395..143dacbb7d9a 100644
--- a/include/uapi/asm-generic/ioctls.h
+++ b/include/uapi/asm-generic/ioctls.h
@@ -74,6 +74,9 @@
 #define TCSETXW		0x5435
 #define TIOCSIG		_IOW('T', 0x36, int)  /* pty: generate signal */
 #define TIOCVHANGUP	0x5437
+#define TIOCGPKT	_IOR('T', 0x38, int) /* Get packet mode state */
+#define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
+#define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 
 #define FIONCLEX	0x5450
 #define FIOCLEX		0x5451
-- 
cgit v1.2.3-55-g7522


From 3c68198e75111a905ac2412be12bf7b29099729b Mon Sep 17 00:00:00 2001
From: Neil Horman
Date: Wed, 24 Oct 2012 09:20:03 +0000
Subject: sctp: Make hmac algorithm selection for cookie generation dynamic

Currently sctp allows for the optional use of md5 of sha1 hmac algorithms to
generate cookie values when establishing new connections via two build time
config options.  Theres no real reason to make this a static selection.  We can
add a sysctl that allows for the dynamic selection of these algorithms at run
time, with the default value determined by the corresponding crypto library
availability.
This comes in handy when, for example running a system in FIPS mode, where use
of md5 is disallowed, but SHA1 is permitted.

Note: This new sysctl has no corresponding socket option to select the cookie
hmac algorithm.  I chose not to implement that intentionally, as RFC 6458
contains no option for this value, and I opted not to pollute the socket option
namespace.

Change notes:
v2)
	* Updated subject to have the proper sctp prefix as per Dave M.
	* Replaced deafult selection options with new options that allow
	  developers to explicitly select available hmac algs at build time
	  as per suggestion by Vlad Y.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Vlad Yasevich <vyasevich@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netdev@vger.kernel.org
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 14 ++++++++
 include/net/netns/sctp.h               |  3 ++
 include/net/sctp/constants.h           |  8 -----
 include/net/sctp/structs.h             |  1 +
 net/sctp/Kconfig                       | 39 ++++++++--------------
 net/sctp/protocol.c                    |  9 ++++++
 net/sctp/socket.c                      | 11 ++++---
 net/sctp/sysctl.c                      | 59 ++++++++++++++++++++++++++++++++++
 8 files changed, 106 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index c7fc10724948..98ac0d7552a1 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1514,6 +1514,20 @@ cookie_preserve_enable - BOOLEAN
 
 	Default: 1
 
+cookie_hmac_alg - STRING
+	Select the hmac algorithm used when generating the cookie value sent by
+	a listening sctp socket to a connecting client in the INIT-ACK chunk.
+	Valid values are:
+	* md5
+	* sha1
+	* none
+	Ability to assign md5 or sha1 as the selected alg is predicated on the
+	configuarion of those algorithms at build time (CONFIG_CRYPTO_MD5 and
+	CONFIG_CRYPTO_SHA1).
+
+	Default: Dependent on configuration.  MD5 if available, else SHA1 if
+	available, else none.
+
 rcvbuf_policy - INTEGER
 	Determines if the receive buffer is attributed to the socket or to
 	association.   SCTP supports the capability to create multiple
diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h
index 5e5eb1f9f14b..3573a81815ad 100644
--- a/include/net/netns/sctp.h
+++ b/include/net/netns/sctp.h
@@ -62,6 +62,9 @@ struct netns_sctp {
 	/* Whether Cookie Preservative is enabled(1) or not(0) */
 	int cookie_preserve_enable;
 
+	/* The namespace default hmac alg */
+	char *sctp_hmac_alg;
+
 	/* Valid.Cookie.Life	    - 60  seconds  */
 	unsigned int valid_cookie_life;
 
diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index d053d2e99876..c29707d654c0 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -312,14 +312,6 @@ enum { SCTP_MAX_GABS = 16 };
 				 * functions simpler to write.
 				 */
 
-#if defined (CONFIG_SCTP_HMAC_MD5)
-#define SCTP_COOKIE_HMAC_ALG "hmac(md5)"
-#elif defined (CONFIG_SCTP_HMAC_SHA1)
-#define SCTP_COOKIE_HMAC_ALG "hmac(sha1)"
-#else
-#define SCTP_COOKIE_HMAC_ALG NULL
-#endif
-
 /* These return values describe the success or failure of a number of
  * routines which form the lower interface to SCTP_outqueue.
  */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 64158aa1bb5f..2b2f61dd4036 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -177,6 +177,7 @@ struct sctp_sock {
 
 	/* Access to HMAC transform. */
 	struct crypto_hash *hmac;
+	char *sctp_hmac_alg;
 
 	/* What is our base endpointer? */
 	struct sctp_endpoint *ep;
diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig
index 126b014eb79b..a9edd2e205f4 100644
--- a/net/sctp/Kconfig
+++ b/net/sctp/Kconfig
@@ -9,7 +9,6 @@ menuconfig IP_SCTP
 	select CRYPTO
 	select CRYPTO_HMAC
 	select CRYPTO_SHA1
-	select CRYPTO_MD5 if SCTP_HMAC_MD5
 	select LIBCRC32C
 	---help---
 	  Stream Control Transmission Protocol
@@ -68,33 +67,21 @@ config SCTP_DBG_OBJCNT
 
 	  If unsure, say N
 
-choice
-	prompt "SCTP: Cookie HMAC Algorithm"
-	default SCTP_HMAC_MD5
+config SCTP_COOKIE_HMAC_MD5
+	bool "Enable optional MD5 hmac cookie generation"
 	help
-	  HMAC algorithm to be used during association initialization.  It
-	  is strongly recommended to use HMAC-SHA1 or HMAC-MD5.  See 
-	  configuration for Cryptographic API and enable those algorithms
-          to make usable by SCTP. 
-
-config SCTP_HMAC_NONE
-	bool "None"
-	help 
-	  Choosing this disables the use of an HMAC during association 
-	  establishment.  It is advised to use either HMAC-MD5 or HMAC-SHA1.
-
-config SCTP_HMAC_SHA1
-	bool "HMAC-SHA1"
-	help 
-	  Enable the use of HMAC-SHA1 during association establishment.  It 
-	  is advised to use either HMAC-MD5 or HMAC-SHA1.
-
-config SCTP_HMAC_MD5
-	bool "HMAC-MD5"
+	  Enable optional MD5 hmac based SCTP cookie generation
+	default y
+	select CRYPTO_HMAC if SCTP_COOKIE_HMAC_MD5
+	select CRYPTO_MD5 if SCTP_COOKIE_HMAC_MD5
+
+config SCTP_COOKIE_HMAC_SHA1
+	bool "Enable optional SHA1 hmac cookie generation"
 	help
-	  Enable the use of HMAC-MD5 during association establishment.  It is 
-	  advised to use either HMAC-MD5 or HMAC-SHA1.
+	  Enable optional SHA1 hmac based SCTP cookie generation
+	default y
+	select CRYPTO_HMAC if SCTP_COOKIE_HMAC_SHA1
+	select CRYPTO_SHA1 if SCTP_COOKIE_HMAC_SHA1
 
-endchoice
 
 endif # IP_SCTP
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 2d518425d598..456bc3dbdd51 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1190,6 +1190,15 @@ static int sctp_net_init(struct net *net)
 	/* Whether Cookie Preservative is enabled(1) or not(0) */
 	net->sctp.cookie_preserve_enable 	= 1;
 
+	/* Default sctp sockets to use md5 as their hmac alg */
+#if defined (CONFIG_CRYPTO_MD5)
+	net->sctp.sctp_hmac_alg			= "md5";
+#elif defined (CONFIG_CRYPTO_SHA1)
+	net->sctp.sctp_hmac_alg			= "sha1";
+#else
+	net->sctp.sctp_hmac_alg			= NULL;
+#endif
+
 	/* Max.Burst		    - 4 */
 	net->sctp.max_burst			= SCTP_DEFAULT_MAX_BURST;
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 59d16ea927f0..fa81bdee00a5 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -110,7 +110,6 @@ static int sctp_do_bind(struct sock *, union sctp_addr *, int);
 static int sctp_autobind(struct sock *sk);
 static void sctp_sock_migrate(struct sock *, struct sock *,
 			      struct sctp_association *, sctp_socket_type_t);
-static char *sctp_hmac_alg = SCTP_COOKIE_HMAC_ALG;
 
 extern struct kmem_cache *sctp_bucket_cachep;
 extern long sysctl_sctp_mem[3];
@@ -3890,6 +3889,8 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
 	sp->default_rcv_context = 0;
 	sp->max_burst = net->sctp.max_burst;
 
+	sp->sctp_hmac_alg = net->sctp.sctp_hmac_alg;
+
 	/* Initialize default setup parameters. These parameters
 	 * can be modified with the SCTP_INITMSG socket option or
 	 * overridden by the SCTP_INIT CMSG.
@@ -5981,13 +5982,15 @@ SCTP_STATIC int sctp_listen_start(struct sock *sk, int backlog)
 	struct sctp_sock *sp = sctp_sk(sk);
 	struct sctp_endpoint *ep = sp->ep;
 	struct crypto_hash *tfm = NULL;
+	char alg[32];
 
 	/* Allocate HMAC for generating cookie. */
-	if (!sctp_sk(sk)->hmac && sctp_hmac_alg) {
-		tfm = crypto_alloc_hash(sctp_hmac_alg, 0, CRYPTO_ALG_ASYNC);
+	if (!sp->hmac && sp->sctp_hmac_alg) {
+		sprintf(alg, "hmac(%s)", sp->sctp_hmac_alg);
+		tfm = crypto_alloc_hash(alg, 0, CRYPTO_ALG_ASYNC);
 		if (IS_ERR(tfm)) {
 			net_info_ratelimited("failed to load transform for %s: %ld\n",
-					     sctp_hmac_alg, PTR_ERR(tfm));
+					     sp->sctp_hmac_alg, PTR_ERR(tfm));
 			return -ENOSYS;
 		}
 		sctp_sk(sk)->hmac = tfm;
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 70e3ba5cb50b..043889ac86c0 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -62,6 +62,11 @@ extern long sysctl_sctp_mem[3];
 extern int sysctl_sctp_rmem[3];
 extern int sysctl_sctp_wmem[3];
 
+static int proc_sctp_do_hmac_alg(ctl_table *ctl,
+				int write,
+				void __user *buffer, size_t *lenp,
+
+				loff_t *ppos);
 static ctl_table sctp_table[] = {
 	{
 		.procname	= "sctp_mem",
@@ -146,6 +151,12 @@ static ctl_table sctp_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "cookie_hmac_alg",
+		.maxlen		= 8,
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_hmac_alg,
+	},
 	{
 		.procname	= "valid_cookie_life",
 		.data		= &init_net.sctp.valid_cookie_life,
@@ -289,6 +300,54 @@ static ctl_table sctp_net_table[] = {
 	{ /* sentinel */ }
 };
 
+static int proc_sctp_do_hmac_alg(ctl_table *ctl,
+				int write,
+				void __user *buffer, size_t *lenp,
+				loff_t *ppos)
+{
+	struct net *net = current->nsproxy->net_ns;
+	char tmp[8];
+	ctl_table tbl;
+	int ret;
+	int changed = 0;
+	char *none = "none";
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+
+	if (write) {
+		tbl.data = tmp;
+		tbl.maxlen = 8;
+	} else {
+		tbl.data = net->sctp.sctp_hmac_alg ? : none;
+		tbl.maxlen = strlen(tbl.data);
+	}
+		ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+
+	if (write) {
+#ifdef CONFIG_CRYPTO_MD5
+		if (!strncmp(tmp, "md5", 3)) {
+			net->sctp.sctp_hmac_alg = "md5";
+			changed = 1;
+		}
+#endif
+#ifdef CONFIG_CRYPTO_SHA1
+		if (!strncmp(tmp, "sha1", 4)) {
+			net->sctp.sctp_hmac_alg = "sha1";
+			changed = 1;
+		}
+#endif
+		if (!strncmp(tmp, "none", 4)) {
+			net->sctp.sctp_hmac_alg = NULL;
+			changed = 1;
+		}
+
+		if (!changed)
+			ret = -EINVAL;
+	}
+
+	return ret;
+}
+
 int sctp_sysctl_net_register(struct net *net)
 {
 	struct ctl_table *table;
-- 
cgit v1.2.3-55-g7522


From 80b0a6029272247f19146bf8f88e5d4bba94cba5 Mon Sep 17 00:00:00 2001
From: Mathias Nyman
Date: Wed, 24 Oct 2012 17:25:27 +0300
Subject: gpiolib: add gpio get direction callback support

Add .get_direction callback to gpio_chip. This allows gpiolib
to check the current direction of a gpio.
Used to show the correct gpio direction in sysfs and debug entries.

If callback is not set then gpiolib will work as previously;
e.g. guessing everything is input until a direction is set.

Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c     | 38 +++++++++++++++++++++++++++++++++++++-
 include/asm-generic/gpio.h |  5 ++++-
 2 files changed, 41 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index d5f9742d9ac1..e468eed261c5 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -191,6 +191,32 @@ err:
 	return ret;
 }
 
+/* caller ensures gpio is valid and requested, chip->get_direction may sleep  */
+static int gpio_get_direction(unsigned gpio)
+{
+	struct gpio_chip	*chip;
+	struct gpio_desc	*desc = &gpio_desc[gpio];
+	int			status = -EINVAL;
+
+	chip = gpio_to_chip(gpio);
+	gpio -= chip->base;
+
+	if (!chip->get_direction)
+		return status;
+
+	status = chip->get_direction(chip, gpio);
+	if (status > 0) {
+		/* GPIOF_DIR_IN, or other positive */
+		status = 1;
+		clear_bit(FLAG_IS_OUT, &desc->flags);
+	}
+	if (status == 0) {
+		/* GPIOF_DIR_OUT */
+		set_bit(FLAG_IS_OUT, &desc->flags);
+	}
+	return status;
+}
+
 #ifdef CONFIG_GPIO_SYSFS
 
 /* lock protects against unexport_gpio() being called while
@@ -223,6 +249,7 @@ static ssize_t gpio_direction_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	const struct gpio_desc	*desc = dev_get_drvdata(dev);
+	unsigned		gpio = desc - gpio_desc;
 	ssize_t			status;
 
 	mutex_lock(&sysfs_lock);
@@ -230,6 +257,7 @@ static ssize_t gpio_direction_show(struct device *dev,
 	if (!test_bit(FLAG_EXPORT, &desc->flags))
 		status = -EIO;
 	else
+		gpio_get_direction(gpio);
 		status = sprintf(buf, "%s\n",
 			test_bit(FLAG_IS_OUT, &desc->flags)
 				? "out" : "in");
@@ -1080,6 +1108,7 @@ int gpiochip_add(struct gpio_chip *chip)
 			 * inputs (often with pullups enabled) so power
 			 * usage is minimized.  Linux code should set the
 			 * gpio direction first thing; but until it does,
+			 * and in case chip->get_direction is not set,
 			 * we may expose the wrong direction in sysfs.
 			 */
 			gpio_desc[id].flags = !chip->direction_input
@@ -1231,9 +1260,15 @@ int gpio_request(unsigned gpio, const char *label)
 			desc_set_label(desc, NULL);
 			module_put(chip->owner);
 			clear_bit(FLAG_REQUESTED, &desc->flags);
+			goto done;
 		}
 	}
-
+	if (chip->get_direction) {
+		/* chip->get_direction may sleep */
+		spin_unlock_irqrestore(&gpio_lock, flags);
+		gpio_get_direction(gpio);
+		spin_lock_irqsave(&gpio_lock, flags);
+	}
 done:
 	if (status)
 		pr_debug("gpio_request: gpio-%d (%s) status %d\n",
@@ -1769,6 +1804,7 @@ static void gpiolib_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 		if (!test_bit(FLAG_REQUESTED, &gdesc->flags))
 			continue;
 
+		gpio_get_direction(gpio);
 		is_out = test_bit(FLAG_IS_OUT, &gdesc->flags);
 		seq_printf(s, " gpio-%-3d (%-20.20s) %s %s",
 			gpio, gdesc->label,
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index a9432fc6b8ba..eb70ca295971 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -56,6 +56,8 @@ struct device_node;
  *	enabling module power and clock; may sleep
  * @free: optional hook for chip-specific deactivation, such as
  *	disabling module power and clock; may sleep
+ * @get_direction: returns direction for signal "offset", 0=out, 1=in,
+ *	(same as GPIOF_DIR_XXX), or negative error
  * @direction_input: configures signal "offset" as input, or returns error
  * @get: returns value for signal "offset"; for output signals this
  *	returns either the value actually sensed, or zero
@@ -100,7 +102,8 @@ struct gpio_chip {
 						unsigned offset);
 	void			(*free)(struct gpio_chip *chip,
 						unsigned offset);
-
+	int			(*get_direction)(struct gpio_chip *chip,
+						unsigned offset);
 	int			(*direction_input)(struct gpio_chip *chip,
 						unsigned offset);
 	int			(*get)(struct gpio_chip *chip,
-- 
cgit v1.2.3-55-g7522


From 877bd862f32b815d54ab5fc10a4fd903d7bf3012 Mon Sep 17 00:00:00 2001
From: Ming Lei
Date: Wed, 24 Oct 2012 19:46:54 +0000
Subject: usbnet: introduce usbnet 3 command helpers

This patch introduces the below 3 usb command helpers:

	usbnet_read_cmd / usbnet_write_cmd / usbnet_write_cmd_async

so that each low level driver doesn't need to implement them
by itself, and the dma buffer allocation for usb transfer and
runtime PM things can be handled just in one place.

Acked-by: Oliver Neukum <oneukum@suse.de>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c   | 132 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/usb/usbnet.h |   6 +++
 2 files changed, 138 insertions(+)

(limited to 'include')

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index f9819d10b1f9..447d20d22b7c 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1610,6 +1610,138 @@ void usbnet_device_suggests_idle(struct usbnet *dev)
 }
 EXPORT_SYMBOL(usbnet_device_suggests_idle);
 
+/*-------------------------------------------------------------------------*/
+int usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
+		    u16 value, u16 index, void *data, u16 size)
+{
+	void *buf = NULL;
+	int err = -ENOMEM;
+
+	netdev_dbg(dev->net, "usbnet_read_cmd cmd=0x%02x reqtype=%02x"
+		   " value=0x%04x index=0x%04x size=%d\n",
+		   cmd, reqtype, value, index, size);
+
+	if (data) {
+		buf = kmalloc(size, GFP_KERNEL);
+		if (!buf)
+			goto out;
+	}
+
+	err = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
+			      cmd, reqtype, value, index, buf, size,
+			      USB_CTRL_GET_TIMEOUT);
+	if (err > 0 && err <= size)
+		memcpy(data, buf, err);
+	kfree(buf);
+out:
+	return err;
+}
+EXPORT_SYMBOL_GPL(usbnet_read_cmd);
+
+int usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
+		     u16 value, u16 index, const void *data, u16 size)
+{
+	void *buf = NULL;
+	int err = -ENOMEM;
+
+	netdev_dbg(dev->net, "usbnet_write_cmd cmd=0x%02x reqtype=%02x"
+		   " value=0x%04x index=0x%04x size=%d\n",
+		   cmd, reqtype, value, index, size);
+
+	if (data) {
+		buf = kmemdup(data, size, GFP_KERNEL);
+		if (!buf)
+			goto out;
+	}
+
+	err = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
+			      cmd, reqtype, value, index, buf, size,
+			      USB_CTRL_SET_TIMEOUT);
+	kfree(buf);
+
+out:
+	return err;
+}
+EXPORT_SYMBOL_GPL(usbnet_write_cmd);
+
+static void usbnet_async_cmd_cb(struct urb *urb)
+{
+	struct usb_ctrlrequest *req = (struct usb_ctrlrequest *)urb->context;
+	int status = urb->status;
+
+	if (status < 0)
+		dev_dbg(&urb->dev->dev, "%s failed with %d",
+			__func__, status);
+
+	kfree(req);
+	usb_free_urb(urb);
+}
+
+int usbnet_write_cmd_async(struct usbnet *dev, u8 cmd, u8 reqtype,
+			   u16 value, u16 index, const void *data, u16 size)
+{
+	struct usb_ctrlrequest *req = NULL;
+	struct urb *urb;
+	int err = -ENOMEM;
+	void *buf = NULL;
+
+	netdev_dbg(dev->net, "usbnet_write_cmd cmd=0x%02x reqtype=%02x"
+		   " value=0x%04x index=0x%04x size=%d\n",
+		   cmd, reqtype, value, index, size);
+
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb) {
+		netdev_err(dev->net, "Error allocating URB in"
+			   " %s!\n", __func__);
+		goto fail;
+	}
+
+	if (data) {
+		buf = kmemdup(data, size, GFP_ATOMIC);
+		if (!buf) {
+			netdev_err(dev->net, "Error allocating buffer"
+				   " in %s!\n", __func__);
+			goto fail_free;
+		}
+	}
+
+	req = kmalloc(sizeof(struct usb_ctrlrequest), GFP_ATOMIC);
+	if (!req) {
+		netdev_err(dev->net, "Failed to allocate memory for %s\n",
+			   __func__);
+		goto fail_free_buf;
+	}
+
+	req->bRequestType = reqtype;
+	req->bRequest = cmd;
+	req->wValue = cpu_to_le16(value);
+	req->wIndex = cpu_to_le16(index);
+	req->wLength = cpu_to_le16(size);
+
+	usb_fill_control_urb(urb, dev->udev,
+			     usb_sndctrlpipe(dev->udev, 0),
+			     (void *)req, buf, size,
+			     usbnet_async_cmd_cb, req);
+	urb->transfer_flags |= URB_FREE_BUFFER;
+
+	err = usb_submit_urb(urb, GFP_ATOMIC);
+	if (err < 0) {
+		netdev_err(dev->net, "Error submitting the control"
+			   " message: status=%d\n", err);
+		goto fail_free;
+	}
+	return 0;
+
+fail_free_buf:
+	kfree(buf);
+fail_free:
+	kfree(req);
+	usb_free_urb(urb);
+fail:
+	return err;
+
+}
+EXPORT_SYMBOL_GPL(usbnet_write_cmd_async);
 /*-------------------------------------------------------------------------*/
 
 static int __init usbnet_init(void)
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index ddbbb7de894b..4410e4166c6c 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -163,6 +163,12 @@ extern int usbnet_resume(struct usb_interface *);
 extern void usbnet_disconnect(struct usb_interface *);
 extern void usbnet_device_suggests_idle(struct usbnet *dev);
 
+extern int usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
+		    u16 value, u16 index, void *data, u16 size);
+extern int usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
+		    u16 value, u16 index, const void *data, u16 size);
+extern int usbnet_write_cmd_async(struct usbnet *dev, u8 cmd, u8 reqtype,
+		    u16 value, u16 index, const void *data, u16 size);
 
 /* Drivers that reuse some of the standard USB CDC infrastructure
  * (notably, using multiple interfaces according to the CDC
-- 
cgit v1.2.3-55-g7522


From 920750ce38520da9d3e5e6f5bccb0a2b88da4d7d Mon Sep 17 00:00:00 2001
From: Daniel Wagner
Date: Thu, 25 Oct 2012 04:16:56 +0000
Subject: cgroup: net_cls: Fix local variable type decleration

The classid type used throughout the kernel is u32.

Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: <netdev@vger.kernel.org>
Cc: <cgroups@vger.kernel.org>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/cls_cgroup.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index b6a6eeb3905f..0fee0617fb7d 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -29,7 +29,7 @@ extern void sock_update_classid(struct sock *sk);
 #if IS_BUILTIN(CONFIG_NET_CLS_CGROUP)
 static inline u32 task_cls_classid(struct task_struct *p)
 {
-	int classid;
+	u32 classid;
 
 	if (in_interrupt())
 		return 0;
-- 
cgit v1.2.3-55-g7522


From fd9a08a7b83074e34c13c6340f673f7a51f53489 Mon Sep 17 00:00:00 2001
From: Daniel Wagner
Date: Thu, 25 Oct 2012 04:16:58 +0000
Subject: cgroup: net_cls: Pass in task to sock_update_classid()

sock_update_classid() assumes that the update operation always are
applied on the current task. sock_update_classid() needs to know on
which tasks to work on in order to be able to migrate task between
cgroups using the struct cgroup_subsys attach() callback.

Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Glauber Costa <glommer@parallels.com>
Cc: Joe Perches <joe@perches.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Stanislav Kinsbursky <skinsbursky@parallels.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: <netdev@vger.kernel.org>
Cc: <cgroups@vger.kernel.org>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c        | 2 +-
 include/net/cls_cgroup.h | 2 +-
 net/core/sock.c          | 6 +++---
 net/socket.c             | 8 ++++----
 4 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 0873cdcf39be..e4858b20bf11 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -587,7 +587,7 @@ static struct sk_buff *tun_alloc_skb(struct tun_struct *tun,
 	struct sk_buff *skb;
 	int err;
 
-	sock_update_classid(sk);
+	sock_update_classid(sk, current);
 
 	/* Under a page?  Don't bother with paged skb. */
 	if (prepad + len < PAGE_SIZE || !linear)
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index 0fee0617fb7d..571de6efad8f 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -24,7 +24,7 @@ struct cgroup_cls_state
 	u32 classid;
 };
 
-extern void sock_update_classid(struct sock *sk);
+extern void sock_update_classid(struct sock *sk, struct task_struct *task);
 
 #if IS_BUILTIN(CONFIG_NET_CLS_CGROUP)
 static inline u32 task_cls_classid(struct task_struct *p)
diff --git a/net/core/sock.c b/net/core/sock.c
index 9fedbbfb0708..0a023b8daa55 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1217,11 +1217,11 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
 
 #ifdef CONFIG_CGROUPS
 #if IS_ENABLED(CONFIG_NET_CLS_CGROUP)
-void sock_update_classid(struct sock *sk)
+void sock_update_classid(struct sock *sk, struct task_struct *task)
 {
 	u32 classid;
 
-	classid = task_cls_classid(current);
+	classid = task_cls_classid(task);
 	if (classid != sk->sk_classid)
 		sk->sk_classid = classid;
 }
@@ -1264,7 +1264,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		sock_net_set(sk, get_net(net));
 		atomic_set(&sk->sk_wmem_alloc, 1);
 
-		sock_update_classid(sk);
+		sock_update_classid(sk, current);
 		sock_update_netprioidx(sk, current);
 	}
 
diff --git a/net/socket.c b/net/socket.c
index d92c490e66fa..f1a481ab7532 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -620,7 +620,7 @@ static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock_iocb *si = kiocb_to_siocb(iocb);
 
-	sock_update_classid(sock->sk);
+	sock_update_classid(sock->sk, current);
 
 	si->sock = sock;
 	si->scm = NULL;
@@ -784,7 +784,7 @@ static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock_iocb *si = kiocb_to_siocb(iocb);
 
-	sock_update_classid(sock->sk);
+	sock_update_classid(sock->sk, current);
 
 	si->sock = sock;
 	si->scm = NULL;
@@ -896,7 +896,7 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 	if (unlikely(!sock->ops->splice_read))
 		return -EINVAL;
 
-	sock_update_classid(sock->sk);
+	sock_update_classid(sock->sk, current);
 
 	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
 }
@@ -3437,7 +3437,7 @@ EXPORT_SYMBOL(kernel_setsockopt);
 int kernel_sendpage(struct socket *sock, struct page *page, int offset,
 		    size_t size, int flags)
 {
-	sock_update_classid(sock->sk);
+	sock_update_classid(sock->sk, current);
 
 	if (sock->ops->sendpage)
 		return sock->ops->sendpage(sock, page, offset, size, flags);
-- 
cgit v1.2.3-55-g7522


From dc95a2c00671cf383cd037d943fbfe178f9ba81a Mon Sep 17 00:00:00 2001
From: David S. Miller
Date: Fri, 26 Oct 2012 05:07:00 -0400
Subject: net: Update args to dummy sock_update_classid().

Only the real implementation got updated.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/cls_cgroup.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index 571de6efad8f..2581638f4a3d 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -61,7 +61,7 @@ static inline u32 task_cls_classid(struct task_struct *p)
 }
 #endif
 #else /* !CGROUP_NET_CLS_CGROUP */
-static inline void sock_update_classid(struct sock *sk)
+static inline void sock_update_classid(struct sock *sk, struct task_struct *task)
 {
 }
 
-- 
cgit v1.2.3-55-g7522


From 1041638f2bba0f1de75e66086d50fb1251d64dcf Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Fri, 19 Oct 2012 15:44:42 +0200
Subject: mac80211: add explicit AP/GO driver operations

Depending on the driver, a lot of setup may be
necessary to start operating as an AP, some of
which may fail. Add an explicit AP start driver
method to make such failures easier to handle,
and add an AP stop driver method for symmetry.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    | 10 ++++++++++
 net/mac80211/cfg.c        | 11 +++++++++++
 net/mac80211/driver-ops.h | 25 +++++++++++++++++++++++++
 net/mac80211/pm.c         |  4 ++++
 net/mac80211/trace.h      | 37 +++++++++++++++++++++++++++++++++++++
 net/mac80211/util.c       |  6 +++++-
 6 files changed, 92 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 00b7204708bd..5f5327452c9a 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2381,6 +2381,13 @@ enum ieee80211_rate_control_changed {
  *	to vif. Possible use is for hw queue remapping.
  * @unassign_vif_chanctx: Notifies device driver about channel context being
  *	unbound from vif.
+ * @start_ap: Start operation on the AP interface, this is called after all the
+ *	information in bss_conf is set and beacon can be retrieved. A channel
+ *	context is bound before this is called. Note that if the driver uses
+ *	software scan or ROC, this (and @stop_ap) isn't called when the AP is
+ *	just "paused" for scanning/ROC, which is indicated by the beacon being
+ *	disabled/enabled via @bss_info_changed.
+ * @stop_ap: Stop operation on the AP interface.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -2406,6 +2413,9 @@ struct ieee80211_ops {
 				 struct ieee80211_bss_conf *info,
 				 u32 changed);
 
+	int (*start_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
+	void (*stop_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
+
 	u64 (*prepare_multicast)(struct ieee80211_hw *hw,
 				 struct netdev_hw_addr_list *mc_list);
 	void (*configure_filter)(struct ieee80211_hw *hw,
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 95bf3d5d009f..34fd3eba3090 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -922,6 +922,15 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		return err;
 	changed |= err;
 
+	err = drv_start_ap(sdata->local, sdata);
+	if (err) {
+		old = rtnl_dereference(sdata->u.ap.beacon);
+		if (old)
+			kfree_rcu(old, rcu_head);
+		RCU_INIT_POINTER(sdata->u.ap.beacon, NULL);
+		return err;
+	}
+
 	ieee80211_bss_info_change_notify(sdata, changed);
 
 	netif_carrier_on(dev);
@@ -979,6 +988,8 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	sta_info_flush(local, sdata);
 	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED);
 
+	drv_stop_ap(sdata->local, sdata);
+
 	/* free all potentially still buffered bcast frames */
 	local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf);
 	skb_queue_purge(&sdata->u.ap.ps.bc_buf);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 77407b31e1ff..1701ad7013a4 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -936,4 +936,29 @@ static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline int drv_start_ap(struct ieee80211_local *local,
+			       struct ieee80211_sub_if_data *sdata)
+{
+	int ret = 0;
+
+	check_sdata_in_driver(sdata);
+
+	trace_drv_start_ap(local, sdata, &sdata->vif.bss_conf);
+	if (local->ops->start_ap)
+		ret = local->ops->start_ap(&local->hw, &sdata->vif);
+	trace_drv_return_int(local, ret);
+	return ret;
+}
+
+static inline void drv_stop_ap(struct ieee80211_local *local,
+			       struct ieee80211_sub_if_data *sdata)
+{
+	check_sdata_in_driver(sdata);
+
+	trace_drv_stop_ap(local, sdata);
+	if (local->ops->stop_ap)
+		local->ops->stop_ap(&local->hw, &sdata->vif);
+	trace_drv_return_void(local);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 9f404ac901ab..0f1c434638bc 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -135,6 +135,10 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 		ieee80211_bss_info_change_notify(sdata,
 			BSS_CHANGED_BEACON_ENABLED);
 
+		if (sdata->vif.type == NL80211_IFTYPE_AP &&
+		    rcu_access_pointer(sdata->u.ap.beacon))
+			drv_stop_ap(local, sdata);
+
 		/* the interface is leaving the channel and is removed */
 		ieee80211_vif_release_channel(sdata);
 		drv_remove_interface(local, sdata);
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 0638541b625f..5e74e77cba9a 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -1396,6 +1396,43 @@ DEFINE_EVENT(local_sdata_chanctx, drv_unassign_vif_chanctx,
 	TP_ARGS(local, sdata, ctx)
 );
 
+TRACE_EVENT(drv_start_ap,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_bss_conf *info),
+
+	TP_ARGS(local, sdata, info),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		__field(u8, dtimper)
+		__field(u16, bcnint)
+		__dynamic_array(u8, ssid, info->ssid_len);
+		__field(bool, hidden_ssid);
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		__entry->dtimper = info->dtim_period;
+		__entry->bcnint = info->beacon_int;
+		memcpy(__get_dynamic_array(ssid), info->ssid, info->ssid_len);
+		__entry->hidden_ssid = info->hidden_ssid;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT  VIF_PR_FMT,
+		LOCAL_PR_ARG, VIF_PR_ARG
+	)
+);
+
+DEFINE_EVENT(local_sdata_evt, drv_stop_ap,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata),
+	TP_ARGS(local, sdata)
+);
+
 /*
  * Tracing for API calls that drivers call.
  */
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index ea8a6744a9db..dd0e6f20fc51 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1467,9 +1467,13 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		case NL80211_IFTYPE_AP:
 			changed |= BSS_CHANGED_SSID;
 
-			if (sdata->vif.type == NL80211_IFTYPE_AP)
+			if (sdata->vif.type == NL80211_IFTYPE_AP) {
 				changed |= BSS_CHANGED_AP_PROBE_RESP;
 
+				if (rcu_access_pointer(sdata->u.ap.beacon))
+					drv_start_ap(local, sdata);
+			}
+
 			/* fall through */
 		case NL80211_IFTYPE_MESH_POINT:
 			changed |= BSS_CHANGED_BEACON |
-- 
cgit v1.2.3-55-g7522


From 91872392f08486f692887d2f06a333f512648f22 Mon Sep 17 00:00:00 2001
From: Borislav Petkov
Date: Tue, 9 Oct 2012 19:52:05 +0200
Subject: drivers/base: Add a DEVICE_BOOL_ATTR macro

... which, analogous to DEVICE_INT_ATTR provides functionality to
set/clear bools. Its purpose is to be used where values need to be used
as booleans in configuration context.

Next patch uses this.

Signed-off-by: Borislav Petkov <bp@alien8.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Tony Luck <tony.luck@intel.com>
---
 drivers/base/core.c    | 21 +++++++++++++++++++++
 include/linux/device.h |  7 +++++++
 2 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index abea76c36a4b..c8ae1f6b01b9 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -171,6 +171,27 @@ ssize_t device_show_int(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(device_show_int);
 
+ssize_t device_store_bool(struct device *dev, struct device_attribute *attr,
+			  const char *buf, size_t size)
+{
+	struct dev_ext_attribute *ea = to_ext_attr(attr);
+
+	if (strtobool(buf, ea->var) < 0)
+		return -EINVAL;
+
+	return size;
+}
+EXPORT_SYMBOL_GPL(device_store_bool);
+
+ssize_t device_show_bool(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct dev_ext_attribute *ea = to_ext_attr(attr);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", *(bool *)(ea->var));
+}
+EXPORT_SYMBOL_GPL(device_show_bool);
+
 /**
  *	device_release - free device structure.
  *	@kobj:	device's kobject.
diff --git a/include/linux/device.h b/include/linux/device.h
index 86ef6ab553b1..50c85a26b003 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -496,6 +496,10 @@ ssize_t device_show_int(struct device *dev, struct device_attribute *attr,
 			char *buf);
 ssize_t device_store_int(struct device *dev, struct device_attribute *attr,
 			 const char *buf, size_t count);
+ssize_t device_show_bool(struct device *dev, struct device_attribute *attr,
+			char *buf);
+ssize_t device_store_bool(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count);
 
 #define DEVICE_ATTR(_name, _mode, _show, _store) \
 	struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store)
@@ -505,6 +509,9 @@ ssize_t device_store_int(struct device *dev, struct device_attribute *attr,
 #define DEVICE_INT_ATTR(_name, _mode, _var) \
 	struct dev_ext_attribute dev_attr_##_name = \
 		{ __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) }
+#define DEVICE_BOOL_ATTR(_name, _mode, _var) \
+	struct dev_ext_attribute dev_attr_##_name = \
+		{ __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) }
 #define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \
 	struct device_attribute dev_attr_##_name =		\
 		__ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store)
-- 
cgit v1.2.3-55-g7522


From b2656a138ab7bc4e7abd3b1cbd6d1f105c7a7186 Mon Sep 17 00:00:00 2001
From: Will Deacon
Date: Wed, 17 Oct 2012 16:45:01 +0100
Subject: asm-generic: io: remove {read,write} string functions

The {read,write}s{b,w,l} functions are not defined across all
architectures and therefore shouldn't be used by portable drivers. We
should encourage driver writers to use the io{read,write}{8,16,32}_rep
functions instead.

This patch removes the {read,write} string functions for the generic IO
header as they have no place in a new architecture port.

Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Ben Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 include/asm-generic/io.h | 30 ------------------------------
 1 file changed, 30 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 616eea53d633..063ce7640910 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -216,36 +216,6 @@ static inline void outsl(unsigned long addr, const void *buffer, int count)
 }
 #endif
 
-static inline void readsl(const void __iomem *addr, void *buf, int len)
-{
-	insl(addr - PCI_IOBASE, buf, len);
-}
-
-static inline void readsw(const void __iomem *addr, void *buf, int len)
-{
-	insw(addr - PCI_IOBASE, buf, len);
-}
-
-static inline void readsb(const void __iomem *addr, void *buf, int len)
-{
-	insb(addr - PCI_IOBASE, buf, len);
-}
-
-static inline void writesl(const void __iomem *addr, const void *buf, int len)
-{
-	outsl(addr - PCI_IOBASE, buf, len);
-}
-
-static inline void writesw(const void __iomem *addr, const void *buf, int len)
-{
-	outsw(addr - PCI_IOBASE, buf, len);
-}
-
-static inline void writesb(const void __iomem *addr, const void *buf, int len)
-{
-	outsb(addr - PCI_IOBASE, buf, len);
-}
-
 #ifndef CONFIG_GENERIC_IOMAP
 #define ioread8(addr)		readb(addr)
 #define ioread16(addr)		readw(addr)
-- 
cgit v1.2.3-55-g7522


From 7e2afc9d072b9f84b314b208a125c2b1ce36b685 Mon Sep 17 00:00:00 2001
From: Arron Wang
Date: Thu, 27 Sep 2012 17:32:54 +0800
Subject: NFC: Set local gb and DEP registries

Set the local general bytes and default value for NFCIP1
Target/Initiator registries if the protocol is NFC-DEP

Signed-off-by: Arron Wang <arron.wang@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/pn544_hci.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/net/nfc/hci.h   |  3 +++
 2 files changed, 65 insertions(+)

(limited to 'include')

diff --git a/drivers/nfc/pn544_hci.c b/drivers/nfc/pn544_hci.c
index c9c8570273ab..8b21a8efd751 100644
--- a/drivers/nfc/pn544_hci.c
+++ b/drivers/nfc/pn544_hci.c
@@ -100,6 +100,10 @@ enum pn544_state {
 #define PN544_SYS_MGMT_INFO_NOTIFICATION	0x02
 
 #define PN544_POLLING_LOOP_MGMT_GATE		0x94
+#define PN544_DEP_MODE				0x01
+#define PN544_DEP_ATR_REQ			0x02
+#define PN544_DEP_ATR_RES			0x03
+#define PN544_DEP_MERGE				0x0D
 #define PN544_PL_RDPHASES			0x06
 #define PN544_PL_EMULATION			0x07
 #define PN544_PL_NFCT_DEACTIVATED		0x09
@@ -630,6 +634,9 @@ static int pn544_hci_start_poll(struct nfc_hci_dev *hdev,
 	int r;
 	u8 duration[2];
 	u8 activated;
+	u8 i_mode = 0x3f; /* Enable all supported modes */
+	u8 t_mode = 0x0f;
+	u8 t_merge = 0x01; /* Enable merge by default */
 
 	pr_info(DRIVER_DESC ": %s protocols 0x%x 0x%x\n",
 		__func__, im_protocols, tm_protocols);
@@ -667,6 +674,61 @@ static int pn544_hci_start_poll(struct nfc_hci_dev *hdev,
 	if (r < 0)
 		return r;
 
+	if ((im_protocols | tm_protocols) & NFC_PROTO_NFC_DEP_MASK) {
+		hdev->gb = nfc_get_local_general_bytes(hdev->ndev,
+							&hdev->gb_len);
+		pr_debug("generate local bytes %p", hdev->gb);
+		if (hdev->gb == NULL || hdev->gb_len == 0) {
+			im_protocols &= ~NFC_PROTO_NFC_DEP_MASK;
+			tm_protocols &= ~NFC_PROTO_NFC_DEP_MASK;
+		}
+	}
+
+	if (im_protocols & NFC_PROTO_NFC_DEP_MASK) {
+		r = nfc_hci_send_event(hdev,
+				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+				NFC_HCI_EVT_END_OPERATION, NULL, 0);
+		if (r < 0)
+			return r;
+
+		r = nfc_hci_set_param(hdev,
+				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+				PN544_DEP_MODE, &i_mode, 1);
+		if (r < 0)
+			return r;
+
+		r = nfc_hci_set_param(hdev,
+				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+				PN544_DEP_ATR_REQ, hdev->gb, hdev->gb_len);
+		if (r < 0)
+			return r;
+
+		r = nfc_hci_send_event(hdev,
+				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+				NFC_HCI_EVT_READER_REQUESTED, NULL, 0);
+		if (r < 0)
+			nfc_hci_send_event(hdev,
+					PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+					NFC_HCI_EVT_END_OPERATION, NULL, 0);
+	}
+
+	if (tm_protocols & NFC_PROTO_NFC_DEP_MASK) {
+		r = nfc_hci_set_param(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
+				PN544_DEP_MODE, &t_mode, 1);
+		if (r < 0)
+			return r;
+
+		r = nfc_hci_set_param(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
+				PN544_DEP_ATR_RES, hdev->gb, hdev->gb_len);
+		if (r < 0)
+			return r;
+
+		r = nfc_hci_set_param(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
+				PN544_DEP_MERGE, &t_merge, 1);
+		if (r < 0)
+			return r;
+	}
+
 	r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
 			       NFC_HCI_EVT_READER_REQUESTED, NULL, 0);
 	if (r < 0)
diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index e900072950cb..df6523dcd3c8 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -114,6 +114,9 @@ struct nfc_hci_dev {
 	int async_cb_type;
 	data_exchange_cb_t async_cb;
 	void *async_cb_context;
+
+	u8 *gb;
+	size_t gb_len;
 };
 
 /* hci device allocation */
-- 
cgit v1.2.3-55-g7522


From f7a5f6c532f33ba66a7ca19e81ed447a83dab2db Mon Sep 17 00:00:00 2001
From: Arron Wang
Date: Thu, 27 Sep 2012 17:32:55 +0800
Subject: NFC: Pass hardware specific HCI event to driver

Signed-off-by: Arron Wang <arron.wang@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/pn544_hci.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
 include/net/nfc/hci.h   |  3 +++
 net/nfc/hci/core.c      | 12 +++++++++---
 3 files changed, 57 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/nfc/pn544_hci.c b/drivers/nfc/pn544_hci.c
index 8b21a8efd751..d81242f4a92b 100644
--- a/drivers/nfc/pn544_hci.c
+++ b/drivers/nfc/pn544_hci.c
@@ -112,6 +112,12 @@ enum pn544_state {
 
 #define PN544_NFC_WI_MGMT_GATE			0xA1
 
+#define PN544_HCI_EVT_SND_DATA			0x01
+#define PN544_HCI_EVT_ACTIVATED			0x02
+#define PN544_HCI_EVT_DEACTIVATED		0x03
+#define PN544_HCI_EVT_RCV_DATA			0x04
+#define PN544_HCI_EVT_CONTINUE_MI		0x05
+
 static struct nfc_hci_gate pn544_gates[] = {
 	{NFC_HCI_ADMIN_GATE, NFC_HCI_INVALID_PIPE},
 	{NFC_HCI_LOOPBACK_GATE, NFC_HCI_INVALID_PIPE},
@@ -897,6 +903,44 @@ static int pn544_hci_check_presence(struct nfc_hci_dev *hdev,
 				NULL, 0, NULL);
 }
 
+void pn544_hci_event_received(struct nfc_hci_dev *hdev, u8 gate, u8 event,
+				struct sk_buff *skb)
+{
+	struct sk_buff *rgb_skb = NULL;
+	int r = 0;
+
+	pr_debug("hci event %d", event);
+	switch (event) {
+	case PN544_HCI_EVT_ACTIVATED:
+		if (gate == PN544_RF_READER_NFCIP1_INITIATOR_GATE)
+			nfc_hci_target_discovered(hdev, gate);
+		else if (gate == PN544_RF_READER_NFCIP1_TARGET_GATE) {
+			r = nfc_hci_get_param(hdev, gate, PN544_DEP_ATR_REQ,
+						&rgb_skb);
+
+			if (r < 0)
+				goto exit;
+
+			nfc_tm_activated(hdev->ndev, NFC_PROTO_NFC_DEP_MASK,
+					NFC_COMM_PASSIVE, rgb_skb->data,
+					rgb_skb->len);
+
+			kfree_skb(rgb_skb);
+		}
+
+		break;
+	case PN544_HCI_EVT_DEACTIVATED:
+		nfc_hci_send_event(hdev, gate,
+			NFC_HCI_EVT_END_OPERATION, NULL, 0);
+		break;
+	default:
+		break;
+	}
+
+exit:
+	kfree_skb(skb);
+}
+
 static struct nfc_hci_ops pn544_hci_ops = {
 	.open = pn544_hci_open,
 	.close = pn544_hci_close,
@@ -907,6 +951,7 @@ static struct nfc_hci_ops pn544_hci_ops = {
 	.complete_target_discovered = pn544_hci_complete_target_discovered,
 	.data_exchange = pn544_hci_data_exchange,
 	.check_presence = pn544_hci_check_presence,
+	.event_received = pn544_hci_event_received,
 };
 
 static int __devinit pn544_hci_probe(struct i2c_client *client,
diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index df6523dcd3c8..490d323a9ec3 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -47,6 +47,8 @@ struct nfc_hci_ops {
 			      data_exchange_cb_t cb, void *cb_context);
 	int (*check_presence)(struct nfc_hci_dev *hdev,
 			      struct nfc_target *target);
+	void (*event_received)(struct nfc_hci_dev *hdev, u8 gate, u8 event,
+				struct sk_buff *skb);
 };
 
 /* Pipes */
@@ -222,5 +224,6 @@ int nfc_hci_send_response(struct nfc_hci_dev *hdev, u8 gate, u8 response,
 			  const u8 *param, size_t param_len);
 int nfc_hci_send_event(struct nfc_hci_dev *hdev, u8 gate, u8 event,
 		       const u8 *param, size_t param_len);
+int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate);
 
 #endif /* __NET_HCI_H */
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 5fbb6e40793e..8a9a811b558a 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -182,7 +182,7 @@ static u32 nfc_hci_sak_to_protocol(u8 sak)
 	}
 }
 
-static int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate)
+int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate)
 {
 	struct nfc_target *targets;
 	struct sk_buff *atqa_skb = NULL;
@@ -275,6 +275,7 @@ exit:
 
 	return r;
 }
+EXPORT_SYMBOL(nfc_hci_target_discovered);
 
 void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event,
 			    struct sk_buff *skb)
@@ -307,8 +308,13 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event,
 					      nfc_hci_pipe2gate(hdev, pipe));
 		break;
 	default:
-		/* TODO: Unknown events are hardware specific
-		 * pass them to the driver (needs a new hci_ops) */
+		if (hdev->ops->event_received) {
+			hdev->ops->event_received(hdev,
+						nfc_hci_pipe2gate(hdev, pipe),
+						event, skb);
+			return;
+		}
+
 		break;
 	}
 
-- 
cgit v1.2.3-55-g7522


From c40d17401f89f575a6ff5774abaa0838398b820c Mon Sep 17 00:00:00 2001
From: Arron Wang
Date: Thu, 27 Sep 2012 17:32:57 +0800
Subject: NFC: Implement HCI DEP link up and down

And implement the corresponding hooks for pn544.

Signed-off-by: Arron Wang <arron.wang@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/pn544_hci.c | 39 +++++++++++++++++++++++++++++++++++++++
 include/net/nfc/hci.h   |  3 +++
 net/nfc/hci/core.c      | 24 ++++++++++++++++++++++++
 3 files changed, 66 insertions(+)

(limited to 'include')

diff --git a/drivers/nfc/pn544_hci.c b/drivers/nfc/pn544_hci.c
index 6d564bd8b3b4..4ed2b8356017 100644
--- a/drivers/nfc/pn544_hci.c
+++ b/drivers/nfc/pn544_hci.c
@@ -746,6 +746,43 @@ static int pn544_hci_start_poll(struct nfc_hci_dev *hdev,
 	return r;
 }
 
+static int pn544_hci_dep_link_up(struct nfc_hci_dev *hdev,
+				struct nfc_target *target, u8 comm_mode,
+				u8 *gb, size_t gb_len)
+{
+	struct sk_buff *rgb_skb = NULL;
+	int r;
+
+	r = nfc_hci_get_param(hdev, target->hci_reader_gate,
+				PN544_DEP_ATR_RES, &rgb_skb);
+	if (r < 0)
+		return r;
+
+	if (rgb_skb->len == 0 || rgb_skb->len > NFC_GB_MAXSIZE) {
+		r = -EPROTO;
+		goto exit;
+	}
+	print_hex_dump(KERN_DEBUG, "remote gb: ", DUMP_PREFIX_OFFSET,
+			16, 1, rgb_skb->data, rgb_skb->len, true);
+
+	r = nfc_set_remote_general_bytes(hdev->ndev, rgb_skb->data,
+						rgb_skb->len);
+
+	if (r == 0)
+		r = nfc_dep_link_is_up(hdev->ndev, target->idx, comm_mode,
+					NFC_RF_INITIATOR);
+exit:
+	kfree_skb(rgb_skb);
+	return r;
+}
+
+static int pn544_hci_dep_link_down(struct nfc_hci_dev *hdev)
+{
+
+	return nfc_hci_send_event(hdev, PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+					NFC_HCI_EVT_END_OPERATION, NULL, 0);
+}
+
 static int pn544_hci_target_from_gate(struct nfc_hci_dev *hdev, u8 gate,
 				      struct nfc_target *target)
 {
@@ -973,6 +1010,8 @@ static struct nfc_hci_ops pn544_hci_ops = {
 	.hci_ready = pn544_hci_ready,
 	.xmit = pn544_hci_xmit,
 	.start_poll = pn544_hci_start_poll,
+	.dep_link_up = pn544_hci_dep_link_up,
+	.dep_link_down = pn544_hci_dep_link_down,
 	.target_from_gate = pn544_hci_target_from_gate,
 	.complete_target_discovered = pn544_hci_complete_target_discovered,
 	.data_exchange = pn544_hci_data_exchange,
diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 490d323a9ec3..6b2d75dc7c01 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -38,6 +38,9 @@ struct nfc_hci_ops {
 	int (*xmit) (struct nfc_hci_dev *hdev, struct sk_buff *skb);
 	int (*start_poll) (struct nfc_hci_dev *hdev,
 			   u32 im_protocols, u32 tm_protocols);
+	int (*dep_link_up)(struct nfc_hci_dev *hdev, struct nfc_target *target,
+			   u8 comm_mode, u8 *gb, size_t gb_len);
+	int (*dep_link_down)(struct nfc_hci_dev *hdev);
 	int (*target_from_gate) (struct nfc_hci_dev *hdev, u8 gate,
 				 struct nfc_target *target);
 	int (*complete_target_discovered) (struct nfc_hci_dev *hdev, u8 gate,
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 052a0a27ac1a..777deb84aa73 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -546,6 +546,28 @@ static void hci_stop_poll(struct nfc_dev *nfc_dev)
 			   NFC_HCI_EVT_END_OPERATION, NULL, 0);
 }
 
+static int hci_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target,
+				__u8 comm_mode, __u8 *gb, size_t gb_len)
+{
+	struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev);
+
+	if (hdev->ops->dep_link_up)
+		return hdev->ops->dep_link_up(hdev, target, comm_mode,
+						gb, gb_len);
+
+	return 0;
+}
+
+static int hci_dep_link_down(struct nfc_dev *nfc_dev)
+{
+	struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev);
+
+	if (hdev->ops->dep_link_down)
+		return hdev->ops->dep_link_down(hdev);
+
+	return 0;
+}
+
 static int hci_activate_target(struct nfc_dev *nfc_dev,
 			       struct nfc_target *target, u32 protocol)
 {
@@ -731,6 +753,8 @@ static struct nfc_ops hci_nfc_ops = {
 	.dev_down = hci_dev_down,
 	.start_poll = hci_start_poll,
 	.stop_poll = hci_stop_poll,
+	.dep_link_up = hci_dep_link_up,
+	.dep_link_down = hci_dep_link_down,
 	.activate_target = hci_activate_target,
 	.deactivate_target = hci_deactivate_target,
 	.im_transceive = hci_transceive,
-- 
cgit v1.2.3-55-g7522


From e81076235b46189a776362ec5e4c6626bf1599ff Mon Sep 17 00:00:00 2001
From: Arron Wang
Date: Thu, 27 Sep 2012 17:32:58 +0800
Subject: NFC: Implement HCI DEP send and receive data

And implement the corresponding hooks for pn544.

Signed-off-by: Arron Wang <arron.wang@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/pn544_hci.c | 36 ++++++++++++++++++++++++++++++++++--
 include/net/nfc/hci.h   |  3 ++-
 net/nfc/hci/core.c      | 19 +++++++++++++++----
 3 files changed, 51 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/nfc/pn544_hci.c b/drivers/nfc/pn544_hci.c
index 4ed2b8356017..554faf0a92d7 100644
--- a/drivers/nfc/pn544_hci.c
+++ b/drivers/nfc/pn544_hci.c
@@ -900,7 +900,7 @@ static void pn544_hci_data_exchange_cb(void *context, struct sk_buff *skb,
  * <= 0: driver handled the data exchange
  *    1: driver doesn't especially handle, please do standard processing
  */
-static int pn544_hci_data_exchange(struct nfc_hci_dev *hdev,
+static int pn544_hci_im_transceive(struct nfc_hci_dev *hdev,
 				   struct nfc_target *target,
 				   struct sk_buff *skb, data_exchange_cb_t cb,
 				   void *cb_context)
@@ -953,11 +953,26 @@ static int pn544_hci_data_exchange(struct nfc_hci_dev *hdev,
 		return nfc_hci_send_cmd_async(hdev, target->hci_reader_gate,
 					      PN544_JEWEL_RAW_CMD, skb->data,
 					      skb->len, cb, cb_context);
+	case PN544_RF_READER_NFCIP1_INITIATOR_GATE:
+		*skb_push(skb, 1) = 0;
+
+		return nfc_hci_send_event(hdev, target->hci_reader_gate,
+					PN544_HCI_EVT_SND_DATA, skb->data,
+					skb->len);
 	default:
 		return 1;
 	}
 }
 
+static int pn544_hci_tm_send(struct nfc_hci_dev *hdev, struct sk_buff *skb)
+{
+	/* Set default false for multiple information chaining */
+	*skb_push(skb, 1) = 0;
+
+	return nfc_hci_send_event(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
+				PN544_HCI_EVT_SND_DATA, skb->data, skb->len);
+}
+
 static int pn544_hci_check_presence(struct nfc_hci_dev *hdev,
 				   struct nfc_target *target)
 {
@@ -996,6 +1011,22 @@ void pn544_hci_event_received(struct nfc_hci_dev *hdev, u8 gate, u8 event,
 		nfc_hci_send_event(hdev, gate,
 			NFC_HCI_EVT_END_OPERATION, NULL, 0);
 		break;
+	case PN544_HCI_EVT_RCV_DATA:
+		if (skb->len < 2) {
+			r = -EPROTO;
+			goto exit;
+		}
+
+		if (skb->data[0] != 0) {
+			pr_debug("data0 %d", skb->data[0]);
+			r = -EPROTO;
+			goto exit;
+		}
+
+		skb_pull(skb, 2);
+		nfc_tm_data_received(hdev->ndev, skb);
+
+		return;
 	default:
 		break;
 	}
@@ -1014,7 +1045,8 @@ static struct nfc_hci_ops pn544_hci_ops = {
 	.dep_link_down = pn544_hci_dep_link_down,
 	.target_from_gate = pn544_hci_target_from_gate,
 	.complete_target_discovered = pn544_hci_complete_target_discovered,
-	.data_exchange = pn544_hci_data_exchange,
+	.im_transceive = pn544_hci_im_transceive,
+	.tm_send = pn544_hci_tm_send,
 	.check_presence = pn544_hci_check_presence,
 	.event_received = pn544_hci_event_received,
 };
diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 6b2d75dc7c01..bc87b8f2d692 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -45,9 +45,10 @@ struct nfc_hci_ops {
 				 struct nfc_target *target);
 	int (*complete_target_discovered) (struct nfc_hci_dev *hdev, u8 gate,
 					   struct nfc_target *target);
-	int (*data_exchange) (struct nfc_hci_dev *hdev,
+	int (*im_transceive) (struct nfc_hci_dev *hdev,
 			      struct nfc_target *target, struct sk_buff *skb,
 			      data_exchange_cb_t cb, void *cb_context);
+	int (*tm_send)(struct nfc_hci_dev *hdev, struct sk_buff *skb);
 	int (*check_presence)(struct nfc_hci_dev *hdev,
 			      struct nfc_target *target);
 	void (*event_received)(struct nfc_hci_dev *hdev, u8 gate, u8 event,
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 777deb84aa73..c2339c468d91 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -616,8 +616,8 @@ static int hci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	switch (target->hci_reader_gate) {
 	case NFC_HCI_RF_READER_A_GATE:
 	case NFC_HCI_RF_READER_B_GATE:
-		if (hdev->ops->data_exchange) {
-			r = hdev->ops->data_exchange(hdev, target, skb, cb,
+		if (hdev->ops->im_transceive) {
+			r = hdev->ops->im_transceive(hdev, target, skb, cb,
 						     cb_context);
 			if (r <= 0)	/* handled */
 				break;
@@ -634,8 +634,8 @@ static int hci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 					   skb->len, hci_transceive_cb, hdev);
 		break;
 	default:
-		if (hdev->ops->data_exchange) {
-			r = hdev->ops->data_exchange(hdev, target, skb, cb,
+		if (hdev->ops->im_transceive) {
+			r = hdev->ops->im_transceive(hdev, target, skb, cb,
 						     cb_context);
 			if (r == 1)
 				r = -ENOTSUPP;
@@ -650,6 +650,16 @@ static int hci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	return r;
 }
 
+int hci_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb)
+{
+	struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev);
+
+	if (hdev->ops->tm_send)
+		return hdev->ops->tm_send(hdev, skb);
+	else
+		return -ENOTSUPP;
+}
+
 static int hci_check_presence(struct nfc_dev *nfc_dev,
 			      struct nfc_target *target)
 {
@@ -758,6 +768,7 @@ static struct nfc_ops hci_nfc_ops = {
 	.activate_target = hci_activate_target,
 	.deactivate_target = hci_deactivate_target,
 	.im_transceive = hci_transceive,
+	.tm_send = hci_tm_send,
 	.check_presence = hci_check_presence,
 };
 
-- 
cgit v1.2.3-55-g7522


From 97f18414af395c547f20300e5d4c81d7190a4155 Mon Sep 17 00:00:00 2001
From: Eric Lapuyade
Date: Tue, 2 Oct 2012 18:44:06 +0200
Subject: NFC: Separate pn544 hci driver in HW dependant and independant parts

The driver now has all HCI stuff isolated in one file, and all the
hardware link specifics in another. Writing a pn544 driver on top of
another hardware link is now just a matter of adding a new file for that
new hardware specifics.

Signed-off-by: Eric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/Makefile       |    2 +-
 drivers/nfc/pn544/Makefile |    7 +
 drivers/nfc/pn544/i2c.c    |  500 ++++++++++++++++++
 drivers/nfc/pn544/pn544.c  |  862 ++++++++++++++++++++++++++++++
 drivers/nfc/pn544/pn544.h  |   32 ++
 drivers/nfc/pn544_hci.c    | 1252 --------------------------------------------
 include/net/nfc/hci.h      |    6 +
 7 files changed, 1408 insertions(+), 1253 deletions(-)
 create mode 100644 drivers/nfc/pn544/Makefile
 create mode 100644 drivers/nfc/pn544/i2c.c
 create mode 100644 drivers/nfc/pn544/pn544.c
 create mode 100644 drivers/nfc/pn544/pn544.h
 delete mode 100644 drivers/nfc/pn544_hci.c

(limited to 'include')

diff --git a/drivers/nfc/Makefile b/drivers/nfc/Makefile
index bf05831fdf09..36c359043f54 100644
--- a/drivers/nfc/Makefile
+++ b/drivers/nfc/Makefile
@@ -2,7 +2,7 @@
 # Makefile for nfc devices
 #
 
-obj-$(CONFIG_PN544_HCI_NFC)	+= pn544_hci.o
+obj-$(CONFIG_PN544_HCI_NFC)	+= pn544/
 obj-$(CONFIG_NFC_PN533)		+= pn533.o
 obj-$(CONFIG_NFC_WILINK)	+= nfcwilink.o
 
diff --git a/drivers/nfc/pn544/Makefile b/drivers/nfc/pn544/Makefile
new file mode 100644
index 000000000000..725733881eb3
--- /dev/null
+++ b/drivers/nfc/pn544/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for PN544 HCI based NFC driver
+#
+
+obj-$(CONFIG_PN544_HCI_NFC)	+= pn544_i2c.o
+
+pn544_i2c-y		:= pn544.o i2c.o
diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
new file mode 100644
index 000000000000..fb430d882352
--- /dev/null
+++ b/drivers/nfc/pn544/i2c.c
@@ -0,0 +1,500 @@
+/*
+ * I2C Link Layer for PN544 HCI based Driver
+ *
+ * Copyright (C) 2012  Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the
+ * Free Software Foundation, Inc.,
+ * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ */
+
+#include <linux/crc-ccitt.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <linux/miscdevice.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+
+#include <linux/nfc/pn544.h>
+
+#include <net/nfc/hci.h>
+#include <net/nfc/llc.h>
+
+#include "pn544.h"
+
+#define PN544_I2C_FRAME_HEADROOM 1
+#define PN544_I2C_FRAME_TAILROOM 2
+
+/* framing in HCI mode */
+#define PN544_HCI_I2C_LLC_LEN		1
+#define PN544_HCI_I2C_LLC_CRC		2
+#define PN544_HCI_I2C_LLC_LEN_CRC	(PN544_HCI_I2C_LLC_LEN + \
+					 PN544_HCI_I2C_LLC_CRC)
+#define PN544_HCI_I2C_LLC_MIN_SIZE	(1 + PN544_HCI_I2C_LLC_LEN_CRC)
+#define PN544_HCI_I2C_LLC_MAX_PAYLOAD	29
+#define PN544_HCI_I2C_LLC_MAX_SIZE	(PN544_HCI_I2C_LLC_LEN_CRC + 1 + \
+					 PN544_HCI_I2C_LLC_MAX_PAYLOAD)
+
+static struct i2c_device_id pn544_hci_i2c_id_table[] = {
+	{"pn544", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, pn544_hci_i2c_id_table);
+
+#define PN544_HCI_I2C_DRIVER_NAME "pn544_hci_i2c"
+
+struct pn544_i2c_phy {
+	struct i2c_client *i2c_dev;
+	struct nfc_hci_dev *hdev;
+
+	unsigned int gpio_en;
+	unsigned int gpio_irq;
+	unsigned int gpio_fw;
+	unsigned int en_polarity;
+
+	int powered;
+
+	int hard_fault;		/*
+				 * < 0 if hardware error occured (e.g. i2c err)
+				 * and prevents normal operation.
+				 */
+};
+
+#define I2C_DUMP_SKB(info, skb)					\
+do {								\
+	pr_debug("%s:\n", info);				\
+	print_hex_dump(KERN_DEBUG, "i2c: ", DUMP_PREFIX_OFFSET,	\
+		       16, 1, (skb)->data, (skb)->len, 0);	\
+} while (0)
+
+static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy)
+{
+	int polarity, retry, ret;
+	char rset_cmd[] = { 0x05, 0xF9, 0x04, 0x00, 0xC3, 0xE5 };
+	int count = sizeof(rset_cmd);
+
+	pr_info(DRIVER_DESC ": %s\n", __func__);
+	dev_info(&phy->i2c_dev->dev, "Detecting nfc_en polarity\n");
+
+	/* Disable fw download */
+	gpio_set_value(phy->gpio_fw, 0);
+
+	for (polarity = 0; polarity < 2; polarity++) {
+		phy->en_polarity = polarity;
+		retry = 3;
+		while (retry--) {
+			/* power off */
+			gpio_set_value(phy->gpio_en, !phy->en_polarity);
+			usleep_range(10000, 15000);
+
+			/* power on */
+			gpio_set_value(phy->gpio_en, phy->en_polarity);
+			usleep_range(10000, 15000);
+
+			/* send reset */
+			dev_dbg(&phy->i2c_dev->dev, "Sending reset cmd\n");
+			ret = i2c_master_send(phy->i2c_dev, rset_cmd, count);
+			if (ret == count) {
+				dev_info(&phy->i2c_dev->dev,
+					 "nfc_en polarity : active %s\n",
+					 (polarity == 0 ? "low" : "high"));
+				goto out;
+			}
+		}
+	}
+
+	dev_err(&phy->i2c_dev->dev,
+		"Could not detect nfc_en polarity, fallback to active high\n");
+
+out:
+	gpio_set_value(phy->gpio_en, !phy->en_polarity);
+}
+
+static int pn544_hci_i2c_enable(void *phy_id)
+{
+	struct pn544_i2c_phy *phy = phy_id;
+
+	pr_info(DRIVER_DESC ": %s\n", __func__);
+
+	gpio_set_value(phy->gpio_fw, 0);
+	gpio_set_value(phy->gpio_en, phy->en_polarity);
+	usleep_range(10000, 15000);
+
+	phy->powered = 1;
+
+	return 0;
+}
+
+static void pn544_hci_i2c_disable(void *phy_id)
+{
+	struct pn544_i2c_phy *phy = phy_id;
+
+	pr_info(DRIVER_DESC ": %s\n", __func__);
+
+	gpio_set_value(phy->gpio_fw, 0);
+	gpio_set_value(phy->gpio_en, !phy->en_polarity);
+	usleep_range(10000, 15000);
+
+	gpio_set_value(phy->gpio_en, phy->en_polarity);
+	usleep_range(10000, 15000);
+
+	gpio_set_value(phy->gpio_en, !phy->en_polarity);
+	usleep_range(10000, 15000);
+
+	phy->powered = 0;
+}
+
+static void pn544_hci_i2c_add_len_crc(struct sk_buff *skb)
+{
+	u16 crc;
+	int len;
+
+	len = skb->len + 2;
+	*skb_push(skb, 1) = len;
+
+	crc = crc_ccitt(0xffff, skb->data, skb->len);
+	crc = ~crc;
+	*skb_put(skb, 1) = crc & 0xff;
+	*skb_put(skb, 1) = crc >> 8;
+}
+
+static void pn544_hci_i2c_remove_len_crc(struct sk_buff *skb)
+{
+	skb_pull(skb, PN544_I2C_FRAME_HEADROOM);
+	skb_trim(skb, PN544_I2C_FRAME_TAILROOM);
+}
+
+/*
+ * Writing a frame must not return the number of written bytes.
+ * It must return either zero for success, or <0 for error.
+ * In addition, it must not alter the skb
+ */
+static int pn544_hci_i2c_write(void *phy_id, struct sk_buff *skb)
+{
+	int r;
+	struct pn544_i2c_phy *phy = phy_id;
+	struct i2c_client *client = phy->i2c_dev;
+
+	if (phy->hard_fault != 0)
+		return phy->hard_fault;
+
+	usleep_range(3000, 6000);
+
+	pn544_hci_i2c_add_len_crc(skb);
+
+	I2C_DUMP_SKB("i2c frame written", skb);
+
+	r = i2c_master_send(client, skb->data, skb->len);
+
+	if (r == -EREMOTEIO) {	/* Retry, chip was in standby */
+		usleep_range(6000, 10000);
+		r = i2c_master_send(client, skb->data, skb->len);
+	}
+
+	if (r >= 0) {
+		if (r != skb->len)
+			r = -EREMOTEIO;
+		else
+			r = 0;
+	}
+
+	pn544_hci_i2c_remove_len_crc(skb);
+
+	return r;
+}
+
+static int check_crc(u8 *buf, int buflen)
+{
+	int len;
+	u16 crc;
+
+	len = buf[0] + 1;
+	crc = crc_ccitt(0xffff, buf, len - 2);
+	crc = ~crc;
+
+	if (buf[len - 2] != (crc & 0xff) || buf[len - 1] != (crc >> 8)) {
+		pr_err(PN544_HCI_I2C_DRIVER_NAME
+		       ": CRC error 0x%x != 0x%x 0x%x\n",
+		       crc, buf[len - 1], buf[len - 2]);
+
+		pr_info(DRIVER_DESC ": %s : BAD CRC\n", __func__);
+		print_hex_dump(KERN_DEBUG, "crc: ", DUMP_PREFIX_NONE,
+			       16, 2, buf, buflen, false);
+		return -EPERM;
+	}
+	return 0;
+}
+
+/*
+ * Reads an shdlc frame and returns it in a newly allocated sk_buff. Guarantees
+ * that i2c bus will be flushed and that next read will start on a new frame.
+ * returned skb contains only LLC header and payload.
+ * returns:
+ * -EREMOTEIO : i2c read error (fatal)
+ * -EBADMSG : frame was incorrect and discarded
+ * -ENOMEM : cannot allocate skb, frame dropped
+ */
+static int pn544_hci_i2c_read(struct pn544_i2c_phy *phy, struct sk_buff **skb)
+{
+	int r;
+	u8 len;
+	u8 tmp[PN544_HCI_I2C_LLC_MAX_SIZE - 1];
+	struct i2c_client *client = phy->i2c_dev;
+
+	r = i2c_master_recv(client, &len, 1);
+	if (r != 1) {
+		dev_err(&client->dev, "cannot read len byte\n");
+		return -EREMOTEIO;
+	}
+
+	if ((len < (PN544_HCI_I2C_LLC_MIN_SIZE - 1)) ||
+	    (len > (PN544_HCI_I2C_LLC_MAX_SIZE - 1))) {
+		dev_err(&client->dev, "invalid len byte\n");
+		r = -EBADMSG;
+		goto flush;
+	}
+
+	*skb = alloc_skb(1 + len, GFP_KERNEL);
+	if (*skb == NULL) {
+		r = -ENOMEM;
+		goto flush;
+	}
+
+	*skb_put(*skb, 1) = len;
+
+	r = i2c_master_recv(client, skb_put(*skb, len), len);
+	if (r != len) {
+		kfree_skb(*skb);
+		return -EREMOTEIO;
+	}
+
+	I2C_DUMP_SKB("i2c frame read", *skb);
+
+	r = check_crc((*skb)->data, (*skb)->len);
+	if (r != 0) {
+		kfree_skb(*skb);
+		r = -EBADMSG;
+		goto flush;
+	}
+
+	skb_pull(*skb, 1);
+	skb_trim(*skb, (*skb)->len - 2);
+
+	usleep_range(3000, 6000);
+
+	return 0;
+
+flush:
+	if (i2c_master_recv(client, tmp, sizeof(tmp)) < 0)
+		r = -EREMOTEIO;
+
+	usleep_range(3000, 6000);
+
+	return r;
+}
+
+/*
+ * Reads an shdlc frame from the chip. This is not as straightforward as it
+ * seems. There are cases where we could loose the frame start synchronization.
+ * The frame format is len-data-crc, and corruption can occur anywhere while
+ * transiting on i2c bus, such that we could read an invalid len.
+ * In order to recover synchronization with the next frame, we must be sure
+ * to read the real amount of data without using the len byte. We do this by
+ * assuming the following:
+ * - the chip will always present only one single complete frame on the bus
+ *   before triggering the interrupt
+ * - the chip will not present a new frame until we have completely read
+ *   the previous one (or until we have handled the interrupt).
+ * The tricky case is when we read a corrupted len that is less than the real
+ * len. We must detect this here in order to determine that we need to flush
+ * the bus. This is the reason why we check the crc here.
+ */
+static irqreturn_t pn544_hci_i2c_irq_thread_fn(int irq, void *phy_id)
+{
+	struct pn544_i2c_phy *phy = phy_id;
+	struct i2c_client *client;
+	struct sk_buff *skb = NULL;
+	int r;
+
+	if (!phy || irq != phy->i2c_dev->irq) {
+		WARN_ON_ONCE(1);
+		return IRQ_NONE;
+	}
+
+	client = phy->i2c_dev;
+	dev_dbg(&client->dev, "IRQ\n");
+
+	if (phy->hard_fault != 0)
+		return IRQ_HANDLED;
+
+	r = pn544_hci_i2c_read(phy, &skb);
+	if (r == -EREMOTEIO) {
+		phy->hard_fault = r;
+
+		nfc_hci_recv_frame(phy->hdev, NULL);
+
+		return IRQ_HANDLED;
+	} else if ((r == -ENOMEM) || (r == -EBADMSG)) {
+		return IRQ_HANDLED;
+	}
+
+	nfc_hci_recv_frame(phy->hdev, skb);
+
+	return IRQ_HANDLED;
+}
+
+static struct nfc_phy_ops i2c_phy_ops = {
+	.write = pn544_hci_i2c_write,
+	.enable = pn544_hci_i2c_enable,
+	.disable = pn544_hci_i2c_disable,
+};
+
+static int __devinit pn544_hci_i2c_probe(struct i2c_client *client,
+				     const struct i2c_device_id *id)
+{
+	struct pn544_i2c_phy *phy;
+	struct pn544_nfc_platform_data *pdata;
+	int r = 0;
+
+	dev_dbg(&client->dev, "%s\n", __func__);
+	dev_dbg(&client->dev, "IRQ: %d\n", client->irq);
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+		dev_err(&client->dev, "Need I2C_FUNC_I2C\n");
+		return -ENODEV;
+	}
+
+	phy = kzalloc(sizeof(struct pn544_i2c_phy), GFP_KERNEL);
+	if (!phy) {
+		dev_err(&client->dev,
+			"Cannot allocate memory for pn544 i2c phy.\n");
+		r = -ENOMEM;
+		goto err_phy_alloc;
+	}
+
+	phy->i2c_dev = client;
+	i2c_set_clientdata(client, phy);
+
+	pdata = client->dev.platform_data;
+	if (pdata == NULL) {
+		dev_err(&client->dev, "No platform data\n");
+		r = -EINVAL;
+		goto err_pdata;
+	}
+
+	if (pdata->request_resources == NULL) {
+		dev_err(&client->dev, "request_resources() missing\n");
+		r = -EINVAL;
+		goto err_pdata;
+	}
+
+	r = pdata->request_resources(client);
+	if (r) {
+		dev_err(&client->dev, "Cannot get platform resources\n");
+		goto err_pdata;
+	}
+
+	phy->gpio_en = pdata->get_gpio(NFC_GPIO_ENABLE);
+	phy->gpio_fw = pdata->get_gpio(NFC_GPIO_FW_RESET);
+	phy->gpio_irq = pdata->get_gpio(NFC_GPIO_IRQ);
+
+	pn544_hci_i2c_platform_init(phy);
+
+	r = request_threaded_irq(client->irq, NULL, pn544_hci_i2c_irq_thread_fn,
+				 IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+				 PN544_HCI_I2C_DRIVER_NAME, phy);
+	if (r < 0) {
+		dev_err(&client->dev, "Unable to register IRQ handler\n");
+		goto err_rti;
+	}
+
+	r = pn544_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
+			    PN544_I2C_FRAME_HEADROOM, PN544_I2C_FRAME_TAILROOM,
+			    PN544_HCI_I2C_LLC_MAX_PAYLOAD, &phy->hdev);
+	if (r < 0)
+		goto err_hci;
+
+	return 0;
+
+err_hci:
+	free_irq(client->irq, phy);
+
+err_rti:
+	if (pdata->free_resources != NULL)
+		pdata->free_resources();
+
+err_pdata:
+	kfree(phy);
+
+err_phy_alloc:
+	return r;
+}
+
+static __devexit int pn544_hci_i2c_remove(struct i2c_client *client)
+{
+	struct pn544_i2c_phy *phy = i2c_get_clientdata(client);
+	struct pn544_nfc_platform_data *pdata = client->dev.platform_data;
+
+	dev_dbg(&client->dev, "%s\n", __func__);
+
+	pn544_hci_remove(phy->hdev);
+
+	if (phy->powered)
+		pn544_hci_i2c_disable(phy);
+
+	free_irq(client->irq, phy);
+	if (pdata->free_resources)
+		pdata->free_resources();
+
+	kfree(phy);
+
+	return 0;
+}
+
+static struct i2c_driver pn544_hci_i2c_driver = {
+	.driver = {
+		   .name = PN544_HCI_I2C_DRIVER_NAME,
+		  },
+	.probe = pn544_hci_i2c_probe,
+	.id_table = pn544_hci_i2c_id_table,
+	.remove = __devexit_p(pn544_hci_i2c_remove),
+};
+
+static int __init pn544_hci_i2c_init(void)
+{
+	int r;
+
+	pr_debug(DRIVER_DESC ": %s\n", __func__);
+
+	r = i2c_add_driver(&pn544_hci_i2c_driver);
+	if (r) {
+		pr_err(PN544_HCI_I2C_DRIVER_NAME
+		       ": driver registration failed\n");
+		return r;
+	}
+
+	return 0;
+}
+
+static void __exit pn544_hci_i2c_exit(void)
+{
+	i2c_del_driver(&pn544_hci_i2c_driver);
+}
+
+module_init(pn544_hci_i2c_init);
+module_exit(pn544_hci_i2c_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/nfc/pn544/pn544.c b/drivers/nfc/pn544/pn544.c
new file mode 100644
index 000000000000..cf344450815c
--- /dev/null
+++ b/drivers/nfc/pn544/pn544.c
@@ -0,0 +1,862 @@
+/*
+ * HCI based Driver for NXP PN544 NFC Chip
+ *
+ * Copyright (C) 2012  Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the
+ * Free Software Foundation, Inc.,
+ * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ */
+
+#include <linux/delay.h>
+#include <linux/slab.h>
+
+#include <linux/nfc.h>
+#include <net/nfc/hci.h>
+#include <net/nfc/llc.h>
+
+#include "pn544.h"
+
+/* Timing restrictions (ms) */
+#define PN544_HCI_RESETVEN_TIME		30
+
+#define HCI_MODE 0
+#define FW_MODE 1
+
+enum pn544_state {
+	PN544_ST_COLD,
+	PN544_ST_FW_READY,
+	PN544_ST_READY,
+};
+
+#define FULL_VERSION_LEN 11
+
+/* Proprietary commands */
+#define PN544_WRITE		0x3f
+
+/* Proprietary gates, events, commands and registers */
+
+/* NFC_HCI_RF_READER_A_GATE additional registers and commands */
+#define PN544_RF_READER_A_AUTO_ACTIVATION			0x10
+#define PN544_RF_READER_A_CMD_CONTINUE_ACTIVATION		0x12
+#define PN544_MIFARE_CMD					0x21
+
+/* Commands that apply to all RF readers */
+#define PN544_RF_READER_CMD_PRESENCE_CHECK	0x30
+#define PN544_RF_READER_CMD_ACTIVATE_NEXT	0x32
+
+/* NFC_HCI_ID_MGMT_GATE additional registers */
+#define PN544_ID_MGMT_FULL_VERSION_SW		0x10
+
+#define PN544_RF_READER_ISO15693_GATE		0x12
+
+#define PN544_RF_READER_F_GATE			0x14
+#define PN544_FELICA_ID				0x04
+#define PN544_FELICA_RAW			0x20
+
+#define PN544_RF_READER_JEWEL_GATE		0x15
+#define PN544_JEWEL_RAW_CMD			0x23
+
+#define PN544_RF_READER_NFCIP1_INITIATOR_GATE	0x30
+#define PN544_RF_READER_NFCIP1_TARGET_GATE	0x31
+
+#define PN544_SYS_MGMT_GATE			0x90
+#define PN544_SYS_MGMT_INFO_NOTIFICATION	0x02
+
+#define PN544_POLLING_LOOP_MGMT_GATE		0x94
+#define PN544_DEP_MODE				0x01
+#define PN544_DEP_ATR_REQ			0x02
+#define PN544_DEP_ATR_RES			0x03
+#define PN544_DEP_MERGE				0x0D
+#define PN544_PL_RDPHASES			0x06
+#define PN544_PL_EMULATION			0x07
+#define PN544_PL_NFCT_DEACTIVATED		0x09
+
+#define PN544_SWP_MGMT_GATE			0xA0
+
+#define PN544_NFC_WI_MGMT_GATE			0xA1
+
+#define PN544_HCI_EVT_SND_DATA			0x01
+#define PN544_HCI_EVT_ACTIVATED			0x02
+#define PN544_HCI_EVT_DEACTIVATED		0x03
+#define PN544_HCI_EVT_RCV_DATA			0x04
+#define PN544_HCI_EVT_CONTINUE_MI		0x05
+
+#define PN544_HCI_CMD_ATTREQUEST		0x12
+#define PN544_HCI_CMD_CONTINUE_ACTIVATION	0x13
+
+static struct nfc_hci_gate pn544_gates[] = {
+	{NFC_HCI_ADMIN_GATE, NFC_HCI_INVALID_PIPE},
+	{NFC_HCI_LOOPBACK_GATE, NFC_HCI_INVALID_PIPE},
+	{NFC_HCI_ID_MGMT_GATE, NFC_HCI_INVALID_PIPE},
+	{NFC_HCI_LINK_MGMT_GATE, NFC_HCI_INVALID_PIPE},
+	{NFC_HCI_RF_READER_B_GATE, NFC_HCI_INVALID_PIPE},
+	{NFC_HCI_RF_READER_A_GATE, NFC_HCI_INVALID_PIPE},
+	{PN544_SYS_MGMT_GATE, NFC_HCI_INVALID_PIPE},
+	{PN544_SWP_MGMT_GATE, NFC_HCI_INVALID_PIPE},
+	{PN544_POLLING_LOOP_MGMT_GATE, NFC_HCI_INVALID_PIPE},
+	{PN544_NFC_WI_MGMT_GATE, NFC_HCI_INVALID_PIPE},
+	{PN544_RF_READER_F_GATE, NFC_HCI_INVALID_PIPE},
+	{PN544_RF_READER_JEWEL_GATE, NFC_HCI_INVALID_PIPE},
+	{PN544_RF_READER_ISO15693_GATE, NFC_HCI_INVALID_PIPE},
+	{PN544_RF_READER_NFCIP1_INITIATOR_GATE, NFC_HCI_INVALID_PIPE},
+	{PN544_RF_READER_NFCIP1_TARGET_GATE, NFC_HCI_INVALID_PIPE}
+};
+
+/* Largest headroom needed for outgoing custom commands */
+#define PN544_CMDS_HEADROOM	2
+
+struct pn544_hci_info {
+	struct nfc_phy_ops *phy_ops;
+	void *phy_id;
+
+	struct nfc_hci_dev *hdev;
+
+	enum pn544_state state;
+
+	struct mutex info_lock;
+
+	int async_cb_type;
+	data_exchange_cb_t async_cb;
+	void *async_cb_context;
+};
+
+static int pn544_hci_open(struct nfc_hci_dev *hdev)
+{
+	struct pn544_hci_info *info = nfc_hci_get_clientdata(hdev);
+	int r = 0;
+
+	mutex_lock(&info->info_lock);
+
+	if (info->state != PN544_ST_COLD) {
+		r = -EBUSY;
+		goto out;
+	}
+
+	r = info->phy_ops->enable(info->phy_id);
+
+	if (r == 0)
+		info->state = PN544_ST_READY;
+
+out:
+	mutex_unlock(&info->info_lock);
+	return r;
+}
+
+static void pn544_hci_close(struct nfc_hci_dev *hdev)
+{
+	struct pn544_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	mutex_lock(&info->info_lock);
+
+	if (info->state == PN544_ST_COLD)
+		goto out;
+
+	info->phy_ops->disable(info->phy_id);
+
+	info->state = PN544_ST_COLD;
+
+out:
+	mutex_unlock(&info->info_lock);
+}
+
+static int pn544_hci_ready(struct nfc_hci_dev *hdev)
+{
+	struct sk_buff *skb;
+	static struct hw_config {
+		u8 adr[2];
+		u8 value;
+	} hw_config[] = {
+		{{0x9f, 0x9a}, 0x00},
+
+		{{0x98, 0x10}, 0xbc},
+
+		{{0x9e, 0x71}, 0x00},
+
+		{{0x98, 0x09}, 0x00},
+
+		{{0x9e, 0xb4}, 0x00},
+
+		{{0x9e, 0xd9}, 0xff},
+		{{0x9e, 0xda}, 0xff},
+		{{0x9e, 0xdb}, 0x23},
+		{{0x9e, 0xdc}, 0x21},
+		{{0x9e, 0xdd}, 0x22},
+		{{0x9e, 0xde}, 0x24},
+
+		{{0x9c, 0x01}, 0x08},
+
+		{{0x9e, 0xaa}, 0x01},
+
+		{{0x9b, 0xd1}, 0x0d},
+		{{0x9b, 0xd2}, 0x24},
+		{{0x9b, 0xd3}, 0x0a},
+		{{0x9b, 0xd4}, 0x22},
+		{{0x9b, 0xd5}, 0x08},
+		{{0x9b, 0xd6}, 0x1e},
+		{{0x9b, 0xdd}, 0x1c},
+
+		{{0x9b, 0x84}, 0x13},
+		{{0x99, 0x81}, 0x7f},
+		{{0x99, 0x31}, 0x70},
+
+		{{0x98, 0x00}, 0x3f},
+
+		{{0x9f, 0x09}, 0x00},
+
+		{{0x9f, 0x0a}, 0x05},
+
+		{{0x9e, 0xd1}, 0xa1},
+		{{0x99, 0x23}, 0x00},
+
+		{{0x9e, 0x74}, 0x80},
+
+		{{0x9f, 0x28}, 0x10},
+
+		{{0x9f, 0x35}, 0x14},
+
+		{{0x9f, 0x36}, 0x60},
+
+		{{0x9c, 0x31}, 0x00},
+
+		{{0x9c, 0x32}, 0xc8},
+
+		{{0x9c, 0x19}, 0x40},
+
+		{{0x9c, 0x1a}, 0x40},
+
+		{{0x9c, 0x0c}, 0x00},
+
+		{{0x9c, 0x0d}, 0x00},
+
+		{{0x9c, 0x12}, 0x00},
+
+		{{0x9c, 0x13}, 0x00},
+
+		{{0x98, 0xa2}, 0x0e},
+
+		{{0x98, 0x93}, 0x40},
+
+		{{0x98, 0x7d}, 0x02},
+		{{0x98, 0x7e}, 0x00},
+		{{0x9f, 0xc8}, 0x01},
+	};
+	struct hw_config *p = hw_config;
+	int count = ARRAY_SIZE(hw_config);
+	struct sk_buff *res_skb;
+	u8 param[4];
+	int r;
+
+	param[0] = 0;
+	while (count--) {
+		param[1] = p->adr[0];
+		param[2] = p->adr[1];
+		param[3] = p->value;
+
+		r = nfc_hci_send_cmd(hdev, PN544_SYS_MGMT_GATE, PN544_WRITE,
+				     param, 4, &res_skb);
+		if (r < 0)
+			return r;
+
+		if (res_skb->len != 1) {
+			kfree_skb(res_skb);
+			return -EPROTO;
+		}
+
+		if (res_skb->data[0] != p->value) {
+			kfree_skb(res_skb);
+			return -EIO;
+		}
+
+		kfree_skb(res_skb);
+
+		p++;
+	}
+
+	param[0] = NFC_HCI_UICC_HOST_ID;
+	r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE,
+			      NFC_HCI_ADMIN_WHITELIST, param, 1);
+	if (r < 0)
+		return r;
+
+	param[0] = 0x3d;
+	r = nfc_hci_set_param(hdev, PN544_SYS_MGMT_GATE,
+			      PN544_SYS_MGMT_INFO_NOTIFICATION, param, 1);
+	if (r < 0)
+		return r;
+
+	param[0] = 0x0;
+	r = nfc_hci_set_param(hdev, NFC_HCI_RF_READER_A_GATE,
+			      PN544_RF_READER_A_AUTO_ACTIVATION, param, 1);
+	if (r < 0)
+		return r;
+
+	r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
+			       NFC_HCI_EVT_END_OPERATION, NULL, 0);
+	if (r < 0)
+		return r;
+
+	param[0] = 0x1;
+	r = nfc_hci_set_param(hdev, PN544_POLLING_LOOP_MGMT_GATE,
+			      PN544_PL_NFCT_DEACTIVATED, param, 1);
+	if (r < 0)
+		return r;
+
+	param[0] = 0x0;
+	r = nfc_hci_set_param(hdev, PN544_POLLING_LOOP_MGMT_GATE,
+			      PN544_PL_RDPHASES, param, 1);
+	if (r < 0)
+		return r;
+
+	r = nfc_hci_get_param(hdev, NFC_HCI_ID_MGMT_GATE,
+			      PN544_ID_MGMT_FULL_VERSION_SW, &skb);
+	if (r < 0)
+		return r;
+
+	if (skb->len != FULL_VERSION_LEN) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	print_hex_dump(KERN_DEBUG, "FULL VERSION SOFTWARE INFO: ",
+		       DUMP_PREFIX_NONE, 16, 1,
+		       skb->data, FULL_VERSION_LEN, false);
+
+	kfree_skb(skb);
+
+	return 0;
+}
+
+static int pn544_hci_xmit(struct nfc_hci_dev *hdev, struct sk_buff *skb)
+{
+	struct pn544_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	return info->phy_ops->write(info->phy_id, skb);
+}
+
+static int pn544_hci_start_poll(struct nfc_hci_dev *hdev,
+				u32 im_protocols, u32 tm_protocols)
+{
+	u8 phases = 0;
+	int r;
+	u8 duration[2];
+	u8 activated;
+	u8 i_mode = 0x3f; /* Enable all supported modes */
+	u8 t_mode = 0x0f;
+	u8 t_merge = 0x01; /* Enable merge by default */
+
+	pr_info(DRIVER_DESC ": %s protocols 0x%x 0x%x\n",
+		__func__, im_protocols, tm_protocols);
+
+	r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
+			       NFC_HCI_EVT_END_OPERATION, NULL, 0);
+	if (r < 0)
+		return r;
+
+	duration[0] = 0x18;
+	duration[1] = 0x6a;
+	r = nfc_hci_set_param(hdev, PN544_POLLING_LOOP_MGMT_GATE,
+			      PN544_PL_EMULATION, duration, 2);
+	if (r < 0)
+		return r;
+
+	activated = 0;
+	r = nfc_hci_set_param(hdev, PN544_POLLING_LOOP_MGMT_GATE,
+			      PN544_PL_NFCT_DEACTIVATED, &activated, 1);
+	if (r < 0)
+		return r;
+
+	if (im_protocols & (NFC_PROTO_ISO14443_MASK | NFC_PROTO_MIFARE_MASK |
+			 NFC_PROTO_JEWEL_MASK))
+		phases |= 1;		/* Type A */
+	if (im_protocols & NFC_PROTO_FELICA_MASK) {
+		phases |= (1 << 2);	/* Type F 212 */
+		phases |= (1 << 3);	/* Type F 424 */
+	}
+
+	phases |= (1 << 5);		/* NFC active */
+
+	r = nfc_hci_set_param(hdev, PN544_POLLING_LOOP_MGMT_GATE,
+			      PN544_PL_RDPHASES, &phases, 1);
+	if (r < 0)
+		return r;
+
+	if ((im_protocols | tm_protocols) & NFC_PROTO_NFC_DEP_MASK) {
+		hdev->gb = nfc_get_local_general_bytes(hdev->ndev,
+							&hdev->gb_len);
+		pr_debug("generate local bytes %p", hdev->gb);
+		if (hdev->gb == NULL || hdev->gb_len == 0) {
+			im_protocols &= ~NFC_PROTO_NFC_DEP_MASK;
+			tm_protocols &= ~NFC_PROTO_NFC_DEP_MASK;
+		}
+	}
+
+	if (im_protocols & NFC_PROTO_NFC_DEP_MASK) {
+		r = nfc_hci_send_event(hdev,
+				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+				NFC_HCI_EVT_END_OPERATION, NULL, 0);
+		if (r < 0)
+			return r;
+
+		r = nfc_hci_set_param(hdev,
+				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+				PN544_DEP_MODE, &i_mode, 1);
+		if (r < 0)
+			return r;
+
+		r = nfc_hci_set_param(hdev,
+				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+				PN544_DEP_ATR_REQ, hdev->gb, hdev->gb_len);
+		if (r < 0)
+			return r;
+
+		r = nfc_hci_send_event(hdev,
+				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+				NFC_HCI_EVT_READER_REQUESTED, NULL, 0);
+		if (r < 0)
+			nfc_hci_send_event(hdev,
+					PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+					NFC_HCI_EVT_END_OPERATION, NULL, 0);
+	}
+
+	if (tm_protocols & NFC_PROTO_NFC_DEP_MASK) {
+		r = nfc_hci_set_param(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
+				PN544_DEP_MODE, &t_mode, 1);
+		if (r < 0)
+			return r;
+
+		r = nfc_hci_set_param(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
+				PN544_DEP_ATR_RES, hdev->gb, hdev->gb_len);
+		if (r < 0)
+			return r;
+
+		r = nfc_hci_set_param(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
+				PN544_DEP_MERGE, &t_merge, 1);
+		if (r < 0)
+			return r;
+	}
+
+	r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
+			       NFC_HCI_EVT_READER_REQUESTED, NULL, 0);
+	if (r < 0)
+		nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
+				   NFC_HCI_EVT_END_OPERATION, NULL, 0);
+
+	return r;
+}
+
+static int pn544_hci_dep_link_up(struct nfc_hci_dev *hdev,
+				struct nfc_target *target, u8 comm_mode,
+				u8 *gb, size_t gb_len)
+{
+	struct sk_buff *rgb_skb = NULL;
+	int r;
+
+	r = nfc_hci_get_param(hdev, target->hci_reader_gate,
+				PN544_DEP_ATR_RES, &rgb_skb);
+	if (r < 0)
+		return r;
+
+	if (rgb_skb->len == 0 || rgb_skb->len > NFC_GB_MAXSIZE) {
+		r = -EPROTO;
+		goto exit;
+	}
+	print_hex_dump(KERN_DEBUG, "remote gb: ", DUMP_PREFIX_OFFSET,
+			16, 1, rgb_skb->data, rgb_skb->len, true);
+
+	r = nfc_set_remote_general_bytes(hdev->ndev, rgb_skb->data,
+						rgb_skb->len);
+
+	if (r == 0)
+		r = nfc_dep_link_is_up(hdev->ndev, target->idx, comm_mode,
+					NFC_RF_INITIATOR);
+exit:
+	kfree_skb(rgb_skb);
+	return r;
+}
+
+static int pn544_hci_dep_link_down(struct nfc_hci_dev *hdev)
+{
+
+	return nfc_hci_send_event(hdev, PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+					NFC_HCI_EVT_END_OPERATION, NULL, 0);
+}
+
+static int pn544_hci_target_from_gate(struct nfc_hci_dev *hdev, u8 gate,
+				      struct nfc_target *target)
+{
+	switch (gate) {
+	case PN544_RF_READER_F_GATE:
+		target->supported_protocols = NFC_PROTO_FELICA_MASK;
+		break;
+	case PN544_RF_READER_JEWEL_GATE:
+		target->supported_protocols = NFC_PROTO_JEWEL_MASK;
+		target->sens_res = 0x0c00;
+		break;
+	case PN544_RF_READER_NFCIP1_INITIATOR_GATE:
+		target->supported_protocols = NFC_PROTO_NFC_DEP_MASK;
+		break;
+	default:
+		return -EPROTO;
+	}
+
+	return 0;
+}
+
+static int pn544_hci_complete_target_discovered(struct nfc_hci_dev *hdev,
+						u8 gate,
+						struct nfc_target *target)
+{
+	struct sk_buff *uid_skb;
+	int r = 0;
+
+	if (gate == PN544_RF_READER_NFCIP1_INITIATOR_GATE)
+		return r;
+
+	if (target->supported_protocols & NFC_PROTO_NFC_DEP_MASK) {
+		r = nfc_hci_send_cmd(hdev,
+			PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+			PN544_HCI_CMD_CONTINUE_ACTIVATION, NULL, 0, NULL);
+		if (r < 0)
+			return r;
+
+		target->hci_reader_gate = PN544_RF_READER_NFCIP1_INITIATOR_GATE;
+	} else if (target->supported_protocols & NFC_PROTO_MIFARE_MASK) {
+		if (target->nfcid1_len != 4 && target->nfcid1_len != 7 &&
+		    target->nfcid1_len != 10)
+			return -EPROTO;
+
+		r = nfc_hci_send_cmd(hdev, NFC_HCI_RF_READER_A_GATE,
+				     PN544_RF_READER_CMD_ACTIVATE_NEXT,
+				     target->nfcid1, target->nfcid1_len, NULL);
+	} else if (target->supported_protocols & NFC_PROTO_FELICA_MASK) {
+		r = nfc_hci_get_param(hdev, PN544_RF_READER_F_GATE,
+				      PN544_FELICA_ID, &uid_skb);
+		if (r < 0)
+			return r;
+
+		if (uid_skb->len != 8) {
+			kfree_skb(uid_skb);
+			return -EPROTO;
+		}
+
+		r = nfc_hci_send_cmd(hdev, PN544_RF_READER_F_GATE,
+				     PN544_RF_READER_CMD_ACTIVATE_NEXT,
+				     uid_skb->data, uid_skb->len, NULL);
+		kfree_skb(uid_skb);
+
+		r = nfc_hci_send_cmd(hdev,
+					PN544_RF_READER_NFCIP1_INITIATOR_GATE,
+					PN544_HCI_CMD_CONTINUE_ACTIVATION,
+					NULL, 0, NULL);
+		if (r < 0)
+			return r;
+
+		target->hci_reader_gate = PN544_RF_READER_NFCIP1_INITIATOR_GATE;
+		target->supported_protocols = NFC_PROTO_NFC_DEP_MASK;
+	} else if (target->supported_protocols & NFC_PROTO_ISO14443_MASK) {
+		/*
+		 * TODO: maybe other ISO 14443 require some kind of continue
+		 * activation, but for now we've seen only this one below.
+		 */
+		if (target->sens_res == 0x4403)	/* Type 4 Mifare DESFire */
+			r = nfc_hci_send_cmd(hdev, NFC_HCI_RF_READER_A_GATE,
+			      PN544_RF_READER_A_CMD_CONTINUE_ACTIVATION,
+			      NULL, 0, NULL);
+	}
+
+	return r;
+}
+
+#define PN544_CB_TYPE_READER_F 1
+
+static void pn544_hci_data_exchange_cb(void *context, struct sk_buff *skb,
+				       int err)
+{
+	struct pn544_hci_info *info = context;
+
+	switch (info->async_cb_type) {
+	case PN544_CB_TYPE_READER_F:
+		if (err == 0)
+			skb_pull(skb, 1);
+		info->async_cb(info->async_cb_context, skb, err);
+		break;
+	default:
+		if (err == 0)
+			kfree_skb(skb);
+		break;
+	}
+}
+
+#define MIFARE_CMD_AUTH_KEY_A	0x60
+#define MIFARE_CMD_AUTH_KEY_B	0x61
+#define MIFARE_CMD_HEADER	2
+#define MIFARE_UID_LEN		4
+#define MIFARE_KEY_LEN		6
+#define MIFARE_CMD_LEN		12
+/*
+ * Returns:
+ * <= 0: driver handled the data exchange
+ *    1: driver doesn't especially handle, please do standard processing
+ */
+static int pn544_hci_im_transceive(struct nfc_hci_dev *hdev,
+				   struct nfc_target *target,
+				   struct sk_buff *skb, data_exchange_cb_t cb,
+				   void *cb_context)
+{
+	struct pn544_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	pr_info(DRIVER_DESC ": %s for gate=%d\n", __func__,
+		target->hci_reader_gate);
+
+	switch (target->hci_reader_gate) {
+	case NFC_HCI_RF_READER_A_GATE:
+		if (target->supported_protocols & NFC_PROTO_MIFARE_MASK) {
+			/*
+			 * It seems that pn544 is inverting key and UID for
+			 * MIFARE authentication commands.
+			 */
+			if (skb->len == MIFARE_CMD_LEN &&
+			    (skb->data[0] == MIFARE_CMD_AUTH_KEY_A ||
+			     skb->data[0] == MIFARE_CMD_AUTH_KEY_B)) {
+				u8 uid[MIFARE_UID_LEN];
+				u8 *data = skb->data + MIFARE_CMD_HEADER;
+
+				memcpy(uid, data + MIFARE_KEY_LEN,
+				       MIFARE_UID_LEN);
+				memmove(data + MIFARE_UID_LEN, data,
+					MIFARE_KEY_LEN);
+				memcpy(data, uid, MIFARE_UID_LEN);
+			}
+
+			return nfc_hci_send_cmd_async(hdev,
+						      target->hci_reader_gate,
+						      PN544_MIFARE_CMD,
+						      skb->data, skb->len,
+						      cb, cb_context);
+		} else
+			return 1;
+	case PN544_RF_READER_F_GATE:
+		*skb_push(skb, 1) = 0;
+		*skb_push(skb, 1) = 0;
+
+		info->async_cb_type = PN544_CB_TYPE_READER_F;
+		info->async_cb = cb;
+		info->async_cb_context = cb_context;
+
+		return nfc_hci_send_cmd_async(hdev, target->hci_reader_gate,
+					      PN544_FELICA_RAW, skb->data,
+					      skb->len,
+					      pn544_hci_data_exchange_cb, info);
+	case PN544_RF_READER_JEWEL_GATE:
+		return nfc_hci_send_cmd_async(hdev, target->hci_reader_gate,
+					      PN544_JEWEL_RAW_CMD, skb->data,
+					      skb->len, cb, cb_context);
+	case PN544_RF_READER_NFCIP1_INITIATOR_GATE:
+		*skb_push(skb, 1) = 0;
+
+		return nfc_hci_send_event(hdev, target->hci_reader_gate,
+					PN544_HCI_EVT_SND_DATA, skb->data,
+					skb->len);
+	default:
+		return 1;
+	}
+}
+
+static int pn544_hci_tm_send(struct nfc_hci_dev *hdev, struct sk_buff *skb)
+{
+	/* Set default false for multiple information chaining */
+	*skb_push(skb, 1) = 0;
+
+	return nfc_hci_send_event(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
+				PN544_HCI_EVT_SND_DATA, skb->data, skb->len);
+}
+
+static int pn544_hci_check_presence(struct nfc_hci_dev *hdev,
+				   struct nfc_target *target)
+{
+	pr_debug("supported protocol %d", target->supported_protocols);
+	if (target->supported_protocols & (NFC_PROTO_ISO14443_MASK |
+					NFC_PROTO_ISO14443_B_MASK)) {
+		return nfc_hci_send_cmd(hdev, target->hci_reader_gate,
+					PN544_RF_READER_CMD_PRESENCE_CHECK,
+					NULL, 0, NULL);
+	} else if (target->supported_protocols & NFC_PROTO_MIFARE_MASK) {
+		if (target->nfcid1_len != 4 && target->nfcid1_len != 7 &&
+		    target->nfcid1_len != 10)
+			return -EOPNOTSUPP;
+
+		 return nfc_hci_send_cmd(hdev, NFC_HCI_RF_READER_A_GATE,
+				     PN544_RF_READER_CMD_ACTIVATE_NEXT,
+				     target->nfcid1, target->nfcid1_len, NULL);
+	} else if (target->supported_protocols & NFC_PROTO_JEWEL_MASK) {
+		return nfc_hci_send_cmd(hdev, target->hci_reader_gate,
+					PN544_JEWEL_RAW_CMD, NULL, 0, NULL);
+	} else if (target->supported_protocols & NFC_PROTO_FELICA_MASK) {
+		return nfc_hci_send_cmd(hdev, PN544_RF_READER_F_GATE,
+					PN544_FELICA_RAW, NULL, 0, NULL);
+	} else if (target->supported_protocols & NFC_PROTO_NFC_DEP_MASK) {
+		return nfc_hci_send_cmd(hdev, target->hci_reader_gate,
+					PN544_HCI_CMD_ATTREQUEST,
+					NULL, 0, NULL);
+	}
+
+	return 0;
+}
+
+void pn544_hci_event_received(struct nfc_hci_dev *hdev, u8 gate, u8 event,
+				struct sk_buff *skb)
+{
+	struct sk_buff *rgb_skb = NULL;
+	int r = 0;
+
+	pr_debug("hci event %d", event);
+	switch (event) {
+	case PN544_HCI_EVT_ACTIVATED:
+		if (gate == PN544_RF_READER_NFCIP1_INITIATOR_GATE)
+			nfc_hci_target_discovered(hdev, gate);
+		else if (gate == PN544_RF_READER_NFCIP1_TARGET_GATE) {
+			r = nfc_hci_get_param(hdev, gate, PN544_DEP_ATR_REQ,
+						&rgb_skb);
+
+			if (r < 0)
+				goto exit;
+
+			nfc_tm_activated(hdev->ndev, NFC_PROTO_NFC_DEP_MASK,
+					NFC_COMM_PASSIVE, rgb_skb->data,
+					rgb_skb->len);
+
+			kfree_skb(rgb_skb);
+		}
+
+		break;
+	case PN544_HCI_EVT_DEACTIVATED:
+		nfc_hci_send_event(hdev, gate,
+			NFC_HCI_EVT_END_OPERATION, NULL, 0);
+		break;
+	case PN544_HCI_EVT_RCV_DATA:
+		if (skb->len < 2) {
+			r = -EPROTO;
+			goto exit;
+		}
+
+		if (skb->data[0] != 0) {
+			pr_debug("data0 %d", skb->data[0]);
+			r = -EPROTO;
+			goto exit;
+		}
+
+		skb_pull(skb, 2);
+		nfc_tm_data_received(hdev->ndev, skb);
+
+		return;
+	default:
+		break;
+	}
+
+exit:
+	kfree_skb(skb);
+}
+
+static struct nfc_hci_ops pn544_hci_ops = {
+	.open = pn544_hci_open,
+	.close = pn544_hci_close,
+	.hci_ready = pn544_hci_ready,
+	.xmit = pn544_hci_xmit,
+	.start_poll = pn544_hci_start_poll,
+	.dep_link_up = pn544_hci_dep_link_up,
+	.dep_link_down = pn544_hci_dep_link_down,
+	.target_from_gate = pn544_hci_target_from_gate,
+	.complete_target_discovered = pn544_hci_complete_target_discovered,
+	.im_transceive = pn544_hci_im_transceive,
+	.tm_send = pn544_hci_tm_send,
+	.check_presence = pn544_hci_check_presence,
+	.event_received = pn544_hci_event_received,
+};
+
+int pn544_hci_probe(void *phy_id, struct nfc_phy_ops *phy_ops, char *llc_name,
+		    int phy_headroom, int phy_tailroom, int phy_payload,
+		    struct nfc_hci_dev **hdev)
+{
+	struct pn544_hci_info *info;
+	u32 protocols;
+	struct nfc_hci_init_data init_data;
+	int r;
+
+	info = kzalloc(sizeof(struct pn544_hci_info), GFP_KERNEL);
+	if (!info) {
+		pr_err("Cannot allocate memory for pn544_hci_info.\n");
+		r = -ENOMEM;
+		goto err_info_alloc;
+	}
+
+	info->phy_ops = phy_ops;
+	info->phy_id = phy_id;
+	info->state = PN544_ST_COLD;
+	mutex_init(&info->info_lock);
+
+	init_data.gate_count = ARRAY_SIZE(pn544_gates);
+
+	memcpy(init_data.gates, pn544_gates, sizeof(pn544_gates));
+
+	/*
+	 * TODO: Session id must include the driver name + some bus addr
+	 * persistent info to discriminate 2 identical chips
+	 */
+	strcpy(init_data.session_id, "ID544HCI");
+
+	protocols = NFC_PROTO_JEWEL_MASK |
+		    NFC_PROTO_MIFARE_MASK |
+		    NFC_PROTO_FELICA_MASK |
+		    NFC_PROTO_ISO14443_MASK |
+		    NFC_PROTO_ISO14443_B_MASK |
+		    NFC_PROTO_NFC_DEP_MASK;
+
+	info->hdev = nfc_hci_allocate_device(&pn544_hci_ops, &init_data,
+					     protocols, llc_name,
+					     phy_headroom + PN544_CMDS_HEADROOM,
+					     phy_tailroom, phy_payload);
+	if (!info->hdev) {
+		pr_err("Cannot allocate nfc hdev.\n");
+		r = -ENOMEM;
+		goto err_alloc_hdev;
+	}
+
+	nfc_hci_set_clientdata(info->hdev, info);
+
+	r = nfc_hci_register_device(info->hdev);
+	if (r)
+		goto err_regdev;
+
+	*hdev = info->hdev;
+
+	return 0;
+
+err_regdev:
+	nfc_hci_free_device(info->hdev);
+
+err_alloc_hdev:
+	kfree(info);
+
+err_info_alloc:
+	return r;
+}
+
+void pn544_hci_remove(struct nfc_hci_dev *hdev)
+{
+	struct pn544_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	nfc_hci_unregister_device(hdev);
+	nfc_hci_free_device(hdev);
+	kfree(info);
+}
diff --git a/drivers/nfc/pn544/pn544.h b/drivers/nfc/pn544/pn544.h
new file mode 100644
index 000000000000..f47c6454914b
--- /dev/null
+++ b/drivers/nfc/pn544/pn544.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (C) 2011 - 2012  Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the
+ * Free Software Foundation, Inc.,
+ * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ */
+
+#ifndef __LOCAL_PN544_H_
+#define __LOCAL_PN544_H_
+
+#include <net/nfc/hci.h>
+
+#define DRIVER_DESC "HCI NFC driver for PN544"
+
+int pn544_hci_probe(void *phy_id, struct nfc_phy_ops *phy_ops, char *llc_name,
+		    int phy_headroom, int phy_tailroom, int phy_payload,
+		    struct nfc_hci_dev **hdev);
+void pn544_hci_remove(struct nfc_hci_dev *hdev);
+
+#endif /* __LOCAL_PN544_H_ */
diff --git a/drivers/nfc/pn544_hci.c b/drivers/nfc/pn544_hci.c
deleted file mode 100644
index 70858b5f81e4..000000000000
--- a/drivers/nfc/pn544_hci.c
+++ /dev/null
@@ -1,1252 +0,0 @@
-/*
- * HCI based Driver for NXP PN544 NFC Chip
- *
- * Copyright (C) 2012  Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- */
-
-#include <linux/crc-ccitt.h>
-#include <linux/module.h>
-#include <linux/delay.h>
-#include <linux/slab.h>
-#include <linux/miscdevice.h>
-#include <linux/interrupt.h>
-#include <linux/gpio.h>
-#include <linux/i2c.h>
-
-#include <linux/nfc.h>
-#include <net/nfc/hci.h>
-#include <net/nfc/llc.h>
-
-#include <linux/nfc/pn544.h>
-
-#define DRIVER_DESC "HCI NFC driver for PN544"
-
-#define PN544_HCI_DRIVER_NAME "pn544_hci"
-
-/* Timing restrictions (ms) */
-#define PN544_HCI_RESETVEN_TIME		30
-
-static struct i2c_device_id pn544_hci_id_table[] = {
-	{"pn544", 0},
-	{}
-};
-
-MODULE_DEVICE_TABLE(i2c, pn544_hci_id_table);
-
-#define HCI_MODE 0
-#define FW_MODE 1
-
-/* framing in HCI mode */
-#define PN544_HCI_LLC_LEN		1
-#define PN544_HCI_LLC_CRC		2
-#define PN544_HCI_LLC_LEN_CRC		(PN544_HCI_LLC_LEN + PN544_HCI_LLC_CRC)
-#define PN544_HCI_LLC_MIN_SIZE		(1 + PN544_HCI_LLC_LEN_CRC)
-#define PN544_HCI_LLC_MAX_PAYLOAD	29
-#define PN544_HCI_LLC_MAX_SIZE		(PN544_HCI_LLC_LEN_CRC + 1 + \
-					 PN544_HCI_LLC_MAX_PAYLOAD)
-
-enum pn544_state {
-	PN544_ST_COLD,
-	PN544_ST_FW_READY,
-	PN544_ST_READY,
-};
-
-#define FULL_VERSION_LEN 11
-
-/* Proprietary commands */
-#define PN544_WRITE		0x3f
-
-/* Proprietary gates, events, commands and registers */
-
-/* NFC_HCI_RF_READER_A_GATE additional registers and commands */
-#define PN544_RF_READER_A_AUTO_ACTIVATION			0x10
-#define PN544_RF_READER_A_CMD_CONTINUE_ACTIVATION		0x12
-#define PN544_MIFARE_CMD					0x21
-
-/* Commands that apply to all RF readers */
-#define PN544_RF_READER_CMD_PRESENCE_CHECK	0x30
-#define PN544_RF_READER_CMD_ACTIVATE_NEXT	0x32
-
-/* NFC_HCI_ID_MGMT_GATE additional registers */
-#define PN544_ID_MGMT_FULL_VERSION_SW		0x10
-
-#define PN544_RF_READER_ISO15693_GATE		0x12
-
-#define PN544_RF_READER_F_GATE			0x14
-#define PN544_FELICA_ID				0x04
-#define PN544_FELICA_RAW			0x20
-
-#define PN544_RF_READER_JEWEL_GATE		0x15
-#define PN544_JEWEL_RAW_CMD			0x23
-
-#define PN544_RF_READER_NFCIP1_INITIATOR_GATE	0x30
-#define PN544_RF_READER_NFCIP1_TARGET_GATE	0x31
-
-#define PN544_SYS_MGMT_GATE			0x90
-#define PN544_SYS_MGMT_INFO_NOTIFICATION	0x02
-
-#define PN544_POLLING_LOOP_MGMT_GATE		0x94
-#define PN544_DEP_MODE				0x01
-#define PN544_DEP_ATR_REQ			0x02
-#define PN544_DEP_ATR_RES			0x03
-#define PN544_DEP_MERGE				0x0D
-#define PN544_PL_RDPHASES			0x06
-#define PN544_PL_EMULATION			0x07
-#define PN544_PL_NFCT_DEACTIVATED		0x09
-
-#define PN544_SWP_MGMT_GATE			0xA0
-
-#define PN544_NFC_WI_MGMT_GATE			0xA1
-
-#define PN544_HCI_EVT_SND_DATA			0x01
-#define PN544_HCI_EVT_ACTIVATED			0x02
-#define PN544_HCI_EVT_DEACTIVATED		0x03
-#define PN544_HCI_EVT_RCV_DATA			0x04
-#define PN544_HCI_EVT_CONTINUE_MI		0x05
-
-#define PN544_HCI_CMD_ATTREQUEST		0x12
-#define PN544_HCI_CMD_CONTINUE_ACTIVATION	0x13
-
-static struct nfc_hci_gate pn544_gates[] = {
-	{NFC_HCI_ADMIN_GATE, NFC_HCI_INVALID_PIPE},
-	{NFC_HCI_LOOPBACK_GATE, NFC_HCI_INVALID_PIPE},
-	{NFC_HCI_ID_MGMT_GATE, NFC_HCI_INVALID_PIPE},
-	{NFC_HCI_LINK_MGMT_GATE, NFC_HCI_INVALID_PIPE},
-	{NFC_HCI_RF_READER_B_GATE, NFC_HCI_INVALID_PIPE},
-	{NFC_HCI_RF_READER_A_GATE, NFC_HCI_INVALID_PIPE},
-	{PN544_SYS_MGMT_GATE, NFC_HCI_INVALID_PIPE},
-	{PN544_SWP_MGMT_GATE, NFC_HCI_INVALID_PIPE},
-	{PN544_POLLING_LOOP_MGMT_GATE, NFC_HCI_INVALID_PIPE},
-	{PN544_NFC_WI_MGMT_GATE, NFC_HCI_INVALID_PIPE},
-	{PN544_RF_READER_F_GATE, NFC_HCI_INVALID_PIPE},
-	{PN544_RF_READER_JEWEL_GATE, NFC_HCI_INVALID_PIPE},
-	{PN544_RF_READER_ISO15693_GATE, NFC_HCI_INVALID_PIPE},
-	{PN544_RF_READER_NFCIP1_INITIATOR_GATE, NFC_HCI_INVALID_PIPE},
-	{PN544_RF_READER_NFCIP1_TARGET_GATE, NFC_HCI_INVALID_PIPE}
-};
-
-/* Largest headroom needed for outgoing custom commands */
-#define PN544_CMDS_HEADROOM	2
-#define PN544_FRAME_HEADROOM 1
-#define PN544_FRAME_TAILROOM 2
-
-struct pn544_hci_info {
-	struct i2c_client *i2c_dev;
-	struct nfc_hci_dev *hdev;
-
-	enum pn544_state state;
-
-	struct mutex info_lock;
-
-	unsigned int gpio_en;
-	unsigned int gpio_irq;
-	unsigned int gpio_fw;
-	unsigned int en_polarity;
-
-	int hard_fault;		/*
-				 * < 0 if hardware error occured (e.g. i2c err)
-				 * and prevents normal operation.
-				 */
-	int async_cb_type;
-	data_exchange_cb_t async_cb;
-	void *async_cb_context;
-};
-
-static void pn544_hci_platform_init(struct pn544_hci_info *info)
-{
-	int polarity, retry, ret;
-	char rset_cmd[] = { 0x05, 0xF9, 0x04, 0x00, 0xC3, 0xE5 };
-	int count = sizeof(rset_cmd);
-
-	pr_info(DRIVER_DESC ": %s\n", __func__);
-	dev_info(&info->i2c_dev->dev, "Detecting nfc_en polarity\n");
-
-	/* Disable fw download */
-	gpio_set_value(info->gpio_fw, 0);
-
-	for (polarity = 0; polarity < 2; polarity++) {
-		info->en_polarity = polarity;
-		retry = 3;
-		while (retry--) {
-			/* power off */
-			gpio_set_value(info->gpio_en, !info->en_polarity);
-			usleep_range(10000, 15000);
-
-			/* power on */
-			gpio_set_value(info->gpio_en, info->en_polarity);
-			usleep_range(10000, 15000);
-
-			/* send reset */
-			dev_dbg(&info->i2c_dev->dev, "Sending reset cmd\n");
-			ret = i2c_master_send(info->i2c_dev, rset_cmd, count);
-			if (ret == count) {
-				dev_info(&info->i2c_dev->dev,
-					 "nfc_en polarity : active %s\n",
-					 (polarity == 0 ? "low" : "high"));
-				goto out;
-			}
-		}
-	}
-
-	dev_err(&info->i2c_dev->dev,
-		"Could not detect nfc_en polarity, fallback to active high\n");
-
-out:
-	gpio_set_value(info->gpio_en, !info->en_polarity);
-}
-
-static int pn544_hci_enable(struct pn544_hci_info *info, int mode)
-{
-	pr_info(DRIVER_DESC ": %s\n", __func__);
-
-	gpio_set_value(info->gpio_fw, 0);
-	gpio_set_value(info->gpio_en, info->en_polarity);
-	usleep_range(10000, 15000);
-
-	return 0;
-}
-
-static void pn544_hci_disable(struct pn544_hci_info *info)
-{
-	pr_info(DRIVER_DESC ": %s\n", __func__);
-
-	gpio_set_value(info->gpio_fw, 0);
-	gpio_set_value(info->gpio_en, !info->en_polarity);
-	usleep_range(10000, 15000);
-
-	gpio_set_value(info->gpio_en, info->en_polarity);
-	usleep_range(10000, 15000);
-
-	gpio_set_value(info->gpio_en, !info->en_polarity);
-	usleep_range(10000, 15000);
-}
-
-static int pn544_hci_i2c_write(struct i2c_client *client, u8 *buf, int len)
-{
-	int r;
-
-	usleep_range(3000, 6000);
-
-	r = i2c_master_send(client, buf, len);
-
-	if (r == -EREMOTEIO) {	/* Retry, chip was in standby */
-		usleep_range(6000, 10000);
-		r = i2c_master_send(client, buf, len);
-	}
-
-	if (r >= 0) {
-		if (r != len)
-			return -EREMOTEIO;
-		else
-			return 0;
-	}
-
-	return r;
-}
-
-static int check_crc(u8 *buf, int buflen)
-{
-	int len;
-	u16 crc;
-
-	len = buf[0] + 1;
-	crc = crc_ccitt(0xffff, buf, len - 2);
-	crc = ~crc;
-
-	if (buf[len - 2] != (crc & 0xff) || buf[len - 1] != (crc >> 8)) {
-		pr_err(PN544_HCI_DRIVER_NAME ": CRC error 0x%x != 0x%x 0x%x\n",
-		       crc, buf[len - 1], buf[len - 2]);
-
-		pr_info(DRIVER_DESC ": %s : BAD CRC\n", __func__);
-		print_hex_dump(KERN_DEBUG, "crc: ", DUMP_PREFIX_NONE,
-			       16, 2, buf, buflen, false);
-		return -EPERM;
-	}
-	return 0;
-}
-
-/*
- * Reads an shdlc frame and returns it in a newly allocated sk_buff. Guarantees
- * that i2c bus will be flushed and that next read will start on a new frame.
- * returned skb contains only LLC header and payload.
- * returns:
- * -EREMOTEIO : i2c read error (fatal)
- * -EBADMSG : frame was incorrect and discarded
- * -ENOMEM : cannot allocate skb, frame dropped
- */
-static int pn544_hci_i2c_read(struct i2c_client *client, struct sk_buff **skb)
-{
-	int r;
-	u8 len;
-	u8 tmp[PN544_HCI_LLC_MAX_SIZE - 1];
-
-	r = i2c_master_recv(client, &len, 1);
-	if (r != 1) {
-		dev_err(&client->dev, "cannot read len byte\n");
-		return -EREMOTEIO;
-	}
-
-	if ((len < (PN544_HCI_LLC_MIN_SIZE - 1)) ||
-	    (len > (PN544_HCI_LLC_MAX_SIZE - 1))) {
-		dev_err(&client->dev, "invalid len byte\n");
-		r = -EBADMSG;
-		goto flush;
-	}
-
-	*skb = alloc_skb(1 + len, GFP_KERNEL);
-	if (*skb == NULL) {
-		r = -ENOMEM;
-		goto flush;
-	}
-
-	*skb_put(*skb, 1) = len;
-
-	r = i2c_master_recv(client, skb_put(*skb, len), len);
-	if (r != len) {
-		kfree_skb(*skb);
-		return -EREMOTEIO;
-	}
-
-	r = check_crc((*skb)->data, (*skb)->len);
-	if (r != 0) {
-		kfree_skb(*skb);
-		r = -EBADMSG;
-		goto flush;
-	}
-
-	skb_pull(*skb, 1);
-	skb_trim(*skb, (*skb)->len - 2);
-
-	usleep_range(3000, 6000);
-
-	return 0;
-
-flush:
-	if (i2c_master_recv(client, tmp, sizeof(tmp)) < 0)
-		r = -EREMOTEIO;
-
-	usleep_range(3000, 6000);
-
-	return r;
-}
-
-/*
- * Reads an shdlc frame from the chip. This is not as straightforward as it
- * seems. There are cases where we could loose the frame start synchronization.
- * The frame format is len-data-crc, and corruption can occur anywhere while
- * transiting on i2c bus, such that we could read an invalid len.
- * In order to recover synchronization with the next frame, we must be sure
- * to read the real amount of data without using the len byte. We do this by
- * assuming the following:
- * - the chip will always present only one single complete frame on the bus
- *   before triggering the interrupt
- * - the chip will not present a new frame until we have completely read
- *   the previous one (or until we have handled the interrupt).
- * The tricky case is when we read a corrupted len that is less than the real
- * len. We must detect this here in order to determine that we need to flush
- * the bus. This is the reason why we check the crc here.
- */
-static irqreturn_t pn544_hci_irq_thread_fn(int irq, void *dev_id)
-{
-	struct pn544_hci_info *info = dev_id;
-	struct i2c_client *client;
-	struct sk_buff *skb = NULL;
-	int r;
-
-	if (!info || irq != info->i2c_dev->irq) {
-		WARN_ON_ONCE(1);
-		return IRQ_NONE;
-	}
-
-	client = info->i2c_dev;
-	dev_dbg(&client->dev, "IRQ\n");
-
-	if (info->hard_fault != 0)
-		return IRQ_HANDLED;
-
-	r = pn544_hci_i2c_read(client, &skb);
-	if (r == -EREMOTEIO) {
-		info->hard_fault = r;
-
-		nfc_hci_recv_frame(info->hdev, NULL);
-
-		return IRQ_HANDLED;
-	} else if ((r == -ENOMEM) || (r == -EBADMSG)) {
-		return IRQ_HANDLED;
-	}
-
-	nfc_hci_recv_frame(info->hdev, skb);
-
-	return IRQ_HANDLED;
-}
-
-static int pn544_hci_open(struct nfc_hci_dev *hdev)
-{
-	struct pn544_hci_info *info = nfc_hci_get_clientdata(hdev);
-	int r = 0;
-
-	mutex_lock(&info->info_lock);
-
-	if (info->state != PN544_ST_COLD) {
-		r = -EBUSY;
-		goto out;
-	}
-
-	r = pn544_hci_enable(info, HCI_MODE);
-
-	if (r == 0)
-		info->state = PN544_ST_READY;
-
-out:
-	mutex_unlock(&info->info_lock);
-	return r;
-}
-
-static void pn544_hci_close(struct nfc_hci_dev *hdev)
-{
-	struct pn544_hci_info *info = nfc_hci_get_clientdata(hdev);
-
-	mutex_lock(&info->info_lock);
-
-	if (info->state == PN544_ST_COLD)
-		goto out;
-
-	pn544_hci_disable(info);
-
-	info->state = PN544_ST_COLD;
-
-out:
-	mutex_unlock(&info->info_lock);
-}
-
-static int pn544_hci_ready(struct nfc_hci_dev *hdev)
-{
-	struct sk_buff *skb;
-	static struct hw_config {
-		u8 adr[2];
-		u8 value;
-	} hw_config[] = {
-		{{0x9f, 0x9a}, 0x00},
-
-		{{0x98, 0x10}, 0xbc},
-
-		{{0x9e, 0x71}, 0x00},
-
-		{{0x98, 0x09}, 0x00},
-
-		{{0x9e, 0xb4}, 0x00},
-
-		{{0x9e, 0xd9}, 0xff},
-		{{0x9e, 0xda}, 0xff},
-		{{0x9e, 0xdb}, 0x23},
-		{{0x9e, 0xdc}, 0x21},
-		{{0x9e, 0xdd}, 0x22},
-		{{0x9e, 0xde}, 0x24},
-
-		{{0x9c, 0x01}, 0x08},
-
-		{{0x9e, 0xaa}, 0x01},
-
-		{{0x9b, 0xd1}, 0x0d},
-		{{0x9b, 0xd2}, 0x24},
-		{{0x9b, 0xd3}, 0x0a},
-		{{0x9b, 0xd4}, 0x22},
-		{{0x9b, 0xd5}, 0x08},
-		{{0x9b, 0xd6}, 0x1e},
-		{{0x9b, 0xdd}, 0x1c},
-
-		{{0x9b, 0x84}, 0x13},
-		{{0x99, 0x81}, 0x7f},
-		{{0x99, 0x31}, 0x70},
-
-		{{0x98, 0x00}, 0x3f},
-
-		{{0x9f, 0x09}, 0x00},
-
-		{{0x9f, 0x0a}, 0x05},
-
-		{{0x9e, 0xd1}, 0xa1},
-		{{0x99, 0x23}, 0x00},
-
-		{{0x9e, 0x74}, 0x80},
-
-		{{0x9f, 0x28}, 0x10},
-
-		{{0x9f, 0x35}, 0x14},
-
-		{{0x9f, 0x36}, 0x60},
-
-		{{0x9c, 0x31}, 0x00},
-
-		{{0x9c, 0x32}, 0xc8},
-
-		{{0x9c, 0x19}, 0x40},
-
-		{{0x9c, 0x1a}, 0x40},
-
-		{{0x9c, 0x0c}, 0x00},
-
-		{{0x9c, 0x0d}, 0x00},
-
-		{{0x9c, 0x12}, 0x00},
-
-		{{0x9c, 0x13}, 0x00},
-
-		{{0x98, 0xa2}, 0x0e},
-
-		{{0x98, 0x93}, 0x40},
-
-		{{0x98, 0x7d}, 0x02},
-		{{0x98, 0x7e}, 0x00},
-		{{0x9f, 0xc8}, 0x01},
-	};
-	struct hw_config *p = hw_config;
-	int count = ARRAY_SIZE(hw_config);
-	struct sk_buff *res_skb;
-	u8 param[4];
-	int r;
-
-	param[0] = 0;
-	while (count--) {
-		param[1] = p->adr[0];
-		param[2] = p->adr[1];
-		param[3] = p->value;
-
-		r = nfc_hci_send_cmd(hdev, PN544_SYS_MGMT_GATE, PN544_WRITE,
-				     param, 4, &res_skb);
-		if (r < 0)
-			return r;
-
-		if (res_skb->len != 1) {
-			kfree_skb(res_skb);
-			return -EPROTO;
-		}
-
-		if (res_skb->data[0] != p->value) {
-			kfree_skb(res_skb);
-			return -EIO;
-		}
-
-		kfree_skb(res_skb);
-
-		p++;
-	}
-
-	param[0] = NFC_HCI_UICC_HOST_ID;
-	r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE,
-			      NFC_HCI_ADMIN_WHITELIST, param, 1);
-	if (r < 0)
-		return r;
-
-	param[0] = 0x3d;
-	r = nfc_hci_set_param(hdev, PN544_SYS_MGMT_GATE,
-			      PN544_SYS_MGMT_INFO_NOTIFICATION, param, 1);
-	if (r < 0)
-		return r;
-
-	param[0] = 0x0;
-	r = nfc_hci_set_param(hdev, NFC_HCI_RF_READER_A_GATE,
-			      PN544_RF_READER_A_AUTO_ACTIVATION, param, 1);
-	if (r < 0)
-		return r;
-
-	r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
-			       NFC_HCI_EVT_END_OPERATION, NULL, 0);
-	if (r < 0)
-		return r;
-
-	param[0] = 0x1;
-	r = nfc_hci_set_param(hdev, PN544_POLLING_LOOP_MGMT_GATE,
-			      PN544_PL_NFCT_DEACTIVATED, param, 1);
-	if (r < 0)
-		return r;
-
-	param[0] = 0x0;
-	r = nfc_hci_set_param(hdev, PN544_POLLING_LOOP_MGMT_GATE,
-			      PN544_PL_RDPHASES, param, 1);
-	if (r < 0)
-		return r;
-
-	r = nfc_hci_get_param(hdev, NFC_HCI_ID_MGMT_GATE,
-			      PN544_ID_MGMT_FULL_VERSION_SW, &skb);
-	if (r < 0)
-		return r;
-
-	if (skb->len != FULL_VERSION_LEN) {
-		kfree_skb(skb);
-		return -EINVAL;
-	}
-
-	print_hex_dump(KERN_DEBUG, "FULL VERSION SOFTWARE INFO: ",
-		       DUMP_PREFIX_NONE, 16, 1,
-		       skb->data, FULL_VERSION_LEN, false);
-
-	kfree_skb(skb);
-
-	return 0;
-}
-
-static void pn544_hci_add_len_crc(struct sk_buff *skb)
-{
-	u16 crc;
-	int len;
-
-	len = skb->len + 2;
-	*skb_push(skb, 1) = len;
-
-	crc = crc_ccitt(0xffff, skb->data, skb->len);
-	crc = ~crc;
-	*skb_put(skb, 1) = crc & 0xff;
-	*skb_put(skb, 1) = crc >> 8;
-}
-
-static void pn544_hci_remove_len_crc(struct sk_buff *skb)
-{
-	skb_pull(skb, PN544_FRAME_HEADROOM);
-	skb_trim(skb, PN544_FRAME_TAILROOM);
-}
-
-static int pn544_hci_xmit(struct nfc_hci_dev *hdev, struct sk_buff *skb)
-{
-	struct pn544_hci_info *info = nfc_hci_get_clientdata(hdev);
-	struct i2c_client *client = info->i2c_dev;
-	int r;
-
-	if (info->hard_fault != 0)
-		return info->hard_fault;
-
-	pn544_hci_add_len_crc(skb);
-	r = pn544_hci_i2c_write(client, skb->data, skb->len);
-	pn544_hci_remove_len_crc(skb);
-
-	return r;
-}
-
-static int pn544_hci_start_poll(struct nfc_hci_dev *hdev,
-				u32 im_protocols, u32 tm_protocols)
-{
-	u8 phases = 0;
-	int r;
-	u8 duration[2];
-	u8 activated;
-	u8 i_mode = 0x3f; /* Enable all supported modes */
-	u8 t_mode = 0x0f;
-	u8 t_merge = 0x01; /* Enable merge by default */
-
-	pr_info(DRIVER_DESC ": %s protocols 0x%x 0x%x\n",
-		__func__, im_protocols, tm_protocols);
-
-	r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
-			       NFC_HCI_EVT_END_OPERATION, NULL, 0);
-	if (r < 0)
-		return r;
-
-	duration[0] = 0x18;
-	duration[1] = 0x6a;
-	r = nfc_hci_set_param(hdev, PN544_POLLING_LOOP_MGMT_GATE,
-			      PN544_PL_EMULATION, duration, 2);
-	if (r < 0)
-		return r;
-
-	activated = 0;
-	r = nfc_hci_set_param(hdev, PN544_POLLING_LOOP_MGMT_GATE,
-			      PN544_PL_NFCT_DEACTIVATED, &activated, 1);
-	if (r < 0)
-		return r;
-
-	if (im_protocols & (NFC_PROTO_ISO14443_MASK | NFC_PROTO_MIFARE_MASK |
-			 NFC_PROTO_JEWEL_MASK))
-		phases |= 1;		/* Type A */
-	if (im_protocols & NFC_PROTO_FELICA_MASK) {
-		phases |= (1 << 2);	/* Type F 212 */
-		phases |= (1 << 3);	/* Type F 424 */
-	}
-
-	phases |= (1 << 5);		/* NFC active */
-
-	r = nfc_hci_set_param(hdev, PN544_POLLING_LOOP_MGMT_GATE,
-			      PN544_PL_RDPHASES, &phases, 1);
-	if (r < 0)
-		return r;
-
-	if ((im_protocols | tm_protocols) & NFC_PROTO_NFC_DEP_MASK) {
-		hdev->gb = nfc_get_local_general_bytes(hdev->ndev,
-							&hdev->gb_len);
-		pr_debug("generate local bytes %p", hdev->gb);
-		if (hdev->gb == NULL || hdev->gb_len == 0) {
-			im_protocols &= ~NFC_PROTO_NFC_DEP_MASK;
-			tm_protocols &= ~NFC_PROTO_NFC_DEP_MASK;
-		}
-	}
-
-	if (im_protocols & NFC_PROTO_NFC_DEP_MASK) {
-		r = nfc_hci_send_event(hdev,
-				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
-				NFC_HCI_EVT_END_OPERATION, NULL, 0);
-		if (r < 0)
-			return r;
-
-		r = nfc_hci_set_param(hdev,
-				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
-				PN544_DEP_MODE, &i_mode, 1);
-		if (r < 0)
-			return r;
-
-		r = nfc_hci_set_param(hdev,
-				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
-				PN544_DEP_ATR_REQ, hdev->gb, hdev->gb_len);
-		if (r < 0)
-			return r;
-
-		r = nfc_hci_send_event(hdev,
-				PN544_RF_READER_NFCIP1_INITIATOR_GATE,
-				NFC_HCI_EVT_READER_REQUESTED, NULL, 0);
-		if (r < 0)
-			nfc_hci_send_event(hdev,
-					PN544_RF_READER_NFCIP1_INITIATOR_GATE,
-					NFC_HCI_EVT_END_OPERATION, NULL, 0);
-	}
-
-	if (tm_protocols & NFC_PROTO_NFC_DEP_MASK) {
-		r = nfc_hci_set_param(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
-				PN544_DEP_MODE, &t_mode, 1);
-		if (r < 0)
-			return r;
-
-		r = nfc_hci_set_param(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
-				PN544_DEP_ATR_RES, hdev->gb, hdev->gb_len);
-		if (r < 0)
-			return r;
-
-		r = nfc_hci_set_param(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
-				PN544_DEP_MERGE, &t_merge, 1);
-		if (r < 0)
-			return r;
-	}
-
-	r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
-			       NFC_HCI_EVT_READER_REQUESTED, NULL, 0);
-	if (r < 0)
-		nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
-				   NFC_HCI_EVT_END_OPERATION, NULL, 0);
-
-	return r;
-}
-
-static int pn544_hci_dep_link_up(struct nfc_hci_dev *hdev,
-				struct nfc_target *target, u8 comm_mode,
-				u8 *gb, size_t gb_len)
-{
-	struct sk_buff *rgb_skb = NULL;
-	int r;
-
-	r = nfc_hci_get_param(hdev, target->hci_reader_gate,
-				PN544_DEP_ATR_RES, &rgb_skb);
-	if (r < 0)
-		return r;
-
-	if (rgb_skb->len == 0 || rgb_skb->len > NFC_GB_MAXSIZE) {
-		r = -EPROTO;
-		goto exit;
-	}
-	print_hex_dump(KERN_DEBUG, "remote gb: ", DUMP_PREFIX_OFFSET,
-			16, 1, rgb_skb->data, rgb_skb->len, true);
-
-	r = nfc_set_remote_general_bytes(hdev->ndev, rgb_skb->data,
-						rgb_skb->len);
-
-	if (r == 0)
-		r = nfc_dep_link_is_up(hdev->ndev, target->idx, comm_mode,
-					NFC_RF_INITIATOR);
-exit:
-	kfree_skb(rgb_skb);
-	return r;
-}
-
-static int pn544_hci_dep_link_down(struct nfc_hci_dev *hdev)
-{
-
-	return nfc_hci_send_event(hdev, PN544_RF_READER_NFCIP1_INITIATOR_GATE,
-					NFC_HCI_EVT_END_OPERATION, NULL, 0);
-}
-
-static int pn544_hci_target_from_gate(struct nfc_hci_dev *hdev, u8 gate,
-				      struct nfc_target *target)
-{
-	switch (gate) {
-	case PN544_RF_READER_F_GATE:
-		target->supported_protocols = NFC_PROTO_FELICA_MASK;
-		break;
-	case PN544_RF_READER_JEWEL_GATE:
-		target->supported_protocols = NFC_PROTO_JEWEL_MASK;
-		target->sens_res = 0x0c00;
-		break;
-	case PN544_RF_READER_NFCIP1_INITIATOR_GATE:
-		target->supported_protocols = NFC_PROTO_NFC_DEP_MASK;
-		break;
-	default:
-		return -EPROTO;
-	}
-
-	return 0;
-}
-
-static int pn544_hci_complete_target_discovered(struct nfc_hci_dev *hdev,
-						u8 gate,
-						struct nfc_target *target)
-{
-	struct sk_buff *uid_skb;
-	int r = 0;
-
-	if (gate == PN544_RF_READER_NFCIP1_INITIATOR_GATE)
-		return r;
-
-	if (target->supported_protocols & NFC_PROTO_NFC_DEP_MASK) {
-		r = nfc_hci_send_cmd(hdev,
-			PN544_RF_READER_NFCIP1_INITIATOR_GATE,
-			PN544_HCI_CMD_CONTINUE_ACTIVATION, NULL, 0, NULL);
-		if (r < 0)
-			return r;
-
-		target->hci_reader_gate = PN544_RF_READER_NFCIP1_INITIATOR_GATE;
-	} else if (target->supported_protocols & NFC_PROTO_MIFARE_MASK) {
-		if (target->nfcid1_len != 4 && target->nfcid1_len != 7 &&
-		    target->nfcid1_len != 10)
-			return -EPROTO;
-
-		r = nfc_hci_send_cmd(hdev, NFC_HCI_RF_READER_A_GATE,
-				     PN544_RF_READER_CMD_ACTIVATE_NEXT,
-				     target->nfcid1, target->nfcid1_len, NULL);
-	} else if (target->supported_protocols & NFC_PROTO_FELICA_MASK) {
-		r = nfc_hci_get_param(hdev, PN544_RF_READER_F_GATE,
-				      PN544_FELICA_ID, &uid_skb);
-		if (r < 0)
-			return r;
-
-		if (uid_skb->len != 8) {
-			kfree_skb(uid_skb);
-			return -EPROTO;
-		}
-
-		r = nfc_hci_send_cmd(hdev, PN544_RF_READER_F_GATE,
-				     PN544_RF_READER_CMD_ACTIVATE_NEXT,
-				     uid_skb->data, uid_skb->len, NULL);
-		kfree_skb(uid_skb);
-
-		r = nfc_hci_send_cmd(hdev,
-					PN544_RF_READER_NFCIP1_INITIATOR_GATE,
-					PN544_HCI_CMD_CONTINUE_ACTIVATION,
-					NULL, 0, NULL);
-		if (r < 0)
-			return r;
-
-		target->hci_reader_gate = PN544_RF_READER_NFCIP1_INITIATOR_GATE;
-		target->supported_protocols = NFC_PROTO_NFC_DEP_MASK;
-	} else if (target->supported_protocols & NFC_PROTO_ISO14443_MASK) {
-		/*
-		 * TODO: maybe other ISO 14443 require some kind of continue
-		 * activation, but for now we've seen only this one below.
-		 */
-		if (target->sens_res == 0x4403)	/* Type 4 Mifare DESFire */
-			r = nfc_hci_send_cmd(hdev, NFC_HCI_RF_READER_A_GATE,
-			      PN544_RF_READER_A_CMD_CONTINUE_ACTIVATION,
-			      NULL, 0, NULL);
-	}
-
-	return r;
-}
-
-#define PN544_CB_TYPE_READER_F 1
-
-static void pn544_hci_data_exchange_cb(void *context, struct sk_buff *skb,
-				       int err)
-{
-	struct pn544_hci_info *info = context;
-
-	switch (info->async_cb_type) {
-	case PN544_CB_TYPE_READER_F:
-		if (err == 0)
-			skb_pull(skb, 1);
-		info->async_cb(info->async_cb_context, skb, err);
-		break;
-	default:
-		if (err == 0)
-			kfree_skb(skb);
-		break;
-	}
-}
-
-#define MIFARE_CMD_AUTH_KEY_A	0x60
-#define MIFARE_CMD_AUTH_KEY_B	0x61
-#define MIFARE_CMD_HEADER	2
-#define MIFARE_UID_LEN		4
-#define MIFARE_KEY_LEN		6
-#define MIFARE_CMD_LEN		12
-/*
- * Returns:
- * <= 0: driver handled the data exchange
- *    1: driver doesn't especially handle, please do standard processing
- */
-static int pn544_hci_im_transceive(struct nfc_hci_dev *hdev,
-				   struct nfc_target *target,
-				   struct sk_buff *skb, data_exchange_cb_t cb,
-				   void *cb_context)
-{
-	struct pn544_hci_info *info = nfc_hci_get_clientdata(hdev);
-
-	pr_info(DRIVER_DESC ": %s for gate=%d\n", __func__,
-		target->hci_reader_gate);
-
-	switch (target->hci_reader_gate) {
-	case NFC_HCI_RF_READER_A_GATE:
-		if (target->supported_protocols & NFC_PROTO_MIFARE_MASK) {
-			/*
-			 * It seems that pn544 is inverting key and UID for
-			 * MIFARE authentication commands.
-			 */
-			if (skb->len == MIFARE_CMD_LEN &&
-			    (skb->data[0] == MIFARE_CMD_AUTH_KEY_A ||
-			     skb->data[0] == MIFARE_CMD_AUTH_KEY_B)) {
-				u8 uid[MIFARE_UID_LEN];
-				u8 *data = skb->data + MIFARE_CMD_HEADER;
-
-				memcpy(uid, data + MIFARE_KEY_LEN,
-				       MIFARE_UID_LEN);
-				memmove(data + MIFARE_UID_LEN, data,
-					MIFARE_KEY_LEN);
-				memcpy(data, uid, MIFARE_UID_LEN);
-			}
-
-			return nfc_hci_send_cmd_async(hdev,
-						      target->hci_reader_gate,
-						      PN544_MIFARE_CMD,
-						      skb->data, skb->len,
-						      cb, cb_context);
-		} else
-			return 1;
-	case PN544_RF_READER_F_GATE:
-		*skb_push(skb, 1) = 0;
-		*skb_push(skb, 1) = 0;
-
-		info->async_cb_type = PN544_CB_TYPE_READER_F;
-		info->async_cb = cb;
-		info->async_cb_context = cb_context;
-
-		return nfc_hci_send_cmd_async(hdev, target->hci_reader_gate,
-					      PN544_FELICA_RAW, skb->data,
-					      skb->len,
-					      pn544_hci_data_exchange_cb, info);
-	case PN544_RF_READER_JEWEL_GATE:
-		return nfc_hci_send_cmd_async(hdev, target->hci_reader_gate,
-					      PN544_JEWEL_RAW_CMD, skb->data,
-					      skb->len, cb, cb_context);
-	case PN544_RF_READER_NFCIP1_INITIATOR_GATE:
-		*skb_push(skb, 1) = 0;
-
-		return nfc_hci_send_event(hdev, target->hci_reader_gate,
-					PN544_HCI_EVT_SND_DATA, skb->data,
-					skb->len);
-	default:
-		return 1;
-	}
-}
-
-static int pn544_hci_tm_send(struct nfc_hci_dev *hdev, struct sk_buff *skb)
-{
-	/* Set default false for multiple information chaining */
-	*skb_push(skb, 1) = 0;
-
-	return nfc_hci_send_event(hdev, PN544_RF_READER_NFCIP1_TARGET_GATE,
-				PN544_HCI_EVT_SND_DATA, skb->data, skb->len);
-}
-
-static int pn544_hci_check_presence(struct nfc_hci_dev *hdev,
-				   struct nfc_target *target)
-{
-	pr_debug("supported protocol %d", target->supported_protocols);
-	if (target->supported_protocols & (NFC_PROTO_ISO14443_MASK |
-					NFC_PROTO_ISO14443_B_MASK)) {
-		return nfc_hci_send_cmd(hdev, target->hci_reader_gate,
-					PN544_RF_READER_CMD_PRESENCE_CHECK,
-					NULL, 0, NULL);
-	} else if (target->supported_protocols & NFC_PROTO_MIFARE_MASK) {
-		if (target->nfcid1_len != 4 && target->nfcid1_len != 7 &&
-		    target->nfcid1_len != 10)
-			return -EOPNOTSUPP;
-
-		 return nfc_hci_send_cmd(hdev, NFC_HCI_RF_READER_A_GATE,
-				     PN544_RF_READER_CMD_ACTIVATE_NEXT,
-				     target->nfcid1, target->nfcid1_len, NULL);
-	} else if (target->supported_protocols & NFC_PROTO_JEWEL_MASK) {
-		return nfc_hci_send_cmd(hdev, target->hci_reader_gate,
-					PN544_JEWEL_RAW_CMD, NULL, 0, NULL);
-	} else if (target->supported_protocols & NFC_PROTO_FELICA_MASK) {
-		return nfc_hci_send_cmd(hdev, PN544_RF_READER_F_GATE,
-					PN544_FELICA_RAW, NULL, 0, NULL);
-	} else if (target->supported_protocols & NFC_PROTO_NFC_DEP_MASK) {
-		return nfc_hci_send_cmd(hdev, target->hci_reader_gate,
-					PN544_HCI_CMD_ATTREQUEST,
-					NULL, 0, NULL);
-	}
-
-	return 0;
-}
-
-void pn544_hci_event_received(struct nfc_hci_dev *hdev, u8 gate, u8 event,
-				struct sk_buff *skb)
-{
-	struct sk_buff *rgb_skb = NULL;
-	int r = 0;
-
-	pr_debug("hci event %d", event);
-	switch (event) {
-	case PN544_HCI_EVT_ACTIVATED:
-		if (gate == PN544_RF_READER_NFCIP1_INITIATOR_GATE)
-			nfc_hci_target_discovered(hdev, gate);
-		else if (gate == PN544_RF_READER_NFCIP1_TARGET_GATE) {
-			r = nfc_hci_get_param(hdev, gate, PN544_DEP_ATR_REQ,
-						&rgb_skb);
-
-			if (r < 0)
-				goto exit;
-
-			nfc_tm_activated(hdev->ndev, NFC_PROTO_NFC_DEP_MASK,
-					NFC_COMM_PASSIVE, rgb_skb->data,
-					rgb_skb->len);
-
-			kfree_skb(rgb_skb);
-		}
-
-		break;
-	case PN544_HCI_EVT_DEACTIVATED:
-		nfc_hci_send_event(hdev, gate,
-			NFC_HCI_EVT_END_OPERATION, NULL, 0);
-		break;
-	case PN544_HCI_EVT_RCV_DATA:
-		if (skb->len < 2) {
-			r = -EPROTO;
-			goto exit;
-		}
-
-		if (skb->data[0] != 0) {
-			pr_debug("data0 %d", skb->data[0]);
-			r = -EPROTO;
-			goto exit;
-		}
-
-		skb_pull(skb, 2);
-		nfc_tm_data_received(hdev->ndev, skb);
-
-		return;
-	default:
-		break;
-	}
-
-exit:
-	kfree_skb(skb);
-}
-
-static struct nfc_hci_ops pn544_hci_ops = {
-	.open = pn544_hci_open,
-	.close = pn544_hci_close,
-	.hci_ready = pn544_hci_ready,
-	.xmit = pn544_hci_xmit,
-	.start_poll = pn544_hci_start_poll,
-	.dep_link_up = pn544_hci_dep_link_up,
-	.dep_link_down = pn544_hci_dep_link_down,
-	.target_from_gate = pn544_hci_target_from_gate,
-	.complete_target_discovered = pn544_hci_complete_target_discovered,
-	.im_transceive = pn544_hci_im_transceive,
-	.tm_send = pn544_hci_tm_send,
-	.check_presence = pn544_hci_check_presence,
-	.event_received = pn544_hci_event_received,
-};
-
-static int __devinit pn544_hci_probe(struct i2c_client *client,
-				     const struct i2c_device_id *id)
-{
-	struct pn544_hci_info *info;
-	struct pn544_nfc_platform_data *pdata;
-	int r = 0;
-	u32 protocols;
-	struct nfc_hci_init_data init_data;
-
-	dev_dbg(&client->dev, "%s\n", __func__);
-	dev_dbg(&client->dev, "IRQ: %d\n", client->irq);
-
-	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
-		dev_err(&client->dev, "Need I2C_FUNC_I2C\n");
-		return -ENODEV;
-	}
-
-	info = kzalloc(sizeof(struct pn544_hci_info), GFP_KERNEL);
-	if (!info) {
-		dev_err(&client->dev,
-			"Cannot allocate memory for pn544_hci_info.\n");
-		r = -ENOMEM;
-		goto err_info_alloc;
-	}
-
-	info->i2c_dev = client;
-	info->state = PN544_ST_COLD;
-	mutex_init(&info->info_lock);
-	i2c_set_clientdata(client, info);
-
-	pdata = client->dev.platform_data;
-	if (pdata == NULL) {
-		dev_err(&client->dev, "No platform data\n");
-		r = -EINVAL;
-		goto err_pdata;
-	}
-
-	if (pdata->request_resources == NULL) {
-		dev_err(&client->dev, "request_resources() missing\n");
-		r = -EINVAL;
-		goto err_pdata;
-	}
-
-	r = pdata->request_resources(client);
-	if (r) {
-		dev_err(&client->dev, "Cannot get platform resources\n");
-		goto err_pdata;
-	}
-
-	info->gpio_en = pdata->get_gpio(NFC_GPIO_ENABLE);
-	info->gpio_fw = pdata->get_gpio(NFC_GPIO_FW_RESET);
-	info->gpio_irq = pdata->get_gpio(NFC_GPIO_IRQ);
-
-	pn544_hci_platform_init(info);
-
-	r = request_threaded_irq(client->irq, NULL, pn544_hci_irq_thread_fn,
-				 IRQF_TRIGGER_RISING | IRQF_ONESHOT,
-				 PN544_HCI_DRIVER_NAME, info);
-	if (r < 0) {
-		dev_err(&client->dev, "Unable to register IRQ handler\n");
-		goto err_rti;
-	}
-
-	init_data.gate_count = ARRAY_SIZE(pn544_gates);
-
-	memcpy(init_data.gates, pn544_gates, sizeof(pn544_gates));
-
-	/*
-	 * TODO: Session id must include the driver name + some bus addr
-	 * persistent info to discriminate 2 identical chips
-	 */
-	strcpy(init_data.session_id, "ID544HCI");
-
-	protocols = NFC_PROTO_JEWEL_MASK |
-		    NFC_PROTO_MIFARE_MASK |
-		    NFC_PROTO_FELICA_MASK |
-		    NFC_PROTO_ISO14443_MASK |
-		    NFC_PROTO_ISO14443_B_MASK |
-		    NFC_PROTO_NFC_DEP_MASK;
-
-	info->hdev = nfc_hci_allocate_device(&pn544_hci_ops, &init_data,
-					     protocols, LLC_SHDLC_NAME,
-					     PN544_FRAME_HEADROOM +
-					     PN544_CMDS_HEADROOM,
-					     PN544_FRAME_TAILROOM,
-					     PN544_HCI_LLC_MAX_PAYLOAD);
-	if (!info->hdev) {
-		dev_err(&client->dev, "Cannot allocate nfc hdev.\n");
-		r = -ENOMEM;
-		goto err_alloc_hdev;
-	}
-
-	nfc_hci_set_clientdata(info->hdev, info);
-
-	r = nfc_hci_register_device(info->hdev);
-	if (r)
-		goto err_regdev;
-
-	return 0;
-
-err_regdev:
-	nfc_hci_free_device(info->hdev);
-
-err_alloc_hdev:
-	free_irq(client->irq, info);
-
-err_rti:
-	if (pdata->free_resources != NULL)
-		pdata->free_resources();
-
-err_pdata:
-	kfree(info);
-
-err_info_alloc:
-	return r;
-}
-
-static __devexit int pn544_hci_remove(struct i2c_client *client)
-{
-	struct pn544_hci_info *info = i2c_get_clientdata(client);
-	struct pn544_nfc_platform_data *pdata = client->dev.platform_data;
-
-	dev_dbg(&client->dev, "%s\n", __func__);
-
-	nfc_hci_free_device(info->hdev);
-
-	if (info->state != PN544_ST_COLD) {
-		if (pdata->disable)
-			pdata->disable();
-	}
-
-	free_irq(client->irq, info);
-	if (pdata->free_resources)
-		pdata->free_resources();
-
-	kfree(info);
-
-	return 0;
-}
-
-static struct i2c_driver pn544_hci_driver = {
-	.driver = {
-		   .name = PN544_HCI_DRIVER_NAME,
-		  },
-	.probe = pn544_hci_probe,
-	.id_table = pn544_hci_id_table,
-	.remove = __devexit_p(pn544_hci_remove),
-};
-
-static int __init pn544_hci_init(void)
-{
-	int r;
-
-	pr_debug(DRIVER_DESC ": %s\n", __func__);
-
-	r = i2c_add_driver(&pn544_hci_driver);
-	if (r) {
-		pr_err(PN544_HCI_DRIVER_NAME ": driver registration failed\n");
-		return r;
-	}
-
-	return 0;
-}
-
-static void __exit pn544_hci_exit(void)
-{
-	i2c_del_driver(&pn544_hci_driver);
-}
-
-module_init(pn544_hci_init);
-module_exit(pn544_hci_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index bc87b8f2d692..639f50af42df 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -24,6 +24,12 @@
 
 #include <net/nfc/nfc.h>
 
+struct nfc_phy_ops {
+	int (*write)(void *dev_id, struct sk_buff *skb);
+	int (*enable)(void *dev_id);
+	void (*disable)(void *dev_id);
+};
+
 struct nfc_hci_dev;
 
 struct nfc_hci_ops {
-- 
cgit v1.2.3-55-g7522


From 7eda8b8e967781cfa5a04962502f9aa428f67e5f Mon Sep 17 00:00:00 2001
From: Samuel Ortiz
Date: Mon, 22 Oct 2012 15:57:58 +0200
Subject: NFC: Use IDR library to assing NFC devices IDs

As a consequence the NFC device IDs won't be increasing all the time,
as IDR provides the first available ID.

Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nfc.h |  2 +-
 net/nfc/core.c        | 23 ++++++++++++++++-------
 2 files changed, 17 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index f05b10682c9d..fce80b2f9be7 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -95,7 +95,7 @@ struct nfc_genl_data {
 };
 
 struct nfc_dev {
-	unsigned int idx;
+	int idx;
 	u32 target_next_idx;
 	struct nfc_target *targets;
 	int n_targets;
diff --git a/net/nfc/core.c b/net/nfc/core.c
index f1c33f233311..e94363dbbf4a 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -40,6 +40,9 @@
 int nfc_devlist_generation;
 DEFINE_MUTEX(nfc_devlist_mutex);
 
+/* NFC device ID bitmap */
+static DEFINE_IDA(nfc_index_ida);
+
 /**
  * nfc_dev_up - turn on the NFC device
  *
@@ -760,7 +763,6 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops,
 				    u32 supported_protocols,
 				    int tx_headroom, int tx_tailroom)
 {
-	static atomic_t dev_no = ATOMIC_INIT(0);
 	struct nfc_dev *dev;
 
 	if (!ops->start_poll || !ops->stop_poll || !ops->activate_target ||
@@ -774,11 +776,6 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops,
 	if (!dev)
 		return NULL;
 
-	dev->dev.class = &nfc_class;
-	dev->idx = atomic_inc_return(&dev_no) - 1;
-	dev_set_name(&dev->dev, "nfc%d", dev->idx);
-	device_initialize(&dev->dev);
-
 	dev->ops = ops;
 	dev->supported_protocols = supported_protocols;
 	dev->tx_headroom = tx_headroom;
@@ -814,6 +811,14 @@ int nfc_register_device(struct nfc_dev *dev)
 
 	pr_debug("dev_name=%s\n", dev_name(&dev->dev));
 
+	dev->idx = ida_simple_get(&nfc_index_ida, 0, 0, GFP_KERNEL);
+	if (dev->idx < 0)
+		return dev->idx;
+
+	dev->dev.class = &nfc_class;
+	dev_set_name(&dev->dev, "nfc%d", dev->idx);
+	device_initialize(&dev->dev);
+
 	mutex_lock(&nfc_devlist_mutex);
 	nfc_devlist_generation++;
 	rc = device_add(&dev->dev);
@@ -842,10 +847,12 @@ EXPORT_SYMBOL(nfc_register_device);
  */
 void nfc_unregister_device(struct nfc_dev *dev)
 {
-	int rc;
+	int rc, id;
 
 	pr_debug("dev_name=%s\n", dev_name(&dev->dev));
 
+	id = dev->idx;
+
 	mutex_lock(&nfc_devlist_mutex);
 	nfc_devlist_generation++;
 
@@ -864,6 +871,8 @@ void nfc_unregister_device(struct nfc_dev *dev)
 		pr_debug("The userspace won't be notified that the device %s was removed\n",
 			 dev_name(&dev->dev));
 
+	ida_simple_remove(&nfc_index_ida, id);
+
 }
 EXPORT_SYMBOL(nfc_unregister_device);
 
-- 
cgit v1.2.3-55-g7522


From 5d8f72b55c275677865de670fa147ed318191d81 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov
Date: Fri, 26 Oct 2012 19:46:06 +0200
Subject: freezer: change ptrace_stop/do_signal_stop to use
 freezable_schedule()

try_to_freeze_tasks() and cgroup_freezer rely on scheduler locks
to ensure that a task doing STOPPED/TRACED -> RUNNING transition
can't escape freezing. This mostly works, but ptrace_stop() does
not necessarily call schedule(), it can change task->state back to
RUNNING and check freezing() without any lock/barrier in between.

We could add the necessary barrier, but this patch changes
ptrace_stop() and do_signal_stop() to use freezable_schedule().
This fixes the race, freezer_count() and freezer_should_skip()
carefully avoid the race.

And this simplifies the code, try_to_freeze_tasks/update_if_frozen
no longer need to use task_is_stopped_or_traced() checks with the
non trivial assumptions. We can rely on the mechanism which was
specially designed to mark the sleeping task as "frozen enough".

v2: As Tejun pointed out, we can also change get_signal_to_deliver()
and move try_to_freeze() up before 'relock' label.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/freezer.h |  7 +++----
 kernel/cgroup_freezer.c |  3 +--
 kernel/freezer.c        | 11 ++---------
 kernel/power/process.c  | 13 +------------
 kernel/signal.c         | 20 ++++++--------------
 5 files changed, 13 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index ee899329e65a..8039893bc3ec 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -134,10 +134,9 @@ static inline bool freezer_should_skip(struct task_struct *p)
 }
 
 /*
- * These macros are intended to be used whenever you want allow a task that's
- * sleeping in TASK_UNINTERRUPTIBLE or TASK_KILLABLE state to be frozen. Note
- * that neither return any clear indication of whether a freeze event happened
- * while in this function.
+ * These macros are intended to be used whenever you want allow a sleeping
+ * task to be frozen. Note that neither return any clear indication of
+ * whether a freeze event happened while in this function.
  */
 
 /* Like schedule(), but should not block the freezer. */
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 8a92b0e52099..bedefd9a22df 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -198,8 +198,7 @@ static void update_if_frozen(struct cgroup *cgroup, struct freezer *freezer)
 			 * completion.  Consider it frozen in addition to
 			 * the usual frozen condition.
 			 */
-			if (!frozen(task) && !task_is_stopped_or_traced(task) &&
-			    !freezer_should_skip(task))
+			if (!frozen(task) && !freezer_should_skip(task))
 				goto notyet;
 		}
 	}
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 11f82a4d4eae..c38893b0efba 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -116,17 +116,10 @@ bool freeze_task(struct task_struct *p)
 		return false;
 	}
 
-	if (!(p->flags & PF_KTHREAD)) {
+	if (!(p->flags & PF_KTHREAD))
 		fake_signal_wake_up(p);
-		/*
-		 * fake_signal_wake_up() goes through p's scheduler
-		 * lock and guarantees that TASK_STOPPED/TRACED ->
-		 * TASK_RUNNING transition can't race with task state
-		 * testing in try_to_freeze_tasks().
-		 */
-	} else {
+	else
 		wake_up_state(p, TASK_INTERRUPTIBLE);
-	}
 
 	spin_unlock_irqrestore(&freezer_lock, flags);
 	return true;
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 87da817f9e13..d5a258b60c6f 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -48,18 +48,7 @@ static int try_to_freeze_tasks(bool user_only)
 			if (p == current || !freeze_task(p))
 				continue;
 
-			/*
-			 * Now that we've done set_freeze_flag, don't
-			 * perturb a task in TASK_STOPPED or TASK_TRACED.
-			 * It is "frozen enough".  If the task does wake
-			 * up, it will immediately call try_to_freeze.
-			 *
-			 * Because freeze_task() goes through p's scheduler lock, it's
-			 * guaranteed that TASK_STOPPED/TRACED -> TASK_RUNNING
-			 * transition can't race with task state testing here.
-			 */
-			if (!task_is_stopped_or_traced(p) &&
-			    !freezer_should_skip(p))
+			if (!freezer_should_skip(p))
 				todo++;
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);
diff --git a/kernel/signal.c b/kernel/signal.c
index 0af8868525d6..5ffb5626e072 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1908,7 +1908,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 		preempt_disable();
 		read_unlock(&tasklist_lock);
 		preempt_enable_no_resched();
-		schedule();
+		freezable_schedule();
 	} else {
 		/*
 		 * By the time we got the lock, our tracer went away.
@@ -1929,13 +1929,6 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 		read_unlock(&tasklist_lock);
 	}
 
-	/*
-	 * While in TASK_TRACED, we were considered "frozen enough".
-	 * Now that we woke up, it's crucial if we're supposed to be
-	 * frozen that we freeze now before running anything substantial.
-	 */
-	try_to_freeze();
-
 	/*
 	 * We are back.  Now reacquire the siglock before touching
 	 * last_siginfo, so that we are sure to have synchronized with
@@ -2092,7 +2085,7 @@ static bool do_signal_stop(int signr)
 		}
 
 		/* Now we don't run again until woken by SIGCONT or SIGKILL */
-		schedule();
+		freezable_schedule();
 		return true;
 	} else {
 		/*
@@ -2200,15 +2193,14 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
 	if (unlikely(uprobe_deny_signal()))
 		return 0;
 
-relock:
 	/*
-	 * We'll jump back here after any time we were stopped in TASK_STOPPED.
-	 * While in TASK_STOPPED, we were considered "frozen enough".
-	 * Now that we woke up, it's crucial if we're supposed to be
-	 * frozen that we freeze now before running anything substantial.
+	 * Do this once, we can't return to user-mode if freezing() == T.
+	 * do_signal_stop() and ptrace_stop() do freezable_schedule() and
+	 * thus do not need another check after return.
 	 */
 	try_to_freeze();
 
+relock:
 	spin_lock_irq(&sighand->siglock);
 	/*
 	 * Every stopped thread goes here after wakeup. Check to see if
-- 
cgit v1.2.3-55-g7522


From 2eb2478d471e45e1d0c8bb3defbf82bf7204e13d Mon Sep 17 00:00:00 2001
From: Matt Porter
Date: Fri, 5 Oct 2012 13:04:40 -0400
Subject: uio: uio_pruss: replace private SRAM API with genalloc

Remove the use of the private DaVinci SRAM API in favor
of genalloc. The pool to be used is provided by platform
data.

Signed-off-by: Matt Porter <mporter@ti.com>
Signed-off-by: "Hans J. Koch" <hjk@hansjkoch.de>
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
---
 drivers/uio/Kconfig                     |  1 +
 drivers/uio/uio_pruss.c                 | 24 +++++++++++++++++-------
 include/linux/platform_data/uio_pruss.h |  3 ++-
 3 files changed, 20 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/uio/Kconfig b/drivers/uio/Kconfig
index 6f3ea9bbc818..c48b93813fc1 100644
--- a/drivers/uio/Kconfig
+++ b/drivers/uio/Kconfig
@@ -97,6 +97,7 @@ config UIO_NETX
 config UIO_PRUSS
 	tristate "Texas Instruments PRUSS driver"
 	depends on ARCH_DAVINCI_DA850
+	select GENERIC_ALLOCATOR
 	help
 	  PRUSS driver for OMAPL138/DA850/AM18XX devices
 	  PRUSS driver requires user space components, examples and user space
diff --git a/drivers/uio/uio_pruss.c b/drivers/uio/uio_pruss.c
index 33a7a273b453..f8738de342be 100644
--- a/drivers/uio/uio_pruss.c
+++ b/drivers/uio/uio_pruss.c
@@ -25,7 +25,7 @@
 #include <linux/clk.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
-#include <mach/sram.h>
+#include <linux/genalloc.h>
 
 #define DRV_NAME "pruss_uio"
 #define DRV_VERSION "1.0"
@@ -65,10 +65,11 @@ struct uio_pruss_dev {
 	dma_addr_t sram_paddr;
 	dma_addr_t ddr_paddr;
 	void __iomem *prussio_vaddr;
-	void *sram_vaddr;
+	unsigned long sram_vaddr;
 	void *ddr_vaddr;
 	unsigned int hostirq_start;
 	unsigned int pintc_base;
+	struct gen_pool *sram_pool;
 };
 
 static irqreturn_t pruss_handler(int irq, struct uio_info *info)
@@ -106,7 +107,9 @@ static void pruss_cleanup(struct platform_device *dev,
 			gdev->ddr_paddr);
 	}
 	if (gdev->sram_vaddr)
-		sram_free(gdev->sram_vaddr, sram_pool_sz);
+		gen_pool_free(gdev->sram_pool,
+			      gdev->sram_vaddr,
+			      sram_pool_sz);
 	kfree(gdev->info);
 	clk_put(gdev->pruss_clk);
 	kfree(gdev);
@@ -152,10 +155,17 @@ static int __devinit pruss_probe(struct platform_device *dev)
 		goto out_free;
 	}
 
-	gdev->sram_vaddr = sram_alloc(sram_pool_sz, &(gdev->sram_paddr));
-	if (!gdev->sram_vaddr) {
-		dev_err(&dev->dev, "Could not allocate SRAM pool\n");
-		goto out_free;
+	if (pdata->sram_pool) {
+		gdev->sram_pool = pdata->sram_pool;
+		gdev->sram_vaddr =
+			gen_pool_alloc(gdev->sram_pool, sram_pool_sz);
+		if (!gdev->sram_vaddr) {
+			dev_err(&dev->dev, "Could not allocate SRAM pool\n");
+			goto out_free;
+		}
+		gdev->sram_paddr =
+			gen_pool_virt_to_phys(gdev->sram_pool,
+					      gdev->sram_vaddr);
 	}
 
 	gdev->ddr_vaddr = dma_alloc_coherent(&dev->dev, extram_pool_sz,
diff --git a/include/linux/platform_data/uio_pruss.h b/include/linux/platform_data/uio_pruss.h
index f39140aabc6f..3d47d219827f 100644
--- a/include/linux/platform_data/uio_pruss.h
+++ b/include/linux/platform_data/uio_pruss.h
@@ -20,6 +20,7 @@
 
 /* To configure the PRUSS INTC base offset for UIO driver */
 struct uio_pruss_pdata {
-	u32	pintc_base;
+	u32		pintc_base;
+	struct gen_pool *sram_pool;
 };
 #endif /* _UIO_PRUSS_H_ */
-- 
cgit v1.2.3-55-g7522


From c003ab1bedf028db15b0185b683d5c387204e8f5 Mon Sep 17 00:00:00 2001
From: David Härdeman
Date: Thu, 11 Oct 2012 19:11:54 -0300
Subject: [media] rc-core: add separate defines for protocol bitmaps and
 numbers

The RC_TYPE_* defines are currently used both where a single protocol is
expected and where a bitmap of protocols is expected.

Functions like rc_keydown() and functions which add/remove entries to the
keytable want a single protocol. Future userspace APIs would also
benefit from numeric protocols (rather than bitmap ones). Keytables are
smaller if they can use a small(ish) integer rather than a bitmap.

Other functions or struct members (e.g. allowed_protos,
enabled_protocols, etc) accept multiple protocols and need a bitmap.

Using different types reduces the risk of programmer error. Using a
protocol enum whereever possible also makes for a more future-proof
user-space API as we don't need to worry about a sufficient number of
bits being available (e.g. in structs used for ioctl() calls).

The use of both a number and a corresponding bit is dalso one in e.g.
the input subsystem as well (see all the references to set/clear bit when
changing keytables for example).

This patch separate the different usages in preparation for
upcoming patches.

Where a single protocol is expected, enum rc_type is used; where one or more
protocol(s) are expected, something like u64 is used.

The patch has been rewritten so that the format of the sysfs "protocols"
file is no longer altered (at the loss of some detail). The file itself
should probably be deprecated in the future though.

Signed-off-by: David Härdeman <david@hardeman.nu>
Cc: Andy Walls <awalls@md.metrocast.net>
Cc: Maxim Levitsky <maximlevitsky@gmail.com>
Cc: Antti Palosaari <crope@iki.fi>
Cc: Mike Isely <isely@pobox.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/common/siano/smsir.c           |   2 +-
 drivers/media/i2c/ir-kbd-i2c.c               |  14 +--
 drivers/media/pci/cx18/cx18-i2c.c            |   2 +-
 drivers/media/pci/cx23885/cx23885-input.c    |   6 +-
 drivers/media/pci/cx88/cx88-input.c          |   8 +-
 drivers/media/pci/ivtv/ivtv-i2c.c            |   8 +-
 drivers/media/pci/saa7134/saa7134-input.c    |   2 +-
 drivers/media/rc/ati_remote.c                |   2 +-
 drivers/media/rc/ene_ir.c                    |   2 +-
 drivers/media/rc/fintek-cir.c                |   2 +-
 drivers/media/rc/gpio-ir-recv.c              |   2 +-
 drivers/media/rc/iguanair.c                  |   2 +-
 drivers/media/rc/imon.c                      |  40 ++++----
 drivers/media/rc/ir-jvc-decoder.c            |   4 +-
 drivers/media/rc/ir-lirc-codec.c             |   4 +-
 drivers/media/rc/ir-mce_kbd-decoder.c        |   4 +-
 drivers/media/rc/ir-nec-decoder.c            |   4 +-
 drivers/media/rc/ir-rc5-decoder.c            |  14 ++-
 drivers/media/rc/ir-rc5-sz-decoder.c         |   6 +-
 drivers/media/rc/ir-rc6-decoder.c            |   8 +-
 drivers/media/rc/ir-sanyo-decoder.c          |   4 +-
 drivers/media/rc/ir-sony-decoder.c           |  17 +++-
 drivers/media/rc/ite-cir.c                   |   2 +-
 drivers/media/rc/keymaps/rc-imon-mce.c       |   2 +-
 drivers/media/rc/keymaps/rc-rc6-mce.c        |   2 +-
 drivers/media/rc/mceusb.c                    |   2 +-
 drivers/media/rc/nuvoton-cir.c               |   2 +-
 drivers/media/rc/rc-loopback.c               |   2 +-
 drivers/media/rc/rc-main.c                   |  73 ++++++++------
 drivers/media/rc/redrat3.c                   |   2 +-
 drivers/media/rc/streamzap.c                 |   2 +-
 drivers/media/rc/ttusbir.c                   |   2 +-
 drivers/media/rc/winbond-cir.c               |   2 +-
 drivers/media/usb/cx231xx/cx231xx-input.c    |   2 +-
 drivers/media/usb/dvb-usb-v2/af9015.c        |   2 +-
 drivers/media/usb/dvb-usb-v2/af9035.c        |   4 +-
 drivers/media/usb/dvb-usb-v2/anysee.c        |   2 +-
 drivers/media/usb/dvb-usb-v2/az6007.c        |   2 +-
 drivers/media/usb/dvb-usb-v2/dvb_usb.h       |   2 +-
 drivers/media/usb/dvb-usb-v2/it913x.c        |   2 +-
 drivers/media/usb/dvb-usb-v2/lmedm04.c       |   2 +-
 drivers/media/usb/dvb-usb-v2/rtl28xxu.c      |   4 +-
 drivers/media/usb/dvb-usb/dib0700.h          |   2 +-
 drivers/media/usb/dvb-usb/dib0700_core.c     |  16 +--
 drivers/media/usb/dvb-usb/dib0700_devices.c  | 146 +++++++++++++--------------
 drivers/media/usb/dvb-usb/dvb-usb.h          |   2 +-
 drivers/media/usb/dvb-usb/pctv452e.c         |   4 +-
 drivers/media/usb/dvb-usb/technisat-usb2.c   |   2 +-
 drivers/media/usb/dvb-usb/ttusb2.c           |   2 +-
 drivers/media/usb/em28xx/em28xx-input.c      |  16 +--
 drivers/media/usb/hdpvr/hdpvr-i2c.c          |   2 +-
 drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c |   4 +-
 drivers/media/usb/tm6000/tm6000-input.c      |  20 ++--
 include/media/ir-kbd-i2c.h                   |   2 +-
 include/media/rc-core.h                      |   4 +-
 include/media/rc-map.h                       |  64 +++++++++---
 56 files changed, 314 insertions(+), 244 deletions(-)

(limited to 'include')

diff --git a/drivers/media/common/siano/smsir.c b/drivers/media/common/siano/smsir.c
index 37bc5c4b8ad8..b8c5cad78537 100644
--- a/drivers/media/common/siano/smsir.c
+++ b/drivers/media/common/siano/smsir.c
@@ -88,7 +88,7 @@ int sms_ir_init(struct smscore_device_t *coredev)
 
 	dev->priv = coredev;
 	dev->driver_type = RC_DRIVER_IR_RAW;
-	dev->allowed_protos = RC_TYPE_ALL;
+	dev->allowed_protos = RC_BIT_ALL;
 	dev->map_name = sms_get_board(board_id)->rc_codes;
 	dev->driver_name = MODULE_NAME;
 
diff --git a/drivers/media/i2c/ir-kbd-i2c.c b/drivers/media/i2c/ir-kbd-i2c.c
index 04f192a0398a..08ae067b2b6f 100644
--- a/drivers/media/i2c/ir-kbd-i2c.c
+++ b/drivers/media/i2c/ir-kbd-i2c.c
@@ -284,7 +284,7 @@ static int ir_probe(struct i2c_client *client, const struct i2c_device_id *id)
 {
 	char *ir_codes = NULL;
 	const char *name = NULL;
-	u64 rc_type = RC_TYPE_UNKNOWN;
+	u64 rc_type = RC_BIT_UNKNOWN;
 	struct IR_i2c *ir;
 	struct rc_dev *rc = NULL;
 	struct i2c_adapter *adap = client->adapter;
@@ -303,7 +303,7 @@ static int ir_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	case 0x64:
 		name        = "Pixelview";
 		ir->get_key = get_key_pixelview;
-		rc_type     = RC_TYPE_OTHER;
+		rc_type     = RC_BIT_OTHER;
 		ir_codes    = RC_MAP_EMPTY;
 		break;
 	case 0x18:
@@ -311,31 +311,31 @@ static int ir_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	case 0x1a:
 		name        = "Hauppauge";
 		ir->get_key = get_key_haup;
-		rc_type     = RC_TYPE_RC5;
+		rc_type     = RC_BIT_RC5;
 		ir_codes    = RC_MAP_HAUPPAUGE;
 		break;
 	case 0x30:
 		name        = "KNC One";
 		ir->get_key = get_key_knc1;
-		rc_type     = RC_TYPE_OTHER;
+		rc_type     = RC_BIT_OTHER;
 		ir_codes    = RC_MAP_EMPTY;
 		break;
 	case 0x6b:
 		name        = "FusionHDTV";
 		ir->get_key = get_key_fusionhdtv;
-		rc_type     = RC_TYPE_RC5;
+		rc_type     = RC_BIT_RC5;
 		ir_codes    = RC_MAP_FUSIONHDTV_MCE;
 		break;
 	case 0x40:
 		name        = "AVerMedia Cardbus remote";
 		ir->get_key = get_key_avermedia_cardbus;
-		rc_type     = RC_TYPE_OTHER;
+		rc_type     = RC_BIT_OTHER;
 		ir_codes    = RC_MAP_AVERMEDIA_CARDBUS;
 		break;
 	case 0x71:
 		name        = "Hauppauge/Zilog Z8";
 		ir->get_key = get_key_haup_xvr;
-		rc_type     = RC_TYPE_RC5;
+		rc_type     = RC_BIT_RC5;
 		ir_codes    = RC_MAP_HAUPPAUGE;
 		break;
 	}
diff --git a/drivers/media/pci/cx18/cx18-i2c.c b/drivers/media/pci/cx18/cx18-i2c.c
index 51609d5c88ce..4908eb7bcf6c 100644
--- a/drivers/media/pci/cx18/cx18-i2c.c
+++ b/drivers/media/pci/cx18/cx18-i2c.c
@@ -98,7 +98,7 @@ static int cx18_i2c_new_ir(struct cx18 *cx, struct i2c_adapter *adap, u32 hw,
 	case CX18_HW_Z8F0811_IR_RX_HAUP:
 		init_data->ir_codes = RC_MAP_HAUPPAUGE;
 		init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP_XVR;
-		init_data->type = RC_TYPE_RC5;
+		init_data->type = RC_BIT_RC5;
 		init_data->name = cx->card_name;
 		info.platform_data = init_data;
 		break;
diff --git a/drivers/media/pci/cx23885/cx23885-input.c b/drivers/media/pci/cx23885/cx23885-input.c
index 2c925f77cf2a..2004039482df 100644
--- a/drivers/media/pci/cx23885/cx23885-input.c
+++ b/drivers/media/pci/cx23885/cx23885-input.c
@@ -270,21 +270,21 @@ int cx23885_input_init(struct cx23885_dev *dev)
 	case CX23885_BOARD_HAUPPAUGE_HVR1250:
 		/* Integrated CX2388[58] IR controller */
 		driver_type = RC_DRIVER_IR_RAW;
-		allowed_protos = RC_TYPE_ALL;
+		allowed_protos = RC_BIT_ALL;
 		/* The grey Hauppauge RC-5 remote */
 		rc_map = RC_MAP_HAUPPAUGE;
 		break;
 	case CX23885_BOARD_TERRATEC_CINERGY_T_PCIE_DUAL:
 		/* Integrated CX23885 IR controller */
 		driver_type = RC_DRIVER_IR_RAW;
-		allowed_protos = RC_TYPE_NEC;
+		allowed_protos = RC_BIT_NEC;
 		/* The grey Terratec remote with orange buttons */
 		rc_map = RC_MAP_NEC_TERRATEC_CINERGY_XS;
 		break;
 	case CX23885_BOARD_TEVII_S470:
 		/* Integrated CX23885 IR controller */
 		driver_type = RC_DRIVER_IR_RAW;
-		allowed_protos = RC_TYPE_ALL;
+		allowed_protos = RC_BIT_ALL;
 		/* A guess at the remote */
 		rc_map = RC_MAP_TEVII_NEC;
 		break;
diff --git a/drivers/media/pci/cx88/cx88-input.c b/drivers/media/pci/cx88/cx88-input.c
index ebf448c48ca3..f29e18c72f44 100644
--- a/drivers/media/pci/cx88/cx88-input.c
+++ b/drivers/media/pci/cx88/cx88-input.c
@@ -248,7 +248,7 @@ int cx88_ir_init(struct cx88_core *core, struct pci_dev *pci)
 	struct cx88_IR *ir;
 	struct rc_dev *dev;
 	char *ir_codes = NULL;
-	u64 rc_type = RC_TYPE_OTHER;
+	u64 rc_type = RC_BIT_OTHER;
 	int err = -ENOMEM;
 	u32 hardware_mask = 0;	/* For devices with a hardware mask, when
 				 * used with a full-code IR table
@@ -416,7 +416,7 @@ int cx88_ir_init(struct cx88_core *core, struct pci_dev *pci)
 		break;
 	case CX88_BOARD_TWINHAN_VP1027_DVBS:
 		ir_codes         = RC_MAP_TWINHAN_VP1027_DVBS;
-		rc_type          = RC_TYPE_NEC;
+		rc_type          = RC_BIT_NEC;
 		ir->sampling     = 0xff00; /* address */
 		break;
 	}
@@ -592,7 +592,7 @@ void cx88_i2c_init_ir(struct cx88_core *core)
 	case CX88_BOARD_LEADTEK_PVR2000:
 		addr_list = pvr2000_addr_list;
 		core->init_data.name = "cx88 Leadtek PVR 2000 remote";
-		core->init_data.type = RC_TYPE_UNKNOWN;
+		core->init_data.type = RC_BIT_UNKNOWN;
 		core->init_data.get_key = get_key_pvr2000;
 		core->init_data.ir_codes = RC_MAP_EMPTY;
 		break;
@@ -613,7 +613,7 @@ void cx88_i2c_init_ir(struct cx88_core *core)
 			/* Hauppauge XVR */
 			core->init_data.name = "cx88 Hauppauge XVR remote";
 			core->init_data.ir_codes = RC_MAP_HAUPPAUGE;
-			core->init_data.type = RC_TYPE_RC5;
+			core->init_data.type = RC_BIT_RC5;
 			core->init_data.internal_get_key_func = IR_KBD_GET_KEY_HAUP_XVR;
 
 			info.platform_data = &core->init_data;
diff --git a/drivers/media/pci/ivtv/ivtv-i2c.c b/drivers/media/pci/ivtv/ivtv-i2c.c
index d47f41a0ef66..46e262becb67 100644
--- a/drivers/media/pci/ivtv/ivtv-i2c.c
+++ b/drivers/media/pci/ivtv/ivtv-i2c.c
@@ -200,21 +200,21 @@ static int ivtv_i2c_new_ir(struct ivtv *itv, u32 hw, const char *type, u8 addr)
 		init_data->ir_codes = RC_MAP_AVERMEDIA_CARDBUS;
 		init_data->internal_get_key_func =
 					IR_KBD_GET_KEY_AVERMEDIA_CARDBUS;
-		init_data->type = RC_TYPE_OTHER;
+		init_data->type = RC_BIT_OTHER;
 		init_data->name = "AVerMedia AVerTV card";
 		break;
 	case IVTV_HW_I2C_IR_RX_HAUP_EXT:
 	case IVTV_HW_I2C_IR_RX_HAUP_INT:
 		init_data->ir_codes = RC_MAP_HAUPPAUGE;
 		init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP;
-		init_data->type = RC_TYPE_RC5;
+		init_data->type = RC_BIT_RC5;
 		init_data->name = itv->card_name;
 		break;
 	case IVTV_HW_Z8F0811_IR_RX_HAUP:
 		/* Default to grey remote */
 		init_data->ir_codes = RC_MAP_HAUPPAUGE;
 		init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP_XVR;
-		init_data->type = RC_TYPE_RC5;
+		init_data->type = RC_BIT_RC5;
 		init_data->name = itv->card_name;
 		break;
 	case IVTV_HW_I2C_IR_RX_ADAPTEC:
@@ -222,7 +222,7 @@ static int ivtv_i2c_new_ir(struct ivtv *itv, u32 hw, const char *type, u8 addr)
 		init_data->name = itv->card_name;
 		/* FIXME: The protocol and RC_MAP needs to be corrected */
 		init_data->ir_codes = RC_MAP_EMPTY;
-		init_data->type = RC_TYPE_UNKNOWN;
+		init_data->type = RC_BIT_UNKNOWN;
 		break;
 	}
 
diff --git a/drivers/media/pci/saa7134/saa7134-input.c b/drivers/media/pci/saa7134/saa7134-input.c
index 0f78f5e537e2..e761262f7475 100644
--- a/drivers/media/pci/saa7134/saa7134-input.c
+++ b/drivers/media/pci/saa7134/saa7134-input.c
@@ -990,7 +990,7 @@ void saa7134_probe_i2c_ir(struct saa7134_dev *dev)
 		dev->init_data.name = "BeholdTV";
 		dev->init_data.get_key = get_key_beholdm6xx;
 		dev->init_data.ir_codes = RC_MAP_BEHOLD;
-		dev->init_data.type = RC_TYPE_NEC;
+		dev->init_data.type = RC_BIT_NEC;
 		info.addr = 0x2d;
 		break;
 	case SAA7134_BOARD_AVERMEDIA_CARDBUS_501:
diff --git a/drivers/media/rc/ati_remote.c b/drivers/media/rc/ati_remote.c
index 49bb356ed14c..2d6fb26a0170 100644
--- a/drivers/media/rc/ati_remote.c
+++ b/drivers/media/rc/ati_remote.c
@@ -784,7 +784,7 @@ static void ati_remote_rc_init(struct ati_remote *ati_remote)
 
 	rdev->priv = ati_remote;
 	rdev->driver_type = RC_DRIVER_SCANCODE;
-	rdev->allowed_protos = RC_TYPE_OTHER;
+	rdev->allowed_protos = RC_BIT_OTHER;
 	rdev->driver_name = "ati_remote";
 
 	rdev->open = ati_remote_rc_open;
diff --git a/drivers/media/rc/ene_ir.c b/drivers/media/rc/ene_ir.c
index d05ac15b5de4..7467a6da39ff 100644
--- a/drivers/media/rc/ene_ir.c
+++ b/drivers/media/rc/ene_ir.c
@@ -1046,7 +1046,7 @@ static int ene_probe(struct pnp_dev *pnp_dev, const struct pnp_device_id *id)
 		learning_mode_force = false;
 
 	rdev->driver_type = RC_DRIVER_IR_RAW;
-	rdev->allowed_protos = RC_TYPE_ALL;
+	rdev->allowed_protos = RC_BIT_ALL;
 	rdev->priv = dev;
 	rdev->open = ene_open;
 	rdev->close = ene_close;
diff --git a/drivers/media/rc/fintek-cir.c b/drivers/media/rc/fintek-cir.c
index 52fd7696b1ba..d2d93cbe628c 100644
--- a/drivers/media/rc/fintek-cir.c
+++ b/drivers/media/rc/fintek-cir.c
@@ -541,7 +541,7 @@ static int fintek_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id
 	/* Set up the rc device */
 	rdev->priv = fintek;
 	rdev->driver_type = RC_DRIVER_IR_RAW;
-	rdev->allowed_protos = RC_TYPE_ALL;
+	rdev->allowed_protos = RC_BIT_ALL;
 	rdev->open = fintek_open;
 	rdev->close = fintek_close;
 	rdev->input_name = FINTEK_DESCRIPTION;
diff --git a/drivers/media/rc/gpio-ir-recv.c b/drivers/media/rc/gpio-ir-recv.c
index 04cb272db16a..ba1a1eb356cf 100644
--- a/drivers/media/rc/gpio-ir-recv.c
+++ b/drivers/media/rc/gpio-ir-recv.c
@@ -95,7 +95,7 @@ static int __devinit gpio_ir_recv_probe(struct platform_device *pdev)
 	if (pdata->allowed_protos)
 		rcdev->allowed_protos = pdata->allowed_protos;
 	else
-		rcdev->allowed_protos = RC_TYPE_ALL;
+		rcdev->allowed_protos = RC_BIT_ALL;
 	rcdev->map_name = pdata->map_name ?: RC_MAP_EMPTY;
 
 	gpio_dev->rcdev = rcdev;
diff --git a/drivers/media/rc/iguanair.c b/drivers/media/rc/iguanair.c
index 51d7057aca04..5a9163da63c3 100644
--- a/drivers/media/rc/iguanair.c
+++ b/drivers/media/rc/iguanair.c
@@ -499,7 +499,7 @@ static int __devinit iguanair_probe(struct usb_interface *intf,
 	usb_to_input_id(ir->udev, &rc->input_id);
 	rc->dev.parent = &intf->dev;
 	rc->driver_type = RC_DRIVER_IR_RAW;
-	rc->allowed_protos = RC_TYPE_ALL;
+	rc->allowed_protos = RC_BIT_ALL;
 	rc->priv = ir;
 	rc->open = iguanair_open;
 	rc->close = iguanair_close;
diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c
index 5dd0386604f0..8f6a28921ed4 100644
--- a/drivers/media/rc/imon.c
+++ b/drivers/media/rc/imon.c
@@ -1001,7 +1001,7 @@ static void imon_touch_display_timeout(unsigned long data)
  * it is not, so we must acquire it prior to calling send_packet, which
  * requires that the lock is held.
  */
-static int imon_ir_change_protocol(struct rc_dev *rc, u64 rc_type)
+static int imon_ir_change_protocol(struct rc_dev *rc, u64 *rc_type)
 {
 	int retval;
 	struct imon_context *ictx = rc->priv;
@@ -1010,31 +1010,27 @@ static int imon_ir_change_protocol(struct rc_dev *rc, u64 rc_type)
 	unsigned char ir_proto_packet[] = {
 		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x86 };
 
-	if (rc_type && !(rc_type & rc->allowed_protos))
+	if (*rc_type && !(*rc_type & rc->allowed_protos))
 		dev_warn(dev, "Looks like you're trying to use an IR protocol "
 			 "this device does not support\n");
 
-	switch (rc_type) {
-	case RC_TYPE_RC6:
+	if (*rc_type & RC_BIT_RC6_MCE) {
 		dev_dbg(dev, "Configuring IR receiver for MCE protocol\n");
 		ir_proto_packet[0] = 0x01;
-		break;
-	case RC_TYPE_UNKNOWN:
-	case RC_TYPE_OTHER:
+		*rc_type = RC_BIT_RC6_MCE;
+	} else if (*rc_type & RC_BIT_OTHER) {
 		dev_dbg(dev, "Configuring IR receiver for iMON protocol\n");
 		if (!pad_stabilize)
 			dev_dbg(dev, "PAD stabilize functionality disabled\n");
 		/* ir_proto_packet[0] = 0x00; // already the default */
-		rc_type = RC_TYPE_OTHER;
-		break;
-	default:
+		*rc_type = RC_BIT_OTHER;
+	} else {
 		dev_warn(dev, "Unsupported IR protocol specified, overriding "
 			 "to iMON IR protocol\n");
 		if (!pad_stabilize)
 			dev_dbg(dev, "PAD stabilize functionality disabled\n");
 		/* ir_proto_packet[0] = 0x00; // already the default */
-		rc_type = RC_TYPE_OTHER;
-		break;
+		*rc_type = RC_BIT_OTHER;
 	}
 
 	memcpy(ictx->usb_tx_buf, &ir_proto_packet, sizeof(ir_proto_packet));
@@ -1048,7 +1044,7 @@ static int imon_ir_change_protocol(struct rc_dev *rc, u64 rc_type)
 	if (retval)
 		goto out;
 
-	ictx->rc_type = rc_type;
+	ictx->rc_type = *rc_type;
 	ictx->pad_mouse = false;
 
 out:
@@ -1323,7 +1319,7 @@ static void imon_pad_to_keys(struct imon_context *ictx, unsigned char *buf)
 		rel_x = buf[2];
 		rel_y = buf[3];
 
-		if (ictx->rc_type == RC_TYPE_OTHER && pad_stabilize) {
+		if (ictx->rc_type == RC_BIT_OTHER && pad_stabilize) {
 			if ((buf[1] == 0) && ((rel_x != 0) || (rel_y != 0))) {
 				dir = stabilize((int)rel_x, (int)rel_y,
 						timeout, threshold);
@@ -1390,7 +1386,7 @@ static void imon_pad_to_keys(struct imon_context *ictx, unsigned char *buf)
 		buf[0] = 0x01;
 		buf[1] = buf[4] = buf[5] = buf[6] = buf[7] = 0;
 
-		if (ictx->rc_type == RC_TYPE_OTHER && pad_stabilize) {
+		if (ictx->rc_type == RC_BIT_OTHER && pad_stabilize) {
 			dir = stabilize((int)rel_x, (int)rel_y,
 					timeout, threshold);
 			if (!dir) {
@@ -1511,7 +1507,7 @@ static void imon_incoming_packet(struct imon_context *ictx,
 		kc = imon_panel_key_lookup(scancode);
 	} else {
 		scancode = be32_to_cpu(*((u32 *)buf));
-		if (ictx->rc_type == RC_TYPE_RC6) {
+		if (ictx->rc_type == RC_BIT_RC6_MCE) {
 			ktype = IMON_KEY_IMON;
 			if (buf[0] == 0x80)
 				ktype = IMON_KEY_MCE;
@@ -1744,7 +1740,7 @@ static void imon_get_ffdc_type(struct imon_context *ictx)
 {
 	u8 ffdc_cfg_byte = ictx->usb_rx_buf[6];
 	u8 detected_display_type = IMON_DISPLAY_TYPE_NONE;
-	u64 allowed_protos = RC_TYPE_OTHER;
+	u64 allowed_protos = RC_BIT_OTHER;
 
 	switch (ffdc_cfg_byte) {
 	/* iMON Knob, no display, iMON IR + vol knob */
@@ -1775,13 +1771,13 @@ static void imon_get_ffdc_type(struct imon_context *ictx)
 	case 0x9e:
 		dev_info(ictx->dev, "0xffdc iMON VFD, MCE IR");
 		detected_display_type = IMON_DISPLAY_TYPE_VFD;
-		allowed_protos = RC_TYPE_RC6;
+		allowed_protos = RC_BIT_RC6_MCE;
 		break;
 	/* iMON LCD, MCE IR */
 	case 0x9f:
 		dev_info(ictx->dev, "0xffdc iMON LCD, MCE IR");
 		detected_display_type = IMON_DISPLAY_TYPE_LCD;
-		allowed_protos = RC_TYPE_RC6;
+		allowed_protos = RC_BIT_RC6_MCE;
 		break;
 	default:
 		dev_info(ictx->dev, "Unknown 0xffdc device, "
@@ -1789,7 +1785,7 @@ static void imon_get_ffdc_type(struct imon_context *ictx)
 		detected_display_type = IMON_DISPLAY_TYPE_VFD;
 		/* We don't know which one it is, allow user to set the
 		 * RC6 one from userspace if OTHER wasn't correct. */
-		allowed_protos |= RC_TYPE_RC6;
+		allowed_protos |= RC_BIT_RC6_MCE;
 		break;
 	}
 
@@ -1875,7 +1871,7 @@ static struct rc_dev *imon_init_rdev(struct imon_context *ictx)
 
 	rdev->priv = ictx;
 	rdev->driver_type = RC_DRIVER_SCANCODE;
-	rdev->allowed_protos = RC_TYPE_OTHER | RC_TYPE_RC6; /* iMON PAD or MCE */
+	rdev->allowed_protos = RC_BIT_OTHER | RC_BIT_RC6_MCE; /* iMON PAD or MCE */
 	rdev->change_protocol = imon_ir_change_protocol;
 	rdev->driver_name = MOD_NAME;
 
@@ -1893,7 +1889,7 @@ static struct rc_dev *imon_init_rdev(struct imon_context *ictx)
 
 	imon_set_display_type(ictx);
 
-	if (ictx->rc_type == RC_TYPE_RC6)
+	if (ictx->rc_type == RC_BIT_RC6_MCE)
 		rdev->map_name = RC_MAP_IMON_MCE;
 	else
 		rdev->map_name = RC_MAP_IMON_PAD;
diff --git a/drivers/media/rc/ir-jvc-decoder.c b/drivers/media/rc/ir-jvc-decoder.c
index 035668e27f6b..69edffb9fe9a 100644
--- a/drivers/media/rc/ir-jvc-decoder.c
+++ b/drivers/media/rc/ir-jvc-decoder.c
@@ -47,7 +47,7 @@ static int ir_jvc_decode(struct rc_dev *dev, struct ir_raw_event ev)
 {
 	struct jvc_dec *data = &dev->raw->jvc;
 
-	if (!(dev->raw->enabled_protocols & RC_TYPE_JVC))
+	if (!(dev->raw->enabled_protocols & RC_BIT_JVC))
 		return 0;
 
 	if (!is_timing_event(ev)) {
@@ -174,7 +174,7 @@ out:
 }
 
 static struct ir_raw_handler jvc_handler = {
-	.protocols	= RC_TYPE_JVC,
+	.protocols	= RC_BIT_JVC,
 	.decode		= ir_jvc_decode,
 };
 
diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c
index 870c93052fd0..9945e5e7f61a 100644
--- a/drivers/media/rc/ir-lirc-codec.c
+++ b/drivers/media/rc/ir-lirc-codec.c
@@ -35,7 +35,7 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	struct lirc_codec *lirc = &dev->raw->lirc;
 	int sample;
 
-	if (!(dev->raw->enabled_protocols & RC_TYPE_LIRC))
+	if (!(dev->raw->enabled_protocols & RC_BIT_LIRC))
 		return 0;
 
 	if (!dev->raw->lirc.drv || !dev->raw->lirc.drv->rbuf)
@@ -408,7 +408,7 @@ static int ir_lirc_unregister(struct rc_dev *dev)
 }
 
 static struct ir_raw_handler lirc_handler = {
-	.protocols	= RC_TYPE_LIRC,
+	.protocols	= RC_BIT_LIRC,
 	.decode		= ir_lirc_decode,
 	.raw_register	= ir_lirc_register,
 	.raw_unregister	= ir_lirc_unregister,
diff --git a/drivers/media/rc/ir-mce_kbd-decoder.c b/drivers/media/rc/ir-mce_kbd-decoder.c
index 3784ebf80ec7..33fafa4cf7cb 100644
--- a/drivers/media/rc/ir-mce_kbd-decoder.c
+++ b/drivers/media/rc/ir-mce_kbd-decoder.c
@@ -216,7 +216,7 @@ static int ir_mce_kbd_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	u32 scancode;
 	unsigned long delay;
 
-	if (!(dev->raw->enabled_protocols & RC_TYPE_MCE_KBD))
+	if (!(dev->raw->enabled_protocols & RC_BIT_MCE_KBD))
 		return 0;
 
 	if (!is_timing_event(ev)) {
@@ -422,7 +422,7 @@ static int ir_mce_kbd_unregister(struct rc_dev *dev)
 }
 
 static struct ir_raw_handler mce_kbd_handler = {
-	.protocols	= RC_TYPE_MCE_KBD,
+	.protocols	= RC_BIT_MCE_KBD,
 	.decode		= ir_mce_kbd_decode,
 	.raw_register	= ir_mce_kbd_register,
 	.raw_unregister	= ir_mce_kbd_unregister,
diff --git a/drivers/media/rc/ir-nec-decoder.c b/drivers/media/rc/ir-nec-decoder.c
index 2ca509e6e16b..a47ee3634969 100644
--- a/drivers/media/rc/ir-nec-decoder.c
+++ b/drivers/media/rc/ir-nec-decoder.c
@@ -52,7 +52,7 @@ static int ir_nec_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	u8 address, not_address, command, not_command;
 	bool send_32bits = false;
 
-	if (!(dev->raw->enabled_protocols & RC_TYPE_NEC))
+	if (!(dev->raw->enabled_protocols & RC_BIT_NEC))
 		return 0;
 
 	if (!is_timing_event(ev)) {
@@ -201,7 +201,7 @@ static int ir_nec_decode(struct rc_dev *dev, struct ir_raw_event ev)
 }
 
 static struct ir_raw_handler nec_handler = {
-	.protocols	= RC_TYPE_NEC,
+	.protocols	= RC_BIT_NEC,
 	.decode		= ir_nec_decode,
 };
 
diff --git a/drivers/media/rc/ir-rc5-decoder.c b/drivers/media/rc/ir-rc5-decoder.c
index 9ab663a507a4..5b4d1ddeac4e 100644
--- a/drivers/media/rc/ir-rc5-decoder.c
+++ b/drivers/media/rc/ir-rc5-decoder.c
@@ -52,8 +52,8 @@ static int ir_rc5_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	u8 toggle;
 	u32 scancode;
 
-        if (!(dev->raw->enabled_protocols & RC_TYPE_RC5))
-                return 0;
+	if (!(dev->raw->enabled_protocols & (RC_BIT_RC5 | RC_BIT_RC5X)))
+		return 0;
 
 	if (!is_timing_event(ev)) {
 		if (ev.reset)
@@ -128,6 +128,10 @@ again:
 		if (data->wanted_bits == RC5X_NBITS) {
 			/* RC5X */
 			u8 xdata, command, system;
+			if (!(dev->raw->enabled_protocols & RC_BIT_RC5X)) {
+				data->state = STATE_INACTIVE;
+				return 0;
+			}
 			xdata    = (data->bits & 0x0003F) >> 0;
 			command  = (data->bits & 0x00FC0) >> 6;
 			system   = (data->bits & 0x1F000) >> 12;
@@ -141,6 +145,10 @@ again:
 		} else {
 			/* RC5 */
 			u8 command, system;
+			if (!(dev->raw->enabled_protocols & RC_BIT_RC5)) {
+				data->state = STATE_INACTIVE;
+				return 0;
+			}
 			command  = (data->bits & 0x0003F) >> 0;
 			system   = (data->bits & 0x007C0) >> 6;
 			toggle   = (data->bits & 0x00800) ? 1 : 0;
@@ -164,7 +172,7 @@ out:
 }
 
 static struct ir_raw_handler rc5_handler = {
-	.protocols	= RC_TYPE_RC5,
+	.protocols	= RC_BIT_RC5 | RC_BIT_RC5X,
 	.decode		= ir_rc5_decode,
 };
 
diff --git a/drivers/media/rc/ir-rc5-sz-decoder.c b/drivers/media/rc/ir-rc5-sz-decoder.c
index ec8d4a2e2c5a..fd807a8308d8 100644
--- a/drivers/media/rc/ir-rc5-sz-decoder.c
+++ b/drivers/media/rc/ir-rc5-sz-decoder.c
@@ -48,8 +48,8 @@ static int ir_rc5_sz_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	u8 toggle, command, system;
 	u32 scancode;
 
-        if (!(dev->raw->enabled_protocols & RC_TYPE_RC5_SZ))
-                return 0;
+	if (!(dev->raw->enabled_protocols & RC_BIT_RC5_SZ))
+		return 0;
 
 	if (!is_timing_event(ev)) {
 		if (ev.reset)
@@ -128,7 +128,7 @@ out:
 }
 
 static struct ir_raw_handler rc5_sz_handler = {
-	.protocols	= RC_TYPE_RC5_SZ,
+	.protocols	= RC_BIT_RC5_SZ,
 	.decode		= ir_rc5_sz_decode,
 };
 
diff --git a/drivers/media/rc/ir-rc6-decoder.c b/drivers/media/rc/ir-rc6-decoder.c
index 4cfdd7fa4bbd..e19072ffb36c 100644
--- a/drivers/media/rc/ir-rc6-decoder.c
+++ b/drivers/media/rc/ir-rc6-decoder.c
@@ -89,7 +89,9 @@ static int ir_rc6_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	u32 scancode;
 	u8 toggle;
 
-	if (!(dev->raw->enabled_protocols & RC_TYPE_RC6))
+	if (!(dev->raw->enabled_protocols &
+	      (RC_BIT_RC6_0 | RC_BIT_RC6_6A_20 | RC_BIT_RC6_6A_24 |
+	       RC_BIT_RC6_6A_32 | RC_BIT_RC6_MCE)))
 		return 0;
 
 	if (!is_timing_event(ev)) {
@@ -271,7 +273,9 @@ out:
 }
 
 static struct ir_raw_handler rc6_handler = {
-	.protocols	= RC_TYPE_RC6,
+	.protocols	= RC_BIT_RC6_0 | RC_BIT_RC6_6A_20 |
+			  RC_BIT_RC6_6A_24 | RC_BIT_RC6_6A_32 |
+			  RC_BIT_RC6_MCE,
 	.decode		= ir_rc6_decode,
 };
 
diff --git a/drivers/media/rc/ir-sanyo-decoder.c b/drivers/media/rc/ir-sanyo-decoder.c
index 7e54ec57bcf9..7e69a3b65370 100644
--- a/drivers/media/rc/ir-sanyo-decoder.c
+++ b/drivers/media/rc/ir-sanyo-decoder.c
@@ -58,7 +58,7 @@ static int ir_sanyo_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	u32 scancode;
 	u8 address, command, not_command;
 
-	if (!(dev->raw->enabled_protocols & RC_TYPE_SANYO))
+	if (!(dev->raw->enabled_protocols & RC_BIT_SANYO))
 		return 0;
 
 	if (!is_timing_event(ev)) {
@@ -179,7 +179,7 @@ static int ir_sanyo_decode(struct rc_dev *dev, struct ir_raw_event ev)
 }
 
 static struct ir_raw_handler sanyo_handler = {
-	.protocols	= RC_TYPE_SANYO,
+	.protocols	= RC_BIT_SANYO,
 	.decode		= ir_sanyo_decode,
 };
 
diff --git a/drivers/media/rc/ir-sony-decoder.c b/drivers/media/rc/ir-sony-decoder.c
index dab98b37621a..fb914342cf4d 100644
--- a/drivers/media/rc/ir-sony-decoder.c
+++ b/drivers/media/rc/ir-sony-decoder.c
@@ -45,7 +45,8 @@ static int ir_sony_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	u32 scancode;
 	u8 device, subdevice, function;
 
-	if (!(dev->raw->enabled_protocols & RC_TYPE_SONY))
+	if (!(dev->raw->enabled_protocols &
+	      (RC_BIT_SONY12 | RC_BIT_SONY15 | RC_BIT_SONY20)))
 		return 0;
 
 	if (!is_timing_event(ev)) {
@@ -123,16 +124,28 @@ static int ir_sony_decode(struct rc_dev *dev, struct ir_raw_event ev)
 
 		switch (data->count) {
 		case 12:
+			if (!(dev->raw->enabled_protocols & RC_BIT_SONY12)) {
+				data->state = STATE_INACTIVE;
+				return 0;
+			}
 			device    = bitrev8((data->bits <<  3) & 0xF8);
 			subdevice = 0;
 			function  = bitrev8((data->bits >>  4) & 0xFE);
 			break;
 		case 15:
+			if (!(dev->raw->enabled_protocols & RC_BIT_SONY15)) {
+				data->state = STATE_INACTIVE;
+				return 0;
+			}
 			device    = bitrev8((data->bits >>  0) & 0xFF);
 			subdevice = 0;
 			function  = bitrev8((data->bits >>  7) & 0xFE);
 			break;
 		case 20:
+			if (!(dev->raw->enabled_protocols & RC_BIT_SONY20)) {
+				data->state = STATE_INACTIVE;
+				return 0;
+			}
 			device    = bitrev8((data->bits >>  5) & 0xF8);
 			subdevice = bitrev8((data->bits >>  0) & 0xFF);
 			function  = bitrev8((data->bits >> 12) & 0xFE);
@@ -157,7 +170,7 @@ out:
 }
 
 static struct ir_raw_handler sony_handler = {
-	.protocols	= RC_TYPE_SONY,
+	.protocols	= RC_BIT_SONY12 | RC_BIT_SONY15 | RC_BIT_SONY20,
 	.decode		= ir_sony_decode,
 };
 
diff --git a/drivers/media/rc/ite-cir.c b/drivers/media/rc/ite-cir.c
index 24c77a42fc36..d63511511df4 100644
--- a/drivers/media/rc/ite-cir.c
+++ b/drivers/media/rc/ite-cir.c
@@ -1563,7 +1563,7 @@ static int ite_probe(struct pnp_dev *pdev, const struct pnp_device_id
 	/* set up ir-core props */
 	rdev->priv = itdev;
 	rdev->driver_type = RC_DRIVER_IR_RAW;
-	rdev->allowed_protos = RC_TYPE_ALL;
+	rdev->allowed_protos = RC_BIT_ALL;
 	rdev->open = ite_open;
 	rdev->close = ite_close;
 	rdev->s_idle = ite_s_idle;
diff --git a/drivers/media/rc/keymaps/rc-imon-mce.c b/drivers/media/rc/keymaps/rc-imon-mce.c
index 124c7228ba8c..f0da960560b0 100644
--- a/drivers/media/rc/keymaps/rc-imon-mce.c
+++ b/drivers/media/rc/keymaps/rc-imon-mce.c
@@ -121,7 +121,7 @@ static struct rc_map_list imon_mce_map = {
 		.scan    = imon_mce,
 		.size    = ARRAY_SIZE(imon_mce),
 		/* its RC6, but w/a hardware decoder */
-		.rc_type = RC_TYPE_RC6,
+		.rc_type = RC_TYPE_RC6_MCE,
 		.name    = RC_MAP_IMON_MCE,
 	}
 };
diff --git a/drivers/media/rc/keymaps/rc-rc6-mce.c b/drivers/media/rc/keymaps/rc-rc6-mce.c
index 753e43ec787b..ef4006fe4de0 100644
--- a/drivers/media/rc/keymaps/rc-rc6-mce.c
+++ b/drivers/media/rc/keymaps/rc-rc6-mce.c
@@ -97,7 +97,7 @@ static struct rc_map_list rc6_mce_map = {
 	.map = {
 		.scan    = rc6_mce,
 		.size    = ARRAY_SIZE(rc6_mce),
-		.rc_type = RC_TYPE_RC6,
+		.rc_type = RC_TYPE_RC6_MCE,
 		.name    = RC_MAP_RC6_MCE,
 	}
 };
diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c
index 850547fe711c..b2146cd99fd8 100644
--- a/drivers/media/rc/mceusb.c
+++ b/drivers/media/rc/mceusb.c
@@ -1205,7 +1205,7 @@ static struct rc_dev *mceusb_init_rc_dev(struct mceusb_dev *ir)
 	rc->dev.parent = dev;
 	rc->priv = ir;
 	rc->driver_type = RC_DRIVER_IR_RAW;
-	rc->allowed_protos = RC_TYPE_ALL;
+	rc->allowed_protos = RC_BIT_ALL;
 	rc->timeout = MS_TO_NS(100);
 	if (!ir->flags.no_tx) {
 		rc->s_tx_mask = mceusb_set_tx_mask;
diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c
index 2ea913a44ae8..0190dfc2ad41 100644
--- a/drivers/media/rc/nuvoton-cir.c
+++ b/drivers/media/rc/nuvoton-cir.c
@@ -1045,7 +1045,7 @@ static int nvt_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id)
 	/* Set up the rc device */
 	rdev->priv = nvt;
 	rdev->driver_type = RC_DRIVER_IR_RAW;
-	rdev->allowed_protos = RC_TYPE_ALL;
+	rdev->allowed_protos = RC_BIT_ALL;
 	rdev->open = nvt_open;
 	rdev->close = nvt_close;
 	rdev->tx_ir = nvt_tx_ir;
diff --git a/drivers/media/rc/rc-loopback.c b/drivers/media/rc/rc-loopback.c
index f9be68132c67..53d02827a472 100644
--- a/drivers/media/rc/rc-loopback.c
+++ b/drivers/media/rc/rc-loopback.c
@@ -195,7 +195,7 @@ static int __init loop_init(void)
 	rc->map_name		= RC_MAP_EMPTY;
 	rc->priv		= &loopdev;
 	rc->driver_type		= RC_DRIVER_IR_RAW;
-	rc->allowed_protos	= RC_TYPE_ALL;
+	rc->allowed_protos	= RC_BIT_ALL;
 	rc->timeout		= 100 * 1000 * 1000; /* 100 ms */
 	rc->min_timeout		= 1;
 	rc->max_timeout		= UINT_MAX;
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index cabc19c10515..601d1ac1c688 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -725,25 +725,36 @@ static struct class ir_input_class = {
 	.devnode	= ir_devnode,
 };
 
+/*
+ * These are the protocol textual descriptions that are
+ * used by the sysfs protocols file. Note that the order
+ * of the entries is relevant.
+ */
 static struct {
 	u64	type;
 	char	*name;
 } proto_names[] = {
-	{ RC_TYPE_UNKNOWN,	"unknown"	},
-	{ RC_TYPE_RC5,		"rc-5"		},
-	{ RC_TYPE_NEC,		"nec"		},
-	{ RC_TYPE_RC6,		"rc-6"		},
-	{ RC_TYPE_JVC,		"jvc"		},
-	{ RC_TYPE_SONY,		"sony"		},
-	{ RC_TYPE_RC5_SZ,	"rc-5-sz"	},
-	{ RC_TYPE_SANYO,	"sanyo"		},
-	{ RC_TYPE_MCE_KBD,	"mce_kbd"	},
-	{ RC_TYPE_LIRC,		"lirc"		},
-	{ RC_TYPE_OTHER,	"other"		},
+	{ RC_BIT_NONE,		"none"		},
+	{ RC_BIT_OTHER,		"other"		},
+	{ RC_BIT_UNKNOWN,	"unknown"	},
+	{ RC_BIT_RC5 |
+	  RC_BIT_RC5X,		"rc-5"		},
+	{ RC_BIT_NEC,		"nec"		},
+	{ RC_BIT_RC6_0 |
+	  RC_BIT_RC6_6A_20 |
+	  RC_BIT_RC6_6A_24 |
+	  RC_BIT_RC6_6A_32 |
+	  RC_BIT_RC6_MCE,	"rc-6"		},
+	{ RC_BIT_JVC,		"jvc"		},
+	{ RC_BIT_SONY12 |
+	  RC_BIT_SONY15 |
+	  RC_BIT_SONY20,	"sony"		},
+	{ RC_BIT_RC5_SZ,	"rc-5-sz"	},
+	{ RC_BIT_SANYO,		"sanyo"		},
+	{ RC_BIT_MCE_KBD,	"mce_kbd"	},
+	{ RC_BIT_LIRC,		"lirc"		},
 };
 
-#define PROTO_NONE	"none"
-
 /**
  * show_protocols() - shows the current IR protocol(s)
  * @device:	the device descriptor
@@ -790,6 +801,9 @@ static ssize_t show_protocols(struct device *device,
 			tmp += sprintf(tmp, "[%s] ", proto_names[i].name);
 		else if (allowed & proto_names[i].type)
 			tmp += sprintf(tmp, "%s ", proto_names[i].name);
+
+		if (allowed & proto_names[i].type)
+			allowed &= ~proto_names[i].type;
 	}
 
 	if (tmp != buf)
@@ -867,26 +881,20 @@ static ssize_t store_protocols(struct device *device,
 			disable = false;
 		}
 
-		if (!enable && !disable && !strncasecmp(tmp, PROTO_NONE, sizeof(PROTO_NONE))) {
-			tmp += sizeof(PROTO_NONE);
-			mask = 0;
-			count++;
-		} else {
-			for (i = 0; i < ARRAY_SIZE(proto_names); i++) {
-				if (!strcasecmp(tmp, proto_names[i].name)) {
-					tmp += strlen(proto_names[i].name);
-					mask = proto_names[i].type;
-					break;
-				}
-			}
-			if (i == ARRAY_SIZE(proto_names)) {
-				IR_dprintk(1, "Unknown protocol: '%s'\n", tmp);
-				ret = -EINVAL;
-				goto out;
+		for (i = 0; i < ARRAY_SIZE(proto_names); i++) {
+			if (!strcasecmp(tmp, proto_names[i].name)) {
+				mask = proto_names[i].type;
+				break;
 			}
-			count++;
 		}
 
+		if (i == ARRAY_SIZE(proto_names)) {
+			IR_dprintk(1, "Unknown protocol: '%s'\n", tmp);
+			return -EINVAL;
+		}
+
+		count++;
+
 		if (enable)
 			type |= mask;
 		else if (disable)
@@ -902,7 +910,7 @@ static ssize_t store_protocols(struct device *device,
 	}
 
 	if (dev->change_protocol) {
-		rc = dev->change_protocol(dev, type);
+		rc = dev->change_protocol(dev, &type);
 		if (rc < 0) {
 			IR_dprintk(1, "Error setting protocols to 0x%llx\n",
 				   (long long)type);
@@ -1117,7 +1125,8 @@ int rc_register_device(struct rc_dev *dev)
 	}
 
 	if (dev->change_protocol) {
-		rc = dev->change_protocol(dev, rc_map->rc_type);
+		u64 rc_type = (1 << rc_map->rc_type);
+		rc = dev->change_protocol(dev, &rc_type);
 		if (rc < 0)
 			goto out_raw;
 	}
diff --git a/drivers/media/rc/redrat3.c b/drivers/media/rc/redrat3.c
index 9f5a17bb5ef5..a8887aba9faf 100644
--- a/drivers/media/rc/redrat3.c
+++ b/drivers/media/rc/redrat3.c
@@ -1082,7 +1082,7 @@ static struct rc_dev *redrat3_init_rc_dev(struct redrat3_dev *rr3)
 	rc->dev.parent = dev;
 	rc->priv = rr3;
 	rc->driver_type = RC_DRIVER_IR_RAW;
-	rc->allowed_protos = RC_TYPE_ALL;
+	rc->allowed_protos = RC_BIT_ALL;
 	rc->timeout = US_TO_NS(2750);
 	rc->tx_ir = redrat3_transmit_ir;
 	rc->s_tx_carrier = redrat3_set_tx_carrier;
diff --git a/drivers/media/rc/streamzap.c b/drivers/media/rc/streamzap.c
index d6f4bfe09391..c720f12f661e 100644
--- a/drivers/media/rc/streamzap.c
+++ b/drivers/media/rc/streamzap.c
@@ -322,7 +322,7 @@ static struct rc_dev *streamzap_init_rc_dev(struct streamzap_ir *sz)
 	rdev->dev.parent = dev;
 	rdev->priv = sz;
 	rdev->driver_type = RC_DRIVER_IR_RAW;
-	rdev->allowed_protos = RC_TYPE_ALL;
+	rdev->allowed_protos = RC_BIT_ALL;
 	rdev->driver_name = DRIVER_NAME;
 	rdev->map_name = RC_MAP_STREAMZAP;
 
diff --git a/drivers/media/rc/ttusbir.c b/drivers/media/rc/ttusbir.c
index fef05235234a..f0921b5483eb 100644
--- a/drivers/media/rc/ttusbir.c
+++ b/drivers/media/rc/ttusbir.c
@@ -316,7 +316,7 @@ static int __devinit ttusbir_probe(struct usb_interface *intf,
 	usb_to_input_id(tt->udev, &rc->input_id);
 	rc->dev.parent = &intf->dev;
 	rc->driver_type = RC_DRIVER_IR_RAW;
-	rc->allowed_protos = RC_TYPE_ALL;
+	rc->allowed_protos = RC_BIT_ALL;
 	rc->priv = tt;
 	rc->driver_name = DRIVER_NAME;
 	rc->map_name = RC_MAP_TT_1500;
diff --git a/drivers/media/rc/winbond-cir.c b/drivers/media/rc/winbond-cir.c
index 7c9b5f33113b..569d8863f439 100644
--- a/drivers/media/rc/winbond-cir.c
+++ b/drivers/media/rc/winbond-cir.c
@@ -1022,7 +1022,7 @@ wbcir_probe(struct pnp_dev *device, const struct pnp_device_id *dev_id)
 	data->dev->priv = data;
 	data->dev->dev.parent = &device->dev;
 	data->dev->timeout = MS_TO_NS(100);
-	data->dev->allowed_protos = RC_TYPE_ALL;
+	data->dev->allowed_protos = RC_BIT_ALL;
 
 	if (!request_region(data->wbase, WAKEUP_IOMEM_LEN, DRVNAME)) {
 		dev_err(dev, "Region 0x%lx-0x%lx already in use!\n",
diff --git a/drivers/media/usb/cx231xx/cx231xx-input.c b/drivers/media/usb/cx231xx/cx231xx-input.c
index 96176e9db5a2..0f7b42446826 100644
--- a/drivers/media/usb/cx231xx/cx231xx-input.c
+++ b/drivers/media/usb/cx231xx/cx231xx-input.c
@@ -99,7 +99,7 @@ int cx231xx_ir_init(struct cx231xx *dev)
 	/* The i2c micro-controller only outputs the cmd part of NEC protocol */
 	dev->init_data.rc_dev->scanmask = 0xff;
 	dev->init_data.rc_dev->driver_name = "cx231xx";
-	dev->init_data.type = RC_TYPE_NEC;
+	dev->init_data.type = RC_BIT_NEC;
 	info.addr = 0x30;
 
 	/* Load and bind ir-kbd-i2c */
diff --git a/drivers/media/usb/dvb-usb-v2/af9015.c b/drivers/media/usb/dvb-usb-v2/af9015.c
index 3d7526e28d42..943d93423705 100644
--- a/drivers/media/usb/dvb-usb-v2/af9015.c
+++ b/drivers/media/usb/dvb-usb-v2/af9015.c
@@ -1306,7 +1306,7 @@ static int af9015_get_rc_config(struct dvb_usb_device *d, struct dvb_usb_rc *rc)
 	if (!rc->map_name)
 		rc->map_name = RC_MAP_EMPTY;
 
-	rc->allowed_protos = RC_TYPE_NEC;
+	rc->allowed_protos = RC_BIT_NEC;
 	rc->query = af9015_rc_query;
 	rc->interval = 500;
 
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index ea27eaff4e34..61ae7f9d0b27 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -1023,10 +1023,10 @@ static int af9035_get_rc_config(struct dvb_usb_device *d, struct dvb_usb_rc *rc)
 		switch (tmp) {
 		case 0: /* NEC */
 		default:
-			rc->allowed_protos = RC_TYPE_NEC;
+			rc->allowed_protos = RC_BIT_NEC;
 			break;
 		case 1: /* RC6 */
-			rc->allowed_protos = RC_TYPE_RC6;
+			rc->allowed_protos = RC_BIT_RC6_MCE;
 			break;
 		}
 
diff --git a/drivers/media/usb/dvb-usb-v2/anysee.c b/drivers/media/usb/dvb-usb-v2/anysee.c
index ec540140c810..e78ca8fc7f85 100644
--- a/drivers/media/usb/dvb-usb-v2/anysee.c
+++ b/drivers/media/usb/dvb-usb-v2/anysee.c
@@ -1048,7 +1048,7 @@ static int anysee_rc_query(struct dvb_usb_device *d)
 
 static int anysee_get_rc_config(struct dvb_usb_device *d, struct dvb_usb_rc *rc)
 {
-	rc->allowed_protos = RC_TYPE_NEC;
+	rc->allowed_protos = RC_BIT_NEC;
 	rc->query          = anysee_rc_query;
 	rc->interval       = 250;  /* windows driver uses 500ms */
 
diff --git a/drivers/media/usb/dvb-usb-v2/az6007.c b/drivers/media/usb/dvb-usb-v2/az6007.c
index 54f1221d930d..d75dbf27e99e 100644
--- a/drivers/media/usb/dvb-usb-v2/az6007.c
+++ b/drivers/media/usb/dvb-usb-v2/az6007.c
@@ -826,7 +826,7 @@ static int az6007_get_rc_config(struct dvb_usb_device *d, struct dvb_usb_rc *rc)
 {
 	pr_debug("Getting az6007 Remote Control properties\n");
 
-	rc->allowed_protos = RC_TYPE_NEC;
+	rc->allowed_protos = RC_BIT_NEC;
 	rc->query          = az6007_rc_query;
 	rc->interval       = 400;
 
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb.h b/drivers/media/usb/dvb-usb-v2/dvb_usb.h
index bae16a1189d6..059291b892b8 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb.h
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb.h
@@ -137,7 +137,7 @@ struct dvb_usb_driver_info {
 struct dvb_usb_rc {
 	const char *map_name;
 	u64 allowed_protos;
-	int (*change_protocol)(struct rc_dev *dev, u64 rc_type);
+	int (*change_protocol)(struct rc_dev *dev, u64 *rc_type);
 	int (*query) (struct dvb_usb_device *d);
 	unsigned int interval;
 	const enum rc_driver_type driver_type;
diff --git a/drivers/media/usb/dvb-usb-v2/it913x.c b/drivers/media/usb/dvb-usb-v2/it913x.c
index 695f9106bc54..0b1ddc24c47c 100644
--- a/drivers/media/usb/dvb-usb-v2/it913x.c
+++ b/drivers/media/usb/dvb-usb-v2/it913x.c
@@ -698,7 +698,7 @@ static int it913x_get_rc_config(struct dvb_usb_device *d, struct dvb_usb_rc *rc)
 		return 0;
 	}
 
-	rc->allowed_protos = RC_TYPE_NEC;
+	rc->allowed_protos = RC_BIT_NEC;
 	rc->query = it913x_rc_query;
 	rc->interval = 250;
 
diff --git a/drivers/media/usb/dvb-usb-v2/lmedm04.c b/drivers/media/usb/dvb-usb-v2/lmedm04.c
index c41d9d9ec7b5..6a2445b48321 100644
--- a/drivers/media/usb/dvb-usb-v2/lmedm04.c
+++ b/drivers/media/usb/dvb-usb-v2/lmedm04.c
@@ -1253,7 +1253,7 @@ static int lme2510_get_stream_config(struct dvb_frontend *fe, u8 *ts_type,
 static int lme2510_get_rc_config(struct dvb_usb_device *d,
 	struct dvb_usb_rc *rc)
 {
-	rc->allowed_protos = RC_TYPE_NEC;
+	rc->allowed_protos = RC_BIT_NEC;
 	return 0;
 }
 
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index adabba8d28bc..ec9108e2a297 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -1197,7 +1197,7 @@ static int rtl2831u_get_rc_config(struct dvb_usb_device *d,
 		struct dvb_usb_rc *rc)
 {
 	rc->map_name = RC_MAP_EMPTY;
-	rc->allowed_protos = RC_TYPE_NEC;
+	rc->allowed_protos = RC_BIT_NEC;
 	rc->query = rtl2831u_rc_query;
 	rc->interval = 400;
 
@@ -1269,7 +1269,7 @@ static int rtl2832u_get_rc_config(struct dvb_usb_device *d,
 		struct dvb_usb_rc *rc)
 {
 	rc->map_name = RC_MAP_EMPTY;
-	rc->allowed_protos = RC_TYPE_NEC;
+	rc->allowed_protos = RC_BIT_NEC;
 	rc->query = rtl2832u_rc_query;
 	rc->interval = 400;
 
diff --git a/drivers/media/usb/dvb-usb/dib0700.h b/drivers/media/usb/dvb-usb/dib0700.h
index 7de125c0b36f..637b6123f391 100644
--- a/drivers/media/usb/dvb-usb/dib0700.h
+++ b/drivers/media/usb/dvb-usb/dib0700.h
@@ -64,7 +64,7 @@ extern int dib0700_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff);
 extern struct i2c_algorithm dib0700_i2c_algo;
 extern int dib0700_identify_state(struct usb_device *udev, struct dvb_usb_device_properties *props,
 			struct dvb_usb_device_description **desc, int *cold);
-extern int dib0700_change_protocol(struct rc_dev *dev, u64 rc_type);
+extern int dib0700_change_protocol(struct rc_dev *dev, u64 *rc_type);
 extern int dib0700_set_i2c_speed(struct dvb_usb_device *d, u16 scl_kHz);
 
 extern int dib0700_device_count;
diff --git a/drivers/media/usb/dvb-usb/dib0700_core.c b/drivers/media/usb/dvb-usb/dib0700_core.c
index ef87229de6af..19b5ed2825d7 100644
--- a/drivers/media/usb/dvb-usb/dib0700_core.c
+++ b/drivers/media/usb/dvb-usb/dib0700_core.c
@@ -605,7 +605,7 @@ int dib0700_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
 	return ret;
 }
 
-int dib0700_change_protocol(struct rc_dev *rc, u64 rc_type)
+int dib0700_change_protocol(struct rc_dev *rc, u64 *rc_type)
 {
 	struct dvb_usb_device *d = rc->priv;
 	struct dib0700_state *st = d->priv;
@@ -621,17 +621,19 @@ int dib0700_change_protocol(struct rc_dev *rc, u64 rc_type)
 	st->buf[2] = 0;
 
 	/* Set the IR mode */
-	if (rc_type == RC_TYPE_RC5)
+	if (*rc_type & RC_BIT_RC5) {
 		new_proto = 1;
-	else if (rc_type == RC_TYPE_NEC)
+		*rc_type = RC_BIT_RC5;
+	} else if (*rc_type & RC_BIT_NEC) {
 		new_proto = 0;
-	else if (rc_type == RC_TYPE_RC6) {
+		*rc_type = RC_BIT_NEC;
+	} else if (*rc_type & RC_BIT_RC6_MCE) {
 		if (st->fw_version < 0x10200) {
 			ret = -EINVAL;
 			goto out;
 		}
-
 		new_proto = 2;
+		*rc_type = RC_BIT_RC6_MCE;
 	} else {
 		ret = -EINVAL;
 		goto out;
@@ -645,7 +647,7 @@ int dib0700_change_protocol(struct rc_dev *rc, u64 rc_type)
 		goto out;
 	}
 
-	d->props.rc.core.protocol = rc_type;
+	d->props.rc.core.protocol = *rc_type;
 
 out:
 	mutex_unlock(&d->usb_mutex);
@@ -707,7 +709,7 @@ static void dib0700_rc_urb_completion(struct urb *purb)
 		 purb->actual_length);
 
 	switch (d->props.rc.core.protocol) {
-	case RC_TYPE_NEC:
+	case RC_BIT_NEC:
 		toggle = 0;
 
 		/* NEC protocol sends repeat code as 0 0 0 FF */
diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c
index 510001da6e83..11798426fa88 100644
--- a/drivers/media/usb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/usb/dvb-usb/dib0700_devices.c
@@ -518,7 +518,7 @@ static int dib0700_rc_query_old_firmware(struct dvb_usb_device *d)
 
 	d->last_event = 0;
 	switch (d->props.rc.core.protocol) {
-	case RC_TYPE_NEC:
+	case RC_BIT_NEC:
 		/* NEC protocol sends repeat code as 0 0 0 FF */
 		if ((key[3-2] == 0x00) && (key[3-3] == 0x00) &&
 		    (key[3] == 0xff))
@@ -3658,9 +3658,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_interval      = DEFAULT_RC_INTERVAL,
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -3698,9 +3698,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_interval      = DEFAULT_RC_INTERVAL,
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -3763,9 +3763,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_interval      = DEFAULT_RC_INTERVAL,
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -3808,9 +3808,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -3890,9 +3890,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -3936,9 +3936,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -3987,9 +3987,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4055,9 +4055,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4106,9 +4106,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_NEC_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4177,9 +4177,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4215,9 +4215,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4295,9 +4295,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4341,9 +4341,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_NEC_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4394,9 +4394,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4433,9 +4433,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4472,9 +4472,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4511,9 +4511,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4550,9 +4550,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4589,9 +4589,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4644,9 +4644,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4681,9 +4681,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4721,9 +4721,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4761,9 +4761,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
@@ -4802,9 +4802,9 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
 			.module_name	  = "dib0700",
 			.rc_query         = dib0700_rc_query_old_firmware,
-			.allowed_protos   = RC_TYPE_RC5 |
-					    RC_TYPE_RC6 |
-					    RC_TYPE_NEC,
+			.allowed_protos   = RC_BIT_RC5 |
+					    RC_BIT_RC6_MCE |
+					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
 	},
diff --git a/drivers/media/usb/dvb-usb/dvb-usb.h b/drivers/media/usb/dvb-usb/dvb-usb.h
index aab0f99bc892..ce4c4e3b58bb 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb.h
+++ b/drivers/media/usb/dvb-usb/dvb-usb.h
@@ -202,7 +202,7 @@ struct dvb_rc {
 	u64 protocol;
 	u64 allowed_protos;
 	enum rc_driver_type driver_type;
-	int (*change_protocol)(struct rc_dev *dev, u64 rc_type);
+	int (*change_protocol)(struct rc_dev *dev, u64 *rc_type);
 	char *module_name;
 	int (*rc_query) (struct dvb_usb_device *d);
 	int rc_interval;
diff --git a/drivers/media/usb/dvb-usb/pctv452e.c b/drivers/media/usb/dvb-usb/pctv452e.c
index 02e878577c3d..d1ddfa13de86 100644
--- a/drivers/media/usb/dvb-usb/pctv452e.c
+++ b/drivers/media/usb/dvb-usb/pctv452e.c
@@ -927,7 +927,7 @@ static struct dvb_usb_device_properties pctv452e_properties = {
 
 	.rc.core = {
 		.rc_codes	= RC_MAP_DIB0700_RC5_TABLE,
-		.allowed_protos	= RC_TYPE_UNKNOWN,
+		.allowed_protos	= RC_BIT_UNKNOWN,
 		.rc_query	= pctv452e_rc_query,
 		.rc_interval	= 100,
 	},
@@ -980,7 +980,7 @@ static struct dvb_usb_device_properties tt_connect_s2_3600_properties = {
 
 	.rc.core = {
 		.rc_codes	= RC_MAP_TT_1500,
-		.allowed_protos	= RC_TYPE_UNKNOWN,
+		.allowed_protos	= RC_BIT_UNKNOWN,
 		.rc_query	= pctv452e_rc_query,
 		.rc_interval	= 100,
 	},
diff --git a/drivers/media/usb/dvb-usb/technisat-usb2.c b/drivers/media/usb/dvb-usb/technisat-usb2.c
index 7a8c8c18590f..40832a1aef6c 100644
--- a/drivers/media/usb/dvb-usb/technisat-usb2.c
+++ b/drivers/media/usb/dvb-usb/technisat-usb2.c
@@ -732,7 +732,7 @@ static struct dvb_usb_device_properties technisat_usb2_devices = {
 		.rc_codes    = RC_MAP_TECHNISAT_USB2,
 		.module_name = "technisat-usb2",
 		.rc_query    = technisat_usb2_rc_query,
-		.allowed_protos = RC_TYPE_ALL,
+		.allowed_protos = RC_BIT_ALL,
 		.driver_type    = RC_DRIVER_IR_RAW,
 	}
 };
diff --git a/drivers/media/usb/dvb-usb/ttusb2.c b/drivers/media/usb/dvb-usb/ttusb2.c
index 6a50cdea3bce..bcdac225ebe1 100644
--- a/drivers/media/usb/dvb-usb/ttusb2.c
+++ b/drivers/media/usb/dvb-usb/ttusb2.c
@@ -741,7 +741,7 @@ static struct dvb_usb_device_properties ttusb2_properties_ct3650 = {
 		.rc_interval      = 150, /* Less than IR_KEYPRESS_TIMEOUT */
 		.rc_codes         = RC_MAP_TT_1500,
 		.rc_query         = tt3650_rc_query,
-		.allowed_protos   = RC_TYPE_UNKNOWN,
+		.allowed_protos   = RC_BIT_UNKNOWN,
 	},
 
 	.num_adapters = 1,
diff --git a/drivers/media/usb/em28xx/em28xx-input.c b/drivers/media/usb/em28xx/em28xx-input.c
index 97d36b4f19db..660bf803c9e4 100644
--- a/drivers/media/usb/em28xx/em28xx-input.c
+++ b/drivers/media/usb/em28xx/em28xx-input.c
@@ -345,7 +345,7 @@ static void em28xx_ir_stop(struct rc_dev *rc)
 	cancel_delayed_work_sync(&ir->work);
 }
 
-static int em28xx_ir_change_protocol(struct rc_dev *rc_dev, u64 rc_type)
+static int em28xx_ir_change_protocol(struct rc_dev *rc_dev, u64 *rc_type)
 {
 	int rc = 0;
 	struct em28xx_IR *ir = rc_dev->priv;
@@ -354,14 +354,16 @@ static int em28xx_ir_change_protocol(struct rc_dev *rc_dev, u64 rc_type)
 
 	/* Adjust xclk based o IR table for RC5/NEC tables */
 
-	if (rc_type == RC_TYPE_RC5) {
+	if (*rc_type & RC_BIT_RC5) {
 		dev->board.xclk |= EM28XX_XCLK_IR_RC5_MODE;
 		ir->full_code = 1;
-	} else if (rc_type == RC_TYPE_NEC) {
+		*rc_type = RC_BIT_RC5;
+	} else if (*rc_type & RC_BIT_NEC) {
 		dev->board.xclk &= ~EM28XX_XCLK_IR_RC5_MODE;
 		ir_config = EM2874_IR_NEC;
 		ir->full_code = 1;
-	} else if (rc_type != RC_TYPE_UNKNOWN)
+		*rc_type = RC_BIT_NEC;
+	} else if (*rc_type != RC_BIT_UNKNOWN)
 		rc = -EINVAL;
 
 	em28xx_write_reg_bits(dev, EM28XX_R0F_XCLK, dev->board.xclk,
@@ -524,6 +526,7 @@ static int em28xx_ir_init(struct em28xx *dev)
 	struct em28xx_IR *ir;
 	struct rc_dev *rc;
 	int err = -ENOMEM;
+	u64 rc_type;
 
 	if (dev->board.ir_codes == NULL) {
 		/* No remote control support */
@@ -546,14 +549,15 @@ static int em28xx_ir_init(struct em28xx *dev)
 	 * em2874 supports more protocols. For now, let's just announce
 	 * the two protocols that were already tested
 	 */
-	rc->allowed_protos = RC_TYPE_RC5 | RC_TYPE_NEC;
+	rc->allowed_protos = RC_BIT_RC5 | RC_BIT_NEC;
 	rc->priv = ir;
 	rc->change_protocol = em28xx_ir_change_protocol;
 	rc->open = em28xx_ir_start;
 	rc->close = em28xx_ir_stop;
 
 	/* By default, keep protocol field untouched */
-	err = em28xx_ir_change_protocol(rc, RC_TYPE_UNKNOWN);
+	rc_type = RC_BIT_UNKNOWN;
+	err = em28xx_ir_change_protocol(rc, &rc_type);
 	if (err)
 		goto err_out_free;
 
diff --git a/drivers/media/usb/hdpvr/hdpvr-i2c.c b/drivers/media/usb/hdpvr/hdpvr-i2c.c
index 82e819fa91c0..031cf024304c 100644
--- a/drivers/media/usb/hdpvr/hdpvr-i2c.c
+++ b/drivers/media/usb/hdpvr/hdpvr-i2c.c
@@ -55,7 +55,7 @@ struct i2c_client *hdpvr_register_ir_rx_i2c(struct hdpvr_device *dev)
 	/* Our default information for ir-kbd-i2c.c to use */
 	init_data->ir_codes = RC_MAP_HAUPPAUGE;
 	init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP_XVR;
-	init_data->type = RC_TYPE_RC5;
+	init_data->type = RC_BIT_RC5;
 	init_data->name = "HD-PVR";
 	init_data->polling_interval = 405; /* ms, duplicated from Windows */
 	hdpvr_ir_rx_i2c_board_info.platform_data = init_data;
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c b/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
index 885ce11f222d..9ab596c78a4e 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
@@ -581,7 +581,7 @@ static void pvr2_i2c_register_ir(struct pvr2_hdw *hdw)
 	case PVR2_IR_SCHEME_29XXX: /* Original 29xxx device */
 		init_data->ir_codes              = RC_MAP_HAUPPAUGE;
 		init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP;
-		init_data->type                  = RC_TYPE_RC5;
+		init_data->type                  = RC_BIT_RC5;
 		init_data->name                  = hdw->hdw_desc->description;
 		init_data->polling_interval      = 100; /* ms From ir-kbd-i2c */
 		/* IR Receiver */
@@ -596,7 +596,7 @@ static void pvr2_i2c_register_ir(struct pvr2_hdw *hdw)
 	case PVR2_IR_SCHEME_24XXX_MCE: /* 24xxx MCE device */
 		init_data->ir_codes              = RC_MAP_HAUPPAUGE;
 		init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP_XVR;
-		init_data->type                  = RC_TYPE_RC5;
+		init_data->type                  = RC_BIT_RC5;
 		init_data->name                  = hdw->hdw_desc->description;
 		/* IR Receiver */
 		info.addr          = 0x71;
diff --git a/drivers/media/usb/tm6000/tm6000-input.c b/drivers/media/usb/tm6000/tm6000-input.c
index dffbd4bd47b1..8a6bbf1d80e1 100644
--- a/drivers/media/usb/tm6000/tm6000-input.c
+++ b/drivers/media/usb/tm6000/tm6000-input.c
@@ -109,12 +109,12 @@ static int tm6000_ir_config(struct tm6000_IR *ir)
 	 */
 
 	switch (ir->rc_type) {
-	case RC_TYPE_NEC:
+	case RC_BIT_NEC:
 		leader = 900;	/* ms */
 		pulse  = 700;	/* ms - the actual value would be 562 */
 		break;
 	default:
-	case RC_TYPE_RC5:
+	case RC_BIT_RC5:
 		leader = 900;	/* ms - from the NEC decoding */
 		pulse  = 1780;	/* ms - The actual value would be 1776 */
 		break;
@@ -122,12 +122,12 @@ static int tm6000_ir_config(struct tm6000_IR *ir)
 
 	pulse = ir_clock_mhz * pulse;
 	leader = ir_clock_mhz * leader;
-	if (ir->rc_type == RC_TYPE_NEC)
+	if (ir->rc_type == RC_BIT_NEC)
 		leader = leader | 0x8000;
 
 	dprintk(2, "%s: %s, %d MHz, leader = 0x%04x, pulse = 0x%06x \n",
 		__func__,
-		(ir->rc_type == RC_TYPE_NEC) ? "NEC" : "RC-5",
+		(ir->rc_type == RC_BIT_NEC) ? "NEC" : "RC-5",
 		ir_clock_mhz, leader, pulse);
 
 	/* Remote WAKEUP = enable, normal mode, from IR decoder output */
@@ -297,7 +297,7 @@ static void tm6000_ir_stop(struct rc_dev *rc)
 	cancel_delayed_work_sync(&ir->work);
 }
 
-static int tm6000_ir_change_protocol(struct rc_dev *rc, u64 rc_type)
+static int tm6000_ir_change_protocol(struct rc_dev *rc, u64 *rc_type)
 {
 	struct tm6000_IR *ir = rc->priv;
 
@@ -306,10 +306,10 @@ static int tm6000_ir_change_protocol(struct rc_dev *rc, u64 rc_type)
 
 	dprintk(2, "%s\n",__func__);
 
-	if ((rc->rc_map.scan) && (rc_type == RC_TYPE_NEC))
+	if ((rc->rc_map.scan) && (*rc_type == RC_BIT_NEC))
 		ir->key_addr = ((rc->rc_map.scan[0].scancode >> 8) & 0xffff);
 
-	ir->rc_type = rc_type;
+	ir->rc_type = *rc_type;
 
 	tm6000_ir_config(ir);
 	/* TODO */
@@ -398,6 +398,7 @@ int tm6000_ir_init(struct tm6000_core *dev)
 	struct tm6000_IR *ir;
 	struct rc_dev *rc;
 	int err = -ENOMEM;
+	u64 rc_type;
 
 	if (!enable_ir)
 		return -ENODEV;
@@ -421,7 +422,7 @@ int tm6000_ir_init(struct tm6000_core *dev)
 	ir->rc = rc;
 
 	/* input setup */
-	rc->allowed_protos = RC_TYPE_RC5 | RC_TYPE_NEC;
+	rc->allowed_protos = RC_BIT_RC5 | RC_BIT_NEC;
 	/* Neded, in order to support NEC remotes with 24 or 32 bits */
 	rc->scanmask = 0xffff;
 	rc->priv = ir;
@@ -444,7 +445,8 @@ int tm6000_ir_init(struct tm6000_core *dev)
 	usb_make_path(dev->udev, ir->phys, sizeof(ir->phys));
 	strlcat(ir->phys, "/input0", sizeof(ir->phys));
 
-	tm6000_ir_change_protocol(rc, RC_TYPE_UNKNOWN);
+	rc_type = RC_BIT_UNKNOWN;
+	tm6000_ir_change_protocol(rc, &rc_type);
 
 	rc->input_name = ir->name;
 	rc->input_phys = ir->phys;
diff --git a/include/media/ir-kbd-i2c.h b/include/media/ir-kbd-i2c.h
index 768aa77925cd..e221bc74020b 100644
--- a/include/media/ir-kbd-i2c.h
+++ b/include/media/ir-kbd-i2c.h
@@ -37,7 +37,7 @@ enum ir_kbd_get_key_fn {
 struct IR_i2c_init_data {
 	char			*ir_codes;
 	const char		*name;
-	u64			type; /* RC_TYPE_RC5, etc */
+	u64			type; /* RC_BIT_RC5, etc */
 	u32			polling_interval; /* 0 means DEFAULT_POLLING_INTERVAL */
 
 	/*
diff --git a/include/media/rc-core.h b/include/media/rc-core.h
index b0c494a69079..f03445f3c767 100644
--- a/include/media/rc-core.h
+++ b/include/media/rc-core.h
@@ -50,7 +50,7 @@ enum rc_driver_type {
  * @input_dev: the input child device used to communicate events to userspace
  * @driver_type: specifies if protocol decoding is done in hardware or software
  * @idle: used to keep track of RX state
- * @allowed_protos: bitmask with the supported RC_TYPE_* protocols
+ * @allowed_protos: bitmask with the supported RC_BIT_* protocols
  * @scanmask: some hardware decoders are not capable of providing the full
  *	scancode to the application. As this is a hardware limit, we can't do
  *	anything with it. Yet, as the same keycode table can be used with other
@@ -113,7 +113,7 @@ struct rc_dev {
 	u32				max_timeout;
 	u32				rx_resolution;
 	u32				tx_resolution;
-	int				(*change_protocol)(struct rc_dev *dev, u64 rc_type);
+	int				(*change_protocol)(struct rc_dev *dev, u64 *rc_type);
 	int				(*open)(struct rc_dev *dev);
 	void				(*close)(struct rc_dev *dev);
 	int				(*s_tx_mask)(struct rc_dev *dev, u32 mask);
diff --git a/include/media/rc-map.h b/include/media/rc-map.h
index cfd5163ff7f3..74f55a3f14eb 100644
--- a/include/media/rc-map.h
+++ b/include/media/rc-map.h
@@ -11,22 +11,54 @@
 
 #include <linux/input.h>
 
-#define RC_TYPE_UNKNOWN	0
-#define RC_TYPE_RC5	(1  << 0)	/* Philips RC5 protocol */
-#define RC_TYPE_NEC	(1  << 1)
-#define RC_TYPE_RC6	(1  << 2)	/* Philips RC6 protocol */
-#define RC_TYPE_JVC	(1  << 3)	/* JVC protocol */
-#define RC_TYPE_SONY	(1  << 4)	/* Sony12/15/20 protocol */
-#define RC_TYPE_RC5_SZ	(1  << 5)	/* RC5 variant used by Streamzap */
-#define RC_TYPE_SANYO   (1  << 6)	/* Sanyo protocol */
-#define RC_TYPE_MCE_KBD	(1  << 29)	/* RC6-ish MCE keyboard/mouse */
-#define RC_TYPE_LIRC	(1  << 30)	/* Pass raw IR to lirc userspace */
-#define RC_TYPE_OTHER	(1u << 31)
+enum rc_type {
+	RC_TYPE_UNKNOWN		= 0,	/* Protocol not known */
+	RC_TYPE_OTHER		= 1,	/* Protocol known but proprietary */
+	RC_TYPE_LIRC		= 2,	/* Pass raw IR to lirc userspace */
+	RC_TYPE_RC5		= 3,	/* Philips RC5 protocol */
+	RC_TYPE_RC5X		= 4,	/* Philips RC5x protocol */
+	RC_TYPE_RC5_SZ		= 5,	/* StreamZap variant of RC5 */
+	RC_TYPE_JVC		= 6,	/* JVC protocol */
+	RC_TYPE_SONY12		= 7,	/* Sony 12 bit protocol */
+	RC_TYPE_SONY15		= 8,	/* Sony 15 bit protocol */
+	RC_TYPE_SONY20		= 9,	/* Sony 20 bit protocol */
+	RC_TYPE_NEC		= 10,	/* NEC protocol */
+	RC_TYPE_SANYO		= 11,	/* Sanyo protocol */
+	RC_TYPE_MCE_KBD		= 12,	/* RC6-ish MCE keyboard/mouse */
+	RC_TYPE_RC6_0		= 13,	/* Philips RC6-0-16 protocol */
+	RC_TYPE_RC6_6A_20	= 14,	/* Philips RC6-6A-20 protocol */
+	RC_TYPE_RC6_6A_24	= 15,	/* Philips RC6-6A-24 protocol */
+	RC_TYPE_RC6_6A_32	= 16,	/* Philips RC6-6A-32 protocol */
+	RC_TYPE_RC6_MCE		= 17,	/* MCE (Philips RC6-6A-32 subtype) protocol */
+};
+
+#define RC_BIT_NONE		0
+#define RC_BIT_UNKNOWN		(1 << RC_TYPE_UNKNOWN)
+#define RC_BIT_OTHER		(1 << RC_TYPE_OTHER)
+#define RC_BIT_LIRC		(1 << RC_TYPE_LIRC)
+#define RC_BIT_RC5		(1 << RC_TYPE_RC5)
+#define RC_BIT_RC5X		(1 << RC_TYPE_RC5X)
+#define RC_BIT_RC5_SZ		(1 << RC_TYPE_RC5_SZ)
+#define RC_BIT_JVC		(1 << RC_TYPE_JVC)
+#define RC_BIT_SONY12		(1 << RC_TYPE_SONY12)
+#define RC_BIT_SONY15		(1 << RC_TYPE_SONY15)
+#define RC_BIT_SONY20		(1 << RC_TYPE_SONY20)
+#define RC_BIT_NEC		(1 << RC_TYPE_NEC)
+#define RC_BIT_SANYO		(1 << RC_TYPE_SANYO)
+#define RC_BIT_MCE_KBD		(1 << RC_TYPE_MCE_KBD)
+#define RC_BIT_RC6_0		(1 << RC_TYPE_RC6_0)
+#define RC_BIT_RC6_6A_20	(1 << RC_TYPE_RC6_6A_20)
+#define RC_BIT_RC6_6A_24	(1 << RC_TYPE_RC6_6A_24)
+#define RC_BIT_RC6_6A_32	(1 << RC_TYPE_RC6_6A_32)
+#define RC_BIT_RC6_MCE		(1 << RC_TYPE_RC6_MCE)
 
-#define RC_TYPE_ALL (RC_TYPE_RC5    | RC_TYPE_NEC   | RC_TYPE_RC6     | \
-		     RC_TYPE_JVC    | RC_TYPE_SONY  | RC_TYPE_LIRC    | \
-		     RC_TYPE_RC5_SZ | RC_TYPE_SANYO | RC_TYPE_MCE_KBD | \
-		     RC_TYPE_OTHER)
+#define RC_BIT_ALL	(RC_BIT_UNKNOWN | RC_BIT_OTHER | RC_BIT_LIRC | \
+			 RC_BIT_RC5 | RC_BIT_RC5X | RC_BIT_RC5_SZ | \
+			 RC_BIT_JVC | \
+			 RC_BIT_SONY12 | RC_BIT_SONY15 | RC_BIT_SONY20 | \
+			 RC_BIT_NEC | RC_BIT_SANYO | RC_BIT_MCE_KBD | \
+			 RC_BIT_RC6_0 | RC_BIT_RC6_6A_20 | RC_BIT_RC6_6A_24 | \
+			 RC_BIT_RC6_6A_32 | RC_BIT_RC6_MCE)
 
 struct rc_map_table {
 	u32	scancode;
@@ -38,7 +70,7 @@ struct rc_map {
 	unsigned int		size;	/* Max number of entries */
 	unsigned int		len;	/* Used number of entries */
 	unsigned int		alloc;	/* Size of *scan in bytes */
-	u64			rc_type;
+	enum rc_type		rc_type;
 	const char		*name;
 	spinlock_t		lock;
 };
-- 
cgit v1.2.3-55-g7522


From 55c6659afaa6fd79a3b5a7c2b42bb87e0c11209d Mon Sep 17 00:00:00 2001
From: Lai Jiangshan
Date: Sat, 13 Oct 2012 01:14:16 +0800
Subject: srcu: Add DEFINE_SRCU()

In old days, we had two different API sets for dynamic-allocated per-CPU
data and DEFINE_PER_CPU()-defined per_cpu data, and because SRCU used
dynamic-allocated per-CPU data, its srcu_struct structures cannot be
declared statically.  This commit therefore introduces DEFINE_SRCU()
and DEFINE_STATIC_SRCU() to allow statically declared SRCU structures,
using the new static per-CPU interfaces.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Updated for __DELAYED_WORK_INITIALIZER() added argument,
	   fixed whitespace issue. ]
---
 include/linux/srcu.h | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 5cce128f196c..6eb691b08358 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -42,6 +42,8 @@ struct rcu_batch {
 	struct rcu_head *head, **tail;
 };
 
+#define RCU_BATCH_INIT(name) { NULL, &(name.head) }
+
 struct srcu_struct {
 	unsigned completed;
 	struct srcu_struct_array __percpu *per_cpu_ref;
@@ -72,14 +74,42 @@ int __init_srcu_struct(struct srcu_struct *sp, const char *name,
 	__init_srcu_struct((sp), #sp, &__srcu_key); \
 })
 
+#define __SRCU_DEP_MAP_INIT(srcu_name)	.dep_map = { .name = #srcu_name },
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 int init_srcu_struct(struct srcu_struct *sp);
 
+#define __SRCU_DEP_MAP_INIT(srcu_name)
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 void process_srcu(struct work_struct *work);
 
+#define __SRCU_STRUCT_INIT(name)					\
+	{								\
+		.completed = -300,					\
+		.per_cpu_ref = &name##_srcu_array,			\
+		.queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock),	\
+		.running = false,					\
+		.batch_queue = RCU_BATCH_INIT(name.batch_queue),	\
+		.batch_check0 = RCU_BATCH_INIT(name.batch_check0),	\
+		.batch_check1 = RCU_BATCH_INIT(name.batch_check1),	\
+		.batch_done = RCU_BATCH_INIT(name.batch_done),		\
+		.work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\
+		__SRCU_DEP_MAP_INIT(name)				\
+	}
+
+/*
+ * define and init a srcu struct at build time.
+ * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it.
+ */
+#define DEFINE_SRCU(name)						\
+	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
+	struct srcu_struct name = __SRCU_STRUCT_INIT(name);
+
+#define DEFINE_STATIC_SRCU(name)					\
+	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
+	static struct srcu_struct name = __SRCU_STRUCT_INIT(name);
+
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
  * @sp: srcu_struct in queue the callback
-- 
cgit v1.2.3-55-g7522


From 9c7066aef4a5eb8e4063de28f06c508bf6f2963a Mon Sep 17 00:00:00 2001
From: Clemens Ladisch
Date: Sat, 27 Oct 2012 21:55:27 +0200
Subject: ALSA: core: fix 64-bit SNDRV_PCM_IOCTL_STATUS ABI breakage

Commit 4eeaaeaea (ALSA: core: add hooks for audio timestamps) added the
new audio_tstamp field to struct snd_pcm_status.  However, struct
timespec requires 64-bit alignment, so the 64-bit compiler would insert
32 bits of padding before this field, which broke SNDRV_PCM_IOCTL_STATUS
with error messages like this:

  kernel: unknown ioctl = 0x80984120

To solve this, insert the padding explicitly so that it can be taken
into account when calculating the ABI structure size.

Signed-off-by: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/uapi/sound/asound.h | 3 ++-
 sound/core/pcm_compat.c     | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 85b2e4dde883..515b8fcd1ca9 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -407,8 +407,9 @@ struct snd_pcm_status {
 	snd_pcm_uframes_t avail_max;	/* max frames available on hw since last status */
 	snd_pcm_uframes_t overrange;	/* count of ADC (capture) overrange detections from last status */
 	snd_pcm_state_t suspended_state; /* suspended stream state */
+	__u32 reserved_alignment;	/* must be filled with zero */
 	struct timespec audio_tstamp;	/* from sample counter or wall clock */
-	unsigned char reserved[60-sizeof(struct timespec)]; /* must be filled with zero */
+	unsigned char reserved[56-sizeof(struct timespec)]; /* must be filled with zero */
 };
 
 struct snd_pcm_mmap_status {
diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c
index af2a3fdb8828..af49721ba0e3 100644
--- a/sound/core/pcm_compat.c
+++ b/sound/core/pcm_compat.c
@@ -190,8 +190,9 @@ struct snd_pcm_status32 {
 	u32 avail_max;
 	u32 overrange;
 	s32 suspended_state;
+	u32 reserved_alignment;
 	struct compat_timespec audio_tstamp;
-	unsigned char reserved[60-sizeof(struct compat_timespec)];
+	unsigned char reserved[56-sizeof(struct compat_timespec)];
 } __attribute__((packed));
 
 
-- 
cgit v1.2.3-55-g7522


From 2e74598d7f4c6d1b34da84037d9a7f8b1c8e04ae Mon Sep 17 00:00:00 2001
From: Kirill Smelkov
Date: Mon, 22 Oct 2012 14:14:01 -0300
Subject: [media] v4l2: Fix typo in struct v4l2_captureparm description

Judging from what drivers do and from my experience temeperframe
fraction is set in seconds - look e.g. here
    static int bttv_g_parm(struct file *file, void *f,
                                    struct v4l2_streamparm *parm)
    {
            struct bttv_fh *fh = f;
            struct bttv *btv = fh->btv;
            v4l2_video_std_frame_period(bttv_tvnorms[btv->tvnorm].v4l2_id,
                                        &parm->parm.capture.timeperframe);
    ...
    void v4l2_video_std_frame_period(int id, struct v4l2_fract *frameperiod)
    {
            if (id & V4L2_STD_525_60) {
                    frameperiod->numerator = 1001;
                    frameperiod->denominator = 30000;
            } else {
                    frameperiod->numerator = 1;
                    frameperiod->denominator = 25;
            }
and also v4l2-ctl in userspace decodes this as seconds:
    if (doioctl(fd, VIDIOC_G_PARM, &parm, "VIDIOC_G_PARM") == 0) {
            const struct v4l2_fract &tf = parm.parm.capture.timeperframe;
            ...
            printf("\tFrames per second: %.3f (%d/%d)\n",
                            (1.0 * tf.denominator) / tf.numerator,
                            tf.denominator, tf.numerator);
The typo was there from day 1 - added in 2002 in e028b61b ([PATCH]
add v4l2 api)(*)
(*) found in history tree
    git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git

Signed-off-by: Kirill Smelkov <kirr@mns.spb.ru>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 include/uapi/linux/videodev2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 57bfa59cda74..2fff7ff3e05b 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -737,7 +737,7 @@ struct v4l2_window {
 struct v4l2_captureparm {
 	__u32		   capability;	  /*  Supported modes */
 	__u32		   capturemode;	  /*  Current mode */
-	struct v4l2_fract  timeperframe;  /*  Time per frame in .1us units */
+	struct v4l2_fract  timeperframe;  /*  Time per frame in seconds */
 	__u32		   extendedmode;  /*  Driver-specific extensions */
 	__u32              readbuffers;   /*  # of buffers for read */
 	__u32		   reserved[4];
-- 
cgit v1.2.3-55-g7522


From d900082bd9060dc955b181dae2f2adf86e27d747 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Thu, 25 Oct 2012 22:28:49 +0000
Subject: rtnl: add a new type of msg to advertise protocol configuration

A new type is added to allow userland to monitor protocol configuration, like
IPv4 or IPv6.
For example, monitoring the state of the forwarding status of an interface of
the system.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/netconf.h   | 22 ++++++++++++++++++++++
 include/uapi/linux/rtnetlink.h |  5 +++++
 2 files changed, 27 insertions(+)
 create mode 100644 include/uapi/linux/netconf.h

(limited to 'include')

diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
new file mode 100644
index 000000000000..d0513726711f
--- /dev/null
+++ b/include/uapi/linux/netconf.h
@@ -0,0 +1,22 @@
+#ifndef _UAPI_LINUX_NETCONF_H_
+#define _UAPI_LINUX_NETCONF_H_
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+struct netconfmsg {
+	__u8	ncm_family;
+};
+
+enum {
+	NETCONFA_UNSPEC,
+	NETCONFA_IFINDEX,
+	NETCONFA_FORWARDING,
+	__NETCONFA_MAX
+};
+#define NETCONFA_MAX	(__NETCONFA_MAX - 1)
+
+#define NETCONFA_IFINDEX_ALL		-1
+#define NETCONFA_IFINDEX_DEFAULT	-2
+
+#endif /* _UAPI_LINUX_NETCONF_H_ */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index fcd768b09f6e..0043b413b8bc 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -120,6 +120,11 @@ enum {
 	RTM_SETDCB,
 #define RTM_SETDCB RTM_SETDCB
 
+	RTM_NEWNETCONF = 80,
+#define RTM_NEWNETCONF RTM_NEWNETCONF
+	RTM_GETNETCONF = 82,
+#define RTM_GETNETCONF RTM_GETNETCONF
+
 	__RTM_MAX,
 #define RTM_MAX		(((__RTM_MAX + 3) & ~3) - 1)
 };
-- 
cgit v1.2.3-55-g7522


From f3a1bfb11ccbc72d44f0b58c92115a40128979c3 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Thu, 25 Oct 2012 22:28:50 +0000
Subject: rtnl/ipv6: use netconf msg to advertise forwarding status

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/rtnetlink.h |  2 ++
 net/ipv6/addrconf.c            | 77 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 79 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 0043b413b8bc..a4d75ea868ed 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -592,6 +592,8 @@ enum rtnetlink_groups {
 #define RTNLGRP_PHONET_ROUTE	RTNLGRP_PHONET_ROUTE
 	RTNLGRP_DCB,
 #define RTNLGRP_DCB		RTNLGRP_DCB
+	RTNLGRP_IPV6_NETCONF,
+#define RTNLGRP_IPV6_NETCONF	RTNLGRP_IPV6_NETCONF
 	__RTNLGRP_MAX
 };
 #define RTNLGRP_MAX	(__RTNLGRP_MAX - 1)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 0424e4e27414..0c57a8f67715 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -81,6 +81,7 @@
 #include <net/pkt_sched.h>
 #include <linux/if_tunnel.h>
 #include <linux/rtnetlink.h>
+#include <linux/netconf.h>
 
 #ifdef CONFIG_IPV6_PRIVACY
 #include <linux/random.h>
@@ -460,6 +461,72 @@ static struct inet6_dev *ipv6_find_idev(struct net_device *dev)
 	return idev;
 }
 
+static int inet6_netconf_msgsize_devconf(int type)
+{
+	int size =  NLMSG_ALIGN(sizeof(struct netconfmsg))
+		    + nla_total_size(4);	/* NETCONFA_IFINDEX */
+
+	if (type == NETCONFA_FORWARDING)
+		size += nla_total_size(4);
+
+	return size;
+}
+
+static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
+				      struct ipv6_devconf *devconf, u32 portid,
+				      u32 seq, int event, unsigned int flags,
+				      int type)
+{
+	struct nlmsghdr  *nlh;
+	struct netconfmsg *ncm;
+
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg),
+			flags);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	ncm = nlmsg_data(nlh);
+	ncm->ncm_family = AF_INET6;
+
+	if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
+		goto nla_put_failure;
+
+	if (type == NETCONFA_FORWARDING &&
+	    nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0)
+		goto nla_put_failure;
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
+					 struct ipv6_devconf *devconf)
+{
+	struct sk_buff *skb;
+	int err = -ENOBUFS;
+
+	skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_ATOMIC);
+	if (skb == NULL)
+		goto errout;
+
+	err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
+					 RTM_NEWNETCONF, 0, type);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(skb);
+		goto errout;
+	}
+	rtnl_notify(skb, net, 0, RTNLGRP_IPV6_NETCONF, NULL, GFP_ATOMIC);
+	return;
+errout:
+	if (err < 0)
+		rtnl_set_sk_err(net, RTNLGRP_IPV6_NETCONF, err);
+}
+
 #ifdef CONFIG_SYSCTL
 static void dev_forward_change(struct inet6_dev *idev)
 {
@@ -486,6 +553,8 @@ static void dev_forward_change(struct inet6_dev *idev)
 		else
 			addrconf_leave_anycast(ifa);
 	}
+	inet6_netconf_notify_devconf(dev_net(dev), NETCONFA_FORWARDING,
+				     dev->ifindex, &idev->cnf);
 }
 
 
@@ -518,6 +587,10 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
 	*p = newf;
 
 	if (p == &net->ipv6.devconf_dflt->forwarding) {
+		if ((!newf) ^ (!old))
+			inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+						     NETCONFA_IFINDEX_DEFAULT,
+						     net->ipv6.devconf_dflt);
 		rtnl_unlock();
 		return 0;
 	}
@@ -525,6 +598,10 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
 	if (p == &net->ipv6.devconf_all->forwarding) {
 		net->ipv6.devconf_dflt->forwarding = newf;
 		addrconf_forward_change(net, newf);
+		if ((!newf) ^ (!old))
+			inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+						     NETCONFA_IFINDEX_ALL,
+						     net->ipv6.devconf_all);
 	} else if ((!newf) ^ (!old))
 		dev_forward_change((struct inet6_dev *)table->extra1);
 	rtnl_unlock();
-- 
cgit v1.2.3-55-g7522


From edc9e748934cf406cab708ca5dda7bd3c0f0a1db Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Thu, 25 Oct 2012 22:28:52 +0000
Subject: rtnl/ipv4: use netconf msg to advertise forwarding status

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/rtnetlink.h |  2 +
 net/ipv4/devinet.c             | 93 ++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 91 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index a4d75ea868ed..3dee071770d5 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -592,6 +592,8 @@ enum rtnetlink_groups {
 #define RTNLGRP_PHONET_ROUTE	RTNLGRP_PHONET_ROUTE
 	RTNLGRP_DCB,
 #define RTNLGRP_DCB		RTNLGRP_DCB
+	RTNLGRP_IPV4_NETCONF,
+#define RTNLGRP_IPV4_NETCONF	RTNLGRP_IPV4_NETCONF
 	RTNLGRP_IPV6_NETCONF,
 #define RTNLGRP_IPV6_NETCONF	RTNLGRP_IPV6_NETCONF
 	__RTNLGRP_MAX
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 2a6abc163ed2..020fdd2e6e19 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -55,6 +55,7 @@
 #include <linux/sysctl.h>
 #endif
 #include <linux/kmod.h>
+#include <linux/netconf.h>
 
 #include <net/arp.h>
 #include <net/ip.h>
@@ -1442,6 +1443,73 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla)
 	return 0;
 }
 
+static int inet_netconf_msgsize_devconf(int type)
+{
+	int size = NLMSG_ALIGN(sizeof(struct netconfmsg))
+		   + nla_total_size(4);	/* NETCONFA_IFINDEX */
+
+	if (type == NETCONFA_FORWARDING)
+		size += nla_total_size(4);
+
+	return size;
+}
+
+static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
+				     struct ipv4_devconf *devconf, u32 portid,
+				     u32 seq, int event, unsigned int flags,
+				     int type)
+{
+	struct nlmsghdr  *nlh;
+	struct netconfmsg *ncm;
+
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg),
+			flags);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	ncm = nlmsg_data(nlh);
+	ncm->ncm_family = AF_INET;
+
+	if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
+		goto nla_put_failure;
+
+	if (type == NETCONFA_FORWARDING &&
+	    nla_put_s32(skb, NETCONFA_FORWARDING,
+			IPV4_DEVCONF(*devconf, FORWARDING)) < 0)
+		goto nla_put_failure;
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
+					struct ipv4_devconf *devconf)
+{
+	struct sk_buff *skb;
+	int err = -ENOBUFS;
+
+	skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_ATOMIC);
+	if (skb == NULL)
+		goto errout;
+
+	err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
+					RTM_NEWNETCONF, 0, type);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(skb);
+		goto errout;
+	}
+	rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_ATOMIC);
+	return;
+errout:
+	if (err < 0)
+		rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err);
+}
+
 #ifdef CONFIG_SYSCTL
 
 static void devinet_copy_dflt_conf(struct net *net, int i)
@@ -1467,6 +1535,12 @@ static void inet_forward_change(struct net *net)
 
 	IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on;
 	IPV4_DEVCONF_DFLT(net, FORWARDING) = on;
+	inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+				    NETCONFA_IFINDEX_ALL,
+				    net->ipv4.devconf_all);
+	inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+				    NETCONFA_IFINDEX_DEFAULT,
+				    net->ipv4.devconf_dflt);
 
 	for_each_netdev(net, dev) {
 		struct in_device *in_dev;
@@ -1474,8 +1548,11 @@ static void inet_forward_change(struct net *net)
 			dev_disable_lro(dev);
 		rcu_read_lock();
 		in_dev = __in_dev_get_rcu(dev);
-		if (in_dev)
+		if (in_dev) {
 			IN_DEV_CONF_SET(in_dev, FORWARDING, on);
+			inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+						    dev->ifindex, &in_dev->cnf);
+		}
 		rcu_read_unlock();
 	}
 }
@@ -1527,15 +1604,23 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write,
 			}
 			if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) {
 				inet_forward_change(net);
-			} else if (*valp) {
+			} else {
 				struct ipv4_devconf *cnf = ctl->extra1;
 				struct in_device *idev =
 					container_of(cnf, struct in_device, cnf);
-				dev_disable_lro(idev->dev);
+				if (*valp)
+					dev_disable_lro(idev->dev);
+				inet_netconf_notify_devconf(net,
+							    NETCONFA_FORWARDING,
+							    idev->dev->ifindex,
+							    cnf);
 			}
 			rtnl_unlock();
 			rt_cache_flush(net);
-		}
+		} else
+			inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+						    NETCONFA_IFINDEX_DEFAULT,
+						    net->ipv4.devconf_dflt);
 	}
 
 	return ret;
-- 
cgit v1.2.3-55-g7522


From 52feb444a90304eb13c03115bb9758101dbb9254 Mon Sep 17 00:00:00 2001
From: Thierry Escande
Date: Wed, 17 Oct 2012 14:43:39 +0200
Subject: NFC: Extend netlink interface for LTO, RW, and MIUX parameters
 support

NFC_CMD_LLC_GET_PARAMS: request LTO, RW, and MIUX parameters for a device

NFC_CMD_LLC_SET_PARAMS: set one or more of LTO, RW, and MIUX parameters for
a device. LTO must be set before the link is up otherwise -EINPROGRESS is
returned. RW and MIUX can be set at anytime and will be passed in subsequent
CONNECT and CC messages. If one of the passed parameters is wrong none is
set and -EINVAL is returned.

Signed-off-by: Thierry Escande <thierry.escande@linux.intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/uapi/linux/nfc.h |  15 +++++
 net/nfc/llcp/commands.c  |  18 ++----
 net/nfc/llcp/llcp.c      |  14 ++---
 net/nfc/llcp/llcp.h      |   3 +
 net/nfc/netlink.c        | 152 +++++++++++++++++++++++++++++++++++++++++++++++
 net/nfc/nfc.h            |   6 ++
 6 files changed, 189 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h
index d908d17da56d..0e63cee8d810 100644
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -60,6 +60,13 @@
  *      target mode.
  * @NFC_EVENT_DEVICE_DEACTIVATED: event emitted when the adapter is deactivated
  *      from target mode.
+ * @NFC_CMD_LLC_GET_PARAMS: request LTO, RW, and MIUX parameters for a device
+ * @NFC_CMD_LLC_SET_PARAMS: set one or more of LTO, RW, and MIUX parameters for
+ *	a device. LTO must be set before the link is up otherwise -EINPROGRESS
+ *	is returned. RW and MIUX can be set at anytime and will be passed in
+ *	subsequent CONNECT and CC messages.
+ *	If one of the passed parameters is wrong none is set and -EINVAL is
+ *	returned.
  */
 enum nfc_commands {
 	NFC_CMD_UNSPEC,
@@ -77,6 +84,8 @@ enum nfc_commands {
 	NFC_EVENT_TARGET_LOST,
 	NFC_EVENT_TM_ACTIVATED,
 	NFC_EVENT_TM_DEACTIVATED,
+	NFC_CMD_LLC_GET_PARAMS,
+	NFC_CMD_LLC_SET_PARAMS,
 /* private: internal use only */
 	__NFC_CMD_AFTER_LAST
 };
@@ -102,6 +111,9 @@ enum nfc_commands {
  * @NFC_ATTR_RF_MODE: Initiator or target
  * @NFC_ATTR_IM_PROTOCOLS: Initiator mode protocols to poll for
  * @NFC_ATTR_TM_PROTOCOLS: Target mode protocols to listen for
+ * @NFC_ATTR_LLC_PARAM_LTO: Link TimeOut parameter
+ * @NFC_ATTR_LLC_PARAM_RW: Receive Window size parameter
+ * @NFC_ATTR_LLC_PARAM_MIUX: MIU eXtension parameter
  */
 enum nfc_attrs {
 	NFC_ATTR_UNSPEC,
@@ -119,6 +131,9 @@ enum nfc_attrs {
 	NFC_ATTR_DEVICE_POWERED,
 	NFC_ATTR_IM_PROTOCOLS,
 	NFC_ATTR_TM_PROTOCOLS,
+	NFC_ATTR_LLC_PARAM_LTO,
+	NFC_ATTR_LLC_PARAM_RW,
+	NFC_ATTR_LLC_PARAM_MIUX,
 /* private: internal use only */
 	__NFC_ATTR_AFTER_LAST
 };
diff --git a/net/nfc/llcp/commands.c b/net/nfc/llcp/commands.c
index 79415353cc28..ed2d17312d61 100644
--- a/net/nfc/llcp/commands.c
+++ b/net/nfc/llcp/commands.c
@@ -316,8 +316,7 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock)
 	struct sk_buff *skb;
 	u8 *service_name_tlv = NULL, service_name_tlv_length;
 	u8 *miux_tlv = NULL, miux_tlv_length;
-	u8 *rw_tlv = NULL, rw_tlv_length, rw;
-	__be16 miux;
+	u8 *rw_tlv = NULL, rw_tlv_length;
 	int err;
 	u16 size = 0;
 
@@ -335,13 +334,11 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock)
 		size += service_name_tlv_length;
 	}
 
-	miux = cpu_to_be16(LLCP_MAX_MIUX);
-	miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0,
+	miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0,
 				      &miux_tlv_length);
 	size += miux_tlv_length;
 
-	rw = LLCP_MAX_RW;
-	rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length);
+	rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &local->rw, 0, &rw_tlv_length);
 	size += rw_tlv_length;
 
 	pr_debug("SKB size %d SN length %zu\n", size, sock->service_name_len);
@@ -378,8 +375,7 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock)
 	struct nfc_llcp_local *local;
 	struct sk_buff *skb;
 	u8 *miux_tlv = NULL, miux_tlv_length;
-	u8 *rw_tlv = NULL, rw_tlv_length, rw;
-	__be16 miux;
+	u8 *rw_tlv = NULL, rw_tlv_length;
 	int err;
 	u16 size = 0;
 
@@ -389,13 +385,11 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock)
 	if (local == NULL)
 		return -ENODEV;
 
-	miux = cpu_to_be16(LLCP_MAX_MIUX);
-	miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0,
+	miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0,
 				      &miux_tlv_length);
 	size += miux_tlv_length;
 
-	rw = LLCP_MAX_RW;
-	rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length);
+	rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &local->rw, 0, &rw_tlv_length);
 	size += rw_tlv_length;
 
 	skb = llcp_allocate_pdu(sock, LLCP_PDU_CC, size);
diff --git a/net/nfc/llcp/llcp.c b/net/nfc/llcp/llcp.c
index 2e23bd348ebd..f6804532047a 100644
--- a/net/nfc/llcp/llcp.c
+++ b/net/nfc/llcp/llcp.c
@@ -467,10 +467,9 @@ static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local)
 static int nfc_llcp_build_gb(struct nfc_llcp_local *local)
 {
 	u8 *gb_cur, *version_tlv, version, version_length;
-	u8 *lto_tlv, lto, lto_length;
+	u8 *lto_tlv, lto_length;
 	u8 *wks_tlv, wks_length;
 	u8 *miux_tlv, miux_length;
-	__be16 miux;
 	u8 gb_len = 0;
 	int ret = 0;
 
@@ -479,9 +478,7 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local)
 					 1, &version_length);
 	gb_len += version_length;
 
-	/* 1500 ms */
-	lto = 150;
-	lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &lto, 1, &lto_length);
+	lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &local->lto, 1, &lto_length);
 	gb_len += lto_length;
 
 	pr_debug("Local wks 0x%lx\n", local->local_wks);
@@ -489,8 +486,7 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local)
 				     &wks_length);
 	gb_len += wks_length;
 
-	miux = cpu_to_be16(LLCP_MAX_MIUX);
-	miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0,
+	miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0,
 				      &miux_length);
 	gb_len += miux_length;
 
@@ -1383,6 +1379,10 @@ int nfc_llcp_register_device(struct nfc_dev *ndev)
 	rwlock_init(&local->connecting_sockets.lock);
 	rwlock_init(&local->raw_sockets.lock);
 
+	local->lto = 150; /* 1500 ms */
+	local->rw = LLCP_MAX_RW;
+	local->miux = cpu_to_be16(LLCP_MAX_MIUX);
+
 	nfc_llcp_build_gb(local);
 
 	local->remote_miu = LLCP_DEFAULT_MIU;
diff --git a/net/nfc/llcp/llcp.h b/net/nfc/llcp/llcp.h
index 276da3a6a589..0d62366f8cc3 100644
--- a/net/nfc/llcp/llcp.h
+++ b/net/nfc/llcp/llcp.h
@@ -64,6 +64,9 @@ struct nfc_llcp_local {
 	u32 target_idx;
 	u8 rf_mode;
 	u8 comm_mode;
+	u8 lto;
+	u8 rw;
+	__be16 miux;
 	unsigned long local_wks;      /* Well known services */
 	unsigned long local_sdp;      /* Local services  */
 	unsigned long local_sap; /* Local SAPs, not available for discovery */
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 614cfd0470b7..3568ae16786d 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -29,6 +29,8 @@
 
 #include "nfc.h"
 
+#include "llcp/llcp.h"
+
 static struct genl_multicast_group nfc_genl_event_mcgrp = {
 	.name = NFC_GENL_MCAST_EVENT_NAME,
 };
@@ -716,6 +718,146 @@ static int nfc_genl_dep_link_down(struct sk_buff *skb, struct genl_info *info)
 	return rc;
 }
 
+static int nfc_genl_send_params(struct sk_buff *msg,
+				struct nfc_llcp_local *local,
+				u32 portid, u32 seq)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &nfc_genl_family, 0,
+			  NFC_CMD_LLC_GET_PARAMS);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, local->dev->idx) ||
+	    nla_put_u8(msg, NFC_ATTR_LLC_PARAM_LTO, local->lto) ||
+	    nla_put_u8(msg, NFC_ATTR_LLC_PARAM_RW, local->rw) ||
+	    nla_put_u16(msg, NFC_ATTR_LLC_PARAM_MIUX, be16_to_cpu(local->miux)))
+		goto nla_put_failure;
+
+	return genlmsg_end(msg, hdr);
+
+nla_put_failure:
+
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nfc_dev *dev;
+	struct nfc_llcp_local *local;
+	int rc = 0;
+	struct sk_buff *msg = NULL;
+	u32 idx;
+
+	if (!info->attrs[NFC_ATTR_DEVICE_INDEX])
+		return -EINVAL;
+
+	idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]);
+
+	dev = nfc_get_device(idx);
+	if (!dev)
+		return -ENODEV;
+
+	device_lock(&dev->dev);
+
+	local = nfc_llcp_find_local(dev);
+	if (!local) {
+		rc = -ENODEV;
+		goto exit;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg) {
+		rc = -ENOMEM;
+		goto exit;
+	}
+
+	rc = nfc_genl_send_params(msg, local, info->snd_portid, info->snd_seq);
+
+exit:
+	device_unlock(&dev->dev);
+
+	nfc_put_device(dev);
+
+	if (rc < 0) {
+		if (msg)
+			nlmsg_free(msg);
+
+		return rc;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nfc_dev *dev;
+	struct nfc_llcp_local *local;
+	u8 rw = 0;
+	u16 miux = 0;
+	u32 idx;
+	int rc = 0;
+
+	if (!info->attrs[NFC_ATTR_DEVICE_INDEX] ||
+	    (!info->attrs[NFC_ATTR_LLC_PARAM_LTO] &&
+	     !info->attrs[NFC_ATTR_LLC_PARAM_RW] &&
+	     !info->attrs[NFC_ATTR_LLC_PARAM_MIUX]))
+		return -EINVAL;
+
+	if (info->attrs[NFC_ATTR_LLC_PARAM_RW]) {
+		rw = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_RW]);
+
+		if (rw > LLCP_MAX_RW)
+			return -EINVAL;
+	}
+
+	if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) {
+		miux = nla_get_u16(info->attrs[NFC_ATTR_LLC_PARAM_MIUX]);
+
+		if (miux > LLCP_MAX_MIUX)
+			return -EINVAL;
+	}
+
+	idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]);
+
+	dev = nfc_get_device(idx);
+	if (!dev)
+		return -ENODEV;
+
+	device_lock(&dev->dev);
+
+	local = nfc_llcp_find_local(dev);
+	if (!local) {
+		nfc_put_device(dev);
+		rc = -ENODEV;
+		goto exit;
+	}
+
+	if (info->attrs[NFC_ATTR_LLC_PARAM_LTO]) {
+		if (dev->dep_link_up) {
+			rc = -EINPROGRESS;
+			goto exit;
+		}
+
+		local->lto = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_LTO]);
+	}
+
+	if (info->attrs[NFC_ATTR_LLC_PARAM_RW])
+		local->rw = rw;
+
+	if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX])
+		local->miux = cpu_to_be16(miux);
+
+exit:
+	device_unlock(&dev->dev);
+
+	nfc_put_device(dev);
+
+	return rc;
+}
+
 static struct genl_ops nfc_genl_ops[] = {
 	{
 		.cmd = NFC_CMD_GET_DEVICE,
@@ -760,6 +902,16 @@ static struct genl_ops nfc_genl_ops[] = {
 		.done = nfc_genl_dump_targets_done,
 		.policy = nfc_genl_policy,
 	},
+	{
+		.cmd = NFC_CMD_LLC_GET_PARAMS,
+		.doit = nfc_genl_llc_get_params,
+		.policy = nfc_genl_policy,
+	},
+	{
+		.cmd = NFC_CMD_LLC_SET_PARAMS,
+		.doit = nfc_genl_llc_set_params,
+		.policy = nfc_genl_policy,
+	},
 };
 
 
diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h
index c5e42b79a418..87d914d2876a 100644
--- a/net/nfc/nfc.h
+++ b/net/nfc/nfc.h
@@ -56,6 +56,7 @@ void nfc_llcp_unregister_device(struct nfc_dev *dev);
 int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len);
 u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len);
 int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb);
+struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev);
 int __init nfc_llcp_init(void);
 void nfc_llcp_exit(void);
 
@@ -97,6 +98,11 @@ static inline int nfc_llcp_data_received(struct nfc_dev *dev,
 	return 0;
 }
 
+static inline struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev)
+{
+	return NULL;
+}
+
 static inline int nfc_llcp_init(void)
 {
 	return 0;
-- 
cgit v1.2.3-55-g7522


From 2bbcce5e0b47e0de83a1b799b9e164f8c5b9b634 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Mon, 29 Oct 2012 12:40:46 +0200
Subject: OMAPDSS: export dss_get_def_display_name()

Export dss_get_def_display_name() with the name of
omapdss_get_def_display_name() so that omapfb can use it after the next
patch which moves default display handling to omapfb.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/omap2/dss/core.c    | 3 ++-
 drivers/video/omap2/dss/display.c | 2 +-
 drivers/video/omap2/dss/dpi.c     | 2 +-
 drivers/video/omap2/dss/dsi.c     | 2 +-
 drivers/video/omap2/dss/dss.h     | 1 -
 drivers/video/omap2/dss/hdmi.c    | 2 +-
 drivers/video/omap2/dss/rfbi.c    | 2 +-
 drivers/video/omap2/dss/sdi.c     | 2 +-
 drivers/video/omap2/dss/venc.c    | 2 +-
 include/video/omapdss.h           | 1 +
 10 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/video/omap2/dss/core.c b/drivers/video/omap2/dss/core.c
index 685d9a957b19..a2ea684169e9 100644
--- a/drivers/video/omap2/dss/core.c
+++ b/drivers/video/omap2/dss/core.c
@@ -53,10 +53,11 @@ static char *def_disp_name;
 module_param_named(def_disp, def_disp_name, charp, 0);
 MODULE_PARM_DESC(def_disp, "default display name");
 
-const char *dss_get_default_display_name(void)
+const char *omapdss_get_default_display_name(void)
 {
 	return core.default_display_name;
 }
+EXPORT_SYMBOL(omapdss_get_default_display_name);
 
 enum omapdss_version omapdss_get_version(void)
 {
diff --git a/drivers/video/omap2/dss/display.c b/drivers/video/omap2/dss/display.c
index 1e587306215f..90edd718e9e7 100644
--- a/drivers/video/omap2/dss/display.c
+++ b/drivers/video/omap2/dss/display.c
@@ -394,7 +394,7 @@ int dss_init_device(struct platform_device *pdev,
 {
 	struct device_attribute *attr;
 	int i, r;
-	const char *def_disp_name = dss_get_default_display_name();
+	const char *def_disp_name = omapdss_get_default_display_name();
 	bool force;
 
 	force = def_disp_name && strcmp(def_disp_name, dssdev->name) == 0;
diff --git a/drivers/video/omap2/dss/dpi.c b/drivers/video/omap2/dss/dpi.c
index 56748cf8760e..11d64b09cffe 100644
--- a/drivers/video/omap2/dss/dpi.c
+++ b/drivers/video/omap2/dss/dpi.c
@@ -389,7 +389,7 @@ static int __init dpi_init_display(struct omap_dss_device *dssdev)
 static struct omap_dss_device * __init dpi_find_dssdev(struct platform_device *pdev)
 {
 	struct omap_dss_board_info *pdata = pdev->dev.platform_data;
-	const char *def_disp_name = dss_get_default_display_name();
+	const char *def_disp_name = omapdss_get_default_display_name();
 	struct omap_dss_device *def_dssdev;
 	int i;
 
diff --git a/drivers/video/omap2/dss/dsi.c b/drivers/video/omap2/dss/dsi.c
index 7d0db2bf2fc6..2ba505b33153 100644
--- a/drivers/video/omap2/dss/dsi.c
+++ b/drivers/video/omap2/dss/dsi.c
@@ -5100,7 +5100,7 @@ static struct omap_dss_device * __init dsi_find_dssdev(struct platform_device *p
 {
 	struct omap_dss_board_info *pdata = pdev->dev.platform_data;
 	struct dsi_data *dsi = dsi_get_dsidrv_data(pdev);
-	const char *def_disp_name = dss_get_default_display_name();
+	const char *def_disp_name = omapdss_get_default_display_name();
 	struct omap_dss_device *def_dssdev;
 	int i;
 
diff --git a/drivers/video/omap2/dss/dss.h b/drivers/video/omap2/dss/dss.h
index 00e0a36723b9..d468743a209e 100644
--- a/drivers/video/omap2/dss/dss.h
+++ b/drivers/video/omap2/dss/dss.h
@@ -160,7 +160,6 @@ struct seq_file;
 struct platform_device;
 
 /* core */
-const char *dss_get_default_display_name(void);
 struct bus_type *dss_get_bus(void);
 struct regulator *dss_get_vdds_dsi(void);
 struct regulator *dss_get_vdds_sdi(void);
diff --git a/drivers/video/omap2/dss/hdmi.c b/drivers/video/omap2/dss/hdmi.c
index c1c54883fbe7..54931f14c099 100644
--- a/drivers/video/omap2/dss/hdmi.c
+++ b/drivers/video/omap2/dss/hdmi.c
@@ -910,7 +910,7 @@ int hdmi_audio_config(struct omap_dss_audio *audio)
 static struct omap_dss_device * __init hdmi_find_dssdev(struct platform_device *pdev)
 {
 	struct omap_dss_board_info *pdata = pdev->dev.platform_data;
-	const char *def_disp_name = dss_get_default_display_name();
+	const char *def_disp_name = omapdss_get_default_display_name();
 	struct omap_dss_device *def_dssdev;
 	int i;
 
diff --git a/drivers/video/omap2/dss/rfbi.c b/drivers/video/omap2/dss/rfbi.c
index 7282e5af3e1a..7bfeb13cf3d0 100644
--- a/drivers/video/omap2/dss/rfbi.c
+++ b/drivers/video/omap2/dss/rfbi.c
@@ -950,7 +950,7 @@ static int __init rfbi_init_display(struct omap_dss_device *dssdev)
 static struct omap_dss_device * __init rfbi_find_dssdev(struct platform_device *pdev)
 {
 	struct omap_dss_board_info *pdata = pdev->dev.platform_data;
-	const char *def_disp_name = dss_get_default_display_name();
+	const char *def_disp_name = omapdss_get_default_display_name();
 	struct omap_dss_device *def_dssdev;
 	int i;
 
diff --git a/drivers/video/omap2/dss/sdi.c b/drivers/video/omap2/dss/sdi.c
index 7760851f6e5d..882ce89765e7 100644
--- a/drivers/video/omap2/dss/sdi.c
+++ b/drivers/video/omap2/dss/sdi.c
@@ -205,7 +205,7 @@ static int __init sdi_init_display(struct omap_dss_device *dssdev)
 static struct omap_dss_device * __init sdi_find_dssdev(struct platform_device *pdev)
 {
 	struct omap_dss_board_info *pdata = pdev->dev.platform_data;
-	const char *def_disp_name = dss_get_default_display_name();
+	const char *def_disp_name = omapdss_get_default_display_name();
 	struct omap_dss_device *def_dssdev;
 	int i;
 
diff --git a/drivers/video/omap2/dss/venc.c b/drivers/video/omap2/dss/venc.c
index 56efa3bb465d..e8fddc9012cb 100644
--- a/drivers/video/omap2/dss/venc.c
+++ b/drivers/video/omap2/dss/venc.c
@@ -744,7 +744,7 @@ static void venc_put_clocks(void)
 static struct omap_dss_device * __init venc_find_dssdev(struct platform_device *pdev)
 {
 	struct omap_dss_board_info *pdata = pdev->dev.platform_data;
-	const char *def_disp_name = dss_get_default_display_name();
+	const char *def_disp_name = omapdss_get_default_display_name();
 	struct omap_dss_device *def_dssdev;
 	int i;
 
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index eac5f2562253..bf2c68ad1995 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -753,6 +753,7 @@ void omap_dss_put_device(struct omap_dss_device *dssdev);
 struct omap_dss_device *omap_dss_get_next_device(struct omap_dss_device *from);
 struct omap_dss_device *omap_dss_find_device(void *data,
 		int (*match)(struct omap_dss_device *dssdev, void *data));
+const char *omapdss_get_default_display_name(void);
 
 int omap_dss_start_device(struct omap_dss_device *dssdev);
 void omap_dss_stop_device(struct omap_dss_device *dssdev);
-- 
cgit v1.2.3-55-g7522


From dcbf832e5823156e8f155359b47bd108cac8ad68 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Fri, 5 Oct 2012 23:07:19 +0200
Subject: vtime: Gather vtime declarations to their own header file

These APIs are scattered around and are going to expand a bit.
Let's create a dedicated header file for sanity.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 include/linux/hardirq.h     | 11 +----------
 include/linux/kernel_stat.h |  9 +--------
 include/linux/vtime.h       | 22 ++++++++++++++++++++++
 3 files changed, 24 insertions(+), 18 deletions(-)
 create mode 100644 include/linux/vtime.h

(limited to 'include')

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index cab3da3d0949..b083a475423d 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -4,6 +4,7 @@
 #include <linux/preempt.h>
 #include <linux/lockdep.h>
 #include <linux/ftrace_irq.h>
+#include <linux/vtime.h>
 #include <asm/hardirq.h>
 
 /*
@@ -129,16 +130,6 @@ extern void synchronize_irq(unsigned int irq);
 # define synchronize_irq(irq)	barrier()
 #endif
 
-struct task_struct;
-
-#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
-static inline void vtime_account(struct task_struct *tsk)
-{
-}
-#else
-extern void vtime_account(struct task_struct *tsk);
-#endif
-
 #if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
 
 static inline void rcu_nmi_enter(void)
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 36d12f0884c3..1865b1f29770 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -7,6 +7,7 @@
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/vtime.h>
 #include <asm/irq.h>
 #include <asm/cputime.h>
 
@@ -130,12 +131,4 @@ extern void account_process_tick(struct task_struct *, int user);
 extern void account_steal_ticks(unsigned long ticks);
 extern void account_idle_ticks(unsigned long ticks);
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void vtime_task_switch(struct task_struct *prev);
-extern void vtime_account_system(struct task_struct *tsk);
-extern void vtime_account_idle(struct task_struct *tsk);
-#else
-static inline void vtime_task_switch(struct task_struct *prev) { }
-#endif
-
 #endif /* _LINUX_KERNEL_STAT_H */
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
new file mode 100644
index 000000000000..7199c24c8204
--- /dev/null
+++ b/include/linux/vtime.h
@@ -0,0 +1,22 @@
+#ifndef _LINUX_KERNEL_VTIME_H
+#define _LINUX_KERNEL_VTIME_H
+
+struct task_struct;
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void vtime_task_switch(struct task_struct *prev);
+extern void vtime_account_system(struct task_struct *tsk);
+extern void vtime_account_idle(struct task_struct *tsk);
+#else
+static inline void vtime_task_switch(struct task_struct *prev) { }
+#endif
+
+#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
+static inline void vtime_account(struct task_struct *tsk)
+{
+}
+#else
+extern void vtime_account(struct task_struct *tsk);
+#endif
+
+#endif /* _LINUX_KERNEL_VTIME_H */
-- 
cgit v1.2.3-55-g7522


From 11113334d1c5dd5355c86e531c29f1202a855c86 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Wed, 24 Oct 2012 18:05:51 +0200
Subject: vtime: Make vtime_account_system() irqsafe

vtime_account_system() currently has only one caller with
vtime_account() which is irq safe.

Now we are going to call it from other places like kvm where
irqs are not always disabled by the time we account the cputime.

So let's make it irqsafe. The arch implementation part is now
prefixed with "__".

vtime_account_idle() arch implementation is prefixed accordingly
to stay consistent.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 arch/ia64/kernel/time.c    |  8 ++++----
 arch/powerpc/kernel/time.c |  4 ++--
 arch/s390/kernel/vtime.c   |  4 ++++
 include/linux/vtime.h      |  4 +++-
 kernel/sched/cputime.c     | 16 +++++++++++++---
 5 files changed, 26 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index f6388216080d..5e4850305d3f 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -106,9 +106,9 @@ void vtime_task_switch(struct task_struct *prev)
 	struct thread_info *ni = task_thread_info(current);
 
 	if (idle_task(smp_processor_id()) != prev)
-		vtime_account_system(prev);
+		__vtime_account_system(prev);
 	else
-		vtime_account_idle(prev);
+		__vtime_account_idle(prev);
 
 	vtime_account_user(prev);
 
@@ -135,14 +135,14 @@ static cputime_t vtime_delta(struct task_struct *tsk)
 	return delta_stime;
 }
 
-void vtime_account_system(struct task_struct *tsk)
+void __vtime_account_system(struct task_struct *tsk)
 {
 	cputime_t delta = vtime_delta(tsk);
 
 	account_system_time(tsk, 0, delta, delta);
 }
 
-void vtime_account_idle(struct task_struct *tsk)
+void __vtime_account_idle(struct task_struct *tsk)
 {
 	account_idle_time(vtime_delta(tsk));
 }
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index ce4cb772dc78..0db456f30d45 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -336,7 +336,7 @@ static u64 vtime_delta(struct task_struct *tsk,
 	return delta;
 }
 
-void vtime_account_system(struct task_struct *tsk)
+void __vtime_account_system(struct task_struct *tsk)
 {
 	u64 delta, sys_scaled, stolen;
 
@@ -346,7 +346,7 @@ void vtime_account_system(struct task_struct *tsk)
 		account_steal_time(stolen);
 }
 
-void vtime_account_idle(struct task_struct *tsk)
+void __vtime_account_idle(struct task_struct *tsk)
 {
 	u64 delta, sys_scaled, stolen;
 
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 790334427895..783e988c4e1e 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -140,6 +140,10 @@ void vtime_account(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(vtime_account);
 
+void __vtime_account_system(struct task_struct *tsk)
+__attribute__((alias("vtime_account")));
+EXPORT_SYMBOL_GPL(__vtime_account_system);
+
 void __kprobes vtime_stop_cpu(void)
 {
 	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 7199c24c8204..b9fc4f9ab470 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -5,10 +5,12 @@ struct task_struct;
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 extern void vtime_task_switch(struct task_struct *prev);
+extern void __vtime_account_system(struct task_struct *tsk);
 extern void vtime_account_system(struct task_struct *tsk);
-extern void vtime_account_idle(struct task_struct *tsk);
+extern void __vtime_account_idle(struct task_struct *tsk);
 #else
 static inline void vtime_task_switch(struct task_struct *prev) { }
+static inline void vtime_account_system(struct task_struct *tsk) { }
 #endif
 
 #if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 81b763ba58a6..0359f47b0ae4 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -433,10 +433,20 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	*st = cputime.stime;
 }
 
+void vtime_account_system(struct task_struct *tsk)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__vtime_account_system(tsk);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(vtime_account_system);
+
 /*
  * Archs that account the whole time spent in the idle task
  * (outside irq) as idle time can rely on this and just implement
- * vtime_account_system() and vtime_account_idle(). Archs that
+ * __vtime_account_system() and __vtime_account_idle(). Archs that
  * have other meaning of the idle time (s390 only includes the
  * time spent by the CPU when it's in low power mode) must override
  * vtime_account().
@@ -449,9 +459,9 @@ void vtime_account(struct task_struct *tsk)
 	local_irq_save(flags);
 
 	if (in_interrupt() || !is_idle_task(tsk))
-		vtime_account_system(tsk);
+		__vtime_account_system(tsk);
 	else
-		vtime_account_idle(tsk);
+		__vtime_account_idle(tsk);
 
 	local_irq_restore(flags);
 }
-- 
cgit v1.2.3-55-g7522


From b080935c8638e08134629d0a9ebdf35669bec14d Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Fri, 5 Oct 2012 23:07:19 +0200
Subject: kvm: Directly account vtime to system on guest switch

Switching to or from guest context is done on ioctl context.
So by the time we call kvm_guest_enter() or kvm_guest_exit()
we know we are not running the idle task.

As a result, we can directly account the cputime using
vtime_account_system().

There are two good reasons to do this:

* We avoid some useless checks on guest switch. It optimizes
a bit this fast path.

* In the case of CONFIG_IRQ_TIME_ACCOUNTING, calling vtime_account()
checks for irq time to account. This is pointless since we know
we are not in an irq on guest switch. This is wasting cpu cycles
for no good reason. vtime_account_system() OTOH is a no-op in
this config option.

* We can remove the irq disable/enable around kvm guest switch in s390.

A further optimization may consist in introducing a vtime_account_guest()
that directly calls account_guest_time().

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Joerg Roedel <joerg.roedel@amd.com>
Cc: Alexander Graf <agraf@suse.de>
Cc: Xiantao Zhang <xiantao.zhang@intel.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 arch/s390/kvm/kvm-s390.c |  4 ----
 include/linux/kvm_host.h | 12 ++++++++++--
 2 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ecced9d18986..d91a95568002 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -608,9 +608,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		kvm_s390_deliver_pending_interrupts(vcpu);
 
 	vcpu->arch.sie_block->icptcode = 0;
-	local_irq_disable();
 	kvm_guest_enter();
-	local_irq_enable();
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
 	trace_kvm_s390_sie_enter(vcpu,
@@ -629,9 +627,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
 	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
-	local_irq_disable();
 	kvm_guest_exit();
-	local_irq_enable();
 
 	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
 	return rc;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 93bfc9f9815c..0e2212fe4784 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -737,7 +737,11 @@ static inline int kvm_deassign_device(struct kvm *kvm,
 static inline void kvm_guest_enter(void)
 {
 	BUG_ON(preemptible());
-	vtime_account(current);
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system(current);
 	current->flags |= PF_VCPU;
 	/* KVM does not hold any references to rcu protected data when it
 	 * switches CPU into a guest mode. In fact switching to a guest mode
@@ -751,7 +755,11 @@ static inline void kvm_guest_enter(void)
 
 static inline void kvm_guest_exit(void)
 {
-	vtime_account(current);
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system(current);
 	current->flags &= ~PF_VCPU;
 }
 
-- 
cgit v1.2.3-55-g7522


From fa5058f3b63153e0147ef65bcdb3a4ee63581346 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Sat, 6 Oct 2012 04:07:19 +0200
Subject: cputime: Specialize irq vtime hooks

With CONFIG_VIRT_CPU_ACCOUNTING, when vtime_account()
is called in irq entry/exit, we perform a check on the
context: if we are interrupting the idle task we
account the pending cputime to idle, otherwise account
to system time or its sub-areas: tsk->stime, hardirq time,
softirq time, ...

However this check for idle only concerns the hardirq entry
and softirq entry:

* Hardirq may directly interrupt the idle task, in which case
we need to flush the pending CPU time to idle.

* The idle task may be directly interrupted by a softirq if
it calls local_bh_enable(). There is probably no such call
in any idle task but we need to cover every case. Ksoftirqd
is not concerned because the idle time is flushed on context
switch and softirq in the end of hardirq have the idle time
already flushed from the hardirq entry.

In the other cases we always account to system/irq time:

* On hardirq exit we account the time to hardirq time.
* On softirq exit we account the time to softirq time.

To optimize this and avoid the indirect call to vtime_account()
and the checks it performs, specialize the vtime irq APIs and
only perform the check on irq entry. Irq exit can directly call
vtime_account_system().

CONFIG_IRQ_TIME_ACCOUNTING behaviour doesn't change and directly
maps to its own vtime_account() implementation. One may want
to take benefits from the new APIs to optimize irq time accounting
as well in the future.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 include/linux/hardirq.h |  4 ++--
 include/linux/vtime.h   | 25 +++++++++++++++++++++++++
 kernel/softirq.c        |  6 +++---
 3 files changed, 30 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index b083a475423d..624ef3f45c8e 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -153,7 +153,7 @@ extern void rcu_nmi_exit(void);
  */
 #define __irq_enter()					\
 	do {						\
-		vtime_account(current);		\
+		vtime_account_irq_enter(current);	\
 		add_preempt_count(HARDIRQ_OFFSET);	\
 		trace_hardirq_enter();			\
 	} while (0)
@@ -169,7 +169,7 @@ extern void irq_enter(void);
 #define __irq_exit()					\
 	do {						\
 		trace_hardirq_exit();			\
-		vtime_account(current);		\
+		vtime_account_irq_exit(current);	\
 		sub_preempt_count(HARDIRQ_OFFSET);	\
 	} while (0)
 
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index b9fc4f9ab470..c35c02223da8 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -21,4 +21,29 @@ static inline void vtime_account(struct task_struct *tsk)
 extern void vtime_account(struct task_struct *tsk);
 #endif
 
+static inline void vtime_account_irq_enter(struct task_struct *tsk)
+{
+	/*
+	 * Hardirq can interrupt idle task anytime. So we need vtime_account()
+	 * that performs the idle check in CONFIG_VIRT_CPU_ACCOUNTING.
+	 * Softirq can also interrupt idle task directly if it calls
+	 * local_bh_enable(). Such case probably don't exist but we never know.
+	 * Ksoftirqd is not concerned because idle time is flushed on context
+	 * switch. Softirqs in the end of hardirqs are also not a problem because
+	 * the idle time is flushed on hardirq time already.
+	 */
+	vtime_account(tsk);
+}
+
+static inline void vtime_account_irq_exit(struct task_struct *tsk)
+{
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	/* On hard|softirq exit we always account to hard|softirq cputime */
+	__vtime_account_system(tsk);
+#endif
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	vtime_account(tsk);
+#endif
+}
+
 #endif /* _LINUX_KERNEL_VTIME_H */
diff --git a/kernel/softirq.c b/kernel/softirq.c
index cc96bdc0c2c9..ed567babe789 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -221,7 +221,7 @@ asmlinkage void __do_softirq(void)
 	current->flags &= ~PF_MEMALLOC;
 
 	pending = local_softirq_pending();
-	vtime_account(current);
+	vtime_account_irq_enter(current);
 
 	__local_bh_disable((unsigned long)__builtin_return_address(0),
 				SOFTIRQ_OFFSET);
@@ -272,7 +272,7 @@ restart:
 
 	lockdep_softirq_exit();
 
-	vtime_account(current);
+	vtime_account_irq_exit(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
@@ -341,7 +341,7 @@ static inline void invoke_softirq(void)
  */
 void irq_exit(void)
 {
-	vtime_account(current);
+	vtime_account_irq_exit(current);
 	trace_hardirq_exit();
 	sub_preempt_count(IRQ_EXIT_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
-- 
cgit v1.2.3-55-g7522


From 3e1df4f506836e6bea1ab61cf88c75c8b1840643 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Sat, 6 Oct 2012 05:23:22 +0200
Subject: cputime: Separate irqtime accounting from generic vtime

vtime_account() doesn't have the same role in
CONFIG_VIRT_CPU_ACCOUNTING and CONFIG_IRQ_TIME_ACCOUNTING.

In the first case it handles time accounting in any context. In
the second case it only handles irq time accounting.

So when vtime_account() is called from outside vtime_account_irq_*()
this call is pointless to CONFIG_IRQ_TIME_ACCOUNTING.

To fix the confusion, change vtime_account() to irqtime_account_irq()
in CONFIG_IRQ_TIME_ACCOUNTING. This way we ensure future account_vtime()
calls won't waste useless cycles in the irqtime APIs.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 include/linux/vtime.h  | 18 ++++++++----------
 kernel/sched/cputime.c |  4 ++--
 2 files changed, 10 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index c35c02223da8..0c2a2d303020 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -8,17 +8,18 @@ extern void vtime_task_switch(struct task_struct *prev);
 extern void __vtime_account_system(struct task_struct *tsk);
 extern void vtime_account_system(struct task_struct *tsk);
 extern void __vtime_account_idle(struct task_struct *tsk);
+extern void vtime_account(struct task_struct *tsk);
 #else
 static inline void vtime_task_switch(struct task_struct *prev) { }
+static inline void __vtime_account_system(struct task_struct *tsk) { }
 static inline void vtime_account_system(struct task_struct *tsk) { }
+static inline void vtime_account(struct task_struct *tsk) { }
 #endif
 
-#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
-static inline void vtime_account(struct task_struct *tsk)
-{
-}
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+extern void irqtime_account_irq(struct task_struct *tsk);
 #else
-extern void vtime_account(struct task_struct *tsk);
+static inline void irqtime_account_irq(struct task_struct *tsk) { }
 #endif
 
 static inline void vtime_account_irq_enter(struct task_struct *tsk)
@@ -33,17 +34,14 @@ static inline void vtime_account_irq_enter(struct task_struct *tsk)
 	 * the idle time is flushed on hardirq time already.
 	 */
 	vtime_account(tsk);
+	irqtime_account_irq(tsk);
 }
 
 static inline void vtime_account_irq_exit(struct task_struct *tsk)
 {
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
 	/* On hard|softirq exit we always account to hard|softirq cputime */
 	__vtime_account_system(tsk);
-#endif
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-	vtime_account(tsk);
-#endif
+	irqtime_account_irq(tsk);
 }
 
 #endif /* _LINUX_KERNEL_VTIME_H */
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 0359f47b0ae4..8d859dae5bed 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -43,7 +43,7 @@ DEFINE_PER_CPU(seqcount_t, irq_time_seq);
  * Called before incrementing preempt_count on {soft,}irq_enter
  * and before decrementing preempt_count on {soft,}irq_exit.
  */
-void vtime_account(struct task_struct *curr)
+void irqtime_account_irq(struct task_struct *curr)
 {
 	unsigned long flags;
 	s64 delta;
@@ -73,7 +73,7 @@ void vtime_account(struct task_struct *curr)
 	irq_time_write_end();
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(vtime_account);
+EXPORT_SYMBOL_GPL(irqtime_account_irq);
 
 static int irqtime_account_hi_update(void)
 {
-- 
cgit v1.2.3-55-g7522


From 81c52c56e2b43589091ee29038bcf793d3f184ab Mon Sep 17 00:00:00 2001
From: Xiao Guangrong
Date: Tue, 16 Oct 2012 20:10:59 +0800
Subject: KVM: do not treat noslot pfn as a error pfn

This patch filters noslot pfn out from error pfns based on Marcelo comment:
noslot pfn is not a error pfn

After this patch,
- is_noslot_pfn indicates that the gfn is not in slot
- is_error_pfn indicates that the gfn is in slot but the error is occurred
  when translate the gfn to pfn
- is_error_noslot_pfn indicates that the pfn either it is error pfns or it
  is noslot pfn
And is_invalid_pfn can be removed, it makes the code more clean

Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/powerpc/kvm/book3s_32_mmu_host.c |  2 +-
 arch/powerpc/kvm/book3s_64_mmu_host.c |  2 +-
 arch/powerpc/kvm/e500_tlb.c           |  2 +-
 arch/x86/kvm/mmu.c                    |  4 ++--
 arch/x86/kvm/paging_tmpl.h            |  2 +-
 arch/x86/kvm/x86.c                    |  2 +-
 include/linux/kvm_host.h              | 28 ++++++++++++++++++++--------
 virt/kvm/iommu.c                      |  4 ++--
 virt/kvm/kvm_main.c                   |  6 +++---
 9 files changed, 32 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index d1107a9b5d13..00e619bf608e 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -155,7 +155,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 
 	/* Get host physical address for gpa */
 	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
-	if (is_error_pfn(hpaddr)) {
+	if (is_error_noslot_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n",
 				 orig_pte->eaddr);
 		r = -EINVAL;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index d0205a545a81..ead58e317294 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -93,7 +93,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 
 	/* Get host physical address for gpa */
 	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
-	if (is_error_pfn(hpaddr)) {
+	if (is_error_noslot_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
 		r = -EINVAL;
 		goto out;
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index c73389477d17..6305ee692ef7 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -524,7 +524,7 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	if (likely(!pfnmap)) {
 		unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
 		pfn = gfn_to_pfn_memslot(slot, gfn);
-		if (is_error_pfn(pfn)) {
+		if (is_error_noslot_pfn(pfn)) {
 			printk(KERN_ERR "Couldn't get real page for gfn %lx!\n",
 					(long)gfn);
 			return;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index aabb1289ff04..b875a9ed9b8e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2699,7 +2699,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	 * PT_PAGE_TABLE_LEVEL and there would be no adjustment done
 	 * here.
 	 */
-	if (!is_error_pfn(pfn) && !kvm_is_mmio_pfn(pfn) &&
+	if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn) &&
 	    level == PT_PAGE_TABLE_LEVEL &&
 	    PageTransCompound(pfn_to_page(pfn)) &&
 	    !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) {
@@ -2733,7 +2733,7 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 	bool ret = true;
 
 	/* The pfn is invalid, report the error! */
-	if (unlikely(is_invalid_pfn(pfn))) {
+	if (unlikely(is_error_pfn(pfn))) {
 		*ret_val = kvm_handle_bad_page(vcpu, gfn, pfn);
 		goto exit;
 	}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index d17decaf1db9..891eb6d93b8b 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -323,7 +323,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	protect_clean_gpte(&pte_access, gpte);
 	pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
 			no_dirty_log && (pte_access & ACC_WRITE_MASK));
-	if (is_invalid_pfn(pfn))
+	if (is_error_pfn(pfn))
 		return false;
 
 	/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6e5f069bee30..49fa1f0e59bd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4504,7 +4504,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
 	 * instruction -> ...
 	 */
 	pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa));
-	if (!is_error_pfn(pfn)) {
+	if (!is_error_noslot_pfn(pfn)) {
 		kvm_release_pfn_clean(pfn);
 		return true;
 	}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 82e2c783a21e..99a47627e046 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -58,28 +58,40 @@
 
 /*
  * For the normal pfn, the highest 12 bits should be zero,
- * so we can mask these bits to indicate the error.
+ * so we can mask bit 62 ~ bit 52  to indicate the error pfn,
+ * mask bit 63 to indicate the noslot pfn.
  */
-#define KVM_PFN_ERR_MASK	(0xfffULL << 52)
+#define KVM_PFN_ERR_MASK	(0x7ffULL << 52)
+#define KVM_PFN_ERR_NOSLOT_MASK	(0xfffULL << 52)
+#define KVM_PFN_NOSLOT		(0x1ULL << 63)
 
 #define KVM_PFN_ERR_FAULT	(KVM_PFN_ERR_MASK)
 #define KVM_PFN_ERR_HWPOISON	(KVM_PFN_ERR_MASK + 1)
-#define KVM_PFN_ERR_BAD		(KVM_PFN_ERR_MASK + 2)
-#define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 3)
+#define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 2)
 
+/*
+ * error pfns indicate that the gfn is in slot but faild to
+ * translate it to pfn on host.
+ */
 static inline bool is_error_pfn(pfn_t pfn)
 {
 	return !!(pfn & KVM_PFN_ERR_MASK);
 }
 
-static inline bool is_noslot_pfn(pfn_t pfn)
+/*
+ * error_noslot pfns indicate that the gfn can not be
+ * translated to pfn - it is not in slot or failed to
+ * translate it to pfn.
+ */
+static inline bool is_error_noslot_pfn(pfn_t pfn)
 {
-	return pfn == KVM_PFN_ERR_BAD;
+	return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK);
 }
 
-static inline bool is_invalid_pfn(pfn_t pfn)
+/* noslot pfn indicates that the gfn is not in slot. */
+static inline bool is_noslot_pfn(pfn_t pfn)
 {
-	return !is_noslot_pfn(pfn) && is_error_pfn(pfn);
+	return pfn == KVM_PFN_NOSLOT;
 }
 
 #define KVM_HVA_ERR_BAD		(PAGE_OFFSET)
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 18e1e30019e3..4a340cb23013 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -52,7 +52,7 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
 	end_gfn = gfn + (size >> PAGE_SHIFT);
 	gfn    += 1;
 
-	if (is_error_pfn(pfn))
+	if (is_error_noslot_pfn(pfn))
 		return pfn;
 
 	while (gfn < end_gfn)
@@ -106,7 +106,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 		 * important because we unmap and unpin in 4kb steps later.
 		 */
 		pfn = kvm_pin_pages(slot, gfn, page_size);
-		if (is_error_pfn(pfn)) {
+		if (is_error_noslot_pfn(pfn)) {
 			gfn += 1;
 			continue;
 		}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index be70035fd42a..2fb73191801f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1208,7 +1208,7 @@ __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic,
 		return KVM_PFN_ERR_RO_FAULT;
 
 	if (kvm_is_error_hva(addr))
-		return KVM_PFN_ERR_BAD;
+		return KVM_PFN_NOSLOT;
 
 	/* Do not map writable pfn in the readonly memslot. */
 	if (writable && memslot_is_readonly(slot)) {
@@ -1290,7 +1290,7 @@ EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
 
 static struct page *kvm_pfn_to_page(pfn_t pfn)
 {
-	if (is_error_pfn(pfn))
+	if (is_error_noslot_pfn(pfn))
 		return KVM_ERR_PTR_BAD_PAGE;
 
 	if (kvm_is_mmio_pfn(pfn)) {
@@ -1322,7 +1322,7 @@ EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(pfn_t pfn)
 {
-	if (!is_error_pfn(pfn) && !kvm_is_mmio_pfn(pfn))
+	if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn))
 		put_page(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
-- 
cgit v1.2.3-55-g7522


From 37c67d03989eca60b28d67398d9388f653454c5d Mon Sep 17 00:00:00 2001
From: Paul Walmsley
Date: Mon, 29 Oct 2012 20:49:44 -0600
Subject: ARM: OMAP2+: WDT: move init; add read_reset_sources pdata function
 pointer

The OMAP watchdog timer driver directly calls a function exported by
code in arch/arm/mach-omap2.  This is not good; it tightly couples
this driver to the mach-omap2 integration code.  Instead, add a
temporary platform_data function pointer to abstract this function
call.  A subsequent patch will convert the watchdog driver to use this
function pointer.

This patch also moves the device creation code out of
arch/arm/mach-omap2/devices.c and into arch/arm/mach-omap2/wd_timer.c.
This is another step towards the removal of
arch/arm/mach-omap2/devices.c.

Cc: Wim Van Sebroeck <wim@iguana.be>
Acked-by: Wim Van Sebroeck <wim@iguana.be>
[paul@pwsan.com: skip wd_timer device creation when DT blob is present]
Signed-off-by: Paul Walmsley <paul@pwsan.com>
---
 arch/arm/mach-omap1/devices.c               | 21 +++++++++++++---
 arch/arm/mach-omap2/devices.c               | 26 --------------------
 arch/arm/mach-omap2/wd_timer.c              | 35 +++++++++++++++++++++++++-
 include/linux/platform_data/omap-wd-timer.h | 38 +++++++++++++++++++++++++++++
 4 files changed, 90 insertions(+), 30 deletions(-)
 create mode 100644 include/linux/platform_data/omap-wd-timer.h

(limited to 'include')

diff --git a/arch/arm/mach-omap1/devices.c b/arch/arm/mach-omap1/devices.c
index 645668e2b1d5..745031870ce4 100644
--- a/arch/arm/mach-omap1/devices.c
+++ b/arch/arm/mach-omap1/devices.c
@@ -17,6 +17,8 @@
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
 
+#include <linux/platform_data/omap-wd-timer.h>
+
 #include <asm/mach/map.h>
 
 #include <mach/tc.h>
@@ -448,18 +450,31 @@ static struct resource wdt_resources[] = {
 };
 
 static struct platform_device omap_wdt_device = {
-	.name	   = "omap_wdt",
-	.id	     = -1,
+	.name		= "omap_wdt",
+	.id		= -1,
 	.num_resources	= ARRAY_SIZE(wdt_resources),
 	.resource	= wdt_resources,
 };
 
 static int __init omap_init_wdt(void)
 {
+	struct omap_wd_timer_platform_data pdata;
+	int ret;
+
 	if (!cpu_is_omap16xx())
 		return -ENODEV;
 
-	return platform_device_register(&omap_wdt_device);
+	pdata.read_reset_sources = omap1_get_reset_sources;
+
+	ret = platform_device_register(&omap_wdt_device);
+	if (!ret) {
+		ret = platform_device_add_data(&omap_wdt_device, &pdata,
+					       sizeof(pdata));
+		if (ret)
+			platform_device_del(&omap_wdt_device);
+	}
+
+	return ret;
 }
 subsys_initcall(omap_init_wdt);
 #endif
diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index 2ad491d6910b..cf365c387c06 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -646,29 +646,3 @@ static int __init omap2_init_devices(void)
 	return 0;
 }
 arch_initcall(omap2_init_devices);
-
-#if defined(CONFIG_OMAP_WATCHDOG) || defined(CONFIG_OMAP_WATCHDOG_MODULE)
-static int __init omap_init_wdt(void)
-{
-	int id = -1;
-	struct platform_device *pdev;
-	struct omap_hwmod *oh;
-	char *oh_name = "wd_timer2";
-	char *dev_name = "omap_wdt";
-
-	if (!cpu_class_is_omap2() || of_have_populated_dt())
-		return 0;
-
-	oh = omap_hwmod_lookup(oh_name);
-	if (!oh) {
-		pr_err("Could not look up wd_timer%d hwmod\n", id);
-		return -EINVAL;
-	}
-
-	pdev = omap_device_build(dev_name, id, oh, NULL, 0, NULL, 0, 0);
-	WARN(IS_ERR(pdev), "Can't build omap_device for %s:%s.\n",
-				dev_name, oh->name);
-	return 0;
-}
-subsys_initcall(omap_init_wdt);
-#endif
diff --git a/arch/arm/mach-omap2/wd_timer.c b/arch/arm/mach-omap2/wd_timer.c
index f6b6c37ac3f4..5a8629ff0ab0 100644
--- a/arch/arm/mach-omap2/wd_timer.c
+++ b/arch/arm/mach-omap2/wd_timer.c
@@ -11,10 +11,14 @@
 #include <linux/io.h>
 #include <linux/err.h>
 
-#include "omap_hwmod.h"
+#include <linux/platform_data/omap-wd-timer.h>
 
+#include "omap_hwmod.h"
+#include "omap_device.h"
 #include "wd_timer.h"
 #include "common.h"
+#include "prm.h"
+#include "soc.h"
 
 /*
  * In order to avoid any assumptions from bootloader regarding WDT
@@ -99,3 +103,32 @@ int omap2_wd_timer_reset(struct omap_hwmod *oh)
 	return (c == MAX_MODULE_SOFTRESET_WAIT) ? -ETIMEDOUT :
 		omap2_wd_timer_disable(oh);
 }
+
+static int __init omap_init_wdt(void)
+{
+	int id = -1;
+	struct platform_device *pdev;
+	struct omap_hwmod *oh;
+	char *oh_name = "wd_timer2";
+	char *dev_name = "omap_wdt";
+	struct omap_wd_timer_platform_data pdata;
+
+	if (!cpu_class_is_omap2() || of_have_populated_dt())
+		return 0;
+
+	oh = omap_hwmod_lookup(oh_name);
+	if (!oh) {
+		pr_err("Could not look up wd_timer%d hwmod\n", id);
+		return -EINVAL;
+	}
+
+	pdata.read_reset_sources = prm_read_reset_sources;
+
+	pdev = omap_device_build(dev_name, id, oh, &pdata,
+				 sizeof(struct omap_wd_timer_platform_data),
+				 NULL, 0, 0);
+	WARN(IS_ERR(pdev), "Can't build omap_device for %s:%s.\n",
+	     dev_name, oh->name);
+	return 0;
+}
+subsys_initcall(omap_init_wdt);
diff --git a/include/linux/platform_data/omap-wd-timer.h b/include/linux/platform_data/omap-wd-timer.h
new file mode 100644
index 000000000000..d75f5f802d98
--- /dev/null
+++ b/include/linux/platform_data/omap-wd-timer.h
@@ -0,0 +1,38 @@
+/*
+ * OMAP2+ WDTIMER-specific function prototypes
+ *
+ * Copyright (C) 2012 Texas Instruments, Inc.
+ * Paul Walmsley
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_PLATFORM_DATA_OMAP_WD_TIMER_H
+#define __LINUX_PLATFORM_DATA_OMAP_WD_TIMER_H
+
+#include <linux/types.h>
+
+/*
+ * Standardized OMAP reset source bits
+ *
+ * This is a subset of the ones listed in arch/arm/mach-omap2/prm.h
+ * and are the only ones needed in the watchdog driver.
+ */
+#define OMAP_MPU_WD_RST_SRC_ID_SHIFT				3
+
+/**
+ * struct omap_wd_timer_platform_data - WDTIMER integration to the host SoC
+ * @read_reset_sources - fn ptr for the SoC to indicate the last reset cause
+ *
+ * The function pointed to by @read_reset_sources must return its data
+ * in a standard format - search for RST_SRC_ID_SHIFT in
+ * arch/arm/mach-omap2
+ */
+struct omap_wd_timer_platform_data {
+	u32 (*read_reset_sources)(void);
+};
+
+#endif
-- 
cgit v1.2.3-55-g7522


From b3343a2a2c95b3b7ed4f6596e860c4276ba46217 Mon Sep 17 00:00:00 2001
From: John Fastabend
Date: Tue, 18 Sep 2012 00:01:12 +0000
Subject: net, ixgbe: handle link local multicast addresses in SR-IOV mode

In SR-IOV mode the PF driver acts as the uplink port and is
used to send control packets e.g. lldpad, stp, etc.

   eth0.1     eth0.2     eth0
   VF         VF         PF
   |          |          |   <-- stand-in for uplink
   |          |          |
  --------------------------
  |  Embedded Switch       |
  --------------------------
              |
             MAC   <-- uplink

But the embedded switch is setup to forward multicast addresses
to all interfaces both VFs and PF and onto the physical link.
This results in reserved MAC addresses used by control protocols
to be forwarded over the switch onto the VF.

In the LLDP case the PF sends an LLDPDU and it is currently
being forwarded to all the VFs who then see the PF as a peer.
This is incorrect.

This patch adds the multicast addresses to the RAR table in the
hardware to prevent this behavior.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Tested-by: Sibai Li <sibai.li@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |  2 +-
 drivers/net/ethernet/intel/ixgbevf/vf.c       |  3 +++
 include/linux/etherdevice.h                   | 19 +++++++++++++++++++
 net/bridge/br_device.c                        |  2 +-
 net/bridge/br_input.c                         | 15 ---------------
 net/bridge/br_private.h                       |  1 -
 net/bridge/br_sysfs_br.c                      |  3 ++-
 7 files changed, 26 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 88d636a7459c..97bab45ed95f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6967,7 +6967,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		return -EINVAL;
 	}
 
-	if (is_unicast_ether_addr(addr)) {
+	if (is_unicast_ether_addr(addr) || is_link_local(addr)) {
 		u32 rar_uc_entries = IXGBE_MAX_PF_MACVLANS;
 
 		if (netdev_uc_count(dev) < rar_uc_entries)
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index 5fa397b953eb..c0fd1ef49400 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -331,6 +331,9 @@ static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw,
 	netdev_for_each_mc_addr(ha, netdev) {
 		if (i == cnt)
 			break;
+		if (is_link_local(ha->addr))
+			continue;
+
 		vector_list[i++] = ixgbevf_mta_vector(hw, ha->addr);
 	}
 
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index b006ba0a9f42..45ded4be7b43 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -51,6 +51,25 @@ extern struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
 #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1)
 #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count)
 
+/* Reserved Ethernet Addresses per IEEE 802.1Q */
+static const u8 br_reserved_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
+
+/**
+ * is_link_local -  Determine if given Eth addr is a link local mcast address.
+ * @addr: Pointer to a six-byte array containing the Ethernet address
+ *
+ * Return true if address is link local reserved addr (01:80:c2:00:00:0X) per
+ * IEEE 802.1Q 8.6.3 Frame filtering.
+ */
+static inline int is_link_local(const unsigned char *dest)
+{
+	__be16 *a = (__be16 *)dest;
+	static const __be16 *b = (const __be16 *)br_reserved_address;
+	static const __be16 m = cpu_to_be16(0xfff0);
+
+	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0;
+}
+
 /**
  * is_zero_ether_addr - Determine if give Ethernet address is all zeros.
  * @addr: Pointer to a six-byte array containing the Ethernet address
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 070e8a68cfc6..d41b6f9698d7 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -356,7 +356,7 @@ void br_dev_setup(struct net_device *dev)
 	br->bridge_id.prio[0] = 0x80;
 	br->bridge_id.prio[1] = 0x00;
 
-	memcpy(br->group_addr, br_group_address, ETH_ALEN);
+	memcpy(br->group_addr, br_reserved_address, ETH_ALEN);
 
 	br->stp_enabled = BR_NO_STP;
 	br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 76f15fda0212..d047978bf025 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -19,9 +19,6 @@
 #include <linux/export.h>
 #include "br_private.h"
 
-/* Bridge group multicast address 802.1d (pg 51). */
-const u8 br_group_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
-
 /* Hook for brouter */
 br_should_route_hook_t __rcu *br_should_route_hook __read_mostly;
 EXPORT_SYMBOL(br_should_route_hook);
@@ -127,18 +124,6 @@ static int br_handle_local_finish(struct sk_buff *skb)
 	return 0;	 /* process further */
 }
 
-/* Does address match the link local multicast address.
- * 01:80:c2:00:00:0X
- */
-static inline int is_link_local(const unsigned char *dest)
-{
-	__be16 *a = (__be16 *)dest;
-	static const __be16 *b = (const __be16 *)br_group_address;
-	static const __be16 m = cpu_to_be16(0xfff0);
-
-	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0;
-}
-
 /*
  * Return NULL if skb is handled
  * note: already called with rcu_read_lock
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 9b278c4ebee1..65b191a05dd6 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -288,7 +288,6 @@ struct br_input_skb_cb {
 	pr_debug("%s: " format,  (br)->dev->name, ##args)
 
 extern struct notifier_block br_device_notifier;
-extern const u8 br_group_address[ETH_ALEN];
 
 /* called under bridge lock */
 static inline int br_is_root_bridge(const struct net_bridge *br)
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index c5c059333eab..e157b0dbcd82 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -14,6 +14,7 @@
 #include <linux/capability.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
+#include <linux/etherdevice.h>
 #include <linux/if_bridge.h>
 #include <linux/rtnetlink.h>
 #include <linux/spinlock.h>
@@ -310,7 +311,7 @@ static ssize_t store_group_addr(struct device *d,
 
 	/* Must be 01:80:c2:00:00:0X */
 	for (i = 0; i < 5; i++)
-		if (new_addr[i] != br_group_address[i])
+		if (new_addr[i] != br_reserved_address[i])
 			return -EINVAL;
 
 	if (new_addr[5] & ~0xf)
-- 
cgit v1.2.3-55-g7522


From 02b91b55260f7a1bdc8da25866cf27f726f5788f Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Thu, 28 Jun 2012 18:26:52 +0200
Subject: drbd: introduce stop-sector to online verify

We now can schedule only a specific range of sectors for online verify,
or interrupt a running verify without interrupting the connection.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_int.h      |  1 +
 drivers/block/drbd/drbd_main.c     | 17 +++++++++++++----
 drivers/block/drbd/drbd_nl.c       | 11 +++++++----
 drivers/block/drbd/drbd_proc.c     | 12 +++++++++---
 drivers/block/drbd/drbd_receiver.c |  8 ++++++++
 drivers/block/drbd/drbd_worker.c   | 33 +++++++++++++++++++++++++++------
 include/linux/drbd.h               |  2 +-
 include/linux/drbd_nl.h            |  1 +
 8 files changed, 67 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 9a6d3a4a739a..3cce7357402b 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1052,6 +1052,7 @@ struct drbd_conf {
 
 	/* where does the admin want us to start? (sector) */
 	sector_t ov_start_sector;
+	sector_t ov_stop_sector;
 	/* where are we now? (sector) */
 	sector_t ov_position;
 	/* Start sector of out of sync range (to merge printk reporting). */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index dfa08b7411c0..df9965d820c9 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1231,13 +1231,15 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
 	wake_up(&mdev->misc_wait);
 	wake_up(&mdev->state_wait);
 
-	/* aborted verify run. log the last position */
+	/* Aborted verify run, or we reached the stop sector.
+	 * Log the last position, unless end-of-device. */
 	if ((os.conn == C_VERIFY_S || os.conn == C_VERIFY_T) &&
-	    ns.conn < C_CONNECTED) {
+	    ns.conn <= C_CONNECTED) {
 		mdev->ov_start_sector =
 			BM_BIT_TO_SECT(drbd_bm_bits(mdev) - mdev->ov_left);
-		dev_info(DEV, "Online Verify reached sector %llu\n",
-			(unsigned long long)mdev->ov_start_sector);
+		if (mdev->ov_left)
+			dev_info(DEV, "Online Verify reached sector %llu\n",
+				(unsigned long long)mdev->ov_start_sector);
 	}
 
 	if ((os.conn == C_PAUSED_SYNC_T || os.conn == C_PAUSED_SYNC_S) &&
@@ -1703,6 +1705,13 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 	if (os.disk < D_UP_TO_DATE && os.conn >= C_SYNC_SOURCE && ns.conn == C_CONNECTED)
 		drbd_send_state(mdev, ns);
 
+	/* Verify finished, or reached stop sector.  Peer did not know about
+	 * the stop sector, and we may even have changed the stop sector during
+	 * verify to interrupt/stop early.  Send the new state. */
+	if (os.conn == C_VERIFY_S && ns.conn == C_CONNECTED
+	&& mdev->agreed_pro_version >= 97)
+		drbd_send_state(mdev, ns);
+
 	/* Wake up role changes, that were delayed because of connection establishing */
 	if (os.conn == C_WF_REPORT_PARAMS && ns.conn != C_WF_REPORT_PARAMS) {
 		clear_bit(STATE_SENT, &mdev->flags);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index ab660556a001..e2d368f1747e 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2211,8 +2211,10 @@ static int drbd_nl_start_ov(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
 				    struct drbd_nl_cfg_reply *reply)
 {
 	/* default to resume from last known position, if possible */
-	struct start_ov args =
-		{ .start_sector = mdev->ov_start_sector };
+	struct start_ov args = {
+		.start_sector = mdev->ov_start_sector,
+		.stop_sector = ULLONG_MAX,
+	};
 
 	if (!start_ov_from_tags(mdev, nlp->tag_list, &args)) {
 		reply->ret_code = ERR_MANDATORY_TAG;
@@ -2224,8 +2226,9 @@ static int drbd_nl_start_ov(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
 	drbd_suspend_io(mdev);
 	wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
 
-	/* w_make_ov_request expects position to be aligned */
-	mdev->ov_start_sector = args.start_sector & ~BM_SECT_PER_BIT;
+	/* w_make_ov_request expects start position to be aligned */
+	mdev->ov_start_sector = args.start_sector & ~(BM_SECT_PER_BIT-1);
+	mdev->ov_stop_sector = args.stop_sector;
 	reply->ret_code = drbd_request_state(mdev,NS(conn,C_VERIFY_S));
 	drbd_resume_io(mdev);
 	return 0;
diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c
index 5496104f90b9..a5a453b4355f 100644
--- a/drivers/block/drbd/drbd_proc.c
+++ b/drivers/block/drbd/drbd_proc.c
@@ -167,18 +167,24 @@ static void drbd_syncer_progress(struct drbd_conf *mdev, struct seq_file *seq)
 		 * we convert to sectors in the display below. */
 		unsigned long bm_bits = drbd_bm_bits(mdev);
 		unsigned long bit_pos;
+		unsigned long long stop_sector = 0;
 		if (mdev->state.conn == C_VERIFY_S ||
-		    mdev->state.conn == C_VERIFY_T)
+		    mdev->state.conn == C_VERIFY_T) {
 			bit_pos = bm_bits - mdev->ov_left;
-		else
+			if (mdev->agreed_pro_version >= 97)
+				stop_sector = mdev->ov_stop_sector;
+		} else
 			bit_pos = mdev->bm_resync_fo;
 		/* Total sectors may be slightly off for oddly
 		 * sized devices. So what. */
 		seq_printf(seq,
-			"\t%3d%% sector pos: %llu/%llu\n",
+			"\t%3d%% sector pos: %llu/%llu",
 			(int)(bit_pos / (bm_bits/100+1)),
 			(unsigned long long)bit_pos * BM_SECT_PER_BIT,
 			(unsigned long long)bm_bits * BM_SECT_PER_BIT);
+		if (stop_sector != 0 && stop_sector != ULLONG_MAX)
+			seq_printf(seq, " stop sector: %llu", stop_sector);
+		seq_printf(seq, "\n");
 	}
 }
 
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 434adf75259a..280735da1963 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -3255,6 +3255,14 @@ static int receive_state(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
 		}
 	}
 
+	/* explicit verify finished notification, stop sector reached. */
+	if (os.conn == C_VERIFY_T && os.disk == D_UP_TO_DATE &&
+	    peer_state.conn == C_CONNECTED && real_peer_disk == D_UP_TO_DATE) {
+		ov_oos_print(mdev);
+		drbd_resync_finished(mdev);
+		return true;
+	}
+
 	/* peer says his disk is inconsistent, while we think it is uptodate,
 	 * and this happens while the peer still thinks we have a sync going on,
 	 * but we think we are already done with the sync.
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 6bce2cc179d4..1352455dd7dd 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -691,6 +691,7 @@ static int w_make_ov_request(struct drbd_conf *mdev, struct drbd_work *w, int ca
 	int number, i, size;
 	sector_t sector;
 	const sector_t capacity = drbd_get_capacity(mdev->this_bdev);
+	bool stop_sector_reached = false;
 
 	if (unlikely(cancel))
 		return 1;
@@ -699,9 +700,17 @@ static int w_make_ov_request(struct drbd_conf *mdev, struct drbd_work *w, int ca
 
 	sector = mdev->ov_position;
 	for (i = 0; i < number; i++) {
-		if (sector >= capacity) {
+		if (sector >= capacity)
 			return 1;
-		}
+
+		/* We check for "finished" only in the reply path:
+		 * w_e_end_ov_reply().
+		 * We need to send at least one request out. */
+		stop_sector_reached = i > 0
+			&& mdev->agreed_pro_version >= 97
+			&& sector >= mdev->ov_stop_sector;
+		if (stop_sector_reached)
+			break;
 
 		size = BM_BLOCK_SIZE;
 
@@ -725,7 +734,8 @@ static int w_make_ov_request(struct drbd_conf *mdev, struct drbd_work *w, int ca
 
  requeue:
 	mdev->rs_in_flight += (i << (BM_BLOCK_SHIFT - 9));
-	mod_timer(&mdev->resync_timer, jiffies + SLEEP_TIME);
+	if (i == 0 || !stop_sector_reached)
+		mod_timer(&mdev->resync_timer, jiffies + SLEEP_TIME);
 	return 1;
 }
 
@@ -808,7 +818,12 @@ int drbd_resync_finished(struct drbd_conf *mdev)
 	dt = (jiffies - mdev->rs_start - mdev->rs_paused) / HZ;
 	if (dt <= 0)
 		dt = 1;
+	
 	db = mdev->rs_total;
+	/* adjust for verify start and stop sectors, respective reached position */
+	if (mdev->state.conn == C_VERIFY_S || mdev->state.conn == C_VERIFY_T)
+		db -= mdev->ov_left;
+
 	dbdt = Bit2KB(db/dt);
 	mdev->rs_paused /= HZ;
 
@@ -831,7 +846,7 @@ int drbd_resync_finished(struct drbd_conf *mdev)
 	ns.conn = C_CONNECTED;
 
 	dev_info(DEV, "%s done (total %lu sec; paused %lu sec; %lu K/sec)\n",
-	     verify_done ? "Online verify " : "Resync",
+	     verify_done ? "Online verify" : "Resync",
 	     dt + mdev->rs_paused, mdev->rs_paused, dbdt);
 
 	n_oos = drbd_bm_total_weight(mdev);
@@ -912,7 +927,9 @@ out:
 	mdev->rs_total  = 0;
 	mdev->rs_failed = 0;
 	mdev->rs_paused = 0;
-	if (verify_done)
+
+	/* reset start sector, if we reached end of device */
+	if (verify_done && mdev->ov_left == 0)
 		mdev->ov_start_sector = 0;
 
 	drbd_md_sync(mdev);
@@ -1158,6 +1175,7 @@ int w_e_end_ov_reply(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
 	unsigned int size = e->size;
 	int digest_size;
 	int ok, eq = 0;
+	bool stop_sector_reached = false;
 
 	if (unlikely(cancel)) {
 		drbd_free_ee(mdev, e);
@@ -1208,7 +1226,10 @@ int w_e_end_ov_reply(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
 	if ((mdev->ov_left & 0x200) == 0x200)
 		drbd_advance_rs_marks(mdev, mdev->ov_left);
 
-	if (mdev->ov_left == 0) {
+	stop_sector_reached = mdev->agreed_pro_version >= 97 &&
+		(sector + (size>>9)) >= mdev->ov_stop_sector;
+
+	if (mdev->ov_left == 0 || stop_sector_reached) {
 		ov_oos_print(mdev);
 		drbd_resync_finished(mdev);
 	}
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 47e3d4850584..4a7eccbd1292 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -56,7 +56,7 @@ extern const char *drbd_buildtag(void);
 #define REL_VERSION "8.3.13"
 #define API_VERSION 88
 #define PRO_VERSION_MIN 86
-#define PRO_VERSION_MAX 96
+#define PRO_VERSION_MAX 97
 
 
 enum drbd_io_error_p {
diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h
index a8706f08ab36..f6a576df19e0 100644
--- a/include/linux/drbd_nl.h
+++ b/include/linux/drbd_nl.h
@@ -145,6 +145,7 @@ NL_PACKET(dump_ee, 24,
 
 NL_PACKET(start_ov, 25,
 	NL_INT64(	66,	T_MAY_IGNORE,	start_sector)
+	NL_INT64(	90,	T_MANDATORY,	stop_sector)
 )
 
 NL_PACKET(new_c_uuid, 26,
-- 
cgit v1.2.3-55-g7522


From ccae7868b0c5697508a541c531cf96b361d62c1c Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Wed, 26 Sep 2012 14:07:04 +0200
Subject: drbd: log request sector offset and size for IO errors

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_req.c | 19 ++++++++++++++++++-
 include/linux/drbd.h          |  2 +-
 2 files changed, 19 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index d9e5962a9a8c..135ea76ed502 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -387,6 +387,20 @@ out_conflict:
 	return 1;
 }
 
+static void drbd_report_io_error(struct drbd_conf *mdev, struct drbd_request *req)
+{
+        char b[BDEVNAME_SIZE];
+
+	if (__ratelimit(&drbd_ratelimit_state))
+		return;
+
+	dev_warn(DEV, "local %s IO error sector %llu+%u on %s\n",
+			(req->rq_state & RQ_WRITE) ? "WRITE" : "READ",
+			(unsigned long long)req->sector,
+			req->size >> 9,
+			bdevname(mdev->ldev->backing_bdev, b));
+}
+
 /* obviously this could be coded as many single functions
  * instead of one huge switch,
  * or by putting the code directly in the respective locations
@@ -455,6 +469,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		req->rq_state |= RQ_LOCAL_COMPLETED;
 		req->rq_state &= ~RQ_LOCAL_PENDING;
 
+		drbd_report_io_error(mdev, req);
 		__drbd_chk_io_error(mdev, DRBD_WRITE_ERROR);
 		_req_may_be_done_not_susp(req, m);
 		break;
@@ -477,6 +492,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 			break;
 		}
 
+		drbd_report_io_error(mdev, req);
 		__drbd_chk_io_error(mdev, DRBD_READ_ERROR);
 
 	goto_queue_for_net_read:
@@ -900,7 +916,8 @@ static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, uns
 
 	if (!(local || remote) && !is_susp(mdev->state)) {
 		if (__ratelimit(&drbd_ratelimit_state))
-			dev_err(DEV, "IO ERROR: neither local nor remote disk\n");
+			dev_err(DEV, "IO ERROR: neither local nor remote data, sector %llu+%u\n",
+					(unsigned long long)req->sector, req->size >> 9);
 		goto fail_free_complete;
 	}
 
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 4a7eccbd1292..94f58a102bbb 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -53,7 +53,7 @@
 
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.3.13"
+#define REL_VERSION "8.3.14"
 #define API_VERSION 88
 #define PRO_VERSION_MIN 86
 #define PRO_VERSION_MAX 97
-- 
cgit v1.2.3-55-g7522


From c8442118ad9cd05cfe3b993f058e70ab25b1009a Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Wed, 24 Oct 2012 10:17:18 +0200
Subject: cfg80211: allow per interface TX power setting

The TX power setting is currently per wiphy (hardware
device) but with multi-channel capabilities that doesn't
make much sense any more.

Allow drivers (and mac80211) to advertise support for
per-interface TX power configuration. When the TX power
is configured for the wiphy, the wdev will be NULL and
the driver can still handle that, but when a wdev is
given the TX power can be set only for that wdev now.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c         |  9 ++++----
 .../net/wireless/brcm80211/brcmfmac/wl_cfg80211.c  |  6 ++++--
 drivers/net/wireless/mwifiex/cfg80211.c            |  1 +
 drivers/net/wireless/rndis_wlan.c                  | 10 +++++++--
 include/net/cfg80211.h                             | 10 ++++++---
 include/uapi/linux/nl80211.h                       |  2 ++
 net/mac80211/cfg.c                                 |  5 ++++-
 net/wireless/nl80211.c                             |  6 +++++-
 net/wireless/rdev-ops.h                            | 11 +++++-----
 net/wireless/trace.h                               | 24 ++++++++++++----------
 net/wireless/wext-compat.c                         |  4 ++--
 11 files changed, 56 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 277089963eb4..d615f9f7506a 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -1384,11 +1384,8 @@ static int ath6kl_cfg80211_set_wiphy_params(struct wiphy *wiphy, u32 changed)
 	return 0;
 }
 
-/*
- * The type nl80211_tx_power_setting replaces the following
- * data type from 2.6.36 onwards
-*/
 static int ath6kl_cfg80211_set_txpower(struct wiphy *wiphy,
+				       struct wireless_dev *wdev,
 				       enum nl80211_tx_power_setting type,
 				       int mbm)
 {
@@ -1423,7 +1420,9 @@ static int ath6kl_cfg80211_set_txpower(struct wiphy *wiphy,
 	return 0;
 }
 
-static int ath6kl_cfg80211_get_txpower(struct wiphy *wiphy, int *dbm)
+static int ath6kl_cfg80211_get_txpower(struct wiphy *wiphy,
+				       struct wireless_dev *wdev,
+				       int *dbm)
 {
 	struct ath6kl *ar = (struct ath6kl *)wiphy_priv(wiphy);
 	struct ath6kl_vif *vif;
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
index cb30feaa565b..904c94121c13 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
@@ -1721,7 +1721,7 @@ brcmf_cfg80211_disconnect(struct wiphy *wiphy, struct net_device *ndev,
 }
 
 static s32
-brcmf_cfg80211_set_tx_power(struct wiphy *wiphy,
+brcmf_cfg80211_set_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev,
 			    enum nl80211_tx_power_setting type, s32 mbm)
 {
 
@@ -1770,7 +1770,9 @@ done:
 	return err;
 }
 
-static s32 brcmf_cfg80211_get_tx_power(struct wiphy *wiphy, s32 *dbm)
+static s32 brcmf_cfg80211_get_tx_power(struct wiphy *wiphy,
+				       struct wireless_dev *wdev,
+				       s32 *dbm)
 {
 	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
 	struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg));
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index fdb1eb861021..8e829b251d83 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -324,6 +324,7 @@ mwifiex_cfg80211_cancel_remain_on_channel(struct wiphy *wiphy,
  */
 static int
 mwifiex_cfg80211_set_tx_power(struct wiphy *wiphy,
+			      struct wireless_dev *wdev,
 			      enum nl80211_tx_power_setting type,
 			      int mbm)
 {
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index bd1f0cb56085..5390af36c064 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -490,9 +490,12 @@ static int rndis_scan(struct wiphy *wiphy,
 static int rndis_set_wiphy_params(struct wiphy *wiphy, u32 changed);
 
 static int rndis_set_tx_power(struct wiphy *wiphy,
+			      struct wireless_dev *wdev,
 			      enum nl80211_tx_power_setting type,
 			      int mbm);
-static int rndis_get_tx_power(struct wiphy *wiphy, int *dbm);
+static int rndis_get_tx_power(struct wiphy *wiphy,
+			      struct wireless_dev *wdev,
+			      int *dbm);
 
 static int rndis_connect(struct wiphy *wiphy, struct net_device *dev,
 				struct cfg80211_connect_params *sme);
@@ -1903,6 +1906,7 @@ static int rndis_set_wiphy_params(struct wiphy *wiphy, u32 changed)
 }
 
 static int rndis_set_tx_power(struct wiphy *wiphy,
+			      struct wireless_dev *wdev,
 			      enum nl80211_tx_power_setting type,
 			      int mbm)
 {
@@ -1930,7 +1934,9 @@ static int rndis_set_tx_power(struct wiphy *wiphy,
 	return -ENOTSUPP;
 }
 
-static int rndis_get_tx_power(struct wiphy *wiphy, int *dbm)
+static int rndis_get_tx_power(struct wiphy *wiphy,
+			      struct wireless_dev *wdev,
+			      int *dbm)
 {
 	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
 	struct usbnet *usbdev = priv->usbdev;
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index c6964572890f..8034a4268fcb 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1551,7 +1551,10 @@ struct cfg80211_gtk_rekey_data {
  *	struct wiphy. If returning an error, no value should be changed.
  *
  * @set_tx_power: set the transmit power according to the parameters,
- *	the power passed is in mBm, to get dBm use MBM_TO_DBM().
+ *	the power passed is in mBm, to get dBm use MBM_TO_DBM(). The
+ *	wdev may be %NULL if power was set for the wiphy, and will
+ *	always be %NULL unless the driver supports per-vif TX power
+ *	(as advertised by the nl80211 feature flag.)
  * @get_tx_power: store the current TX power into the dbm variable;
  *	return 0 if successful
  *
@@ -1748,9 +1751,10 @@ struct cfg80211_ops {
 
 	int	(*set_wiphy_params)(struct wiphy *wiphy, u32 changed);
 
-	int	(*set_tx_power)(struct wiphy *wiphy,
+	int	(*set_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev,
 				enum nl80211_tx_power_setting type, int mbm);
-	int	(*get_tx_power)(struct wiphy *wiphy, int *dbm);
+	int	(*get_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev,
+				int *dbm);
 
 	int	(*set_wds_peer)(struct wiphy *wiphy, struct net_device *dev,
 				const u8 *addr);
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 617d0fbfc96f..4c5f6748ed7d 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3051,6 +3051,7 @@ enum nl80211_ap_sme_features {
  * @NL80211_FEATURE_LOW_PRIORITY_SCAN: This driver supports low priority scan
  * @NL80211_FEATURE_SCAN_FLUSH: Scan flush is supported
  * @NL80211_FEATURE_AP_SCAN: Support scanning using an AP vif
+ * @NL80211_FEATURE_VIF_TXPOWER: The driver supports per-vif TX power setting
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -3062,6 +3063,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_LOW_PRIORITY_SCAN		= 1 << 6,
 	NL80211_FEATURE_SCAN_FLUSH			= 1 << 7,
 	NL80211_FEATURE_AP_SCAN				= 1 << 8,
+	NL80211_FEATURE_VIF_TXPOWER			= 1 << 9,
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 34fd3eba3090..a352e4d22dd9 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1992,6 +1992,7 @@ static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed)
 }
 
 static int ieee80211_set_tx_power(struct wiphy *wiphy,
+				  struct wireless_dev *wdev,
 				  enum nl80211_tx_power_setting type, int mbm)
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
@@ -2026,7 +2027,9 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 	return 0;
 }
 
-static int ieee80211_get_tx_power(struct wiphy *wiphy, int *dbm)
+static int ieee80211_get_tx_power(struct wiphy *wiphy,
+				  struct wireless_dev *wdev,
+				  int *dbm)
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 879ca620fd6f..87d4670ee53a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1585,9 +1585,13 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_TX_POWER_SETTING]) {
+		struct wireless_dev *txp_wdev = wdev;
 		enum nl80211_tx_power_setting type;
 		int idx, mbm = 0;
 
+		if (!(rdev->wiphy.features & NL80211_FEATURE_VIF_TXPOWER))
+			txp_wdev = NULL;
+
 		if (!rdev->ops->set_tx_power) {
 			result = -EOPNOTSUPP;
 			goto bad_res;
@@ -1607,7 +1611,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 			mbm = nla_get_u32(info->attrs[idx]);
 		}
 
-		result = rdev_set_tx_power(rdev, type, mbm);
+		result = rdev_set_tx_power(rdev, txp_wdev, type, mbm);
 		if (result)
 			goto bad_res;
 	}
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index eb5f8974e148..6e5fa659068d 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -476,21 +476,22 @@ rdev_set_wiphy_params(struct cfg80211_registered_device *rdev, u32 changed)
 }
 
 static inline int rdev_set_tx_power(struct cfg80211_registered_device *rdev,
+				    struct wireless_dev *wdev,
 				    enum nl80211_tx_power_setting type, int mbm)
 {
 	int ret;
-	trace_rdev_set_tx_power(&rdev->wiphy, type, mbm);
-	ret = rdev->ops->set_tx_power(&rdev->wiphy, type, mbm);
+	trace_rdev_set_tx_power(&rdev->wiphy, wdev, type, mbm);
+	ret = rdev->ops->set_tx_power(&rdev->wiphy, wdev, type, mbm);
 	trace_rdev_return_int(&rdev->wiphy, ret);
 	return ret;
 }
 
 static inline int rdev_get_tx_power(struct cfg80211_registered_device *rdev,
-				    int *dbm)
+				    struct wireless_dev *wdev, int *dbm)
 {
 	int ret;
-	trace_rdev_get_tx_power(&rdev->wiphy);
-	ret = rdev->ops->get_tx_power(&rdev->wiphy, dbm);
+	trace_rdev_get_tx_power(&rdev->wiphy, wdev);
+	ret = rdev->ops->get_tx_power(&rdev->wiphy, wdev, dbm);
 	trace_rdev_return_int_int(&rdev->wiphy, ret, *dbm);
 	return ret;
 }
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 0ca71caf85fb..8e03c6382a8a 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -26,7 +26,7 @@
 #define WIPHY_PR_ARG MAC_PR_ARG(wiphy_mac)
 
 #define WDEV_ENTRY __field(u32, id)
-#define WDEV_ASSIGN (__entry->id) = (wdev->identifier)
+#define WDEV_ASSIGN (__entry->id) = (wdev ? wdev->identifier : 0)
 #define WDEV_PR_FMT ", wdev id: %u"
 #define WDEV_PR_ARG (__entry->id)
 
@@ -260,11 +260,6 @@ DEFINE_EVENT(wiphy_only_evt, rdev_get_antenna,
 	TP_ARGS(wiphy)
 );
 
-DEFINE_EVENT(wiphy_only_evt, rdev_get_tx_power,
-	TP_PROTO(struct wiphy *wiphy),
-	TP_ARGS(wiphy)
-);
-
 DEFINE_EVENT(wiphy_only_evt, rdev_rfkill_poll,
 	TP_PROTO(struct wiphy *wiphy),
 	TP_ARGS(wiphy)
@@ -1230,22 +1225,29 @@ TRACE_EVENT(rdev_set_wiphy_params,
 		  WIPHY_PR_ARG, __entry->changed)
 );
 
+DEFINE_EVENT(wiphy_wdev_evt, rdev_get_tx_power,
+	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev),
+	TP_ARGS(wiphy, wdev)
+);
+
 TRACE_EVENT(rdev_set_tx_power,
-	TP_PROTO(struct wiphy *wiphy, enum nl80211_tx_power_setting type,
-		 int mbm),
-	TP_ARGS(wiphy, type, mbm),
+	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev,
+		 enum nl80211_tx_power_setting type, int mbm),
+	TP_ARGS(wiphy, wdev, type, mbm),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
+		WDEV_ENTRY
 		__field(enum nl80211_tx_power_setting, type)
 		__field(int, mbm)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
+		WDEV_ASSIGN;
 		__entry->type = type;
 		__entry->mbm = mbm;
 	),
-	TP_printk(WIPHY_PR_FMT ", type: %d, mbm: %d",
-		  WIPHY_PR_ARG, __entry->type, __entry->mbm)
+	TP_printk(WIPHY_PR_FMT WDEV_PR_FMT ", type: %d, mbm: %d",
+		  WIPHY_PR_ARG, WDEV_PR_ARG,__entry->type, __entry->mbm)
 );
 
 TRACE_EVENT(rdev_return_int_int,
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 6488d2dbc1d7..742ab6ec4c9d 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -895,7 +895,7 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev,
 		return 0;
 	}
 
-	return rdev_set_tx_power(rdev, type, DBM_TO_MBM(dbm));
+	return rdev_set_tx_power(rdev, wdev, type, DBM_TO_MBM(dbm));
 }
 
 static int cfg80211_wext_giwtxpower(struct net_device *dev,
@@ -914,7 +914,7 @@ static int cfg80211_wext_giwtxpower(struct net_device *dev,
 	if (!rdev->ops->get_tx_power)
 		return -EOPNOTSUPP;
 
-	err = rdev_get_tx_power(rdev, &val);
+	err = rdev_get_tx_power(rdev, wdev, &val);
 	if (err)
 		return err;
 
-- 
cgit v1.2.3-55-g7522


From 1ea6f9c0d48b11b6ec3ec4b5579ec74fc3951cf8 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Wed, 24 Oct 2012 10:59:25 +0200
Subject: mac80211: handle TX power per virtual interface

Even before channel contexts/multi-channel, having a
single global TX power limit was already problematic,
in particular if two managed interfaces connected to
two APs with different power constraints. The channel
context introduction completely broke this though and
in fact I had disabled TX power configuration there
for drivers using channel contexts.

Change everything to track TX power per interface so
that different user settings and different channel
maxima are treated correctly. Also continue tracking
the global TX power though for compatibility with
applications that attempt to configure the wiphy's
TX power globally.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h        |  7 ++++++-
 net/mac80211/cfg.c            | 47 +++++++++++++++++++++++++++++--------------
 net/mac80211/chan.c           |  2 ++
 net/mac80211/debugfs_netdev.c |  6 ++++++
 net/mac80211/ieee80211_i.h    | 12 +++++++++--
 net/mac80211/iface.c          | 38 ++++++++++++++++++++++++++++++++++
 net/mac80211/main.c           | 27 +++++++++++++++----------
 net/mac80211/mlme.c           | 32 +++++++++++++++--------------
 net/mac80211/trace.h          |  2 ++
 net/mac80211/util.c           |  3 ++-
 10 files changed, 131 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 5f5327452c9a..dfa589b721b6 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -207,6 +207,7 @@ struct ieee80211_chanctx_conf {
  * @BSS_CHANGED_SSID: SSID changed for this BSS (AP mode)
  * @BSS_CHANGED_AP_PROBE_RESP: Probe Response changed for this BSS (AP mode)
  * @BSS_CHANGED_PS: PS changed for this BSS (STA mode)
+ * @BSS_CHANGED_TXPOWER: TX power setting changed for this interface
  */
 enum ieee80211_bss_change {
 	BSS_CHANGED_ASSOC		= 1<<0,
@@ -227,6 +228,7 @@ enum ieee80211_bss_change {
 	BSS_CHANGED_SSID		= 1<<15,
 	BSS_CHANGED_AP_PROBE_RESP	= 1<<16,
 	BSS_CHANGED_PS			= 1<<17,
+	BSS_CHANGED_TXPOWER		= 1<<18,
 
 	/* when adding here, make sure to change ieee80211_reconfig */
 };
@@ -309,6 +311,7 @@ enum ieee80211_rssi_event {
  * @ssid: The SSID of the current vif. Only valid in AP-mode.
  * @ssid_len: Length of SSID given in @ssid.
  * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode.
+ * @txpower: TX power in dBm
  */
 struct ieee80211_bss_conf {
 	const u8 *bssid;
@@ -341,6 +344,7 @@ struct ieee80211_bss_conf {
 	u8 ssid[IEEE80211_MAX_SSID_LEN];
 	size_t ssid_len;
 	bool hidden_ssid;
+	int txpower;
 };
 
 /**
@@ -884,7 +888,8 @@ enum ieee80211_smps_mode {
  *	powersave documentation below. This variable is valid only when
  *	the CONF_PS flag is set.
  *
- * @power_level: requested transmit power (in dBm)
+ * @power_level: requested transmit power (in dBm), backward compatibility
+ *	value only that is set to the minimum of all interfaces
  *
  * @channel: the channel to tune to
  * @channel_type: the channel (HT) type
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index a352e4d22dd9..986e9a139d42 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1996,33 +1996,46 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 				  enum nl80211_tx_power_setting type, int mbm)
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
-	struct ieee80211_channel *chan = local->_oper_channel;
-	u32 changes = 0;
+	struct ieee80211_sub_if_data *sdata;
 
-	/* FIXME */
-	if (local->use_chanctx)
-		return -EOPNOTSUPP;
+	if (wdev) {
+		sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
+
+		switch (type) {
+		case NL80211_TX_POWER_AUTOMATIC:
+			sdata->user_power_level = IEEE80211_UNSET_POWER_LEVEL;
+			break;
+		case NL80211_TX_POWER_LIMITED:
+		case NL80211_TX_POWER_FIXED:
+			if (mbm < 0 || (mbm % 100))
+				return -EOPNOTSUPP;
+			sdata->user_power_level = MBM_TO_DBM(mbm);
+			break;
+		}
+
+		ieee80211_recalc_txpower(sdata);
+
+		return 0;
+	}
 
 	switch (type) {
 	case NL80211_TX_POWER_AUTOMATIC:
-		local->user_power_level = -1;
+		local->user_power_level = IEEE80211_UNSET_POWER_LEVEL;
 		break;
 	case NL80211_TX_POWER_LIMITED:
-		if (mbm < 0 || (mbm % 100))
-			return -EOPNOTSUPP;
-		local->user_power_level = MBM_TO_DBM(mbm);
-		break;
 	case NL80211_TX_POWER_FIXED:
 		if (mbm < 0 || (mbm % 100))
 			return -EOPNOTSUPP;
-		/* TODO: move to cfg80211 when it knows the channel */
-		if (MBM_TO_DBM(mbm) > chan->max_power)
-			return -EINVAL;
 		local->user_power_level = MBM_TO_DBM(mbm);
 		break;
 	}
 
-	ieee80211_hw_config(local, changes);
+	mutex_lock(&local->iflist_mtx);
+	list_for_each_entry(sdata, &local->interfaces, list)
+		sdata->user_power_level = local->user_power_level;
+	list_for_each_entry(sdata, &local->interfaces, list)
+		ieee80211_recalc_txpower(sdata);
+	mutex_unlock(&local->iflist_mtx);
 
 	return 0;
 }
@@ -2032,8 +2045,12 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy,
 				  int *dbm)
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
+	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
 
-	*dbm = local->hw.conf.power_level;
+	if (!local->use_chanctx)
+		*dbm = local->hw.conf.power_level;
+	else
+		*dbm = sdata->vif.bss_conf.txpower;
 
 	return 0;
 }
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index f84b86028a9c..a2b06d40aebf 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -173,6 +173,8 @@ static int ieee80211_assign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
 	rcu_assign_pointer(sdata->vif.chanctx_conf, &ctx->conf);
 	ctx->refcount++;
 
+	ieee80211_recalc_txpower(sdata);
+
 	return 0;
 }
 
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 3393ad5b8ab1..07c5721323ca 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -168,6 +168,9 @@ IEEE80211_IF_FILE(rc_rateidx_mcs_mask_5ghz,
 IEEE80211_IF_FILE(flags, flags, HEX);
 IEEE80211_IF_FILE(state, state, LHEX);
 IEEE80211_IF_FILE(channel_type, vif.bss_conf.channel_type, DEC);
+IEEE80211_IF_FILE(txpower, vif.bss_conf.txpower, DEC);
+IEEE80211_IF_FILE(ap_power_level, ap_power_level, DEC);
+IEEE80211_IF_FILE(user_power_level, user_power_level, DEC);
 
 /* STA attributes */
 IEEE80211_IF_FILE(bssid, u.mgd.bssid, MAC);
@@ -632,6 +635,9 @@ static void add_files(struct ieee80211_sub_if_data *sdata)
 	DEBUGFS_ADD(flags);
 	DEBUGFS_ADD(state);
 	DEBUGFS_ADD(channel_type);
+	DEBUGFS_ADD(txpower);
+	DEBUGFS_ADD(user_power_level);
+	DEBUGFS_ADD(ap_power_level);
 
 	if (sdata->vif.type != NL80211_IFTYPE_MONITOR)
 		add_common_files(sdata);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 3026519b236a..a1f7c139308e 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -56,6 +56,9 @@ struct ieee80211_local;
 #define TU_TO_JIFFIES(x)	(usecs_to_jiffies((x) * 1024))
 #define TU_TO_EXP_TIME(x)	(jiffies + TU_TO_JIFFIES(x))
 
+/* power level hasn't been configured (or set to automatic) */
+#define IEEE80211_UNSET_POWER_LEVEL	INT_MIN
+
 /*
  * Some APs experience problems when working with U-APSD. Decrease the
  * probability of that happening by using legacy mode for all ACs but VO.
@@ -743,6 +746,9 @@ struct ieee80211_sub_if_data {
 	u8 needed_rx_chains;
 	enum ieee80211_smps_mode smps_mode;
 
+	int user_power_level; /* in dBm */
+	int ap_power_level; /* in dBm */
+
 	/*
 	 * AP this belongs to: self in AP mode and
 	 * corresponding AP in VLAN mode, NULL for
@@ -1117,8 +1123,7 @@ struct ieee80211_local {
 	int dynamic_ps_user_timeout;
 	bool disable_dynamic_ps;
 
-	int user_power_level; /* in dBm */
-	int ap_power_level; /* in dBm */
+	int user_power_level; /* in dBm, for all interfaces */
 
 	enum ieee80211_smps_mode smps_mode;
 
@@ -1365,6 +1370,9 @@ void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata,
 int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up);
 void ieee80211_sdata_stop(struct ieee80211_sub_if_data *sdata);
 
+bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata);
+void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata);
+
 static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata)
 {
 	return test_bit(SDATA_STATE_RUNNING, &sdata->state);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 1a6fe135f201..80ce90b29d9d 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -42,6 +42,41 @@
  * by either the RTNL, the iflist_mtx or RCU.
  */
 
+bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_chanctx_conf *chanctx_conf;
+	int power;
+
+	rcu_read_lock();
+	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
+	if (!chanctx_conf) {
+		rcu_read_unlock();
+		return false;
+	}
+
+	power = chanctx_conf->channel->max_power;
+	rcu_read_unlock();
+
+	if (sdata->user_power_level != IEEE80211_UNSET_POWER_LEVEL)
+		power = min(power, sdata->user_power_level);
+
+	if (sdata->ap_power_level != IEEE80211_UNSET_POWER_LEVEL)
+		power = min(power, sdata->ap_power_level);
+
+	if (power != sdata->vif.bss_conf.txpower) {
+		sdata->vif.bss_conf.txpower = power;
+		ieee80211_hw_config(sdata->local, 0);
+		return true;
+	}
+
+	return false;
+}
+
+void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
+{
+	if (__ieee80211_recalc_txpower(sdata))
+		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_TXPOWER);
+}
 
 static u32 ieee80211_idle_off(struct ieee80211_local *local,
 			      const char *reason)
@@ -1510,6 +1545,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 
 	ieee80211_set_default_queues(sdata);
 
+	sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL;
+	sdata->user_power_level = local->user_power_level;
+
 	/* setup type-dependent data */
 	ieee80211_setup_sdata(sdata, type);
 
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index fd8345c20051..70e87600cacc 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -95,11 +95,13 @@ static void ieee80211_reconfig_filter(struct work_struct *work)
 
 static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local)
 {
+	struct ieee80211_sub_if_data *sdata;
 	struct ieee80211_channel *chan;
 	u32 changed = 0;
 	int power;
 	enum nl80211_channel_type channel_type;
 	u32 offchannel_flag;
+	bool scanning = false;
 
 	offchannel_flag = local->hw.conf.flags & IEEE80211_CONF_OFFCHANNEL;
 	if (local->scan_channel) {
@@ -146,16 +148,18 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local)
 		changed |= IEEE80211_CONF_CHANGE_SMPS;
 	}
 
-	if (test_bit(SCAN_SW_SCANNING, &local->scanning) ||
-	    test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning) ||
-	    test_bit(SCAN_HW_SCANNING, &local->scanning) ||
-	    !local->ap_power_level)
-		power = chan->max_power;
-	else
-		power = min(chan->max_power, local->ap_power_level);
+	scanning = test_bit(SCAN_SW_SCANNING, &local->scanning) ||
+		   test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning) ||
+		   test_bit(SCAN_HW_SCANNING, &local->scanning);
+	power = chan->max_power;
 
-	if (local->user_power_level >= 0)
-		power = min(power, local->user_power_level);
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		if (!rcu_access_pointer(sdata->vif.chanctx_conf))
+			continue;
+		power = min(power, sdata->vif.bss_conf.txpower);
+	}
+	rcu_read_unlock();
 
 	if (local->hw.conf.power_level != power) {
 		changed |= IEEE80211_CONF_CHANGE_POWER;
@@ -600,7 +604,8 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 
 	wiphy->features |= NL80211_FEATURE_SK_TX_STATUS |
 			   NL80211_FEATURE_SAE |
-			   NL80211_FEATURE_HT_IBSS;
+			   NL80211_FEATURE_HT_IBSS |
+			   NL80211_FEATURE_VIF_TXPOWER;
 
 	if (!ops->hw_scan)
 		wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN |
@@ -633,7 +638,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	local->hw.radiotap_mcs_details = IEEE80211_RADIOTAP_MCS_HAVE_MCS |
 					 IEEE80211_RADIOTAP_MCS_HAVE_GI |
 					 IEEE80211_RADIOTAP_MCS_HAVE_BW;
-	local->user_power_level = -1;
+	local->user_power_level = IEEE80211_UNSET_POWER_LEVEL;
 	wiphy->ht_capa_mod_mask = &mac80211_ht_capa_mod_mask;
 
 	INIT_LIST_HEAD(&local->interfaces);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 1d1fdf0791f0..d29762fdd887 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -820,10 +820,10 @@ void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 					 cbss->beacon_interval));
 }
 
-static void ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
-					struct ieee80211_channel *channel,
-					const u8 *country_ie, u8 country_ie_len,
-					const u8 *pwr_constr_elem)
+static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
+				       struct ieee80211_channel *channel,
+				       const u8 *country_ie, u8 country_ie_len,
+				       const u8 *pwr_constr_elem)
 {
 	struct ieee80211_country_ie_triplet *triplet;
 	int chan = ieee80211_frequency_to_channel(channel->center_freq);
@@ -832,7 +832,7 @@ static void ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
 
 	/* Invalid IE */
 	if (country_ie_len % 2 || country_ie_len < IEEE80211_COUNTRY_IE_MIN_LEN)
-		return;
+		return 0;
 
 	triplet = (void *)(country_ie + 3);
 	country_ie_len -= 3;
@@ -873,19 +873,21 @@ static void ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (!have_chan_pwr)
-		return;
+		return 0;
 
 	new_ap_level = max_t(int, 0, chan_pwr - *pwr_constr_elem);
 
-	if (sdata->local->ap_power_level == new_ap_level)
-		return;
+	if (sdata->ap_power_level == new_ap_level)
+		return 0;
 
 	sdata_info(sdata,
 		   "Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n",
 		   new_ap_level, chan_pwr, *pwr_constr_elem,
 		   sdata->u.mgd.bssid);
-	sdata->local->ap_power_level = new_ap_level;
-	ieee80211_hw_config(sdata->local, 0);
+	sdata->ap_power_level = new_ap_level;
+	if (__ieee80211_recalc_txpower(sdata))
+		return BSS_CHANGED_TXPOWER;
+	return 0;
 }
 
 void ieee80211_enable_dyn_ps(struct ieee80211_vif *vif)
@@ -1489,7 +1491,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	memset(&ifmgd->ht_capa, 0, sizeof(ifmgd->ht_capa));
 	memset(&ifmgd->ht_capa_mask, 0, sizeof(ifmgd->ht_capa_mask));
 
-	local->ap_power_level = 0;
+	sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL;
 
 	del_timer_sync(&local->dynamic_ps_timer);
 	cancel_work_sync(&local->dynamic_ps_enable_work);
@@ -2623,10 +2625,10 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	if (elems.country_elem && elems.pwr_constr_elem &&
 	    mgmt->u.probe_resp.capab_info &
 				cpu_to_le16(WLAN_CAPABILITY_SPECTRUM_MGMT))
-		ieee80211_handle_pwr_constr(sdata, chan,
-					    elems.country_elem,
-					    elems.country_elem_len,
-					    elems.pwr_constr_elem);
+		changed |= ieee80211_handle_pwr_constr(sdata, chan,
+						       elems.country_elem,
+						       elems.country_elem_len,
+						       elems.pwr_constr_elem);
 
 	ieee80211_bss_info_change_notify(sdata, changed);
 }
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 5e74e77cba9a..eeebbd9cb888 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -342,6 +342,7 @@ TRACE_EVENT(drv_bss_info_changed,
 		__field(bool, ps);
 		__dynamic_array(u8, ssid, info->ssid_len);
 		__field(bool, hidden_ssid);
+		__field(int, txpower)
 	),
 
 	TP_fast_assign(
@@ -376,6 +377,7 @@ TRACE_EVENT(drv_bss_info_changed,
 		__entry->ps = info->ps;
 		memcpy(__get_dynamic_array(ssid), info->ssid, info->ssid_len);
 		__entry->hidden_ssid = info->hidden_ssid;
+		__entry->txpower = info->txpower;
 	),
 
 	TP_printk(
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 6636d3962317..1a511afbdf07 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1478,7 +1478,8 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 			  BSS_CHANGED_BSSID |
 			  BSS_CHANGED_CQM |
 			  BSS_CHANGED_QOS |
-			  BSS_CHANGED_IDLE;
+			  BSS_CHANGED_IDLE |
+			  BSS_CHANGED_TXPOWER;
 
 		switch (sdata->vif.type) {
 		case NL80211_IFTYPE_STATION:
-- 
cgit v1.2.3-55-g7522


From 5d9db883761ad1bc2245fd3018715549b974203d Mon Sep 17 00:00:00 2001
From: Matthew Garrett
Date: Fri, 5 Oct 2012 13:54:56 +0800
Subject: efi: Add support for a UEFI variable filesystem

The existing EFI variables code only supports variables of up to 1024
bytes. This limitation existed in version 0.99 of the EFI specification,
but was removed before any full releases. Since variables can now be
larger than a single page, sysfs isn't the best interface for this. So,
instead, let's add a filesystem. Variables can be read, written and
created, with the first 4 bytes of each variable representing its UEFI
attributes. The create() method doesn't actually commit to flash since
zero-length variables can't exist per-spec.

Updates from Jeremy Kerr <jeremy.kerr@canonical.com>.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
Signed-off-by: Jeremy Kerr <jeremy.kerr@canonical.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
 drivers/firmware/efivars.c | 384 ++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/efi.h        |   5 +
 2 files changed, 383 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index d10c9873dd9a..b605c4849772 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -80,6 +80,10 @@
 #include <linux/slab.h>
 #include <linux/pstore.h>
 
+#include <linux/fs.h>
+#include <linux/ramfs.h>
+#include <linux/pagemap.h>
+
 #include <asm/uaccess.h>
 
 #define EFIVARS_VERSION "0.08"
@@ -91,6 +95,7 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(EFIVARS_VERSION);
 
 #define DUMP_NAME_LEN 52
+#define GUID_LEN 37
 
 /*
  * The maximum size of VariableName + Data = 1024
@@ -108,7 +113,6 @@ struct efi_variable {
 	__u32         Attributes;
 } __attribute__((packed));
 
-
 struct efivar_entry {
 	struct efivars *efivars;
 	struct efi_variable var;
@@ -122,6 +126,9 @@ struct efivar_attribute {
 	ssize_t (*store)(struct efivar_entry *entry, const char *buf, size_t count);
 };
 
+static struct efivars __efivars;
+static struct efivar_operations ops;
+
 #define PSTORE_EFI_ATTRIBUTES \
 	(EFI_VARIABLE_NON_VOLATILE | \
 	 EFI_VARIABLE_BOOTSERVICE_ACCESS | \
@@ -629,14 +636,380 @@ static struct kobj_type efivar_ktype = {
 	.default_attrs = def_attrs,
 };
 
-static struct pstore_info efi_pstore_info;
-
 static inline void
 efivar_unregister(struct efivar_entry *var)
 {
 	kobject_put(&var->kobj);
 }
 
+static int efivarfs_file_open(struct inode *inode, struct file *file)
+{
+	file->private_data = inode->i_private;
+	return 0;
+}
+
+static ssize_t efivarfs_file_write(struct file *file,
+		const char __user *userbuf, size_t count, loff_t *ppos)
+{
+	struct efivar_entry *var = file->private_data;
+	struct efivars *efivars;
+	efi_status_t status;
+	void *data;
+	u32 attributes;
+	struct inode *inode = file->f_mapping->host;
+	int datasize = count - sizeof(attributes);
+
+	if (count < sizeof(attributes))
+		return -EINVAL;
+
+	data = kmalloc(datasize, GFP_KERNEL);
+
+	if (!data)
+		return -ENOMEM;
+
+	efivars = var->efivars;
+
+	if (copy_from_user(&attributes, userbuf, sizeof(attributes))) {
+		count = -EFAULT;
+		goto out;
+	}
+
+	if (attributes & ~(EFI_VARIABLE_MASK)) {
+		count = -EINVAL;
+		goto out;
+	}
+
+	if (copy_from_user(data, userbuf + sizeof(attributes), datasize)) {
+		count = -EFAULT;
+		goto out;
+	}
+
+	if (validate_var(&var->var, data, datasize) == false) {
+		count = -EINVAL;
+		goto out;
+	}
+
+	status = efivars->ops->set_variable(var->var.VariableName,
+					    &var->var.VendorGuid,
+					    attributes, datasize,
+					    data);
+
+	switch (status) {
+	case EFI_SUCCESS:
+		mutex_lock(&inode->i_mutex);
+		i_size_write(inode, count);
+		mutex_unlock(&inode->i_mutex);
+		break;
+	case EFI_INVALID_PARAMETER:
+		count = -EINVAL;
+		break;
+	case EFI_OUT_OF_RESOURCES:
+		count = -ENOSPC;
+		break;
+	case EFI_DEVICE_ERROR:
+		count = -EIO;
+		break;
+	case EFI_WRITE_PROTECTED:
+		count = -EROFS;
+		break;
+	case EFI_SECURITY_VIOLATION:
+		count = -EACCES;
+		break;
+	case EFI_NOT_FOUND:
+		count = -ENOENT;
+		break;
+	default:
+		count = -EINVAL;
+		break;
+	}
+out:
+	kfree(data);
+
+	return count;
+}
+
+static ssize_t efivarfs_file_read(struct file *file, char __user *userbuf,
+		size_t count, loff_t *ppos)
+{
+	struct efivar_entry *var = file->private_data;
+	struct efivars *efivars = var->efivars;
+	efi_status_t status;
+	unsigned long datasize = 0;
+	u32 attributes;
+	void *data;
+	ssize_t size;
+
+	status = efivars->ops->get_variable(var->var.VariableName,
+					    &var->var.VendorGuid,
+					    &attributes, &datasize, NULL);
+
+	if (status != EFI_BUFFER_TOO_SMALL)
+		return 0;
+
+	data = kmalloc(datasize + 4, GFP_KERNEL);
+
+	if (!data)
+		return 0;
+
+	status = efivars->ops->get_variable(var->var.VariableName,
+					    &var->var.VendorGuid,
+					    &attributes, &datasize,
+					    (data + 4));
+
+	if (status != EFI_SUCCESS)
+		return 0;
+
+	memcpy(data, &attributes, 4);
+	size = simple_read_from_buffer(userbuf, count, ppos,
+					data, datasize + 4);
+	kfree(data);
+
+	return size;
+}
+
+static void efivarfs_evict_inode(struct inode *inode)
+{
+	clear_inode(inode);
+}
+
+static const struct super_operations efivarfs_ops = {
+	.statfs = simple_statfs,
+	.drop_inode = generic_delete_inode,
+	.evict_inode = efivarfs_evict_inode,
+	.show_options = generic_show_options,
+};
+
+static struct super_block *efivarfs_sb;
+
+static const struct inode_operations efivarfs_dir_inode_operations;
+
+static const struct file_operations efivarfs_file_operations = {
+	.open	= efivarfs_file_open,
+	.read	= efivarfs_file_read,
+	.write	= efivarfs_file_write,
+	.llseek	= no_llseek,
+};
+
+static struct inode *efivarfs_get_inode(struct super_block *sb,
+				const struct inode *dir, int mode, dev_t dev)
+{
+	struct inode *inode = new_inode(sb);
+
+	if (inode) {
+		inode->i_ino = get_next_ino();
+		inode->i_uid = inode->i_gid = 0;
+		inode->i_mode = mode;
+		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		switch (mode & S_IFMT) {
+		case S_IFREG:
+			inode->i_fop = &efivarfs_file_operations;
+			break;
+		case S_IFDIR:
+			inode->i_op = &efivarfs_dir_inode_operations;
+			inode->i_fop = &simple_dir_operations;
+			inc_nlink(inode);
+			break;
+		}
+	}
+	return inode;
+}
+
+static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid)
+{
+	guid->b[0] = hex_to_bin(str[6]) << 4 | hex_to_bin(str[7]);
+	guid->b[1] = hex_to_bin(str[4]) << 4 | hex_to_bin(str[5]);
+	guid->b[2] = hex_to_bin(str[2]) << 4 | hex_to_bin(str[3]);
+	guid->b[3] = hex_to_bin(str[0]) << 4 | hex_to_bin(str[1]);
+	guid->b[4] = hex_to_bin(str[11]) << 4 | hex_to_bin(str[12]);
+	guid->b[5] = hex_to_bin(str[9]) << 4 | hex_to_bin(str[10]);
+	guid->b[6] = hex_to_bin(str[16]) << 4 | hex_to_bin(str[17]);
+	guid->b[7] = hex_to_bin(str[14]) << 4 | hex_to_bin(str[15]);
+	guid->b[8] = hex_to_bin(str[19]) << 4 | hex_to_bin(str[20]);
+	guid->b[9] = hex_to_bin(str[21]) << 4 | hex_to_bin(str[22]);
+	guid->b[10] = hex_to_bin(str[24]) << 4 | hex_to_bin(str[25]);
+	guid->b[11] = hex_to_bin(str[26]) << 4 | hex_to_bin(str[27]);
+	guid->b[12] = hex_to_bin(str[28]) << 4 | hex_to_bin(str[29]);
+	guid->b[13] = hex_to_bin(str[30]) << 4 | hex_to_bin(str[31]);
+	guid->b[14] = hex_to_bin(str[32]) << 4 | hex_to_bin(str[33]);
+	guid->b[15] = hex_to_bin(str[34]) << 4 | hex_to_bin(str[35]);
+}
+
+static int efivarfs_create(struct inode *dir, struct dentry *dentry,
+			  umode_t mode, bool excl)
+{
+	struct inode *inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0);
+	struct efivars *efivars = &__efivars;
+	struct efivar_entry *var;
+	int namelen, i = 0, err = 0;
+
+	if (dentry->d_name.len < 38)
+		return -EINVAL;
+
+	if (!inode)
+		return -ENOSPC;
+
+	var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL);
+
+	if (!var)
+		return -ENOMEM;
+
+	namelen = dentry->d_name.len - GUID_LEN;
+
+	efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1,
+			&var->var.VendorGuid);
+
+	for (i = 0; i < namelen; i++)
+		var->var.VariableName[i] = dentry->d_name.name[i];
+
+	var->var.VariableName[i] = '\0';
+
+	inode->i_private = var;
+	var->efivars = efivars;
+	var->kobj.kset = efivars->kset;
+
+	err = kobject_init_and_add(&var->kobj, &efivar_ktype, NULL, "%s",
+			     dentry->d_name.name);
+	if (err)
+		goto out;
+
+	kobject_uevent(&var->kobj, KOBJ_ADD);
+	spin_lock(&efivars->lock);
+	list_add(&var->list, &efivars->list);
+	spin_unlock(&efivars->lock);
+	d_instantiate(dentry, inode);
+	dget(dentry);
+out:
+	if (err)
+		kfree(var);
+	return err;
+}
+
+static int efivarfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct efivar_entry *var = dentry->d_inode->i_private;
+	struct efivars *efivars = var->efivars;
+	efi_status_t status;
+
+	spin_lock(&efivars->lock);
+
+	status = efivars->ops->set_variable(var->var.VariableName,
+					    &var->var.VendorGuid,
+					    0, 0, NULL);
+
+	if (status == EFI_SUCCESS || status == EFI_NOT_FOUND) {
+		list_del(&var->list);
+		spin_unlock(&efivars->lock);
+		efivar_unregister(var);
+		drop_nlink(dir);
+		dput(dentry);
+		return 0;
+	}
+
+	spin_unlock(&efivars->lock);
+	return -EINVAL;
+};
+
+int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct inode *inode = NULL;
+	struct dentry *root;
+	struct efivar_entry *entry, *n;
+	struct efivars *efivars = &__efivars;
+	int err;
+
+	efivarfs_sb = sb;
+
+	sb->s_maxbytes          = MAX_LFS_FILESIZE;
+	sb->s_blocksize         = PAGE_CACHE_SIZE;
+	sb->s_blocksize_bits    = PAGE_CACHE_SHIFT;
+	sb->s_magic             = PSTOREFS_MAGIC;
+	sb->s_op                = &efivarfs_ops;
+	sb->s_time_gran         = 1;
+
+	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+	if (!inode) {
+		err = -ENOMEM;
+		goto fail;
+	}
+	inode->i_op = &efivarfs_dir_inode_operations;
+
+	root = d_make_root(inode);
+	sb->s_root = root;
+	if (!root) {
+		err = -ENOMEM;
+		goto fail;
+	}
+
+	list_for_each_entry_safe(entry, n, &efivars->list, list) {
+		struct inode *inode;
+		struct dentry *dentry, *root = efivarfs_sb->s_root;
+		char *name;
+		unsigned long size = 0;
+		int len, i;
+
+		len = utf16_strlen(entry->var.VariableName);
+
+		/* GUID plus trailing NULL */
+		name = kmalloc(len + 38, GFP_ATOMIC);
+
+		for (i = 0; i < len; i++)
+			name[i] = entry->var.VariableName[i] & 0xFF;
+
+		name[len] = '-';
+
+		efi_guid_unparse(&entry->var.VendorGuid, name + len + 1);
+
+		name[len+GUID_LEN] = '\0';
+
+		inode = efivarfs_get_inode(efivarfs_sb, root->d_inode,
+					  S_IFREG | 0644, 0);
+		dentry = d_alloc_name(root, name);
+
+		efivars->ops->get_variable(entry->var.VariableName,
+					   &entry->var.VendorGuid,
+					   &entry->var.Attributes,
+					   &size,
+					   NULL);
+
+		mutex_lock(&inode->i_mutex);
+		inode->i_private = entry;
+		i_size_write(inode, size+4);
+		mutex_unlock(&inode->i_mutex);
+		d_add(dentry, inode);
+	}
+
+	return 0;
+fail:
+	iput(inode);
+	return err;
+}
+
+static struct dentry *efivarfs_mount(struct file_system_type *fs_type,
+				    int flags, const char *dev_name, void *data)
+{
+	return mount_single(fs_type, flags, data, efivarfs_fill_super);
+}
+
+static void efivarfs_kill_sb(struct super_block *sb)
+{
+	kill_litter_super(sb);
+	efivarfs_sb = NULL;
+}
+
+static struct file_system_type efivarfs_type = {
+	.name    = "efivarfs",
+	.mount   = efivarfs_mount,
+	.kill_sb = efivarfs_kill_sb,
+};
+
+static const struct inode_operations efivarfs_dir_inode_operations = {
+	.lookup = simple_lookup,
+	.unlink = efivarfs_unlink,
+	.create = efivarfs_create,
+};
+
+static struct pstore_info efi_pstore_info;
+
 #ifdef CONFIG_PSTORE
 
 static int efi_pstore_open(struct pstore_info *psi)
@@ -1198,6 +1571,8 @@ int register_efivars(struct efivars *efivars,
 		pstore_register(&efivars->efi_pstore_info);
 	}
 
+	register_filesystem(&efivarfs_type);
+
 out:
 	kfree(variable_name);
 
@@ -1205,9 +1580,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(register_efivars);
 
-static struct efivars __efivars;
-static struct efivar_operations ops;
-
 /*
  * For now we register the efi subsystem with the firmware subsystem
  * and the vars subsystem with the efi subsystem.  In the future, it
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 8670eb1eb8cd..b2af1571592b 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -29,7 +29,12 @@
 #define EFI_UNSUPPORTED		( 3 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_BAD_BUFFER_SIZE     ( 4 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_BUFFER_TOO_SMALL	( 5 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_NOT_READY		( 6 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_DEVICE_ERROR	( 7 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_WRITE_PROTECTED	( 8 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_OUT_OF_RESOURCES	( 9 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_NOT_FOUND		(14 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_SECURITY_VIOLATION	(26 | (1UL << (BITS_PER_LONG-1)))
 
 typedef unsigned long efi_status_t;
 typedef u8 efi_bool_t;
-- 
cgit v1.2.3-55-g7522


From 605e70c7aa1b7b0d554baf945630c1d606bbfbc3 Mon Sep 17 00:00:00 2001
From: Lee, Chun-Yi
Date: Fri, 5 Oct 2012 13:54:56 +0800
Subject: efi: add efivars kobject to efi sysfs folder

UEFI variable filesystem need a new mount point, so this patch add
efivars kobject to efi_kobj for create a /sys/firmware/efi/efivars
folder.

Cc: Matthew Garrett <mjg@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Lee, Chun-Yi <jlee@suse.com>
Signed-off-by: Jeremy Kerr <jeremy.kerr@canonical.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
 drivers/firmware/efivars.c | 9 +++++++++
 include/linux/efi.h        | 1 +
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index d7658b4a5010..6793965b7c8b 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -1527,6 +1527,7 @@ void unregister_efivars(struct efivars *efivars)
 		sysfs_remove_bin_file(&efivars->kset->kobj, efivars->del_var);
 	kfree(efivars->new_var);
 	kfree(efivars->del_var);
+	kobject_put(efivars->kobject);
 	kset_unregister(efivars->kset);
 }
 EXPORT_SYMBOL_GPL(unregister_efivars);
@@ -1558,6 +1559,14 @@ int register_efivars(struct efivars *efivars,
 		goto out;
 	}
 
+	efivars->kobject = kobject_create_and_add("efivars", parent_kobj);
+	if (!efivars->kobject) {
+		pr_err("efivars: Subsystem registration failed.\n");
+		error = -ENOMEM;
+		kset_unregister(efivars->kset);
+		goto out;
+	}
+
 	/*
 	 * Per EFI spec, the maximum storage allocated for both
 	 * the variable name and variable data is 1024 bytes.
diff --git a/include/linux/efi.h b/include/linux/efi.h
index b2af1571592b..337aefbfb003 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -662,6 +662,7 @@ struct efivars {
 	spinlock_t lock;
 	struct list_head list;
 	struct kset *kset;
+	struct kobject *kobject;
 	struct bin_attribute *new_var, *del_var;
 	const struct efivar_operations *ops;
 	struct efivar_entry *walk_entry;
-- 
cgit v1.2.3-55-g7522


From bd52276fa1d420c3a504b76ffaaa1642cc79d4c4 Mon Sep 17 00:00:00 2001
From: Jan Beulich
Date: Fri, 25 May 2012 16:20:31 +0100
Subject: x86-64/efi: Use EFI to deal with platform wall clock (again)

Other than ix86, x86-64 on EFI so far didn't set the
{g,s}et_wallclock accessors to the EFI routines, thus
incorrectly using raw RTC accesses instead.

Simply removing the #ifdef around the respective code isn't
enough, however: While so far early get-time calls were done in
physical mode, this doesn't work properly for x86-64, as virtual
addresses would still need to be set up for all runtime regions
(which wasn't the case on the system I have access to), so
instead the patch moves the call to efi_enter_virtual_mode()
ahead (which in turn allows to drop all code related to calling
efi-get-time in physical mode).

Additionally the earlier calling of efi_set_executable()
requires the CPA code to cope, i.e. during early boot it must be
avoided to call cpa_flush_array(), as the first thing this
function does is a BUG_ON(irqs_disabled()).

Also make the two EFI functions in question here static -
they're not being referenced elsewhere.

History:

    This commit was originally merged as bacef661acdb ("x86-64/efi:
    Use EFI to deal with platform wall clock") but it resulted in some
    ASUS machines no longer booting due to a firmware bug, and so was
    reverted in f026cfa82f62. A pre-emptive fix for the buggy ASUS
    firmware was merged in 03a1c254975e ("x86, efi: 1:1 pagetable
    mapping for virtual EFI calls") so now this patch can be
    reapplied.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Tested-by: Matt Fleming <matt.fleming@intel.com>
Acked-by: Matthew Garrett <mjg@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com> [added commit history]
---
 arch/x86/mm/pageattr.c      | 10 ++++++----
 arch/x86/platform/efi/efi.c | 30 ++++--------------------------
 include/linux/efi.h         |  2 --
 init/main.c                 |  8 ++++----
 4 files changed, 14 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a718e0d23503..931930a96160 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -919,11 +919,13 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	/*
 	 * On success we use clflush, when the CPU supports it to
-	 * avoid the wbindv. If the CPU does not support it and in the
-	 * error case we fall back to cpa_flush_all (which uses
-	 * wbindv):
+	 * avoid the wbindv. If the CPU does not support it, in the
+	 * error case, and during early boot (for EFI) we fall back
+	 * to cpa_flush_all (which uses wbinvd):
 	 */
-	if (!ret && cpu_has_clflush) {
+	if (early_boot_irqs_disabled)
+		__cpa_flush_all((void *)(long)cache);
+	else if (!ret && cpu_has_clflush) {
 		if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
 			cpa_flush_array(addr, numpages, cache,
 					cpa.flags, pages);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index aded2a91162a..757834434e59 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -235,22 +235,7 @@ static efi_status_t __init phys_efi_set_virtual_address_map(
 	return status;
 }
 
-static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
-					     efi_time_cap_t *tc)
-{
-	unsigned long flags;
-	efi_status_t status;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	efi_call_phys_prelog();
-	status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm),
-				virt_to_phys(tc));
-	efi_call_phys_epilog();
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return status;
-}
-
-int efi_set_rtc_mmss(unsigned long nowtime)
+static int efi_set_rtc_mmss(unsigned long nowtime)
 {
 	int real_seconds, real_minutes;
 	efi_status_t 	status;
@@ -279,7 +264,7 @@ int efi_set_rtc_mmss(unsigned long nowtime)
 	return 0;
 }
 
-unsigned long efi_get_time(void)
+static unsigned long efi_get_time(void)
 {
 	efi_status_t status;
 	efi_time_t eft;
@@ -635,18 +620,13 @@ static int __init efi_runtime_init(void)
 	}
 	/*
 	 * We will only need *early* access to the following
-	 * two EFI runtime services before set_virtual_address_map
+	 * EFI runtime service before set_virtual_address_map
 	 * is invoked.
 	 */
-	efi_phys.get_time = (efi_get_time_t *)runtime->get_time;
 	efi_phys.set_virtual_address_map =
 		(efi_set_virtual_address_map_t *)
 		runtime->set_virtual_address_map;
-	/*
-	 * Make efi_get_time can be called before entering
-	 * virtual mode.
-	 */
-	efi.get_time = phys_efi_get_time;
+
 	early_iounmap(runtime, sizeof(efi_runtime_services_t));
 
 	return 0;
@@ -734,12 +714,10 @@ void __init efi_init(void)
 		efi_enabled = 0;
 		return;
 	}
-#ifdef CONFIG_X86_32
 	if (efi_native) {
 		x86_platform.get_wallclock = efi_get_time;
 		x86_platform.set_wallclock = efi_set_rtc_mmss;
 	}
-#endif
 
 #if EFI_DEBUG
 	print_efi_memmap();
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 337aefbfb003..5e2308d9c6be 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -516,8 +516,6 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size);
 extern int __init efi_uart_console_only (void);
 extern void efi_initialize_iomem_resources(struct resource *code_resource,
 		struct resource *data_resource, struct resource *bss_resource);
-extern unsigned long efi_get_time(void);
-extern int efi_set_rtc_mmss(unsigned long nowtime);
 extern void efi_reserve_boot_services(void);
 extern struct efi_memory_map memmap;
 
diff --git a/init/main.c b/init/main.c
index 9cf77ab138a6..ae70b647b4d9 100644
--- a/init/main.c
+++ b/init/main.c
@@ -461,6 +461,10 @@ static void __init mm_init(void)
 	percpu_init_late();
 	pgtable_cache_init();
 	vmalloc_init();
+#ifdef CONFIG_X86
+	if (efi_enabled)
+		efi_enter_virtual_mode();
+#endif
 }
 
 asmlinkage void __init start_kernel(void)
@@ -601,10 +605,6 @@ asmlinkage void __init start_kernel(void)
 	calibrate_delay();
 	pidmap_init();
 	anon_vma_init();
-#ifdef CONFIG_X86
-	if (efi_enabled)
-		efi_enter_virtual_mode();
-#endif
 	thread_info_cache_init();
 	cred_init();
 	fork_init(totalram_pages);
-- 
cgit v1.2.3-55-g7522


From 91716322d834cba34f4a7ed5e4a39673eb90862b Mon Sep 17 00:00:00 2001
From: Matt Fleming
Date: Mon, 22 Oct 2012 15:51:45 +0100
Subject: efivarfs: Add unique magic number

Using pstore's superblock magic number is no doubt going to cause
problems in the future. Give efivarfs its own magic number.

Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
 drivers/firmware/efivars.c | 2 +-
 include/uapi/linux/magic.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index 2c044343c99b..3b0cf9acb504 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -991,7 +991,7 @@ int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_maxbytes          = MAX_LFS_FILESIZE;
 	sb->s_blocksize         = PAGE_CACHE_SIZE;
 	sb->s_blocksize_bits    = PAGE_CACHE_SHIFT;
-	sb->s_magic             = PSTOREFS_MAGIC;
+	sb->s_magic             = EFIVARFS_MAGIC;
 	sb->s_op                = &efivarfs_ops;
 	sb->s_time_gran         = 1;
 
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index e15192cb9cf4..12f68c7ceba6 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -27,6 +27,7 @@
 #define ISOFS_SUPER_MAGIC	0x9660
 #define JFFS2_SUPER_MAGIC	0x72b6
 #define PSTOREFS_MAGIC		0x6165676C
+#define EFIVARFS_MAGIC		0xde5e81e4
 
 #define MINIX_SUPER_MAGIC	0x137F		/* minix v1 fs, 14 char names */
 #define MINIX_SUPER_MAGIC2	0x138F		/* minix v1 fs, 30 char names */
-- 
cgit v1.2.3-55-g7522


From e05ed4d1fad9e730995abb08cb9bc3bffac5018b Mon Sep 17 00:00:00 2001
From: Alexander Duyck
Date: Mon, 15 Oct 2012 10:19:39 -0700
Subject: swiotlb: Return physical addresses when calling
 swiotlb_tbl_map_single

This change makes it so that swiotlb_tbl_map_single will return a physical
address instead of a virtual address when called.  The advantage to this once
again is that we are avoiding a number of virt_to_phys and phys_to_virt
translations by working with everything as a physical address.

One change I had to make in order to support using physical addresses is that
I could no longer trust 0 to be a invalid physical address on all platforms.
So instead I made it so that ~0 is returned on error.  This should never be a
valid return value as it implies that only one byte would be available for
use.

In order to clarify things since we now have 2 physical addresses in use
inside of swiotlb_tbl_map_single I am renaming phys to orig_addr, and
dma_addr to tlb_addr.  This way is should be clear that orig_addr is
contained within io_orig_addr and tlb_addr is an address within the
io_tlb_addr buffer.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/swiotlb-xen.c | 22 ++++++-------
 include/linux/swiotlb.h   | 11 +++++--
 lib/swiotlb.c             | 78 ++++++++++++++++++++++++-----------------------
 3 files changed, 59 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 58db6df866ef..8a6035aa69c9 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -338,9 +338,8 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 				enum dma_data_direction dir,
 				struct dma_attrs *attrs)
 {
-	phys_addr_t phys = page_to_phys(page) + offset;
+	phys_addr_t map, phys = page_to_phys(page) + offset;
 	dma_addr_t dev_addr = xen_phys_to_bus(phys);
-	void *map;
 
 	BUG_ON(dir == DMA_NONE);
 	/*
@@ -356,16 +355,16 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * Oh well, have to allocate and map a bounce buffer.
 	 */
 	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir);
-	if (!map)
+	if (map == SWIOTLB_MAP_ERROR)
 		return DMA_ERROR_CODE;
 
-	dev_addr = xen_virt_to_bus(map);
+	dev_addr = xen_phys_to_bus(map);
 
 	/*
 	 * Ensure that the address returned is DMA'ble
 	 */
 	if (!dma_capable(dev, dev_addr, size)) {
-		swiotlb_tbl_unmap_single(dev, map, size, dir);
+		swiotlb_tbl_unmap_single(dev, phys_to_virt(map), size, dir);
 		dev_addr = 0;
 	}
 	return dev_addr;
@@ -494,11 +493,12 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 		if (swiotlb_force ||
 		    !dma_capable(hwdev, dev_addr, sg->length) ||
 		    range_straddles_page_boundary(paddr, sg->length)) {
-			void *map = swiotlb_tbl_map_single(hwdev,
-							   start_dma_addr,
-							   sg_phys(sg),
-							   sg->length, dir);
-			if (!map) {
+			phys_addr_t map = swiotlb_tbl_map_single(hwdev,
+								 start_dma_addr,
+								 sg_phys(sg),
+								 sg->length,
+								 dir);
+			if (map == SWIOTLB_MAP_ERROR) {
 				/* Don't panic here, we expect map_sg users
 				   to do proper error handling. */
 				xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
@@ -506,7 +506,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 				sgl[0].dma_length = 0;
 				return DMA_ERROR_CODE;
 			}
-			sg->dma_address = xen_virt_to_bus(map);
+			sg->dma_address = xen_phys_to_bus(map);
 		} else
 			sg->dma_address = dev_addr;
 		sg->dma_length = sg->length;
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 8d08b3ed406d..1995f3e04fed 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -34,9 +34,14 @@ enum dma_sync_target {
 	SYNC_FOR_CPU = 0,
 	SYNC_FOR_DEVICE = 1,
 };
-extern void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr,
-				    phys_addr_t phys, size_t size,
-				    enum dma_data_direction dir);
+
+/* define the last possible byte of physical address space as a mapping error */
+#define SWIOTLB_MAP_ERROR (~(phys_addr_t)0x0)
+
+extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
+					  dma_addr_t tbl_dma_addr,
+					  phys_addr_t phys, size_t size,
+					  enum dma_data_direction dir);
 
 extern void swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr,
 				     size_t size, enum dma_data_direction dir);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index f8c0d4e1d1d3..3adc148bb8d8 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -393,12 +393,13 @@ void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
 }
 EXPORT_SYMBOL_GPL(swiotlb_bounce);
 
-void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr,
-			     phys_addr_t phys, size_t size,
-			     enum dma_data_direction dir)
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
+				   dma_addr_t tbl_dma_addr,
+				   phys_addr_t orig_addr, size_t size,
+				   enum dma_data_direction dir)
 {
 	unsigned long flags;
-	char *dma_addr;
+	phys_addr_t tlb_addr;
 	unsigned int nslots, stride, index, wrap;
 	int i;
 	unsigned long mask;
@@ -462,7 +463,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr,
 				io_tlb_list[i] = 0;
 			for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
 				io_tlb_list[i] = ++count;
-			dma_addr = (char *)phys_to_virt(io_tlb_start) + (index << IO_TLB_SHIFT);
+			tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT);
 
 			/*
 			 * Update the indices to avoid searching in the next
@@ -480,7 +481,7 @@ void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr,
 
 not_found:
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
-	return NULL;
+	return SWIOTLB_MAP_ERROR;
 found:
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
 
@@ -490,11 +491,12 @@ found:
 	 * needed.
 	 */
 	for (i = 0; i < nslots; i++)
-		io_tlb_orig_addr[index+i] = phys + (i << IO_TLB_SHIFT);
+		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
 	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
-		swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);
+		swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr), size,
+			       DMA_TO_DEVICE);
 
-	return dma_addr;
+	return tlb_addr;
 }
 EXPORT_SYMBOL_GPL(swiotlb_tbl_map_single);
 
@@ -502,9 +504,8 @@ EXPORT_SYMBOL_GPL(swiotlb_tbl_map_single);
  * Allocates bounce buffer and returns its kernel virtual address.
  */
 
-static void *
-map_single(struct device *hwdev, phys_addr_t phys, size_t size,
-	   enum dma_data_direction dir)
+phys_addr_t map_single(struct device *hwdev, phys_addr_t phys, size_t size,
+		       enum dma_data_direction dir)
 {
 	dma_addr_t start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
 
@@ -598,12 +599,15 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		dma_mask = hwdev->coherent_dma_mask;
 
 	ret = (void *)__get_free_pages(flags, order);
-	if (ret && swiotlb_virt_to_bus(hwdev, ret) + size - 1 > dma_mask) {
-		/*
-		 * The allocated memory isn't reachable by the device.
-		 */
-		free_pages((unsigned long) ret, order);
-		ret = NULL;
+	if (ret) {
+		dev_addr = swiotlb_virt_to_bus(hwdev, ret);
+		if (dev_addr + size - 1 > dma_mask) {
+			/*
+			 * The allocated memory isn't reachable by the device.
+			 */
+			free_pages((unsigned long) ret, order);
+			ret = NULL;
+		}
 	}
 	if (!ret) {
 		/*
@@ -611,13 +615,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		 * GFP_DMA memory; fall back on map_single(), which
 		 * will grab memory from the lowest available address range.
 		 */
-		ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
-		if (!ret)
+		phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
+		if (paddr == SWIOTLB_MAP_ERROR)
 			return NULL;
-	}
 
-	memset(ret, 0, size);
-	dev_addr = swiotlb_virt_to_bus(hwdev, ret);
+		ret = phys_to_virt(paddr);
+		dev_addr = phys_to_dma(hwdev, paddr);
+	}
 
 	/* Confirm address can be DMA'd by device */
 	if (dev_addr + size - 1 > dma_mask) {
@@ -629,7 +633,10 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		swiotlb_tbl_unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
 		return NULL;
 	}
+
 	*dma_handle = dev_addr;
+	memset(ret, 0, size);
+
 	return ret;
 }
 EXPORT_SYMBOL(swiotlb_alloc_coherent);
@@ -686,9 +693,8 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 			    enum dma_data_direction dir,
 			    struct dma_attrs *attrs)
 {
-	phys_addr_t phys = page_to_phys(page) + offset;
+	phys_addr_t map, phys = page_to_phys(page) + offset;
 	dma_addr_t dev_addr = phys_to_dma(dev, phys);
-	void *map;
 
 	BUG_ON(dir == DMA_NONE);
 	/*
@@ -699,22 +705,18 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
 		return dev_addr;
 
-	/*
-	 * Oh well, have to allocate and map a bounce buffer.
-	 */
+	/* Oh well, have to allocate and map a bounce buffer. */
 	map = map_single(dev, phys, size, dir);
-	if (!map) {
+	if (map == SWIOTLB_MAP_ERROR) {
 		swiotlb_full(dev, size, dir, 1);
 		return phys_to_dma(dev, io_tlb_overflow_buffer);
 	}
 
-	dev_addr = swiotlb_virt_to_bus(dev, map);
+	dev_addr = phys_to_dma(dev, map);
 
-	/*
-	 * Ensure that the address returned is DMA'ble
-	 */
+	/* Ensure that the address returned is DMA'ble */
 	if (!dma_capable(dev, dev_addr, size)) {
-		swiotlb_tbl_unmap_single(dev, map, size, dir);
+		swiotlb_tbl_unmap_single(dev, phys_to_virt(map), size, dir);
 		return phys_to_dma(dev, io_tlb_overflow_buffer);
 	}
 
@@ -840,9 +842,9 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 
 		if (swiotlb_force ||
 		    !dma_capable(hwdev, dev_addr, sg->length)) {
-			void *map = map_single(hwdev, sg_phys(sg),
-					       sg->length, dir);
-			if (!map) {
+			phys_addr_t map = map_single(hwdev, sg_phys(sg),
+						     sg->length, dir);
+			if (map == SWIOTLB_MAP_ERROR) {
 				/* Don't panic here, we expect map_sg users
 				   to do proper error handling. */
 				swiotlb_full(hwdev, sg->length, dir, 0);
@@ -851,7 +853,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 				sgl[0].dma_length = 0;
 				return 0;
 			}
-			sg->dma_address = swiotlb_virt_to_bus(hwdev, map);
+			sg->dma_address = phys_to_dma(hwdev, map);
 		} else
 			sg->dma_address = dev_addr;
 		sg->dma_length = sg->length;
-- 
cgit v1.2.3-55-g7522


From 61ca08c3220032dd88815b3465d56cb779258168 Mon Sep 17 00:00:00 2001
From: Alexander Duyck
Date: Mon, 15 Oct 2012 10:19:44 -0700
Subject: swiotlb: Use physical addresses for swiotlb_tbl_unmap_single

This change makes it so that the unmap functionality also uses physical
addresses.  This helps to further reduce the use of virt_to_phys and
phys_to_virt functions.

In order to clarify things since we now have 2 physical addresses in use
inside of swiotlb_tbl_unmap_single I am renaming phys to orig_addr, and
dma_addr to tlb_addr.  This way is should be clear that orig_addr is
contained within io_orig_addr and tlb_addr is an address within the
io_tlb_addr buffer.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/swiotlb-xen.c |  4 ++--
 include/linux/swiotlb.h   |  3 ++-
 lib/swiotlb.c             | 37 +++++++++++++++++++------------------
 3 files changed, 23 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 8a6035aa69c9..4cedc284b5df 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -364,7 +364,7 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * Ensure that the address returned is DMA'ble
 	 */
 	if (!dma_capable(dev, dev_addr, size)) {
-		swiotlb_tbl_unmap_single(dev, phys_to_virt(map), size, dir);
+		swiotlb_tbl_unmap_single(dev, map, size, dir);
 		dev_addr = 0;
 	}
 	return dev_addr;
@@ -388,7 +388,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr)) {
-		swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
+		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir);
 		return;
 	}
 
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 1995f3e04fed..291643c6b88b 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -43,7 +43,8 @@ extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 					  phys_addr_t phys, size_t size,
 					  enum dma_data_direction dir);
 
-extern void swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr,
+extern void swiotlb_tbl_unmap_single(struct device *hwdev,
+				     phys_addr_t tlb_addr,
 				     size_t size, enum dma_data_direction dir);
 
 extern void swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr,
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 3adc148bb8d8..d7701dcf407f 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -515,20 +515,20 @@ phys_addr_t map_single(struct device *hwdev, phys_addr_t phys, size_t size,
 /*
  * dma_addr is the kernel virtual address of the bounce buffer to unmap.
  */
-void
-swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, size_t size,
-			enum dma_data_direction dir)
+void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
+			      size_t size, enum dma_data_direction dir)
 {
 	unsigned long flags;
 	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	int index = (dma_addr - (char *)phys_to_virt(io_tlb_start)) >> IO_TLB_SHIFT;
-	phys_addr_t phys = io_tlb_orig_addr[index];
+	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+	phys_addr_t orig_addr = io_tlb_orig_addr[index];
 
 	/*
 	 * First, sync the memory before unmapping the entry
 	 */
 	if (phys && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
-		swiotlb_bounce(phys, dma_addr, size, DMA_FROM_DEVICE);
+		swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr),
+			       size, DMA_FROM_DEVICE);
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -621,17 +621,18 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 
 		ret = phys_to_virt(paddr);
 		dev_addr = phys_to_dma(hwdev, paddr);
-	}
 
-	/* Confirm address can be DMA'd by device */
-	if (dev_addr + size - 1 > dma_mask) {
-		printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
-		       (unsigned long long)dma_mask,
-		       (unsigned long long)dev_addr);
+		/* Confirm address can be DMA'd by device */
+		if (dev_addr + size - 1 > dma_mask) {
+			printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
+			       (unsigned long long)dma_mask,
+			       (unsigned long long)dev_addr);
 
-		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-		swiotlb_tbl_unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
-		return NULL;
+			/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
+			swiotlb_tbl_unmap_single(hwdev, paddr,
+						 size, DMA_TO_DEVICE);
+			return NULL;
+		}
 	}
 
 	*dma_handle = dev_addr;
@@ -652,7 +653,7 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 		free_pages((unsigned long)vaddr, get_order(size));
 	else
 		/* DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single */
-		swiotlb_tbl_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
+		swiotlb_tbl_unmap_single(hwdev, paddr, size, DMA_TO_DEVICE);
 }
 EXPORT_SYMBOL(swiotlb_free_coherent);
 
@@ -716,7 +717,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 
 	/* Ensure that the address returned is DMA'ble */
 	if (!dma_capable(dev, dev_addr, size)) {
-		swiotlb_tbl_unmap_single(dev, phys_to_virt(map), size, dir);
+		swiotlb_tbl_unmap_single(dev, map, size, dir);
 		return phys_to_dma(dev, io_tlb_overflow_buffer);
 	}
 
@@ -740,7 +741,7 @@ static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 	BUG_ON(dir == DMA_NONE);
 
 	if (is_swiotlb_buffer(paddr)) {
-		swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
+		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir);
 		return;
 	}
 
-- 
cgit v1.2.3-55-g7522


From fbfda893eb570bbe9e9ad9128b6e9cf2a1e48c87 Mon Sep 17 00:00:00 2001
From: Alexander Duyck
Date: Mon, 15 Oct 2012 10:19:49 -0700
Subject: swiotlb: Use physical addresses instead of virtual in
 swiotlb_tbl_sync_single

This change makes it so that the sync functionality also uses physical
addresses.  This helps to further reduce the use of virt_to_phys and
phys_to_virt functions.

In order to clarify things since we now have 2 physical addresses in use
inside of swiotlb_tbl_sync_single I am renaming phys to orig_addr, and
dma_addr to tlb_addr.  This way is should be clear that orig_addr is
contained within io_orig_addr and tlb_addr is an address within the
io_tlb_addr buffer.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/swiotlb-xen.c |  3 +--
 include/linux/swiotlb.h   |  3 ++-
 lib/swiotlb.c             | 22 +++++++++++-----------
 3 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 4cedc284b5df..af47e7594460 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -433,8 +433,7 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr)) {
-		swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir,
-				       target);
+		swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
 		return;
 	}
 
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 291643c6b88b..e0ac98fd81a9 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -47,7 +47,8 @@ extern void swiotlb_tbl_unmap_single(struct device *hwdev,
 				     phys_addr_t tlb_addr,
 				     size_t size, enum dma_data_direction dir);
 
-extern void swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr,
+extern void swiotlb_tbl_sync_single(struct device *hwdev,
+				    phys_addr_t tlb_addr,
 				    size_t size, enum dma_data_direction dir,
 				    enum dma_sync_target target);
 
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index d7701dcf407f..16a548dc91ac 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -557,26 +557,27 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 }
 EXPORT_SYMBOL_GPL(swiotlb_tbl_unmap_single);
 
-void
-swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr, size_t size,
-			enum dma_data_direction dir,
-			enum dma_sync_target target)
+void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
+			     size_t size, enum dma_data_direction dir,
+			     enum dma_sync_target target)
 {
-	int index = (dma_addr - (char *)phys_to_virt(io_tlb_start)) >> IO_TLB_SHIFT;
-	phys_addr_t phys = io_tlb_orig_addr[index];
+	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+	phys_addr_t orig_addr = io_tlb_orig_addr[index];
 
-	phys += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1));
+	orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
 
 	switch (target) {
 	case SYNC_FOR_CPU:
 		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
-			swiotlb_bounce(phys, dma_addr, size, DMA_FROM_DEVICE);
+			swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr),
+				       size, DMA_FROM_DEVICE);
 		else
 			BUG_ON(dir != DMA_TO_DEVICE);
 		break;
 	case SYNC_FOR_DEVICE:
 		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
-			swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);
+			swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr),
+				       size, DMA_TO_DEVICE);
 		else
 			BUG_ON(dir != DMA_FROM_DEVICE);
 		break;
@@ -785,8 +786,7 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 	BUG_ON(dir == DMA_NONE);
 
 	if (is_swiotlb_buffer(paddr)) {
-		swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir,
-				       target);
+		swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
 		return;
 	}
 
-- 
cgit v1.2.3-55-g7522


From af51a9f1848ff50079a10def56a2c064f326af22 Mon Sep 17 00:00:00 2001
From: Alexander Duyck
Date: Mon, 15 Oct 2012 10:19:55 -0700
Subject: swiotlb: Do not export swiotlb_bounce since there are no external
 consumers

Currently swiotlb is the only consumer for swiotlb_bounce.  Since that is the
case it doesn't make much sense to be exporting it so make it a static
function only.

In addition we can save a few more lines of code by making it so that it
accepts the DMA address as a physical address instead of a virtual one.  This
is the last piece in essentially pushing all of the DMA address values to use
physical addresses in swiotlb.

In order to clarify things since we now have 2 physical addresses in use
inside of swiotlb_bounce I am renaming phys to orig_addr, and dma_addr to
tlb_addr.  This way is should be clear that orig_addr is contained within
io_orig_addr and tlb_addr is an address within the io_tlb_addr buffer.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 include/linux/swiotlb.h |  3 ---
 lib/swiotlb.c           | 35 ++++++++++++++++-------------------
 2 files changed, 16 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index e0ac98fd81a9..071d62c214a6 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -53,9 +53,6 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev,
 				    enum dma_sync_target target);
 
 /* Accessory functions. */
-extern void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
-			   enum dma_data_direction dir);
-
 extern void
 *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			dma_addr_t *dma_handle, gfp_t flags);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 16a548dc91ac..196b06984dec 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -355,14 +355,15 @@ static int is_swiotlb_buffer(phys_addr_t paddr)
 /*
  * Bounce: copy the swiotlb buffer back to the original dma location
  */
-void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
-		    enum dma_data_direction dir)
+static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
+			   size_t size, enum dma_data_direction dir)
 {
-	unsigned long pfn = PFN_DOWN(phys);
+	unsigned long pfn = PFN_DOWN(orig_addr);
+	unsigned char *vaddr = phys_to_virt(tlb_addr);
 
 	if (PageHighMem(pfn_to_page(pfn))) {
 		/* The buffer does not have a mapping.  Map it in and copy */
-		unsigned int offset = phys & ~PAGE_MASK;
+		unsigned int offset = orig_addr & ~PAGE_MASK;
 		char *buffer;
 		unsigned int sz = 0;
 		unsigned long flags;
@@ -373,25 +374,23 @@ void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
 			local_irq_save(flags);
 			buffer = kmap_atomic(pfn_to_page(pfn));
 			if (dir == DMA_TO_DEVICE)
-				memcpy(dma_addr, buffer + offset, sz);
+				memcpy(vaddr, buffer + offset, sz);
 			else
-				memcpy(buffer + offset, dma_addr, sz);
+				memcpy(buffer + offset, vaddr, sz);
 			kunmap_atomic(buffer);
 			local_irq_restore(flags);
 
 			size -= sz;
 			pfn++;
-			dma_addr += sz;
+			vaddr += sz;
 			offset = 0;
 		}
+	} else if (dir == DMA_TO_DEVICE) {
+		memcpy(vaddr, phys_to_virt(orig_addr), size);
 	} else {
-		if (dir == DMA_TO_DEVICE)
-			memcpy(dma_addr, phys_to_virt(phys), size);
-		else
-			memcpy(phys_to_virt(phys), dma_addr, size);
+		memcpy(phys_to_virt(orig_addr), vaddr, size);
 	}
 }
-EXPORT_SYMBOL_GPL(swiotlb_bounce);
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 				   dma_addr_t tbl_dma_addr,
@@ -493,8 +492,7 @@ found:
 	for (i = 0; i < nslots; i++)
 		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
 	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
-		swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr), size,
-			       DMA_TO_DEVICE);
+		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
 
 	return tlb_addr;
 }
@@ -526,9 +524,8 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	/*
 	 * First, sync the memory before unmapping the entry
 	 */
-	if (phys && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
-		swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr),
-			       size, DMA_FROM_DEVICE);
+	if (orig_addr && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -569,14 +566,14 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 	switch (target) {
 	case SYNC_FOR_CPU:
 		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
-			swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr),
+			swiotlb_bounce(orig_addr, tlb_addr,
 				       size, DMA_FROM_DEVICE);
 		else
 			BUG_ON(dir != DMA_TO_DEVICE);
 		break;
 	case SYNC_FOR_DEVICE:
 		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
-			swiotlb_bounce(orig_addr, phys_to_virt(tlb_addr),
+			swiotlb_bounce(orig_addr, tlb_addr,
 				       size, DMA_TO_DEVICE);
 		else
 			BUG_ON(dir != DMA_FROM_DEVICE);
-- 
cgit v1.2.3-55-g7522


From 5e3b08749951e5746d3e747f1ffae37eff2d08d5 Mon Sep 17 00:00:00 2001
From: Rob Clark
Date: Mon, 29 Oct 2012 09:31:12 +0100
Subject: staging: drm/omap: add support for ARCH_MULTIPLATFORM

Remove usage of plat/cpu.h and get information from platform data
instead.  This enables omapdrm to be built with ARCH_MULTIPLATFORM.

Signed-off-by: Rob Clark <rob@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm/mach-omap2/drm.c                | 7 +++++++
 drivers/staging/omapdrm/Kconfig          | 2 +-
 drivers/staging/omapdrm/omap_dmm_tiler.h | 1 -
 drivers/staging/omapdrm/omap_drv.c       | 6 +++++-
 drivers/staging/omapdrm/omap_drv.h       | 2 ++
 include/linux/platform_data/omap_drm.h   | 1 +
 6 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/drm.c b/arch/arm/mach-omap2/drm.c
index 72e0f01b715c..49a7ffb716a5 100644
--- a/arch/arm/mach-omap2/drm.c
+++ b/arch/arm/mach-omap2/drm.c
@@ -23,15 +23,20 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
+#include <linux/platform_data/omap_drm.h>
 
 #include <plat/omap_device.h>
 #include <plat/omap_hwmod.h>
+#include <plat/cpu.h>
 
 #if defined(CONFIG_DRM_OMAP) || (CONFIG_DRM_OMAP_MODULE)
 
+static struct omap_drm_platform_data platform_data;
+
 static struct platform_device omap_drm_device = {
 	.dev = {
 		.coherent_dma_mask = DMA_BIT_MASK(32),
+		.platform_data = &platform_data,
 	},
 	.name = "omapdrm",
 	.id = 0,
@@ -52,6 +57,8 @@ static int __init omap_init_drm(void)
 			oh->name);
 	}
 
+	platform_data.omaprev = GET_OMAP_REVISION();
+
 	return platform_device_register(&omap_drm_device);
 
 }
diff --git a/drivers/staging/omapdrm/Kconfig b/drivers/staging/omapdrm/Kconfig
index 81a7cba4a0c5..b724a4131435 100644
--- a/drivers/staging/omapdrm/Kconfig
+++ b/drivers/staging/omapdrm/Kconfig
@@ -2,7 +2,7 @@
 config DRM_OMAP
 	tristate "OMAP DRM"
 	depends on DRM && !CONFIG_FB_OMAP2
-	depends on ARCH_OMAP2PLUS
+	depends on ARCH_OMAP2PLUS || ARCH_MULTIPLATFORM
 	select DRM_KMS_HELPER
 	select OMAP2_DSS
 	select FB_SYS_FILLRECT
diff --git a/drivers/staging/omapdrm/omap_dmm_tiler.h b/drivers/staging/omapdrm/omap_dmm_tiler.h
index c0271a2ac877..4fdd61e54bd2 100644
--- a/drivers/staging/omapdrm/omap_dmm_tiler.h
+++ b/drivers/staging/omapdrm/omap_dmm_tiler.h
@@ -16,7 +16,6 @@
 #ifndef OMAP_DMM_TILER_H
 #define OMAP_DMM_TILER_H
 
-#include <plat/cpu.h>
 #include "omap_drv.h"
 #include "tcm.h"
 
diff --git a/drivers/staging/omapdrm/omap_drv.c b/drivers/staging/omapdrm/omap_drv.c
index 09653b88e0ec..6ae2f763b27a 100644
--- a/drivers/staging/omapdrm/omap_drv.c
+++ b/drivers/staging/omapdrm/omap_drv.c
@@ -417,13 +417,14 @@ static void omap_modeset_free(struct drm_device *dev)
 static int ioctl_get_param(struct drm_device *dev, void *data,
 		struct drm_file *file_priv)
 {
+	struct omap_drm_private *priv = dev->dev_private;
 	struct drm_omap_param *args = data;
 
 	DBG("%p: param=%llu", dev, args->param);
 
 	switch (args->param) {
 	case OMAP_PARAM_CHIPSET_ID:
-		args->value = GET_OMAP_TYPE;
+		args->value = priv->omaprev;
 		break;
 	default:
 		DBG("unknown parameter %lld", args->param);
@@ -555,6 +556,7 @@ struct drm_ioctl_desc ioctls[DRM_COMMAND_END - DRM_COMMAND_BASE] = {
  */
 static int dev_load(struct drm_device *dev, unsigned long flags)
 {
+	struct omap_drm_platform_data *pdata = dev->dev->platform_data;
 	struct omap_drm_private *priv;
 	int ret;
 
@@ -566,6 +568,8 @@ static int dev_load(struct drm_device *dev, unsigned long flags)
 		return -ENOMEM;
 	}
 
+	priv->omaprev = pdata->omaprev;
+
 	dev->dev_private = priv;
 
 	priv->wq = alloc_ordered_workqueue("omapdrm", 0);
diff --git a/drivers/staging/omapdrm/omap_drv.h b/drivers/staging/omapdrm/omap_drv.h
index 9dc72d143ff3..8f7c447930fa 100644
--- a/drivers/staging/omapdrm/omap_drv.h
+++ b/drivers/staging/omapdrm/omap_drv.h
@@ -40,6 +40,8 @@
 #define MAX_MAPPERS 2
 
 struct omap_drm_private {
+	uint32_t omaprev;
+
 	unsigned int num_crtcs;
 	struct drm_crtc *crtcs[8];
 
diff --git a/include/linux/platform_data/omap_drm.h b/include/linux/platform_data/omap_drm.h
index 3da73bdc2031..f4e4a237ebd2 100644
--- a/include/linux/platform_data/omap_drm.h
+++ b/include/linux/platform_data/omap_drm.h
@@ -46,6 +46,7 @@ struct omap_kms_platform_data {
 };
 
 struct omap_drm_platform_data {
+	uint32_t omaprev;
 	struct omap_kms_platform_data *kms_pdata;
 };
 
-- 
cgit v1.2.3-55-g7522


From dc4dc36056392c0b0b1ca9e81bebff964b9297e0 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 30 Oct 2012 12:34:05 +0530
Subject: spi: tegra: add spi driver for SLINK controller

Tegra20/Tegra30 supports the spi interface through its SLINK
controller. Add spi driver for SLINK controller.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Reviewed-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 .../bindings/spi/nvidia,tegra20-slink.txt          |   26 +
 drivers/spi/Kconfig                                |    6 +
 drivers/spi/Makefile                               |    2 +-
 drivers/spi/spi-tegra20-slink.c                    | 1359 ++++++++++++++++++++
 include/linux/spi/spi-tegra.h                      |   40 +
 5 files changed, 1432 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt
 create mode 100644 drivers/spi/spi-tegra20-slink.c
 create mode 100644 include/linux/spi/spi-tegra.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt b/Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt
new file mode 100644
index 000000000000..f5b1ad1a1ec3
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt
@@ -0,0 +1,26 @@
+NVIDIA Tegra20/Tegra30 SLINK controller.
+
+Required properties:
+- compatible : should be "nvidia,tegra20-slink", "nvidia,tegra30-slink".
+- reg: Should contain SLINK registers location and length.
+- interrupts: Should contain SLINK interrupts.
+- nvidia,dma-request-selector : The Tegra DMA controller's phandle and
+  request selector for this SLINK controller.
+
+Recommended properties:
+- spi-max-frequency: Definition as per
+                     Documentation/devicetree/bindings/spi/spi-bus.txt
+
+Example:
+
+slink@7000d600 {
+	compatible = "nvidia,tegra20-slink";
+	reg = <0x7000d600 0x200>;
+	interrupts = <0 82 0x04>;
+	nvidia,dma-request-selector = <&apbdma 16>;
+	spi-max-frequency = <25000000>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "disabled";
+};
+
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 1acae359cabe..25290d9780b2 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -385,6 +385,12 @@ config SPI_MXS
 	help
 	  SPI driver for Freescale MXS devices.
 
+config SPI_TEGRA20_SLINK
+	tristate "Nvidia Tegra20/Tegra30 SLINK Controller"
+	depends on ARCH_TEGRA && TEGRA20_APB_DMA
+	help
+	  SPI driver for Nvidia Tegra20/Tegra30 SLINK Controller interface.
+
 config SPI_TI_SSP
 	tristate "TI Sequencer Serial Port - SPI Support"
 	depends on MFD_TI_SSP
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index c48df47e4b0f..f87c0f142e5a 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -60,10 +60,10 @@ obj-$(CONFIG_SPI_SH_MSIOF)		+= spi-sh-msiof.o
 obj-$(CONFIG_SPI_SH_SCI)		+= spi-sh-sci.o
 obj-$(CONFIG_SPI_SIRF)		+= spi-sirf.o
 obj-$(CONFIG_SPI_STMP3XXX)		+= spi-stmp.o
+obj-$(CONFIG_SPI_TEGRA20_SLINK)		+= spi-tegra20-slink.o
 obj-$(CONFIG_SPI_TI_SSP)		+= spi-ti-ssp.o
 obj-$(CONFIG_SPI_TLE62X0)		+= spi-tle62x0.o
 obj-$(CONFIG_SPI_TOPCLIFF_PCH)		+= spi-topcliff-pch.o
 obj-$(CONFIG_SPI_TXX9)			+= spi-txx9.o
 obj-$(CONFIG_SPI_XCOMM)		+= spi-xcomm.o
 obj-$(CONFIG_SPI_XILINX)		+= spi-xilinx.o
-
diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c
new file mode 100644
index 000000000000..b8985be81d96
--- /dev/null
+++ b/drivers/spi/spi-tegra20-slink.c
@@ -0,0 +1,1359 @@
+/*
+ * SPI driver for Nvidia's Tegra20/Tegra30 SLINK Controller.
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-tegra.h>
+#include <mach/clk.h>
+
+#define SLINK_COMMAND			0x000
+#define SLINK_BIT_LENGTH(x)		(((x) & 0x1f) << 0)
+#define SLINK_WORD_SIZE(x)		(((x) & 0x1f) << 5)
+#define SLINK_BOTH_EN			(1 << 10)
+#define SLINK_CS_SW			(1 << 11)
+#define SLINK_CS_VALUE			(1 << 12)
+#define SLINK_CS_POLARITY		(1 << 13)
+#define SLINK_IDLE_SDA_DRIVE_LOW	(0 << 16)
+#define SLINK_IDLE_SDA_DRIVE_HIGH	(1 << 16)
+#define SLINK_IDLE_SDA_PULL_LOW		(2 << 16)
+#define SLINK_IDLE_SDA_PULL_HIGH	(3 << 16)
+#define SLINK_IDLE_SDA_MASK		(3 << 16)
+#define SLINK_CS_POLARITY1		(1 << 20)
+#define SLINK_CK_SDA			(1 << 21)
+#define SLINK_CS_POLARITY2		(1 << 22)
+#define SLINK_CS_POLARITY3		(1 << 23)
+#define SLINK_IDLE_SCLK_DRIVE_LOW	(0 << 24)
+#define SLINK_IDLE_SCLK_DRIVE_HIGH	(1 << 24)
+#define SLINK_IDLE_SCLK_PULL_LOW	(2 << 24)
+#define SLINK_IDLE_SCLK_PULL_HIGH	(3 << 24)
+#define SLINK_IDLE_SCLK_MASK		(3 << 24)
+#define SLINK_M_S			(1 << 28)
+#define SLINK_WAIT			(1 << 29)
+#define SLINK_GO			(1 << 30)
+#define SLINK_ENB			(1 << 31)
+
+#define SLINK_MODES			(SLINK_IDLE_SCLK_MASK | SLINK_CK_SDA)
+
+#define SLINK_COMMAND2			0x004
+#define SLINK_LSBFE			(1 << 0)
+#define SLINK_SSOE			(1 << 1)
+#define SLINK_SPIE			(1 << 4)
+#define SLINK_BIDIROE			(1 << 6)
+#define SLINK_MODFEN			(1 << 7)
+#define SLINK_INT_SIZE(x)		(((x) & 0x1f) << 8)
+#define SLINK_CS_ACTIVE_BETWEEN		(1 << 17)
+#define SLINK_SS_EN_CS(x)		(((x) & 0x3) << 18)
+#define SLINK_SS_SETUP(x)		(((x) & 0x3) << 20)
+#define SLINK_FIFO_REFILLS_0		(0 << 22)
+#define SLINK_FIFO_REFILLS_1		(1 << 22)
+#define SLINK_FIFO_REFILLS_2		(2 << 22)
+#define SLINK_FIFO_REFILLS_3		(3 << 22)
+#define SLINK_FIFO_REFILLS_MASK		(3 << 22)
+#define SLINK_WAIT_PACK_INT(x)		(((x) & 0x7) << 26)
+#define SLINK_SPC0			(1 << 29)
+#define SLINK_TXEN			(1 << 30)
+#define SLINK_RXEN			(1 << 31)
+
+#define SLINK_STATUS			0x008
+#define SLINK_COUNT(val)		(((val) >> 0) & 0x1f)
+#define SLINK_WORD(val)			(((val) >> 5) & 0x1f)
+#define SLINK_BLK_CNT(val)		(((val) >> 0) & 0xffff)
+#define SLINK_MODF			(1 << 16)
+#define SLINK_RX_UNF			(1 << 18)
+#define SLINK_TX_OVF			(1 << 19)
+#define SLINK_TX_FULL			(1 << 20)
+#define SLINK_TX_EMPTY			(1 << 21)
+#define SLINK_RX_FULL			(1 << 22)
+#define SLINK_RX_EMPTY			(1 << 23)
+#define SLINK_TX_UNF			(1 << 24)
+#define SLINK_RX_OVF			(1 << 25)
+#define SLINK_TX_FLUSH			(1 << 26)
+#define SLINK_RX_FLUSH			(1 << 27)
+#define SLINK_SCLK			(1 << 28)
+#define SLINK_ERR			(1 << 29)
+#define SLINK_RDY			(1 << 30)
+#define SLINK_BSY			(1 << 31)
+#define SLINK_FIFO_ERROR		(SLINK_TX_OVF | SLINK_RX_UNF |	\
+					SLINK_TX_UNF | SLINK_RX_OVF)
+
+#define SLINK_FIFO_EMPTY		(SLINK_TX_EMPTY | SLINK_RX_EMPTY)
+
+#define SLINK_MAS_DATA			0x010
+#define SLINK_SLAVE_DATA		0x014
+
+#define SLINK_DMA_CTL			0x018
+#define SLINK_DMA_BLOCK_SIZE(x)		(((x) & 0xffff) << 0)
+#define SLINK_TX_TRIG_1			(0 << 16)
+#define SLINK_TX_TRIG_4			(1 << 16)
+#define SLINK_TX_TRIG_8			(2 << 16)
+#define SLINK_TX_TRIG_16		(3 << 16)
+#define SLINK_TX_TRIG_MASK		(3 << 16)
+#define SLINK_RX_TRIG_1			(0 << 18)
+#define SLINK_RX_TRIG_4			(1 << 18)
+#define SLINK_RX_TRIG_8			(2 << 18)
+#define SLINK_RX_TRIG_16		(3 << 18)
+#define SLINK_RX_TRIG_MASK		(3 << 18)
+#define SLINK_PACKED			(1 << 20)
+#define SLINK_PACK_SIZE_4		(0 << 21)
+#define SLINK_PACK_SIZE_8		(1 << 21)
+#define SLINK_PACK_SIZE_16		(2 << 21)
+#define SLINK_PACK_SIZE_32		(3 << 21)
+#define SLINK_PACK_SIZE_MASK		(3 << 21)
+#define SLINK_IE_TXC			(1 << 26)
+#define SLINK_IE_RXC			(1 << 27)
+#define SLINK_DMA_EN			(1 << 31)
+
+#define SLINK_STATUS2			0x01c
+#define SLINK_TX_FIFO_EMPTY_COUNT(val)	(((val) & 0x3f) >> 0)
+#define SLINK_RX_FIFO_FULL_COUNT(val)	(((val) & 0x3f0000) >> 16)
+#define SLINK_SS_HOLD_TIME(val)		(((val) & 0xF) << 6)
+
+#define SLINK_TX_FIFO			0x100
+#define SLINK_RX_FIFO			0x180
+
+#define DATA_DIR_TX			(1 << 0)
+#define DATA_DIR_RX			(1 << 1)
+
+#define SLINK_DMA_TIMEOUT		(msecs_to_jiffies(1000))
+
+#define DEFAULT_SPI_DMA_BUF_LEN		(16*1024)
+#define TX_FIFO_EMPTY_COUNT_MAX		SLINK_TX_FIFO_EMPTY_COUNT(0x20)
+#define RX_FIFO_FULL_COUNT_ZERO		SLINK_RX_FIFO_FULL_COUNT(0)
+
+#define SLINK_STATUS2_RESET \
+	(TX_FIFO_EMPTY_COUNT_MAX | RX_FIFO_FULL_COUNT_ZERO << 16)
+
+#define MAX_CHIP_SELECT			4
+#define SLINK_FIFO_DEPTH		32
+
+struct tegra_slink_chip_data {
+	bool cs_hold_time;
+};
+
+struct tegra_slink_data {
+	struct device				*dev;
+	struct spi_master			*master;
+	const struct tegra_slink_chip_data	*chip_data;
+	spinlock_t				lock;
+
+	struct clk				*clk;
+	void __iomem				*base;
+	phys_addr_t				phys;
+	unsigned				irq;
+	int					dma_req_sel;
+	u32					spi_max_frequency;
+	u32					cur_speed;
+
+	struct spi_device			*cur_spi;
+	unsigned				cur_pos;
+	unsigned				cur_len;
+	unsigned				words_per_32bit;
+	unsigned				bytes_per_word;
+	unsigned				curr_dma_words;
+	unsigned				cur_direction;
+
+	unsigned				cur_rx_pos;
+	unsigned				cur_tx_pos;
+
+	unsigned				dma_buf_size;
+	unsigned				max_buf_size;
+	bool					is_curr_dma_xfer;
+	bool					is_hw_based_cs;
+
+	struct completion			rx_dma_complete;
+	struct completion			tx_dma_complete;
+
+	u32					tx_status;
+	u32					rx_status;
+	u32					status_reg;
+	bool					is_packed;
+	unsigned long				packed_size;
+
+	u32					command_reg;
+	u32					command2_reg;
+	u32					dma_control_reg;
+	u32					def_command_reg;
+	u32					def_command2_reg;
+
+	struct completion			xfer_completion;
+	struct spi_transfer			*curr_xfer;
+	struct dma_chan				*rx_dma_chan;
+	u32					*rx_dma_buf;
+	dma_addr_t				rx_dma_phys;
+	struct dma_async_tx_descriptor		*rx_dma_desc;
+
+	struct dma_chan				*tx_dma_chan;
+	u32					*tx_dma_buf;
+	dma_addr_t				tx_dma_phys;
+	struct dma_async_tx_descriptor		*tx_dma_desc;
+};
+
+static int tegra_slink_runtime_suspend(struct device *dev);
+static int tegra_slink_runtime_resume(struct device *dev);
+
+static inline unsigned long tegra_slink_readl(struct tegra_slink_data *tspi,
+		unsigned long reg)
+{
+	return readl(tspi->base + reg);
+}
+
+static inline void tegra_slink_writel(struct tegra_slink_data *tspi,
+		unsigned long val, unsigned long reg)
+{
+	writel(val, tspi->base + reg);
+
+	/* Read back register to make sure that register writes completed */
+	if (reg != SLINK_TX_FIFO)
+		readl(tspi->base + SLINK_MAS_DATA);
+}
+
+static void tegra_slink_clear_status(struct tegra_slink_data *tspi)
+{
+	unsigned long val;
+	unsigned long val_write = 0;
+
+	val = tegra_slink_readl(tspi, SLINK_STATUS);
+
+	/* Write 1 to clear status register */
+	val_write = SLINK_RDY | SLINK_FIFO_ERROR;
+	tegra_slink_writel(tspi, val_write, SLINK_STATUS);
+}
+
+static unsigned long tegra_slink_get_packed_size(struct tegra_slink_data *tspi,
+				  struct spi_transfer *t)
+{
+	unsigned long val;
+
+	switch (tspi->bytes_per_word) {
+	case 0:
+		val = SLINK_PACK_SIZE_4;
+		break;
+	case 1:
+		val = SLINK_PACK_SIZE_8;
+		break;
+	case 2:
+		val = SLINK_PACK_SIZE_16;
+		break;
+	case 4:
+		val = SLINK_PACK_SIZE_32;
+		break;
+	default:
+		val = 0;
+	}
+	return val;
+}
+
+static unsigned tegra_slink_calculate_curr_xfer_param(
+	struct spi_device *spi, struct tegra_slink_data *tspi,
+	struct spi_transfer *t)
+{
+	unsigned remain_len = t->len - tspi->cur_pos;
+	unsigned max_word;
+	unsigned bits_per_word ;
+	unsigned max_len;
+	unsigned total_fifo_words;
+
+	bits_per_word = t->bits_per_word ? t->bits_per_word :
+						spi->bits_per_word;
+	tspi->bytes_per_word = (bits_per_word - 1) / 8 + 1;
+
+	if (bits_per_word == 8 || bits_per_word == 16) {
+		tspi->is_packed = 1;
+		tspi->words_per_32bit = 32/bits_per_word;
+	} else {
+		tspi->is_packed = 0;
+		tspi->words_per_32bit = 1;
+	}
+	tspi->packed_size = tegra_slink_get_packed_size(tspi, t);
+
+	if (tspi->is_packed) {
+		max_len = min(remain_len, tspi->max_buf_size);
+		tspi->curr_dma_words = max_len/tspi->bytes_per_word;
+		total_fifo_words = max_len/4;
+	} else {
+		max_word = (remain_len - 1) / tspi->bytes_per_word + 1;
+		max_word = min(max_word, tspi->max_buf_size/4);
+		tspi->curr_dma_words = max_word;
+		total_fifo_words = max_word;
+	}
+	return total_fifo_words;
+}
+
+static unsigned tegra_slink_fill_tx_fifo_from_client_txbuf(
+	struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned nbytes;
+	unsigned tx_empty_count;
+	unsigned long fifo_status;
+	unsigned max_n_32bit;
+	unsigned i, count;
+	unsigned long x;
+	unsigned int written_words;
+	unsigned fifo_words_left;
+	u8 *tx_buf = (u8 *)t->tx_buf + tspi->cur_tx_pos;
+
+	fifo_status = tegra_slink_readl(tspi, SLINK_STATUS2);
+	tx_empty_count = SLINK_TX_FIFO_EMPTY_COUNT(fifo_status);
+
+	if (tspi->is_packed) {
+		fifo_words_left = tx_empty_count * tspi->words_per_32bit;
+		written_words = min(fifo_words_left, tspi->curr_dma_words);
+		nbytes = written_words * tspi->bytes_per_word;
+		max_n_32bit = DIV_ROUND_UP(nbytes, 4);
+		for (count = 0; count < max_n_32bit; count++) {
+			x = 0;
+			for (i = 0; (i < 4) && nbytes; i++, nbytes--)
+				x |= (*tx_buf++) << (i*8);
+			tegra_slink_writel(tspi, x, SLINK_TX_FIFO);
+		}
+	} else {
+		max_n_32bit = min(tspi->curr_dma_words,  tx_empty_count);
+		written_words = max_n_32bit;
+		nbytes = written_words * tspi->bytes_per_word;
+		for (count = 0; count < max_n_32bit; count++) {
+			x = 0;
+			for (i = 0; nbytes && (i < tspi->bytes_per_word);
+							i++, nbytes--)
+				x |= ((*tx_buf++) << i*8);
+			tegra_slink_writel(tspi, x, SLINK_TX_FIFO);
+		}
+	}
+	tspi->cur_tx_pos += written_words * tspi->bytes_per_word;
+	return written_words;
+}
+
+static unsigned int tegra_slink_read_rx_fifo_to_client_rxbuf(
+		struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned rx_full_count;
+	unsigned long fifo_status;
+	unsigned i, count;
+	unsigned long x;
+	unsigned int read_words = 0;
+	unsigned len;
+	u8 *rx_buf = (u8 *)t->rx_buf + tspi->cur_rx_pos;
+
+	fifo_status = tegra_slink_readl(tspi, SLINK_STATUS2);
+	rx_full_count = SLINK_RX_FIFO_FULL_COUNT(fifo_status);
+	if (tspi->is_packed) {
+		len = tspi->curr_dma_words * tspi->bytes_per_word;
+		for (count = 0; count < rx_full_count; count++) {
+			x = tegra_slink_readl(tspi, SLINK_RX_FIFO);
+			for (i = 0; len && (i < 4); i++, len--)
+				*rx_buf++ = (x >> i*8) & 0xFF;
+		}
+		tspi->cur_rx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
+		read_words += tspi->curr_dma_words;
+	} else {
+		unsigned int bits_per_word;
+
+		bits_per_word = t->bits_per_word ? t->bits_per_word :
+						tspi->cur_spi->bits_per_word;
+		for (count = 0; count < rx_full_count; count++) {
+			x = tegra_slink_readl(tspi, SLINK_RX_FIFO);
+			for (i = 0; (i < tspi->bytes_per_word); i++)
+				*rx_buf++ = (x >> (i*8)) & 0xFF;
+		}
+		tspi->cur_rx_pos += rx_full_count * tspi->bytes_per_word;
+		read_words += rx_full_count;
+	}
+	return read_words;
+}
+
+static void tegra_slink_copy_client_txbuf_to_spi_txbuf(
+		struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned len;
+
+	/* Make the dma buffer to read by cpu */
+	dma_sync_single_for_cpu(tspi->dev, tspi->tx_dma_phys,
+				tspi->dma_buf_size, DMA_TO_DEVICE);
+
+	if (tspi->is_packed) {
+		len = tspi->curr_dma_words * tspi->bytes_per_word;
+		memcpy(tspi->tx_dma_buf, t->tx_buf + tspi->cur_pos, len);
+	} else {
+		unsigned int i;
+		unsigned int count;
+		u8 *tx_buf = (u8 *)t->tx_buf + tspi->cur_tx_pos;
+		unsigned consume = tspi->curr_dma_words * tspi->bytes_per_word;
+		unsigned int x;
+
+		for (count = 0; count < tspi->curr_dma_words; count++) {
+			x = 0;
+			for (i = 0; consume && (i < tspi->bytes_per_word);
+							i++, consume--)
+				x |= ((*tx_buf++) << i * 8);
+			tspi->tx_dma_buf[count] = x;
+		}
+	}
+	tspi->cur_tx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
+
+	/* Make the dma buffer to read by dma */
+	dma_sync_single_for_device(tspi->dev, tspi->tx_dma_phys,
+				tspi->dma_buf_size, DMA_TO_DEVICE);
+}
+
+static void tegra_slink_copy_spi_rxbuf_to_client_rxbuf(
+		struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned len;
+
+	/* Make the dma buffer to read by cpu */
+	dma_sync_single_for_cpu(tspi->dev, tspi->rx_dma_phys,
+		tspi->dma_buf_size, DMA_FROM_DEVICE);
+
+	if (tspi->is_packed) {
+		len = tspi->curr_dma_words * tspi->bytes_per_word;
+		memcpy(t->rx_buf + tspi->cur_rx_pos, tspi->rx_dma_buf, len);
+	} else {
+		unsigned int i;
+		unsigned int count;
+		unsigned char *rx_buf = t->rx_buf + tspi->cur_rx_pos;
+		unsigned int x;
+		unsigned int rx_mask, bits_per_word;
+
+		bits_per_word = t->bits_per_word ? t->bits_per_word :
+						tspi->cur_spi->bits_per_word;
+		rx_mask = (1 << bits_per_word) - 1;
+		for (count = 0; count < tspi->curr_dma_words; count++) {
+			x = tspi->rx_dma_buf[count];
+			x &= rx_mask;
+			for (i = 0; (i < tspi->bytes_per_word); i++)
+				*rx_buf++ = (x >> (i*8)) & 0xFF;
+		}
+	}
+	tspi->cur_rx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
+
+	/* Make the dma buffer to read by dma */
+	dma_sync_single_for_device(tspi->dev, tspi->rx_dma_phys,
+		tspi->dma_buf_size, DMA_FROM_DEVICE);
+}
+
+static void tegra_slink_dma_complete(void *args)
+{
+	struct completion *dma_complete = args;
+
+	complete(dma_complete);
+}
+
+static int tegra_slink_start_tx_dma(struct tegra_slink_data *tspi, int len)
+{
+	INIT_COMPLETION(tspi->tx_dma_complete);
+	tspi->tx_dma_desc = dmaengine_prep_slave_single(tspi->tx_dma_chan,
+				tspi->tx_dma_phys, len, DMA_MEM_TO_DEV,
+				DMA_PREP_INTERRUPT |  DMA_CTRL_ACK);
+	if (!tspi->tx_dma_desc) {
+		dev_err(tspi->dev, "Not able to get desc for Tx\n");
+		return -EIO;
+	}
+
+	tspi->tx_dma_desc->callback = tegra_slink_dma_complete;
+	tspi->tx_dma_desc->callback_param = &tspi->tx_dma_complete;
+
+	dmaengine_submit(tspi->tx_dma_desc);
+	dma_async_issue_pending(tspi->tx_dma_chan);
+	return 0;
+}
+
+static int tegra_slink_start_rx_dma(struct tegra_slink_data *tspi, int len)
+{
+	INIT_COMPLETION(tspi->rx_dma_complete);
+	tspi->rx_dma_desc = dmaengine_prep_slave_single(tspi->rx_dma_chan,
+				tspi->rx_dma_phys, len, DMA_DEV_TO_MEM,
+				DMA_PREP_INTERRUPT |  DMA_CTRL_ACK);
+	if (!tspi->rx_dma_desc) {
+		dev_err(tspi->dev, "Not able to get desc for Rx\n");
+		return -EIO;
+	}
+
+	tspi->rx_dma_desc->callback = tegra_slink_dma_complete;
+	tspi->rx_dma_desc->callback_param = &tspi->rx_dma_complete;
+
+	dmaengine_submit(tspi->rx_dma_desc);
+	dma_async_issue_pending(tspi->rx_dma_chan);
+	return 0;
+}
+
+static int tegra_slink_start_dma_based_transfer(
+		struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned long val;
+	unsigned long test_val;
+	unsigned int len;
+	int ret = 0;
+	unsigned long status;
+
+	/* Make sure that Rx and Tx fifo are empty */
+	status = tegra_slink_readl(tspi, SLINK_STATUS);
+	if ((status & SLINK_FIFO_EMPTY) != SLINK_FIFO_EMPTY) {
+		dev_err(tspi->dev,
+			"Rx/Tx fifo are not empty status 0x%08lx\n", status);
+		return -EIO;
+	}
+
+	val = SLINK_DMA_BLOCK_SIZE(tspi->curr_dma_words - 1);
+	val |= tspi->packed_size;
+	if (tspi->is_packed)
+		len = DIV_ROUND_UP(tspi->curr_dma_words * tspi->bytes_per_word,
+					4) * 4;
+	else
+		len = tspi->curr_dma_words * 4;
+
+	/* Set attention level based on length of transfer */
+	if (len & 0xF)
+		val |= SLINK_TX_TRIG_1 | SLINK_RX_TRIG_1;
+	else if (((len) >> 4) & 0x1)
+		val |= SLINK_TX_TRIG_4 | SLINK_RX_TRIG_4;
+	else
+		val |= SLINK_TX_TRIG_8 | SLINK_RX_TRIG_8;
+
+	if (tspi->cur_direction & DATA_DIR_TX)
+		val |= SLINK_IE_TXC;
+
+	if (tspi->cur_direction & DATA_DIR_RX)
+		val |= SLINK_IE_RXC;
+
+	tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+	tspi->dma_control_reg = val;
+
+	if (tspi->cur_direction & DATA_DIR_TX) {
+		tegra_slink_copy_client_txbuf_to_spi_txbuf(tspi, t);
+		wmb();
+		ret = tegra_slink_start_tx_dma(tspi, len);
+		if (ret < 0) {
+			dev_err(tspi->dev,
+				"Starting tx dma failed, err %d\n", ret);
+			return ret;
+		}
+
+		/* Wait for tx fifo to be fill before starting slink */
+		test_val = tegra_slink_readl(tspi, SLINK_STATUS);
+		while (!(test_val & SLINK_TX_FULL))
+			test_val = tegra_slink_readl(tspi, SLINK_STATUS);
+	}
+
+	if (tspi->cur_direction & DATA_DIR_RX) {
+		/* Make the dma buffer to read by dma */
+		dma_sync_single_for_device(tspi->dev, tspi->rx_dma_phys,
+				tspi->dma_buf_size, DMA_FROM_DEVICE);
+
+		ret = tegra_slink_start_rx_dma(tspi, len);
+		if (ret < 0) {
+			dev_err(tspi->dev,
+				"Starting rx dma failed, err %d\n", ret);
+			if (tspi->cur_direction & DATA_DIR_TX)
+				dmaengine_terminate_all(tspi->tx_dma_chan);
+			return ret;
+		}
+	}
+	tspi->is_curr_dma_xfer = true;
+	if (tspi->is_packed) {
+		val |= SLINK_PACKED;
+		tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+		/* HW need small delay after settign Packed mode */
+		udelay(1);
+	}
+	tspi->dma_control_reg = val;
+
+	val |= SLINK_DMA_EN;
+	tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+	return ret;
+}
+
+static int tegra_slink_start_cpu_based_transfer(
+		struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned long val;
+	unsigned cur_words;
+
+	val = tspi->packed_size;
+	if (tspi->cur_direction & DATA_DIR_TX)
+		val |= SLINK_IE_TXC;
+
+	if (tspi->cur_direction & DATA_DIR_RX)
+		val |= SLINK_IE_RXC;
+
+	tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+	tspi->dma_control_reg = val;
+
+	if (tspi->cur_direction & DATA_DIR_TX)
+		cur_words = tegra_slink_fill_tx_fifo_from_client_txbuf(tspi, t);
+	else
+		cur_words = tspi->curr_dma_words;
+	val |= SLINK_DMA_BLOCK_SIZE(cur_words - 1);
+	tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+	tspi->dma_control_reg = val;
+
+	tspi->is_curr_dma_xfer = false;
+	if (tspi->is_packed) {
+		val |= SLINK_PACKED;
+		tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+		udelay(1);
+		wmb();
+	}
+	tspi->dma_control_reg = val;
+	val |= SLINK_DMA_EN;
+	tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+	return 0;
+}
+
+static int tegra_slink_init_dma_param(struct tegra_slink_data *tspi,
+			bool dma_to_memory)
+{
+	struct dma_chan *dma_chan;
+	u32 *dma_buf;
+	dma_addr_t dma_phys;
+	int ret;
+	struct dma_slave_config dma_sconfig;
+	dma_cap_mask_t mask;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+	dma_chan = dma_request_channel(mask, NULL, NULL);
+	if (!dma_chan) {
+		dev_err(tspi->dev,
+			"Dma channel is not available, will try later\n");
+		return -EPROBE_DEFER;
+	}
+
+	dma_buf = dma_alloc_coherent(tspi->dev, tspi->dma_buf_size,
+				&dma_phys, GFP_KERNEL);
+	if (!dma_buf) {
+		dev_err(tspi->dev, " Not able to allocate the dma buffer\n");
+		dma_release_channel(dma_chan);
+		return -ENOMEM;
+	}
+
+	dma_sconfig.slave_id = tspi->dma_req_sel;
+	if (dma_to_memory) {
+		dma_sconfig.src_addr = tspi->phys + SLINK_RX_FIFO;
+		dma_sconfig.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dma_sconfig.src_maxburst = 0;
+	} else {
+		dma_sconfig.dst_addr = tspi->phys + SLINK_TX_FIFO;
+		dma_sconfig.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dma_sconfig.dst_maxburst = 0;
+	}
+
+	ret = dmaengine_slave_config(dma_chan, &dma_sconfig);
+	if (ret)
+		goto scrub;
+	if (dma_to_memory) {
+		tspi->rx_dma_chan = dma_chan;
+		tspi->rx_dma_buf = dma_buf;
+		tspi->rx_dma_phys = dma_phys;
+	} else {
+		tspi->tx_dma_chan = dma_chan;
+		tspi->tx_dma_buf = dma_buf;
+		tspi->tx_dma_phys = dma_phys;
+	}
+	return 0;
+
+scrub:
+	dma_free_coherent(tspi->dev, tspi->dma_buf_size, dma_buf, dma_phys);
+	dma_release_channel(dma_chan);
+	return ret;
+}
+
+static void tegra_slink_deinit_dma_param(struct tegra_slink_data *tspi,
+	bool dma_to_memory)
+{
+	u32 *dma_buf;
+	dma_addr_t dma_phys;
+	struct dma_chan *dma_chan;
+
+	if (dma_to_memory) {
+		dma_buf = tspi->rx_dma_buf;
+		dma_chan = tspi->rx_dma_chan;
+		dma_phys = tspi->rx_dma_phys;
+		tspi->rx_dma_chan = NULL;
+		tspi->rx_dma_buf = NULL;
+	} else {
+		dma_buf = tspi->tx_dma_buf;
+		dma_chan = tspi->tx_dma_chan;
+		dma_phys = tspi->tx_dma_phys;
+		tspi->tx_dma_buf = NULL;
+		tspi->tx_dma_chan = NULL;
+	}
+	if (!dma_chan)
+		return;
+
+	dma_free_coherent(tspi->dev, tspi->dma_buf_size, dma_buf, dma_phys);
+	dma_release_channel(dma_chan);
+}
+
+static int tegra_slink_start_transfer_one(struct spi_device *spi,
+		struct spi_transfer *t, bool is_first_of_msg,
+		bool is_single_xfer)
+{
+	struct tegra_slink_data *tspi = spi_master_get_devdata(spi->master);
+	u32 speed;
+	u8 bits_per_word;
+	unsigned total_fifo_words;
+	int ret;
+	struct tegra_spi_device_controller_data *cdata = spi->controller_data;
+	unsigned long command;
+	unsigned long command2;
+
+	bits_per_word = t->bits_per_word ? t->bits_per_word :
+					spi->bits_per_word;
+	speed = t->speed_hz ? t->speed_hz : spi->max_speed_hz;
+	if (!speed)
+		speed = tspi->spi_max_frequency;
+	if (speed != tspi->cur_speed) {
+		clk_set_rate(tspi->clk, speed * 4);
+		tspi->cur_speed = speed;
+	}
+
+	tspi->cur_spi = spi;
+	tspi->cur_pos = 0;
+	tspi->cur_rx_pos = 0;
+	tspi->cur_tx_pos = 0;
+	tspi->curr_xfer = t;
+	total_fifo_words = tegra_slink_calculate_curr_xfer_param(spi, tspi, t);
+
+	if (is_first_of_msg) {
+		tegra_slink_clear_status(tspi);
+
+		command = tspi->def_command_reg;
+		command |= SLINK_BIT_LENGTH(bits_per_word - 1);
+
+		command2 = tspi->def_command2_reg;
+		command2 |= SLINK_SS_EN_CS(spi->chip_select);
+
+		/* possibly use the hw based chip select */
+		tspi->is_hw_based_cs = false;
+		if (cdata && cdata->is_hw_based_cs && is_single_xfer &&
+			((tspi->curr_dma_words * tspi->bytes_per_word) ==
+						(t->len - tspi->cur_pos))) {
+			int setup_count;
+			int sts2;
+
+			setup_count = cdata->cs_setup_clk_count >> 1;
+			setup_count = max(setup_count, 3);
+			command2 |= SLINK_SS_SETUP(setup_count);
+			if (tspi->chip_data->cs_hold_time) {
+				int hold_count;
+
+				hold_count = cdata->cs_hold_clk_count;
+				hold_count = max(hold_count, 0xF);
+				sts2 = tegra_slink_readl(tspi, SLINK_STATUS2);
+				sts2 &= ~SLINK_SS_HOLD_TIME(0xF);
+				sts2 |= SLINK_SS_HOLD_TIME(hold_count);
+				tegra_slink_writel(tspi, sts2, SLINK_STATUS2);
+			}
+			tspi->is_hw_based_cs = true;
+		}
+
+		if (tspi->is_hw_based_cs)
+			command &= ~SLINK_CS_SW;
+		else
+			command |= SLINK_CS_SW | SLINK_CS_VALUE;
+
+		command &= ~SLINK_MODES;
+		if (spi->mode & SPI_CPHA)
+			command |= SLINK_CK_SDA;
+
+		if (spi->mode & SPI_CPOL)
+			command |= SLINK_IDLE_SCLK_DRIVE_HIGH;
+		else
+			command |= SLINK_IDLE_SCLK_DRIVE_LOW;
+	} else {
+		command = tspi->command_reg;
+		command &= ~SLINK_BIT_LENGTH(~0);
+		command |= SLINK_BIT_LENGTH(bits_per_word - 1);
+
+		command2 = tspi->command2_reg;
+		command2 &= ~(SLINK_RXEN | SLINK_TXEN);
+	}
+
+	tegra_slink_writel(tspi, command, SLINK_COMMAND);
+	tspi->command_reg = command;
+
+	tspi->cur_direction = 0;
+	if (t->rx_buf) {
+		command2 |= SLINK_RXEN;
+		tspi->cur_direction |= DATA_DIR_RX;
+	}
+	if (t->tx_buf) {
+		command2 |= SLINK_TXEN;
+		tspi->cur_direction |= DATA_DIR_TX;
+	}
+	tegra_slink_writel(tspi, command2, SLINK_COMMAND2);
+	tspi->command2_reg = command2;
+
+	if (total_fifo_words > SLINK_FIFO_DEPTH)
+		ret = tegra_slink_start_dma_based_transfer(tspi, t);
+	else
+		ret = tegra_slink_start_cpu_based_transfer(tspi, t);
+	return ret;
+}
+
+static int tegra_slink_setup(struct spi_device *spi)
+{
+	struct tegra_slink_data *tspi = spi_master_get_devdata(spi->master);
+	unsigned long val;
+	unsigned long flags;
+	int ret;
+	unsigned int cs_pol_bit[MAX_CHIP_SELECT] = {
+			SLINK_CS_POLARITY,
+			SLINK_CS_POLARITY1,
+			SLINK_CS_POLARITY2,
+			SLINK_CS_POLARITY3,
+	};
+
+	dev_dbg(&spi->dev, "setup %d bpw, %scpol, %scpha, %dHz\n",
+		spi->bits_per_word,
+		spi->mode & SPI_CPOL ? "" : "~",
+		spi->mode & SPI_CPHA ? "" : "~",
+		spi->max_speed_hz);
+
+	BUG_ON(spi->chip_select >= MAX_CHIP_SELECT);
+
+	ret = pm_runtime_get_sync(tspi->dev);
+	if (ret < 0) {
+		dev_err(tspi->dev, "pm runtime failed, e = %d\n", ret);
+		return ret;
+	}
+
+	spin_lock_irqsave(&tspi->lock, flags);
+	val = tspi->def_command_reg;
+	if (spi->mode & SPI_CS_HIGH)
+		val |= cs_pol_bit[spi->chip_select];
+	else
+		val &= ~cs_pol_bit[spi->chip_select];
+	tspi->def_command_reg = val;
+	tegra_slink_writel(tspi, tspi->def_command_reg, SLINK_COMMAND);
+	spin_unlock_irqrestore(&tspi->lock, flags);
+
+	pm_runtime_put(tspi->dev);
+	return 0;
+}
+
+static int tegra_slink_prepare_transfer(struct spi_master *master)
+{
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+
+	return pm_runtime_get_sync(tspi->dev);
+}
+
+static int tegra_slink_unprepare_transfer(struct spi_master *master)
+{
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+
+	pm_runtime_put(tspi->dev);
+	return 0;
+}
+
+static int tegra_slink_transfer_one_message(struct spi_master *master,
+			struct spi_message *msg)
+{
+	bool is_first_msg = true;
+	int single_xfer;
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	struct spi_transfer *xfer;
+	struct spi_device *spi = msg->spi;
+	int ret;
+
+	msg->status = 0;
+	msg->actual_length = 0;
+	single_xfer = list_is_singular(&msg->transfers);
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		INIT_COMPLETION(tspi->xfer_completion);
+		ret = tegra_slink_start_transfer_one(spi, xfer,
+					is_first_msg, single_xfer);
+		if (ret < 0) {
+			dev_err(tspi->dev,
+				"spi can not start transfer, err %d\n", ret);
+			goto exit;
+		}
+		is_first_msg = false;
+		ret = wait_for_completion_timeout(&tspi->xfer_completion,
+						SLINK_DMA_TIMEOUT);
+		if (WARN_ON(ret == 0)) {
+			dev_err(tspi->dev,
+				"spi trasfer timeout, err %d\n", ret);
+			ret = -EIO;
+			goto exit;
+		}
+
+		if (tspi->tx_status ||  tspi->rx_status) {
+			dev_err(tspi->dev, "Error in Transfer\n");
+			ret = -EIO;
+			goto exit;
+		}
+		msg->actual_length += xfer->len;
+		if (xfer->cs_change && xfer->delay_usecs) {
+			tegra_slink_writel(tspi, tspi->def_command_reg,
+					SLINK_COMMAND);
+			udelay(xfer->delay_usecs);
+		}
+	}
+	ret = 0;
+exit:
+	tegra_slink_writel(tspi, tspi->def_command_reg, SLINK_COMMAND);
+	tegra_slink_writel(tspi, tspi->def_command2_reg, SLINK_COMMAND2);
+	msg->status = ret;
+	spi_finalize_current_message(master);
+	return ret;
+}
+
+static irqreturn_t handle_cpu_based_xfer(struct tegra_slink_data *tspi)
+{
+	struct spi_transfer *t = tspi->curr_xfer;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tspi->lock, flags);
+	if (tspi->tx_status ||  tspi->rx_status ||
+				(tspi->status_reg & SLINK_BSY)) {
+		dev_err(tspi->dev,
+			"CpuXfer ERROR bit set 0x%x\n", tspi->status_reg);
+		dev_err(tspi->dev,
+			"CpuXfer 0x%08x:0x%08x:0x%08x\n", tspi->command_reg,
+				tspi->command2_reg, tspi->dma_control_reg);
+		tegra_periph_reset_assert(tspi->clk);
+		udelay(2);
+		tegra_periph_reset_deassert(tspi->clk);
+		complete(&tspi->xfer_completion);
+		goto exit;
+	}
+
+	if (tspi->cur_direction & DATA_DIR_RX)
+		tegra_slink_read_rx_fifo_to_client_rxbuf(tspi, t);
+
+	if (tspi->cur_direction & DATA_DIR_TX)
+		tspi->cur_pos = tspi->cur_tx_pos;
+	else
+		tspi->cur_pos = tspi->cur_rx_pos;
+
+	if (tspi->cur_pos == t->len) {
+		complete(&tspi->xfer_completion);
+		goto exit;
+	}
+
+	tegra_slink_calculate_curr_xfer_param(tspi->cur_spi, tspi, t);
+	tegra_slink_start_cpu_based_transfer(tspi, t);
+exit:
+	spin_unlock_irqrestore(&tspi->lock, flags);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t handle_dma_based_xfer(struct tegra_slink_data *tspi)
+{
+	struct spi_transfer *t = tspi->curr_xfer;
+	long wait_status;
+	int err = 0;
+	unsigned total_fifo_words;
+	unsigned long flags;
+
+	/* Abort dmas if any error */
+	if (tspi->cur_direction & DATA_DIR_TX) {
+		if (tspi->tx_status) {
+			dmaengine_terminate_all(tspi->tx_dma_chan);
+			err += 1;
+		} else {
+			wait_status = wait_for_completion_interruptible_timeout(
+				&tspi->tx_dma_complete, SLINK_DMA_TIMEOUT);
+			if (wait_status <= 0) {
+				dmaengine_terminate_all(tspi->tx_dma_chan);
+				dev_err(tspi->dev, "TxDma Xfer failed\n");
+				err += 1;
+			}
+		}
+	}
+
+	if (tspi->cur_direction & DATA_DIR_RX) {
+		if (tspi->rx_status) {
+			dmaengine_terminate_all(tspi->rx_dma_chan);
+			err += 2;
+		} else {
+			wait_status = wait_for_completion_interruptible_timeout(
+				&tspi->rx_dma_complete, SLINK_DMA_TIMEOUT);
+			if (wait_status <= 0) {
+				dmaengine_terminate_all(tspi->rx_dma_chan);
+				dev_err(tspi->dev, "RxDma Xfer failed\n");
+				err += 2;
+			}
+		}
+	}
+
+	spin_lock_irqsave(&tspi->lock, flags);
+	if (err) {
+		dev_err(tspi->dev,
+			"DmaXfer: ERROR bit set 0x%x\n", tspi->status_reg);
+		dev_err(tspi->dev,
+			"DmaXfer 0x%08x:0x%08x:0x%08x\n", tspi->command_reg,
+				tspi->command2_reg, tspi->dma_control_reg);
+		tegra_periph_reset_assert(tspi->clk);
+		udelay(2);
+		tegra_periph_reset_deassert(tspi->clk);
+		complete(&tspi->xfer_completion);
+		spin_unlock_irqrestore(&tspi->lock, flags);
+		return IRQ_HANDLED;
+	}
+
+	if (tspi->cur_direction & DATA_DIR_RX)
+		tegra_slink_copy_spi_rxbuf_to_client_rxbuf(tspi, t);
+
+	if (tspi->cur_direction & DATA_DIR_TX)
+		tspi->cur_pos = tspi->cur_tx_pos;
+	else
+		tspi->cur_pos = tspi->cur_rx_pos;
+
+	if (tspi->cur_pos == t->len) {
+		complete(&tspi->xfer_completion);
+		goto exit;
+	}
+
+	/* Continue transfer in current message */
+	total_fifo_words = tegra_slink_calculate_curr_xfer_param(tspi->cur_spi,
+							tspi, t);
+	if (total_fifo_words > SLINK_FIFO_DEPTH)
+		err = tegra_slink_start_dma_based_transfer(tspi, t);
+	else
+		err = tegra_slink_start_cpu_based_transfer(tspi, t);
+
+exit:
+	spin_unlock_irqrestore(&tspi->lock, flags);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t tegra_slink_isr_thread(int irq, void *context_data)
+{
+	struct tegra_slink_data *tspi = context_data;
+
+	if (!tspi->is_curr_dma_xfer)
+		return handle_cpu_based_xfer(tspi);
+	return handle_dma_based_xfer(tspi);
+}
+
+static irqreturn_t tegra_slink_isr(int irq, void *context_data)
+{
+	struct tegra_slink_data *tspi = context_data;
+
+	tspi->status_reg = tegra_slink_readl(tspi, SLINK_STATUS);
+	if (tspi->cur_direction & DATA_DIR_TX)
+		tspi->tx_status = tspi->status_reg &
+					(SLINK_TX_OVF | SLINK_TX_UNF);
+
+	if (tspi->cur_direction & DATA_DIR_RX)
+		tspi->rx_status = tspi->status_reg &
+					(SLINK_RX_OVF | SLINK_RX_UNF);
+	tegra_slink_clear_status(tspi);
+
+	return IRQ_WAKE_THREAD;
+}
+
+static struct tegra_spi_platform_data *tegra_slink_parse_dt(
+		struct platform_device *pdev)
+{
+	struct tegra_spi_platform_data *pdata;
+	const unsigned int *prop;
+	struct device_node *np = pdev->dev.of_node;
+	u32 of_dma[2];
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata) {
+		dev_err(&pdev->dev, "Memory alloc for pdata failed\n");
+		return NULL;
+	}
+
+	if (of_property_read_u32_array(np, "nvidia,dma-request-selector",
+				of_dma, 2) >= 0)
+		pdata->dma_req_sel = of_dma[1];
+
+	prop = of_get_property(np, "spi-max-frequency", NULL);
+	if (prop)
+		pdata->spi_max_frequency = be32_to_cpup(prop);
+
+	return pdata;
+}
+
+const struct tegra_slink_chip_data tegra30_spi_cdata = {
+	.cs_hold_time = true,
+};
+
+const struct tegra_slink_chip_data tegra20_spi_cdata = {
+	.cs_hold_time = false,
+};
+
+static struct of_device_id tegra_slink_of_match[] __devinitconst = {
+	{ .compatible = "nvidia,tegra20-slink", .data = &tegra20_spi_cdata, },
+	{ .compatible = "nvidia,tegra30-slink", .data = &tegra30_spi_cdata, },
+	{}
+};
+MODULE_DEVICE_TABLE(of, tegra_slink_of_match);
+
+static int __devinit tegra_slink_probe(struct platform_device *pdev)
+{
+	struct spi_master	*master;
+	struct tegra_slink_data	*tspi;
+	struct resource		*r;
+	struct tegra_spi_platform_data *pdata = pdev->dev.platform_data;
+	int ret, spi_irq;
+	const struct tegra_slink_chip_data *cdata = NULL;
+	const struct of_device_id *match;
+
+	match = of_match_device(of_match_ptr(tegra_slink_of_match), &pdev->dev);
+	if (!match) {
+		dev_err(&pdev->dev, "Error: No device match found\n");
+		return -ENODEV;
+	}
+	cdata = match->data;
+	if (!pdata && pdev->dev.of_node)
+		pdata = tegra_slink_parse_dt(pdev);
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "No platform data, exiting\n");
+		return -ENODEV;
+	}
+
+	if (!pdata->spi_max_frequency)
+		pdata->spi_max_frequency = 25000000; /* 25MHz */
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*tspi));
+	if (!master) {
+		dev_err(&pdev->dev, "master allocation failed\n");
+		return -ENOMEM;
+	}
+
+	/* the spi->mode bits understood by this driver: */
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	master->setup = tegra_slink_setup;
+	master->prepare_transfer_hardware = tegra_slink_prepare_transfer;
+	master->transfer_one_message = tegra_slink_transfer_one_message;
+	master->unprepare_transfer_hardware = tegra_slink_unprepare_transfer;
+	master->num_chipselect = MAX_CHIP_SELECT;
+	master->bus_num = -1;
+
+	dev_set_drvdata(&pdev->dev, master);
+	tspi = spi_master_get_devdata(master);
+	tspi->master = master;
+	tspi->dma_req_sel = pdata->dma_req_sel;
+	tspi->dev = &pdev->dev;
+	tspi->chip_data = cdata;
+	spin_lock_init(&tspi->lock);
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r) {
+		dev_err(&pdev->dev, "No IO memory resource\n");
+		ret = -ENODEV;
+		goto exit_free_master;
+	}
+	tspi->phys = r->start;
+	tspi->base = devm_request_and_ioremap(&pdev->dev, r);
+	if (!tspi->base) {
+		dev_err(&pdev->dev,
+			"Cannot request memregion/iomap dma address\n");
+		ret = -EADDRNOTAVAIL;
+		goto exit_free_master;
+	}
+
+	spi_irq = platform_get_irq(pdev, 0);
+	tspi->irq = spi_irq;
+	ret = request_threaded_irq(tspi->irq, tegra_slink_isr,
+			tegra_slink_isr_thread, IRQF_ONESHOT,
+			dev_name(&pdev->dev), tspi);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to register ISR for IRQ %d\n",
+					tspi->irq);
+		goto exit_free_master;
+	}
+
+	tspi->clk = devm_clk_get(&pdev->dev, "slink");
+	if (IS_ERR(tspi->clk)) {
+		dev_err(&pdev->dev, "can not get clock\n");
+		ret = PTR_ERR(tspi->clk);
+		goto exit_free_irq;
+	}
+
+	tspi->max_buf_size = SLINK_FIFO_DEPTH << 2;
+	tspi->dma_buf_size = DEFAULT_SPI_DMA_BUF_LEN;
+	tspi->spi_max_frequency = pdata->spi_max_frequency;
+
+	if (pdata->dma_req_sel) {
+		ret = tegra_slink_init_dma_param(tspi, true);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "RxDma Init failed, err %d\n", ret);
+			goto exit_free_irq;
+		}
+
+		ret = tegra_slink_init_dma_param(tspi, false);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "TxDma Init failed, err %d\n", ret);
+			goto exit_rx_dma_free;
+		}
+		tspi->max_buf_size = tspi->dma_buf_size;
+		init_completion(&tspi->tx_dma_complete);
+		init_completion(&tspi->rx_dma_complete);
+	}
+
+	init_completion(&tspi->xfer_completion);
+
+	pm_runtime_enable(&pdev->dev);
+	if (!pm_runtime_enabled(&pdev->dev)) {
+		ret = tegra_slink_runtime_resume(&pdev->dev);
+		if (ret)
+			goto exit_pm_disable;
+	}
+
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "pm runtime get failed, e = %d\n", ret);
+		goto exit_pm_disable;
+	}
+	tspi->def_command_reg  = SLINK_M_S;
+	tspi->def_command2_reg = SLINK_CS_ACTIVE_BETWEEN;
+	tegra_slink_writel(tspi, tspi->def_command_reg, SLINK_COMMAND);
+	tegra_slink_writel(tspi, tspi->def_command2_reg, SLINK_COMMAND2);
+	pm_runtime_put(&pdev->dev);
+
+	master->dev.of_node = pdev->dev.of_node;
+	ret = spi_register_master(master);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "can not register to master err %d\n", ret);
+		goto exit_pm_disable;
+	}
+	return ret;
+
+exit_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		tegra_slink_runtime_suspend(&pdev->dev);
+	tegra_slink_deinit_dma_param(tspi, false);
+exit_rx_dma_free:
+	tegra_slink_deinit_dma_param(tspi, true);
+exit_free_irq:
+	free_irq(spi_irq, tspi);
+exit_free_master:
+	spi_master_put(master);
+	return ret;
+}
+
+static int __devexit tegra_slink_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = dev_get_drvdata(&pdev->dev);
+	struct tegra_slink_data	*tspi = spi_master_get_devdata(master);
+
+	free_irq(tspi->irq, tspi);
+	spi_unregister_master(master);
+
+	if (tspi->tx_dma_chan)
+		tegra_slink_deinit_dma_param(tspi, false);
+
+	if (tspi->rx_dma_chan)
+		tegra_slink_deinit_dma_param(tspi, true);
+
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		tegra_slink_runtime_suspend(&pdev->dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int tegra_slink_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+
+	return spi_master_suspend(master);
+}
+
+static int tegra_slink_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "pm runtime failed, e = %d\n", ret);
+		return ret;
+	}
+	tegra_slink_writel(tspi, tspi->command_reg, SLINK_COMMAND);
+	tegra_slink_writel(tspi, tspi->command2_reg, SLINK_COMMAND2);
+	pm_runtime_put(dev);
+
+	return spi_master_resume(master);
+}
+#endif
+
+static int tegra_slink_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+
+	/* Flush all write which are in PPSB queue by reading back */
+	tegra_slink_readl(tspi, SLINK_MAS_DATA);
+
+	clk_disable_unprepare(tspi->clk);
+	return 0;
+}
+
+static int tegra_slink_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	int ret;
+
+	ret = clk_prepare_enable(tspi->clk);
+	if (ret < 0) {
+		dev_err(tspi->dev, "clk_prepare failed: %d\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static const struct dev_pm_ops slink_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_slink_runtime_suspend,
+		tegra_slink_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(tegra_slink_suspend, tegra_slink_resume)
+};
+static struct platform_driver tegra_slink_driver = {
+	.driver = {
+		.name		= "spi-tegra-slink",
+		.owner		= THIS_MODULE,
+		.pm		= &slink_pm_ops,
+		.of_match_table	= of_match_ptr(tegra_slink_of_match),
+	},
+	.probe =	tegra_slink_probe,
+	.remove =	__devexit_p(tegra_slink_remove),
+};
+module_platform_driver(tegra_slink_driver);
+
+MODULE_ALIAS("platform:spi-tegra-slink");
+MODULE_DESCRIPTION("NVIDIA Tegra20/Tegra30 SLINK Controller Driver");
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/spi/spi-tegra.h b/include/linux/spi/spi-tegra.h
new file mode 100644
index 000000000000..786932c62edb
--- /dev/null
+++ b/include/linux/spi/spi-tegra.h
@@ -0,0 +1,40 @@
+/*
+ * spi-tegra.h: SPI interface for Nvidia Tegra20 SLINK controller.
+ *
+ * Copyright (C) 2011 NVIDIA Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef _LINUX_SPI_TEGRA_H
+#define _LINUX_SPI_TEGRA_H
+
+struct tegra_spi_platform_data {
+	int dma_req_sel;
+	unsigned int spi_max_frequency;
+};
+
+/*
+ * Controller data from device to pass some info like
+ * hw based chip select can be used or not and if yes
+ * then CS hold and setup time.
+ */
+struct tegra_spi_device_controller_data {
+	bool is_hw_based_cs;
+	int cs_setup_clk_count;
+	int cs_hold_clk_count;
+};
+
+#endif /* _LINUX_SPI_TEGRA_H */
-- 
cgit v1.2.3-55-g7522


From 1778794031aae75d4464904319d320edc3e77d39 Mon Sep 17 00:00:00 2001
From: Yinghai Lu
Date: Tue, 30 Oct 2012 14:31:10 -0600
Subject: PCI: Separate out pci_assign_unassigned_bus_resources()

It is main portion of pci_rescan_bus().

Separate it out and prepare to use it for PCI root bus hot add later.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>---
 drivers/pci/setup-bus.c | 33 +++++++++++++++++++--------------
 include/linux/pci.h     |  1 +
 2 files changed, 20 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 1e808ca338f8..f64c071d6923 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1550,25 +1550,12 @@ enable_all:
 }
 EXPORT_SYMBOL_GPL(pci_assign_unassigned_bridge_resources);
 
-#ifdef CONFIG_HOTPLUG
-/**
- * pci_rescan_bus - scan a PCI bus for devices.
- * @bus: PCI bus to scan
- *
- * Scan a PCI bus and child buses for new devices, adds them,
- * and enables them.
- *
- * Returns the max number of subordinate bus discovered.
- */
-unsigned int __ref pci_rescan_bus(struct pci_bus *bus)
+void pci_assign_unassigned_bus_resources(struct pci_bus *bus)
 {
-	unsigned int max;
 	struct pci_dev *dev;
 	LIST_HEAD(add_list); /* list of resources that
 					want additional resources */
 
-	max = pci_scan_child_bus(bus);
-
 	down_read(&pci_bus_sem);
 	list_for_each_entry(dev, &bus->devices, bus_list)
 		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
@@ -1581,6 +1568,24 @@ unsigned int __ref pci_rescan_bus(struct pci_bus *bus)
 	BUG_ON(!list_empty(&add_list));
 
 	pci_enable_bridges(bus);
+}
+
+#ifdef CONFIG_HOTPLUG
+/**
+ * pci_rescan_bus - scan a PCI bus for devices.
+ * @bus: PCI bus to scan
+ *
+ * Scan a PCI bus and child buses for new devices, adds them,
+ * and enables them.
+ *
+ * Returns the max number of subordinate bus discovered.
+ */
+unsigned int __ref pci_rescan_bus(struct pci_bus *bus)
+{
+	unsigned int max;
+
+	max = pci_scan_child_bus(bus);
+	pci_assign_unassigned_bus_resources(bus);
 	pci_bus_add_devices(bus);
 
 	return max;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index ee2179546c63..f543eb3b1c0c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -958,6 +958,7 @@ void pci_bus_size_bridges(struct pci_bus *bus);
 int pci_claim_resource(struct pci_dev *, int);
 void pci_assign_unassigned_resources(void);
 void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge);
+void pci_assign_unassigned_bus_resources(struct pci_bus *bus);
 void pdev_enable_device(struct pci_dev *);
 int pci_enable_resources(struct pci_dev *, int mask);
 void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *),
-- 
cgit v1.2.3-55-g7522


From 2ac4ad2a1468123f6bb439a547880a9c0d302e0a Mon Sep 17 00:00:00 2001
From: Vineet Gupta
Date: Sat, 27 Oct 2012 12:47:12 +0530
Subject: serial/arc-uart: Add new driver

Driver for non-standard on-chip UART, instantiated in the ARC (Synopsys)
FPGA Boards such as ARCAngel4/ML50x

Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Reviewed-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/Kconfig       |  23 ++
 drivers/tty/serial/Makefile      |   1 +
 drivers/tty/serial/arc_uart.c    | 746 +++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/serial_core.h |   2 +
 4 files changed, 772 insertions(+)
 create mode 100644 drivers/tty/serial/arc_uart.c

(limited to 'include')

diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 2a53be5f010d..b1768012ed21 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1423,4 +1423,27 @@ config SERIAL_EFM32_UART_CONSOLE
 	depends on SERIAL_EFM32_UART=y
 	select SERIAL_CORE_CONSOLE
 
+config SERIAL_ARC
+	tristate "ARC UART driver support"
+	select SERIAL_CORE
+	help
+	  Driver for on-chip UART for ARC(Synopsys) for the legacy
+	  FPGA Boards (ML50x/ARCAngel4)
+
+config SERIAL_ARC_CONSOLE
+	bool "Console on ARC UART"
+	depends on SERIAL_ARC=y
+	select SERIAL_CORE_CONSOLE
+	help
+	  Enable system Console on ARC UART
+
+config SERIAL_ARC_NR_PORTS
+	int "Number of ARC UART ports"
+	depends on SERIAL_ARC
+	range 1 3
+	default "1"
+	help
+	  Set this to the number of serial ports you want the driver
+	  to support.
+
 endmenu
diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile
index 4f694dafa719..df1b998c436b 100644
--- a/drivers/tty/serial/Makefile
+++ b/drivers/tty/serial/Makefile
@@ -82,3 +82,4 @@ obj-$(CONFIG_SERIAL_XILINX_PS_UART) += xilinx_uartps.o
 obj-$(CONFIG_SERIAL_SIRFSOC) += sirfsoc_uart.o
 obj-$(CONFIG_SERIAL_AR933X)   += ar933x_uart.o
 obj-$(CONFIG_SERIAL_EFM32_UART) += efm32-uart.o
+obj-$(CONFIG_SERIAL_ARC)	+= arc_uart.o
diff --git a/drivers/tty/serial/arc_uart.c b/drivers/tty/serial/arc_uart.c
new file mode 100644
index 000000000000..e9c61d1b1c79
--- /dev/null
+++ b/drivers/tty/serial/arc_uart.c
@@ -0,0 +1,746 @@
+/*
+ * ARC On-Chip(fpga) UART Driver
+ *
+ * Copyright (C) 2010-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * vineetg: July 10th 2012
+ *  -Decoupled the driver from arch/arc
+ *    +Using platform_get_resource() for irq/membase (thx to bfin_uart.c)
+ *    +Using early_platform_xxx() for early console (thx to mach-shmobile/xxx)
+ *
+ * Vineetg: Aug 21st 2010
+ *  -Is uart_tx_stopped() not done in tty write path as it has already been
+ *   taken care of, in serial core
+ *
+ * Vineetg: Aug 18th 2010
+ *  -New Serial Core based ARC UART driver
+ *  -Derived largely from blackfin driver albiet with some major tweaks
+ *
+ * TODO:
+ *  -check if sysreq works
+ */
+
+#if defined(CONFIG_SERIAL_ARC_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
+#define SUPPORT_SYSRQ
+#endif
+
+#include <linux/module.h>
+#include <linux/serial.h>
+#include <linux/console.h>
+#include <linux/sysrq.h>
+#include <linux/platform_device.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <linux/serial_core.h>
+#include <linux/io.h>
+
+/*************************************
+ * ARC UART Hardware Specs
+ ************************************/
+#define ARC_UART_TX_FIFO_SIZE  1
+
+/*
+ * UART Register set (this is not a Standards Compliant IP)
+ * Also each reg is Word aligned, but only 8 bits wide
+ */
+#define R_ID0	0
+#define R_ID1	4
+#define R_ID2	8
+#define R_ID3	12
+#define R_DATA	16
+#define R_STS	20
+#define R_BAUDL	24
+#define R_BAUDH	28
+
+/* Bits for UART Status Reg (R/W) */
+#define RXIENB  0x04	/* Receive Interrupt Enable */
+#define TXIENB  0x40	/* Transmit Interrupt Enable */
+
+#define RXEMPTY 0x20	/* Receive FIFO Empty: No char receivede */
+#define TXEMPTY 0x80	/* Transmit FIFO Empty, thus char can be written into */
+
+#define RXFULL  0x08	/* Receive FIFO full */
+#define RXFULL1 0x10	/* Receive FIFO has space for 1 char (tot space=4) */
+
+#define RXFERR  0x01	/* Frame Error: Stop Bit not detected */
+#define RXOERR  0x02	/* OverFlow Err: Char recv but RXFULL still set */
+
+/* Uart bit fiddling helpers: lowest level */
+#define RBASE(uart, reg)      (uart->port.membase + reg)
+#define UART_REG_SET(u, r, v) writeb((v), RBASE(u, r))
+#define UART_REG_GET(u, r)    readb(RBASE(u, r))
+
+#define UART_REG_OR(u, r, v)  UART_REG_SET(u, r, UART_REG_GET(u, r) | (v))
+#define UART_REG_CLR(u, r, v) UART_REG_SET(u, r, UART_REG_GET(u, r) & ~(v))
+
+/* Uart bit fiddling helpers: API level */
+#define UART_SET_DATA(uart, val)   UART_REG_SET(uart, R_DATA, val)
+#define UART_GET_DATA(uart)        UART_REG_GET(uart, R_DATA)
+
+#define UART_SET_BAUDH(uart, val)  UART_REG_SET(uart, R_BAUDH, val)
+#define UART_SET_BAUDL(uart, val)  UART_REG_SET(uart, R_BAUDL, val)
+
+#define UART_CLR_STATUS(uart, val) UART_REG_CLR(uart, R_STS, val)
+#define UART_GET_STATUS(uart)      UART_REG_GET(uart, R_STS)
+
+#define UART_ALL_IRQ_DISABLE(uart) UART_REG_CLR(uart, R_STS, RXIENB|TXIENB)
+#define UART_RX_IRQ_DISABLE(uart)  UART_REG_CLR(uart, R_STS, RXIENB)
+#define UART_TX_IRQ_DISABLE(uart)  UART_REG_CLR(uart, R_STS, TXIENB)
+
+#define UART_ALL_IRQ_ENABLE(uart)  UART_REG_OR(uart, R_STS, RXIENB|TXIENB)
+#define UART_RX_IRQ_ENABLE(uart)   UART_REG_OR(uart, R_STS, RXIENB)
+#define UART_TX_IRQ_ENABLE(uart)   UART_REG_OR(uart, R_STS, TXIENB)
+
+#define ARC_SERIAL_DEV_NAME	"ttyARC"
+
+struct arc_uart_port {
+	struct uart_port port;
+	unsigned long baud;
+	int is_emulated;	/* H/w vs. Instruction Set Simulator */
+};
+
+#define to_arc_port(uport)  container_of(uport, struct arc_uart_port, port)
+
+static struct arc_uart_port arc_uart_ports[CONFIG_SERIAL_ARC_NR_PORTS];
+
+#ifdef CONFIG_SERIAL_ARC_CONSOLE
+static struct console arc_console;
+#endif
+
+#define DRIVER_NAME	"arc-uart"
+
+static struct uart_driver arc_uart_driver = {
+	.owner		= THIS_MODULE,
+	.driver_name	= DRIVER_NAME,
+	.dev_name	= ARC_SERIAL_DEV_NAME,
+	.major		= 0,
+	.minor		= 0,
+	.nr		= CONFIG_SERIAL_ARC_NR_PORTS,
+#ifdef CONFIG_SERIAL_ARC_CONSOLE
+	.cons		= &arc_console,
+#endif
+};
+
+static void arc_serial_stop_rx(struct uart_port *port)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+
+	UART_RX_IRQ_DISABLE(uart);
+}
+
+static void arc_serial_stop_tx(struct uart_port *port)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+
+	while (!(UART_GET_STATUS(uart) & TXEMPTY))
+		cpu_relax();
+
+	UART_TX_IRQ_DISABLE(uart);
+}
+
+/*
+ * Return TIOCSER_TEMT when transmitter is not busy.
+ */
+static unsigned int arc_serial_tx_empty(struct uart_port *port)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+	unsigned int stat;
+
+	stat = UART_GET_STATUS(uart);
+	if (stat & TXEMPTY)
+		return TIOCSER_TEMT;
+
+	return 0;
+}
+
+/*
+ * Driver internal routine, used by both tty(serial core) as well as tx-isr
+ *  -Called under spinlock in either cases
+ *  -also tty->stopped / tty->hw_stopped has already been checked
+ *     = by uart_start( ) before calling us
+ *     = tx_ist checks that too before calling
+ */
+static void arc_serial_tx_chars(struct arc_uart_port *uart)
+{
+	struct circ_buf *xmit = &uart->port.state->xmit;
+	int sent = 0;
+	unsigned char ch;
+
+	if (unlikely(uart->port.x_char)) {
+		UART_SET_DATA(uart, uart->port.x_char);
+		uart->port.icount.tx++;
+		uart->port.x_char = 0;
+		sent = 1;
+	} else if (xmit->tail != xmit->head) {	/* TODO: uart_circ_empty */
+		ch = xmit->buf[xmit->tail];
+		xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
+		uart->port.icount.tx++;
+		while (!(UART_GET_STATUS(uart) & TXEMPTY))
+			cpu_relax();
+		UART_SET_DATA(uart, ch);
+		sent = 1;
+	}
+
+	/*
+	 * If num chars in xmit buffer are too few, ask tty layer for more.
+	 * By Hard ISR to schedule processing in software interrupt part
+	 */
+	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
+		uart_write_wakeup(&uart->port);
+
+	if (sent)
+		UART_TX_IRQ_ENABLE(uart);
+}
+
+/*
+ * port is locked and interrupts are disabled
+ * uart_start( ) calls us under the port spinlock irqsave
+ */
+static void arc_serial_start_tx(struct uart_port *port)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+
+	arc_serial_tx_chars(uart);
+}
+
+static void arc_serial_rx_chars(struct arc_uart_port *uart)
+{
+	struct tty_struct *tty = tty_port_tty_get(&uart->port.state->port);
+	unsigned int status, ch, flg = 0;
+
+	if (!tty)
+		return;
+
+	/*
+	 * UART has 4 deep RX-FIFO. Driver's recongnition of this fact
+	 * is very subtle. Here's how ...
+	 * Upon getting a RX-Intr, such that RX-EMPTY=0, meaning data available,
+	 * driver reads the DATA Reg and keeps doing that in a loop, until
+	 * RX-EMPTY=1. Multiple chars being avail, with a single Interrupt,
+	 * before RX-EMPTY=0, implies some sort of buffering going on in the
+	 * controller, which is indeed the Rx-FIFO.
+	 */
+	while (!((status = UART_GET_STATUS(uart)) & RXEMPTY)) {
+
+		ch = UART_GET_DATA(uart);
+		uart->port.icount.rx++;
+
+		if (unlikely(status & (RXOERR | RXFERR))) {
+			if (status & RXOERR) {
+				uart->port.icount.overrun++;
+				flg = TTY_OVERRUN;
+				UART_CLR_STATUS(uart, RXOERR);
+			}
+
+			if (status & RXFERR) {
+				uart->port.icount.frame++;
+				flg = TTY_FRAME;
+				UART_CLR_STATUS(uart, RXFERR);
+			}
+		} else
+			flg = TTY_NORMAL;
+
+		if (unlikely(uart_handle_sysrq_char(&uart->port, ch)))
+			goto done;
+
+		uart_insert_char(&uart->port, status, RXOERR, ch, flg);
+
+done:
+		tty_flip_buffer_push(tty);
+	}
+
+	tty_kref_put(tty);
+}
+
+/*
+ * A note on the Interrupt handling state machine of this driver
+ *
+ * kernel printk writes funnel thru the console driver framework and in order
+ * to keep things simple as well as efficient, it writes to UART in polled
+ * mode, in one shot, and exits.
+ *
+ * OTOH, Userland output (via tty layer), uses interrupt based writes as there
+ * can be undeterministic delay between char writes.
+ *
+ * Thus Rx-interrupts are always enabled, while tx-interrupts are by default
+ * disabled.
+ *
+ * When tty has some data to send out, serial core calls driver's start_tx
+ * which
+ *   -checks-if-tty-buffer-has-char-to-send
+ *   -writes-data-to-uart
+ *   -enable-tx-intr
+ *
+ * Once data bits are pushed out, controller raises the Tx-room-avail-Interrupt.
+ * The first thing Tx ISR does is disable further Tx interrupts (as this could
+ * be the last char to send, before settling down into the quiet polled mode).
+ * It then calls the exact routine used by tty layer write to send out any
+ * more char in tty buffer. In case of sending, it re-enables Tx-intr. In case
+ * of no data, it remains disabled.
+ * This is how the transmit state machine is dynamically switched on/off
+ */
+
+static irqreturn_t arc_serial_isr(int irq, void *dev_id)
+{
+	struct arc_uart_port *uart = dev_id;
+	unsigned int status;
+
+	status = UART_GET_STATUS(uart);
+
+	/*
+	 * Single IRQ for both Rx (data available) Tx (room available) Interrupt
+	 * notifications from the UART Controller.
+	 * To demultiplex between the two, we check the relevant bits
+	 */
+	if ((status & RXIENB) && !(status & RXEMPTY)) {
+
+		/* already in ISR, no need of xx_irqsave */
+		spin_lock(&uart->port.lock);
+		arc_serial_rx_chars(uart);
+		spin_unlock(&uart->port.lock);
+	}
+
+	if ((status & TXIENB) && (status & TXEMPTY)) {
+
+		/* Unconditionally disable further Tx-Interrupts.
+		 * will be enabled by tx_chars() if needed.
+		 */
+		UART_TX_IRQ_DISABLE(uart);
+
+		spin_lock(&uart->port.lock);
+
+		if (!uart_tx_stopped(&uart->port))
+			arc_serial_tx_chars(uart);
+
+		spin_unlock(&uart->port.lock);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static unsigned int arc_serial_get_mctrl(struct uart_port *port)
+{
+	/*
+	 * Pretend we have a Modem status reg and following bits are
+	 *  always set, to satify the serial core state machine
+	 *  (DSR) Data Set Ready
+	 *  (CTS) Clear To Send
+	 *  (CAR) Carrier Detect
+	 */
+	return TIOCM_CTS | TIOCM_DSR | TIOCM_CAR;
+}
+
+static void arc_serial_set_mctrl(struct uart_port *port, unsigned int mctrl)
+{
+	/* MCR not present */
+}
+
+/* Enable Modem Status Interrupts */
+
+static void arc_serial_enable_ms(struct uart_port *port)
+{
+	/* MSR not present */
+}
+
+static void arc_serial_break_ctl(struct uart_port *port, int break_state)
+{
+	/* ARC UART doesn't support sending Break signal */
+}
+
+static int arc_serial_startup(struct uart_port *port)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+
+	/* Before we hook up the ISR, Disable all UART Interrupts */
+	UART_ALL_IRQ_DISABLE(uart);
+
+	if (request_irq(uart->port.irq, arc_serial_isr, 0, "arc uart rx-tx",
+			uart)) {
+		dev_warn(uart->port.dev, "Unable to attach ARC UART intr\n");
+		return -EBUSY;
+	}
+
+	UART_RX_IRQ_ENABLE(uart); /* Only Rx IRQ enabled to begin with */
+
+	return 0;
+}
+
+/* This is not really needed */
+static void arc_serial_shutdown(struct uart_port *port)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+	free_irq(uart->port.irq, uart);
+}
+
+static void
+arc_serial_set_termios(struct uart_port *port, struct ktermios *new,
+		       struct ktermios *old)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+	unsigned int baud, uartl, uarth, hw_val;
+	unsigned long flags;
+
+	/*
+	 * Use the generic handler so that any specially encoded baud rates
+	 * such as SPD_xx flags or "%B0" can be handled
+	 * Max Baud I suppose will not be more than current 115K * 4
+	 * Formula for ARC UART is: hw-val = ((CLK/(BAUD*4)) -1)
+	 * spread over two 8-bit registers
+	 */
+	baud = uart_get_baud_rate(port, new, old, 0, 460800);
+
+	hw_val = port->uartclk / (uart->baud * 4) - 1;
+	uartl = hw_val & 0xFF;
+	uarth = (hw_val >> 8) & 0xFF;
+
+	/*
+	 * UART ISS(Instruction Set simulator) emulation has a subtle bug:
+	 * A existing value of Baudh = 0 is used as a indication to startup
+	 * it's internal state machine.
+	 * Thus if baudh is set to 0, 2 times, it chokes.
+	 * This happens with BAUD=115200 and the formaula above
+	 * Until that is fixed, when running on ISS, we will set baudh to !0
+	 */
+	if (uart->is_emulated)
+		uarth = 1;
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	UART_ALL_IRQ_DISABLE(uart);
+
+	UART_SET_BAUDL(uart, uartl);
+	UART_SET_BAUDH(uart, uarth);
+
+	UART_RX_IRQ_ENABLE(uart);
+
+	/*
+	 * UART doesn't support Parity/Hardware Flow Control;
+	 * Only supports 8N1 character size
+	 */
+	new->c_cflag &= ~(CMSPAR|CRTSCTS|CSIZE);
+	new->c_cflag |= CS8;
+
+	if (old)
+		tty_termios_copy_hw(new, old);
+
+	/* Don't rewrite B0 */
+	if (tty_termios_baud_rate(new))
+		tty_termios_encode_baud_rate(new, baud, baud);
+
+	uart_update_timeout(port, new->c_cflag, baud);
+
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static const char *arc_serial_type(struct uart_port *port)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+
+	return uart->port.type == PORT_ARC ? DRIVER_NAME : NULL;
+}
+
+static void arc_serial_release_port(struct uart_port *port)
+{
+}
+
+static int arc_serial_request_port(struct uart_port *port)
+{
+	return 0;
+}
+
+/*
+ * Verify the new serial_struct (for TIOCSSERIAL).
+ */
+static int
+arc_serial_verify_port(struct uart_port *port, struct serial_struct *ser)
+{
+	if (port->type != PORT_UNKNOWN && ser->type != PORT_ARC)
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Configure/autoconfigure the port.
+ */
+static void arc_serial_config_port(struct uart_port *port, int flags)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+
+	if (flags & UART_CONFIG_TYPE)
+		uart->port.type = PORT_ARC;
+}
+
+#if defined(CONFIG_CONSOLE_POLL) || defined(CONFIG_SERIAL_ARC_CONSOLE)
+
+static void arc_serial_poll_putchar(struct uart_port *port, unsigned char chr)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+
+	while (!(UART_GET_STATUS(uart) & TXEMPTY))
+		cpu_relax();
+
+	UART_SET_DATA(uart, chr);
+}
+#endif
+
+#ifdef CONFIG_CONSOLE_POLL
+static int arc_serial_poll_getchar(struct uart_port *port)
+{
+	struct arc_uart_port *uart = to_arc_port(port);
+	unsigned char chr;
+
+	while (!(UART_GET_STATUS(uart) & RXEMPTY))
+		cpu_relax();
+
+	chr = UART_GET_DATA(uart);
+	return chr;
+}
+#endif
+
+static struct uart_ops arc_serial_pops = {
+	.tx_empty	= arc_serial_tx_empty,
+	.set_mctrl	= arc_serial_set_mctrl,
+	.get_mctrl	= arc_serial_get_mctrl,
+	.stop_tx	= arc_serial_stop_tx,
+	.start_tx	= arc_serial_start_tx,
+	.stop_rx	= arc_serial_stop_rx,
+	.enable_ms	= arc_serial_enable_ms,
+	.break_ctl	= arc_serial_break_ctl,
+	.startup	= arc_serial_startup,
+	.shutdown	= arc_serial_shutdown,
+	.set_termios	= arc_serial_set_termios,
+	.type		= arc_serial_type,
+	.release_port	= arc_serial_release_port,
+	.request_port	= arc_serial_request_port,
+	.config_port	= arc_serial_config_port,
+	.verify_port	= arc_serial_verify_port,
+#ifdef CONFIG_CONSOLE_POLL
+	.poll_put_char = arc_serial_poll_putchar,
+	.poll_get_char = arc_serial_poll_getchar,
+#endif
+};
+
+static int __devinit
+arc_uart_init_one(struct platform_device *pdev, struct arc_uart_port *uart)
+{
+	struct resource *res, *res2;
+	unsigned long *plat_data;
+
+	if (pdev->id < 0 || pdev->id >= CONFIG_SERIAL_ARC_NR_PORTS) {
+		dev_err(&pdev->dev, "Wrong uart platform device id.\n");
+		return -ENOENT;
+	}
+
+	plat_data = ((unsigned long *)(pdev->dev.platform_data));
+	uart->baud = plat_data[0];
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
+
+	res2 = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!res2)
+		return -ENODEV;
+
+	uart->port.mapbase = res->start;
+	uart->port.membase = ioremap_nocache(res->start, resource_size(res));
+	if (!uart->port.membase)
+		/* No point of dev_err since UART itself is hosed here */
+		return -ENXIO;
+
+	uart->port.irq = res2->start;
+	uart->port.dev = &pdev->dev;
+	uart->port.iotype = UPIO_MEM;
+	uart->port.flags = UPF_BOOT_AUTOCONF;
+	uart->port.line = pdev->id;
+	uart->port.ops = &arc_serial_pops;
+
+	uart->port.uartclk = plat_data[1];
+	uart->port.fifosize = ARC_UART_TX_FIFO_SIZE;
+
+	/*
+	 * uart_insert_char( ) uses it in decideding whether to ignore a
+	 * char or not. Explicitly setting it here, removes the subtelty
+	 */
+	uart->port.ignore_status_mask = 0;
+
+	/* Real Hardware vs. emulated to work around a bug */
+	uart->is_emulated = !!plat_data[2];
+
+	return 0;
+}
+
+#ifdef CONFIG_SERIAL_ARC_CONSOLE
+
+static int __devinit arc_serial_console_setup(struct console *co, char *options)
+{
+	struct uart_port *port;
+	int baud = 115200;
+	int bits = 8;
+	int parity = 'n';
+	int flow = 'n';
+
+	if (co->index < 0 || co->index >= CONFIG_SERIAL_ARC_NR_PORTS)
+		return -ENODEV;
+
+	/*
+	 * The uart port backing the console (e.g. ttyARC1) might not have been
+	 * init yet. If so, defer the console setup to after the port.
+	 */
+	port = &arc_uart_ports[co->index].port;
+	if (!port->membase)
+		return -ENODEV;
+
+	if (options)
+		uart_parse_options(options, &baud, &parity, &bits, &flow);
+
+	/*
+	 * Serial core will call port->ops->set_termios( )
+	 * which will set the baud reg
+	 */
+	return uart_set_options(port, co, baud, parity, bits, flow);
+}
+
+static void arc_serial_console_putchar(struct uart_port *port, int ch)
+{
+	arc_serial_poll_putchar(port, (unsigned char)ch);
+}
+
+/*
+ * Interrupts are disabled on entering
+ */
+static void arc_serial_console_write(struct console *co, const char *s,
+				     unsigned int count)
+{
+	struct uart_port *port = &arc_uart_ports[co->index].port;
+	unsigned long flags;
+
+	spin_lock_irqsave(&port->lock, flags);
+	uart_console_write(port, s, count, arc_serial_console_putchar);
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static struct console arc_console = {
+	.name	= ARC_SERIAL_DEV_NAME,
+	.write	= arc_serial_console_write,
+	.device	= uart_console_device,
+	.setup	= arc_serial_console_setup,
+	.flags	= CON_PRINTBUFFER,
+	.index	= -1,
+	.data	= &arc_uart_driver
+};
+
+static __init void early_serial_write(struct console *con, const char *s,
+					unsigned int n)
+{
+	struct uart_port *port = &arc_uart_ports[con->index].port;
+	unsigned int i;
+
+	for (i = 0; i < n; i++, s++) {
+		if (*s == '\n')
+			arc_serial_poll_putchar(port, '\r');
+		arc_serial_poll_putchar(port, *s);
+	}
+}
+
+static struct __initdata console arc_early_serial_console = {
+	.name = "early_ARCuart",
+	.write = early_serial_write,
+	.flags = CON_PRINTBUFFER | CON_BOOT,
+	.index = -1
+};
+
+static int __devinit arc_serial_probe_earlyprintk(struct platform_device *pdev)
+{
+	arc_early_serial_console.index = pdev->id;
+
+	arc_uart_init_one(pdev, &arc_uart_ports[pdev->id]);
+
+	arc_serial_console_setup(&arc_early_serial_console, NULL);
+
+	register_console(&arc_early_serial_console);
+	return 0;
+}
+#else
+static int __devinit arc_serial_probe_earlyprintk(struct platform_device *pdev)
+{
+	return -ENODEV;
+}
+#endif	/* CONFIG_SERIAL_ARC_CONSOLE */
+
+static int __devinit arc_serial_probe(struct platform_device *pdev)
+{
+	struct arc_uart_port *uart;
+	int rc;
+
+	if (is_early_platform_device(pdev))
+		return arc_serial_probe_earlyprintk(pdev);
+
+	uart = &arc_uart_ports[pdev->id];
+	rc = arc_uart_init_one(pdev, uart);
+	if (rc)
+		return rc;
+
+	return uart_add_one_port(&arc_uart_driver, &uart->port);
+}
+
+static int __devexit arc_serial_remove(struct platform_device *pdev)
+{
+	/* This will never be called */
+	return 0;
+}
+
+static struct platform_driver arc_platform_driver = {
+	.probe = arc_serial_probe,
+	.remove = __devexit_p(arc_serial_remove),
+	.driver = {
+		.name = DRIVER_NAME,
+		.owner = THIS_MODULE,
+	 },
+};
+
+#ifdef CONFIG_SERIAL_ARC_CONSOLE
+/*
+ * Register an early platform driver of "earlyprintk" class.
+ * ARCH platform code installs the driver and probes the early devices
+ * The installation could rely on user specifying earlyprintk=xyx in cmd line
+ * or it could be done independently, for all "earlyprintk" class drivers.
+ * [see arch/arc/plat-arcfpga/platform.c]
+ */
+early_platform_init("earlyprintk", &arc_platform_driver);
+
+#endif  /* CONFIG_SERIAL_ARC_CONSOLE */
+
+static int __init arc_serial_init(void)
+{
+	int ret;
+
+	ret = uart_register_driver(&arc_uart_driver);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&arc_platform_driver);
+	if (ret)
+		uart_unregister_driver(&arc_uart_driver);
+
+	return ret;
+}
+
+static void __exit arc_serial_exit(void)
+{
+	platform_driver_unregister(&arc_platform_driver);
+	uart_unregister_driver(&arc_uart_driver);
+}
+
+module_init(arc_serial_init);
+module_exit(arc_serial_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("plat-arcfpga/uart");
+MODULE_AUTHOR("Vineet Gupta");
+MODULE_DESCRIPTION("ARC(Synopsys) On-Chip(fpga) serial driver");
diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h
index 7e1ab20adc03..ebcc73f0418a 100644
--- a/include/uapi/linux/serial_core.h
+++ b/include/uapi/linux/serial_core.h
@@ -215,5 +215,7 @@
 /* Energy Micro efm32 SoC */
 #define PORT_EFMUART   100
 
+/* ARC (Synopsys) on-chip UART */
+#define PORT_ARC       101
 
 #endif /* _UAPILINUX_SERIAL_CORE_H */
-- 
cgit v1.2.3-55-g7522


From 242860a47a75b933a79a30f6a40bf4858f4a3ecc Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia
Date: Fri, 19 Oct 2012 09:33:12 -0300
Subject: mm/sl[aou]b: Move common kmem_cache_size() to slab.h

This function is identically defined in all three allocators
and it's trivial to move it to slab.h

Since now it's static, inline, header-defined function
this patch also drops the EXPORT_SYMBOL tag.

Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Ezequiel Garcia <elezegarcia@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
---
 include/linux/slab.h | 9 ++++++++-
 mm/slab.c            | 6 ------
 mm/slob.c            | 6 ------
 mm/slub.c            | 9 ---------
 4 files changed, 8 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 83d1a1454b7e..743a10415122 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -128,7 +128,6 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
 void kmem_cache_free(struct kmem_cache *, void *);
-unsigned int kmem_cache_size(struct kmem_cache *);
 
 /*
  * Please use this macro to create slab caches. Simply specify the
@@ -388,6 +387,14 @@ static inline void *kzalloc_node(size_t size, gfp_t flags, int node)
 	return kmalloc_node(size, flags | __GFP_ZERO, node);
 }
 
+/*
+ * Determine the size of a slab object
+ */
+static inline unsigned int kmem_cache_size(struct kmem_cache *s)
+{
+	return s->object_size;
+}
+
 void __init kmem_cache_init_late(void);
 
 #endif	/* _LINUX_SLAB_H */
diff --git a/mm/slab.c b/mm/slab.c
index 6d5c83c6ddd5..1f7fd5f51f87 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3969,12 +3969,6 @@ void kfree(const void *objp)
 }
 EXPORT_SYMBOL(kfree);
 
-unsigned int kmem_cache_size(struct kmem_cache *cachep)
-{
-	return cachep->object_size;
-}
-EXPORT_SYMBOL(kmem_cache_size);
-
 /*
  * This initializes kmem_list3 or resizes various caches for all nodes.
  */
diff --git a/mm/slob.c b/mm/slob.c
index 287a88aa4a61..fffbc820774d 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -604,12 +604,6 @@ void kmem_cache_free(struct kmem_cache *c, void *b)
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
-unsigned int kmem_cache_size(struct kmem_cache *c)
-{
-	return c->object_size;
-}
-EXPORT_SYMBOL(kmem_cache_size);
-
 int __kmem_cache_shutdown(struct kmem_cache *c)
 {
 	/* No way to check for remaining objects */
diff --git a/mm/slub.c b/mm/slub.c
index 35483e0ab6bc..deee7c754a7d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3121,15 +3121,6 @@ error:
 	return -EINVAL;
 }
 
-/*
- * Determine the size of a slab object
- */
-unsigned int kmem_cache_size(struct kmem_cache *s)
-{
-	return s->object_size;
-}
-EXPORT_SYMBOL(kmem_cache_size);
-
 static void list_slab_objects(struct kmem_cache *s, struct page *page,
 							const char *text)
 {
-- 
cgit v1.2.3-55-g7522


From bcb2f99c6c43a8da6cb4002e8b0acf6f1275f3a8 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior
Date: Mon, 22 Oct 2012 22:14:57 +0200
Subject: usb: gadget: use a computation macro for INT endpoint interval

The 5+4 magic for HS tries to aim 32ms which is also what is intended
with 1 << 5 for FS. This little macro should make this easier to
understand.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/gadget/f_acm.c    | 7 +++----
 drivers/usb/gadget/f_ecm.c    | 8 ++++----
 drivers/usb/gadget/f_ncm.c    | 6 +++---
 drivers/usb/gadget/f_rndis.c  | 8 ++++----
 include/linux/usb/composite.h | 2 ++
 5 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/gadget/f_acm.c b/drivers/usb/gadget/f_acm.c
index d672250a61fa..7c30bb49850b 100644
--- a/drivers/usb/gadget/f_acm.c
+++ b/drivers/usb/gadget/f_acm.c
@@ -87,7 +87,7 @@ static inline struct f_acm *port_to_acm(struct gserial *p)
 
 /* notification endpoint uses smallish and infrequent fixed-size messages */
 
-#define GS_LOG2_NOTIFY_INTERVAL		5	/* 1 << 5 == 32 msec */
+#define GS_NOTIFY_INTERVAL_MS		32
 #define GS_NOTIFY_MAXPACKET		10	/* notification + 2 bytes */
 
 /* interface and class descriptors: */
@@ -167,7 +167,7 @@ static struct usb_endpoint_descriptor acm_fs_notify_desc = {
 	.bEndpointAddress =	USB_DIR_IN,
 	.bmAttributes =		USB_ENDPOINT_XFER_INT,
 	.wMaxPacketSize =	cpu_to_le16(GS_NOTIFY_MAXPACKET),
-	.bInterval =		1 << GS_LOG2_NOTIFY_INTERVAL,
+	.bInterval =		GS_NOTIFY_INTERVAL_MS,
 };
 
 static struct usb_endpoint_descriptor acm_fs_in_desc = {
@@ -199,14 +199,13 @@ static struct usb_descriptor_header *acm_fs_function[] = {
 };
 
 /* high speed support: */
-
 static struct usb_endpoint_descriptor acm_hs_notify_desc = {
 	.bLength =		USB_DT_ENDPOINT_SIZE,
 	.bDescriptorType =	USB_DT_ENDPOINT,
 	.bEndpointAddress =	USB_DIR_IN,
 	.bmAttributes =		USB_ENDPOINT_XFER_INT,
 	.wMaxPacketSize =	cpu_to_le16(GS_NOTIFY_MAXPACKET),
-	.bInterval =		GS_LOG2_NOTIFY_INTERVAL+4,
+	.bInterval =		USB_MS_TO_HS_INTERVAL(GS_NOTIFY_INTERVAL_MS),
 };
 
 static struct usb_endpoint_descriptor acm_hs_in_desc = {
diff --git a/drivers/usb/gadget/f_ecm.c b/drivers/usb/gadget/f_ecm.c
index 8ab9e9638f91..789242749df5 100644
--- a/drivers/usb/gadget/f_ecm.c
+++ b/drivers/usb/gadget/f_ecm.c
@@ -91,7 +91,7 @@ static inline unsigned ecm_bitrate(struct usb_gadget *g)
  * encapsulated commands (vendor-specific, using control-OUT).
  */
 
-#define LOG2_STATUS_INTERVAL_MSEC	5	/* 1 << 5 == 32 msec */
+#define ECM_STATUS_INTERVAL_MS		32
 #define ECM_STATUS_BYTECOUNT		16	/* 8 byte header + data */
 
 
@@ -192,7 +192,7 @@ static struct usb_endpoint_descriptor fs_ecm_notify_desc = {
 	.bEndpointAddress =	USB_DIR_IN,
 	.bmAttributes =		USB_ENDPOINT_XFER_INT,
 	.wMaxPacketSize =	cpu_to_le16(ECM_STATUS_BYTECOUNT),
-	.bInterval =		1 << LOG2_STATUS_INTERVAL_MSEC,
+	.bInterval =		ECM_STATUS_INTERVAL_MS,
 };
 
 static struct usb_endpoint_descriptor fs_ecm_in_desc = {
@@ -239,7 +239,7 @@ static struct usb_endpoint_descriptor hs_ecm_notify_desc = {
 	.bEndpointAddress =	USB_DIR_IN,
 	.bmAttributes =		USB_ENDPOINT_XFER_INT,
 	.wMaxPacketSize =	cpu_to_le16(ECM_STATUS_BYTECOUNT),
-	.bInterval =		LOG2_STATUS_INTERVAL_MSEC + 4,
+	.bInterval =		USB_MS_TO_HS_INTERVAL(ECM_STATUS_INTERVAL_MS),
 };
 
 static struct usb_endpoint_descriptor hs_ecm_in_desc = {
@@ -288,7 +288,7 @@ static struct usb_endpoint_descriptor ss_ecm_notify_desc = {
 	.bEndpointAddress =	USB_DIR_IN,
 	.bmAttributes =		USB_ENDPOINT_XFER_INT,
 	.wMaxPacketSize =	cpu_to_le16(ECM_STATUS_BYTECOUNT),
-	.bInterval =		LOG2_STATUS_INTERVAL_MSEC + 4,
+	.bInterval =		USB_MS_TO_HS_INTERVAL(ECM_STATUS_INTERVAL_MS),
 };
 
 static struct usb_ss_ep_comp_descriptor ss_ecm_intr_comp_desc = {
diff --git a/drivers/usb/gadget/f_ncm.c b/drivers/usb/gadget/f_ncm.c
index b651b529c67f..4f0950069a43 100644
--- a/drivers/usb/gadget/f_ncm.c
+++ b/drivers/usb/gadget/f_ncm.c
@@ -121,7 +121,7 @@ static struct usb_cdc_ncm_ntb_parameters ntb_parameters = {
  * waste less bandwidth.
  */
 
-#define LOG2_STATUS_INTERVAL_MSEC	5	/* 1 << 5 == 32 msec */
+#define NCM_STATUS_INTERVAL_MS		32
 #define NCM_STATUS_BYTECOUNT		16	/* 8 byte header + data */
 
 static struct usb_interface_assoc_descriptor ncm_iad_desc __initdata = {
@@ -230,7 +230,7 @@ static struct usb_endpoint_descriptor fs_ncm_notify_desc __initdata = {
 	.bEndpointAddress =	USB_DIR_IN,
 	.bmAttributes =		USB_ENDPOINT_XFER_INT,
 	.wMaxPacketSize =	cpu_to_le16(NCM_STATUS_BYTECOUNT),
-	.bInterval =		1 << LOG2_STATUS_INTERVAL_MSEC,
+	.bInterval =		NCM_STATUS_INTERVAL_MS,
 };
 
 static struct usb_endpoint_descriptor fs_ncm_in_desc __initdata = {
@@ -275,7 +275,7 @@ static struct usb_endpoint_descriptor hs_ncm_notify_desc __initdata = {
 	.bEndpointAddress =	USB_DIR_IN,
 	.bmAttributes =		USB_ENDPOINT_XFER_INT,
 	.wMaxPacketSize =	cpu_to_le16(NCM_STATUS_BYTECOUNT),
-	.bInterval =		LOG2_STATUS_INTERVAL_MSEC + 4,
+	.bInterval =		USB_MS_TO_HS_INTERVAL(NCM_STATUS_INTERVAL_MS),
 };
 static struct usb_endpoint_descriptor hs_ncm_in_desc __initdata = {
 	.bLength =		USB_DT_ENDPOINT_SIZE,
diff --git a/drivers/usb/gadget/f_rndis.c b/drivers/usb/gadget/f_rndis.c
index b1681e45aca7..61f4b13c6cf5 100644
--- a/drivers/usb/gadget/f_rndis.c
+++ b/drivers/usb/gadget/f_rndis.c
@@ -101,7 +101,7 @@ static unsigned int bitrate(struct usb_gadget *g)
 /*
  */
 
-#define LOG2_STATUS_INTERVAL_MSEC	5	/* 1 << 5 == 32 msec */
+#define RNDIS_STATUS_INTERVAL_MS	32
 #define STATUS_BYTECOUNT		8	/* 8 bytes data */
 
 
@@ -190,7 +190,7 @@ static struct usb_endpoint_descriptor fs_notify_desc = {
 	.bEndpointAddress =	USB_DIR_IN,
 	.bmAttributes =		USB_ENDPOINT_XFER_INT,
 	.wMaxPacketSize =	cpu_to_le16(STATUS_BYTECOUNT),
-	.bInterval =		1 << LOG2_STATUS_INTERVAL_MSEC,
+	.bInterval =		RNDIS_STATUS_INTERVAL_MS,
 };
 
 static struct usb_endpoint_descriptor fs_in_desc = {
@@ -236,7 +236,7 @@ static struct usb_endpoint_descriptor hs_notify_desc = {
 	.bEndpointAddress =	USB_DIR_IN,
 	.bmAttributes =		USB_ENDPOINT_XFER_INT,
 	.wMaxPacketSize =	cpu_to_le16(STATUS_BYTECOUNT),
-	.bInterval =		LOG2_STATUS_INTERVAL_MSEC + 4,
+	.bInterval =		USB_MS_TO_HS_INTERVAL(RNDIS_STATUS_INTERVAL_MS)
 };
 
 static struct usb_endpoint_descriptor hs_in_desc = {
@@ -284,7 +284,7 @@ static struct usb_endpoint_descriptor ss_notify_desc = {
 	.bEndpointAddress =	USB_DIR_IN,
 	.bmAttributes =		USB_ENDPOINT_XFER_INT,
 	.wMaxPacketSize =	cpu_to_le16(STATUS_BYTECOUNT),
-	.bInterval =		LOG2_STATUS_INTERVAL_MSEC + 4,
+	.bInterval =		USB_MS_TO_HS_INTERVAL(RNDIS_STATUS_INTERVAL_MS)
 };
 
 static struct usb_ss_ep_comp_descriptor ss_intr_comp_desc = {
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index f8dda0621800..8634a127bdd3 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -38,6 +38,7 @@
 #include <linux/version.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
+#include <linux/log2.h>
 
 /*
  * USB function drivers should return USB_GADGET_DELAYED_STATUS if they
@@ -51,6 +52,7 @@
 /* big enough to hold our biggest descriptor */
 #define USB_COMP_EP0_BUFSIZ	1024
 
+#define USB_MS_TO_HS_INTERVAL(x)	(ilog2((x * 1000 / 125)) + 1)
 struct usb_configuration;
 
 /**
-- 
cgit v1.2.3-55-g7522


From 10287baec761d33f0a82d84b46e37a44030350d8 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior
Date: Mon, 22 Oct 2012 22:15:06 +0200
Subject: usb: gadget: always update HS/SS descriptors and create a copy of
 them

HS and SS descriptors are staticaly created. They are updated during the
bind process with the endpoint address, string id or interface numbers.

After that, the descriptor chain is linked to struct usb_function which
is used by composite in order to serve the GET_DESCRIPTOR requests,
number of available configs and so on.

There is no need to assign the HS descriptor only if the UDC supports
HS speed because composite won't report those to the host if HS support
has not been reached. The same reasoning is valid for SS.

This patch makes sure each function updates HS/SS descriptors
unconditionally and uses the newly introduced helper function to create a
copy the descriptors for the speed which is supported by the UDC.

While at that, also rename f->descriptors to f->fs_descriptors in order
to make it more explicit what that means.

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/gadget/composite.c      |   8 +--
 drivers/usb/gadget/config.c         |  39 +++++++++++++-
 drivers/usb/gadget/f_acm.c          |  45 +++++-----------
 drivers/usb/gadget/f_ecm.c          |  57 ++++++--------------
 drivers/usb/gadget/f_eem.c          |  46 ++++------------
 drivers/usb/gadget/f_fs.c           |   4 +-
 drivers/usb/gadget/f_hid.c          |  30 ++++-------
 drivers/usb/gadget/f_loopback.c     |  28 +++++-----
 drivers/usb/gadget/f_mass_storage.c |  59 +++++++-------------
 drivers/usb/gadget/f_midi.c         |   8 +--
 drivers/usb/gadget/f_ncm.c          |  32 +++--------
 drivers/usb/gadget/f_obex.c         |  23 ++++----
 drivers/usb/gadget/f_phonet.c       |  15 +++---
 drivers/usb/gadget/f_rndis.c        |  55 +++++--------------
 drivers/usb/gadget/f_serial.c       |  38 ++++---------
 drivers/usb/gadget/f_sourcesink.c   | 104 +++++++++++++++++-------------------
 drivers/usb/gadget/f_subset.c       |  48 +++++------------
 drivers/usb/gadget/f_uac1.c         |  22 +++-----
 drivers/usb/gadget/f_uac2.c         |  16 ++----
 drivers/usb/gadget/f_uvc.c          |  79 ++++++++++++---------------
 drivers/usb/gadget/printer.c        |  12 +++--
 drivers/usb/gadget/tcm_usb_gadget.c |  10 ++--
 include/linux/usb/composite.h       |   2 +-
 include/linux/usb/gadget.h          |   7 +++
 24 files changed, 307 insertions(+), 480 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 957f973dd96a..2a6bfe759c29 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -107,7 +107,7 @@ int config_ep_by_speed(struct usb_gadget *g,
 		}
 		/* else: fall through */
 	default:
-		speed_desc = f->descriptors;
+		speed_desc = f->fs_descriptors;
 	}
 	/* find descriptors */
 	for_each_ep_desc(speed_desc, d_spd) {
@@ -200,7 +200,7 @@ int usb_add_function(struct usb_configuration *config,
 	 * as full speed ... it's the function drivers that will need
 	 * to avoid bulk and ISO transfers.
 	 */
-	if (!config->fullspeed && function->descriptors)
+	if (!config->fullspeed && function->fs_descriptors)
 		config->fullspeed = true;
 	if (!config->highspeed && function->hs_descriptors)
 		config->highspeed = true;
@@ -363,7 +363,7 @@ static int config_buf(struct usb_configuration *config,
 			descriptors = f->hs_descriptors;
 			break;
 		default:
-			descriptors = f->descriptors;
+			descriptors = f->fs_descriptors;
 		}
 
 		if (!descriptors)
@@ -620,7 +620,7 @@ static int set_config(struct usb_composite_dev *cdev,
 			descriptors = f->hs_descriptors;
 			break;
 		default:
-			descriptors = f->descriptors;
+			descriptors = f->fs_descriptors;
 		}
 
 		for (; *descriptors; ++descriptors) {
diff --git a/drivers/usb/gadget/config.c b/drivers/usb/gadget/config.c
index e3a98929d346..34e12fc52c23 100644
--- a/drivers/usb/gadget/config.c
+++ b/drivers/usb/gadget/config.c
@@ -19,7 +19,7 @@
 
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
-
+#include <linux/usb/composite.h>
 
 /**
  * usb_descriptor_fillbuf - fill buffer with descriptors
@@ -158,3 +158,40 @@ usb_copy_descriptors(struct usb_descriptor_header **src)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(usb_copy_descriptors);
+
+int usb_assign_descriptors(struct usb_function *f,
+		struct usb_descriptor_header **fs,
+		struct usb_descriptor_header **hs,
+		struct usb_descriptor_header **ss)
+{
+	struct usb_gadget *g = f->config->cdev->gadget;
+
+	if (fs) {
+		f->fs_descriptors = usb_copy_descriptors(fs);
+		if (!f->fs_descriptors)
+			goto err;
+	}
+	if (hs && gadget_is_dualspeed(g)) {
+		f->hs_descriptors = usb_copy_descriptors(hs);
+		if (!f->hs_descriptors)
+			goto err;
+	}
+	if (ss && gadget_is_superspeed(g)) {
+		f->ss_descriptors = usb_copy_descriptors(ss);
+		if (!f->ss_descriptors)
+			goto err;
+	}
+	return 0;
+err:
+	usb_free_all_descriptors(f);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(usb_assign_descriptors);
+
+void usb_free_all_descriptors(struct usb_function *f)
+{
+	usb_free_descriptors(f->fs_descriptors);
+	usb_free_descriptors(f->hs_descriptors);
+	usb_free_descriptors(f->ss_descriptors);
+}
+EXPORT_SYMBOL_GPL(usb_free_all_descriptors);
diff --git a/drivers/usb/gadget/f_acm.c b/drivers/usb/gadget/f_acm.c
index 7c30bb49850b..308242b5d6e0 100644
--- a/drivers/usb/gadget/f_acm.c
+++ b/drivers/usb/gadget/f_acm.c
@@ -658,37 +658,22 @@ acm_bind(struct usb_configuration *c, struct usb_function *f)
 	acm->notify_req->complete = acm_cdc_notify_complete;
 	acm->notify_req->context = acm;
 
-	/* copy descriptors */
-	f->descriptors = usb_copy_descriptors(acm_fs_function);
-	if (!f->descriptors)
-		goto fail;
-
 	/* support all relevant hardware speeds... we expect that when
 	 * hardware is dual speed, all bulk-capable endpoints work at
 	 * both speeds
 	 */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		acm_hs_in_desc.bEndpointAddress =
-				acm_fs_in_desc.bEndpointAddress;
-		acm_hs_out_desc.bEndpointAddress =
-				acm_fs_out_desc.bEndpointAddress;
-		acm_hs_notify_desc.bEndpointAddress =
-				acm_fs_notify_desc.bEndpointAddress;
-
-		/* copy descriptors */
-		f->hs_descriptors = usb_copy_descriptors(acm_hs_function);
-	}
-	if (gadget_is_superspeed(c->cdev->gadget)) {
-		acm_ss_in_desc.bEndpointAddress =
-			acm_fs_in_desc.bEndpointAddress;
-		acm_ss_out_desc.bEndpointAddress =
-			acm_fs_out_desc.bEndpointAddress;
-
-		/* copy descriptors, and track endpoint copies */
-		f->ss_descriptors = usb_copy_descriptors(acm_ss_function);
-		if (!f->ss_descriptors)
-			goto fail;
-	}
+	acm_hs_in_desc.bEndpointAddress = acm_fs_in_desc.bEndpointAddress;
+	acm_hs_out_desc.bEndpointAddress = acm_fs_out_desc.bEndpointAddress;
+	acm_hs_notify_desc.bEndpointAddress =
+		acm_fs_notify_desc.bEndpointAddress;
+
+	acm_ss_in_desc.bEndpointAddress = acm_fs_in_desc.bEndpointAddress;
+	acm_ss_out_desc.bEndpointAddress = acm_fs_out_desc.bEndpointAddress;
+
+	status = usb_assign_descriptors(f, acm_fs_function, acm_hs_function,
+			acm_ss_function);
+	if (status)
+		goto fail;
 
 	DBG(cdev, "acm ttyGS%d: %s speed IN/%s OUT/%s NOTIFY/%s\n",
 			acm->port_num,
@@ -720,11 +705,7 @@ acm_unbind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct f_acm		*acm = func_to_acm(f);
 
-	if (gadget_is_dualspeed(c->cdev->gadget))
-		usb_free_descriptors(f->hs_descriptors);
-	if (gadget_is_superspeed(c->cdev->gadget))
-		usb_free_descriptors(f->ss_descriptors);
-	usb_free_descriptors(f->descriptors);
+	usb_free_all_descriptors(f);
 	gs_free_req(acm->notify, acm->notify_req);
 	kfree(acm);
 }
diff --git a/drivers/usb/gadget/f_ecm.c b/drivers/usb/gadget/f_ecm.c
index a158740255ce..2d3c5a46de8e 100644
--- a/drivers/usb/gadget/f_ecm.c
+++ b/drivers/usb/gadget/f_ecm.c
@@ -743,42 +743,24 @@ ecm_bind(struct usb_configuration *c, struct usb_function *f)
 	ecm->notify_req->context = ecm;
 	ecm->notify_req->complete = ecm_notify_complete;
 
-	/* copy descriptors, and track endpoint copies */
-	f->descriptors = usb_copy_descriptors(ecm_fs_function);
-	if (!f->descriptors)
-		goto fail;
-
 	/* support all relevant hardware speeds... we expect that when
 	 * hardware is dual speed, all bulk-capable endpoints work at
 	 * both speeds
 	 */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		hs_ecm_in_desc.bEndpointAddress =
-				fs_ecm_in_desc.bEndpointAddress;
-		hs_ecm_out_desc.bEndpointAddress =
-				fs_ecm_out_desc.bEndpointAddress;
-		hs_ecm_notify_desc.bEndpointAddress =
-				fs_ecm_notify_desc.bEndpointAddress;
-
-		/* copy descriptors, and track endpoint copies */
-		f->hs_descriptors = usb_copy_descriptors(ecm_hs_function);
-		if (!f->hs_descriptors)
-			goto fail;
-	}
-
-	if (gadget_is_superspeed(c->cdev->gadget)) {
-		ss_ecm_in_desc.bEndpointAddress =
-				fs_ecm_in_desc.bEndpointAddress;
-		ss_ecm_out_desc.bEndpointAddress =
-				fs_ecm_out_desc.bEndpointAddress;
-		ss_ecm_notify_desc.bEndpointAddress =
-				fs_ecm_notify_desc.bEndpointAddress;
-
-		/* copy descriptors, and track endpoint copies */
-		f->ss_descriptors = usb_copy_descriptors(ecm_ss_function);
-		if (!f->ss_descriptors)
-			goto fail;
-	}
+	hs_ecm_in_desc.bEndpointAddress = fs_ecm_in_desc.bEndpointAddress;
+	hs_ecm_out_desc.bEndpointAddress = fs_ecm_out_desc.bEndpointAddress;
+	hs_ecm_notify_desc.bEndpointAddress =
+		fs_ecm_notify_desc.bEndpointAddress;
+
+	ss_ecm_in_desc.bEndpointAddress = fs_ecm_in_desc.bEndpointAddress;
+	ss_ecm_out_desc.bEndpointAddress = fs_ecm_out_desc.bEndpointAddress;
+	ss_ecm_notify_desc.bEndpointAddress =
+		fs_ecm_notify_desc.bEndpointAddress;
+
+	status = usb_assign_descriptors(f, ecm_fs_function, ecm_hs_function,
+			ecm_ss_function);
+	if (status)
+		goto fail;
 
 	/* NOTE:  all that is done without knowing or caring about
 	 * the network link ... which is unavailable to this code
@@ -796,11 +778,6 @@ ecm_bind(struct usb_configuration *c, struct usb_function *f)
 	return 0;
 
 fail:
-	if (f->descriptors)
-		usb_free_descriptors(f->descriptors);
-	if (f->hs_descriptors)
-		usb_free_descriptors(f->hs_descriptors);
-
 	if (ecm->notify_req) {
 		kfree(ecm->notify_req->buf);
 		usb_ep_free_request(ecm->notify, ecm->notify_req);
@@ -826,11 +803,7 @@ ecm_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	DBG(c->cdev, "ecm unbind\n");
 
-	if (gadget_is_superspeed(c->cdev->gadget))
-		usb_free_descriptors(f->ss_descriptors);
-	if (gadget_is_dualspeed(c->cdev->gadget))
-		usb_free_descriptors(f->hs_descriptors);
-	usb_free_descriptors(f->descriptors);
+	usb_free_all_descriptors(f);
 
 	kfree(ecm->notify_req->buf);
 	usb_ep_free_request(ecm->notify, ecm->notify_req);
diff --git a/drivers/usb/gadget/f_eem.c b/drivers/usb/gadget/f_eem.c
index a9cf20522ffa..cf0ebee85563 100644
--- a/drivers/usb/gadget/f_eem.c
+++ b/drivers/usb/gadget/f_eem.c
@@ -274,38 +274,20 @@ eem_bind(struct usb_configuration *c, struct usb_function *f)
 
 	status = -ENOMEM;
 
-	/* copy descriptors, and track endpoint copies */
-	f->descriptors = usb_copy_descriptors(eem_fs_function);
-	if (!f->descriptors)
-		goto fail;
-
 	/* support all relevant hardware speeds... we expect that when
 	 * hardware is dual speed, all bulk-capable endpoints work at
 	 * both speeds
 	 */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		eem_hs_in_desc.bEndpointAddress =
-				eem_fs_in_desc.bEndpointAddress;
-		eem_hs_out_desc.bEndpointAddress =
-				eem_fs_out_desc.bEndpointAddress;
-
-		/* copy descriptors, and track endpoint copies */
-		f->hs_descriptors = usb_copy_descriptors(eem_hs_function);
-		if (!f->hs_descriptors)
-			goto fail;
-	}
+	eem_hs_in_desc.bEndpointAddress = eem_fs_in_desc.bEndpointAddress;
+	eem_hs_out_desc.bEndpointAddress = eem_fs_out_desc.bEndpointAddress;
 
-	if (gadget_is_superspeed(c->cdev->gadget)) {
-		eem_ss_in_desc.bEndpointAddress =
-				eem_fs_in_desc.bEndpointAddress;
-		eem_ss_out_desc.bEndpointAddress =
-				eem_fs_out_desc.bEndpointAddress;
+	eem_ss_in_desc.bEndpointAddress = eem_fs_in_desc.bEndpointAddress;
+	eem_ss_out_desc.bEndpointAddress = eem_fs_out_desc.bEndpointAddress;
 
-		/* copy descriptors, and track endpoint copies */
-		f->ss_descriptors = usb_copy_descriptors(eem_ss_function);
-		if (!f->ss_descriptors)
-			goto fail;
-	}
+	status = usb_assign_descriptors(f, eem_fs_function, eem_hs_function,
+			eem_ss_function);
+	if (status)
+		goto fail;
 
 	DBG(cdev, "CDC Ethernet (EEM): %s speed IN/%s OUT/%s\n",
 			gadget_is_superspeed(c->cdev->gadget) ? "super" :
@@ -314,11 +296,7 @@ eem_bind(struct usb_configuration *c, struct usb_function *f)
 	return 0;
 
 fail:
-	if (f->descriptors)
-		usb_free_descriptors(f->descriptors);
-	if (f->hs_descriptors)
-		usb_free_descriptors(f->hs_descriptors);
-
+	usb_free_all_descriptors(f);
 	if (eem->port.out_ep)
 		eem->port.out_ep->driver_data = NULL;
 	if (eem->port.in_ep)
@@ -336,11 +314,7 @@ eem_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	DBG(c->cdev, "eem unbind\n");
 
-	if (gadget_is_superspeed(c->cdev->gadget))
-		usb_free_descriptors(f->ss_descriptors);
-	if (gadget_is_dualspeed(c->cdev->gadget))
-		usb_free_descriptors(f->hs_descriptors);
-	usb_free_descriptors(f->descriptors);
+	usb_free_all_descriptors(f);
 	kfree(eem);
 }
 
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index 64c4ec10d1fc..4a6961c517f2 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -2097,7 +2097,7 @@ static int __ffs_func_bind_do_descs(enum ffs_entity_type type, u8 *valuep,
 	if (isHS)
 		func->function.hs_descriptors[(long)valuep] = desc;
 	else
-		func->function.descriptors[(long)valuep]    = desc;
+		func->function.fs_descriptors[(long)valuep]    = desc;
 
 	if (!desc || desc->bDescriptorType != USB_DT_ENDPOINT)
 		return 0;
@@ -2249,7 +2249,7 @@ static int ffs_func_bind(struct usb_configuration *c,
 	 * numbers without worrying that it may be described later on.
 	 */
 	if (likely(full)) {
-		func->function.descriptors = data->fs_descs;
+		func->function.fs_descriptors = data->fs_descs;
 		ret = ffs_do_descs(ffs->fs_descs_count,
 				   data->raw_descs,
 				   sizeof data->raw_descs,
diff --git a/drivers/usb/gadget/f_hid.c b/drivers/usb/gadget/f_hid.c
index 511e527178e2..6e69a8e8d22a 100644
--- a/drivers/usb/gadget/f_hid.c
+++ b/drivers/usb/gadget/f_hid.c
@@ -573,7 +573,6 @@ static int __init hidg_bind(struct usb_configuration *c, struct usb_function *f)
 		goto fail;
 	hidg_interface_desc.bInterfaceNumber = status;
 
-
 	/* allocate instance-specific endpoints */
 	status = -ENODEV;
 	ep = usb_ep_autoconfig(c->cdev->gadget, &hidg_fs_in_ep_desc);
@@ -609,20 +608,15 @@ static int __init hidg_bind(struct usb_configuration *c, struct usb_function *f)
 	hidg_desc.desc[0].wDescriptorLength =
 		cpu_to_le16(hidg->report_desc_length);
 
-	/* copy descriptors */
-	f->descriptors = usb_copy_descriptors(hidg_fs_descriptors);
-	if (!f->descriptors)
-		goto fail;
+	hidg_hs_in_ep_desc.bEndpointAddress =
+		hidg_fs_in_ep_desc.bEndpointAddress;
+	hidg_hs_out_ep_desc.bEndpointAddress =
+		hidg_fs_out_ep_desc.bEndpointAddress;
 
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		hidg_hs_in_ep_desc.bEndpointAddress =
-			hidg_fs_in_ep_desc.bEndpointAddress;
-		hidg_hs_out_ep_desc.bEndpointAddress =
-			hidg_fs_out_ep_desc.bEndpointAddress;
-		f->hs_descriptors = usb_copy_descriptors(hidg_hs_descriptors);
-		if (!f->hs_descriptors)
-			goto fail;
-	}
+	status = usb_assign_descriptors(f, hidg_fs_descriptors,
+			hidg_hs_descriptors, NULL);
+	if (status)
+		goto fail;
 
 	mutex_init(&hidg->lock);
 	spin_lock_init(&hidg->spinlock);
@@ -649,9 +643,7 @@ fail:
 			usb_ep_free_request(hidg->in_ep, hidg->req);
 	}
 
-	usb_free_descriptors(f->hs_descriptors);
-	usb_free_descriptors(f->descriptors);
-
+	usb_free_all_descriptors(f);
 	return status;
 }
 
@@ -668,9 +660,7 @@ static void hidg_unbind(struct usb_configuration *c, struct usb_function *f)
 	kfree(hidg->req->buf);
 	usb_ep_free_request(hidg->in_ep, hidg->req);
 
-	/* free descriptors copies */
-	usb_free_descriptors(f->hs_descriptors);
-	usb_free_descriptors(f->descriptors);
+	usb_free_all_descriptors(f);
 
 	kfree(hidg->report_desc);
 	kfree(hidg);
diff --git a/drivers/usb/gadget/f_loopback.c b/drivers/usb/gadget/f_loopback.c
index 7275706caeb0..bb39cb2bb3a3 100644
--- a/drivers/usb/gadget/f_loopback.c
+++ b/drivers/usb/gadget/f_loopback.c
@@ -177,6 +177,7 @@ loopback_bind(struct usb_configuration *c, struct usb_function *f)
 	struct usb_composite_dev *cdev = c->cdev;
 	struct f_loopback	*loop = func_to_loop(f);
 	int			id;
+	int ret;
 
 	/* allocate interface ID(s) */
 	id = usb_interface_id(c, f);
@@ -201,22 +202,19 @@ autoconf_fail:
 	loop->out_ep->driver_data = cdev;	/* claim */
 
 	/* support high speed hardware */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		hs_loop_source_desc.bEndpointAddress =
-				fs_loop_source_desc.bEndpointAddress;
-		hs_loop_sink_desc.bEndpointAddress =
-				fs_loop_sink_desc.bEndpointAddress;
-		f->hs_descriptors = hs_loopback_descs;
-	}
+	hs_loop_source_desc.bEndpointAddress =
+		fs_loop_source_desc.bEndpointAddress;
+	hs_loop_sink_desc.bEndpointAddress = fs_loop_sink_desc.bEndpointAddress;
 
 	/* support super speed hardware */
-	if (gadget_is_superspeed(c->cdev->gadget)) {
-		ss_loop_source_desc.bEndpointAddress =
-				fs_loop_source_desc.bEndpointAddress;
-		ss_loop_sink_desc.bEndpointAddress =
-				fs_loop_sink_desc.bEndpointAddress;
-		f->ss_descriptors = ss_loopback_descs;
-	}
+	ss_loop_source_desc.bEndpointAddress =
+		fs_loop_source_desc.bEndpointAddress;
+	ss_loop_sink_desc.bEndpointAddress = fs_loop_sink_desc.bEndpointAddress;
+
+	ret = usb_assign_descriptors(f, fs_loopback_descs, hs_loopback_descs,
+			ss_loopback_descs);
+	if (ret)
+		return ret;
 
 	DBG(cdev, "%s speed %s: IN/%s, OUT/%s\n",
 	    (gadget_is_superspeed(c->cdev->gadget) ? "super" :
@@ -228,6 +226,7 @@ autoconf_fail:
 static void
 loopback_unbind(struct usb_configuration *c, struct usb_function *f)
 {
+	usb_free_all_descriptors(f);
 	kfree(func_to_loop(f));
 }
 
@@ -379,7 +378,6 @@ static int __init loopback_bind_config(struct usb_configuration *c)
 		return -ENOMEM;
 
 	loop->function.name = "loopback";
-	loop->function.descriptors = fs_loopback_descs;
 	loop->function.bind = loopback_bind;
 	loop->function.unbind = loopback_unbind;
 	loop->function.set_alt = loopback_set_alt;
diff --git a/drivers/usb/gadget/f_mass_storage.c b/drivers/usb/gadget/f_mass_storage.c
index 3a7668bde3ef..3433e432a4ae 100644
--- a/drivers/usb/gadget/f_mass_storage.c
+++ b/drivers/usb/gadget/f_mass_storage.c
@@ -2904,9 +2904,7 @@ static void fsg_unbind(struct usb_configuration *c, struct usb_function *f)
 	}
 
 	fsg_common_put(common);
-	usb_free_descriptors(fsg->function.descriptors);
-	usb_free_descriptors(fsg->function.hs_descriptors);
-	usb_free_descriptors(fsg->function.ss_descriptors);
+	usb_free_all_descriptors(&fsg->function);
 	kfree(fsg);
 }
 
@@ -2916,6 +2914,8 @@ static int fsg_bind(struct usb_configuration *c, struct usb_function *f)
 	struct usb_gadget	*gadget = c->cdev->gadget;
 	int			i;
 	struct usb_ep		*ep;
+	unsigned		max_burst;
+	int			ret;
 
 	fsg->gadget = gadget;
 
@@ -2939,45 +2939,27 @@ static int fsg_bind(struct usb_configuration *c, struct usb_function *f)
 	ep->driver_data = fsg->common;	/* claim the endpoint */
 	fsg->bulk_out = ep;
 
-	/* Copy descriptors */
-	f->descriptors = usb_copy_descriptors(fsg_fs_function);
-	if (unlikely(!f->descriptors))
-		return -ENOMEM;
-
-	if (gadget_is_dualspeed(gadget)) {
-		/* Assume endpoint addresses are the same for both speeds */
-		fsg_hs_bulk_in_desc.bEndpointAddress =
-			fsg_fs_bulk_in_desc.bEndpointAddress;
-		fsg_hs_bulk_out_desc.bEndpointAddress =
-			fsg_fs_bulk_out_desc.bEndpointAddress;
-		f->hs_descriptors = usb_copy_descriptors(fsg_hs_function);
-		if (unlikely(!f->hs_descriptors)) {
-			usb_free_descriptors(f->descriptors);
-			return -ENOMEM;
-		}
-	}
-
-	if (gadget_is_superspeed(gadget)) {
-		unsigned	max_burst;
+	/* Assume endpoint addresses are the same for both speeds */
+	fsg_hs_bulk_in_desc.bEndpointAddress =
+		fsg_fs_bulk_in_desc.bEndpointAddress;
+	fsg_hs_bulk_out_desc.bEndpointAddress =
+		fsg_fs_bulk_out_desc.bEndpointAddress;
 
-		/* Calculate bMaxBurst, we know packet size is 1024 */
-		max_burst = min_t(unsigned, FSG_BUFLEN / 1024, 15);
+	/* Calculate bMaxBurst, we know packet size is 1024 */
+	max_burst = min_t(unsigned, FSG_BUFLEN / 1024, 15);
 
-		fsg_ss_bulk_in_desc.bEndpointAddress =
-			fsg_fs_bulk_in_desc.bEndpointAddress;
-		fsg_ss_bulk_in_comp_desc.bMaxBurst = max_burst;
+	fsg_ss_bulk_in_desc.bEndpointAddress =
+		fsg_fs_bulk_in_desc.bEndpointAddress;
+	fsg_ss_bulk_in_comp_desc.bMaxBurst = max_burst;
 
-		fsg_ss_bulk_out_desc.bEndpointAddress =
-			fsg_fs_bulk_out_desc.bEndpointAddress;
-		fsg_ss_bulk_out_comp_desc.bMaxBurst = max_burst;
+	fsg_ss_bulk_out_desc.bEndpointAddress =
+		fsg_fs_bulk_out_desc.bEndpointAddress;
+	fsg_ss_bulk_out_comp_desc.bMaxBurst = max_burst;
 
-		f->ss_descriptors = usb_copy_descriptors(fsg_ss_function);
-		if (unlikely(!f->ss_descriptors)) {
-			usb_free_descriptors(f->hs_descriptors);
-			usb_free_descriptors(f->descriptors);
-			return -ENOMEM;
-		}
-	}
+	ret = usb_assign_descriptors(f, fsg_fs_function, fsg_hs_function,
+			fsg_ss_function);
+	if (ret)
+		goto autoconf_fail;
 
 	return 0;
 
@@ -2986,7 +2968,6 @@ autoconf_fail:
 	return -ENOTSUPP;
 }
 
-
 /****************************** ADD FUNCTION ******************************/
 
 static struct usb_gadget_strings *fsg_strings_array[] = {
diff --git a/drivers/usb/gadget/f_midi.c b/drivers/usb/gadget/f_midi.c
index b265ee8fa5aa..263e721c2694 100644
--- a/drivers/usb/gadget/f_midi.c
+++ b/drivers/usb/gadget/f_midi.c
@@ -414,8 +414,7 @@ static void f_midi_unbind(struct usb_configuration *c, struct usb_function *f)
 	kfree(midi->id);
 	midi->id = NULL;
 
-	usb_free_descriptors(f->descriptors);
-	usb_free_descriptors(f->hs_descriptors);
+	usb_free_all_descriptors(f);
 	kfree(midi);
 }
 
@@ -882,9 +881,10 @@ f_midi_bind(struct usb_configuration *c, struct usb_function *f)
 	 * both speeds
 	 */
 	/* copy descriptors, and track endpoint copies */
-	f->descriptors = usb_copy_descriptors(midi_function);
-	if (!f->descriptors)
+	f->fs_descriptors = usb_copy_descriptors(midi_function);
+	if (!f->fs_descriptors)
 		goto fail_f_midi;
+
 	if (gadget_is_dualspeed(c->cdev->gadget)) {
 		bulk_in_desc.wMaxPacketSize = cpu_to_le16(512);
 		bulk_out_desc.wMaxPacketSize = cpu_to_le16(512);
diff --git a/drivers/usb/gadget/f_ncm.c b/drivers/usb/gadget/f_ncm.c
index 424fc3d1cc36..326d7e6c297c 100644
--- a/drivers/usb/gadget/f_ncm.c
+++ b/drivers/usb/gadget/f_ncm.c
@@ -1208,30 +1208,18 @@ ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	ncm->notify_req->context = ncm;
 	ncm->notify_req->complete = ncm_notify_complete;
 
-	/* copy descriptors, and track endpoint copies */
-	f->descriptors = usb_copy_descriptors(ncm_fs_function);
-	if (!f->descriptors)
-		goto fail;
-
 	/*
 	 * support all relevant hardware speeds... we expect that when
 	 * hardware is dual speed, all bulk-capable endpoints work at
 	 * both speeds
 	 */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		hs_ncm_in_desc.bEndpointAddress =
-				fs_ncm_in_desc.bEndpointAddress;
-		hs_ncm_out_desc.bEndpointAddress =
-				fs_ncm_out_desc.bEndpointAddress;
-		hs_ncm_notify_desc.bEndpointAddress =
-				fs_ncm_notify_desc.bEndpointAddress;
-
-		/* copy descriptors, and track endpoint copies */
-		f->hs_descriptors = usb_copy_descriptors(ncm_hs_function);
-		if (!f->hs_descriptors)
-			goto fail;
-	}
+	hs_ncm_in_desc.bEndpointAddress = fs_ncm_in_desc.bEndpointAddress;
+	hs_ncm_out_desc.bEndpointAddress = fs_ncm_out_desc.bEndpointAddress;
+	hs_ncm_notify_desc.bEndpointAddress =
+		fs_ncm_notify_desc.bEndpointAddress;
 
+	status = usb_assign_descriptors(f, ncm_fs_function, ncm_hs_function,
+			NULL);
 	/*
 	 * NOTE:  all that is done without knowing or caring about
 	 * the network link ... which is unavailable to this code
@@ -1248,9 +1236,7 @@ ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	return 0;
 
 fail:
-	if (f->descriptors)
-		usb_free_descriptors(f->descriptors);
-
+	usb_free_all_descriptors(f);
 	if (ncm->notify_req) {
 		kfree(ncm->notify_req->buf);
 		usb_ep_free_request(ncm->notify, ncm->notify_req);
@@ -1276,9 +1262,7 @@ ncm_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	DBG(c->cdev, "ncm unbind\n");
 
-	if (gadget_is_dualspeed(c->cdev->gadget))
-		usb_free_descriptors(f->hs_descriptors);
-	usb_free_descriptors(f->descriptors);
+	usb_free_all_descriptors(f);
 
 	kfree(ncm->notify_req->buf);
 	usb_ep_free_request(ncm->notify, ncm->notify_req);
diff --git a/drivers/usb/gadget/f_obex.c b/drivers/usb/gadget/f_obex.c
index 5f400f66aa9b..d74491ad82cb 100644
--- a/drivers/usb/gadget/f_obex.c
+++ b/drivers/usb/gadget/f_obex.c
@@ -331,23 +331,19 @@ obex_bind(struct usb_configuration *c, struct usb_function *f)
 	obex->port.out = ep;
 	ep->driver_data = cdev;	/* claim */
 
-	/* copy descriptors, and track endpoint copies */
-	f->descriptors = usb_copy_descriptors(fs_function);
-
 	/* support all relevant hardware speeds... we expect that when
 	 * hardware is dual speed, all bulk-capable endpoints work at
 	 * both speeds
 	 */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
 
-		obex_hs_ep_in_desc.bEndpointAddress =
-				obex_fs_ep_in_desc.bEndpointAddress;
-		obex_hs_ep_out_desc.bEndpointAddress =
-				obex_fs_ep_out_desc.bEndpointAddress;
+	obex_hs_ep_in_desc.bEndpointAddress =
+		obex_fs_ep_in_desc.bEndpointAddress;
+	obex_hs_ep_out_desc.bEndpointAddress =
+		obex_fs_ep_out_desc.bEndpointAddress;
 
-		/* copy descriptors, and track endpoint copies */
-		f->hs_descriptors = usb_copy_descriptors(hs_function);
-	}
+	status = usb_assign_descriptors(f, fs_function, hs_function, NULL);
+	if (status)
+		goto fail;
 
 	/* Avoid letting this gadget enumerate until the userspace
 	 * OBEX server is active.
@@ -368,6 +364,7 @@ obex_bind(struct usb_configuration *c, struct usb_function *f)
 	return 0;
 
 fail:
+	usb_free_all_descriptors(f);
 	/* we might as well release our claims on endpoints */
 	if (obex->port.out)
 		obex->port.out->driver_data = NULL;
@@ -382,9 +379,7 @@ fail:
 static void
 obex_unbind(struct usb_configuration *c, struct usb_function *f)
 {
-	if (gadget_is_dualspeed(c->cdev->gadget))
-		usb_free_descriptors(f->hs_descriptors);
-	usb_free_descriptors(f->descriptors);
+	usb_free_all_descriptors(f);
 	kfree(func_to_obex(f));
 }
 
diff --git a/drivers/usb/gadget/f_phonet.c b/drivers/usb/gadget/f_phonet.c
index a6c19a486d53..b21ab558b6c0 100644
--- a/drivers/usb/gadget/f_phonet.c
+++ b/drivers/usb/gadget/f_phonet.c
@@ -515,14 +515,14 @@ int pn_bind(struct usb_configuration *c, struct usb_function *f)
 	fp->in_ep = ep;
 	ep->driver_data = fp; /* Claim */
 
-	pn_hs_sink_desc.bEndpointAddress =
-		pn_fs_sink_desc.bEndpointAddress;
-	pn_hs_source_desc.bEndpointAddress =
-		pn_fs_source_desc.bEndpointAddress;
+	pn_hs_sink_desc.bEndpointAddress = pn_fs_sink_desc.bEndpointAddress;
+	pn_hs_source_desc.bEndpointAddress = pn_fs_source_desc.bEndpointAddress;
 
 	/* Do not try to bind Phonet twice... */
-	fp->function.descriptors = fs_pn_function;
-	fp->function.hs_descriptors = hs_pn_function;
+	status = usb_assign_descriptors(f, fs_pn_function, hs_pn_function,
+			NULL);
+	if (status)
+		goto err;
 
 	/* Incoming USB requests */
 	status = -ENOMEM;
@@ -551,7 +551,7 @@ err_req:
 	for (i = 0; i < phonet_rxq_size && fp->out_reqv[i]; i++)
 		usb_ep_free_request(fp->out_ep, fp->out_reqv[i]);
 err:
-
+	usb_free_all_descriptors(f);
 	if (fp->out_ep)
 		fp->out_ep->driver_data = NULL;
 	if (fp->in_ep)
@@ -573,6 +573,7 @@ pn_unbind(struct usb_configuration *c, struct usb_function *f)
 		if (fp->out_reqv[i])
 			usb_ep_free_request(fp->out_ep, fp->out_reqv[i]);
 
+	usb_free_all_descriptors(f);
 	kfree(fp);
 }
 
diff --git a/drivers/usb/gadget/f_rndis.c b/drivers/usb/gadget/f_rndis.c
index 7c27626f0235..e7c25105bd8e 100644
--- a/drivers/usb/gadget/f_rndis.c
+++ b/drivers/usb/gadget/f_rndis.c
@@ -722,42 +722,22 @@ rndis_bind(struct usb_configuration *c, struct usb_function *f)
 	rndis->notify_req->context = rndis;
 	rndis->notify_req->complete = rndis_response_complete;
 
-	/* copy descriptors, and track endpoint copies */
-	f->descriptors = usb_copy_descriptors(eth_fs_function);
-	if (!f->descriptors)
-		goto fail;
-
 	/* support all relevant hardware speeds... we expect that when
 	 * hardware is dual speed, all bulk-capable endpoints work at
 	 * both speeds
 	 */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		hs_in_desc.bEndpointAddress =
-				fs_in_desc.bEndpointAddress;
-		hs_out_desc.bEndpointAddress =
-				fs_out_desc.bEndpointAddress;
-		hs_notify_desc.bEndpointAddress =
-				fs_notify_desc.bEndpointAddress;
-
-		/* copy descriptors, and track endpoint copies */
-		f->hs_descriptors = usb_copy_descriptors(eth_hs_function);
-		if (!f->hs_descriptors)
-			goto fail;
-	}
+	hs_in_desc.bEndpointAddress = fs_in_desc.bEndpointAddress;
+	hs_out_desc.bEndpointAddress = fs_out_desc.bEndpointAddress;
+	hs_notify_desc.bEndpointAddress = fs_notify_desc.bEndpointAddress;
 
-	if (gadget_is_superspeed(c->cdev->gadget)) {
-		ss_in_desc.bEndpointAddress =
-				fs_in_desc.bEndpointAddress;
-		ss_out_desc.bEndpointAddress =
-				fs_out_desc.bEndpointAddress;
-		ss_notify_desc.bEndpointAddress =
-				fs_notify_desc.bEndpointAddress;
-
-		/* copy descriptors, and track endpoint copies */
-		f->ss_descriptors = usb_copy_descriptors(eth_ss_function);
-		if (!f->ss_descriptors)
-			goto fail;
-	}
+	ss_in_desc.bEndpointAddress = fs_in_desc.bEndpointAddress;
+	ss_out_desc.bEndpointAddress = fs_out_desc.bEndpointAddress;
+	ss_notify_desc.bEndpointAddress = fs_notify_desc.bEndpointAddress;
+
+	status = usb_assign_descriptors(f, eth_fs_function, eth_hs_function,
+			eth_ss_function);
+	if (status)
+		goto fail;
 
 	rndis->port.open = rndis_open;
 	rndis->port.close = rndis_close;
@@ -788,12 +768,7 @@ rndis_bind(struct usb_configuration *c, struct usb_function *f)
 	return 0;
 
 fail:
-	if (gadget_is_superspeed(c->cdev->gadget) && f->ss_descriptors)
-		usb_free_descriptors(f->ss_descriptors);
-	if (gadget_is_dualspeed(c->cdev->gadget) && f->hs_descriptors)
-		usb_free_descriptors(f->hs_descriptors);
-	if (f->descriptors)
-		usb_free_descriptors(f->descriptors);
+	usb_free_all_descriptors(f);
 
 	if (rndis->notify_req) {
 		kfree(rndis->notify_req->buf);
@@ -822,11 +797,7 @@ rndis_unbind(struct usb_configuration *c, struct usb_function *f)
 	rndis_exit();
 	rndis_string_defs[0].id = 0;
 
-	if (gadget_is_superspeed(c->cdev->gadget))
-		usb_free_descriptors(f->ss_descriptors);
-	if (gadget_is_dualspeed(c->cdev->gadget))
-		usb_free_descriptors(f->hs_descriptors);
-	usb_free_descriptors(f->descriptors);
+	usb_free_all_descriptors(f);
 
 	kfree(rndis->notify_req->buf);
 	usb_ep_free_request(rndis->notify, rndis->notify_req);
diff --git a/drivers/usb/gadget/f_serial.c b/drivers/usb/gadget/f_serial.c
index 07197d63d9b1..98fa7795df5f 100644
--- a/drivers/usb/gadget/f_serial.c
+++ b/drivers/usb/gadget/f_serial.c
@@ -213,34 +213,20 @@ gser_bind(struct usb_configuration *c, struct usb_function *f)
 	gser->port.out = ep;
 	ep->driver_data = cdev;	/* claim */
 
-	/* copy descriptors, and track endpoint copies */
-	f->descriptors = usb_copy_descriptors(gser_fs_function);
-
 	/* support all relevant hardware speeds... we expect that when
 	 * hardware is dual speed, all bulk-capable endpoints work at
 	 * both speeds
 	 */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		gser_hs_in_desc.bEndpointAddress =
-				gser_fs_in_desc.bEndpointAddress;
-		gser_hs_out_desc.bEndpointAddress =
-				gser_fs_out_desc.bEndpointAddress;
-
-		/* copy descriptors, and track endpoint copies */
-		f->hs_descriptors = usb_copy_descriptors(gser_hs_function);
-	}
-	if (gadget_is_superspeed(c->cdev->gadget)) {
-		gser_ss_in_desc.bEndpointAddress =
-			gser_fs_in_desc.bEndpointAddress;
-		gser_ss_out_desc.bEndpointAddress =
-			gser_fs_out_desc.bEndpointAddress;
-
-		/* copy descriptors, and track endpoint copies */
-		f->ss_descriptors = usb_copy_descriptors(gser_ss_function);
-		if (!f->ss_descriptors)
-			goto fail;
-	}
+	gser_hs_in_desc.bEndpointAddress = gser_fs_in_desc.bEndpointAddress;
+	gser_hs_out_desc.bEndpointAddress = gser_fs_out_desc.bEndpointAddress;
 
+	gser_ss_in_desc.bEndpointAddress = gser_fs_in_desc.bEndpointAddress;
+	gser_ss_out_desc.bEndpointAddress = gser_fs_out_desc.bEndpointAddress;
+
+	status = usb_assign_descriptors(f, gser_fs_function, gser_hs_function,
+			gser_ss_function);
+	if (status)
+		goto fail;
 	DBG(cdev, "generic ttyGS%d: %s speed IN/%s OUT/%s\n",
 			gser->port_num,
 			gadget_is_superspeed(c->cdev->gadget) ? "super" :
@@ -263,11 +249,7 @@ fail:
 static void
 gser_unbind(struct usb_configuration *c, struct usb_function *f)
 {
-	if (gadget_is_dualspeed(c->cdev->gadget))
-		usb_free_descriptors(f->hs_descriptors);
-	if (gadget_is_superspeed(c->cdev->gadget))
-		usb_free_descriptors(f->ss_descriptors);
-	usb_free_descriptors(f->descriptors);
+	usb_free_all_descriptors(f);
 	kfree(func_to_gser(f));
 }
 
diff --git a/drivers/usb/gadget/f_sourcesink.c b/drivers/usb/gadget/f_sourcesink.c
index 3c126fde6e7e..102d49beb9df 100644
--- a/drivers/usb/gadget/f_sourcesink.c
+++ b/drivers/usb/gadget/f_sourcesink.c
@@ -319,6 +319,7 @@ sourcesink_bind(struct usb_configuration *c, struct usb_function *f)
 	struct usb_composite_dev *cdev = c->cdev;
 	struct f_sourcesink	*ss = func_to_ss(f);
 	int	id;
+	int ret;
 
 	/* allocate interface ID(s) */
 	id = usb_interface_id(c, f);
@@ -387,64 +388,57 @@ no_iso:
 		isoc_maxpacket = 1024;
 
 	/* support high speed hardware */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		hs_source_desc.bEndpointAddress =
-				fs_source_desc.bEndpointAddress;
-		hs_sink_desc.bEndpointAddress =
-				fs_sink_desc.bEndpointAddress;
+	hs_source_desc.bEndpointAddress = fs_source_desc.bEndpointAddress;
+	hs_sink_desc.bEndpointAddress = fs_sink_desc.bEndpointAddress;
 
-		/*
-		 * Fill in the HS isoc descriptors from the module parameters.
-		 * We assume that the user knows what they are doing and won't
-		 * give parameters that their UDC doesn't support.
-		 */
-		hs_iso_source_desc.wMaxPacketSize = isoc_maxpacket;
-		hs_iso_source_desc.wMaxPacketSize |= isoc_mult << 11;
-		hs_iso_source_desc.bInterval = isoc_interval;
-		hs_iso_source_desc.bEndpointAddress =
-				fs_iso_source_desc.bEndpointAddress;
-
-		hs_iso_sink_desc.wMaxPacketSize = isoc_maxpacket;
-		hs_iso_sink_desc.wMaxPacketSize |= isoc_mult << 11;
-		hs_iso_sink_desc.bInterval = isoc_interval;
-		hs_iso_sink_desc.bEndpointAddress =
-				fs_iso_sink_desc.bEndpointAddress;
-
-		f->hs_descriptors = hs_source_sink_descs;
-	}
+	/*
+	 * Fill in the HS isoc descriptors from the module parameters.
+	 * We assume that the user knows what they are doing and won't
+	 * give parameters that their UDC doesn't support.
+	 */
+	hs_iso_source_desc.wMaxPacketSize = isoc_maxpacket;
+	hs_iso_source_desc.wMaxPacketSize |= isoc_mult << 11;
+	hs_iso_source_desc.bInterval = isoc_interval;
+	hs_iso_source_desc.bEndpointAddress =
+		fs_iso_source_desc.bEndpointAddress;
+
+	hs_iso_sink_desc.wMaxPacketSize = isoc_maxpacket;
+	hs_iso_sink_desc.wMaxPacketSize |= isoc_mult << 11;
+	hs_iso_sink_desc.bInterval = isoc_interval;
+	hs_iso_sink_desc.bEndpointAddress = fs_iso_sink_desc.bEndpointAddress;
 
 	/* support super speed hardware */
-	if (gadget_is_superspeed(c->cdev->gadget)) {
-		ss_source_desc.bEndpointAddress =
-				fs_source_desc.bEndpointAddress;
-		ss_sink_desc.bEndpointAddress =
-				fs_sink_desc.bEndpointAddress;
+	ss_source_desc.bEndpointAddress =
+		fs_source_desc.bEndpointAddress;
+	ss_sink_desc.bEndpointAddress =
+		fs_sink_desc.bEndpointAddress;
 
-		/*
-		 * Fill in the SS isoc descriptors from the module parameters.
-		 * We assume that the user knows what they are doing and won't
-		 * give parameters that their UDC doesn't support.
-		 */
-		ss_iso_source_desc.wMaxPacketSize = isoc_maxpacket;
-		ss_iso_source_desc.bInterval = isoc_interval;
-		ss_iso_source_comp_desc.bmAttributes = isoc_mult;
-		ss_iso_source_comp_desc.bMaxBurst = isoc_maxburst;
-		ss_iso_source_comp_desc.wBytesPerInterval =
-			isoc_maxpacket * (isoc_mult + 1) * (isoc_maxburst + 1);
-		ss_iso_source_desc.bEndpointAddress =
-				fs_iso_source_desc.bEndpointAddress;
-
-		ss_iso_sink_desc.wMaxPacketSize = isoc_maxpacket;
-		ss_iso_sink_desc.bInterval = isoc_interval;
-		ss_iso_sink_comp_desc.bmAttributes = isoc_mult;
-		ss_iso_sink_comp_desc.bMaxBurst = isoc_maxburst;
-		ss_iso_sink_comp_desc.wBytesPerInterval =
-			isoc_maxpacket * (isoc_mult + 1) * (isoc_maxburst + 1);
-		ss_iso_sink_desc.bEndpointAddress =
-				fs_iso_sink_desc.bEndpointAddress;
-
-		f->ss_descriptors = ss_source_sink_descs;
-	}
+	/*
+	 * Fill in the SS isoc descriptors from the module parameters.
+	 * We assume that the user knows what they are doing and won't
+	 * give parameters that their UDC doesn't support.
+	 */
+	ss_iso_source_desc.wMaxPacketSize = isoc_maxpacket;
+	ss_iso_source_desc.bInterval = isoc_interval;
+	ss_iso_source_comp_desc.bmAttributes = isoc_mult;
+	ss_iso_source_comp_desc.bMaxBurst = isoc_maxburst;
+	ss_iso_source_comp_desc.wBytesPerInterval =
+		isoc_maxpacket * (isoc_mult + 1) * (isoc_maxburst + 1);
+	ss_iso_source_desc.bEndpointAddress =
+		fs_iso_source_desc.bEndpointAddress;
+
+	ss_iso_sink_desc.wMaxPacketSize = isoc_maxpacket;
+	ss_iso_sink_desc.bInterval = isoc_interval;
+	ss_iso_sink_comp_desc.bmAttributes = isoc_mult;
+	ss_iso_sink_comp_desc.bMaxBurst = isoc_maxburst;
+	ss_iso_sink_comp_desc.wBytesPerInterval =
+		isoc_maxpacket * (isoc_mult + 1) * (isoc_maxburst + 1);
+	ss_iso_sink_desc.bEndpointAddress = fs_iso_sink_desc.bEndpointAddress;
+
+	ret = usb_assign_descriptors(f, fs_source_sink_descs,
+			hs_source_sink_descs, ss_source_sink_descs);
+	if (ret)
+		return ret;
 
 	DBG(cdev, "%s speed %s: IN/%s, OUT/%s, ISO-IN/%s, ISO-OUT/%s\n",
 	    (gadget_is_superspeed(c->cdev->gadget) ? "super" :
@@ -458,6 +452,7 @@ no_iso:
 static void
 sourcesink_unbind(struct usb_configuration *c, struct usb_function *f)
 {
+	usb_free_all_descriptors(f);
 	kfree(func_to_ss(f));
 }
 
@@ -773,7 +768,6 @@ static int __init sourcesink_bind_config(struct usb_configuration *c)
 		return -ENOMEM;
 
 	ss->function.name = "source/sink";
-	ss->function.descriptors = fs_source_sink_descs;
 	ss->function.bind = sourcesink_bind;
 	ss->function.unbind = sourcesink_unbind;
 	ss->function.set_alt = sourcesink_set_alt;
diff --git a/drivers/usb/gadget/f_subset.c b/drivers/usb/gadget/f_subset.c
index deb437c3b53e..856dbae586f1 100644
--- a/drivers/usb/gadget/f_subset.c
+++ b/drivers/usb/gadget/f_subset.c
@@ -319,38 +319,22 @@ geth_bind(struct usb_configuration *c, struct usb_function *f)
 	geth->port.out_ep = ep;
 	ep->driver_data = cdev;	/* claim */
 
-	/* copy descriptors, and track endpoint copies */
-	f->descriptors = usb_copy_descriptors(fs_eth_function);
-	if (!f->descriptors)
-		goto fail;
-
 	/* support all relevant hardware speeds... we expect that when
 	 * hardware is dual speed, all bulk-capable endpoints work at
 	 * both speeds
 	 */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		hs_subset_in_desc.bEndpointAddress =
-				fs_subset_in_desc.bEndpointAddress;
-		hs_subset_out_desc.bEndpointAddress =
-				fs_subset_out_desc.bEndpointAddress;
-
-		/* copy descriptors, and track endpoint copies */
-		f->hs_descriptors = usb_copy_descriptors(hs_eth_function);
-		if (!f->hs_descriptors)
-			goto fail;
-	}
+	hs_subset_in_desc.bEndpointAddress = fs_subset_in_desc.bEndpointAddress;
+	hs_subset_out_desc.bEndpointAddress =
+		fs_subset_out_desc.bEndpointAddress;
 
-	if (gadget_is_superspeed(c->cdev->gadget)) {
-		ss_subset_in_desc.bEndpointAddress =
-				fs_subset_in_desc.bEndpointAddress;
-		ss_subset_out_desc.bEndpointAddress =
-				fs_subset_out_desc.bEndpointAddress;
+	ss_subset_in_desc.bEndpointAddress = fs_subset_in_desc.bEndpointAddress;
+	ss_subset_out_desc.bEndpointAddress =
+		fs_subset_out_desc.bEndpointAddress;
 
-		/* copy descriptors, and track endpoint copies */
-		f->ss_descriptors = usb_copy_descriptors(ss_eth_function);
-		if (!f->ss_descriptors)
-			goto fail;
-	}
+	status = usb_assign_descriptors(f, fs_eth_function, hs_eth_function,
+			ss_eth_function);
+	if (status)
+		goto fail;
 
 	/* NOTE:  all that is done without knowing or caring about
 	 * the network link ... which is unavailable to this code
@@ -364,11 +348,7 @@ geth_bind(struct usb_configuration *c, struct usb_function *f)
 	return 0;
 
 fail:
-	if (f->descriptors)
-		usb_free_descriptors(f->descriptors);
-	if (f->hs_descriptors)
-		usb_free_descriptors(f->hs_descriptors);
-
+	usb_free_all_descriptors(f);
 	/* we might as well release our claims on endpoints */
 	if (geth->port.out_ep)
 		geth->port.out_ep->driver_data = NULL;
@@ -383,11 +363,7 @@ fail:
 static void
 geth_unbind(struct usb_configuration *c, struct usb_function *f)
 {
-	if (gadget_is_superspeed(c->cdev->gadget))
-		usb_free_descriptors(f->ss_descriptors);
-	if (gadget_is_dualspeed(c->cdev->gadget))
-		usb_free_descriptors(f->hs_descriptors);
-	usb_free_descriptors(f->descriptors);
+	usb_free_all_descriptors(f);
 	geth_string_defs[1].s = NULL;
 	kfree(func_to_geth(f));
 }
diff --git a/drivers/usb/gadget/f_uac1.c b/drivers/usb/gadget/f_uac1.c
index c8ed41ba1042..f570e667a640 100644
--- a/drivers/usb/gadget/f_uac1.c
+++ b/drivers/usb/gadget/f_uac1.c
@@ -630,7 +630,7 @@ f_audio_bind(struct usb_configuration *c, struct usb_function *f)
 	struct usb_composite_dev *cdev = c->cdev;
 	struct f_audio		*audio = func_to_audio(f);
 	int			status;
-	struct usb_ep		*ep;
+	struct usb_ep		*ep = NULL;
 
 	f_audio_build_desc(audio);
 
@@ -659,21 +659,14 @@ f_audio_bind(struct usb_configuration *c, struct usb_function *f)
 	status = -ENOMEM;
 
 	/* copy descriptors, and track endpoint copies */
-	f->descriptors = usb_copy_descriptors(f_audio_desc);
-
-	/*
-	 * support all relevant hardware speeds... we expect that when
-	 * hardware is dual speed, all bulk-capable endpoints work at
-	 * both speeds
-	 */
-	if (gadget_is_dualspeed(c->cdev->gadget)) {
-		f->hs_descriptors = usb_copy_descriptors(f_audio_desc);
-	}
-
+	status = usb_assign_descriptors(f, f_audio_desc, f_audio_desc, NULL);
+	if (status)
+		goto fail;
 	return 0;
 
 fail:
-
+	if (ep)
+		ep->driver_data = NULL;
 	return status;
 }
 
@@ -682,8 +675,7 @@ f_audio_unbind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct f_audio		*audio = func_to_audio(f);
 
-	usb_free_descriptors(f->descriptors);
-	usb_free_descriptors(f->hs_descriptors);
+	usb_free_all_descriptors(f);
 	kfree(audio);
 }
 
diff --git a/drivers/usb/gadget/f_uac2.c b/drivers/usb/gadget/f_uac2.c
index f02b8ece5287..730a260e1841 100644
--- a/drivers/usb/gadget/f_uac2.c
+++ b/drivers/usb/gadget/f_uac2.c
@@ -998,9 +998,9 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn)
 	hs_epin_desc.bEndpointAddress = fs_epin_desc.bEndpointAddress;
 	hs_epin_desc.wMaxPacketSize = fs_epin_desc.wMaxPacketSize;
 
-	fn->descriptors = usb_copy_descriptors(fs_audio_desc);
-	if (gadget_is_dualspeed(gadget))
-		fn->hs_descriptors = usb_copy_descriptors(hs_audio_desc);
+	ret = usb_assign_descriptors(fn, fs_audio_desc, hs_audio_desc, NULL);
+	if (ret)
+		goto err;
 
 	prm = &agdev->uac2.c_prm;
 	prm->max_psize = hs_epout_desc.wMaxPacketSize;
@@ -1029,8 +1029,7 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn)
 err:
 	kfree(agdev->uac2.p_prm.rbuf);
 	kfree(agdev->uac2.c_prm.rbuf);
-	usb_free_descriptors(fn->hs_descriptors);
-	usb_free_descriptors(fn->descriptors);
+	usb_free_all_descriptors(fn);
 	if (agdev->in_ep)
 		agdev->in_ep->driver_data = NULL;
 	if (agdev->out_ep)
@@ -1042,8 +1041,6 @@ static void
 afunc_unbind(struct usb_configuration *cfg, struct usb_function *fn)
 {
 	struct audio_dev *agdev = func_to_agdev(fn);
-	struct usb_composite_dev *cdev = cfg->cdev;
-	struct usb_gadget *gadget = cdev->gadget;
 	struct uac2_rtd_params *prm;
 
 	alsa_uac2_exit(agdev);
@@ -1053,10 +1050,7 @@ afunc_unbind(struct usb_configuration *cfg, struct usb_function *fn)
 
 	prm = &agdev->uac2.c_prm;
 	kfree(prm->rbuf);
-
-	if (gadget_is_dualspeed(gadget))
-		usb_free_descriptors(fn->hs_descriptors);
-	usb_free_descriptors(fn->descriptors);
+	usb_free_all_descriptors(fn);
 
 	if (agdev->in_ep)
 		agdev->in_ep->driver_data = NULL;
diff --git a/drivers/usb/gadget/f_uvc.c b/drivers/usb/gadget/f_uvc.c
index 10f13c1213c7..28ff2546a5b3 100644
--- a/drivers/usb/gadget/f_uvc.c
+++ b/drivers/usb/gadget/f_uvc.c
@@ -583,9 +583,7 @@ uvc_function_unbind(struct usb_configuration *c, struct usb_function *f)
 	usb_ep_free_request(cdev->gadget->ep0, uvc->control_req);
 	kfree(uvc->control_buf);
 
-	kfree(f->descriptors);
-	kfree(f->hs_descriptors);
-	kfree(f->ss_descriptors);
+	usb_free_all_descriptors(f);
 
 	kfree(uvc);
 }
@@ -651,49 +649,40 @@ uvc_function_bind(struct usb_configuration *c, struct usb_function *f)
 	/* sanity check the streaming endpoint module parameters */
 	if (streaming_maxpacket > 1024)
 		streaming_maxpacket = 1024;
+	/*
+	 * Fill in the HS descriptors from the module parameters for the Video
+	 * Streaming endpoint.
+	 * NOTE: We assume that the user knows what they are doing and won't
+	 * give parameters that their UDC doesn't support.
+	 */
+	uvc_hs_streaming_ep.wMaxPacketSize = streaming_maxpacket;
+	uvc_hs_streaming_ep.wMaxPacketSize |= streaming_mult << 11;
+	uvc_hs_streaming_ep.bInterval = streaming_interval;
+	uvc_hs_streaming_ep.bEndpointAddress =
+		uvc_fs_streaming_ep.bEndpointAddress;
 
-	/* Copy descriptors for FS. */
-	f->descriptors = uvc_copy_descriptors(uvc, USB_SPEED_FULL);
-
-	/* support high speed hardware */
-	if (gadget_is_dualspeed(cdev->gadget)) {
-		/*
-		 * Fill in the HS descriptors from the module parameters for the
-		 * Video Streaming endpoint.
-		 * NOTE: We assume that the user knows what they are doing and
-		 * won't give parameters that their UDC doesn't support.
-		 */
-		uvc_hs_streaming_ep.wMaxPacketSize = streaming_maxpacket;
-		uvc_hs_streaming_ep.wMaxPacketSize |= streaming_mult << 11;
-		uvc_hs_streaming_ep.bInterval = streaming_interval;
-		uvc_hs_streaming_ep.bEndpointAddress =
-				uvc_fs_streaming_ep.bEndpointAddress;
-
-		/* Copy descriptors. */
-		f->hs_descriptors = uvc_copy_descriptors(uvc, USB_SPEED_HIGH);
-	}
+	/*
+	 * Fill in the SS descriptors from the module parameters for the Video
+	 * Streaming endpoint.
+	 * NOTE: We assume that the user knows what they are doing and won't
+	 * give parameters that their UDC doesn't support.
+	 */
+	uvc_ss_streaming_ep.wMaxPacketSize = streaming_maxpacket;
+	uvc_ss_streaming_ep.bInterval = streaming_interval;
+	uvc_ss_streaming_comp.bmAttributes = streaming_mult;
+	uvc_ss_streaming_comp.bMaxBurst = streaming_maxburst;
+	uvc_ss_streaming_comp.wBytesPerInterval =
+		streaming_maxpacket * (streaming_mult + 1) *
+		(streaming_maxburst + 1);
+	uvc_ss_streaming_ep.bEndpointAddress =
+		uvc_fs_streaming_ep.bEndpointAddress;
 
-	/* support super speed hardware */
-	if (gadget_is_superspeed(c->cdev->gadget)) {
-		/*
-		 * Fill in the SS descriptors from the module parameters for the
-		 * Video Streaming endpoint.
-		 * NOTE: We assume that the user knows what they are doing and
-		 * won't give parameters that their UDC doesn't support.
-		 */
-		uvc_ss_streaming_ep.wMaxPacketSize = streaming_maxpacket;
-		uvc_ss_streaming_ep.bInterval = streaming_interval;
-		uvc_ss_streaming_comp.bmAttributes = streaming_mult;
-		uvc_ss_streaming_comp.bMaxBurst = streaming_maxburst;
-		uvc_ss_streaming_comp.wBytesPerInterval =
-			streaming_maxpacket * (streaming_mult + 1) *
-			(streaming_maxburst + 1);
-		uvc_ss_streaming_ep.bEndpointAddress =
-				uvc_fs_streaming_ep.bEndpointAddress;
-
-		/* Copy descriptors. */
+	/* Copy descriptors */
+	f->fs_descriptors = uvc_copy_descriptors(uvc, USB_SPEED_FULL);
+	if (gadget_is_dualspeed(cdev->gadget))
+		f->hs_descriptors = uvc_copy_descriptors(uvc, USB_SPEED_HIGH);
+	if (gadget_is_superspeed(c->cdev->gadget))
 		f->ss_descriptors = uvc_copy_descriptors(uvc, USB_SPEED_SUPER);
-	}
 
 	/* Preallocate control endpoint request. */
 	uvc->control_req = usb_ep_alloc_request(cdev->gadget->ep0, GFP_KERNEL);
@@ -741,9 +730,7 @@ error:
 		kfree(uvc->control_buf);
 	}
 
-	kfree(f->descriptors);
-	kfree(f->hs_descriptors);
-	kfree(f->ss_descriptors);
+	usb_free_all_descriptors(f);
 	return ret;
 }
 
diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c
index e156e3f26727..35bcc83d1e04 100644
--- a/drivers/usb/gadget/printer.c
+++ b/drivers/usb/gadget/printer.c
@@ -983,8 +983,10 @@ static int __init printer_func_bind(struct usb_configuration *c,
 {
 	struct printer_dev *dev = container_of(f, struct printer_dev, function);
 	struct usb_composite_dev *cdev = c->cdev;
-	struct usb_ep		*in_ep, *out_ep;
+	struct usb_ep *in_ep;
+	struct usb_ep *out_ep = NULL;
 	int id;
+	int ret;
 
 	id = usb_interface_id(c, f);
 	if (id < 0)
@@ -1010,6 +1012,11 @@ autoconf_fail:
 	hs_ep_in_desc.bEndpointAddress = fs_ep_in_desc.bEndpointAddress;
 	hs_ep_out_desc.bEndpointAddress = fs_ep_out_desc.bEndpointAddress;
 
+	ret = usb_assign_descriptors(f, fs_printer_function,
+			hs_printer_function, NULL);
+	if (ret)
+		return ret;
+
 	dev->in_ep = in_ep;
 	dev->out_ep = out_ep;
 	return 0;
@@ -1018,6 +1025,7 @@ autoconf_fail:
 static void printer_func_unbind(struct usb_configuration *c,
 		struct usb_function *f)
 {
+	usb_free_all_descriptors(f);
 }
 
 static int printer_func_set_alt(struct usb_function *f,
@@ -1110,8 +1118,6 @@ static int __init printer_bind_config(struct usb_configuration *c)
 	dev = &usb_printer_gadget;
 
 	dev->function.name = shortname;
-	dev->function.descriptors = fs_printer_function;
-	dev->function.hs_descriptors = hs_printer_function;
 	dev->function.bind = printer_func_bind;
 	dev->function.setup = printer_func_setup;
 	dev->function.unbind = printer_func_unbind;
diff --git a/drivers/usb/gadget/tcm_usb_gadget.c b/drivers/usb/gadget/tcm_usb_gadget.c
index 49596096b435..27a2337f9868 100644
--- a/drivers/usb/gadget/tcm_usb_gadget.c
+++ b/drivers/usb/gadget/tcm_usb_gadget.c
@@ -2240,6 +2240,7 @@ static int usbg_bind(struct usb_configuration *c, struct usb_function *f)
 	struct usb_gadget	*gadget = c->cdev->gadget;
 	struct usb_ep		*ep;
 	int			iface;
+	int			ret;
 
 	iface = usb_interface_id(c, f);
 	if (iface < 0)
@@ -2290,6 +2291,11 @@ static int usbg_bind(struct usb_configuration *c, struct usb_function *f)
 		uasp_ss_status_desc.bEndpointAddress;
 	uasp_fs_cmd_desc.bEndpointAddress = uasp_ss_cmd_desc.bEndpointAddress;
 
+	ret = usb_assign_descriptors(f, uasp_fs_function_desc,
+			uasp_hs_function_desc, uasp_ss_function_desc);
+	if (ret)
+		goto ep_fail;
+
 	return 0;
 ep_fail:
 	pr_err("Can't claim all required eps\n");
@@ -2305,6 +2311,7 @@ static void usbg_unbind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct f_uas *fu = to_f_uas(f);
 
+	usb_free_all_descriptors(f);
 	kfree(fu);
 }
 
@@ -2385,9 +2392,6 @@ static int usbg_cfg_bind(struct usb_configuration *c)
 	if (!fu)
 		return -ENOMEM;
 	fu->function.name = "Target Function";
-	fu->function.descriptors = uasp_fs_function_desc;
-	fu->function.hs_descriptors = uasp_hs_function_desc;
-	fu->function.ss_descriptors = uasp_ss_function_desc;
 	fu->function.bind = usbg_bind;
 	fu->function.unbind = usbg_unbind;
 	fu->function.set_alt = usbg_set_alt;
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 8634a127bdd3..b09c37e04a91 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -119,7 +119,7 @@ struct usb_configuration;
 struct usb_function {
 	const char			*name;
 	struct usb_gadget_strings	**strings;
-	struct usb_descriptor_header	**descriptors;
+	struct usb_descriptor_header	**fs_descriptors;
 	struct usb_descriptor_header	**hs_descriptors;
 	struct usb_descriptor_header	**ss_descriptors;
 
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 5b6e50888248..0af6569b8cc6 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -939,6 +939,13 @@ static inline void usb_free_descriptors(struct usb_descriptor_header **v)
 	kfree(v);
 }
 
+struct usb_function;
+int usb_assign_descriptors(struct usb_function *f,
+		struct usb_descriptor_header **fs,
+		struct usb_descriptor_header **hs,
+		struct usb_descriptor_header **ss);
+void usb_free_all_descriptors(struct usb_function *f);
+
 /*-------------------------------------------------------------------------*/
 
 /* utility to simplify map/unmap of usb_requests to/from DMA */
-- 
cgit v1.2.3-55-g7522


From e5a55a898720096f43bc24938f8875c0a1b34cd7 Mon Sep 17 00:00:00 2001
From: John Fastabend
Date: Wed, 24 Oct 2012 08:12:57 +0000
Subject: net: create generic bridge ops

The PF_BRIDGE:RTM_{GET|SET}LINK nlmsg family and type are
currently embedded in the ./net/bridge module. This prohibits
them from being used by other bridging devices. One example
of this being hardware that has embedded bridging components.

In order to use these nlmsg types more generically this patch
adds two net_device_ops hooks. One to set link bridge attributes
and another to dump the current bride attributes.

	ndo_bridge_setlink()
	ndo_bridge_getlink()

CC: Lennert Buytenhek <buytenh@wantstofly.org>
CC: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 10 ++++++
 net/bridge/br_device.c    |  2 ++
 net/bridge/br_netlink.c   | 73 ++++++++----------------------------------
 net/bridge/br_private.h   |  3 ++
 net/core/rtnetlink.c      | 80 +++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 108 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f8eda0276f03..7bf867c97043 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -887,6 +887,10 @@ struct netdev_fcoe_hbainfo {
  *		       struct net_device *dev, int idx)
  *	Used to add FDB entries to dump requests. Implementers should add
  *	entries to skb and update idx with the number of entries.
+ *
+ * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh)
+ * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq,
+ *			     struct net_device *dev)
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -998,6 +1002,12 @@ struct net_device_ops {
 						struct netlink_callback *cb,
 						struct net_device *dev,
 						int idx);
+
+	int			(*ndo_bridge_setlink)(struct net_device *dev,
+						      struct nlmsghdr *nlh);
+	int			(*ndo_bridge_getlink)(struct sk_buff *skb,
+						      u32 pid, u32 seq,
+						      struct net_device *dev);
 };
 
 /*
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 070e8a68cfc6..63b5b088e80f 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -313,6 +313,8 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_fdb_add		 = br_fdb_add,
 	.ndo_fdb_del		 = br_fdb_delete,
 	.ndo_fdb_dump		 = br_fdb_dump,
+	.ndo_bridge_getlink	 = br_getlink,
+	.ndo_bridge_setlink	 = br_setlink,
 };
 
 static void br_dev_free(struct net_device *dev)
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 093f527276a3..743511bb7319 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -111,54 +111,33 @@ errout:
 /*
  * Dump information about all ports, in response to GETLINK
  */
-static int br_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
+int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+	       struct net_device *dev)
 {
-	struct net *net = sock_net(skb->sk);
-	struct net_device *dev;
-	int idx;
-
-	idx = 0;
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		struct net_bridge_port *port = br_port_get_rcu(dev);
-
-		/* not a bridge port */
-		if (!port || idx < cb->args[0])
-			goto skip;
-
-		if (br_fill_ifinfo(skb, port,
-				   NETLINK_CB(cb->skb).portid,
-				   cb->nlh->nlmsg_seq, RTM_NEWLINK,
-				   NLM_F_MULTI) < 0)
-			break;
-skip:
-		++idx;
-	}
-	rcu_read_unlock();
-	cb->args[0] = idx;
+	int err = 0;
+	struct net_bridge_port *port = br_port_get_rcu(dev);
+
+	/* not a bridge port */
+	if (!port)
+		goto out;
 
-	return skb->len;
+	err = br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI);
+out:
+	return err;
 }
 
 /*
  * Change state of port (ie from forwarding to blocking etc)
  * Used by spanning tree in user space.
  */
-static int br_rtm_setlink(struct sk_buff *skb,  struct nlmsghdr *nlh, void *arg)
+int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
 {
-	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
 	struct nlattr *protinfo;
-	struct net_device *dev;
 	struct net_bridge_port *p;
 	u8 new_state;
 
-	if (nlmsg_len(nlh) < sizeof(*ifm))
-		return -EINVAL;
-
 	ifm = nlmsg_data(nlh);
-	if (ifm->ifi_family != AF_BRIDGE)
-		return -EPFNOSUPPORT;
 
 	protinfo = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_PROTINFO);
 	if (!protinfo || nla_len(protinfo) < sizeof(u8))
@@ -168,10 +147,6 @@ static int br_rtm_setlink(struct sk_buff *skb,  struct nlmsghdr *nlh, void *arg)
 	if (new_state > BR_STATE_BLOCKING)
 		return -EINVAL;
 
-	dev = __dev_get_by_index(net, ifm->ifi_index);
-	if (!dev)
-		return -ENODEV;
-
 	p = br_port_get_rtnl(dev);
 	if (!p)
 		return -EINVAL;
@@ -218,29 +193,7 @@ struct rtnl_link_ops br_link_ops __read_mostly = {
 
 int __init br_netlink_init(void)
 {
-	int err;
-
-	err = rtnl_link_register(&br_link_ops);
-	if (err < 0)
-		goto err1;
-
-	err = __rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL,
-			      br_dump_ifinfo, NULL);
-	if (err)
-		goto err2;
-	err = __rtnl_register(PF_BRIDGE, RTM_SETLINK,
-			      br_rtm_setlink, NULL, NULL);
-	if (err)
-		goto err3;
-
-	return 0;
-
-err3:
-	rtnl_unregister_all(PF_BRIDGE);
-err2:
-	rtnl_link_unregister(&br_link_ops);
-err1:
-	return err;
+	return rtnl_link_register(&br_link_ops);
 }
 
 void __exit br_netlink_fini(void)
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 9b278c4ebee1..fdcd5f626ca6 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -553,6 +553,9 @@ extern struct rtnl_link_ops br_link_ops;
 extern int br_netlink_init(void);
 extern void br_netlink_fini(void);
 extern void br_ifinfo_notify(int event, struct net_bridge_port *port);
+extern int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg);
+extern int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+		      struct net_device *dev);
 
 #ifdef CONFIG_SYSFS
 /* br_sysfs_if.c */
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 64fe3cca2a4e..a068666b322f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2252,6 +2252,83 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+	int idx = 0;
+	u32 portid = NETLINK_CB(cb->skb).portid;
+	u32 seq = cb->nlh->nlmsg_seq;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		const struct net_device_ops *ops = dev->netdev_ops;
+		struct net_device *master = dev->master;
+
+		if (idx < cb->args[0])
+			continue;
+
+		if (master && master->netdev_ops->ndo_bridge_getlink) {
+			const struct net_device_ops *bops = master->netdev_ops;
+			int err = bops->ndo_bridge_getlink(skb, portid,
+							   seq, dev);
+
+			if (err < 0)
+				break;
+			else
+				idx++;
+		}
+
+		if (ops->ndo_bridge_getlink) {
+			int err = ops->ndo_bridge_getlink(skb, portid,
+							  seq, dev);
+
+			if (err < 0)
+				break;
+			else
+				idx++;
+		}
+	}
+	rcu_read_unlock();
+	cb->args[0] = idx;
+
+	return skb->len;
+}
+
+static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       void *arg)
+{
+	struct net *net = sock_net(skb->sk);
+	struct ifinfomsg *ifm;
+	struct net_device *dev;
+	int err = -EINVAL;
+
+	if (nlmsg_len(nlh) < sizeof(*ifm))
+		return -EINVAL;
+
+	ifm = nlmsg_data(nlh);
+	if (ifm->ifi_family != AF_BRIDGE)
+		return -EPFNOSUPPORT;
+
+	dev = __dev_get_by_index(net, ifm->ifi_index);
+	if (!dev) {
+		pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
+		return -ENODEV;
+	}
+
+	if (dev->master && dev->master->netdev_ops->ndo_bridge_setlink) {
+		err = dev->master->netdev_ops->ndo_bridge_setlink(dev, nlh);
+		if (err)
+			goto out;
+	}
+
+	if (dev->netdev_ops->ndo_bridge_setlink)
+		err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh);
+
+out:
+	return err;
+}
+
 /* Protected by RTNL sempahore.  */
 static struct rtattr **rta_buf;
 static int rtattr_max;
@@ -2433,5 +2510,8 @@ void __init rtnetlink_init(void)
 	rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL);
 	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL);
 	rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL);
+
+	rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, NULL);
+	rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL);
 }
 
-- 
cgit v1.2.3-55-g7522


From 2469ffd723f76ac2d3ce3d4f31ee31ee0a06cd38 Mon Sep 17 00:00:00 2001
From: John Fastabend
Date: Wed, 24 Oct 2012 08:13:03 +0000
Subject: net: set and query VEB/VEPA bridge mode via PF_BRIDGE

Hardware switches may support enabling and disabling the
loopback switch which puts the device in a VEPA mode defined
in the IEEE 802.1Qbg specification. In this mode frames are
not switched in the hardware but sent directly to the switch.
SR-IOV capable NICs will likely support this mode I am
aware of at least two such devices. Also I am told (but don't
have any of this hardware available) that there are devices
that only support VEPA modes. In these cases it is important
at a minimum to be able to query these attributes.

This patch adds an additional IFLA_BRIDGE_MODE attribute that can be
set and dumped via the PF_BRIDGE:{SET|GET}LINK operations. Also
anticipating bridge attributes that may be common for both embedded
bridges and software bridges this adds a flags attribute
IFLA_BRIDGE_FLAGS currently used to determine if the command or event
is being generated to/from an embedded bridge or software bridge.
Finally, the event generation is pulled out of the bridge module and
into rtnetlink proper.

For example using the macvlan driver in VEPA mode on top of
an embedded switch requires putting the embedded switch into
a VEPA mode to get the expected results.

	--------  --------
        | VEPA |  | VEPA |       <-- macvlan vepa edge relays
        --------  --------
           |        |
           |        |
        ------------------
        |      VEPA      |       <-- embedded switch in NIC
        ------------------
                |
                |
        -------------------
        | external switch |      <-- shiny new physical
	-------------------          switch with VEPA support

A packet sent from the macvlan VEPA at the top could be
loopbacked on the embedded switch and never seen by the
external switch. So in order for this to work the embedded
switch needs to be set in the VEPA state via the above
described commands.

By making these attributes nested in IFLA_AF_SPEC we allow
future extensions to be made as needed.

CC: Lennert Buytenhek <buytenh@wantstofly.org>
CC: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h | 18 +++++++++
 net/bridge/br_netlink.c        |  2 -
 net/bridge/br_private.h        |  4 +-
 net/core/rtnetlink.c           | 85 ++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 102 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index a8fe9549ddbc..b3885791e11e 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -97,5 +97,23 @@ struct __fdb_entry {
 	__u16 unused;
 };
 
+/* Bridge Flags */
+#define BRIDGE_FLAGS_MASTER	1	/* Bridge command to/from master */
+#define BRIDGE_FLAGS_SELF	2	/* Bridge command to/from lowerdev */
 
+#define BRIDGE_MODE_VEB		0	/* Default loopback mode */
+#define BRIDGE_MODE_VEPA	1	/* 802.1Qbg defined VEPA mode */
+
+/* Bridge management nested attributes
+ * [IFLA_AF_SPEC] = {
+ *     [IFLA_BRIDGE_FLAGS]
+ *     [IFLA_BRIDGE_MODE]
+ * }
+ */
+enum {
+	IFLA_BRIDGE_FLAGS,
+	IFLA_BRIDGE_MODE,
+	__IFLA_BRIDGE_MAX,
+};
+#define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1)
 #endif /* _UAPI_LINUX_IF_BRIDGE_H */
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 743511bb7319..14b065cbd214 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -166,8 +166,6 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
 	br_port_state_selection(p->br);
 	spin_unlock_bh(&p->br->lock);
 
-	br_ifinfo_notify(RTM_NEWLINK, p);
-
 	return 0;
 }
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index fdcd5f626ca6..6f40c14a2a65 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -158,7 +158,9 @@ struct net_bridge_port
 
 static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev)
 {
-	struct net_bridge_port *port = rcu_dereference(dev->rx_handler_data);
+	struct net_bridge_port *port =
+			rcu_dereference_rtnl(dev->rx_handler_data);
+
 	return br_port_exists(dev) ? port : NULL;
 }
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a068666b322f..8d2af0f77d36 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2295,13 +2295,60 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+static inline size_t bridge_nlmsg_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct ifinfomsg))
+		+ nla_total_size(IFNAMSIZ)	/* IFLA_IFNAME */
+		+ nla_total_size(MAX_ADDR_LEN)	/* IFLA_ADDRESS */
+		+ nla_total_size(sizeof(u32))	/* IFLA_MASTER */
+		+ nla_total_size(sizeof(u32))	/* IFLA_MTU */
+		+ nla_total_size(sizeof(u32))	/* IFLA_LINK */
+		+ nla_total_size(sizeof(u32))	/* IFLA_OPERSTATE */
+		+ nla_total_size(sizeof(u8))	/* IFLA_PROTINFO */
+		+ nla_total_size(sizeof(struct nlattr))	/* IFLA_AF_SPEC */
+		+ nla_total_size(sizeof(u16))	/* IFLA_BRIDGE_FLAGS */
+		+ nla_total_size(sizeof(u16));	/* IFLA_BRIDGE_MODE */
+}
+
+static int rtnl_bridge_notify(struct net_device *dev, u16 flags)
+{
+	struct net *net = dev_net(dev);
+	struct net_device *master = dev->master;
+	struct sk_buff *skb;
+	int err = -EOPNOTSUPP;
+
+	skb = nlmsg_new(bridge_nlmsg_size(), GFP_ATOMIC);
+	if (!skb) {
+		err = -ENOMEM;
+		goto errout;
+	}
+
+	if (!flags && master && master->netdev_ops->ndo_bridge_getlink)
+		err = master->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev);
+	else if (dev->netdev_ops->ndo_bridge_getlink)
+		err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev);
+
+	if (err < 0)
+		goto errout;
+
+	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
+	return 0;
+errout:
+	WARN_ON(err == -EMSGSIZE);
+	kfree_skb(skb);
+	rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	return err;
+}
+
 static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			       void *arg)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
 	struct net_device *dev;
-	int err = -EINVAL;
+	struct nlattr *br_spec, *attr = NULL;
+	int rem, err = -EOPNOTSUPP;
+	u16 flags = 0;
 
 	if (nlmsg_len(nlh) < sizeof(*ifm))
 		return -EINVAL;
@@ -2316,15 +2363,45 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -ENODEV;
 	}
 
-	if (dev->master && dev->master->netdev_ops->ndo_bridge_setlink) {
+	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (br_spec) {
+		nla_for_each_nested(attr, br_spec, rem) {
+			if (nla_type(attr) == IFLA_BRIDGE_FLAGS) {
+				flags = nla_get_u16(attr);
+				break;
+			}
+		}
+	}
+
+	if (!flags || (flags & BRIDGE_FLAGS_MASTER)) {
+		if (!dev->master ||
+		    !dev->master->netdev_ops->ndo_bridge_setlink) {
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+
 		err = dev->master->netdev_ops->ndo_bridge_setlink(dev, nlh);
 		if (err)
 			goto out;
+
+		flags &= ~BRIDGE_FLAGS_MASTER;
 	}
 
-	if (dev->netdev_ops->ndo_bridge_setlink)
-		err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh);
+	if ((flags & BRIDGE_FLAGS_SELF)) {
+		if (!dev->netdev_ops->ndo_bridge_setlink)
+			err = -EOPNOTSUPP;
+		else
+			err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh);
+
+		if (!err)
+			flags &= ~BRIDGE_FLAGS_SELF;
+	}
 
+	if (attr && nla_type(attr) == IFLA_BRIDGE_FLAGS)
+		memcpy(nla_data(attr), &flags, sizeof(flags));
+	/* Generate event to notify upper layer of bridge change */
+	if (!err)
+		err = rtnl_bridge_notify(dev, flags);
 out:
 	return err;
 }
-- 
cgit v1.2.3-55-g7522


From 815cccbf10b27115fb3e5827bef26768616e5e27 Mon Sep 17 00:00:00 2001
From: John Fastabend
Date: Wed, 24 Oct 2012 08:13:09 +0000
Subject: ixgbe: add setlink, getlink support to ixgbe and ixgbevf

This adds support for the net device ops to manage the embedded
hardware bridge on ixgbe devices. With this patch the bridge
mode can be toggled between VEB and VEPA to support stacking
macvlan devices or using the embedded switch without any SW
component in 802.1Qbg/br environments.

Additionally, this adds source address pruning to the ixgbevf
driver to prune any frames sent back from a reflective relay on
the switch. This is required because the existing hardware does
not support this. Without it frames get pushed into the stack
with its own src mac which is invalid per 802.1Qbg VEPA
definition.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c     | 59 +++++++++++++++++++++--
 drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c    |  3 ++
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 10 ++++
 include/linux/rtnetlink.h                         |  3 ++
 net/core/rtnetlink.c                              | 50 +++++++++++++++++++
 5 files changed, 122 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 88d636a7459c..9a88e01216bb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -44,6 +44,7 @@
 #include <linux/ethtool.h>
 #include <linux/if.h>
 #include <linux/if_vlan.h>
+#include <linux/if_bridge.h>
 #include <linux/prefetch.h>
 #include <scsi/fc/fc_fcoe.h>
 
@@ -3224,7 +3225,6 @@ static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter)
 	IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset ^ 1), reg_offset - 1);
 	IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), (~0) << vf_shift);
 	IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset ^ 1), reg_offset - 1);
-	IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN);
 
 	/* Map PF MAC address in RAR Entry 0 to first pool following VFs */
 	hw->mac.ops.set_vmdq(hw, 0, VMDQ_P(0));
@@ -3247,8 +3247,6 @@ static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter)
 
 	IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext);
 
-	/* enable Tx loopback for VF/PF communication */
-	IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN);
 
 	/* Enable MAC Anti-Spoofing */
 	hw->mac.ops.set_mac_anti_spoofing(hw, (adapter->num_vfs != 0),
@@ -7025,6 +7023,59 @@ static int ixgbe_ndo_fdb_dump(struct sk_buff *skb,
 	return idx;
 }
 
+static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
+				    struct nlmsghdr *nlh)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct nlattr *attr, *br_spec;
+	int rem;
+
+	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
+		return -EOPNOTSUPP;
+
+	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+
+	nla_for_each_nested(attr, br_spec, rem) {
+		__u16 mode;
+		u32 reg = 0;
+
+		if (nla_type(attr) != IFLA_BRIDGE_MODE)
+			continue;
+
+		mode = nla_get_u16(attr);
+		if (mode == BRIDGE_MODE_VEPA)
+			reg = 0;
+		else if (mode == BRIDGE_MODE_VEB)
+			reg = IXGBE_PFDTXGSWC_VT_LBEN;
+		else
+			return -EINVAL;
+
+		IXGBE_WRITE_REG(&adapter->hw, IXGBE_PFDTXGSWC, reg);
+
+		e_info(drv, "enabling bridge mode: %s\n",
+			mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB");
+	}
+
+	return 0;
+}
+
+static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+				    struct net_device *dev)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	u16 mode;
+
+	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
+		return 0;
+
+	if (IXGBE_READ_REG(&adapter->hw, IXGBE_PFDTXGSWC) & 1)
+		mode = BRIDGE_MODE_VEB;
+	else
+		mode = BRIDGE_MODE_VEPA;
+
+	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode);
+}
+
 static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_open		= ixgbe_open,
 	.ndo_stop		= ixgbe_close,
@@ -7064,6 +7115,8 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_fdb_add		= ixgbe_ndo_fdb_add,
 	.ndo_fdb_del		= ixgbe_ndo_fdb_del,
 	.ndo_fdb_dump		= ixgbe_ndo_fdb_dump,
+	.ndo_bridge_setlink	= ixgbe_ndo_bridge_setlink,
+	.ndo_bridge_getlink	= ixgbe_ndo_bridge_getlink,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 96876b7442b1..7e3ac28ffba8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -117,6 +117,9 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter,
 		}
 	}
 
+	/* Initialize default switching mode VEB */
+	IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN);
+
 	/* If call to enable VFs succeeded then allocate memory
 	 * for per VF control structures.
 	 */
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 07d7eaba6f1b..ac6a76deb01d 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -478,6 +478,16 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		}
 		skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 
+		/* Workaround hardware that can't do proper VEPA multicast
+		 * source pruning.
+		 */
+		if ((skb->pkt_type & (PACKET_BROADCAST | PACKET_MULTICAST)) &&
+		    !(compare_ether_addr(adapter->netdev->dev_addr,
+					eth_hdr(skb)->h_source))) {
+			dev_kfree_skb_irq(skb);
+			goto next_desc;
+		}
+
 		ixgbevf_receive_skb(q_vector, skb, staterr, rx_desc);
 
 next_desc:
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 7002bbfd5d4a..489dd7bb28ec 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -69,4 +69,7 @@ extern int ndo_dflt_fdb_dump(struct sk_buff *skb,
 			     struct netlink_callback *cb,
 			     struct net_device *dev,
 			     int idx);
+
+extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+				   struct net_device *dev, u16 mode);
 #endif	/* __LINUX_RTNETLINK_H */
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 8d2af0f77d36..51dc58ff0091 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2252,6 +2252,56 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+			    struct net_device *dev, u16 mode)
+{
+	struct nlmsghdr *nlh;
+	struct ifinfomsg *ifm;
+	struct nlattr *br_afspec;
+	u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
+
+	nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	ifm = nlmsg_data(nlh);
+	ifm->ifi_family = AF_BRIDGE;
+	ifm->__ifi_pad = 0;
+	ifm->ifi_type = dev->type;
+	ifm->ifi_index = dev->ifindex;
+	ifm->ifi_flags = dev_get_flags(dev);
+	ifm->ifi_change = 0;
+
+
+	if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
+	    nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
+	    nla_put_u8(skb, IFLA_OPERSTATE, operstate) ||
+	    (dev->master &&
+	     nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) ||
+	    (dev->addr_len &&
+	     nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
+	    (dev->ifindex != dev->iflink &&
+	     nla_put_u32(skb, IFLA_LINK, dev->iflink)))
+		goto nla_put_failure;
+
+	br_afspec = nla_nest_start(skb, IFLA_AF_SPEC);
+	if (!br_afspec)
+		goto nla_put_failure;
+
+	if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF) ||
+	    nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) {
+		nla_nest_cancel(skb, br_afspec);
+		goto nla_put_failure;
+	}
+	nla_nest_end(skb, br_afspec);
+
+	return nlmsg_end(skb, nlh);
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL(ndo_dflt_bridge_getlink);
+
 static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
-- 
cgit v1.2.3-55-g7522


From ecd5cf5dc5b07bc57aedf4c92453d6c343e3d840 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn
Date: Fri, 26 Oct 2012 11:52:08 +0000
Subject: net: compute skb->rxhash if nic hash may be 3-tuple

Network device drivers can communicate a Toeplitz hash in skb->rxhash,
but devices differ in their hashing capabilities. All compute a 5-tuple
hash for TCP over IPv4, but for other connection-oriented protocols,
they may compute only a 3-tuple. This breaks RPS load balancing, e.g.,
for TCP over IPv6 flows. Additionally, for GRE and other tunnels,
the kernel computes a 5-tuple hash over the inner packet if possible,
but devices do not.

This patch recomputes the rxhash in software in all cases where it
cannot be certain that a 5-tuple was computed. Device drivers can avoid
recomputation by setting the skb->l4_rxhash flag.

Recomputing adds cycles to each packet when RPS is enabled or the
packet arrives over a tunnel. A comparison of 200x TCP_STREAM between
two servers running unmodified netnext with rxhash computation
in hardware vs software (using ethtool -K eth0 rxhash [on|off]) shows
how much time is spent in __skb_get_rxhash in this worst case:

     0.03%          swapper  [kernel.kallsyms]     [k] __skb_get_rxhash
     0.03%          swapper  [kernel.kallsyms]     [k] __skb_get_rxhash
     0.05%          swapper  [kernel.kallsyms]     [k] __skb_get_rxhash

With 200x TCP_RR it increases to

     0.10%          netperf  [kernel.kallsyms]     [k] __skb_get_rxhash
     0.10%          netperf  [kernel.kallsyms]     [k] __skb_get_rxhash
     0.10%          netperf  [kernel.kallsyms]     [k] __skb_get_rxhash

I considered having the patch explicitly skips recomputation when it knows
that it will not improve the hash (TCP over IPv4), but that conditional
complicates code without saving many cycles in practice, because it has
to take place after flow dissector.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6a2c34e6d962..a2a0bdb95a8f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -643,7 +643,7 @@ extern unsigned int   skb_find_text(struct sk_buff *skb, unsigned int from,
 extern void __skb_get_rxhash(struct sk_buff *skb);
 static inline __u32 skb_get_rxhash(struct sk_buff *skb)
 {
-	if (!skb->rxhash)
+	if (!skb->l4_rxhash)
 		__skb_get_rxhash(skb);
 
 	return skb->rxhash;
-- 
cgit v1.2.3-55-g7522


From f3335031b9452baebfe49b8b5e55d3fe0c4677d1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Sat, 27 Oct 2012 02:26:17 +0000
Subject: net: filter: add vlan tag access

BPF filters lack ability to access skb->vlan_tci

This patch adds two new ancillary accessors :

SKF_AD_VLAN_TAG         (44) mapped to vlan_tx_tag_get(skb)

SKF_AD_VLAN_TAG_PRESENT (48) mapped to vlan_tx_tag_present(skb)

This allows libpcap/tcpdump to use a kernel filter instead of
having to fallback to accept all packets, then filter them in
user space.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Ani Sinha <ani@aristanetworks.com>
Suggested-by: Daniel Borkmann <danborkmann@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/filter.h      | 2 ++
 include/uapi/linux/filter.h | 4 +++-
 net/core/filter.c           | 9 +++++++++
 3 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 24d251f3bab0..c9f0005c35e2 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -123,6 +123,8 @@ enum {
 	BPF_S_ANC_CPU,
 	BPF_S_ANC_ALU_XOR_X,
 	BPF_S_ANC_SECCOMP_LD_W,
+	BPF_S_ANC_VLAN_TAG,
+	BPF_S_ANC_VLAN_TAG_PRESENT,
 };
 
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h
index 3d7922433aba..9cfde6941099 100644
--- a/include/uapi/linux/filter.h
+++ b/include/uapi/linux/filter.h
@@ -127,7 +127,9 @@ struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
 #define SKF_AD_RXHASH	32
 #define SKF_AD_CPU	36
 #define SKF_AD_ALU_XOR_X	40
-#define SKF_AD_MAX	44
+#define SKF_AD_VLAN_TAG	44
+#define SKF_AD_VLAN_TAG_PRESENT 48
+#define SKF_AD_MAX	52
 #define SKF_NET_OFF   (-0x100000)
 #define SKF_LL_OFF    (-0x200000)
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 3d92ebb7fbcf..5a114d41bf11 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -39,6 +39,7 @@
 #include <linux/reciprocal_div.h>
 #include <linux/ratelimit.h>
 #include <linux/seccomp.h>
+#include <linux/if_vlan.h>
 
 /* No hurry in this branch
  *
@@ -341,6 +342,12 @@ load_b:
 		case BPF_S_ANC_CPU:
 			A = raw_smp_processor_id();
 			continue;
+		case BPF_S_ANC_VLAN_TAG:
+			A = vlan_tx_tag_get(skb);
+			continue;
+		case BPF_S_ANC_VLAN_TAG_PRESENT:
+			A = !!vlan_tx_tag_present(skb);
+			continue;
 		case BPF_S_ANC_NLATTR: {
 			struct nlattr *nla;
 
@@ -600,6 +607,8 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
 			ANCILLARY(RXHASH);
 			ANCILLARY(CPU);
 			ANCILLARY(ALU_XOR_X);
+			ANCILLARY(VLAN_TAG);
+			ANCILLARY(VLAN_TAG_PRESENT);
 			}
 		}
 		ftest->code = code;
-- 
cgit v1.2.3-55-g7522


From c73cee717e7d5da0698acb720ad1219646fe4f46 Mon Sep 17 00:00:00 2001
From: Alan Stern
Date: Wed, 31 Oct 2012 13:21:06 -0400
Subject: USB: EHCI: remove ehci_port_power() routine

This patch (as1623) removes the ehci_port_power() routine and all the
places that call it.  There's no reason for ehci-hcd to change the
port power settings; the hub driver takes care of all that stuff.

There is one exception: When the controller is resumed from
hibernation or following a loss of power, the ports that are supposed
to be handed over to a companion controller must be powered on first.
Otherwise the handover won't work.  This process is not visible to the
hub driver, so it has to be handled in ehci-hcd.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm/mach-cns3xxx/cns3420vb.c     |  1 -
 arch/mips/ath79/dev-usb.c             |  2 --
 arch/mips/loongson1/common/platform.c |  1 -
 drivers/usb/chipidea/host.c           | 18 +-----------------
 drivers/usb/host/ehci-atmel.c         |  9 +--------
 drivers/usb/host/ehci-fsl.c           |  1 -
 drivers/usb/host/ehci-grlib.c         | 18 +-----------------
 drivers/usb/host/ehci-hcd.c           | 21 ---------------------
 drivers/usb/host/ehci-hub.c           | 13 +++++++++++++
 drivers/usb/host/ehci-msm.c           |  1 -
 drivers/usb/host/ehci-mxc.c           |  8 +-------
 drivers/usb/host/ehci-octeon.c        |  3 ---
 drivers/usb/host/ehci-omap.c          |  3 ---
 drivers/usb/host/ehci-orion.c         | 16 +---------------
 drivers/usb/host/ehci-pci.c           |  1 -
 drivers/usb/host/ehci-platform.c      |  5 -----
 drivers/usb/host/ehci-pmcmsp.c        |  1 -
 drivers/usb/host/ehci-sh.c            |  9 +--------
 drivers/usb/host/ehci-spear.c         |  9 +--------
 drivers/usb/host/ehci-tegra.c         |  8 +-------
 include/linux/usb/ehci_pdriver.h      |  2 --
 21 files changed, 21 insertions(+), 129 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-cns3xxx/cns3420vb.c b/arch/arm/mach-cns3xxx/cns3420vb.c
index 8a00cee82228..ae305397003c 100644
--- a/arch/arm/mach-cns3xxx/cns3420vb.c
+++ b/arch/arm/mach-cns3xxx/cns3420vb.c
@@ -162,7 +162,6 @@ static void csn3xxx_usb_power_off(struct platform_device *pdev)
 }
 
 static struct usb_ehci_pdata cns3xxx_usb_ehci_pdata = {
-	.port_power_off	= 1,
 	.power_on	= csn3xxx_usb_power_on,
 	.power_off	= csn3xxx_usb_power_off,
 };
diff --git a/arch/mips/ath79/dev-usb.c b/arch/mips/ath79/dev-usb.c
index 072bb9be2304..bd2bc108e1b5 100644
--- a/arch/mips/ath79/dev-usb.c
+++ b/arch/mips/ath79/dev-usb.c
@@ -50,13 +50,11 @@ static u64 ath79_ehci_dmamask = DMA_BIT_MASK(32);
 
 static struct usb_ehci_pdata ath79_ehci_pdata_v1 = {
 	.has_synopsys_hc_bug	= 1,
-	.port_power_off		= 1,
 };
 
 static struct usb_ehci_pdata ath79_ehci_pdata_v2 = {
 	.caps_offset		= 0x100,
 	.has_tt			= 1,
-	.port_power_off		= 1,
 };
 
 static struct platform_device ath79_ehci_device = {
diff --git a/arch/mips/loongson1/common/platform.c b/arch/mips/loongson1/common/platform.c
index 2874bf224418..0412ad61e290 100644
--- a/arch/mips/loongson1/common/platform.c
+++ b/arch/mips/loongson1/common/platform.c
@@ -109,7 +109,6 @@ static struct resource ls1x_ehci_resources[] = {
 };
 
 static struct usb_ehci_pdata ls1x_ehci_pdata = {
-	.port_power_off	= 1,
 };
 
 struct platform_device ls1x_ehci_device = {
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index ebff9f4f56ec..ebc041ff9cd5 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -31,22 +31,6 @@
 #include "bits.h"
 #include "host.h"
 
-static int ci_ehci_setup(struct usb_hcd *hcd)
-{
-	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
-	int ret;
-
-	hcd->has_tt = 1;
-
-	ret = ehci_setup(hcd);
-	if (ret)
-		return ret;
-
-	ehci_port_power(ehci, 0);
-
-	return ret;
-}
-
 static const struct hc_driver ci_ehci_hc_driver = {
 	.description	= "ehci_hcd",
 	.product_desc	= "ChipIdea HDRC EHCI",
@@ -61,7 +45,7 @@ static const struct hc_driver ci_ehci_hc_driver = {
 	/*
 	 * basic lifecycle operations
 	 */
-	.reset		= ci_ehci_setup,
+	.reset		= ehci_setup,
 	.start		= ehci_run,
 	.stop		= ehci_stop,
 	.shutdown	= ehci_shutdown,
diff --git a/drivers/usb/host/ehci-atmel.c b/drivers/usb/host/ehci-atmel.c
index 411bb74152eb..d23321ec0e46 100644
--- a/drivers/usb/host/ehci-atmel.c
+++ b/drivers/usb/host/ehci-atmel.c
@@ -53,18 +53,11 @@ static void atmel_stop_ehci(struct platform_device *pdev)
 static int ehci_atmel_setup(struct usb_hcd *hcd)
 {
 	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
-	int retval;
 
 	/* registers start at offset 0x0 */
 	ehci->caps = hcd->regs;
 
-	retval = ehci_setup(hcd);
-	if (retval)
-		return retval;
-
-	ehci_port_power(ehci, 0);
-
-	return retval;
+	return ehci_setup(hcd);
 }
 
 static const struct hc_driver ehci_atmel_hc_driver = {
diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
index 0d2f35ca93f1..fd9b5424b860 100644
--- a/drivers/usb/host/ehci-fsl.c
+++ b/drivers/usb/host/ehci-fsl.c
@@ -349,7 +349,6 @@ static int ehci_fsl_reinit(struct ehci_hcd *ehci)
 {
 	if (ehci_fsl_usb_setup(ehci))
 		return -EINVAL;
-	ehci_port_power(ehci, 0);
 
 	return 0;
 }
diff --git a/drivers/usb/host/ehci-grlib.c b/drivers/usb/host/ehci-grlib.c
index 3180cb3624d9..da4269550fba 100644
--- a/drivers/usb/host/ehci-grlib.c
+++ b/drivers/usb/host/ehci-grlib.c
@@ -34,22 +34,6 @@
 
 #define GRUSBHC_HCIVERSION 0x0100 /* Known value of cap. reg. HCIVERSION */
 
-/* called during probe() after chip reset completes */
-static int ehci_grlib_setup(struct usb_hcd *hcd)
-{
-	struct ehci_hcd	*ehci = hcd_to_ehci(hcd);
-	int		retval;
-
-	retval = ehci_setup(hcd);
-	if (retval)
-		return retval;
-
-	ehci_port_power(ehci, 1);
-
-	return retval;
-}
-
-
 static const struct hc_driver ehci_grlib_hc_driver = {
 	.description		= hcd_name,
 	.product_desc		= "GRLIB GRUSBHC EHCI",
@@ -64,7 +48,7 @@ static const struct hc_driver ehci_grlib_hc_driver = {
 	/*
 	 * basic lifecycle operations
 	 */
-	.reset			= ehci_grlib_setup,
+	.reset			= ehci_setup,
 	.start			= ehci_run,
 	.stop			= ehci_stop,
 	.shutdown		= ehci_shutdown,
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 68dd1c99b1f5..ab4a769a4104 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -371,24 +371,6 @@ static void ehci_shutdown(struct usb_hcd *hcd)
 	hrtimer_cancel(&ehci->hrtimer);
 }
 
-static void ehci_port_power (struct ehci_hcd *ehci, int is_on)
-{
-	unsigned port;
-
-	if (!HCS_PPC (ehci->hcs_params))
-		return;
-
-	ehci_dbg (ehci, "...power%s ports...\n", is_on ? "up" : "down");
-	for (port = HCS_N_PORTS (ehci->hcs_params); port > 0; )
-		(void) ehci_hub_control(ehci_to_hcd(ehci),
-				is_on ? SetPortFeature : ClearPortFeature,
-				USB_PORT_FEAT_POWER,
-				port--, NULL, 0);
-	/* Flush those writes */
-	ehci_readl(ehci, &ehci->regs->command);
-	msleep(20);
-}
-
 /*-------------------------------------------------------------------------*/
 
 /*
@@ -1184,9 +1166,6 @@ static int __maybe_unused ehci_resume(struct usb_hcd *hcd, bool hibernated)
 	ehci->rh_state = EHCI_RH_SUSPENDED;
 	spin_unlock_irq(&ehci->lock);
 
-	/* here we "know" root ports should always stay powered */
-	ehci_port_power(ehci, 1);
-
 	return 1;
 }
 
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index a2c56cdd2c3a..a59c61fea09f 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -56,6 +56,19 @@ static void ehci_handover_companion_ports(struct ehci_hcd *ehci)
 	if (!ehci->owned_ports)
 		return;
 
+	/* Make sure the ports are powered */
+	port = HCS_N_PORTS(ehci->hcs_params);
+	while (port--) {
+		if (test_bit(port, &ehci->owned_ports)) {
+			reg = &ehci->regs->port_status[port];
+			status = ehci_readl(ehci, reg) & ~PORT_RWC_BITS;
+			if (!(status & PORT_POWER)) {
+				status |= PORT_POWER;
+				ehci_writel(ehci, status, reg);
+			}
+		}
+	}
+
 	/* Give the connections some time to appear */
 	msleep(20);
 
diff --git a/drivers/usb/host/ehci-msm.c b/drivers/usb/host/ehci-msm.c
index 4af4dc5b618c..7fa1ba4de789 100644
--- a/drivers/usb/host/ehci-msm.c
+++ b/drivers/usb/host/ehci-msm.c
@@ -53,7 +53,6 @@ static int ehci_msm_reset(struct usb_hcd *hcd)
 	/* Disable streaming mode and select host mode */
 	writel(0x13, USB_USBMODE);
 
-	ehci_port_power(ehci, 1);
 	return 0;
 }
 
diff --git a/drivers/usb/host/ehci-mxc.c b/drivers/usb/host/ehci-mxc.c
index 4a08fc0b27c9..a37224a4a49b 100644
--- a/drivers/usb/host/ehci-mxc.c
+++ b/drivers/usb/host/ehci-mxc.c
@@ -40,16 +40,10 @@ struct ehci_mxc_priv {
 static int ehci_mxc_setup(struct usb_hcd *hcd)
 {
 	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
-	int retval;
 
 	hcd->has_tt = 1;
 
-	retval = ehci_setup(hcd);
-	if (retval)
-		return retval;
-
-	ehci_port_power(ehci, 0);
-	return 0;
+	return ehci_setup(hcd);
 }
 
 static const struct hc_driver ehci_mxc_hc_driver = {
diff --git a/drivers/usb/host/ehci-octeon.c b/drivers/usb/host/ehci-octeon.c
index ba26957abf46..a89750fff4ff 100644
--- a/drivers/usb/host/ehci-octeon.c
+++ b/drivers/usb/host/ehci-octeon.c
@@ -159,9 +159,6 @@ static int ehci_octeon_drv_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, hcd);
 
-	/* root ports should always stay powered */
-	ehci_port_power(ehci, 1);
-
 	return 0;
 err3:
 	ehci_octeon_stop();
diff --git a/drivers/usb/host/ehci-omap.c b/drivers/usb/host/ehci-omap.c
index d7fe287d0678..44e7d0f638e8 100644
--- a/drivers/usb/host/ehci-omap.c
+++ b/drivers/usb/host/ehci-omap.c
@@ -146,9 +146,6 @@ static int omap_ehci_init(struct usb_hcd *hcd)
 			gpio_set_value_cansleep(pdata->reset_gpio_port[1], 1);
 	}
 
-	/* root ports should always stay powered */
-	ehci_port_power(ehci, 1);
-
 	return rc;
 }
 
diff --git a/drivers/usb/host/ehci-orion.c b/drivers/usb/host/ehci-orion.c
index 9c2717d66730..96da679becef 100644
--- a/drivers/usb/host/ehci-orion.c
+++ b/drivers/usb/host/ehci-orion.c
@@ -101,20 +101,6 @@ static void orion_usb_phy_v1_setup(struct usb_hcd *hcd)
 	wrl(USB_MODE, 0x13);
 }
 
-static int ehci_orion_setup(struct usb_hcd *hcd)
-{
-	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
-	int retval;
-
-	retval = ehci_setup(hcd);
-	if (retval)
-		return retval;
-
-	ehci_port_power(ehci, 0);
-
-	return retval;
-}
-
 static const struct hc_driver ehci_orion_hc_driver = {
 	.description = hcd_name,
 	.product_desc = "Marvell Orion EHCI",
@@ -129,7 +115,7 @@ static const struct hc_driver ehci_orion_hc_driver = {
 	/*
 	 * basic lifecycle operations
 	 */
-	.reset = ehci_orion_setup,
+	.reset = ehci_setup,
 	.start = ehci_run,
 	.stop = ehci_stop,
 	.shutdown = ehci_shutdown,
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index e17330ae0aee..c92dcaee0d4d 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -297,7 +297,6 @@ static int ehci_pci_setup(struct usb_hcd *hcd)
 		ehci_warn(ehci, "selective suspend/wakeup unavailable\n");
 #endif
 
-	ehci_port_power(ehci, 1);
 	retval = ehci_pci_reinit(ehci, pdev);
 done:
 	return retval;
diff --git a/drivers/usb/host/ehci-platform.c b/drivers/usb/host/ehci-platform.c
index 272728c48c9e..6e6c23bdb484 100644
--- a/drivers/usb/host/ehci-platform.c
+++ b/drivers/usb/host/ehci-platform.c
@@ -40,11 +40,6 @@ static int ehci_platform_reset(struct usb_hcd *hcd)
 
 	if (pdata->no_io_watchdog)
 		ehci->need_io_watchdog = 0;
-	if (pdata->port_power_on)
-		ehci_port_power(ehci, 1);
-	if (pdata->port_power_off)
-		ehci_port_power(ehci, 0);
-
 	return 0;
 }
 
diff --git a/drivers/usb/host/ehci-pmcmsp.c b/drivers/usb/host/ehci-pmcmsp.c
index 087aee2a904f..363890ee41d2 100644
--- a/drivers/usb/host/ehci-pmcmsp.c
+++ b/drivers/usb/host/ehci-pmcmsp.c
@@ -90,7 +90,6 @@ static int ehci_msp_setup(struct usb_hcd *hcd)
 		return retval;
 
 	usb_hcd_tdi_set_mode(ehci);
-	ehci_port_power(ehci, 0);
 
 	return retval;
 }
diff --git a/drivers/usb/host/ehci-sh.c b/drivers/usb/host/ehci-sh.c
index 6081e1ed3ac9..0c90a24fa989 100644
--- a/drivers/usb/host/ehci-sh.c
+++ b/drivers/usb/host/ehci-sh.c
@@ -21,17 +21,10 @@ struct ehci_sh_priv {
 static int ehci_sh_reset(struct usb_hcd *hcd)
 {
 	struct ehci_hcd	*ehci = hcd_to_ehci(hcd);
-	int ret;
 
 	ehci->caps = hcd->regs;
 
-	ret = ehci_setup(hcd);
-	if (unlikely(ret))
-		return ret;
-
-	ehci_port_power(ehci, 0);
-
-	return ret;
+	return ehci_setup(hcd);
 }
 
 static const struct hc_driver ehci_sh_hc_driver = {
diff --git a/drivers/usb/host/ehci-spear.c b/drivers/usb/host/ehci-spear.c
index c718a065e154..719ca48a471a 100644
--- a/drivers/usb/host/ehci-spear.c
+++ b/drivers/usb/host/ehci-spear.c
@@ -37,18 +37,11 @@ static void spear_stop_ehci(struct spear_ehci *ehci)
 static int ehci_spear_setup(struct usb_hcd *hcd)
 {
 	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
-	int retval = 0;
 
 	/* registers start at offset 0x0 */
 	ehci->caps = hcd->regs;
 
-	retval = ehci_setup(hcd);
-	if (retval)
-		return retval;
-
-	ehci_port_power(ehci, 0);
-
-	return retval;
+	return ehci_setup(hcd);
 }
 
 static const struct hc_driver ehci_spear_hc_driver = {
diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c
index 2de089001ae9..94ee3212094e 100644
--- a/drivers/usb/host/ehci-tegra.c
+++ b/drivers/usb/host/ehci-tegra.c
@@ -280,7 +280,6 @@ static void tegra_ehci_shutdown(struct usb_hcd *hcd)
 static int tegra_ehci_setup(struct usb_hcd *hcd)
 {
 	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
-	int retval;
 
 	/* EHCI registers start at offset 0x100 */
 	ehci->caps = hcd->regs + 0x100;
@@ -288,12 +287,7 @@ static int tegra_ehci_setup(struct usb_hcd *hcd)
 	/* switch to host mode */
 	hcd->has_tt = 1;
 
-	retval = ehci_setup(hcd);
-	if (retval)
-		return retval;
-
-	ehci_port_power(ehci, 1);
-	return retval;
+	return ehci_setup(hcd);
 }
 
 struct dma_aligned_buffer {
diff --git a/include/linux/usb/ehci_pdriver.h b/include/linux/usb/ehci_pdriver.h
index 67ac74bde6d0..99238b096f7e 100644
--- a/include/linux/usb/ehci_pdriver.h
+++ b/include/linux/usb/ehci_pdriver.h
@@ -41,8 +41,6 @@ struct usb_ehci_pdata {
 	unsigned	has_synopsys_hc_bug:1;
 	unsigned	big_endian_desc:1;
 	unsigned	big_endian_mmio:1;
-	unsigned	port_power_on:1;
-	unsigned	port_power_off:1;
 	unsigned	no_io_watchdog:1;
 
 	/* Turn on all power and clocks */
-- 
cgit v1.2.3-55-g7522


From 17b72feb2be14e6d37023267dc0e199e8e0e3fdc Mon Sep 17 00:00:00 2001
From: Bjørn Mork
Date: Wed, 31 Oct 2012 06:08:39 +0100
Subject: USB: add USB_DEVICE_INTERFACE_CLASS macro

Matching on device and interface class with with unspecified
subclass and protocol is sometimes useful.  This is slightly
different from USB_DEVICE_AND_INTERFACE_INFO which requires
the full interface class/subclass/protocol triplet.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/linux/usb.h b/include/linux/usb.h
index f51f9981de1e..689b14b26c8d 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -807,6 +807,22 @@ static inline int usb_make_path(struct usb_device *dev, char *buf, size_t size)
 	.bcdDevice_lo = (lo), \
 	.bcdDevice_hi = (hi)
 
+/**
+ * USB_DEVICE_INTERFACE_CLASS - describe a usb device with a specific interface class
+ * @vend: the 16 bit USB Vendor ID
+ * @prod: the 16 bit USB Product ID
+ * @cl: bInterfaceClass value
+ *
+ * This macro is used to create a struct usb_device_id that matches a
+ * specific interface class of devices.
+ */
+#define USB_DEVICE_INTERFACE_CLASS(vend, prod, cl) \
+	.match_flags = USB_DEVICE_ID_MATCH_DEVICE | \
+		       USB_DEVICE_ID_MATCH_INT_CLASS, \
+	.idVendor = (vend), \
+	.idProduct = (prod), \
+	.bInterfaceClass = (cl)
+
 /**
  * USB_DEVICE_INTERFACE_PROTOCOL - describe a usb device with a specific interface protocol
  * @vend: the 16 bit USB Vendor ID
-- 
cgit v1.2.3-55-g7522


From 884bfe89a462fcc85c8abd96171519cf2fe70929 Mon Sep 17 00:00:00 2001
From: Slava Pestov
Date: Fri, 15 Jul 2011 14:23:58 -0700
Subject: ring-buffer: Add a 'dropped events' counter

The existing 'overrun' counter is incremented when the ring
buffer wraps around, with overflow on (the default). We wanted
a way to count requests lost from the buffer filling up with
overflow off, too. I decided to add a new counter instead
of retro-fitting the existing one because it seems like a
different statistic to count conceptually, and also because
of how the code was structured.

Link: http://lkml.kernel.org/r/1310765038-26399-1-git-send-email-slavapestov@google.com

Signed-off-by: Slava Pestov <slavapestov@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  1 +
 kernel/trace/ring_buffer.c  | 41 +++++++++++++++++++++++++++++++++++------
 kernel/trace/trace.c        |  3 +++
 3 files changed, 39 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 6c8835f74f79..2007375cfe77 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -166,6 +166,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b979426d16c6..0ebeb1d76ddf 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -460,9 +460,10 @@ struct ring_buffer_per_cpu {
 	unsigned long			lost_events;
 	unsigned long			last_overrun;
 	local_t				entries_bytes;
-	local_t				commit_overrun;
-	local_t				overrun;
 	local_t				entries;
+	local_t				overrun;
+	local_t				commit_overrun;
+	local_t				dropped_events;
 	local_t				committing;
 	local_t				commits;
 	unsigned long			read;
@@ -2155,8 +2156,10 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 			 * If we are not in overwrite mode,
 			 * this is easy, just stop here.
 			 */
-			if (!(buffer->flags & RB_FL_OVERWRITE))
+			if (!(buffer->flags & RB_FL_OVERWRITE)) {
+				local_inc(&cpu_buffer->dropped_events);
 				goto out_reset;
+			}
 
 			ret = rb_handle_head_page(cpu_buffer,
 						  tail_page,
@@ -2995,7 +2998,8 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
 
 /**
- * ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer
+ * ring_buffer_overrun_cpu - get the number of overruns caused by the ring
+ * buffer wrapping around (only if RB_FL_OVERWRITE is on).
  * @buffer: The ring buffer
  * @cpu: The per CPU buffer to get the number of overruns from
  */
@@ -3015,7 +3019,9 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
 EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
 /**
- * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
+ * ring_buffer_commit_overrun_cpu - get the number of overruns caused by
+ * commits failing due to the buffer wrapping around while there are uncommitted
+ * events, such as during an interrupt storm.
  * @buffer: The ring buffer
  * @cpu: The per CPU buffer to get the number of overruns from
  */
@@ -3035,6 +3041,28 @@ ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu);
 
+/**
+ * ring_buffer_dropped_events_cpu - get the number of dropped events caused by
+ * the ring buffer filling up (only if RB_FL_OVERWRITE is off).
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long
+ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long ret;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	ret = local_read(&cpu_buffer->dropped_events);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu);
+
 /**
  * ring_buffer_entries - get the number of entries in a buffer
  * @buffer: The ring buffer
@@ -3864,9 +3892,10 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
 	cpu_buffer->reader_page->read = 0;
 
-	local_set(&cpu_buffer->commit_overrun, 0);
 	local_set(&cpu_buffer->entries_bytes, 0);
 	local_set(&cpu_buffer->overrun, 0);
+	local_set(&cpu_buffer->commit_overrun, 0);
+	local_set(&cpu_buffer->dropped_events, 0);
 	local_set(&cpu_buffer->entries, 0);
 	local_set(&cpu_buffer->committing, 0);
 	local_set(&cpu_buffer->commits, 0);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f6928edacd6d..36c213fbfce7 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4385,6 +4385,9 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	usec_rem = do_div(t, USEC_PER_SEC);
 	trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem);
 
+	cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "dropped events: %ld\n", cnt);
+
 	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
 
 	kfree(s);
-- 
cgit v1.2.3-55-g7522


From 01e3e710a9265fb7092efd67243d7b6dd6e2548a Mon Sep 17 00:00:00 2001
From: David Sharp
Date: Thu, 7 Jun 2012 16:46:24 -0700
Subject: tracing: Trivial cleanup

Remove ftrace_format_syscall() declaration; it is neither defined nor
used. Also update a comment and formatting.

Link: http://lkml.kernel.org/r/1339112785-21806-1-git-send-email-vnagarnaik@google.com

Signed-off-by: David Sharp <dhsharp@google.com>
Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/syscall.h    | 2 --
 kernel/trace/ring_buffer.c | 6 +++---
 2 files changed, 3 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 31966a4fb8cc..0c95796177d7 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -39,8 +39,6 @@ extern int reg_event_syscall_enter(struct ftrace_event_call *call);
 extern void unreg_event_syscall_enter(struct ftrace_event_call *call);
 extern int reg_event_syscall_exit(struct ftrace_event_call *call);
 extern void unreg_event_syscall_exit(struct ftrace_event_call *call);
-extern int
-ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s);
 enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags,
 				      struct trace_event *event);
 enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 0ebeb1d76ddf..23a384b92512 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1821,7 +1821,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)
 }
 
 /**
- * ring_buffer_update_event - update event type and data
+ * rb_update_event - update event type and data
  * @event: the even to update
  * @type: the type of event
  * @length: the size of the event field in the ring buffer
@@ -2723,8 +2723,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);
  * and not the length of the event which would hold the header.
  */
 int ring_buffer_write(struct ring_buffer *buffer,
-			unsigned long length,
-			void *data)
+		      unsigned long length,
+		      void *data)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
-- 
cgit v1.2.3-55-g7522


From 6f86ab9fcaef122abb837819139eadac1a0ca966 Mon Sep 17 00:00:00 2001
From: Vaibhav Nagarnaik
Date: Thu, 7 Jun 2012 16:46:25 -0700
Subject: tracing: Cleanup unnecessary function declarations

The functions defined in include/trace/syscalls.h are not used directly
since struct ftrace_event_class was introduced. Remove them from the
header file and rearrange the ftrace_event_class declarations in
trace_syscalls.c.

Link: http://lkml.kernel.org/r/1339112785-21806-2-git-send-email-vnagarnaik@google.com

Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/syscall.h       | 21 ---------------
 kernel/trace/trace_syscalls.c | 61 ++++++++++++++++++++-----------------------
 2 files changed, 29 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 0c95796177d7..84bc4197e736 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -31,25 +31,4 @@ struct syscall_metadata {
 	struct ftrace_event_call *exit_event;
 };
 
-#ifdef CONFIG_FTRACE_SYSCALLS
-extern unsigned long arch_syscall_addr(int nr);
-extern int init_syscall_trace(struct ftrace_event_call *call);
-
-extern int reg_event_syscall_enter(struct ftrace_event_call *call);
-extern void unreg_event_syscall_enter(struct ftrace_event_call *call);
-extern int reg_event_syscall_exit(struct ftrace_event_call *call);
-extern void unreg_event_syscall_exit(struct ftrace_event_call *call);
-enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags,
-				      struct trace_event *event);
-enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags,
-				     struct trace_event *event);
-#endif
-
-#ifdef CONFIG_PERF_EVENTS
-int perf_sysenter_enable(struct ftrace_event_call *call);
-void perf_sysenter_disable(struct ftrace_event_call *call);
-int perf_sysexit_enable(struct ftrace_event_call *call);
-void perf_sysexit_disable(struct ftrace_event_call *call);
-#endif
-
 #endif /* _TRACE_SYSCALL_H */
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 2485a7d09b11..7609dd6714c2 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -21,9 +21,6 @@ static int syscall_enter_register(struct ftrace_event_call *event,
 static int syscall_exit_register(struct ftrace_event_call *event,
 				 enum trace_reg type, void *data);
 
-static int syscall_enter_define_fields(struct ftrace_event_call *call);
-static int syscall_exit_define_fields(struct ftrace_event_call *call);
-
 static struct list_head *
 syscall_get_enter_fields(struct ftrace_event_call *call)
 {
@@ -32,30 +29,6 @@ syscall_get_enter_fields(struct ftrace_event_call *call)
 	return &entry->enter_fields;
 }
 
-struct trace_event_functions enter_syscall_print_funcs = {
-	.trace		= print_syscall_enter,
-};
-
-struct trace_event_functions exit_syscall_print_funcs = {
-	.trace		= print_syscall_exit,
-};
-
-struct ftrace_event_class event_class_syscall_enter = {
-	.system		= "syscalls",
-	.reg		= syscall_enter_register,
-	.define_fields	= syscall_enter_define_fields,
-	.get_fields	= syscall_get_enter_fields,
-	.raw_init	= init_syscall_trace,
-};
-
-struct ftrace_event_class event_class_syscall_exit = {
-	.system		= "syscalls",
-	.reg		= syscall_exit_register,
-	.define_fields	= syscall_exit_define_fields,
-	.fields		= LIST_HEAD_INIT(event_class_syscall_exit.fields),
-	.raw_init	= init_syscall_trace,
-};
-
 extern struct syscall_metadata *__start_syscalls_metadata[];
 extern struct syscall_metadata *__stop_syscalls_metadata[];
 
@@ -432,7 +405,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
 	mutex_unlock(&syscall_trace_lock);
 }
 
-int init_syscall_trace(struct ftrace_event_call *call)
+static int init_syscall_trace(struct ftrace_event_call *call)
 {
 	int id;
 	int num;
@@ -457,6 +430,30 @@ int init_syscall_trace(struct ftrace_event_call *call)
 	return id;
 }
 
+struct trace_event_functions enter_syscall_print_funcs = {
+	.trace		= print_syscall_enter,
+};
+
+struct trace_event_functions exit_syscall_print_funcs = {
+	.trace		= print_syscall_exit,
+};
+
+struct ftrace_event_class event_class_syscall_enter = {
+	.system		= "syscalls",
+	.reg		= syscall_enter_register,
+	.define_fields	= syscall_enter_define_fields,
+	.get_fields	= syscall_get_enter_fields,
+	.raw_init	= init_syscall_trace,
+};
+
+struct ftrace_event_class event_class_syscall_exit = {
+	.system		= "syscalls",
+	.reg		= syscall_exit_register,
+	.define_fields	= syscall_exit_define_fields,
+	.fields		= LIST_HEAD_INIT(event_class_syscall_exit.fields),
+	.raw_init	= init_syscall_trace,
+};
+
 unsigned long __init __weak arch_syscall_addr(int nr)
 {
 	return (unsigned long)sys_call_table[nr];
@@ -537,7 +534,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
 }
 
-int perf_sysenter_enable(struct ftrace_event_call *call)
+static int perf_sysenter_enable(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -558,7 +555,7 @@ int perf_sysenter_enable(struct ftrace_event_call *call)
 	return ret;
 }
 
-void perf_sysenter_disable(struct ftrace_event_call *call)
+static void perf_sysenter_disable(struct ftrace_event_call *call)
 {
 	int num;
 
@@ -615,7 +612,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
 }
 
-int perf_sysexit_enable(struct ftrace_event_call *call)
+static int perf_sysexit_enable(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -636,7 +633,7 @@ int perf_sysexit_enable(struct ftrace_event_call *call)
 	return ret;
 }
 
-void perf_sysexit_disable(struct ftrace_event_call *call)
+static void perf_sysexit_disable(struct ftrace_event_call *call)
 {
 	int num;
 
-- 
cgit v1.2.3-55-g7522


From 60efc15ae96c7aace8060411b0d5add20e1ab21e Mon Sep 17 00:00:00 2001
From: Michal Hocko
Date: Thu, 25 Oct 2012 15:41:51 +0200
Subject: linux/kernel.h: Remove duplicate trace_printk declaration

!CONFIG_TRACING both declares and defines (empty) trace_printk.
The first one is not redundant so it can be removed.

Link: http://lkml.kernel.org/r/1351172511-18125-1-git-send-email-mhocko@suse.cz

Signed-off-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/kernel.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index a123b13b70fd..7785d5df6d8b 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -527,9 +527,6 @@ __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
 
 extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode);
 #else
-static inline __printf(1, 2)
-int trace_printk(const char *fmt, ...);
-
 static inline void tracing_start(void) { }
 static inline void tracing_stop(void) { }
 static inline void ftrace_off_permanent(void) { }
@@ -539,8 +536,8 @@ static inline void tracing_on(void) { }
 static inline void tracing_off(void) { }
 static inline int tracing_is_on(void) { return 0; }
 
-static inline int
-trace_printk(const char *fmt, ...)
+static inline __printf(1, 2)
+int trace_printk(const char *fmt, ...)
 {
 	return 0;
 }
-- 
cgit v1.2.3-55-g7522


From 293a7a0a165c4f8327bbcf396cee9ec672727c98 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner
Date: Tue, 16 Oct 2012 15:07:49 -0700
Subject: genirq: Provide means to retrigger parent

Attempts to retrigger nested threaded IRQs currently fail because they
have no primary handler. In order to support retrigger of nested
IRQs, the parent IRQ needs to be retriggered.

To fix, when an IRQ needs to be resent, if the interrupt has a parent
IRQ and runs in the context of the parent IRQ, then resend the parent.

Also, handle_nested_irq() needs to clear the replay flag like the
other handlers, otherwise check_irq_resend() will set it and it will
never be cleared.  Without clearing, it results in the first resend
working fine, but check_irq_resend() returning early on subsequent
resends because the replay flag is still set.

Problem discovered on ARM/OMAP platforms where a nested IRQ that's
also a wakeup IRQ happens late in suspend and needed to be retriggered
during the resume process.

[khilman@ti.com: changelog edits, clear IRQS_REPLAY in handle_nested_irq()]

Reported-by: Kevin Hilman <khilman@ti.com>
Tested-by: Kevin Hilman <khilman@ti.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1350425269-11489-1-git-send-email-khilman@deeprootsystems.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h     |  9 +++++++++
 include/linux/irqdesc.h |  3 +++
 kernel/irq/chip.c       |  1 +
 kernel/irq/manage.c     | 16 ++++++++++++++++
 kernel/irq/resend.c     |  8 ++++++++
 5 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 216b0ba109d7..526f10a637c1 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -392,6 +392,15 @@ static inline void irq_move_masked_irq(struct irq_data *data) { }
 
 extern int no_irq_affinity;
 
+#ifdef CONFIG_HARDIRQS_SW_RESEND
+int irq_set_parent(int irq, int parent_irq);
+#else
+static inline int irq_set_parent(int irq, int parent_irq)
+{
+	return 0;
+}
+#endif
+
 /*
  * Built-in IRQ handlers for various IRQ types,
  * callable via desc->handle_irq()
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 0ba014c55056..623325e2ff97 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -11,6 +11,8 @@
 struct irq_affinity_notify;
 struct proc_dir_entry;
 struct module;
+struct irq_desc;
+
 /**
  * struct irq_desc - interrupt descriptor
  * @irq_data:		per irq and chip data passed down to chip functions
@@ -65,6 +67,7 @@ struct irq_desc {
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*dir;
 #endif
+	int			parent_irq;
 	struct module		*owner;
 	const char		*name;
 } ____cacheline_internodealigned_in_smp;
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 57d86d07221e..3aca9f29d30e 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -272,6 +272,7 @@ void handle_nested_irq(unsigned int irq)
 
 	raw_spin_lock_irq(&desc->lock);
 
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	action = desc->action;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 4c69326aa773..d06a396c7ce3 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -616,6 +616,22 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 	return ret;
 }
 
+#ifdef CONFIG_HARDIRQS_SW_RESEND
+int irq_set_parent(int irq, int parent_irq)
+{
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
+
+	if (!desc)
+		return -EINVAL;
+
+	desc->parent_irq = parent_irq;
+
+	irq_put_desc_unlock(desc, flags);
+	return 0;
+}
+#endif
+
 /*
  * Default primary interrupt handler for threaded interrupts. Is
  * assigned as primary handler when request_threaded_irq is called
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 6454db7b6a4d..9065107f083e 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -74,6 +74,14 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 		if (!desc->irq_data.chip->irq_retrigger ||
 		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
+			/*
+			 * If the interrupt has a parent irq and runs
+			 * in the thread context of the parent irq,
+			 * retrigger the parent.
+			 */
+			if (desc->parent_irq &&
+			    irq_settings_is_nested_thread(desc))
+				irq = desc->parent_irq;
 			/* Set it pending and activate the softirq: */
 			set_bit(irq, irqs_resend);
 			tasklet_schedule(&resend_tasklet);
-- 
cgit v1.2.3-55-g7522


From 86b00e0da6be7bbc16412f126c5b548ac5d91d50 Mon Sep 17 00:00:00 2001
From: Alex Elder
Date: Thu, 25 Oct 2012 23:34:42 -0500
Subject: rbd: get parent spec for version 2 images

Add support for getting the the information identifying the parent
image for rbd images that have them.  The child image holds a
reference to its parent image specification structure.  Create a new
entry "parent" in /sys/bus/rbd/image/N/ to report the identifying
information for the parent image, if any.

Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
---
 Documentation/ABI/testing/sysfs-bus-rbd |   4 +
 drivers/block/rbd.c                     | 131 ++++++++++++++++++++++++++++++++
 include/linux/ceph/rados.h              |   2 +
 3 files changed, 137 insertions(+)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-bus-rbd b/Documentation/ABI/testing/sysfs-bus-rbd
index 1cf2adf46b11..cd9213ccf3dc 100644
--- a/Documentation/ABI/testing/sysfs-bus-rbd
+++ b/Documentation/ABI/testing/sysfs-bus-rbd
@@ -70,6 +70,10 @@ snap_*
 
 	A directory per each snapshot
 
+parent
+
+	Information identifying the pool, image, and snapshot id for
+	the parent image in a layered rbd image (format 2 only).
 
 Entries under /sys/bus/rbd/devices/<dev-id>/snap_<snap-name>
 -------------------------------------------------------------
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 28052ff679ca..bce1fcfb5185 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -217,6 +217,9 @@ struct rbd_device {
 	struct ceph_osd_event   *watch_event;
 	struct ceph_osd_request *watch_request;
 
+	struct rbd_spec		*parent_spec;
+	u64			parent_overlap;
+
 	/* protects updating the header */
 	struct rw_semaphore     header_rwsem;
 
@@ -2009,6 +2012,49 @@ static ssize_t rbd_snap_show(struct device *dev,
 	return sprintf(buf, "%s\n", rbd_dev->spec->snap_name);
 }
 
+/*
+ * For an rbd v2 image, shows the pool id, image id, and snapshot id
+ * for the parent image.  If there is no parent, simply shows
+ * "(no parent image)".
+ */
+static ssize_t rbd_parent_show(struct device *dev,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
+	struct rbd_spec *spec = rbd_dev->parent_spec;
+	int count;
+	char *bufp = buf;
+
+	if (!spec)
+		return sprintf(buf, "(no parent image)\n");
+
+	count = sprintf(bufp, "pool_id %llu\npool_name %s\n",
+			(unsigned long long) spec->pool_id, spec->pool_name);
+	if (count < 0)
+		return count;
+	bufp += count;
+
+	count = sprintf(bufp, "image_id %s\nimage_name %s\n", spec->image_id,
+			spec->image_name ? spec->image_name : "(unknown)");
+	if (count < 0)
+		return count;
+	bufp += count;
+
+	count = sprintf(bufp, "snap_id %llu\nsnap_name %s\n",
+			(unsigned long long) spec->snap_id, spec->snap_name);
+	if (count < 0)
+		return count;
+	bufp += count;
+
+	count = sprintf(bufp, "overlap %llu\n", rbd_dev->parent_overlap);
+	if (count < 0)
+		return count;
+	bufp += count;
+
+	return (ssize_t) (bufp - buf);
+}
+
 static ssize_t rbd_image_refresh(struct device *dev,
 				 struct device_attribute *attr,
 				 const char *buf,
@@ -2032,6 +2078,7 @@ static DEVICE_ATTR(name, S_IRUGO, rbd_name_show, NULL);
 static DEVICE_ATTR(image_id, S_IRUGO, rbd_image_id_show, NULL);
 static DEVICE_ATTR(refresh, S_IWUSR, NULL, rbd_image_refresh);
 static DEVICE_ATTR(current_snap, S_IRUGO, rbd_snap_show, NULL);
+static DEVICE_ATTR(parent, S_IRUGO, rbd_parent_show, NULL);
 
 static struct attribute *rbd_attrs[] = {
 	&dev_attr_size.attr,
@@ -2043,6 +2090,7 @@ static struct attribute *rbd_attrs[] = {
 	&dev_attr_name.attr,
 	&dev_attr_image_id.attr,
 	&dev_attr_current_snap.attr,
+	&dev_attr_parent.attr,
 	&dev_attr_refresh.attr,
 	NULL
 };
@@ -2192,6 +2240,7 @@ struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
 
 static void rbd_dev_destroy(struct rbd_device *rbd_dev)
 {
+	rbd_spec_put(rbd_dev->parent_spec);
 	kfree(rbd_dev->header_name);
 	rbd_put_client(rbd_dev->rbd_client);
 	rbd_spec_put(rbd_dev->spec);
@@ -2400,6 +2449,71 @@ static int rbd_dev_v2_features(struct rbd_device *rbd_dev)
 						&rbd_dev->header.features);
 }
 
+static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
+{
+	struct rbd_spec *parent_spec;
+	size_t size;
+	void *reply_buf = NULL;
+	__le64 snapid;
+	void *p;
+	void *end;
+	char *image_id;
+	u64 overlap;
+	size_t len = 0;
+	int ret;
+
+	parent_spec = rbd_spec_alloc();
+	if (!parent_spec)
+		return -ENOMEM;
+
+	size = sizeof (__le64) +				/* pool_id */
+		sizeof (__le32) + RBD_IMAGE_ID_LEN_MAX +	/* image_id */
+		sizeof (__le64) +				/* snap_id */
+		sizeof (__le64);				/* overlap */
+	reply_buf = kmalloc(size, GFP_KERNEL);
+	if (!reply_buf) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	snapid = cpu_to_le64(CEPH_NOSNAP);
+	ret = rbd_req_sync_exec(rbd_dev, rbd_dev->header_name,
+				"rbd", "get_parent",
+				(char *) &snapid, sizeof (snapid),
+				(char *) reply_buf, size,
+				CEPH_OSD_FLAG_READ, NULL);
+	dout("%s: rbd_req_sync_exec returned %d\n", __func__, ret);
+	if (ret < 0)
+		goto out_err;
+
+	ret = -ERANGE;
+	p = reply_buf;
+	end = (char *) reply_buf + size;
+	ceph_decode_64_safe(&p, end, parent_spec->pool_id, out_err);
+	if (parent_spec->pool_id == CEPH_NOPOOL)
+		goto out;	/* No parent?  No problem. */
+
+	image_id = ceph_extract_encoded_string(&p, end, &len, GFP_KERNEL);
+	if (IS_ERR(image_id)) {
+		ret = PTR_ERR(image_id);
+		goto out_err;
+	}
+	parent_spec->image_id = image_id;
+	ceph_decode_64_safe(&p, end, parent_spec->snap_id, out_err);
+	ceph_decode_64_safe(&p, end, overlap, out_err);
+
+	rbd_dev->parent_overlap = overlap;
+	rbd_dev->parent_spec = parent_spec;
+	parent_spec = NULL;	/* rbd_dev now owns this */
+out:
+	ret = 0;
+out_err:
+	kfree(reply_buf);
+	rbd_spec_put(parent_spec);
+
+	return ret;
+}
+
 static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev, u64 *ver)
 {
 	size_t size;
@@ -3154,6 +3268,12 @@ static int rbd_dev_v1_probe(struct rbd_device *rbd_dev)
 	ret = rbd_read_header(rbd_dev, &rbd_dev->header);
 	if (ret < 0)
 		goto out_err;
+
+	/* Version 1 images have no parent (no layering) */
+
+	rbd_dev->parent_spec = NULL;
+	rbd_dev->parent_overlap = 0;
+
 	rbd_dev->image_format = 1;
 
 	dout("discovered version 1 image, header name is %s\n",
@@ -3205,6 +3325,14 @@ static int rbd_dev_v2_probe(struct rbd_device *rbd_dev)
 	if (ret < 0)
 		goto out_err;
 
+	/* If the image supports layering, get the parent info */
+
+	if (rbd_dev->header.features & RBD_FEATURE_LAYERING) {
+		ret = rbd_dev_v2_parent_info(rbd_dev);
+		if (ret < 0)
+			goto out_err;
+	}
+
 	/* crypto and compression type aren't (yet) supported for v2 images */
 
 	rbd_dev->header.crypt_type = 0;
@@ -3224,6 +3352,9 @@ static int rbd_dev_v2_probe(struct rbd_device *rbd_dev)
 
 	return 0;
 out_err:
+	rbd_dev->parent_overlap = 0;
+	rbd_spec_put(rbd_dev->parent_spec);
+	rbd_dev->parent_spec = NULL;
 	kfree(rbd_dev->header_name);
 	rbd_dev->header_name = NULL;
 	kfree(rbd_dev->header.object_prefix);
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 0a99099801a4..15077db662ed 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -87,6 +87,8 @@ struct ceph_pg {
  *
  *  lpgp_num -- as above.
  */
+#define CEPH_NOPOOL  ((__u64) (-1))  /* pool id not defined */
+
 #define CEPH_PG_TYPE_REP     1
 #define CEPH_PG_TYPE_RAID4   2
 #define CEPH_PG_POOL_VERSION 2
-- 
cgit v1.2.3-55-g7522


From 72afc71ffca0f444ee0e1ef8c7e34ab209bb48b3 Mon Sep 17 00:00:00 2001
From: Alex Elder
Date: Tue, 30 Oct 2012 19:40:33 -0500
Subject: libceph: define ceph_pg_pool_name_by_id()

Define and export function ceph_pg_pool_name_by_id() to supply
the name of a pg pool whose id is given.  This will be used by
the next patch.

Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
---
 include/linux/ceph/osdmap.h |  1 +
 net/ceph/osdmap.c           | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index e88a620b9f8a..5ea57ba69320 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -123,6 +123,7 @@ extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
 extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
 				struct ceph_pg pgid);
 
+extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id);
 extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name);
 
 #endif
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index f552aa48fd9e..de73214b5d26 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -469,6 +469,22 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id)
 	return NULL;
 }
 
+const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id)
+{
+	struct ceph_pg_pool_info *pi;
+
+	if (id == CEPH_NOPOOL)
+		return NULL;
+
+	if (WARN_ON_ONCE(id > (u64) INT_MAX))
+		return NULL;
+
+	pi = __lookup_pg_pool(&map->pg_pools, (int) id);
+
+	return pi ? pi->name : NULL;
+}
+EXPORT_SYMBOL(ceph_pg_pool_name_by_id);
+
 int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name)
 {
 	struct rb_node *rbp;
-- 
cgit v1.2.3-55-g7522


From 1858fe97c87c33c4975e291ecbbd6c1a20315674 Mon Sep 17 00:00:00 2001
From: Javier Martin
Date: Wed, 31 Oct 2012 11:53:34 +0100
Subject: ASoC: tlv320aic32x4: Add rstn gpio to platform data.

Add the possibility to specify a gpio through platform data
so that a HW reset can be issued to the codec.

Signed-off-by: Javier Martin <javier.martin@vista-silicon.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/sound/tlv320aic32x4.h    |  1 +
 sound/soc/codecs/tlv320aic32x4.c | 14 ++++++++++++++
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/sound/tlv320aic32x4.h b/include/sound/tlv320aic32x4.h
index c009f70b4029..24e5d991f148 100644
--- a/include/sound/tlv320aic32x4.h
+++ b/include/sound/tlv320aic32x4.h
@@ -26,6 +26,7 @@ struct aic32x4_pdata {
 	u32 power_cfg;
 	u32 micpga_routing;
 	bool swapdacs;
+	int rstn_gpio;
 };
 
 #endif
diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c
index d7d0e18f794c..e39e08d5d8e4 100644
--- a/sound/soc/codecs/tlv320aic32x4.c
+++ b/sound/soc/codecs/tlv320aic32x4.c
@@ -28,6 +28,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/pm.h>
+#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/cdev.h>
 #include <linux/slab.h>
@@ -65,6 +66,7 @@ struct aic32x4_priv {
 	u32 power_cfg;
 	u32 micpga_routing;
 	bool swapdacs;
+	int rstn_gpio;
 };
 
 /* 0dB min, 1dB steps */
@@ -627,10 +629,20 @@ static int aic32x4_probe(struct snd_soc_codec *codec)
 {
 	struct aic32x4_priv *aic32x4 = snd_soc_codec_get_drvdata(codec);
 	u32 tmp_reg;
+	int ret;
 
 	codec->hw_write = (hw_write_t) i2c_master_send;
 	codec->control_data = aic32x4->control_data;
 
+	if (aic32x4->rstn_gpio >= 0) {
+		ret = devm_gpio_request_one(codec->dev, aic32x4->rstn_gpio,
+				GPIOF_OUT_INIT_LOW, "tlv320aic32x4 rstn");
+		if (ret != 0)
+			return ret;
+		ndelay(10);
+		gpio_set_value(aic32x4->rstn_gpio, 1);
+	}
+
 	snd_soc_write(codec, AIC32X4_RESET, 0x01);
 
 	/* Power platform configuration */
@@ -723,10 +735,12 @@ static __devinit int aic32x4_i2c_probe(struct i2c_client *i2c,
 		aic32x4->power_cfg = pdata->power_cfg;
 		aic32x4->swapdacs = pdata->swapdacs;
 		aic32x4->micpga_routing = pdata->micpga_routing;
+		aic32x4->rstn_gpio = pdata->rstn_gpio;
 	} else {
 		aic32x4->power_cfg = 0;
 		aic32x4->swapdacs = false;
 		aic32x4->micpga_routing = 0;
+		aic32x4->rstn_gpio = -1;
 	}
 
 	ret = snd_soc_register_codec(&i2c->dev,
-- 
cgit v1.2.3-55-g7522


From bbb009941efaece3898910a862f6d23aa55d6ba8 Mon Sep 17 00:00:00 2001
From: Jason Wang
Date: Wed, 31 Oct 2012 19:45:59 +0000
Subject: tuntap: introduce multiqueue flags

Add flags to be used by creating multiqueue tuntap device.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_tun.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 25a585ce23e6..8ef3a87b58a0 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -34,6 +34,7 @@
 #define TUN_ONE_QUEUE	0x0080
 #define TUN_PERSIST 	0x0100	
 #define TUN_VNET_HDR 	0x0200
+#define TUN_TAP_MQ      0x0400
 
 /* Ioctl defines */
 #define TUNSETNOCSUM  _IOW('T', 200, int) 
@@ -61,6 +62,7 @@
 #define IFF_ONE_QUEUE	0x2000
 #define IFF_VNET_HDR	0x4000
 #define IFF_TUN_EXCL	0x8000
+#define IFF_MULTI_QUEUE 0x0100
 
 /* Features for GSO (TUNSETOFFLOAD). */
 #define TUN_F_CSUM	0x01	/* You can hand me unchecksummed packets. */
-- 
cgit v1.2.3-55-g7522


From cde8b15f1aabe327038ee4e0e11dd6b798572f69 Mon Sep 17 00:00:00 2001
From: Jason Wang
Date: Wed, 31 Oct 2012 19:46:01 +0000
Subject: tuntap: add ioctl to attach or detach a file form tuntap device

Sometimes usespace may need to active/deactive a queue, this could be done by
detaching and attaching a file from tuntap device.

This patch introduces a new ioctls - TUNSETQUEUE which could be used to do
this. Flag IFF_ATTACH_QUEUE were introduced to do attaching while
IFF_DETACH_QUEUE were introduced to do the detaching.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c           | 56 ++++++++++++++++++++++++++++++++++++++-------
 include/uapi/linux/if_tun.h |  3 +++
 2 files changed, 51 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 2762c55aeb66..79b6f9ecc12c 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -195,6 +195,15 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb)
 	return txq;
 }
 
+static inline bool tun_not_capable(struct tun_struct *tun)
+{
+	const struct cred *cred = current_cred();
+
+	return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) ||
+		  (gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
+		!capable(CAP_NET_ADMIN);
+}
+
 static void tun_set_real_num_queues(struct tun_struct *tun)
 {
 	netif_set_real_num_tx_queues(tun->dev, tun->numqueues);
@@ -1310,8 +1319,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 	dev = __dev_get_by_name(net, ifr->ifr_name);
 	if (dev) {
-		const struct cred *cred = current_cred();
-
 		if (ifr->ifr_flags & IFF_TUN_EXCL)
 			return -EBUSY;
 		if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops)
@@ -1321,9 +1328,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		else
 			return -EINVAL;
 
-		if (((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) ||
-		     (gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
-		    !capable(CAP_NET_ADMIN))
+		if (tun_not_capable(tun))
 			return -EPERM;
 		err = security_tun_dev_attach(tfile->socket.sk);
 		if (err < 0)
@@ -1530,6 +1535,40 @@ static void tun_set_sndbuf(struct tun_struct *tun)
 	}
 }
 
+static int tun_set_queue(struct file *file, struct ifreq *ifr)
+{
+	struct tun_file *tfile = file->private_data;
+	struct tun_struct *tun;
+	struct net_device *dev;
+	int ret = 0;
+
+	rtnl_lock();
+
+	if (ifr->ifr_flags & IFF_ATTACH_QUEUE) {
+		dev = __dev_get_by_name(tfile->net, ifr->ifr_name);
+		if (!dev) {
+			ret = -EINVAL;
+			goto unlock;
+		}
+
+		tun = netdev_priv(dev);
+		if (dev->netdev_ops != &tap_netdev_ops &&
+			dev->netdev_ops != &tun_netdev_ops)
+			ret = -EINVAL;
+		else if (tun_not_capable(tun))
+			ret = -EPERM;
+		else
+			ret = tun_attach(tun, file);
+	} else if (ifr->ifr_flags & IFF_DETACH_QUEUE)
+		__tun_detach(tfile, false);
+	else
+		ret = -EINVAL;
+
+unlock:
+	rtnl_unlock();
+	return ret;
+}
+
 static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			    unsigned long arg, int ifreq_len)
 {
@@ -1543,7 +1582,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	int vnet_hdr_sz;
 	int ret;
 
-	if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89) {
+	if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) {
 		if (copy_from_user(&ifr, argp, ifreq_len))
 			return -EFAULT;
 	} else {
@@ -1554,9 +1593,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		 * This is needed because we never checked for invalid flags on
 		 * TUNSETIFF. */
 		return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE |
-				IFF_VNET_HDR,
+				IFF_VNET_HDR | IFF_MULTI_QUEUE,
 				(unsigned int __user*)argp);
-	}
+	} else if (cmd == TUNSETQUEUE)
+		return tun_set_queue(file, &ifr);
 
 	ret = 0;
 	rtnl_lock();
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 8ef3a87b58a0..958497ad5bb5 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -54,6 +54,7 @@
 #define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog)
 #define TUNGETVNETHDRSZ _IOR('T', 215, int)
 #define TUNSETVNETHDRSZ _IOW('T', 216, int)
+#define TUNSETQUEUE  _IOW('T', 217, int)
 
 /* TUNSETIFF ifr flags */
 #define IFF_TUN		0x0001
@@ -63,6 +64,8 @@
 #define IFF_VNET_HDR	0x4000
 #define IFF_TUN_EXCL	0x8000
 #define IFF_MULTI_QUEUE 0x0100
+#define IFF_ATTACH_QUEUE 0x0200
+#define IFF_DETACH_QUEUE 0x0400
 
 /* Features for GSO (TUNSETOFFLOAD). */
 #define TUN_F_CSUM	0x01	/* You can hand me unchecksummed packets. */
-- 
cgit v1.2.3-55-g7522


From a8fc92778080c845eaadc369a0ecf5699a03bef0 Mon Sep 17 00:00:00 2001
From: Pavel Emelyanov
Date: Thu, 1 Nov 2012 02:01:48 +0000
Subject: sk-filter: Add ability to get socket filter program (v2)

The SO_ATTACH_FILTER option is set only. I propose to add the get
ability by using SO_ATTACH_FILTER in getsockopt. To be less
irritating to eyes the SO_GET_FILTER alias to it is declared. This
ability is required by checkpoint-restore project to be able to
save full state of a socket.

There are two issues with getting filter back.

First, kernel modifies the sock_filter->code on filter load, thus in
order to return the filter element back to user we have to decode it
into user-visible constants. Fortunately the modification in question
is interconvertible.

Second, the BPF_S_ALU_DIV_K code modifies the command argument k to
speed up the run-time division by doing kernel_k = reciprocal(user_k).
Bad news is that different user_k may result in same kernel_k, so we
can't get the original user_k back. Good news is that we don't have
to do it. What we need to is calculate a user2_k so, that

  reciprocal(user2_k) == reciprocal(user_k) == kernel_k

i.e. if it's re-loaded back the compiled again value will be exactly
the same as it was. That said, the user2_k can be calculated like this

  user2_k = reciprocal(kernel_k)

with an exception, that if kernel_k == 0, then user2_k == 1.

The optlen argument is treated like this -- when zero, kernel returns
the amount of sock_fprog elements in filter, otherwise it should be
large enough for the sock_fprog array.

changes since v1:
* Declared SO_GET_FILTER in all arch headers
* Added decode of vlan-tag codes

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/alpha/include/asm/socket.h        |   1 +
 arch/avr32/include/uapi/asm/socket.h   |   1 +
 arch/cris/include/asm/socket.h         |   1 +
 arch/frv/include/uapi/asm/socket.h     |   1 +
 arch/h8300/include/asm/socket.h        |   1 +
 arch/ia64/include/uapi/asm/socket.h    |   1 +
 arch/m32r/include/asm/socket.h         |   1 +
 arch/m68k/include/asm/socket.h         |   1 +
 arch/mips/include/uapi/asm/socket.h    |   1 +
 arch/mn10300/include/uapi/asm/socket.h |   1 +
 arch/parisc/include/asm/socket.h       |   1 +
 arch/powerpc/include/uapi/asm/socket.h |   1 +
 arch/s390/include/uapi/asm/socket.h    |   1 +
 arch/sparc/include/uapi/asm/socket.h   |   1 +
 arch/xtensa/include/asm/socket.h       |   1 +
 include/linux/filter.h                 |   1 +
 include/uapi/asm-generic/socket.h      |   1 +
 net/core/filter.c                      | 130 +++++++++++++++++++++++++++++++++
 net/core/sock.c                        |   6 ++
 19 files changed, 153 insertions(+)

(limited to 'include')

diff --git a/arch/alpha/include/asm/socket.h b/arch/alpha/include/asm/socket.h
index 7d2f75be932e..0087d053b77f 100644
--- a/arch/alpha/include/asm/socket.h
+++ b/arch/alpha/include/asm/socket.h
@@ -47,6 +47,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		28
 #define SO_TIMESTAMP		29
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index a473f8c6a9aa..486df68abeec 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -40,6 +40,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		28
 #define SO_TIMESTAMP		29
diff --git a/arch/cris/include/asm/socket.h b/arch/cris/include/asm/socket.h
index ae52825021af..b681b043f6c8 100644
--- a/arch/cris/include/asm/socket.h
+++ b/arch/cris/include/asm/socket.h
@@ -42,6 +42,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		28
 #define SO_TIMESTAMP           29
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index a5b1d7dbb205..871f89b7fbda 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -40,6 +40,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME             28
 #define SO_TIMESTAMP		29
diff --git a/arch/h8300/include/asm/socket.h b/arch/h8300/include/asm/socket.h
index ec4554e7b04b..90a2e573c7e6 100644
--- a/arch/h8300/include/asm/socket.h
+++ b/arch/h8300/include/asm/socket.h
@@ -40,6 +40,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME             28
 #define SO_TIMESTAMP		29
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 41fc28a4a18a..23d6759bb57b 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -49,6 +49,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER	26
 #define SO_DETACH_FILTER	27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		28
 #define SO_TIMESTAMP		29
diff --git a/arch/m32r/include/asm/socket.h b/arch/m32r/include/asm/socket.h
index a15f40b52783..5e7088a26726 100644
--- a/arch/m32r/include/asm/socket.h
+++ b/arch/m32r/include/asm/socket.h
@@ -40,6 +40,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		28
 #define SO_TIMESTAMP		29
diff --git a/arch/m68k/include/asm/socket.h b/arch/m68k/include/asm/socket.h
index d1be684edf97..285da3b6ad92 100644
--- a/arch/m68k/include/asm/socket.h
+++ b/arch/m68k/include/asm/socket.h
@@ -40,6 +40,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME             28
 #define SO_TIMESTAMP		29
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index c5ed59549cb8..17307ab90474 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -63,6 +63,7 @@ To add: #define SO_REUSEPORT 0x0200	/* Allow local address and port reuse.  */
 /* Socket filtering */
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME             28
 #define SO_TIMESTAMP		29
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index 820463a484b8..af5366bbfe62 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -40,6 +40,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		28
 #define SO_TIMESTAMP		29
diff --git a/arch/parisc/include/asm/socket.h b/arch/parisc/include/asm/socket.h
index 1b52c2c31a7a..d9ff4731253b 100644
--- a/arch/parisc/include/asm/socket.h
+++ b/arch/parisc/include/asm/socket.h
@@ -48,6 +48,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER        0x401a
 #define SO_DETACH_FILTER        0x401b
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_ACCEPTCONN		0x401c
 
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index 3d5179bb122f..eb0b1864d400 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -47,6 +47,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER	26
 #define SO_DETACH_FILTER	27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		28
 #define SO_TIMESTAMP		29
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 69718cd6d635..436d07c23be8 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -46,6 +46,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		28
 #define SO_TIMESTAMP		29
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index bea1568ae4af..c83a937ead00 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -41,6 +41,7 @@
 
 #define SO_ATTACH_FILTER	0x001a
 #define SO_DETACH_FILTER        0x001b
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		0x001c
 #define SO_TIMESTAMP		0x001d
diff --git a/arch/xtensa/include/asm/socket.h b/arch/xtensa/include/asm/socket.h
index e36c68184920..38079be1cf1e 100644
--- a/arch/xtensa/include/asm/socket.h
+++ b/arch/xtensa/include/asm/socket.h
@@ -52,6 +52,7 @@
 
 #define SO_ATTACH_FILTER        26
 #define SO_DETACH_FILTER        27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		28
 #define SO_TIMESTAMP		29
diff --git a/include/linux/filter.h b/include/linux/filter.h
index c9f0005c35e2..c45eabc135e1 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -45,6 +45,7 @@ extern void sk_unattached_filter_destroy(struct sk_filter *fp);
 extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 extern int sk_detach_filter(struct sock *sk);
 extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
+extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len);
 
 #ifdef CONFIG_BPF_JIT
 extern void bpf_jit_compile(struct sk_filter *fp);
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index b1bea03274d5..2d32d073a6f9 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -43,6 +43,7 @@
 /* Socket filtering */
 #define SO_ATTACH_FILTER	26
 #define SO_DETACH_FILTER	27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
 
 #define SO_PEERNAME		28
 #define SO_TIMESTAMP		29
diff --git a/net/core/filter.c b/net/core/filter.c
index 5a114d41bf11..c23543cba132 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -760,3 +760,133 @@ int sk_detach_filter(struct sock *sk)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(sk_detach_filter);
+
+static void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
+{
+	static const u16 decodes[] = {
+		[BPF_S_ALU_ADD_K]	= BPF_ALU|BPF_ADD|BPF_K,
+		[BPF_S_ALU_ADD_X]	= BPF_ALU|BPF_ADD|BPF_X,
+		[BPF_S_ALU_SUB_K]	= BPF_ALU|BPF_SUB|BPF_K,
+		[BPF_S_ALU_SUB_X]	= BPF_ALU|BPF_SUB|BPF_X,
+		[BPF_S_ALU_MUL_K]	= BPF_ALU|BPF_MUL|BPF_K,
+		[BPF_S_ALU_MUL_X]	= BPF_ALU|BPF_MUL|BPF_X,
+		[BPF_S_ALU_DIV_X]	= BPF_ALU|BPF_DIV|BPF_X,
+		[BPF_S_ALU_MOD_K]	= BPF_ALU|BPF_MOD|BPF_K,
+		[BPF_S_ALU_MOD_X]	= BPF_ALU|BPF_MOD|BPF_X,
+		[BPF_S_ALU_AND_K]	= BPF_ALU|BPF_AND|BPF_K,
+		[BPF_S_ALU_AND_X]	= BPF_ALU|BPF_AND|BPF_X,
+		[BPF_S_ALU_OR_K]	= BPF_ALU|BPF_OR|BPF_K,
+		[BPF_S_ALU_OR_X]	= BPF_ALU|BPF_OR|BPF_X,
+		[BPF_S_ALU_XOR_K]	= BPF_ALU|BPF_XOR|BPF_K,
+		[BPF_S_ALU_XOR_X]	= BPF_ALU|BPF_XOR|BPF_X,
+		[BPF_S_ALU_LSH_K]	= BPF_ALU|BPF_LSH|BPF_K,
+		[BPF_S_ALU_LSH_X]	= BPF_ALU|BPF_LSH|BPF_X,
+		[BPF_S_ALU_RSH_K]	= BPF_ALU|BPF_RSH|BPF_K,
+		[BPF_S_ALU_RSH_X]	= BPF_ALU|BPF_RSH|BPF_X,
+		[BPF_S_ALU_NEG]		= BPF_ALU|BPF_NEG,
+		[BPF_S_LD_W_ABS]	= BPF_LD|BPF_W|BPF_ABS,
+		[BPF_S_LD_H_ABS]	= BPF_LD|BPF_H|BPF_ABS,
+		[BPF_S_LD_B_ABS]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_PROTOCOL]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_PKTTYPE]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_IFINDEX]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_NLATTR]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_NLATTR_NEST]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_MARK]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_QUEUE]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_HATYPE]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_RXHASH]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_CPU]		= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_ALU_XOR_X]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_SECCOMP_LD_W] = BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_VLAN_TAG]	= BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS,
+		[BPF_S_LD_W_LEN]	= BPF_LD|BPF_W|BPF_LEN,
+		[BPF_S_LD_W_IND]	= BPF_LD|BPF_W|BPF_IND,
+		[BPF_S_LD_H_IND]	= BPF_LD|BPF_H|BPF_IND,
+		[BPF_S_LD_B_IND]	= BPF_LD|BPF_B|BPF_IND,
+		[BPF_S_LD_IMM]		= BPF_LD|BPF_IMM,
+		[BPF_S_LDX_W_LEN]	= BPF_LDX|BPF_W|BPF_LEN,
+		[BPF_S_LDX_B_MSH]	= BPF_LDX|BPF_B|BPF_MSH,
+		[BPF_S_LDX_IMM]		= BPF_LDX|BPF_IMM,
+		[BPF_S_MISC_TAX]	= BPF_MISC|BPF_TAX,
+		[BPF_S_MISC_TXA]	= BPF_MISC|BPF_TXA,
+		[BPF_S_RET_K]		= BPF_RET|BPF_K,
+		[BPF_S_RET_A]		= BPF_RET|BPF_A,
+		[BPF_S_ALU_DIV_K]	= BPF_ALU|BPF_DIV|BPF_K,
+		[BPF_S_LD_MEM]		= BPF_LD|BPF_MEM,
+		[BPF_S_LDX_MEM]		= BPF_LDX|BPF_MEM,
+		[BPF_S_ST]		= BPF_ST,
+		[BPF_S_STX]		= BPF_STX,
+		[BPF_S_JMP_JA]		= BPF_JMP|BPF_JA,
+		[BPF_S_JMP_JEQ_K]	= BPF_JMP|BPF_JEQ|BPF_K,
+		[BPF_S_JMP_JEQ_X]	= BPF_JMP|BPF_JEQ|BPF_X,
+		[BPF_S_JMP_JGE_K]	= BPF_JMP|BPF_JGE|BPF_K,
+		[BPF_S_JMP_JGE_X]	= BPF_JMP|BPF_JGE|BPF_X,
+		[BPF_S_JMP_JGT_K]	= BPF_JMP|BPF_JGT|BPF_K,
+		[BPF_S_JMP_JGT_X]	= BPF_JMP|BPF_JGT|BPF_X,
+		[BPF_S_JMP_JSET_K]	= BPF_JMP|BPF_JSET|BPF_K,
+		[BPF_S_JMP_JSET_X]	= BPF_JMP|BPF_JSET|BPF_X,
+	};
+	u16 code;
+
+	code = filt->code;
+
+	to->code = decodes[code];
+	to->jt = filt->jt;
+	to->jf = filt->jf;
+
+	if (code == BPF_S_ALU_DIV_K) {
+		/*
+		 * When loaded this rule user gave us X, which was
+		 * translated into R = r(X). Now we calculate the
+		 * RR = r(R) and report it back. If next time this
+		 * value is loaded and RRR = r(RR) is calculated
+		 * then the R == RRR will be true.
+		 *
+		 * One exception. X == 1 translates into R == 0 and
+		 * we can't calculate RR out of it with r().
+		 */
+
+		if (filt->k == 0)
+			to->k = 1;
+		else
+			to->k = reciprocal_value(filt->k);
+
+		BUG_ON(reciprocal_value(to->k) != filt->k);
+	} else
+		to->k = filt->k;
+}
+
+int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len)
+{
+	struct sk_filter *filter;
+	int i, ret;
+
+	lock_sock(sk);
+	filter = rcu_dereference_protected(sk->sk_filter,
+			sock_owned_by_user(sk));
+	ret = 0;
+	if (!filter)
+		goto out;
+	ret = filter->len;
+	if (!len)
+		goto out;
+	ret = -EINVAL;
+	if (len < filter->len)
+		goto out;
+
+	ret = -EFAULT;
+	for (i = 0; i < filter->len; i++) {
+		struct sock_filter fb;
+
+		sk_decode_filter(&filter->insns[i], &fb);
+		if (copy_to_user(&ubuf[i], &fb, sizeof(fb)))
+			goto out;
+	}
+
+	ret = filter->len;
+out:
+	release_sock(sk);
+	return ret;
+}
diff --git a/net/core/sock.c b/net/core/sock.c
index 0a023b8daa55..06286006a2cc 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1077,6 +1077,12 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 	case SO_BINDTODEVICE:
 		v.val = sk->sk_bound_dev_if;
 		break;
+	case SO_GET_FILTER:
+		len = sk_get_filter(sk, (struct sock_filter __user *)optval, len);
+		if (len < 0)
+			return len;
+
+		goto lenout;
 	default:
 		return -ENOPROTOOPT;
 	}
-- 
cgit v1.2.3-55-g7522


From 215b13dd288c2e1e4461c1530a801f5f83e8cd90 Mon Sep 17 00:00:00 2001
From: Richard Cochran
Date: Wed, 31 Oct 2012 06:19:07 +0000
Subject: ptp: add an ioctl to compare PHC time with system time

This patch adds an ioctl for PTP Hardware Clock (PHC) devices that allows
user space to measure the time offset between the PHC and the system
clock. Rather than hard coding any kind of estimation algorithm into the
kernel, this patch takes the more flexible approach of just delivering
an array of raw clock readings. In that way, the user space clock servo
may be adapted to new and different hardware clocks.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c      | 32 ++++++++++++++++++++++++++++++++
 include/uapi/linux/ptp_clock.h | 14 ++++++++++++++
 2 files changed, 46 insertions(+)

(limited to 'include')

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index e7f301da2902..4f8ae8057a7e 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -33,9 +33,13 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 {
 	struct ptp_clock_caps caps;
 	struct ptp_clock_request req;
+	struct ptp_sys_offset sysoff;
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
 	struct ptp_clock_info *ops = ptp->info;
+	struct ptp_clock_time *pct;
+	struct timespec ts;
 	int enable, err = 0;
+	unsigned int i;
 
 	switch (cmd) {
 
@@ -88,6 +92,34 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 		err = ops->enable(ops, &req, enable);
 		break;
 
+	case PTP_SYS_OFFSET:
+		if (copy_from_user(&sysoff, (void __user *)arg,
+				   sizeof(sysoff))) {
+			err = -EFAULT;
+			break;
+		}
+		if (sysoff.n_samples > PTP_MAX_SAMPLES) {
+			err = -EINVAL;
+			break;
+		}
+		pct = &sysoff.ts[0];
+		for (i = 0; i < sysoff.n_samples; i++) {
+			getnstimeofday(&ts);
+			pct->sec = ts.tv_sec;
+			pct->nsec = ts.tv_nsec;
+			pct++;
+			ptp->info->gettime(ptp->info, &ts);
+			pct->sec = ts.tv_sec;
+			pct->nsec = ts.tv_nsec;
+			pct++;
+		}
+		getnstimeofday(&ts);
+		pct->sec = ts.tv_sec;
+		pct->nsec = ts.tv_nsec;
+		if (copy_to_user((void __user *)arg, &sysoff, sizeof(sysoff)))
+			err = -EFAULT;
+		break;
+
 	default:
 		err = -ENOTTY;
 		break;
diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h
index 94e981f810a2..b65c834f83e9 100644
--- a/include/uapi/linux/ptp_clock.h
+++ b/include/uapi/linux/ptp_clock.h
@@ -67,12 +67,26 @@ struct ptp_perout_request {
 	unsigned int rsv[4];          /* Reserved for future use. */
 };
 
+#define PTP_MAX_SAMPLES 25 /* Maximum allowed offset measurement samples. */
+
+struct ptp_sys_offset {
+	unsigned int n_samples; /* Desired number of measurements. */
+	unsigned int rsv[3];    /* Reserved for future use. */
+	/*
+	 * Array of interleaved system/phc time stamps. The kernel
+	 * will provide 2*n_samples + 1 time stamps, with the last
+	 * one as a system time stamp.
+	 */
+	struct ptp_clock_time ts[2 * PTP_MAX_SAMPLES + 1];
+};
+
 #define PTP_CLK_MAGIC '='
 
 #define PTP_CLOCK_GETCAPS  _IOR(PTP_CLK_MAGIC, 1, struct ptp_clock_caps)
 #define PTP_EXTTS_REQUEST  _IOW(PTP_CLK_MAGIC, 2, struct ptp_extts_request)
 #define PTP_PEROUT_REQUEST _IOW(PTP_CLK_MAGIC, 3, struct ptp_perout_request)
 #define PTP_ENABLE_PPS     _IOW(PTP_CLK_MAGIC, 4, int)
+#define PTP_SYS_OFFSET     _IOW(PTP_CLK_MAGIC, 5, struct ptp_sys_offset)
 
 struct ptp_extts_event {
 	struct ptp_clock_time t; /* Time event occured. */
-- 
cgit v1.2.3-55-g7522


From 65f8f9a1c1db831e5159e3e3e50912d1f214cd0c Mon Sep 17 00:00:00 2001
From: Richard Cochran
Date: Wed, 31 Oct 2012 06:27:25 +0000
Subject: time: remove the timecompare code.

This patch removes the timecompare code from the kernel. The top five
reasons to do this are:

1. There are no more users of this code.
2. The original idea was a bit weak.
3. The original author has disappeared.
4. The code was not general purpose but tuned to a particular hardware,
5. There are better ways to accomplish clock synchronization.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: John Stultz <john.stultz@linaro.org>
Tested-by: Bob Liu <lliubbo@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/timecompare.h | 125 ----------------------------
 kernel/time/Makefile        |   2 +-
 kernel/time/timecompare.c   | 193 --------------------------------------------
 3 files changed, 1 insertion(+), 319 deletions(-)
 delete mode 100644 include/linux/timecompare.h
 delete mode 100644 kernel/time/timecompare.c

(limited to 'include')

diff --git a/include/linux/timecompare.h b/include/linux/timecompare.h
deleted file mode 100644
index 546e2234e4b3..000000000000
--- a/include/linux/timecompare.h
+++ /dev/null
@@ -1,125 +0,0 @@
-/*
- * Utility code which helps transforming between two different time
- * bases, called "source" and "target" time in this code.
- *
- * Source time has to be provided via the timecounter API while target
- * time is accessed via a function callback whose prototype
- * intentionally matches ktime_get() and ktime_get_real(). These
- * interfaces where chosen like this so that the code serves its
- * initial purpose without additional glue code.
- *
- * This purpose is synchronizing a hardware clock in a NIC with system
- * time, in order to implement the Precision Time Protocol (PTP,
- * IEEE1588) with more accurate hardware assisted time stamping.  In
- * that context only synchronization against system time (=
- * ktime_get_real()) is currently needed. But this utility code might
- * become useful in other situations, which is why it was written as
- * general purpose utility code.
- *
- * The source timecounter is assumed to return monotonically
- * increasing time (but this code does its best to compensate if that
- * is not the case) whereas target time may jump.
- *
- * The target time corresponding to a source time is determined by
- * reading target time, reading source time, reading target time
- * again, then assuming that average target time corresponds to source
- * time. In other words, the assumption is that reading the source
- * time is slow and involves equal time for sending the request and
- * receiving the reply, whereas reading target time is assumed to be
- * fast.
- *
- * Copyright (C) 2009 Intel Corporation.
- * Author: Patrick Ohly <patrick.ohly@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
- */
-#ifndef _LINUX_TIMECOMPARE_H
-#define _LINUX_TIMECOMPARE_H
-
-#include <linux/clocksource.h>
-#include <linux/ktime.h>
-
-/**
- * struct timecompare - stores state and configuration for the two clocks
- *
- * Initialize to zero, then set source/target/num_samples.
- *
- * Transformation between source time and target time is done with:
- * target_time = source_time + offset +
- *               (source_time - last_update) * skew /
- *               TIMECOMPARE_SKEW_RESOLUTION
- *
- * @source:          used to get source time stamps via timecounter_read()
- * @target:          function returning target time (for example, ktime_get
- *                   for monotonic time, or ktime_get_real for wall clock)
- * @num_samples:     number of times that source time and target time are to
- *                   be compared when determining their offset
- * @offset:          (target time - source time) at the time of the last update
- * @skew:            average (target time - source time) / delta source time *
- *                   TIMECOMPARE_SKEW_RESOLUTION
- * @last_update:     last source time stamp when time offset was measured
- */
-struct timecompare {
-	struct timecounter *source;
-	ktime_t (*target)(void);
-	int num_samples;
-
-	s64 offset;
-	s64 skew;
-	u64 last_update;
-};
-
-/**
- * timecompare_transform - transform source time stamp into target time base
- * @sync:            context for time sync
- * @source_tstamp:   the result of timecounter_read() or
- *                   timecounter_cyc2time()
- */
-extern ktime_t timecompare_transform(struct timecompare *sync,
-				     u64 source_tstamp);
-
-/**
- * timecompare_offset - measure current (target time - source time) offset
- * @sync:            context for time sync
- * @offset:          average offset during sample period returned here
- * @source_tstamp:   average source time during sample period returned here
- *
- * Returns number of samples used. Might be zero (= no result) in the
- * unlikely case that target time was monotonically decreasing for all
- * samples (= broken).
- */
-extern int timecompare_offset(struct timecompare *sync,
-			      s64 *offset,
-			      u64 *source_tstamp);
-
-extern void __timecompare_update(struct timecompare *sync,
-				 u64 source_tstamp);
-
-/**
- * timecompare_update - update offset and skew by measuring current offset
- * @sync:            context for time sync
- * @source_tstamp:   the result of timecounter_read() or
- *                   timecounter_cyc2time(), pass zero to force update
- *
- * Updates are only done at most once per second.
- */
-static inline void timecompare_update(struct timecompare *sync,
-				      u64 source_tstamp)
-{
-	if (!source_tstamp ||
-	    (s64)(source_tstamp - sync->last_update) >= NSEC_PER_SEC)
-		__timecompare_update(sync, source_tstamp);
-}
-
-#endif /* _LINUX_TIMECOMPARE_H */
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index e2fd74b8e8c2..ff7d9d2ab504 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,4 +1,4 @@
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
 obj-y += timeconv.o posix-clock.o alarmtimer.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
deleted file mode 100644
index a9ae369925ce..000000000000
--- a/kernel/time/timecompare.c
+++ /dev/null
@@ -1,193 +0,0 @@
-/*
- * Copyright (C) 2009 Intel Corporation.
- * Author: Patrick Ohly <patrick.ohly@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/timecompare.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/math64.h>
-#include <linux/kernel.h>
-
-/*
- * fixed point arithmetic scale factor for skew
- *
- * Usually one would measure skew in ppb (parts per billion, 1e9), but
- * using a factor of 2 simplifies the math.
- */
-#define TIMECOMPARE_SKEW_RESOLUTION (((s64)1)<<30)
-
-ktime_t timecompare_transform(struct timecompare *sync,
-			      u64 source_tstamp)
-{
-	u64 nsec;
-
-	nsec = source_tstamp + sync->offset;
-	nsec += (s64)(source_tstamp - sync->last_update) * sync->skew /
-		TIMECOMPARE_SKEW_RESOLUTION;
-
-	return ns_to_ktime(nsec);
-}
-EXPORT_SYMBOL_GPL(timecompare_transform);
-
-int timecompare_offset(struct timecompare *sync,
-		       s64 *offset,
-		       u64 *source_tstamp)
-{
-	u64 start_source = 0, end_source = 0;
-	struct {
-		s64 offset;
-		s64 duration_target;
-	} buffer[10], sample, *samples;
-	int counter = 0, i;
-	int used;
-	int index;
-	int num_samples = sync->num_samples;
-
-	if (num_samples > ARRAY_SIZE(buffer)) {
-		samples = kmalloc(sizeof(*samples) * num_samples, GFP_ATOMIC);
-		if (!samples) {
-			samples = buffer;
-			num_samples = ARRAY_SIZE(buffer);
-		}
-	} else {
-		samples = buffer;
-	}
-
-	/* run until we have enough valid samples, but do not try forever */
-	i = 0;
-	counter = 0;
-	while (1) {
-		u64 ts;
-		ktime_t start, end;
-
-		start = sync->target();
-		ts = timecounter_read(sync->source);
-		end = sync->target();
-
-		if (!i)
-			start_source = ts;
-
-		/* ignore negative durations */
-		sample.duration_target = ktime_to_ns(ktime_sub(end, start));
-		if (sample.duration_target >= 0) {
-			/*
-			 * assume symetric delay to and from source:
-			 * average target time corresponds to measured
-			 * source time
-			 */
-			sample.offset =
-				(ktime_to_ns(end) + ktime_to_ns(start)) / 2 -
-				ts;
-
-			/* simple insertion sort based on duration */
-			index = counter - 1;
-			while (index >= 0) {
-				if (samples[index].duration_target <
-				    sample.duration_target)
-					break;
-				samples[index + 1] = samples[index];
-				index--;
-			}
-			samples[index + 1] = sample;
-			counter++;
-		}
-
-		i++;
-		if (counter >= num_samples || i >= 100000) {
-			end_source = ts;
-			break;
-		}
-	}
-
-	*source_tstamp = (end_source + start_source) / 2;
-
-	/* remove outliers by only using 75% of the samples */
-	used = counter * 3 / 4;
-	if (!used)
-		used = counter;
-	if (used) {
-		/* calculate average */
-		s64 off = 0;
-		for (index = 0; index < used; index++)
-			off += samples[index].offset;
-		*offset = div_s64(off, used);
-	}
-
-	if (samples && samples != buffer)
-		kfree(samples);
-
-	return used;
-}
-EXPORT_SYMBOL_GPL(timecompare_offset);
-
-void __timecompare_update(struct timecompare *sync,
-			  u64 source_tstamp)
-{
-	s64 offset;
-	u64 average_time;
-
-	if (!timecompare_offset(sync, &offset, &average_time))
-		return;
-
-	if (!sync->last_update) {
-		sync->last_update = average_time;
-		sync->offset = offset;
-		sync->skew = 0;
-	} else {
-		s64 delta_nsec = average_time - sync->last_update;
-
-		/* avoid division by negative or small deltas */
-		if (delta_nsec >= 10000) {
-			s64 delta_offset_nsec = offset - sync->offset;
-			s64 skew; /* delta_offset_nsec *
-				     TIMECOMPARE_SKEW_RESOLUTION /
-				     delta_nsec */
-			u64 divisor;
-
-			/* div_s64() is limited to 32 bit divisor */
-			skew = delta_offset_nsec * TIMECOMPARE_SKEW_RESOLUTION;
-			divisor = delta_nsec;
-			while (unlikely(divisor >= ((s64)1) << 32)) {
-				/* divide both by 2; beware, right shift
-				   of negative value has undefined
-				   behavior and can only be used for
-				   the positive divisor */
-				skew = div_s64(skew, 2);
-				divisor >>= 1;
-			}
-			skew = div_s64(skew, divisor);
-
-			/*
-			 * Calculate new overall skew as 4/16 the
-			 * old value and 12/16 the new one. This is
-			 * a rather arbitrary tradeoff between
-			 * only using the latest measurement (0/16 and
-			 * 16/16) and even more weight on past measurements.
-			 */
-#define TIMECOMPARE_NEW_SKEW_PER_16 12
-			sync->skew =
-				div_s64((16 - TIMECOMPARE_NEW_SKEW_PER_16) *
-					sync->skew +
-					TIMECOMPARE_NEW_SKEW_PER_16 * skew,
-					16);
-			sync->last_update = average_time;
-			sync->offset = offset;
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(__timecompare_update);
-- 
cgit v1.2.3-55-g7522


From 6b60393e08f9263c7b129d54eeb261e8f970175c Mon Sep 17 00:00:00 2001
From: Richard Cochran
Date: Mon, 29 Oct 2012 08:45:17 +0000
Subject: cpsw: add a DT field for the cpts offset

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/cpsw.txt | 3 +++
 drivers/net/ethernet/ti/cpsw.c                 | 7 +++++++
 include/linux/platform_data/cpsw.h             | 1 +
 3 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index 3af47b78caea..dba014fc5e7b 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -16,6 +16,7 @@ Required properties:
 - ale_entries		: Specifies No of entries ALE can hold
 - host_port_reg_ofs	: Specifies host port register offset
 - hw_stats_reg_ofs	: Specifies hardware statistics register offset
+- cpts_reg_ofs		: Specifies the offset of the CPTS registers
 - bd_ram_ofs		: Specifies internal desciptor RAM offset
 - bd_ram_size		: Specifies internal descriptor RAM size
 - rx_descs		: Specifies number of Rx descriptors
@@ -52,6 +53,7 @@ Examples:
 		ale_entries = <1024>;
 		host_port_reg_ofs = <0x108>;
 		hw_stats_reg_ofs = <0x900>;
+		cpts_reg_ofs = <0xc00>;
 		bd_ram_ofs = <0x2000>;
 		bd_ram_size = <0x2000>;
 		no_bd_ram = <0>;
@@ -86,6 +88,7 @@ Examples:
 		ale_entries = <1024>;
 		host_port_reg_ofs = <0x108>;
 		hw_stats_reg_ofs = <0x900>;
+		cpts_reg_ofs = <0xc00>;
 		bd_ram_ofs = <0x2000>;
 		bd_ram_size = <0x2000>;
 		no_bd_ram = <0>;
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 588f5c340490..f1af5e08cabb 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -912,6 +912,13 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 	}
 	data->hw_stats_reg_ofs = prop;
 
+	if (of_property_read_u32(node, "cpts_reg_ofs", &prop)) {
+		pr_err("Missing cpts_reg_ofs property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->cpts_reg_ofs = prop;
+
 	if (of_property_read_u32(node, "bd_ram_ofs", &prop)) {
 		pr_err("Missing bd_ram_ofs property in the DT.\n");
 		ret = -EINVAL;
diff --git a/include/linux/platform_data/cpsw.h b/include/linux/platform_data/cpsw.h
index c4e23d029498..a052b1dca957 100644
--- a/include/linux/platform_data/cpsw.h
+++ b/include/linux/platform_data/cpsw.h
@@ -41,6 +41,7 @@ struct cpsw_platform_data {
 	u32     host_port_num; /* The port number for the host port */
 
 	u32	hw_stats_reg_ofs;  /* cpsw hardware statistics counters */
+	u32	cpts_reg_ofs;      /* cpts registers */
 
 	u32	bd_ram_ofs;   /* embedded buffer descriptor RAM offset*/
 	u32	bd_ram_size;  /*buffer descriptor ram size */
-- 
cgit v1.2.3-55-g7522


From 78ca0b287314ad6b7b06161b3ff9b13e8a8bcce0 Mon Sep 17 00:00:00 2001
From: Richard Cochran
Date: Mon, 29 Oct 2012 08:45:18 +0000
Subject: cpsw: add a DT field for the active time stamping port

Because time stamping on both external ports of the switch simultaneously
is positively useless from the application's point of view, this patch
provides a DT configuration method to choose the active port.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/cpsw.txt | 3 +++
 drivers/net/ethernet/ti/cpsw.c                 | 7 +++++++
 include/linux/platform_data/cpsw.h             | 1 +
 3 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index dba014fc5e7b..9f61f2b51681 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -23,6 +23,7 @@ Required properties:
 - mac_control		: Specifies Default MAC control register content
 			  for the specific platform
 - slaves		: Specifies number for slaves
+- cpts_active_slave	: Specifies the slave to use for time stamping
 - slave_reg_ofs		: Specifies slave register offset
 - sliver_reg_ofs	: Specifies slave sliver register offset
 - phy_id		: Specifies slave phy id
@@ -60,6 +61,7 @@ Examples:
 		rx_descs = <64>;
 		mac_control = <0x20>;
 		slaves = <2>;
+		cpts_active_slave = <0>;
 		cpsw_emac0: slave@0 {
 			slave_reg_ofs = <0x200>;
 			sliver_reg_ofs = <0xd80>;
@@ -95,6 +97,7 @@ Examples:
 		rx_descs = <64>;
 		mac_control = <0x20>;
 		slaves = <2>;
+		cpts_active_slave = <0>;
 		cpsw_emac0: slave@0 {
 			slave_reg_ofs = <0x200>;
 			sliver_reg_ofs = <0xd80>;
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index f1af5e08cabb..f16579123c1b 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -847,6 +847,13 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 	}
 	data->slaves = prop;
 
+	if (of_property_read_u32(node, "cpts_active_slave", &prop)) {
+		pr_err("Missing cpts_active_slave property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->cpts_active_slave = prop;
+
 	data->slave_data = kzalloc(sizeof(struct cpsw_slave_data) *
 				   data->slaves, GFP_KERNEL);
 	if (!data->slave_data) {
diff --git a/include/linux/platform_data/cpsw.h b/include/linux/platform_data/cpsw.h
index a052b1dca957..15a077eb0689 100644
--- a/include/linux/platform_data/cpsw.h
+++ b/include/linux/platform_data/cpsw.h
@@ -33,6 +33,7 @@ struct cpsw_platform_data {
 
 	u32	slaves;		/* number of slave cpgmac ports */
 	struct cpsw_slave_data	*slave_data;
+	u32	cpts_active_slave; /* time stamping slave */
 
 	u32	ale_reg_ofs;	/* address lookup engine reg offset */
 	u32	ale_entries;	/* ale table size */
-- 
cgit v1.2.3-55-g7522


From 00ab94eeaf6c1ad38ad7368c5148fed31403c8a2 Mon Sep 17 00:00:00 2001
From: Richard Cochran
Date: Mon, 29 Oct 2012 08:45:19 +0000
Subject: cpts: specify the input clock frequency via DT

This patch adds a way to configure the CPTS input clock scaling factors
via the device tree.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/cpsw.txt |  6 ++++++
 drivers/net/ethernet/ti/cpsw.c                 | 14 ++++++++++++++
 include/linux/platform_data/cpsw.h             |  2 ++
 3 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index 9f61f2b51681..221460714c56 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -24,6 +24,8 @@ Required properties:
 			  for the specific platform
 - slaves		: Specifies number for slaves
 - cpts_active_slave	: Specifies the slave to use for time stamping
+- cpts_clock_mult	: Numerator to convert input clock ticks into nanoseconds
+- cpts_clock_shift	: Denominator to convert input clock ticks into nanoseconds
 - slave_reg_ofs		: Specifies slave register offset
 - sliver_reg_ofs	: Specifies slave sliver register offset
 - phy_id		: Specifies slave phy id
@@ -62,6 +64,8 @@ Examples:
 		mac_control = <0x20>;
 		slaves = <2>;
 		cpts_active_slave = <0>;
+		cpts_clock_mult = <0x80000000>;
+		cpts_clock_shift = <29>;
 		cpsw_emac0: slave@0 {
 			slave_reg_ofs = <0x200>;
 			sliver_reg_ofs = <0xd80>;
@@ -98,6 +102,8 @@ Examples:
 		mac_control = <0x20>;
 		slaves = <2>;
 		cpts_active_slave = <0>;
+		cpts_clock_mult = <0x80000000>;
+		cpts_clock_shift = <29>;
 		cpsw_emac0: slave@0 {
 			slave_reg_ofs = <0x200>;
 			sliver_reg_ofs = <0xd80>;
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index f16579123c1b..c04627cd60dd 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -854,6 +854,20 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 	}
 	data->cpts_active_slave = prop;
 
+	if (of_property_read_u32(node, "cpts_clock_mult", &prop)) {
+		pr_err("Missing cpts_clock_mult property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->cpts_clock_mult = prop;
+
+	if (of_property_read_u32(node, "cpts_clock_shift", &prop)) {
+		pr_err("Missing cpts_clock_shift property in the DT.\n");
+		ret = -EINVAL;
+		goto error_ret;
+	}
+	data->cpts_clock_shift = prop;
+
 	data->slave_data = kzalloc(sizeof(struct cpsw_slave_data) *
 				   data->slaves, GFP_KERNEL);
 	if (!data->slave_data) {
diff --git a/include/linux/platform_data/cpsw.h b/include/linux/platform_data/cpsw.h
index 15a077eb0689..b5c16c3df458 100644
--- a/include/linux/platform_data/cpsw.h
+++ b/include/linux/platform_data/cpsw.h
@@ -34,6 +34,8 @@ struct cpsw_platform_data {
 	u32	slaves;		/* number of slave cpgmac ports */
 	struct cpsw_slave_data	*slave_data;
 	u32	cpts_active_slave; /* time stamping slave */
+	u32	cpts_clock_mult;  /* convert input clock ticks to nanoseconds */
+	u32	cpts_clock_shift; /* convert input clock ticks to nanoseconds */
 
 	u32	ale_reg_ofs;	/* address lookup engine reg offset */
 	u32	ale_entries;	/* ale table size */
-- 
cgit v1.2.3-55-g7522


From cc535dfb6a85b42218307c43f60668d7bd6f4318 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Mon, 29 Oct 2012 04:53:27 +0000
Subject: rtnl/ipv4: use netconf msg to advertise rp_filter status

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/netconf.h |  1 +
 net/ipv4/devinet.c           | 24 ++++++++++++++++++++++++
 2 files changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
index d0513726711f..75dcbc587fb5 100644
--- a/include/uapi/linux/netconf.h
+++ b/include/uapi/linux/netconf.h
@@ -12,6 +12,7 @@ enum {
 	NETCONFA_UNSPEC,
 	NETCONFA_IFINDEX,
 	NETCONFA_FORWARDING,
+	NETCONFA_RP_FILTER,
 	__NETCONFA_MAX
 };
 #define NETCONFA_MAX	(__NETCONFA_MAX - 1)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f8b1e0494d75..f6db227c1fd9 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1451,6 +1451,8 @@ static int inet_netconf_msgsize_devconf(int type)
 	/* type -1 is used for ALL */
 	if (type == -1 || type == NETCONFA_FORWARDING)
 		size += nla_total_size(4);
+	if (type == -1 || type == NETCONFA_RP_FILTER)
+		size += nla_total_size(4);
 
 	return size;
 }
@@ -1479,6 +1481,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	    nla_put_s32(skb, NETCONFA_FORWARDING,
 			IPV4_DEVCONF(*devconf, FORWARDING)) < 0)
 		goto nla_put_failure;
+	if ((type == -1 || type == NETCONFA_RP_FILTER) &&
+	    nla_put_s32(skb, NETCONFA_RP_FILTER,
+			IPV4_DEVCONF(*devconf, RP_FILTER)) < 0)
+		goto nla_put_failure;
 
 	return nlmsg_end(skb, nlh);
 
@@ -1515,6 +1521,7 @@ errout:
 static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
 	[NETCONFA_IFINDEX]	= { .len = sizeof(int) },
 	[NETCONFA_FORWARDING]	= { .len = sizeof(int) },
+	[NETCONFA_RP_FILTER]	= { .len = sizeof(int) },
 };
 
 static int inet_netconf_get_devconf(struct sk_buff *in_skb,
@@ -1647,6 +1654,23 @@ static int devinet_conf_proc(ctl_table *ctl, int write,
 		    i == IPV4_DEVCONF_ROUTE_LOCALNET - 1)
 			if ((new_value == 0) && (old_value != 0))
 				rt_cache_flush(net);
+		if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
+		    new_value != old_value) {
+			int ifindex;
+
+			if (cnf == net->ipv4.devconf_dflt)
+				ifindex = NETCONFA_IFINDEX_DEFAULT;
+			else if (cnf == net->ipv4.devconf_all)
+				ifindex = NETCONFA_IFINDEX_ALL;
+			else {
+				struct in_device *idev =
+					container_of(cnf, struct in_device,
+						     cnf);
+				ifindex = idev->dev->ifindex;
+			}
+			inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER,
+						    ifindex, cnf);
+		}
 	}
 
 	return ret;
-- 
cgit v1.2.3-55-g7522


From 711584ea4c8ce47045c8ed4da3d6c6fdf513db92 Mon Sep 17 00:00:00 2001
From: Denis Kirjanov
Date: Mon, 22 Oct 2012 17:22:01 +0400
Subject: Bluetooth:Replace list_for_each with list_for_each_entry() helper

Replace list_for_each with list_for_each_entry() helper

Signed-off-by: Denis Kirjanov <kirjanov@gmail.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 5ab80b7e8369..c885e545e651 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -880,7 +880,7 @@ struct hci_cb {
 
 static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status)
 {
-	struct list_head *p;
+	struct hci_cb *cb;
 	__u8 encrypt;
 
 	hci_proto_auth_cfm(conn, status);
@@ -891,8 +891,7 @@ static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status)
 	encrypt = (conn->link_mode & HCI_LM_ENCRYPT) ? 0x01 : 0x00;
 
 	read_lock(&hci_cb_list_lock);
-	list_for_each(p, &hci_cb_list) {
-		struct hci_cb *cb = list_entry(p, struct hci_cb, list);
+	list_for_each_entry(cb, &hci_cb_list, list) {
 		if (cb->security_cfm)
 			cb->security_cfm(conn, status, encrypt);
 	}
@@ -902,7 +901,7 @@ static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status)
 static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status,
 								__u8 encrypt)
 {
-	struct list_head *p;
+	struct hci_cb *cb;
 
 	if (conn->sec_level == BT_SECURITY_SDP)
 		conn->sec_level = BT_SECURITY_LOW;
@@ -913,8 +912,7 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status,
 	hci_proto_encrypt_cfm(conn, status, encrypt);
 
 	read_lock(&hci_cb_list_lock);
-	list_for_each(p, &hci_cb_list) {
-		struct hci_cb *cb = list_entry(p, struct hci_cb, list);
+	list_for_each_entry(cb, &hci_cb_list, list) {
 		if (cb->security_cfm)
 			cb->security_cfm(conn, status, encrypt);
 	}
@@ -923,11 +921,10 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status,
 
 static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status)
 {
-	struct list_head *p;
+	struct hci_cb *cb;
 
 	read_lock(&hci_cb_list_lock);
-	list_for_each(p, &hci_cb_list) {
-		struct hci_cb *cb = list_entry(p, struct hci_cb, list);
+	list_for_each_entry(cb, &hci_cb_list, list) {
 		if (cb->key_change_cfm)
 			cb->key_change_cfm(conn, status);
 	}
@@ -937,11 +934,10 @@ static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status)
 static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status,
 								__u8 role)
 {
-	struct list_head *p;
+	struct hci_cb *cb;
 
 	read_lock(&hci_cb_list_lock);
-	list_for_each(p, &hci_cb_list) {
-		struct hci_cb *cb = list_entry(p, struct hci_cb, list);
+	list_for_each_entry(cb, &hci_cb_list, list) {
 		if (cb->role_switch_cfm)
 			cb->role_switch_cfm(conn, status, role);
 	}
-- 
cgit v1.2.3-55-g7522


From 761f09e4d6d2bfe4a517d14ca28aec041c8a7415 Mon Sep 17 00:00:00 2001
From: Johan Hedberg
Date: Wed, 24 Oct 2012 21:12:00 +0300
Subject: Bluetooth: Add missing feature test macros

This patch adds missing feature test macros needed for various use cases
and also sorts the macros according to the feature bit location in the
feature mask (for easy lookup).

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index c885e545e651..6642b3c91d33 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -750,18 +750,28 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define SET_HCIDEV_DEV(hdev, pdev) ((hdev)->dev.parent = (pdev))
 
 /* ----- LMP capabilities ----- */
-#define lmp_rswitch_capable(dev)   ((dev)->features[0] & LMP_RSWITCH)
 #define lmp_encrypt_capable(dev)   ((dev)->features[0] & LMP_ENCRYPT)
+#define lmp_rswitch_capable(dev)   ((dev)->features[0] & LMP_RSWITCH)
+#define lmp_hold_capable(dev)      ((dev)->features[0] & LMP_HOLD)
 #define lmp_sniff_capable(dev)     ((dev)->features[0] & LMP_SNIFF)
-#define lmp_sniffsubr_capable(dev) ((dev)->features[5] & LMP_SNIFF_SUBR)
+#define lmp_park_capable(dev)      ((dev)->features[1] & LMP_PARK)
+#define lmp_inq_rssi_capable(dev)  ((dev)->features[3] & LMP_RSSI_INQ)
 #define lmp_esco_capable(dev)      ((dev)->features[3] & LMP_ESCO)
+#define lmp_bredr_capable(dev)     (!((dev)->features[4] & LMP_NO_BREDR))
+#define lmp_le_capable(dev)        ((dev)->features[4] & LMP_LE)
+#define lmp_sniffsubr_capable(dev) ((dev)->features[5] & LMP_SNIFF_SUBR)
+#define lmp_pause_enc_capable(dev) ((dev)->features[5] & LMP_PAUSE_ENC)
+#define lmp_ext_inq_capable(dev)   ((dev)->features[6] & LMP_EXT_INQ)
+#define lmp_le_br_capable(dev)     ((dev)->features[6] & LMP_SIMUL_LE_BR)
 #define lmp_ssp_capable(dev)       ((dev)->features[6] & LMP_SIMPLE_PAIR)
 #define lmp_no_flush_capable(dev)  ((dev)->features[6] & LMP_NO_FLUSH)
-#define lmp_le_capable(dev)        ((dev)->features[4] & LMP_LE)
-#define lmp_bredr_capable(dev)     (!((dev)->features[4] & LMP_NO_BREDR))
+#define lmp_lsto_capable(dev)      ((dev)->features[7] & LMP_LSTO)
+#define lmp_inq_tx_pwr_capable(dev) ((dev)->features[7] & LMP_INQ_TX_PWR)
+#define lmp_ext_feat_capable(dev)  ((dev)->features[7] & LMP_EXTFEATURES)
 
 /* ----- Extended LMP capabilities ----- */
 #define lmp_host_le_capable(dev)   ((dev)->host_features[0] & LMP_HOST_LE)
+#define lmp_host_le_br_capable(dev) ((dev)->host_features[0] & LMP_HOST_LE_BREDR)
 
 /* ----- HCI protocols ----- */
 static inline int hci_proto_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr,
-- 
cgit v1.2.3-55-g7522


From 33f8f5269ea7c220e18a15959dad2b42e1b61051 Mon Sep 17 00:00:00 2001
From: Johan Hedberg
Date: Wed, 24 Oct 2012 21:12:02 +0300
Subject: Bluetooth: Add flag for LE GAP Peripheral role

This patch adds a flag to be used for LE GAP Peripheral role. In this
role undirected advertising will be enabled and operations not allowed
in Peripheral role (such as scanning and initiating connections) will be
disallowed.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 348f4bfeaadb..6c414f4302fe 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -115,6 +115,7 @@ enum {
 	HCI_SSP_ENABLED,
 	HCI_HS_ENABLED,
 	HCI_LE_ENABLED,
+	HCI_LE_PERIPHERAL,
 	HCI_CONNECTABLE,
 	HCI_DISCOVERABLE,
 	HCI_LINK_SECURITY,
-- 
cgit v1.2.3-55-g7522


From 6b4b73ee75bd65c4a47b1a323cb7c5180a6d2ea7 Mon Sep 17 00:00:00 2001
From: Johan Hedberg
Date: Thu, 25 Oct 2012 00:09:52 +0300
Subject: Bluetooth: Fix sending unnecessary HCI_Write_SSP_Mode command

This patch fixes sending an unnecessary HCI_Write_SSP_Mode command if
the command has already been sent as part of the default HCI init
sequence.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 1 +
 net/bluetooth/mgmt.c             | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 6642b3c91d33..b3490c634db7 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -770,6 +770,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define lmp_ext_feat_capable(dev)  ((dev)->features[7] & LMP_EXTFEATURES)
 
 /* ----- Extended LMP capabilities ----- */
+#define lmp_host_ssp_capable(dev)  ((dev)->host_features[0] & LMP_HOST_SSP)
 #define lmp_host_le_capable(dev)   ((dev)->host_features[0] & LMP_HOST_LE)
 #define lmp_host_le_br_capable(dev) ((dev)->host_features[0] & LMP_HOST_LE_BREDR)
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 585654bd250f..9017287224d3 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2913,7 +2913,8 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered)
 	mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match);
 
 	if (powered) {
-		if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) {
+		if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags) &&
+		    !lmp_host_ssp_capable(hdev)) {
 			u8 ssp = 1;
 
 			hci_send_cmd(hdev, HCI_OP_WRITE_SSP_MODE, 1, &ssp);
-- 
cgit v1.2.3-55-g7522


From 27695fb415ab150e1972a882c2538bf9bf130cb0 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 25 Oct 2012 15:20:45 +0300
Subject: Bluetooth: AMP: Process Logical Link complete evt

After receiving HCI Logical Link Complete event finish EFS
configuration by sending L2CAP Conf Response with success code.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h |  2 ++
 net/bluetooth/hci_event.c     | 42 ++++++++++++++++++++++++++++++++++++++++++
 net/bluetooth/l2cap_core.c    |  4 ++--
 3 files changed, 46 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 49783e948856..24c61ef933b5 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -810,5 +810,7 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
 void l2cap_chan_del(struct l2cap_chan *chan, int err);
 void l2cap_send_conn_req(struct l2cap_chan *chan);
 void l2cap_move_start(struct l2cap_chan *chan);
+void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
+		       u8 status);
 
 #endif /* __L2CAP_H */
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index d2c45591f06d..aa79ed278959 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3695,6 +3695,44 @@ static void hci_phy_link_complete_evt(struct hci_dev *hdev,
 	}
 }
 
+static void hci_loglink_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_ev_logical_link_complete *ev = (void *) skb->data;
+	struct hci_conn *hcon;
+	struct hci_chan *hchan;
+	struct amp_mgr *mgr;
+
+	BT_DBG("%s log_handle 0x%4.4x phy_handle 0x%2.2x status 0x%2.2x",
+	       hdev->name, le16_to_cpu(ev->handle), ev->phy_handle,
+	       ev->status);
+
+	hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle);
+	if (!hcon)
+		return;
+
+	/* Create AMP hchan */
+	hchan = hci_chan_create(hcon);
+	if (!hchan)
+		return;
+
+	hchan->handle = le16_to_cpu(ev->handle);
+
+	BT_DBG("hcon %p mgr %p hchan %p", hcon, hcon->amp_mgr, hchan);
+
+	mgr = hcon->amp_mgr;
+	if (mgr && mgr->bredr_chan) {
+		struct l2cap_chan *bredr_chan = mgr->bredr_chan;
+
+		l2cap_chan_lock(bredr_chan);
+
+		bredr_chan->conn->mtu = hdev->block_mtu;
+		l2cap_logical_cfm(bredr_chan, hchan, 0);
+		hci_conn_hold(hcon);
+
+		l2cap_chan_unlock(bredr_chan);
+	}
+}
+
 static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_le_conn_complete *ev = (void *) skb->data;
@@ -4026,6 +4064,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_phy_link_complete_evt(hdev, skb);
 		break;
 
+	case HCI_EV_LOGICAL_LINK_COMPLETE:
+		hci_loglink_complete_evt(hdev, skb);
+		break;
+
 	case HCI_EV_NUM_COMP_BLOCKS:
 		hci_num_comp_blocks_evt(hdev, skb);
 		break;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 600d8080f234..d1728af8e84f 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4428,8 +4428,8 @@ static void l2cap_logical_finish_move(struct l2cap_chan *chan,
 }
 
 /* Call with chan locked */
-static void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
-			      u8 status)
+void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
+		       u8 status)
 {
 	BT_DBG("chan %p, hchan %p, status %d", chan, hchan, status);
 
-- 
cgit v1.2.3-55-g7522


From 5ce66b59d787478f57a6f3368ff23d75a06e76e2 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Wed, 31 Oct 2012 15:46:30 +0200
Subject: Bluetooth: AMP: Add Logical Link Create function

After physical link is created logical link needs to be created.
The process starts after L2CAP channel is created and L2CAP
Configuration Response with result PENDING is received.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h |  1 +
 net/bluetooth/amp.c         | 49 +++++++++++++++++++++++++++++++++++++++++++++
 net/bluetooth/hci_event.c   |  9 +++++++++
 net/bluetooth/l2cap_core.c  | 19 +++++++++++++-----
 4 files changed, 73 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index 2e7c79ea0463..70d5c153de15 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -46,5 +46,6 @@ void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 			struct hci_conn *hcon);
 void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle);
 void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle);
+void amp_create_logical_link(struct l2cap_chan *chan);
 
 #endif /* __AMP_H */
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 231d7ef53ecb..fbb63605a27e 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -372,3 +372,52 @@ void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 
 	hci_send_cmd(hdev, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp);
 }
+
+void amp_create_logical_link(struct l2cap_chan *chan)
+{
+	struct hci_cp_create_accept_logical_link cp;
+	struct hci_conn *hcon;
+	struct hci_dev *hdev;
+
+	BT_DBG("chan %p", chan);
+
+	if (!chan->hs_hcon)
+		return;
+
+	hdev = hci_dev_hold(chan->hs_hcon->hdev);
+	if (!hdev)
+		return;
+
+	BT_DBG("chan %p ctrl_id %d dst %pMR", chan, chan->ctrl_id,
+	       chan->conn->dst);
+
+	hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, chan->conn->dst);
+	if (!hcon)
+		goto done;
+
+	cp.phy_handle = hcon->handle;
+
+	cp.tx_flow_spec.id = chan->local_id;
+	cp.tx_flow_spec.stype = chan->local_stype;
+	cp.tx_flow_spec.msdu = cpu_to_le16(chan->local_msdu);
+	cp.tx_flow_spec.sdu_itime = cpu_to_le32(chan->local_sdu_itime);
+	cp.tx_flow_spec.acc_lat = cpu_to_le32(chan->local_acc_lat);
+	cp.tx_flow_spec.flush_to = cpu_to_le32(chan->local_flush_to);
+
+	cp.rx_flow_spec.id = chan->remote_id;
+	cp.rx_flow_spec.stype = chan->remote_stype;
+	cp.rx_flow_spec.msdu = cpu_to_le16(chan->remote_msdu);
+	cp.rx_flow_spec.sdu_itime = cpu_to_le32(chan->remote_sdu_itime);
+	cp.rx_flow_spec.acc_lat = cpu_to_le32(chan->remote_acc_lat);
+	cp.rx_flow_spec.flush_to = cpu_to_le32(chan->remote_flush_to);
+
+	if (hcon->out)
+		hci_send_cmd(hdev, HCI_OP_CREATE_LOGICAL_LINK, sizeof(cp),
+			     &cp);
+	else
+		hci_send_cmd(hdev, HCI_OP_ACCEPT_LOGICAL_LINK, sizeof(cp),
+			     &cp);
+
+done:
+	hci_dev_put(hdev);
+}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index c4e10e656c68..14cad155af3c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1835,6 +1835,11 @@ static void hci_cs_accept_phylink(struct hci_dev *hdev, u8 status)
 	amp_write_remote_assoc(hdev, cp->phy_handle);
 }
 
+static void hci_cs_create_logical_link(struct hci_dev *hdev, u8 status)
+{
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+}
+
 static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 status = *((__u8 *) skb->data);
@@ -2669,6 +2674,10 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cs_accept_phylink(hdev, ev->status);
 		break;
 
+	case HCI_OP_CREATE_LOGICAL_LINK:
+		hci_cs_create_logical_link(hdev, ev->status);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode);
 		break;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 782e49c97e7e..ecc5020c9242 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -38,6 +38,7 @@
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/smp.h>
 #include <net/bluetooth/a2mp.h>
+#include <net/bluetooth/amp.h>
 
 bool disable_ertm;
 
@@ -1013,6 +1014,12 @@ static bool __amp_capable(struct l2cap_chan *chan)
 		return false;
 }
 
+static bool l2cap_check_efs(struct l2cap_chan *chan)
+{
+	/* Check EFS parameters */
+	return true;
+}
+
 void l2cap_send_conn_req(struct l2cap_chan *chan)
 {
 	struct l2cap_conn *conn = chan->conn;
@@ -3957,13 +3964,15 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn,
 				goto done;
 			}
 
-			/* check compatibility */
-
-			if (!chan->ctrl_id)
+			if (!chan->ctrl_id) {
 				l2cap_send_efs_conf_rsp(chan, buf, cmd->ident,
 							0);
-			else
-				chan->ident = cmd->ident;
+			} else {
+				if (l2cap_check_efs(chan)) {
+					amp_create_logical_link(chan);
+					chan->ident = cmd->ident;
+				}
+			}
 		}
 		goto done;
 
-- 
cgit v1.2.3-55-g7522


From 606e2a10a6d23e900dad0b098a09438a5f7e0495 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Wed, 31 Oct 2012 15:46:31 +0200
Subject: Bluetooth: AMP: Process Disc Logical Link

Add processing for HCI Disconnection Logical Link Complete
Event.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h |  1 +
 net/bluetooth/amp.c         |  7 +++++++
 net/bluetooth/hci_event.c   | 28 ++++++++++++++++++++++++++++
 3 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index 70d5c153de15..405fb9c987ef 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -47,5 +47,6 @@ void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle);
 void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle);
 void amp_create_logical_link(struct l2cap_chan *chan);
+void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason);
 
 #endif /* __AMP_H */
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index fbb63605a27e..0f3fef34eabc 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -421,3 +421,10 @@ void amp_create_logical_link(struct l2cap_chan *chan)
 done:
 	hci_dev_put(hdev);
 }
+
+void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason)
+{
+	BT_DBG("hchan %p", hchan);
+
+	hci_chan_del(hchan);
+}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 14cad155af3c..07dce614f81a 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3741,6 +3741,30 @@ static void hci_loglink_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 }
 
+static void hci_disconn_loglink_complete_evt(struct hci_dev *hdev,
+					     struct sk_buff *skb)
+{
+	struct hci_ev_disconn_logical_link_complete *ev = (void *) skb->data;
+	struct hci_chan *hchan;
+
+	BT_DBG("%s log handle 0x%4.4x status 0x%2.2x", hdev->name,
+	       le16_to_cpu(ev->handle), ev->status);
+
+	if (ev->status)
+		return;
+
+	hci_dev_lock(hdev);
+
+	hchan = hci_chan_lookup_handle(hdev, le16_to_cpu(ev->handle));
+	if (!hchan)
+		goto unlock;
+
+	amp_destroy_logical_link(hchan, ev->reason);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_le_conn_complete *ev = (void *) skb->data;
@@ -4076,6 +4100,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_loglink_complete_evt(hdev, skb);
 		break;
 
+	case HCI_EV_DISCONN_LOGICAL_LINK_COMPLETE:
+		hci_disconn_loglink_complete_evt(hdev, skb);
+		break;
+
 	case HCI_EV_NUM_COMP_BLOCKS:
 		hci_num_comp_blocks_evt(hdev, skb);
 		break;
-- 
cgit v1.2.3-55-g7522


From 419e08c1121ab346bf5f66fe0a21950529355cee Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Wed, 31 Oct 2012 15:46:34 +0200
Subject: Bluetooth: Disconnect logical link when deleting chan

Disconnect logical link for high speed channel hs_hchan
associated with L2CAP channel chan.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h |  1 +
 net/bluetooth/amp.c         | 14 ++++++++++++++
 net/bluetooth/l2cap_core.c  |  7 +++++++
 3 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index 405fb9c987ef..f1c0017f69e7 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -47,6 +47,7 @@ void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle);
 void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle);
 void amp_create_logical_link(struct l2cap_chan *chan);
+void amp_disconnect_logical_link(struct hci_chan *hchan);
 void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason);
 
 #endif /* __AMP_H */
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 0f3fef34eabc..917e034b9aa5 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -422,6 +422,20 @@ done:
 	hci_dev_put(hdev);
 }
 
+void amp_disconnect_logical_link(struct hci_chan *hchan)
+{
+	struct hci_conn *hcon = hchan->conn;
+	struct hci_cp_disconn_logical_link cp;
+
+	if (hcon->state != BT_CONNECTED) {
+		BT_DBG("hchan %p not connected", hchan);
+		return;
+	}
+
+	cp.log_handle = cpu_to_le16(hchan->handle);
+	hci_send_cmd(hcon->hdev, HCI_OP_DISCONN_LOGICAL_LINK, sizeof(cp), &cp);
+}
+
 void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason)
 {
 	BT_DBG("hchan %p", hchan);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ecc5020c9242..bb2cd9eaa8a1 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -578,6 +578,13 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err)
 			mgr->bredr_chan = NULL;
 	}
 
+	if (chan->hs_hchan) {
+		struct hci_chan *hs_hchan = chan->hs_hchan;
+
+		BT_DBG("chan %p disconnect hs_hchan %p", chan, hs_hchan);
+		amp_disconnect_logical_link(hs_hchan);
+	}
+
 	chan->ops->teardown(chan, err);
 
 	if (test_bit(CONF_NOT_COMPLETE, &chan->conf_state))
-- 
cgit v1.2.3-55-g7522


From cf70ff220a918b25d383510f913de52308d04bb2 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Wed, 31 Oct 2012 15:46:36 +0200
Subject: Bluetooth: AMP: Use l2cap_physical_cfm in phylink complete evt

When receiving HCI Phylink Complete event run amp_physical_cfm
which initialize BR/EDR L2CAP channel associated with High Speed
link and run l2cap_physical_cfm which shall send L2CAP Create
Chan Request.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/amp.h   |  1 +
 include/net/bluetooth/l2cap.h |  1 +
 net/bluetooth/amp.c           | 24 ++++++++++++++++++++++++
 net/bluetooth/hci_event.c     | 15 ++-------------
 4 files changed, 28 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
index f1c0017f69e7..7ea3db77ba89 100644
--- a/include/net/bluetooth/amp.h
+++ b/include/net/bluetooth/amp.h
@@ -46,6 +46,7 @@ void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 			struct hci_conn *hcon);
 void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle);
 void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle);
+void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon);
 void amp_create_logical_link(struct l2cap_chan *chan);
 void amp_disconnect_logical_link(struct hci_chan *hchan);
 void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason);
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 24c61ef933b5..18149c8b4d1d 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -812,5 +812,6 @@ void l2cap_send_conn_req(struct l2cap_chan *chan);
 void l2cap_move_start(struct l2cap_chan *chan);
 void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
 		       u8 status);
+void l2cap_physical_cfm(struct l2cap_chan *chan, int result);
 
 #endif /* __L2CAP_H */
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 917e034b9aa5..650bb8df04fd 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -373,6 +373,30 @@ void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
 	hci_send_cmd(hdev, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp);
 }
 
+void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon)
+{
+	struct hci_dev *bredr_hdev = hci_dev_hold(bredr_hcon->hdev);
+	struct amp_mgr *mgr = hs_hcon->amp_mgr;
+	struct l2cap_chan *bredr_chan;
+
+	BT_DBG("bredr_hcon %p hs_hcon %p mgr %p", bredr_hcon, hs_hcon, mgr);
+
+	if (!bredr_hdev || !mgr || !mgr->bredr_chan)
+		return;
+
+	bredr_chan = mgr->bredr_chan;
+
+	set_bit(FLAG_EFS_ENABLE, &bredr_chan->flags);
+	bredr_chan->ctrl_id = hs_hcon->remote_id;
+	bredr_chan->hs_hcon = hs_hcon;
+	bredr_chan->conn->mtu = hs_hcon->hdev->block_mtu;
+	bredr_chan->fcs = L2CAP_FCS_NONE;
+
+	l2cap_physical_cfm(bredr_chan, 0);
+
+	hci_dev_put(bredr_hdev);
+}
+
 void amp_create_logical_link(struct l2cap_chan *chan)
 {
 	struct hci_cp_create_accept_logical_link cp;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0572f051c693..c08ac7c03711 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3696,20 +3696,9 @@ static void hci_phy_link_complete_evt(struct hci_dev *hdev,
 	hci_conn_hold_device(hcon);
 	hci_conn_add_sysfs(hcon);
 
-	hci_dev_unlock(hdev);
-
-	if (hcon->out) {
-		struct hci_dev *bredr_hdev = hci_dev_hold(bredr_hcon->hdev);
-
-		if (!bredr_hdev)
-			return;
+	amp_physical_cfm(bredr_hcon, hcon);
 
-		/* Placeholder - create chan req
-		l2cap_chan_create_cfm(bredr_hcon, hcon->remote_id);
-		*/
-
-		hci_dev_put(bredr_hdev);
-	}
+	hci_dev_unlock(hdev);
 }
 
 static void hci_loglink_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
-- 
cgit v1.2.3-55-g7522


From fffadc08ebf1f4c61bb8f9be0f1d8c3c053d815f Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 1 Nov 2012 15:37:03 +0200
Subject: Bluetooth: Rename ctrl_id to remote_amp_id

Since we have started to use local_amp_id for local AMP
Controller Id it makes sense to rename ctrl_id to remote_amp_id
since it represents remote AMP controller Id.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h | 3 +--
 net/bluetooth/a2mp.c          | 4 ++--
 net/bluetooth/amp.c           | 5 ++---
 net/bluetooth/l2cap_core.c    | 2 +-
 4 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 18149c8b4d1d..d65db459c843 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -481,6 +481,7 @@ struct l2cap_chan {
 	unsigned long	conn_state;
 	unsigned long	flags;
 
+	__u8		remote_amp_id;
 	__u8		local_amp_id;
 	__u8		move_id;
 	__u8		move_state;
@@ -518,8 +519,6 @@ struct l2cap_chan {
 	__u32		remote_acc_lat;
 	__u32		remote_flush_to;
 
-	__u8		ctrl_id;
-
 	struct delayed_work	chan_timer;
 	struct delayed_work	retrans_timer;
 	struct delayed_work	monitor_timer;
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index d5136cfb57e2..2f67d5ecc907 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -423,7 +423,7 @@ static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	BT_DBG("Created hcon %p: loc:%d -> rem:%d", hcon, hdev->id, rsp->id);
 
-	mgr->bredr_chan->ctrl_id = rsp->id;
+	mgr->bredr_chan->remote_amp_id = rsp->id;
 
 	amp_create_phylink(hdev, mgr, hcon);
 
@@ -939,7 +939,7 @@ void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status)
 		goto clean;
 
 	req->local_id = hdev->id;
-	req->remote_id = bredr_chan->ctrl_id;
+	req->remote_id = bredr_chan->remote_amp_id;
 	memcpy(req->amp_assoc, loc_assoc->data, loc_assoc->len);
 
 	a2mp_send(mgr, A2MP_CREATEPHYSLINK_REQ, __next_ident(mgr), len, req);
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 650bb8df04fd..4b2fea6c1c2a 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -387,7 +387,7 @@ void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon)
 	bredr_chan = mgr->bredr_chan;
 
 	set_bit(FLAG_EFS_ENABLE, &bredr_chan->flags);
-	bredr_chan->ctrl_id = hs_hcon->remote_id;
+	bredr_chan->remote_amp_id = hs_hcon->remote_id;
 	bredr_chan->hs_hcon = hs_hcon;
 	bredr_chan->conn->mtu = hs_hcon->hdev->block_mtu;
 	bredr_chan->fcs = L2CAP_FCS_NONE;
@@ -412,8 +412,7 @@ void amp_create_logical_link(struct l2cap_chan *chan)
 	if (!hdev)
 		return;
 
-	BT_DBG("chan %p ctrl_id %d dst %pMR", chan, chan->ctrl_id,
-	       chan->conn->dst);
+	BT_DBG("chan %p dst %pMR", chan, chan->conn->dst);
 
 	hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, chan->conn->dst);
 	if (!hcon)
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 2f0e165eef4d..a1faaab41839 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4615,7 +4615,7 @@ static void l2cap_do_move_cancel(struct l2cap_chan *chan, int result)
 void l2cap_physical_cfm(struct l2cap_chan *chan, int result)
 {
 	u8 local_amp_id = chan->local_amp_id;
-	u8 remote_amp_id = chan->ctrl_id;
+	u8 remote_amp_id = chan->remote_amp_id;
 
 	BT_DBG("chan %p, result %d, local_amp_id %d, remote_amp_id %d",
 	       chan, result, local_amp_id, remote_amp_id);
-- 
cgit v1.2.3-55-g7522


From 0c0afedf55ff409be9db0b0aeeaa1c6fe0f3cd3c Mon Sep 17 00:00:00 2001
From: Johan Hedberg
Date: Thu, 1 Nov 2012 13:27:26 +0200
Subject: Bluetooth: Fix parameter order of hci_get_route

The actual parameter order of hci_get_route is (dst, src) and not (src,
dst). All current callers use the right order but the header file shows
the parameters in the wrong order.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index b3490c634db7..ce6dbeb6dfb6 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -685,7 +685,7 @@ static inline uint8_t __hci_num_ctrl(void)
 }
 
 struct hci_dev *hci_dev_get(int index);
-struct hci_dev *hci_get_route(bdaddr_t *src, bdaddr_t *dst);
+struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src);
 
 struct hci_dev *hci_alloc_dev(void);
 void hci_free_dev(struct hci_dev *hdev);
-- 
cgit v1.2.3-55-g7522


From 121d1e0941e05c64ee4223064dd83eb24e871739 Mon Sep 17 00:00:00 2001
From: Florian Westphal
Date: Tue, 30 Oct 2012 01:08:49 +0000
Subject: netfilter: ipv6: add getsockopt to retrieve origdst

userspace can query the original ipv4 destination address of a REDIRECTed
connection via
getsockopt(m_sock, SOL_IP, SO_ORIGINAL_DST, &m_server_addr, &addrsize)

but for ipv6 no such option existed.

This adds getsockopt(..., IPPROTO_IPV6, IP6T_SO_ORIGINAL_DST, ...).

Without this, userspace needs to parse /proc or use ctnetlink, which
appears to be overkill.

This uses option number 80 for IP6T_SO_ORIGINAL_DST, which is spare,
to use the same number we use in the IPv4 socket option SO_ORIGINAL_DST.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/in6.h                       |  1 +
 include/uapi/linux/netfilter_ipv6/ip6_tables.h |  3 ++
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 61 ++++++++++++++++++++++++++
 3 files changed, 65 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 1e3159989958..f79c3721da6e 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -240,6 +240,7 @@ struct in6_flowlabel_req {
  *
  * IP6T_SO_GET_REVISION_MATCH	68
  * IP6T_SO_GET_REVISION_TARGET	69
+ * IP6T_SO_ORIGINAL_DST		80
  */
 
 /* RFC5014: Source address selection */
diff --git a/include/uapi/linux/netfilter_ipv6/ip6_tables.h b/include/uapi/linux/netfilter_ipv6/ip6_tables.h
index bf1ef65cc582..649c68062dca 100644
--- a/include/uapi/linux/netfilter_ipv6/ip6_tables.h
+++ b/include/uapi/linux/netfilter_ipv6/ip6_tables.h
@@ -178,6 +178,9 @@ struct ip6t_error {
 #define IP6T_SO_GET_REVISION_TARGET	(IP6T_BASE_CTL + 5)
 #define IP6T_SO_GET_MAX			IP6T_SO_GET_REVISION_TARGET
 
+/* obtain original address if REDIRECT'd connection */
+#define IP6T_SO_ORIGINAL_DST            80
+
 /* ICMP matching stuff */
 struct ip6t_icmp {
 	__u8 type;				/* type to match */
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 8860d23e61cf..02dcafdc7a95 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -21,6 +21,7 @@
 
 #include <linux/netfilter_bridge.h>
 #include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
@@ -295,6 +296,50 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
 	},
 };
 
+static int
+ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct ipv6_pinfo *inet6 = inet6_sk(sk);
+	const struct nf_conntrack_tuple_hash *h;
+	struct sockaddr_in6 sin6;
+	struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 };
+	struct nf_conn *ct;
+
+	tuple.src.u3.in6 = inet6->rcv_saddr;
+	tuple.src.u.tcp.port = inet->inet_sport;
+	tuple.dst.u3.in6 = inet6->daddr;
+	tuple.dst.u.tcp.port = inet->inet_dport;
+	tuple.dst.protonum = sk->sk_protocol;
+
+	if (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_SCTP)
+		return -ENOPROTOOPT;
+
+	if (*len < 0 || (unsigned int) *len < sizeof(sin6))
+		return -EINVAL;
+
+	h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple);
+	if (!h) {
+		pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n",
+			 &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port),
+			 &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port));
+		return -ENOENT;
+	}
+
+	ct = nf_ct_tuplehash_to_ctrack(h);
+
+	sin6.sin6_family = AF_INET6;
+	sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
+	sin6.sin6_flowinfo = inet6->flow_label & IPV6_FLOWINFO_MASK;
+	memcpy(&sin6.sin6_addr,
+		&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6,
+					sizeof(sin6.sin6_addr));
+	sin6.sin6_scope_id = sk->sk_bound_dev_if;
+
+	nf_ct_put(ct);
+	return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0;
+}
+
 #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
 
 #include <linux/netfilter/nfnetlink.h>
@@ -359,6 +404,14 @@ MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6));
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>");
 
+static struct nf_sockopt_ops so_getorigdst6 = {
+	.pf		= NFPROTO_IPV6,
+	.get_optmin	= IP6T_SO_ORIGINAL_DST,
+	.get_optmax	= IP6T_SO_ORIGINAL_DST + 1,
+	.get		= ipv6_getorigdst,
+	.owner		= THIS_MODULE,
+};
+
 static int ipv6_net_init(struct net *net)
 {
 	int ret = 0;
@@ -425,6 +478,12 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
 	need_conntrack();
 	nf_defrag_ipv6_enable();
 
+	ret = nf_register_sockopt(&so_getorigdst6);
+	if (ret < 0) {
+		pr_err("Unable to register netfilter socket option\n");
+		return ret;
+	}
+
 	ret = register_pernet_subsys(&ipv6_net_ops);
 	if (ret < 0)
 		goto cleanup_pernet;
@@ -440,6 +499,7 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
  cleanup_ipv6:
 	unregister_pernet_subsys(&ipv6_net_ops);
  cleanup_pernet:
+	nf_unregister_sockopt(&so_getorigdst6);
 	return ret;
 }
 
@@ -448,6 +508,7 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void)
 	synchronize_net();
 	nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops));
 	unregister_pernet_subsys(&ipv6_net_ops);
+	nf_unregister_sockopt(&so_getorigdst6);
 }
 
 module_init(nf_conntrack_l3proto_ipv6_init);
-- 
cgit v1.2.3-55-g7522


From 50ecf2c3afead23a05227ab004e4212eca08c207 Mon Sep 17 00:00:00 2001
From: Yoshihiro YUNOMAE
Date: Thu, 11 Oct 2012 16:27:54 -0700
Subject: ring-buffer: Change unsigned long type of
 ring_buffer_oldest_event_ts() to u64

ring_buffer_oldest_event_ts() should return a value of u64 type, because
ring_buffer_per_cpu->buffer_page->buffer_data_page->time_stamp is u64 type.

Link: http://lkml.kernel.org/r/1349998076-15495-5-git-send-email-dhsharp@google.com

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Vaibhav Nagarnaik <vnagarnaik@google.com>
Signed-off-by: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com>
Signed-off-by: David Sharp <dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h | 2 +-
 kernel/trace/ring_buffer.c  | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 2007375cfe77..519777e3fa01 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -159,7 +159,7 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer);
 void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
 
-unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu);
+u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_bytes_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_entries(struct ring_buffer *buffer);
 unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 23a384b92512..3c7834c24e54 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2932,12 +2932,12 @@ rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer)
  * @buffer: The ring buffer
  * @cpu: The per CPU buffer to read from.
  */
-unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu)
+u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu)
 {
 	unsigned long flags;
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct buffer_page *bpage;
-	unsigned long ret;
+	u64 ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
-- 
cgit v1.2.3-55-g7522


From 0d5c6e1c19bab82fad4837108c2902f557d62a04 Mon Sep 17 00:00:00 2001
From: Steven Rostedt
Date: Thu, 1 Nov 2012 20:54:21 -0400
Subject: tracing: Use irq_work for wake ups and remove *_nowake_*() functions

Have the ring buffer commit function use the irq_work infrastructure to
wake up any waiters waiting on the ring buffer for new data. The irq_work
was created for such a purpose, where doing the actual wake up at the
time of adding data is too dangerous, as an event or function trace may
be in the midst of the work queue locks and cause deadlocks. The irq_work
will either delay the action to the next timer interrupt, or trigger an IPI
to itself forcing an interrupt to do the work (in a safe location).

With irq_work, all ring buffer commits can safely do wakeups, removing
the need for the ring buffer commit "nowake" variants, which were used
by events and function tracing. All commits can now safely use the
normal commit, and the "nowake" variants can be removed.

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h      |  14 ++---
 include/trace/ftrace.h            |   3 +-
 kernel/trace/Kconfig              |   1 +
 kernel/trace/trace.c              | 121 +++++++++++++++++++++-----------------
 kernel/trace/trace.h              |   5 --
 kernel/trace/trace_events.c       |   2 +-
 kernel/trace/trace_kprobe.c       |   8 +--
 kernel/trace/trace_sched_switch.c |   2 +-
 kernel/trace/trace_selftest.c     |   1 +
 9 files changed, 84 insertions(+), 73 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 642928cf57b4..b80c8ddfbbdc 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -127,13 +127,13 @@ trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer,
 void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
 					struct ring_buffer_event *event,
 					unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
-				       struct ring_buffer_event *event,
-					unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer,
-					    struct ring_buffer_event *event,
-					    unsigned long flags, int pc,
-					    struct pt_regs *regs);
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
+				struct ring_buffer_event *event,
+				unsigned long flags, int pc);
+void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+				     struct ring_buffer_event *event,
+				     unsigned long flags, int pc,
+				     struct pt_regs *regs);
 void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
 					 struct ring_buffer_event *event);
 
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index a763888a36f9..698f2a890322 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -545,8 +545,7 @@ ftrace_raw_event_##call(void *__data, proto)				\
 	{ assign; }							\
 									\
 	if (!filter_current_check_discard(buffer, event_call, entry, event)) \
-		trace_nowake_buffer_unlock_commit(buffer,		\
-						  event, irq_flags, pc); \
+		trace_buffer_unlock_commit(buffer, event, irq_flags, pc); \
 }
 /*
  * The ftrace_test_probe is compiled out, it is only here as a build time check
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 4cea4f41c1d9..5d89335a485f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -119,6 +119,7 @@ config TRACING
 	select BINARY_PRINTF
 	select EVENT_TRACING
 	select TRACE_CLOCK
+	select IRQ_WORK
 
 config GENERIC_TRACER
 	bool
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d5cbc0d3f209..37d1c703e3ec 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -19,6 +19,7 @@
 #include <linux/seq_file.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
+#include <linux/irq_work.h>
 #include <linux/debugfs.h>
 #include <linux/pagemap.h>
 #include <linux/hardirq.h>
@@ -84,6 +85,14 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
  */
 static DEFINE_PER_CPU(bool, trace_cmdline_save);
 
+/*
+ * When a reader is waiting for data, then this variable is
+ * set to true.
+ */
+static bool trace_wakeup_needed;
+
+static struct irq_work trace_work_wakeup;
+
 /*
  * Kill all tracing for good (never come back).
  * It is initialized to 1 but will turn to zero if the initialization
@@ -329,12 +338,18 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 static int trace_stop_count;
 static DEFINE_RAW_SPINLOCK(tracing_start_lock);
 
-static void wakeup_work_handler(struct work_struct *work)
+/**
+ * trace_wake_up - wake up tasks waiting for trace input
+ *
+ * Schedules a delayed work to wake up any task that is blocked on the
+ * trace_wait queue. These is used with trace_poll for tasks polling the
+ * trace.
+ */
+static void trace_wake_up(struct irq_work *work)
 {
-	wake_up(&trace_wait);
-}
+	wake_up_all(&trace_wait);
 
-static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler);
+}
 
 /**
  * tracing_on - enable tracing buffers
@@ -389,22 +404,6 @@ int tracing_is_on(void)
 }
 EXPORT_SYMBOL_GPL(tracing_is_on);
 
-/**
- * trace_wake_up - wake up tasks waiting for trace input
- *
- * Schedules a delayed work to wake up any task that is blocked on the
- * trace_wait queue. These is used with trace_poll for tasks polling the
- * trace.
- */
-void trace_wake_up(void)
-{
-	const unsigned long delay = msecs_to_jiffies(2);
-
-	if (trace_flags & TRACE_ITER_BLOCK)
-		return;
-	schedule_delayed_work(&wakeup_work, delay);
-}
-
 static int __init set_buf_size(char *str)
 {
 	unsigned long buf_size;
@@ -753,6 +752,40 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
+static void default_wait_pipe(struct trace_iterator *iter)
+{
+	DEFINE_WAIT(wait);
+
+	prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE);
+
+	/*
+	 * The events can happen in critical sections where
+	 * checking a work queue can cause deadlocks.
+	 * After adding a task to the queue, this flag is set
+	 * only to notify events to try to wake up the queue
+	 * using irq_work.
+	 *
+	 * We don't clear it even if the buffer is no longer
+	 * empty. The flag only causes the next event to run
+	 * irq_work to do the work queue wake up. The worse
+	 * that can happen if we race with !trace_empty() is that
+	 * an event will cause an irq_work to try to wake up
+	 * an empty queue.
+	 *
+	 * There's no reason to protect this flag either, as
+	 * the work queue and irq_work logic will do the necessary
+	 * synchronization for the wake ups. The only thing
+	 * that is necessary is that the wake up happens after
+	 * a task has been queued. It's OK for spurious wake ups.
+	 */
+	trace_wakeup_needed = true;
+
+	if (trace_empty(iter))
+		schedule();
+
+	finish_wait(&trace_wait, &wait);
+}
+
 /**
  * register_tracer - register a tracer with the ftrace system.
  * @type - the plugin for the tracer
@@ -1156,30 +1189,32 @@ void
 __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
 {
 	__this_cpu_write(trace_cmdline_save, true);
+	if (trace_wakeup_needed) {
+		trace_wakeup_needed = false;
+		/* irq_work_queue() supplies it's own memory barriers */
+		irq_work_queue(&trace_work_wakeup);
+	}
 	ring_buffer_unlock_commit(buffer, event);
 }
 
 static inline void
 __trace_buffer_unlock_commit(struct ring_buffer *buffer,
 			     struct ring_buffer_event *event,
-			     unsigned long flags, int pc,
-			     int wake)
+			     unsigned long flags, int pc)
 {
 	__buffer_unlock_commit(buffer, event);
 
 	ftrace_trace_stack(buffer, flags, 6, pc);
 	ftrace_trace_userstack(buffer, flags, pc);
-
-	if (wake)
-		trace_wake_up();
 }
 
 void trace_buffer_unlock_commit(struct ring_buffer *buffer,
 				struct ring_buffer_event *event,
 				unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc);
 }
+EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
 
 struct ring_buffer_event *
 trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
@@ -1196,29 +1231,21 @@ void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
 					struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
 
-void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
-				       struct ring_buffer_event *event,
-				       unsigned long flags, int pc)
-{
-	__trace_buffer_unlock_commit(buffer, event, flags, pc, 0);
-}
-EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
-
-void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer,
-					    struct ring_buffer_event *event,
-					    unsigned long flags, int pc,
-					    struct pt_regs *regs)
+void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+				     struct ring_buffer_event *event,
+				     unsigned long flags, int pc,
+				     struct pt_regs *regs)
 {
 	__buffer_unlock_commit(buffer, event);
 
 	ftrace_trace_stack_regs(buffer, flags, 0, pc, regs);
 	ftrace_trace_userstack(buffer, flags, pc);
 }
-EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit_regs);
+EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs);
 
 void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
 					 struct ring_buffer_event *event)
@@ -3354,19 +3381,6 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
 	}
 }
 
-
-void default_wait_pipe(struct trace_iterator *iter)
-{
-	DEFINE_WAIT(wait);
-
-	prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE);
-
-	if (trace_empty(iter))
-		schedule();
-
-	finish_wait(&trace_wait, &wait);
-}
-
 /*
  * This is a make-shift waitqueue.
  * A tracer might use this callback on some rare cases:
@@ -5107,6 +5121,7 @@ __init static int tracer_alloc_buffers(void)
 #endif
 
 	trace_init_cmdlines();
+	init_irq_work(&trace_work_wakeup, trace_wake_up);
 
 	register_tracer(&nop_trace);
 	current_trace = &nop_trace;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3e8a176f64e6..55010ed175f0 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -327,7 +327,6 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu)
 
 int tracer_init(struct tracer *t, struct trace_array *tr);
 int tracing_is_enabled(void);
-void trace_wake_up(void);
 void tracing_reset(struct trace_array *tr, int cpu);
 void tracing_reset_online_cpus(struct trace_array *tr);
 void tracing_reset_current(int cpu);
@@ -349,9 +348,6 @@ trace_buffer_lock_reserve(struct ring_buffer *buffer,
 			  unsigned long len,
 			  unsigned long flags,
 			  int pc);
-void trace_buffer_unlock_commit(struct ring_buffer *buffer,
-				struct ring_buffer_event *event,
-				unsigned long flags, int pc);
 
 struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 						struct trace_array_cpu *data);
@@ -370,7 +366,6 @@ void trace_init_global_iter(struct trace_iterator *iter);
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu);
 
-void default_wait_pipe(struct trace_iterator *iter);
 void poll_wait_pipe(struct trace_iterator *iter);
 
 void ftrace(struct trace_array *tr,
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index cb2df3b70f7f..880073d0b946 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1760,7 +1760,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip,
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	trace_nowake_buffer_unlock_commit(buffer, event, flags, pc);
+	trace_buffer_unlock_commit(buffer, event, flags, pc);
 
  out:
 	atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 5a3c533ef060..1865d5f76538 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -751,8 +751,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
-		trace_nowake_buffer_unlock_commit_regs(buffer, event,
-						       irq_flags, pc, regs);
+		trace_buffer_unlock_commit_regs(buffer, event,
+						irq_flags, pc, regs);
 }
 
 /* Kretprobe handler */
@@ -784,8 +784,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
-		trace_nowake_buffer_unlock_commit_regs(buffer, event,
-						       irq_flags, pc, regs);
+		trace_buffer_unlock_commit_regs(buffer, event,
+						irq_flags, pc, regs);
 }
 
 /* Event entry printers */
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index b0a136ac382a..3374c792ccd8 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -102,7 +102,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_cpu			= task_cpu(wakee);
 
 	if (!filter_check_discard(call, entry, buffer, event))
-		trace_nowake_buffer_unlock_commit(buffer, event, flags, pc);
+		trace_buffer_unlock_commit(buffer, event, flags, pc);
 }
 
 static void
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 091b815f7b0a..47623169a815 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1094,6 +1094,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
+	printk("ret = %d\n", ret);
 	if (!ret)
 		ret = trace_test_buffer(&max_tr, &count);
 
-- 
cgit v1.2.3-55-g7522


From 873e698067cfa21420576632e1c3387c0f90ce4a Mon Sep 17 00:00:00 2001
From: Tony Lindgren
Date: Wed, 31 Oct 2012 09:54:56 -0700
Subject: ARM: OMAP: Remove NEED_MACH_GPIO_H

Omap no longer needs this option, mach/gpio.h is
empty.

Also remove mach/irqs.h from gpio-omap.h and
include it directly from the related omap1
gpio init files.

Otherwise omap2+ build fails for MULTI_PLATFORM.

Cc: Peter Ujfalusi <peter.ujfalusi@ti.com>
Cc: Jarkko Nikula <jarkko.nikula@bitmer.com>
Cc: Liam Girdwood <lrg@ti.com>
Cc: alsa-devel@alsa-project.org
Acked-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/Kconfig                        | 1 -
 arch/arm/mach-omap1/gpio15xx.c          | 2 ++
 arch/arm/mach-omap1/gpio16xx.c          | 2 ++
 arch/arm/mach-omap1/gpio7xx.c           | 2 ++
 arch/arm/mach-omap1/include/mach/gpio.h | 3 ---
 arch/arm/mach-omap2/include/mach/gpio.h | 3 ---
 include/linux/platform_data/gpio-omap.h | 1 -
 sound/soc/omap/am3517evm.c              | 2 --
 sound/soc/omap/n810.c                   | 1 -
 sound/soc/omap/osk5912.c                | 1 -
 sound/soc/omap/sdp3430.c                | 2 --
 sound/soc/omap/zoom2.c                  | 3 ---
 12 files changed, 6 insertions(+), 17 deletions(-)
 delete mode 100644 arch/arm/mach-omap1/include/mach/gpio.h
 delete mode 100644 arch/arm/mach-omap2/include/mach/gpio.h

(limited to 'include')

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 73067efd4845..6207cf734b2b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -937,7 +937,6 @@ config ARCH_OMAP
 	select CLKSRC_MMIO
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CLK
-	select NEED_MACH_GPIO_H
 	help
 	  Support for TI's OMAP platform (OMAP1/2/3/4).
 
diff --git a/arch/arm/mach-omap1/gpio15xx.c b/arch/arm/mach-omap1/gpio15xx.c
index 98e6f39224a4..02b3eb2e201c 100644
--- a/arch/arm/mach-omap1/gpio15xx.c
+++ b/arch/arm/mach-omap1/gpio15xx.c
@@ -19,6 +19,8 @@
 #include <linux/gpio.h>
 #include <linux/platform_data/gpio-omap.h>
 
+#include <mach/irqs.h>
+
 #define OMAP1_MPUIO_VBASE		OMAP1_MPUIO_BASE
 #define OMAP1510_GPIO_BASE		0xFFFCE000
 
diff --git a/arch/arm/mach-omap1/gpio16xx.c b/arch/arm/mach-omap1/gpio16xx.c
index 33f419236b17..b9952a258d82 100644
--- a/arch/arm/mach-omap1/gpio16xx.c
+++ b/arch/arm/mach-omap1/gpio16xx.c
@@ -19,6 +19,8 @@
 #include <linux/gpio.h>
 #include <linux/platform_data/gpio-omap.h>
 
+#include <mach/irqs.h>
+
 #define OMAP1610_GPIO1_BASE		0xfffbe400
 #define OMAP1610_GPIO2_BASE		0xfffbec00
 #define OMAP1610_GPIO3_BASE		0xfffbb400
diff --git a/arch/arm/mach-omap1/gpio7xx.c b/arch/arm/mach-omap1/gpio7xx.c
index 958ce9acee95..f5819b2b7cbe 100644
--- a/arch/arm/mach-omap1/gpio7xx.c
+++ b/arch/arm/mach-omap1/gpio7xx.c
@@ -19,6 +19,8 @@
 #include <linux/gpio.h>
 #include <linux/platform_data/gpio-omap.h>
 
+#include <mach/irqs.h>
+
 #define OMAP7XX_GPIO1_BASE		0xfffbc000
 #define OMAP7XX_GPIO2_BASE		0xfffbc800
 #define OMAP7XX_GPIO3_BASE		0xfffbd000
diff --git a/arch/arm/mach-omap1/include/mach/gpio.h b/arch/arm/mach-omap1/include/mach/gpio.h
deleted file mode 100644
index ebf86c0f4f46..000000000000
--- a/arch/arm/mach-omap1/include/mach/gpio.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/*
- * arch/arm/mach-omap1/include/mach/gpio.h
- */
diff --git a/arch/arm/mach-omap2/include/mach/gpio.h b/arch/arm/mach-omap2/include/mach/gpio.h
deleted file mode 100644
index 5621cc59c9f4..000000000000
--- a/arch/arm/mach-omap2/include/mach/gpio.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/*
- * arch/arm/mach-omap2/include/mach/gpio.h
- */
diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h
index e8741c2678d5..5d50b25a73d7 100644
--- a/include/linux/platform_data/gpio-omap.h
+++ b/include/linux/platform_data/gpio-omap.h
@@ -26,7 +26,6 @@
 
 #include <linux/io.h>
 #include <linux/platform_device.h>
-#include <mach/irqs.h>
 
 #define OMAP1_MPUIO_BASE			0xfffb5000
 
diff --git a/sound/soc/omap/am3517evm.c b/sound/soc/omap/am3517evm.c
index fad350682ca2..c1900b2a6f28 100644
--- a/sound/soc/omap/am3517evm.c
+++ b/sound/soc/omap/am3517evm.c
@@ -25,8 +25,6 @@
 #include <sound/soc.h>
 
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
-#include <mach/gpio.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
 
 #include "omap-mcbsp.h"
diff --git a/sound/soc/omap/n810.c b/sound/soc/omap/n810.c
index 521bfc3d2b2b..230b8c144848 100644
--- a/sound/soc/omap/n810.c
+++ b/sound/soc/omap/n810.c
@@ -29,7 +29,6 @@
 #include <sound/soc.h>
 
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
diff --git a/sound/soc/omap/osk5912.c b/sound/soc/omap/osk5912.c
index 3960e8df9c76..06ef8d67ed1c 100644
--- a/sound/soc/omap/osk5912.c
+++ b/sound/soc/omap/osk5912.c
@@ -28,7 +28,6 @@
 #include <sound/soc.h>
 
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
 #include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
diff --git a/sound/soc/omap/sdp3430.c b/sound/soc/omap/sdp3430.c
index 597cae769cea..b462a2c9385f 100644
--- a/sound/soc/omap/sdp3430.c
+++ b/sound/soc/omap/sdp3430.c
@@ -31,8 +31,6 @@
 #include <sound/jack.h>
 
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
-#include <mach/gpio.h>
 #include <linux/platform_data/gpio-omap.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
 
diff --git a/sound/soc/omap/zoom2.c b/sound/soc/omap/zoom2.c
index 677b567935f8..27c501c301b7 100644
--- a/sound/soc/omap/zoom2.c
+++ b/sound/soc/omap/zoom2.c
@@ -26,9 +26,6 @@
 #include <sound/soc.h>
 
 #include <asm/mach-types.h>
-#include <mach/hardware.h>
-#include <mach/gpio.h>
-#include <mach/board-zoom.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
 
 /* Register descriptions for twl4030 codec part */
-- 
cgit v1.2.3-55-g7522


From e19d6763cc300fcb706bd291b24ac06be71e1ce6 Mon Sep 17 00:00:00 2001
From: Michael S. Tsirkin
Date: Thu, 1 Nov 2012 09:16:22 +0000
Subject: skb: report completion status for zero copy skbs

Even if skb is marked for zero copy, net core might still decide
to copy it later which is somewhat slower than a copy in user context:
besides copying the data we need to pin/unpin the pages.

Add a parameter reporting such cases through zero copy callback:
if this happens a lot, device can take this into account
and switch to copying in user context.

This patch updates all users but ignores the passed value for now:
it will be used by follow-up patches.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c  | 2 +-
 drivers/vhost/vhost.h  | 2 +-
 include/linux/skbuff.h | 4 +++-
 net/core/skbuff.c      | 4 ++--
 4 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 99ac2cb08b43..73d08db2e677 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1600,7 +1600,7 @@ void vhost_ubuf_put_and_wait(struct vhost_ubuf_ref *ubufs)
 	kfree(ubufs);
 }
 
-void vhost_zerocopy_callback(struct ubuf_info *ubuf)
+void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool status)
 {
 	struct vhost_ubuf_ref *ubufs = ubuf->ctx;
 	struct vhost_virtqueue *vq = ubufs->vq;
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 1125af3d27d1..2de4ce2fec40 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -191,7 +191,7 @@ bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 		    unsigned int log_num, u64 len);
-void vhost_zerocopy_callback(struct ubuf_info *);
+void vhost_zerocopy_callback(struct ubuf_info *, bool);
 int vhost_zerocopy_signal_used(struct vhost_virtqueue *vq);
 
 #define vq_err(vq, fmt, ...) do {                                  \
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a2a0bdb95a8f..e5eae5bc1d4d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -235,11 +235,13 @@ enum {
 /*
  * The callback notifies userspace to release buffers when skb DMA is done in
  * lower device, the skb last reference should be 0 when calling this.
+ * The zerocopy_success argument is true if zero copy transmit occurred,
+ * false on data copy or out of memory error caused by data copy attempt.
  * The ctx field is used to track device context.
  * The desc field is used to track userspace buffer index.
  */
 struct ubuf_info {
-	void (*callback)(struct ubuf_info *);
+	void (*callback)(struct ubuf_info *, bool zerocopy_success);
 	void *ctx;
 	unsigned long desc;
 };
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6e04b1fa11f2..4abdf71a23f8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -519,7 +519,7 @@ static void skb_release_data(struct sk_buff *skb)
 
 			uarg = skb_shinfo(skb)->destructor_arg;
 			if (uarg->callback)
-				uarg->callback(uarg);
+				uarg->callback(uarg, true);
 		}
 
 		if (skb_has_frag_list(skb))
@@ -797,7 +797,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
 	for (i = 0; i < num_frags; i++)
 		skb_frag_unref(skb, i);
 
-	uarg->callback(uarg);
+	uarg->callback(uarg, false);
 
 	/* skb frags point to kernel buffers */
 	for (i = num_frags - 1; i >= 0; i--) {
-- 
cgit v1.2.3-55-g7522


From 25121173f7b1e4ac3fc692df6e7b8c52ec36abba Mon Sep 17 00:00:00 2001
From: Michael S. Tsirkin
Date: Thu, 1 Nov 2012 09:16:28 +0000
Subject: skb: api to report errors for zero copy skbs

Orphaning frags for zero copy skbs needs to allocate data in atomic
context so is has a chance to fail. If it does we currently discard
the skb which is safe, but we don't report anything to the caller,
so it can not recover by e.g. disabling zero copy.

Add an API to free skb reporting such errors: this is used
by tun in case orphaning frags fails.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  1 +
 net/core/skbuff.c      | 20 ++++++++++++++++++++
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e5eae5bc1d4d..f2af494330ab 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -568,6 +568,7 @@ static inline struct rtable *skb_rtable(const struct sk_buff *skb)
 }
 
 extern void kfree_skb(struct sk_buff *skb);
+extern void skb_tx_error(struct sk_buff *skb);
 extern void consume_skb(struct sk_buff *skb);
 extern void	       __kfree_skb(struct sk_buff *skb);
 extern struct kmem_cache *skbuff_head_cache;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 4abdf71a23f8..d9addea10309 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -634,6 +634,26 @@ void kfree_skb(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(kfree_skb);
 
+/**
+ *	skb_tx_error - report an sk_buff xmit error
+ *	@skb: buffer that triggered an error
+ *
+ *	Report xmit error if a device callback is tracking this skb.
+ *	skb must be freed afterwards.
+ */
+void skb_tx_error(struct sk_buff *skb)
+{
+	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
+		struct ubuf_info *uarg;
+
+		uarg = skb_shinfo(skb)->destructor_arg;
+		if (uarg->callback)
+			uarg->callback(uarg, false);
+		skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
+	}
+}
+EXPORT_SYMBOL(skb_tx_error);
+
 /**
  *	consume_skb - free an skbuff
  *	@skb: buffer to free
-- 
cgit v1.2.3-55-g7522


From 46acc460c07b5c74287560a00b6cbc6111136ab6 Mon Sep 17 00:00:00 2001
From: Ben Hutchings
Date: Thu, 1 Nov 2012 09:11:11 +0000
Subject: eth: Make is_link_local() consistent with other address tests

Function name should include '_ether_addr'.
Return type should be bool.
Parameter name should be 'addr' not 'dest' (also matching kernel-doc).

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c     | 2 +-
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +-
 drivers/net/ethernet/intel/ixgbevf/vf.c           | 2 +-
 include/linux/etherdevice.h                       | 6 +++---
 net/bridge/br_input.c                             | 2 +-
 net/bridge/br_sysfs_br.c                          | 2 +-
 6 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index b54bc40f00b0..690535a0322f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6953,7 +6953,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		return -EINVAL;
 	}
 
-	if (is_unicast_ether_addr(addr) || is_link_local(addr)) {
+	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
 		u32 rar_uc_entries = IXGBE_MAX_PF_MACVLANS;
 
 		if (netdev_uc_count(dev) < rar_uc_entries)
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index c281ee9c9e2a..f3d3947ae962 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -2979,7 +2979,7 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	unsigned short f;
 #endif
 	u8 *dst_mac = skb_header_pointer(skb, 0, 0, NULL);
-	if (!dst_mac || is_link_local(dst_mac)) {
+	if (!dst_mac || is_link_local_ether_addr(dst_mac)) {
 		dev_kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index c0fd1ef49400..0c94557b53df 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -331,7 +331,7 @@ static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw,
 	netdev_for_each_mc_addr(ha, netdev) {
 		if (i == cnt)
 			break;
-		if (is_link_local(ha->addr))
+		if (is_link_local_ether_addr(ha->addr))
 			continue;
 
 		vector_list[i++] = ixgbevf_mta_vector(hw, ha->addr);
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 45ded4be7b43..7cf2516ec74c 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -55,15 +55,15 @@ extern struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
 static const u8 br_reserved_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
 
 /**
- * is_link_local -  Determine if given Eth addr is a link local mcast address.
+ * is_link_local_ether_addr - Determine if given Ethernet address is link-local
  * @addr: Pointer to a six-byte array containing the Ethernet address
  *
  * Return true if address is link local reserved addr (01:80:c2:00:00:0X) per
  * IEEE 802.1Q 8.6.3 Frame filtering.
  */
-static inline int is_link_local(const unsigned char *dest)
+static inline bool is_link_local_ether_addr(const u8 *addr)
 {
-	__be16 *a = (__be16 *)dest;
+	__be16 *a = (__be16 *)addr;
 	static const __be16 *b = (const __be16 *)br_reserved_address;
 	static const __be16 m = cpu_to_be16(0xfff0);
 
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index d047978bf025..4b34207419b1 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -147,7 +147,7 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 
 	p = br_port_get_rcu(skb->dev);
 
-	if (unlikely(is_link_local(dest))) {
+	if (unlikely(is_link_local_ether_addr(dest))) {
 		/*
 		 * See IEEE 802.1D Table 7-10 Reserved addresses
 		 *
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index 82385fd2f187..cffb76e2161c 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -309,7 +309,7 @@ static ssize_t store_group_addr(struct device *d,
 		   &new_addr[3], &new_addr[4], &new_addr[5]) != 6)
 		return -EINVAL;
 
-	if (!is_link_local(new_addr))
+	if (!is_link_local_ether_addr(new_addr))
 		return -EINVAL;
 
 	if (new_addr[5] == 1 ||		/* 802.3x Pause address */
-- 
cgit v1.2.3-55-g7522


From 2bc80059fe19229e68a306ce12f5e61e80b92c5c Mon Sep 17 00:00:00 2001
From: Ben Hutchings
Date: Thu, 1 Nov 2012 09:12:02 +0000
Subject: eth: Rename and properly align br_reserved_address array

Since this array is no longer part of the bridge driver, it should
have an 'eth' prefix not 'br'.

We also assume that either it's 16-bit-aligned or the architecture has
efficient unaligned access.  Ensure the first of these is true by
explicitly aligning it.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/etherdevice.h | 5 +++--
 net/bridge/br_device.c      | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 7cf2516ec74c..243eea1e33d8 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -52,7 +52,8 @@ extern struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
 #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count)
 
 /* Reserved Ethernet Addresses per IEEE 802.1Q */
-static const u8 br_reserved_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
+static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) =
+{ 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
 
 /**
  * is_link_local_ether_addr - Determine if given Ethernet address is link-local
@@ -64,7 +65,7 @@ static const u8 br_reserved_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00,
 static inline bool is_link_local_ether_addr(const u8 *addr)
 {
 	__be16 *a = (__be16 *)addr;
-	static const __be16 *b = (const __be16 *)br_reserved_address;
+	static const __be16 *b = (const __be16 *)eth_reserved_addr_base;
 	static const __be16 m = cpu_to_be16(0xfff0);
 
 	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 4245e991dd98..7c78e2640190 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -358,7 +358,7 @@ void br_dev_setup(struct net_device *dev)
 	br->bridge_id.prio[0] = 0x80;
 	br->bridge_id.prio[1] = 0x00;
 
-	memcpy(br->group_addr, br_reserved_address, ETH_ALEN);
+	memcpy(br->group_addr, eth_reserved_addr_base, ETH_ALEN);
 
 	br->stp_enabled = BR_NO_STP;
 	br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
-- 
cgit v1.2.3-55-g7522


From 19f5ee2716373519fda2129e9333f4c3847aa742 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov
Date: Sun, 28 Oct 2012 18:14:14 +0100
Subject: uprobes: Kill arch_uprobe_enable/disable_step() hooks

Kill arch_uprobe_enable/disable_step() hooks, they do nothing and
nobody needs them.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
 include/linux/uprobes.h |  2 --
 kernel/events/uprobes.c | 10 ----------
 2 files changed, 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 24594571c5a3..2615c4d7788d 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -101,8 +101,6 @@ extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm);
 extern void uprobe_free_utask(struct task_struct *t);
 extern void uprobe_copy_process(struct task_struct *t);
 extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
-extern void __weak arch_uprobe_enable_step(struct arch_uprobe *arch);
-extern void __weak arch_uprobe_disable_step(struct arch_uprobe *arch);
 extern int uprobe_post_sstep_notifier(struct pt_regs *regs);
 extern int uprobe_pre_sstep_notifier(struct pt_regs *regs);
 extern void uprobe_notify_resume(struct pt_regs *regs);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index abbfd8440a6d..39c75cc51efc 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1430,14 +1430,6 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 	return uprobe;
 }
 
-void __weak arch_uprobe_enable_step(struct arch_uprobe *arch)
-{
-}
-
-void __weak arch_uprobe_disable_step(struct arch_uprobe *arch)
-{
-}
-
 /*
  * Run handler and ask thread to singlestep.
  * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
@@ -1491,7 +1483,6 @@ static void handle_swbp(struct pt_regs *regs)
 		goto out;
 
 	if (!pre_ssout(uprobe, regs, bp_vaddr)) {
-		arch_uprobe_enable_step(&uprobe->arch);
 		utask->active_uprobe = uprobe;
 		utask->state = UTASK_SSTEP;
 		return;
@@ -1523,7 +1514,6 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
 	else
 		WARN_ON_ONCE(1);
 
-	arch_uprobe_disable_step(&uprobe->arch);
 	put_uprobe(uprobe);
 	utask->active_uprobe = NULL;
 	utask->state = UTASK_RUNNING;
-- 
cgit v1.2.3-55-g7522


From e6c022a4fa2d2d9ca9d0a7ac3b05ad988f39fc30 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Sat, 27 Oct 2012 23:16:46 +0000
Subject: tcp: better retrans tracking for defer-accept

For passive TCP connections using TCP_DEFER_ACCEPT facility,
we incorrectly increment req->retrans each time timeout triggers
while no SYNACK is sent.

SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for
which we received the ACK from client). Only the last SYNACK is sent
so that we can receive again an ACK from client, to move the req into
accept queue. We plan to change this later to avoid the useless
retransmit (and potential problem as this SYNACK could be lost)

TCP_INFO later gives wrong information to user, claiming imaginary
retransmits.

Decouple req->retrans field into two independent fields :

num_retrans : number of retransmit
num_timeout : number of timeouts

num_timeout is the counter that is incremented at each timeout,
regardless of actual SYNACK being sent or not, and used to
compute the exponential timeout.

Introduce inet_rtx_syn_ack() helper to increment num_retrans
only if ->rtx_syn_ack() succeeded.

Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans
when we re-send a SYNACK in answer to a (retransmitted) SYN.
Prior to this patch, we were not counting these retransmits.

Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS
only if a synack packet was successfully queued.

Reported-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Elliott Hughes <enh@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/request_sock.h      | 12 ++++++++----
 net/dccp/minisocks.c            |  3 +--
 net/ipv4/inet_connection_sock.c | 25 ++++++++++++++++++-------
 net/ipv4/inet_diag.c            |  2 +-
 net/ipv4/syncookies.c           |  2 +-
 net/ipv4/tcp_input.c            |  2 +-
 net/ipv4/tcp_ipv4.c             | 16 ++++++++++------
 net/ipv4/tcp_minisocks.c        |  8 ++++----
 net/ipv4/tcp_timer.c            |  8 ++++----
 net/ipv6/syncookies.c           |  2 +-
 net/ipv6/tcp_ipv6.c             | 11 +++++++----
 11 files changed, 56 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index b01d8dd9ee7c..a51dbd17c2de 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -49,13 +49,16 @@ struct request_sock_ops {
 					   struct request_sock *req);
 };
 
+extern int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req);
+
 /* struct request_sock - mini sock to represent a connection request
  */
 struct request_sock {
 	struct request_sock		*dl_next; /* Must be first member! */
 	u16				mss;
-	u8				retrans;
-	u8				cookie_ts; /* syncookie: encode tcpopts in timestamp */
+	u8				num_retrans; /* number of retransmits */
+	u8				cookie_ts:1; /* syncookie: encode tcpopts in timestamp */
+	u8				num_timeout:7; /* number of timeouts */
 	/* The following two fields can be easily recomputed I think -AK */
 	u32				window_clamp; /* window clamp at creation time */
 	u32				rcv_wnd;	  /* rcv_wnd offered first time */
@@ -231,7 +234,7 @@ static inline int reqsk_queue_removed(struct request_sock_queue *queue,
 {
 	struct listen_sock *lopt = queue->listen_opt;
 
-	if (req->retrans == 0)
+	if (req->num_timeout == 0)
 		--lopt->qlen_young;
 
 	return --lopt->qlen;
@@ -269,7 +272,8 @@ static inline void reqsk_queue_hash_req(struct request_sock_queue *queue,
 	struct listen_sock *lopt = queue->listen_opt;
 
 	req->expires = jiffies + timeout;
-	req->retrans = 0;
+	req->num_retrans = 0;
+	req->num_timeout = 0;
 	req->sk = NULL;
 	req->dl_next = lopt->syn_table[hash];
 
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index ea850ce35d4a..662071b249cc 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -174,8 +174,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 			 * To protect against Request floods, increment retrans
 			 * counter (backoff, monitored by dccp_response_timer).
 			 */
-			req->retrans++;
-			req->rsk_ops->rtx_syn_ack(sk, req, NULL);
+			inet_rtx_syn_ack(sk, req);
 		}
 		/* Network Duplicate, discard packet */
 		return NULL;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d34ce2972c8f..2026542d6836 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -521,21 +521,31 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
 				  int *expire, int *resend)
 {
 	if (!rskq_defer_accept) {
-		*expire = req->retrans >= thresh;
+		*expire = req->num_timeout >= thresh;
 		*resend = 1;
 		return;
 	}
-	*expire = req->retrans >= thresh &&
-		  (!inet_rsk(req)->acked || req->retrans >= max_retries);
+	*expire = req->num_timeout >= thresh &&
+		  (!inet_rsk(req)->acked || req->num_timeout >= max_retries);
 	/*
 	 * Do not resend while waiting for data after ACK,
 	 * start to resend on end of deferring period to give
 	 * last chance for data or ACK to create established socket.
 	 */
 	*resend = !inet_rsk(req)->acked ||
-		  req->retrans >= rskq_defer_accept - 1;
+		  req->num_timeout >= rskq_defer_accept - 1;
 }
 
+int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
+{
+	int err = req->rsk_ops->rtx_syn_ack(parent, req, NULL);
+
+	if (!err)
+		req->num_retrans++;
+	return err;
+}
+EXPORT_SYMBOL(inet_rtx_syn_ack);
+
 void inet_csk_reqsk_queue_prune(struct sock *parent,
 				const unsigned long interval,
 				const unsigned long timeout,
@@ -599,13 +609,14 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 				req->rsk_ops->syn_ack_timeout(parent, req);
 				if (!expire &&
 				    (!resend ||
-				     !req->rsk_ops->rtx_syn_ack(parent, req, NULL) ||
+				     !inet_rtx_syn_ack(parent, req) ||
 				     inet_rsk(req)->acked)) {
 					unsigned long timeo;
 
-					if (req->retrans++ == 0)
+					if (req->num_timeout++ == 0)
 						lopt->qlen_young--;
-					timeo = min((timeout << req->retrans), max_rto);
+					timeo = min(timeout << req->num_timeout,
+						    max_rto);
 					req->expires = now + timeo;
 					reqp = &req->dl_next;
 					continue;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index e5bad82d3584..b5e781b529aa 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -620,7 +620,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 	r->idiag_family = sk->sk_family;
 	r->idiag_state = TCP_SYN_RECV;
 	r->idiag_timer = 1;
-	r->idiag_retrans = req->retrans;
+	r->idiag_retrans = req->num_retrans;
 
 	r->id.idiag_if = sk->sk_bound_dev_if;
 	sock_diag_save_cookie(req, r->id.idiag_cookie);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index ba48e799b031..b236ef04914f 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -340,7 +340,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	}
 
 	req->expires	= 0UL;
-	req->retrans	= 0;
+	req->num_retrans = 0;
 
 	/*
 	 * We need to lookup the route here to get at the correct
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 60cf836120a1..e95b4e508afe 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5991,7 +5991,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 				 */
 				if (req) {
 					tcp_synack_rtt_meas(sk, req);
-					tp->total_retrans = req->retrans;
+					tp->total_retrans = req->num_retrans;
 
 					reqsk_fastopen_remove(sk, req, false);
 				} else {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 60e2e5d3ce29..e3607669064e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -877,10 +877,13 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 }
 
 static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req,
-			      struct request_values *rvp)
+			     struct request_values *rvp)
 {
-	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-	return tcp_v4_send_synack(sk, NULL, req, rvp, 0, false);
+	int res = tcp_v4_send_synack(sk, NULL, req, rvp, 0, false);
+
+	if (!res)
+		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+	return res;
 }
 
 /*
@@ -1386,7 +1389,8 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk,
 	struct sock *child;
 	int err;
 
-	req->retrans = 0;
+	req->num_retrans = 0;
+	req->num_timeout = 0;
 	req->sk = NULL;
 
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
@@ -1740,7 +1744,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	tcp_initialize_rcv_mss(newsk);
 	tcp_synack_rtt_meas(newsk, req);
-	newtp->total_retrans = req->retrans;
+	newtp->total_retrans = req->num_retrans;
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Copy over the MD5 key from the original socket */
@@ -2638,7 +2642,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req,
 		0, 0, /* could print option size, but that is af dependent. */
 		1,    /* timers active (only the expire timer) */
 		jiffies_delta_to_clock_t(delta),
-		req->retrans,
+		req->num_timeout,
 		from_kuid_munged(seq_user_ns(f), uid),
 		0,  /* non standard timer */
 		0, /* open_requests have no inode */
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 27536ba16c9d..0404b3f4c959 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -552,7 +552,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			 * it can be estimated (approximately)
 			 * from another data.
 			 */
-			tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->retrans);
+			tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout);
 			paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
 		}
 	}
@@ -581,7 +581,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		 * Note that even if there is new data in the SYN packet
 		 * they will be thrown away too.
 		 */
-		req->rsk_ops->rtx_syn_ack(sk, req, NULL);
+		inet_rtx_syn_ack(sk, req);
 		return NULL;
 	}
 
@@ -695,7 +695,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	/* Got ACK for our SYNACK, so update baseline for SYNACK RTT sample. */
 	if (tmp_opt.saw_tstamp && tmp_opt.rcv_tsecr)
 		tcp_rsk(req)->snt_synack = tmp_opt.rcv_tsecr;
-	else if (req->retrans) /* don't take RTT sample if retrans && ~TS */
+	else if (req->num_retrans) /* don't take RTT sample if retrans && ~TS */
 		tcp_rsk(req)->snt_synack = 0;
 
 	/* For Fast Open no more processing is needed (sk is the
@@ -705,7 +705,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		return sk;
 
 	/* While TCP_DEFER_ACCEPT is active, drop bare ACK. */
-	if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
+	if (req->num_timeout < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
 	    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
 		inet_rsk(req)->acked = 1;
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDEFERACCEPTDROP);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index fc04711e80c8..62c69ab19fdf 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -318,7 +318,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk)
 	req = tcp_sk(sk)->fastopen_rsk;
 	req->rsk_ops->syn_ack_timeout(sk, req);
 
-	if (req->retrans >= max_retries) {
+	if (req->num_timeout >= max_retries) {
 		tcp_write_err(sk);
 		return;
 	}
@@ -327,10 +327,10 @@ static void tcp_fastopen_synack_timer(struct sock *sk)
 	 * regular retransmit because if the child socket has been accepted
 	 * it's not good to give up too easily.
 	 */
-	req->rsk_ops->rtx_syn_ack(sk, req, NULL);
-	req->retrans++;
+	inet_rtx_syn_ack(sk, req);
+	req->num_timeout++;
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-			  TCP_TIMEOUT_INIT << req->retrans, TCP_RTO_MAX);
+			  TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
 }
 
 /*
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 182ab9a85d6c..40161977f7cf 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -214,7 +214,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		ireq6->iif = inet6_iif(skb);
 
 	req->expires = 0UL;
-	req->retrans = 0;
+	req->num_retrans = 0;
 	ireq->ecn_ok		= ecn_ok;
 	ireq->snd_wscale	= tcp_opt.snd_wscale;
 	ireq->sack_ok		= tcp_opt.sack_ok;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index bb6782e84996..c73d0ebde9c8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -495,9 +495,12 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req,
 			     struct request_values *rvp)
 {
 	struct flowi6 fl6;
+	int res;
 
-	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-	return tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0);
+	res = tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0);
+	if (!res)
+		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+	return res;
 }
 
 static void tcp_v6_reqsk_destructor(struct request_sock *req)
@@ -1364,7 +1367,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	tcp_initialize_rcv_mss(newsk);
 	tcp_synack_rtt_meas(newsk, req);
-	newtp->total_retrans = req->retrans;
+	newtp->total_retrans = req->num_retrans;
 
 	newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
 	newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
@@ -1866,7 +1869,7 @@ static void get_openreq6(struct seq_file *seq,
 		   0,0, /* could print option size, but that is af dependent. */
 		   1,   /* timers active (only the expire timer) */
 		   jiffies_to_clock_t(ttd),
-		   req->retrans,
+		   req->num_timeout,
 		   from_kuid_munged(seq_user_ns(seq), uid),
 		   0,  /* non standard timer */
 		   0, /* open_requests have no inode */
-- 
cgit v1.2.3-55-g7522


From 398f382c0a5bd62f0f31871e844700e1b9fd1ad3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Sun, 28 Oct 2012 08:27:19 +0000
Subject: pktgen: clean up ktime_t helpers

Some years ago, the ktime_t helper functions ktime_now() and ktime_lt()
have been introduced. Instead of defining them inside pktgen.c, they
should either use ktime_t library functions or, if not available, they
should be defined in ktime.h, so that also others can benefit from them.
ktime_compare() is introduced with a similar notion as in timespec_compare().

Signed-off-by: Daniel Borkmann <daniel.borkmann@tik.ee.ethz.ch>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ktime.h | 19 +++++++++++++++++++
 net/core/pktgen.c     | 41 +++++++++++++----------------------------
 2 files changed, 32 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 06177ba10a16..e83512f63df5 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -282,6 +282,25 @@ static inline int ktime_equal(const ktime_t cmp1, const ktime_t cmp2)
 	return cmp1.tv64 == cmp2.tv64;
 }
 
+/**
+ * ktime_compare - Compares two ktime_t variables for less, greater or equal
+ * @cmp1:	comparable1
+ * @cmp2:	comparable2
+ *
+ * Returns ...
+ *   cmp1  < cmp2: return <0
+ *   cmp1 == cmp2: return 0
+ *   cmp1  > cmp2: return >0
+ */
+static inline int ktime_compare(const ktime_t cmp1, const ktime_t cmp2)
+{
+	if (cmp1.tv64 < cmp2.tv64)
+		return -1;
+	if (cmp1.tv64 > cmp2.tv64)
+		return 1;
+	return 0;
+}
+
 static inline s64 ktime_to_us(const ktime_t kt)
 {
 	struct timeval tv = ktime_to_timeval(kt);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 1d1c216ffd9a..b29dacf900f9 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -419,20 +419,6 @@ struct pktgen_thread {
 #define REMOVE 1
 #define FIND   0
 
-static inline ktime_t ktime_now(void)
-{
-	struct timespec ts;
-	ktime_get_ts(&ts);
-
-	return timespec_to_ktime(ts);
-}
-
-/* This works even if 32 bit because of careful byte order choice */
-static inline int ktime_lt(const ktime_t cmp1, const ktime_t cmp2)
-{
-	return cmp1.tv64 < cmp2.tv64;
-}
-
 static const char version[] =
 	"Packet Generator for packet performance testing. "
 	"Version: " VERSION "\n";
@@ -675,7 +661,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\n");
 
 	/* not really stopped, more like last-running-at */
-	stopped = pkt_dev->running ? ktime_now() : pkt_dev->stopped_at;
+	stopped = pkt_dev->running ? ktime_get() : pkt_dev->stopped_at;
 	idle = pkt_dev->idle_acc;
 	do_div(idle, NSEC_PER_USEC);
 
@@ -2141,12 +2127,12 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
 		return;
 	}
 
-	start_time = ktime_now();
+	start_time = ktime_get();
 	if (remaining < 100000) {
 		/* for small delays (<100us), just loop until limit is reached */
 		do {
-			end_time = ktime_now();
-		} while (ktime_lt(end_time, spin_until));
+			end_time = ktime_get();
+		} while (ktime_compare(end_time, spin_until) < 0);
 	} else {
 		/* see do_nanosleep */
 		hrtimer_init_sleeper(&t, current);
@@ -2162,7 +2148,7 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
 			hrtimer_cancel(&t.timer);
 		} while (t.task && pkt_dev->running && !signal_pending(current));
 		__set_current_state(TASK_RUNNING);
-		end_time = ktime_now();
+		end_time = ktime_get();
 	}
 
 	pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time));
@@ -2912,8 +2898,7 @@ static void pktgen_run(struct pktgen_thread *t)
 			pktgen_clear_counters(pkt_dev);
 			pkt_dev->running = 1;	/* Cranke yeself! */
 			pkt_dev->skb = NULL;
-			pkt_dev->started_at =
-				pkt_dev->next_tx = ktime_now();
+			pkt_dev->started_at = pkt_dev->next_tx = ktime_get();
 
 			set_pkt_overhead(pkt_dev);
 
@@ -3072,7 +3057,7 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev)
 
 	kfree_skb(pkt_dev->skb);
 	pkt_dev->skb = NULL;
-	pkt_dev->stopped_at = ktime_now();
+	pkt_dev->stopped_at = ktime_get();
 	pkt_dev->running = 0;
 
 	show_results(pkt_dev, nr_frags);
@@ -3091,7 +3076,7 @@ static struct pktgen_dev *next_to_run(struct pktgen_thread *t)
 			continue;
 		if (best == NULL)
 			best = pkt_dev;
-		else if (ktime_lt(pkt_dev->next_tx, best->next_tx))
+		else if (ktime_compare(pkt_dev->next_tx, best->next_tx) < 0)
 			best = pkt_dev;
 	}
 	if_unlock(t);
@@ -3176,14 +3161,14 @@ static void pktgen_rem_thread(struct pktgen_thread *t)
 
 static void pktgen_resched(struct pktgen_dev *pkt_dev)
 {
-	ktime_t idle_start = ktime_now();
+	ktime_t idle_start = ktime_get();
 	schedule();
-	pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start));
+	pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start));
 }
 
 static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev)
 {
-	ktime_t idle_start = ktime_now();
+	ktime_t idle_start = ktime_get();
 
 	while (atomic_read(&(pkt_dev->skb->users)) != 1) {
 		if (signal_pending(current))
@@ -3194,7 +3179,7 @@ static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev)
 		else
 			cpu_relax();
 	}
-	pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start));
+	pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start));
 }
 
 static void pktgen_xmit(struct pktgen_dev *pkt_dev)
@@ -3216,7 +3201,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 	 * "never transmit"
 	 */
 	if (unlikely(pkt_dev->delay == ULLONG_MAX)) {
-		pkt_dev->next_tx = ktime_add_ns(ktime_now(), ULONG_MAX);
+		pkt_dev->next_tx = ktime_add_ns(ktime_get(), ULONG_MAX);
 		return;
 	}
 
-- 
cgit v1.2.3-55-g7522


From b26ddd813031666293c95e84c997eb8b1f97bd38 Mon Sep 17 00:00:00 2001
From: Neil Horman
Date: Mon, 29 Oct 2012 08:32:13 +0000
Subject: sctp: Clean up type-punning in sctp_cmd_t union

Lots of points in the sctp_cmd_interpreter function treat the sctp_cmd_t arg as
a void pointer, even though they are written as various other types.  Theres no
need for this as doing so just leads to possible type-punning issues that could
cause crashes, and if we remain type-consistent we can actually just remove the
void * member of the union entirely.

Change Notes:

v2)
	* Dropped chunk that modified SCTP_NULL to create a marker pattern
	 should anyone try to use a SCTP_NULL() assigned sctp_arg_t, Assigning
	 to .zero provides the same effect and should be faster, per Vlad Y.

v3)
	* Reverted part of V2, opting to use memset instead of .zero, so that
	 the entire union is initalized thus avoiding the i164 speculative load
	 problems previously encountered, per Dave M..  Also rewrote
	 SCTP_[NO]FORCE so as to use common infrastructure a little more

Signed-off-by: Neil Horman <nhorman@tuxdriver.com
CC: Vlad Yasevich <vyasevich@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: linux-sctp@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/command.h  | 38 ++++++++++++++++++++++----------------
 include/net/sctp/ulpqueue.h |  2 +-
 net/sctp/sm_sideeffect.c    | 45 ++++++++++++++++++++++-----------------------
 net/sctp/ulpqueue.c         |  3 +--
 4 files changed, 46 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 712b3bebeda7..35247271e557 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -130,8 +130,6 @@ typedef union {
 	__be16 err;
 	sctp_state_t state;
 	sctp_event_timeout_t to;
-	unsigned long zero;
-	void *ptr;
 	struct sctp_chunk *chunk;
 	struct sctp_association *asoc;
 	struct sctp_transport *transport;
@@ -154,23 +152,15 @@ typedef union {
  * which takes an __s32 and returns a sctp_arg_t containing the
  * __s32.  So, after foo = SCTP_I32(arg), foo.i32 == arg.
  */
-static inline sctp_arg_t SCTP_NULL(void)
-{
-	sctp_arg_t retval; retval.ptr = NULL; return retval;
-}
-static inline sctp_arg_t SCTP_NOFORCE(void)
-{
-	sctp_arg_t retval = {.zero = 0UL}; retval.i32 = 0; return retval;
-}
-static inline sctp_arg_t SCTP_FORCE(void)
-{
-	sctp_arg_t retval = {.zero = 0UL}; retval.i32 = 1; return retval;
-}
 
 #define SCTP_ARG_CONSTRUCTOR(name, type, elt) \
 static inline sctp_arg_t	\
 SCTP_## name (type arg)		\
-{ sctp_arg_t retval = {.zero = 0UL}; retval.elt = arg; return retval; }
+{ sctp_arg_t retval;\
+  memset(&retval, 0, sizeof(sctp_arg_t));\
+  retval.elt = arg;\
+  return retval;\
+}
 
 SCTP_ARG_CONSTRUCTOR(I32,	__s32, i32)
 SCTP_ARG_CONSTRUCTOR(U32,	__u32, u32)
@@ -181,7 +171,6 @@ SCTP_ARG_CONSTRUCTOR(ERROR,     int, error)
 SCTP_ARG_CONSTRUCTOR(PERR,      __be16, err)	/* protocol error */
 SCTP_ARG_CONSTRUCTOR(STATE,	sctp_state_t, state)
 SCTP_ARG_CONSTRUCTOR(TO,	sctp_event_timeout_t, to)
-SCTP_ARG_CONSTRUCTOR(PTR,	void *, ptr)
 SCTP_ARG_CONSTRUCTOR(CHUNK,	struct sctp_chunk *, chunk)
 SCTP_ARG_CONSTRUCTOR(ASOC,	struct sctp_association *, asoc)
 SCTP_ARG_CONSTRUCTOR(TRANSPORT,	struct sctp_transport *, transport)
@@ -192,6 +181,23 @@ SCTP_ARG_CONSTRUCTOR(PACKET,	struct sctp_packet *, packet)
 SCTP_ARG_CONSTRUCTOR(SACKH,	sctp_sackhdr_t *, sackh)
 SCTP_ARG_CONSTRUCTOR(DATAMSG,	struct sctp_datamsg *, msg)
 
+static inline sctp_arg_t SCTP_FORCE(void)
+{
+	return SCTP_I32(1);
+}
+
+static inline sctp_arg_t SCTP_NOFORCE(void)
+{
+	return SCTP_I32(0);
+}
+
+static inline sctp_arg_t SCTP_NULL(void)
+{
+	sctp_arg_t retval;
+	memset(&retval, 0, sizeof(sctp_arg_t));
+	return retval;
+}
+
 typedef struct {
 	sctp_arg_t obj;
 	sctp_verb_t verb;
diff --git a/include/net/sctp/ulpqueue.h b/include/net/sctp/ulpqueue.h
index 2e5ee0d8458d..ff1b8ba73ab1 100644
--- a/include/net/sctp/ulpqueue.h
+++ b/include/net/sctp/ulpqueue.h
@@ -72,7 +72,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *, struct sctp_ulpevent *ev);
 void sctp_ulpq_renege(struct sctp_ulpq *, struct sctp_chunk *, gfp_t);
 
 /* Perform partial delivery. */
-void sctp_ulpq_partial_delivery(struct sctp_ulpq *, struct sctp_chunk *, gfp_t);
+void sctp_ulpq_partial_delivery(struct sctp_ulpq *, gfp_t);
 
 /* Abort the partial delivery. */
 void sctp_ulpq_abort_pd(struct sctp_ulpq *, gfp_t);
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 6773d7803627..6eecf7e6338d 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1268,14 +1268,14 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 				sctp_outq_uncork(&asoc->outqueue);
 				local_cork = 0;
 			}
-			asoc = cmd->obj.ptr;
+			asoc = cmd->obj.asoc;
 			/* Register with the endpoint.  */
 			sctp_endpoint_add_asoc(ep, asoc);
 			sctp_hash_established(asoc);
 			break;
 
 		case SCTP_CMD_UPDATE_ASSOC:
-		       sctp_assoc_update(asoc, cmd->obj.ptr);
+		       sctp_assoc_update(asoc, cmd->obj.asoc);
 		       break;
 
 		case SCTP_CMD_PURGE_OUTQUEUE:
@@ -1315,7 +1315,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 			break;
 
 		case SCTP_CMD_PROCESS_FWDTSN:
-			sctp_cmd_process_fwdtsn(&asoc->ulpq, cmd->obj.ptr);
+			sctp_cmd_process_fwdtsn(&asoc->ulpq, cmd->obj.chunk);
 			break;
 
 		case SCTP_CMD_GEN_SACK:
@@ -1331,7 +1331,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 		case SCTP_CMD_PROCESS_SACK:
 			/* Process an inbound SACK.  */
 			error = sctp_cmd_process_sack(commands, asoc,
-						      cmd->obj.ptr);
+						      cmd->obj.chunk);
 			break;
 
 		case SCTP_CMD_GEN_INIT_ACK:
@@ -1352,15 +1352,15 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 			 * layer which will bail.
 			 */
 			error = sctp_cmd_process_init(commands, asoc, chunk,
-						      cmd->obj.ptr, gfp);
+						      cmd->obj.init, gfp);
 			break;
 
 		case SCTP_CMD_GEN_COOKIE_ECHO:
 			/* Generate a COOKIE ECHO chunk.  */
 			new_obj = sctp_make_cookie_echo(asoc, chunk);
 			if (!new_obj) {
-				if (cmd->obj.ptr)
-					sctp_chunk_free(cmd->obj.ptr);
+				if (cmd->obj.chunk)
+					sctp_chunk_free(cmd->obj.chunk);
 				goto nomem;
 			}
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
@@ -1369,9 +1369,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 			/* If there is an ERROR chunk to be sent along with
 			 * the COOKIE_ECHO, send it, too.
 			 */
-			if (cmd->obj.ptr)
+			if (cmd->obj.chunk)
 				sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
-						SCTP_CHUNK(cmd->obj.ptr));
+						SCTP_CHUNK(cmd->obj.chunk));
 
 			if (new_obj->transport) {
 				new_obj->transport->init_sent_count++;
@@ -1417,18 +1417,18 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 		case SCTP_CMD_CHUNK_ULP:
 			/* Send a chunk to the sockets layer.  */
 			SCTP_DEBUG_PRINTK("sm_sideff: %s %p, %s %p.\n",
-					  "chunk_up:", cmd->obj.ptr,
+					  "chunk_up:", cmd->obj.chunk,
 					  "ulpq:", &asoc->ulpq);
-			sctp_ulpq_tail_data(&asoc->ulpq, cmd->obj.ptr,
+			sctp_ulpq_tail_data(&asoc->ulpq, cmd->obj.chunk,
 					    GFP_ATOMIC);
 			break;
 
 		case SCTP_CMD_EVENT_ULP:
 			/* Send a notification to the sockets layer.  */
 			SCTP_DEBUG_PRINTK("sm_sideff: %s %p, %s %p.\n",
-					  "event_up:",cmd->obj.ptr,
+					  "event_up:",cmd->obj.ulpevent,
 					  "ulpq:",&asoc->ulpq);
-			sctp_ulpq_tail_event(&asoc->ulpq, cmd->obj.ptr);
+			sctp_ulpq_tail_event(&asoc->ulpq, cmd->obj.ulpevent);
 			break;
 
 		case SCTP_CMD_REPLY:
@@ -1438,12 +1438,12 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 				local_cork = 1;
 			}
 			/* Send a chunk to our peer.  */
-			error = sctp_outq_tail(&asoc->outqueue, cmd->obj.ptr);
+			error = sctp_outq_tail(&asoc->outqueue, cmd->obj.chunk);
 			break;
 
 		case SCTP_CMD_SEND_PKT:
 			/* Send a full packet to our peer.  */
-			packet = cmd->obj.ptr;
+			packet = cmd->obj.packet;
 			sctp_packet_transmit(packet);
 			sctp_ootb_pkt_free(packet);
 			break;
@@ -1480,7 +1480,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 			break;
 
 		case SCTP_CMD_SETUP_T2:
-			sctp_cmd_setup_t2(commands, asoc, cmd->obj.ptr);
+			sctp_cmd_setup_t2(commands, asoc, cmd->obj.chunk);
 			break;
 
 		case SCTP_CMD_TIMER_START_ONCE:
@@ -1514,7 +1514,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 			break;
 
 		case SCTP_CMD_INIT_CHOOSE_TRANSPORT:
-			chunk = cmd->obj.ptr;
+			chunk = cmd->obj.chunk;
 			t = sctp_assoc_choose_alter_transport(asoc,
 						asoc->init_last_sent_to);
 			asoc->init_last_sent_to = t;
@@ -1665,17 +1665,16 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 			break;
 
 		case SCTP_CMD_PART_DELIVER:
-			sctp_ulpq_partial_delivery(&asoc->ulpq, cmd->obj.ptr,
-						   GFP_ATOMIC);
+			sctp_ulpq_partial_delivery(&asoc->ulpq, GFP_ATOMIC);
 			break;
 
 		case SCTP_CMD_RENEGE:
-			sctp_ulpq_renege(&asoc->ulpq, cmd->obj.ptr,
+			sctp_ulpq_renege(&asoc->ulpq, cmd->obj.chunk,
 					 GFP_ATOMIC);
 			break;
 
 		case SCTP_CMD_SETUP_T4:
-			sctp_cmd_setup_t4(commands, asoc, cmd->obj.ptr);
+			sctp_cmd_setup_t4(commands, asoc, cmd->obj.chunk);
 			break;
 
 		case SCTP_CMD_PROCESS_OPERR:
@@ -1734,8 +1733,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 			break;
 
 		default:
-			pr_warn("Impossible command: %u, %p\n",
-				cmd->verb, cmd->obj.ptr);
+			pr_warn("Impossible command: %u\n",
+				cmd->verb);
 			break;
 		}
 
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 360d8697b95c..ada17464b65b 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -997,7 +997,6 @@ static __u16 sctp_ulpq_renege_frags(struct sctp_ulpq *ulpq, __u16 needed)
 
 /* Partial deliver the first message as there is pressure on rwnd. */
 void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq,
-				struct sctp_chunk *chunk,
 				gfp_t gfp)
 {
 	struct sctp_ulpevent *event;
@@ -1060,7 +1059,7 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 		sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn, chunk->transport);
 		sctp_ulpq_tail_data(ulpq, chunk, gfp);
 
-		sctp_ulpq_partial_delivery(ulpq, chunk, gfp);
+		sctp_ulpq_partial_delivery(ulpq, gfp);
 	}
 
 	sk_mem_reclaim(asoc->base.sk);
-- 
cgit v1.2.3-55-g7522


From 6da025fa23bb10c82f80de319c837ed2b02306e4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Sun, 28 Oct 2012 22:33:23 +0000
Subject: ipv4: avoid a test in ip_rt_put()

We can save a test in ip_rt_put(), considering dst_release() accepts
a NULL parameter, and dst is first element in rtable.

Add a BUILD_BUG_ON() to catch any change that could break this
assertion.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Cong Wang <amwang@redhat.com>
Acked-by: Cong Wang <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index bc40b633a5c4..2ea40c1b5e00 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -198,10 +198,13 @@ struct in_ifaddr;
 extern void fib_add_ifaddr(struct in_ifaddr *);
 extern void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *);
 
-static inline void ip_rt_put(struct rtable * rt)
+static inline void ip_rt_put(struct rtable *rt)
 {
-	if (rt)
-		dst_release(&rt->dst);
+	/* dst_release() accepts a NULL parameter.
+	 * We rely on dst being first structure in struct rtable
+	 */
+	BUILD_BUG_ON(offsetof(struct rtable, dst) != 0);
+	dst_release(&rt->dst);
 }
 
 #define IPTOS_RT_MASK	(IPTOS_TOS_MASK & ~3)
-- 
cgit v1.2.3-55-g7522


From 94e187c01512c9cf29e2ff54bf1a1b045f38293d Mon Sep 17 00:00:00 2001
From: Amerigo Wang
Date: Mon, 29 Oct 2012 00:13:19 +0000
Subject: ipv6: introduce ip6_rt_put()

As suggested by Eric, we could introduce a helper function
for ipv6 too, to avoid checking if rt is NULL before
dst_release().

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h              |  9 +++++++++
 net/ipv6/addrconf.c                |  7 +++----
 net/ipv6/anycast.c                 |  2 +-
 net/ipv6/fib6_rules.c              |  2 +-
 net/ipv6/ip6_gre.c                 |  2 +-
 net/ipv6/ip6_output.c              |  4 ++--
 net/ipv6/ip6_tunnel.c              |  5 ++---
 net/ipv6/mcast.c                   |  4 ++--
 net/ipv6/ndisc.c                   |  7 +++----
 net/ipv6/netfilter/ip6t_rpfilter.c |  2 +-
 net/ipv6/route.c                   | 14 +++++++-------
 11 files changed, 32 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 20210d79e36a..d1327e4d126b 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -213,6 +213,15 @@ static inline void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
 	dst_hold(new);
 }
 
+static inline void ip6_rt_put(struct rt6_info *rt)
+{
+	/* dst_release() accepts a NULL parameter.
+	 * We rely on dst being first structure in struct rt6_info
+	 */
+	BUILD_BUG_ON(offsetof(struct rt6_info, dst) != 0);
+	dst_release(&rt->dst);
+}
+
 struct fib6_walker_t {
 	struct list_head lh;
 	struct fib6_node *root, *node;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ced58e1d91b6..fab23db8ee73 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -699,7 +699,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
 		pr_warn("Freeing alive inet6 address %p\n", ifp);
 		return;
 	}
-	dst_release(&ifp->rt->dst);
+	ip6_rt_put(ifp->rt);
 
 	kfree_rcu(ifp, rcu);
 }
@@ -951,7 +951,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 				rt6_set_expires(rt, expires);
 			}
 		}
-		dst_release(&rt->dst);
+		ip6_rt_put(rt);
 	}
 
 	/* clean up prefsrc entries */
@@ -2027,8 +2027,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 			addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len,
 					      dev, expires, flags);
 		}
-		if (rt)
-			dst_release(&rt->dst);
+		ip6_rt_put(rt);
 	}
 
 	/* Try to figure out our local address for this prefix */
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index cdf02be5f191..4963c769a13f 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -84,7 +84,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		rt = rt6_lookup(net, addr, NULL, 0, 0);
 		if (rt) {
 			dev = rt->dst.dev;
-			dst_release(&rt->dst);
+			ip6_rt_put(rt);
 		} else if (ishost) {
 			err = -EADDRNOTAVAIL;
 			goto error;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index d9fb9110f607..2e1a432867c0 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -100,7 +100,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 		goto out;
 	}
 again:
-	dst_release(&rt->dst);
+	ip6_rt_put(rt);
 	rt = NULL;
 	goto out;
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 0185679c5f53..bbe2e7b538b4 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1069,7 +1069,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
 					dev->mtu = IPV6_MIN_MTU;
 			}
 		}
-		dst_release(&rt->dst);
+		ip6_rt_put(rt);
 	}
 
 	t->hlen = addend;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e10c77b4fbec..3deaa4e2e8e2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -755,7 +755,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 		if (err == 0) {
 			IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 				      IPSTATS_MIB_FRAGOKS);
-			dst_release(&rt->dst);
+			ip6_rt_put(rt);
 			return 0;
 		}
 
@@ -767,7 +767,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 		IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 			      IPSTATS_MIB_FRAGFAILS);
-		dst_release(&rt->dst);
+		ip6_rt_put(rt);
 		return err;
 
 slow_path_clean:
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index cb7e2ded6f08..09482f723064 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -663,8 +663,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 		icmpv6_send(skb2, rel_type, rel_code, rel_info);
 
-		if (rt)
-			dst_release(&rt->dst);
+		ip6_rt_put(rt);
 
 		kfree_skb(skb2);
 	}
@@ -1208,7 +1207,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 			if (dev->mtu < IPV6_MIN_MTU)
 				dev->mtu = IPV6_MIN_MTU;
 		}
-		dst_release(&rt->dst);
+		ip6_rt_put(rt);
 	}
 }
 
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 92f8e48e4ba4..b19ed51a45bb 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -163,7 +163,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		rt = rt6_lookup(net, addr, NULL, 0, 0);
 		if (rt) {
 			dev = rt->dst.dev;
-			dst_release(&rt->dst);
+			ip6_rt_put(rt);
 		}
 	} else
 		dev = dev_get_by_index_rcu(net, ifindex);
@@ -260,7 +260,7 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
 
 		if (rt) {
 			dev = rt->dst.dev;
-			dst_release(&rt->dst);
+			ip6_rt_put(rt);
 		}
 	} else
 		dev = dev_get_by_index_rcu(net, ifindex);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index ff36194a71aa..ae0cf818a8f0 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1145,7 +1145,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 			ND_PRINTK(0, err,
 				  "RA: %s got default router without neighbour\n",
 				  __func__);
-			dst_release(&rt->dst);
+			ip6_rt_put(rt);
 			return;
 		}
 	}
@@ -1170,7 +1170,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 			ND_PRINTK(0, err,
 				  "RA: %s got default router without neighbour\n",
 				  __func__);
-			dst_release(&rt->dst);
+			ip6_rt_put(rt);
 			return;
 		}
 		neigh->flags |= NTF_ROUTER;
@@ -1326,8 +1326,7 @@ skip_routeinfo:
 		ND_PRINTK(2, warn, "RA: invalid RA options\n");
 	}
 out:
-	if (rt)
-		dst_release(&rt->dst);
+	ip6_rt_put(rt);
 	if (neigh)
 		neigh_release(neigh);
 }
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index 5d1d8b04d694..5060d54199ab 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -67,7 +67,7 @@ static bool rpfilter_lookup_reverse6(const struct sk_buff *skb,
 	if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE))
 		ret = true;
  out:
-	dst_release(&rt->dst);
+	ip6_rt_put(rt);
 	return ret;
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9c7b5d800495..c1cfcb7e5632 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -732,7 +732,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 		else
 			rt6_set_expires(rt, jiffies + HZ * lifetime);
 
-		dst_release(&rt->dst);
+		ip6_rt_put(rt);
 	}
 	return 0;
 }
@@ -948,7 +948,7 @@ restart:
 	else
 		goto out2;
 
-	dst_release(&rt->dst);
+	ip6_rt_put(rt);
 	rt = nrt ? : net->ipv6.ip6_null_entry;
 
 	dst_hold(&rt->dst);
@@ -965,7 +965,7 @@ restart:
 	 * Race condition! In the gap, when table->tb6_lock was
 	 * released someone could insert this route.  Relookup.
 	 */
-	dst_release(&rt->dst);
+	ip6_rt_put(rt);
 	goto relookup;
 
 out:
@@ -1576,7 +1576,7 @@ int ip6_route_add(struct fib6_config *cfg)
 				goto out;
 			if (dev) {
 				if (dev != grt->dst.dev) {
-					dst_release(&grt->dst);
+					ip6_rt_put(grt);
 					goto out;
 				}
 			} else {
@@ -1587,7 +1587,7 @@ int ip6_route_add(struct fib6_config *cfg)
 			}
 			if (!(grt->rt6i_flags & RTF_GATEWAY))
 				err = 0;
-			dst_release(&grt->dst);
+			ip6_rt_put(grt);
 
 			if (err)
 				goto out;
@@ -1673,7 +1673,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
 	write_unlock_bh(&table->tb6_lock);
 
 out:
-	dst_release(&rt->dst);
+	ip6_rt_put(rt);
 	return err;
 }
 
@@ -2732,7 +2732,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb) {
-		dst_release(&rt->dst);
+		ip6_rt_put(rt);
 		err = -ENOBUFS;
 		goto errout;
 	}
-- 
cgit v1.2.3-55-g7522


From 4f99ad51292078cc47343c17d3870764588cff73 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli
Date: Tue, 30 Oct 2012 04:08:41 +0000
Subject: if_ether.h: add B.A.T.M.A.N.-Advanced Ethertype

Add Ethertype 0x4305 (not an officially registered id).
This Ethertype is used by every frame generated by B.A.T.M.A.N.-Advanced. Its
definition is currently batman-adv local only and since it is not officially
registered it is better to make its definition kernel-wide so that we avoid
collisions given by future unofficial uses of the same Ethertype.

Signed-off-by: Antonio Quartulli <ordex@autistici.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_ether.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
index 0343e1f0582c..67fb87ca1094 100644
--- a/include/uapi/linux/if_ether.h
+++ b/include/uapi/linux/if_ether.h
@@ -48,6 +48,7 @@
 #define	ETH_P_BPQ	0x08FF		/* G8BPQ AX.25 Ethernet Packet	[ NOT AN OFFICIALLY REGISTERED ID ] */
 #define ETH_P_IEEEPUP	0x0a00		/* Xerox IEEE802.3 PUP packet */
 #define ETH_P_IEEEPUPAT	0x0a01		/* Xerox IEEE802.3 PUP Addr Trans packet */
+#define ETH_P_BATMAN	0x4305		/* B.A.T.M.A.N.-Advanced packet [ NOT AN OFFICIALLY REGISTERED ID ] */
 #define ETH_P_DEC       0x6000          /* DEC Assigned proto           */
 #define ETH_P_DNA_DL    0x6001          /* DEC DNA Dump/Load            */
 #define ETH_P_DNA_RC    0x6002          /* DEC DNA Remote Console       */
-- 
cgit v1.2.3-55-g7522


From cdfcc572be0a8b423cecfb4ab5fd735fafe9c54a Mon Sep 17 00:00:00 2001
From: Yinghai Lu
Date: Tue, 30 Oct 2012 14:31:38 -0600
Subject: PCI: Add pci_stop_and_remove_root_bus()

It supports both PCI root bus and PCI bus under PCI bridge.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>---
 drivers/pci/remove.c | 36 ++++++++++++++++++++++++++++++++++++
 include/linux/pci.h  |  2 ++
 2 files changed, 38 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 513972f3ed13..7c0fd9252e6f 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -111,3 +111,39 @@ void pci_stop_and_remove_bus_device(struct pci_dev *dev)
 	pci_remove_bus_device(dev);
 }
 EXPORT_SYMBOL(pci_stop_and_remove_bus_device);
+
+void pci_stop_root_bus(struct pci_bus *bus)
+{
+	struct pci_dev *child, *tmp;
+	struct pci_host_bridge *host_bridge;
+
+	if (!pci_is_root_bus(bus))
+		return;
+
+	host_bridge = to_pci_host_bridge(bus->bridge);
+	list_for_each_entry_safe_reverse(child, tmp,
+					 &bus->devices, bus_list)
+		pci_stop_bus_device(child);
+
+	/* stop the host bridge */
+	device_del(&host_bridge->dev);
+}
+
+void pci_remove_root_bus(struct pci_bus *bus)
+{
+	struct pci_dev *child, *tmp;
+	struct pci_host_bridge *host_bridge;
+
+	if (!pci_is_root_bus(bus))
+		return;
+
+	host_bridge = to_pci_host_bridge(bus->bridge);
+	list_for_each_entry_safe(child, tmp,
+				 &bus->devices, bus_list)
+		pci_remove_bus_device(child);
+	pci_remove_bus(bus);
+	host_bridge->bus = NULL;
+
+	/* remove the host bridge */
+	put_device(&host_bridge->dev);
+}
diff --git a/include/linux/pci.h b/include/linux/pci.h
index f543eb3b1c0c..786094254d57 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -712,6 +712,8 @@ extern struct pci_dev *pci_dev_get(struct pci_dev *dev);
 extern void pci_dev_put(struct pci_dev *dev);
 extern void pci_remove_bus(struct pci_bus *b);
 extern void pci_stop_and_remove_bus_device(struct pci_dev *dev);
+void pci_stop_root_bus(struct pci_bus *bus);
+void pci_remove_root_bus(struct pci_bus *bus);
 void pci_setup_cardbus(struct pci_bus *bus);
 extern void pci_sort_breadthfirst(void);
 #define dev_is_pci(d) ((d)->bus == &pci_bus_type)
-- 
cgit v1.2.3-55-g7522


From 3b98c0c2093d1f92e5b7394ae0b13d142e7ef880 Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Mon, 7 Mar 2011 12:49:34 +0100
Subject: drbd: switch configuration interface from connector to genetlink

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_actlog.c |    3 +-
 drivers/block/drbd/drbd_int.h    |   36 +-
 drivers/block/drbd/drbd_main.c   |   27 +-
 drivers/block/drbd/drbd_nl.c     | 1536 +++++++++++++++++++-------------------
 drivers/block/drbd/drbd_state.c  |    7 +-
 include/linux/drbd.h             |   35 +-
 include/linux/genl_magic_func.h  |    2 +-
 7 files changed, 806 insertions(+), 840 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 7cd78617669b..c1a90616776b 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -702,6 +702,7 @@ static int w_update_odbm(struct drbd_work *w, int unused)
 {
 	struct update_odbm_work *udw = container_of(w, struct update_odbm_work, w);
 	struct drbd_conf *mdev = w->mdev;
+	struct sib_info sib = { .sib_reason = SIB_SYNC_PROGRESS, };
 
 	if (!get_ldev(mdev)) {
 		if (__ratelimit(&drbd_ratelimit_state))
@@ -725,7 +726,7 @@ static int w_update_odbm(struct drbd_work *w, int unused)
 			break;
 		}
 	}
-	drbd_bcast_sync_progress(mdev);
+	drbd_bcast_event(mdev, &sib);
 
 	return 1;
 }
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index e68758344647..429fd8da6b71 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -44,6 +44,7 @@
 #include <net/tcp.h>
 #include <linux/lru_cache.h>
 #include <linux/prefetch.h>
+#include <linux/drbd_genl_api.h>
 #include <linux/drbd.h>
 #include "drbd_state.h"
 
@@ -65,7 +66,6 @@
 extern unsigned int minor_count;
 extern int disable_sendpage;
 extern int allow_oos;
-extern unsigned int cn_idx;
 
 #ifdef CONFIG_DRBD_FAULT_INJECTION
 extern int enable_faults;
@@ -865,14 +865,6 @@ struct drbd_md {
 	 */
 };
 
-/* for sync_conf and other types... */
-#define NL_PACKET(name, number, fields) struct name { fields };
-#define NL_INTEGER(pn,pr,member) int member;
-#define NL_INT64(pn,pr,member) __u64 member;
-#define NL_BIT(pn,pr,member)   unsigned member:1;
-#define NL_STRING(pn,pr,member,len) unsigned char member[len]; int member ## _len;
-#include "linux/drbd_nl.h"
-
 struct drbd_backing_dev {
 	struct block_device *backing_bdev;
 	struct block_device *md_bdev;
@@ -1502,7 +1494,7 @@ enum drbd_ret_code conn_new_minor(struct drbd_tconn *tconn, unsigned int minor,
 extern void drbd_free_mdev(struct drbd_conf *mdev);
 extern void drbd_delete_device(unsigned int minor);
 
-struct drbd_tconn *drbd_new_tconn(char *name);
+struct drbd_tconn *drbd_new_tconn(const char *name);
 extern void drbd_free_tconn(struct drbd_tconn *tconn);
 struct drbd_tconn *conn_by_name(const char *name);
 
@@ -1679,16 +1671,22 @@ extern int __drbd_set_out_of_sync(struct drbd_conf *mdev, sector_t sector,
 extern void drbd_al_apply_to_bm(struct drbd_conf *mdev);
 extern void drbd_al_shrink(struct drbd_conf *mdev);
 
-
 /* drbd_nl.c */
-
-void drbd_nl_cleanup(void);
-int __init drbd_nl_init(void);
-void drbd_bcast_state(struct drbd_conf *mdev, union drbd_state);
-void drbd_bcast_sync_progress(struct drbd_conf *mdev);
-void drbd_bcast_ee(struct drbd_conf *, const char *, const int, const char *,
-		   const char *, const struct drbd_peer_request *);
-
+/* state info broadcast */
+struct sib_info {
+	enum drbd_state_info_bcast_reason sib_reason;
+	union {
+		struct {
+			char *helper_name;
+			unsigned helper_exit_code;
+		};
+		struct {
+			union drbd_state os;
+			union drbd_state ns;
+		};
+	};
+};
+void drbd_bcast_event(struct drbd_conf *mdev, const struct sib_info *sib);
 
 /*
  * inline helper functions
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 9f6db5947c65..9697ab872098 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -86,7 +86,6 @@ MODULE_PARM_DESC(allow_oos, "DONT USE!");
 module_param(minor_count, uint, 0444);
 module_param(disable_sendpage, bool, 0644);
 module_param(allow_oos, bool, 0);
-module_param(cn_idx, uint, 0444);
 module_param(proc_details, int, 0644);
 
 #ifdef CONFIG_DRBD_FAULT_INJECTION
@@ -108,7 +107,6 @@ module_param(fault_devs, int, 0644);
 unsigned int minor_count = DRBD_MINOR_COUNT_DEF;
 int disable_sendpage;
 int allow_oos;
-unsigned int cn_idx = CN_IDX_DRBD;
 int proc_details;       /* Detail level in proc drbd*/
 
 /* Module parameter for setting the user mode helper program
@@ -2175,7 +2173,7 @@ static void drbd_cleanup(void)
 	if (drbd_proc)
 		remove_proc_entry("drbd", NULL);
 
-	drbd_nl_cleanup();
+	drbd_genl_unregister();
 
 	idr_for_each_entry(&minors, mdev, i)
 		drbd_delete_device(i);
@@ -2237,6 +2235,9 @@ struct drbd_tconn *conn_by_name(const char *name)
 {
 	struct drbd_tconn *tconn;
 
+	if (!name || !name[0])
+		return NULL;
+
 	write_lock_irq(&global_state_lock);
 	list_for_each_entry(tconn, &drbd_tconns, all_tconn) {
 		if (!strcmp(tconn->name, name))
@@ -2248,7 +2249,7 @@ found:
 	return tconn;
 }
 
-struct drbd_tconn *drbd_new_tconn(char *name)
+struct drbd_tconn *drbd_new_tconn(const char *name)
 {
 	struct drbd_tconn *tconn;
 
@@ -2333,6 +2334,7 @@ enum drbd_ret_code conn_new_minor(struct drbd_tconn *tconn, unsigned int minor,
 
 	mdev->tconn = tconn;
 	mdev->minor = minor;
+	mdev->vnr = vnr;
 
 	drbd_init_set_defaults(mdev);
 
@@ -2461,10 +2463,6 @@ int __init drbd_init(void)
 #endif
 	}
 
-	err = drbd_nl_init();
-	if (err)
-		return err;
-
 	err = register_blkdev(DRBD_MAJOR, "drbd");
 	if (err) {
 		printk(KERN_ERR
@@ -2473,6 +2471,13 @@ int __init drbd_init(void)
 		return err;
 	}
 
+	err = drbd_genl_register();
+	if (err) {
+		printk(KERN_ERR "drbd: unable to register generic netlink family\n");
+		goto fail;
+	}
+
+
 	register_reboot_notifier(&drbd_notifier);
 
 	/*
@@ -2487,12 +2492,12 @@ int __init drbd_init(void)
 
 	err = drbd_create_mempools();
 	if (err)
-		goto Enomem;
+		goto fail;
 
 	drbd_proc = proc_create_data("drbd", S_IFREG | S_IRUGO , NULL, &drbd_proc_fops, NULL);
 	if (!drbd_proc)	{
 		printk(KERN_ERR "drbd: unable to register proc file\n");
-		goto Enomem;
+		goto fail;
 	}
 
 	rwlock_init(&global_state_lock);
@@ -2507,7 +2512,7 @@ int __init drbd_init(void)
 
 	return 0; /* Success! */
 
-Enomem:
+fail:
 	drbd_cleanup();
 	if (err == -ENOMEM)
 		/* currently always the case */
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index f2739fd188a0..f9be14248e33 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -29,110 +29,225 @@
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/slab.h>
-#include <linux/connector.h>
 #include <linux/blkpg.h>
 #include <linux/cpumask.h>
 #include "drbd_int.h"
 #include "drbd_req.h"
 #include "drbd_wrappers.h"
 #include <asm/unaligned.h>
-#include <linux/drbd_tag_magic.h>
 #include <linux/drbd_limits.h>
-#include <linux/compiler.h>
 #include <linux/kthread.h>
 
-static unsigned short *tl_add_blob(unsigned short *, enum drbd_tags, const void *, int);
-static unsigned short *tl_add_str(unsigned short *, enum drbd_tags, const char *);
-static unsigned short *tl_add_int(unsigned short *, enum drbd_tags, const void *);
-
-/* see get_sb_bdev and bd_claim */
+#include <net/genetlink.h>
+
+/* .doit */
+// int drbd_adm_create_resource(struct sk_buff *skb, struct genl_info *info);
+// int drbd_adm_delete_resource(struct sk_buff *skb, struct genl_info *info);
+
+int drbd_adm_add_minor(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_delete_minor(struct sk_buff *skb, struct genl_info *info);
+
+int drbd_adm_create_connection(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_delete_connection(struct sk_buff *skb, struct genl_info *info);
+
+int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_pause_sync(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_resume_sync(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_suspend_io(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_outdate(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_syncer(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info);
+/* .dumpit */
+int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb);
+
+#include <linux/drbd_genl_api.h>
+#include <linux/genl_magic_func.h>
+
+/* used blkdev_get_by_path, to claim our meta data device(s) */
 static char *drbd_m_holder = "Hands off! this is DRBD's meta data device.";
 
-/* Generate the tag_list to struct functions */
-#define NL_PACKET(name, number, fields) \
-static int name ## _from_tags( \
-	unsigned short *tags, struct name *arg) __attribute__ ((unused)); \
-static int name ## _from_tags( \
-	unsigned short *tags, struct name *arg) \
-{ \
-	int tag; \
-	int dlen; \
-	\
-	while ((tag = get_unaligned(tags++)) != TT_END) {	\
-		dlen = get_unaligned(tags++);			\
-		switch (tag_number(tag)) { \
-		fields \
-		default: \
-			if (tag & T_MANDATORY) { \
-				printk(KERN_ERR "drbd: Unknown tag: %d\n", tag_number(tag)); \
-				return 0; \
-			} \
-		} \
-		tags = (unsigned short *)((char *)tags + dlen); \
-	} \
-	return 1; \
+/* Configuration is strictly serialized, because generic netlink message
+ * processing is strictly serialized by the genl_lock().
+ * Which means we can use one static global drbd_config_context struct.
+ */
+static struct drbd_config_context {
+	/* assigned from drbd_genlmsghdr */
+	unsigned int minor;
+	/* assigned from request attributes, if present */
+	unsigned int volume;
+#define VOLUME_UNSPECIFIED		(-1U)
+	/* pointer into the request skb,
+	 * limited lifetime! */
+	char *conn_name;
+
+	/* reply buffer */
+	struct sk_buff *reply_skb;
+	/* pointer into reply buffer */
+	struct drbd_genlmsghdr *reply_dh;
+	/* resolved from attributes, if possible */
+	struct drbd_conf *mdev;
+	struct drbd_tconn *tconn;
+} adm_ctx;
+
+static void drbd_adm_send_reply(struct sk_buff *skb, struct genl_info *info)
+{
+	genlmsg_end(skb, genlmsg_data(nlmsg_data(nlmsg_hdr(skb))));
+	if (genlmsg_reply(skb, info))
+		printk(KERN_ERR "drbd: error sending genl reply\n");
 }
-#define NL_INTEGER(pn, pr, member) \
-	case pn: /* D_ASSERT( tag_type(tag) == TT_INTEGER ); */ \
-		arg->member = get_unaligned((int *)(tags));	\
-		break;
-#define NL_INT64(pn, pr, member) \
-	case pn: /* D_ASSERT( tag_type(tag) == TT_INT64 ); */ \
-		arg->member = get_unaligned((u64 *)(tags));	\
-		break;
-#define NL_BIT(pn, pr, member) \
-	case pn: /* D_ASSERT( tag_type(tag) == TT_BIT ); */ \
-		arg->member = *(char *)(tags) ? 1 : 0; \
-		break;
-#define NL_STRING(pn, pr, member, len) \
-	case pn: /* D_ASSERT( tag_type(tag) == TT_STRING ); */ \
-		if (dlen > len) { \
-			printk(KERN_ERR "drbd: arg too long: %s (%u wanted, max len: %u bytes)\n", \
-				#member, dlen, (unsigned int)len); \
-			return 0; \
-		} \
-		 arg->member ## _len = dlen; \
-		 memcpy(arg->member, tags, min_t(size_t, dlen, len)); \
-		 break;
-#include "linux/drbd_nl.h"
-
-/* Generate the struct to tag_list functions */
-#define NL_PACKET(name, number, fields) \
-static unsigned short* \
-name ## _to_tags( \
-	struct name *arg, unsigned short *tags) __attribute__ ((unused)); \
-static unsigned short* \
-name ## _to_tags( \
-	struct name *arg, unsigned short *tags) \
-{ \
-	fields \
-	return tags; \
+
+/* Used on a fresh "drbd_adm_prepare"d reply_skb, this cannot fail: The only
+ * reason it could fail was no space in skb, and there are 4k available. */
+static int drbd_msg_put_info(const char *info)
+{
+	struct sk_buff *skb = adm_ctx.reply_skb;
+	struct nlattr *nla;
+	int err = -EMSGSIZE;
+
+	if (!info || !info[0])
+		return 0;
+
+	nla = nla_nest_start(skb, DRBD_NLA_CFG_REPLY);
+	if (!nla)
+		return err;
+
+	err = nla_put_string(skb, T_info_text, info);
+	if (err) {
+		nla_nest_cancel(skb, nla);
+		return err;
+	} else
+		nla_nest_end(skb, nla);
+	return 0;
 }
 
-#define NL_INTEGER(pn, pr, member) \
-	put_unaligned(pn | pr | TT_INTEGER, tags++);	\
-	put_unaligned(sizeof(int), tags++);		\
-	put_unaligned(arg->member, (int *)tags);	\
-	tags = (unsigned short *)((char *)tags+sizeof(int));
-#define NL_INT64(pn, pr, member) \
-	put_unaligned(pn | pr | TT_INT64, tags++);	\
-	put_unaligned(sizeof(u64), tags++);		\
-	put_unaligned(arg->member, (u64 *)tags);	\
-	tags = (unsigned short *)((char *)tags+sizeof(u64));
-#define NL_BIT(pn, pr, member) \
-	put_unaligned(pn | pr | TT_BIT, tags++);	\
-	put_unaligned(sizeof(char), tags++);		\
-	*(char *)tags = arg->member; \
-	tags = (unsigned short *)((char *)tags+sizeof(char));
-#define NL_STRING(pn, pr, member, len) \
-	put_unaligned(pn | pr | TT_STRING, tags++);	\
-	put_unaligned(arg->member ## _len, tags++);	\
-	memcpy(tags, arg->member, arg->member ## _len); \
-	tags = (unsigned short *)((char *)tags + arg->member ## _len);
-#include "linux/drbd_nl.h"
-
-void drbd_bcast_ev_helper(struct drbd_conf *mdev, char *helper_name);
-void drbd_nl_send_reply(struct cn_msg *, int);
+/* This would be a good candidate for a "pre_doit" hook,
+ * and per-family private info->pointers.
+ * But we need to stay compatible with older kernels.
+ * If it returns successfully, adm_ctx members are valid.
+ */
+#define DRBD_ADM_NEED_MINOR	1
+#define DRBD_ADM_NEED_CONN	2
+static int drbd_adm_prepare(struct sk_buff *skb, struct genl_info *info,
+		unsigned flags)
+{
+	struct drbd_genlmsghdr *d_in = info->userhdr;
+	const u8 cmd = info->genlhdr->cmd;
+	int err;
+
+	memset(&adm_ctx, 0, sizeof(adm_ctx));
+
+	/* genl_rcv_msg only checks for CAP_NET_ADMIN on "GENL_ADMIN_PERM" :( */
+	if (cmd != DRBD_ADM_GET_STATUS
+	&& security_netlink_recv(skb, CAP_SYS_ADMIN))
+	       return -EPERM;
+
+	adm_ctx.reply_skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!adm_ctx.reply_skb)
+		goto fail;
+
+	adm_ctx.reply_dh = genlmsg_put_reply(adm_ctx.reply_skb,
+					info, &drbd_genl_family, 0, cmd);
+	/* put of a few bytes into a fresh skb of >= 4k will always succeed.
+	 * but anyways */
+	if (!adm_ctx.reply_dh)
+		goto fail;
+
+	adm_ctx.reply_dh->minor = d_in->minor;
+	adm_ctx.reply_dh->ret_code = NO_ERROR;
+
+	if (info->attrs[DRBD_NLA_CFG_CONTEXT]) {
+		struct nlattr *nla;
+		/* parse and validate only */
+		err = drbd_cfg_context_from_attrs(NULL, info->attrs);
+		if (err)
+			goto fail;
+
+		/* It was present, and valid,
+		 * copy it over to the reply skb. */
+		err = nla_put_nohdr(adm_ctx.reply_skb,
+				info->attrs[DRBD_NLA_CFG_CONTEXT]->nla_len,
+				info->attrs[DRBD_NLA_CFG_CONTEXT]);
+		if (err)
+			goto fail;
+
+		/* and assign stuff to the global adm_ctx */
+		nla = nested_attr_tb[__nla_type(T_ctx_volume)];
+		adm_ctx.volume = nla ? nla_get_u32(nla) : VOLUME_UNSPECIFIED;
+		nla = nested_attr_tb[__nla_type(T_ctx_conn_name)];
+		if (nla)
+			adm_ctx.conn_name = nla_data(nla);
+	} else
+		adm_ctx.volume = VOLUME_UNSPECIFIED;
+
+	adm_ctx.minor = d_in->minor;
+	adm_ctx.mdev = minor_to_mdev(d_in->minor);
+	adm_ctx.tconn = conn_by_name(adm_ctx.conn_name);
+
+	if (!adm_ctx.mdev && (flags & DRBD_ADM_NEED_MINOR)) {
+		drbd_msg_put_info("unknown minor");
+		return ERR_MINOR_INVALID;
+	}
+	if (!adm_ctx.tconn && (flags & DRBD_ADM_NEED_CONN)) {
+		drbd_msg_put_info("unknown connection");
+		return ERR_INVALID_REQUEST;
+	}
+
+	/* some more paranoia, if the request was over-determined */
+	if (adm_ctx.mdev &&
+	    adm_ctx.volume != VOLUME_UNSPECIFIED &&
+	    adm_ctx.volume != adm_ctx.mdev->vnr) {
+		pr_warning("request: minor=%u, volume=%u; but that minor is volume %u in %s\n",
+				adm_ctx.minor, adm_ctx.volume,
+				adm_ctx.mdev->vnr, adm_ctx.mdev->tconn->name);
+		drbd_msg_put_info("over-determined configuration context mismatch");
+		return ERR_INVALID_REQUEST;
+	}
+	if (adm_ctx.mdev && adm_ctx.tconn &&
+	    adm_ctx.mdev->tconn != adm_ctx.tconn) {
+		pr_warning("request: minor=%u, conn=%s; but that minor belongs to connection %s\n",
+				adm_ctx.minor, adm_ctx.conn_name, adm_ctx.mdev->tconn->name);
+		drbd_msg_put_info("over-determined configuration context mismatch");
+		return ERR_INVALID_REQUEST;
+	}
+	return NO_ERROR;
+
+fail:
+	nlmsg_free(adm_ctx.reply_skb);
+	adm_ctx.reply_skb = NULL;
+	return -ENOMEM;
+}
+
+static int drbd_adm_finish(struct genl_info *info, int retcode)
+{
+	struct nlattr *nla;
+	const char *conn_name = NULL;
+
+	if (!adm_ctx.reply_skb)
+		return -ENOMEM;
+
+	adm_ctx.reply_dh->ret_code = retcode;
+
+	nla = info->attrs[DRBD_NLA_CFG_CONTEXT];
+	if (nla) {
+		nla = nla_find_nested(nla, __nla_type(T_ctx_conn_name));
+		if (nla)
+			conn_name = nla_data(nla);
+	}
+
+	drbd_adm_send_reply(adm_ctx.reply_skb, info);
+	return 0;
+}
 
 int drbd_khelper(struct drbd_conf *mdev, char *cmd)
 {
@@ -142,9 +257,9 @@ int drbd_khelper(struct drbd_conf *mdev, char *cmd)
 			NULL, /* Will be set to address family */
 			NULL, /* Will be set to address */
 			NULL };
-
 	char mb[12], af[20], ad[60], *afs;
 	char *argv[] = {usermode_helper, cmd, mb, NULL };
+	struct sib_info sib;
 	int ret;
 
 	snprintf(mb, 12, "minor-%d", mdev_to_minor(mdev));
@@ -177,8 +292,9 @@ int drbd_khelper(struct drbd_conf *mdev, char *cmd)
 	drbd_md_sync(mdev);
 
 	dev_info(DEV, "helper command: %s %s %s\n", usermode_helper, cmd, mb);
-
-	drbd_bcast_ev_helper(mdev, cmd);
+	sib.sib_reason = SIB_HELPER_PRE;
+	sib.helper_name = cmd;
+	drbd_bcast_event(mdev, &sib);
 	ret = call_usermodehelper(usermode_helper, argv, envp, 1);
 	if (ret)
 		dev_warn(DEV, "helper command: %s %s %s exit code %u (0x%x)\n",
@@ -188,6 +304,9 @@ int drbd_khelper(struct drbd_conf *mdev, char *cmd)
 		dev_info(DEV, "helper command: %s %s %s exit code %u (0x%x)\n",
 				usermode_helper, cmd, mb,
 				(ret >> 8) & 0xff, ret);
+	sib.sib_reason = SIB_HELPER_POST;
+	sib.helper_exit_code = ret;
+	drbd_bcast_event(mdev, &sib);
 
 	if (ret < 0) /* Ignore any ERRNOs we got. */
 		ret = 0;
@@ -362,7 +481,7 @@ drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force)
 		}
 
 		if (rv == SS_NOTHING_TO_DO)
-			goto fail;
+			goto out;
 		if (rv == SS_PRIMARY_NOP && mask.pdsk == 0) {
 			nps = drbd_try_outdate_peer(mdev);
 
@@ -388,13 +507,13 @@ drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force)
 			rv = _drbd_request_state(mdev, mask, val,
 						CS_VERBOSE + CS_WAIT_COMPLETE);
 			if (rv < SS_SUCCESS)
-				goto fail;
+				goto out;
 		}
 		break;
 	}
 
 	if (rv < SS_SUCCESS)
-		goto fail;
+		goto out;
 
 	if (forced)
 		dev_warn(DEV, "Forced to consider local data as UpToDate!\n");
@@ -438,33 +557,46 @@ drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force)
 	drbd_md_sync(mdev);
 
 	kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE);
- fail:
+out:
 	mutex_unlock(mdev->state_mutex);
 	return rv;
 }
 
-static int drbd_nl_primary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			   struct drbd_nl_cfg_reply *reply)
+static const char *from_attrs_err_to_txt(int err)
 {
-	struct primary primary_args;
-
-	memset(&primary_args, 0, sizeof(struct primary));
-	if (!primary_from_tags(nlp->tag_list, &primary_args)) {
-		reply->ret_code = ERR_MANDATORY_TAG;
-		return 0;
-	}
-
-	reply->ret_code =
-		drbd_set_role(mdev, R_PRIMARY, primary_args.primary_force);
-
-	return 0;
+	return	err == -ENOMSG ? "required attribute missing" :
+		err == -EOPNOTSUPP ? "unknown mandatory attribute" :
+		"invalid attribute value";
 }
 
-static int drbd_nl_secondary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			     struct drbd_nl_cfg_reply *reply)
+int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info)
 {
-	reply->ret_code = drbd_set_role(mdev, R_SECONDARY, 0);
+	struct set_role_parms parms;
+	int err;
+	enum drbd_ret_code retcode;
 
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
+
+	memset(&parms, 0, sizeof(parms));
+	if (info->attrs[DRBD_NLA_SET_ROLE_PARMS]) {
+		err = set_role_parms_from_attrs(&parms, info->attrs);
+		if (err) {
+			retcode = ERR_MANDATORY_TAG;
+			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			goto out;
+		}
+	}
+
+	if (info->genlhdr->cmd == DRBD_ADM_PRIMARY)
+		retcode = drbd_set_role(adm_ctx.mdev, R_PRIMARY, parms.assume_uptodate);
+	else
+		retcode = drbd_set_role(adm_ctx.mdev, R_SECONDARY, 0);
+out:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
@@ -541,6 +673,12 @@ char *ppsize(char *buf, unsigned long long size)
  *  R_PRIMARY D_INCONSISTENT, and C_SYNC_TARGET:
  *  peer may not initiate a resize.
  */
+/* Note these are not to be confused with
+ * drbd_adm_suspend_io/drbd_adm_resume_io,
+ * which are (sub) state changes triggered by admin (drbdsetup),
+ * and can be long lived.
+ * This changes an mdev->flag, is triggered by drbd internals,
+ * and should be short-lived. */
 void drbd_suspend_io(struct drbd_conf *mdev)
 {
 	set_bit(SUSPEND_IO, &mdev->flags);
@@ -881,11 +1019,10 @@ static void drbd_suspend_al(struct drbd_conf *mdev)
 		dev_info(DEV, "Suspended AL updates\n");
 }
 
-/* does always return 0;
- * interesting return code is in reply->ret_code */
-static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			     struct drbd_nl_cfg_reply *reply)
+int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_conf *mdev;
+	int err;
 	enum drbd_ret_code retcode;
 	enum determine_dev_size dd;
 	sector_t max_possible_sectors;
@@ -897,6 +1034,13 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	enum drbd_state_rv rv;
 	int cp_discovered = 0;
 
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto fail;
+
+	mdev = adm_ctx.mdev;
 	conn_reconfig_start(mdev->tconn);
 
 	/* if you want to reconfigure, please tear down first */
@@ -910,7 +1054,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	 * to realize a "hot spare" feature (not that I'd recommend that) */
 	wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
 
-	/* allocation not in the IO path, cqueue thread context */
+	/* allocation not in the IO path, drbdsetup context */
 	nbc = kzalloc(sizeof(struct drbd_backing_dev), GFP_KERNEL);
 	if (!nbc) {
 		retcode = ERR_NOMEM;
@@ -922,12 +1066,14 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	nbc->dc.fencing       = DRBD_FENCING_DEF;
 	nbc->dc.max_bio_bvecs = DRBD_MAX_BIO_BVECS_DEF;
 
-	if (!disk_conf_from_tags(nlp->tag_list, &nbc->dc)) {
+	err = disk_conf_from_attrs(&nbc->dc, info->attrs);
+	if (err) {
 		retcode = ERR_MANDATORY_TAG;
+		drbd_msg_put_info(from_attrs_err_to_txt(err));
 		goto fail;
 	}
 
-	if (nbc->dc.meta_dev_idx < DRBD_MD_INDEX_FLEX_INT) {
+	if ((int)nbc->dc.meta_dev_idx < DRBD_MD_INDEX_FLEX_INT) {
 		retcode = ERR_MD_IDX_INVALID;
 		goto fail;
 	}
@@ -961,7 +1107,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	 */
 	bdev = blkdev_get_by_path(nbc->dc.meta_dev,
 				  FMODE_READ | FMODE_WRITE | FMODE_EXCL,
-				  (nbc->dc.meta_dev_idx < 0) ?
+				  ((int)nbc->dc.meta_dev_idx < 0) ?
 				  (void *)mdev : (void *)drbd_m_holder);
 	if (IS_ERR(bdev)) {
 		dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.meta_dev,
@@ -997,7 +1143,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 		goto fail;
 	}
 
-	if (nbc->dc.meta_dev_idx < 0) {
+	if ((int)nbc->dc.meta_dev_idx < 0) {
 		max_possible_sectors = DRBD_MAX_SECTORS_FLEX;
 		/* at least one MB, otherwise it does not make sense */
 		min_md_device_sectors = (2<<10);
@@ -1028,7 +1174,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 		dev_warn(DEV, "==> truncating very big lower level device "
 			"to currently maximum possible %llu sectors <==\n",
 			(unsigned long long) max_possible_sectors);
-		if (nbc->dc.meta_dev_idx >= 0)
+		if ((int)nbc->dc.meta_dev_idx >= 0)
 			dev_warn(DEV, "==>> using internal or flexible "
 				      "meta data may help <<==\n");
 	}
@@ -1242,8 +1388,8 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 
 	kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE);
 	put_ldev(mdev);
-	reply->ret_code = retcode;
 	conn_reconfig_done(mdev->tconn);
+	drbd_adm_finish(info, retcode);
 	return 0;
 
  force_diskless_dec:
@@ -1251,6 +1397,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
  force_diskless:
 	drbd_force_state(mdev, NS(disk, D_FAILED));
 	drbd_md_sync(mdev);
+	conn_reconfig_done(mdev->tconn);
  fail:
 	if (nbc) {
 		if (nbc->backing_bdev)
@@ -1263,8 +1410,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	}
 	lc_destroy(resync_lru);
 
-	reply->ret_code = retcode;
-	conn_reconfig_done(mdev->tconn);
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
@@ -1273,42 +1419,54 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
  * Then we transition to D_DISKLESS, and wait for put_ldev() to return all
  * internal references as well.
  * Only then we have finally detached. */
-static int drbd_nl_detach(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			  struct drbd_nl_cfg_reply *reply)
+int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_conf *mdev;
 	enum drbd_ret_code retcode;
-	int ret;
+
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
+
+	mdev = adm_ctx.mdev;
 	drbd_suspend_io(mdev); /* so no-one is stuck in drbd_al_begin_io */
-	retcode = drbd_request_state(mdev, NS(disk, D_FAILED));
-	/* D_FAILED will transition to DISKLESS. */
-	ret = wait_event_interruptible(mdev->misc_wait,
-			mdev->state.disk != D_FAILED);
+	retcode = drbd_request_state(mdev, NS(disk, D_DISKLESS));
+	wait_event(mdev->misc_wait,
+			mdev->state.disk != D_DISKLESS ||
+			!atomic_read(&mdev->local_cnt));
 	drbd_resume_io(mdev);
-	if ((int)retcode == (int)SS_IS_DISKLESS)
-		retcode = SS_NOTHING_TO_DO;
-	if (ret)
-		retcode = ERR_INTR;
-	reply->ret_code = retcode;
+out:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
-static int drbd_nl_net_conf(struct drbd_tconn *tconn, struct drbd_nl_cfg_req *nlp,
-			    struct drbd_nl_cfg_reply *reply)
+int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 {
-	int i;
-	enum drbd_ret_code retcode;
+	char hmac_name[CRYPTO_MAX_ALG_NAME];
+	struct drbd_conf *mdev;
 	struct net_conf *new_conf = NULL;
 	struct crypto_hash *tfm = NULL;
 	struct crypto_hash *integrity_w_tfm = NULL;
 	struct crypto_hash *integrity_r_tfm = NULL;
-	struct drbd_conf *mdev;
-	char hmac_name[CRYPTO_MAX_ALG_NAME];
 	void *int_dig_out = NULL;
 	void *int_dig_in = NULL;
 	void *int_dig_vv = NULL;
 	struct drbd_tconn *oconn;
+	struct drbd_tconn *tconn;
 	struct sockaddr *new_my_addr, *new_peer_addr, *taken_addr;
+	enum drbd_ret_code retcode;
+	int i;
+	int err;
 
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_CONN);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
+
+	tconn = adm_ctx.tconn;
 	conn_reconfig_start(tconn);
 
 	if (tconn->cstate > C_STANDALONE) {
@@ -1343,8 +1501,10 @@ static int drbd_nl_net_conf(struct drbd_tconn *tconn, struct drbd_nl_cfg_req *nl
 	new_conf->on_congestion    = DRBD_ON_CONGESTION_DEF;
 	new_conf->cong_extents     = DRBD_CONG_EXTENTS_DEF;
 
-	if (!net_conf_from_tags(nlp->tag_list, new_conf)) {
+	err = net_conf_from_attrs(new_conf, info->attrs);
+	if (err) {
 		retcode = ERR_MANDATORY_TAG;
+		drbd_msg_put_info(from_attrs_err_to_txt(err));
 		goto fail;
 	}
 
@@ -1495,8 +1655,8 @@ static int drbd_nl_net_conf(struct drbd_tconn *tconn, struct drbd_nl_cfg_req *nl
 		mdev->recv_cnt = 0;
 		kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE);
 	}
-	reply->ret_code = retcode;
 	conn_reconfig_done(tconn);
+	drbd_adm_finish(info, retcode);
 	return 0;
 
 fail:
@@ -1508,24 +1668,37 @@ fail:
 	crypto_free_hash(integrity_r_tfm);
 	kfree(new_conf);
 
-	reply->ret_code = retcode;
 	conn_reconfig_done(tconn);
+out:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
-static int drbd_nl_disconnect(struct drbd_tconn *tconn, struct drbd_nl_cfg_req *nlp,
-			      struct drbd_nl_cfg_reply *reply)
+int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info)
 {
-	int retcode;
-	struct disconnect dc;
+	struct disconnect_parms parms;
+	struct drbd_tconn *tconn;
+	enum drbd_ret_code retcode;
+	int err;
 
-	memset(&dc, 0, sizeof(struct disconnect));
-	if (!disconnect_from_tags(nlp->tag_list, &dc)) {
-		retcode = ERR_MANDATORY_TAG;
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_CONN);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
 		goto fail;
+
+	tconn = adm_ctx.tconn;
+	memset(&parms, 0, sizeof(parms));
+	if (info->attrs[DRBD_NLA_DISCONNECT_PARMS]) {
+		err = disconnect_parms_from_attrs(&parms, info->attrs);
+		if (err) {
+			retcode = ERR_MANDATORY_TAG;
+			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			goto fail;
+		}
 	}
 
-	if (dc.force) {
+	if (parms.force_disconnect) {
 		spin_lock_irq(&tconn->req_lock);
 		if (tconn->cstate >= C_WF_CONNECTION)
 			_conn_request_state(tconn, NS(conn, C_DISCONNECTING), CS_HARD);
@@ -1567,7 +1740,7 @@ static int drbd_nl_disconnect(struct drbd_tconn *tconn, struct drbd_nl_cfg_req *
  done:
 	retcode = NO_ERROR;
  fail:
-	reply->ret_code = retcode;
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
@@ -1587,20 +1760,32 @@ void resync_after_online_grow(struct drbd_conf *mdev)
 		_drbd_request_state(mdev, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE + CS_SERIALIZE);
 }
 
-static int drbd_nl_resize(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			  struct drbd_nl_cfg_reply *reply)
+int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 {
-	struct resize rs;
-	int retcode = NO_ERROR;
+	struct resize_parms rs;
+	struct drbd_conf *mdev;
+	enum drbd_ret_code retcode;
 	enum determine_dev_size dd;
 	enum dds_flags ddsf;
+	int err;
 
-	memset(&rs, 0, sizeof(struct resize));
-	if (!resize_from_tags(nlp->tag_list, &rs)) {
-		retcode = ERR_MANDATORY_TAG;
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
 		goto fail;
+
+	memset(&rs, 0, sizeof(struct resize_parms));
+	if (info->attrs[DRBD_NLA_RESIZE_PARMS]) {
+		err = resize_parms_from_attrs(&rs, info->attrs);
+		if (err) {
+			retcode = ERR_MANDATORY_TAG;
+			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			goto fail;
+		}
 	}
 
+	mdev = adm_ctx.mdev;
 	if (mdev->state.conn > C_CONNECTED) {
 		retcode = ERR_RESIZE_RESYNC;
 		goto fail;
@@ -1644,14 +1829,14 @@ static int drbd_nl_resize(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
 	}
 
  fail:
-	reply->ret_code = retcode;
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
-static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			       struct drbd_nl_cfg_reply *reply)
+int drbd_adm_syncer(struct sk_buff *skb, struct genl_info *info)
 {
-	int retcode = NO_ERROR;
+	struct drbd_conf *mdev;
+	enum drbd_ret_code retcode;
 	int err;
 	int ovr; /* online verify running */
 	int rsr; /* re-sync running */
@@ -1662,12 +1847,21 @@ static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *n
 	int *rs_plan_s = NULL;
 	int fifo_size;
 
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto fail;
+	mdev = adm_ctx.mdev;
+
 	if (!zalloc_cpumask_var(&new_cpu_mask, GFP_KERNEL)) {
 		retcode = ERR_NOMEM;
+		drbd_msg_put_info("unable to allocate cpumask");
 		goto fail;
 	}
 
-	if (nlp->flags & DRBD_NL_SET_DEFAULTS) {
+	if (((struct drbd_genlmsghdr*)info->userhdr)->flags
+			& DRBD_GENL_F_SET_DEFAULTS) {
 		memset(&sc, 0, sizeof(struct syncer_conf));
 		sc.rate       = DRBD_RATE_DEF;
 		sc.after      = DRBD_AFTER_DEF;
@@ -1681,8 +1875,10 @@ static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *n
 	} else
 		memcpy(&sc, &mdev->sync_conf, sizeof(struct syncer_conf));
 
-	if (!syncer_conf_from_tags(nlp->tag_list, &sc)) {
+	err = syncer_conf_from_attrs(&sc, info->attrs);
+	if (err) {
 		retcode = ERR_MANDATORY_TAG;
+		drbd_msg_put_info(from_attrs_err_to_txt(err));
 		goto fail;
 	}
 
@@ -1832,14 +2028,23 @@ fail:
 	free_cpumask_var(new_cpu_mask);
 	crypto_free_hash(csums_tfm);
 	crypto_free_hash(verify_tfm);
-	reply->ret_code = retcode;
+
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
-static int drbd_nl_invalidate(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			      struct drbd_nl_cfg_reply *reply)
+int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info)
 {
-	int retcode;
+	struct drbd_conf *mdev;
+	int retcode; /* enum drbd_ret_code rsp. enum drbd_state_rv */
+
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
+
+	mdev = adm_ctx.mdev;
 
 	/* If there is still bitmap IO pending, probably because of a previous
 	 * resync just being finished, wait for it before requesting a new resync. */
@@ -1862,7 +2067,8 @@ static int drbd_nl_invalidate(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nl
 		retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T));
 	}
 
-	reply->ret_code = retcode;
+out:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
@@ -1875,56 +2081,58 @@ static int drbd_bmio_set_susp_al(struct drbd_conf *mdev)
 	return rv;
 }
 
-static int drbd_nl_invalidate_peer(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-				   struct drbd_nl_cfg_reply *reply)
+static int drbd_adm_simple_request_state(struct sk_buff *skb, struct genl_info *info,
+		union drbd_state mask, union drbd_state val)
 {
-	int retcode;
-
-	/* If there is still bitmap IO pending, probably because of a previous
-	 * resync just being finished, wait for it before requesting a new resync. */
-	wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
+	enum drbd_ret_code retcode;
 
-	retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S), CS_ORDERED);
-
-	if (retcode < SS_SUCCESS) {
-		if (retcode == SS_NEED_CONNECTION && mdev->state.role == R_PRIMARY) {
-			/* The peer will get a resync upon connect anyways. Just make that
-			   into a full resync. */
-			retcode = drbd_request_state(mdev, NS(pdsk, D_INCONSISTENT));
-			if (retcode >= SS_SUCCESS) {
-				if (drbd_bitmap_io(mdev, &drbd_bmio_set_susp_al,
-					"set_n_write from invalidate_peer",
-					BM_LOCKED_SET_ALLOWED))
-					retcode = ERR_IO_MD_DISK;
-			}
-		} else
-			retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
-	}
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
 
-	reply->ret_code = retcode;
+	retcode = drbd_request_state(adm_ctx.mdev, mask, val);
+out:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
-static int drbd_nl_pause_sync(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			      struct drbd_nl_cfg_reply *reply)
+int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info)
 {
-	int retcode = NO_ERROR;
+	return drbd_adm_simple_request_state(skb, info, NS(conn, C_STARTING_SYNC_S));
+}
 
-	if (drbd_request_state(mdev, NS(user_isp, 1)) == SS_NOTHING_TO_DO)
-		retcode = ERR_PAUSE_IS_SET;
+int drbd_adm_pause_sync(struct sk_buff *skb, struct genl_info *info)
+{
+	enum drbd_ret_code retcode;
+
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
 
-	reply->ret_code = retcode;
+	if (drbd_request_state(adm_ctx.mdev, NS(user_isp, 1)) == SS_NOTHING_TO_DO)
+		retcode = ERR_PAUSE_IS_SET;
+out:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
-static int drbd_nl_resume_sync(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			       struct drbd_nl_cfg_reply *reply)
+int drbd_adm_resume_sync(struct sk_buff *skb, struct genl_info *info)
 {
-	int retcode = NO_ERROR;
 	union drbd_state s;
+	enum drbd_ret_code retcode;
+
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
 
-	if (drbd_request_state(mdev, NS(user_isp, 0)) == SS_NOTHING_TO_DO) {
-		s = mdev->state;
+	if (drbd_request_state(adm_ctx.mdev, NS(user_isp, 0)) == SS_NOTHING_TO_DO) {
+		s = adm_ctx.mdev->state;
 		if (s.conn == C_PAUSED_SYNC_S || s.conn == C_PAUSED_SYNC_T) {
 			retcode = s.aftr_isp ? ERR_PIC_AFTER_DEP :
 				  s.peer_isp ? ERR_PIC_PEER_DEP : ERR_PAUSE_IS_CLEAR;
@@ -1933,28 +2141,35 @@ static int drbd_nl_resume_sync(struct drbd_conf *mdev, struct drbd_nl_cfg_req *n
 		}
 	}
 
-	reply->ret_code = retcode;
+out:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
-static int drbd_nl_suspend_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			      struct drbd_nl_cfg_reply *reply)
+int drbd_adm_suspend_io(struct sk_buff *skb, struct genl_info *info)
 {
-	reply->ret_code = drbd_request_state(mdev, NS(susp, 1));
-
-	return 0;
+	return drbd_adm_simple_request_state(skb, info, NS(susp, 1));
 }
 
-static int drbd_nl_resume_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			     struct drbd_nl_cfg_reply *reply)
+int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_conf *mdev;
+	int retcode; /* enum drbd_ret_code rsp. enum drbd_state_rv */
+
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
+
+	mdev = adm_ctx.mdev;
 	if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
 		drbd_uuid_new_current(mdev);
 		clear_bit(NEW_CUR_UUID, &mdev->flags);
 	}
 	drbd_suspend_io(mdev);
-	reply->ret_code = drbd_request_state(mdev, NS3(susp, 0, susp_nod, 0, susp_fen, 0));
-	if (reply->ret_code == SS_SUCCESS) {
+	retcode = drbd_request_state(mdev, NS3(susp, 0, susp_nod, 0, susp_fen, 0));
+	if (retcode == SS_SUCCESS) {
 		if (mdev->state.conn < C_CONNECTED)
 			tl_clear(mdev->tconn);
 		if (mdev->state.disk == D_DISKLESS || mdev->state.disk == D_FAILED)
@@ -1962,138 +2177,259 @@ static int drbd_nl_resume_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	}
 	drbd_resume_io(mdev);
 
+out:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
-static int drbd_nl_outdate(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			   struct drbd_nl_cfg_reply *reply)
+int drbd_adm_outdate(struct sk_buff *skb, struct genl_info *info)
 {
-	reply->ret_code = drbd_request_state(mdev, NS(disk, D_OUTDATED));
-	return 0;
+	return drbd_adm_simple_request_state(skb, info, NS(disk, D_OUTDATED));
 }
 
-static int drbd_nl_get_config(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			   struct drbd_nl_cfg_reply *reply)
+int nla_put_status_info(struct sk_buff *skb, struct drbd_conf *mdev,
+		const struct sib_info *sib)
 {
-	unsigned short *tl;
-
-	tl = reply->tag_list;
-
-	if (get_ldev(mdev)) {
-		tl = disk_conf_to_tags(&mdev->ldev->dc, tl);
-		put_ldev(mdev);
+	struct state_info *si = NULL; /* for sizeof(si->member); */
+	struct nlattr *nla;
+	int got_ldev;
+	int got_net;
+	int err = 0;
+	int exclude_sensitive;
+
+	/* If sib != NULL, this is drbd_bcast_event, which anyone can listen
+	 * to.  So we better exclude_sensitive information.
+	 *
+	 * If sib == NULL, this is drbd_adm_get_status, executed synchronously
+	 * in the context of the requesting user process. Exclude sensitive
+	 * information, unless current has superuser.
+	 *
+	 * NOTE: for drbd_adm_get_status_all(), this is a netlink dump, and
+	 * relies on the current implementation of netlink_dump(), which
+	 * executes the dump callback successively from netlink_recvmsg(),
+	 * always in the context of the receiving process */
+	exclude_sensitive = sib || !capable(CAP_SYS_ADMIN);
+
+	got_ldev = get_ldev(mdev);
+	got_net = get_net_conf(mdev->tconn);
+
+	/* We need to add connection name and volume number information still.
+	 * Minor number is in drbd_genlmsghdr. */
+	nla = nla_nest_start(skb, DRBD_NLA_CFG_CONTEXT);
+	if (!nla)
+		goto nla_put_failure;
+	NLA_PUT_U32(skb, T_ctx_volume, mdev->vnr);
+	NLA_PUT_STRING(skb, T_ctx_conn_name, mdev->tconn->name);
+	nla_nest_end(skb, nla);
+
+	if (got_ldev)
+		if (disk_conf_to_skb(skb, &mdev->ldev->dc, exclude_sensitive))
+			goto nla_put_failure;
+	if (got_net)
+		if (net_conf_to_skb(skb, mdev->tconn->net_conf, exclude_sensitive))
+			goto nla_put_failure;
+
+	if (syncer_conf_to_skb(skb, &mdev->sync_conf, exclude_sensitive))
+			goto nla_put_failure;
+
+	nla = nla_nest_start(skb, DRBD_NLA_STATE_INFO);
+	if (!nla)
+		goto nla_put_failure;
+	NLA_PUT_U32(skb, T_sib_reason, sib ? sib->sib_reason : SIB_GET_STATUS_REPLY);
+	NLA_PUT_U32(skb, T_current_state, mdev->state.i);
+	NLA_PUT_U64(skb, T_ed_uuid, mdev->ed_uuid);
+	NLA_PUT_U64(skb, T_capacity, drbd_get_capacity(mdev->this_bdev));
+
+	if (got_ldev) {
+		NLA_PUT_U32(skb, T_disk_flags, mdev->ldev->md.flags);
+		NLA_PUT(skb, T_uuids, sizeof(si->uuids), mdev->ldev->md.uuid);
+		NLA_PUT_U64(skb, T_bits_total, drbd_bm_bits(mdev));
+		NLA_PUT_U64(skb, T_bits_oos, drbd_bm_total_weight(mdev));
+		if (C_SYNC_SOURCE <= mdev->state.conn &&
+		    C_PAUSED_SYNC_T >= mdev->state.conn) {
+			NLA_PUT_U64(skb, T_bits_rs_total, mdev->rs_total);
+			NLA_PUT_U64(skb, T_bits_rs_failed, mdev->rs_failed);
+		}
 	}
 
-	if (get_net_conf(mdev->tconn)) {
-		tl = net_conf_to_tags(mdev->tconn->net_conf, tl);
-		put_net_conf(mdev->tconn);
+	if (sib) {
+		switch(sib->sib_reason) {
+		case SIB_SYNC_PROGRESS:
+		case SIB_GET_STATUS_REPLY:
+			break;
+		case SIB_STATE_CHANGE:
+			NLA_PUT_U32(skb, T_prev_state, sib->os.i);
+			NLA_PUT_U32(skb, T_new_state, sib->ns.i);
+			break;
+		case SIB_HELPER_POST:
+			NLA_PUT_U32(skb,
+				T_helper_exit_code, sib->helper_exit_code);
+			/* fall through */
+		case SIB_HELPER_PRE:
+			NLA_PUT_STRING(skb, T_helper, sib->helper_name);
+			break;
+		}
 	}
-	tl = syncer_conf_to_tags(&mdev->sync_conf, tl);
-
-	put_unaligned(TT_END, tl++); /* Close the tag list */
+	nla_nest_end(skb, nla);
 
-	return (int)((char *)tl - (char *)reply->tag_list);
+	if (0)
+nla_put_failure:
+		err = -EMSGSIZE;
+	if (got_ldev)
+		put_ldev(mdev);
+	if (got_net)
+		put_net_conf(mdev->tconn);
+	return err;
 }
 
-static int drbd_nl_get_state(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			     struct drbd_nl_cfg_reply *reply)
+int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info)
 {
-	unsigned short *tl = reply->tag_list;
-	union drbd_state s = mdev->state;
-	unsigned long rs_left;
-	unsigned int res;
+	enum drbd_ret_code retcode;
+	int err;
 
-	tl = get_state_to_tags((struct get_state *)&s, tl);
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
 
-	/* no local ref, no bitmap, no syncer progress. */
-	if (s.conn >= C_SYNC_SOURCE && s.conn <= C_PAUSED_SYNC_T) {
-		if (get_ldev(mdev)) {
-			drbd_get_syncer_progress(mdev, &rs_left, &res);
-			tl = tl_add_int(tl, T_sync_progress, &res);
-			put_ldev(mdev);
-		}
+	err = nla_put_status_info(adm_ctx.reply_skb, adm_ctx.mdev, NULL);
+	if (err) {
+		nlmsg_free(adm_ctx.reply_skb);
+		return err;
 	}
-	put_unaligned(TT_END, tl++); /* Close the tag list */
-
-	return (int)((char *)tl - (char *)reply->tag_list);
+out:
+	drbd_adm_finish(info, retcode);
+	return 0;
 }
 
-static int drbd_nl_get_uuids(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			     struct drbd_nl_cfg_reply *reply)
+int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	unsigned short *tl;
-
-	tl = reply->tag_list;
+	struct drbd_conf *mdev;
+	struct drbd_genlmsghdr *dh;
+	int minor = cb->args[0];
+
+	/* Open coded deferred single idr_for_each_entry iteration.
+	 * This may miss entries inserted after this dump started,
+	 * or entries deleted before they are reached.
+	 * But we need to make sure the mdev won't disappear while
+	 * we are looking at it. */
+
+	rcu_read_lock();
+	mdev = idr_get_next(&minors, &minor);
+	if (mdev) {
+		dh = genlmsg_put(skb, NETLINK_CB(cb->skb).pid,
+				cb->nlh->nlmsg_seq, &drbd_genl_family,
+				NLM_F_MULTI, DRBD_ADM_GET_STATUS);
+		if (!dh)
+			goto errout;
+
+		D_ASSERT(mdev->minor == minor);
+
+		dh->minor = minor;
+		dh->ret_code = NO_ERROR;
+
+		if (nla_put_status_info(skb, mdev, NULL)) {
+			genlmsg_cancel(skb, dh);
+			goto errout;
+		}
+		genlmsg_end(skb, dh);
+        }
 
-	if (get_ldev(mdev)) {
-		tl = tl_add_blob(tl, T_uuids, mdev->ldev->md.uuid, UI_SIZE*sizeof(u64));
-		tl = tl_add_int(tl, T_uuids_flags, &mdev->ldev->md.flags);
-		put_ldev(mdev);
-	}
-	put_unaligned(TT_END, tl++); /* Close the tag list */
+errout:
+	rcu_read_unlock();
+	/* where to start idr_get_next with the next iteration */
+        cb->args[0] = minor+1;
 
-	return (int)((char *)tl - (char *)reply->tag_list);
+	/* No more minors found: empty skb. Which will terminate the dump. */
+        return skb->len;
 }
 
-/**
- * drbd_nl_get_timeout_flag() - Used by drbdsetup to find out which timeout value to use
- * @mdev:	DRBD device.
- * @nlp:	Netlink/connector packet from drbdsetup
- * @reply:	Reply packet for drbdsetup
- */
-static int drbd_nl_get_timeout_flag(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-				    struct drbd_nl_cfg_reply *reply)
+int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info)
 {
-	unsigned short *tl;
-	char rv;
-
-	tl = reply->tag_list;
+	enum drbd_ret_code retcode;
+	struct timeout_parms tp;
+	int err;
 
-	rv = mdev->state.pdsk == D_OUTDATED        ? UT_PEER_OUTDATED :
-	  test_bit(USE_DEGR_WFC_T, &mdev->flags) ? UT_DEGRADED : UT_DEFAULT;
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
 
-	tl = tl_add_blob(tl, T_use_degraded, &rv, sizeof(rv));
-	put_unaligned(TT_END, tl++); /* Close the tag list */
+	tp.timeout_type =
+		adm_ctx.mdev->state.pdsk == D_OUTDATED ? UT_PEER_OUTDATED :
+		test_bit(USE_DEGR_WFC_T, &adm_ctx.mdev->flags) ? UT_DEGRADED :
+		UT_DEFAULT;
 
-	return (int)((char *)tl - (char *)reply->tag_list);
+	err = timeout_parms_to_priv_skb(adm_ctx.reply_skb, &tp);
+	if (err) {
+		nlmsg_free(adm_ctx.reply_skb);
+		return err;
+	}
+out:
+	drbd_adm_finish(info, retcode);
+	return 0;
 }
 
-static int drbd_nl_start_ov(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-				    struct drbd_nl_cfg_reply *reply)
+int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info)
 {
-	/* default to resume from last known position, if possible */
-	struct start_ov args =
-		{ .start_sector = mdev->ov_start_sector };
+	struct drbd_conf *mdev;
+	enum drbd_ret_code retcode;
 
-	if (!start_ov_from_tags(nlp->tag_list, &args)) {
-		reply->ret_code = ERR_MANDATORY_TAG;
-		return 0;
-	}
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
 
+	mdev = adm_ctx.mdev;
+	if (info->attrs[DRBD_NLA_START_OV_PARMS]) {
+		/* resume from last known position, if possible */
+		struct start_ov_parms parms =
+			{ .ov_start_sector = mdev->ov_start_sector };
+		int err = start_ov_parms_from_attrs(&parms, info->attrs);
+		if (err) {
+			retcode = ERR_MANDATORY_TAG;
+			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			goto out;
+		}
+		/* w_make_ov_request expects position to be aligned */
+		mdev->ov_start_sector = parms.ov_start_sector & ~BM_SECT_PER_BIT;
+	}
 	/* If there is still bitmap IO pending, e.g. previous resync or verify
 	 * just being finished, wait for it before requesting a new resync. */
 	wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
-
-	/* w_make_ov_request expects position to be aligned */
-	mdev->ov_start_sector = args.start_sector & ~BM_SECT_PER_BIT;
-	reply->ret_code = drbd_request_state(mdev,NS(conn,C_VERIFY_S));
+	retcode = drbd_request_state(mdev,NS(conn,C_VERIFY_S));
+out:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
 
-static int drbd_nl_new_c_uuid(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			      struct drbd_nl_cfg_reply *reply)
+int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info)
 {
-	int retcode = NO_ERROR;
+	struct drbd_conf *mdev;
+	enum drbd_ret_code retcode;
 	int skip_initial_sync = 0;
 	int err;
+	struct new_c_uuid_parms args;
 
-	struct new_c_uuid args;
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out_nolock;
 
-	memset(&args, 0, sizeof(struct new_c_uuid));
-	if (!new_c_uuid_from_tags(nlp->tag_list, &args)) {
-		reply->ret_code = ERR_MANDATORY_TAG;
-		return 0;
+	mdev = adm_ctx.mdev;
+	memset(&args, 0, sizeof(args));
+	if (info->attrs[DRBD_NLA_NEW_C_UUID_PARMS]) {
+		err = new_c_uuid_parms_from_attrs(&args, info->attrs);
+		if (err) {
+			retcode = ERR_MANDATORY_TAG;
+			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			goto out_nolock;
+		}
 	}
 
 	mutex_lock(mdev->state_mutex); /* Protects us against serialized state changes. */
@@ -2139,510 +2475,164 @@ out_dec:
 	put_ldev(mdev);
 out:
 	mutex_unlock(mdev->state_mutex);
-
-	reply->ret_code = retcode;
-	return 0;
-}
-
-static int drbd_nl_new_conn(struct drbd_nl_cfg_req *nlp, struct drbd_nl_cfg_reply *reply)
-{
-	struct new_connection args;
-
-	if (!new_connection_from_tags(nlp->tag_list, &args)) {
-		reply->ret_code = ERR_MANDATORY_TAG;
-		return 0;
-	}
-
-	reply->ret_code = NO_ERROR;
-	if (!drbd_new_tconn(args.name))
-		reply->ret_code = ERR_NOMEM;
-
-	return 0;
-}
-
-static int drbd_nl_new_minor(struct drbd_tconn *tconn,
-		      struct drbd_nl_cfg_req *nlp, struct drbd_nl_cfg_reply *reply)
-{
-	struct new_minor args;
-
-	args.vol_nr = 0;
-	args.minor = 0;
-
-	if (!new_minor_from_tags(nlp->tag_list, &args)) {
-		reply->ret_code = ERR_MANDATORY_TAG;
-		return 0;
-	}
-
-	reply->ret_code = conn_new_minor(tconn, args.minor, args.vol_nr);
-
+out_nolock:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
-static int drbd_nl_del_minor(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
-			     struct drbd_nl_cfg_reply *reply)
+static enum drbd_ret_code
+drbd_check_conn_name(const char *name)
 {
-	if (mdev->state.disk == D_DISKLESS &&
-	    mdev->state.conn == C_STANDALONE &&
-	    mdev->state.role == R_SECONDARY) {
-		drbd_delete_device(mdev_to_minor(mdev));
-		reply->ret_code = NO_ERROR;
-	} else {
-		reply->ret_code = ERR_MINOR_CONFIGURED;
+	if (!name || !name[0]) {
+		drbd_msg_put_info("connection name missing");
+		return ERR_MANDATORY_TAG;
 	}
-	return 0;
-}
-
-static int drbd_nl_del_conn(struct drbd_tconn *tconn,
-			    struct drbd_nl_cfg_req *nlp, struct drbd_nl_cfg_reply *reply)
-{
-	if (conn_lowest_minor(tconn) < 0) {
-		drbd_free_tconn(tconn);
-		reply->ret_code = NO_ERROR;
-	} else {
-		reply->ret_code = ERR_CONN_IN_USE;
+	/* if we want to use these in sysfs/configfs/debugfs some day,
+	 * we must not allow slashes */
+	if (strchr(name, '/')) {
+		drbd_msg_put_info("invalid connection name");
+		return ERR_INVALID_REQUEST;
 	}
-
-	return 0;
+	return NO_ERROR;
 }
 
-enum cn_handler_type {
-	CHT_MINOR,
-	CHT_CONN,
-	CHT_CTOR,
-	/* CHT_RES, later */
-};
-struct cn_handler_struct {
-	enum cn_handler_type type;
-	union {
-		int (*minor_based)(struct drbd_conf *,
-				   struct drbd_nl_cfg_req *,
-				   struct drbd_nl_cfg_reply *);
-		int (*conn_based)(struct drbd_tconn *,
-				  struct drbd_nl_cfg_req *,
-				  struct drbd_nl_cfg_reply *);
-		int (*constructor)(struct drbd_nl_cfg_req *,
-				   struct drbd_nl_cfg_reply *);
-	};
-	int reply_body_size;
-};
-
-static struct cn_handler_struct cnd_table[] = {
-	[ P_primary ]		= { CHT_MINOR, { &drbd_nl_primary },	0 },
-	[ P_secondary ]		= { CHT_MINOR, { &drbd_nl_secondary },	0 },
-	[ P_disk_conf ]		= { CHT_MINOR, { &drbd_nl_disk_conf },	0 },
-	[ P_detach ]		= { CHT_MINOR, { &drbd_nl_detach },	0 },
-	[ P_net_conf ]		= { CHT_CONN,  { .conn_based = &drbd_nl_net_conf },	0 },
-	[ P_disconnect ]	= { CHT_CONN,  { .conn_based = &drbd_nl_disconnect },	0 },
-	[ P_resize ]		= { CHT_MINOR, { &drbd_nl_resize },	0 },
-	[ P_syncer_conf ]	= { CHT_MINOR, { &drbd_nl_syncer_conf },0 },
-	[ P_invalidate ]	= { CHT_MINOR, { &drbd_nl_invalidate },	0 },
-	[ P_invalidate_peer ]	= { CHT_MINOR, { &drbd_nl_invalidate_peer },0 },
-	[ P_pause_sync ]	= { CHT_MINOR, { &drbd_nl_pause_sync },	0 },
-	[ P_resume_sync ]	= { CHT_MINOR, { &drbd_nl_resume_sync },0 },
-	[ P_suspend_io ]	= { CHT_MINOR, { &drbd_nl_suspend_io },	0 },
-	[ P_resume_io ]		= { CHT_MINOR, { &drbd_nl_resume_io },	0 },
-	[ P_outdate ]		= { CHT_MINOR, { &drbd_nl_outdate },	0 },
-	[ P_get_config ]	= { CHT_MINOR, { &drbd_nl_get_config },
-				    sizeof(struct syncer_conf_tag_len_struct) +
-				    sizeof(struct disk_conf_tag_len_struct) +
-				    sizeof(struct net_conf_tag_len_struct) },
-	[ P_get_state ]		= { CHT_MINOR, { &drbd_nl_get_state },
-				    sizeof(struct get_state_tag_len_struct) +
-				    sizeof(struct sync_progress_tag_len_struct)	},
-	[ P_get_uuids ]		= { CHT_MINOR, { &drbd_nl_get_uuids },
-				    sizeof(struct get_uuids_tag_len_struct) },
-	[ P_get_timeout_flag ]	= { CHT_MINOR, { &drbd_nl_get_timeout_flag },
-				    sizeof(struct get_timeout_flag_tag_len_struct)},
-	[ P_start_ov ]		= { CHT_MINOR, { &drbd_nl_start_ov },	0 },
-	[ P_new_c_uuid ]	= { CHT_MINOR, { &drbd_nl_new_c_uuid },	0 },
-	[ P_new_connection ]	= { CHT_CTOR,  { .constructor = &drbd_nl_new_conn }, 0 },
-	[ P_new_minor ]		= { CHT_CONN,  { .conn_based = &drbd_nl_new_minor }, 0 },
-	[ P_del_minor ]		= { CHT_MINOR, { &drbd_nl_del_minor },	0 },
-	[ P_del_connection ]    = { CHT_CONN,  { .conn_based = &drbd_nl_del_conn }, 0 },
-};
-
-static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms *nsp)
+int drbd_adm_create_connection(struct sk_buff *skb, struct genl_info *info)
 {
-	struct drbd_nl_cfg_req *nlp = (struct drbd_nl_cfg_req *)req->data;
-	struct cn_handler_struct *cm;
-	struct cn_msg *cn_reply;
-	struct drbd_nl_cfg_reply *reply;
-	struct drbd_conf *mdev;
-	struct drbd_tconn *tconn;
-	int retcode, rr;
-	int reply_size = sizeof(struct cn_msg)
-		+ sizeof(struct drbd_nl_cfg_reply)
-		+ sizeof(short int);
-
-	if (!try_module_get(THIS_MODULE)) {
-		printk(KERN_ERR "drbd: try_module_get() failed!\n");
-		return;
-	}
-
-	if (!cap_raised(current_cap(), CAP_SYS_ADMIN)) {
-		retcode = ERR_PERM;
-		goto fail;
-	}
+	enum drbd_ret_code retcode;
 
-	if (nlp->packet_type >= P_nl_after_last_packet ||
-	    nlp->packet_type == P_return_code_only) {
-		retcode = ERR_PACKET_NR;
-		goto fail;
-	}
+	retcode = drbd_adm_prepare(skb, info, 0);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
 
-	cm = cnd_table + nlp->packet_type;
+	retcode = drbd_check_conn_name(adm_ctx.conn_name);
+	if (retcode != NO_ERROR)
+		goto out;
 
-	/* This may happen if packet number is 0: */
-	if (cm->minor_based == NULL) {
-		retcode = ERR_PACKET_NR;
-		goto fail;
+	if (adm_ctx.tconn) {
+		retcode = ERR_INVALID_REQUEST;
+		drbd_msg_put_info("connection exists");
+		goto out;
 	}
 
-	reply_size += cm->reply_body_size;
-
-	/* allocation not in the IO path, cqueue thread context */
-	cn_reply = kzalloc(reply_size, GFP_KERNEL);
-	if (!cn_reply) {
+	if (!drbd_new_tconn(adm_ctx.conn_name))
 		retcode = ERR_NOMEM;
-		goto fail;
-	}
-	reply = (struct drbd_nl_cfg_reply *) cn_reply->data;
-
-	reply->packet_type =
-		cm->reply_body_size ? nlp->packet_type : P_return_code_only;
-	reply->minor = nlp->drbd_minor;
-	reply->ret_code = NO_ERROR; /* Might by modified by cm->function. */
-	/* reply->tag_list; might be modified by cm->function. */
-
-	retcode = ERR_MINOR_INVALID;
-	rr = 0;
-	switch (cm->type) {
-	case CHT_MINOR:
-		mdev = minor_to_mdev(nlp->drbd_minor);
-		if (!mdev)
-			goto fail;
-		rr = cm->minor_based(mdev, nlp, reply);
-		break;
-	case CHT_CONN:
-		tconn = conn_by_name(nlp->obj_name);
-		if (!tconn) {
-			retcode = ERR_CONN_NOT_KNOWN;
-			goto fail;
-		}
-		rr = cm->conn_based(tconn, nlp, reply);
-		break;
-	case CHT_CTOR:
-		rr = cm->constructor(nlp, reply);
-		break;
-	/* case CHT_RES: */
-	}
-
-	cn_reply->id = req->id;
-	cn_reply->seq = req->seq;
-	cn_reply->ack = req->ack  + 1;
-	cn_reply->len = sizeof(struct drbd_nl_cfg_reply) + rr;
-	cn_reply->flags = 0;
-
-	rr = cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_KERNEL);
-	if (rr && rr != -ESRCH)
-		printk(KERN_INFO "drbd: cn_netlink_send()=%d\n", rr);
-
-	kfree(cn_reply);
-	module_put(THIS_MODULE);
-	return;
- fail:
-	drbd_nl_send_reply(req, retcode);
-	module_put(THIS_MODULE);
-}
-
-static atomic_t drbd_nl_seq = ATOMIC_INIT(2); /* two. */
-
-static unsigned short *
-__tl_add_blob(unsigned short *tl, enum drbd_tags tag, const void *data,
-	unsigned short len, int nul_terminated)
-{
-	unsigned short l = tag_descriptions[tag_number(tag)].max_len;
-	len = (len < l) ? len :  l;
-	put_unaligned(tag, tl++);
-	put_unaligned(len, tl++);
-	memcpy(tl, data, len);
-	tl = (unsigned short*)((char*)tl + len);
-	if (nul_terminated)
-		*((char*)tl - 1) = 0;
-	return tl;
-}
-
-static unsigned short *
-tl_add_blob(unsigned short *tl, enum drbd_tags tag, const void *data, int len)
-{
-	return __tl_add_blob(tl, tag, data, len, 0);
-}
-
-static unsigned short *
-tl_add_str(unsigned short *tl, enum drbd_tags tag, const char *str)
-{
-	return __tl_add_blob(tl, tag, str, strlen(str)+1, 0);
-}
-
-static unsigned short *
-tl_add_int(unsigned short *tl, enum drbd_tags tag, const void *val)
-{
-	put_unaligned(tag, tl++);
-	switch(tag_type(tag)) {
-	case TT_INTEGER:
-		put_unaligned(sizeof(int), tl++);
-		put_unaligned(*(int *)val, (int *)tl);
-		tl = (unsigned short*)((char*)tl+sizeof(int));
-		break;
-	case TT_INT64:
-		put_unaligned(sizeof(u64), tl++);
-		put_unaligned(*(u64 *)val, (u64 *)tl);
-		tl = (unsigned short*)((char*)tl+sizeof(u64));
-		break;
-	default:
-		/* someone did something stupid. */
-		;
-	}
-	return tl;
-}
-
-void drbd_bcast_state(struct drbd_conf *mdev, union drbd_state state)
-{
-	char buffer[sizeof(struct cn_msg)+
-		    sizeof(struct drbd_nl_cfg_reply)+
-		    sizeof(struct get_state_tag_len_struct)+
-		    sizeof(short int)];
-	struct cn_msg *cn_reply = (struct cn_msg *) buffer;
-	struct drbd_nl_cfg_reply *reply =
-		(struct drbd_nl_cfg_reply *)cn_reply->data;
-	unsigned short *tl = reply->tag_list;
-
-	/* dev_warn(DEV, "drbd_bcast_state() got called\n"); */
-
-	tl = get_state_to_tags((struct get_state *)&state, tl);
-
-	put_unaligned(TT_END, tl++); /* Close the tag list */
-
-	cn_reply->id.idx = CN_IDX_DRBD;
-	cn_reply->id.val = CN_VAL_DRBD;
-
-	cn_reply->seq = atomic_inc_return(&drbd_nl_seq);
-	cn_reply->ack = 0; /* not used here. */
-	cn_reply->len = sizeof(struct drbd_nl_cfg_reply) +
-		(int)((char *)tl - (char *)reply->tag_list);
-	cn_reply->flags = 0;
-
-	reply->packet_type = P_get_state;
-	reply->minor = mdev_to_minor(mdev);
-	reply->ret_code = NO_ERROR;
-
-	cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO);
-}
-
-void drbd_bcast_ev_helper(struct drbd_conf *mdev, char *helper_name)
-{
-	char buffer[sizeof(struct cn_msg)+
-		    sizeof(struct drbd_nl_cfg_reply)+
-		    sizeof(struct call_helper_tag_len_struct)+
-		    sizeof(short int)];
-	struct cn_msg *cn_reply = (struct cn_msg *) buffer;
-	struct drbd_nl_cfg_reply *reply =
-		(struct drbd_nl_cfg_reply *)cn_reply->data;
-	unsigned short *tl = reply->tag_list;
-
-	/* dev_warn(DEV, "drbd_bcast_state() got called\n"); */
-
-	tl = tl_add_str(tl, T_helper, helper_name);
-	put_unaligned(TT_END, tl++); /* Close the tag list */
-
-	cn_reply->id.idx = CN_IDX_DRBD;
-	cn_reply->id.val = CN_VAL_DRBD;
-
-	cn_reply->seq = atomic_inc_return(&drbd_nl_seq);
-	cn_reply->ack = 0; /* not used here. */
-	cn_reply->len = sizeof(struct drbd_nl_cfg_reply) +
-		(int)((char *)tl - (char *)reply->tag_list);
-	cn_reply->flags = 0;
-
-	reply->packet_type = P_call_helper;
-	reply->minor = mdev_to_minor(mdev);
-	reply->ret_code = NO_ERROR;
-
-	cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO);
+out:
+	drbd_adm_finish(info, retcode);
+	return 0;
 }
 
-void drbd_bcast_ee(struct drbd_conf *mdev, const char *reason, const int dgs,
-		   const char *seen_hash, const char *calc_hash,
-			   const struct drbd_peer_request *peer_req)
+int drbd_adm_add_minor(struct sk_buff *skb, struct genl_info *info)
 {
-	struct cn_msg *cn_reply;
-	struct drbd_nl_cfg_reply *reply;
-	unsigned short *tl;
-	struct page *page;
-	unsigned len;
+	struct drbd_genlmsghdr *dh = info->userhdr;
+	enum drbd_ret_code retcode;
 
-	if (!peer_req)
-		return;
-	if (!reason || !reason[0])
-		return;
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_CONN);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
 
-	/* apparently we have to memcpy twice, first to prepare the data for the
-	 * struct cn_msg, then within cn_netlink_send from the cn_msg to the
-	 * netlink skb. */
-	/* receiver thread context, which is not in the writeout path (of this node),
-	 * but may be in the writeout path of the _other_ node.
-	 * GFP_NOIO to avoid potential "distributed deadlock". */
-	cn_reply = kzalloc(
-		sizeof(struct cn_msg)+
-		sizeof(struct drbd_nl_cfg_reply)+
-		sizeof(struct dump_ee_tag_len_struct)+
-		sizeof(short int),
-		GFP_NOIO);
-
-	if (!cn_reply) {
-		dev_err(DEV, "could not kmalloc buffer for drbd_bcast_ee, "
-			     "sector %llu, size %u\n",
-			(unsigned long long)peer_req->i.sector,
-			peer_req->i.size);
-		return;
+	/* FIXME drop minor_count parameter, limit to MINORMASK */
+	if (dh->minor >= minor_count) {
+		drbd_msg_put_info("requested minor out of range");
+		retcode = ERR_INVALID_REQUEST;
+		goto out;
 	}
-
-	reply = (struct drbd_nl_cfg_reply*)cn_reply->data;
-	tl = reply->tag_list;
-
-	tl = tl_add_str(tl, T_dump_ee_reason, reason);
-	tl = tl_add_blob(tl, T_seen_digest, seen_hash, dgs);
-	tl = tl_add_blob(tl, T_calc_digest, calc_hash, dgs);
-	tl = tl_add_int(tl, T_ee_sector, &peer_req->i.sector);
-	tl = tl_add_int(tl, T_ee_block_id, &peer_req->block_id);
-
-	/* dump the first 32k */
-	len = min_t(unsigned, peer_req->i.size, 32 << 10);
-	put_unaligned(T_ee_data, tl++);
-	put_unaligned(len, tl++);
-
-	page = peer_req->pages;
-	page_chain_for_each(page) {
-		void *d = kmap_atomic(page, KM_USER0);
-		unsigned l = min_t(unsigned, len, PAGE_SIZE);
-		memcpy(tl, d, l);
-		kunmap_atomic(d, KM_USER0);
-		tl = (unsigned short*)((char*)tl + l);
-		len -= l;
-		if (len == 0)
-			break;
+	/* FIXME we need a define here */
+	if (adm_ctx.volume >= 256) {
+		drbd_msg_put_info("requested volume id out of range");
+		retcode = ERR_INVALID_REQUEST;
+		goto out;
 	}
-	put_unaligned(TT_END, tl++); /* Close the tag list */
-
-	cn_reply->id.idx = CN_IDX_DRBD;
-	cn_reply->id.val = CN_VAL_DRBD;
-
-	cn_reply->seq = atomic_inc_return(&drbd_nl_seq);
-	cn_reply->ack = 0; // not used here.
-	cn_reply->len = sizeof(struct drbd_nl_cfg_reply) +
-		(int)((char*)tl - (char*)reply->tag_list);
-	cn_reply->flags = 0;
 
-	reply->packet_type = P_dump_ee;
-	reply->minor = mdev_to_minor(mdev);
-	reply->ret_code = NO_ERROR;
-
-	cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO);
-	kfree(cn_reply);
+	retcode = conn_new_minor(adm_ctx.tconn, dh->minor, adm_ctx.volume);
+out:
+	drbd_adm_finish(info, retcode);
+	return 0;
 }
 
-void drbd_bcast_sync_progress(struct drbd_conf *mdev)
+int drbd_adm_delete_minor(struct sk_buff *skb, struct genl_info *info)
 {
-	char buffer[sizeof(struct cn_msg)+
-		    sizeof(struct drbd_nl_cfg_reply)+
-		    sizeof(struct sync_progress_tag_len_struct)+
-		    sizeof(short int)];
-	struct cn_msg *cn_reply = (struct cn_msg *) buffer;
-	struct drbd_nl_cfg_reply *reply =
-		(struct drbd_nl_cfg_reply *)cn_reply->data;
-	unsigned short *tl = reply->tag_list;
-	unsigned long rs_left;
-	unsigned int res;
-
-	/* no local ref, no bitmap, no syncer progress, no broadcast. */
-	if (!get_ldev(mdev))
-		return;
-	drbd_get_syncer_progress(mdev, &rs_left, &res);
-	put_ldev(mdev);
-
-	tl = tl_add_int(tl, T_sync_progress, &res);
-	put_unaligned(TT_END, tl++); /* Close the tag list */
-
-	cn_reply->id.idx = CN_IDX_DRBD;
-	cn_reply->id.val = CN_VAL_DRBD;
-
-	cn_reply->seq = atomic_inc_return(&drbd_nl_seq);
-	cn_reply->ack = 0; /* not used here. */
-	cn_reply->len = sizeof(struct drbd_nl_cfg_reply) +
-		(int)((char *)tl - (char *)reply->tag_list);
-	cn_reply->flags = 0;
+	struct drbd_conf *mdev;
+	enum drbd_ret_code retcode;
 
-	reply->packet_type = P_sync_progress;
-	reply->minor = mdev_to_minor(mdev);
-	reply->ret_code = NO_ERROR;
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
 
-	cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO);
+	mdev = adm_ctx.mdev;
+	if (mdev->state.disk == D_DISKLESS &&
+	    mdev->state.conn == C_STANDALONE &&
+	    mdev->state.role == R_SECONDARY) {
+		drbd_delete_device(mdev_to_minor(mdev));
+		retcode = NO_ERROR;
+	} else
+		retcode = ERR_MINOR_CONFIGURED;
+out:
+	drbd_adm_finish(info, retcode);
+	return 0;
 }
 
-int __init drbd_nl_init(void)
+int drbd_adm_delete_connection(struct sk_buff *skb, struct genl_info *info)
 {
-	static struct cb_id cn_id_drbd;
-	int err, try=10;
-
-	cn_id_drbd.val = CN_VAL_DRBD;
-	do {
-		cn_id_drbd.idx = cn_idx;
-		err = cn_add_callback(&cn_id_drbd, "cn_drbd", &drbd_connector_callback);
-		if (!err)
-			break;
-		cn_idx = (cn_idx + CN_IDX_STEP);
-	} while (try--);
+	enum drbd_ret_code retcode;
 
-	if (err) {
-		printk(KERN_ERR "drbd: cn_drbd failed to register\n");
-		return err;
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_CONN);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
+
+	if (conn_lowest_minor(adm_ctx.tconn) < 0) {
+		drbd_free_tconn(adm_ctx.tconn);
+		retcode = NO_ERROR;
+	} else {
+		retcode = ERR_CONN_IN_USE;
 	}
 
+out:
+	drbd_adm_finish(info, retcode);
 	return 0;
 }
 
-void drbd_nl_cleanup(void)
+void drbd_bcast_event(struct drbd_conf *mdev, const struct sib_info *sib)
 {
-	static struct cb_id cn_id_drbd;
-
-	cn_id_drbd.idx = cn_idx;
-	cn_id_drbd.val = CN_VAL_DRBD;
+	static atomic_t drbd_genl_seq = ATOMIC_INIT(2); /* two. */
+	struct sk_buff *msg;
+	struct drbd_genlmsghdr *d_out;
+	unsigned seq;
+	int err = -ENOMEM;
+
+	seq = atomic_inc_return(&drbd_genl_seq);
+	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_NOIO);
+	if (!msg)
+		goto failed;
+
+	err = -EMSGSIZE;
+	d_out = genlmsg_put(msg, 0, seq, &drbd_genl_family, 0, DRBD_EVENT);
+	if (!d_out) /* cannot happen, but anyways. */
+		goto nla_put_failure;
+	d_out->minor = mdev_to_minor(mdev);
+	d_out->ret_code = 0;
+
+	if (nla_put_status_info(msg, mdev, sib))
+		goto nla_put_failure;
+	genlmsg_end(msg, d_out);
+	err = drbd_genl_multicast_events(msg, 0);
+	/* msg has been consumed or freed in netlink_broadcast() */
+	if (err && err != -ESRCH)
+		goto failed;
 
-	cn_del_callback(&cn_id_drbd);
-}
+	return;
 
-void drbd_nl_send_reply(struct cn_msg *req, int ret_code)
-{
-	char buffer[sizeof(struct cn_msg)+sizeof(struct drbd_nl_cfg_reply)];
-	struct cn_msg *cn_reply = (struct cn_msg *) buffer;
-	struct drbd_nl_cfg_reply *reply =
-		(struct drbd_nl_cfg_reply *)cn_reply->data;
-	int rr;
-
-	memset(buffer, 0, sizeof(buffer));
-	cn_reply->id = req->id;
-
-	cn_reply->seq = req->seq;
-	cn_reply->ack = req->ack  + 1;
-	cn_reply->len = sizeof(struct drbd_nl_cfg_reply);
-	cn_reply->flags = 0;
-
-	reply->packet_type = P_return_code_only;
-	reply->minor = ((struct drbd_nl_cfg_req *)req->data)->drbd_minor;
-	reply->ret_code = ret_code;
-
-	rr = cn_netlink_send(cn_reply, CN_IDX_DRBD, GFP_NOIO);
-	if (rr && rr != -ESRCH)
-		printk(KERN_INFO "drbd: cn_netlink_send()=%d\n", rr);
+nla_put_failure:
+	nlmsg_free(msg);
+failed:
+	dev_err(DEV, "Error %d while broadcasting event. "
+			"Event seq:%u sib_reason:%u\n",
+			err, seq, sib->sib_reason);
 }
-
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index ffee90d6d374..a280bc238acd 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -970,6 +970,11 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 	enum drbd_fencing_p fp;
 	enum drbd_req_event what = NOTHING;
 	union drbd_state nsm = (union drbd_state){ .i = -1 };
+	struct sib_info sib;
+
+	sib.sib_reason = SIB_STATE_CHANGE;
+	sib.os = os;
+	sib.ns = ns;
 
 	if (os.conn != C_CONNECTED && ns.conn == C_CONNECTED) {
 		clear_bit(CRASHED_PRIMARY, &mdev->flags);
@@ -984,7 +989,7 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 	}
 
 	/* Inform userspace about the change... */
-	drbd_bcast_state(mdev, ns);
+	drbd_bcast_event(mdev, &sib);
 
 	if (!(os.role == R_PRIMARY && os.disk < D_UP_TO_DATE && os.pdsk < D_UP_TO_DATE) &&
 	    (ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE))
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index e192167e6145..d28fdd8fcd49 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -51,7 +51,6 @@
 
 #endif
 
-
 extern const char *drbd_buildtag(void);
 #define REL_VERSION "8.3.11"
 #define API_VERSION 88
@@ -159,6 +158,7 @@ enum drbd_ret_code {
 	ERR_CONN_IN_USE         = 159,
 	ERR_MINOR_CONFIGURED    = 160,
 	ERR_MINOR_EXISTS	= 161,
+	ERR_INVALID_REQUEST	= 162,
 
 	/* insert new ones above this line */
 	AFTER_LAST_ERR_CODE
@@ -349,37 +349,4 @@ enum drbd_timeout_flag {
 #define DRBD_MD_INDEX_FLEX_EXT -2
 #define DRBD_MD_INDEX_FLEX_INT -3
 
-/* Start of the new netlink/connector stuff */
-
-enum drbd_ncr_flags {
-	DRBD_NL_CREATE_DEVICE = 0x01,
-	DRBD_NL_SET_DEFAULTS =  0x02,
-};
-#define DRBD_NL_OBJ_NAME_LEN 32
-
-
-/* For searching a vacant cn_idx value */
-#define CN_IDX_STEP			6977
-
-struct drbd_nl_cfg_req {
-	int packet_type;
-	union {
-		struct {
-			unsigned int drbd_minor;
-			enum drbd_ncr_flags flags;
-		};
-		struct {
-			char obj_name[DRBD_NL_OBJ_NAME_LEN];
-		};
-	};
-	unsigned short tag_list[];
-};
-
-struct drbd_nl_cfg_reply {
-	int packet_type;
-	unsigned int minor;
-	int ret_code; /* enum ret_code or set_st_err_t */
-	unsigned short tag_list[]; /* only used with get_* calls */
-};
-
 #endif
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 8a86f659d363..c8c67239f616 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -95,7 +95,7 @@ static struct nla_policy s_name ## _nl_policy[] __read_mostly =		\
 #endif
 #endif
 
-#if 1
+#ifdef GENL_MAGIC_DEBUG
 static void dprint_field(const char *dir, int nla_type,
 		const char *name, void *valp)
 {
-- 
cgit v1.2.3-55-g7522


From 73d901b74f1070c8a664349b564ba6f8bc8ab283 Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Mon, 7 Mar 2011 10:38:56 +0100
Subject: drbd: remove now unused connector related files

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_nl.h        | 172 -----------------------------------------
 include/linux/drbd_tag_magic.h |  84 --------------------
 2 files changed, 256 deletions(-)
 delete mode 100644 include/linux/drbd_nl.h
 delete mode 100644 include/linux/drbd_tag_magic.h

(limited to 'include')

diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h
deleted file mode 100644
index 1216c7a432c5..000000000000
--- a/include/linux/drbd_nl.h
+++ /dev/null
@@ -1,172 +0,0 @@
-/*
-   PAKET( name,
-	  TYPE ( pn, pr, member )
-	  ...
-   )
-
-   You may never reissue one of the pn arguments
-*/
-
-#if !defined(NL_PACKET) || !defined(NL_STRING) || !defined(NL_INTEGER) || !defined(NL_BIT) || !defined(NL_INT64)
-#error "The macros NL_PACKET, NL_STRING, NL_INTEGER, NL_INT64 and NL_BIT needs to be defined"
-#endif
-
-NL_PACKET(primary, 1,
-       NL_BIT(		1,	T_MAY_IGNORE,	primary_force)
-)
-
-NL_PACKET(secondary, 2, )
-
-NL_PACKET(disk_conf, 3,
-	NL_INT64(	2,	T_MAY_IGNORE,	disk_size)
-	NL_STRING(	3,	T_MANDATORY,	backing_dev,	128)
-	NL_STRING(	4,	T_MANDATORY,	meta_dev,	128)
-	NL_INTEGER(	5,	T_MANDATORY,	meta_dev_idx)
-	NL_INTEGER(	6,	T_MAY_IGNORE,	on_io_error)
-	NL_INTEGER(	7,	T_MAY_IGNORE,	fencing)
-	NL_BIT(		37,	T_MAY_IGNORE,	use_bmbv)
-	NL_BIT(		53,	T_MAY_IGNORE,	no_disk_flush)
-	NL_BIT(		54,	T_MAY_IGNORE,	no_md_flush)
-	  /*  55 max_bio_size was available in 8.2.6rc2 */
-	NL_INTEGER(	56,	T_MAY_IGNORE,	max_bio_bvecs)
-	NL_BIT(		57,	T_MAY_IGNORE,	no_disk_barrier)
-	NL_BIT(		58,	T_MAY_IGNORE,	no_disk_drain)
-)
-
-NL_PACKET(detach, 4, )
-
-NL_PACKET(net_conf, 5,
-	NL_STRING(	8,	T_MANDATORY,	my_addr,	128)
-	NL_STRING(	9,	T_MANDATORY,	peer_addr,	128)
-	NL_STRING(	10,	T_MAY_IGNORE,	shared_secret,	SHARED_SECRET_MAX)
-	NL_STRING(	11,	T_MAY_IGNORE,	cram_hmac_alg,	SHARED_SECRET_MAX)
-	NL_STRING(	44,	T_MAY_IGNORE,	integrity_alg,	SHARED_SECRET_MAX)
-	NL_INTEGER(	14,	T_MAY_IGNORE,	timeout)
-	NL_INTEGER(	15,	T_MANDATORY,	wire_protocol)
-	NL_INTEGER(	16,	T_MAY_IGNORE,	try_connect_int)
-	NL_INTEGER(	17,	T_MAY_IGNORE,	ping_int)
-	NL_INTEGER(	18,	T_MAY_IGNORE,	max_epoch_size)
-	NL_INTEGER(	19,	T_MAY_IGNORE,	max_buffers)
-	NL_INTEGER(	20,	T_MAY_IGNORE,	unplug_watermark)
-	NL_INTEGER(	21,	T_MAY_IGNORE,	sndbuf_size)
-	NL_INTEGER(	22,	T_MAY_IGNORE,	ko_count)
-	NL_INTEGER(	24,	T_MAY_IGNORE,	after_sb_0p)
-	NL_INTEGER(	25,	T_MAY_IGNORE,	after_sb_1p)
-	NL_INTEGER(	26,	T_MAY_IGNORE,	after_sb_2p)
-	NL_INTEGER(	39,	T_MAY_IGNORE,	rr_conflict)
-	NL_INTEGER(	40,	T_MAY_IGNORE,	ping_timeo)
-	NL_INTEGER(	67,	T_MAY_IGNORE,	rcvbuf_size)
-	NL_INTEGER(	81,	T_MAY_IGNORE,	on_congestion)
-	NL_INTEGER(	82,	T_MAY_IGNORE,	cong_fill)
-	NL_INTEGER(	83,	T_MAY_IGNORE,	cong_extents)
-	  /* 59 addr_family was available in GIT, never released */
-	NL_BIT(		60,	T_MANDATORY,	mind_af)
-	NL_BIT(		27,	T_MAY_IGNORE,	want_lose)
-	NL_BIT(		28,	T_MAY_IGNORE,	two_primaries)
-	NL_BIT(		41,	T_MAY_IGNORE,	always_asbp)
-	NL_BIT(		61,	T_MAY_IGNORE,	no_cork)
-	NL_BIT(		62,	T_MANDATORY,	auto_sndbuf_size)
-	NL_BIT(		70,	T_MANDATORY,	dry_run)
-)
-
-NL_PACKET(disconnect, 6,
-	NL_BIT(		84,	T_MAY_IGNORE,	force)
-)
-
-NL_PACKET(resize, 7,
-	NL_INT64(		29,	T_MAY_IGNORE,	resize_size)
-	NL_BIT(			68,	T_MAY_IGNORE,	resize_force)
-	NL_BIT(			69,	T_MANDATORY,	no_resync)
-)
-
-NL_PACKET(syncer_conf, 8,
-	NL_INTEGER(	30,	T_MAY_IGNORE,	rate)
-	NL_INTEGER(	31,	T_MAY_IGNORE,	after)
-	NL_INTEGER(	32,	T_MAY_IGNORE,	al_extents)
-/*	NL_INTEGER(     71,	T_MAY_IGNORE,	dp_volume)
- *	NL_INTEGER(     72,	T_MAY_IGNORE,	dp_interval)
- *	NL_INTEGER(     73,	T_MAY_IGNORE,	throttle_th)
- *	NL_INTEGER(     74,	T_MAY_IGNORE,	hold_off_th)
- * feature will be reimplemented differently with 8.3.9 */
-	NL_STRING(      52,     T_MAY_IGNORE,   verify_alg,     SHARED_SECRET_MAX)
-	NL_STRING(      51,     T_MAY_IGNORE,   cpu_mask,       32)
-	NL_STRING(	64,	T_MAY_IGNORE,	csums_alg,	SHARED_SECRET_MAX)
-	NL_BIT(         65,     T_MAY_IGNORE,   use_rle)
-	NL_INTEGER(	75,	T_MAY_IGNORE,	on_no_data)
-	NL_INTEGER(	76,	T_MAY_IGNORE,	c_plan_ahead)
-	NL_INTEGER(     77,	T_MAY_IGNORE,	c_delay_target)
-	NL_INTEGER(     78,	T_MAY_IGNORE,	c_fill_target)
-	NL_INTEGER(     79,	T_MAY_IGNORE,	c_max_rate)
-	NL_INTEGER(     80,	T_MAY_IGNORE,	c_min_rate)
-)
-
-NL_PACKET(invalidate, 9, )
-NL_PACKET(invalidate_peer, 10, )
-NL_PACKET(pause_sync, 11, )
-NL_PACKET(resume_sync, 12, )
-NL_PACKET(suspend_io, 13, )
-NL_PACKET(resume_io, 14, )
-NL_PACKET(outdate, 15, )
-NL_PACKET(get_config, 16, )
-NL_PACKET(get_state, 17,
-	NL_INTEGER(	33,	T_MAY_IGNORE,	state_i)
-)
-
-NL_PACKET(get_uuids, 18,
-	NL_STRING(	34,	T_MAY_IGNORE,	uuids,	(UI_SIZE*sizeof(__u64)))
-	NL_INTEGER(	35,	T_MAY_IGNORE,	uuids_flags)
-)
-
-NL_PACKET(get_timeout_flag, 19,
-	NL_BIT(		36,	T_MAY_IGNORE,	use_degraded)
-)
-
-NL_PACKET(call_helper, 20,
-	NL_STRING(	38,	T_MAY_IGNORE,	helper,		32)
-)
-
-/* Tag nr 42 already allocated in drbd-8.1 development. */
-
-NL_PACKET(sync_progress, 23,
-	NL_INTEGER(	43,	T_MAY_IGNORE,	sync_progress)
-)
-
-NL_PACKET(dump_ee, 24,
-	NL_STRING(	45,	T_MAY_IGNORE,	dump_ee_reason, 32)
-	NL_STRING(	46,	T_MAY_IGNORE,	seen_digest, SHARED_SECRET_MAX)
-	NL_STRING(	47,	T_MAY_IGNORE,	calc_digest, SHARED_SECRET_MAX)
-	NL_INT64(	48,	T_MAY_IGNORE,	ee_sector)
-	NL_INT64(	49,	T_MAY_IGNORE,	ee_block_id)
-	NL_STRING(	50,	T_MAY_IGNORE,	ee_data,	32 << 10)
-)
-
-NL_PACKET(start_ov, 25,
-	NL_INT64(	66,	T_MAY_IGNORE,	start_sector)
-)
-
-NL_PACKET(new_c_uuid, 26,
-       NL_BIT(		63,	T_MANDATORY,	clear_bm)
-)
-
-#ifdef NL_RESPONSE
-NL_RESPONSE(return_code_only, 27)
-#endif
-
-NL_PACKET(new_connection, 28, /* CHT_CTOR */
-	NL_STRING(	85,	T_MANDATORY,	name, DRBD_NL_OBJ_NAME_LEN)
-)
-
-NL_PACKET(new_minor, 29, /* CHT_CONN */
-	NL_INTEGER(	86,	T_MANDATORY,	minor)
-	NL_INTEGER(	87,	T_MANDATORY,	vol_nr)
-)
-
-NL_PACKET(del_minor, 30, ) /* CHT_MINOR */
-NL_PACKET(del_connection, 31, ) /* CHT_CONN */
-
-#undef NL_PACKET
-#undef NL_INTEGER
-#undef NL_INT64
-#undef NL_BIT
-#undef NL_STRING
-#undef NL_RESPONSE
diff --git a/include/linux/drbd_tag_magic.h b/include/linux/drbd_tag_magic.h
deleted file mode 100644
index 069543190516..000000000000
--- a/include/linux/drbd_tag_magic.h
+++ /dev/null
@@ -1,84 +0,0 @@
-#ifndef DRBD_TAG_MAGIC_H
-#define DRBD_TAG_MAGIC_H
-
-#define TT_END     0
-#define TT_REMOVED 0xE000
-
-/* declare packet_type enums */
-enum packet_types {
-#define NL_PACKET(name, number, fields) P_ ## name = number,
-#define NL_RESPONSE(name, number) P_ ## name = number,
-#define NL_INTEGER(pn, pr, member)
-#define NL_INT64(pn, pr, member)
-#define NL_BIT(pn, pr, member)
-#define NL_STRING(pn, pr, member, len)
-#include "drbd_nl.h"
-	P_nl_after_last_packet,
-};
-
-/* These struct are used to deduce the size of the tag lists: */
-#define NL_PACKET(name, number, fields)	\
-	struct name ## _tag_len_struct { fields };
-#define NL_INTEGER(pn, pr, member)		\
-	int member; int tag_and_len ## member;
-#define NL_INT64(pn, pr, member)		\
-	__u64 member; int tag_and_len ## member;
-#define NL_BIT(pn, pr, member)		\
-	unsigned char member:1; int tag_and_len ## member;
-#define NL_STRING(pn, pr, member, len)	\
-	unsigned char member[len]; int member ## _len; \
-	int tag_and_len ## member;
-#include "linux/drbd_nl.h"
-
-/* declare tag-list-sizes */
-static const int tag_list_sizes[] = {
-#define NL_PACKET(name, number, fields) 2 fields ,
-#define NL_INTEGER(pn, pr, member)      + 4 + 4
-#define NL_INT64(pn, pr, member)        + 4 + 8
-#define NL_BIT(pn, pr, member)          + 4 + 1
-#define NL_STRING(pn, pr, member, len)  + 4 + (len)
-#include "drbd_nl.h"
-};
-
-/* The two highest bits are used for the tag type */
-#define TT_MASK      0xC000
-#define TT_INTEGER   0x0000
-#define TT_INT64     0x4000
-#define TT_BIT       0x8000
-#define TT_STRING    0xC000
-/* The next bit indicates if processing of the tag is mandatory */
-#define T_MANDATORY  0x2000
-#define T_MAY_IGNORE 0x0000
-#define TN_MASK      0x1fff
-/* The remaining 13 bits are used to enumerate the tags */
-
-#define tag_type(T)   ((T) & TT_MASK)
-#define tag_number(T) ((T) & TN_MASK)
-
-/* declare tag enums */
-#define NL_PACKET(name, number, fields) fields
-enum drbd_tags {
-#define NL_INTEGER(pn, pr, member)     T_ ## member = pn | TT_INTEGER | pr ,
-#define NL_INT64(pn, pr, member)       T_ ## member = pn | TT_INT64   | pr ,
-#define NL_BIT(pn, pr, member)         T_ ## member = pn | TT_BIT     | pr ,
-#define NL_STRING(pn, pr, member, len) T_ ## member = pn | TT_STRING  | pr ,
-#include "drbd_nl.h"
-};
-
-struct tag {
-	const char *name;
-	int type_n_flags;
-	int max_len;
-};
-
-/* declare tag names */
-#define NL_PACKET(name, number, fields) fields
-static const struct tag tag_descriptions[] = {
-#define NL_INTEGER(pn, pr, member)     [ pn ] = { #member, TT_INTEGER | pr, sizeof(int)   },
-#define NL_INT64(pn, pr, member)       [ pn ] = { #member, TT_INT64   | pr, sizeof(__u64) },
-#define NL_BIT(pn, pr, member)         [ pn ] = { #member, TT_BIT     | pr, sizeof(int)   },
-#define NL_STRING(pn, pr, member, len) [ pn ] = { #member, TT_STRING  | pr, (len)         },
-#include "drbd_nl.h"
-};
-
-#endif
-- 
cgit v1.2.3-55-g7522


From 85f75dd7630436b0aa46a6393099c0f23121f5f0 Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Tue, 15 Mar 2011 16:26:37 +0100
Subject: drbd: introduce in-kernel "down" command

This greatly simplifies deconfiguration of whole resources.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_main.c |   2 -
 drivers/block/drbd/drbd_nl.c   | 203 ++++++++++++++++++++++++++++++-----------
 include/linux/drbd_genl.h      |   2 +
 3 files changed, 154 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 113c7b465384..40b7b93def75 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2303,9 +2303,7 @@ fail:
 
 void drbd_free_tconn(struct drbd_tconn *tconn)
 {
-	mutex_lock(&drbd_cfg_mutex);
 	list_del(&tconn->all_tconn);
-	mutex_unlock(&drbd_cfg_mutex);
 	idr_destroy(&tconn->volumes);
 
 	free_cpumask_var(tconn->cpu_mask);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index f965dfe4b5ff..d952e877f8d5 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -49,6 +49,7 @@ int drbd_adm_delete_minor(struct sk_buff *skb, struct genl_info *info);
 
 int drbd_adm_create_connection(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_delete_connection(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_down(struct sk_buff *skb, struct genl_info *info);
 
 int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info);
@@ -1416,6 +1417,18 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
+static int adm_detach(struct drbd_conf *mdev)
+{
+	enum drbd_ret_code retcode;
+	drbd_suspend_io(mdev); /* so no-one is stuck in drbd_al_begin_io */
+	retcode = drbd_request_state(mdev, NS(disk, D_DISKLESS));
+	wait_event(mdev->misc_wait,
+			mdev->state.disk != D_DISKLESS ||
+			!atomic_read(&mdev->local_cnt));
+	drbd_resume_io(mdev);
+	return retcode;
+}
+
 /* Detaching the disk is a process in multiple stages.  First we need to lock
  * out application IO, in-flight IO, IO stuck in drbd_al_begin_io.
  * Then we transition to D_DISKLESS, and wait for put_ldev() to return all
@@ -1423,7 +1436,6 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
  * Only then we have finally detached. */
 int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info)
 {
-	struct drbd_conf *mdev;
 	enum drbd_ret_code retcode;
 
 	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
@@ -1432,13 +1444,7 @@ int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto out;
 
-	mdev = adm_ctx.mdev;
-	drbd_suspend_io(mdev); /* so no-one is stuck in drbd_al_begin_io */
-	retcode = drbd_request_state(mdev, NS(disk, D_DISKLESS));
-	wait_event(mdev->misc_wait,
-			mdev->state.disk != D_DISKLESS ||
-			!atomic_read(&mdev->local_cnt));
-	drbd_resume_io(mdev);
+	retcode = adm_detach(adm_ctx.mdev);
 out:
 	drbd_adm_finish(info, retcode);
 	return 0;
@@ -1680,10 +1686,49 @@ out:
 	return 0;
 }
 
+static enum drbd_state_rv conn_try_disconnect(struct drbd_tconn *tconn, bool force)
+{
+	enum drbd_state_rv rv;
+	if (force) {
+		spin_lock_irq(&tconn->req_lock);
+		if (tconn->cstate >= C_WF_CONNECTION)
+			_conn_request_state(tconn, NS(conn, C_DISCONNECTING), CS_HARD);
+		spin_unlock_irq(&tconn->req_lock);
+		return SS_SUCCESS;
+	}
+
+	rv = conn_request_state(tconn, NS(conn, C_DISCONNECTING), 0);
+
+	switch (rv) {
+	case SS_NOTHING_TO_DO:
+	case SS_ALREADY_STANDALONE:
+		return SS_SUCCESS;
+	case SS_PRIMARY_NOP:
+		/* Our state checking code wants to see the peer outdated. */
+		rv = conn_request_state(tconn, NS2(conn, C_DISCONNECTING,
+							pdsk, D_OUTDATED), CS_VERBOSE);
+		break;
+	case SS_CW_FAILED_BY_PEER:
+		/* The peer probably wants to see us outdated. */
+		rv = conn_request_state(tconn, NS2(conn, C_DISCONNECTING,
+							disk, D_OUTDATED), 0);
+		if (rv == SS_IS_DISKLESS || rv == SS_LOWER_THAN_OUTDATED) {
+			conn_request_state(tconn, NS(conn, C_DISCONNECTING), CS_HARD);
+			rv = SS_SUCCESS;
+		}
+		break;
+	default:;
+		/* no special handling necessary */
+	}
+
+	return rv;
+}
+
 int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info)
 {
 	struct disconnect_parms parms;
 	struct drbd_tconn *tconn;
+	enum drbd_state_rv rv;
 	enum drbd_ret_code retcode;
 	int err;
 
@@ -1704,35 +1749,8 @@ int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	if (parms.force_disconnect) {
-		spin_lock_irq(&tconn->req_lock);
-		if (tconn->cstate >= C_WF_CONNECTION)
-			_conn_request_state(tconn, NS(conn, C_DISCONNECTING), CS_HARD);
-		spin_unlock_irq(&tconn->req_lock);
-		goto done;
-	}
-
-	retcode = conn_request_state(tconn, NS(conn, C_DISCONNECTING), 0);
-
-	if (retcode == SS_NOTHING_TO_DO)
-		goto done;
-	else if (retcode == SS_ALREADY_STANDALONE)
-		goto done;
-	else if (retcode == SS_PRIMARY_NOP) {
-		/* Our state checking code wants to see the peer outdated. */
-		retcode = conn_request_state(tconn, NS2(conn, C_DISCONNECTING,
-							pdsk, D_OUTDATED), CS_VERBOSE);
-	} else if (retcode == SS_CW_FAILED_BY_PEER) {
-		/* The peer probably wants to see us outdated. */
-		retcode = conn_request_state(tconn, NS2(conn, C_DISCONNECTING,
-							disk, D_OUTDATED), 0);
-		if (retcode == SS_IS_DISKLESS || retcode == SS_LOWER_THAN_OUTDATED) {
-			conn_request_state(tconn, NS(conn, C_DISCONNECTING), CS_HARD);
-			retcode = SS_SUCCESS;
-		}
-	}
-
-	if (retcode < SS_SUCCESS)
+	rv = conn_try_disconnect(tconn, parms.force_disconnect);
+	if (rv < SS_SUCCESS)
 		goto fail;
 
 	if (wait_event_interruptible(tconn->ping_wait,
@@ -1743,7 +1761,6 @@ int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info)
 		goto fail;
 	}
 
- done:
 	retcode = NO_ERROR;
  fail:
 	drbd_adm_finish(info, retcode);
@@ -2644,9 +2661,21 @@ out:
 	return 0;
 }
 
+static enum drbd_ret_code adm_delete_minor(struct drbd_conf *mdev)
+{
+	if (mdev->state.disk == D_DISKLESS &&
+	    /* no need to be mdev->state.conn == C_STANDALONE &&
+	     * we may want to delete a minor from a live replication group.
+	     */
+	    mdev->state.role == R_SECONDARY) {
+		drbd_delete_device(mdev_to_minor(mdev));
+		return NO_ERROR;
+	} else
+		return ERR_MINOR_CONFIGURED;
+}
+
 int drbd_adm_delete_minor(struct sk_buff *skb, struct genl_info *info)
 {
-	struct drbd_conf *mdev;
 	enum drbd_ret_code retcode;
 
 	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
@@ -2655,19 +2684,89 @@ int drbd_adm_delete_minor(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto out;
 
-	mdev = adm_ctx.mdev;
-	if (mdev->state.disk == D_DISKLESS &&
-	    /* no need to be mdev->state.conn == C_STANDALONE &&
-	     * we may want to delete a minor from a live replication group.
-	     */
-	    mdev->state.role == R_SECONDARY) {
-		drbd_delete_device(mdev_to_minor(mdev));
-		retcode = NO_ERROR;
-		/* if this was the last volume of this connection,
-		 * this will terminate all threads */
+	mutex_lock(&drbd_cfg_mutex);
+	retcode = adm_delete_minor(adm_ctx.mdev);
+	mutex_unlock(&drbd_cfg_mutex);
+	/* if this was the last volume of this connection,
+	 * this will terminate all threads */
+	if (retcode == NO_ERROR)
 		conn_reconfig_done(adm_ctx.tconn);
-	} else
-		retcode = ERR_MINOR_CONFIGURED;
+out:
+	drbd_adm_finish(info, retcode);
+	return 0;
+}
+
+int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
+{
+	enum drbd_ret_code retcode;
+	enum drbd_state_rv rv;
+	struct drbd_conf *mdev;
+	unsigned i;
+
+	retcode = drbd_adm_prepare(skb, info, 0);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
+
+	if (!adm_ctx.tconn) {
+		retcode = ERR_CONN_NOT_KNOWN;
+		goto out;
+	}
+
+	mutex_lock(&drbd_cfg_mutex);
+	/* demote */
+	idr_for_each_entry(&adm_ctx.tconn->volumes, mdev, i) {
+		retcode = drbd_set_role(mdev, R_SECONDARY, 0);
+		if (retcode < SS_SUCCESS) {
+			drbd_msg_put_info("failed to demote");
+			goto out_unlock;
+		}
+	}
+
+	/* disconnect */
+	rv = conn_try_disconnect(adm_ctx.tconn, 0);
+	if (rv < SS_SUCCESS) {
+		retcode = rv; /* enum type mismatch! */
+		drbd_msg_put_info("failed to disconnect");
+		goto out_unlock;
+	}
+
+	/* detach */
+	idr_for_each_entry(&adm_ctx.tconn->volumes, mdev, i) {
+		rv = adm_detach(mdev);
+		if (rv < SS_SUCCESS) {
+			retcode = rv; /* enum type mismatch! */
+			drbd_msg_put_info("failed to detach");
+			goto out_unlock;
+		}
+	}
+
+	/* delete volumes */
+	idr_for_each_entry(&adm_ctx.tconn->volumes, mdev, i) {
+		retcode = adm_delete_minor(mdev);
+		if (retcode != NO_ERROR) {
+			/* "can not happen" */
+			drbd_msg_put_info("failed to delete volume");
+			goto out_unlock;
+		}
+	}
+
+	/* stop all threads */
+	conn_reconfig_done(adm_ctx.tconn);
+
+	/* delete connection */
+	if (conn_lowest_minor(adm_ctx.tconn) < 0) {
+		drbd_free_tconn(adm_ctx.tconn);
+		retcode = NO_ERROR;
+	} else {
+		/* "can not happen" */
+		retcode = ERR_CONN_IN_USE;
+		drbd_msg_put_info("failed to delete connection");
+		goto out_unlock;
+	}
+out_unlock:
+	mutex_unlock(&drbd_cfg_mutex);
 out:
 	drbd_adm_finish(info, retcode);
 	return 0;
@@ -2683,12 +2782,14 @@ int drbd_adm_delete_connection(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto out;
 
+	mutex_lock(&drbd_cfg_mutex);
 	if (conn_lowest_minor(adm_ctx.tconn) < 0) {
 		drbd_free_tconn(adm_ctx.tconn);
 		retcode = NO_ERROR;
 	} else {
 		retcode = ERR_CONN_IN_USE;
 	}
+	mutex_unlock(&drbd_cfg_mutex);
 
 out:
 	drbd_adm_finish(info, retcode);
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 84e16848f7a1..a07d69279b1a 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -347,3 +347,5 @@ GENL_op(DRBD_ADM_OUTDATE,	25, GENL_doit(drbd_adm_outdate),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
 GENL_op(DRBD_ADM_GET_TIMEOUT_TYPE, 26, GENL_doit(drbd_adm_get_timeout_type),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+GENL_op(DRBD_ADM_DOWN,		27, GENL_doit(drbd_adm_down),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
-- 
cgit v1.2.3-55-g7522


From 047e95e259e81d7b97eca10cda0aa93082531ac1 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Wed, 16 Mar 2011 14:43:36 +0100
Subject: drbd: Allow volumes to become primary only on one side

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_state.c   | 21 ++++++++++++++++++---
 drivers/block/drbd/drbd_strings.c |  1 +
 include/linux/drbd.h              |  3 ++-
 3 files changed, 21 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 886b996ec7b3..11685658659e 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -329,6 +329,18 @@ static void print_state_change(struct drbd_conf *mdev, union drbd_state os, unio
 		dev_info(DEV, "%s\n", pb);
 }
 
+static bool vol_has_primary_peer(struct drbd_tconn *tconn)
+{
+	struct drbd_conf *mdev;
+	int minor;
+
+	idr_for_each_entry(&tconn->volumes, mdev, minor) {
+		if (mdev->state.peer == R_PRIMARY)
+			return true;
+	}
+	return false;
+}
+
 /**
  * is_valid_state() - Returns an SS_ error code if ns is not valid
  * @mdev:	DRBD device.
@@ -349,9 +361,12 @@ is_valid_state(struct drbd_conf *mdev, union drbd_state ns)
 	}
 
 	if (get_net_conf(mdev->tconn)) {
-		if (!mdev->tconn->net_conf->two_primaries &&
-		    ns.role == R_PRIMARY && ns.peer == R_PRIMARY)
-			rv = SS_TWO_PRIMARIES;
+		if (!mdev->tconn->net_conf->two_primaries && ns.role == R_PRIMARY) {
+			if (ns.peer == R_PRIMARY)
+				rv = SS_TWO_PRIMARIES;
+			else if (vol_has_primary_peer(mdev->tconn))
+				rv = SS_O_VOL_PEER_PRI;
+			}
 		put_net_conf(mdev->tconn);
 	}
 
diff --git a/drivers/block/drbd/drbd_strings.c b/drivers/block/drbd/drbd_strings.c
index c44a2a602772..9a664bd27404 100644
--- a/drivers/block/drbd/drbd_strings.c
+++ b/drivers/block/drbd/drbd_strings.c
@@ -89,6 +89,7 @@ static const char *drbd_state_sw_errors[] = {
 	[-SS_LOWER_THAN_OUTDATED] = "Disk state is lower than outdated",
 	[-SS_IN_TRANSIENT_STATE] = "In transient state, retry after next state change",
 	[-SS_CONCURRENT_ST_CHG] = "Concurrent state changes detected and aborted",
+	[-SS_O_VOL_PEER_PRI] = "Other vol primary on peer not allowed by config",
 };
 
 const char *drbd_conn_str(enum drbd_conns s)
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index d28fdd8fcd49..9cdb888607ae 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -300,7 +300,8 @@ enum drbd_state_rv {
 	SS_NOT_SUPPORTED = -17,      /* drbd-8.2 only */
 	SS_IN_TRANSIENT_STATE = -18,  /* Retry after the next state change */
 	SS_CONCURRENT_ST_CHG = -19,   /* Concurrent cluster side state change! */
-	SS_AFTER_LAST_ERROR = -20,    /* Keep this at bottom */
+	SS_O_VOL_PEER_PRI = -20,
+	SS_AFTER_LAST_ERROR = -21,    /* Keep this at bottom */
 };
 
 /* from drbd_strings.c */
-- 
cgit v1.2.3-55-g7522


From 2cbacafd7af0f1cc7a433668c662a91ba6aabc1b Mon Sep 17 00:00:00 2001
From: Russell King
Date: Tue, 17 Apr 2012 16:34:13 +0100
Subject: SERIAL: core: add hardware assisted s/w flow control support

Ports which are capable of handling s/w flow control in hardware to
know when the s/w flow control termios settings are changed.  Add a
flag to allow the low level serial drivers to indicate that they
support this, and these changes should be propagated to them.

Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 drivers/tty/serial/serial_core.c | 16 ++++++++++++++--
 include/linux/serial_core.h      |  2 ++
 2 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index bc2065d323b9..bd10bbd56446 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1213,7 +1213,19 @@ static void uart_set_termios(struct tty_struct *tty,
 	struct uart_port *uport = state->uart_port;
 	unsigned long flags;
 	unsigned int cflag = tty->termios.c_cflag;
+	unsigned int iflag_mask = IGNBRK|BRKINT|IGNPAR|PARMRK|INPCK;
+	bool sw_changed = false;
 
+	/*
+	 * Drivers doing software flow control also need to know
+	 * about changes to these input settings.
+	 */
+	if (uport->flags & UPF_SOFT_FLOW) {
+		iflag_mask |= IXANY|IXON|IXOFF;
+		sw_changed =
+		   tty->termios.c_cc[VSTART] != old_termios->c_cc[VSTART] ||
+		   tty->termios.c_cc[VSTOP] != old_termios->c_cc[VSTOP];
+	}
 
 	/*
 	 * These are the bits that are used to setup various
@@ -1221,11 +1233,11 @@ static void uart_set_termios(struct tty_struct *tty,
 	 * bits in c_cflag; c_[io]speed will always be set
 	 * appropriately by set_termios() in tty_ioctl.c
 	 */
-#define RELEVANT_IFLAG(iflag)	((iflag) & (IGNBRK|BRKINT|IGNPAR|PARMRK|INPCK))
 	if ((cflag ^ old_termios->c_cflag) == 0 &&
 	    tty->termios.c_ospeed == old_termios->c_ospeed &&
 	    tty->termios.c_ispeed == old_termios->c_ispeed &&
-	    RELEVANT_IFLAG(tty->termios.c_iflag ^ old_termios->c_iflag) == 0) {
+	    ((tty->termios.c_iflag ^ old_termios->c_iflag) & iflag_mask) == 0 &&
+	    !sw_changed) {
 		return;
 	}
 
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 3c430228d232..00051388de3c 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -163,6 +163,8 @@ struct uart_port {
 #define UPF_BUGGY_UART		((__force upf_t) (1 << 14))
 #define UPF_NO_TXEN_TEST	((__force upf_t) (1 << 15))
 #define UPF_MAGIC_MULTIPLIER	((__force upf_t) (1 << 16))
+/* Port has hardware-assisted s/w flow control */
+#define UPF_SOFT_FLOW		((__force upf_t) (1 << 22))
 #define UPF_CONS_FLOW		((__force upf_t) (1 << 23))
 #define UPF_SHARE_IRQ		((__force upf_t) (1 << 24))
 #define UPF_EXAR_EFR		((__force upf_t) (1 << 25))
-- 
cgit v1.2.3-55-g7522


From dba05832cbe4f305dfd998fb26d7c685d91fbbd8 Mon Sep 17 00:00:00 2001
From: Russell King
Date: Tue, 17 Apr 2012 16:41:10 +0100
Subject: SERIAL: core: add hardware assisted h/w flow control support

Ports which are handling h/w flow control in hardware must not have
their RTS state altered depending on the tty's hardware-stopped state.
Avoid this additional logic when setting the termios state.

Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 drivers/tty/serial/serial_core.c | 7 +++++++
 include/linux/serial_core.h      | 2 ++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index bd10bbd56446..9d8796e77188 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1255,6 +1255,13 @@ static void uart_set_termios(struct tty_struct *tty,
 		uart_set_mctrl(uport, mask);
 	}
 
+	/*
+	 * If the port is doing h/w assisted flow control, do nothing.
+	 * We assume that tty->hw_stopped has never been set.
+	 */
+	if (uport->flags & UPF_HARD_FLOW)
+		return;
+
 	/* Handle turning off CRTSCTS */
 	if ((old_termios->c_cflag & CRTSCTS) && !(cflag & CRTSCTS)) {
 		spin_lock_irqsave(&uport->lock, flags);
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 00051388de3c..e2cda5d04e48 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -163,6 +163,8 @@ struct uart_port {
 #define UPF_BUGGY_UART		((__force upf_t) (1 << 14))
 #define UPF_NO_TXEN_TEST	((__force upf_t) (1 << 15))
 #define UPF_MAGIC_MULTIPLIER	((__force upf_t) (1 << 16))
+/* Port has hardware-assisted h/w flow control (iow, auto-RTS *not* auto-CTS) */
+#define UPF_HARD_FLOW		((__force upf_t) (1 << 21))
 /* Port has hardware-assisted s/w flow control */
 #define UPF_SOFT_FLOW		((__force upf_t) (1 << 22))
 #define UPF_CONS_FLOW		((__force upf_t) (1 << 23))
-- 
cgit v1.2.3-55-g7522


From 9aba8d5b011193c8e01d565c5b585df5b94f1db2 Mon Sep 17 00:00:00 2001
From: Russell King
Date: Tue, 17 Apr 2012 17:23:14 +0100
Subject: SERIAL: core: add throttle/unthrottle callbacks for hardware assisted
 flow control

Add two callbacks for hardware assisted flow control; we need to know
when the tty layers want us to stop and restart due to their buffer
levels.

Call a driver specific throttle/unthrottle function if and only if the
driver indicates that it is using an enabled hardware assisted flow
control method, otherwise fall back to the non-hardware assisted
methods.

Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 drivers/tty/serial/serial_core.c | 31 +++++++++++++++++++++++++++----
 include/linux/serial_core.h      |  2 ++
 2 files changed, 29 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 9d8796e77188..098bb99c2b9f 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -610,27 +610,50 @@ static void uart_send_xchar(struct tty_struct *tty, char ch)
 static void uart_throttle(struct tty_struct *tty)
 {
 	struct uart_state *state = tty->driver_data;
+	struct uart_port *port = state->uart_port;
+	uint32_t mask = 0;
 
 	if (I_IXOFF(tty))
+		mask |= UPF_SOFT_FLOW;
+	if (tty->termios.c_cflag & CRTSCTS)
+		mask |= UPF_HARD_FLOW;
+
+	if (port->flags & mask) {
+		port->ops->throttle(port);
+		mask &= ~port->flags;
+	}
+
+	if (mask & UPF_SOFT_FLOW)
 		uart_send_xchar(tty, STOP_CHAR(tty));
 
-	if (tty->termios.c_cflag & CRTSCTS)
-		uart_clear_mctrl(state->uart_port, TIOCM_RTS);
+	if (mask & UPF_HARD_FLOW)
+		uart_clear_mctrl(port, TIOCM_RTS);
 }
 
 static void uart_unthrottle(struct tty_struct *tty)
 {
 	struct uart_state *state = tty->driver_data;
 	struct uart_port *port = state->uart_port;
+	uint32_t mask = 0;
 
-	if (I_IXOFF(tty)) {
+	if (I_IXOFF(tty))
+		mask |= UPF_SOFT_FLOW;
+	if (tty->termios.c_cflag & CRTSCTS)
+		mask |= UPF_HARD_FLOW;
+
+	if (port->flags & mask) {
+		port->ops->unthrottle(port);
+		mask &= ~port->flags;
+	}
+
+	if (mask & UPF_SOFT_FLOW) {
 		if (port->x_char)
 			port->x_char = 0;
 		else
 			uart_send_xchar(tty, START_CHAR(tty));
 	}
 
-	if (tty->termios.c_cflag & CRTSCTS)
+	if (mask & UPF_HARD_FLOW)
 		uart_set_mctrl(port, TIOCM_RTS);
 }
 
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index e2cda5d04e48..c6690a2a27fb 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -46,6 +46,8 @@ struct uart_ops {
 	unsigned int	(*get_mctrl)(struct uart_port *);
 	void		(*stop_tx)(struct uart_port *);
 	void		(*start_tx)(struct uart_port *);
+	void		(*throttle)(struct uart_port *);
+	void		(*unthrottle)(struct uart_port *);
 	void		(*send_xchar)(struct uart_port *, char ch);
 	void		(*stop_rx)(struct uart_port *);
 	void		(*enable_ms)(struct uart_port *);
-- 
cgit v1.2.3-55-g7522


From 2389d5014342e9535aad212d0c68d439aaf534ba Mon Sep 17 00:00:00 2001
From: Linus Walleij
Date: Wed, 31 Oct 2012 22:04:31 +0100
Subject: ARM: plat-versatile: move FPGA irq driver to drivers/irqchip

This moves the Versatile FPGA interrupt controller driver, used in
the Integrator/AP, Integrator/CP and some Versatile boards, out
of arch/arm/plat-versatile and down to drivers/irqchip where we
have consensus that such drivers belong. The header file is
consequently moved to <linux/platform_data/irq-versatile-fpga.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/arm/Kconfig                                |   4 +-
 arch/arm/mach-integrator/integrator_ap.c        |   3 +-
 arch/arm/mach-integrator/integrator_cp.c        |   2 +-
 arch/arm/mach-versatile/core.c                  |   2 +-
 arch/arm/plat-versatile/Kconfig                 |   9 --
 arch/arm/plat-versatile/Makefile                |   1 -
 arch/arm/plat-versatile/fpga-irq.c              | 204 ------------------------
 arch/arm/plat-versatile/include/plat/fpga-irq.h |  13 --
 drivers/irqchip/Kconfig                         |   9 +-
 drivers/irqchip/Makefile                        |   1 +
 drivers/irqchip/irq-versatile-fpga.c            | 204 ++++++++++++++++++++++++
 include/linux/irqchip/versatile-fpga.h          |  13 ++
 12 files changed, 231 insertions(+), 234 deletions(-)
 delete mode 100644 arch/arm/plat-versatile/fpga-irq.c
 delete mode 100644 arch/arm/plat-versatile/include/plat/fpga-irq.h
 create mode 100644 drivers/irqchip/irq-versatile-fpga.c
 create mode 100644 include/linux/irqchip/versatile-fpga.h

(limited to 'include')

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 73067efd4845..2205e3eb55bf 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -284,8 +284,8 @@ config ARCH_INTEGRATOR
 	select MULTI_IRQ_HANDLER
 	select NEED_MACH_MEMORY_H
 	select PLAT_VERSATILE
-	select PLAT_VERSATILE_FPGA_IRQ
 	select SPARSE_IRQ
+	select VERSATILE_FPGA_IRQ
 	help
 	  Support for ARM's Integrator platform.
 
@@ -318,7 +318,7 @@ config ARCH_VERSATILE
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_CLCD
 	select PLAT_VERSATILE_CLOCK
-	select PLAT_VERSATILE_FPGA_IRQ
+	select VERSATILE_FPGA_IRQ
 	help
 	  This enables support for ARM Ltd Versatile board.
 
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 4f13bc57e5a4..e67a9fe18d1b 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -31,6 +31,7 @@
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/irqchip/versatile-fpga.h>
 #include <linux/mtd/physmap.h>
 #include <linux/clk.h>
 #include <linux/platform_data/clk-integrator.h>
@@ -56,8 +57,6 @@
 #include <asm/mach/pci.h>
 #include <asm/mach/time.h>
 
-#include <plat/fpga-irq.h>
-
 #include "common.h"
 
 /* 
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index 4423bc8e84c5..acecf04f50f7 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -20,6 +20,7 @@
 #include <linux/amba/clcd.h>
 #include <linux/amba/mmci.h>
 #include <linux/io.h>
+#include <linux/irqchip/versatile-fpga.h>
 #include <linux/gfp.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_data/clk-integrator.h>
@@ -46,7 +47,6 @@
 #include <asm/hardware/timer-sp.h>
 
 #include <plat/clcd.h>
-#include <plat/fpga-irq.h>
 #include <plat/sched_clock.h>
 
 #include "common.h"
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index 5b5c1eeb5b5c..5d5929450366 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -32,6 +32,7 @@
 #include <linux/amba/mmci.h>
 #include <linux/amba/pl022.h>
 #include <linux/io.h>
+#include <linux/irqchip/versatile-fpga.h>
 #include <linux/gfp.h>
 #include <linux/clkdev.h>
 #include <linux/mtd/physmap.h>
@@ -51,7 +52,6 @@
 #include <asm/hardware/timer-sp.h>
 
 #include <plat/clcd.h>
-#include <plat/fpga-irq.h>
 #include <plat/sched_clock.h>
 
 #include "core.h"
diff --git a/arch/arm/plat-versatile/Kconfig b/arch/arm/plat-versatile/Kconfig
index 2a4ae8a6a081..619f0fa0f06c 100644
--- a/arch/arm/plat-versatile/Kconfig
+++ b/arch/arm/plat-versatile/Kconfig
@@ -6,15 +6,6 @@ config PLAT_VERSATILE_CLOCK
 config PLAT_VERSATILE_CLCD
 	bool
 
-config PLAT_VERSATILE_FPGA_IRQ
-	bool
-	select IRQ_DOMAIN
-
-config PLAT_VERSATILE_FPGA_IRQ_NR
-       int
-       default 4
-       depends on PLAT_VERSATILE_FPGA_IRQ
-
 config PLAT_VERSATILE_LEDS
 	def_bool y if NEW_LEDS
 	depends on ARCH_REALVIEW || ARCH_VERSATILE
diff --git a/arch/arm/plat-versatile/Makefile b/arch/arm/plat-versatile/Makefile
index 74cfd94cbf80..f88d448b629c 100644
--- a/arch/arm/plat-versatile/Makefile
+++ b/arch/arm/plat-versatile/Makefile
@@ -2,7 +2,6 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include
 
 obj-$(CONFIG_PLAT_VERSATILE_CLOCK) += clock.o
 obj-$(CONFIG_PLAT_VERSATILE_CLCD) += clcd.o
-obj-$(CONFIG_PLAT_VERSATILE_FPGA_IRQ) += fpga-irq.o
 obj-$(CONFIG_PLAT_VERSATILE_LEDS) += leds.o
 obj-$(CONFIG_PLAT_VERSATILE_SCHED_CLOCK) += sched-clock.o
 obj-$(CONFIG_SMP) += headsmp.o platsmp.o
diff --git a/arch/arm/plat-versatile/fpga-irq.c b/arch/arm/plat-versatile/fpga-irq.c
deleted file mode 100644
index dfe317c20354..000000000000
--- a/arch/arm/plat-versatile/fpga-irq.c
+++ /dev/null
@@ -1,204 +0,0 @@
-/*
- *  Support for Versatile FPGA-based IRQ controllers
- */
-#include <linux/bitops.h>
-#include <linux/irq.h>
-#include <linux/io.h>
-#include <linux/irqdomain.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-
-#include <asm/exception.h>
-#include <asm/mach/irq.h>
-#include <plat/fpga-irq.h>
-
-#define IRQ_STATUS		0x00
-#define IRQ_RAW_STATUS		0x04
-#define IRQ_ENABLE_SET		0x08
-#define IRQ_ENABLE_CLEAR	0x0c
-#define INT_SOFT_SET		0x10
-#define INT_SOFT_CLEAR		0x14
-#define FIQ_STATUS		0x20
-#define FIQ_RAW_STATUS		0x24
-#define FIQ_ENABLE		0x28
-#define FIQ_ENABLE_SET		0x28
-#define FIQ_ENABLE_CLEAR	0x2C
-
-/**
- * struct fpga_irq_data - irq data container for the FPGA IRQ controller
- * @base: memory offset in virtual memory
- * @chip: chip container for this instance
- * @domain: IRQ domain for this instance
- * @valid: mask for valid IRQs on this controller
- * @used_irqs: number of active IRQs on this controller
- */
-struct fpga_irq_data {
-	void __iomem *base;
-	struct irq_chip chip;
-	u32 valid;
-	struct irq_domain *domain;
-	u8 used_irqs;
-};
-
-/* we cannot allocate memory when the controllers are initially registered */
-static struct fpga_irq_data fpga_irq_devices[CONFIG_PLAT_VERSATILE_FPGA_IRQ_NR];
-static int fpga_irq_id;
-
-static void fpga_irq_mask(struct irq_data *d)
-{
-	struct fpga_irq_data *f = irq_data_get_irq_chip_data(d);
-	u32 mask = 1 << d->hwirq;
-
-	writel(mask, f->base + IRQ_ENABLE_CLEAR);
-}
-
-static void fpga_irq_unmask(struct irq_data *d)
-{
-	struct fpga_irq_data *f = irq_data_get_irq_chip_data(d);
-	u32 mask = 1 << d->hwirq;
-
-	writel(mask, f->base + IRQ_ENABLE_SET);
-}
-
-static void fpga_irq_handle(unsigned int irq, struct irq_desc *desc)
-{
-	struct fpga_irq_data *f = irq_desc_get_handler_data(desc);
-	u32 status = readl(f->base + IRQ_STATUS);
-
-	if (status == 0) {
-		do_bad_IRQ(irq, desc);
-		return;
-	}
-
-	do {
-		irq = ffs(status) - 1;
-		status &= ~(1 << irq);
-		generic_handle_irq(irq_find_mapping(f->domain, irq));
-	} while (status);
-}
-
-/*
- * Handle each interrupt in a single FPGA IRQ controller.  Returns non-zero
- * if we've handled at least one interrupt.  This does a single read of the
- * status register and handles all interrupts in order from LSB first.
- */
-static int handle_one_fpga(struct fpga_irq_data *f, struct pt_regs *regs)
-{
-	int handled = 0;
-	int irq;
-	u32 status;
-
-	while ((status  = readl(f->base + IRQ_STATUS))) {
-		irq = ffs(status) - 1;
-		handle_IRQ(irq_find_mapping(f->domain, irq), regs);
-		handled = 1;
-	}
-
-	return handled;
-}
-
-/*
- * Keep iterating over all registered FPGA IRQ controllers until there are
- * no pending interrupts.
- */
-asmlinkage void __exception_irq_entry fpga_handle_irq(struct pt_regs *regs)
-{
-	int i, handled;
-
-	do {
-		for (i = 0, handled = 0; i < fpga_irq_id; ++i)
-			handled |= handle_one_fpga(&fpga_irq_devices[i], regs);
-	} while (handled);
-}
-
-static int fpga_irqdomain_map(struct irq_domain *d, unsigned int irq,
-		irq_hw_number_t hwirq)
-{
-	struct fpga_irq_data *f = d->host_data;
-
-	/* Skip invalid IRQs, only register handlers for the real ones */
-	if (!(f->valid & BIT(hwirq)))
-		return -ENOTSUPP;
-	irq_set_chip_data(irq, f);
-	irq_set_chip_and_handler(irq, &f->chip,
-				handle_level_irq);
-	set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
-	return 0;
-}
-
-static struct irq_domain_ops fpga_irqdomain_ops = {
-	.map = fpga_irqdomain_map,
-	.xlate = irq_domain_xlate_onetwocell,
-};
-
-void __init fpga_irq_init(void __iomem *base, const char *name, int irq_start,
-			  int parent_irq, u32 valid, struct device_node *node)
-{
-	struct fpga_irq_data *f;
-	int i;
-
-	if (fpga_irq_id >= ARRAY_SIZE(fpga_irq_devices)) {
-		pr_err("%s: too few FPGA IRQ controllers, increase CONFIG_PLAT_VERSATILE_FPGA_IRQ_NR\n", __func__);
-		return;
-	}
-	f = &fpga_irq_devices[fpga_irq_id];
-	f->base = base;
-	f->chip.name = name;
-	f->chip.irq_ack = fpga_irq_mask;
-	f->chip.irq_mask = fpga_irq_mask;
-	f->chip.irq_unmask = fpga_irq_unmask;
-	f->valid = valid;
-
-	if (parent_irq != -1) {
-		irq_set_handler_data(parent_irq, f);
-		irq_set_chained_handler(parent_irq, fpga_irq_handle);
-	}
-
-	/* This will also allocate irq descriptors */
-	f->domain = irq_domain_add_simple(node, fls(valid), irq_start,
-					  &fpga_irqdomain_ops, f);
-
-	/* This will allocate all valid descriptors in the linear case */
-	for (i = 0; i < fls(valid); i++)
-		if (valid & BIT(i)) {
-			if (!irq_start)
-				irq_create_mapping(f->domain, i);
-			f->used_irqs++;
-		}
-
-	pr_info("FPGA IRQ chip %d \"%s\" @ %p, %u irqs\n",
-		fpga_irq_id, name, base, f->used_irqs);
-
-	fpga_irq_id++;
-}
-
-#ifdef CONFIG_OF
-int __init fpga_irq_of_init(struct device_node *node,
-			    struct device_node *parent)
-{
-	struct fpga_irq_data *f;
-	void __iomem *base;
-	u32 clear_mask;
-	u32 valid_mask;
-
-	if (WARN_ON(!node))
-		return -ENODEV;
-
-	base = of_iomap(node, 0);
-	WARN(!base, "unable to map fpga irq registers\n");
-
-	if (of_property_read_u32(node, "clear-mask", &clear_mask))
-		clear_mask = 0;
-
-	if (of_property_read_u32(node, "valid-mask", &valid_mask))
-		valid_mask = 0;
-
-	fpga_irq_init(base, node->name, 0, -1, valid_mask, node);
-
-	writel(clear_mask, base + IRQ_ENABLE_CLEAR);
-	writel(clear_mask, base + FIQ_ENABLE_CLEAR);
-
-	return 0;
-}
-#endif
diff --git a/arch/arm/plat-versatile/include/plat/fpga-irq.h b/arch/arm/plat-versatile/include/plat/fpga-irq.h
deleted file mode 100644
index 1fac9651d3ca..000000000000
--- a/arch/arm/plat-versatile/include/plat/fpga-irq.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef PLAT_FPGA_IRQ_H
-#define PLAT_FPGA_IRQ_H
-
-struct device_node;
-struct pt_regs;
-
-void fpga_handle_irq(struct pt_regs *regs);
-void fpga_irq_init(void __iomem *, const char *, int, int, u32,
-		struct device_node *node);
-int fpga_irq_of_init(struct device_node *node,
-		     struct device_node *parent);
-
-#endif
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 1bb8bf6d7fd4..62ca575701d3 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -1 +1,8 @@
-# empty
+config VERSATILE_FPGA_IRQ
+	bool
+	select IRQ_DOMAIN
+
+config VERSATILE_FPGA_IRQ_NR
+       int
+       default 4
+       depends on VERSATILE_FPGA_IRQ
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 054321db4350..e2e6eb5d32f4 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -1 +1,2 @@
 obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2835.o
+obj-$(CONFIG_VERSATILE_FPGA_IRQ) += irq-versatile-fpga.o
diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c
new file mode 100644
index 000000000000..789b3e526930
--- /dev/null
+++ b/drivers/irqchip/irq-versatile-fpga.c
@@ -0,0 +1,204 @@
+/*
+ *  Support for Versatile FPGA-based IRQ controllers
+ */
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/irqchip/versatile-fpga.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#include <asm/exception.h>
+#include <asm/mach/irq.h>
+
+#define IRQ_STATUS		0x00
+#define IRQ_RAW_STATUS		0x04
+#define IRQ_ENABLE_SET		0x08
+#define IRQ_ENABLE_CLEAR	0x0c
+#define INT_SOFT_SET		0x10
+#define INT_SOFT_CLEAR		0x14
+#define FIQ_STATUS		0x20
+#define FIQ_RAW_STATUS		0x24
+#define FIQ_ENABLE		0x28
+#define FIQ_ENABLE_SET		0x28
+#define FIQ_ENABLE_CLEAR	0x2C
+
+/**
+ * struct fpga_irq_data - irq data container for the FPGA IRQ controller
+ * @base: memory offset in virtual memory
+ * @chip: chip container for this instance
+ * @domain: IRQ domain for this instance
+ * @valid: mask for valid IRQs on this controller
+ * @used_irqs: number of active IRQs on this controller
+ */
+struct fpga_irq_data {
+	void __iomem *base;
+	struct irq_chip chip;
+	u32 valid;
+	struct irq_domain *domain;
+	u8 used_irqs;
+};
+
+/* we cannot allocate memory when the controllers are initially registered */
+static struct fpga_irq_data fpga_irq_devices[CONFIG_VERSATILE_FPGA_IRQ_NR];
+static int fpga_irq_id;
+
+static void fpga_irq_mask(struct irq_data *d)
+{
+	struct fpga_irq_data *f = irq_data_get_irq_chip_data(d);
+	u32 mask = 1 << d->hwirq;
+
+	writel(mask, f->base + IRQ_ENABLE_CLEAR);
+}
+
+static void fpga_irq_unmask(struct irq_data *d)
+{
+	struct fpga_irq_data *f = irq_data_get_irq_chip_data(d);
+	u32 mask = 1 << d->hwirq;
+
+	writel(mask, f->base + IRQ_ENABLE_SET);
+}
+
+static void fpga_irq_handle(unsigned int irq, struct irq_desc *desc)
+{
+	struct fpga_irq_data *f = irq_desc_get_handler_data(desc);
+	u32 status = readl(f->base + IRQ_STATUS);
+
+	if (status == 0) {
+		do_bad_IRQ(irq, desc);
+		return;
+	}
+
+	do {
+		irq = ffs(status) - 1;
+		status &= ~(1 << irq);
+		generic_handle_irq(irq_find_mapping(f->domain, irq));
+	} while (status);
+}
+
+/*
+ * Handle each interrupt in a single FPGA IRQ controller.  Returns non-zero
+ * if we've handled at least one interrupt.  This does a single read of the
+ * status register and handles all interrupts in order from LSB first.
+ */
+static int handle_one_fpga(struct fpga_irq_data *f, struct pt_regs *regs)
+{
+	int handled = 0;
+	int irq;
+	u32 status;
+
+	while ((status  = readl(f->base + IRQ_STATUS))) {
+		irq = ffs(status) - 1;
+		handle_IRQ(irq_find_mapping(f->domain, irq), regs);
+		handled = 1;
+	}
+
+	return handled;
+}
+
+/*
+ * Keep iterating over all registered FPGA IRQ controllers until there are
+ * no pending interrupts.
+ */
+asmlinkage void __exception_irq_entry fpga_handle_irq(struct pt_regs *regs)
+{
+	int i, handled;
+
+	do {
+		for (i = 0, handled = 0; i < fpga_irq_id; ++i)
+			handled |= handle_one_fpga(&fpga_irq_devices[i], regs);
+	} while (handled);
+}
+
+static int fpga_irqdomain_map(struct irq_domain *d, unsigned int irq,
+		irq_hw_number_t hwirq)
+{
+	struct fpga_irq_data *f = d->host_data;
+
+	/* Skip invalid IRQs, only register handlers for the real ones */
+	if (!(f->valid & BIT(hwirq)))
+		return -ENOTSUPP;
+	irq_set_chip_data(irq, f);
+	irq_set_chip_and_handler(irq, &f->chip,
+				handle_level_irq);
+	set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+	return 0;
+}
+
+static struct irq_domain_ops fpga_irqdomain_ops = {
+	.map = fpga_irqdomain_map,
+	.xlate = irq_domain_xlate_onetwocell,
+};
+
+void __init fpga_irq_init(void __iomem *base, const char *name, int irq_start,
+			  int parent_irq, u32 valid, struct device_node *node)
+{
+	struct fpga_irq_data *f;
+	int i;
+
+	if (fpga_irq_id >= ARRAY_SIZE(fpga_irq_devices)) {
+		pr_err("%s: too few FPGA IRQ controllers, increase CONFIG_PLAT_VERSATILE_FPGA_IRQ_NR\n", __func__);
+		return;
+	}
+	f = &fpga_irq_devices[fpga_irq_id];
+	f->base = base;
+	f->chip.name = name;
+	f->chip.irq_ack = fpga_irq_mask;
+	f->chip.irq_mask = fpga_irq_mask;
+	f->chip.irq_unmask = fpga_irq_unmask;
+	f->valid = valid;
+
+	if (parent_irq != -1) {
+		irq_set_handler_data(parent_irq, f);
+		irq_set_chained_handler(parent_irq, fpga_irq_handle);
+	}
+
+	/* This will also allocate irq descriptors */
+	f->domain = irq_domain_add_simple(node, fls(valid), irq_start,
+					  &fpga_irqdomain_ops, f);
+
+	/* This will allocate all valid descriptors in the linear case */
+	for (i = 0; i < fls(valid); i++)
+		if (valid & BIT(i)) {
+			if (!irq_start)
+				irq_create_mapping(f->domain, i);
+			f->used_irqs++;
+		}
+
+	pr_info("FPGA IRQ chip %d \"%s\" @ %p, %u irqs\n",
+		fpga_irq_id, name, base, f->used_irqs);
+
+	fpga_irq_id++;
+}
+
+#ifdef CONFIG_OF
+int __init fpga_irq_of_init(struct device_node *node,
+			    struct device_node *parent)
+{
+	struct fpga_irq_data *f;
+	void __iomem *base;
+	u32 clear_mask;
+	u32 valid_mask;
+
+	if (WARN_ON(!node))
+		return -ENODEV;
+
+	base = of_iomap(node, 0);
+	WARN(!base, "unable to map fpga irq registers\n");
+
+	if (of_property_read_u32(node, "clear-mask", &clear_mask))
+		clear_mask = 0;
+
+	if (of_property_read_u32(node, "valid-mask", &valid_mask))
+		valid_mask = 0;
+
+	fpga_irq_init(base, node->name, 0, -1, valid_mask, node);
+
+	writel(clear_mask, base + IRQ_ENABLE_CLEAR);
+	writel(clear_mask, base + FIQ_ENABLE_CLEAR);
+
+	return 0;
+}
+#endif
diff --git a/include/linux/irqchip/versatile-fpga.h b/include/linux/irqchip/versatile-fpga.h
new file mode 100644
index 000000000000..1fac9651d3ca
--- /dev/null
+++ b/include/linux/irqchip/versatile-fpga.h
@@ -0,0 +1,13 @@
+#ifndef PLAT_FPGA_IRQ_H
+#define PLAT_FPGA_IRQ_H
+
+struct device_node;
+struct pt_regs;
+
+void fpga_handle_irq(struct pt_regs *regs);
+void fpga_irq_init(void __iomem *, const char *, int, int, u32,
+		struct device_node *node);
+int fpga_irq_of_init(struct device_node *node,
+		     struct device_node *parent);
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 23064088d6aea049746755e9851760620921a80b Mon Sep 17 00:00:00 2001
From: Durgadoss R
Date: Tue, 18 Sep 2012 11:04:52 +0530
Subject: Thermal: Refactor thermal.h file

This patch rearranges the code in thermal.h file,
in the following order, so that it is easy to
read/maintain.
1. All #defines
2. All enums
3. All fops structures
4. All device structures
5. All function declarations

Signed-off-by: Durgadoss R <durgadoss.r@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 include/linux/thermal.h | 78 +++++++++++++++++++++++++++----------------------
 1 file changed, 43 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 91b34812cd84..8611e3eba60c 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -29,6 +29,23 @@
 #include <linux/device.h>
 #include <linux/workqueue.h>
 
+#define THERMAL_TRIPS_NONE	-1
+#define THERMAL_MAX_TRIPS	12
+#define THERMAL_NAME_LENGTH	20
+
+/* No upper/lower limit requirement */
+#define THERMAL_NO_LIMIT	-1UL
+
+/* Unit conversion macros */
+#define KELVIN_TO_CELSIUS(t)	(long)(((long)t-2732 >= 0) ?	\
+				((long)t-2732+5)/10 : ((long)t-2732-5)/10)
+#define CELSIUS_TO_KELVIN(t)	((t)*10+2732)
+
+/* Adding event notification support elements */
+#define THERMAL_GENL_FAMILY_NAME                "thermal_event"
+#define THERMAL_GENL_VERSION                    0x01
+#define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_group"
+
 struct thermal_zone_device;
 struct thermal_cooling_device;
 
@@ -50,6 +67,30 @@ enum thermal_trend {
 	THERMAL_TREND_DROPPING, /* temperature is dropping */
 };
 
+/* Events supported by Thermal Netlink */
+enum events {
+	THERMAL_AUX0,
+	THERMAL_AUX1,
+	THERMAL_CRITICAL,
+	THERMAL_DEV_FAULT,
+};
+
+/* attributes of thermal_genl_family */
+enum {
+	THERMAL_GENL_ATTR_UNSPEC,
+	THERMAL_GENL_ATTR_EVENT,
+	__THERMAL_GENL_ATTR_MAX,
+};
+#define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1)
+
+/* commands supported by the thermal_genl_family */
+enum {
+	THERMAL_GENL_CMD_UNSPEC,
+	THERMAL_GENL_CMD_EVENT,
+	__THERMAL_GENL_CMD_MAX,
+};
+#define THERMAL_GENL_CMD_MAX (__THERMAL_GENL_CMD_MAX - 1)
+
 struct thermal_zone_device_ops {
 	int (*bind) (struct thermal_zone_device *,
 		     struct thermal_cooling_device *);
@@ -83,11 +124,6 @@ struct thermal_cooling_device_ops {
 	int (*set_cur_state) (struct thermal_cooling_device *, unsigned long);
 };
 
-#define THERMAL_NO_LIMIT -1UL /* no upper/lower limit requirement */
-
-#define THERMAL_TRIPS_NONE -1
-#define THERMAL_MAX_TRIPS 12
-#define THERMAL_NAME_LENGTH 20
 struct thermal_cooling_device {
 	int id;
 	char type[THERMAL_NAME_LENGTH];
@@ -100,10 +136,6 @@ struct thermal_cooling_device {
 	struct list_head node;
 };
 
-#define KELVIN_TO_CELSIUS(t)	(long)(((long)t-2732 >= 0) ?	\
-				((long)t-2732+5)/10 : ((long)t-2732-5)/10)
-#define CELSIUS_TO_KELVIN(t)	((t)*10+2732)
-
 struct thermal_attr {
 	struct device_attribute attr;
 	char name[THERMAL_NAME_LENGTH];
@@ -131,38 +163,13 @@ struct thermal_zone_device {
 	struct list_head node;
 	struct delayed_work poll_queue;
 };
-/* Adding event notification support elements */
-#define THERMAL_GENL_FAMILY_NAME                "thermal_event"
-#define THERMAL_GENL_VERSION                    0x01
-#define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_group"
-
-enum events {
-	THERMAL_AUX0,
-	THERMAL_AUX1,
-	THERMAL_CRITICAL,
-	THERMAL_DEV_FAULT,
-};
 
 struct thermal_genl_event {
 	u32 orig;
 	enum events event;
 };
-/* attributes of thermal_genl_family */
-enum {
-	THERMAL_GENL_ATTR_UNSPEC,
-	THERMAL_GENL_ATTR_EVENT,
-	__THERMAL_GENL_ATTR_MAX,
-};
-#define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1)
-
-/* commands supported by the thermal_genl_family */
-enum {
-	THERMAL_GENL_CMD_UNSPEC,
-	THERMAL_GENL_CMD_EVENT,
-	__THERMAL_GENL_CMD_MAX,
-};
-#define THERMAL_GENL_CMD_MAX (__THERMAL_GENL_CMD_MAX - 1)
 
+/* Function declarations */
 struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
 		void *, const struct thermal_zone_device_ops *, int, int);
 void thermal_zone_device_unregister(struct thermal_zone_device *);
@@ -173,6 +180,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int,
 int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int,
 				       struct thermal_cooling_device *);
 void thermal_zone_device_update(struct thermal_zone_device *);
+
 struct thermal_cooling_device *thermal_cooling_device_register(char *, void *,
 		const struct thermal_cooling_device_ops *);
 void thermal_cooling_device_unregister(struct thermal_cooling_device *);
-- 
cgit v1.2.3-55-g7522


From 9b4298a088907811a4fe5a5d7cd2454da60708c5 Mon Sep 17 00:00:00 2001
From: Durgadoss R
Date: Tue, 18 Sep 2012 11:04:54 +0530
Subject: Thermal: Add get trend, get instance API's to thermal_sys

This patch adds the following API's to thermal_sys.c, that
can be used by other Thermal drivers.
 * get_tz_trend: obtain the trend of the given thermal zone
 * get_thermal_instance: obtain the instance corresponding
   to the given tz, cdev and the trip point.

Signed-off-by: Durgadoss R <durgadoss.r@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/thermal/thermal_sys.c | 40 ++++++++++++++++++++++++++++++++++++++++
 include/linux/thermal.h       |  4 ++++
 2 files changed, 44 insertions(+)

(limited to 'include')

diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index bbc834625f7f..1f98c560a88e 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -82,6 +82,46 @@ static void release_idr(struct idr *idr, struct mutex *lock, int id)
 		mutex_unlock(lock);
 }
 
+int get_tz_trend(struct thermal_zone_device *tz, int trip)
+{
+	enum thermal_trend trend;
+
+	if (!tz->ops->get_trend || tz->ops->get_trend(tz, trip, &trend)) {
+		if (tz->temperature > tz->last_temperature)
+			trend = THERMAL_TREND_RAISING;
+		else if (tz->temperature < tz->last_temperature)
+			trend = THERMAL_TREND_DROPPING;
+		else
+			trend = THERMAL_TREND_STABLE;
+	}
+
+	return trend;
+}
+EXPORT_SYMBOL(get_tz_trend);
+
+struct thermal_instance *get_thermal_instance(struct thermal_zone_device *tz,
+			struct thermal_cooling_device *cdev, int trip)
+{
+	struct thermal_instance *pos = NULL;
+	struct thermal_instance *target_instance = NULL;
+
+	mutex_lock(&tz->lock);
+	mutex_lock(&cdev->lock);
+
+	list_for_each_entry(pos, &tz->thermal_instances, tz_node) {
+		if (pos->tz == tz && pos->trip == trip && pos->cdev == cdev) {
+			target_instance = pos;
+			break;
+		}
+	}
+
+	mutex_unlock(&cdev->lock);
+	mutex_unlock(&tz->lock);
+
+	return target_instance;
+}
+EXPORT_SYMBOL(get_thermal_instance);
+
 /* sys I/F for thermal zone */
 
 #define to_thermal_zone(_dev) \
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 8611e3eba60c..32af124d23cd 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -185,6 +185,10 @@ struct thermal_cooling_device *thermal_cooling_device_register(char *, void *,
 		const struct thermal_cooling_device_ops *);
 void thermal_cooling_device_unregister(struct thermal_cooling_device *);
 
+int get_tz_trend(struct thermal_zone_device *, int);
+struct thermal_instance *get_thermal_instance(struct thermal_zone_device *,
+		struct thermal_cooling_device *, int);
+
 #ifdef CONFIG_NET
 extern int thermal_generate_netlink_event(u32 orig, enum events event);
 #else
-- 
cgit v1.2.3-55-g7522


From ef87394791206019e4e4e04cb746865f2dc115ed Mon Sep 17 00:00:00 2001
From: Durgadoss R
Date: Tue, 18 Sep 2012 11:04:55 +0530
Subject: Thermal: Add platform level information to thermal.h

This patch adds platform level information to thermal.h
by introducing two structures to hold:
 * bind parameters for a thermal zone,
 * zone level platform parameters

Signed-off-by: Durgadoss R <durgadoss.r@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 include/linux/thermal.h | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'include')

diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 32af124d23cd..4caa32e400b4 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -157,6 +157,7 @@ struct thermal_zone_device {
 	int passive;
 	unsigned int forced_passive;
 	const struct thermal_zone_device_ops *ops;
+	const struct thermal_zone_params *tzp;
 	struct list_head thermal_instances;
 	struct idr idr;
 	struct mutex lock; /* protect thermal_instances list */
@@ -164,6 +165,34 @@ struct thermal_zone_device {
 	struct delayed_work poll_queue;
 };
 
+/* Structure that holds binding parameters for a zone */
+struct thermal_bind_params {
+	struct thermal_cooling_device *cdev;
+
+	/*
+	 * This is a measure of 'how effectively these devices can
+	 * cool 'this' thermal zone. The shall be determined by platform
+	 * characterization. This is on a 'percentage' scale.
+	 * See Documentation/thermal/sysfs-api.txt for more information.
+	 */
+	int weight;
+
+	/*
+	 * This is a bit mask that gives the binding relation between this
+	 * thermal zone and cdev, for a particular trip point.
+	 * See Documentation/thermal/sysfs-api.txt for more information.
+	 */
+	int trip_mask;
+	int (*match) (struct thermal_zone_device *tz,
+			struct thermal_cooling_device *cdev);
+};
+
+/* Structure to define Thermal Zone parameters */
+struct thermal_zone_params {
+	int num_tbps;	/* Number of tbp entries */
+	struct thermal_bind_params *tbp;
+};
+
 struct thermal_genl_event {
 	u32 orig;
 	enum events event;
-- 
cgit v1.2.3-55-g7522


From 50125a9b27dd09e9afdc1b8712ba0b3859886c68 Mon Sep 17 00:00:00 2001
From: Durgadoss R
Date: Tue, 18 Sep 2012 11:04:56 +0530
Subject: Thermal: Pass zone parameters as argument to tzd_register

This patch adds the thermal zone parameter as an argument to
the tzd_register() function call; and updates other drivers
using this function.

Signed-off-by: Durgadoss R <durgadoss.r@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/acpi/thermal.c                             | 6 +++---
 drivers/platform/x86/acerhdf.c                     | 2 +-
 drivers/platform/x86/intel_mid_thermal.c           | 2 +-
 drivers/power/power_supply_core.c                  | 2 +-
 drivers/staging/omap-thermal/omap-thermal-common.c | 2 +-
 drivers/thermal/exynos_thermal.c                   | 2 +-
 drivers/thermal/rcar_thermal.c                     | 2 +-
 drivers/thermal/spear_thermal.c                    | 2 +-
 drivers/thermal/thermal_sys.c                      | 3 +++
 include/linux/thermal.h                            | 3 ++-
 10 files changed, 15 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 804204d41999..1794468223c4 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -900,14 +900,14 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz)
 	if (tz->trips.passive.flags.valid)
 		tz->thermal_zone =
 			thermal_zone_device_register("acpitz", trips, 0, tz,
-						     &acpi_thermal_zone_ops,
+						&acpi_thermal_zone_ops, NULL,
 						     tz->trips.passive.tsp*100,
 						     tz->polling_frequency*100);
 	else
 		tz->thermal_zone =
 			thermal_zone_device_register("acpitz", trips, 0, tz,
-						     &acpi_thermal_zone_ops, 0,
-						     tz->polling_frequency*100);
+						&acpi_thermal_zone_ops, NULL,
+						0, tz->polling_frequency*100);
 	if (IS_ERR(tz->thermal_zone))
 		return -ENODEV;
 
diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c
index 84c56881ba80..c2e3e63d2c15 100644
--- a/drivers/platform/x86/acerhdf.c
+++ b/drivers/platform/x86/acerhdf.c
@@ -662,7 +662,7 @@ static int acerhdf_register_thermal(void)
 		return -EINVAL;
 
 	thz_dev = thermal_zone_device_register("acerhdf", 1, 0, NULL,
-					      &acerhdf_dev_ops, 0,
+					      &acerhdf_dev_ops, NULL, 0,
 					      (kernelmode) ? interval*1000 : 0);
 	if (IS_ERR(thz_dev))
 		return -EINVAL;
diff --git a/drivers/platform/x86/intel_mid_thermal.c b/drivers/platform/x86/intel_mid_thermal.c
index c8097616dd62..93de09019d1d 100644
--- a/drivers/platform/x86/intel_mid_thermal.c
+++ b/drivers/platform/x86/intel_mid_thermal.c
@@ -502,7 +502,7 @@ static int mid_thermal_probe(struct platform_device *pdev)
 			goto err;
 		}
 		pinfo->tzd[i] = thermal_zone_device_register(name[i],
-				0, 0, td_info, &tzd_ops, 0, 0);
+				0, 0, td_info, &tzd_ops, NULL, 0, 0);
 		if (IS_ERR(pinfo->tzd[i])) {
 			kfree(td_info);
 			ret = PTR_ERR(pinfo->tzd[i]);
diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index 2436f1350013..f77a41272e5d 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -201,7 +201,7 @@ static int psy_register_thermal(struct power_supply *psy)
 	for (i = 0; i < psy->num_properties; i++) {
 		if (psy->properties[i] == POWER_SUPPLY_PROP_TEMP) {
 			psy->tzd = thermal_zone_device_register(psy->name, 0, 0,
-					psy, &psy_tzd_ops, 0, 0);
+					psy, &psy_tzd_ops, NULL, 0, 0);
 			if (IS_ERR(psy->tzd))
 				return PTR_ERR(psy->tzd);
 			break;
diff --git a/drivers/staging/omap-thermal/omap-thermal-common.c b/drivers/staging/omap-thermal/omap-thermal-common.c
index 5c0c203b887f..788f64f2f467 100644
--- a/drivers/staging/omap-thermal/omap-thermal-common.c
+++ b/drivers/staging/omap-thermal/omap-thermal-common.c
@@ -270,7 +270,7 @@ int omap_thermal_expose_sensor(struct omap_bandgap *bg_ptr, int id,
 	/* Create thermal zone */
 	data->omap_thermal = thermal_zone_device_register(domain,
 				OMAP_TRIP_NUMBER, 0, data, &omap_thermal_ops,
-				FAST_TEMP_MONITORING_RATE,
+				NULL, FAST_TEMP_MONITORING_RATE,
 				FAST_TEMP_MONITORING_RATE);
 	if (IS_ERR_OR_NULL(data->omap_thermal)) {
 		dev_err(bg_ptr->dev, "thermal zone device is NULL\n");
diff --git a/drivers/thermal/exynos_thermal.c b/drivers/thermal/exynos_thermal.c
index 6dd29e4ce36b..7772d1603769 100644
--- a/drivers/thermal/exynos_thermal.c
+++ b/drivers/thermal/exynos_thermal.c
@@ -451,7 +451,7 @@ static int exynos_register_thermal(struct thermal_sensor_conf *sensor_conf)
 	th_zone->cool_dev_size++;
 
 	th_zone->therm_dev = thermal_zone_device_register(sensor_conf->name,
-			EXYNOS_ZONE_COUNT, 0, NULL, &exynos_dev_ops, 0,
+			EXYNOS_ZONE_COUNT, 0, NULL, &exynos_dev_ops, NULL, 0,
 			IDLE_INTERVAL);
 
 	if (IS_ERR(th_zone->therm_dev)) {
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index f7a1b574a304..762f6373d50c 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -211,7 +211,7 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 	}
 
 	zone = thermal_zone_device_register("rcar_thermal", 0, 0, priv,
-					    &rcar_thermal_zone_ops, 0, 0);
+				    &rcar_thermal_zone_ops, NULL, 0, 0);
 	if (IS_ERR(zone)) {
 		dev_err(&pdev->dev, "thermal zone device is NULL\n");
 		ret = PTR_ERR(zone);
diff --git a/drivers/thermal/spear_thermal.c b/drivers/thermal/spear_thermal.c
index 9bc969261d01..6b2d8b21aaee 100644
--- a/drivers/thermal/spear_thermal.c
+++ b/drivers/thermal/spear_thermal.c
@@ -147,7 +147,7 @@ static int spear_thermal_probe(struct platform_device *pdev)
 	writel_relaxed(stdev->flags, stdev->thermal_base);
 
 	spear_thermal = thermal_zone_device_register("spear_thermal", 0, 0,
-				stdev, &ops, 0, 0);
+				stdev, &ops, NULL, 0, 0);
 	if (IS_ERR(spear_thermal)) {
 		dev_err(&pdev->dev, "thermal zone device is NULL\n");
 		ret = PTR_ERR(spear_thermal);
diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index 1f98c560a88e..dca3bfc0e702 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -1341,6 +1341,7 @@ static void remove_trip_attrs(struct thermal_zone_device *tz)
  * @mask:	a bit string indicating the writeablility of trip points
  * @devdata:	private device data
  * @ops:	standard thermal zone device callbacks
+ * @tzp:	thermal zone platform parameters
  * @passive_delay: number of milliseconds to wait between polls when
  *		   performing passive cooling
  * @polling_delay: number of milliseconds to wait between polls when checking
@@ -1353,6 +1354,7 @@ static void remove_trip_attrs(struct thermal_zone_device *tz)
 struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	int trips, int mask, void *devdata,
 	const struct thermal_zone_device_ops *ops,
+	const struct thermal_zone_params *tzp,
 	int passive_delay, int polling_delay)
 {
 	struct thermal_zone_device *tz;
@@ -1386,6 +1388,7 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 
 	strcpy(tz->type, type ? : "");
 	tz->ops = ops;
+	tz->tzp = tzp;
 	tz->device.class = &thermal_class;
 	tz->devdata = devdata;
 	tz->trips = trips;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 4caa32e400b4..58cb1c036a0e 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -200,7 +200,8 @@ struct thermal_genl_event {
 
 /* Function declarations */
 struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
-		void *, const struct thermal_zone_device_ops *, int, int);
+		void *, const struct thermal_zone_device_ops *,
+		const struct thermal_zone_params *, int, int);
 void thermal_zone_device_unregister(struct thermal_zone_device *);
 
 int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int,
-- 
cgit v1.2.3-55-g7522


From a4a15485fbba44d162d626141b9a7404e790f570 Mon Sep 17 00:00:00 2001
From: Durgadoss R
Date: Tue, 18 Sep 2012 11:04:57 +0530
Subject: Thermal: Add thermal governor registration APIs

This patch creates a structure to hold platform
thermal governor information, and provides APIs
for individual thermal governors to register/unregister
with the Thermal framework.

Signed-off-by: Durgadoss R <durgadoss.r@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/thermal/thermal_sys.c | 90 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/thermal.h       | 16 ++++++++
 2 files changed, 106 insertions(+)

(limited to 'include')

diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index dca3bfc0e702..0afd84cb127d 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -49,7 +49,86 @@ static DEFINE_MUTEX(thermal_idr_lock);
 
 static LIST_HEAD(thermal_tz_list);
 static LIST_HEAD(thermal_cdev_list);
+static LIST_HEAD(thermal_governor_list);
+
 static DEFINE_MUTEX(thermal_list_lock);
+static DEFINE_MUTEX(thermal_governor_lock);
+
+static struct thermal_governor *__find_governor(const char *name)
+{
+	struct thermal_governor *pos;
+
+	list_for_each_entry(pos, &thermal_governor_list, governor_list)
+		if (!strnicmp(name, pos->name, THERMAL_NAME_LENGTH))
+			return pos;
+
+	return NULL;
+}
+
+int thermal_register_governor(struct thermal_governor *governor)
+{
+	int err;
+	const char *name;
+	struct thermal_zone_device *pos;
+
+	if (!governor)
+		return -EINVAL;
+
+	mutex_lock(&thermal_governor_lock);
+
+	err = -EBUSY;
+	if (__find_governor(governor->name) == NULL) {
+		err = 0;
+		list_add(&governor->governor_list, &thermal_governor_list);
+	}
+
+	mutex_lock(&thermal_list_lock);
+
+	list_for_each_entry(pos, &thermal_tz_list, node) {
+		if (pos->governor)
+			continue;
+		if (pos->tzp)
+			name = pos->tzp->governor_name;
+		else
+			name = DEFAULT_THERMAL_GOVERNOR;
+		if (!strnicmp(name, governor->name, THERMAL_NAME_LENGTH))
+			pos->governor = governor;
+	}
+
+	mutex_unlock(&thermal_list_lock);
+	mutex_unlock(&thermal_governor_lock);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(thermal_register_governor);
+
+void thermal_unregister_governor(struct thermal_governor *governor)
+{
+	struct thermal_zone_device *pos;
+
+	if (!governor)
+		return;
+
+	mutex_lock(&thermal_governor_lock);
+
+	if (__find_governor(governor->name) == NULL)
+		goto exit;
+
+	mutex_lock(&thermal_list_lock);
+
+	list_for_each_entry(pos, &thermal_tz_list, node) {
+		if (!strnicmp(pos->governor->name, governor->name,
+						THERMAL_NAME_LENGTH))
+			pos->governor = NULL;
+	}
+
+	mutex_unlock(&thermal_list_lock);
+	list_del(&governor->governor_list);
+exit:
+	mutex_unlock(&thermal_governor_lock);
+	return;
+}
+EXPORT_SYMBOL_GPL(thermal_unregister_governor);
 
 static int get_idr(struct idr *idr, struct mutex *lock, int *id)
 {
@@ -1437,6 +1516,16 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	if (result)
 		goto unregister;
 
+	/* Update 'this' zone's governor information */
+	mutex_lock(&thermal_governor_lock);
+
+	if (tz->tzp)
+		tz->governor = __find_governor(tz->tzp->governor_name);
+	else
+		tz->governor = __find_governor(DEFAULT_THERMAL_GOVERNOR);
+
+	mutex_unlock(&thermal_governor_lock);
+
 	result = thermal_add_hwmon_sysfs(tz);
 	if (result)
 		goto unregister;
@@ -1500,6 +1589,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 	if (tz->ops->get_mode)
 		device_remove_file(&tz->device, &dev_attr_mode);
 	remove_trip_attrs(tz);
+	tz->governor = NULL;
 
 	thermal_remove_hwmon_sysfs(tz);
 	release_idr(&thermal_tz_idr, &thermal_idr_lock, tz->id);
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 58cb1c036a0e..6182bd5f7504 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -46,6 +46,9 @@
 #define THERMAL_GENL_VERSION                    0x01
 #define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_group"
 
+/* Default Thermal Governor: Does Linear Throttling */
+#define DEFAULT_THERMAL_GOVERNOR	"step_wise"
+
 struct thermal_zone_device;
 struct thermal_cooling_device;
 
@@ -158,6 +161,7 @@ struct thermal_zone_device {
 	unsigned int forced_passive;
 	const struct thermal_zone_device_ops *ops;
 	const struct thermal_zone_params *tzp;
+	struct thermal_governor *governor;
 	struct list_head thermal_instances;
 	struct idr idr;
 	struct mutex lock; /* protect thermal_instances list */
@@ -165,6 +169,14 @@ struct thermal_zone_device {
 	struct delayed_work poll_queue;
 };
 
+/* Structure that holds thermal governor information */
+struct thermal_governor {
+	char name[THERMAL_NAME_LENGTH];
+	int (*throttle)(struct thermal_zone_device *tz, int trip);
+	struct list_head	governor_list;
+	struct module		*owner;
+};
+
 /* Structure that holds binding parameters for a zone */
 struct thermal_bind_params {
 	struct thermal_cooling_device *cdev;
@@ -189,6 +201,7 @@ struct thermal_bind_params {
 
 /* Structure to define Thermal Zone parameters */
 struct thermal_zone_params {
+	char governor_name[THERMAL_NAME_LENGTH];
 	int num_tbps;	/* Number of tbp entries */
 	struct thermal_bind_params *tbp;
 };
@@ -219,6 +232,9 @@ int get_tz_trend(struct thermal_zone_device *, int);
 struct thermal_instance *get_thermal_instance(struct thermal_zone_device *,
 		struct thermal_cooling_device *, int);
 
+int thermal_register_governor(struct thermal_governor *);
+void thermal_unregister_governor(struct thermal_governor *);
+
 #ifdef CONFIG_NET
 extern int thermal_generate_netlink_event(u32 orig, enum events event);
 #else
-- 
cgit v1.2.3-55-g7522


From dc76548269ca2c44e5ddc29db5c36188bc4f2234 Mon Sep 17 00:00:00 2001
From: Durgadoss R
Date: Tue, 18 Sep 2012 11:05:00 +0530
Subject: Thermal: Make thermal_cdev_update as a global function

This patch makes the thermal_cdev_update function as a
global one, so that other files can use it. This function
serves as a single arbitrator to set the state of a cooling
device.

Signed-off-by: Durgadoss R <durgadoss.r@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/thermal/thermal_sys.c | 5 +++--
 include/linux/thermal.h       | 1 +
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index a32803224e3c..9d21f82986ee 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -1257,7 +1257,7 @@ void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
 }
 EXPORT_SYMBOL(thermal_cooling_device_unregister);
 
-static void thermal_cdev_do_update(struct thermal_cooling_device *cdev)
+void thermal_cdev_update(struct thermal_cooling_device *cdev)
 {
 	struct thermal_instance *instance;
 	unsigned long target = 0;
@@ -1278,13 +1278,14 @@ static void thermal_cdev_do_update(struct thermal_cooling_device *cdev)
 	cdev->ops->set_cur_state(cdev, target);
 	cdev->updated = true;
 }
+EXPORT_SYMBOL(thermal_cdev_update);
 
 static void thermal_zone_do_update(struct thermal_zone_device *tz)
 {
 	struct thermal_instance *instance;
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node)
-		thermal_cdev_do_update(instance->cdev);
+		thermal_cdev_update(instance->cdev);
 }
 
 /*
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 6182bd5f7504..2bd915841818 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -231,6 +231,7 @@ void thermal_cooling_device_unregister(struct thermal_cooling_device *);
 int get_tz_trend(struct thermal_zone_device *, int);
 struct thermal_instance *get_thermal_instance(struct thermal_zone_device *,
 		struct thermal_cooling_device *, int);
+void thermal_cdev_update(struct thermal_cooling_device *);
 
 int thermal_register_governor(struct thermal_governor *);
 void thermal_unregister_governor(struct thermal_governor *);
-- 
cgit v1.2.3-55-g7522


From f2b4caafd4aa64c9438b0a94af78b127228e6905 Mon Sep 17 00:00:00 2001
From: Durgadoss R
Date: Tue, 18 Sep 2012 11:05:05 +0530
Subject: Thermal: Add a notification API

This patch adds a notification API which the sensor drivers'
can use to notify the framework. The framework then takes
care of the throttling according to the configured policy.

Signed-off-by: Durgadoss R <durgadoss.r@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/thermal/thermal_sys.c | 18 ++++++++++++++++++
 include/linux/thermal.h       |  1 +
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index 64f3e9735316..a69f24c4414a 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -1368,6 +1368,24 @@ void thermal_cdev_update(struct thermal_cooling_device *cdev)
 }
 EXPORT_SYMBOL(thermal_cdev_update);
 
+/**
+ * notify_thermal_framework - Sensor drivers use this API to notify framework
+ * @tz:		thermal zone device
+ * @trip:	indicates which trip point has been crossed
+ *
+ * This function handles the trip events from sensor drivers. It starts
+ * throttling the cooling devices according to the policy configured.
+ * For CRITICAL and HOT trip points, this notifies the respective drivers,
+ * and does actual throttling for other trip points i.e ACTIVE and PASSIVE.
+ * The throttling policy is based on the configured platform data; if no
+ * platform data is provided, this uses the step_wise throttling policy.
+ */
+void notify_thermal_framework(struct thermal_zone_device *tz, int trip)
+{
+	handle_thermal_trip(tz, trip);
+}
+EXPORT_SYMBOL(notify_thermal_framework);
+
 /**
  * create_trip_attrs - create attributes for trip points
  * @tz:		the thermal zone device
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 2bd915841818..807f2146fe35 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -232,6 +232,7 @@ int get_tz_trend(struct thermal_zone_device *, int);
 struct thermal_instance *get_thermal_instance(struct thermal_zone_device *,
 		struct thermal_cooling_device *, int);
 void thermal_cdev_update(struct thermal_cooling_device *);
+void notify_thermal_framework(struct thermal_zone_device *, int);
 
 int thermal_register_governor(struct thermal_governor *);
 void thermal_unregister_governor(struct thermal_governor *);
-- 
cgit v1.2.3-55-g7522


From 7cb15e10365203bffc5cc75c79725b6c31aa663e Mon Sep 17 00:00:00 2001
From: Linus Walleij
Date: Wed, 10 Oct 2012 14:27:58 +0200
Subject: pinctrl/nomadik: move the platform data header

This moves the platform data header for the Nomadik pin controller
to <linux/platform_data/pinctrl-nomadik.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/arm/mach-nomadik/board-nhk8815.c             |   2 +-
 arch/arm/mach-nomadik/cpu-8815.c                  |   2 +-
 arch/arm/mach-nomadik/i2c-8815nhk.c               |   2 +-
 arch/arm/mach-ux500/board-mop500-audio.c          |   2 +-
 arch/arm/mach-ux500/board-mop500-pins.c           |   2 +-
 arch/arm/mach-ux500/board-mop500.c                |   2 +-
 arch/arm/mach-ux500/cpu-db8500.c                  |   4 +-
 arch/arm/mach-ux500/devices-common.c              |   3 +-
 arch/arm/plat-nomadik/include/plat/gpio-nomadik.h | 108 ----------------------
 drivers/pinctrl/pinctrl-nomadik.c                 |   2 +-
 drivers/pinctrl/pinctrl-nomadik.h                 |   2 +-
 include/linux/platform_data/pinctrl-nomadik.h     | 108 ++++++++++++++++++++++
 12 files changed, 119 insertions(+), 120 deletions(-)
 delete mode 100644 arch/arm/plat-nomadik/include/plat/gpio-nomadik.h
 create mode 100644 include/linux/platform_data/pinctrl-nomadik.h

(limited to 'include')

diff --git a/arch/arm/mach-nomadik/board-nhk8815.c b/arch/arm/mach-nomadik/board-nhk8815.c
index bfa1eab91f41..3a41ad00bd68 100644
--- a/arch/arm/mach-nomadik/board-nhk8815.c
+++ b/arch/arm/mach-nomadik/board-nhk8815.c
@@ -24,6 +24,7 @@
 #include <linux/i2c.h>
 #include <linux/io.h>
 #include <linux/pinctrl/machine.h>
+#include <linux/platform_data/pinctrl-nomadik.h>
 #include <asm/hardware/vic.h>
 #include <asm/sizes.h>
 #include <asm/mach-types.h>
@@ -32,7 +33,6 @@
 #include <asm/mach/flash.h>
 #include <asm/mach/time.h>
 
-#include <plat/gpio-nomadik.h>
 #include <plat/mtu.h>
 #include <plat/pincfg.h>
 
diff --git a/arch/arm/mach-nomadik/cpu-8815.c b/arch/arm/mach-nomadik/cpu-8815.c
index b617eaed0ce5..1273931303fb 100644
--- a/arch/arm/mach-nomadik/cpu-8815.c
+++ b/arch/arm/mach-nomadik/cpu-8815.c
@@ -26,8 +26,8 @@
 #include <linux/irq.h>
 #include <linux/dma-mapping.h>
 #include <linux/platform_data/clk-nomadik.h>
+#include <linux/platform_data/pinctrl-nomadik.h>
 
-#include <plat/gpio-nomadik.h>
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-nomadik/i2c-8815nhk.c b/arch/arm/mach-nomadik/i2c-8815nhk.c
index 6d14454d4609..f81496f5790e 100644
--- a/arch/arm/mach-nomadik/i2c-8815nhk.c
+++ b/arch/arm/mach-nomadik/i2c-8815nhk.c
@@ -4,7 +4,7 @@
 #include <linux/i2c-algo-bit.h>
 #include <linux/i2c-gpio.h>
 #include <linux/platform_device.h>
-#include <plat/gpio-nomadik.h>
+#include <linux/platform_data/pinctrl-nomadik.h>
 #include <plat/pincfg.h>
 
 /*
diff --git a/arch/arm/mach-ux500/board-mop500-audio.c b/arch/arm/mach-ux500/board-mop500-audio.c
index 070629a95625..ea828cc56357 100644
--- a/arch/arm/mach-ux500/board-mop500-audio.c
+++ b/arch/arm/mach-ux500/board-mop500-audio.c
@@ -7,8 +7,8 @@
 #include <linux/platform_device.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
+#include <linux/platform_data/pinctrl-nomadik.h>
 
-#include <plat/gpio-nomadik.h>
 #include <plat/pincfg.h>
 #include <plat/ste_dma40.h>
 
diff --git a/arch/arm/mach-ux500/board-mop500-pins.c b/arch/arm/mach-ux500/board-mop500-pins.c
index a267c6d30e37..05f2bb581130 100644
--- a/arch/arm/mach-ux500/board-mop500-pins.c
+++ b/arch/arm/mach-ux500/board-mop500-pins.c
@@ -9,10 +9,10 @@
 #include <linux/bug.h>
 #include <linux/string.h>
 #include <linux/pinctrl/machine.h>
+#include <linux/platform_data/pinctrl-nomadik.h>
 
 #include <asm/mach-types.h>
 #include <plat/pincfg.h>
-#include <plat/gpio-nomadik.h>
 
 #include <mach/hardware.h>
 
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index 416d436111f2..0a3dd601a400 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -37,13 +37,13 @@
 #include <linux/of_platform.h>
 #include <linux/leds.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/platform_data/pinctrl-nomadik.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/hardware/gic.h>
 
 #include <plat/ste_dma40.h>
-#include <plat/gpio-nomadik.h>
 
 #include <mach/hardware.h>
 #include <mach/setup.h>
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index bcdfe6b1d453..87a8f9fbb100 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -17,14 +17,14 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/mfd/abx500/ab8500.h>
+#include <linux/platform_data/usb-musb-ux500.h>
+#include <linux/platform_data/pinctrl-nomadik.h>
 
 #include <asm/pmu.h>
 #include <asm/mach/map.h>
-#include <plat/gpio-nomadik.h>
 #include <mach/hardware.h>
 #include <mach/setup.h>
 #include <mach/devices.h>
-#include <linux/platform_data/usb-musb-ux500.h>
 #include <mach/db8500-regs.h>
 
 #include "devices-db8500.h"
diff --git a/arch/arm/mach-ux500/devices-common.c b/arch/arm/mach-ux500/devices-common.c
index dfdd4a54668d..692a77a1c153 100644
--- a/arch/arm/mach-ux500/devices-common.c
+++ b/arch/arm/mach-ux500/devices-common.c
@@ -11,8 +11,7 @@
 #include <linux/irq.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
-
-#include <plat/gpio-nomadik.h>
+#include <linux/platform_data/pinctrl-nomadik.h>
 
 #include <mach/hardware.h>
 
diff --git a/arch/arm/plat-nomadik/include/plat/gpio-nomadik.h b/arch/arm/plat-nomadik/include/plat/gpio-nomadik.h
deleted file mode 100644
index a74999438de4..000000000000
--- a/arch/arm/plat-nomadik/include/plat/gpio-nomadik.h
+++ /dev/null
@@ -1,108 +0,0 @@
-/*
- * Structures and registers for GPIO access in the Nomadik SoC
- *
- * Copyright (C) 2008 STMicroelectronics
- *     Author: Prafulla WADASKAR <prafulla.wadaskar@st.com>
- * Copyright (C) 2009 Alessandro Rubini <rubini@unipv.it>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __PLAT_NOMADIK_GPIO
-#define __PLAT_NOMADIK_GPIO
-
-/*
- * "nmk_gpio" and "NMK_GPIO" stand for "Nomadik GPIO", leaving
- * the "gpio" namespace for generic and cross-machine functions
- */
-
-#define GPIO_BLOCK_SHIFT 5
-#define NMK_GPIO_PER_CHIP (1 << GPIO_BLOCK_SHIFT)
-
-/* Register in the logic block */
-#define NMK_GPIO_DAT	0x00
-#define NMK_GPIO_DATS	0x04
-#define NMK_GPIO_DATC	0x08
-#define NMK_GPIO_PDIS	0x0c
-#define NMK_GPIO_DIR	0x10
-#define NMK_GPIO_DIRS	0x14
-#define NMK_GPIO_DIRC	0x18
-#define NMK_GPIO_SLPC	0x1c
-#define NMK_GPIO_AFSLA	0x20
-#define NMK_GPIO_AFSLB	0x24
-#define NMK_GPIO_LOWEMI	0x28
-
-#define NMK_GPIO_RIMSC	0x40
-#define NMK_GPIO_FIMSC	0x44
-#define NMK_GPIO_IS	0x48
-#define NMK_GPIO_IC	0x4c
-#define NMK_GPIO_RWIMSC	0x50
-#define NMK_GPIO_FWIMSC	0x54
-#define NMK_GPIO_WKS	0x58
-/* These appear in DB8540 and later ASICs */
-#define NMK_GPIO_EDGELEVEL 0x5C
-#define NMK_GPIO_LEVEL	0x60
-
-/* Alternate functions: function C is set in hw by setting both A and B */
-#define NMK_GPIO_ALT_GPIO	0
-#define NMK_GPIO_ALT_A	1
-#define NMK_GPIO_ALT_B	2
-#define NMK_GPIO_ALT_C	(NMK_GPIO_ALT_A | NMK_GPIO_ALT_B)
-
-#define NMK_GPIO_ALT_CX_SHIFT 2
-#define NMK_GPIO_ALT_C1	((1<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
-#define NMK_GPIO_ALT_C2	((2<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
-#define NMK_GPIO_ALT_C3	((3<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
-#define NMK_GPIO_ALT_C4	((4<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
-
-/* Pull up/down values */
-enum nmk_gpio_pull {
-	NMK_GPIO_PULL_NONE,
-	NMK_GPIO_PULL_UP,
-	NMK_GPIO_PULL_DOWN,
-};
-
-/* Sleep mode */
-enum nmk_gpio_slpm {
-	NMK_GPIO_SLPM_INPUT,
-	NMK_GPIO_SLPM_WAKEUP_ENABLE = NMK_GPIO_SLPM_INPUT,
-	NMK_GPIO_SLPM_NOCHANGE,
-	NMK_GPIO_SLPM_WAKEUP_DISABLE = NMK_GPIO_SLPM_NOCHANGE,
-};
-
-extern int nmk_gpio_set_slpm(int gpio, enum nmk_gpio_slpm mode);
-extern int nmk_gpio_set_pull(int gpio, enum nmk_gpio_pull pull);
-#ifdef CONFIG_PINCTRL_NOMADIK
-extern int nmk_gpio_set_mode(int gpio, int gpio_mode);
-#else
-static inline int nmk_gpio_set_mode(int gpio, int gpio_mode)
-{
-	return -ENODEV;
-}
-#endif
-extern int nmk_gpio_get_mode(int gpio);
-
-extern void nmk_gpio_wakeups_suspend(void);
-extern void nmk_gpio_wakeups_resume(void);
-
-extern void nmk_gpio_clocks_enable(void);
-extern void nmk_gpio_clocks_disable(void);
-
-extern void nmk_gpio_read_pull(int gpio_bank, u32 *pull_up);
-
-/*
- * Platform data to register a block: only the initial gpio/irq number.
- */
-struct nmk_gpio_platform_data {
-	char *name;
-	int first_gpio;
-	int first_irq;
-	int num_gpio;
-	u32 (*get_secondary_status)(unsigned int bank);
-	void (*set_ioforce)(bool enable);
-	bool supports_sleepmode;
-};
-
-#endif /* __PLAT_NOMADIK_GPIO */
diff --git a/drivers/pinctrl/pinctrl-nomadik.c b/drivers/pinctrl/pinctrl-nomadik.c
index f5c0da1f3b30..e24fa05e59b8 100644
--- a/drivers/pinctrl/pinctrl-nomadik.c
+++ b/drivers/pinctrl/pinctrl-nomadik.c
@@ -44,11 +44,11 @@ static inline u32 prcmu_read(unsigned int reg) {
 static inline void prcmu_write(unsigned int reg, u32 value) {}
 static inline void prcmu_write_masked(unsigned int reg, u32 mask, u32 value) {}
 #endif
+#include <linux/platform_data/pinctrl-nomadik.h>
 
 #include <asm/mach/irq.h>
 
 #include <plat/pincfg.h>
-#include <plat/gpio-nomadik.h>
 
 #include "pinctrl-nomadik.h"
 
diff --git a/drivers/pinctrl/pinctrl-nomadik.h b/drivers/pinctrl/pinctrl-nomadik.h
index eef316e979a0..bcd4191e10ea 100644
--- a/drivers/pinctrl/pinctrl-nomadik.h
+++ b/drivers/pinctrl/pinctrl-nomadik.h
@@ -1,7 +1,7 @@
 #ifndef PINCTRL_PINCTRL_NOMADIK_H
 #define PINCTRL_PINCTRL_NOMADIK_H
 
-#include <plat/gpio-nomadik.h>
+#include <linux/platform_data/pinctrl-nomadik.h>
 
 /* Package definitions */
 #define PINCTRL_NMK_STN8815	0
diff --git a/include/linux/platform_data/pinctrl-nomadik.h b/include/linux/platform_data/pinctrl-nomadik.h
new file mode 100644
index 000000000000..a74999438de4
--- /dev/null
+++ b/include/linux/platform_data/pinctrl-nomadik.h
@@ -0,0 +1,108 @@
+/*
+ * Structures and registers for GPIO access in the Nomadik SoC
+ *
+ * Copyright (C) 2008 STMicroelectronics
+ *     Author: Prafulla WADASKAR <prafulla.wadaskar@st.com>
+ * Copyright (C) 2009 Alessandro Rubini <rubini@unipv.it>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __PLAT_NOMADIK_GPIO
+#define __PLAT_NOMADIK_GPIO
+
+/*
+ * "nmk_gpio" and "NMK_GPIO" stand for "Nomadik GPIO", leaving
+ * the "gpio" namespace for generic and cross-machine functions
+ */
+
+#define GPIO_BLOCK_SHIFT 5
+#define NMK_GPIO_PER_CHIP (1 << GPIO_BLOCK_SHIFT)
+
+/* Register in the logic block */
+#define NMK_GPIO_DAT	0x00
+#define NMK_GPIO_DATS	0x04
+#define NMK_GPIO_DATC	0x08
+#define NMK_GPIO_PDIS	0x0c
+#define NMK_GPIO_DIR	0x10
+#define NMK_GPIO_DIRS	0x14
+#define NMK_GPIO_DIRC	0x18
+#define NMK_GPIO_SLPC	0x1c
+#define NMK_GPIO_AFSLA	0x20
+#define NMK_GPIO_AFSLB	0x24
+#define NMK_GPIO_LOWEMI	0x28
+
+#define NMK_GPIO_RIMSC	0x40
+#define NMK_GPIO_FIMSC	0x44
+#define NMK_GPIO_IS	0x48
+#define NMK_GPIO_IC	0x4c
+#define NMK_GPIO_RWIMSC	0x50
+#define NMK_GPIO_FWIMSC	0x54
+#define NMK_GPIO_WKS	0x58
+/* These appear in DB8540 and later ASICs */
+#define NMK_GPIO_EDGELEVEL 0x5C
+#define NMK_GPIO_LEVEL	0x60
+
+/* Alternate functions: function C is set in hw by setting both A and B */
+#define NMK_GPIO_ALT_GPIO	0
+#define NMK_GPIO_ALT_A	1
+#define NMK_GPIO_ALT_B	2
+#define NMK_GPIO_ALT_C	(NMK_GPIO_ALT_A | NMK_GPIO_ALT_B)
+
+#define NMK_GPIO_ALT_CX_SHIFT 2
+#define NMK_GPIO_ALT_C1	((1<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
+#define NMK_GPIO_ALT_C2	((2<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
+#define NMK_GPIO_ALT_C3	((3<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
+#define NMK_GPIO_ALT_C4	((4<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
+
+/* Pull up/down values */
+enum nmk_gpio_pull {
+	NMK_GPIO_PULL_NONE,
+	NMK_GPIO_PULL_UP,
+	NMK_GPIO_PULL_DOWN,
+};
+
+/* Sleep mode */
+enum nmk_gpio_slpm {
+	NMK_GPIO_SLPM_INPUT,
+	NMK_GPIO_SLPM_WAKEUP_ENABLE = NMK_GPIO_SLPM_INPUT,
+	NMK_GPIO_SLPM_NOCHANGE,
+	NMK_GPIO_SLPM_WAKEUP_DISABLE = NMK_GPIO_SLPM_NOCHANGE,
+};
+
+extern int nmk_gpio_set_slpm(int gpio, enum nmk_gpio_slpm mode);
+extern int nmk_gpio_set_pull(int gpio, enum nmk_gpio_pull pull);
+#ifdef CONFIG_PINCTRL_NOMADIK
+extern int nmk_gpio_set_mode(int gpio, int gpio_mode);
+#else
+static inline int nmk_gpio_set_mode(int gpio, int gpio_mode)
+{
+	return -ENODEV;
+}
+#endif
+extern int nmk_gpio_get_mode(int gpio);
+
+extern void nmk_gpio_wakeups_suspend(void);
+extern void nmk_gpio_wakeups_resume(void);
+
+extern void nmk_gpio_clocks_enable(void);
+extern void nmk_gpio_clocks_disable(void);
+
+extern void nmk_gpio_read_pull(int gpio_bank, u32 *pull_up);
+
+/*
+ * Platform data to register a block: only the initial gpio/irq number.
+ */
+struct nmk_gpio_platform_data {
+	char *name;
+	int first_gpio;
+	int first_irq;
+	int num_gpio;
+	u32 (*get_secondary_status)(unsigned int bank);
+	void (*set_ioforce)(bool enable);
+	bool supports_sleepmode;
+};
+
+#endif /* __PLAT_NOMADIK_GPIO */
-- 
cgit v1.2.3-55-g7522


From c3123cfdc9e3241055f1ba0d6ceb8b41f97e31b9 Mon Sep 17 00:00:00 2001
From: Linus Walleij
Date: Wed, 10 Oct 2012 14:35:17 +0200
Subject: pinctrl/nomadik: merge old pincfg header

This merges the old <plat/pincfg.h> header into
<linux/platform_data/pinctrl-nomadik.h> and rids us of
yet one more <plat/*> include.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/arm/mach-nomadik/board-nhk8815.c         |   1 -
 arch/arm/mach-nomadik/i2c-8815nhk.c           |   1 -
 arch/arm/mach-ux500/board-mop500-audio.c      |   1 -
 arch/arm/mach-ux500/board-mop500-pins.c       |   1 -
 arch/arm/plat-nomadik/include/plat/pincfg.h   | 173 --------------------------
 drivers/pinctrl/pinctrl-nomadik.c             |   4 +-
 include/linux/platform_data/pinctrl-nomadik.h | 158 +++++++++++++++++++++++
 7 files changed, 159 insertions(+), 180 deletions(-)
 delete mode 100644 arch/arm/plat-nomadik/include/plat/pincfg.h

(limited to 'include')

diff --git a/arch/arm/mach-nomadik/board-nhk8815.c b/arch/arm/mach-nomadik/board-nhk8815.c
index 3a41ad00bd68..22ef8a1abe08 100644
--- a/arch/arm/mach-nomadik/board-nhk8815.c
+++ b/arch/arm/mach-nomadik/board-nhk8815.c
@@ -34,7 +34,6 @@
 #include <asm/mach/time.h>
 
 #include <plat/mtu.h>
-#include <plat/pincfg.h>
 
 #include <linux/platform_data/mtd-nomadik-nand.h>
 #include <mach/fsmc.h>
diff --git a/arch/arm/mach-nomadik/i2c-8815nhk.c b/arch/arm/mach-nomadik/i2c-8815nhk.c
index f81496f5790e..0c2f6628299a 100644
--- a/arch/arm/mach-nomadik/i2c-8815nhk.c
+++ b/arch/arm/mach-nomadik/i2c-8815nhk.c
@@ -5,7 +5,6 @@
 #include <linux/i2c-gpio.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/pinctrl-nomadik.h>
-#include <plat/pincfg.h>
 
 /*
  * There are two busses in the 8815NHK.
diff --git a/arch/arm/mach-ux500/board-mop500-audio.c b/arch/arm/mach-ux500/board-mop500-audio.c
index ea828cc56357..33631c9f1218 100644
--- a/arch/arm/mach-ux500/board-mop500-audio.c
+++ b/arch/arm/mach-ux500/board-mop500-audio.c
@@ -9,7 +9,6 @@
 #include <linux/gpio.h>
 #include <linux/platform_data/pinctrl-nomadik.h>
 
-#include <plat/pincfg.h>
 #include <plat/ste_dma40.h>
 
 #include <mach/devices.h>
diff --git a/arch/arm/mach-ux500/board-mop500-pins.c b/arch/arm/mach-ux500/board-mop500-pins.c
index 05f2bb581130..c34d4efd0d5c 100644
--- a/arch/arm/mach-ux500/board-mop500-pins.c
+++ b/arch/arm/mach-ux500/board-mop500-pins.c
@@ -12,7 +12,6 @@
 #include <linux/platform_data/pinctrl-nomadik.h>
 
 #include <asm/mach-types.h>
-#include <plat/pincfg.h>
 
 #include <mach/hardware.h>
 
diff --git a/arch/arm/plat-nomadik/include/plat/pincfg.h b/arch/arm/plat-nomadik/include/plat/pincfg.h
deleted file mode 100644
index 3b8ec60af351..000000000000
--- a/arch/arm/plat-nomadik/include/plat/pincfg.h
+++ /dev/null
@@ -1,173 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2010
- *
- * License terms: GNU General Public License, version 2
- * Author: Rabin Vincent <rabin.vincent@stericsson.com> for ST-Ericsson
- *
- * Based on arch/arm/mach-pxa/include/mach/mfp.h:
- *   Copyright (C) 2007 Marvell International Ltd.
- *   eric miao <eric.miao@marvell.com>
- */
-
-#ifndef __PLAT_PINCFG_H
-#define __PLAT_PINCFG_H
-
-/*
- * pin configurations are represented by 32-bit integers:
- *
- *	bit  0.. 8 - Pin Number (512 Pins Maximum)
- *	bit  9..10 - Alternate Function Selection
- *	bit 11..12 - Pull up/down state
- *	bit     13 - Sleep mode behaviour
- *	bit     14 - Direction
- *	bit     15 - Value (if output)
- *	bit 16..18 - SLPM pull up/down state
- *	bit 19..20 - SLPM direction
- *	bit 21..22 - SLPM Value (if output)
- *	bit 23..25 - PDIS value (if input)
- *	bit	26 - Gpio mode
- *	bit	27 - Sleep mode
- *
- * to facilitate the definition, the following macros are provided
- *
- * PIN_CFG_DEFAULT - default config (0):
- *		     pull up/down = disabled
- *		     sleep mode = input/wakeup
- *		     direction = input
- *		     value = low
- *		     SLPM direction = same as normal
- *		     SLPM pull = same as normal
- *		     SLPM value = same as normal
- *
- * PIN_CFG	   - default config with alternate function
- */
-
-typedef unsigned long pin_cfg_t;
-
-#define PIN_NUM_MASK		0x1ff
-#define PIN_NUM(x)		((x) & PIN_NUM_MASK)
-
-#define PIN_ALT_SHIFT		9
-#define PIN_ALT_MASK		(0x3 << PIN_ALT_SHIFT)
-#define PIN_ALT(x)		(((x) & PIN_ALT_MASK) >> PIN_ALT_SHIFT)
-#define PIN_GPIO		(NMK_GPIO_ALT_GPIO << PIN_ALT_SHIFT)
-#define PIN_ALT_A		(NMK_GPIO_ALT_A << PIN_ALT_SHIFT)
-#define PIN_ALT_B		(NMK_GPIO_ALT_B << PIN_ALT_SHIFT)
-#define PIN_ALT_C		(NMK_GPIO_ALT_C << PIN_ALT_SHIFT)
-
-#define PIN_PULL_SHIFT		11
-#define PIN_PULL_MASK		(0x3 << PIN_PULL_SHIFT)
-#define PIN_PULL(x)		(((x) & PIN_PULL_MASK) >> PIN_PULL_SHIFT)
-#define PIN_PULL_NONE		(NMK_GPIO_PULL_NONE << PIN_PULL_SHIFT)
-#define PIN_PULL_UP		(NMK_GPIO_PULL_UP << PIN_PULL_SHIFT)
-#define PIN_PULL_DOWN		(NMK_GPIO_PULL_DOWN << PIN_PULL_SHIFT)
-
-#define PIN_SLPM_SHIFT		13
-#define PIN_SLPM_MASK		(0x1 << PIN_SLPM_SHIFT)
-#define PIN_SLPM(x)		(((x) & PIN_SLPM_MASK) >> PIN_SLPM_SHIFT)
-#define PIN_SLPM_MAKE_INPUT	(NMK_GPIO_SLPM_INPUT << PIN_SLPM_SHIFT)
-#define PIN_SLPM_NOCHANGE	(NMK_GPIO_SLPM_NOCHANGE << PIN_SLPM_SHIFT)
-/* These two replace the above in DB8500v2+ */
-#define PIN_SLPM_WAKEUP_ENABLE	(NMK_GPIO_SLPM_WAKEUP_ENABLE << PIN_SLPM_SHIFT)
-#define PIN_SLPM_WAKEUP_DISABLE	(NMK_GPIO_SLPM_WAKEUP_DISABLE << PIN_SLPM_SHIFT)
-#define PIN_SLPM_USE_MUX_SETTINGS_IN_SLEEP PIN_SLPM_WAKEUP_DISABLE
-
-#define PIN_SLPM_GPIO  PIN_SLPM_WAKEUP_ENABLE /* In SLPM, pin is a gpio */
-#define PIN_SLPM_ALTFUNC PIN_SLPM_WAKEUP_DISABLE /* In SLPM, pin is altfunc */
-
-#define PIN_DIR_SHIFT		14
-#define PIN_DIR_MASK		(0x1 << PIN_DIR_SHIFT)
-#define PIN_DIR(x)		(((x) & PIN_DIR_MASK) >> PIN_DIR_SHIFT)
-#define PIN_DIR_INPUT		(0 << PIN_DIR_SHIFT)
-#define PIN_DIR_OUTPUT		(1 << PIN_DIR_SHIFT)
-
-#define PIN_VAL_SHIFT		15
-#define PIN_VAL_MASK		(0x1 << PIN_VAL_SHIFT)
-#define PIN_VAL(x)		(((x) & PIN_VAL_MASK) >> PIN_VAL_SHIFT)
-#define PIN_VAL_LOW		(0 << PIN_VAL_SHIFT)
-#define PIN_VAL_HIGH		(1 << PIN_VAL_SHIFT)
-
-#define PIN_SLPM_PULL_SHIFT	16
-#define PIN_SLPM_PULL_MASK	(0x7 << PIN_SLPM_PULL_SHIFT)
-#define PIN_SLPM_PULL(x)	\
-	(((x) & PIN_SLPM_PULL_MASK) >> PIN_SLPM_PULL_SHIFT)
-#define PIN_SLPM_PULL_NONE	\
-	((1 + NMK_GPIO_PULL_NONE) << PIN_SLPM_PULL_SHIFT)
-#define PIN_SLPM_PULL_UP	\
-	((1 + NMK_GPIO_PULL_UP) << PIN_SLPM_PULL_SHIFT)
-#define PIN_SLPM_PULL_DOWN	\
-	((1 + NMK_GPIO_PULL_DOWN) << PIN_SLPM_PULL_SHIFT)
-
-#define PIN_SLPM_DIR_SHIFT	19
-#define PIN_SLPM_DIR_MASK	(0x3 << PIN_SLPM_DIR_SHIFT)
-#define PIN_SLPM_DIR(x)		\
-	(((x) & PIN_SLPM_DIR_MASK) >> PIN_SLPM_DIR_SHIFT)
-#define PIN_SLPM_DIR_INPUT	((1 + 0) << PIN_SLPM_DIR_SHIFT)
-#define PIN_SLPM_DIR_OUTPUT	((1 + 1) << PIN_SLPM_DIR_SHIFT)
-
-#define PIN_SLPM_VAL_SHIFT	21
-#define PIN_SLPM_VAL_MASK	(0x3 << PIN_SLPM_VAL_SHIFT)
-#define PIN_SLPM_VAL(x)		\
-	(((x) & PIN_SLPM_VAL_MASK) >> PIN_SLPM_VAL_SHIFT)
-#define PIN_SLPM_VAL_LOW	((1 + 0) << PIN_SLPM_VAL_SHIFT)
-#define PIN_SLPM_VAL_HIGH	((1 + 1) << PIN_SLPM_VAL_SHIFT)
-
-#define PIN_SLPM_PDIS_SHIFT		23
-#define PIN_SLPM_PDIS_MASK		(0x3 << PIN_SLPM_PDIS_SHIFT)
-#define PIN_SLPM_PDIS(x)	\
-	(((x) & PIN_SLPM_PDIS_MASK) >> PIN_SLPM_PDIS_SHIFT)
-#define PIN_SLPM_PDIS_NO_CHANGE		(0 << PIN_SLPM_PDIS_SHIFT)
-#define PIN_SLPM_PDIS_DISABLED		(1 << PIN_SLPM_PDIS_SHIFT)
-#define PIN_SLPM_PDIS_ENABLED		(2 << PIN_SLPM_PDIS_SHIFT)
-
-#define PIN_LOWEMI_SHIFT	25
-#define PIN_LOWEMI_MASK		(0x1 << PIN_LOWEMI_SHIFT)
-#define PIN_LOWEMI(x)		(((x) & PIN_LOWEMI_MASK) >> PIN_LOWEMI_SHIFT)
-#define PIN_LOWEMI_DISABLED	(0 << PIN_LOWEMI_SHIFT)
-#define PIN_LOWEMI_ENABLED	(1 << PIN_LOWEMI_SHIFT)
-
-#define PIN_GPIOMODE_SHIFT	26
-#define PIN_GPIOMODE_MASK	(0x1 << PIN_GPIOMODE_SHIFT)
-#define PIN_GPIOMODE(x)		(((x) & PIN_GPIOMODE_MASK) >> PIN_GPIOMODE_SHIFT)
-#define PIN_GPIOMODE_DISABLED	(0 << PIN_GPIOMODE_SHIFT)
-#define PIN_GPIOMODE_ENABLED	(1 << PIN_GPIOMODE_SHIFT)
-
-#define PIN_SLEEPMODE_SHIFT	27
-#define PIN_SLEEPMODE_MASK	(0x1 << PIN_SLEEPMODE_SHIFT)
-#define PIN_SLEEPMODE(x)	(((x) & PIN_SLEEPMODE_MASK) >> PIN_SLEEPMODE_SHIFT)
-#define PIN_SLEEPMODE_DISABLED	(0 << PIN_SLEEPMODE_SHIFT)
-#define PIN_SLEEPMODE_ENABLED	(1 << PIN_SLEEPMODE_SHIFT)
-
-
-/* Shortcuts.  Use these instead of separate DIR, PULL, and VAL.  */
-#define PIN_INPUT_PULLDOWN	(PIN_DIR_INPUT | PIN_PULL_DOWN)
-#define PIN_INPUT_PULLUP	(PIN_DIR_INPUT | PIN_PULL_UP)
-#define PIN_INPUT_NOPULL	(PIN_DIR_INPUT | PIN_PULL_NONE)
-#define PIN_OUTPUT_LOW		(PIN_DIR_OUTPUT | PIN_VAL_LOW)
-#define PIN_OUTPUT_HIGH		(PIN_DIR_OUTPUT | PIN_VAL_HIGH)
-
-#define PIN_SLPM_INPUT_PULLDOWN	(PIN_SLPM_DIR_INPUT | PIN_SLPM_PULL_DOWN)
-#define PIN_SLPM_INPUT_PULLUP	(PIN_SLPM_DIR_INPUT | PIN_SLPM_PULL_UP)
-#define PIN_SLPM_INPUT_NOPULL	(PIN_SLPM_DIR_INPUT | PIN_SLPM_PULL_NONE)
-#define PIN_SLPM_OUTPUT_LOW	(PIN_SLPM_DIR_OUTPUT | PIN_SLPM_VAL_LOW)
-#define PIN_SLPM_OUTPUT_HIGH	(PIN_SLPM_DIR_OUTPUT | PIN_SLPM_VAL_HIGH)
-
-#define PIN_CFG_DEFAULT		(0)
-
-#define PIN_CFG(num, alt)		\
-	(PIN_CFG_DEFAULT |\
-	 (PIN_NUM(num) | PIN_##alt))
-
-#define PIN_CFG_INPUT(num, alt, pull)		\
-	(PIN_CFG_DEFAULT |\
-	 (PIN_NUM(num) | PIN_##alt | PIN_INPUT_##pull))
-
-#define PIN_CFG_OUTPUT(num, alt, val)		\
-	(PIN_CFG_DEFAULT |\
-	 (PIN_NUM(num) | PIN_##alt | PIN_OUTPUT_##val))
-
-extern int nmk_config_pin(pin_cfg_t cfg, bool sleep);
-extern int nmk_config_pins(pin_cfg_t *cfgs, int num);
-extern int nmk_config_pins_sleep(pin_cfg_t *cfgs, int num);
-
-#endif
diff --git a/drivers/pinctrl/pinctrl-nomadik.c b/drivers/pinctrl/pinctrl-nomadik.c
index e24fa05e59b8..a49052305756 100644
--- a/drivers/pinctrl/pinctrl-nomadik.c
+++ b/drivers/pinctrl/pinctrl-nomadik.c
@@ -48,8 +48,6 @@ static inline void prcmu_write_masked(unsigned int reg, u32 mask, u32 value) {}
 
 #include <asm/mach/irq.h>
 
-#include <plat/pincfg.h>
-
 #include "pinctrl-nomadik.h"
 
 /*
@@ -534,7 +532,7 @@ static int __nmk_config_pins(pin_cfg_t *cfgs, int num, bool sleep)
  * and its sleep mode based on the specified configuration.  The @cfg is
  * usually one of the SoC specific macros defined in mach/<soc>-pins.h.  These
  * are constructed using, and can be further enhanced with, the macros in
- * plat/pincfg.h.
+ * <linux/platform_data/pinctrl-nomadik.h>
  *
  * If a pin's mode is set to GPIO, it is configured as an input to avoid
  * side-effects.  The gpio can be manipulated later using standard GPIO API
diff --git a/include/linux/platform_data/pinctrl-nomadik.h b/include/linux/platform_data/pinctrl-nomadik.h
index a74999438de4..f73b2f0c55b7 100644
--- a/include/linux/platform_data/pinctrl-nomadik.h
+++ b/include/linux/platform_data/pinctrl-nomadik.h
@@ -13,6 +13,160 @@
 #ifndef __PLAT_NOMADIK_GPIO
 #define __PLAT_NOMADIK_GPIO
 
+/*
+ * pin configurations are represented by 32-bit integers:
+ *
+ *	bit  0.. 8 - Pin Number (512 Pins Maximum)
+ *	bit  9..10 - Alternate Function Selection
+ *	bit 11..12 - Pull up/down state
+ *	bit     13 - Sleep mode behaviour
+ *	bit     14 - Direction
+ *	bit     15 - Value (if output)
+ *	bit 16..18 - SLPM pull up/down state
+ *	bit 19..20 - SLPM direction
+ *	bit 21..22 - SLPM Value (if output)
+ *	bit 23..25 - PDIS value (if input)
+ *	bit	26 - Gpio mode
+ *	bit	27 - Sleep mode
+ *
+ * to facilitate the definition, the following macros are provided
+ *
+ * PIN_CFG_DEFAULT - default config (0):
+ *		     pull up/down = disabled
+ *		     sleep mode = input/wakeup
+ *		     direction = input
+ *		     value = low
+ *		     SLPM direction = same as normal
+ *		     SLPM pull = same as normal
+ *		     SLPM value = same as normal
+ *
+ * PIN_CFG	   - default config with alternate function
+ */
+
+typedef unsigned long pin_cfg_t;
+
+#define PIN_NUM_MASK		0x1ff
+#define PIN_NUM(x)		((x) & PIN_NUM_MASK)
+
+#define PIN_ALT_SHIFT		9
+#define PIN_ALT_MASK		(0x3 << PIN_ALT_SHIFT)
+#define PIN_ALT(x)		(((x) & PIN_ALT_MASK) >> PIN_ALT_SHIFT)
+#define PIN_GPIO		(NMK_GPIO_ALT_GPIO << PIN_ALT_SHIFT)
+#define PIN_ALT_A		(NMK_GPIO_ALT_A << PIN_ALT_SHIFT)
+#define PIN_ALT_B		(NMK_GPIO_ALT_B << PIN_ALT_SHIFT)
+#define PIN_ALT_C		(NMK_GPIO_ALT_C << PIN_ALT_SHIFT)
+
+#define PIN_PULL_SHIFT		11
+#define PIN_PULL_MASK		(0x3 << PIN_PULL_SHIFT)
+#define PIN_PULL(x)		(((x) & PIN_PULL_MASK) >> PIN_PULL_SHIFT)
+#define PIN_PULL_NONE		(NMK_GPIO_PULL_NONE << PIN_PULL_SHIFT)
+#define PIN_PULL_UP		(NMK_GPIO_PULL_UP << PIN_PULL_SHIFT)
+#define PIN_PULL_DOWN		(NMK_GPIO_PULL_DOWN << PIN_PULL_SHIFT)
+
+#define PIN_SLPM_SHIFT		13
+#define PIN_SLPM_MASK		(0x1 << PIN_SLPM_SHIFT)
+#define PIN_SLPM(x)		(((x) & PIN_SLPM_MASK) >> PIN_SLPM_SHIFT)
+#define PIN_SLPM_MAKE_INPUT	(NMK_GPIO_SLPM_INPUT << PIN_SLPM_SHIFT)
+#define PIN_SLPM_NOCHANGE	(NMK_GPIO_SLPM_NOCHANGE << PIN_SLPM_SHIFT)
+/* These two replace the above in DB8500v2+ */
+#define PIN_SLPM_WAKEUP_ENABLE	(NMK_GPIO_SLPM_WAKEUP_ENABLE << PIN_SLPM_SHIFT)
+#define PIN_SLPM_WAKEUP_DISABLE	(NMK_GPIO_SLPM_WAKEUP_DISABLE << PIN_SLPM_SHIFT)
+#define PIN_SLPM_USE_MUX_SETTINGS_IN_SLEEP PIN_SLPM_WAKEUP_DISABLE
+
+#define PIN_SLPM_GPIO  PIN_SLPM_WAKEUP_ENABLE /* In SLPM, pin is a gpio */
+#define PIN_SLPM_ALTFUNC PIN_SLPM_WAKEUP_DISABLE /* In SLPM, pin is altfunc */
+
+#define PIN_DIR_SHIFT		14
+#define PIN_DIR_MASK		(0x1 << PIN_DIR_SHIFT)
+#define PIN_DIR(x)		(((x) & PIN_DIR_MASK) >> PIN_DIR_SHIFT)
+#define PIN_DIR_INPUT		(0 << PIN_DIR_SHIFT)
+#define PIN_DIR_OUTPUT		(1 << PIN_DIR_SHIFT)
+
+#define PIN_VAL_SHIFT		15
+#define PIN_VAL_MASK		(0x1 << PIN_VAL_SHIFT)
+#define PIN_VAL(x)		(((x) & PIN_VAL_MASK) >> PIN_VAL_SHIFT)
+#define PIN_VAL_LOW		(0 << PIN_VAL_SHIFT)
+#define PIN_VAL_HIGH		(1 << PIN_VAL_SHIFT)
+
+#define PIN_SLPM_PULL_SHIFT	16
+#define PIN_SLPM_PULL_MASK	(0x7 << PIN_SLPM_PULL_SHIFT)
+#define PIN_SLPM_PULL(x)	\
+	(((x) & PIN_SLPM_PULL_MASK) >> PIN_SLPM_PULL_SHIFT)
+#define PIN_SLPM_PULL_NONE	\
+	((1 + NMK_GPIO_PULL_NONE) << PIN_SLPM_PULL_SHIFT)
+#define PIN_SLPM_PULL_UP	\
+	((1 + NMK_GPIO_PULL_UP) << PIN_SLPM_PULL_SHIFT)
+#define PIN_SLPM_PULL_DOWN	\
+	((1 + NMK_GPIO_PULL_DOWN) << PIN_SLPM_PULL_SHIFT)
+
+#define PIN_SLPM_DIR_SHIFT	19
+#define PIN_SLPM_DIR_MASK	(0x3 << PIN_SLPM_DIR_SHIFT)
+#define PIN_SLPM_DIR(x)		\
+	(((x) & PIN_SLPM_DIR_MASK) >> PIN_SLPM_DIR_SHIFT)
+#define PIN_SLPM_DIR_INPUT	((1 + 0) << PIN_SLPM_DIR_SHIFT)
+#define PIN_SLPM_DIR_OUTPUT	((1 + 1) << PIN_SLPM_DIR_SHIFT)
+
+#define PIN_SLPM_VAL_SHIFT	21
+#define PIN_SLPM_VAL_MASK	(0x3 << PIN_SLPM_VAL_SHIFT)
+#define PIN_SLPM_VAL(x)		\
+	(((x) & PIN_SLPM_VAL_MASK) >> PIN_SLPM_VAL_SHIFT)
+#define PIN_SLPM_VAL_LOW	((1 + 0) << PIN_SLPM_VAL_SHIFT)
+#define PIN_SLPM_VAL_HIGH	((1 + 1) << PIN_SLPM_VAL_SHIFT)
+
+#define PIN_SLPM_PDIS_SHIFT		23
+#define PIN_SLPM_PDIS_MASK		(0x3 << PIN_SLPM_PDIS_SHIFT)
+#define PIN_SLPM_PDIS(x)	\
+	(((x) & PIN_SLPM_PDIS_MASK) >> PIN_SLPM_PDIS_SHIFT)
+#define PIN_SLPM_PDIS_NO_CHANGE		(0 << PIN_SLPM_PDIS_SHIFT)
+#define PIN_SLPM_PDIS_DISABLED		(1 << PIN_SLPM_PDIS_SHIFT)
+#define PIN_SLPM_PDIS_ENABLED		(2 << PIN_SLPM_PDIS_SHIFT)
+
+#define PIN_LOWEMI_SHIFT	25
+#define PIN_LOWEMI_MASK		(0x1 << PIN_LOWEMI_SHIFT)
+#define PIN_LOWEMI(x)		(((x) & PIN_LOWEMI_MASK) >> PIN_LOWEMI_SHIFT)
+#define PIN_LOWEMI_DISABLED	(0 << PIN_LOWEMI_SHIFT)
+#define PIN_LOWEMI_ENABLED	(1 << PIN_LOWEMI_SHIFT)
+
+#define PIN_GPIOMODE_SHIFT	26
+#define PIN_GPIOMODE_MASK	(0x1 << PIN_GPIOMODE_SHIFT)
+#define PIN_GPIOMODE(x)		(((x) & PIN_GPIOMODE_MASK) >> PIN_GPIOMODE_SHIFT)
+#define PIN_GPIOMODE_DISABLED	(0 << PIN_GPIOMODE_SHIFT)
+#define PIN_GPIOMODE_ENABLED	(1 << PIN_GPIOMODE_SHIFT)
+
+#define PIN_SLEEPMODE_SHIFT	27
+#define PIN_SLEEPMODE_MASK	(0x1 << PIN_SLEEPMODE_SHIFT)
+#define PIN_SLEEPMODE(x)	(((x) & PIN_SLEEPMODE_MASK) >> PIN_SLEEPMODE_SHIFT)
+#define PIN_SLEEPMODE_DISABLED	(0 << PIN_SLEEPMODE_SHIFT)
+#define PIN_SLEEPMODE_ENABLED	(1 << PIN_SLEEPMODE_SHIFT)
+
+
+/* Shortcuts.  Use these instead of separate DIR, PULL, and VAL.  */
+#define PIN_INPUT_PULLDOWN	(PIN_DIR_INPUT | PIN_PULL_DOWN)
+#define PIN_INPUT_PULLUP	(PIN_DIR_INPUT | PIN_PULL_UP)
+#define PIN_INPUT_NOPULL	(PIN_DIR_INPUT | PIN_PULL_NONE)
+#define PIN_OUTPUT_LOW		(PIN_DIR_OUTPUT | PIN_VAL_LOW)
+#define PIN_OUTPUT_HIGH		(PIN_DIR_OUTPUT | PIN_VAL_HIGH)
+
+#define PIN_SLPM_INPUT_PULLDOWN	(PIN_SLPM_DIR_INPUT | PIN_SLPM_PULL_DOWN)
+#define PIN_SLPM_INPUT_PULLUP	(PIN_SLPM_DIR_INPUT | PIN_SLPM_PULL_UP)
+#define PIN_SLPM_INPUT_NOPULL	(PIN_SLPM_DIR_INPUT | PIN_SLPM_PULL_NONE)
+#define PIN_SLPM_OUTPUT_LOW	(PIN_SLPM_DIR_OUTPUT | PIN_SLPM_VAL_LOW)
+#define PIN_SLPM_OUTPUT_HIGH	(PIN_SLPM_DIR_OUTPUT | PIN_SLPM_VAL_HIGH)
+
+#define PIN_CFG_DEFAULT		(0)
+
+#define PIN_CFG(num, alt)		\
+	(PIN_CFG_DEFAULT |\
+	 (PIN_NUM(num) | PIN_##alt))
+
+#define PIN_CFG_INPUT(num, alt, pull)		\
+	(PIN_CFG_DEFAULT |\
+	 (PIN_NUM(num) | PIN_##alt | PIN_INPUT_##pull))
+
+#define PIN_CFG_OUTPUT(num, alt, val)		\
+	(PIN_CFG_DEFAULT |\
+	 (PIN_NUM(num) | PIN_##alt | PIN_OUTPUT_##val))
+
 /*
  * "nmk_gpio" and "NMK_GPIO" stand for "Nomadik GPIO", leaving
  * the "gpio" namespace for generic and cross-machine functions
@@ -72,6 +226,10 @@ enum nmk_gpio_slpm {
 	NMK_GPIO_SLPM_WAKEUP_DISABLE = NMK_GPIO_SLPM_NOCHANGE,
 };
 
+/* Older deprecated pin config API that should go away soon */
+extern int nmk_config_pin(pin_cfg_t cfg, bool sleep);
+extern int nmk_config_pins(pin_cfg_t *cfgs, int num);
+extern int nmk_config_pins_sleep(pin_cfg_t *cfgs, int num);
 extern int nmk_gpio_set_slpm(int gpio, enum nmk_gpio_slpm mode);
 extern int nmk_gpio_set_pull(int gpio, enum nmk_gpio_pull pull);
 #ifdef CONFIG_PINCTRL_NOMADIK
-- 
cgit v1.2.3-55-g7522


From 865fab601b8f910b2c634cf4c9211176f2c71cad Mon Sep 17 00:00:00 2001
From: Linus Walleij
Date: Thu, 18 Oct 2012 14:20:16 +0200
Subject: ARM: plat-nomadik: move DMA40 header to <linux/platform_data>

This moves the DMA40 platform data header from <plat/ste_dma40.h>
to <linux/platform_data/dma-ste-dma40.h> where is belongs.

Cc: Dan Williams <djbw@fb.com>
Cc: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: Ola Lilja <ola.o.lilja@stericsson.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Andreas Westin <andreas.westin@stericsson.com>
Acked-by: Vinod Koul <vinod.koul@intel.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/arm/mach-ux500/board-mop500-audio.c       |   3 +-
 arch/arm/mach-ux500/board-mop500-sdi.c         |   2 +-
 arch/arm/mach-ux500/board-mop500.c             |   3 +-
 arch/arm/mach-ux500/devices-db8500.c           |   3 +-
 arch/arm/mach-ux500/include/mach/msp.h         |   2 +-
 arch/arm/mach-ux500/usb.c                      |   4 +-
 arch/arm/plat-nomadik/include/plat/ste_dma40.h | 223 -------------------------
 drivers/crypto/ux500/cryp/cryp_core.c          |   3 +-
 drivers/dma/ste_dma40.c                        |   3 +-
 drivers/dma/ste_dma40_ll.c                     |   2 +-
 include/linux/platform_data/crypto-ux500.h     |   2 +-
 include/linux/platform_data/dma-ste-dma40.h    | 223 +++++++++++++++++++++++++
 sound/soc/ux500/ux500_pcm.c                    |   3 +-
 13 files changed, 235 insertions(+), 241 deletions(-)
 delete mode 100644 arch/arm/plat-nomadik/include/plat/ste_dma40.h
 create mode 100644 include/linux/platform_data/dma-ste-dma40.h

(limited to 'include')

diff --git a/arch/arm/mach-ux500/board-mop500-audio.c b/arch/arm/mach-ux500/board-mop500-audio.c
index 33631c9f1218..71a2ca726476 100644
--- a/arch/arm/mach-ux500/board-mop500-audio.c
+++ b/arch/arm/mach-ux500/board-mop500-audio.c
@@ -8,8 +8,7 @@
 #include <linux/init.h>
 #include <linux/gpio.h>
 #include <linux/platform_data/pinctrl-nomadik.h>
-
-#include <plat/ste_dma40.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
 #include <mach/devices.h>
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-ux500/board-mop500-sdi.c b/arch/arm/mach-ux500/board-mop500-sdi.c
index 9c8e4a9e83ee..051b62c27102 100644
--- a/arch/arm/mach-ux500/board-mop500-sdi.c
+++ b/arch/arm/mach-ux500/board-mop500-sdi.c
@@ -11,9 +11,9 @@
 #include <linux/amba/mmci.h>
 #include <linux/mmc/host.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
 #include <asm/mach-types.h>
-#include <plat/ste_dma40.h>
 #include <mach/devices.h>
 #include <mach/hardware.h>
 
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index 0a3dd601a400..0213e896fbfd 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -38,13 +38,12 @@
 #include <linux/leds.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_data/pinctrl-nomadik.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/hardware/gic.h>
 
-#include <plat/ste_dma40.h>
-
 #include <mach/hardware.h>
 #include <mach/setup.h>
 #include <mach/devices.h>
diff --git a/arch/arm/mach-ux500/devices-db8500.c b/arch/arm/mach-ux500/devices-db8500.c
index 91754a8a0d49..bdc963cb2f45 100644
--- a/arch/arm/mach-ux500/devices-db8500.c
+++ b/arch/arm/mach-ux500/devices-db8500.c
@@ -12,8 +12,7 @@
 #include <linux/gpio.h>
 #include <linux/amba/bus.h>
 #include <linux/amba/pl022.h>
-
-#include <plat/ste_dma40.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
 #include <mach/hardware.h>
 #include <mach/setup.h>
diff --git a/arch/arm/mach-ux500/include/mach/msp.h b/arch/arm/mach-ux500/include/mach/msp.h
index 3cc7142eee02..9991aea3d577 100644
--- a/arch/arm/mach-ux500/include/mach/msp.h
+++ b/arch/arm/mach-ux500/include/mach/msp.h
@@ -8,7 +8,7 @@
 #ifndef __MSP_H
 #define __MSP_H
 
-#include <plat/ste_dma40.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
 enum msp_i2s_id {
 	MSP_I2S_0 = 0,
diff --git a/arch/arm/mach-ux500/usb.c b/arch/arm/mach-ux500/usb.c
index 145482e74418..78ac65f62e87 100644
--- a/arch/arm/mach-ux500/usb.c
+++ b/arch/arm/mach-ux500/usb.c
@@ -7,10 +7,10 @@
 #include <linux/platform_device.h>
 #include <linux/usb/musb.h>
 #include <linux/dma-mapping.h>
+#include <linux/platform_data/usb-musb-ux500.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
-#include <plat/ste_dma40.h>
 #include <mach/hardware.h>
-#include <linux/platform_data/usb-musb-ux500.h>
 
 #define MUSB_DMA40_RX_CH { \
 		.mode = STEDMA40_MODE_LOGICAL, \
diff --git a/arch/arm/plat-nomadik/include/plat/ste_dma40.h b/arch/arm/plat-nomadik/include/plat/ste_dma40.h
deleted file mode 100644
index 9ff93b065686..000000000000
--- a/arch/arm/plat-nomadik/include/plat/ste_dma40.h
+++ /dev/null
@@ -1,223 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2007-2010
- * Author: Per Forlin <per.forlin@stericsson.com> for ST-Ericsson
- * Author: Jonas Aaberg <jonas.aberg@stericsson.com> for ST-Ericsson
- * License terms: GNU General Public License (GPL) version 2
- */
-
-
-#ifndef STE_DMA40_H
-#define STE_DMA40_H
-
-#include <linux/dmaengine.h>
-#include <linux/scatterlist.h>
-#include <linux/workqueue.h>
-#include <linux/interrupt.h>
-
-/*
- * Maxium size for a single dma descriptor
- * Size is limited to 16 bits.
- * Size is in the units of addr-widths (1,2,4,8 bytes)
- * Larger transfers will be split up to multiple linked desc
- */
-#define STEDMA40_MAX_SEG_SIZE 0xFFFF
-
-/* dev types for memcpy */
-#define STEDMA40_DEV_DST_MEMORY (-1)
-#define	STEDMA40_DEV_SRC_MEMORY (-1)
-
-enum stedma40_mode {
-	STEDMA40_MODE_LOGICAL = 0,
-	STEDMA40_MODE_PHYSICAL,
-	STEDMA40_MODE_OPERATION,
-};
-
-enum stedma40_mode_opt {
-	STEDMA40_PCHAN_BASIC_MODE = 0,
-	STEDMA40_LCHAN_SRC_LOG_DST_LOG = 0,
-	STEDMA40_PCHAN_MODULO_MODE,
-	STEDMA40_PCHAN_DOUBLE_DST_MODE,
-	STEDMA40_LCHAN_SRC_PHY_DST_LOG,
-	STEDMA40_LCHAN_SRC_LOG_DST_PHY,
-};
-
-#define STEDMA40_ESIZE_8_BIT  0x0
-#define STEDMA40_ESIZE_16_BIT 0x1
-#define STEDMA40_ESIZE_32_BIT 0x2
-#define STEDMA40_ESIZE_64_BIT 0x3
-
-/* The value 4 indicates that PEN-reg shall be set to 0 */
-#define STEDMA40_PSIZE_PHY_1  0x4
-#define STEDMA40_PSIZE_PHY_2  0x0
-#define STEDMA40_PSIZE_PHY_4  0x1
-#define STEDMA40_PSIZE_PHY_8  0x2
-#define STEDMA40_PSIZE_PHY_16 0x3
-
-/*
- * The number of elements differ in logical and
- * physical mode
- */
-#define STEDMA40_PSIZE_LOG_1  STEDMA40_PSIZE_PHY_2
-#define STEDMA40_PSIZE_LOG_4  STEDMA40_PSIZE_PHY_4
-#define STEDMA40_PSIZE_LOG_8  STEDMA40_PSIZE_PHY_8
-#define STEDMA40_PSIZE_LOG_16 STEDMA40_PSIZE_PHY_16
-
-/* Maximum number of possible physical channels */
-#define STEDMA40_MAX_PHYS 32
-
-enum stedma40_flow_ctrl {
-	STEDMA40_NO_FLOW_CTRL,
-	STEDMA40_FLOW_CTRL,
-};
-
-enum stedma40_periph_data_width {
-	STEDMA40_BYTE_WIDTH = STEDMA40_ESIZE_8_BIT,
-	STEDMA40_HALFWORD_WIDTH = STEDMA40_ESIZE_16_BIT,
-	STEDMA40_WORD_WIDTH = STEDMA40_ESIZE_32_BIT,
-	STEDMA40_DOUBLEWORD_WIDTH = STEDMA40_ESIZE_64_BIT
-};
-
-enum stedma40_xfer_dir {
-	STEDMA40_MEM_TO_MEM = 1,
-	STEDMA40_MEM_TO_PERIPH,
-	STEDMA40_PERIPH_TO_MEM,
-	STEDMA40_PERIPH_TO_PERIPH
-};
-
-
-/**
- * struct stedma40_chan_cfg - dst/src channel configuration
- *
- * @big_endian: true if the src/dst should be read as big endian
- * @data_width: Data width of the src/dst hardware
- * @p_size: Burst size
- * @flow_ctrl: Flow control on/off.
- */
-struct stedma40_half_channel_info {
-	bool big_endian;
-	enum stedma40_periph_data_width data_width;
-	int psize;
-	enum stedma40_flow_ctrl flow_ctrl;
-};
-
-/**
- * struct stedma40_chan_cfg - Structure to be filled by client drivers.
- *
- * @dir: MEM 2 MEM, PERIPH 2 MEM , MEM 2 PERIPH, PERIPH 2 PERIPH
- * @high_priority: true if high-priority
- * @realtime: true if realtime mode is to be enabled.  Only available on DMA40
- * version 3+, i.e DB8500v2+
- * @mode: channel mode: physical, logical, or operation
- * @mode_opt: options for the chosen channel mode
- * @src_dev_type: Src device type
- * @dst_dev_type: Dst device type
- * @src_info: Parameters for dst half channel
- * @dst_info: Parameters for dst half channel
- * @use_fixed_channel: if true, use physical channel specified by phy_channel
- * @phy_channel: physical channel to use, only if use_fixed_channel is true
- *
- * This structure has to be filled by the client drivers.
- * It is recommended to do all dma configurations for clients in the machine.
- *
- */
-struct stedma40_chan_cfg {
-	enum stedma40_xfer_dir			 dir;
-	bool					 high_priority;
-	bool					 realtime;
-	enum stedma40_mode			 mode;
-	enum stedma40_mode_opt			 mode_opt;
-	int					 src_dev_type;
-	int					 dst_dev_type;
-	struct stedma40_half_channel_info	 src_info;
-	struct stedma40_half_channel_info	 dst_info;
-
-	bool					 use_fixed_channel;
-	int					 phy_channel;
-};
-
-/**
- * struct stedma40_platform_data - Configuration struct for the dma device.
- *
- * @dev_len: length of dev_tx and dev_rx
- * @dev_tx: mapping between destination event line and io address
- * @dev_rx: mapping between source event line and io address
- * @memcpy: list of memcpy event lines
- * @memcpy_len: length of memcpy
- * @memcpy_conf_phy: default configuration of physical channel memcpy
- * @memcpy_conf_log: default configuration of logical channel memcpy
- * @disabled_channels: A vector, ending with -1, that marks physical channels
- * that are for different reasons not available for the driver.
- */
-struct stedma40_platform_data {
-	u32				 dev_len;
-	const dma_addr_t		*dev_tx;
-	const dma_addr_t		*dev_rx;
-	int				*memcpy;
-	u32				 memcpy_len;
-	struct stedma40_chan_cfg	*memcpy_conf_phy;
-	struct stedma40_chan_cfg	*memcpy_conf_log;
-	int				 disabled_channels[STEDMA40_MAX_PHYS];
-	bool				 use_esram_lcla;
-};
-
-#ifdef CONFIG_STE_DMA40
-
-/**
- * stedma40_filter() - Provides stedma40_chan_cfg to the
- * ste_dma40 dma driver via the dmaengine framework.
- * does some checking of what's provided.
- *
- * Never directly called by client. It used by dmaengine.
- * @chan: dmaengine handle.
- * @data: Must be of type: struct stedma40_chan_cfg and is
- * the configuration of the framework.
- *
- *
- */
-
-bool stedma40_filter(struct dma_chan *chan, void *data);
-
-/**
- * stedma40_slave_mem() - Transfers a raw data buffer to or from a slave
- * (=device)
- *
- * @chan: dmaengine handle
- * @addr: source or destination physicall address.
- * @size: bytes to transfer
- * @direction: direction of transfer
- * @flags: is actually enum dma_ctrl_flags. See dmaengine.h
- */
-
-static inline struct
-dma_async_tx_descriptor *stedma40_slave_mem(struct dma_chan *chan,
-					    dma_addr_t addr,
-					    unsigned int size,
-					    enum dma_transfer_direction direction,
-					    unsigned long flags)
-{
-	struct scatterlist sg;
-	sg_init_table(&sg, 1);
-	sg.dma_address = addr;
-	sg.length = size;
-
-	return dmaengine_prep_slave_sg(chan, &sg, 1, direction, flags);
-}
-
-#else
-static inline bool stedma40_filter(struct dma_chan *chan, void *data)
-{
-	return false;
-}
-
-static inline struct
-dma_async_tx_descriptor *stedma40_slave_mem(struct dma_chan *chan,
-					    dma_addr_t addr,
-					    unsigned int size,
-					    enum dma_transfer_direction direction,
-					    unsigned long flags)
-{
-	return NULL;
-}
-#endif
-
-#endif
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index bc615cc56266..8bc5fef07e7a 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -23,6 +23,7 @@
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 #include <linux/semaphore.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
@@ -30,8 +31,6 @@
 #include <crypto/des.h>
 #include <crypto/scatterwalk.h>
 
-#include <plat/ste_dma40.h>
-
 #include <linux/platform_data/crypto-ux500.h>
 #include <mach/hardware.h>
 
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index ae55091c2272..23c5573e62dd 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -19,8 +19,7 @@
 #include <linux/err.h>
 #include <linux/amba/bus.h>
 #include <linux/regulator/consumer.h>
-
-#include <plat/ste_dma40.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
 #include "dmaengine.h"
 #include "ste_dma40_ll.h"
diff --git a/drivers/dma/ste_dma40_ll.c b/drivers/dma/ste_dma40_ll.c
index cad9e1daedff..851ad56e8409 100644
--- a/drivers/dma/ste_dma40_ll.c
+++ b/drivers/dma/ste_dma40_ll.c
@@ -6,7 +6,7 @@
  */
 
 #include <linux/kernel.h>
-#include <plat/ste_dma40.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
 #include "ste_dma40_ll.h"
 
diff --git a/include/linux/platform_data/crypto-ux500.h b/include/linux/platform_data/crypto-ux500.h
index 5b2d0817e26a..94df96d9a336 100644
--- a/include/linux/platform_data/crypto-ux500.h
+++ b/include/linux/platform_data/crypto-ux500.h
@@ -7,7 +7,7 @@
 #ifndef _CRYPTO_UX500_H
 #define _CRYPTO_UX500_H
 #include <linux/dmaengine.h>
-#include <plat/ste_dma40.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
 struct hash_platform_data {
 	void *mem_to_engine;
diff --git a/include/linux/platform_data/dma-ste-dma40.h b/include/linux/platform_data/dma-ste-dma40.h
new file mode 100644
index 000000000000..9ff93b065686
--- /dev/null
+++ b/include/linux/platform_data/dma-ste-dma40.h
@@ -0,0 +1,223 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2007-2010
+ * Author: Per Forlin <per.forlin@stericsson.com> for ST-Ericsson
+ * Author: Jonas Aaberg <jonas.aberg@stericsson.com> for ST-Ericsson
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+
+#ifndef STE_DMA40_H
+#define STE_DMA40_H
+
+#include <linux/dmaengine.h>
+#include <linux/scatterlist.h>
+#include <linux/workqueue.h>
+#include <linux/interrupt.h>
+
+/*
+ * Maxium size for a single dma descriptor
+ * Size is limited to 16 bits.
+ * Size is in the units of addr-widths (1,2,4,8 bytes)
+ * Larger transfers will be split up to multiple linked desc
+ */
+#define STEDMA40_MAX_SEG_SIZE 0xFFFF
+
+/* dev types for memcpy */
+#define STEDMA40_DEV_DST_MEMORY (-1)
+#define	STEDMA40_DEV_SRC_MEMORY (-1)
+
+enum stedma40_mode {
+	STEDMA40_MODE_LOGICAL = 0,
+	STEDMA40_MODE_PHYSICAL,
+	STEDMA40_MODE_OPERATION,
+};
+
+enum stedma40_mode_opt {
+	STEDMA40_PCHAN_BASIC_MODE = 0,
+	STEDMA40_LCHAN_SRC_LOG_DST_LOG = 0,
+	STEDMA40_PCHAN_MODULO_MODE,
+	STEDMA40_PCHAN_DOUBLE_DST_MODE,
+	STEDMA40_LCHAN_SRC_PHY_DST_LOG,
+	STEDMA40_LCHAN_SRC_LOG_DST_PHY,
+};
+
+#define STEDMA40_ESIZE_8_BIT  0x0
+#define STEDMA40_ESIZE_16_BIT 0x1
+#define STEDMA40_ESIZE_32_BIT 0x2
+#define STEDMA40_ESIZE_64_BIT 0x3
+
+/* The value 4 indicates that PEN-reg shall be set to 0 */
+#define STEDMA40_PSIZE_PHY_1  0x4
+#define STEDMA40_PSIZE_PHY_2  0x0
+#define STEDMA40_PSIZE_PHY_4  0x1
+#define STEDMA40_PSIZE_PHY_8  0x2
+#define STEDMA40_PSIZE_PHY_16 0x3
+
+/*
+ * The number of elements differ in logical and
+ * physical mode
+ */
+#define STEDMA40_PSIZE_LOG_1  STEDMA40_PSIZE_PHY_2
+#define STEDMA40_PSIZE_LOG_4  STEDMA40_PSIZE_PHY_4
+#define STEDMA40_PSIZE_LOG_8  STEDMA40_PSIZE_PHY_8
+#define STEDMA40_PSIZE_LOG_16 STEDMA40_PSIZE_PHY_16
+
+/* Maximum number of possible physical channels */
+#define STEDMA40_MAX_PHYS 32
+
+enum stedma40_flow_ctrl {
+	STEDMA40_NO_FLOW_CTRL,
+	STEDMA40_FLOW_CTRL,
+};
+
+enum stedma40_periph_data_width {
+	STEDMA40_BYTE_WIDTH = STEDMA40_ESIZE_8_BIT,
+	STEDMA40_HALFWORD_WIDTH = STEDMA40_ESIZE_16_BIT,
+	STEDMA40_WORD_WIDTH = STEDMA40_ESIZE_32_BIT,
+	STEDMA40_DOUBLEWORD_WIDTH = STEDMA40_ESIZE_64_BIT
+};
+
+enum stedma40_xfer_dir {
+	STEDMA40_MEM_TO_MEM = 1,
+	STEDMA40_MEM_TO_PERIPH,
+	STEDMA40_PERIPH_TO_MEM,
+	STEDMA40_PERIPH_TO_PERIPH
+};
+
+
+/**
+ * struct stedma40_chan_cfg - dst/src channel configuration
+ *
+ * @big_endian: true if the src/dst should be read as big endian
+ * @data_width: Data width of the src/dst hardware
+ * @p_size: Burst size
+ * @flow_ctrl: Flow control on/off.
+ */
+struct stedma40_half_channel_info {
+	bool big_endian;
+	enum stedma40_periph_data_width data_width;
+	int psize;
+	enum stedma40_flow_ctrl flow_ctrl;
+};
+
+/**
+ * struct stedma40_chan_cfg - Structure to be filled by client drivers.
+ *
+ * @dir: MEM 2 MEM, PERIPH 2 MEM , MEM 2 PERIPH, PERIPH 2 PERIPH
+ * @high_priority: true if high-priority
+ * @realtime: true if realtime mode is to be enabled.  Only available on DMA40
+ * version 3+, i.e DB8500v2+
+ * @mode: channel mode: physical, logical, or operation
+ * @mode_opt: options for the chosen channel mode
+ * @src_dev_type: Src device type
+ * @dst_dev_type: Dst device type
+ * @src_info: Parameters for dst half channel
+ * @dst_info: Parameters for dst half channel
+ * @use_fixed_channel: if true, use physical channel specified by phy_channel
+ * @phy_channel: physical channel to use, only if use_fixed_channel is true
+ *
+ * This structure has to be filled by the client drivers.
+ * It is recommended to do all dma configurations for clients in the machine.
+ *
+ */
+struct stedma40_chan_cfg {
+	enum stedma40_xfer_dir			 dir;
+	bool					 high_priority;
+	bool					 realtime;
+	enum stedma40_mode			 mode;
+	enum stedma40_mode_opt			 mode_opt;
+	int					 src_dev_type;
+	int					 dst_dev_type;
+	struct stedma40_half_channel_info	 src_info;
+	struct stedma40_half_channel_info	 dst_info;
+
+	bool					 use_fixed_channel;
+	int					 phy_channel;
+};
+
+/**
+ * struct stedma40_platform_data - Configuration struct for the dma device.
+ *
+ * @dev_len: length of dev_tx and dev_rx
+ * @dev_tx: mapping between destination event line and io address
+ * @dev_rx: mapping between source event line and io address
+ * @memcpy: list of memcpy event lines
+ * @memcpy_len: length of memcpy
+ * @memcpy_conf_phy: default configuration of physical channel memcpy
+ * @memcpy_conf_log: default configuration of logical channel memcpy
+ * @disabled_channels: A vector, ending with -1, that marks physical channels
+ * that are for different reasons not available for the driver.
+ */
+struct stedma40_platform_data {
+	u32				 dev_len;
+	const dma_addr_t		*dev_tx;
+	const dma_addr_t		*dev_rx;
+	int				*memcpy;
+	u32				 memcpy_len;
+	struct stedma40_chan_cfg	*memcpy_conf_phy;
+	struct stedma40_chan_cfg	*memcpy_conf_log;
+	int				 disabled_channels[STEDMA40_MAX_PHYS];
+	bool				 use_esram_lcla;
+};
+
+#ifdef CONFIG_STE_DMA40
+
+/**
+ * stedma40_filter() - Provides stedma40_chan_cfg to the
+ * ste_dma40 dma driver via the dmaengine framework.
+ * does some checking of what's provided.
+ *
+ * Never directly called by client. It used by dmaengine.
+ * @chan: dmaengine handle.
+ * @data: Must be of type: struct stedma40_chan_cfg and is
+ * the configuration of the framework.
+ *
+ *
+ */
+
+bool stedma40_filter(struct dma_chan *chan, void *data);
+
+/**
+ * stedma40_slave_mem() - Transfers a raw data buffer to or from a slave
+ * (=device)
+ *
+ * @chan: dmaengine handle
+ * @addr: source or destination physicall address.
+ * @size: bytes to transfer
+ * @direction: direction of transfer
+ * @flags: is actually enum dma_ctrl_flags. See dmaengine.h
+ */
+
+static inline struct
+dma_async_tx_descriptor *stedma40_slave_mem(struct dma_chan *chan,
+					    dma_addr_t addr,
+					    unsigned int size,
+					    enum dma_transfer_direction direction,
+					    unsigned long flags)
+{
+	struct scatterlist sg;
+	sg_init_table(&sg, 1);
+	sg.dma_address = addr;
+	sg.length = size;
+
+	return dmaengine_prep_slave_sg(chan, &sg, 1, direction, flags);
+}
+
+#else
+static inline bool stedma40_filter(struct dma_chan *chan, void *data)
+{
+	return false;
+}
+
+static inline struct
+dma_async_tx_descriptor *stedma40_slave_mem(struct dma_chan *chan,
+					    dma_addr_t addr,
+					    unsigned int size,
+					    enum dma_transfer_direction direction,
+					    unsigned long flags)
+{
+	return NULL;
+}
+#endif
+
+#endif
diff --git a/sound/soc/ux500/ux500_pcm.c b/sound/soc/ux500/ux500_pcm.c
index 1a04e248453c..b55b79f7536c 100644
--- a/sound/soc/ux500/ux500_pcm.c
+++ b/sound/soc/ux500/ux500_pcm.c
@@ -18,8 +18,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/slab.h>
-
-#include <plat/ste_dma40.h>
+#include <linux/platform_data/dma-ste-dma40.h>
 
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
-- 
cgit v1.2.3-55-g7522


From 694e33a7f42de7dcc8b43c3990c597b19ef9b438 Mon Sep 17 00:00:00 2001
From: Linus Walleij
Date: Thu, 18 Oct 2012 14:01:25 +0200
Subject: ARM: plat-nomadik: move MTU, kill plat-nomadik

This moves the MTU timer driver from arch/arm/plat-nomadik
to drivers/clocksource and moves the header file to the
platform_data directory.

As this moves the last file being compiled to an object out
of arch/arm/plat-nomadik, we have to "turn off the light"
and delete the plat-nomadik directory, because it is not
allowed to have an empty Makefile in a plat-* directory.
This is probably also a desired side effect of depopulating
the arch/arm directory of drivers. Luckily we have just
deleted all the <plat/*> include files prior to this so
by moving the last one we may delete the directory.

After this all the Ux500 and Nomadik device drivers live
outside of the arch/arm hierarchy.

Cc: Alessandro Rubini <rubini@unipv.it>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/arm/Kconfig                                   |   1 -
 arch/arm/Makefile                                  |   1 -
 arch/arm/mach-nomadik/Kconfig                      |   2 +-
 arch/arm/mach-nomadik/board-nhk8815.c              |   6 +-
 arch/arm/mach-ux500/Kconfig                        |   2 +-
 arch/arm/mach-ux500/timer.c                        |   3 +-
 arch/arm/plat-nomadik/Kconfig                      |  29 ---
 arch/arm/plat-nomadik/Makefile                     |   5 -
 arch/arm/plat-nomadik/include/plat/mtu.h           |   9 -
 arch/arm/plat-nomadik/timer.c                      | 224 ---------------------
 drivers/char/hw_random/Kconfig                     |   2 +-
 drivers/clocksource/Kconfig                        |  17 +-
 drivers/clocksource/Makefile                       |   1 +
 drivers/clocksource/nomadik-mtu.c                  | 224 +++++++++++++++++++++
 drivers/input/keyboard/Kconfig                     |   2 +-
 drivers/mtd/nand/Kconfig                           |   2 +-
 .../linux/platform_data/clocksource-nomadik-mtu.h  |   9 +
 17 files changed, 258 insertions(+), 281 deletions(-)
 delete mode 100644 arch/arm/plat-nomadik/Kconfig
 delete mode 100644 arch/arm/plat-nomadik/Makefile
 delete mode 100644 arch/arm/plat-nomadik/include/plat/mtu.h
 delete mode 100644 arch/arm/plat-nomadik/timer.c
 create mode 100644 drivers/clocksource/nomadik-mtu.c
 create mode 100644 include/linux/platform_data/clocksource-nomadik-mtu.h

(limited to 'include')

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ade7e924bef5..8dae1e016ac8 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1065,7 +1065,6 @@ source "arch/arm/mach-mxs/Kconfig"
 source "arch/arm/mach-netx/Kconfig"
 
 source "arch/arm/mach-nomadik/Kconfig"
-source "arch/arm/plat-nomadik/Kconfig"
 
 source "arch/arm/plat-omap/Kconfig"
 
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 5f914fca911b..89087d599ad2 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -201,7 +201,6 @@ plat-$(CONFIG_ARCH_OMAP)	+= omap
 plat-$(CONFIG_ARCH_S3C64XX)	+= samsung
 plat-$(CONFIG_ARCH_ZYNQ)	+= versatile
 plat-$(CONFIG_PLAT_IOP)		+= iop
-plat-$(CONFIG_PLAT_NOMADIK)	+= nomadik
 plat-$(CONFIG_PLAT_ORION)	+= orion
 plat-$(CONFIG_PLAT_PXA)		+= pxa
 plat-$(CONFIG_PLAT_S3C24XX)	+= s3c24xx samsung
diff --git a/arch/arm/mach-nomadik/Kconfig b/arch/arm/mach-nomadik/Kconfig
index c744946ef022..706dc5727bbe 100644
--- a/arch/arm/mach-nomadik/Kconfig
+++ b/arch/arm/mach-nomadik/Kconfig
@@ -4,7 +4,7 @@ menu "Nomadik boards"
 
 config MACH_NOMADIK_8815NHK
 	bool "ST 8815 Nomadik Hardware Kit (evaluation board)"
-	select HAS_MTU
+	select CLKSRC_NOMADIK_MTU
 	select NOMADIK_8815
 
 endmenu
diff --git a/arch/arm/mach-nomadik/board-nhk8815.c b/arch/arm/mach-nomadik/board-nhk8815.c
index 16f10e04a805..5ccdf53c5a9d 100644
--- a/arch/arm/mach-nomadik/board-nhk8815.c
+++ b/arch/arm/mach-nomadik/board-nhk8815.c
@@ -25,16 +25,14 @@
 #include <linux/io.h>
 #include <linux/pinctrl/machine.h>
 #include <linux/platform_data/pinctrl-nomadik.h>
+#include <linux/platform_data/clocksource-nomadik-mtu.h>
+#include <linux/platform_data/mtd-nomadik-nand.h>
 #include <asm/hardware/vic.h>
 #include <asm/sizes.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/time.h>
-
-#include <plat/mtu.h>
-
-#include <linux/platform_data/mtd-nomadik-nand.h>
 #include <mach/fsmc.h>
 #include <mach/irqs.h>
 
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index e8c3f0d70ca6..5dea90636d94 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -7,8 +7,8 @@ config UX500_SOC_COMMON
 	select ARM_ERRATA_764369 if SMP
 	select ARM_GIC
 	select CACHE_L2X0
+	select CLKSRC_NOMADIK_MTU
 	select COMMON_CLK
-	select HAS_MTU
 	select PINCTRL
 	select PINCTRL_NOMADIK
 	select PL310_ERRATA_753970 if CACHE_PL310
diff --git a/arch/arm/mach-ux500/timer.c b/arch/arm/mach-ux500/timer.c
index 20d02fa01ec3..875309acb022 100644
--- a/arch/arm/mach-ux500/timer.c
+++ b/arch/arm/mach-ux500/timer.c
@@ -9,11 +9,10 @@
 #include <linux/clksrc-dbx500-prcmu.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/platform_data/clocksource-nomadik-mtu.h>
 
 #include <asm/smp_twd.h>
 
-#include <plat/mtu.h>
-
 #include <mach/setup.h>
 #include <mach/hardware.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/plat-nomadik/Kconfig b/arch/arm/plat-nomadik/Kconfig
deleted file mode 100644
index 19f55cae5d73..000000000000
--- a/arch/arm/plat-nomadik/Kconfig
+++ /dev/null
@@ -1,29 +0,0 @@
-# We keep common IP's here for Nomadik and other similar
-# familiy of processors from ST-Ericsson. At the moment we have
-# just MTU, others to follow soon.
-
-config PLAT_NOMADIK
-	bool
-	depends on ARCH_NOMADIK || ARCH_U8500
-	default y
-	select CLKSRC_MMIO
-	help
-	  Common platform code for Nomadik and other ST-Ericsson
-	  platforms.
-
-if PLAT_NOMADIK
-
-config HAS_MTU
-	bool
-	help
-	  Support for Multi Timer Unit. MTU provides access
-	  to multiple interrupt generating programmable
-	  32-bit free running decrementing counters.
-
-config NOMADIK_MTU_SCHED_CLOCK
-	bool
-	depends on HAS_MTU
-	help
-	  Use the Multi Timer Unit as the sched_clock.
-
-endif
diff --git a/arch/arm/plat-nomadik/Makefile b/arch/arm/plat-nomadik/Makefile
deleted file mode 100644
index 37c7cdd0f8f0..000000000000
--- a/arch/arm/plat-nomadik/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# arch/arm/plat-nomadik/Makefile
-# Copyright 2009 ST-Ericsson
-# Licensed under GPLv2
-
-obj-$(CONFIG_HAS_MTU)	+= timer.o
diff --git a/arch/arm/plat-nomadik/include/plat/mtu.h b/arch/arm/plat-nomadik/include/plat/mtu.h
deleted file mode 100644
index 80088973b734..000000000000
--- a/arch/arm/plat-nomadik/include/plat/mtu.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __PLAT_MTU_H
-#define __PLAT_MTU_H
-
-void nmdk_timer_init(void __iomem *base, int irq);
-void nmdk_clkevt_reset(void);
-void nmdk_clksrc_reset(void);
-
-#endif /* __PLAT_MTU_H */
-
diff --git a/arch/arm/plat-nomadik/timer.c b/arch/arm/plat-nomadik/timer.c
deleted file mode 100644
index f9114306657b..000000000000
--- a/arch/arm/plat-nomadik/timer.c
+++ /dev/null
@@ -1,224 +0,0 @@
-/*
- *  linux/arch/arm/plat-nomadik/timer.c
- *
- * Copyright (C) 2008 STMicroelectronics
- * Copyright (C) 2010 Alessandro Rubini
- * Copyright (C) 2010 Linus Walleij for ST-Ericsson
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2, as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/io.h>
-#include <linux/clockchips.h>
-#include <linux/clk.h>
-#include <linux/jiffies.h>
-#include <linux/err.h>
-#include <asm/mach/time.h>
-#include <asm/sched_clock.h>
-
-/*
- * The MTU device hosts four different counters, with 4 set of
- * registers. These are register names.
- */
-
-#define MTU_IMSC	0x00	/* Interrupt mask set/clear */
-#define MTU_RIS		0x04	/* Raw interrupt status */
-#define MTU_MIS		0x08	/* Masked interrupt status */
-#define MTU_ICR		0x0C	/* Interrupt clear register */
-
-/* per-timer registers take 0..3 as argument */
-#define MTU_LR(x)	(0x10 + 0x10 * (x) + 0x00)	/* Load value */
-#define MTU_VAL(x)	(0x10 + 0x10 * (x) + 0x04)	/* Current value */
-#define MTU_CR(x)	(0x10 + 0x10 * (x) + 0x08)	/* Control reg */
-#define MTU_BGLR(x)	(0x10 + 0x10 * (x) + 0x0c)	/* At next overflow */
-
-/* bits for the control register */
-#define MTU_CRn_ENA		0x80
-#define MTU_CRn_PERIODIC	0x40	/* if 0 = free-running */
-#define MTU_CRn_PRESCALE_MASK	0x0c
-#define MTU_CRn_PRESCALE_1		0x00
-#define MTU_CRn_PRESCALE_16		0x04
-#define MTU_CRn_PRESCALE_256		0x08
-#define MTU_CRn_32BITS		0x02
-#define MTU_CRn_ONESHOT		0x01	/* if 0 = wraps reloading from BGLR*/
-
-/* Other registers are usual amba/primecell registers, currently not used */
-#define MTU_ITCR	0xff0
-#define MTU_ITOP	0xff4
-
-#define MTU_PERIPH_ID0	0xfe0
-#define MTU_PERIPH_ID1	0xfe4
-#define MTU_PERIPH_ID2	0xfe8
-#define MTU_PERIPH_ID3	0xfeC
-
-#define MTU_PCELL0	0xff0
-#define MTU_PCELL1	0xff4
-#define MTU_PCELL2	0xff8
-#define MTU_PCELL3	0xffC
-
-static void __iomem *mtu_base;
-static bool clkevt_periodic;
-static u32 clk_prescale;
-static u32 nmdk_cycle;		/* write-once */
-
-#ifdef CONFIG_NOMADIK_MTU_SCHED_CLOCK
-/*
- * Override the global weak sched_clock symbol with this
- * local implementation which uses the clocksource to get some
- * better resolution when scheduling the kernel.
- */
-static u32 notrace nomadik_read_sched_clock(void)
-{
-	if (unlikely(!mtu_base))
-		return 0;
-
-	return -readl(mtu_base + MTU_VAL(0));
-}
-#endif
-
-/* Clockevent device: use one-shot mode */
-static int nmdk_clkevt_next(unsigned long evt, struct clock_event_device *ev)
-{
-	writel(1 << 1, mtu_base + MTU_IMSC);
-	writel(evt, mtu_base + MTU_LR(1));
-	/* Load highest value, enable device, enable interrupts */
-	writel(MTU_CRn_ONESHOT | clk_prescale |
-	       MTU_CRn_32BITS | MTU_CRn_ENA,
-	       mtu_base + MTU_CR(1));
-
-	return 0;
-}
-
-void nmdk_clkevt_reset(void)
-{
-	if (clkevt_periodic) {
-		/* Timer: configure load and background-load, and fire it up */
-		writel(nmdk_cycle, mtu_base + MTU_LR(1));
-		writel(nmdk_cycle, mtu_base + MTU_BGLR(1));
-
-		writel(MTU_CRn_PERIODIC | clk_prescale |
-		       MTU_CRn_32BITS | MTU_CRn_ENA,
-		       mtu_base + MTU_CR(1));
-		writel(1 << 1, mtu_base + MTU_IMSC);
-	} else {
-		/* Generate an interrupt to start the clockevent again */
-		(void) nmdk_clkevt_next(nmdk_cycle, NULL);
-	}
-}
-
-static void nmdk_clkevt_mode(enum clock_event_mode mode,
-			     struct clock_event_device *dev)
-{
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		clkevt_periodic = true;
-		nmdk_clkevt_reset();
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		clkevt_periodic = false;
-		break;
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_UNUSED:
-		writel(0, mtu_base + MTU_IMSC);
-		/* disable timer */
-		writel(0, mtu_base + MTU_CR(1));
-		/* load some high default value */
-		writel(0xffffffff, mtu_base + MTU_LR(1));
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
-}
-
-static struct clock_event_device nmdk_clkevt = {
-	.name		= "mtu_1",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.rating		= 200,
-	.set_mode	= nmdk_clkevt_mode,
-	.set_next_event	= nmdk_clkevt_next,
-};
-
-/*
- * IRQ Handler for timer 1 of the MTU block.
- */
-static irqreturn_t nmdk_timer_interrupt(int irq, void *dev_id)
-{
-	struct clock_event_device *evdev = dev_id;
-
-	writel(1 << 1, mtu_base + MTU_ICR); /* Interrupt clear reg */
-	evdev->event_handler(evdev);
-	return IRQ_HANDLED;
-}
-
-static struct irqaction nmdk_timer_irq = {
-	.name		= "Nomadik Timer Tick",
-	.flags		= IRQF_DISABLED | IRQF_TIMER,
-	.handler	= nmdk_timer_interrupt,
-	.dev_id		= &nmdk_clkevt,
-};
-
-void nmdk_clksrc_reset(void)
-{
-	/* Disable */
-	writel(0, mtu_base + MTU_CR(0));
-
-	/* ClockSource: configure load and background-load, and fire it up */
-	writel(nmdk_cycle, mtu_base + MTU_LR(0));
-	writel(nmdk_cycle, mtu_base + MTU_BGLR(0));
-
-	writel(clk_prescale | MTU_CRn_32BITS | MTU_CRn_ENA,
-	       mtu_base + MTU_CR(0));
-}
-
-void __init nmdk_timer_init(void __iomem *base, int irq)
-{
-	unsigned long rate;
-	struct clk *clk0;
-
-	mtu_base = base;
-	clk0 = clk_get_sys("mtu0", NULL);
-	BUG_ON(IS_ERR(clk0));
-	BUG_ON(clk_prepare(clk0) < 0);
-	BUG_ON(clk_enable(clk0) < 0);
-
-	/*
-	 * Tick rate is 2.4MHz for Nomadik and 2.4Mhz, 100MHz or 133 MHz
-	 * for ux500.
-	 * Use a divide-by-16 counter if the tick rate is more than 32MHz.
-	 * At 32 MHz, the timer (with 32 bit counter) can be programmed
-	 * to wake-up at a max 127s a head in time. Dividing a 2.4 MHz timer
-	 * with 16 gives too low timer resolution.
-	 */
-	rate = clk_get_rate(clk0);
-	if (rate > 32000000) {
-		rate /= 16;
-		clk_prescale = MTU_CRn_PRESCALE_16;
-	} else {
-		clk_prescale = MTU_CRn_PRESCALE_1;
-	}
-
-	/* Cycles for periodic mode */
-	nmdk_cycle = DIV_ROUND_CLOSEST(rate, HZ);
-
-
-	/* Timer 0 is the free running clocksource */
-	nmdk_clksrc_reset();
-
-	if (clocksource_mmio_init(mtu_base + MTU_VAL(0), "mtu_0",
-			rate, 200, 32, clocksource_mmio_readl_down))
-		pr_err("timer: failed to initialize clock source %s\n",
-		       "mtu_0");
-
-#ifdef CONFIG_NOMADIK_MTU_SCHED_CLOCK
-	setup_sched_clock(nomadik_read_sched_clock, 32, rate);
-#endif
-
-	/* Timer 1 is used for events, register irq and clockevents */
-	setup_irq(irq, &nmdk_timer_irq);
-	nmdk_clkevt.cpumask = cpumask_of(0);
-	clockevents_config_and_register(&nmdk_clkevt, rate, 2, 0xffffffffU);
-}
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index fbd9b2b850ef..5bc09eec9bbb 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -216,7 +216,7 @@ config HW_RANDOM_MXC_RNGA
 
 config HW_RANDOM_NOMADIK
 	tristate "ST-Ericsson Nomadik Random Number Generator support"
-	depends on HW_RANDOM && PLAT_NOMADIK
+	depends on HW_RANDOM && ARCH_NOMADIK
 	---help---
 	  This driver provides kernel-side support for the Random Number
 	  Generator hardware found on ST-Ericsson SoCs (8815 and 8500).
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 6a78073c3808..c9f67de8b7b4 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -22,6 +22,21 @@ config DW_APB_TIMER_OF
 config ARMADA_370_XP_TIMER
 	bool
 
+config CLKSRC_NOMADIK_MTU
+	bool
+	depends on (ARCH_NOMADIK || ARCH_U8500)
+	select CLKSRC_MMIO
+	help
+	  Support for Multi Timer Unit. MTU provides access
+	  to multiple interrupt generating programmable
+	  32-bit free running decrementing counters.
+
+config CLKSRC_NOMADIK_MTU_SCHED_CLOCK
+	bool
+	depends on CLKSRC_NOMADIK_MTU
+	help
+	  Use the Multi Timer Unit as the sched_clock.
+
 config CLKSRC_DBX500_PRCMU
 	bool "Clocksource PRCMU Timer"
 	depends on UX500_SOC_DB8500
@@ -31,7 +46,7 @@ config CLKSRC_DBX500_PRCMU
 
 config CLKSRC_DBX500_PRCMU_SCHED_CLOCK
 	bool "Clocksource PRCMU Timer sched_clock"
-	depends on (CLKSRC_DBX500_PRCMU && !NOMADIK_MTU_SCHED_CLOCK)
+	depends on (CLKSRC_DBX500_PRCMU && !CLKSRC_NOMADIK_MTU_SCHED_CLOCK)
 	default y
 	help
 	  Use the always on PRCMU Timer as sched_clock
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 603be366f762..24fb888ee0a2 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_CLKBLD_I8253)	+= i8253.o
 obj-$(CONFIG_CLKSRC_MMIO)	+= mmio.o
 obj-$(CONFIG_DW_APB_TIMER)	+= dw_apb_timer.o
 obj-$(CONFIG_DW_APB_TIMER_OF)	+= dw_apb_timer_of.o
+obj-$(CONFIG_CLKSRC_NOMADIK_MTU)	+= nomadik-mtu.o
 obj-$(CONFIG_CLKSRC_DBX500_PRCMU)	+= clksrc-dbx500-prcmu.o
 obj-$(CONFIG_ARMADA_370_XP_TIMER)	+= time-armada-370-xp.o
 obj-$(CONFIG_ARCH_BCM2835)	+= bcm2835_timer.o
diff --git a/drivers/clocksource/nomadik-mtu.c b/drivers/clocksource/nomadik-mtu.c
new file mode 100644
index 000000000000..23c780ba0d35
--- /dev/null
+++ b/drivers/clocksource/nomadik-mtu.c
@@ -0,0 +1,224 @@
+/*
+ * Copyright (C) 2008 STMicroelectronics
+ * Copyright (C) 2010 Alessandro Rubini
+ * Copyright (C) 2010 Linus Walleij for ST-Ericsson
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2, as
+ * published by the Free Software Foundation.
+ */
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/clk.h>
+#include <linux/jiffies.h>
+#include <linux/err.h>
+#include <linux/platform_data/clocksource-nomadik-mtu.h>
+#include <asm/mach/time.h>
+#include <asm/sched_clock.h>
+
+/*
+ * The MTU device hosts four different counters, with 4 set of
+ * registers. These are register names.
+ */
+
+#define MTU_IMSC	0x00	/* Interrupt mask set/clear */
+#define MTU_RIS		0x04	/* Raw interrupt status */
+#define MTU_MIS		0x08	/* Masked interrupt status */
+#define MTU_ICR		0x0C	/* Interrupt clear register */
+
+/* per-timer registers take 0..3 as argument */
+#define MTU_LR(x)	(0x10 + 0x10 * (x) + 0x00)	/* Load value */
+#define MTU_VAL(x)	(0x10 + 0x10 * (x) + 0x04)	/* Current value */
+#define MTU_CR(x)	(0x10 + 0x10 * (x) + 0x08)	/* Control reg */
+#define MTU_BGLR(x)	(0x10 + 0x10 * (x) + 0x0c)	/* At next overflow */
+
+/* bits for the control register */
+#define MTU_CRn_ENA		0x80
+#define MTU_CRn_PERIODIC	0x40	/* if 0 = free-running */
+#define MTU_CRn_PRESCALE_MASK	0x0c
+#define MTU_CRn_PRESCALE_1		0x00
+#define MTU_CRn_PRESCALE_16		0x04
+#define MTU_CRn_PRESCALE_256		0x08
+#define MTU_CRn_32BITS		0x02
+#define MTU_CRn_ONESHOT		0x01	/* if 0 = wraps reloading from BGLR*/
+
+/* Other registers are usual amba/primecell registers, currently not used */
+#define MTU_ITCR	0xff0
+#define MTU_ITOP	0xff4
+
+#define MTU_PERIPH_ID0	0xfe0
+#define MTU_PERIPH_ID1	0xfe4
+#define MTU_PERIPH_ID2	0xfe8
+#define MTU_PERIPH_ID3	0xfeC
+
+#define MTU_PCELL0	0xff0
+#define MTU_PCELL1	0xff4
+#define MTU_PCELL2	0xff8
+#define MTU_PCELL3	0xffC
+
+static void __iomem *mtu_base;
+static bool clkevt_periodic;
+static u32 clk_prescale;
+static u32 nmdk_cycle;		/* write-once */
+
+#ifdef CONFIG_NOMADIK_MTU_SCHED_CLOCK
+/*
+ * Override the global weak sched_clock symbol with this
+ * local implementation which uses the clocksource to get some
+ * better resolution when scheduling the kernel.
+ */
+static u32 notrace nomadik_read_sched_clock(void)
+{
+	if (unlikely(!mtu_base))
+		return 0;
+
+	return -readl(mtu_base + MTU_VAL(0));
+}
+#endif
+
+/* Clockevent device: use one-shot mode */
+static int nmdk_clkevt_next(unsigned long evt, struct clock_event_device *ev)
+{
+	writel(1 << 1, mtu_base + MTU_IMSC);
+	writel(evt, mtu_base + MTU_LR(1));
+	/* Load highest value, enable device, enable interrupts */
+	writel(MTU_CRn_ONESHOT | clk_prescale |
+	       MTU_CRn_32BITS | MTU_CRn_ENA,
+	       mtu_base + MTU_CR(1));
+
+	return 0;
+}
+
+void nmdk_clkevt_reset(void)
+{
+	if (clkevt_periodic) {
+		/* Timer: configure load and background-load, and fire it up */
+		writel(nmdk_cycle, mtu_base + MTU_LR(1));
+		writel(nmdk_cycle, mtu_base + MTU_BGLR(1));
+
+		writel(MTU_CRn_PERIODIC | clk_prescale |
+		       MTU_CRn_32BITS | MTU_CRn_ENA,
+		       mtu_base + MTU_CR(1));
+		writel(1 << 1, mtu_base + MTU_IMSC);
+	} else {
+		/* Generate an interrupt to start the clockevent again */
+		(void) nmdk_clkevt_next(nmdk_cycle, NULL);
+	}
+}
+
+static void nmdk_clkevt_mode(enum clock_event_mode mode,
+			     struct clock_event_device *dev)
+{
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		clkevt_periodic = true;
+		nmdk_clkevt_reset();
+		break;
+	case CLOCK_EVT_MODE_ONESHOT:
+		clkevt_periodic = false;
+		break;
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	case CLOCK_EVT_MODE_UNUSED:
+		writel(0, mtu_base + MTU_IMSC);
+		/* disable timer */
+		writel(0, mtu_base + MTU_CR(1));
+		/* load some high default value */
+		writel(0xffffffff, mtu_base + MTU_LR(1));
+		break;
+	case CLOCK_EVT_MODE_RESUME:
+		break;
+	}
+}
+
+static struct clock_event_device nmdk_clkevt = {
+	.name		= "mtu_1",
+	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
+	.rating		= 200,
+	.set_mode	= nmdk_clkevt_mode,
+	.set_next_event	= nmdk_clkevt_next,
+};
+
+/*
+ * IRQ Handler for timer 1 of the MTU block.
+ */
+static irqreturn_t nmdk_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evdev = dev_id;
+
+	writel(1 << 1, mtu_base + MTU_ICR); /* Interrupt clear reg */
+	evdev->event_handler(evdev);
+	return IRQ_HANDLED;
+}
+
+static struct irqaction nmdk_timer_irq = {
+	.name		= "Nomadik Timer Tick",
+	.flags		= IRQF_DISABLED | IRQF_TIMER,
+	.handler	= nmdk_timer_interrupt,
+	.dev_id		= &nmdk_clkevt,
+};
+
+void nmdk_clksrc_reset(void)
+{
+	/* Disable */
+	writel(0, mtu_base + MTU_CR(0));
+
+	/* ClockSource: configure load and background-load, and fire it up */
+	writel(nmdk_cycle, mtu_base + MTU_LR(0));
+	writel(nmdk_cycle, mtu_base + MTU_BGLR(0));
+
+	writel(clk_prescale | MTU_CRn_32BITS | MTU_CRn_ENA,
+	       mtu_base + MTU_CR(0));
+}
+
+void __init nmdk_timer_init(void __iomem *base, int irq)
+{
+	unsigned long rate;
+	struct clk *clk0;
+
+	mtu_base = base;
+	clk0 = clk_get_sys("mtu0", NULL);
+	BUG_ON(IS_ERR(clk0));
+	BUG_ON(clk_prepare(clk0) < 0);
+	BUG_ON(clk_enable(clk0) < 0);
+
+	/*
+	 * Tick rate is 2.4MHz for Nomadik and 2.4Mhz, 100MHz or 133 MHz
+	 * for ux500.
+	 * Use a divide-by-16 counter if the tick rate is more than 32MHz.
+	 * At 32 MHz, the timer (with 32 bit counter) can be programmed
+	 * to wake-up at a max 127s a head in time. Dividing a 2.4 MHz timer
+	 * with 16 gives too low timer resolution.
+	 */
+	rate = clk_get_rate(clk0);
+	if (rate > 32000000) {
+		rate /= 16;
+		clk_prescale = MTU_CRn_PRESCALE_16;
+	} else {
+		clk_prescale = MTU_CRn_PRESCALE_1;
+	}
+
+	/* Cycles for periodic mode */
+	nmdk_cycle = DIV_ROUND_CLOSEST(rate, HZ);
+
+
+	/* Timer 0 is the free running clocksource */
+	nmdk_clksrc_reset();
+
+	if (clocksource_mmio_init(mtu_base + MTU_VAL(0), "mtu_0",
+			rate, 200, 32, clocksource_mmio_readl_down))
+		pr_err("timer: failed to initialize clock source %s\n",
+		       "mtu_0");
+
+#ifdef CONFIG_NOMADIK_MTU_SCHED_CLOCK
+	setup_sched_clock(nomadik_read_sched_clock, 32, rate);
+#endif
+
+	/* Timer 1 is used for events, register irq and clockevents */
+	setup_irq(irq, &nmdk_timer_irq);
+	nmdk_clkevt.cpumask = cpumask_of(0);
+	clockevents_config_and_register(&nmdk_clkevt, rate, 2, 0xffffffffU);
+}
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index b4b65af8612a..855fc52945db 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -408,7 +408,7 @@ config KEYBOARD_NEWTON
 
 config KEYBOARD_NOMADIK
 	tristate "ST-Ericsson Nomadik SKE keyboard"
-	depends on PLAT_NOMADIK
+	depends on (ARCH_NOMADIK || ARCH_U8500)
 	select INPUT_MATRIXKMAP
 	help
 	  Say Y here if you want to use a keypad provided on the SKE controller
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 4883139460be..e4f57482f0ae 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -559,7 +559,7 @@ config MTD_NAND_JZ4740
 
 config MTD_NAND_FSMC
 	tristate "Support for NAND on ST Micros FSMC"
-	depends on PLAT_SPEAR || PLAT_NOMADIK || MACH_U300
+	depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300
 	help
 	  Enables support for NAND Flash chips on the ST Microelectronics
 	  Flexible Static Memory Controller (FSMC)
diff --git a/include/linux/platform_data/clocksource-nomadik-mtu.h b/include/linux/platform_data/clocksource-nomadik-mtu.h
new file mode 100644
index 000000000000..80088973b734
--- /dev/null
+++ b/include/linux/platform_data/clocksource-nomadik-mtu.h
@@ -0,0 +1,9 @@
+#ifndef __PLAT_MTU_H
+#define __PLAT_MTU_H
+
+void nmdk_timer_init(void __iomem *base, int irq);
+void nmdk_clkevt_reset(void);
+void nmdk_clksrc_reset(void);
+
+#endif /* __PLAT_MTU_H */
+
-- 
cgit v1.2.3-55-g7522


From ba350fbc53b5798104b3fc245bb3c3461a4ef8dc Mon Sep 17 00:00:00 2001
From: Arend van Spriel
Date: Mon, 5 Nov 2012 15:29:09 +0100
Subject: wireless: add peer-to-peer related definitions

The Peer-to-Peer IE is vendor-specific IE identified by WiFi Alliance
OUI and specific P2P OUI type. The payload of this IE consists of
so-called P2P attributes. This patch adds definitions for processing
these attributes.

Reviewed-by: Hante Meuleman <meuleman@broadcom.com>
Reviewed-by: Pieter-Paul Giesberts <pieterpg@broadcom.com>
Reviewed-by: Franky (Zhenhui) Lin <frankyl@broadcom.com>
Signed-off-by: Arend van Spriel <arend@broadcom.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 85764a900731..4530d4960953 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -905,6 +905,38 @@ struct ieee80211_tdls_data {
 	} u;
 } __packed;
 
+/*
+ * Peer-to-Peer IE attribute related definitions.
+ */
+/**
+ * enum ieee80211_p2p_attr_id - identifies type of peer-to-peer attribute.
+ */
+enum ieee80211_p2p_attr_id {
+	IEEE80211_P2P_ATTR_STATUS = 0,
+	IEEE80211_P2P_ATTR_MINOR_REASON,
+	IEEE80211_P2P_ATTR_CAPABILITY,
+	IEEE80211_P2P_ATTR_DEVICE_ID,
+	IEEE80211_P2P_ATTR_GO_INTENT,
+	IEEE80211_P2P_ATTR_GO_CONFIG_TIMEOUT,
+	IEEE80211_P2P_ATTR_LISTEN_CHANNEL,
+	IEEE80211_P2P_ATTR_GROUP_BSSID,
+	IEEE80211_P2P_ATTR_EXT_LISTEN_TIMING,
+	IEEE80211_P2P_ATTR_INTENDED_IFACE_ADDR,
+	IEEE80211_P2P_ATTR_MANAGABILITY,
+	IEEE80211_P2P_ATTR_CHANNEL_LIST,
+	IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
+	IEEE80211_P2P_ATTR_DEVICE_INFO,
+	IEEE80211_P2P_ATTR_GROUP_INFO,
+	IEEE80211_P2P_ATTR_GROUP_ID,
+	IEEE80211_P2P_ATTR_INTERFACE,
+	IEEE80211_P2P_ATTR_OPER_CHANNEL,
+	IEEE80211_P2P_ATTR_INVITE_FLAGS,
+	/* 19 - 220: Reserved */
+	IEEE80211_P2P_ATTR_VENDOR_SPECIFIC = 221,
+
+	IEEE80211_P2P_ATTR_MAX
+};
+
 /**
  * struct ieee80211_bar - HT Block Ack Request
  *
-- 
cgit v1.2.3-55-g7522


From f4e583c8935c6f52f9385ee7cfbea8f65c66a737 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli
Date: Fri, 2 Nov 2012 13:27:48 +0100
Subject: nl/cfg80211: add the NL80211_CMD_SET_MCAST_RATE command

This command triggers a new callback: set_mcast_rate(). It enables
the user to change the rate used to send multicast frames for vif
configured as IBSS or MESH_POINT

Signed-off-by: Antonio Quartulli <ordex@autistici.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  6 ++++++
 include/uapi/linux/nl80211.h |  5 +++++
 net/wireless/nl80211.c       | 39 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 8034a4268fcb..cee791fd4cff 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1545,6 +1545,9 @@ struct cfg80211_gtk_rekey_data {
  *	to a merge.
  * @leave_ibss: Leave the IBSS.
  *
+ * @set_mcast_rate: Set the specified multicast rate (only if vif is in ADHOC or
+ *	MESH mode)
+ *
  * @set_wiphy_params: Notify that wiphy parameters have changed;
  *	@changed bitfield (see &enum wiphy_params_flags) describes which values
  *	have changed. The actual parameter values are available in
@@ -1749,6 +1752,9 @@ struct cfg80211_ops {
 			     struct cfg80211_ibss_params *params);
 	int	(*leave_ibss)(struct wiphy *wiphy, struct net_device *dev);
 
+	int	(*set_mcast_rate)(struct wiphy *wiphy, struct net_device *dev,
+				  int rate[IEEE80211_NUM_BANDS]);
+
 	int	(*set_wiphy_params)(struct wiphy *wiphy, u32 changed);
 
 	int	(*set_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev,
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 4c5f6748ed7d..cbd2d6bb907a 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -578,6 +578,9 @@
  *	station, due to particular reason. %NL80211_ATTR_CONN_FAILED_REASON
  *	is used for this.
  *
+ * @NL80211_CMD_SET_MCAST_RATE: Change the rate used to send multicast frames
+ *	for IBSS or MESH vif.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -726,6 +729,8 @@ enum nl80211_commands {
 
 	NL80211_CMD_CONN_FAILED,
 
+	NL80211_CMD_SET_MCAST_RATE,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 87d4670ee53a..9b0a3b8fd20a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1110,6 +1110,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 portid, u32 seq, int flag
 			goto nla_put_failure;
 	}
 	CMD(start_p2p_device, START_P2P_DEVICE);
+	CMD(set_mcast_rate, SET_MCAST_RATE);
 
 #ifdef CONFIG_NL80211_TESTMODE
 	CMD(testmode_cmd, TESTMODE);
@@ -5448,6 +5449,36 @@ static int nl80211_leave_ibss(struct sk_buff *skb, struct genl_info *info)
 	return cfg80211_leave_ibss(rdev, dev, false);
 }
 
+static int nl80211_set_mcast_rate(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	int mcast_rate[IEEE80211_NUM_BANDS];
+	u32 nla_rate;
+	int err;
+
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC &&
+	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT)
+		return -EOPNOTSUPP;
+
+	if (!rdev->ops->set_mcast_rate)
+		return -EOPNOTSUPP;
+
+	memset(mcast_rate, 0, sizeof(mcast_rate));
+
+	if (!info->attrs[NL80211_ATTR_MCAST_RATE])
+		return -EINVAL;
+
+	nla_rate = nla_get_u32(info->attrs[NL80211_ATTR_MCAST_RATE]);
+	if (!nl80211_parse_mcast_rate(rdev, mcast_rate, nla_rate))
+		return -EINVAL;
+
+	err = rdev->ops->set_mcast_rate(&rdev->wiphy, dev, mcast_rate);
+
+	return err;
+}
+
+
 #ifdef CONFIG_NL80211_TESTMODE
 static struct genl_multicast_group nl80211_testmode_mcgrp = {
 	.name = "testmode",
@@ -7629,6 +7660,14 @@ static struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_SET_MCAST_RATE,
+		.doit = nl80211_set_mcast_rate,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 static struct genl_multicast_group nl80211_mlme_mcgrp = {
-- 
cgit v1.2.3-55-g7522


From 37c73b5f323c973c1db6857494a6685260440be1 Mon Sep 17 00:00:00 2001
From: Ben Greear
Date: Fri, 26 Oct 2012 14:49:25 -0700
Subject: cfg80211: allow registering more than one beacon listener

The commit:

commit 5e760230e42cf759bd923457ca2753aacf2e656e
Author: Johannes Berg <johannes.berg@intel.com>
Date:   Fri Nov 4 11:18:17 2011 +0100

    cfg80211: allow registering to beacons

allowed only a single process to register for beacon events
per wiphy.  This breaks cases where a user may want two or
more VIFs on a wiphy and run a seperate hostapd process on
each vif.

This patch allows multiple beacon listeners, fixing the
regression.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  3 +-
 net/mac80211/rx.c      |  2 +-
 net/wireless/core.c    |  7 ++++
 net/wireless/core.h    |  7 +++-
 net/wireless/nl80211.c | 88 ++++++++++++++++++++++++++++++++++----------------
 5 files changed, 75 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index cee791fd4cff..10c9fc68d1af 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3560,7 +3560,6 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
  * @len: length of the frame
  * @freq: frequency the frame was received on
  * @sig_dbm: signal strength in mBm, or 0 if unknown
- * @gfp: allocation flags
  *
  * Use this function to report to userspace when a beacon was
  * received. It is not useful to call this when there is no
@@ -3568,7 +3567,7 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
  */
 void cfg80211_report_obss_beacon(struct wiphy *wiphy,
 				 const u8 *frame, size_t len,
-				 int freq, int sig_dbm, gfp_t gfp);
+				 int freq, int sig_dbm);
 
 /**
  * cfg80211_can_beacon_sec_chan - test if ht40 on extension channel can be used
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 38b382682cae..6ad330341b71 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2200,7 +2200,7 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx)
 
 		cfg80211_report_obss_beacon(rx->local->hw.wiphy,
 					    rx->skb->data, rx->skb->len,
-					    status->freq, sig, GFP_ATOMIC);
+					    status->freq, sig);
 		rx->flags |= IEEE80211_RX_BEACON_REPORTED;
 	}
 
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 26711f46a3be..14d990400354 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -326,6 +326,8 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 	mutex_init(&rdev->devlist_mtx);
 	mutex_init(&rdev->sched_scan_mtx);
 	INIT_LIST_HEAD(&rdev->wdev_list);
+	INIT_LIST_HEAD(&rdev->beacon_registrations);
+	spin_lock_init(&rdev->beacon_registrations_lock);
 	spin_lock_init(&rdev->bss_lock);
 	INIT_LIST_HEAD(&rdev->bss_list);
 	INIT_WORK(&rdev->scan_done_wk, __cfg80211_scan_done);
@@ -698,10 +700,15 @@ EXPORT_SYMBOL(wiphy_unregister);
 void cfg80211_dev_free(struct cfg80211_registered_device *rdev)
 {
 	struct cfg80211_internal_bss *scan, *tmp;
+	struct cfg80211_beacon_registration *reg, *treg;
 	rfkill_destroy(rdev->rfkill);
 	mutex_destroy(&rdev->mtx);
 	mutex_destroy(&rdev->devlist_mtx);
 	mutex_destroy(&rdev->sched_scan_mtx);
+	list_for_each_entry_safe(reg, treg, &rdev->beacon_registrations, list) {
+		list_del(&reg->list);
+		kfree(reg);
+	}
 	list_for_each_entry_safe(scan, tmp, &rdev->bss_list, list)
 		cfg80211_put_bss(&scan->pub);
 	kfree(rdev);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index b8eb743fe7da..e53831c876bb 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -55,7 +55,8 @@ struct cfg80211_registered_device {
 	int opencount; /* also protected by devlist_mtx */
 	wait_queue_head_t dev_wait;
 
-	u32 ap_beacons_nlportid;
+	struct list_head beacon_registrations;
+	spinlock_t beacon_registrations_lock;
 
 	/* protected by RTNL only */
 	int num_running_ifaces;
@@ -260,6 +261,10 @@ enum cfg80211_chan_mode {
 	CHAN_MODE_EXCLUSIVE,
 };
 
+struct cfg80211_beacon_registration {
+	struct list_head list;
+	u32 nlportid;
+};
 
 /* free object */
 extern void cfg80211_dev_free(struct cfg80211_registered_device *rdev);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 9b0a3b8fd20a..ba44f98c56d9 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6934,16 +6934,35 @@ static int nl80211_probe_client(struct sk_buff *skb,
 static int nl80211_register_beacons(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct cfg80211_beacon_registration *reg, *nreg;
+	int rv;
 
 	if (!(rdev->wiphy.flags & WIPHY_FLAG_REPORTS_OBSS))
 		return -EOPNOTSUPP;
 
-	if (rdev->ap_beacons_nlportid)
-		return -EBUSY;
+	nreg = kzalloc(sizeof(*nreg), GFP_KERNEL);
+	if (!nreg)
+		return -ENOMEM;
+
+	/* First, check if already registered. */
+	spin_lock_bh(&rdev->beacon_registrations_lock);
+	list_for_each_entry(reg, &rdev->beacon_registrations, list) {
+		if (reg->nlportid == info->snd_portid) {
+			rv = -EALREADY;
+			goto out_err;
+		}
+	}
+	/* Add it to the list */
+	nreg->nlportid = info->snd_portid;
+	list_add(&nreg->list, &rdev->beacon_registrations);
 
-	rdev->ap_beacons_nlportid = info->snd_portid;
+	spin_unlock_bh(&rdev->beacon_registrations_lock);
 
 	return 0;
+out_err:
+	spin_unlock_bh(&rdev->beacon_registrations_lock);
+	kfree(nreg);
+	return rv;
 }
 
 static int nl80211_start_p2p_device(struct sk_buff *skb, struct genl_info *info)
@@ -8957,43 +8976,46 @@ EXPORT_SYMBOL(cfg80211_probe_status);
 
 void cfg80211_report_obss_beacon(struct wiphy *wiphy,
 				 const u8 *frame, size_t len,
-				 int freq, int sig_dbm, gfp_t gfp)
+				 int freq, int sig_dbm)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
 	struct sk_buff *msg;
 	void *hdr;
-	u32 nlportid = ACCESS_ONCE(rdev->ap_beacons_nlportid);
+	struct cfg80211_beacon_registration *reg;
 
 	trace_cfg80211_report_obss_beacon(wiphy, frame, len, freq, sig_dbm);
 
-	if (!nlportid)
-		return;
-
-	msg = nlmsg_new(len + 100, gfp);
-	if (!msg)
-		return;
+	spin_lock_bh(&rdev->beacon_registrations_lock);
+	list_for_each_entry(reg, &rdev->beacon_registrations, list) {
+		msg = nlmsg_new(len + 100, GFP_ATOMIC);
+		if (!msg) {
+			spin_unlock_bh(&rdev->beacon_registrations_lock);
+			return;
+		}
 
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_FRAME);
-	if (!hdr) {
-		nlmsg_free(msg);
-		return;
-	}
+		hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_FRAME);
+		if (!hdr)
+			goto nla_put_failure;
 
-	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
-	    (freq &&
-	     nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, freq)) ||
-	    (sig_dbm &&
-	     nla_put_u32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm)) ||
-	    nla_put(msg, NL80211_ATTR_FRAME, len, frame))
-		goto nla_put_failure;
+		if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
+		    (freq &&
+		     nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, freq)) ||
+		    (sig_dbm &&
+		     nla_put_u32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm)) ||
+		    nla_put(msg, NL80211_ATTR_FRAME, len, frame))
+			goto nla_put_failure;
 
-	genlmsg_end(msg, hdr);
+		genlmsg_end(msg, hdr);
 
-	genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid);
+		genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, reg->nlportid);
+	}
+	spin_unlock_bh(&rdev->beacon_registrations_lock);
 	return;
 
  nla_put_failure:
-	genlmsg_cancel(msg, hdr);
+	spin_unlock_bh(&rdev->beacon_registrations_lock);
+	if (hdr)
+		genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
 }
 EXPORT_SYMBOL(cfg80211_report_obss_beacon);
@@ -9005,6 +9027,7 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 	struct netlink_notify *notify = _notify;
 	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
+	struct cfg80211_beacon_registration *reg, *tmp;
 
 	if (state != NETLINK_URELEASE)
 		return NOTIFY_DONE;
@@ -9014,8 +9037,17 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 	list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) {
 		list_for_each_entry_rcu(wdev, &rdev->wdev_list, list)
 			cfg80211_mlme_unregister_socket(wdev, notify->portid);
-		if (rdev->ap_beacons_nlportid == notify->portid)
-			rdev->ap_beacons_nlportid = 0;
+
+		spin_lock_bh(&rdev->beacon_registrations_lock);
+		list_for_each_entry_safe(reg, tmp, &rdev->beacon_registrations,
+					 list) {
+			if (reg->nlportid == notify->portid) {
+				list_del(&reg->list);
+				kfree(reg);
+				break;
+			}
+		}
+		spin_unlock_bh(&rdev->beacon_registrations_lock);
 	}
 
 	rcu_read_unlock();
-- 
cgit v1.2.3-55-g7522


From 3ecbf05be159a95e1d23ba9b3b21c5bc2941ba6b Mon Sep 17 00:00:00 2001
From: Pawel Moll
Date: Mon, 24 Sep 2012 14:55:40 +0100
Subject: mfd: Versatile Express config infrastructure

Versatile Express platform has an elaborated configuration system,
consisting of microcontrollers residing on the mother- and
daughterboards known as Motherboard/Daughterboard Configuration
Controller (MCC and DCC). The controllers are responsible for
the platform initialization (reset generation, flash programming,
FPGA bitfiles loading etc.) but also control clock generators,
voltage regulators, gather environmental data like temperature,
power consumption etc. Even the video output switch (FPGA) is
controlled that way.

Those devices are _not_ visible in the main address space and
the usual communication channel uses some kind of a bridge in
the peripheral block sending commands (requests) to the
controllers and receiving responses. It can take up to
500 microseconds for a transaction to be completed, therefore
it is important to provide a non-blocking interface to it.

This patch adds an abstraction of this infrastructure. Bridge
drivers can register themselves with the framework. Then,
a driver of a device can request an abstract "function" - the
request will be redirected to a bridge referred by thedd
"arm,vexpress,config-bridge" property of the device tree node.

Signed-off-by: Pawel Moll <pawel.moll@arm.com>
---
 Documentation/devicetree/bindings/arm/vexpress.txt |  68 ++++-
 drivers/mfd/Kconfig                                |   6 +
 drivers/mfd/Makefile                               |   1 +
 drivers/mfd/vexpress-config.c                      | 277 +++++++++++++++++++++
 include/linux/vexpress.h                           |  85 +++++++
 5 files changed, 436 insertions(+), 1 deletion(-)
 create mode 100644 drivers/mfd/vexpress-config.c
 create mode 100644 include/linux/vexpress.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/arm/vexpress.txt b/Documentation/devicetree/bindings/arm/vexpress.txt
index ec8b50cbb2e8..5d9996b9eabf 100644
--- a/Documentation/devicetree/bindings/arm/vexpress.txt
+++ b/Documentation/devicetree/bindings/arm/vexpress.txt
@@ -11,6 +11,10 @@ the motherboard file using a /include/ directive. As the motherboard
 can be initialized in one of two different configurations ("memory
 maps"), care must be taken to include the correct one.
 
+
+Root node
+---------
+
 Required properties in the root node:
 - compatible value:
 	compatible = "arm,vexpress,<model>", "arm,vexpress";
@@ -45,6 +49,10 @@ Optional properties in the root node:
   - Coretile Express A9x4 (V2P-CA9) HBI-0225:
 	arm,hbi = <0x225>;
 
+
+CPU nodes
+---------
+
 Top-level standard "cpus" node is required. It must contain a node
 with device_type = "cpu" property for every available core, eg.:
 
@@ -59,6 +67,52 @@ with device_type = "cpu" property for every available core, eg.:
 		};
 	};
 
+
+Configuration infrastructure
+----------------------------
+
+The platform has an elaborated configuration system, consisting of
+microcontrollers residing on the mother- and daughterboards known
+as Motherboard/Daughterboard Configuration Controller (MCC and DCC).
+The controllers are responsible for the platform initialization
+(reset generation, flash programming, FPGA bitfiles loading etc.)
+but also control clock generators, voltage regulators, gather
+environmental data like temperature, power consumption etc. Even
+the video output switch (FPGA) is controlled that way.
+
+Nodes describing devices controlled by this infrastructure should
+point at the bridge device node:
+- bridge phandle:
+	arm,vexpress,config-bridge = <phandle>;
+This property can be also defined in a parent node (eg. for a DCC)
+and is effective for all children.
+
+
+Platform topology
+-----------------
+
+As Versatile Express can be configured in number of physically
+different setups, the device tree should describe platform topology.
+Root node and main motherboard node must define the following
+property, describing physical location of the children nodes:
+- site number:
+	arm,vexpress,site = <number>;
+  where 0 means motherboard, 1 or 2 are daugtherboard sites,
+  0xf means "master" site (site containing main CPU tile)
+- when daughterboards are stacked on one site, their position
+  in the stack be be described with:
+	arm,vexpress,position = <number>;
+- when describing tiles consisting more than one DCC, its number
+  can be described with:
+	arm,vexpress,dcc = <number>;
+
+Any of the numbers above defaults to zero if not defined in
+the node or any of its parent.
+
+
+Motherboard
+-----------
+
 The motherboard description file provides a single "motherboard" node
 using 2 address cells corresponding to the Static Memory Bus used
 between the motherboard and the tile. The first cell defines the Chip
@@ -96,13 +150,16 @@ The tile description must define "ranges", "interrupt-map-mask" and
 "interrupt-map" properties to translate the motherboard's address
 and interrupt space into one used by the tile's processor.
 
-Abbreviated example:
+
+Example of a VE tile description (simplified)
+---------------------------------------------
 
 /dts-v1/;
 
 / {
 	model = "V2P-CA5s";
 	arm,hbi = <0x225>;
+	arm,vexpress,site = <0xf>;
 	compatible = "arm,vexpress-v2p-ca5s", "arm,vexpress";
 	interrupt-parent = <&gic>;
 	#address-cells = <1>;
@@ -134,6 +191,15 @@ Abbreviated example:
 		      <0x2c000100 0x100>;
 	};
 
+	dcc {
+		compatible = "simple-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			compatible = "arm,vexpress-osc";
+		};
+	};
+
 	motherboard {
 		/* CS0 is visible at 0x08000000 */
 		ranges = <0 0 0x08000000 0x04000000>;
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index acab3ef8a310..637bcdf8ce77 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1070,3 +1070,9 @@ config MCP_UCB1200_TS
 	depends on MCP_UCB1200 && INPUT
 
 endmenu
+
+config VEXPRESS_CONFIG
+	bool
+	help
+	  Platform configuration infrastructure for the ARM Ltd.
+	  Versatile Express.
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index d8ccb630ddb0..e807164f68da 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -138,3 +138,4 @@ obj-$(CONFIG_MFD_RC5T583)	+= rc5t583.o rc5t583-irq.o
 obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o sec-irq.o
 obj-$(CONFIG_MFD_SYSCON)	+= syscon.o
 obj-$(CONFIG_MFD_LM3533)	+= lm3533-core.o lm3533-ctrlbank.o
+obj-$(CONFIG_VEXPRESS_CONFIG)	+= vexpress-config.o
diff --git a/drivers/mfd/vexpress-config.c b/drivers/mfd/vexpress-config.c
new file mode 100644
index 000000000000..fae15d880758
--- /dev/null
+++ b/drivers/mfd/vexpress-config.c
@@ -0,0 +1,277 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#define pr_fmt(fmt) "vexpress-config: " fmt
+
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/vexpress.h>
+
+
+#define VEXPRESS_CONFIG_MAX_BRIDGES 2
+
+struct vexpress_config_bridge {
+	struct device_node *node;
+	struct vexpress_config_bridge_info *info;
+	struct list_head transactions;
+	spinlock_t transactions_lock;
+} vexpress_config_bridges[VEXPRESS_CONFIG_MAX_BRIDGES];
+
+static DECLARE_BITMAP(vexpress_config_bridges_map,
+		ARRAY_SIZE(vexpress_config_bridges));
+static DEFINE_MUTEX(vexpress_config_bridges_mutex);
+
+struct vexpress_config_bridge *vexpress_config_bridge_register(
+		struct device_node *node,
+		struct vexpress_config_bridge_info *info)
+{
+	struct vexpress_config_bridge *bridge;
+	int i;
+
+	pr_debug("Registering bridge '%s'\n", info->name);
+
+	mutex_lock(&vexpress_config_bridges_mutex);
+	i = find_first_zero_bit(vexpress_config_bridges_map,
+			ARRAY_SIZE(vexpress_config_bridges));
+	if (i >= ARRAY_SIZE(vexpress_config_bridges)) {
+		pr_err("Can't register more bridges!\n");
+		mutex_unlock(&vexpress_config_bridges_mutex);
+		return NULL;
+	}
+	__set_bit(i, vexpress_config_bridges_map);
+	bridge = &vexpress_config_bridges[i];
+
+	bridge->node = node;
+	bridge->info = info;
+	INIT_LIST_HEAD(&bridge->transactions);
+	spin_lock_init(&bridge->transactions_lock);
+
+	mutex_unlock(&vexpress_config_bridges_mutex);
+
+	return bridge;
+}
+
+void vexpress_config_bridge_unregister(struct vexpress_config_bridge *bridge)
+{
+	struct vexpress_config_bridge __bridge = *bridge;
+	int i;
+
+	mutex_lock(&vexpress_config_bridges_mutex);
+	for (i = 0; i < ARRAY_SIZE(vexpress_config_bridges); i++)
+		if (&vexpress_config_bridges[i] == bridge)
+			__clear_bit(i, vexpress_config_bridges_map);
+	mutex_unlock(&vexpress_config_bridges_mutex);
+
+	WARN_ON(!list_empty(&__bridge.transactions));
+	while (!list_empty(&__bridge.transactions))
+		cpu_relax();
+}
+
+
+struct vexpress_config_func {
+	struct vexpress_config_bridge *bridge;
+	void *func;
+};
+
+struct vexpress_config_func *__vexpress_config_func_get(struct device *dev,
+		struct device_node *node)
+{
+	struct device_node *bridge_node;
+	struct vexpress_config_func *func;
+	int i;
+
+	if (WARN_ON(dev && node && dev->of_node != node))
+		return NULL;
+	if (dev && !node)
+		node = dev->of_node;
+
+	func = kzalloc(sizeof(*func), GFP_KERNEL);
+	if (!func)
+		return NULL;
+
+	bridge_node = of_node_get(node);
+	while (bridge_node) {
+		const __be32 *prop = of_get_property(bridge_node,
+				"arm,vexpress,config-bridge", NULL);
+
+		if (prop) {
+			bridge_node = of_find_node_by_phandle(
+					be32_to_cpup(prop));
+			break;
+		}
+
+		bridge_node = of_get_next_parent(bridge_node);
+	}
+
+	mutex_lock(&vexpress_config_bridges_mutex);
+	for (i = 0; i < ARRAY_SIZE(vexpress_config_bridges); i++) {
+		struct vexpress_config_bridge *bridge =
+				&vexpress_config_bridges[i];
+
+		if (test_bit(i, vexpress_config_bridges_map) &&
+				bridge->node == bridge_node) {
+			func->bridge = bridge;
+			func->func = bridge->info->func_get(dev, node);
+			break;
+		}
+	}
+	mutex_unlock(&vexpress_config_bridges_mutex);
+
+	if (!func->func) {
+		of_node_put(node);
+		kfree(func);
+		return NULL;
+	}
+
+	return func;
+}
+
+void vexpress_config_func_put(struct vexpress_config_func *func)
+{
+	func->bridge->info->func_put(func->func);
+	of_node_put(func->bridge->node);
+	kfree(func);
+}
+
+
+struct vexpress_config_trans {
+	struct vexpress_config_func *func;
+	int offset;
+	bool write;
+	u32 *data;
+	int status;
+	struct completion completion;
+	struct list_head list;
+};
+
+static void vexpress_config_dump_trans(const char *what,
+		struct vexpress_config_trans *trans)
+{
+	pr_debug("%s %s trans %p func 0x%p offset %d data 0x%x status %d\n",
+			what, trans->write ? "write" : "read", trans,
+			trans->func->func, trans->offset,
+			trans->data ? *trans->data : 0, trans->status);
+}
+
+static int vexpress_config_schedule(struct vexpress_config_trans *trans)
+{
+	int status;
+	struct vexpress_config_bridge *bridge = trans->func->bridge;
+	unsigned long flags;
+
+	init_completion(&trans->completion);
+	trans->status = -EFAULT;
+
+	spin_lock_irqsave(&bridge->transactions_lock, flags);
+
+	vexpress_config_dump_trans("Executing", trans);
+
+	if (list_empty(&bridge->transactions))
+		status = bridge->info->func_exec(trans->func->func,
+				trans->offset, trans->write, trans->data);
+	else
+		status = VEXPRESS_CONFIG_STATUS_WAIT;
+
+	switch (status) {
+	case VEXPRESS_CONFIG_STATUS_DONE:
+		vexpress_config_dump_trans("Finished", trans);
+		trans->status = status;
+		break;
+	case VEXPRESS_CONFIG_STATUS_WAIT:
+		list_add_tail(&trans->list, &bridge->transactions);
+		break;
+	}
+
+	spin_unlock_irqrestore(&bridge->transactions_lock, flags);
+
+	return status;
+}
+
+void vexpress_config_complete(struct vexpress_config_bridge *bridge,
+		int status)
+{
+	struct vexpress_config_trans *trans;
+	unsigned long flags;
+
+	spin_lock_irqsave(&bridge->transactions_lock, flags);
+
+	trans = list_first_entry(&bridge->transactions,
+			struct vexpress_config_trans, list);
+	vexpress_config_dump_trans("Completed", trans);
+
+	trans->status = status;
+	list_del(&trans->list);
+
+	if (!list_empty(&bridge->transactions)) {
+		vexpress_config_dump_trans("Pending", trans);
+
+		bridge->info->func_exec(trans->func->func, trans->offset,
+				trans->write, trans->data);
+	}
+	spin_unlock_irqrestore(&bridge->transactions_lock, flags);
+
+	complete(&trans->completion);
+}
+
+int vexpress_config_wait(struct vexpress_config_trans *trans)
+{
+	wait_for_completion(&trans->completion);
+
+	return trans->status;
+}
+
+
+int vexpress_config_read(struct vexpress_config_func *func, int offset,
+		u32 *data)
+{
+	struct vexpress_config_trans trans = {
+		.func = func,
+		.offset = offset,
+		.write = false,
+		.data = data,
+		.status = 0,
+	};
+	int status = vexpress_config_schedule(&trans);
+
+	if (status == VEXPRESS_CONFIG_STATUS_WAIT)
+		status = vexpress_config_wait(&trans);
+
+	return status;
+}
+EXPORT_SYMBOL(vexpress_config_read);
+
+int vexpress_config_write(struct vexpress_config_func *func, int offset,
+		u32 data)
+{
+	struct vexpress_config_trans trans = {
+		.func = func,
+		.offset = offset,
+		.write = true,
+		.data = &data,
+		.status = 0,
+	};
+	int status = vexpress_config_schedule(&trans);
+
+	if (status == VEXPRESS_CONFIG_STATUS_WAIT)
+		status = vexpress_config_wait(&trans);
+
+	return status;
+}
+EXPORT_SYMBOL(vexpress_config_write);
diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h
new file mode 100644
index 000000000000..c2d877a7b691
--- /dev/null
+++ b/include/linux/vexpress.h
@@ -0,0 +1,85 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#ifndef _LINUX_VEXPRESS_H
+#define _LINUX_VEXPRESS_H
+
+#include <linux/device.h>
+
+#define VEXPRESS_SITE_MB		0
+#define VEXPRESS_SITE_DB1		1
+#define VEXPRESS_SITE_DB2		2
+#define VEXPRESS_SITE_MASTER		0xf
+
+#define VEXPRESS_CONFIG_STATUS_DONE	0
+#define VEXPRESS_CONFIG_STATUS_WAIT	1
+
+/* Config bridge API */
+
+/**
+ * struct vexpress_config_bridge_info - description of the platform
+ * configuration infrastructure bridge.
+ *
+ * @name:	Bridge name
+ *
+ * @func_get:	Obtains pointer to a configuration function for a given
+ *		device or a Device Tree node, to be used with @func_put
+ *		and @func_exec. The node pointer should take precedence
+ *		over device pointer when both are passed.
+ *
+ * @func_put:	Tells the bridge that the function will not be used any
+ *		more, so all allocated resources can be released.
+ *
+ * @func_exec:	Executes a configuration function read or write operation.
+ *		The offset selects a 32 bit word of the value accessed.
+ *		Must return VEXPRESS_CONFIG_STATUS_DONE when operation
+ *		is finished immediately, VEXPRESS_CONFIG_STATUS_WAIT when
+ *		will be completed in some time or negative value in case
+ *		of error.
+ */
+struct vexpress_config_bridge_info {
+	const char *name;
+	void *(*func_get)(struct device *dev, struct device_node *node);
+	void (*func_put)(void *func);
+	int (*func_exec)(void *func, int offset, bool write, u32 *data);
+};
+
+struct vexpress_config_bridge;
+
+struct vexpress_config_bridge *vexpress_config_bridge_register(
+		struct device_node *node,
+		struct vexpress_config_bridge_info *info);
+void vexpress_config_bridge_unregister(struct vexpress_config_bridge *bridge);
+
+void vexpress_config_complete(struct vexpress_config_bridge *bridge,
+		int status);
+
+/* Config function API */
+
+struct vexpress_config_func;
+
+struct vexpress_config_func *__vexpress_config_func_get(struct device *dev,
+		struct device_node *node);
+#define vexpress_config_func_get_by_dev(dev) \
+		__vexpress_config_func_get(dev, NULL)
+#define vexpress_config_func_get_by_node(node) \
+		__vexpress_config_func_get(NULL, node)
+void vexpress_config_func_put(struct vexpress_config_func *func);
+
+/* Both may sleep! */
+int vexpress_config_read(struct vexpress_config_func *func, int offset,
+		u32 *data);
+int vexpress_config_write(struct vexpress_config_func *func, int offset,
+		u32 data);
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 88e0abcd7a8171ca7af3402373e7bd81fe9b6754 Mon Sep 17 00:00:00 2001
From: Pawel Moll
Date: Tue, 18 Sep 2012 12:24:57 +0100
Subject: mfd: Versatile Express system registers driver

This is a platform driver for Versatile Express' "system
register" block. It's a random collection of registers providing
the following functionality:

- low level platform functions like board ID access; in order to
  use those, the driver must be initialized early, either statically
  or based on the DT

- config bus bridge via "system control" interface; as the response
  from the controller does not generate interrupt (yet), the status
  register is periodically polled using a timer

- pseudo GPIO lines providing MMC card status and Flash WP#
  signal control

- LED interface for a set of 8 LEDs on the motherboard, with
  "heartbeat", "mmc0" and "cpu0" to "cpu5" as default triggers

Signed-off-by: Pawel Moll <pawel.moll@arm.com>
---
 .../devicetree/bindings/arm/vexpress-sysreg.txt    |  50 ++
 drivers/mfd/Makefile                               |   2 +-
 drivers/mfd/vexpress-sysreg.c                      | 552 +++++++++++++++++++++
 include/linux/vexpress.h                           |  25 +
 4 files changed, 628 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/devicetree/bindings/arm/vexpress-sysreg.txt
 create mode 100644 drivers/mfd/vexpress-sysreg.c

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/arm/vexpress-sysreg.txt b/Documentation/devicetree/bindings/arm/vexpress-sysreg.txt
new file mode 100644
index 000000000000..9cf3f25544c7
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/vexpress-sysreg.txt
@@ -0,0 +1,50 @@
+ARM Versatile Express system registers
+--------------------------------------
+
+This is a system control registers block, providing multiple low level
+platform functions like board detection and identification, software
+interrupt generation, MMC and NOR Flash control etc.
+
+Required node properties:
+- compatible value : = "arm,vexpress,sysreg";
+- reg : physical base address and the size of the registers window
+- gpio-controller : specifies that the node is a GPIO controller
+- #gpio-cells : size of the GPIO specifier, should be 2:
+  - first cell is the pseudo-GPIO line number:
+    0 - MMC CARDIN
+    1 - MMC WPROT
+    2 - NOR FLASH WPn
+  - second cell can take standard GPIO flags (currently ignored).
+
+Example:
+	v2m_sysreg: sysreg@10000000 {
+ 		compatible = "arm,vexpress-sysreg";
+ 		reg = <0x10000000 0x1000>;
+		gpio-controller;
+		#gpio-cells = <2>;
+ 	};
+
+This block also can also act a bridge to the platform's configuration
+bus via "system control" interface, addressing devices with site number,
+position in the board stack, config controller, function and device
+numbers - see motherboard's TRM for more details.
+
+The node describing a config device must refer to the sysreg node via
+"arm,vexpress,config-bridge" phandle (can be also defined in the node's
+parent) and relies on the board topology properties - see main vexpress
+node documentation for more details. It must must also define the
+following property:
+- arm,vexpress-sysreg,func : must contain two cells:
+  - first cell defines function number (eg. 1 for clock generator,
+    2 for voltage regulators etc.)
+  - device number (eg. osc 0, osc 1 etc.)
+
+Example:
+	mcc {
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+		};
+	};
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index e807164f68da..296817c6c06f 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -138,4 +138,4 @@ obj-$(CONFIG_MFD_RC5T583)	+= rc5t583.o rc5t583-irq.o
 obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o sec-irq.o
 obj-$(CONFIG_MFD_SYSCON)	+= syscon.o
 obj-$(CONFIG_MFD_LM3533)	+= lm3533-core.o lm3533-ctrlbank.o
-obj-$(CONFIG_VEXPRESS_CONFIG)	+= vexpress-config.o
+obj-$(CONFIG_VEXPRESS_CONFIG)	+= vexpress-config.o vexpress-sysreg.o
diff --git a/drivers/mfd/vexpress-sysreg.c b/drivers/mfd/vexpress-sysreg.c
new file mode 100644
index 000000000000..059d6b17b14a
--- /dev/null
+++ b/drivers/mfd/vexpress-sysreg.c
@@ -0,0 +1,552 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#include <linux/err.h>
+#include <linux/gpio.h>
+#include <linux/io.h>
+#include <linux/leds.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/timer.h>
+#include <linux/vexpress.h>
+
+#define SYS_ID			0x000
+#define SYS_SW			0x004
+#define SYS_LED			0x008
+#define SYS_100HZ		0x024
+#define SYS_FLAGS		0x030
+#define SYS_FLAGSSET		0x030
+#define SYS_FLAGSCLR		0x034
+#define SYS_NVFLAGS		0x038
+#define SYS_NVFLAGSSET		0x038
+#define SYS_NVFLAGSCLR		0x03c
+#define SYS_MCI			0x048
+#define SYS_FLASH		0x04c
+#define SYS_CFGSW		0x058
+#define SYS_24MHZ		0x05c
+#define SYS_MISC		0x060
+#define SYS_DMA			0x064
+#define SYS_PROCID0		0x084
+#define SYS_PROCID1		0x088
+#define SYS_CFGDATA		0x0a0
+#define SYS_CFGCTRL		0x0a4
+#define SYS_CFGSTAT		0x0a8
+
+#define SYS_HBI_MASK		0xfff
+#define SYS_ID_HBI_SHIFT	16
+#define SYS_PROCIDx_HBI_SHIFT	0
+
+#define SYS_MCI_CARDIN		(1 << 0)
+#define SYS_MCI_WPROT		(1 << 1)
+
+#define SYS_FLASH_WPn		(1 << 0)
+
+#define SYS_MISC_MASTERSITE	(1 << 14)
+
+#define SYS_CFGCTRL_START	(1 << 31)
+#define SYS_CFGCTRL_WRITE	(1 << 30)
+#define SYS_CFGCTRL_DCC(n)	(((n) & 0xf) << 26)
+#define SYS_CFGCTRL_FUNC(n)	(((n) & 0x3f) << 20)
+#define SYS_CFGCTRL_SITE(n)	(((n) & 0x3) << 16)
+#define SYS_CFGCTRL_POSITION(n)	(((n) & 0xf) << 12)
+#define SYS_CFGCTRL_DEVICE(n)	(((n) & 0xfff) << 0)
+
+#define SYS_CFGSTAT_ERR		(1 << 1)
+#define SYS_CFGSTAT_COMPLETE	(1 << 0)
+
+
+static void __iomem *vexpress_sysreg_base;
+static struct device *vexpress_sysreg_dev;
+static int vexpress_master_site;
+
+
+void vexpress_flags_set(u32 data)
+{
+	writel(~0, vexpress_sysreg_base + SYS_FLAGSCLR);
+	writel(data, vexpress_sysreg_base + SYS_FLAGSSET);
+}
+
+u32 vexpress_get_procid(int site)
+{
+	if (site == VEXPRESS_SITE_MASTER)
+		site = vexpress_master_site;
+
+	return readl(vexpress_sysreg_base + (site == VEXPRESS_SITE_DB1 ?
+			SYS_PROCID0 : SYS_PROCID1));
+}
+
+u32 vexpress_get_hbi(int site)
+{
+	u32 id;
+
+	switch (site) {
+	case VEXPRESS_SITE_MB:
+		id = readl(vexpress_sysreg_base + SYS_ID);
+		return (id >> SYS_ID_HBI_SHIFT) & SYS_HBI_MASK;
+	case VEXPRESS_SITE_MASTER:
+	case VEXPRESS_SITE_DB1:
+	case VEXPRESS_SITE_DB2:
+		id = vexpress_get_procid(site);
+		return (id >> SYS_PROCIDx_HBI_SHIFT) & SYS_HBI_MASK;
+	}
+
+	return ~0;
+}
+
+void __iomem *vexpress_get_24mhz_clock_base(void)
+{
+	return vexpress_sysreg_base + SYS_24MHZ;
+}
+
+
+static void vexpress_sysreg_find_prop(struct device_node *node,
+		const char *name, u32 *val)
+{
+	of_node_get(node);
+	while (node) {
+		if (of_property_read_u32(node, name, val) == 0) {
+			of_node_put(node);
+			return;
+		}
+		node = of_get_next_parent(node);
+	}
+}
+
+unsigned __vexpress_get_site(struct device *dev, struct device_node *node)
+{
+	u32 site = 0;
+
+	WARN_ON(dev && node && dev->of_node != node);
+	if (dev && !node)
+		node = dev->of_node;
+
+	if (node) {
+		vexpress_sysreg_find_prop(node, "arm,vexpress,site", &site);
+	} else if (dev && dev->bus == &platform_bus_type) {
+		struct platform_device *pdev = to_platform_device(dev);
+
+		if (pdev->num_resources == 1 &&
+				pdev->resource[0].flags == IORESOURCE_BUS)
+			site = pdev->resource[0].start;
+	} else if (dev && strncmp(dev_name(dev), "ct:", 3) == 0) {
+		site = VEXPRESS_SITE_MASTER;
+	}
+
+	if (site == VEXPRESS_SITE_MASTER)
+		site = vexpress_master_site;
+
+	return site;
+}
+
+
+struct vexpress_sysreg_config_func {
+	u32 template;
+	u32 device;
+};
+
+static struct vexpress_config_bridge *vexpress_sysreg_config_bridge;
+static struct timer_list vexpress_sysreg_config_timer;
+static u32 *vexpress_sysreg_config_data;
+static int vexpress_sysreg_config_tries;
+
+static void *vexpress_sysreg_config_func_get(struct device *dev,
+		struct device_node *node)
+{
+	struct vexpress_sysreg_config_func *config_func;
+	u32 site;
+	u32 position = 0;
+	u32 dcc = 0;
+	u32 func_device[2];
+	int err = -EFAULT;
+
+	if (node) {
+		of_node_get(node);
+		vexpress_sysreg_find_prop(node, "arm,vexpress,site", &site);
+		vexpress_sysreg_find_prop(node, "arm,vexpress,position",
+				&position);
+		vexpress_sysreg_find_prop(node, "arm,vexpress,dcc", &dcc);
+		err = of_property_read_u32_array(node,
+				"arm,vexpress-sysreg,func", func_device,
+				ARRAY_SIZE(func_device));
+		of_node_put(node);
+	} else if (dev && dev->bus == &platform_bus_type) {
+		struct platform_device *pdev = to_platform_device(dev);
+
+		if (pdev->num_resources == 1 &&
+				pdev->resource[0].flags == IORESOURCE_BUS) {
+			site = pdev->resource[0].start;
+			func_device[0] = pdev->resource[0].end;
+			func_device[1] = pdev->id;
+			err = 0;
+		}
+	}
+	if (err)
+		return NULL;
+
+	config_func = kzalloc(sizeof(*config_func), GFP_KERNEL);
+	if (!config_func)
+		return NULL;
+
+	config_func->template = SYS_CFGCTRL_DCC(dcc);
+	config_func->template |= SYS_CFGCTRL_FUNC(func_device[0]);
+	config_func->template |= SYS_CFGCTRL_SITE(site == VEXPRESS_SITE_MASTER ?
+			vexpress_master_site : site);
+	config_func->template |= SYS_CFGCTRL_POSITION(position);
+	config_func->device |= func_device[1];
+
+	dev_dbg(vexpress_sysreg_dev, "func 0x%p = 0x%x, %d\n", config_func,
+			config_func->template, config_func->device);
+
+	return config_func;
+}
+
+static void vexpress_sysreg_config_func_put(void *func)
+{
+	kfree(func);
+}
+
+static int vexpress_sysreg_config_func_exec(void *func, int offset,
+		bool write, u32 *data)
+{
+	int status;
+	struct vexpress_sysreg_config_func *config_func = func;
+	u32 command;
+
+	if (WARN_ON(!vexpress_sysreg_base))
+		return -ENOENT;
+
+	command = readl(vexpress_sysreg_base + SYS_CFGCTRL);
+	if (WARN_ON(command & SYS_CFGCTRL_START))
+		return -EBUSY;
+
+	command = SYS_CFGCTRL_START;
+	command |= write ? SYS_CFGCTRL_WRITE : 0;
+	command |= config_func->template;
+	command |= SYS_CFGCTRL_DEVICE(config_func->device + offset);
+
+	/* Use a canary for reads */
+	if (!write)
+		*data = 0xdeadbeef;
+
+	dev_dbg(vexpress_sysreg_dev, "command %x, data %x\n",
+			command, *data);
+	writel(*data, vexpress_sysreg_base + SYS_CFGDATA);
+	writel(0, vexpress_sysreg_base + SYS_CFGSTAT);
+	writel(command, vexpress_sysreg_base + SYS_CFGCTRL);
+	mb();
+
+	if (vexpress_sysreg_dev) {
+		/* Schedule completion check */
+		if (!write)
+			vexpress_sysreg_config_data = data;
+		vexpress_sysreg_config_tries = 100;
+		mod_timer(&vexpress_sysreg_config_timer,
+				jiffies + usecs_to_jiffies(100));
+		status = VEXPRESS_CONFIG_STATUS_WAIT;
+	} else {
+		/* Early execution, no timer available, have to spin */
+		u32 cfgstat;
+
+		do {
+			cpu_relax();
+			cfgstat = readl(vexpress_sysreg_base + SYS_CFGSTAT);
+		} while (!cfgstat);
+
+		if (!write && (cfgstat & SYS_CFGSTAT_COMPLETE))
+			*data = readl(vexpress_sysreg_base + SYS_CFGDATA);
+		status = VEXPRESS_CONFIG_STATUS_DONE;
+
+		if (cfgstat & SYS_CFGSTAT_ERR)
+			status = -EINVAL;
+	}
+
+	return status;
+}
+
+struct vexpress_config_bridge_info vexpress_sysreg_config_bridge_info = {
+	.name = "vexpress-sysreg",
+	.func_get = vexpress_sysreg_config_func_get,
+	.func_put = vexpress_sysreg_config_func_put,
+	.func_exec = vexpress_sysreg_config_func_exec,
+};
+
+static void vexpress_sysreg_config_complete(unsigned long data)
+{
+	int status = VEXPRESS_CONFIG_STATUS_DONE;
+	u32 cfgstat = readl(vexpress_sysreg_base + SYS_CFGSTAT);
+
+	if (cfgstat & SYS_CFGSTAT_ERR)
+		status = -EINVAL;
+	if (!vexpress_sysreg_config_tries--)
+		status = -ETIMEDOUT;
+
+	if (status < 0) {
+		dev_err(vexpress_sysreg_dev, "error %d\n", status);
+	} else if (!(cfgstat & SYS_CFGSTAT_COMPLETE)) {
+		mod_timer(&vexpress_sysreg_config_timer,
+				jiffies + usecs_to_jiffies(50));
+		return;
+	}
+
+	if (vexpress_sysreg_config_data) {
+		*vexpress_sysreg_config_data = readl(vexpress_sysreg_base +
+				SYS_CFGDATA);
+		dev_dbg(vexpress_sysreg_dev, "read data %x\n",
+				*vexpress_sysreg_config_data);
+		vexpress_sysreg_config_data = NULL;
+	}
+
+	vexpress_config_complete(vexpress_sysreg_config_bridge, status);
+}
+
+
+void __init vexpress_sysreg_early_init(void __iomem *base)
+{
+	struct device_node *node = of_find_compatible_node(NULL, NULL,
+			"arm,vexpress-sysreg");
+
+	if (node)
+		base = of_iomap(node, 0);
+
+	if (WARN_ON(!base))
+		return;
+
+	vexpress_sysreg_base = base;
+
+	if (readl(vexpress_sysreg_base + SYS_MISC) & SYS_MISC_MASTERSITE)
+		vexpress_master_site = VEXPRESS_SITE_DB2;
+	else
+		vexpress_master_site = VEXPRESS_SITE_DB1;
+
+	vexpress_sysreg_config_bridge = vexpress_config_bridge_register(
+			node, &vexpress_sysreg_config_bridge_info);
+	WARN_ON(!vexpress_sysreg_config_bridge);
+}
+
+void __init vexpress_sysreg_of_early_init(void)
+{
+	vexpress_sysreg_early_init(NULL);
+}
+
+
+static struct vexpress_sysreg_gpio {
+	unsigned long reg;
+	u32 value;
+} vexpress_sysreg_gpios[] = {
+	[VEXPRESS_GPIO_MMC_CARDIN] = {
+		.reg = SYS_MCI,
+		.value = SYS_MCI_CARDIN,
+	},
+	[VEXPRESS_GPIO_MMC_WPROT] = {
+		.reg = SYS_MCI,
+		.value = SYS_MCI_WPROT,
+	},
+	[VEXPRESS_GPIO_FLASH_WPn] = {
+		.reg = SYS_FLASH,
+		.value = SYS_FLASH_WPn,
+	},
+};
+
+static int vexpress_sysreg_gpio_direction_input(struct gpio_chip *chip,
+				       unsigned offset)
+{
+	return 0;
+}
+
+static int vexpress_sysreg_gpio_direction_output(struct gpio_chip *chip,
+						unsigned offset, int value)
+{
+	return 0;
+}
+
+static int vexpress_sysreg_gpio_get(struct gpio_chip *chip,
+				       unsigned offset)
+{
+	struct vexpress_sysreg_gpio *gpio = &vexpress_sysreg_gpios[offset];
+	u32 reg_value = readl(vexpress_sysreg_base + gpio->reg);
+
+	return !!(reg_value & gpio->value);
+}
+
+static void vexpress_sysreg_gpio_set(struct gpio_chip *chip,
+				       unsigned offset, int value)
+{
+	struct vexpress_sysreg_gpio *gpio = &vexpress_sysreg_gpios[offset];
+	u32 reg_value = readl(vexpress_sysreg_base + gpio->reg);
+
+	if (value)
+		reg_value |= gpio->value;
+	else
+		reg_value &= ~gpio->value;
+
+	writel(reg_value, vexpress_sysreg_base + gpio->reg);
+}
+
+static struct gpio_chip vexpress_sysreg_gpio_chip = {
+	.label = "vexpress-sysreg",
+	.direction_input = vexpress_sysreg_gpio_direction_input,
+	.direction_output = vexpress_sysreg_gpio_direction_output,
+	.get = vexpress_sysreg_gpio_get,
+	.set = vexpress_sysreg_gpio_set,
+	.ngpio = ARRAY_SIZE(vexpress_sysreg_gpios),
+	.base = 0,
+};
+
+
+static ssize_t vexpress_sysreg_sys_id_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "0x%08x\n", readl(vexpress_sysreg_base + SYS_ID));
+}
+
+DEVICE_ATTR(sys_id, S_IRUGO, vexpress_sysreg_sys_id_show, NULL);
+
+static int __devinit vexpress_sysreg_probe(struct platform_device *pdev)
+{
+	int err;
+	struct resource *res = platform_get_resource(pdev,
+			IORESOURCE_MEM, 0);
+
+	if (!devm_request_mem_region(&pdev->dev, res->start,
+			resource_size(res), pdev->name)) {
+		dev_err(&pdev->dev, "Failed to request memory region!\n");
+		return -EBUSY;
+	}
+
+	if (!vexpress_sysreg_base)
+		vexpress_sysreg_base = devm_ioremap(&pdev->dev, res->start,
+				resource_size(res));
+
+	if (!vexpress_sysreg_base) {
+		dev_err(&pdev->dev, "Failed to obtain base address!\n");
+		return -EFAULT;
+	}
+
+	setup_timer(&vexpress_sysreg_config_timer,
+			vexpress_sysreg_config_complete, 0);
+
+	vexpress_sysreg_gpio_chip.dev = &pdev->dev;
+	err = gpiochip_add(&vexpress_sysreg_gpio_chip);
+	if (err) {
+		vexpress_config_bridge_unregister(
+				vexpress_sysreg_config_bridge);
+		dev_err(&pdev->dev, "Failed to register GPIO chip! (%d)\n",
+				err);
+		return err;
+	}
+
+	vexpress_sysreg_dev = &pdev->dev;
+
+	device_create_file(vexpress_sysreg_dev, &dev_attr_sys_id);
+
+	return 0;
+}
+
+static const struct of_device_id vexpress_sysreg_match[] = {
+	{ .compatible = "arm,vexpress-sysreg", },
+	{},
+};
+
+static struct platform_driver vexpress_sysreg_driver = {
+	.driver = {
+		.name = "vexpress-sysreg",
+		.of_match_table = vexpress_sysreg_match,
+	},
+	.probe = vexpress_sysreg_probe,
+};
+
+static int __init vexpress_sysreg_init(void)
+{
+	return platform_driver_register(&vexpress_sysreg_driver);
+}
+core_initcall(vexpress_sysreg_init);
+
+
+#if defined(CONFIG_LEDS_CLASS)
+
+struct vexpress_sysreg_led {
+	u32 mask;
+	struct led_classdev cdev;
+} vexpress_sysreg_leds[] = {
+	{ .mask = 1 << 0, .cdev.name = "v2m:green:user1",
+			.cdev.default_trigger = "heartbeat", },
+	{ .mask = 1 << 1, .cdev.name = "v2m:green:user2",
+			.cdev.default_trigger = "mmc0", },
+	{ .mask = 1 << 2, .cdev.name = "v2m:green:user3",
+			.cdev.default_trigger = "cpu0", },
+	{ .mask = 1 << 3, .cdev.name = "v2m:green:user4",
+			.cdev.default_trigger = "cpu1", },
+	{ .mask = 1 << 4, .cdev.name = "v2m:green:user5",
+			.cdev.default_trigger = "cpu2", },
+	{ .mask = 1 << 5, .cdev.name = "v2m:green:user6",
+			.cdev.default_trigger = "cpu3", },
+	{ .mask = 1 << 6, .cdev.name = "v2m:green:user7",
+			.cdev.default_trigger = "cpu4", },
+	{ .mask = 1 << 7, .cdev.name = "v2m:green:user8",
+			.cdev.default_trigger = "cpu5", },
+};
+
+static DEFINE_SPINLOCK(vexpress_sysreg_leds_lock);
+
+static void vexpress_sysreg_led_brightness_set(struct led_classdev *cdev,
+		enum led_brightness brightness)
+{
+	struct vexpress_sysreg_led *led = container_of(cdev,
+			struct vexpress_sysreg_led, cdev);
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&vexpress_sysreg_leds_lock, flags);
+
+	val = readl(vexpress_sysreg_base + SYS_LED);
+	if (brightness == LED_OFF)
+		val &= ~led->mask;
+	else
+		val |= led->mask;
+	writel(val, vexpress_sysreg_base + SYS_LED);
+
+	spin_unlock_irqrestore(&vexpress_sysreg_leds_lock, flags);
+}
+
+static int __init vexpress_sysreg_init_leds(void)
+{
+	struct vexpress_sysreg_led *led;
+	int i;
+
+	/* Clear all user LEDs */
+	writel(0, vexpress_sysreg_base + SYS_LED);
+
+	for (i = 0, led = vexpress_sysreg_leds;
+			i < ARRAY_SIZE(vexpress_sysreg_leds); i++, led++) {
+		int err;
+
+		led->cdev.brightness_set = vexpress_sysreg_led_brightness_set;
+		err = led_classdev_register(vexpress_sysreg_dev, &led->cdev);
+		if (err) {
+			dev_err(vexpress_sysreg_dev,
+					"Failed to register LED %d! (%d)\n",
+					i, err);
+			while (led--, i--)
+				led_classdev_unregister(&led->cdev);
+			return err;
+		}
+	}
+
+	return 0;
+}
+device_initcall(vexpress_sysreg_init_leds);
+
+#endif
diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h
index c2d877a7b691..09c81d7a22de 100644
--- a/include/linux/vexpress.h
+++ b/include/linux/vexpress.h
@@ -24,6 +24,17 @@
 #define VEXPRESS_CONFIG_STATUS_DONE	0
 #define VEXPRESS_CONFIG_STATUS_WAIT	1
 
+#define VEXPRESS_GPIO_MMC_CARDIN	0
+#define VEXPRESS_GPIO_MMC_WPROT		1
+#define VEXPRESS_GPIO_FLASH_WPn		2
+
+#define VEXPRESS_RES_FUNC(_site, _func)	\
+{					\
+	.start = (_site),		\
+	.end = (_func),			\
+	.flags = IORESOURCE_BUS,	\
+}
+
 /* Config bridge API */
 
 /**
@@ -82,4 +93,18 @@ int vexpress_config_read(struct vexpress_config_func *func, int offset,
 int vexpress_config_write(struct vexpress_config_func *func, int offset,
 		u32 data);
 
+/* Platform control */
+
+u32 vexpress_get_procid(int site);
+u32 vexpress_get_hbi(int site);
+void *vexpress_get_24mhz_clock_base(void);
+void vexpress_flags_set(u32 data);
+
+#define vexpress_get_site_by_node(node) __vexpress_get_site(NULL, node)
+#define vexpress_get_site_by_dev(dev) __vexpress_get_site(dev, NULL)
+unsigned __vexpress_get_site(struct device *dev, struct device_node *node);
+
+void vexpress_sysreg_early_init(void __iomem *base);
+void vexpress_sysreg_of_early_init(void);
+
 #endif
-- 
cgit v1.2.3-55-g7522


From 38669e045dbf8f62a008898a7fb1e93975b3817c Mon Sep 17 00:00:00 2001
From: Pawel Moll
Date: Tue, 9 Oct 2012 12:56:36 +0100
Subject: ARM: vexpress: Start using new Versatile Express infrastructure

This patch starts using all the configuration infrastructure.

- generic GPIO library is forced now

- sysreg GPIOs are used as MMC CD and WP information sources;
  thanks to this MMCI auxiliary data is not longer necessary

- DVI muxer and mode control is removed from non-DT V2P-CA9 code
  as this is now handled by the vexpress-dvi driver

- clock generators control is removed as is being handled by the
  common clock driver now

- the sysreg and sysctl control is now delegated to the
  appropriate drivers and all related code was removed

- NOR Flash set_vpp function has been removed as the control
  bit used does _not_ control its VPP line, but the #WP signal
  instead (which is de facto unusable in case of Linux MTD
  drivers); this also allowed the remove its DT auxiliary
  data

The non-DT code defines only minimal required number of
the config devices. Device Trees are updated to make use
of all new features.

Signed-off-by: Pawel Moll <pawel.moll@arm.com>
---
 arch/arm/include/asm/hardware/sp810.h             |   6 -
 arch/arm/mach-vexpress/Kconfig                    |   4 +-
 arch/arm/mach-vexpress/Makefile                   |   2 +-
 arch/arm/mach-vexpress/ct-ca9x4.c                 |  41 +--
 arch/arm/mach-vexpress/include/mach/motherboard.h |  81 ------
 arch/arm/mach-vexpress/platsmp.c                  |   3 +-
 arch/arm/mach-vexpress/v2m.c                      | 332 +++++-----------------
 include/linux/vexpress.h                          |  11 +
 8 files changed, 110 insertions(+), 370 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/hardware/sp810.h b/arch/arm/include/asm/hardware/sp810.h
index afd7e916472f..6636430dd0e6 100644
--- a/arch/arm/include/asm/hardware/sp810.h
+++ b/arch/arm/include/asm/hardware/sp810.h
@@ -50,12 +50,6 @@
 #define SCPCELLID2		0xFF8
 #define SCPCELLID3		0xFFC
 
-#define SCCTRL_TIMEREN0SEL_REFCLK	(0 << 15)
-#define SCCTRL_TIMEREN0SEL_TIMCLK	(1 << 15)
-
-#define SCCTRL_TIMEREN1SEL_REFCLK	(0 << 17)
-#define SCCTRL_TIMEREN1SEL_TIMCLK	(1 << 17)
-
 #define SCCTRL_TIMERENnSEL_SHIFT(n)	(15 + ((n) * 2))
 
 static inline void sysctl_soft_reset(void __iomem *base)
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index c95296066203..99e63f5f99d1 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -1,11 +1,12 @@
 config ARCH_VEXPRESS
 	bool "ARM Ltd. Versatile Express family" if ARCH_MULTI_V7
-	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_GIC
 	select ARM_TIMER_SP804
 	select CLKDEV_LOOKUP
 	select COMMON_CLK
+	select COMMON_CLK_VERSATILE
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CLK
@@ -17,6 +18,7 @@ config ARCH_VEXPRESS
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_CLCD
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
+	select VEXPRESS_CONFIG
 	help
 	  This option enables support for systems using Cortex processor based
 	  ARM core and logic (FPGA) tiles on the Versatile Express motherboard,
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 42703e8b4d3b..80b64971fbdd 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -4,7 +4,7 @@
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
 	-I$(srctree)/arch/arm/plat-versatile/include
 
-obj-y					:= v2m.o
+obj-y					:= v2m.o reset.o
 obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
 obj-$(CONFIG_SMP)			+= platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index 4f471fa3e3c5..60838ddb8564 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -9,6 +9,7 @@
 #include <linux/amba/bus.h>
 #include <linux/amba/clcd.h>
 #include <linux/clkdev.h>
+#include <linux/vexpress.h>
 
 #include <asm/hardware/arm_timer.h>
 #include <asm/hardware/cache-l2x0.h>
@@ -64,19 +65,6 @@ static void __init ct_ca9x4_init_irq(void)
 	ca9x4_twd_init();
 }
 
-static void ct_ca9x4_clcd_enable(struct clcd_fb *fb)
-{
-	u32 site = v2m_get_master_site();
-
-	/*
-	 * Old firmware was using the "site" component of the command
-	 * to control the DVI muxer (while it should be always 0 ie. MB).
-	 * Newer firmware uses the data register. Keep both for compatibility.
-	 */
-	v2m_cfg_write(SYS_CFG_MUXFPGA | SYS_CFG_SITE(site), site);
-	v2m_cfg_write(SYS_CFG_DVIMODE | SYS_CFG_SITE(SYS_CFG_SITE_MB), 2);
-}
-
 static int ct_ca9x4_clcd_setup(struct clcd_fb *fb)
 {
 	unsigned long framesize = 1024 * 768 * 2;
@@ -93,7 +81,6 @@ static struct clcd_board ct_ca9x4_clcd_data = {
 	.caps		= CLCD_CAP_5551 | CLCD_CAP_565,
 	.check		= clcdfb_check,
 	.decode		= clcdfb_decode,
-	.enable		= ct_ca9x4_clcd_enable,
 	.setup		= ct_ca9x4_clcd_setup,
 	.mmap		= versatile_clcd_mmap_dma,
 	.remove		= versatile_clcd_remove_dma,
@@ -111,14 +98,6 @@ static struct amba_device *ct_ca9x4_amba_devs[] __initdata = {
 	&gpio_device,
 };
 
-
-static struct v2m_osc ct_osc1 = {
-	.osc = 1,
-	.rate_min = 10000000,
-	.rate_max = 80000000,
-	.rate_default = 23750000,
-};
-
 static struct resource pmu_resources[] = {
 	[0] = {
 		.start	= IRQ_CT_CA9X4_PMU_CPU0,
@@ -149,10 +128,18 @@ static struct platform_device pmu_device = {
 	.resource	= pmu_resources,
 };
 
+static struct platform_device osc1_device = {
+	.name		= "vexpress-osc",
+	.id		= 1,
+	.num_resources	= 1,
+	.resource	= (struct resource []) {
+		VEXPRESS_RES_FUNC(0xf, 1),
+	},
+};
+
 static void __init ct_ca9x4_init(void)
 {
 	int i;
-	struct clk *clk;
 
 #ifdef CONFIG_CACHE_L2X0
 	void __iomem *l2x0_base = ioremap(CT_CA9X4_L2CC, SZ_4K);
@@ -164,14 +151,14 @@ static void __init ct_ca9x4_init(void)
 	l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff);
 #endif
 
-	ct_osc1.site = v2m_get_master_site();
-	clk = v2m_osc_register("ct:osc1", &ct_osc1);
-	clk_register_clkdev(clk, NULL, "ct:clcd");
-
 	for (i = 0; i < ARRAY_SIZE(ct_ca9x4_amba_devs); i++)
 		amba_device_register(ct_ca9x4_amba_devs[i], &iomem_resource);
 
 	platform_device_register(&pmu_device);
+	platform_device_register(&osc1_device);
+
+	WARN_ON(clk_register_clkdev(vexpress_osc_setup(&osc1_device.dev),
+			NULL, "ct:clcd"));
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/arm/mach-vexpress/include/mach/motherboard.h b/arch/arm/mach-vexpress/include/mach/motherboard.h
index 1e388c7bf4d7..68abc8b72781 100644
--- a/arch/arm/mach-vexpress/include/mach/motherboard.h
+++ b/arch/arm/mach-vexpress/include/mach/motherboard.h
@@ -1,8 +1,6 @@
 #ifndef __MACH_MOTHERBOARD_H
 #define __MACH_MOTHERBOARD_H
 
-#include <linux/clk-provider.h>
-
 /*
  * Physical addresses, offset from V2M_PA_CS0-3
  */
@@ -41,31 +39,6 @@
 #define V2M_CF			(V2M_PA_CS7 + 0x0001a000)
 #define V2M_CLCD		(V2M_PA_CS7 + 0x0001f000)
 
-/*
- * Offsets from SYSREGS base
- */
-#define V2M_SYS_ID		0x000
-#define V2M_SYS_SW		0x004
-#define V2M_SYS_LED		0x008
-#define V2M_SYS_100HZ		0x024
-#define V2M_SYS_FLAGS		0x030
-#define V2M_SYS_FLAGSSET	0x030
-#define V2M_SYS_FLAGSCLR	0x034
-#define V2M_SYS_NVFLAGS		0x038
-#define V2M_SYS_NVFLAGSSET	0x038
-#define V2M_SYS_NVFLAGSCLR	0x03c
-#define V2M_SYS_MCI		0x048
-#define V2M_SYS_FLASH		0x03c
-#define V2M_SYS_CFGSW		0x058
-#define V2M_SYS_24MHZ		0x05c
-#define V2M_SYS_MISC		0x060
-#define V2M_SYS_DMA		0x064
-#define V2M_SYS_PROCID0		0x084
-#define V2M_SYS_PROCID1		0x088
-#define V2M_SYS_CFGDATA		0x0a0
-#define V2M_SYS_CFGCTRL		0x0a4
-#define V2M_SYS_CFGSTAT		0x0a8
-
 
 /*
  * Interrupts.  Those in {} are for AMBA devices
@@ -90,43 +63,6 @@
 #define IRQ_V2M_PCIE		(32 + 17)
 
 
-/*
- * Configuration
- */
-#define SYS_CFG_START		(1 << 31)
-#define SYS_CFG_WRITE		(1 << 30)
-#define SYS_CFG_OSC		(1 << 20)
-#define SYS_CFG_VOLT		(2 << 20)
-#define SYS_CFG_AMP		(3 << 20)
-#define SYS_CFG_TEMP		(4 << 20)
-#define SYS_CFG_RESET		(5 << 20)
-#define SYS_CFG_SCC		(6 << 20)
-#define SYS_CFG_MUXFPGA		(7 << 20)
-#define SYS_CFG_SHUTDOWN	(8 << 20)
-#define SYS_CFG_REBOOT		(9 << 20)
-#define SYS_CFG_DVIMODE		(11 << 20)
-#define SYS_CFG_POWER		(12 << 20)
-#define SYS_CFG_SITE(n)		((n) << 16)
-#define SYS_CFG_SITE_MB		0
-#define SYS_CFG_SITE_DB1	1
-#define SYS_CFG_SITE_DB2	2
-#define SYS_CFG_STACK(n)	((n) << 12)
-
-#define SYS_CFG_ERR		(1 << 1)
-#define SYS_CFG_COMPLETE	(1 << 0)
-
-int v2m_cfg_write(u32 devfn, u32 data);
-int v2m_cfg_read(u32 devfn, u32 *data);
-void v2m_flags_set(u32 data);
-
-/*
- * Miscellaneous
- */
-#define SYS_MISC_MASTERSITE	(1 << 14)
-#define SYS_PROCIDx_HBI_MASK	0xfff
-
-int v2m_get_master_site(void);
-
 /*
  * Core tile IDs
  */
@@ -149,21 +85,4 @@ struct ct_desc {
 
 extern struct ct_desc *ct_desc;
 
-/*
- * OSC clock provider
- */
-struct v2m_osc {
-	struct clk_hw hw;
-	u8 site; /* 0 = motherboard, 1 = site 1, 2 = site 2 */
-	u8 stack; /* board stack position */
-	u16 osc;
-	unsigned long rate_min;
-	unsigned long rate_max;
-	unsigned long rate_default;
-};
-
-#define to_v2m_osc(osc) container_of(osc, struct v2m_osc, hw)
-
-struct clk *v2m_osc_register(const char *name, struct v2m_osc *osc);
-
 #endif
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index 7db27c8c05cc..c5d70de9bb4e 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -13,6 +13,7 @@
 #include <linux/smp.h>
 #include <linux/io.h>
 #include <linux/of_fdt.h>
+#include <linux/vexpress.h>
 
 #include <asm/smp_scu.h>
 #include <asm/hardware/gic.h>
@@ -193,7 +194,7 @@ static void __init vexpress_smp_prepare_cpus(unsigned int max_cpus)
 	 * until it receives a soft interrupt, and then the
 	 * secondary CPU branches to this address.
 	 */
-	v2m_flags_set(virt_to_phys(versatile_secondary_startup));
+	vexpress_flags_set(virt_to_phys(versatile_secondary_startup));
 }
 
 struct smp_operations __initdata vexpress_smp_ops = {
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 560e0df728f8..99d4172816be 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -16,11 +16,10 @@
 #include <linux/smsc911x.h>
 #include <linux/spinlock.h>
 #include <linux/usb/isp1760.h>
-#include <linux/clkdev.h>
-#include <linux/clk-provider.h>
 #include <linux/mtd/physmap.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
+#include <linux/vexpress.h>
 
 #include <asm/arch_timer.h>
 #include <asm/mach-types.h>
@@ -33,7 +32,6 @@
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/hardware/gic.h>
 #include <asm/hardware/timer-sp.h>
-#include <asm/hardware/sp810.h>
 
 #include <mach/ct-ca9x4.h>
 #include <mach/motherboard.h>
@@ -58,22 +56,6 @@ static struct map_desc v2m_io_desc[] __initdata = {
 	},
 };
 
-static void __iomem *v2m_sysreg_base;
-
-static void __init v2m_sysctl_init(void __iomem *base)
-{
-	u32 scctrl;
-
-	if (WARN_ON(!base))
-		return;
-
-	/* Select 1MHz TIMCLK as the reference clock for SP804 timers */
-	scctrl = readl(base + SCCTRL);
-	scctrl |= SCCTRL_TIMEREN0SEL_TIMCLK;
-	scctrl |= SCCTRL_TIMEREN1SEL_TIMCLK;
-	writel(scctrl, base + SCCTRL);
-}
-
 static void __init v2m_sp804_init(void __iomem *base, unsigned int irq)
 {
 	if (WARN_ON(!base || irq == NO_IRQ))
@@ -87,69 +69,6 @@ static void __init v2m_sp804_init(void __iomem *base, unsigned int irq)
 }
 
 
-static DEFINE_SPINLOCK(v2m_cfg_lock);
-
-int v2m_cfg_write(u32 devfn, u32 data)
-{
-	/* Configuration interface broken? */
-	u32 val;
-
-	printk("%s: writing %08x to %08x\n", __func__, data, devfn);
-
-	devfn |= SYS_CFG_START | SYS_CFG_WRITE;
-
-	spin_lock(&v2m_cfg_lock);
-	val = readl(v2m_sysreg_base + V2M_SYS_CFGSTAT);
-	writel(val & ~SYS_CFG_COMPLETE, v2m_sysreg_base + V2M_SYS_CFGSTAT);
-
-	writel(data, v2m_sysreg_base +  V2M_SYS_CFGDATA);
-	writel(devfn, v2m_sysreg_base + V2M_SYS_CFGCTRL);
-
-	do {
-		val = readl(v2m_sysreg_base + V2M_SYS_CFGSTAT);
-	} while (val == 0);
-	spin_unlock(&v2m_cfg_lock);
-
-	return !!(val & SYS_CFG_ERR);
-}
-
-int v2m_cfg_read(u32 devfn, u32 *data)
-{
-	u32 val;
-
-	devfn |= SYS_CFG_START;
-
-	spin_lock(&v2m_cfg_lock);
-	writel(0, v2m_sysreg_base + V2M_SYS_CFGSTAT);
-	writel(devfn, v2m_sysreg_base + V2M_SYS_CFGCTRL);
-
-	mb();
-
-	do {
-		cpu_relax();
-		val = readl(v2m_sysreg_base + V2M_SYS_CFGSTAT);
-	} while (val == 0);
-
-	*data = readl(v2m_sysreg_base + V2M_SYS_CFGDATA);
-	spin_unlock(&v2m_cfg_lock);
-
-	return !!(val & SYS_CFG_ERR);
-}
-
-void __init v2m_flags_set(u32 data)
-{
-	writel(~0, v2m_sysreg_base + V2M_SYS_FLAGSCLR);
-	writel(data, v2m_sysreg_base + V2M_SYS_FLAGSSET);
-}
-
-int v2m_get_master_site(void)
-{
-	u32 misc = readl(v2m_sysreg_base + V2M_SYS_MISC);
-
-	return misc & SYS_MISC_MASTERSITE ? SYS_CFG_SITE_DB2 : SYS_CFG_SITE_DB1;
-}
-
-
 static struct resource v2m_pcie_i2c_resource = {
 	.start	= V2M_SERIAL_BUS_PCI,
 	.end	= V2M_SERIAL_BUS_PCI + SZ_4K - 1,
@@ -237,14 +156,8 @@ static struct platform_device v2m_usb_device = {
 	.dev.platform_data = &v2m_usb_config,
 };
 
-static void v2m_flash_set_vpp(struct platform_device *pdev, int on)
-{
-	writel(on != 0, v2m_sysreg_base + V2M_SYS_FLASH);
-}
-
 static struct physmap_flash_data v2m_flash_data = {
 	.width		= 4,
-	.set_vpp	= v2m_flash_set_vpp,
 };
 
 static struct resource v2m_flash_resources[] = {
@@ -291,14 +204,61 @@ static struct platform_device v2m_cf_device = {
 	.dev.platform_data = &v2m_pata_data,
 };
 
-static unsigned int v2m_mmci_status(struct device *dev)
-{
-	return readl(v2m_sysreg_base + V2M_SYS_MCI) & (1 << 0);
-}
-
 static struct mmci_platform_data v2m_mmci_data = {
 	.ocr_mask	= MMC_VDD_32_33|MMC_VDD_33_34,
-	.status		= v2m_mmci_status,
+	.gpio_wp	= VEXPRESS_GPIO_MMC_WPROT,
+	.gpio_cd	= VEXPRESS_GPIO_MMC_CARDIN,
+};
+
+static struct resource v2m_sysreg_resources[] = {
+	{
+		.start	= V2M_SYSREGS,
+		.end	= V2M_SYSREGS + 0xfff,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device v2m_sysreg_device = {
+	.name		= "vexpress-sysreg",
+	.id		= -1,
+	.resource	= v2m_sysreg_resources,
+	.num_resources	= ARRAY_SIZE(v2m_sysreg_resources),
+};
+
+static struct platform_device v2m_muxfpga_device = {
+	.name		= "vexpress-muxfpga",
+	.id		= 0,
+	.num_resources	= 1,
+	.resource	= (struct resource []) {
+		VEXPRESS_RES_FUNC(0, 7),
+	}
+};
+
+static struct platform_device v2m_shutdown_device = {
+	.name		= "vexpress-shutdown",
+	.id		= 0,
+	.num_resources	= 1,
+	.resource	= (struct resource []) {
+		VEXPRESS_RES_FUNC(0, 8),
+	}
+};
+
+static struct platform_device v2m_reboot_device = {
+	.name		= "vexpress-reboot",
+	.id		= 0,
+	.num_resources	= 1,
+	.resource	= (struct resource []) {
+		VEXPRESS_RES_FUNC(0, 9),
+	}
+};
+
+static struct platform_device v2m_dvimode_device = {
+	.name		= "vexpress-dvimode",
+	.id		= 0,
+	.num_resources	= 1,
+	.resource	= (struct resource []) {
+		VEXPRESS_RES_FUNC(0, 11),
+	}
 };
 
 static AMBA_APB_DEVICE(aaci,  "mb:aaci",  0, V2M_AACI, IRQ_V2M_AACI, NULL);
@@ -325,123 +285,9 @@ static struct amba_device *v2m_amba_devs[] __initdata = {
 	&rtc_device,
 };
 
-
-static unsigned long v2m_osc_recalc_rate(struct clk_hw *hw,
-		unsigned long parent_rate)
-{
-	struct v2m_osc *osc = to_v2m_osc(hw);
-
-	return !parent_rate ? osc->rate_default : parent_rate;
-}
-
-static long v2m_osc_round_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long *parent_rate)
-{
-	struct v2m_osc *osc = to_v2m_osc(hw);
-
-	if (WARN_ON(rate < osc->rate_min))
-		rate = osc->rate_min;
-
-	if (WARN_ON(rate > osc->rate_max))
-		rate = osc->rate_max;
-
-	return rate;
-}
-
-static int v2m_osc_set_rate(struct clk_hw *hw, unsigned long rate,
-		unsigned long parent_rate)
-{
-	struct v2m_osc *osc = to_v2m_osc(hw);
-
-	v2m_cfg_write(SYS_CFG_OSC | SYS_CFG_SITE(osc->site) |
-			SYS_CFG_STACK(osc->stack) | osc->osc, rate);
-
-	return 0;
-}
-
-static struct clk_ops v2m_osc_ops = {
-	.recalc_rate = v2m_osc_recalc_rate,
-	.round_rate = v2m_osc_round_rate,
-	.set_rate = v2m_osc_set_rate,
-};
-
-struct clk * __init v2m_osc_register(const char *name, struct v2m_osc *osc)
-{
-	struct clk_init_data init;
-
-	WARN_ON(osc->site > 2);
-	WARN_ON(osc->stack > 15);
-	WARN_ON(osc->osc > 4095);
-
-	init.name = name;
-	init.ops = &v2m_osc_ops;
-	init.flags = CLK_IS_ROOT;
-	init.num_parents = 0;
-
-	osc->hw.init = &init;
-
-	return clk_register(NULL, &osc->hw);
-}
-
-static struct v2m_osc v2m_mb_osc1 = {
-	.site = SYS_CFG_SITE_MB,
-	.osc = 1,
-	.rate_min = 23750000,
-	.rate_max = 63500000,
-	.rate_default = 23750000,
-};
-
-static const char *v2m_ref_clk_periphs[] __initconst = {
-	"mb:wdt",   "1000f000.wdt",  "1c0f0000.wdt",	/* SP805 WDT */
-};
-
-static const char *v2m_osc1_periphs[] __initconst = {
-	"mb:clcd",  "1001f000.clcd", "1c1f0000.clcd",	/* PL111 CLCD */
-};
-
-static const char *v2m_osc2_periphs[] __initconst = {
-	"mb:mmci",  "10005000.mmci", "1c050000.mmci",	/* PL180 MMCI */
-	"mb:kmi0",  "10006000.kmi",  "1c060000.kmi",	/* PL050 KMI0 */
-	"mb:kmi1",  "10007000.kmi",  "1c070000.kmi",	/* PL050 KMI1 */
-	"mb:uart0", "10009000.uart", "1c090000.uart",	/* PL011 UART0 */
-	"mb:uart1", "1000a000.uart", "1c0a0000.uart",	/* PL011 UART1 */
-	"mb:uart2", "1000b000.uart", "1c0b0000.uart",	/* PL011 UART2 */
-	"mb:uart3", "1000c000.uart", "1c0c0000.uart",	/* PL011 UART3 */
-};
-
-static void __init v2m_clk_init(void)
-{
-	struct clk *clk;
-	int i;
-
-	clk = clk_register_fixed_rate(NULL, "dummy_apb_pclk", NULL,
-			CLK_IS_ROOT, 0);
-	WARN_ON(clk_register_clkdev(clk, "apb_pclk", NULL));
-
-	clk = clk_register_fixed_rate(NULL, "mb:ref_clk", NULL,
-			CLK_IS_ROOT, 32768);
-	for (i = 0; i < ARRAY_SIZE(v2m_ref_clk_periphs); i++)
-		WARN_ON(clk_register_clkdev(clk, NULL, v2m_ref_clk_periphs[i]));
-
-	clk = clk_register_fixed_rate(NULL, "mb:sp804_clk", NULL,
-			CLK_IS_ROOT, 1000000);
-	WARN_ON(clk_register_clkdev(clk, "v2m-timer0", "sp804"));
-	WARN_ON(clk_register_clkdev(clk, "v2m-timer1", "sp804"));
-
-	clk = v2m_osc_register("mb:osc1", &v2m_mb_osc1);
-	for (i = 0; i < ARRAY_SIZE(v2m_osc1_periphs); i++)
-		WARN_ON(clk_register_clkdev(clk, NULL, v2m_osc1_periphs[i]));
-
-	clk = clk_register_fixed_rate(NULL, "mb:osc2", NULL,
-			CLK_IS_ROOT, 24000000);
-	for (i = 0; i < ARRAY_SIZE(v2m_osc2_periphs); i++)
-		WARN_ON(clk_register_clkdev(clk, NULL, v2m_osc2_periphs[i]));
-}
-
 static void __init v2m_timer_init(void)
 {
-	v2m_sysctl_init(ioremap(V2M_SYSCTL, SZ_4K));
-	v2m_clk_init();
+	vexpress_clk_init(ioremap(V2M_SYSCTL, SZ_4K));
 	v2m_sp804_init(ioremap(V2M_TIMER01, SZ_4K), IRQ_V2M_TIMER0);
 }
 
@@ -453,19 +299,7 @@ static void __init v2m_init_early(void)
 {
 	if (ct_desc->init_early)
 		ct_desc->init_early();
-	versatile_sched_clock_init(v2m_sysreg_base + V2M_SYS_24MHZ, 24000000);
-}
-
-static void v2m_power_off(void)
-{
-	if (v2m_cfg_write(SYS_CFG_SHUTDOWN | SYS_CFG_SITE(SYS_CFG_SITE_MB), 0))
-		printk(KERN_EMERG "Unable to shutdown\n");
-}
-
-static void v2m_restart(char str, const char *cmd)
-{
-	if (v2m_cfg_write(SYS_CFG_REBOOT | SYS_CFG_SITE(SYS_CFG_SITE_MB), 0))
-		printk(KERN_EMERG "Unable to reboot\n");
+	versatile_sched_clock_init(vexpress_get_24mhz_clock_base(), 24000000);
 }
 
 struct ct_desc *ct_desc;
@@ -482,7 +316,7 @@ static void __init v2m_populate_ct_desc(void)
 	u32 current_tile_id;
 
 	ct_desc = NULL;
-	current_tile_id = readl(v2m_sysreg_base + V2M_SYS_PROCID0)
+	current_tile_id = vexpress_get_procid(VEXPRESS_SITE_MASTER)
 				& V2M_CT_ID_MASK;
 
 	for (i = 0; i < ARRAY_SIZE(ct_descs) && !ct_desc; ++i)
@@ -498,7 +332,7 @@ static void __init v2m_populate_ct_desc(void)
 static void __init v2m_map_io(void)
 {
 	iotable_init(v2m_io_desc, ARRAY_SIZE(v2m_io_desc));
-	v2m_sysreg_base = ioremap(V2M_SYSREGS, SZ_4K);
+	vexpress_sysreg_early_init(ioremap(V2M_SYSREGS, SZ_4K));
 	v2m_populate_ct_desc();
 	ct_desc->map_io();
 }
@@ -515,6 +349,12 @@ static void __init v2m_init(void)
 	regulator_register_fixed(0, v2m_eth_supplies,
 			ARRAY_SIZE(v2m_eth_supplies));
 
+	platform_device_register(&v2m_muxfpga_device);
+	platform_device_register(&v2m_shutdown_device);
+	platform_device_register(&v2m_reboot_device);
+	platform_device_register(&v2m_dvimode_device);
+
+	platform_device_register(&v2m_sysreg_device);
 	platform_device_register(&v2m_pcie_i2c_device);
 	platform_device_register(&v2m_ddc_i2c_device);
 	platform_device_register(&v2m_flash_device);
@@ -525,7 +365,7 @@ static void __init v2m_init(void)
 	for (i = 0; i < ARRAY_SIZE(v2m_amba_devs); i++)
 		amba_device_register(v2m_amba_devs[i], &iomem_resource);
 
-	pm_power_off = v2m_power_off;
+	pm_power_off = vexpress_power_off;
 
 	ct_desc->init_tile();
 }
@@ -539,7 +379,7 @@ MACHINE_START(VEXPRESS, "ARM-Versatile Express")
 	.timer		= &v2m_timer,
 	.handle_irq	= gic_handle_irq,
 	.init_machine	= v2m_init,
-	.restart	= v2m_restart,
+	.restart	= vexpress_restart,
 MACHINE_END
 
 static struct map_desc v2m_rs1_io_desc __initdata = {
@@ -580,20 +420,13 @@ void __init v2m_dt_map_io(void)
 
 void __init v2m_dt_init_early(void)
 {
-	struct device_node *node;
 	u32 dt_hbi;
 
-	node = of_find_compatible_node(NULL, NULL, "arm,vexpress-sysreg");
-	v2m_sysreg_base = of_iomap(node, 0);
-	if (WARN_ON(!v2m_sysreg_base))
-		return;
+	vexpress_sysreg_of_early_init();
 
 	/* Confirm board type against DT property, if available */
 	if (of_property_read_u32(allnodes, "arm,hbi", &dt_hbi) == 0) {
-		int site = v2m_get_master_site();
-		u32 id = readl(v2m_sysreg_base + (site == SYS_CFG_SITE_DB2 ?
-				V2M_SYS_PROCID1 : V2M_SYS_PROCID0));
-		u32 hbi = id & SYS_PROCIDx_HBI_MASK;
+		u32 hbi = vexpress_get_hbi(VEXPRESS_SITE_MASTER);
 
 		if (WARN_ON(dt_hbi != hbi))
 			pr_warning("vexpress: DT HBI (%x) is not matching "
@@ -617,10 +450,7 @@ static void __init v2m_dt_timer_init(void)
 	const char *path;
 	int err;
 
-	node = of_find_compatible_node(NULL, NULL, "arm,sp810");
-	v2m_sysctl_init(of_iomap(node, 0));
-
-	v2m_clk_init();
+	vexpress_clk_of_init();
 
 	err = of_property_read_string(of_aliases, "arm,v2m_timer", &path);
 	if (WARN_ON(err))
@@ -631,33 +461,29 @@ static void __init v2m_dt_timer_init(void)
 		twd_local_timer_of_register();
 
 	if (arch_timer_sched_clock_init() != 0)
-		versatile_sched_clock_init(v2m_sysreg_base + V2M_SYS_24MHZ, 24000000);
+		versatile_sched_clock_init(vexpress_get_24mhz_clock_base(),
+				24000000);
 }
 
 static struct sys_timer v2m_dt_timer = {
 	.init = v2m_dt_timer_init,
 };
 
-static struct of_dev_auxdata v2m_dt_auxdata_lookup[] __initdata = {
-	OF_DEV_AUXDATA("arm,vexpress-flash", V2M_NOR0, "physmap-flash",
-			&v2m_flash_data),
-	OF_DEV_AUXDATA("arm,primecell", V2M_MMCI, "mb:mmci", &v2m_mmci_data),
-	/* RS1 memory map */
-	OF_DEV_AUXDATA("arm,vexpress-flash", 0x08000000, "physmap-flash",
-			&v2m_flash_data),
-	OF_DEV_AUXDATA("arm,primecell", 0x1c050000, "mb:mmci", &v2m_mmci_data),
+static const struct of_device_id v2m_dt_bus_match[] __initconst = {
+	{ .compatible = "simple-bus", },
+	{ .compatible = "arm,amba-bus", },
+	{ .compatible = "arm,vexpress,config-bus", },
 	{}
 };
 
 static void __init v2m_dt_init(void)
 {
 	l2x0_of_init(0x00400000, 0xfe0fffff);
-	of_platform_populate(NULL, of_default_bus_match_table,
-			v2m_dt_auxdata_lookup, NULL);
-	pm_power_off = v2m_power_off;
+	of_platform_populate(NULL, v2m_dt_bus_match, NULL, NULL);
+	pm_power_off = vexpress_power_off;
 }
 
-const static char *v2m_dt_match[] __initconst = {
+static const char * const v2m_dt_match[] __initconst = {
 	"arm,vexpress",
 	"xen,xenvm",
 	NULL,
@@ -672,5 +498,5 @@ DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express")
 	.timer		= &v2m_dt_timer,
 	.init_machine	= v2m_dt_init,
 	.handle_irq	= gic_handle_irq,
-	.restart	= v2m_restart,
+	.restart	= vexpress_restart,
 MACHINE_END
diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h
index 09c81d7a22de..c52215ff4245 100644
--- a/include/linux/vexpress.h
+++ b/include/linux/vexpress.h
@@ -107,4 +107,15 @@ unsigned __vexpress_get_site(struct device *dev, struct device_node *node);
 void vexpress_sysreg_early_init(void __iomem *base);
 void vexpress_sysreg_of_early_init(void);
 
+void vexpress_power_off(void);
+void vexpress_restart(char str, const char *cmd);
+
+/* Clocks */
+
+struct clk *vexpress_osc_setup(struct device *dev);
+void vexpress_osc_of_setup(struct device_node *node);
+
+void vexpress_clk_init(void __iomem *sp810_base);
+void vexpress_clk_of_init(void);
+
 #endif
-- 
cgit v1.2.3-55-g7522


From ed95779340b50e362245c81b5dec0d11a1debfa8 Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 5 Nov 2012 09:16:58 -0800
Subject: cgroup: kill cgroup_subsys->__DEPRECATED_clear_css_refs

2ef37d3fe4 ("memcg: Simplify mem_cgroup_force_empty_list error
handling") removed the last user of __DEPRECATED_clear_css_refs.  This
patch removes __DEPRECATED_clear_css_refs and mechanisms to support
it.

* Conditionals dependent on __DEPRECATED_clear_css_refs removed.

* cgroup_clear_css_refs() can no longer fail.  All that needs to be
  done are deactivating refcnts, setting CSS_REMOVED and putting the
  base reference on each css.  Remove cgroup_clear_css_refs() and the
  failure path, and open-code the loops into cgroup_rmdir().

This patch keeps the two for_each_subsys() loops separate while open
coding them.  They can be merged now but there are scheduled changes
which need them to be separate, so keep them separate to reduce the
amount of churn.

local_irq_save/restore() from cgroup_clear_css_refs() are replaced
with local_irq_disable/enable() for simplicity.  This is safe as
cgroup_rmdir() is always called with IRQ enabled.  Note that this IRQ
switching is necessary to ensure that css_tryget() isn't called from
IRQ context on the same CPU while lower context is between CSS
deactivation and setting CSS_REMOVED as css_tryget() would hang
forever in such cases waiting for CSS to be re-activated or
CSS_REMOVED set.  This will go away soon.

v2: cgroup_call_pre_destroy() removal dropped per Michal.  Commit
    message updated to explain local_irq_disable/enable() conversion.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  12 -----
 kernel/cgroup.c        | 131 ++++++++++++++-----------------------------------
 2 files changed, 36 insertions(+), 107 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c90eaa803440..02e09c0e98ab 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -86,7 +86,6 @@ struct cgroup_subsys_state {
 enum {
 	CSS_ROOT, /* This CSS is the root of the subsystem */
 	CSS_REMOVED, /* This CSS is dead */
-	CSS_CLEAR_CSS_REFS,		/* @ss->__DEPRECATED_clear_css_refs */
 };
 
 /* Caller must verify that the css is not for root cgroup */
@@ -485,17 +484,6 @@ struct cgroup_subsys {
 	 */
 	bool use_id;
 
-	/*
-	 * If %true, cgroup removal will try to clear css refs by retrying
-	 * ss->pre_destroy() until there's no css ref left.  This behavior
-	 * is strictly for backward compatibility and will be removed as
-	 * soon as the current user (memcg) is updated.
-	 *
-	 * If %false, ss->pre_destroy() can't fail and cgroup removal won't
-	 * wait for css refs to drop to zero before proceeding.
-	 */
-	bool __DEPRECATED_clear_css_refs;
-
 #define MAX_CGROUP_TYPE_NAMELEN 32
 	const char *name;
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 79818507e444..8c605e2bdd1a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -865,11 +865,8 @@ static int cgroup_call_pre_destroy(struct cgroup *cgrp)
 			continue;
 
 		ret = ss->pre_destroy(cgrp);
-		if (ret) {
-			/* ->pre_destroy() failure is being deprecated */
-			WARN_ON_ONCE(!ss->__DEPRECATED_clear_css_refs);
+		if (WARN_ON_ONCE(ret))
 			break;
-		}
 	}
 
 	return ret;
@@ -3901,14 +3898,12 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	cgrp->subsys[ss->subsys_id] = css;
 
 	/*
-	 * If !clear_css_refs, css holds an extra ref to @cgrp->dentry
-	 * which is put on the last css_put().  dput() requires process
-	 * context, which css_put() may be called without.  @css->dput_work
-	 * will be used to invoke dput() asynchronously from css_put().
+	 * css holds an extra ref to @cgrp->dentry which is put on the last
+	 * css_put().  dput() requires process context, which css_put() may
+	 * be called without.  @css->dput_work will be used to invoke
+	 * dput() asynchronously from css_put().
 	 */
 	INIT_WORK(&css->dput_work, css_dput_fn);
-	if (ss->__DEPRECATED_clear_css_refs)
-		set_bit(CSS_CLEAR_CSS_REFS, &css->flags);
 }
 
 /*
@@ -3978,10 +3973,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (err < 0)
 		goto err_remove;
 
-	/* If !clear_css_refs, each css holds a ref to the cgroup's dentry */
+	/* each css holds a ref to the cgroup's dentry */
 	for_each_subsys(root, ss)
-		if (!ss->__DEPRECATED_clear_css_refs)
-			dget(dentry);
+		dget(dentry);
 
 	/* The cgroup directory was pre-locked for us */
 	BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex));
@@ -4066,71 +4060,6 @@ static int cgroup_has_css_refs(struct cgroup *cgrp)
 	return 0;
 }
 
-/*
- * Atomically mark all (or else none) of the cgroup's CSS objects as
- * CSS_REMOVED. Return true on success, or false if the cgroup has
- * busy subsystems. Call with cgroup_mutex held
- *
- * Depending on whether a subsys has __DEPRECATED_clear_css_refs set or
- * not, cgroup removal behaves differently.
- *
- * If clear is set, css refcnt for the subsystem should be zero before
- * cgroup removal can be committed.  This is implemented by
- * CGRP_WAIT_ON_RMDIR and retry logic around ->pre_destroy(), which may be
- * called multiple times until all css refcnts reach zero and is allowed to
- * veto removal on any invocation.  This behavior is deprecated and will be
- * removed as soon as the existing user (memcg) is updated.
- *
- * If clear is not set, each css holds an extra reference to the cgroup's
- * dentry and cgroup removal proceeds regardless of css refs.
- * ->pre_destroy() will be called at least once and is not allowed to fail.
- * On the last put of each css, whenever that may be, the extra dentry ref
- * is put so that dentry destruction happens only after all css's are
- * released.
- */
-static int cgroup_clear_css_refs(struct cgroup *cgrp)
-{
-	struct cgroup_subsys *ss;
-	unsigned long flags;
-	bool failed = false;
-
-	local_irq_save(flags);
-
-	/*
-	 * Block new css_tryget() by deactivating refcnt.  If all refcnts
-	 * for subsystems w/ clear_css_refs set were 1 at the moment of
-	 * deactivation, we succeeded.
-	 */
-	for_each_subsys(cgrp->root, ss) {
-		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
-
-		WARN_ON(atomic_read(&css->refcnt) < 0);
-		atomic_add(CSS_DEACT_BIAS, &css->refcnt);
-
-		if (ss->__DEPRECATED_clear_css_refs)
-			failed |= css_refcnt(css) != 1;
-	}
-
-	/*
-	 * If succeeded, set REMOVED and put all the base refs; otherwise,
-	 * restore refcnts to positive values.  Either way, all in-progress
-	 * css_tryget() will be released.
-	 */
-	for_each_subsys(cgrp->root, ss) {
-		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
-
-		if (!failed) {
-			set_bit(CSS_REMOVED, &css->flags);
-			css_put(css);
-		} else {
-			atomic_sub(CSS_DEACT_BIAS, &css->refcnt);
-		}
-	}
-
-	local_irq_restore(flags);
-	return !failed;
-}
-
 static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 {
 	struct cgroup *cgrp = dentry->d_fsdata;
@@ -4138,10 +4067,10 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	struct cgroup *parent;
 	DEFINE_WAIT(wait);
 	struct cgroup_event *event, *tmp;
+	struct cgroup_subsys *ss;
 	int ret;
 
 	/* the vfs holds both inode->i_mutex already */
-again:
 	mutex_lock(&cgroup_mutex);
 	if (atomic_read(&cgrp->count) != 0) {
 		mutex_unlock(&cgroup_mutex);
@@ -4182,21 +4111,34 @@ again:
 		return -EBUSY;
 	}
 	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
-	if (!cgroup_clear_css_refs(cgrp)) {
-		mutex_unlock(&cgroup_mutex);
-		/*
-		 * Because someone may call cgroup_wakeup_rmdir_waiter() before
-		 * prepare_to_wait(), we need to check this flag.
-		 */
-		if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))
-			schedule();
-		finish_wait(&cgroup_rmdir_waitq, &wait);
-		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-		if (signal_pending(current))
-			return -EINTR;
-		goto again;
+
+	local_irq_disable();
+
+	/* block new css_tryget() by deactivating refcnt */
+	for_each_subsys(cgrp->root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+
+		WARN_ON(atomic_read(&css->refcnt) < 0);
+		atomic_add(CSS_DEACT_BIAS, &css->refcnt);
+	}
+
+	/*
+	 * Set REMOVED.  All in-progress css_tryget() will be released.
+	 * Put all the base refs.  Each css holds an extra reference to the
+	 * cgroup's dentry and cgroup removal proceeds regardless of css
+	 * refs.  On the last put of each css, whenever that may be, the
+	 * extra dentry ref is put so that dentry destruction happens only
+	 * after all css's are released.
+	 */
+	for_each_subsys(cgrp->root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+
+		set_bit(CSS_REMOVED, &css->flags);
+		css_put(css);
 	}
-	/* NO css_tryget() can success after here. */
+
+	local_irq_enable();
+
 	finish_wait(&cgroup_rmdir_waitq, &wait);
 	clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
 
@@ -4949,8 +4891,7 @@ void __css_put(struct cgroup_subsys_state *css)
 		cgroup_wakeup_rmdir_waiter(cgrp);
 		break;
 	case 0:
-		if (!test_bit(CSS_CLEAR_CSS_REFS, &css->flags))
-			schedule_work(&css->dput_work);
+		schedule_work(&css->dput_work);
 		break;
 	}
 	rcu_read_unlock();
-- 
cgit v1.2.3-55-g7522


From e93160803ffda2e67d9ff9cacb63bb6868c8398f Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 5 Nov 2012 09:16:58 -0800
Subject: cgroup: kill CSS_REMOVED

CSS_REMOVED is one of the several contortions which were necessary to
support css reference draining on cgroup removal.  All css->refcnts
which need draining should be deactivated and verified to equal zero
atomically w.r.t. css_tryget().  If any one isn't zero, all refcnts
needed to be re-activated and css_tryget() shouldn't fail in the
process.

This was achieved by letting css_tryget() busy-loop until either the
refcnt is reactivated (failed removal attempt) or CSS_REMOVED is set
(committing to removal).

Now that css refcnt draining is no longer used, there's no need for
atomic rollback mechanism.  css_tryget() simply can look at the
reference count and fail if it's deactivated - it's never getting
re-activated.

This patch removes CSS_REMOVED and updates __css_tryget() to fail if
the refcnt is deactivated.  As deactivation and removal are a single
step now, they no longer need to be protected against css_tryget()
happening from irq context.  Remove local_irq_disable/enable() from
cgroup_rmdir().

Note that this removes css_is_removed() whose only user is VM_BUG_ON()
in memcontrol.c.  We can replace it with a check on the refcnt but
given that the only use case is a debug assert, I think it's better to
simply unexport it.

v2: Comment updated and explanation on local_irq_disable/enable()
    added per Michal Hocko.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
---
 include/linux/cgroup.h |  6 ------
 kernel/cgroup.c        | 31 ++++++++++++-------------------
 mm/memcontrol.c        |  7 +++----
 3 files changed, 15 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 02e09c0e98ab..a3098046250b 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -85,7 +85,6 @@ struct cgroup_subsys_state {
 /* bits in struct cgroup_subsys_state flags field */
 enum {
 	CSS_ROOT, /* This CSS is the root of the subsystem */
-	CSS_REMOVED, /* This CSS is dead */
 };
 
 /* Caller must verify that the css is not for root cgroup */
@@ -108,11 +107,6 @@ static inline void css_get(struct cgroup_subsys_state *css)
 		__css_get(css, 1);
 }
 
-static inline bool css_is_removed(struct cgroup_subsys_state *css)
-{
-	return test_bit(CSS_REMOVED, &css->flags);
-}
-
 /*
  * Call css_tryget() to take a reference on a css if your existing
  * (known-valid) reference isn't already ref-counted. Returns false if
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8c605e2bdd1a..c194f9e4fc7b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -170,8 +170,8 @@ struct css_id {
 	 * The css to which this ID points. This pointer is set to valid value
 	 * after cgroup is populated. If cgroup is removed, this will be NULL.
 	 * This pointer is expected to be RCU-safe because destroy()
-	 * is called after synchronize_rcu(). But for safe use, css_is_removed()
-	 * css_tryget() should be used for avoiding race.
+	 * is called after synchronize_rcu(). But for safe use, css_tryget()
+	 * should be used for avoiding race.
 	 */
 	struct cgroup_subsys_state __rcu *css;
 	/*
@@ -4112,8 +4112,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	}
 	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
 
-	local_irq_disable();
-
 	/* block new css_tryget() by deactivating refcnt */
 	for_each_subsys(cgrp->root, ss) {
 		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
@@ -4123,21 +4121,14 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	}
 
 	/*
-	 * Set REMOVED.  All in-progress css_tryget() will be released.
 	 * Put all the base refs.  Each css holds an extra reference to the
 	 * cgroup's dentry and cgroup removal proceeds regardless of css
 	 * refs.  On the last put of each css, whenever that may be, the
 	 * extra dentry ref is put so that dentry destruction happens only
 	 * after all css's are released.
 	 */
-	for_each_subsys(cgrp->root, ss) {
-		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
-
-		set_bit(CSS_REMOVED, &css->flags);
-		css_put(css);
-	}
-
-	local_irq_enable();
+	for_each_subsys(cgrp->root, ss)
+		css_put(cgrp->subsys[ss->subsys_id]);
 
 	finish_wait(&cgroup_rmdir_waitq, &wait);
 	clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
@@ -4861,15 +4852,17 @@ static void check_for_release(struct cgroup *cgrp)
 /* Caller must verify that the css is not for root cgroup */
 bool __css_tryget(struct cgroup_subsys_state *css)
 {
-	do {
-		int v = css_refcnt(css);
+	while (true) {
+		int t, v;
 
-		if (atomic_cmpxchg(&css->refcnt, v, v + 1) == v)
+		v = css_refcnt(css);
+		t = atomic_cmpxchg(&css->refcnt, v, v + 1);
+		if (likely(t == v))
 			return true;
+		else if (t < 0)
+			return false;
 		cpu_relax();
-	} while (!test_bit(CSS_REMOVED, &css->flags));
-
-	return false;
+	}
 }
 EXPORT_SYMBOL_GPL(__css_tryget);
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5a1d584ffed3..37c356646544 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2343,7 +2343,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 again:
 	if (*ptr) { /* css should be a valid one */
 		memcg = *ptr;
-		VM_BUG_ON(css_is_removed(&memcg->css));
 		if (mem_cgroup_is_root(memcg))
 			goto done;
 		if (nr_pages == 1 && consume_stock(memcg))
@@ -2483,9 +2482,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
 
 /*
  * A helper function to get mem_cgroup from ID. must be called under
- * rcu_read_lock(). The caller must check css_is_removed() or some if
- * it's concern. (dropping refcnt from swap can be called against removed
- * memcg.)
+ * rcu_read_lock().  The caller is responsible for calling css_tryget if
+ * the mem_cgroup is used for charging. (dropping refcnt from swap can be
+ * called against removed memcg.)
  */
 static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 {
-- 
cgit v1.2.3-55-g7522


From b25ed609d0eecf077db607e88ea70bae83b6adb2 Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 5 Nov 2012 09:16:59 -0800
Subject: cgroup: remove CGRP_WAIT_ON_RMDIR, cgroup_exclude_rmdir() and
 cgroup_release_and_wakeup_rmdir()

CGRP_WAIT_ON_RMDIR is another kludge which was added to make cgroup
destruction rollback somewhat working.  cgroup_rmdir() used to drain
CSS references and CGRP_WAIT_ON_RMDIR and the associated waitqueue and
helpers were used to allow the task performing rmdir to wait for the
next relevant event.

Unfortunately, the wait is visible to controllers too and the
mechanism got exposed to memcg by 887032670d ("cgroup avoid permanent
sleep at rmdir").

Now that the draining and retries are gone, CGRP_WAIT_ON_RMDIR is
unnecessary.  Remove it and all the mechanisms supporting it.  Note
that memcontrol.c changes are essentially revert of 887032670d
("cgroup avoid permanent sleep at rmdir").

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Balbir Singh <bsingharora@gmail.com>
---
 include/linux/cgroup.h | 21 ---------------------
 kernel/cgroup.c        | 51 --------------------------------------------------
 mm/memcontrol.c        | 24 +-----------------------
 3 files changed, 1 insertion(+), 95 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index a3098046250b..47868a86ba2b 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -144,10 +144,6 @@ enum {
 	CGRP_RELEASABLE,
 	/* Control Group requires release notifications to userspace */
 	CGRP_NOTIFY_ON_RELEASE,
-	/*
-	 * A thread in rmdir() is wating for this cgroup.
-	 */
-	CGRP_WAIT_ON_RMDIR,
 	/*
 	 * Clone cgroup values when creating a new child cgroup
 	 */
@@ -411,23 +407,6 @@ int cgroup_task_count(const struct cgroup *cgrp);
 /* Return true if cgrp is a descendant of the task's cgroup */
 int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task);
 
-/*
- * When the subsys has to access css and may add permanent refcnt to css,
- * it should take care of racy conditions with rmdir(). Following set of
- * functions, is for stop/restart rmdir if necessary.
- * Because these will call css_get/put, "css" should be alive css.
- *
- *  cgroup_exclude_rmdir();
- *  ...do some jobs which may access arbitrary empty cgroup
- *  cgroup_release_and_wakeup_rmdir();
- *
- *  When someone removes a cgroup while cgroup_exclude_rmdir() holds it,
- *  it sleeps and cgroup_release_and_wakeup_rmdir() will wake him up.
- */
-
-void cgroup_exclude_rmdir(struct cgroup_subsys_state *css);
-void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css);
-
 /*
  * Control Group taskset, used to pass around set of tasks to cgroup_subsys
  * methods.
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 66204a6f68f3..c5f6fb28dd0e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -965,33 +965,6 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
 	remove_dir(dentry);
 }
 
-/*
- * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
- * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
- * reference to css->refcnt. In general, this refcnt is expected to goes down
- * to zero, soon.
- *
- * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
- */
-static DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
-
-static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
-{
-	if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
-		wake_up_all(&cgroup_rmdir_waitq);
-}
-
-void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
-{
-	css_get(css);
-}
-
-void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
-{
-	cgroup_wakeup_rmdir_waiter(css->cgroup);
-	css_put(css);
-}
-
 /*
  * Call with cgroup_mutex held. Drops reference counts on modules, including
  * any duplicate ones that parse_cgroupfs_options took. If this function
@@ -1963,12 +1936,6 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	}
 
 	synchronize_rcu();
-
-	/*
-	 * wake up rmdir() waiter. the rmdir should fail since the cgroup
-	 * is no longer empty.
-	 */
-	cgroup_wakeup_rmdir_waiter(cgrp);
 out:
 	if (retval) {
 		for_each_subsys(root, ss) {
@@ -2138,7 +2105,6 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	 * step 5: success! and cleanup
 	 */
 	synchronize_rcu();
-	cgroup_wakeup_rmdir_waiter(cgrp);
 	retval = 0;
 out_put_css_set_refs:
 	if (retval) {
@@ -4058,26 +4024,13 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	struct cgroup_event *event, *tmp;
 	struct cgroup_subsys *ss;
 
-	/*
-	 * In general, subsystem has no css->refcnt after pre_destroy(). But
-	 * in racy cases, subsystem may have to get css->refcnt after
-	 * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
-	 * make rmdir return -EBUSY too often. To avoid that, we use waitqueue
-	 * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
-	 * and subsystem's reference count handling. Please see css_get/put
-	 * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
-	 */
-	set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-
 	/* the vfs holds both inode->i_mutex already */
 	mutex_lock(&cgroup_mutex);
 	parent = cgrp->parent;
 	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
-		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
 		mutex_unlock(&cgroup_mutex);
 		return -EBUSY;
 	}
-	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
 
 	/*
 	 * Block new css_tryget() by deactivating refcnt and mark @cgrp
@@ -4114,9 +4067,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	for_each_subsys(cgrp->root, ss)
 		css_put(cgrp->subsys[ss->subsys_id]);
 
-	finish_wait(&cgroup_rmdir_waitq, &wait);
-	clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
-
 	raw_spin_lock(&release_list_lock);
 	if (!list_empty(&cgrp->release_list))
 		list_del_init(&cgrp->release_list);
@@ -4864,7 +4814,6 @@ void __css_put(struct cgroup_subsys_state *css)
 			set_bit(CGRP_RELEASABLE, &cgrp->flags);
 			check_for_release(cgrp);
 		}
-		cgroup_wakeup_rmdir_waiter(cgrp);
 		break;
 	case 0:
 		schedule_work(&css->dput_work);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 37c356646544..930edfaa5187 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2681,13 +2681,6 @@ static int mem_cgroup_move_account(struct page *page,
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
 	mem_cgroup_charge_statistics(to, anon, nr_pages);
-	/*
-	 * We charges against "to" which may not have any tasks. Then, "to"
-	 * can be under rmdir(). But in current implementation, caller of
-	 * this function is just force_empty() and move charge, so it's
-	 * guaranteed that "to" is never removed. So, we don't check rmdir
-	 * status here.
-	 */
 	move_unlock_mem_cgroup(from, &flags);
 	ret = 0;
 unlock:
@@ -2893,7 +2886,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 		return;
 	if (!memcg)
 		return;
-	cgroup_exclude_rmdir(&memcg->css);
 
 	__mem_cgroup_commit_charge(memcg, page, 1, ctype, true);
 	/*
@@ -2907,12 +2899,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 		swp_entry_t ent = {.val = page_private(page)};
 		mem_cgroup_uncharge_swap(ent);
 	}
-	/*
-	 * At swapin, we may charge account against cgroup which has no tasks.
-	 * So, rmdir()->pre_destroy() can be called while we do this charge.
-	 * In that case, we need to call pre_destroy() again. check it here.
-	 */
-	cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
 void mem_cgroup_commit_charge_swapin(struct page *page,
@@ -3360,8 +3346,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 
 	if (!memcg)
 		return;
-	/* blocks rmdir() */
-	cgroup_exclude_rmdir(&memcg->css);
+
 	if (!migration_ok) {
 		used = oldpage;
 		unused = newpage;
@@ -3395,13 +3380,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	 */
 	if (anon)
 		mem_cgroup_uncharge_page(used);
-	/*
-	 * At migration, we may charge account against cgroup which has no
-	 * tasks.
-	 * So, rmdir()->pre_destroy() can be called while we do this charge.
-	 * In that case, we need to call pre_destroy() again. check it here.
-	 */
-	cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
 /*
-- 
cgit v1.2.3-55-g7522


From bcf6de1b9129531215d26dd9af8331e84973bc52 Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 5 Nov 2012 09:16:59 -0800
Subject: cgroup: make ->pre_destroy() return void

All ->pre_destory() implementations return 0 now, which is the only
allowed return value.  Make it return void.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
---
 block/blk-cgroup.c     | 3 +--
 include/linux/cgroup.h | 2 +-
 kernel/cgroup.c        | 2 +-
 mm/hugetlb_cgroup.c    | 4 +---
 mm/memcontrol.c        | 3 +--
 5 files changed, 5 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index f3b44a65fc7a..a7816f3d0059 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -600,7 +600,7 @@ struct cftype blkcg_files[] = {
  *
  * This is the blkcg counterpart of ioc_release_fn().
  */
-static int blkcg_pre_destroy(struct cgroup *cgroup)
+static void blkcg_pre_destroy(struct cgroup *cgroup)
 {
 	struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
 
@@ -622,7 +622,6 @@ static int blkcg_pre_destroy(struct cgroup *cgroup)
 	}
 
 	spin_unlock_irq(&blkcg->lock);
-	return 0;
 }
 
 static void blkcg_destroy(struct cgroup *cgroup)
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 47868a86ba2b..adb2adc8ec1a 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -436,7 +436,7 @@ int cgroup_taskset_size(struct cgroup_taskset *tset);
 
 struct cgroup_subsys {
 	struct cgroup_subsys_state *(*create)(struct cgroup *cgrp);
-	int (*pre_destroy)(struct cgroup *cgrp);
+	void (*pre_destroy)(struct cgroup *cgrp);
 	void (*destroy)(struct cgroup *cgrp);
 	int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c5f6fb28dd0e..83cd7d041c62 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4054,7 +4054,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	mutex_unlock(&cgroup_mutex);
 	for_each_subsys(cgrp->root, ss)
 		if (ss->pre_destroy)
-			WARN_ON_ONCE(ss->pre_destroy(cgrp));
+			ss->pre_destroy(cgrp);
 	mutex_lock(&cgroup_mutex);
 
 	/*
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index dc595c6b1f55..0d3a1a317731 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -155,7 +155,7 @@ out:
  * Force the hugetlb cgroup to empty the hugetlb resources by moving them to
  * the parent cgroup.
  */
-static int hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
+static void hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
 {
 	struct hstate *h;
 	struct page *page;
@@ -172,8 +172,6 @@ static int hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
 		}
 		cond_resched();
 	} while (hugetlb_cgroup_have_usage(cgroup));
-
-	return 0;
 }
 
 int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6678f991c6c6..a1811ce60e20 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5002,12 +5002,11 @@ free_out:
 	return ERR_PTR(error);
 }
 
-static int mem_cgroup_pre_destroy(struct cgroup *cont)
+static void mem_cgroup_pre_destroy(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
 	mem_cgroup_reparent_charges(memcg);
-	return 0;
 }
 
 static void mem_cgroup_destroy(struct cgroup *cont)
-- 
cgit v1.2.3-55-g7522


From cc95e347cbba3a29c6f8c95ec737624afe489d8e Mon Sep 17 00:00:00 2001
From: Stephen Warren
Date: Wed, 19 Sep 2012 15:51:01 -0600
Subject: ARM: tegra: move tegra-ahb.h out of arch/arm/mach-tegra/

We wish to empty arch/arm/mach-tegra/include/mach/ as much as possible
to enable single zImage. Move tegra-ahb.h to a more central location
(suggested by Arnd, OK'd by Greg KH), and actually make tegra-ahb.c
include the header to ensure client and provider agree on the prototype.

Signed-off-by: Stephen Warren <swarren@nvidia.com>
---
 arch/arm/mach-tegra/include/mach/tegra-ahb.h | 19 -------------------
 drivers/amba/tegra-ahb.c                     |  1 +
 drivers/iommu/tegra-smmu.c                   |  3 +--
 include/linux/tegra-ahb.h                    | 19 +++++++++++++++++++
 4 files changed, 21 insertions(+), 21 deletions(-)
 delete mode 100644 arch/arm/mach-tegra/include/mach/tegra-ahb.h
 create mode 100644 include/linux/tegra-ahb.h

(limited to 'include')

diff --git a/arch/arm/mach-tegra/include/mach/tegra-ahb.h b/arch/arm/mach-tegra/include/mach/tegra-ahb.h
deleted file mode 100644
index e0f8c84b1d8c..000000000000
--- a/arch/arm/mach-tegra/include/mach/tegra-ahb.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- */
-
-#ifndef __MACH_TEGRA_AHB_H__
-#define __MACH_TEGRA_AHB_H__
-
-extern int tegra_ahb_enable_smmu(struct device_node *ahb);
-
-#endif	/* __MACH_TEGRA_AHB_H__ */
diff --git a/drivers/amba/tegra-ahb.c b/drivers/amba/tegra-ahb.c
index 0b6f0b28a487..bd5de08ad6fd 100644
--- a/drivers/amba/tegra-ahb.c
+++ b/drivers/amba/tegra-ahb.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
+#include <linux/tegra-ahb.h>
 
 #define DRV_NAME "tegra-ahb"
 
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 3fb95dde20f5..41678639b7e3 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -34,12 +34,11 @@
 #include <linux/of_iommu.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/tegra-ahb.h>
 
 #include <asm/page.h>
 #include <asm/cacheflush.h>
 
-#include <mach/tegra-ahb.h>
-
 enum smmu_hwgrp {
 	HWGRP_AFI,
 	HWGRP_AVPC,
diff --git a/include/linux/tegra-ahb.h b/include/linux/tegra-ahb.h
new file mode 100644
index 000000000000..f1cd075ceee1
--- /dev/null
+++ b/include/linux/tegra-ahb.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __LINUX_AHB_H__
+#define __LINUX_AHB_H__
+
+extern int tegra_ahb_enable_smmu(struct device_node *ahb);
+
+#endif	/* __LINUX_AHB_H__ */
-- 
cgit v1.2.3-55-g7522


From 4eb3ccf157639a9d9c7829de94017c46c73d9cc4 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Mon, 5 Nov 2012 09:56:00 +0000
Subject: staging:iio: Move the ad7887 driver out of staging

The driver does not expose any custom API to userspace and none of the standard
static code checker tools report any issues, so move it out of staging.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/adc/Kconfig              |  13 ++
 drivers/iio/adc/Makefile             |   1 +
 drivers/iio/adc/ad7887.c             | 378 +++++++++++++++++++++++++++++++++++
 drivers/staging/iio/adc/Kconfig      |  13 --
 drivers/staging/iio/adc/Makefile     |   2 -
 drivers/staging/iio/adc/ad7887.c     | 378 -----------------------------------
 drivers/staging/iio/adc/ad7887.h     |  31 ---
 include/linux/platform_data/ad7887.h |  26 +++
 8 files changed, 418 insertions(+), 424 deletions(-)
 create mode 100644 drivers/iio/adc/ad7887.c
 delete mode 100644 drivers/staging/iio/adc/ad7887.c
 delete mode 100644 drivers/staging/iio/adc/ad7887.h
 create mode 100644 include/linux/platform_data/ad7887.h

(limited to 'include')

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 492758120338..706386ba02e3 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -45,6 +45,19 @@ config AD7476
 	  To compile this driver as a module, choose M here: the
 	  module will be called ad7476.
 
+config AD7887
+	tristate "Analog Devices AD7887 ADC driver"
+	depends on SPI
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
+	help
+	  Say yes here to build support for Analog Devices
+	  AD7887 SPI analog to digital converter (ADC).
+	  If unsure, say N (but it's safe to say "Y").
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ad7887.
+
 config AT91_ADC
 	tristate "Atmel AT91 ADC"
 	depends on ARCH_AT91
diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile
index 900995d5e179..034eacb8f7c9 100644
--- a/drivers/iio/adc/Makefile
+++ b/drivers/iio/adc/Makefile
@@ -6,5 +6,6 @@ obj-$(CONFIG_AD_SIGMA_DELTA) += ad_sigma_delta.o
 obj-$(CONFIG_AD7266) += ad7266.o
 obj-$(CONFIG_AD7476) += ad7476.o
 obj-$(CONFIG_AD7791) += ad7791.o
+obj-$(CONFIG_AD7887) += ad7887.o
 obj-$(CONFIG_AT91_ADC) += at91_adc.o
 obj-$(CONFIG_LP8788_ADC) += lp8788_adc.o
diff --git a/drivers/iio/adc/ad7887.c b/drivers/iio/adc/ad7887.c
new file mode 100644
index 000000000000..fd62309b4d3d
--- /dev/null
+++ b/drivers/iio/adc/ad7887.c
@@ -0,0 +1,378 @@
+/*
+ * AD7887 SPI ADC driver
+ *
+ * Copyright 2010-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/spi/spi.h>
+#include <linux/regulator/consumer.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/iio/buffer.h>
+
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
+
+#include <linux/platform_data/ad7887.h>
+
+#define AD7887_REF_DIS		(1 << 5) /* on-chip reference disable */
+#define AD7887_DUAL		(1 << 4) /* dual-channel mode */
+#define AD7887_CH_AIN1		(1 << 3) /* convert on channel 1, DUAL=1 */
+#define AD7887_CH_AIN0		(0 << 3) /* convert on channel 0, DUAL=0,1 */
+#define AD7887_PM_MODE1		(0)	 /* CS based shutdown */
+#define AD7887_PM_MODE2		(1)	 /* full on */
+#define AD7887_PM_MODE3		(2)	 /* auto shutdown after conversion */
+#define AD7887_PM_MODE4		(3)	 /* standby mode */
+
+enum ad7887_channels {
+	AD7887_CH0,
+	AD7887_CH0_CH1,
+	AD7887_CH1,
+};
+
+#define RES_MASK(bits)	((1 << (bits)) - 1)
+
+/**
+ * struct ad7887_chip_info - chip specifc information
+ * @int_vref_mv:	the internal reference voltage
+ * @channel:		channel specification
+ */
+struct ad7887_chip_info {
+	u16				int_vref_mv;
+	struct iio_chan_spec		channel[3];
+};
+
+struct ad7887_state {
+	struct spi_device		*spi;
+	const struct ad7887_chip_info	*chip_info;
+	struct regulator		*reg;
+	struct spi_transfer		xfer[4];
+	struct spi_message		msg[3];
+	struct spi_message		*ring_msg;
+	unsigned char			tx_cmd_buf[4];
+
+	/*
+	 * DMA (thus cache coherency maintenance) requires the
+	 * transfer buffers to live in their own cache lines.
+	 * Buffer needs to be large enough to hold two 16 bit samples and a
+	 * 64 bit aligned 64 bit timestamp.
+	 */
+	unsigned char data[ALIGN(4, sizeof(s64)) + sizeof(s64)]
+		____cacheline_aligned;
+};
+
+enum ad7887_supported_device_ids {
+	ID_AD7887
+};
+
+static int ad7887_ring_preenable(struct iio_dev *indio_dev)
+{
+	struct ad7887_state *st = iio_priv(indio_dev);
+	int ret;
+
+	ret = iio_sw_buffer_preenable(indio_dev);
+	if (ret < 0)
+		return ret;
+
+	/* We know this is a single long so can 'cheat' */
+	switch (*indio_dev->active_scan_mask) {
+	case (1 << 0):
+		st->ring_msg = &st->msg[AD7887_CH0];
+		break;
+	case (1 << 1):
+		st->ring_msg = &st->msg[AD7887_CH1];
+		/* Dummy read: push CH1 setting down to hardware */
+		spi_sync(st->spi, st->ring_msg);
+		break;
+	case ((1 << 1) | (1 << 0)):
+		st->ring_msg = &st->msg[AD7887_CH0_CH1];
+		break;
+	}
+
+	return 0;
+}
+
+static int ad7887_ring_postdisable(struct iio_dev *indio_dev)
+{
+	struct ad7887_state *st = iio_priv(indio_dev);
+
+	/* dummy read: restore default CH0 settin */
+	return spi_sync(st->spi, &st->msg[AD7887_CH0]);
+}
+
+/**
+ * ad7887_trigger_handler() bh of trigger launched polling to ring buffer
+ *
+ * Currently there is no option in this driver to disable the saving of
+ * timestamps within the ring.
+ **/
+static irqreturn_t ad7887_trigger_handler(int irq, void *p)
+{
+	struct iio_poll_func *pf = p;
+	struct iio_dev *indio_dev = pf->indio_dev;
+	struct ad7887_state *st = iio_priv(indio_dev);
+	s64 time_ns;
+	int b_sent;
+
+	b_sent = spi_sync(st->spi, st->ring_msg);
+	if (b_sent)
+		goto done;
+
+	time_ns = iio_get_time_ns();
+
+	if (indio_dev->scan_timestamp)
+		memcpy(st->data + indio_dev->scan_bytes - sizeof(s64),
+		       &time_ns, sizeof(time_ns));
+
+	iio_push_to_buffer(indio_dev->buffer, st->data);
+done:
+	iio_trigger_notify_done(indio_dev->trig);
+
+	return IRQ_HANDLED;
+}
+
+static const struct iio_buffer_setup_ops ad7887_ring_setup_ops = {
+	.preenable = &ad7887_ring_preenable,
+	.postenable = &iio_triggered_buffer_postenable,
+	.predisable = &iio_triggered_buffer_predisable,
+	.postdisable = &ad7887_ring_postdisable,
+};
+
+static int ad7887_scan_direct(struct ad7887_state *st, unsigned ch)
+{
+	int ret = spi_sync(st->spi, &st->msg[ch]);
+	if (ret)
+		return ret;
+
+	return (st->data[(ch * 2)] << 8) | st->data[(ch * 2) + 1];
+}
+
+static int ad7887_read_raw(struct iio_dev *indio_dev,
+			   struct iio_chan_spec const *chan,
+			   int *val,
+			   int *val2,
+			   long m)
+{
+	int ret;
+	struct ad7887_state *st = iio_priv(indio_dev);
+
+	switch (m) {
+	case IIO_CHAN_INFO_RAW:
+		mutex_lock(&indio_dev->mlock);
+		if (iio_buffer_enabled(indio_dev))
+			ret = -EBUSY;
+		else
+			ret = ad7887_scan_direct(st, chan->address);
+		mutex_unlock(&indio_dev->mlock);
+
+		if (ret < 0)
+			return ret;
+		*val = ret >> chan->scan_type.shift;
+		*val &= RES_MASK(chan->scan_type.realbits);
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		if (st->reg) {
+			*val = regulator_get_voltage(st->reg);
+			if (*val < 0)
+				return *val;
+			*val /= 1000;
+		} else {
+			*val = st->chip_info->int_vref_mv;
+		}
+
+		*val2 = chan->scan_type.realbits;
+
+		return IIO_VAL_FRACTIONAL_LOG2;
+	}
+	return -EINVAL;
+}
+
+
+static const struct ad7887_chip_info ad7887_chip_info_tbl[] = {
+	/*
+	 * More devices added in future
+	 */
+	[ID_AD7887] = {
+		.channel[0] = {
+			.type = IIO_VOLTAGE,
+			.indexed = 1,
+			.channel = 1,
+			.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT |
+			IIO_CHAN_INFO_SCALE_SHARED_BIT,
+			.address = 1,
+			.scan_index = 1,
+			.scan_type = IIO_ST('u', 12, 16, 0),
+		},
+		.channel[1] = {
+			.type = IIO_VOLTAGE,
+			.indexed = 1,
+			.channel = 0,
+			.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT |
+			IIO_CHAN_INFO_SCALE_SHARED_BIT,
+			.address = 0,
+			.scan_index = 0,
+			.scan_type = IIO_ST('u', 12, 16, 0),
+		},
+		.channel[2] = IIO_CHAN_SOFT_TIMESTAMP(2),
+		.int_vref_mv = 2500,
+	},
+};
+
+static const struct iio_info ad7887_info = {
+	.read_raw = &ad7887_read_raw,
+	.driver_module = THIS_MODULE,
+};
+
+static int __devinit ad7887_probe(struct spi_device *spi)
+{
+	struct ad7887_platform_data *pdata = spi->dev.platform_data;
+	struct ad7887_state *st;
+	struct iio_dev *indio_dev = iio_device_alloc(sizeof(*st));
+	uint8_t mode;
+	int ret;
+
+	if (indio_dev == NULL)
+		return -ENOMEM;
+
+	st = iio_priv(indio_dev);
+
+	if (!pdata || !pdata->use_onchip_ref) {
+		st->reg = regulator_get(&spi->dev, "vref");
+		if (IS_ERR(st->reg)) {
+			ret = PTR_ERR(st->reg);
+			goto error_free;
+		}
+
+		ret = regulator_enable(st->reg);
+		if (ret)
+			goto error_put_reg;
+	}
+
+	st->chip_info =
+		&ad7887_chip_info_tbl[spi_get_device_id(spi)->driver_data];
+
+	spi_set_drvdata(spi, indio_dev);
+	st->spi = spi;
+
+	/* Estabilish that the iio_dev is a child of the spi device */
+	indio_dev->dev.parent = &spi->dev;
+	indio_dev->name = spi_get_device_id(spi)->name;
+	indio_dev->info = &ad7887_info;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+
+	/* Setup default message */
+
+	mode = AD7887_PM_MODE4;
+	if (!pdata || !pdata->use_onchip_ref)
+		mode |= AD7887_REF_DIS;
+	if (pdata && pdata->en_dual)
+		mode |= AD7887_DUAL;
+
+	st->tx_cmd_buf[0] = AD7887_CH_AIN0 | mode;
+
+	st->xfer[0].rx_buf = &st->data[0];
+	st->xfer[0].tx_buf = &st->tx_cmd_buf[0];
+	st->xfer[0].len = 2;
+
+	spi_message_init(&st->msg[AD7887_CH0]);
+	spi_message_add_tail(&st->xfer[0], &st->msg[AD7887_CH0]);
+
+	if (pdata && pdata->en_dual) {
+		st->tx_cmd_buf[2] = AD7887_CH_AIN1 | mode;
+
+		st->xfer[1].rx_buf = &st->data[0];
+		st->xfer[1].tx_buf = &st->tx_cmd_buf[2];
+		st->xfer[1].len = 2;
+
+		st->xfer[2].rx_buf = &st->data[2];
+		st->xfer[2].tx_buf = &st->tx_cmd_buf[0];
+		st->xfer[2].len = 2;
+
+		spi_message_init(&st->msg[AD7887_CH0_CH1]);
+		spi_message_add_tail(&st->xfer[1], &st->msg[AD7887_CH0_CH1]);
+		spi_message_add_tail(&st->xfer[2], &st->msg[AD7887_CH0_CH1]);
+
+		st->xfer[3].rx_buf = &st->data[2];
+		st->xfer[3].tx_buf = &st->tx_cmd_buf[2];
+		st->xfer[3].len = 2;
+
+		spi_message_init(&st->msg[AD7887_CH1]);
+		spi_message_add_tail(&st->xfer[3], &st->msg[AD7887_CH1]);
+
+		indio_dev->channels = st->chip_info->channel;
+		indio_dev->num_channels = 3;
+	} else {
+		indio_dev->channels = &st->chip_info->channel[1];
+		indio_dev->num_channels = 2;
+	}
+
+	ret = iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+			&ad7887_trigger_handler, &ad7887_ring_setup_ops);
+	if (ret)
+		goto error_disable_reg;
+
+	ret = iio_device_register(indio_dev);
+	if (ret)
+		goto error_unregister_ring;
+
+	return 0;
+error_unregister_ring:
+	iio_triggered_buffer_cleanup(indio_dev);
+error_disable_reg:
+	if (st->reg)
+		regulator_disable(st->reg);
+error_put_reg:
+	if (st->reg)
+		regulator_put(st->reg);
+error_free:
+	iio_device_free(indio_dev);
+
+	return ret;
+}
+
+static int __devexit ad7887_remove(struct spi_device *spi)
+{
+	struct iio_dev *indio_dev = spi_get_drvdata(spi);
+	struct ad7887_state *st = iio_priv(indio_dev);
+
+	iio_device_unregister(indio_dev);
+	iio_triggered_buffer_cleanup(indio_dev);
+	if (st->reg) {
+		regulator_disable(st->reg);
+		regulator_put(st->reg);
+	}
+	iio_device_free(indio_dev);
+
+	return 0;
+}
+
+static const struct spi_device_id ad7887_id[] = {
+	{"ad7887", ID_AD7887},
+	{}
+};
+MODULE_DEVICE_TABLE(spi, ad7887_id);
+
+static struct spi_driver ad7887_driver = {
+	.driver = {
+		.name	= "ad7887",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= ad7887_probe,
+	.remove		= __devexit_p(ad7887_remove),
+	.id_table	= ad7887_id,
+};
+module_spi_driver(ad7887_driver);
+
+MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>");
+MODULE_DESCRIPTION("Analog Devices AD7887 ADC");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/staging/iio/adc/Kconfig b/drivers/staging/iio/adc/Kconfig
index 71a515d0a6de..eba64fb64d82 100644
--- a/drivers/staging/iio/adc/Kconfig
+++ b/drivers/staging/iio/adc/Kconfig
@@ -68,19 +68,6 @@ config AD799X_RING_BUFFER
 	  Say yes here to include ring buffer support in the AD799X
 	  ADC driver.
 
-config AD7887
-	tristate "Analog Devices AD7887 ADC driver"
-	depends on SPI
-	select IIO_BUFFER
-	select IIO_TRIGGERED_BUFFER
-	help
-	  Say yes here to build support for Analog Devices
-	  AD7887 SPI analog to digital converter (ADC).
-	  If unsure, say N (but it's safe to say "Y").
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called ad7887.
-
 config AD7780
 	tristate "Analog Devices AD7780 and similar ADCs driver"
 	depends on SPI
diff --git a/drivers/staging/iio/adc/Makefile b/drivers/staging/iio/adc/Makefile
index 8036fd14f68a..c56b41ee285b 100644
--- a/drivers/staging/iio/adc/Makefile
+++ b/drivers/staging/iio/adc/Makefile
@@ -17,8 +17,6 @@ ad799x-y := ad799x_core.o
 ad799x-$(CONFIG_AD799X_RING_BUFFER) += ad799x_ring.o
 obj-$(CONFIG_AD799X) += ad799x.o
 
-obj-$(CONFIG_AD7887) += ad7887.o
-
 ad7298-y := ad7298_core.o
 ad7298-$(CONFIG_IIO_BUFFER) += ad7298_ring.o
 obj-$(CONFIG_AD7298) += ad7298.o
diff --git a/drivers/staging/iio/adc/ad7887.c b/drivers/staging/iio/adc/ad7887.c
deleted file mode 100644
index 72cfe191cd83..000000000000
--- a/drivers/staging/iio/adc/ad7887.c
+++ /dev/null
@@ -1,378 +0,0 @@
-/*
- * AD7887 SPI ADC driver
- *
- * Copyright 2010-2011 Analog Devices Inc.
- *
- * Licensed under the GPL-2.
- */
-
-#include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/sysfs.h>
-#include <linux/spi/spi.h>
-#include <linux/regulator/consumer.h>
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/interrupt.h>
-
-#include <linux/iio/iio.h>
-#include <linux/iio/sysfs.h>
-#include <linux/iio/buffer.h>
-
-#include <linux/iio/trigger_consumer.h>
-#include <linux/iio/triggered_buffer.h>
-
-#include "ad7887.h"
-
-#define AD7887_REF_DIS		(1 << 5) /* on-chip reference disable */
-#define AD7887_DUAL		(1 << 4) /* dual-channel mode */
-#define AD7887_CH_AIN1		(1 << 3) /* convert on channel 1, DUAL=1 */
-#define AD7887_CH_AIN0		(0 << 3) /* convert on channel 0, DUAL=0,1 */
-#define AD7887_PM_MODE1		(0)	 /* CS based shutdown */
-#define AD7887_PM_MODE2		(1)	 /* full on */
-#define AD7887_PM_MODE3		(2)	 /* auto shutdown after conversion */
-#define AD7887_PM_MODE4		(3)	 /* standby mode */
-
-enum ad7887_channels {
-	AD7887_CH0,
-	AD7887_CH0_CH1,
-	AD7887_CH1,
-};
-
-#define RES_MASK(bits)	((1 << (bits)) - 1)
-
-/**
- * struct ad7887_chip_info - chip specifc information
- * @int_vref_mv:	the internal reference voltage
- * @channel:		channel specification
- */
-struct ad7887_chip_info {
-	u16				int_vref_mv;
-	struct iio_chan_spec		channel[3];
-};
-
-struct ad7887_state {
-	struct spi_device		*spi;
-	const struct ad7887_chip_info	*chip_info;
-	struct regulator		*reg;
-	struct spi_transfer		xfer[4];
-	struct spi_message		msg[3];
-	struct spi_message		*ring_msg;
-	unsigned char			tx_cmd_buf[4];
-
-	/*
-	 * DMA (thus cache coherency maintenance) requires the
-	 * transfer buffers to live in their own cache lines.
-	 * Buffer needs to be large enough to hold two 16 bit samples and a
-	 * 64 bit aligned 64 bit timestamp.
-	 */
-	unsigned char data[ALIGN(4, sizeof(s64)) + sizeof(s64)]
-		____cacheline_aligned;
-};
-
-enum ad7887_supported_device_ids {
-	ID_AD7887
-};
-
-static int ad7887_ring_preenable(struct iio_dev *indio_dev)
-{
-	struct ad7887_state *st = iio_priv(indio_dev);
-	int ret;
-
-	ret = iio_sw_buffer_preenable(indio_dev);
-	if (ret < 0)
-		return ret;
-
-	/* We know this is a single long so can 'cheat' */
-	switch (*indio_dev->active_scan_mask) {
-	case (1 << 0):
-		st->ring_msg = &st->msg[AD7887_CH0];
-		break;
-	case (1 << 1):
-		st->ring_msg = &st->msg[AD7887_CH1];
-		/* Dummy read: push CH1 setting down to hardware */
-		spi_sync(st->spi, st->ring_msg);
-		break;
-	case ((1 << 1) | (1 << 0)):
-		st->ring_msg = &st->msg[AD7887_CH0_CH1];
-		break;
-	}
-
-	return 0;
-}
-
-static int ad7887_ring_postdisable(struct iio_dev *indio_dev)
-{
-	struct ad7887_state *st = iio_priv(indio_dev);
-
-	/* dummy read: restore default CH0 settin */
-	return spi_sync(st->spi, &st->msg[AD7887_CH0]);
-}
-
-/**
- * ad7887_trigger_handler() bh of trigger launched polling to ring buffer
- *
- * Currently there is no option in this driver to disable the saving of
- * timestamps within the ring.
- **/
-static irqreturn_t ad7887_trigger_handler(int irq, void *p)
-{
-	struct iio_poll_func *pf = p;
-	struct iio_dev *indio_dev = pf->indio_dev;
-	struct ad7887_state *st = iio_priv(indio_dev);
-	s64 time_ns;
-	int b_sent;
-
-	b_sent = spi_sync(st->spi, st->ring_msg);
-	if (b_sent)
-		goto done;
-
-	time_ns = iio_get_time_ns();
-
-	if (indio_dev->scan_timestamp)
-		memcpy(st->data + indio_dev->scan_bytes - sizeof(s64),
-		       &time_ns, sizeof(time_ns));
-
-	iio_push_to_buffer(indio_dev->buffer, st->data);
-done:
-	iio_trigger_notify_done(indio_dev->trig);
-
-	return IRQ_HANDLED;
-}
-
-static const struct iio_buffer_setup_ops ad7887_ring_setup_ops = {
-	.preenable = &ad7887_ring_preenable,
-	.postenable = &iio_triggered_buffer_postenable,
-	.predisable = &iio_triggered_buffer_predisable,
-	.postdisable = &ad7887_ring_postdisable,
-};
-
-static int ad7887_scan_direct(struct ad7887_state *st, unsigned ch)
-{
-	int ret = spi_sync(st->spi, &st->msg[ch]);
-	if (ret)
-		return ret;
-
-	return (st->data[(ch * 2)] << 8) | st->data[(ch * 2) + 1];
-}
-
-static int ad7887_read_raw(struct iio_dev *indio_dev,
-			   struct iio_chan_spec const *chan,
-			   int *val,
-			   int *val2,
-			   long m)
-{
-	int ret;
-	struct ad7887_state *st = iio_priv(indio_dev);
-
-	switch (m) {
-	case IIO_CHAN_INFO_RAW:
-		mutex_lock(&indio_dev->mlock);
-		if (iio_buffer_enabled(indio_dev))
-			ret = -EBUSY;
-		else
-			ret = ad7887_scan_direct(st, chan->address);
-		mutex_unlock(&indio_dev->mlock);
-
-		if (ret < 0)
-			return ret;
-		*val = ret >> chan->scan_type.shift;
-		*val &= RES_MASK(chan->scan_type.realbits);
-		return IIO_VAL_INT;
-	case IIO_CHAN_INFO_SCALE:
-		if (st->reg) {
-			*val = regulator_get_voltage(st->reg);
-			if (*val < 0)
-				return *val;
-			*val /= 1000;
-		} else {
-			*val = st->chip_info->int_vref_mv;
-		}
-
-		*val2 = chan->scan_type.realbits;
-
-		return IIO_VAL_FRACTIONAL_LOG2;
-	}
-	return -EINVAL;
-}
-
-
-static const struct ad7887_chip_info ad7887_chip_info_tbl[] = {
-	/*
-	 * More devices added in future
-	 */
-	[ID_AD7887] = {
-		.channel[0] = {
-			.type = IIO_VOLTAGE,
-			.indexed = 1,
-			.channel = 1,
-			.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT |
-			IIO_CHAN_INFO_SCALE_SHARED_BIT,
-			.address = 1,
-			.scan_index = 1,
-			.scan_type = IIO_ST('u', 12, 16, 0),
-		},
-		.channel[1] = {
-			.type = IIO_VOLTAGE,
-			.indexed = 1,
-			.channel = 0,
-			.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT |
-			IIO_CHAN_INFO_SCALE_SHARED_BIT,
-			.address = 0,
-			.scan_index = 0,
-			.scan_type = IIO_ST('u', 12, 16, 0),
-		},
-		.channel[2] = IIO_CHAN_SOFT_TIMESTAMP(2),
-		.int_vref_mv = 2500,
-	},
-};
-
-static const struct iio_info ad7887_info = {
-	.read_raw = &ad7887_read_raw,
-	.driver_module = THIS_MODULE,
-};
-
-static int __devinit ad7887_probe(struct spi_device *spi)
-{
-	struct ad7887_platform_data *pdata = spi->dev.platform_data;
-	struct ad7887_state *st;
-	struct iio_dev *indio_dev = iio_device_alloc(sizeof(*st));
-	uint8_t mode;
-	int ret;
-
-	if (indio_dev == NULL)
-		return -ENOMEM;
-
-	st = iio_priv(indio_dev);
-
-	if (!pdata || !pdata->use_onchip_ref) {
-		st->reg = regulator_get(&spi->dev, "vref");
-		if (IS_ERR(st->reg)) {
-			ret = PTR_ERR(st->reg);
-			goto error_free;
-		}
-
-		ret = regulator_enable(st->reg);
-		if (ret)
-			goto error_put_reg;
-	}
-
-	st->chip_info =
-		&ad7887_chip_info_tbl[spi_get_device_id(spi)->driver_data];
-
-	spi_set_drvdata(spi, indio_dev);
-	st->spi = spi;
-
-	/* Estabilish that the iio_dev is a child of the spi device */
-	indio_dev->dev.parent = &spi->dev;
-	indio_dev->name = spi_get_device_id(spi)->name;
-	indio_dev->info = &ad7887_info;
-	indio_dev->modes = INDIO_DIRECT_MODE;
-
-	/* Setup default message */
-
-	mode = AD7887_PM_MODE4;
-	if (!pdata || !pdata->use_onchip_ref)
-		mode |= AD7887_REF_DIS;
-	if (pdata && pdata->en_dual)
-		mode |= AD7887_DUAL;
-
-	st->tx_cmd_buf[0] = AD7887_CH_AIN0 | mode;
-
-	st->xfer[0].rx_buf = &st->data[0];
-	st->xfer[0].tx_buf = &st->tx_cmd_buf[0];
-	st->xfer[0].len = 2;
-
-	spi_message_init(&st->msg[AD7887_CH0]);
-	spi_message_add_tail(&st->xfer[0], &st->msg[AD7887_CH0]);
-
-	if (pdata && pdata->en_dual) {
-		st->tx_cmd_buf[2] = AD7887_CH_AIN1 | mode;
-
-		st->xfer[1].rx_buf = &st->data[0];
-		st->xfer[1].tx_buf = &st->tx_cmd_buf[2];
-		st->xfer[1].len = 2;
-
-		st->xfer[2].rx_buf = &st->data[2];
-		st->xfer[2].tx_buf = &st->tx_cmd_buf[0];
-		st->xfer[2].len = 2;
-
-		spi_message_init(&st->msg[AD7887_CH0_CH1]);
-		spi_message_add_tail(&st->xfer[1], &st->msg[AD7887_CH0_CH1]);
-		spi_message_add_tail(&st->xfer[2], &st->msg[AD7887_CH0_CH1]);
-
-		st->xfer[3].rx_buf = &st->data[2];
-		st->xfer[3].tx_buf = &st->tx_cmd_buf[2];
-		st->xfer[3].len = 2;
-
-		spi_message_init(&st->msg[AD7887_CH1]);
-		spi_message_add_tail(&st->xfer[3], &st->msg[AD7887_CH1]);
-
-		indio_dev->channels = st->chip_info->channel;
-		indio_dev->num_channels = 3;
-	} else {
-		indio_dev->channels = &st->chip_info->channel[1];
-		indio_dev->num_channels = 2;
-	}
-
-	ret = iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
-			&ad7887_trigger_handler, &ad7887_ring_setup_ops);
-	if (ret)
-		goto error_disable_reg;
-
-	ret = iio_device_register(indio_dev);
-	if (ret)
-		goto error_unregister_ring;
-
-	return 0;
-error_unregister_ring:
-	iio_triggered_buffer_cleanup(indio_dev);
-error_disable_reg:
-	if (st->reg)
-		regulator_disable(st->reg);
-error_put_reg:
-	if (st->reg)
-		regulator_put(st->reg);
-error_free:
-	iio_device_free(indio_dev);
-
-	return ret;
-}
-
-static int __devexit ad7887_remove(struct spi_device *spi)
-{
-	struct iio_dev *indio_dev = spi_get_drvdata(spi);
-	struct ad7887_state *st = iio_priv(indio_dev);
-
-	iio_device_unregister(indio_dev);
-	iio_triggered_buffer_cleanup(indio_dev);
-	if (st->reg) {
-		regulator_disable(st->reg);
-		regulator_put(st->reg);
-	}
-	iio_device_free(indio_dev);
-
-	return 0;
-}
-
-static const struct spi_device_id ad7887_id[] = {
-	{"ad7887", ID_AD7887},
-	{}
-};
-MODULE_DEVICE_TABLE(spi, ad7887_id);
-
-static struct spi_driver ad7887_driver = {
-	.driver = {
-		.name	= "ad7887",
-		.owner	= THIS_MODULE,
-	},
-	.probe		= ad7887_probe,
-	.remove		= __devexit_p(ad7887_remove),
-	.id_table	= ad7887_id,
-};
-module_spi_driver(ad7887_driver);
-
-MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>");
-MODULE_DESCRIPTION("Analog Devices AD7887 ADC");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/staging/iio/adc/ad7887.h b/drivers/staging/iio/adc/ad7887.h
deleted file mode 100644
index 16c2d05e5e05..000000000000
--- a/drivers/staging/iio/adc/ad7887.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * AD7887 SPI ADC driver
- *
- * Copyright 2010 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later.
- */
-#ifndef IIO_ADC_AD7887_H_
-#define IIO_ADC_AD7887_H_
-
-/*
- * TODO: struct ad7887_platform_data needs to go into include/linux/iio
- */
-
-
-/**
- * struct ad7887_platform_data - AD7887 ADC driver platform data
- * @en_dual: Whether to use dual channel mode. If set to true AIN1 becomes the
- *	second input channel, and Vref is internally connected to Vdd. If set to
- *	false the device is used in single channel mode and AIN1/Vref is used as
- *	VREF input.
- * @use_onchip_ref: Whether to use the onchip reference. If set to true the
- *	internal 2.5V reference is used. If set to false a external reference is
- *	used.
- */
-struct ad7887_platform_data {
-	bool en_dual;
-	bool use_onchip_ref;
-};
-
-#endif /* IIO_ADC_AD7887_H_ */
diff --git a/include/linux/platform_data/ad7887.h b/include/linux/platform_data/ad7887.h
new file mode 100644
index 000000000000..1e06eac3174d
--- /dev/null
+++ b/include/linux/platform_data/ad7887.h
@@ -0,0 +1,26 @@
+/*
+ * AD7887 SPI ADC driver
+ *
+ * Copyright 2010 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+#ifndef IIO_ADC_AD7887_H_
+#define IIO_ADC_AD7887_H_
+
+/**
+ * struct ad7887_platform_data - AD7887 ADC driver platform data
+ * @en_dual: Whether to use dual channel mode. If set to true AIN1 becomes the
+ *	second input channel, and Vref is internally connected to Vdd. If set to
+ *	false the device is used in single channel mode and AIN1/Vref is used as
+ *	VREF input.
+ * @use_onchip_ref: Whether to use the onchip reference. If set to true the
+ *	internal 2.5V reference is used. If set to false a external reference is
+ *	used.
+ */
+struct ad7887_platform_data {
+	bool en_dual;
+	bool use_onchip_ref;
+};
+
+#endif /* IIO_ADC_AD7887_H_ */
-- 
cgit v1.2.3-55-g7522


From d1fb57435c108b8dd66d7f47b4c60c1798dcae4c Mon Sep 17 00:00:00 2001
From: Patil, Rachna
Date: Tue, 16 Oct 2012 12:55:39 +0530
Subject: input: TSC: ti_tscadc: Add Step configuration as platform data

There are 16 programmable Step Configuration
registers which are used by the sequencer.
Program the Steps in order to configure a channel
input to be sampled. If the same step is applied
several times, the coordinate values read are more
accurate.
Hence we provide the user an option of how many steps
should be configured.

For ex: If this value is assigned as 4, This means that
4 steps are applied to read x co-ordinate and 4 steps to read
y co-ordinate. Furtheron the interrupt handler already
holds code to use delta filter and report the best value
out of these values to the input sub-system.

Signed-off-by: Patil, Rachna <rachna@ti.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/input/touchscreen/ti_tscadc.c | 25 +++++++++++++------------
 include/linux/input/ti_tscadc.h       |  6 ++++++
 2 files changed, 19 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/input/touchscreen/ti_tscadc.c b/drivers/input/touchscreen/ti_tscadc.c
index d198cab61a69..c1bd8e5c132c 100644
--- a/drivers/input/touchscreen/ti_tscadc.c
+++ b/drivers/input/touchscreen/ti_tscadc.c
@@ -41,10 +41,6 @@
 #define REG_CHARGEDELAY		0x060
 #define REG_STEPCONFIG(n)	(0x64 + ((n - 1) * 8))
 #define REG_STEPDELAY(n)	(0x68 + ((n - 1) * 8))
-#define REG_STEPCONFIG13	0x0C4
-#define REG_STEPDELAY13		0x0C8
-#define REG_STEPCONFIG14	0x0CC
-#define REG_STEPDELAY14		0x0D0
 #define REG_FIFO0CNT		0xE4
 #define REG_FIFO1THR		0xF4
 #define REG_FIFO0		0x100
@@ -134,6 +130,7 @@ struct tscadc {
 	unsigned int		wires;
 	unsigned int		x_plate_resistance;
 	bool			pen_down;
+	int			steps_to_configure;
 };
 
 static unsigned int tscadc_readl(struct tscadc *ts, unsigned int reg)
@@ -150,9 +147,10 @@ static void tscadc_writel(struct tscadc *tsc, unsigned int reg,
 static void tscadc_step_config(struct tscadc *ts_dev)
 {
 	unsigned int	config;
-	int i;
+	int i, total_steps;
 
 	/* Configure the Step registers */
+	total_steps = 2 * ts_dev->steps_to_configure;
 
 	config = STEPCONFIG_MODE_HWSYNC |
 			STEPCONFIG_AVG_16 | STEPCONFIG_XPP;
@@ -170,7 +168,7 @@ static void tscadc_step_config(struct tscadc *ts_dev)
 		break;
 	}
 
-	for (i = 1; i < 7; i++) {
+	for (i = 1; i <= ts_dev->steps_to_configure; i++) {
 		tscadc_writel(ts_dev, REG_STEPCONFIG(i), config);
 		tscadc_writel(ts_dev, REG_STEPDELAY(i), STEPCONFIG_OPENDLY);
 	}
@@ -192,7 +190,7 @@ static void tscadc_step_config(struct tscadc *ts_dev)
 		break;
 	}
 
-	for (i = 7; i < 13; i++) {
+	for (i = (ts_dev->steps_to_configure + 1); i <= total_steps; i++) {
 		tscadc_writel(ts_dev, REG_STEPCONFIG(i), config);
 		tscadc_writel(ts_dev, REG_STEPDELAY(i), STEPCONFIG_OPENDLY);
 	}
@@ -211,12 +209,14 @@ static void tscadc_step_config(struct tscadc *ts_dev)
 	config = STEPCONFIG_MODE_HWSYNC |
 			STEPCONFIG_AVG_16 | STEPCONFIG_YPP |
 			STEPCONFIG_XNN | STEPCONFIG_INM_ADCREFM;
-	tscadc_writel(ts_dev, REG_STEPCONFIG13, config);
-	tscadc_writel(ts_dev, REG_STEPDELAY13, STEPCONFIG_OPENDLY);
+	tscadc_writel(ts_dev, REG_STEPCONFIG(total_steps + 1), config);
+	tscadc_writel(ts_dev, REG_STEPDELAY(total_steps + 1),
+			STEPCONFIG_OPENDLY);
 
 	config |= STEPCONFIG_INP_AN3 | STEPCONFIG_FIFO1;
-	tscadc_writel(ts_dev, REG_STEPCONFIG14, config);
-	tscadc_writel(ts_dev, REG_STEPDELAY14, STEPCONFIG_OPENDLY);
+	tscadc_writel(ts_dev, REG_STEPCONFIG(total_steps + 2), config);
+	tscadc_writel(ts_dev, REG_STEPDELAY(total_steps + 2),
+			STEPCONFIG_OPENDLY);
 
 	tscadc_writel(ts_dev, REG_SE, STPENB_STEPENB);
 }
@@ -379,6 +379,7 @@ static int __devinit tscadc_probe(struct platform_device *pdev)
 	ts_dev->irq = irq;
 	ts_dev->wires = pdata->wires;
 	ts_dev->x_plate_resistance = pdata->x_plate_resistance;
+	ts_dev->steps_to_configure = pdata->steps_to_configure;
 
 	res = request_mem_region(res->start, resource_size(res), pdev->name);
 	if (!res) {
@@ -447,7 +448,7 @@ static int __devinit tscadc_probe(struct platform_device *pdev)
 	tscadc_idle_config(ts_dev);
 	tscadc_writel(ts_dev, REG_IRQENABLE, IRQENB_FIFO1THRES);
 	tscadc_step_config(ts_dev);
-	tscadc_writel(ts_dev, REG_FIFO1THR, 6);
+	tscadc_writel(ts_dev, REG_FIFO1THR, ts_dev->steps_to_configure);
 
 	ctrl |= CNTRLREG_TSCSSENB;
 	tscadc_writel(ts_dev, REG_CTRL, ctrl);
diff --git a/include/linux/input/ti_tscadc.h b/include/linux/input/ti_tscadc.h
index b10a527a92a4..ad442a3eb68b 100644
--- a/include/linux/input/ti_tscadc.h
+++ b/include/linux/input/ti_tscadc.h
@@ -7,11 +7,17 @@
  *			i.e. 4/5/8 wire touchscreen support
  *			on the platform.
  * @x_plate_resistance:	X plate resistance.
+ * @steps_to_configure:	The sequencer supports a total of
+ *			16 programmable steps.
+ *			A step configured to read a single
+ *			co-ordinate value, can be applied
+ *			more number of times for better results.
  */
 
 struct tsc_data {
 	int wires;
 	int x_plate_resistance;
+	int steps_to_configure;
 };
 
 #endif
-- 
cgit v1.2.3-55-g7522


From 55c04de5176ea3eac6fdc469a6a063c5cb91ed7c Mon Sep 17 00:00:00 2001
From: Patil, Rachna
Date: Tue, 16 Oct 2012 12:55:42 +0530
Subject: input: TSC: ti_tscadc: Rename the existing touchscreen driver

Make way for addition of MFD driver.
The existing touchsreen driver is a MFD client.
For better readability we rename the file to
indicate its functionality as only touchscreen.

Signed-off-by: Patil, Rachna <rachna@ti.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/input/touchscreen/Kconfig         |   4 +-
 drivers/input/touchscreen/Makefile        |   2 +-
 drivers/input/touchscreen/ti_am335x_tsc.c | 522 ++++++++++++++++++++++++++++++
 drivers/input/touchscreen/ti_tscadc.c     | 522 ------------------------------
 include/linux/input/ti_am335x_tsc.h       |  23 ++
 include/linux/input/ti_tscadc.h           |  23 --
 6 files changed, 548 insertions(+), 548 deletions(-)
 create mode 100644 drivers/input/touchscreen/ti_am335x_tsc.c
 delete mode 100644 drivers/input/touchscreen/ti_tscadc.c
 create mode 100644 include/linux/input/ti_am335x_tsc.h
 delete mode 100644 include/linux/input/ti_tscadc.h

(limited to 'include')

diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index f7668b24c378..d31dc5faeaaf 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -529,7 +529,7 @@ config TOUCHSCREEN_TOUCHWIN
 	  To compile this driver as a module, choose M here: the
 	  module will be called touchwin.
 
-config TOUCHSCREEN_TI_TSCADC
+config TOUCHSCREEN_TI_AM335X_TSC
 	tristate "TI Touchscreen Interface"
 	depends on ARCH_OMAP2PLUS
 	help
@@ -539,7 +539,7 @@ config TOUCHSCREEN_TI_TSCADC
 	  If unsure, say N.
 
 	  To compile this driver as a module, choose M here: the
-	  module will be called ti_tscadc.
+	  module will be called ti_am335x_tsc.
 
 config TOUCHSCREEN_ATMEL_TSADCC
 	tristate "Atmel Touchscreen Interface"
diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile
index 178eb128d90f..7c4c78ebe49e 100644
--- a/drivers/input/touchscreen/Makefile
+++ b/drivers/input/touchscreen/Makefile
@@ -52,7 +52,7 @@ obj-$(CONFIG_TOUCHSCREEN_PIXCIR)	+= pixcir_i2c_ts.o
 obj-$(CONFIG_TOUCHSCREEN_S3C2410)	+= s3c2410_ts.o
 obj-$(CONFIG_TOUCHSCREEN_ST1232)	+= st1232.o
 obj-$(CONFIG_TOUCHSCREEN_STMPE)		+= stmpe-ts.o
-obj-$(CONFIG_TOUCHSCREEN_TI_TSCADC)	+= ti_tscadc.o
+obj-$(CONFIG_TOUCHSCREEN_TI_AM335X_TSC)	+= ti_am335x_tsc.o
 obj-$(CONFIG_TOUCHSCREEN_TNETV107X)	+= tnetv107x-ts.o
 obj-$(CONFIG_TOUCHSCREEN_TOUCHIT213)	+= touchit213.o
 obj-$(CONFIG_TOUCHSCREEN_TOUCHRIGHT)	+= touchright.o
diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c
new file mode 100644
index 000000000000..462950acb97b
--- /dev/null
+++ b/drivers/input/touchscreen/ti_am335x_tsc.c
@@ -0,0 +1,522 @@
+/*
+ * TI Touch Screen driver
+ *
+ * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/input.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/input/ti_am335x_tsc.h>
+#include <linux/delay.h>
+
+#define REG_RAWIRQSTATUS	0x024
+#define REG_IRQSTATUS		0x028
+#define REG_IRQENABLE		0x02C
+#define REG_IRQWAKEUP		0x034
+#define REG_CTRL		0x040
+#define REG_ADCFSM		0x044
+#define REG_CLKDIV		0x04C
+#define REG_SE			0x054
+#define REG_IDLECONFIG		0x058
+#define REG_CHARGECONFIG	0x05C
+#define REG_CHARGEDELAY		0x060
+#define REG_STEPCONFIG(n)	(0x64 + ((n - 1) * 8))
+#define REG_STEPDELAY(n)	(0x68 + ((n - 1) * 8))
+#define REG_FIFO0CNT		0xE4
+#define REG_FIFO0THR		0xE8
+#define REG_FIFO1THR		0xF4
+#define REG_FIFO0		0x100
+#define REG_FIFO1		0x200
+
+/*	Register Bitfields	*/
+#define IRQWKUP_ENB		BIT(0)
+
+/* Step Enable */
+#define STEPENB_MASK		(0x1FFFF << 0)
+#define STEPENB(val)		(val << 0)
+#define STPENB_STEPENB		STEPENB(0x7FFF)
+
+/* IRQ enable */
+#define IRQENB_FIFO0THRES	BIT(2)
+#define IRQENB_FIFO1THRES	BIT(5)
+#define IRQENB_PENUP		BIT(9)
+
+/* Step Configuration */
+#define STEPCONFIG_MODE_MASK	(3 << 0)
+#define STEPCONFIG_MODE(val)	(val << 0)
+#define STEPCONFIG_MODE_HWSYNC	STEPCONFIG_MODE(2)
+#define STEPCONFIG_AVG_MASK	(7 << 2)
+#define STEPCONFIG_AVG(val)	(val << 2)
+#define STEPCONFIG_AVG_16	STEPCONFIG_AVG(4)
+#define STEPCONFIG_XPP		BIT(5)
+#define STEPCONFIG_XNN		BIT(6)
+#define STEPCONFIG_YPP		BIT(7)
+#define STEPCONFIG_YNN		BIT(8)
+#define STEPCONFIG_XNP		BIT(9)
+#define STEPCONFIG_YPN		BIT(10)
+#define STEPCONFIG_INM_MASK	(0xF << 15)
+#define STEPCONFIG_INM(val)	(val << 15)
+#define STEPCONFIG_INM_ADCREFM	STEPCONFIG_INM(8)
+#define STEPCONFIG_INP_MASK	(0xF << 19)
+#define STEPCONFIG_INP(val)	(val << 19)
+#define STEPCONFIG_INP_AN2	STEPCONFIG_INP(2)
+#define STEPCONFIG_INP_AN3	STEPCONFIG_INP(3)
+#define STEPCONFIG_INP_AN4	STEPCONFIG_INP(4)
+#define STEPCONFIG_INP_ADCREFM	STEPCONFIG_INP(8)
+#define STEPCONFIG_FIFO1	BIT(26)
+
+/* Delay register */
+#define STEPDELAY_OPEN_MASK	(0x3FFFF << 0)
+#define STEPDELAY_OPEN(val)	(val << 0)
+#define STEPCONFIG_OPENDLY	STEPDELAY_OPEN(0x098)
+
+/* Charge Config */
+#define STEPCHARGE_RFP_MASK	(7 << 12)
+#define STEPCHARGE_RFP(val)	(val << 12)
+#define STEPCHARGE_RFP_XPUL	STEPCHARGE_RFP(1)
+#define STEPCHARGE_INM_MASK	(0xF << 15)
+#define STEPCHARGE_INM(val)	(val << 15)
+#define STEPCHARGE_INM_AN1	STEPCHARGE_INM(1)
+#define STEPCHARGE_INP_MASK	(0xF << 19)
+#define STEPCHARGE_INP(val)	(val << 19)
+#define STEPCHARGE_INP_AN1	STEPCHARGE_INP(1)
+#define STEPCHARGE_RFM_MASK	(3 << 23)
+#define STEPCHARGE_RFM(val)	(val << 23)
+#define STEPCHARGE_RFM_XNUR	STEPCHARGE_RFM(1)
+
+/* Charge delay */
+#define CHARGEDLY_OPEN_MASK	(0x3FFFF << 0)
+#define CHARGEDLY_OPEN(val)	(val << 0)
+#define CHARGEDLY_OPENDLY	CHARGEDLY_OPEN(1)
+
+/* Control register */
+#define CNTRLREG_TSCSSENB	BIT(0)
+#define CNTRLREG_STEPID		BIT(1)
+#define CNTRLREG_STEPCONFIGWRT	BIT(2)
+#define CNTRLREG_AFE_CTRL_MASK	(3 << 5)
+#define CNTRLREG_AFE_CTRL(val)	(val << 5)
+#define CNTRLREG_4WIRE		CNTRLREG_AFE_CTRL(1)
+#define CNTRLREG_5WIRE		CNTRLREG_AFE_CTRL(2)
+#define CNTRLREG_8WIRE		CNTRLREG_AFE_CTRL(3)
+#define CNTRLREG_TSCENB		BIT(7)
+
+#define ADCFSM_STEPID		0x10
+#define SEQ_SETTLE		275
+#define ADC_CLK			3000000
+#define MAX_12BIT		((1 << 12) - 1)
+
+struct titsc {
+	struct input_dev	*input;
+	struct clk		*tsc_ick;
+	void __iomem		*tsc_base;
+	unsigned int		irq;
+	unsigned int		wires;
+	unsigned int		x_plate_resistance;
+	bool			pen_down;
+	int			steps_to_configure;
+};
+
+static unsigned int titsc_readl(struct titsc *ts, unsigned int reg)
+{
+	return readl(ts->tsc_base + reg);
+}
+
+static void titsc_writel(struct titsc *tsc, unsigned int reg,
+					unsigned int val)
+{
+	writel(val, tsc->tsc_base + reg);
+}
+
+static void titsc_step_config(struct titsc *ts_dev)
+{
+	unsigned int	config;
+	int i, total_steps;
+
+	/* Configure the Step registers */
+	total_steps = 2 * ts_dev->steps_to_configure;
+
+	config = STEPCONFIG_MODE_HWSYNC |
+			STEPCONFIG_AVG_16 | STEPCONFIG_XPP;
+	switch (ts_dev->wires) {
+	case 4:
+		config |= STEPCONFIG_INP_AN2 | STEPCONFIG_XNN;
+		break;
+	case 5:
+		config |= STEPCONFIG_YNN |
+				STEPCONFIG_INP_AN4 | STEPCONFIG_XNN |
+				STEPCONFIG_YPP;
+		break;
+	case 8:
+		config |= STEPCONFIG_INP_AN2 | STEPCONFIG_XNN;
+		break;
+	}
+
+	for (i = 1; i <= ts_dev->steps_to_configure; i++) {
+		titsc_writel(ts_dev, REG_STEPCONFIG(i), config);
+		titsc_writel(ts_dev, REG_STEPDELAY(i), STEPCONFIG_OPENDLY);
+	}
+
+	config = 0;
+	config = STEPCONFIG_MODE_HWSYNC |
+			STEPCONFIG_AVG_16 | STEPCONFIG_YNN |
+			STEPCONFIG_INM_ADCREFM | STEPCONFIG_FIFO1;
+	switch (ts_dev->wires) {
+	case 4:
+		config |= STEPCONFIG_YPP;
+		break;
+	case 5:
+		config |= STEPCONFIG_XPP | STEPCONFIG_INP_AN4 |
+				STEPCONFIG_XNP | STEPCONFIG_YPN;
+		break;
+	case 8:
+		config |= STEPCONFIG_YPP;
+		break;
+	}
+
+	for (i = (ts_dev->steps_to_configure + 1); i <= total_steps; i++) {
+		titsc_writel(ts_dev, REG_STEPCONFIG(i), config);
+		titsc_writel(ts_dev, REG_STEPDELAY(i), STEPCONFIG_OPENDLY);
+	}
+
+	config = 0;
+	/* Charge step configuration */
+	config = STEPCONFIG_XPP | STEPCONFIG_YNN |
+			STEPCHARGE_RFP_XPUL | STEPCHARGE_RFM_XNUR |
+			STEPCHARGE_INM_AN1 | STEPCHARGE_INP_AN1;
+
+	titsc_writel(ts_dev, REG_CHARGECONFIG, config);
+	titsc_writel(ts_dev, REG_CHARGEDELAY, CHARGEDLY_OPENDLY);
+
+	config = 0;
+	/* Configure to calculate pressure */
+	config = STEPCONFIG_MODE_HWSYNC |
+			STEPCONFIG_AVG_16 | STEPCONFIG_YPP |
+			STEPCONFIG_XNN | STEPCONFIG_INM_ADCREFM;
+	titsc_writel(ts_dev, REG_STEPCONFIG(total_steps + 1), config);
+	titsc_writel(ts_dev, REG_STEPDELAY(total_steps + 1),
+			STEPCONFIG_OPENDLY);
+
+	config |= STEPCONFIG_INP_AN3 | STEPCONFIG_FIFO1;
+	titsc_writel(ts_dev, REG_STEPCONFIG(total_steps + 2), config);
+	titsc_writel(ts_dev, REG_STEPDELAY(total_steps + 2),
+			STEPCONFIG_OPENDLY);
+
+	titsc_writel(ts_dev, REG_SE, STPENB_STEPENB);
+}
+
+static void titsc_idle_config(struct titsc *ts_config)
+{
+	unsigned int idleconfig;
+
+	idleconfig = STEPCONFIG_YNN |
+			STEPCONFIG_INM_ADCREFM |
+			STEPCONFIG_YPN | STEPCONFIG_INP_ADCREFM;
+	titsc_writel(ts_config, REG_IDLECONFIG, idleconfig);
+}
+
+static void titsc_read_coordinates(struct titsc *ts_dev,
+				    unsigned int *x, unsigned int *y)
+{
+	unsigned int fifocount = titsc_readl(ts_dev, REG_FIFO0CNT);
+	unsigned int prev_val_x = ~0, prev_val_y = ~0;
+	unsigned int prev_diff_x = ~0, prev_diff_y = ~0;
+	unsigned int read, diff;
+	unsigned int i;
+
+	/*
+	 * Delta filter is used to remove large variations in sampled
+	 * values from ADC. The filter tries to predict where the next
+	 * coordinate could be. This is done by taking a previous
+	 * coordinate and subtracting it form current one. Further the
+	 * algorithm compares the difference with that of a present value,
+	 * if true the value is reported to the sub system.
+	 */
+	for (i = 0; i < fifocount - 1; i++) {
+		read = titsc_readl(ts_dev, REG_FIFO0) & 0xfff;
+		diff = abs(read - prev_val_x);
+		if (diff < prev_diff_x) {
+			prev_diff_x = diff;
+			*x = read;
+		}
+		prev_val_x = read;
+
+		read = titsc_readl(ts_dev, REG_FIFO1) & 0xfff;
+		diff = abs(read - prev_val_y);
+		if (diff < prev_diff_y) {
+			prev_diff_y = diff;
+			*y = read;
+		}
+		prev_val_y = read;
+	}
+}
+
+static irqreturn_t titsc_irq(int irq, void *dev)
+{
+	struct titsc *ts_dev = dev;
+	struct input_dev *input_dev = ts_dev->input;
+	unsigned int status, irqclr = 0;
+	unsigned int x = 0, y = 0;
+	unsigned int z1, z2, z;
+	unsigned int fsm;
+
+	status = titsc_readl(ts_dev, REG_IRQSTATUS);
+	if (status & IRQENB_FIFO0THRES) {
+		titsc_read_coordinates(ts_dev, &x, &y);
+
+		z1 = titsc_readl(ts_dev, REG_FIFO0) & 0xfff;
+		z2 = titsc_readl(ts_dev, REG_FIFO1) & 0xfff;
+
+		if (ts_dev->pen_down && z1 != 0 && z2 != 0) {
+			/*
+			 * Calculate pressure using formula
+			 * Resistance(touch) = x plate resistance *
+			 * x postion/4096 * ((z2 / z1) - 1)
+			 */
+			z = z2 - z1;
+			z *= x;
+			z *= ts_dev->x_plate_resistance;
+			z /= z1;
+			z = (z + 2047) >> 12;
+
+			if (z <= MAX_12BIT) {
+				input_report_abs(input_dev, ABS_X, x);
+				input_report_abs(input_dev, ABS_Y, y);
+				input_report_abs(input_dev, ABS_PRESSURE, z);
+				input_report_key(input_dev, BTN_TOUCH, 1);
+				input_sync(input_dev);
+			}
+		}
+		irqclr |= IRQENB_FIFO0THRES;
+	}
+
+	/*
+	 * Time for sequencer to settle, to read
+	 * correct state of the sequencer.
+	 */
+	udelay(SEQ_SETTLE);
+
+	status = titsc_readl(ts_dev, REG_RAWIRQSTATUS);
+	if (status & IRQENB_PENUP) {
+		/* Pen up event */
+		fsm = titsc_readl(ts_dev, REG_ADCFSM);
+		if (fsm == ADCFSM_STEPID) {
+			ts_dev->pen_down = false;
+			input_report_key(input_dev, BTN_TOUCH, 0);
+			input_report_abs(input_dev, ABS_PRESSURE, 0);
+			input_sync(input_dev);
+		} else {
+			ts_dev->pen_down = true;
+		}
+		irqclr |= IRQENB_PENUP;
+	}
+
+	titsc_writel(ts_dev, REG_IRQSTATUS, irqclr);
+
+	titsc_writel(ts_dev, REG_SE, STPENB_STEPENB);
+	return IRQ_HANDLED;
+}
+
+/*
+ * The functions for inserting/removing driver as a module.
+ */
+
+static int __devinit titsc_probe(struct platform_device *pdev)
+{
+	const struct tsc_data *pdata = pdev->dev.platform_data;
+	struct resource *res;
+	struct titsc *ts_dev;
+	struct input_dev *input_dev;
+	struct clk *clk;
+	int err;
+	int clk_value, ctrl, irq;
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "missing platform data.\n");
+		return -EINVAL;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "no memory resource defined.\n");
+		return -EINVAL;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "no irq ID is specified.\n");
+		return -EINVAL;
+	}
+
+	/* Allocate memory for device */
+	ts_dev = kzalloc(sizeof(struct titsc), GFP_KERNEL);
+	input_dev = input_allocate_device();
+	if (!ts_dev || !input_dev) {
+		dev_err(&pdev->dev, "failed to allocate memory.\n");
+		err = -ENOMEM;
+		goto err_free_mem;
+	}
+
+	ts_dev->input = input_dev;
+	ts_dev->irq = irq;
+	ts_dev->wires = pdata->wires;
+	ts_dev->x_plate_resistance = pdata->x_plate_resistance;
+	ts_dev->steps_to_configure = pdata->steps_to_configure;
+
+	res = request_mem_region(res->start, resource_size(res), pdev->name);
+	if (!res) {
+		dev_err(&pdev->dev, "failed to reserve registers.\n");
+		err = -EBUSY;
+		goto err_free_mem;
+	}
+
+	ts_dev->tsc_base = ioremap(res->start, resource_size(res));
+	if (!ts_dev->tsc_base) {
+		dev_err(&pdev->dev, "failed to map registers.\n");
+		err = -ENOMEM;
+		goto err_release_mem_region;
+	}
+
+	err = request_irq(ts_dev->irq, titsc_irq,
+			  0, pdev->dev.driver->name, ts_dev);
+	if (err) {
+		dev_err(&pdev->dev, "failed to allocate irq.\n");
+		goto err_unmap_regs;
+	}
+
+	ts_dev->tsc_ick = clk_get(&pdev->dev, "adc_tsc_ick");
+	if (IS_ERR(ts_dev->tsc_ick)) {
+		dev_err(&pdev->dev, "failed to get TSC ick\n");
+		goto err_free_irq;
+	}
+	clk_enable(ts_dev->tsc_ick);
+
+	clk = clk_get(&pdev->dev, "adc_tsc_fck");
+	if (IS_ERR(clk)) {
+		dev_err(&pdev->dev, "failed to get TSC fck\n");
+		err = PTR_ERR(clk);
+		goto err_disable_clk;
+	}
+
+	clk_value = clk_get_rate(clk) / ADC_CLK;
+	clk_put(clk);
+
+	if (clk_value < 7) {
+		dev_err(&pdev->dev, "clock input less than min clock requirement\n");
+		goto err_disable_clk;
+	}
+	/* CLKDIV needs to be configured to the value minus 1 */
+	titsc_writel(ts_dev, REG_CLKDIV, clk_value - 1);
+
+	 /* Enable wake-up of the SoC using touchscreen */
+	titsc_writel(ts_dev, REG_IRQWAKEUP, IRQWKUP_ENB);
+
+	ctrl = CNTRLREG_STEPCONFIGWRT |
+			CNTRLREG_TSCENB |
+			CNTRLREG_STEPID;
+	switch (ts_dev->wires) {
+	case 4:
+		ctrl |= CNTRLREG_4WIRE;
+		break;
+	case 5:
+		ctrl |= CNTRLREG_5WIRE;
+		break;
+	case 8:
+		ctrl |= CNTRLREG_8WIRE;
+		break;
+	}
+	titsc_writel(ts_dev, REG_CTRL, ctrl);
+
+	titsc_idle_config(ts_dev);
+	titsc_writel(ts_dev, REG_IRQENABLE, IRQENB_FIFO0THRES);
+	titsc_step_config(ts_dev);
+	titsc_writel(ts_dev, REG_FIFO0THR, ts_dev->steps_to_configure);
+
+	ctrl |= CNTRLREG_TSCSSENB;
+	titsc_writel(ts_dev, REG_CTRL, ctrl);
+
+	input_dev->name = "ti-tsc-adc";
+	input_dev->dev.parent = &pdev->dev;
+
+	input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
+	input_dev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH);
+
+	input_set_abs_params(input_dev, ABS_X, 0, MAX_12BIT, 0, 0);
+	input_set_abs_params(input_dev, ABS_Y, 0, MAX_12BIT, 0, 0);
+	input_set_abs_params(input_dev, ABS_PRESSURE, 0, MAX_12BIT, 0, 0);
+
+	/* register to the input system */
+	err = input_register_device(input_dev);
+	if (err)
+		goto err_disable_clk;
+
+	platform_set_drvdata(pdev, ts_dev);
+	return 0;
+
+err_disable_clk:
+	clk_disable(ts_dev->tsc_ick);
+	clk_put(ts_dev->tsc_ick);
+err_free_irq:
+	free_irq(ts_dev->irq, ts_dev);
+err_unmap_regs:
+	iounmap(ts_dev->tsc_base);
+err_release_mem_region:
+	release_mem_region(res->start, resource_size(res));
+err_free_mem:
+	input_free_device(input_dev);
+	kfree(ts_dev);
+	return err;
+}
+
+static int __devexit titsc_remove(struct platform_device *pdev)
+{
+	struct titsc *ts_dev = platform_get_drvdata(pdev);
+	struct resource *res;
+
+	free_irq(ts_dev->irq, ts_dev);
+
+	input_unregister_device(ts_dev->input);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	iounmap(ts_dev->tsc_base);
+	release_mem_region(res->start, resource_size(res));
+
+	clk_disable(ts_dev->tsc_ick);
+	clk_put(ts_dev->tsc_ick);
+
+	kfree(ts_dev);
+
+	platform_set_drvdata(pdev, NULL);
+	return 0;
+}
+
+static struct platform_driver ti_tsc_driver = {
+	.probe	= titsc_probe,
+	.remove	= __devexit_p(titsc_remove),
+	.driver	= {
+		.name   = "tsc",
+		.owner	= THIS_MODULE,
+	},
+};
+module_platform_driver(ti_tsc_driver);
+
+MODULE_DESCRIPTION("TI touchscreen controller driver");
+MODULE_AUTHOR("Rachna Patil <rachna@ti.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/input/touchscreen/ti_tscadc.c b/drivers/input/touchscreen/ti_tscadc.c
deleted file mode 100644
index ec0a442478a8..000000000000
--- a/drivers/input/touchscreen/ti_tscadc.c
+++ /dev/null
@@ -1,522 +0,0 @@
-/*
- * TI Touch Screen driver
- *
- * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/input.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/clk.h>
-#include <linux/platform_device.h>
-#include <linux/io.h>
-#include <linux/input/ti_tscadc.h>
-#include <linux/delay.h>
-
-#define REG_RAWIRQSTATUS	0x024
-#define REG_IRQSTATUS		0x028
-#define REG_IRQENABLE		0x02C
-#define REG_IRQWAKEUP		0x034
-#define REG_CTRL		0x040
-#define REG_ADCFSM		0x044
-#define REG_CLKDIV		0x04C
-#define REG_SE			0x054
-#define REG_IDLECONFIG		0x058
-#define REG_CHARGECONFIG	0x05C
-#define REG_CHARGEDELAY		0x060
-#define REG_STEPCONFIG(n)	(0x64 + ((n - 1) * 8))
-#define REG_STEPDELAY(n)	(0x68 + ((n - 1) * 8))
-#define REG_FIFO0CNT		0xE4
-#define REG_FIFO0THR		0xE8
-#define REG_FIFO1THR		0xF4
-#define REG_FIFO0		0x100
-#define REG_FIFO1		0x200
-
-/*	Register Bitfields	*/
-#define IRQWKUP_ENB		BIT(0)
-
-/* Step Enable */
-#define STEPENB_MASK		(0x1FFFF << 0)
-#define STEPENB(val)		(val << 0)
-#define STPENB_STEPENB		STEPENB(0x7FFF)
-
-/* IRQ enable */
-#define IRQENB_FIFO0THRES	BIT(2)
-#define IRQENB_FIFO1THRES	BIT(5)
-#define IRQENB_PENUP		BIT(9)
-
-/* Step Configuration */
-#define STEPCONFIG_MODE_MASK	(3 << 0)
-#define STEPCONFIG_MODE(val)	(val << 0)
-#define STEPCONFIG_MODE_HWSYNC	STEPCONFIG_MODE(2)
-#define STEPCONFIG_AVG_MASK	(7 << 2)
-#define STEPCONFIG_AVG(val)	(val << 2)
-#define STEPCONFIG_AVG_16	STEPCONFIG_AVG(4)
-#define STEPCONFIG_XPP		BIT(5)
-#define STEPCONFIG_XNN		BIT(6)
-#define STEPCONFIG_YPP		BIT(7)
-#define STEPCONFIG_YNN		BIT(8)
-#define STEPCONFIG_XNP		BIT(9)
-#define STEPCONFIG_YPN		BIT(10)
-#define STEPCONFIG_INM_MASK	(0xF << 15)
-#define STEPCONFIG_INM(val)	(val << 15)
-#define STEPCONFIG_INM_ADCREFM	STEPCONFIG_INM(8)
-#define STEPCONFIG_INP_MASK	(0xF << 19)
-#define STEPCONFIG_INP(val)	(val << 19)
-#define STEPCONFIG_INP_AN2	STEPCONFIG_INP(2)
-#define STEPCONFIG_INP_AN3	STEPCONFIG_INP(3)
-#define STEPCONFIG_INP_AN4	STEPCONFIG_INP(4)
-#define STEPCONFIG_INP_ADCREFM	STEPCONFIG_INP(8)
-#define STEPCONFIG_FIFO1	BIT(26)
-
-/* Delay register */
-#define STEPDELAY_OPEN_MASK	(0x3FFFF << 0)
-#define STEPDELAY_OPEN(val)	(val << 0)
-#define STEPCONFIG_OPENDLY	STEPDELAY_OPEN(0x098)
-
-/* Charge Config */
-#define STEPCHARGE_RFP_MASK	(7 << 12)
-#define STEPCHARGE_RFP(val)	(val << 12)
-#define STEPCHARGE_RFP_XPUL	STEPCHARGE_RFP(1)
-#define STEPCHARGE_INM_MASK	(0xF << 15)
-#define STEPCHARGE_INM(val)	(val << 15)
-#define STEPCHARGE_INM_AN1	STEPCHARGE_INM(1)
-#define STEPCHARGE_INP_MASK	(0xF << 19)
-#define STEPCHARGE_INP(val)	(val << 19)
-#define STEPCHARGE_INP_AN1	STEPCHARGE_INP(1)
-#define STEPCHARGE_RFM_MASK	(3 << 23)
-#define STEPCHARGE_RFM(val)	(val << 23)
-#define STEPCHARGE_RFM_XNUR	STEPCHARGE_RFM(1)
-
-/* Charge delay */
-#define CHARGEDLY_OPEN_MASK	(0x3FFFF << 0)
-#define CHARGEDLY_OPEN(val)	(val << 0)
-#define CHARGEDLY_OPENDLY	CHARGEDLY_OPEN(1)
-
-/* Control register */
-#define CNTRLREG_TSCSSENB	BIT(0)
-#define CNTRLREG_STEPID		BIT(1)
-#define CNTRLREG_STEPCONFIGWRT	BIT(2)
-#define CNTRLREG_AFE_CTRL_MASK	(3 << 5)
-#define CNTRLREG_AFE_CTRL(val)	(val << 5)
-#define CNTRLREG_4WIRE		CNTRLREG_AFE_CTRL(1)
-#define CNTRLREG_5WIRE		CNTRLREG_AFE_CTRL(2)
-#define CNTRLREG_8WIRE		CNTRLREG_AFE_CTRL(3)
-#define CNTRLREG_TSCENB		BIT(7)
-
-#define ADCFSM_STEPID		0x10
-#define SEQ_SETTLE		275
-#define ADC_CLK			3000000
-#define MAX_12BIT		((1 << 12) - 1)
-
-struct tscadc {
-	struct input_dev	*input;
-	struct clk		*tsc_ick;
-	void __iomem		*tsc_base;
-	unsigned int		irq;
-	unsigned int		wires;
-	unsigned int		x_plate_resistance;
-	bool			pen_down;
-	int			steps_to_configure;
-};
-
-static unsigned int tscadc_readl(struct tscadc *ts, unsigned int reg)
-{
-	return readl(ts->tsc_base + reg);
-}
-
-static void tscadc_writel(struct tscadc *tsc, unsigned int reg,
-					unsigned int val)
-{
-	writel(val, tsc->tsc_base + reg);
-}
-
-static void tscadc_step_config(struct tscadc *ts_dev)
-{
-	unsigned int	config;
-	int i, total_steps;
-
-	/* Configure the Step registers */
-	total_steps = 2 * ts_dev->steps_to_configure;
-
-	config = STEPCONFIG_MODE_HWSYNC |
-			STEPCONFIG_AVG_16 | STEPCONFIG_XPP;
-	switch (ts_dev->wires) {
-	case 4:
-		config |= STEPCONFIG_INP_AN2 | STEPCONFIG_XNN;
-		break;
-	case 5:
-		config |= STEPCONFIG_YNN |
-				STEPCONFIG_INP_AN4 | STEPCONFIG_XNN |
-				STEPCONFIG_YPP;
-		break;
-	case 8:
-		config |= STEPCONFIG_INP_AN2 | STEPCONFIG_XNN;
-		break;
-	}
-
-	for (i = 1; i <= ts_dev->steps_to_configure; i++) {
-		tscadc_writel(ts_dev, REG_STEPCONFIG(i), config);
-		tscadc_writel(ts_dev, REG_STEPDELAY(i), STEPCONFIG_OPENDLY);
-	}
-
-	config = 0;
-	config = STEPCONFIG_MODE_HWSYNC |
-			STEPCONFIG_AVG_16 | STEPCONFIG_YNN |
-			STEPCONFIG_INM_ADCREFM | STEPCONFIG_FIFO1;
-	switch (ts_dev->wires) {
-	case 4:
-		config |= STEPCONFIG_YPP;
-		break;
-	case 5:
-		config |= STEPCONFIG_XPP | STEPCONFIG_INP_AN4 |
-				STEPCONFIG_XNP | STEPCONFIG_YPN;
-		break;
-	case 8:
-		config |= STEPCONFIG_YPP;
-		break;
-	}
-
-	for (i = (ts_dev->steps_to_configure + 1); i <= total_steps; i++) {
-		tscadc_writel(ts_dev, REG_STEPCONFIG(i), config);
-		tscadc_writel(ts_dev, REG_STEPDELAY(i), STEPCONFIG_OPENDLY);
-	}
-
-	config = 0;
-	/* Charge step configuration */
-	config = STEPCONFIG_XPP | STEPCONFIG_YNN |
-			STEPCHARGE_RFP_XPUL | STEPCHARGE_RFM_XNUR |
-			STEPCHARGE_INM_AN1 | STEPCHARGE_INP_AN1;
-
-	tscadc_writel(ts_dev, REG_CHARGECONFIG, config);
-	tscadc_writel(ts_dev, REG_CHARGEDELAY, CHARGEDLY_OPENDLY);
-
-	config = 0;
-	/* Configure to calculate pressure */
-	config = STEPCONFIG_MODE_HWSYNC |
-			STEPCONFIG_AVG_16 | STEPCONFIG_YPP |
-			STEPCONFIG_XNN | STEPCONFIG_INM_ADCREFM;
-	tscadc_writel(ts_dev, REG_STEPCONFIG(total_steps + 1), config);
-	tscadc_writel(ts_dev, REG_STEPDELAY(total_steps + 1),
-			STEPCONFIG_OPENDLY);
-
-	config |= STEPCONFIG_INP_AN3 | STEPCONFIG_FIFO1;
-	tscadc_writel(ts_dev, REG_STEPCONFIG(total_steps + 2), config);
-	tscadc_writel(ts_dev, REG_STEPDELAY(total_steps + 2),
-			STEPCONFIG_OPENDLY);
-
-	tscadc_writel(ts_dev, REG_SE, STPENB_STEPENB);
-}
-
-static void tscadc_idle_config(struct tscadc *ts_config)
-{
-	unsigned int idleconfig;
-
-	idleconfig = STEPCONFIG_YNN |
-			STEPCONFIG_INM_ADCREFM |
-			STEPCONFIG_YPN | STEPCONFIG_INP_ADCREFM;
-	tscadc_writel(ts_config, REG_IDLECONFIG, idleconfig);
-}
-
-static void tscadc_read_coordinates(struct tscadc *ts_dev,
-				    unsigned int *x, unsigned int *y)
-{
-	unsigned int fifocount = tscadc_readl(ts_dev, REG_FIFO0CNT);
-	unsigned int prev_val_x = ~0, prev_val_y = ~0;
-	unsigned int prev_diff_x = ~0, prev_diff_y = ~0;
-	unsigned int read, diff;
-	unsigned int i;
-
-	/*
-	 * Delta filter is used to remove large variations in sampled
-	 * values from ADC. The filter tries to predict where the next
-	 * coordinate could be. This is done by taking a previous
-	 * coordinate and subtracting it form current one. Further the
-	 * algorithm compares the difference with that of a present value,
-	 * if true the value is reported to the sub system.
-	 */
-	for (i = 0; i < fifocount - 1; i++) {
-		read = tscadc_readl(ts_dev, REG_FIFO0) & 0xfff;
-		diff = abs(read - prev_val_x);
-		if (diff < prev_diff_x) {
-			prev_diff_x = diff;
-			*x = read;
-		}
-		prev_val_x = read;
-
-		read = tscadc_readl(ts_dev, REG_FIFO1) & 0xfff;
-		diff = abs(read - prev_val_y);
-		if (diff < prev_diff_y) {
-			prev_diff_y = diff;
-			*y = read;
-		}
-		prev_val_y = read;
-	}
-}
-
-static irqreturn_t tscadc_irq(int irq, void *dev)
-{
-	struct tscadc *ts_dev = dev;
-	struct input_dev *input_dev = ts_dev->input;
-	unsigned int status, irqclr = 0;
-	unsigned int x = 0, y = 0;
-	unsigned int z1, z2, z;
-	unsigned int fsm;
-
-	status = tscadc_readl(ts_dev, REG_IRQSTATUS);
-	if (status & IRQENB_FIFO0THRES) {
-		tscadc_read_coordinates(ts_dev, &x, &y);
-
-		z1 = tscadc_readl(ts_dev, REG_FIFO0) & 0xfff;
-		z2 = tscadc_readl(ts_dev, REG_FIFO1) & 0xfff;
-
-		if (ts_dev->pen_down && z1 != 0 && z2 != 0) {
-			/*
-			 * Calculate pressure using formula
-			 * Resistance(touch) = x plate resistance *
-			 * x postion/4096 * ((z2 / z1) - 1)
-			 */
-			z = z2 - z1;
-			z *= x;
-			z *= ts_dev->x_plate_resistance;
-			z /= z1;
-			z = (z + 2047) >> 12;
-
-			if (z <= MAX_12BIT) {
-				input_report_abs(input_dev, ABS_X, x);
-				input_report_abs(input_dev, ABS_Y, y);
-				input_report_abs(input_dev, ABS_PRESSURE, z);
-				input_report_key(input_dev, BTN_TOUCH, 1);
-				input_sync(input_dev);
-			}
-		}
-		irqclr |= IRQENB_FIFO0THRES;
-	}
-
-	/*
-	 * Time for sequencer to settle, to read
-	 * correct state of the sequencer.
-	 */
-	udelay(SEQ_SETTLE);
-
-	status = tscadc_readl(ts_dev, REG_RAWIRQSTATUS);
-	if (status & IRQENB_PENUP) {
-		/* Pen up event */
-		fsm = tscadc_readl(ts_dev, REG_ADCFSM);
-		if (fsm == ADCFSM_STEPID) {
-			ts_dev->pen_down = false;
-			input_report_key(input_dev, BTN_TOUCH, 0);
-			input_report_abs(input_dev, ABS_PRESSURE, 0);
-			input_sync(input_dev);
-		} else {
-			ts_dev->pen_down = true;
-		}
-		irqclr |= IRQENB_PENUP;
-	}
-
-	tscadc_writel(ts_dev, REG_IRQSTATUS, irqclr);
-
-	tscadc_writel(ts_dev, REG_SE, STPENB_STEPENB);
-	return IRQ_HANDLED;
-}
-
-/*
- * The functions for inserting/removing driver as a module.
- */
-
-static int __devinit tscadc_probe(struct platform_device *pdev)
-{
-	const struct tsc_data *pdata = pdev->dev.platform_data;
-	struct resource *res;
-	struct tscadc *ts_dev;
-	struct input_dev *input_dev;
-	struct clk *clk;
-	int err;
-	int clk_value, ctrl, irq;
-
-	if (!pdata) {
-		dev_err(&pdev->dev, "missing platform data.\n");
-		return -EINVAL;
-	}
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "no memory resource defined.\n");
-		return -EINVAL;
-	}
-
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "no irq ID is specified.\n");
-		return -EINVAL;
-	}
-
-	/* Allocate memory for device */
-	ts_dev = kzalloc(sizeof(struct tscadc), GFP_KERNEL);
-	input_dev = input_allocate_device();
-	if (!ts_dev || !input_dev) {
-		dev_err(&pdev->dev, "failed to allocate memory.\n");
-		err = -ENOMEM;
-		goto err_free_mem;
-	}
-
-	ts_dev->input = input_dev;
-	ts_dev->irq = irq;
-	ts_dev->wires = pdata->wires;
-	ts_dev->x_plate_resistance = pdata->x_plate_resistance;
-	ts_dev->steps_to_configure = pdata->steps_to_configure;
-
-	res = request_mem_region(res->start, resource_size(res), pdev->name);
-	if (!res) {
-		dev_err(&pdev->dev, "failed to reserve registers.\n");
-		err = -EBUSY;
-		goto err_free_mem;
-	}
-
-	ts_dev->tsc_base = ioremap(res->start, resource_size(res));
-	if (!ts_dev->tsc_base) {
-		dev_err(&pdev->dev, "failed to map registers.\n");
-		err = -ENOMEM;
-		goto err_release_mem_region;
-	}
-
-	err = request_irq(ts_dev->irq, tscadc_irq,
-			  0, pdev->dev.driver->name, ts_dev);
-	if (err) {
-		dev_err(&pdev->dev, "failed to allocate irq.\n");
-		goto err_unmap_regs;
-	}
-
-	ts_dev->tsc_ick = clk_get(&pdev->dev, "adc_tsc_ick");
-	if (IS_ERR(ts_dev->tsc_ick)) {
-		dev_err(&pdev->dev, "failed to get TSC ick\n");
-		goto err_free_irq;
-	}
-	clk_enable(ts_dev->tsc_ick);
-
-	clk = clk_get(&pdev->dev, "adc_tsc_fck");
-	if (IS_ERR(clk)) {
-		dev_err(&pdev->dev, "failed to get TSC fck\n");
-		err = PTR_ERR(clk);
-		goto err_disable_clk;
-	}
-
-	clk_value = clk_get_rate(clk) / ADC_CLK;
-	clk_put(clk);
-
-	if (clk_value < 7) {
-		dev_err(&pdev->dev, "clock input less than min clock requirement\n");
-		goto err_disable_clk;
-	}
-	/* CLKDIV needs to be configured to the value minus 1 */
-	tscadc_writel(ts_dev, REG_CLKDIV, clk_value - 1);
-
-	 /* Enable wake-up of the SoC using touchscreen */
-	tscadc_writel(ts_dev, REG_IRQWAKEUP, IRQWKUP_ENB);
-
-	ctrl = CNTRLREG_STEPCONFIGWRT |
-			CNTRLREG_TSCENB |
-			CNTRLREG_STEPID;
-	switch (ts_dev->wires) {
-	case 4:
-		ctrl |= CNTRLREG_4WIRE;
-		break;
-	case 5:
-		ctrl |= CNTRLREG_5WIRE;
-		break;
-	case 8:
-		ctrl |= CNTRLREG_8WIRE;
-		break;
-	}
-	tscadc_writel(ts_dev, REG_CTRL, ctrl);
-
-	tscadc_idle_config(ts_dev);
-	tscadc_writel(ts_dev, REG_IRQENABLE, IRQENB_FIFO0THRES);
-	tscadc_step_config(ts_dev);
-	tscadc_writel(ts_dev, REG_FIFO0THR, ts_dev->steps_to_configure);
-
-	ctrl |= CNTRLREG_TSCSSENB;
-	tscadc_writel(ts_dev, REG_CTRL, ctrl);
-
-	input_dev->name = "ti-tsc-adc";
-	input_dev->dev.parent = &pdev->dev;
-
-	input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
-	input_dev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH);
-
-	input_set_abs_params(input_dev, ABS_X, 0, MAX_12BIT, 0, 0);
-	input_set_abs_params(input_dev, ABS_Y, 0, MAX_12BIT, 0, 0);
-	input_set_abs_params(input_dev, ABS_PRESSURE, 0, MAX_12BIT, 0, 0);
-
-	/* register to the input system */
-	err = input_register_device(input_dev);
-	if (err)
-		goto err_disable_clk;
-
-	platform_set_drvdata(pdev, ts_dev);
-	return 0;
-
-err_disable_clk:
-	clk_disable(ts_dev->tsc_ick);
-	clk_put(ts_dev->tsc_ick);
-err_free_irq:
-	free_irq(ts_dev->irq, ts_dev);
-err_unmap_regs:
-	iounmap(ts_dev->tsc_base);
-err_release_mem_region:
-	release_mem_region(res->start, resource_size(res));
-err_free_mem:
-	input_free_device(input_dev);
-	kfree(ts_dev);
-	return err;
-}
-
-static int __devexit tscadc_remove(struct platform_device *pdev)
-{
-	struct tscadc *ts_dev = platform_get_drvdata(pdev);
-	struct resource *res;
-
-	free_irq(ts_dev->irq, ts_dev);
-
-	input_unregister_device(ts_dev->input);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	iounmap(ts_dev->tsc_base);
-	release_mem_region(res->start, resource_size(res));
-
-	clk_disable(ts_dev->tsc_ick);
-	clk_put(ts_dev->tsc_ick);
-
-	kfree(ts_dev);
-
-	platform_set_drvdata(pdev, NULL);
-	return 0;
-}
-
-static struct platform_driver ti_tsc_driver = {
-	.probe	= tscadc_probe,
-	.remove	= __devexit_p(tscadc_remove),
-	.driver	= {
-		.name   = "tsc",
-		.owner	= THIS_MODULE,
-	},
-};
-module_platform_driver(ti_tsc_driver);
-
-MODULE_DESCRIPTION("TI touchscreen controller driver");
-MODULE_AUTHOR("Rachna Patil <rachna@ti.com>");
-MODULE_LICENSE("GPL");
diff --git a/include/linux/input/ti_am335x_tsc.h b/include/linux/input/ti_am335x_tsc.h
new file mode 100644
index 000000000000..49269a2aa329
--- /dev/null
+++ b/include/linux/input/ti_am335x_tsc.h
@@ -0,0 +1,23 @@
+#ifndef __LINUX_TI_AM335X_TSC_H
+#define __LINUX_TI_AM335X_TSC_H
+
+/**
+ * struct tsc_data	Touchscreen wire configuration
+ * @wires:		Wires refer to application modes
+ *			i.e. 4/5/8 wire touchscreen support
+ *			on the platform.
+ * @x_plate_resistance:	X plate resistance.
+ * @steps_to_configure:	The sequencer supports a total of
+ *			16 programmable steps.
+ *			A step configured to read a single
+ *			co-ordinate value, can be applied
+ *			more number of times for better results.
+ */
+
+struct tsc_data {
+	int wires;
+	int x_plate_resistance;
+	int steps_to_configure;
+};
+
+#endif
diff --git a/include/linux/input/ti_tscadc.h b/include/linux/input/ti_tscadc.h
deleted file mode 100644
index ad442a3eb68b..000000000000
--- a/include/linux/input/ti_tscadc.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef __LINUX_TI_TSCADC_H
-#define __LINUX_TI_TSCADC_H
-
-/**
- * struct tsc_data	Touchscreen wire configuration
- * @wires:		Wires refer to application modes
- *			i.e. 4/5/8 wire touchscreen support
- *			on the platform.
- * @x_plate_resistance:	X plate resistance.
- * @steps_to_configure:	The sequencer supports a total of
- *			16 programmable steps.
- *			A step configured to read a single
- *			co-ordinate value, can be applied
- *			more number of times for better results.
- */
-
-struct tsc_data {
-	int wires;
-	int x_plate_resistance;
-	int steps_to_configure;
-};
-
-#endif
-- 
cgit v1.2.3-55-g7522


From 01636eb970a029897b06fb96026941429212ddd9 Mon Sep 17 00:00:00 2001
From: Patil, Rachna
Date: Tue, 16 Oct 2012 12:55:43 +0530
Subject: mfd: ti_tscadc: Add support for TI's TSC/ADC MFDevice

Add the mfd core driver which supports touchscreen
and ADC.
With this patch we are only adding infrastructure to
support the MFD clients.

Signed-off-by: Patil, Rachna <rachna@ti.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/Kconfig                  |  11 ++
 drivers/mfd/Makefile                 |   1 +
 drivers/mfd/ti_am335x_tscadc.c       | 250 +++++++++++++++++++++++++++++++++++
 include/linux/mfd/ti_am335x_tscadc.h | 137 +++++++++++++++++++
 4 files changed, 399 insertions(+)
 create mode 100644 drivers/mfd/ti_am335x_tscadc.c
 create mode 100644 include/linux/mfd/ti_am335x_tscadc.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index acab3ef8a310..9bba7f78ff36 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -94,6 +94,17 @@ config MFD_TI_SSP
 	  To compile this driver as a module, choose M here: the
 	  module will be called ti-ssp.
 
+config MFD_TI_AM335X_TSCADC
+	tristate "TI ADC / Touch Screen chip support"
+	select MFD_CORE
+	select REGMAP
+	select REGMAP_MMIO
+	help
+	  If you say yes here you get support for Texas Instruments series
+	  of Touch Screen /ADC chips.
+	  To compile this driver as a module, choose M here: the
+	  module will be called ti_am335x_tscadc.
+
 config HTC_EGPIO
 	bool "HTC EGPIO support"
 	depends on GENERIC_HARDIRQS && GPIOLIB && ARM
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index d8ccb630ddb0..442c17e40741 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_HTC_I2CPLD)	+= htc-i2cpld.o
 obj-$(CONFIG_MFD_DAVINCI_VOICECODEC)	+= davinci_voicecodec.o
 obj-$(CONFIG_MFD_DM355EVM_MSP)	+= dm355evm_msp.o
 obj-$(CONFIG_MFD_TI_SSP)	+= ti-ssp.o
+obj-$(CONFIG_MFD_TI_AM335X_TSCADC)	+= ti_am335x_tscadc.o
 
 obj-$(CONFIG_MFD_STA2X11)	+= sta2x11-mfd.o
 obj-$(CONFIG_MFD_STMPE)		+= stmpe.o
diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
new file mode 100644
index 000000000000..14df67bc390f
--- /dev/null
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -0,0 +1,250 @@
+/*
+ * TI Touch Screen / ADC MFD driver
+ *
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/regmap.h>
+#include <linux/mfd/core.h>
+#include <linux/pm_runtime.h>
+
+#include <linux/mfd/ti_am335x_tscadc.h>
+
+static unsigned int tscadc_readl(struct ti_tscadc_dev *tsadc, unsigned int reg)
+{
+	unsigned int val;
+
+	regmap_read(tsadc->regmap_tscadc, reg, &val);
+	return val;
+}
+
+static void tscadc_writel(struct ti_tscadc_dev *tsadc, unsigned int reg,
+					unsigned int val)
+{
+	regmap_write(tsadc->regmap_tscadc, reg, val);
+}
+
+static const struct regmap_config tscadc_regmap_config = {
+	.name = "ti_tscadc",
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+};
+
+static void tscadc_idle_config(struct ti_tscadc_dev *config)
+{
+	unsigned int idleconfig;
+
+	idleconfig = STEPCONFIG_YNN | STEPCONFIG_INM_ADCREFM |
+			STEPCONFIG_INP_ADCREFM | STEPCONFIG_YPN;
+
+	tscadc_writel(config, REG_IDLECONFIG, idleconfig);
+}
+
+static	int __devinit ti_tscadc_probe(struct platform_device *pdev)
+{
+	struct ti_tscadc_dev	*tscadc;
+	struct resource		*res;
+	struct clk		*clk;
+	struct mfd_tscadc_board	*pdata = pdev->dev.platform_data;
+	int			irq;
+	int			err, ctrl;
+	int			clk_value, clock_rate;
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "Could not find platform data\n");
+		return -EINVAL;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "no memory resource defined.\n");
+		return -EINVAL;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "no irq ID is specified.\n");
+		return -EINVAL;
+	}
+
+	/* Allocate memory for device */
+	tscadc = devm_kzalloc(&pdev->dev,
+			sizeof(struct ti_tscadc_dev), GFP_KERNEL);
+	if (!tscadc) {
+		dev_err(&pdev->dev, "failed to allocate memory.\n");
+		return -ENOMEM;
+	}
+	tscadc->dev = &pdev->dev;
+	tscadc->irq = irq;
+
+	res = devm_request_mem_region(&pdev->dev,
+			res->start, resource_size(res), pdev->name);
+	if (!res) {
+		dev_err(&pdev->dev, "failed to reserve registers.\n");
+		err = -EBUSY;
+		goto err;
+	}
+
+	tscadc->tscadc_base = devm_ioremap(&pdev->dev,
+			res->start, resource_size(res));
+	if (!tscadc->tscadc_base) {
+		dev_err(&pdev->dev, "failed to map registers.\n");
+		err = -ENOMEM;
+		goto err;
+	}
+
+	tscadc->regmap_tscadc = devm_regmap_init_mmio(&pdev->dev,
+			tscadc->tscadc_base, &tscadc_regmap_config);
+	if (IS_ERR(tscadc->regmap_tscadc)) {
+		dev_err(&pdev->dev, "regmap init failed\n");
+		err = PTR_ERR(tscadc->regmap_tscadc);
+		goto err;
+	}
+
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
+
+	/*
+	 * The TSC_ADC_Subsystem has 2 clock domains
+	 * OCP_CLK and ADC_CLK.
+	 * The ADC clock is expected to run at target of 3MHz,
+	 * and expected to capture 12-bit data at a rate of 200 KSPS.
+	 * The TSC_ADC_SS controller design assumes the OCP clock is
+	 * at least 6x faster than the ADC clock.
+	 */
+	clk = clk_get(&pdev->dev, "adc_tsc_fck");
+	if (IS_ERR(clk)) {
+		dev_err(&pdev->dev, "failed to get TSC fck\n");
+		err = PTR_ERR(clk);
+		goto err_disable_clk;
+	}
+	clock_rate = clk_get_rate(clk);
+	clk_put(clk);
+	clk_value = clock_rate / ADC_CLK;
+	if (clk_value < MAX_CLK_DIV) {
+		dev_err(&pdev->dev, "clock input less than min clock requirement\n");
+		err = -EINVAL;
+		goto err_disable_clk;
+	}
+	/* TSCADC_CLKDIV needs to be configured to the value minus 1 */
+	clk_value = clk_value - 1;
+	tscadc_writel(tscadc, REG_CLKDIV, clk_value);
+
+	/* Set the control register bits */
+	ctrl = CNTRLREG_STEPCONFIGWRT |
+			CNTRLREG_TSCENB |
+			CNTRLREG_STEPID |
+			CNTRLREG_4WIRE;
+	tscadc_writel(tscadc, REG_CTRL, ctrl);
+
+	/* Set register bits for Idle Config Mode */
+	tscadc_idle_config(tscadc);
+
+	/* Enable the TSC module enable bit */
+	ctrl = tscadc_readl(tscadc, REG_CTRL);
+	ctrl |= CNTRLREG_TSCSSENB;
+	tscadc_writel(tscadc, REG_CTRL, ctrl);
+
+	err = mfd_add_devices(&pdev->dev, pdev->id, tscadc->cells,
+			TSCADC_CELLS, NULL, 0, NULL);
+	if (err < 0)
+		goto err_disable_clk;
+
+	device_init_wakeup(&pdev->dev, true);
+	platform_set_drvdata(pdev, tscadc);
+
+	return 0;
+
+err_disable_clk:
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+err:
+	return err;
+}
+
+static int __devexit ti_tscadc_remove(struct platform_device *pdev)
+{
+	struct ti_tscadc_dev	*tscadc = platform_get_drvdata(pdev);
+
+	tscadc_writel(tscadc, REG_SE, 0x00);
+
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	mfd_remove_devices(tscadc->dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int tscadc_suspend(struct device *dev)
+{
+	struct ti_tscadc_dev	*tscadc_dev = dev_get_drvdata(dev);
+
+	tscadc_writel(tscadc_dev, REG_SE, 0x00);
+	pm_runtime_put_sync(dev);
+
+	return 0;
+}
+
+static int tscadc_resume(struct device *dev)
+{
+	struct ti_tscadc_dev	*tscadc_dev = dev_get_drvdata(dev);
+	unsigned int restore, ctrl;
+
+	pm_runtime_get_sync(dev);
+
+	/* context restore */
+	ctrl = CNTRLREG_STEPCONFIGWRT | CNTRLREG_TSCENB |
+			CNTRLREG_STEPID | CNTRLREG_4WIRE;
+	tscadc_writel(tscadc_dev, REG_CTRL, ctrl);
+	tscadc_idle_config(tscadc_dev);
+	tscadc_writel(tscadc_dev, REG_SE, STPENB_STEPENB);
+	restore = tscadc_readl(tscadc_dev, REG_CTRL);
+	tscadc_writel(tscadc_dev, REG_CTRL,
+			(restore | CNTRLREG_TSCSSENB));
+
+	return 0;
+}
+
+static const struct dev_pm_ops tscadc_pm_ops = {
+	.suspend = tscadc_suspend,
+	.resume = tscadc_resume,
+};
+#define TSCADC_PM_OPS (&tscadc_pm_ops)
+#else
+#define TSCADC_PM_OPS NULL
+#endif
+
+static struct platform_driver ti_tscadc_driver = {
+	.driver = {
+		.name   = "ti_tscadc",
+		.owner	= THIS_MODULE,
+		.pm	= TSCADC_PM_OPS,
+	},
+	.probe	= ti_tscadc_probe,
+	.remove	= __devexit_p(ti_tscadc_remove),
+
+};
+
+module_platform_driver(ti_tscadc_driver);
+
+MODULE_DESCRIPTION("TI touchscreen / ADC MFD controller driver");
+MODULE_AUTHOR("Rachna Patil <rachna@ti.com>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
new file mode 100644
index 000000000000..b7232b157061
--- /dev/null
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -0,0 +1,137 @@
+#ifndef __LINUX_TI_AM335X_TSCADC_MFD_H
+#define __LINUX_TI_AM335X_TSCADC_MFD_H
+
+/*
+ * TI Touch Screen / ADC MFD driver
+ *
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/mfd/core.h>
+
+#define REG_RAWIRQSTATUS	0x024
+#define REG_IRQSTATUS		0x028
+#define REG_IRQENABLE		0x02C
+#define REG_IRQCLR		0x030
+#define REG_IRQWAKEUP		0x034
+#define REG_CTRL		0x040
+#define REG_ADCFSM		0x044
+#define REG_CLKDIV		0x04C
+#define REG_SE			0x054
+#define REG_IDLECONFIG		0x058
+#define REG_CHARGECONFIG	0x05C
+#define REG_CHARGEDELAY		0x060
+#define REG_STEPCONFIG(n)	(0x64 + ((n - 1) * 8))
+#define REG_STEPDELAY(n)	(0x68 + ((n - 1) * 8))
+#define REG_FIFO0CNT		0xE4
+#define REG_FIFO0THR		0xE8
+#define REG_FIFO1CNT		0xF0
+#define REG_FIFO1THR		0xF4
+#define REG_FIFO0		0x100
+#define REG_FIFO1		0x200
+
+/*	Register Bitfields	*/
+/* IRQ wakeup enable */
+#define IRQWKUP_ENB		BIT(0)
+
+/* Step Enable */
+#define STEPENB_MASK		(0x1FFFF << 0)
+#define STEPENB(val)		((val) << 0)
+#define STPENB_STEPENB		STEPENB(0x1FFFF)
+
+/* IRQ enable */
+#define IRQENB_HW_PEN		BIT(0)
+#define IRQENB_FIFO0THRES	BIT(2)
+#define IRQENB_FIFO1THRES	BIT(5)
+#define IRQENB_PENUP		BIT(9)
+
+/* Step Configuration */
+#define STEPCONFIG_MODE_MASK	(3 << 0)
+#define STEPCONFIG_MODE(val)	((val) << 0)
+#define STEPCONFIG_MODE_HWSYNC	STEPCONFIG_MODE(2)
+#define STEPCONFIG_AVG_MASK	(7 << 2)
+#define STEPCONFIG_AVG(val)	((val) << 2)
+#define STEPCONFIG_AVG_16	STEPCONFIG_AVG(4)
+#define STEPCONFIG_XPP		BIT(5)
+#define STEPCONFIG_XNN		BIT(6)
+#define STEPCONFIG_YPP		BIT(7)
+#define STEPCONFIG_YNN		BIT(8)
+#define STEPCONFIG_XNP		BIT(9)
+#define STEPCONFIG_YPN		BIT(10)
+#define STEPCONFIG_INM_MASK	(0xF << 15)
+#define STEPCONFIG_INM(val)	((val) << 15)
+#define STEPCONFIG_INM_ADCREFM	STEPCONFIG_INM(8)
+#define STEPCONFIG_INP_MASK	(0xF << 19)
+#define STEPCONFIG_INP(val)	((val) << 19)
+#define STEPCONFIG_INP_AN2	STEPCONFIG_INP(2)
+#define STEPCONFIG_INP_AN3	STEPCONFIG_INP(3)
+#define STEPCONFIG_INP_AN4	STEPCONFIG_INP(4)
+#define STEPCONFIG_INP_ADCREFM	STEPCONFIG_INP(8)
+#define STEPCONFIG_FIFO1	BIT(26)
+
+/* Delay register */
+#define STEPDELAY_OPEN_MASK	(0x3FFFF << 0)
+#define STEPDELAY_OPEN(val)	((val) << 0)
+#define STEPCONFIG_OPENDLY	STEPDELAY_OPEN(0x098)
+#define STEPDELAY_SAMPLE_MASK	(0xFF << 24)
+#define STEPDELAY_SAMPLE(val)	((val) << 24)
+#define STEPCONFIG_SAMPLEDLY	STEPDELAY_SAMPLE(0)
+
+/* Charge Config */
+#define STEPCHARGE_RFP_MASK	(7 << 12)
+#define STEPCHARGE_RFP(val)	((val) << 12)
+#define STEPCHARGE_RFP_XPUL	STEPCHARGE_RFP(1)
+#define STEPCHARGE_INM_MASK	(0xF << 15)
+#define STEPCHARGE_INM(val)	((val) << 15)
+#define STEPCHARGE_INM_AN1	STEPCHARGE_INM(1)
+#define STEPCHARGE_INP_MASK	(0xF << 19)
+#define STEPCHARGE_INP(val)	((val) << 19)
+#define STEPCHARGE_INP_AN1	STEPCHARGE_INP(1)
+#define STEPCHARGE_RFM_MASK	(3 << 23)
+#define STEPCHARGE_RFM(val)	((val) << 23)
+#define STEPCHARGE_RFM_XNUR	STEPCHARGE_RFM(1)
+
+/* Charge delay */
+#define CHARGEDLY_OPEN_MASK	(0x3FFFF << 0)
+#define CHARGEDLY_OPEN(val)	((val) << 0)
+#define CHARGEDLY_OPENDLY	CHARGEDLY_OPEN(1)
+
+/* Control register */
+#define CNTRLREG_TSCSSENB	BIT(0)
+#define CNTRLREG_STEPID		BIT(1)
+#define CNTRLREG_STEPCONFIGWRT	BIT(2)
+#define CNTRLREG_POWERDOWN	BIT(4)
+#define CNTRLREG_AFE_CTRL_MASK	(3 << 5)
+#define CNTRLREG_AFE_CTRL(val)	((val) << 5)
+#define CNTRLREG_4WIRE		CNTRLREG_AFE_CTRL(1)
+#define CNTRLREG_5WIRE		CNTRLREG_AFE_CTRL(2)
+#define CNTRLREG_8WIRE		CNTRLREG_AFE_CTRL(3)
+#define CNTRLREG_TSCENB		BIT(7)
+
+#define ADC_CLK			3000000
+#define	MAX_CLK_DIV		7
+
+#define TSCADC_CELLS		0
+
+struct mfd_tscadc_board {
+	struct tsc_data *tsc_init;
+};
+
+struct ti_tscadc_dev {
+	struct device *dev;
+	struct regmap *regmap_tscadc;
+	void __iomem *tscadc_base;
+	int irq;
+	struct mfd_cell cells[TSCADC_CELLS];
+};
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 2b99bafab19145a72e2c557326fc4662a864a162 Mon Sep 17 00:00:00 2001
From: Patil, Rachna
Date: Tue, 16 Oct 2012 12:55:44 +0530
Subject: input: TSC: ti_tsc: Convert TSC into a MFDevice

This patch converts touchscreen into a MFD client.
All the register definitions, clock initialization,
etc has been moved to MFD core driver.

Signed-off-by: Patil, Rachna <rachna@ti.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/input/touchscreen/Kconfig         |   2 +-
 drivers/input/touchscreen/ti_am335x_tsc.c | 318 +++++++++---------------------
 drivers/mfd/ti_am335x_tscadc.c            |  11 ++
 include/linux/mfd/ti_am335x_tscadc.h      |  10 +-
 4 files changed, 118 insertions(+), 223 deletions(-)

(limited to 'include')

diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index d31dc5faeaaf..0c45caddd41c 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -531,7 +531,7 @@ config TOUCHSCREEN_TOUCHWIN
 
 config TOUCHSCREEN_TI_AM335X_TSC
 	tristate "TI Touchscreen Interface"
-	depends on ARCH_OMAP2PLUS
+	depends on MFD_TI_AM335X_TSCADC
 	help
 	  Say Y here if you have 4/5/8 wire touchscreen controller
 	  to be connected to the ADC controller on your TI AM335x SoC.
diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c
index 462950acb97b..7a18a8a15228 100644
--- a/drivers/input/touchscreen/ti_am335x_tsc.c
+++ b/drivers/input/touchscreen/ti_am335x_tsc.c
@@ -27,106 +27,15 @@
 #include <linux/input/ti_am335x_tsc.h>
 #include <linux/delay.h>
 
-#define REG_RAWIRQSTATUS	0x024
-#define REG_IRQSTATUS		0x028
-#define REG_IRQENABLE		0x02C
-#define REG_IRQWAKEUP		0x034
-#define REG_CTRL		0x040
-#define REG_ADCFSM		0x044
-#define REG_CLKDIV		0x04C
-#define REG_SE			0x054
-#define REG_IDLECONFIG		0x058
-#define REG_CHARGECONFIG	0x05C
-#define REG_CHARGEDELAY		0x060
-#define REG_STEPCONFIG(n)	(0x64 + ((n - 1) * 8))
-#define REG_STEPDELAY(n)	(0x68 + ((n - 1) * 8))
-#define REG_FIFO0CNT		0xE4
-#define REG_FIFO0THR		0xE8
-#define REG_FIFO1THR		0xF4
-#define REG_FIFO0		0x100
-#define REG_FIFO1		0x200
-
-/*	Register Bitfields	*/
-#define IRQWKUP_ENB		BIT(0)
-
-/* Step Enable */
-#define STEPENB_MASK		(0x1FFFF << 0)
-#define STEPENB(val)		(val << 0)
-#define STPENB_STEPENB		STEPENB(0x7FFF)
-
-/* IRQ enable */
-#define IRQENB_FIFO0THRES	BIT(2)
-#define IRQENB_FIFO1THRES	BIT(5)
-#define IRQENB_PENUP		BIT(9)
-
-/* Step Configuration */
-#define STEPCONFIG_MODE_MASK	(3 << 0)
-#define STEPCONFIG_MODE(val)	(val << 0)
-#define STEPCONFIG_MODE_HWSYNC	STEPCONFIG_MODE(2)
-#define STEPCONFIG_AVG_MASK	(7 << 2)
-#define STEPCONFIG_AVG(val)	(val << 2)
-#define STEPCONFIG_AVG_16	STEPCONFIG_AVG(4)
-#define STEPCONFIG_XPP		BIT(5)
-#define STEPCONFIG_XNN		BIT(6)
-#define STEPCONFIG_YPP		BIT(7)
-#define STEPCONFIG_YNN		BIT(8)
-#define STEPCONFIG_XNP		BIT(9)
-#define STEPCONFIG_YPN		BIT(10)
-#define STEPCONFIG_INM_MASK	(0xF << 15)
-#define STEPCONFIG_INM(val)	(val << 15)
-#define STEPCONFIG_INM_ADCREFM	STEPCONFIG_INM(8)
-#define STEPCONFIG_INP_MASK	(0xF << 19)
-#define STEPCONFIG_INP(val)	(val << 19)
-#define STEPCONFIG_INP_AN2	STEPCONFIG_INP(2)
-#define STEPCONFIG_INP_AN3	STEPCONFIG_INP(3)
-#define STEPCONFIG_INP_AN4	STEPCONFIG_INP(4)
-#define STEPCONFIG_INP_ADCREFM	STEPCONFIG_INP(8)
-#define STEPCONFIG_FIFO1	BIT(26)
-
-/* Delay register */
-#define STEPDELAY_OPEN_MASK	(0x3FFFF << 0)
-#define STEPDELAY_OPEN(val)	(val << 0)
-#define STEPCONFIG_OPENDLY	STEPDELAY_OPEN(0x098)
-
-/* Charge Config */
-#define STEPCHARGE_RFP_MASK	(7 << 12)
-#define STEPCHARGE_RFP(val)	(val << 12)
-#define STEPCHARGE_RFP_XPUL	STEPCHARGE_RFP(1)
-#define STEPCHARGE_INM_MASK	(0xF << 15)
-#define STEPCHARGE_INM(val)	(val << 15)
-#define STEPCHARGE_INM_AN1	STEPCHARGE_INM(1)
-#define STEPCHARGE_INP_MASK	(0xF << 19)
-#define STEPCHARGE_INP(val)	(val << 19)
-#define STEPCHARGE_INP_AN1	STEPCHARGE_INP(1)
-#define STEPCHARGE_RFM_MASK	(3 << 23)
-#define STEPCHARGE_RFM(val)	(val << 23)
-#define STEPCHARGE_RFM_XNUR	STEPCHARGE_RFM(1)
-
-/* Charge delay */
-#define CHARGEDLY_OPEN_MASK	(0x3FFFF << 0)
-#define CHARGEDLY_OPEN(val)	(val << 0)
-#define CHARGEDLY_OPENDLY	CHARGEDLY_OPEN(1)
-
-/* Control register */
-#define CNTRLREG_TSCSSENB	BIT(0)
-#define CNTRLREG_STEPID		BIT(1)
-#define CNTRLREG_STEPCONFIGWRT	BIT(2)
-#define CNTRLREG_AFE_CTRL_MASK	(3 << 5)
-#define CNTRLREG_AFE_CTRL(val)	(val << 5)
-#define CNTRLREG_4WIRE		CNTRLREG_AFE_CTRL(1)
-#define CNTRLREG_5WIRE		CNTRLREG_AFE_CTRL(2)
-#define CNTRLREG_8WIRE		CNTRLREG_AFE_CTRL(3)
-#define CNTRLREG_TSCENB		BIT(7)
+#include <linux/mfd/ti_am335x_tscadc.h>
 
 #define ADCFSM_STEPID		0x10
 #define SEQ_SETTLE		275
-#define ADC_CLK			3000000
 #define MAX_12BIT		((1 << 12) - 1)
 
 struct titsc {
 	struct input_dev	*input;
-	struct clk		*tsc_ick;
-	void __iomem		*tsc_base;
+	struct ti_tscadc_dev	*mfd_tscadc;
 	unsigned int		irq;
 	unsigned int		wires;
 	unsigned int		x_plate_resistance;
@@ -136,13 +45,13 @@ struct titsc {
 
 static unsigned int titsc_readl(struct titsc *ts, unsigned int reg)
 {
-	return readl(ts->tsc_base + reg);
+	return readl(ts->mfd_tscadc->tscadc_base + reg);
 }
 
 static void titsc_writel(struct titsc *tsc, unsigned int reg,
 					unsigned int val)
 {
-	writel(val, tsc->tsc_base + reg);
+	writel(val, tsc->mfd_tscadc->tscadc_base + reg);
 }
 
 static void titsc_step_config(struct titsc *ts_dev)
@@ -219,17 +128,7 @@ static void titsc_step_config(struct titsc *ts_dev)
 	titsc_writel(ts_dev, REG_STEPDELAY(total_steps + 2),
 			STEPCONFIG_OPENDLY);
 
-	titsc_writel(ts_dev, REG_SE, STPENB_STEPENB);
-}
-
-static void titsc_idle_config(struct titsc *ts_config)
-{
-	unsigned int idleconfig;
-
-	idleconfig = STEPCONFIG_YNN |
-			STEPCONFIG_INM_ADCREFM |
-			STEPCONFIG_YPN | STEPCONFIG_INP_ADCREFM;
-	titsc_writel(ts_config, REG_IDLECONFIG, idleconfig);
+	titsc_writel(ts_dev, REG_SE, STPENB_STEPENB_TC);
 }
 
 static void titsc_read_coordinates(struct titsc *ts_dev,
@@ -239,7 +138,7 @@ static void titsc_read_coordinates(struct titsc *ts_dev,
 	unsigned int prev_val_x = ~0, prev_val_y = ~0;
 	unsigned int prev_diff_x = ~0, prev_diff_y = ~0;
 	unsigned int read, diff;
-	unsigned int i;
+	unsigned int i, channel;
 
 	/*
 	 * Delta filter is used to remove large variations in sampled
@@ -250,21 +149,32 @@ static void titsc_read_coordinates(struct titsc *ts_dev,
 	 * if true the value is reported to the sub system.
 	 */
 	for (i = 0; i < fifocount - 1; i++) {
-		read = titsc_readl(ts_dev, REG_FIFO0) & 0xfff;
-		diff = abs(read - prev_val_x);
-		if (diff < prev_diff_x) {
-			prev_diff_x = diff;
-			*x = read;
+		read = titsc_readl(ts_dev, REG_FIFO0);
+		channel = read & 0xf0000;
+		channel = channel >> 0x10;
+		if ((channel >= 0) && (channel < ts_dev->steps_to_configure)) {
+			read &= 0xfff;
+			diff = abs(read - prev_val_x);
+			if (diff < prev_diff_x) {
+				prev_diff_x = diff;
+				*x = read;
+			}
+			prev_val_x = read;
 		}
-		prev_val_x = read;
 
-		read = titsc_readl(ts_dev, REG_FIFO1) & 0xfff;
-		diff = abs(read - prev_val_y);
-		if (diff < prev_diff_y) {
-			prev_diff_y = diff;
-			*y = read;
+		read = titsc_readl(ts_dev, REG_FIFO1);
+		channel = read & 0xf0000;
+		channel = channel >> 0x10;
+		if ((channel >= ts_dev->steps_to_configure) &&
+			(channel < (2 * ts_dev->steps_to_configure - 1))) {
+			read &= 0xfff;
+			diff = abs(read - prev_val_y);
+			if (diff < prev_diff_y) {
+				prev_diff_y = diff;
+				*y = read;
+			}
+			prev_val_y = read;
 		}
-		prev_val_y = read;
 	}
 }
 
@@ -276,6 +186,8 @@ static irqreturn_t titsc_irq(int irq, void *dev)
 	unsigned int x = 0, y = 0;
 	unsigned int z1, z2, z;
 	unsigned int fsm;
+	unsigned int fifo1count, fifo0count;
+	int i;
 
 	status = titsc_readl(ts_dev, REG_IRQSTATUS);
 	if (status & IRQENB_FIFO0THRES) {
@@ -284,6 +196,14 @@ static irqreturn_t titsc_irq(int irq, void *dev)
 		z1 = titsc_readl(ts_dev, REG_FIFO0) & 0xfff;
 		z2 = titsc_readl(ts_dev, REG_FIFO1) & 0xfff;
 
+		fifo1count = titsc_readl(ts_dev, REG_FIFO1CNT);
+		for (i = 0; i < fifo1count; i++)
+			titsc_readl(ts_dev, REG_FIFO1);
+
+		fifo0count = titsc_readl(ts_dev, REG_FIFO0CNT);
+		for (i = 0; i < fifo0count; i++)
+			titsc_readl(ts_dev, REG_FIFO0);
+
 		if (ts_dev->pen_down && z1 != 0 && z2 != 0) {
 			/*
 			 * Calculate pressure using formula
@@ -330,7 +250,7 @@ static irqreturn_t titsc_irq(int irq, void *dev)
 
 	titsc_writel(ts_dev, REG_IRQSTATUS, irqclr);
 
-	titsc_writel(ts_dev, REG_SE, STPENB_STEPENB);
+	titsc_writel(ts_dev, REG_SE, STPENB_STEPENB_TC);
 	return IRQ_HANDLED;
 }
 
@@ -340,28 +260,16 @@ static irqreturn_t titsc_irq(int irq, void *dev)
 
 static int __devinit titsc_probe(struct platform_device *pdev)
 {
-	const struct tsc_data *pdata = pdev->dev.platform_data;
-	struct resource *res;
 	struct titsc *ts_dev;
 	struct input_dev *input_dev;
-	struct clk *clk;
+	struct ti_tscadc_dev *tscadc_dev = pdev->dev.platform_data;
+	struct mfd_tscadc_board	*pdata;
 	int err;
-	int clk_value, ctrl, irq;
 
-	if (!pdata) {
-		dev_err(&pdev->dev, "missing platform data.\n");
-		return -EINVAL;
-	}
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "no memory resource defined.\n");
-		return -EINVAL;
-	}
+	pdata = tscadc_dev->dev->platform_data;
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "no irq ID is specified.\n");
+	if (!pdata) {
+		dev_err(&pdev->dev, "Could not find platform data\n");
 		return -EINVAL;
 	}
 
@@ -374,85 +282,26 @@ static int __devinit titsc_probe(struct platform_device *pdev)
 		goto err_free_mem;
 	}
 
+	tscadc_dev->tsc = ts_dev;
+	ts_dev->mfd_tscadc = tscadc_dev;
 	ts_dev->input = input_dev;
-	ts_dev->irq = irq;
-	ts_dev->wires = pdata->wires;
-	ts_dev->x_plate_resistance = pdata->x_plate_resistance;
-	ts_dev->steps_to_configure = pdata->steps_to_configure;
-
-	res = request_mem_region(res->start, resource_size(res), pdev->name);
-	if (!res) {
-		dev_err(&pdev->dev, "failed to reserve registers.\n");
-		err = -EBUSY;
-		goto err_free_mem;
-	}
-
-	ts_dev->tsc_base = ioremap(res->start, resource_size(res));
-	if (!ts_dev->tsc_base) {
-		dev_err(&pdev->dev, "failed to map registers.\n");
-		err = -ENOMEM;
-		goto err_release_mem_region;
-	}
+	ts_dev->irq = tscadc_dev->irq;
+	ts_dev->wires = pdata->tsc_init->wires;
+	ts_dev->x_plate_resistance = pdata->tsc_init->x_plate_resistance;
+	ts_dev->steps_to_configure = pdata->tsc_init->steps_to_configure;
 
 	err = request_irq(ts_dev->irq, titsc_irq,
 			  0, pdev->dev.driver->name, ts_dev);
 	if (err) {
 		dev_err(&pdev->dev, "failed to allocate irq.\n");
-		goto err_unmap_regs;
-	}
-
-	ts_dev->tsc_ick = clk_get(&pdev->dev, "adc_tsc_ick");
-	if (IS_ERR(ts_dev->tsc_ick)) {
-		dev_err(&pdev->dev, "failed to get TSC ick\n");
-		goto err_free_irq;
-	}
-	clk_enable(ts_dev->tsc_ick);
-
-	clk = clk_get(&pdev->dev, "adc_tsc_fck");
-	if (IS_ERR(clk)) {
-		dev_err(&pdev->dev, "failed to get TSC fck\n");
-		err = PTR_ERR(clk);
-		goto err_disable_clk;
-	}
-
-	clk_value = clk_get_rate(clk) / ADC_CLK;
-	clk_put(clk);
-
-	if (clk_value < 7) {
-		dev_err(&pdev->dev, "clock input less than min clock requirement\n");
-		goto err_disable_clk;
-	}
-	/* CLKDIV needs to be configured to the value minus 1 */
-	titsc_writel(ts_dev, REG_CLKDIV, clk_value - 1);
-
-	 /* Enable wake-up of the SoC using touchscreen */
-	titsc_writel(ts_dev, REG_IRQWAKEUP, IRQWKUP_ENB);
-
-	ctrl = CNTRLREG_STEPCONFIGWRT |
-			CNTRLREG_TSCENB |
-			CNTRLREG_STEPID;
-	switch (ts_dev->wires) {
-	case 4:
-		ctrl |= CNTRLREG_4WIRE;
-		break;
-	case 5:
-		ctrl |= CNTRLREG_5WIRE;
-		break;
-	case 8:
-		ctrl |= CNTRLREG_8WIRE;
-		break;
+		goto err_free_mem;
 	}
-	titsc_writel(ts_dev, REG_CTRL, ctrl);
 
-	titsc_idle_config(ts_dev);
 	titsc_writel(ts_dev, REG_IRQENABLE, IRQENB_FIFO0THRES);
 	titsc_step_config(ts_dev);
 	titsc_writel(ts_dev, REG_FIFO0THR, ts_dev->steps_to_configure);
 
-	ctrl |= CNTRLREG_TSCSSENB;
-	titsc_writel(ts_dev, REG_CTRL, ctrl);
-
-	input_dev->name = "ti-tsc-adc";
+	input_dev->name = "ti-tsc";
 	input_dev->dev.parent = &pdev->dev;
 
 	input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
@@ -465,20 +314,13 @@ static int __devinit titsc_probe(struct platform_device *pdev)
 	/* register to the input system */
 	err = input_register_device(input_dev);
 	if (err)
-		goto err_disable_clk;
+		goto err_free_irq;
 
 	platform_set_drvdata(pdev, ts_dev);
 	return 0;
 
-err_disable_clk:
-	clk_disable(ts_dev->tsc_ick);
-	clk_put(ts_dev->tsc_ick);
 err_free_irq:
 	free_irq(ts_dev->irq, ts_dev);
-err_unmap_regs:
-	iounmap(ts_dev->tsc_base);
-err_release_mem_region:
-	release_mem_region(res->start, resource_size(res));
 err_free_mem:
 	input_free_device(input_dev);
 	kfree(ts_dev);
@@ -487,32 +329,66 @@ err_free_mem:
 
 static int __devexit titsc_remove(struct platform_device *pdev)
 {
-	struct titsc *ts_dev = platform_get_drvdata(pdev);
-	struct resource *res;
+	struct ti_tscadc_dev *tscadc_dev = pdev->dev.platform_data;
+	struct titsc *ts_dev = tscadc_dev->tsc;
 
 	free_irq(ts_dev->irq, ts_dev);
 
 	input_unregister_device(ts_dev->input);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	iounmap(ts_dev->tsc_base);
-	release_mem_region(res->start, resource_size(res));
+	platform_set_drvdata(pdev, NULL);
+	kfree(ts_dev);
+	return 0;
+}
 
-	clk_disable(ts_dev->tsc_ick);
-	clk_put(ts_dev->tsc_ick);
+#ifdef CONFIG_PM
+static int titsc_suspend(struct device *dev)
+{
+	struct ti_tscadc_dev *tscadc_dev = dev->platform_data;
+	struct titsc *ts_dev = tscadc_dev->tsc;
+	unsigned int idle;
+
+	if (device_may_wakeup(tscadc_dev->dev)) {
+		idle = titsc_readl(ts_dev, REG_IRQENABLE);
+		titsc_writel(ts_dev, REG_IRQENABLE,
+				(idle | IRQENB_HW_PEN));
+		titsc_writel(ts_dev, REG_IRQWAKEUP, IRQWKUP_ENB);
+	}
+	return 0;
+}
 
-	kfree(ts_dev);
+static int titsc_resume(struct device *dev)
+{
+	struct ti_tscadc_dev *tscadc_dev = dev->platform_data;
+	struct titsc *ts_dev = tscadc_dev->tsc;
 
-	platform_set_drvdata(pdev, NULL);
+	if (device_may_wakeup(tscadc_dev->dev)) {
+		titsc_writel(ts_dev, REG_IRQWAKEUP,
+				0x00);
+		titsc_writel(ts_dev, REG_IRQCLR, IRQENB_HW_PEN);
+	}
+	titsc_step_config(ts_dev);
+	titsc_writel(ts_dev, REG_FIFO0THR,
+			ts_dev->steps_to_configure);
 	return 0;
 }
 
+static const struct dev_pm_ops titsc_pm_ops = {
+	.suspend = titsc_suspend,
+	.resume  = titsc_resume,
+};
+#define TITSC_PM_OPS (&titsc_pm_ops)
+#else
+#define TITSC_PM_OPS NULL
+#endif
+
 static struct platform_driver ti_tsc_driver = {
 	.probe	= titsc_probe,
 	.remove	= __devexit_p(titsc_remove),
 	.driver	= {
 		.name   = "tsc",
 		.owner	= THIS_MODULE,
+		.pm	= TITSC_PM_OPS,
 	},
 };
 module_platform_driver(ti_tsc_driver);
diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index 14df67bc390f..d812be4b61df 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -24,6 +24,7 @@
 #include <linux/pm_runtime.h>
 
 #include <linux/mfd/ti_am335x_tscadc.h>
+#include <linux/input/ti_am335x_tsc.h>
 
 static unsigned int tscadc_readl(struct ti_tscadc_dev *tsadc, unsigned int reg)
 {
@@ -62,15 +63,19 @@ static	int __devinit ti_tscadc_probe(struct platform_device *pdev)
 	struct resource		*res;
 	struct clk		*clk;
 	struct mfd_tscadc_board	*pdata = pdev->dev.platform_data;
+	struct mfd_cell		*cell;
 	int			irq;
 	int			err, ctrl;
 	int			clk_value, clock_rate;
+	int			tsc_wires;
 
 	if (!pdata) {
 		dev_err(&pdev->dev, "Could not find platform data\n");
 		return -EINVAL;
 	}
 
+	tsc_wires = pdata->tsc_init->wires;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		dev_err(&pdev->dev, "no memory resource defined.\n");
@@ -161,6 +166,12 @@ static	int __devinit ti_tscadc_probe(struct platform_device *pdev)
 	ctrl |= CNTRLREG_TSCSSENB;
 	tscadc_writel(tscadc, REG_CTRL, ctrl);
 
+	/* TSC Cell */
+	cell = &tscadc->cells[TSC_CELL];
+	cell->name = "tsc";
+	cell->platform_data = tscadc;
+	cell->pdata_size = sizeof(*tscadc);
+
 	err = mfd_add_devices(&pdev->dev, pdev->id, tscadc->cells,
 			TSCADC_CELLS, NULL, 0, NULL);
 	if (err < 0)
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index b7232b157061..fc18b2ef753f 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -47,6 +47,7 @@
 #define STEPENB_MASK		(0x1FFFF << 0)
 #define STEPENB(val)		((val) << 0)
 #define STPENB_STEPENB		STEPENB(0x1FFFF)
+#define STPENB_STEPENB_TC	STEPENB(0x1FFF)
 
 /* IRQ enable */
 #define IRQENB_HW_PEN		BIT(0)
@@ -120,7 +121,11 @@
 #define ADC_CLK			3000000
 #define	MAX_CLK_DIV		7
 
-#define TSCADC_CELLS		0
+#define TSCADC_CELLS		1
+
+enum tscadc_cells {
+	TSC_CELL,
+};
 
 struct mfd_tscadc_board {
 	struct tsc_data *tsc_init;
@@ -132,6 +137,9 @@ struct ti_tscadc_dev {
 	void __iomem *tscadc_base;
 	int irq;
 	struct mfd_cell cells[TSCADC_CELLS];
+
+	/* tsc device */
+	struct titsc *tsc;
 };
 
 #endif
-- 
cgit v1.2.3-55-g7522


From 5e53a69b44e893227b046a7bc74db3cb40d7f39b Mon Sep 17 00:00:00 2001
From: Patil, Rachna
Date: Tue, 16 Oct 2012 12:55:45 +0530
Subject: IIO : ADC: tiadc: Add support of TI's ADC driver

This patch adds support for TI's ADC driver.
This is a multifunctional device.
Analog input lines are provided on which
voltage measurements can be carried out.
You can have upto 8 input lines.

Signed-off-by: Patil, Rachna <rachna@ti.com>
Acked-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/iio/adc/Kconfig                     |   7 +
 drivers/iio/adc/Makefile                    |   1 +
 drivers/iio/adc/ti_am335x_adc.c             | 260 ++++++++++++++++++++++++++++
 drivers/mfd/ti_am335x_tscadc.c              |  18 +-
 include/linux/mfd/ti_am335x_tscadc.h        |   9 +-
 include/linux/platform_data/ti_am335x_adc.h |  14 ++
 6 files changed, 307 insertions(+), 2 deletions(-)
 create mode 100644 drivers/iio/adc/ti_am335x_adc.c
 create mode 100644 include/linux/platform_data/ti_am335x_adc.h

(limited to 'include')

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 492758120338..1401ed1af39f 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -60,4 +60,11 @@ config LP8788_ADC
 	help
 	  Say yes here to build support for TI LP8788 ADC.
 
+config TI_AM335X_ADC
+	tristate "TI's ADC driver"
+	depends on MFD_TI_AM335X_TSCADC
+	help
+	  Say yes here to build support for Texas Instruments ADC
+	  driver which is also a MFD client.
+
 endmenu
diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile
index 900995d5e179..4410a90fc84b 100644
--- a/drivers/iio/adc/Makefile
+++ b/drivers/iio/adc/Makefile
@@ -8,3 +8,4 @@ obj-$(CONFIG_AD7476) += ad7476.o
 obj-$(CONFIG_AD7791) += ad7791.o
 obj-$(CONFIG_AT91_ADC) += at91_adc.o
 obj-$(CONFIG_LP8788_ADC) += lp8788_adc.o
+obj-$(CONFIG_TI_AM335X_ADC) += ti_am335x_adc.o
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
new file mode 100644
index 000000000000..02a43c87a8a3
--- /dev/null
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -0,0 +1,260 @@
+/*
+ * TI ADC MFD driver
+ *
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/iio/iio.h>
+
+#include <linux/mfd/ti_am335x_tscadc.h>
+#include <linux/platform_data/ti_am335x_adc.h>
+
+struct tiadc_device {
+	struct ti_tscadc_dev *mfd_tscadc;
+	int channels;
+};
+
+static unsigned int tiadc_readl(struct tiadc_device *adc, unsigned int reg)
+{
+	return readl(adc->mfd_tscadc->tscadc_base + reg);
+}
+
+static void tiadc_writel(struct tiadc_device *adc, unsigned int reg,
+					unsigned int val)
+{
+	writel(val, adc->mfd_tscadc->tscadc_base + reg);
+}
+
+static void tiadc_step_config(struct tiadc_device *adc_dev)
+{
+	unsigned int stepconfig;
+	int i, channels = 0, steps;
+
+	/*
+	 * There are 16 configurable steps and 8 analog input
+	 * lines available which are shared between Touchscreen and ADC.
+	 *
+	 * Steps backwards i.e. from 16 towards 0 are used by ADC
+	 * depending on number of input lines needed.
+	 * Channel would represent which analog input
+	 * needs to be given to ADC to digitalize data.
+	 */
+
+	steps = TOTAL_STEPS - adc_dev->channels;
+	channels = TOTAL_CHANNELS - adc_dev->channels;
+
+	stepconfig = STEPCONFIG_AVG_16 | STEPCONFIG_FIFO1;
+
+	for (i = (steps + 1); i <= TOTAL_STEPS; i++) {
+		tiadc_writel(adc_dev, REG_STEPCONFIG(i),
+				stepconfig | STEPCONFIG_INP(channels));
+		tiadc_writel(adc_dev, REG_STEPDELAY(i),
+				STEPCONFIG_OPENDLY);
+		channels++;
+	}
+	tiadc_writel(adc_dev, REG_SE, STPENB_STEPENB);
+}
+
+static int tiadc_channel_init(struct iio_dev *indio_dev, int channels)
+{
+	struct iio_chan_spec *chan_array;
+	int i;
+
+	indio_dev->num_channels = channels;
+	chan_array = kcalloc(indio_dev->num_channels,
+			sizeof(struct iio_chan_spec), GFP_KERNEL);
+
+	if (chan_array == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < (indio_dev->num_channels); i++) {
+		struct iio_chan_spec *chan = chan_array + i;
+		chan->type = IIO_VOLTAGE;
+		chan->indexed = 1;
+		chan->channel = i;
+		chan->info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT;
+	}
+
+	indio_dev->channels = chan_array;
+
+	return indio_dev->num_channels;
+}
+
+static void tiadc_channels_remove(struct iio_dev *indio_dev)
+{
+	kfree(indio_dev->channels);
+}
+
+static int tiadc_read_raw(struct iio_dev *indio_dev,
+		struct iio_chan_spec const *chan,
+		int *val, int *val2, long mask)
+{
+	struct tiadc_device *adc_dev = iio_priv(indio_dev);
+	int i;
+	unsigned int fifo1count, readx1;
+
+	/*
+	 * When the sub-system is first enabled,
+	 * the sequencer will always start with the
+	 * lowest step (1) and continue until step (16).
+	 * For ex: If we have enabled 4 ADC channels and
+	 * currently use only 1 out of them, the
+	 * sequencer still configures all the 4 steps,
+	 * leading to 3 unwanted data.
+	 * Hence we need to flush out this data.
+	 */
+
+	fifo1count = tiadc_readl(adc_dev, REG_FIFO1CNT);
+	for (i = 0; i < fifo1count; i++) {
+		readx1 = tiadc_readl(adc_dev, REG_FIFO1);
+		if (i == chan->channel)
+			*val = readx1 & 0xfff;
+	}
+	tiadc_writel(adc_dev, REG_SE, STPENB_STEPENB);
+
+	return IIO_VAL_INT;
+}
+
+static const struct iio_info tiadc_info = {
+	.read_raw = &tiadc_read_raw,
+};
+
+static int __devinit tiadc_probe(struct platform_device *pdev)
+{
+	struct iio_dev		*indio_dev;
+	struct tiadc_device	*adc_dev;
+	struct ti_tscadc_dev	*tscadc_dev = pdev->dev.platform_data;
+	struct mfd_tscadc_board	*pdata;
+	int			err;
+
+	pdata = tscadc_dev->dev->platform_data;
+	if (!pdata || !pdata->adc_init) {
+		dev_err(&pdev->dev, "Could not find platform data\n");
+		return -EINVAL;
+	}
+
+	indio_dev = iio_device_alloc(sizeof(struct tiadc_device));
+	if (indio_dev == NULL) {
+		dev_err(&pdev->dev, "failed to allocate iio device\n");
+		err = -ENOMEM;
+		goto err_ret;
+	}
+	adc_dev = iio_priv(indio_dev);
+
+	adc_dev->mfd_tscadc = tscadc_dev;
+	adc_dev->channels = pdata->adc_init->adc_channels;
+
+	indio_dev->dev.parent = &pdev->dev;
+	indio_dev->name = dev_name(&pdev->dev);
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->info = &tiadc_info;
+
+	tiadc_step_config(adc_dev);
+
+	err = tiadc_channel_init(indio_dev, adc_dev->channels);
+	if (err < 0)
+		goto err_free_device;
+
+	err = iio_device_register(indio_dev);
+	if (err)
+		goto err_free_channels;
+
+	platform_set_drvdata(pdev, indio_dev);
+
+	return 0;
+
+err_free_channels:
+	tiadc_channels_remove(indio_dev);
+err_free_device:
+	iio_device_free(indio_dev);
+err_ret:
+	return err;
+}
+
+static int __devexit tiadc_remove(struct platform_device *pdev)
+{
+	struct iio_dev *indio_dev = platform_get_drvdata(pdev);
+
+	iio_device_unregister(indio_dev);
+	tiadc_channels_remove(indio_dev);
+
+	iio_device_free(indio_dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int tiadc_suspend(struct device *dev)
+{
+	struct iio_dev *indio_dev = dev_get_drvdata(dev);
+	struct tiadc_device *adc_dev = iio_priv(indio_dev);
+	struct ti_tscadc_dev *tscadc_dev = dev->platform_data;
+	unsigned int idle;
+
+	if (!device_may_wakeup(tscadc_dev->dev)) {
+		idle = tiadc_readl(adc_dev, REG_CTRL);
+		idle &= ~(CNTRLREG_TSCSSENB);
+		tiadc_writel(adc_dev, REG_CTRL, (idle |
+				CNTRLREG_POWERDOWN));
+	}
+
+	return 0;
+}
+
+static int tiadc_resume(struct device *dev)
+{
+	struct iio_dev *indio_dev = dev_get_drvdata(dev);
+	struct tiadc_device *adc_dev = iio_priv(indio_dev);
+	unsigned int restore;
+
+	/* Make sure ADC is powered up */
+	restore = tiadc_readl(adc_dev, REG_CTRL);
+	restore &= ~(CNTRLREG_POWERDOWN);
+	tiadc_writel(adc_dev, REG_CTRL, restore);
+
+	tiadc_step_config(adc_dev);
+
+	return 0;
+}
+
+static const struct dev_pm_ops tiadc_pm_ops = {
+	.suspend = tiadc_suspend,
+	.resume = tiadc_resume,
+};
+#define TIADC_PM_OPS (&tiadc_pm_ops)
+#else
+#define TIADC_PM_OPS NULL
+#endif
+
+static struct platform_driver tiadc_driver = {
+	.driver = {
+		.name   = "tiadc",
+		.owner	= THIS_MODULE,
+		.pm	= TIADC_PM_OPS,
+	},
+	.probe	= tiadc_probe,
+	.remove	= __devexit_p(tiadc_remove),
+};
+
+module_platform_driver(tiadc_driver);
+
+MODULE_DESCRIPTION("TI ADC controller driver");
+MODULE_AUTHOR("Rachna Patil <rachna@ti.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index d812be4b61df..e947dd8bbcc3 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -25,6 +25,7 @@
 
 #include <linux/mfd/ti_am335x_tscadc.h>
 #include <linux/input/ti_am335x_tsc.h>
+#include <linux/platform_data/ti_am335x_adc.h>
 
 static unsigned int tscadc_readl(struct ti_tscadc_dev *tsadc, unsigned int reg)
 {
@@ -67,14 +68,23 @@ static	int __devinit ti_tscadc_probe(struct platform_device *pdev)
 	int			irq;
 	int			err, ctrl;
 	int			clk_value, clock_rate;
-	int			tsc_wires;
+	int			tsc_wires, adc_channels = 0, total_channels;
 
 	if (!pdata) {
 		dev_err(&pdev->dev, "Could not find platform data\n");
 		return -EINVAL;
 	}
 
+	if (pdata->adc_init)
+		adc_channels = pdata->adc_init->adc_channels;
+
 	tsc_wires = pdata->tsc_init->wires;
+	total_channels = tsc_wires + adc_channels;
+
+	if (total_channels > 8) {
+		dev_err(&pdev->dev, "Number of i/p channels more than 8\n");
+		return -EINVAL;
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
@@ -172,6 +182,12 @@ static	int __devinit ti_tscadc_probe(struct platform_device *pdev)
 	cell->platform_data = tscadc;
 	cell->pdata_size = sizeof(*tscadc);
 
+	/* ADC Cell */
+	cell = &tscadc->cells[ADC_CELL];
+	cell->name = "tiadc";
+	cell->platform_data = tscadc;
+	cell->pdata_size = sizeof(*tscadc);
+
 	err = mfd_add_devices(&pdev->dev, pdev->id, tscadc->cells,
 			TSCADC_CELLS, NULL, 0, NULL);
 	if (err < 0)
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index fc18b2ef753f..c79ad5d2f271 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -120,15 +120,19 @@
 
 #define ADC_CLK			3000000
 #define	MAX_CLK_DIV		7
+#define TOTAL_STEPS		16
+#define TOTAL_CHANNELS		8
 
-#define TSCADC_CELLS		1
+#define TSCADC_CELLS		2
 
 enum tscadc_cells {
 	TSC_CELL,
+	ADC_CELL,
 };
 
 struct mfd_tscadc_board {
 	struct tsc_data *tsc_init;
+	struct adc_data *adc_init;
 };
 
 struct ti_tscadc_dev {
@@ -140,6 +144,9 @@ struct ti_tscadc_dev {
 
 	/* tsc device */
 	struct titsc *tsc;
+
+	/* adc device */
+	struct adc_device *adc;
 };
 
 #endif
diff --git a/include/linux/platform_data/ti_am335x_adc.h b/include/linux/platform_data/ti_am335x_adc.h
new file mode 100644
index 000000000000..e41d5834cb84
--- /dev/null
+++ b/include/linux/platform_data/ti_am335x_adc.h
@@ -0,0 +1,14 @@
+#ifndef __LINUX_TI_AM335X_ADC_H
+#define __LINUX_TI_AM335X_ADC_H
+
+/**
+ * struct adc_data	ADC Input information
+ * @adc_channels:	Number of analog inputs
+ *			available for ADC.
+ */
+
+struct adc_data {
+	unsigned int adc_channels;
+};
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 79c4412298771b8996302806abc8a11e760da9b3 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas
Date: Tue, 30 Oct 2012 15:24:06 +0900
Subject: ACPI: Pass segment/bus to _PRT add/del so they don't depend on
 pci_bus

This effectively reverts 859a3f86ca8 ("ACPI: simplify
acpi_pci_irq_add_prt() API") and d9efae3688a ("ACPI: simplify
acpi_pci_irq_del_prt() API").

The reason is to disentangle these routines from the struct pci_bus.
We want to be able to add the _PRT before the struct pci_bus
exists, and delete the _PRT after we've removed the pci_bus.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Taku Izumi <izumi.taku@jp.fujitsu.com>---
 drivers/acpi/pci_bind.c     | 10 +++++-----
 drivers/acpi/pci_irq.c      | 17 ++++++++---------
 drivers/acpi/pci_root.c     |  5 +++--
 include/acpi/acpi_drivers.h |  4 ++--
 4 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/pci_bind.c b/drivers/acpi/pci_bind.c
index 2ef04098cc1d..911144b22c89 100644
--- a/drivers/acpi/pci_bind.c
+++ b/drivers/acpi/pci_bind.c
@@ -49,7 +49,7 @@ static int acpi_pci_unbind(struct acpi_device *device)
 	if (!dev->subordinate)
 		goto out;
 
-	acpi_pci_irq_del_prt(dev->subordinate);
+	acpi_pci_irq_del_prt(pci_domain_nr(dev->bus), dev->subordinate->number);
 
 	device->ops.bind = NULL;
 	device->ops.unbind = NULL;
@@ -63,7 +63,7 @@ static int acpi_pci_bind(struct acpi_device *device)
 {
 	acpi_status status;
 	acpi_handle handle;
-	struct pci_bus *bus;
+	unsigned char bus;
 	struct pci_dev *dev;
 
 	dev = acpi_get_pci_dev(device->handle);
@@ -100,11 +100,11 @@ static int acpi_pci_bind(struct acpi_device *device)
 		goto out;
 
 	if (dev->subordinate)
-		bus = dev->subordinate;
+		bus = dev->subordinate->number;
 	else
-		bus = dev->bus;
+		bus = dev->bus->number;
 
-	acpi_pci_irq_add_prt(device->handle, bus);
+	acpi_pci_irq_add_prt(device->handle, pci_domain_nr(dev->bus), bus);
 
 out:
 	pci_dev_put(dev);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 0eefa12e648c..8835cc38aa30 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -184,7 +184,7 @@ static void do_prt_fixups(struct acpi_prt_entry *entry,
 	}
 }
 
-static int acpi_pci_irq_add_entry(acpi_handle handle, struct pci_bus *bus,
+static int acpi_pci_irq_add_entry(acpi_handle handle, int segment, int bus,
 				  struct acpi_pci_routing_table *prt)
 {
 	struct acpi_prt_entry *entry;
@@ -198,8 +198,8 @@ static int acpi_pci_irq_add_entry(acpi_handle handle, struct pci_bus *bus,
 	 * 1=INTA, 2=INTB.  We use the PCI encoding throughout, so convert
 	 * it here.
 	 */
-	entry->id.segment = pci_domain_nr(bus);
-	entry->id.bus = bus->number;
+	entry->id.segment = segment;
+	entry->id.bus = bus;
 	entry->id.device = (prt->address >> 16) & 0xFFFF;
 	entry->pin = prt->pin + 1;
 
@@ -244,7 +244,7 @@ static int acpi_pci_irq_add_entry(acpi_handle handle, struct pci_bus *bus,
 	return 0;
 }
 
-int acpi_pci_irq_add_prt(acpi_handle handle, struct pci_bus *bus)
+int acpi_pci_irq_add_prt(acpi_handle handle, int segment, int bus)
 {
 	acpi_status status;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -273,7 +273,7 @@ int acpi_pci_irq_add_prt(acpi_handle handle, struct pci_bus *bus)
 
 	entry = buffer.pointer;
 	while (entry && (entry->length > 0)) {
-		acpi_pci_irq_add_entry(handle, bus, entry);
+		acpi_pci_irq_add_entry(handle, segment, bus, entry);
 		entry = (struct acpi_pci_routing_table *)
 		    ((unsigned long)entry + entry->length);
 	}
@@ -282,17 +282,16 @@ int acpi_pci_irq_add_prt(acpi_handle handle, struct pci_bus *bus)
 	return 0;
 }
 
-void acpi_pci_irq_del_prt(struct pci_bus *bus)
+void acpi_pci_irq_del_prt(int segment, int bus)
 {
 	struct acpi_prt_entry *entry, *tmp;
 
 	printk(KERN_DEBUG
 	       "ACPI: Delete PCI Interrupt Routing Table for %04x:%02x\n",
-	       pci_domain_nr(bus), bus->number);
+	       segment, bus);
 	spin_lock(&acpi_prt_lock);
 	list_for_each_entry_safe(entry, tmp, &acpi_prt_list, list) {
-		if (pci_domain_nr(bus) == entry->id.segment
-			&& bus->number == entry->id.bus) {
+		if (segment == entry->id.segment && bus == entry->id.bus) {
 			list_del(&entry->list);
 			kfree(entry);
 		}
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 012f40d1d75d..db31edaab9ce 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -554,7 +554,8 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 	 */
 	status = acpi_get_handle(device->handle, METHOD_NAME__PRT, &handle);
 	if (ACPI_SUCCESS(status))
-		result = acpi_pci_irq_add_prt(device->handle, root->bus);
+		result = acpi_pci_irq_add_prt(device->handle, root->segment,
+					      root->secondary.start);
 
 	/*
 	 * Scan and bind all _ADR-Based Devices
@@ -682,7 +683,7 @@ static int acpi_pci_root_remove(struct acpi_device *device, int type)
 
 	status = acpi_get_handle(device->handle, METHOD_NAME__PRT, &handle);
 	if (ACPI_SUCCESS(status))
-		acpi_pci_irq_del_prt(root->bus);
+		acpi_pci_irq_del_prt(root->segment, root->secondary.start);
 
 	pci_remove_root_bus(root->bus);
 
diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h
index bb145e4b935e..8b1d7a6a9695 100644
--- a/include/acpi/acpi_drivers.h
+++ b/include/acpi/acpi_drivers.h
@@ -92,8 +92,8 @@ int acpi_pci_link_free_irq(acpi_handle handle);
 
 /* ACPI PCI Interrupt Routing (pci_irq.c) */
 
-int acpi_pci_irq_add_prt(acpi_handle handle, struct pci_bus *bus);
-void acpi_pci_irq_del_prt(struct pci_bus *bus);
+int acpi_pci_irq_add_prt(acpi_handle handle, int segment, int bus);
+void acpi_pci_irq_del_prt(int segment, int bus);
 
 /* ACPI PCI Device Binding (pci_bind.c) */
 
-- 
cgit v1.2.3-55-g7522


From ab6f6d85210c4d0265cf48e9958c04e08595055a Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto
Date: Mon, 5 Nov 2012 18:30:38 -0800
Subject: ASoC: fsi: add master clock control functions

Current FSI driver required set_rate() platform callback function
to set audio clock if it was master mode,
because it seemed that CPG/FSI-DIV clocks calculation depend on
platform/board/cpu.
But it was calculable regardless of platform.
This patch supports audio clock calculation method,
but the sampling rate under 32kHz is not supported at this point.
Old type set_rate() is still supported now,
but it will be deleted on next version

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/sound/sh_fsi.h |   6 +
 sound/soc/sh/fsi.c     | 378 ++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 378 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/sh_fsi.h b/include/sound/sh_fsi.h
index 906010344dd7..27ee1dcc3e2e 100644
--- a/include/sound/sh_fsi.h
+++ b/include/sound/sh_fsi.h
@@ -26,6 +26,7 @@
  * A:  inversion
  * B:  format mode
  * C:  chip specific
+ * D:  clock selecter if master mode
  */
 
 /* A: clock inversion */
@@ -44,6 +45,11 @@
 #define SH_FSI_OPTION_MASK	0x00000F00
 #define SH_FSI_ENABLE_STREAM_MODE	(1 << 8) /* for 16bit data */
 
+/* D:  clock selecter if master mode */
+#define SH_FSI_CLK_MASK		0x0000F000
+#define SH_FSI_CLK_EXTERNAL	(1 << 12)
+#define SH_FSI_CLK_CPG		(2 << 12) /* FSIxCK + FSI-DIV */
+
 /*
  * set_rate return value
  *
diff --git a/sound/soc/sh/fsi.c b/sound/soc/sh/fsi.c
index ef257bcb5341..bdaca356aaad 100644
--- a/sound/soc/sh/fsi.c
+++ b/sound/soc/sh/fsi.c
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <sound/soc.h>
+#include <sound/pcm_params.h>
 #include <sound/sh_fsi.h>
 
 /* PortA/PortB register */
@@ -187,6 +188,14 @@ typedef int (*set_rate_func)(struct device *dev, int rate, int enable);
  *		--> go to codecs
  */
 
+/*
+ *	FSI clock
+ *
+ * FSIxCLK [CPG] (ick) ------->	|
+ *				|-> FSI_DIV (div)-> FSI2
+ * FSIxCK [external] (xck) --->	|
+ */
+
 /*
  *		struct
  */
@@ -227,6 +236,20 @@ struct fsi_stream {
 	dma_addr_t		dma;
 };
 
+struct fsi_clk {
+	/* see [FSI clock] */
+	struct clk *own;
+	struct clk *xck;
+	struct clk *ick;
+	struct clk *div;
+	int (*set_rate)(struct device *dev,
+			struct fsi_priv *fsi,
+			unsigned long rate);
+
+	unsigned long rate;
+	unsigned int count;
+};
+
 struct fsi_priv {
 	void __iomem *base;
 	struct fsi_master *master;
@@ -235,6 +258,8 @@ struct fsi_priv {
 	struct fsi_stream playback;
 	struct fsi_stream capture;
 
+	struct fsi_clk clock;
+
 	u32 fmt;
 
 	int chan_num:16;
@@ -716,14 +741,335 @@ static void fsi_spdif_clk_ctrl(struct fsi_priv *fsi, int enable)
 /*
  *		clock function
  */
+static int fsi_clk_init(struct device *dev,
+			struct fsi_priv *fsi,
+			int xck,
+			int ick,
+			int div,
+			int (*set_rate)(struct device *dev,
+					struct fsi_priv *fsi,
+					unsigned long rate))
+{
+	struct fsi_clk *clock = &fsi->clock;
+	int is_porta = fsi_is_port_a(fsi);
+
+	clock->xck	= NULL;
+	clock->ick	= NULL;
+	clock->div	= NULL;
+	clock->rate	= 0;
+	clock->count	= 0;
+	clock->set_rate	= set_rate;
+
+	clock->own = devm_clk_get(dev, NULL);
+	if (IS_ERR(clock->own))
+		return -EINVAL;
+
+	/* external clock */
+	if (xck) {
+		clock->xck = devm_clk_get(dev, is_porta ? "xcka" : "xckb");
+		if (IS_ERR(clock->xck)) {
+			dev_err(dev, "can't get xck clock\n");
+			return -EINVAL;
+		}
+		if (clock->xck == clock->own) {
+			dev_err(dev, "cpu doesn't support xck clock\n");
+			return -EINVAL;
+		}
+	}
+
+	/* FSIACLK/FSIBCLK */
+	if (ick) {
+		clock->ick = devm_clk_get(dev,  is_porta ? "icka" : "ickb");
+		if (IS_ERR(clock->ick)) {
+			dev_err(dev, "can't get ick clock\n");
+			return -EINVAL;
+		}
+		if (clock->ick == clock->own) {
+			dev_err(dev, "cpu doesn't support ick clock\n");
+			return -EINVAL;
+		}
+	}
+
+	/* FSI-DIV */
+	if (div) {
+		clock->div = devm_clk_get(dev,  is_porta ? "diva" : "divb");
+		if (IS_ERR(clock->div)) {
+			dev_err(dev, "can't get div clock\n");
+			return -EINVAL;
+		}
+		if (clock->div == clock->own) {
+			dev_err(dev, "cpu doens't support div clock\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+#define fsi_clk_invalid(fsi) fsi_clk_valid(fsi, 0)
+static void fsi_clk_valid(struct fsi_priv *fsi, unsigned long rate)
+{
+	fsi->clock.rate = rate;
+}
+
+static int fsi_clk_is_valid(struct fsi_priv *fsi)
+{
+	return	fsi->clock.set_rate &&
+		fsi->clock.rate;
+}
+
+static int fsi_clk_enable(struct device *dev,
+			  struct fsi_priv *fsi,
+			  unsigned long rate)
+{
+	struct fsi_clk *clock = &fsi->clock;
+	int ret = -EINVAL;
+
+	if (!fsi_clk_is_valid(fsi))
+		return ret;
+
+	if (0 == clock->count) {
+		ret = clock->set_rate(dev, fsi, rate);
+		if (ret < 0) {
+			fsi_clk_invalid(fsi);
+			return ret;
+		}
+
+		if (clock->xck)
+			clk_enable(clock->xck);
+		if (clock->ick)
+			clk_enable(clock->ick);
+		if (clock->div)
+			clk_enable(clock->div);
+
+		clock->count++;
+	}
+
+	return ret;
+}
+
+static int fsi_clk_disable(struct device *dev,
+			    struct fsi_priv *fsi)
+{
+	struct fsi_clk *clock = &fsi->clock;
+
+	if (!fsi_clk_is_valid(fsi))
+		return -EINVAL;
+
+	if (1 == clock->count--) {
+		if (clock->xck)
+			clk_disable(clock->xck);
+		if (clock->ick)
+			clk_disable(clock->ick);
+		if (clock->div)
+			clk_disable(clock->div);
+	}
+
+	return 0;
+}
+
+static int fsi_clk_set_ackbpf(struct device *dev,
+			      struct fsi_priv *fsi,
+			      int ackmd, int bpfmd)
+{
+	u32 data = 0;
+
+	/* check ackmd/bpfmd relationship */
+	if (bpfmd > ackmd) {
+		dev_err(dev, "unsupported rate (%d/%d)\n", ackmd, bpfmd);
+		return -EINVAL;
+	}
+
+	/*  ACKMD */
+	switch (ackmd) {
+	case 512:
+		data |= (0x0 << 12);
+		break;
+	case 256:
+		data |= (0x1 << 12);
+		break;
+	case 128:
+		data |= (0x2 << 12);
+		break;
+	case 64:
+		data |= (0x3 << 12);
+		break;
+	case 32:
+		data |= (0x4 << 12);
+		break;
+	default:
+		dev_err(dev, "unsupported ackmd (%d)\n", ackmd);
+		return -EINVAL;
+	}
+
+	/* BPFMD */
+	switch (bpfmd) {
+	case 32:
+		data |= (0x0 << 8);
+		break;
+	case 64:
+		data |= (0x1 << 8);
+		break;
+	case 128:
+		data |= (0x2 << 8);
+		break;
+	case 256:
+		data |= (0x3 << 8);
+		break;
+	case 512:
+		data |= (0x4 << 8);
+		break;
+	case 16:
+		data |= (0x7 << 8);
+		break;
+	default:
+		dev_err(dev, "unsupported bpfmd (%d)\n", bpfmd);
+		return -EINVAL;
+	}
+
+	dev_dbg(dev, "ACKMD/BPFMD = %d/%d\n", ackmd, bpfmd);
+
+	fsi_reg_mask_set(fsi, CKG1, (ACKMD_MASK | BPFMD_MASK) , data);
+	udelay(10);
+
+	return 0;
+}
+
+static int fsi_clk_set_rate_external(struct device *dev,
+				     struct fsi_priv *fsi,
+				     unsigned long rate)
+{
+	struct clk *xck = fsi->clock.xck;
+	struct clk *ick = fsi->clock.ick;
+	unsigned long xrate;
+	int ackmd, bpfmd;
+	int ret = 0;
+
+	/* check clock rate */
+	xrate = clk_get_rate(xck);
+	if (xrate % rate) {
+		dev_err(dev, "unsupported clock rate\n");
+		return -EINVAL;
+	}
+
+	clk_set_parent(ick, xck);
+	clk_set_rate(ick, xrate);
+
+	bpfmd = fsi->chan_num * 32;
+	ackmd = xrate / rate;
+
+	dev_dbg(dev, "external/rate = %ld/%ld\n", xrate, rate);
+
+	ret = fsi_clk_set_ackbpf(dev, fsi, ackmd, bpfmd);
+	if (ret < 0)
+		dev_err(dev, "%s failed", __func__);
+
+	return ret;
+}
+
+static int fsi_clk_set_rate_cpg(struct device *dev,
+				struct fsi_priv *fsi,
+				unsigned long rate)
+{
+	struct clk *ick = fsi->clock.ick;
+	struct clk *div = fsi->clock.div;
+	unsigned long target = 0; /* 12288000 or 11289600 */
+	unsigned long actual, cout;
+	unsigned long diff, min;
+	unsigned long best_cout, best_act;
+	int adj;
+	int ackmd, bpfmd;
+	int ret = -EINVAL;
+
+	if (!(12288000 % rate))
+		target = 12288000;
+	if (!(11289600 % rate))
+		target = 11289600;
+	if (!target) {
+		dev_err(dev, "unsupported rate\n");
+		return ret;
+	}
+
+	bpfmd = fsi->chan_num * 32;
+	ackmd = target / rate;
+	ret = fsi_clk_set_ackbpf(dev, fsi, ackmd, bpfmd);
+	if (ret < 0) {
+		dev_err(dev, "%s failed", __func__);
+		return ret;
+	}
+
+	/*
+	 * The clock flow is
+	 *
+	 * [CPG] = cout => [FSI_DIV] = audio => [FSI] => [codec]
+	 *
+	 * But, it needs to find best match of CPG and FSI_DIV
+	 * combination, since it is difficult to generate correct
+	 * frequency of audio clock from ick clock only.
+	 * Because ick is created from its parent clock.
+	 *
+	 * target	= rate x [512/256/128/64]fs
+	 * cout		= round(target x adjustment)
+	 * actual	= cout / adjustment (by FSI-DIV) ~= target
+	 * audio	= actual
+	 */
+	min = ~0;
+	best_cout = 0;
+	best_act = 0;
+	for (adj = 1; adj < 0xffff; adj++) {
+
+		cout = target * adj;
+		if (cout > 100000000) /* max clock = 100MHz */
+			break;
+
+		/* cout/actual audio clock */
+		cout	= clk_round_rate(ick, cout);
+		actual	= cout / adj;
+
+		/* find best frequency */
+		diff = abs(actual - target);
+		if (diff < min) {
+			min		= diff;
+			best_cout	= cout;
+			best_act	= actual;
+		}
+	}
+
+	ret = clk_set_rate(ick, best_cout);
+	if (ret < 0) {
+		dev_err(dev, "ick clock failed\n");
+		return -EIO;
+	}
+
+	ret = clk_set_rate(div, clk_round_rate(div, best_act));
+	if (ret < 0) {
+		dev_err(dev, "div clock failed\n");
+		return -EIO;
+	}
+
+	dev_dbg(dev, "ick/div = %ld/%ld\n",
+		clk_get_rate(ick), clk_get_rate(div));
+
+	return ret;
+}
+
 static int fsi_set_master_clk(struct device *dev, struct fsi_priv *fsi,
 			      long rate, int enable)
 {
 	set_rate_func set_rate = fsi_get_info_set_rate(fsi);
 	int ret;
 
-	if (!set_rate)
-		return 0;
+	/*
+	 * CAUTION
+	 *
+	 * set_rate will be deleted
+	 */
+	if (!set_rate) {
+		if (enable)
+			return fsi_clk_enable(dev, fsi, rate);
+		else
+			return fsi_clk_disable(dev, fsi);
+	}
 
 	ret = set_rate(dev, rate, enable);
 	if (ret < 0) /* error */
@@ -1355,6 +1701,7 @@ static int fsi_dai_startup(struct snd_pcm_substream *substream,
 {
 	struct fsi_priv *fsi = fsi_get_priv(substream);
 
+	fsi_clk_invalid(fsi);
 	fsi->rate = 0;
 
 	return 0;
@@ -1365,6 +1712,7 @@ static void fsi_dai_shutdown(struct snd_pcm_substream *substream,
 {
 	struct fsi_priv *fsi = fsi_get_priv(substream);
 
+	fsi_clk_invalid(fsi);
 	fsi->rate = 0;
 }
 
@@ -1446,9 +1794,25 @@ static int fsi_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		return -EINVAL;
 	}
 
-	if (fsi_is_clk_master(fsi) && !set_rate) {
-		dev_err(dai->dev, "platform doesn't have set_rate\n");
-		return -EINVAL;
+	if (fsi_is_clk_master(fsi)) {
+		/*
+		 * CAUTION
+		 *
+		 * set_rate will be deleted
+		 */
+		if (set_rate)
+			dev_warn(dai->dev, "set_rate will be removed soon\n");
+
+		switch (flags & SH_FSI_CLK_MASK) {
+		case SH_FSI_CLK_EXTERNAL:
+			fsi_clk_init(dai->dev, fsi, 1, 1, 0,
+				     fsi_clk_set_rate_external);
+			break;
+		case SH_FSI_CLK_CPG:
+			fsi_clk_init(dai->dev, fsi, 0, 1, 1,
+				     fsi_clk_set_rate_cpg);
+			break;
+		}
 	}
 
 	/* set format */
@@ -1472,8 +1836,10 @@ static int fsi_dai_hw_params(struct snd_pcm_substream *substream,
 {
 	struct fsi_priv *fsi = fsi_get_priv(substream);
 
-	if (fsi_is_clk_master(fsi))
+	if (fsi_is_clk_master(fsi)) {
 		fsi->rate = params_rate(params);
+		fsi_clk_valid(fsi, fsi->rate);
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3-55-g7522


From 636036d29a20154b897571e1d5949faac98bfb7c Mon Sep 17 00:00:00 2001
From: Bo Shen
Date: Tue, 6 Nov 2012 13:57:51 +0800
Subject: ARM: at91: atmel-ssc: add platform device id table

Add platform device id to check whether the SSC controller support
pdc or dam for data transfer

If match "at91rm9200_ssc", which support pdc for data transfer
If match "at91sam9g45_ssc", which support dma for data transfer

Signed-off-by: Bo Shen <voice.shen@atmel.com>
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 arch/arm/mach-at91/at91rm9200.c          |  6 +++---
 arch/arm/mach-at91/at91rm9200_devices.c  |  6 +++---
 arch/arm/mach-at91/at91sam9260.c         |  2 +-
 arch/arm/mach-at91/at91sam9260_devices.c |  2 +-
 arch/arm/mach-at91/at91sam9261.c         |  6 +++---
 arch/arm/mach-at91/at91sam9261_devices.c |  6 +++---
 arch/arm/mach-at91/at91sam9263.c         |  4 ++--
 arch/arm/mach-at91/at91sam9263_devices.c |  4 ++--
 arch/arm/mach-at91/at91sam9g45.c         |  4 ++--
 arch/arm/mach-at91/at91sam9g45_devices.c |  4 ++--
 arch/arm/mach-at91/at91sam9rl.c          |  4 ++--
 arch/arm/mach-at91/at91sam9rl_devices.c  |  4 ++--
 drivers/misc/atmel-ssc.c                 | 23 +++++++++++++++++++++++
 include/linux/atmel-ssc.h                |  5 +++++
 14 files changed, 54 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c
index 5269825194a8..400d1a34683c 100644
--- a/arch/arm/mach-at91/at91rm9200.c
+++ b/arch/arm/mach-at91/at91rm9200.c
@@ -184,9 +184,9 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.1", &tc3_clk),
 	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.1", &tc4_clk),
 	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.1", &tc5_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.2", &ssc2_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.1", &ssc1_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.2", &ssc2_clk),
 	CLKDEV_CON_DEV_ID(NULL, "i2c-at91rm9200.0", &twi_clk),
 	/* fake hclk clock */
 	CLKDEV_CON_DEV_ID("hclk", "at91_ohci", &ohci_clk),
diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c
index 1e122bcd7845..f40925a552a1 100644
--- a/arch/arm/mach-at91/at91rm9200_devices.c
+++ b/arch/arm/mach-at91/at91rm9200_devices.c
@@ -752,7 +752,7 @@ static struct resource ssc0_resources[] = {
 };
 
 static struct platform_device at91rm9200_ssc0_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 0,
 	.dev	= {
 		.dma_mask		= &ssc0_dmamask,
@@ -794,7 +794,7 @@ static struct resource ssc1_resources[] = {
 };
 
 static struct platform_device at91rm9200_ssc1_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 1,
 	.dev	= {
 		.dma_mask		= &ssc1_dmamask,
@@ -836,7 +836,7 @@ static struct resource ssc2_resources[] = {
 };
 
 static struct platform_device at91rm9200_ssc2_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 2,
 	.dev	= {
 		.dma_mask		= &ssc2_dmamask,
diff --git a/arch/arm/mach-at91/at91sam9260.c b/arch/arm/mach-at91/at91sam9260.c
index f8202615f4a8..d14ab6aea250 100644
--- a/arch/arm/mach-at91/at91sam9260.c
+++ b/arch/arm/mach-at91/at91sam9260.c
@@ -210,7 +210,7 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.1", &tc3_clk),
 	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.1", &tc4_clk),
 	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.1", &tc5_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.0", &ssc_clk),
 	CLKDEV_CON_DEV_ID(NULL, "i2c-at91sam9260.0", &twi_clk),
 	CLKDEV_CON_DEV_ID(NULL, "i2c-at91sam9g20.0", &twi_clk),
 	/* more usart lookup table for DT entries */
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 46edfaf275f7..df7bebf07f10 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -742,7 +742,7 @@ static struct resource ssc_resources[] = {
 };
 
 static struct platform_device at91sam9260_ssc_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 0,
 	.dev	= {
 		.dma_mask		= &ssc_dmamask,
diff --git a/arch/arm/mach-at91/at91sam9261.c b/arch/arm/mach-at91/at91sam9261.c
index 04295c04b3e0..c7b605796dd4 100644
--- a/arch/arm/mach-at91/at91sam9261.c
+++ b/arch/arm/mach-at91/at91sam9261.c
@@ -174,9 +174,9 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
 	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
 	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.2", &ssc2_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.1", &ssc1_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.2", &ssc2_clk),
 	CLKDEV_CON_DEV_ID("hclk", "at91_ohci", &hck0),
 	CLKDEV_CON_DEV_ID(NULL, "i2c-at91sam9261.0", &twi_clk),
 	CLKDEV_CON_DEV_ID(NULL, "i2c-at91sam9g10.0", &twi_clk),
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index b9487696b7be..d8afd2130b79 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -706,7 +706,7 @@ static struct resource ssc0_resources[] = {
 };
 
 static struct platform_device at91sam9261_ssc0_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 0,
 	.dev	= {
 		.dma_mask		= &ssc0_dmamask,
@@ -748,7 +748,7 @@ static struct resource ssc1_resources[] = {
 };
 
 static struct platform_device at91sam9261_ssc1_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 1,
 	.dev	= {
 		.dma_mask		= &ssc1_dmamask,
@@ -790,7 +790,7 @@ static struct resource ssc2_resources[] = {
 };
 
 static struct platform_device at91sam9261_ssc2_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 2,
 	.dev	= {
 		.dma_mask		= &ssc2_dmamask,
diff --git a/arch/arm/mach-at91/at91sam9263.c b/arch/arm/mach-at91/at91sam9263.c
index d6f9c23927c4..b87be18f08ae 100644
--- a/arch/arm/mach-at91/at91sam9263.c
+++ b/arch/arm/mach-at91/at91sam9263.c
@@ -186,8 +186,8 @@ static struct clk *periph_clocks[] __initdata = {
 static struct clk_lookup periph_clocks_lookups[] = {
 	/* One additional fake clock for macb_hclk */
 	CLKDEV_CON_ID("hclk", &macb_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.1", &ssc1_clk),
 	CLKDEV_CON_DEV_ID("mci_clk", "atmel_mci.0", &mmc0_clk),
 	CLKDEV_CON_DEV_ID("mci_clk", "atmel_mci.1", &mmc1_clk),
 	CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk),
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index cb85da2eccea..025c9704bfe6 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -1199,7 +1199,7 @@ static struct resource ssc0_resources[] = {
 };
 
 static struct platform_device at91sam9263_ssc0_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 0,
 	.dev	= {
 		.dma_mask		= &ssc0_dmamask,
@@ -1241,7 +1241,7 @@ static struct resource ssc1_resources[] = {
 };
 
 static struct platform_device at91sam9263_ssc1_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 1,
 	.dev	= {
 		.dma_mask		= &ssc1_dmamask,
diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c
index 84af1b506d92..f4f96a61e4b8 100644
--- a/arch/arm/mach-at91/at91sam9g45.c
+++ b/arch/arm/mach-at91/at91sam9g45.c
@@ -239,8 +239,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.1", &tcb0_clk),
 	CLKDEV_CON_DEV_ID(NULL, "i2c-at91sam9g10.0", &twi0_clk),
 	CLKDEV_CON_DEV_ID(NULL, "i2c-at91sam9g10.1", &twi1_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91sam9g45_ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91sam9g45_ssc.1", &ssc1_clk),
 	CLKDEV_CON_DEV_ID(NULL, "atmel-trng", &trng_clk),
 	CLKDEV_CON_DEV_ID(NULL, "atmel_sha", &aestdessha_clk),
 	CLKDEV_CON_DEV_ID(NULL, "atmel_tdes", &aestdessha_clk),
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index b1596072dcc2..27e3bf64a8bc 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -1459,7 +1459,7 @@ static struct resource ssc0_resources[] = {
 };
 
 static struct platform_device at91sam9g45_ssc0_device = {
-	.name	= "ssc",
+	.name	= "at91sam9g45_ssc",
 	.id	= 0,
 	.dev	= {
 		.dma_mask		= &ssc0_dmamask,
@@ -1501,7 +1501,7 @@ static struct resource ssc1_resources[] = {
 };
 
 static struct platform_device at91sam9g45_ssc1_device = {
-	.name	= "ssc",
+	.name	= "at91sam9g45_ssc",
 	.id	= 1,
 	.dev	= {
 		.dma_mask		= &ssc1_dmamask,
diff --git a/arch/arm/mach-at91/at91sam9rl.c b/arch/arm/mach-at91/at91sam9rl.c
index 72e908412222..4110b5480d49 100644
--- a/arch/arm/mach-at91/at91sam9rl.c
+++ b/arch/arm/mach-at91/at91sam9rl.c
@@ -184,8 +184,8 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
 	CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
 	CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
-	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.0", &ssc0_clk),
+	CLKDEV_CON_DEV_ID("pclk", "at91rm9200_ssc.1", &ssc1_clk),
 	CLKDEV_CON_DEV_ID(NULL, "i2c-at91sam9g20.0", &twi0_clk),
 	CLKDEV_CON_DEV_ID(NULL, "i2c-at91sam9g20.1", &twi1_clk),
 	CLKDEV_CON_ID("pioA", &pioA_clk),
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index 5047bdc92adf..b656110e8afe 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -832,7 +832,7 @@ static struct resource ssc0_resources[] = {
 };
 
 static struct platform_device at91sam9rl_ssc0_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 0,
 	.dev	= {
 		.dma_mask		= &ssc0_dmamask,
@@ -874,7 +874,7 @@ static struct resource ssc1_resources[] = {
 };
 
 static struct platform_device at91sam9rl_ssc1_device = {
-	.name	= "ssc",
+	.name	= "at91rm9200_ssc",
 	.id	= 1,
 	.dev	= {
 		.dma_mask		= &ssc1_dmamask,
diff --git a/drivers/misc/atmel-ssc.c b/drivers/misc/atmel-ssc.c
index ac00f83ea86b..f40abd8a6695 100644
--- a/drivers/misc/atmel-ssc.c
+++ b/drivers/misc/atmel-ssc.c
@@ -68,6 +68,26 @@ void ssc_free(struct ssc_device *ssc)
 }
 EXPORT_SYMBOL(ssc_free);
 
+static struct atmel_ssc_platform_data at91rm9200_config = {
+	.use_dma = 0,
+};
+
+static struct atmel_ssc_platform_data at91sam9g45_config = {
+	.use_dma = 1,
+};
+
+static const struct platform_device_id atmel_ssc_devtypes[] = {
+	{
+		.name = "at91rm9200_ssc",
+		.driver_data = (unsigned long) &at91rm9200_config,
+	}, {
+		.name = "at91sam9g45_ssc",
+		.driver_data = (unsigned long) &at91sam9g45_config,
+	}, {
+		/* sentinel */
+	}
+};
+
 static int ssc_probe(struct platform_device *pdev)
 {
 	struct resource *regs;
@@ -80,6 +100,8 @@ static int ssc_probe(struct platform_device *pdev)
 	}
 
 	ssc->pdev = pdev;
+	ssc->pdata = (struct atmel_ssc_platform_data *)
+			platform_get_device_id(pdev)->driver_data;
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!regs) {
@@ -139,6 +161,7 @@ static struct platform_driver ssc_driver = {
 		.name		= "ssc",
 		.owner		= THIS_MODULE,
 	},
+	.id_table	= atmel_ssc_devtypes,
 	.probe		= ssc_probe,
 	.remove		= __devexit_p(ssc_remove),
 };
diff --git a/include/linux/atmel-ssc.h b/include/linux/atmel-ssc.h
index 4eb31752e2b7..1ca0e3292bc9 100644
--- a/include/linux/atmel-ssc.h
+++ b/include/linux/atmel-ssc.h
@@ -5,10 +5,15 @@
 #include <linux/list.h>
 #include <linux/io.h>
 
+struct atmel_ssc_platform_data {
+	int			use_dma;
+};
+
 struct ssc_device {
 	struct list_head	list;
 	void __iomem		*regs;
 	struct platform_device	*pdev;
+	struct atmel_ssc_platform_data *pdata;
 	struct clk		*clk;
 	int			user;
 	int			irq;
-- 
cgit v1.2.3-55-g7522


From 0ee453552f0b1ea87f6f50a077b0ed9d9ac7d6ac Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Mon, 29 Oct 2012 19:48:40 +0100
Subject: wireless: add utility function to get P2P attribute

Parsing the P2P attributes can be tricky as their
contents can be split across multiple (vendor) IEs.
Thus, it's not possible to parse them like IEs (by
returning a pointer to the data.) Instead, provide
a function that copies the attribute data into a
caller-provided buffer and returns the size needed
(useful in case the buffer was too small.)

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 19 ++++++++++
 net/wireless/util.c    | 99 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 118 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 10c9fc68d1af..81d725038f97 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3617,6 +3617,25 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate);
  */
 void cfg80211_unregister_wdev(struct wireless_dev *wdev);
 
+/**
+ * cfg80211_get_p2p_attr - find and copy a P2P attribute from IE buffer
+ * @ies: the input IE buffer
+ * @len: the input length
+ * @attr: the attribute ID to find
+ * @buf: output buffer, can be %NULL if the data isn't needed, e.g.
+ *	if the function is only called to get the needed buffer size
+ * @bufsize: size of the output buffer
+ *
+ * The function finds a given P2P attribute in the (vendor) IEs and
+ * copies its contents to the given buffer.
+ *
+ * The return value is a negative error code (-%EILSEQ or -%ENOENT) if
+ * the data is malformed or the attribute can't be found (respectively),
+ * or the length of the found attribute (which can be zero).
+ */
+unsigned int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len,
+				   u8 attr, u8 *buf, unsigned int bufsize);
+
 /* Logging, debugging and troubleshooting/diagnostic helpers. */
 
 /* wiphy_printk helpers, similar to dev_printk */
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 5b6c1df72f31..b99f01cda1f6 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -980,6 +980,105 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate)
 }
 EXPORT_SYMBOL(cfg80211_calculate_bitrate);
 
+unsigned int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len,
+				   u8 attr, u8 *buf, unsigned int bufsize)
+{
+	u8 *out = buf;
+	u16 attr_remaining = 0;
+	bool desired_attr = false;
+	u16 desired_len = 0;
+
+	while (len > 0) {
+		unsigned int iedatalen;
+		unsigned int copy;
+		const u8 *iedata;
+
+		if (len < 2)
+			return -EILSEQ;
+		iedatalen = ies[1];
+		if (iedatalen + 2 > len)
+			return -EILSEQ;
+
+		if (ies[0] != WLAN_EID_VENDOR_SPECIFIC)
+			goto cont;
+
+		if (iedatalen < 4)
+			goto cont;
+
+		iedata = ies + 2;
+
+		/* check WFA OUI, P2P subtype */
+		if (iedata[0] != 0x50 || iedata[1] != 0x6f ||
+		    iedata[2] != 0x9a || iedata[3] != 0x09)
+			goto cont;
+
+		iedatalen -= 4;
+		iedata += 4;
+
+		/* check attribute continuation into this IE */
+		copy = min_t(unsigned int, attr_remaining, iedatalen);
+		if (copy && desired_attr) {
+			desired_len += copy;
+			if (out) {
+				memcpy(out, iedata, min(bufsize, copy));
+				out += min(bufsize, copy);
+				bufsize -= min(bufsize, copy);
+			}
+
+
+			if (copy == attr_remaining)
+				return desired_len;
+		}
+
+		attr_remaining -= copy;
+		if (attr_remaining)
+			goto cont;
+
+		iedatalen -= copy;
+		iedata += copy;
+
+		while (iedatalen > 0) {
+			u16 attr_len;
+
+			/* P2P attribute ID & size must fit */
+			if (iedatalen < 3)
+				return -EILSEQ;
+			desired_attr = iedata[0] == attr;
+			attr_len = get_unaligned_le16(iedata + 1);
+			iedatalen -= 3;
+			iedata += 3;
+
+			copy = min_t(unsigned int, attr_len, iedatalen);
+
+			if (desired_attr) {
+				desired_len += copy;
+				if (out) {
+					memcpy(out, iedata, min(bufsize, copy));
+					out += min(bufsize, copy);
+					bufsize -= min(bufsize, copy);
+				}
+
+				if (copy == attr_len)
+					return desired_len;
+			}
+
+			iedata += copy;
+			iedatalen -= copy;
+			attr_remaining = attr_len - copy;
+		}
+
+ cont:
+		len -= ies[1] + 2;
+		ies += ies[1] + 2;
+	}
+
+	if (attr_remaining && desired_attr)
+		return -EILSEQ;
+
+	return -ENOENT;
+}
+EXPORT_SYMBOL(cfg80211_get_p2p_attr);
+
 int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
 				 u32 beacon_int)
 {
-- 
cgit v1.2.3-55-g7522


From 488dd7b53de9ea41edf7a475be63da51bdd05093 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Mon, 29 Oct 2012 20:08:01 +0100
Subject: mac80211: pass P2P powersave parameters to driver

While connected to a GO, parse the P2P NoA attribute
and pass the CT Window and opportunistic powersave
parameters to the driver.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  7 +++++++
 net/mac80211/ieee80211_i.h |  2 ++
 net/mac80211/mlme.c        | 40 ++++++++++++++++++++++++++++++++++++++++
 net/mac80211/trace.h       |  4 ++++
 4 files changed, 53 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index dfa589b721b6..23803addca3c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -208,6 +208,8 @@ struct ieee80211_chanctx_conf {
  * @BSS_CHANGED_AP_PROBE_RESP: Probe Response changed for this BSS (AP mode)
  * @BSS_CHANGED_PS: PS changed for this BSS (STA mode)
  * @BSS_CHANGED_TXPOWER: TX power setting changed for this interface
+ * @BSS_CHANGED_P2P_PS: P2P powersave settings (CTWindow, opportunistic PS)
+ *	changed (currently only in P2P client mode, GO mode will be later)
  */
 enum ieee80211_bss_change {
 	BSS_CHANGED_ASSOC		= 1<<0,
@@ -229,6 +231,7 @@ enum ieee80211_bss_change {
 	BSS_CHANGED_AP_PROBE_RESP	= 1<<16,
 	BSS_CHANGED_PS			= 1<<17,
 	BSS_CHANGED_TXPOWER		= 1<<18,
+	BSS_CHANGED_P2P_PS		= 1<<19,
 
 	/* when adding here, make sure to change ieee80211_reconfig */
 };
@@ -312,6 +315,8 @@ enum ieee80211_rssi_event {
  * @ssid_len: Length of SSID given in @ssid.
  * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode.
  * @txpower: TX power in dBm
+ * @p2p_ctwindow: P2P CTWindow, only for P2P client interfaces
+ * @p2p_oppps: P2P opportunistic PS is enabled
  */
 struct ieee80211_bss_conf {
 	const u8 *bssid;
@@ -345,6 +350,8 @@ struct ieee80211_bss_conf {
 	size_t ssid_len;
 	bool hidden_ssid;
 	int txpower;
+	u8 p2p_ctwindow;
+	bool p2p_oppps;
 };
 
 /**
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index d272e0cabc37..e1fb97cc9a41 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -473,6 +473,8 @@ struct ieee80211_if_managed {
 
 	u8 use_4addr;
 
+	u8 p2p_noa_index;
+
 	/* Signal strength from the last Beacon frame in the current BSS. */
 	int last_beacon_signal;
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 02ffe8738243..61614461e089 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1365,6 +1365,22 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata,
 
 	sdata->u.mgd.flags |= IEEE80211_STA_RESET_SIGNAL_AVE;
 
+	if (sdata->vif.p2p) {
+		u8 noa[2];
+		int ret;
+
+		ret = cfg80211_get_p2p_attr(cbss->information_elements,
+					    cbss->len_information_elements,
+					    IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
+					    noa, sizeof(noa));
+		if (ret >= 2) {
+			bss_conf->p2p_oppps = noa[1] & 0x80;
+			bss_conf->p2p_ctwindow = noa[1] & 0x7f;
+			bss_info_changed |= BSS_CHANGED_P2P_PS;
+			sdata->u.mgd.p2p_noa_index = noa[0];
+		}
+	}
+
 	/* just to be sure */
 	ieee80211_stop_poll(sdata);
 
@@ -1487,6 +1503,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	changed |= BSS_CHANGED_ASSOC;
 	sdata->vif.bss_conf.assoc = false;
 
+	sdata->vif.bss_conf.p2p_ctwindow = 0;
+	sdata->vif.bss_conf.p2p_oppps = false;
+
 	/* on the next assoc, re-program HT parameters */
 	memset(&ifmgd->ht_capa, 0, sizeof(ifmgd->ht_capa));
 	memset(&ifmgd->ht_capa_mask, 0, sizeof(ifmgd->ht_capa_mask));
@@ -2594,6 +2613,27 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
+	if (sdata->vif.p2p) {
+		u8 noa[2];
+		int ret;
+
+		ret = cfg80211_get_p2p_attr(mgmt->u.beacon.variable,
+					    len - baselen,
+					    IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
+					    noa, sizeof(noa));
+		if (ret >= 2 && sdata->u.mgd.p2p_noa_index != noa[0]) {
+			bss_conf->p2p_oppps = noa[1] & 0x80;
+			bss_conf->p2p_ctwindow = noa[1] & 0x7f;
+			changed |= BSS_CHANGED_P2P_PS;
+			sdata->u.mgd.p2p_noa_index = noa[0];
+			/*
+			 * make sure we update all information, the CRC
+			 * mechanism doesn't look at P2P attributes.
+			 */
+			ifmgd->beacon_crc_valid = false;
+		}
+	}
+
 	if (ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid)
 		return;
 	ifmgd->beacon_crc = ncrc;
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index eeebbd9cb888..7794e533989a 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -343,6 +343,8 @@ TRACE_EVENT(drv_bss_info_changed,
 		__dynamic_array(u8, ssid, info->ssid_len);
 		__field(bool, hidden_ssid);
 		__field(int, txpower)
+		__field(u8, p2p_ctwindow)
+		__field(bool, p2p_oppps)
 	),
 
 	TP_fast_assign(
@@ -378,6 +380,8 @@ TRACE_EVENT(drv_bss_info_changed,
 		memcpy(__get_dynamic_array(ssid), info->ssid, info->ssid_len);
 		__entry->hidden_ssid = info->hidden_ssid;
 		__entry->txpower = info->txpower;
+		__entry->p2p_ctwindow = info->p2p_ctwindow;
+		__entry->p2p_oppps = info->p2p_oppps;
 	),
 
 	TP_printk(
-- 
cgit v1.2.3-55-g7522


From bcd2360c1ff9fff69eb45bedc5fba7240c6da875 Mon Sep 17 00:00:00 2001
From: Jean-Christophe PLAGNIOL-VILLARD
Date: Tue, 30 Oct 2012 05:12:23 +0800
Subject: arm: at91: move platfarm_data to include/linux/platform_data/atmel.h

Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Cc: Nicolas Ferre <nicolas.ferre@atmel.com>
---
 arch/arm/mach-at91/include/mach/board.h     | 55 -----------------------
 arch/avr32/mach-at32ap/include/mach/board.h |  7 ---
 drivers/ata/pata_at91.c                     |  2 +-
 drivers/input/touchscreen/atmel_tsadcc.c    |  2 +-
 drivers/mmc/host/atmel-mci.c                |  2 +-
 drivers/net/can/at91_can.c                  |  3 +-
 drivers/net/ethernet/cadence/at91_ether.c   |  2 +-
 drivers/pcmcia/at91_cf.c                    |  2 +-
 drivers/rtc/rtc-at91sam9.c                  |  2 +-
 drivers/spi/spi-atmel.c                     |  2 +-
 drivers/tty/serial/atmel_serial.c           |  2 +-
 drivers/usb/gadget/at91_udc.c               |  2 +-
 drivers/usb/gadget/atmel_usba_udc.c         |  2 +-
 drivers/usb/host/ohci-at91.c                |  2 +-
 drivers/video/atmel_lcdfb.c                 |  2 +-
 include/linux/platform_data/atmel.h         | 67 +++++++++++++++++++++++++++++
 16 files changed, 80 insertions(+), 76 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-at91/include/mach/board.h b/arch/arm/mach-at91/include/mach/board.h
index c55a4364ffb4..662451d85fc9 100644
--- a/arch/arm/mach-at91/include/mach/board.h
+++ b/arch/arm/mach-at91/include/mach/board.h
@@ -31,42 +31,15 @@
 #ifndef __ASM_ARCH_BOARD_H
 #define __ASM_ARCH_BOARD_H
 
-#include <linux/mtd/partitions.h>
-#include <linux/device.h>
-#include <linux/i2c.h>
-#include <linux/leds.h>
-#include <linux/spi/spi.h>
-#include <linux/usb/atmel_usba_udc.h>
-#include <linux/atmel-mci.h>
-#include <sound/atmel-ac97c.h>
-#include <linux/serial.h>
-#include <linux/platform_data/macb.h>
 #include <linux/platform_data/atmel.h>
 
  /* USB Device */
-struct at91_udc_data {
-	int	vbus_pin;		/* high == host powering us */
-	u8	vbus_active_low;	/* vbus polarity */
-	u8	vbus_polled;		/* Use polling, not interrupt */
-	int	pullup_pin;		/* active == D+ pulled up */
-	u8	pullup_active_low;	/* true == pullup_pin is active low */
-};
 extern void __init at91_add_device_udc(struct at91_udc_data *data);
 
  /* USB High Speed Device */
 extern void __init at91_add_device_usba(struct usba_platform_data *data);
 
  /* Compact Flash */
-struct at91_cf_data {
-	int	irq_pin;		/* I/O IRQ */
-	int	det_pin;		/* Card detect */
-	int	vcc_pin;		/* power switching */
-	int	rst_pin;		/* card reset */
-	u8	chipselect;		/* EBI Chip Select number */
-	u8	flags;
-#define AT91_CF_TRUE_IDE	0x01
-#define AT91_IDE_SWAP_A0_A2	0x02
-};
 extern void __init at91_add_device_cf(struct at91_cf_data *data);
 
  /* MMC / SD */
@@ -86,16 +59,6 @@ extern void __init at91_add_device_mci(short mmc_id, struct mci_platform_data *d
 extern void __init at91_add_device_eth(struct macb_platform_data *data);
 
  /* USB Host */
-#define AT91_MAX_USBH_PORTS	3
-struct at91_usbh_data {
-	int		vbus_pin[AT91_MAX_USBH_PORTS];	/* port power-control pin */
-	int             overcurrent_pin[AT91_MAX_USBH_PORTS];
-	u8		ports;				/* number of ports on root hub */
-	u8              overcurrent_supported;
-	u8              vbus_pin_active_low[AT91_MAX_USBH_PORTS];
-	u8              overcurrent_status[AT91_MAX_USBH_PORTS];
-	u8              overcurrent_changed[AT91_MAX_USBH_PORTS];
-};
 extern void __init at91_add_device_usbh(struct at91_usbh_data *data);
 extern void __init at91_add_device_usbh_ohci(struct at91_usbh_data *data);
 extern void __init at91_add_device_usbh_ehci(struct at91_usbh_data *data);
@@ -124,13 +87,6 @@ extern void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pin
 
 extern struct platform_device *atmel_default_console_device;
 
-struct atmel_uart_data {
-	int			num;		/* port num */
-	short			use_dma_tx;	/* use transmit DMA? */
-	short			use_dma_rx;	/* use receive DMA? */
-	void __iomem		*regs;		/* virt. base address, if any */
-	struct serial_rs485	rs485;		/* rs485 settings */
-};
 extern void __init at91_add_device_serial(void);
 
 /*
@@ -173,24 +129,13 @@ extern void __init at91_add_device_isi(struct isi_platform_data *data,
 		bool use_pck_as_mck);
 
  /* Touchscreen Controller */
-struct at91_tsadcc_data {
-	unsigned int    adc_clock;
-	u8		pendet_debounce;
-	u8		ts_sample_hold_time;
-};
 extern void __init at91_add_device_tsadcc(struct at91_tsadcc_data *data);
 
 /* CAN */
-struct at91_can_data {
-	void (*transceiver_switch)(int on);
-};
 extern void __init at91_add_device_can(struct at91_can_data *data);
 
  /* LEDs */
 extern void __init at91_gpio_leds(struct gpio_led *leds, int nr);
 extern void __init at91_pwm_leds(struct gpio_led *leds, int nr);
 
-/* FIXME: this needs a better location, but gets stuff building again */
-extern int at91_suspend_entering_slow_clock(void);
-
 #endif
diff --git a/arch/avr32/mach-at32ap/include/mach/board.h b/arch/avr32/mach-at32ap/include/mach/board.h
index 70742ec997f8..dca93450cb0e 100644
--- a/arch/avr32/mach-at32ap/include/mach/board.h
+++ b/arch/avr32/mach-at32ap/include/mach/board.h
@@ -34,13 +34,6 @@ extern struct platform_device *atmel_default_console_device;
 #define	ATMEL_USART_CTS		0x02
 #define	ATMEL_USART_CLK		0x04
 
-struct atmel_uart_data {
-	int		num;		/* port num */
-	short		use_dma_tx;	/* use transmit DMA? */
-	short		use_dma_rx;	/* use receive DMA? */
-	void __iomem	*regs;		/* virtual base address, if any */
-	struct serial_rs485	rs485;		/* rs485 settings */
-};
 void at32_map_usart(unsigned int hw_id, unsigned int line, int flags);
 struct platform_device *at32_add_device_usart(unsigned int id);
 
diff --git a/drivers/ata/pata_at91.c b/drivers/ata/pata_at91.c
index 53d3770a0b1b..2a96bb2c53ee 100644
--- a/drivers/ata/pata_at91.c
+++ b/drivers/ata/pata_at91.c
@@ -27,9 +27,9 @@
 #include <linux/libata.h>
 #include <linux/platform_device.h>
 #include <linux/ata_platform.h>
+#include <linux/platform_data/atmel.h>
 
 #include <mach/at91sam9_smc.h>
-#include <mach/board.h>
 #include <asm/gpio.h>
 
 #define DRV_NAME		"pata_at91"
diff --git a/drivers/input/touchscreen/atmel_tsadcc.c b/drivers/input/touchscreen/atmel_tsadcc.c
index 201b2d2ec1b3..ea392ee138ed 100644
--- a/drivers/input/touchscreen/atmel_tsadcc.c
+++ b/drivers/input/touchscreen/atmel_tsadcc.c
@@ -22,7 +22,7 @@
 #include <linux/clk.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
-#include <mach/board.h>
+#include <linux/platform_data/atmel.h>
 #include <mach/cpu.h>
 
 /* Register definitions based on AT91SAM9RL64 preliminary draft datasheet */
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index ddf096e3803f..868998925826 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/types.h>
+#include <linux/platform_data/atmel.h>
 
 #include <linux/mmc/host.h>
 #include <linux/mmc/sdio.h>
@@ -40,7 +41,6 @@
 #include <asm/unaligned.h>
 
 #include <mach/cpu.h>
-#include <mach/board.h>
 
 #include "atmel-mci-regs.h"
 
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index fcff73a73b1d..994b6acd65f4 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -33,12 +33,11 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <linux/platform_data/atmel.h>
 
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
 
-#include <mach/board.h>
-
 #define AT91_MB_MASK(i)		((1 << (i)) - 1)
 
 /* Common registers */
diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c
index 4e980a7886fb..35fc6edbacf8 100644
--- a/drivers/net/ethernet/cadence/at91_ether.c
+++ b/drivers/net/ethernet/cadence/at91_ether.c
@@ -31,6 +31,7 @@
 #include <linux/clk.h>
 #include <linux/gfp.h>
 #include <linux/phy.h>
+#include <linux/platform_data/atmel.h>
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
@@ -38,7 +39,6 @@
 
 #include <mach/at91rm9200_emac.h>
 #include <asm/gpio.h>
-#include <mach/board.h>
 
 #include "at91_ether.h"
 
diff --git a/drivers/pcmcia/at91_cf.c b/drivers/pcmcia/at91_cf.c
index 9694c1e783a5..01463c781847 100644
--- a/drivers/pcmcia/at91_cf.c
+++ b/drivers/pcmcia/at91_cf.c
@@ -17,6 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/gpio.h>
+#include <linux/platform_data/atmel.h>
 
 #include <pcmcia/ss.h>
 
@@ -24,7 +25,6 @@
 #include <asm/io.h>
 #include <asm/sizes.h>
 
-#include <mach/board.h>
 #include <mach/at91rm9200_mc.h>
 #include <mach/at91_ramc.h>
 
diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c
index 2dfe7a2fb998..e981798e9a9b 100644
--- a/drivers/rtc/rtc-at91sam9.c
+++ b/drivers/rtc/rtc-at91sam9.c
@@ -19,8 +19,8 @@
 #include <linux/interrupt.h>
 #include <linux/ioctl.h>
 #include <linux/slab.h>
+#include <linux/platform_data/atmel.h>
 
-#include <mach/board.h>
 #include <mach/at91_rtt.h>
 #include <mach/cpu.h>
 
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 16d6a839c7fa..61fb0ec26f06 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -19,9 +19,9 @@
 #include <linux/interrupt.h>
 #include <linux/spi/spi.h>
 #include <linux/slab.h>
+#include <linux/platform_data/atmel.h>
 
 #include <asm/io.h>
-#include <mach/board.h>
 #include <asm/gpio.h>
 #include <mach/cpu.h>
 
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 3d7e1ee2fa57..5660ec2618a3 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -39,12 +39,12 @@
 #include <linux/atmel_pdc.h>
 #include <linux/atmel_serial.h>
 #include <linux/uaccess.h>
+#include <linux/platform_data/atmel.h>
 
 #include <asm/io.h>
 #include <asm/ioctls.h>
 
 #include <asm/mach/serial_at91.h>
-#include <mach/board.h>
 
 #ifdef CONFIG_ARM
 #include <mach/cpu.h>
diff --git a/drivers/usb/gadget/at91_udc.c b/drivers/usb/gadget/at91_udc.c
index 89d90b5fb787..a7b042b781d5 100644
--- a/drivers/usb/gadget/at91_udc.c
+++ b/drivers/usb/gadget/at91_udc.c
@@ -31,6 +31,7 @@
 #include <linux/usb/gadget.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
+#include <linux/platform_data/atmel.h>
 
 #include <asm/byteorder.h>
 #include <mach/hardware.h>
@@ -38,7 +39,6 @@
 #include <asm/irq.h>
 #include <asm/gpio.h>
 
-#include <mach/board.h>
 #include <mach/cpu.h>
 #include <mach/at91sam9261_matrix.h>
 #include <mach/at91_matrix.h>
diff --git a/drivers/usb/gadget/atmel_usba_udc.c b/drivers/usb/gadget/atmel_usba_udc.c
index 9a9bced813ed..a7aed84d98c9 100644
--- a/drivers/usb/gadget/atmel_usba_udc.c
+++ b/drivers/usb/gadget/atmel_usba_udc.c
@@ -21,9 +21,9 @@
 #include <linux/usb/gadget.h>
 #include <linux/usb/atmel_usba_udc.h>
 #include <linux/delay.h>
+#include <linux/platform_data/atmel.h>
 
 #include <asm/gpio.h>
-#include <mach/board.h>
 
 #include "atmel_usba_udc.h"
 
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 0bf72f943b00..8e62f81ae1ed 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -16,11 +16,11 @@
 #include <linux/platform_device.h>
 #include <linux/of_platform.h>
 #include <linux/of_gpio.h>
+#include <linux/platform_data/atmel.h>
 
 #include <mach/hardware.h>
 #include <asm/gpio.h>
 
-#include <mach/board.h>
 #include <mach/cpu.h>
 
 #ifndef CONFIG_ARCH_AT91
diff --git a/drivers/video/atmel_lcdfb.c b/drivers/video/atmel_lcdfb.c
index 94cac9f9919f..12cf5f31ee8f 100644
--- a/drivers/video/atmel_lcdfb.c
+++ b/drivers/video/atmel_lcdfb.c
@@ -19,8 +19,8 @@
 #include <linux/backlight.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
+#include <linux/platform_data/atmel.h>
 
-#include <mach/board.h>
 #include <mach/cpu.h>
 #include <asm/gpio.h>
 
diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h
index b0f2c56a8ea2..dbd6d53cc270 100644
--- a/include/linux/platform_data/atmel.h
+++ b/include/linux/platform_data/atmel.h
@@ -8,6 +8,49 @@
 #define __ATMEL_H__
 
 #include <linux/mtd/nand.h>
+#include <linux/mtd/partitions.h>
+#include <linux/device.h>
+#include <linux/i2c.h>
+#include <linux/leds.h>
+#include <linux/spi/spi.h>
+#include <linux/usb/atmel_usba_udc.h>
+#include <linux/atmel-mci.h>
+#include <sound/atmel-ac97c.h>
+#include <linux/serial.h>
+#include <linux/platform_data/macb.h>
+
+ /* USB Device */
+struct at91_udc_data {
+	int	vbus_pin;		/* high == host powering us */
+	u8	vbus_active_low;	/* vbus polarity */
+	u8	vbus_polled;		/* Use polling, not interrupt */
+	int	pullup_pin;		/* active == D+ pulled up */
+	u8	pullup_active_low;	/* true == pullup_pin is active low */
+};
+
+ /* Compact Flash */
+struct at91_cf_data {
+	int	irq_pin;		/* I/O IRQ */
+	int	det_pin;		/* Card detect */
+	int	vcc_pin;		/* power switching */
+	int	rst_pin;		/* card reset */
+	u8	chipselect;		/* EBI Chip Select number */
+	u8	flags;
+#define AT91_CF_TRUE_IDE	0x01
+#define AT91_IDE_SWAP_A0_A2	0x02
+};
+
+ /* USB Host */
+#define AT91_MAX_USBH_PORTS	3
+struct at91_usbh_data {
+	int		vbus_pin[AT91_MAX_USBH_PORTS];	/* port power-control pin */
+	int             overcurrent_pin[AT91_MAX_USBH_PORTS];
+	u8		ports;				/* number of ports on root hub */
+	u8              overcurrent_supported;
+	u8              vbus_pin_active_low[AT91_MAX_USBH_PORTS];
+	u8              overcurrent_status[AT91_MAX_USBH_PORTS];
+	u8              overcurrent_changed[AT91_MAX_USBH_PORTS];
+};
 
  /* NAND / SmartMedia */
 struct atmel_nand_data {
@@ -24,4 +67,28 @@ struct atmel_nand_data {
 	unsigned int	num_parts;
 };
 
+ /* Serial */
+struct atmel_uart_data {
+	int			num;		/* port num */
+	short			use_dma_tx;	/* use transmit DMA? */
+	short			use_dma_rx;	/* use receive DMA? */
+	void __iomem		*regs;		/* virt. base address, if any */
+	struct serial_rs485	rs485;		/* rs485 settings */
+};
+
+ /* Touchscreen Controller */
+struct at91_tsadcc_data {
+	unsigned int    adc_clock;
+	u8		pendet_debounce;
+	u8		ts_sample_hold_time;
+};
+
+/* CAN */
+struct at91_can_data {
+	void (*transceiver_switch)(int on);
+};
+
+/* FIXME: this needs a better location, but gets stuff building again */
+extern int at91_suspend_entering_slow_clock(void);
+
 #endif /* __ATMEL_H__ */
-- 
cgit v1.2.3-55-g7522


From 0b3904ab2a48488e23332ac1ecd2d45961ec6718 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä
Date: Thu, 25 Oct 2012 18:05:05 +0000
Subject: drm: Constify some function arguments

None of drm_mode_debug_printmodeline(), drm_mode_equal(), drm_mode_width()
or drm_mode_height() change the mode passed in, so make the arguments
const.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_modes.c | 8 ++++----
 include/drm/drm_crtc.h      | 8 ++++----
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 59450f39bf96..d8da30e90db5 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -46,7 +46,7 @@
  *
  * Describe @mode using DRM_DEBUG.
  */
-void drm_mode_debug_printmodeline(struct drm_display_mode *mode)
+void drm_mode_debug_printmodeline(const struct drm_display_mode *mode)
 {
 	DRM_DEBUG_KMS("Modeline %d:\"%s\" %d %d %d %d %d %d %d %d %d %d "
 			"0x%x 0x%x\n",
@@ -558,7 +558,7 @@ EXPORT_SYMBOL(drm_mode_list_concat);
  * RETURNS:
  * @mode->hdisplay
  */
-int drm_mode_width(struct drm_display_mode *mode)
+int drm_mode_width(const struct drm_display_mode *mode)
 {
 	return mode->hdisplay;
 
@@ -579,7 +579,7 @@ EXPORT_SYMBOL(drm_mode_width);
  * RETURNS:
  * @mode->vdisplay
  */
-int drm_mode_height(struct drm_display_mode *mode)
+int drm_mode_height(const struct drm_display_mode *mode)
 {
 	return mode->vdisplay;
 }
@@ -768,7 +768,7 @@ EXPORT_SYMBOL(drm_mode_duplicate);
  * RETURNS:
  * True if the modes are equal, false otherwise.
  */
-bool drm_mode_equal(struct drm_display_mode *mode1, struct drm_display_mode *mode2)
+bool drm_mode_equal(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2)
 {
 	/* do clock check convert to PICOS so fb modes get matched
 	 * the same */
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 3fa18b7e9497..49dd8c2eea7d 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -887,14 +887,14 @@ extern void drm_mode_remove(struct drm_connector *connector, struct drm_display_
 extern void drm_mode_copy(struct drm_display_mode *dst, const struct drm_display_mode *src);
 extern struct drm_display_mode *drm_mode_duplicate(struct drm_device *dev,
 						   const struct drm_display_mode *mode);
-extern void drm_mode_debug_printmodeline(struct drm_display_mode *mode);
+extern void drm_mode_debug_printmodeline(const struct drm_display_mode *mode);
 extern void drm_mode_config_init(struct drm_device *dev);
 extern void drm_mode_config_reset(struct drm_device *dev);
 extern void drm_mode_config_cleanup(struct drm_device *dev);
 extern void drm_mode_set_name(struct drm_display_mode *mode);
-extern bool drm_mode_equal(struct drm_display_mode *mode1, struct drm_display_mode *mode2);
-extern int drm_mode_width(struct drm_display_mode *mode);
-extern int drm_mode_height(struct drm_display_mode *mode);
+extern bool drm_mode_equal(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2);
+extern int drm_mode_width(const struct drm_display_mode *mode);
+extern int drm_mode_height(const struct drm_display_mode *mode);
 
 /* for us by fb module */
 extern int drm_mode_attachmode_crtc(struct drm_device *dev,
-- 
cgit v1.2.3-55-g7522


From a9dbfff1cbe5972ae0ef07b51530a70240ec9f2c Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst
Date: Fri, 12 Oct 2012 16:58:36 +0200
Subject: drm/ttm: add ttm_bo_is_reserved

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c | 12 ++++++------
 include/drm/ttm/ttm_bo_api.h | 14 ++++++++++++++
 2 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index bf6e4b5a73b5..e6bfcfdd3b60 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -162,9 +162,9 @@ int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo, bool interruptible)
 {
 	if (interruptible) {
 		return wait_event_interruptible(bo->event_queue,
-					       atomic_read(&bo->reserved) == 0);
+					       !ttm_bo_is_reserved(bo));
 	} else {
-		wait_event(bo->event_queue, atomic_read(&bo->reserved) == 0);
+		wait_event(bo->event_queue, !ttm_bo_is_reserved(bo));
 		return 0;
 	}
 }
@@ -175,7 +175,7 @@ void ttm_bo_add_to_lru(struct ttm_buffer_object *bo)
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_mem_type_manager *man;
 
-	BUG_ON(!atomic_read(&bo->reserved));
+	BUG_ON(!ttm_bo_is_reserved(bo));
 
 	if (!(bo->mem.placement & TTM_PL_FLAG_NO_EVICT)) {
 
@@ -756,7 +756,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 		goto out;
 	}
 
-	BUG_ON(!atomic_read(&bo->reserved));
+	BUG_ON(!ttm_bo_is_reserved(bo));
 
 	evict_mem = bo->mem;
 	evict_mem.mm_node = NULL;
@@ -1073,7 +1073,7 @@ int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 	struct ttm_mem_reg mem;
 	struct ttm_bo_device *bdev = bo->bdev;
 
-	BUG_ON(!atomic_read(&bo->reserved));
+	BUG_ON(!ttm_bo_is_reserved(bo));
 
 	/*
 	 * FIXME: It's possible to pipeline buffer moves.
@@ -1130,7 +1130,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 {
 	int ret;
 
-	BUG_ON(!atomic_read(&bo->reserved));
+	BUG_ON(!ttm_bo_is_reserved(bo));
 	/* Check that range is valid */
 	if (placement->lpfn || placement->fpfn)
 		if (placement->fpfn > placement->lpfn ||
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index e8028ade567f..36e8408e00fa 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -736,4 +736,18 @@ extern ssize_t ttm_bo_io(struct ttm_bo_device *bdev, struct file *filp,
 
 extern void ttm_bo_swapout_all(struct ttm_bo_device *bdev);
 
+/**
+ * ttm_bo_is_reserved - return an indication if a ttm buffer object is reserved
+ *
+ * @bo:     The buffer object to check.
+ *
+ * This function returns an indication if a bo is reserved or not, and should
+ * only be used to print an error when it is not from incorrect api usage, since
+ * there's no guarantee that it is the caller that is holding the reservation.
+ */
+static inline bool ttm_bo_is_reserved(struct ttm_buffer_object *bo)
+{
+	return atomic_read(&bo->reserved);
+}
+
 #endif
-- 
cgit v1.2.3-55-g7522


From 0fd97ccf45be26fb01b3a412f1f6c6b5044b2f16 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig
Date: Mon, 8 Oct 2012 00:03:19 -0400
Subject: target: kill struct se_subsystem_dev

Simplify the code a lot by killing the superflous struct se_subsystem_dev.
Instead se_device is allocated early on by the backend driver, which allocates
it as part of its own per-device structure, borrowing the scheme that is for
example used for inode allocation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/loopback/tcm_loop.h           |   1 -
 drivers/target/target_core_alua.c            | 152 ++++---
 drivers/target/target_core_alua.h            |   4 +-
 drivers/target/target_core_configfs.c        | 528 +++++++----------------
 drivers/target/target_core_device.c          | 613 +++++++++++++--------------
 drivers/target/target_core_fabric_configfs.c |  14 +-
 drivers/target/target_core_file.c            | 138 +++---
 drivers/target/target_core_file.h            |   2 +
 drivers/target/target_core_hba.c             |   4 +-
 drivers/target/target_core_iblock.c          | 185 ++++----
 drivers/target/target_core_iblock.h          |   1 +
 drivers/target/target_core_internal.h        |  12 +-
 drivers/target/target_core_pr.c              | 148 +++----
 drivers/target/target_core_pr.h              |   2 +-
 drivers/target/target_core_pscsi.c           | 270 +++++-------
 drivers/target/target_core_pscsi.h           |   2 +-
 drivers/target/target_core_rd.c              |  94 ++--
 drivers/target/target_core_rd.h              |   1 +
 drivers/target/target_core_sbc.c             |  31 +-
 drivers/target/target_core_spc.c             |  91 ++--
 drivers/target/target_core_stat.c            | 307 ++++----------
 drivers/target/target_core_tmr.c             |   6 +-
 drivers/target/target_core_transport.c       | 217 +---------
 drivers/target/target_core_ua.c              |   6 +-
 include/target/target_core_backend.h         |  25 +-
 include/target/target_core_base.h            | 104 ++---
 26 files changed, 1049 insertions(+), 1909 deletions(-)

(limited to 'include')

diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h
index 7b54893db665..dd7a84ee78e1 100644
--- a/drivers/target/loopback/tcm_loop.h
+++ b/drivers/target/loopback/tcm_loop.h
@@ -53,7 +53,6 @@ struct tcm_loop_hba {
 	struct se_hba_s *se_hba;
 	struct se_lun *tl_hba_lun;
 	struct se_port *tl_hba_lun_sep;
-	struct se_device_s *se_dev_hba_ptr;
 	struct tcm_loop_nexus *tl_nexus;
 	struct device dev;
 	struct Scsi_Host *sh;
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 9a5f9a7aecd2..15c127b780d8 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -61,7 +61,7 @@ struct t10_alua_lu_gp *default_lu_gp;
  */
 int target_emulate_report_target_port_groups(struct se_cmd *cmd)
 {
-	struct se_subsystem_dev *su_dev = cmd->se_dev->se_sub_dev;
+	struct se_device *dev = cmd->se_dev;
 	struct se_port *port;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
@@ -86,8 +86,8 @@ int target_emulate_report_target_port_groups(struct se_cmd *cmd)
 	}
 	buf = transport_kmap_data_sg(cmd);
 
-	spin_lock(&su_dev->t10_alua.tg_pt_gps_lock);
-	list_for_each_entry(tg_pt_gp, &su_dev->t10_alua.tg_pt_gps_list,
+	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
+	list_for_each_entry(tg_pt_gp, &dev->t10_alua.tg_pt_gps_list,
 			tg_pt_gp_list) {
 		/*
 		 * Check if the Target port group and Target port descriptor list
@@ -160,7 +160,7 @@ int target_emulate_report_target_port_groups(struct se_cmd *cmd)
 		}
 		spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
 	}
-	spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 	/*
 	 * Set the RETURN DATA LENGTH set in the header of the DataIN Payload
 	 */
@@ -203,7 +203,6 @@ int target_emulate_report_target_port_groups(struct se_cmd *cmd)
 int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
 	struct se_port *port, *l_port = cmd->se_lun->lun_sep;
 	struct se_node_acl *nacl = cmd->se_sess->se_node_acl;
 	struct t10_alua_tg_pt_gp *tg_pt_gp = NULL, *l_tg_pt_gp;
@@ -303,9 +302,9 @@ int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 			 * Locate the matching target port group ID from
 			 * the global tg_pt_gp list
 			 */
-			spin_lock(&su_dev->t10_alua.tg_pt_gps_lock);
+			spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 			list_for_each_entry(tg_pt_gp,
-					&su_dev->t10_alua.tg_pt_gps_list,
+					&dev->t10_alua.tg_pt_gps_list,
 					tg_pt_gp_list) {
 				if (!tg_pt_gp->tg_pt_gp_valid_id)
 					continue;
@@ -315,18 +314,18 @@ int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 
 				atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
 				smp_mb__after_atomic_inc();
-				spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+				spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
 				rc = core_alua_do_port_transition(tg_pt_gp,
 						dev, l_port, nacl,
 						alua_access_state, 1);
 
-				spin_lock(&su_dev->t10_alua.tg_pt_gps_lock);
+				spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 				atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
 				smp_mb__after_atomic_dec();
 				break;
 			}
-			spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+			spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 			/*
 			 * If not matching target port group ID can be located
 			 * throw an exception with ASCQ: INVALID_PARAMETER_LIST
@@ -758,8 +757,7 @@ static int core_alua_update_tpg_primary_metadata(
 	int primary_state,
 	unsigned char *md_buf)
 {
-	struct se_subsystem_dev *su_dev = tg_pt_gp->tg_pt_gp_su_dev;
-	struct t10_wwn *wwn = &su_dev->t10_wwn;
+	struct t10_wwn *wwn = &tg_pt_gp->tg_pt_gp_dev->t10_wwn;
 	char path[ALUA_METADATA_PATH_LEN];
 	int len;
 
@@ -899,7 +897,6 @@ int core_alua_do_port_transition(
 {
 	struct se_device *dev;
 	struct se_port *port;
-	struct se_subsystem_dev *su_dev;
 	struct se_node_acl *nacl;
 	struct t10_alua_lu_gp *lu_gp;
 	struct t10_alua_lu_gp_member *lu_gp_mem, *local_lu_gp_mem;
@@ -949,14 +946,13 @@ int core_alua_do_port_transition(
 				lu_gp_mem_list) {
 
 		dev = lu_gp_mem->lu_gp_mem_dev;
-		su_dev = dev->se_sub_dev;
 		atomic_inc(&lu_gp_mem->lu_gp_mem_ref_cnt);
 		smp_mb__after_atomic_inc();
 		spin_unlock(&lu_gp->lu_gp_lock);
 
-		spin_lock(&su_dev->t10_alua.tg_pt_gps_lock);
+		spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 		list_for_each_entry(tg_pt_gp,
-				&su_dev->t10_alua.tg_pt_gps_list,
+				&dev->t10_alua.tg_pt_gps_list,
 				tg_pt_gp_list) {
 
 			if (!tg_pt_gp->tg_pt_gp_valid_id)
@@ -981,7 +977,7 @@ int core_alua_do_port_transition(
 			}
 			atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
 			smp_mb__after_atomic_inc();
-			spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+			spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 			/*
 			 * core_alua_do_transition_tg_pt() will always return
 			 * success.
@@ -989,11 +985,11 @@ int core_alua_do_port_transition(
 			core_alua_do_transition_tg_pt(tg_pt_gp, port,
 					nacl, md_buf, new_state, explict);
 
-			spin_lock(&su_dev->t10_alua.tg_pt_gps_lock);
+			spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 			atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
 			smp_mb__after_atomic_dec();
 		}
-		spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+		spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
 		spin_lock(&lu_gp->lu_gp_lock);
 		atomic_dec(&lu_gp_mem->lu_gp_mem_ref_cnt);
@@ -1268,8 +1264,7 @@ void core_alua_free_lu_gp(struct t10_alua_lu_gp *lu_gp)
 
 void core_alua_free_lu_gp_mem(struct se_device *dev)
 {
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
-	struct t10_alua *alua = &su_dev->t10_alua;
+	struct t10_alua *alua = &dev->t10_alua;
 	struct t10_alua_lu_gp *lu_gp;
 	struct t10_alua_lu_gp_member *lu_gp_mem;
 
@@ -1358,10 +1353,8 @@ void __core_alua_drop_lu_gp_mem(
 	spin_unlock(&lu_gp->lu_gp_lock);
 }
 
-struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(
-	struct se_subsystem_dev *su_dev,
-	const char *name,
-	int def_group)
+struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(struct se_device *dev,
+		const char *name, int def_group)
 {
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 
@@ -1375,7 +1368,7 @@ struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(
 	mutex_init(&tg_pt_gp->tg_pt_gp_md_mutex);
 	spin_lock_init(&tg_pt_gp->tg_pt_gp_lock);
 	atomic_set(&tg_pt_gp->tg_pt_gp_ref_cnt, 0);
-	tg_pt_gp->tg_pt_gp_su_dev = su_dev;
+	tg_pt_gp->tg_pt_gp_dev = dev;
 	tg_pt_gp->tg_pt_gp_md_buf_len = ALUA_MD_BUF_LEN;
 	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
 		ALUA_ACCESS_STATE_ACTIVE_OPTMIZED);
@@ -1392,14 +1385,14 @@ struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(
 	tg_pt_gp->tg_pt_gp_implict_trans_secs = ALUA_DEFAULT_IMPLICT_TRANS_SECS;
 
 	if (def_group) {
-		spin_lock(&su_dev->t10_alua.tg_pt_gps_lock);
+		spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 		tg_pt_gp->tg_pt_gp_id =
-				su_dev->t10_alua.alua_tg_pt_gps_counter++;
+				dev->t10_alua.alua_tg_pt_gps_counter++;
 		tg_pt_gp->tg_pt_gp_valid_id = 1;
-		su_dev->t10_alua.alua_tg_pt_gps_count++;
+		dev->t10_alua.alua_tg_pt_gps_count++;
 		list_add_tail(&tg_pt_gp->tg_pt_gp_list,
-			      &su_dev->t10_alua.tg_pt_gps_list);
-		spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+			      &dev->t10_alua.tg_pt_gps_list);
+		spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 	}
 
 	return tg_pt_gp;
@@ -1409,9 +1402,10 @@ int core_alua_set_tg_pt_gp_id(
 	struct t10_alua_tg_pt_gp *tg_pt_gp,
 	u16 tg_pt_gp_id)
 {
-	struct se_subsystem_dev *su_dev = tg_pt_gp->tg_pt_gp_su_dev;
+	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
 	struct t10_alua_tg_pt_gp *tg_pt_gp_tmp;
 	u16 tg_pt_gp_id_tmp;
+
 	/*
 	 * The tg_pt_gp->tg_pt_gp_id may only be set once..
 	 */
@@ -1421,19 +1415,19 @@ int core_alua_set_tg_pt_gp_id(
 		return -EINVAL;
 	}
 
-	spin_lock(&su_dev->t10_alua.tg_pt_gps_lock);
-	if (su_dev->t10_alua.alua_tg_pt_gps_count == 0x0000ffff) {
+	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
+	if (dev->t10_alua.alua_tg_pt_gps_count == 0x0000ffff) {
 		pr_err("Maximum ALUA alua_tg_pt_gps_count:"
 			" 0x0000ffff reached\n");
-		spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+		spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 		kmem_cache_free(t10_alua_tg_pt_gp_cache, tg_pt_gp);
 		return -ENOSPC;
 	}
 again:
 	tg_pt_gp_id_tmp = (tg_pt_gp_id != 0) ? tg_pt_gp_id :
-			su_dev->t10_alua.alua_tg_pt_gps_counter++;
+			dev->t10_alua.alua_tg_pt_gps_counter++;
 
-	list_for_each_entry(tg_pt_gp_tmp, &su_dev->t10_alua.tg_pt_gps_list,
+	list_for_each_entry(tg_pt_gp_tmp, &dev->t10_alua.tg_pt_gps_list,
 			tg_pt_gp_list) {
 		if (tg_pt_gp_tmp->tg_pt_gp_id == tg_pt_gp_id_tmp) {
 			if (!tg_pt_gp_id)
@@ -1441,7 +1435,7 @@ again:
 
 			pr_err("ALUA Target Port Group ID: %hu already"
 				" exists, ignoring request\n", tg_pt_gp_id);
-			spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+			spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 			return -EINVAL;
 		}
 	}
@@ -1449,9 +1443,9 @@ again:
 	tg_pt_gp->tg_pt_gp_id = tg_pt_gp_id_tmp;
 	tg_pt_gp->tg_pt_gp_valid_id = 1;
 	list_add_tail(&tg_pt_gp->tg_pt_gp_list,
-			&su_dev->t10_alua.tg_pt_gps_list);
-	su_dev->t10_alua.alua_tg_pt_gps_count++;
-	spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+			&dev->t10_alua.tg_pt_gps_list);
+	dev->t10_alua.alua_tg_pt_gps_count++;
+	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
 	return 0;
 }
@@ -1480,8 +1474,9 @@ struct t10_alua_tg_pt_gp_member *core_alua_allocate_tg_pt_gp_mem(
 void core_alua_free_tg_pt_gp(
 	struct t10_alua_tg_pt_gp *tg_pt_gp)
 {
-	struct se_subsystem_dev *su_dev = tg_pt_gp->tg_pt_gp_su_dev;
+	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem, *tg_pt_gp_mem_tmp;
+
 	/*
 	 * Once we have reached this point, config_item_put() has already
 	 * been called from target_core_alua_drop_tg_pt_gp().
@@ -1490,10 +1485,11 @@ void core_alua_free_tg_pt_gp(
 	 * no assications *OR* explict ALUA via SET_TARGET_PORT_GROUPS
 	 * can be made while we are releasing struct t10_alua_tg_pt_gp.
 	 */
-	spin_lock(&su_dev->t10_alua.tg_pt_gps_lock);
+	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 	list_del(&tg_pt_gp->tg_pt_gp_list);
-	su_dev->t10_alua.alua_tg_pt_gps_counter--;
-	spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+	dev->t10_alua.alua_tg_pt_gps_counter--;
+	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
+
 	/*
 	 * Allow a struct t10_alua_tg_pt_gp_member * referenced by
 	 * core_alua_get_tg_pt_gp_by_name() in
@@ -1502,6 +1498,7 @@ void core_alua_free_tg_pt_gp(
 	 */
 	while (atomic_read(&tg_pt_gp->tg_pt_gp_ref_cnt))
 		cpu_relax();
+
 	/*
 	 * Release reference to struct t10_alua_tg_pt_gp from all associated
 	 * struct se_port.
@@ -1525,9 +1522,9 @@ void core_alua_free_tg_pt_gp(
 		 * default_tg_pt_gp.
 		 */
 		spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
-		if (tg_pt_gp != su_dev->t10_alua.default_tg_pt_gp) {
+		if (tg_pt_gp != dev->t10_alua.default_tg_pt_gp) {
 			__core_alua_attach_tg_pt_gp_mem(tg_pt_gp_mem,
-					su_dev->t10_alua.default_tg_pt_gp);
+					dev->t10_alua.default_tg_pt_gp);
 		} else
 			tg_pt_gp_mem->tg_pt_gp = NULL;
 		spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
@@ -1541,8 +1538,7 @@ void core_alua_free_tg_pt_gp(
 
 void core_alua_free_tg_pt_gp_mem(struct se_port *port)
 {
-	struct se_subsystem_dev *su_dev = port->sep_lun->lun_se_dev->se_sub_dev;
-	struct t10_alua *alua = &su_dev->t10_alua;
+	struct t10_alua *alua = &port->sep_lun->lun_se_dev->t10_alua;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 
@@ -1574,25 +1570,24 @@ void core_alua_free_tg_pt_gp_mem(struct se_port *port)
 }
 
 static struct t10_alua_tg_pt_gp *core_alua_get_tg_pt_gp_by_name(
-	struct se_subsystem_dev *su_dev,
-	const char *name)
+		struct se_device *dev, const char *name)
 {
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 	struct config_item *ci;
 
-	spin_lock(&su_dev->t10_alua.tg_pt_gps_lock);
-	list_for_each_entry(tg_pt_gp, &su_dev->t10_alua.tg_pt_gps_list,
+	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
+	list_for_each_entry(tg_pt_gp, &dev->t10_alua.tg_pt_gps_list,
 			tg_pt_gp_list) {
 		if (!tg_pt_gp->tg_pt_gp_valid_id)
 			continue;
 		ci = &tg_pt_gp->tg_pt_gp_group.cg_item;
 		if (!strcmp(config_item_name(ci), name)) {
 			atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
-			spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+			spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 			return tg_pt_gp;
 		}
 	}
-	spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
 	return NULL;
 }
@@ -1600,11 +1595,11 @@ static struct t10_alua_tg_pt_gp *core_alua_get_tg_pt_gp_by_name(
 static void core_alua_put_tg_pt_gp_from_name(
 	struct t10_alua_tg_pt_gp *tg_pt_gp)
 {
-	struct se_subsystem_dev *su_dev = tg_pt_gp->tg_pt_gp_su_dev;
+	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
 
-	spin_lock(&su_dev->t10_alua.tg_pt_gps_lock);
+	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 	atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
-	spin_unlock(&su_dev->t10_alua.tg_pt_gps_lock);
+	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 }
 
 /*
@@ -1640,9 +1635,8 @@ static void __core_alua_drop_tg_pt_gp_mem(
 
 ssize_t core_alua_show_tg_pt_gp_info(struct se_port *port, char *page)
 {
-	struct se_subsystem_dev *su_dev = port->sep_lun->lun_se_dev->se_sub_dev;
 	struct config_item *tg_pt_ci;
-	struct t10_alua *alua = &su_dev->t10_alua;
+	struct t10_alua *alua = &port->sep_lun->lun_se_dev->t10_alua;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 	ssize_t len = 0;
@@ -1683,7 +1677,7 @@ ssize_t core_alua_store_tg_pt_gp_info(
 {
 	struct se_portal_group *tpg;
 	struct se_lun *lun;
-	struct se_subsystem_dev *su_dev = port->sep_lun->lun_se_dev->se_sub_dev;
+	struct se_device *dev = port->sep_lun->lun_se_dev;
 	struct t10_alua_tg_pt_gp *tg_pt_gp = NULL, *tg_pt_gp_new = NULL;
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 	unsigned char buf[TG_PT_GROUP_NAME_BUF];
@@ -1692,7 +1686,7 @@ ssize_t core_alua_store_tg_pt_gp_info(
 	tpg = port->sep_tpg;
 	lun = port->sep_lun;
 
-	if (su_dev->t10_alua.alua_type != SPC3_ALUA_EMULATED) {
+	if (dev->t10_alua.alua_type != SPC3_ALUA_EMULATED) {
 		pr_warn("SPC3_ALUA_EMULATED not enabled for"
 			" %s/tpgt_%hu/%s\n", tpg->se_tpg_tfo->tpg_get_wwn(tpg),
 			tpg->se_tpg_tfo->tpg_get_tag(tpg),
@@ -1716,7 +1710,7 @@ ssize_t core_alua_store_tg_pt_gp_info(
 		 * struct t10_alua_tg_pt_gp.  This reference is released with
 		 * core_alua_put_tg_pt_gp_from_name() below.
 		 */
-		tg_pt_gp_new = core_alua_get_tg_pt_gp_by_name(su_dev,
+		tg_pt_gp_new = core_alua_get_tg_pt_gp_by_name(dev,
 					strstrip(buf));
 		if (!tg_pt_gp_new)
 			return -ENODEV;
@@ -1750,7 +1744,7 @@ ssize_t core_alua_store_tg_pt_gp_info(
 
 			__core_alua_drop_tg_pt_gp_mem(tg_pt_gp_mem, tg_pt_gp);
 			__core_alua_attach_tg_pt_gp_mem(tg_pt_gp_mem,
-					su_dev->t10_alua.default_tg_pt_gp);
+					dev->t10_alua.default_tg_pt_gp);
 			spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
 
 			return count;
@@ -2054,32 +2048,29 @@ ssize_t core_alua_store_secondary_write_metadata(
 	return count;
 }
 
-int core_setup_alua(struct se_device *dev, int force_pt)
+int core_setup_alua(struct se_device *dev)
 {
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
-	struct t10_alua *alua = &su_dev->t10_alua;
+	struct t10_alua *alua = &dev->t10_alua;
 	struct t10_alua_lu_gp_member *lu_gp_mem;
+
 	/*
 	 * If this device is from Target_Core_Mod/pSCSI, use the ALUA logic
 	 * of the Underlying SCSI hardware.  In Linux/SCSI terms, this can
 	 * cause a problem because libata and some SATA RAID HBAs appear
 	 * under Linux/SCSI, but emulate SCSI logic themselves.
 	 */
-	if (((dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) &&
-	    !(dev->se_sub_dev->se_dev_attrib.emulate_alua)) || force_pt) {
-		alua->alua_type = SPC_ALUA_PASSTHROUGH;
-		alua->alua_state_check = &core_alua_state_check_nop;
+	if ((dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE) ||
+	    (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV &&
+	     !dev->dev_attrib.emulate_alua)) {
 		pr_debug("%s: Using SPC_ALUA_PASSTHROUGH, no ALUA"
 			" emulation\n", dev->transport->name);
-		return 0;
-	}
-	/*
-	 * If SPC-3 or above is reported by real or emulated struct se_device,
-	 * use emulated ALUA.
-	 */
-	if (dev->transport->get_device_rev(dev) >= SCSI_3) {
+
+		alua->alua_type = SPC_ALUA_PASSTHROUGH;
+		alua->alua_state_check = &core_alua_state_check_nop;
+	} else if (dev->transport->get_device_rev(dev) >= SCSI_3) {
 		pr_debug("%s: Enabling ALUA Emulation for SPC-3"
 			" device\n", dev->transport->name);
+
 		/*
 		 * Associate this struct se_device with the default ALUA
 		 * LUN Group.
@@ -2099,10 +2090,11 @@ int core_setup_alua(struct se_device *dev, int force_pt)
 			" core/alua/lu_gps/default_lu_gp\n",
 			dev->transport->name);
 	} else {
-		alua->alua_type = SPC2_ALUA_DISABLED;
-		alua->alua_state_check = &core_alua_state_check_nop;
 		pr_debug("%s: Disabling ALUA Emulation for SPC-2"
 			" device\n", dev->transport->name);
+
+		alua->alua_type = SPC2_ALUA_DISABLED;
+		alua->alua_state_check = &core_alua_state_check_nop;
 	}
 
 	return 0;
diff --git a/drivers/target/target_core_alua.h b/drivers/target/target_core_alua.h
index f920c170d47b..5019157ffe69 100644
--- a/drivers/target/target_core_alua.h
+++ b/drivers/target/target_core_alua.h
@@ -91,7 +91,7 @@ extern void __core_alua_drop_lu_gp_mem(struct t10_alua_lu_gp_member *,
 					struct t10_alua_lu_gp *);
 extern void core_alua_drop_lu_gp_dev(struct se_device *);
 extern struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(
-			struct se_subsystem_dev *, const char *, int);
+			struct se_device *, const char *, int);
 extern int core_alua_set_tg_pt_gp_id(struct t10_alua_tg_pt_gp *, u16);
 extern struct t10_alua_tg_pt_gp_member *core_alua_allocate_tg_pt_gp_mem(
 					struct se_port *);
@@ -131,6 +131,6 @@ extern ssize_t core_alua_show_secondary_write_metadata(struct se_lun *,
 					char *);
 extern ssize_t core_alua_store_secondary_write_metadata(struct se_lun *,
 					const char *, size_t);
-extern int core_setup_alua(struct se_device *, int);
+extern int core_setup_alua(struct se_device *);
 
 #endif /* TARGET_CORE_ALUA_H */
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index c123327499a3..7272016ed05f 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -565,21 +565,8 @@ static ssize_t target_core_dev_show_attr_##_name(			\
 	struct se_dev_attrib *da,					\
 	char *page)							\
 {									\
-	struct se_device *dev;						\
-	struct se_subsystem_dev *se_dev = da->da_sub_dev;			\
-	ssize_t rb;							\
-									\
-	spin_lock(&se_dev->se_dev_lock);				\
-	dev = se_dev->se_dev_ptr;					\
-	if (!dev) {							\
-		spin_unlock(&se_dev->se_dev_lock); 			\
-		return -ENODEV;						\
-	}								\
-	rb = snprintf(page, PAGE_SIZE, "%u\n",				\
-		(u32)dev->se_sub_dev->se_dev_attrib._name);		\
-	spin_unlock(&se_dev->se_dev_lock);				\
-									\
-	return rb;							\
+	return snprintf(page, PAGE_SIZE, "%u\n",			\
+		(u32)da->da_dev->dev_attrib._name);			\
 }
 
 #define DEF_DEV_ATTRIB_STORE(_name)					\
@@ -588,26 +575,16 @@ static ssize_t target_core_dev_store_attr_##_name(			\
 	const char *page,						\
 	size_t count)							\
 {									\
-	struct se_device *dev;						\
-	struct se_subsystem_dev *se_dev = da->da_sub_dev;			\
 	unsigned long val;						\
 	int ret;							\
 									\
-	spin_lock(&se_dev->se_dev_lock);				\
-	dev = se_dev->se_dev_ptr;					\
-	if (!dev) {							\
-		spin_unlock(&se_dev->se_dev_lock);			\
-		return -ENODEV;						\
-	}								\
 	ret = strict_strtoul(page, 0, &val);				\
 	if (ret < 0) {							\
-		spin_unlock(&se_dev->se_dev_lock);                      \
 		pr_err("strict_strtoul() failed with"		\
 			" ret: %d\n", ret);				\
 		return -EINVAL;						\
 	}								\
-	ret = se_dev_set_##_name(dev, (u32)val);			\
-	spin_unlock(&se_dev->se_dev_lock);				\
+	ret = se_dev_set_##_name(da->da_dev, (u32)val);			\
 									\
 	return (!ret) ? count : -EINVAL;				\
 }
@@ -764,13 +741,6 @@ static ssize_t target_core_dev_wwn_show_attr_vpd_unit_serial(
 	struct t10_wwn *t10_wwn,
 	char *page)
 {
-	struct se_subsystem_dev *se_dev = t10_wwn->t10_sub_dev;
-	struct se_device *dev;
-
-	dev = se_dev->se_dev_ptr;
-	if (!dev)
-		return -ENODEV;
-
 	return sprintf(page, "T10 VPD Unit Serial Number: %s\n",
 		&t10_wwn->unit_serial[0]);
 }
@@ -780,8 +750,7 @@ static ssize_t target_core_dev_wwn_store_attr_vpd_unit_serial(
 	const char *page,
 	size_t count)
 {
-	struct se_subsystem_dev *su_dev = t10_wwn->t10_sub_dev;
-	struct se_device *dev;
+	struct se_device *dev = t10_wwn->t10_dev;
 	unsigned char buf[INQUIRY_VPD_SERIAL_LEN];
 
 	/*
@@ -794,7 +763,7 @@ static ssize_t target_core_dev_wwn_store_attr_vpd_unit_serial(
 	 * it is doing 'the right thing' wrt a world wide unique
 	 * VPD Unit Serial Number that OS dependent multipath can depend on.
 	 */
-	if (su_dev->su_dev_flags & SDF_FIRMWARE_VPD_UNIT_SERIAL) {
+	if (dev->dev_flags & DF_FIRMWARE_VPD_UNIT_SERIAL) {
 		pr_err("Underlying SCSI device firmware provided VPD"
 			" Unit Serial, ignoring request\n");
 		return -EOPNOTSUPP;
@@ -811,15 +780,13 @@ static ssize_t target_core_dev_wwn_store_attr_vpd_unit_serial(
 	 * (underneath the initiator side OS dependent multipath code)
 	 * could cause negative effects.
 	 */
-	dev = su_dev->se_dev_ptr;
-	if (dev) {
-		if (atomic_read(&dev->dev_export_obj.obj_access_count)) {
-			pr_err("Unable to set VPD Unit Serial while"
-				" active %d $FABRIC_MOD exports exist\n",
-				atomic_read(&dev->dev_export_obj.obj_access_count));
-			return -EINVAL;
-		}
+	if (dev->export_count) {
+		pr_err("Unable to set VPD Unit Serial while"
+			" active %d $FABRIC_MOD exports exist\n",
+			dev->export_count);
+		return -EINVAL;
 	}
+
 	/*
 	 * This currently assumes ASCII encoding for emulated VPD Unit Serial.
 	 *
@@ -828,12 +795,12 @@ static ssize_t target_core_dev_wwn_store_attr_vpd_unit_serial(
 	 */
 	memset(buf, 0, INQUIRY_VPD_SERIAL_LEN);
 	snprintf(buf, INQUIRY_VPD_SERIAL_LEN, "%s", page);
-	snprintf(su_dev->t10_wwn.unit_serial, INQUIRY_VPD_SERIAL_LEN,
+	snprintf(dev->t10_wwn.unit_serial, INQUIRY_VPD_SERIAL_LEN,
 			"%s", strstrip(buf));
-	su_dev->su_dev_flags |= SDF_EMULATED_VPD_UNIT_SERIAL;
+	dev->dev_flags |= DF_EMULATED_VPD_UNIT_SERIAL;
 
 	pr_debug("Target_Core_ConfigFS: Set emulated VPD Unit Serial:"
-			" %s\n", su_dev->t10_wwn.unit_serial);
+			" %s\n", dev->t10_wwn.unit_serial);
 
 	return count;
 }
@@ -847,16 +814,10 @@ static ssize_t target_core_dev_wwn_show_attr_vpd_protocol_identifier(
 	struct t10_wwn *t10_wwn,
 	char *page)
 {
-	struct se_subsystem_dev *se_dev = t10_wwn->t10_sub_dev;
-	struct se_device *dev;
 	struct t10_vpd *vpd;
 	unsigned char buf[VPD_TMP_BUF_SIZE];
 	ssize_t len = 0;
 
-	dev = se_dev->se_dev_ptr;
-	if (!dev)
-		return -ENODEV;
-
 	memset(buf, 0, VPD_TMP_BUF_SIZE);
 
 	spin_lock(&t10_wwn->t10_vpd_lock);
@@ -894,16 +855,10 @@ static ssize_t target_core_dev_wwn_show_attr_##_name(			\
 	struct t10_wwn *t10_wwn,					\
 	char *page)							\
 {									\
-	struct se_subsystem_dev *se_dev = t10_wwn->t10_sub_dev;		\
-	struct se_device *dev;						\
 	struct t10_vpd *vpd;							\
 	unsigned char buf[VPD_TMP_BUF_SIZE];				\
 	ssize_t len = 0;						\
 									\
-	dev = se_dev->se_dev_ptr;					\
-	if (!dev)							\
-		return -ENODEV;						\
-									\
 	spin_lock(&t10_wwn->t10_vpd_lock);				\
 	list_for_each_entry(vpd, &t10_wwn->t10_vpd_list, vpd_list) {	\
 		if (vpd->association != _assoc)				\
@@ -1003,7 +958,7 @@ static struct config_item_type target_core_dev_wwn_cit = {
 
 /*  Start functions for struct config_item_type target_core_dev_pr_cit */
 
-CONFIGFS_EATTR_STRUCT(target_core_dev_pr, se_subsystem_dev);
+CONFIGFS_EATTR_STRUCT(target_core_dev_pr, se_device);
 #define SE_DEV_PR_ATTR(_name, _mode)					\
 static struct target_core_dev_pr_attribute target_core_dev_pr_##_name = \
 	__CONFIGFS_EATTR(_name, _mode,					\
@@ -1071,23 +1026,17 @@ static ssize_t target_core_dev_pr_show_spc2_res(
 	return *len;
 }
 
-static ssize_t target_core_dev_pr_show_attr_res_holder(
-	struct se_subsystem_dev *su_dev,
-	char *page)
+static ssize_t target_core_dev_pr_show_attr_res_holder(struct se_device *dev,
+		char *page)
 {
 	ssize_t len = 0;
 
-	if (!su_dev->se_dev_ptr)
-		return -ENODEV;
-
-	switch (su_dev->t10_pr.res_type) {
+	switch (dev->t10_pr.res_type) {
 	case SPC3_PERSISTENT_RESERVATIONS:
-		target_core_dev_pr_show_spc3_res(su_dev->se_dev_ptr,
-				page, &len);
+		target_core_dev_pr_show_spc3_res(dev, page, &len);
 		break;
 	case SPC2_RESERVATIONS:
-		target_core_dev_pr_show_spc2_res(su_dev->se_dev_ptr,
-				page, &len);
+		target_core_dev_pr_show_spc2_res(dev, page, &len);
 		break;
 	case SPC_PASSTHROUGH:
 		len += sprintf(page+len, "Passthrough\n");
@@ -1102,22 +1051,13 @@ static ssize_t target_core_dev_pr_show_attr_res_holder(
 
 SE_DEV_PR_ATTR_RO(res_holder);
 
-/*
- * res_pr_all_tgt_pts
- */
 static ssize_t target_core_dev_pr_show_attr_res_pr_all_tgt_pts(
-	struct se_subsystem_dev *su_dev,
-	char *page)
+		struct se_device *dev, char *page)
 {
-	struct se_device *dev;
 	struct t10_pr_registration *pr_reg;
 	ssize_t len = 0;
 
-	dev = su_dev->se_dev_ptr;
-	if (!dev)
-		return -ENODEV;
-
-	if (su_dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
 		return len;
 
 	spin_lock(&dev->dev_reservation_lock);
@@ -1144,20 +1084,13 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_all_tgt_pts(
 
 SE_DEV_PR_ATTR_RO(res_pr_all_tgt_pts);
 
-/*
- * res_pr_generation
- */
 static ssize_t target_core_dev_pr_show_attr_res_pr_generation(
-	struct se_subsystem_dev *su_dev,
-	char *page)
+		struct se_device *dev, char *page)
 {
-	if (!su_dev->se_dev_ptr)
-		return -ENODEV;
-
-	if (su_dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
 		return 0;
 
-	return sprintf(page, "0x%08x\n", su_dev->t10_pr.pr_generation);
+	return sprintf(page, "0x%08x\n", dev->t10_pr.pr_generation);
 }
 
 SE_DEV_PR_ATTR_RO(res_pr_generation);
@@ -1166,10 +1099,8 @@ SE_DEV_PR_ATTR_RO(res_pr_generation);
  * res_pr_holder_tg_port
  */
 static ssize_t target_core_dev_pr_show_attr_res_pr_holder_tg_port(
-	struct se_subsystem_dev *su_dev,
-	char *page)
+		struct se_device *dev, char *page)
 {
-	struct se_device *dev;
 	struct se_node_acl *se_nacl;
 	struct se_lun *lun;
 	struct se_portal_group *se_tpg;
@@ -1177,11 +1108,7 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_holder_tg_port(
 	struct target_core_fabric_ops *tfo;
 	ssize_t len = 0;
 
-	dev = su_dev->se_dev_ptr;
-	if (!dev)
-		return -ENODEV;
-
-	if (su_dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
 		return len;
 
 	spin_lock(&dev->dev_reservation_lock);
@@ -1211,12 +1138,8 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_holder_tg_port(
 
 SE_DEV_PR_ATTR_RO(res_pr_holder_tg_port);
 
-/*
- * res_pr_registered_i_pts
- */
 static ssize_t target_core_dev_pr_show_attr_res_pr_registered_i_pts(
-	struct se_subsystem_dev *su_dev,
-	char *page)
+		struct se_device *dev, char *page)
 {
 	struct target_core_fabric_ops *tfo;
 	struct t10_pr_registration *pr_reg;
@@ -1225,16 +1148,13 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_registered_i_pts(
 	ssize_t len = 0;
 	int reg_count = 0, prf_isid;
 
-	if (!su_dev->se_dev_ptr)
-		return -ENODEV;
-
-	if (su_dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
 		return len;
 
 	len += sprintf(page+len, "SPC-3 PR Registrations:\n");
 
-	spin_lock(&su_dev->t10_pr.registration_lock);
-	list_for_each_entry(pr_reg, &su_dev->t10_pr.registration_list,
+	spin_lock(&dev->t10_pr.registration_lock);
+	list_for_each_entry(pr_reg, &dev->t10_pr.registration_list,
 			pr_reg_list) {
 
 		memset(buf, 0, 384);
@@ -1254,7 +1174,7 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_registered_i_pts(
 		len += sprintf(page+len, "%s", buf);
 		reg_count++;
 	}
-	spin_unlock(&su_dev->t10_pr.registration_lock);
+	spin_unlock(&dev->t10_pr.registration_lock);
 
 	if (!reg_count)
 		len += sprintf(page+len, "None\n");
@@ -1264,22 +1184,13 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_registered_i_pts(
 
 SE_DEV_PR_ATTR_RO(res_pr_registered_i_pts);
 
-/*
- * res_pr_type
- */
 static ssize_t target_core_dev_pr_show_attr_res_pr_type(
-	struct se_subsystem_dev *su_dev,
-	char *page)
+		struct se_device *dev, char *page)
 {
-	struct se_device *dev;
 	struct t10_pr_registration *pr_reg;
 	ssize_t len = 0;
 
-	dev = su_dev->se_dev_ptr;
-	if (!dev)
-		return -ENODEV;
-
-	if (su_dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
 		return len;
 
 	spin_lock(&dev->dev_reservation_lock);
@@ -1298,19 +1209,12 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_type(
 
 SE_DEV_PR_ATTR_RO(res_pr_type);
 
-/*
- * res_type
- */
 static ssize_t target_core_dev_pr_show_attr_res_type(
-	struct se_subsystem_dev *su_dev,
-	char *page)
+		struct se_device *dev, char *page)
 {
 	ssize_t len = 0;
 
-	if (!su_dev->se_dev_ptr)
-		return -ENODEV;
-
-	switch (su_dev->t10_pr.res_type) {
+	switch (dev->t10_pr.res_type) {
 	case SPC3_PERSISTENT_RESERVATIONS:
 		len = sprintf(page, "SPC3_PERSISTENT_RESERVATIONS\n");
 		break;
@@ -1330,22 +1234,14 @@ static ssize_t target_core_dev_pr_show_attr_res_type(
 
 SE_DEV_PR_ATTR_RO(res_type);
 
-/*
- * res_aptpl_active
- */
-
 static ssize_t target_core_dev_pr_show_attr_res_aptpl_active(
-	struct se_subsystem_dev *su_dev,
-	char *page)
+		struct se_device *dev, char *page)
 {
-	if (!su_dev->se_dev_ptr)
-		return -ENODEV;
-
-	if (su_dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
 		return 0;
 
 	return sprintf(page, "APTPL Bit Status: %s\n",
-		(su_dev->t10_pr.pr_aptpl_active) ? "Activated" : "Disabled");
+		(dev->t10_pr.pr_aptpl_active) ? "Activated" : "Disabled");
 }
 
 SE_DEV_PR_ATTR_RO(res_aptpl_active);
@@ -1354,13 +1250,9 @@ SE_DEV_PR_ATTR_RO(res_aptpl_active);
  * res_aptpl_metadata
  */
 static ssize_t target_core_dev_pr_show_attr_res_aptpl_metadata(
-	struct se_subsystem_dev *su_dev,
-	char *page)
+		struct se_device *dev, char *page)
 {
-	if (!su_dev->se_dev_ptr)
-		return -ENODEV;
-
-	if (su_dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
 		return 0;
 
 	return sprintf(page, "Ready to process PR APTPL metadata..\n");
@@ -1392,11 +1284,10 @@ static match_table_t tokens = {
 };
 
 static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
-	struct se_subsystem_dev *su_dev,
+	struct se_device *dev,
 	const char *page,
 	size_t count)
 {
-	struct se_device *dev;
 	unsigned char *i_fabric = NULL, *i_port = NULL, *isid = NULL;
 	unsigned char *t_fabric = NULL, *t_port = NULL;
 	char *orig, *ptr, *arg_p, *opts;
@@ -1408,14 +1299,10 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
 	u16 port_rpti = 0, tpgt = 0;
 	u8 type = 0, scope;
 
-	dev = su_dev->se_dev_ptr;
-	if (!dev)
-		return -ENODEV;
-
-	if (su_dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
 		return 0;
 
-	if (atomic_read(&dev->dev_export_obj.obj_access_count)) {
+	if (dev->export_count) {
 		pr_debug("Unable to process APTPL metadata while"
 			" active fabric exports exist\n");
 		return -EINVAL;
@@ -1558,7 +1445,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
 		goto out;
 	}
 
-	ret = core_scsi3_alloc_aptpl_registration(&su_dev->t10_pr, sa_res_key,
+	ret = core_scsi3_alloc_aptpl_registration(&dev->t10_pr, sa_res_key,
 			i_port, isid, mapped_lun, t_port, tpgt, target_lun,
 			res_holder, all_tg_pt, type);
 out:
@@ -1573,7 +1460,7 @@ out:
 
 SE_DEV_PR_ATTR(res_aptpl_metadata, S_IRUGO | S_IWUSR);
 
-CONFIGFS_EATTR_OPS(target_core_dev_pr, se_subsystem_dev, se_dev_pr_group);
+CONFIGFS_EATTR_OPS(target_core_dev_pr, se_device, dev_pr_group);
 
 static struct configfs_attribute *target_core_dev_pr_attrs[] = {
 	&target_core_dev_pr_res_holder.attr,
@@ -1605,18 +1492,14 @@ static struct config_item_type target_core_dev_pr_cit = {
 
 static ssize_t target_core_show_dev_info(void *p, char *page)
 {
-	struct se_subsystem_dev *se_dev = p;
-	struct se_hba *hba = se_dev->se_dev_hba;
-	struct se_subsystem_api *t = hba->transport;
+	struct se_device *dev = p;
+	struct se_subsystem_api *t = dev->transport;
 	int bl = 0;
 	ssize_t read_bytes = 0;
 
-	if (!se_dev->se_dev_ptr)
-		return -ENODEV;
-
-	transport_dump_dev_state(se_dev->se_dev_ptr, page, &bl);
+	transport_dump_dev_state(dev, page, &bl);
 	read_bytes += bl;
-	read_bytes += t->show_configfs_dev_params(hba, se_dev, page+read_bytes);
+	read_bytes += t->show_configfs_dev_params(dev, page+read_bytes);
 	return read_bytes;
 }
 
@@ -1633,17 +1516,10 @@ static ssize_t target_core_store_dev_control(
 	const char *page,
 	size_t count)
 {
-	struct se_subsystem_dev *se_dev = p;
-	struct se_hba *hba = se_dev->se_dev_hba;
-	struct se_subsystem_api *t = hba->transport;
+	struct se_device *dev = p;
+	struct se_subsystem_api *t = dev->transport;
 
-	if (!se_dev->se_dev_su_ptr) {
-		pr_err("Unable to locate struct se_subsystem_dev>se"
-				"_dev_su_ptr\n");
-		return -EINVAL;
-	}
-
-	return t->set_configfs_dev_params(hba, se_dev, page, count);
+	return t->set_configfs_dev_params(dev, page, count);
 }
 
 static struct target_core_configfs_attribute target_core_attr_dev_control = {
@@ -1656,12 +1532,12 @@ static struct target_core_configfs_attribute target_core_attr_dev_control = {
 
 static ssize_t target_core_show_dev_alias(void *p, char *page)
 {
-	struct se_subsystem_dev *se_dev = p;
+	struct se_device *dev = p;
 
-	if (!(se_dev->su_dev_flags & SDF_USING_ALIAS))
+	if (!(dev->dev_flags & DF_USING_ALIAS))
 		return 0;
 
-	return snprintf(page, PAGE_SIZE, "%s\n", se_dev->se_dev_alias);
+	return snprintf(page, PAGE_SIZE, "%s\n", dev->dev_alias);
 }
 
 static ssize_t target_core_store_dev_alias(
@@ -1669,8 +1545,8 @@ static ssize_t target_core_store_dev_alias(
 	const char *page,
 	size_t count)
 {
-	struct se_subsystem_dev *se_dev = p;
-	struct se_hba *hba = se_dev->se_dev_hba;
+	struct se_device *dev = p;
+	struct se_hba *hba = dev->se_hba;
 	ssize_t read_bytes;
 
 	if (count > (SE_DEV_ALIAS_LEN-1)) {
@@ -1680,19 +1556,18 @@ static ssize_t target_core_store_dev_alias(
 		return -EINVAL;
 	}
 
-	read_bytes = snprintf(&se_dev->se_dev_alias[0], SE_DEV_ALIAS_LEN,
-			"%s", page);
+	read_bytes = snprintf(&dev->dev_alias[0], SE_DEV_ALIAS_LEN, "%s", page);
 	if (!read_bytes)
 		return -EINVAL;
-	if (se_dev->se_dev_alias[read_bytes - 1] == '\n')
-		se_dev->se_dev_alias[read_bytes - 1] = '\0';
+	if (dev->dev_alias[read_bytes - 1] == '\n')
+		dev->dev_alias[read_bytes - 1] = '\0';
 
-	se_dev->su_dev_flags |= SDF_USING_ALIAS;
+	dev->dev_flags |= DF_USING_ALIAS;
 
 	pr_debug("Target_Core_ConfigFS: %s/%s set alias: %s\n",
 		config_item_name(&hba->hba_group.cg_item),
-		config_item_name(&se_dev->se_dev_group.cg_item),
-		se_dev->se_dev_alias);
+		config_item_name(&dev->dev_group.cg_item),
+		dev->dev_alias);
 
 	return read_bytes;
 }
@@ -1707,12 +1582,12 @@ static struct target_core_configfs_attribute target_core_attr_dev_alias = {
 
 static ssize_t target_core_show_dev_udev_path(void *p, char *page)
 {
-	struct se_subsystem_dev *se_dev = p;
+	struct se_device *dev = p;
 
-	if (!(se_dev->su_dev_flags & SDF_USING_UDEV_PATH))
+	if (!(dev->dev_flags & DF_USING_UDEV_PATH))
 		return 0;
 
-	return snprintf(page, PAGE_SIZE, "%s\n", se_dev->se_dev_udev_path);
+	return snprintf(page, PAGE_SIZE, "%s\n", dev->udev_path);
 }
 
 static ssize_t target_core_store_dev_udev_path(
@@ -1720,8 +1595,8 @@ static ssize_t target_core_store_dev_udev_path(
 	const char *page,
 	size_t count)
 {
-	struct se_subsystem_dev *se_dev = p;
-	struct se_hba *hba = se_dev->se_dev_hba;
+	struct se_device *dev = p;
+	struct se_hba *hba = dev->se_hba;
 	ssize_t read_bytes;
 
 	if (count > (SE_UDEV_PATH_LEN-1)) {
@@ -1731,19 +1606,19 @@ static ssize_t target_core_store_dev_udev_path(
 		return -EINVAL;
 	}
 
-	read_bytes = snprintf(&se_dev->se_dev_udev_path[0], SE_UDEV_PATH_LEN,
+	read_bytes = snprintf(&dev->udev_path[0], SE_UDEV_PATH_LEN,
 			"%s", page);
 	if (!read_bytes)
 		return -EINVAL;
-	if (se_dev->se_dev_udev_path[read_bytes - 1] == '\n')
-		se_dev->se_dev_udev_path[read_bytes - 1] = '\0';
+	if (dev->udev_path[read_bytes - 1] == '\n')
+		dev->udev_path[read_bytes - 1] = '\0';
 
-	se_dev->su_dev_flags |= SDF_USING_UDEV_PATH;
+	dev->dev_flags |= DF_USING_UDEV_PATH;
 
 	pr_debug("Target_Core_ConfigFS: %s/%s set udev_path: %s\n",
 		config_item_name(&hba->hba_group.cg_item),
-		config_item_name(&se_dev->se_dev_group.cg_item),
-		se_dev->se_dev_udev_path);
+		config_item_name(&dev->dev_group.cg_item),
+		dev->udev_path);
 
 	return read_bytes;
 }
@@ -1761,11 +1636,9 @@ static ssize_t target_core_store_dev_enable(
 	const char *page,
 	size_t count)
 {
-	struct se_subsystem_dev *se_dev = p;
-	struct se_device *dev;
-	struct se_hba *hba = se_dev->se_dev_hba;
-	struct se_subsystem_api *t = hba->transport;
+	struct se_device *dev = p;
 	char *ptr;
+	int ret;
 
 	ptr = strstr(page, "1");
 	if (!ptr) {
@@ -1773,25 +1646,10 @@ static ssize_t target_core_store_dev_enable(
 				" is \"1\"\n");
 		return -EINVAL;
 	}
-	if (se_dev->se_dev_ptr) {
-		pr_err("se_dev->se_dev_ptr already set for storage"
-				" object\n");
-		return -EEXIST;
-	}
-
-	if (t->check_configfs_dev_params(hba, se_dev) < 0)
-		return -EINVAL;
-
-	dev = t->create_virtdevice(hba, se_dev, se_dev->se_dev_su_ptr);
-	if (IS_ERR(dev))
-		return PTR_ERR(dev);
-	else if (!dev)
-		return -EINVAL;
-
-	se_dev->se_dev_ptr = dev;
-	pr_debug("Target_Core_ConfigFS: Registered se_dev->se_dev_ptr:"
-		" %p\n", se_dev->se_dev_ptr);
 
+	ret = target_configure_device(dev);
+	if (ret)
+		return ret;
 	return count;
 }
 
@@ -1805,18 +1663,13 @@ static struct target_core_configfs_attribute target_core_attr_dev_enable = {
 
 static ssize_t target_core_show_alua_lu_gp(void *p, char *page)
 {
-	struct se_device *dev;
-	struct se_subsystem_dev *su_dev = p;
+	struct se_device *dev = p;
 	struct config_item *lu_ci;
 	struct t10_alua_lu_gp *lu_gp;
 	struct t10_alua_lu_gp_member *lu_gp_mem;
 	ssize_t len = 0;
 
-	dev = su_dev->se_dev_ptr;
-	if (!dev)
-		return -ENODEV;
-
-	if (su_dev->t10_alua.alua_type != SPC3_ALUA_EMULATED)
+	if (dev->t10_alua.alua_type != SPC3_ALUA_EMULATED)
 		return len;
 
 	lu_gp_mem = dev->dev_alua_lu_gp_mem;
@@ -1843,22 +1696,17 @@ static ssize_t target_core_store_alua_lu_gp(
 	const char *page,
 	size_t count)
 {
-	struct se_device *dev;
-	struct se_subsystem_dev *su_dev = p;
-	struct se_hba *hba = su_dev->se_dev_hba;
+	struct se_device *dev = p;
+	struct se_hba *hba = dev->se_hba;
 	struct t10_alua_lu_gp *lu_gp = NULL, *lu_gp_new = NULL;
 	struct t10_alua_lu_gp_member *lu_gp_mem;
 	unsigned char buf[LU_GROUP_NAME_BUF];
 	int move = 0;
 
-	dev = su_dev->se_dev_ptr;
-	if (!dev)
-		return -ENODEV;
-
-	if (su_dev->t10_alua.alua_type != SPC3_ALUA_EMULATED) {
+	if (dev->t10_alua.alua_type != SPC3_ALUA_EMULATED) {
 		pr_warn("SPC3_ALUA_EMULATED not enabled for %s/%s\n",
 			config_item_name(&hba->hba_group.cg_item),
-			config_item_name(&su_dev->se_dev_group.cg_item));
+			config_item_name(&dev->dev_group.cg_item));
 		return -EINVAL;
 	}
 	if (count > LU_GROUP_NAME_BUF) {
@@ -1902,7 +1750,7 @@ static ssize_t target_core_store_alua_lu_gp(
 				" from ALUA LU Group: core/alua/lu_gps/%s, ID:"
 				" %hu\n",
 				config_item_name(&hba->hba_group.cg_item),
-				config_item_name(&su_dev->se_dev_group.cg_item),
+				config_item_name(&dev->dev_group.cg_item),
 				config_item_name(&lu_gp->lu_gp_group.cg_item),
 				lu_gp->lu_gp_id);
 
@@ -1927,7 +1775,7 @@ static ssize_t target_core_store_alua_lu_gp(
 		" core/alua/lu_gps/%s, ID: %hu\n",
 		(move) ? "Moving" : "Adding",
 		config_item_name(&hba->hba_group.cg_item),
-		config_item_name(&su_dev->se_dev_group.cg_item),
+		config_item_name(&dev->dev_group.cg_item),
 		config_item_name(&lu_gp_new->lu_gp_group.cg_item),
 		lu_gp_new->lu_gp_id);
 
@@ -1955,69 +1803,44 @@ static struct configfs_attribute *lio_core_dev_attrs[] = {
 
 static void target_core_dev_release(struct config_item *item)
 {
-	struct se_subsystem_dev *se_dev = container_of(to_config_group(item),
-				struct se_subsystem_dev, se_dev_group);
-	struct se_hba *hba = item_to_hba(&se_dev->se_dev_hba->hba_group.cg_item);
-	struct se_subsystem_api *t = hba->transport;
-	struct config_group *dev_cg = &se_dev->se_dev_group;
+	struct config_group *dev_cg = to_config_group(item);
+	struct se_device *dev =
+		container_of(dev_cg, struct se_device, dev_group);
 
 	kfree(dev_cg->default_groups);
-	/*
-	 * This pointer will set when the storage is enabled with:
-	 *`echo 1 > $CONFIGFS/core/$HBA/$DEV/dev_enable`
-	 */
-	if (se_dev->se_dev_ptr) {
-		pr_debug("Target_Core_ConfigFS: Calling se_free_"
-			"virtual_device() for se_dev_ptr: %p\n",
-			se_dev->se_dev_ptr);
-
-		se_free_virtual_device(se_dev->se_dev_ptr, hba);
-	} else {
-		/*
-		 * Release struct se_subsystem_dev->se_dev_su_ptr..
-		 */
-		pr_debug("Target_Core_ConfigFS: Calling t->free_"
-			"device() for se_dev_su_ptr: %p\n",
-			se_dev->se_dev_su_ptr);
-
-		t->free_device(se_dev->se_dev_su_ptr);
-	}
-
-	pr_debug("Target_Core_ConfigFS: Deallocating se_subsystem"
-			"_dev_t: %p\n", se_dev);
-	kfree(se_dev);
+	target_free_device(dev);
 }
 
 static ssize_t target_core_dev_show(struct config_item *item,
 				     struct configfs_attribute *attr,
 				     char *page)
 {
-	struct se_subsystem_dev *se_dev = container_of(
-			to_config_group(item), struct se_subsystem_dev,
-			se_dev_group);
+	struct config_group *dev_cg = to_config_group(item);
+	struct se_device *dev =
+		container_of(dev_cg, struct se_device, dev_group);
 	struct target_core_configfs_attribute *tc_attr = container_of(
 			attr, struct target_core_configfs_attribute, attr);
 
 	if (!tc_attr->show)
 		return -EINVAL;
 
-	return tc_attr->show(se_dev, page);
+	return tc_attr->show(dev, page);
 }
 
 static ssize_t target_core_dev_store(struct config_item *item,
 				      struct configfs_attribute *attr,
 				      const char *page, size_t count)
 {
-	struct se_subsystem_dev *se_dev = container_of(
-			to_config_group(item), struct se_subsystem_dev,
-			se_dev_group);
+	struct config_group *dev_cg = to_config_group(item);
+	struct se_device *dev =
+		container_of(dev_cg, struct se_device, dev_group);
 	struct target_core_configfs_attribute *tc_attr = container_of(
 			attr, struct target_core_configfs_attribute, attr);
 
 	if (!tc_attr->store)
 		return -EINVAL;
 
-	return tc_attr->store(se_dev, page, count);
+	return tc_attr->store(dev, page, count);
 }
 
 static struct configfs_item_operations target_core_dev_item_ops = {
@@ -2107,7 +1930,6 @@ static ssize_t target_core_alua_lu_gp_show_attr_members(
 {
 	struct se_device *dev;
 	struct se_hba *hba;
-	struct se_subsystem_dev *su_dev;
 	struct t10_alua_lu_gp_member *lu_gp_mem;
 	ssize_t len = 0, cur_len;
 	unsigned char buf[LU_GROUP_NAME_BUF];
@@ -2117,12 +1939,11 @@ static ssize_t target_core_alua_lu_gp_show_attr_members(
 	spin_lock(&lu_gp->lu_gp_lock);
 	list_for_each_entry(lu_gp_mem, &lu_gp->lu_gp_mem_list, lu_gp_mem_list) {
 		dev = lu_gp_mem->lu_gp_mem_dev;
-		su_dev = dev->se_sub_dev;
-		hba = su_dev->se_dev_hba;
+		hba = dev->se_hba;
 
 		cur_len = snprintf(buf, LU_GROUP_NAME_BUF, "%s/%s\n",
 			config_item_name(&hba->hba_group.cg_item),
-			config_item_name(&su_dev->se_dev_group.cg_item));
+			config_item_name(&dev->dev_group.cg_item));
 		cur_len++; /* Extra byte for NULL terminator */
 
 		if ((cur_len + len) > PAGE_SIZE) {
@@ -2260,7 +2081,7 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_access_state(
 	const char *page,
 	size_t count)
 {
-	struct se_subsystem_dev *su_dev = tg_pt_gp->tg_pt_gp_su_dev;
+	struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
 	unsigned long tmp;
 	int new_state, ret;
 
@@ -2284,7 +2105,7 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_access_state(
 		return -EINVAL;
 	}
 
-	ret = core_alua_do_port_transition(tg_pt_gp, su_dev->se_dev_ptr,
+	ret = core_alua_do_port_transition(tg_pt_gp, dev,
 					NULL, NULL, new_state, 0);
 	return (!ret) ? count : -EINVAL;
 }
@@ -2620,11 +2441,10 @@ static struct config_group *target_core_alua_create_tg_pt_gp(
 	struct t10_alua *alua = container_of(group, struct t10_alua,
 					alua_tg_pt_gps_group);
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	struct se_subsystem_dev *su_dev = alua->t10_sub_dev;
 	struct config_group *alua_tg_pt_gp_cg = NULL;
 	struct config_item *alua_tg_pt_gp_ci = NULL;
 
-	tg_pt_gp = core_alua_allocate_tg_pt_gp(su_dev, name, 0);
+	tg_pt_gp = core_alua_allocate_tg_pt_gp(alua->t10_dev, name, 0);
 	if (!tg_pt_gp)
 		return NULL;
 
@@ -2721,10 +2541,10 @@ static struct config_group *target_core_make_subdev(
 	const char *name)
 {
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
-	struct se_subsystem_dev *se_dev;
 	struct se_subsystem_api *t;
 	struct config_item *hba_ci = &group->cg_item;
 	struct se_hba *hba = item_to_hba(hba_ci);
+	struct se_device *dev;
 	struct config_group *dev_cg = NULL, *tg_pt_gp_cg = NULL;
 	struct config_group *dev_stat_grp = NULL;
 	int errno = -ENOMEM, ret;
@@ -2737,120 +2557,80 @@ static struct config_group *target_core_make_subdev(
 	 */
 	t = hba->transport;
 
-	se_dev = kzalloc(sizeof(struct se_subsystem_dev), GFP_KERNEL);
-	if (!se_dev) {
-		pr_err("Unable to allocate memory for"
-				" struct se_subsystem_dev\n");
-		goto unlock;
-	}
-	INIT_LIST_HEAD(&se_dev->t10_wwn.t10_vpd_list);
-	spin_lock_init(&se_dev->t10_wwn.t10_vpd_lock);
-	INIT_LIST_HEAD(&se_dev->t10_pr.registration_list);
-	INIT_LIST_HEAD(&se_dev->t10_pr.aptpl_reg_list);
-	spin_lock_init(&se_dev->t10_pr.registration_lock);
-	spin_lock_init(&se_dev->t10_pr.aptpl_reg_lock);
-	INIT_LIST_HEAD(&se_dev->t10_alua.tg_pt_gps_list);
-	spin_lock_init(&se_dev->t10_alua.tg_pt_gps_lock);
-	spin_lock_init(&se_dev->se_dev_lock);
-	se_dev->t10_pr.pr_aptpl_buf_len = PR_APTPL_BUF_LEN;
-	se_dev->t10_wwn.t10_sub_dev = se_dev;
-	se_dev->t10_alua.t10_sub_dev = se_dev;
-	se_dev->se_dev_attrib.da_sub_dev = se_dev;
-
-	se_dev->se_dev_hba = hba;
-	dev_cg = &se_dev->se_dev_group;
+	dev = target_alloc_device(hba, name);
+	if (!dev)
+		goto out_unlock;
+
+	dev_cg = &dev->dev_group;
 
 	dev_cg->default_groups = kzalloc(sizeof(struct config_group) * 7,
 			GFP_KERNEL);
 	if (!dev_cg->default_groups)
-		goto out;
-	/*
-	 * Set se_dev_su_ptr from struct se_subsystem_api returned void ptr
-	 * for ->allocate_virtdevice()
-	 *
-	 * se_dev->se_dev_ptr will be set after ->create_virtdev()
-	 * has been called successfully in the next level up in the
-	 * configfs tree for device object's struct config_group.
-	 */
-	se_dev->se_dev_su_ptr = t->allocate_virtdevice(hba, name);
-	if (!se_dev->se_dev_su_ptr) {
-		pr_err("Unable to locate subsystem dependent pointer"
-			" from allocate_virtdevice()\n");
-		goto out;
-	}
+		goto out_free_device;
 
-	config_group_init_type_name(&se_dev->se_dev_group, name,
-			&target_core_dev_cit);
-	config_group_init_type_name(&se_dev->se_dev_attrib.da_group, "attrib",
+	config_group_init_type_name(dev_cg, name, &target_core_dev_cit);
+	config_group_init_type_name(&dev->dev_attrib.da_group, "attrib",
 			&target_core_dev_attrib_cit);
-	config_group_init_type_name(&se_dev->se_dev_pr_group, "pr",
+	config_group_init_type_name(&dev->dev_pr_group, "pr",
 			&target_core_dev_pr_cit);
-	config_group_init_type_name(&se_dev->t10_wwn.t10_wwn_group, "wwn",
+	config_group_init_type_name(&dev->t10_wwn.t10_wwn_group, "wwn",
 			&target_core_dev_wwn_cit);
-	config_group_init_type_name(&se_dev->t10_alua.alua_tg_pt_gps_group,
+	config_group_init_type_name(&dev->t10_alua.alua_tg_pt_gps_group,
 			"alua", &target_core_alua_tg_pt_gps_cit);
-	config_group_init_type_name(&se_dev->dev_stat_grps.stat_group,
+	config_group_init_type_name(&dev->dev_stat_grps.stat_group,
 			"statistics", &target_core_stat_cit);
 
-	dev_cg->default_groups[0] = &se_dev->se_dev_attrib.da_group;
-	dev_cg->default_groups[1] = &se_dev->se_dev_pr_group;
-	dev_cg->default_groups[2] = &se_dev->t10_wwn.t10_wwn_group;
-	dev_cg->default_groups[3] = &se_dev->t10_alua.alua_tg_pt_gps_group;
-	dev_cg->default_groups[4] = &se_dev->dev_stat_grps.stat_group;
+	dev_cg->default_groups[0] = &dev->dev_attrib.da_group;
+	dev_cg->default_groups[1] = &dev->dev_pr_group;
+	dev_cg->default_groups[2] = &dev->t10_wwn.t10_wwn_group;
+	dev_cg->default_groups[3] = &dev->t10_alua.alua_tg_pt_gps_group;
+	dev_cg->default_groups[4] = &dev->dev_stat_grps.stat_group;
 	dev_cg->default_groups[5] = NULL;
 	/*
 	 * Add core/$HBA/$DEV/alua/default_tg_pt_gp
 	 */
-	tg_pt_gp = core_alua_allocate_tg_pt_gp(se_dev, "default_tg_pt_gp", 1);
+	tg_pt_gp = core_alua_allocate_tg_pt_gp(dev, "default_tg_pt_gp", 1);
 	if (!tg_pt_gp)
-		goto out;
+		goto out_free_dev_cg_default_groups;
+	dev->t10_alua.default_tg_pt_gp = tg_pt_gp;
 
-	tg_pt_gp_cg = &se_dev->t10_alua.alua_tg_pt_gps_group;
+	tg_pt_gp_cg = &dev->t10_alua.alua_tg_pt_gps_group;
 	tg_pt_gp_cg->default_groups = kzalloc(sizeof(struct config_group) * 2,
 				GFP_KERNEL);
 	if (!tg_pt_gp_cg->default_groups) {
 		pr_err("Unable to allocate tg_pt_gp_cg->"
 				"default_groups\n");
-		goto out;
+		goto out_free_tg_pt_gp;
 	}
 
 	config_group_init_type_name(&tg_pt_gp->tg_pt_gp_group,
 			"default_tg_pt_gp", &target_core_alua_tg_pt_gp_cit);
 	tg_pt_gp_cg->default_groups[0] = &tg_pt_gp->tg_pt_gp_group;
 	tg_pt_gp_cg->default_groups[1] = NULL;
-	se_dev->t10_alua.default_tg_pt_gp = tg_pt_gp;
 	/*
 	 * Add core/$HBA/$DEV/statistics/ default groups
 	 */
-	dev_stat_grp = &se_dev->dev_stat_grps.stat_group;
+	dev_stat_grp = &dev->dev_stat_grps.stat_group;
 	dev_stat_grp->default_groups = kzalloc(sizeof(struct config_group) * 4,
 				GFP_KERNEL);
 	if (!dev_stat_grp->default_groups) {
 		pr_err("Unable to allocate dev_stat_grp->default_groups\n");
-		goto out;
+		goto out_free_tg_pt_gp_cg_default_groups;
 	}
-	target_stat_setup_dev_default_groups(se_dev);
-
-	pr_debug("Target_Core_ConfigFS: Allocated struct se_subsystem_dev:"
-		" %p se_dev_su_ptr: %p\n", se_dev, se_dev->se_dev_su_ptr);
+	target_stat_setup_dev_default_groups(dev);
 
 	mutex_unlock(&hba->hba_access_mutex);
-	return &se_dev->se_dev_group;
-out:
-	if (se_dev->t10_alua.default_tg_pt_gp) {
-		core_alua_free_tg_pt_gp(se_dev->t10_alua.default_tg_pt_gp);
-		se_dev->t10_alua.default_tg_pt_gp = NULL;
-	}
-	if (dev_stat_grp)
-		kfree(dev_stat_grp->default_groups);
-	if (tg_pt_gp_cg)
-		kfree(tg_pt_gp_cg->default_groups);
-	if (dev_cg)
-		kfree(dev_cg->default_groups);
-	if (se_dev->se_dev_su_ptr)
-		t->free_device(se_dev->se_dev_su_ptr);
-	kfree(se_dev);
-unlock:
+	return dev_cg;
+
+out_free_tg_pt_gp_cg_default_groups:
+	kfree(tg_pt_gp_cg->default_groups);
+out_free_tg_pt_gp:
+	core_alua_free_tg_pt_gp(tg_pt_gp);
+out_free_dev_cg_default_groups:
+	kfree(dev_cg->default_groups);
+out_free_device:
+	target_free_device(dev);
+out_unlock:
 	mutex_unlock(&hba->hba_access_mutex);
 	return ERR_PTR(errno);
 }
@@ -2859,18 +2639,19 @@ static void target_core_drop_subdev(
 	struct config_group *group,
 	struct config_item *item)
 {
-	struct se_subsystem_dev *se_dev = container_of(to_config_group(item),
-				struct se_subsystem_dev, se_dev_group);
+	struct config_group *dev_cg = to_config_group(item);
+	struct se_device *dev =
+		container_of(dev_cg, struct se_device, dev_group);
 	struct se_hba *hba;
 	struct config_item *df_item;
-	struct config_group *dev_cg, *tg_pt_gp_cg, *dev_stat_grp;
+	struct config_group *tg_pt_gp_cg, *dev_stat_grp;
 	int i;
 
-	hba = item_to_hba(&se_dev->se_dev_hba->hba_group.cg_item);
+	hba = item_to_hba(&dev->se_hba->hba_group.cg_item);
 
 	mutex_lock(&hba->hba_access_mutex);
 
-	dev_stat_grp = &se_dev->dev_stat_grps.stat_group;
+	dev_stat_grp = &dev->dev_stat_grps.stat_group;
 	for (i = 0; dev_stat_grp->default_groups[i]; i++) {
 		df_item = &dev_stat_grp->default_groups[i]->cg_item;
 		dev_stat_grp->default_groups[i] = NULL;
@@ -2878,7 +2659,7 @@ static void target_core_drop_subdev(
 	}
 	kfree(dev_stat_grp->default_groups);
 
-	tg_pt_gp_cg = &se_dev->t10_alua.alua_tg_pt_gps_group;
+	tg_pt_gp_cg = &dev->t10_alua.alua_tg_pt_gps_group;
 	for (i = 0; tg_pt_gp_cg->default_groups[i]; i++) {
 		df_item = &tg_pt_gp_cg->default_groups[i]->cg_item;
 		tg_pt_gp_cg->default_groups[i] = NULL;
@@ -2889,17 +2670,15 @@ static void target_core_drop_subdev(
 	 * core_alua_free_tg_pt_gp() is called from ->default_tg_pt_gp
 	 * directly from target_core_alua_tg_pt_gp_release().
 	 */
-	se_dev->t10_alua.default_tg_pt_gp = NULL;
+	dev->t10_alua.default_tg_pt_gp = NULL;
 
-	dev_cg = &se_dev->se_dev_group;
 	for (i = 0; dev_cg->default_groups[i]; i++) {
 		df_item = &dev_cg->default_groups[i]->cg_item;
 		dev_cg->default_groups[i] = NULL;
 		config_item_put(df_item);
 	}
 	/*
-	 * The releasing of se_dev and associated se_dev->se_dev_ptr is done
-	 * from target_core_dev_item_ops->release() ->target_core_dev_release().
+	 * se_dev is released from target_core_dev_item_ops->release()
 	 */
 	config_item_put(item);
 	mutex_unlock(&hba->hba_access_mutex);
@@ -2962,13 +2741,10 @@ static ssize_t target_core_hba_store_attr_hba_mode(struct se_hba *hba,
 		return -EINVAL;
 	}
 
-	spin_lock(&hba->device_lock);
-	if (!list_empty(&hba->hba_dev_list)) {
+	if (hba->dev_count) {
 		pr_err("Unable to set hba_mode with active devices\n");
-		spin_unlock(&hba->device_lock);
 		return -EINVAL;
 	}
-	spin_unlock(&hba->device_lock);
 
 	ret = transport->pmode_enable_hba(hba, mode_flag);
 	if (ret < 0)
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 9abef9f8eb76..b27c75a0e2e2 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -50,11 +50,7 @@
 #include "target_core_pr.h"
 #include "target_core_ua.h"
 
-static void se_dev_start(struct se_device *dev);
-static void se_dev_stop(struct se_device *dev);
-
 static struct se_hba *lun0_hba;
-static struct se_subsystem_dev *lun0_su_dev;
 /* not static, needed by tpg.c */
 struct se_device *g_lun0_dev;
 
@@ -136,15 +132,6 @@ int transport_lookup_cmd_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 		se_cmd->orig_fe_lun = 0;
 		se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
 	}
-	/*
-	 * Determine if the struct se_lun is online.
-	 * FIXME: Check for LUN_RESET + UNIT Attention
-	 */
-	if (se_dev_check_online(se_lun->lun_se_dev) != 0) {
-		se_cmd->scsi_sense_reason = TCM_NON_EXISTENT_LUN;
-		se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		return -ENODEV;
-	}
 
 	/* Directly associate cmd with se_dev */
 	se_cmd->se_dev = se_lun->lun_se_dev;
@@ -202,14 +189,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 		se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 		return -ENODEV;
 	}
-	/*
-	 * Determine if the struct se_lun is online.
-	 * FIXME: Check for LUN_RESET + UNIT Attention
-	 */
-	if (se_dev_check_online(se_lun->lun_se_dev) != 0) {
-		se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		return -ENODEV;
-	}
 
 	/* Directly associate cmd with se_dev */
 	se_cmd->se_dev = se_lun->lun_se_dev;
@@ -565,7 +544,6 @@ static void core_export_port(
 	struct se_port *port,
 	struct se_lun *lun)
 {
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem = NULL;
 
 	spin_lock(&dev->se_port_lock);
@@ -578,7 +556,7 @@ static void core_export_port(
 	list_add_tail(&port->sep_list, &dev->dev_sep_list);
 	spin_unlock(&dev->se_port_lock);
 
-	if (su_dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) {
+	if (dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) {
 		tg_pt_gp_mem = core_alua_allocate_tg_pt_gp_mem(port);
 		if (IS_ERR(tg_pt_gp_mem) || !tg_pt_gp_mem) {
 			pr_err("Unable to allocate t10_alua_tg_pt"
@@ -587,7 +565,7 @@ static void core_export_port(
 		}
 		spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
 		__core_alua_attach_tg_pt_gp_mem(tg_pt_gp_mem,
-			su_dev->t10_alua.default_tg_pt_gp);
+			dev->t10_alua.default_tg_pt_gp);
 		spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
 		pr_debug("%s/%s: Adding to default ALUA Target Port"
 			" Group: alua/default_tg_pt_gp\n",
@@ -625,6 +603,7 @@ int core_dev_export(
 	struct se_portal_group *tpg,
 	struct se_lun *lun)
 {
+	struct se_hba *hba = dev->se_hba;
 	struct se_port *port;
 
 	port = core_alloc_port(dev);
@@ -632,9 +611,11 @@ int core_dev_export(
 		return PTR_ERR(port);
 
 	lun->lun_se_dev = dev;
-	se_dev_start(dev);
 
-	atomic_inc(&dev->dev_export_obj.obj_access_count);
+	spin_lock(&hba->device_lock);
+	dev->export_count++;
+	spin_unlock(&hba->device_lock);
+
 	core_export_port(dev, tpg, port, lun);
 	return 0;
 }
@@ -644,6 +625,7 @@ void core_dev_unexport(
 	struct se_portal_group *tpg,
 	struct se_lun *lun)
 {
+	struct se_hba *hba = dev->se_hba;
 	struct se_port *port = lun->lun_sep;
 
 	spin_lock(&lun->lun_sep_lock);
@@ -654,11 +636,13 @@ void core_dev_unexport(
 	spin_unlock(&lun->lun_sep_lock);
 
 	spin_lock(&dev->se_port_lock);
-	atomic_dec(&dev->dev_export_obj.obj_access_count);
 	core_release_port(dev, port);
 	spin_unlock(&dev->se_port_lock);
 
-	se_dev_stop(dev);
+	spin_lock(&hba->device_lock);
+	dev->export_count--;
+	spin_unlock(&hba->device_lock);
+
 	lun->lun_se_dev = NULL;
 }
 
@@ -725,127 +709,17 @@ done:
 	return 0;
 }
 
-/*	se_release_device_for_hba():
- *
- *
- */
-void se_release_device_for_hba(struct se_device *dev)
-{
-	struct se_hba *hba = dev->se_hba;
-
-	if ((dev->dev_status & TRANSPORT_DEVICE_ACTIVATED) ||
-	    (dev->dev_status & TRANSPORT_DEVICE_DEACTIVATED) ||
-	    (dev->dev_status & TRANSPORT_DEVICE_SHUTDOWN) ||
-	    (dev->dev_status & TRANSPORT_DEVICE_OFFLINE_ACTIVATED) ||
-	    (dev->dev_status & TRANSPORT_DEVICE_OFFLINE_DEACTIVATED))
-		se_dev_stop(dev);
-
-	if (dev->dev_ptr) {
-		destroy_workqueue(dev->tmr_wq);
-		if (dev->transport->free_device)
-			dev->transport->free_device(dev->dev_ptr);
-	}
-
-	spin_lock(&hba->device_lock);
-	list_del(&dev->dev_list);
-	hba->dev_count--;
-	spin_unlock(&hba->device_lock);
-
-	core_scsi3_free_all_registrations(dev);
-	se_release_vpd_for_dev(dev);
-
-	kfree(dev);
-}
-
-void se_release_vpd_for_dev(struct se_device *dev)
+static void se_release_vpd_for_dev(struct se_device *dev)
 {
 	struct t10_vpd *vpd, *vpd_tmp;
 
-	spin_lock(&dev->se_sub_dev->t10_wwn.t10_vpd_lock);
+	spin_lock(&dev->t10_wwn.t10_vpd_lock);
 	list_for_each_entry_safe(vpd, vpd_tmp,
-			&dev->se_sub_dev->t10_wwn.t10_vpd_list, vpd_list) {
+			&dev->t10_wwn.t10_vpd_list, vpd_list) {
 		list_del(&vpd->vpd_list);
 		kfree(vpd);
 	}
-	spin_unlock(&dev->se_sub_dev->t10_wwn.t10_vpd_lock);
-}
-
-/*	se_free_virtual_device():
- *
- *	Used for IBLOCK, RAMDISK, and FILEIO Transport Drivers.
- */
-int se_free_virtual_device(struct se_device *dev, struct se_hba *hba)
-{
-	if (!list_empty(&dev->dev_sep_list))
-		dump_stack();
-
-	core_alua_free_lu_gp_mem(dev);
-	se_release_device_for_hba(dev);
-
-	return 0;
-}
-
-static void se_dev_start(struct se_device *dev)
-{
-	struct se_hba *hba = dev->se_hba;
-
-	spin_lock(&hba->device_lock);
-	atomic_inc(&dev->dev_obj.obj_access_count);
-	if (atomic_read(&dev->dev_obj.obj_access_count) == 1) {
-		if (dev->dev_status & TRANSPORT_DEVICE_DEACTIVATED) {
-			dev->dev_status &= ~TRANSPORT_DEVICE_DEACTIVATED;
-			dev->dev_status |= TRANSPORT_DEVICE_ACTIVATED;
-		} else if (dev->dev_status &
-			   TRANSPORT_DEVICE_OFFLINE_DEACTIVATED) {
-			dev->dev_status &=
-				~TRANSPORT_DEVICE_OFFLINE_DEACTIVATED;
-			dev->dev_status |= TRANSPORT_DEVICE_OFFLINE_ACTIVATED;
-		}
-	}
-	spin_unlock(&hba->device_lock);
-}
-
-static void se_dev_stop(struct se_device *dev)
-{
-	struct se_hba *hba = dev->se_hba;
-
-	spin_lock(&hba->device_lock);
-	atomic_dec(&dev->dev_obj.obj_access_count);
-	if (atomic_read(&dev->dev_obj.obj_access_count) == 0) {
-		if (dev->dev_status & TRANSPORT_DEVICE_ACTIVATED) {
-			dev->dev_status &= ~TRANSPORT_DEVICE_ACTIVATED;
-			dev->dev_status |= TRANSPORT_DEVICE_DEACTIVATED;
-		} else if (dev->dev_status &
-			   TRANSPORT_DEVICE_OFFLINE_ACTIVATED) {
-			dev->dev_status &= ~TRANSPORT_DEVICE_OFFLINE_ACTIVATED;
-			dev->dev_status |= TRANSPORT_DEVICE_OFFLINE_DEACTIVATED;
-		}
-	}
-	spin_unlock(&hba->device_lock);
-}
-
-int se_dev_check_online(struct se_device *dev)
-{
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&dev->dev_status_lock, flags);
-	ret = ((dev->dev_status & TRANSPORT_DEVICE_ACTIVATED) ||
-	       (dev->dev_status & TRANSPORT_DEVICE_DEACTIVATED)) ? 0 : 1;
-	spin_unlock_irqrestore(&dev->dev_status_lock, flags);
-
-	return ret;
-}
-
-int se_dev_check_shutdown(struct se_device *dev)
-{
-	int ret;
-
-	spin_lock_irq(&dev->dev_status_lock);
-	ret = (dev->dev_status & TRANSPORT_DEVICE_SHUTDOWN);
-	spin_unlock_irq(&dev->dev_status_lock);
-
-	return ret;
+	spin_unlock(&dev->t10_wwn.t10_vpd_lock);
 }
 
 static u32 se_dev_align_max_sectors(u32 max_sectors, u32 block_size)
@@ -866,72 +740,13 @@ static u32 se_dev_align_max_sectors(u32 max_sectors, u32 block_size)
 	return aligned_max_sectors;
 }
 
-void se_dev_set_default_attribs(
-	struct se_device *dev,
-	struct se_dev_limits *dev_limits)
-{
-	struct queue_limits *limits = &dev_limits->limits;
-
-	dev->se_sub_dev->se_dev_attrib.emulate_dpo = DA_EMULATE_DPO;
-	dev->se_sub_dev->se_dev_attrib.emulate_fua_write = DA_EMULATE_FUA_WRITE;
-	dev->se_sub_dev->se_dev_attrib.emulate_fua_read = DA_EMULATE_FUA_READ;
-	dev->se_sub_dev->se_dev_attrib.emulate_write_cache = DA_EMULATE_WRITE_CACHE;
-	dev->se_sub_dev->se_dev_attrib.emulate_ua_intlck_ctrl = DA_EMULATE_UA_INTLLCK_CTRL;
-	dev->se_sub_dev->se_dev_attrib.emulate_tas = DA_EMULATE_TAS;
-	dev->se_sub_dev->se_dev_attrib.emulate_tpu = DA_EMULATE_TPU;
-	dev->se_sub_dev->se_dev_attrib.emulate_tpws = DA_EMULATE_TPWS;
-	dev->se_sub_dev->se_dev_attrib.emulate_reservations = DA_EMULATE_RESERVATIONS;
-	dev->se_sub_dev->se_dev_attrib.emulate_alua = DA_EMULATE_ALUA;
-	dev->se_sub_dev->se_dev_attrib.enforce_pr_isids = DA_ENFORCE_PR_ISIDS;
-	dev->se_sub_dev->se_dev_attrib.is_nonrot = DA_IS_NONROT;
-	dev->se_sub_dev->se_dev_attrib.emulate_rest_reord = DA_EMULATE_REST_REORD;
-	/*
-	 * The TPU=1 and TPWS=1 settings will be set in TCM/IBLOCK
-	 * iblock_create_virtdevice() from struct queue_limits values
-	 * if blk_queue_discard()==1
-	 */
-	dev->se_sub_dev->se_dev_attrib.max_unmap_lba_count = DA_MAX_UNMAP_LBA_COUNT;
-	dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count =
-		DA_MAX_UNMAP_BLOCK_DESC_COUNT;
-	dev->se_sub_dev->se_dev_attrib.unmap_granularity = DA_UNMAP_GRANULARITY_DEFAULT;
-	dev->se_sub_dev->se_dev_attrib.unmap_granularity_alignment =
-				DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT;
-	/*
-	 * block_size is based on subsystem plugin dependent requirements.
-	 */
-	dev->se_sub_dev->se_dev_attrib.hw_block_size = limits->logical_block_size;
-	dev->se_sub_dev->se_dev_attrib.block_size = limits->logical_block_size;
-	/*
-	 * Align max_hw_sectors down to PAGE_SIZE I/O transfers
-	 */
-	limits->max_hw_sectors = se_dev_align_max_sectors(limits->max_hw_sectors,
-						limits->logical_block_size);
-	dev->se_sub_dev->se_dev_attrib.hw_max_sectors = limits->max_hw_sectors;
-
-	/*
-	 * Set fabric_max_sectors, which is reported in block limits
-	 * VPD page (B0h).
-	 */
-	dev->se_sub_dev->se_dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS;
-	/*
-	 * Set optimal_sectors from fabric_max_sectors, which can be
-	 * lowered via configfs.
-	 */
-	dev->se_sub_dev->se_dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS;
-	/*
-	 * queue_depth is based on subsystem plugin dependent requirements.
-	 */
-	dev->se_sub_dev->se_dev_attrib.hw_queue_depth = dev_limits->hw_queue_depth;
-	dev->se_sub_dev->se_dev_attrib.queue_depth = dev_limits->queue_depth;
-}
-
 int se_dev_set_max_unmap_lba_count(
 	struct se_device *dev,
 	u32 max_unmap_lba_count)
 {
-	dev->se_sub_dev->se_dev_attrib.max_unmap_lba_count = max_unmap_lba_count;
+	dev->dev_attrib.max_unmap_lba_count = max_unmap_lba_count;
 	pr_debug("dev[%p]: Set max_unmap_lba_count: %u\n",
-			dev, dev->se_sub_dev->se_dev_attrib.max_unmap_lba_count);
+			dev, dev->dev_attrib.max_unmap_lba_count);
 	return 0;
 }
 
@@ -939,10 +754,10 @@ int se_dev_set_max_unmap_block_desc_count(
 	struct se_device *dev,
 	u32 max_unmap_block_desc_count)
 {
-	dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count =
+	dev->dev_attrib.max_unmap_block_desc_count =
 		max_unmap_block_desc_count;
 	pr_debug("dev[%p]: Set max_unmap_block_desc_count: %u\n",
-			dev, dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count);
+			dev, dev->dev_attrib.max_unmap_block_desc_count);
 	return 0;
 }
 
@@ -950,9 +765,9 @@ int se_dev_set_unmap_granularity(
 	struct se_device *dev,
 	u32 unmap_granularity)
 {
-	dev->se_sub_dev->se_dev_attrib.unmap_granularity = unmap_granularity;
+	dev->dev_attrib.unmap_granularity = unmap_granularity;
 	pr_debug("dev[%p]: Set unmap_granularity: %u\n",
-			dev, dev->se_sub_dev->se_dev_attrib.unmap_granularity);
+			dev, dev->dev_attrib.unmap_granularity);
 	return 0;
 }
 
@@ -960,9 +775,9 @@ int se_dev_set_unmap_granularity_alignment(
 	struct se_device *dev,
 	u32 unmap_granularity_alignment)
 {
-	dev->se_sub_dev->se_dev_attrib.unmap_granularity_alignment = unmap_granularity_alignment;
+	dev->dev_attrib.unmap_granularity_alignment = unmap_granularity_alignment;
 	pr_debug("dev[%p]: Set unmap_granularity_alignment: %u\n",
-			dev, dev->se_sub_dev->se_dev_attrib.unmap_granularity_alignment);
+			dev, dev->dev_attrib.unmap_granularity_alignment);
 	return 0;
 }
 
@@ -993,9 +808,9 @@ int se_dev_set_emulate_fua_write(struct se_device *dev, int flag)
 		pr_err("emulate_fua_write not supported for pSCSI\n");
 		return -EINVAL;
 	}
-	dev->se_sub_dev->se_dev_attrib.emulate_fua_write = flag;
+	dev->dev_attrib.emulate_fua_write = flag;
 	pr_debug("dev[%p]: SE Device Forced Unit Access WRITEs: %d\n",
-			dev, dev->se_sub_dev->se_dev_attrib.emulate_fua_write);
+			dev, dev->dev_attrib.emulate_fua_write);
 	return 0;
 }
 
@@ -1025,9 +840,9 @@ int se_dev_set_emulate_write_cache(struct se_device *dev, int flag)
 		pr_err("emulate_write_cache not supported for pSCSI\n");
 		return -EINVAL;
 	}
-	dev->se_sub_dev->se_dev_attrib.emulate_write_cache = flag;
+	dev->dev_attrib.emulate_write_cache = flag;
 	pr_debug("dev[%p]: SE Device WRITE_CACHE_EMULATION flag: %d\n",
-			dev, dev->se_sub_dev->se_dev_attrib.emulate_write_cache);
+			dev, dev->dev_attrib.emulate_write_cache);
 	return 0;
 }
 
@@ -1038,16 +853,15 @@ int se_dev_set_emulate_ua_intlck_ctrl(struct se_device *dev, int flag)
 		return -EINVAL;
 	}
 
-	if (atomic_read(&dev->dev_export_obj.obj_access_count)) {
+	if (dev->export_count) {
 		pr_err("dev[%p]: Unable to change SE Device"
-			" UA_INTRLCK_CTRL while dev_export_obj: %d count"
-			" exists\n", dev,
-			atomic_read(&dev->dev_export_obj.obj_access_count));
+			" UA_INTRLCK_CTRL while export_count is %d\n",
+			dev, dev->export_count);
 		return -EINVAL;
 	}
-	dev->se_sub_dev->se_dev_attrib.emulate_ua_intlck_ctrl = flag;
+	dev->dev_attrib.emulate_ua_intlck_ctrl = flag;
 	pr_debug("dev[%p]: SE Device UA_INTRLCK_CTRL flag: %d\n",
-		dev, dev->se_sub_dev->se_dev_attrib.emulate_ua_intlck_ctrl);
+		dev, dev->dev_attrib.emulate_ua_intlck_ctrl);
 
 	return 0;
 }
@@ -1059,15 +873,15 @@ int se_dev_set_emulate_tas(struct se_device *dev, int flag)
 		return -EINVAL;
 	}
 
-	if (atomic_read(&dev->dev_export_obj.obj_access_count)) {
+	if (dev->export_count) {
 		pr_err("dev[%p]: Unable to change SE Device TAS while"
-			" dev_export_obj: %d count exists\n", dev,
-			atomic_read(&dev->dev_export_obj.obj_access_count));
+			" export_count is %d\n",
+			dev, dev->export_count);
 		return -EINVAL;
 	}
-	dev->se_sub_dev->se_dev_attrib.emulate_tas = flag;
+	dev->dev_attrib.emulate_tas = flag;
 	pr_debug("dev[%p]: SE Device TASK_ABORTED status bit: %s\n",
-		dev, (dev->se_sub_dev->se_dev_attrib.emulate_tas) ? "Enabled" : "Disabled");
+		dev, (dev->dev_attrib.emulate_tas) ? "Enabled" : "Disabled");
 
 	return 0;
 }
@@ -1082,12 +896,12 @@ int se_dev_set_emulate_tpu(struct se_device *dev, int flag)
 	 * We expect this value to be non-zero when generic Block Layer
 	 * Discard supported is detected iblock_create_virtdevice().
 	 */
-	if (flag && !dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count) {
+	if (flag && !dev->dev_attrib.max_unmap_block_desc_count) {
 		pr_err("Generic Block Discard not supported\n");
 		return -ENOSYS;
 	}
 
-	dev->se_sub_dev->se_dev_attrib.emulate_tpu = flag;
+	dev->dev_attrib.emulate_tpu = flag;
 	pr_debug("dev[%p]: SE Device Thin Provisioning UNMAP bit: %d\n",
 				dev, flag);
 	return 0;
@@ -1103,12 +917,12 @@ int se_dev_set_emulate_tpws(struct se_device *dev, int flag)
 	 * We expect this value to be non-zero when generic Block Layer
 	 * Discard supported is detected iblock_create_virtdevice().
 	 */
-	if (flag && !dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count) {
+	if (flag && !dev->dev_attrib.max_unmap_block_desc_count) {
 		pr_err("Generic Block Discard not supported\n");
 		return -ENOSYS;
 	}
 
-	dev->se_sub_dev->se_dev_attrib.emulate_tpws = flag;
+	dev->dev_attrib.emulate_tpws = flag;
 	pr_debug("dev[%p]: SE Device Thin Provisioning WRITE_SAME: %d\n",
 				dev, flag);
 	return 0;
@@ -1120,9 +934,9 @@ int se_dev_set_enforce_pr_isids(struct se_device *dev, int flag)
 		pr_err("Illegal value %d\n", flag);
 		return -EINVAL;
 	}
-	dev->se_sub_dev->se_dev_attrib.enforce_pr_isids = flag;
+	dev->dev_attrib.enforce_pr_isids = flag;
 	pr_debug("dev[%p]: SE Device enforce_pr_isids bit: %s\n", dev,
-		(dev->se_sub_dev->se_dev_attrib.enforce_pr_isids) ? "Enabled" : "Disabled");
+		(dev->dev_attrib.enforce_pr_isids) ? "Enabled" : "Disabled");
 	return 0;
 }
 
@@ -1132,7 +946,7 @@ int se_dev_set_is_nonrot(struct se_device *dev, int flag)
 		printk(KERN_ERR "Illegal value %d\n", flag);
 		return -EINVAL;
 	}
-	dev->se_sub_dev->se_dev_attrib.is_nonrot = flag;
+	dev->dev_attrib.is_nonrot = flag;
 	pr_debug("dev[%p]: SE Device is_nonrot bit: %d\n",
 	       dev, flag);
 	return 0;
@@ -1145,7 +959,7 @@ int se_dev_set_emulate_rest_reord(struct se_device *dev, int flag)
 			" reordering not implemented\n", dev);
 		return -ENOSYS;
 	}
-	dev->se_sub_dev->se_dev_attrib.emulate_rest_reord = flag;
+	dev->dev_attrib.emulate_rest_reord = flag;
 	pr_debug("dev[%p]: SE Device emulate_rest_reord: %d\n", dev, flag);
 	return 0;
 }
@@ -1155,10 +969,10 @@ int se_dev_set_emulate_rest_reord(struct se_device *dev, int flag)
  */
 int se_dev_set_queue_depth(struct se_device *dev, u32 queue_depth)
 {
-	if (atomic_read(&dev->dev_export_obj.obj_access_count)) {
+	if (dev->export_count) {
 		pr_err("dev[%p]: Unable to change SE Device TCQ while"
-			" dev_export_obj: %d count exists\n", dev,
-			atomic_read(&dev->dev_export_obj.obj_access_count));
+			" export_count is %d\n",
+			dev, dev->export_count);
 		return -EINVAL;
 	}
 	if (!queue_depth) {
@@ -1168,26 +982,26 @@ int se_dev_set_queue_depth(struct se_device *dev, u32 queue_depth)
 	}
 
 	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) {
-		if (queue_depth > dev->se_sub_dev->se_dev_attrib.hw_queue_depth) {
+		if (queue_depth > dev->dev_attrib.hw_queue_depth) {
 			pr_err("dev[%p]: Passed queue_depth: %u"
 				" exceeds TCM/SE_Device TCQ: %u\n",
 				dev, queue_depth,
-				dev->se_sub_dev->se_dev_attrib.hw_queue_depth);
+				dev->dev_attrib.hw_queue_depth);
 			return -EINVAL;
 		}
 	} else {
-		if (queue_depth > dev->se_sub_dev->se_dev_attrib.queue_depth) {
-			if (queue_depth > dev->se_sub_dev->se_dev_attrib.hw_queue_depth) {
+		if (queue_depth > dev->dev_attrib.queue_depth) {
+			if (queue_depth > dev->dev_attrib.hw_queue_depth) {
 				pr_err("dev[%p]: Passed queue_depth:"
 					" %u exceeds TCM/SE_Device MAX"
 					" TCQ: %u\n", dev, queue_depth,
-					dev->se_sub_dev->se_dev_attrib.hw_queue_depth);
+					dev->dev_attrib.hw_queue_depth);
 				return -EINVAL;
 			}
 		}
 	}
 
-	dev->se_sub_dev->se_dev_attrib.queue_depth = dev->queue_depth = queue_depth;
+	dev->dev_attrib.queue_depth = dev->queue_depth = queue_depth;
 	pr_debug("dev[%p]: SE Device TCQ Depth changed to: %u\n",
 			dev, queue_depth);
 	return 0;
@@ -1195,10 +1009,10 @@ int se_dev_set_queue_depth(struct se_device *dev, u32 queue_depth)
 
 int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors)
 {
-	if (atomic_read(&dev->dev_export_obj.obj_access_count)) {
+	if (dev->export_count) {
 		pr_err("dev[%p]: Unable to change SE Device"
-			" fabric_max_sectors while dev_export_obj: %d count exists\n",
-			dev, atomic_read(&dev->dev_export_obj.obj_access_count));
+			" fabric_max_sectors while export_count is %d\n",
+			dev, dev->export_count);
 		return -EINVAL;
 	}
 	if (!fabric_max_sectors) {
@@ -1213,11 +1027,11 @@ int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors)
 		return -EINVAL;
 	}
 	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) {
-		if (fabric_max_sectors > dev->se_sub_dev->se_dev_attrib.hw_max_sectors) {
+		if (fabric_max_sectors > dev->dev_attrib.hw_max_sectors) {
 			pr_err("dev[%p]: Passed fabric_max_sectors: %u"
 				" greater than TCM/SE_Device max_sectors:"
 				" %u\n", dev, fabric_max_sectors,
-				dev->se_sub_dev->se_dev_attrib.hw_max_sectors);
+				dev->dev_attrib.hw_max_sectors);
 			 return -EINVAL;
 		}
 	} else {
@@ -1233,9 +1047,9 @@ int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors)
 	 * Align max_sectors down to PAGE_SIZE to follow transport_allocate_data_tasks()
 	 */
 	fabric_max_sectors = se_dev_align_max_sectors(fabric_max_sectors,
-						      dev->se_sub_dev->se_dev_attrib.block_size);
+						      dev->dev_attrib.block_size);
 
-	dev->se_sub_dev->se_dev_attrib.fabric_max_sectors = fabric_max_sectors;
+	dev->dev_attrib.fabric_max_sectors = fabric_max_sectors;
 	pr_debug("dev[%p]: SE Device max_sectors changed to %u\n",
 			dev, fabric_max_sectors);
 	return 0;
@@ -1243,10 +1057,10 @@ int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors)
 
 int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors)
 {
-	if (atomic_read(&dev->dev_export_obj.obj_access_count)) {
+	if (dev->export_count) {
 		pr_err("dev[%p]: Unable to change SE Device"
-			" optimal_sectors while dev_export_obj: %d count exists\n",
-			dev, atomic_read(&dev->dev_export_obj.obj_access_count));
+			" optimal_sectors while export_count is %d\n",
+			dev, dev->export_count);
 		return -EINVAL;
 	}
 	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) {
@@ -1254,14 +1068,14 @@ int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors)
 				" changed for TCM/pSCSI\n", dev);
 		return -EINVAL;
 	}
-	if (optimal_sectors > dev->se_sub_dev->se_dev_attrib.fabric_max_sectors) {
+	if (optimal_sectors > dev->dev_attrib.fabric_max_sectors) {
 		pr_err("dev[%p]: Passed optimal_sectors %u cannot be"
 			" greater than fabric_max_sectors: %u\n", dev,
-			optimal_sectors, dev->se_sub_dev->se_dev_attrib.fabric_max_sectors);
+			optimal_sectors, dev->dev_attrib.fabric_max_sectors);
 		return -EINVAL;
 	}
 
-	dev->se_sub_dev->se_dev_attrib.optimal_sectors = optimal_sectors;
+	dev->dev_attrib.optimal_sectors = optimal_sectors;
 	pr_debug("dev[%p]: SE Device optimal_sectors changed to %u\n",
 			dev, optimal_sectors);
 	return 0;
@@ -1269,10 +1083,10 @@ int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors)
 
 int se_dev_set_block_size(struct se_device *dev, u32 block_size)
 {
-	if (atomic_read(&dev->dev_export_obj.obj_access_count)) {
+	if (dev->export_count) {
 		pr_err("dev[%p]: Unable to change SE Device block_size"
-			" while dev_export_obj: %d count exists\n", dev,
-			atomic_read(&dev->dev_export_obj.obj_access_count));
+			" while export_count is %d\n",
+			dev, dev->export_count);
 		return -EINVAL;
 	}
 
@@ -1293,7 +1107,7 @@ int se_dev_set_block_size(struct se_device *dev, u32 block_size)
 		return -EINVAL;
 	}
 
-	dev->se_sub_dev->se_dev_attrib.block_size = block_size;
+	dev->dev_attrib.block_size = block_size;
 	pr_debug("dev[%p]: SE Device block_size changed to %u\n",
 			dev, block_size);
 	return 0;
@@ -1307,12 +1121,6 @@ struct se_lun *core_dev_add_lun(
 	struct se_lun *lun_p;
 	int rc;
 
-	if (atomic_read(&dev->dev_access_obj.obj_access_count) != 0) {
-		pr_err("Unable to export struct se_device while dev_access_obj: %d\n",
-			atomic_read(&dev->dev_access_obj.obj_access_count));
-		return ERR_PTR(-EACCES);
-	}
-
 	lun_p = core_tpg_pre_addlun(tpg, lun);
 	if (IS_ERR(lun_p))
 		return lun_p;
@@ -1568,12 +1376,220 @@ void core_dev_free_initiator_node_lun_acl(
 	kfree(lacl);
 }
 
+static void scsi_dump_inquiry(struct se_device *dev)
+{
+	struct t10_wwn *wwn = &dev->t10_wwn;
+	char buf[17];
+	int i, device_type;
+	/*
+	 * Print Linux/SCSI style INQUIRY formatting to the kernel ring buffer
+	 */
+	for (i = 0; i < 8; i++)
+		if (wwn->vendor[i] >= 0x20)
+			buf[i] = wwn->vendor[i];
+		else
+			buf[i] = ' ';
+	buf[i] = '\0';
+	pr_debug("  Vendor: %s\n", buf);
+
+	for (i = 0; i < 16; i++)
+		if (wwn->model[i] >= 0x20)
+			buf[i] = wwn->model[i];
+		else
+			buf[i] = ' ';
+	buf[i] = '\0';
+	pr_debug("  Model: %s\n", buf);
+
+	for (i = 0; i < 4; i++)
+		if (wwn->revision[i] >= 0x20)
+			buf[i] = wwn->revision[i];
+		else
+			buf[i] = ' ';
+	buf[i] = '\0';
+	pr_debug("  Revision: %s\n", buf);
+
+	device_type = dev->transport->get_device_type(dev);
+	pr_debug("  Type:   %s ", scsi_device_type(device_type));
+	pr_debug("                 ANSI SCSI revision: %02x\n",
+				dev->transport->get_device_rev(dev));
+}
+
+struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
+{
+	struct se_device *dev;
+
+	dev = hba->transport->alloc_device(hba, name);
+	if (!dev)
+		return NULL;
+
+	dev->se_hba = hba;
+	dev->transport = hba->transport;
+
+	INIT_LIST_HEAD(&dev->dev_list);
+	INIT_LIST_HEAD(&dev->dev_sep_list);
+	INIT_LIST_HEAD(&dev->dev_tmr_list);
+	INIT_LIST_HEAD(&dev->delayed_cmd_list);
+	INIT_LIST_HEAD(&dev->state_list);
+	INIT_LIST_HEAD(&dev->qf_cmd_list);
+	spin_lock_init(&dev->stats_lock);
+	spin_lock_init(&dev->execute_task_lock);
+	spin_lock_init(&dev->delayed_cmd_lock);
+	spin_lock_init(&dev->dev_reservation_lock);
+	spin_lock_init(&dev->se_port_lock);
+	spin_lock_init(&dev->se_tmr_lock);
+	spin_lock_init(&dev->qf_cmd_lock);
+	atomic_set(&dev->dev_ordered_id, 0);
+	INIT_LIST_HEAD(&dev->t10_wwn.t10_vpd_list);
+	spin_lock_init(&dev->t10_wwn.t10_vpd_lock);
+	INIT_LIST_HEAD(&dev->t10_pr.registration_list);
+	INIT_LIST_HEAD(&dev->t10_pr.aptpl_reg_list);
+	spin_lock_init(&dev->t10_pr.registration_lock);
+	spin_lock_init(&dev->t10_pr.aptpl_reg_lock);
+	INIT_LIST_HEAD(&dev->t10_alua.tg_pt_gps_list);
+	spin_lock_init(&dev->t10_alua.tg_pt_gps_lock);
+
+	dev->t10_pr.pr_aptpl_buf_len = PR_APTPL_BUF_LEN;
+	dev->t10_wwn.t10_dev = dev;
+	dev->t10_alua.t10_dev = dev;
+
+	dev->dev_attrib.da_dev = dev;
+	dev->dev_attrib.emulate_dpo = DA_EMULATE_DPO;
+	dev->dev_attrib.emulate_fua_write = DA_EMULATE_FUA_WRITE;
+	dev->dev_attrib.emulate_fua_read = DA_EMULATE_FUA_READ;
+	dev->dev_attrib.emulate_write_cache = DA_EMULATE_WRITE_CACHE;
+	dev->dev_attrib.emulate_ua_intlck_ctrl = DA_EMULATE_UA_INTLLCK_CTRL;
+	dev->dev_attrib.emulate_tas = DA_EMULATE_TAS;
+	dev->dev_attrib.emulate_tpu = DA_EMULATE_TPU;
+	dev->dev_attrib.emulate_tpws = DA_EMULATE_TPWS;
+	dev->dev_attrib.emulate_reservations = DA_EMULATE_RESERVATIONS;
+	dev->dev_attrib.emulate_alua = DA_EMULATE_ALUA;
+	dev->dev_attrib.enforce_pr_isids = DA_ENFORCE_PR_ISIDS;
+	dev->dev_attrib.is_nonrot = DA_IS_NONROT;
+	dev->dev_attrib.emulate_rest_reord = DA_EMULATE_REST_REORD;
+	dev->dev_attrib.max_unmap_lba_count = DA_MAX_UNMAP_LBA_COUNT;
+	dev->dev_attrib.max_unmap_block_desc_count =
+		DA_MAX_UNMAP_BLOCK_DESC_COUNT;
+	dev->dev_attrib.unmap_granularity = DA_UNMAP_GRANULARITY_DEFAULT;
+	dev->dev_attrib.unmap_granularity_alignment =
+				DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT;
+	dev->dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS;
+	dev->dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS;
+
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+		dev->dev_task_attr_type = SAM_TASK_ATTR_PASSTHROUGH;
+	else
+		dev->dev_task_attr_type = SAM_TASK_ATTR_EMULATED;
+
+	return dev;
+}
+
+int target_configure_device(struct se_device *dev)
+{
+	struct se_hba *hba = dev->se_hba;
+	int ret;
+
+	if (dev->dev_flags & DF_CONFIGURED) {
+		pr_err("se_dev->se_dev_ptr already set for storage"
+				" object\n");
+		return -EEXIST;
+	}
+
+	ret = dev->transport->configure_device(dev);
+	if (ret)
+		goto out;
+	dev->dev_flags |= DF_CONFIGURED;
+
+	/*
+	 * XXX: there is not much point to have two different values here..
+	 */
+	dev->dev_attrib.block_size = dev->dev_attrib.hw_block_size;
+	dev->dev_attrib.queue_depth = dev->dev_attrib.hw_queue_depth;
+
+	/*
+	 * Align max_hw_sectors down to PAGE_SIZE I/O transfers
+	 */
+	dev->dev_attrib.hw_max_sectors =
+		se_dev_align_max_sectors(dev->dev_attrib.hw_max_sectors,
+					 dev->dev_attrib.hw_block_size);
+
+	dev->dev_index = scsi_get_new_index(SCSI_DEVICE_INDEX);
+	dev->creation_time = get_jiffies_64();
+
+	core_setup_reservations(dev);
+
+	ret = core_setup_alua(dev);
+	if (ret)
+		goto out;
+
+	/*
+	 * Startup the struct se_device processing thread
+	 */
+	dev->tmr_wq = alloc_workqueue("tmr-%s", WQ_MEM_RECLAIM | WQ_UNBOUND, 1,
+				      dev->transport->name);
+	if (!dev->tmr_wq) {
+		pr_err("Unable to create tmr workqueue for %s\n",
+			dev->transport->name);
+		ret = -ENOMEM;
+		goto out_free_alua;
+	}
+
+	/*
+	 * Setup work_queue for QUEUE_FULL
+	 */
+	INIT_WORK(&dev->qf_work_queue, target_qf_do_work);
+
+	/*
+	 * Preload the initial INQUIRY const values if we are doing
+	 * anything virtual (IBLOCK, FILEIO, RAMDISK), but not for TCM/pSCSI
+	 * passthrough because this is being provided by the backend LLD.
+	 */
+	if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV) {
+		strncpy(&dev->t10_wwn.vendor[0], "LIO-ORG", 8);
+		strncpy(&dev->t10_wwn.model[0],
+			dev->transport->inquiry_prod, 16);
+		strncpy(&dev->t10_wwn.revision[0],
+			dev->transport->inquiry_rev, 4);
+	}
+
+	scsi_dump_inquiry(dev);
+
+	spin_lock(&hba->device_lock);
+	hba->dev_count++;
+	spin_unlock(&hba->device_lock);
+	return 0;
+
+out_free_alua:
+	core_alua_free_lu_gp_mem(dev);
+out:
+	se_release_vpd_for_dev(dev);
+	return ret;
+}
+
+void target_free_device(struct se_device *dev)
+{
+	struct se_hba *hba = dev->se_hba;
+
+	WARN_ON(!list_empty(&dev->dev_sep_list));
+
+	if (dev->dev_flags & DF_CONFIGURED) {
+		destroy_workqueue(dev->tmr_wq);
+
+		spin_lock(&hba->device_lock);
+		hba->dev_count--;
+		spin_unlock(&hba->device_lock);
+	}
+
+	core_alua_free_lu_gp_mem(dev);
+	core_scsi3_free_all_registrations(dev);
+	se_release_vpd_for_dev(dev);
+
+	dev->transport->free_device(dev);
+}
+
 int core_dev_setup_virtual_lun0(void)
 {
 	struct se_hba *hba;
 	struct se_device *dev;
-	struct se_subsystem_dev *se_dev = NULL;
-	struct se_subsystem_api *t;
 	char buf[16];
 	int ret;
 
@@ -1581,60 +1597,28 @@ int core_dev_setup_virtual_lun0(void)
 	if (IS_ERR(hba))
 		return PTR_ERR(hba);
 
-	lun0_hba = hba;
-	t = hba->transport;
-
-	se_dev = kzalloc(sizeof(struct se_subsystem_dev), GFP_KERNEL);
-	if (!se_dev) {
-		pr_err("Unable to allocate memory for"
-				" struct se_subsystem_dev\n");
+	dev = target_alloc_device(hba, "virt_lun0");
+	if (!dev) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_free_hba;
 	}
-	INIT_LIST_HEAD(&se_dev->t10_wwn.t10_vpd_list);
-	spin_lock_init(&se_dev->t10_wwn.t10_vpd_lock);
-	INIT_LIST_HEAD(&se_dev->t10_pr.registration_list);
-	INIT_LIST_HEAD(&se_dev->t10_pr.aptpl_reg_list);
-	spin_lock_init(&se_dev->t10_pr.registration_lock);
-	spin_lock_init(&se_dev->t10_pr.aptpl_reg_lock);
-	INIT_LIST_HEAD(&se_dev->t10_alua.tg_pt_gps_list);
-	spin_lock_init(&se_dev->t10_alua.tg_pt_gps_lock);
-	spin_lock_init(&se_dev->se_dev_lock);
-	se_dev->t10_pr.pr_aptpl_buf_len = PR_APTPL_BUF_LEN;
-	se_dev->t10_wwn.t10_sub_dev = se_dev;
-	se_dev->t10_alua.t10_sub_dev = se_dev;
-	se_dev->se_dev_attrib.da_sub_dev = se_dev;
-	se_dev->se_dev_hba = hba;
-
-	se_dev->se_dev_su_ptr = t->allocate_virtdevice(hba, "virt_lun0");
-	if (!se_dev->se_dev_su_ptr) {
-		pr_err("Unable to locate subsystem dependent pointer"
-			" from allocate_virtdevice()\n");
-		ret = -ENOMEM;
-		goto out;
-	}
-	lun0_su_dev = se_dev;
 
 	memset(buf, 0, 16);
 	sprintf(buf, "rd_pages=8");
-	t->set_configfs_dev_params(hba, se_dev, buf, sizeof(buf));
+	hba->transport->set_configfs_dev_params(dev, buf, sizeof(buf));
 
-	dev = t->create_virtdevice(hba, se_dev, se_dev->se_dev_su_ptr);
-	if (IS_ERR(dev)) {
-		ret = PTR_ERR(dev);
-		goto out;
-	}
-	se_dev->se_dev_ptr = dev;
-	g_lun0_dev = dev;
+	ret = target_configure_device(dev);
+	if (ret)
+		goto out_free_se_dev;
 
+	lun0_hba = hba;
+	g_lun0_dev = dev;
 	return 0;
-out:
-	lun0_su_dev = NULL;
-	kfree(se_dev);
-	if (lun0_hba) {
-		core_delete_hba(lun0_hba);
-		lun0_hba = NULL;
-	}
+
+out_free_se_dev:
+	target_free_device(dev);
+out_free_hba:
+	core_delete_hba(hba);
 	return ret;
 }
 
@@ -1642,14 +1626,11 @@ out:
 void core_dev_release_virtual_lun0(void)
 {
 	struct se_hba *hba = lun0_hba;
-	struct se_subsystem_dev *su_dev = lun0_su_dev;
 
 	if (!hba)
 		return;
 
 	if (g_lun0_dev)
-		se_free_virtual_device(g_lun0_dev, hba);
-
-	kfree(su_dev);
+		target_free_device(g_lun0_dev);
 	core_delete_hba(hba);
 }
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index bca737bb813d..aa6731337f84 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -734,14 +734,12 @@ static int target_fabric_port_link(
 	struct config_item *se_dev_ci)
 {
 	struct config_item *tpg_ci;
-	struct se_device *dev;
 	struct se_lun *lun = container_of(to_config_group(lun_ci),
 				struct se_lun, lun_group);
 	struct se_lun *lun_p;
 	struct se_portal_group *se_tpg;
-	struct se_subsystem_dev *se_dev = container_of(
-				to_config_group(se_dev_ci), struct se_subsystem_dev,
-				se_dev_group);
+	struct se_device *dev =
+		container_of(to_config_group(se_dev_ci), struct se_device, dev_group);
 	struct target_fabric_configfs *tf;
 	int ret;
 
@@ -755,14 +753,6 @@ static int target_fabric_port_link(
 		return -EEXIST;
 	}
 
-	dev = se_dev->se_dev_ptr;
-	if (!dev) {
-		pr_err("Unable to locate struct se_device pointer from"
-			" %s\n", config_item_name(se_dev_ci));
-		ret = -ENODEV;
-		goto out;
-	}
-
 	lun_p = core_dev_add_lun(se_tpg, dev, lun->unpacked_lun);
 	if (IS_ERR(lun_p)) {
 		pr_err("core_dev_add_lun() failed\n");
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 0360383dfb94..a89d80dacad2 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -41,7 +41,10 @@
 
 #include "target_core_file.h"
 
-static struct se_subsystem_api fileio_template;
+static inline struct fd_dev *FD_DEV(struct se_device *dev)
+{
+	return container_of(dev, struct fd_dev, dev);
+}
 
 /*	fd_attach_hba(): (Part of se_subsystem_api_t template)
  *
@@ -82,7 +85,7 @@ static void fd_detach_hba(struct se_hba *hba)
 	hba->hba_ptr = NULL;
 }
 
-static void *fd_allocate_virtdevice(struct se_hba *hba, const char *name)
+static struct se_device *fd_alloc_device(struct se_hba *hba, const char *name)
 {
 	struct fd_dev *fd_dev;
 	struct fd_host *fd_host = hba->hba_ptr;
@@ -97,34 +100,28 @@ static void *fd_allocate_virtdevice(struct se_hba *hba, const char *name)
 
 	pr_debug("FILEIO: Allocated fd_dev for %p\n", name);
 
-	return fd_dev;
+	return &fd_dev->dev;
 }
 
-/*	fd_create_virtdevice(): (Part of se_subsystem_api_t template)
- *
- *
- */
-static struct se_device *fd_create_virtdevice(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev,
-	void *p)
+static int fd_configure_device(struct se_device *dev)
 {
-	struct se_device *dev;
-	struct se_dev_limits dev_limits;
-	struct queue_limits *limits;
-	struct fd_dev *fd_dev = p;
-	struct fd_host *fd_host = hba->hba_ptr;
+	struct fd_dev *fd_dev = FD_DEV(dev);
+	struct fd_host *fd_host = dev->se_hba->hba_ptr;
 	struct file *file;
 	struct inode *inode = NULL;
-	int dev_flags = 0, flags, ret = -EINVAL;
+	int flags, ret = -EINVAL;
 
-	memset(&dev_limits, 0, sizeof(struct se_dev_limits));
+	if (!(fd_dev->fbd_flags & FBDF_HAS_PATH)) {
+		pr_err("Missing fd_dev_name=\n");
+		return -EINVAL;
+	}
 
 	/*
 	 * Use O_DSYNC by default instead of O_SYNC to forgo syncing
 	 * of pure timestamp updates.
 	 */
 	flags = O_RDWR | O_CREAT | O_LARGEFILE | O_DSYNC;
+
 	/*
 	 * Optionally allow fd_buffered_io=1 to be enabled for people
 	 * who want use the fs buffer cache as an WriteCache mechanism.
@@ -154,22 +151,17 @@ static struct se_device *fd_create_virtdevice(
 	 */
 	inode = file->f_mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
-		struct request_queue *q;
+		struct request_queue *q = bdev_get_queue(inode->i_bdev);
 		unsigned long long dev_size;
-		/*
-		 * Setup the local scope queue_limits from struct request_queue->limits
-		 * to pass into transport_add_device_to_core_hba() as struct se_dev_limits.
-		 */
-		q = bdev_get_queue(inode->i_bdev);
-		limits = &dev_limits.limits;
-		limits->logical_block_size = bdev_logical_block_size(inode->i_bdev);
-		limits->max_hw_sectors = queue_max_hw_sectors(q);
-		limits->max_sectors = queue_max_sectors(q);
+
+		dev->dev_attrib.hw_block_size =
+			bdev_logical_block_size(inode->i_bdev);
+		dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q);
+
 		/*
 		 * Determine the number of bytes from i_size_read() minus
 		 * one (1) logical sector from underlying struct block_device
 		 */
-		fd_dev->fd_block_size = bdev_logical_block_size(inode->i_bdev);
 		dev_size = (i_size_read(file->f_mapping->host) -
 				       fd_dev->fd_block_size);
 
@@ -185,26 +177,18 @@ static struct se_device *fd_create_virtdevice(
 			goto fail;
 		}
 
-		limits = &dev_limits.limits;
-		limits->logical_block_size = FD_BLOCKSIZE;
-		limits->max_hw_sectors = FD_MAX_SECTORS;
-		limits->max_sectors = FD_MAX_SECTORS;
-		fd_dev->fd_block_size = FD_BLOCKSIZE;
+		dev->dev_attrib.hw_block_size = FD_BLOCKSIZE;
+		dev->dev_attrib.hw_max_sectors = FD_MAX_SECTORS;
 	}
 
-	dev_limits.hw_queue_depth = FD_MAX_DEVICE_QUEUE_DEPTH;
-	dev_limits.queue_depth = FD_DEVICE_QUEUE_DEPTH;
+	fd_dev->fd_block_size = dev->dev_attrib.hw_block_size;
 
-	dev = transport_add_device_to_core_hba(hba, &fileio_template,
-				se_dev, dev_flags, fd_dev,
-				&dev_limits, "FILEIO", FD_VERSION);
-	if (!dev)
-		goto fail;
+	dev->dev_attrib.hw_queue_depth = FD_MAX_DEVICE_QUEUE_DEPTH;
 
 	if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
 		pr_debug("FILEIO: Forcing setting of emulate_write_cache=1"
 			" with FDBD_HAS_BUFFERED_IO_WCE\n");
-		dev->se_sub_dev->se_dev_attrib.emulate_write_cache = 1;
+		dev->dev_attrib.emulate_write_cache = 1;
 	}
 
 	fd_dev->fd_dev_id = fd_host->fd_host_dev_id_count++;
@@ -214,22 +198,18 @@ static struct se_device *fd_create_virtdevice(
 		" %llu total bytes\n", fd_host->fd_host_id, fd_dev->fd_dev_id,
 			fd_dev->fd_dev_name, fd_dev->fd_dev_size);
 
-	return dev;
+	return 0;
 fail:
 	if (fd_dev->fd_file) {
 		filp_close(fd_dev->fd_file, NULL);
 		fd_dev->fd_file = NULL;
 	}
-	return ERR_PTR(ret);
+	return ret;
 }
 
-/*	fd_free_device(): (Part of se_subsystem_api_t template)
- *
- *
- */
-static void fd_free_device(void *p)
+static void fd_free_device(struct se_device *dev)
 {
-	struct fd_dev *fd_dev = p;
+	struct fd_dev *fd_dev = FD_DEV(dev);
 
 	if (fd_dev->fd_file) {
 		filp_close(fd_dev->fd_file, NULL);
@@ -243,13 +223,12 @@ static int fd_do_readv(struct se_cmd *cmd, struct scatterlist *sgl,
 		u32 sgl_nents)
 {
 	struct se_device *se_dev = cmd->se_dev;
-	struct fd_dev *dev = se_dev->dev_ptr;
+	struct fd_dev *dev = FD_DEV(se_dev);
 	struct file *fd = dev->fd_file;
 	struct scatterlist *sg;
 	struct iovec *iov;
 	mm_segment_t old_fs;
-	loff_t pos = (cmd->t_task_lba *
-		      se_dev->se_sub_dev->se_dev_attrib.block_size);
+	loff_t pos = (cmd->t_task_lba * se_dev->dev_attrib.block_size);
 	int ret = 0, i;
 
 	iov = kzalloc(sizeof(struct iovec) * sgl_nents, GFP_KERNEL);
@@ -296,13 +275,12 @@ static int fd_do_writev(struct se_cmd *cmd, struct scatterlist *sgl,
 		u32 sgl_nents)
 {
 	struct se_device *se_dev = cmd->se_dev;
-	struct fd_dev *dev = se_dev->dev_ptr;
+	struct fd_dev *dev = FD_DEV(se_dev);
 	struct file *fd = dev->fd_file;
 	struct scatterlist *sg;
 	struct iovec *iov;
 	mm_segment_t old_fs;
-	loff_t pos = (cmd->t_task_lba *
-		      se_dev->se_sub_dev->se_dev_attrib.block_size);
+	loff_t pos = (cmd->t_task_lba * se_dev->dev_attrib.block_size);
 	int ret, i = 0;
 
 	iov = kzalloc(sizeof(struct iovec) * sgl_nents, GFP_KERNEL);
@@ -334,7 +312,7 @@ static int fd_do_writev(struct se_cmd *cmd, struct scatterlist *sgl,
 static int fd_execute_sync_cache(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
-	struct fd_dev *fd_dev = dev->dev_ptr;
+	struct fd_dev *fd_dev = FD_DEV(dev);
 	int immed = (cmd->t_task_cdb[1] & 0x2);
 	loff_t start, end;
 	int ret;
@@ -353,7 +331,7 @@ static int fd_execute_sync_cache(struct se_cmd *cmd)
 		start = 0;
 		end = LLONG_MAX;
 	} else {
-		start = cmd->t_task_lba * dev->se_sub_dev->se_dev_attrib.block_size;
+		start = cmd->t_task_lba * dev->dev_attrib.block_size;
 		if (cmd->data_length)
 			end = start + cmd->data_length;
 		else
@@ -399,11 +377,11 @@ static int fd_execute_rw(struct se_cmd *cmd)
 		 * Allow this to happen independent of WCE=0 setting.
 		 */
 		if (ret > 0 &&
-		    dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0 &&
+		    dev->dev_attrib.emulate_fua_write > 0 &&
 		    (cmd->se_cmd_flags & SCF_FUA)) {
-			struct fd_dev *fd_dev = dev->dev_ptr;
+			struct fd_dev *fd_dev = FD_DEV(dev);
 			loff_t start = cmd->t_task_lba *
-				dev->se_sub_dev->se_dev_attrib.block_size;
+				dev->dev_attrib.block_size;
 			loff_t end = start + cmd->data_length;
 
 			vfs_fsync_range(fd_dev->fd_file, start, end, 1);
@@ -430,12 +408,10 @@ static match_table_t tokens = {
 	{Opt_err, NULL}
 };
 
-static ssize_t fd_set_configfs_dev_params(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev,
-	const char *page, ssize_t count)
+static ssize_t fd_set_configfs_dev_params(struct se_device *dev,
+		const char *page, ssize_t count)
 {
-	struct fd_dev *fd_dev = se_dev->se_dev_su_ptr;
+	struct fd_dev *fd_dev = FD_DEV(dev);
 	char *orig, *ptr, *arg_p, *opts;
 	substring_t args[MAX_OPT_ARGS];
 	int ret = 0, arg, token;
@@ -502,24 +478,9 @@ out:
 	return (!ret) ? count : ret;
 }
 
-static ssize_t fd_check_configfs_dev_params(struct se_hba *hba, struct se_subsystem_dev *se_dev)
-{
-	struct fd_dev *fd_dev = se_dev->se_dev_su_ptr;
-
-	if (!(fd_dev->fbd_flags & FBDF_HAS_PATH)) {
-		pr_err("Missing fd_dev_name=\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static ssize_t fd_show_configfs_dev_params(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev,
-	char *b)
+static ssize_t fd_show_configfs_dev_params(struct se_device *dev, char *b)
 {
-	struct fd_dev *fd_dev = se_dev->se_dev_su_ptr;
+	struct fd_dev *fd_dev = FD_DEV(dev);
 	ssize_t bl = 0;
 
 	bl = sprintf(b + bl, "TCM FILEIO ID: %u", fd_dev->fd_dev_id);
@@ -550,7 +511,7 @@ static u32 fd_get_device_type(struct se_device *dev)
 
 static sector_t fd_get_blocks(struct se_device *dev)
 {
-	struct fd_dev *fd_dev = dev->dev_ptr;
+	struct fd_dev *fd_dev = FD_DEV(dev);
 	struct file *f = fd_dev->fd_file;
 	struct inode *i = f->f_mapping->host;
 	unsigned long long dev_size;
@@ -564,7 +525,7 @@ static sector_t fd_get_blocks(struct se_device *dev)
 	else
 		dev_size = fd_dev->fd_dev_size;
 
-	return div_u64(dev_size, dev->se_sub_dev->se_dev_attrib.block_size);
+	return div_u64(dev_size, dev->dev_attrib.block_size);
 }
 
 static struct spc_ops fd_spc_ops = {
@@ -579,15 +540,16 @@ static int fd_parse_cdb(struct se_cmd *cmd)
 
 static struct se_subsystem_api fileio_template = {
 	.name			= "fileio",
+	.inquiry_prod		= "FILEIO",
+	.inquiry_rev		= FD_VERSION,
 	.owner			= THIS_MODULE,
 	.transport_type		= TRANSPORT_PLUGIN_VHBA_PDEV,
 	.attach_hba		= fd_attach_hba,
 	.detach_hba		= fd_detach_hba,
-	.allocate_virtdevice	= fd_allocate_virtdevice,
-	.create_virtdevice	= fd_create_virtdevice,
+	.alloc_device		= fd_alloc_device,
+	.configure_device	= fd_configure_device,
 	.free_device		= fd_free_device,
 	.parse_cdb		= fd_parse_cdb,
-	.check_configfs_dev_params = fd_check_configfs_dev_params,
 	.set_configfs_dev_params = fd_set_configfs_dev_params,
 	.show_configfs_dev_params = fd_show_configfs_dev_params,
 	.get_device_rev		= fd_get_device_rev,
diff --git a/drivers/target/target_core_file.h b/drivers/target/target_core_file.h
index 876ae53ef5b8..bc02b018ae46 100644
--- a/drivers/target/target_core_file.h
+++ b/drivers/target/target_core_file.h
@@ -17,6 +17,8 @@
 #define FDBD_HAS_BUFFERED_IO_WCE 0x04
 
 struct fd_dev {
+	struct se_device dev;
+
 	u32		fbd_flags;
 	unsigned char	fd_dev_name[FD_MAX_DEV_NAME];
 	/* Unique Ramdisk Device ID in Ramdisk HBA */
diff --git a/drivers/target/target_core_hba.c b/drivers/target/target_core_hba.c
index 3dd1bd4b6f71..048b7b4b9102 100644
--- a/drivers/target/target_core_hba.c
+++ b/drivers/target/target_core_hba.c
@@ -113,7 +113,6 @@ core_alloc_hba(const char *plugin_name, u32 plugin_dep_id, u32 hba_flags)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	INIT_LIST_HEAD(&hba->hba_dev_list);
 	spin_lock_init(&hba->device_lock);
 	mutex_init(&hba->hba_access_mutex);
 
@@ -152,8 +151,7 @@ out_free_hba:
 int
 core_delete_hba(struct se_hba *hba)
 {
-	if (!list_empty(&hba->hba_dev_list))
-		dump_stack();
+	WARN_ON(hba->dev_count);
 
 	hba->transport->detach_hba(hba);
 
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 57d7674c5013..dd6cd92cd9d8 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -50,6 +50,12 @@
 #define IBLOCK_MAX_BIO_PER_TASK	 32	/* max # of bios to submit at a time */
 #define IBLOCK_BIO_POOL_SIZE	128
 
+static inline struct iblock_dev *IBLOCK_DEV(struct se_device *dev)
+{
+	return container_of(dev, struct iblock_dev, dev);
+}
+
+
 static struct se_subsystem_api iblock_template;
 
 static void iblock_bio_done(struct bio *, int);
@@ -70,7 +76,7 @@ static void iblock_detach_hba(struct se_hba *hba)
 {
 }
 
-static void *iblock_allocate_virtdevice(struct se_hba *hba, const char *name)
+static struct se_device *iblock_alloc_device(struct se_hba *hba, const char *name)
 {
 	struct iblock_dev *ib_dev = NULL;
 
@@ -82,40 +88,28 @@ static void *iblock_allocate_virtdevice(struct se_hba *hba, const char *name)
 
 	pr_debug( "IBLOCK: Allocated ib_dev for %s\n", name);
 
-	return ib_dev;
+	return &ib_dev->dev;
 }
 
-static struct se_device *iblock_create_virtdevice(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev,
-	void *p)
+static int iblock_configure_device(struct se_device *dev)
 {
-	struct iblock_dev *ib_dev = p;
-	struct se_device *dev;
-	struct se_dev_limits dev_limits;
-	struct block_device *bd = NULL;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 	struct request_queue *q;
-	struct queue_limits *limits;
-	u32 dev_flags = 0;
+	struct block_device *bd = NULL;
 	fmode_t mode;
-	int ret = -EINVAL;
+	int ret = -ENOMEM;
 
-	if (!ib_dev) {
-		pr_err("Unable to locate struct iblock_dev parameter\n");
-		return ERR_PTR(ret);
+	if (!(ib_dev->ibd_flags & IBDF_HAS_UDEV_PATH)) {
+		pr_err("Missing udev_path= parameters for IBLOCK\n");
+		return -EINVAL;
 	}
-	memset(&dev_limits, 0, sizeof(struct se_dev_limits));
 
 	ib_dev->ibd_bio_set = bioset_create(IBLOCK_BIO_POOL_SIZE, 0);
 	if (!ib_dev->ibd_bio_set) {
-		pr_err("IBLOCK: Unable to create bioset()\n");
-		return ERR_PTR(-ENOMEM);
+		pr_err("IBLOCK: Unable to create bioset\n");
+		goto out;
 	}
-	pr_debug("IBLOCK: Created bio_set()\n");
-	/*
-	 * iblock_check_configfs_dev_params() ensures that ib_dev->ibd_udev_path
-	 * must already have been set in order for echo 1 > $HBA/$DEV/enable to run.
-	 */
+
 	pr_debug( "IBLOCK: Claiming struct block_device: %s\n",
 			ib_dev->ibd_udev_path);
 
@@ -126,27 +120,15 @@ static struct se_device *iblock_create_virtdevice(
 	bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev);
 	if (IS_ERR(bd)) {
 		ret = PTR_ERR(bd);
-		goto failed;
+		goto out_free_bioset;
 	}
-	/*
-	 * Setup the local scope queue_limits from struct request_queue->limits
-	 * to pass into transport_add_device_to_core_hba() as struct se_dev_limits.
-	 */
-	q = bdev_get_queue(bd);
-	limits = &dev_limits.limits;
-	limits->logical_block_size = bdev_logical_block_size(bd);
-	limits->max_hw_sectors = UINT_MAX;
-	limits->max_sectors = UINT_MAX;
-	dev_limits.hw_queue_depth = q->nr_requests;
-	dev_limits.queue_depth = q->nr_requests;
-
 	ib_dev->ibd_bd = bd;
 
-	dev = transport_add_device_to_core_hba(hba,
-			&iblock_template, se_dev, dev_flags, ib_dev,
-			&dev_limits, "IBLOCK", IBLOCK_VERSION);
-	if (!dev)
-		goto failed;
+	q = bdev_get_queue(bd);
+
+	dev->dev_attrib.hw_block_size = bdev_logical_block_size(bd);
+	dev->dev_attrib.hw_max_sectors = UINT_MAX;
+	dev->dev_attrib.hw_queue_depth = q->nr_requests;
 
 	/*
 	 * Check if the underlying struct block_device request_queue supports
@@ -154,15 +136,16 @@ static struct se_device *iblock_create_virtdevice(
 	 * in ATA and we need to set TPE=1
 	 */
 	if (blk_queue_discard(q)) {
-		dev->se_sub_dev->se_dev_attrib.max_unmap_lba_count =
+		dev->dev_attrib.max_unmap_lba_count =
 				q->limits.max_discard_sectors;
+
 		/*
 		 * Currently hardcoded to 1 in Linux/SCSI code..
 		 */
-		dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count = 1;
-		dev->se_sub_dev->se_dev_attrib.unmap_granularity =
+		dev->dev_attrib.max_unmap_block_desc_count = 1;
+		dev->dev_attrib.unmap_granularity =
 				q->limits.discard_granularity >> 9;
-		dev->se_sub_dev->se_dev_attrib.unmap_granularity_alignment =
+		dev->dev_attrib.unmap_granularity_alignment =
 				q->limits.discard_alignment;
 
 		pr_debug("IBLOCK: BLOCK Discard support available,"
@@ -170,22 +153,19 @@ static struct se_device *iblock_create_virtdevice(
 	}
 
 	if (blk_queue_nonrot(q))
-		dev->se_sub_dev->se_dev_attrib.is_nonrot = 1;
-
-	return dev;
+		dev->dev_attrib.is_nonrot = 1;
+	return 0;
 
-failed:
-	if (ib_dev->ibd_bio_set) {
-		bioset_free(ib_dev->ibd_bio_set);
-		ib_dev->ibd_bio_set = NULL;
-	}
-	ib_dev->ibd_bd = NULL;
-	return ERR_PTR(ret);
+out_free_bioset:
+	bioset_free(ib_dev->ibd_bio_set);
+	ib_dev->ibd_bio_set = NULL;
+out:
+	return ret;
 }
 
-static void iblock_free_device(void *p)
+static void iblock_free_device(struct se_device *dev)
 {
-	struct iblock_dev *ib_dev = p;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 
 	if (ib_dev->ibd_bd != NULL)
 		blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
@@ -203,12 +183,12 @@ static unsigned long long iblock_emulate_read_cap_with_block_size(
 					bdev_logical_block_size(bd)) - 1);
 	u32 block_size = bdev_logical_block_size(bd);
 
-	if (block_size == dev->se_sub_dev->se_dev_attrib.block_size)
+	if (block_size == dev->dev_attrib.block_size)
 		return blocks_long;
 
 	switch (block_size) {
 	case 4096:
-		switch (dev->se_sub_dev->se_dev_attrib.block_size) {
+		switch (dev->dev_attrib.block_size) {
 		case 2048:
 			blocks_long <<= 1;
 			break;
@@ -222,7 +202,7 @@ static unsigned long long iblock_emulate_read_cap_with_block_size(
 		}
 		break;
 	case 2048:
-		switch (dev->se_sub_dev->se_dev_attrib.block_size) {
+		switch (dev->dev_attrib.block_size) {
 		case 4096:
 			blocks_long >>= 1;
 			break;
@@ -237,7 +217,7 @@ static unsigned long long iblock_emulate_read_cap_with_block_size(
 		}
 		break;
 	case 1024:
-		switch (dev->se_sub_dev->se_dev_attrib.block_size) {
+		switch (dev->dev_attrib.block_size) {
 		case 4096:
 			blocks_long >>= 2;
 			break;
@@ -252,7 +232,7 @@ static unsigned long long iblock_emulate_read_cap_with_block_size(
 		}
 		break;
 	case 512:
-		switch (dev->se_sub_dev->se_dev_attrib.block_size) {
+		switch (dev->dev_attrib.block_size) {
 		case 4096:
 			blocks_long >>= 3;
 			break;
@@ -299,7 +279,7 @@ static void iblock_end_io_flush(struct bio *bio, int err)
  */
 static int iblock_execute_sync_cache(struct se_cmd *cmd)
 {
-	struct iblock_dev *ib_dev = cmd->se_dev->dev_ptr;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(cmd->se_dev);
 	int immed = (cmd->t_task_cdb[1] & 0x2);
 	struct bio *bio;
 
@@ -322,7 +302,7 @@ static int iblock_execute_sync_cache(struct se_cmd *cmd)
 static int iblock_execute_unmap(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
-	struct iblock_dev *ibd = dev->dev_ptr;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 	unsigned char *buf, *ptr = NULL;
 	sector_t lba;
 	int size;
@@ -349,7 +329,7 @@ static int iblock_execute_unmap(struct se_cmd *cmd)
 	else
 		size = bd_dl;
 
-	if (size / 16 > dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count) {
+	if (size / 16 > dev->dev_attrib.max_unmap_block_desc_count) {
 		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
 		ret = -EINVAL;
 		goto err;
@@ -366,7 +346,7 @@ static int iblock_execute_unmap(struct se_cmd *cmd)
 		pr_debug("UNMAP: Using lba: %llu and range: %u\n",
 				 (unsigned long long)lba, range);
 
-		if (range > dev->se_sub_dev->se_dev_attrib.max_unmap_lba_count) {
+		if (range > dev->dev_attrib.max_unmap_lba_count) {
 			cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
 			ret = -EINVAL;
 			goto err;
@@ -378,7 +358,7 @@ static int iblock_execute_unmap(struct se_cmd *cmd)
 			goto err;
 		}
 
-		ret = blkdev_issue_discard(ibd->ibd_bd, lba, range,
+		ret = blkdev_issue_discard(ib_dev->ibd_bd, lba, range,
 					   GFP_KERNEL, 0);
 		if (ret < 0) {
 			pr_err("blkdev_issue_discard() failed: %d\n",
@@ -399,10 +379,10 @@ err:
 
 static int iblock_execute_write_same(struct se_cmd *cmd)
 {
-	struct iblock_dev *ibd = cmd->se_dev->dev_ptr;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(cmd->se_dev);
 	int ret;
 
-	ret = blkdev_issue_discard(ibd->ibd_bd, cmd->t_task_lba,
+	ret = blkdev_issue_discard(ib_dev->ibd_bd, cmd->t_task_lba,
 				   spc_get_write_same_sectors(cmd), GFP_KERNEL,
 				   0);
 	if (ret < 0) {
@@ -425,11 +405,10 @@ static match_table_t tokens = {
 	{Opt_err, NULL}
 };
 
-static ssize_t iblock_set_configfs_dev_params(struct se_hba *hba,
-					       struct se_subsystem_dev *se_dev,
-					       const char *page, ssize_t count)
+static ssize_t iblock_set_configfs_dev_params(struct se_device *dev,
+		const char *page, ssize_t count)
 {
-	struct iblock_dev *ib_dev = se_dev->se_dev_su_ptr;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 	char *orig, *ptr, *arg_p, *opts;
 	substring_t args[MAX_OPT_ARGS];
 	int ret = 0, token;
@@ -491,43 +470,26 @@ out:
 	return (!ret) ? count : ret;
 }
 
-static ssize_t iblock_check_configfs_dev_params(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev)
-{
-	struct iblock_dev *ibd = se_dev->se_dev_su_ptr;
-
-	if (!(ibd->ibd_flags & IBDF_HAS_UDEV_PATH)) {
-		pr_err("Missing udev_path= parameters for IBLOCK\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static ssize_t iblock_show_configfs_dev_params(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev,
-	char *b)
+static ssize_t iblock_show_configfs_dev_params(struct se_device *dev, char *b)
 {
-	struct iblock_dev *ibd = se_dev->se_dev_su_ptr;
-	struct block_device *bd = ibd->ibd_bd;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	struct block_device *bd = ib_dev->ibd_bd;
 	char buf[BDEVNAME_SIZE];
 	ssize_t bl = 0;
 
 	if (bd)
 		bl += sprintf(b + bl, "iBlock device: %s",
 				bdevname(bd, buf));
-	if (ibd->ibd_flags & IBDF_HAS_UDEV_PATH)
+	if (ib_dev->ibd_flags & IBDF_HAS_UDEV_PATH)
 		bl += sprintf(b + bl, "  UDEV PATH: %s",
-				ibd->ibd_udev_path);
-	bl += sprintf(b + bl, "  readonly: %d\n", ibd->ibd_readonly);
+				ib_dev->ibd_udev_path);
+	bl += sprintf(b + bl, "  readonly: %d\n", ib_dev->ibd_readonly);
 
 	bl += sprintf(b + bl, "        ");
 	if (bd) {
 		bl += sprintf(b + bl, "Major: %d Minor: %d  %s\n",
 			MAJOR(bd->bd_dev), MINOR(bd->bd_dev), (!bd->bd_contains) ?
-			"" : (bd->bd_holder == ibd) ?
+			"" : (bd->bd_holder == ib_dev) ?
 			"CLAIMED: IBLOCK" : "CLAIMED: OS");
 	} else {
 		bl += sprintf(b + bl, "Major: 0 Minor: 0\n");
@@ -556,7 +518,7 @@ static void iblock_complete_cmd(struct se_cmd *cmd)
 static struct bio *
 iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num)
 {
-	struct iblock_dev *ib_dev = cmd->se_dev->dev_ptr;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(cmd->se_dev);
 	struct bio *bio;
 
 	/*
@@ -611,8 +573,8 @@ static int iblock_execute_rw(struct se_cmd *cmd)
 		 * Force data to disk if we pretend to not have a volatile
 		 * write cache, or the initiator set the Force Unit Access bit.
 		 */
-		if (dev->se_sub_dev->se_dev_attrib.emulate_write_cache == 0 ||
-		    (dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0 &&
+		if (dev->dev_attrib.emulate_write_cache == 0 ||
+		    (dev->dev_attrib.emulate_fua_write > 0 &&
 		     (cmd->se_cmd_flags & SCF_FUA)))
 			rw = WRITE_FUA;
 		else
@@ -625,17 +587,17 @@ static int iblock_execute_rw(struct se_cmd *cmd)
 	 * Convert the blocksize advertised to the initiator to the 512 byte
 	 * units unconditionally used by the Linux block layer.
 	 */
-	if (dev->se_sub_dev->se_dev_attrib.block_size == 4096)
+	if (dev->dev_attrib.block_size == 4096)
 		block_lba = (cmd->t_task_lba << 3);
-	else if (dev->se_sub_dev->se_dev_attrib.block_size == 2048)
+	else if (dev->dev_attrib.block_size == 2048)
 		block_lba = (cmd->t_task_lba << 2);
-	else if (dev->se_sub_dev->se_dev_attrib.block_size == 1024)
+	else if (dev->dev_attrib.block_size == 1024)
 		block_lba = (cmd->t_task_lba << 1);
-	else if (dev->se_sub_dev->se_dev_attrib.block_size == 512)
+	else if (dev->dev_attrib.block_size == 512)
 		block_lba = cmd->t_task_lba;
 	else {
 		pr_err("Unsupported SCSI -> BLOCK LBA conversion:"
-				" %u\n", dev->se_sub_dev->se_dev_attrib.block_size);
+				" %u\n", dev->dev_attrib.block_size);
 		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		return -ENOSYS;
 	}
@@ -714,8 +676,8 @@ static u32 iblock_get_device_type(struct se_device *dev)
 
 static sector_t iblock_get_blocks(struct se_device *dev)
 {
-	struct iblock_dev *ibd = dev->dev_ptr;
-	struct block_device *bd = ibd->ibd_bd;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	struct block_device *bd = ib_dev->ibd_bd;
 	struct request_queue *q = bdev_get_queue(bd);
 
 	return iblock_emulate_read_cap_with_block_size(dev, bd, q);
@@ -761,15 +723,16 @@ static int iblock_parse_cdb(struct se_cmd *cmd)
 
 static struct se_subsystem_api iblock_template = {
 	.name			= "iblock",
+	.inquiry_prod		= "IBLOCK",
+	.inquiry_rev		= IBLOCK_VERSION,
 	.owner			= THIS_MODULE,
 	.transport_type		= TRANSPORT_PLUGIN_VHBA_PDEV,
 	.attach_hba		= iblock_attach_hba,
 	.detach_hba		= iblock_detach_hba,
-	.allocate_virtdevice	= iblock_allocate_virtdevice,
-	.create_virtdevice	= iblock_create_virtdevice,
+	.alloc_device		= iblock_alloc_device,
+	.configure_device	= iblock_configure_device,
 	.free_device		= iblock_free_device,
 	.parse_cdb		= iblock_parse_cdb,
-	.check_configfs_dev_params = iblock_check_configfs_dev_params,
 	.set_configfs_dev_params = iblock_set_configfs_dev_params,
 	.show_configfs_dev_params = iblock_show_configfs_dev_params,
 	.get_device_rev		= iblock_get_device_rev,
diff --git a/drivers/target/target_core_iblock.h b/drivers/target/target_core_iblock.h
index 533627ae79ec..01c2afd81500 100644
--- a/drivers/target/target_core_iblock.h
+++ b/drivers/target/target_core_iblock.h
@@ -14,6 +14,7 @@ struct iblock_req {
 #define IBDF_HAS_UDEV_PATH		0x01
 
 struct iblock_dev {
+	struct se_device dev;
 	unsigned char ibd_udev_path[SE_UDEV_PATH_LEN];
 	u32	ibd_flags;
 	struct bio_set	*ibd_bio_set;
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 0fd428225d11..5854ed67af59 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -20,12 +20,6 @@ int	core_dev_export(struct se_device *, struct se_portal_group *,
 void	core_dev_unexport(struct se_device *, struct se_portal_group *,
 		struct se_lun *);
 int	target_report_luns(struct se_cmd *);
-void	se_release_device_for_hba(struct se_device *);
-void	se_release_vpd_for_dev(struct se_device *);
-int	se_free_virtual_device(struct se_device *, struct se_hba *);
-int	se_dev_check_online(struct se_device *);
-int	se_dev_check_shutdown(struct se_device *);
-void	se_dev_set_default_attribs(struct se_device *, struct se_dev_limits *);
 int	se_dev_set_task_timeout(struct se_device *, u32);
 int	se_dev_set_max_unmap_lba_count(struct se_device *, u32);
 int	se_dev_set_max_unmap_block_desc_count(struct se_device *, u32);
@@ -60,6 +54,9 @@ void	core_dev_free_initiator_node_lun_acl(struct se_portal_group *,
 		struct se_lun_acl *lacl);
 int	core_dev_setup_virtual_lun0(void);
 void	core_dev_release_virtual_lun0(void);
+struct se_device *target_alloc_device(struct se_hba *hba, const char *name);
+int	target_configure_device(struct se_device *dev);
+void	target_free_device(struct se_device *);
 
 /* target_core_hba.c */
 struct se_hba *core_alloc_hba(const char *, u32, u32);
@@ -106,9 +103,10 @@ bool	target_stop_cmd(struct se_cmd *cmd, unsigned long *flags);
 int	transport_clear_lun_from_sessions(struct se_lun *);
 void	transport_send_task_abort(struct se_cmd *);
 int	target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
+void	target_qf_do_work(struct work_struct *work);
 
 /* target_core_stat.c */
-void	target_stat_setup_dev_default_groups(struct se_subsystem_dev *);
+void	target_stat_setup_dev_default_groups(struct se_device *);
 void	target_stat_setup_port_default_groups(struct se_lun *);
 void	target_stat_setup_mappedlun_default_groups(struct se_lun_acl *);
 
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 8c323a98c4a0..2b289891672f 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -103,7 +103,7 @@ static int core_scsi2_reservation_check(struct se_cmd *cmd, u32 *pr_reg_type)
 		spin_unlock(&dev->dev_reservation_lock);
 		return -EINVAL;
 	}
-	if (!(dev->dev_flags & DF_SPC2_RESERVATIONS_WITH_ISID)) {
+	if (!(dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS_WITH_ISID)) {
 		spin_unlock(&dev->dev_reservation_lock);
 		return 0;
 	}
@@ -120,10 +120,10 @@ static void core_scsi3_put_pr_reg(struct t10_pr_registration *);
 static int target_check_scsi2_reservation_conflict(struct se_cmd *cmd)
 {
 	struct se_session *se_sess = cmd->se_sess;
-	struct se_subsystem_dev *su_dev = cmd->se_dev->se_sub_dev;
+	struct se_device *dev = cmd->se_dev;
 	struct t10_pr_registration *pr_reg;
-	struct t10_reservation *pr_tmpl = &su_dev->t10_pr;
-	int crh = (su_dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS);
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
+	int crh = (dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS);
 	int conflict = 0;
 
 	if (!crh)
@@ -223,10 +223,10 @@ int target_scsi2_reservation_release(struct se_cmd *cmd)
 		goto out_unlock;
 
 	dev->dev_reserved_node_acl = NULL;
-	dev->dev_flags &= ~DF_SPC2_RESERVATIONS;
-	if (dev->dev_flags & DF_SPC2_RESERVATIONS_WITH_ISID) {
+	dev->dev_reservation_flags &= ~DRF_SPC2_RESERVATIONS;
+	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS_WITH_ISID) {
 		dev->dev_res_bin_isid = 0;
-		dev->dev_flags &= ~DF_SPC2_RESERVATIONS_WITH_ISID;
+		dev->dev_reservation_flags &= ~DRF_SPC2_RESERVATIONS_WITH_ISID;
 	}
 	tpg = sess->se_tpg;
 	pr_debug("SCSI-2 Released reservation for %s LUN: %u ->"
@@ -292,10 +292,10 @@ int target_scsi2_reservation_reserve(struct se_cmd *cmd)
 	}
 
 	dev->dev_reserved_node_acl = sess->se_node_acl;
-	dev->dev_flags |= DF_SPC2_RESERVATIONS;
+	dev->dev_reservation_flags |= DRF_SPC2_RESERVATIONS;
 	if (sess->sess_bin_isid != 0) {
 		dev->dev_res_bin_isid = sess->sess_bin_isid;
-		dev->dev_flags |= DF_SPC2_RESERVATIONS_WITH_ISID;
+		dev->dev_reservation_flags |= DRF_SPC2_RESERVATIONS_WITH_ISID;
 	}
 	pr_debug("SCSI-2 Reserved %s LUN: %u -> MAPPED LUN: %u"
 		" for %s\n", tpg->se_tpg_tfo->get_fabric_name(),
@@ -333,7 +333,7 @@ static int core_scsi3_pr_seq_non_holder(
 	/*
 	 * A legacy SPC-2 reservation is being held.
 	 */
-	if (cmd->se_dev->dev_flags & DF_SPC2_RESERVATIONS)
+	if (cmd->se_dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
 		return core_scsi2_reservation_seq_non_holder(cmd,
 					cdb, pr_reg_type);
 
@@ -565,8 +565,8 @@ static int core_scsi3_pr_seq_non_holder(
 
 static u32 core_scsi3_pr_generation(struct se_device *dev)
 {
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
 	u32 prg;
+
 	/*
 	 * PRGeneration field shall contain the value of a 32-bit wrapping
 	 * counter mainted by the device server.
@@ -577,7 +577,7 @@ static u32 core_scsi3_pr_generation(struct se_device *dev)
 	 * See spc4r17 section 6.3.12 READ_KEYS service action
 	 */
 	spin_lock(&dev->dev_reservation_lock);
-	prg = su_dev->t10_pr.pr_generation++;
+	prg = dev->t10_pr.pr_generation++;
 	spin_unlock(&dev->dev_reservation_lock);
 
 	return prg;
@@ -596,7 +596,7 @@ static int core_scsi3_pr_reservation_check(
 	/*
 	 * A legacy SPC-2 reservation is being held.
 	 */
-	if (dev->dev_flags & DF_SPC2_RESERVATIONS)
+	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
 		return core_scsi2_reservation_check(cmd, pr_reg_type);
 
 	spin_lock(&dev->dev_reservation_lock);
@@ -636,7 +636,6 @@ static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	int all_tg_pt,
 	int aptpl)
 {
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
 	struct t10_pr_registration *pr_reg;
 
 	pr_reg = kmem_cache_zalloc(t10_pr_reg_cache, GFP_ATOMIC);
@@ -645,7 +644,7 @@ static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 		return NULL;
 	}
 
-	pr_reg->pr_aptpl_buf = kzalloc(su_dev->t10_pr.pr_aptpl_buf_len,
+	pr_reg->pr_aptpl_buf = kzalloc(dev->t10_pr.pr_aptpl_buf_len,
 					GFP_ATOMIC);
 	if (!pr_reg->pr_aptpl_buf) {
 		pr_err("Unable to allocate pr_reg->pr_aptpl_buf\n");
@@ -929,7 +928,7 @@ static int __core_scsi3_check_aptpl_registration(
 	struct se_dev_entry *deve)
 {
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp;
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	unsigned char i_port[PR_APTPL_MAX_IPORT_LEN];
 	unsigned char t_port[PR_APTPL_MAX_TPORT_LEN];
 	u16 tpgt;
@@ -996,11 +995,10 @@ int core_scsi3_check_aptpl_registration(
 	struct se_lun *lun,
 	struct se_lun_acl *lun_acl)
 {
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
 	struct se_node_acl *nacl = lun_acl->se_lun_nacl;
 	struct se_dev_entry *deve = nacl->device_list[lun_acl->mapped_lun];
 
-	if (su_dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
 		return 0;
 
 	return __core_scsi3_check_aptpl_registration(dev, tpg, lun,
@@ -1051,10 +1049,9 @@ static void __core_scsi3_add_registration(
 	int register_type,
 	int register_move)
 {
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
 	struct target_core_fabric_ops *tfo = nacl->se_tpg->se_tpg_tfo;
 	struct t10_pr_registration *pr_reg_tmp, *pr_reg_tmp_safe;
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 
 	/*
 	 * Increment PRgeneration counter for struct se_device upon a successful
@@ -1066,7 +1063,7 @@ static void __core_scsi3_add_registration(
 	 * for the REGISTER.
 	 */
 	pr_reg->pr_res_generation = (register_move) ?
-			su_dev->t10_pr.pr_generation++ :
+			dev->t10_pr.pr_generation++ :
 			core_scsi3_pr_generation(dev);
 
 	spin_lock(&pr_tmpl->registration_lock);
@@ -1135,7 +1132,7 @@ static struct t10_pr_registration *__core_scsi3_locate_pr_reg(
 	struct se_node_acl *nacl,
 	unsigned char *isid)
 {
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp;
 	struct se_portal_group *tpg;
 
@@ -1160,7 +1157,7 @@ static struct t10_pr_registration *__core_scsi3_locate_pr_reg(
 			 * for fabric modules (iSCSI) requiring them.
 			 */
 			if (tpg->se_tpg_tfo->sess_get_initiator_sid != NULL) {
-				if (dev->se_sub_dev->se_dev_attrib.enforce_pr_isids)
+				if (dev->dev_attrib.enforce_pr_isids)
 					continue;
 			}
 			atomic_inc(&pr_reg->pr_res_holders);
@@ -1274,7 +1271,7 @@ static void __core_scsi3_free_registration(
 {
 	struct target_core_fabric_ops *tfo =
 			pr_reg->pr_reg_nacl->se_tpg->se_tpg_tfo;
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	char i_buf[PR_REG_ISID_ID_LEN];
 	int prf_isid;
 
@@ -1335,7 +1332,7 @@ void core_scsi3_free_pr_reg_from_nacl(
 	struct se_device *dev,
 	struct se_node_acl *nacl)
 {
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp, *pr_res_holder;
 	/*
 	 * If the passed se_node_acl matches the reservation holder,
@@ -1365,7 +1362,7 @@ void core_scsi3_free_pr_reg_from_nacl(
 void core_scsi3_free_all_registrations(
 	struct se_device *dev)
 {
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp, *pr_res_holder;
 
 	spin_lock(&dev->dev_reservation_lock);
@@ -1899,7 +1896,6 @@ static int __core_scsi3_update_aptpl_buf(
 {
 	struct se_lun *lun;
 	struct se_portal_group *tpg;
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
 	struct t10_pr_registration *pr_reg;
 	unsigned char tmp[512], isid_buf[32];
 	ssize_t len = 0;
@@ -1917,8 +1913,8 @@ static int __core_scsi3_update_aptpl_buf(
 	/*
 	 * Walk the registration list..
 	 */
-	spin_lock(&su_dev->t10_pr.registration_lock);
-	list_for_each_entry(pr_reg, &su_dev->t10_pr.registration_list,
+	spin_lock(&dev->t10_pr.registration_lock);
+	list_for_each_entry(pr_reg, &dev->t10_pr.registration_list,
 			pr_reg_list) {
 
 		tmp[0] = '\0';
@@ -1963,7 +1959,7 @@ static int __core_scsi3_update_aptpl_buf(
 		if ((len + strlen(tmp) >= pr_aptpl_buf_len)) {
 			pr_err("Unable to update renaming"
 				" APTPL metadata\n");
-			spin_unlock(&su_dev->t10_pr.registration_lock);
+			spin_unlock(&dev->t10_pr.registration_lock);
 			return -EMSGSIZE;
 		}
 		len += sprintf(buf+len, "%s", tmp);
@@ -1981,13 +1977,13 @@ static int __core_scsi3_update_aptpl_buf(
 		if ((len + strlen(tmp) >= pr_aptpl_buf_len)) {
 			pr_err("Unable to update renaming"
 				" APTPL metadata\n");
-			spin_unlock(&su_dev->t10_pr.registration_lock);
+			spin_unlock(&dev->t10_pr.registration_lock);
 			return -EMSGSIZE;
 		}
 		len += sprintf(buf+len, "%s", tmp);
 		reg_count++;
 	}
-	spin_unlock(&su_dev->t10_pr.registration_lock);
+	spin_unlock(&dev->t10_pr.registration_lock);
 
 	if (!reg_count)
 		len += sprintf(buf+len, "No Registrations or Reservations");
@@ -2019,7 +2015,7 @@ static int __core_scsi3_write_aptpl_to_file(
 	unsigned char *buf,
 	u32 pr_aptpl_buf_len)
 {
-	struct t10_wwn *wwn = &dev->se_sub_dev->t10_wwn;
+	struct t10_wwn *wwn = &dev->t10_wwn;
 	struct file *file;
 	struct iovec iov[1];
 	mm_segment_t old_fs;
@@ -2120,7 +2116,7 @@ static int core_scsi3_emulate_pro_register(
 	struct se_lun *se_lun = cmd->se_lun;
 	struct se_portal_group *se_tpg;
 	struct t10_pr_registration *pr_reg, *pr_reg_p, *pr_reg_tmp, *pr_reg_e;
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	/* Used for APTPL metadata w/ UNREGISTER */
 	unsigned char *pr_aptpl_buf = NULL;
 	unsigned char isid_buf[PR_REG_ISID_LEN], *isid_ptr = NULL;
@@ -2434,7 +2430,7 @@ static int core_scsi3_pro_reserve(
 	struct se_session *se_sess = cmd->se_sess;
 	struct se_lun *se_lun = cmd->se_lun;
 	struct t10_pr_registration *pr_reg, *pr_res_holder;
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	char i_buf[PR_REG_ISID_ID_LEN];
 	int ret, prf_isid;
 
@@ -2667,7 +2663,7 @@ static int core_scsi3_emulate_pro_release(
 	struct se_session *se_sess = cmd->se_sess;
 	struct se_lun *se_lun = cmd->se_lun;
 	struct t10_pr_registration *pr_reg, *pr_reg_p, *pr_res_holder;
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	int ret, all_reg = 0;
 
 	if (!se_sess || !se_lun) {
@@ -2836,7 +2832,7 @@ static int core_scsi3_emulate_pro_clear(
 	struct se_device *dev = cmd->se_dev;
 	struct se_node_acl *pr_reg_nacl;
 	struct se_session *se_sess = cmd->se_sess;
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp, *pr_reg_n, *pr_res_holder;
 	u32 pr_res_mapped_lun = 0;
 	int calling_it_nexus = 0;
@@ -3006,7 +3002,7 @@ static int core_scsi3_pro_preempt(
 	struct se_session *se_sess = cmd->se_sess;
 	LIST_HEAD(preempt_and_abort_list);
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp, *pr_reg_n, *pr_res_holder;
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	u32 pr_res_mapped_lun = 0;
 	int all_reg = 0, calling_it_nexus = 0, released_regs = 0;
 	int prh_type = 0, prh_scope = 0, ret;
@@ -3358,7 +3354,7 @@ static int core_scsi3_emulate_pro_register_and_move(
 	struct se_portal_group *se_tpg, *dest_se_tpg = NULL;
 	struct target_core_fabric_ops *dest_tf_ops = NULL, *tf_ops;
 	struct t10_pr_registration *pr_reg, *pr_res_holder, *dest_pr_reg;
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	unsigned char *buf;
 	unsigned char *initiator_str;
 	char *iport_ptr = NULL, dest_iport[64], i_buf[PR_REG_ISID_ID_LEN];
@@ -3823,7 +3819,7 @@ int target_scsi3_emulate_pr_out(struct se_cmd *cmd)
 	 * initiator or service action and shall terminate with a RESERVATION
 	 * CONFLICT status.
 	 */
-	if (cmd->se_dev->dev_flags & DF_SPC2_RESERVATIONS) {
+	if (cmd->se_dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS) {
 		pr_err("Received PERSISTENT_RESERVE CDB while legacy"
 			" SPC-2 reservation is held, returning"
 			" RESERVATION_CONFLICT\n");
@@ -3959,8 +3955,7 @@ out:
  */
 static int core_scsi3_pri_read_keys(struct se_cmd *cmd)
 {
-	struct se_device *se_dev = cmd->se_dev;
-	struct se_subsystem_dev *su_dev = se_dev->se_sub_dev;
+	struct se_device *dev = cmd->se_dev;
 	struct t10_pr_registration *pr_reg;
 	unsigned char *buf;
 	u32 add_len = 0, off = 8;
@@ -3973,13 +3968,13 @@ static int core_scsi3_pri_read_keys(struct se_cmd *cmd)
 	}
 
 	buf = transport_kmap_data_sg(cmd);
-	buf[0] = ((su_dev->t10_pr.pr_generation >> 24) & 0xff);
-	buf[1] = ((su_dev->t10_pr.pr_generation >> 16) & 0xff);
-	buf[2] = ((su_dev->t10_pr.pr_generation >> 8) & 0xff);
-	buf[3] = (su_dev->t10_pr.pr_generation & 0xff);
+	buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff);
+	buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff);
+	buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff);
+	buf[3] = (dev->t10_pr.pr_generation & 0xff);
 
-	spin_lock(&su_dev->t10_pr.registration_lock);
-	list_for_each_entry(pr_reg, &su_dev->t10_pr.registration_list,
+	spin_lock(&dev->t10_pr.registration_lock);
+	list_for_each_entry(pr_reg, &dev->t10_pr.registration_list,
 			pr_reg_list) {
 		/*
 		 * Check for overflow of 8byte PRI READ_KEYS payload and
@@ -3999,7 +3994,7 @@ static int core_scsi3_pri_read_keys(struct se_cmd *cmd)
 
 		add_len += 8;
 	}
-	spin_unlock(&su_dev->t10_pr.registration_lock);
+	spin_unlock(&dev->t10_pr.registration_lock);
 
 	buf[4] = ((add_len >> 24) & 0xff);
 	buf[5] = ((add_len >> 16) & 0xff);
@@ -4018,8 +4013,7 @@ static int core_scsi3_pri_read_keys(struct se_cmd *cmd)
  */
 static int core_scsi3_pri_read_reservation(struct se_cmd *cmd)
 {
-	struct se_device *se_dev = cmd->se_dev;
-	struct se_subsystem_dev *su_dev = se_dev->se_sub_dev;
+	struct se_device *dev = cmd->se_dev;
 	struct t10_pr_registration *pr_reg;
 	unsigned char *buf;
 	u64 pr_res_key;
@@ -4033,13 +4027,13 @@ static int core_scsi3_pri_read_reservation(struct se_cmd *cmd)
 	}
 
 	buf = transport_kmap_data_sg(cmd);
-	buf[0] = ((su_dev->t10_pr.pr_generation >> 24) & 0xff);
-	buf[1] = ((su_dev->t10_pr.pr_generation >> 16) & 0xff);
-	buf[2] = ((su_dev->t10_pr.pr_generation >> 8) & 0xff);
-	buf[3] = (su_dev->t10_pr.pr_generation & 0xff);
+	buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff);
+	buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff);
+	buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff);
+	buf[3] = (dev->t10_pr.pr_generation & 0xff);
 
-	spin_lock(&se_dev->dev_reservation_lock);
-	pr_reg = se_dev->dev_pr_res_holder;
+	spin_lock(&dev->dev_reservation_lock);
+	pr_reg = dev->dev_pr_res_holder;
 	if (pr_reg) {
 		/*
 		 * Set the hardcoded Additional Length
@@ -4090,7 +4084,7 @@ static int core_scsi3_pri_read_reservation(struct se_cmd *cmd)
 	}
 
 err:
-	spin_unlock(&se_dev->dev_reservation_lock);
+	spin_unlock(&dev->dev_reservation_lock);
 	transport_kunmap_data_sg(cmd);
 
 	return 0;
@@ -4104,7 +4098,7 @@ err:
 static int core_scsi3_pri_report_capabilities(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
-	struct t10_reservation *pr_tmpl = &dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	unsigned char *buf;
 	u16 add_len = 8; /* Hardcoded to 8. */
 
@@ -4159,12 +4153,11 @@ static int core_scsi3_pri_report_capabilities(struct se_cmd *cmd)
  */
 static int core_scsi3_pri_read_full_status(struct se_cmd *cmd)
 {
-	struct se_device *se_dev = cmd->se_dev;
+	struct se_device *dev = cmd->se_dev;
 	struct se_node_acl *se_nacl;
-	struct se_subsystem_dev *su_dev = se_dev->se_sub_dev;
 	struct se_portal_group *se_tpg;
 	struct t10_pr_registration *pr_reg, *pr_reg_tmp;
-	struct t10_reservation *pr_tmpl = &se_dev->se_sub_dev->t10_pr;
+	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	unsigned char *buf;
 	u32 add_desc_len = 0, add_len = 0, desc_len, exp_desc_len;
 	u32 off = 8; /* off into first Full Status descriptor */
@@ -4179,10 +4172,10 @@ static int core_scsi3_pri_read_full_status(struct se_cmd *cmd)
 
 	buf = transport_kmap_data_sg(cmd);
 
-	buf[0] = ((su_dev->t10_pr.pr_generation >> 24) & 0xff);
-	buf[1] = ((su_dev->t10_pr.pr_generation >> 16) & 0xff);
-	buf[2] = ((su_dev->t10_pr.pr_generation >> 8) & 0xff);
-	buf[3] = (su_dev->t10_pr.pr_generation & 0xff);
+	buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff);
+	buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff);
+	buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff);
+	buf[3] = (dev->t10_pr.pr_generation & 0xff);
 
 	spin_lock(&pr_tmpl->registration_lock);
 	list_for_each_entry_safe(pr_reg, pr_reg_tmp,
@@ -4316,7 +4309,7 @@ int target_scsi3_emulate_pr_in(struct se_cmd *cmd)
 	 * initiator or service action and shall terminate with a RESERVATION
 	 * CONFLICT status.
 	 */
-	if (cmd->se_dev->dev_flags & DF_SPC2_RESERVATIONS) {
+	if (cmd->se_dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS) {
 		pr_err("Received PERSISTENT_RESERVE CDB while legacy"
 			" SPC-2 reservation is held, returning"
 			" RESERVATION_CONFLICT\n");
@@ -4363,30 +4356,25 @@ static int core_pt_seq_non_holder(
 	return 0;
 }
 
-int core_setup_reservations(struct se_device *dev, int force_pt)
+void core_setup_reservations(struct se_device *dev)
 {
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
-	struct t10_reservation *rest = &su_dev->t10_pr;
+	struct t10_reservation *rest = &dev->t10_pr;
+
 	/*
 	 * If this device is from Target_Core_Mod/pSCSI, use the reservations
 	 * of the Underlying SCSI hardware.  In Linux/SCSI terms, this can
 	 * cause a problem because libata and some SATA RAID HBAs appear
 	 * under Linux/SCSI, but to emulate reservations themselves.
 	 */
-	if (((dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) &&
-	    !(dev->se_sub_dev->se_dev_attrib.emulate_reservations)) || force_pt) {
+	if ((dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE) ||
+	    (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV &&
+	     !dev->dev_attrib.emulate_reservations)) {
 		rest->res_type = SPC_PASSTHROUGH;
 		rest->pr_ops.t10_reservation_check = &core_pt_reservation_check;
 		rest->pr_ops.t10_seq_non_holder = &core_pt_seq_non_holder;
 		pr_debug("%s: Using SPC_PASSTHROUGH, no reservation"
 			" emulation\n", dev->transport->name);
-		return 0;
-	}
-	/*
-	 * If SPC-3 or above is reported by real or emulated struct se_device,
-	 * use emulated Persistent Reservations.
-	 */
-	if (dev->transport->get_device_rev(dev) >= SCSI_3) {
+	} else if (dev->transport->get_device_rev(dev) >= SCSI_3) {
 		rest->res_type = SPC3_PERSISTENT_RESERVATIONS;
 		rest->pr_ops.t10_reservation_check = &core_scsi3_pr_reservation_check;
 		rest->pr_ops.t10_seq_non_holder = &core_scsi3_pr_seq_non_holder;
@@ -4400,6 +4388,4 @@ int core_setup_reservations(struct se_device *dev, int force_pt)
 		pr_debug("%s: Using SPC2_RESERVATIONS emulation\n",
 			dev->transport->name);
 	}
-
-	return 0;
 }
diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h
index af6c460d886d..78451437d2c2 100644
--- a/drivers/target/target_core_pr.h
+++ b/drivers/target/target_core_pr.h
@@ -63,6 +63,6 @@ extern unsigned char *core_scsi3_pr_dump_type(int);
 
 extern int target_scsi3_emulate_pr_in(struct se_cmd *);
 extern int target_scsi3_emulate_pr_out(struct se_cmd *);
-extern int core_setup_reservations(struct se_device *, int);
+extern void core_setup_reservations(struct se_device *);
 
 #endif /* TARGET_CORE_PR_H */
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 617c086a8a02..b2965084eb4f 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -53,6 +53,11 @@
 
 #define ISPRINT(a)  ((a >= ' ') && (a <= '~'))
 
+static inline struct pscsi_dev_virt *PSCSI_DEV(struct se_device *dev)
+{
+	return container_of(dev, struct pscsi_dev_virt, dev);
+}
+
 static struct se_subsystem_api pscsi_template;
 
 static int pscsi_execute_cmd(struct se_cmd *cmd);
@@ -219,7 +224,7 @@ pscsi_get_inquiry_vpd_serial(struct scsi_device *sdev, struct t10_wwn *wwn)
 
 	snprintf(&wwn->unit_serial[0], INQUIRY_VPD_SERIAL_LEN, "%s", &buf[4]);
 
-	wwn->t10_sub_dev->su_dev_flags |= SDF_FIRMWARE_VPD_UNIT_SERIAL;
+	wwn->t10_dev->dev_flags |= DF_FIRMWARE_VPD_UNIT_SERIAL;
 
 	kfree(buf);
 	return 0;
@@ -299,23 +304,13 @@ out:
 	kfree(buf);
 }
 
-/*	pscsi_add_device_to_list():
- *
- *
- */
-static struct se_device *pscsi_add_device_to_list(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev,
-	struct pscsi_dev_virt *pdv,
-	struct scsi_device *sd,
-	int dev_flags)
+static int pscsi_add_device_to_list(struct se_device *dev,
+		struct scsi_device *sd)
 {
-	struct se_device *dev;
-	struct se_dev_limits dev_limits;
-	struct request_queue *q;
-	struct queue_limits *limits;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
+	struct request_queue *q = sd->request_queue;
 
-	memset(&dev_limits, 0, sizeof(struct se_dev_limits));
+	pdv->pdv_sd = sd;
 
 	if (!sd->queue_depth) {
 		sd->queue_depth = PSCSI_DEFAULT_QUEUEDEPTH;
@@ -324,54 +319,27 @@ static struct se_device *pscsi_add_device_to_list(
 			" queue_depth to %d\n", sd->channel, sd->id,
 				sd->lun, sd->queue_depth);
 	}
-	/*
-	 * Setup the local scope queue_limits from struct request_queue->limits
-	 * to pass into transport_add_device_to_core_hba() as struct se_dev_limits.
-	 */
-	q = sd->request_queue;
-	limits = &dev_limits.limits;
-	limits->logical_block_size = sd->sector_size;
-	limits->max_hw_sectors = min_t(int, sd->host->max_sectors, queue_max_hw_sectors(q));
-	limits->max_sectors = min_t(int, sd->host->max_sectors, queue_max_sectors(q));
-	dev_limits.hw_queue_depth = sd->queue_depth;
-	dev_limits.queue_depth = sd->queue_depth;
+
+	dev->dev_attrib.hw_block_size = sd->sector_size;
+	dev->dev_attrib.hw_max_sectors =
+		min_t(int, sd->host->max_sectors, queue_max_hw_sectors(q));
+	dev->dev_attrib.hw_queue_depth = sd->queue_depth;
+
 	/*
 	 * Setup our standard INQUIRY info into se_dev->t10_wwn
 	 */
-	pscsi_set_inquiry_info(sd, &se_dev->t10_wwn);
-
-	/*
-	 * Set the pointer pdv->pdv_sd to from passed struct scsi_device,
-	 * which has already been referenced with Linux SCSI code with
-	 * scsi_device_get() in this file's pscsi_create_virtdevice().
-	 *
-	 * The passthrough operations called by the transport_add_device_*
-	 * function below will require this pointer to be set for passthroug
-	 *  ops.
-	 *
-	 * For the shutdown case in pscsi_free_device(), this struct
-	 * scsi_device  reference is released with Linux SCSI code
-	 * scsi_device_put() and the pdv->pdv_sd cleared.
-	 */
-	pdv->pdv_sd = sd;
-	dev = transport_add_device_to_core_hba(hba, &pscsi_template,
-				se_dev, dev_flags, pdv,
-				&dev_limits, NULL, NULL);
-	if (!dev) {
-		pdv->pdv_sd = NULL;
-		return NULL;
-	}
+	pscsi_set_inquiry_info(sd, &dev->t10_wwn);
 
 	/*
 	 * Locate VPD WWN Information used for various purposes within
 	 * the Storage Engine.
 	 */
-	if (!pscsi_get_inquiry_vpd_serial(sd, &se_dev->t10_wwn)) {
+	if (!pscsi_get_inquiry_vpd_serial(sd, &dev->t10_wwn)) {
 		/*
 		 * If VPD Unit Serial returned GOOD status, try
 		 * VPD Device Identification page (0x83).
 		 */
-		pscsi_get_inquiry_vpd_device_ident(sd, &se_dev->t10_wwn);
+		pscsi_get_inquiry_vpd_device_ident(sd, &dev->t10_wwn);
 	}
 
 	/*
@@ -379,10 +347,11 @@ static struct se_device *pscsi_add_device_to_list(
 	 */
 	if (sd->type == TYPE_TAPE)
 		pscsi_tape_read_blocksize(dev, sd);
-	return dev;
+	return 0;
 }
 
-static void *pscsi_allocate_virtdevice(struct se_hba *hba, const char *name)
+static struct se_device *pscsi_alloc_device(struct se_hba *hba,
+		const char *name)
 {
 	struct pscsi_dev_virt *pdv;
 
@@ -391,139 +360,125 @@ static void *pscsi_allocate_virtdevice(struct se_hba *hba, const char *name)
 		pr_err("Unable to allocate memory for struct pscsi_dev_virt\n");
 		return NULL;
 	}
-	pdv->pdv_se_hba = hba;
 
 	pr_debug("PSCSI: Allocated pdv: %p for %s\n", pdv, name);
-	return pdv;
+	return &pdv->dev;
 }
 
 /*
  * Called with struct Scsi_Host->host_lock called.
  */
-static struct se_device *pscsi_create_type_disk(
-	struct scsi_device *sd,
-	struct pscsi_dev_virt *pdv,
-	struct se_subsystem_dev *se_dev,
-	struct se_hba *hba)
+static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
 	__releases(sh->host_lock)
 {
-	struct se_device *dev;
-	struct pscsi_hba_virt *phv = pdv->pdv_se_hba->hba_ptr;
+	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 	struct Scsi_Host *sh = sd->host;
 	struct block_device *bd;
-	u32 dev_flags = 0;
+	int ret;
 
 	if (scsi_device_get(sd)) {
 		pr_err("scsi_device_get() failed for %d:%d:%d:%d\n",
 			sh->host_no, sd->channel, sd->id, sd->lun);
 		spin_unlock_irq(sh->host_lock);
-		return NULL;
+		return -EIO;
 	}
 	spin_unlock_irq(sh->host_lock);
 	/*
 	 * Claim exclusive struct block_device access to struct scsi_device
 	 * for TYPE_DISK using supplied udev_path
 	 */
-	bd = blkdev_get_by_path(se_dev->se_dev_udev_path,
+	bd = blkdev_get_by_path(dev->udev_path,
 				FMODE_WRITE|FMODE_READ|FMODE_EXCL, pdv);
 	if (IS_ERR(bd)) {
 		pr_err("pSCSI: blkdev_get_by_path() failed\n");
 		scsi_device_put(sd);
-		return NULL;
+		return PTR_ERR(bd);
 	}
 	pdv->pdv_bd = bd;
 
-	dev = pscsi_add_device_to_list(hba, se_dev, pdv, sd, dev_flags);
-	if (!dev) {
+	ret = pscsi_add_device_to_list(dev, sd);
+	if (ret) {
 		blkdev_put(pdv->pdv_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
 		scsi_device_put(sd);
-		return NULL;
+		return ret;
 	}
+
 	pr_debug("CORE_PSCSI[%d] - Added TYPE_DISK for %d:%d:%d:%d\n",
 		phv->phv_host_id, sh->host_no, sd->channel, sd->id, sd->lun);
-
-	return dev;
+	return 0;
 }
 
 /*
  * Called with struct Scsi_Host->host_lock called.
  */
-static struct se_device *pscsi_create_type_rom(
-	struct scsi_device *sd,
-	struct pscsi_dev_virt *pdv,
-	struct se_subsystem_dev *se_dev,
-	struct se_hba *hba)
+static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd)
 	__releases(sh->host_lock)
 {
-	struct se_device *dev;
-	struct pscsi_hba_virt *phv = pdv->pdv_se_hba->hba_ptr;
+	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
 	struct Scsi_Host *sh = sd->host;
-	u32 dev_flags = 0;
+	int ret;
 
 	if (scsi_device_get(sd)) {
 		pr_err("scsi_device_get() failed for %d:%d:%d:%d\n",
 			sh->host_no, sd->channel, sd->id, sd->lun);
 		spin_unlock_irq(sh->host_lock);
-		return NULL;
+		return -EIO;
 	}
 	spin_unlock_irq(sh->host_lock);
 
-	dev = pscsi_add_device_to_list(hba, se_dev, pdv, sd, dev_flags);
-	if (!dev) {
+	ret = pscsi_add_device_to_list(dev, sd);
+	if (ret) {
 		scsi_device_put(sd);
-		return NULL;
+		return ret;
 	}
 	pr_debug("CORE_PSCSI[%d] - Added Type: %s for %d:%d:%d:%d\n",
 		phv->phv_host_id, scsi_device_type(sd->type), sh->host_no,
 		sd->channel, sd->id, sd->lun);
 
-	return dev;
+	return 0;
 }
 
 /*
- *Called with struct Scsi_Host->host_lock called.
+ * Called with struct Scsi_Host->host_lock called.
  */
-static struct se_device *pscsi_create_type_other(
-	struct scsi_device *sd,
-	struct pscsi_dev_virt *pdv,
-	struct se_subsystem_dev *se_dev,
-	struct se_hba *hba)
+static int pscsi_create_type_other(struct se_device *dev,
+		struct scsi_device *sd)
 	__releases(sh->host_lock)
 {
-	struct se_device *dev;
-	struct pscsi_hba_virt *phv = pdv->pdv_se_hba->hba_ptr;
+	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
 	struct Scsi_Host *sh = sd->host;
-	u32 dev_flags = 0;
+	int ret;
 
 	spin_unlock_irq(sh->host_lock);
-	dev = pscsi_add_device_to_list(hba, se_dev, pdv, sd, dev_flags);
-	if (!dev)
-		return NULL;
+	ret = pscsi_add_device_to_list(dev, sd);
+	if (ret)
+		return ret;
 
 	pr_debug("CORE_PSCSI[%d] - Added Type: %s for %d:%d:%d:%d\n",
 		phv->phv_host_id, scsi_device_type(sd->type), sh->host_no,
 		sd->channel, sd->id, sd->lun);
-
-	return dev;
+	return 0;
 }
 
-static struct se_device *pscsi_create_virtdevice(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev,
-	void *p)
+int pscsi_configure_device(struct se_device *dev)
 {
-	struct pscsi_dev_virt *pdv = p;
-	struct se_device *dev;
+	struct se_hba *hba = dev->se_hba;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 	struct scsi_device *sd;
-	struct pscsi_hba_virt *phv = hba->hba_ptr;
+	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
 	struct Scsi_Host *sh = phv->phv_lld_host;
 	int legacy_mode_enable = 0;
+	int ret;
 
-	if (!pdv) {
-		pr_err("Unable to locate struct pscsi_dev_virt"
-				" parameter\n");
-		return ERR_PTR(-EINVAL);
+	if (!(pdv->pdv_flags & PDF_HAS_CHANNEL_ID) ||
+	    !(pdv->pdv_flags & PDF_HAS_TARGET_ID) ||
+	    !(pdv->pdv_flags & PDF_HAS_LUN_ID)) {
+		pr_err("Missing scsi_channel_id=, scsi_target_id= and"
+			" scsi_lun_id= parameters\n");
+		return -EINVAL;
 	}
+
 	/*
 	 * If not running in PHV_LLD_SCSI_HOST_NO mode, locate the
 	 * struct Scsi_Host we will need to bring the TCM/pSCSI object online
@@ -532,16 +487,16 @@ static struct se_device *pscsi_create_virtdevice(
 		if (phv->phv_mode == PHV_LLD_SCSI_HOST_NO) {
 			pr_err("pSCSI: Unable to locate struct"
 				" Scsi_Host for PHV_LLD_SCSI_HOST_NO\n");
-			return ERR_PTR(-ENODEV);
+			return -ENODEV;
 		}
 		/*
 		 * For the newer PHV_VIRTUAL_HOST_ID struct scsi_device
 		 * reference, we enforce that udev_path has been set
 		 */
-		if (!(se_dev->su_dev_flags & SDF_USING_UDEV_PATH)) {
+		if (!(dev->dev_flags & DF_USING_UDEV_PATH)) {
 			pr_err("pSCSI: udev_path attribute has not"
 				" been set before ENABLE=1\n");
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 		}
 		/*
 		 * If no scsi_host_id= was passed for PHV_VIRTUAL_HOST_ID,
@@ -549,17 +504,14 @@ static struct se_device *pscsi_create_virtdevice(
 		 * and enable for PHV_LLD_SCSI_HOST_NO mode.
 		 */
 		if (!(pdv->pdv_flags & PDF_HAS_VIRT_HOST_ID)) {
-			spin_lock(&hba->device_lock);
-			if (!list_empty(&hba->hba_dev_list)) {
+			if (hba->dev_count) {
 				pr_err("pSCSI: Unable to set hba_mode"
 					" with active devices\n");
-				spin_unlock(&hba->device_lock);
-				return ERR_PTR(-EEXIST);
+				return -EEXIST;
 			}
-			spin_unlock(&hba->device_lock);
 
 			if (pscsi_pmode_enable_hba(hba, 1) != 1)
-				return ERR_PTR(-ENODEV);
+				return -ENODEV;
 
 			legacy_mode_enable = 1;
 			hba->hba_flags |= HBA_FLAGS_PSCSI_MODE;
@@ -569,14 +521,14 @@ static struct se_device *pscsi_create_virtdevice(
 			if (IS_ERR(sh)) {
 				pr_err("pSCSI: Unable to locate"
 					" pdv_host_id: %d\n", pdv->pdv_host_id);
-				return ERR_CAST(sh);
+				return PTR_ERR(sh);
 			}
 		}
 	} else {
 		if (phv->phv_mode == PHV_VIRTUAL_HOST_ID) {
 			pr_err("pSCSI: PHV_VIRTUAL_HOST_ID set while"
 				" struct Scsi_Host exists\n");
-			return ERR_PTR(-EEXIST);
+			return -EEXIST;
 		}
 	}
 
@@ -593,17 +545,17 @@ static struct se_device *pscsi_create_virtdevice(
 		 */
 		switch (sd->type) {
 		case TYPE_DISK:
-			dev = pscsi_create_type_disk(sd, pdv, se_dev, hba);
+			ret = pscsi_create_type_disk(dev, sd);
 			break;
 		case TYPE_ROM:
-			dev = pscsi_create_type_rom(sd, pdv, se_dev, hba);
+			ret = pscsi_create_type_rom(dev, sd);
 			break;
 		default:
-			dev = pscsi_create_type_other(sd, pdv, se_dev, hba);
+			ret = pscsi_create_type_other(dev, sd);
 			break;
 		}
 
-		if (!dev) {
+		if (ret) {
 			if (phv->phv_mode == PHV_VIRTUAL_HOST_ID)
 				scsi_host_put(sh);
 			else if (legacy_mode_enable) {
@@ -611,9 +563,9 @@ static struct se_device *pscsi_create_virtdevice(
 				hba->hba_flags &= ~HBA_FLAGS_PSCSI_MODE;
 			}
 			pdv->pdv_sd = NULL;
-			return ERR_PTR(-ENODEV);
+			return ret;
 		}
-		return dev;
+		return 0;
 	}
 	spin_unlock_irq(sh->host_lock);
 
@@ -627,17 +579,13 @@ static struct se_device *pscsi_create_virtdevice(
 		hba->hba_flags &= ~HBA_FLAGS_PSCSI_MODE;
 	}
 
-	return ERR_PTR(-ENODEV);
+	return -ENODEV;
 }
 
-/*	pscsi_free_device(): (Part of se_subsystem_api_t template)
- *
- *
- */
-static void pscsi_free_device(void *p)
+static void pscsi_free_device(struct se_device *dev)
 {
-	struct pscsi_dev_virt *pdv = p;
-	struct pscsi_hba_virt *phv = pdv->pdv_se_hba->hba_ptr;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
+	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
 	struct scsi_device *sd = pdv->pdv_sd;
 
 	if (sd) {
@@ -670,7 +618,7 @@ static void pscsi_free_device(void *p)
 static void pscsi_transport_complete(struct se_cmd *cmd, struct scatterlist *sg,
 				     unsigned char *sense_buffer)
 {
-	struct pscsi_dev_virt *pdv = cmd->se_dev->dev_ptr;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev);
 	struct scsi_device *sd = pdv->pdv_sd;
 	int result;
 	struct pscsi_plugin_task *pt = cmd->priv;
@@ -770,13 +718,11 @@ static match_table_t tokens = {
 	{Opt_err, NULL}
 };
 
-static ssize_t pscsi_set_configfs_dev_params(struct se_hba *hba,
-	struct se_subsystem_dev *se_dev,
-	const char *page,
-	ssize_t count)
+static ssize_t pscsi_set_configfs_dev_params(struct se_device *dev,
+		const char *page, ssize_t count)
 {
-	struct pscsi_dev_virt *pdv = se_dev->se_dev_su_ptr;
-	struct pscsi_hba_virt *phv = hba->hba_ptr;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
+	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
 	char *orig, *ptr, *opts;
 	substring_t args[MAX_OPT_ARGS];
 	int ret = 0, arg, token;
@@ -841,29 +787,10 @@ out:
 	return (!ret) ? count : ret;
 }
 
-static ssize_t pscsi_check_configfs_dev_params(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev)
-{
-	struct pscsi_dev_virt *pdv = se_dev->se_dev_su_ptr;
-
-	if (!(pdv->pdv_flags & PDF_HAS_CHANNEL_ID) ||
-	    !(pdv->pdv_flags & PDF_HAS_TARGET_ID) ||
-	    !(pdv->pdv_flags & PDF_HAS_LUN_ID)) {
-		pr_err("Missing scsi_channel_id=, scsi_target_id= and"
-			" scsi_lun_id= parameters\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static ssize_t pscsi_show_configfs_dev_params(struct se_hba *hba,
-					      struct se_subsystem_dev *se_dev,
-					      char *b)
+static ssize_t pscsi_show_configfs_dev_params(struct se_device *dev, char *b)
 {
-	struct pscsi_hba_virt *phv = hba->hba_ptr;
-        struct pscsi_dev_virt *pdv = se_dev->se_dev_su_ptr;
+	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 	struct scsi_device *sd = pdv->pdv_sd;
 	unsigned char host_id[16];
 	ssize_t bl;
@@ -933,7 +860,7 @@ static int pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl,
 		u32 sgl_nents, enum dma_data_direction data_direction,
 		struct bio **hbio)
 {
-	struct pscsi_dev_virt *pdv = cmd->se_dev->dev_ptr;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev);
 	struct bio *bio = NULL, *tbio = NULL;
 	struct page *page;
 	struct scatterlist *sg;
@@ -1104,7 +1031,7 @@ static int pscsi_execute_cmd(struct se_cmd *cmd)
 	struct scatterlist *sgl = cmd->t_data_sg;
 	u32 sgl_nents = cmd->t_data_nents;
 	enum dma_data_direction data_direction = cmd->data_direction;
-	struct pscsi_dev_virt *pdv = cmd->se_dev->dev_ptr;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev);
 	struct pscsi_plugin_task *pt;
 	struct request *req;
 	struct bio *hbio;
@@ -1191,7 +1118,7 @@ fail:
  */
 static u32 pscsi_get_device_rev(struct se_device *dev)
 {
-	struct pscsi_dev_virt *pdv = dev->dev_ptr;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 	struct scsi_device *sd = pdv->pdv_sd;
 
 	return (sd->scsi_level - 1) ? sd->scsi_level - 1 : 1;
@@ -1203,7 +1130,7 @@ static u32 pscsi_get_device_rev(struct se_device *dev)
  */
 static u32 pscsi_get_device_type(struct se_device *dev)
 {
-	struct pscsi_dev_virt *pdv = dev->dev_ptr;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 	struct scsi_device *sd = pdv->pdv_sd;
 
 	return sd->type;
@@ -1211,7 +1138,7 @@ static u32 pscsi_get_device_type(struct se_device *dev)
 
 static sector_t pscsi_get_blocks(struct se_device *dev)
 {
-	struct pscsi_dev_virt *pdv = dev->dev_ptr;
+	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 
 	if (pdv->pdv_bd && pdv->pdv_bd->bd_part)
 		return pdv->pdv_bd->bd_part->nr_sects;
@@ -1259,12 +1186,11 @@ static struct se_subsystem_api pscsi_template = {
 	.attach_hba		= pscsi_attach_hba,
 	.detach_hba		= pscsi_detach_hba,
 	.pmode_enable_hba	= pscsi_pmode_enable_hba,
-	.allocate_virtdevice	= pscsi_allocate_virtdevice,
-	.create_virtdevice	= pscsi_create_virtdevice,
+	.alloc_device		= pscsi_alloc_device,
+	.configure_device	= pscsi_configure_device,
 	.free_device		= pscsi_free_device,
 	.transport_complete	= pscsi_transport_complete,
 	.parse_cdb		= pscsi_parse_cdb,
-	.check_configfs_dev_params = pscsi_check_configfs_dev_params,
 	.set_configfs_dev_params = pscsi_set_configfs_dev_params,
 	.show_configfs_dev_params = pscsi_show_configfs_dev_params,
 	.get_device_rev		= pscsi_get_device_rev,
diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h
index bc1e5e11eca0..1bd757dff8ee 100644
--- a/drivers/target/target_core_pscsi.h
+++ b/drivers/target/target_core_pscsi.h
@@ -37,6 +37,7 @@ struct pscsi_plugin_task {
 #define PDF_HAS_VIRT_HOST_ID	0x20
 
 struct pscsi_dev_virt {
+	struct se_device dev;
 	int	pdv_flags;
 	int	pdv_host_id;
 	int	pdv_channel_id;
@@ -44,7 +45,6 @@ struct pscsi_dev_virt {
 	int	pdv_lun_id;
 	struct block_device *pdv_bd;
 	struct scsi_device *pdv_sd;
-	struct se_hba *pdv_se_hba;
 } ____cacheline_aligned;
 
 typedef enum phv_modes {
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index d00bbe33ff8b..d083f39c4b67 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -41,7 +41,10 @@
 
 #include "target_core_rd.h"
 
-static struct se_subsystem_api rd_mcp_template;
+static inline struct rd_dev *RD_DEV(struct se_device *dev)
+{
+	return container_of(dev, struct rd_dev, dev);
+}
 
 /*	rd_attach_hba(): (Part of se_subsystem_api_t template)
  *
@@ -196,7 +199,7 @@ static int rd_build_device_space(struct rd_dev *rd_dev)
 	return 0;
 }
 
-static void *rd_allocate_virtdevice(struct se_hba *hba, const char *name)
+static struct se_device *rd_alloc_device(struct se_hba *hba, const char *name)
 {
 	struct rd_dev *rd_dev;
 	struct rd_host *rd_host = hba->hba_ptr;
@@ -209,39 +212,27 @@ static void *rd_allocate_virtdevice(struct se_hba *hba, const char *name)
 
 	rd_dev->rd_host = rd_host;
 
-	return rd_dev;
+	return &rd_dev->dev;
 }
 
-static struct se_device *rd_create_virtdevice(struct se_hba *hba,
-		struct se_subsystem_dev *se_dev, void *p)
+static int rd_configure_device(struct se_device *dev)
 {
-	struct se_device *dev;
-	struct se_dev_limits dev_limits;
-	struct rd_dev *rd_dev = p;
-	struct rd_host *rd_host = hba->hba_ptr;
-	int dev_flags = 0, ret;
-	char prod[16], rev[4];
+	struct rd_dev *rd_dev = RD_DEV(dev);
+	struct rd_host *rd_host = dev->se_hba->hba_ptr;
+	int ret;
 
-	memset(&dev_limits, 0, sizeof(struct se_dev_limits));
+	if (!(rd_dev->rd_flags & RDF_HAS_PAGE_COUNT)) {
+		pr_debug("Missing rd_pages= parameter\n");
+		return -EINVAL;
+	}
 
 	ret = rd_build_device_space(rd_dev);
 	if (ret < 0)
 		goto fail;
 
-	snprintf(prod, 16, "RAMDISK-MCP");
-	snprintf(rev, 4, "%s", RD_MCP_VERSION);
-
-	dev_limits.limits.logical_block_size = RD_BLOCKSIZE;
-	dev_limits.limits.max_hw_sectors = UINT_MAX;
-	dev_limits.limits.max_sectors = UINT_MAX;
-	dev_limits.hw_queue_depth = RD_MAX_DEVICE_QUEUE_DEPTH;
-	dev_limits.queue_depth = RD_DEVICE_QUEUE_DEPTH;
-
-	dev = transport_add_device_to_core_hba(hba,
-			&rd_mcp_template, se_dev, dev_flags, rd_dev,
-			&dev_limits, prod, rev);
-	if (!dev)
-		goto fail;
+	dev->dev_attrib.hw_block_size = RD_BLOCKSIZE;
+	dev->dev_attrib.hw_max_sectors = UINT_MAX;
+	dev->dev_attrib.hw_queue_depth = RD_MAX_DEVICE_QUEUE_DEPTH;
 
 	rd_dev->rd_dev_id = rd_host->rd_host_dev_id_count++;
 
@@ -251,16 +242,16 @@ static struct se_device *rd_create_virtdevice(struct se_hba *hba,
 		rd_dev->sg_table_count,
 		(unsigned long)(rd_dev->rd_page_count * PAGE_SIZE));
 
-	return dev;
+	return 0;
 
 fail:
 	rd_release_device_space(rd_dev);
-	return ERR_PTR(ret);
+	return ret;
 }
 
-static void rd_free_device(void *p)
+static void rd_free_device(struct se_device *dev)
 {
-	struct rd_dev *rd_dev = p;
+	struct rd_dev *rd_dev = RD_DEV(dev);
 
 	rd_release_device_space(rd_dev);
 	kfree(rd_dev);
@@ -290,7 +281,7 @@ static int rd_execute_rw(struct se_cmd *cmd)
 	u32 sgl_nents = cmd->t_data_nents;
 	enum dma_data_direction data_direction = cmd->data_direction;
 	struct se_device *se_dev = cmd->se_dev;
-	struct rd_dev *dev = se_dev->dev_ptr;
+	struct rd_dev *dev = RD_DEV(se_dev);
 	struct rd_dev_sg_table *table;
 	struct scatterlist *rd_sg;
 	struct sg_mapping_iter m;
@@ -300,7 +291,7 @@ static int rd_execute_rw(struct se_cmd *cmd)
 	u32 src_len;
 	u64 tmp;
 
-	tmp = cmd->t_task_lba * se_dev->se_sub_dev->se_dev_attrib.block_size;
+	tmp = cmd->t_task_lba * se_dev->dev_attrib.block_size;
 	rd_offset = do_div(tmp, PAGE_SIZE);
 	rd_page = tmp;
 	rd_size = cmd->data_length;
@@ -378,13 +369,10 @@ static match_table_t tokens = {
 	{Opt_err, NULL}
 };
 
-static ssize_t rd_set_configfs_dev_params(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev,
-	const char *page,
-	ssize_t count)
+static ssize_t rd_set_configfs_dev_params(struct se_device *dev,
+		const char *page, ssize_t count)
 {
-	struct rd_dev *rd_dev = se_dev->se_dev_su_ptr;
+	struct rd_dev *rd_dev = RD_DEV(dev);
 	char *orig, *ptr, *opts;
 	substring_t args[MAX_OPT_ARGS];
 	int ret = 0, arg, token;
@@ -417,24 +405,10 @@ static ssize_t rd_set_configfs_dev_params(
 	return (!ret) ? count : ret;
 }
 
-static ssize_t rd_check_configfs_dev_params(struct se_hba *hba, struct se_subsystem_dev *se_dev)
+static ssize_t rd_show_configfs_dev_params(struct se_device *dev, char *b)
 {
-	struct rd_dev *rd_dev = se_dev->se_dev_su_ptr;
-
-	if (!(rd_dev->rd_flags & RDF_HAS_PAGE_COUNT)) {
-		pr_debug("Missing rd_pages= parameter\n");
-		return -EINVAL;
-	}
+	struct rd_dev *rd_dev = RD_DEV(dev);
 
-	return 0;
-}
-
-static ssize_t rd_show_configfs_dev_params(
-	struct se_hba *hba,
-	struct se_subsystem_dev *se_dev,
-	char *b)
-{
-	struct rd_dev *rd_dev = se_dev->se_dev_su_ptr;
 	ssize_t bl = sprintf(b, "TCM RamDisk ID: %u  RamDisk Makeup: rd_mcp\n",
 			rd_dev->rd_dev_id);
 	bl += sprintf(b + bl, "        PAGES/PAGE_SIZE: %u*%lu"
@@ -455,9 +429,10 @@ static u32 rd_get_device_type(struct se_device *dev)
 
 static sector_t rd_get_blocks(struct se_device *dev)
 {
-	struct rd_dev *rd_dev = dev->dev_ptr;
+	struct rd_dev *rd_dev = RD_DEV(dev);
+
 	unsigned long long blocks_long = ((rd_dev->rd_page_count * PAGE_SIZE) /
-			dev->se_sub_dev->se_dev_attrib.block_size) - 1;
+			dev->dev_attrib.block_size) - 1;
 
 	return blocks_long;
 }
@@ -473,14 +448,15 @@ static int rd_parse_cdb(struct se_cmd *cmd)
 
 static struct se_subsystem_api rd_mcp_template = {
 	.name			= "rd_mcp",
+	.inquiry_prod		= "RAMDISK-MCP",
+	.inquiry_rev		= RD_MCP_VERSION,
 	.transport_type		= TRANSPORT_PLUGIN_VHBA_VDEV,
 	.attach_hba		= rd_attach_hba,
 	.detach_hba		= rd_detach_hba,
-	.allocate_virtdevice	= rd_allocate_virtdevice,
-	.create_virtdevice	= rd_create_virtdevice,
+	.alloc_device		= rd_alloc_device,
+	.configure_device	= rd_configure_device,
 	.free_device		= rd_free_device,
 	.parse_cdb		= rd_parse_cdb,
-	.check_configfs_dev_params = rd_check_configfs_dev_params,
 	.set_configfs_dev_params = rd_set_configfs_dev_params,
 	.show_configfs_dev_params = rd_show_configfs_dev_params,
 	.get_device_rev		= rd_get_device_rev,
diff --git a/drivers/target/target_core_rd.h b/drivers/target/target_core_rd.h
index 21458125fe51..933b38b6e563 100644
--- a/drivers/target/target_core_rd.h
+++ b/drivers/target/target_core_rd.h
@@ -24,6 +24,7 @@ struct rd_dev_sg_table {
 #define RDF_HAS_PAGE_COUNT	0x01
 
 struct rd_dev {
+	struct se_device dev;
 	u32		rd_flags;
 	/* Unique Ramdisk Device ID in Ramdisk HBA */
 	u32		rd_dev_id;
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index a6e27d967c7b..035193d04fa2 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -54,10 +54,10 @@ static int sbc_emulate_readcapacity(struct se_cmd *cmd)
 	buf[1] = (blocks >> 16) & 0xff;
 	buf[2] = (blocks >> 8) & 0xff;
 	buf[3] = blocks & 0xff;
-	buf[4] = (dev->se_sub_dev->se_dev_attrib.block_size >> 24) & 0xff;
-	buf[5] = (dev->se_sub_dev->se_dev_attrib.block_size >> 16) & 0xff;
-	buf[6] = (dev->se_sub_dev->se_dev_attrib.block_size >> 8) & 0xff;
-	buf[7] = dev->se_sub_dev->se_dev_attrib.block_size & 0xff;
+	buf[4] = (dev->dev_attrib.block_size >> 24) & 0xff;
+	buf[5] = (dev->dev_attrib.block_size >> 16) & 0xff;
+	buf[6] = (dev->dev_attrib.block_size >> 8) & 0xff;
+	buf[7] = dev->dev_attrib.block_size & 0xff;
 
 	rbuf = transport_kmap_data_sg(cmd);
 	if (rbuf) {
@@ -85,15 +85,15 @@ static int sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 	buf[5] = (blocks >> 16) & 0xff;
 	buf[6] = (blocks >> 8) & 0xff;
 	buf[7] = blocks & 0xff;
-	buf[8] = (dev->se_sub_dev->se_dev_attrib.block_size >> 24) & 0xff;
-	buf[9] = (dev->se_sub_dev->se_dev_attrib.block_size >> 16) & 0xff;
-	buf[10] = (dev->se_sub_dev->se_dev_attrib.block_size >> 8) & 0xff;
-	buf[11] = dev->se_sub_dev->se_dev_attrib.block_size & 0xff;
+	buf[8] = (dev->dev_attrib.block_size >> 24) & 0xff;
+	buf[9] = (dev->dev_attrib.block_size >> 16) & 0xff;
+	buf[10] = (dev->dev_attrib.block_size >> 8) & 0xff;
+	buf[11] = dev->dev_attrib.block_size & 0xff;
 	/*
 	 * Set Thin Provisioning Enable bit following sbc3r22 in section
 	 * READ CAPACITY (16) byte 14 if emulate_tpu or emulate_tpws is enabled.
 	 */
-	if (dev->se_sub_dev->se_dev_attrib.emulate_tpu || dev->se_sub_dev->se_dev_attrib.emulate_tpws)
+	if (dev->dev_attrib.emulate_tpu || dev->dev_attrib.emulate_tpws)
 		buf[14] = 0x80;
 
 	rbuf = transport_kmap_data_sg(cmd);
@@ -143,7 +143,7 @@ static int sbc_emulate_noop(struct se_cmd *cmd)
 
 static inline u32 sbc_get_size(struct se_cmd *cmd, u32 sectors)
 {
-	return cmd->se_dev->se_sub_dev->se_dev_attrib.block_size * sectors;
+	return cmd->se_dev->dev_attrib.block_size * sectors;
 }
 
 static int sbc_check_valid_sectors(struct se_cmd *cmd)
@@ -152,7 +152,7 @@ static int sbc_check_valid_sectors(struct se_cmd *cmd)
 	unsigned long long end_lba;
 	u32 sectors;
 
-	sectors = cmd->data_length / dev->se_sub_dev->se_dev_attrib.block_size;
+	sectors = cmd->data_length / dev->dev_attrib.block_size;
 	end_lba = dev->transport->get_blocks(dev) + 1;
 
 	if (cmd->t_task_lba + sectors > end_lba) {
@@ -315,7 +315,6 @@ out:
 
 int sbc_parse_cdb(struct se_cmd *cmd, struct spc_ops *ops)
 {
-	struct se_subsystem_dev *su_dev = cmd->se_dev->se_sub_dev;
 	struct se_device *dev = cmd->se_dev;
 	unsigned char *cdb = cmd->t_task_cdb;
 	unsigned int size;
@@ -562,18 +561,18 @@ int sbc_parse_cdb(struct se_cmd *cmd, struct spc_ops *ops)
 	if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
 		unsigned long long end_lba;
 
-		if (sectors > su_dev->se_dev_attrib.fabric_max_sectors) {
+		if (sectors > dev->dev_attrib.fabric_max_sectors) {
 			printk_ratelimited(KERN_ERR "SCSI OP %02xh with too"
 				" big sectors %u exceeds fabric_max_sectors:"
 				" %u\n", cdb[0], sectors,
-				su_dev->se_dev_attrib.fabric_max_sectors);
+				dev->dev_attrib.fabric_max_sectors);
 			goto out_invalid_cdb_field;
 		}
-		if (sectors > su_dev->se_dev_attrib.hw_max_sectors) {
+		if (sectors > dev->dev_attrib.hw_max_sectors) {
 			printk_ratelimited(KERN_ERR "SCSI OP %02xh with too"
 				" big sectors %u exceeds backend hw_max_sectors:"
 				" %u\n", cdb[0], sectors,
-				su_dev->se_dev_attrib.hw_max_sectors);
+				dev->dev_attrib.hw_max_sectors);
 			goto out_invalid_cdb_field;
 		}
 
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 6fd434d3d7e4..0af45ae32f8c 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -95,14 +95,14 @@ static int spc_emulate_inquiry_std(struct se_cmd *cmd, char *buf)
 	/*
 	 * Enable SCCS and TPGS fields for Emulated ALUA
 	 */
-	if (dev->se_sub_dev->t10_alua.alua_type == SPC3_ALUA_EMULATED)
+	if (dev->t10_alua.alua_type == SPC3_ALUA_EMULATED)
 		spc_fill_alua_data(lun->lun_sep, buf);
 
 	buf[7] = 0x2; /* CmdQue=1 */
 
 	snprintf(&buf[8], 8, "LIO-ORG");
-	snprintf(&buf[16], 16, "%s", dev->se_sub_dev->t10_wwn.model);
-	snprintf(&buf[32], 4, "%s", dev->se_sub_dev->t10_wwn.revision);
+	snprintf(&buf[16], 16, "%s", dev->t10_wwn.model);
+	snprintf(&buf[32], 4, "%s", dev->t10_wwn.revision);
 	buf[4] = 31; /* Set additional length to 31 */
 
 	return 0;
@@ -114,15 +114,13 @@ static int spc_emulate_evpd_80(struct se_cmd *cmd, unsigned char *buf)
 	struct se_device *dev = cmd->se_dev;
 	u16 len = 0;
 
-	if (dev->se_sub_dev->su_dev_flags &
-			SDF_EMULATED_VPD_UNIT_SERIAL) {
+	if (dev->dev_flags & DF_EMULATED_VPD_UNIT_SERIAL) {
 		u32 unit_serial_len;
 
-		unit_serial_len = strlen(dev->se_sub_dev->t10_wwn.unit_serial);
+		unit_serial_len = strlen(dev->t10_wwn.unit_serial);
 		unit_serial_len++; /* For NULL Terminator */
 
-		len += sprintf(&buf[4], "%s",
-			dev->se_sub_dev->t10_wwn.unit_serial);
+		len += sprintf(&buf[4], "%s", dev->t10_wwn.unit_serial);
 		len++; /* Extra Byte for NULL Terminator */
 		buf[3] = len;
 	}
@@ -132,7 +130,7 @@ static int spc_emulate_evpd_80(struct se_cmd *cmd, unsigned char *buf)
 static void spc_parse_naa_6h_vendor_specific(struct se_device *dev,
 		unsigned char *buf)
 {
-	unsigned char *p = &dev->se_sub_dev->t10_wwn.unit_serial[0];
+	unsigned char *p = &dev->t10_wwn.unit_serial[0];
 	int cnt;
 	bool next = true;
 
@@ -173,7 +171,7 @@ static int spc_emulate_evpd_83(struct se_cmd *cmd, unsigned char *buf)
 	struct t10_alua_lu_gp_member *lu_gp_mem;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
-	unsigned char *prod = &dev->se_sub_dev->t10_wwn.model[0];
+	unsigned char *prod = &dev->t10_wwn.model[0];
 	u32 prod_len;
 	u32 unit_serial_len, off = 0;
 	u16 len = 0, id_len;
@@ -188,7 +186,7 @@ static int spc_emulate_evpd_83(struct se_cmd *cmd, unsigned char *buf)
 	 * /sys/kernel/config/target/core/$HBA/$DEV/wwn/vpd_unit_serial
 	 * value in order to return the NAA id.
 	 */
-	if (!(dev->se_sub_dev->su_dev_flags & SDF_EMULATED_VPD_UNIT_SERIAL))
+	if (!(dev->dev_flags & DF_EMULATED_VPD_UNIT_SERIAL))
 		goto check_t10_vend_desc;
 
 	/* CODE SET == Binary */
@@ -236,14 +234,12 @@ check_t10_vend_desc:
 	prod_len += strlen(prod);
 	prod_len++; /* For : */
 
-	if (dev->se_sub_dev->su_dev_flags &
-			SDF_EMULATED_VPD_UNIT_SERIAL) {
-		unit_serial_len =
-			strlen(&dev->se_sub_dev->t10_wwn.unit_serial[0]);
+	if (dev->dev_flags & DF_EMULATED_VPD_UNIT_SERIAL) {
+		unit_serial_len = strlen(&dev->t10_wwn.unit_serial[0]);
 		unit_serial_len++; /* For NULL Terminator */
 
 		id_len += sprintf(&buf[off+12], "%s:%s", prod,
-				&dev->se_sub_dev->t10_wwn.unit_serial[0]);
+				&dev->t10_wwn.unit_serial[0]);
 	}
 	buf[off] = 0x2; /* ASCII */
 	buf[off+1] = 0x1; /* T10 Vendor ID */
@@ -298,8 +294,7 @@ check_t10_vend_desc:
 		 * Get the PROTOCOL IDENTIFIER as defined by spc4r17
 		 * section 7.5.1 Table 362
 		 */
-		if (dev->se_sub_dev->t10_alua.alua_type !=
-				SPC3_ALUA_EMULATED)
+		if (dev->t10_alua.alua_type != SPC3_ALUA_EMULATED)
 			goto check_scsi_name;
 
 		tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
@@ -422,7 +417,7 @@ static int spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf)
 	buf[5] = 0x07;
 
 	/* If WriteCache emulation is enabled, set V_SUP */
-	if (cmd->se_dev->se_sub_dev->se_dev_attrib.emulate_write_cache > 0)
+	if (cmd->se_dev->dev_attrib.emulate_write_cache > 0)
 		buf[6] = 0x01;
 	return 0;
 }
@@ -439,7 +434,7 @@ static int spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 	 * emulate_tpu=1 or emulate_tpws=1 we will be expect a
 	 * different page length for Thin Provisioning.
 	 */
-	if (dev->se_sub_dev->se_dev_attrib.emulate_tpu || dev->se_sub_dev->se_dev_attrib.emulate_tpws)
+	if (dev->dev_attrib.emulate_tpu || dev->dev_attrib.emulate_tpws)
 		have_tp = 1;
 
 	buf[0] = dev->transport->get_device_type(dev);
@@ -456,14 +451,14 @@ static int spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 	/*
 	 * Set MAXIMUM TRANSFER LENGTH
 	 */
-	max_sectors = min(dev->se_sub_dev->se_dev_attrib.fabric_max_sectors,
-			  dev->se_sub_dev->se_dev_attrib.hw_max_sectors);
+	max_sectors = min(dev->dev_attrib.fabric_max_sectors,
+			  dev->dev_attrib.hw_max_sectors);
 	put_unaligned_be32(max_sectors, &buf[8]);
 
 	/*
 	 * Set OPTIMAL TRANSFER LENGTH
 	 */
-	put_unaligned_be32(dev->se_sub_dev->se_dev_attrib.optimal_sectors, &buf[12]);
+	put_unaligned_be32(dev->dev_attrib.optimal_sectors, &buf[12]);
 
 	/*
 	 * Exit now if we don't support TP.
@@ -474,25 +469,25 @@ static int spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 	/*
 	 * Set MAXIMUM UNMAP LBA COUNT
 	 */
-	put_unaligned_be32(dev->se_sub_dev->se_dev_attrib.max_unmap_lba_count, &buf[20]);
+	put_unaligned_be32(dev->dev_attrib.max_unmap_lba_count, &buf[20]);
 
 	/*
 	 * Set MAXIMUM UNMAP BLOCK DESCRIPTOR COUNT
 	 */
-	put_unaligned_be32(dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count,
+	put_unaligned_be32(dev->dev_attrib.max_unmap_block_desc_count,
 			   &buf[24]);
 
 	/*
 	 * Set OPTIMAL UNMAP GRANULARITY
 	 */
-	put_unaligned_be32(dev->se_sub_dev->se_dev_attrib.unmap_granularity, &buf[28]);
+	put_unaligned_be32(dev->dev_attrib.unmap_granularity, &buf[28]);
 
 	/*
 	 * UNMAP GRANULARITY ALIGNMENT
 	 */
-	put_unaligned_be32(dev->se_sub_dev->se_dev_attrib.unmap_granularity_alignment,
+	put_unaligned_be32(dev->dev_attrib.unmap_granularity_alignment,
 			   &buf[32]);
-	if (dev->se_sub_dev->se_dev_attrib.unmap_granularity_alignment != 0)
+	if (dev->dev_attrib.unmap_granularity_alignment != 0)
 		buf[32] |= 0x80; /* Set the UGAVALID bit */
 
 	return 0;
@@ -505,7 +500,7 @@ static int spc_emulate_evpd_b1(struct se_cmd *cmd, unsigned char *buf)
 
 	buf[0] = dev->transport->get_device_type(dev);
 	buf[3] = 0x3c;
-	buf[5] = dev->se_sub_dev->se_dev_attrib.is_nonrot ? 1 : 0;
+	buf[5] = dev->dev_attrib.is_nonrot ? 1 : 0;
 
 	return 0;
 }
@@ -546,7 +541,7 @@ static int spc_emulate_evpd_b2(struct se_cmd *cmd, unsigned char *buf)
 	 * the UNMAP command (see 5.25). A TPU bit set to zero indicates
 	 * that the device server does not support the UNMAP command.
 	 */
-	if (dev->se_sub_dev->se_dev_attrib.emulate_tpu != 0)
+	if (dev->dev_attrib.emulate_tpu != 0)
 		buf[5] = 0x80;
 
 	/*
@@ -555,7 +550,7 @@ static int spc_emulate_evpd_b2(struct se_cmd *cmd, unsigned char *buf)
 	 * A TPWS bit set to zero indicates that the device server does not
 	 * support the use of the WRITE SAME (16) command to unmap LBAs.
 	 */
-	if (dev->se_sub_dev->se_dev_attrib.emulate_tpws != 0)
+	if (dev->dev_attrib.emulate_tpws != 0)
 		buf[5] |= 0x40;
 
 	return 0;
@@ -586,8 +581,7 @@ static int spc_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf)
 	 * Registered Extended LUN WWN has been set via ConfigFS
 	 * during device creation/restart.
 	 */
-	if (cmd->se_dev->se_sub_dev->su_dev_flags &
-			SDF_EMULATED_VPD_UNIT_SERIAL) {
+	if (cmd->se_dev->dev_flags & DF_EMULATED_VPD_UNIT_SERIAL) {
 		buf[3] = ARRAY_SIZE(evpd_handlers);
 		for (p = 0; p < ARRAY_SIZE(evpd_handlers); ++p)
 			buf[p + 4] = evpd_handlers[p].page;
@@ -690,7 +684,7 @@ static int spc_modesense_control(struct se_device *dev, unsigned char *p)
 	 * command sequence order shall be explicitly handled by the application client
 	 * through the selection of appropriate ommands and task attributes.
 	 */
-	p[3] = (dev->se_sub_dev->se_dev_attrib.emulate_rest_reord == 1) ? 0x00 : 0x10;
+	p[3] = (dev->dev_attrib.emulate_rest_reord == 1) ? 0x00 : 0x10;
 	/*
 	 * From spc4r17, section 7.4.6 Control mode Page
 	 *
@@ -720,8 +714,8 @@ static int spc_modesense_control(struct se_device *dev, unsigned char *p)
 	 * for a BUSY, TASK SET FULL, or RESERVATION CONFLICT status regardless
 	 * to the number of commands completed with one of those status codes.
 	 */
-	p[4] = (dev->se_sub_dev->se_dev_attrib.emulate_ua_intlck_ctrl == 2) ? 0x30 :
-	       (dev->se_sub_dev->se_dev_attrib.emulate_ua_intlck_ctrl == 1) ? 0x20 : 0x00;
+	p[4] = (dev->dev_attrib.emulate_ua_intlck_ctrl == 2) ? 0x30 :
+	       (dev->dev_attrib.emulate_ua_intlck_ctrl == 1) ? 0x20 : 0x00;
 	/*
 	 * From spc4r17, section 7.4.6 Control mode Page
 	 *
@@ -734,7 +728,7 @@ static int spc_modesense_control(struct se_device *dev, unsigned char *p)
 	 * which the command was received shall be completed with TASK ABORTED
 	 * status (see SAM-4).
 	 */
-	p[5] = (dev->se_sub_dev->se_dev_attrib.emulate_tas) ? 0x40 : 0x00;
+	p[5] = (dev->dev_attrib.emulate_tas) ? 0x40 : 0x00;
 	p[8] = 0xff;
 	p[9] = 0xff;
 	p[11] = 30;
@@ -746,7 +740,7 @@ static int spc_modesense_caching(struct se_device *dev, unsigned char *p)
 {
 	p[0] = 0x08;
 	p[1] = 0x12;
-	if (dev->se_sub_dev->se_dev_attrib.emulate_write_cache > 0)
+	if (dev->dev_attrib.emulate_write_cache > 0)
 		p[2] = 0x04; /* Write Cache Enable */
 	p[12] = 0x20; /* Disabled Read Ahead */
 
@@ -826,8 +820,8 @@ static int spc_emulate_modesense(struct se_cmd *cmd)
 		    (cmd->se_deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)))
 			spc_modesense_write_protect(&buf[3], type);
 
-		if ((dev->se_sub_dev->se_dev_attrib.emulate_write_cache > 0) &&
-		    (dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0))
+		if ((dev->dev_attrib.emulate_write_cache > 0) &&
+		    (dev->dev_attrib.emulate_fua_write > 0))
 			spc_modesense_dpofua(&buf[3], type);
 	} else {
 		offset -= 1;
@@ -839,8 +833,8 @@ static int spc_emulate_modesense(struct se_cmd *cmd)
 		    (cmd->se_deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)))
 			spc_modesense_write_protect(&buf[2], type);
 
-		if ((dev->se_sub_dev->se_dev_attrib.emulate_write_cache > 0) &&
-		    (dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0))
+		if ((dev->dev_attrib.emulate_write_cache > 0) &&
+		    (dev->dev_attrib.emulate_fua_write > 0))
 			spc_modesense_dpofua(&buf[2], type);
 	}
 
@@ -923,7 +917,6 @@ static int spc_emulate_testunitready(struct se_cmd *cmd)
 int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 {
 	struct se_device *dev = cmd->se_dev;
-	struct se_subsystem_dev *su_dev = dev->se_sub_dev;
 	unsigned char *cdb = cmd->t_task_cdb;
 
 	switch (cdb[0]) {
@@ -946,12 +939,12 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		*size = (cdb[7] << 8) + cdb[8];
 		break;
 	case PERSISTENT_RESERVE_IN:
-		if (su_dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS)
+		if (dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS)
 			cmd->execute_cmd = target_scsi3_emulate_pr_in;
 		*size = (cdb[7] << 8) + cdb[8];
 		break;
 	case PERSISTENT_RESERVE_OUT:
-		if (su_dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS)
+		if (dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS)
 			cmd->execute_cmd = target_scsi3_emulate_pr_out;
 		*size = (cdb[7] << 8) + cdb[8];
 		break;
@@ -962,7 +955,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		else
 			*size = cmd->data_length;
 
-		if (su_dev->t10_pr.res_type != SPC_PASSTHROUGH)
+		if (dev->t10_pr.res_type != SPC_PASSTHROUGH)
 			cmd->execute_cmd = target_scsi2_reservation_release;
 		break;
 	case RESERVE:
@@ -983,7 +976,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		 * is running in SPC_PASSTHROUGH, and wants reservations
 		 * emulation disabled.
 		 */
-		if (su_dev->t10_pr.res_type != SPC_PASSTHROUGH)
+		if (dev->t10_pr.res_type != SPC_PASSTHROUGH)
 			cmd->execute_cmd = target_scsi2_reservation_reserve;
 		break;
 	case REQUEST_SENSE:
@@ -1040,7 +1033,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 			 * Check for emulated MI_REPORT_TARGET_PGS
 			 */
 			if ((cdb[1] & 0x1f) == MI_REPORT_TARGET_PGS &&
-			    su_dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) {
+			    dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) {
 				cmd->execute_cmd =
 					target_emulate_report_target_port_groups;
 			}
@@ -1059,7 +1052,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 			 * Check for emulated MO_SET_TARGET_PGS.
 			 */
 			if (cdb[1] == MO_SET_TARGET_PGS &&
-			    su_dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) {
+			    dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) {
 				cmd->execute_cmd =
 					target_emulate_set_target_port_groups;
 			}
diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c
index cb6b0036ae95..9bbb0170b726 100644
--- a/drivers/target/target_core_stat.c
+++ b/drivers/target/target_core_stat.c
@@ -80,13 +80,9 @@ static struct target_stat_scsi_dev_attribute				\
 static ssize_t target_stat_scsi_dev_show_attr_inst(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_hba *hba = se_subdev->se_dev_hba;
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
+	struct se_hba *hba = dev->se_hba;
 
 	return snprintf(page, PAGE_SIZE, "%u\n", hba->hba_index);
 }
@@ -95,12 +91,8 @@ DEV_STAT_SCSI_DEV_ATTR_RO(inst);
 static ssize_t target_stat_scsi_dev_show_attr_indx(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	return snprintf(page, PAGE_SIZE, "%u\n", dev->dev_index);
 }
@@ -109,13 +101,6 @@ DEV_STAT_SCSI_DEV_ATTR_RO(indx);
 static ssize_t target_stat_scsi_dev_show_attr_role(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
-
 	return snprintf(page, PAGE_SIZE, "Target\n");
 }
 DEV_STAT_SCSI_DEV_ATTR_RO(role);
@@ -123,12 +108,8 @@ DEV_STAT_SCSI_DEV_ATTR_RO(role);
 static ssize_t target_stat_scsi_dev_show_attr_ports(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	return snprintf(page, PAGE_SIZE, "%u\n", dev->dev_port_count);
 }
@@ -176,13 +157,9 @@ static struct target_stat_scsi_tgt_dev_attribute			\
 static ssize_t target_stat_scsi_tgt_dev_show_attr_inst(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_hba *hba = se_subdev->se_dev_hba;
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
+	struct se_hba *hba = dev->se_hba;
 
 	return snprintf(page, PAGE_SIZE, "%u\n", hba->hba_index);
 }
@@ -191,12 +168,8 @@ DEV_STAT_SCSI_TGT_DEV_ATTR_RO(inst);
 static ssize_t target_stat_scsi_tgt_dev_show_attr_indx(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	return snprintf(page, PAGE_SIZE, "%u\n", dev->dev_index);
 }
@@ -205,13 +178,6 @@ DEV_STAT_SCSI_TGT_DEV_ATTR_RO(indx);
 static ssize_t target_stat_scsi_tgt_dev_show_attr_num_lus(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
-
 	return snprintf(page, PAGE_SIZE, "%u\n", LU_COUNT);
 }
 DEV_STAT_SCSI_TGT_DEV_ATTR_RO(num_lus);
@@ -219,60 +185,27 @@ DEV_STAT_SCSI_TGT_DEV_ATTR_RO(num_lus);
 static ssize_t target_stat_scsi_tgt_dev_show_attr_status(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-	char status[16];
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
-	if (!dev)
-		return -ENODEV;
-
-	switch (dev->dev_status) {
-	case TRANSPORT_DEVICE_ACTIVATED:
-		strcpy(status, "activated");
-		break;
-	case TRANSPORT_DEVICE_DEACTIVATED:
-		strcpy(status, "deactivated");
-		break;
-	case TRANSPORT_DEVICE_SHUTDOWN:
-		strcpy(status, "shutdown");
-		break;
-	case TRANSPORT_DEVICE_OFFLINE_ACTIVATED:
-	case TRANSPORT_DEVICE_OFFLINE_DEACTIVATED:
-		strcpy(status, "offline");
-		break;
-	default:
-		sprintf(status, "unknown(%d)", dev->dev_status);
-		break;
-	}
-
-	return snprintf(page, PAGE_SIZE, "%s\n", status);
+	if (dev->export_count)
+		return snprintf(page, PAGE_SIZE, "activated");
+	else
+		return snprintf(page, PAGE_SIZE, "deactivated");
 }
 DEV_STAT_SCSI_TGT_DEV_ATTR_RO(status);
 
 static ssize_t target_stat_scsi_tgt_dev_show_attr_non_access_lus(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 	int non_accessible_lus;
 
-	if (!dev)
-		return -ENODEV;
-
-	switch (dev->dev_status) {
-	case TRANSPORT_DEVICE_ACTIVATED:
+	if (dev->export_count)
 		non_accessible_lus = 0;
-		break;
-	case TRANSPORT_DEVICE_DEACTIVATED:
-	case TRANSPORT_DEVICE_SHUTDOWN:
-	case TRANSPORT_DEVICE_OFFLINE_ACTIVATED:
-	case TRANSPORT_DEVICE_OFFLINE_DEACTIVATED:
-	default:
+	else
 		non_accessible_lus = 1;
-		break;
-	}
 
 	return snprintf(page, PAGE_SIZE, "%u\n", non_accessible_lus);
 }
@@ -281,12 +214,8 @@ DEV_STAT_SCSI_TGT_DEV_ATTR_RO(non_access_lus);
 static ssize_t target_stat_scsi_tgt_dev_show_attr_resets(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	return snprintf(page, PAGE_SIZE, "%u\n", dev->num_resets);
 }
@@ -335,13 +264,9 @@ static struct target_stat_scsi_lu_attribute target_stat_scsi_lu_##_name = \
 static ssize_t target_stat_scsi_lu_show_attr_inst(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_hba *hba = se_subdev->se_dev_hba;
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
+	struct se_hba *hba = dev->se_hba;
 
 	return snprintf(page, PAGE_SIZE, "%u\n", hba->hba_index);
 }
@@ -350,12 +275,8 @@ DEV_STAT_SCSI_LU_ATTR_RO(inst);
 static ssize_t target_stat_scsi_lu_show_attr_dev(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	return snprintf(page, PAGE_SIZE, "%u\n", dev->dev_index);
 }
@@ -364,13 +285,6 @@ DEV_STAT_SCSI_LU_ATTR_RO(dev);
 static ssize_t target_stat_scsi_lu_show_attr_indx(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
-
 	return snprintf(page, PAGE_SIZE, "%u\n", SCSI_LU_INDEX);
 }
 DEV_STAT_SCSI_LU_ATTR_RO(indx);
@@ -378,12 +292,6 @@ DEV_STAT_SCSI_LU_ATTR_RO(indx);
 static ssize_t target_stat_scsi_lu_show_attr_lun(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
 	/* FIXME: scsiLuDefaultLun */
 	return snprintf(page, PAGE_SIZE, "%llu\n", (unsigned long long)0);
 }
@@ -392,35 +300,28 @@ DEV_STAT_SCSI_LU_ATTR_RO(lun);
 static ssize_t target_stat_scsi_lu_show_attr_lu_name(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
-	if (!dev)
-		return -ENODEV;
 	/* scsiLuWwnName */
 	return snprintf(page, PAGE_SIZE, "%s\n",
-			(strlen(dev->se_sub_dev->t10_wwn.unit_serial)) ?
-			dev->se_sub_dev->t10_wwn.unit_serial : "None");
+			(strlen(dev->t10_wwn.unit_serial)) ?
+			dev->t10_wwn.unit_serial : "None");
 }
 DEV_STAT_SCSI_LU_ATTR_RO(lu_name);
 
 static ssize_t target_stat_scsi_lu_show_attr_vend(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 	int i;
-	char str[sizeof(dev->se_sub_dev->t10_wwn.vendor)+1];
-
-	if (!dev)
-		return -ENODEV;
+	char str[sizeof(dev->t10_wwn.vendor)+1];
 
 	/* scsiLuVendorId */
-	for (i = 0; i < sizeof(dev->se_sub_dev->t10_wwn.vendor); i++)
-		str[i] = ISPRINT(dev->se_sub_dev->t10_wwn.vendor[i]) ?
-			dev->se_sub_dev->t10_wwn.vendor[i] : ' ';
+	for (i = 0; i < sizeof(dev->t10_wwn.vendor); i++)
+		str[i] = ISPRINT(dev->t10_wwn.vendor[i]) ?
+			dev->t10_wwn.vendor[i] : ' ';
 	str[i] = '\0';
 	return snprintf(page, PAGE_SIZE, "%s\n", str);
 }
@@ -429,19 +330,15 @@ DEV_STAT_SCSI_LU_ATTR_RO(vend);
 static ssize_t target_stat_scsi_lu_show_attr_prod(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 	int i;
-	char str[sizeof(dev->se_sub_dev->t10_wwn.model)+1];
-
-	if (!dev)
-		return -ENODEV;
+	char str[sizeof(dev->t10_wwn.model)+1];
 
 	/* scsiLuProductId */
-	for (i = 0; i < sizeof(dev->se_sub_dev->t10_wwn.vendor); i++)
-		str[i] = ISPRINT(dev->se_sub_dev->t10_wwn.model[i]) ?
-			dev->se_sub_dev->t10_wwn.model[i] : ' ';
+	for (i = 0; i < sizeof(dev->t10_wwn.vendor); i++)
+		str[i] = ISPRINT(dev->t10_wwn.model[i]) ?
+			dev->t10_wwn.model[i] : ' ';
 	str[i] = '\0';
 	return snprintf(page, PAGE_SIZE, "%s\n", str);
 }
@@ -450,19 +347,15 @@ DEV_STAT_SCSI_LU_ATTR_RO(prod);
 static ssize_t target_stat_scsi_lu_show_attr_rev(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 	int i;
-	char str[sizeof(dev->se_sub_dev->t10_wwn.revision)+1];
-
-	if (!dev)
-		return -ENODEV;
+	char str[sizeof(dev->t10_wwn.revision)+1];
 
 	/* scsiLuRevisionId */
-	for (i = 0; i < sizeof(dev->se_sub_dev->t10_wwn.revision); i++)
-		str[i] = ISPRINT(dev->se_sub_dev->t10_wwn.revision[i]) ?
-			dev->se_sub_dev->t10_wwn.revision[i] : ' ';
+	for (i = 0; i < sizeof(dev->t10_wwn.revision); i++)
+		str[i] = ISPRINT(dev->t10_wwn.revision[i]) ?
+			dev->t10_wwn.revision[i] : ' ';
 	str[i] = '\0';
 	return snprintf(page, PAGE_SIZE, "%s\n", str);
 }
@@ -471,12 +364,8 @@ DEV_STAT_SCSI_LU_ATTR_RO(rev);
 static ssize_t target_stat_scsi_lu_show_attr_dev_type(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuPeripheralType */
 	return snprintf(page, PAGE_SIZE, "%u\n",
@@ -487,30 +376,18 @@ DEV_STAT_SCSI_LU_ATTR_RO(dev_type);
 static ssize_t target_stat_scsi_lu_show_attr_status(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuStatus */
 	return snprintf(page, PAGE_SIZE, "%s\n",
-		(dev->dev_status == TRANSPORT_DEVICE_ACTIVATED) ?
-		"available" : "notavailable");
+		(dev->export_count) ? "available" : "notavailable");
 }
 DEV_STAT_SCSI_LU_ATTR_RO(status);
 
 static ssize_t target_stat_scsi_lu_show_attr_state_bit(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
-
 	/* scsiLuState */
 	return snprintf(page, PAGE_SIZE, "exposed\n");
 }
@@ -519,12 +396,8 @@ DEV_STAT_SCSI_LU_ATTR_RO(state_bit);
 static ssize_t target_stat_scsi_lu_show_attr_num_cmds(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuNumCommands */
 	return snprintf(page, PAGE_SIZE, "%llu\n",
@@ -535,12 +408,8 @@ DEV_STAT_SCSI_LU_ATTR_RO(num_cmds);
 static ssize_t target_stat_scsi_lu_show_attr_read_mbytes(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuReadMegaBytes */
 	return snprintf(page, PAGE_SIZE, "%u\n", (u32)(dev->read_bytes >> 20));
@@ -550,12 +419,8 @@ DEV_STAT_SCSI_LU_ATTR_RO(read_mbytes);
 static ssize_t target_stat_scsi_lu_show_attr_write_mbytes(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuWrittenMegaBytes */
 	return snprintf(page, PAGE_SIZE, "%u\n", (u32)(dev->write_bytes >> 20));
@@ -565,12 +430,8 @@ DEV_STAT_SCSI_LU_ATTR_RO(write_mbytes);
 static ssize_t target_stat_scsi_lu_show_attr_resets(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuInResets */
 	return snprintf(page, PAGE_SIZE, "%u\n", dev->num_resets);
@@ -580,13 +441,6 @@ DEV_STAT_SCSI_LU_ATTR_RO(resets);
 static ssize_t target_stat_scsi_lu_show_attr_full_stat(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
-
 	/* FIXME: scsiLuOutTaskSetFullStatus */
 	return snprintf(page, PAGE_SIZE, "%u\n", 0);
 }
@@ -595,13 +449,6 @@ DEV_STAT_SCSI_LU_ATTR_RO(full_stat);
 static ssize_t target_stat_scsi_lu_show_attr_hs_num_cmds(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
-
 	/* FIXME: scsiLuHSInCommands */
 	return snprintf(page, PAGE_SIZE, "%u\n", 0);
 }
@@ -610,12 +457,8 @@ DEV_STAT_SCSI_LU_ATTR_RO(hs_num_cmds);
 static ssize_t target_stat_scsi_lu_show_attr_creation_time(
 	struct se_dev_stat_grps *sgrps, char *page)
 {
-	struct se_subsystem_dev *se_subdev = container_of(sgrps,
-			struct se_subsystem_dev, dev_stat_grps);
-	struct se_device *dev = se_subdev->se_dev_ptr;
-
-	if (!dev)
-		return -ENODEV;
+	struct se_device *dev =
+		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuCreationTime */
 	return snprintf(page, PAGE_SIZE, "%u\n", (u32)(((u32)dev->creation_time -
@@ -662,20 +505,20 @@ static struct config_item_type target_stat_scsi_lu_cit = {
  * Called from target_core_configfs.c:target_core_make_subdev() to setup
  * the target statistics groups + configfs CITs located in target_core_stat.c
  */
-void target_stat_setup_dev_default_groups(struct se_subsystem_dev *se_subdev)
+void target_stat_setup_dev_default_groups(struct se_device *dev)
 {
-	struct config_group *dev_stat_grp = &se_subdev->dev_stat_grps.stat_group;
+	struct config_group *dev_stat_grp = &dev->dev_stat_grps.stat_group;
 
-	config_group_init_type_name(&se_subdev->dev_stat_grps.scsi_dev_group,
+	config_group_init_type_name(&dev->dev_stat_grps.scsi_dev_group,
 			"scsi_dev", &target_stat_scsi_dev_cit);
-	config_group_init_type_name(&se_subdev->dev_stat_grps.scsi_tgt_dev_group,
+	config_group_init_type_name(&dev->dev_stat_grps.scsi_tgt_dev_group,
 			"scsi_tgt_dev", &target_stat_scsi_tgt_dev_cit);
-	config_group_init_type_name(&se_subdev->dev_stat_grps.scsi_lu_group,
+	config_group_init_type_name(&dev->dev_stat_grps.scsi_lu_group,
 			"scsi_lu", &target_stat_scsi_lu_cit);
 
-	dev_stat_grp->default_groups[0] = &se_subdev->dev_stat_grps.scsi_dev_group;
-	dev_stat_grp->default_groups[1] = &se_subdev->dev_stat_grps.scsi_tgt_dev_group;
-	dev_stat_grp->default_groups[2] = &se_subdev->dev_stat_grps.scsi_lu_group;
+	dev_stat_grp->default_groups[0] = &dev->dev_stat_grps.scsi_dev_group;
+	dev_stat_grp->default_groups[1] = &dev->dev_stat_grps.scsi_tgt_dev_group;
+	dev_stat_grp->default_groups[2] = &dev->dev_stat_grps.scsi_lu_group;
 	dev_stat_grp->default_groups[3] = NULL;
 }
 
@@ -1161,7 +1004,7 @@ static ssize_t target_stat_scsi_transport_show_attr_dev_name(
 		return -ENODEV;
 	}
 	tpg = sep->sep_tpg;
-	wwn = &dev->se_sub_dev->t10_wwn;
+	wwn = &dev->t10_wwn;
 	/* scsiTransportDevName */
 	ret = snprintf(page, PAGE_SIZE, "%s+%s\n",
 			tpg->se_tpg_tfo->tpg_get_wwn(tpg),
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index be75c4331a92..2aaceae964ee 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -371,7 +371,7 @@ int core_tmr_lun_reset(
 	 * which the command was received shall be completed with TASK ABORTED
 	 * status (see SAM-4).
 	 */
-	tas = dev->se_sub_dev->se_dev_attrib.emulate_tas;
+	tas = dev->dev_attrib.emulate_tas;
 	/*
 	 * Determine if this se_tmr is coming from a $FABRIC_MOD
 	 * or struct se_device passthrough..
@@ -399,10 +399,10 @@ int core_tmr_lun_reset(
 	 * LOGICAL UNIT RESET
 	 */
 	if (!preempt_and_abort_list &&
-	     (dev->dev_flags & DF_SPC2_RESERVATIONS)) {
+	     (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)) {
 		spin_lock(&dev->dev_reservation_lock);
 		dev->dev_reserved_node_acl = NULL;
-		dev->dev_flags &= ~DF_SPC2_RESERVATIONS;
+		dev->dev_reservation_flags &= ~DRF_SPC2_RESERVATIONS;
 		spin_unlock(&dev->dev_reservation_lock);
 		pr_debug("LUN_RESET: SCSI-2 Released reservation\n");
 	}
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 9097155e9ebe..d6d24a47ed66 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -659,7 +659,7 @@ static void target_add_to_state_list(struct se_cmd *cmd)
 static void transport_write_pending_qf(struct se_cmd *cmd);
 static void transport_complete_qf(struct se_cmd *cmd);
 
-static void target_qf_do_work(struct work_struct *work)
+void target_qf_do_work(struct work_struct *work)
 {
 	struct se_device *dev = container_of(work, struct se_device,
 					qf_work_queue);
@@ -712,29 +712,15 @@ void transport_dump_dev_state(
 	int *bl)
 {
 	*bl += sprintf(b + *bl, "Status: ");
-	switch (dev->dev_status) {
-	case TRANSPORT_DEVICE_ACTIVATED:
+	if (dev->export_count)
 		*bl += sprintf(b + *bl, "ACTIVATED");
-		break;
-	case TRANSPORT_DEVICE_DEACTIVATED:
+	else
 		*bl += sprintf(b + *bl, "DEACTIVATED");
-		break;
-	case TRANSPORT_DEVICE_SHUTDOWN:
-		*bl += sprintf(b + *bl, "SHUTDOWN");
-		break;
-	case TRANSPORT_DEVICE_OFFLINE_ACTIVATED:
-	case TRANSPORT_DEVICE_OFFLINE_DEACTIVATED:
-		*bl += sprintf(b + *bl, "OFFLINE");
-		break;
-	default:
-		*bl += sprintf(b + *bl, "UNKNOWN=%d", dev->dev_status);
-		break;
-	}
 
 	*bl += sprintf(b + *bl, "  Max Queue Depth: %d", dev->queue_depth);
 	*bl += sprintf(b + *bl, "  SectorSize: %u  HwMaxSectors: %u\n",
-		dev->se_sub_dev->se_dev_attrib.block_size,
-		dev->se_sub_dev->se_dev_attrib.hw_max_sectors);
+		dev->dev_attrib.block_size,
+		dev->dev_attrib.hw_max_sectors);
 	*bl += sprintf(b + *bl, "        ");
 }
 
@@ -991,185 +977,6 @@ transport_set_vpd_ident(struct t10_vpd *vpd, unsigned char *page_83)
 }
 EXPORT_SYMBOL(transport_set_vpd_ident);
 
-static void core_setup_task_attr_emulation(struct se_device *dev)
-{
-	/*
-	 * If this device is from Target_Core_Mod/pSCSI, disable the
-	 * SAM Task Attribute emulation.
-	 *
-	 * This is currently not available in upsream Linux/SCSI Target
-	 * mode code, and is assumed to be disabled while using TCM/pSCSI.
-	 */
-	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV) {
-		dev->dev_task_attr_type = SAM_TASK_ATTR_PASSTHROUGH;
-		return;
-	}
-
-	dev->dev_task_attr_type = SAM_TASK_ATTR_EMULATED;
-	pr_debug("%s: Using SAM_TASK_ATTR_EMULATED for SPC: 0x%02x"
-		" device\n", dev->transport->name,
-		dev->transport->get_device_rev(dev));
-}
-
-static void scsi_dump_inquiry(struct se_device *dev)
-{
-	struct t10_wwn *wwn = &dev->se_sub_dev->t10_wwn;
-	char buf[17];
-	int i, device_type;
-	/*
-	 * Print Linux/SCSI style INQUIRY formatting to the kernel ring buffer
-	 */
-	for (i = 0; i < 8; i++)
-		if (wwn->vendor[i] >= 0x20)
-			buf[i] = wwn->vendor[i];
-		else
-			buf[i] = ' ';
-	buf[i] = '\0';
-	pr_debug("  Vendor: %s\n", buf);
-
-	for (i = 0; i < 16; i++)
-		if (wwn->model[i] >= 0x20)
-			buf[i] = wwn->model[i];
-		else
-			buf[i] = ' ';
-	buf[i] = '\0';
-	pr_debug("  Model: %s\n", buf);
-
-	for (i = 0; i < 4; i++)
-		if (wwn->revision[i] >= 0x20)
-			buf[i] = wwn->revision[i];
-		else
-			buf[i] = ' ';
-	buf[i] = '\0';
-	pr_debug("  Revision: %s\n", buf);
-
-	device_type = dev->transport->get_device_type(dev);
-	pr_debug("  Type:   %s ", scsi_device_type(device_type));
-	pr_debug("                 ANSI SCSI revision: %02x\n",
-				dev->transport->get_device_rev(dev));
-}
-
-struct se_device *transport_add_device_to_core_hba(
-	struct se_hba *hba,
-	struct se_subsystem_api *transport,
-	struct se_subsystem_dev *se_dev,
-	u32 device_flags,
-	void *transport_dev,
-	struct se_dev_limits *dev_limits,
-	const char *inquiry_prod,
-	const char *inquiry_rev)
-{
-	int force_pt;
-	struct se_device  *dev;
-
-	dev = kzalloc(sizeof(struct se_device), GFP_KERNEL);
-	if (!dev) {
-		pr_err("Unable to allocate memory for se_dev_t\n");
-		return NULL;
-	}
-
-	dev->dev_flags		= device_flags;
-	dev->dev_status		|= TRANSPORT_DEVICE_DEACTIVATED;
-	dev->dev_ptr		= transport_dev;
-	dev->se_hba		= hba;
-	dev->se_sub_dev		= se_dev;
-	dev->transport		= transport;
-	INIT_LIST_HEAD(&dev->dev_list);
-	INIT_LIST_HEAD(&dev->dev_sep_list);
-	INIT_LIST_HEAD(&dev->dev_tmr_list);
-	INIT_LIST_HEAD(&dev->delayed_cmd_list);
-	INIT_LIST_HEAD(&dev->state_list);
-	INIT_LIST_HEAD(&dev->qf_cmd_list);
-	spin_lock_init(&dev->execute_task_lock);
-	spin_lock_init(&dev->delayed_cmd_lock);
-	spin_lock_init(&dev->dev_reservation_lock);
-	spin_lock_init(&dev->dev_status_lock);
-	spin_lock_init(&dev->se_port_lock);
-	spin_lock_init(&dev->se_tmr_lock);
-	spin_lock_init(&dev->qf_cmd_lock);
-	atomic_set(&dev->dev_ordered_id, 0);
-
-	se_dev_set_default_attribs(dev, dev_limits);
-
-	dev->dev_index = scsi_get_new_index(SCSI_DEVICE_INDEX);
-	dev->creation_time = get_jiffies_64();
-	spin_lock_init(&dev->stats_lock);
-
-	spin_lock(&hba->device_lock);
-	list_add_tail(&dev->dev_list, &hba->hba_dev_list);
-	hba->dev_count++;
-	spin_unlock(&hba->device_lock);
-	/*
-	 * Setup the SAM Task Attribute emulation for struct se_device
-	 */
-	core_setup_task_attr_emulation(dev);
-	/*
-	 * Force PR and ALUA passthrough emulation with internal object use.
-	 */
-	force_pt = (hba->hba_flags & HBA_FLAGS_INTERNAL_USE);
-	/*
-	 * Setup the Reservations infrastructure for struct se_device
-	 */
-	core_setup_reservations(dev, force_pt);
-	/*
-	 * Setup the Asymmetric Logical Unit Assignment for struct se_device
-	 */
-	if (core_setup_alua(dev, force_pt) < 0)
-		goto err_dev_list;
-
-	/*
-	 * Startup the struct se_device processing thread
-	 */
-	dev->tmr_wq = alloc_workqueue("tmr-%s", WQ_MEM_RECLAIM | WQ_UNBOUND, 1,
-				      dev->transport->name);
-	if (!dev->tmr_wq) {
-		pr_err("Unable to create tmr workqueue for %s\n",
-			dev->transport->name);
-		goto err_dev_list;
-	}
-	/*
-	 * Setup work_queue for QUEUE_FULL
-	 */
-	INIT_WORK(&dev->qf_work_queue, target_qf_do_work);
-	/*
-	 * Preload the initial INQUIRY const values if we are doing
-	 * anything virtual (IBLOCK, FILEIO, RAMDISK), but not for TCM/pSCSI
-	 * passthrough because this is being provided by the backend LLD.
-	 * This is required so that transport_get_inquiry() copies these
-	 * originals once back into DEV_T10_WWN(dev) for the virtual device
-	 * setup.
-	 */
-	if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV) {
-		if (!inquiry_prod || !inquiry_rev) {
-			pr_err("All non TCM/pSCSI plugins require"
-				" INQUIRY consts\n");
-			goto err_wq;
-		}
-
-		strncpy(&dev->se_sub_dev->t10_wwn.vendor[0], "LIO-ORG", 8);
-		strncpy(&dev->se_sub_dev->t10_wwn.model[0], inquiry_prod, 16);
-		strncpy(&dev->se_sub_dev->t10_wwn.revision[0], inquiry_rev, 4);
-	}
-	scsi_dump_inquiry(dev);
-
-	return dev;
-
-err_wq:
-	destroy_workqueue(dev->tmr_wq);
-err_dev_list:
-	spin_lock(&hba->device_lock);
-	list_del(&dev->dev_list);
-	hba->dev_count--;
-	spin_unlock(&hba->device_lock);
-
-	se_release_vpd_for_dev(dev);
-
-	kfree(dev);
-
-	return NULL;
-}
-EXPORT_SYMBOL(transport_add_device_to_core_hba);
-
 int target_cmd_size_check(struct se_cmd *cmd, unsigned int size)
 {
 	struct se_device *dev = cmd->se_dev;
@@ -1191,7 +998,7 @@ int target_cmd_size_check(struct se_cmd *cmd, unsigned int size)
 		 * Reject READ_* or WRITE_* with overflow/underflow for
 		 * type SCF_SCSI_DATA_CDB.
 		 */
-		if (dev->se_sub_dev->se_dev_attrib.block_size != 512)  {
+		if (dev->dev_attrib.block_size != 512)  {
 			pr_err("Failing OVERFLOW/UNDERFLOW for LBA op"
 				" CDB on non 512-byte sector setup subsystem"
 				" plugin: %s\n", dev->transport->name);
@@ -1293,7 +1100,7 @@ int target_setup_cmd_from_cdb(
 	struct se_cmd *cmd,
 	unsigned char *cdb)
 {
-	struct se_subsystem_dev *su_dev = cmd->se_dev->se_sub_dev;
+	struct se_device *dev = cmd->se_dev;
 	u32 pr_reg_type = 0;
 	u8 alua_ascq = 0;
 	unsigned long flags;
@@ -1345,7 +1152,7 @@ int target_setup_cmd_from_cdb(
 		return -EINVAL;
 	}
 
-	ret = su_dev->t10_alua.alua_state_check(cmd, cdb, &alua_ascq);
+	ret = dev->t10_alua.alua_state_check(cmd, cdb, &alua_ascq);
 	if (ret != 0) {
 		/*
 		 * Set SCSI additional sense code (ASC) to 'LUN Not Accessible';
@@ -1371,8 +1178,8 @@ int target_setup_cmd_from_cdb(
 	/*
 	 * Check status for SPC-3 Persistent Reservations
 	 */
-	if (su_dev->t10_pr.pr_ops.t10_reservation_check(cmd, &pr_reg_type)) {
-		if (su_dev->t10_pr.pr_ops.t10_seq_non_holder(
+	if (dev->t10_pr.pr_ops.t10_reservation_check(cmd, &pr_reg_type)) {
+		if (dev->t10_pr.pr_ops.t10_seq_non_holder(
 					cmd, cdb, pr_reg_type) != 0) {
 			cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 			cmd->se_cmd_flags |= SCF_SCSI_RESERVATION_CONFLICT;
@@ -1387,7 +1194,7 @@ int target_setup_cmd_from_cdb(
 		 */
 	}
 
-	ret = cmd->se_dev->transport->parse_cdb(cmd);
+	ret = dev->transport->parse_cdb(cmd);
 	if (ret < 0)
 		return ret;
 
@@ -1759,7 +1566,7 @@ void transport_generic_request_failure(struct se_cmd *cmd)
 		 * See spc4r17, section 7.4.6 Control Mode Page, Table 349
 		 */
 		if (cmd->se_sess &&
-		    cmd->se_dev->se_sub_dev->se_dev_attrib.emulate_ua_intlck_ctrl == 2)
+		    cmd->se_dev->dev_attrib.emulate_ua_intlck_ctrl == 2)
 			core_scsi3_ua_allocate(cmd->se_sess->se_node_acl,
 				cmd->orig_fe_lun, 0x2C,
 				ASCQ_2CH_PREVIOUS_RESERVATION_CONFLICT_STATUS);
diff --git a/drivers/target/target_core_ua.c b/drivers/target/target_core_ua.c
index 6666a0c74f60..59c95ee14749 100644
--- a/drivers/target/target_core_ua.c
+++ b/drivers/target/target_core_ua.c
@@ -237,7 +237,7 @@ void core_scsi3_ua_for_check_condition(
 		 * highest priority UNIT_ATTENTION and ASC/ASCQ without
 		 * clearing it.
 		 */
-		if (dev->se_sub_dev->se_dev_attrib.emulate_ua_intlck_ctrl != 0) {
+		if (dev->dev_attrib.emulate_ua_intlck_ctrl != 0) {
 			*asc = ua->ua_asc;
 			*ascq = ua->ua_ascq;
 			break;
@@ -265,8 +265,8 @@ void core_scsi3_ua_for_check_condition(
 		" INTLCK_CTRL: %d, mapped LUN: %u, got CDB: 0x%02x"
 		" reported ASC: 0x%02x, ASCQ: 0x%02x\n",
 		nacl->se_tpg->se_tpg_tfo->get_fabric_name(),
-		(dev->se_sub_dev->se_dev_attrib.emulate_ua_intlck_ctrl != 0) ? "Reporting" :
-		"Releasing", dev->se_sub_dev->se_dev_attrib.emulate_ua_intlck_ctrl,
+		(dev->dev_attrib.emulate_ua_intlck_ctrl != 0) ? "Reporting" :
+		"Releasing", dev->dev_attrib.emulate_ua_intlck_ctrl,
 		cmd->orig_fe_lun, cmd->t_task_cdb[0], *asc, *ascq);
 }
 
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 2acd54018b64..6c5bfb5ac17f 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -9,6 +9,8 @@ struct se_subsystem_api {
 	struct list_head sub_api_list;
 
 	char name[16];
+	char inquiry_prod[16];
+	char inquiry_rev[4];
 	struct module *owner;
 
 	u8 transport_type;
@@ -16,21 +18,20 @@ struct se_subsystem_api {
 	int (*attach_hba)(struct se_hba *, u32);
 	void (*detach_hba)(struct se_hba *);
 	int (*pmode_enable_hba)(struct se_hba *, unsigned long);
-	void *(*allocate_virtdevice)(struct se_hba *, const char *);
-	struct se_device *(*create_virtdevice)(struct se_hba *,
-				struct se_subsystem_dev *, void *);
-	void (*free_device)(void *);
+
+	struct se_device *(*alloc_device)(struct se_hba *, const char *);
+	int (*configure_device)(struct se_device *);
+	void (*free_device)(struct se_device *device);
+
+	ssize_t (*set_configfs_dev_params)(struct se_device *,
+					   const char *, ssize_t);
+	ssize_t (*show_configfs_dev_params)(struct se_device *, char *);
+
 	void (*transport_complete)(struct se_cmd *cmd,
 				   struct scatterlist *,
 				   unsigned char *);
 
 	int (*parse_cdb)(struct se_cmd *cmd);
-	ssize_t (*check_configfs_dev_params)(struct se_hba *,
-			struct se_subsystem_dev *);
-	ssize_t (*set_configfs_dev_params)(struct se_hba *,
-			struct se_subsystem_dev *, const char *, ssize_t);
-	ssize_t (*show_configfs_dev_params)(struct se_hba *,
-			struct se_subsystem_dev *, char *);
 	u32 (*get_device_rev)(struct se_device *);
 	u32 (*get_device_type)(struct se_device *);
 	sector_t (*get_blocks)(struct se_device *);
@@ -47,10 +48,6 @@ struct spc_ops {
 int	transport_subsystem_register(struct se_subsystem_api *);
 void	transport_subsystem_release(struct se_subsystem_api *);
 
-struct se_device *transport_add_device_to_core_hba(struct se_hba *,
-		struct se_subsystem_api *, struct se_subsystem_dev *, u32,
-		void *, struct se_dev_limits *, const char *, const char *);
-
 void	target_complete_cmd(struct se_cmd *, u8);
 
 int	sbc_parse_cdb(struct se_cmd *cmd, struct spc_ops *ops);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 5be89373ceac..f6355fc325a8 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -62,20 +62,6 @@
 
 #define PYX_TRANSPORT_STATUS_INTERVAL		5 /* In seconds */
 
-/*
- * struct se_subsystem_dev->su_dev_flags
-*/
-#define SDF_FIRMWARE_VPD_UNIT_SERIAL		0x00000001
-#define SDF_EMULATED_VPD_UNIT_SERIAL		0x00000002
-#define SDF_USING_UDEV_PATH			0x00000004
-#define SDF_USING_ALIAS				0x00000008
-
-/*
- * struct se_device->dev_flags
- */
-#define DF_SPC2_RESERVATIONS			0x00000001
-#define DF_SPC2_RESERVATIONS_WITH_ISID		0x00000002
-
 /* struct se_dev_attrib sanity values */
 /* Default max_unmap_lba_count */
 #define DA_MAX_UNMAP_LBA_COUNT			0
@@ -182,16 +168,6 @@ enum transport_lunflags_table {
 	TRANSPORT_LUNFLAGS_READ_WRITE		= 0x04,
 };
 
-/* struct se_device->dev_status */
-enum transport_device_status_table {
-	TRANSPORT_DEVICE_ACTIVATED		= 0x01,
-	TRANSPORT_DEVICE_DEACTIVATED		= 0x02,
-	TRANSPORT_DEVICE_QUEUE_FULL		= 0x04,
-	TRANSPORT_DEVICE_SHUTDOWN		= 0x08,
-	TRANSPORT_DEVICE_OFFLINE_ACTIVATED	= 0x10,
-	TRANSPORT_DEVICE_OFFLINE_DEACTIVATED	= 0x20,
-};
-
 /*
  * Used by transport_send_check_condition_and_sense() and se_cmd->scsi_sense_reason
  * to signal which ASC/ASCQ sense payload should be built.
@@ -246,10 +222,6 @@ enum tcm_tmrsp_table {
 	TMR_FUNCTION_REJECTED		= 255,
 };
 
-struct se_obj {
-	atomic_t obj_access_count;
-};
-
 /*
  * Used by TCM Core internally to signal if ALUA emulation is enabled or
  * disabled, or running in with TCM/pSCSI passthrough mode
@@ -288,7 +260,7 @@ struct t10_alua {
 	u16	alua_tg_pt_gps_counter;
 	u32	alua_tg_pt_gps_count;
 	spinlock_t tg_pt_gps_lock;
-	struct se_subsystem_dev *t10_sub_dev;
+	struct se_device *t10_dev;
 	/* Used for default ALUA Target Port Group */
 	struct t10_alua_tg_pt_gp *default_tg_pt_gp;
 	/* Used for default ALUA Target Port Group ConfigFS group */
@@ -335,7 +307,7 @@ struct t10_alua_tg_pt_gp {
 	atomic_t tg_pt_gp_ref_cnt;
 	spinlock_t tg_pt_gp_lock;
 	struct mutex tg_pt_gp_md_mutex;
-	struct se_subsystem_dev *tg_pt_gp_su_dev;
+	struct se_device *tg_pt_gp_dev;
 	struct config_group tg_pt_gp_group;
 	struct list_head tg_pt_gp_list;
 	struct list_head tg_pt_gp_mem_list;
@@ -366,7 +338,7 @@ struct t10_wwn {
 	char revision[4];
 	char unit_serial[INQUIRY_VPD_SERIAL_LEN];
 	spinlock_t t10_vpd_lock;
-	struct se_subsystem_dev *t10_sub_dev;
+	struct se_device *t10_dev;
 	struct config_group t10_wwn_group;
 	struct list_head t10_vpd_list;
 };
@@ -662,15 +634,6 @@ struct se_dev_entry {
 	struct list_head	ua_list;
 };
 
-struct se_dev_limits {
-	/* Max supported HW queue depth */
-	u32		hw_queue_depth;
-	/* Max supported virtual queue depth */
-	u32		queue_depth;
-	/* From include/linux/blkdev.h for the other HW/SW limits. */
-	struct queue_limits limits;
-};
-
 struct se_dev_attrib {
 	int		emulate_dpo;
 	int		emulate_fua_write;
@@ -696,7 +659,7 @@ struct se_dev_attrib {
 	u32		max_unmap_block_desc_count;
 	u32		unmap_granularity;
 	u32		unmap_granularity_alignment;
-	struct se_subsystem_dev *da_sub_dev;
+	struct se_device *da_dev;
 	struct config_group da_group;
 };
 
@@ -707,48 +670,24 @@ struct se_dev_stat_grps {
 	struct config_group scsi_lu_group;
 };
 
-struct se_subsystem_dev {
-/* Used for struct se_subsystem_dev-->se_dev_alias, must be less than PAGE_SIZE */
-#define SE_DEV_ALIAS_LEN		512
-	unsigned char	se_dev_alias[SE_DEV_ALIAS_LEN];
-/* Used for struct se_subsystem_dev->se_dev_udev_path[], must be less than PAGE_SIZE */
-#define SE_UDEV_PATH_LEN		512
-	unsigned char	se_dev_udev_path[SE_UDEV_PATH_LEN];
-	u32		su_dev_flags;
-	struct se_hba *se_dev_hba;
-	struct se_device *se_dev_ptr;
-	struct se_dev_attrib se_dev_attrib;
-	/* T10 Asymmetric Logical Unit Assignment for Target Ports */
-	struct t10_alua	t10_alua;
-	/* T10 Inquiry and VPD WWN Information */
-	struct t10_wwn	t10_wwn;
-	/* T10 SPC-2 + SPC-3 Reservations */
-	struct t10_reservation t10_pr;
-	spinlock_t      se_dev_lock;
-	void            *se_dev_su_ptr;
-	struct config_group se_dev_group;
-	/* For T10 Reservations */
-	struct config_group se_dev_pr_group;
-	/* For target_core_stat.c groups */
-	struct se_dev_stat_grps dev_stat_grps;
-};
-
 struct se_device {
 	/* RELATIVE TARGET PORT IDENTIFER Counter */
 	u16			dev_rpti_counter;
 	/* Used for SAM Task Attribute ordering */
 	u32			dev_cur_ordered_id;
 	u32			dev_flags;
+#define DF_CONFIGURED				0x00000001
+#define DF_FIRMWARE_VPD_UNIT_SERIAL		0x00000002
+#define DF_EMULATED_VPD_UNIT_SERIAL		0x00000004
+#define DF_USING_UDEV_PATH			0x00000008
+#define DF_USING_ALIAS				0x00000010
 	u32			dev_port_count;
-	/* See transport_device_status_table */
-	u32			dev_status;
 	/* Physical device queue depth */
 	u32			queue_depth;
 	/* Used for SPC-2 reservations enforce of ISIDs */
 	u64			dev_res_bin_isid;
 	t10_task_attr_index_t	dev_task_attr_type;
 	/* Pointer to transport specific device structure */
-	void 			*dev_ptr;
 	u32			dev_index;
 	u64			creation_time;
 	u32			num_resets;
@@ -761,13 +700,13 @@ struct se_device {
 	atomic_t		dev_ordered_id;
 	atomic_t		dev_ordered_sync;
 	atomic_t		dev_qf_count;
-	struct se_obj		dev_obj;
-	struct se_obj		dev_access_obj;
-	struct se_obj		dev_export_obj;
+	int			export_count;
 	spinlock_t		delayed_cmd_lock;
 	spinlock_t		execute_task_lock;
 	spinlock_t		dev_reservation_lock;
-	spinlock_t		dev_status_lock;
+	unsigned int		dev_reservation_flags;
+#define DRF_SPC2_RESERVATIONS			0x00000001
+#define DRF_SPC2_RESERVATIONS_WITH_ISID		0x00000002
 	spinlock_t		se_port_lock;
 	spinlock_t		se_tmr_lock;
 	spinlock_t		qf_cmd_lock;
@@ -786,7 +725,20 @@ struct se_device {
 	struct list_head	qf_cmd_list;
 	/* Pointer to associated SE HBA */
 	struct se_hba		*se_hba;
-	struct se_subsystem_dev *se_sub_dev;
+	/* T10 Inquiry and VPD WWN Information */
+	struct t10_wwn		t10_wwn;
+	/* T10 Asymmetric Logical Unit Assignment for Target Ports */
+	struct t10_alua		t10_alua;
+	/* T10 SPC-2 + SPC-3 Reservations */
+	struct t10_reservation	t10_pr;
+	struct se_dev_attrib	dev_attrib;
+	struct config_group	dev_group;
+	struct config_group	dev_pr_group;
+	struct se_dev_stat_grps dev_stat_grps;
+#define SE_DEV_ALIAS_LEN 512		/* must be less than PAGE_SIZE */
+	unsigned char		dev_alias[SE_DEV_ALIAS_LEN];
+#define SE_UDEV_PATH_LEN 512		/* must be less than PAGE_SIZE */
+	unsigned char		udev_path[SE_UDEV_PATH_LEN];
 	/* Pointer to template of function pointers for transport */
 	struct se_subsystem_api *transport;
 	/* Linked list for struct se_hba struct se_device list */
@@ -803,8 +755,6 @@ struct se_hba {
 	u32			hba_index;
 	/* Pointer to transport specific host structure. */
 	void			*hba_ptr;
-	/* Linked list for struct se_device */
-	struct list_head	hba_dev_list;
 	struct list_head	hba_node;
 	spinlock_t		device_lock;
 	struct config_group	hba_group;
-- 
cgit v1.2.3-55-g7522


From 9e999a6c51fe74a41a76038c64ce038ff9243bfb Mon Sep 17 00:00:00 2001
From: Christoph Hellwig
Date: Sun, 7 Oct 2012 10:55:50 -0400
Subject: target: rename spc_ops

These really are sbc_ops, so name them correctly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_file.c    | 4 ++--
 drivers/target/target_core_iblock.c  | 4 ++--
 drivers/target/target_core_rd.c      | 4 ++--
 drivers/target/target_core_sbc.c     | 2 +-
 include/target/target_core_backend.h | 4 ++--
 5 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index a89d80dacad2..571d3645f58a 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -528,14 +528,14 @@ static sector_t fd_get_blocks(struct se_device *dev)
 	return div_u64(dev_size, dev->dev_attrib.block_size);
 }
 
-static struct spc_ops fd_spc_ops = {
+static struct sbc_ops fd_sbc_ops = {
 	.execute_rw		= fd_execute_rw,
 	.execute_sync_cache	= fd_execute_sync_cache,
 };
 
 static int fd_parse_cdb(struct se_cmd *cmd)
 {
-	return sbc_parse_cdb(cmd, &fd_spc_ops);
+	return sbc_parse_cdb(cmd, &fd_sbc_ops);
 }
 
 static struct se_subsystem_api fileio_template = {
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index dd6cd92cd9d8..969eed8bff52 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -709,7 +709,7 @@ static void iblock_bio_done(struct bio *bio, int err)
 	iblock_complete_cmd(cmd);
 }
 
-static struct spc_ops iblock_spc_ops = {
+static struct sbc_ops iblock_sbc_ops = {
 	.execute_rw		= iblock_execute_rw,
 	.execute_sync_cache	= iblock_execute_sync_cache,
 	.execute_write_same	= iblock_execute_write_same,
@@ -718,7 +718,7 @@ static struct spc_ops iblock_spc_ops = {
 
 static int iblock_parse_cdb(struct se_cmd *cmd)
 {
-	return sbc_parse_cdb(cmd, &iblock_spc_ops);
+	return sbc_parse_cdb(cmd, &iblock_sbc_ops);
 }
 
 static struct se_subsystem_api iblock_template = {
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index d083f39c4b67..1b36e67b1153 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -437,13 +437,13 @@ static sector_t rd_get_blocks(struct se_device *dev)
 	return blocks_long;
 }
 
-static struct spc_ops rd_spc_ops = {
+static struct sbc_ops rd_sbc_ops = {
 	.execute_rw		= rd_execute_rw,
 };
 
 static int rd_parse_cdb(struct se_cmd *cmd)
 {
-	return sbc_parse_cdb(cmd, &rd_spc_ops);
+	return sbc_parse_cdb(cmd, &rd_sbc_ops);
 }
 
 static struct se_subsystem_api rd_mcp_template = {
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 035193d04fa2..a77a19c8d923 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -313,7 +313,7 @@ out:
 	kfree(buf);
 }
 
-int sbc_parse_cdb(struct se_cmd *cmd, struct spc_ops *ops)
+int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 {
 	struct se_device *dev = cmd->se_dev;
 	unsigned char *cdb = cmd->t_task_cdb;
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 6c5bfb5ac17f..1c43955f4cb5 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -38,7 +38,7 @@ struct se_subsystem_api {
 	unsigned char *(*get_sense_buffer)(struct se_cmd *);
 };
 
-struct spc_ops {
+struct sbc_ops {
 	int (*execute_rw)(struct se_cmd *cmd);
 	int (*execute_sync_cache)(struct se_cmd *cmd);
 	int (*execute_write_same)(struct se_cmd *cmd);
@@ -50,7 +50,7 @@ void	transport_subsystem_release(struct se_subsystem_api *);
 
 void	target_complete_cmd(struct se_cmd *, u8);
 
-int	sbc_parse_cdb(struct se_cmd *cmd, struct spc_ops *ops);
+int	sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops);
 int	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
 int	spc_get_write_same_sectors(struct se_cmd *cmd);
 
-- 
cgit v1.2.3-55-g7522


From 8de530a523fd3cc46b5d8d96f3016298c5c808ac Mon Sep 17 00:00:00 2001
From: Christoph Hellwig
Date: Sun, 7 Oct 2012 10:55:52 -0400
Subject: target/pscsi: call spc_emulate_report_luns directly

No need to indirect through spc_parse_cdb if we only ever call it for
REPORT LUNS emulation.

(nab: Add missing EXPORT_SYMBOL for spc_emulate_report_luns)

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_pscsi.c   | 11 ++---------
 drivers/target/target_core_spc.c     |  3 ++-
 include/target/target_core_backend.h |  1 +
 3 files changed, 5 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index b2965084eb4f..dc10e29934d7 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -985,8 +985,6 @@ static inline void pscsi_clear_cdb_lun(unsigned char *cdb)
 static int pscsi_parse_cdb(struct se_cmd *cmd)
 {
 	unsigned char *cdb = cmd->t_task_cdb;
-	unsigned int dummy_size;
-	int ret;
 
 	if (cmd->se_cmd_flags & SCF_BIDI) {
 		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
@@ -1003,10 +1001,7 @@ static int pscsi_parse_cdb(struct se_cmd *cmd)
 	 */
 	switch (cdb[0]) {
 	case REPORT_LUNS:
-		ret = spc_parse_cdb(cmd, &dummy_size);
-		if (ret)
-			return ret;
-		break;
+		return spc_emulate_report_luns(cmd);
 	case READ_6:
 	case READ_10:
 	case READ_12:
@@ -1020,10 +1015,8 @@ static int pscsi_parse_cdb(struct se_cmd *cmd)
 		/* FALLTHROUGH*/
 	default:
 		cmd->execute_cmd = pscsi_execute_cmd;
-		break;
+		return 0;
 	}
-
-	return 0;
 }
 
 static int pscsi_execute_cmd(struct se_cmd *cmd)
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 07b82700dcd8..1f1ddb8183c7 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -908,7 +908,7 @@ static int spc_emulate_request_sense(struct se_cmd *cmd)
 	return 0;
 }
 
-static int spc_emulate_report_luns(struct se_cmd *cmd)
+int spc_emulate_report_luns(struct se_cmd *cmd)
 {
 	struct se_dev_entry *deve;
 	struct se_session *sess = cmd->se_sess;
@@ -970,6 +970,7 @@ done:
 	target_complete_cmd(cmd, GOOD);
 	return 0;
 }
+EXPORT_SYMBOL(spc_emulate_report_luns);
 
 static int spc_emulate_testunitready(struct se_cmd *cmd)
 {
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 1c43955f4cb5..e7a03056c957 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -52,6 +52,7 @@ void	target_complete_cmd(struct se_cmd *, u8);
 
 int	sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops);
 int	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
+int	spc_emulate_report_luns(struct se_cmd *cmd);
 int	spc_get_write_same_sectors(struct se_cmd *cmd);
 
 void	transport_set_vpd_proto_id(struct t10_vpd *, unsigned char *);
-- 
cgit v1.2.3-55-g7522


From 6f23ac8a39418d6c6711f4fd73cc4519067d7f08 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig
Date: Sun, 7 Oct 2012 10:55:53 -0400
Subject: target: provide generic sbc device type/revision helpers

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_file.c    | 22 ++--------------------
 drivers/target/target_core_iblock.c  | 14 ++------------
 drivers/target/target_core_rd.c      | 14 ++------------
 drivers/target/target_core_sbc.c     | 12 ++++++++++++
 include/target/target_core_backend.h |  5 ++++-
 5 files changed, 22 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 571d3645f58a..2a3e2bbd8078 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -491,24 +491,6 @@ static ssize_t fd_show_configfs_dev_params(struct se_device *dev, char *b)
 	return bl;
 }
 
-/*	fd_get_device_rev(): (Part of se_subsystem_api_t template)
- *
- *
- */
-static u32 fd_get_device_rev(struct se_device *dev)
-{
-	return SCSI_SPC_2; /* Returns SPC-3 in Initiator Data */
-}
-
-/*	fd_get_device_type(): (Part of se_subsystem_api_t template)
- *
- *
- */
-static u32 fd_get_device_type(struct se_device *dev)
-{
-	return TYPE_DISK;
-}
-
 static sector_t fd_get_blocks(struct se_device *dev)
 {
 	struct fd_dev *fd_dev = FD_DEV(dev);
@@ -552,8 +534,8 @@ static struct se_subsystem_api fileio_template = {
 	.parse_cdb		= fd_parse_cdb,
 	.set_configfs_dev_params = fd_set_configfs_dev_params,
 	.show_configfs_dev_params = fd_show_configfs_dev_params,
-	.get_device_rev		= fd_get_device_rev,
-	.get_device_type	= fd_get_device_type,
+	.get_device_rev		= sbc_get_device_rev,
+	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= fd_get_blocks,
 };
 
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 969eed8bff52..701877f9cd33 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -664,16 +664,6 @@ fail:
 	return -ENOMEM;
 }
 
-static u32 iblock_get_device_rev(struct se_device *dev)
-{
-	return SCSI_SPC_2; /* Returns SPC-3 in Initiator Data */
-}
-
-static u32 iblock_get_device_type(struct se_device *dev)
-{
-	return TYPE_DISK;
-}
-
 static sector_t iblock_get_blocks(struct se_device *dev)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
@@ -735,8 +725,8 @@ static struct se_subsystem_api iblock_template = {
 	.parse_cdb		= iblock_parse_cdb,
 	.set_configfs_dev_params = iblock_set_configfs_dev_params,
 	.show_configfs_dev_params = iblock_show_configfs_dev_params,
-	.get_device_rev		= iblock_get_device_rev,
-	.get_device_type	= iblock_get_device_type,
+	.get_device_rev		= sbc_get_device_rev,
+	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= iblock_get_blocks,
 };
 
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 1b36e67b1153..6348b6672526 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -417,16 +417,6 @@ static ssize_t rd_show_configfs_dev_params(struct se_device *dev, char *b)
 	return bl;
 }
 
-static u32 rd_get_device_rev(struct se_device *dev)
-{
-	return SCSI_SPC_2; /* Returns SPC-3 in Initiator Data */
-}
-
-static u32 rd_get_device_type(struct se_device *dev)
-{
-	return TYPE_DISK;
-}
-
 static sector_t rd_get_blocks(struct se_device *dev)
 {
 	struct rd_dev *rd_dev = RD_DEV(dev);
@@ -459,8 +449,8 @@ static struct se_subsystem_api rd_mcp_template = {
 	.parse_cdb		= rd_parse_cdb,
 	.set_configfs_dev_params = rd_set_configfs_dev_params,
 	.show_configfs_dev_params = rd_show_configfs_dev_params,
-	.get_device_rev		= rd_get_device_rev,
-	.get_device_type	= rd_get_device_type,
+	.get_device_rev		= sbc_get_device_rev,
+	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= rd_get_blocks,
 };
 
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index a77a19c8d923..01686954cfa0 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -603,3 +603,15 @@ out_invalid_cdb_field:
 	return -EINVAL;
 }
 EXPORT_SYMBOL(sbc_parse_cdb);
+
+u32 sbc_get_device_rev(struct se_device *dev)
+{
+	return SCSI_SPC_2; /* Returns SPC-3 in Initiator Data */
+}
+EXPORT_SYMBOL(sbc_get_device_rev);
+
+u32 sbc_get_device_type(struct se_device *dev)
+{
+	return TYPE_DISK;
+}
+EXPORT_SYMBOL(sbc_get_device_type);
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index e7a03056c957..b7f3936453e1 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -50,11 +50,14 @@ void	transport_subsystem_release(struct se_subsystem_api *);
 
 void	target_complete_cmd(struct se_cmd *, u8);
 
-int	sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops);
 int	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
 int	spc_emulate_report_luns(struct se_cmd *cmd);
 int	spc_get_write_same_sectors(struct se_cmd *cmd);
 
+int	sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops);
+u32	sbc_get_device_rev(struct se_device *dev);
+u32	sbc_get_device_type(struct se_device *dev);
+
 void	transport_set_vpd_proto_id(struct t10_vpd *, unsigned char *);
 int	transport_set_vpd_assoc(struct t10_vpd *, unsigned char *);
 int	transport_set_vpd_ident_type(struct t10_vpd *, unsigned char *);
-- 
cgit v1.2.3-55-g7522


From 019c4ca621488739b1bfb7597a14ac7f0cbcc908 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig
Date: Wed, 10 Oct 2012 17:37:14 -0400
Subject: target: kill dev->dev_task_attr_type

We can just key off ordered tag emulation of the transport_type field.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c    |   5 --
 drivers/target/target_core_spc.c       |   6 +-
 drivers/target/target_core_transport.c | 130 +++++++++++++++++----------------
 include/target/target_core_base.h      |  11 ---
 4 files changed, 69 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index e45a70970548..6a27e7fd33fb 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1412,11 +1412,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	dev->dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS;
 	dev->dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS;
 
-	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
-		dev->dev_task_attr_type = SAM_TASK_ATTR_PASSTHROUGH;
-	else
-		dev->dev_task_attr_type = SAM_TASK_ATTR_EMULATED;
-
 	return dev;
 }
 
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 1f1ddb8183c7..8ca62631ec7f 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -1054,8 +1054,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		 * Do implict HEAD_OF_QUEUE processing for INQUIRY.
 		 * See spc4r17 section 5.3
 		 */
-		if (cmd->se_dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED)
-			cmd->sam_task_attr = MSG_HEAD_TAG;
+		cmd->sam_task_attr = MSG_HEAD_TAG;
 		cmd->execute_cmd = spc_emulate_inquiry;
 		break;
 	case SECURITY_PROTOCOL_IN:
@@ -1083,8 +1082,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		 * Do implict HEAD_OF_QUEUE processing for REPORT_LUNS
 		 * See spc4r17 section 5.3
 		 */
-		if (cmd->se_dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED)
-			cmd->sam_task_attr = MSG_HEAD_TAG;
+		cmd->sam_task_attr = MSG_HEAD_TAG;
 		break;
 	case TEST_UNIT_READY:
 		cmd->execute_cmd = spc_emulate_testunitready;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index c80d88435f90..757e3777ce79 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1068,11 +1068,13 @@ EXPORT_SYMBOL(transport_init_se_cmd);
 
 static int transport_check_alloc_task_attr(struct se_cmd *cmd)
 {
+	struct se_device *dev = cmd->se_dev;
+
 	/*
 	 * Check if SAM Task Attribute emulation is enabled for this
 	 * struct se_device storage object
 	 */
-	if (cmd->se_dev->dev_task_attr_type != SAM_TASK_ATTR_EMULATED)
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
 		return 0;
 
 	if (cmd->sam_task_attr == MSG_ACA_TAG) {
@@ -1084,11 +1086,11 @@ static int transport_check_alloc_task_attr(struct se_cmd *cmd)
 	 * Used to determine when ORDERED commands should go from
 	 * Dormant to Active status.
 	 */
-	cmd->se_ordered_id = atomic_inc_return(&cmd->se_dev->dev_ordered_id);
+	cmd->se_ordered_id = atomic_inc_return(&dev->dev_ordered_id);
 	smp_mb__after_atomic_inc();
 	pr_debug("Allocated se_ordered_id: %u for Task Attr: 0x%02x on %s\n",
 			cmd->se_ordered_id, cmd->sam_task_attr,
-			cmd->se_dev->transport->name);
+			dev->transport->name);
 	return 0;
 }
 
@@ -1534,8 +1536,7 @@ void transport_generic_request_failure(struct se_cmd *cmd)
 	/*
 	 * For SAM Task Attribute emulation for failed struct se_cmd
 	 */
-	if (cmd->se_dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED)
-		transport_complete_task_attr(cmd);
+	transport_complete_task_attr(cmd);
 
 	switch (cmd->scsi_sense_reason) {
 	case TCM_NON_EXISTENT_LUN:
@@ -1619,49 +1620,12 @@ static void __target_execute_cmd(struct se_cmd *cmd)
 	}
 }
 
-void target_execute_cmd(struct se_cmd *cmd)
+static bool target_handle_task_attr(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 
-	/*
-	 * If the received CDB has aleady been aborted stop processing it here.
-	 */
-	if (transport_check_aborted_status(cmd, 1))
-		return;
-
-	/*
-	 * Determine if IOCTL context caller in requesting the stopping of this
-	 * command for LUN shutdown purposes.
-	 */
-	spin_lock_irq(&cmd->t_state_lock);
-	if (cmd->transport_state & CMD_T_LUN_STOP) {
-		pr_debug("%s:%d CMD_T_LUN_STOP for ITT: 0x%08x\n",
-			__func__, __LINE__, cmd->se_tfo->get_task_tag(cmd));
-
-		cmd->transport_state &= ~CMD_T_ACTIVE;
-		spin_unlock_irq(&cmd->t_state_lock);
-		complete(&cmd->transport_lun_stop_comp);
-		return;
-	}
-	/*
-	 * Determine if frontend context caller is requesting the stopping of
-	 * this command for frontend exceptions.
-	 */
-	if (cmd->transport_state & CMD_T_STOP) {
-		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08x\n",
-			__func__, __LINE__,
-			cmd->se_tfo->get_task_tag(cmd));
-
-		spin_unlock_irq(&cmd->t_state_lock);
-		complete(&cmd->t_transport_stop_comp);
-		return;
-	}
-
-	cmd->t_state = TRANSPORT_PROCESSING;
-	spin_unlock_irq(&cmd->t_state_lock);
-
-	if (dev->dev_task_attr_type != SAM_TASK_ATTR_EMULATED)
-		goto execute;
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+		return false;
 
 	/*
 	 * Check for the existence of HEAD_OF_QUEUE, and if true return 1
@@ -1672,7 +1636,7 @@ void target_execute_cmd(struct se_cmd *cmd)
 		pr_debug("Added HEAD_OF_QUEUE for CDB: 0x%02x, "
 			 "se_ordered_id: %u\n",
 			 cmd->t_task_cdb[0], cmd->se_ordered_id);
-		goto execute;
+		return false;
 	case MSG_ORDERED_TAG:
 		atomic_inc(&dev->dev_ordered_sync);
 		smp_mb__after_atomic_inc();
@@ -1686,7 +1650,7 @@ void target_execute_cmd(struct se_cmd *cmd)
 		 * exist that need to be completed first.
 		 */
 		if (!atomic_read(&dev->simple_cmds))
-			goto execute;
+			return false;
 		break;
 	default:
 		/*
@@ -1697,23 +1661,61 @@ void target_execute_cmd(struct se_cmd *cmd)
 		break;
 	}
 
-	if (atomic_read(&dev->dev_ordered_sync) != 0) {
-		spin_lock(&dev->delayed_cmd_lock);
-		list_add_tail(&cmd->se_delayed_node, &dev->delayed_cmd_list);
-		spin_unlock(&dev->delayed_cmd_lock);
+	if (atomic_read(&dev->dev_ordered_sync) == 0)
+		return false;
 
-		pr_debug("Added CDB: 0x%02x Task Attr: 0x%02x to"
-			" delayed CMD list, se_ordered_id: %u\n",
-			cmd->t_task_cdb[0], cmd->sam_task_attr,
-			cmd->se_ordered_id);
+	spin_lock(&dev->delayed_cmd_lock);
+	list_add_tail(&cmd->se_delayed_node, &dev->delayed_cmd_list);
+	spin_unlock(&dev->delayed_cmd_lock);
+
+	pr_debug("Added CDB: 0x%02x Task Attr: 0x%02x to"
+		" delayed CMD list, se_ordered_id: %u\n",
+		cmd->t_task_cdb[0], cmd->sam_task_attr,
+		cmd->se_ordered_id);
+	return true;
+}
+
+void target_execute_cmd(struct se_cmd *cmd)
+{
+	/*
+	 * If the received CDB has aleady been aborted stop processing it here.
+	 */
+	if (transport_check_aborted_status(cmd, 1))
 		return;
-	}
 
-execute:
 	/*
-	 * Otherwise, no ORDERED task attributes exist..
+	 * Determine if IOCTL context caller in requesting the stopping of this
+	 * command for LUN shutdown purposes.
 	 */
-	__target_execute_cmd(cmd);
+	spin_lock_irq(&cmd->t_state_lock);
+	if (cmd->transport_state & CMD_T_LUN_STOP) {
+		pr_debug("%s:%d CMD_T_LUN_STOP for ITT: 0x%08x\n",
+			__func__, __LINE__, cmd->se_tfo->get_task_tag(cmd));
+
+		cmd->transport_state &= ~CMD_T_ACTIVE;
+		spin_unlock_irq(&cmd->t_state_lock);
+		complete(&cmd->transport_lun_stop_comp);
+		return;
+	}
+	/*
+	 * Determine if frontend context caller is requesting the stopping of
+	 * this command for frontend exceptions.
+	 */
+	if (cmd->transport_state & CMD_T_STOP) {
+		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08x\n",
+			__func__, __LINE__,
+			cmd->se_tfo->get_task_tag(cmd));
+
+		spin_unlock_irq(&cmd->t_state_lock);
+		complete(&cmd->t_transport_stop_comp);
+		return;
+	}
+
+	cmd->t_state = TRANSPORT_PROCESSING;
+	spin_unlock_irq(&cmd->t_state_lock);
+
+	if (!target_handle_task_attr(cmd))
+		__target_execute_cmd(cmd);
 }
 EXPORT_SYMBOL(target_execute_cmd);
 
@@ -1752,6 +1754,9 @@ static void transport_complete_task_attr(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+		return;
+
 	if (cmd->sam_task_attr == MSG_SIMPLE_TAG) {
 		atomic_dec(&dev->simple_cmds);
 		smp_mb__after_atomic_dec();
@@ -1780,8 +1785,7 @@ static void transport_complete_qf(struct se_cmd *cmd)
 {
 	int ret = 0;
 
-	if (cmd->se_dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED)
-		transport_complete_task_attr(cmd);
+	transport_complete_task_attr(cmd);
 
 	if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) {
 		ret = cmd->se_tfo->queue_status(cmd);
@@ -1839,8 +1843,8 @@ static void target_complete_ok_work(struct work_struct *work)
 	 * delayed execution list after a HEAD_OF_QUEUE or ORDERED Task
 	 * Attribute.
 	 */
-	if (cmd->se_dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED)
-		transport_complete_task_attr(cmd);
+	transport_complete_task_attr(cmd);
+
 	/*
 	 * Check to schedule QUEUE_FULL work, or execute an existing
 	 * cmd->transport_qf_callback()
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index f6355fc325a8..15af1307d064 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -232,16 +232,6 @@ typedef enum {
 	SPC3_ALUA_EMULATED
 } t10_alua_index_t;
 
-/*
- * Used by TCM Core internally to signal if SAM Task Attribute emulation
- * is enabled or disabled, or running in with TCM/pSCSI passthrough mode
- */
-typedef enum {
-	SAM_TASK_ATTR_PASSTHROUGH,
-	SAM_TASK_ATTR_UNTAGGED,
-	SAM_TASK_ATTR_EMULATED
-} t10_task_attr_index_t;
-
 /*
  * Used for target SCSI statistics
  */
@@ -686,7 +676,6 @@ struct se_device {
 	u32			queue_depth;
 	/* Used for SPC-2 reservations enforce of ISIDs */
 	u64			dev_res_bin_isid;
-	t10_task_attr_index_t	dev_task_attr_type;
 	/* Pointer to transport specific device structure */
 	u32			dev_index;
 	u64			creation_time;
-- 
cgit v1.2.3-55-g7522


From d977f4377fbc396b888e12fdb3b13118b09ca7db Mon Sep 17 00:00:00 2001
From: Christoph Hellwig
Date: Wed, 10 Oct 2012 17:37:15 -0400
Subject: target: simplify reservations code

We do not support host-level reservations for the pscsi backend, and all
virtual backends are newere than SCSI-2, so just make the combined
SPC-3 + SCSI-2 support the only supported variant and kill the switches
for the different implementations, given that this code handles the no-op
version just fine.

(hch: Update DRF_SPC2_RESERVATIONS lock usage)

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/target/target_core_configfs.c  | 158 +++++++++------------------
 drivers/target/target_core_device.c    |   3 -
 drivers/target/target_core_pr.c        | 192 +++++++++++----------------------
 drivers/target/target_core_pr.h        |   2 +-
 drivers/target/target_core_spc.c       |  19 +---
 drivers/target/target_core_transport.c |  22 ++--
 include/target/target_core_base.h      |  29 -----
 7 files changed, 127 insertions(+), 298 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 7272016ed05f..3d5570da41eb 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -970,13 +970,8 @@ static struct target_core_dev_pr_attribute target_core_dev_pr_##_name =	\
 	__CONFIGFS_EATTR_RO(_name,					\
 	target_core_dev_pr_show_attr_##_name);
 
-/*
- * res_holder
- */
-static ssize_t target_core_dev_pr_show_spc3_res(
-	struct se_device *dev,
-	char *page,
-	ssize_t *len)
+static ssize_t target_core_dev_pr_show_spc3_res(struct se_device *dev,
+		char *page)
 {
 	struct se_node_acl *se_nacl;
 	struct t10_pr_registration *pr_reg;
@@ -985,68 +980,52 @@ static ssize_t target_core_dev_pr_show_spc3_res(
 
 	memset(i_buf, 0, PR_REG_ISID_ID_LEN);
 
-	spin_lock(&dev->dev_reservation_lock);
 	pr_reg = dev->dev_pr_res_holder;
-	if (!pr_reg) {
-		*len += sprintf(page + *len, "No SPC-3 Reservation holder\n");
-		spin_unlock(&dev->dev_reservation_lock);
-		return *len;
-	}
+	if (!pr_reg)
+		return sprintf(page, "No SPC-3 Reservation holder\n");
+
 	se_nacl = pr_reg->pr_reg_nacl;
 	prf_isid = core_pr_dump_initiator_port(pr_reg, &i_buf[0],
 				PR_REG_ISID_ID_LEN);
 
-	*len += sprintf(page + *len, "SPC-3 Reservation: %s Initiator: %s%s\n",
+	return sprintf(page, "SPC-3 Reservation: %s Initiator: %s%s\n",
 		se_nacl->se_tpg->se_tpg_tfo->get_fabric_name(),
 		se_nacl->initiatorname, (prf_isid) ? &i_buf[0] : "");
-	spin_unlock(&dev->dev_reservation_lock);
-
-	return *len;
 }
 
-static ssize_t target_core_dev_pr_show_spc2_res(
-	struct se_device *dev,
-	char *page,
-	ssize_t *len)
+static ssize_t target_core_dev_pr_show_spc2_res(struct se_device *dev,
+		char *page)
 {
 	struct se_node_acl *se_nacl;
+	ssize_t len;
 
-	spin_lock(&dev->dev_reservation_lock);
 	se_nacl = dev->dev_reserved_node_acl;
-	if (!se_nacl) {
-		*len += sprintf(page + *len, "No SPC-2 Reservation holder\n");
-		spin_unlock(&dev->dev_reservation_lock);
-		return *len;
+	if (se_nacl) {
+		len = sprintf(page,
+			      "SPC-2 Reservation: %s Initiator: %s\n",
+			      se_nacl->se_tpg->se_tpg_tfo->get_fabric_name(),
+			      se_nacl->initiatorname);
+	} else {
+		len = sprintf(page, "No SPC-2 Reservation holder\n");
 	}
-	*len += sprintf(page + *len, "SPC-2 Reservation: %s Initiator: %s\n",
-		se_nacl->se_tpg->se_tpg_tfo->get_fabric_name(),
-		se_nacl->initiatorname);
-	spin_unlock(&dev->dev_reservation_lock);
-
-	return *len;
+	return len;
 }
 
 static ssize_t target_core_dev_pr_show_attr_res_holder(struct se_device *dev,
 		char *page)
 {
-	ssize_t len = 0;
+	int ret;
 
-	switch (dev->t10_pr.res_type) {
-	case SPC3_PERSISTENT_RESERVATIONS:
-		target_core_dev_pr_show_spc3_res(dev, page, &len);
-		break;
-	case SPC2_RESERVATIONS:
-		target_core_dev_pr_show_spc2_res(dev, page, &len);
-		break;
-	case SPC_PASSTHROUGH:
-		len += sprintf(page+len, "Passthrough\n");
-		break;
-	default:
-		len += sprintf(page+len, "Unknown\n");
-		break;
-	}
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+		return sprintf(page, "Passthrough\n");
 
-	return len;
+	spin_lock(&dev->dev_reservation_lock);
+	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
+		ret = target_core_dev_pr_show_spc2_res(dev, page);
+	else
+		ret = target_core_dev_pr_show_spc3_res(dev, page);
+	spin_unlock(&dev->dev_reservation_lock);
+	return ret;
 }
 
 SE_DEV_PR_ATTR_RO(res_holder);
@@ -1054,31 +1033,20 @@ SE_DEV_PR_ATTR_RO(res_holder);
 static ssize_t target_core_dev_pr_show_attr_res_pr_all_tgt_pts(
 		struct se_device *dev, char *page)
 {
-	struct t10_pr_registration *pr_reg;
 	ssize_t len = 0;
 
-	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
-		return len;
-
 	spin_lock(&dev->dev_reservation_lock);
-	pr_reg = dev->dev_pr_res_holder;
-	if (!pr_reg) {
+	if (!dev->dev_pr_res_holder) {
 		len = sprintf(page, "No SPC-3 Reservation holder\n");
-		spin_unlock(&dev->dev_reservation_lock);
-		return len;
-	}
-	/*
-	 * See All Target Ports (ALL_TG_PT) bit in spcr17, section 6.14.3
-	 * Basic PERSISTENT RESERVER OUT parameter list, page 290
-	 */
-	if (pr_reg->pr_reg_all_tg_pt)
+	} else if (dev->dev_pr_res_holder->pr_reg_all_tg_pt) {
 		len = sprintf(page, "SPC-3 Reservation: All Target"
 			" Ports registration\n");
-	else
+	} else {
 		len = sprintf(page, "SPC-3 Reservation: Single"
 			" Target Port registration\n");
-	spin_unlock(&dev->dev_reservation_lock);
+	}
 
+	spin_unlock(&dev->dev_reservation_lock);
 	return len;
 }
 
@@ -1087,9 +1055,6 @@ SE_DEV_PR_ATTR_RO(res_pr_all_tgt_pts);
 static ssize_t target_core_dev_pr_show_attr_res_pr_generation(
 		struct se_device *dev, char *page)
 {
-	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
-		return 0;
-
 	return sprintf(page, "0x%08x\n", dev->t10_pr.pr_generation);
 }
 
@@ -1108,16 +1073,13 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_holder_tg_port(
 	struct target_core_fabric_ops *tfo;
 	ssize_t len = 0;
 
-	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
-		return len;
-
 	spin_lock(&dev->dev_reservation_lock);
 	pr_reg = dev->dev_pr_res_holder;
 	if (!pr_reg) {
 		len = sprintf(page, "No SPC-3 Reservation holder\n");
-		spin_unlock(&dev->dev_reservation_lock);
-		return len;
+		goto out_unlock;
 	}
+
 	se_nacl = pr_reg->pr_reg_nacl;
 	se_tpg = se_nacl->se_tpg;
 	lun = pr_reg->pr_reg_tg_pt_lun;
@@ -1131,8 +1093,9 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_holder_tg_port(
 		" %s Logical Unit: %u\n", lun->lun_sep->sep_rtpi,
 		tfo->get_fabric_name(), tfo->tpg_get_tag(se_tpg),
 		tfo->get_fabric_name(), lun->unpacked_lun);
-	spin_unlock(&dev->dev_reservation_lock);
 
+out_unlock:
+	spin_unlock(&dev->dev_reservation_lock);
 	return len;
 }
 
@@ -1148,9 +1111,6 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_registered_i_pts(
 	ssize_t len = 0;
 	int reg_count = 0, prf_isid;
 
-	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
-		return len;
-
 	len += sprintf(page+len, "SPC-3 PR Registrations:\n");
 
 	spin_lock(&dev->t10_pr.registration_lock);
@@ -1190,20 +1150,16 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_type(
 	struct t10_pr_registration *pr_reg;
 	ssize_t len = 0;
 
-	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
-		return len;
-
 	spin_lock(&dev->dev_reservation_lock);
 	pr_reg = dev->dev_pr_res_holder;
-	if (!pr_reg) {
+	if (pr_reg) {
+		len = sprintf(page, "SPC-3 Reservation Type: %s\n",
+			core_scsi3_pr_dump_type(pr_reg->pr_res_type));
+	} else {
 		len = sprintf(page, "No SPC-3 Reservation holder\n");
-		spin_unlock(&dev->dev_reservation_lock);
-		return len;
 	}
-	len = sprintf(page, "SPC-3 Reservation Type: %s\n",
-		core_scsi3_pr_dump_type(pr_reg->pr_res_type));
-	spin_unlock(&dev->dev_reservation_lock);
 
+	spin_unlock(&dev->dev_reservation_lock);
 	return len;
 }
 
@@ -1212,24 +1168,12 @@ SE_DEV_PR_ATTR_RO(res_pr_type);
 static ssize_t target_core_dev_pr_show_attr_res_type(
 		struct se_device *dev, char *page)
 {
-	ssize_t len = 0;
-
-	switch (dev->t10_pr.res_type) {
-	case SPC3_PERSISTENT_RESERVATIONS:
-		len = sprintf(page, "SPC3_PERSISTENT_RESERVATIONS\n");
-		break;
-	case SPC2_RESERVATIONS:
-		len = sprintf(page, "SPC2_RESERVATIONS\n");
-		break;
-	case SPC_PASSTHROUGH:
-		len = sprintf(page, "SPC_PASSTHROUGH\n");
-		break;
-	default:
-		len = sprintf(page, "UNKNOWN\n");
-		break;
-	}
-
-	return len;
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+		return sprintf(page, "SPC_PASSTHROUGH\n");
+	else if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
+		return sprintf(page, "SPC2_RESERVATIONS\n");
+	else
+		return sprintf(page, "SPC3_PERSISTENT_RESERVATIONS\n");
 }
 
 SE_DEV_PR_ATTR_RO(res_type);
@@ -1237,7 +1181,7 @@ SE_DEV_PR_ATTR_RO(res_type);
 static ssize_t target_core_dev_pr_show_attr_res_aptpl_active(
 		struct se_device *dev, char *page)
 {
-	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
 		return 0;
 
 	return sprintf(page, "APTPL Bit Status: %s\n",
@@ -1252,7 +1196,7 @@ SE_DEV_PR_ATTR_RO(res_aptpl_active);
 static ssize_t target_core_dev_pr_show_attr_res_aptpl_metadata(
 		struct se_device *dev, char *page)
 {
-	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
 		return 0;
 
 	return sprintf(page, "Ready to process PR APTPL metadata..\n");
@@ -1299,7 +1243,9 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
 	u16 port_rpti = 0, tpgt = 0;
 	u8 type = 0, scope;
 
-	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+		return 0;
+	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
 		return 0;
 
 	if (dev->export_count) {
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 6a27e7fd33fb..4ae1d3913821 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1398,7 +1398,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	dev->dev_attrib.emulate_tas = DA_EMULATE_TAS;
 	dev->dev_attrib.emulate_tpu = DA_EMULATE_TPU;
 	dev->dev_attrib.emulate_tpws = DA_EMULATE_TPWS;
-	dev->dev_attrib.emulate_reservations = DA_EMULATE_RESERVATIONS;
 	dev->dev_attrib.emulate_alua = DA_EMULATE_ALUA;
 	dev->dev_attrib.enforce_pr_isids = DA_ENFORCE_PR_ISIDS;
 	dev->dev_attrib.is_nonrot = DA_IS_NONROT;
@@ -1447,8 +1446,6 @@ int target_configure_device(struct se_device *dev)
 	dev->dev_index = scsi_get_new_index(SCSI_DEVICE_INDEX);
 	dev->creation_time = get_jiffies_64();
 
-	core_setup_reservations(dev);
-
 	ret = core_setup_alua(dev);
 	if (ret)
 		goto out;
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 2b289891672f..f561a08ff8e5 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -68,49 +68,32 @@ int core_pr_dump_initiator_port(
 static void __core_scsi3_complete_pro_release(struct se_device *, struct se_node_acl *,
 			struct t10_pr_registration *, int);
 
-static int core_scsi2_reservation_seq_non_holder(
-	struct se_cmd *cmd,
-	unsigned char *cdb,
-	u32 pr_reg_type)
+static int target_scsi2_reservation_check(struct se_cmd *cmd)
 {
-	switch (cdb[0]) {
+	struct se_device *dev = cmd->se_dev;
+	struct se_session *sess = cmd->se_sess;
+
+	switch (cmd->t_task_cdb[0]) {
 	case INQUIRY:
 	case RELEASE:
 	case RELEASE_10:
 		return 0;
 	default:
-		return 1;
+		break;
 	}
 
-	return 1;
-}
-
-static int core_scsi2_reservation_check(struct se_cmd *cmd, u32 *pr_reg_type)
-{
-	struct se_device *dev = cmd->se_dev;
-	struct se_session *sess = cmd->se_sess;
-	int ret;
-
-	if (!sess)
+	if (!dev->dev_reserved_node_acl || !sess)
 		return 0;
 
-	spin_lock(&dev->dev_reservation_lock);
-	if (!dev->dev_reserved_node_acl || !sess) {
-		spin_unlock(&dev->dev_reservation_lock);
-		return 0;
-	}
-	if (dev->dev_reserved_node_acl != sess->se_node_acl) {
-		spin_unlock(&dev->dev_reservation_lock);
-		return -EINVAL;
-	}
-	if (!(dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS_WITH_ISID)) {
-		spin_unlock(&dev->dev_reservation_lock);
-		return 0;
+	if (dev->dev_reserved_node_acl != sess->se_node_acl)
+		return -EBUSY;
+
+	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS_WITH_ISID) {
+		if (dev->dev_res_bin_isid != sess->sess_bin_isid)
+			return -EBUSY;
 	}
-	ret = (dev->dev_res_bin_isid == sess->sess_bin_isid) ? 0 : -EINVAL;
-	spin_unlock(&dev->dev_reservation_lock);
 
-	return ret;
+	return 0;
 }
 
 static struct t10_pr_registration *core_scsi3_locate_pr_reg(struct se_device *,
@@ -123,12 +106,8 @@ static int target_check_scsi2_reservation_conflict(struct se_cmd *cmd)
 	struct se_device *dev = cmd->se_dev;
 	struct t10_pr_registration *pr_reg;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
-	int crh = (dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS);
 	int conflict = 0;
 
-	if (!crh)
-		return -EINVAL;
-
 	pr_reg = core_scsi3_locate_pr_reg(cmd->se_dev, se_sess->se_node_acl,
 			se_sess);
 	if (pr_reg) {
@@ -319,9 +298,9 @@ out:
  */
 static int core_scsi3_pr_seq_non_holder(
 	struct se_cmd *cmd,
-	unsigned char *cdb,
 	u32 pr_reg_type)
 {
+	unsigned char *cdb = cmd->t_task_cdb;
 	struct se_dev_entry *se_deve;
 	struct se_session *se_sess = cmd->se_sess;
 	int other_cdb = 0, ignore_reg;
@@ -330,17 +309,11 @@ static int core_scsi3_pr_seq_non_holder(
 	int we = 0; /* Write Exclusive */
 	int legacy = 0; /* Act like a legacy device and return
 			 * RESERVATION CONFLICT on some CDBs */
-	/*
-	 * A legacy SPC-2 reservation is being held.
-	 */
-	if (cmd->se_dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
-		return core_scsi2_reservation_seq_non_holder(cmd,
-					cdb, pr_reg_type);
 
 	se_deve = se_sess->se_node_acl->device_list[cmd->orig_fe_lun];
 	/*
 	 * Determine if the registration should be ignored due to
-	 * non-matching ISIDs in core_scsi3_pr_reservation_check().
+	 * non-matching ISIDs in target_scsi3_pr_reservation_check().
 	 */
 	ignore_reg = (pr_reg_type & 0x80000000);
 	if (ignore_reg)
@@ -563,6 +536,36 @@ static int core_scsi3_pr_seq_non_holder(
 	return 1; /* Conflict by default */
 }
 
+static int target_scsi3_pr_reservation_check(struct se_cmd *cmd)
+{
+	struct se_device *dev = cmd->se_dev;
+	struct se_session *sess = cmd->se_sess;
+	u32 pr_reg_type;
+
+	if (!dev->dev_pr_res_holder)
+		return 0;
+
+	pr_reg_type = dev->dev_pr_res_holder->pr_res_type;
+	cmd->pr_res_key = dev->dev_pr_res_holder->pr_res_key;
+	if (dev->dev_pr_res_holder->pr_reg_nacl != sess->se_node_acl)
+		goto check_nonholder;
+
+	if (dev->dev_pr_res_holder->isid_present_at_reg) {
+		if (dev->dev_pr_res_holder->pr_reg_bin_isid !=
+		    sess->sess_bin_isid) {
+			pr_reg_type |= 0x80000000;
+			goto check_nonholder;
+		}
+	}
+
+	return 0;
+
+check_nonholder:
+	if (core_scsi3_pr_seq_non_holder(cmd, pr_reg_type))
+		return -EBUSY;
+	return 0;
+}
+
 static u32 core_scsi3_pr_generation(struct se_device *dev)
 {
 	u32 prg;
@@ -583,50 +586,6 @@ static u32 core_scsi3_pr_generation(struct se_device *dev)
 	return prg;
 }
 
-static int core_scsi3_pr_reservation_check(
-	struct se_cmd *cmd,
-	u32 *pr_reg_type)
-{
-	struct se_device *dev = cmd->se_dev;
-	struct se_session *sess = cmd->se_sess;
-	int ret;
-
-	if (!sess)
-		return 0;
-	/*
-	 * A legacy SPC-2 reservation is being held.
-	 */
-	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
-		return core_scsi2_reservation_check(cmd, pr_reg_type);
-
-	spin_lock(&dev->dev_reservation_lock);
-	if (!dev->dev_pr_res_holder) {
-		spin_unlock(&dev->dev_reservation_lock);
-		return 0;
-	}
-	*pr_reg_type = dev->dev_pr_res_holder->pr_res_type;
-	cmd->pr_res_key = dev->dev_pr_res_holder->pr_res_key;
-	if (dev->dev_pr_res_holder->pr_reg_nacl != sess->se_node_acl) {
-		spin_unlock(&dev->dev_reservation_lock);
-		return -EINVAL;
-	}
-	if (!dev->dev_pr_res_holder->isid_present_at_reg) {
-		spin_unlock(&dev->dev_reservation_lock);
-		return 0;
-	}
-	ret = (dev->dev_pr_res_holder->pr_reg_bin_isid ==
-	       sess->sess_bin_isid) ? 0 : -EINVAL;
-	/*
-	 * Use bit in *pr_reg_type to notify ISID mismatch in
-	 * core_scsi3_pr_seq_non_holder().
-	 */
-	if (ret != 0)
-		*pr_reg_type |= 0x80000000;
-	spin_unlock(&dev->dev_reservation_lock);
-
-	return ret;
-}
-
 static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	struct se_device *dev,
 	struct se_node_acl *nacl,
@@ -998,7 +957,7 @@ int core_scsi3_check_aptpl_registration(
 	struct se_node_acl *nacl = lun_acl->se_lun_nacl;
 	struct se_dev_entry *deve = nacl->device_list[lun_acl->mapped_lun];
 
-	if (dev->t10_pr.res_type != SPC3_PERSISTENT_RESERVATIONS)
+	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
 		return 0;
 
 	return __core_scsi3_check_aptpl_registration(dev, tpg, lun,
@@ -4343,49 +4302,24 @@ int target_scsi3_emulate_pr_in(struct se_cmd *cmd)
 	return ret;
 }
 
-static int core_pt_reservation_check(struct se_cmd *cmd, u32 *pr_res_type)
+int target_check_reservation(struct se_cmd *cmd)
 {
-	return 0;
-}
+	struct se_device *dev = cmd->se_dev;
+	int ret;
 
-static int core_pt_seq_non_holder(
-	struct se_cmd *cmd,
-	unsigned char *cdb,
-	u32 pr_reg_type)
-{
-	return 0;
-}
+	if (!cmd->se_sess)
+		return 0;
+	if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
+		return 0;
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+		return 0;
 
-void core_setup_reservations(struct se_device *dev)
-{
-	struct t10_reservation *rest = &dev->t10_pr;
+	spin_lock(&dev->dev_reservation_lock);
+	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
+		ret = target_scsi2_reservation_check(cmd);
+	else
+		ret = target_scsi3_pr_reservation_check(cmd);
+	spin_unlock(&dev->dev_reservation_lock);
 
-	/*
-	 * If this device is from Target_Core_Mod/pSCSI, use the reservations
-	 * of the Underlying SCSI hardware.  In Linux/SCSI terms, this can
-	 * cause a problem because libata and some SATA RAID HBAs appear
-	 * under Linux/SCSI, but to emulate reservations themselves.
-	 */
-	if ((dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE) ||
-	    (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV &&
-	     !dev->dev_attrib.emulate_reservations)) {
-		rest->res_type = SPC_PASSTHROUGH;
-		rest->pr_ops.t10_reservation_check = &core_pt_reservation_check;
-		rest->pr_ops.t10_seq_non_holder = &core_pt_seq_non_holder;
-		pr_debug("%s: Using SPC_PASSTHROUGH, no reservation"
-			" emulation\n", dev->transport->name);
-	} else if (dev->transport->get_device_rev(dev) >= SCSI_3) {
-		rest->res_type = SPC3_PERSISTENT_RESERVATIONS;
-		rest->pr_ops.t10_reservation_check = &core_scsi3_pr_reservation_check;
-		rest->pr_ops.t10_seq_non_holder = &core_scsi3_pr_seq_non_holder;
-		pr_debug("%s: Using SPC3_PERSISTENT_RESERVATIONS"
-			" emulation\n", dev->transport->name);
-	} else {
-		rest->res_type = SPC2_RESERVATIONS;
-		rest->pr_ops.t10_reservation_check = &core_scsi2_reservation_check;
-		rest->pr_ops.t10_seq_non_holder =
-				&core_scsi2_reservation_seq_non_holder;
-		pr_debug("%s: Using SPC2_RESERVATIONS emulation\n",
-			dev->transport->name);
-	}
+	return ret;
 }
diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h
index 78451437d2c2..7616f2690ca0 100644
--- a/drivers/target/target_core_pr.h
+++ b/drivers/target/target_core_pr.h
@@ -63,6 +63,6 @@ extern unsigned char *core_scsi3_pr_dump_type(int);
 
 extern int target_scsi3_emulate_pr_in(struct se_cmd *);
 extern int target_scsi3_emulate_pr_out(struct se_cmd *);
-extern void core_setup_reservations(struct se_device *);
+extern int target_check_reservation(struct se_cmd *cmd);
 
 #endif /* TARGET_CORE_PR_H */
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 8ca62631ec7f..862e4347f68f 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -1003,14 +1003,12 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		*size = (cdb[7] << 8) + cdb[8];
 		break;
 	case PERSISTENT_RESERVE_IN:
-		if (dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS)
-			cmd->execute_cmd = target_scsi3_emulate_pr_in;
 		*size = (cdb[7] << 8) + cdb[8];
+		cmd->execute_cmd = target_scsi3_emulate_pr_in;
 		break;
 	case PERSISTENT_RESERVE_OUT:
-		if (dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS)
-			cmd->execute_cmd = target_scsi3_emulate_pr_out;
 		*size = (cdb[7] << 8) + cdb[8];
+		cmd->execute_cmd = target_scsi3_emulate_pr_out;
 		break;
 	case RELEASE:
 	case RELEASE_10:
@@ -1019,8 +1017,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		else
 			*size = cmd->data_length;
 
-		if (dev->t10_pr.res_type != SPC_PASSTHROUGH)
-			cmd->execute_cmd = target_scsi2_reservation_release;
+		cmd->execute_cmd = target_scsi2_reservation_release;
 		break;
 	case RESERVE:
 	case RESERVE_10:
@@ -1033,15 +1030,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		else
 			*size = cmd->data_length;
 
-		/*
-		 * Setup the legacy emulated handler for SPC-2 and
-		 * >= SPC-3 compatible reservation handling (CRH=1)
-		 * Otherwise, we assume the underlying SCSI logic is
-		 * is running in SPC_PASSTHROUGH, and wants reservations
-		 * emulation disabled.
-		 */
-		if (dev->t10_pr.res_type != SPC_PASSTHROUGH)
-			cmd->execute_cmd = target_scsi2_reservation_reserve;
+		cmd->execute_cmd = target_scsi2_reservation_reserve;
 		break;
 	case REQUEST_SENSE:
 		*size = cdb[4];
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 757e3777ce79..e996bdf480cf 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1103,7 +1103,6 @@ int target_setup_cmd_from_cdb(
 	unsigned char *cdb)
 {
 	struct se_device *dev = cmd->se_dev;
-	u32 pr_reg_type = 0;
 	u8 alua_ascq = 0;
 	unsigned long flags;
 	int ret;
@@ -1180,20 +1179,13 @@ int target_setup_cmd_from_cdb(
 	/*
 	 * Check status for SPC-3 Persistent Reservations
 	 */
-	if (dev->t10_pr.pr_ops.t10_reservation_check(cmd, &pr_reg_type)) {
-		if (dev->t10_pr.pr_ops.t10_seq_non_holder(
-					cmd, cdb, pr_reg_type) != 0) {
-			cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-			cmd->se_cmd_flags |= SCF_SCSI_RESERVATION_CONFLICT;
-			cmd->scsi_status = SAM_STAT_RESERVATION_CONFLICT;
-			cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-			return -EBUSY;
-		}
-		/*
-		 * This means the CDB is allowed for the SCSI Initiator port
-		 * when said port is *NOT* holding the legacy SPC-2 or
-		 * SPC-3 Persistent Reservation.
-		 */
+	ret = target_check_reservation(cmd);
+	if (ret) {
+		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
+		cmd->se_cmd_flags |= SCF_SCSI_RESERVATION_CONFLICT;
+		cmd->scsi_status = SAM_STAT_RESERVATION_CONFLICT;
+		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+		return ret;
 	}
 
 	ret = dev->transport->parse_cdb(cmd);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 15af1307d064..892a93dec19c 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -93,8 +93,6 @@
  */
 #define DA_EMULATE_TPWS				0
 /* No Emulation for PSCSI by default */
-#define DA_EMULATE_RESERVATIONS			0
-/* No Emulation for PSCSI by default */
 #define DA_EMULATE_ALUA				0
 /* Enforce SCSI Initiator Port TransportID with 'ISID' for PR */
 #define DA_ENFORCE_PR_ISIDS			1
@@ -333,18 +331,6 @@ struct t10_wwn {
 	struct list_head t10_vpd_list;
 };
 
-
-/*
- * Used by TCM Core internally to signal if >= SPC-3 persistent reservations
- * emulation is enabled or disabled, or running in with TCM/pSCSI passthrough
- * mode
- */
-typedef enum {
-	SPC_PASSTHROUGH,
-	SPC2_RESERVATIONS,
-	SPC3_PERSISTENT_RESERVATIONS
-} t10_reservations_index_t;
-
 struct t10_pr_registration {
 	/* Used for fabrics that contain WWN+ISID */
 #define PR_REG_ISID_LEN				16
@@ -386,18 +372,6 @@ struct t10_pr_registration {
 	struct list_head pr_reg_atp_mem_list;
 };
 
-/*
- * This set of function pointer ops is set based upon SPC3_PERSISTENT_RESERVATIONS,
- * SPC2_RESERVATIONS or SPC_PASSTHROUGH in drivers/target/target_core_pr.c:
- * core_setup_reservations()
- */
-struct t10_reservation_ops {
-	int (*t10_reservation_check)(struct se_cmd *, u32 *);
-	int (*t10_seq_non_holder)(struct se_cmd *, unsigned char *, u32);
-	int (*t10_pr_register)(struct se_cmd *);
-	int (*t10_pr_clear)(struct se_cmd *);
-};
-
 struct t10_reservation {
 	/* Reservation effects all target ports */
 	int pr_all_tg_pt;
@@ -408,7 +382,6 @@ struct t10_reservation {
 #define PR_APTPL_BUF_LEN			8192
 	u32 pr_aptpl_buf_len;
 	u32 pr_generation;
-	t10_reservations_index_t res_type;
 	spinlock_t registration_lock;
 	spinlock_t aptpl_reg_lock;
 	/*
@@ -424,7 +397,6 @@ struct t10_reservation {
 	struct se_node_acl *pr_res_holder;
 	struct list_head registration_list;
 	struct list_head aptpl_reg_list;
-	struct t10_reservation_ops pr_ops;
 };
 
 struct se_tmr_req {
@@ -633,7 +605,6 @@ struct se_dev_attrib {
 	int		emulate_tas;
 	int		emulate_tpu;
 	int		emulate_tpws;
-	int		emulate_reservations;
 	int		emulate_alua;
 	int		enforce_pr_isids;
 	int		is_nonrot;
-- 
cgit v1.2.3-55-g7522


From c87fbd5656f263f0fc1c37d20f402797c068232e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig
Date: Wed, 10 Oct 2012 17:37:16 -0400
Subject: target: simplify alua support

We always support ALUA for virtual backends, and never for physical ones.  Simplify
the code to just deal with these two cases and remove the superflous abstractions.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_alua.c      | 135 ++++++++++++---------------------
 drivers/target/target_core_alua.h      |   1 +
 drivers/target/target_core_configfs.c  |  28 ++-----
 drivers/target/target_core_device.c    |   4 +-
 drivers/target/target_core_spc.c       |  12 +--
 drivers/target/target_core_transport.c |  38 ++--------
 include/target/target_core_base.h      |  13 ----
 7 files changed, 65 insertions(+), 166 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 15c127b780d8..b3302a9200a2 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -522,40 +522,26 @@ static inline int core_alua_state_transition(
 }
 
 /*
- * Used for alua_type SPC_ALUA_PASSTHROUGH and SPC2_ALUA_DISABLED
- * in transport_cmd_sequencer().  This function is assigned to
- * struct t10_alua *->state_check() in core_setup_alua()
- */
-static int core_alua_state_check_nop(
-	struct se_cmd *cmd,
-	unsigned char *cdb,
-	u8 *alua_ascq)
-{
-	return 0;
-}
-
-/*
- * Used for alua_type SPC3_ALUA_EMULATED in transport_cmd_sequencer().
- * This function is assigned to struct t10_alua *->state_check() in
- * core_setup_alua()
- *
- * Also, this function can return three different return codes to
- * signal transport_generic_cmd_sequencer()
- *
  * return 1: Is used to signal LUN not accecsable, and check condition/not ready
  * return 0: Used to signal success
  * reutrn -1: Used to signal failure, and invalid cdb field
  */
-static int core_alua_state_check(
-	struct se_cmd *cmd,
-	unsigned char *cdb,
-	u8 *alua_ascq)
+int target_alua_state_check(struct se_cmd *cmd)
 {
+	struct se_device *dev = cmd->se_dev;
+	unsigned char *cdb = cmd->t_task_cdb;
 	struct se_lun *lun = cmd->se_lun;
 	struct se_port *port = lun->lun_sep;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 	int out_alua_state, nonop_delay_msecs;
+	u8 alua_ascq;
+	int ret;
+
+	if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
+		return 0;
+	if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+		return 0;
 
 	if (!port)
 		return 0;
@@ -564,11 +550,11 @@ static int core_alua_state_check(
 	 * access state: OFFLINE
 	 */
 	if (atomic_read(&port->sep_tg_pt_secondary_offline)) {
-		*alua_ascq = ASCQ_04H_ALUA_OFFLINE;
 		pr_debug("ALUA: Got secondary offline status for local"
 				" target port\n");
-		*alua_ascq = ASCQ_04H_ALUA_OFFLINE;
-		return 1;
+		alua_ascq = ASCQ_04H_ALUA_OFFLINE;
+		ret = 1;
+		goto out;
 	}
 	 /*
 	 * Second, obtain the struct t10_alua_tg_pt_gp_member pointer to the
@@ -593,14 +579,18 @@ static int core_alua_state_check(
 
 	switch (out_alua_state) {
 	case ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED:
-		return core_alua_state_nonoptimized(cmd, cdb,
-					nonop_delay_msecs, alua_ascq);
+		ret = core_alua_state_nonoptimized(cmd, cdb,
+					nonop_delay_msecs, &alua_ascq);
+		break;
 	case ALUA_ACCESS_STATE_STANDBY:
-		return core_alua_state_standby(cmd, cdb, alua_ascq);
+		ret = core_alua_state_standby(cmd, cdb, &alua_ascq);
+		break;
 	case ALUA_ACCESS_STATE_UNAVAILABLE:
-		return core_alua_state_unavailable(cmd, cdb, alua_ascq);
+		ret = core_alua_state_unavailable(cmd, cdb, &alua_ascq);
+		break;
 	case ALUA_ACCESS_STATE_TRANSITION:
-		return core_alua_state_transition(cmd, cdb, alua_ascq);
+		ret = core_alua_state_transition(cmd, cdb, &alua_ascq);
+		break;
 	/*
 	 * OFFLINE is a secondary ALUA target port group access state, that is
 	 * handled above with struct se_port->sep_tg_pt_secondary_offline=1
@@ -609,10 +599,27 @@ static int core_alua_state_check(
 	default:
 		pr_err("Unknown ALUA access state: 0x%02x\n",
 				out_alua_state);
-		return -EINVAL;
+		ret = -EINVAL;
+		break;
 	}
 
-	return 0;
+out:
+	if (ret > 0) {
+		/*
+		 * Set SCSI additional sense code (ASC) to 'LUN Not Accessible';
+		 * The ALUA additional sense code qualifier (ASCQ) is determined
+		 * by the ALUA primary or secondary access state..
+		 */
+		pr_debug("[%s]: ALUA TG Port not available, "
+			"SenseKey: NOT_READY, ASC/ASCQ: "
+			"0x04/0x%02x\n",
+			cmd->se_tfo->get_fabric_name(), alua_ascq);
+
+		cmd->scsi_asc = 0x04;
+		cmd->scsi_ascq = alua_ascq;
+	}
+
+	return ret;
 }
 
 /*
@@ -1264,13 +1271,9 @@ void core_alua_free_lu_gp(struct t10_alua_lu_gp *lu_gp)
 
 void core_alua_free_lu_gp_mem(struct se_device *dev)
 {
-	struct t10_alua *alua = &dev->t10_alua;
 	struct t10_alua_lu_gp *lu_gp;
 	struct t10_alua_lu_gp_member *lu_gp_mem;
 
-	if (alua->alua_type != SPC3_ALUA_EMULATED)
-		return;
-
 	lu_gp_mem = dev->dev_alua_lu_gp_mem;
 	if (!lu_gp_mem)
 		return;
@@ -1538,13 +1541,9 @@ void core_alua_free_tg_pt_gp(
 
 void core_alua_free_tg_pt_gp_mem(struct se_port *port)
 {
-	struct t10_alua *alua = &port->sep_lun->lun_se_dev->t10_alua;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 
-	if (alua->alua_type != SPC3_ALUA_EMULATED)
-		return;
-
 	tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
 	if (!tg_pt_gp_mem)
 		return;
@@ -1636,14 +1635,10 @@ static void __core_alua_drop_tg_pt_gp_mem(
 ssize_t core_alua_show_tg_pt_gp_info(struct se_port *port, char *page)
 {
 	struct config_item *tg_pt_ci;
-	struct t10_alua *alua = &port->sep_lun->lun_se_dev->t10_alua;
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem;
 	ssize_t len = 0;
 
-	if (alua->alua_type != SPC3_ALUA_EMULATED)
-		return len;
-
 	tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
 	if (!tg_pt_gp_mem)
 		return len;
@@ -1686,13 +1681,9 @@ ssize_t core_alua_store_tg_pt_gp_info(
 	tpg = port->sep_tpg;
 	lun = port->sep_lun;
 
-	if (dev->t10_alua.alua_type != SPC3_ALUA_EMULATED) {
-		pr_warn("SPC3_ALUA_EMULATED not enabled for"
-			" %s/tpgt_%hu/%s\n", tpg->se_tpg_tfo->tpg_get_wwn(tpg),
-			tpg->se_tpg_tfo->tpg_get_tag(tpg),
-			config_item_name(&lun->lun_group.cg_item));
-		return -EINVAL;
-	}
+	tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
+	if (!tg_pt_gp_mem)
+		return 0;
 
 	if (count > TG_PT_GROUP_NAME_BUF) {
 		pr_err("ALUA Target Port Group alias too large!\n");
@@ -1715,13 +1706,6 @@ ssize_t core_alua_store_tg_pt_gp_info(
 		if (!tg_pt_gp_new)
 			return -ENODEV;
 	}
-	tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
-	if (!tg_pt_gp_mem) {
-		if (tg_pt_gp_new)
-			core_alua_put_tg_pt_gp_from_name(tg_pt_gp_new);
-		pr_err("NULL struct se_port->sep_alua_tg_pt_gp_mem pointer\n");
-		return -EINVAL;
-	}
 
 	spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
 	tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
@@ -2050,26 +2034,9 @@ ssize_t core_alua_store_secondary_write_metadata(
 
 int core_setup_alua(struct se_device *dev)
 {
-	struct t10_alua *alua = &dev->t10_alua;
-	struct t10_alua_lu_gp_member *lu_gp_mem;
-
-	/*
-	 * If this device is from Target_Core_Mod/pSCSI, use the ALUA logic
-	 * of the Underlying SCSI hardware.  In Linux/SCSI terms, this can
-	 * cause a problem because libata and some SATA RAID HBAs appear
-	 * under Linux/SCSI, but emulate SCSI logic themselves.
-	 */
-	if ((dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE) ||
-	    (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV &&
-	     !dev->dev_attrib.emulate_alua)) {
-		pr_debug("%s: Using SPC_ALUA_PASSTHROUGH, no ALUA"
-			" emulation\n", dev->transport->name);
-
-		alua->alua_type = SPC_ALUA_PASSTHROUGH;
-		alua->alua_state_check = &core_alua_state_check_nop;
-	} else if (dev->transport->get_device_rev(dev) >= SCSI_3) {
-		pr_debug("%s: Enabling ALUA Emulation for SPC-3"
-			" device\n", dev->transport->name);
+	if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV &&
+	    !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
+		struct t10_alua_lu_gp_member *lu_gp_mem;
 
 		/*
 		 * Associate this struct se_device with the default ALUA
@@ -2079,8 +2046,6 @@ int core_setup_alua(struct se_device *dev)
 		if (IS_ERR(lu_gp_mem))
 			return PTR_ERR(lu_gp_mem);
 
-		alua->alua_type = SPC3_ALUA_EMULATED;
-		alua->alua_state_check = &core_alua_state_check;
 		spin_lock(&lu_gp_mem->lu_gp_mem_lock);
 		__core_alua_attach_lu_gp_mem(lu_gp_mem,
 				default_lu_gp);
@@ -2089,12 +2054,6 @@ int core_setup_alua(struct se_device *dev)
 		pr_debug("%s: Adding to default ALUA LU Group:"
 			" core/alua/lu_gps/default_lu_gp\n",
 			dev->transport->name);
-	} else {
-		pr_debug("%s: Disabling ALUA Emulation for SPC-2"
-			" device\n", dev->transport->name);
-
-		alua->alua_type = SPC2_ALUA_DISABLED;
-		alua->alua_state_check = &core_alua_state_check_nop;
 	}
 
 	return 0;
diff --git a/drivers/target/target_core_alua.h b/drivers/target/target_core_alua.h
index 5019157ffe69..a2af8aa15b98 100644
--- a/drivers/target/target_core_alua.h
+++ b/drivers/target/target_core_alua.h
@@ -132,5 +132,6 @@ extern ssize_t core_alua_show_secondary_write_metadata(struct se_lun *,
 extern ssize_t core_alua_store_secondary_write_metadata(struct se_lun *,
 					const char *, size_t);
 extern int core_setup_alua(struct se_device *);
+extern int target_alua_state_check(struct se_cmd *cmd);
 
 #endif /* TARGET_CORE_ALUA_H */
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 3d5570da41eb..7b473b66da7b 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -1615,15 +1615,9 @@ static ssize_t target_core_show_alua_lu_gp(void *p, char *page)
 	struct t10_alua_lu_gp_member *lu_gp_mem;
 	ssize_t len = 0;
 
-	if (dev->t10_alua.alua_type != SPC3_ALUA_EMULATED)
-		return len;
-
 	lu_gp_mem = dev->dev_alua_lu_gp_mem;
-	if (!lu_gp_mem) {
-		pr_err("NULL struct se_device->dev_alua_lu_gp_mem"
-				" pointer\n");
-		return -EINVAL;
-	}
+	if (!lu_gp_mem)
+		return 0;
 
 	spin_lock(&lu_gp_mem->lu_gp_mem_lock);
 	lu_gp = lu_gp_mem->lu_gp;
@@ -1649,12 +1643,10 @@ static ssize_t target_core_store_alua_lu_gp(
 	unsigned char buf[LU_GROUP_NAME_BUF];
 	int move = 0;
 
-	if (dev->t10_alua.alua_type != SPC3_ALUA_EMULATED) {
-		pr_warn("SPC3_ALUA_EMULATED not enabled for %s/%s\n",
-			config_item_name(&hba->hba_group.cg_item),
-			config_item_name(&dev->dev_group.cg_item));
-		return -EINVAL;
-	}
+	lu_gp_mem = dev->dev_alua_lu_gp_mem;
+	if (!lu_gp_mem)
+		return 0;
+
 	if (count > LU_GROUP_NAME_BUF) {
 		pr_err("ALUA LU Group Alias too large!\n");
 		return -EINVAL;
@@ -1675,14 +1667,6 @@ static ssize_t target_core_store_alua_lu_gp(
 		if (!lu_gp_new)
 			return -ENODEV;
 	}
-	lu_gp_mem = dev->dev_alua_lu_gp_mem;
-	if (!lu_gp_mem) {
-		if (lu_gp_new)
-			core_alua_put_lu_gp_from_name(lu_gp_new);
-		pr_err("NULL struct se_device->dev_alua_lu_gp_mem"
-				" pointer\n");
-		return -EINVAL;
-	}
 
 	spin_lock(&lu_gp_mem->lu_gp_mem_lock);
 	lu_gp = lu_gp_mem->lu_gp;
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 4ae1d3913821..3c3a3019ce7b 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -556,7 +556,8 @@ static void core_export_port(
 	list_add_tail(&port->sep_list, &dev->dev_sep_list);
 	spin_unlock(&dev->se_port_lock);
 
-	if (dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) {
+	if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV &&
+	    !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
 		tg_pt_gp_mem = core_alua_allocate_tg_pt_gp_mem(port);
 		if (IS_ERR(tg_pt_gp_mem) || !tg_pt_gp_mem) {
 			pr_err("Unable to allocate t10_alua_tg_pt"
@@ -1398,7 +1399,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	dev->dev_attrib.emulate_tas = DA_EMULATE_TAS;
 	dev->dev_attrib.emulate_tpu = DA_EMULATE_TPU;
 	dev->dev_attrib.emulate_tpws = DA_EMULATE_TPWS;
-	dev->dev_attrib.emulate_alua = DA_EMULATE_ALUA;
 	dev->dev_attrib.enforce_pr_isids = DA_ENFORCE_PR_ISIDS;
 	dev->dev_attrib.is_nonrot = DA_IS_NONROT;
 	dev->dev_attrib.emulate_rest_reord = DA_EMULATE_REST_REORD;
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 862e4347f68f..7ecac453b11a 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -95,8 +95,7 @@ static int spc_emulate_inquiry_std(struct se_cmd *cmd, char *buf)
 	/*
 	 * Enable SCCS and TPGS fields for Emulated ALUA
 	 */
-	if (dev->t10_alua.alua_type == SPC3_ALUA_EMULATED)
-		spc_fill_alua_data(lun->lun_sep, buf);
+	spc_fill_alua_data(lun->lun_sep, buf);
 
 	buf[7] = 0x2; /* CmdQue=1 */
 
@@ -294,9 +293,6 @@ check_t10_vend_desc:
 		 * Get the PROTOCOL IDENTIFIER as defined by spc4r17
 		 * section 7.5.1 Table 362
 		 */
-		if (dev->t10_alua.alua_type != SPC3_ALUA_EMULATED)
-			goto check_scsi_name;
-
 		tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
 		if (!tg_pt_gp_mem)
 			goto check_lu_gp;
@@ -1083,8 +1079,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 			 * MAINTENANCE_IN from SCC-2
 			 * Check for emulated MI_REPORT_TARGET_PGS
 			 */
-			if ((cdb[1] & 0x1f) == MI_REPORT_TARGET_PGS &&
-			    dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) {
+			if ((cdb[1] & 0x1f) == MI_REPORT_TARGET_PGS) {
 				cmd->execute_cmd =
 					target_emulate_report_target_port_groups;
 			}
@@ -1102,8 +1097,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 			 * MAINTENANCE_OUT from SCC-2
 			 * Check for emulated MO_SET_TARGET_PGS.
 			 */
-			if (cdb[1] == MO_SET_TARGET_PGS &&
-			    dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) {
+			if (cdb[1] == MO_SET_TARGET_PGS) {
 				cmd->execute_cmd =
 					target_emulate_set_target_port_groups;
 			}
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index e996bdf480cf..c4c931b525d2 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -70,7 +70,6 @@ static void transport_handle_queue_full(struct se_cmd *cmd,
 static int transport_generic_get_mem(struct se_cmd *cmd);
 static int target_get_sess_cmd(struct se_session *, struct se_cmd *, bool);
 static void transport_put_cmd(struct se_cmd *cmd);
-static int transport_set_sense_codes(struct se_cmd *cmd, u8 asc, u8 ascq);
 static void target_complete_ok_work(struct work_struct *work);
 
 int init_se_kmem_caches(void)
@@ -1103,7 +1102,6 @@ int target_setup_cmd_from_cdb(
 	unsigned char *cdb)
 {
 	struct se_device *dev = cmd->se_dev;
-	u8 alua_ascq = 0;
 	unsigned long flags;
 	int ret;
 
@@ -1153,26 +1151,13 @@ int target_setup_cmd_from_cdb(
 		return -EINVAL;
 	}
 
-	ret = dev->t10_alua.alua_state_check(cmd, cdb, &alua_ascq);
-	if (ret != 0) {
-		/*
-		 * Set SCSI additional sense code (ASC) to 'LUN Not Accessible';
-		 * The ALUA additional sense code qualifier (ASCQ) is determined
-		 * by the ALUA primary or secondary access state..
-		 */
-		if (ret > 0) {
-			pr_debug("[%s]: ALUA TG Port not available, "
-				"SenseKey: NOT_READY, ASC/ASCQ: "
-				"0x04/0x%02x\n",
-				cmd->se_tfo->get_fabric_name(), alua_ascq);
-
-			transport_set_sense_codes(cmd, 0x04, alua_ascq);
-			cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-			cmd->scsi_sense_reason = TCM_CHECK_CONDITION_NOT_READY;
-			return -EINVAL;
-		}
+	ret = target_alua_state_check(cmd);
+	if (ret) {
 		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+		if (ret > 0)
+			cmd->scsi_sense_reason = TCM_CHECK_CONDITION_NOT_READY;
+		else
+			cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
 		return -EINVAL;
 	}
 
@@ -2640,17 +2625,6 @@ static int transport_get_sense_codes(
 	return 0;
 }
 
-static int transport_set_sense_codes(
-	struct se_cmd *cmd,
-	u8 asc,
-	u8 ascq)
-{
-	cmd->scsi_asc = asc;
-	cmd->scsi_ascq = ascq;
-
-	return 0;
-}
-
 int transport_send_check_condition_and_sense(
 	struct se_cmd *cmd,
 	u8 reason,
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 892a93dec19c..11b0a68dc765 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -220,16 +220,6 @@ enum tcm_tmrsp_table {
 	TMR_FUNCTION_REJECTED		= 255,
 };
 
-/*
- * Used by TCM Core internally to signal if ALUA emulation is enabled or
- * disabled, or running in with TCM/pSCSI passthrough mode
- */
-typedef enum {
-	SPC_ALUA_PASSTHROUGH,
-	SPC2_ALUA_DISABLED,
-	SPC3_ALUA_EMULATED
-} t10_alua_index_t;
-
 /*
  * Used for target SCSI statistics
  */
@@ -243,7 +233,6 @@ typedef enum {
 struct se_cmd;
 
 struct t10_alua {
-	t10_alua_index_t alua_type;
 	/* ALUA Target Port Group ID */
 	u16	alua_tg_pt_gps_counter;
 	u32	alua_tg_pt_gps_count;
@@ -253,7 +242,6 @@ struct t10_alua {
 	struct t10_alua_tg_pt_gp *default_tg_pt_gp;
 	/* Used for default ALUA Target Port Group ConfigFS group */
 	struct config_group alua_tg_pt_gps_group;
-	int (*alua_state_check)(struct se_cmd *, unsigned char *, u8 *);
 	struct list_head tg_pt_gps_list;
 };
 
@@ -605,7 +593,6 @@ struct se_dev_attrib {
 	int		emulate_tas;
 	int		emulate_tpu;
 	int		emulate_tpws;
-	int		emulate_alua;
 	int		enforce_pr_isids;
 	int		is_nonrot;
 	int		emulate_rest_reord;
-- 
cgit v1.2.3-55-g7522


From 48c2567d1a10b5a2cab72b37775b886b08f88726 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig
Date: Wed, 10 Oct 2012 17:37:17 -0400
Subject: target: remove ->get_device_rev

Now that the reservations and ALUA code have been cleaned up there is no need
for the get_device_rev method, as we only need the standards revision in the
inquiry data, where we can hardcode it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c  |  2 --
 drivers/target/target_core_file.c    |  1 -
 drivers/target/target_core_iblock.c  |  1 -
 drivers/target/target_core_pscsi.c   | 13 -------------
 drivers/target/target_core_rd.c      |  1 -
 drivers/target/target_core_sbc.c     |  6 ------
 drivers/target/target_core_spc.c     |  2 +-
 include/target/target_core_backend.h |  1 -
 8 files changed, 1 insertion(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 3c3a3019ce7b..066e8159afcd 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1348,8 +1348,6 @@ static void scsi_dump_inquiry(struct se_device *dev)
 
 	device_type = dev->transport->get_device_type(dev);
 	pr_debug("  Type:   %s ", scsi_device_type(device_type));
-	pr_debug("                 ANSI SCSI revision: %02x\n",
-				dev->transport->get_device_rev(dev));
 }
 
 struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 2a3e2bbd8078..342a6a6dcca0 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -534,7 +534,6 @@ static struct se_subsystem_api fileio_template = {
 	.parse_cdb		= fd_parse_cdb,
 	.set_configfs_dev_params = fd_set_configfs_dev_params,
 	.show_configfs_dev_params = fd_show_configfs_dev_params,
-	.get_device_rev		= sbc_get_device_rev,
 	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= fd_get_blocks,
 };
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 701877f9cd33..17fc01d6baea 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -725,7 +725,6 @@ static struct se_subsystem_api iblock_template = {
 	.parse_cdb		= iblock_parse_cdb,
 	.set_configfs_dev_params = iblock_set_configfs_dev_params,
 	.show_configfs_dev_params = iblock_show_configfs_dev_params,
-	.get_device_rev		= sbc_get_device_rev,
 	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= iblock_get_blocks,
 };
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index dd6ac7c380c9..aa3e80a2f8db 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -1106,18 +1106,6 @@ fail:
 	return -ENOMEM;
 }
 
-/*	pscsi_get_device_rev():
- *
- *
- */
-static u32 pscsi_get_device_rev(struct se_device *dev)
-{
-	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
-	struct scsi_device *sd = pdv->pdv_sd;
-
-	return (sd->scsi_level - 1) ? sd->scsi_level - 1 : 1;
-}
-
 /*	pscsi_get_device_type():
  *
  *
@@ -1187,7 +1175,6 @@ static struct se_subsystem_api pscsi_template = {
 	.parse_cdb		= pscsi_parse_cdb,
 	.set_configfs_dev_params = pscsi_set_configfs_dev_params,
 	.show_configfs_dev_params = pscsi_show_configfs_dev_params,
-	.get_device_rev		= pscsi_get_device_rev,
 	.get_device_type	= pscsi_get_device_type,
 	.get_blocks		= pscsi_get_blocks,
 };
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 6348b6672526..92b1307a9931 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -449,7 +449,6 @@ static struct se_subsystem_api rd_mcp_template = {
 	.parse_cdb		= rd_parse_cdb,
 	.set_configfs_dev_params = rd_set_configfs_dev_params,
 	.show_configfs_dev_params = rd_show_configfs_dev_params,
-	.get_device_rev		= sbc_get_device_rev,
 	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= rd_get_blocks,
 };
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 01686954cfa0..a4eb9c553654 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -604,12 +604,6 @@ out_invalid_cdb_field:
 }
 EXPORT_SYMBOL(sbc_parse_cdb);
 
-u32 sbc_get_device_rev(struct se_device *dev)
-{
-	return SCSI_SPC_2; /* Returns SPC-3 in Initiator Data */
-}
-EXPORT_SYMBOL(sbc_get_device_rev);
-
 u32 sbc_get_device_type(struct se_device *dev)
 {
 	return TYPE_DISK;
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 7ecac453b11a..71d440f0573e 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -78,7 +78,7 @@ static int spc_emulate_inquiry_std(struct se_cmd *cmd, char *buf)
 	if (dev->transport->get_device_type(dev) == TYPE_TAPE)
 		buf[1] = 0x80;
 
-	buf[2] = dev->transport->get_device_rev(dev);
+	buf[2] = 0x05; /* SPC-3 */
 
 	/*
 	 * NORMACA and HISUP = 0, RESPONSE DATA FORMAT = 2
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index b7f3936453e1..e57f738f04f9 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -32,7 +32,6 @@ struct se_subsystem_api {
 				   unsigned char *);
 
 	int (*parse_cdb)(struct se_cmd *cmd);
-	u32 (*get_device_rev)(struct se_device *);
 	u32 (*get_device_type)(struct se_device *);
 	sector_t (*get_blocks)(struct se_device *);
 	unsigned char *(*get_sense_buffer)(struct se_cmd *);
-- 
cgit v1.2.3-55-g7522


From de103c93aff0bed0ae984274e5dc8b95899badab Mon Sep 17 00:00:00 2001
From: Christoph Hellwig
Date: Tue, 6 Nov 2012 12:24:09 -0800
Subject: target: pass sense_reason as a return value

Pass the sense reason as an explicit return value from the I/O submission
path instead of storing it in struct se_cmd and using negative return
values.  This cleans up a lot of the code pathes, and with the sparse
annotations for the new sense_reason_t type allows for much better
error checking.

(nab: Convert spc_emulate_modesense + spc_emulate_modeselect to use
      sense_reason_t with Roland's MODE SELECT changes)

Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/infiniband/ulp/srpt/ib_srpt.c    |  43 +-
 drivers/scsi/qla2xxx/tcm_qla2xxx.c       |   4 +-
 drivers/target/iscsi/iscsi_target.c      |  80 +--
 drivers/target/iscsi/iscsi_target_core.h |   2 +-
 drivers/target/iscsi/iscsi_target_erl1.c |  11 +-
 drivers/target/target_core_alua.c        |  98 ++--
 drivers/target/target_core_alua.h        |   6 +-
 drivers/target/target_core_device.c      |  31 +-
 drivers/target/target_core_file.c        |  22 +-
 drivers/target/target_core_iblock.c      |  55 +-
 drivers/target/target_core_internal.h    |   2 +-
 drivers/target/target_core_pr.c          | 918 ++++++++++++++-----------------
 drivers/target/target_core_pr.h          |  10 +-
 drivers/target/target_core_pscsi.c       |  51 +-
 drivers/target/target_core_rd.c          |  10 +-
 drivers/target/target_core_sbc.c         |  87 ++-
 drivers/target/target_core_spc.c         | 126 ++---
 drivers/target/target_core_transport.c   | 252 ++++-----
 drivers/target/target_core_ua.c          |  11 +-
 drivers/target/target_core_ua.h          |   2 +-
 drivers/vhost/tcm_vhost.c                |   4 -
 include/target/target_core_backend.h     |  16 +-
 include/target/target_core_base.h        |  46 +-
 include/target/target_core_fabric.h      |  13 +-
 24 files changed, 841 insertions(+), 1059 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index cf23c46185b2..e6fafc62acae 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1730,7 +1730,7 @@ static int srpt_handle_cmd(struct srpt_rdma_ch *ch,
 	uint64_t unpacked_lun;
 	u64 data_len;
 	enum dma_data_direction dir;
-	int ret;
+	sense_reason_t ret;
 
 	BUG_ON(!send_ioctx);
 
@@ -1755,12 +1755,10 @@ static int srpt_handle_cmd(struct srpt_rdma_ch *ch,
 		break;
 	}
 
-	ret = srpt_get_desc_tbl(send_ioctx, srp_cmd, &dir, &data_len);
-	if (ret) {
+	if (srpt_get_desc_tbl(send_ioctx, srp_cmd, &dir, &data_len)) {
 		printk(KERN_ERR "0x%llx: parsing SRP descriptor table failed.\n",
 		       srp_cmd->tag);
-		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
+		ret = TCM_INVALID_CDB_FIELD;
 		kref_put(&send_ioctx->kref, srpt_put_send_ioctx_kref);
 		goto send_sense;
 	}
@@ -1769,26 +1767,26 @@ static int srpt_handle_cmd(struct srpt_rdma_ch *ch,
 	cmd->data_direction = dir;
 	unpacked_lun = srpt_unpack_lun((uint8_t *)&srp_cmd->lun,
 				       sizeof(srp_cmd->lun));
-	if (transport_lookup_cmd_lun(cmd, unpacked_lun) < 0) {
+	ret = transport_lookup_cmd_lun(cmd, unpacked_lun);
+	if (ret) {
 		kref_put(&send_ioctx->kref, srpt_put_send_ioctx_kref);
 		goto send_sense;
 	}
 	ret = target_setup_cmd_from_cdb(cmd, srp_cmd->cdb);
-	if (ret < 0) {
+	if (ret) {
 		kref_put(&send_ioctx->kref, srpt_put_send_ioctx_kref);
-		if (cmd->se_cmd_flags & SCF_SCSI_RESERVATION_CONFLICT) {
+		if (ret == TCM_RESERVATION_CONFLICT) {
 			srpt_queue_status(cmd);
 			return 0;
-		} else
-			goto send_sense;
+		}
+		goto send_sense;
 	}
 
 	transport_handle_cdb_direct(cmd);
 	return 0;
 
 send_sense:
-	transport_send_check_condition_and_sense(cmd, cmd->scsi_sense_reason,
-						 0);
+	transport_send_check_condition_and_sense(cmd, ret, 0);
 	return -1;
 }
 
@@ -1882,16 +1880,14 @@ static void srpt_handle_tsk_mgmt(struct srpt_rdma_ch *ch,
 	send_ioctx->tag = srp_tsk->tag;
 	tcm_tmr = srp_tmr_to_tcm(srp_tsk->tsk_mgmt_func);
 	if (tcm_tmr < 0) {
-		send_ioctx->cmd.se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 		send_ioctx->cmd.se_tmr_req->response =
 			TMR_TASK_MGMT_FUNCTION_NOT_SUPPORTED;
-		goto process_tmr;
+		goto fail;
 	}
 	res = core_tmr_alloc_req(cmd, NULL, tcm_tmr, GFP_KERNEL);
 	if (res < 0) {
-		send_ioctx->cmd.se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 		send_ioctx->cmd.se_tmr_req->response = TMR_FUNCTION_REJECTED;
-		goto process_tmr;
+		goto fail;
 	}
 
 	unpacked_lun = srpt_unpack_lun((uint8_t *)&srp_tsk->lun,
@@ -1899,22 +1895,19 @@ static void srpt_handle_tsk_mgmt(struct srpt_rdma_ch *ch,
 	res = transport_lookup_tmr_lun(&send_ioctx->cmd, unpacked_lun);
 	if (res) {
 		pr_debug("rejecting TMR for LUN %lld\n", unpacked_lun);
-		send_ioctx->cmd.se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 		send_ioctx->cmd.se_tmr_req->response = TMR_LUN_DOES_NOT_EXIST;
-		goto process_tmr;
+		goto fail;
 	}
 
 	if (srp_tsk->tsk_mgmt_func == SRP_TSK_ABORT_TASK)
 		srpt_rx_mgmt_fn_tag(send_ioctx, srp_tsk->task_tag);
 
-process_tmr:
 	kref_get(&send_ioctx->kref);
-	if (!(send_ioctx->cmd.se_cmd_flags & SCF_SCSI_CDB_EXCEPTION))
-		transport_generic_handle_tmr(&send_ioctx->cmd);
-	else
-		transport_send_check_condition_and_sense(cmd,
-						cmd->scsi_sense_reason, 0);
-
+	transport_generic_handle_tmr(&send_ioctx->cmd);
+	return;
+fail:
+	kref_get(&send_ioctx->kref);
+	transport_send_check_condition_and_sense(cmd, 0, 0); // XXX:
 }
 
 /**
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 3d74f2f39ae1..c5696240d8f6 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -620,8 +620,8 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 			return;
 		}
 
-		cmd->se_cmd.scsi_sense_reason = TCM_CHECK_CONDITION_ABORT_CMD;
-		transport_generic_request_failure(&cmd->se_cmd);
+		transport_generic_request_failure(&cmd->se_cmd,
+						  TCM_CHECK_CONDITION_ABORT_CMD);
 		return;
 	}
 
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 035c2c762537..093fb6010272 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -767,9 +767,8 @@ static int iscsit_handle_scsi_cmd(
 	struct iscsi_conn *conn,
 	unsigned char *buf)
 {
-	int	data_direction, cmdsn_ret = 0, immed_ret, ret, transport_ret;
-	int	dump_immediate_data = 0, send_check_condition = 0, payload_length;
-	struct iscsi_cmd	*cmd = NULL;
+	int data_direction, payload_length, cmdsn_ret = 0, immed_ret;
+	struct iscsi_cmd *cmd = NULL;
 	struct iscsi_scsi_req *hdr;
 	int iscsi_task_attr;
 	int sam_task_attr;
@@ -956,38 +955,26 @@ done:
 		" ExpXferLen: %u, Length: %u, CID: %hu\n", hdr->itt,
 		hdr->cmdsn, hdr->data_length, payload_length, conn->cid);
 
-	/*
-	 * The CDB is going to an se_device_t.
-	 */
-	ret = transport_lookup_cmd_lun(&cmd->se_cmd,
-				       scsilun_to_int(&hdr->lun));
-	if (ret < 0) {
-		if (cmd->se_cmd.scsi_sense_reason == TCM_NON_EXISTENT_LUN) {
-			pr_debug("Responding to non-acl'ed,"
-				" non-existent or non-exported iSCSI LUN:"
-				" 0x%016Lx\n", get_unaligned_le64(&hdr->lun));
+	cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd,
+						     scsilun_to_int(&hdr->lun));
+	if (cmd->sense_reason)
+		goto attach_cmd;
+
+	cmd->sense_reason = target_setup_cmd_from_cdb(&cmd->se_cmd, hdr->cdb);
+	if (cmd->sense_reason) {
+		if (cmd->sense_reason == TCM_OUT_OF_RESOURCES) {
+			return iscsit_add_reject_from_cmd(
+					ISCSI_REASON_BOOKMARK_NO_RESOURCES,
+					1, 1, buf, cmd);
 		}
-		send_check_condition = 1;
+
 		goto attach_cmd;
 	}
 
-	transport_ret = target_setup_cmd_from_cdb(&cmd->se_cmd, hdr->cdb);
-	if (transport_ret == -ENOMEM) {
+	if (iscsit_build_pdu_and_seq_lists(cmd, payload_length) < 0) {
 		return iscsit_add_reject_from_cmd(
-				ISCSI_REASON_BOOKMARK_NO_RESOURCES,
-				1, 1, buf, cmd);
-	} else if (transport_ret < 0) {
-		/*
-		 * Unsupported SAM Opcode.  CHECK_CONDITION will be sent
-		 * in iscsit_execute_cmd() during the CmdSN OOO Execution
-		 * Mechinism.
-		 */
-		send_check_condition = 1;
-	} else {
-		if (iscsit_build_pdu_and_seq_lists(cmd, payload_length) < 0)
-			return iscsit_add_reject_from_cmd(
-				ISCSI_REASON_BOOKMARK_NO_RESOURCES,
-				1, 1, buf, cmd);
+			ISCSI_REASON_BOOKMARK_NO_RESOURCES,
+			1, 1, buf, cmd);
 	}
 
 attach_cmd:
@@ -1000,11 +987,12 @@ attach_cmd:
 	 */
 	core_alua_check_nonop_delay(&cmd->se_cmd);
 
-	ret = iscsit_allocate_iovecs(cmd);
-	if (ret < 0)
+	if (iscsit_allocate_iovecs(cmd) < 0) {
 		return iscsit_add_reject_from_cmd(
 				ISCSI_REASON_BOOKMARK_NO_RESOURCES,
 				1, 0, buf, cmd);
+	}
+
 	/*
 	 * Check the CmdSN against ExpCmdSN/MaxCmdSN here if
 	 * the Immediate Bit is not set, and no Immediate
@@ -1031,10 +1019,7 @@ attach_cmd:
 	 * If no Immediate Data is attached, it's OK to return now.
 	 */
 	if (!cmd->immediate_data) {
-		if (send_check_condition)
-			return 0;
-
-		if (cmd->unsolicited_data) {
+		if (!cmd->sense_reason && cmd->unsolicited_data) {
 			iscsit_set_dataout_sequence_values(cmd);
 
 			spin_lock_bh(&cmd->dataout_timeout_lock);
@@ -1050,19 +1035,17 @@ attach_cmd:
 	 * thread.  They are processed in CmdSN order by
 	 * iscsit_check_received_cmdsn() below.
 	 */
-	if (send_check_condition) {
+	if (cmd->sense_reason) {
 		immed_ret = IMMEDIATE_DATA_NORMAL_OPERATION;
-		dump_immediate_data = 1;
 		goto after_immediate_data;
 	}
 	/*
 	 * Call directly into transport_generic_new_cmd() to perform
 	 * the backend memory allocation.
 	 */
-	ret = transport_generic_new_cmd(&cmd->se_cmd);
-	if (ret < 0) {
+	cmd->sense_reason = transport_generic_new_cmd(&cmd->se_cmd);
+	if (cmd->sense_reason) {
 		immed_ret = IMMEDIATE_DATA_NORMAL_OPERATION;
-		dump_immediate_data = 1;
 		goto after_immediate_data;
 	}
 
@@ -1079,7 +1062,7 @@ after_immediate_data:
 		 * Special case for Unsupported SAM WRITE Opcodes
 		 * and ImmediateData=Yes.
 		 */
-		if (dump_immediate_data) {
+		if (cmd->sense_reason) {
 			if (iscsit_dump_data_payload(conn, payload_length, 1) < 0)
 				return -1;
 		} else if (cmd->unsolicited_data) {
@@ -1272,8 +1255,7 @@ static int iscsit_handle_data_out(struct iscsi_conn *conn, unsigned char *buf)
 		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
 
 		spin_lock_irqsave(&se_cmd->t_state_lock, flags);
-		if (!(se_cmd->se_cmd_flags & SCF_SUPPORTED_SAM_OPCODE) ||
-		     (se_cmd->se_cmd_flags & SCF_SCSI_CDB_EXCEPTION))
+		if (!(se_cmd->se_cmd_flags & SCF_SUPPORTED_SAM_OPCODE))
 			dump_unsolicited_data = 1;
 		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
 
@@ -1742,7 +1724,6 @@ static int iscsit_handle_task_mgt_cmd(
 		ret = transport_lookup_tmr_lun(&cmd->se_cmd,
 					       scsilun_to_int(&hdr->lun));
 		if (ret < 0) {
-			cmd->se_cmd.se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 			se_tmr->response = ISCSI_TMF_RSP_NO_LUN;
 			goto attach;
 		}
@@ -1751,10 +1732,8 @@ static int iscsit_handle_task_mgt_cmd(
 	switch (function) {
 	case ISCSI_TM_FUNC_ABORT_TASK:
 		se_tmr->response = iscsit_tmr_abort_task(cmd, buf);
-		if (se_tmr->response != ISCSI_TMF_RSP_COMPLETE) {
-			cmd->se_cmd.se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
+		if (se_tmr->response)
 			goto attach;
-		}
 		break;
 	case ISCSI_TM_FUNC_ABORT_TASK_SET:
 	case ISCSI_TM_FUNC_CLEAR_ACA:
@@ -1763,14 +1742,12 @@ static int iscsit_handle_task_mgt_cmd(
 		break;
 	case ISCSI_TM_FUNC_TARGET_WARM_RESET:
 		if (iscsit_tmr_task_warm_reset(conn, tmr_req, buf) < 0) {
-			cmd->se_cmd.se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 			se_tmr->response = ISCSI_TMF_RSP_AUTH_FAILED;
 			goto attach;
 		}
 		break;
 	case ISCSI_TM_FUNC_TARGET_COLD_RESET:
 		if (iscsit_tmr_task_cold_reset(conn, tmr_req, buf) < 0) {
-			cmd->se_cmd.se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 			se_tmr->response = ISCSI_TMF_RSP_AUTH_FAILED;
 			goto attach;
 		}
@@ -1781,7 +1758,7 @@ static int iscsit_handle_task_mgt_cmd(
 		 * Perform sanity checks on the ExpDataSN only if the
 		 * TASK_REASSIGN was successful.
 		 */
-		if (se_tmr->response != ISCSI_TMF_RSP_COMPLETE)
+		if (se_tmr->response)
 			break;
 
 		if (iscsit_check_task_reassign_expdatasn(tmr_req, conn) < 0)
@@ -1792,7 +1769,6 @@ static int iscsit_handle_task_mgt_cmd(
 	default:
 		pr_err("Unknown TMR function: 0x%02x, protocol"
 			" error.\n", function);
-		cmd->se_cmd.se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 		se_tmr->response = ISCSI_TMF_RSP_NOT_SUPPORTED;
 		goto attach;
 	}
diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h
index 21048dbf7d13..7a333d28d9a2 100644
--- a/drivers/target/iscsi/iscsi_target_core.h
+++ b/drivers/target/iscsi/iscsi_target_core.h
@@ -474,7 +474,7 @@ struct iscsi_cmd {
 	struct scatterlist	*first_data_sg;
 	u32			first_data_sg_off;
 	u32			kmapped_nents;
-
+	sense_reason_t		sense_reason;
 }  ____cacheline_aligned;
 
 struct iscsi_tmr_req {
diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c
index 21f29d91a8cb..0b52a2371305 100644
--- a/drivers/target/iscsi/iscsi_target_erl1.c
+++ b/drivers/target/iscsi/iscsi_target_erl1.c
@@ -929,11 +929,10 @@ int iscsit_execute_cmd(struct iscsi_cmd *cmd, int ooo)
 	case ISCSI_OP_SCSI_CMD:
 		/*
 		 * Go ahead and send the CHECK_CONDITION status for
-		 * any SCSI CDB exceptions that may have occurred, also
-		 * handle the SCF_SCSI_RESERVATION_CONFLICT case here as well.
+		 * any SCSI CDB exceptions that may have occurred.
 		 */
-		if (se_cmd->se_cmd_flags & SCF_SCSI_CDB_EXCEPTION) {
-			if (se_cmd->scsi_sense_reason == TCM_RESERVATION_CONFLICT) {
+		if (cmd->sense_reason) {
+			if (cmd->sense_reason == TCM_RESERVATION_CONFLICT) {
 				cmd->i_state = ISTATE_SEND_STATUS;
 				spin_unlock_bh(&cmd->istate_lock);
 				iscsit_add_cmd_to_response_queue(cmd, cmd->conn,
@@ -956,7 +955,7 @@ int iscsit_execute_cmd(struct iscsi_cmd *cmd, int ooo)
 			 * exception
 			 */
 			return transport_send_check_condition_and_sense(se_cmd,
-					se_cmd->scsi_sense_reason, 0);
+					cmd->sense_reason, 0);
 		}
 		/*
 		 * Special case for delayed CmdSN with Immediate
@@ -1013,7 +1012,7 @@ int iscsit_execute_cmd(struct iscsi_cmd *cmd, int ooo)
 		iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
 		break;
 	case ISCSI_OP_SCSI_TMFUNC:
-		if (se_cmd->se_cmd_flags & SCF_SCSI_CDB_EXCEPTION) {
+		if (cmd->se_cmd.se_tmr_req->response) {
 			spin_unlock_bh(&cmd->istate_lock);
 			iscsit_add_cmd_to_response_queue(cmd, cmd->conn,
 					cmd->i_state);
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index b3302a9200a2..e62dc529e516 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -41,7 +41,7 @@
 #include "target_core_alua.h"
 #include "target_core_ua.h"
 
-static int core_alua_check_transition(int state, int *primary);
+static sense_reason_t core_alua_check_transition(int state, int *primary);
 static int core_alua_set_tg_pt_secondary_state(
 		struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
 		struct se_port *port, int explict, int offline);
@@ -59,7 +59,8 @@ struct t10_alua_lu_gp *default_lu_gp;
  *
  * See spc4r17 section 6.27
  */
-int target_emulate_report_target_port_groups(struct se_cmd *cmd)
+sense_reason_t
+target_emulate_report_target_port_groups(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_port *port;
@@ -68,6 +69,7 @@ int target_emulate_report_target_port_groups(struct se_cmd *cmd)
 	unsigned char *buf;
 	u32 rd_len = 0, off;
 	int ext_hdr = (cmd->t_task_cdb[1] & 0x20);
+
 	/*
 	 * Skip over RESERVED area to first Target port group descriptor
 	 * depending on the PARAMETER DATA FORMAT type..
@@ -81,10 +83,11 @@ int target_emulate_report_target_port_groups(struct se_cmd *cmd)
 		pr_warn("REPORT TARGET PORT GROUPS allocation length %u too"
 			" small for %s header\n", cmd->data_length,
 			(ext_hdr) ? "extended" : "normal");
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
+		return TCM_INVALID_CDB_FIELD;
 	}
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 	list_for_each_entry(tg_pt_gp, &dev->t10_alua.tg_pt_gps_list,
@@ -200,7 +203,8 @@ int target_emulate_report_target_port_groups(struct se_cmd *cmd)
  *
  * See spc4r17 section 6.35
  */
-int target_emulate_set_target_port_groups(struct se_cmd *cmd)
+sense_reason_t
+target_emulate_set_target_port_groups(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_port *port, *l_port = cmd->se_lun->lun_sep;
@@ -209,22 +213,23 @@ int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem, *l_tg_pt_gp_mem;
 	unsigned char *buf;
 	unsigned char *ptr;
+	sense_reason_t rc;
 	u32 len = 4; /* Skip over RESERVED area in header */
-	int alua_access_state, primary = 0, rc;
+	int alua_access_state, primary = 0;
 	u16 tg_pt_id, rtpi;
 
-	if (!l_port) {
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
-	}
+	if (!l_port)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
 	if (cmd->data_length < 4) {
 		pr_warn("SET TARGET PORT GROUPS parameter list length %u too"
 			" small\n", cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		return -EINVAL;
+		return TCM_INVALID_PARAMETER_LIST;
 	}
 
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	/*
 	 * Determine if explict ALUA via SET_TARGET_PORT_GROUPS is allowed
@@ -233,8 +238,7 @@ int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 	l_tg_pt_gp_mem = l_port->sep_alua_tg_pt_gp_mem;
 	if (!l_tg_pt_gp_mem) {
 		pr_err("Unable to access l_port->sep_alua_tg_pt_gp_mem\n");
-		cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
-		rc = -EINVAL;
+		rc = TCM_UNSUPPORTED_SCSI_OPCODE;
 		goto out;
 	}
 	spin_lock(&l_tg_pt_gp_mem->tg_pt_gp_mem_lock);
@@ -242,24 +246,22 @@ int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 	if (!l_tg_pt_gp) {
 		spin_unlock(&l_tg_pt_gp_mem->tg_pt_gp_mem_lock);
 		pr_err("Unable to access *l_tg_pt_gp_mem->tg_pt_gp\n");
-		cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
-		rc = -EINVAL;
+		rc = TCM_UNSUPPORTED_SCSI_OPCODE;
 		goto out;
 	}
-	rc = (l_tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICT_ALUA);
 	spin_unlock(&l_tg_pt_gp_mem->tg_pt_gp_mem_lock);
 
-	if (!rc) {
+	if (l_tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICT_ALUA) {
 		pr_debug("Unable to process SET_TARGET_PORT_GROUPS"
 				" while TPGS_EXPLICT_ALUA is disabled\n");
-		cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
-		rc = -EINVAL;
+		rc = TCM_UNSUPPORTED_SCSI_OPCODE;
 		goto out;
 	}
 
 	ptr = &buf[4]; /* Skip over RESERVED area in header */
 
 	while (len < cmd->data_length) {
+		bool found = false;
 		alua_access_state = (ptr[0] & 0x0f);
 		/*
 		 * Check the received ALUA access state, and determine if
@@ -267,7 +269,7 @@ int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 		 * access state.
 		 */
 		rc = core_alua_check_transition(alua_access_state, &primary);
-		if (rc != 0) {
+		if (rc) {
 			/*
 			 * If the SET TARGET PORT GROUPS attempts to establish
 			 * an invalid combination of target port asymmetric
@@ -278,11 +280,9 @@ int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 			 * REQUEST, and the additional sense code set to INVALID
 			 * FIELD IN PARAMETER LIST.
 			 */
-			cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-			rc = -EINVAL;
 			goto out;
 		}
-		rc = -1;
+
 		/*
 		 * If the ASYMMETRIC ACCESS STATE field (see table 267)
 		 * specifies a primary target port asymmetric access state,
@@ -314,11 +314,13 @@ int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 
 				atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
 				smp_mb__after_atomic_inc();
+
 				spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
-				rc = core_alua_do_port_transition(tg_pt_gp,
+				if (!core_alua_do_port_transition(tg_pt_gp,
 						dev, l_port, nacl,
-						alua_access_state, 1);
+						alua_access_state, 1))
+					found = true;
 
 				spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 				atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
@@ -326,15 +328,6 @@ int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 				break;
 			}
 			spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
-			/*
-			 * If not matching target port group ID can be located
-			 * throw an exception with ASCQ: INVALID_PARAMETER_LIST
-			 */
-			if (rc != 0) {
-				cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-				rc = -EINVAL;
-				goto out;
-			}
 		} else {
 			/*
 			 * Extact the RELATIVE TARGET PORT IDENTIFIER to identify
@@ -353,25 +346,22 @@ int target_emulate_set_target_port_groups(struct se_cmd *cmd)
 					continue;
 
 				tg_pt_gp_mem = port->sep_alua_tg_pt_gp_mem;
+
 				spin_unlock(&dev->se_port_lock);
 
-				rc = core_alua_set_tg_pt_secondary_state(
-						tg_pt_gp_mem, port, 1, 1);
+				if (!core_alua_set_tg_pt_secondary_state(
+						tg_pt_gp_mem, port, 1, 1))
+					found = true;
 
 				spin_lock(&dev->se_port_lock);
 				break;
 			}
 			spin_unlock(&dev->se_port_lock);
-			/*
-			 * If not matching relative target port identifier can
-			 * be located, throw an exception with ASCQ:
-			 * INVALID_PARAMETER_LIST
-			 */
-			if (rc != 0) {
-				cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-				rc = -EINVAL;
-				goto out;
-			}
+		}
+
+		if (!found) {
+			rc = TCM_INVALID_PARAMETER_LIST;
+			goto out;
 		}
 
 		ptr += 4;
@@ -526,7 +516,8 @@ static inline int core_alua_state_transition(
  * return 0: Used to signal success
  * reutrn -1: Used to signal failure, and invalid cdb field
  */
-int target_alua_state_check(struct se_cmd *cmd)
+sense_reason_t
+target_alua_state_check(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	unsigned char *cdb = cmd->t_task_cdb;
@@ -599,8 +590,7 @@ int target_alua_state_check(struct se_cmd *cmd)
 	default:
 		pr_err("Unknown ALUA access state: 0x%02x\n",
 				out_alua_state);
-		ret = -EINVAL;
-		break;
+		return TCM_INVALID_CDB_FIELD;
 	}
 
 out:
@@ -617,15 +607,17 @@ out:
 
 		cmd->scsi_asc = 0x04;
 		cmd->scsi_ascq = alua_ascq;
+		return TCM_CHECK_CONDITION_NOT_READY;
 	}
 
-	return ret;
+	return 0;
 }
 
 /*
  * Check implict and explict ALUA state change request.
  */
-static int core_alua_check_transition(int state, int *primary)
+static sense_reason_t
+core_alua_check_transition(int state, int *primary)
 {
 	switch (state) {
 	case ALUA_ACCESS_STATE_ACTIVE_OPTMIZED:
@@ -647,7 +639,7 @@ static int core_alua_check_transition(int state, int *primary)
 		break;
 	default:
 		pr_err("Unknown ALUA access state: 0x%02x\n", state);
-		return -EINVAL;
+		return TCM_INVALID_PARAMETER_LIST;
 	}
 
 	return 0;
diff --git a/drivers/target/target_core_alua.h b/drivers/target/target_core_alua.h
index a2af8aa15b98..e539c3e7f4ad 100644
--- a/drivers/target/target_core_alua.h
+++ b/drivers/target/target_core_alua.h
@@ -72,8 +72,8 @@ extern struct kmem_cache *t10_alua_lu_gp_mem_cache;
 extern struct kmem_cache *t10_alua_tg_pt_gp_cache;
 extern struct kmem_cache *t10_alua_tg_pt_gp_mem_cache;
 
-extern int target_emulate_report_target_port_groups(struct se_cmd *);
-extern int target_emulate_set_target_port_groups(struct se_cmd *);
+extern sense_reason_t target_emulate_report_target_port_groups(struct se_cmd *);
+extern sense_reason_t target_emulate_set_target_port_groups(struct se_cmd *);
 extern int core_alua_check_nonop_delay(struct se_cmd *);
 extern int core_alua_do_port_transition(struct t10_alua_tg_pt_gp *,
 				struct se_device *, struct se_port *,
@@ -132,6 +132,6 @@ extern ssize_t core_alua_show_secondary_write_metadata(struct se_lun *,
 extern ssize_t core_alua_store_secondary_write_metadata(struct se_lun *,
 					const char *, size_t);
 extern int core_setup_alua(struct se_device *);
-extern int target_alua_state_check(struct se_cmd *cmd);
+extern sense_reason_t target_alua_state_check(struct se_cmd *cmd);
 
 #endif /* TARGET_CORE_ALUA_H */
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 066e8159afcd..599374e6d245 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -54,18 +54,16 @@ static struct se_hba *lun0_hba;
 /* not static, needed by tpg.c */
 struct se_device *g_lun0_dev;
 
-int transport_lookup_cmd_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
+sense_reason_t
+transport_lookup_cmd_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 {
 	struct se_lun *se_lun = NULL;
 	struct se_session *se_sess = se_cmd->se_sess;
 	struct se_device *dev;
 	unsigned long flags;
 
-	if (unpacked_lun >= TRANSPORT_MAX_LUNS_PER_TPG) {
-		se_cmd->scsi_sense_reason = TCM_NON_EXISTENT_LUN;
-		se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		return -ENODEV;
-	}
+	if (unpacked_lun >= TRANSPORT_MAX_LUNS_PER_TPG)
+		return TCM_NON_EXISTENT_LUN;
 
 	spin_lock_irqsave(&se_sess->se_node_acl->device_list_lock, flags);
 	se_cmd->se_deve = se_sess->se_node_acl->device_list[unpacked_lun];
@@ -77,14 +75,12 @@ int transport_lookup_cmd_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 
 		if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
 		    (deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)) {
-			se_cmd->scsi_sense_reason = TCM_WRITE_PROTECTED;
-			se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 			pr_err("TARGET_CORE[%s]: Detected WRITE_PROTECTED LUN"
 				" Access for 0x%08x\n",
 				se_cmd->se_tfo->get_fabric_name(),
 				unpacked_lun);
 			spin_unlock_irqrestore(&se_sess->se_node_acl->device_list_lock, flags);
-			return -EACCES;
+			return TCM_WRITE_PROTECTED;
 		}
 
 		if (se_cmd->data_direction == DMA_TO_DEVICE)
@@ -109,23 +105,18 @@ int transport_lookup_cmd_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 		 * MappedLUN=0 exists for this Initiator Port.
 		 */
 		if (unpacked_lun != 0) {
-			se_cmd->scsi_sense_reason = TCM_NON_EXISTENT_LUN;
-			se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 			pr_err("TARGET_CORE[%s]: Detected NON_EXISTENT_LUN"
 				" Access for 0x%08x\n",
 				se_cmd->se_tfo->get_fabric_name(),
 				unpacked_lun);
-			return -ENODEV;
+			return TCM_NON_EXISTENT_LUN;
 		}
 		/*
 		 * Force WRITE PROTECT for virtual LUN 0
 		 */
 		if ((se_cmd->data_direction != DMA_FROM_DEVICE) &&
-		    (se_cmd->data_direction != DMA_NONE)) {
-			se_cmd->scsi_sense_reason = TCM_WRITE_PROTECTED;
-			se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-			return -EACCES;
-		}
+		    (se_cmd->data_direction != DMA_NONE))
+			return TCM_WRITE_PROTECTED;
 
 		se_lun = &se_sess->se_tpg->tpg_virt_lun0;
 		se_cmd->se_lun = &se_sess->se_tpg->tpg_virt_lun0;
@@ -162,11 +153,8 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 	struct se_tmr_req *se_tmr = se_cmd->se_tmr_req;
 	unsigned long flags;
 
-	if (unpacked_lun >= TRANSPORT_MAX_LUNS_PER_TPG) {
-		se_cmd->scsi_sense_reason = TCM_NON_EXISTENT_LUN;
-		se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
+	if (unpacked_lun >= TRANSPORT_MAX_LUNS_PER_TPG)
 		return -ENODEV;
-	}
 
 	spin_lock_irqsave(&se_sess->se_node_acl->device_list_lock, flags);
 	se_cmd->se_deve = se_sess->se_node_acl->device_list[unpacked_lun];
@@ -186,7 +174,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 			" Access for 0x%08x\n",
 			se_cmd->se_tfo->get_fabric_name(),
 			unpacked_lun);
-		se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
 		return -ENODEV;
 	}
 
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 342a6a6dcca0..3ccef831a641 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -309,7 +309,8 @@ static int fd_do_writev(struct se_cmd *cmd, struct scatterlist *sgl,
 	return 1;
 }
 
-static int fd_execute_sync_cache(struct se_cmd *cmd)
+static sense_reason_t
+fd_execute_sync_cache(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct fd_dev *fd_dev = FD_DEV(dev);
@@ -345,17 +346,16 @@ static int fd_execute_sync_cache(struct se_cmd *cmd)
 	if (immed)
 		return 0;
 
-	if (ret) {
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	if (ret)
 		target_complete_cmd(cmd, SAM_STAT_CHECK_CONDITION);
-	} else {
+	else
 		target_complete_cmd(cmd, SAM_STAT_GOOD);
-	}
 
 	return 0;
 }
 
-static int fd_execute_rw(struct se_cmd *cmd)
+static sense_reason_t
+fd_execute_rw(struct se_cmd *cmd)
 {
 	struct scatterlist *sgl = cmd->t_data_sg;
 	u32 sgl_nents = cmd->t_data_nents;
@@ -388,10 +388,9 @@ static int fd_execute_rw(struct se_cmd *cmd)
 		}
 	}
 
-	if (ret < 0) {
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return ret;
-	}
+	if (ret < 0)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
 	if (ret)
 		target_complete_cmd(cmd, SAM_STAT_GOOD);
 	return 0;
@@ -515,7 +514,8 @@ static struct sbc_ops fd_sbc_ops = {
 	.execute_sync_cache	= fd_execute_sync_cache,
 };
 
-static int fd_parse_cdb(struct se_cmd *cmd)
+static sense_reason_t
+fd_parse_cdb(struct se_cmd *cmd)
 {
 	return sbc_parse_cdb(cmd, &fd_sbc_ops);
 }
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 17fc01d6baea..53f4501819f9 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -261,13 +261,10 @@ static void iblock_end_io_flush(struct bio *bio, int err)
 		pr_err("IBLOCK: cache flush failed: %d\n", err);
 
 	if (cmd) {
-		if (err) {
-			cmd->scsi_sense_reason =
-				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		if (err)
 			target_complete_cmd(cmd, SAM_STAT_CHECK_CONDITION);
-		} else {
+		else
 			target_complete_cmd(cmd, SAM_STAT_GOOD);
-		}
 	}
 
 	bio_put(bio);
@@ -277,7 +274,8 @@ static void iblock_end_io_flush(struct bio *bio, int err)
  * Implement SYCHRONIZE CACHE.  Note that we can't handle lba ranges and must
  * always flush the whole cache.
  */
-static int iblock_execute_sync_cache(struct se_cmd *cmd)
+static sense_reason_t
+iblock_execute_sync_cache(struct se_cmd *cmd)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(cmd->se_dev);
 	int immed = (cmd->t_task_cdb[1] & 0x2);
@@ -299,7 +297,8 @@ static int iblock_execute_sync_cache(struct se_cmd *cmd)
 	return 0;
 }
 
-static int iblock_execute_unmap(struct se_cmd *cmd)
+static sense_reason_t
+iblock_execute_unmap(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
@@ -307,17 +306,18 @@ static int iblock_execute_unmap(struct se_cmd *cmd)
 	sector_t lba;
 	int size;
 	u32 range;
-	int ret = 0;
-	int dl, bd_dl;
+	sense_reason_t ret = 0;
+	int dl, bd_dl, err;
 
 	if (cmd->data_length < 8) {
 		pr_warn("UNMAP parameter list length %u too small\n",
 			cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		return -EINVAL;
+		return TCM_INVALID_PARAMETER_LIST;
 	}
 
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	dl = get_unaligned_be16(&buf[0]);
 	bd_dl = get_unaligned_be16(&buf[2]);
@@ -330,8 +330,7 @@ static int iblock_execute_unmap(struct se_cmd *cmd)
 		size = bd_dl;
 
 	if (size / 16 > dev->dev_attrib.max_unmap_block_desc_count) {
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
 		goto err;
 	}
 
@@ -347,22 +346,21 @@ static int iblock_execute_unmap(struct se_cmd *cmd)
 				 (unsigned long long)lba, range);
 
 		if (range > dev->dev_attrib.max_unmap_lba_count) {
-			cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-			ret = -EINVAL;
+			ret = TCM_INVALID_PARAMETER_LIST;
 			goto err;
 		}
 
 		if (lba + range > dev->transport->get_blocks(dev) + 1) {
-			cmd->scsi_sense_reason = TCM_ADDRESS_OUT_OF_RANGE;
-			ret = -EINVAL;
+			ret = TCM_ADDRESS_OUT_OF_RANGE;
 			goto err;
 		}
 
-		ret = blkdev_issue_discard(ib_dev->ibd_bd, lba, range,
+		err = blkdev_issue_discard(ib_dev->ibd_bd, lba, range,
 					   GFP_KERNEL, 0);
-		if (ret < 0) {
+		if (err < 0) {
 			pr_err("blkdev_issue_discard() failed: %d\n",
-					ret);
+					err);
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 			goto err;
 		}
 
@@ -377,7 +375,8 @@ err:
 	return ret;
 }
 
-static int iblock_execute_write_same(struct se_cmd *cmd)
+static sense_reason_t
+iblock_execute_write_same(struct se_cmd *cmd)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(cmd->se_dev);
 	int ret;
@@ -387,7 +386,7 @@ static int iblock_execute_write_same(struct se_cmd *cmd)
 				   0);
 	if (ret < 0) {
 		pr_debug("blkdev_issue_discard() failed for WRITE_SAME\n");
-		return ret;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 
 	target_complete_cmd(cmd, GOOD);
@@ -552,7 +551,8 @@ static void iblock_submit_bios(struct bio_list *list, int rw)
 	blk_finish_plug(&plug);
 }
 
-static int iblock_execute_rw(struct se_cmd *cmd)
+static sense_reason_t
+iblock_execute_rw(struct se_cmd *cmd)
 {
 	struct scatterlist *sgl = cmd->t_data_sg;
 	u32 sgl_nents = cmd->t_data_nents;
@@ -598,8 +598,7 @@ static int iblock_execute_rw(struct se_cmd *cmd)
 	else {
 		pr_err("Unsupported SCSI -> BLOCK LBA conversion:"
 				" %u\n", dev->dev_attrib.block_size);
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -ENOSYS;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 
 	ibr = kzalloc(sizeof(struct iblock_req), GFP_KERNEL);
@@ -659,9 +658,8 @@ fail_put_bios:
 		bio_put(bio);
 fail_free_ibr:
 	kfree(ibr);
-	cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 fail:
-	return -ENOMEM;
+	return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 }
 
 static sector_t iblock_get_blocks(struct se_device *dev)
@@ -706,7 +704,8 @@ static struct sbc_ops iblock_sbc_ops = {
 	.execute_unmap		= iblock_execute_unmap,
 };
 
-static int iblock_parse_cdb(struct se_cmd *cmd)
+static sense_reason_t
+iblock_parse_cdb(struct se_cmd *cmd)
 {
 	return sbc_parse_cdb(cmd, &iblock_sbc_ops);
 }
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 2f37720c4db3..bc9c52284845 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -101,7 +101,7 @@ int	transport_dump_vpd_ident(struct t10_vpd *, unsigned char *, int);
 bool	target_stop_cmd(struct se_cmd *cmd, unsigned long *flags);
 int	transport_clear_lun_from_sessions(struct se_lun *);
 void	transport_send_task_abort(struct se_cmd *);
-int	target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
+sense_reason_t	target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
 void	target_qf_do_work(struct work_struct *work);
 
 /* target_core_stat.c */
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index f561a08ff8e5..ffbe0ea9bbad 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -68,7 +68,8 @@ int core_pr_dump_initiator_port(
 static void __core_scsi3_complete_pro_release(struct se_device *, struct se_node_acl *,
 			struct t10_pr_registration *, int);
 
-static int target_scsi2_reservation_check(struct se_cmd *cmd)
+static sense_reason_t
+target_scsi2_reservation_check(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_session *sess = cmd->se_sess;
@@ -86,11 +87,11 @@ static int target_scsi2_reservation_check(struct se_cmd *cmd)
 		return 0;
 
 	if (dev->dev_reserved_node_acl != sess->se_node_acl)
-		return -EBUSY;
+		return TCM_RESERVATION_CONFLICT;
 
 	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS_WITH_ISID) {
 		if (dev->dev_res_bin_isid != sess->sess_bin_isid)
-			return -EBUSY;
+			return TCM_RESERVATION_CONFLICT;
 	}
 
 	return 0;
@@ -165,32 +166,28 @@ static int target_check_scsi2_reservation_conflict(struct se_cmd *cmd)
 		pr_err("Received legacy SPC-2 RESERVE/RELEASE"
 			" while active SPC-3 registrations exist,"
 			" returning RESERVATION_CONFLICT\n");
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
 		return -EBUSY;
 	}
 
 	return 0;
 }
 
-int target_scsi2_reservation_release(struct se_cmd *cmd)
+sense_reason_t
+target_scsi2_reservation_release(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_session *sess = cmd->se_sess;
 	struct se_portal_group *tpg;
-	int ret = 0, rc;
+	int rc;
 
 	if (!sess || !sess->se_tpg)
 		goto out;
 	rc = target_check_scsi2_reservation_conflict(cmd);
 	if (rc == 1)
 		goto out;
-	else if (rc < 0) {
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		ret = -EINVAL;
-		goto out;
-	}
+	if (rc < 0)
+		return TCM_RESERVATION_CONFLICT;
 
-	ret = 0;
 	spin_lock(&dev->dev_reservation_lock);
 	if (!dev->dev_reserved_node_acl || !sess)
 		goto out_unlock;
@@ -216,25 +213,24 @@ int target_scsi2_reservation_release(struct se_cmd *cmd)
 out_unlock:
 	spin_unlock(&dev->dev_reservation_lock);
 out:
-	if (!ret)
-		target_complete_cmd(cmd, GOOD);
-	return ret;
+	target_complete_cmd(cmd, GOOD);
+	return 0;
 }
 
-int target_scsi2_reservation_reserve(struct se_cmd *cmd)
+sense_reason_t
+target_scsi2_reservation_reserve(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_session *sess = cmd->se_sess;
 	struct se_portal_group *tpg;
-	int ret = 0, rc;
+	sense_reason_t ret = 0;
+	int rc;
 
 	if ((cmd->t_task_cdb[1] & 0x01) &&
 	    (cmd->t_task_cdb[1] & 0x02)) {
 		pr_err("LongIO and Obselete Bits set, returning"
 				" ILLEGAL_REQUEST\n");
-		cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
-		ret = -EINVAL;
-		goto out;
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
 	}
 	/*
 	 * This is currently the case for target_core_mod passthrough struct se_cmd
@@ -245,13 +241,10 @@ int target_scsi2_reservation_reserve(struct se_cmd *cmd)
 	rc = target_check_scsi2_reservation_conflict(cmd);
 	if (rc == 1)
 		goto out;
-	else if (rc < 0) {
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		ret = -EINVAL;
-		goto out;
-	}
 
-	ret = 0;
+	if (rc < 0)
+		return TCM_RESERVATION_CONFLICT;
+
 	tpg = sess->se_tpg;
 	spin_lock(&dev->dev_reservation_lock);
 	if (dev->dev_reserved_node_acl &&
@@ -265,8 +258,7 @@ int target_scsi2_reservation_reserve(struct se_cmd *cmd)
 			" from %s \n", cmd->se_lun->unpacked_lun,
 			cmd->se_deve->mapped_lun,
 			sess->se_node_acl->initiatorname);
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		ret = -EINVAL;
+		ret = TCM_RESERVATION_CONFLICT;
 		goto out_unlock;
 	}
 
@@ -536,7 +528,8 @@ static int core_scsi3_pr_seq_non_holder(
 	return 1; /* Conflict by default */
 }
 
-static int target_scsi3_pr_reservation_check(struct se_cmd *cmd)
+static sense_reason_t
+target_scsi3_pr_reservation_check(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_session *sess = cmd->se_sess;
@@ -562,7 +555,7 @@ static int target_scsi3_pr_reservation_check(struct se_cmd *cmd)
 
 check_nonholder:
 	if (core_scsi3_pr_seq_non_holder(cmd, pr_reg_type))
-		return -EBUSY;
+		return TCM_RESERVATION_CONFLICT;
 	return 0;
 }
 
@@ -1435,7 +1428,8 @@ static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve)
 	smp_mb__after_atomic_dec();
 }
 
-static int core_scsi3_decode_spec_i_port(
+static sense_reason_t
+core_scsi3_decode_spec_i_port(
 	struct se_cmd *cmd,
 	struct se_portal_group *tpg,
 	unsigned char *l_isid,
@@ -1457,8 +1451,9 @@ static int core_scsi3_decode_spec_i_port(
 	unsigned char *buf;
 	unsigned char *ptr, *i_str = NULL, proto_ident, tmp_proto_ident;
 	char *iport_ptr = NULL, dest_iport[64], i_buf[PR_REG_ISID_ID_LEN];
+	sense_reason_t ret;
 	u32 tpdl, tid_len = 0;
-	int ret, dest_local_nexus, prf_isid;
+	int dest_local_nexus, prf_isid;
 	u32 dest_rtpi = 0;
 
 	memset(dest_iport, 0, 64);
@@ -1473,8 +1468,7 @@ static int core_scsi3_decode_spec_i_port(
 	tidh_new = kzalloc(sizeof(struct pr_transport_id_holder), GFP_KERNEL);
 	if (!tidh_new) {
 		pr_err("Unable to allocate tidh_new\n");
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	INIT_LIST_HEAD(&tidh_new->dest_list);
 	tidh_new->dest_tpg = tpg;
@@ -1486,8 +1480,7 @@ static int core_scsi3_decode_spec_i_port(
 				sa_res_key, all_tg_pt, aptpl);
 	if (!local_pr_reg) {
 		kfree(tidh_new);
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -ENOMEM;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	tidh_new->dest_pr_reg = local_pr_reg;
 	/*
@@ -1501,12 +1494,16 @@ static int core_scsi3_decode_spec_i_port(
 	if (cmd->data_length < 28) {
 		pr_warn("SPC-PR: Received PR OUT parameter list"
 			" length too small: %u\n", cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
 		goto out;
 	}
 
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf) {
+		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		goto out;
+	}
+
 	/*
 	 * For a PERSISTENT RESERVE OUT specify initiator ports payload,
 	 * first extract TransportID Parameter Data Length, and make sure
@@ -1521,9 +1518,8 @@ static int core_scsi3_decode_spec_i_port(
 		pr_err("SPC-3 PR: Illegal tpdl: %u + 28 byte header"
 			" does not equal CDB data_length: %u\n", tpdl,
 			cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
-		goto out;
+		ret = TCM_INVALID_PARAMETER_LIST;
+		goto out_unmap;
 	}
 	/*
 	 * Start processing the received transport IDs using the
@@ -1566,16 +1562,13 @@ static int core_scsi3_decode_spec_i_port(
 			smp_mb__after_atomic_inc();
 			spin_unlock(&dev->se_port_lock);
 
-			ret = core_scsi3_tpg_depend_item(tmp_tpg);
-			if (ret != 0) {
+			if (core_scsi3_tpg_depend_item(tmp_tpg)) {
 				pr_err(" core_scsi3_tpg_depend_item()"
 					" for tmp_tpg\n");
 				atomic_dec(&tmp_tpg->tpg_pr_ref_count);
 				smp_mb__after_atomic_dec();
-				cmd->scsi_sense_reason =
-					TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-				ret = -EINVAL;
-				goto out;
+				ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+				goto out_unmap;
 			}
 			/*
 			 * Locate the destination initiator ACL to be registered
@@ -1597,17 +1590,14 @@ static int core_scsi3_decode_spec_i_port(
 				continue;
 			}
 
-			ret = core_scsi3_nodeacl_depend_item(dest_node_acl);
-			if (ret != 0) {
+			if (core_scsi3_nodeacl_depend_item(dest_node_acl)) {
 				pr_err("configfs_depend_item() failed"
 					" for dest_node_acl->acl_group\n");
 				atomic_dec(&dest_node_acl->acl_pr_ref_count);
 				smp_mb__after_atomic_dec();
 				core_scsi3_tpg_undepend_item(tmp_tpg);
-				cmd->scsi_sense_reason =
-					TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-				ret = -EINVAL;
-				goto out;
+				ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+				goto out_unmap;
 			}
 
 			dest_tpg = tmp_tpg;
@@ -1624,9 +1614,8 @@ static int core_scsi3_decode_spec_i_port(
 		if (!dest_tpg) {
 			pr_err("SPC-3 PR SPEC_I_PT: Unable to locate"
 					" dest_tpg\n");
-			cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-			ret = -EINVAL;
-			goto out;
+			ret = TCM_INVALID_PARAMETER_LIST;
+			goto out_unmap;
 		}
 
 		pr_debug("SPC-3 PR SPEC_I_PT: Got %s data_length: %u tpdl: %u"
@@ -1639,9 +1628,8 @@ static int core_scsi3_decode_spec_i_port(
 				" %u for Transport ID: %s\n", tid_len, ptr);
 			core_scsi3_nodeacl_undepend_item(dest_node_acl);
 			core_scsi3_tpg_undepend_item(dest_tpg);
-			cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-			ret = -EINVAL;
-			goto out;
+			ret = TCM_INVALID_PARAMETER_LIST;
+			goto out_unmap;
 		}
 		/*
 		 * Locate the desintation struct se_dev_entry pointer for matching
@@ -1658,23 +1646,19 @@ static int core_scsi3_decode_spec_i_port(
 
 			core_scsi3_nodeacl_undepend_item(dest_node_acl);
 			core_scsi3_tpg_undepend_item(dest_tpg);
-			cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-			ret = -EINVAL;
-			goto out;
+			ret = TCM_INVALID_PARAMETER_LIST;
+			goto out_unmap;
 		}
 
-		ret = core_scsi3_lunacl_depend_item(dest_se_deve);
-		if (ret < 0) {
+		if (core_scsi3_lunacl_depend_item(dest_se_deve)) {
 			pr_err("core_scsi3_lunacl_depend_item()"
 					" failed\n");
 			atomic_dec(&dest_se_deve->pr_ref_count);
 			smp_mb__after_atomic_dec();
 			core_scsi3_nodeacl_undepend_item(dest_node_acl);
 			core_scsi3_tpg_undepend_item(dest_tpg);
-			cmd->scsi_sense_reason =
-				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-			ret = -EINVAL;
-			goto out;
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+			goto out_unmap;
 		}
 
 		pr_debug("SPC-3 PR SPEC_I_PT: Located %s Node: %s"
@@ -1710,10 +1694,8 @@ static int core_scsi3_decode_spec_i_port(
 			core_scsi3_lunacl_undepend_item(dest_se_deve);
 			core_scsi3_nodeacl_undepend_item(dest_node_acl);
 			core_scsi3_tpg_undepend_item(dest_tpg);
-			cmd->scsi_sense_reason =
-				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-			ret = -ENOMEM;
-			goto out;
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+			goto out_unmap;
 		}
 		INIT_LIST_HEAD(&tidh_new->dest_list);
 		tidh_new->dest_tpg = dest_tpg;
@@ -1744,9 +1726,8 @@ static int core_scsi3_decode_spec_i_port(
 			core_scsi3_nodeacl_undepend_item(dest_node_acl);
 			core_scsi3_tpg_undepend_item(dest_tpg);
 			kfree(tidh_new);
-			cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-			ret = -EINVAL;
-			goto out;
+			ret = TCM_INVALID_PARAMETER_LIST;
+			goto out_unmap;
 		}
 		tidh_new->dest_pr_reg = dest_pr_reg;
 		list_add_tail(&tidh_new->dest_list, &tid_dest_list);
@@ -1804,8 +1785,9 @@ static int core_scsi3_decode_spec_i_port(
 	}
 
 	return 0;
-out:
+out_unmap:
 	transport_kunmap_data_sg(cmd);
+out:
 	/*
 	 * For the failure case, release everything from tid_dest_list
 	 * including *dest_pr_reg and the configfs dependances..
@@ -2020,14 +2002,15 @@ static int __core_scsi3_write_aptpl_to_file(
 	return 0;
 }
 
-static int core_scsi3_update_and_write_aptpl(
-	struct se_device *dev,
-	unsigned char *in_buf,
-	u32 in_pr_aptpl_buf_len)
+static int
+core_scsi3_update_and_write_aptpl(struct se_device *dev, unsigned char *in_buf,
+		u32 in_pr_aptpl_buf_len)
 {
 	unsigned char null_buf[64], *buf;
 	u32 pr_aptpl_buf_len;
-	int ret, clear_aptpl_metadata = 0;
+	int clear_aptpl_metadata = 0;
+	int ret;
+
 	/*
 	 * Can be called with a NULL pointer from PROUT service action CLEAR
 	 */
@@ -2049,25 +2032,17 @@ static int core_scsi3_update_and_write_aptpl(
 				clear_aptpl_metadata);
 	if (ret != 0)
 		return ret;
+
 	/*
 	 * __core_scsi3_write_aptpl_to_file() will call strlen()
 	 * on the passed buf to determine pr_aptpl_buf_len.
 	 */
-	ret = __core_scsi3_write_aptpl_to_file(dev, buf, 0);
-	if (ret != 0)
-		return ret;
-
-	return ret;
+	return __core_scsi3_write_aptpl_to_file(dev, buf, 0);
 }
 
-static int core_scsi3_emulate_pro_register(
-	struct se_cmd *cmd,
-	u64 res_key,
-	u64 sa_res_key,
-	int aptpl,
-	int all_tg_pt,
-	int spec_i_pt,
-	int ignore_key)
+static sense_reason_t
+core_scsi3_emulate_pro_register(struct se_cmd *cmd, u64 res_key, u64 sa_res_key,
+		int aptpl, int all_tg_pt, int spec_i_pt, int ignore_key)
 {
 	struct se_session *se_sess = cmd->se_sess;
 	struct se_device *dev = cmd->se_dev;
@@ -2079,12 +2054,12 @@ static int core_scsi3_emulate_pro_register(
 	/* Used for APTPL metadata w/ UNREGISTER */
 	unsigned char *pr_aptpl_buf = NULL;
 	unsigned char isid_buf[PR_REG_ISID_LEN], *isid_ptr = NULL;
-	int pr_holder = 0, ret = 0, type;
+	sense_reason_t ret;
+	int pr_holder = 0, type;
 
 	if (!se_sess || !se_lun) {
 		pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	se_tpg = se_sess->se_tpg;
 	se_deve = se_sess->se_node_acl->device_list[cmd->orig_fe_lun];
@@ -2103,8 +2078,7 @@ static int core_scsi3_emulate_pro_register(
 		if (res_key) {
 			pr_warn("SPC-3 PR: Reservation Key non-zero"
 				" for SA REGISTER, returning CONFLICT\n");
-			cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-			return -EINVAL;
+			return TCM_RESERVATION_CONFLICT;
 		}
 		/*
 		 * Do nothing but return GOOD status.
@@ -2118,15 +2092,13 @@ static int core_scsi3_emulate_pro_register(
 			 * Port Endpoint that the PRO was received from on the
 			 * Logical Unit of the SCSI device server.
 			 */
-			ret = core_scsi3_alloc_registration(cmd->se_dev,
+			if (core_scsi3_alloc_registration(cmd->se_dev,
 					se_sess->se_node_acl, se_deve, isid_ptr,
 					sa_res_key, all_tg_pt, aptpl,
-					ignore_key, 0);
-			if (ret != 0) {
+					ignore_key, 0)) {
 				pr_err("Unable to allocate"
 					" struct t10_pr_registration\n");
-				cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-				return -EINVAL;
+				return TCM_INVALID_PARAMETER_LIST;
 			}
 		} else {
 			/*
@@ -2160,201 +2132,192 @@ static int core_scsi3_emulate_pro_register(
 		pr_reg = core_scsi3_locate_pr_reg(cmd->se_dev,
 				se_sess->se_node_acl, se_sess);
 
-		ret = core_scsi3_update_and_write_aptpl(cmd->se_dev,
+		if (core_scsi3_update_and_write_aptpl(cmd->se_dev,
 				&pr_reg->pr_aptpl_buf[0],
-				pr_tmpl->pr_aptpl_buf_len);
-		if (!ret) {
+				pr_tmpl->pr_aptpl_buf_len)) {
 			pr_tmpl->pr_aptpl_active = 1;
 			pr_debug("SPC-3 PR: Set APTPL Bit Activated for REGISTER\n");
 		}
 
-		core_scsi3_put_pr_reg(pr_reg);
-		return ret;
-	} else {
-		/*
-		 * Locate the existing *pr_reg via struct se_node_acl pointers
-		 */
-		pr_reg = pr_reg_e;
-		type = pr_reg->pr_res_type;
-
-		if (!ignore_key) {
-			if (res_key != pr_reg->pr_res_key) {
-				pr_err("SPC-3 PR REGISTER: Received"
-					" res_key: 0x%016Lx does not match"
-					" existing SA REGISTER res_key:"
-					" 0x%016Lx\n", res_key,
-					pr_reg->pr_res_key);
-				core_scsi3_put_pr_reg(pr_reg);
-				cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-				return -EINVAL;
-			}
+		goto out_put_pr_reg;
+	}
+
+	/*
+	 * Locate the existing *pr_reg via struct se_node_acl pointers
+	 */
+	pr_reg = pr_reg_e;
+	type = pr_reg->pr_res_type;
+
+	if (!ignore_key) {
+		if (res_key != pr_reg->pr_res_key) {
+			pr_err("SPC-3 PR REGISTER: Received"
+				" res_key: 0x%016Lx does not match"
+				" existing SA REGISTER res_key:"
+				" 0x%016Lx\n", res_key,
+				pr_reg->pr_res_key);
+			ret = TCM_RESERVATION_CONFLICT;
+			goto out_put_pr_reg;
 		}
-		if (spec_i_pt) {
-			pr_err("SPC-3 PR UNREGISTER: SPEC_I_PT"
-				" set while sa_res_key=0\n");
-			core_scsi3_put_pr_reg(pr_reg);
-			cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-			return -EINVAL;
+	}
+
+	if (spec_i_pt) {
+		pr_err("SPC-3 PR UNREGISTER: SPEC_I_PT"
+			" set while sa_res_key=0\n");
+		ret = TCM_INVALID_PARAMETER_LIST;
+		goto out_put_pr_reg;
+	}
+
+	/*
+	 * An existing ALL_TG_PT=1 registration being released
+	 * must also set ALL_TG_PT=1 in the incoming PROUT.
+	 */
+	if (pr_reg->pr_reg_all_tg_pt && !(all_tg_pt)) {
+		pr_err("SPC-3 PR UNREGISTER: ALL_TG_PT=1"
+			" registration exists, but ALL_TG_PT=1 bit not"
+			" present in received PROUT\n");
+		ret = TCM_INVALID_CDB_FIELD;
+		goto out_put_pr_reg;
+	}
+
+	/*
+	 * Allocate APTPL metadata buffer used for UNREGISTER ops
+	 */
+	if (aptpl) {
+		pr_aptpl_buf = kzalloc(pr_tmpl->pr_aptpl_buf_len,
+					GFP_KERNEL);
+		if (!pr_aptpl_buf) {
+			pr_err("Unable to allocate"
+				" pr_aptpl_buf\n");
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+			goto out_put_pr_reg;
 		}
-		/*
-		 * An existing ALL_TG_PT=1 registration being released
-		 * must also set ALL_TG_PT=1 in the incoming PROUT.
-		 */
-		if (pr_reg->pr_reg_all_tg_pt && !(all_tg_pt)) {
-			pr_err("SPC-3 PR UNREGISTER: ALL_TG_PT=1"
-				" registration exists, but ALL_TG_PT=1 bit not"
-				" present in received PROUT\n");
-			core_scsi3_put_pr_reg(pr_reg);
-			cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-			return -EINVAL;
+	}
+
+	/*
+	 * sa_res_key=0 Unregister Reservation Key for registered I_T
+	 * Nexus sa_res_key=1 Change Reservation Key for registered I_T
+	 * Nexus.
+	 */
+	if (!sa_res_key) {
+		pr_holder = core_scsi3_check_implict_release(
+				cmd->se_dev, pr_reg);
+		if (pr_holder < 0) {
+			kfree(pr_aptpl_buf);
+			ret = TCM_RESERVATION_CONFLICT;
+			goto out_put_pr_reg;
 		}
+
+		spin_lock(&pr_tmpl->registration_lock);
 		/*
-		 * Allocate APTPL metadata buffer used for UNREGISTER ops
+		 * Release all ALL_TG_PT=1 for the matching SCSI Initiator Port
+		 * and matching pr_res_key.
 		 */
-		if (aptpl) {
-			pr_aptpl_buf = kzalloc(pr_tmpl->pr_aptpl_buf_len,
-						GFP_KERNEL);
-			if (!pr_aptpl_buf) {
-				pr_err("Unable to allocate"
-					" pr_aptpl_buf\n");
-				core_scsi3_put_pr_reg(pr_reg);
-				cmd->scsi_sense_reason =
-					TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-				return -EINVAL;
+		if (pr_reg->pr_reg_all_tg_pt) {
+			list_for_each_entry_safe(pr_reg_p, pr_reg_tmp,
+					&pr_tmpl->registration_list,
+					pr_reg_list) {
+
+				if (!pr_reg_p->pr_reg_all_tg_pt)
+					continue;
+				if (pr_reg_p->pr_res_key != res_key)
+					continue;
+				if (pr_reg == pr_reg_p)
+					continue;
+				if (strcmp(pr_reg->pr_reg_nacl->initiatorname,
+					   pr_reg_p->pr_reg_nacl->initiatorname))
+					continue;
+
+				__core_scsi3_free_registration(dev,
+						pr_reg_p, NULL, 0);
 			}
 		}
+
 		/*
-		 * sa_res_key=0 Unregister Reservation Key for registered I_T
-		 * Nexus sa_res_key=1 Change Reservation Key for registered I_T
-		 * Nexus.
+		 * Release the calling I_T Nexus registration now..
 		 */
-		if (!sa_res_key) {
-			pr_holder = core_scsi3_check_implict_release(
-					cmd->se_dev, pr_reg);
-			if (pr_holder < 0) {
-				kfree(pr_aptpl_buf);
-				core_scsi3_put_pr_reg(pr_reg);
-				cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-				return -EINVAL;
-			}
-
-			spin_lock(&pr_tmpl->registration_lock);
-			/*
-			 * Release all ALL_TG_PT=1 for the matching SCSI Initiator Port
-			 * and matching pr_res_key.
-			 */
-			if (pr_reg->pr_reg_all_tg_pt) {
-				list_for_each_entry_safe(pr_reg_p, pr_reg_tmp,
-						&pr_tmpl->registration_list,
-						pr_reg_list) {
-
-					if (!pr_reg_p->pr_reg_all_tg_pt)
-						continue;
+		__core_scsi3_free_registration(cmd->se_dev, pr_reg, NULL, 1);
 
-					if (pr_reg_p->pr_res_key != res_key)
-						continue;
-
-					if (pr_reg == pr_reg_p)
-						continue;
-
-					if (strcmp(pr_reg->pr_reg_nacl->initiatorname,
-						   pr_reg_p->pr_reg_nacl->initiatorname))
-						continue;
-
-					__core_scsi3_free_registration(dev,
-							pr_reg_p, NULL, 0);
-				}
-			}
-			/*
-			 * Release the calling I_T Nexus registration now..
-			 */
-			__core_scsi3_free_registration(cmd->se_dev, pr_reg,
-							NULL, 1);
-			/*
-			 * From spc4r17, section 5.7.11.3 Unregistering
-			 *
-			 * If the persistent reservation is a registrants only
-			 * type, the device server shall establish a unit
-			 * attention condition for the initiator port associated
-			 * with every registered I_T nexus except for the I_T
-			 * nexus on which the PERSISTENT RESERVE OUT command was
-			 * received, with the additional sense code set to
-			 * RESERVATIONS RELEASED.
-			 */
-			if (pr_holder &&
-			   ((type == PR_TYPE_WRITE_EXCLUSIVE_REGONLY) ||
-			    (type == PR_TYPE_EXCLUSIVE_ACCESS_REGONLY))) {
-				list_for_each_entry(pr_reg_p,
-						&pr_tmpl->registration_list,
-						pr_reg_list) {
-
-					core_scsi3_ua_allocate(
-						pr_reg_p->pr_reg_nacl,
-						pr_reg_p->pr_res_mapped_lun,
-						0x2A,
-						ASCQ_2AH_RESERVATIONS_RELEASED);
-				}
+		/*
+		 * From spc4r17, section 5.7.11.3 Unregistering
+		 *
+		 * If the persistent reservation is a registrants only
+		 * type, the device server shall establish a unit
+		 * attention condition for the initiator port associated
+		 * with every registered I_T nexus except for the I_T
+		 * nexus on which the PERSISTENT RESERVE OUT command was
+		 * received, with the additional sense code set to
+		 * RESERVATIONS RELEASED.
+		 */
+		if (pr_holder &&
+		   (type == PR_TYPE_WRITE_EXCLUSIVE_REGONLY ||
+		    type == PR_TYPE_EXCLUSIVE_ACCESS_REGONLY)) {
+			list_for_each_entry(pr_reg_p,
+					&pr_tmpl->registration_list,
+					pr_reg_list) {
+
+				core_scsi3_ua_allocate(
+					pr_reg_p->pr_reg_nacl,
+					pr_reg_p->pr_res_mapped_lun,
+					0x2A,
+					ASCQ_2AH_RESERVATIONS_RELEASED);
 			}
-			spin_unlock(&pr_tmpl->registration_lock);
+		}
+		spin_unlock(&pr_tmpl->registration_lock);
 
-			if (!aptpl) {
-				pr_tmpl->pr_aptpl_active = 0;
-				core_scsi3_update_and_write_aptpl(dev, NULL, 0);
-				pr_debug("SPC-3 PR: Set APTPL Bit Deactivated"
-						" for UNREGISTER\n");
-				return 0;
-			}
+		if (!aptpl) {
+			pr_tmpl->pr_aptpl_active = 0;
+			core_scsi3_update_and_write_aptpl(dev, NULL, 0);
+			pr_debug("SPC-3 PR: Set APTPL Bit Deactivated"
+					" for UNREGISTER\n");
+			return 0;
+		}
 
-			ret = core_scsi3_update_and_write_aptpl(dev,
-					&pr_aptpl_buf[0],
-					pr_tmpl->pr_aptpl_buf_len);
-			if (!ret) {
-				pr_tmpl->pr_aptpl_active = 1;
-				pr_debug("SPC-3 PR: Set APTPL Bit Activated"
-						" for UNREGISTER\n");
-			}
+		if (!core_scsi3_update_and_write_aptpl(dev, &pr_aptpl_buf[0],
+				pr_tmpl->pr_aptpl_buf_len)) {
+			pr_tmpl->pr_aptpl_active = 1;
+			pr_debug("SPC-3 PR: Set APTPL Bit Activated"
+					" for UNREGISTER\n");
+		}
 
-			kfree(pr_aptpl_buf);
-			return ret;
-		} else {
-			/*
-			 * Increment PRgeneration counter for struct se_device"
-			 * upon a successful REGISTER, see spc4r17 section 6.3.2
-			 * READ_KEYS service action.
-			 */
-			pr_reg->pr_res_generation = core_scsi3_pr_generation(
-							cmd->se_dev);
-			pr_reg->pr_res_key = sa_res_key;
-			pr_debug("SPC-3 PR [%s] REGISTER%s: Changed Reservation"
-				" Key for %s to: 0x%016Lx PRgeneration:"
-				" 0x%08x\n", cmd->se_tfo->get_fabric_name(),
-				(ignore_key) ? "_AND_IGNORE_EXISTING_KEY" : "",
-				pr_reg->pr_reg_nacl->initiatorname,
-				pr_reg->pr_res_key, pr_reg->pr_res_generation);
-
-			if (!aptpl) {
-				pr_tmpl->pr_aptpl_active = 0;
-				core_scsi3_update_and_write_aptpl(dev, NULL, 0);
-				core_scsi3_put_pr_reg(pr_reg);
-				pr_debug("SPC-3 PR: Set APTPL Bit Deactivated"
-						" for REGISTER\n");
-				return 0;
-			}
+		goto out_free_aptpl_buf;
+	}
 
-			ret = core_scsi3_update_and_write_aptpl(dev,
-					&pr_aptpl_buf[0],
-					pr_tmpl->pr_aptpl_buf_len);
-			if (!ret) {
-				pr_tmpl->pr_aptpl_active = 1;
-				pr_debug("SPC-3 PR: Set APTPL Bit Activated"
-						" for REGISTER\n");
-			}
+	/*
+	 * Increment PRgeneration counter for struct se_device"
+	 * upon a successful REGISTER, see spc4r17 section 6.3.2
+	 * READ_KEYS service action.
+	 */
+	pr_reg->pr_res_generation = core_scsi3_pr_generation(cmd->se_dev);
+	pr_reg->pr_res_key = sa_res_key;
+	pr_debug("SPC-3 PR [%s] REGISTER%s: Changed Reservation"
+		" Key for %s to: 0x%016Lx PRgeneration:"
+		" 0x%08x\n", cmd->se_tfo->get_fabric_name(),
+		(ignore_key) ? "_AND_IGNORE_EXISTING_KEY" : "",
+		pr_reg->pr_reg_nacl->initiatorname,
+		pr_reg->pr_res_key, pr_reg->pr_res_generation);
 
-			kfree(pr_aptpl_buf);
-			core_scsi3_put_pr_reg(pr_reg);
-		}
+	if (!aptpl) {
+		pr_tmpl->pr_aptpl_active = 0;
+		core_scsi3_update_and_write_aptpl(dev, NULL, 0);
+		pr_debug("SPC-3 PR: Set APTPL Bit Deactivated"
+				" for REGISTER\n");
+		ret = 0;
+		goto out_put_pr_reg;
 	}
-	return 0;
+
+	if (!core_scsi3_update_and_write_aptpl(dev, &pr_aptpl_buf[0],
+						pr_tmpl->pr_aptpl_buf_len)) {
+		pr_tmpl->pr_aptpl_active = 1;
+		pr_debug("SPC-3 PR: Set APTPL Bit Activated"
+			" for REGISTER\n");
+	}
+
+out_free_aptpl_buf:
+	kfree(pr_aptpl_buf);
+	ret = 0;
+out_put_pr_reg:
+	core_scsi3_put_pr_reg(pr_reg);
+	return ret;
 }
 
 unsigned char *core_scsi3_pr_dump_type(int type)
@@ -2379,26 +2342,23 @@ unsigned char *core_scsi3_pr_dump_type(int type)
 	return "Unknown SPC-3 PR Type";
 }
 
-static int core_scsi3_pro_reserve(
-	struct se_cmd *cmd,
-	struct se_device *dev,
-	int type,
-	int scope,
-	u64 res_key)
+static sense_reason_t
+core_scsi3_pro_reserve(struct se_cmd *cmd, int type, int scope, u64 res_key)
 {
+	struct se_device *dev = cmd->se_dev;
 	struct se_session *se_sess = cmd->se_sess;
 	struct se_lun *se_lun = cmd->se_lun;
 	struct t10_pr_registration *pr_reg, *pr_res_holder;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	char i_buf[PR_REG_ISID_ID_LEN];
-	int ret, prf_isid;
+	sense_reason_t ret;
+	int prf_isid;
 
 	memset(i_buf, 0, PR_REG_ISID_ID_LEN);
 
 	if (!se_sess || !se_lun) {
 		pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	/*
 	 * Locate the existing *pr_reg via struct se_node_acl pointers
@@ -2408,8 +2368,7 @@ static int core_scsi3_pro_reserve(
 	if (!pr_reg) {
 		pr_err("SPC-3 PR: Unable to locate"
 			" PR_REGISTERED *pr_reg for RESERVE\n");
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	/*
 	 * From spc4r17 Section 5.7.9: Reserving:
@@ -2424,9 +2383,8 @@ static int core_scsi3_pro_reserve(
 		pr_err("SPC-3 PR RESERVE: Received res_key: 0x%016Lx"
 			" does not match existing SA REGISTER res_key:"
 			" 0x%016Lx\n", res_key, pr_reg->pr_res_key);
-		core_scsi3_put_pr_reg(pr_reg);
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		return -EINVAL;
+		ret = TCM_RESERVATION_CONFLICT;
+		goto out_put_pr_reg;
 	}
 	/*
 	 * From spc4r17 Section 5.7.9: Reserving:
@@ -2440,9 +2398,8 @@ static int core_scsi3_pro_reserve(
 	 */
 	if (scope != PR_SCOPE_LU_SCOPE) {
 		pr_err("SPC-3 PR: Illegal SCOPE: 0x%02x\n", scope);
-		core_scsi3_put_pr_reg(pr_reg);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		return -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
+		goto out_put_pr_reg;
 	}
 	/*
 	 * See if we have an existing PR reservation holder pointer at
@@ -2473,9 +2430,8 @@ static int core_scsi3_pro_reserve(
 				pr_res_holder->pr_reg_nacl->initiatorname);
 
 			spin_unlock(&dev->dev_reservation_lock);
-			core_scsi3_put_pr_reg(pr_reg);
-			cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-			return -EINVAL;
+			ret = TCM_RESERVATION_CONFLICT;
+			goto out_put_pr_reg;
 		}
 		/*
 		 * From spc4r17 Section 5.7.9: Reserving:
@@ -2497,9 +2453,8 @@ static int core_scsi3_pro_reserve(
 				pr_res_holder->pr_reg_nacl->initiatorname);
 
 			spin_unlock(&dev->dev_reservation_lock);
-			core_scsi3_put_pr_reg(pr_reg);
-			cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-			return -EINVAL;
+			ret = TCM_RESERVATION_CONFLICT;
+			goto out_put_pr_reg;
 		}
 		/*
 		 * From spc4r17 Section 5.7.9: Reserving:
@@ -2512,8 +2467,8 @@ static int core_scsi3_pro_reserve(
 		 * shall completethe command with GOOD status.
 		 */
 		spin_unlock(&dev->dev_reservation_lock);
-		core_scsi3_put_pr_reg(pr_reg);
-		return 0;
+		ret = 0;
+		goto out_put_pr_reg;
 	}
 	/*
 	 * Otherwise, our *pr_reg becomes the PR reservation holder for said
@@ -2537,27 +2492,24 @@ static int core_scsi3_pro_reserve(
 	spin_unlock(&dev->dev_reservation_lock);
 
 	if (pr_tmpl->pr_aptpl_active) {
-		ret = core_scsi3_update_and_write_aptpl(cmd->se_dev,
+		if (!core_scsi3_update_and_write_aptpl(cmd->se_dev,
 				&pr_reg->pr_aptpl_buf[0],
-				pr_tmpl->pr_aptpl_buf_len);
-		if (!ret)
+				pr_tmpl->pr_aptpl_buf_len)) {
 			pr_debug("SPC-3 PR: Updated APTPL metadata"
 					" for RESERVE\n");
+		}
 	}
 
+	ret = 0;
+out_put_pr_reg:
 	core_scsi3_put_pr_reg(pr_reg);
-	return 0;
+	return ret;
 }
 
-static int core_scsi3_emulate_pro_reserve(
-	struct se_cmd *cmd,
-	int type,
-	int scope,
-	u64 res_key)
+static sense_reason_t
+core_scsi3_emulate_pro_reserve(struct se_cmd *cmd, int type, int scope,
+		u64 res_key)
 {
-	struct se_device *dev = cmd->se_dev;
-	int ret = 0;
-
 	switch (type) {
 	case PR_TYPE_WRITE_EXCLUSIVE:
 	case PR_TYPE_EXCLUSIVE_ACCESS:
@@ -2565,16 +2517,12 @@ static int core_scsi3_emulate_pro_reserve(
 	case PR_TYPE_EXCLUSIVE_ACCESS_REGONLY:
 	case PR_TYPE_WRITE_EXCLUSIVE_ALLREG:
 	case PR_TYPE_EXCLUSIVE_ACCESS_ALLREG:
-		ret = core_scsi3_pro_reserve(cmd, dev, type, scope, res_key);
-		break;
+		return core_scsi3_pro_reserve(cmd, type, scope, res_key);
 	default:
 		pr_err("SPC-3 PR: Unknown Service Action RESERVE Type:"
 			" 0x%02x\n", type);
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
+		return TCM_INVALID_CDB_FIELD;
 	}
-
-	return ret;
 }
 
 /*
@@ -2612,23 +2560,21 @@ static void __core_scsi3_complete_pro_release(
 	pr_reg->pr_res_holder = pr_reg->pr_res_type = pr_reg->pr_res_scope = 0;
 }
 
-static int core_scsi3_emulate_pro_release(
-	struct se_cmd *cmd,
-	int type,
-	int scope,
-	u64 res_key)
+static sense_reason_t
+core_scsi3_emulate_pro_release(struct se_cmd *cmd, int type, int scope,
+		u64 res_key)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_session *se_sess = cmd->se_sess;
 	struct se_lun *se_lun = cmd->se_lun;
 	struct t10_pr_registration *pr_reg, *pr_reg_p, *pr_res_holder;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
-	int ret, all_reg = 0;
+	int all_reg = 0;
+	sense_reason_t ret = 0;
 
 	if (!se_sess || !se_lun) {
 		pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	/*
 	 * Locate the existing *pr_reg via struct se_node_acl pointers
@@ -2637,8 +2583,7 @@ static int core_scsi3_emulate_pro_release(
 	if (!pr_reg) {
 		pr_err("SPC-3 PR: Unable to locate"
 			" PR_REGISTERED *pr_reg for RELEASE\n");
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	/*
 	 * From spc4r17 Section 5.7.11.2 Releasing:
@@ -2659,7 +2604,6 @@ static int core_scsi3_emulate_pro_release(
 		 * No persistent reservation, return GOOD status.
 		 */
 		spin_unlock(&dev->dev_reservation_lock);
-		core_scsi3_put_pr_reg(pr_reg);
 		return 0;
 	}
 	if ((pr_res_holder->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_ALLREG) ||
@@ -2673,9 +2617,9 @@ static int core_scsi3_emulate_pro_release(
 		 * persistent reservation holder. return GOOD status.
 		 */
 		spin_unlock(&dev->dev_reservation_lock);
-		core_scsi3_put_pr_reg(pr_reg);
-		return 0;
+		goto out_put_pr_reg;
 	}
+
 	/*
 	 * From spc4r17 Section 5.7.11.2 Releasing:
 	 *
@@ -2695,9 +2639,8 @@ static int core_scsi3_emulate_pro_release(
 			" does not match existing SA REGISTER res_key:"
 			" 0x%016Lx\n", res_key, pr_reg->pr_res_key);
 		spin_unlock(&dev->dev_reservation_lock);
-		core_scsi3_put_pr_reg(pr_reg);
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		return -EINVAL;
+		ret = TCM_RESERVATION_CONFLICT;
+		goto out_put_pr_reg;
 	}
 	/*
 	 * From spc4r17 Section 5.7.11.2 Releasing and above:
@@ -2718,9 +2661,8 @@ static int core_scsi3_emulate_pro_release(
 			pr_res_holder->pr_reg_nacl->initiatorname);
 
 		spin_unlock(&dev->dev_reservation_lock);
-		core_scsi3_put_pr_reg(pr_reg);
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		return -EINVAL;
+		ret = TCM_RESERVATION_CONFLICT;
+		goto out_put_pr_reg;
 	}
 	/*
 	 * In response to a persistent reservation release request from the
@@ -2773,20 +2715,18 @@ static int core_scsi3_emulate_pro_release(
 
 write_aptpl:
 	if (pr_tmpl->pr_aptpl_active) {
-		ret = core_scsi3_update_and_write_aptpl(cmd->se_dev,
-				&pr_reg->pr_aptpl_buf[0],
-				pr_tmpl->pr_aptpl_buf_len);
-		if (!ret)
+		if (!core_scsi3_update_and_write_aptpl(cmd->se_dev,
+			&pr_reg->pr_aptpl_buf[0], pr_tmpl->pr_aptpl_buf_len)) {
 			pr_debug("SPC-3 PR: Updated APTPL metadata for RELEASE\n");
+		}
 	}
-
+out_put_pr_reg:
 	core_scsi3_put_pr_reg(pr_reg);
-	return 0;
+	return ret;
 }
 
-static int core_scsi3_emulate_pro_clear(
-	struct se_cmd *cmd,
-	u64 res_key)
+static sense_reason_t
+core_scsi3_emulate_pro_clear(struct se_cmd *cmd, u64 res_key)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_node_acl *pr_reg_nacl;
@@ -2803,8 +2743,7 @@ static int core_scsi3_emulate_pro_clear(
 	if (!pr_reg_n) {
 		pr_err("SPC-3 PR: Unable to locate"
 			" PR_REGISTERED *pr_reg for CLEAR\n");
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	/*
 	 * From spc4r17 section 5.7.11.6, Clearing:
@@ -2823,8 +2762,7 @@ static int core_scsi3_emulate_pro_clear(
 			" existing SA REGISTER res_key:"
 			" 0x%016Lx\n", res_key, pr_reg_n->pr_res_key);
 		core_scsi3_put_pr_reg(pr_reg_n);
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		return -EINVAL;
+		return TCM_RESERVATION_CONFLICT;
 	}
 	/*
 	 * a) Release the persistent reservation, if any;
@@ -2948,13 +2886,9 @@ static void core_scsi3_release_preempt_and_abort(
 	}
 }
 
-static int core_scsi3_pro_preempt(
-	struct se_cmd *cmd,
-	int type,
-	int scope,
-	u64 res_key,
-	u64 sa_res_key,
-	int abort)
+static sense_reason_t
+core_scsi3_pro_preempt(struct se_cmd *cmd, int type, int scope, u64 res_key,
+		u64 sa_res_key, int abort)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_node_acl *pr_reg_nacl;
@@ -2964,12 +2898,10 @@ static int core_scsi3_pro_preempt(
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
 	u32 pr_res_mapped_lun = 0;
 	int all_reg = 0, calling_it_nexus = 0, released_regs = 0;
-	int prh_type = 0, prh_scope = 0, ret;
+	int prh_type = 0, prh_scope = 0;
 
-	if (!se_sess) {
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
-	}
+	if (!se_sess)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	pr_reg_n = core_scsi3_locate_pr_reg(cmd->se_dev, se_sess->se_node_acl,
 				se_sess);
@@ -2977,19 +2909,16 @@ static int core_scsi3_pro_preempt(
 		pr_err("SPC-3 PR: Unable to locate"
 			" PR_REGISTERED *pr_reg for PREEMPT%s\n",
 			(abort) ? "_AND_ABORT" : "");
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		return -EINVAL;
+		return TCM_RESERVATION_CONFLICT;
 	}
 	if (pr_reg_n->pr_res_key != res_key) {
 		core_scsi3_put_pr_reg(pr_reg_n);
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		return -EINVAL;
+		return TCM_RESERVATION_CONFLICT;
 	}
 	if (scope != PR_SCOPE_LU_SCOPE) {
 		pr_err("SPC-3 PR: Illegal SCOPE: 0x%02x\n", scope);
 		core_scsi3_put_pr_reg(pr_reg_n);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		return -EINVAL;
+		return TCM_INVALID_PARAMETER_LIST;
 	}
 
 	spin_lock(&dev->dev_reservation_lock);
@@ -3002,8 +2931,7 @@ static int core_scsi3_pro_preempt(
 	if (!all_reg && !sa_res_key) {
 		spin_unlock(&dev->dev_reservation_lock);
 		core_scsi3_put_pr_reg(pr_reg_n);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		return -EINVAL;
+		return TCM_INVALID_PARAMETER_LIST;
 	}
 	/*
 	 * From spc4r17, section 5.7.11.4.4 Removing Registrations:
@@ -3097,8 +3025,7 @@ static int core_scsi3_pro_preempt(
 		if (!released_regs) {
 			spin_unlock(&dev->dev_reservation_lock);
 			core_scsi3_put_pr_reg(pr_reg_n);
-			cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-			return -EINVAL;
+			return TCM_RESERVATION_CONFLICT;
 		}
 		/*
 		 * For an existing all registrants type reservation
@@ -3117,13 +3044,13 @@ static int core_scsi3_pro_preempt(
 		spin_unlock(&dev->dev_reservation_lock);
 
 		if (pr_tmpl->pr_aptpl_active) {
-			ret = core_scsi3_update_and_write_aptpl(cmd->se_dev,
+			if (!core_scsi3_update_and_write_aptpl(cmd->se_dev,
 					&pr_reg_n->pr_aptpl_buf[0],
-					pr_tmpl->pr_aptpl_buf_len);
-			if (!ret)
+					pr_tmpl->pr_aptpl_buf_len)) {
 				pr_debug("SPC-3 PR: Updated APTPL"
 					" metadata for  PREEMPT%s\n", (abort) ?
 					"_AND_ABORT" : "");
+			}
 		}
 
 		core_scsi3_put_pr_reg(pr_reg_n);
@@ -3253,12 +3180,12 @@ static int core_scsi3_pro_preempt(
 	}
 
 	if (pr_tmpl->pr_aptpl_active) {
-		ret = core_scsi3_update_and_write_aptpl(cmd->se_dev,
+		if (!core_scsi3_update_and_write_aptpl(cmd->se_dev,
 				&pr_reg_n->pr_aptpl_buf[0],
-				pr_tmpl->pr_aptpl_buf_len);
-		if (!ret)
+				pr_tmpl->pr_aptpl_buf_len)) {
 			pr_debug("SPC-3 PR: Updated APTPL metadata for PREEMPT"
-				"%s\n", (abort) ? "_AND_ABORT" : "");
+				"%s\n", abort ? "_AND_ABORT" : "");
+		}
 	}
 
 	core_scsi3_put_pr_reg(pr_reg_n);
@@ -3266,16 +3193,10 @@ static int core_scsi3_pro_preempt(
 	return 0;
 }
 
-static int core_scsi3_emulate_pro_preempt(
-	struct se_cmd *cmd,
-	int type,
-	int scope,
-	u64 res_key,
-	u64 sa_res_key,
-	int abort)
+static sense_reason_t
+core_scsi3_emulate_pro_preempt(struct se_cmd *cmd, int type, int scope,
+		u64 res_key, u64 sa_res_key, int abort)
 {
-	int ret = 0;
-
 	switch (type) {
 	case PR_TYPE_WRITE_EXCLUSIVE:
 	case PR_TYPE_EXCLUSIVE_ACCESS:
@@ -3283,26 +3204,19 @@ static int core_scsi3_emulate_pro_preempt(
 	case PR_TYPE_EXCLUSIVE_ACCESS_REGONLY:
 	case PR_TYPE_WRITE_EXCLUSIVE_ALLREG:
 	case PR_TYPE_EXCLUSIVE_ACCESS_ALLREG:
-		ret = core_scsi3_pro_preempt(cmd, type, scope,
-				res_key, sa_res_key, abort);
-		break;
+		return core_scsi3_pro_preempt(cmd, type, scope, res_key,
+					      sa_res_key, abort);
 	default:
 		pr_err("SPC-3 PR: Unknown Service Action PREEMPT%s"
 			" Type: 0x%02x\n", (abort) ? "_AND_ABORT" : "", type);
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
+		return TCM_INVALID_CDB_FIELD;
 	}
-
-	return ret;
 }
 
 
-static int core_scsi3_emulate_pro_register_and_move(
-	struct se_cmd *cmd,
-	u64 res_key,
-	u64 sa_res_key,
-	int aptpl,
-	int unreg)
+static sense_reason_t
+core_scsi3_emulate_pro_register_and_move(struct se_cmd *cmd, u64 res_key,
+		u64 sa_res_key, int aptpl, int unreg)
 {
 	struct se_session *se_sess = cmd->se_sess;
 	struct se_device *dev = cmd->se_dev;
@@ -3318,15 +3232,16 @@ static int core_scsi3_emulate_pro_register_and_move(
 	unsigned char *initiator_str;
 	char *iport_ptr = NULL, dest_iport[64], i_buf[PR_REG_ISID_ID_LEN];
 	u32 tid_len, tmp_tid_len;
-	int new_reg = 0, type, scope, ret, matching_iname, prf_isid;
+	int new_reg = 0, type, scope, matching_iname, prf_isid;
+	sense_reason_t ret;
 	unsigned short rtpi;
 	unsigned char proto_ident;
 
 	if (!se_sess || !se_lun) {
 		pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
+
 	memset(dest_iport, 0, 64);
 	memset(i_buf, 0, PR_REG_ISID_ID_LEN);
 	se_tpg = se_sess->se_tpg;
@@ -3342,8 +3257,7 @@ static int core_scsi3_emulate_pro_register_and_move(
 	if (!pr_reg) {
 		pr_err("SPC-3 PR: Unable to locate PR_REGISTERED"
 			" *pr_reg for REGISTER_AND_MOVE\n");
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -EINVAL;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	/*
 	 * The provided reservation key much match the existing reservation key
@@ -3353,9 +3267,8 @@ static int core_scsi3_emulate_pro_register_and_move(
 		pr_warn("SPC-3 PR REGISTER_AND_MOVE: Received"
 			" res_key: 0x%016Lx does not match existing SA REGISTER"
 			" res_key: 0x%016Lx\n", res_key, pr_reg->pr_res_key);
-		core_scsi3_put_pr_reg(pr_reg);
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		return -EINVAL;
+		ret = TCM_RESERVATION_CONFLICT;
+		goto out_put_pr_reg;
 	}
 	/*
 	 * The service active reservation key needs to be non zero
@@ -3363,9 +3276,8 @@ static int core_scsi3_emulate_pro_register_and_move(
 	if (!sa_res_key) {
 		pr_warn("SPC-3 PR REGISTER_AND_MOVE: Received zero"
 			" sa_res_key\n");
-		core_scsi3_put_pr_reg(pr_reg);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		return -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
+		goto out_put_pr_reg;
 	}
 
 	/*
@@ -3374,6 +3286,11 @@ static int core_scsi3_emulate_pro_register_and_move(
 	 * information.
 	 */
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf) {
+		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		goto out_put_pr_reg;
+	}
+
 	rtpi = (buf[18] & 0xff) << 8;
 	rtpi |= buf[19] & 0xff;
 	tid_len = (buf[20] & 0xff) << 24;
@@ -3387,9 +3304,8 @@ static int core_scsi3_emulate_pro_register_and_move(
 		pr_err("SPC-3 PR: Illegal tid_len: %u + 24 byte header"
 			" does not equal CDB data_length: %u\n", tid_len,
 			cmd->data_length);
-		core_scsi3_put_pr_reg(pr_reg);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		return -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
+		goto out_put_pr_reg;
 	}
 
 	spin_lock(&dev->se_port_lock);
@@ -3407,15 +3323,13 @@ static int core_scsi3_emulate_pro_register_and_move(
 		smp_mb__after_atomic_inc();
 		spin_unlock(&dev->se_port_lock);
 
-		ret = core_scsi3_tpg_depend_item(dest_se_tpg);
-		if (ret != 0) {
+		if (core_scsi3_tpg_depend_item(dest_se_tpg)) {
 			pr_err("core_scsi3_tpg_depend_item() failed"
 				" for dest_se_tpg\n");
 			atomic_dec(&dest_se_tpg->tpg_pr_ref_count);
 			smp_mb__after_atomic_dec();
-			core_scsi3_put_pr_reg(pr_reg);
-			cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-			return -EINVAL;
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+			goto out_put_pr_reg;
 		}
 
 		spin_lock(&dev->se_port_lock);
@@ -3427,12 +3341,15 @@ static int core_scsi3_emulate_pro_register_and_move(
 		pr_err("SPC-3 PR REGISTER_AND_MOVE: Unable to locate"
 			" fabric ops from Relative Target Port Identifier:"
 			" %hu\n", rtpi);
-		core_scsi3_put_pr_reg(pr_reg);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		return -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
+		goto out_put_pr_reg;
 	}
 
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf) {
+		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		goto out_put_pr_reg;
+	}
 	proto_ident = (buf[24] & 0x0f);
 
 	pr_debug("SPC-3 PR REGISTER_AND_MOVE: Extracted Protocol Identifier:"
@@ -3444,16 +3361,14 @@ static int core_scsi3_emulate_pro_register_and_move(
 			" from fabric: %s\n", proto_ident,
 			dest_tf_ops->get_fabric_proto_ident(dest_se_tpg),
 			dest_tf_ops->get_fabric_name());
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
 		goto out;
 	}
 	if (dest_tf_ops->tpg_parse_pr_out_transport_id == NULL) {
 		pr_err("SPC-3 PR REGISTER_AND_MOVE: Fabric does not"
 			" containg a valid tpg_parse_pr_out_transport_id"
 			" function pointer\n");
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		ret = -EINVAL;
+		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		goto out;
 	}
 	initiator_str = dest_tf_ops->tpg_parse_pr_out_transport_id(dest_se_tpg,
@@ -3461,8 +3376,7 @@ static int core_scsi3_emulate_pro_register_and_move(
 	if (!initiator_str) {
 		pr_err("SPC-3 PR REGISTER_AND_MOVE: Unable to locate"
 			" initiator_str from Transport ID\n");
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
 		goto out;
 	}
 
@@ -3491,8 +3405,7 @@ static int core_scsi3_emulate_pro_register_and_move(
 		pr_err("SPC-3 PR REGISTER_AND_MOVE: TransportID: %s"
 			" matches: %s on received I_T Nexus\n", initiator_str,
 			pr_reg_nacl->initiatorname);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
 		goto out;
 	}
 	if (!strcmp(iport_ptr, pr_reg->pr_reg_isid)) {
@@ -3500,8 +3413,7 @@ static int core_scsi3_emulate_pro_register_and_move(
 			" matches: %s %s on received I_T Nexus\n",
 			initiator_str, iport_ptr, pr_reg_nacl->initiatorname,
 			pr_reg->pr_reg_isid);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
 		goto out;
 	}
 after_iport_check:
@@ -3521,19 +3433,17 @@ after_iport_check:
 		pr_err("Unable to locate %s dest_node_acl for"
 			" TransportID%s\n", dest_tf_ops->get_fabric_name(),
 			initiator_str);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
 		goto out;
 	}
-	ret = core_scsi3_nodeacl_depend_item(dest_node_acl);
-	if (ret != 0) {
+
+	if (core_scsi3_nodeacl_depend_item(dest_node_acl)) {
 		pr_err("core_scsi3_nodeacl_depend_item() for"
 			" dest_node_acl\n");
 		atomic_dec(&dest_node_acl->acl_pr_ref_count);
 		smp_mb__after_atomic_dec();
 		dest_node_acl = NULL;
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
 		goto out;
 	}
 
@@ -3549,19 +3459,16 @@ after_iport_check:
 	if (!dest_se_deve) {
 		pr_err("Unable to locate %s dest_se_deve from RTPI:"
 			" %hu\n",  dest_tf_ops->get_fabric_name(), rtpi);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
+		ret = TCM_INVALID_PARAMETER_LIST;
 		goto out;
 	}
 
-	ret = core_scsi3_lunacl_depend_item(dest_se_deve);
-	if (ret < 0) {
+	if (core_scsi3_lunacl_depend_item(dest_se_deve)) {
 		pr_err("core_scsi3_lunacl_depend_item() failed\n");
 		atomic_dec(&dest_se_deve->pr_ref_count);
 		smp_mb__after_atomic_dec();
 		dest_se_deve = NULL;
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		ret = -EINVAL;
+		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		goto out;
 	}
 
@@ -3580,8 +3487,7 @@ after_iport_check:
 		pr_warn("SPC-3 PR REGISTER_AND_MOVE: No reservation"
 			" currently held\n");
 		spin_unlock(&dev->dev_reservation_lock);
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		ret = -EINVAL;
+		ret = TCM_INVALID_CDB_FIELD;
 		goto out;
 	}
 	/*
@@ -3594,8 +3500,7 @@ after_iport_check:
 		pr_warn("SPC-3 PR REGISTER_AND_MOVE: Calling I_T"
 			" Nexus is not reservation holder\n");
 		spin_unlock(&dev->dev_reservation_lock);
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		ret = -EINVAL;
+		ret = TCM_RESERVATION_CONFLICT;
 		goto out;
 	}
 	/*
@@ -3613,8 +3518,7 @@ after_iport_check:
 			" reservation for type: %s\n",
 			core_scsi3_pr_dump_type(pr_res_holder->pr_res_type));
 		spin_unlock(&dev->dev_reservation_lock);
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		ret = -EINVAL;
+		ret = TCM_RESERVATION_CONFLICT;
 		goto out;
 	}
 	pr_res_nacl = pr_res_holder->pr_reg_nacl;
@@ -3646,13 +3550,11 @@ after_iport_check:
 	dest_pr_reg = __core_scsi3_locate_pr_reg(dev, dest_node_acl,
 					iport_ptr);
 	if (!dest_pr_reg) {
-		ret = core_scsi3_alloc_registration(cmd->se_dev,
+		if (core_scsi3_alloc_registration(cmd->se_dev,
 				dest_node_acl, dest_se_deve, iport_ptr,
-				sa_res_key, 0, aptpl, 2, 1);
-		if (ret != 0) {
+				sa_res_key, 0, aptpl, 2, 1)) {
 			spin_unlock(&dev->dev_reservation_lock);
-			cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-			ret = -EINVAL;
+			ret = TCM_INVALID_PARAMETER_LIST;
 			goto out;
 		}
 		dest_pr_reg = __core_scsi3_locate_pr_reg(dev, dest_node_acl,
@@ -3723,12 +3625,12 @@ after_iport_check:
 				" REGISTER_AND_MOVE\n");
 	} else {
 		pr_tmpl->pr_aptpl_active = 1;
-		ret = core_scsi3_update_and_write_aptpl(cmd->se_dev,
+		if (!core_scsi3_update_and_write_aptpl(cmd->se_dev,
 				&dest_pr_reg->pr_aptpl_buf[0],
-				pr_tmpl->pr_aptpl_buf_len);
-		if (!ret)
+				pr_tmpl->pr_aptpl_buf_len)) {
 			pr_debug("SPC-3 PR: Set APTPL Bit Activated for"
 					" REGISTER_AND_MOVE\n");
+		}
 	}
 
 	transport_kunmap_data_sg(cmd);
@@ -3743,6 +3645,8 @@ out:
 	if (dest_node_acl)
 		core_scsi3_nodeacl_undepend_item(dest_node_acl);
 	core_scsi3_tpg_undepend_item(dest_se_tpg);
+
+out_put_pr_reg:
 	core_scsi3_put_pr_reg(pr_reg);
 	return ret;
 }
@@ -3760,14 +3664,15 @@ static unsigned long long core_scsi3_extract_reservation_key(unsigned char *cdb)
 /*
  * See spc4r17 section 6.14 Table 170
  */
-int target_scsi3_emulate_pr_out(struct se_cmd *cmd)
+sense_reason_t
+target_scsi3_emulate_pr_out(struct se_cmd *cmd)
 {
 	unsigned char *cdb = &cmd->t_task_cdb[0];
 	unsigned char *buf;
 	u64 res_key, sa_res_key;
 	int sa, scope, type, aptpl;
 	int spec_i_pt = 0, all_tg_pt = 0, unreg = 0;
-	int ret;
+	sense_reason_t ret;
 
 	/*
 	 * Following spc2r20 5.5.1 Reservations overview:
@@ -3782,28 +3687,22 @@ int target_scsi3_emulate_pr_out(struct se_cmd *cmd)
 		pr_err("Received PERSISTENT_RESERVE CDB while legacy"
 			" SPC-2 reservation is held, returning"
 			" RESERVATION_CONFLICT\n");
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		ret = -EINVAL;
-		goto out;
+		return TCM_RESERVATION_CONFLICT;
 	}
 
 	/*
 	 * FIXME: A NULL struct se_session pointer means an this is not coming from
 	 * a $FABRIC_MOD's nexus, but from internal passthrough ops.
 	 */
-	if (!cmd->se_sess) {
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		ret = -EINVAL;
-		goto out;
-	}
+	if (!cmd->se_sess)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	if (cmd->data_length < 24) {
 		pr_warn("SPC-PR: Received PR OUT parameter list"
 			" length too small: %u\n", cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
-		goto out;
+		return TCM_INVALID_PARAMETER_LIST;
 	}
+
 	/*
 	 * From the PERSISTENT_RESERVE_OUT command descriptor block (CDB)
 	 */
@@ -3812,6 +3711,9 @@ int target_scsi3_emulate_pr_out(struct se_cmd *cmd)
 	type = (cdb[2] & 0x0f);
 
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
 	/*
 	 * From PERSISTENT_RESERVE_OUT parameter list (payload)
 	 */
@@ -3835,11 +3737,8 @@ int target_scsi3_emulate_pr_out(struct se_cmd *cmd)
 	/*
 	 * SPEC_I_PT=1 is only valid for Service action: REGISTER
 	 */
-	if (spec_i_pt && ((cdb[1] & 0x1f) != PRO_REGISTER)) {
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
-		goto out;
-	}
+	if (spec_i_pt && ((cdb[1] & 0x1f) != PRO_REGISTER))
+		return TCM_INVALID_PARAMETER_LIST;
 
 	/*
 	 * From spc4r17 section 6.14:
@@ -3854,10 +3753,9 @@ int target_scsi3_emulate_pr_out(struct se_cmd *cmd)
 	    (cmd->data_length != 24)) {
 		pr_warn("SPC-PR: Received PR OUT illegal parameter"
 			" list length: %u\n", cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
-		goto out;
+		return TCM_INVALID_PARAMETER_LIST;
 	}
+
 	/*
 	 * (core_scsi3_emulate_pro_* function parameters
 	 * are defined by spc4r17 Table 174:
@@ -3896,12 +3794,9 @@ int target_scsi3_emulate_pr_out(struct se_cmd *cmd)
 	default:
 		pr_err("Unknown PERSISTENT_RESERVE_OUT service"
 			" action: 0x%02x\n", cdb[1] & 0x1f);
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		ret = -EINVAL;
-		break;
+		return TCM_INVALID_CDB_FIELD;
 	}
 
-out:
 	if (!ret)
 		target_complete_cmd(cmd, GOOD);
 	return ret;
@@ -3912,7 +3807,8 @@ out:
  *
  * See spc4r17 section 5.7.6.2 and section 6.13.2, Table 160
  */
-static int core_scsi3_pri_read_keys(struct se_cmd *cmd)
+static sense_reason_t
+core_scsi3_pri_read_keys(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct t10_pr_registration *pr_reg;
@@ -3922,11 +3818,13 @@ static int core_scsi3_pri_read_keys(struct se_cmd *cmd)
 	if (cmd->data_length < 8) {
 		pr_err("PRIN SA READ_KEYS SCSI Data Length: %u"
 			" too small\n", cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
+		return TCM_INVALID_CDB_FIELD;
 	}
 
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
 	buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff);
 	buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff);
 	buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff);
@@ -3970,7 +3868,8 @@ static int core_scsi3_pri_read_keys(struct se_cmd *cmd)
  *
  * See spc4r17 section 5.7.6.3 and section 6.13.3.2 Table 161 and 162
  */
-static int core_scsi3_pri_read_reservation(struct se_cmd *cmd)
+static sense_reason_t
+core_scsi3_pri_read_reservation(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct t10_pr_registration *pr_reg;
@@ -3981,11 +3880,13 @@ static int core_scsi3_pri_read_reservation(struct se_cmd *cmd)
 	if (cmd->data_length < 8) {
 		pr_err("PRIN SA READ_RESERVATIONS SCSI Data Length: %u"
 			" too small\n", cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
+		return TCM_INVALID_CDB_FIELD;
 	}
 
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
 	buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff);
 	buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff);
 	buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff);
@@ -4054,7 +3955,8 @@ err:
  *
  * See spc4r17 section 6.13.4 Table 165
  */
-static int core_scsi3_pri_report_capabilities(struct se_cmd *cmd)
+static sense_reason_t
+core_scsi3_pri_report_capabilities(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct t10_reservation *pr_tmpl = &dev->t10_pr;
@@ -4064,11 +3966,12 @@ static int core_scsi3_pri_report_capabilities(struct se_cmd *cmd)
 	if (cmd->data_length < 6) {
 		pr_err("PRIN SA REPORT_CAPABILITIES SCSI Data Length:"
 			" %u too small\n", cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
+		return TCM_INVALID_CDB_FIELD;
 	}
 
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	buf[0] = ((add_len << 8) & 0xff);
 	buf[1] = (add_len & 0xff);
@@ -4110,7 +4013,8 @@ static int core_scsi3_pri_report_capabilities(struct se_cmd *cmd)
  *
  * See spc4r17 section 6.13.5 Table 168 and 169
  */
-static int core_scsi3_pri_read_full_status(struct se_cmd *cmd)
+static sense_reason_t
+core_scsi3_pri_read_full_status(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_node_acl *se_nacl;
@@ -4125,11 +4029,12 @@ static int core_scsi3_pri_read_full_status(struct se_cmd *cmd)
 	if (cmd->data_length < 8) {
 		pr_err("PRIN SA READ_FULL_STATUS SCSI Data Length: %u"
 			" too small\n", cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
+		return TCM_INVALID_CDB_FIELD;
 	}
 
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff);
 	buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff);
@@ -4255,9 +4160,10 @@ static int core_scsi3_pri_read_full_status(struct se_cmd *cmd)
 	return 0;
 }
 
-int target_scsi3_emulate_pr_in(struct se_cmd *cmd)
+sense_reason_t
+target_scsi3_emulate_pr_in(struct se_cmd *cmd)
 {
-	int ret;
+	sense_reason_t ret;
 
 	/*
 	 * Following spc2r20 5.5.1 Reservations overview:
@@ -4272,8 +4178,7 @@ int target_scsi3_emulate_pr_in(struct se_cmd *cmd)
 		pr_err("Received PERSISTENT_RESERVE CDB while legacy"
 			" SPC-2 reservation is held, returning"
 			" RESERVATION_CONFLICT\n");
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
-		return -EINVAL;
+		return TCM_RESERVATION_CONFLICT;
 	}
 
 	switch (cmd->t_task_cdb[1] & 0x1f) {
@@ -4292,9 +4197,7 @@ int target_scsi3_emulate_pr_in(struct se_cmd *cmd)
 	default:
 		pr_err("Unknown PERSISTENT_RESERVE_IN service"
 			" action: 0x%02x\n", cmd->t_task_cdb[1] & 0x1f);
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		ret = -EINVAL;
-		break;
+		return TCM_INVALID_CDB_FIELD;
 	}
 
 	if (!ret)
@@ -4302,10 +4205,11 @@ int target_scsi3_emulate_pr_in(struct se_cmd *cmd)
 	return ret;
 }
 
-int target_check_reservation(struct se_cmd *cmd)
+sense_reason_t
+target_check_reservation(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
-	int ret;
+	sense_reason_t ret;
 
 	if (!cmd->se_sess)
 		return 0;
diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h
index 7616f2690ca0..b4a004247ab2 100644
--- a/drivers/target/target_core_pr.h
+++ b/drivers/target/target_core_pr.h
@@ -47,8 +47,8 @@ extern struct kmem_cache *t10_pr_reg_cache;
 
 extern int core_pr_dump_initiator_port(struct t10_pr_registration *,
 			char *, u32);
-extern int target_scsi2_reservation_release(struct se_cmd *);
-extern int target_scsi2_reservation_reserve(struct se_cmd *);
+extern sense_reason_t target_scsi2_reservation_release(struct se_cmd *);
+extern sense_reason_t target_scsi2_reservation_reserve(struct se_cmd *);
 extern int core_scsi3_alloc_aptpl_registration(
 			struct t10_reservation *, u64,
 			unsigned char *, unsigned char *, u32,
@@ -61,8 +61,8 @@ extern void core_scsi3_free_pr_reg_from_nacl(struct se_device *,
 extern void core_scsi3_free_all_registrations(struct se_device *);
 extern unsigned char *core_scsi3_pr_dump_type(int);
 
-extern int target_scsi3_emulate_pr_in(struct se_cmd *);
-extern int target_scsi3_emulate_pr_out(struct se_cmd *);
-extern int target_check_reservation(struct se_cmd *cmd);
+extern sense_reason_t target_scsi3_emulate_pr_in(struct se_cmd *);
+extern sense_reason_t target_scsi3_emulate_pr_out(struct se_cmd *);
+extern sense_reason_t target_check_reservation(struct se_cmd *);
 
 #endif /* TARGET_CORE_PR_H */
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index aa3e80a2f8db..b5c722bdd993 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -60,7 +60,7 @@ static inline struct pscsi_dev_virt *PSCSI_DEV(struct se_device *dev)
 
 static struct se_subsystem_api pscsi_template;
 
-static int pscsi_execute_cmd(struct se_cmd *cmd);
+static sense_reason_t pscsi_execute_cmd(struct se_cmd *cmd);
 static void pscsi_req_done(struct request *, int);
 
 /*	pscsi_attach_hba():
@@ -642,7 +642,11 @@ static void pscsi_transport_complete(struct se_cmd *cmd, struct scatterlist *sg,
 	if (((cdb[0] == MODE_SENSE) || (cdb[0] == MODE_SENSE_10)) &&
 	     (status_byte(result) << 1) == SAM_STAT_GOOD) {
 		if (cmd->se_deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY) {
-			unsigned char *buf = transport_kmap_data_sg(cmd);
+			unsigned char *buf;
+
+			buf = transport_kmap_data_sg(cmd);
+			if (!buf)
+				; /* XXX: TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE */
 
 			if (cdb[0] == MODE_SENSE_10) {
 				if (!(buf[3] & 0x80))
@@ -856,9 +860,9 @@ static inline struct bio *pscsi_get_bio(int sg_num)
 	return bio;
 }
 
-static int pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl,
-		u32 sgl_nents, enum dma_data_direction data_direction,
-		struct bio **hbio)
+static sense_reason_t
+pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
+		enum dma_data_direction data_direction, struct bio **hbio)
 {
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev);
 	struct bio *bio = NULL, *tbio = NULL;
@@ -946,7 +950,7 @@ static int pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl,
 		}
 	}
 
-	return sgl_nents;
+	return 0;
 fail:
 	while (*hbio) {
 		bio = *hbio;
@@ -954,8 +958,7 @@ fail:
 		bio->bi_next = NULL;
 		bio_endio(bio, 0);	/* XXX: should be error */
 	}
-	cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-	return -ENOMEM;
+	return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 }
 
 /*
@@ -982,15 +985,13 @@ static inline void pscsi_clear_cdb_lun(unsigned char *cdb)
 	}
 }
 
-static int pscsi_parse_cdb(struct se_cmd *cmd)
+static sense_reason_t
+pscsi_parse_cdb(struct se_cmd *cmd)
 {
 	unsigned char *cdb = cmd->t_task_cdb;
 
-	if (cmd->se_cmd_flags & SCF_BIDI) {
-		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
-		return -EINVAL;
-	}
+	if (cmd->se_cmd_flags & SCF_BIDI)
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
 
 	pscsi_clear_cdb_lun(cdb);
 
@@ -1020,7 +1021,8 @@ static int pscsi_parse_cdb(struct se_cmd *cmd)
 	}
 }
 
-static int pscsi_execute_cmd(struct se_cmd *cmd)
+static sense_reason_t
+pscsi_execute_cmd(struct se_cmd *cmd)
 {
 	struct scatterlist *sgl = cmd->t_data_sg;
 	u32 sgl_nents = cmd->t_data_nents;
@@ -1029,7 +1031,7 @@ static int pscsi_execute_cmd(struct se_cmd *cmd)
 	struct pscsi_plugin_task *pt;
 	struct request *req;
 	struct bio *hbio;
-	int ret;
+	sense_reason_t ret;
 
 	/*
 	 * Dynamically alloc cdb space, since it may be larger than
@@ -1037,8 +1039,7 @@ static int pscsi_execute_cmd(struct se_cmd *cmd)
 	 */
 	pt = kzalloc(sizeof(*pt) + scsi_command_size(cmd->t_task_cdb), GFP_KERNEL);
 	if (!pt) {
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		return -ENOMEM;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	cmd->priv = pt;
 
@@ -1052,24 +1053,21 @@ static int pscsi_execute_cmd(struct se_cmd *cmd)
 		if (!req || IS_ERR(req)) {
 			pr_err("PSCSI: blk_get_request() failed: %ld\n",
 					req ? IS_ERR(req) : -ENOMEM);
-			cmd->scsi_sense_reason =
-				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 			goto fail;
 		}
 	} else {
 		BUG_ON(!cmd->data_length);
 
 		ret = pscsi_map_sg(cmd, sgl, sgl_nents, data_direction, &hbio);
-		if (ret < 0) {
-			cmd->scsi_sense_reason =
-				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		if (ret)
 			goto fail;
-		}
 
 		req = blk_make_request(pdv->pdv_sd->request_queue, hbio,
 				       GFP_KERNEL);
 		if (IS_ERR(req)) {
 			pr_err("pSCSI: blk_make_request() failed\n");
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 			goto fail_free_bio;
 		}
 	}
@@ -1100,10 +1098,10 @@ fail_free_bio:
 		bio->bi_next = NULL;
 		bio_endio(bio, 0);	/* XXX: should be error */
 	}
-	cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 fail:
 	kfree(pt);
-	return -ENOMEM;
+	return ret;
 }
 
 /*	pscsi_get_device_type():
@@ -1152,7 +1150,6 @@ static void pscsi_req_done(struct request *req, int uptodate)
 		pr_debug("PSCSI Host Byte exception at cmd: %p CDB:"
 			" 0x%02x Result: 0x%08x\n", cmd, pt->pscsi_cdb[0],
 			pt->pscsi_result);
-		cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
 		target_complete_cmd(cmd, SAM_STAT_CHECK_CONDITION);
 		break;
 	}
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 92b1307a9931..126529cd5325 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -275,7 +275,8 @@ static struct rd_dev_sg_table *rd_get_sg_table(struct rd_dev *rd_dev, u32 page)
 	return NULL;
 }
 
-static int rd_execute_rw(struct se_cmd *cmd)
+static sense_reason_t
+rd_execute_rw(struct se_cmd *cmd)
 {
 	struct scatterlist *sgl = cmd->t_data_sg;
 	u32 sgl_nents = cmd->t_data_nents;
@@ -298,7 +299,7 @@ static int rd_execute_rw(struct se_cmd *cmd)
 
 	table = rd_get_sg_table(dev, rd_page);
 	if (!table)
-		return -EINVAL;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	rd_sg = &table->sg_table[rd_page - table->page_start_offset];
 
@@ -348,7 +349,7 @@ static int rd_execute_rw(struct se_cmd *cmd)
 		table = rd_get_sg_table(dev, rd_page);
 		if (!table) {
 			sg_miter_stop(&m);
-			return -EINVAL;
+			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		}
 
 		/* since we increment, the first sg entry is correct */
@@ -431,7 +432,8 @@ static struct sbc_ops rd_sbc_ops = {
 	.execute_rw		= rd_execute_rw,
 };
 
-static int rd_parse_cdb(struct se_cmd *cmd)
+static sense_reason_t
+rd_parse_cdb(struct se_cmd *cmd)
 {
 	return sbc_parse_cdb(cmd, &rd_sbc_ops);
 }
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index a4eb9c553654..3929fa201088 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -37,7 +37,8 @@
 #include "target_core_ua.h"
 
 
-static int sbc_emulate_readcapacity(struct se_cmd *cmd)
+static sense_reason_t
+sbc_emulate_readcapacity(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	unsigned long long blocks_long = dev->transport->get_blocks(dev);
@@ -60,16 +61,18 @@ static int sbc_emulate_readcapacity(struct se_cmd *cmd)
 	buf[7] = dev->dev_attrib.block_size & 0xff;
 
 	rbuf = transport_kmap_data_sg(cmd);
-	if (rbuf) {
-		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
-		transport_kunmap_data_sg(cmd);
-	}
+	if (!rbuf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
+	memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+	transport_kunmap_data_sg(cmd);
 
 	target_complete_cmd(cmd, GOOD);
 	return 0;
 }
 
-static int sbc_emulate_readcapacity_16(struct se_cmd *cmd)
+static sense_reason_t
+sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	unsigned char *rbuf;
@@ -97,10 +100,11 @@ static int sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 		buf[14] = 0x80;
 
 	rbuf = transport_kmap_data_sg(cmd);
-	if (rbuf) {
-		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
-		transport_kunmap_data_sg(cmd);
-	}
+	if (!rbuf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
+	memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+	transport_kunmap_data_sg(cmd);
 
 	target_complete_cmd(cmd, GOOD);
 	return 0;
@@ -129,7 +133,8 @@ int spc_get_write_same_sectors(struct se_cmd *cmd)
 }
 EXPORT_SYMBOL(spc_get_write_same_sectors);
 
-static int sbc_emulate_verify(struct se_cmd *cmd)
+static sense_reason_t
+sbc_emulate_verify(struct se_cmd *cmd)
 {
 	target_complete_cmd(cmd, GOOD);
 	return 0;
@@ -313,13 +318,14 @@ out:
 	kfree(buf);
 }
 
-int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
+sense_reason_t
+sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 {
 	struct se_device *dev = cmd->se_dev;
 	unsigned char *cdb = cmd->t_task_cdb;
 	unsigned int size;
 	u32 sectors = 0;
-	int ret;
+	sense_reason_t ret;
 
 	switch (cdb[0]) {
 	case READ_6:
@@ -378,9 +384,9 @@ int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		cmd->execute_cmd = ops->execute_rw;
 		break;
 	case XDWRITEREAD_10:
-		if ((cmd->data_direction != DMA_TO_DEVICE) ||
+		if (cmd->data_direction != DMA_TO_DEVICE ||
 		    !(cmd->se_cmd_flags & SCF_BIDI))
-			goto out_invalid_cdb_field;
+			return TCM_INVALID_CDB_FIELD;
 		sectors = transport_get_sectors_10(cdb);
 
 		cmd->t_task_lba = transport_lba_32(cdb);
@@ -419,26 +425,26 @@ int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 			break;
 		case WRITE_SAME_32:
 			if (!ops->execute_write_same)
-				goto out_unsupported_cdb;
+				return TCM_UNSUPPORTED_SCSI_OPCODE;
 
 			sectors = transport_get_sectors_32(cdb);
 			if (!sectors) {
 				pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not"
 				       " supported\n");
-				goto out_invalid_cdb_field;
+				return TCM_INVALID_CDB_FIELD;
 			}
 
 			size = sbc_get_size(cmd, 1);
 			cmd->t_task_lba = get_unaligned_be64(&cdb[12]);
 
 			if (sbc_write_same_supported(dev, &cdb[10]) < 0)
-				goto out_unsupported_cdb;
+				return TCM_UNSUPPORTED_SCSI_OPCODE;
 			cmd->execute_cmd = ops->execute_write_same;
 			break;
 		default:
 			pr_err("VARIABLE_LENGTH_CMD service action"
 				" 0x%04x not supported\n", service_action);
-			goto out_unsupported_cdb;
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
 		}
 		break;
 	}
@@ -454,7 +460,7 @@ int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		default:
 			pr_err("Unsupported SA: 0x%02x\n",
 				cmd->t_task_cdb[1] & 0x1f);
-			goto out_invalid_cdb_field;
+			return TCM_INVALID_CDB_FIELD;
 		}
 		size = (cdb[10] << 24) | (cdb[11] << 16) |
 		       (cdb[12] << 8) | cdb[13];
@@ -462,7 +468,7 @@ int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 	case SYNCHRONIZE_CACHE:
 	case SYNCHRONIZE_CACHE_16:
 		if (!ops->execute_sync_cache)
-			goto out_unsupported_cdb;
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
 
 		/*
 		 * Extract LBA and range to be flushed for emulated SYNCHRONIZE_CACHE
@@ -483,42 +489,42 @@ int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		 */
 		if (cmd->t_task_lba || sectors) {
 			if (sbc_check_valid_sectors(cmd) < 0)
-				goto out_invalid_cdb_field;
+				return TCM_INVALID_CDB_FIELD;
 		}
 		cmd->execute_cmd = ops->execute_sync_cache;
 		break;
 	case UNMAP:
 		if (!ops->execute_unmap)
-			goto out_unsupported_cdb;
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
 
 		size = get_unaligned_be16(&cdb[7]);
 		cmd->execute_cmd = ops->execute_unmap;
 		break;
 	case WRITE_SAME_16:
 		if (!ops->execute_write_same)
-			goto out_unsupported_cdb;
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
 
 		sectors = transport_get_sectors_16(cdb);
 		if (!sectors) {
 			pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not supported\n");
-			goto out_invalid_cdb_field;
+			return TCM_INVALID_CDB_FIELD;
 		}
 
 		size = sbc_get_size(cmd, 1);
 		cmd->t_task_lba = get_unaligned_be64(&cdb[2]);
 
 		if (sbc_write_same_supported(dev, &cdb[1]) < 0)
-			goto out_unsupported_cdb;
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
 		cmd->execute_cmd = ops->execute_write_same;
 		break;
 	case WRITE_SAME:
 		if (!ops->execute_write_same)
-			goto out_unsupported_cdb;
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
 
 		sectors = transport_get_sectors_10(cdb);
 		if (!sectors) {
 			pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not supported\n");
-			goto out_invalid_cdb_field;
+			return TCM_INVALID_CDB_FIELD;
 		}
 
 		size = sbc_get_size(cmd, 1);
@@ -529,7 +535,7 @@ int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		 * of byte 1 bit 3 UNMAP instead of original reserved field
 		 */
 		if (sbc_write_same_supported(dev, &cdb[1]) < 0)
-			goto out_unsupported_cdb;
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
 		cmd->execute_cmd = ops->execute_write_same;
 		break;
 	case VERIFY:
@@ -556,7 +562,7 @@ int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 
 	/* reject any command that we don't have a handler for */
 	if (!(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) && !cmd->execute_cmd)
-		goto out_unsupported_cdb;
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
 
 	if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
 		unsigned long long end_lba;
@@ -566,14 +572,14 @@ int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 				" big sectors %u exceeds fabric_max_sectors:"
 				" %u\n", cdb[0], sectors,
 				dev->dev_attrib.fabric_max_sectors);
-			goto out_invalid_cdb_field;
+			return TCM_INVALID_CDB_FIELD;
 		}
 		if (sectors > dev->dev_attrib.hw_max_sectors) {
 			printk_ratelimited(KERN_ERR "SCSI OP %02xh with too"
 				" big sectors %u exceeds backend hw_max_sectors:"
 				" %u\n", cdb[0], sectors,
 				dev->dev_attrib.hw_max_sectors);
-			goto out_invalid_cdb_field;
+			return TCM_INVALID_CDB_FIELD;
 		}
 
 		end_lba = dev->transport->get_blocks(dev) + 1;
@@ -581,26 +587,13 @@ int sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 			pr_err("cmd exceeds last lba %llu "
 				"(lba %llu, sectors %u)\n",
 				end_lba, cmd->t_task_lba, sectors);
-			goto out_invalid_cdb_field;
+			return TCM_INVALID_CDB_FIELD;
 		}
 
 		size = sbc_get_size(cmd, sectors);
 	}
 
-	ret = target_cmd_size_check(cmd, size);
-	if (ret < 0)
-		return ret;
-
-	return 0;
-
-out_unsupported_cdb:
-	cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-	cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
-	return -EINVAL;
-out_invalid_cdb_field:
-	cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-	cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-	return -EINVAL;
+	return target_cmd_size_check(cmd, size);
 }
 EXPORT_SYMBOL(sbc_parse_cdb);
 
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index f9c2bd02043c..4b3c18305ec8 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -69,7 +69,8 @@ static void spc_fill_alua_data(struct se_port *port, unsigned char *buf)
 	spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
 }
 
-static int spc_emulate_inquiry_std(struct se_cmd *cmd, char *buf)
+static sense_reason_t
+spc_emulate_inquiry_std(struct se_cmd *cmd, char *buf)
 {
 	struct se_lun *lun = cmd->se_lun;
 	struct se_device *dev = cmd->se_dev;
@@ -108,7 +109,8 @@ static int spc_emulate_inquiry_std(struct se_cmd *cmd, char *buf)
 }
 
 /* unit serial number */
-static int spc_emulate_evpd_80(struct se_cmd *cmd, unsigned char *buf)
+static sense_reason_t
+spc_emulate_evpd_80(struct se_cmd *cmd, unsigned char *buf)
 {
 	struct se_device *dev = cmd->se_dev;
 	u16 len = 0;
@@ -161,7 +163,8 @@ static void spc_parse_naa_6h_vendor_specific(struct se_device *dev,
  * Device identification VPD, for a complete list of
  * DESIGNATOR TYPEs see spc4r17 Table 459.
  */
-static int spc_emulate_evpd_83(struct se_cmd *cmd, unsigned char *buf)
+static sense_reason_t
+spc_emulate_evpd_83(struct se_cmd *cmd, unsigned char *buf)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_lun *lun = cmd->se_lun;
@@ -406,7 +409,8 @@ check_scsi_name:
 }
 
 /* Extended INQUIRY Data VPD Page */
-static int spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf)
+static sense_reason_t
+spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf)
 {
 	buf[3] = 0x3c;
 	/* Set HEADSUP, ORDSUP, SIMPSUP */
@@ -419,7 +423,8 @@ static int spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf)
 }
 
 /* Block Limits VPD page */
-static int spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
+static sense_reason_t
+spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 {
 	struct se_device *dev = cmd->se_dev;
 	u32 max_sectors;
@@ -490,7 +495,8 @@ static int spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 }
 
 /* Block Device Characteristics VPD page */
-static int spc_emulate_evpd_b1(struct se_cmd *cmd, unsigned char *buf)
+static sense_reason_t
+spc_emulate_evpd_b1(struct se_cmd *cmd, unsigned char *buf)
 {
 	struct se_device *dev = cmd->se_dev;
 
@@ -502,7 +508,8 @@ static int spc_emulate_evpd_b1(struct se_cmd *cmd, unsigned char *buf)
 }
 
 /* Thin Provisioning VPD */
-static int spc_emulate_evpd_b2(struct se_cmd *cmd, unsigned char *buf)
+static sense_reason_t
+spc_emulate_evpd_b2(struct se_cmd *cmd, unsigned char *buf)
 {
 	struct se_device *dev = cmd->se_dev;
 
@@ -552,11 +559,12 @@ static int spc_emulate_evpd_b2(struct se_cmd *cmd, unsigned char *buf)
 	return 0;
 }
 
-static int spc_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf);
+static sense_reason_t
+spc_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf);
 
 static struct {
 	uint8_t		page;
-	int		(*emulate)(struct se_cmd *, unsigned char *);
+	sense_reason_t	(*emulate)(struct se_cmd *, unsigned char *);
 } evpd_handlers[] = {
 	{ .page = 0x00, .emulate = spc_emulate_evpd_00 },
 	{ .page = 0x80, .emulate = spc_emulate_evpd_80 },
@@ -568,7 +576,8 @@ static struct {
 };
 
 /* supported vital product data pages */
-static int spc_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf)
+static sense_reason_t
+spc_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf)
 {
 	int p;
 
@@ -586,14 +595,16 @@ static int spc_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf)
 	return 0;
 }
 
-static int spc_emulate_inquiry(struct se_cmd *cmd)
+static sense_reason_t
+spc_emulate_inquiry(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_portal_group *tpg = cmd->se_lun->lun_sep->sep_tpg;
 	unsigned char *rbuf;
 	unsigned char *cdb = cmd->t_task_cdb;
 	unsigned char buf[SE_INQUIRY_BUF];
-	int p, ret;
+	sense_reason_t ret;
+	int p;
 
 	memset(buf, 0, SE_INQUIRY_BUF);
 
@@ -606,8 +617,7 @@ static int spc_emulate_inquiry(struct se_cmd *cmd)
 		if (cdb[2]) {
 			pr_err("INQUIRY with EVPD==0 but PAGE CODE=%02x\n",
 			       cdb[2]);
-			cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-			ret = -EINVAL;
+			ret = TCM_INVALID_CDB_FIELD;
 			goto out;
 		}
 
@@ -624,15 +634,15 @@ static int spc_emulate_inquiry(struct se_cmd *cmd)
 	}
 
 	pr_err("Unknown VPD Code: 0x%02x\n", cdb[2]);
-	cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-	ret = -EINVAL;
+	ret = TCM_INVALID_CDB_FIELD;
 
 out:
 	rbuf = transport_kmap_data_sg(cmd);
-	if (rbuf) {
-		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
-		transport_kunmap_data_sg(cmd);
-	}
+	if (!rbuf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
+	memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+	transport_kunmap_data_sg(cmd);
 
 	if (!ret)
 		target_complete_cmd(cmd, GOOD);
@@ -834,7 +844,7 @@ static int spc_modesense_long_blockdesc(unsigned char *buf, u64 blocks, u32 bloc
 	return 17;
 }
 
-static int spc_emulate_modesense(struct se_cmd *cmd)
+static sense_reason_t spc_emulate_modesense(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	char *cdb = cmd->t_task_cdb;
@@ -851,7 +861,8 @@ static int spc_emulate_modesense(struct se_cmd *cmd)
 	int i;
 
 	map_buf = transport_kmap_data_sg(cmd);
-
+	if (!map_buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	/*
 	 * If SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC is not set, then we
 	 * know we actually allocated a full page.  Otherwise, if the
@@ -864,8 +875,7 @@ static int spc_emulate_modesense(struct se_cmd *cmd)
 		buf = kzalloc(SE_MODE_PAGE_BUF, GFP_KERNEL);
 		if (!buf) {
 			transport_kunmap_data_sg(cmd);
-			cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-			return -ENOMEM;
+			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		}
 	} else {
 		buf = map_buf;
@@ -920,9 +930,10 @@ static int spc_emulate_modesense(struct se_cmd *cmd)
 
 	if (page == 0x3f) {
 		if (subpage != 0x00 && subpage != 0xff) {
-			cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-			length = -EINVAL;
-			goto out;
+			pr_warn("MODE_SENSE: Invalid subpage code: 0x%02x\n", subpage);
+			kfree(buf);
+			transport_kunmap_data_sg(cmd);
+			return TCM_INVALID_CDB_FIELD;
 		}
 
 		for (i = 0; i < ARRAY_SIZE(modesense_handlers); ++i) {
@@ -958,8 +969,8 @@ static int spc_emulate_modesense(struct se_cmd *cmd)
 		pr_err("MODE SENSE: unimplemented page/subpage: 0x%02x/0x%02x\n",
 		       page, subpage);
 
-	cmd->scsi_sense_reason = TCM_UNKNOWN_MODE_PAGE;
-	return -EINVAL;
+	transport_kunmap_data_sg(cmd);
+	return TCM_UNKNOWN_MODE_PAGE;
 
 set_length:
 	if (ten)
@@ -967,7 +978,6 @@ set_length:
 	else
 		buf[0] = length - 1;
 
-out:
 	if (buf != map_buf) {
 		memcpy(map_buf, buf, cmd->data_length);
 		kfree(buf);
@@ -978,7 +988,7 @@ out:
 	return 0;
 }
 
-static int spc_emulate_modeselect(struct se_cmd *cmd)
+static sense_reason_t spc_emulate_modeselect(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 	char *cdb = cmd->t_task_cdb;
@@ -993,10 +1003,11 @@ static int spc_emulate_modeselect(struct se_cmd *cmd)
 	int i;
 
 	buf = transport_kmap_data_sg(cmd);
+	if (!buf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	if (!pf) {
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		ret = -EINVAL;
+		ret = TCM_INVALID_CDB_FIELD;
 		goto out;
 	}
 
@@ -1011,15 +1022,12 @@ static int spc_emulate_modeselect(struct se_cmd *cmd)
 			goto check_contents;
 		}
 
-	cmd->scsi_sense_reason = TCM_UNKNOWN_MODE_PAGE;
-	ret = -EINVAL;
+	ret = TCM_UNKNOWN_MODE_PAGE;
 	goto out;
 
 check_contents:
-	if (memcmp(buf + off, tbuf, length)) {
-		cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
-		ret = -EINVAL;
-	}
+	if (memcmp(buf + off, tbuf, length))
+		ret = TCM_INVALID_PARAMETER_LIST;
 
 out:
 	transport_kunmap_data_sg(cmd);
@@ -1029,7 +1037,7 @@ out:
 	return ret;
 }
 
-static int spc_emulate_request_sense(struct se_cmd *cmd)
+static sense_reason_t spc_emulate_request_sense(struct se_cmd *cmd)
 {
 	unsigned char *cdb = cmd->t_task_cdb;
 	unsigned char *rbuf;
@@ -1041,19 +1049,14 @@ static int spc_emulate_request_sense(struct se_cmd *cmd)
 	if (cdb[1] & 0x01) {
 		pr_err("REQUEST_SENSE description emulation not"
 			" supported\n");
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -ENOSYS;
+		return TCM_INVALID_CDB_FIELD;
 	}
 
 	rbuf = transport_kmap_data_sg(cmd);
-	if (cmd->scsi_sense_reason != 0) {
-		/*
-		 * Out of memory.  We will fail with CHECK CONDITION, so
-		 * we must not clear the unit attention condition.
-		 */
-		target_complete_cmd(cmd, CHECK_CONDITION);
-		return 0;
-	} else if (!core_scsi3_ua_clear_for_request_sense(cmd, &ua_asc, &ua_ascq)) {
+	if (!rbuf)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
+	if (!core_scsi3_ua_clear_for_request_sense(cmd, &ua_asc, &ua_ascq)) {
 		/*
 		 * CURRENT ERROR, UNIT ATTENTION
 		 */
@@ -1080,16 +1083,14 @@ static int spc_emulate_request_sense(struct se_cmd *cmd)
 		buf[7] = 0x0A;
 	}
 
-	if (rbuf) {
-		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
-		transport_kunmap_data_sg(cmd);
-	}
+	memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+	transport_kunmap_data_sg(cmd);
 
 	target_complete_cmd(cmd, GOOD);
 	return 0;
 }
 
-int spc_emulate_report_luns(struct se_cmd *cmd)
+sense_reason_t spc_emulate_report_luns(struct se_cmd *cmd)
 {
 	struct se_dev_entry *deve;
 	struct se_session *sess = cmd->se_sess;
@@ -1099,13 +1100,12 @@ int spc_emulate_report_luns(struct se_cmd *cmd)
 	if (cmd->data_length < 16) {
 		pr_warn("REPORT LUNS allocation length %u too small\n",
 			cmd->data_length);
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
+		return TCM_INVALID_CDB_FIELD;
 	}
 
 	buf = transport_kmap_data_sg(cmd);
 	if (!buf)
-		return -ENOMEM;
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	/*
 	 * If no struct se_session pointer is present, this struct se_cmd is
@@ -1153,13 +1153,15 @@ done:
 }
 EXPORT_SYMBOL(spc_emulate_report_luns);
 
-static int spc_emulate_testunitready(struct se_cmd *cmd)
+static sense_reason_t
+spc_emulate_testunitready(struct se_cmd *cmd)
 {
 	target_complete_cmd(cmd, GOOD);
 	return 0;
 }
 
-int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
+sense_reason_t
+spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 {
 	struct se_device *dev = cmd->se_dev;
 	unsigned char *cdb = cmd->t_task_cdb;
@@ -1300,9 +1302,7 @@ int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		pr_warn("TARGET_CORE[%s]: Unsupported SCSI Opcode"
 			" 0x%02x, sending CHECK_CONDITION.\n",
 			cmd->se_tfo->get_fabric_name(), cdb[0]);
-		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
-		return -EINVAL;
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
 	}
 
 	return 0;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index c4c931b525d2..98044bf1da08 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -557,7 +557,8 @@ static void target_complete_failure_work(struct work_struct *work)
 {
 	struct se_cmd *cmd = container_of(work, struct se_cmd, work);
 
-	transport_generic_request_failure(cmd);
+	transport_generic_request_failure(cmd,
+			TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE);
 }
 
 /*
@@ -625,7 +626,6 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 		complete(&cmd->t_transport_stop_comp);
 		return;
 	} else if (cmd->transport_state & CMD_T_FAILED) {
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		INIT_WORK(&cmd->work, target_complete_failure_work);
 	} else {
 		INIT_WORK(&cmd->work, target_complete_ok_work);
@@ -976,7 +976,8 @@ transport_set_vpd_ident(struct t10_vpd *vpd, unsigned char *page_83)
 }
 EXPORT_SYMBOL(transport_set_vpd_ident);
 
-int target_cmd_size_check(struct se_cmd *cmd, unsigned int size)
+sense_reason_t
+target_cmd_size_check(struct se_cmd *cmd, unsigned int size)
 {
 	struct se_device *dev = cmd->se_dev;
 
@@ -991,7 +992,7 @@ int target_cmd_size_check(struct se_cmd *cmd, unsigned int size)
 		if (cmd->data_direction == DMA_TO_DEVICE) {
 			pr_err("Rejecting underflow/overflow"
 					" WRITE data\n");
-			goto out_invalid_cdb_field;
+			return TCM_INVALID_CDB_FIELD;
 		}
 		/*
 		 * Reject READ_* or WRITE_* with overflow/underflow for
@@ -1002,7 +1003,7 @@ int target_cmd_size_check(struct se_cmd *cmd, unsigned int size)
 				" CDB on non 512-byte sector setup subsystem"
 				" plugin: %s\n", dev->transport->name);
 			/* Returns CHECK_CONDITION + INVALID_CDB_FIELD */
-			goto out_invalid_cdb_field;
+			return TCM_INVALID_CDB_FIELD;
 		}
 		/*
 		 * For the overflow case keep the existing fabric provided
@@ -1022,10 +1023,6 @@ int target_cmd_size_check(struct se_cmd *cmd, unsigned int size)
 
 	return 0;
 
-out_invalid_cdb_field:
-	cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-	cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-	return -EINVAL;
 }
 
 /*
@@ -1065,7 +1062,8 @@ void transport_init_se_cmd(
 }
 EXPORT_SYMBOL(transport_init_se_cmd);
 
-static int transport_check_alloc_task_attr(struct se_cmd *cmd)
+static sense_reason_t
+transport_check_alloc_task_attr(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
 
@@ -1079,7 +1077,7 @@ static int transport_check_alloc_task_attr(struct se_cmd *cmd)
 	if (cmd->sam_task_attr == MSG_ACA_TAG) {
 		pr_debug("SAM Task Attribute ACA"
 			" emulation is not supported\n");
-		return -EINVAL;
+		return TCM_INVALID_CDB_FIELD;
 	}
 	/*
 	 * Used to determine when ORDERED commands should go from
@@ -1093,17 +1091,12 @@ static int transport_check_alloc_task_attr(struct se_cmd *cmd)
 	return 0;
 }
 
-/*	target_setup_cmd_from_cdb():
- *
- *	Called from fabric RX Thread.
- */
-int target_setup_cmd_from_cdb(
-	struct se_cmd *cmd,
-	unsigned char *cdb)
+sense_reason_t
+target_setup_cmd_from_cdb(struct se_cmd *cmd, unsigned char *cdb)
 {
 	struct se_device *dev = cmd->se_dev;
 	unsigned long flags;
-	int ret;
+	sense_reason_t ret;
 
 	/*
 	 * Ensure that the received CDB is less than the max (252 + 8) bytes
@@ -1113,9 +1106,7 @@ int target_setup_cmd_from_cdb(
 		pr_err("Received SCSI CDB with command_size: %d that"
 			" exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n",
 			scsi_command_size(cdb), SCSI_MAX_VARLEN_CDB_SIZE);
-		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
+		return TCM_INVALID_CDB_FIELD;
 	}
 	/*
 	 * If the received CDB is larger than TCM_MAX_COMMAND_SIZE,
@@ -1130,10 +1121,7 @@ int target_setup_cmd_from_cdb(
 				" %u > sizeof(cmd->__t_task_cdb): %lu ops\n",
 				scsi_command_size(cdb),
 				(unsigned long)sizeof(cmd->__t_task_cdb));
-			cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-			cmd->scsi_sense_reason =
-					TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-			return -ENOMEM;
+			return TCM_OUT_OF_RESOURCES;
 		}
 	} else
 		cmd->t_task_cdb = &cmd->__t_task_cdb[0];
@@ -1145,50 +1133,30 @@ int target_setup_cmd_from_cdb(
 	/*
 	 * Check for an existing UNIT ATTENTION condition
 	 */
-	if (core_scsi3_ua_check(cmd, cdb) < 0) {
-		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		cmd->scsi_sense_reason = TCM_CHECK_CONDITION_UNIT_ATTENTION;
-		return -EINVAL;
-	}
+	ret = target_scsi3_ua_check(cmd);
+	if (ret)
+		return ret;
 
 	ret = target_alua_state_check(cmd);
-	if (ret) {
-		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		if (ret > 0)
-			cmd->scsi_sense_reason = TCM_CHECK_CONDITION_NOT_READY;
-		else
-			cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
-	}
+	if (ret)
+		return ret;
 
-	/*
-	 * Check status for SPC-3 Persistent Reservations
-	 */
 	ret = target_check_reservation(cmd);
-	if (ret) {
-		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		cmd->se_cmd_flags |= SCF_SCSI_RESERVATION_CONFLICT;
-		cmd->scsi_status = SAM_STAT_RESERVATION_CONFLICT;
-		cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT;
+	if (ret)
 		return ret;
-	}
 
 	ret = dev->transport->parse_cdb(cmd);
-	if (ret < 0)
+	if (ret)
+		return ret;
+
+	ret = transport_check_alloc_task_attr(cmd);
+	if (ret)
 		return ret;
 
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
 	cmd->se_cmd_flags |= SCF_SUPPORTED_SAM_OPCODE;
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-	/*
-	 * Check for SAM Task Attribute Emulation
-	 */
-	if (transport_check_alloc_task_attr(cmd) < 0) {
-		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
-	}
 	spin_lock(&cmd->se_lun->lun_sep_lock);
 	if (cmd->se_lun->lun_sep)
 		cmd->se_lun->lun_sep->sep_stats.cmd_pdus++;
@@ -1204,7 +1172,7 @@ EXPORT_SYMBOL(target_setup_cmd_from_cdb);
 int transport_handle_cdb_direct(
 	struct se_cmd *cmd)
 {
-	int ret;
+	sense_reason_t ret;
 
 	if (!cmd->se_lun) {
 		dump_stack();
@@ -1234,13 +1202,41 @@ int transport_handle_cdb_direct(
 	 * and call transport_generic_request_failure() if necessary..
 	 */
 	ret = transport_generic_new_cmd(cmd);
-	if (ret < 0)
-		transport_generic_request_failure(cmd);
-
+	if (ret)
+		transport_generic_request_failure(cmd, ret);
 	return 0;
 }
 EXPORT_SYMBOL(transport_handle_cdb_direct);
 
+static sense_reason_t
+transport_generic_map_mem_to_cmd(struct se_cmd *cmd, struct scatterlist *sgl,
+		u32 sgl_count, struct scatterlist *sgl_bidi, u32 sgl_bidi_count)
+{
+	if (!sgl || !sgl_count)
+		return 0;
+
+	/*
+	 * Reject SCSI data overflow with map_mem_to_cmd() as incoming
+	 * scatterlists already have been set to follow what the fabric
+	 * passes for the original expected data transfer length.
+	 */
+	if (cmd->se_cmd_flags & SCF_OVERFLOW_BIT) {
+		pr_warn("Rejecting SCSI DATA overflow for fabric using"
+			" SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC\n");
+		return TCM_INVALID_CDB_FIELD;
+	}
+
+	cmd->t_data_sg = sgl;
+	cmd->t_data_nents = sgl_count;
+
+	if (sgl_bidi && sgl_bidi_count) {
+		cmd->t_bidi_data_sg = sgl_bidi;
+		cmd->t_bidi_data_nents = sgl_bidi_count;
+	}
+	cmd->se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
+	return 0;
+}
+
 /*
  * target_submit_cmd_map_sgls - lookup unpacked lun and submit uninitialized
  * 			 se_cmd + use pre-allocated SGL memory.
@@ -1273,7 +1269,8 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess
 		struct scatterlist *sgl_bidi, u32 sgl_bidi_count)
 {
 	struct se_portal_group *se_tpg;
-	int rc;
+	sense_reason_t rc;
+	int ret;
 
 	se_tpg = se_sess->se_tpg;
 	BUG_ON(!se_tpg);
@@ -1294,9 +1291,9 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess
 	 * for fabrics using TARGET_SCF_ACK_KREF that expect a second
 	 * kref_put() to happen during fabric packet acknowledgement.
 	 */
-	rc = target_get_sess_cmd(se_sess, se_cmd, (flags & TARGET_SCF_ACK_KREF));
-	if (rc)
-		return rc;
+	ret = target_get_sess_cmd(se_sess, se_cmd, (flags & TARGET_SCF_ACK_KREF));
+	if (ret)
+		return ret;
 	/*
 	 * Signal bidirectional data payloads to target-core
 	 */
@@ -1305,16 +1302,16 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess
 	/*
 	 * Locate se_lun pointer and attach it to struct se_cmd
 	 */
-	if (transport_lookup_cmd_lun(se_cmd, unpacked_lun) < 0) {
-		transport_send_check_condition_and_sense(se_cmd,
-				se_cmd->scsi_sense_reason, 0);
+	rc = transport_lookup_cmd_lun(se_cmd, unpacked_lun);
+	if (rc) {
+		transport_send_check_condition_and_sense(se_cmd, rc, 0);
 		target_put_sess_cmd(se_sess, se_cmd);
 		return 0;
 	}
 
 	rc = target_setup_cmd_from_cdb(se_cmd, cdb);
 	if (rc != 0) {
-		transport_generic_request_failure(se_cmd);
+		transport_generic_request_failure(se_cmd, rc);
 		return 0;
 	}
 	/*
@@ -1349,7 +1346,7 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess
 		rc = transport_generic_map_mem_to_cmd(se_cmd, sgl, sgl_count,
 				sgl_bidi, sgl_bidi_count);
 		if (rc != 0) {
-			transport_generic_request_failure(se_cmd);
+			transport_generic_request_failure(se_cmd, rc);
 			return 0;
 		}
 	}
@@ -1495,16 +1492,17 @@ bool target_stop_cmd(struct se_cmd *cmd, unsigned long *flags)
 /*
  * Handle SAM-esque emulation for generic transport request failures.
  */
-void transport_generic_request_failure(struct se_cmd *cmd)
+void transport_generic_request_failure(struct se_cmd *cmd,
+		sense_reason_t sense_reason)
 {
 	int ret = 0;
 
 	pr_debug("-----[ Storage Engine Exception for cmd: %p ITT: 0x%08x"
 		" CDB: 0x%02x\n", cmd, cmd->se_tfo->get_task_tag(cmd),
 		cmd->t_task_cdb[0]);
-	pr_debug("-----[ i_state: %d t_state: %d scsi_sense_reason: %d\n",
+	pr_debug("-----[ i_state: %d t_state: %d sense_reason: %d\n",
 		cmd->se_tfo->get_cmd_state(cmd),
-		cmd->t_state, cmd->scsi_sense_reason);
+		cmd->t_state, sense_reason);
 	pr_debug("-----[ CMD_T_ACTIVE: %d CMD_T_STOP: %d CMD_T_SENT: %d\n",
 		(cmd->transport_state & CMD_T_ACTIVE) != 0,
 		(cmd->transport_state & CMD_T_STOP) != 0,
@@ -1515,7 +1513,7 @@ void transport_generic_request_failure(struct se_cmd *cmd)
 	 */
 	transport_complete_task_attr(cmd);
 
-	switch (cmd->scsi_sense_reason) {
+	switch (sense_reason) {
 	case TCM_NON_EXISTENT_LUN:
 	case TCM_UNSUPPORTED_SCSI_OPCODE:
 	case TCM_INVALID_CDB_FIELD:
@@ -1528,6 +1526,9 @@ void transport_generic_request_failure(struct se_cmd *cmd)
 	case TCM_CHECK_CONDITION_UNIT_ATTENTION:
 	case TCM_CHECK_CONDITION_NOT_READY:
 		break;
+	case TCM_OUT_OF_RESOURCES:
+		sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		break;
 	case TCM_RESERVATION_CONFLICT:
 		/*
 		 * No SENSE Data payload for this case, set SCSI Status
@@ -1555,13 +1556,12 @@ void transport_generic_request_failure(struct se_cmd *cmd)
 		goto check_stop;
 	default:
 		pr_err("Unknown transport error for CDB 0x%02x: %d\n",
-			cmd->t_task_cdb[0], cmd->scsi_sense_reason);
-		cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
+			cmd->t_task_cdb[0], sense_reason);
+		sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE;
 		break;
 	}
 
-	ret = transport_send_check_condition_and_sense(cmd,
-			cmd->scsi_sense_reason, 0);
+	ret = transport_send_check_condition_and_sense(cmd, sense_reason, 0);
 	if (ret == -EAGAIN || ret == -ENOMEM)
 		goto queue_full;
 
@@ -1579,21 +1579,21 @@ EXPORT_SYMBOL(transport_generic_request_failure);
 
 static void __target_execute_cmd(struct se_cmd *cmd)
 {
-	int error = 0;
+	sense_reason_t ret;
 
 	spin_lock_irq(&cmd->t_state_lock);
 	cmd->transport_state |= (CMD_T_BUSY|CMD_T_SENT);
 	spin_unlock_irq(&cmd->t_state_lock);
 
-	if (cmd->execute_cmd)
-		error = cmd->execute_cmd(cmd);
-
-	if (error) {
-		spin_lock_irq(&cmd->t_state_lock);
-		cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT);
-		spin_unlock_irq(&cmd->t_state_lock);
+	if (cmd->execute_cmd) {
+		ret = cmd->execute_cmd(cmd);
+		if (ret) {
+			spin_lock_irq(&cmd->t_state_lock);
+			cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT);
+			spin_unlock_irq(&cmd->t_state_lock);
 
-		transport_generic_request_failure(cmd);
+			transport_generic_request_failure(cmd, ret);
+		}
 	}
 }
 
@@ -1987,53 +1987,6 @@ out_busy:
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 }
 
-/*
- * transport_generic_map_mem_to_cmd - Use fabric-alloced pages instead of
- * allocating in the core.
- * @cmd:  Associated se_cmd descriptor
- * @mem:  SGL style memory for TCM WRITE / READ
- * @sg_mem_num: Number of SGL elements
- * @mem_bidi_in: SGL style memory for TCM BIDI READ
- * @sg_mem_bidi_num: Number of BIDI READ SGL elements
- *
- * Return: nonzero return cmd was rejected for -ENOMEM or inproper usage
- * of parameters.
- */
-int transport_generic_map_mem_to_cmd(
-	struct se_cmd *cmd,
-	struct scatterlist *sgl,
-	u32 sgl_count,
-	struct scatterlist *sgl_bidi,
-	u32 sgl_bidi_count)
-{
-	if (!sgl || !sgl_count)
-		return 0;
-
-	/*
-	 * Reject SCSI data overflow with map_mem_to_cmd() as incoming
-	 * scatterlists already have been set to follow what the fabric
-	 * passes for the original expected data transfer length.
-	 */
-	if (cmd->se_cmd_flags & SCF_OVERFLOW_BIT) {
-		pr_warn("Rejecting SCSI DATA overflow for fabric using"
-			" SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC\n");
-		cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-		cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD;
-		return -EINVAL;
-	}
-
-	cmd->t_data_sg = sgl;
-	cmd->t_data_nents = sgl_count;
-
-	if (sgl_bidi && sgl_bidi_count) {
-		cmd->t_bidi_data_sg = sgl_bidi;
-		cmd->t_bidi_data_nents = sgl_bidi_count;
-	}
-	cmd->se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
-	return 0;
-}
-EXPORT_SYMBOL(transport_generic_map_mem_to_cmd);
-
 void *transport_kmap_data_sg(struct se_cmd *cmd)
 {
 	struct scatterlist *sg = cmd->t_data_sg;
@@ -2054,10 +2007,8 @@ void *transport_kmap_data_sg(struct se_cmd *cmd)
 
 	/* >1 page. use vmap */
 	pages = kmalloc(sizeof(*pages) * cmd->t_data_nents, GFP_KERNEL);
-	if (!pages) {
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	if (!pages)
 		return NULL;
-	}
 
 	/* convert sg[] to pages[] */
 	for_each_sg(cmd->t_data_sg, sg, cmd->t_data_nents, i) {
@@ -2066,10 +2017,8 @@ void *transport_kmap_data_sg(struct se_cmd *cmd)
 
 	cmd->t_data_vmap = vmap(pages, cmd->t_data_nents,  VM_MAP, PAGE_KERNEL);
 	kfree(pages);
-	if (!cmd->t_data_vmap) {
-		cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	if (!cmd->t_data_vmap)
 		return NULL;
-	}
 
 	return cmd->t_data_vmap + cmd->t_data_sg[0].offset;
 }
@@ -2135,7 +2084,8 @@ out:
  * might not have the payload yet, so notify the fabric via a call to
  * ->write_pending instead. Otherwise place it on the execution queue.
  */
-int transport_generic_new_cmd(struct se_cmd *cmd)
+sense_reason_t
+transport_generic_new_cmd(struct se_cmd *cmd)
 {
 	int ret = 0;
 
@@ -2148,7 +2098,7 @@ int transport_generic_new_cmd(struct se_cmd *cmd)
 	    cmd->data_length) {
 		ret = transport_generic_get_mem(cmd);
 		if (ret < 0)
-			goto out_fail;
+			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 
 	atomic_inc(&cmd->t_fe_count);
@@ -2174,14 +2124,11 @@ int transport_generic_new_cmd(struct se_cmd *cmd)
 	if (ret == -EAGAIN || ret == -ENOMEM)
 		goto queue_full;
 
-	if (ret < 0)
-		return ret;
-	return 1;
+	/* fabric drivers should only return -EAGAIN or -ENOMEM as error */
+	WARN_ON(ret);
+
+	return 0;
 
-out_fail:
-	cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION;
-	cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-	return -EINVAL;
 queue_full:
 	pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n", cmd);
 	cmd->t_state = TRANSPORT_COMPLETE_QF_WP;
@@ -2625,10 +2572,9 @@ static int transport_get_sense_codes(
 	return 0;
 }
 
-int transport_send_check_condition_and_sense(
-	struct se_cmd *cmd,
-	u8 reason,
-	int from_transport)
+int
+transport_send_check_condition_and_sense(struct se_cmd *cmd,
+		sense_reason_t reason, int from_transport)
 {
 	unsigned char *buffer = cmd->sense_buffer;
 	unsigned long flags;
diff --git a/drivers/target/target_core_ua.c b/drivers/target/target_core_ua.c
index 59c95ee14749..60c8f41b9f1c 100644
--- a/drivers/target/target_core_ua.c
+++ b/drivers/target/target_core_ua.c
@@ -38,9 +38,8 @@
 #include "target_core_pr.h"
 #include "target_core_ua.h"
 
-int core_scsi3_ua_check(
-	struct se_cmd *cmd,
-	unsigned char *cdb)
+sense_reason_t
+target_scsi3_ua_check(struct se_cmd *cmd)
 {
 	struct se_dev_entry *deve;
 	struct se_session *sess = cmd->se_sess;
@@ -71,16 +70,14 @@ int core_scsi3_ua_check(
 	 *    was received, then the device server shall process the command
 	 *    and either:
 	 */
-	switch (cdb[0]) {
+	switch (cmd->t_task_cdb[0]) {
 	case INQUIRY:
 	case REPORT_LUNS:
 	case REQUEST_SENSE:
 		return 0;
 	default:
-		return -EINVAL;
+		return TCM_CHECK_CONDITION_UNIT_ATTENTION;
 	}
-
-	return -EINVAL;
 }
 
 int core_scsi3_ua_allocate(
diff --git a/drivers/target/target_core_ua.h b/drivers/target/target_core_ua.h
index 6e6b03460a1a..0204952fe4d3 100644
--- a/drivers/target/target_core_ua.h
+++ b/drivers/target/target_core_ua.h
@@ -26,7 +26,7 @@
 
 extern struct kmem_cache *se_ua_cache;
 
-extern int core_scsi3_ua_check(struct se_cmd *, unsigned char *);
+extern sense_reason_t target_scsi3_ua_check(struct se_cmd *);
 extern int core_scsi3_ua_allocate(struct se_node_acl *, u32, u8, u8);
 extern void core_scsi3_ua_release_all(struct se_dev_entry *);
 extern void core_scsi3_ua_for_check_condition(struct se_cmd *, u8 *, u8 *);
diff --git a/drivers/vhost/tcm_vhost.c b/drivers/vhost/tcm_vhost.c
index aa31692064dd..6a69bf55aea9 100644
--- a/drivers/vhost/tcm_vhost.c
+++ b/drivers/vhost/tcm_vhost.c
@@ -541,10 +541,6 @@ static void tcm_vhost_submission_work(struct work_struct *work)
 
 	if (tv_cmd->tvc_sgl_count) {
 		sg_ptr = tv_cmd->tvc_sgl;
-		/*
-		 * For BIDI commands, pass in the extra READ buffer
-		 * to transport_generic_map_mem_to_cmd() below..
-		 */
 /* FIXME: Fix BIDI operation in tcm_vhost_submission_work() */
 #if 0
 		if (se_cmd->se_cmd_flags & SCF_BIDI) {
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index e57f738f04f9..aa868090b9ab 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -31,17 +31,17 @@ struct se_subsystem_api {
 				   struct scatterlist *,
 				   unsigned char *);
 
-	int (*parse_cdb)(struct se_cmd *cmd);
+	sense_reason_t (*parse_cdb)(struct se_cmd *cmd);
 	u32 (*get_device_type)(struct se_device *);
 	sector_t (*get_blocks)(struct se_device *);
 	unsigned char *(*get_sense_buffer)(struct se_cmd *);
 };
 
 struct sbc_ops {
-	int (*execute_rw)(struct se_cmd *cmd);
-	int (*execute_sync_cache)(struct se_cmd *cmd);
-	int (*execute_write_same)(struct se_cmd *cmd);
-	int (*execute_unmap)(struct se_cmd *cmd);
+	sense_reason_t (*execute_rw)(struct se_cmd *cmd);
+	sense_reason_t (*execute_sync_cache)(struct se_cmd *cmd);
+	sense_reason_t (*execute_write_same)(struct se_cmd *cmd);
+	sense_reason_t (*execute_unmap)(struct se_cmd *cmd);
 };
 
 int	transport_subsystem_register(struct se_subsystem_api *);
@@ -49,11 +49,11 @@ void	transport_subsystem_release(struct se_subsystem_api *);
 
 void	target_complete_cmd(struct se_cmd *, u8);
 
-int	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
-int	spc_emulate_report_luns(struct se_cmd *cmd);
+sense_reason_t	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
+sense_reason_t	spc_emulate_report_luns(struct se_cmd *cmd);
 int	spc_get_write_same_sectors(struct se_cmd *cmd);
 
-int	sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops);
+sense_reason_t	sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops);
 u32	sbc_get_device_rev(struct se_device *dev);
 u32	sbc_get_device_type(struct se_device *dev);
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 11b0a68dc765..5350f6e580f0 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -144,8 +144,6 @@ enum se_cmd_flags_table {
 	SCF_EMULATED_TASK_SENSE		= 0x00000004,
 	SCF_SCSI_DATA_CDB		= 0x00000008,
 	SCF_SCSI_TMR_CDB		= 0x00000010,
-	SCF_SCSI_CDB_EXCEPTION		= 0x00000020,
-	SCF_SCSI_RESERVATION_CONFLICT	= 0x00000040,
 	SCF_FUA				= 0x00000080,
 	SCF_SE_LUN_CMD			= 0x00000100,
 	SCF_BIDI			= 0x00000400,
@@ -167,27 +165,32 @@ enum transport_lunflags_table {
 };
 
 /*
- * Used by transport_send_check_condition_and_sense() and se_cmd->scsi_sense_reason
+ * Used by transport_send_check_condition_and_sense()
  * to signal which ASC/ASCQ sense payload should be built.
  */
+typedef unsigned __bitwise__ sense_reason_t;
+
 enum tcm_sense_reason_table {
-	TCM_NON_EXISTENT_LUN			= 0x01,
-	TCM_UNSUPPORTED_SCSI_OPCODE		= 0x02,
-	TCM_INCORRECT_AMOUNT_OF_DATA		= 0x03,
-	TCM_UNEXPECTED_UNSOLICITED_DATA		= 0x04,
-	TCM_SERVICE_CRC_ERROR			= 0x05,
-	TCM_SNACK_REJECTED			= 0x06,
-	TCM_SECTOR_COUNT_TOO_MANY		= 0x07,
-	TCM_INVALID_CDB_FIELD			= 0x08,
-	TCM_INVALID_PARAMETER_LIST		= 0x09,
-	TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE	= 0x0a,
-	TCM_UNKNOWN_MODE_PAGE			= 0x0b,
-	TCM_WRITE_PROTECTED			= 0x0c,
-	TCM_CHECK_CONDITION_ABORT_CMD		= 0x0d,
-	TCM_CHECK_CONDITION_UNIT_ATTENTION	= 0x0e,
-	TCM_CHECK_CONDITION_NOT_READY		= 0x0f,
-	TCM_RESERVATION_CONFLICT		= 0x10,
-	TCM_ADDRESS_OUT_OF_RANGE		= 0x11,
+#define R(x)	(__force sense_reason_t )(x)
+	TCM_NON_EXISTENT_LUN			= R(0x01),
+	TCM_UNSUPPORTED_SCSI_OPCODE		= R(0x02),
+	TCM_INCORRECT_AMOUNT_OF_DATA		= R(0x03),
+	TCM_UNEXPECTED_UNSOLICITED_DATA		= R(0x04),
+	TCM_SERVICE_CRC_ERROR			= R(0x05),
+	TCM_SNACK_REJECTED			= R(0x06),
+	TCM_SECTOR_COUNT_TOO_MANY		= R(0x07),
+	TCM_INVALID_CDB_FIELD			= R(0x08),
+	TCM_INVALID_PARAMETER_LIST		= R(0x09),
+	TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE	= R(0x0a),
+	TCM_UNKNOWN_MODE_PAGE			= R(0x0b),
+	TCM_WRITE_PROTECTED			= R(0x0c),
+	TCM_CHECK_CONDITION_ABORT_CMD		= R(0x0d),
+	TCM_CHECK_CONDITION_UNIT_ATTENTION	= R(0x0e),
+	TCM_CHECK_CONDITION_NOT_READY		= R(0x0f),
+	TCM_RESERVATION_CONFLICT		= R(0x10),
+	TCM_ADDRESS_OUT_OF_RANGE		= R(0x11),
+	TCM_OUT_OF_RESOURCES			= R(0x12),
+#undef R
 };
 
 enum target_sc_flags_table {
@@ -407,7 +410,6 @@ struct se_cmd {
 	u8			scsi_status;
 	u8			scsi_asc;
 	u8			scsi_ascq;
-	u8			scsi_sense_reason;
 	u16			scsi_sense_length;
 	/* Delay for ALUA Active/NonOptimized state access in milliseconds */
 	int			alua_nonop_delay;
@@ -445,7 +447,7 @@ struct se_cmd {
 	struct completion	cmd_wait_comp;
 	struct kref		cmd_kref;
 	struct target_core_fabric_ops *se_tfo;
-	int (*execute_cmd)(struct se_cmd *);
+	sense_reason_t		(*execute_cmd)(struct se_cmd *);
 	void (*transport_complete_callback)(struct se_cmd *);
 
 	unsigned char		*t_task_cdb;
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 81ddb4ae6c3f..9087b200e552 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -98,8 +98,8 @@ void	transport_deregister_session(struct se_session *);
 
 void	transport_init_se_cmd(struct se_cmd *, struct target_core_fabric_ops *,
 		struct se_session *, u32, int, int, unsigned char *);
-int	transport_lookup_cmd_lun(struct se_cmd *, u32);
-int	target_setup_cmd_from_cdb(struct se_cmd *, unsigned char *);
+sense_reason_t transport_lookup_cmd_lun(struct se_cmd *, u32);
+sense_reason_t target_setup_cmd_from_cdb(struct se_cmd *, unsigned char *);
 int	target_submit_cmd_map_sgls(struct se_cmd *, struct se_session *,
 		unsigned char *, unsigned char *, u32, u32, int, int, int,
 		struct scatterlist *, u32, struct scatterlist *, u32);
@@ -110,9 +110,7 @@ int	target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess,
 		void *fabric_tmr_ptr, unsigned char tm_type,
 		gfp_t, unsigned int, int);
 int	transport_handle_cdb_direct(struct se_cmd *);
-int	transport_generic_map_mem_to_cmd(struct se_cmd *cmd,
-		struct scatterlist *, u32, struct scatterlist *, u32);
-int	transport_generic_new_cmd(struct se_cmd *);
+sense_reason_t	transport_generic_new_cmd(struct se_cmd *);
 
 void	target_execute_cmd(struct se_cmd *cmd);
 
@@ -120,7 +118,8 @@ void	transport_generic_free_cmd(struct se_cmd *, int);
 
 bool	transport_wait_for_tasks(struct se_cmd *);
 int	transport_check_aborted_status(struct se_cmd *, int);
-int	transport_send_check_condition_and_sense(struct se_cmd *, u8, int);
+int	transport_send_check_condition_and_sense(struct se_cmd *,
+		sense_reason_t, int);
 
 int	target_put_sess_cmd(struct se_session *, struct se_cmd *);
 void	target_sess_cmd_list_set_waiting(struct se_session *);
@@ -131,7 +130,7 @@ int	core_alua_check_nonop_delay(struct se_cmd *);
 int	core_tmr_alloc_req(struct se_cmd *, void *, u8, gfp_t);
 void	core_tmr_release_req(struct se_tmr_req *);
 int	transport_generic_handle_tmr(struct se_cmd *);
-void	transport_generic_request_failure(struct se_cmd *);
+void	transport_generic_request_failure(struct se_cmd *, sense_reason_t);
 int	transport_lookup_tmr_lun(struct se_cmd *, u32);
 
 struct se_node_acl *core_tpg_check_initiator_node_acl(struct se_portal_group *,
-- 
cgit v1.2.3-55-g7522


From 0547fad2dd7ccaaf3c914ba49073fa37e4e241eb Mon Sep 17 00:00:00 2001
From: Ming Lei
Date: Tue, 6 Nov 2012 04:53:04 +0000
Subject: usbnet: introduce usbnet_{read|write}_cmd_nopm

This patch introduces the below two helpers to prepare for solving
the usbnet runtime PM problem, which may cause some network utilities
(ifconfig, ethtool,...) touch a suspended device.

	usbnet_read_cmd_nopm()
	usbnet_write_cmd_nopm()

The above two helpers should be called by usbnet resume/suspend
callback to avoid deadlock.

Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c   | 62 ++++++++++++++++++++++++++++++++++++++++++----
 include/linux/usb/usbnet.h |  4 +++
 2 files changed, 61 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 447d20d22b7c..0ac1ff3571cb 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1611,8 +1611,8 @@ void usbnet_device_suggests_idle(struct usbnet *dev)
 EXPORT_SYMBOL(usbnet_device_suggests_idle);
 
 /*-------------------------------------------------------------------------*/
-int usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
-		    u16 value, u16 index, void *data, u16 size)
+static int __usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
+			     u16 value, u16 index, void *data, u16 size)
 {
 	void *buf = NULL;
 	int err = -ENOMEM;
@@ -1636,10 +1636,10 @@ int usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 out:
 	return err;
 }
-EXPORT_SYMBOL_GPL(usbnet_read_cmd);
 
-int usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
-		     u16 value, u16 index, const void *data, u16 size)
+static int __usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
+			      u16 value, u16 index, const void *data,
+			      u16 size)
 {
 	void *buf = NULL;
 	int err = -ENOMEM;
@@ -1662,8 +1662,56 @@ int usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 out:
 	return err;
 }
+
+/*
+ * The function can't be called inside suspend/resume callback,
+ * otherwise deadlock will be caused.
+ */
+int usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
+		    u16 value, u16 index, void *data, u16 size)
+{
+	return __usbnet_read_cmd(dev, cmd, reqtype, value, index,
+				 data, size);
+}
+EXPORT_SYMBOL_GPL(usbnet_read_cmd);
+
+/*
+ * The function can't be called inside suspend/resume callback,
+ * otherwise deadlock will be caused.
+ */
+int usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
+		     u16 value, u16 index, const void *data, u16 size)
+{
+	return __usbnet_write_cmd(dev, cmd, reqtype, value, index,
+				  data, size);
+}
 EXPORT_SYMBOL_GPL(usbnet_write_cmd);
 
+/*
+ * The function can be called inside suspend/resume callback safely
+ * and should only be called by suspend/resume callback generally.
+ */
+int usbnet_read_cmd_nopm(struct usbnet *dev, u8 cmd, u8 reqtype,
+			  u16 value, u16 index, void *data, u16 size)
+{
+	return __usbnet_read_cmd(dev, cmd, reqtype, value, index,
+				 data, size);
+}
+EXPORT_SYMBOL_GPL(usbnet_read_cmd_nopm);
+
+/*
+ * The function can be called inside suspend/resume callback safely
+ * and should only be called by suspend/resume callback generally.
+ */
+int usbnet_write_cmd_nopm(struct usbnet *dev, u8 cmd, u8 reqtype,
+			  u16 value, u16 index, const void *data,
+			  u16 size)
+{
+	return __usbnet_write_cmd(dev, cmd, reqtype, value, index,
+				  data, size);
+}
+EXPORT_SYMBOL_GPL(usbnet_write_cmd_nopm);
+
 static void usbnet_async_cmd_cb(struct urb *urb)
 {
 	struct usb_ctrlrequest *req = (struct usb_ctrlrequest *)urb->context;
@@ -1677,6 +1725,10 @@ static void usbnet_async_cmd_cb(struct urb *urb)
 	usb_free_urb(urb);
 }
 
+/*
+ * The caller must make sure that device can't be put into suspend
+ * state until the control URB completes.
+ */
 int usbnet_write_cmd_async(struct usbnet *dev, u8 cmd, u8 reqtype,
 			   u16 value, u16 index, const void *data, u16 size)
 {
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 4410e4166c6c..9bbeabf66c54 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -167,6 +167,10 @@ extern int usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 		    u16 value, u16 index, void *data, u16 size);
 extern int usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 		    u16 value, u16 index, const void *data, u16 size);
+extern int usbnet_read_cmd_nopm(struct usbnet *dev, u8 cmd, u8 reqtype,
+		    u16 value, u16 index, void *data, u16 size);
+extern int usbnet_write_cmd_nopm(struct usbnet *dev, u8 cmd, u8 reqtype,
+		    u16 value, u16 index, const void *data, u16 size);
 extern int usbnet_write_cmd_async(struct usbnet *dev, u8 cmd, u8 reqtype,
 		    u16 value, u16 index, const void *data, u16 size);
 
-- 
cgit v1.2.3-55-g7522


From 642c92da36ae0bed3c31fdd408411ab95f4e326b Mon Sep 17 00:00:00 2001
From: Taku Izumi
Date: Tue, 30 Oct 2012 15:26:18 +0900
Subject: PCI: Don't pass pci_dev to pci_ext_cfg_avail()

pci_ext_cfg_avail() doesn't use the "struct pci_dev *" passed to
it, and there's no requirement that a host bridge even be represented
by a pci_dev.  This drops the pci_ext_cfg_avail() parameter.

[bhelgaas: changelog]
Signed-off-by: Taku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>---
 arch/x86/pci/common.c   | 2 +-
 drivers/acpi/pci_root.c | 2 +-
 drivers/pci/pci.c       | 5 ++---
 include/linux/pci.h     | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 720e973fc34a..52dbf1aeeb63 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -626,7 +626,7 @@ void pcibios_disable_device (struct pci_dev *dev)
 		pcibios_disable_irq(dev);
 }
 
-int pci_ext_cfg_avail(struct pci_dev *dev)
+int pci_ext_cfg_avail(void)
 {
 	if (raw_pci_ext_ops)
 		return 1;
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 66f3ae74d130..50f329d7ccff 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -564,7 +564,7 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 		acpi_pci_bridge_scan(child);
 
 	/* Indicate support for various _OSC capabilities. */
-	if (pci_ext_cfg_avail(root->bus->self))
+	if (pci_ext_cfg_avail())
 		flags |= OSC_EXT_PCI_CONFIG_SUPPORT;
 	if (pcie_aspm_support_enabled())
 		flags |= OSC_ACTIVE_STATE_PWR_SUPPORT |
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 54858838f098..01b68bfa2321 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3833,14 +3833,13 @@ static void __devinit pci_no_domains(void)
 }
 
 /**
- * pci_ext_cfg_enabled - can we access extended PCI config space?
- * @dev: The PCI device of the root bridge.
+ * pci_ext_cfg_avail - can we access extended PCI config space?
  *
  * Returns 1 if we can access PCI extended config space (offsets
  * greater than 0xff). This is the default implementation. Architecture
  * implementations can override this.
  */
-int __weak pci_ext_cfg_avail(struct pci_dev *dev)
+int __weak pci_ext_cfg_avail(void)
 {
 	return 1;
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 786094254d57..9253af697ca4 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1604,7 +1604,7 @@ static inline void pci_mmcfg_early_init(void) { }
 static inline void pci_mmcfg_late_init(void) { }
 #endif
 
-int pci_ext_cfg_avail(struct pci_dev *dev);
+int pci_ext_cfg_avail(void);
 
 void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar);
 
-- 
cgit v1.2.3-55-g7522


From 5920cd3a41f1aefc30e9ce86384fc2fe9f5fe0c0 Mon Sep 17 00:00:00 2001
From: Paul Chavent
Date: Tue, 6 Nov 2012 23:10:47 +0000
Subject: packet: tx_ring: allow the user to choose tx data offset

The tx data offset of packet mmap tx ring used to be :
(TPACKET2_HDRLEN - sizeof(struct sockaddr_ll))

The problem is that, with SOCK_RAW socket, the payload (14 bytes after
the beginning of the user data) is misaligned.

This patch allows to let the user gives an offset for it's tx data if
he desires.

Set sock option PACKET_TX_HAS_OFF to 1, then specify in each frame of
your tx ring tp_net for SOCK_DGRAM, or tp_mac for SOCK_RAW.

Signed-off-by: Paul Chavent <paul.chavent@onera.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/packet_mmap.txt | 13 +++++++++
 include/uapi/linux/if_packet.h           |  1 +
 net/packet/af_packet.c                   | 46 +++++++++++++++++++++++++++++++-
 net/packet/internal.h                    |  1 +
 4 files changed, 60 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 1c08a4b0981f..7cd879eba5dc 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -163,6 +163,19 @@ As capture, each frame contains two parts:
 
  A complete tutorial is available at: http://wiki.gnu-log.net/
 
+By default, the user should put data at :
+ frame base + TPACKET_HDRLEN - sizeof(struct sockaddr_ll)
+
+So, whatever you choose for the socket mode (SOCK_DGRAM or SOCK_RAW),
+the beginning of the user data will be at :
+ frame base + TPACKET_ALIGN(sizeof(struct tpacket_hdr))
+
+If you wish to put user data at a custom offset from the beginning of
+the frame (for payload alignment with SOCK_RAW mode for instance) you
+can set tp_net (with SOCK_DGRAM) or tp_mac (with SOCK_RAW). In order
+to make this work it must be enabled previously with setsockopt()
+and the PACKET_TX_HAS_OFF option.
+
 --------------------------------------------------------------------------------
 + PACKET_MMAP settings
 --------------------------------------------------------------------------------
diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index f3799295d231..f9a60375f0d0 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -50,6 +50,7 @@ struct sockaddr_ll {
 #define PACKET_TX_TIMESTAMP		16
 #define PACKET_TIMESTAMP		17
 #define PACKET_FANOUT			18
+#define PACKET_TX_HAS_OFF		19
 
 #define PACKET_FANOUT_HASH		0
 #define PACKET_FANOUT_LB		1
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9034f52659b5..f262dbfc7f06 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1881,7 +1881,35 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
-	data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll);
+	if (po->tp_tx_has_off) {
+		int off_min, off_max, off;
+		off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
+		off_max = po->tx_ring.frame_size - tp_len;
+		if (sock->type == SOCK_DGRAM) {
+			switch (po->tp_version) {
+			case TPACKET_V2:
+				off = ph.h2->tp_net;
+				break;
+			default:
+				off = ph.h1->tp_net;
+				break;
+			}
+		} else {
+			switch (po->tp_version) {
+			case TPACKET_V2:
+				off = ph.h2->tp_mac;
+				break;
+			default:
+				off = ph.h1->tp_mac;
+				break;
+			}
+		}
+		if (unlikely((off < off_min) || (off_max < off)))
+			return -EINVAL;
+		data = ph.raw + off;
+	} else {
+		data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll);
+	}
 	to_write = tp_len;
 
 	if (sock->type == SOCK_DGRAM) {
@@ -3109,6 +3137,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		return fanout_add(sk, val & 0xffff, val >> 16);
 	}
+	case PACKET_TX_HAS_OFF:
+	{
+		unsigned int val;
+
+		if (optlen != sizeof(val))
+			return -EINVAL;
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
+			return -EBUSY;
+		if (copy_from_user(&val, optval, sizeof(val)))
+			return -EFAULT;
+		po->tp_tx_has_off = !!val;
+		return 0;
+	}
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -3200,6 +3241,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 			((u32)po->fanout->type << 16)) :
 		       0);
 		break;
+	case PACKET_TX_HAS_OFF:
+		val = po->tp_tx_has_off;
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 44945f6b7252..e84cab8cb7a9 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -109,6 +109,7 @@ struct packet_sock {
 	unsigned int		tp_hdrlen;
 	unsigned int		tp_reserve;
 	unsigned int		tp_loss:1;
+	unsigned int		tp_tx_has_off:1;
 	unsigned int		tp_tstamp;
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
 };
-- 
cgit v1.2.3-55-g7522


From 216b6cbdcbd86b1db0754d58886b466ae31f5a63 Mon Sep 17 00:00:00 2001
From: Namjae Jeon
Date: Wed, 29 Aug 2012 10:10:10 -0400
Subject: exportfs: add FILEID_INVALID to indicate invalid fid_type

This commit adds FILEID_INVALID = 0xff in fid_type to
indicate invalid fid_type

It avoids using magic number 255

Signed-off-by: Namjae Jeon <linkinjeon@gmail.com>
Signed-off-by: Vivek Trivedi <vtrivedi018@gmail.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/exportfs/expfs.c      | 4 ++--
 fs/fhandle.c             | 2 +-
 fs/nfsd/nfsfh.c          | 4 ++--
 include/linux/exportfs.h | 5 +++++
 4 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 29ab099e3e08..f1f1c59c2966 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -322,10 +322,10 @@ static int export_encode_fh(struct inode *inode, struct fid *fid,
 
 	if (parent && (len < 4)) {
 		*max_len = 4;
-		return 255;
+		return FILEID_INVALID;
 	} else if (len < 2) {
 		*max_len = 2;
-		return 255;
+		return FILEID_INVALID;
 	}
 
 	len = 2;
diff --git a/fs/fhandle.c b/fs/fhandle.c
index f775bfdd6e4a..26f12b95702a 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -52,7 +52,7 @@ static long do_sys_name_to_handle(struct path *path,
 	handle_bytes = handle_dwords * sizeof(u32);
 	handle->handle_bytes = handle_bytes;
 	if ((handle->handle_bytes > f_handle.handle_bytes) ||
-	    (retval == 255) || (retval == -ENOSPC)) {
+	    (retval == FILEID_INVALID) || (retval == -ENOSPC)) {
 		/* As per old exportfs_encode_fh documentation
 		 * we could return ENOSPC to indicate overflow
 		 * But file system returned 255 always. So handle
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 032af381b3aa..814afaa4458a 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -572,7 +572,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 
 		if (inode)
 			_fh_update(fhp, exp, dentry);
-		if (fhp->fh_handle.fh_fileid_type == 255) {
+		if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
 			fh_put(fhp);
 			return nfserr_opnotsupp;
 		}
@@ -603,7 +603,7 @@ fh_update(struct svc_fh *fhp)
 			goto out;
 
 		_fh_update(fhp, fhp->fh_export, dentry);
-		if (fhp->fh_handle.fh_fileid_type == 255)
+		if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
 			return nfserr_opnotsupp;
 	}
 out:
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 12291a7ee275..0e1452546300 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -83,6 +83,11 @@ enum fid_type {
 	 * 64 bit parent inode number.
 	 */
 	FILEID_NILFS_WITH_PARENT = 0x62,
+
+	/*
+	 * Filesystems must not use 0xff file ID.
+	 */
+	FILEID_INVALID = 0xff,
 };
 
 struct fid {
-- 
cgit v1.2.3-55-g7522


From 9d626eccb1de90a310f3fb9bc5e8803706be1a95 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto
Date: Tue, 30 Oct 2012 20:06:55 -0700
Subject: sh: clkfwk: add sh_clk_fsidiv_register()

This patch adds sh_clk_fsidiv_register() to share FSI-DIV clock code

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 drivers/sh/clk/cpg.c   | 86 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/sh_clk.h |  9 ++++++
 2 files changed, 95 insertions(+)

(limited to 'include')

diff --git a/drivers/sh/clk/cpg.c b/drivers/sh/clk/cpg.c
index 07e9fb4f8041..b3dc44146ca0 100644
--- a/drivers/sh/clk/cpg.c
+++ b/drivers/sh/clk/cpg.c
@@ -361,3 +361,89 @@ int __init sh_clk_div4_reparent_register(struct clk *clks, int nr,
 	return sh_clk_div_register_ops(clks, nr, table,
 				       &sh_clk_div4_reparent_clk_ops);
 }
+
+/* FSI-DIV */
+static unsigned long fsidiv_recalc(struct clk *clk)
+{
+	u32 value;
+
+	value = __raw_readl(clk->mapping->base);
+
+	value >>= 16;
+	if (value < 2)
+		return clk->parent->rate;
+
+	return clk->parent->rate / value;
+}
+
+static long fsidiv_round_rate(struct clk *clk, unsigned long rate)
+{
+	return clk_rate_div_range_round(clk, 1, 0xffff, rate);
+}
+
+static void fsidiv_disable(struct clk *clk)
+{
+	__raw_writel(0, clk->mapping->base);
+}
+
+static int fsidiv_enable(struct clk *clk)
+{
+	u32 value;
+
+	value  = __raw_readl(clk->mapping->base) >> 16;
+	if (value < 2)
+		return 0;
+
+	__raw_writel((value << 16) | 0x3, clk->mapping->base);
+
+	return 0;
+}
+
+static int fsidiv_set_rate(struct clk *clk, unsigned long rate)
+{
+	u32 val;
+	int idx;
+
+	idx = (clk->parent->rate / rate) & 0xffff;
+	if (idx < 2)
+		__raw_writel(0, clk->mapping->base);
+	else
+		__raw_writel(idx << 16, clk->mapping->base);
+
+	return 0;
+}
+
+static struct sh_clk_ops fsidiv_clk_ops = {
+	.recalc		= fsidiv_recalc,
+	.round_rate	= fsidiv_round_rate,
+	.set_rate	= fsidiv_set_rate,
+	.enable		= fsidiv_enable,
+	.disable	= fsidiv_disable,
+};
+
+int __init sh_clk_fsidiv_register(struct clk *clks, int nr)
+{
+	struct clk_mapping *map;
+	int i;
+
+	for (i = 0; i < nr; i++) {
+
+		map = kzalloc(sizeof(struct clk_mapping), GFP_KERNEL);
+		if (!map) {
+			pr_err("%s: unable to alloc memory\n", __func__);
+			return -ENOMEM;
+		}
+
+		/* clks[i].enable_reg came from SH_CLK_FSIDIV() */
+		map->phys		= (phys_addr_t)clks[i].enable_reg;
+		map->len		= 8;
+
+		clks[i].enable_reg	= 0; /* remove .enable_reg */
+		clks[i].ops		= &fsidiv_clk_ops;
+		clks[i].mapping		= map;
+
+		clk_register(&clks[i]);
+	}
+
+	return 0;
+}
diff --git a/include/linux/sh_clk.h b/include/linux/sh_clk.h
index 50910913b268..60c72395ec6b 100644
--- a/include/linux/sh_clk.h
+++ b/include/linux/sh_clk.h
@@ -199,4 +199,13 @@ int sh_clk_div6_reparent_register(struct clk *clks, int nr);
 #define CLKDEV_DEV_ID(_id, _clk) { .dev_id = _id, .clk = _clk }
 #define CLKDEV_ICK_ID(_cid, _did, _clk) { .con_id = _cid, .dev_id = _did, .clk = _clk }
 
+/* .enable_reg will be updated to .mapping on sh_clk_fsidiv_register() */
+#define SH_CLK_FSIDIV(_reg, _parent)		\
+{						\
+	.enable_reg = (void __iomem *)_reg,	\
+	.parent		= _parent,		\
+}
+
+int sh_clk_fsidiv_register(struct clk *clks, int nr);
+
 #endif /* __SH_CLOCK_H */
-- 
cgit v1.2.3-55-g7522


From ada8a8a13b13a2749818524a7949935f68d2b3eb Mon Sep 17 00:00:00 2001
From: Wei WANG
Date: Mon, 29 Oct 2012 13:49:33 +0800
Subject: mfd: Add realtek pcie card reader driver

Realtek PCI-E card reader driver adapts requests from upper-level
sdmmc/memstick layer to the real physical card reader.

Signed-off-by: Wei WANG <wei_wang@realsil.com.cn>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/Kconfig             |    9 +
 drivers/mfd/Makefile            |    3 +
 drivers/mfd/rtl8411.c           |  251 ++++++++
 drivers/mfd/rts5209.c           |  223 +++++++
 drivers/mfd/rts5229.c           |  205 +++++++
 drivers/mfd/rtsx_pcr.c          | 1251 +++++++++++++++++++++++++++++++++++++++
 drivers/mfd/rtsx_pcr.h          |   32 +
 include/linux/mfd/rtsx_common.h |   48 ++
 include/linux/mfd/rtsx_pci.h    |  794 +++++++++++++++++++++++++
 9 files changed, 2816 insertions(+)
 create mode 100644 drivers/mfd/rtl8411.c
 create mode 100644 drivers/mfd/rts5209.c
 create mode 100644 drivers/mfd/rts5229.c
 create mode 100644 drivers/mfd/rtsx_pcr.c
 create mode 100644 drivers/mfd/rtsx_pcr.h
 create mode 100644 include/linux/mfd/rtsx_common.h
 create mode 100644 include/linux/mfd/rtsx_pci.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 9bba7f78ff36..d0cb4d4bc2cc 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -63,6 +63,15 @@ config MFD_SM501_GPIO
 	 lines on the SM501. The platform data is used to supply the
 	 base number for the first GPIO line to register.
 
+config MFD_RTSX_PCI
+	tristate "Support for Realtek PCI-E card reader"
+	depends on PCI
+	help
+	  This supports for Realtek PCI-Express card reader including rts5209,
+	  rts5229, rtl8411, etc. Realtek card reader supports access to many
+	  types of memory cards, such as Memory Stick, Memory Stick Pro,
+	  Secure Digital and MultiMediaCard.
+
 config MFD_ASIC3
 	bool "Support for Compaq ASIC3"
 	depends on GENERIC_HARDIRQS && GPIOLIB && ARM
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 442c17e40741..a4093a44304a 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -9,6 +9,9 @@ obj-$(CONFIG_MFD_88PM805)	+= 88pm805.o 88pm80x.o
 obj-$(CONFIG_MFD_SM501)		+= sm501.o
 obj-$(CONFIG_MFD_ASIC3)		+= asic3.o tmio_core.o
 
+rtsx_pci-objs			:= rtsx_pcr.o rts5209.o rts5229.o rtl8411.o
+obj-$(CONFIG_MFD_RTSX_PCI)	+= rtsx_pci.o
+
 obj-$(CONFIG_HTC_EGPIO)		+= htc-egpio.o
 obj-$(CONFIG_HTC_PASIC3)	+= htc-pasic3.o
 obj-$(CONFIG_HTC_I2CPLD)	+= htc-i2cpld.o
diff --git a/drivers/mfd/rtl8411.c b/drivers/mfd/rtl8411.c
new file mode 100644
index 000000000000..89f046ca9e41
--- /dev/null
+++ b/drivers/mfd/rtl8411.c
@@ -0,0 +1,251 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/mfd/rtsx_pci.h>
+
+#include "rtsx_pcr.h"
+
+static u8 rtl8411_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	rtsx_pci_read_register(pcr, SYS_VER, &val);
+	return val & 0x0F;
+}
+
+static int rtl8411_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CD_PAD_CTL,
+			CD_DISABLE_MASK | CD_AUTO_DISABLE, CD_ENABLE);
+}
+
+static int rtl8411_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_GPIO, 0x01, 0x00);
+}
+
+static int rtl8411_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_GPIO, 0x01, 0x01);
+}
+
+static int rtl8411_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_AUTO_BLINK, 0xFF, 0x0D);
+}
+
+static int rtl8411_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_AUTO_BLINK, 0x08, 0x00);
+}
+
+static int rtl8411_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	int err;
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			BPP_POWER_MASK, BPP_POWER_5_PERCENT_ON);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, LDO_CTL,
+			BPP_LDO_POWB, BPP_LDO_SUSPEND);
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	/* To avoid too large in-rush current */
+	udelay(150);
+
+	err = rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+			BPP_POWER_MASK, BPP_POWER_10_PERCENT_ON);
+	if (err < 0)
+		return err;
+
+	udelay(150);
+
+	err = rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+			BPP_POWER_MASK, BPP_POWER_15_PERCENT_ON);
+	if (err < 0)
+		return err;
+
+	udelay(150);
+
+	err = rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+			BPP_POWER_MASK, BPP_POWER_ON);
+	if (err < 0)
+		return err;
+
+	return rtsx_pci_write_register(pcr, LDO_CTL, BPP_LDO_POWB, BPP_LDO_ON);
+}
+
+static int rtl8411_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	int err;
+
+	err = rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+			BPP_POWER_MASK, BPP_POWER_OFF);
+	if (err < 0)
+		return err;
+
+	return rtsx_pci_write_register(pcr, LDO_CTL,
+			BPP_LDO_POWB, BPP_LDO_SUSPEND);
+}
+
+static unsigned int rtl8411_cd_deglitch(struct rtsx_pcr *pcr)
+{
+	unsigned int card_exist;
+
+	card_exist = rtsx_pci_readl(pcr, RTSX_BIPR);
+	card_exist &= CARD_EXIST;
+	if (!card_exist) {
+		/* Enable card CD */
+		rtsx_pci_write_register(pcr, CD_PAD_CTL,
+				CD_DISABLE_MASK, CD_ENABLE);
+		/* Enable card interrupt */
+		rtsx_pci_write_register(pcr, EFUSE_CONTENT, 0xe0, 0x00);
+		return 0;
+	}
+
+	if (hweight32(card_exist) > 1) {
+		rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+				BPP_POWER_MASK, BPP_POWER_5_PERCENT_ON);
+		msleep(100);
+
+		card_exist = rtsx_pci_readl(pcr, RTSX_BIPR);
+		if (card_exist & MS_EXIST)
+			card_exist = MS_EXIST;
+		else if (card_exist & SD_EXIST)
+			card_exist = SD_EXIST;
+		else
+			card_exist = 0;
+
+		rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+				BPP_POWER_MASK, BPP_POWER_OFF);
+
+		dev_dbg(&(pcr->pci->dev),
+				"After CD deglitch, card_exist = 0x%x\n",
+				card_exist);
+	}
+
+	if (card_exist & MS_EXIST) {
+		/* Disable SD interrupt */
+		rtsx_pci_write_register(pcr, EFUSE_CONTENT, 0xe0, 0x40);
+		rtsx_pci_write_register(pcr, CD_PAD_CTL,
+				CD_DISABLE_MASK, MS_CD_EN_ONLY);
+	} else if (card_exist & SD_EXIST) {
+		/* Disable MS interrupt */
+		rtsx_pci_write_register(pcr, EFUSE_CONTENT, 0xe0, 0x80);
+		rtsx_pci_write_register(pcr, CD_PAD_CTL,
+				CD_DISABLE_MASK, SD_CD_EN_ONLY);
+	}
+
+	return card_exist;
+}
+
+static const struct pcr_ops rtl8411_pcr_ops = {
+	.extra_init_hw = rtl8411_extra_init_hw,
+	.optimize_phy = NULL,
+	.turn_on_led = rtl8411_turn_on_led,
+	.turn_off_led = rtl8411_turn_off_led,
+	.enable_auto_blink = rtl8411_enable_auto_blink,
+	.disable_auto_blink = rtl8411_disable_auto_blink,
+	.card_power_on = rtl8411_card_power_on,
+	.card_power_off = rtl8411_card_power_off,
+	.cd_deglitch = rtl8411_cd_deglitch,
+};
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rtl8411_sd_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xA9),
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x09),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x09),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x04),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rtl8411_sd_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0x65),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0x95),
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x09),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x05),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x04),
+	0,
+};
+
+/* MS Pull Control Enable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rtl8411_ms_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0x65),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0x95),
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x05),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x05),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x04),
+	0,
+};
+
+/* MS Pull Control Disable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rtl8411_ms_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0x65),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0x95),
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x09),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x05),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x04),
+	0,
+};
+
+void rtl8411_init_params(struct rtsx_pcr *pcr)
+{
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104;
+	pcr->num_slots = 2;
+	pcr->ops = &rtl8411_pcr_ops;
+
+	pcr->ic_version = rtl8411_get_ic_version(pcr);
+	pcr->sd_pull_ctl_enable_tbl = rtl8411_sd_pull_ctl_enable_tbl;
+	pcr->sd_pull_ctl_disable_tbl = rtl8411_sd_pull_ctl_disable_tbl;
+	pcr->ms_pull_ctl_enable_tbl = rtl8411_ms_pull_ctl_enable_tbl;
+	pcr->ms_pull_ctl_disable_tbl = rtl8411_ms_pull_ctl_disable_tbl;
+}
diff --git a/drivers/mfd/rts5209.c b/drivers/mfd/rts5209.c
new file mode 100644
index 000000000000..283a4f148084
--- /dev/null
+++ b/drivers/mfd/rts5209.c
@@ -0,0 +1,223 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/mfd/rtsx_pci.h>
+
+#include "rtsx_pcr.h"
+
+static u8 rts5209_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	val = rtsx_pci_readb(pcr, 0x1C);
+	return val & 0x0F;
+}
+
+static void rts5209_init_vendor_cfg(struct rtsx_pcr *pcr)
+{
+	u32 val;
+
+	rtsx_pci_read_config_dword(pcr, 0x724, &val);
+	dev_dbg(&(pcr->pci->dev), "Cfg 0x724: 0x%x\n", val);
+
+	if (!(val & 0x80)) {
+		if (val & 0x08)
+			pcr->ms_pmos = false;
+		else
+			pcr->ms_pmos = true;
+	}
+}
+
+static int rts5209_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_init_cmd(pcr);
+
+	/* Turn off LED */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_GPIO, 0xFF, 0x03);
+	/* Configure GPIO as output */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_GPIO_DIR, 0xFF, 0x03);
+
+	return rtsx_pci_send_cmd(pcr, 100);
+}
+
+static int rts5209_optimize_phy(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_phy_register(pcr, 0x00, 0xB966);
+}
+
+static int rts5209_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_GPIO, 0x01, 0x00);
+}
+
+static int rts5209_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_GPIO, 0x01, 0x01);
+}
+
+static int rts5209_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_AUTO_BLINK, 0xFF, 0x0D);
+}
+
+static int rts5209_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_AUTO_BLINK, 0x08, 0x00);
+}
+
+static int rts5209_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	int err;
+	u8 pwr_mask, partial_pwr_on, pwr_on;
+
+	pwr_mask = SD_POWER_MASK;
+	partial_pwr_on = SD_PARTIAL_POWER_ON;
+	pwr_on = SD_POWER_ON;
+
+	if (pcr->ms_pmos && (card == RTSX_MS_CARD)) {
+		pwr_mask = MS_POWER_MASK;
+		partial_pwr_on = MS_PARTIAL_POWER_ON;
+		pwr_on = MS_POWER_ON;
+	}
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			pwr_mask, partial_pwr_on);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0x04);
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	/* To avoid too large in-rush current */
+	udelay(150);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL, pwr_mask, pwr_on);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0x00);
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int rts5209_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	u8 pwr_mask, pwr_off;
+
+	pwr_mask = SD_POWER_MASK;
+	pwr_off = SD_POWER_OFF;
+
+	if (pcr->ms_pmos && (card == RTSX_MS_CARD)) {
+		pwr_mask = MS_POWER_MASK;
+		pwr_off = MS_POWER_OFF;
+	}
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			pwr_mask | PMOS_STRG_MASK, pwr_off | PMOS_STRG_400mA);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0X06);
+	return rtsx_pci_send_cmd(pcr, 100);
+}
+
+static const struct pcr_ops rts5209_pcr_ops = {
+	.extra_init_hw = rts5209_extra_init_hw,
+	.optimize_phy = rts5209_optimize_phy,
+	.turn_on_led = rts5209_turn_on_led,
+	.turn_off_led = rts5209_turn_off_led,
+	.enable_auto_blink = rts5209_enable_auto_blink,
+	.disable_auto_blink = rts5209_disable_auto_blink,
+	.card_power_on = rts5209_card_power_on,
+	.card_power_off = rts5209_card_power_off,
+	.cd_deglitch = NULL,
+};
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5209_sd_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE9),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5209_sd_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD5),
+	0,
+};
+
+/* MS Pull Control Enable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rts5209_ms_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x15),
+	0,
+};
+
+/* MS Pull Control Disable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rts5209_ms_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x15),
+	0,
+};
+
+void rts5209_init_params(struct rtsx_pcr *pcr)
+{
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 |
+		EXTRA_CAPS_SD_SDR104 | EXTRA_CAPS_MMC_8BIT;
+	pcr->num_slots = 2;
+	pcr->ops = &rts5209_pcr_ops;
+
+	rts5209_init_vendor_cfg(pcr);
+
+	pcr->ic_version = rts5209_get_ic_version(pcr);
+	pcr->sd_pull_ctl_enable_tbl = rts5209_sd_pull_ctl_enable_tbl;
+	pcr->sd_pull_ctl_disable_tbl = rts5209_sd_pull_ctl_disable_tbl;
+	pcr->ms_pull_ctl_enable_tbl = rts5209_ms_pull_ctl_enable_tbl;
+	pcr->ms_pull_ctl_disable_tbl = rts5209_ms_pull_ctl_disable_tbl;
+}
diff --git a/drivers/mfd/rts5229.c b/drivers/mfd/rts5229.c
new file mode 100644
index 000000000000..b9dbab266fda
--- /dev/null
+++ b/drivers/mfd/rts5229.c
@@ -0,0 +1,205 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/mfd/rtsx_pci.h>
+
+#include "rtsx_pcr.h"
+
+static u8 rts5229_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	rtsx_pci_read_register(pcr, DUMMY_REG_RESET_0, &val);
+	return val & 0x0F;
+}
+
+static int rts5229_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_init_cmd(pcr);
+
+	/* Configure GPIO as output */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, GPIO_CTL, 0x02, 0x02);
+	/* Switch LDO3318 source from DV33 to card_3v3 */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, LDO_PWR_SEL, 0x03, 0x00);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, LDO_PWR_SEL, 0x03, 0x01);
+	/* LED shine disabled, set initial shine cycle period */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, OLT_LED_CTL, 0x0F, 0x02);
+
+	return rtsx_pci_send_cmd(pcr, 100);
+}
+
+static int rts5229_optimize_phy(struct rtsx_pcr *pcr)
+{
+	/* Optimize RX sensitivity */
+	return rtsx_pci_write_phy_register(pcr, 0x00, 0xBA42);
+}
+
+static int rts5229_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL, 0x02, 0x02);
+}
+
+static int rts5229_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL, 0x02, 0x00);
+}
+
+static int rts5229_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL, 0x08, 0x08);
+}
+
+static int rts5229_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL, 0x08, 0x00);
+}
+
+static int rts5229_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	int err;
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			SD_POWER_MASK, SD_PARTIAL_POWER_ON);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0x02);
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	/* To avoid too large in-rush current */
+	udelay(150);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			SD_POWER_MASK, SD_POWER_ON);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0x06);
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int rts5229_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			SD_POWER_MASK | PMOS_STRG_MASK,
+			SD_POWER_OFF | PMOS_STRG_400mA);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0X00);
+	return rtsx_pci_send_cmd(pcr, 100);
+}
+
+static const struct pcr_ops rts5229_pcr_ops = {
+	.extra_init_hw = rts5229_extra_init_hw,
+	.optimize_phy = rts5229_optimize_phy,
+	.turn_on_led = rts5229_turn_on_led,
+	.turn_off_led = rts5229_turn_off_led,
+	.enable_auto_blink = rts5229_enable_auto_blink,
+	.disable_auto_blink = rts5229_disable_auto_blink,
+	.card_power_on = rts5229_card_power_on,
+	.card_power_off = rts5229_card_power_off,
+	.cd_deglitch = NULL,
+};
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5229_sd_pull_ctl_enable_tbl1[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE9),
+	0,
+};
+
+/* For RTS5229 version C */
+static const u32 rts5229_sd_pull_ctl_enable_tbl2[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD9),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5229_sd_pull_ctl_disable_tbl1[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD5),
+	0,
+};
+
+/* For RTS5229 version C */
+static const u32 rts5229_sd_pull_ctl_disable_tbl2[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE5),
+	0,
+};
+
+/* MS Pull Control Enable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rts5229_ms_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x15),
+	0,
+};
+
+/* MS Pull Control Disable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rts5229_ms_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x15),
+	0,
+};
+
+void rts5229_init_params(struct rtsx_pcr *pcr)
+{
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104;
+	pcr->num_slots = 2;
+	pcr->ops = &rts5229_pcr_ops;
+
+	pcr->ic_version = rts5229_get_ic_version(pcr);
+	if (pcr->ic_version == IC_VER_C) {
+		pcr->sd_pull_ctl_enable_tbl = rts5229_sd_pull_ctl_enable_tbl2;
+		pcr->sd_pull_ctl_disable_tbl = rts5229_sd_pull_ctl_disable_tbl2;
+	} else {
+		pcr->sd_pull_ctl_enable_tbl = rts5229_sd_pull_ctl_enable_tbl1;
+		pcr->sd_pull_ctl_disable_tbl = rts5229_sd_pull_ctl_disable_tbl1;
+	}
+	pcr->ms_pull_ctl_enable_tbl = rts5229_ms_pull_ctl_enable_tbl;
+	pcr->ms_pull_ctl_disable_tbl = rts5229_ms_pull_ctl_disable_tbl;
+}
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
new file mode 100644
index 000000000000..56d4377c62c2
--- /dev/null
+++ b/drivers/mfd/rtsx_pcr.c
@@ -0,0 +1,1251 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+#include <linux/highmem.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/idr.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/rtsx_pci.h>
+#include <asm/unaligned.h>
+
+#include "rtsx_pcr.h"
+
+static bool msi_en = true;
+module_param(msi_en, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(msi_en, "Enable MSI");
+
+static DEFINE_IDR(rtsx_pci_idr);
+static DEFINE_SPINLOCK(rtsx_pci_lock);
+
+static struct mfd_cell rtsx_pcr_cells[] = {
+	[RTSX_SD_CARD] = {
+		.name = DRV_NAME_RTSX_PCI_SDMMC,
+	},
+	[RTSX_MS_CARD] = {
+		.name = DRV_NAME_RTSX_PCI_MS,
+	},
+};
+
+static DEFINE_PCI_DEVICE_TABLE(rtsx_pci_ids) = {
+	{ PCI_DEVICE(0x10EC, 0x5209), PCI_CLASS_OTHERS << 16, 0xFF0000 },
+	{ PCI_DEVICE(0x10EC, 0x5229), PCI_CLASS_OTHERS << 16, 0xFF0000 },
+	{ PCI_DEVICE(0x10EC, 0x5289), PCI_CLASS_OTHERS << 16, 0xFF0000 },
+	{ 0, }
+};
+
+MODULE_DEVICE_TABLE(pci, rtsx_pci_ids);
+
+void rtsx_pci_start_run(struct rtsx_pcr *pcr)
+{
+	/* If pci device removed, don't queue idle work any more */
+	if (pcr->remove_pci)
+		return;
+
+	if (pcr->state != PDEV_STAT_RUN) {
+		pcr->state = PDEV_STAT_RUN;
+		if (pcr->ops->enable_auto_blink)
+			pcr->ops->enable_auto_blink(pcr);
+	}
+
+	mod_delayed_work(system_wq, &pcr->idle_work, msecs_to_jiffies(200));
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_start_run);
+
+int rtsx_pci_write_register(struct rtsx_pcr *pcr, u16 addr, u8 mask, u8 data)
+{
+	int i;
+	u32 val = HAIMR_WRITE_START;
+
+	val |= (u32)(addr & 0x3FFF) << 16;
+	val |= (u32)mask << 8;
+	val |= (u32)data;
+
+	rtsx_pci_writel(pcr, RTSX_HAIMR, val);
+
+	for (i = 0; i < MAX_RW_REG_CNT; i++) {
+		val = rtsx_pci_readl(pcr, RTSX_HAIMR);
+		if ((val & HAIMR_TRANS_END) == 0) {
+			if (data != (u8)val)
+				return -EIO;
+			return 0;
+		}
+	}
+
+	return -ETIMEDOUT;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_write_register);
+
+int rtsx_pci_read_register(struct rtsx_pcr *pcr, u16 addr, u8 *data)
+{
+	u32 val = HAIMR_READ_START;
+	int i;
+
+	val |= (u32)(addr & 0x3FFF) << 16;
+	rtsx_pci_writel(pcr, RTSX_HAIMR, val);
+
+	for (i = 0; i < MAX_RW_REG_CNT; i++) {
+		val = rtsx_pci_readl(pcr, RTSX_HAIMR);
+		if ((val & HAIMR_TRANS_END) == 0)
+			break;
+	}
+
+	if (i >= MAX_RW_REG_CNT)
+		return -ETIMEDOUT;
+
+	if (data)
+		*data = (u8)(val & 0xFF);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_read_register);
+
+int rtsx_pci_write_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 val)
+{
+	int err, i, finished = 0;
+	u8 tmp;
+
+	rtsx_pci_init_cmd(pcr);
+
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYDATA0, 0xFF, (u8)val);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYDATA1, 0xFF, (u8)(val >> 8));
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYADDR, 0xFF, addr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYRWCTL, 0xFF, 0x81);
+
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i < 100000; i++) {
+		err = rtsx_pci_read_register(pcr, PHYRWCTL, &tmp);
+		if (err < 0)
+			return err;
+
+		if (!(tmp & 0x80)) {
+			finished = 1;
+			break;
+		}
+	}
+
+	if (!finished)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_write_phy_register);
+
+int rtsx_pci_read_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 *val)
+{
+	int err, i, finished = 0;
+	u16 data;
+	u8 *ptr, tmp;
+
+	rtsx_pci_init_cmd(pcr);
+
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYADDR, 0xFF, addr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYRWCTL, 0xFF, 0x80);
+
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i < 100000; i++) {
+		err = rtsx_pci_read_register(pcr, PHYRWCTL, &tmp);
+		if (err < 0)
+			return err;
+
+		if (!(tmp & 0x80)) {
+			finished = 1;
+			break;
+		}
+	}
+
+	if (!finished)
+		return -ETIMEDOUT;
+
+	rtsx_pci_init_cmd(pcr);
+
+	rtsx_pci_add_cmd(pcr, READ_REG_CMD, PHYDATA0, 0, 0);
+	rtsx_pci_add_cmd(pcr, READ_REG_CMD, PHYDATA1, 0, 0);
+
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	ptr = rtsx_pci_get_cmd_data(pcr);
+	data = ((u16)ptr[1] << 8) | ptr[0];
+
+	if (val)
+		*val = data;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_read_phy_register);
+
+void rtsx_pci_stop_cmd(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, STOP_CMD);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, STOP_DMA);
+
+	rtsx_pci_write_register(pcr, DMACTL, 0x80, 0x80);
+	rtsx_pci_write_register(pcr, RBCTL, 0x80, 0x80);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_stop_cmd);
+
+void rtsx_pci_add_cmd(struct rtsx_pcr *pcr,
+		u8 cmd_type, u16 reg_addr, u8 mask, u8 data)
+{
+	unsigned long flags;
+	u32 val = 0;
+	u32 *ptr = (u32 *)(pcr->host_cmds_ptr);
+
+	val |= (u32)(cmd_type & 0x03) << 30;
+	val |= (u32)(reg_addr & 0x3FFF) << 16;
+	val |= (u32)mask << 8;
+	val |= (u32)data;
+
+	spin_lock_irqsave(&pcr->lock, flags);
+	ptr += pcr->ci;
+	if (pcr->ci < (HOST_CMDS_BUF_LEN / 4)) {
+		put_unaligned_le32(val, ptr);
+		ptr++;
+		pcr->ci++;
+	}
+	spin_unlock_irqrestore(&pcr->lock, flags);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_add_cmd);
+
+void rtsx_pci_send_cmd_no_wait(struct rtsx_pcr *pcr)
+{
+	u32 val = 1 << 31;
+
+	rtsx_pci_writel(pcr, RTSX_HCBAR, pcr->host_cmds_addr);
+
+	val |= (u32)(pcr->ci * 4) & 0x00FFFFFF;
+	/* Hardware Auto Response */
+	val |= 0x40000000;
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, val);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_send_cmd_no_wait);
+
+int rtsx_pci_send_cmd(struct rtsx_pcr *pcr, int timeout)
+{
+	struct completion trans_done;
+	u32 val = 1 << 31;
+	long timeleft;
+	unsigned long flags;
+	int err = 0;
+
+	spin_lock_irqsave(&pcr->lock, flags);
+
+	/* set up data structures for the wakeup system */
+	pcr->done = &trans_done;
+	pcr->trans_result = TRANS_NOT_READY;
+	init_completion(&trans_done);
+
+	rtsx_pci_writel(pcr, RTSX_HCBAR, pcr->host_cmds_addr);
+
+	val |= (u32)(pcr->ci * 4) & 0x00FFFFFF;
+	/* Hardware Auto Response */
+	val |= 0x40000000;
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, val);
+
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	/* Wait for TRANS_OK_INT */
+	timeleft = wait_for_completion_interruptible_timeout(
+			&trans_done, msecs_to_jiffies(timeout));
+	if (timeleft <= 0) {
+		dev_dbg(&(pcr->pci->dev), "Timeout (%s %d)\n",
+				__func__, __LINE__);
+		err = -ETIMEDOUT;
+		goto finish_send_cmd;
+	}
+
+	spin_lock_irqsave(&pcr->lock, flags);
+	if (pcr->trans_result == TRANS_RESULT_FAIL)
+		err = -EINVAL;
+	else if (pcr->trans_result == TRANS_RESULT_OK)
+		err = 0;
+	else if (pcr->trans_result == TRANS_NO_DEVICE)
+		err = -ENODEV;
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+finish_send_cmd:
+	spin_lock_irqsave(&pcr->lock, flags);
+	pcr->done = NULL;
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	if ((err < 0) && (err != -ENODEV))
+		rtsx_pci_stop_cmd(pcr);
+
+	if (pcr->finish_me)
+		complete(pcr->finish_me);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_send_cmd);
+
+static void rtsx_pci_add_sg_tbl(struct rtsx_pcr *pcr,
+		dma_addr_t addr, unsigned int len, int end)
+{
+	u64 *ptr = (u64 *)(pcr->host_sg_tbl_ptr) + pcr->sgi;
+	u64 val;
+	u8 option = SG_VALID | SG_TRANS_DATA;
+
+	dev_dbg(&(pcr->pci->dev), "DMA addr: 0x%x, Len: 0x%x\n",
+			(unsigned int)addr, len);
+
+	if (end)
+		option |= SG_END;
+	val = ((u64)addr << 32) | ((u64)len << 12) | option;
+
+	put_unaligned_le64(val, ptr);
+	ptr++;
+	pcr->sgi++;
+}
+
+int rtsx_pci_transfer_data(struct rtsx_pcr *pcr, struct scatterlist *sglist,
+		int num_sg, bool read, int timeout)
+{
+	struct completion trans_done;
+	u8 dir;
+	int err = 0, i, count;
+	long timeleft;
+	unsigned long flags;
+	struct scatterlist *sg;
+	enum dma_data_direction dma_dir;
+	u32 val;
+	dma_addr_t addr;
+	unsigned int len;
+
+	dev_dbg(&(pcr->pci->dev), "--> %s: num_sg = %d\n", __func__, num_sg);
+
+	/* don't transfer data during abort processing */
+	if (pcr->remove_pci)
+		return -EINVAL;
+
+	if ((sglist == NULL) || (num_sg <= 0))
+		return -EINVAL;
+
+	if (read) {
+		dir = DEVICE_TO_HOST;
+		dma_dir = DMA_FROM_DEVICE;
+	} else {
+		dir = HOST_TO_DEVICE;
+		dma_dir = DMA_TO_DEVICE;
+	}
+
+	count = dma_map_sg(&(pcr->pci->dev), sglist, num_sg, dma_dir);
+	if (count < 1) {
+		dev_err(&(pcr->pci->dev), "scatterlist map failed\n");
+		return -EINVAL;
+	}
+	dev_dbg(&(pcr->pci->dev), "DMA mapping count: %d\n", count);
+
+	val = ((u32)(dir & 0x01) << 29) | TRIG_DMA | ADMA_MODE;
+	pcr->sgi = 0;
+	for_each_sg(sglist, sg, count, i) {
+		addr = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+		rtsx_pci_add_sg_tbl(pcr, addr, len, i == count - 1);
+	}
+
+	spin_lock_irqsave(&pcr->lock, flags);
+
+	pcr->done = &trans_done;
+	pcr->trans_result = TRANS_NOT_READY;
+	init_completion(&trans_done);
+	rtsx_pci_writel(pcr, RTSX_HDBAR, pcr->host_sg_tbl_addr);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, val);
+
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	timeleft = wait_for_completion_interruptible_timeout(
+			&trans_done, msecs_to_jiffies(timeout));
+	if (timeleft <= 0) {
+		dev_dbg(&(pcr->pci->dev), "Timeout (%s %d)\n",
+				__func__, __LINE__);
+		err = -ETIMEDOUT;
+		goto out;
+	}
+
+	spin_lock_irqsave(&pcr->lock, flags);
+
+	if (pcr->trans_result == TRANS_RESULT_FAIL)
+		err = -EINVAL;
+	else if (pcr->trans_result == TRANS_NO_DEVICE)
+		err = -ENODEV;
+
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+out:
+	spin_lock_irqsave(&pcr->lock, flags);
+	pcr->done = NULL;
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	dma_unmap_sg(&(pcr->pci->dev), sglist, num_sg, dma_dir);
+
+	if ((err < 0) && (err != -ENODEV))
+		rtsx_pci_stop_cmd(pcr);
+
+	if (pcr->finish_me)
+		complete(pcr->finish_me);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_transfer_data);
+
+int rtsx_pci_read_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len)
+{
+	int err;
+	int i, j;
+	u16 reg;
+	u8 *ptr;
+
+	if (buf_len > 512)
+		buf_len = 512;
+
+	ptr = buf;
+	reg = PPBUF_BASE2;
+	for (i = 0; i < buf_len / 256; i++) {
+		rtsx_pci_init_cmd(pcr);
+
+		for (j = 0; j < 256; j++)
+			rtsx_pci_add_cmd(pcr, READ_REG_CMD, reg++, 0, 0);
+
+		err = rtsx_pci_send_cmd(pcr, 250);
+		if (err < 0)
+			return err;
+
+		memcpy(ptr, rtsx_pci_get_cmd_data(pcr), 256);
+		ptr += 256;
+	}
+
+	if (buf_len % 256) {
+		rtsx_pci_init_cmd(pcr);
+
+		for (j = 0; j < buf_len % 256; j++)
+			rtsx_pci_add_cmd(pcr, READ_REG_CMD, reg++, 0, 0);
+
+		err = rtsx_pci_send_cmd(pcr, 250);
+		if (err < 0)
+			return err;
+	}
+
+	memcpy(ptr, rtsx_pci_get_cmd_data(pcr), buf_len % 256);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_read_ppbuf);
+
+int rtsx_pci_write_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len)
+{
+	int err;
+	int i, j;
+	u16 reg;
+	u8 *ptr;
+
+	if (buf_len > 512)
+		buf_len = 512;
+
+	ptr = buf;
+	reg = PPBUF_BASE2;
+	for (i = 0; i < buf_len / 256; i++) {
+		rtsx_pci_init_cmd(pcr);
+
+		for (j = 0; j < 256; j++) {
+			rtsx_pci_add_cmd(pcr, WRITE_REG_CMD,
+					reg++, 0xFF, *ptr);
+			ptr++;
+		}
+
+		err = rtsx_pci_send_cmd(pcr, 250);
+		if (err < 0)
+			return err;
+	}
+
+	if (buf_len % 256) {
+		rtsx_pci_init_cmd(pcr);
+
+		for (j = 0; j < buf_len % 256; j++) {
+			rtsx_pci_add_cmd(pcr, WRITE_REG_CMD,
+					reg++, 0xFF, *ptr);
+			ptr++;
+		}
+
+		err = rtsx_pci_send_cmd(pcr, 250);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_write_ppbuf);
+
+static int rtsx_pci_set_pull_ctl(struct rtsx_pcr *pcr, const u32 *tbl)
+{
+	int err;
+
+	rtsx_pci_init_cmd(pcr);
+
+	while (*tbl & 0xFFFF0000) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD,
+				(u16)(*tbl >> 16), 0xFF, (u8)(*tbl));
+		tbl++;
+	}
+
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+int rtsx_pci_card_pull_ctl_enable(struct rtsx_pcr *pcr, int card)
+{
+	const u32 *tbl;
+
+	if (card == RTSX_SD_CARD)
+		tbl = pcr->sd_pull_ctl_enable_tbl;
+	else if (card == RTSX_MS_CARD)
+		tbl = pcr->ms_pull_ctl_enable_tbl;
+	else
+		return -EINVAL;
+
+	return rtsx_pci_set_pull_ctl(pcr, tbl);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_card_pull_ctl_enable);
+
+int rtsx_pci_card_pull_ctl_disable(struct rtsx_pcr *pcr, int card)
+{
+	const u32 *tbl;
+
+	if (card == RTSX_SD_CARD)
+		tbl = pcr->sd_pull_ctl_disable_tbl;
+	else if (card == RTSX_MS_CARD)
+		tbl = pcr->ms_pull_ctl_disable_tbl;
+	else
+		return -EINVAL;
+
+
+	return rtsx_pci_set_pull_ctl(pcr, tbl);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_card_pull_ctl_disable);
+
+static void rtsx_pci_enable_bus_int(struct rtsx_pcr *pcr)
+{
+	pcr->bier = TRANS_OK_INT_EN | TRANS_FAIL_INT_EN | SD_INT_EN;
+
+	if (pcr->num_slots > 1)
+		pcr->bier |= MS_INT_EN;
+
+	/* Enable Bus Interrupt */
+	rtsx_pci_writel(pcr, RTSX_BIER, pcr->bier);
+
+	dev_dbg(&(pcr->pci->dev), "RTSX_BIER: 0x%08x\n", pcr->bier);
+}
+
+static inline u8 double_ssc_depth(u8 depth)
+{
+	return ((depth > 1) ? (depth - 1) : depth);
+}
+
+static u8 revise_ssc_depth(u8 ssc_depth, u8 div)
+{
+	if (div > CLK_DIV_1) {
+		if (ssc_depth > (div - 1))
+			ssc_depth -= (div - 1);
+		else
+			ssc_depth = SSC_DEPTH_4M;
+	}
+
+	return ssc_depth;
+}
+
+int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk)
+{
+	int err, clk;
+	u8 N, min_N, max_N, clk_divider;
+	u8 mcu_cnt, div, max_div;
+	u8 depth[] = {
+		[RTSX_SSC_DEPTH_4M] = SSC_DEPTH_4M,
+		[RTSX_SSC_DEPTH_2M] = SSC_DEPTH_2M,
+		[RTSX_SSC_DEPTH_1M] = SSC_DEPTH_1M,
+		[RTSX_SSC_DEPTH_500K] = SSC_DEPTH_500K,
+		[RTSX_SSC_DEPTH_250K] = SSC_DEPTH_250K,
+	};
+
+	if (initial_mode) {
+		/* We use 250k(around) here, in initial stage */
+		clk_divider = SD_CLK_DIVIDE_128;
+		card_clock = 30000000;
+	} else {
+		clk_divider = SD_CLK_DIVIDE_0;
+	}
+	err = rtsx_pci_write_register(pcr, SD_CFG1,
+			SD_CLK_DIVIDE_MASK, clk_divider);
+	if (err < 0)
+		return err;
+
+	card_clock /= 1000000;
+	dev_dbg(&(pcr->pci->dev), "Switch card clock to %dMHz\n", card_clock);
+
+	min_N = 80;
+	max_N = 208;
+	max_div = CLK_DIV_8;
+
+	clk = card_clock;
+	if (!initial_mode && double_clk)
+		clk = card_clock * 2;
+	dev_dbg(&(pcr->pci->dev),
+			"Internal SSC clock: %dMHz (cur_clock = %d)\n",
+			clk, pcr->cur_clock);
+
+	if (clk == pcr->cur_clock)
+		return 0;
+
+	N = (u8)(clk - 2);
+	if ((clk <= 2) || (N > max_N))
+		return -EINVAL;
+
+	mcu_cnt = (u8)(125/clk + 3);
+	if (mcu_cnt > 15)
+		mcu_cnt = 15;
+
+	/* Make sure that the SSC clock div_n is equal or greater than min_N */
+	div = CLK_DIV_1;
+	while ((N < min_N) && (div < max_div)) {
+		N = (N + 2) * 2 - 2;
+		div++;
+	}
+	dev_dbg(&(pcr->pci->dev), "N = %d, div = %d\n", N, div);
+
+	ssc_depth = depth[ssc_depth];
+	if (double_clk)
+		ssc_depth = double_ssc_depth(ssc_depth);
+
+	ssc_depth = revise_ssc_depth(ssc_depth, div);
+	dev_dbg(&(pcr->pci->dev), "ssc_depth = %d\n", ssc_depth);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL,
+			CLK_LOW_FREQ, CLK_LOW_FREQ);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_DIV,
+			0xFF, (div << 4) | mcu_cnt);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2,
+			SSC_DEPTH_MASK, ssc_depth);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_DIV_N_0, 0xFF, N);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, SSC_RSTB);
+	if (vpclk) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+	}
+
+	err = rtsx_pci_send_cmd(pcr, 2000);
+	if (err < 0)
+		return err;
+
+	/* Wait SSC clock stable */
+	udelay(10);
+	err = rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0);
+	if (err < 0)
+		return err;
+
+	pcr->cur_clock = clk;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_switch_clock);
+
+int rtsx_pci_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	if (pcr->ops->card_power_on)
+		return pcr->ops->card_power_on(pcr, card);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_card_power_on);
+
+int rtsx_pci_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	if (pcr->ops->card_power_off)
+		return pcr->ops->card_power_off(pcr, card);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_card_power_off);
+
+unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr)
+{
+	unsigned int val;
+
+	val = rtsx_pci_readl(pcr, RTSX_BIPR);
+	if (pcr->ops->cd_deglitch)
+		val = pcr->ops->cd_deglitch(pcr);
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_card_exist);
+
+void rtsx_pci_complete_unfinished_transfer(struct rtsx_pcr *pcr)
+{
+	struct completion finish;
+
+	pcr->finish_me = &finish;
+	init_completion(&finish);
+
+	if (pcr->done)
+		complete(pcr->done);
+
+	if (!pcr->remove_pci)
+		rtsx_pci_stop_cmd(pcr);
+
+	wait_for_completion_interruptible_timeout(&finish,
+			msecs_to_jiffies(2));
+	pcr->finish_me = NULL;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_complete_unfinished_transfer);
+
+static void rtsx_pci_card_detect(struct work_struct *work)
+{
+	struct delayed_work *dwork;
+	struct rtsx_pcr *pcr;
+	unsigned long flags;
+	unsigned int card_detect = 0;
+	u32 irq_status;
+
+	dwork = to_delayed_work(work);
+	pcr = container_of(dwork, struct rtsx_pcr, carddet_work);
+
+	dev_dbg(&(pcr->pci->dev), "--> %s\n", __func__);
+
+	spin_lock_irqsave(&pcr->lock, flags);
+
+	irq_status = rtsx_pci_readl(pcr, RTSX_BIPR);
+	dev_dbg(&(pcr->pci->dev), "irq_status: 0x%08x\n", irq_status);
+
+	if (pcr->card_inserted || pcr->card_removed) {
+		dev_dbg(&(pcr->pci->dev),
+				"card_inserted: 0x%x, card_removed: 0x%x\n",
+				pcr->card_inserted, pcr->card_removed);
+
+		if (pcr->ops->cd_deglitch)
+			pcr->card_inserted = pcr->ops->cd_deglitch(pcr);
+
+		card_detect = pcr->card_inserted | pcr->card_removed;
+		pcr->card_inserted = 0;
+		pcr->card_removed = 0;
+	}
+
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	if (card_detect & SD_EXIST)
+		pcr->slots[RTSX_SD_CARD].card_event(
+				pcr->slots[RTSX_SD_CARD].p_dev);
+	if (card_detect & MS_EXIST)
+		pcr->slots[RTSX_MS_CARD].card_event(
+				pcr->slots[RTSX_MS_CARD].p_dev);
+}
+
+static irqreturn_t rtsx_pci_isr(int irq, void *dev_id)
+{
+	struct rtsx_pcr *pcr = dev_id;
+	u32 int_reg;
+
+	if (!pcr)
+		return IRQ_NONE;
+
+	spin_lock(&pcr->lock);
+
+	int_reg = rtsx_pci_readl(pcr, RTSX_BIPR);
+	/* Clear interrupt flag */
+	rtsx_pci_writel(pcr, RTSX_BIPR, int_reg);
+	if ((int_reg & pcr->bier) == 0) {
+		spin_unlock(&pcr->lock);
+		return IRQ_NONE;
+	}
+	if (int_reg == 0xFFFFFFFF) {
+		spin_unlock(&pcr->lock);
+		return IRQ_HANDLED;
+	}
+
+	int_reg &= (pcr->bier | 0x7FFFFF);
+
+	if (int_reg & SD_INT) {
+		if (int_reg & SD_EXIST) {
+			pcr->card_inserted |= SD_EXIST;
+		} else {
+			pcr->card_removed |= SD_EXIST;
+			pcr->card_inserted &= ~SD_EXIST;
+		}
+	}
+
+	if (int_reg & MS_INT) {
+		if (int_reg & MS_EXIST) {
+			pcr->card_inserted |= MS_EXIST;
+		} else {
+			pcr->card_removed |= MS_EXIST;
+			pcr->card_inserted &= ~MS_EXIST;
+		}
+	}
+
+	if (pcr->card_inserted || pcr->card_removed)
+		schedule_delayed_work(&pcr->carddet_work,
+				msecs_to_jiffies(200));
+
+	if (int_reg & (NEED_COMPLETE_INT | DELINK_INT)) {
+		if (int_reg & (TRANS_FAIL_INT | DELINK_INT)) {
+			pcr->trans_result = TRANS_RESULT_FAIL;
+			if (pcr->done)
+				complete(pcr->done);
+		} else if (int_reg & TRANS_OK_INT) {
+			pcr->trans_result = TRANS_RESULT_OK;
+			if (pcr->done)
+				complete(pcr->done);
+		}
+	}
+
+	spin_unlock(&pcr->lock);
+	return IRQ_HANDLED;
+}
+
+static int rtsx_pci_acquire_irq(struct rtsx_pcr *pcr)
+{
+	dev_info(&(pcr->pci->dev), "%s: pcr->msi_en = %d, pci->irq = %d\n",
+			__func__, pcr->msi_en, pcr->pci->irq);
+
+	if (request_irq(pcr->pci->irq, rtsx_pci_isr,
+			pcr->msi_en ? 0 : IRQF_SHARED,
+			DRV_NAME_RTSX_PCI, pcr)) {
+		dev_err(&(pcr->pci->dev),
+			"rtsx_sdmmc: unable to grab IRQ %d, disabling device\n",
+			pcr->pci->irq);
+		return -1;
+	}
+
+	pcr->irq = pcr->pci->irq;
+	pci_intx(pcr->pci, !pcr->msi_en);
+
+	return 0;
+}
+
+static void rtsx_pci_idle_work(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct rtsx_pcr *pcr = container_of(dwork, struct rtsx_pcr, idle_work);
+
+	dev_dbg(&(pcr->pci->dev), "--> %s\n", __func__);
+
+	mutex_lock(&pcr->pcr_mutex);
+
+	pcr->state = PDEV_STAT_IDLE;
+
+	if (pcr->ops->disable_auto_blink)
+		pcr->ops->disable_auto_blink(pcr);
+	if (pcr->ops->turn_off_led)
+		pcr->ops->turn_off_led(pcr);
+
+	mutex_unlock(&pcr->pcr_mutex);
+}
+
+static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
+{
+	int err;
+
+	rtsx_pci_writel(pcr, RTSX_HCBAR, pcr->host_cmds_addr);
+
+	rtsx_pci_enable_bus_int(pcr);
+
+	/* Power on SSC */
+	err = rtsx_pci_write_register(pcr, FPDCTL, SSC_POWER_DOWN, 0);
+	if (err < 0)
+		return err;
+
+	/* Wait SSC power stable */
+	udelay(200);
+
+	if (pcr->ops->optimize_phy) {
+		err = pcr->ops->optimize_phy(pcr);
+		if (err < 0)
+			return err;
+	}
+
+	rtsx_pci_init_cmd(pcr);
+
+	/* Set mcu_cnt to 7 to ensure data can be sampled properly */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_DIV, 0x07, 0x07);
+
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, HOST_SLEEP_STATE, 0x03, 0x00);
+	/* Disable card clock */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_CLK_EN, 0x1E, 0);
+	/* Reset ASPM state to default value */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, ASPM_FORCE_CTL, 0x3F, 0);
+	/* Reset delink mode */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CHANGE_LINK_STATE, 0x0A, 0);
+	/* Card driving select */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD30_DRIVE_SEL,
+			0x07, DRIVER_TYPE_D);
+	/* Enable SSC Clock */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1,
+			0xFF, SSC_8X_EN | SSC_SEL_4M);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF, 0x12);
+	/* Disable cd_pwr_save */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CHANGE_LINK_STATE, 0x16, 0x10);
+	/* Clear Link Ready Interrupt */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, IRQSTAT0,
+			LINK_RDY_INT, LINK_RDY_INT);
+	/* Enlarge the estimation window of PERST# glitch
+	 * to reduce the chance of invalid card interrupt
+	 */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PERST_GLITCH_WIDTH, 0xFF, 0x80);
+	/* Update RC oscillator to 400k
+	 * bit[0] F_HIGH: for RC oscillator, Rst_value is 1'b1
+	 *                1: 2M  0: 400k
+	 */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, RCCTL, 0x01, 0x00);
+	/* Set interrupt write clear
+	 * bit 1: U_elbi_if_rd_clr_en
+	 *	1: Enable ELBI interrupt[31:22] & [7:0] flag read clear
+	 *	0: ELBI interrupt flag[31:22] & [7:0] only can be write clear
+	 */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, NFTS_TX_CTRL, 0x02, 0);
+	/* Force CLKREQ# PIN to drive 0 to request clock */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0x08, 0x08);
+
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	/* Enable clk_request_n to enable clock power management */
+	rtsx_pci_write_config_byte(pcr, 0x81, 1);
+	/* Enter L1 when host tx idle */
+	rtsx_pci_write_config_byte(pcr, 0x70F, 0x5B);
+
+	if (pcr->ops->extra_init_hw) {
+		err = pcr->ops->extra_init_hw(pcr);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
+static int rtsx_pci_init_chip(struct rtsx_pcr *pcr)
+{
+	int err;
+
+	spin_lock_init(&pcr->lock);
+	mutex_init(&pcr->pcr_mutex);
+
+	switch (PCI_PID(pcr)) {
+	default:
+	case 0x5209:
+		rts5209_init_params(pcr);
+		break;
+
+	case 0x5229:
+		rts5229_init_params(pcr);
+		break;
+
+	case 0x5289:
+		rtl8411_init_params(pcr);
+		break;
+	}
+
+	dev_dbg(&(pcr->pci->dev), "PID: 0x%04x, IC version: 0x%02x\n",
+			PCI_PID(pcr), pcr->ic_version);
+
+	pcr->slots = kcalloc(pcr->num_slots, sizeof(struct rtsx_slot),
+			GFP_KERNEL);
+	if (!pcr->slots)
+		return -ENOMEM;
+
+	pcr->state = PDEV_STAT_IDLE;
+	err = rtsx_pci_init_hw(pcr);
+	if (err < 0) {
+		kfree(pcr->slots);
+		return err;
+	}
+
+	return 0;
+}
+
+static int __devinit rtsx_pci_probe(struct pci_dev *pcidev,
+				    const struct pci_device_id *id)
+{
+	struct rtsx_pcr *pcr;
+	struct pcr_handle *handle;
+	u32 base, len;
+	int ret, i;
+
+	dev_dbg(&(pcidev->dev),
+		": Realtek PCI-E Card Reader found at %s [%04x:%04x] (rev %x)\n",
+		pci_name(pcidev), (int)pcidev->vendor, (int)pcidev->device,
+		(int)pcidev->revision);
+
+	ret = pci_enable_device(pcidev);
+	if (ret)
+		return ret;
+
+	ret = pci_request_regions(pcidev, DRV_NAME_RTSX_PCI);
+	if (ret)
+		goto disable;
+
+	pcr = kzalloc(sizeof(*pcr), GFP_KERNEL);
+	if (!pcr) {
+		ret = -ENOMEM;
+		goto release_pci;
+	}
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle) {
+		ret = -ENOMEM;
+		goto free_pcr;
+	}
+	handle->pcr = pcr;
+
+	if (!idr_pre_get(&rtsx_pci_idr, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto free_handle;
+	}
+
+	spin_lock(&rtsx_pci_lock);
+	ret = idr_get_new(&rtsx_pci_idr, pcr, &pcr->id);
+	spin_unlock(&rtsx_pci_lock);
+	if (ret)
+		goto free_handle;
+
+	pcr->pci = pcidev;
+	dev_set_drvdata(&pcidev->dev, handle);
+
+	len = pci_resource_len(pcidev, 0);
+	base = pci_resource_start(pcidev, 0);
+	pcr->remap_addr = ioremap_nocache(base, len);
+	if (!pcr->remap_addr) {
+		ret = -ENOMEM;
+		goto free_host;
+	}
+
+	pcr->rtsx_resv_buf = dma_alloc_coherent(&(pcidev->dev),
+			RTSX_RESV_BUF_LEN, &(pcr->rtsx_resv_buf_addr),
+			GFP_KERNEL);
+	if (pcr->rtsx_resv_buf == NULL) {
+		ret = -ENXIO;
+		goto unmap;
+	}
+	pcr->host_cmds_ptr = pcr->rtsx_resv_buf;
+	pcr->host_cmds_addr = pcr->rtsx_resv_buf_addr;
+	pcr->host_sg_tbl_ptr = pcr->rtsx_resv_buf + HOST_CMDS_BUF_LEN;
+	pcr->host_sg_tbl_addr = pcr->rtsx_resv_buf_addr + HOST_CMDS_BUF_LEN;
+
+	pcr->card_inserted = 0;
+	pcr->card_removed = 0;
+	INIT_DELAYED_WORK(&pcr->carddet_work, rtsx_pci_card_detect);
+	INIT_DELAYED_WORK(&pcr->idle_work, rtsx_pci_idle_work);
+
+	pcr->msi_en = msi_en;
+	if (pcr->msi_en) {
+		ret = pci_enable_msi(pcidev);
+		if (ret < 0)
+			pcr->msi_en = false;
+	}
+
+	ret = rtsx_pci_acquire_irq(pcr);
+	if (ret < 0)
+		goto free_dma;
+
+	pci_set_master(pcidev);
+	synchronize_irq(pcr->irq);
+
+	ret = rtsx_pci_init_chip(pcr);
+	if (ret < 0)
+		goto disable_irq;
+
+	for (i = 0; i < ARRAY_SIZE(rtsx_pcr_cells); i++) {
+		rtsx_pcr_cells[i].platform_data = handle;
+		rtsx_pcr_cells[i].pdata_size = sizeof(*handle);
+	}
+	ret = mfd_add_devices(&pcidev->dev, pcr->id, rtsx_pcr_cells,
+			ARRAY_SIZE(rtsx_pcr_cells), NULL, 0, NULL);
+	if (ret < 0)
+		goto disable_irq;
+
+	schedule_delayed_work(&pcr->idle_work, msecs_to_jiffies(200));
+
+	return 0;
+
+disable_irq:
+	free_irq(pcr->irq, (void *)pcr);
+free_dma:
+	dma_free_coherent(&(pcr->pci->dev), RTSX_RESV_BUF_LEN,
+			pcr->rtsx_resv_buf, pcr->rtsx_resv_buf_addr);
+unmap:
+	iounmap(pcr->remap_addr);
+free_host:
+	dev_set_drvdata(&pcidev->dev, NULL);
+free_handle:
+	kfree(handle);
+free_pcr:
+	kfree(pcr);
+release_pci:
+	pci_release_regions(pcidev);
+disable:
+	pci_disable_device(pcidev);
+
+	return ret;
+}
+
+static void __devexit rtsx_pci_remove(struct pci_dev *pcidev)
+{
+	struct pcr_handle *handle = pci_get_drvdata(pcidev);
+	struct rtsx_pcr *pcr = handle->pcr;
+
+	pcr->remove_pci = true;
+
+	cancel_delayed_work(&pcr->carddet_work);
+	cancel_delayed_work(&pcr->idle_work);
+
+	mfd_remove_devices(&pcidev->dev);
+
+	dma_free_coherent(&(pcr->pci->dev), RTSX_RESV_BUF_LEN,
+			pcr->rtsx_resv_buf, pcr->rtsx_resv_buf_addr);
+	free_irq(pcr->irq, (void *)pcr);
+	if (pcr->msi_en)
+		pci_disable_msi(pcr->pci);
+	iounmap(pcr->remap_addr);
+
+	dev_set_drvdata(&pcidev->dev, NULL);
+	pci_release_regions(pcidev);
+	pci_disable_device(pcidev);
+
+	spin_lock(&rtsx_pci_lock);
+	idr_remove(&rtsx_pci_idr, pcr->id);
+	spin_unlock(&rtsx_pci_lock);
+
+	kfree(pcr->slots);
+	kfree(pcr);
+	kfree(handle);
+
+	dev_dbg(&(pcidev->dev),
+		": Realtek PCI-E Card Reader at %s [%04x:%04x] has been removed\n",
+		pci_name(pcidev), (int)pcidev->vendor, (int)pcidev->device);
+}
+
+#ifdef CONFIG_PM
+
+static int rtsx_pci_suspend(struct pci_dev *pcidev, pm_message_t state)
+{
+	struct pcr_handle *handle;
+	struct rtsx_pcr *pcr;
+	int ret = 0;
+
+	dev_dbg(&(pcidev->dev), "--> %s\n", __func__);
+
+	handle = pci_get_drvdata(pcidev);
+	pcr = handle->pcr;
+
+	cancel_delayed_work(&pcr->carddet_work);
+	cancel_delayed_work(&pcr->idle_work);
+
+	mutex_lock(&pcr->pcr_mutex);
+
+	if (pcr->ops->turn_off_led)
+		pcr->ops->turn_off_led(pcr);
+
+	rtsx_pci_writel(pcr, RTSX_BIER, 0);
+	pcr->bier = 0;
+
+	rtsx_pci_write_register(pcr, PETXCFG, 0x08, 0x08);
+	rtsx_pci_write_register(pcr, HOST_SLEEP_STATE, 0x03, 0x02);
+
+	pci_save_state(pcidev);
+	pci_enable_wake(pcidev, pci_choose_state(pcidev, state), 0);
+	pci_disable_device(pcidev);
+	pci_set_power_state(pcidev, pci_choose_state(pcidev, state));
+
+	mutex_unlock(&pcr->pcr_mutex);
+	return ret;
+}
+
+static int rtsx_pci_resume(struct pci_dev *pcidev)
+{
+	struct pcr_handle *handle;
+	struct rtsx_pcr *pcr;
+	int ret = 0;
+
+	dev_dbg(&(pcidev->dev), "--> %s\n", __func__);
+
+	handle = pci_get_drvdata(pcidev);
+	pcr = handle->pcr;
+
+	mutex_lock(&pcr->pcr_mutex);
+
+	pci_set_power_state(pcidev, PCI_D0);
+	pci_restore_state(pcidev);
+	ret = pci_enable_device(pcidev);
+	if (ret)
+		goto out;
+	pci_set_master(pcidev);
+
+	ret = rtsx_pci_write_register(pcr, HOST_SLEEP_STATE, 0x03, 0x00);
+	if (ret)
+		goto out;
+
+	ret = rtsx_pci_init_hw(pcr);
+	if (ret)
+		goto out;
+
+	schedule_delayed_work(&pcr->idle_work, msecs_to_jiffies(200));
+
+out:
+	mutex_unlock(&pcr->pcr_mutex);
+	return ret;
+}
+
+#else /* CONFIG_PM */
+
+#define rtsx_pci_suspend NULL
+#define rtsx_pci_resume NULL
+
+#endif /* CONFIG_PM */
+
+static struct pci_driver rtsx_pci_driver = {
+	.name = DRV_NAME_RTSX_PCI,
+	.id_table = rtsx_pci_ids,
+	.probe = rtsx_pci_probe,
+	.remove = __devexit_p(rtsx_pci_remove),
+	.suspend = rtsx_pci_suspend,
+	.resume = rtsx_pci_resume,
+};
+module_pci_driver(rtsx_pci_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Wei WANG <wei_wang@realsil.com.cn>");
+MODULE_DESCRIPTION("Realtek PCI-E Card Reader Driver");
diff --git a/drivers/mfd/rtsx_pcr.h b/drivers/mfd/rtsx_pcr.h
new file mode 100644
index 000000000000..12462c1df1a9
--- /dev/null
+++ b/drivers/mfd/rtsx_pcr.h
@@ -0,0 +1,32 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#ifndef __RTSX_PCR_H
+#define __RTSX_PCR_H
+
+#include <linux/mfd/rtsx_pci.h>
+
+void rts5209_init_params(struct rtsx_pcr *pcr);
+void rts5229_init_params(struct rtsx_pcr *pcr);
+void rtl8411_init_params(struct rtsx_pcr *pcr);
+
+#endif
diff --git a/include/linux/mfd/rtsx_common.h b/include/linux/mfd/rtsx_common.h
new file mode 100644
index 000000000000..a8d393e3066b
--- /dev/null
+++ b/include/linux/mfd/rtsx_common.h
@@ -0,0 +1,48 @@
+/* Driver for Realtek driver-based card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#ifndef __RTSX_COMMON_H
+#define __RTSX_COMMON_H
+
+#define DRV_NAME_RTSX_PCI		"rtsx_pci"
+#define DRV_NAME_RTSX_PCI_SDMMC		"rtsx_pci_sdmmc"
+#define DRV_NAME_RTSX_PCI_MS		"rtsx_pci_ms"
+
+#define RTSX_REG_PAIR(addr, val)	(((u32)(addr) << 16) | (u8)(val))
+
+#define RTSX_SSC_DEPTH_4M		0x01
+#define RTSX_SSC_DEPTH_2M		0x02
+#define RTSX_SSC_DEPTH_1M		0x03
+#define RTSX_SSC_DEPTH_500K		0x04
+#define RTSX_SSC_DEPTH_250K		0x05
+
+#define RTSX_SD_CARD			0
+#define RTSX_MS_CARD			1
+
+struct platform_device;
+
+struct rtsx_slot {
+	struct platform_device	*p_dev;
+	void			(*card_event)(struct platform_device *p_dev);
+};
+
+#endif
diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
new file mode 100644
index 000000000000..060b721fcbfb
--- /dev/null
+++ b/include/linux/mfd/rtsx_pci.h
@@ -0,0 +1,794 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#ifndef __RTSX_PCI_H
+#define __RTSX_PCI_H
+
+#include <linux/sched.h>
+#include <linux/pci.h>
+
+#include "rtsx_common.h"
+
+#define MAX_RW_REG_CNT			1024
+
+/* PCI Operation Register Address */
+#define RTSX_HCBAR			0x00
+#define RTSX_HCBCTLR			0x04
+#define RTSX_HDBAR			0x08
+#define RTSX_HDBCTLR			0x0C
+#define RTSX_HAIMR			0x10
+#define RTSX_BIPR			0x14
+#define RTSX_BIER			0x18
+
+/* Host command buffer control register */
+#define STOP_CMD			(0x01 << 28)
+
+/* Host data buffer control register */
+#define SDMA_MODE			0x00
+#define ADMA_MODE			(0x02 << 26)
+#define STOP_DMA			(0x01 << 28)
+#define TRIG_DMA			(0x01 << 31)
+
+/* Host access internal memory register */
+#define HAIMR_TRANS_START		(0x01 << 31)
+#define HAIMR_READ			0x00
+#define HAIMR_WRITE			(0x01 << 30)
+#define HAIMR_READ_START		(HAIMR_TRANS_START | HAIMR_READ)
+#define HAIMR_WRITE_START		(HAIMR_TRANS_START | HAIMR_WRITE)
+#define HAIMR_TRANS_END			(HAIMR_TRANS_START)
+
+/* Bus interrupt pending register */
+#define CMD_DONE_INT			(1 << 31)
+#define DATA_DONE_INT			(1 << 30)
+#define TRANS_OK_INT			(1 << 29)
+#define TRANS_FAIL_INT			(1 << 28)
+#define XD_INT				(1 << 27)
+#define MS_INT				(1 << 26)
+#define SD_INT				(1 << 25)
+#define GPIO0_INT			(1 << 24)
+#define OC_INT				(1 << 23)
+#define SD_WRITE_PROTECT		(1 << 19)
+#define XD_EXIST			(1 << 18)
+#define MS_EXIST			(1 << 17)
+#define SD_EXIST			(1 << 16)
+#define DELINK_INT			GPIO0_INT
+#define MS_OC_INT			(1 << 23)
+#define SD_OC_INT			(1 << 22)
+
+#define CARD_INT		(XD_INT | MS_INT | SD_INT)
+#define NEED_COMPLETE_INT	(DATA_DONE_INT | TRANS_OK_INT | TRANS_FAIL_INT)
+#define RTSX_INT		(CMD_DONE_INT | NEED_COMPLETE_INT | \
+					CARD_INT | GPIO0_INT | OC_INT)
+
+#define CARD_EXIST		(XD_EXIST | MS_EXIST | SD_EXIST)
+
+/* Bus interrupt enable register */
+#define CMD_DONE_INT_EN		(1 << 31)
+#define DATA_DONE_INT_EN	(1 << 30)
+#define TRANS_OK_INT_EN		(1 << 29)
+#define TRANS_FAIL_INT_EN	(1 << 28)
+#define XD_INT_EN		(1 << 27)
+#define MS_INT_EN		(1 << 26)
+#define SD_INT_EN		(1 << 25)
+#define GPIO0_INT_EN		(1 << 24)
+#define OC_INT_EN		(1 << 23)
+#define DELINK_INT_EN		GPIO0_INT_EN
+#define MS_OC_INT_EN		(1 << 23)
+#define SD_OC_INT_EN		(1 << 22)
+
+#define READ_REG_CMD		0
+#define WRITE_REG_CMD		1
+#define CHECK_REG_CMD		2
+
+/*
+ * macros for easy use
+ */
+#define rtsx_pci_writel(pcr, reg, value) \
+	iowrite32(value, (pcr)->remap_addr + reg)
+#define rtsx_pci_readl(pcr, reg) \
+	ioread32((pcr)->remap_addr + reg)
+#define rtsx_pci_writew(pcr, reg, value) \
+	iowrite16(value, (pcr)->remap_addr + reg)
+#define rtsx_pci_readw(pcr, reg) \
+	ioread16((pcr)->remap_addr + reg)
+#define rtsx_pci_writeb(pcr, reg, value) \
+	iowrite8(value, (pcr)->remap_addr + reg)
+#define rtsx_pci_readb(pcr, reg) \
+	ioread8((pcr)->remap_addr + reg)
+
+#define rtsx_pci_read_config_byte(pcr, where, val) \
+	pci_read_config_byte((pcr)->pci, where, val)
+
+#define rtsx_pci_write_config_byte(pcr, where, val) \
+	pci_write_config_byte((pcr)->pci, where, val)
+
+#define rtsx_pci_read_config_dword(pcr, where, val) \
+	pci_read_config_dword((pcr)->pci, where, val)
+
+#define rtsx_pci_write_config_dword(pcr, where, val) \
+	pci_write_config_dword((pcr)->pci, where, val)
+
+#define STATE_TRANS_NONE	0
+#define STATE_TRANS_CMD		1
+#define STATE_TRANS_BUF		2
+#define STATE_TRANS_SG		3
+
+#define TRANS_NOT_READY		0
+#define TRANS_RESULT_OK		1
+#define TRANS_RESULT_FAIL	2
+#define TRANS_NO_DEVICE		3
+
+#define RTSX_RESV_BUF_LEN	4096
+#define HOST_CMDS_BUF_LEN	1024
+#define HOST_SG_TBL_BUF_LEN	(RTSX_RESV_BUF_LEN - HOST_CMDS_BUF_LEN)
+#define HOST_SG_TBL_ITEMS	(HOST_SG_TBL_BUF_LEN / 8)
+#define MAX_SG_ITEM_LEN		0x80000
+
+#define HOST_TO_DEVICE		0
+#define DEVICE_TO_HOST		1
+
+#define MAX_PHASE		31
+#define RX_TUNING_CNT		3
+
+/* SG descriptor */
+#define SG_INT			0x04
+#define SG_END			0x02
+#define SG_VALID		0x01
+
+#define SG_NO_OP		0x00
+#define SG_TRANS_DATA		(0x02 << 4)
+#define SG_LINK_DESC		(0x03 << 4)
+
+/* SD bank voltage */
+#define SD_IO_3V3		0
+#define SD_IO_1V8		1
+
+
+/* Card Clock Enable Register */
+#define SD_CLK_EN			0x04
+#define MS_CLK_EN			0x08
+
+/* Card Select Register */
+#define SD_MOD_SEL			2
+#define MS_MOD_SEL			3
+
+/* Card Output Enable Register */
+#define SD_OUTPUT_EN			0x04
+#define MS_OUTPUT_EN			0x08
+
+/* CARD_SHARE_MODE */
+#define CARD_SHARE_MASK			0x0F
+#define CARD_SHARE_MULTI_LUN		0x00
+#define	CARD_SHARE_NORMAL		0x00
+#define	CARD_SHARE_48_SD		0x04
+#define	CARD_SHARE_48_MS		0x08
+/* CARD_SHARE_MODE for barossa */
+#define CARD_SHARE_BAROSSA_SD		0x01
+#define CARD_SHARE_BAROSSA_MS		0x02
+
+/* SD30_DRIVE_SEL */
+#define DRIVER_TYPE_A			0x05
+#define DRIVER_TYPE_B			0x03
+#define DRIVER_TYPE_C			0x02
+#define DRIVER_TYPE_D			0x01
+
+/* FPDCTL */
+#define SSC_POWER_DOWN			0x01
+#define SD_OC_POWER_DOWN		0x02
+#define ALL_POWER_DOWN			0x07
+#define OC_POWER_DOWN			0x06
+
+/* CLK_CTL */
+#define CHANGE_CLK			0x01
+
+/* LDO_CTL */
+#define BPP_LDO_POWB			0x03
+#define BPP_LDO_ON			0x00
+#define BPP_LDO_SUSPEND			0x02
+#define BPP_LDO_OFF			0x03
+
+/* CD_PAD_CTL */
+#define CD_DISABLE_MASK			0x07
+#define MS_CD_DISABLE			0x04
+#define SD_CD_DISABLE			0x02
+#define XD_CD_DISABLE			0x01
+#define CD_DISABLE			0x07
+#define CD_ENABLE			0x00
+#define MS_CD_EN_ONLY			0x03
+#define SD_CD_EN_ONLY			0x05
+#define XD_CD_EN_ONLY			0x06
+#define FORCE_CD_LOW_MASK		0x38
+#define FORCE_CD_XD_LOW			0x08
+#define FORCE_CD_SD_LOW			0x10
+#define FORCE_CD_MS_LOW			0x20
+#define CD_AUTO_DISABLE			0x40
+
+/* SD_STAT1 */
+#define	SD_CRC7_ERR			0x80
+#define	SD_CRC16_ERR			0x40
+#define	SD_CRC_WRITE_ERR		0x20
+#define	SD_CRC_WRITE_ERR_MASK		0x1C
+#define	GET_CRC_TIME_OUT		0x02
+#define	SD_TUNING_COMPARE_ERR		0x01
+
+/* SD_STAT2 */
+#define	SD_RSP_80CLK_TIMEOUT		0x01
+
+/* SD_BUS_STAT */
+#define	SD_CLK_TOGGLE_EN		0x80
+#define	SD_CLK_FORCE_STOP	        0x40
+#define	SD_DAT3_STATUS		        0x10
+#define	SD_DAT2_STATUS		        0x08
+#define	SD_DAT1_STATUS		        0x04
+#define	SD_DAT0_STATUS		        0x02
+#define	SD_CMD_STATUS			0x01
+
+/* SD_PAD_CTL */
+#define	SD_IO_USING_1V8		        0x80
+#define	SD_IO_USING_3V3		        0x7F
+#define	TYPE_A_DRIVING		        0x00
+#define	TYPE_B_DRIVING			0x01
+#define	TYPE_C_DRIVING			0x02
+#define	TYPE_D_DRIVING		        0x03
+
+/* SD_SAMPLE_POINT_CTL */
+#define	DDR_FIX_RX_DAT			0x00
+#define	DDR_VAR_RX_DAT			0x80
+#define	DDR_FIX_RX_DAT_EDGE		0x00
+#define	DDR_FIX_RX_DAT_14_DELAY		0x40
+#define	DDR_FIX_RX_CMD			0x00
+#define	DDR_VAR_RX_CMD			0x20
+#define	DDR_FIX_RX_CMD_POS_EDGE		0x00
+#define	DDR_FIX_RX_CMD_14_DELAY		0x10
+#define	SD20_RX_POS_EDGE		0x00
+#define	SD20_RX_14_DELAY		0x08
+#define SD20_RX_SEL_MASK		0x08
+
+/* SD_PUSH_POINT_CTL */
+#define	DDR_FIX_TX_CMD_DAT		0x00
+#define	DDR_VAR_TX_CMD_DAT		0x80
+#define	DDR_FIX_TX_DAT_14_TSU		0x00
+#define	DDR_FIX_TX_DAT_12_TSU		0x40
+#define	DDR_FIX_TX_CMD_NEG_EDGE		0x00
+#define	DDR_FIX_TX_CMD_14_AHEAD		0x20
+#define	SD20_TX_NEG_EDGE		0x00
+#define	SD20_TX_14_AHEAD		0x10
+#define SD20_TX_SEL_MASK		0x10
+#define	DDR_VAR_SDCLK_POL_SWAP		0x01
+
+/* SD_TRANSFER */
+#define	SD_TRANSFER_START		0x80
+#define	SD_TRANSFER_END			0x40
+#define SD_STAT_IDLE			0x20
+#define	SD_TRANSFER_ERR			0x10
+/* SD Transfer Mode definition */
+#define	SD_TM_NORMAL_WRITE		0x00
+#define	SD_TM_AUTO_WRITE_3		0x01
+#define	SD_TM_AUTO_WRITE_4		0x02
+#define	SD_TM_AUTO_READ_3		0x05
+#define	SD_TM_AUTO_READ_4		0x06
+#define	SD_TM_CMD_RSP			0x08
+#define	SD_TM_AUTO_WRITE_1		0x09
+#define	SD_TM_AUTO_WRITE_2		0x0A
+#define	SD_TM_NORMAL_READ		0x0C
+#define	SD_TM_AUTO_READ_1		0x0D
+#define	SD_TM_AUTO_READ_2		0x0E
+#define	SD_TM_AUTO_TUNING		0x0F
+
+/* SD_VPTX_CTL / SD_VPRX_CTL */
+#define PHASE_CHANGE			0x80
+#define PHASE_NOT_RESET			0x40
+
+/* SD_DCMPS_TX_CTL / SD_DCMPS_RX_CTL */
+#define DCMPS_CHANGE			0x80
+#define DCMPS_CHANGE_DONE		0x40
+#define DCMPS_ERROR			0x20
+#define DCMPS_CURRENT_PHASE		0x1F
+
+/* SD Configure 1 Register */
+#define SD_CLK_DIVIDE_0			0x00
+#define	SD_CLK_DIVIDE_256		0xC0
+#define	SD_CLK_DIVIDE_128		0x80
+#define	SD_BUS_WIDTH_1BIT		0x00
+#define	SD_BUS_WIDTH_4BIT		0x01
+#define	SD_BUS_WIDTH_8BIT		0x02
+#define	SD_ASYNC_FIFO_NOT_RST		0x10
+#define	SD_20_MODE			0x00
+#define	SD_DDR_MODE			0x04
+#define	SD_30_MODE			0x08
+
+#define SD_CLK_DIVIDE_MASK		0xC0
+
+/* SD_CMD_STATE */
+#define SD_CMD_IDLE			0x80
+
+/* SD_DATA_STATE */
+#define SD_DATA_IDLE			0x80
+
+/* DCM_DRP_CTL */
+#define DCM_RESET			0x08
+#define DCM_LOCKED			0x04
+#define DCM_208M			0x00
+#define DCM_TX			        0x01
+#define DCM_RX			        0x02
+
+/* DCM_DRP_TRIG */
+#define DRP_START			0x80
+#define DRP_DONE			0x40
+
+/* DCM_DRP_CFG */
+#define DRP_WRITE			0x80
+#define DRP_READ			0x00
+#define DCM_WRITE_ADDRESS_50		0x50
+#define DCM_WRITE_ADDRESS_51		0x51
+#define DCM_READ_ADDRESS_00		0x00
+#define DCM_READ_ADDRESS_51		0x51
+
+/* IRQSTAT0 */
+#define DMA_DONE_INT			0x80
+#define SUSPEND_INT			0x40
+#define LINK_RDY_INT			0x20
+#define LINK_DOWN_INT			0x10
+
+/* DMACTL */
+#define DMA_RST				0x80
+#define DMA_BUSY			0x04
+#define DMA_DIR_TO_CARD			0x00
+#define DMA_DIR_FROM_CARD		0x02
+#define DMA_EN				0x01
+#define DMA_128				(0 << 4)
+#define DMA_256				(1 << 4)
+#define DMA_512				(2 << 4)
+#define DMA_1024			(3 << 4)
+#define DMA_PACK_SIZE_MASK		0x30
+
+/* SSC_CTL1 */
+#define SSC_RSTB			0x80
+#define SSC_8X_EN			0x40
+#define SSC_FIX_FRAC			0x20
+#define SSC_SEL_1M			0x00
+#define SSC_SEL_2M			0x08
+#define SSC_SEL_4M			0x10
+#define SSC_SEL_8M			0x18
+
+/* SSC_CTL2 */
+#define SSC_DEPTH_MASK			0x07
+#define SSC_DEPTH_DISALBE		0x00
+#define SSC_DEPTH_4M			0x01
+#define SSC_DEPTH_2M			0x02
+#define SSC_DEPTH_1M			0x03
+#define SSC_DEPTH_500K			0x04
+#define SSC_DEPTH_250K			0x05
+
+/* System Clock Control Register */
+#define CLK_LOW_FREQ			0x01
+
+/* System Clock Divider Register */
+#define CLK_DIV_1			0x01
+#define CLK_DIV_2			0x02
+#define CLK_DIV_4			0x03
+#define CLK_DIV_8			0x04
+
+/* MS_CFG */
+#define	SAMPLE_TIME_RISING		0x00
+#define	SAMPLE_TIME_FALLING		0x80
+#define	PUSH_TIME_DEFAULT		0x00
+#define	PUSH_TIME_ODD			0x40
+#define	NO_EXTEND_TOGGLE		0x00
+#define	EXTEND_TOGGLE_CHK		0x20
+#define	MS_BUS_WIDTH_1			0x00
+#define	MS_BUS_WIDTH_4			0x10
+#define	MS_BUS_WIDTH_8			0x18
+#define	MS_2K_SECTOR_MODE		0x04
+#define	MS_512_SECTOR_MODE		0x00
+#define	MS_TOGGLE_TIMEOUT_EN		0x00
+#define	MS_TOGGLE_TIMEOUT_DISEN		0x01
+#define MS_NO_CHECK_INT			0x02
+
+/* MS_TRANS_CFG */
+#define	WAIT_INT			0x80
+#define	NO_WAIT_INT			0x00
+#define	NO_AUTO_READ_INT_REG		0x00
+#define	AUTO_READ_INT_REG		0x40
+#define	MS_CRC16_ERR			0x20
+#define	MS_RDY_TIMEOUT			0x10
+#define	MS_INT_CMDNK			0x08
+#define	MS_INT_BREQ			0x04
+#define	MS_INT_ERR			0x02
+#define	MS_INT_CED			0x01
+
+/* MS_TRANSFER */
+#define	MS_TRANSFER_START		0x80
+#define	MS_TRANSFER_END			0x40
+#define	MS_TRANSFER_ERR			0x20
+#define	MS_BS_STATE			0x10
+#define	MS_TM_READ_BYTES		0x00
+#define	MS_TM_NORMAL_READ		0x01
+#define	MS_TM_WRITE_BYTES		0x04
+#define	MS_TM_NORMAL_WRITE		0x05
+#define	MS_TM_AUTO_READ			0x08
+#define	MS_TM_AUTO_WRITE		0x0C
+
+/* SD Configure 2 Register */
+#define	SD_CALCULATE_CRC7		0x00
+#define	SD_NO_CALCULATE_CRC7		0x80
+#define	SD_CHECK_CRC16			0x00
+#define	SD_NO_CHECK_CRC16		0x40
+#define SD_NO_CHECK_WAIT_CRC_TO		0x20
+#define	SD_WAIT_BUSY_END		0x08
+#define	SD_NO_WAIT_BUSY_END		0x00
+#define	SD_CHECK_CRC7			0x00
+#define	SD_NO_CHECK_CRC7		0x04
+#define	SD_RSP_LEN_0			0x00
+#define	SD_RSP_LEN_6			0x01
+#define	SD_RSP_LEN_17			0x02
+/* SD/MMC Response Type Definition */
+#define	SD_RSP_TYPE_R0			0x04
+#define	SD_RSP_TYPE_R1			0x01
+#define	SD_RSP_TYPE_R1b			0x09
+#define	SD_RSP_TYPE_R2			0x02
+#define	SD_RSP_TYPE_R3			0x05
+#define	SD_RSP_TYPE_R4			0x05
+#define	SD_RSP_TYPE_R5			0x01
+#define	SD_RSP_TYPE_R6			0x01
+#define	SD_RSP_TYPE_R7			0x01
+
+/* SD_CONFIURE3 */
+#define	SD_RSP_80CLK_TIMEOUT_EN		0x01
+
+/* Card Transfer Reset Register */
+#define SPI_STOP			0x01
+#define XD_STOP				0x02
+#define SD_STOP				0x04
+#define MS_STOP				0x08
+#define SPI_CLR_ERR			0x10
+#define XD_CLR_ERR			0x20
+#define SD_CLR_ERR			0x40
+#define MS_CLR_ERR			0x80
+
+/* Card Data Source Register */
+#define PINGPONG_BUFFER			0x01
+#define RING_BUFFER			0x00
+
+/* Card Power Control Register */
+#define PMOS_STRG_MASK			0x10
+#define PMOS_STRG_800mA			0x10
+#define PMOS_STRG_400mA			0x00
+#define SD_POWER_OFF			0x03
+#define SD_PARTIAL_POWER_ON		0x01
+#define SD_POWER_ON			0x00
+#define SD_POWER_MASK			0x03
+#define MS_POWER_OFF			0x0C
+#define MS_PARTIAL_POWER_ON		0x04
+#define MS_POWER_ON			0x00
+#define MS_POWER_MASK			0x0C
+#define BPP_POWER_OFF			0x0F
+#define BPP_POWER_5_PERCENT_ON		0x0E
+#define BPP_POWER_10_PERCENT_ON		0x0C
+#define BPP_POWER_15_PERCENT_ON		0x08
+#define BPP_POWER_ON			0x00
+#define BPP_POWER_MASK			0x0F
+
+/* PWR_GATE_CTRL */
+#define PWR_GATE_EN			0x01
+#define LDO3318_PWR_MASK		0x06
+#define LDO_ON				0x00
+#define LDO_SUSPEND			0x04
+#define LDO_OFF				0x06
+
+/* CARD_CLK_SOURCE */
+#define CRC_FIX_CLK			(0x00 << 0)
+#define CRC_VAR_CLK0			(0x01 << 0)
+#define CRC_VAR_CLK1			(0x02 << 0)
+#define SD30_FIX_CLK			(0x00 << 2)
+#define SD30_VAR_CLK0			(0x01 << 2)
+#define SD30_VAR_CLK1			(0x02 << 2)
+#define SAMPLE_FIX_CLK			(0x00 << 4)
+#define SAMPLE_VAR_CLK0			(0x01 << 4)
+#define SAMPLE_VAR_CLK1			(0x02 << 4)
+
+#define MS_CFG				0xFD40
+#define MS_TPC				0xFD41
+#define MS_TRANS_CFG			0xFD42
+#define MS_TRANSFER			0xFD43
+#define MS_INT_REG			0xFD44
+#define MS_BYTE_CNT			0xFD45
+#define MS_SECTOR_CNT_L			0xFD46
+#define MS_SECTOR_CNT_H			0xFD47
+#define MS_DBUS_H			0xFD48
+
+#define SD_CFG1				0xFDA0
+#define SD_CFG2				0xFDA1
+#define SD_CFG3				0xFDA2
+#define SD_STAT1			0xFDA3
+#define SD_STAT2			0xFDA4
+#define SD_BUS_STAT			0xFDA5
+#define SD_PAD_CTL			0xFDA6
+#define SD_SAMPLE_POINT_CTL		0xFDA7
+#define SD_PUSH_POINT_CTL		0xFDA8
+#define SD_CMD0				0xFDA9
+#define SD_CMD1				0xFDAA
+#define SD_CMD2				0xFDAB
+#define SD_CMD3				0xFDAC
+#define SD_CMD4				0xFDAD
+#define SD_CMD5				0xFDAE
+#define SD_BYTE_CNT_L			0xFDAF
+#define SD_BYTE_CNT_H			0xFDB0
+#define SD_BLOCK_CNT_L			0xFDB1
+#define SD_BLOCK_CNT_H			0xFDB2
+#define SD_TRANSFER			0xFDB3
+#define SD_CMD_STATE			0xFDB5
+#define SD_DATA_STATE			0xFDB6
+
+#define SRCTL				0xFC13
+
+#define	DCM_DRP_CTL			0xFC23
+#define	DCM_DRP_TRIG			0xFC24
+#define	DCM_DRP_CFG			0xFC25
+#define	DCM_DRP_WR_DATA_L		0xFC26
+#define	DCM_DRP_WR_DATA_H		0xFC27
+#define	DCM_DRP_RD_DATA_L		0xFC28
+#define	DCM_DRP_RD_DATA_H		0xFC29
+#define SD_VPCLK0_CTL			0xFC2A
+#define SD_VPCLK1_CTL			0xFC2B
+#define SD_DCMPS0_CTL			0xFC2C
+#define SD_DCMPS1_CTL			0xFC2D
+#define SD_VPTX_CTL			SD_VPCLK0_CTL
+#define SD_VPRX_CTL			SD_VPCLK1_CTL
+#define SD_DCMPS_TX_CTL			SD_DCMPS0_CTL
+#define SD_DCMPS_RX_CTL			SD_DCMPS1_CTL
+#define CARD_CLK_SOURCE			0xFC2E
+
+#define CARD_PWR_CTL			0xFD50
+#define CARD_CLK_SWITCH			0xFD51
+#define CARD_SHARE_MODE			0xFD52
+#define CARD_DRIVE_SEL			0xFD53
+#define CARD_STOP			0xFD54
+#define CARD_OE				0xFD55
+#define CARD_AUTO_BLINK			0xFD56
+#define CARD_GPIO_DIR			0xFD57
+#define CARD_GPIO			0xFD58
+#define CARD_DATA_SOURCE		0xFD5B
+#define CARD_SELECT			0xFD5C
+#define SD30_DRIVE_SEL			0xFD5E
+#define CARD_CLK_EN			0xFD69
+#define SDIO_CTRL			0xFD6B
+#define CD_PAD_CTL			0xFD73
+
+#define FPDCTL				0xFC00
+#define PDINFO				0xFC01
+
+#define CLK_CTL				0xFC02
+#define CLK_DIV				0xFC03
+#define CLK_SEL				0xFC04
+
+#define SSC_DIV_N_0			0xFC0F
+#define SSC_DIV_N_1			0xFC10
+#define SSC_CTL1			0xFC11
+#define SSC_CTL2			0xFC12
+
+#define RCCTL				0xFC14
+
+#define FPGA_PULL_CTL			0xFC1D
+#define OLT_LED_CTL			0xFC1E
+#define GPIO_CTL			0xFC1F
+
+#define LDO_CTL				0xFC1E
+#define SYS_VER				0xFC32
+
+#define CARD_PULL_CTL1			0xFD60
+#define CARD_PULL_CTL2			0xFD61
+#define CARD_PULL_CTL3			0xFD62
+#define CARD_PULL_CTL4			0xFD63
+#define CARD_PULL_CTL5			0xFD64
+#define CARD_PULL_CTL6			0xFD65
+
+/* PCI Express Related Registers */
+#define IRQEN0				0xFE20
+#define IRQSTAT0			0xFE21
+#define IRQEN1				0xFE22
+#define IRQSTAT1			0xFE23
+#define TLPRIEN				0xFE24
+#define TLPRISTAT			0xFE25
+#define TLPTIEN				0xFE26
+#define TLPTISTAT			0xFE27
+#define DMATC0				0xFE28
+#define DMATC1				0xFE29
+#define DMATC2				0xFE2A
+#define DMATC3				0xFE2B
+#define DMACTL				0xFE2C
+#define BCTL				0xFE2D
+#define RBBC0				0xFE2E
+#define RBBC1				0xFE2F
+#define RBDAT				0xFE30
+#define RBCTL				0xFE34
+#define CFGADDR0			0xFE35
+#define CFGADDR1			0xFE36
+#define CFGDATA0			0xFE37
+#define CFGDATA1			0xFE38
+#define CFGDATA2			0xFE39
+#define CFGDATA3			0xFE3A
+#define CFGRWCTL			0xFE3B
+#define PHYRWCTL			0xFE3C
+#define PHYDATA0			0xFE3D
+#define PHYDATA1			0xFE3E
+#define PHYADDR				0xFE3F
+#define MSGRXDATA0			0xFE40
+#define MSGRXDATA1			0xFE41
+#define MSGRXDATA2			0xFE42
+#define MSGRXDATA3			0xFE43
+#define MSGTXDATA0			0xFE44
+#define MSGTXDATA1			0xFE45
+#define MSGTXDATA2			0xFE46
+#define MSGTXDATA3			0xFE47
+#define MSGTXCTL			0xFE48
+#define PETXCFG				0xFE49
+
+#define CDRESUMECTL			0xFE52
+#define WAKE_SEL_CTL			0xFE54
+#define PME_FORCE_CTL			0xFE56
+#define ASPM_FORCE_CTL			0xFE57
+#define PM_CLK_FORCE_CTL		0xFE58
+#define PERST_GLITCH_WIDTH		0xFE5C
+#define CHANGE_LINK_STATE		0xFE5B
+#define RESET_LOAD_REG			0xFE5E
+#define EFUSE_CONTENT			0xFE5F
+#define HOST_SLEEP_STATE		0xFE60
+#define SDIO_CFG			0xFE70
+
+#define NFTS_TX_CTRL			0xFE72
+
+#define PWR_GATE_CTRL			0xFE75
+#define PWD_SUSPEND_EN			0xFE76
+#define LDO_PWR_SEL			0xFE78
+
+#define DUMMY_REG_RESET_0		0xFE90
+
+/* Memory mapping */
+#define SRAM_BASE			0xE600
+#define RBUF_BASE			0xF400
+#define PPBUF_BASE1			0xF800
+#define PPBUF_BASE2			0xFA00
+#define IMAGE_FLAG_ADDR0		0xCE80
+#define IMAGE_FLAG_ADDR1		0xCE81
+
+#define rtsx_pci_init_cmd(pcr)		((pcr)->ci = 0)
+
+struct rtsx_pcr;
+
+struct pcr_handle {
+	struct rtsx_pcr			*pcr;
+};
+
+struct pcr_ops {
+	int		(*extra_init_hw)(struct rtsx_pcr *pcr);
+	int		(*optimize_phy)(struct rtsx_pcr *pcr);
+	int		(*turn_on_led)(struct rtsx_pcr *pcr);
+	int		(*turn_off_led)(struct rtsx_pcr *pcr);
+	int		(*enable_auto_blink)(struct rtsx_pcr *pcr);
+	int		(*disable_auto_blink)(struct rtsx_pcr *pcr);
+	int		(*card_power_on)(struct rtsx_pcr *pcr, int card);
+	int		(*card_power_off)(struct rtsx_pcr *pcr, int card);
+	unsigned int	(*cd_deglitch)(struct rtsx_pcr *pcr);
+};
+
+enum PDEV_STAT  {PDEV_STAT_IDLE, PDEV_STAT_RUN};
+
+struct rtsx_pcr {
+	struct pci_dev			*pci;
+	unsigned int			id;
+
+	/* pci resources */
+	unsigned long			addr;
+	void __iomem			*remap_addr;
+	int				irq;
+
+	/* host reserved buffer */
+	void				*rtsx_resv_buf;
+	dma_addr_t			rtsx_resv_buf_addr;
+
+	void				*host_cmds_ptr;
+	dma_addr_t			host_cmds_addr;
+	int				ci;
+
+	void				*host_sg_tbl_ptr;
+	dma_addr_t			host_sg_tbl_addr;
+	int				sgi;
+
+	u32				bier;
+	char				trans_result;
+
+	unsigned int			card_inserted;
+	unsigned int			card_removed;
+
+	struct delayed_work		carddet_work;
+	struct delayed_work		idle_work;
+
+	spinlock_t			lock;
+	struct mutex			pcr_mutex;
+	struct completion		*done;
+	struct completion		*finish_me;
+
+	unsigned int			cur_clock;
+	bool				ms_pmos;
+	bool				remove_pci;
+	bool				msi_en;
+
+#define EXTRA_CAPS_SD_SDR50		(1 << 0)
+#define EXTRA_CAPS_SD_SDR104		(1 << 1)
+#define EXTRA_CAPS_SD_DDR50		(1 << 2)
+#define EXTRA_CAPS_MMC_HSDDR		(1 << 3)
+#define EXTRA_CAPS_MMC_HS200		(1 << 4)
+#define EXTRA_CAPS_MMC_8BIT		(1 << 5)
+	u32				extra_caps;
+
+#define IC_VER_A			0
+#define IC_VER_B			1
+#define IC_VER_C			2
+#define IC_VER_D			3
+	u8				ic_version;
+
+	const u32			*sd_pull_ctl_enable_tbl;
+	const u32			*sd_pull_ctl_disable_tbl;
+	const u32			*ms_pull_ctl_enable_tbl;
+	const u32			*ms_pull_ctl_disable_tbl;
+
+	const struct pcr_ops		*ops;
+	enum PDEV_STAT			state;
+
+	int				num_slots;
+	struct rtsx_slot		*slots;
+};
+
+#define CHK_PCI_PID(pcr, pid)		((pcr)->pci->device == (pid))
+#define PCI_VID(pcr)			((pcr)->pci->vendor)
+#define PCI_PID(pcr)			((pcr)->pci->device)
+
+void rtsx_pci_start_run(struct rtsx_pcr *pcr);
+int rtsx_pci_write_register(struct rtsx_pcr *pcr, u16 addr, u8 mask, u8 data);
+int rtsx_pci_read_register(struct rtsx_pcr *pcr, u16 addr, u8 *data);
+int rtsx_pci_write_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 val);
+int rtsx_pci_read_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 *val);
+void rtsx_pci_stop_cmd(struct rtsx_pcr *pcr);
+void rtsx_pci_add_cmd(struct rtsx_pcr *pcr,
+		u8 cmd_type, u16 reg_addr, u8 mask, u8 data);
+void rtsx_pci_send_cmd_no_wait(struct rtsx_pcr *pcr);
+int rtsx_pci_send_cmd(struct rtsx_pcr *pcr, int timeout);
+int rtsx_pci_transfer_data(struct rtsx_pcr *pcr, struct scatterlist *sglist,
+		int num_sg, bool read, int timeout);
+int rtsx_pci_read_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len);
+int rtsx_pci_write_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len);
+int rtsx_pci_card_pull_ctl_enable(struct rtsx_pcr *pcr, int card);
+int rtsx_pci_card_pull_ctl_disable(struct rtsx_pcr *pcr, int card);
+int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk);
+int rtsx_pci_card_power_on(struct rtsx_pcr *pcr, int card);
+int rtsx_pci_card_power_off(struct rtsx_pcr *pcr, int card);
+unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr);
+void rtsx_pci_complete_unfinished_transfer(struct rtsx_pcr *pcr);
+
+static inline u8 *rtsx_pci_get_cmd_data(struct rtsx_pcr *pcr)
+{
+	return (u8 *)(pcr->host_cmds_ptr);
+}
+
+#endif
-- 
cgit v1.2.3-55-g7522


From f399002e68e626e7bc443e6fcab1772704cc197f Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Wed, 23 Mar 2011 14:31:09 +0100
Subject: drbd: distribute former syncer_conf settings to disk, connection, and
 resource level

This commit breaks the API again.

Move per-volume former syncer options into disk_conf.
Move per-connection former syncer options into net_conf.
Renamed the remainign sync_conf to res_opts

Syncer settings have been changeable at runtime, so we need to prepare
for these settings to be runtime-changeable in their new home as well.

Introduce new configuration operations, and share the netlink attribute
between "attach" (create new disk) and "disk-opts" (change options).
Same for "connect" and "net-opts".

Some fields cannot be changed at runtime, however.
Introduce a new flag GENLA_F_INVARIANT to be able to trigger on that in
the generated validation and assignment functions.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h      |  10 +-
 drivers/block/drbd/drbd_main.c     |  72 +++--
 drivers/block/drbd/drbd_nl.c       | 550 ++++++++++++++++++++++++-------------
 drivers/block/drbd/drbd_receiver.c |  51 ++--
 drivers/block/drbd/drbd_state.c    |   4 +-
 drivers/block/drbd/drbd_worker.c   |  50 ++--
 include/linux/drbd_genl.h          | 133 +++++----
 include/linux/drbd_limits.h        |   2 +
 include/linux/genl_magic_func.h    |  49 ++--
 include/linux/genl_magic_struct.h  |  18 +-
 10 files changed, 572 insertions(+), 367 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index d6e7e657e7a4..bc265f3733c6 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -860,7 +860,7 @@ struct drbd_md {
 	s32 bm_offset;	/* signed relative sector offset to bitmap */
 
 	/* u32 al_nr_extents;	   important for restoring the AL
-	 * is stored into  sync_conf.al_extents, which in turn
+	 * is stored into  ldev->dc.al_extents, which in turn
 	 * gets applied to act_log->nr_elements
 	 */
 };
@@ -929,6 +929,7 @@ struct drbd_tconn {			/* is a resource from the config file */
 	atomic_t net_cnt;		/* Users of net_conf */
 	wait_queue_head_t net_cnt_wait;
 	wait_queue_head_t ping_wait;		/* Woken upon reception of a ping, and a state change */
+	struct res_opts res_opts;
 
 	struct drbd_socket data;	/* data/barrier/cstate/parameter packets */
 	struct drbd_socket meta;	/* ping/ack (metadata) packets */
@@ -945,6 +946,8 @@ struct drbd_tconn {			/* is a resource from the config file */
 	struct crypto_hash *cram_hmac_tfm;
 	struct crypto_hash *integrity_w_tfm; /* to be used by the worker thread */
 	struct crypto_hash *integrity_r_tfm; /* to be used by the receiver thread */
+	struct crypto_hash *csums_tfm;
+	struct crypto_hash *verify_tfm;
 	void *int_dig_out;
 	void *int_dig_in;
 	void *int_dig_vv;
@@ -963,7 +966,6 @@ struct drbd_conf {
 	unsigned long flags;
 
 	/* configured by drbdsetup */
-	struct syncer_conf sync_conf;
 	struct drbd_backing_dev *ldev __protected_by(local);
 
 	sector_t p_size;     /* partner's disk size */
@@ -1037,8 +1039,6 @@ struct drbd_conf {
 	/* size of out-of-sync range in sectors. */
 	sector_t ov_last_oos_size;
 	unsigned long ov_left; /* in bits */
-	struct crypto_hash *csums_tfm;
-	struct crypto_hash *verify_tfm;
 
 	struct drbd_bitmap *bitmap;
 	unsigned long bm_resync_fo; /* bit offset for drbd_bm_find_next */
@@ -1188,7 +1188,7 @@ extern int conn_send_cmd2(struct drbd_tconn *tconn, enum drbd_packet cmd,
 			  char *data, size_t size);
 #define USE_DATA_SOCKET 1
 #define USE_META_SOCKET 0
-extern int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc);
+extern int drbd_send_sync_param(struct drbd_conf *mdev);
 extern int drbd_send_b_ack(struct drbd_conf *mdev, u32 barrier_nr,
 			u32 set_size);
 extern int drbd_send_ack(struct drbd_conf *, enum drbd_packet,
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 79a0e042252f..bdb12723585e 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -784,7 +784,7 @@ int conn_send_cmd2(struct drbd_tconn *tconn, enum drbd_packet cmd, char *data,
 	return ok;
 }
 
-int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc)
+int drbd_send_sync_param(struct drbd_conf *mdev)
 {
 	struct p_rs_param_95 *p;
 	struct socket *sock;
@@ -793,7 +793,7 @@ int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc)
 
 	size = apv <= 87 ? sizeof(struct p_rs_param)
 		: apv == 88 ? sizeof(struct p_rs_param)
-			+ strlen(mdev->sync_conf.verify_alg) + 1
+			+ strlen(mdev->tconn->net_conf->verify_alg) + 1
 		: apv <= 94 ? sizeof(struct p_rs_param_89)
 		: /* apv >= 95 */ sizeof(struct p_rs_param_95);
 
@@ -812,16 +812,25 @@ int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc)
 		/* initialize verify_alg and csums_alg */
 		memset(p->verify_alg, 0, 2 * SHARED_SECRET_MAX);
 
-		p->rate = cpu_to_be32(sc->rate);
-		p->c_plan_ahead = cpu_to_be32(sc->c_plan_ahead);
-		p->c_delay_target = cpu_to_be32(sc->c_delay_target);
-		p->c_fill_target = cpu_to_be32(sc->c_fill_target);
-		p->c_max_rate = cpu_to_be32(sc->c_max_rate);
+		if (get_ldev(mdev)) {
+			p->rate = cpu_to_be32(mdev->ldev->dc.resync_rate);
+			p->c_plan_ahead = cpu_to_be32(mdev->ldev->dc.c_plan_ahead);
+			p->c_delay_target = cpu_to_be32(mdev->ldev->dc.c_delay_target);
+			p->c_fill_target = cpu_to_be32(mdev->ldev->dc.c_fill_target);
+			p->c_max_rate = cpu_to_be32(mdev->ldev->dc.c_max_rate);
+			put_ldev(mdev);
+		} else {
+			p->rate = cpu_to_be32(DRBD_RATE_DEF);
+			p->c_plan_ahead = cpu_to_be32(DRBD_C_PLAN_AHEAD_DEF);
+			p->c_delay_target = cpu_to_be32(DRBD_C_DELAY_TARGET_DEF);
+			p->c_fill_target = cpu_to_be32(DRBD_C_FILL_TARGET_DEF);
+			p->c_max_rate = cpu_to_be32(DRBD_C_MAX_RATE_DEF);
+		}
 
 		if (apv >= 88)
-			strcpy(p->verify_alg, mdev->sync_conf.verify_alg);
+			strcpy(p->verify_alg, mdev->tconn->net_conf->verify_alg);
 		if (apv >= 89)
-			strcpy(p->csums_alg, mdev->sync_conf.csums_alg);
+			strcpy(p->csums_alg, mdev->tconn->net_conf->csums_alg);
 
 		rv = _drbd_send_cmd(mdev, sock, cmd, &p->head, size, 0);
 	} else
@@ -1043,7 +1052,7 @@ int fill_bitmap_rle_bits(struct drbd_conf *mdev,
 	int bits;
 
 	/* may we use this feature? */
-	if ((mdev->sync_conf.use_rle == 0) ||
+	if ((mdev->tconn->net_conf->use_rle == 0) ||
 		(mdev->tconn->agreed_pro_version < 90))
 			return 0;
 
@@ -1790,26 +1799,8 @@ static int drbd_release(struct gendisk *gd, fmode_t mode)
 
 static void drbd_set_defaults(struct drbd_conf *mdev)
 {
-	/* This way we get a compile error when sync_conf grows,
-	   and we forgot to initialize it here */
-	mdev->sync_conf = (struct syncer_conf) {
-		/* .rate = */		DRBD_RATE_DEF,
-		/* .after = */		DRBD_AFTER_DEF,
-		/* .al_extents = */	DRBD_AL_EXTENTS_DEF,
-		/* .verify_alg = */	{}, 0,
-		/* .cpu_mask = */	{}, 0,
-		/* .csums_alg = */	{}, 0,
-		/* .use_rle = */	0,
-		/* .on_no_data = */	DRBD_ON_NO_DATA_DEF,
-		/* .c_plan_ahead = */	DRBD_C_PLAN_AHEAD_DEF,
-		/* .c_delay_target = */	DRBD_C_DELAY_TARGET_DEF,
-		/* .c_fill_target = */	DRBD_C_FILL_TARGET_DEF,
-		/* .c_max_rate = */	DRBD_C_MAX_RATE_DEF,
-		/* .c_min_rate = */	DRBD_C_MIN_RATE_DEF
-	};
-
-	/* Have to use that way, because the layout differs between
-	   big endian and little endian */
+	/* Beware! The actual layout differs
+	 * between big endian and little endian */
 	mdev->state = (union drbd_state) {
 		{ .role = R_SECONDARY,
 		  .peer = R_UNKNOWN,
@@ -2286,6 +2277,11 @@ struct drbd_tconn *drbd_new_tconn(const char *name)
 	drbd_thread_init(tconn, &tconn->worker, drbd_worker, "worker");
 	drbd_thread_init(tconn, &tconn->asender, drbd_asender, "asender");
 
+	tconn->res_opts = (struct res_opts) {
+		{}, 0, /* cpu_mask */
+		DRBD_ON_NO_DATA_DEF, /* on_no_data */
+	};
+
 	mutex_lock(&drbd_cfg_mutex);
 	list_add_tail(&tconn->all_tconn, &drbd_tconns);
 	mutex_unlock(&drbd_cfg_mutex);
@@ -2559,10 +2555,10 @@ void drbd_free_sock(struct drbd_tconn *tconn)
 
 void drbd_free_resources(struct drbd_conf *mdev)
 {
-	crypto_free_hash(mdev->csums_tfm);
-	mdev->csums_tfm = NULL;
-	crypto_free_hash(mdev->verify_tfm);
-	mdev->verify_tfm = NULL;
+	crypto_free_hash(mdev->tconn->csums_tfm);
+	mdev->tconn->csums_tfm = NULL;
+	crypto_free_hash(mdev->tconn->verify_tfm);
+	mdev->tconn->verify_tfm = NULL;
 	crypto_free_hash(mdev->tconn->cram_hmac_tfm);
 	mdev->tconn->cram_hmac_tfm = NULL;
 	crypto_free_hash(mdev->tconn->integrity_w_tfm);
@@ -2589,7 +2585,7 @@ struct meta_data_on_disk {
 	u32 md_size_sect;
 	u32 al_offset;         /* offset to this block */
 	u32 al_nr_extents;     /* important for restoring the AL */
-	      /* `-- act_log->nr_elements <-- sync_conf.al_extents */
+	      /* `-- act_log->nr_elements <-- ldev->dc.al_extents */
 	u32 bm_offset;         /* offset to the bitmap, from here */
 	u32 bm_bytes_per_bit;  /* BM_BLOCK_SIZE */
 	u32 la_peer_max_bio_size;   /* last peer max_bio_size */
@@ -2715,7 +2711,7 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 	for (i = UI_CURRENT; i < UI_SIZE; i++)
 		bdev->md.uuid[i] = be64_to_cpu(buffer->uuid[i]);
 	bdev->md.flags = be32_to_cpu(buffer->flags);
-	mdev->sync_conf.al_extents = be32_to_cpu(buffer->al_nr_extents);
+	bdev->dc.al_extents = be32_to_cpu(buffer->al_nr_extents);
 	bdev->md.device_uuid = be64_to_cpu(buffer->device_uuid);
 
 	spin_lock_irq(&mdev->tconn->req_lock);
@@ -2727,8 +2723,8 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 	}
 	spin_unlock_irq(&mdev->tconn->req_lock);
 
-	if (mdev->sync_conf.al_extents < 7)
-		mdev->sync_conf.al_extents = 127;
+	if (bdev->dc.al_extents < 7)
+		bdev->dc.al_extents = 127;
 
  err:
 	mutex_unlock(&mdev->md_io_mutex);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index ac0a175e778c..18cd2ed4e8ca 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -53,8 +53,10 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info);
 
 int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info);
@@ -66,7 +68,7 @@ int drbd_adm_resume_sync(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_suspend_io(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_outdate(struct sk_buff *skb, struct genl_info *info);
-int drbd_adm_syncer(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info);
 /* .dumpit */
@@ -170,7 +172,7 @@ static int drbd_adm_prepare(struct sk_buff *skb, struct genl_info *info,
 	if (info->attrs[DRBD_NLA_CFG_CONTEXT]) {
 		struct nlattr *nla;
 		/* parse and validate only */
-		err = drbd_cfg_context_from_attrs(NULL, info->attrs);
+		err = drbd_cfg_context_from_attrs(NULL, info);
 		if (err)
 			goto fail;
 
@@ -616,6 +618,7 @@ static const char *from_attrs_err_to_txt(int err)
 {
 	return	err == -ENOMSG ? "required attribute missing" :
 		err == -EOPNOTSUPP ? "unknown mandatory attribute" :
+		err == -EEXIST ? "can not change invariant setting" :
 		"invalid attribute value";
 }
 
@@ -633,7 +636,7 @@ int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info)
 
 	memset(&parms, 0, sizeof(parms));
 	if (info->attrs[DRBD_NLA_SET_ROLE_PARMS]) {
-		err = set_role_parms_from_attrs(&parms, info->attrs);
+		err = set_role_parms_from_attrs(&parms, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
 			drbd_msg_put_info(from_attrs_err_to_txt(err));
@@ -898,24 +901,24 @@ drbd_new_dev_size(struct drbd_conf *mdev, struct drbd_backing_dev *bdev, int ass
  * failed, and 0 on success. You should call drbd_md_sync() after you called
  * this function.
  */
-static int drbd_check_al_size(struct drbd_conf *mdev)
+static int drbd_check_al_size(struct drbd_conf *mdev, struct disk_conf *dc)
 {
 	struct lru_cache *n, *t;
 	struct lc_element *e;
 	unsigned int in_use;
 	int i;
 
-	if (!expect(mdev->sync_conf.al_extents >= DRBD_AL_EXTENTS_MIN))
-		mdev->sync_conf.al_extents = DRBD_AL_EXTENTS_MIN;
+	if (!expect(dc->al_extents >= DRBD_AL_EXTENTS_MIN))
+		dc->al_extents = DRBD_AL_EXTENTS_MIN;
 
 	if (mdev->act_log &&
-	    mdev->act_log->nr_elements == mdev->sync_conf.al_extents)
+	    mdev->act_log->nr_elements == dc->al_extents)
 		return 0;
 
 	in_use = 0;
 	t = mdev->act_log;
 	n = lc_create("act_log", drbd_al_ext_cache, AL_UPDATES_PER_TRANSACTION,
-		mdev->sync_conf.al_extents, sizeof(struct lc_element), 0);
+		dc->al_extents, sizeof(struct lc_element), 0);
 
 	if (n == NULL) {
 		dev_err(DEV, "Cannot allocate act_log lru!\n");
@@ -1069,6 +1072,114 @@ static void drbd_suspend_al(struct drbd_conf *mdev)
 		dev_info(DEV, "Suspended AL updates\n");
 }
 
+int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
+{
+	enum drbd_ret_code retcode;
+	struct drbd_conf *mdev;
+	struct disk_conf *ndc; /* new disk conf */
+	int err, fifo_size;
+	int *rs_plan_s = NULL;
+
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
+
+	mdev = adm_ctx.mdev;
+
+	/* we also need a disk
+	 * to change the options on */
+	if (!get_ldev(mdev)) {
+		retcode = ERR_NO_DISK;
+		goto out;
+	}
+
+/* FIXME freeze IO, cluster wide.
+ *
+ * We should make sure no-one uses
+ * some half-updated struct when we
+ * assign it later. */
+
+	ndc = kmalloc(sizeof(*ndc), GFP_KERNEL);
+	if (!ndc) {
+		retcode = ERR_NOMEM;
+		goto fail;
+	}
+
+	memcpy(ndc, &mdev->ldev->dc, sizeof(*ndc));
+	err = disk_conf_from_attrs_for_change(ndc, info);
+	if (err) {
+		retcode = ERR_MANDATORY_TAG;
+		drbd_msg_put_info(from_attrs_err_to_txt(err));
+	}
+
+	if (!expect(ndc->resync_rate >= 1))
+		ndc->resync_rate = 1;
+
+	/* clip to allowed range */
+	if (!expect(ndc->al_extents >= DRBD_AL_EXTENTS_MIN))
+		ndc->al_extents = DRBD_AL_EXTENTS_MIN;
+	if (!expect(ndc->al_extents <= DRBD_AL_EXTENTS_MAX))
+		ndc->al_extents = DRBD_AL_EXTENTS_MAX;
+
+	/* most sanity checks done, try to assign the new sync-after
+	 * dependency.  need to hold the global lock in there,
+	 * to avoid a race in the dependency loop check. */
+	retcode = drbd_alter_sa(mdev, ndc->resync_after);
+	if (retcode != NO_ERROR)
+		goto fail;
+
+	fifo_size = (ndc->c_plan_ahead * 10 * SLEEP_TIME) / HZ;
+	if (fifo_size != mdev->rs_plan_s.size && fifo_size > 0) {
+		rs_plan_s   = kzalloc(sizeof(int) * fifo_size, GFP_KERNEL);
+		if (!rs_plan_s) {
+			dev_err(DEV, "kmalloc of fifo_buffer failed");
+			retcode = ERR_NOMEM;
+			goto fail;
+		}
+	}
+
+	if (fifo_size != mdev->rs_plan_s.size) {
+		kfree(mdev->rs_plan_s.values);
+		mdev->rs_plan_s.values = rs_plan_s;
+		mdev->rs_plan_s.size   = fifo_size;
+		mdev->rs_planed = 0;
+		rs_plan_s = NULL;
+	}
+
+	wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
+	drbd_al_shrink(mdev);
+	err = drbd_check_al_size(mdev, ndc);
+	lc_unlock(mdev->act_log);
+	wake_up(&mdev->al_wait);
+
+	if (err) {
+		retcode = ERR_NOMEM;
+		goto fail;
+	}
+
+	/* FIXME
+	 * To avoid someone looking at a half-updated struct, we probably
+	 * should have a rw-semaphor on net_conf and disk_conf.
+	 */
+	mdev->ldev->dc = *ndc;
+
+	drbd_md_sync(mdev);
+
+
+	if (mdev->state.conn >= C_CONNECTED)
+		drbd_send_sync_param(mdev);
+
+ fail:
+	put_ldev(mdev);
+	kfree(ndc);
+	kfree(rs_plan_s);
+ out:
+	drbd_adm_finish(info, retcode);
+	return 0;
+}
+
 int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_conf *mdev;
@@ -1111,12 +1222,29 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		goto fail;
 	}
 
-	nbc->dc.disk_size     = DRBD_DISK_SIZE_SECT_DEF;
-	nbc->dc.on_io_error   = DRBD_ON_IO_ERROR_DEF;
-	nbc->dc.fencing       = DRBD_FENCING_DEF;
-	nbc->dc.max_bio_bvecs = DRBD_MAX_BIO_BVECS_DEF;
-
-	err = disk_conf_from_attrs(&nbc->dc, info->attrs);
+	nbc->dc = (struct disk_conf) {
+		{}, 0, /* backing_dev */
+		{}, 0, /* meta_dev */
+		0, /* meta_dev_idx */
+		DRBD_DISK_SIZE_SECT_DEF, /* disk_size */
+		DRBD_MAX_BIO_BVECS_DEF, /* max_bio_bvecs */
+		DRBD_ON_IO_ERROR_DEF, /* on_io_error */
+		DRBD_FENCING_DEF, /* fencing */
+		DRBD_RATE_DEF, /* resync_rate */
+		DRBD_AFTER_DEF, /* resync_after */
+		DRBD_AL_EXTENTS_DEF, /* al_extents */
+		DRBD_C_PLAN_AHEAD_DEF, /* c_plan_ahead */
+		DRBD_C_DELAY_TARGET_DEF, /* c_delay_target */
+		DRBD_C_FILL_TARGET_DEF, /* c_fill_target */
+		DRBD_C_MAX_RATE_DEF, /* c_max_rate */
+		DRBD_C_MIN_RATE_DEF, /* c_min_rate */
+		0, /* no_disk_barrier */
+		0, /* no_disk_flush */
+		0, /* no_disk_drain */
+		0, /* no_md_flush */
+	};
+
+	err = disk_conf_from_attrs(&nbc->dc, info);
 	if (err) {
 		retcode = ERR_MANDATORY_TAG;
 		drbd_msg_put_info(from_attrs_err_to_txt(err));
@@ -1267,7 +1395,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	/* Since we are diskless, fix the activity log first... */
-	if (drbd_check_al_size(mdev)) {
+	if (drbd_check_al_size(mdev, &nbc->dc)) {
 		retcode = ERR_NOMEM;
 		goto force_diskless_dec;
 	}
@@ -1498,6 +1626,158 @@ out:
 	return 0;
 }
 
+static bool conn_resync_running(struct drbd_tconn *tconn)
+{
+	struct drbd_conf *mdev;
+	int vnr;
+
+	idr_for_each_entry(&tconn->volumes, mdev, vnr) {
+		if (mdev->state.conn == C_SYNC_SOURCE ||
+		    mdev->state.conn == C_SYNC_TARGET ||
+		    mdev->state.conn == C_PAUSED_SYNC_S ||
+		    mdev->state.conn == C_PAUSED_SYNC_T)
+			return true;
+	}
+	return false;
+}
+
+static bool conn_ov_running(struct drbd_tconn *tconn)
+{
+	struct drbd_conf *mdev;
+	int vnr;
+
+	idr_for_each_entry(&tconn->volumes, mdev, vnr) {
+		if (mdev->state.conn == C_VERIFY_S ||
+		    mdev->state.conn == C_VERIFY_T)
+			return true;
+	}
+	return false;
+}
+
+int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
+{
+	enum drbd_ret_code retcode;
+	struct drbd_tconn *tconn;
+	struct net_conf *new_conf = NULL;
+	int err;
+	int ovr; /* online verify running */
+	int rsr; /* re-sync running */
+	struct crypto_hash *verify_tfm = NULL;
+	struct crypto_hash *csums_tfm = NULL;
+
+
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_CONN);
+	if (!adm_ctx.reply_skb)
+		return retcode;
+	if (retcode != NO_ERROR)
+		goto out;
+
+	tconn = adm_ctx.tconn;
+
+	new_conf = kzalloc(sizeof(struct net_conf), GFP_KERNEL);
+	if (!new_conf) {
+		retcode = ERR_NOMEM;
+		goto out;
+	}
+
+	/* we also need a net config
+	 * to change the options on */
+	if (!get_net_conf(tconn)) {
+		drbd_msg_put_info("net conf missing, try connect");
+		retcode = ERR_INVALID_REQUEST;
+		goto out;
+	}
+
+	conn_reconfig_start(tconn);
+
+	memcpy(new_conf, tconn->net_conf, sizeof(*new_conf));
+	err = net_conf_from_attrs_for_change(new_conf, info);
+	if (err) {
+		retcode = ERR_MANDATORY_TAG;
+		drbd_msg_put_info(from_attrs_err_to_txt(err));
+		goto fail;
+	}
+
+	/* re-sync running */
+	rsr = conn_resync_running(tconn);
+	if (rsr && strcmp(new_conf->csums_alg, tconn->net_conf->csums_alg)) {
+		retcode = ERR_CSUMS_RESYNC_RUNNING;
+		goto fail;
+	}
+
+	if (!rsr && new_conf->csums_alg[0]) {
+		csums_tfm = crypto_alloc_hash(new_conf->csums_alg, 0, CRYPTO_ALG_ASYNC);
+		if (IS_ERR(csums_tfm)) {
+			csums_tfm = NULL;
+			retcode = ERR_CSUMS_ALG;
+			goto fail;
+		}
+
+		if (!drbd_crypto_is_hash(crypto_hash_tfm(csums_tfm))) {
+			retcode = ERR_CSUMS_ALG_ND;
+			goto fail;
+		}
+	}
+
+	/* online verify running */
+	ovr = conn_ov_running(tconn);
+	if (ovr) {
+		if (strcmp(new_conf->verify_alg, tconn->net_conf->verify_alg)) {
+			retcode = ERR_VERIFY_RUNNING;
+			goto fail;
+		}
+	}
+
+	if (!ovr && new_conf->verify_alg[0]) {
+		verify_tfm = crypto_alloc_hash(new_conf->verify_alg, 0, CRYPTO_ALG_ASYNC);
+		if (IS_ERR(verify_tfm)) {
+			verify_tfm = NULL;
+			retcode = ERR_VERIFY_ALG;
+			goto fail;
+		}
+
+		if (!drbd_crypto_is_hash(crypto_hash_tfm(verify_tfm))) {
+			retcode = ERR_VERIFY_ALG_ND;
+			goto fail;
+		}
+	}
+
+
+	/* For now, use struct assignment, not pointer assignment.
+	 * We don't have any means to determine who might still
+	 * keep a local alias into the struct,
+	 * so we cannot just free it and hope for the best :(
+	 * FIXME
+	 * To avoid someone looking at a half-updated struct, we probably
+	 * should have a rw-semaphor on net_conf and disk_conf.
+	 */
+	*tconn->net_conf = *new_conf;
+
+	if (!rsr) {
+		crypto_free_hash(tconn->csums_tfm);
+		tconn->csums_tfm = csums_tfm;
+		csums_tfm = NULL;
+	}
+	if (!ovr) {
+		crypto_free_hash(tconn->verify_tfm);
+		tconn->verify_tfm = verify_tfm;
+		verify_tfm = NULL;
+	}
+
+	if (tconn->cstate >= C_WF_REPORT_PARAMS)
+		drbd_send_sync_param(minor_to_mdev(conn_lowest_minor(tconn)));
+
+ fail:
+	crypto_free_hash(csums_tfm);
+	crypto_free_hash(verify_tfm);
+	kfree(new_conf);
+	put_net_conf(tconn);
+	conn_reconfig_done(tconn);
+ out:
+	drbd_adm_finish(info, retcode);
+	return 0;
+}
+
 int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 {
 	char hmac_name[CRYPTO_MAX_ALG_NAME];
@@ -1531,33 +1811,47 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	/* allocation not in the IO path, cqueue thread context */
-	new_conf = kzalloc(sizeof(struct net_conf), GFP_KERNEL);
+	new_conf = kmalloc(sizeof(struct net_conf), GFP_KERNEL);
 	if (!new_conf) {
 		retcode = ERR_NOMEM;
 		goto fail;
 	}
 
-	new_conf->timeout	   = DRBD_TIMEOUT_DEF;
-	new_conf->try_connect_int  = DRBD_CONNECT_INT_DEF;
-	new_conf->ping_int	   = DRBD_PING_INT_DEF;
-	new_conf->max_epoch_size   = DRBD_MAX_EPOCH_SIZE_DEF;
-	new_conf->max_buffers	   = DRBD_MAX_BUFFERS_DEF;
-	new_conf->unplug_watermark = DRBD_UNPLUG_WATERMARK_DEF;
-	new_conf->sndbuf_size	   = DRBD_SNDBUF_SIZE_DEF;
-	new_conf->rcvbuf_size	   = DRBD_RCVBUF_SIZE_DEF;
-	new_conf->ko_count	   = DRBD_KO_COUNT_DEF;
-	new_conf->after_sb_0p	   = DRBD_AFTER_SB_0P_DEF;
-	new_conf->after_sb_1p	   = DRBD_AFTER_SB_1P_DEF;
-	new_conf->after_sb_2p	   = DRBD_AFTER_SB_2P_DEF;
-	new_conf->want_lose	   = 0;
-	new_conf->two_primaries    = 0;
-	new_conf->wire_protocol    = DRBD_PROT_C;
-	new_conf->ping_timeo	   = DRBD_PING_TIMEO_DEF;
-	new_conf->rr_conflict	   = DRBD_RR_CONFLICT_DEF;
-	new_conf->on_congestion    = DRBD_ON_CONGESTION_DEF;
-	new_conf->cong_extents     = DRBD_CONG_EXTENTS_DEF;
-
-	err = net_conf_from_attrs(new_conf, info->attrs);
+	*new_conf = (struct net_conf) {
+		{}, 0, /* my_addr */
+		{}, 0, /* peer_addr */
+		{}, 0, /* shared_secret */
+		{}, 0, /* cram_hmac_alg */
+		{}, 0, /* integrity_alg */
+		{}, 0, /* verify_alg */
+		{}, 0, /* csums_alg */
+		DRBD_PROTOCOL_DEF, /* wire_protocol */
+		DRBD_CONNECT_INT_DEF, /* try_connect_int */
+		DRBD_TIMEOUT_DEF, /* timeout */
+		DRBD_PING_INT_DEF, /* ping_int */
+		DRBD_PING_TIMEO_DEF, /* ping_timeo */
+		DRBD_SNDBUF_SIZE_DEF, /* sndbuf_size */
+		DRBD_RCVBUF_SIZE_DEF, /* rcvbuf_size */
+		DRBD_KO_COUNT_DEF, /* ko_count */
+		DRBD_MAX_BUFFERS_DEF, /* max_buffers */
+		DRBD_MAX_EPOCH_SIZE_DEF, /* max_epoch_size */
+		DRBD_UNPLUG_WATERMARK_DEF, /* unplug_watermark */
+		DRBD_AFTER_SB_0P_DEF, /* after_sb_0p */
+		DRBD_AFTER_SB_1P_DEF, /* after_sb_1p */
+		DRBD_AFTER_SB_2P_DEF, /* after_sb_2p */
+		DRBD_RR_CONFLICT_DEF, /* rr_conflict */
+		DRBD_ON_CONGESTION_DEF, /* on_congestion */
+		DRBD_CONG_FILL_DEF, /* cong_fill */
+		DRBD_CONG_EXTENTS_DEF, /* cong_extents */
+		0, /* two_primaries */
+		0, /* want_lose */
+		0, /* no_cork */
+		0, /* always_asbp */
+		0, /* dry_run */
+		0, /* use_rle */
+	};
+
+	err = net_conf_from_attrs(new_conf, info);
 	if (err) {
 		retcode = ERR_MANDATORY_TAG;
 		drbd_msg_put_info(from_attrs_err_to_txt(err));
@@ -1789,7 +2083,7 @@ int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info)
 	tconn = adm_ctx.tconn;
 	memset(&parms, 0, sizeof(parms));
 	if (info->attrs[DRBD_NLA_DISCONNECT_PARMS]) {
-		err = disconnect_parms_from_attrs(&parms, info->attrs);
+		err = disconnect_parms_from_attrs(&parms, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
 			drbd_msg_put_info(from_attrs_err_to_txt(err));
@@ -1848,7 +2142,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 
 	memset(&rs, 0, sizeof(struct resize_parms));
 	if (info->attrs[DRBD_NLA_RESIZE_PARMS]) {
-		err = resize_parms_from_attrs(&rs, info->attrs);
+		err = resize_parms_from_attrs(&rs, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
 			drbd_msg_put_info(from_attrs_err_to_txt(err));
@@ -1904,26 +2198,21 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-int drbd_adm_syncer(struct sk_buff *skb, struct genl_info *info)
+int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info)
 {
-	struct drbd_conf *mdev;
 	enum drbd_ret_code retcode;
-	int err;
-	int ovr; /* online verify running */
-	int rsr; /* re-sync running */
-	struct crypto_hash *verify_tfm = NULL;
-	struct crypto_hash *csums_tfm = NULL;
-	struct syncer_conf sc;
 	cpumask_var_t new_cpu_mask;
+	struct drbd_tconn *tconn;
 	int *rs_plan_s = NULL;
-	int fifo_size;
+	struct res_opts sc;
+	int err;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_CONN);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto fail;
-	mdev = adm_ctx.mdev;
+	tconn = adm_ctx.tconn;
 
 	if (!zalloc_cpumask_var(&new_cpu_mask, GFP_KERNEL)) {
 		retcode = ERR_NOMEM;
@@ -1933,172 +2222,43 @@ int drbd_adm_syncer(struct sk_buff *skb, struct genl_info *info)
 
 	if (((struct drbd_genlmsghdr*)info->userhdr)->flags
 			& DRBD_GENL_F_SET_DEFAULTS) {
-		memset(&sc, 0, sizeof(struct syncer_conf));
-		sc.rate       = DRBD_RATE_DEF;
-		sc.after      = DRBD_AFTER_DEF;
-		sc.al_extents = DRBD_AL_EXTENTS_DEF;
+		memset(&sc, 0, sizeof(struct res_opts));
 		sc.on_no_data  = DRBD_ON_NO_DATA_DEF;
-		sc.c_plan_ahead = DRBD_C_PLAN_AHEAD_DEF;
-		sc.c_delay_target = DRBD_C_DELAY_TARGET_DEF;
-		sc.c_fill_target = DRBD_C_FILL_TARGET_DEF;
-		sc.c_max_rate = DRBD_C_MAX_RATE_DEF;
-		sc.c_min_rate = DRBD_C_MIN_RATE_DEF;
 	} else
-		memcpy(&sc, &mdev->sync_conf, sizeof(struct syncer_conf));
+		sc = tconn->res_opts;
 
-	err = syncer_conf_from_attrs(&sc, info->attrs);
+	err = res_opts_from_attrs(&sc, info);
 	if (err) {
 		retcode = ERR_MANDATORY_TAG;
 		drbd_msg_put_info(from_attrs_err_to_txt(err));
 		goto fail;
 	}
 
-	/* re-sync running */
-	rsr = (	mdev->state.conn == C_SYNC_SOURCE ||
-		mdev->state.conn == C_SYNC_TARGET ||
-		mdev->state.conn == C_PAUSED_SYNC_S ||
-		mdev->state.conn == C_PAUSED_SYNC_T );
-
-	if (rsr && strcmp(sc.csums_alg, mdev->sync_conf.csums_alg)) {
-		retcode = ERR_CSUMS_RESYNC_RUNNING;
-		goto fail;
-	}
-
-	if (!rsr && sc.csums_alg[0]) {
-		csums_tfm = crypto_alloc_hash(sc.csums_alg, 0, CRYPTO_ALG_ASYNC);
-		if (IS_ERR(csums_tfm)) {
-			csums_tfm = NULL;
-			retcode = ERR_CSUMS_ALG;
-			goto fail;
-		}
-
-		if (!drbd_crypto_is_hash(crypto_hash_tfm(csums_tfm))) {
-			retcode = ERR_CSUMS_ALG_ND;
-			goto fail;
-		}
-	}
-
-	/* online verify running */
-	ovr = (mdev->state.conn == C_VERIFY_S || mdev->state.conn == C_VERIFY_T);
-
-	if (ovr) {
-		if (strcmp(sc.verify_alg, mdev->sync_conf.verify_alg)) {
-			retcode = ERR_VERIFY_RUNNING;
-			goto fail;
-		}
-	}
-
-	if (!ovr && sc.verify_alg[0]) {
-		verify_tfm = crypto_alloc_hash(sc.verify_alg, 0, CRYPTO_ALG_ASYNC);
-		if (IS_ERR(verify_tfm)) {
-			verify_tfm = NULL;
-			retcode = ERR_VERIFY_ALG;
-			goto fail;
-		}
-
-		if (!drbd_crypto_is_hash(crypto_hash_tfm(verify_tfm))) {
-			retcode = ERR_VERIFY_ALG_ND;
-			goto fail;
-		}
-	}
-
 	/* silently ignore cpu mask on UP kernel */
 	if (nr_cpu_ids > 1 && sc.cpu_mask[0] != 0) {
 		err = __bitmap_parse(sc.cpu_mask, 32, 0,
 				cpumask_bits(new_cpu_mask), nr_cpu_ids);
 		if (err) {
-			dev_warn(DEV, "__bitmap_parse() failed with %d\n", err);
+			conn_warn(tconn, "__bitmap_parse() failed with %d\n", err);
 			retcode = ERR_CPU_MASK_PARSE;
 			goto fail;
 		}
 	}
 
-	if (!expect(sc.rate >= 1))
-		sc.rate = 1;
-
-	/* clip to allowed range */
-	if (!expect(sc.al_extents >= DRBD_AL_EXTENTS_MIN))
-		sc.al_extents = DRBD_AL_EXTENTS_MIN;
-	if (!expect(sc.al_extents <= DRBD_AL_EXTENTS_MAX))
-		sc.al_extents = DRBD_AL_EXTENTS_MAX;
-
-	/* most sanity checks done, try to assign the new sync-after
-	 * dependency.  need to hold the global lock in there,
-	 * to avoid a race in the dependency loop check. */
-	retcode = drbd_alter_sa(mdev, sc.after);
-	if (retcode != NO_ERROR)
-		goto fail;
-
-	fifo_size = (sc.c_plan_ahead * 10 * SLEEP_TIME) / HZ;
-	if (fifo_size != mdev->rs_plan_s.size && fifo_size > 0) {
-		rs_plan_s   = kzalloc(sizeof(int) * fifo_size, GFP_KERNEL);
-		if (!rs_plan_s) {
-			dev_err(DEV, "kmalloc of fifo_buffer failed");
-			retcode = ERR_NOMEM;
-			goto fail;
-		}
-	}
-
-	/* ok, assign the rest of it as well.
-	 * lock against receive_SyncParam() */
-	spin_lock(&mdev->peer_seq_lock);
-	mdev->sync_conf = sc;
-
-	if (!rsr) {
-		crypto_free_hash(mdev->csums_tfm);
-		mdev->csums_tfm = csums_tfm;
-		csums_tfm = NULL;
-	}
-
-	if (!ovr) {
-		crypto_free_hash(mdev->verify_tfm);
-		mdev->verify_tfm = verify_tfm;
-		verify_tfm = NULL;
-	}
-
-	if (fifo_size != mdev->rs_plan_s.size) {
-		kfree(mdev->rs_plan_s.values);
-		mdev->rs_plan_s.values = rs_plan_s;
-		mdev->rs_plan_s.size   = fifo_size;
-		mdev->rs_planed = 0;
-		rs_plan_s = NULL;
-	}
-
-	spin_unlock(&mdev->peer_seq_lock);
 
-	if (get_ldev(mdev)) {
-		wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
-		drbd_al_shrink(mdev);
-		err = drbd_check_al_size(mdev);
-		lc_unlock(mdev->act_log);
-		wake_up(&mdev->al_wait);
+	tconn->res_opts = sc;
 
-		put_ldev(mdev);
-		drbd_md_sync(mdev);
-
-		if (err) {
-			retcode = ERR_NOMEM;
-			goto fail;
-		}
-	}
-
-	if (mdev->state.conn >= C_CONNECTED)
-		drbd_send_sync_param(mdev, &sc);
-
-	if (!cpumask_equal(mdev->tconn->cpu_mask, new_cpu_mask)) {
-		cpumask_copy(mdev->tconn->cpu_mask, new_cpu_mask);
-		drbd_calc_cpu_mask(mdev->tconn);
-		mdev->tconn->receiver.reset_cpu_mask = 1;
-		mdev->tconn->asender.reset_cpu_mask = 1;
-		mdev->tconn->worker.reset_cpu_mask = 1;
+	if (!cpumask_equal(tconn->cpu_mask, new_cpu_mask)) {
+		cpumask_copy(tconn->cpu_mask, new_cpu_mask);
+		drbd_calc_cpu_mask(tconn);
+		tconn->receiver.reset_cpu_mask = 1;
+		tconn->asender.reset_cpu_mask = 1;
+		tconn->worker.reset_cpu_mask = 1;
 	}
 
-	kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE);
 fail:
 	kfree(rs_plan_s);
 	free_cpumask_var(new_cpu_mask);
-	crypto_free_hash(csums_tfm);
-	crypto_free_hash(verify_tfm);
 
 	drbd_adm_finish(info, retcode);
 	return 0;
@@ -2307,6 +2467,9 @@ int nla_put_status_info(struct sk_buff *skb, struct drbd_conf *mdev,
 	if (nla_put_drbd_cfg_context(skb, mdev->tconn->name, mdev->vnr))
 		goto nla_put_failure;
 
+	if (res_opts_to_skb(skb, &mdev->tconn->res_opts, exclude_sensitive))
+		goto nla_put_failure;
+
 	if (got_ldev)
 		if (disk_conf_to_skb(skb, &mdev->ldev->dc, exclude_sensitive))
 			goto nla_put_failure;
@@ -2314,9 +2477,6 @@ int nla_put_status_info(struct sk_buff *skb, struct drbd_conf *mdev,
 		if (net_conf_to_skb(skb, mdev->tconn->net_conf, exclude_sensitive))
 			goto nla_put_failure;
 
-	if (syncer_conf_to_skb(skb, &mdev->sync_conf, exclude_sensitive))
-			goto nla_put_failure;
-
 	nla = nla_nest_start(skb, DRBD_NLA_STATE_INFO);
 	if (!nla)
 		goto nla_put_failure;
@@ -2532,7 +2692,7 @@ int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info)
 		/* resume from last known position, if possible */
 		struct start_ov_parms parms =
 			{ .ov_start_sector = mdev->ov_start_sector };
-		int err = start_ov_parms_from_attrs(&parms, info->attrs);
+		int err = start_ov_parms_from_attrs(&parms, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
 			drbd_msg_put_info(from_attrs_err_to_txt(err));
@@ -2568,7 +2728,7 @@ int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info)
 	mdev = adm_ctx.mdev;
 	memset(&args, 0, sizeof(args));
 	if (info->attrs[DRBD_NLA_NEW_C_UUID_PARMS]) {
-		err = new_c_uuid_parms_from_attrs(&args, info->attrs);
+		err = new_c_uuid_parms_from_attrs(&args, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
 			drbd_msg_put_info(from_attrs_err_to_txt(err));
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 50c52712715e..c8c826b2444f 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -763,7 +763,7 @@ int drbd_connected(int vnr, void *p, void *data)
 		&mdev->tconn->cstate_mutex :
 		&mdev->own_state_mutex;
 
-	ok &= drbd_send_sync_param(mdev, &mdev->sync_conf);
+	ok &= drbd_send_sync_param(mdev);
 	ok &= drbd_send_sizes(mdev, 0, 0);
 	ok &= drbd_send_uuids(mdev);
 	ok &= drbd_send_state(mdev);
@@ -2085,7 +2085,7 @@ int drbd_rs_should_slow_down(struct drbd_conf *mdev, sector_t sector)
 	int throttle = 0;
 
 	/* feature disabled? */
-	if (mdev->sync_conf.c_min_rate == 0)
+	if (mdev->ldev->dc.c_min_rate == 0)
 		return 0;
 
 	spin_lock_irq(&mdev->al_lock);
@@ -2125,7 +2125,7 @@ int drbd_rs_should_slow_down(struct drbd_conf *mdev, sector_t sector)
 		db = mdev->rs_mark_left[i] - rs_left;
 		dbdt = Bit2KB(db/dt);
 
-		if (dbdt > mdev->sync_conf.c_min_rate)
+		if (dbdt > mdev->ldev->dc.c_min_rate)
 			throttle = 1;
 	}
 	return throttle;
@@ -3001,7 +3001,10 @@ static int receive_SyncParam(struct drbd_conf *mdev, enum drbd_packet cmd,
 	if (drbd_recv(mdev->tconn, &p->head.payload, header_size) != header_size)
 		return false;
 
-	mdev->sync_conf.rate	  = be32_to_cpu(p->rate);
+	if (get_ldev(mdev)) {
+		mdev->ldev->dc.resync_rate = be32_to_cpu(p->rate);
+		put_ldev(mdev);
+	}
 
 	if (apv >= 88) {
 		if (apv == 88) {
@@ -3029,10 +3032,10 @@ static int receive_SyncParam(struct drbd_conf *mdev, enum drbd_packet cmd,
 			p->csums_alg[SHARED_SECRET_MAX-1] = 0;
 		}
 
-		if (strcmp(mdev->sync_conf.verify_alg, p->verify_alg)) {
+		if (strcmp(mdev->tconn->net_conf->verify_alg, p->verify_alg)) {
 			if (mdev->state.conn == C_WF_REPORT_PARAMS) {
 				dev_err(DEV, "Different verify-alg settings. me=\"%s\" peer=\"%s\"\n",
-				    mdev->sync_conf.verify_alg, p->verify_alg);
+				    mdev->tconn->net_conf->verify_alg, p->verify_alg);
 				goto disconnect;
 			}
 			verify_tfm = drbd_crypto_alloc_digest_safe(mdev,
@@ -3043,10 +3046,10 @@ static int receive_SyncParam(struct drbd_conf *mdev, enum drbd_packet cmd,
 			}
 		}
 
-		if (apv >= 89 && strcmp(mdev->sync_conf.csums_alg, p->csums_alg)) {
+		if (apv >= 89 && strcmp(mdev->tconn->net_conf->csums_alg, p->csums_alg)) {
 			if (mdev->state.conn == C_WF_REPORT_PARAMS) {
 				dev_err(DEV, "Different csums-alg settings. me=\"%s\" peer=\"%s\"\n",
-				    mdev->sync_conf.csums_alg, p->csums_alg);
+				    mdev->tconn->net_conf->csums_alg, p->csums_alg);
 				goto disconnect;
 			}
 			csums_tfm = drbd_crypto_alloc_digest_safe(mdev,
@@ -3057,37 +3060,39 @@ static int receive_SyncParam(struct drbd_conf *mdev, enum drbd_packet cmd,
 			}
 		}
 
-		if (apv > 94) {
-			mdev->sync_conf.rate	  = be32_to_cpu(p->rate);
-			mdev->sync_conf.c_plan_ahead = be32_to_cpu(p->c_plan_ahead);
-			mdev->sync_conf.c_delay_target = be32_to_cpu(p->c_delay_target);
-			mdev->sync_conf.c_fill_target = be32_to_cpu(p->c_fill_target);
-			mdev->sync_conf.c_max_rate = be32_to_cpu(p->c_max_rate);
+		if (apv > 94 && get_ldev(mdev)) {
+			mdev->ldev->dc.resync_rate = be32_to_cpu(p->rate);
+			mdev->ldev->dc.c_plan_ahead = be32_to_cpu(p->c_plan_ahead);
+			mdev->ldev->dc.c_delay_target = be32_to_cpu(p->c_delay_target);
+			mdev->ldev->dc.c_fill_target = be32_to_cpu(p->c_fill_target);
+			mdev->ldev->dc.c_max_rate = be32_to_cpu(p->c_max_rate);
 
-			fifo_size = (mdev->sync_conf.c_plan_ahead * 10 * SLEEP_TIME) / HZ;
+			fifo_size = (mdev->ldev->dc.c_plan_ahead * 10 * SLEEP_TIME) / HZ;
 			if (fifo_size != mdev->rs_plan_s.size && fifo_size > 0) {
 				rs_plan_s   = kzalloc(sizeof(int) * fifo_size, GFP_KERNEL);
 				if (!rs_plan_s) {
 					dev_err(DEV, "kmalloc of fifo_buffer failed");
+					put_ldev(mdev);
 					goto disconnect;
 				}
 			}
+			put_ldev(mdev);
 		}
 
 		spin_lock(&mdev->peer_seq_lock);
 		/* lock against drbd_nl_syncer_conf() */
 		if (verify_tfm) {
-			strcpy(mdev->sync_conf.verify_alg, p->verify_alg);
-			mdev->sync_conf.verify_alg_len = strlen(p->verify_alg) + 1;
-			crypto_free_hash(mdev->verify_tfm);
-			mdev->verify_tfm = verify_tfm;
+			strcpy(mdev->tconn->net_conf->verify_alg, p->verify_alg);
+			mdev->tconn->net_conf->verify_alg_len = strlen(p->verify_alg) + 1;
+			crypto_free_hash(mdev->tconn->verify_tfm);
+			mdev->tconn->verify_tfm = verify_tfm;
 			dev_info(DEV, "using verify-alg: \"%s\"\n", p->verify_alg);
 		}
 		if (csums_tfm) {
-			strcpy(mdev->sync_conf.csums_alg, p->csums_alg);
-			mdev->sync_conf.csums_alg_len = strlen(p->csums_alg) + 1;
-			crypto_free_hash(mdev->csums_tfm);
-			mdev->csums_tfm = csums_tfm;
+			strcpy(mdev->tconn->net_conf->csums_alg, p->csums_alg);
+			mdev->tconn->net_conf->csums_alg_len = strlen(p->csums_alg) + 1;
+			crypto_free_hash(mdev->tconn->csums_tfm);
+			mdev->tconn->csums_tfm = csums_tfm;
 			dev_info(DEV, "using csums-alg: \"%s\"\n", p->csums_alg);
 		}
 		if (fifo_size != mdev->rs_plan_s.size) {
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 11685658659e..77fad527fb1d 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -402,7 +402,7 @@ is_valid_state(struct drbd_conf *mdev, union drbd_state ns)
 		rv = SS_CONNECTED_OUTDATES;
 
 	else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
-		 (mdev->sync_conf.verify_alg[0] == 0))
+		 (mdev->tconn->net_conf->verify_alg[0] == 0))
 		rv = SS_NO_VERIFY_ALG;
 
 	else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
@@ -668,7 +668,7 @@ static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state
 	    (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk > D_OUTDATED))
 		ns.susp_fen = 1; /* Suspend IO while fence-peer handler runs (peer lost) */
 
-	if (mdev->sync_conf.on_no_data == OND_SUSPEND_IO &&
+	if (mdev->tconn->res_opts.on_no_data == OND_SUSPEND_IO &&
 	    (ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE))
 		ns.susp_nod = 1; /* Suspend IO while no data available (no accessible data available) */
 
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index a730520e468e..005876b32f74 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -310,12 +310,12 @@ static int w_e_send_csum(struct drbd_work *w, int cancel)
 	if (unlikely((peer_req->flags & EE_WAS_ERROR) != 0))
 		goto out;
 
-	digest_size = crypto_hash_digestsize(mdev->csums_tfm);
+	digest_size = crypto_hash_digestsize(mdev->tconn->csums_tfm);
 	digest = kmalloc(digest_size, GFP_NOIO);
 	if (digest) {
 		sector_t sector = peer_req->i.sector;
 		unsigned int size = peer_req->i.size;
-		drbd_csum_ee(mdev, mdev->csums_tfm, peer_req, digest);
+		drbd_csum_ee(mdev, mdev->tconn->csums_tfm, peer_req, digest);
 		/* Free peer_req and pages before send.
 		 * In case we block on congestion, we could otherwise run into
 		 * some distributed deadlock, if the other side blocks on
@@ -451,13 +451,13 @@ static int drbd_rs_controller(struct drbd_conf *mdev)
 
 	spin_lock(&mdev->peer_seq_lock); /* get an atomic view on mdev->rs_plan_s */
 
-	steps = mdev->rs_plan_s.size; /* (mdev->sync_conf.c_plan_ahead * 10 * SLEEP_TIME) / HZ; */
+	steps = mdev->rs_plan_s.size; /* (mdev->ldev->dc.c_plan_ahead * 10 * SLEEP_TIME) / HZ; */
 
 	if (mdev->rs_in_flight + sect_in == 0) { /* At start of resync */
-		want = ((mdev->sync_conf.rate * 2 * SLEEP_TIME) / HZ) * steps;
+		want = ((mdev->ldev->dc.resync_rate * 2 * SLEEP_TIME) / HZ) * steps;
 	} else { /* normal path */
-		want = mdev->sync_conf.c_fill_target ? mdev->sync_conf.c_fill_target :
-			sect_in * mdev->sync_conf.c_delay_target * HZ / (SLEEP_TIME * 10);
+		want = mdev->ldev->dc.c_fill_target ? mdev->ldev->dc.c_fill_target :
+			sect_in * mdev->ldev->dc.c_delay_target * HZ / (SLEEP_TIME * 10);
 	}
 
 	correction = want - mdev->rs_in_flight - mdev->rs_planed;
@@ -476,7 +476,7 @@ static int drbd_rs_controller(struct drbd_conf *mdev)
 	if (req_sect < 0)
 		req_sect = 0;
 
-	max_sect = (mdev->sync_conf.c_max_rate * 2 * SLEEP_TIME) / HZ;
+	max_sect = (mdev->ldev->dc.c_max_rate * 2 * SLEEP_TIME) / HZ;
 	if (req_sect > max_sect)
 		req_sect = max_sect;
 
@@ -492,11 +492,11 @@ static int drbd_rs_controller(struct drbd_conf *mdev)
 static int drbd_rs_number_requests(struct drbd_conf *mdev)
 {
 	int number;
-	if (mdev->rs_plan_s.size) { /* mdev->sync_conf.c_plan_ahead */
+	if (mdev->rs_plan_s.size) { /* mdev->ldev->dc.c_plan_ahead */
 		number = drbd_rs_controller(mdev) >> (BM_BLOCK_SHIFT - 9);
 		mdev->c_sync_rate = number * HZ * (BM_BLOCK_SIZE / 1024) / SLEEP_TIME;
 	} else {
-		mdev->c_sync_rate = mdev->sync_conf.rate;
+		mdev->c_sync_rate = mdev->ldev->dc.resync_rate;
 		number = SLEEP_TIME * mdev->c_sync_rate  / ((BM_BLOCK_SIZE / 1024) * HZ);
 	}
 
@@ -619,7 +619,7 @@ next_sector:
 		/* adjust very last sectors, in case we are oddly sized */
 		if (sector + (size>>9) > capacity)
 			size = (capacity-sector)<<9;
-		if (mdev->tconn->agreed_pro_version >= 89 && mdev->csums_tfm) {
+		if (mdev->tconn->agreed_pro_version >= 89 && mdev->tconn->csums_tfm) {
 			switch (read_for_csum(mdev, sector, size)) {
 			case -EIO: /* Disk failure */
 				put_ldev(mdev);
@@ -810,7 +810,7 @@ int drbd_resync_finished(struct drbd_conf *mdev)
 		if (os.conn == C_SYNC_TARGET || os.conn == C_PAUSED_SYNC_T)
 			khelper_cmd = "after-resync-target";
 
-		if (mdev->csums_tfm && mdev->rs_total) {
+		if (mdev->tconn->csums_tfm && mdev->rs_total) {
 			const unsigned long s = mdev->rs_same_csum;
 			const unsigned long t = mdev->rs_total;
 			const int ratio =
@@ -1019,13 +1019,13 @@ int w_e_end_csum_rs_req(struct drbd_work *w, int cancel)
 		/* quick hack to try to avoid a race against reconfiguration.
 		 * a real fix would be much more involved,
 		 * introducing more locking mechanisms */
-		if (mdev->csums_tfm) {
-			digest_size = crypto_hash_digestsize(mdev->csums_tfm);
+		if (mdev->tconn->csums_tfm) {
+			digest_size = crypto_hash_digestsize(mdev->tconn->csums_tfm);
 			D_ASSERT(digest_size == di->digest_size);
 			digest = kmalloc(digest_size, GFP_NOIO);
 		}
 		if (digest) {
-			drbd_csum_ee(mdev, mdev->csums_tfm, peer_req, digest);
+			drbd_csum_ee(mdev, mdev->tconn->csums_tfm, peer_req, digest);
 			eq = !memcmp(digest, di->digest, digest_size);
 			kfree(digest);
 		}
@@ -1069,7 +1069,7 @@ int w_e_end_ov_req(struct drbd_work *w, int cancel)
 	if (unlikely(cancel))
 		goto out;
 
-	digest_size = crypto_hash_digestsize(mdev->verify_tfm);
+	digest_size = crypto_hash_digestsize(mdev->tconn->verify_tfm);
 	digest = kmalloc(digest_size, GFP_NOIO);
 	if (!digest) {
 		ok = 0;	/* terminate the connection in case the allocation failed */
@@ -1077,7 +1077,7 @@ int w_e_end_ov_req(struct drbd_work *w, int cancel)
 	}
 
 	if (likely(!(peer_req->flags & EE_WAS_ERROR)))
-		drbd_csum_ee(mdev, mdev->verify_tfm, peer_req, digest);
+		drbd_csum_ee(mdev, mdev->tconn->verify_tfm, peer_req, digest);
 	else
 		memset(digest, 0, digest_size);
 
@@ -1141,10 +1141,10 @@ int w_e_end_ov_reply(struct drbd_work *w, int cancel)
 	di = peer_req->digest;
 
 	if (likely((peer_req->flags & EE_WAS_ERROR) == 0)) {
-		digest_size = crypto_hash_digestsize(mdev->verify_tfm);
+		digest_size = crypto_hash_digestsize(mdev->tconn->verify_tfm);
 		digest = kmalloc(digest_size, GFP_NOIO);
 		if (digest) {
-			drbd_csum_ee(mdev, mdev->verify_tfm, peer_req, digest);
+			drbd_csum_ee(mdev, mdev->tconn->verify_tfm, peer_req, digest);
 
 			D_ASSERT(digest_size == di->digest_size);
 			eq = !memcmp(digest, di->digest, digest_size);
@@ -1319,9 +1319,9 @@ static int _drbd_may_sync_now(struct drbd_conf *mdev)
 	struct drbd_conf *odev = mdev;
 
 	while (1) {
-		if (odev->sync_conf.after == -1)
+		if (odev->ldev->dc.resync_after == -1)
 			return 1;
-		odev = minor_to_mdev(odev->sync_conf.after);
+		odev = minor_to_mdev(odev->ldev->dc.resync_after);
 		if (!expect(odev))
 			return 1;
 		if ((odev->state.conn >= C_SYNC_SOURCE &&
@@ -1408,11 +1408,11 @@ static int sync_after_error(struct drbd_conf *mdev, int o_minor)
 			return ERR_SYNC_AFTER_CYCLE;
 
 		/* dependency chain ends here, no cycles. */
-		if (odev->sync_conf.after == -1)
+		if (odev->ldev->dc.resync_after == -1)
 			return NO_ERROR;
 
 		/* follow the dependency chain */
-		odev = minor_to_mdev(odev->sync_conf.after);
+		odev = minor_to_mdev(odev->ldev->dc.resync_after);
 	}
 }
 
@@ -1424,7 +1424,7 @@ int drbd_alter_sa(struct drbd_conf *mdev, int na)
 	write_lock_irq(&global_state_lock);
 	retcode = sync_after_error(mdev, na);
 	if (retcode == NO_ERROR) {
-		mdev->sync_conf.after = na;
+		mdev->ldev->dc.resync_after = na;
 		do {
 			changes  = _drbd_pause_after(mdev);
 			changes |= _drbd_resume_next(mdev);
@@ -1637,7 +1637,7 @@ int drbd_worker(struct drbd_thread *thi)
 	struct drbd_work *w = NULL;
 	struct drbd_conf *mdev;
 	LIST_HEAD(work_list);
-	int minor, intr = 0;
+	int vnr, intr = 0;
 
 	while (get_t_state(thi) == RUNNING) {
 		drbd_thread_current_set_cpu(thi);
@@ -1722,7 +1722,7 @@ int drbd_worker(struct drbd_thread *thi)
 	spin_unlock_irq(&tconn->data.work.q_lock);
 
 	drbd_thread_stop(&tconn->receiver);
-	idr_for_each_entry(&tconn->volumes, mdev, minor) {
+	idr_for_each_entry(&tconn->volumes, mdev, vnr) {
 		D_ASSERT(mdev->state.disk == D_DISKLESS && mdev->state.conn == C_STANDALONE);
 		/* _drbd_set_state only uses stop_nowait.
 		 * wait here for the exiting receiver. */
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index a07d69279b1a..938e8560a833 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -102,66 +102,73 @@ GENL_struct(DRBD_NLA_CFG_CONTEXT, 2, drbd_cfg_context,
 )
 
 GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
-	__u64_field(1, GENLA_F_MANDATORY,	disk_size)
-	__str_field(2, GENLA_F_REQUIRED,	backing_dev,	128)
-	__str_field(3, GENLA_F_REQUIRED,	meta_dev,	128)
-	__u32_field(4, GENLA_F_REQUIRED,	meta_dev_idx)
-	__u32_field(5, GENLA_F_MANDATORY,	max_bio_bvecs)
+	__str_field(1, GENLA_F_REQUIRED | GENLA_F_INVARIANT,	backing_dev,	128)
+	__str_field(2, GENLA_F_REQUIRED | GENLA_F_INVARIANT,	meta_dev,	128)
+	__u32_field(3, GENLA_F_REQUIRED | GENLA_F_INVARIANT,	meta_dev_idx)
+
+	/* use the resize command to try and change the disk_size */
+	__u64_field(4, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	disk_size)
+	/* we could change the max_bio_bvecs,
+	 * but it won't propagate through the stack */
+	__u32_field(5, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	max_bio_bvecs)
+
 	__u32_field(6, GENLA_F_MANDATORY,	on_io_error)
 	__u32_field(7, GENLA_F_MANDATORY,	fencing)
-	__flg_field(8, GENLA_F_MANDATORY,	no_disk_barrier)
-	__flg_field(9, GENLA_F_MANDATORY,	no_disk_flush)
-	__flg_field(10, GENLA_F_MANDATORY,	no_disk_drain)
-	__flg_field(11, GENLA_F_MANDATORY,	no_md_flush)
-	__flg_field(12, GENLA_F_MANDATORY,	use_bmbv)
+
+	__u32_field(8,	GENLA_F_MANDATORY,	resync_rate)
+	__u32_field(9,	GENLA_F_MANDATORY,	resync_after)
+	__u32_field(10,	GENLA_F_MANDATORY,	al_extents)
+	__u32_field(11,	GENLA_F_MANDATORY,	c_plan_ahead)
+	__u32_field(12,	GENLA_F_MANDATORY,	c_delay_target)
+	__u32_field(13,	GENLA_F_MANDATORY,	c_fill_target)
+	__u32_field(14,	GENLA_F_MANDATORY,	c_max_rate)
+	__u32_field(15,	GENLA_F_MANDATORY,	c_min_rate)
+
+	__flg_field(16, GENLA_F_MANDATORY,	no_disk_barrier)
+	__flg_field(17, GENLA_F_MANDATORY,	no_disk_flush)
+	__flg_field(18, GENLA_F_MANDATORY,	no_disk_drain)
+	__flg_field(19, GENLA_F_MANDATORY,	no_md_flush)
+
 )
 
-GENL_struct(DRBD_NLA_SYNCER_CONF, 4, syncer_conf,
-	__u32_field(1,	GENLA_F_MANDATORY,	rate)
-	__u32_field(2,	GENLA_F_MANDATORY,	after)
-	__u32_field(3,	GENLA_F_MANDATORY,	al_extents)
-	__str_field(4,	GENLA_F_MANDATORY,	cpu_mask,       32)
-	__str_field(5,	GENLA_F_MANDATORY,	verify_alg,     SHARED_SECRET_MAX)
-	__str_field(6,	GENLA_F_MANDATORY,	csums_alg,	SHARED_SECRET_MAX)
-	__flg_field(7,	GENLA_F_MANDATORY,	use_rle)
-	__u32_field(8,	GENLA_F_MANDATORY,	on_no_data)
-	__u32_field(9,	GENLA_F_MANDATORY,	c_plan_ahead)
-	__u32_field(10,	GENLA_F_MANDATORY,	c_delay_target)
-	__u32_field(11,	GENLA_F_MANDATORY,	c_fill_target)
-	__u32_field(12,	GENLA_F_MANDATORY,	c_max_rate)
-	__u32_field(13,	GENLA_F_MANDATORY,	c_min_rate)
+GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
+	__str_field(1,	GENLA_F_MANDATORY,	cpu_mask,       32)
+	__u32_field(2,	GENLA_F_MANDATORY,	on_no_data)
 )
 
 GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
-	__str_field(1,	GENLA_F_MANDATORY | GENLA_F_SENSITIVE,
+	__bin_field(1,	GENLA_F_REQUIRED | GENLA_F_INVARIANT,	my_addr,	128)
+	__bin_field(2,	GENLA_F_REQUIRED | GENLA_F_INVARIANT,	peer_addr,	128)
+	__str_field(3,	GENLA_F_MANDATORY | GENLA_F_SENSITIVE,
 						shared_secret,	SHARED_SECRET_MAX)
-	__str_field(2,	GENLA_F_MANDATORY,	cram_hmac_alg,	SHARED_SECRET_MAX)
-	__str_field(3,	GENLA_F_MANDATORY,	integrity_alg,	SHARED_SECRET_MAX)
-	__str_field(4,	GENLA_F_REQUIRED,	my_addr,	128)
-	__str_field(5,	GENLA_F_REQUIRED,	peer_addr,	128)
-	__u32_field(6,	GENLA_F_REQUIRED,	wire_protocol)
-	__u32_field(7,	GENLA_F_MANDATORY,	try_connect_int)
-	__u32_field(8,	GENLA_F_MANDATORY,	timeout)
-	__u32_field(9,	GENLA_F_MANDATORY,	ping_int)
-	__u32_field(10,	GENLA_F_MANDATORY,	ping_timeo)
-	__u32_field(11,	GENLA_F_MANDATORY,	sndbuf_size)
-	__u32_field(12,	GENLA_F_MANDATORY,	rcvbuf_size)
-	__u32_field(13,	GENLA_F_MANDATORY,	ko_count)
-	__u32_field(14,	GENLA_F_MANDATORY,	max_buffers)
-	__u32_field(15,	GENLA_F_MANDATORY,	max_epoch_size)
-	__u32_field(16,	GENLA_F_MANDATORY,	unplug_watermark)
-	__u32_field(17,	GENLA_F_MANDATORY,	after_sb_0p)
-	__u32_field(18,	GENLA_F_MANDATORY,	after_sb_1p)
-	__u32_field(19,	GENLA_F_MANDATORY,	after_sb_2p)
-	__u32_field(20,	GENLA_F_MANDATORY,	rr_conflict)
-	__u32_field(21,	GENLA_F_MANDATORY,	on_congestion)
-	__u32_field(22,	GENLA_F_MANDATORY,	cong_fill)
-	__u32_field(23,	GENLA_F_MANDATORY,	cong_extents)
-	__flg_field(24, GENLA_F_MANDATORY,	two_primaries)
-	__flg_field(25, GENLA_F_MANDATORY,	want_lose)
-	__flg_field(26, GENLA_F_MANDATORY,	no_cork)
-	__flg_field(27, GENLA_F_MANDATORY,	always_asbp)
-	__flg_field(28, GENLA_F_MANDATORY,	dry_run)
+	__str_field(4,	GENLA_F_MANDATORY,	cram_hmac_alg,	SHARED_SECRET_MAX)
+	__str_field(5,	GENLA_F_MANDATORY,	integrity_alg,	SHARED_SECRET_MAX)
+	__str_field(6,	GENLA_F_MANDATORY,	verify_alg,     SHARED_SECRET_MAX)
+	__str_field(7,	GENLA_F_MANDATORY,	csums_alg,	SHARED_SECRET_MAX)
+	__u32_field(8,	GENLA_F_MANDATORY,	wire_protocol)
+	__u32_field(9,	GENLA_F_MANDATORY,	try_connect_int)
+	__u32_field(10,	GENLA_F_MANDATORY,	timeout)
+	__u32_field(11,	GENLA_F_MANDATORY,	ping_int)
+	__u32_field(12,	GENLA_F_MANDATORY,	ping_timeo)
+	__u32_field(13,	GENLA_F_MANDATORY,	sndbuf_size)
+	__u32_field(14,	GENLA_F_MANDATORY,	rcvbuf_size)
+	__u32_field(15,	GENLA_F_MANDATORY,	ko_count)
+	__u32_field(16,	GENLA_F_MANDATORY,	max_buffers)
+	__u32_field(17,	GENLA_F_MANDATORY,	max_epoch_size)
+	__u32_field(18,	GENLA_F_MANDATORY,	unplug_watermark)
+	__u32_field(19,	GENLA_F_MANDATORY,	after_sb_0p)
+	__u32_field(20,	GENLA_F_MANDATORY,	after_sb_1p)
+	__u32_field(21,	GENLA_F_MANDATORY,	after_sb_2p)
+	__u32_field(22,	GENLA_F_MANDATORY,	rr_conflict)
+	__u32_field(23,	GENLA_F_MANDATORY,	on_congestion)
+	__u32_field(24,	GENLA_F_MANDATORY,	cong_fill)
+	__u32_field(25,	GENLA_F_MANDATORY,	cong_extents)
+	__flg_field(26, GENLA_F_MANDATORY,	two_primaries)
+	__flg_field(27, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	want_lose)
+	__flg_field(28, GENLA_F_MANDATORY,	no_cork)
+	__flg_field(29, GENLA_F_MANDATORY,	always_asbp)
+	__flg_field(30, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	dry_run)
+	__flg_field(31,	GENLA_F_MANDATORY,	use_rle)
 )
 
 GENL_struct(DRBD_NLA_SET_ROLE_PARMS, 6, set_role_parms,
@@ -270,11 +277,10 @@ GENL_op(DRBD_ADM_ADD_LINK, 7, GENL_doit(drbd_adm_create_connection),
 GENL_op(DRBD_ADM_DEL_LINK, 8, GENL_doit(drbd_adm_delete_connection),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
 
-	/* operates on replication links */
-GENL_op(DRBD_ADM_SYNCER, 9,
-	GENL_doit(drbd_adm_syncer),
+GENL_op(DRBD_ADM_RESOURCE_OPTS, 9,
+	GENL_doit(drbd_adm_resource_opts),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_SYNCER_CONF, GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_RESOURCE_OPTS, GENLA_F_MANDATORY)
 )
 
 GENL_op(
@@ -284,16 +290,28 @@ GENL_op(
 	GENL_tla_expected(DRBD_NLA_NET_CONF, GENLA_F_REQUIRED)
 )
 
+GENL_op(
+	DRBD_ADM_CHG_NET_OPTS, 29,
+	GENL_doit(drbd_adm_net_opts),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NET_CONF, GENLA_F_REQUIRED)
+)
+
 GENL_op(DRBD_ADM_DISCONNECT, 11, GENL_doit(drbd_adm_disconnect),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
 
-	/* operates on minors */
 GENL_op(DRBD_ADM_ATTACH, 12,
 	GENL_doit(drbd_adm_attach),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
 	GENL_tla_expected(DRBD_NLA_DISK_CONF, GENLA_F_REQUIRED)
 )
 
+GENL_op(DRBD_ADM_CHG_DISK_OPTS, 28,
+	GENL_doit(drbd_adm_disk_opts),
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_DISK_OPTS, GENLA_F_REQUIRED)
+)
+
 GENL_op(
 	DRBD_ADM_RESIZE, 13,
 	GENL_doit(drbd_adm_resize),
@@ -301,7 +319,6 @@ GENL_op(
 	GENL_tla_expected(DRBD_NLA_RESIZE_PARMS, GENLA_F_MANDATORY)
 )
 
-	/* operates on all volumes within a resource */
 GENL_op(
 	DRBD_ADM_PRIMARY, 14,
 	GENL_doit(drbd_adm_set_role),
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 22920a8af4e2..659a8eb38830 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -166,5 +166,7 @@
 #define DRBD_CONG_EXTENTS_MAX	DRBD_AL_EXTENTS_MAX
 #define DRBD_CONG_EXTENTS_DEF	DRBD_AL_EXTENTS_DEF
 
+#define DRBD_PROTOCOL_DEF DRBD_PROT_C
+
 #undef RANGE
 #endif
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index c8c67239f616..e458282a3728 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -190,11 +190,12 @@ static struct nlattr *nested_attr_tb[128];
 
 #undef GENL_struct
 #define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
-	/* static, potentially unused */				\
-int s_name ## _from_attrs(struct s_name *s, struct nlattr *tb[])	\
+/* *_from_attrs functions are static, but potentially unused */		\
+static int __ ## s_name ## _from_attrs(struct s_name *s,		\
+		struct genl_info *info, bool exclude_invariants)	\
 {									\
 	const int maxtype = ARRAY_SIZE(s_name ## _nl_policy)-1;		\
-	struct nlattr *tla = tb[tag_number];				\
+	struct nlattr *tla = info->attrs[tag_number];			\
 	struct nlattr **ntb = nested_attr_tb;				\
 	struct nlattr *nla;						\
 	int err;							\
@@ -211,33 +212,49 @@ int s_name ## _from_attrs(struct s_name *s, struct nlattr *tb[])	\
 									\
 	s_fields							\
 	return 0;							\
-}
+}					__attribute__((unused))		\
+static int s_name ## _from_attrs(struct s_name *s,			\
+						struct genl_info *info)	\
+{									\
+	return __ ## s_name ## _from_attrs(s, info, false);		\
+}					__attribute__((unused))		\
+static int s_name ## _from_attrs_for_change(struct s_name *s,		\
+						struct genl_info *info)	\
+{									\
+	return __ ## s_name ## _from_attrs(s, info, true);		\
+}					__attribute__((unused))		\
 
-#undef __field
-#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)	\
+#define __assign(attr_nr, attr_flag, name, nla_type, type, assignment...)	\
 		nla = ntb[__nla_type(attr_nr)];				\
 		if (nla) {						\
-			if (s)						\
-				s->name = __get(nla);			\
-			DPRINT_FIELD("<<", nla_type, name, s, nla);	\
+			if (exclude_invariants && ((attr_flag) & GENLA_F_INVARIANT)) {		\
+				pr_info("<< must not change invariant attr: %s\n", #name);	\
+				return -EEXIST;				\
+			}						\
+			assignment;					\
+		} else if (exclude_invariants && ((attr_flag) & GENLA_F_INVARIANT)) {		\
+			/* attribute missing from payload, */		\
+			/* which was expected */			\
 		} else if ((attr_flag) & GENLA_F_REQUIRED) {		\
 			pr_info("<< missing attr: %s\n", #name);	\
 			return -ENOMSG;					\
 		}
 
+#undef __field
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)	\
+	__assign(attr_nr, attr_flag, name, nla_type, type,		\
+			if (s)						\
+				s->name = __get(nla);			\
+			DPRINT_FIELD("<<", nla_type, name, s, nla))
+
 /* validate_nla() already checked nla_len <= maxlen appropriately. */
 #undef __array
 #define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
-		nla = ntb[__nla_type(attr_nr)];				\
-		if (nla) {						\
+	__assign(attr_nr, attr_flag, name, nla_type, type,		\
 			if (s)						\
 				s->name ## _len =			\
 					__get(s->name, nla, maxlen);	\
-			DPRINT_ARRAY("<<", nla_type, name, s, nla);	\
-		} else if ((attr_flag) & GENLA_F_REQUIRED) {		\
-			pr_info("<< missing attr: %s\n", #name);	\
-			return -ENOMSG;					\
-		}							\
+			DPRINT_ARRAY("<<", nla_type, name, s, nla))
 
 #include GENL_MAGIC_INCLUDE_FILE
 
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index 745ebfd6c7e5..9a605b9ee834 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -59,12 +59,20 @@ enum {
 	GENLA_F_MANDATORY	= 1 << 14,
 	GENLA_F_REQUIRED	= 1 << 15,
 
-	/* This will not be present in the __u16 .nla_type, but can be
-	 * triggered on in <struct>_to_skb, to exclude "sensitive"
-	 * information from broadcasts, or on unpriviledged get requests.
-	 * This is useful because genetlink multicast groups can be listened in
-	 * on by anyone.  */
+	/* Below will not be present in the __u16 .nla_type, but can be
+	 * triggered on in <struct>_to_skb resp. <struct>_from_attrs */
+
+	/* To exclude "sensitive" information from broadcasts, or on
+	 * unpriviledged get requests.  This is useful because genetlink
+	 * multicast groups can be listened in on by anyone.  */
 	GENLA_F_SENSITIVE	= 1 << 16,
+
+	/* INVARIAN options cannot be changed at runtime.
+	 * Useful to share an attribute policy and struct definition,
+	 * between some "create" and "change" commands,
+	 * but disallow certain fields to be changed online.
+	 */
+	GENLA_F_INVARIANT	= 1 << 17,
 };
 
 #define __nla_type(x)	((__u16)((__u16)(x) & (__u16)NLA_TYPE_MASK))
-- 
cgit v1.2.3-55-g7522


From cb703454a283d8dd5599e928eeea30367ca18874 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Thu, 24 Mar 2011 11:03:07 +0100
Subject: drbd: Converted drbd_try_outdate_peer() from mdev to tconn

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h      |   4 +-
 drivers/block/drbd/drbd_nl.c       | 144 ++++++++++++++++++-------------------
 drivers/block/drbd/drbd_receiver.c |   7 +-
 drivers/block/drbd/drbd_state.c    |  85 ++++++++++++++++++----
 drivers/block/drbd/drbd_state.h    |   5 ++
 include/linux/drbd.h               |   3 +-
 6 files changed, 152 insertions(+), 96 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index c1eb4462096e..74637cc1461c 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1472,8 +1472,8 @@ extern void drbd_reconsider_max_bio_size(struct drbd_conf *mdev);
 extern enum drbd_state_rv drbd_set_role(struct drbd_conf *mdev,
 					enum drbd_role new_role,
 					int force);
-extern enum drbd_disk_state drbd_try_outdate_peer(struct drbd_conf *mdev);
-extern void drbd_try_outdate_peer_async(struct drbd_conf *mdev);
+extern bool conn_try_outdate_peer(struct drbd_tconn *tconn);
+extern void conn_try_outdate_peer_async(struct drbd_tconn *tconn);
 extern int drbd_khelper(struct drbd_conf *mdev, char *cmd);
 
 /* drbd_worker.c */
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index f1ec727f7df5..85290a9beb6d 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -366,116 +366,122 @@ int conn_khelper(struct drbd_tconn *tconn, char *cmd)
 	return ret;
 }
 
-enum drbd_disk_state drbd_try_outdate_peer(struct drbd_conf *mdev)
+static enum drbd_fencing_p highest_fencing_policy(struct drbd_tconn *tconn)
 {
+	enum drbd_fencing_p fp = FP_NOT_AVAIL;
+	struct drbd_conf *mdev;
+	int vnr;
+
+	idr_for_each_entry(&tconn->volumes, mdev, vnr) {
+		if (get_ldev_if_state(mdev, D_CONSISTENT)) {
+			fp = max_t(enum drbd_fencing_p, fp, mdev->ldev->dc.fencing);
+			put_ldev(mdev);
+		}
+	}
+
+	return fp;
+}
+
+bool conn_try_outdate_peer(struct drbd_tconn *tconn)
+{
+	union drbd_state mask = { };
+	union drbd_state val = { };
+	enum drbd_fencing_p fp;
 	char *ex_to_string;
 	int r;
-	enum drbd_disk_state nps;
-	enum drbd_fencing_p fp;
 
-	D_ASSERT(mdev->state.pdsk == D_UNKNOWN);
+	if (tconn->cstate >= C_WF_REPORT_PARAMS) {
+		conn_err(tconn, "Expected cstate < C_WF_REPORT_PARAMS\n");
+		return false;
+	}
 
-	if (get_ldev_if_state(mdev, D_CONSISTENT)) {
-		fp = mdev->ldev->dc.fencing;
-		put_ldev(mdev);
-	} else {
-		dev_warn(DEV, "Not fencing peer, I'm not even Consistent myself.\n");
-		nps = mdev->state.pdsk;
+	fp = highest_fencing_policy(tconn);
+	switch (fp) {
+	case FP_NOT_AVAIL:
+		conn_warn(tconn, "Not fencing peer, I'm not even Consistent myself.\n");
 		goto out;
+	case FP_DONT_CARE:
+		return true;
+	default: ;
 	}
 
-	r = drbd_khelper(mdev, "fence-peer");
+	r = conn_khelper(tconn, "fence-peer");
 
 	switch ((r>>8) & 0xff) {
 	case 3: /* peer is inconsistent */
 		ex_to_string = "peer is inconsistent or worse";
-		nps = D_INCONSISTENT;
+		mask.pdsk = D_MASK;
+		val.pdsk = D_INCONSISTENT;
 		break;
 	case 4: /* peer got outdated, or was already outdated */
 		ex_to_string = "peer was fenced";
-		nps = D_OUTDATED;
+		mask.pdsk = D_MASK;
+		val.pdsk = D_OUTDATED;
 		break;
 	case 5: /* peer was down */
-		if (mdev->state.disk == D_UP_TO_DATE) {
+		if (conn_highest_disk(tconn) == D_UP_TO_DATE) {
 			/* we will(have) create(d) a new UUID anyways... */
 			ex_to_string = "peer is unreachable, assumed to be dead";
-			nps = D_OUTDATED;
+			mask.pdsk = D_MASK;
+			val.pdsk = D_OUTDATED;
 		} else {
 			ex_to_string = "peer unreachable, doing nothing since disk != UpToDate";
-			nps = mdev->state.pdsk;
 		}
 		break;
 	case 6: /* Peer is primary, voluntarily outdate myself.
 		 * This is useful when an unconnected R_SECONDARY is asked to
 		 * become R_PRIMARY, but finds the other peer being active. */
 		ex_to_string = "peer is active";
-		dev_warn(DEV, "Peer is primary, outdating myself.\n");
-		nps = D_UNKNOWN;
-		_drbd_request_state(mdev, NS(disk, D_OUTDATED), CS_WAIT_COMPLETE);
+		conn_warn(tconn, "Peer is primary, outdating myself.\n");
+		mask.disk = D_MASK;
+		val.disk = D_OUTDATED;
 		break;
 	case 7:
 		if (fp != FP_STONITH)
-			dev_err(DEV, "fence-peer() = 7 && fencing != Stonith !!!\n");
+			conn_err(tconn, "fence-peer() = 7 && fencing != Stonith !!!\n");
 		ex_to_string = "peer was stonithed";
-		nps = D_OUTDATED;
+		mask.pdsk = D_MASK;
+		val.pdsk = D_OUTDATED;
 		break;
 	default:
 		/* The script is broken ... */
-		nps = D_UNKNOWN;
-		dev_err(DEV, "fence-peer helper broken, returned %d\n", (r>>8)&0xff);
-		return nps;
+		conn_err(tconn, "fence-peer helper broken, returned %d\n", (r>>8)&0xff);
+		return false; /* Eventually leave IO frozen */
 	}
 
-	dev_info(DEV, "fence-peer helper returned %d (%s)\n",
-			(r>>8) & 0xff, ex_to_string);
+	conn_info(tconn, "fence-peer helper returned %d (%s)\n",
+		  (r>>8) & 0xff, ex_to_string);
 
-out:
-	if (mdev->state.susp_fen && nps >= D_UNKNOWN) {
-		/* The handler was not successful... unfreeze here, the
-		   state engine can not unfreeze... */
-		_drbd_request_state(mdev, NS(susp_fen, 0), CS_VERBOSE);
-	}
+ out:
 
-	return nps;
+	/* Not using
+	   conn_request_state(tconn, mask, val, CS_VERBOSE);
+	   here, because we might were able to re-establish the connection in the
+	   meantime. */
+	spin_lock_irq(&tconn->req_lock);
+	if (tconn->cstate < C_WF_REPORT_PARAMS)
+		_conn_request_state(tconn, mask, val, CS_VERBOSE);
+	spin_unlock_irq(&tconn->req_lock);
+
+	return conn_highest_pdsk(tconn) <= D_OUTDATED;
 }
 
 static int _try_outdate_peer_async(void *data)
 {
-	struct drbd_conf *mdev = (struct drbd_conf *)data;
-	enum drbd_disk_state nps;
-	union drbd_state ns;
+	struct drbd_tconn *tconn = (struct drbd_tconn *)data;
 
-	nps = drbd_try_outdate_peer(mdev);
-
-	/* Not using
-	   drbd_request_state(mdev, NS(pdsk, nps));
-	   here, because we might were able to re-establish the connection
-	   in the meantime. This can only partially be solved in the state's
-	   engine is_valid_state() and is_valid_state_transition()
-	   functions.
-
-	   nps can be D_INCONSISTENT, D_OUTDATED or D_UNKNOWN.
-	   pdsk == D_INCONSISTENT while conn >= C_CONNECTED is valid,
-	   therefore we have to have the pre state change check here.
-	*/
-	spin_lock_irq(&mdev->tconn->req_lock);
-	ns = mdev->state;
-	if (ns.conn < C_WF_REPORT_PARAMS) {
-		ns.pdsk = nps;
-		_drbd_set_state(mdev, ns, CS_VERBOSE, NULL);
-	}
-	spin_unlock_irq(&mdev->tconn->req_lock);
+	conn_try_outdate_peer(tconn);
 
 	return 0;
 }
 
-void drbd_try_outdate_peer_async(struct drbd_conf *mdev)
+void conn_try_outdate_peer_async(struct drbd_tconn *tconn)
 {
 	struct task_struct *opa;
 
-	opa = kthread_run(_try_outdate_peer_async, mdev, "drbd%d_a_helper", mdev_to_minor(mdev));
+	opa = kthread_run(_try_outdate_peer_async, tconn, "drbd_async_h");
 	if (IS_ERR(opa))
-		dev_err(DEV, "out of mem, failed to invoke fence-peer helper\n");
+		conn_err(tconn, "out of mem, failed to invoke fence-peer helper\n");
 }
 
 enum drbd_state_rv
@@ -486,7 +492,6 @@ drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force)
 	int try = 0;
 	int forced = 0;
 	union drbd_state mask, val;
-	enum drbd_disk_state nps;
 
 	if (new_role == R_PRIMARY)
 		request_ping(mdev->tconn); /* Detect a dead peer ASAP */
@@ -519,32 +524,23 @@ drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force)
 		if (rv == SS_NO_UP_TO_DATE_DISK &&
 		    mdev->state.disk == D_CONSISTENT && mask.pdsk == 0) {
 			D_ASSERT(mdev->state.pdsk == D_UNKNOWN);
-			nps = drbd_try_outdate_peer(mdev);
 
-			if (nps == D_OUTDATED || nps == D_INCONSISTENT) {
+			if (conn_try_outdate_peer(mdev->tconn)) {
 				val.disk = D_UP_TO_DATE;
 				mask.disk = D_MASK;
 			}
-
-			val.pdsk = nps;
-			mask.pdsk = D_MASK;
-
 			continue;
 		}
 
 		if (rv == SS_NOTHING_TO_DO)
 			goto out;
 		if (rv == SS_PRIMARY_NOP && mask.pdsk == 0) {
-			nps = drbd_try_outdate_peer(mdev);
-
-			if (force && nps > D_OUTDATED) {
+			if (!conn_try_outdate_peer(mdev->tconn) && force) {
 				dev_warn(DEV, "Forced into split brain situation!\n");
-				nps = D_OUTDATED;
-			}
-
-			mask.pdsk = D_MASK;
-			val.pdsk  = nps;
+				mask.pdsk = D_MASK;
+				val.pdsk  = D_OUTDATED;
 
+			}
 			continue;
 		}
 		if (rv == SS_TWO_PRIMARIES) {
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 1fd871bc889e..91aa49f478e8 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -4030,9 +4030,11 @@ static void drbd_disconnect(struct drbd_tconn *tconn)
 	drbd_free_sock(tconn);
 
 	idr_for_each(&tconn->volumes, drbd_disconnected, tconn);
-
 	conn_info(tconn, "Connection closed\n");
 
+	if (conn_highest_role(tconn) == R_PRIMARY && conn_highest_pdsk(tconn) >= D_UNKNOWN)
+		conn_try_outdate_peer_async(tconn);
+
 	spin_lock_irq(&tconn->req_lock);
 	oc = tconn->cstate;
 	if (oc >= C_UNCONNECTED)
@@ -4109,9 +4111,6 @@ static int drbd_disconnected(int vnr, void *p, void *data)
 		put_ldev(mdev);
 	}
 
-	if (mdev->state.role == R_PRIMARY && fp >= FP_RESOURCE && mdev->state.pdsk >= D_UNKNOWN)
-		drbd_try_outdate_peer_async(mdev);
-
 	/* serialize with bitmap writeout triggered by the state change,
 	 * if any. */
 	wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 52ff1c7379e9..b4f668db3296 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -61,6 +61,73 @@ bool conn_all_vols_unconf(struct drbd_tconn *tconn)
 	return true;
 }
 
+/* Unfortunately the states where not correctly ordered, when
+   they where defined. therefore can not use max_t() here. */
+static enum drbd_role max_role(enum drbd_role role1, enum drbd_role role2)
+{
+	if (role1 == R_PRIMARY || role2 == R_PRIMARY)
+		return R_PRIMARY;
+	if (role1 == R_SECONDARY || role2 == R_SECONDARY)
+		return R_SECONDARY;
+	return R_UNKNOWN;
+}
+static enum drbd_role min_role(enum drbd_role role1, enum drbd_role role2)
+{
+	if (role1 == R_UNKNOWN || role2 == R_UNKNOWN)
+		return R_UNKNOWN;
+	if (role1 == R_SECONDARY || role2 == R_SECONDARY)
+		return R_SECONDARY;
+	return R_PRIMARY;
+}
+
+enum drbd_role conn_highest_role(struct drbd_tconn *tconn)
+{
+	enum drbd_role role = R_UNKNOWN;
+	struct drbd_conf *mdev;
+	int vnr;
+
+	idr_for_each_entry(&tconn->volumes, mdev, vnr)
+		role = max_role(role, mdev->state.role);
+
+	return role;
+}
+
+enum drbd_role conn_highest_peer(struct drbd_tconn *tconn)
+{
+	enum drbd_role peer = R_UNKNOWN;
+	struct drbd_conf *mdev;
+	int vnr;
+
+	idr_for_each_entry(&tconn->volumes, mdev, vnr)
+		peer = max_role(peer, mdev->state.peer);
+
+	return peer;
+}
+
+enum drbd_disk_state conn_highest_disk(struct drbd_tconn *tconn)
+{
+	enum drbd_disk_state ds = D_DISKLESS;
+	struct drbd_conf *mdev;
+	int vnr;
+
+	idr_for_each_entry(&tconn->volumes, mdev, vnr)
+		ds = max_t(enum drbd_disk_state, ds, mdev->state.disk);
+
+	return ds;
+}
+
+enum drbd_disk_state conn_highest_pdsk(struct drbd_tconn *tconn)
+{
+	enum drbd_disk_state ds = D_DISKLESS;
+	struct drbd_conf *mdev;
+	int vnr;
+
+	idr_for_each_entry(&tconn->volumes, mdev, vnr)
+		ds = max_t(enum drbd_disk_state, ds, mdev->state.pdsk);
+
+	return ds;
+}
+
 /**
  * cl_wide_st_chg() - true if the state change is a cluster wide one
  * @mdev:	DRBD device.
@@ -329,18 +396,6 @@ static void print_state_change(struct drbd_conf *mdev, union drbd_state os, unio
 		dev_info(DEV, "%s\n", pb);
 }
 
-static bool vol_has_primary_peer(struct drbd_tconn *tconn)
-{
-	struct drbd_conf *mdev;
-	int vnr;
-
-	idr_for_each_entry(&tconn->volumes, mdev, vnr) {
-		if (mdev->state.peer == R_PRIMARY)
-			return true;
-	}
-	return false;
-}
-
 /**
  * is_valid_state() - Returns an SS_ error code if ns is not valid
  * @mdev:	DRBD device.
@@ -364,7 +419,7 @@ is_valid_state(struct drbd_conf *mdev, union drbd_state ns)
 		if (!mdev->tconn->net_conf->two_primaries && ns.role == R_PRIMARY) {
 			if (ns.peer == R_PRIMARY)
 				rv = SS_TWO_PRIMARIES;
-			else if (vol_has_primary_peer(mdev->tconn))
+			else if (conn_highest_peer(mdev->tconn) == R_PRIMARY)
 				rv = SS_O_VOL_PEER_PRI;
 			}
 		put_net_conf(mdev->tconn);
@@ -1390,8 +1445,8 @@ static int _set_state_itr_fn(int vnr, void *p, void *data)
 
 	rv = __drbd_set_state(mdev, ns, flags, NULL);
 
-	ms.role = max_t(enum drbd_role, mdev->state.role, ms.role);
-	ms.peer = max_t(enum drbd_role, mdev->state.peer, ms.peer);
+	ms.role = max_role(ns.role, ms.role);
+	ms.peer = max_role(ns.peer, ms.peer);
 	ms.disk = max_t(enum drbd_role, mdev->state.disk, ms.disk);
 	ms.pdsk = max_t(enum drbd_role, mdev->state.pdsk, ms.pdsk);
 	params->ms = ms;
diff --git a/drivers/block/drbd/drbd_state.h b/drivers/block/drbd/drbd_state.h
index 55df0728bc88..394a1998acd9 100644
--- a/drivers/block/drbd/drbd_state.h
+++ b/drivers/block/drbd/drbd_state.h
@@ -110,4 +110,9 @@ static inline int drbd_request_state(struct drbd_conf *mdev,
 	return _drbd_request_state(mdev, mask, val, CS_VERBOSE + CS_ORDERED);
 }
 
+enum drbd_role conn_highest_role(struct drbd_tconn *tconn);
+enum drbd_role conn_highest_peer(struct drbd_tconn *tconn);
+enum drbd_disk_state conn_highest_disk(struct drbd_tconn *tconn);
+enum drbd_disk_state conn_highest_pdsk(struct drbd_tconn *tconn);
+
 #endif
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 9cdb888607ae..60d308819096 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -65,7 +65,8 @@ enum drbd_io_error_p {
 };
 
 enum drbd_fencing_p {
-	FP_DONT_CARE,
+	FP_NOT_AVAIL = -1, /* Not a policy */
+	FP_DONT_CARE = 0,
 	FP_RESOURCE,
 	FP_STONITH
 };
-- 
cgit v1.2.3-55-g7522


From 0c8e36d9b843be56e4e43d4ef3c3eb6a97205599 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 30 Mar 2011 16:00:17 +0200
Subject: drbd: Introduce protocol version 100 headers

The 8 byte header finally becomes too small. With the protocol 100 header we
have 16 bit for the volume number, proper 32 bit for the data length, and
32 bit for further extensions in the future.

Previous versions of drbd are using version 80 headers for all packets
short enough for protocol 80.  They support both header versions in
worker context, but only version 80 headers in asynchronous context.
For backwards compatibility, continue to use version 80 headers for
short packets before protocol version 100.

From protocol version 100 on, use the same header version for all
packets.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h      |  8 ++++++++
 drivers/block/drbd/drbd_main.c     | 32 ++++++++++++++++++++++++++------
 drivers/block/drbd/drbd_nl.c       |  3 +--
 drivers/block/drbd/drbd_receiver.c | 14 ++++++++++++--
 include/linux/drbd.h               |  1 +
 include/linux/drbd_genl.h          |  2 --
 include/linux/drbd_limits.h        |  2 ++
 7 files changed, 50 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 6d55bb75a081..bf1aad683387 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -307,6 +307,14 @@ struct p_header95 {
 	u32	  length;	/* Use only 24 bits of that. Ignore the highest 8 bit. */
 } __packed;
 
+struct p_header100 {
+	u32	  magic;
+	u16	  volume;
+	u16	  command;
+	u32	  length;
+	u32	  pad;
+} __packed;
+
 extern unsigned int drbd_header_size(struct drbd_tconn *tconn);
 
 /* these defines must not be changed without changing the protocol version */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index b9dcc50135c4..5d9112cefcd7 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -698,9 +698,15 @@ void drbd_thread_current_set_cpu(struct drbd_thread *thi)
  */
 unsigned int drbd_header_size(struct drbd_tconn *tconn)
 {
-	BUILD_BUG_ON(sizeof(struct p_header80) != sizeof(struct p_header95));
-	BUILD_BUG_ON(!IS_ALIGNED(sizeof(struct p_header80), 8));
-	return sizeof(struct p_header80);
+	if (tconn->agreed_pro_version >= 100) {
+		BUILD_BUG_ON(!IS_ALIGNED(sizeof(struct p_header100), 8));
+		return sizeof(struct p_header100);
+	} else {
+		BUILD_BUG_ON(sizeof(struct p_header80) !=
+			     sizeof(struct p_header95));
+		BUILD_BUG_ON(!IS_ALIGNED(sizeof(struct p_header80), 8));
+		return sizeof(struct p_header80);
+	}
 }
 
 static unsigned int prepare_header80(struct p_header80 *h, enum drbd_packet cmd, int size)
@@ -719,10 +725,24 @@ static unsigned int prepare_header95(struct p_header95 *h, enum drbd_packet cmd,
 	return sizeof(struct p_header95);
 }
 
-static unsigned int prepare_header(struct drbd_tconn *tconn, int vnr, void *buffer,
-				   enum drbd_packet cmd, int size)
+static unsigned int prepare_header100(struct p_header100 *h, enum drbd_packet cmd,
+				      int size, int vnr)
+{
+	h->magic = cpu_to_be32(DRBD_MAGIC_100);
+	h->volume = cpu_to_be16(vnr);
+	h->command = cpu_to_be16(cmd);
+	h->length = cpu_to_be32(size);
+	h->pad = 0;
+	return sizeof(struct p_header100);
+}
+
+static unsigned int prepare_header(struct drbd_tconn *tconn, int vnr,
+				   void *buffer, enum drbd_packet cmd, int size)
 {
-	if (tconn->agreed_pro_version >= 95)
+	if (tconn->agreed_pro_version >= 100)
+		return prepare_header100(buffer, cmd, size, vnr);
+	else if (tconn->agreed_pro_version >= 95 &&
+		 size > DRBD_MAX_SIZE_H80_PACKET)
 		return prepare_header95(buffer, cmd, size);
 	else
 		return prepare_header80(buffer, cmd, size);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index d9bb1a5c756a..0f52b88719c8 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2833,8 +2833,7 @@ int drbd_adm_add_minor(struct sk_buff *skb, struct genl_info *info)
 		retcode = ERR_INVALID_REQUEST;
 		goto out;
 	}
-	/* FIXME we need a define here */
-	if (adm_ctx.volume >= 256) {
+	if (adm_ctx.volume > DRBD_VOLUME_MAX) {
 		drbd_msg_put_info("requested volume id out of range");
 		retcode = ERR_INVALID_REQUEST;
 		goto out;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 7e0ab2246fb6..311b95453cb7 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -983,8 +983,18 @@ static int decode_header(struct drbd_tconn *tconn, void *header, struct packet_i
 {
 	unsigned int header_size = drbd_header_size(tconn);
 
-	if (header_size == sizeof(struct p_header95) &&
-	    *(__be16 *)header == cpu_to_be16(DRBD_MAGIC_BIG)) {
+	if (header_size == sizeof(struct p_header100) &&
+	    *(__be32 *)header == cpu_to_be32(DRBD_MAGIC_100)) {
+		struct p_header100 *h = header;
+		if (h->pad != 0) {
+			conn_err(tconn, "Header padding is not zero\n");
+			return -EINVAL;
+		}
+		pi->vnr = be16_to_cpu(h->volume);
+		pi->cmd = be16_to_cpu(h->command);
+		pi->size = be32_to_cpu(h->length);
+	} else if (header_size == sizeof(struct p_header95) &&
+		   *(__be16 *)header == cpu_to_be16(DRBD_MAGIC_BIG)) {
 		struct p_header95 *h = header;
 
 		pi->cmd = be16_to_cpu(h->command);
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 60d308819096..fe8d6ba31bcb 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -341,6 +341,7 @@ enum drbd_timeout_flag {
 
 #define DRBD_MAGIC 0x83740267
 #define DRBD_MAGIC_BIG 0x835a
+#define DRBD_MAGIC_100 0x8620ec20
 
 /* how I came up with this magic?
  * base64 decode "actlog==" ;) */
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 938e8560a833..10144d546a66 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -95,8 +95,6 @@ GENL_struct(DRBD_NLA_CFG_REPLY, 1, drbd_cfg_reply,
  * and/or the replication group (aka resource) name,
  * and the volume id within the resource. */
 GENL_struct(DRBD_NLA_CFG_CONTEXT, 2, drbd_cfg_context,
-		/* currently only 256 volumes per group,
-		 * but maybe we still change that */
 	__u32_field(1, GENLA_F_MANDATORY,	ctx_volume)
 	__str_field(2, GENLA_F_MANDATORY,	ctx_conn_name, 128)
 )
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 659a8eb38830..7f5149bef70e 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -19,6 +19,8 @@
 #define DRBD_MINOR_COUNT_MAX 256
 #define DRBD_MINOR_COUNT_DEF 32
 
+#define DRBD_VOLUME_MAX 65535
+
 #define DRBD_DIALOG_REFRESH_MIN 0
 #define DRBD_DIALOG_REFRESH_MAX 600
 
-- 
cgit v1.2.3-55-g7522


From b032b6fa3528d6eed972db32257cb316a66e0dac Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Wed, 13 Apr 2011 18:16:10 -0700
Subject: drbd: Allow online change of replication protocol only with agreed_pv
 >= 100

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c | 5 +++++
 include/linux/drbd.h         | 1 +
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 40de384aade6..d4b29fd603f4 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1671,6 +1671,11 @@ check_net_options(struct drbd_tconn *tconn, struct net_conf *new_conf)
 	struct drbd_conf *mdev;
 	int i;
 
+	if (tconn->net_conf && tconn->agreed_pro_version < 100 &&
+	    tconn->cstate == C_WF_REPORT_PARAMS &&
+	    new_conf->wire_protocol != tconn->net_conf->wire_protocol)
+		return ERR_NEED_APV_100;
+
 	if (new_conf->two_primaries &&
 	    (new_conf->wire_protocol != DRBD_PROT_C))
 		return ERR_NOT_PROTO_C;
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index fe8d6ba31bcb..6c7c85d8fc41 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -160,6 +160,7 @@ enum drbd_ret_code {
 	ERR_MINOR_CONFIGURED    = 160,
 	ERR_MINOR_EXISTS	= 161,
 	ERR_INVALID_REQUEST	= 162,
+	ERR_NEED_APV_100	= 163,
 
 	/* insert new ones above this line */
 	AFTER_LAST_ERR_CODE
-- 
cgit v1.2.3-55-g7522


From d8cd289dbe69ce9b8115d6f200ceff657e5dafa0 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Tue, 3 May 2011 12:27:11 +0200
Subject: drbd: Remove left-over unused define

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_limits.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 7f5149bef70e..bcebb016fda3 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -170,5 +170,4 @@
 
 #define DRBD_PROTOCOL_DEF DRBD_PROT_C
 
-#undef RANGE
 #endif
-- 
cgit v1.2.3-55-g7522


From b966b5dd8e17e6c105ca55533fd412de5d5b429e Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Tue, 3 May 2011 14:56:09 +0200
Subject: drbd: Generate the drbd_set_*_defaults() functions from drbd_genl.h

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h     |  2 +-
 drivers/block/drbd/drbd_main.c    |  2 +-
 drivers/block/drbd/drbd_nl.c      | 86 +++++-------------------------------
 include/linux/drbd_genl.h         | 91 +++++++++++++++++++--------------------
 include/linux/genl_magic_func.h   | 26 +++++++++++
 include/linux/genl_magic_struct.h |  8 ++++
 6 files changed, 91 insertions(+), 124 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 44f77265d2b0..8655fcb82028 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1390,7 +1390,7 @@ extern int is_valid_ar_handle(struct drbd_request *, sector_t);
 
 
 /* drbd_nl.c */
-extern void drbd_set_res_opts_default(struct res_opts *r);
+extern void drbd_set_res_opts_defaults(struct res_opts *r);
 extern int drbd_msg_put_info(const char *info);
 extern void drbd_suspend_io(struct drbd_conf *mdev);
 extern void drbd_resume_io(struct drbd_conf *mdev);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 427e959e4869..4ae3e7a99d7c 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2488,7 +2488,7 @@ struct drbd_tconn *conn_create(const char *name)
 	drbd_thread_init(tconn, &tconn->worker, drbd_worker, "worker");
 	drbd_thread_init(tconn, &tconn->asender, drbd_asender, "asender");
 
-	drbd_set_res_opts_default(&tconn->res_opts);
+	drbd_set_res_opts_defaults(&tconn->res_opts);
 
 	down_write(&drbd_cfg_rwsem);
 	kref_init(&tconn->kref);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 7320ac00f0fb..f5732cf46c2f 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1090,77 +1090,6 @@ static bool should_set_defaults(struct genl_info *info)
 	return 0 != (flags & DRBD_GENL_F_SET_DEFAULTS);
 }
 
-/* Maybe we should we generate these functions
- * from the drbd_genl.h magic as well?
- * That way we would not "accidentally forget" to add defaults here. */
-
-#define RESET_ARRAY_FIELD(field) do { \
-	memset(field, 0, sizeof(field)); \
-	field ## _len = 0; \
-} while (0)
-void drbd_set_res_opts_default(struct res_opts *r)
-{
-	RESET_ARRAY_FIELD(r->cpu_mask);
-	r->on_no_data  = DRBD_ON_NO_DATA_DEF;
-}
-
-static void drbd_set_net_conf_defaults(struct net_conf *nc)
-{
-	/* Do NOT (re)set those fields marked as GENLA_F_INVARIANT
-	 * in drbd_genl.h, they can only be change with disconnect/reconnect */
-	RESET_ARRAY_FIELD(nc->shared_secret);
-
-	RESET_ARRAY_FIELD(nc->cram_hmac_alg);
-	RESET_ARRAY_FIELD(nc->integrity_alg);
-	RESET_ARRAY_FIELD(nc->verify_alg);
-	RESET_ARRAY_FIELD(nc->csums_alg);
-#undef RESET_ARRAY_FIELD
-
-	nc->wire_protocol = DRBD_PROTOCOL_DEF;
-	nc->try_connect_int = DRBD_CONNECT_INT_DEF;
-	nc->timeout = DRBD_TIMEOUT_DEF;
-	nc->ping_int = DRBD_PING_INT_DEF;
-	nc->ping_timeo = DRBD_PING_TIMEO_DEF;
-	nc->sndbuf_size = DRBD_SNDBUF_SIZE_DEF;
-	nc->rcvbuf_size = DRBD_RCVBUF_SIZE_DEF;
-	nc->ko_count = DRBD_KO_COUNT_DEF;
-	nc->max_buffers = DRBD_MAX_BUFFERS_DEF;
-	nc->max_epoch_size = DRBD_MAX_EPOCH_SIZE_DEF;
-	nc->unplug_watermark = DRBD_UNPLUG_WATERMARK_DEF;
-	nc->after_sb_0p = DRBD_AFTER_SB_0P_DEF;
-	nc->after_sb_1p = DRBD_AFTER_SB_1P_DEF;
-	nc->after_sb_2p = DRBD_AFTER_SB_2P_DEF;
-	nc->rr_conflict = DRBD_RR_CONFLICT_DEF;
-	nc->on_congestion = DRBD_ON_CONGESTION_DEF;
-	nc->cong_fill = DRBD_CONG_FILL_DEF;
-	nc->cong_extents = DRBD_CONG_EXTENTS_DEF;
-	nc->two_primaries = 0;
-	nc->no_cork = 0;
-	nc->always_asbp = 0;
-	nc->use_rle = 0;
-}
-
-static void drbd_set_disk_conf_defaults(struct disk_conf *dc)
-{
-	/* Do NOT (re)set those fields marked as GENLA_F_INVARIANT
-	 * in drbd_genl.h, they can only be change with detach/reattach */
-	dc->on_io_error = DRBD_ON_IO_ERROR_DEF;
-	dc->fencing = DRBD_FENCING_DEF;
-	dc->resync_rate = DRBD_RATE_DEF;
-	dc->resync_after = DRBD_AFTER_DEF;
-	dc->al_extents = DRBD_AL_EXTENTS_DEF;
-	dc->c_plan_ahead = DRBD_C_PLAN_AHEAD_DEF;
-	dc->c_delay_target = DRBD_C_DELAY_TARGET_DEF;
-	dc->c_fill_target = DRBD_C_FILL_TARGET_DEF;
-	dc->c_max_rate = DRBD_C_MAX_RATE_DEF;
-	dc->c_min_rate = DRBD_C_MIN_RATE_DEF;
-	dc->no_disk_barrier = 0;
-	dc->no_disk_flush = 0;
-	dc->no_disk_drain = 0;
-	dc->no_md_flush = 0;
-}
-
-
 int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 {
 	enum drbd_ret_code retcode;
@@ -1198,7 +1127,7 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 
 	memcpy(new_disk_conf, &mdev->ldev->dc, sizeof(*new_disk_conf));
 	if (should_set_defaults(info))
-		drbd_set_disk_conf_defaults(new_disk_conf);
+		set_disk_conf_defaults(new_disk_conf);
 
 	err = disk_conf_from_attrs_for_change(new_disk_conf, info);
 	if (err) {
@@ -1315,7 +1244,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		goto fail;
 	}
 
-	drbd_set_disk_conf_defaults(&nbc->dc);
+	set_disk_conf_defaults(&nbc->dc);
 
 	err = disk_conf_from_attrs(&nbc->dc, info);
 	if (err) {
@@ -1911,7 +1840,7 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
 
 	*new_conf = *old_conf;
 	if (should_set_defaults(info))
-		drbd_set_net_conf_defaults(new_conf);
+		set_net_conf_defaults(new_conf);
 
 	err = net_conf_from_attrs_for_change(new_conf, info);
 	if (err) {
@@ -2029,7 +1958,7 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 		goto fail;
 	}
 
-	drbd_set_net_conf_defaults(new_conf);
+	set_net_conf_defaults(new_conf);
 
 	err = net_conf_from_attrs(new_conf, info);
 	if (err) {
@@ -2301,6 +2230,11 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
+void drbd_set_res_opts_defaults(struct res_opts *r)
+{
+	return set_res_opts_defaults(r);
+}
+
 int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info)
 {
 	enum drbd_ret_code retcode;
@@ -2325,7 +2259,7 @@ int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info)
 
 	res_opts = tconn->res_opts;
 	if (should_set_defaults(info))
-		drbd_set_res_opts_default(&res_opts);
+		set_res_opts_defaults(&res_opts);
 
 	err = res_opts_from_attrs(&res_opts, info);
 	if (err) {
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 10144d546a66..549800668cb9 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -110,63 +110,62 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	 * but it won't propagate through the stack */
 	__u32_field(5, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	max_bio_bvecs)
 
-	__u32_field(6, GENLA_F_MANDATORY,	on_io_error)
-	__u32_field(7, GENLA_F_MANDATORY,	fencing)
-
-	__u32_field(8,	GENLA_F_MANDATORY,	resync_rate)
-	__u32_field(9,	GENLA_F_MANDATORY,	resync_after)
-	__u32_field(10,	GENLA_F_MANDATORY,	al_extents)
-	__u32_field(11,	GENLA_F_MANDATORY,	c_plan_ahead)
-	__u32_field(12,	GENLA_F_MANDATORY,	c_delay_target)
-	__u32_field(13,	GENLA_F_MANDATORY,	c_fill_target)
-	__u32_field(14,	GENLA_F_MANDATORY,	c_max_rate)
-	__u32_field(15,	GENLA_F_MANDATORY,	c_min_rate)
-
-	__flg_field(16, GENLA_F_MANDATORY,	no_disk_barrier)
-	__flg_field(17, GENLA_F_MANDATORY,	no_disk_flush)
-	__flg_field(18, GENLA_F_MANDATORY,	no_disk_drain)
-	__flg_field(19, GENLA_F_MANDATORY,	no_md_flush)
-
+	__u32_field_def(6, GENLA_F_MANDATORY,	on_io_error, DRBD_ON_IO_ERROR_DEF)
+	__u32_field_def(7, GENLA_F_MANDATORY,	fencing, DRBD_FENCING_DEF)
+
+	__u32_field_def(8,	GENLA_F_MANDATORY,	resync_rate, DRBD_RATE_DEF)
+	__u32_field_def(9,	GENLA_F_MANDATORY,	resync_after, DRBD_AFTER_DEF)
+	__u32_field_def(10,	GENLA_F_MANDATORY,	al_extents, DRBD_AL_EXTENTS_DEF)
+	__u32_field_def(11,	GENLA_F_MANDATORY,	c_plan_ahead, DRBD_C_PLAN_AHEAD_DEF)
+	__u32_field_def(12,	GENLA_F_MANDATORY,	c_delay_target, DRBD_C_DELAY_TARGET_DEF)
+	__u32_field_def(13,	GENLA_F_MANDATORY,	c_fill_target, DRBD_C_FILL_TARGET_DEF)
+	__u32_field_def(14,	GENLA_F_MANDATORY,	c_max_rate, DRBD_C_MAX_RATE_DEF)
+	__u32_field_def(15,	GENLA_F_MANDATORY,	c_min_rate, DRBD_C_MIN_RATE_DEF)
+
+	__flg_field_def(16, GENLA_F_MANDATORY,	no_disk_barrier, 0)
+	__flg_field_def(17, GENLA_F_MANDATORY,	no_disk_flush, 0)
+	__flg_field_def(18, GENLA_F_MANDATORY,	no_disk_drain, 0)
+	__flg_field_def(19, GENLA_F_MANDATORY,	no_md_flush, 0)
 )
 
 GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
-	__str_field(1,	GENLA_F_MANDATORY,	cpu_mask,       32)
-	__u32_field(2,	GENLA_F_MANDATORY,	on_no_data)
+	__str_field_def(1,	GENLA_F_MANDATORY,	cpu_mask,       32)
+	__u32_field_def(2,	GENLA_F_MANDATORY,	on_no_data, DRBD_ON_NO_DATA_DEF)
 )
 
 GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
 	__bin_field(1,	GENLA_F_REQUIRED | GENLA_F_INVARIANT,	my_addr,	128)
 	__bin_field(2,	GENLA_F_REQUIRED | GENLA_F_INVARIANT,	peer_addr,	128)
-	__str_field(3,	GENLA_F_MANDATORY | GENLA_F_SENSITIVE,
+	__str_field_def(3,	GENLA_F_MANDATORY | GENLA_F_SENSITIVE,
 						shared_secret,	SHARED_SECRET_MAX)
-	__str_field(4,	GENLA_F_MANDATORY,	cram_hmac_alg,	SHARED_SECRET_MAX)
-	__str_field(5,	GENLA_F_MANDATORY,	integrity_alg,	SHARED_SECRET_MAX)
-	__str_field(6,	GENLA_F_MANDATORY,	verify_alg,     SHARED_SECRET_MAX)
-	__str_field(7,	GENLA_F_MANDATORY,	csums_alg,	SHARED_SECRET_MAX)
-	__u32_field(8,	GENLA_F_MANDATORY,	wire_protocol)
-	__u32_field(9,	GENLA_F_MANDATORY,	try_connect_int)
-	__u32_field(10,	GENLA_F_MANDATORY,	timeout)
-	__u32_field(11,	GENLA_F_MANDATORY,	ping_int)
-	__u32_field(12,	GENLA_F_MANDATORY,	ping_timeo)
-	__u32_field(13,	GENLA_F_MANDATORY,	sndbuf_size)
-	__u32_field(14,	GENLA_F_MANDATORY,	rcvbuf_size)
-	__u32_field(15,	GENLA_F_MANDATORY,	ko_count)
-	__u32_field(16,	GENLA_F_MANDATORY,	max_buffers)
-	__u32_field(17,	GENLA_F_MANDATORY,	max_epoch_size)
-	__u32_field(18,	GENLA_F_MANDATORY,	unplug_watermark)
-	__u32_field(19,	GENLA_F_MANDATORY,	after_sb_0p)
-	__u32_field(20,	GENLA_F_MANDATORY,	after_sb_1p)
-	__u32_field(21,	GENLA_F_MANDATORY,	after_sb_2p)
-	__u32_field(22,	GENLA_F_MANDATORY,	rr_conflict)
-	__u32_field(23,	GENLA_F_MANDATORY,	on_congestion)
-	__u32_field(24,	GENLA_F_MANDATORY,	cong_fill)
-	__u32_field(25,	GENLA_F_MANDATORY,	cong_extents)
-	__flg_field(26, GENLA_F_MANDATORY,	two_primaries)
+	__str_field_def(4,	GENLA_F_MANDATORY,	cram_hmac_alg,	SHARED_SECRET_MAX)
+	__str_field_def(5,	GENLA_F_MANDATORY,	integrity_alg,	SHARED_SECRET_MAX)
+	__str_field_def(6,	GENLA_F_MANDATORY,	verify_alg,     SHARED_SECRET_MAX)
+	__str_field_def(7,	GENLA_F_MANDATORY,	csums_alg,	SHARED_SECRET_MAX)
+	__u32_field_def(8,	GENLA_F_MANDATORY,	wire_protocol, DRBD_PROTOCOL_DEF)
+	__u32_field_def(9,	GENLA_F_MANDATORY,	try_connect_int, DRBD_CONNECT_INT_DEF)
+	__u32_field_def(10,	GENLA_F_MANDATORY,	timeout, DRBD_TIMEOUT_DEF)
+	__u32_field_def(11,	GENLA_F_MANDATORY,	ping_int, DRBD_PING_INT_DEF)
+	__u32_field_def(12,	GENLA_F_MANDATORY,	ping_timeo, DRBD_PING_TIMEO_DEF)
+	__u32_field_def(13,	GENLA_F_MANDATORY,	sndbuf_size, DRBD_SNDBUF_SIZE_DEF)
+	__u32_field_def(14,	GENLA_F_MANDATORY,	rcvbuf_size, DRBD_RCVBUF_SIZE_DEF)
+	__u32_field_def(15,	GENLA_F_MANDATORY,	ko_count, DRBD_KO_COUNT_DEF)
+	__u32_field_def(16,	GENLA_F_MANDATORY,	max_buffers, DRBD_MAX_BUFFERS_DEF)
+	__u32_field_def(17,	GENLA_F_MANDATORY,	max_epoch_size, DRBD_MAX_EPOCH_SIZE_DEF)
+	__u32_field_def(18,	GENLA_F_MANDATORY,	unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF)
+	__u32_field_def(19,	GENLA_F_MANDATORY,	after_sb_0p, DRBD_AFTER_SB_0P_DEF)
+	__u32_field_def(20,	GENLA_F_MANDATORY,	after_sb_1p, DRBD_AFTER_SB_1P_DEF)
+	__u32_field_def(21,	GENLA_F_MANDATORY,	after_sb_2p, DRBD_AFTER_SB_2P_DEF)
+	__u32_field_def(22,	GENLA_F_MANDATORY,	rr_conflict, DRBD_RR_CONFLICT_DEF)
+	__u32_field_def(23,	GENLA_F_MANDATORY,	on_congestion, DRBD_ON_CONGESTION_DEF)
+	__u32_field_def(24,	GENLA_F_MANDATORY,	cong_fill, DRBD_CONG_FILL_DEF)
+	__u32_field_def(25,	GENLA_F_MANDATORY,	cong_extents, DRBD_CONG_EXTENTS_DEF)
+	__flg_field_def(26, GENLA_F_MANDATORY,	two_primaries, 0)
 	__flg_field(27, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	want_lose)
-	__flg_field(28, GENLA_F_MANDATORY,	no_cork)
-	__flg_field(29, GENLA_F_MANDATORY,	always_asbp)
+	__flg_field_def(28, GENLA_F_MANDATORY,	no_cork, 0)
+	__flg_field_def(29, GENLA_F_MANDATORY,	always_asbp, 0)
 	__flg_field(30, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	dry_run)
-	__flg_field(31,	GENLA_F_MANDATORY,	use_rle)
+	__flg_field_def(31,	GENLA_F_MANDATORY,	use_rle, 0)
 )
 
 GENL_struct(DRBD_NLA_SET_ROLE_PARMS, 6, set_role_parms,
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index e458282a3728..e908f1c50355 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -427,6 +427,32 @@ static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb,		\
 
 #include GENL_MAGIC_INCLUDE_FILE
 
+
+/* Functions for initializing structs to default values.  */
+
+#undef __field
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)
+#undef __array
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put)
+#undef __u32_field_def
+#define __u32_field_def(attr_nr, attr_flag, name, default)		\
+	x->name = default;
+#undef __flg_field_def
+#define __flg_field_def(attr_nr, attr_flag, name, default)		\
+	x->name = default;
+#undef __str_field_def
+#define __str_field_def(attr_nr, attr_flag, name, maxlen)		\
+	memset(x->name, 0, sizeof(x->name));				\
+	x->name ## _len = 0;
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
+static void set_ ## s_name ## _defaults(struct s_name *x) __attribute__((unused)); \
+static void set_ ## s_name ## _defaults(struct s_name *x) {	\
+s_fields								\
+}
+
+#include GENL_MAGIC_INCLUDE_FILE
+
 #endif /* __KERNEL__ */
 
 /* }}}1 */
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index 9a605b9ee834..f2c7cc7831df 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -107,6 +107,14 @@ enum {
 	__array(attr_nr, attr_flag, name, NLA_BINARY, char, maxlen, \
 			nla_memcpy, NLA_PUT)
 
+/* fields with default values */
+#define __flg_field_def(attr_nr, attr_flag, name, default) \
+	__flg_field(attr_nr, attr_flag, name)
+#define __u32_field_def(attr_nr, attr_flag, name, default) \
+	__u32_field(attr_nr, attr_flag, name)
+#define __str_field_def(attr_nr, attr_flag, name, maxlen) \
+	__str_field(attr_nr, attr_flag, name, maxlen)
+
 #define __nla_put_flag(skb, attrtype, value)		\
 	do {						\
 		if (value)				\
-- 
cgit v1.2.3-55-g7522


From 563e4cf25ec804eb02cd30a41baa2fcc6c06679b Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Wed, 4 May 2011 10:33:52 +0200
Subject: drbd: Introduce __s32_field in the genetlink macro magic

...and drop explicit typecasts (int)meta_dev_idx < 0.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c      | 8 ++++----
 include/linux/drbd_genl.h         | 2 +-
 include/linux/genl_magic_struct.h | 3 +++
 3 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index a1854e3aa15e..b8ea4807c981 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1253,7 +1253,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		goto fail;
 	}
 
-	if ((int)nbc->dc.meta_dev_idx < DRBD_MD_INDEX_FLEX_INT) {
+	if (nbc->dc.meta_dev_idx < DRBD_MD_INDEX_FLEX_INT) {
 		retcode = ERR_MD_IDX_INVALID;
 		goto fail;
 	}
@@ -1289,7 +1289,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	 */
 	bdev = blkdev_get_by_path(nbc->dc.meta_dev,
 				  FMODE_READ | FMODE_WRITE | FMODE_EXCL,
-				  ((int)nbc->dc.meta_dev_idx < 0) ?
+				  (nbc->dc.meta_dev_idx < 0) ?
 				  (void *)mdev : (void *)drbd_m_holder);
 	if (IS_ERR(bdev)) {
 		dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.meta_dev,
@@ -1325,7 +1325,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		goto fail;
 	}
 
-	if ((int)nbc->dc.meta_dev_idx < 0) {
+	if (nbc->dc.meta_dev_idx < 0) {
 		max_possible_sectors = DRBD_MAX_SECTORS_FLEX;
 		/* at least one MB, otherwise it does not make sense */
 		min_md_device_sectors = (2<<10);
@@ -1356,7 +1356,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		dev_warn(DEV, "==> truncating very big lower level device "
 			"to currently maximum possible %llu sectors <==\n",
 			(unsigned long long) max_possible_sectors);
-		if ((int)nbc->dc.meta_dev_idx >= 0)
+		if (nbc->dc.meta_dev_idx >= 0)
 			dev_warn(DEV, "==>> using internal or flexible "
 				      "meta data may help <<==\n");
 	}
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 549800668cb9..f143e3c0f33b 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -102,7 +102,7 @@ GENL_struct(DRBD_NLA_CFG_CONTEXT, 2, drbd_cfg_context,
 GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__str_field(1, GENLA_F_REQUIRED | GENLA_F_INVARIANT,	backing_dev,	128)
 	__str_field(2, GENLA_F_REQUIRED | GENLA_F_INVARIANT,	meta_dev,	128)
-	__u32_field(3, GENLA_F_REQUIRED | GENLA_F_INVARIANT,	meta_dev_idx)
+	__s32_field(3, GENLA_F_REQUIRED | GENLA_F_INVARIANT,	meta_dev_idx)
 
 	/* use the resize command to try and change the disk_size */
 	__u64_field(4, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	disk_size)
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index f2c7cc7831df..ddbdd0a24476 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -97,6 +97,9 @@ enum {
 #define __u32_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U32, __u32, \
 			nla_get_u32, NLA_PUT_U32)
+#define __s32_field(attr_nr, attr_flag, name)	\
+	__field(attr_nr, attr_flag, name, NLA_U32, __s32, \
+			nla_get_u32, NLA_PUT_U32)
 #define __u64_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U64, __u64, \
 			nla_get_u64, NLA_PUT_U64)
-- 
cgit v1.2.3-55-g7522


From a5d8e1fb9d22851de89bbf52db6b11c56b895dd4 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 4 May 2011 16:06:51 +0200
Subject: drbd: Convert boolean flags on netlink from NLA_FLAG to NLA_U8

Flags of type NLA_FLAG are either present or absent, but do not have a
value by themselves.  Use type NLA_U8 for our boolean flags instead, and
use the value to determine if the flag should be on or off.

On the drbdsetup command line, all those flags have an optional yes/no
argument which defaults to yes.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/genl_magic_struct.h | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index ddbdd0a24476..b1ddbb5bd725 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -86,8 +86,8 @@ enum {
 
 /* possible field types */
 #define __flg_field(attr_nr, attr_flag, name) \
-	__field(attr_nr, attr_flag, name, NLA_FLAG, char, \
-			nla_get_flag, __nla_put_flag)
+	__field(attr_nr, attr_flag, name, NLA_U8, char, \
+			nla_get_u8, NLA_PUT_U8)
 #define __u8_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U8, unsigned char, \
 			nla_get_u8, NLA_PUT_U8)
@@ -118,12 +118,6 @@ enum {
 #define __str_field_def(attr_nr, attr_flag, name, maxlen) \
 	__str_field(attr_nr, attr_flag, name, maxlen)
 
-#define __nla_put_flag(skb, attrtype, value)		\
-	do {						\
-		if (value)				\
-			NLA_PUT_FLAG(skb, attrtype);	\
-	} while (0)
-
 #define GENL_op_init(args...)	args
 #define GENL_doit(handler)		\
 	.doit = handler,		\
-- 
cgit v1.2.3-55-g7522


From 66b2f6b9c59c5e7003e13281dfe72e174f93988c Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 4 May 2011 15:25:35 +0200
Subject: drbd: Turn no-disk-flushes into disk-flushes={yes|no}

Change the --no-disk-flushes drbdsetup command line option as well as
the no_disk_flush netlink packet.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_receiver.c | 2 +-
 include/linux/drbd_genl.h          | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 83d39859a9fe..e7a6eeae94e2 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1179,7 +1179,7 @@ void drbd_bump_write_ordering(struct drbd_conf *mdev, enum write_ordering_e wo)
 	rcu_read_lock();
 	dc = rcu_dereference(mdev->ldev->disk_conf);
 
-	if (wo == WO_bdev_flush && dc->no_disk_flush)
+	if (wo == WO_bdev_flush && !dc->disk_flushes)
 		wo = WO_drain_io;
 	if (wo == WO_drain_io && dc->no_disk_drain)
 		wo = WO_none;
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index f143e3c0f33b..945c4dd3470c 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -122,8 +122,8 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__u32_field_def(14,	GENLA_F_MANDATORY,	c_max_rate, DRBD_C_MAX_RATE_DEF)
 	__u32_field_def(15,	GENLA_F_MANDATORY,	c_min_rate, DRBD_C_MIN_RATE_DEF)
 
-	__flg_field_def(16, GENLA_F_MANDATORY,	no_disk_barrier, 0)
-	__flg_field_def(17, GENLA_F_MANDATORY,	no_disk_flush, 0)
+	__flg_field_def(16, GENLA_F_MANDATORY,	disk_barrier, 1)
+	__flg_field_def(17, GENLA_F_MANDATORY,	disk_flushes, 1)
 	__flg_field_def(18, GENLA_F_MANDATORY,	no_disk_drain, 0)
 	__flg_field_def(19, GENLA_F_MANDATORY,	no_md_flush, 0)
 )
-- 
cgit v1.2.3-55-g7522


From d0c980e236243cd03aa2291243587ac1ba3c2b04 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 4 May 2011 15:25:35 +0200
Subject: drbd: Turn no-disk-drain into disk-drain={yes|no}

Change the --no-disk-drain drbdsetup command line option as well as
the no_disk_drain netlink packet.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_receiver.c | 2 +-
 include/linux/drbd_genl.h          | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index e7a6eeae94e2..5d1bdda8ec9f 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1181,7 +1181,7 @@ void drbd_bump_write_ordering(struct drbd_conf *mdev, enum write_ordering_e wo)
 
 	if (wo == WO_bdev_flush && !dc->disk_flushes)
 		wo = WO_drain_io;
-	if (wo == WO_drain_io && dc->no_disk_drain)
+	if (wo == WO_drain_io && !dc->disk_drain)
 		wo = WO_none;
 	rcu_read_unlock();
 	mdev->write_ordering = wo;
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 945c4dd3470c..30ad6600b444 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -124,7 +124,7 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 
 	__flg_field_def(16, GENLA_F_MANDATORY,	disk_barrier, 1)
 	__flg_field_def(17, GENLA_F_MANDATORY,	disk_flushes, 1)
-	__flg_field_def(18, GENLA_F_MANDATORY,	no_disk_drain, 0)
+	__flg_field_def(18, GENLA_F_MANDATORY,	disk_drain, 1)
 	__flg_field_def(19, GENLA_F_MANDATORY,	no_md_flush, 0)
 )
 
-- 
cgit v1.2.3-55-g7522


From e544046ab842ab93c275a6fc4e043c1cb637076d Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 4 May 2011 15:25:35 +0200
Subject: drbd: Turn no-md-flushes into md-flushes={yes|no}

Change the --no-md-flushes drbdsetup command line option as well as
the no_md_flush netlink packet.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c | 6 +++---
 include/linux/drbd_genl.h    | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 9af097416e26..4a946a877bde 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1449,10 +1449,10 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 
 	/* Reset the "barriers don't work" bits here, then force meta data to
 	 * be written, to ensure we determine if barriers are supported. */
-	if (new_disk_conf->no_md_flush)
-		set_bit(MD_NO_FUA, &mdev->flags);
-	else
+	if (new_disk_conf->md_flushes)
 		clear_bit(MD_NO_FUA, &mdev->flags);
+	else
+		set_bit(MD_NO_FUA, &mdev->flags);
 
 	/* Point of no return reached.
 	 * Devices and memory are no longer released by error cleanup below.
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 30ad6600b444..53518fc23154 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -125,7 +125,7 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__flg_field_def(16, GENLA_F_MANDATORY,	disk_barrier, 1)
 	__flg_field_def(17, GENLA_F_MANDATORY,	disk_flushes, 1)
 	__flg_field_def(18, GENLA_F_MANDATORY,	disk_drain, 1)
-	__flg_field_def(19, GENLA_F_MANDATORY,	no_md_flush, 0)
+	__flg_field_def(19, GENLA_F_MANDATORY,	md_flushes, 1)
 )
 
 GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
-- 
cgit v1.2.3-55-g7522


From bb77d34ecc6fe6cdc3f4f0841a516695c2eacc04 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 4 May 2011 15:25:35 +0200
Subject: drbd: Turn no-tcp-cork into tcp-cork={yes|no}

Change the --no-tcp-cork drbdsetup command line option as well as
the no_cork netlink packet.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_receiver.c | 8 ++++----
 drivers/block/drbd/drbd_worker.c   | 2 +-
 include/linux/drbd_genl.h          | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 5d1bdda8ec9f..b4858bb78940 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -5040,7 +5040,7 @@ int drbd_asender(struct drbd_thread *thi)
 	int expect   = header_size;
 	bool ping_timeout_active = false;
 	struct net_conf *nc;
-	int ping_timeo, no_cork, ping_int;
+	int ping_timeo, tcp_cork, ping_int;
 
 	current->policy = SCHED_RR;  /* Make this a realtime task! */
 	current->rt_priority = 2;    /* more important than all other tasks */
@@ -5051,7 +5051,7 @@ int drbd_asender(struct drbd_thread *thi)
 		rcu_read_lock();
 		nc = rcu_dereference(tconn->net_conf);
 		ping_timeo = nc->ping_timeo;
-		no_cork = nc->no_cork;
+		tcp_cork = nc->tcp_cork;
 		ping_int = nc->ping_int;
 		rcu_read_unlock();
 
@@ -5066,14 +5066,14 @@ int drbd_asender(struct drbd_thread *thi)
 
 		/* TODO: conditionally cork; it may hurt latency if we cork without
 		   much to send */
-		if (!no_cork)
+		if (tcp_cork)
 			drbd_tcp_cork(tconn->meta.socket);
 		if (tconn_finish_peer_reqs(tconn)) {
 			conn_err(tconn, "tconn_finish_peer_reqs() failed\n");
 			goto reconnect;
 		}
 		/* but unconditionally uncork unless disabled */
-		if (!no_cork)
+		if (tcp_cork)
 			drbd_tcp_uncork(tconn->meta.socket);
 
 		/* short circuit, recv_msg would return EINTR anyways. */
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index e37c42d5dd6e..78c3de49eff6 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1694,7 +1694,7 @@ int drbd_worker(struct drbd_thread *thi)
 
 			rcu_read_lock();
 			nc = rcu_dereference(tconn->net_conf);
-			cork = nc ? !nc->no_cork : 0;
+			cork = nc ? nc->tcp_cork : 0;
 			rcu_read_unlock();
 
 			if (tconn->data.socket && cork)
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 53518fc23154..6632d10f1ee1 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -162,7 +162,7 @@ GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
 	__u32_field_def(25,	GENLA_F_MANDATORY,	cong_extents, DRBD_CONG_EXTENTS_DEF)
 	__flg_field_def(26, GENLA_F_MANDATORY,	two_primaries, 0)
 	__flg_field(27, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	want_lose)
-	__flg_field_def(28, GENLA_F_MANDATORY,	no_cork, 0)
+	__flg_field_def(28, GENLA_F_MANDATORY,	tcp_cork, 1)
 	__flg_field_def(29, GENLA_F_MANDATORY,	always_asbp, 0)
 	__flg_field(30, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	dry_run)
 	__flg_field_def(31,	GENLA_F_MANDATORY,	use_rle, 0)
-- 
cgit v1.2.3-55-g7522


From 7bac3e6f7e74993475a94487effe05dc1f68bdc7 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Fri, 6 May 2011 17:50:57 +0200
Subject: drbd: Also define the default values of boolean flags in a single
 place

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_genl.h   | 16 ++++++++--------
 include/linux/drbd_limits.h | 10 ++++++++++
 2 files changed, 18 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 6632d10f1ee1..02647dc8c67c 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -122,10 +122,10 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__u32_field_def(14,	GENLA_F_MANDATORY,	c_max_rate, DRBD_C_MAX_RATE_DEF)
 	__u32_field_def(15,	GENLA_F_MANDATORY,	c_min_rate, DRBD_C_MIN_RATE_DEF)
 
-	__flg_field_def(16, GENLA_F_MANDATORY,	disk_barrier, 1)
-	__flg_field_def(17, GENLA_F_MANDATORY,	disk_flushes, 1)
-	__flg_field_def(18, GENLA_F_MANDATORY,	disk_drain, 1)
-	__flg_field_def(19, GENLA_F_MANDATORY,	md_flushes, 1)
+	__flg_field_def(16, GENLA_F_MANDATORY,	disk_barrier, DRBD_DISK_BARRIER_DEF)
+	__flg_field_def(17, GENLA_F_MANDATORY,	disk_flushes, DRBD_DISK_FLUSHES_DEF)
+	__flg_field_def(18, GENLA_F_MANDATORY,	disk_drain, DRBD_DISK_DRAIN_DEF)
+	__flg_field_def(19, GENLA_F_MANDATORY,	md_flushes, DRBD_MD_FLUSHES_DEF)
 )
 
 GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
@@ -160,12 +160,12 @@ GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
 	__u32_field_def(23,	GENLA_F_MANDATORY,	on_congestion, DRBD_ON_CONGESTION_DEF)
 	__u32_field_def(24,	GENLA_F_MANDATORY,	cong_fill, DRBD_CONG_FILL_DEF)
 	__u32_field_def(25,	GENLA_F_MANDATORY,	cong_extents, DRBD_CONG_EXTENTS_DEF)
-	__flg_field_def(26, GENLA_F_MANDATORY,	two_primaries, 0)
+	__flg_field_def(26, GENLA_F_MANDATORY,	two_primaries, DRBD_ALLOW_TWO_PRIMARIES_DEF)
 	__flg_field(27, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	want_lose)
-	__flg_field_def(28, GENLA_F_MANDATORY,	tcp_cork, 1)
-	__flg_field_def(29, GENLA_F_MANDATORY,	always_asbp, 0)
+	__flg_field_def(28, GENLA_F_MANDATORY,	tcp_cork, DRBD_TCP_CORK_DEF)
+	__flg_field_def(29, GENLA_F_MANDATORY,	always_asbp, DRBD_ALWAYS_ASBP_DEF)
 	__flg_field(30, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	dry_run)
-	__flg_field_def(31,	GENLA_F_MANDATORY,	use_rle, 0)
+	__flg_field_def(31,	GENLA_F_MANDATORY,	use_rle, DRBD_USE_RLE_DEF)
 )
 
 GENL_struct(DRBD_NLA_SET_ROLE_PARMS, 6, set_role_parms,
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index bcebb016fda3..3d3e2d5125cb 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -170,4 +170,14 @@
 
 #define DRBD_PROTOCOL_DEF DRBD_PROT_C
 
+#define DRBD_DISK_BARRIER_DEF	0
+#define DRBD_DISK_FLUSHES_DEF	1
+#define DRBD_DISK_DRAIN_DEF	1
+#define DRBD_MD_FLUSHES_DEF	1
+#define DRBD_TCP_CORK_DEF	1
+
+#define DRBD_ALLOW_TWO_PRIMARIES_DEF	0
+#define DRBD_ALWAYS_ASBP_DEF	0
+#define DRBD_USE_RLE_DEF	0
+
 #endif
-- 
cgit v1.2.3-55-g7522


From 6139f60dc192e2c5478c1126d1aff7905dc0a98a Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Fri, 6 May 2011 20:00:02 +0200
Subject: drbd: Rename the want_lose field/flag to discard_my_data

This is what it is called in config files and on the command line as
well.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h      |  2 +-
 drivers/block/drbd/drbd_main.c     |  6 +++---
 drivers/block/drbd/drbd_nl.c       |  4 ++--
 drivers/block/drbd/drbd_receiver.c | 14 +++++++-------
 include/linux/drbd_genl.h          |  2 +-
 5 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 56b190c65546..fa36757ffc4a 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -413,7 +413,7 @@ struct p_rs_param_95 {
 } __packed;
 
 enum drbd_conn_flags {
-	CF_WANT_LOSE = 1,
+	CF_DISCARD_MY_DATA = 1,
 	CF_DRY_RUN = 2,
 };
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 22c2b4c881da..86c8bc5ac603 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -943,8 +943,8 @@ int __drbd_send_protocol(struct drbd_tconn *tconn)
 	p->after_sb_2p   = cpu_to_be32(nc->after_sb_2p);
 	p->two_primaries = cpu_to_be32(nc->two_primaries);
 	cf = 0;
-	if (nc->want_lose)
-		cf |= CF_WANT_LOSE;
+	if (nc->discard_my_data)
+		cf |= CF_DISCARD_MY_DATA;
 	if (nc->dry_run)
 		cf |= CF_DRY_RUN;
 	p->conn_flags    = cpu_to_be32(cf);
@@ -988,7 +988,7 @@ int _drbd_send_uuids(struct drbd_conf *mdev, u64 uuid_flags)
 	mdev->comm_bm_set = drbd_bm_total_weight(mdev);
 	p->uuid[UI_SIZE] = cpu_to_be64(mdev->comm_bm_set);
 	rcu_read_lock();
-	uuid_flags |= rcu_dereference(mdev->tconn->net_conf)->want_lose ? 1 : 0;
+	uuid_flags |= rcu_dereference(mdev->tconn->net_conf)->discard_my_data ? 1 : 0;
 	rcu_read_unlock();
 	uuid_flags |= test_bit(CRASHED_PRIMARY, &mdev->flags) ? 2 : 0;
 	uuid_flags |= mdev->new_state_tmp.disk == D_INCONSISTENT ? 4 : 0;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 195428ee6052..9a82306adf92 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -606,7 +606,7 @@ drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force)
 		mutex_lock(&mdev->tconn->conf_update);
 		nc = mdev->tconn->net_conf;
 		if (nc)
-			nc->want_lose = 0; /* without copy; single bit op is atomic */
+			nc->discard_my_data = 0; /* without copy; single bit op is atomic */
 		mutex_unlock(&mdev->tconn->conf_update);
 
 		set_disk_ro(mdev->vdisk, false);
@@ -1738,7 +1738,7 @@ _check_net_options(struct drbd_tconn *tconn, struct net_conf *old_conf, struct n
 			if (new_conf->wire_protocol == DRBD_PROT_A && fp == FP_STONITH)
 				return ERR_STONITH_AND_PROT_A;
 		}
-		if (mdev->state.role == R_PRIMARY && new_conf->want_lose)
+		if (mdev->state.role == R_PRIMARY && new_conf->discard_my_data)
 			return ERR_DISCARD;
 	}
 
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index aa42967398e3..e4e8f8a408d1 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2908,9 +2908,9 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_conf *mdev, enum drbd_rol
 	}
 
 	if (hg == -100) {
-		if (nc->want_lose && !(mdev->p_uuid[UI_FLAGS]&1))
+		if (nc->discard_my_data && !(mdev->p_uuid[UI_FLAGS]&1))
 			hg = -1;
-		if (!nc->want_lose && (mdev->p_uuid[UI_FLAGS]&1))
+		if (!nc->discard_my_data && (mdev->p_uuid[UI_FLAGS]&1))
 			hg = 1;
 
 		if (abs(hg) < 100)
@@ -3009,7 +3009,7 @@ static int receive_protocol(struct drbd_tconn *tconn, struct packet_info *pi)
 {
 	struct p_protocol *p = pi->data;
 	int p_proto, p_after_sb_0p, p_after_sb_1p, p_after_sb_2p;
-	int p_want_lose, p_two_primaries, cf;
+	int p_discard_my_data, p_two_primaries, cf;
 	struct net_conf *nc;
 
 	p_proto		= be32_to_cpu(p->protocol);
@@ -3018,7 +3018,7 @@ static int receive_protocol(struct drbd_tconn *tconn, struct packet_info *pi)
 	p_after_sb_2p	= be32_to_cpu(p->after_sb_2p);
 	p_two_primaries = be32_to_cpu(p->two_primaries);
 	cf		= be32_to_cpu(p->conn_flags);
-	p_want_lose = cf & CF_WANT_LOSE;
+	p_discard_my_data = cf & CF_DISCARD_MY_DATA;
 
 	if (tconn->agreed_pro_version >= 87) {
 		char integrity_alg[SHARED_SECRET_MAX];
@@ -3075,8 +3075,8 @@ static int receive_protocol(struct drbd_tconn *tconn, struct packet_info *pi)
 		goto disconnect_rcu_unlock;
 	}
 
-	if (p_want_lose && nc->want_lose) {
-		conn_err(tconn, "both sides have the 'want_lose' flag set\n");
+	if (p_discard_my_data && nc->discard_my_data) {
+		conn_err(tconn, "both sides have the 'discard_my_data' flag set\n");
 		goto disconnect_rcu_unlock;
 	}
 
@@ -3806,7 +3806,7 @@ static int receive_state(struct drbd_tconn *tconn, struct packet_info *pi)
 	}
 
 	mutex_lock(&mdev->tconn->conf_update);
-	mdev->tconn->net_conf->want_lose = 0; /* without copy; single bit op is atomic */
+	mdev->tconn->net_conf->discard_my_data = 0; /* without copy; single bit op is atomic */
 	mutex_unlock(&mdev->tconn->conf_update);
 
 	drbd_md_sync(mdev); /* update connected indicator, la_size, ... */
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 02647dc8c67c..6aece551d87e 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -161,7 +161,7 @@ GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
 	__u32_field_def(24,	GENLA_F_MANDATORY,	cong_fill, DRBD_CONG_FILL_DEF)
 	__u32_field_def(25,	GENLA_F_MANDATORY,	cong_extents, DRBD_CONG_EXTENTS_DEF)
 	__flg_field_def(26, GENLA_F_MANDATORY,	two_primaries, DRBD_ALLOW_TWO_PRIMARIES_DEF)
-	__flg_field(27, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	want_lose)
+	__flg_field(27, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	discard_my_data)
 	__flg_field_def(28, GENLA_F_MANDATORY,	tcp_cork, DRBD_TCP_CORK_DEF)
 	__flg_field_def(29, GENLA_F_MANDATORY,	always_asbp, DRBD_ALWAYS_ASBP_DEF)
 	__flg_field(30, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	dry_run)
-- 
cgit v1.2.3-55-g7522


From 6394b9358e6187414b7a6de7ba2c681ee4a790ac Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 11 May 2011 14:29:52 +0200
Subject: drbd: Refer to resync-rate consistently throughout the code

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h      | 6 +++---
 drivers/block/drbd/drbd_main.c     | 4 ++--
 drivers/block/drbd/drbd_receiver.c | 2 +-
 include/linux/drbd_genl.h          | 2 +-
 include/linux/drbd_limits.h        | 7 ++++---
 5 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index fa36757ffc4a..8026adacd3d2 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -389,21 +389,21 @@ struct p_barrier_ack {
 } __packed;
 
 struct p_rs_param {
-	u32 rate;
+	u32 resync_rate;
 
 	      /* Since protocol version 88 and higher. */
 	char verify_alg[0];
 } __packed;
 
 struct p_rs_param_89 {
-	u32 rate;
+	u32 resync_rate;
         /* protocol version 89: */
 	char verify_alg[SHARED_SECRET_MAX];
 	char csums_alg[SHARED_SECRET_MAX];
 } __packed;
 
 struct p_rs_param_95 {
-	u32 rate;
+	u32 resync_rate;
 	char verify_alg[SHARED_SECRET_MAX];
 	char csums_alg[SHARED_SECRET_MAX];
 	u32 c_plan_ahead;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 86c8bc5ac603..26d7763d5255 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -888,14 +888,14 @@ int drbd_send_sync_param(struct drbd_conf *mdev)
 
 	if (get_ldev(mdev)) {
 		dc = rcu_dereference(mdev->ldev->disk_conf);
-		p->rate = cpu_to_be32(dc->resync_rate);
+		p->resync_rate = cpu_to_be32(dc->resync_rate);
 		p->c_plan_ahead = cpu_to_be32(dc->c_plan_ahead);
 		p->c_delay_target = cpu_to_be32(dc->c_delay_target);
 		p->c_fill_target = cpu_to_be32(dc->c_fill_target);
 		p->c_max_rate = cpu_to_be32(dc->c_max_rate);
 		put_ldev(mdev);
 	} else {
-		p->rate = cpu_to_be32(DRBD_RATE_DEF);
+		p->resync_rate = cpu_to_be32(DRBD_RESYNC_RATE_DEF);
 		p->c_plan_ahead = cpu_to_be32(DRBD_C_PLAN_AHEAD_DEF);
 		p->c_delay_target = cpu_to_be32(DRBD_C_DELAY_TARGET_DEF);
 		p->c_fill_target = cpu_to_be32(DRBD_C_FILL_TARGET_DEF);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index e4e8f8a408d1..684f79542727 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -3221,7 +3221,7 @@ static int receive_SyncParam(struct drbd_tconn *tconn, struct packet_info *pi)
 		old_disk_conf = mdev->ldev->disk_conf;
 		*new_disk_conf = *old_disk_conf;
 
-		new_disk_conf->resync_rate = be32_to_cpu(p->rate);
+		new_disk_conf->resync_rate = be32_to_cpu(p->resync_rate);
 	}
 
 	if (apv >= 88) {
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 6aece551d87e..778708d92939 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -113,7 +113,7 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__u32_field_def(6, GENLA_F_MANDATORY,	on_io_error, DRBD_ON_IO_ERROR_DEF)
 	__u32_field_def(7, GENLA_F_MANDATORY,	fencing, DRBD_FENCING_DEF)
 
-	__u32_field_def(8,	GENLA_F_MANDATORY,	resync_rate, DRBD_RATE_DEF)
+	__u32_field_def(8,	GENLA_F_MANDATORY,	resync_rate, DRBD_RESYNC_RATE_DEF)
 	__u32_field_def(9,	GENLA_F_MANDATORY,	resync_after, DRBD_AFTER_DEF)
 	__u32_field_def(10,	GENLA_F_MANDATORY,	al_extents, DRBD_AL_EXTENTS_DEF)
 	__u32_field_def(11,	GENLA_F_MANDATORY,	c_plan_ahead, DRBD_C_PLAN_AHEAD_DEF)
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 3d3e2d5125cb..48339ae69d50 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -98,10 +98,11 @@
 
 /* syncer { */
   /* FIXME allow rate to be zero? */
-#define DRBD_RATE_MIN 1
+#define DRBD_RESYNC_RATE_MIN 1
 /* channel bonding 10 GbE, or other hardware */
-#define DRBD_RATE_MAX (4 << 20)
-#define DRBD_RATE_DEF 250  /* kb/second */
+#define DRBD_RESYNC_RATE_MAX (4 << 20)
+#define DRBD_RESYNC_RATE_DEF 250
+#define DRBD_RESYNC_RATE_SCALE 'k'  /* kilobytes */
 
   /* less than 7 would hit performance unnecessarily.
    * 919 slots context information per transaction,
-- 
cgit v1.2.3-55-g7522


From 69ef82dea4c34e4a0541fc3f415b0fef70fe12b0 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 11 May 2011 14:34:35 +0200
Subject: drbd: Refer to connect-int consistently throughout the code

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_receiver.c | 12 ++++++------
 include/linux/drbd_genl.h          |  2 +-
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 684f79542727..7deade196a33 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -617,7 +617,7 @@ static struct socket *drbd_try_connect(struct drbd_tconn *tconn)
 	struct sockaddr_in6 peer_in6;
 	struct net_conf *nc;
 	int err, peer_addr_len, my_addr_len;
-	int sndbuf_size, rcvbuf_size, try_connect_int;
+	int sndbuf_size, rcvbuf_size, connect_int;
 	int disconnect_on_error = 1;
 
 	rcu_read_lock();
@@ -629,7 +629,7 @@ static struct socket *drbd_try_connect(struct drbd_tconn *tconn)
 
 	sndbuf_size = nc->sndbuf_size;
 	rcvbuf_size = nc->rcvbuf_size;
-	try_connect_int = nc->try_connect_int;
+	connect_int = nc->connect_int;
 
 	my_addr_len = min_t(int, nc->my_addr_len, sizeof(src_in6));
 	memcpy(&src_in6, nc->my_addr, my_addr_len);
@@ -653,7 +653,7 @@ static struct socket *drbd_try_connect(struct drbd_tconn *tconn)
 	}
 
 	sock->sk->sk_rcvtimeo =
-	sock->sk->sk_sndtimeo = try_connect_int * HZ;
+	sock->sk->sk_sndtimeo = connect_int * HZ;
 	drbd_setbufsize(sock, sndbuf_size, rcvbuf_size);
 
        /* explicitly bind to the configured IP as source IP
@@ -702,7 +702,7 @@ out:
 static struct socket *drbd_wait_for_connect(struct drbd_tconn *tconn)
 {
 	int timeo, err, my_addr_len;
-	int sndbuf_size, rcvbuf_size, try_connect_int;
+	int sndbuf_size, rcvbuf_size, connect_int;
 	struct socket *s_estab = NULL, *s_listen;
 	struct sockaddr_in6 my_addr;
 	struct net_conf *nc;
@@ -717,7 +717,7 @@ static struct socket *drbd_wait_for_connect(struct drbd_tconn *tconn)
 
 	sndbuf_size = nc->sndbuf_size;
 	rcvbuf_size = nc->rcvbuf_size;
-	try_connect_int = nc->try_connect_int;
+	connect_int = nc->connect_int;
 
 	my_addr_len = min_t(int, nc->my_addr_len, sizeof(struct sockaddr_in6));
 	memcpy(&my_addr, nc->my_addr, my_addr_len);
@@ -731,7 +731,7 @@ static struct socket *drbd_wait_for_connect(struct drbd_tconn *tconn)
 		goto out;
 	}
 
-	timeo = try_connect_int * HZ;
+	timeo = connect_int * HZ;
 	timeo += (random32() & 1) ? timeo / 7 : -timeo / 7; /* 28.5% random jitter */
 
 	s_listen->sk->sk_reuse    = 1; /* SO_REUSEADDR */
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 778708d92939..67c816c0fc28 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -143,7 +143,7 @@ GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
 	__str_field_def(6,	GENLA_F_MANDATORY,	verify_alg,     SHARED_SECRET_MAX)
 	__str_field_def(7,	GENLA_F_MANDATORY,	csums_alg,	SHARED_SECRET_MAX)
 	__u32_field_def(8,	GENLA_F_MANDATORY,	wire_protocol, DRBD_PROTOCOL_DEF)
-	__u32_field_def(9,	GENLA_F_MANDATORY,	try_connect_int, DRBD_CONNECT_INT_DEF)
+	__u32_field_def(9,	GENLA_F_MANDATORY,	connect_int, DRBD_CONNECT_INT_DEF)
 	__u32_field_def(10,	GENLA_F_MANDATORY,	timeout, DRBD_TIMEOUT_DEF)
 	__u32_field_def(11,	GENLA_F_MANDATORY,	ping_int, DRBD_PING_INT_DEF)
 	__u32_field_def(12,	GENLA_F_MANDATORY,	ping_timeo, DRBD_PING_TIMEO_DEF)
-- 
cgit v1.2.3-55-g7522


From 95f8efd08bcce65df994049a292b94e56c7ada67 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Thu, 12 May 2011 11:15:34 +0200
Subject: drbd: Fix the upper limit of resync-after

The 32-bit resync_after netlink field takes a device minor number as
parameter, which is no longer limited to 255.  We cannot statically
verify which device numbers are valid, so set the ummer limit to the
highest possible signed 32-bit integer.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h    |  4 ++--
 drivers/block/drbd/drbd_nl.c     |  4 ++--
 drivers/block/drbd/drbd_worker.c | 26 +++++++++++++-------------
 include/linux/drbd.h             |  4 ++--
 include/linux/drbd_genl.h        |  2 +-
 include/linux/drbd_limits.h      |  7 ++++---
 6 files changed, 24 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 8026adacd3d2..e16722840767 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1408,8 +1408,8 @@ extern int drbd_khelper(struct drbd_conf *mdev, char *cmd);
 
 /* drbd_worker.c */
 extern int drbd_worker(struct drbd_thread *thi);
-enum drbd_ret_code drbd_sync_after_valid(struct drbd_conf *mdev, int o_minor);
-void drbd_sync_after_changed(struct drbd_conf *mdev);
+enum drbd_ret_code drbd_resync_after_valid(struct drbd_conf *mdev, int o_minor);
+void drbd_resync_after_changed(struct drbd_conf *mdev);
 extern void drbd_start_resync(struct drbd_conf *mdev, enum drbd_conns side);
 extern void resume_next_sg(struct drbd_conf *mdev);
 extern void suspend_other_sg(struct drbd_conf *mdev);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 9a82306adf92..74c27f1507f3 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1183,10 +1183,10 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	write_lock_irq(&global_state_lock);
-	retcode = drbd_sync_after_valid(mdev, new_disk_conf->resync_after);
+	retcode = drbd_resync_after_valid(mdev, new_disk_conf->resync_after);
 	if (retcode == NO_ERROR) {
 		rcu_assign_pointer(mdev->ldev->disk_conf, new_disk_conf);
-		drbd_sync_after_changed(mdev);
+		drbd_resync_after_changed(mdev);
 	}
 	write_unlock_irq(&global_state_lock);
 
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index ec8f4245ef9a..6410c55831e0 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -57,7 +57,7 @@ static int w_make_ov_request(struct drbd_work *w, int cancel);
 
 /* About the global_state_lock
    Each state transition on an device holds a read lock. In case we have
-   to evaluate the sync after dependencies, we grab a write lock, because
+   to evaluate the resync after dependencies, we grab a write lock, because
    we need stable states on all devices for that.  */
 rwlock_t global_state_lock;
 
@@ -1340,17 +1340,17 @@ int w_restart_disk_io(struct drbd_work *w, int cancel)
 static int _drbd_may_sync_now(struct drbd_conf *mdev)
 {
 	struct drbd_conf *odev = mdev;
-	int ra;
+	int resync_after;
 
 	while (1) {
 		if (!odev->ldev)
 			return 1;
 		rcu_read_lock();
-		ra = rcu_dereference(odev->ldev->disk_conf)->resync_after;
+		resync_after = rcu_dereference(odev->ldev->disk_conf)->resync_after;
 		rcu_read_unlock();
-		if (ra == -1)
+		if (resync_after == -1)
 			return 1;
-		odev = minor_to_mdev(ra);
+		odev = minor_to_mdev(resync_after);
 		if (!expect(odev))
 			return 1;
 		if ((odev->state.conn >= C_SYNC_SOURCE &&
@@ -1426,36 +1426,36 @@ void suspend_other_sg(struct drbd_conf *mdev)
 }
 
 /* caller must hold global_state_lock */
-enum drbd_ret_code drbd_sync_after_valid(struct drbd_conf *mdev, int o_minor)
+enum drbd_ret_code drbd_resync_after_valid(struct drbd_conf *mdev, int o_minor)
 {
 	struct drbd_conf *odev;
-	int ra;
+	int resync_after;
 
 	if (o_minor == -1)
 		return NO_ERROR;
 	if (o_minor < -1 || minor_to_mdev(o_minor) == NULL)
-		return ERR_SYNC_AFTER;
+		return ERR_RESYNC_AFTER;
 
 	/* check for loops */
 	odev = minor_to_mdev(o_minor);
 	while (1) {
 		if (odev == mdev)
-			return ERR_SYNC_AFTER_CYCLE;
+			return ERR_RESYNC_AFTER_CYCLE;
 
 		rcu_read_lock();
-		ra = rcu_dereference(odev->ldev->disk_conf)->resync_after;
+		resync_after = rcu_dereference(odev->ldev->disk_conf)->resync_after;
 		rcu_read_unlock();
 		/* dependency chain ends here, no cycles. */
-		if (ra == -1)
+		if (resync_after == -1)
 			return NO_ERROR;
 
 		/* follow the dependency chain */
-		odev = minor_to_mdev(ra);
+		odev = minor_to_mdev(resync_after);
 	}
 }
 
 /* caller must hold global_state_lock */
-void drbd_sync_after_changed(struct drbd_conf *mdev)
+void drbd_resync_after_changed(struct drbd_conf *mdev)
 {
 	int changes;
 
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 6c7c85d8fc41..05063e6db81f 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -130,8 +130,8 @@ enum drbd_ret_code {
 	ERR_INTR		= 129, /* EINTR */
 	ERR_RESIZE_RESYNC	= 130,
 	ERR_NO_PRIMARY		= 131,
-	ERR_SYNC_AFTER		= 132,
-	ERR_SYNC_AFTER_CYCLE	= 133,
+	ERR_RESYNC_AFTER	= 132,
+	ERR_RESYNC_AFTER_CYCLE	= 133,
 	ERR_PAUSE_IS_SET	= 134,
 	ERR_PAUSE_IS_CLEAR	= 135,
 	ERR_PACKET_NR		= 137,
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 67c816c0fc28..a59466f7f661 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -114,7 +114,7 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__u32_field_def(7, GENLA_F_MANDATORY,	fencing, DRBD_FENCING_DEF)
 
 	__u32_field_def(8,	GENLA_F_MANDATORY,	resync_rate, DRBD_RESYNC_RATE_DEF)
-	__u32_field_def(9,	GENLA_F_MANDATORY,	resync_after, DRBD_AFTER_DEF)
+	__u32_field_def(9,	GENLA_F_MANDATORY,	resync_after, DRBD_RESYNC_AFTER_DEF)
 	__u32_field_def(10,	GENLA_F_MANDATORY,	al_extents, DRBD_AL_EXTENTS_DEF)
 	__u32_field_def(11,	GENLA_F_MANDATORY,	c_plan_ahead, DRBD_C_PLAN_AHEAD_DEF)
 	__u32_field_def(12,	GENLA_F_MANDATORY,	c_delay_target, DRBD_C_DELAY_TARGET_DEF)
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 48339ae69d50..c4a8f0fef7b2 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -113,9 +113,10 @@
 #define DRBD_AL_EXTENTS_MAX  6433
 #define DRBD_AL_EXTENTS_DEF  127
 
-#define DRBD_AFTER_MIN  -1
-#define DRBD_AFTER_MAX  255
-#define DRBD_AFTER_DEF  -1
+#define DRBD_RESYNC_AFTER_MIN  -1
+#define DRBD_RESYNC_AFTER_MAX  (1<<30)
+#define DRBD_RESYNC_AFTER_DEF  -1
+#define DRBD_RESYNC_AFTER_SCALE '1'
 
 /* } */
 
-- 
cgit v1.2.3-55-g7522


From 3a45abd577727d2268e190d372600f8652883453 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Thu, 12 May 2011 12:02:54 +0200
Subject: drbd: Convert resync-after into a signed netlink field

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_genl.h         | 2 +-
 include/linux/genl_magic_func.h   | 3 +++
 include/linux/genl_magic_struct.h | 2 ++
 3 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index a59466f7f661..7b174a093a8d 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -114,7 +114,7 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__u32_field_def(7, GENLA_F_MANDATORY,	fencing, DRBD_FENCING_DEF)
 
 	__u32_field_def(8,	GENLA_F_MANDATORY,	resync_rate, DRBD_RESYNC_RATE_DEF)
-	__u32_field_def(9,	GENLA_F_MANDATORY,	resync_after, DRBD_RESYNC_AFTER_DEF)
+	__s32_field_def(9,	GENLA_F_MANDATORY,	resync_after, DRBD_RESYNC_AFTER_DEF)
 	__u32_field_def(10,	GENLA_F_MANDATORY,	al_extents, DRBD_AL_EXTENTS_DEF)
 	__u32_field_def(11,	GENLA_F_MANDATORY,	c_plan_ahead, DRBD_C_PLAN_AHEAD_DEF)
 	__u32_field_def(12,	GENLA_F_MANDATORY,	c_delay_target, DRBD_C_DELAY_TARGET_DEF)
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index e908f1c50355..94e839aafae3 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -437,6 +437,9 @@ static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb,		\
 #undef __u32_field_def
 #define __u32_field_def(attr_nr, attr_flag, name, default)		\
 	x->name = default;
+#undef __s32_field_def
+#define __s32_field_def(attr_nr, attr_flag, name, default)		\
+	x->name = default;
 #undef __flg_field_def
 #define __flg_field_def(attr_nr, attr_flag, name, default)		\
 	x->name = default;
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index b1ddbb5bd725..0fca21fd1af5 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -115,6 +115,8 @@ enum {
 	__flg_field(attr_nr, attr_flag, name)
 #define __u32_field_def(attr_nr, attr_flag, name, default) \
 	__u32_field(attr_nr, attr_flag, name)
+#define __s32_field_def(attr_nr, attr_flag, name, default) \
+	__s32_field(attr_nr, attr_flag, name)
 #define __str_field_def(attr_nr, attr_flag, name, maxlen) \
 	__str_field(attr_nr, attr_flag, name, maxlen)
 
-- 
cgit v1.2.3-55-g7522


From c5482bbd9607bf38cbc952eacaa429e6ba3160a0 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 11 May 2011 14:44:55 +0200
Subject: drbd: Rename DISK_SIZE_SECT -> DISK_SIZE

We don't have the units in constant names in other places, either.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_limits.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index c4a8f0fef7b2..8f8bbea545e0 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -125,9 +125,10 @@
  * the upper limit with 64bit kernel, enough ram and flexible meta data
  * is 1 PiB, currently. */
 /* DRBD_MAX_SECTORS */
-#define DRBD_DISK_SIZE_SECT_MIN  0
-#define DRBD_DISK_SIZE_SECT_MAX  (1 * (2LLU << 40))
-#define DRBD_DISK_SIZE_SECT_DEF  0 /* = disabled = no user size... */
+#define DRBD_DISK_SIZE_MIN  0
+#define DRBD_DISK_SIZE_MAX  (16 * (2LLU << 30))
+#define DRBD_DISK_SIZE_DEF  0 /* = disabled = no user size... */
+#define DRBD_DISK_SIZE_SCALE 's'  /* sectors */
 
 #define DRBD_ON_IO_ERROR_DEF EP_DETACH
 #define DRBD_FENCING_DEF FP_DONT_CARE
-- 
cgit v1.2.3-55-g7522


From dcb20d1a8e7d9602e52a9b673ae4d7f746d2cbb2 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Mon, 16 May 2011 14:30:24 +0200
Subject: drbd: Refuse to change network options online when...

* the peer does not speak protocol_version 100 and the
  user wants to change one of:
    - wire_protocol
    - two_primaries
    - integrity_alg

* the user wants to remove the allow_two_primaries flag
  when there are two primaries

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c | 22 ++++++++++++++++++----
 include/linux/drbd.h         |  1 +
 2 files changed, 19 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 74c27f1507f3..133a6724657d 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1722,10 +1722,24 @@ _check_net_options(struct drbd_tconn *tconn, struct net_conf *old_conf, struct n
 	struct drbd_conf *mdev;
 	int i;
 
-	if (old_conf && tconn->agreed_pro_version < 100 &&
-	    tconn->cstate == C_WF_REPORT_PARAMS &&
-	    new_conf->wire_protocol != old_conf->wire_protocol)
-		return ERR_NEED_APV_100;
+	if (old_conf && tconn->cstate == C_WF_REPORT_PARAMS && tconn->agreed_pro_version < 100) {
+		if (new_conf->wire_protocol != old_conf->wire_protocol)
+			return ERR_NEED_APV_100;
+
+		if (new_conf->two_primaries != old_conf->two_primaries)
+			return ERR_NEED_APV_100;
+
+		if (!new_conf->integrity_alg != !old_conf->integrity_alg)
+			return ERR_NEED_APV_100;
+
+		if (strcmp(new_conf->integrity_alg, old_conf->integrity_alg))
+			return ERR_NEED_APV_100;
+	}
+
+	if (!new_conf->two_primaries &&
+	    conn_highest_role(tconn) == R_PRIMARY &&
+	    conn_highest_peer(tconn) == R_PRIMARY)
+		return ERR_NEED_ALLOW_TWO_PRI;
 
 	if (new_conf->two_primaries &&
 	    (new_conf->wire_protocol != DRBD_PROT_C))
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 05063e6db81f..679e81123229 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -161,6 +161,7 @@ enum drbd_ret_code {
 	ERR_MINOR_EXISTS	= 161,
 	ERR_INVALID_REQUEST	= 162,
 	ERR_NEED_APV_100	= 163,
+	ERR_NEED_ALLOW_TWO_PRI  = 164,
 
 	/* insert new ones above this line */
 	AFTER_LAST_ERR_CODE
-- 
cgit v1.2.3-55-g7522


From 309f0b70ab789bf85c5f5f32dbc466d42f024747 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Fri, 13 May 2011 01:24:14 +0200
Subject: drbd: Use more generic constant names

These constants are useful for the same purpose in more than one place.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_limits.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 8f8bbea545e0..3627f760966e 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -113,10 +113,10 @@
 #define DRBD_AL_EXTENTS_MAX  6433
 #define DRBD_AL_EXTENTS_DEF  127
 
-#define DRBD_RESYNC_AFTER_MIN  -1
-#define DRBD_RESYNC_AFTER_MAX  (1<<30)
-#define DRBD_RESYNC_AFTER_DEF  -1
-#define DRBD_RESYNC_AFTER_SCALE '1'
+#define DRBD_MINOR_NUMBER_MIN  -1
+#define DRBD_MINOR_NUMBER_MAX  (1<<30)
+#define DRBD_MINOR_NUMBER_DEF  -1
+#define DRBD_MINOR_NUMBER_SCALE '1'
 
 /* } */
 
-- 
cgit v1.2.3-55-g7522


From 509100e6012db92f4af3796436b450447c6c8268 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Tue, 17 May 2011 13:29:46 +0200
Subject: drbd: Output signed / unsigned netlink fields correctly

Note: All input values are still treated as signed; unsigned long long values
are still broken.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/genl_magic_func.h   | 23 +++++++++++------
 include/linux/genl_magic_struct.h | 52 ++++++++++++++++++++++++++++-----------
 2 files changed, 53 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 94e839aafae3..2ae16126c6a4 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -78,12 +78,13 @@ static struct nla_policy s_name ## _nl_policy[] __read_mostly =		\
 { s_fields };
 
 #undef __field
-#define __field(attr_nr, attr_flag, name, nla_type, _type, __get, __put) \
+#define __field(attr_nr, attr_flag, name, nla_type, _type, __get,	\
+		 __put, __is_signed)					\
 	[__nla_type(attr_nr)] = { .type = nla_type },
 
 #undef __array
 #define __array(attr_nr, attr_flag, name, nla_type, _type, maxlen,	\
-		__get, __put)						\
+		__get, __put, __is_signed)				\
 	[__nla_type(attr_nr)] = { .type = nla_type,			\
 		.len = maxlen - (nla_type == NLA_NUL_STRING) },
 
@@ -241,7 +242,8 @@ static int s_name ## _from_attrs_for_change(struct s_name *s,		\
 		}
 
 #undef __field
-#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)	\
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put,	\
+		__is_signed)						\
 	__assign(attr_nr, attr_flag, name, nla_type, type,		\
 			if (s)						\
 				s->name = __get(nla);			\
@@ -249,7 +251,8 @@ static int s_name ## _from_attrs_for_change(struct s_name *s,		\
 
 /* validate_nla() already checked nla_len <= maxlen appropriately. */
 #undef __array
-#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen,	\
+		__get, __put, __is_signed)				\
 	__assign(attr_nr, attr_flag, name, nla_type, type,		\
 			if (s)						\
 				s->name ## _len =			\
@@ -410,14 +413,16 @@ static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb,		\
 
 
 #undef __field
-#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)	\
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put,	\
+		__is_signed)						\
 	if (!exclude_sensitive || !((attr_flag) & GENLA_F_SENSITIVE)) {	\
 		DPRINT_FIELD(">>", nla_type, name, s, NULL);		\
 		__put(skb, attr_nr, s->name);				\
 	}
 
 #undef __array
-#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen,	\
+		__get, __put, __is_signed)				\
 	if (!exclude_sensitive || !((attr_flag) & GENLA_F_SENSITIVE)) {	\
 		DPRINT_ARRAY(">>",nla_type, name, s, NULL);		\
 		__put(skb, attr_nr, min_t(int, maxlen,			\
@@ -431,9 +436,11 @@ static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb,		\
 /* Functions for initializing structs to default values.  */
 
 #undef __field
-#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put,	\
+		__is_signed)
 #undef __array
-#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put)
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen,	\
+		__get, __put, __is_signed)
 #undef __u32_field_def
 #define __u32_field_def(attr_nr, attr_flag, name, default)		\
 	x->name = default;
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index 0fca21fd1af5..ba911da84d9f 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -87,28 +87,28 @@ enum {
 /* possible field types */
 #define __flg_field(attr_nr, attr_flag, name) \
 	__field(attr_nr, attr_flag, name, NLA_U8, char, \
-			nla_get_u8, NLA_PUT_U8)
+			nla_get_u8, NLA_PUT_U8, false)
 #define __u8_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U8, unsigned char, \
-			nla_get_u8, NLA_PUT_U8)
+			nla_get_u8, NLA_PUT_U8, false)
 #define __u16_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U16, __u16, \
-			nla_get_u16, NLA_PUT_U16)
+			nla_get_u16, NLA_PUT_U16, false)
 #define __u32_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U32, __u32, \
-			nla_get_u32, NLA_PUT_U32)
+			nla_get_u32, NLA_PUT_U32, false)
 #define __s32_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U32, __s32, \
-			nla_get_u32, NLA_PUT_U32)
+			nla_get_u32, NLA_PUT_U32, true)
 #define __u64_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U64, __u64, \
-			nla_get_u64, NLA_PUT_U64)
+			nla_get_u64, NLA_PUT_U64, false)
 #define __str_field(attr_nr, attr_flag, name, maxlen) \
 	__array(attr_nr, attr_flag, name, NLA_NUL_STRING, char, maxlen, \
-			nla_strlcpy, NLA_PUT)
+			nla_strlcpy, NLA_PUT, false)
 #define __bin_field(attr_nr, attr_flag, name, maxlen) \
 	__array(attr_nr, attr_flag, name, NLA_BINARY, char, maxlen, \
-			nla_memcpy, NLA_PUT)
+			nla_memcpy, NLA_PUT, false)
 
 /* fields with default values */
 #define __flg_field_def(attr_nr, attr_flag, name, default) \
@@ -174,11 +174,13 @@ enum {								\
 };
 
 #undef __field
-#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)	\
+#define __field(attr_nr, attr_flag, name, nla_type, type,	\
+		__get, __put, __is_signed)			\
 	T_ ## name = (__u16)(attr_nr | attr_flag),
 
 #undef __array
-#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
+#define __array(attr_nr, attr_flag, name, nla_type, type,	\
+		maxlen, __get, __put, __is_signed)		\
 	T_ ## name = (__u16)(attr_nr | attr_flag),
 
 #include GENL_MAGIC_INCLUDE_FILE
@@ -238,11 +240,13 @@ static inline void ct_assert_unique_ ## s_name ## _attributes(void)	\
 }
 
 #undef __field
-#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put)	\
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put,	\
+		__is_signed)						\
 	case attr_nr:
 
 #undef __array
-#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen,	\
+		__get, __put, __is_signed)				\
 	case attr_nr:
 
 #include GENL_MAGIC_INCLUDE_FILE
@@ -260,16 +264,36 @@ static inline void ct_assert_unique_ ## s_name ## _attributes(void)	\
 struct s_name { s_fields };
 
 #undef __field
-#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put) \
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put,	\
+		__is_signed)						\
 	type name;
 
 #undef __array
-#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen, __get, __put) \
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen,	\
+		__get, __put, __is_signed)				\
 	type name[maxlen];	\
 	__u32 name ## _len;
 
 #include GENL_MAGIC_INCLUDE_FILE
 
+#undef GENL_struct
+#define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
+enum {									\
+	s_fields							\
+};
+
+#undef __field
+#define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put,	\
+		is_signed)						\
+	F_ ## name ## _IS_SIGNED = is_signed,
+
+#undef __array
+#define __array(attr_nr, attr_flag, name, nla_type, type, maxlen,	\
+		__get, __put, is_signed)				\
+	F_ ## name ## _IS_SIGNED = is_signed,
+
+#include GENL_MAGIC_INCLUDE_FILE
+
 /* }}}1 */
 #endif /* GENL_MAGIC_STRUCT_H */
 /* vim: set foldmethod=marker nofoldenable : */
-- 
cgit v1.2.3-55-g7522


From bbbef2d5ad8203f67274196dac90754ae106a463 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 18 May 2011 16:48:16 +0200
Subject: drbd: Remove unused GENLA_F_MAY_IGNORE flag

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/genl_magic_struct.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index ba911da84d9f..f3c3425ac30f 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -40,11 +40,6 @@ extern void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void);
  * yet implemented features, if newer userland tries to use them even though
  * the genl_family version clearly indicates they are not available.
  *
- * @GENLA_F_MAY_IGNORE: To clearly document the fact, for good measure.
- * To be used for API extensions for things that have sane defaults,
- * so newer userland can still talk to older kernel, knowing it will
- * silently ignore these attributes if not yet known.
- *
  * NOTE: These flags overload
  *   NLA_F_NESTED		(1 << 15)
  *   NLA_F_NET_BYTEORDER	(1 << 14)
@@ -55,7 +50,6 @@ extern void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void);
  * See also: nla_type()
  */
 enum {
-	GENLA_F_MAY_IGNORE	= 0,
 	GENLA_F_MANDATORY	= 1 << 14,
 	GENLA_F_REQUIRED	= 1 << 15,
 
-- 
cgit v1.2.3-55-g7522


From 5f9359201b5cf1d94fe0e0c47fcba38cfc921863 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Thu, 19 May 2011 17:39:28 +0200
Subject: drbd: Make drbd's use of netlink attribute flags less confusing

Make it more clear in the flag names which flags are internal to drbd, and
which are not.

The check for mandatory attributes is the only extension visible at the netlink
layer.  Attributes with this flag set would look like unknown attributes to
some kernel versions.  The netlink layer would ignore them and also skip
consistency checks on the attribute type and legth.  To avoid this, we check
for mandatory attributes first, remove the mandatory flag, and then process the
attributes normally.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_genl.h         | 244 +++++++++++++++++++-------------------
 include/linux/genl_magic_func.h   | 107 ++++++++---------
 include/linux/genl_magic_struct.h |  64 ++++------
 3 files changed, 193 insertions(+), 222 deletions(-)

(limited to 'include')

diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 7b174a093a8d..4ceecb9307d9 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -86,7 +86,7 @@
  */
 GENL_struct(DRBD_NLA_CFG_REPLY, 1, drbd_cfg_reply,
 		/* "arbitrary" size strings, nla_policy.len = 0 */
-	__str_field(1, GENLA_F_MANDATORY,	info_text, 0)
+	__str_field(1, DRBD_GENLA_F_MANDATORY,	info_text, 0)
 )
 
 /* Configuration requests typically need a context to operate on.
@@ -95,133 +95,133 @@ GENL_struct(DRBD_NLA_CFG_REPLY, 1, drbd_cfg_reply,
  * and/or the replication group (aka resource) name,
  * and the volume id within the resource. */
 GENL_struct(DRBD_NLA_CFG_CONTEXT, 2, drbd_cfg_context,
-	__u32_field(1, GENLA_F_MANDATORY,	ctx_volume)
-	__str_field(2, GENLA_F_MANDATORY,	ctx_conn_name, 128)
+	__u32_field(1, DRBD_GENLA_F_MANDATORY,	ctx_volume)
+	__str_field(2, DRBD_GENLA_F_MANDATORY,	ctx_conn_name, 128)
 )
 
 GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
-	__str_field(1, GENLA_F_REQUIRED | GENLA_F_INVARIANT,	backing_dev,	128)
-	__str_field(2, GENLA_F_REQUIRED | GENLA_F_INVARIANT,	meta_dev,	128)
-	__s32_field(3, GENLA_F_REQUIRED | GENLA_F_INVARIANT,	meta_dev_idx)
+	__str_field(1, DRBD_F_REQUIRED | DRBD_F_INVARIANT,	backing_dev,	128)
+	__str_field(2, DRBD_F_REQUIRED | DRBD_F_INVARIANT,	meta_dev,	128)
+	__s32_field(3, DRBD_F_REQUIRED | DRBD_F_INVARIANT,	meta_dev_idx)
 
 	/* use the resize command to try and change the disk_size */
-	__u64_field(4, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	disk_size)
+	__u64_field(4, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	disk_size)
 	/* we could change the max_bio_bvecs,
 	 * but it won't propagate through the stack */
-	__u32_field(5, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	max_bio_bvecs)
-
-	__u32_field_def(6, GENLA_F_MANDATORY,	on_io_error, DRBD_ON_IO_ERROR_DEF)
-	__u32_field_def(7, GENLA_F_MANDATORY,	fencing, DRBD_FENCING_DEF)
-
-	__u32_field_def(8,	GENLA_F_MANDATORY,	resync_rate, DRBD_RESYNC_RATE_DEF)
-	__s32_field_def(9,	GENLA_F_MANDATORY,	resync_after, DRBD_RESYNC_AFTER_DEF)
-	__u32_field_def(10,	GENLA_F_MANDATORY,	al_extents, DRBD_AL_EXTENTS_DEF)
-	__u32_field_def(11,	GENLA_F_MANDATORY,	c_plan_ahead, DRBD_C_PLAN_AHEAD_DEF)
-	__u32_field_def(12,	GENLA_F_MANDATORY,	c_delay_target, DRBD_C_DELAY_TARGET_DEF)
-	__u32_field_def(13,	GENLA_F_MANDATORY,	c_fill_target, DRBD_C_FILL_TARGET_DEF)
-	__u32_field_def(14,	GENLA_F_MANDATORY,	c_max_rate, DRBD_C_MAX_RATE_DEF)
-	__u32_field_def(15,	GENLA_F_MANDATORY,	c_min_rate, DRBD_C_MIN_RATE_DEF)
-
-	__flg_field_def(16, GENLA_F_MANDATORY,	disk_barrier, DRBD_DISK_BARRIER_DEF)
-	__flg_field_def(17, GENLA_F_MANDATORY,	disk_flushes, DRBD_DISK_FLUSHES_DEF)
-	__flg_field_def(18, GENLA_F_MANDATORY,	disk_drain, DRBD_DISK_DRAIN_DEF)
-	__flg_field_def(19, GENLA_F_MANDATORY,	md_flushes, DRBD_MD_FLUSHES_DEF)
+	__u32_field(5, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	max_bio_bvecs)
+
+	__u32_field_def(6, DRBD_GENLA_F_MANDATORY,	on_io_error, DRBD_ON_IO_ERROR_DEF)
+	__u32_field_def(7, DRBD_GENLA_F_MANDATORY,	fencing, DRBD_FENCING_DEF)
+
+	__u32_field_def(8,	DRBD_GENLA_F_MANDATORY,	resync_rate, DRBD_RESYNC_RATE_DEF)
+	__s32_field_def(9,	DRBD_GENLA_F_MANDATORY,	resync_after, DRBD_MINOR_NUMBER_DEF)
+	__u32_field_def(10,	DRBD_GENLA_F_MANDATORY,	al_extents, DRBD_AL_EXTENTS_DEF)
+	__u32_field_def(11,	DRBD_GENLA_F_MANDATORY,	c_plan_ahead, DRBD_C_PLAN_AHEAD_DEF)
+	__u32_field_def(12,	DRBD_GENLA_F_MANDATORY,	c_delay_target, DRBD_C_DELAY_TARGET_DEF)
+	__u32_field_def(13,	DRBD_GENLA_F_MANDATORY,	c_fill_target, DRBD_C_FILL_TARGET_DEF)
+	__u32_field_def(14,	DRBD_GENLA_F_MANDATORY,	c_max_rate, DRBD_C_MAX_RATE_DEF)
+	__u32_field_def(15,	DRBD_GENLA_F_MANDATORY,	c_min_rate, DRBD_C_MIN_RATE_DEF)
+
+	__flg_field_def(16, DRBD_GENLA_F_MANDATORY,	disk_barrier, DRBD_DISK_BARRIER_DEF)
+	__flg_field_def(17, DRBD_GENLA_F_MANDATORY,	disk_flushes, DRBD_DISK_FLUSHES_DEF)
+	__flg_field_def(18, DRBD_GENLA_F_MANDATORY,	disk_drain, DRBD_DISK_DRAIN_DEF)
+	__flg_field_def(19, DRBD_GENLA_F_MANDATORY,	md_flushes, DRBD_MD_FLUSHES_DEF)
 )
 
 GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
-	__str_field_def(1,	GENLA_F_MANDATORY,	cpu_mask,       32)
-	__u32_field_def(2,	GENLA_F_MANDATORY,	on_no_data, DRBD_ON_NO_DATA_DEF)
+	__str_field_def(1,	DRBD_GENLA_F_MANDATORY,	cpu_mask,       32)
+	__u32_field_def(2,	DRBD_GENLA_F_MANDATORY,	on_no_data, DRBD_ON_NO_DATA_DEF)
 )
 
 GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
-	__bin_field(1,	GENLA_F_REQUIRED | GENLA_F_INVARIANT,	my_addr,	128)
-	__bin_field(2,	GENLA_F_REQUIRED | GENLA_F_INVARIANT,	peer_addr,	128)
-	__str_field_def(3,	GENLA_F_MANDATORY | GENLA_F_SENSITIVE,
+	__bin_field(1,	DRBD_F_REQUIRED | DRBD_F_INVARIANT,	my_addr,	128)
+	__bin_field(2,	DRBD_F_REQUIRED | DRBD_F_INVARIANT,	peer_addr,	128)
+	__str_field_def(3,	DRBD_GENLA_F_MANDATORY | DRBD_F_SENSITIVE,
 						shared_secret,	SHARED_SECRET_MAX)
-	__str_field_def(4,	GENLA_F_MANDATORY,	cram_hmac_alg,	SHARED_SECRET_MAX)
-	__str_field_def(5,	GENLA_F_MANDATORY,	integrity_alg,	SHARED_SECRET_MAX)
-	__str_field_def(6,	GENLA_F_MANDATORY,	verify_alg,     SHARED_SECRET_MAX)
-	__str_field_def(7,	GENLA_F_MANDATORY,	csums_alg,	SHARED_SECRET_MAX)
-	__u32_field_def(8,	GENLA_F_MANDATORY,	wire_protocol, DRBD_PROTOCOL_DEF)
-	__u32_field_def(9,	GENLA_F_MANDATORY,	connect_int, DRBD_CONNECT_INT_DEF)
-	__u32_field_def(10,	GENLA_F_MANDATORY,	timeout, DRBD_TIMEOUT_DEF)
-	__u32_field_def(11,	GENLA_F_MANDATORY,	ping_int, DRBD_PING_INT_DEF)
-	__u32_field_def(12,	GENLA_F_MANDATORY,	ping_timeo, DRBD_PING_TIMEO_DEF)
-	__u32_field_def(13,	GENLA_F_MANDATORY,	sndbuf_size, DRBD_SNDBUF_SIZE_DEF)
-	__u32_field_def(14,	GENLA_F_MANDATORY,	rcvbuf_size, DRBD_RCVBUF_SIZE_DEF)
-	__u32_field_def(15,	GENLA_F_MANDATORY,	ko_count, DRBD_KO_COUNT_DEF)
-	__u32_field_def(16,	GENLA_F_MANDATORY,	max_buffers, DRBD_MAX_BUFFERS_DEF)
-	__u32_field_def(17,	GENLA_F_MANDATORY,	max_epoch_size, DRBD_MAX_EPOCH_SIZE_DEF)
-	__u32_field_def(18,	GENLA_F_MANDATORY,	unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF)
-	__u32_field_def(19,	GENLA_F_MANDATORY,	after_sb_0p, DRBD_AFTER_SB_0P_DEF)
-	__u32_field_def(20,	GENLA_F_MANDATORY,	after_sb_1p, DRBD_AFTER_SB_1P_DEF)
-	__u32_field_def(21,	GENLA_F_MANDATORY,	after_sb_2p, DRBD_AFTER_SB_2P_DEF)
-	__u32_field_def(22,	GENLA_F_MANDATORY,	rr_conflict, DRBD_RR_CONFLICT_DEF)
-	__u32_field_def(23,	GENLA_F_MANDATORY,	on_congestion, DRBD_ON_CONGESTION_DEF)
-	__u32_field_def(24,	GENLA_F_MANDATORY,	cong_fill, DRBD_CONG_FILL_DEF)
-	__u32_field_def(25,	GENLA_F_MANDATORY,	cong_extents, DRBD_CONG_EXTENTS_DEF)
-	__flg_field_def(26, GENLA_F_MANDATORY,	two_primaries, DRBD_ALLOW_TWO_PRIMARIES_DEF)
-	__flg_field(27, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	discard_my_data)
-	__flg_field_def(28, GENLA_F_MANDATORY,	tcp_cork, DRBD_TCP_CORK_DEF)
-	__flg_field_def(29, GENLA_F_MANDATORY,	always_asbp, DRBD_ALWAYS_ASBP_DEF)
-	__flg_field(30, GENLA_F_MANDATORY | GENLA_F_INVARIANT,	dry_run)
-	__flg_field_def(31,	GENLA_F_MANDATORY,	use_rle, DRBD_USE_RLE_DEF)
+	__str_field_def(4,	DRBD_GENLA_F_MANDATORY,	cram_hmac_alg,	SHARED_SECRET_MAX)
+	__str_field_def(5,	DRBD_GENLA_F_MANDATORY,	integrity_alg,	SHARED_SECRET_MAX)
+	__str_field_def(6,	DRBD_GENLA_F_MANDATORY,	verify_alg,     SHARED_SECRET_MAX)
+	__str_field_def(7,	DRBD_GENLA_F_MANDATORY,	csums_alg,	SHARED_SECRET_MAX)
+	__u32_field_def(8,	DRBD_GENLA_F_MANDATORY,	wire_protocol, DRBD_PROTOCOL_DEF)
+	__u32_field_def(9,	DRBD_GENLA_F_MANDATORY,	connect_int, DRBD_CONNECT_INT_DEF)
+	__u32_field_def(10,	DRBD_GENLA_F_MANDATORY,	timeout, DRBD_TIMEOUT_DEF)
+	__u32_field_def(11,	DRBD_GENLA_F_MANDATORY,	ping_int, DRBD_PING_INT_DEF)
+	__u32_field_def(12,	DRBD_GENLA_F_MANDATORY,	ping_timeo, DRBD_PING_TIMEO_DEF)
+	__u32_field_def(13,	DRBD_GENLA_F_MANDATORY,	sndbuf_size, DRBD_SNDBUF_SIZE_DEF)
+	__u32_field_def(14,	DRBD_GENLA_F_MANDATORY,	rcvbuf_size, DRBD_RCVBUF_SIZE_DEF)
+	__u32_field_def(15,	DRBD_GENLA_F_MANDATORY,	ko_count, DRBD_KO_COUNT_DEF)
+	__u32_field_def(16,	DRBD_GENLA_F_MANDATORY,	max_buffers, DRBD_MAX_BUFFERS_DEF)
+	__u32_field_def(17,	DRBD_GENLA_F_MANDATORY,	max_epoch_size, DRBD_MAX_EPOCH_SIZE_DEF)
+	__u32_field_def(18,	DRBD_GENLA_F_MANDATORY,	unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF)
+	__u32_field_def(19,	DRBD_GENLA_F_MANDATORY,	after_sb_0p, DRBD_AFTER_SB_0P_DEF)
+	__u32_field_def(20,	DRBD_GENLA_F_MANDATORY,	after_sb_1p, DRBD_AFTER_SB_1P_DEF)
+	__u32_field_def(21,	DRBD_GENLA_F_MANDATORY,	after_sb_2p, DRBD_AFTER_SB_2P_DEF)
+	__u32_field_def(22,	DRBD_GENLA_F_MANDATORY,	rr_conflict, DRBD_RR_CONFLICT_DEF)
+	__u32_field_def(23,	DRBD_GENLA_F_MANDATORY,	on_congestion, DRBD_ON_CONGESTION_DEF)
+	__u32_field_def(24,	DRBD_GENLA_F_MANDATORY,	cong_fill, DRBD_CONG_FILL_DEF)
+	__u32_field_def(25,	DRBD_GENLA_F_MANDATORY,	cong_extents, DRBD_CONG_EXTENTS_DEF)
+	__flg_field_def(26, DRBD_GENLA_F_MANDATORY,	two_primaries, DRBD_ALLOW_TWO_PRIMARIES_DEF)
+	__flg_field(27, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	discard_my_data)
+	__flg_field_def(28, DRBD_GENLA_F_MANDATORY,	tcp_cork, DRBD_TCP_CORK_DEF)
+	__flg_field_def(29, DRBD_GENLA_F_MANDATORY,	always_asbp, DRBD_ALWAYS_ASBP_DEF)
+	__flg_field(30, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	dry_run)
+	__flg_field_def(31,	DRBD_GENLA_F_MANDATORY,	use_rle, DRBD_USE_RLE_DEF)
 )
 
 GENL_struct(DRBD_NLA_SET_ROLE_PARMS, 6, set_role_parms,
-	__flg_field(1, GENLA_F_MANDATORY,	assume_uptodate)
+	__flg_field(1, DRBD_GENLA_F_MANDATORY,	assume_uptodate)
 )
 
 GENL_struct(DRBD_NLA_RESIZE_PARMS, 7, resize_parms,
-	__u64_field(1, GENLA_F_MANDATORY,	resize_size)
-	__flg_field(2, GENLA_F_MANDATORY,	resize_force)
-	__flg_field(3, GENLA_F_MANDATORY,	no_resync)
+	__u64_field(1, DRBD_GENLA_F_MANDATORY,	resize_size)
+	__flg_field(2, DRBD_GENLA_F_MANDATORY,	resize_force)
+	__flg_field(3, DRBD_GENLA_F_MANDATORY,	no_resync)
 )
 
 GENL_struct(DRBD_NLA_STATE_INFO, 8, state_info,
 	/* the reason of the broadcast,
 	 * if this is an event triggered broadcast. */
-	__u32_field(1, GENLA_F_MANDATORY,	sib_reason)
-	__u32_field(2, GENLA_F_REQUIRED,	current_state)
-	__u64_field(3, GENLA_F_MANDATORY,	capacity)
-	__u64_field(4, GENLA_F_MANDATORY,	ed_uuid)
+	__u32_field(1, DRBD_GENLA_F_MANDATORY,	sib_reason)
+	__u32_field(2, DRBD_F_REQUIRED,	current_state)
+	__u64_field(3, DRBD_GENLA_F_MANDATORY,	capacity)
+	__u64_field(4, DRBD_GENLA_F_MANDATORY,	ed_uuid)
 
 	/* These are for broadcast from after state change work.
 	 * prev_state and new_state are from the moment the state change took
 	 * place, new_state is not neccessarily the same as current_state,
 	 * there may have been more state changes since.  Which will be
 	 * broadcasted soon, in their respective after state change work.  */
-	__u32_field(5, GENLA_F_MANDATORY,	prev_state)
-	__u32_field(6, GENLA_F_MANDATORY,	new_state)
+	__u32_field(5, DRBD_GENLA_F_MANDATORY,	prev_state)
+	__u32_field(6, DRBD_GENLA_F_MANDATORY,	new_state)
 
 	/* if we have a local disk: */
-	__bin_field(7, GENLA_F_MANDATORY,	uuids, (UI_SIZE*sizeof(__u64)))
-	__u32_field(8, GENLA_F_MANDATORY,	disk_flags)
-	__u64_field(9, GENLA_F_MANDATORY,	bits_total)
-	__u64_field(10, GENLA_F_MANDATORY,	bits_oos)
+	__bin_field(7, DRBD_GENLA_F_MANDATORY,	uuids, (UI_SIZE*sizeof(__u64)))
+	__u32_field(8, DRBD_GENLA_F_MANDATORY,	disk_flags)
+	__u64_field(9, DRBD_GENLA_F_MANDATORY,	bits_total)
+	__u64_field(10, DRBD_GENLA_F_MANDATORY,	bits_oos)
 	/* and in case resync or online verify is active */
-	__u64_field(11, GENLA_F_MANDATORY,	bits_rs_total)
-	__u64_field(12, GENLA_F_MANDATORY,	bits_rs_failed)
+	__u64_field(11, DRBD_GENLA_F_MANDATORY,	bits_rs_total)
+	__u64_field(12, DRBD_GENLA_F_MANDATORY,	bits_rs_failed)
 
 	/* for pre and post notifications of helper execution */
-	__str_field(13, GENLA_F_MANDATORY,	helper, 32)
-	__u32_field(14, GENLA_F_MANDATORY,	helper_exit_code)
+	__str_field(13, DRBD_GENLA_F_MANDATORY,	helper, 32)
+	__u32_field(14, DRBD_GENLA_F_MANDATORY,	helper_exit_code)
 )
 
 GENL_struct(DRBD_NLA_START_OV_PARMS, 9, start_ov_parms,
-	__u64_field(1, GENLA_F_MANDATORY,	ov_start_sector)
+	__u64_field(1, DRBD_GENLA_F_MANDATORY,	ov_start_sector)
 )
 
 GENL_struct(DRBD_NLA_NEW_C_UUID_PARMS, 10, new_c_uuid_parms,
-	__flg_field(1, GENLA_F_MANDATORY, clear_bm)
+	__flg_field(1, DRBD_GENLA_F_MANDATORY, clear_bm)
 )
 
 GENL_struct(DRBD_NLA_TIMEOUT_PARMS, 11, timeout_parms,
-	__u32_field(1,	GENLA_F_REQUIRED,	timeout_type)
+	__u32_field(1,	DRBD_F_REQUIRED,	timeout_type)
 )
 
 GENL_struct(DRBD_NLA_DISCONNECT_PARMS, 12, disconnect_parms,
-	__flg_field(1, GENLA_F_MANDATORY,	force_disconnect)
+	__flg_field(1, DRBD_GENLA_F_MANDATORY,	force_disconnect)
 )
 
 /*
@@ -232,11 +232,11 @@ GENL_mc_group(events)
 	/* kernel -> userspace announcement of changes */
 GENL_notification(
 	DRBD_EVENT, 1, events,
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_STATE_INFO, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_NET_CONF, GENLA_F_MANDATORY)
-	GENL_tla_expected(DRBD_NLA_DISK_CONF, GENLA_F_MANDATORY)
-	GENL_tla_expected(DRBD_NLA_SYNCER_CONF, GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_STATE_INFO, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NET_CONF, DRBD_GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_DISK_CONF, DRBD_GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_SYNCER_CONF, DRBD_GENLA_F_MANDATORY)
 )
 
 	/* query kernel for specific or all info */
@@ -250,116 +250,116 @@ GENL_op(
 	),
 	/* To select the object .doit.
 	 * Or a subset of objects in .dumpit. */
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY)
 )
 
 #if 0
 	/* TO BE DONE */
 	/* create or destroy resources, aka replication groups */
 GENL_op(DRBD_ADM_CREATE_RESOURCE, 3, GENL_doit(drbd_adm_create_resource),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_DELETE_RESOURCE, 4, GENL_doit(drbd_adm_delete_resource),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 #endif
 
 	/* add DRBD minor devices as volumes to resources */
 GENL_op(DRBD_ADM_ADD_MINOR, 5, GENL_doit(drbd_adm_add_minor),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_DEL_MINOR, 6, GENL_doit(drbd_adm_delete_minor),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 
 	/* add or delete replication links to resources */
 GENL_op(DRBD_ADM_ADD_LINK, 7, GENL_doit(drbd_adm_create_connection),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_DEL_LINK, 8, GENL_doit(drbd_adm_delete_connection),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 
 GENL_op(DRBD_ADM_RESOURCE_OPTS, 9,
 	GENL_doit(drbd_adm_resource_opts),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_RESOURCE_OPTS, GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_RESOURCE_OPTS, DRBD_GENLA_F_MANDATORY)
 )
 
 GENL_op(
 	DRBD_ADM_CONNECT, 10,
 	GENL_doit(drbd_adm_connect),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_NET_CONF, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NET_CONF, DRBD_F_REQUIRED)
 )
 
 GENL_op(
 	DRBD_ADM_CHG_NET_OPTS, 29,
 	GENL_doit(drbd_adm_net_opts),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_NET_CONF, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NET_CONF, DRBD_F_REQUIRED)
 )
 
 GENL_op(DRBD_ADM_DISCONNECT, 11, GENL_doit(drbd_adm_disconnect),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 
 GENL_op(DRBD_ADM_ATTACH, 12,
 	GENL_doit(drbd_adm_attach),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_DISK_CONF, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_DISK_CONF, DRBD_F_REQUIRED)
 )
 
 GENL_op(DRBD_ADM_CHG_DISK_OPTS, 28,
 	GENL_doit(drbd_adm_disk_opts),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_DISK_OPTS, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_DISK_OPTS, DRBD_F_REQUIRED)
 )
 
 GENL_op(
 	DRBD_ADM_RESIZE, 13,
 	GENL_doit(drbd_adm_resize),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_RESIZE_PARMS, GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_RESIZE_PARMS, DRBD_GENLA_F_MANDATORY)
 )
 
 GENL_op(
 	DRBD_ADM_PRIMARY, 14,
 	GENL_doit(drbd_adm_set_role),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_SET_ROLE_PARMS, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_SET_ROLE_PARMS, DRBD_F_REQUIRED)
 )
 
 GENL_op(
 	DRBD_ADM_SECONDARY, 15,
 	GENL_doit(drbd_adm_set_role),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_SET_ROLE_PARMS, GENLA_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_SET_ROLE_PARMS, DRBD_F_REQUIRED)
 )
 
 GENL_op(
 	DRBD_ADM_NEW_C_UUID, 16,
 	GENL_doit(drbd_adm_new_c_uuid),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED)
-	GENL_tla_expected(DRBD_NLA_NEW_C_UUID_PARMS, GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_NEW_C_UUID_PARMS, DRBD_GENLA_F_MANDATORY)
 )
 
 GENL_op(
 	DRBD_ADM_START_OV, 17,
 	GENL_doit(drbd_adm_start_ov),
-	GENL_tla_expected(DRBD_NLA_START_OV_PARMS, GENLA_F_MANDATORY)
+	GENL_tla_expected(DRBD_NLA_START_OV_PARMS, DRBD_GENLA_F_MANDATORY)
 )
 
 GENL_op(DRBD_ADM_DETACH,	18, GENL_doit(drbd_adm_detach),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_INVALIDATE,	19, GENL_doit(drbd_adm_invalidate),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_INVAL_PEER,	20, GENL_doit(drbd_adm_invalidate_peer),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_PAUSE_SYNC,	21, GENL_doit(drbd_adm_pause_sync),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_RESUME_SYNC,	22, GENL_doit(drbd_adm_resume_sync),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_SUSPEND_IO,	23, GENL_doit(drbd_adm_suspend_io),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_RESUME_IO,	24, GENL_doit(drbd_adm_resume_io),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_OUTDATE,	25, GENL_doit(drbd_adm_outdate),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_GET_TIMEOUT_TYPE, 26, GENL_doit(drbd_adm_get_timeout_type),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_DOWN,		27, GENL_doit(drbd_adm_down),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, GENLA_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 2ae16126c6a4..58edd403a3ff 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -3,53 +3,6 @@
 
 #include <linux/genl_magic_struct.h>
 
-/*
- * Extension of genl attribute validation policies			{{{1
- *									{{{2
- */
-
-/**
- * nla_is_required - return true if this attribute is required
- * @nla: netlink attribute
- */
-static inline int nla_is_required(const struct nlattr *nla)
-{
-        return nla->nla_type & GENLA_F_REQUIRED;
-}
-
-/**
- * nla_is_mandatory - return true if understanding this attribute is mandatory
- * @nla: netlink attribute
- * Note: REQUIRED attributes are implicitly MANDATORY as well
- */
-static inline int nla_is_mandatory(const struct nlattr *nla)
-{
-        return nla->nla_type & (GENLA_F_MANDATORY | GENLA_F_REQUIRED);
-}
-
-/* Functionality to be integrated into nla_parse(), and validate_nla(),
- * respectively.
- *
- * Enforcing the "mandatory" bit is done here,
- * by rejecting unknown mandatory attributes.
- *
- * Part of enforcing the "required" flag would mean to embed it into
- * nla_policy.type, and extending validate_nla(), which currently does
- * BUG_ON(pt->type > NLA_TYPE_MAX); we have to work on existing kernels,
- * so we cannot do that.  Thats why enforcing "required" is done in the
- * generated assignment functions below. */
-static int nla_check_unknown(int maxtype, struct nlattr *head, int len)
-{
-	struct nlattr *nla;
-	int rem;
-        nla_for_each_attr(nla, head, len, rem) {
-		__u16 type = nla_type(nla);
-		if (type > maxtype && nla_is_mandatory(nla))
-			return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
 /*
  * Magic: declare tla policy						{{{1
  * Magic: declare nested policies
@@ -80,13 +33,13 @@ static struct nla_policy s_name ## _nl_policy[] __read_mostly =		\
 #undef __field
 #define __field(attr_nr, attr_flag, name, nla_type, _type, __get,	\
 		 __put, __is_signed)					\
-	[__nla_type(attr_nr)] = { .type = nla_type },
+	[attr_nr] = { .type = nla_type },
 
 #undef __array
 #define __array(attr_nr, attr_flag, name, nla_type, _type, maxlen,	\
 		__get, __put, __is_signed)				\
-	[__nla_type(attr_nr)] = { .type = nla_type,			\
-		.len = maxlen - (nla_type == NLA_NUL_STRING) },
+	[attr_nr] = { .type = nla_type,					\
+		      .len = maxlen - (nla_type == NLA_NUL_STRING) },
 
 #include GENL_MAGIC_INCLUDE_FILE
 
@@ -189,6 +142,43 @@ static struct nlattr *nested_attr_tb[128];
 #define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); }))
 #endif
 
+static inline int drbd_nla_check_mandatory(int maxtype, struct nlattr *nla)
+{
+	struct nlattr *head = nla_data(nla);
+	int len = nla_len(nla);
+	int rem;
+
+	/*
+	 * validate_nla (called from nla_parse_nested) ignores attributes
+	 * beyond maxtype, and does not understand the DRBD_GENLA_F_MANDATORY flag.
+	 * In order to have it validate attributes with the DRBD_GENLA_F_MANDATORY
+	 * flag set also, check and remove that flag before calling
+	 * nla_parse_nested.
+	 */
+
+	nla_for_each_attr(nla, head, len, rem) {
+		if (nla->nla_type & DRBD_GENLA_F_MANDATORY) {
+			if (nla_type(nla) > maxtype)
+				return -EOPNOTSUPP;
+			nla->nla_type &= ~DRBD_GENLA_F_MANDATORY;
+		}
+	}
+	return 0;
+}
+
+static inline int drbd_nla_parse_nested(struct nlattr *tb[], int maxtype,
+					struct nlattr *nla,
+					const struct nla_policy *policy)
+{
+	int err;
+
+	err = drbd_nla_check_mandatory(maxtype, nla);
+	if (!err)
+		err = nla_parse_nested(tb, maxtype, nla, policy);
+
+	return err;
+}
+
 #undef GENL_struct
 #define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
 /* *_from_attrs functions are static, but potentially unused */		\
@@ -204,12 +194,9 @@ static int __ ## s_name ## _from_attrs(struct s_name *s,		\
 	if (!tla)							\
 		return -ENOMSG;						\
 	DPRINT_TLA(#s_name, "<=-", #tag_name);				\
-	err = nla_parse_nested(ntb, maxtype, tla, s_name ## _nl_policy); \
+	err = drbd_nla_parse_nested(ntb, maxtype, tla, s_name ## _nl_policy);	\
 	if (err)							\
 		return err;						\
-	err = nla_check_unknown(maxtype, nla_data(tla), nla_len(tla));	\
-	if (err)							\
-	      return err;						\
 									\
 	s_fields							\
 	return 0;							\
@@ -226,17 +213,17 @@ static int s_name ## _from_attrs_for_change(struct s_name *s,		\
 }					__attribute__((unused))		\
 
 #define __assign(attr_nr, attr_flag, name, nla_type, type, assignment...)	\
-		nla = ntb[__nla_type(attr_nr)];				\
+		nla = ntb[attr_nr];						\
 		if (nla) {						\
-			if (exclude_invariants && ((attr_flag) & GENLA_F_INVARIANT)) {		\
+			if (exclude_invariants && ((attr_flag) & DRBD_F_INVARIANT)) {		\
 				pr_info("<< must not change invariant attr: %s\n", #name);	\
 				return -EEXIST;				\
 			}						\
 			assignment;					\
-		} else if (exclude_invariants && ((attr_flag) & GENLA_F_INVARIANT)) {		\
+		} else if (exclude_invariants && ((attr_flag) & DRBD_F_INVARIANT)) {		\
 			/* attribute missing from payload, */		\
 			/* which was expected */			\
-		} else if ((attr_flag) & GENLA_F_REQUIRED) {		\
+		} else if ((attr_flag) & DRBD_F_REQUIRED) {		\
 			pr_info("<< missing attr: %s\n", #name);	\
 			return -ENOMSG;					\
 		}
@@ -415,7 +402,7 @@ static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb,		\
 #undef __field
 #define __field(attr_nr, attr_flag, name, nla_type, type, __get, __put,	\
 		__is_signed)						\
-	if (!exclude_sensitive || !((attr_flag) & GENLA_F_SENSITIVE)) {	\
+	if (!exclude_sensitive || !((attr_flag) & DRBD_F_SENSITIVE)) {	\
 		DPRINT_FIELD(">>", nla_type, name, s, NULL);		\
 		__put(skb, attr_nr, s->name);				\
 	}
@@ -423,7 +410,7 @@ static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb,		\
 #undef __array
 #define __array(attr_nr, attr_flag, name, nla_type, type, maxlen,	\
 		__get, __put, __is_signed)				\
-	if (!exclude_sensitive || !((attr_flag) & GENLA_F_SENSITIVE)) {	\
+	if (!exclude_sensitive || !((attr_flag) & DRBD_F_SENSITIVE)) {	\
 		DPRINT_ARRAY(">>",nla_type, name, s, NULL);		\
 		__put(skb, attr_nr, min_t(int, maxlen,			\
 			s->name ## _len + (nla_type == NLA_NUL_STRING)),\
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index f3c3425ac30f..1d0bd79e27b3 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -26,50 +26,34 @@ extern void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void);
  * Extension of genl attribute validation policies			{{{2
  */
 
-/**
- * GENLA_F_FLAGS - policy type flags to ease compatible ABI evolvement
- *
- * @GENLA_F_REQUIRED: attribute has to be present, or message is considered invalid.
- * Adding new REQUIRED attributes breaks ABI compatibility, so don't do that.
+/*
+ * @DRBD_GENLA_F_MANDATORY: By default, netlink ignores attributes it does not
+ * know about.  This flag can be set in nlattr->nla_type to indicate that this
+ * attribute must not be ignored.
  *
- * @GENLA_F_MANDATORY: if present, receiver _must_ understand it.
- * Without this, unknown attributes (> maxtype) are _silently_ ignored
- * by validate_nla().
+ * We check and remove this flag in drbd_nla_check_mandatory() before
+ * validating the attribute types and lengths via nla_parse_nested().
+ */
+#define DRBD_GENLA_F_MANDATORY (1 << 14)
+
+/*
+ * Flags specific to drbd and not visible at the netlink layer, used in
+ * <struct>_from_attrs and <struct>_to_skb:
  *
- * To be used for API extensions, so older kernel can reject requests for not
- * yet implemented features, if newer userland tries to use them even though
- * the genl_family version clearly indicates they are not available.
+ * @DRBD_F_REQUIRED: Attribute is required; a request without this attribute is
+ * invalid.
  *
- * NOTE: These flags overload
- *   NLA_F_NESTED		(1 << 15)
- *   NLA_F_NET_BYTEORDER	(1 << 14)
- * from linux/netlink.h, which are not useful for validate_nla():
- * NET_BYTEORDER is not used anywhere, and NESTED would be specified by setting
- * .type = NLA_NESTED in the appropriate policy.
+ * @DRBD_F_SENSITIVE: Attribute includes sensitive information and must not be
+ * included in unpriviledged get requests or broadcasts.
  *
- * See also: nla_type()
+ * @DRBD_F_INVARIANT: Attribute is set when an object is initially created, but
+ * cannot subsequently be changed.
  */
-enum {
-	GENLA_F_MANDATORY	= 1 << 14,
-	GENLA_F_REQUIRED	= 1 << 15,
-
-	/* Below will not be present in the __u16 .nla_type, but can be
-	 * triggered on in <struct>_to_skb resp. <struct>_from_attrs */
-
-	/* To exclude "sensitive" information from broadcasts, or on
-	 * unpriviledged get requests.  This is useful because genetlink
-	 * multicast groups can be listened in on by anyone.  */
-	GENLA_F_SENSITIVE	= 1 << 16,
-
-	/* INVARIAN options cannot be changed at runtime.
-	 * Useful to share an attribute policy and struct definition,
-	 * between some "create" and "change" commands,
-	 * but disallow certain fields to be changed online.
-	 */
-	GENLA_F_INVARIANT	= 1 << 17,
-};
+#define DRBD_F_REQUIRED (1 << 0)
+#define DRBD_F_SENSITIVE (1 << 1)
+#define DRBD_F_INVARIANT (1 << 2)
 
-#define __nla_type(x)	((__u16)((__u16)(x) & (__u16)NLA_TYPE_MASK))
+#define __nla_type(x)	((__u16)((x) & NLA_TYPE_MASK & ~DRBD_GENLA_F_MANDATORY))
 
 /*									}}}1
  * MAGIC
@@ -170,12 +154,12 @@ enum {								\
 #undef __field
 #define __field(attr_nr, attr_flag, name, nla_type, type,	\
 		__get, __put, __is_signed)			\
-	T_ ## name = (__u16)(attr_nr | attr_flag),
+	T_ ## name = (__u16)(attr_nr | ((attr_flag) & DRBD_GENLA_F_MANDATORY)),
 
 #undef __array
 #define __array(attr_nr, attr_flag, name, nla_type, type,	\
 		maxlen, __get, __put, __is_signed)		\
-	T_ ## name = (__u16)(attr_nr | attr_flag),
+	T_ ## name = (__u16)(attr_nr | ((attr_flag) & DRBD_GENLA_F_MANDATORY)),
 
 #include GENL_MAGIC_INCLUDE_FILE
 
-- 
cgit v1.2.3-55-g7522


From 5084d71d89e1a94193378efb12ac659e4e6ada3f Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Tue, 24 May 2011 14:08:58 +0200
Subject: drbd: drbd_nla_check_mandatory(): Need to remove the
 DRBD_GENLA_F_MANDATORY flag first

We need to remove the flag before checking for valid types.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/genl_magic_func.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 58edd403a3ff..357f2ad403b1 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -158,9 +158,9 @@ static inline int drbd_nla_check_mandatory(int maxtype, struct nlattr *nla)
 
 	nla_for_each_attr(nla, head, len, rem) {
 		if (nla->nla_type & DRBD_GENLA_F_MANDATORY) {
+			nla->nla_type &= ~DRBD_GENLA_F_MANDATORY;
 			if (nla_type(nla) > maxtype)
 				return -EOPNOTSUPP;
-			nla->nla_type &= ~DRBD_GENLA_F_MANDATORY;
 		}
 	}
 	return 0;
-- 
cgit v1.2.3-55-g7522


From 67b58bf723b083d4776cd7c9959246ef46c0d36f Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Mon, 6 Jun 2011 15:36:04 +0200
Subject: drbd: spelling fix: too small

It is not "to small", but "too small".

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c | 8 ++++----
 include/linux/drbd.h         | 4 ++--
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 59923db780b9..31d27dd92924 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1360,7 +1360,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		dev_err(DEV, "max capacity %llu smaller than disk size %llu\n",
 			(unsigned long long) drbd_get_max_capacity(nbc),
 			(unsigned long long) new_disk_conf->disk_size);
-		retcode = ERR_DISK_TO_SMALL;
+		retcode = ERR_DISK_TOO_SMALL;
 		goto fail;
 	}
 
@@ -1374,7 +1374,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (drbd_get_capacity(nbc->md_bdev) < min_md_device_sectors) {
-		retcode = ERR_MD_DISK_TO_SMALL;
+		retcode = ERR_MD_DISK_TOO_SMALL;
 		dev_warn(DEV, "refusing attach: md-device too small, "
 		     "at least %llu sectors needed for this meta-disk type\n",
 		     (unsigned long long) min_md_device_sectors);
@@ -1385,7 +1385,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	 * (we may currently be R_PRIMARY with no local disk...) */
 	if (drbd_get_max_capacity(nbc) <
 	    drbd_get_capacity(mdev->this_bdev)) {
-		retcode = ERR_DISK_TO_SMALL;
+		retcode = ERR_DISK_TOO_SMALL;
 		goto fail;
 	}
 
@@ -1447,7 +1447,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	if (drbd_md_test_flag(nbc, MDF_CONSISTENT) &&
 	    drbd_new_dev_size(mdev, nbc, nbc->disk_conf->disk_size, 0) < nbc->md.la_size_sect) {
 		dev_warn(DEV, "refusing to truncate a consistent device\n");
-		retcode = ERR_DISK_TO_SMALL;
+		retcode = ERR_DISK_TOO_SMALL;
 		goto force_diskless_dec;
 	}
 
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 679e81123229..fedda00374af 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -112,8 +112,8 @@ enum drbd_ret_code {
 	ERR_OPEN_MD_DISK	= 105,
 	ERR_DISK_NOT_BDEV	= 107,
 	ERR_MD_NOT_BDEV		= 108,
-	ERR_DISK_TO_SMALL	= 111,
-	ERR_MD_DISK_TO_SMALL	= 112,
+	ERR_DISK_TOO_SMALL	= 111,
+	ERR_MD_DISK_TOO_SMALL	= 112,
 	ERR_BDCLAIM_DISK	= 114,
 	ERR_BDCLAIM_MD_DISK	= 115,
 	ERR_MD_IDX_INVALID	= 116,
-- 
cgit v1.2.3-55-g7522


From 789c1b626cb490acb36cf481b45040b324f60fde Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Mon, 6 Jun 2011 16:16:44 +0200
Subject: drbd: Use the terminology suggested by the command names in the
 source code and messages

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c | 16 ++++++++--------
 include/linux/drbd.h         |  4 ++--
 include/linux/drbd_genl.h    | 17 ++++-------------
 3 files changed, 14 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 31d27dd92924..5b4090f52f5a 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -47,8 +47,8 @@
 int drbd_adm_add_minor(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_delete_minor(struct sk_buff *skb, struct genl_info *info);
 
-int drbd_adm_create_connection(struct sk_buff *skb, struct genl_info *info);
-int drbd_adm_delete_connection(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_down(struct sk_buff *skb, struct genl_info *info);
 
 int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info);
@@ -2972,7 +2972,7 @@ drbd_check_conn_name(const char *name)
 	return NO_ERROR;
 }
 
-int drbd_adm_create_connection(struct sk_buff *skb, struct genl_info *info)
+int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info)
 {
 	enum drbd_ret_code retcode;
 
@@ -2989,7 +2989,7 @@ int drbd_adm_create_connection(struct sk_buff *skb, struct genl_info *info)
 	if (adm_ctx.tconn) {
 		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL) {
 			retcode = ERR_INVALID_REQUEST;
-			drbd_msg_put_info("connection exists");
+			drbd_msg_put_info("resource exists");
 		}
 		/* else: still NO_ERROR */
 		goto out;
@@ -3086,7 +3086,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 
 	if (!adm_ctx.tconn) {
-		retcode = ERR_CONN_NOT_KNOWN;
+		retcode = ERR_RES_NOT_KNOWN;
 		goto out;
 	}
 
@@ -3140,7 +3140,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		retcode = NO_ERROR;
 	} else {
 		/* "can not happen" */
-		retcode = ERR_CONN_IN_USE;
+		retcode = ERR_RES_IN_USE;
 		drbd_msg_put_info("failed to delete connection");
 	}
 	goto out;
@@ -3149,7 +3149,7 @@ out:
 	return 0;
 }
 
-int drbd_adm_delete_connection(struct sk_buff *skb, struct genl_info *info)
+int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 {
 	enum drbd_ret_code retcode;
 
@@ -3166,7 +3166,7 @@ int drbd_adm_delete_connection(struct sk_buff *skb, struct genl_info *info)
 
 		retcode = NO_ERROR;
 	} else {
-		retcode = ERR_CONN_IN_USE;
+		retcode = ERR_RES_IN_USE;
 	}
 
 	if (retcode == NO_ERROR)
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index fedda00374af..161cd414b036 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -155,8 +155,8 @@ enum drbd_ret_code {
 	ERR_CONG_NOT_PROTO_A	= 155,
 	ERR_PIC_AFTER_DEP	= 156,
 	ERR_PIC_PEER_DEP	= 157,
-	ERR_CONN_NOT_KNOWN      = 158,
-	ERR_CONN_IN_USE         = 159,
+	ERR_RES_NOT_KNOWN	= 158,
+	ERR_RES_IN_USE		= 159,
 	ERR_MINOR_CONFIGURED    = 160,
 	ERR_MINOR_EXISTS	= 161,
 	ERR_INVALID_REQUEST	= 162,
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 4ceecb9307d9..47ef324b69db 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -253,25 +253,16 @@ GENL_op(
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY)
 )
 
-#if 0
-	/* TO BE DONE */
-	/* create or destroy resources, aka replication groups */
-GENL_op(DRBD_ADM_CREATE_RESOURCE, 3, GENL_doit(drbd_adm_create_resource),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
-GENL_op(DRBD_ADM_DELETE_RESOURCE, 4, GENL_doit(drbd_adm_delete_resource),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
-#endif
-
 	/* add DRBD minor devices as volumes to resources */
-GENL_op(DRBD_ADM_ADD_MINOR, 5, GENL_doit(drbd_adm_add_minor),
+GENL_op(DRBD_ADM_NEW_MINOR, 5, GENL_doit(drbd_adm_add_minor),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_DEL_MINOR, 6, GENL_doit(drbd_adm_delete_minor),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 
-	/* add or delete replication links to resources */
-GENL_op(DRBD_ADM_ADD_LINK, 7, GENL_doit(drbd_adm_create_connection),
+	/* add or delete resources */
+GENL_op(DRBD_ADM_NEW_RESOURCE, 7, GENL_doit(drbd_adm_new_resource),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
-GENL_op(DRBD_ADM_DEL_LINK, 8, GENL_doit(drbd_adm_delete_connection),
+GENL_op(DRBD_ADM_DEL_RESOURCE, 8, GENL_doit(drbd_adm_del_resource),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 
 GENL_op(DRBD_ADM_RESOURCE_OPTS, 9,
-- 
cgit v1.2.3-55-g7522


From 7c3063cc6f0e75cdf312f5f318f9a4c02e460397 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Thu, 9 Jun 2011 17:52:12 +0200
Subject: drbd: Also need to check for DRBD_GENLA_F_MANDATORY flags before
 nla_find_nested()

This is done by introducing drbd_nla_find_nested() which handles the flag
before calling nla_find_nested().

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h   |  6 +++
 drivers/block/drbd/drbd_nl.c    | 96 ++++++++++++++++++++++++++++++++---------
 include/linux/drbd_genl.h       |  2 +-
 include/linux/genl_magic_func.h | 37 ----------------
 4 files changed, 83 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index c3019730a24f..c58430183d5f 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1407,6 +1407,12 @@ extern bool conn_try_outdate_peer(struct drbd_tconn *tconn);
 extern void conn_try_outdate_peer_async(struct drbd_tconn *tconn);
 extern int drbd_khelper(struct drbd_conf *mdev, char *cmd);
 
+struct nla_policy;
+extern int drbd_nla_check_mandatory(int maxtype, struct nlattr *nla);
+extern int drbd_nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+				 const struct nla_policy *policy);
+extern struct nlattr *drbd_nla_find_nested(int maxtype, struct nlattr *nla, int attrtype);
+
 /* drbd_worker.c */
 extern int drbd_worker(struct drbd_thread *thi);
 enum drbd_ret_code drbd_resync_after_valid(struct drbd_conf *mdev, int o_minor);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 5b4090f52f5a..24187f1c93d5 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -92,7 +92,7 @@ static struct drbd_config_context {
 #define VOLUME_UNSPECIFIED		(-1U)
 	/* pointer into the request skb,
 	 * limited lifetime! */
-	char *conn_name;
+	char *resource_name;
 
 	/* reply buffer */
 	struct sk_buff *reply_skb;
@@ -191,15 +191,15 @@ static int drbd_adm_prepare(struct sk_buff *skb, struct genl_info *info,
 		/* and assign stuff to the global adm_ctx */
 		nla = nested_attr_tb[__nla_type(T_ctx_volume)];
 		adm_ctx.volume = nla ? nla_get_u32(nla) : VOLUME_UNSPECIFIED;
-		nla = nested_attr_tb[__nla_type(T_ctx_conn_name)];
+		nla = nested_attr_tb[__nla_type(T_ctx_resource_name)];
 		if (nla)
-			adm_ctx.conn_name = nla_data(nla);
+			adm_ctx.resource_name = nla_data(nla);
 	} else
 		adm_ctx.volume = VOLUME_UNSPECIFIED;
 
 	adm_ctx.minor = d_in->minor;
 	adm_ctx.mdev = minor_to_mdev(d_in->minor);
-	adm_ctx.tconn = conn_get_by_name(adm_ctx.conn_name);
+	adm_ctx.tconn = conn_get_by_name(adm_ctx.resource_name);
 
 	if (!adm_ctx.mdev && (flags & DRBD_ADM_NEED_MINOR)) {
 		drbd_msg_put_info("unknown minor");
@@ -214,7 +214,8 @@ static int drbd_adm_prepare(struct sk_buff *skb, struct genl_info *info,
 	if (adm_ctx.mdev && adm_ctx.tconn &&
 	    adm_ctx.mdev->tconn != adm_ctx.tconn) {
 		pr_warning("request: minor=%u, conn=%s; but that minor belongs to connection %s\n",
-				adm_ctx.minor, adm_ctx.conn_name, adm_ctx.mdev->tconn->name);
+				adm_ctx.minor, adm_ctx.resource_name,
+				adm_ctx.mdev->tconn->name);
 		drbd_msg_put_info("minor exists in different connection");
 		return ERR_INVALID_REQUEST;
 	}
@@ -239,7 +240,7 @@ fail:
 static int drbd_adm_finish(struct genl_info *info, int retcode)
 {
 	struct nlattr *nla;
-	const char *conn_name = NULL;
+	const char *resource_name = NULL;
 
 	if (adm_ctx.tconn) {
 		kref_put(&adm_ctx.tconn->kref, &conn_destroy);
@@ -253,9 +254,10 @@ static int drbd_adm_finish(struct genl_info *info, int retcode)
 
 	nla = info->attrs[DRBD_NLA_CFG_CONTEXT];
 	if (nla) {
-		nla = nla_find_nested(nla, __nla_type(T_ctx_conn_name));
-		if (nla)
-			conn_name = nla_data(nla);
+		int maxtype = ARRAY_SIZE(drbd_cfg_context_nl_policy) - 1;
+		nla = drbd_nla_find_nested(maxtype, nla, __nla_type(T_ctx_resource_name));
+		if (nla && !IS_ERR(nla))
+			resource_name = nla_data(nla);
 	}
 
 	drbd_adm_send_reply(adm_ctx.reply_skb, info);
@@ -2526,7 +2528,7 @@ int drbd_adm_outdate(struct sk_buff *skb, struct genl_info *info)
 	return drbd_adm_simple_request_state(skb, info, NS(disk, D_OUTDATED));
 }
 
-int nla_put_drbd_cfg_context(struct sk_buff *skb, const char *conn_name, unsigned vnr)
+int nla_put_drbd_cfg_context(struct sk_buff *skb, const char *resource_name, unsigned vnr)
 {
 	struct nlattr *nla;
 	nla = nla_nest_start(skb, DRBD_NLA_CFG_CONTEXT);
@@ -2534,7 +2536,7 @@ int nla_put_drbd_cfg_context(struct sk_buff *skb, const char *conn_name, unsigne
 		goto nla_put_failure;
 	if (vnr != VOLUME_UNSPECIFIED)
 		NLA_PUT_U32(skb, T_ctx_volume, vnr);
-	NLA_PUT_STRING(skb, T_ctx_conn_name, conn_name);
+	NLA_PUT_STRING(skb, T_ctx_resource_name, resource_name);
 	nla_nest_end(skb, nla);
 	return 0;
 
@@ -2778,8 +2780,9 @@ int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	const unsigned hdrlen = GENL_HDRLEN + GENL_MAGIC_FAMILY_HDRSZ;
 	struct nlattr *nla;
-	const char *conn_name;
+	const char *resource_name;
 	struct drbd_tconn *tconn;
+	int maxtype;
 
 	/* Is this a followup call? */
 	if (cb->args[0]) {
@@ -2799,12 +2802,15 @@ int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb)
 	/* No explicit context given.  Dump all. */
 	if (!nla)
 		goto dump;
-	nla = nla_find_nested(nla, __nla_type(T_ctx_conn_name));
+	maxtype = ARRAY_SIZE(drbd_cfg_context_nl_policy) - 1;
+	nla = drbd_nla_find_nested(maxtype, nla, __nla_type(T_ctx_resource_name));
+	if (IS_ERR(nla))
+		return PTR_ERR(nla);
 	/* context given, but no name present? */
 	if (!nla)
 		return -EINVAL;
-	conn_name = nla_data(nla);
-	tconn = conn_get_by_name(conn_name);
+	resource_name = nla_data(nla);
+	tconn = conn_get_by_name(resource_name);
 
 	if (!tconn)
 		return -ENODEV;
@@ -2957,16 +2963,16 @@ out_nolock:
 }
 
 static enum drbd_ret_code
-drbd_check_conn_name(const char *name)
+drbd_check_resource_name(const char *name)
 {
 	if (!name || !name[0]) {
-		drbd_msg_put_info("connection name missing");
+		drbd_msg_put_info("resource name missing");
 		return ERR_MANDATORY_TAG;
 	}
 	/* if we want to use these in sysfs/configfs/debugfs some day,
 	 * we must not allow slashes */
 	if (strchr(name, '/')) {
-		drbd_msg_put_info("invalid connection name");
+		drbd_msg_put_info("invalid resource name");
 		return ERR_INVALID_REQUEST;
 	}
 	return NO_ERROR;
@@ -2982,7 +2988,7 @@ int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto out;
 
-	retcode = drbd_check_conn_name(adm_ctx.conn_name);
+	retcode = drbd_check_resource_name(adm_ctx.resource_name);
 	if (retcode != NO_ERROR)
 		goto out;
 
@@ -2995,7 +3001,7 @@ int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 	}
 
-	if (!conn_create(adm_ctx.conn_name))
+	if (!conn_create(adm_ctx.resource_name))
 		retcode = ERR_NOMEM;
 out:
 	drbd_adm_finish(info, retcode);
@@ -3213,3 +3219,53 @@ failed:
 			"Event seq:%u sib_reason:%u\n",
 			err, seq, sib->sib_reason);
 }
+
+int drbd_nla_check_mandatory(int maxtype, struct nlattr *nla)
+{
+	struct nlattr *head = nla_data(nla);
+	int len = nla_len(nla);
+	int rem;
+
+	/*
+	 * validate_nla (called from nla_parse_nested) ignores attributes
+	 * beyond maxtype, and does not understand the DRBD_GENLA_F_MANDATORY flag.
+	 * In order to have it validate attributes with the DRBD_GENLA_F_MANDATORY
+	 * flag set also, check and remove that flag before calling
+	 * nla_parse_nested.
+	 */
+
+	nla_for_each_attr(nla, head, len, rem) {
+		if (nla->nla_type & DRBD_GENLA_F_MANDATORY) {
+			nla->nla_type &= ~DRBD_GENLA_F_MANDATORY;
+			if (nla_type(nla) > maxtype)
+				return -EOPNOTSUPP;
+		}
+	}
+	return 0;
+}
+
+int drbd_nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+			  const struct nla_policy *policy)
+{
+	int err;
+
+	err = drbd_nla_check_mandatory(maxtype, nla);
+	if (!err)
+		err = nla_parse_nested(tb, maxtype, nla, policy);
+
+	return err;
+}
+
+struct nlattr *drbd_nla_find_nested(int maxtype, struct nlattr *nla, int attrtype)
+{
+	int err;
+	/*
+	 * If any nested attribute has the DRBD_GENLA_F_MANDATORY flag set and
+	 * we don't know about that attribute, reject all the nested
+	 * attributes.
+	 */
+	err = drbd_nla_check_mandatory(maxtype, nla);
+	if (err)
+		return ERR_PTR(err);
+	return nla_find_nested(nla, attrtype);
+}
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 47ef324b69db..0c2102c05384 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -96,7 +96,7 @@ GENL_struct(DRBD_NLA_CFG_REPLY, 1, drbd_cfg_reply,
  * and the volume id within the resource. */
 GENL_struct(DRBD_NLA_CFG_CONTEXT, 2, drbd_cfg_context,
 	__u32_field(1, DRBD_GENLA_F_MANDATORY,	ctx_volume)
-	__str_field(2, DRBD_GENLA_F_MANDATORY,	ctx_conn_name, 128)
+	__str_field(2, DRBD_GENLA_F_MANDATORY,	ctx_resource_name, 128)
 )
 
 GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 357f2ad403b1..0b8a88e2e83e 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -142,43 +142,6 @@ static struct nlattr *nested_attr_tb[128];
 #define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); }))
 #endif
 
-static inline int drbd_nla_check_mandatory(int maxtype, struct nlattr *nla)
-{
-	struct nlattr *head = nla_data(nla);
-	int len = nla_len(nla);
-	int rem;
-
-	/*
-	 * validate_nla (called from nla_parse_nested) ignores attributes
-	 * beyond maxtype, and does not understand the DRBD_GENLA_F_MANDATORY flag.
-	 * In order to have it validate attributes with the DRBD_GENLA_F_MANDATORY
-	 * flag set also, check and remove that flag before calling
-	 * nla_parse_nested.
-	 */
-
-	nla_for_each_attr(nla, head, len, rem) {
-		if (nla->nla_type & DRBD_GENLA_F_MANDATORY) {
-			nla->nla_type &= ~DRBD_GENLA_F_MANDATORY;
-			if (nla_type(nla) > maxtype)
-				return -EOPNOTSUPP;
-		}
-	}
-	return 0;
-}
-
-static inline int drbd_nla_parse_nested(struct nlattr *tb[], int maxtype,
-					struct nlattr *nla,
-					const struct nla_policy *policy)
-{
-	int err;
-
-	err = drbd_nla_check_mandatory(maxtype, nla);
-	if (!err)
-		err = nla_parse_nested(tb, maxtype, nla, policy);
-
-	return err;
-}
-
 #undef GENL_struct
 #define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
 /* *_from_attrs functions are static, but potentially unused */		\
-- 
cgit v1.2.3-55-g7522


From 089c075d88ac9407b8d7c5c8fc4b21c0d940bd82 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Tue, 14 Jun 2011 18:28:09 +0200
Subject: drbd: Convert the generic netlink interface to accept connection
 endpoints

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h      |   7 ++
 drivers/block/drbd/drbd_main.c     |  21 +++++
 drivers/block/drbd/drbd_nl.c       | 158 ++++++++++++++++++++++---------------
 drivers/block/drbd/drbd_receiver.c |  21 +++--
 drivers/block/drbd/drbd_state.c    |   2 +
 include/linux/drbd_genl.h          |  62 +++++++--------
 6 files changed, 164 insertions(+), 107 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index c3019730a24f..6d6d1056d824 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -836,6 +836,11 @@ struct drbd_tconn {			/* is a resource from the config file */
 	wait_queue_head_t ping_wait;	/* Woken upon reception of a ping, and a state change */
 	struct res_opts res_opts;
 
+	struct sockaddr_storage my_addr;
+	int my_addr_len;
+	struct sockaddr_storage peer_addr;
+	int peer_addr_len;
+
 	struct drbd_socket data;	/* data/barrier/cstate/parameter packets */
 	struct drbd_socket meta;	/* ping/ack (metadata) packets */
 	int agreed_pro_version;		/* actually used protocol version */
@@ -1377,6 +1382,8 @@ extern void drbd_minor_destroy(struct kref *kref);
 struct drbd_tconn *conn_create(const char *name);
 extern void conn_destroy(struct kref *kref);
 struct drbd_tconn *conn_get_by_name(const char *name);
+extern struct drbd_tconn *conn_get_by_addrs(void *my_addr, int my_addr_len,
+					    void *peer_addr, int peer_addr_len);
 extern void conn_free_crypto(struct drbd_tconn *tconn);
 
 extern int proc_details;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 178c711bc4af..79f275dc43a4 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2420,6 +2420,27 @@ found:
 	return tconn;
 }
 
+struct drbd_tconn *conn_get_by_addrs(void *my_addr, int my_addr_len,
+				     void *peer_addr, int peer_addr_len)
+{
+	struct drbd_tconn *tconn;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tconn, &drbd_tconns, all_tconn) {
+		if (tconn->my_addr_len == my_addr_len &&
+		    tconn->peer_addr_len == peer_addr_len &&
+		    !memcmp(&tconn->my_addr, my_addr, my_addr_len) &&
+		    !memcmp(&tconn->peer_addr, peer_addr, peer_addr_len)) {
+			kref_get(&tconn->kref);
+			goto found;
+		}
+	}
+	tconn = NULL;
+found:
+	rcu_read_unlock();
+	return tconn;
+}
+
 static int drbd_alloc_socket(struct drbd_socket *socket)
 {
 	socket->rbuf = (void *) __get_free_page(GFP_KERNEL);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 352be132b4be..e7933e04e7b8 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -94,6 +94,8 @@ static struct drbd_config_context {
 	/* pointer into the request skb,
 	 * limited lifetime! */
 	char *resource_name;
+	struct nlattr *my_addr;
+	struct nlattr *peer_addr;
 
 	/* reply buffer */
 	struct sk_buff *reply_skb;
@@ -142,6 +144,7 @@ int drbd_msg_put_info(const char *info)
  */
 #define DRBD_ADM_NEED_MINOR	1
 #define DRBD_ADM_NEED_RESOURCE	2
+#define DRBD_ADM_NEED_CONNECTION 4
 static int drbd_adm_prepare(struct sk_buff *skb, struct genl_info *info,
 		unsigned flags)
 {
@@ -174,6 +177,7 @@ static int drbd_adm_prepare(struct sk_buff *skb, struct genl_info *info,
 	adm_ctx.reply_dh->minor = d_in->minor;
 	adm_ctx.reply_dh->ret_code = NO_ERROR;
 
+	adm_ctx.volume = VOLUME_UNSPECIFIED;
 	if (info->attrs[DRBD_NLA_CFG_CONTEXT]) {
 		struct nlattr *nla;
 		/* parse and validate only */
@@ -191,12 +195,21 @@ static int drbd_adm_prepare(struct sk_buff *skb, struct genl_info *info,
 
 		/* and assign stuff to the global adm_ctx */
 		nla = nested_attr_tb[__nla_type(T_ctx_volume)];
-		adm_ctx.volume = nla ? nla_get_u32(nla) : VOLUME_UNSPECIFIED;
+		if (nla)
+			adm_ctx.volume = nla_get_u32(nla);
 		nla = nested_attr_tb[__nla_type(T_ctx_resource_name)];
 		if (nla)
 			adm_ctx.resource_name = nla_data(nla);
-	} else
-		adm_ctx.volume = VOLUME_UNSPECIFIED;
+		adm_ctx.my_addr = nested_attr_tb[__nla_type(T_ctx_my_addr)];
+		adm_ctx.peer_addr = nested_attr_tb[__nla_type(T_ctx_peer_addr)];
+		if ((adm_ctx.my_addr &&
+		     nla_len(adm_ctx.my_addr) > sizeof(adm_ctx.tconn->my_addr)) ||
+		    (adm_ctx.peer_addr &&
+		     nla_len(adm_ctx.peer_addr) > sizeof(adm_ctx.tconn->peer_addr))) {
+			err = -EINVAL;
+			goto fail;
+		}
+	}
 
 	adm_ctx.minor = d_in->minor;
 	adm_ctx.mdev = minor_to_mdev(d_in->minor);
@@ -211,6 +224,26 @@ static int drbd_adm_prepare(struct sk_buff *skb, struct genl_info *info,
 		return ERR_INVALID_REQUEST;
 	}
 
+	if (flags & DRBD_ADM_NEED_CONNECTION) {
+		if (adm_ctx.tconn && !(flags & DRBD_ADM_NEED_RESOURCE)) {
+			drbd_msg_put_info("no resource name expected");
+			return ERR_INVALID_REQUEST;
+		}
+		if (adm_ctx.mdev) {
+			drbd_msg_put_info("no minor number expected");
+			return ERR_INVALID_REQUEST;
+		}
+		if (adm_ctx.my_addr && adm_ctx.peer_addr)
+			adm_ctx.tconn = conn_get_by_addrs(nla_data(adm_ctx.my_addr),
+							  nla_len(adm_ctx.my_addr),
+							  nla_data(adm_ctx.peer_addr),
+							  nla_len(adm_ctx.peer_addr));
+		if (!adm_ctx.tconn) {
+			drbd_msg_put_info("unknown connection");
+			return ERR_INVALID_REQUEST;
+		}
+	}
+
 	/* some more paranoia, if the request was over-determined */
 	if (adm_ctx.mdev && adm_ctx.tconn &&
 	    adm_ctx.mdev->tconn != adm_ctx.tconn) {
@@ -268,30 +301,28 @@ static int drbd_adm_finish(struct genl_info *info, int retcode)
 static void setup_khelper_env(struct drbd_tconn *tconn, char **envp)
 {
 	char *afs;
-	struct net_conf *nc;
 
-	rcu_read_lock();
-	nc = rcu_dereference(tconn->net_conf);
-	if (nc) {
-		switch (((struct sockaddr *)nc->peer_addr)->sa_family) {
-		case AF_INET6:
-			afs = "ipv6";
-			snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI6",
-				 &((struct sockaddr_in6 *)nc->peer_addr)->sin6_addr);
-			break;
-		case AF_INET:
-			afs = "ipv4";
-			snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI4",
-				 &((struct sockaddr_in *)nc->peer_addr)->sin_addr);
-			break;
-		default:
-			afs = "ssocks";
-			snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI4",
-				 &((struct sockaddr_in *)nc->peer_addr)->sin_addr);
-		}
-		snprintf(envp[3], 20, "DRBD_PEER_AF=%s", afs);
+	/* FIXME: A future version will not allow this case. */
+	if (tconn->my_addr_len == 0 || tconn->peer_addr_len == 0)
+		return;
+
+	switch (((struct sockaddr *)&tconn->peer_addr)->sa_family) {
+	case AF_INET6:
+		afs = "ipv6";
+		snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI6",
+			 &((struct sockaddr_in6 *)&tconn->peer_addr)->sin6_addr);
+		break;
+	case AF_INET:
+		afs = "ipv4";
+		snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI4",
+			 &((struct sockaddr_in *)&tconn->peer_addr)->sin_addr);
+		break;
+	default:
+		afs = "ssocks";
+		snprintf(envp[4], 60, "DRBD_PEER_ADDRESS=%pI4",
+			 &((struct sockaddr_in *)&tconn->peer_addr)->sin_addr);
 	}
-	rcu_read_unlock();
+	snprintf(envp[3], 20, "DRBD_PEER_AF=%s", afs);
 }
 
 int drbd_khelper(struct drbd_conf *mdev, char *cmd)
@@ -1874,7 +1905,7 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
 	int rsr; /* re-sync running */
 	struct crypto crypto = { };
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_RESOURCE);
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_CONNECTION);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -1986,18 +2017,39 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 	struct drbd_conf *mdev;
 	struct net_conf *old_conf, *new_conf = NULL;
 	struct crypto crypto = { };
-	struct drbd_tconn *oconn;
 	struct drbd_tconn *tconn;
-	struct sockaddr *new_my_addr, *new_peer_addr, *taken_addr;
 	enum drbd_ret_code retcode;
 	int i;
 	int err;
 
 	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_RESOURCE);
+
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto out;
+	if (!(adm_ctx.my_addr && adm_ctx.peer_addr)) {
+		drbd_msg_put_info("connection endpoint(s) missing");
+		retcode = ERR_INVALID_REQUEST;
+		goto out;
+	}
+
+	/* No need for _rcu here. All reconfiguration is
+	 * strictly serialized on genl_lock(). We are protected against
+	 * concurrent reconfiguration/addition/deletion */
+	list_for_each_entry(tconn, &drbd_tconns, all_tconn) {
+		if (nla_len(adm_ctx.my_addr) == tconn->my_addr_len &&
+		    !memcmp(nla_data(adm_ctx.my_addr), &tconn->my_addr, tconn->my_addr_len)) {
+			retcode = ERR_LOCAL_ADDR;
+			goto out;
+		}
+
+		if (nla_len(adm_ctx.peer_addr) == tconn->peer_addr_len &&
+		    !memcmp(nla_data(adm_ctx.peer_addr), &tconn->peer_addr, tconn->peer_addr_len)) {
+			retcode = ERR_PEER_ADDR;
+			goto out;
+		}
+	}
 
 	tconn = adm_ctx.tconn;
 	conn_reconfig_start(tconn);
@@ -2027,37 +2079,6 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto fail;
 
-	retcode = NO_ERROR;
-
-	new_my_addr = (struct sockaddr *)&new_conf->my_addr;
-	new_peer_addr = (struct sockaddr *)&new_conf->peer_addr;
-
-	/* No need for _rcu here. All reconfiguration is
-	 * strictly serialized on genl_lock(). We are protected against
-	 * concurrent reconfiguration/addition/deletion */
-	list_for_each_entry(oconn, &drbd_tconns, all_tconn) {
-		struct net_conf *nc;
-		if (oconn == tconn)
-			continue;
-
-		rcu_read_lock();
-		nc = rcu_dereference(oconn->net_conf);
-		if (nc) {
-			taken_addr = (struct sockaddr *)&nc->my_addr;
-			if (new_conf->my_addr_len == nc->my_addr_len &&
-			    !memcmp(new_my_addr, taken_addr, new_conf->my_addr_len))
-				retcode = ERR_LOCAL_ADDR;
-
-			taken_addr = (struct sockaddr *)&nc->peer_addr;
-			if (new_conf->peer_addr_len == nc->peer_addr_len &&
-			    !memcmp(new_peer_addr, taken_addr, new_conf->peer_addr_len))
-				retcode = ERR_PEER_ADDR;
-		}
-		rcu_read_unlock();
-		if (retcode != NO_ERROR)
-			goto fail;
-	}
-
 	retcode = alloc_crypto(&crypto, new_conf);
 	if (retcode != NO_ERROR)
 		goto fail;
@@ -2083,6 +2104,11 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 	tconn->csums_tfm = crypto.csums_tfm;
 	tconn->verify_tfm = crypto.verify_tfm;
 
+	tconn->my_addr_len = nla_len(adm_ctx.my_addr);
+	memcpy(&tconn->my_addr, nla_data(adm_ctx.my_addr), tconn->my_addr_len);
+	tconn->peer_addr_len = nla_len(adm_ctx.peer_addr);
+	memcpy(&tconn->peer_addr, nla_data(adm_ctx.peer_addr), tconn->peer_addr_len);
+
 	mutex_unlock(&tconn->conf_update);
 
 	rcu_read_lock();
@@ -2170,7 +2196,7 @@ int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info)
 	enum drbd_ret_code retcode;
 	int err;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_RESOURCE);
+	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_CONNECTION);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -2529,7 +2555,7 @@ int drbd_adm_outdate(struct sk_buff *skb, struct genl_info *info)
 	return drbd_adm_simple_request_state(skb, info, NS(disk, D_OUTDATED));
 }
 
-int nla_put_drbd_cfg_context(struct sk_buff *skb, const char *resource_name, unsigned vnr)
+int nla_put_drbd_cfg_context(struct sk_buff *skb, struct drbd_tconn *tconn, unsigned vnr)
 {
 	struct nlattr *nla;
 	nla = nla_nest_start(skb, DRBD_NLA_CFG_CONTEXT);
@@ -2537,7 +2563,11 @@ int nla_put_drbd_cfg_context(struct sk_buff *skb, const char *resource_name, uns
 		goto nla_put_failure;
 	if (vnr != VOLUME_UNSPECIFIED)
 		NLA_PUT_U32(skb, T_ctx_volume, vnr);
-	NLA_PUT_STRING(skb, T_ctx_resource_name, resource_name);
+	NLA_PUT_STRING(skb, T_ctx_resource_name, tconn->name);
+	if (tconn->my_addr_len)
+		NLA_PUT(skb, T_ctx_my_addr, tconn->my_addr_len, &tconn->my_addr);
+	if (tconn->peer_addr_len)
+		NLA_PUT(skb, T_ctx_peer_addr, tconn->peer_addr_len, &tconn->peer_addr);
 	nla_nest_end(skb, nla);
 	return 0;
 
@@ -2574,7 +2604,7 @@ int nla_put_status_info(struct sk_buff *skb, struct drbd_conf *mdev,
 
 	/* We need to add connection name and volume number information still.
 	 * Minor number is in drbd_genlmsghdr. */
-	if (nla_put_drbd_cfg_context(skb, mdev->tconn->name, mdev->vnr))
+	if (nla_put_drbd_cfg_context(skb, mdev->tconn, mdev->vnr))
 		goto nla_put_failure;
 
 	if (res_opts_to_skb(skb, &mdev->tconn->res_opts, exclude_sensitive))
@@ -2736,7 +2766,7 @@ next_tconn:
 			/* this is a tconn without a single volume */
 			dh->minor = -1U;
 			dh->ret_code = NO_ERROR;
-			if (nla_put_drbd_cfg_context(skb, tconn->name, VOLUME_UNSPECIFIED))
+			if (nla_put_drbd_cfg_context(skb, tconn, VOLUME_UNSPECIFIED))
 				genlmsg_cancel(skb, dh);
 			else
 				genlmsg_end(skb, dh);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 4ba097293278..ab1d36cb6214 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -626,23 +626,21 @@ static struct socket *drbd_try_connect(struct drbd_tconn *tconn)
 		rcu_read_unlock();
 		return NULL;
 	}
-
 	sndbuf_size = nc->sndbuf_size;
 	rcvbuf_size = nc->rcvbuf_size;
 	connect_int = nc->connect_int;
+	rcu_read_unlock();
 
-	my_addr_len = min_t(int, nc->my_addr_len, sizeof(src_in6));
-	memcpy(&src_in6, nc->my_addr, my_addr_len);
+	my_addr_len = min_t(int, tconn->my_addr_len, sizeof(src_in6));
+	memcpy(&src_in6, &tconn->my_addr, my_addr_len);
 
-	if (((struct sockaddr *)nc->my_addr)->sa_family == AF_INET6)
+	if (((struct sockaddr *)&tconn->my_addr)->sa_family == AF_INET6)
 		src_in6.sin6_port = 0;
 	else
 		((struct sockaddr_in *)&src_in6)->sin_port = 0; /* AF_INET & AF_SCI */
 
-	peer_addr_len = min_t(int, nc->peer_addr_len, sizeof(src_in6));
-	memcpy(&peer_in6, nc->peer_addr, peer_addr_len);
-
-	rcu_read_unlock();
+	peer_addr_len = min_t(int, tconn->peer_addr_len, sizeof(src_in6));
+	memcpy(&peer_in6, &tconn->peer_addr, peer_addr_len);
 
 	what = "sock_create_kern";
 	err = sock_create_kern(((struct sockaddr *)&src_in6)->sa_family,
@@ -714,15 +712,14 @@ static struct socket *drbd_wait_for_connect(struct drbd_tconn *tconn)
 		rcu_read_unlock();
 		return NULL;
 	}
-
 	sndbuf_size = nc->sndbuf_size;
 	rcvbuf_size = nc->rcvbuf_size;
 	connect_int = nc->connect_int;
-
-	my_addr_len = min_t(int, nc->my_addr_len, sizeof(struct sockaddr_in6));
-	memcpy(&my_addr, nc->my_addr, my_addr_len);
 	rcu_read_unlock();
 
+	my_addr_len = min_t(int, tconn->my_addr_len, sizeof(struct sockaddr_in6));
+	memcpy(&my_addr, &tconn->my_addr, my_addr_len);
+
 	what = "sock_create_kern";
 	err = sock_create_kern(((struct sockaddr *)&my_addr)->sa_family,
 		SOCK_STREAM, IPPROTO_TCP, &s_listen);
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index cd55f46d5c55..d978e4d98a15 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1418,6 +1418,8 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused)
 
 		mutex_lock(&tconn->conf_update);
 		old_conf = tconn->net_conf;
+		tconn->my_addr_len = 0;
+		tconn->peer_addr_len = 0;
 		rcu_assign_pointer(tconn->net_conf, NULL);
 		conn_free_crypto(tconn);
 		mutex_unlock(&tconn->conf_update);
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 0c2102c05384..b93db6c83882 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -97,6 +97,8 @@ GENL_struct(DRBD_NLA_CFG_REPLY, 1, drbd_cfg_reply,
 GENL_struct(DRBD_NLA_CFG_CONTEXT, 2, drbd_cfg_context,
 	__u32_field(1, DRBD_GENLA_F_MANDATORY,	ctx_volume)
 	__str_field(2, DRBD_GENLA_F_MANDATORY,	ctx_resource_name, 128)
+	__bin_field(3, DRBD_GENLA_F_MANDATORY,	ctx_my_addr, 128)
+	__bin_field(4, DRBD_GENLA_F_MANDATORY,	ctx_peer_addr, 128)
 )
 
 GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
@@ -134,38 +136,36 @@ GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
 )
 
 GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
-	__bin_field(1,	DRBD_F_REQUIRED | DRBD_F_INVARIANT,	my_addr,	128)
-	__bin_field(2,	DRBD_F_REQUIRED | DRBD_F_INVARIANT,	peer_addr,	128)
-	__str_field_def(3,	DRBD_GENLA_F_MANDATORY | DRBD_F_SENSITIVE,
+	__str_field_def(1,	DRBD_GENLA_F_MANDATORY | DRBD_F_SENSITIVE,
 						shared_secret,	SHARED_SECRET_MAX)
-	__str_field_def(4,	DRBD_GENLA_F_MANDATORY,	cram_hmac_alg,	SHARED_SECRET_MAX)
-	__str_field_def(5,	DRBD_GENLA_F_MANDATORY,	integrity_alg,	SHARED_SECRET_MAX)
-	__str_field_def(6,	DRBD_GENLA_F_MANDATORY,	verify_alg,     SHARED_SECRET_MAX)
-	__str_field_def(7,	DRBD_GENLA_F_MANDATORY,	csums_alg,	SHARED_SECRET_MAX)
-	__u32_field_def(8,	DRBD_GENLA_F_MANDATORY,	wire_protocol, DRBD_PROTOCOL_DEF)
-	__u32_field_def(9,	DRBD_GENLA_F_MANDATORY,	connect_int, DRBD_CONNECT_INT_DEF)
-	__u32_field_def(10,	DRBD_GENLA_F_MANDATORY,	timeout, DRBD_TIMEOUT_DEF)
-	__u32_field_def(11,	DRBD_GENLA_F_MANDATORY,	ping_int, DRBD_PING_INT_DEF)
-	__u32_field_def(12,	DRBD_GENLA_F_MANDATORY,	ping_timeo, DRBD_PING_TIMEO_DEF)
-	__u32_field_def(13,	DRBD_GENLA_F_MANDATORY,	sndbuf_size, DRBD_SNDBUF_SIZE_DEF)
-	__u32_field_def(14,	DRBD_GENLA_F_MANDATORY,	rcvbuf_size, DRBD_RCVBUF_SIZE_DEF)
-	__u32_field_def(15,	DRBD_GENLA_F_MANDATORY,	ko_count, DRBD_KO_COUNT_DEF)
-	__u32_field_def(16,	DRBD_GENLA_F_MANDATORY,	max_buffers, DRBD_MAX_BUFFERS_DEF)
-	__u32_field_def(17,	DRBD_GENLA_F_MANDATORY,	max_epoch_size, DRBD_MAX_EPOCH_SIZE_DEF)
-	__u32_field_def(18,	DRBD_GENLA_F_MANDATORY,	unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF)
-	__u32_field_def(19,	DRBD_GENLA_F_MANDATORY,	after_sb_0p, DRBD_AFTER_SB_0P_DEF)
-	__u32_field_def(20,	DRBD_GENLA_F_MANDATORY,	after_sb_1p, DRBD_AFTER_SB_1P_DEF)
-	__u32_field_def(21,	DRBD_GENLA_F_MANDATORY,	after_sb_2p, DRBD_AFTER_SB_2P_DEF)
-	__u32_field_def(22,	DRBD_GENLA_F_MANDATORY,	rr_conflict, DRBD_RR_CONFLICT_DEF)
-	__u32_field_def(23,	DRBD_GENLA_F_MANDATORY,	on_congestion, DRBD_ON_CONGESTION_DEF)
-	__u32_field_def(24,	DRBD_GENLA_F_MANDATORY,	cong_fill, DRBD_CONG_FILL_DEF)
-	__u32_field_def(25,	DRBD_GENLA_F_MANDATORY,	cong_extents, DRBD_CONG_EXTENTS_DEF)
-	__flg_field_def(26, DRBD_GENLA_F_MANDATORY,	two_primaries, DRBD_ALLOW_TWO_PRIMARIES_DEF)
-	__flg_field(27, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	discard_my_data)
-	__flg_field_def(28, DRBD_GENLA_F_MANDATORY,	tcp_cork, DRBD_TCP_CORK_DEF)
-	__flg_field_def(29, DRBD_GENLA_F_MANDATORY,	always_asbp, DRBD_ALWAYS_ASBP_DEF)
-	__flg_field(30, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	dry_run)
-	__flg_field_def(31,	DRBD_GENLA_F_MANDATORY,	use_rle, DRBD_USE_RLE_DEF)
+	__str_field_def(2,	DRBD_GENLA_F_MANDATORY,	cram_hmac_alg,	SHARED_SECRET_MAX)
+	__str_field_def(3,	DRBD_GENLA_F_MANDATORY,	integrity_alg,	SHARED_SECRET_MAX)
+	__str_field_def(4,	DRBD_GENLA_F_MANDATORY,	verify_alg,     SHARED_SECRET_MAX)
+	__str_field_def(5,	DRBD_GENLA_F_MANDATORY,	csums_alg,	SHARED_SECRET_MAX)
+	__u32_field_def(6,	DRBD_GENLA_F_MANDATORY,	wire_protocol, DRBD_PROTOCOL_DEF)
+	__u32_field_def(7,	DRBD_GENLA_F_MANDATORY,	connect_int, DRBD_CONNECT_INT_DEF)
+	__u32_field_def(8,	DRBD_GENLA_F_MANDATORY,	timeout, DRBD_TIMEOUT_DEF)
+	__u32_field_def(9,	DRBD_GENLA_F_MANDATORY,	ping_int, DRBD_PING_INT_DEF)
+	__u32_field_def(10,	DRBD_GENLA_F_MANDATORY,	ping_timeo, DRBD_PING_TIMEO_DEF)
+	__u32_field_def(11,	DRBD_GENLA_F_MANDATORY,	sndbuf_size, DRBD_SNDBUF_SIZE_DEF)
+	__u32_field_def(12,	DRBD_GENLA_F_MANDATORY,	rcvbuf_size, DRBD_RCVBUF_SIZE_DEF)
+	__u32_field_def(13,	DRBD_GENLA_F_MANDATORY,	ko_count, DRBD_KO_COUNT_DEF)
+	__u32_field_def(14,	DRBD_GENLA_F_MANDATORY,	max_buffers, DRBD_MAX_BUFFERS_DEF)
+	__u32_field_def(15,	DRBD_GENLA_F_MANDATORY,	max_epoch_size, DRBD_MAX_EPOCH_SIZE_DEF)
+	__u32_field_def(16,	DRBD_GENLA_F_MANDATORY,	unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF)
+	__u32_field_def(17,	DRBD_GENLA_F_MANDATORY,	after_sb_0p, DRBD_AFTER_SB_0P_DEF)
+	__u32_field_def(18,	DRBD_GENLA_F_MANDATORY,	after_sb_1p, DRBD_AFTER_SB_1P_DEF)
+	__u32_field_def(19,	DRBD_GENLA_F_MANDATORY,	after_sb_2p, DRBD_AFTER_SB_2P_DEF)
+	__u32_field_def(20,	DRBD_GENLA_F_MANDATORY,	rr_conflict, DRBD_RR_CONFLICT_DEF)
+	__u32_field_def(21,	DRBD_GENLA_F_MANDATORY,	on_congestion, DRBD_ON_CONGESTION_DEF)
+	__u32_field_def(22,	DRBD_GENLA_F_MANDATORY,	cong_fill, DRBD_CONG_FILL_DEF)
+	__u32_field_def(23,	DRBD_GENLA_F_MANDATORY,	cong_extents, DRBD_CONG_EXTENTS_DEF)
+	__flg_field_def(24, DRBD_GENLA_F_MANDATORY,	two_primaries, DRBD_ALLOW_TWO_PRIMARIES_DEF)
+	__flg_field(25, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	discard_my_data)
+	__flg_field_def(26, DRBD_GENLA_F_MANDATORY,	tcp_cork, DRBD_TCP_CORK_DEF)
+	__flg_field_def(27, DRBD_GENLA_F_MANDATORY,	always_asbp, DRBD_ALWAYS_ASBP_DEF)
+	__flg_field(28, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	dry_run)
+	__flg_field_def(29,	DRBD_GENLA_F_MANDATORY,	use_rle, DRBD_USE_RLE_DEF)
 )
 
 GENL_struct(DRBD_NLA_SET_ROLE_PARMS, 6, set_role_parms,
-- 
cgit v1.2.3-55-g7522


From 6dff2902208364d058746ee794da4d960f6eec6f Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Tue, 28 Jun 2011 14:18:12 +0200
Subject: drbd: Rename --dry-run to --tentative

drbdadm already has a --dry-run option, so this option cannot directly be
passed through to drbdsetup.  Rename the drbdsetup option to resolve this
conflict.

For backward compatibility, make --dry-run an alias of --tentative.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_main.c     | 4 ++--
 drivers/block/drbd/drbd_receiver.c | 6 +++---
 include/linux/drbd_genl.h          | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 933d4767c110..72b1dfa4b656 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -926,7 +926,7 @@ int __drbd_send_protocol(struct drbd_tconn *tconn, enum drbd_packet cmd)
 	rcu_read_lock();
 	nc = rcu_dereference(tconn->net_conf);
 
-	if (nc->dry_run && tconn->agreed_pro_version < 92) {
+	if (nc->tentative && tconn->agreed_pro_version < 92) {
 		rcu_read_unlock();
 		mutex_unlock(&sock->mutex);
 		conn_err(tconn, "--dry-run is not supported by peer");
@@ -945,7 +945,7 @@ int __drbd_send_protocol(struct drbd_tconn *tconn, enum drbd_packet cmd)
 	cf = 0;
 	if (nc->discard_my_data)
 		cf |= CF_DISCARD_MY_DATA;
-	if (nc->dry_run)
+	if (nc->tentative)
 		cf |= CF_DRY_RUN;
 	p->conn_flags    = cpu_to_be32(cf);
 
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index ab1d36cb6214..d55a3cb21c31 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2836,7 +2836,7 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_conf *mdev, enum drbd_rol
 	enum drbd_conns rv = C_MASK;
 	enum drbd_disk_state mydisk;
 	struct net_conf *nc;
-	int hg, rule_nr, rr_conflict, dry_run;
+	int hg, rule_nr, rr_conflict, tentative;
 
 	mydisk = mdev->state.disk;
 	if (mydisk == D_NEGOTIATING)
@@ -2916,7 +2916,7 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_conf *mdev, enum drbd_rol
 			     (hg < 0) ? "peer" : "this");
 	}
 	rr_conflict = nc->rr_conflict;
-	dry_run = nc->dry_run;
+	tentative = nc->tentative;
 	rcu_read_unlock();
 
 	if (hg == -100) {
@@ -2949,7 +2949,7 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_conf *mdev, enum drbd_rol
 		}
 	}
 
-	if (dry_run || test_bit(CONN_DRY_RUN, &mdev->tconn->flags)) {
+	if (tentative || test_bit(CONN_DRY_RUN, &mdev->tconn->flags)) {
 		if (hg == 0)
 			dev_info(DEV, "dry-run connect: No resync, would become Connected immediately.\n");
 		else
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index b93db6c83882..e879a9324380 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -164,7 +164,7 @@ GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
 	__flg_field(25, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	discard_my_data)
 	__flg_field_def(26, DRBD_GENLA_F_MANDATORY,	tcp_cork, DRBD_TCP_CORK_DEF)
 	__flg_field_def(27, DRBD_GENLA_F_MANDATORY,	always_asbp, DRBD_ALWAYS_ASBP_DEF)
-	__flg_field(28, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	dry_run)
+	__flg_field(28, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	tentative)
 	__flg_field_def(29,	DRBD_GENLA_F_MANDATORY,	use_rle, DRBD_USE_RLE_DEF)
 )
 
-- 
cgit v1.2.3-55-g7522


From f03c254961cce65ee2b21c4beccb6975b6f9d308 Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Mon, 20 Jun 2011 22:21:19 +0200
Subject: drbd: allow ping-timeout of up to 30 seconds

Allow up to 300 centi-seconds to be configured for the "ping timeout".
There may be setups where heavy congestion, huge buffers, and asymmetric
bandwidth limitations may need a "huge" ping-timeout as work-around
for "spurious connection loss" problems.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_limits.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 3627f760966e..82db83410f08 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -62,7 +62,7 @@
 
  /* timeout for the ping packets.*/
 #define DRBD_PING_TIMEO_MIN  1
-#define DRBD_PING_TIMEO_MAX  100
+#define DRBD_PING_TIMEO_MAX  300
 #define DRBD_PING_TIMEO_DEF  5
 
   /* max number of write requests between write barriers */
-- 
cgit v1.2.3-55-g7522


From d942ae44537669418a7cbfd916531d30513dbca8 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Tue, 31 May 2011 13:07:24 +0200
Subject: drbd: Fixes from the 8.3 development branch

 * commit 'ae57a0a':
   drbd: Only print sanitize state's warnings, if the state change happens
   drbd: we should write meta data updates with FLUSH FUA
   drbd: fix limit define, we support 1 PiByte now
   drbd: fix log message argument order
   drbd: Typo in user-visible message.
   drbd: Make "(rcv|snd)buf-size" and "ping-timeout" available for the proxy, too.
   drbd: Allow keywords to be used in multiple config sections.
   drbd: fix typos in comments.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h   | 10 ++++----
 drivers/block/drbd/drbd_state.c | 56 ++++++++++++++++++++++++++++++-----------
 include/linux/drbd_limits.h     |  2 +-
 3 files changed, 47 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index de42c7cf7caf..1d71b3a3586a 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -372,11 +372,11 @@ struct p_connection_features {
 	u32 protocol_max;
 
 	/* should be more than enough for future enhancements
-	 * for now, feature_flags and the reserverd array shall be zero.
+	 * for now, feature_flags and the reserved array shall be zero.
 	 */
 
 	u32 _pad;
-	u64 reserverd[7];
+	u64 reserved[7];
 } __packed;
 
 struct p_barrier {
@@ -914,7 +914,7 @@ struct drbd_conf {
 	atomic_t ap_bio_cnt;	 /* Requests we need to complete */
 	atomic_t ap_pending_cnt; /* AP data packets on the wire, ack expected */
 	atomic_t rs_pending_cnt; /* RS request/data packets on the wire */
-	atomic_t unacked_cnt;	 /* Need to send replys for */
+	atomic_t unacked_cnt;	 /* Need to send replies for */
 	atomic_t local_cnt;	 /* Waiting for local completion */
 
 	/* Interval tree of pending local requests */
@@ -2153,7 +2153,7 @@ static inline int drbd_state_is_stable(struct drbd_conf *mdev)
 		/* disk state is stable as well. */
 		break;
 
-	/* no new io accepted during tansitional states */
+	/* no new io accepted during transitional states */
 	case D_ATTACHING:
 	case D_FAILED:
 	case D_NEGOTIATING:
@@ -2217,7 +2217,7 @@ static inline void inc_ap_bio(struct drbd_conf *mdev)
 	/* we wait here
 	 *    as long as the device is suspended
 	 *    until the bitmap is no longer on the fly during connection
-	 *    handshake as long as we would exeed the max_buffer limit.
+	 *    handshake as long as we would exceed the max_buffer limit.
 	 *
 	 * to avoid races with the reconnect code,
 	 * we need to atomic_inc within the spinlock. */
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 8c9d0348736d..2cf69b25f1e7 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -37,6 +37,15 @@ struct after_state_chg_work {
 	struct completion *done;
 };
 
+enum sanitize_state_warnings {
+	NO_WARNING,
+	ABORTED_ONLINE_VERIFY,
+	ABORTED_RESYNC,
+	CONNECTION_LOST_NEGOTIATING,
+	IMPLICITLY_UPGRADED_DISK,
+	IMPLICITLY_UPGRADED_PDSK,
+};
+
 static int w_after_state_ch(struct drbd_work *w, int unused);
 static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 			   union drbd_state ns, enum chg_state_flags flags);
@@ -44,7 +53,7 @@ static enum drbd_state_rv is_valid_state(struct drbd_conf *, union drbd_state);
 static enum drbd_state_rv is_valid_soft_transition(union drbd_state, union drbd_state);
 static enum drbd_state_rv is_valid_transition(union drbd_state os, union drbd_state ns);
 static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state ns,
-				       const char **warn_sync_abort);
+				       enum sanitize_state_warnings *warn);
 
 static inline bool is_susp(union drbd_state s)
 {
@@ -656,6 +665,21 @@ is_valid_transition(union drbd_state os, union drbd_state ns)
 	return rv;
 }
 
+static void print_sanitize_warnings(struct drbd_conf *mdev, enum sanitize_state_warnings warn)
+{
+	static const char *msg_table[] = {
+		[NO_WARNING] = "",
+		[ABORTED_ONLINE_VERIFY] = "Online-verify aborted.",
+		[ABORTED_RESYNC] = "Resync aborted.",
+		[CONNECTION_LOST_NEGOTIATING] = "Connection lost while negotiating, no data!",
+		[IMPLICITLY_UPGRADED_DISK] = "Implicitly upgraded disk",
+		[IMPLICITLY_UPGRADED_PDSK] = "Implicitly upgraded pdsk",
+	};
+
+	if (warn != NO_WARNING)
+		dev_warn(DEV, "%s\n", msg_table[warn]);
+}
+
 /**
  * sanitize_state() - Resolves implicitly necessary additional changes to a state transition
  * @mdev:	DRBD device.
@@ -667,11 +691,14 @@ is_valid_transition(union drbd_state os, union drbd_state ns)
  * to D_UNKNOWN. This rule and many more along those lines are in this function.
  */
 static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state ns,
-				       const char **warn_sync_abort)
+				       enum sanitize_state_warnings *warn)
 {
 	enum drbd_fencing_p fp;
 	enum drbd_disk_state disk_min, disk_max, pdsk_min, pdsk_max;
 
+	if (warn)
+		*warn = NO_WARNING;
+
 	fp = FP_DONT_CARE;
 	if (get_ldev(mdev)) {
 		rcu_read_lock();
@@ -695,10 +722,9 @@ static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state
 	/* An implication of the disk states onto the connection state */
 	/* Abort resync if a disk fails/detaches */
 	if (ns.conn > C_CONNECTED && (ns.disk <= D_FAILED || ns.pdsk <= D_FAILED)) {
-		if (warn_sync_abort)
-			*warn_sync_abort =
-				ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T ?
-				"Online-verify" : "Resync";
+		if (warn)
+			*warn = ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T ?
+				ABORTED_ONLINE_VERIFY : ABORTED_RESYNC;
 		ns.conn = C_CONNECTED;
 	}
 
@@ -709,7 +735,8 @@ static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state
 			ns.disk = mdev->new_state_tmp.disk;
 			ns.pdsk = mdev->new_state_tmp.pdsk;
 		} else {
-			dev_alert(DEV, "Connection lost while negotiating, no data!\n");
+			if (warn)
+				*warn = CONNECTION_LOST_NEGOTIATING;
 			ns.disk = D_DISKLESS;
 			ns.pdsk = D_UNKNOWN;
 		}
@@ -791,16 +818,16 @@ static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state
 		ns.disk = disk_max;
 
 	if (ns.disk < disk_min) {
-		dev_warn(DEV, "Implicitly set disk from %s to %s\n",
-			 drbd_disk_str(ns.disk), drbd_disk_str(disk_min));
+		if (warn)
+			*warn = IMPLICITLY_UPGRADED_DISK;
 		ns.disk = disk_min;
 	}
 	if (ns.pdsk > pdsk_max)
 		ns.pdsk = pdsk_max;
 
 	if (ns.pdsk < pdsk_min) {
-		dev_warn(DEV, "Implicitly set pdsk from %s to %s\n",
-			 drbd_disk_str(ns.pdsk), drbd_disk_str(pdsk_min));
+		if (warn)
+			*warn = IMPLICITLY_UPGRADED_PDSK;
 		ns.pdsk = pdsk_min;
 	}
 
@@ -875,12 +902,12 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
 {
 	union drbd_state os;
 	enum drbd_state_rv rv = SS_SUCCESS;
-	const char *warn_sync_abort = NULL;
+	enum sanitize_state_warnings ssw;
 	struct after_state_chg_work *ascw;
 
 	os = drbd_read_state(mdev);
 
-	ns = sanitize_state(mdev, ns, &warn_sync_abort);
+	ns = sanitize_state(mdev, ns, &ssw);
 	if (ns.i == os.i)
 		return SS_NOTHING_TO_DO;
 
@@ -909,8 +936,7 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
 		return rv;
 	}
 
-	if (warn_sync_abort)
-		dev_warn(DEV, "%s aborted.\n", warn_sync_abort);
+	print_sanitize_warnings(mdev, ssw);
 
 	drbd_pr_state_change(mdev, os, ns, flags);
 
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 82db83410f08..f1046b13d9f6 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -126,7 +126,7 @@
  * is 1 PiB, currently. */
 /* DRBD_MAX_SECTORS */
 #define DRBD_DISK_SIZE_MIN  0
-#define DRBD_DISK_SIZE_MAX  (16 * (2LLU << 30))
+#define DRBD_DISK_SIZE_MAX  (1 * (2LLU << 40))
 #define DRBD_DISK_SIZE_DEF  0 /* = disabled = no user size... */
 #define DRBD_DISK_SIZE_SCALE 's'  /* sectors */
 
-- 
cgit v1.2.3-55-g7522


From cdfda633d235028e9b27381dedb65416409e8729 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Tue, 5 Jul 2011 15:38:59 +0200
Subject: drbd: detach from frozen backing device

* drbd-8.3:
  documentation: Documented detach's --force and disk's --disk-timeout
  drbd: Implemented the disk-timeout option
  drbd: Force flag for the detach operation
  drbd: Allow new IOs while the local disk in in FAILED state
  drbd: Bitmap IO functions can not return prematurely if the disk breaks
  drbd: Added a kref to bm_aio_ctx
  drbd: Hold a reference to ldev while doing meta-data IO
  drbd: Keep a reference to the bio until the completion handler finished
  drbd: Implemented wait_until_done_or_disk_failure()
  drbd: Replaced md_io_mutex by an atomic: md_io_in_use
  drbd: moved md_io into mdev
  drbd: Immediately allow completion of IOs, that wait for IO completions on a failed disk
  drbd: Keep a reference to barrier acked requests

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_actlog.c   |  75 ++++++++++++++++++------
 drivers/block/drbd/drbd_bitmap.c   | 115 +++++++++++++++++++++++++++----------
 drivers/block/drbd/drbd_int.h      |  12 ++--
 drivers/block/drbd/drbd_main.c     |  77 ++++++++++++++++++++++---
 drivers/block/drbd/drbd_nl.c       |  28 ++++++++-
 drivers/block/drbd/drbd_receiver.c |   2 -
 drivers/block/drbd/drbd_req.c      |  52 +++++++++++------
 drivers/block/drbd/drbd_req.h      |  19 +++---
 drivers/block/drbd/drbd_state.c    |   7 +++
 drivers/block/drbd/drbd_worker.c   |   9 ++-
 include/linux/drbd_genl.h          |   9 ++-
 include/linux/drbd_limits.h        |   6 ++
 12 files changed, 321 insertions(+), 90 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index aeb483daea06..58b5b61628fc 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -114,18 +114,44 @@ struct drbd_atodb_wait {
 
 static int w_al_write_transaction(struct drbd_work *, int);
 
+void *drbd_md_get_buffer(struct drbd_conf *mdev)
+{
+	int r;
+
+	wait_event(mdev->misc_wait,
+		   (r = atomic_cmpxchg(&mdev->md_io_in_use, 0, 1)) == 0 ||
+		   mdev->state.disk <= D_FAILED);
+
+	return r ? NULL : page_address(mdev->md_io_page);
+}
+
+void drbd_md_put_buffer(struct drbd_conf *mdev)
+{
+	if (atomic_dec_and_test(&mdev->md_io_in_use))
+		wake_up(&mdev->misc_wait);
+}
+
+static bool md_io_allowed(struct drbd_conf *mdev)
+{
+	enum drbd_disk_state ds = mdev->state.disk;
+	return ds >= D_NEGOTIATING || ds == D_ATTACHING;
+}
+
+void wait_until_done_or_disk_failure(struct drbd_conf *mdev, unsigned int *done)
+{
+	wait_event(mdev->misc_wait, *done || !md_io_allowed(mdev));
+}
+
 static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
 				 struct drbd_backing_dev *bdev,
 				 struct page *page, sector_t sector,
 				 int rw, int size)
 {
 	struct bio *bio;
-	struct drbd_md_io md_io;
 	int err;
 
-	md_io.mdev = mdev;
-	init_completion(&md_io.event);
-	md_io.error = 0;
+	mdev->md_io.done = 0;
+	mdev->md_io.error = -ENODEV;
 
 	if ((rw & WRITE) && !test_bit(MD_NO_FUA, &mdev->flags))
 		rw |= REQ_FUA | REQ_FLUSH;
@@ -137,17 +163,25 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
 	err = -EIO;
 	if (bio_add_page(bio, page, size, 0) != size)
 		goto out;
-	bio->bi_private = &md_io;
+	bio->bi_private = &mdev->md_io;
 	bio->bi_end_io = drbd_md_io_complete;
 	bio->bi_rw = rw;
 
+	if (!get_ldev_if_state(mdev, D_ATTACHING)) {  /* Corresponding put_ldev in drbd_md_io_complete() */
+		dev_err(DEV, "ASSERT FAILED: get_ldev_if_state() == 1 in _drbd_md_sync_page_io()\n");
+		err = -ENODEV;
+		goto out;
+	}
+
+	bio_get(bio); /* one bio_put() is in the completion handler */
+	atomic_inc(&mdev->md_io_in_use); /* drbd_md_put_buffer() is in the completion handler */
 	if (drbd_insert_fault(mdev, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
 		bio_endio(bio, -EIO);
 	else
 		submit_bio(rw, bio);
-	wait_for_completion(&md_io.event);
+	wait_until_done_or_disk_failure(mdev, &mdev->md_io.done);
 	if (bio_flagged(bio, BIO_UPTODATE))
-		err = md_io.error;
+		err = mdev->md_io.error;
 
  out:
 	bio_put(bio);
@@ -160,7 +194,7 @@ int drbd_md_sync_page_io(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
 	int err;
 	struct page *iop = mdev->md_io_page;
 
-	D_ASSERT(mutex_is_locked(&mdev->md_io_mutex));
+	D_ASSERT(atomic_read(&mdev->md_io_in_use) == 1);
 
 	BUG_ON(!bdev->md_bdev);
 
@@ -344,8 +378,14 @@ w_al_write_transaction(struct drbd_work *w, int unused)
 		return 0;
 	}
 
-	mutex_lock(&mdev->md_io_mutex); /* protects md_io_buffer, al_tr_cycle, ... */
-	buffer = page_address(mdev->md_io_page);
+	buffer = drbd_md_get_buffer(mdev); /* protects md_io_buffer, al_tr_cycle, ... */
+	if (!buffer) {
+		dev_err(DEV, "disk failed while waiting for md_io buffer\n");
+		aw->err = -EIO;
+		complete(&((struct update_al_work *)w)->event);
+		put_ldev(mdev);
+		return 1;
+	}
 
 	memset(buffer, 0, sizeof(*buffer));
 	buffer->magic = cpu_to_be32(DRBD_AL_MAGIC);
@@ -415,7 +455,7 @@ w_al_write_transaction(struct drbd_work *w, int unused)
 		mdev->al_tr_number++;
 	}
 
-	mutex_unlock(&mdev->md_io_mutex);
+	drbd_md_put_buffer(mdev);
 	complete(&((struct update_al_work *)w)->event);
 	put_ldev(mdev);
 
@@ -506,8 +546,9 @@ int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 	/* lock out all other meta data io for now,
 	 * and make sure the page is mapped.
 	 */
-	mutex_lock(&mdev->md_io_mutex);
-	b = page_address(mdev->md_io_page);
+	b = drbd_md_get_buffer(mdev);
+	if (!b)
+		return 0;
 
 	/* Always use the full ringbuffer space for now.
 	 * possible optimization: read in all of it,
@@ -528,7 +569,7 @@ int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 
 		/* IO error */
 		if (rv == -1) {
-			mutex_unlock(&mdev->md_io_mutex);
+			drbd_md_put_buffer(mdev);
 			return 0;
 		}
 
@@ -558,7 +599,7 @@ int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 	if (!found_valid) {
 		if (found_initialized != mx)
 			dev_warn(DEV, "No usable activity log found.\n");
-		mutex_unlock(&mdev->md_io_mutex);
+		drbd_md_put_buffer(mdev);
 		return 1;
 	}
 
@@ -573,7 +614,7 @@ int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 		if (!expect(rv != 0))
 			goto cancel;
 		if (rv == -1) {
-			mutex_unlock(&mdev->md_io_mutex);
+			drbd_md_put_buffer(mdev);
 			return 0;
 		}
 
@@ -643,7 +684,7 @@ cancel:
 	mdev->al_tr_pos = (to + 1) % (MD_AL_SECTORS*512/MD_BLOCK_SIZE);
 
 	/* ok, we are done with it */
-	mutex_unlock(&mdev->md_io_mutex);
+	drbd_md_put_buffer(mdev);
 
 	dev_info(DEV, "Found %d transactions (%d active extents) in activity log.\n",
 	     transactions, active_extents);
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 52c48143b22a..706e5220dd4a 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -918,13 +918,22 @@ void drbd_bm_clear_all(struct drbd_conf *mdev)
 struct bm_aio_ctx {
 	struct drbd_conf *mdev;
 	atomic_t in_flight;
-	struct completion done;
+	unsigned int done;
 	unsigned flags;
 #define BM_AIO_COPY_PAGES	1
 #define BM_AIO_WRITE_HINTED	2
 	int error;
+	struct kref kref;
 };
 
+static void bm_aio_ctx_destroy(struct kref *kref)
+{
+	struct bm_aio_ctx *ctx = container_of(kref, struct bm_aio_ctx, kref);
+
+	put_ldev(ctx->mdev);
+	kfree(ctx);
+}
+
 /* bv_page may be a copy, or may be the original */
 static void bm_async_io_complete(struct bio *bio, int error)
 {
@@ -968,13 +977,16 @@ static void bm_async_io_complete(struct bio *bio, int error)
 
 	bio_put(bio);
 
-	if (atomic_dec_and_test(&ctx->in_flight))
-		complete(&ctx->done);
+	if (atomic_dec_and_test(&ctx->in_flight)) {
+		ctx->done = 1;
+		wake_up(&mdev->misc_wait);
+		kref_put(&ctx->kref, &bm_aio_ctx_destroy);
+	}
 }
 
 static void bm_page_io_async(struct bm_aio_ctx *ctx, int page_nr, int rw) __must_hold(local)
 {
-	struct bio *bio = bio_alloc_drbd(GFP_KERNEL);
+	struct bio *bio = bio_alloc_drbd(GFP_NOIO);
 	struct drbd_conf *mdev = ctx->mdev;
 	struct drbd_bitmap *b = mdev->bitmap;
 	struct page *page;
@@ -1032,12 +1044,7 @@ static void bm_page_io_async(struct bm_aio_ctx *ctx, int page_nr, int rw) __must
  */
 static int bm_rw(struct drbd_conf *mdev, int rw, unsigned flags, unsigned lazy_writeout_upper_idx) __must_hold(local)
 {
-	struct bm_aio_ctx ctx = {
-		.mdev = mdev,
-		.in_flight = ATOMIC_INIT(1),
-		.done = COMPLETION_INITIALIZER_ONSTACK(ctx.done),
-		.flags = flags,
-	};
+	struct bm_aio_ctx *ctx;
 	struct drbd_bitmap *b = mdev->bitmap;
 	int num_pages, i, count = 0;
 	unsigned long now;
@@ -1052,7 +1059,27 @@ static int bm_rw(struct drbd_conf *mdev, int rw, unsigned flags, unsigned lazy_w
 	 * For lazy writeout, we don't care for ongoing changes to the bitmap,
 	 * as we submit copies of pages anyways.
 	 */
-	if (!ctx.flags)
+
+	ctx = kmalloc(sizeof(struct bm_aio_ctx), GFP_NOIO);
+	if (!ctx)
+		return -ENOMEM;
+
+	*ctx = (struct bm_aio_ctx) {
+		.mdev = mdev,
+		.in_flight = ATOMIC_INIT(1),
+		.done = 0,
+		.flags = flags,
+		.error = 0,
+		.kref = { ATOMIC_INIT(2) },
+	};
+
+	if (!get_ldev_if_state(mdev, D_ATTACHING)) {  /* put is in bm_aio_ctx_destroy() */
+		dev_err(DEV, "ASSERT FAILED: get_ldev_if_state() == 1 in bm_rw()\n");
+		err = -ENODEV;
+		goto out;
+	}
+
+	if (!ctx->flags)
 		WARN_ON(!(BM_LOCKED_MASK & b->bm_flags));
 
 	num_pages = b->bm_number_of_pages;
@@ -1081,32 +1108,40 @@ static int bm_rw(struct drbd_conf *mdev, int rw, unsigned flags, unsigned lazy_w
 				continue;
 			}
 		}
-		atomic_inc(&ctx.in_flight);
-		bm_page_io_async(&ctx, i, rw);
+		atomic_inc(&ctx->in_flight);
+		bm_page_io_async(ctx, i, rw);
 		++count;
 		cond_resched();
 	}
 
 	/*
-	 * We initialize ctx.in_flight to one to make sure bm_async_io_complete
-	 * will not complete() early, and decrement / test it here.  If there
+	 * We initialize ctx->in_flight to one to make sure bm_async_io_complete
+	 * will not set ctx->done early, and decrement / test it here.  If there
 	 * are still some bios in flight, we need to wait for them here.
+	 * If all IO is done already (or nothing had been submitted), there is
+	 * no need to wait.  Still, we need to put the kref associated with the
+	 * "in_flight reached zero, all done" event.
 	 */
-	if (!atomic_dec_and_test(&ctx.in_flight))
-		wait_for_completion(&ctx.done);
+	if (!atomic_dec_and_test(&ctx->in_flight))
+		wait_until_done_or_disk_failure(mdev, &ctx->done);
+	else
+		kref_put(&ctx->kref, &bm_aio_ctx_destroy);
 
 	/* summary for global bitmap IO */
 	if (flags == 0)
 		dev_info(DEV, "bitmap %s of %u pages took %lu jiffies\n",
-				rw == WRITE ? "WRITE" : "READ",
-				count, jiffies - now);
+			 rw == WRITE ? "WRITE" : "READ",
+			 count, jiffies - now);
 
-	if (ctx.error) {
+	if (ctx->error) {
 		dev_alert(DEV, "we had at least one MD IO ERROR during bitmap IO\n");
 		drbd_chk_io_error(mdev, 1, true);
-		err = -EIO; /* ctx.error ? */
+		err = -EIO; /* ctx->error ? */
 	}
 
+	if (atomic_read(&ctx->in_flight))
+		err = -EIO; /* Disk failed during IO... */
+
 	now = jiffies;
 	if (rw == WRITE) {
 		drbd_md_flush(mdev);
@@ -1121,6 +1156,8 @@ static int bm_rw(struct drbd_conf *mdev, int rw, unsigned flags, unsigned lazy_w
 		dev_info(DEV, "%s (%lu bits) marked out-of-sync by on disk bit-map.\n",
 		     ppsize(ppb, now << (BM_BLOCK_SHIFT-10)), now);
 
+out:
+	kref_put(&ctx->kref, &bm_aio_ctx_destroy);
 	return err;
 }
 
@@ -1177,28 +1214,46 @@ int drbd_bm_write_hinted(struct drbd_conf *mdev) __must_hold(local)
  */
 int drbd_bm_write_page(struct drbd_conf *mdev, unsigned int idx) __must_hold(local)
 {
-	struct bm_aio_ctx ctx = {
+	struct bm_aio_ctx *ctx;
+	int err;
+
+	if (bm_test_page_unchanged(mdev->bitmap->bm_pages[idx])) {
+		dynamic_dev_dbg(DEV, "skipped bm page write for idx %u\n", idx);
+		return 0;
+	}
+
+	ctx = kmalloc(sizeof(struct bm_aio_ctx), GFP_NOIO);
+	if (!ctx)
+		return -ENOMEM;
+
+	*ctx = (struct bm_aio_ctx) {
 		.mdev = mdev,
 		.in_flight = ATOMIC_INIT(1),
-		.done = COMPLETION_INITIALIZER_ONSTACK(ctx.done),
+		.done = 0,
 		.flags = BM_AIO_COPY_PAGES,
+		.error = 0,
+		.kref = { ATOMIC_INIT(2) },
 	};
 
-	if (bm_test_page_unchanged(mdev->bitmap->bm_pages[idx])) {
-		dynamic_dev_dbg(DEV, "skipped bm page write for idx %u\n", idx);
-		return 0;
+	if (!get_ldev_if_state(mdev, D_ATTACHING)) {  /* put is in bm_aio_ctx_destroy() */
+		dev_err(DEV, "ASSERT FAILED: get_ldev_if_state() == 1 in drbd_bm_write_page()\n");
+		err = -ENODEV;
+		goto out;
 	}
 
-	bm_page_io_async(&ctx, idx, WRITE_SYNC);
-	wait_for_completion(&ctx.done);
+	bm_page_io_async(ctx, idx, WRITE_SYNC);
+	wait_until_done_or_disk_failure(mdev, &ctx->done);
 
-	if (ctx.error)
+	if (ctx->error)
 		drbd_chk_io_error(mdev, 1, true);
 		/* that should force detach, so the in memory bitmap will be
 		 * gone in a moment as well. */
 
 	mdev->bm_writ_cnt++;
-	return ctx.error;
+	err = atomic_read(&ctx->in_flight) ? -EIO : ctx->error;
+ out:
+	kref_put(&ctx->kref, &bm_aio_ctx_destroy);
+	return err;
 }
 
 /* NOTE
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 6035784f0de3..4e582058a7c9 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -780,8 +780,7 @@ struct drbd_backing_dev {
 };
 
 struct drbd_md_io {
-	struct drbd_conf *mdev;
-	struct completion event;
+	unsigned int done;
 	int error;
 };
 
@@ -852,6 +851,7 @@ struct drbd_tconn {			/* is a resource from the config file */
 	struct drbd_tl_epoch *newest_tle;
 	struct drbd_tl_epoch *oldest_tle;
 	struct list_head out_of_sequence_requests;
+	struct list_head barrier_acked_requests;
 
 	struct crypto_hash *cram_hmac_tfm;
 	struct crypto_hash *integrity_tfm;  /* checksums we compute, updates protected by tconn->data->mutex */
@@ -978,7 +978,8 @@ struct drbd_conf {
 	atomic_t pp_in_use_by_net;	/* sendpage()d, still referenced by tcp */
 	wait_queue_head_t ee_wait;
 	struct page *md_io_page;	/* one page buffer for md_io */
-	struct mutex md_io_mutex;	/* protects the md_io_buffer */
+	struct drbd_md_io md_io;
+	atomic_t md_io_in_use;		/* protects the md_io, md_io_page and md_io_tmpp */
 	spinlock_t al_lock;
 	wait_queue_head_t al_wait;
 	struct lru_cache *act_log;	/* activity log */
@@ -1424,9 +1425,12 @@ extern void resume_next_sg(struct drbd_conf *mdev);
 extern void suspend_other_sg(struct drbd_conf *mdev);
 extern int drbd_resync_finished(struct drbd_conf *mdev);
 /* maybe rather drbd_main.c ? */
+extern void *drbd_md_get_buffer(struct drbd_conf *mdev);
+extern void drbd_md_put_buffer(struct drbd_conf *mdev);
 extern int drbd_md_sync_page_io(struct drbd_conf *mdev,
 		struct drbd_backing_dev *bdev, sector_t sector, int rw);
 extern void drbd_ov_out_of_sync_found(struct drbd_conf *, sector_t, int);
+extern void wait_until_done_or_disk_failure(struct drbd_conf *mdev, unsigned int *done);
 extern void drbd_rs_controller_reset(struct drbd_conf *mdev);
 
 static inline void ov_out_of_sync_print(struct drbd_conf *mdev)
@@ -2151,12 +2155,12 @@ static inline int drbd_state_is_stable(struct drbd_conf *mdev)
 	case D_OUTDATED:
 	case D_CONSISTENT:
 	case D_UP_TO_DATE:
+	case D_FAILED:
 		/* disk state is stable as well. */
 		break;
 
 	/* no new io accepted during transitional states */
 	case D_ATTACHING:
-	case D_FAILED:
 	case D_NEGOTIATING:
 	case D_UNKNOWN:
 	case D_MASK:
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 448de7bf8223..15384986e4a4 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -215,6 +215,7 @@ static int tl_init(struct drbd_tconn *tconn)
 	tconn->oldest_tle = b;
 	tconn->newest_tle = b;
 	INIT_LIST_HEAD(&tconn->out_of_sequence_requests);
+	INIT_LIST_HEAD(&tconn->barrier_acked_requests);
 
 	return 1;
 }
@@ -315,7 +316,7 @@ void tl_release(struct drbd_tconn *tconn, unsigned int barrier_nr,
 	   These have been list_move'd to the out_of_sequence_requests list in
 	   _req_mod(, BARRIER_ACKED) above.
 	   */
-	list_del_init(&b->requests);
+	list_splice_init(&b->requests, &tconn->barrier_acked_requests);
 	mdev = b->w.mdev;
 
 	nob = b->next;
@@ -417,8 +418,23 @@ void _tl_restart(struct drbd_tconn *tconn, enum drbd_req_event what)
 		b = tmp;
 		list_splice(&carry_reads, &b->requests);
 	}
-}
 
+	/* Actions operating on the disk state, also want to work on
+	   requests that got barrier acked. */
+	switch (what) {
+	case FAIL_FROZEN_DISK_IO:
+	case RESTART_FROZEN_DISK_IO:
+		list_for_each_safe(le, tle, &tconn->barrier_acked_requests) {
+			req = list_entry(le, struct drbd_request, tl_requests);
+			_req_mod(req, what);
+		}
+	case CONNECTION_LOST_WHILE_PENDING:
+	case RESEND:
+		break;
+	default:
+		conn_err(tconn, "what = %d in _tl_restart()\n", what);
+	}
+}
 
 /**
  * tl_clear() - Clears all requests and &struct drbd_tl_epoch objects out of the TL
@@ -467,6 +483,42 @@ void tl_restart(struct drbd_tconn *tconn, enum drbd_req_event what)
 	spin_unlock_irq(&tconn->req_lock);
 }
 
+/**
+ * tl_apply() - Applies an event to all requests for a certain mdev in the TL
+ * @mdev:	DRBD device.
+ * @what:       The action/event to perform with all request objects
+ *
+ * @what might ony be ABORT_DISK_IO.
+ */
+void tl_apply(struct drbd_conf *mdev, enum drbd_req_event what)
+{
+	struct drbd_tconn *tconn = mdev->tconn;
+	struct drbd_tl_epoch *b;
+	struct list_head *le, *tle;
+	struct drbd_request *req;
+
+	D_ASSERT(what == ABORT_DISK_IO);
+
+	spin_lock_irq(&tconn->req_lock);
+	b = tconn->oldest_tle;
+	while (b) {
+		list_for_each_safe(le, tle, &b->requests) {
+			req = list_entry(le, struct drbd_request, tl_requests);
+			if (req->w.mdev == mdev)
+				_req_mod(req, what);
+		}
+		b = b->next;
+	}
+
+	list_for_each_safe(le, tle, &tconn->barrier_acked_requests) {
+		req = list_entry(le, struct drbd_request, tl_requests);
+		if (req->w.mdev == mdev)
+			_req_mod(req, what);
+	}
+
+	spin_unlock_irq(&tconn->req_lock);
+}
+
 static int drbd_thread_setup(void *arg)
 {
 	struct drbd_thread *thi = (struct drbd_thread *) arg;
@@ -2003,8 +2055,8 @@ void drbd_init_set_defaults(struct drbd_conf *mdev)
 	atomic_set(&mdev->rs_sect_in, 0);
 	atomic_set(&mdev->rs_sect_ev, 0);
 	atomic_set(&mdev->ap_in_flight, 0);
+	atomic_set(&mdev->md_io_in_use, 0);
 
-	mutex_init(&mdev->md_io_mutex);
 	mutex_init(&mdev->own_state_mutex);
 	mdev->state_mutex = &mdev->own_state_mutex;
 
@@ -2282,6 +2334,8 @@ void drbd_minor_destroy(struct kref *kref)
 	struct drbd_conf *mdev = container_of(kref, struct drbd_conf, kref);
 	struct drbd_tconn *tconn = mdev->tconn;
 
+	del_timer_sync(&mdev->request_timer);
+
 	/* paranoia asserts */
 	D_ASSERT(mdev->open_cnt == 0);
 	D_ASSERT(list_empty(&mdev->tconn->data.work.q));
@@ -2868,8 +2922,10 @@ void drbd_md_sync(struct drbd_conf *mdev)
 	if (!get_ldev_if_state(mdev, D_FAILED))
 		return;
 
-	mutex_lock(&mdev->md_io_mutex);
-	buffer = (struct meta_data_on_disk *)page_address(mdev->md_io_page);
+	buffer = drbd_md_get_buffer(mdev);
+	if (!buffer)
+		goto out;
+
 	memset(buffer, 0, 512);
 
 	buffer->la_size = cpu_to_be64(drbd_get_capacity(mdev->this_bdev));
@@ -2900,7 +2956,8 @@ void drbd_md_sync(struct drbd_conf *mdev)
 	 * since we updated it on metadata. */
 	mdev->ldev->md.la_size_sect = drbd_get_capacity(mdev->this_bdev);
 
-	mutex_unlock(&mdev->md_io_mutex);
+	drbd_md_put_buffer(mdev);
+out:
 	put_ldev(mdev);
 }
 
@@ -2920,8 +2977,9 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 	if (!get_ldev_if_state(mdev, D_ATTACHING))
 		return ERR_IO_MD_DISK;
 
-	mutex_lock(&mdev->md_io_mutex);
-	buffer = (struct meta_data_on_disk *)page_address(mdev->md_io_page);
+	buffer = drbd_md_get_buffer(mdev);
+	if (!buffer)
+		goto out;
 
 	if (drbd_md_sync_page_io(mdev, bdev, bdev->md.md_offset, READ)) {
 		/* NOTE: can't do normal error processing here as this is
@@ -2983,7 +3041,8 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 		bdev->disk_conf->al_extents = DRBD_AL_EXTENTS_DEF;
 
  err:
-	mutex_unlock(&mdev->md_io_mutex);
+	drbd_md_put_buffer(mdev);
+ out:
 	put_ldev(mdev);
 
 	return rv;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 97d1dab045d2..bf8d0b077624 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1236,6 +1236,7 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 	synchronize_rcu();
 	kfree(old_disk_conf);
 	kfree(old_plan);
+	mod_timer(&mdev->request_timer, jiffies + HZ);
 	goto success;
 
 fail_unlock:
@@ -1628,6 +1629,8 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	if (rv < SS_SUCCESS)
 		goto force_diskless_dec;
 
+	mod_timer(&mdev->request_timer, jiffies + HZ);
+
 	if (mdev->state.role == R_PRIMARY)
 		mdev->ldev->md.uuid[UI_CURRENT] |=  (u64)1;
 	else
@@ -1667,10 +1670,17 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-static int adm_detach(struct drbd_conf *mdev)
+static int adm_detach(struct drbd_conf *mdev, int force)
 {
 	enum drbd_state_rv retcode;
 	int ret;
+
+	if (force) {
+		drbd_force_state(mdev, NS(disk, D_FAILED));
+		retcode = SS_SUCCESS;
+		goto out;
+	}
+
 	drbd_suspend_io(mdev); /* so no-one is stuck in drbd_al_begin_io */
 	retcode = drbd_request_state(mdev, NS(disk, D_FAILED));
 	/* D_FAILED will transition to DISKLESS. */
@@ -1681,6 +1691,7 @@ static int adm_detach(struct drbd_conf *mdev)
 		retcode = SS_NOTHING_TO_DO;
 	if (ret)
 		retcode = ERR_INTR;
+out:
 	return retcode;
 }
 
@@ -1692,6 +1703,8 @@ static int adm_detach(struct drbd_conf *mdev)
 int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info)
 {
 	enum drbd_ret_code retcode;
+	struct detach_parms parms = { };
+	int err;
 
 	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
@@ -1699,7 +1712,16 @@ int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto out;
 
-	retcode = adm_detach(adm_ctx.mdev);
+	if (info->attrs[DRBD_NLA_DETACH_PARMS]) {
+		err = detach_parms_from_attrs(&parms, info);
+		if (err) {
+			retcode = ERR_MANDATORY_TAG;
+			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			goto out;
+		}
+	}
+
+	retcode = adm_detach(adm_ctx.mdev, parms.force_detach);
 out:
 	drbd_adm_finish(info, retcode);
 	return 0;
@@ -3116,7 +3138,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 
 	/* detach */
 	idr_for_each_entry(&adm_ctx.tconn->volumes, mdev, i) {
-		retcode = adm_detach(mdev);
+		retcode = adm_detach(mdev, 0);
 		if (retcode < SS_SUCCESS) {
 			drbd_msg_put_info("failed to detach");
 			goto out;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 7218750d2937..3a7e54b8f418 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -4366,8 +4366,6 @@ static int drbd_disconnected(struct drbd_conf *mdev)
 	atomic_set(&mdev->rs_pending_cnt, 0);
 	wake_up(&mdev->misc_wait);
 
-	del_timer(&mdev->request_timer);
-
 	del_timer_sync(&mdev->resync_timer);
 	resync_timer_fn((unsigned long)mdev);
 
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index c4e4553f5c2c..8fa51cda3b7e 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -213,8 +213,7 @@ void _req_may_be_done(struct drbd_request *req, struct bio_and_error *m)
 {
 	const unsigned long s = req->rq_state;
 	struct drbd_conf *mdev = req->w.mdev;
-	/* only WRITES may end up here without a master bio (on barrier ack) */
-	int rw = req->master_bio ? bio_data_dir(req->master_bio) : WRITE;
+	int rw = req->rq_state & RQ_WRITE ? WRITE : READ;
 
 	/* we must not complete the master bio, while it is
 	 *	still being processed by _drbd_send_zc_bio (drbd_send_dblock)
@@ -225,7 +224,7 @@ void _req_may_be_done(struct drbd_request *req, struct bio_and_error *m)
 	 *	the receiver,
 	 *	the bio_endio completion callbacks.
 	 */
-	if (s & RQ_LOCAL_PENDING)
+	if (s & RQ_LOCAL_PENDING && !(s & RQ_LOCAL_ABORTED))
 		return;
 	if (req->i.waiting) {
 		/* Retry all conflicting peer requests.  */
@@ -288,6 +287,9 @@ void _req_may_be_done(struct drbd_request *req, struct bio_and_error *m)
 		req->master_bio = NULL;
 	}
 
+	if (s & RQ_LOCAL_PENDING)
+		return;
+
 	if ((s & RQ_NET_MASK) == 0 || (s & RQ_NET_DONE)) {
 		/* this is disconnected (local only) operation,
 		 * or protocol C P_WRITE_ACK,
@@ -362,7 +364,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		break;
 
 	case COMPLETED_OK:
-		if (bio_data_dir(req->master_bio) == WRITE)
+		if (req->rq_state & RQ_WRITE)
 			mdev->writ_cnt += req->i.size >> 9;
 		else
 			mdev->read_cnt += req->i.size >> 9;
@@ -374,6 +376,14 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		put_ldev(mdev);
 		break;
 
+	case ABORT_DISK_IO:
+		req->rq_state |= RQ_LOCAL_ABORTED;
+		if (req->rq_state & RQ_WRITE)
+			_req_may_be_done_not_susp(req, m);
+		else
+			goto goto_queue_for_net_read;
+		break;
+
 	case WRITE_COMPLETED_WITH_ERROR:
 		req->rq_state |= RQ_LOCAL_COMPLETED;
 		req->rq_state &= ~RQ_LOCAL_PENDING;
@@ -402,6 +412,8 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		__drbd_chk_io_error(mdev, false);
 		put_ldev(mdev);
 
+	goto_queue_for_net_read:
+
 		/* no point in retrying if there is no good remote data,
 		 * or we have no connection. */
 		if (mdev->state.pdsk != D_UP_TO_DATE) {
@@ -1071,14 +1083,21 @@ void request_timer_fn(unsigned long data)
 	struct drbd_request *req; /* oldest request */
 	struct list_head *le;
 	struct net_conf *nc;
-	unsigned long et; /* effective timeout = ko_count * timeout */
+	unsigned long ent = 0, dt = 0, et; /* effective timeout = ko_count * timeout */
 
 	rcu_read_lock();
 	nc = rcu_dereference(tconn->net_conf);
-	et = nc ? nc->timeout * HZ/10 * nc->ko_count : 0;
+	ent = nc ? nc->timeout * HZ/10 * nc->ko_count : 0;
+
+	if (get_ldev(mdev)) {
+		dt = rcu_dereference(mdev->ldev->disk_conf)->disk_timeout * HZ / 10;
+		put_ldev(mdev);
+	}
 	rcu_read_unlock();
 
-	if (!et || mdev->state.conn < C_WF_REPORT_PARAMS)
+	et = min_not_zero(dt, ent);
+
+	if (!et || (mdev->state.conn < C_WF_REPORT_PARAMS && mdev->state.disk <= D_FAILED))
 		return; /* Recurring timer stopped */
 
 	spin_lock_irq(&tconn->req_lock);
@@ -1091,17 +1110,18 @@ void request_timer_fn(unsigned long data)
 
 	le = le->prev;
 	req = list_entry(le, struct drbd_request, tl_requests);
-	if (time_is_before_eq_jiffies(req->start_time + et)) {
-		if (req->rq_state & RQ_NET_PENDING) {
+	if (ent && req->rq_state & RQ_NET_PENDING) {
+		if (time_is_before_eq_jiffies(req->start_time + ent)) {
 			dev_warn(DEV, "Remote failed to finish a request within ko-count * timeout\n");
-			_drbd_set_state(_NS(mdev, conn, C_TIMEOUT), CS_VERBOSE, NULL);
-		} else {
-			dev_warn(DEV, "Local backing block device frozen?\n");
-			mod_timer(&mdev->request_timer, jiffies + et);
+			_drbd_set_state(_NS(mdev, conn, C_TIMEOUT), CS_VERBOSE | CS_HARD, NULL);
+		}
+	}
+	if (dt && req->rq_state & RQ_LOCAL_PENDING) {
+		if (time_is_before_eq_jiffies(req->start_time + dt)) {
+			dev_warn(DEV, "Local backing device failed to meet the disk-timeout\n");
+			__drbd_chk_io_error(mdev, 1);
 		}
-	} else {
-		mod_timer(&mdev->request_timer, req->start_time + et);
 	}
-
 	spin_unlock_irq(&tconn->req_lock);
+	mod_timer(&mdev->request_timer, req->start_time + et);
 }
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index 5135c95fbf85..f6aff150addb 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -106,6 +106,7 @@ enum drbd_req_event {
 	READ_COMPLETED_WITH_ERROR,
 	READ_AHEAD_COMPLETED_WITH_ERROR,
 	WRITE_COMPLETED_WITH_ERROR,
+	ABORT_DISK_IO,
 	COMPLETED_OK,
 	RESEND,
 	FAIL_FROZEN_DISK_IO,
@@ -119,18 +120,21 @@ enum drbd_req_event {
  * same time, so we should hold the request lock anyways.
  */
 enum drbd_req_state_bits {
-	/* 210
-	 * 000: no local possible
-	 * 001: to be submitted
+	/* 3210
+	 * 0000: no local possible
+	 * 0001: to be submitted
 	 *    UNUSED, we could map: 011: submitted, completion still pending
-	 * 110: completed ok
-	 * 010: completed with error
+	 * 0110: completed ok
+	 * 0010: completed with error
+	 * 1001: Aborted (before completion)
+	 * 1x10: Aborted and completed -> free
 	 */
 	__RQ_LOCAL_PENDING,
 	__RQ_LOCAL_COMPLETED,
 	__RQ_LOCAL_OK,
+	__RQ_LOCAL_ABORTED,
 
-	/* 76543
+	/* 87654
 	 * 00000: no network possible
 	 * 00001: to be send
 	 * 00011: to be send, on worker queue
@@ -209,8 +213,9 @@ enum drbd_req_state_bits {
 #define RQ_LOCAL_PENDING   (1UL << __RQ_LOCAL_PENDING)
 #define RQ_LOCAL_COMPLETED (1UL << __RQ_LOCAL_COMPLETED)
 #define RQ_LOCAL_OK        (1UL << __RQ_LOCAL_OK)
+#define RQ_LOCAL_ABORTED   (1UL << __RQ_LOCAL_ABORTED)
 
-#define RQ_LOCAL_MASK      ((RQ_LOCAL_OK << 1)-1) /* 0x07 */
+#define RQ_LOCAL_MASK      ((RQ_LOCAL_ABORTED << 1)-1)
 
 #define RQ_NET_PENDING     (1UL << __RQ_NET_PENDING)
 #define RQ_NET_QUEUED      (1UL << __RQ_NET_QUEUED)
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 4c13a6f4f184..f51cefdbeff3 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -29,6 +29,9 @@
 #include "drbd_int.h"
 #include "drbd_req.h"
 
+/* in drbd_main.c */
+extern void tl_apply(struct drbd_conf *mdev, enum drbd_req_event what);
+
 struct after_state_chg_work {
 	struct drbd_work w;
 	union drbd_state os;
@@ -1315,6 +1318,10 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 		rcu_read_unlock();
 		was_io_error = test_and_clear_bit(WAS_IO_ERROR, &mdev->flags);
 
+		/* Immediately allow completion of all application IO, that waits
+		   for completion from the local disk. */
+		tl_apply(mdev, ABORT_DISK_IO);
+
 		/* current state still has to be D_FAILED,
 		 * there is only one way out: to D_DISKLESS,
 		 * and that may only happen after our put_ldev below. */
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 6410c55831e0..dac8d9bc4bec 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -67,11 +67,18 @@ rwlock_t global_state_lock;
 void drbd_md_io_complete(struct bio *bio, int error)
 {
 	struct drbd_md_io *md_io;
+	struct drbd_conf *mdev;
 
 	md_io = (struct drbd_md_io *)bio->bi_private;
+	mdev = container_of(md_io, struct drbd_conf, md_io);
+
 	md_io->error = error;
 
-	complete(&md_io->event);
+	md_io->done = 1;
+	wake_up(&mdev->misc_wait);
+	bio_put(bio);
+	drbd_md_put_buffer(mdev);
+	put_ldev(mdev);
 }
 
 /* reads on behalf of the partner,
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index e879a9324380..2e6cefefe5e5 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -128,6 +128,7 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__flg_field_def(17, DRBD_GENLA_F_MANDATORY,	disk_flushes, DRBD_DISK_FLUSHES_DEF)
 	__flg_field_def(18, DRBD_GENLA_F_MANDATORY,	disk_drain, DRBD_DISK_DRAIN_DEF)
 	__flg_field_def(19, DRBD_GENLA_F_MANDATORY,	md_flushes, DRBD_MD_FLUSHES_DEF)
+	__u32_field_def(20,	DRBD_GENLA_F_MANDATORY,	disk_timeout, DRBD_DISK_TIMEOUT_DEF)
 )
 
 GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
@@ -224,6 +225,10 @@ GENL_struct(DRBD_NLA_DISCONNECT_PARMS, 12, disconnect_parms,
 	__flg_field(1, DRBD_GENLA_F_MANDATORY,	force_disconnect)
 )
 
+GENL_struct(DRBD_NLA_DETACH_PARMS, 13, detach_parms,
+	__flg_field(1, DRBD_GENLA_F_MANDATORY,	force_detach)
+)
+
 /*
  * Notifications and commands (genlmsghdr->cmd)
  */
@@ -335,7 +340,9 @@ GENL_op(
 )
 
 GENL_op(DRBD_ADM_DETACH,	18, GENL_doit(drbd_adm_detach),
-	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
+	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+	GENL_tla_expected(DRBD_NLA_DETACH_PARMS, DRBD_GENLA_F_MANDATORY))
+
 GENL_op(DRBD_ADM_INVALIDATE,	19, GENL_doit(drbd_adm_invalidate),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 GENL_op(DRBD_ADM_INVAL_PEER,	20, GENL_doit(drbd_adm_invalidate_peer),
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index f1046b13d9f6..ddd332db2a5d 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -50,6 +50,12 @@
 #define DRBD_TIMEOUT_MAX 600
 #define DRBD_TIMEOUT_DEF 60       /* 6 seconds */
 
+ /* If backing disk takes longer than disk_timeout, mark the disk as failed */
+#define DRBD_DISK_TIMEOUT_MIN 0    /* 0 = disabled */
+#define DRBD_DISK_TIMEOUT_MAX 6000 /* 10 Minutes */
+#define DRBD_DISK_TIMEOUT_DEF 0    /* disabled */
+#define DRBD_DISK_TIMEOUT_SCALE '1'
+
   /* active connection retries when C_WF_CONNECTION */
 #define DRBD_CONNECT_INT_MIN 1
 #define DRBD_CONNECT_INT_MAX 120
-- 
cgit v1.2.3-55-g7522


From d5d7ebd42250620a6da2a8f6943c024391433488 Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Tue, 5 Jul 2011 20:59:26 +0200
Subject: drbd: on attach, enforce clean meta data

Detection of unclean shutdown has moved into user space.

The kernel code will, whenever it updates the meta data, mark it as
"unclean", and will refuse to attach to such unclean meta data.

"drbdadm up" now schedules "drbdmeta apply-al", which will apply
the activity log to the bitmap, and/or reinitialize it, if necessary,
as well as set a "clean" indicator flag.

This moves a bit code out of kernel space.
As a side effect, it also prevents some 8.3 module from accidentally
ignoring the 8.4 style activity log, if someone should downgrade,
whether on purpose, or accidentally because he changed kernel versions
without providing an 8.4 for the new kernel, and the new kernel comes
with in-tree 8.3.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_actlog.c | 259 ---------------------------------------
 drivers/block/drbd/drbd_int.h    |   6 -
 drivers/block/drbd/drbd_main.c   |  26 ++--
 drivers/block/drbd/drbd_nl.c     |  19 +--
 drivers/block/drbd/drbd_state.c  |   1 +
 include/linux/drbd.h             |  10 +-
 6 files changed, 28 insertions(+), 293 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 58b5b61628fc..da8ffd54fc18 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -462,265 +462,6 @@ w_al_write_transaction(struct drbd_work *w, int unused)
 	return 0;
 }
 
-/* FIXME
- * reading of the activity log,
- * and potentially dirtying of the affected bitmap regions,
- * should be done from userland only.
- * DRBD would simply always attach with an empty activity log,
- * and refuse to attach to something that looks like a crashed primary.
- */
-
-/**
- * drbd_al_read_tr() - Read a single transaction from the on disk activity log
- * @mdev:	DRBD device.
- * @bdev:	Block device to read form.
- * @b:		pointer to an al_transaction.
- * @index:	On disk slot of the transaction to read.
- *
- * Returns -1 on IO error, 0 on checksum error and 1 upon success.
- */
-static int drbd_al_read_tr(struct drbd_conf *mdev,
-			   struct drbd_backing_dev *bdev,
-			   int index)
-{
-	struct al_transaction_on_disk *b = page_address(mdev->md_io_page);
-	sector_t sector;
-	u32 crc;
-
-	sector =  bdev->md.md_offset
-		+ bdev->md.al_offset
-		+ index * (MD_BLOCK_SIZE>>9);
-
-	/* Dont process error normally,
-	 * as this is done before disk is attached! */
-	if (drbd_md_sync_page_io(mdev, bdev, sector, READ))
-		return -1;
-
-	if (!expect(b->magic == cpu_to_be32(DRBD_AL_MAGIC)))
-		return 0;
-
-	if (!expect(be16_to_cpu(b->n_updates) <= AL_UPDATES_PER_TRANSACTION))
-		return 0;
-
-	if (!expect(be16_to_cpu(b->context_size) <= DRBD_AL_EXTENTS_MAX))
-		return 0;
-
-	if (!expect(be16_to_cpu(b->context_start_slot_nr) < DRBD_AL_EXTENTS_MAX))
-		return 0;
-
-	crc = be32_to_cpu(b->crc32c);
-	b->crc32c = 0;
-	if (!expect(crc == crc32c(0, b, 4096)))
-		return 0;
-
-	return 1;
-}
-
-/**
- * drbd_al_read_log() - Restores the activity log from its on disk representation.
- * @mdev:	DRBD device.
- * @bdev:	Block device to read form.
- *
- * Returns 1 on success, returns 0 when reading the log failed due to IO errors.
- */
-int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
-{
-	struct al_transaction_on_disk *b;
-	int i;
-	int rv;
-	int mx;
-	int active_extents = 0;
-	int transactions = 0;
-	int found_valid = 0;
-	int found_initialized = 0;
-	int from = 0;
-	int to = 0;
-	u32 from_tnr = 0;
-	u32 to_tnr = 0;
-	u32 cnr;
-
-	/* Note that this is expected to be called with a newly created,
-	 * clean and all unused activity log of the "expected size".
-	 */
-
-	/* lock out all other meta data io for now,
-	 * and make sure the page is mapped.
-	 */
-	b = drbd_md_get_buffer(mdev);
-	if (!b)
-		return 0;
-
-	/* Always use the full ringbuffer space for now.
-	 * possible optimization: read in all of it,
-	 * then scan the in-memory pages. */
-
-	mx = (MD_AL_SECTORS*512/MD_BLOCK_SIZE);
-
-	/* Find the valid transaction in the log */
-	for (i = 0; i < mx; i++) {
-		rv = drbd_al_read_tr(mdev, bdev, i);
-		/* invalid data in that block */
-		if (rv == 0)
-			continue;
-		if (be16_to_cpu(b->transaction_type) == AL_TR_INITIALIZED) {
-			++found_initialized;
-			continue;
-		}
-
-		/* IO error */
-		if (rv == -1) {
-			drbd_md_put_buffer(mdev);
-			return 0;
-		}
-
-		cnr = be32_to_cpu(b->tr_number);
-		if (++found_valid == 1) {
-			from = i;
-			to = i;
-			from_tnr = cnr;
-			to_tnr = cnr;
-			continue;
-		}
-
-		D_ASSERT(cnr != to_tnr);
-		D_ASSERT(cnr != from_tnr);
-		if ((int)cnr - (int)from_tnr < 0) {
-			D_ASSERT(from_tnr - cnr + i - from == mx);
-			from = i;
-			from_tnr = cnr;
-		}
-		if ((int)cnr - (int)to_tnr > 0) {
-			D_ASSERT(cnr - to_tnr == i - to);
-			to = i;
-			to_tnr = cnr;
-		}
-	}
-
-	if (!found_valid) {
-		if (found_initialized != mx)
-			dev_warn(DEV, "No usable activity log found.\n");
-		drbd_md_put_buffer(mdev);
-		return 1;
-	}
-
-	/* Read the valid transactions.
-	 * dev_info(DEV, "Reading from %d to %d.\n",from,to); */
-	i = from;
-	while (1) {
-		struct lc_element *e;
-		unsigned j, n, slot, extent_nr;
-
-		rv = drbd_al_read_tr(mdev, bdev, i);
-		if (!expect(rv != 0))
-			goto cancel;
-		if (rv == -1) {
-			drbd_md_put_buffer(mdev);
-			return 0;
-		}
-
-		/* deal with different transaction types.
-		 * not yet implemented */
-		if (!expect(b->transaction_type == 0))
-			goto cancel;
-
-		/* on the fly re-create/resize activity log?
-		 * will be a special transaction type flag. */
-		if (!expect(be16_to_cpu(b->context_size) == mdev->act_log->nr_elements))
-			goto cancel;
-		if (!expect(be16_to_cpu(b->context_start_slot_nr) < mdev->act_log->nr_elements))
-			goto cancel;
-
-		/* We are the only user of the activity log right now,
-		 * don't actually need to take that lock. */
-		spin_lock_irq(&mdev->al_lock);
-
-		/* first, apply the context, ... */
-		for (j = 0, slot = be16_to_cpu(b->context_start_slot_nr);
-		     j < AL_CONTEXT_PER_TRANSACTION &&
-		     slot < mdev->act_log->nr_elements; j++, slot++) {
-			extent_nr = be32_to_cpu(b->context[j]);
-			e = lc_element_by_index(mdev->act_log, slot);
-			if (e->lc_number != extent_nr) {
-				if (extent_nr != LC_FREE)
-					active_extents++;
-				else
-					active_extents--;
-			}
-			lc_set(mdev->act_log, extent_nr, slot);
-		}
-
-		/* ... then apply the updates,
-		 * which override the context information.
-		 * drbd_al_read_tr already did the rangecheck
-		 * on n <= AL_UPDATES_PER_TRANSACTION */
-		n = be16_to_cpu(b->n_updates);
-		for (j = 0; j < n; j++) {
-			slot = be16_to_cpu(b->update_slot_nr[j]);
-			extent_nr = be32_to_cpu(b->update_extent_nr[j]);
-			if (!expect(slot < mdev->act_log->nr_elements))
-				break;
-			e = lc_element_by_index(mdev->act_log, slot);
-			if (e->lc_number != extent_nr) {
-				if (extent_nr != LC_FREE)
-					active_extents++;
-				else
-					active_extents--;
-			}
-			lc_set(mdev->act_log, extent_nr, slot);
-		}
-		spin_unlock_irq(&mdev->al_lock);
-
-		transactions++;
-
-cancel:
-		if (i == to)
-			break;
-		i++;
-		if (i >= mx)
-			i = 0;
-	}
-
-	mdev->al_tr_number = to_tnr+1;
-	mdev->al_tr_pos = (to + 1) % (MD_AL_SECTORS*512/MD_BLOCK_SIZE);
-
-	/* ok, we are done with it */
-	drbd_md_put_buffer(mdev);
-
-	dev_info(DEV, "Found %d transactions (%d active extents) in activity log.\n",
-	     transactions, active_extents);
-
-	return 1;
-}
-
-/**
- * drbd_al_apply_to_bm() - Sets the bitmap to dirty(1) where covered by active AL extents
- * @mdev:	DRBD device.
- */
-void drbd_al_apply_to_bm(struct drbd_conf *mdev)
-{
-	unsigned int enr;
-	unsigned long add = 0;
-	char ppb[10];
-	int i, tmp;
-
-	wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
-
-	for (i = 0; i < mdev->act_log->nr_elements; i++) {
-		enr = lc_element_by_index(mdev->act_log, i)->lc_number;
-		if (enr == LC_FREE)
-			continue;
-		tmp = drbd_bm_ALe_set_all(mdev, enr);
-		dynamic_dev_dbg(DEV, "AL: set %d bits in extent %u\n", tmp, enr);
-		add += tmp;
-	}
-
-	lc_unlock(mdev->act_log);
-	wake_up(&mdev->al_wait);
-
-	dev_info(DEV, "Marked additional %s as out-of-sync based on AL.\n",
-	     ppsize(ppb, Bit2KB(add)));
-}
-
 static int _try_lc_del(struct drbd_conf *mdev, struct lc_element *al_ext)
 {
 	int rv;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 4e582058a7c9..9d0d6d0fb820 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -164,10 +164,6 @@ drbd_insert_fault(struct drbd_conf *mdev, unsigned int type) {
 /* usual integer division */
 #define div_floor(A, B) ((A)/(B))
 
-/* drbd_meta-data.c (still in drbd_main.c) */
-/* 4th incarnation of the disk layout. */
-#define DRBD_MD_MAGIC (DRBD_MAGIC+4)
-
 extern struct ratelimit_state drbd_ratelimit_state;
 extern struct idr minors; /* RCU, updates: genl_lock() */
 extern struct list_head drbd_tconns; /* RCU, updates: genl_lock() */
@@ -1560,7 +1556,6 @@ extern void drbd_rs_cancel_all(struct drbd_conf *mdev);
 extern int drbd_rs_del_all(struct drbd_conf *mdev);
 extern void drbd_rs_failed_io(struct drbd_conf *mdev,
 		sector_t sector, int size);
-extern int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *);
 extern void drbd_advance_rs_marks(struct drbd_conf *mdev, unsigned long still_to_go);
 extern void __drbd_set_in_sync(struct drbd_conf *mdev, sector_t sector,
 		int size, const char *file, const unsigned int line);
@@ -1570,7 +1565,6 @@ extern int __drbd_set_out_of_sync(struct drbd_conf *mdev, sector_t sector,
 		int size, const char *file, const unsigned int line);
 #define drbd_set_out_of_sync(mdev, sector, size) \
 	__drbd_set_out_of_sync(mdev, sector, size, __FILE__, __LINE__)
-extern void drbd_al_apply_to_bm(struct drbd_conf *mdev);
 extern void drbd_al_shrink(struct drbd_conf *mdev);
 
 /* drbd_nl.c */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 15384986e4a4..f1d696ab6e83 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2932,7 +2932,7 @@ void drbd_md_sync(struct drbd_conf *mdev)
 	for (i = UI_CURRENT; i < UI_SIZE; i++)
 		buffer->uuid[i] = cpu_to_be64(mdev->ldev->md.uuid[i]);
 	buffer->flags = cpu_to_be32(mdev->ldev->md.flags);
-	buffer->magic = cpu_to_be32(DRBD_MD_MAGIC);
+	buffer->magic = cpu_to_be32(DRBD_MD_MAGIC_84_UNCLEAN);
 
 	buffer->md_size_sect  = cpu_to_be32(mdev->ldev->md.md_size_sect);
 	buffer->al_offset     = cpu_to_be32(mdev->ldev->md.al_offset);
@@ -2967,11 +2967,12 @@ out:
  * @bdev:	Device from which the meta data should be read in.
  *
  * Return 0 (NO_ERROR) on success, and an enum drbd_ret_code in case
- * something goes wrong.  Currently only: ERR_IO_MD_DISK, ERR_MD_INVALID.
+ * something goes wrong.
  */
 int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 {
 	struct meta_data_on_disk *buffer;
+	u32 magic, flags;
 	int i, rv = NO_ERROR;
 
 	if (!get_ldev_if_state(mdev, D_ATTACHING))
@@ -2989,8 +2990,20 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 		goto err;
 	}
 
-	if (buffer->magic != cpu_to_be32(DRBD_MD_MAGIC)) {
-		dev_err(DEV, "Error while reading metadata, magic not found.\n");
+	magic = be32_to_cpu(buffer->magic);
+	flags = be32_to_cpu(buffer->flags);
+	if (magic == DRBD_MD_MAGIC_84_UNCLEAN ||
+	    (magic == DRBD_MD_MAGIC_08 && !(flags & MDF_AL_CLEAN))) {
+			/* btw: that's Activity Log clean, not "all" clean. */
+		dev_err(DEV, "Found unclean meta data. Did you \"drbdadm apply-al\"?\n");
+		rv = ERR_MD_UNCLEAN;
+		goto err;
+	}
+	if (magic != DRBD_MD_MAGIC_08) {
+		if (magic == DRBD_MD_MAGIC_07) 
+			dev_err(DEV, "Found old (0.7) meta data magic. Did you \"drbdadm create-md\"?\n");
+		else
+			dev_err(DEV, "Meta data magic not found. Did you \"drbdadm create-md\"?\n");
 		rv = ERR_MD_INVALID;
 		goto err;
 	}
@@ -3035,11 +3048,6 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 	}
 	spin_unlock_irq(&mdev->tconn->req_lock);
 
-	/* This blocks wants to be get removed... */
-	bdev->disk_conf->al_extents = be32_to_cpu(buffer->al_nr_extents);
-	if (bdev->disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
-		bdev->disk_conf->al_extents = DRBD_AL_EXTENTS_DEF;
-
  err:
 	drbd_md_put_buffer(mdev);
  out:
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index bf8d0b077624..b39f5dc0f47b 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1267,7 +1267,6 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	union drbd_state ns, os;
 	enum drbd_state_rv rv;
 	struct net_conf *nc;
-	int cp_discovered = 0;
 
 	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
@@ -1477,11 +1476,6 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		goto force_diskless_dec;
 	}
 
-	if (!drbd_al_read_log(mdev, nbc)) {
-		retcode = ERR_IO_MD_DISK;
-		goto force_diskless_dec;
-	}
-
 	/* Reset the "barriers don't work" bits here, then force meta data to
 	 * be written, to ensure we determine if barriers are supported. */
 	if (new_disk_conf->md_flushes)
@@ -1511,10 +1505,8 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		clear_bit(CRASHED_PRIMARY, &mdev->flags);
 
 	if (drbd_md_test_flag(mdev->ldev, MDF_PRIMARY_IND) &&
-	    !(mdev->state.role == R_PRIMARY && mdev->tconn->susp_nod)) {
+	    !(mdev->state.role == R_PRIMARY && mdev->tconn->susp_nod))
 		set_bit(CRASHED_PRIMARY, &mdev->flags);
-		cp_discovered = 1;
-	}
 
 	mdev->send_cnt = 0;
 	mdev->recv_cnt = 0;
@@ -1566,15 +1558,6 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	if (cp_discovered) {
-		drbd_al_apply_to_bm(mdev);
-		if (drbd_bitmap_io(mdev, &drbd_bm_write,
-			"crashed primary apply AL", BM_LOCKED_MASK)) {
-			retcode = ERR_IO_MD_DISK;
-			goto force_diskless_dec;
-		}
-	}
-
 	if (_drbd_bm_total_weight(mdev) == drbd_bm_bits(mdev))
 		drbd_suspend_al(mdev); /* IO is still suspended here... */
 
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index f51cefdbeff3..c4d0d96d7906 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1017,6 +1017,7 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
 						 MDF_CONNECTED_IND|MDF_WAS_UP_TO_DATE|
 						 MDF_PEER_OUT_DATED|MDF_CRASHED_PRIMARY);
 
+		mdf &= ~MDF_AL_CLEAN;
 		if (test_bit(CRASHED_PRIMARY, &mdev->flags))
 			mdf |= MDF_CRASHED_PRIMARY;
 		if (mdev->state.role == R_PRIMARY ||
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 161cd414b036..1e9f754b66ac 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -162,6 +162,7 @@ enum drbd_ret_code {
 	ERR_INVALID_REQUEST	= 162,
 	ERR_NEED_APV_100	= 163,
 	ERR_NEED_ALLOW_TWO_PRI  = 164,
+	ERR_MD_UNCLEAN          = 165,
 
 	/* insert new ones above this line */
 	AFTER_LAST_ERR_CODE
@@ -321,7 +322,8 @@ extern const char *drbd_set_st_err_str(enum drbd_state_rv);
 #define MDF_FULL_SYNC		(1 << 3)
 #define MDF_WAS_UP_TO_DATE	(1 << 4)
 #define MDF_PEER_OUT_DATED	(1 << 5)
-#define MDF_CRASHED_PRIMARY     (1 << 6)
+#define MDF_CRASHED_PRIMARY	(1 << 6)
+#define MDF_AL_CLEAN		(1 << 7)
 
 enum drbd_uuid_index {
 	UI_CURRENT,
@@ -341,10 +343,16 @@ enum drbd_timeout_flag {
 
 #define UUID_JUST_CREATED ((__u64)4)
 
+/* magic numbers used in meta data and network packets */
 #define DRBD_MAGIC 0x83740267
 #define DRBD_MAGIC_BIG 0x835a
 #define DRBD_MAGIC_100 0x8620ec20
 
+#define DRBD_MD_MAGIC_07   (DRBD_MAGIC+3)
+#define DRBD_MD_MAGIC_08   (DRBD_MAGIC+4)
+#define DRBD_MD_MAGIC_84_UNCLEAN	(DRBD_MAGIC+5)
+
+
 /* how I came up with this magic?
  * base64 decode "actlog==" ;) */
 #define DRBD_AL_MAGIC 0x69cb65a2
-- 
cgit v1.2.3-55-g7522


From 65d94927e036cd8e8e1406fa7fc387b4ae730159 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Wed, 13 Jul 2011 10:24:51 +0200
Subject: drbd: Changed some defaults

* Enabled the resync controller, with a fill target of 50Kib. That gives
  reasonable resync speeds without tuning. A much better default than
  the 250KiB/s fixed.

* Enable bitmap compression. It is save to use, and most people have
  more CPU power than network bandwidth.

* ko-count of 7: Abort a connection if the peer fails to process a
  write request within 42 seconds.

* al-extents of 1237: ~5 GiB seems to be a much more sane default
  these days.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_limits.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index ddd332db2a5d..defdebfecb72 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -16,7 +16,7 @@
 #define DEBUG_RANGE_CHECK 0
 
 #define DRBD_MINOR_COUNT_MIN 1
-#define DRBD_MINOR_COUNT_MAX 256
+#define DRBD_MINOR_COUNT_MAX (1U << 20)
 #define DRBD_MINOR_COUNT_DEF 32
 
 #define DRBD_VOLUME_MAX 65535
@@ -99,7 +99,7 @@
    * 200 should be more than enough even for very short timeouts */
 #define DRBD_KO_COUNT_MIN  0
 #define DRBD_KO_COUNT_MAX  200
-#define DRBD_KO_COUNT_DEF  0
+#define DRBD_KO_COUNT_DEF  7
 /* } */
 
 /* syncer { */
@@ -117,7 +117,7 @@
    * 919 * 7 = 6433 */
 #define DRBD_AL_EXTENTS_MIN  7
 #define DRBD_AL_EXTENTS_MAX  6433
-#define DRBD_AL_EXTENTS_DEF  127
+#define DRBD_AL_EXTENTS_DEF  1237
 
 #define DRBD_MINOR_NUMBER_MIN  -1
 #define DRBD_MINOR_NUMBER_MAX  (1<<30)
@@ -151,7 +151,7 @@
 
 #define DRBD_C_PLAN_AHEAD_MIN  0
 #define DRBD_C_PLAN_AHEAD_MAX  300
-#define DRBD_C_PLAN_AHEAD_DEF  0 /* RS rate controller disabled by default */
+#define DRBD_C_PLAN_AHEAD_DEF  20
 
 #define DRBD_C_DELAY_TARGET_MIN 1
 #define DRBD_C_DELAY_TARGET_MAX 100
@@ -159,7 +159,7 @@
 
 #define DRBD_C_FILL_TARGET_MIN 0
 #define DRBD_C_FILL_TARGET_MAX (1<<20) /* 500MByte in sec */
-#define DRBD_C_FILL_TARGET_DEF 0 /* By default disabled -> controlled by delay_target */
+#define DRBD_C_FILL_TARGET_DEF 100 /* Try to place 50KiB in socket send buffer during resync */
 
 #define DRBD_C_MAX_RATE_MIN     250 /* kByte/sec */
 #define DRBD_C_MAX_RATE_MAX     (4 << 20)
@@ -167,7 +167,7 @@
 
 #define DRBD_C_MIN_RATE_MIN     0 /* kByte/sec */
 #define DRBD_C_MIN_RATE_MAX     (4 << 20)
-#define DRBD_C_MIN_RATE_DEF     4096
+#define DRBD_C_MIN_RATE_DEF     250
 
 #define DRBD_CONG_FILL_MIN	0
 #define DRBD_CONG_FILL_MAX	(10<<21) /* 10GByte in sectors */
@@ -187,6 +187,6 @@
 
 #define DRBD_ALLOW_TWO_PRIMARIES_DEF	0
 #define DRBD_ALWAYS_ASBP_DEF	0
-#define DRBD_USE_RLE_DEF	0
+#define DRBD_USE_RLE_DEF	1
 
 #endif
-- 
cgit v1.2.3-55-g7522


From 32bdb64038ba3127245912dae2cc8a450bb1d705 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Mon, 9 May 2011 18:26:20 +0200
Subject: drbd: Define scale factors in a single place

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_limits.h | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index defdebfecb72..cd3565cfed44 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -18,29 +18,35 @@
 #define DRBD_MINOR_COUNT_MIN 1
 #define DRBD_MINOR_COUNT_MAX (1U << 20)
 #define DRBD_MINOR_COUNT_DEF 32
+#define DRBD_MINOR_COUNT_SCALE '1'
 
 #define DRBD_VOLUME_MAX 65535
 
 #define DRBD_DIALOG_REFRESH_MIN 0
 #define DRBD_DIALOG_REFRESH_MAX 600
+#define DRBD_DIALOG_REFRESH_SCALE '1'
 
 /* valid port number */
 #define DRBD_PORT_MIN 1
 #define DRBD_PORT_MAX 0xffff
+#define DRBD_PORT_SCALE '1'
 
 /* startup { */
   /* if you want more than 3.4 days, disable */
 #define DRBD_WFC_TIMEOUT_MIN 0
 #define DRBD_WFC_TIMEOUT_MAX 300000
 #define DRBD_WFC_TIMEOUT_DEF 0
+#define DRBD_WFC_TIMEOUT_SCALE '1'
 
 #define DRBD_DEGR_WFC_TIMEOUT_MIN 0
 #define DRBD_DEGR_WFC_TIMEOUT_MAX 300000
 #define DRBD_DEGR_WFC_TIMEOUT_DEF 0
+#define DRBD_DEGR_WFC_TIMEOUT_SCALE '1'
 
 #define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0
 #define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000
 #define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0
+#define DRBD_OUTDATED_WFC_TIMEOUT_SCALE '1'
 /* }*/
 
 /* net { */
@@ -49,6 +55,7 @@
 #define DRBD_TIMEOUT_MIN 1
 #define DRBD_TIMEOUT_MAX 600
 #define DRBD_TIMEOUT_DEF 60       /* 6 seconds */
+#define DRBD_TIMEOUT_SCALE '1'
 
  /* If backing disk takes longer than disk_timeout, mark the disk as failed */
 #define DRBD_DISK_TIMEOUT_MIN 0    /* 0 = disabled */
@@ -60,46 +67,55 @@
 #define DRBD_CONNECT_INT_MIN 1
 #define DRBD_CONNECT_INT_MAX 120
 #define DRBD_CONNECT_INT_DEF 10   /* seconds */
+#define DRBD_CONNECT_INT_SCALE '1'
 
   /* keep-alive probes when idle */
 #define DRBD_PING_INT_MIN 1
 #define DRBD_PING_INT_MAX 120
 #define DRBD_PING_INT_DEF 10
+#define DRBD_PING_INT_SCALE '1'
 
  /* timeout for the ping packets.*/
 #define DRBD_PING_TIMEO_MIN  1
 #define DRBD_PING_TIMEO_MAX  300
 #define DRBD_PING_TIMEO_DEF  5
+#define DRBD_PING_TIMEO_SCALE '1'
 
   /* max number of write requests between write barriers */
 #define DRBD_MAX_EPOCH_SIZE_MIN 1
 #define DRBD_MAX_EPOCH_SIZE_MAX 20000
 #define DRBD_MAX_EPOCH_SIZE_DEF 2048
+#define DRBD_MAX_EPOCH_SIZE_SCALE '1'
 
   /* I don't think that a tcp send buffer of more than 10M is useful */
 #define DRBD_SNDBUF_SIZE_MIN  0
 #define DRBD_SNDBUF_SIZE_MAX  (10<<20)
 #define DRBD_SNDBUF_SIZE_DEF  0
+#define DRBD_SNDBUF_SIZE_SCALE '1'
 
 #define DRBD_RCVBUF_SIZE_MIN  0
 #define DRBD_RCVBUF_SIZE_MAX  (10<<20)
 #define DRBD_RCVBUF_SIZE_DEF  0
+#define DRBD_RCVBUF_SIZE_SCALE '1'
 
   /* @4k PageSize -> 128kB - 512MB */
 #define DRBD_MAX_BUFFERS_MIN  32
 #define DRBD_MAX_BUFFERS_MAX  131072
 #define DRBD_MAX_BUFFERS_DEF  2048
+#define DRBD_MAX_BUFFERS_SCALE '1'
 
   /* @4k PageSize -> 4kB - 512MB */
 #define DRBD_UNPLUG_WATERMARK_MIN  1
 #define DRBD_UNPLUG_WATERMARK_MAX  131072
 #define DRBD_UNPLUG_WATERMARK_DEF (DRBD_MAX_BUFFERS_DEF/16)
+#define DRBD_UNPLUG_WATERMARK_SCALE '1'
 
   /* 0 is disabled.
    * 200 should be more than enough even for very short timeouts */
 #define DRBD_KO_COUNT_MIN  0
 #define DRBD_KO_COUNT_MAX  200
 #define DRBD_KO_COUNT_DEF  7
+#define DRBD_KO_COUNT_SCALE '1'
 /* } */
 
 /* syncer { */
@@ -118,6 +134,7 @@
 #define DRBD_AL_EXTENTS_MIN  7
 #define DRBD_AL_EXTENTS_MAX  6433
 #define DRBD_AL_EXTENTS_DEF  1237
+#define DRBD_AL_EXTENTS_SCALE '1'
 
 #define DRBD_MINOR_NUMBER_MIN  -1
 #define DRBD_MINOR_NUMBER_MAX  (1<<30)
@@ -148,34 +165,42 @@
 #define DRBD_MAX_BIO_BVECS_MIN 0
 #define DRBD_MAX_BIO_BVECS_MAX 128
 #define DRBD_MAX_BIO_BVECS_DEF 0
+#define DRBD_MAX_BIO_BVECS_SCALE '1'
 
 #define DRBD_C_PLAN_AHEAD_MIN  0
 #define DRBD_C_PLAN_AHEAD_MAX  300
 #define DRBD_C_PLAN_AHEAD_DEF  20
+#define DRBD_C_PLAN_AHEAD_SCALE '1'
 
 #define DRBD_C_DELAY_TARGET_MIN 1
 #define DRBD_C_DELAY_TARGET_MAX 100
 #define DRBD_C_DELAY_TARGET_DEF 10
+#define DRBD_C_DELAY_TARGET_SCALE '1'
 
 #define DRBD_C_FILL_TARGET_MIN 0
 #define DRBD_C_FILL_TARGET_MAX (1<<20) /* 500MByte in sec */
 #define DRBD_C_FILL_TARGET_DEF 100 /* Try to place 50KiB in socket send buffer during resync */
+#define DRBD_C_FILL_TARGET_SCALE 's'  /* sectors */
 
-#define DRBD_C_MAX_RATE_MIN     250 /* kByte/sec */
+#define DRBD_C_MAX_RATE_MIN     250
 #define DRBD_C_MAX_RATE_MAX     (4 << 20)
 #define DRBD_C_MAX_RATE_DEF     102400
+#define DRBD_C_MAX_RATE_SCALE	'k'  /* kilobytes */
 
-#define DRBD_C_MIN_RATE_MIN     0 /* kByte/sec */
+#define DRBD_C_MIN_RATE_MIN     0
 #define DRBD_C_MIN_RATE_MAX     (4 << 20)
 #define DRBD_C_MIN_RATE_DEF     250
+#define DRBD_C_MIN_RATE_SCALE	'k'  /* kilobytes */
 
 #define DRBD_CONG_FILL_MIN	0
 #define DRBD_CONG_FILL_MAX	(10<<21) /* 10GByte in sectors */
 #define DRBD_CONG_FILL_DEF	0
+#define DRBD_CONG_FILL_SCALE	's'  /* sectors */
 
 #define DRBD_CONG_EXTENTS_MIN	DRBD_AL_EXTENTS_MIN
 #define DRBD_CONG_EXTENTS_MAX	DRBD_AL_EXTENTS_MAX
 #define DRBD_CONG_EXTENTS_DEF	DRBD_AL_EXTENTS_DEF
+#define DRBD_CONG_EXTENTS_SCALE DRBD_AL_EXTENTS_SCALE
 
 #define DRBD_PROTOCOL_DEF DRBD_PROT_C
 
-- 
cgit v1.2.3-55-g7522


From 0317d9ecbc9bac43642b4aa70e3e1106f4fd26a1 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 13 Jul 2011 13:40:30 +0200
Subject: drbd: Fix the maximum accepted minor device number

The maximum minor device number allowed by the kernel is (1<<20 - 1).  Reject
device numbers higher than that to earlier catch possible errors.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_limits.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index cd3565cfed44..7d956e91ae7b 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -137,7 +137,7 @@
 #define DRBD_AL_EXTENTS_SCALE '1'
 
 #define DRBD_MINOR_NUMBER_MIN  -1
-#define DRBD_MINOR_NUMBER_MAX  (1<<30)
+#define DRBD_MINOR_NUMBER_MAX  ((1 << 20) - 1)
 #define DRBD_MINOR_NUMBER_DEF  -1
 #define DRBD_MINOR_NUMBER_SCALE '1'
 
-- 
cgit v1.2.3-55-g7522


From b80c043327ea4faac62a329a1d35f16c47a5128e Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Mon, 18 Jul 2011 11:09:17 +0200
Subject: drbd: The minor_count module parameter is only a hint nowadays

* The max of minor_count is 255
* In drbdadm count the number of minors, instead of finding
  the highest minor number
* No longer us the magic in the init script

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 include/linux/drbd_limits.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 7d956e91ae7b..6d0a24331ed2 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -16,7 +16,7 @@
 #define DEBUG_RANGE_CHECK 0
 
 #define DRBD_MINOR_COUNT_MIN 1
-#define DRBD_MINOR_COUNT_MAX (1U << 20)
+#define DRBD_MINOR_COUNT_MAX 255
 #define DRBD_MINOR_COUNT_DEF 32
 #define DRBD_MINOR_COUNT_SCALE '1'
 
-- 
cgit v1.2.3-55-g7522


From 380207d08e7c4d1b19c0323777278992b4fbf9d6 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Fri, 11 Nov 2011 12:31:20 +0100
Subject: drbd: Load balancing of read requests

New config option for the disk secition "read-balancing", with
the values: prefer-local, prefer-remote, round-robin, when-congested-remote.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h      |  1 +
 drivers/block/drbd/drbd_receiver.c |  2 +-
 drivers/block/drbd/drbd_req.c      | 57 +++++++++++++++++++++++++++++++++++++-
 include/linux/drbd.h               |  8 ++++++
 include/linux/drbd_genl.h          |  1 +
 include/linux/drbd_limits.h        |  1 +
 6 files changed, 68 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index d397681fb7aa..e2cccb40f5af 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -698,6 +698,7 @@ enum {
 	AHEAD_TO_SYNC_SOURCE,   /* Ahead -> SyncSource queued */
 	B_RS_H_DONE,		/* Before resync handler done (already executed) */
 	DISCARD_MY_DATA,	/* discard_my_data flag per volume */
+	READ_BALANCE_RR,
 };
 
 struct drbd_bitmap; /* opaque for drbd_conf */
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index e546dd3fab8a..733b8bd663d5 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -4974,7 +4974,7 @@ static int got_NegDReply(struct drbd_tconn *tconn, struct packet_info *pi)
 
 	update_peer_seq(mdev, be32_to_cpu(p->seq_num));
 
-	dev_err(DEV, "Got NegDReply; Sector %llus, len %u; Fail original request.\n",
+	dev_err(DEV, "Got NegDReply; Sector %llus, len %u.\n",
 	    (unsigned long long)sector, be32_to_cpu(p->blksize));
 
 	return validate_req_change_req_state(mdev, p->block_id, sector,
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index ceb04a94aace..98251e2a7fb7 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -563,6 +563,11 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		if (req->rq_state & RQ_NET_SENT && req->rq_state & RQ_WRITE)
 			atomic_sub(req->i.size >> 9, &mdev->ap_in_flight);
 
+		if (!(req->rq_state & RQ_WRITE) &&
+		    mdev->state.disk == D_UP_TO_DATE &&
+		    !IS_ERR_OR_NULL(req->private_bio))
+			goto goto_read_retry_local;
+
 		/* if it is still queued, we may not complete it here.
 		 * it will be canceled soon. */
 		if (!(req->rq_state & RQ_NET_QUEUED))
@@ -625,10 +630,22 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		req->rq_state &= ~(RQ_NET_OK|RQ_NET_PENDING);
 
 		req->rq_state |= RQ_NET_DONE;
+
+		if (!(req->rq_state & RQ_WRITE) &&
+		    mdev->state.disk == D_UP_TO_DATE &&
+		    !IS_ERR_OR_NULL(req->private_bio))
+			goto goto_read_retry_local;
+
 		_req_may_be_done_not_susp(req, m);
 		/* else: done by HANDED_OVER_TO_NETWORK */
 		break;
 
+	goto_read_retry_local:
+		req->rq_state |= RQ_LOCAL_PENDING;
+		req->private_bio->bi_bdev = mdev->ldev->backing_bdev;
+		generic_make_request(req->private_bio);
+		break;
+
 	case FAIL_FROZEN_DISK_IO:
 		if (!(req->rq_state & RQ_LOCAL_COMPLETED))
 			break;
@@ -689,6 +706,11 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		dec_ap_pending(mdev);
 		req->rq_state &= ~RQ_NET_PENDING;
 		req->rq_state |= (RQ_NET_OK|RQ_NET_DONE);
+		if (!IS_ERR_OR_NULL(req->private_bio)) {
+			bio_put(req->private_bio);
+			req->private_bio = NULL;
+			put_ldev(mdev);
+		}
 		_req_may_be_done_not_susp(req, m);
 		break;
 	};
@@ -723,6 +745,35 @@ static bool drbd_may_do_local_read(struct drbd_conf *mdev, sector_t sector, int
 	return drbd_bm_count_bits(mdev, sbnr, ebnr) == 0;
 }
 
+static bool remote_due_to_read_balancing(struct drbd_conf *mdev)
+{
+	enum drbd_read_balancing rbm;
+	struct backing_dev_info *bdi;
+
+	if (mdev->state.pdsk < D_UP_TO_DATE)
+		return false;
+
+	rcu_read_lock();
+	rbm = rcu_dereference(mdev->ldev->disk_conf)->read_balancing;
+	rcu_read_unlock();
+
+	switch (rbm) {
+	case RB_CONGESTED_REMOTE:
+		bdi = &mdev->ldev->backing_bdev->bd_disk->queue->backing_dev_info;
+		return bdi_read_congested(bdi);
+	case RB_LEAST_PENDING:
+		return atomic_read(&mdev->local_cnt) >
+			atomic_read(&mdev->ap_pending_cnt) + atomic_read(&mdev->rs_pending_cnt);
+	case RB_ROUND_ROBIN:
+		return test_and_change_bit(READ_BALANCE_RR, &mdev->flags);
+	case RB_PREFER_REMOTE:
+		return true;
+	case RB_PREFER_LOCAL:
+	default:
+		return false;
+	}
+}
+
 /*
  * complete_conflicting_writes  -  wait for any conflicting write requests
  *
@@ -790,6 +841,10 @@ int __drbd_make_request(struct drbd_conf *mdev, struct bio *bio, unsigned long s
 				bio_put(req->private_bio);
 				req->private_bio = NULL;
 				put_ldev(mdev);
+			} else if (remote_due_to_read_balancing(mdev)) {
+				/* Keep the private bio in case we need it
+				   for a local retry */
+				local = 0;
 			}
 		}
 		remote = !local && mdev->state.pdsk >= D_UP_TO_DATE;
@@ -1017,7 +1072,7 @@ fail_free_complete:
 	if (req->rq_state & RQ_IN_ACT_LOG)
 		drbd_al_complete_io(mdev, &req->i);
 fail_and_free_req:
-	if (local) {
+	if (!IS_ERR_OR_NULL(req->private_bio)) {
 		bio_put(req->private_bio);
 		req->private_bio = NULL;
 		put_ldev(mdev);
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 1e9f754b66ac..157ba3d74dc7 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -102,6 +102,14 @@ enum drbd_on_congestion {
 	OC_DISCONNECT,
 };
 
+enum drbd_read_balancing {
+	RB_PREFER_LOCAL,
+	RB_PREFER_REMOTE,
+	RB_ROUND_ROBIN,
+	RB_LEAST_PENDING,
+	RB_CONGESTED_REMOTE,
+};
+
 /* KEEP the order, do not delete or insert. Only append. */
 enum drbd_ret_code {
 	ERR_CODE_BASE		= 100,
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 2e6cefefe5e5..826008f297fe 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -129,6 +129,7 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__flg_field_def(18, DRBD_GENLA_F_MANDATORY,	disk_drain, DRBD_DISK_DRAIN_DEF)
 	__flg_field_def(19, DRBD_GENLA_F_MANDATORY,	md_flushes, DRBD_MD_FLUSHES_DEF)
 	__u32_field_def(20,	DRBD_GENLA_F_MANDATORY,	disk_timeout, DRBD_DISK_TIMEOUT_DEF)
+	__u32_field_def(21,	0 /* OPTIONAL */,       read_balancing, DRBD_READ_BALANCING_DEF)
 )
 
 GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 6d0a24331ed2..17ef66a5c114 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -161,6 +161,7 @@
 #define DRBD_RR_CONFLICT_DEF ASB_DISCONNECT
 #define DRBD_ON_NO_DATA_DEF OND_IO_ERROR
 #define DRBD_ON_CONGESTION_DEF OC_BLOCK
+#define DRBD_READ_BALANCING_DEF RB_PREFER_LOCAL
 
 #define DRBD_MAX_BIO_BVECS_MIN 0
 #define DRBD_MAX_BIO_BVECS_MAX 128
-- 
cgit v1.2.3-55-g7522


From d60de03a6694302b691bdf858ede9cbdfb7112d6 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Thu, 17 Nov 2011 10:12:31 +0100
Subject: drbd: Load balancing method: striping

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_req.c | 13 +++++++++++--
 include/linux/drbd.h          |  6 ++++++
 2 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 98251e2a7fb7..5b28de0c5960 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -745,10 +745,11 @@ static bool drbd_may_do_local_read(struct drbd_conf *mdev, sector_t sector, int
 	return drbd_bm_count_bits(mdev, sbnr, ebnr) == 0;
 }
 
-static bool remote_due_to_read_balancing(struct drbd_conf *mdev)
+static bool remote_due_to_read_balancing(struct drbd_conf *mdev, sector_t sector)
 {
 	enum drbd_read_balancing rbm;
 	struct backing_dev_info *bdi;
+	int stripe_shift;
 
 	if (mdev->state.pdsk < D_UP_TO_DATE)
 		return false;
@@ -764,6 +765,14 @@ static bool remote_due_to_read_balancing(struct drbd_conf *mdev)
 	case RB_LEAST_PENDING:
 		return atomic_read(&mdev->local_cnt) >
 			atomic_read(&mdev->ap_pending_cnt) + atomic_read(&mdev->rs_pending_cnt);
+	case RB_32K_STRIPING:  /* stripe_shift = 15 */
+	case RB_64K_STRIPING:
+	case RB_128K_STRIPING:
+	case RB_256K_STRIPING:
+	case RB_512K_STRIPING:
+	case RB_1M_STRIPING:   /* stripe_shift = 20 */
+		stripe_shift = (rbm - RB_32K_STRIPING + 15);
+		return (sector >> (stripe_shift - 9)) & 1;
 	case RB_ROUND_ROBIN:
 		return test_and_change_bit(READ_BALANCE_RR, &mdev->flags);
 	case RB_PREFER_REMOTE:
@@ -841,7 +850,7 @@ int __drbd_make_request(struct drbd_conf *mdev, struct bio *bio, unsigned long s
 				bio_put(req->private_bio);
 				req->private_bio = NULL;
 				put_ldev(mdev);
-			} else if (remote_due_to_read_balancing(mdev)) {
+			} else if (remote_due_to_read_balancing(mdev, sector)) {
 				/* Keep the private bio in case we need it
 				   for a local retry */
 				local = 0;
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 157ba3d74dc7..1e86156c10f7 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -108,6 +108,12 @@ enum drbd_read_balancing {
 	RB_ROUND_ROBIN,
 	RB_LEAST_PENDING,
 	RB_CONGESTED_REMOTE,
+	RB_32K_STRIPING,
+	RB_64K_STRIPING,
+	RB_128K_STRIPING,
+	RB_256K_STRIPING,
+	RB_512K_STRIPING,
+	RB_1M_STRIPING,
 };
 
 /* KEEP the order, do not delete or insert. Only append. */
-- 
cgit v1.2.3-55-g7522


From 26ec92871be1e6bd48d0be9ab38ee1ebbeea49f1 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher
Date: Wed, 11 Jul 2012 20:36:03 +0200
Subject: drbd: Stop using NLA_PUT*().

These macros no longer exist in kernel version v3.5-rc1.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c      | 54 +++++++++++++++++++++++----------------
 include/linux/genl_magic_func.h   |  8 +++---
 include/linux/genl_magic_struct.h | 16 ++++++------
 3 files changed, 45 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index cbd45de533cb..dc5bd6bbb280 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2554,13 +2554,17 @@ int nla_put_drbd_cfg_context(struct sk_buff *skb, struct drbd_tconn *tconn, unsi
 	nla = nla_nest_start(skb, DRBD_NLA_CFG_CONTEXT);
 	if (!nla)
 		goto nla_put_failure;
-	if (vnr != VOLUME_UNSPECIFIED)
-		NLA_PUT_U32(skb, T_ctx_volume, vnr);
-	NLA_PUT_STRING(skb, T_ctx_resource_name, tconn->name);
-	if (tconn->my_addr_len)
-		NLA_PUT(skb, T_ctx_my_addr, tconn->my_addr_len, &tconn->my_addr);
-	if (tconn->peer_addr_len)
-		NLA_PUT(skb, T_ctx_peer_addr, tconn->peer_addr_len, &tconn->peer_addr);
+	if (vnr != VOLUME_UNSPECIFIED &&
+	    nla_put_u32(skb, T_ctx_volume, vnr))
+		goto nla_put_failure;
+	if (nla_put_string(skb, T_ctx_resource_name, tconn->name))
+		goto nla_put_failure;
+	if (tconn->my_addr_len &&
+	    nla_put(skb, T_ctx_my_addr, tconn->my_addr_len, &tconn->my_addr))
+		goto nla_put_failure;
+	if (tconn->peer_addr_len &&
+	    nla_put(skb, T_ctx_peer_addr, tconn->peer_addr_len, &tconn->peer_addr))
+		goto nla_put_failure;
 	nla_nest_end(skb, nla);
 	return 0;
 
@@ -2618,20 +2622,23 @@ int nla_put_status_info(struct sk_buff *skb, struct drbd_conf *mdev,
 	nla = nla_nest_start(skb, DRBD_NLA_STATE_INFO);
 	if (!nla)
 		goto nla_put_failure;
-	NLA_PUT_U32(skb, T_sib_reason, sib ? sib->sib_reason : SIB_GET_STATUS_REPLY);
-	NLA_PUT_U32(skb, T_current_state, mdev->state.i);
-	NLA_PUT_U64(skb, T_ed_uuid, mdev->ed_uuid);
-	NLA_PUT_U64(skb, T_capacity, drbd_get_capacity(mdev->this_bdev));
+	if (nla_put_u32(skb, T_sib_reason, sib ? sib->sib_reason : SIB_GET_STATUS_REPLY) ||
+	    nla_put_u32(skb, T_current_state, mdev->state.i) ||
+	    nla_put_u64(skb, T_ed_uuid, mdev->ed_uuid) ||
+	    nla_put_u64(skb, T_capacity, drbd_get_capacity(mdev->this_bdev)))
+		goto nla_put_failure;
 
 	if (got_ldev) {
-		NLA_PUT_U32(skb, T_disk_flags, mdev->ldev->md.flags);
-		NLA_PUT(skb, T_uuids, sizeof(si->uuids), mdev->ldev->md.uuid);
-		NLA_PUT_U64(skb, T_bits_total, drbd_bm_bits(mdev));
-		NLA_PUT_U64(skb, T_bits_oos, drbd_bm_total_weight(mdev));
+		if (nla_put_u32(skb, T_disk_flags, mdev->ldev->md.flags) ||
+		    nla_put(skb, T_uuids, sizeof(si->uuids), mdev->ldev->md.uuid) ||
+		    nla_put_u64(skb, T_bits_total, drbd_bm_bits(mdev)) ||
+		    nla_put_u64(skb, T_bits_oos, drbd_bm_total_weight(mdev)))
+			goto nla_put_failure;
 		if (C_SYNC_SOURCE <= mdev->state.conn &&
 		    C_PAUSED_SYNC_T >= mdev->state.conn) {
-			NLA_PUT_U64(skb, T_bits_rs_total, mdev->rs_total);
-			NLA_PUT_U64(skb, T_bits_rs_failed, mdev->rs_failed);
+			if (nla_put_u64(skb, T_bits_rs_total, mdev->rs_total) ||
+			    nla_put_u64(skb, T_bits_rs_failed, mdev->rs_failed))
+				goto nla_put_failure;
 		}
 	}
 
@@ -2641,15 +2648,18 @@ int nla_put_status_info(struct sk_buff *skb, struct drbd_conf *mdev,
 		case SIB_GET_STATUS_REPLY:
 			break;
 		case SIB_STATE_CHANGE:
-			NLA_PUT_U32(skb, T_prev_state, sib->os.i);
-			NLA_PUT_U32(skb, T_new_state, sib->ns.i);
+			if (nla_put_u32(skb, T_prev_state, sib->os.i) ||
+			    nla_put_u32(skb, T_new_state, sib->ns.i))
+				goto nla_put_failure;
 			break;
 		case SIB_HELPER_POST:
-			NLA_PUT_U32(skb,
-				T_helper_exit_code, sib->helper_exit_code);
+			if (nla_put_u32(skb, T_helper_exit_code,
+					sib->helper_exit_code))
+				goto nla_put_failure;
 			/* fall through */
 		case SIB_HELPER_PRE:
-			NLA_PUT_STRING(skb, T_helper, sib->helper_name);
+			if (nla_put_string(skb, T_helper, sib->helper_name))
+				goto nla_put_failure;
 			break;
 		}
 	}
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 0b8a88e2e83e..023bc346b877 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -367,7 +367,8 @@ static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb,		\
 		__is_signed)						\
 	if (!exclude_sensitive || !((attr_flag) & DRBD_F_SENSITIVE)) {	\
 		DPRINT_FIELD(">>", nla_type, name, s, NULL);		\
-		__put(skb, attr_nr, s->name);				\
+		if (__put(skb, attr_nr, s->name))			\
+			goto nla_put_failure;				\
 	}
 
 #undef __array
@@ -375,9 +376,10 @@ static inline int s_name ## _to_unpriv_skb(struct sk_buff *skb,		\
 		__get, __put, __is_signed)				\
 	if (!exclude_sensitive || !((attr_flag) & DRBD_F_SENSITIVE)) {	\
 		DPRINT_ARRAY(">>",nla_type, name, s, NULL);		\
-		__put(skb, attr_nr, min_t(int, maxlen,			\
+		if (__put(skb, attr_nr, min_t(int, maxlen,		\
 			s->name ## _len + (nla_type == NLA_NUL_STRING)),\
-						s->name);		\
+						s->name))		\
+			goto nla_put_failure;				\
 	}
 
 #include GENL_MAGIC_INCLUDE_FILE
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index 1d0bd79e27b3..eecd19b37001 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -65,28 +65,28 @@ extern void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void);
 /* possible field types */
 #define __flg_field(attr_nr, attr_flag, name) \
 	__field(attr_nr, attr_flag, name, NLA_U8, char, \
-			nla_get_u8, NLA_PUT_U8, false)
+			nla_get_u8, nla_put_u8, false)
 #define __u8_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U8, unsigned char, \
-			nla_get_u8, NLA_PUT_U8, false)
+			nla_get_u8, nla_put_u8, false)
 #define __u16_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U16, __u16, \
-			nla_get_u16, NLA_PUT_U16, false)
+			nla_get_u16, nla_put_u16, false)
 #define __u32_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U32, __u32, \
-			nla_get_u32, NLA_PUT_U32, false)
+			nla_get_u32, nla_put_u32, false)
 #define __s32_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U32, __s32, \
-			nla_get_u32, NLA_PUT_U32, true)
+			nla_get_u32, nla_put_u32, true)
 #define __u64_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U64, __u64, \
-			nla_get_u64, NLA_PUT_U64, false)
+			nla_get_u64, nla_put_u64, false)
 #define __str_field(attr_nr, attr_flag, name, maxlen) \
 	__array(attr_nr, attr_flag, name, NLA_NUL_STRING, char, maxlen, \
-			nla_strlcpy, NLA_PUT, false)
+			nla_strlcpy, nla_put, false)
 #define __bin_field(attr_nr, attr_flag, name, maxlen) \
 	__array(attr_nr, attr_flag, name, NLA_BINARY, char, maxlen, \
-			nla_memcpy, NLA_PUT, false)
+			nla_memcpy, nla_put, false)
 
 /* fields with default values */
 #define __flg_field_def(attr_nr, attr_flag, name, default) \
-- 
cgit v1.2.3-55-g7522


From 9a51ab1c1b3c1e21f076cdd571bbe6ca7d1b504c Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Mon, 20 Feb 2012 21:53:28 +0100
Subject: drbd: New disk option al-updates

By disabling al-updates one might increase performace. The price for
that is that in case a crashed primary (that had al-updates disabled)
is reintegraded, it will receive a full-resync instead of a bitmap
based resync.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_actlog.c | 12 ++++++++++--
 drivers/block/drbd/drbd_nl.c     | 17 +++++++++++++++--
 include/linux/drbd.h             |  1 +
 include/linux/drbd_genl.h        |  3 +++
 include/linux/drbd_limits.h      |  1 +
 5 files changed, 30 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 9eae28944312..83d48d210b69 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -276,8 +276,16 @@ void drbd_al_begin_io(struct drbd_conf *mdev, struct drbd_interval *i)
 		/* Double check: it may have been committed by someone else,
 		 * while we have been waiting for the lock. */
 		if (mdev->act_log->pending_changes) {
-			al_write_transaction(mdev);
-			mdev->al_writ_cnt++;
+			bool write_al_updates;
+
+			rcu_read_lock();
+			write_al_updates = rcu_dereference(mdev->ldev->disk_conf)->al_updates;
+			rcu_read_unlock();
+
+			if (write_al_updates) {
+				al_write_transaction(mdev);
+				mdev->al_writ_cnt++;
+			}
 
 			spin_lock_irq(&mdev->al_lock);
 			/* FIXME
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index dc5bd6bbb280..c5d4fac1a111 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1230,6 +1230,11 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 
 	mutex_unlock(&mdev->tconn->conf_update);
 
+	if (new_disk_conf->al_updates)
+		mdev->ldev->md.flags &= MDF_AL_DISABLED;
+	else
+		mdev->ldev->md.flags |= MDF_AL_DISABLED;
+
 	drbd_bump_write_ordering(mdev->tconn, WO_bdev_flush);
 
 	drbd_md_sync(mdev);
@@ -1545,7 +1550,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	} else if (dd == grew)
 		set_bit(RESYNC_AFTER_NEG, &mdev->flags);
 
-	if (drbd_md_test_flag(mdev->ldev, MDF_FULL_SYNC)) {
+	if (drbd_md_test_flag(mdev->ldev, MDF_FULL_SYNC) ||
+	    (test_bit(CRASHED_PRIMARY, &mdev->flags) &&
+	     drbd_md_test_flag(mdev->ldev, MDF_AL_DISABLED))) {
 		dev_info(DEV, "Assuming that all blocks are out of sync "
 		     "(aka FullSync)\n");
 		if (drbd_bitmap_io(mdev, &drbd_bmio_set_n_write,
@@ -1588,13 +1595,19 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	if (ns.disk == D_CONSISTENT &&
 	    (ns.pdsk == D_OUTDATED || rcu_dereference(mdev->ldev->disk_conf)->fencing == FP_DONT_CARE))
 		ns.disk = D_UP_TO_DATE;
-	rcu_read_unlock();
 
 	/* All tests on MDF_PRIMARY_IND, MDF_CONNECTED_IND,
 	   MDF_CONSISTENT and MDF_WAS_UP_TO_DATE must happen before
 	   this point, because drbd_request_state() modifies these
 	   flags. */
 
+	if (rcu_dereference(mdev->ldev->disk_conf)->al_updates)
+		mdev->ldev->md.flags &= MDF_AL_DISABLED;
+	else
+		mdev->ldev->md.flags |= MDF_AL_DISABLED;
+
+	rcu_read_unlock();
+
 	/* In case we are C_CONNECTED postpone any decision on the new disk
 	   state after the negotiation phase. */
 	if (mdev->state.conn == C_CONNECTED) {
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 1e86156c10f7..36ae7dd28d90 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -338,6 +338,7 @@ extern const char *drbd_set_st_err_str(enum drbd_state_rv);
 #define MDF_PEER_OUT_DATED	(1 << 5)
 #define MDF_CRASHED_PRIMARY	(1 << 6)
 #define MDF_AL_CLEAN		(1 << 7)
+#define MDF_AL_DISABLED		(1 << 8)
 
 enum drbd_uuid_index {
 	UI_CURRENT,
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 826008f297fe..92ec4b50a885 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -130,6 +130,8 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__flg_field_def(19, DRBD_GENLA_F_MANDATORY,	md_flushes, DRBD_MD_FLUSHES_DEF)
 	__u32_field_def(20,	DRBD_GENLA_F_MANDATORY,	disk_timeout, DRBD_DISK_TIMEOUT_DEF)
 	__u32_field_def(21,	0 /* OPTIONAL */,       read_balancing, DRBD_READ_BALANCING_DEF)
+	/* 9: __u32_field_def(22,	DRBD_GENLA_F_MANDATORY,	unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF) */
+	__flg_field_def(23,     0 /* OPTIONAL */,	al_updates, DRBD_AL_UPDATES_DEF)
 )
 
 GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
@@ -168,6 +170,7 @@ GENL_struct(DRBD_NLA_NET_CONF, 5, net_conf,
 	__flg_field_def(27, DRBD_GENLA_F_MANDATORY,	always_asbp, DRBD_ALWAYS_ASBP_DEF)
 	__flg_field(28, DRBD_GENLA_F_MANDATORY | DRBD_F_INVARIANT,	tentative)
 	__flg_field_def(29,	DRBD_GENLA_F_MANDATORY,	use_rle, DRBD_USE_RLE_DEF)
+	/* 9: __u32_field_def(30,	DRBD_GENLA_F_MANDATORY,	fencing_policy, DRBD_FENCING_DEF) */
 )
 
 GENL_struct(DRBD_NLA_SET_ROLE_PARMS, 6, set_role_parms,
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 17ef66a5c114..1fa19c5f5e64 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -210,6 +210,7 @@
 #define DRBD_DISK_DRAIN_DEF	1
 #define DRBD_MD_FLUSHES_DEF	1
 #define DRBD_TCP_CORK_DEF	1
+#define DRBD_AL_UPDATES_DEF     1
 
 #define DRBD_ALLOW_TWO_PRIMARIES_DEF	0
 #define DRBD_ALWAYS_ASBP_DEF	0
-- 
cgit v1.2.3-55-g7522


From 37be2f59d3149b95afaeeeff94edde2c07f165d2 Mon Sep 17 00:00:00 2001
From: Eric Sandeen
Date: Thu, 8 Nov 2012 11:22:46 -0500
Subject: ext4: remove ext4_handle_release_buffer()

ext4_handle_release_buffer() was intended to remove journal
write access from a buffer, but it doesn't actually do anything
at all other than add a BUFFER_TRACE point, but it's not reliably
used for that either.  Remove all the associated dead code.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/ext4/ext4_jbd2.h   |  7 -------
 fs/ext4/resize.c      | 17 +++--------------
 fs/ext4/xattr.c       |  1 -
 fs/jbd2/journal.c     |  1 -
 fs/jbd2/transaction.c | 11 -----------
 include/linux/jbd2.h  |  1 -
 6 files changed, 3 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 56d258c18303..7177f9b21cb2 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -254,13 +254,6 @@ static inline void ext4_handle_sync(handle_t *handle)
 		handle->h_sync = 1;
 }
 
-static inline void ext4_handle_release_buffer(handle_t *handle,
-						struct buffer_head *bh)
-{
-	if (ext4_handle_valid(handle))
-		jbd2_journal_release_buffer(handle, bh);
-}
-
 static inline int ext4_handle_is_aborted(handle_t *handle)
 {
 	if (ext4_handle_valid(handle))
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 47bf06a2765d..d99387b89edd 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -783,7 +783,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 
 	err = ext4_journal_get_write_access(handle, gdb_bh);
 	if (unlikely(err))
-		goto exit_sbh;
+		goto exit_dind;
 
 	err = ext4_journal_get_write_access(handle, dind);
 	if (unlikely(err))
@@ -792,7 +792,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	/* ext4_reserve_inode_write() gets a reference on the iloc */
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
 	if (unlikely(err))
-		goto exit_dindj;
+		goto exit_dind;
 
 	n_group_desc = ext4_kvmalloc((gdb_num + 1) *
 				     sizeof(struct buffer_head *),
@@ -846,12 +846,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 
 exit_inode:
 	ext4_kvfree(n_group_desc);
-	/* ext4_handle_release_buffer(handle, iloc.bh); */
 	brelse(iloc.bh);
-exit_dindj:
-	/* ext4_handle_release_buffer(handle, dind); */
-exit_sbh:
-	/* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
 exit_dind:
 	brelse(dind);
 exit_bh:
@@ -969,14 +964,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
 	}
 
 	for (i = 0; i < reserved_gdb; i++) {
-		if ((err = ext4_journal_get_write_access(handle, primary[i]))) {
-			/*
-			int j;
-			for (j = 0; j < i; j++)
-				ext4_handle_release_buffer(handle, primary[j]);
-			 */
+		if ((err = ext4_journal_get_write_access(handle, primary[i])))
 			goto exit_bh;
-		}
 	}
 
 	if ((err = ext4_reserve_inode_write(handle, inode, &iloc)))
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 2cdb98d62980..b1adda1b750d 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -794,7 +794,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			int offset = (char *)s->here - bs->bh->b_data;
 
 			unlock_buffer(bs->bh);
-			ext4_handle_release_buffer(handle, bs->bh);
 			if (ce) {
 				mb_cache_entry_release(ce);
 				ce = NULL;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 484b8d1c6cb6..dbf41f9452db 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -60,7 +60,6 @@ EXPORT_SYMBOL(jbd2_journal_get_create_access);
 EXPORT_SYMBOL(jbd2_journal_get_undo_access);
 EXPORT_SYMBOL(jbd2_journal_set_triggers);
 EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
-EXPORT_SYMBOL(jbd2_journal_release_buffer);
 EXPORT_SYMBOL(jbd2_journal_forget);
 #if 0
 EXPORT_SYMBOL(journal_sync_buffer);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index a74ba4659549..deffd945c8e2 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1207,17 +1207,6 @@ out:
 	return ret;
 }
 
-/*
- * jbd2_journal_release_buffer: undo a get_write_access without any buffer
- * updates, if the update decided in the end that it didn't need access.
- *
- */
-void
-jbd2_journal_release_buffer(handle_t *handle, struct buffer_head *bh)
-{
-	BUFFER_TRACE(bh, "entry");
-}
-
 /**
  * void jbd2_journal_forget() - bforget() for potentially-journaled buffers.
  * @handle: transaction handle
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 3efc43f3f162..de7f55682088 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1096,7 +1096,6 @@ extern int	 jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
 void		 jbd2_journal_set_triggers(struct buffer_head *,
 					   struct jbd2_buffer_trigger_type *type);
 extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
-extern void	 jbd2_journal_release_buffer (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
 extern void	 journal_sync_buffer (struct buffer_head *);
 extern void	 jbd2_journal_invalidatepage(journal_t *,
-- 
cgit v1.2.3-55-g7522


From fd47d3e1c2949838e858379aaf2bc20647be2912 Mon Sep 17 00:00:00 2001
From: Behan Webster
Date: Thu, 8 Nov 2012 11:24:46 -0500
Subject: jbd2: remove VLAIS usage from JBD2 code

The use of variable length arrays in structs (VLAIS) in the Linux Kernel code
precludes the use of compilers which don't implement VLAIS (for instance the
Clang compiler). Since ctx is always a 32-bit CRC, hard coding a size of 4
bytes accomplishes the same thing without the use of VLAIS. This is the same
technique already employed in fs/ext4/ext4.h

Signed-off-by: Mark Charlebois <charlebm@gmail.com>
Signed-off-by: Behan Webster <behanw@converseincode.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 include/linux/jbd2.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index de7f55682088..1be23d9fdacb 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1302,15 +1302,21 @@ static inline int jbd_space_needed(journal_t *journal)
 
 extern int jbd_blocks_per_page(struct inode *inode);
 
+/* JBD uses a CRC32 checksum */
+#define JBD_MAX_CHECKSUM_SIZE 4
+
 static inline u32 jbd2_chksum(journal_t *journal, u32 crc,
 			      const void *address, unsigned int length)
 {
 	struct {
 		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(journal->j_chksum_driver)];
+		char ctx[JBD_MAX_CHECKSUM_SIZE];
 	} desc;
 	int err;
 
+	BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) >
+		JBD_MAX_CHECKSUM_SIZE);
+
 	desc.shash.tfm = journal->j_chksum_driver;
 	desc.shash.flags = 0;
 	*(u32 *)desc.ctx = crc;
-- 
cgit v1.2.3-55-g7522


From 2be975c6d920de989ff5e4bc09ffe87e59d94662 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov
Date: Sat, 3 Nov 2012 12:16:12 -0700
Subject: Input: introduce managed input devices (add devres support)

There is a demand from driver's writers to use managed devices framework
for their drivers. Unfortunately up to this moment input devices did not
provide support for managed devices and that lead to mixing two styles
of resource management which usually introduced more bugs, such as
manually unregistering input device but relying in devres to free
interrupt handler which (unless device is properly shut off) can cause
ISR to reference already freed memory.

This change introduces devm_input_allocate_device() that will allocate
managed instance of input device so that driver writers who prefer
using devm_* framework do not have to mix 2 styles.

Reviewed-by: Henrik Rydberg <rydberg@euromail.se>
Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/input.c | 176 ++++++++++++++++++++++++++++++++++++++++++--------
 include/linux/input.h |   7 +-
 2 files changed, 155 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/input/input.c b/drivers/input/input.c
index f1be1a77edf3..ce01332f7b3a 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1726,7 +1726,7 @@ EXPORT_SYMBOL_GPL(input_class);
 /**
  * input_allocate_device - allocate memory for new input device
  *
- * Returns prepared struct input_dev or NULL.
+ * Returns prepared struct input_dev or %NULL.
  *
  * NOTE: Use input_free_device() to free devices that have not been
  * registered; input_unregister_device() should be used for already
@@ -1753,6 +1753,70 @@ struct input_dev *input_allocate_device(void)
 }
 EXPORT_SYMBOL(input_allocate_device);
 
+struct input_devres {
+	struct input_dev *input;
+};
+
+static int devm_input_device_match(struct device *dev, void *res, void *data)
+{
+	struct input_devres *devres = res;
+
+	return devres->input == data;
+}
+
+static void devm_input_device_release(struct device *dev, void *res)
+{
+	struct input_devres *devres = res;
+	struct input_dev *input = devres->input;
+
+	dev_dbg(dev, "%s: dropping reference to %s\n",
+		__func__, dev_name(&input->dev));
+	input_put_device(input);
+}
+
+/**
+ * devm_input_allocate_device - allocate managed input device
+ * @dev: device owning the input device being created
+ *
+ * Returns prepared struct input_dev or %NULL.
+ *
+ * Managed input devices do not need to be explicitly unregistered or
+ * freed as it will be done automatically when owner device unbinds from
+ * its driver (or binding fails). Once managed input device is allocated,
+ * it is ready to be set up and registered in the same fashion as regular
+ * input device. There are no special devm_input_device_[un]register()
+ * variants, regular ones work with both managed and unmanaged devices.
+ *
+ * NOTE: the owner device is set up as parent of input device and users
+ * should not override it.
+ */
+
+struct input_dev *devm_input_allocate_device(struct device *dev)
+{
+	struct input_dev *input;
+	struct input_devres *devres;
+
+	devres = devres_alloc(devm_input_device_release,
+			      sizeof(struct input_devres), GFP_KERNEL);
+	if (!devres)
+		return NULL;
+
+	input = input_allocate_device();
+	if (!input) {
+		devres_free(devres);
+		return NULL;
+	}
+
+	input->dev.parent = dev;
+	input->devres_managed = true;
+
+	devres->input = input;
+	devres_add(dev, devres);
+
+	return input;
+}
+EXPORT_SYMBOL(devm_input_allocate_device);
+
 /**
  * input_free_device - free memory occupied by input_dev structure
  * @dev: input device to free
@@ -1769,8 +1833,14 @@ EXPORT_SYMBOL(input_allocate_device);
  */
 void input_free_device(struct input_dev *dev)
 {
-	if (dev)
+	if (dev) {
+		if (dev->devres_managed)
+			WARN_ON(devres_destroy(dev->dev.parent,
+						devm_input_device_release,
+						devm_input_device_match,
+						dev));
 		input_put_device(dev);
+	}
 }
 EXPORT_SYMBOL(input_free_device);
 
@@ -1891,6 +1961,38 @@ static void input_cleanse_bitmasks(struct input_dev *dev)
 	INPUT_CLEANSE_BITMASK(dev, SW, sw);
 }
 
+static void __input_unregister_device(struct input_dev *dev)
+{
+	struct input_handle *handle, *next;
+
+	input_disconnect_device(dev);
+
+	mutex_lock(&input_mutex);
+
+	list_for_each_entry_safe(handle, next, &dev->h_list, d_node)
+		handle->handler->disconnect(handle);
+	WARN_ON(!list_empty(&dev->h_list));
+
+	del_timer_sync(&dev->timer);
+	list_del_init(&dev->node);
+
+	input_wakeup_procfs_readers();
+
+	mutex_unlock(&input_mutex);
+
+	device_del(&dev->dev);
+}
+
+static void devm_input_device_unregister(struct device *dev, void *res)
+{
+	struct input_devres *devres = res;
+	struct input_dev *input = devres->input;
+
+	dev_dbg(dev, "%s: unregistering device %s\n",
+		__func__, dev_name(&input->dev));
+	__input_unregister_device(input);
+}
+
 /**
  * input_register_device - register device with input core
  * @dev: device to be registered
@@ -1906,11 +2008,21 @@ static void input_cleanse_bitmasks(struct input_dev *dev)
 int input_register_device(struct input_dev *dev)
 {
 	static atomic_t input_no = ATOMIC_INIT(0);
+	struct input_devres *devres = NULL;
 	struct input_handler *handler;
 	unsigned int packet_size;
 	const char *path;
 	int error;
 
+	if (dev->devres_managed) {
+		devres = devres_alloc(devm_input_device_unregister,
+				      sizeof(struct input_devres), GFP_KERNEL);
+		if (!devres)
+			return -ENOMEM;
+
+		devres->input = dev;
+	}
+
 	/* Every input device generates EV_SYN/SYN_REPORT events. */
 	__set_bit(EV_SYN, dev->evbit);
 
@@ -1926,8 +2038,10 @@ int input_register_device(struct input_dev *dev)
 
 	dev->max_vals = max(dev->hint_events_per_packet, packet_size) + 2;
 	dev->vals = kcalloc(dev->max_vals, sizeof(*dev->vals), GFP_KERNEL);
-	if (!dev->vals)
-		return -ENOMEM;
+	if (!dev->vals) {
+		error = -ENOMEM;
+		goto err_devres_free;
+	}
 
 	/*
 	 * If delay and period are pre-set by the driver, then autorepeating
@@ -1952,7 +2066,7 @@ int input_register_device(struct input_dev *dev)
 
 	error = device_add(&dev->dev);
 	if (error)
-		return error;
+		goto err_free_vals;
 
 	path = kobject_get_path(&dev->dev.kobj, GFP_KERNEL);
 	pr_info("%s as %s\n",
@@ -1961,10 +2075,8 @@ int input_register_device(struct input_dev *dev)
 	kfree(path);
 
 	error = mutex_lock_interruptible(&input_mutex);
-	if (error) {
-		device_del(&dev->dev);
-		return error;
-	}
+	if (error)
+		goto err_device_del;
 
 	list_add_tail(&dev->node, &input_dev_list);
 
@@ -1975,7 +2087,21 @@ int input_register_device(struct input_dev *dev)
 
 	mutex_unlock(&input_mutex);
 
+	if (dev->devres_managed) {
+		dev_dbg(dev->dev.parent, "%s: registering %s with devres.\n",
+			__func__, dev_name(&dev->dev));
+		devres_add(dev->dev.parent, devres);
+	}
 	return 0;
+
+err_device_del:
+	device_del(&dev->dev);
+err_free_vals:
+	kfree(dev->vals);
+	dev->vals = NULL;
+err_devres_free:
+	devres_free(devres);
+	return error;
 }
 EXPORT_SYMBOL(input_register_device);
 
@@ -1988,24 +2114,20 @@ EXPORT_SYMBOL(input_register_device);
  */
 void input_unregister_device(struct input_dev *dev)
 {
-	struct input_handle *handle, *next;
-
-	input_disconnect_device(dev);
-
-	mutex_lock(&input_mutex);
-
-	list_for_each_entry_safe(handle, next, &dev->h_list, d_node)
-		handle->handler->disconnect(handle);
-	WARN_ON(!list_empty(&dev->h_list));
-
-	del_timer_sync(&dev->timer);
-	list_del_init(&dev->node);
-
-	input_wakeup_procfs_readers();
-
-	mutex_unlock(&input_mutex);
-
-	device_unregister(&dev->dev);
+	if (dev->devres_managed) {
+		WARN_ON(devres_destroy(dev->dev.parent,
+					devm_input_device_unregister,
+					devm_input_device_match,
+					dev));
+		__input_unregister_device(dev);
+		/*
+		 * We do not do input_put_device() here because it will be done
+		 * when 2nd devres fires up.
+		 */
+	} else {
+		__input_unregister_device(dev);
+		input_put_device(dev);
+	}
 }
 EXPORT_SYMBOL(input_unregister_device);
 
diff --git a/include/linux/input.h b/include/linux/input.h
index cab994ba6d91..5538cc09a4f5 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -112,6 +112,8 @@ struct input_value {
  * @h_list: list of input handles associated with the device. When
  *	accessing the list dev->mutex must be held
  * @node: used to place the device onto input_dev_list
+ * @devres_managed: indicates that devices is managed with devres framework
+ *	and needs not be explicitly unregistered or freed.
  */
 struct input_dev {
 	const char *name;
@@ -180,6 +182,8 @@ struct input_dev {
 	unsigned int num_vals;
 	unsigned int max_vals;
 	struct input_value *vals;
+
+	bool devres_managed;
 };
 #define to_input_dev(d) container_of(d, struct input_dev, dev)
 
@@ -323,7 +327,8 @@ struct input_handle {
 	struct list_head	h_node;
 };
 
-struct input_dev *input_allocate_device(void);
+struct input_dev __must_check *input_allocate_device(void);
+struct input_dev __must_check *devm_input_allocate_device(struct device *);
 void input_free_device(struct input_dev *dev);
 
 static inline struct input_dev *input_get_device(struct input_dev *dev)
-- 
cgit v1.2.3-55-g7522


From b5645534ce84c21695c2f82d4d4f67cf2a67229a Mon Sep 17 00:00:00 2001
From: Zheng Liu
Date: Thu, 8 Nov 2012 14:33:43 -0500
Subject: ext4: print 'flags' in ext4_ext_handle_uninitialized_extents

In trace_ext4_ext_handle_uninitialized_extents we don't care about the
value of map->m_flags because this value is probably 0, and we prefer
to get the value of flags because we can know how to handle this
extent in this function.

Reviewed-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/extents.c           | 4 ++--
 include/trace/events/ext4.h | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7011ac967208..59e6e12e0029 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3663,8 +3663,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 		  flags, allocated);
 	ext4_ext_show_leaf(inode, path);
 
-	trace_ext4_ext_handle_uninitialized_extents(inode, map, allocated,
-						    newblock);
+	trace_ext4_ext_handle_uninitialized_extents(inode, map, flags,
+						    allocated, newblock);
 
 	/* get_block() before submit the IO, split the extent */
 	if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index d49b285385e8..25914e3002c7 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -1680,10 +1680,10 @@ DEFINE_EVENT(ext4__trim, ext4_trim_all_free,
 );
 
 TRACE_EVENT(ext4_ext_handle_uninitialized_extents,
-	TP_PROTO(struct inode *inode, struct ext4_map_blocks *map,
+	TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int flags,
 		 unsigned int allocated, ext4_fsblk_t newblock),
 
-	TP_ARGS(inode, map, allocated, newblock),
+	TP_ARGS(inode, map, flags, allocated, newblock),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,		dev		)
@@ -1699,7 +1699,7 @@ TRACE_EVENT(ext4_ext_handle_uninitialized_extents,
 	TP_fast_assign(
 		__entry->dev		= inode->i_sb->s_dev;
 		__entry->ino		= inode->i_ino;
-		__entry->flags		= map->m_flags;
+		__entry->flags		= flags;
 		__entry->lblk		= map->m_lblk;
 		__entry->pblk		= map->m_pblk;
 		__entry->len		= map->m_len;
@@ -1707,7 +1707,7 @@ TRACE_EVENT(ext4_ext_handle_uninitialized_extents,
 		__entry->newblk		= newblock;
 	),
 
-	TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %d"
+	TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %x "
 		  "allocated %d newblock %llu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-- 
cgit v1.2.3-55-g7522


From 19b303d8b5a0e8150a4697c01ca03e75a0a17469 Mon Sep 17 00:00:00 2001
From: Zheng Liu
Date: Thu, 8 Nov 2012 14:34:04 -0500
Subject: ext4: print map->m_flags in trace_ext4_ext/ind_map_blocks_exit

When we use trace_ext4_ext/ind_map_blocks_exit, print the value of
map->m_flags in order that we can understand the extent's current
status.

Reviewed-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/extents.c           |  3 +--
 fs/ext4/indirect.c          |  3 +--
 include/trace/events/ext4.h | 27 +++++++++++++--------------
 3 files changed, 15 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 59e6e12e0029..7a64c193b2af 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4284,8 +4284,7 @@ out2:
 		kfree(path);
 	}
 
-	trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
-		newblock, map->m_len, err ? err : allocated);
+	trace_ext4_ext_map_blocks_exit(inode, map, err ? err : allocated);
 
 	return err ? err : allocated;
 }
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 792e388e7b44..292337f27c9c 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -755,8 +755,7 @@ cleanup:
 		partial--;
 	}
 out:
-	trace_ext4_ind_map_blocks_exit(inode, map->m_lblk,
-				map->m_pblk, map->m_len, err);
+	trace_ext4_ind_map_blocks_exit(inode, map, err);
 	return err;
 }
 
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 25914e3002c7..d2a125a6db8b 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -1519,10 +1519,9 @@ DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter,
 );
 
 DECLARE_EVENT_CLASS(ext4__map_blocks_exit,
-	TP_PROTO(struct inode *inode, ext4_lblk_t lblk,
-		 ext4_fsblk_t pblk, unsigned int len, int ret),
+	TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret),
 
-	TP_ARGS(inode, lblk, pblk, len, ret),
+	TP_ARGS(inode, map, ret),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,		dev		)
@@ -1530,37 +1529,37 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_exit,
 		__field(	ext4_fsblk_t,	pblk		)
 		__field(	ext4_lblk_t,	lblk		)
 		__field(	unsigned int,	len		)
+		__field(	unsigned int,	flags		)
 		__field(	int,		ret		)
 	),
 
 	TP_fast_assign(
 		__entry->dev    = inode->i_sb->s_dev;
 		__entry->ino    = inode->i_ino;
-		__entry->pblk	= pblk;
-		__entry->lblk	= lblk;
-		__entry->len	= len;
+		__entry->pblk	= map->m_pblk;
+		__entry->lblk	= map->m_lblk;
+		__entry->len	= map->m_len;
+		__entry->flags	= map->m_flags;
 		__entry->ret	= ret;
 	),
 
-	TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u ret %d",
+	TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u flags %x ret %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->lblk, __entry->pblk,
-		  __entry->len, __entry->ret)
+		  __entry->len, __entry->flags, __entry->ret)
 );
 
 DEFINE_EVENT(ext4__map_blocks_exit, ext4_ext_map_blocks_exit,
-	TP_PROTO(struct inode *inode, ext4_lblk_t lblk,
-		 ext4_fsblk_t pblk, unsigned len, int ret),
+	TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret),
 
-	TP_ARGS(inode, lblk, pblk, len, ret)
+	TP_ARGS(inode, map, ret)
 );
 
 DEFINE_EVENT(ext4__map_blocks_exit, ext4_ind_map_blocks_exit,
-	TP_PROTO(struct inode *inode, ext4_lblk_t lblk,
-		 ext4_fsblk_t pblk, unsigned len, int ret),
+	TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret),
 
-	TP_ARGS(inode, lblk, pblk, len, ret)
+	TP_ARGS(inode, map, ret)
 );
 
 TRACE_EVENT(ext4_ext_load_extent,
-- 
cgit v1.2.3-55-g7522


From a4477c4ddb5d3552b4d204f49047bdbb097c4450 Mon Sep 17 00:00:00 2001
From: Li RongQing
Date: Wed, 7 Nov 2012 21:56:33 +0000
Subject: ipv6: remove rt6i_peer_genid from rt6_info and its handler

6431cbc25f(Create a mechanism for upward inetpeer propagation into routes)
introduces these codes, but this mechanism is never enabled since
rt6i_peer_genid always is zero whether it is not assigned or assigned by
rt6_peer_genid(). After 5943634fc5 (ipv4: Maintain redirect and PMTU info
in struct rtable again), the ipv4 related codes of this mechanism has been
removed, I think we maybe able to remove them now.

Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  1 -
 net/ipv6/route.c      | 18 ++----------------
 2 files changed, 2 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index d1327e4d126b..fdc48a94a063 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -117,7 +117,6 @@ struct rt6_info {
 	struct rt6key			rt6i_src;
 	struct rt6key			rt6i_prefsrc;
 	u32				rt6i_metric;
-	u32				rt6i_peer_genid;
 
 	struct inet6_dev		*rt6i_idev;
 	unsigned long			_rt6i_peer;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c1cfcb7e5632..6863f8b43bbd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -321,13 +321,6 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 	}
 }
 
-static atomic_t __rt6_peer_genid = ATOMIC_INIT(0);
-
-static u32 rt6_peer_genid(void)
-{
-	return atomic_read(&__rt6_peer_genid);
-}
-
 void rt6_bind_peer(struct rt6_info *rt, int create)
 {
 	struct inet_peer_base *base;
@@ -341,8 +334,6 @@ void rt6_bind_peer(struct rt6_info *rt, int create)
 	if (peer) {
 		if (!rt6_set_peer(rt, peer))
 			inet_putpeer(peer);
-		else
-			rt->rt6i_peer_genid = rt6_peer_genid();
 	}
 }
 
@@ -1099,14 +1090,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 	if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev)))
 		return NULL;
 
-	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) {
-		if (rt->rt6i_peer_genid != rt6_peer_genid()) {
-			if (!rt6_has_peer(rt))
-				rt6_bind_peer(rt, 0);
-			rt->rt6i_peer_genid = rt6_peer_genid();
-		}
+	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
 		return dst;
-	}
+
 	return NULL;
 }
 
-- 
cgit v1.2.3-55-g7522


From 992e9fdd7b3f656ab8aea895f0038336950774ed Mon Sep 17 00:00:00 2001
From: Zheng Liu
Date: Thu, 8 Nov 2012 21:57:33 -0500
Subject: ext4: add some tracepoints in extent status tree

This patch adds some tracepoints in extent status tree.

Signed-off-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/extents_status.c    |   8 ++++
 include/trace/events/ext4.h | 101 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 109 insertions(+)

(limited to 'include')

diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 02c09be3d773..564d981a2fcc 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -14,6 +14,8 @@
 #include "extents_status.h"
 #include "ext4_extents.h"
 
+#include <trace/events/ext4.h>
+
 /*
  * According to previous discussion in Ext4 Developer Workshop, we
  * will introduce a new structure called io tree to track all extent
@@ -224,6 +226,8 @@ ext4_lblk_t ext4_es_find_extent(struct inode *inode, struct extent_status *es)
 	struct rb_node *node;
 	ext4_lblk_t ret = EXT_MAX_BLOCKS;
 
+	trace_ext4_es_find_extent_enter(inode, es->start);
+
 	read_lock(&EXT4_I(inode)->i_es_lock);
 	tree = &EXT4_I(inode)->i_es_tree;
 
@@ -253,6 +257,8 @@ out:
 	}
 
 	read_unlock(&EXT4_I(inode)->i_es_lock);
+
+	trace_ext4_es_find_extent_exit(inode, es, ret);
 	return ret;
 }
 
@@ -393,6 +399,7 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t offset,
 	struct ext4_es_tree *tree;
 	int err = 0;
 
+	trace_ext4_es_insert_extent(inode, offset, len);
 	es_debug("add [%u/%u) to extent status tree of inode %lu\n",
 		 offset, len, inode->i_ino);
 
@@ -422,6 +429,7 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t offset,
 	ext4_lblk_t len1, len2, end;
 	int err = 0;
 
+	trace_ext4_es_remove_extent(inode, offset, len);
 	es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
 		 offset, len, inode->i_ino);
 
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index d2a125a6db8b..f6372b011366 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -15,6 +15,7 @@ struct ext4_inode_info;
 struct mpage_da_data;
 struct ext4_map_blocks;
 struct ext4_extent;
+struct extent_status;
 
 #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode))
 
@@ -2054,6 +2055,106 @@ TRACE_EVENT(ext4_ext_remove_space_done,
 		  (unsigned short) __entry->eh_entries)
 );
 
+TRACE_EVENT(ext4_es_insert_extent,
+	TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t len),
+
+	TP_ARGS(inode, start, len),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	loff_t,	start			)
+		__field(	loff_t, len			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->start	= start;
+		__entry->len	= len;
+	),
+
+	TP_printk("dev %d,%d ino %lu es [%lld/%lld)",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  __entry->start, __entry->len)
+);
+
+TRACE_EVENT(ext4_es_remove_extent,
+	TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t len),
+
+	TP_ARGS(inode, start, len),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	loff_t,	start			)
+		__field(	loff_t,	len			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->start	= start;
+		__entry->len	= len;
+	),
+
+	TP_printk("dev %d,%d ino %lu es [%lld/%lld)",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  __entry->start, __entry->len)
+);
+
+TRACE_EVENT(ext4_es_find_extent_enter,
+	TP_PROTO(struct inode *inode, ext4_lblk_t start),
+
+	TP_ARGS(inode, start),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	ext4_lblk_t,	start		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->start	= start;
+	),
+
+	TP_printk("dev %d,%d ino %lu start %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino, __entry->start)
+);
+
+TRACE_EVENT(ext4_es_find_extent_exit,
+	TP_PROTO(struct inode *inode, struct extent_status *es,
+		 ext4_lblk_t ret),
+
+	TP_ARGS(inode, es, ret),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	ext4_lblk_t,	start		)
+		__field(	ext4_lblk_t,	len		)
+		__field(	ext4_lblk_t,	ret		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->start	= es->start;
+		__entry->len	= es->len;
+		__entry->ret	= ret;
+	),
+
+	TP_printk("dev %d,%d ino %lu es [%u/%u) ret %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  __entry->start, __entry->len, __entry->ret)
+);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3-55-g7522


From 58ffa580a748dd16b1e5ab260bea39cdbd1e94ef Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Thu, 26 Jul 2012 14:09:49 +0200
Subject: drbd: introduce stop-sector to online verify

We now can schedule only a specific range of sectors for online verify,
or interrupt a running verify without interrupting the connection.

Had to bump the protocol version differently, we are now 101.
Added verify_can_do_stop_sector() { protocol >= 97 && protocol != 100; }

Also, the return value convention for worker callbacks has changed,
we returned "true/false" for "keep the connection up" in 8.3,
we return 0 for success and <= for failure in 8.4.
Affected: receive_state()

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h      |  7 +++++++
 drivers/block/drbd/drbd_nl.c       | 14 +++++++++-----
 drivers/block/drbd/drbd_proc.c     | 12 +++++++++---
 drivers/block/drbd/drbd_receiver.c | 10 +++++++++-
 drivers/block/drbd/drbd_state.c    | 17 +++++++++++++----
 drivers/block/drbd/drbd_worker.c   | 33 +++++++++++++++++++++++++++------
 include/linux/drbd.h               |  2 +-
 include/linux/drbd_genl.h          |  1 +
 8 files changed, 76 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 22adfc7189de..eddc4388a1b1 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -971,6 +971,7 @@ struct drbd_conf {
 
 	/* where does the admin want us to start? (sector) */
 	sector_t ov_start_sector;
+	sector_t ov_stop_sector;
 	/* where are we now? (sector) */
 	sector_t ov_position;
 	/* Start sector of out of sync range (to merge printk reporting). */
@@ -2264,6 +2265,12 @@ static inline void dec_ap_bio(struct drbd_conf *mdev)
 		wake_up(&mdev->misc_wait);
 }
 
+static inline bool verify_can_do_stop_sector(struct drbd_conf *mdev)
+{
+	return mdev->tconn->agreed_pro_version >= 97 &&
+		mdev->tconn->agreed_pro_version != 100;
+}
+
 static inline int drbd_set_ed_uuid(struct drbd_conf *mdev, u64 val)
 {
 	int changed = mdev->ed_uuid != val;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 4afd626ca3dc..eefb56308aea 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2939,6 +2939,7 @@ int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_conf *mdev;
 	enum drbd_ret_code retcode;
+	struct start_ov_parms parms;
 
 	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
@@ -2947,19 +2948,22 @@ int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 
 	mdev = adm_ctx.mdev;
+
+	/* resume from last known position, if possible */
+	parms.ov_start_sector = mdev->ov_start_sector;
+	parms.ov_stop_sector = ULLONG_MAX;
 	if (info->attrs[DRBD_NLA_START_OV_PARMS]) {
-		/* resume from last known position, if possible */
-		struct start_ov_parms parms =
-			{ .ov_start_sector = mdev->ov_start_sector };
 		int err = start_ov_parms_from_attrs(&parms, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
 			drbd_msg_put_info(from_attrs_err_to_txt(err));
 			goto out;
 		}
-		/* w_make_ov_request expects position to be aligned */
-		mdev->ov_start_sector = parms.ov_start_sector & ~BM_SECT_PER_BIT;
 	}
+	/* w_make_ov_request expects position to be aligned */
+	mdev->ov_start_sector = parms.ov_start_sector & ~(BM_SECT_PER_BIT-1);
+	mdev->ov_stop_sector = parms.ov_stop_sector;
+
 	/* If there is still bitmap IO pending, e.g. previous resync or verify
 	 * just being finished, wait for it before requesting a new resync. */
 	drbd_suspend_io(mdev);
diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c
index e0f0d2a6d538..56672a61eb94 100644
--- a/drivers/block/drbd/drbd_proc.c
+++ b/drivers/block/drbd/drbd_proc.c
@@ -167,18 +167,24 @@ static void drbd_syncer_progress(struct drbd_conf *mdev, struct seq_file *seq)
 		 * we convert to sectors in the display below. */
 		unsigned long bm_bits = drbd_bm_bits(mdev);
 		unsigned long bit_pos;
+		unsigned long long stop_sector = 0;
 		if (mdev->state.conn == C_VERIFY_S ||
-		    mdev->state.conn == C_VERIFY_T)
+		    mdev->state.conn == C_VERIFY_T) {
 			bit_pos = bm_bits - mdev->ov_left;
-		else
+			if (verify_can_do_stop_sector(mdev))
+				stop_sector = mdev->ov_stop_sector;
+		} else
 			bit_pos = mdev->bm_resync_fo;
 		/* Total sectors may be slightly off for oddly
 		 * sized devices. So what. */
 		seq_printf(seq,
-			"\t%3d%% sector pos: %llu/%llu\n",
+			"\t%3d%% sector pos: %llu/%llu",
 			(int)(bit_pos / (bm_bits/100+1)),
 			(unsigned long long)bit_pos * BM_SECT_PER_BIT,
 			(unsigned long long)bm_bits * BM_SECT_PER_BIT);
+		if (stop_sector != 0 && stop_sector != ULLONG_MAX)
+			seq_printf(seq, " stop sector: %llu", stop_sector);
+		seq_printf(seq, "\n");
 	}
 }
 
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 7fe6b01618d4..8fddec96dfbe 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -3843,7 +3843,7 @@ static int receive_state(struct drbd_tconn *tconn, struct packet_info *pi)
 	 * already decided to close the connection again,
 	 * we must not "re-establish" it here. */
 	if (os.conn <= C_TEAR_DOWN)
-		return false;
+		return -ECONNRESET;
 
 	/* If this is the "end of sync" confirmation, usually the peer disk
 	 * transitions from D_INCONSISTENT to D_UP_TO_DATE. For empty (0 bits
@@ -3875,6 +3875,14 @@ static int receive_state(struct drbd_tconn *tconn, struct packet_info *pi)
 		}
 	}
 
+	/* explicit verify finished notification, stop sector reached. */
+	if (os.conn == C_VERIFY_T && os.disk == D_UP_TO_DATE &&
+	    peer_state.conn == C_CONNECTED && real_peer_disk == D_UP_TO_DATE) {
+		ov_out_of_sync_print(mdev);
+		drbd_resync_finished(mdev);
+		return 0;
+	}
+
 	/* peer says his disk is inconsistent, while we think it is uptodate,
 	 * and this happens while the peer still thinks we have a sync going on,
 	 * but we think we are already done with the sync.
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 444581828d70..12f2b4fbe559 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -975,13 +975,15 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
 	wake_up(&mdev->state_wait);
 	wake_up(&mdev->tconn->ping_wait);
 
-	/* aborted verify run. log the last position */
+	/* Aborted verify run, or we reached the stop sector.
+	 * Log the last position, unless end-of-device. */
 	if ((os.conn == C_VERIFY_S || os.conn == C_VERIFY_T) &&
-	    ns.conn < C_CONNECTED) {
+	    ns.conn <= C_CONNECTED) {
 		mdev->ov_start_sector =
 			BM_BIT_TO_SECT(drbd_bm_bits(mdev) - mdev->ov_left);
-		dev_info(DEV, "Online Verify reached sector %llu\n",
-			(unsigned long long)mdev->ov_start_sector);
+		if (mdev->ov_left)
+			dev_info(DEV, "Online Verify reached sector %llu\n",
+				(unsigned long long)mdev->ov_start_sector);
 	}
 
 	if ((os.conn == C_PAUSED_SYNC_T || os.conn == C_PAUSED_SYNC_S) &&
@@ -1422,6 +1424,13 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 	if (os.disk < D_UP_TO_DATE && os.conn >= C_SYNC_SOURCE && ns.conn == C_CONNECTED)
 		drbd_send_state(mdev, ns);
 
+	/* Verify finished, or reached stop sector.  Peer did not know about
+	 * the stop sector, and we may even have changed the stop sector during
+	 * verify to interrupt/stop early.  Send the new state. */
+	if (os.conn == C_VERIFY_S && ns.conn == C_CONNECTED
+	&& verify_can_do_stop_sector(mdev))
+		drbd_send_state(mdev, ns);
+
 	/* Wake up role changes, that were delayed because of connection establishing */
 	if (os.conn == C_WF_REPORT_PARAMS && ns.conn != C_WF_REPORT_PARAMS) {
 		if (test_and_clear_bit(STATE_SENT, &mdev->tconn->flags))
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 9d7e1fb0f431..1c9c6fd332c3 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -692,6 +692,7 @@ static int w_make_ov_request(struct drbd_work *w, int cancel)
 	int number, i, size;
 	sector_t sector;
 	const sector_t capacity = drbd_get_capacity(mdev->this_bdev);
+	bool stop_sector_reached = false;
 
 	if (unlikely(cancel))
 		return 1;
@@ -700,9 +701,17 @@ static int w_make_ov_request(struct drbd_work *w, int cancel)
 
 	sector = mdev->ov_position;
 	for (i = 0; i < number; i++) {
-		if (sector >= capacity) {
+		if (sector >= capacity)
 			return 1;
-		}
+
+		/* We check for "finished" only in the reply path:
+		 * w_e_end_ov_reply().
+		 * We need to send at least one request out. */
+		stop_sector_reached = i > 0
+			&& verify_can_do_stop_sector(mdev)
+			&& sector >= mdev->ov_stop_sector;
+		if (stop_sector_reached)
+			break;
 
 		size = BM_BLOCK_SIZE;
 
@@ -726,7 +735,8 @@ static int w_make_ov_request(struct drbd_work *w, int cancel)
 
  requeue:
 	mdev->rs_in_flight += (i << (BM_BLOCK_SHIFT - 9));
-	mod_timer(&mdev->resync_timer, jiffies + SLEEP_TIME);
+	if (i == 0 || !stop_sector_reached)
+		mod_timer(&mdev->resync_timer, jiffies + SLEEP_TIME);
 	return 1;
 }
 
@@ -792,7 +802,12 @@ int drbd_resync_finished(struct drbd_conf *mdev)
 	dt = (jiffies - mdev->rs_start - mdev->rs_paused) / HZ;
 	if (dt <= 0)
 		dt = 1;
+	
 	db = mdev->rs_total;
+	/* adjust for verify start and stop sectors, respective reached position */
+	if (mdev->state.conn == C_VERIFY_S || mdev->state.conn == C_VERIFY_T)
+		db -= mdev->ov_left;
+
 	dbdt = Bit2KB(db/dt);
 	mdev->rs_paused /= HZ;
 
@@ -815,7 +830,7 @@ int drbd_resync_finished(struct drbd_conf *mdev)
 	ns.conn = C_CONNECTED;
 
 	dev_info(DEV, "%s done (total %lu sec; paused %lu sec; %lu K/sec)\n",
-	     verify_done ? "Online verify " : "Resync",
+	     verify_done ? "Online verify" : "Resync",
 	     dt + mdev->rs_paused, mdev->rs_paused, dbdt);
 
 	n_oos = drbd_bm_total_weight(mdev);
@@ -896,7 +911,9 @@ out:
 	mdev->rs_total  = 0;
 	mdev->rs_failed = 0;
 	mdev->rs_paused = 0;
-	if (verify_done)
+
+	/* reset start sector, if we reached end of device */
+	if (verify_done && mdev->ov_left == 0)
 		mdev->ov_start_sector = 0;
 
 	drbd_md_sync(mdev);
@@ -1144,6 +1161,7 @@ int w_e_end_ov_reply(struct drbd_work *w, int cancel)
 	unsigned int size = peer_req->i.size;
 	int digest_size;
 	int err, eq = 0;
+	bool stop_sector_reached = false;
 
 	if (unlikely(cancel)) {
 		drbd_free_peer_req(mdev, peer_req);
@@ -1194,7 +1212,10 @@ int w_e_end_ov_reply(struct drbd_work *w, int cancel)
 	if ((mdev->ov_left & 0x200) == 0x200)
 		drbd_advance_rs_marks(mdev, mdev->ov_left);
 
-	if (mdev->ov_left == 0) {
+	stop_sector_reached = verify_can_do_stop_sector(mdev) &&
+		(sector + (size>>9)) >= mdev->ov_stop_sector;
+
+	if (mdev->ov_left == 0 || stop_sector_reached) {
 		ov_out_of_sync_print(mdev);
 		drbd_resync_finished(mdev);
 	}
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 36ae7dd28d90..5171c3530886 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -55,7 +55,7 @@ extern const char *drbd_buildtag(void);
 #define REL_VERSION "8.3.11"
 #define API_VERSION 88
 #define PRO_VERSION_MIN 86
-#define PRO_VERSION_MAX 100
+#define PRO_VERSION_MAX 101
 
 
 enum drbd_io_error_p {
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 92ec4b50a885..9430e9ab37a8 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -215,6 +215,7 @@ GENL_struct(DRBD_NLA_STATE_INFO, 8, state_info,
 
 GENL_struct(DRBD_NLA_START_OV_PARMS, 9, start_ov_parms,
 	__u64_field(1, DRBD_GENLA_F_MANDATORY,	ov_start_sector)
+	__u64_field(2, DRBD_GENLA_F_MANDATORY,	ov_stop_sector)
 )
 
 GENL_struct(DRBD_NLA_NEW_C_UUID_PARMS, 10, new_c_uuid_parms,
-- 
cgit v1.2.3-55-g7522


From 3174f8c5045ad247563434c4b4897bd89313eafc Mon Sep 17 00:00:00 2001
From: Philipp Marek
Date: Sat, 3 Mar 2012 21:04:30 +0100
Subject: drbd: pass some more information to userspace.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c | 11 ++++++++++-
 include/linux/drbd_genl.h    | 10 ++++++++++
 2 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index eefb56308aea..466d6b1d9309 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2666,7 +2666,16 @@ int nla_put_status_info(struct sk_buff *skb, struct drbd_conf *mdev,
 	if (nla_put_u32(skb, T_sib_reason, sib ? sib->sib_reason : SIB_GET_STATUS_REPLY) ||
 	    nla_put_u32(skb, T_current_state, mdev->state.i) ||
 	    nla_put_u64(skb, T_ed_uuid, mdev->ed_uuid) ||
-	    nla_put_u64(skb, T_capacity, drbd_get_capacity(mdev->this_bdev)))
+	    nla_put_u64(skb, T_capacity, drbd_get_capacity(mdev->this_bdev)) ||
+	    nla_put_u64(skb, T_send_cnt, mdev->send_cnt) ||
+	    nla_put_u64(skb, T_recv_cnt, mdev->recv_cnt) ||
+	    nla_put_u64(skb, T_read_cnt, mdev->read_cnt) ||
+	    nla_put_u64(skb, T_writ_cnt, mdev->writ_cnt) ||
+	    nla_put_u64(skb, T_al_writ_cnt, mdev->al_writ_cnt) ||
+	    nla_put_u64(skb, T_bm_writ_cnt, mdev->bm_writ_cnt) ||
+	    nla_put_u32(skb, T_ap_bio_cnt, atomic_read(&mdev->ap_bio_cnt)) ||
+	    nla_put_u32(skb, T_ap_pending_cnt, atomic_read(&mdev->ap_pending_cnt)) ||
+	    nla_put_u32(skb, T_rs_pending_cnt, atomic_read(&mdev->rs_pending_cnt)))
 		goto nla_put_failure;
 
 	if (got_ldev) {
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 9430e9ab37a8..d0d8fac8a6e4 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -211,6 +211,16 @@ GENL_struct(DRBD_NLA_STATE_INFO, 8, state_info,
 	/* for pre and post notifications of helper execution */
 	__str_field(13, DRBD_GENLA_F_MANDATORY,	helper, 32)
 	__u32_field(14, DRBD_GENLA_F_MANDATORY,	helper_exit_code)
+
+	__u64_field(15,                      0, send_cnt)
+	__u64_field(16,                      0, recv_cnt)
+	__u64_field(17,                      0, read_cnt)
+	__u64_field(18,                      0, writ_cnt)
+	__u64_field(19,                      0, al_writ_cnt)
+	__u64_field(20,                      0, bm_writ_cnt)
+	__u32_field(21,                      0, ap_bio_cnt)
+	__u32_field(22,                      0, ap_pending_cnt)
+	__u32_field(23,                      0, rs_pending_cnt)
 )
 
 GENL_struct(DRBD_NLA_START_OV_PARMS, 9, start_ov_parms,
-- 
cgit v1.2.3-55-g7522


From eb12010e9af119c84e6b2214064a98681027e0e3 Mon Sep 17 00:00:00 2001
From: Lars Ellenberg
Date: Wed, 1 Aug 2012 12:46:20 +0200
Subject: drbd: disambiguation, s/ERR_DISCARD/ERR_DISCARD_IMPOSSIBLE/

If for some reason (typically "split-brained" cluster manager)
drbd replica data has diverged, we can chose a victim,
and reconnect using "--discard-my-data", causing the victim
to become sync-target, fetching all changed blocks from the peer.

If we are Primary, we are potentially in use, and we refuse to
"roll back" changes to the data below the page cache and other users.

Rename the error symbol for this to ERR_DISCARD_IMPOSSIBLE.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c | 2 +-
 include/linux/drbd.h         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 35bb572a2076..d1073705bf1f 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1829,7 +1829,7 @@ _check_net_options(struct drbd_tconn *tconn, struct net_conf *old_conf, struct n
 				return ERR_STONITH_AND_PROT_A;
 		}
 		if (mdev->state.role == R_PRIMARY && new_conf->discard_my_data)
-			return ERR_DISCARD;
+			return ERR_DISCARD_IMPOSSIBLE;
 	}
 
 	if (new_conf->on_congestion != OC_BLOCK && new_conf->wire_protocol != DRBD_PROT_A)
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 5171c3530886..0b93e5e2e064 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -136,7 +136,7 @@ enum drbd_ret_code {
 	ERR_AUTH_ALG		= 120,
 	ERR_AUTH_ALG_ND		= 121,
 	ERR_NOMEM		= 122,
-	ERR_DISCARD		= 123,
+	ERR_DISCARD_IMPOSSIBLE	= 123,
 	ERR_DISK_CONFIGURED	= 124,
 	ERR_NET_CONFIGURED	= 125,
 	ERR_MANDATORY_TAG	= 126,
-- 
cgit v1.2.3-55-g7522


From 328e0f125bf41f4f33f684db22015f92cb44fe56 Mon Sep 17 00:00:00 2001
From: Philipp Reisner
Date: Fri, 19 Oct 2012 14:37:47 +0200
Subject: drbd: Broadcast sync progress no more often than once per second

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h    | 1 +
 drivers/block/drbd/drbd_nl.c     | 6 ++++++
 drivers/block/drbd/drbd_worker.c | 4 ++++
 include/linux/drbd.h             | 4 ++--
 4 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 057ffed6eb7e..784f4eb2ed61 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -965,6 +965,7 @@ struct drbd_conf {
 	unsigned long rs_mark_time[DRBD_SYNC_MARKS];
 	/* current index into rs_mark_{left,time} */
 	int rs_last_mark;
+	unsigned long rs_last_bcast; /* [unit jiffies] */
 
 	/* where does the admin want us to start? (sector) */
 	sector_t ov_start_sector;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 298dd3e35e02..d339a2754a85 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -3295,6 +3295,12 @@ void drbd_bcast_event(struct drbd_conf *mdev, const struct sib_info *sib)
 	unsigned seq;
 	int err = -ENOMEM;
 
+	if (sib->sib_reason == SIB_SYNC_PROGRESS &&
+	    time_after(jiffies, mdev->rs_last_bcast + HZ))
+		mdev->rs_last_bcast = jiffies;
+	else
+		return;
+
 	seq = atomic_inc_return(&drbd_genl_seq);
 	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_NOIO);
 	if (!msg)
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 64a7305c678a..424dc7bdf9b7 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1696,6 +1696,10 @@ void drbd_start_resync(struct drbd_conf *mdev, enum drbd_conns side)
 	write_unlock_irq(&global_state_lock);
 
 	if (r == SS_SUCCESS) {
+		/* reset rs_last_bcast when a resync or verify is started,
+		 * to deal with potential jiffies wrap. */
+		mdev->rs_last_bcast = jiffies - HZ;
+
 		dev_info(DEV, "Began resync as %s (will sync %lu KB [%lu bits set]).\n",
 		     drbd_conn_str(ns.conn),
 		     (unsigned long) mdev->rs_total << (BM_BLOCK_SHIFT-10),
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 0b93e5e2e064..0c5a18ec322c 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -52,8 +52,8 @@
 #endif
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.3.11"
-#define API_VERSION 88
+#define REL_VERSION "8.4.2"
+#define API_VERSION 1
 #define PRO_VERSION_MIN 86
 #define PRO_VERSION_MAX 101
 
-- 
cgit v1.2.3-55-g7522


From 9214ad7f9a0bfbfb2c204305e7391ce8b7fe4d29 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Tue, 6 Nov 2012 19:18:13 +0100
Subject: mac80211: call driver method when restart completes

When the driver requests a restart (reconfiguration) it
gets all the normal method calls, but can't really tell
why they're happening. Call a new restart_complete op
in the driver when the restart completes, so it could
keep its own state about the restart and clear it there.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    |  6 ++++++
 net/mac80211/driver-ops.h | 10 ++++++++++
 net/mac80211/trace.h      |  5 +++++
 net/mac80211/util.c       |  4 +++-
 4 files changed, 24 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 23803addca3c..e1d830992319 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2400,6 +2400,10 @@ enum ieee80211_rate_control_changed {
  *	just "paused" for scanning/ROC, which is indicated by the beacon being
  *	disabled/enabled via @bss_info_changed.
  * @stop_ap: Stop operation on the AP interface.
+ *
+ * @restart_complete: Called after a call to ieee80211_restart_hw(), when the
+ *	reconfiguration has completed. This can help the driver implement the
+ *	reconfiguration step. This callback may sleep.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -2561,6 +2565,8 @@ struct ieee80211_ops {
 	void (*unassign_vif_chanctx)(struct ieee80211_hw *hw,
 				     struct ieee80211_vif *vif,
 				     struct ieee80211_chanctx_conf *ctx);
+
+	void (*restart_complete)(struct ieee80211_hw *hw);
 };
 
 /**
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 1701ad7013a4..4dc2577886ff 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -961,4 +961,14 @@ static inline void drv_stop_ap(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline void drv_restart_complete(struct ieee80211_local *local)
+{
+	might_sleep();
+
+	trace_drv_restart_complete(local);
+	if (local->ops->restart_complete)
+		local->ops->restart_complete(&local->hw);
+	trace_drv_return_void(local);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 06a69ebcaede..758836c85a80 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -1411,6 +1411,11 @@ DEFINE_EVENT(local_sdata_evt, drv_stop_ap,
 	TP_ARGS(local, sdata)
 );
 
+DEFINE_EVENT(local_only_evt, drv_restart_complete,
+	TP_PROTO(struct ieee80211_local *local),
+	TP_ARGS(local)
+);
+
 /*
  * Tracing for API calls that drivers call.
  */
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 1a511afbdf07..84858a14c8bf 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1599,8 +1599,10 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	 * If this is for hw restart things are still running.
 	 * We may want to change that later, however.
 	 */
-	if (!local->suspended)
+	if (!local->suspended) {
+		drv_restart_complete(local);
 		return 0;
+	}
 
 #ifdef CONFIG_PM
 	/* first set suspended false, then resuming */
-- 
cgit v1.2.3-55-g7522


From 8b2c98243e8d00f9c6b6059976d6de51491ee0c7 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Tue, 6 Nov 2012 20:23:30 +0100
Subject: mac80211: clarify interface iteration and make it configurable

During hardware restart, all interfaces are iterated even
though they haven't been re-added to the driver, document
this behaviour. The same also happens during resume, which
is even more confusing since all of the interfaces were
previously removed from the driver. Make this optional so
drivers relying on the current behaviour can still use it,
but to let drivers that don't want this behaviour disable
it.

Also convert all API users, keeping the old semantics
except in hwsim, where the new normal ones are desired.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath5k/base.c           | 10 ++++++----
 drivers/net/wireless/ath/ath5k/mac80211-ops.c   |  5 +++--
 drivers/net/wireless/ath/ath9k/htc_drv_beacon.c |  6 +++---
 drivers/net/wireless/ath/ath9k/htc_drv_main.c   | 20 ++++++++++++--------
 drivers/net/wireless/ath/ath9k/main.c           | 15 +++++++++------
 drivers/net/wireless/mac80211_hwsim.c           | 11 ++++++++---
 drivers/net/wireless/rt2x00/rt2x00dev.c         | 19 ++++++++++---------
 drivers/net/wireless/rt2x00/rt2x00mac.c         |  6 +++---
 drivers/net/wireless/ti/wlcore/main.c           |  2 +-
 include/net/mac80211.h                          | 23 +++++++++++++++++++++--
 net/mac80211/util.c                             | 18 ++++++++++++++----
 11 files changed, 90 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index 9f31cfa56cc0..cdd19232960c 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -511,8 +511,9 @@ ath5k_update_bssid_mask_and_opmode(struct ath5k_hw *ah,
 		ath5k_vif_iter(&iter_data, vif->addr, vif);
 
 	/* Get list of all active MAC addresses */
-	ieee80211_iterate_active_interfaces_atomic(ah->hw, ath5k_vif_iter,
-						   &iter_data);
+	ieee80211_iterate_active_interfaces_atomic(
+		ah->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+		ath5k_vif_iter, &iter_data);
 	memcpy(ah->bssidmask, iter_data.mask, ETH_ALEN);
 
 	ah->opmode = iter_data.opmode;
@@ -3045,8 +3046,9 @@ ath5k_any_vif_assoc(struct ath5k_hw *ah)
 	iter_data.need_set_hw_addr = false;
 	iter_data.found_active = true;
 
-	ieee80211_iterate_active_interfaces_atomic(ah->hw, ath5k_vif_iter,
-						   &iter_data);
+	ieee80211_iterate_active_interfaces_atomic(
+		ah->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+		ath5k_vif_iter, &iter_data);
 	return iter_data.any_assoc;
 }
 
diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index 7a28538e6e05..1ea8c8795c8e 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -452,8 +452,9 @@ ath5k_configure_filter(struct ieee80211_hw *hw, unsigned int changed_flags,
 	iter_data.hw_macaddr = NULL;
 	iter_data.n_stas = 0;
 	iter_data.need_set_hw_addr = false;
-	ieee80211_iterate_active_interfaces_atomic(ah->hw, ath5k_vif_iter,
-						   &iter_data);
+	ieee80211_iterate_active_interfaces_atomic(
+		ah->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+		ath5k_vif_iter, &iter_data);
 
 	/* Set up RX Filter */
 	if (iter_data.n_stas > 1) {
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
index f42d2eb6af99..1318d79f5c44 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
@@ -587,9 +587,9 @@ static bool ath9k_htc_check_beacon_config(struct ath9k_htc_priv *priv,
 	    (priv->num_sta_vif > 1) &&
 	    (vif->type == NL80211_IFTYPE_STATION)) {
 		beacon_configured = false;
-		ieee80211_iterate_active_interfaces_atomic(priv->hw,
-							   ath9k_htc_beacon_iter,
-							   &beacon_configured);
+		ieee80211_iterate_active_interfaces_atomic(
+			priv->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+			ath9k_htc_beacon_iter, &beacon_configured);
 
 		if (beacon_configured) {
 			ath_dbg(common, CONFIG,
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 66f6a74c508e..02cce95331d8 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -127,8 +127,9 @@ static void ath9k_htc_vif_reconfig(struct ath9k_htc_priv *priv)
 	priv->rearm_ani = false;
 	priv->reconfig_beacon = false;
 
-	ieee80211_iterate_active_interfaces_atomic(priv->hw,
-						   ath9k_htc_vif_iter, priv);
+	ieee80211_iterate_active_interfaces_atomic(
+		priv->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+		ath9k_htc_vif_iter, priv);
 	if (priv->rearm_ani)
 		ath9k_htc_start_ani(priv);
 
@@ -165,8 +166,9 @@ static void ath9k_htc_set_bssid_mask(struct ath9k_htc_priv *priv,
 		ath9k_htc_bssid_iter(&iter_data, vif->addr, vif);
 
 	/* Get list of all active MAC addresses */
-	ieee80211_iterate_active_interfaces_atomic(priv->hw, ath9k_htc_bssid_iter,
-						   &iter_data);
+	ieee80211_iterate_active_interfaces_atomic(
+		priv->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+		ath9k_htc_bssid_iter, &iter_data);
 
 	memcpy(common->bssidmask, iter_data.mask, ETH_ALEN);
 	ath_hw_setbssidmask(common);
@@ -1144,8 +1146,9 @@ static void ath9k_htc_remove_interface(struct ieee80211_hw *hw,
 	 */
 	if ((vif->type == NL80211_IFTYPE_AP) && (priv->num_ap_vif == 0)) {
 		priv->rearm_ani = false;
-		ieee80211_iterate_active_interfaces_atomic(priv->hw,
-						   ath9k_htc_vif_iter, priv);
+		ieee80211_iterate_active_interfaces_atomic(
+			priv->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+			ath9k_htc_vif_iter, priv);
 		if (!priv->rearm_ani)
 			ath9k_htc_stop_ani(priv);
 	}
@@ -1466,8 +1469,9 @@ static void ath9k_htc_bss_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 static void ath9k_htc_choose_set_bssid(struct ath9k_htc_priv *priv)
 {
 	if (priv->num_sta_assoc_vif == 1) {
-		ieee80211_iterate_active_interfaces_atomic(priv->hw,
-							   ath9k_htc_bss_iter, priv);
+		ieee80211_iterate_active_interfaces_atomic(
+			priv->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+			ath9k_htc_bss_iter, priv);
 		ath9k_htc_set_bssid(priv);
 	}
 }
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 578a7234aa56..c084532291a1 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -924,8 +924,9 @@ void ath9k_calculate_iter_data(struct ieee80211_hw *hw,
 		ath9k_vif_iter(iter_data, vif->addr, vif);
 
 	/* Get list of all active MAC addresses */
-	ieee80211_iterate_active_interfaces_atomic(sc->hw, ath9k_vif_iter,
-						   iter_data);
+	ieee80211_iterate_active_interfaces_atomic(
+		sc->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+		ath9k_vif_iter, iter_data);
 }
 
 /* Called with sc->mutex held. */
@@ -975,8 +976,9 @@ static void ath9k_calculate_summary_state(struct ieee80211_hw *hw,
 	if (ah->opmode == NL80211_IFTYPE_STATION &&
 	    old_opmode == NL80211_IFTYPE_AP &&
 	    test_bit(SC_OP_PRIM_STA_VIF, &sc->sc_flags)) {
-		ieee80211_iterate_active_interfaces_atomic(sc->hw,
-						   ath9k_sta_vif_iter, sc);
+		ieee80211_iterate_active_interfaces_atomic(
+			sc->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+			ath9k_sta_vif_iter, sc);
 	}
 }
 
@@ -1505,8 +1507,9 @@ static void ath9k_bss_info_changed(struct ieee80211_hw *hw,
 				clear_bit(SC_OP_BEACONS, &sc->sc_flags);
 		}
 
-		ieee80211_iterate_active_interfaces_atomic(sc->hw,
-						   ath9k_bss_assoc_iter, sc);
+		ieee80211_iterate_active_interfaces_atomic(
+			sc->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+			ath9k_bss_assoc_iter, sc);
 
 		if (!test_bit(SC_OP_PRIM_STA_VIF, &sc->sc_flags) &&
 		    ah->opmode == NL80211_IFTYPE_STATION) {
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 9b4f76718db7..a8ec7086ad09 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -571,6 +571,7 @@ static bool mac80211_hwsim_addr_match(struct mac80211_hwsim_data *data,
 	md.ret = false;
 	md.addr = addr;
 	ieee80211_iterate_active_interfaces_atomic(data->hw,
+						   IEEE80211_IFACE_ITER_NORMAL,
 						   mac80211_hwsim_addr_iter,
 						   &md);
 
@@ -744,8 +745,8 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw,
 		if (!hwsim_chans_compat(chan, data2->tmp_chan) &&
 		    !hwsim_chans_compat(chan, data2->channel)) {
 			ieee80211_iterate_active_interfaces_atomic(
-				data2->hw, mac80211_hwsim_tx_iter,
-				&tx_iter_data);
+				data2->hw, IEEE80211_IFACE_ITER_NORMAL,
+				mac80211_hwsim_tx_iter, &tx_iter_data);
 			if (!tx_iter_data.receive)
 				continue;
 		}
@@ -958,7 +959,8 @@ static void mac80211_hwsim_beacon(unsigned long arg)
 		return;
 
 	ieee80211_iterate_active_interfaces_atomic(
-		hw, mac80211_hwsim_beacon_tx, hw);
+		hw, IEEE80211_IFACE_ITER_NORMAL,
+		mac80211_hwsim_beacon_tx, hw);
 
 	data->beacon_timer.expires = jiffies + data->beacon_int;
 	add_timer(&data->beacon_timer);
@@ -1680,14 +1682,17 @@ static int hwsim_fops_ps_write(void *dat, u64 val)
 
 	if (val == PS_MANUAL_POLL) {
 		ieee80211_iterate_active_interfaces(data->hw,
+						    IEEE80211_IFACE_ITER_NORMAL,
 						    hwsim_send_ps_poll, data);
 		data->ps_poll_pending = true;
 	} else if (old_ps == PS_DISABLED && val != PS_DISABLED) {
 		ieee80211_iterate_active_interfaces(data->hw,
+						    IEEE80211_IFACE_ITER_NORMAL,
 						    hwsim_send_nullfunc_ps,
 						    data);
 	} else if (old_ps != PS_DISABLED && val == PS_DISABLED) {
 		ieee80211_iterate_active_interfaces(data->hw,
+						    IEEE80211_IFACE_ITER_NORMAL,
 						    hwsim_send_nullfunc_no_ps,
 						    data);
 	}
diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c
index 69097d1faeb6..67d167993d45 100644
--- a/drivers/net/wireless/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/rt2x00/rt2x00dev.c
@@ -157,6 +157,7 @@ static void rt2x00lib_intf_scheduled(struct work_struct *work)
 	 * requested configurations.
 	 */
 	ieee80211_iterate_active_interfaces(rt2x00dev->hw,
+					    IEEE80211_IFACE_ITER_RESUME_ALL,
 					    rt2x00lib_intf_scheduled_iter,
 					    rt2x00dev);
 }
@@ -225,9 +226,9 @@ void rt2x00lib_beacondone(struct rt2x00_dev *rt2x00dev)
 		return;
 
 	/* send buffered bc/mc frames out for every bssid */
-	ieee80211_iterate_active_interfaces_atomic(rt2x00dev->hw,
-						   rt2x00lib_bc_buffer_iter,
-						   rt2x00dev);
+	ieee80211_iterate_active_interfaces_atomic(
+		rt2x00dev->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+		rt2x00lib_bc_buffer_iter, rt2x00dev);
 	/*
 	 * Devices with pre tbtt interrupt don't need to update the beacon
 	 * here as they will fetch the next beacon directly prior to
@@ -237,9 +238,9 @@ void rt2x00lib_beacondone(struct rt2x00_dev *rt2x00dev)
 		return;
 
 	/* fetch next beacon */
-	ieee80211_iterate_active_interfaces_atomic(rt2x00dev->hw,
-						   rt2x00lib_beaconupdate_iter,
-						   rt2x00dev);
+	ieee80211_iterate_active_interfaces_atomic(
+		rt2x00dev->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+		rt2x00lib_beaconupdate_iter, rt2x00dev);
 }
 EXPORT_SYMBOL_GPL(rt2x00lib_beacondone);
 
@@ -249,9 +250,9 @@ void rt2x00lib_pretbtt(struct rt2x00_dev *rt2x00dev)
 		return;
 
 	/* fetch next beacon */
-	ieee80211_iterate_active_interfaces_atomic(rt2x00dev->hw,
-						   rt2x00lib_beaconupdate_iter,
-						   rt2x00dev);
+	ieee80211_iterate_active_interfaces_atomic(
+		rt2x00dev->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+		rt2x00lib_beaconupdate_iter, rt2x00dev);
 }
 EXPORT_SYMBOL_GPL(rt2x00lib_pretbtt);
 
diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c
index 98a9e48f8e4a..ed7a1bb3f245 100644
--- a/drivers/net/wireless/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/rt2x00/rt2x00mac.c
@@ -424,9 +424,9 @@ int rt2x00mac_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 	if (!test_bit(DEVICE_STATE_ENABLED_RADIO, &rt2x00dev->flags))
 		return 0;
 
-	ieee80211_iterate_active_interfaces_atomic(rt2x00dev->hw,
-						   rt2x00mac_set_tim_iter,
-						   rt2x00dev);
+	ieee80211_iterate_active_interfaces_atomic(
+		rt2x00dev->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
+		rt2x00mac_set_tim_iter, rt2x00dev);
 
 	/* queue work to upodate the beacon template */
 	ieee80211_queue_work(rt2x00dev->hw, &rt2x00dev->intf_work);
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 25530c8760cb..380cf1ff6cd1 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -677,7 +677,7 @@ static void wl12xx_get_vif_count(struct ieee80211_hw *hw,
 	memset(data, 0, sizeof(*data));
 	data->cur_vif = cur_vif;
 
-	ieee80211_iterate_active_interfaces(hw,
+	ieee80211_iterate_active_interfaces(hw, IEEE80211_IFACE_ITER_RESUME_ALL,
 					    wl12xx_vif_count_iter, data);
 }
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index e1d830992319..a789dd1d4c10 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3412,6 +3412,21 @@ void ieee80211_sched_scan_results(struct ieee80211_hw *hw);
  */
 void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw);
 
+/**
+ * enum ieee80211_interface_iteration_flags - interface iteration flags
+ * @IEEE80211_IFACE_ITER_NORMAL: Iterate over all interfaces that have
+ *	been added to the driver; However, note that during hardware
+ *	reconfiguration (after restart_hw) it will iterate over a new
+ *	interface and over all the existing interfaces even if they
+ *	haven't been re-added to the driver yet.
+ * @IEEE80211_IFACE_ITER_RESUME_ALL: During resume, iterate over all
+ *	interfaces, even if they haven't been re-added to the driver yet.
+ */
+enum ieee80211_interface_iteration_flags {
+	IEEE80211_IFACE_ITER_NORMAL	= 0,
+	IEEE80211_IFACE_ITER_RESUME_ALL	= BIT(0),
+};
+
 /**
  * ieee80211_iterate_active_interfaces - iterate active interfaces
  *
@@ -3420,13 +3435,15 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw);
  * This function allows the iterator function to sleep, when the iterator
  * function is atomic @ieee80211_iterate_active_interfaces_atomic can
  * be used.
- * Does not iterate over a new interface during add_interface()
+ * Does not iterate over a new interface during add_interface().
  *
  * @hw: the hardware struct of which the interfaces should be iterated over
+ * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags
  * @iterator: the iterator function to call
  * @data: first argument of the iterator function
  */
 void ieee80211_iterate_active_interfaces(struct ieee80211_hw *hw,
+					 u32 iter_flags,
 					 void (*iterator)(void *data, u8 *mac,
 						struct ieee80211_vif *vif),
 					 void *data);
@@ -3438,13 +3455,15 @@ void ieee80211_iterate_active_interfaces(struct ieee80211_hw *hw,
  * hardware that are currently active and calls the callback for them.
  * This function requires the iterator callback function to be atomic,
  * if that is not desired, use @ieee80211_iterate_active_interfaces instead.
- * Does not iterate over a new interface during add_interface()
+ * Does not iterate over a new interface during add_interface().
  *
  * @hw: the hardware struct of which the interfaces should be iterated over
+ * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags
  * @iterator: the iterator function to call, cannot sleep
  * @data: first argument of the iterator function
  */
 void ieee80211_iterate_active_interfaces_atomic(struct ieee80211_hw *hw,
+						u32 iter_flags,
 						void (*iterator)(void *data,
 						    u8 *mac,
 						    struct ieee80211_vif *vif),
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 84858a14c8bf..01b9fa62f3e3 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -512,7 +512,7 @@ void ieee80211_wake_queues(struct ieee80211_hw *hw)
 EXPORT_SYMBOL(ieee80211_wake_queues);
 
 void ieee80211_iterate_active_interfaces(
-	struct ieee80211_hw *hw,
+	struct ieee80211_hw *hw, u32 iter_flags,
 	void (*iterator)(void *data, u8 *mac,
 			 struct ieee80211_vif *vif),
 	void *data)
@@ -530,6 +530,9 @@ void ieee80211_iterate_active_interfaces(
 		default:
 			break;
 		}
+		if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) &&
+		    !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
+			continue;
 		if (ieee80211_sdata_running(sdata))
 			iterator(data, sdata->vif.addr,
 				 &sdata->vif);
@@ -537,7 +540,9 @@ void ieee80211_iterate_active_interfaces(
 
 	sdata = rcu_dereference_protected(local->monitor_sdata,
 					  lockdep_is_held(&local->iflist_mtx));
-	if (sdata)
+	if (sdata &&
+	    (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL ||
+	     sdata->flags & IEEE80211_SDATA_IN_DRIVER))
 		iterator(data, sdata->vif.addr, &sdata->vif);
 
 	mutex_unlock(&local->iflist_mtx);
@@ -545,7 +550,7 @@ void ieee80211_iterate_active_interfaces(
 EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces);
 
 void ieee80211_iterate_active_interfaces_atomic(
-	struct ieee80211_hw *hw,
+	struct ieee80211_hw *hw, u32 iter_flags,
 	void (*iterator)(void *data, u8 *mac,
 			 struct ieee80211_vif *vif),
 	void *data)
@@ -563,13 +568,18 @@ void ieee80211_iterate_active_interfaces_atomic(
 		default:
 			break;
 		}
+		if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) &&
+		    !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
+			continue;
 		if (ieee80211_sdata_running(sdata))
 			iterator(data, sdata->vif.addr,
 				 &sdata->vif);
 	}
 
 	sdata = rcu_dereference(local->monitor_sdata);
-	if (sdata)
+	if (sdata &&
+	    (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL ||
+	     sdata->flags & IEEE80211_SDATA_IN_DRIVER))
 		iterator(data, sdata->vif.addr, &sdata->vif);
 
 	rcu_read_unlock();
-- 
cgit v1.2.3-55-g7522


From a8638030f668884720b8f4456448d0ce33952b05 Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Fri, 9 Nov 2012 09:12:29 -0800
Subject: cgroup: add cgroup_subsys->post_create()

Currently, there's no way for a controller to find out whether a new
cgroup finished all ->create() allocatinos successfully and is
considered "live" by cgroup.

This becomes a problem later when we add generic descendants walking
to cgroup which can be used by controllers as controllers don't have a
synchronization point where it can synchronize against new cgroups
appearing in such walks.

This patch adds ->post_create().  It's called after all ->create()
succeeded and the cgroup is linked into the generic cgroup hierarchy.
This plays the counterpart of ->pre_destroy().

When used in combination with the to-be-added generic descendant
iterators, ->post_create() can be used to implement reliable state
inheritance.  It will be explained with the descendant iterators.

v2: Added a paragraph about its future use w/ descendant iterators per
    Michal.

v3: Forgot to add ->post_create() invocation to cgroup_load_subsys().
    Fixed.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Glauber Costa <glommer@parallels.com>
---
 include/linux/cgroup.h |  1 +
 kernel/cgroup.c        | 15 +++++++++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index fe876a77031a..b4421221111d 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -438,6 +438,7 @@ int cgroup_taskset_size(struct cgroup_taskset *tset);
 
 struct cgroup_subsys {
 	struct cgroup_subsys_state *(*create)(struct cgroup *cgrp);
+	void (*post_create)(struct cgroup *cgrp);
 	void (*pre_destroy)(struct cgroup *cgrp);
 	void (*destroy)(struct cgroup *cgrp);
 	int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 998ab5957c6a..26f2edbaf4f5 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4059,10 +4059,15 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (err < 0)
 		goto err_remove;
 
-	/* each css holds a ref to the cgroup's dentry */
-	for_each_subsys(root, ss)
+	for_each_subsys(root, ss) {
+		/* each css holds a ref to the cgroup's dentry */
 		dget(dentry);
 
+		/* creation succeeded, notify subsystems */
+		if (ss->post_create)
+			ss->post_create(cgrp);
+	}
+
 	/* The cgroup directory was pre-locked for us */
 	BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex));
 
@@ -4280,6 +4285,9 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 
 	ss->active = 1;
 
+	if (ss->post_create)
+		ss->post_create(&ss->root->top_cgroup);
+
 	/* this function shouldn't be used with modular subsystems, since they
 	 * need to register a subsys_id, among other things */
 	BUG_ON(ss->module);
@@ -4389,6 +4397,9 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 
 	ss->active = 1;
 
+	if (ss->post_create)
+		ss->post_create(&ss->root->top_cgroup);
+
 	/* success! */
 	mutex_unlock(&cgroup_mutex);
 	return 0;
-- 
cgit v1.2.3-55-g7522


From eb6fd5040ee799009173daa49c3e7aa0362167c9 Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Fri, 9 Nov 2012 09:12:29 -0800
Subject: cgroup: use rculist ops for cgroup->children

Use RCU safe list operations for cgroup->children.  This will be used
to implement cgroup children / descendant walking which can be used by
controllers.

Note that cgroup_create() now puts a new cgroup at the end of the
->children list instead of head.  This isn't strictly necessary but is
done so that the iteration order is more conventional.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h | 1 +
 kernel/cgroup.c        | 8 +++-----
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b4421221111d..90c33ebdd6bc 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -12,6 +12,7 @@
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/rcupdate.h>
+#include <linux/rculist.h>
 #include <linux/cgroupstats.h>
 #include <linux/prio_heap.h>
 #include <linux/rwsem.h>
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 26f2edbaf4f5..2ed5968a04e7 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1650,7 +1650,6 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 
 		free_cg_links(&tmp_cg_links);
 
-		BUG_ON(!list_empty(&root_cgrp->sibling));
 		BUG_ON(!list_empty(&root_cgrp->children));
 		BUG_ON(root->number_of_cgroups != 1);
 
@@ -1699,7 +1698,6 @@ static void cgroup_kill_sb(struct super_block *sb) {
 
 	BUG_ON(root->number_of_cgroups != 1);
 	BUG_ON(!list_empty(&cgrp->children));
-	BUG_ON(!list_empty(&cgrp->sibling));
 
 	mutex_lock(&cgroup_mutex);
 	mutex_lock(&cgroup_root_mutex);
@@ -4052,7 +4050,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 		}
 	}
 
-	list_add(&cgrp->sibling, &cgrp->parent->children);
+	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
 	root->number_of_cgroups++;
 
 	err = cgroup_create_dir(cgrp, dentry, mode);
@@ -4083,7 +4081,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
  err_remove:
 
-	list_del(&cgrp->sibling);
+	list_del_rcu(&cgrp->sibling);
 	root->number_of_cgroups--;
 
  err_destroy:
@@ -4209,7 +4207,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	raw_spin_unlock(&release_list_lock);
 
 	/* delete this cgroup from parent->children */
-	list_del_init(&cgrp->sibling);
+	list_del_rcu(&cgrp->sibling);
 
 	list_del_init(&cgrp->allcg_node);
 
-- 
cgit v1.2.3-55-g7522


From 574bd9f7c7c1d32f52dea5488018a6ff79031e22 Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Fri, 9 Nov 2012 09:12:29 -0800
Subject: cgroup: implement generic child / descendant walk macros

Currently, cgroup doesn't provide any generic helper for walking a
given cgroup's children or descendants.  This patch adds the following
three macros.

* cgroup_for_each_child() - walk immediate children of a cgroup.

* cgroup_for_each_descendant_pre() - visit all descendants of a cgroup
  in pre-order tree traversal.

* cgroup_for_each_descendant_post() - visit all descendants of a
  cgroup in post-order tree traversal.

All three only require the user to hold RCU read lock during
traversal.  Verifying that each iterated cgroup is online is the
responsibility of the user.  When used with proper synchronization,
cgroup_for_each_descendant_pre() can be used to propagate state
updates to descendants in reliable way.  See comments for details.

v2: s/config/state/ in commit message and comments per Michal.  More
    documentation on synchronization rules.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujisu.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h | 94 ++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/cgroup.c        | 86 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 180 insertions(+)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 90c33ebdd6bc..8f64b459fbd4 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -534,6 +534,100 @@ static inline struct cgroup* task_cgroup(struct task_struct *task,
 	return task_subsys_state(task, subsys_id)->cgroup;
 }
 
+/**
+ * cgroup_for_each_child - iterate through children of a cgroup
+ * @pos: the cgroup * to use as the loop cursor
+ * @cgroup: cgroup whose children to walk
+ *
+ * Walk @cgroup's children.  Must be called under rcu_read_lock().  A child
+ * cgroup which hasn't finished ->post_create() or already has finished
+ * ->pre_destroy() may show up during traversal and it's each subsystem's
+ * responsibility to verify that each @pos is alive.
+ *
+ * If a subsystem synchronizes against the parent in its ->post_create()
+ * and before starting iterating, a cgroup which finished ->post_create()
+ * is guaranteed to be visible in the future iterations.
+ */
+#define cgroup_for_each_child(pos, cgroup)				\
+	list_for_each_entry_rcu(pos, &(cgroup)->children, sibling)
+
+struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
+					  struct cgroup *cgroup);
+
+/**
+ * cgroup_for_each_descendant_pre - pre-order walk of a cgroup's descendants
+ * @pos: the cgroup * to use as the loop cursor
+ * @cgroup: cgroup whose descendants to walk
+ *
+ * Walk @cgroup's descendants.  Must be called under rcu_read_lock().  A
+ * descendant cgroup which hasn't finished ->post_create() or already has
+ * finished ->pre_destroy() may show up during traversal and it's each
+ * subsystem's responsibility to verify that each @pos is alive.
+ *
+ * If a subsystem synchronizes against the parent in its ->post_create()
+ * and before starting iterating, and synchronizes against @pos on each
+ * iteration, any descendant cgroup which finished ->post_create() is
+ * guaranteed to be visible in the future iterations.
+ *
+ * In other words, the following guarantees that a descendant can't escape
+ * state updates of its ancestors.
+ *
+ * my_post_create(@cgrp)
+ * {
+ *	Lock @cgrp->parent and @cgrp;
+ *	Inherit state from @cgrp->parent;
+ *	Unlock both.
+ * }
+ *
+ * my_update_state(@cgrp)
+ * {
+ *	Lock @cgrp;
+ *	Update @cgrp's state;
+ *	Unlock @cgrp;
+ *
+ *	cgroup_for_each_descendant_pre(@pos, @cgrp) {
+ *		Lock @pos;
+ *		Verify @pos is alive and inherit state from @pos->parent;
+ *		Unlock @pos;
+ *	}
+ * }
+ *
+ * As long as the inheriting step, including checking the parent state, is
+ * enclosed inside @pos locking, double-locking the parent isn't necessary
+ * while inheriting.  The state update to the parent is guaranteed to be
+ * visible by walking order and, as long as inheriting operations to the
+ * same @pos are atomic to each other, multiple updates racing each other
+ * still result in the correct state.  It's guaranateed that at least one
+ * inheritance happens for any cgroup after the latest update to its
+ * parent.
+ *
+ * If checking parent's state requires locking the parent, each inheriting
+ * iteration should lock and unlock both @pos->parent and @pos.
+ *
+ * Alternatively, a subsystem may choose to use a single global lock to
+ * synchronize ->post_create() and ->pre_destroy() against tree-walking
+ * operations.
+ */
+#define cgroup_for_each_descendant_pre(pos, cgroup)			\
+	for (pos = cgroup_next_descendant_pre(NULL, (cgroup)); (pos);	\
+	     pos = cgroup_next_descendant_pre((pos), (cgroup)))
+
+struct cgroup *cgroup_next_descendant_post(struct cgroup *pos,
+					   struct cgroup *cgroup);
+
+/**
+ * cgroup_for_each_descendant_post - post-order walk of a cgroup's descendants
+ * @pos: the cgroup * to use as the loop cursor
+ * @cgroup: cgroup whose descendants to walk
+ *
+ * Similar to cgroup_for_each_descendant_pre() but performs post-order
+ * traversal instead.  Note that the walk visibility guarantee described in
+ * pre-order walk doesn't apply the same to post-order walks.
+ */
+#define cgroup_for_each_descendant_post(pos, cgroup)			\
+	for (pos = cgroup_next_descendant_post(NULL, (cgroup)); (pos);	\
+	     pos = cgroup_next_descendant_post((pos), (cgroup)))
+
 /* A cgroup_iter should be treated as an opaque object */
 struct cgroup_iter {
 	struct list_head *cg_link;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2ed5968a04e7..0f8fa6aa371b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2984,6 +2984,92 @@ static void cgroup_enable_task_cg_lists(void)
 	write_unlock(&css_set_lock);
 }
 
+/**
+ * cgroup_next_descendant_pre - find the next descendant for pre-order walk
+ * @pos: the current position (%NULL to initiate traversal)
+ * @cgroup: cgroup whose descendants to walk
+ *
+ * To be used by cgroup_for_each_descendant_pre().  Find the next
+ * descendant to visit for pre-order traversal of @cgroup's descendants.
+ */
+struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
+					  struct cgroup *cgroup)
+{
+	struct cgroup *next;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* if first iteration, pretend we just visited @cgroup */
+	if (!pos) {
+		if (list_empty(&cgroup->children))
+			return NULL;
+		pos = cgroup;
+	}
+
+	/* visit the first child if exists */
+	next = list_first_or_null_rcu(&pos->children, struct cgroup, sibling);
+	if (next)
+		return next;
+
+	/* no child, visit my or the closest ancestor's next sibling */
+	do {
+		next = list_entry_rcu(pos->sibling.next, struct cgroup,
+				      sibling);
+		if (&next->sibling != &pos->parent->children)
+			return next;
+
+		pos = pos->parent;
+	} while (pos != cgroup);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(cgroup_next_descendant_pre);
+
+static struct cgroup *cgroup_leftmost_descendant(struct cgroup *pos)
+{
+	struct cgroup *last;
+
+	do {
+		last = pos;
+		pos = list_first_or_null_rcu(&pos->children, struct cgroup,
+					     sibling);
+	} while (pos);
+
+	return last;
+}
+
+/**
+ * cgroup_next_descendant_post - find the next descendant for post-order walk
+ * @pos: the current position (%NULL to initiate traversal)
+ * @cgroup: cgroup whose descendants to walk
+ *
+ * To be used by cgroup_for_each_descendant_post().  Find the next
+ * descendant to visit for post-order traversal of @cgroup's descendants.
+ */
+struct cgroup *cgroup_next_descendant_post(struct cgroup *pos,
+					   struct cgroup *cgroup)
+{
+	struct cgroup *next;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* if first iteration, visit the leftmost descendant */
+	if (!pos) {
+		next = cgroup_leftmost_descendant(cgroup);
+		return next != cgroup ? next : NULL;
+	}
+
+	/* if there's an unvisited sibling, visit its leftmost descendant */
+	next = list_entry_rcu(pos->sibling.next, struct cgroup, sibling);
+	if (&next->sibling != &pos->parent->children)
+		return cgroup_leftmost_descendant(next);
+
+	/* no sibling left, visit parent */
+	next = pos->parent;
+	return next != cgroup ? next : NULL;
+}
+EXPORT_SYMBOL_GPL(cgroup_next_descendant_post);
+
 void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
 	__acquires(css_set_lock)
 {
-- 
cgit v1.2.3-55-g7522


From b891b4dc1eed33543c5818dae43ce8bb55f2080c Mon Sep 17 00:00:00 2001
From: Jingoo Han
Date: Fri, 9 Nov 2012 15:56:03 +0900
Subject: PCI: Fix bit definitions of PCI_EXP_LNKCAP2 register

According to the PCIe 3.0 spec, PCI_EXP_LNKCAP2_SLS_2_5GB is
1st bit of PCI_EXP_LNKCAP2 register, not 0th bit. So, the bit
definition of supported link speed vector should be fixed.

[bhelgaas: change "Current" to "Supported"]
Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>---
 include/uapi/linux/pci_regs.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 20ae747ddf34..259763d2df71 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -544,9 +544,9 @@
 #define  PCI_EXP_OBFF_WAKE_EN	0x6000	/* OBFF using WAKE# signaling */
 #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	44	/* v2 endpoints end here */
 #define PCI_EXP_LNKCAP2		44	/* Link Capability 2 */
-#define  PCI_EXP_LNKCAP2_SLS_2_5GB 0x01	/* Current Link Speed 2.5GT/s */
-#define  PCI_EXP_LNKCAP2_SLS_5_0GB 0x02	/* Current Link Speed 5.0GT/s */
-#define  PCI_EXP_LNKCAP2_SLS_8_0GB 0x04	/* Current Link Speed 8.0GT/s */
+#define  PCI_EXP_LNKCAP2_SLS_2_5GB 0x02	/* Supported Link Speed 2.5GT/s */
+#define  PCI_EXP_LNKCAP2_SLS_5_0GB 0x04	/* Supported Link Speed 5.0GT/s */
+#define  PCI_EXP_LNKCAP2_SLS_8_0GB 0x08	/* Supported Link Speed 8.0GT/s */
 #define  PCI_EXP_LNKCAP2_CROSSLINK 0x100 /* Crosslink supported */
 #define PCI_EXP_LNKCTL2		48	/* Link Control 2 */
 #define PCI_EXP_LNKSTA2		50	/* Link Status 2 */
-- 
cgit v1.2.3-55-g7522


From d77807230e1ef30dbdee85aa24d27073a14dd168 Mon Sep 17 00:00:00 2001
From: David Howells
Date: Wed, 7 Nov 2012 02:37:17 +0000
Subject: UAPI: (Scripted) Disintegrate include/linux/hdlc

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Dave Jones <davej@redhat.com>
Acked-by: Krzysztof Halasa <khc@pm.waw.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/hdlc/Kbuild       |  1 -
 include/linux/hdlc/ioctl.h      | 81 -----------------------------------------
 include/uapi/linux/hdlc/Kbuild  |  1 +
 include/uapi/linux/hdlc/ioctl.h | 81 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 82 insertions(+), 82 deletions(-)
 delete mode 100644 include/linux/hdlc/ioctl.h
 create mode 100644 include/uapi/linux/hdlc/ioctl.h

(limited to 'include')

diff --git a/include/linux/hdlc/Kbuild b/include/linux/hdlc/Kbuild
index 1fb26448faa9..e69de29bb2d1 100644
--- a/include/linux/hdlc/Kbuild
+++ b/include/linux/hdlc/Kbuild
@@ -1 +0,0 @@
-header-y += ioctl.h
diff --git a/include/linux/hdlc/ioctl.h b/include/linux/hdlc/ioctl.h
deleted file mode 100644
index 583972364357..000000000000
--- a/include/linux/hdlc/ioctl.h
+++ /dev/null
@@ -1,81 +0,0 @@
-#ifndef __HDLC_IOCTL_H__
-#define __HDLC_IOCTL_H__
-
-
-#define GENERIC_HDLC_VERSION 4	/* For synchronization with sethdlc utility */
-
-#define CLOCK_DEFAULT   0	/* Default setting */
-#define CLOCK_EXT	1	/* External TX and RX clock - DTE */
-#define CLOCK_INT	2	/* Internal TX and RX clock - DCE */
-#define CLOCK_TXINT	3	/* Internal TX and external RX clock */
-#define CLOCK_TXFROMRX	4	/* TX clock derived from external RX clock */
-
-
-#define ENCODING_DEFAULT	0 /* Default setting */
-#define ENCODING_NRZ		1
-#define ENCODING_NRZI		2
-#define ENCODING_FM_MARK	3
-#define ENCODING_FM_SPACE	4
-#define ENCODING_MANCHESTER	5
-
-
-#define PARITY_DEFAULT		0 /* Default setting */
-#define PARITY_NONE		1 /* No parity */
-#define PARITY_CRC16_PR0	2 /* CRC16, initial value 0x0000 */
-#define PARITY_CRC16_PR1	3 /* CRC16, initial value 0xFFFF */
-#define PARITY_CRC16_PR0_CCITT	4 /* CRC16, initial 0x0000, ITU-T version */
-#define PARITY_CRC16_PR1_CCITT	5 /* CRC16, initial 0xFFFF, ITU-T version */
-#define PARITY_CRC32_PR0_CCITT	6 /* CRC32, initial value 0x00000000 */
-#define PARITY_CRC32_PR1_CCITT	7 /* CRC32, initial value 0xFFFFFFFF */
-
-#define LMI_DEFAULT		0 /* Default setting */
-#define LMI_NONE		1 /* No LMI, all PVCs are static */
-#define LMI_ANSI		2 /* ANSI Annex D */
-#define LMI_CCITT		3 /* ITU-T Annex A */
-#define LMI_CISCO		4 /* The "original" LMI, aka Gang of Four */
-
-typedef struct { 
-	unsigned int clock_rate; /* bits per second */
-	unsigned int clock_type; /* internal, external, TX-internal etc. */
-	unsigned short loopback;
-} sync_serial_settings;          /* V.35, V.24, X.21 */
-
-typedef struct { 
-	unsigned int clock_rate; /* bits per second */
-	unsigned int clock_type; /* internal, external, TX-internal etc. */
-	unsigned short loopback;
-	unsigned int slot_map;
-} te1_settings;                  /* T1, E1 */
-
-typedef struct {
-	unsigned short encoding;
-	unsigned short parity;
-} raw_hdlc_proto;
-
-typedef struct {
-	unsigned int t391;
-	unsigned int t392;
-	unsigned int n391;
-	unsigned int n392;
-	unsigned int n393;
-	unsigned short lmi;
-	unsigned short dce; /* 1 for DCE (network side) operation */
-} fr_proto;
-
-typedef struct {
-	unsigned int dlci;
-} fr_proto_pvc;          /* for creating/deleting FR PVCs */
-
-typedef struct {
-	unsigned int dlci;
-	char master[IFNAMSIZ];	/* Name of master FRAD device */
-}fr_proto_pvc_info;		/* for returning PVC information only */
-
-typedef struct {
-    unsigned int interval;
-    unsigned int timeout;
-} cisco_proto;
-
-/* PPP doesn't need any info now - supply length = 0 to ioctl */
-
-#endif /* __HDLC_IOCTL_H__ */
diff --git a/include/uapi/linux/hdlc/Kbuild b/include/uapi/linux/hdlc/Kbuild
index aafaa5aa54d4..8c1d2cb75e33 100644
--- a/include/uapi/linux/hdlc/Kbuild
+++ b/include/uapi/linux/hdlc/Kbuild
@@ -1 +1,2 @@
 # UAPI Header export list
+header-y += ioctl.h
diff --git a/include/uapi/linux/hdlc/ioctl.h b/include/uapi/linux/hdlc/ioctl.h
new file mode 100644
index 000000000000..46939b24d612
--- /dev/null
+++ b/include/uapi/linux/hdlc/ioctl.h
@@ -0,0 +1,81 @@
+#ifndef __HDLC_IOCTL_H__
+#define __HDLC_IOCTL_H__
+
+
+#define GENERIC_HDLC_VERSION 4	/* For synchronization with sethdlc utility */
+
+#define CLOCK_DEFAULT   0	/* Default setting */
+#define CLOCK_EXT	1	/* External TX and RX clock - DTE */
+#define CLOCK_INT	2	/* Internal TX and RX clock - DCE */
+#define CLOCK_TXINT	3	/* Internal TX and external RX clock */
+#define CLOCK_TXFROMRX	4	/* TX clock derived from external RX clock */
+
+
+#define ENCODING_DEFAULT	0 /* Default setting */
+#define ENCODING_NRZ		1
+#define ENCODING_NRZI		2
+#define ENCODING_FM_MARK	3
+#define ENCODING_FM_SPACE	4
+#define ENCODING_MANCHESTER	5
+
+
+#define PARITY_DEFAULT		0 /* Default setting */
+#define PARITY_NONE		1 /* No parity */
+#define PARITY_CRC16_PR0	2 /* CRC16, initial value 0x0000 */
+#define PARITY_CRC16_PR1	3 /* CRC16, initial value 0xFFFF */
+#define PARITY_CRC16_PR0_CCITT	4 /* CRC16, initial 0x0000, ITU-T version */
+#define PARITY_CRC16_PR1_CCITT	5 /* CRC16, initial 0xFFFF, ITU-T version */
+#define PARITY_CRC32_PR0_CCITT	6 /* CRC32, initial value 0x00000000 */
+#define PARITY_CRC32_PR1_CCITT	7 /* CRC32, initial value 0xFFFFFFFF */
+
+#define LMI_DEFAULT		0 /* Default setting */
+#define LMI_NONE		1 /* No LMI, all PVCs are static */
+#define LMI_ANSI		2 /* ANSI Annex D */
+#define LMI_CCITT		3 /* ITU-T Annex A */
+#define LMI_CISCO		4 /* The "original" LMI, aka Gang of Four */
+
+typedef struct {
+	unsigned int clock_rate; /* bits per second */
+	unsigned int clock_type; /* internal, external, TX-internal etc. */
+	unsigned short loopback;
+} sync_serial_settings;          /* V.35, V.24, X.21 */
+
+typedef struct {
+	unsigned int clock_rate; /* bits per second */
+	unsigned int clock_type; /* internal, external, TX-internal etc. */
+	unsigned short loopback;
+	unsigned int slot_map;
+} te1_settings;                  /* T1, E1 */
+
+typedef struct {
+	unsigned short encoding;
+	unsigned short parity;
+} raw_hdlc_proto;
+
+typedef struct {
+	unsigned int t391;
+	unsigned int t392;
+	unsigned int n391;
+	unsigned int n392;
+	unsigned int n393;
+	unsigned short lmi;
+	unsigned short dce; /* 1 for DCE (network side) operation */
+} fr_proto;
+
+typedef struct {
+	unsigned int dlci;
+} fr_proto_pvc;          /* for creating/deleting FR PVCs */
+
+typedef struct {
+	unsigned int dlci;
+	char master[IFNAMSIZ];	/* Name of master FRAD device */
+}fr_proto_pvc_info;		/* for returning PVC information only */
+
+typedef struct {
+    unsigned int interval;
+    unsigned int timeout;
+} cisco_proto;
+
+/* PPP doesn't need any info now - supply length = 0 to ioctl */
+
+#endif /* __HDLC_IOCTL_H__ */
-- 
cgit v1.2.3-55-g7522


From c48c8d51c29efba160a1b27555d97f6ee0d049a6 Mon Sep 17 00:00:00 2001
From: David Howells
Date: Wed, 7 Nov 2012 02:37:24 +0000
Subject: Fix the wanxl firmware to include missing constants

Fix the wanxl firmware to include missing constants such as PARITY_NONE.  It
should be #including the linux/hdlc/ioctl.h header.

To make this work, we also have to guard parts of ioctl.h with !__ASSEMBLY__.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/Makefile        | 2 +-
 drivers/net/wan/wanxlfw.S       | 1 +
 include/uapi/linux/hdlc/ioctl.h | 3 +++
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile
index 4dac96b3db2a..b0a61636fc94 100644
--- a/drivers/net/wan/Makefile
+++ b/drivers/net/wan/Makefile
@@ -52,7 +52,7 @@ endif
 
 quiet_cmd_build_wanxlfw = BLD FW  $@
       cmd_build_wanxlfw = \
-	$(CPP) -Wp,-MD,$(depfile) -I$(srctree)/include/uapi $< | $(AS68K) -m68360 -o $(obj)/wanxlfw.o; \
+	$(CPP) -D__ASSEMBLY__ -Wp,-MD,$(depfile) -I$(srctree)/include/uapi $< | $(AS68K) -m68360 -o $(obj)/wanxlfw.o; \
 	$(LD68K) --oformat binary -Ttext 0x1000 $(obj)/wanxlfw.o -o $(obj)/wanxlfw.bin; \
 	hexdump -ve '"\n" 16/1 "0x%02X,"' $(obj)/wanxlfw.bin | sed 's/0x  ,//g;1s/^/static u8 firmware[]={/;$$s/,$$/\n};\n/' >$(obj)/wanxlfw.inc; \
 	rm -f $(obj)/wanxlfw.bin $(obj)/wanxlfw.o
diff --git a/drivers/net/wan/wanxlfw.S b/drivers/net/wan/wanxlfw.S
index 73aae2bf2f1c..21565d59ec7b 100644
--- a/drivers/net/wan/wanxlfw.S
+++ b/drivers/net/wan/wanxlfw.S
@@ -35,6 +35,7 @@
 */
 
 #include <linux/hdlc.h>
+#include <linux/hdlc/ioctl.h>
 #include "wanxl.h"
 
 /* memory addresses and offsets */
diff --git a/include/uapi/linux/hdlc/ioctl.h b/include/uapi/linux/hdlc/ioctl.h
index 46939b24d612..04bc0274a189 100644
--- a/include/uapi/linux/hdlc/ioctl.h
+++ b/include/uapi/linux/hdlc/ioctl.h
@@ -34,6 +34,8 @@
 #define LMI_CCITT		3 /* ITU-T Annex A */
 #define LMI_CISCO		4 /* The "original" LMI, aka Gang of Four */
 
+#ifndef __ASSEMBLY__
+
 typedef struct {
 	unsigned int clock_rate; /* bits per second */
 	unsigned int clock_type; /* internal, external, TX-internal etc. */
@@ -78,4 +80,5 @@ typedef struct {
 
 /* PPP doesn't need any info now - supply length = 0 to ioctl */
 
+#endif /* __ASSEMBLY__ */
 #endif /* __HDLC_IOCTL_H__ */
-- 
cgit v1.2.3-55-g7522


From 0974658da47cb399b76794057823bf3cd22acf37 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Fri, 9 Nov 2012 06:09:59 +0000
Subject: ipip: advertise tunnel param via rtnl

It is usefull for daemons that monitor link event to have the full parameters of
these interfaces when a rtnl message is sent.
It allows also to dump them via rtnetlink.

It is based on what is done for GRE tunnels.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_tunnel.h | 11 ++++++++
 net/ipv4/ipip.c                | 57 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 67 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 5db5942575fe..ccb21d585bf4 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -37,6 +37,17 @@ struct ip_tunnel_parm {
 	struct iphdr		iph;
 };
 
+enum {
+	IFLA_IPTUN_UNSPEC,
+	IFLA_IPTUN_LINK,
+	IFLA_IPTUN_LOCAL,
+	IFLA_IPTUN_REMOTE,
+	IFLA_IPTUN_TTL,
+	IFLA_IPTUN_TOS,
+	__IFLA_IPTUN_MAX,
+};
+#define IFLA_IPTUN_MAX	(__IFLA_IPTUN_MAX - 1)
+
 /* SIT-mode i_flags */
 #define	SIT_ISATAP	0x0001
 
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index cc49cc1ff3b9..720855e41100 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -138,6 +138,7 @@ struct ipip_net {
 static int ipip_tunnel_init(struct net_device *dev);
 static void ipip_tunnel_setup(struct net_device *dev);
 static void ipip_dev_free(struct net_device *dev);
+static struct rtnl_link_ops ipip_link_ops __read_mostly;
 
 /*
  * Locking : hash tables are protected by RCU and RTNL
@@ -305,6 +306,7 @@ static struct ip_tunnel *ipip_tunnel_locate(struct net *net,
 		goto failed_free;
 
 	strcpy(nt->parms.name, dev->name);
+	dev->rtnl_link_ops = &ipip_link_ops;
 
 	dev_hold(dev);
 	ipip_tunnel_link(ipn, nt);
@@ -841,6 +843,47 @@ static int __net_init ipip_fb_tunnel_init(struct net_device *dev)
 	return 0;
 }
 
+static size_t ipip_get_size(const struct net_device *dev)
+{
+	return
+		/* IFLA_IPTUN_LINK */
+		nla_total_size(4) +
+		/* IFLA_IPTUN_LOCAL */
+		nla_total_size(4) +
+		/* IFLA_IPTUN_REMOTE */
+		nla_total_size(4) +
+		/* IFLA_IPTUN_TTL */
+		nla_total_size(1) +
+		/* IFLA_IPTUN_TOS */
+		nla_total_size(1) +
+		0;
+}
+
+static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	struct ip_tunnel_parm *parm = &tunnel->parms;
+
+	if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
+	    nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
+	    nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
+	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) ||
+	    nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static struct rtnl_link_ops ipip_link_ops __read_mostly = {
+	.kind		= "ipip",
+	.maxtype	= IFLA_IPTUN_MAX,
+	.priv_size	= sizeof(struct ip_tunnel),
+	.get_size	= ipip_get_size,
+	.fill_info	= ipip_fill_info,
+};
+
 static struct xfrm_tunnel ipip_handler __read_mostly = {
 	.handler	=	ipip_rcv,
 	.err_handler	=	ipip_err,
@@ -937,14 +980,26 @@ static int __init ipip_init(void)
 		return err;
 	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
 	if (err < 0) {
-		unregister_pernet_device(&ipip_net_ops);
 		pr_info("%s: can't register tunnel\n", __func__);
+		goto xfrm_tunnel_failed;
 	}
+	err = rtnl_link_register(&ipip_link_ops);
+	if (err < 0)
+		goto rtnl_link_failed;
+
+out:
 	return err;
+
+rtnl_link_failed:
+	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+xfrm_tunnel_failed:
+	unregister_pernet_device(&ipip_net_ops);
+	goto out;
 }
 
 static void __exit ipip_fini(void)
 {
+	rtnl_link_unregister(&ipip_link_ops);
 	if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET))
 		pr_info("%s: can't deregister tunnel\n", __func__);
 
-- 
cgit v1.2.3-55-g7522


From c075b13098b399dc565b4d53f42047a8d40ed3ba Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Fri, 9 Nov 2012 06:10:01 +0000
Subject: ip6tnl: advertise tunnel param via rtnl

It is usefull for daemons that monitor link event to have the full parameters of
these interfaces when a rtnl message is sent.
It allows also to dump them via rtnetlink.

It is based on what is done for GRE tunnels.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_tunnel.h |  3 +++
 net/ipv6/ip6_tunnel.c          | 57 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index ccb21d585bf4..c1bf0b5a8da1 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -44,6 +44,9 @@ enum {
 	IFLA_IPTUN_REMOTE,
 	IFLA_IPTUN_TTL,
 	IFLA_IPTUN_TOS,
+	IFLA_IPTUN_ENCAP_LIMIT,
+	IFLA_IPTUN_FLOWINFO,
+	IFLA_IPTUN_FLAGS,
 	__IFLA_IPTUN_MAX,
 };
 #define IFLA_IPTUN_MAX	(__IFLA_IPTUN_MAX - 1)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 09482f723064..424ed45ef122 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -83,6 +83,7 @@ static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2)
 
 static int ip6_tnl_dev_init(struct net_device *dev);
 static void ip6_tnl_dev_setup(struct net_device *dev);
+static struct rtnl_link_ops ip6_link_ops __read_mostly;
 
 static int ip6_tnl_net_id __read_mostly;
 struct ip6_tnl_net {
@@ -299,6 +300,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 		goto failed_free;
 
 	strcpy(t->parms.name, dev->name);
+	dev->rtnl_link_ops = &ip6_link_ops;
 
 	dev_hold(dev);
 	ip6_tnl_link(ip6n, t);
@@ -1504,6 +1506,55 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
 	return 0;
 }
 
+static size_t ip6_get_size(const struct net_device *dev)
+{
+	return
+		/* IFLA_IPTUN_LINK */
+		nla_total_size(4) +
+		/* IFLA_IPTUN_LOCAL */
+		nla_total_size(sizeof(struct in6_addr)) +
+		/* IFLA_IPTUN_REMOTE */
+		nla_total_size(sizeof(struct in6_addr)) +
+		/* IFLA_IPTUN_TTL */
+		nla_total_size(1) +
+		/* IFLA_IPTUN_ENCAP_LIMIT */
+		nla_total_size(1) +
+		/* IFLA_IPTUN_FLOWINFO */
+		nla_total_size(4) +
+		/* IFLA_IPTUN_FLAGS */
+		nla_total_size(4) +
+		0;
+}
+
+static int ip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct ip6_tnl *tunnel = netdev_priv(dev);
+	struct __ip6_tnl_parm *parm = &tunnel->parms;
+
+	if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
+	    nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr),
+		    &parm->raddr) ||
+	    nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr),
+		    &parm->laddr) ||
+	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) ||
+	    nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) ||
+	    nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) ||
+	    nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static struct rtnl_link_ops ip6_link_ops __read_mostly = {
+	.kind		= "ip6tnl",
+	.maxtype	= IFLA_IPTUN_MAX,
+	.priv_size	= sizeof(struct ip6_tnl),
+	.get_size	= ip6_get_size,
+	.fill_info	= ip6_fill_info,
+};
+
 static struct xfrm6_tunnel ip4ip6_handler __read_mostly = {
 	.handler	= ip4ip6_rcv,
 	.err_handler	= ip4ip6_err,
@@ -1612,9 +1663,14 @@ static int __init ip6_tunnel_init(void)
 		pr_err("%s: can't register ip6ip6\n", __func__);
 		goto out_ip6ip6;
 	}
+	err = rtnl_link_register(&ip6_link_ops);
+	if (err < 0)
+		goto rtnl_link_failed;
 
 	return 0;
 
+rtnl_link_failed:
+	xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6);
 out_ip6ip6:
 	xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET);
 out_ip4ip6:
@@ -1629,6 +1685,7 @@ out_pernet:
 
 static void __exit ip6_tunnel_cleanup(void)
 {
+	rtnl_link_unregister(&ip6_link_ops);
 	if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET))
 		pr_info("%s: can't deregister ip4ip6\n", __func__);
 
-- 
cgit v1.2.3-55-g7522


From f8f626754ebeca613cf1af2e6f890cfde0e74d5b Mon Sep 17 00:00:00 2001
From: Jesse Gross
Date: Fri, 9 Nov 2012 17:05:07 -0800
Subject: ipv6: Move ipv6_find_hdr() out of Netfilter code.

Open vSwitch will soon also use ipv6_find_hdr() so this moves it
out of Netfilter-specific code into a more common location.

Signed-off-by: Jesse Gross <jesse@nicira.com>
---
 include/linux/netfilter_ipv6/ip6_tables.h |   9 ---
 include/net/ipv6.h                        |   9 +++
 net/ipv6/exthdrs_core.c                   | 103 ++++++++++++++++++++++++++++++
 net/ipv6/netfilter/ip6_tables.c           | 103 ------------------------------
 net/netfilter/xt_HMARK.c                  |   8 +--
 5 files changed, 116 insertions(+), 116 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h
index 5f84c6229dc6..610208b18c05 100644
--- a/include/linux/netfilter_ipv6/ip6_tables.h
+++ b/include/linux/netfilter_ipv6/ip6_tables.h
@@ -47,15 +47,6 @@ ip6t_ext_hdr(u8 nexthdr)
 	       (nexthdr == IPPROTO_DSTOPTS);
 }
 
-enum {
-	IP6T_FH_F_FRAG	= (1 << 0),
-	IP6T_FH_F_AUTH	= (1 << 1),
-};
-
-/* find specified header and get offset to it */
-extern int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
-			 int target, unsigned short *fragoff, int *fragflg);
-
 #ifdef CONFIG_COMPAT
 #include <net/compat.h>
 
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 979bf6c13141..b2f0cfb0a381 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -630,6 +630,15 @@ extern int			ipv6_skip_exthdr(const struct sk_buff *, int start,
 
 extern bool			ipv6_ext_hdr(u8 nexthdr);
 
+enum {
+	IP6_FH_F_FRAG	= (1 << 0),
+	IP6_FH_F_AUTH	= (1 << 1),
+};
+
+/* find specified header and get offset to it */
+extern int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
+			 int target, unsigned short *fragoff, int *fragflg);
+
 extern int ipv6_find_tlv(struct sk_buff *skb, int offset, int type);
 
 extern struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index f73d59a14131..8ea253ad35b1 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -111,3 +111,106 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
 	return start;
 }
 EXPORT_SYMBOL(ipv6_skip_exthdr);
+
+/*
+ * find the offset to specified header or the protocol number of last header
+ * if target < 0. "last header" is transport protocol header, ESP, or
+ * "No next header".
+ *
+ * Note that *offset is used as input/output parameter. an if it is not zero,
+ * then it must be a valid offset to an inner IPv6 header. This can be used
+ * to explore inner IPv6 header, eg. ICMPv6 error messages.
+ *
+ * If target header is found, its offset is set in *offset and return protocol
+ * number. Otherwise, return -1.
+ *
+ * If the first fragment doesn't contain the final protocol header or
+ * NEXTHDR_NONE it is considered invalid.
+ *
+ * Note that non-1st fragment is special case that "the protocol number
+ * of last header" is "next header" field in Fragment header. In this case,
+ * *offset is meaningless and fragment offset is stored in *fragoff if fragoff
+ * isn't NULL.
+ *
+ * if flags is not NULL and it's a fragment, then the frag flag IP6_FH_F_FRAG
+ * will be set. If it's an AH header, the IP6_FH_F_AUTH flag is set and
+ * target < 0, then this function will stop at the AH header.
+ */
+int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
+		  int target, unsigned short *fragoff, int *flags)
+{
+	unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
+	u8 nexthdr = ipv6_hdr(skb)->nexthdr;
+	unsigned int len;
+
+	if (fragoff)
+		*fragoff = 0;
+
+	if (*offset) {
+		struct ipv6hdr _ip6, *ip6;
+
+		ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6);
+		if (!ip6 || (ip6->version != 6)) {
+			printk(KERN_ERR "IPv6 header not found\n");
+			return -EBADMSG;
+		}
+		start = *offset + sizeof(struct ipv6hdr);
+		nexthdr = ip6->nexthdr;
+	}
+	len = skb->len - start;
+
+	while (nexthdr != target) {
+		struct ipv6_opt_hdr _hdr, *hp;
+		unsigned int hdrlen;
+
+		if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
+			if (target < 0)
+				break;
+			return -ENOENT;
+		}
+
+		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
+		if (hp == NULL)
+			return -EBADMSG;
+		if (nexthdr == NEXTHDR_FRAGMENT) {
+			unsigned short _frag_off;
+			__be16 *fp;
+
+			if (flags)	/* Indicate that this is a fragment */
+				*flags |= IP6_FH_F_FRAG;
+			fp = skb_header_pointer(skb,
+						start+offsetof(struct frag_hdr,
+							       frag_off),
+						sizeof(_frag_off),
+						&_frag_off);
+			if (fp == NULL)
+				return -EBADMSG;
+
+			_frag_off = ntohs(*fp) & ~0x7;
+			if (_frag_off) {
+				if (target < 0 &&
+				    ((!ipv6_ext_hdr(hp->nexthdr)) ||
+				     hp->nexthdr == NEXTHDR_NONE)) {
+					if (fragoff)
+						*fragoff = _frag_off;
+					return hp->nexthdr;
+				}
+				return -ENOENT;
+			}
+			hdrlen = 8;
+		} else if (nexthdr == NEXTHDR_AUTH) {
+			if (flags && (*flags & IP6_FH_F_AUTH) && (target < 0))
+				break;
+			hdrlen = (hp->hdrlen + 2) << 2;
+		} else
+			hdrlen = ipv6_optlen(hp);
+
+		nexthdr = hp->nexthdr;
+		len -= hdrlen;
+		start += hdrlen;
+	}
+
+	*offset = start;
+	return nexthdr;
+}
+EXPORT_SYMBOL(ipv6_find_hdr);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index d7cb04506c3d..1ce4f157ce4f 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -2273,112 +2273,9 @@ static void __exit ip6_tables_fini(void)
 	unregister_pernet_subsys(&ip6_tables_net_ops);
 }
 
-/*
- * find the offset to specified header or the protocol number of last header
- * if target < 0. "last header" is transport protocol header, ESP, or
- * "No next header".
- *
- * Note that *offset is used as input/output parameter. an if it is not zero,
- * then it must be a valid offset to an inner IPv6 header. This can be used
- * to explore inner IPv6 header, eg. ICMPv6 error messages.
- *
- * If target header is found, its offset is set in *offset and return protocol
- * number. Otherwise, return -1.
- *
- * If the first fragment doesn't contain the final protocol header or
- * NEXTHDR_NONE it is considered invalid.
- *
- * Note that non-1st fragment is special case that "the protocol number
- * of last header" is "next header" field in Fragment header. In this case,
- * *offset is meaningless and fragment offset is stored in *fragoff if fragoff
- * isn't NULL.
- *
- * if flags is not NULL and it's a fragment, then the frag flag IP6T_FH_F_FRAG
- * will be set. If it's an AH header, the IP6T_FH_F_AUTH flag is set and
- * target < 0, then this function will stop at the AH header.
- */
-int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
-		  int target, unsigned short *fragoff, int *flags)
-{
-	unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
-	u8 nexthdr = ipv6_hdr(skb)->nexthdr;
-	unsigned int len;
-
-	if (fragoff)
-		*fragoff = 0;
-
-	if (*offset) {
-		struct ipv6hdr _ip6, *ip6;
-
-		ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6);
-		if (!ip6 || (ip6->version != 6)) {
-			printk(KERN_ERR "IPv6 header not found\n");
-			return -EBADMSG;
-		}
-		start = *offset + sizeof(struct ipv6hdr);
-		nexthdr = ip6->nexthdr;
-	}
-	len = skb->len - start;
-
-	while (nexthdr != target) {
-		struct ipv6_opt_hdr _hdr, *hp;
-		unsigned int hdrlen;
-
-		if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
-			if (target < 0)
-				break;
-			return -ENOENT;
-		}
-
-		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
-		if (hp == NULL)
-			return -EBADMSG;
-		if (nexthdr == NEXTHDR_FRAGMENT) {
-			unsigned short _frag_off;
-			__be16 *fp;
-
-			if (flags)	/* Indicate that this is a fragment */
-				*flags |= IP6T_FH_F_FRAG;
-			fp = skb_header_pointer(skb,
-						start+offsetof(struct frag_hdr,
-							       frag_off),
-						sizeof(_frag_off),
-						&_frag_off);
-			if (fp == NULL)
-				return -EBADMSG;
-
-			_frag_off = ntohs(*fp) & ~0x7;
-			if (_frag_off) {
-				if (target < 0 &&
-				    ((!ipv6_ext_hdr(hp->nexthdr)) ||
-				     hp->nexthdr == NEXTHDR_NONE)) {
-					if (fragoff)
-						*fragoff = _frag_off;
-					return hp->nexthdr;
-				}
-				return -ENOENT;
-			}
-			hdrlen = 8;
-		} else if (nexthdr == NEXTHDR_AUTH) {
-			if (flags && (*flags & IP6T_FH_F_AUTH) && (target < 0))
-				break;
-			hdrlen = (hp->hdrlen + 2) << 2;
-		} else
-			hdrlen = ipv6_optlen(hp);
-
-		nexthdr = hp->nexthdr;
-		len -= hdrlen;
-		start += hdrlen;
-	}
-
-	*offset = start;
-	return nexthdr;
-}
-
 EXPORT_SYMBOL(ip6t_register_table);
 EXPORT_SYMBOL(ip6t_unregister_table);
 EXPORT_SYMBOL(ip6t_do_table);
-EXPORT_SYMBOL(ipv6_find_hdr);
 
 module_init(ip6_tables_init);
 module_exit(ip6_tables_fini);
diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c
index 1686ca1b53a1..73b73f687c58 100644
--- a/net/netfilter/xt_HMARK.c
+++ b/net/netfilter/xt_HMARK.c
@@ -167,7 +167,7 @@ hmark_pkt_set_htuple_ipv6(const struct sk_buff *skb, struct hmark_tuple *t,
 			  const struct xt_hmark_info *info)
 {
 	struct ipv6hdr *ip6, _ip6;
-	int flag = IP6T_FH_F_AUTH;
+	int flag = IP6_FH_F_AUTH;
 	unsigned int nhoff = 0;
 	u16 fragoff = 0;
 	int nexthdr;
@@ -177,7 +177,7 @@ hmark_pkt_set_htuple_ipv6(const struct sk_buff *skb, struct hmark_tuple *t,
 	if (nexthdr < 0)
 		return 0;
 	/* No need to check for icmp errors on fragments */
-	if ((flag & IP6T_FH_F_FRAG) || (nexthdr != IPPROTO_ICMPV6))
+	if ((flag & IP6_FH_F_FRAG) || (nexthdr != IPPROTO_ICMPV6))
 		goto noicmp;
 	/* Use inner header in case of ICMP errors */
 	if (get_inner6_hdr(skb, &nhoff)) {
@@ -185,7 +185,7 @@ hmark_pkt_set_htuple_ipv6(const struct sk_buff *skb, struct hmark_tuple *t,
 		if (ip6 == NULL)
 			return -1;
 		/* If AH present, use SPI like in ESP. */
-		flag = IP6T_FH_F_AUTH;
+		flag = IP6_FH_F_AUTH;
 		nexthdr = ipv6_find_hdr(skb, &nhoff, -1, &fragoff, &flag);
 		if (nexthdr < 0)
 			return -1;
@@ -201,7 +201,7 @@ noicmp:
 	if (t->proto == IPPROTO_ICMPV6)
 		return 0;
 
-	if (flag & IP6T_FH_F_FRAG)
+	if (flag & IP6_FH_F_FRAG)
 		return 0;
 
 	hmark_set_tuple_ports(skb, nhoff, t, info);
-- 
cgit v1.2.3-55-g7522


From 1789382a72a537447d65ea4131d8bcc1ad85ce7b Mon Sep 17 00:00:00 2001
From: Donald Dutile
Date: Mon, 5 Nov 2012 15:20:36 -0500
Subject: PCI: SRIOV control and status via sysfs

Provide files under sysfs to determine the maximum number of VFs
an SR-IOV-capable PCIe device supports, and methods to enable and
disable the VFs on a per-device basis.

Currently, VF enablement by SR-IOV-capable PCIe devices is done
via driver-specific module parameters.  If not setup in modprobe files,
it requires admin to unload & reload PF drivers with number of desired
VFs to enable.  Additionally, the enablement is system wide: all
devices controlled by the same driver have the same number of VFs
enabled.  Although the latter is probably desired, there are PCI
configurations setup by system BIOS that may not enable that to occur.

Two files are created for the PF of PCIe devices with SR-IOV support:

    sriov_totalvfs	Contains the maximum number of VFs the device
			could support as reported by the TotalVFs register
			in the SR-IOV extended capability.

    sriov_numvfs	Contains the number of VFs currently enabled on
			this device as reported by the NumVFs register in
			the SR-IOV extended capability.

			Writing zero to this file disables all VFs.

			Writing a positive number to this file enables that
			number of VFs.

These files are readable for all SR-IOV PF devices.  Writes to the
sriov_numvfs file are effective only if a driver that supports the
sriov_configure() method is attached.

Signed-off-by: Donald Dutile <ddutile@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>---
 drivers/pci/pci-sysfs.c | 127 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci.h     |   1 +
 2 files changed, 128 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index fbbb97f28259..74508c63bd47 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -404,6 +404,106 @@ static ssize_t d3cold_allowed_show(struct device *dev,
 }
 #endif
 
+#ifdef CONFIG_PCI_IOV
+static ssize_t sriov_totalvfs_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return sprintf(buf, "%u\n", pdev->sriov->total);
+}
+
+
+static ssize_t sriov_numvfs_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return sprintf(buf, "%u\n", pdev->sriov->nr_virtfn);
+}
+
+/*
+ * num_vfs > 0; number of vfs to enable
+ * num_vfs = 0; disable all vfs
+ *
+ * Note: SRIOV spec doesn't allow partial VF
+ *       disable, so its all or none.
+ */
+static ssize_t sriov_numvfs_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int num_vfs_enabled = 0;
+	int num_vfs;
+	int ret = 0;
+	u16 total;
+
+	if (kstrtoint(buf, 0, &num_vfs) < 0)
+		return -EINVAL;
+
+	/* is PF driver loaded w/callback */
+	if (!pdev->driver || !pdev->driver->sriov_configure) {
+		dev_info(&pdev->dev,
+			 "Driver doesn't support SRIOV configuration via sysfs\n");
+		return -ENOSYS;
+	}
+
+	/* if enabling vf's ... */
+	total = pdev->sriov->total;
+	/* Requested VFs to enable < totalvfs and none enabled already */
+	if ((num_vfs > 0) && (num_vfs <= total)) {
+		if (pdev->sriov->nr_virtfn == 0) {
+			num_vfs_enabled =
+				pdev->driver->sriov_configure(pdev, num_vfs);
+			if ((num_vfs_enabled >= 0) &&
+			    (num_vfs_enabled != num_vfs)) {
+				dev_warn(&pdev->dev,
+					 "Only %d VFs enabled\n",
+					 num_vfs_enabled);
+				return count;
+			} else if (num_vfs_enabled < 0)
+				/* error code from driver callback */
+				return num_vfs_enabled;
+		} else if (num_vfs == pdev->sriov->nr_virtfn) {
+			dev_warn(&pdev->dev,
+				 "%d VFs already enabled; no enable action taken\n",
+				 num_vfs);
+			return count;
+		} else {
+			dev_warn(&pdev->dev,
+				 "%d VFs already enabled. Disable before enabling %d VFs\n",
+				 pdev->sriov->nr_virtfn, num_vfs);
+			return -EINVAL;
+		}
+	}
+
+	/* disable vfs */
+	if (num_vfs == 0) {
+		if (pdev->sriov->nr_virtfn != 0) {
+			ret = pdev->driver->sriov_configure(pdev, 0);
+			return ret ? ret : count;
+		} else {
+			dev_warn(&pdev->dev,
+				 "All VFs disabled; no disable action taken\n");
+			return count;
+		}
+	}
+
+	dev_err(&pdev->dev,
+		"Invalid value for number of VFs to enable: %d\n", num_vfs);
+
+	return -EINVAL;
+}
+
+static struct device_attribute sriov_totalvfs_attr = __ATTR_RO(sriov_totalvfs);
+static struct device_attribute sriov_numvfs_attr =
+		__ATTR(sriov_numvfs, (S_IRUGO|S_IWUSR|S_IWGRP),
+		       sriov_numvfs_show, sriov_numvfs_store);
+#endif /* CONFIG_PCI_IOV */
+
 struct device_attribute pci_dev_attrs[] = {
 	__ATTR_RO(resource),
 	__ATTR_RO(vendor),
@@ -1421,6 +1521,30 @@ static umode_t pci_dev_attrs_are_visible(struct kobject *kobj,
 	return a->mode;
 }
 
+#ifdef CONFIG_PCI_IOV
+static struct attribute *sriov_dev_attrs[] = {
+	&sriov_totalvfs_attr.attr,
+	&sriov_numvfs_attr.attr,
+	NULL,
+};
+
+static umode_t sriov_attrs_are_visible(struct kobject *kobj,
+					 struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+
+	if (!dev_is_pf(dev))
+		return 0;
+
+	return a->mode;
+}
+
+static struct attribute_group sriov_dev_attr_group = {
+	.attrs = sriov_dev_attrs,
+	.is_visible = sriov_attrs_are_visible,
+};
+#endif /* CONFIG_PCI_IOV */
+
 static struct attribute_group pci_dev_attr_group = {
 	.attrs = pci_dev_dev_attrs,
 	.is_visible = pci_dev_attrs_are_visible,
@@ -1428,6 +1552,9 @@ static struct attribute_group pci_dev_attr_group = {
 
 static const struct attribute_group *pci_dev_attr_groups[] = {
 	&pci_dev_attr_group,
+#ifdef CONFIG_PCI_IOV
+	&sriov_dev_attr_group,
+#endif
 	NULL,
 };
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index ee2179546c63..7ef8fba319da 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -573,6 +573,7 @@ struct pci_driver {
 	int  (*resume_early) (struct pci_dev *dev);
 	int  (*resume) (struct pci_dev *dev);	                /* Device woken up */
 	void (*shutdown) (struct pci_dev *dev);
+	int (*sriov_configure) (struct pci_dev *dev, int num_vfs); /* PF pdev */
 	const struct pci_error_handlers *err_handler;
 	struct device_driver	driver;
 	struct pci_dynids dynids;
-- 
cgit v1.2.3-55-g7522


From bff73156d3ad661655e6d9ef04c2284cf3abb0f1 Mon Sep 17 00:00:00 2001
From: Donald Dutile
Date: Mon, 5 Nov 2012 15:20:37 -0500
Subject: PCI: Provide method to reduce the number of total VFs supported

Some implementations of SRIOV provide a capability structure
value of TotalVFs that is greater than what the software can support.
Provide a method to reduce the capability structure reported value
to the value the driver can support.
This ensures sysfs reports the current capability of the system,
hardware and software.
Example for its use: igb & ixgbe -- report 8 & 64 as TotalVFs,
but drivers only support 7 & 63 maximum.

Signed-off-by: Donald Dutile <ddutile@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>---
 drivers/pci/iov.c       | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/pci/pci-sysfs.c |  4 ++--
 drivers/pci/pci.h       |  1 +
 include/linux/pci.h     | 10 ++++++++++
 4 files changed, 60 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index aeccc911abb8..f6781e42d00d 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -735,3 +735,50 @@ int pci_num_vf(struct pci_dev *dev)
 		return dev->sriov->nr_virtfn;
 }
 EXPORT_SYMBOL_GPL(pci_num_vf);
+
+/**
+ * pci_sriov_set_totalvfs -- reduce the TotalVFs available
+ * @dev: the PCI PF device
+ * numvfs: number that should be used for TotalVFs supported
+ *
+ * Should be called from PF driver's probe routine with
+ * device's mutex held.
+ *
+ * Returns 0 if PF is an SRIOV-capable device and
+ * value of numvfs valid. If not a PF with VFS, return -EINVAL;
+ * if VFs already enabled, return -EBUSY.
+ */
+int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs)
+{
+	if (!dev || !dev->is_physfn || (numvfs > dev->sriov->total))
+		return -EINVAL;
+
+	/* Shouldn't change if VFs already enabled */
+	if (dev->sriov->ctrl & PCI_SRIOV_CTRL_VFE)
+		return -EBUSY;
+	else
+		dev->sriov->drvttl = numvfs;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_sriov_set_totalvfs);
+
+/**
+ * pci_sriov_get_totalvfs -- get total VFs supported on this devic3
+ * @dev: the PCI PF device
+ *
+ * For a PCIe device with SRIOV support, return the PCIe
+ * SRIOV capability value of TotalVFs or the value of drvttl
+ * if the driver reduced it.  Otherwise, -EINVAL.
+ */
+int pci_sriov_get_totalvfs(struct pci_dev *dev)
+{
+	if (!dev || !dev->is_physfn)
+		return -EINVAL;
+
+	if (dev->sriov->drvttl)
+		return dev->sriov->drvttl;
+	else
+		return dev->sriov->total;
+}
+EXPORT_SYMBOL_GPL(pci_sriov_get_totalvfs);
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 74508c63bd47..99b5f83d2468 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -411,7 +411,7 @@ static ssize_t sriov_totalvfs_show(struct device *dev,
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 
-	return sprintf(buf, "%u\n", pdev->sriov->total);
+	return sprintf(buf, "%u\n", pci_sriov_get_totalvfs(pdev));
 }
 
 
@@ -452,7 +452,7 @@ static ssize_t sriov_numvfs_store(struct device *dev,
 	}
 
 	/* if enabling vf's ... */
-	total = pdev->sriov->total;
+	total = pci_sriov_get_totalvfs(pdev);
 	/* Requested VFs to enable < totalvfs and none enabled already */
 	if ((num_vfs > 0) && (num_vfs <= total)) {
 		if (pdev->sriov->nr_virtfn == 0) {
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 6f6cd145bb7e..553bbba76eec 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -240,6 +240,7 @@ struct pci_sriov {
 	u16 stride;		/* following VF stride */
 	u32 pgsz;		/* page size for BAR alignment */
 	u8 link;		/* Function Dependency Link */
+	u16 drvttl;		/* max num VFs driver supports */
 	struct pci_dev *dev;	/* lowest numbered PF */
 	struct pci_dev *self;	/* this PF */
 	struct mutex lock;	/* lock for VF bus */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 7ef8fba319da..1ad824966e64 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1611,6 +1611,8 @@ extern int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn);
 extern void pci_disable_sriov(struct pci_dev *dev);
 extern irqreturn_t pci_sriov_migration(struct pci_dev *dev);
 extern int pci_num_vf(struct pci_dev *dev);
+extern int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs);
+extern int pci_sriov_get_totalvfs(struct pci_dev *dev);
 #else
 static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn)
 {
@@ -1627,6 +1629,14 @@ static inline int pci_num_vf(struct pci_dev *dev)
 {
 	return 0;
 }
+static inline int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs)
+{
+	return 0;
+}
+static inline int pci_sriov_get_totalvfs(struct pci_dev *dev)
+{
+	return 0;
+}
 #endif
 
 #if defined(CONFIG_HOTPLUG_PCI) || defined(CONFIG_HOTPLUG_PCI_MODULE)
-- 
cgit v1.2.3-55-g7522


From 800963fd598e2acbcd3a21a17e3ab3c185ad0d6a Mon Sep 17 00:00:00 2001
From: Henrik Rydberg
Date: Sat, 10 Nov 2012 00:32:36 -0800
Subject: Input: document new members of struct input_dev

Fixes kernel-doc warnings for the members added in 3.7-rc1.

Signed-off-by: Henrik Rydberg <rydberg@euromail.se>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 include/linux/input.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/input.h b/include/linux/input.h
index 5538cc09a4f5..82ce323b9986 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -112,6 +112,9 @@ struct input_value {
  * @h_list: list of input handles associated with the device. When
  *	accessing the list dev->mutex must be held
  * @node: used to place the device onto input_dev_list
+ * @num_vals: number of values queued in the current frame
+ * @max_vals: maximum number of values queued in a frame
+ * @vals: array of values queued in the current frame
  * @devres_managed: indicates that devices is managed with devres framework
  *	and needs not be explicitly unregistered or freed.
  */
-- 
cgit v1.2.3-55-g7522


From 84b36ce5f79c01f792c623f14e92ed86cdccb42f Mon Sep 17 00:00:00 2001
From: Jonathan Cameron
Date: Sat, 30 Jun 2012 20:06:00 +0100
Subject: staging:iio: Add support for multiple buffers

Route all buffer writes through the demux.
Addition or removal of a buffer results in tear down and
setup of all the buffers for a given device.

Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Tested-by: srinivas pandruvada <srinivas.pandruvada@intel.com>
---
 drivers/iio/accel/hid-sensor-accel-3d.c         |  15 +-
 drivers/iio/adc/ad7266.c                        |   3 +-
 drivers/iio/adc/ad7476.c                        |   2 +-
 drivers/iio/adc/ad7887.c                        |   2 +-
 drivers/iio/adc/ad_sigma_delta.c                |   2 +-
 drivers/iio/adc/at91_adc.c                      |   3 +-
 drivers/iio/gyro/hid-sensor-gyro-3d.c           |  15 +-
 drivers/iio/industrialio-buffer.c               | 380 ++++++++++++++++--------
 drivers/iio/industrialio-core.c                 |   1 +
 drivers/iio/light/adjd_s311.c                   |   3 +-
 drivers/iio/light/hid-sensor-als.c              |  15 +-
 drivers/iio/magnetometer/hid-sensor-magn-3d.c   |  15 +-
 drivers/staging/iio/accel/adis16201_ring.c      |   2 +-
 drivers/staging/iio/accel/adis16203_ring.c      |   2 +-
 drivers/staging/iio/accel/adis16204_ring.c      |   2 +-
 drivers/staging/iio/accel/adis16209_ring.c      |   2 +-
 drivers/staging/iio/accel/adis16240_ring.c      |   2 +-
 drivers/staging/iio/accel/lis3l02dq_ring.c      |   2 +-
 drivers/staging/iio/adc/ad7298_ring.c           |   2 +-
 drivers/staging/iio/adc/ad7606_ring.c           |   2 +-
 drivers/staging/iio/adc/ad799x_ring.c           |   2 +-
 drivers/staging/iio/adc/max1363_ring.c          |   2 +-
 drivers/staging/iio/adc/mxs-lradc.c             |   3 +-
 drivers/staging/iio/gyro/adis16260_ring.c       |   2 +-
 drivers/staging/iio/iio_simple_dummy_buffer.c   |   5 +-
 drivers/staging/iio/impedance-analyzer/ad5933.c |   4 +-
 drivers/staging/iio/imu/adis16400_ring.c        |   5 +-
 drivers/staging/iio/meter/ade7758_ring.c        |   2 +-
 include/linux/iio/buffer.h                      |  24 +-
 include/linux/iio/iio.h                         |   2 +
 30 files changed, 313 insertions(+), 210 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c
index 314a4057879e..a95cda0e387f 100644
--- a/drivers/iio/accel/hid-sensor-accel-3d.c
+++ b/drivers/iio/accel/hid-sensor-accel-3d.c
@@ -197,21 +197,8 @@ static const struct iio_info accel_3d_info = {
 /* Function to push data to buffer */
 static void hid_sensor_push_data(struct iio_dev *indio_dev, u8 *data, int len)
 {
-	struct iio_buffer *buffer = indio_dev->buffer;
-	int datum_sz;
-
 	dev_dbg(&indio_dev->dev, "hid_sensor_push_data\n");
-	if (!buffer) {
-		dev_err(&indio_dev->dev, "Buffer == NULL\n");
-		return;
-	}
-	datum_sz = buffer->access->get_bytes_per_datum(buffer);
-	if (len > datum_sz) {
-		dev_err(&indio_dev->dev, "Datum size mismatch %d:%d\n", len,
-				datum_sz);
-		return;
-	}
-	iio_push_to_buffer(buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 }
 
 /* Callback handler to send event after all samples are received and captured */
diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index b11f214779a2..a6f4fc5f8201 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -91,7 +91,6 @@ static irqreturn_t ad7266_trigger_handler(int irq, void *p)
 {
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
-	struct iio_buffer *buffer = indio_dev->buffer;
 	struct ad7266_state *st = iio_priv(indio_dev);
 	int ret;
 
@@ -99,7 +98,7 @@ static irqreturn_t ad7266_trigger_handler(int irq, void *p)
 	if (ret == 0) {
 		if (indio_dev->scan_timestamp)
 			((s64 *)st->data)[1] = pf->timestamp;
-		iio_push_to_buffer(buffer, (u8 *)st->data);
+		iio_push_to_buffers(indio_dev, (u8 *)st->data);
 	}
 
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/adc/ad7476.c b/drivers/iio/adc/ad7476.c
index 7f2f45a0a48d..330248bfebae 100644
--- a/drivers/iio/adc/ad7476.c
+++ b/drivers/iio/adc/ad7476.c
@@ -76,7 +76,7 @@ static irqreturn_t ad7476_trigger_handler(int irq, void  *p)
 	if (indio_dev->scan_timestamp)
 		((s64 *)st->data)[1] = time_ns;
 
-	iio_push_to_buffer(indio_dev->buffer, st->data);
+	iio_push_to_buffers(indio_dev, st->data);
 done:
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/adc/ad7887.c b/drivers/iio/adc/ad7887.c
index fd62309b4d3d..81153fafac7a 100644
--- a/drivers/iio/adc/ad7887.c
+++ b/drivers/iio/adc/ad7887.c
@@ -134,7 +134,7 @@ static irqreturn_t ad7887_trigger_handler(int irq, void *p)
 		memcpy(st->data + indio_dev->scan_bytes - sizeof(s64),
 		       &time_ns, sizeof(time_ns));
 
-	iio_push_to_buffer(indio_dev->buffer, st->data);
+	iio_push_to_buffers(indio_dev, st->data);
 done:
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index 67baa1363d7a..afe6d78c8ff0 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -391,7 +391,7 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
 		break;
 	}
 
-	iio_push_to_buffer(indio_dev->buffer, (uint8_t *)data);
+	iio_push_to_buffers(indio_dev, (uint8_t *)data);
 
 	iio_trigger_notify_done(indio_dev->trig);
 	sigma_delta->irq_dis = false;
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index 2e2c9a80aa37..03b85940f4ba 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -65,7 +65,6 @@ static irqreturn_t at91_adc_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *idev = pf->indio_dev;
 	struct at91_adc_state *st = iio_priv(idev);
-	struct iio_buffer *buffer = idev->buffer;
 	int i, j = 0;
 
 	for (i = 0; i < idev->masklength; i++) {
@@ -81,7 +80,7 @@ static irqreturn_t at91_adc_trigger_handler(int irq, void *p)
 		*timestamp = pf->timestamp;
 	}
 
-	iio_push_to_buffer(buffer, st->buffer);
+	iio_push_to_buffers(indio_dev, (u8 *)st->buffer);
 
 	iio_trigger_notify_done(idev->trig);
 
diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c
index 4c56ada51c39..02ef989b830d 100644
--- a/drivers/iio/gyro/hid-sensor-gyro-3d.c
+++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c
@@ -197,21 +197,8 @@ static const struct iio_info gyro_3d_info = {
 /* Function to push data to buffer */
 static void hid_sensor_push_data(struct iio_dev *indio_dev, u8 *data, int len)
 {
-	struct iio_buffer *buffer = indio_dev->buffer;
-	int datum_sz;
-
 	dev_dbg(&indio_dev->dev, "hid_sensor_push_data\n");
-	if (!buffer) {
-		dev_err(&indio_dev->dev, "Buffer == NULL\n");
-		return;
-	}
-	datum_sz = buffer->access->get_bytes_per_datum(buffer);
-	if (len > datum_sz) {
-		dev_err(&indio_dev->dev, "Datum size mismatch %d:%d\n", len,
-				datum_sz);
-		return;
-	}
-	iio_push_to_buffer(buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 }
 
 /* Callback handler to send event after all samples are received and captured */
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 722a83fd8d85..aaadd32f9f0d 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -31,6 +31,18 @@ static const char * const iio_endian_prefix[] = {
 	[IIO_LE] = "le",
 };
 
+static bool iio_buffer_is_active(struct iio_dev *indio_dev,
+				 struct iio_buffer *buf)
+{
+	struct list_head *p;
+
+	list_for_each(p, &indio_dev->buffer_list)
+		if (p == &buf->buffer_list)
+			return true;
+
+	return false;
+}
+
 /**
  * iio_buffer_read_first_n_outer() - chrdev read for buffer access
  *
@@ -134,7 +146,7 @@ static ssize_t iio_scan_el_store(struct device *dev,
 	if (ret < 0)
 		return ret;
 	mutex_lock(&indio_dev->mlock);
-	if (iio_buffer_enabled(indio_dev)) {
+	if (iio_buffer_is_active(indio_dev, indio_dev->buffer)) {
 		ret = -EBUSY;
 		goto error_ret;
 	}
@@ -180,12 +192,11 @@ static ssize_t iio_scan_el_ts_store(struct device *dev,
 		return ret;
 
 	mutex_lock(&indio_dev->mlock);
-	if (iio_buffer_enabled(indio_dev)) {
+	if (iio_buffer_is_active(indio_dev, indio_dev->buffer)) {
 		ret = -EBUSY;
 		goto error_ret;
 	}
 	indio_dev->buffer->scan_timestamp = state;
-	indio_dev->scan_timestamp = state;
 error_ret:
 	mutex_unlock(&indio_dev->mlock);
 
@@ -385,7 +396,7 @@ ssize_t iio_buffer_write_length(struct device *dev,
 			return len;
 
 	mutex_lock(&indio_dev->mlock);
-	if (iio_buffer_enabled(indio_dev)) {
+	if (iio_buffer_is_active(indio_dev, indio_dev->buffer)) {
 		ret = -EBUSY;
 	} else {
 		if (buffer->access->set_length)
@@ -398,102 +409,14 @@ ssize_t iio_buffer_write_length(struct device *dev,
 }
 EXPORT_SYMBOL(iio_buffer_write_length);
 
-ssize_t iio_buffer_store_enable(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf,
-				size_t len)
-{
-	int ret;
-	bool requested_state, current_state;
-	int previous_mode;
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct iio_buffer *buffer = indio_dev->buffer;
-
-	mutex_lock(&indio_dev->mlock);
-	previous_mode = indio_dev->currentmode;
-	requested_state = !(buf[0] == '0');
-	current_state = iio_buffer_enabled(indio_dev);
-	if (current_state == requested_state) {
-		printk(KERN_INFO "iio-buffer, current state requested again\n");
-		goto done;
-	}
-	if (requested_state) {
-		if (indio_dev->setup_ops->preenable) {
-			ret = indio_dev->setup_ops->preenable(indio_dev);
-			if (ret) {
-				printk(KERN_ERR
-				       "Buffer not started: "
-				       "buffer preenable failed\n");
-				goto error_ret;
-			}
-		}
-		if (buffer->access->request_update) {
-			ret = buffer->access->request_update(buffer);
-			if (ret) {
-				printk(KERN_INFO
-				       "Buffer not started: "
-				       "buffer parameter update failed\n");
-				goto error_ret;
-			}
-		}
-		/* Definitely possible for devices to support both of these. */
-		if (indio_dev->modes & INDIO_BUFFER_TRIGGERED) {
-			if (!indio_dev->trig) {
-				printk(KERN_INFO
-				       "Buffer not started: no trigger\n");
-				ret = -EINVAL;
-				goto error_ret;
-			}
-			indio_dev->currentmode = INDIO_BUFFER_TRIGGERED;
-		} else if (indio_dev->modes & INDIO_BUFFER_HARDWARE)
-			indio_dev->currentmode = INDIO_BUFFER_HARDWARE;
-		else { /* should never be reached */
-			ret = -EINVAL;
-			goto error_ret;
-		}
-
-		if (indio_dev->setup_ops->postenable) {
-			ret = indio_dev->setup_ops->postenable(indio_dev);
-			if (ret) {
-				printk(KERN_INFO
-				       "Buffer not started: "
-				       "postenable failed\n");
-				indio_dev->currentmode = previous_mode;
-				if (indio_dev->setup_ops->postdisable)
-					indio_dev->setup_ops->
-						postdisable(indio_dev);
-				goto error_ret;
-			}
-		}
-	} else {
-		if (indio_dev->setup_ops->predisable) {
-			ret = indio_dev->setup_ops->predisable(indio_dev);
-			if (ret)
-				goto error_ret;
-		}
-		indio_dev->currentmode = INDIO_DIRECT_MODE;
-		if (indio_dev->setup_ops->postdisable) {
-			ret = indio_dev->setup_ops->postdisable(indio_dev);
-			if (ret)
-				goto error_ret;
-		}
-	}
-done:
-	mutex_unlock(&indio_dev->mlock);
-	return len;
-
-error_ret:
-	mutex_unlock(&indio_dev->mlock);
-	return ret;
-}
-EXPORT_SYMBOL(iio_buffer_store_enable);
-
 ssize_t iio_buffer_show_enable(struct device *dev,
 			       struct device_attribute *attr,
 			       char *buf)
 {
 	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	return sprintf(buf, "%d\n", iio_buffer_enabled(indio_dev));
+	return sprintf(buf, "%d\n",
+		       iio_buffer_is_active(indio_dev,
+					    indio_dev->buffer));
 }
 EXPORT_SYMBOL(iio_buffer_show_enable);
 
@@ -537,35 +460,220 @@ static int iio_compute_scan_bytes(struct iio_dev *indio_dev, const long *mask,
 	return bytes;
 }
 
-int iio_sw_buffer_preenable(struct iio_dev *indio_dev)
+int iio_update_buffers(struct iio_dev *indio_dev,
+		       struct iio_buffer *insert_buffer,
+		       struct iio_buffer *remove_buffer)
 {
-	struct iio_buffer *buffer = indio_dev->buffer;
-	dev_dbg(&indio_dev->dev, "%s\n", __func__);
+	int ret;
+	int success = 0;
+	struct iio_buffer *buffer;
+	unsigned long *compound_mask;
+	const unsigned long *old_mask;
 
-	/* How much space will the demuxed element take? */
-	indio_dev->scan_bytes =
-		iio_compute_scan_bytes(indio_dev, buffer->scan_mask,
-				       buffer->scan_timestamp);
-	buffer->access->set_bytes_per_datum(buffer, indio_dev->scan_bytes);
+	/* Wind down existing buffers - iff there are any */
+	if (!list_empty(&indio_dev->buffer_list)) {
+		if (indio_dev->setup_ops->predisable) {
+			ret = indio_dev->setup_ops->predisable(indio_dev);
+			if (ret)
+				goto error_ret;
+		}
+		indio_dev->currentmode = INDIO_DIRECT_MODE;
+		if (indio_dev->setup_ops->postdisable) {
+			ret = indio_dev->setup_ops->postdisable(indio_dev);
+			if (ret)
+				goto error_ret;
+		}
+	}
+	/* Keep a copy of current setup to allow roll back */
+	old_mask = indio_dev->active_scan_mask;
+	if (!indio_dev->available_scan_masks)
+		indio_dev->active_scan_mask = NULL;
+
+	if (remove_buffer)
+		list_del(&remove_buffer->buffer_list);
+	if (insert_buffer)
+		list_add(&insert_buffer->buffer_list, &indio_dev->buffer_list);
+
+	/* If no buffers in list, we are done */
+	if (list_empty(&indio_dev->buffer_list)) {
+		indio_dev->currentmode = INDIO_DIRECT_MODE;
+		if (indio_dev->available_scan_masks == NULL)
+			kfree(old_mask);
+		return 0;
+	}
 
 	/* What scan mask do we actually have ?*/
-	if (indio_dev->available_scan_masks)
+	compound_mask = kcalloc(BITS_TO_LONGS(indio_dev->masklength),
+				sizeof(long), GFP_KERNEL);
+	if (compound_mask == NULL) {
+		if (indio_dev->available_scan_masks == NULL)
+			kfree(old_mask);
+		return -ENOMEM;
+	}
+	indio_dev->scan_timestamp = 0;
+
+	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list) {
+		bitmap_or(compound_mask, compound_mask, buffer->scan_mask,
+			  indio_dev->masklength);
+		indio_dev->scan_timestamp |= buffer->scan_timestamp;
+	}
+	if (indio_dev->available_scan_masks) {
 		indio_dev->active_scan_mask =
 			iio_scan_mask_match(indio_dev->available_scan_masks,
 					    indio_dev->masklength,
-					    buffer->scan_mask);
-	else
-		indio_dev->active_scan_mask = buffer->scan_mask;
-
-	if (indio_dev->active_scan_mask == NULL)
-		return -EINVAL;
+					    compound_mask);
+		if (indio_dev->active_scan_mask == NULL) {
+			/*
+			 * Roll back.
+			 * Note can only occur when adding a buffer.
+			 */
+			list_del(&insert_buffer->buffer_list);
+			indio_dev->active_scan_mask = old_mask;
+			success = -EINVAL;
+		}
+	} else {
+		indio_dev->active_scan_mask = compound_mask;
+	}
 
 	iio_update_demux(indio_dev);
 
-	if (indio_dev->info->update_scan_mode)
-		return indio_dev->info
+	/* Wind up again */
+	if (indio_dev->setup_ops->preenable) {
+		ret = indio_dev->setup_ops->preenable(indio_dev);
+		if (ret) {
+			printk(KERN_ERR
+			       "Buffer not started:"
+			       "buffer preenable failed\n");
+			goto error_remove_inserted;
+		}
+	}
+	indio_dev->scan_bytes =
+		iio_compute_scan_bytes(indio_dev,
+				       indio_dev->active_scan_mask,
+				       indio_dev->scan_timestamp);
+	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list)
+		if (buffer->access->request_update) {
+			ret = buffer->access->request_update(buffer);
+			if (ret) {
+				printk(KERN_INFO
+				       "Buffer not started:"
+				       "buffer parameter update failed\n");
+				goto error_run_postdisable;
+			}
+		}
+	if (indio_dev->info->update_scan_mode) {
+		ret = indio_dev->info
 			->update_scan_mode(indio_dev,
 					   indio_dev->active_scan_mask);
+		if (ret < 0) {
+			printk(KERN_INFO "update scan mode failed\n");
+			goto error_run_postdisable;
+		}
+	}
+	/* Definitely possible for devices to support both of these.*/
+	if (indio_dev->modes & INDIO_BUFFER_TRIGGERED) {
+		if (!indio_dev->trig) {
+			printk(KERN_INFO "Buffer not started: no trigger\n");
+			ret = -EINVAL;
+			/* Can only occur on first buffer */
+			goto error_run_postdisable;
+		}
+		indio_dev->currentmode = INDIO_BUFFER_TRIGGERED;
+	} else if (indio_dev->modes & INDIO_BUFFER_HARDWARE) {
+		indio_dev->currentmode = INDIO_BUFFER_HARDWARE;
+	} else { /* should never be reached */
+		ret = -EINVAL;
+		goto error_run_postdisable;
+	}
+
+	if (indio_dev->setup_ops->postenable) {
+		ret = indio_dev->setup_ops->postenable(indio_dev);
+		if (ret) {
+			printk(KERN_INFO
+			       "Buffer not started: postenable failed\n");
+			indio_dev->currentmode = INDIO_DIRECT_MODE;
+			if (indio_dev->setup_ops->postdisable)
+				indio_dev->setup_ops->postdisable(indio_dev);
+			goto error_disable_all_buffers;
+		}
+	}
+
+	if (indio_dev->available_scan_masks)
+		kfree(compound_mask);
+	else
+		kfree(old_mask);
+
+	return success;
+
+error_disable_all_buffers:
+	indio_dev->currentmode = INDIO_DIRECT_MODE;
+error_run_postdisable:
+	if (indio_dev->setup_ops->postdisable)
+		indio_dev->setup_ops->postdisable(indio_dev);
+error_remove_inserted:
+
+	if (insert_buffer)
+		list_del(&insert_buffer->buffer_list);
+	indio_dev->active_scan_mask = old_mask;
+	kfree(compound_mask);
+error_ret:
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iio_update_buffers);
+
+ssize_t iio_buffer_store_enable(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf,
+				size_t len)
+{
+	int ret;
+	bool requested_state;
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct iio_buffer *pbuf = indio_dev->buffer;
+	bool inlist;
+
+	ret = strtobool(buf, &requested_state);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&indio_dev->mlock);
+
+	/* Find out if it is in the list */
+	inlist = iio_buffer_is_active(indio_dev, pbuf);
+	/* Already in desired state */
+	if (inlist == requested_state)
+		goto done;
+
+	if (requested_state)
+		ret = iio_update_buffers(indio_dev,
+					 indio_dev->buffer, NULL);
+	else
+		ret = iio_update_buffers(indio_dev,
+					 NULL, indio_dev->buffer);
+
+	if (ret < 0)
+		goto done;
+done:
+	mutex_unlock(&indio_dev->mlock);
+	return (ret < 0) ? ret : len;
+}
+EXPORT_SYMBOL(iio_buffer_store_enable);
+
+int iio_sw_buffer_preenable(struct iio_dev *indio_dev)
+{
+	struct iio_buffer *buffer;
+	unsigned bytes;
+	dev_dbg(&indio_dev->dev, "%s\n", __func__);
+
+	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list)
+		if (buffer->access->set_bytes_per_datum) {
+			bytes = iio_compute_scan_bytes(indio_dev,
+						       buffer->scan_mask,
+						       buffer->scan_timestamp);
+
+			buffer->access->set_bytes_per_datum(buffer, bytes);
+		}
 	return 0;
 }
 EXPORT_SYMBOL(iio_sw_buffer_preenable);
@@ -599,7 +707,11 @@ static bool iio_validate_scan_mask(struct iio_dev *indio_dev,
  * iio_scan_mask_set() - set particular bit in the scan mask
  * @buffer: the buffer whose scan mask we are interested in
  * @bit: the bit to be set.
- **/
+ *
+ * Note that at this point we have no way of knowing what other
+ * buffers might request, hence this code only verifies that the
+ * individual buffers request is plausible.
+ */
 int iio_scan_mask_set(struct iio_dev *indio_dev,
 		      struct iio_buffer *buffer, int bit)
 {
@@ -682,13 +794,12 @@ static unsigned char *iio_demux(struct iio_buffer *buffer,
 	return buffer->demux_bounce;
 }
 
-int iio_push_to_buffer(struct iio_buffer *buffer, unsigned char *data)
+static int iio_push_to_buffer(struct iio_buffer *buffer, unsigned char *data)
 {
 	unsigned char *dataout = iio_demux(buffer, data);
 
 	return buffer->access->store_to(buffer, dataout);
 }
-EXPORT_SYMBOL_GPL(iio_push_to_buffer);
 
 static void iio_buffer_demux_free(struct iio_buffer *buffer)
 {
@@ -699,10 +810,26 @@ static void iio_buffer_demux_free(struct iio_buffer *buffer)
 	}
 }
 
-int iio_update_demux(struct iio_dev *indio_dev)
+
+int iio_push_to_buffers(struct iio_dev *indio_dev, unsigned char *data)
+{
+	int ret;
+	struct iio_buffer *buf;
+
+	list_for_each_entry(buf, &indio_dev->buffer_list, buffer_list) {
+		ret = iio_push_to_buffer(buf, data);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iio_push_to_buffers);
+
+static int iio_buffer_update_demux(struct iio_dev *indio_dev,
+				   struct iio_buffer *buffer)
 {
 	const struct iio_chan_spec *ch;
-	struct iio_buffer *buffer = indio_dev->buffer;
 	int ret, in_ind = -1, out_ind, length;
 	unsigned in_loc = 0, out_loc = 0;
 	struct iio_demux_table *p;
@@ -787,4 +914,23 @@ error_clear_mux_table:
 
 	return ret;
 }
+
+int iio_update_demux(struct iio_dev *indio_dev)
+{
+	struct iio_buffer *buffer;
+	int ret;
+
+	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list) {
+		ret = iio_buffer_update_demux(indio_dev, buffer);
+		if (ret < 0)
+			goto error_clear_mux_table;
+	}
+	return 0;
+
+error_clear_mux_table:
+	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list)
+		iio_buffer_demux_free(buffer);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(iio_update_demux);
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index cd700368eed0..060a4045be85 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -856,6 +856,7 @@ struct iio_dev *iio_device_alloc(int sizeof_priv)
 			return NULL;
 		}
 		dev_set_name(&dev->dev, "iio:device%d", dev->id);
+		INIT_LIST_HEAD(&dev->buffer_list);
 	}
 
 	return dev;
diff --git a/drivers/iio/light/adjd_s311.c b/drivers/iio/light/adjd_s311.c
index 164b62b91a4b..36d210a06b28 100644
--- a/drivers/iio/light/adjd_s311.c
+++ b/drivers/iio/light/adjd_s311.c
@@ -164,7 +164,6 @@ static irqreturn_t adjd_s311_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct adjd_s311_data *data = iio_priv(indio_dev);
-	struct iio_buffer *buffer = indio_dev->buffer;
 	s64 time_ns = iio_get_time_ns();
 	int len = 0;
 	int i, j = 0;
@@ -187,7 +186,7 @@ static irqreturn_t adjd_s311_trigger_handler(int irq, void *p)
 	if (indio_dev->scan_timestamp)
 		*(s64 *)((u8 *)data->buffer + ALIGN(len, sizeof(s64)))
 			= time_ns;
-	iio_push_to_buffer(buffer, (u8 *)data->buffer);
+	iio_push_to_buffers(indio_dev, (u8 *)data->buffer);
 
 done:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index 96e3691e42c4..8e1f69844eea 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -176,21 +176,8 @@ static const struct iio_info als_info = {
 /* Function to push data to buffer */
 static void hid_sensor_push_data(struct iio_dev *indio_dev, u8 *data, int len)
 {
-	struct iio_buffer *buffer = indio_dev->buffer;
-	int datum_sz;
-
 	dev_dbg(&indio_dev->dev, "hid_sensor_push_data\n");
-	if (!buffer) {
-		dev_err(&indio_dev->dev, "Buffer == NULL\n");
-		return;
-	}
-	datum_sz = buffer->access->get_bytes_per_datum(buffer);
-	if (len > datum_sz) {
-		dev_err(&indio_dev->dev, "Datum size mismatch %d:%d\n", len,
-				datum_sz);
-		return;
-	}
-	iio_push_to_buffer(buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 }
 
 /* Callback handler to send event after all samples are received and captured */
diff --git a/drivers/iio/magnetometer/hid-sensor-magn-3d.c b/drivers/iio/magnetometer/hid-sensor-magn-3d.c
index c4f0d274f577..d1b5fb74b9bf 100644
--- a/drivers/iio/magnetometer/hid-sensor-magn-3d.c
+++ b/drivers/iio/magnetometer/hid-sensor-magn-3d.c
@@ -198,21 +198,8 @@ static const struct iio_info magn_3d_info = {
 /* Function to push data to buffer */
 static void hid_sensor_push_data(struct iio_dev *indio_dev, u8 *data, int len)
 {
-	struct iio_buffer *buffer = indio_dev->buffer;
-	int datum_sz;
-
 	dev_dbg(&indio_dev->dev, "hid_sensor_push_data\n");
-	if (!buffer) {
-		dev_err(&indio_dev->dev, "Buffer == NULL\n");
-		return;
-	}
-	datum_sz = buffer->access->get_bytes_per_datum(buffer);
-	if (len > datum_sz) {
-		dev_err(&indio_dev->dev, "Datum size mismatch %d:%d\n", len,
-				datum_sz);
-		return;
-	}
-	iio_push_to_buffer(buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 }
 
 /* Callback handler to send event after all samples are received and captured */
diff --git a/drivers/staging/iio/accel/adis16201_ring.c b/drivers/staging/iio/accel/adis16201_ring.c
index 97c09f0c26ae..e14ca60092a2 100644
--- a/drivers/staging/iio/accel/adis16201_ring.c
+++ b/drivers/staging/iio/accel/adis16201_ring.c
@@ -82,7 +82,7 @@ static irqreturn_t adis16201_trigger_handler(int irq, void *p)
 	if (indio_dev->scan_timestamp)
 		*((s64 *)(data + ((i + 3)/4)*4)) = pf->timestamp;
 
-	iio_push_to_buffer(indio_dev->buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 
 	kfree(data);
 done:
diff --git a/drivers/staging/iio/accel/adis16203_ring.c b/drivers/staging/iio/accel/adis16203_ring.c
index 7507e1a04591..eba2e285c84a 100644
--- a/drivers/staging/iio/accel/adis16203_ring.c
+++ b/drivers/staging/iio/accel/adis16203_ring.c
@@ -81,7 +81,7 @@ static irqreturn_t adis16203_trigger_handler(int irq, void *p)
 	if (indio_dev->scan_timestamp)
 		*((s64 *)(data + ((i + 3)/4)*4)) = pf->timestamp;
 
-	iio_push_to_buffer(indio_dev->buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 
 	kfree(data);
 done:
diff --git a/drivers/staging/iio/accel/adis16204_ring.c b/drivers/staging/iio/accel/adis16204_ring.c
index 4c976bec986b..3611a13836c9 100644
--- a/drivers/staging/iio/accel/adis16204_ring.c
+++ b/drivers/staging/iio/accel/adis16204_ring.c
@@ -78,7 +78,7 @@ static irqreturn_t adis16204_trigger_handler(int irq, void *p)
 	if (indio_dev->scan_timestamp)
 		*((s64 *)(data + ((i + 3)/4)*4)) = pf->timestamp;
 
-	iio_push_to_buffer(indio_dev->buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 
 	kfree(data);
 done:
diff --git a/drivers/staging/iio/accel/adis16209_ring.c b/drivers/staging/iio/accel/adis16209_ring.c
index f939e29d6c82..6af9a5dbc709 100644
--- a/drivers/staging/iio/accel/adis16209_ring.c
+++ b/drivers/staging/iio/accel/adis16209_ring.c
@@ -78,7 +78,7 @@ static irqreturn_t adis16209_trigger_handler(int irq, void *p)
 	if (indio_dev->scan_timestamp)
 		*((s64 *)(data + ((i + 3)/4)*4)) = pf->timestamp;
 
-	iio_push_to_buffer(indio_dev->buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 
 	kfree(data);
 done:
diff --git a/drivers/staging/iio/accel/adis16240_ring.c b/drivers/staging/iio/accel/adis16240_ring.c
index caff8e25e0a2..e2ac8a8c8107 100644
--- a/drivers/staging/iio/accel/adis16240_ring.c
+++ b/drivers/staging/iio/accel/adis16240_ring.c
@@ -76,7 +76,7 @@ static irqreturn_t adis16240_trigger_handler(int irq, void *p)
 	if (indio_dev->scan_timestamp)
 		*((s64 *)(data + ((i + 3)/4)*4)) = pf->timestamp;
 
-	iio_push_to_buffer(indio_dev->buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 
 	kfree(data);
 done:
diff --git a/drivers/staging/iio/accel/lis3l02dq_ring.c b/drivers/staging/iio/accel/lis3l02dq_ring.c
index 246352716537..bc38651c315e 100644
--- a/drivers/staging/iio/accel/lis3l02dq_ring.c
+++ b/drivers/staging/iio/accel/lis3l02dq_ring.c
@@ -154,7 +154,7 @@ static irqreturn_t lis3l02dq_trigger_handler(int irq, void *p)
 	if (indio_dev->scan_timestamp)
 		*(s64 *)((u8 *)data + ALIGN(len, sizeof(s64)))
 			= pf->timestamp;
-	iio_push_to_buffer(indio_dev->buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 
 	kfree(data);
 done:
diff --git a/drivers/staging/iio/adc/ad7298_ring.c b/drivers/staging/iio/adc/ad7298_ring.c
index c2906a85fedb..b3dd514b9627 100644
--- a/drivers/staging/iio/adc/ad7298_ring.c
+++ b/drivers/staging/iio/adc/ad7298_ring.c
@@ -93,7 +93,7 @@ static irqreturn_t ad7298_trigger_handler(int irq, void *p)
 						 indio_dev->masklength); i++)
 		buf[i] = be16_to_cpu(st->rx_buf[i]);
 
-	iio_push_to_buffer(indio_dev->buffer, (u8 *)buf);
+	iio_push_to_buffers(indio_dev, (u8 *)buf);
 
 done:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/staging/iio/adc/ad7606_ring.c b/drivers/staging/iio/adc/ad7606_ring.c
index ba04d0ffd4f4..2b25cb07fe41 100644
--- a/drivers/staging/iio/adc/ad7606_ring.c
+++ b/drivers/staging/iio/adc/ad7606_ring.c
@@ -83,7 +83,7 @@ static void ad7606_poll_bh_to_ring(struct work_struct *work_s)
 	if (indio_dev->scan_timestamp)
 		*((s64 *)(buf + indio_dev->scan_bytes - sizeof(s64))) = time_ns;
 
-	iio_push_to_buffer(indio_dev->buffer, buf);
+	iio_push_to_buffers(indio_dev, buf);
 done:
 	gpio_set_value(st->pdata->gpio_convst, 0);
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/staging/iio/adc/ad799x_ring.c b/drivers/staging/iio/adc/ad799x_ring.c
index 86026d9b20bc..2c5f38475a8e 100644
--- a/drivers/staging/iio/adc/ad799x_ring.c
+++ b/drivers/staging/iio/adc/ad799x_ring.c
@@ -77,7 +77,7 @@ static irqreturn_t ad799x_trigger_handler(int irq, void *p)
 		memcpy(rxbuf + indio_dev->scan_bytes - sizeof(s64),
 			&time_ns, sizeof(time_ns));
 
-	iio_push_to_buffer(indio_dev->buffer, rxbuf);
+	iio_push_to_buffers(indio_dev, rxbuf);
 done:
 	kfree(rxbuf);
 out:
diff --git a/drivers/staging/iio/adc/max1363_ring.c b/drivers/staging/iio/adc/max1363_ring.c
index 5f74f3b7671a..688304bdbaf0 100644
--- a/drivers/staging/iio/adc/max1363_ring.c
+++ b/drivers/staging/iio/adc/max1363_ring.c
@@ -80,7 +80,7 @@ static irqreturn_t max1363_trigger_handler(int irq, void *p)
 
 	if (indio_dev->scan_timestamp)
 		memcpy(rxbuf + d_size - sizeof(s64), &time_ns, sizeof(time_ns));
-	iio_push_to_buffer(indio_dev->buffer, rxbuf);
+	iio_push_to_buffers(indio_dev, rxbuf);
 
 done_free:
 	kfree(rxbuf);
diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c
index df5bba284b73..3b467d8c5882 100644
--- a/drivers/staging/iio/adc/mxs-lradc.c
+++ b/drivers/staging/iio/adc/mxs-lradc.c
@@ -237,7 +237,6 @@ static irqreturn_t mxs_lradc_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *iio = pf->indio_dev;
 	struct mxs_lradc *lradc = iio_priv(iio);
-	struct iio_buffer *buffer = iio->buffer;
 	const uint32_t chan_value = LRADC_CH_ACCUMULATE |
 		((LRADC_DELAY_TIMER_LOOP - 1) << LRADC_CH_NUM_SAMPLES_OFFSET);
 	int i, j = 0;
@@ -256,7 +255,7 @@ static irqreturn_t mxs_lradc_trigger_handler(int irq, void *p)
 		*timestamp = pf->timestamp;
 	}
 
-	iio_push_to_buffer(buffer, (u8 *)lradc->buffer);
+	iio_push_to_buffers(iio, (u8 *)lradc->buffer);
 
 	iio_trigger_notify_done(iio->trig);
 
diff --git a/drivers/staging/iio/gyro/adis16260_ring.c b/drivers/staging/iio/gyro/adis16260_ring.c
index e294cb49736d..d6c48f850a9e 100644
--- a/drivers/staging/iio/gyro/adis16260_ring.c
+++ b/drivers/staging/iio/gyro/adis16260_ring.c
@@ -81,7 +81,7 @@ static irqreturn_t adis16260_trigger_handler(int irq, void *p)
 	if (indio_dev->scan_timestamp)
 		*((s64 *)(data + ((i + 3)/4)*4)) = pf->timestamp;
 
-	iio_push_to_buffer(indio_dev->buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 
 	kfree(data);
 done:
diff --git a/drivers/staging/iio/iio_simple_dummy_buffer.c b/drivers/staging/iio/iio_simple_dummy_buffer.c
index 697d9700db2f..dee16f0e7570 100644
--- a/drivers/staging/iio/iio_simple_dummy_buffer.c
+++ b/drivers/staging/iio/iio_simple_dummy_buffer.c
@@ -46,7 +46,6 @@ static irqreturn_t iio_simple_dummy_trigger_h(int irq, void *p)
 {
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
-	struct iio_buffer *buffer = indio_dev->buffer;
 	int len = 0;
 	u16 *data;
 
@@ -76,7 +75,7 @@ static irqreturn_t iio_simple_dummy_trigger_h(int irq, void *p)
 		     i < bitmap_weight(indio_dev->active_scan_mask,
 				       indio_dev->masklength);
 		     i++, j++) {
-			j = find_next_bit(buffer->scan_mask,
+			j = find_next_bit(indio_dev->active_scan_mask,
 					  indio_dev->masklength, j);
 			/* random access read from the 'device' */
 			data[i] = fakedata[j];
@@ -87,7 +86,7 @@ static irqreturn_t iio_simple_dummy_trigger_h(int irq, void *p)
 	if (indio_dev->scan_timestamp)
 		*(s64 *)((u8 *)data + ALIGN(len, sizeof(s64)))
 			= iio_get_time_ns();
-	iio_push_to_buffer(buffer, (u8 *)data);
+	iio_push_to_buffers(indio_dev, (u8 *)data);
 
 	kfree(data);
 
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index de21d47f33e9..b1fef147d5b5 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -647,7 +647,6 @@ static void ad5933_work(struct work_struct *work)
 	struct ad5933_state *st = container_of(work,
 		struct ad5933_state, work.work);
 	struct iio_dev *indio_dev = i2c_get_clientdata(st->client);
-	struct iio_buffer *ring = indio_dev->buffer;
 	signed short buf[2];
 	unsigned char status;
 
@@ -677,8 +676,7 @@ static void ad5933_work(struct work_struct *work)
 		} else {
 			buf[0] = be16_to_cpu(buf[0]);
 		}
-		/* save datum to the ring */
-		iio_push_to_buffer(ring, (u8 *)buf);
+		iio_push_to_buffers(indio_dev, (u8 *)buf);
 	} else {
 		/* no data available - try again later */
 		schedule_delayed_work(&st->work, st->poll_time_jiffies);
diff --git a/drivers/staging/iio/imu/adis16400_ring.c b/drivers/staging/iio/imu/adis16400_ring.c
index 260bdd1a4681..d46c1e38cf7b 100644
--- a/drivers/staging/iio/imu/adis16400_ring.c
+++ b/drivers/staging/iio/imu/adis16400_ring.c
@@ -114,7 +114,6 @@ static irqreturn_t adis16400_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct adis16400_state *st = iio_priv(indio_dev);
-	struct iio_buffer *ring = indio_dev->buffer;
 	int i = 0, j, ret = 0;
 	s16 *data;
 
@@ -148,9 +147,9 @@ static irqreturn_t adis16400_trigger_handler(int irq, void *p)
 		}
 	}
 	/* Guaranteed to be aligned with 8 byte boundary */
-	if (ring->scan_timestamp)
+	if (indio_dev->scan_timestamp)
 		*((s64 *)(data + ((i + 3)/4)*4)) = pf->timestamp;
-	iio_push_to_buffer(ring, (u8 *) data);
+	iio_push_to_buffers(indio_dev, (u8 *) data);
 
 done:
 	kfree(data);
diff --git a/drivers/staging/iio/meter/ade7758_ring.c b/drivers/staging/iio/meter/ade7758_ring.c
index 9e49baccf660..4552a4c7fe33 100644
--- a/drivers/staging/iio/meter/ade7758_ring.c
+++ b/drivers/staging/iio/meter/ade7758_ring.c
@@ -73,7 +73,7 @@ static irqreturn_t ade7758_trigger_handler(int irq, void *p)
 	if (indio_dev->scan_timestamp)
 		dat64[1] = pf->timestamp;
 
-	iio_push_to_buffer(indio_dev->buffer, (u8 *)dat64);
+	iio_push_to_buffers(indio_dev, (u8 *)dat64);
 
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h
index c629b3a1d9a9..027040569180 100644
--- a/include/linux/iio/buffer.h
+++ b/include/linux/iio/buffer.h
@@ -66,7 +66,8 @@ struct iio_buffer_access_funcs {
  * @stufftoread:	[INTERN] flag to indicate new data.
  * @demux_list:		[INTERN] list of operations required to demux the scan.
  * @demux_bounce:	[INTERN] buffer for doing gather from incoming scan.
- **/
+ * @buffer_list:	[INTERN] entry in the devices list of current buffers.
+ */
 struct iio_buffer {
 	int					length;
 	int					bytes_per_datum;
@@ -81,8 +82,21 @@ struct iio_buffer {
 	const struct attribute_group *attrs;
 	struct list_head			demux_list;
 	unsigned char				*demux_bounce;
+	struct list_head			buffer_list;
 };
 
+/**
+ * iio_update_buffers() - add or remove buffer from active list
+ * @indio_dev:		device to add buffer to
+ * @insert_buffer:	buffer to insert
+ * @remove_buffer:	buffer_to_remove
+ *
+ * Note this will tear down the all buffering and build it up again
+ */
+int iio_update_buffers(struct iio_dev *indio_dev,
+		       struct iio_buffer *insert_buffer,
+		       struct iio_buffer *remove_buffer);
+
 /**
  * iio_buffer_init() - Initialize the buffer structure
  * @buffer:		buffer to be initialized
@@ -115,11 +129,11 @@ int iio_scan_mask_set(struct iio_dev *indio_dev,
 		      struct iio_buffer *buffer, int bit);
 
 /**
- * iio_push_to_buffer() - push to a registered buffer.
- * @buffer:		IIO buffer structure for device
- * @data:		the data to push to the buffer
+ * iio_push_to_buffers() - push to a registered buffer.
+ * @indio_dev:		iio_dev structure for device.
+ * @data:		Full scan.
  */
-int iio_push_to_buffer(struct iio_buffer *buffer, unsigned char *data);
+int iio_push_to_buffers(struct iio_dev *indio_dev, unsigned char *data);
 
 int iio_update_demux(struct iio_dev *indio_dev);
 
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 7806c24e5bc8..adca93a999a7 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -410,6 +410,7 @@ struct iio_buffer_setup_ops {
  *			and owner
  * @event_interface:	[INTERN] event chrdevs associated with interrupt lines
  * @buffer:		[DRIVER] any buffer present
+ * @buffer_list:	[INTERN] list of all buffers currently attached
  * @scan_bytes:		[INTERN] num bytes captured to be fed to buffer demux
  * @mlock:		[INTERN] lock used to prevent simultaneous device state
  *			changes
@@ -448,6 +449,7 @@ struct iio_dev {
 	struct iio_event_interface	*event_interface;
 
 	struct iio_buffer		*buffer;
+	struct list_head		buffer_list;
 	int				scan_bytes;
 	struct mutex			mlock;
 
-- 
cgit v1.2.3-55-g7522


From 0464415dd21785aa8e8b12dbc939fcb5ca52f464 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron
Date: Sat, 30 Jun 2012 20:06:00 +0100
Subject: staging:iio:in kernel users: Add a data field for channel specific
 info.

Used to allow information about a given channel mapping to be passed
through from board files to the consumer drivers.

Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/inkern.c         | 1 +
 include/linux/iio/consumer.h | 2 ++
 include/linux/iio/machine.h  | 2 ++
 3 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c
index b394621d362c..d55e98fb300e 100644
--- a/drivers/iio/inkern.c
+++ b/drivers/iio/inkern.c
@@ -203,6 +203,7 @@ struct iio_channel *iio_channel_get_all(const char *name)
 		if (name && strcmp(name, c->map->consumer_dev_name) != 0)
 			continue;
 		chans[mapind].indio_dev = c->indio_dev;
+		chans[mapind].data = c->map->consumer_data;
 		chans[mapind].channel =
 			iio_chan_spec_from_name(chans[mapind].indio_dev,
 						c->map->adc_channel_label);
diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h
index e875bcf0478f..57efee63a6da 100644
--- a/include/linux/iio/consumer.h
+++ b/include/linux/iio/consumer.h
@@ -18,10 +18,12 @@ struct iio_chan_spec;
  * struct iio_channel - everything needed for a consumer to use a channel
  * @indio_dev:		Device on which the channel exists.
  * @channel:		Full description of the channel.
+ * @data:		Data about the channel used by consumer.
  */
 struct iio_channel {
 	struct iio_dev *indio_dev;
 	const struct iio_chan_spec *channel;
+	void *data;
 };
 
 /**
diff --git a/include/linux/iio/machine.h b/include/linux/iio/machine.h
index 809a3f08d5a5..1601a2a63a72 100644
--- a/include/linux/iio/machine.h
+++ b/include/linux/iio/machine.h
@@ -19,11 +19,13 @@
  * @consumer_dev_name:	Name to uniquely identify the consumer device.
  * @consumer_channel:	Unique name used to identify the channel on the
  *			consumer side.
+ * @consumer_data:	Data about the channel for use by the consumer driver.
  */
 struct iio_map {
 	const char *adc_channel_label;
 	const char *consumer_dev_name;
 	const char *consumer_channel;
+	void *consumer_data;
 };
 
 #endif
-- 
cgit v1.2.3-55-g7522


From 92d1079b281f89f1c65c6aece3cfab4fb422c797 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron
Date: Sat, 30 Jun 2012 20:06:00 +0100
Subject: staging:iio: add a callback buffer for in kernel push interface

This callback buffer is meant to be opaque to users, but basically
adds a very simple pass through buffer to which data may be
pushed when it is inserted into the buffer list.

Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/Kconfig          |   6 +++
 drivers/iio/Makefile         |   1 +
 drivers/iio/buffer_cb.c      | 113 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/iio/consumer.h |  46 ++++++++++++++++++
 4 files changed, 166 insertions(+)
 create mode 100644 drivers/iio/buffer_cb.c

(limited to 'include')

diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig
index fc937aca71fb..65ae734c607d 100644
--- a/drivers/iio/Kconfig
+++ b/drivers/iio/Kconfig
@@ -20,6 +20,12 @@ config IIO_BUFFER
 
 if IIO_BUFFER
 
+config IIO_BUFFER_CB
+boolean "IIO callback buffer used for push in-kernel interfaces"
+	help
+	  Should be selected by any drivers that do-inkernel push
+	  usage.  That is, those where the data is pushed to the consumer.
+
 config IIO_KFIFO_BUF
 	select IIO_TRIGGER
 	tristate "Industrial I/O buffering based on kfifo"
diff --git a/drivers/iio/Makefile b/drivers/iio/Makefile
index 761f2b65ac52..31d76a07ec65 100644
--- a/drivers/iio/Makefile
+++ b/drivers/iio/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_IIO) += industrialio.o
 industrialio-y := industrialio-core.o industrialio-event.o inkern.o
 industrialio-$(CONFIG_IIO_BUFFER) += industrialio-buffer.o
 industrialio-$(CONFIG_IIO_TRIGGER) += industrialio-trigger.o
+industrialio-$(CONFIG_IIO_BUFFER_CB) += buffer_cb.o
 
 obj-$(CONFIG_IIO_TRIGGERED_BUFFER) += industrialio-triggered-buffer.o
 obj-$(CONFIG_IIO_KFIFO_BUF) += kfifo_buf.o
diff --git a/drivers/iio/buffer_cb.c b/drivers/iio/buffer_cb.c
new file mode 100644
index 000000000000..4d40e24f3721
--- /dev/null
+++ b/drivers/iio/buffer_cb.c
@@ -0,0 +1,113 @@
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/consumer.h>
+
+struct iio_cb_buffer {
+	struct iio_buffer buffer;
+	int (*cb)(u8 *data, void *private);
+	void *private;
+	struct iio_channel *channels;
+};
+
+static int iio_buffer_cb_store_to(struct iio_buffer *buffer, u8 *data)
+{
+	struct iio_cb_buffer *cb_buff = container_of(buffer,
+						     struct iio_cb_buffer,
+						     buffer);
+
+	return cb_buff->cb(data, cb_buff->private);
+}
+
+static struct iio_buffer_access_funcs iio_cb_access = {
+	.store_to = &iio_buffer_cb_store_to,
+};
+
+struct iio_cb_buffer *iio_channel_get_all_cb(const char *name,
+					     int (*cb)(u8 *data,
+						       void *private),
+					     void *private)
+{
+	int ret;
+	struct iio_cb_buffer *cb_buff;
+	struct iio_dev *indio_dev;
+	struct iio_channel *chan;
+
+	cb_buff = kzalloc(sizeof(*cb_buff), GFP_KERNEL);
+	if (cb_buff == NULL) {
+		ret = -ENOMEM;
+		goto error_ret;
+	}
+
+	cb_buff->private = private;
+	cb_buff->cb = cb;
+	cb_buff->buffer.access = &iio_cb_access;
+	INIT_LIST_HEAD(&cb_buff->buffer.demux_list);
+
+	cb_buff->channels = iio_channel_get_all(name);
+	if (IS_ERR(cb_buff->channels)) {
+		ret = PTR_ERR(cb_buff->channels);
+		goto error_free_cb_buff;
+	}
+
+	indio_dev = cb_buff->channels[0].indio_dev;
+	cb_buff->buffer.scan_mask
+		= kcalloc(BITS_TO_LONGS(indio_dev->masklength), sizeof(long),
+			  GFP_KERNEL);
+	if (cb_buff->buffer.scan_mask == NULL) {
+		ret = -ENOMEM;
+		goto error_release_channels;
+	}
+	chan = &cb_buff->channels[0];
+	while (chan->indio_dev) {
+		if (chan->indio_dev != indio_dev) {
+			ret = -EINVAL;
+			goto error_release_channels;
+		}
+		set_bit(chan->channel->scan_index,
+			cb_buff->buffer.scan_mask);
+		chan++;
+	}
+
+	return cb_buff;
+
+error_release_channels:
+	iio_channel_release_all(cb_buff->channels);
+error_free_cb_buff:
+	kfree(cb_buff);
+error_ret:
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(iio_channel_get_all_cb);
+
+int iio_channel_start_all_cb(struct iio_cb_buffer *cb_buff)
+{
+	return iio_update_buffers(cb_buff->channels[0].indio_dev,
+				  &cb_buff->buffer,
+				  NULL);
+}
+EXPORT_SYMBOL_GPL(iio_channel_start_all_cb);
+
+void iio_channel_stop_all_cb(struct iio_cb_buffer *cb_buff)
+{
+	iio_update_buffers(cb_buff->channels[0].indio_dev,
+			   NULL,
+			   &cb_buff->buffer);
+}
+EXPORT_SYMBOL_GPL(iio_channel_stop_all_cb);
+
+void iio_channel_release_all_cb(struct iio_cb_buffer *cb_buff)
+{
+	iio_channel_release_all(cb_buff->channels);
+	kfree(cb_buff);
+}
+EXPORT_SYMBOL_GPL(iio_channel_release_all_cb);
+
+struct iio_channel
+*iio_channel_cb_get_channels(const struct iio_cb_buffer *cb_buffer)
+{
+	return cb_buffer->channels;
+}
+EXPORT_SYMBOL_GPL(iio_channel_cb_get_channels);
diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h
index 57efee63a6da..126c0a9375f2 100644
--- a/include/linux/iio/consumer.h
+++ b/include/linux/iio/consumer.h
@@ -61,6 +61,52 @@ struct iio_channel *iio_channel_get_all(const char *name);
  */
 void iio_channel_release_all(struct iio_channel *chan);
 
+struct iio_cb_buffer;
+/**
+ * iio_channel_get_all_cb() - register callback for triggered capture
+ * @name:		Name of client device.
+ * @cb:			Callback function.
+ * @private:		Private data passed to callback.
+ *
+ * NB right now we have no ability to mux data from multiple devices.
+ * So if the channels requested come from different devices this will
+ * fail.
+ */
+struct iio_cb_buffer *iio_channel_get_all_cb(const char *name,
+					     int (*cb)(u8 *data,
+						       void *private),
+					     void *private);
+/**
+ * iio_channel_release_all_cb() - release and unregister the callback.
+ * @cb_buffer:		The callback buffer that was allocated.
+ */
+void iio_channel_release_all_cb(struct iio_cb_buffer *cb_buffer);
+
+/**
+ * iio_channel_start_all_cb() - start the flow of data through callback.
+ * @cb_buff:		The callback buffer we are starting.
+ */
+int iio_channel_start_all_cb(struct iio_cb_buffer *cb_buff);
+
+/**
+ * iio_channel_stop_all_cb() - stop the flow of data through the callback.
+ * @cb_buff:		The callback buffer we are stopping.
+ */
+void iio_channel_stop_all_cb(struct iio_cb_buffer *cb_buff);
+
+/**
+ * iio_channel_cb_get_channels() - get access to the underlying channels.
+ * @cb_buff:		The callback buffer from whom we want the channel
+ *			information.
+ *
+ * This function allows one to obtain information about the channels.
+ * Whilst this may allow direct reading if all buffers are disabled, the
+ * primary aim is to allow drivers that are consuming a channel to query
+ * things like scaling of the channel.
+ */
+struct iio_channel
+*iio_channel_cb_get_channels(const struct iio_cb_buffer *cb_buffer);
+
 /**
  * iio_read_channel_raw() - read from a given channel
  * @chan:		The channel being queried.
-- 
cgit v1.2.3-55-g7522


From 76f93992e4c44f30be797d5c99d6f369ed001747 Mon Sep 17 00:00:00 2001
From: Lee Jones
Date: Mon, 5 Nov 2012 16:10:31 +0100
Subject: mfd: Provide the STMPE driver with its own IRQ domain

The STMPE driver is yet another IRQ controller which requires its
own IRQ domain. So, we provide it with one.

Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/stmpe.c       | 82 +++++++++++++++++++++++++++++------------------
 include/linux/mfd/stmpe.h |  2 ++
 2 files changed, 52 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c
index ad13cb00a749..5c8d8f260df2 100644
--- a/drivers/mfd/stmpe.c
+++ b/drivers/mfd/stmpe.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/irqdomain.h>
 #include <linux/pm.h>
 #include <linux/slab.h>
 #include <linux/mfd/core.h>
@@ -757,7 +758,9 @@ static irqreturn_t stmpe_irq(int irq, void *data)
 	int i;
 
 	if (variant->id_val == STMPE801_ID) {
-		handle_nested_irq(stmpe->irq_base);
+		int base = irq_create_mapping(stmpe->domain, 0);
+
+		handle_nested_irq(base);
 		return IRQ_HANDLED;
 	}
 
@@ -778,8 +781,9 @@ static irqreturn_t stmpe_irq(int irq, void *data)
 		while (status) {
 			int bit = __ffs(status);
 			int line = bank * 8 + bit;
+			int nestedirq = irq_create_mapping(stmpe->domain, line);
 
-			handle_nested_irq(stmpe->irq_base + line);
+			handle_nested_irq(nestedirq);
 			status &= ~(1 << bit);
 		}
 
@@ -820,7 +824,7 @@ static void stmpe_irq_sync_unlock(struct irq_data *data)
 static void stmpe_irq_mask(struct irq_data *data)
 {
 	struct stmpe *stmpe = irq_data_get_irq_chip_data(data);
-	int offset = data->irq - stmpe->irq_base;
+	int offset = data->hwirq;
 	int regoffset = offset / 8;
 	int mask = 1 << (offset % 8);
 
@@ -830,7 +834,7 @@ static void stmpe_irq_mask(struct irq_data *data)
 static void stmpe_irq_unmask(struct irq_data *data)
 {
 	struct stmpe *stmpe = irq_data_get_irq_chip_data(data);
-	int offset = data->irq - stmpe->irq_base;
+	int offset = data->hwirq;
 	int regoffset = offset / 8;
 	int mask = 1 << (offset % 8);
 
@@ -845,43 +849,62 @@ static struct irq_chip stmpe_irq_chip = {
 	.irq_unmask		= stmpe_irq_unmask,
 };
 
-static int __devinit stmpe_irq_init(struct stmpe *stmpe)
+static int stmpe_irq_map(struct irq_domain *d, unsigned int virq,
+                                irq_hw_number_t hwirq)
 {
+	struct stmpe *stmpe = d->host_data;
 	struct irq_chip *chip = NULL;
-	int num_irqs = stmpe->variant->num_irqs;
-	int base = stmpe->irq_base;
-	int irq;
 
 	if (stmpe->variant->id_val != STMPE801_ID)
 		chip = &stmpe_irq_chip;
 
-	for (irq = base; irq < base + num_irqs; irq++) {
-		irq_set_chip_data(irq, stmpe);
-		irq_set_chip_and_handler(irq, chip, handle_edge_irq);
-		irq_set_nested_thread(irq, 1);
+	irq_set_chip_data(virq, stmpe);
+	irq_set_chip_and_handler(virq, chip, handle_edge_irq);
+	irq_set_nested_thread(virq, 1);
 #ifdef CONFIG_ARM
-		set_irq_flags(irq, IRQF_VALID);
+	set_irq_flags(virq, IRQF_VALID);
 #else
-		irq_set_noprobe(irq);
+	irq_set_noprobe(virq);
 #endif
-	}
 
 	return 0;
 }
 
-static void stmpe_irq_remove(struct stmpe *stmpe)
+static void stmpe_irq_unmap(struct irq_domain *d, unsigned int virq)
 {
-	int num_irqs = stmpe->variant->num_irqs;
-	int base = stmpe->irq_base;
-	int irq;
-
-	for (irq = base; irq < base + num_irqs; irq++) {
 #ifdef CONFIG_ARM
-		set_irq_flags(irq, 0);
+		set_irq_flags(virq, 0);
 #endif
-		irq_set_chip_and_handler(irq, NULL, NULL);
-		irq_set_chip_data(irq, NULL);
+		irq_set_chip_and_handler(virq, NULL, NULL);
+		irq_set_chip_data(virq, NULL);
+}
+
+static struct irq_domain_ops stmpe_irq_ops = {
+        .map    = stmpe_irq_map,
+        .unmap  = stmpe_irq_unmap,
+        .xlate  = irq_domain_xlate_twocell,
+};
+
+static int __devinit stmpe_irq_init(struct stmpe *stmpe)
+{
+	int base = stmpe->irq_base;
+	int num_irqs = stmpe->variant->num_irqs;
+
+	if (base) {
+		stmpe->domain = irq_domain_add_legacy(
+			NULL, num_irqs, base, 0, &stmpe_irq_ops, stmpe);
+	}
+	else {
+		stmpe->domain = irq_domain_add_linear(
+			NULL, num_irqs, &stmpe_irq_ops, stmpe);
+	}
+
+	if (!stmpe->domain) {
+		dev_err(stmpe->dev, "Failed to create irqdomain\n");
+		return -ENOSYS;
 	}
+
+	return 0;
 }
 
 static int __devinit stmpe_chip_init(struct stmpe *stmpe)
@@ -954,7 +977,7 @@ static int __devinit stmpe_add_device(struct stmpe *stmpe,
 				      struct mfd_cell *cell)
 {
 	return mfd_add_devices(stmpe->dev, stmpe->pdata->id, cell, 1,
-			       NULL, stmpe->irq_base, NULL);
+			       NULL, stmpe->irq_base, stmpe->domain);
 }
 
 static int __devinit stmpe_devices_init(struct stmpe *stmpe)
@@ -1067,7 +1090,7 @@ int __devinit stmpe_probe(struct stmpe_client_info *ci, int partnum)
 		if (ret) {
 			dev_err(stmpe->dev, "failed to request IRQ: %d\n",
 					ret);
-			goto out_removeirq;
+			goto free_gpio;
 		}
 	}
 
@@ -1083,9 +1106,6 @@ out_removedevs:
 	mfd_remove_devices(stmpe->dev);
 	if (stmpe->irq >= 0)
 		free_irq(stmpe->irq, stmpe);
-out_removeirq:
-	if (stmpe->irq >= 0)
-		stmpe_irq_remove(stmpe);
 free_gpio:
 	if (pdata->irq_over_gpio)
 		gpio_free(pdata->irq_gpio);
@@ -1098,10 +1118,8 @@ int stmpe_remove(struct stmpe *stmpe)
 {
 	mfd_remove_devices(stmpe->dev);
 
-	if (stmpe->irq >= 0) {
+	if (stmpe->irq >= 0)
 		free_irq(stmpe->irq, stmpe);
-		stmpe_irq_remove(stmpe);
-	}
 
 	if (stmpe->pdata->irq_over_gpio)
 		gpio_free(stmpe->pdata->irq_gpio);
diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h
index f8d5b4d5843f..15dac790365f 100644
--- a/include/linux/mfd/stmpe.h
+++ b/include/linux/mfd/stmpe.h
@@ -62,6 +62,7 @@ struct stmpe_client_info;
  * @lock: lock protecting I/O operations
  * @irq_lock: IRQ bus lock
  * @dev: device, mostly for dev_dbg()
+ * @irq_domain: IRQ domain
  * @client: client - i2c or spi
  * @ci: client specific information
  * @partnum: part number
@@ -79,6 +80,7 @@ struct stmpe {
 	struct mutex lock;
 	struct mutex irq_lock;
 	struct device *dev;
+	struct irq_domain *domain;
 	void *client;
 	struct stmpe_client_info *ci;
 	enum stmpe_partnum partnum;
-- 
cgit v1.2.3-55-g7522


From cfc1a062063bb5b8e3fa2b007043dfc9e27b5a40 Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Sat, 27 Oct 2012 15:52:04 +0200
Subject: drm: add helper to sort panels to the head of the connector list

Userspace seems to like this, see

commit cb0953d734348e8862d6d7edc666cfb3bf6d8fae
Author: Adam Jackson <ajax@redhat.com>
Date:   Fri Jul 16 14:46:29 2010 -0400

    drm/i915: Initialize LVDS and eDP outputs before anything else

    This makes them sort to the front in X, which makes them likely to be
    the primary outputs if you haven't specified a preference in your DE,
    which is likely to be what you want.

    Signed-off-by: Adam Jackson <ajax@redhat.com>
    Signed-off-by: Eric Anholt <eric@anholt.net>

Sorting the connector list after the fact is much easier than trying
to be clever with the init sequence.

Acked-by: Dave Airlie <airlied@gmail.com>
Reviewed-by: Adam Jackson <ajax@redhat.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc_helper.c | 18 ++++++++++++++++++
 include/drm/drm_crtc_helper.h     |  2 ++
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 1227adf74dbc..710516815de7 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -39,6 +39,24 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_edid.h>
 
+void drm_helper_move_panel_connectors_to_head(struct drm_device *dev)
+{
+	struct drm_connector *connector, *tmp;
+	struct list_head panel_list;
+
+	INIT_LIST_HEAD(&panel_list);
+
+	list_for_each_entry_safe(connector, tmp,
+				 &dev->mode_config.connector_list, head) {
+		if (connector->connector_type == DRM_MODE_CONNECTOR_LVDS ||
+		    connector->connector_type == DRM_MODE_CONNECTOR_eDP)
+			list_move_tail(&connector->head, &panel_list);
+	}
+
+	list_splice(&panel_list, &dev->mode_config.connector_list);
+}
+EXPORT_SYMBOL(drm_helper_move_panel_connectors_to_head);
+
 static bool drm_kms_helper_poll = true;
 module_param_named(poll, drm_kms_helper_poll, bool, 0600);
 
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index e01cc80c9c30..defee28f6b95 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -137,6 +137,8 @@ extern bool drm_helper_encoder_in_use(struct drm_encoder *encoder);
 
 extern void drm_helper_connector_dpms(struct drm_connector *connector, int mode);
 
+extern void drm_helper_move_panel_connectors_to_head(struct drm_device *);
+
 extern int drm_helper_mode_fill_fb_struct(struct drm_framebuffer *fb,
 					  struct drm_mode_fb_cmd2 *mode_cmd);
 
-- 
cgit v1.2.3-55-g7522


From e76e9aebcdbfebae8f4cd147e3c0f800d36e97f3 Mon Sep 17 00:00:00 2001
From: Ben Widawsky
Date: Sun, 4 Nov 2012 09:21:27 -0800
Subject: drm/i915: Stop using AGP layer for GEN6+

As a quick hack we make the old intel_gtt structure mutable so we can
fool a bunch of the existing code which depends on elements in that data
structure. We can/should try to remove this in a subsequent patch.

This should preserve the old gtt init behavior which upon writing these
patches seems incorrect. The next patch will fix these things.

The one exception is VLV which doesn't have the preserved flush control
write behavior. Since we want to do that for all GEN6+ stuff, we'll
handle that in a later patch. Mainstream VLV support doesn't actually
exist yet anyway.

v2: Update the comment to remove the "voodoo"
Check that the last pte written matches what we readback

v3: actually kill cache_level_to_agp_type since most of the flags will
disappear in an upcoming patch

v4: v3 was actually not what we wanted (Daniel)
Make the ggtt bind assertions better and stricter (Chris)
Fix some uncaught errors at gtt init (Chris)
Some other random stuff that Chris wanted

v5: check for i==0 in gen6_ggtt_bind_object to shut up gcc (Ben)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by [v4]: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Make the cache_level -> agp_flags conversion for pre-gen6 a
tad more robust by mapping everything != CACHE_NONE to the cached agp
flag - we have a 1:1 uncached mapping, but different modes of
cacheable (at least on later generations). Suggested by Chris Wilson.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/char/agp/intel-gtt.c               |   2 +-
 drivers/gpu/drm/i915/i915_dma.c            |  16 +-
 drivers/gpu/drm/i915/i915_drv.h            |  10 +-
 drivers/gpu/drm/i915/i915_gem.c            |  12 +-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |   2 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c        | 257 +++++++++++++++++++++++++----
 drivers/gpu/drm/i915/i915_reg.h            |   6 +
 include/drm/intel-gtt.h                    |   3 +-
 8 files changed, 257 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 38390f7c6ab6..4dfbb80f0fd5 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -1686,7 +1686,7 @@ int intel_gmch_probe(struct pci_dev *bridge_pdev, struct pci_dev *gpu_pdev,
 }
 EXPORT_SYMBOL(intel_gmch_probe);
 
-const struct intel_gtt *intel_gtt_get(void)
+struct intel_gtt *intel_gtt_get(void)
 {
 	return &intel_private.base;
 }
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index ff06e3239ada..1eea5be43617 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1496,19 +1496,9 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		goto free_priv;
 	}
 
-	ret = intel_gmch_probe(dev_priv->bridge_dev, dev->pdev, NULL);
-	if (!ret) {
-		DRM_ERROR("failed to set up gmch\n");
-		ret = -EIO;
+	ret = i915_gem_gtt_init(dev);
+	if (ret)
 		goto put_bridge;
-	}
-
-	dev_priv->mm.gtt = intel_gtt_get();
-	if (!dev_priv->mm.gtt) {
-		DRM_ERROR("Failed to initialize GTT\n");
-		ret = -ENODEV;
-		goto put_gmch;
-	}
 
 	i915_kick_out_firmware_fb(dev_priv);
 
@@ -1683,7 +1673,7 @@ out_mtrrfree:
 out_rmmap:
 	pci_iounmap(dev->pdev, dev_priv->regs);
 put_gmch:
-	intel_gmch_remove();
+	i915_gem_gtt_fini(dev);
 put_bridge:
 	pci_dev_put(dev_priv->bridge_dev);
 free_priv:
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c4339c2b1b57..f316916fe65e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -746,7 +746,7 @@ typedef struct drm_i915_private {
 
 	struct {
 		/** Bridge to intel-gtt-ko */
-		const struct intel_gtt *gtt;
+		struct intel_gtt *gtt;
 		/** Memory allocator for GTT stolen memory */
 		struct drm_mm stolen;
 		/** Memory allocator for GTT */
@@ -1538,6 +1538,14 @@ void i915_gem_init_global_gtt(struct drm_device *dev,
 			      unsigned long start,
 			      unsigned long mappable_end,
 			      unsigned long end);
+int i915_gem_gtt_init(struct drm_device *dev);
+void i915_gem_gtt_fini(struct drm_device *dev);
+extern inline void i915_gem_chipset_flush(struct drm_device *dev)
+{
+	if (INTEL_INFO(dev)->gen < 6)
+		intel_gtt_chipset_flush();
+}
+
 
 /* i915_gem_evict.c */
 int __must_check i915_gem_evict_something(struct drm_device *dev, int min_size,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d8eaebfea93e..c161fdbd830f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -845,12 +845,12 @@ out:
 		 * domain anymore. */
 		if (obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
 			i915_gem_clflush_object(obj);
-			intel_gtt_chipset_flush();
+			i915_gem_chipset_flush(dev);
 		}
 	}
 
 	if (needs_clflush_after)
-		intel_gtt_chipset_flush();
+		i915_gem_chipset_flush(dev);
 
 	return ret;
 }
@@ -3058,7 +3058,7 @@ i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj)
 		return;
 
 	i915_gem_clflush_object(obj);
-	intel_gtt_chipset_flush();
+	i915_gem_chipset_flush(obj->base.dev);
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
@@ -3959,7 +3959,7 @@ i915_gem_init_hw(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	int ret;
 
-	if (!intel_enable_gtt())
+	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
 		return -EIO;
 
 	if (IS_HASWELL(dev) && (I915_READ(0x120010) == 1))
@@ -4294,7 +4294,7 @@ void i915_gem_detach_phys_object(struct drm_device *dev,
 			page_cache_release(page);
 		}
 	}
-	intel_gtt_chipset_flush();
+	i915_gem_chipset_flush(dev);
 
 	obj->phys_obj->cur_obj = NULL;
 	obj->phys_obj = NULL;
@@ -4381,7 +4381,7 @@ i915_gem_phys_pwrite(struct drm_device *dev,
 			return -EFAULT;
 	}
 
-	intel_gtt_chipset_flush();
+	i915_gem_chipset_flush(dev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 91d43d5c4526..d80e9dd00c48 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -672,7 +672,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 	}
 
 	if (flush_domains & I915_GEM_DOMAIN_CPU)
-		intel_gtt_chipset_flush();
+		i915_gem_chipset_flush(ring->dev);
 
 	if (flush_domains & I915_GEM_DOMAIN_GTT)
 		wmb();
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 06202fd6dbdd..e74be0c2c6a5 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -262,26 +262,6 @@ void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
 			       obj->base.size >> PAGE_SHIFT);
 }
 
-/* XXX kill agp_type! */
-static unsigned int cache_level_to_agp_type(struct drm_device *dev,
-					    enum i915_cache_level cache_level)
-{
-	switch (cache_level) {
-	case I915_CACHE_LLC_MLC:
-		/* Older chipsets do not have this extra level of CPU
-		 * cacheing, so fallthrough and request the PTE simply
-		 * as cached.
-		 */
-		if (INTEL_INFO(dev)->gen >= 6 && !IS_HASWELL(dev))
-			return AGP_USER_CACHED_MEMORY_LLC_MLC;
-	case I915_CACHE_LLC:
-		return AGP_USER_CACHED_MEMORY;
-	default:
-	case I915_CACHE_NONE:
-		return AGP_USER_MEMORY;
-	}
-}
-
 static bool do_idling(struct drm_i915_private *dev_priv)
 {
 	bool ret = dev_priv->mm.interruptible;
@@ -304,13 +284,38 @@ static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible)
 		dev_priv->mm.interruptible = interruptible;
 }
 
+
+static void i915_ggtt_clear_range(struct drm_device *dev,
+				 unsigned first_entry,
+				 unsigned num_entries)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	gtt_pte_t scratch_pte;
+	volatile void __iomem *gtt_base = dev_priv->mm.gtt->gtt + first_entry;
+	const int max_entries = dev_priv->mm.gtt->gtt_total_entries - first_entry;
+
+	if (INTEL_INFO(dev)->gen < 6) {
+		intel_gtt_clear_range(first_entry, num_entries);
+		return;
+	}
+
+	if (WARN(num_entries > max_entries,
+		 "First entry = %d; Num entries = %d (max=%d)\n",
+		 first_entry, num_entries, max_entries))
+		num_entries = max_entries;
+
+	scratch_pte = pte_encode(dev, dev_priv->mm.gtt->scratch_page_dma, I915_CACHE_LLC);
+	memset_io(gtt_base, scratch_pte, num_entries * sizeof(scratch_pte));
+	readl(gtt_base);
+}
+
 void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
 
 	/* First fill our portion of the GTT with scratch pages */
-	intel_gtt_clear_range(dev_priv->mm.gtt_start / PAGE_SIZE,
+	i915_ggtt_clear_range(dev, dev_priv->mm.gtt_start / PAGE_SIZE,
 			      (dev_priv->mm.gtt_end - dev_priv->mm.gtt_start) / PAGE_SIZE);
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
@@ -318,7 +323,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 		i915_gem_gtt_bind_object(obj, obj->cache_level);
 	}
 
-	intel_gtt_chipset_flush();
+	i915_gem_chipset_flush(dev);
 }
 
 int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
@@ -334,21 +339,69 @@ int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
+/*
+ * Binds an object into the global gtt with the specified cache level. The object
+ * will be accessible to the GPU via commands whose operands reference offsets
+ * within the global GTT as well as accessible by the GPU through the GMADR
+ * mapped BAR (dev_priv->mm.gtt->gtt).
+ */
+static void gen6_ggtt_bind_object(struct drm_i915_gem_object *obj,
+				  enum i915_cache_level level)
+{
+	struct drm_device *dev = obj->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct sg_table *st = obj->pages;
+	struct scatterlist *sg = st->sgl;
+	const int first_entry = obj->gtt_space->start >> PAGE_SHIFT;
+	const int max_entries = dev_priv->mm.gtt->gtt_total_entries - first_entry;
+	gtt_pte_t __iomem *gtt_entries = dev_priv->mm.gtt->gtt + first_entry;
+	int unused, i = 0;
+	unsigned int len, m = 0;
+	dma_addr_t addr;
+
+	for_each_sg(st->sgl, sg, st->nents, unused) {
+		len = sg_dma_len(sg) >> PAGE_SHIFT;
+		for (m = 0; m < len; m++) {
+			addr = sg_dma_address(sg) + (m << PAGE_SHIFT);
+			gtt_entries[i] = pte_encode(dev, addr, level);
+			i++;
+		}
+	}
+
+	BUG_ON(i > max_entries);
+	BUG_ON(i != obj->base.size / PAGE_SIZE);
+
+	/* XXX: This serves as a posting read to make sure that the PTE has
+	 * actually been updated. There is some concern that even though
+	 * registers and PTEs are within the same BAR that they are potentially
+	 * of NUMA access patterns. Therefore, even with the way we assume
+	 * hardware should work, we must keep this posting read for paranoia.
+	 */
+	if (i != 0)
+		WARN_ON(readl(&gtt_entries[i-1]) != pte_encode(dev, addr, level));
+}
+
 void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj,
 			      enum i915_cache_level cache_level)
 {
 	struct drm_device *dev = obj->base.dev;
-	unsigned int agp_type = cache_level_to_agp_type(dev, cache_level);
+	if (INTEL_INFO(dev)->gen < 6) {
+		unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+			AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+		intel_gtt_insert_sg_entries(obj->pages,
+					    obj->gtt_space->start >> PAGE_SHIFT,
+					    flags);
+	} else {
+		gen6_ggtt_bind_object(obj, cache_level);
+	}
 
-	intel_gtt_insert_sg_entries(obj->pages,
-				    obj->gtt_space->start >> PAGE_SHIFT,
-				    agp_type);
 	obj->has_global_gtt_mapping = 1;
 }
 
 void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
 {
-	intel_gtt_clear_range(obj->gtt_space->start >> PAGE_SHIFT,
+	i915_ggtt_clear_range(obj->base.dev,
+			      obj->gtt_space->start >> PAGE_SHIFT,
 			      obj->base.size >> PAGE_SHIFT);
 
 	obj->has_global_gtt_mapping = 0;
@@ -406,5 +459,153 @@ void i915_gem_init_global_gtt(struct drm_device *dev,
 	dev_priv->mm.mappable_gtt_total = min(end, mappable_end) - start;
 
 	/* ... but ensure that we clear the entire range. */
-	intel_gtt_clear_range(start / PAGE_SIZE, (end-start) / PAGE_SIZE);
+	i915_ggtt_clear_range(dev, start / PAGE_SIZE, (end-start) / PAGE_SIZE);
+}
+
+static int setup_scratch_page(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct page *page;
+	dma_addr_t dma_addr;
+
+	page = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO);
+	if (page == NULL)
+		return -ENOMEM;
+	get_page(page);
+	set_pages_uc(page, 1);
+
+#ifdef CONFIG_INTEL_IOMMU
+	dma_addr = pci_map_page(dev->pdev, page, 0, PAGE_SIZE,
+				PCI_DMA_BIDIRECTIONAL);
+	if (pci_dma_mapping_error(dev->pdev, dma_addr))
+		return -EINVAL;
+#else
+	dma_addr = page_to_phys(page);
+#endif
+	dev_priv->mm.gtt->scratch_page = page;
+	dev_priv->mm.gtt->scratch_page_dma = dma_addr;
+
+	return 0;
+}
+
+static void teardown_scratch_page(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	set_pages_wb(dev_priv->mm.gtt->scratch_page, 1);
+	pci_unmap_page(dev->pdev, dev_priv->mm.gtt->scratch_page_dma,
+		       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+	put_page(dev_priv->mm.gtt->scratch_page);
+	__free_page(dev_priv->mm.gtt->scratch_page);
+}
+
+static inline unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
+{
+	snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
+	snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
+	return snb_gmch_ctl << 20;
+}
+
+static inline unsigned int gen6_get_stolen_size(u16 snb_gmch_ctl)
+{
+	snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT;
+	snb_gmch_ctl &= SNB_GMCH_GMS_MASK;
+	return snb_gmch_ctl << 25; /* 32 MB units */
+}
+
+int i915_gem_gtt_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	phys_addr_t gtt_bus_addr;
+	u16 snb_gmch_ctl;
+	u32 tmp;
+	int ret;
+
+	/* On modern platforms we need not worry ourself with the legacy
+	 * hostbridge query stuff. Skip it entirely
+	 */
+	if (INTEL_INFO(dev)->gen < 6) {
+		ret = intel_gmch_probe(dev_priv->bridge_dev, dev->pdev, NULL);
+		if (!ret) {
+			DRM_ERROR("failed to set up gmch\n");
+			return -EIO;
+		}
+
+		dev_priv->mm.gtt = intel_gtt_get();
+		if (!dev_priv->mm.gtt) {
+			DRM_ERROR("Failed to initialize GTT\n");
+			intel_gmch_remove();
+			return -ENODEV;
+		}
+		return 0;
+	}
+
+	dev_priv->mm.gtt = kzalloc(sizeof(*dev_priv->mm.gtt), GFP_KERNEL);
+	if (!dev_priv->mm.gtt)
+		return -ENOMEM;
+
+	if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(40)))
+		pci_set_consistent_dma_mask(dev->pdev, DMA_BIT_MASK(40));
+
+	pci_read_config_dword(dev->pdev, PCI_BASE_ADDRESS_0, &tmp);
+	/* For GEN6+ the PTEs for the ggtt live at 2MB + BAR0 */
+	gtt_bus_addr = (tmp & PCI_BASE_ADDRESS_MEM_MASK) + (2<<20);
+
+	pci_read_config_dword(dev->pdev, PCI_BASE_ADDRESS_2, &tmp);
+	dev_priv->mm.gtt->gma_bus_addr = tmp & PCI_BASE_ADDRESS_MEM_MASK;
+
+	/* i9xx_setup */
+	pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
+	dev_priv->mm.gtt->gtt_total_entries =
+		gen6_get_total_gtt_size(snb_gmch_ctl) / sizeof(gtt_pte_t);
+	dev_priv->mm.gtt->stolen_size = gen6_get_stolen_size(snb_gmch_ctl);
+
+	dev_priv->mm.gtt->gtt_mappable_entries = pci_resource_len(dev->pdev, 2) >> PAGE_SHIFT;
+	/* 64/512MB is the current min/max we actually know of, but this is just a
+	 * coarse sanity check.
+	 */
+	if ((dev_priv->mm.gtt->gtt_mappable_entries >> 8) < 64 ||
+	    dev_priv->mm.gtt->gtt_mappable_entries > dev_priv->mm.gtt->gtt_total_entries) {
+		DRM_ERROR("Unknown GMADR entries (%d)\n",
+			  dev_priv->mm.gtt->gtt_mappable_entries);
+		ret = -ENXIO;
+		goto err_out;
+	}
+
+	ret = setup_scratch_page(dev);
+	if (ret) {
+		DRM_ERROR("Scratch setup failed\n");
+		goto err_out;
+	}
+
+	dev_priv->mm.gtt->gtt = ioremap(gtt_bus_addr,
+					dev_priv->mm.gtt->gtt_total_entries * sizeof(gtt_pte_t));
+	if (!dev_priv->mm.gtt->gtt) {
+		DRM_ERROR("Failed to map the gtt page table\n");
+		teardown_scratch_page(dev);
+		ret = -ENOMEM;
+		goto err_out;
+	}
+
+	/* GMADR is the PCI aperture used by SW to access tiled GFX surfaces in a linear fashion. */
+	DRM_INFO("Memory Usable by graphics device = %dK\n", dev_priv->mm.gtt->gtt_total_entries >> 10);
+	DRM_DEBUG_DRIVER("GMADR size = %dM\n", dev_priv->mm.gtt->gtt_mappable_entries >> 8);
+	DRM_DEBUG_DRIVER("GTT stolen size = %dM\n", dev_priv->mm.gtt->stolen_size >> 20);
+
+	return 0;
+
+err_out:
+	kfree(dev_priv->mm.gtt);
+	if (INTEL_INFO(dev)->gen < 6)
+		intel_gmch_remove();
+	return ret;
+}
+
+void i915_gem_gtt_fini(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	iounmap(dev_priv->mm.gtt->gtt);
+	teardown_scratch_page(dev);
+	if (INTEL_INFO(dev)->gen < 6)
+		intel_gmch_remove();
+	kfree(dev_priv->mm.gtt);
 }
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0866ac3d0a3f..449403f60e4f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -41,6 +41,12 @@
  */
 #define INTEL_GMCH_CTRL		0x52
 #define INTEL_GMCH_VGA_DISABLE  (1 << 1)
+#define SNB_GMCH_CTRL		0x50
+#define    SNB_GMCH_GGMS_SHIFT	8 /* GTT Graphics Memory Size */
+#define    SNB_GMCH_GGMS_MASK	0x3
+#define    SNB_GMCH_GMS_SHIFT   3 /* Graphics Mode Select */
+#define    SNB_GMCH_GMS_MASK    0x1f
+
 
 /* PCI config space */
 
diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h
index 2e37e9f02e71..94e8f2c7f9e1 100644
--- a/include/drm/intel-gtt.h
+++ b/include/drm/intel-gtt.h
@@ -3,7 +3,7 @@
 #ifndef _DRM_INTEL_GTT_H
 #define	_DRM_INTEL_GTT_H
 
-const struct intel_gtt {
+struct intel_gtt {
 	/* Size of memory reserved for graphics by the BIOS */
 	unsigned int stolen_size;
 	/* Total number of gtt entries. */
@@ -17,6 +17,7 @@ const struct intel_gtt {
 	unsigned int do_idle_maps : 1;
 	/* Share the scratch page dma with ppgtts. */
 	dma_addr_t scratch_page_dma;
+	struct page *scratch_page;
 	/* for ppgtt PDE access */
 	u32 __iomem *gtt;
 	/* needed for ioremap in drm/i915 */
-- 
cgit v1.2.3-55-g7522


From 009946f89b7795699848a922fc2f7804390017d9 Mon Sep 17 00:00:00 2001
From: Ben Widawsky
Date: Sun, 4 Nov 2012 09:21:29 -0800
Subject: drm/i915: Kill off now unused gen6+ AGP code

v2: Accidently removed an ILK case in i9xx_setup (Nicely found by Chris)

CC: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by [v1] : Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/char/agp/intel-agp.h |  91 -------------
 drivers/char/agp/intel-gtt.c | 318 ++-----------------------------------------
 include/drm/intel-gtt.h      |   4 -
 3 files changed, 11 insertions(+), 402 deletions(-)

(limited to 'include')

diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h
index 6ec0fff79bc2..1042c1b90376 100644
--- a/drivers/char/agp/intel-agp.h
+++ b/drivers/char/agp/intel-agp.h
@@ -62,12 +62,6 @@
 #define I810_PTE_LOCAL		0x00000002
 #define I810_PTE_VALID		0x00000001
 #define I830_PTE_SYSTEM_CACHED  0x00000006
-/* GT PTE cache control fields */
-#define GEN6_PTE_UNCACHED	0x00000002
-#define HSW_PTE_UNCACHED	0x00000000
-#define GEN6_PTE_LLC		0x00000004
-#define GEN6_PTE_LLC_MLC	0x00000006
-#define GEN6_PTE_GFDT		0x00000008
 
 #define I810_SMRAM_MISCC	0x70
 #define I810_GFX_MEM_WIN_SIZE	0x00010000
@@ -97,7 +91,6 @@
 #define G4x_GMCH_SIZE_VT_2M	(G4x_GMCH_SIZE_2M | G4x_GMCH_SIZE_VT_EN)
 
 #define GFX_FLSH_CNTL		0x2170 /* 915+ */
-#define GFX_FLSH_CNTL_VLV	0x101008
 
 #define I810_DRAM_CTL		0x3000
 #define I810_DRAM_ROW_0		0x00000001
@@ -148,29 +141,6 @@
 #define INTEL_I7505_AGPCTRL	0x70
 #define INTEL_I7505_MCHCFG	0x50
 
-#define SNB_GMCH_CTRL	0x50
-#define SNB_GMCH_GMS_STOLEN_MASK	0xF8
-#define SNB_GMCH_GMS_STOLEN_32M		(1 << 3)
-#define SNB_GMCH_GMS_STOLEN_64M		(2 << 3)
-#define SNB_GMCH_GMS_STOLEN_96M		(3 << 3)
-#define SNB_GMCH_GMS_STOLEN_128M	(4 << 3)
-#define SNB_GMCH_GMS_STOLEN_160M	(5 << 3)
-#define SNB_GMCH_GMS_STOLEN_192M	(6 << 3)
-#define SNB_GMCH_GMS_STOLEN_224M	(7 << 3)
-#define SNB_GMCH_GMS_STOLEN_256M	(8 << 3)
-#define SNB_GMCH_GMS_STOLEN_288M	(9 << 3)
-#define SNB_GMCH_GMS_STOLEN_320M	(0xa << 3)
-#define SNB_GMCH_GMS_STOLEN_352M	(0xb << 3)
-#define SNB_GMCH_GMS_STOLEN_384M	(0xc << 3)
-#define SNB_GMCH_GMS_STOLEN_416M	(0xd << 3)
-#define SNB_GMCH_GMS_STOLEN_448M	(0xe << 3)
-#define SNB_GMCH_GMS_STOLEN_480M	(0xf << 3)
-#define SNB_GMCH_GMS_STOLEN_512M	(0x10 << 3)
-#define SNB_GTT_SIZE_0M			(0 << 8)
-#define SNB_GTT_SIZE_1M			(1 << 8)
-#define SNB_GTT_SIZE_2M			(2 << 8)
-#define SNB_GTT_SIZE_MASK		(3 << 8)
-
 /* pci devices ids */
 #define PCI_DEVICE_ID_INTEL_E7221_HB	0x2588
 #define PCI_DEVICE_ID_INTEL_E7221_IG	0x258a
@@ -219,66 +189,5 @@
 #define PCI_DEVICE_ID_INTEL_IRONLAKE_MA_HB	    0x0062
 #define PCI_DEVICE_ID_INTEL_IRONLAKE_MC2_HB    0x006a
 #define PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG	    0x0046
-#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB		0x0100  /* Desktop */
-#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT1_IG		0x0102
-#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT2_IG		0x0112
-#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT2_PLUS_IG	0x0122
-#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB		0x0104  /* Mobile */
-#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT1_IG	0x0106
-#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT2_IG	0x0116
-#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT2_PLUS_IG	0x0126
-#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_S_HB		0x0108  /* Server */
-#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_S_IG		0x010A
-#define PCI_DEVICE_ID_INTEL_IVYBRIDGE_HB		0x0150  /* Desktop */
-#define PCI_DEVICE_ID_INTEL_IVYBRIDGE_GT1_IG		0x0152
-#define PCI_DEVICE_ID_INTEL_IVYBRIDGE_GT2_IG		0x0162
-#define PCI_DEVICE_ID_INTEL_IVYBRIDGE_M_HB		0x0154  /* Mobile */
-#define PCI_DEVICE_ID_INTEL_IVYBRIDGE_M_GT1_IG		0x0156
-#define PCI_DEVICE_ID_INTEL_IVYBRIDGE_M_GT2_IG		0x0166
-#define PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_HB		0x0158  /* Server */
-#define PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_GT1_IG		0x015A
-#define PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_GT2_IG		0x016A
-#define PCI_DEVICE_ID_INTEL_VALLEYVIEW_HB		0x0F00 /* VLV1 */
-#define PCI_DEVICE_ID_INTEL_VALLEYVIEW_IG		0x0F30
-#define PCI_DEVICE_ID_INTEL_HASWELL_HB			0x0400 /* Desktop */
-#define PCI_DEVICE_ID_INTEL_HASWELL_D_GT1_IG		0x0402
-#define PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_IG		0x0412
-#define PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_PLUS_IG	0x0422
-#define PCI_DEVICE_ID_INTEL_HASWELL_M_HB		0x0404 /* Mobile */
-#define PCI_DEVICE_ID_INTEL_HASWELL_M_GT1_IG		0x0406
-#define PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_IG		0x0416
-#define PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_PLUS_IG	0x0426
-#define PCI_DEVICE_ID_INTEL_HASWELL_S_HB		0x0408 /* Server */
-#define PCI_DEVICE_ID_INTEL_HASWELL_S_GT1_IG		0x040a
-#define PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_IG		0x041a
-#define PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_PLUS_IG	0x042a
-#define PCI_DEVICE_ID_INTEL_HASWELL_E_HB		0x0c04
-#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT1_IG	0x0C02
-#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_IG	0x0C12
-#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_PLUS_IG	0x0C22
-#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT1_IG	0x0C06
-#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_IG	0x0C16
-#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_PLUS_IG	0x0C26
-#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT1_IG	0x0C0A
-#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_IG	0x0C1A
-#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_PLUS_IG	0x0C2A
-#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT1_IG	0x0A02
-#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_IG	0x0A12
-#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_PLUS_IG	0x0A22
-#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT1_IG	0x0A06
-#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_IG	0x0A16
-#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_PLUS_IG	0x0A26
-#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT1_IG	0x0A0A
-#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_IG	0x0A1A
-#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_PLUS_IG	0x0A2A
-#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT1_IG	0x0D12
-#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_IG	0x0D22
-#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_PLUS_IG	0x0D32
-#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT1_IG	0x0D16
-#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_IG	0x0D26
-#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_PLUS_IG	0x0D36
-#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT1_IG	0x0D1A
-#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_IG	0x0D2A
-#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_PLUS_IG	0x0D3A
 
 #endif
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 4dfbb80f0fd5..dbd901e94ea6 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -367,62 +367,6 @@ static unsigned int intel_gtt_stolen_size(void)
 			stolen_size = 0;
 			break;
 		}
-	} else if (INTEL_GTT_GEN == 6) {
-		/*
-		 * SandyBridge has new memory control reg at 0x50.w
-		 */
-		u16 snb_gmch_ctl;
-		pci_read_config_word(intel_private.pcidev, SNB_GMCH_CTRL, &snb_gmch_ctl);
-		switch (snb_gmch_ctl & SNB_GMCH_GMS_STOLEN_MASK) {
-		case SNB_GMCH_GMS_STOLEN_32M:
-			stolen_size = MB(32);
-			break;
-		case SNB_GMCH_GMS_STOLEN_64M:
-			stolen_size = MB(64);
-			break;
-		case SNB_GMCH_GMS_STOLEN_96M:
-			stolen_size = MB(96);
-			break;
-		case SNB_GMCH_GMS_STOLEN_128M:
-			stolen_size = MB(128);
-			break;
-		case SNB_GMCH_GMS_STOLEN_160M:
-			stolen_size = MB(160);
-			break;
-		case SNB_GMCH_GMS_STOLEN_192M:
-			stolen_size = MB(192);
-			break;
-		case SNB_GMCH_GMS_STOLEN_224M:
-			stolen_size = MB(224);
-			break;
-		case SNB_GMCH_GMS_STOLEN_256M:
-			stolen_size = MB(256);
-			break;
-		case SNB_GMCH_GMS_STOLEN_288M:
-			stolen_size = MB(288);
-			break;
-		case SNB_GMCH_GMS_STOLEN_320M:
-			stolen_size = MB(320);
-			break;
-		case SNB_GMCH_GMS_STOLEN_352M:
-			stolen_size = MB(352);
-			break;
-		case SNB_GMCH_GMS_STOLEN_384M:
-			stolen_size = MB(384);
-			break;
-		case SNB_GMCH_GMS_STOLEN_416M:
-			stolen_size = MB(416);
-			break;
-		case SNB_GMCH_GMS_STOLEN_448M:
-			stolen_size = MB(448);
-			break;
-		case SNB_GMCH_GMS_STOLEN_480M:
-			stolen_size = MB(480);
-			break;
-		case SNB_GMCH_GMS_STOLEN_512M:
-			stolen_size = MB(512);
-			break;
-		}
 	} else {
 		switch (gmch_ctrl & I855_GMCH_GMS_MASK) {
 		case I855_GMCH_GMS_STOLEN_1M:
@@ -556,29 +500,9 @@ static unsigned int i965_gtt_total_entries(void)
 
 static unsigned int intel_gtt_total_entries(void)
 {
-	int size;
-
 	if (IS_G33 || INTEL_GTT_GEN == 4 || INTEL_GTT_GEN == 5)
 		return i965_gtt_total_entries();
-	else if (INTEL_GTT_GEN == 6) {
-		u16 snb_gmch_ctl;
-
-		pci_read_config_word(intel_private.pcidev, SNB_GMCH_CTRL, &snb_gmch_ctl);
-		switch (snb_gmch_ctl & SNB_GTT_SIZE_MASK) {
-		default:
-		case SNB_GTT_SIZE_0M:
-			printk(KERN_ERR "Bad GTT size mask: 0x%04x.\n", snb_gmch_ctl);
-			size = MB(0);
-			break;
-		case SNB_GTT_SIZE_1M:
-			size = MB(1);
-			break;
-		case SNB_GTT_SIZE_2M:
-			size = MB(2);
-			break;
-		}
-		return size/4;
-	} else {
+	else {
 		/* On previous hardware, the GTT size was just what was
 		 * required to map the aperture.
 		 */
@@ -778,9 +702,6 @@ bool intel_enable_gtt(void)
 {
 	u8 __iomem *reg;
 
-	if (INTEL_GTT_GEN >= 6)
-	    return true;
-
 	if (INTEL_GTT_GEN == 2) {
 		u16 gmch_ctrl;
 
@@ -1149,85 +1070,6 @@ static void i965_write_entry(dma_addr_t addr,
 	writel(addr | pte_flags, intel_private.gtt + entry);
 }
 
-static bool gen6_check_flags(unsigned int flags)
-{
-	return true;
-}
-
-static void haswell_write_entry(dma_addr_t addr, unsigned int entry,
-				unsigned int flags)
-{
-	unsigned int type_mask = flags & ~AGP_USER_CACHED_MEMORY_GFDT;
-	unsigned int gfdt = flags & AGP_USER_CACHED_MEMORY_GFDT;
-	u32 pte_flags;
-
-	if (type_mask == AGP_USER_MEMORY)
-		pte_flags = HSW_PTE_UNCACHED | I810_PTE_VALID;
-	else if (type_mask == AGP_USER_CACHED_MEMORY_LLC_MLC) {
-		pte_flags = GEN6_PTE_LLC_MLC | I810_PTE_VALID;
-		if (gfdt)
-			pte_flags |= GEN6_PTE_GFDT;
-	} else { /* set 'normal'/'cached' to LLC by default */
-		pte_flags = GEN6_PTE_LLC | I810_PTE_VALID;
-		if (gfdt)
-			pte_flags |= GEN6_PTE_GFDT;
-	}
-
-	/* gen6 has bit11-4 for physical addr bit39-32 */
-	addr |= (addr >> 28) & 0xff0;
-	writel(addr | pte_flags, intel_private.gtt + entry);
-}
-
-static void gen6_write_entry(dma_addr_t addr, unsigned int entry,
-			     unsigned int flags)
-{
-	unsigned int type_mask = flags & ~AGP_USER_CACHED_MEMORY_GFDT;
-	unsigned int gfdt = flags & AGP_USER_CACHED_MEMORY_GFDT;
-	u32 pte_flags;
-
-	if (type_mask == AGP_USER_MEMORY)
-		pte_flags = GEN6_PTE_UNCACHED | I810_PTE_VALID;
-	else if (type_mask == AGP_USER_CACHED_MEMORY_LLC_MLC) {
-		pte_flags = GEN6_PTE_LLC_MLC | I810_PTE_VALID;
-		if (gfdt)
-			pte_flags |= GEN6_PTE_GFDT;
-	} else { /* set 'normal'/'cached' to LLC by default */
-		pte_flags = GEN6_PTE_LLC | I810_PTE_VALID;
-		if (gfdt)
-			pte_flags |= GEN6_PTE_GFDT;
-	}
-
-	/* gen6 has bit11-4 for physical addr bit39-32 */
-	addr |= (addr >> 28) & 0xff0;
-	writel(addr | pte_flags, intel_private.gtt + entry);
-}
-
-static void valleyview_write_entry(dma_addr_t addr, unsigned int entry,
-				   unsigned int flags)
-{
-	unsigned int type_mask = flags & ~AGP_USER_CACHED_MEMORY_GFDT;
-	unsigned int gfdt = flags & AGP_USER_CACHED_MEMORY_GFDT;
-	u32 pte_flags;
-
-	if (type_mask == AGP_USER_MEMORY)
-		pte_flags = GEN6_PTE_UNCACHED | I810_PTE_VALID;
-	else {
-		pte_flags = GEN6_PTE_LLC | I810_PTE_VALID;
-		if (gfdt)
-			pte_flags |= GEN6_PTE_GFDT;
-	}
-
-	/* gen6 has bit11-4 for physical addr bit39-32 */
-	addr |= (addr >> 28) & 0xff0;
-	writel(addr | pte_flags, intel_private.gtt + entry);
-
-	writel(1, intel_private.registers + GFX_FLSH_CNTL_VLV);
-}
-
-static void gen6_cleanup(void)
-{
-}
-
 /* Certain Gen5 chipsets require require idling the GPU before
  * unmapping anything from the GTT when VT-d is enabled.
  */
@@ -1249,41 +1091,29 @@ static inline int needs_idle_maps(void)
 
 static int i9xx_setup(void)
 {
-	u32 reg_addr;
+	u32 reg_addr, gtt_addr;
 	int size = KB(512);
 
 	pci_read_config_dword(intel_private.pcidev, I915_MMADDR, &reg_addr);
 
 	reg_addr &= 0xfff80000;
 
-	if (INTEL_GTT_GEN >= 7)
-		size = MB(2);
-
 	intel_private.registers = ioremap(reg_addr, size);
 	if (!intel_private.registers)
 		return -ENOMEM;
 
-	if (INTEL_GTT_GEN == 3) {
-		u32 gtt_addr;
-
+	switch (INTEL_GTT_GEN) {
+	case 3:
 		pci_read_config_dword(intel_private.pcidev,
 				      I915_PTEADDR, &gtt_addr);
 		intel_private.gtt_bus_addr = gtt_addr;
-	} else {
-		u32 gtt_offset;
-
-		switch (INTEL_GTT_GEN) {
-		case 5:
-		case 6:
-		case 7:
-			gtt_offset = MB(2);
-			break;
-		case 4:
-		default:
-			gtt_offset =  KB(512);
-			break;
-		}
-		intel_private.gtt_bus_addr = reg_addr + gtt_offset;
+		break;
+	case 5:
+		intel_private.gtt_bus_addr = reg_addr + MB(2);
+		break;
+	default:
+		intel_private.gtt_bus_addr = reg_addr + KB(512);
+		break;
 	}
 
 	if (needs_idle_maps())
@@ -1395,32 +1225,6 @@ static const struct intel_gtt_driver ironlake_gtt_driver = {
 	.check_flags = i830_check_flags,
 	.chipset_flush = i9xx_chipset_flush,
 };
-static const struct intel_gtt_driver sandybridge_gtt_driver = {
-	.gen = 6,
-	.setup = i9xx_setup,
-	.cleanup = gen6_cleanup,
-	.write_entry = gen6_write_entry,
-	.dma_mask_size = 40,
-	.check_flags = gen6_check_flags,
-	.chipset_flush = i9xx_chipset_flush,
-};
-static const struct intel_gtt_driver haswell_gtt_driver = {
-	.gen = 6,
-	.setup = i9xx_setup,
-	.cleanup = gen6_cleanup,
-	.write_entry = haswell_write_entry,
-	.dma_mask_size = 40,
-	.check_flags = gen6_check_flags,
-	.chipset_flush = i9xx_chipset_flush,
-};
-static const struct intel_gtt_driver valleyview_gtt_driver = {
-	.gen = 7,
-	.setup = i9xx_setup,
-	.cleanup = gen6_cleanup,
-	.write_entry = valleyview_write_entry,
-	.dma_mask_size = 40,
-	.check_flags = gen6_check_flags,
-};
 
 /* Table to describe Intel GMCH and AGP/PCIE GART drivers.  At least one of
  * driver and gmch_driver must be non-null, and find_gmch will determine
@@ -1501,106 +1305,6 @@ static const struct intel_gtt_driver_description {
 	    "HD Graphics", &ironlake_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG,
 	    "HD Graphics", &ironlake_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT1_IG,
-	    "Sandybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT2_IG,
-	    "Sandybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT2_PLUS_IG,
-	    "Sandybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT1_IG,
-	    "Sandybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT2_IG,
-	    "Sandybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT2_PLUS_IG,
-	    "Sandybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_SANDYBRIDGE_S_IG,
-	    "Sandybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_IVYBRIDGE_GT1_IG,
-	    "Ivybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_IVYBRIDGE_GT2_IG,
-	    "Ivybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_IVYBRIDGE_M_GT1_IG,
-	    "Ivybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_IVYBRIDGE_M_GT2_IG,
-	    "Ivybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_GT1_IG,
-	    "Ivybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_GT2_IG,
-	    "Ivybridge", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_VALLEYVIEW_IG,
-	    "ValleyView", &valleyview_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT1_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_IG,
-	    "Haswell", &haswell_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_PLUS_IG,
-	    "Haswell", &haswell_gtt_driver },
 	{ 0, NULL, NULL }
 };
 
diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h
index 94e8f2c7f9e1..6eb76a1f11ab 100644
--- a/include/drm/intel-gtt.h
+++ b/include/drm/intel-gtt.h
@@ -40,10 +40,6 @@ void intel_gtt_clear_range(unsigned int first_entry, unsigned int num_entries);
 #define AGP_DCACHE_MEMORY	1
 #define AGP_PHYS_MEMORY		2
 
-/* New caching attributes for gen6/sandybridge */
-#define AGP_USER_CACHED_MEMORY_LLC_MLC (AGP_USER_TYPES + 2)
-#define AGP_USER_UNCACHED_MEMORY (AGP_USER_TYPES + 4)
-
 /* flag for GFDT type */
 #define AGP_USER_CACHED_MEMORY_GFDT (1 << 3)
 
-- 
cgit v1.2.3-55-g7522


From 90a38d999739f35f4fc925c875e6ee518546b66c Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven
Date: Mon, 15 Oct 2012 22:44:45 +0200
Subject: mfd: Remove Unicode Byte Order Marks from da9055

Older gcc (< 4.4) doesn't like files starting with Unicode BOMs:

include/linux/mfd/da9055/core.h:1: error: stray ‘\357’ in program
include/linux/mfd/da9055/core.h:1: error: stray ‘\273’ in program
include/linux/mfd/da9055/core.h:1: error: stray ‘\277’ in program
include/linux/mfd/da9055/pdata.h:1: error: stray ‘\357’ in program
include/linux/mfd/da9055/pdata.h:1: error: stray ‘\273’ in program
include/linux/mfd/da9055/pdata.h:1: error: stray ‘\277’ in program
include/linux/mfd/da9055/reg.h:1: error: stray ‘\357’ in program
include/linux/mfd/da9055/reg.h:1: error: stray ‘\273’ in program
include/linux/mfd/da9055/reg.h:1: error: stray ‘\277’ in program

Remove the BOMs, the rest of the files is plain ASCII anyway.

Output of "file" before:

include/linux/mfd/da9055/core.h:  UTF-8 Unicode (with BOM) C program text
include/linux/mfd/da9055/pdata.h: UTF-8 Unicode (with BOM) C program text
include/linux/mfd/da9055/reg.h:   UTF-8 Unicode (with BOM) C program text

Output of "file" after:

include/linux/mfd/da9055/core.h:  ASCII C program text
include/linux/mfd/da9055/pdata.h: ASCII C program text
include/linux/mfd/da9055/reg.h:   ASCII C program text

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/linux/mfd/da9055/core.h  | 2 +-
 include/linux/mfd/da9055/pdata.h | 2 +-
 include/linux/mfd/da9055/reg.h   | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/da9055/core.h b/include/linux/mfd/da9055/core.h
index c96ad682c59e..956afa445998 100644
--- a/include/linux/mfd/da9055/core.h
+++ b/include/linux/mfd/da9055/core.h
@@ -1,4 +1,4 @@
-/*
+/*
  * da9055 declarations for DA9055 PMICs.
  *
  * Copyright(c) 2012 Dialog Semiconductor Ltd.
diff --git a/include/linux/mfd/da9055/pdata.h b/include/linux/mfd/da9055/pdata.h
index 147293b4471d..b9b204edb4e9 100644
--- a/include/linux/mfd/da9055/pdata.h
+++ b/include/linux/mfd/da9055/pdata.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2012 Dialog Semiconductor Ltd.
+/* Copyright (C) 2012 Dialog Semiconductor Ltd.
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
diff --git a/include/linux/mfd/da9055/reg.h b/include/linux/mfd/da9055/reg.h
index df237ee54803..2b592e072dbf 100644
--- a/include/linux/mfd/da9055/reg.h
+++ b/include/linux/mfd/da9055/reg.h
@@ -1,4 +1,4 @@
-/*
+/*
  * DA9055 declarations for DA9055 PMICs.
  *
  * Copyright(c) 2012 Dialog Semiconductor Ltd.
-- 
cgit v1.2.3-55-g7522


From 2a91c9f781de209d420d751e43eb43ffe6934803 Mon Sep 17 00:00:00 2001
From: Amitkumar Karwar
Date: Fri, 9 Nov 2012 17:51:30 -0800
Subject: nl/cfg80211: advertise OBSS scan requirement

wpa_supplicant will do OBSS scan for drivers that implement
auth/assoc API. Drivers that implement nl80211 connect API
(rather than auth/assoc) may need wpa_supplicant to do this
as well.

Add a new feature flag to inform it (wpa_s) that a driver
needs wpa_supplicant to do OBSS scans.

Signed-off-by: Amitkumar Karwar <akarwar@marvell.com>
Signed-off-by: Bing Zhao <bzhao@marvell.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index cbd2d6bb907a..06ddc89f026c 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3057,6 +3057,9 @@ enum nl80211_ap_sme_features {
  * @NL80211_FEATURE_SCAN_FLUSH: Scan flush is supported
  * @NL80211_FEATURE_AP_SCAN: Support scanning using an AP vif
  * @NL80211_FEATURE_VIF_TXPOWER: The driver supports per-vif TX power setting
+ * @NL80211_FEATURE_NEED_OBSS_SCAN: The driver expects userspace to perform
+ *	OBSS scans and generate 20/40 BSS coex reports. This flag is used only
+ *	for drivers implementing the CONNECT API, for AUTH/ASSOC it is implied.
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -3069,6 +3072,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_SCAN_FLUSH			= 1 << 7,
 	NL80211_FEATURE_AP_SCAN				= 1 << 8,
 	NL80211_FEATURE_VIF_TXPOWER			= 1 << 9,
+	NL80211_FEATURE_NEED_OBSS_SCAN			= 1 << 10,
 };
 
 /**
-- 
cgit v1.2.3-55-g7522


From 9195bb8e381d81d5a315f911904cdf0cfcc919b8 Mon Sep 17 00:00:00 2001
From: Ansis Atteka
Date: Fri, 9 Nov 2012 17:11:31 -0800
Subject: ipv6: improve ipv6_find_hdr() to skip empty routing headers

This patch prepares ipv6_find_hdr() function so that it could be
able to skip routing headers, where segements_left is 0. This is
required to handle multiple routing header case correctly when
changing IPv6 addresses.

Signed-off-by: Ansis Atteka <aatteka@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
---
 include/net/ipv6.h      |  5 +++--
 net/ipv6/exthdrs_core.c | 36 ++++++++++++++++++++++++++++--------
 2 files changed, 31 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index b2f0cfb0a381..acbd8e034310 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -631,8 +631,9 @@ extern int			ipv6_skip_exthdr(const struct sk_buff *, int start,
 extern bool			ipv6_ext_hdr(u8 nexthdr);
 
 enum {
-	IP6_FH_F_FRAG	= (1 << 0),
-	IP6_FH_F_AUTH	= (1 << 1),
+	IP6_FH_F_FRAG		= (1 << 0),
+	IP6_FH_F_AUTH		= (1 << 1),
+	IP6_FH_F_SKIP_RH	= (1 << 2),
 };
 
 /* find specified header and get offset to it */
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 8ea253ad35b1..11b4e29c8452 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -132,9 +132,11 @@ EXPORT_SYMBOL(ipv6_skip_exthdr);
  * *offset is meaningless and fragment offset is stored in *fragoff if fragoff
  * isn't NULL.
  *
- * if flags is not NULL and it's a fragment, then the frag flag IP6_FH_F_FRAG
- * will be set. If it's an AH header, the IP6_FH_F_AUTH flag is set and
- * target < 0, then this function will stop at the AH header.
+ * if flags is not NULL and it's a fragment, then the frag flag
+ * IP6_FH_F_FRAG will be set. If it's an AH header, the
+ * IP6_FH_F_AUTH flag is set and target < 0, then this function will
+ * stop at the AH header. If IP6_FH_F_SKIP_RH flag was passed, then this
+ * function will skip all those routing headers, where segements_left was 0.
  */
 int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 		  int target, unsigned short *fragoff, int *flags)
@@ -142,6 +144,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 	unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
 	u8 nexthdr = ipv6_hdr(skb)->nexthdr;
 	unsigned int len;
+	bool found;
 
 	if (fragoff)
 		*fragoff = 0;
@@ -159,9 +162,10 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 	}
 	len = skb->len - start;
 
-	while (nexthdr != target) {
+	do {
 		struct ipv6_opt_hdr _hdr, *hp;
 		unsigned int hdrlen;
+		found = (nexthdr == target);
 
 		if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
 			if (target < 0)
@@ -172,6 +176,20 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
 		if (hp == NULL)
 			return -EBADMSG;
+
+		if (nexthdr == NEXTHDR_ROUTING) {
+			struct ipv6_rt_hdr _rh, *rh;
+
+			rh = skb_header_pointer(skb, start, sizeof(_rh),
+						&_rh);
+			if (rh == NULL)
+				return -EBADMSG;
+
+			if (flags && (*flags & IP6_FH_F_SKIP_RH) &&
+			    rh->segments_left == 0)
+				found = false;
+		}
+
 		if (nexthdr == NEXTHDR_FRAGMENT) {
 			unsigned short _frag_off;
 			__be16 *fp;
@@ -205,10 +223,12 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 		} else
 			hdrlen = ipv6_optlen(hp);
 
-		nexthdr = hp->nexthdr;
-		len -= hdrlen;
-		start += hdrlen;
-	}
+		if (!found) {
+			nexthdr = hp->nexthdr;
+			len -= hdrlen;
+			start += hdrlen;
+		}
+	} while (!found);
 
 	*offset = start;
 	return nexthdr;
-- 
cgit v1.2.3-55-g7522


From 89d16665d388837b30972081d97b814be26d68a2 Mon Sep 17 00:00:00 2001
From: Matt Fleming
Date: Fri, 9 Nov 2012 21:02:56 +0000
Subject: efivarfs: Use query_variable_info() to limit kmalloc()

We don't want someone who can write EFI variables to be able to
allocate arbitrarily large amounts of memory, so cap it to something
sensible like the amount of free space for EFI variables.

Acked-by: Jeremy Kerr <jeremy.kerr@canonical.com>
Cc: Matthew Garrett <mjg@redhat.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
 drivers/firmware/efivars.c | 43 ++++++++++++++++++++++++++++++++++---------
 include/linux/efi.h        |  1 +
 2 files changed, 35 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index 9ac934018bba..d6b8d2f628fa 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -694,28 +694,51 @@ static ssize_t efivarfs_file_write(struct file *file,
 	struct inode *inode = file->f_mapping->host;
 	unsigned long datasize = count - sizeof(attributes);
 	unsigned long newdatasize;
+	u64 storage_size, remaining_size, max_size;
 	ssize_t bytes = 0;
 
 	if (count < sizeof(attributes))
 		return -EINVAL;
 
-	data = kmalloc(datasize, GFP_KERNEL);
+	if (copy_from_user(&attributes, userbuf, sizeof(attributes)))
+		return -EFAULT;
 
-	if (!data)
-		return -ENOMEM;
+	if (attributes & ~(EFI_VARIABLE_MASK))
+		return -EINVAL;
 
 	efivars = var->efivars;
 
-	if (copy_from_user(&attributes, userbuf, sizeof(attributes))) {
-		bytes = -EFAULT;
-		goto out;
+	/*
+	 * Ensure that the user can't allocate arbitrarily large
+	 * amounts of memory. Pick a default size of 64K if
+	 * QueryVariableInfo() isn't supported by the firmware.
+	 */
+	spin_lock(&efivars->lock);
+
+	if (!efivars->ops->query_variable_info)
+		status = EFI_UNSUPPORTED;
+	else {
+		const struct efivar_operations *fops = efivars->ops;
+		status = fops->query_variable_info(attributes, &storage_size,
+						   &remaining_size, &max_size);
 	}
 
-	if (attributes & ~(EFI_VARIABLE_MASK)) {
-		bytes = -EINVAL;
-		goto out;
+	spin_unlock(&efivars->lock);
+
+	if (status != EFI_SUCCESS) {
+		if (status != EFI_UNSUPPORTED)
+			return efi_status_to_err(status);
+
+		remaining_size = 65536;
 	}
 
+	if (datasize > remaining_size)
+		return -ENOSPC;
+
+	data = kmalloc(datasize, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
 	if (copy_from_user(data, userbuf + sizeof(attributes), datasize)) {
 		bytes = -EFAULT;
 		goto out;
@@ -1709,6 +1732,8 @@ efivars_init(void)
 	ops.get_variable = efi.get_variable;
 	ops.set_variable = efi.set_variable;
 	ops.get_next_variable = efi.get_next_variable;
+	ops.query_variable_info = efi.query_variable_info;
+
 	error = register_efivars(&__efivars, &ops, efi_kobj);
 	if (error)
 		goto err_put;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 5e2308d9c6be..f80079cd84f4 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -646,6 +646,7 @@ struct efivar_operations {
 	efi_get_variable_t *get_variable;
 	efi_get_next_variable_t *get_next_variable;
 	efi_set_variable_t *set_variable;
+	efi_query_variable_info_t *query_variable_info;
 };
 
 struct efivars {
-- 
cgit v1.2.3-55-g7522


From 9f488ba8633fe77910ea0ba80ec762d9c34af1b6 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman
Date: Tue, 13 Nov 2012 10:46:33 -0800
Subject: IIO: fix build error in lp8788-charger.c

Turns out that consumer.h needs to include types.h on some platforms to
build properly (like powerpc).

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/iio/consumer.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h
index 126c0a9375f2..16c35ac045bd 100644
--- a/include/linux/iio/consumer.h
+++ b/include/linux/iio/consumer.h
@@ -9,6 +9,8 @@
  */
 #ifndef _IIO_INKERN_CONSUMER_H_
 #define _IIO_INKERN_CONSUMER_H_
+
+#include <linux/types.h>
 #include <linux/iio/types.h>
 
 struct iio_dev;
-- 
cgit v1.2.3-55-g7522


From ab7edb149c7548541ee588b8372c2041b6f1cbc8 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi
Date: Thu, 11 Oct 2012 13:55:32 +0200
Subject: mfd: twl6040: Convert to use regmap_irq

With regmap_irq it is possible to remove the twl6040-irq.c file and
simplify the code.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/Kconfig         |   4 +-
 drivers/mfd/Makefile        |   2 +-
 drivers/mfd/twl6040-core.c  |  55 ++++++++----
 drivers/mfd/twl6040-irq.c   | 205 --------------------------------------------
 include/linux/mfd/twl6040.h |  10 +--
 5 files changed, 48 insertions(+), 228 deletions(-)
 delete mode 100644 drivers/mfd/twl6040-irq.c

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 3f2187ae8c5d..34242cada125 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -321,10 +321,10 @@ config MFD_TWL4030_AUDIO
 
 config TWL6040_CORE
 	bool "Support for TWL6040 audio codec"
-	depends on I2C=y && GENERIC_HARDIRQS
+	depends on I2C=y
 	select MFD_CORE
 	select REGMAP_I2C
-	select IRQ_DOMAIN
+	select REGMAP_IRQ
 	default n
 	help
 	  Say yes here if you want support for Texas Instruments TWL6040 audio
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index a4093a44304a..05bebf66ccd2 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -67,7 +67,7 @@ obj-$(CONFIG_TWL4030_CORE)	+= twl-core.o twl4030-irq.o twl6030-irq.o
 obj-$(CONFIG_TWL4030_MADC)      += twl4030-madc.o
 obj-$(CONFIG_TWL4030_POWER)    += twl4030-power.o
 obj-$(CONFIG_MFD_TWL4030_AUDIO)	+= twl4030-audio.o
-obj-$(CONFIG_TWL6040_CORE)	+= twl6040-core.o twl6040-irq.o
+obj-$(CONFIG_TWL6040_CORE)	+= twl6040-core.o
 
 obj-$(CONFIG_MFD_MC13XXX)	+= mc13xxx-core.o
 obj-$(CONFIG_MFD_MC13XXX_SPI)	+= mc13xxx-spi.o
diff --git a/drivers/mfd/twl6040-core.c b/drivers/mfd/twl6040-core.c
index 5817bc6d09dc..e5f7b795afff 100644
--- a/drivers/mfd/twl6040-core.c
+++ b/drivers/mfd/twl6040-core.c
@@ -499,6 +499,25 @@ static struct regmap_config twl6040_regmap_config = {
 	.readable_reg = twl6040_readable_reg,
 };
 
+static const struct regmap_irq twl6040_irqs[] = {
+	{ .reg_offset = 0, .mask = TWL6040_THINT, },
+	{ .reg_offset = 0, .mask = TWL6040_PLUGINT | TWL6040_UNPLUGINT, },
+	{ .reg_offset = 0, .mask = TWL6040_HOOKINT, },
+	{ .reg_offset = 0, .mask = TWL6040_HFINT, },
+	{ .reg_offset = 0, .mask = TWL6040_VIBINT, },
+	{ .reg_offset = 0, .mask = TWL6040_READYINT, },
+};
+
+static struct regmap_irq_chip twl6040_irq_chip = {
+	.name = "twl6040",
+	.irqs = twl6040_irqs,
+	.num_irqs = ARRAY_SIZE(twl6040_irqs),
+
+	.num_regs = 1,
+	.status_base = TWL6040_REG_INTID,
+	.mask_base = TWL6040_REG_INTMR,
+};
+
 static int __devinit twl6040_probe(struct i2c_client *client,
 				     const struct i2c_device_id *id)
 {
@@ -574,21 +593,27 @@ static int __devinit twl6040_probe(struct i2c_client *client,
 			goto gpio_err;
 	}
 
-	/* codec interrupt */
-	ret = twl6040_irq_init(twl6040);
-	if (ret)
+	ret = regmap_add_irq_chip(twl6040->regmap, twl6040->irq,
+			IRQF_ONESHOT, 0, &twl6040_irq_chip,
+			&twl6040->irq_data);
+	if (ret < 0)
 		goto irq_init_err;
 
-	ret = request_threaded_irq(twl6040->irq_base + TWL6040_IRQ_READY,
-				   NULL, twl6040_readyint_handler, IRQF_ONESHOT,
+	twl6040->irq_ready = regmap_irq_get_virq(twl6040->irq_data,
+					       TWL6040_IRQ_READY);
+	twl6040->irq_th = regmap_irq_get_virq(twl6040->irq_data,
+					       TWL6040_IRQ_TH);
+
+	ret = request_threaded_irq(twl6040->irq_ready, NULL,
+				   twl6040_readyint_handler, IRQF_ONESHOT,
 				   "twl6040_irq_ready", twl6040);
 	if (ret) {
 		dev_err(twl6040->dev, "READY IRQ request failed: %d\n", ret);
 		goto readyirq_err;
 	}
 
-	ret = request_threaded_irq(twl6040->irq_base + TWL6040_IRQ_TH,
-				   NULL, twl6040_thint_handler, IRQF_ONESHOT,
+	ret = request_threaded_irq(twl6040->irq_th, NULL,
+				   twl6040_thint_handler, IRQF_ONESHOT,
 				   "twl6040_irq_th", twl6040);
 	if (ret) {
 		dev_err(twl6040->dev, "Thermal IRQ request failed: %d\n", ret);
@@ -604,7 +629,7 @@ static int __devinit twl6040_probe(struct i2c_client *client,
 	 * The ASoC codec can work without pdata, pass the platform_data only if
 	 * it has been provided.
 	 */
-	irq = twl6040->irq_base + TWL6040_IRQ_PLUG;
+	irq = regmap_irq_get_virq(twl6040->irq_data, TWL6040_IRQ_PLUG);
 	cell = &twl6040->cells[children];
 	cell->name = "twl6040-codec";
 	twl6040_codec_rsrc[0].start = irq;
@@ -618,7 +643,7 @@ static int __devinit twl6040_probe(struct i2c_client *client,
 	children++;
 
 	if (twl6040_has_vibra(pdata, node)) {
-		irq = twl6040->irq_base + TWL6040_IRQ_VIB;
+		irq = regmap_irq_get_virq(twl6040->irq_data, TWL6040_IRQ_VIB);
 
 		cell = &twl6040->cells[children];
 		cell->name = "twl6040-vibra";
@@ -657,11 +682,11 @@ static int __devinit twl6040_probe(struct i2c_client *client,
 	return 0;
 
 mfd_err:
-	free_irq(twl6040->irq_base + TWL6040_IRQ_TH, twl6040);
+	free_irq(twl6040->irq_th, twl6040);
 thirq_err:
-	free_irq(twl6040->irq_base + TWL6040_IRQ_READY, twl6040);
+	free_irq(twl6040->irq_ready, twl6040);
 readyirq_err:
-	twl6040_irq_exit(twl6040);
+	regmap_del_irq_chip(twl6040->irq, twl6040->irq_data);
 irq_init_err:
 	if (gpio_is_valid(twl6040->audpwron))
 		gpio_free(twl6040->audpwron);
@@ -685,9 +710,9 @@ static int __devexit twl6040_remove(struct i2c_client *client)
 	if (gpio_is_valid(twl6040->audpwron))
 		gpio_free(twl6040->audpwron);
 
-	free_irq(twl6040->irq_base + TWL6040_IRQ_READY, twl6040);
-	free_irq(twl6040->irq_base + TWL6040_IRQ_TH, twl6040);
-	twl6040_irq_exit(twl6040);
+	free_irq(twl6040->irq_ready, twl6040);
+	free_irq(twl6040->irq_th, twl6040);
+	regmap_del_irq_chip(twl6040->irq, twl6040->irq_data);
 
 	mfd_remove_devices(&client->dev);
 	i2c_set_clientdata(client, NULL);
diff --git a/drivers/mfd/twl6040-irq.c b/drivers/mfd/twl6040-irq.c
deleted file mode 100644
index 4b42543da228..000000000000
--- a/drivers/mfd/twl6040-irq.c
+++ /dev/null
@@ -1,205 +0,0 @@
-/*
- * Interrupt controller support for TWL6040
- *
- * Author:     Misael Lopez Cruz <misael.lopez@ti.com>
- *
- * Copyright:   (C) 2011 Texas Instruments, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/err.h>
-#include <linux/irq.h>
-#include <linux/of.h>
-#include <linux/irqdomain.h>
-#include <linux/interrupt.h>
-#include <linux/mfd/core.h>
-#include <linux/mfd/twl6040.h>
-
-struct twl6040_irq_data {
-	int mask;
-	int status;
-};
-
-static struct twl6040_irq_data twl6040_irqs[] = {
-	{
-		.mask = TWL6040_THMSK,
-		.status = TWL6040_THINT,
-	},
-	{
-		.mask = TWL6040_PLUGMSK,
-		.status = TWL6040_PLUGINT | TWL6040_UNPLUGINT,
-	},
-	{
-		.mask = TWL6040_HOOKMSK,
-		.status = TWL6040_HOOKINT,
-	},
-	{
-		.mask = TWL6040_HFMSK,
-		.status = TWL6040_HFINT,
-	},
-	{
-		.mask = TWL6040_VIBMSK,
-		.status = TWL6040_VIBINT,
-	},
-	{
-		.mask = TWL6040_READYMSK,
-		.status = TWL6040_READYINT,
-	},
-};
-
-static inline
-struct twl6040_irq_data *irq_to_twl6040_irq(struct twl6040 *twl6040,
-					    int irq)
-{
-	return &twl6040_irqs[irq - twl6040->irq_base];
-}
-
-static void twl6040_irq_lock(struct irq_data *data)
-{
-	struct twl6040 *twl6040 = irq_data_get_irq_chip_data(data);
-
-	mutex_lock(&twl6040->irq_mutex);
-}
-
-static void twl6040_irq_sync_unlock(struct irq_data *data)
-{
-	struct twl6040 *twl6040 = irq_data_get_irq_chip_data(data);
-
-	/* write back to hardware any change in irq mask */
-	if (twl6040->irq_masks_cur != twl6040->irq_masks_cache) {
-		twl6040->irq_masks_cache = twl6040->irq_masks_cur;
-		twl6040_reg_write(twl6040, TWL6040_REG_INTMR,
-				  twl6040->irq_masks_cur);
-	}
-
-	mutex_unlock(&twl6040->irq_mutex);
-}
-
-static void twl6040_irq_enable(struct irq_data *data)
-{
-	struct twl6040 *twl6040 = irq_data_get_irq_chip_data(data);
-	struct twl6040_irq_data *irq_data = irq_to_twl6040_irq(twl6040,
-							       data->irq);
-
-	twl6040->irq_masks_cur &= ~irq_data->mask;
-}
-
-static void twl6040_irq_disable(struct irq_data *data)
-{
-	struct twl6040 *twl6040 = irq_data_get_irq_chip_data(data);
-	struct twl6040_irq_data *irq_data = irq_to_twl6040_irq(twl6040,
-							       data->irq);
-
-	twl6040->irq_masks_cur |= irq_data->mask;
-}
-
-static struct irq_chip twl6040_irq_chip = {
-	.name			= "twl6040",
-	.irq_bus_lock		= twl6040_irq_lock,
-	.irq_bus_sync_unlock	= twl6040_irq_sync_unlock,
-	.irq_enable		= twl6040_irq_enable,
-	.irq_disable		= twl6040_irq_disable,
-};
-
-static irqreturn_t twl6040_irq_thread(int irq, void *data)
-{
-	struct twl6040 *twl6040 = data;
-	u8 intid;
-	int i;
-
-	intid = twl6040_reg_read(twl6040, TWL6040_REG_INTID);
-
-	/* apply masking and report (backwards to handle READYINT first) */
-	for (i = ARRAY_SIZE(twl6040_irqs) - 1; i >= 0; i--) {
-		if (twl6040->irq_masks_cur & twl6040_irqs[i].mask)
-			intid &= ~twl6040_irqs[i].status;
-		if (intid & twl6040_irqs[i].status)
-			handle_nested_irq(twl6040->irq_base + i);
-	}
-
-	/* ack unmasked irqs */
-	twl6040_reg_write(twl6040, TWL6040_REG_INTID, intid);
-
-	return IRQ_HANDLED;
-}
-
-int twl6040_irq_init(struct twl6040 *twl6040)
-{
-	struct device_node *node = twl6040->dev->of_node;
-	int i, nr_irqs, irq_base, ret;
-	u8 val;
-
-	mutex_init(&twl6040->irq_mutex);
-
-	/* mask the individual interrupt sources */
-	twl6040->irq_masks_cur = TWL6040_ALLINT_MSK;
-	twl6040->irq_masks_cache = TWL6040_ALLINT_MSK;
-	twl6040_reg_write(twl6040, TWL6040_REG_INTMR, TWL6040_ALLINT_MSK);
-
-	nr_irqs = ARRAY_SIZE(twl6040_irqs);
-
-	irq_base = irq_alloc_descs(-1, 0, nr_irqs, 0);
-	if (IS_ERR_VALUE(irq_base)) {
-		dev_err(twl6040->dev, "Fail to allocate IRQ descs\n");
-		return irq_base;
-	}
-	twl6040->irq_base = irq_base;
-
-	irq_domain_add_legacy(node, ARRAY_SIZE(twl6040_irqs), irq_base, 0,
-			      &irq_domain_simple_ops, NULL);
-
-	/* Register them with genirq */
-	for (i = irq_base; i < irq_base + nr_irqs; i++) {
-		irq_set_chip_data(i, twl6040);
-		irq_set_chip_and_handler(i, &twl6040_irq_chip,
-					 handle_level_irq);
-		irq_set_nested_thread(i, 1);
-
-		/* ARM needs us to explicitly flag the IRQ as valid
-		 * and will set them noprobe when we do so. */
-#ifdef CONFIG_ARM
-		set_irq_flags(i, IRQF_VALID);
-#else
-		irq_set_noprobe(i);
-#endif
-	}
-
-	ret = request_threaded_irq(twl6040->irq, NULL, twl6040_irq_thread,
-				   IRQF_ONESHOT, "twl6040", twl6040);
-	if (ret) {
-		dev_err(twl6040->dev, "failed to request IRQ %d: %d\n",
-			twl6040->irq, ret);
-		return ret;
-	}
-
-	/* reset interrupts */
-	val = twl6040_reg_read(twl6040, TWL6040_REG_INTID);
-
-	/* interrupts cleared on write */
-	twl6040_clear_bits(twl6040, TWL6040_REG_ACCCTL, TWL6040_INTCLRMODE);
-
-	return 0;
-}
-EXPORT_SYMBOL(twl6040_irq_init);
-
-void twl6040_irq_exit(struct twl6040 *twl6040)
-{
-	free_irq(twl6040->irq, twl6040);
-}
-EXPORT_SYMBOL(twl6040_irq_exit);
diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h
index a8eff4ad9be5..94ac944d12f0 100644
--- a/include/linux/mfd/twl6040.h
+++ b/include/linux/mfd/twl6040.h
@@ -207,10 +207,12 @@ struct twl6040_platform_data {
 };
 
 struct regmap;
+struct regmap_irq_chips_data;
 
 struct twl6040 {
 	struct device *dev;
 	struct regmap *regmap;
+	struct regmap_irq_chip_data *irq_data;
 	struct regulator_bulk_data supplies[2]; /* supplies for vio, v2v1 */
 	struct mutex mutex;
 	struct mutex irq_mutex;
@@ -228,9 +230,8 @@ struct twl6040 {
 	unsigned int mclk;
 
 	unsigned int irq;
-	unsigned int irq_base;
-	u8 irq_masks_cur;
-	u8 irq_masks_cache;
+	unsigned int irq_ready;
+	unsigned int irq_th;
 };
 
 int twl6040_reg_read(struct twl6040 *twl6040, unsigned int reg);
@@ -245,8 +246,7 @@ int twl6040_set_pll(struct twl6040 *twl6040, int pll_id,
 		    unsigned int freq_in, unsigned int freq_out);
 int twl6040_get_pll(struct twl6040 *twl6040);
 unsigned int twl6040_get_sysclk(struct twl6040 *twl6040);
-int twl6040_irq_init(struct twl6040 *twl6040);
-void twl6040_irq_exit(struct twl6040 *twl6040);
+
 /* Get the combined status of the vibra control register */
 int twl6040_get_vibralr_status(struct twl6040 *twl6040);
 
-- 
cgit v1.2.3-55-g7522


From 605511a848ae3ac4b2ce272ae6cbf8930b29ebb3 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 13 Nov 2012 19:18:05 +0530
Subject: mfd: Convert tps6586x to irq_domain

Allocate the irq base if it base is not porvided i.e.
in case of device tree invocation of this driver.
Convert the tps6586x driver to irq domain, using a
legacy IRQ mapping if an irq_base is specified in
platform data or dynamically allocated and otherwise
using a linear mapping.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/tps6586x.c       | 91 ++++++++++++++++++++++++++++++++------------
 include/linux/mfd/tps6586x.h |  1 +
 2 files changed, 67 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c
index 467464368773..2cdf1e6c00c8 100644
--- a/drivers/mfd/tps6586x.c
+++ b/drivers/mfd/tps6586x.c
@@ -17,12 +17,14 @@
 
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/irqdomain.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/i2c.h>
+#include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/regulator/machine.h>
@@ -116,6 +118,7 @@ struct tps6586x {
 	int			irq_base;
 	u32			irq_en;
 	u8			mask_reg[5];
+	struct irq_domain	*irq_domain;
 };
 
 static inline struct tps6586x *dev_to_tps6586x(struct device *dev)
@@ -184,6 +187,14 @@ int tps6586x_update(struct device *dev, int reg, uint8_t val, uint8_t mask)
 }
 EXPORT_SYMBOL_GPL(tps6586x_update);
 
+int tps6586x_irq_get_virq(struct device *dev, int irq)
+{
+	struct tps6586x *tps6586x = dev_to_tps6586x(dev);
+
+	return irq_create_mapping(tps6586x->irq_domain, irq);
+}
+EXPORT_SYMBOL_GPL(tps6586x_irq_get_virq);
+
 static int __remove_subdev(struct device *dev, void *unused)
 {
 	platform_device_unregister(to_platform_device(dev));
@@ -205,7 +216,7 @@ static void tps6586x_irq_lock(struct irq_data *data)
 static void tps6586x_irq_enable(struct irq_data *irq_data)
 {
 	struct tps6586x *tps6586x = irq_data_get_irq_chip_data(irq_data);
-	unsigned int __irq = irq_data->irq - tps6586x->irq_base;
+	unsigned int __irq = irq_data->hwirq;
 	const struct tps6586x_irq_data *data = &tps6586x_irqs[__irq];
 
 	tps6586x->mask_reg[data->mask_reg] &= ~data->mask_mask;
@@ -216,7 +227,7 @@ static void tps6586x_irq_disable(struct irq_data *irq_data)
 {
 	struct tps6586x *tps6586x = irq_data_get_irq_chip_data(irq_data);
 
-	unsigned int __irq = irq_data->irq - tps6586x->irq_base;
+	unsigned int __irq = irq_data->hwirq;
 	const struct tps6586x_irq_data *data = &tps6586x_irqs[__irq];
 
 	tps6586x->mask_reg[data->mask_reg] |= data->mask_mask;
@@ -239,6 +250,39 @@ static void tps6586x_irq_sync_unlock(struct irq_data *data)
 	mutex_unlock(&tps6586x->irq_lock);
 }
 
+static struct irq_chip tps6586x_irq_chip = {
+	.name = "tps6586x",
+	.irq_bus_lock = tps6586x_irq_lock,
+	.irq_bus_sync_unlock = tps6586x_irq_sync_unlock,
+	.irq_disable = tps6586x_irq_disable,
+	.irq_enable = tps6586x_irq_enable,
+};
+
+static int tps6586x_irq_map(struct irq_domain *h, unsigned int virq,
+				irq_hw_number_t hw)
+{
+	struct tps6586x *tps6586x = h->host_data;
+
+	irq_set_chip_data(virq, tps6586x);
+	irq_set_chip_and_handler(virq, &tps6586x_irq_chip, handle_simple_irq);
+	irq_set_nested_thread(virq, 1);
+
+	/* ARM needs us to explicitly flag the IRQ as valid
+	 * and will set them noprobe when we do so. */
+#ifdef CONFIG_ARM
+	set_irq_flags(virq, IRQF_VALID);
+#else
+	irq_set_noprobe(virq);
+#endif
+
+	return 0;
+}
+
+static struct irq_domain_ops tps6586x_domain_ops = {
+	.map    = tps6586x_irq_map,
+	.xlate  = irq_domain_xlate_twocell,
+};
+
 static irqreturn_t tps6586x_irq(int irq, void *data)
 {
 	struct tps6586x *tps6586x = data;
@@ -259,7 +303,8 @@ static irqreturn_t tps6586x_irq(int irq, void *data)
 		int i = __ffs(acks);
 
 		if (tps6586x->irq_en & (1 << i))
-			handle_nested_irq(tps6586x->irq_base + i);
+			handle_nested_irq(
+				irq_find_mapping(tps6586x->irq_domain, i));
 
 		acks &= ~(1 << i);
 	}
@@ -272,11 +317,8 @@ static int __devinit tps6586x_irq_init(struct tps6586x *tps6586x, int irq,
 {
 	int i, ret;
 	u8 tmp[4];
-
-	if (!irq_base) {
-		dev_warn(tps6586x->dev, "No interrupt support on IRQ base\n");
-		return -EINVAL;
-	}
+	int new_irq_base;
+	int irq_num = ARRAY_SIZE(tps6586x_irqs);
 
 	mutex_init(&tps6586x->irq_lock);
 	for (i = 0; i < 5; i++) {
@@ -286,25 +328,24 @@ static int __devinit tps6586x_irq_init(struct tps6586x *tps6586x, int irq,
 
 	tps6586x_reads(tps6586x->dev, TPS6586X_INT_ACK1, sizeof(tmp), tmp);
 
-	tps6586x->irq_base = irq_base;
-
-	tps6586x->irq_chip.name = "tps6586x";
-	tps6586x->irq_chip.irq_enable = tps6586x_irq_enable;
-	tps6586x->irq_chip.irq_disable = tps6586x_irq_disable;
-	tps6586x->irq_chip.irq_bus_lock = tps6586x_irq_lock;
-	tps6586x->irq_chip.irq_bus_sync_unlock = tps6586x_irq_sync_unlock;
-
-	for (i = 0; i < ARRAY_SIZE(tps6586x_irqs); i++) {
-		int __irq = i + tps6586x->irq_base;
-		irq_set_chip_data(__irq, tps6586x);
-		irq_set_chip_and_handler(__irq, &tps6586x->irq_chip,
-					 handle_simple_irq);
-		irq_set_nested_thread(__irq, 1);
-#ifdef CONFIG_ARM
-		set_irq_flags(__irq, IRQF_VALID);
-#endif
+	if  (irq_base > 0) {
+		new_irq_base = irq_alloc_descs(irq_base, 0, irq_num, -1);
+		if (new_irq_base < 0) {
+			dev_err(tps6586x->dev,
+				"Failed to alloc IRQs: %d\n", new_irq_base);
+			return new_irq_base;
+		}
+	} else {
+		new_irq_base = 0;
 	}
 
+	tps6586x->irq_domain = irq_domain_add_simple(tps6586x->dev->of_node,
+				irq_num, new_irq_base, &tps6586x_domain_ops,
+				tps6586x);
+	if (!tps6586x->irq_domain) {
+		dev_err(tps6586x->dev, "Failed to create IRQ domain\n");
+		return -ENOMEM;
+	}
 	ret = request_threaded_irq(irq, NULL, tps6586x_irq, IRQF_ONESHOT,
 				   "tps6586x", tps6586x);
 
diff --git a/include/linux/mfd/tps6586x.h b/include/linux/mfd/tps6586x.h
index 2dd123194958..ebd8b08a386b 100644
--- a/include/linux/mfd/tps6586x.h
+++ b/include/linux/mfd/tps6586x.h
@@ -93,5 +93,6 @@ extern int tps6586x_set_bits(struct device *dev, int reg, uint8_t bit_mask);
 extern int tps6586x_clr_bits(struct device *dev, int reg, uint8_t bit_mask);
 extern int tps6586x_update(struct device *dev, int reg, uint8_t val,
 			   uint8_t mask);
+extern int tps6586x_irq_get_virq(struct device *dev, int irq);
 
 #endif /*__LINUX_MFD_TPS6586X_H */
-- 
cgit v1.2.3-55-g7522


From d6ad418763888f617ac5b4849823e4cd670df1dd Mon Sep 17 00:00:00 2001
From: John Stultz
Date: Tue, 28 Feb 2012 16:50:11 -0800
Subject: time: Kill xtime_lock, replacing it with jiffies_lock

Now that timekeeping is protected by its own locks, rename
the xtime_lock to jifffies_lock to better describe what it
protects.

CC: Thomas Gleixner <tglx@linutronix.de>
CC: Eric Dumazet <eric.dumazet@gmail.com>
CC: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 drivers/clocksource/i8253.c |  2 +-
 include/linux/jiffies.h     |  3 ++-
 kernel/time/jiffies.c       |  6 ++++--
 kernel/time/tick-common.c   |  8 ++++----
 kernel/time/tick-internal.h |  1 -
 kernel/time/tick-sched.c    | 22 +++++++++++-----------
 kernel/time/timekeeping.c   | 14 +++-----------
 7 files changed, 25 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
index e7cab2da910f..14ee3efcc404 100644
--- a/drivers/clocksource/i8253.c
+++ b/drivers/clocksource/i8253.c
@@ -35,7 +35,7 @@ static cycle_t i8253_read(struct clocksource *cs)
 
 	raw_spin_lock_irqsave(&i8253_lock, flags);
 	/*
-	 * Although our caller may have the read side of xtime_lock,
+	 * Although our caller may have the read side of jiffies_lock,
 	 * this is now a seqlock, and we are cheating in this routine
 	 * by having side effects on state that we cannot undo if
 	 * there is a collision on the seqlock and our caller has to
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 6b87413da9d6..82ed068b1ebe 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -70,11 +70,12 @@ extern int register_refined_jiffies(long clock_tick_rate);
 
 /*
  * The 64-bit value is not atomic - you MUST NOT read it
- * without sampling the sequence number in xtime_lock.
+ * without sampling the sequence number in jiffies_lock.
  * get_jiffies_64() will do this for you as appropriate.
  */
 extern u64 __jiffy_data jiffies_64;
 extern unsigned long volatile __jiffy_data jiffies;
+extern seqlock_t jiffies_lock;
 
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void);
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 25f5b2699d37..7a925ba456fb 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -67,6 +67,8 @@ static struct clocksource clocksource_jiffies = {
 	.shift		= JIFFIES_SHIFT,
 };
 
+__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
+
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
 {
@@ -74,9 +76,9 @@ u64 get_jiffies_64(void)
 	u64 ret;
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqbegin(&jiffies_lock);
 		ret = jiffies_64;
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqretry(&jiffies_lock, seq));
 	return ret;
 }
 EXPORT_SYMBOL(get_jiffies_64);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index da6c9ecad4e4..b1600a6973f4 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -63,13 +63,13 @@ int tick_is_oneshot_available(void)
 static void tick_periodic(int cpu)
 {
 	if (tick_do_timer_cpu == cpu) {
-		write_seqlock(&xtime_lock);
+		write_seqlock(&jiffies_lock);
 
 		/* Keep track of the next tick event */
 		tick_next_period = ktime_add(tick_next_period, tick_period);
 
 		do_timer(1);
-		write_sequnlock(&xtime_lock);
+		write_sequnlock(&jiffies_lock);
 	}
 
 	update_process_times(user_mode(get_irq_regs()));
@@ -130,9 +130,9 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 		ktime_t next;
 
 		do {
-			seq = read_seqbegin(&xtime_lock);
+			seq = read_seqbegin(&jiffies_lock);
 			next = tick_next_period;
-		} while (read_seqretry(&xtime_lock, seq));
+		} while (read_seqretry(&jiffies_lock, seq));
 
 		clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 4e265b901fed..cf3e59ed6dc0 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -141,4 +141,3 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
 #endif
 
 extern void do_timer(unsigned long ticks);
-extern seqlock_t xtime_lock;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a40260885265..a678046c3e5e 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -31,7 +31,7 @@
 static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
 
 /*
- * The time, when the last jiffy update happened. Protected by xtime_lock.
+ * The time, when the last jiffy update happened. Protected by jiffies_lock.
  */
 static ktime_t last_jiffies_update;
 
@@ -49,14 +49,14 @@ static void tick_do_update_jiffies64(ktime_t now)
 	ktime_t delta;
 
 	/*
-	 * Do a quick check without holding xtime_lock:
+	 * Do a quick check without holding jiffies_lock:
 	 */
 	delta = ktime_sub(now, last_jiffies_update);
 	if (delta.tv64 < tick_period.tv64)
 		return;
 
-	/* Reevalute with xtime_lock held */
-	write_seqlock(&xtime_lock);
+	/* Reevalute with jiffies_lock held */
+	write_seqlock(&jiffies_lock);
 
 	delta = ktime_sub(now, last_jiffies_update);
 	if (delta.tv64 >= tick_period.tv64) {
@@ -79,7 +79,7 @@ static void tick_do_update_jiffies64(ktime_t now)
 		/* Keep the tick_next_period variable up to date */
 		tick_next_period = ktime_add(last_jiffies_update, tick_period);
 	}
-	write_sequnlock(&xtime_lock);
+	write_sequnlock(&jiffies_lock);
 }
 
 /*
@@ -89,12 +89,12 @@ static ktime_t tick_init_jiffy_update(void)
 {
 	ktime_t period;
 
-	write_seqlock(&xtime_lock);
+	write_seqlock(&jiffies_lock);
 	/* Did we start the jiffies update yet ? */
 	if (last_jiffies_update.tv64 == 0)
 		last_jiffies_update = tick_next_period;
 	period = last_jiffies_update;
-	write_sequnlock(&xtime_lock);
+	write_sequnlock(&jiffies_lock);
 	return period;
 }
 
@@ -282,11 +282,11 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqbegin(&jiffies_lock);
 		last_update = last_jiffies_update;
 		last_jiffies = jiffies;
 		time_delta = timekeeping_max_deferment();
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqretry(&jiffies_lock, seq));
 
 	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
 	    arch_needs_cpu(cpu)) {
@@ -658,7 +658,7 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 	 * concurrency: This happens only when the cpu in charge went
 	 * into a long sleep. If two cpus happen to assign themself to
 	 * this duty, then the jiffies update is still serialized by
-	 * xtime_lock.
+	 * jiffies_lock.
 	 */
 	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
 		tick_do_timer_cpu = cpu;
@@ -810,7 +810,7 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
 	 * concurrency: This happens only when the cpu in charge went
 	 * into a long sleep. If two cpus happen to assign themself to
 	 * this duty, then the jiffies update is still serialized by
-	 * xtime_lock.
+	 * jiffies_lock.
 	 */
 	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
 		tick_do_timer_cpu = cpu;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index e424970bb562..4c7de02eacdc 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -25,12 +25,6 @@
 
 static struct timekeeper timekeeper;
 
-/*
- * This read-write spinlock protects us from races in SMP while
- * playing with xtime.
- */
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
-
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
 
@@ -1299,9 +1293,7 @@ struct timespec get_monotonic_coarse(void)
 }
 
 /*
- * The 64-bit jiffies value is not atomic - you MUST NOT read it
- * without sampling the sequence number in xtime_lock.
- * jiffies is defined in the linker script...
+ * Must hold jiffies_lock
  */
 void do_timer(unsigned long ticks)
 {
@@ -1389,7 +1381,7 @@ EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset);
  */
 void xtime_update(unsigned long ticks)
 {
-	write_seqlock(&xtime_lock);
+	write_seqlock(&jiffies_lock);
 	do_timer(ticks);
-	write_sequnlock(&xtime_lock);
+	write_sequnlock(&jiffies_lock);
 }
-- 
cgit v1.2.3-55-g7522


From 5cb04436eef62aa8f5c482f8ec8deba391dea465 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa
Date: Tue, 6 Nov 2012 16:46:20 +0000
Subject: ipv6: add knob to send unsolicited ND on link-layer address change

This patch introduces a new knob ndisc_notify. If enabled, the kernel
will transmit an unsolicited neighbour advertisement on link-layer address
change to update the neighbour tables of the corresponding hosts more quickly.

This is the equivalent to arp_notify in ipv4 world.

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h      | 1 +
 include/uapi/linux/ipv6.h | 1 +
 net/ipv6/addrconf.c       | 8 ++++++++
 net/ipv6/ndisc.c          | 7 +++++++
 4 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index bcba48a97868..5e11905a4f01 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -47,6 +47,7 @@ struct ipv6_devconf {
 	__s32		disable_ipv6;
 	__s32		accept_dad;
 	__s32		force_tllao;
+	__s32           ndisc_notify;
 	void		*sysctl;
 };
 
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index a6d7d1c536c3..5a2991cf0251 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -157,6 +157,7 @@ enum {
 	DEVCONF_DISABLE_IPV6,
 	DEVCONF_ACCEPT_DAD,
 	DEVCONF_FORCE_TLLAO,
+	DEVCONF_NDISC_NOTIFY,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index fab23db8ee73..cb803b7bb0d8 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4037,6 +4037,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6;
 	array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad;
 	array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao;
+	array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -4704,6 +4705,13 @@ static struct addrconf_sysctl_table
 			.mode           = 0644,
 			.proc_handler   = proc_dointvec
 		},
+		{
+			.procname       = "ndisc_notify",
+			.data           = &ipv6_devconf.ndisc_notify,
+			.maxlen         = sizeof(int),
+			.mode           = 0644,
+			.proc_handler   = proc_dointvec
+		},
 		{
 			/* sentinel */
 		}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 6ba4b54a550a..f41853bca428 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1572,11 +1572,18 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
 {
 	struct net_device *dev = ptr;
 	struct net *net = dev_net(dev);
+	struct inet6_dev *idev;
 
 	switch (event) {
 	case NETDEV_CHANGEADDR:
 		neigh_changeaddr(&nd_tbl, dev);
 		fib6_run_gc(~0UL, net);
+		idev = in6_dev_get(dev);
+		if (!idev)
+			break;
+		if (idev->cnf.ndisc_notify)
+			ndisc_send_unsol_na(dev);
+		in6_dev_put(idev);
 		break;
 	case NETDEV_DOWN:
 		neigh_ifdown(&nd_tbl, dev);
-- 
cgit v1.2.3-55-g7522


From f4bda337bbb6e245e2a07f344990adeb6a70ff35 Mon Sep 17 00:00:00 2001
From: Thomas Pedersen
Date: Tue, 13 Nov 2012 10:46:27 -0800
Subject: mac80211: support RX_FLAG_MACTIME_END

Allow drivers to indicate their mactime is at RX completion and adjust
for this in mac80211. Also rename the existing RX_FLAG_MACTIME_MPDU to
RX_FLAG_MACTIME_START to clarify its intent. Based on similar code by
Johannes Berg.

Signed-off-by: Thomas Pedersen <thomas@cozybit.com>
[fix docs, atheros drivers]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath5k/base.c          |  2 +-
 drivers/net/wireless/ath/ath9k/htc_drv_txrx.c  |  2 +-
 drivers/net/wireless/ath/ath9k/recv.c          |  2 +-
 drivers/net/wireless/b43/xmit.c                |  2 +-
 drivers/net/wireless/b43legacy/xmit.c          |  2 +-
 drivers/net/wireless/brcm80211/brcmsmac/main.c |  2 +-
 drivers/net/wireless/iwlegacy/4965-mac.c       |  2 +-
 drivers/net/wireless/iwlwifi/dvm/rx.c          |  2 +-
 drivers/net/wireless/mac80211_hwsim.c          |  2 +-
 drivers/net/wireless/p54/txrx.c                |  2 +-
 drivers/net/wireless/rtl818x/rtl8180/dev.c     |  2 +-
 drivers/net/wireless/rtl818x/rtl8187/dev.c     |  2 +-
 drivers/net/wireless/rtlwifi/rtl8192ce/trx.c   |  2 +-
 drivers/net/wireless/rtlwifi/rtl8192cu/trx.c   |  2 +-
 drivers/net/wireless/rtlwifi/rtl8192de/trx.c   |  2 +-
 drivers/net/wireless/rtlwifi/rtl8192se/trx.c   |  2 +-
 drivers/net/wireless/ti/wl1251/rx.c            |  2 +-
 include/net/mac80211.h                         |  8 +++-
 net/mac80211/ibss.c                            | 29 +++------------
 net/mac80211/ieee80211_i.h                     | 11 ++++++
 net/mac80211/mesh_sync.c                       | 44 ++++------------------
 net/mac80211/rx.c                              | 14 +++++--
 net/mac80211/util.c                            | 51 ++++++++++++++++++++++++++
 23 files changed, 108 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index cdd19232960c..2fd5bab2e22a 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -1349,7 +1349,7 @@ ath5k_receive_frame(struct ath5k_hw *ah, struct sk_buff *skb,
 	 * right now, so it's not too bad...
 	 */
 	rxs->mactime = ath5k_extend_tsf(ah, rs->rs_tstamp);
-	rxs->flag |= RX_FLAG_MACTIME_MPDU;
+	rxs->flag |= RX_FLAG_MACTIME_START;
 
 	rxs->freq = ah->curchan->center_freq;
 	rxs->band = ah->curchan->band;
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index 06cdcb772d78..e4ec98332988 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -1082,7 +1082,7 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv,
 	rx_status->freq = hw->conf.channel->center_freq;
 	rx_status->signal =  rxbuf->rxstatus.rs_rssi + ATH_DEFAULT_NOISE_FLOOR;
 	rx_status->antenna = rxbuf->rxstatus.rs_antenna;
-	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
+	rx_status->flag |= RX_FLAG_MACTIME_START;
 
 	return true;
 
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index a04028bce28b..6aafbb77c498 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -976,7 +976,7 @@ static int ath9k_rx_skb_preprocess(struct ath_common *common,
 	rx_status->freq = hw->conf.channel->center_freq;
 	rx_status->signal = ah->noise + rx_stats->rs_rssi;
 	rx_status->antenna = rx_stats->rs_antenna;
-	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
+	rx_status->flag |= RX_FLAG_MACTIME_START;
 	if (rx_stats->rs_moreaggr)
 		rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL;
 
diff --git a/drivers/net/wireless/b43/xmit.c b/drivers/net/wireless/b43/xmit.c
index 136510edf3cf..8cb206a89083 100644
--- a/drivers/net/wireless/b43/xmit.c
+++ b/drivers/net/wireless/b43/xmit.c
@@ -796,7 +796,7 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 		status.mactime += mactime;
 		if (low_mactime_now <= mactime)
 			status.mactime -= 0x10000;
-		status.flag |= RX_FLAG_MACTIME_MPDU;
+		status.flag |= RX_FLAG_MACTIME_START;
 	}
 
 	chanid = (chanstat & B43_RX_CHAN_ID) >> B43_RX_CHAN_ID_SHIFT;
diff --git a/drivers/net/wireless/b43legacy/xmit.c b/drivers/net/wireless/b43legacy/xmit.c
index b8ffea6f5c64..849a28c80302 100644
--- a/drivers/net/wireless/b43legacy/xmit.c
+++ b/drivers/net/wireless/b43legacy/xmit.c
@@ -557,7 +557,7 @@ void b43legacy_rx(struct b43legacy_wldev *dev,
 		status.mactime += mactime;
 		if (low_mactime_now <= mactime)
 			status.mactime -= 0x10000;
-		status.flag |= RX_FLAG_MACTIME_MPDU;
+		status.flag |= RX_FLAG_MACTIME_START;
 	}
 
 	chanid = (chanstat & B43legacy_RX_CHAN_ID) >>
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/main.c b/drivers/net/wireless/brcm80211/brcmsmac/main.c
index 565c15abbed5..02363f8afd77 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/main.c
@@ -7508,7 +7508,7 @@ prep_mac80211_status(struct brcms_c_info *wlc, struct d11rxhdr *rxh,
 
 	/* fill in TSF and flag its presence */
 	rx_status->mactime = brcms_c_recover_tsf64(wlc, rxh);
-	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
+	rx_status->flag |= RX_FLAG_MACTIME_START;
 
 	channel = BRCMS_CHAN_CHANNEL(rxh->RxChan);
 
diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c
index eac4dc8bc879..ef68b7239955 100644
--- a/drivers/net/wireless/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/iwlegacy/4965-mac.c
@@ -686,7 +686,7 @@ il4965_hdl_rx(struct il_priv *il, struct il_rx_buf *rxb)
 
 	/* TSF isn't reliable. In order to allow smooth user experience,
 	 * this W/A doesn't propagate it to the mac80211 */
-	/*rx_status.flag |= RX_FLAG_MACTIME_MPDU; */
+	/*rx_status.flag |= RX_FLAG_MACTIME_START; */
 
 	il->ucode_beacon_time = le32_to_cpu(phy_res->beacon_time_stamp);
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/rx.c b/drivers/net/wireless/iwlwifi/dvm/rx.c
index 5a9c325804f6..ad50fb915831 100644
--- a/drivers/net/wireless/iwlwifi/dvm/rx.c
+++ b/drivers/net/wireless/iwlwifi/dvm/rx.c
@@ -951,7 +951,7 @@ static int iwlagn_rx_reply_rx(struct iwl_priv *priv,
 
 	/* TSF isn't reliable. In order to allow smooth user experience,
 	 * this W/A doesn't propagate it to the mac80211 */
-	/*rx_status.flag |= RX_FLAG_MACTIME_MPDU;*/
+	/*rx_status.flag |= RX_FLAG_MACTIME_START;*/
 
 	priv->ucode_beacon_time = le32_to_cpu(phy_res->beacon_time_stamp);
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index a8ec7086ad09..ce522aa93af7 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -699,7 +699,7 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw,
 	struct ieee80211_rate *txrate = ieee80211_get_tx_rate(hw, info);
 
 	memset(&rx_status, 0, sizeof(rx_status));
-	rx_status.flag |= RX_FLAG_MACTIME_MPDU;
+	rx_status.flag |= RX_FLAG_MACTIME_START;
 	rx_status.freq = chan->center_freq;
 	rx_status.band = chan->band;
 	rx_status.rate_idx = info->control.rates[0].idx;
diff --git a/drivers/net/wireless/p54/txrx.c b/drivers/net/wireless/p54/txrx.c
index 5861e13a6fd8..8ae982bd7cf3 100644
--- a/drivers/net/wireless/p54/txrx.c
+++ b/drivers/net/wireless/p54/txrx.c
@@ -369,7 +369,7 @@ static int p54_rx_data(struct p54_common *priv, struct sk_buff *skb)
 	rx_status->mactime = ((u64)priv->tsf_high32) << 32 | tsf32;
 	priv->tsf_low32 = tsf32;
 
-	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
+	rx_status->flag |= RX_FLAG_MACTIME_START;
 
 	if (hdr->flags & cpu_to_le16(P54_HDR_FLAG_DATA_ALIGN))
 		header_len += hdr->align[0];
diff --git a/drivers/net/wireless/rtl818x/rtl8180/dev.c b/drivers/net/wireless/rtl818x/rtl8180/dev.c
index 021d83e1b1d3..b4218a5f2066 100644
--- a/drivers/net/wireless/rtl818x/rtl8180/dev.c
+++ b/drivers/net/wireless/rtl818x/rtl8180/dev.c
@@ -150,7 +150,7 @@ static void rtl8180_handle_rx(struct ieee80211_hw *dev)
 			rx_status.freq = dev->conf.channel->center_freq;
 			rx_status.band = dev->conf.channel->band;
 			rx_status.mactime = le64_to_cpu(entry->tsft);
-			rx_status.flag |= RX_FLAG_MACTIME_MPDU;
+			rx_status.flag |= RX_FLAG_MACTIME_START;
 			if (flags & RTL818X_RX_DESC_FLAG_CRC32_ERR)
 				rx_status.flag |= RX_FLAG_FAILED_FCS_CRC;
 
diff --git a/drivers/net/wireless/rtl818x/rtl8187/dev.c b/drivers/net/wireless/rtl818x/rtl8187/dev.c
index 7811b6315973..52e6bebcf089 100644
--- a/drivers/net/wireless/rtl818x/rtl8187/dev.c
+++ b/drivers/net/wireless/rtl818x/rtl8187/dev.c
@@ -381,7 +381,7 @@ static void rtl8187_rx_cb(struct urb *urb)
 	rx_status.rate_idx = rate;
 	rx_status.freq = dev->conf.channel->center_freq;
 	rx_status.band = dev->conf.channel->band;
-	rx_status.flag |= RX_FLAG_MACTIME_MPDU;
+	rx_status.flag |= RX_FLAG_MACTIME_START;
 	if (flags & RTL818X_RX_DESC_FLAG_CRC32_ERR)
 		rx_status.flag |= RX_FLAG_FAILED_FCS_CRC;
 	memcpy(IEEE80211_SKB_RXCB(skb), &rx_status, sizeof(rx_status));
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c b/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
index 390d6d4fcaa0..a8fecd7638f6 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
@@ -567,7 +567,7 @@ bool rtl92ce_rx_query_desc(struct ieee80211_hw *hw,
 	if (GET_RX_DESC_RXHT(pdesc))
 		rx_status->flag |= RX_FLAG_HT;
 
-	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
+	rx_status->flag |= RX_FLAG_MACTIME_START;
 
 	if (stats->decrypted)
 		rx_status->flag |= RX_FLAG_DECRYPTED;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
index 6e66f04c363f..b6222eedb835 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
@@ -334,7 +334,7 @@ bool rtl92cu_rx_query_desc(struct ieee80211_hw *hw,
 		rx_status->flag |= RX_FLAG_40MHZ;
 	if (GET_RX_DESC_RX_HT(pdesc))
 		rx_status->flag |= RX_FLAG_HT;
-	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
+	rx_status->flag |= RX_FLAG_MACTIME_START;
 	if (stats->decrypted)
 		rx_status->flag |= RX_FLAG_DECRYPTED;
 	rx_status->rate_idx = rtlwifi_rate_mapping(hw,
diff --git a/drivers/net/wireless/rtlwifi/rtl8192de/trx.c b/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
index 4686f340b9d6..3baaf21abed4 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
@@ -514,7 +514,7 @@ bool rtl92de_rx_query_desc(struct ieee80211_hw *hw,	struct rtl_stats *stats,
 		rx_status->flag |= RX_FLAG_40MHZ;
 	if (GET_RX_DESC_RXHT(pdesc))
 		rx_status->flag |= RX_FLAG_HT;
-	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
+	rx_status->flag |= RX_FLAG_MACTIME_START;
 	if (stats->decrypted)
 		rx_status->flag |= RX_FLAG_DECRYPTED;
 	rx_status->rate_idx = rtlwifi_rate_mapping(hw,
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
index e3cf4c02122a..26d027cb5069 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
@@ -554,7 +554,7 @@ bool rtl92se_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats,
 	if (stats->is_ht)
 		rx_status->flag |= RX_FLAG_HT;
 
-	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
+	rx_status->flag |= RX_FLAG_MACTIME_START;
 
 	/* hw will set stats->decrypted true, if it finds the
 	 * frame is open data frame or mgmt frame,
diff --git a/drivers/net/wireless/ti/wl1251/rx.c b/drivers/net/wireless/ti/wl1251/rx.c
index 6af35265c900..23289d49dd31 100644
--- a/drivers/net/wireless/ti/wl1251/rx.c
+++ b/drivers/net/wireless/ti/wl1251/rx.c
@@ -81,7 +81,7 @@ static void wl1251_rx_status(struct wl1251 *wl,
 	status->freq = ieee80211_channel_to_frequency(desc->channel,
 						      status->band);
 
-	status->flag |= RX_FLAG_MACTIME_MPDU;
+	status->flag |= RX_FLAG_MACTIME_START;
 
 	if (desc->flags & RX_DESC_ENCRYPTION_MASK) {
 		status->flag |= RX_FLAG_IV_STRIPPED | RX_FLAG_MMIC_STRIPPED;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index a789dd1d4c10..b484a6569eac 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -711,10 +711,13 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	the frame.
  * @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on
  *	the frame.
- * @RX_FLAG_MACTIME_MPDU: The timestamp passed in the RX status (@mactime
+ * @RX_FLAG_MACTIME_START: The timestamp passed in the RX status (@mactime
  *	field) is valid and contains the time the first symbol of the MPDU
  *	was received. This is useful in monitor mode and for proper IBSS
  *	merging.
+ * @RX_FLAG_MACTIME_END: The timestamp passed in the RX status (@mactime
+ *	field) is valid and contains the time the last symbol of the MPDU
+ *	(including FCS) was received.
  * @RX_FLAG_SHORTPRE: Short preamble was used for this frame
  * @RX_FLAG_HT: HT MCS was used and rate_idx is MCS index
  * @RX_FLAG_40MHZ: HT40 (40 MHz) was used
@@ -745,7 +748,7 @@ enum mac80211_rx_flags {
 	RX_FLAG_IV_STRIPPED		= BIT(4),
 	RX_FLAG_FAILED_FCS_CRC		= BIT(5),
 	RX_FLAG_FAILED_PLCP_CRC 	= BIT(6),
-	RX_FLAG_MACTIME_MPDU		= BIT(7),
+	RX_FLAG_MACTIME_START		= BIT(7),
 	RX_FLAG_SHORTPRE		= BIT(8),
 	RX_FLAG_HT			= BIT(9),
 	RX_FLAG_40MHZ			= BIT(10),
@@ -759,6 +762,7 @@ enum mac80211_rx_flags {
 	RX_FLAG_AMPDU_IS_LAST		= BIT(18),
 	RX_FLAG_AMPDU_DELIM_CRC_ERROR	= BIT(19),
 	RX_FLAG_AMPDU_DELIM_CRC_KNOWN	= BIT(20),
+	RX_FLAG_MACTIME_END		= BIT(21),
 };
 
 /**
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index c7386b2b767e..cc11558d8c1a 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -543,30 +543,11 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 	if (ether_addr_equal(cbss->bssid, sdata->u.ibss.bssid))
 		goto put_bss;
 
-	if (rx_status->flag & RX_FLAG_MACTIME_MPDU) {
-		/*
-		 * For correct IBSS merging we need mactime; since mactime is
-		 * defined as the time the first data symbol of the frame hits
-		 * the PHY, and the timestamp of the beacon is defined as "the
-		 * time that the data symbol containing the first bit of the
-		 * timestamp is transmitted to the PHY plus the transmitting
-		 * STA's delays through its local PHY from the MAC-PHY
-		 * interface to its interface with the WM" (802.11 11.1.2)
-		 * - equals the time this bit arrives at the receiver - we have
-		 * to take into account the offset between the two.
-		 *
-		 * E.g. at 1 MBit that means mactime is 192 usec earlier
-		 * (=24 bytes * 8 usecs/byte) than the beacon timestamp.
-		 */
-		int rate;
-
-		if (rx_status->flag & RX_FLAG_HT)
-			rate = 65; /* TODO: HT rates */
-		else
-			rate = local->hw.wiphy->bands[band]->
-				bitrates[rx_status->rate_idx].bitrate;
-
-		rx_timestamp = rx_status->mactime + (24 * 8 * 10 / rate);
+	if (ieee80211_have_rx_timestamp(rx_status)) {
+		/* time when timestamp field was received */
+		rx_timestamp =
+			ieee80211_calculate_rx_timestamp(local, rx_status,
+							 len + FCS_LEN, 24);
 	} else {
 		/*
 		 * second best option: get current TSF
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index e1fb97cc9a41..bff82a8e62f3 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1259,7 +1259,18 @@ static inline int ieee80211_bssid_match(const u8 *raddr, const u8 *addr)
 	       is_broadcast_ether_addr(raddr);
 }
 
+static inline bool
+ieee80211_have_rx_timestamp(struct ieee80211_rx_status *status)
+{
+	WARN_ON_ONCE(status->flag & RX_FLAG_MACTIME_START &&
+		     status->flag & RX_FLAG_MACTIME_END);
+	return status->flag & (RX_FLAG_MACTIME_START | RX_FLAG_MACTIME_END);
+}
 
+u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
+				     struct ieee80211_rx_status *status,
+				     unsigned int mpdu_len,
+				     unsigned int mpdu_offset);
 int ieee80211_hw_config(struct ieee80211_local *local, u32 changed);
 void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx);
 void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c
index 407c8705e10d..9c6ea9cfe1b3 100644
--- a/net/mac80211/mesh_sync.c
+++ b/net/mac80211/mesh_sync.c
@@ -116,43 +116,13 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
 		goto no_sync;
 	}
 
-	if (rx_status->flag & RX_FLAG_MACTIME_MPDU && rx_status->mactime) {
-		/*
-		 * The mactime is defined as the time the first data symbol
-		 * of the frame hits the PHY, and the timestamp of the beacon
-		 * is defined as "the time that the data symbol containing the
-		 * first bit of the timestamp is transmitted to the PHY plus
-		 * the transmitting STA's delays through its local PHY from the
-		 * MAC-PHY interface to its interface with the WM" (802.11
-		 * 11.1.2)
-		 *
-		 * T_r, in 13.13.2.2.2, is just defined as "the frame reception
-		 * time" but we unless we interpret that time to be the same
-		 * time of the beacon timestamp, the offset calculation will be
-		 * off.  Below we adjust t_r to be "the time at which the first
-		 * symbol of the timestamp element in the beacon is received".
-		 * This correction depends on the rate.
-		 *
-		 * Based on similar code in ibss.c
-		 */
-		int rate;
-
-		if (rx_status->flag & RX_FLAG_HT) {
-			/* TODO:
-			 * In principle there could be HT-beacons (Dual Beacon
-			 * HT Operation options), but for now ignore them and
-			 * just use the primary (i.e. non-HT) beacons for
-			 * synchronization.
-			 * */
-			goto no_sync;
-		} else
-			rate = local->hw.wiphy->bands[rx_status->band]->
-				bitrates[rx_status->rate_idx].bitrate;
-
-		/* 24 bytes of header * 8 bits/byte *
-		 * 10*(100 Kbps)/Mbps / rate (100 Kbps)*/
-		t_r = rx_status->mactime + (24 * 8 * 10 / rate);
-	}
+	if (ieee80211_have_rx_timestamp(rx_status))
+		/* time when timestamp field was received */
+		t_r = ieee80211_calculate_rx_timestamp(local, rx_status,
+						       24 + 12 +
+						       elems->total_len +
+						       FCS_LEN,
+						       24);
 
 	/* Timing offset calculation (see 13.13.2.2.2) */
 	t_t = le64_to_cpu(mgmt->u.beacon.timestamp);
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 6ad330341b71..e3daee8fdf7a 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -81,7 +81,7 @@ ieee80211_rx_radiotap_len(struct ieee80211_local *local,
 	/* always present fields */
 	len = sizeof(struct ieee80211_radiotap_header) + 9;
 
-	if (status->flag & RX_FLAG_MACTIME_MPDU)
+	if (ieee80211_have_rx_timestamp(status))
 		len += 8;
 	if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM)
 		len += 1;
@@ -117,6 +117,11 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	struct ieee80211_radiotap_header *rthdr;
 	unsigned char *pos;
 	u16 rx_flags = 0;
+	int mpdulen;
+
+	mpdulen = skb->len;
+	if (!(has_fcs && (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS)))
+		mpdulen += FCS_LEN;
 
 	rthdr = (struct ieee80211_radiotap_header *)skb_push(skb, rtap_len);
 	memset(rthdr, 0, rtap_len);
@@ -134,8 +139,11 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	/* the order of the following fields is important */
 
 	/* IEEE80211_RADIOTAP_TSFT */
-	if (status->flag & RX_FLAG_MACTIME_MPDU) {
-		put_unaligned_le64(status->mactime, pos);
+	if (ieee80211_have_rx_timestamp(status)) {
+		put_unaligned_le64(
+			ieee80211_calculate_rx_timestamp(local, status,
+							 mpdulen, 0),
+			pos);
 		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_TSFT);
 		pos += 8;
 	}
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 4e4f58513673..5bad758abfb3 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2013,3 +2013,54 @@ u8 ieee80211_mcs_to_chains(const struct ieee80211_mcs_info *mcs)
 		return 2;
 	return 1;
 }
+
+/**
+ * ieee80211_calculate_rx_timestamp - calculate timestamp in frame
+ * @local: mac80211 hw info struct
+ * @status: RX status
+ * @mpdu_len: total MPDU length (including FCS)
+ * @mpdu_offset: offset into MPDU to calculate timestamp at
+ *
+ * This function calculates the RX timestamp at the given MPDU offset, taking
+ * into account what the RX timestamp was. An offset of 0 will just normalize
+ * the timestamp to TSF at beginning of MPDU reception.
+ */
+u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
+				     struct ieee80211_rx_status *status,
+				     unsigned int mpdu_len,
+				     unsigned int mpdu_offset)
+{
+	u64 ts = status->mactime;
+	struct rate_info ri;
+	u16 rate;
+
+	if (WARN_ON(!ieee80211_have_rx_timestamp(status)))
+		return 0;
+
+	memset(&ri, 0, sizeof(ri));
+
+	/* Fill cfg80211 rate info */
+	if (status->flag & RX_FLAG_HT) {
+		ri.mcs = status->rate_idx;
+		ri.flags |= RATE_INFO_FLAGS_MCS;
+		if (status->flag & RX_FLAG_40MHZ)
+			ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
+		if (status->flag & RX_FLAG_SHORT_GI)
+			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
+	} else {
+		struct ieee80211_supported_band *sband;
+
+		sband = local->hw.wiphy->bands[status->band];
+		ri.legacy = sband->bitrates[status->rate_idx].bitrate;
+	}
+
+	rate = cfg80211_calculate_bitrate(&ri);
+
+	/* rewind from end of MPDU */
+	if (status->flag & RX_FLAG_MACTIME_END)
+		ts -= mpdu_len * 8 * 10 / rate;
+
+	ts += mpdu_offset * 8 * 10 / rate;
+
+	return ts;
+}
-- 
cgit v1.2.3-55-g7522


From 8cbd9cc6254065c97c4bac42daa55ba1abe73a8e Mon Sep 17 00:00:00 2001
From: David Sharp
Date: Tue, 13 Nov 2012 12:18:21 -0800
Subject: tracing,x86: Add a TSC trace_clock

In order to promote interoperability between userspace tracers and ftrace,
add a trace_clock that reports raw TSC values which will then be recorded
in the ring buffer. Userspace tracers that also record TSCs are then on
exactly the same time base as the kernel and events can be unambiguously
interlaced.

Tested: Enabled a tracepoint and the "tsc" trace_clock and saw very large
timestamp values.

v2:
Move arch-specific bits out of generic code.
v3:
Rename "x86-tsc", cleanups
v7:
Generic arch bits in Kbuild.

Google-Bug-Id: 6980623
Link: http://lkml.kernel.org/r/1352837903-32191-1-git-send-email-dhsharp@google.com

Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@linux.intel.com>
Signed-off-by: David Sharp <dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/alpha/include/asm/Kbuild      |  1 +
 arch/arm/include/asm/Kbuild        |  1 +
 arch/arm64/include/asm/Kbuild      |  1 +
 arch/avr32/include/asm/Kbuild      |  1 +
 arch/blackfin/include/asm/Kbuild   |  1 +
 arch/c6x/include/asm/Kbuild        |  1 +
 arch/cris/include/asm/Kbuild       |  1 +
 arch/frv/include/asm/Kbuild        |  1 +
 arch/h8300/include/asm/Kbuild      |  1 +
 arch/hexagon/include/asm/Kbuild    |  1 +
 arch/ia64/include/asm/Kbuild       |  1 +
 arch/m32r/include/asm/Kbuild       |  1 +
 arch/m68k/include/asm/Kbuild       |  1 +
 arch/microblaze/include/asm/Kbuild |  1 +
 arch/mips/include/asm/Kbuild       |  1 +
 arch/mn10300/include/asm/Kbuild    |  1 +
 arch/openrisc/include/asm/Kbuild   |  1 +
 arch/parisc/include/asm/Kbuild     |  1 +
 arch/powerpc/include/asm/Kbuild    |  1 +
 arch/s390/include/asm/Kbuild       |  1 +
 arch/score/include/asm/Kbuild      |  1 +
 arch/sh/include/asm/Kbuild         |  1 +
 arch/sparc/include/asm/Kbuild      |  1 +
 arch/tile/include/asm/Kbuild       |  1 +
 arch/um/include/asm/Kbuild         |  1 +
 arch/unicore32/include/asm/Kbuild  |  1 +
 arch/x86/include/asm/trace_clock.h | 20 ++++++++++++++++++++
 arch/x86/kernel/Makefile           |  1 +
 arch/x86/kernel/trace_clock.c      | 21 +++++++++++++++++++++
 arch/xtensa/include/asm/Kbuild     |  1 +
 include/asm-generic/trace_clock.h  | 16 ++++++++++++++++
 include/linux/trace_clock.h        |  2 ++
 kernel/trace/trace.c               |  1 +
 33 files changed, 88 insertions(+)
 create mode 100644 arch/x86/include/asm/trace_clock.h
 create mode 100644 arch/x86/kernel/trace_clock.c
 create mode 100644 include/asm-generic/trace_clock.h

(limited to 'include')

diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index 64ffc9e9e548..dcfabb9f05a0 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -11,3 +11,4 @@ header-y += reg.h
 header-y += regdef.h
 header-y += sysinfo.h
 generic-y += exec.h
+generic-y += trace_clock.h
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index f70ae175a3d6..514e398f1a07 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -31,5 +31,6 @@ generic-y += sockios.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += timex.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += unaligned.h
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index a581a2205938..6e9ca462127f 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -43,6 +43,7 @@ generic-y += swab.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += unaligned.h
 generic-y += user.h
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 4807ded352c5..4dd4f78d3dcc 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -1,3 +1,4 @@
 
 generic-y	+= clkdev.h
 generic-y	+= exec.h
+generic-y	+= trace_clock.h
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 5a0625aad6a0..27d70759474c 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -38,6 +38,7 @@ generic-y += statfs.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += unaligned.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 112a496d8355..eae7b5963e86 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -49,6 +49,7 @@ generic-y += termbits.h
 generic-y += termios.h
 generic-y += tlbflush.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += user.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 6d43a951b5ec..15a122c3767c 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -11,3 +11,4 @@ header-y += sync_serial.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += module.h
+generic-y += trace_clock.h
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 4a159da23633..c5d767028306 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -1,3 +1,4 @@
 
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += trace_clock.h
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 50bbf387b2f8..4bc8ae73e08a 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += module.h
+generic-y += trace_clock.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 3bfa9b30f448..bdb54ceb53bc 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -48,6 +48,7 @@ generic-y += stat.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += unaligned.h
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index dd02f09b6eda..05b03ecd7933 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -2,3 +2,4 @@
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += kvm_para.h
+generic-y += trace_clock.h
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index 50bbf387b2f8..4bc8ae73e08a 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += module.h
+generic-y += trace_clock.h
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 88fa3ac86fae..7f1949c0e089 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -24,6 +24,7 @@ generic-y += sections.h
 generic-y += siginfo.h
 generic-y += statfs.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 8653072d7e9f..2957fcc71764 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm
 header-y  += elf.h
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += trace_clock.h
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 533053d12ced..9b54b7a403d4 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -1 +1,2 @@
 # MIPS headers
+generic-y += trace_clock.h
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 4a159da23633..c5d767028306 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -1,3 +1,4 @@
 
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += trace_clock.h
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 78de6805268d..8971026e1c63 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -60,6 +60,7 @@ generic-y += swab.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += user.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index bac8debecffb..ff4c9faed546 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
 	  segment.h topology.h vga.h device.h percpu.h hw_irq.h mutex.h \
 	  div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \
 	  poll.h xor.h clkdev.h exec.h
+generic-y += trace_clock.h
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index a4fe15e33c6f..2d62b484b3fc 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -2,3 +2,4 @@
 
 generic-y += clkdev.h
 generic-y += rwsem.h
+generic-y += trace_clock.h
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 0633dc6d254d..f313f9cbcf44 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,3 +1,4 @@
 
 
 generic-y += clkdev.h
+generic-y += trace_clock.h
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index ec697aeefd05..16e41fe1a419 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm
 header-y +=
 
 generic-y += clkdev.h
+generic-y += trace_clock.h
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 29f83beeef7a..280bea9e5e2b 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -31,5 +31,6 @@ generic-y += socket.h
 generic-y += statfs.h
 generic-y += termbits.h
 generic-y += termios.h
+generic-y += trace_clock.h
 generic-y += ucontext.h
 generic-y += xor.h
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 645a58da0e86..e26d430ce2fd 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -8,4 +8,5 @@ generic-y += local64.h
 generic-y += irq_regs.h
 generic-y += local.h
 generic-y += module.h
+generic-y += trace_clock.h
 generic-y += word-at-a-time.h
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 6948015e08a2..b17b9b8e53cd 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -34,5 +34,6 @@ generic-y += sockios.h
 generic-y += statfs.h
 generic-y += termbits.h
 generic-y += termios.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += xor.h
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 0f6e7b328265..b30f34a79882 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -2,3 +2,4 @@ generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h
 generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
 generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h
 generic-y += switch_to.h clkdev.h
+generic-y += trace_clock.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index c910c9857e11..7be503e45695 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -54,6 +54,7 @@ generic-y += syscalls.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += unaligned.h
diff --git a/arch/x86/include/asm/trace_clock.h b/arch/x86/include/asm/trace_clock.h
new file mode 100644
index 000000000000..5c1652728b6d
--- /dev/null
+++ b/arch/x86/include/asm/trace_clock.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_X86_TRACE_CLOCK_H
+#define _ASM_X86_TRACE_CLOCK_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_X86_TSC
+
+extern u64 notrace trace_clock_x86_tsc(void);
+
+# define ARCH_TRACE_CLOCKS \
+	{ trace_clock_x86_tsc,	"x86-tsc" },
+
+#else /* !CONFIG_X86_TSC */
+
+#define ARCH_TRACE_CLOCKS
+
+#endif
+
+#endif  /* _ASM_X86_TRACE_CLOCK_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9fd5eed3f8f5..34e923a53762 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
+obj-$(CONFIG_X86_TSC)		+= trace_clock.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c
new file mode 100644
index 000000000000..25b993729f9b
--- /dev/null
+++ b/arch/x86/kernel/trace_clock.c
@@ -0,0 +1,21 @@
+/*
+ * X86 trace clocks
+ */
+#include <asm/trace_clock.h>
+#include <asm/barrier.h>
+#include <asm/msr.h>
+
+/*
+ * trace_clock_x86_tsc(): A clock that is just the cycle counter.
+ *
+ * Unlike the other clocks, this is not in nanoseconds.
+ */
+u64 notrace trace_clock_x86_tsc(void)
+{
+	u64 ret;
+
+	rdtsc_barrier();
+	rdtscll(ret);
+
+	return ret;
+}
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 6d1302789995..095f0a2244f7 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -25,4 +25,5 @@ generic-y += siginfo.h
 generic-y += statfs.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += xor.h
diff --git a/include/asm-generic/trace_clock.h b/include/asm-generic/trace_clock.h
new file mode 100644
index 000000000000..6726f1bafb5e
--- /dev/null
+++ b/include/asm-generic/trace_clock.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_GENERIC_TRACE_CLOCK_H
+#define _ASM_GENERIC_TRACE_CLOCK_H
+/*
+ * Arch-specific trace clocks.
+ */
+
+/*
+ * Additional trace clocks added to the trace_clocks
+ * array in kernel/trace/trace.c
+ * None if the architecture has not defined it.
+ */
+#ifndef ARCH_TRACE_CLOCKS
+# define ARCH_TRACE_CLOCKS
+#endif
+
+#endif  /* _ASM_GENERIC_TRACE_CLOCK_H */
diff --git a/include/linux/trace_clock.h b/include/linux/trace_clock.h
index 4eb490237d4c..d563f37e1a1d 100644
--- a/include/linux/trace_clock.h
+++ b/include/linux/trace_clock.h
@@ -12,6 +12,8 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 
+#include <asm/trace_clock.h>
+
 extern u64 notrace trace_clock_local(void);
 extern u64 notrace trace_clock(void);
 extern u64 notrace trace_clock_global(void);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c1434b5ce4d1..0d20620c0d27 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -488,6 +488,7 @@ static struct {
 	{ trace_clock_local,	"local" },
 	{ trace_clock_global,	"global" },
 	{ trace_clock_counter,	"counter" },
+	ARCH_TRACE_CLOCKS
 };
 
 int trace_clock_id;
-- 
cgit v1.2.3-55-g7522


From 8be0709f10e3dd5d7d07933ad61a9f18c4b93ca5 Mon Sep 17 00:00:00 2001
From: David Sharp
Date: Tue, 13 Nov 2012 12:18:22 -0800
Subject: tracing: Format non-nanosec times from tsc clock without a decimal
 point.

With the addition of the "tsc" clock, formatting timestamps to look like
fractional seconds is misleading. Mark clocks as either in nanoseconds or
not, and format non-nanosecond timestamps as decimal integers.

Tested:
$ cd /sys/kernel/debug/tracing/
$ cat trace_clock
[local] global tsc
$ echo sched_switch > set_event
$ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on
$ cat trace
          <idle>-0     [000]  6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120
           sleep-29964 [000]  6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...
$ echo 1 > options/latency-format
$ cat trace
  <idle>-0       0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120
   sleep-29964   0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...
$ echo tsc > trace_clock
$ cat trace
$ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on
$ echo 0 > options/latency-format
$ cat trace
          <idle>-0     [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120
           sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...
echo 1 > options/latency-format
$ cat trace
  <idle>-0       0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120
   sleep-31128   0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...

v2:
Move arch-specific bits out of generic code.
v4:
Fix x86_32 build due to 64-bit division.

Google-Bug-Id: 6980623
Link: http://lkml.kernel.org/r/1352837903-32191-2-git-send-email-dhsharp@google.com

Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: David Sharp <dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/include/asm/trace_clock.h |  2 +-
 include/linux/ftrace_event.h       |  6 +++
 kernel/trace/trace.c               | 15 ++++++--
 kernel/trace/trace.h               |  4 --
 kernel/trace/trace_output.c        | 78 ++++++++++++++++++++++++++------------
 5 files changed, 72 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/trace_clock.h b/arch/x86/include/asm/trace_clock.h
index 5c1652728b6d..beab86cc282d 100644
--- a/arch/x86/include/asm/trace_clock.h
+++ b/arch/x86/include/asm/trace_clock.h
@@ -9,7 +9,7 @@
 extern u64 notrace trace_clock_x86_tsc(void);
 
 # define ARCH_TRACE_CLOCKS \
-	{ trace_clock_x86_tsc,	"x86-tsc" },
+	{ trace_clock_x86_tsc,	"x86-tsc",	.in_ns = 0 },
 
 #else /* !CONFIG_X86_TSC */
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index b80c8ddfbbdc..a3d489531d83 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -86,6 +86,12 @@ struct trace_iterator {
 	cpumask_var_t		started;
 };
 
+enum trace_iter_flags {
+	TRACE_FILE_LAT_FMT	= 1,
+	TRACE_FILE_ANNOTATE	= 2,
+	TRACE_FILE_TIME_IN_NS	= 4,
+};
+
 
 struct trace_event;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0d20620c0d27..d943e69569cd 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -484,10 +484,11 @@ static const char *trace_options[] = {
 static struct {
 	u64 (*func)(void);
 	const char *name;
+	int in_ns;		/* is this clock in nanoseconds? */
 } trace_clocks[] = {
-	{ trace_clock_local,	"local" },
-	{ trace_clock_global,	"global" },
-	{ trace_clock_counter,	"counter" },
+	{ trace_clock_local,	"local",	1 },
+	{ trace_clock_global,	"global",	1 },
+	{ trace_clock_counter,	"counter",	0 },
 	ARCH_TRACE_CLOCKS
 };
 
@@ -2478,6 +2479,10 @@ __tracing_open(struct inode *inode, struct file *file)
 	if (ring_buffer_overruns(iter->tr->buffer))
 		iter->iter_flags |= TRACE_FILE_ANNOTATE;
 
+	/* Output in nanoseconds only if we are using a clock in nanoseconds. */
+	if (trace_clocks[trace_clock_id].in_ns)
+		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
 	/* stop the trace while dumping */
 	tracing_stop();
 
@@ -3339,6 +3344,10 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	if (trace_flags & TRACE_ITER_LATENCY_FMT)
 		iter->iter_flags |= TRACE_FILE_LAT_FMT;
 
+	/* Output in nanoseconds only if we are using a clock in nanoseconds. */
+	if (trace_clocks[trace_clock_id].in_ns)
+		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
 	iter->cpu_file = cpu_file;
 	iter->tr = &global_trace;
 	mutex_init(&iter->mutex);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 55010ed175f0..c75d7988902c 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -406,10 +406,6 @@ void tracing_stop_sched_switch_record(void);
 void tracing_start_sched_switch_record(void);
 int register_tracer(struct tracer *type);
 int is_tracing_stopped(void);
-enum trace_file_type {
-	TRACE_FILE_LAT_FMT	= 1,
-	TRACE_FILE_ANNOTATE	= 2,
-};
 
 extern cpumask_var_t __read_mostly tracing_buffer_mask;
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 123b189c732c..194d79602dc7 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -610,24 +610,54 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 	return trace_print_lat_fmt(s, entry);
 }
 
-static unsigned long preempt_mark_thresh = 100;
+static unsigned long preempt_mark_thresh_us = 100;
 
 static int
-lat_print_timestamp(struct trace_seq *s, u64 abs_usecs,
-		    unsigned long rel_usecs)
+lat_print_timestamp(struct trace_iterator *iter, u64 next_ts)
 {
-	return trace_seq_printf(s, " %4lldus%c: ", abs_usecs,
-				rel_usecs > preempt_mark_thresh ? '!' :
-				  rel_usecs > 1 ? '+' : ' ');
+	unsigned long verbose = trace_flags & TRACE_ITER_VERBOSE;
+	unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS;
+	unsigned long long abs_ts = iter->ts - iter->tr->time_start;
+	unsigned long long rel_ts = next_ts - iter->ts;
+	struct trace_seq *s = &iter->seq;
+
+	if (in_ns) {
+		abs_ts = ns2usecs(abs_ts);
+		rel_ts = ns2usecs(rel_ts);
+	}
+
+	if (verbose && in_ns) {
+		unsigned long abs_usec = do_div(abs_ts, USEC_PER_MSEC);
+		unsigned long abs_msec = (unsigned long)abs_ts;
+		unsigned long rel_usec = do_div(rel_ts, USEC_PER_MSEC);
+		unsigned long rel_msec = (unsigned long)rel_ts;
+
+		return trace_seq_printf(
+				s, "[%08llx] %ld.%03ldms (+%ld.%03ldms): ",
+				ns2usecs(iter->ts),
+				abs_msec, abs_usec,
+				rel_msec, rel_usec);
+	} else if (verbose && !in_ns) {
+		return trace_seq_printf(
+				s, "[%016llx] %lld (+%lld): ",
+				iter->ts, abs_ts, rel_ts);
+	} else if (!verbose && in_ns) {
+		return trace_seq_printf(
+				s, " %4lldus%c: ",
+				abs_ts,
+				rel_ts > preempt_mark_thresh_us ? '!' :
+				  rel_ts > 1 ? '+' : ' ');
+	} else { /* !verbose && !in_ns */
+		return trace_seq_printf(s, " %4lld: ", abs_ts);
+	}
 }
 
 int trace_print_context(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent;
-	unsigned long long t = ns2usecs(iter->ts);
-	unsigned long usec_rem = do_div(t, USEC_PER_SEC);
-	unsigned long secs = (unsigned long)t;
+	unsigned long long t;
+	unsigned long secs, usec_rem;
 	char comm[TASK_COMM_LEN];
 	int ret;
 
@@ -644,8 +674,13 @@ int trace_print_context(struct trace_iterator *iter)
 			return 0;
 	}
 
-	return trace_seq_printf(s, " %5lu.%06lu: ",
-				secs, usec_rem);
+	if (iter->iter_flags & TRACE_FILE_TIME_IN_NS) {
+		t = ns2usecs(iter->ts);
+		usec_rem = do_div(t, USEC_PER_SEC);
+		secs = (unsigned long)t;
+		return trace_seq_printf(s, " %5lu.%06lu: ", secs, usec_rem);
+	} else
+		return trace_seq_printf(s, " %12llu: ", iter->ts);
 }
 
 int trace_print_lat_context(struct trace_iterator *iter)
@@ -659,36 +694,29 @@ int trace_print_lat_context(struct trace_iterator *iter)
 			   *next_entry = trace_find_next_entry(iter, NULL,
 							       &next_ts);
 	unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE);
-	unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start);
-	unsigned long rel_usecs;
 
 	/* Restore the original ent_size */
 	iter->ent_size = ent_size;
 
 	if (!next_entry)
 		next_ts = iter->ts;
-	rel_usecs = ns2usecs(next_ts - iter->ts);
 
 	if (verbose) {
 		char comm[TASK_COMM_LEN];
 
 		trace_find_cmdline(entry->pid, comm);
 
-		ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08llx]"
-				       " %ld.%03ldms (+%ld.%03ldms): ", comm,
-				       entry->pid, iter->cpu, entry->flags,
-				       entry->preempt_count, iter->idx,
-				       ns2usecs(iter->ts),
-				       abs_usecs / USEC_PER_MSEC,
-				       abs_usecs % USEC_PER_MSEC,
-				       rel_usecs / USEC_PER_MSEC,
-				       rel_usecs % USEC_PER_MSEC);
+		ret = trace_seq_printf(
+				s, "%16s %5d %3d %d %08x %08lx ",
+				comm, entry->pid, iter->cpu, entry->flags,
+				entry->preempt_count, iter->idx);
 	} else {
 		ret = lat_print_generic(s, entry, iter->cpu);
-		if (ret)
-			ret = lat_print_timestamp(s, abs_usecs, rel_usecs);
 	}
 
+	if (ret)
+		ret = lat_print_timestamp(iter, next_ts);
+
 	return ret;
 }
 
-- 
cgit v1.2.3-55-g7522


From 1c7d66732458dc187008e3f5b2f71e019e320fc2 Mon Sep 17 00:00:00 2001
From: Shan Wei
Date: Sat, 3 Nov 2012 12:38:33 +0800
Subject: tracing: Kill unused and puzzled sample code in ftrace.h

When doing per-cpu helper optimizing work, find that this code is so puzzled.
1. It's mark as comment text, maybe a sample function for guidelines
   or a todo work.
2. But, this sample code is odd where struct perf_trace_buf is nonexistent.
   commit ce71b9 delete struct perf_trace_buf definition.

   Author: Frederic Weisbecker <fweisbec@gmail.com>
   Date:   Sun Nov 22 05:26:55 2009 +0100

   tracing: Use the perf recursion protection from trace event

Is it necessary to keep there?
just compile test.

Link: http://lkml.kernel.org/r/50949FC9.6050202@gmail.com

Signed-off-by: Shan Wei <davidshan@tencent.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/ftrace.h | 73 --------------------------------------------------
 1 file changed, 73 deletions(-)

(limited to 'include')

diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 698f2a890322..40dc5e8fe340 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -619,79 +619,6 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-/*
- * Define the insertion callback to perf events
- *
- * The job is very similar to ftrace_raw_event_<call> except that we don't
- * insert in the ring buffer but in a perf counter.
- *
- * static void ftrace_perf_<call>(proto)
- * {
- *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
- *	struct ftrace_event_call *event_call = &event_<call>;
- *	extern void perf_tp_event(int, u64, u64, void *, int);
- *	struct ftrace_raw_##call *entry;
- *	struct perf_trace_buf *trace_buf;
- *	u64 __addr = 0, __count = 1;
- *	unsigned long irq_flags;
- *	struct trace_entry *ent;
- *	int __entry_size;
- *	int __data_size;
- *	int __cpu
- *	int pc;
- *
- *	pc = preempt_count();
- *
- *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
- *
- *	// Below we want to get the aligned size by taking into account
- *	// the u32 field that will later store the buffer size
- *	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
- *			     sizeof(u64));
- *	__entry_size -= sizeof(u32);
- *
- *	// Protect the non nmi buffer
- *	// This also protects the rcu read side
- *	local_irq_save(irq_flags);
- *	__cpu = smp_processor_id();
- *
- *	if (in_nmi())
- *		trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
- *	else
- *		trace_buf = rcu_dereference_sched(perf_trace_buf);
- *
- *	if (!trace_buf)
- *		goto end;
- *
- *	trace_buf = per_cpu_ptr(trace_buf, __cpu);
- *
- * 	// Avoid recursion from perf that could mess up the buffer
- * 	if (trace_buf->recursion++)
- *		goto end_recursion;
- *
- * 	raw_data = trace_buf->buf;
- *
- *	// Make recursion update visible before entering perf_tp_event
- *	// so that we protect from perf recursions.
- *
- *	barrier();
- *
- *	//zero dead bytes from alignment to avoid stack leak to userspace:
- *	*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;
- *	entry = (struct ftrace_raw_<call> *)raw_data;
- *	ent = &entry->ent;
- *	tracing_generic_entry_update(ent, irq_flags, pc);
- *	ent->type = event_call->id;
- *
- *	<tstruct> <- do some jobs with dynamic arrays
- *
- *	<assign>  <- affect our values
- *
- *	perf_tp_event(event_call->id, __addr, __count, entry,
- *		     __entry_size);  <- submit them to perf counter
- *
- * }
- */
 
 #ifdef CONFIG_PERF_EVENTS
 
-- 
cgit v1.2.3-55-g7522


From bb08f76d8419a163b7a4212a0e4ea6bd25acacd1 Mon Sep 17 00:00:00 2001
From: Paul E. McKenney
Date: Sat, 20 Oct 2012 12:33:37 -0700
Subject: rcu: Remove list_for_each_continue_rcu()

The list_for_each_continue_rcu() macro is no longer used, so this commit
removes it.  The list_for_each_entry_continue_rcu() macro should be
used instead.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/RCU/checklist.txt | 17 ++++++++---------
 Documentation/RCU/whatisRCU.txt |  4 +---
 include/linux/rculist.h         | 17 -----------------
 3 files changed, 9 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index cdb20d41a44a..31ef8fe07f82 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -271,15 +271,14 @@ over a rather long period of time, but improvements are always welcome!
 	The same cautions apply to call_rcu_bh() and call_rcu_sched().
 
 9.	All RCU list-traversal primitives, which include
-	rcu_dereference(), list_for_each_entry_rcu(),
-	list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
-	must be either within an RCU read-side critical section or
-	must be protected by appropriate update-side locks.  RCU
-	read-side critical sections are delimited by rcu_read_lock()
-	and rcu_read_unlock(), or by similar primitives such as
-	rcu_read_lock_bh() and rcu_read_unlock_bh(), in which case
-	the matching rcu_dereference() primitive must be used in order
-	to keep lockdep happy, in this case, rcu_dereference_bh().
+	rcu_dereference(), list_for_each_entry_rcu(), and
+	list_for_each_safe_rcu(), must be either within an RCU read-side
+	critical section or must be protected by appropriate update-side
+	locks.	RCU read-side critical sections are delimited by
+	rcu_read_lock() and rcu_read_unlock(), or by similar primitives
+	such as rcu_read_lock_bh() and rcu_read_unlock_bh(), in which
+	case the matching rcu_dereference() primitive must be used in
+	order to keep lockdep happy, in this case, rcu_dereference_bh().
 
 	The reason that it is permissible to use RCU list-traversal
 	primitives when the update-side lock is held is that doing so
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index bf0f6de2aa00..9d30de00d730 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -789,9 +789,7 @@ RCU list traversal:
 	list_for_each_entry_rcu
 	hlist_for_each_entry_rcu
 	hlist_nulls_for_each_entry_rcu
-
-	list_for_each_continue_rcu	(to be deprecated in favor of new
-					 list_for_each_entry_continue_rcu)
+	list_for_each_entry_continue_rcu
 
 RCU pointer/list update:
 
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index e0f0fab20415..c92dd28eaa6c 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -286,23 +286,6 @@ static inline void list_splice_init_rcu(struct list_head *list,
 		&pos->member != (head); \
 		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
-
-/**
- * list_for_each_continue_rcu
- * @pos:	the &struct list_head to use as a loop cursor.
- * @head:	the head for your list.
- *
- * Iterate over an rcu-protected list, continuing after current point.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as list_add_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define list_for_each_continue_rcu(pos, head) \
-	for ((pos) = rcu_dereference_raw(list_next_rcu(pos)); \
-		(pos) != (head); \
-		(pos) = rcu_dereference_raw(list_next_rcu(pos)))
-
 /**
  * list_for_each_entry_continue_rcu - continue iteration over list of given type
  * @pos:	the type * to use as a loop cursor.
-- 
cgit v1.2.3-55-g7522


From f0a0e6f282c72247e7c8ec17c68d528c1bb4d49e Mon Sep 17 00:00:00 2001
From: Paul E. McKenney
Date: Tue, 23 Oct 2012 13:47:01 -0700
Subject: rcu: Clarify memory-ordering properties of grace-period primitives

This commit explicitly states the memory-ordering properties of the
RCU grace-period primitives.  Although these properties were in some
sense implied by the fundmental property of RCU ("a grace period must
wait for all pre-existing RCU read-side critical sections to complete"),
stating it explicitly will be a great labor-saving device.

Reported-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/rcupdate.h | 25 +++++++++++++++++++++++++
 kernel/rcutree.c         | 29 +++++++++++++++++++++++++----
 kernel/rcutree_plugin.h  |  8 ++++++++
 3 files changed, 58 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 7c968e4f929e..6256759fb81e 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -90,6 +90,25 @@ extern void do_trace_rcu_torture_read(char *rcutorturename,
  * that started after call_rcu() was invoked.  RCU read-side critical
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing RCU read-side critical section.  On systems with more
+ * than one CPU, this means that when "func()" is invoked, each CPU is
+ * guaranteed to have executed a full memory barrier since the end of its
+ * last RCU read-side critical section whose beginning preceded the call
+ * to call_rcu().  It also means that each CPU executing an RCU read-side
+ * critical section that continues beyond the start of "func()" must have
+ * executed a memory barrier after the call_rcu() but before the beginning
+ * of that RCU read-side critical section.  Note that these guarantees
+ * include CPUs that are offline, idle, or executing in user mode, as
+ * well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting RCU callback function "func()", then both CPU A and CPU B are
+ * guaranteed to execute a full memory barrier during the time interval
+ * between the call to call_rcu() and the invocation of "func()" -- even
+ * if CPU A and CPU B are the same CPU (but again only if the system has
+ * more than one CPU).
  */
 extern void call_rcu(struct rcu_head *head,
 			      void (*func)(struct rcu_head *head));
@@ -118,6 +137,9 @@ extern void call_rcu(struct rcu_head *head,
  *  OR
  *  - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
  *  These may be nested.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
  */
 extern void call_rcu_bh(struct rcu_head *head,
 			void (*func)(struct rcu_head *head));
@@ -137,6 +159,9 @@ extern void call_rcu_bh(struct rcu_head *head,
  *  OR
  *  anything that disables preemption.
  *  These may be nested.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
  */
 extern void call_rcu_sched(struct rcu_head *head,
 			   void (*func)(struct rcu_head *rcu));
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index e4c2192b47c8..15a2beec320f 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -2228,10 +2228,28 @@ static inline int rcu_blocking_is_gp(void)
  * rcu_read_lock_sched().
  *
  * This means that all preempt_disable code sequences, including NMI and
- * hardware-interrupt handlers, in progress on entry will have completed
- * before this primitive returns.  However, this does not guarantee that
- * softirq handlers will have completed, since in some kernels, these
- * handlers can run in process context, and can block.
+ * non-threaded hardware-interrupt handlers, in progress on entry will
+ * have completed before this primitive returns.  However, this does not
+ * guarantee that softirq handlers will have completed, since in some
+ * kernels, these handlers can run in process context, and can block.
+ *
+ * Note that this guarantee implies further memory-ordering guarantees.
+ * On systems with more than one CPU, when synchronize_sched() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since the
+ * end of its last RCU-sched read-side critical section whose beginning
+ * preceded the call to synchronize_sched().  In addition, each CPU having
+ * an RCU read-side critical section that extends beyond the return from
+ * synchronize_sched() is guaranteed to have executed a full memory barrier
+ * after the beginning of synchronize_sched() and before the beginning of
+ * that RCU read-side critical section.  Note that these guarantees include
+ * CPUs that are offline, idle, or executing in user mode, as well as CPUs
+ * that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_sched(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_sched() -- even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
  *
  * This primitive provides the guarantees made by the (now removed)
  * synchronize_kernel() API.  In contrast, synchronize_rcu() only
@@ -2259,6 +2277,9 @@ EXPORT_SYMBOL_GPL(synchronize_sched);
  * read-side critical sections have completed.  RCU read-side critical
  * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
  * and may be nested.
+ *
+ * See the description of synchronize_sched() for more detailed information
+ * on memory ordering guarantees.
  */
 void synchronize_rcu_bh(void)
 {
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index f92115488187..57e0ef8ed721 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -670,6 +670,9 @@ EXPORT_SYMBOL_GPL(kfree_call_rcu);
  * concurrently with new RCU read-side critical sections that began while
  * synchronize_rcu() was waiting.  RCU read-side critical sections are
  * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
+ *
+ * See the description of synchronize_sched() for more detailed information
+ * on memory ordering guarantees.
  */
 void synchronize_rcu(void)
 {
@@ -875,6 +878,11 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 
 /**
  * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
+ *
+ * Note that this primitive does not necessarily wait for an RCU grace period
+ * to complete.  For example, if there are no RCU callbacks queued anywhere
+ * in the system, then rcu_barrier() is within its rights to return
+ * immediately, without waiting for anything, much less an RCU grace period.
  */
 void rcu_barrier(void)
 {
-- 
cgit v1.2.3-55-g7522


From 2cd451792db174382aaca96c75bc3bf47a6065fe Mon Sep 17 00:00:00 2001
From: Daniel Mack
Date: Wed, 14 Nov 2012 11:14:26 +0800
Subject: spi/omap: fix D0/D1 direction confusion

0384e90b8 ("spi/mcspi: allow configuration of pin directions") did what
it claimed to do the wrong way around. D0/D1 is configured as output by
*clearing* the bits in the conf registers, hence also breaking the
former default behaviour.

Fix this before that change is merged to mainline.

Signed-off-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 Documentation/devicetree/bindings/spi/omap-spi.txt | 6 +++---
 drivers/spi/spi-omap2-mcspi.c                      | 6 +++---
 include/linux/platform_data/spi-omap2-mcspi.h      | 4 ++--
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/spi/omap-spi.txt b/Documentation/devicetree/bindings/spi/omap-spi.txt
index 2ef0a6b85653..938809c6829b 100644
--- a/Documentation/devicetree/bindings/spi/omap-spi.txt
+++ b/Documentation/devicetree/bindings/spi/omap-spi.txt
@@ -6,9 +6,9 @@ Required properties:
   - "ti,omap4-spi" for OMAP4+.
 - ti,spi-num-cs : Number of chipselect supported  by the instance.
 - ti,hwmods: Name of the hwmod associated to the McSPI
-- ti,pindir-d0-in-d1-out: Select the D0 pin as input and D1 as
-			  output. The default is D0 as output and
-			  D1 as input.
+- ti,pindir-d0-out-d1-in: Select the D0 pin as output and D1 as
+			  input. The default is D0 as input and
+			  D1 as output.
 
 Example:
 
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 51046332677c..89f73c425c3d 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -766,7 +766,7 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi,
 	/* standard 4-wire master mode:  SCK, MOSI/out, MISO/in, nCS
 	 * REVISIT: this controller could support SPI_3WIRE mode.
 	 */
-	if (mcspi->pin_dir == MCSPI_PINDIR_D0_OUT_D1_IN) {
+	if (mcspi->pin_dir == MCSPI_PINDIR_D0_IN_D1_OUT) {
 		l &= ~OMAP2_MCSPI_CHCONF_IS;
 		l &= ~OMAP2_MCSPI_CHCONF_DPE1;
 		l |= OMAP2_MCSPI_CHCONF_DPE0;
@@ -1188,8 +1188,8 @@ static int __devinit omap2_mcspi_probe(struct platform_device *pdev)
 		of_property_read_u32(node, "ti,spi-num-cs", &num_cs);
 		master->num_chipselect = num_cs;
 		master->bus_num = bus_num++;
-		if (of_get_property(node, "ti,pindir-d0-in-d1-out", NULL))
-			mcspi->pin_dir = MCSPI_PINDIR_D0_IN_D1_OUT;
+		if (of_get_property(node, "ti,pindir-d0-out-d1-in", NULL))
+			mcspi->pin_dir = MCSPI_PINDIR_D0_OUT_D1_IN;
 	} else {
 		pdata = pdev->dev.platform_data;
 		master->num_chipselect = pdata->num_cs;
diff --git a/include/linux/platform_data/spi-omap2-mcspi.h b/include/linux/platform_data/spi-omap2-mcspi.h
index ce70f7b5a8e1..a65572d53211 100644
--- a/include/linux/platform_data/spi-omap2-mcspi.h
+++ b/include/linux/platform_data/spi-omap2-mcspi.h
@@ -7,8 +7,8 @@
 
 #define OMAP4_MCSPI_REG_OFFSET 0x100
 
-#define MCSPI_PINDIR_D0_OUT_D1_IN	0
-#define MCSPI_PINDIR_D0_IN_D1_OUT	1
+#define MCSPI_PINDIR_D0_IN_D1_OUT	0
+#define MCSPI_PINDIR_D0_OUT_D1_IN	1
 
 struct omap2_mcspi_platform_config {
 	unsigned short	num_cs;
-- 
cgit v1.2.3-55-g7522


From fe1e43f7190da98b396265639845a6cc0d748aad Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Wed, 14 Nov 2012 16:47:10 +0900
Subject: regulator: core: Add regulator_is_supported_voltage_tol()

If consumers wish to set voltages based on a tolerance it stands to reason
that they will also want to query for support in the same manner.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Acked-by: Liam Girdwood <lrg@ti.com>
---
 include/linux/regulator/consumer.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index c43cd3556b1f..49415a23b2d8 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -367,4 +367,12 @@ static inline int regulator_set_voltage_tol(struct regulator *regulator,
 				     new_uV - tol_uV, new_uV + tol_uV);
 }
 
+static inline int regulator_is_supported_voltage_tol(struct regulator *regulator,
+						     int target_uV, int tol_uV)
+{
+	return regulator_is_supported_voltage(regulator,
+					      target_uV - tol_uV,
+					      target_uV + tol_uV);
+}
+
 #endif
-- 
cgit v1.2.3-55-g7522


From 49839dc93970789cea46f5171cd7f6ec11af64c7 Mon Sep 17 00:00:00 2001
From: Paul Walmsley
Date: Tue, 6 Nov 2012 16:31:32 +0000
Subject: Revert "ARM: OMAP: convert I2C driver to PM QoS for MPU latency
 constraints"

This reverts commit 3db11feffc1ad2ab9dea27789e6b5b3032827adc
(ARM: OMAP: convert I2C driver to PM QoS for MPU latency constraints).
This commit causes I2C timeouts to appear on several OMAP3430/3530-based
boards:

  http://marc.info/?l=linux-arm-kernel&m=135071372426971&w=2
  http://marc.info/?l=linux-arm-kernel&m=135067558415214&w=2
  http://marc.info/?l=linux-arm-kernel&m=135216013608196&w=2

and appears to have been sent for merging before one of its prerequisites
was merged:

  http://marc.info/?l=linux-arm-kernel&m=135219411617621&w=2

Signed-off-by: Paul Walmsley <paul@pwsan.com>
Acked-by: Jean Pihet <j-pihet@ti.com>
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
---
 arch/arm/plat-omap/i2c.c      | 21 +++++++++++++++++++++
 drivers/i2c/busses/i2c-omap.c | 32 ++++++++++++++------------------
 include/linux/i2c-omap.h      |  1 +
 3 files changed, 36 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/arm/plat-omap/i2c.c b/arch/arm/plat-omap/i2c.c
index a5683a84c6ee..6013831a043e 100644
--- a/arch/arm/plat-omap/i2c.c
+++ b/arch/arm/plat-omap/i2c.c
@@ -26,12 +26,14 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
+#include <linux/i2c-omap.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/clk.h>
 
 #include <mach/irqs.h>
 #include <plat/i2c.h>
+#include <plat/omap-pm.h>
 #include <plat/omap_device.h>
 
 #define OMAP_I2C_SIZE		0x3f
@@ -127,6 +129,16 @@ static inline int omap1_i2c_add_bus(int bus_id)
 
 
 #ifdef CONFIG_ARCH_OMAP2PLUS
+/*
+ * XXX This function is a temporary compatibility wrapper - only
+ * needed until the I2C driver can be converted to call
+ * omap_pm_set_max_dev_wakeup_lat() and handle a return code.
+ */
+static void omap_pm_set_max_mpu_wakeup_lat_compat(struct device *dev, long t)
+{
+	omap_pm_set_max_mpu_wakeup_lat(dev, t);
+}
+
 static inline int omap2_i2c_add_bus(int bus_id)
 {
 	int l;
@@ -158,6 +170,15 @@ static inline int omap2_i2c_add_bus(int bus_id)
 	dev_attr = (struct omap_i2c_dev_attr *)oh->dev_attr;
 	pdata->flags = dev_attr->flags;
 
+	/*
+	 * When waiting for completion of a i2c transfer, we need to
+	 * set a wake up latency constraint for the MPU. This is to
+	 * ensure quick enough wakeup from idle, when transfer
+	 * completes.
+	 * Only omap3 has support for constraints
+	 */
+	if (cpu_is_omap34xx())
+		pdata->set_mpu_wkup_lat = omap_pm_set_max_mpu_wakeup_lat_compat;
 	pdev = omap_device_build(name, bus_id, oh, pdata,
 			sizeof(struct omap_i2c_bus_platform_data),
 			NULL, 0, 0);
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index db31eaed6ea5..0b0254312d21 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -43,7 +43,6 @@
 #include <linux/slab.h>
 #include <linux/i2c-omap.h>
 #include <linux/pm_runtime.h>
-#include <linux/pm_qos.h>
 
 /* I2C controller revisions */
 #define OMAP_I2C_OMAP1_REV_2		0x20
@@ -187,8 +186,9 @@ struct omap_i2c_dev {
 	int			reg_shift;      /* bit shift for I2C register addresses */
 	struct completion	cmd_complete;
 	struct resource		*ioarea;
-	u32			latency;	/* maximum MPU wkup latency */
-	struct pm_qos_request	pm_qos_request;
+	u32			latency;	/* maximum mpu wkup latency */
+	void			(*set_mpu_wkup_lat)(struct device *dev,
+						    long latency);
 	u32			speed;		/* Speed of bus in kHz */
 	u32			dtrev;		/* extra revision from DT */
 	u32			flags;
@@ -494,7 +494,9 @@ static void omap_i2c_resize_fifo(struct omap_i2c_dev *dev, u8 size, bool is_rx)
 		dev->b_hw = 1; /* Enable hardware fixes */
 
 	/* calculate wakeup latency constraint for MPU */
-	dev->latency = (1000000 * dev->threshold) / (1000 * dev->speed / 8);
+	if (dev->set_mpu_wkup_lat != NULL)
+		dev->latency = (1000000 * dev->threshold) /
+			(1000 * dev->speed / 8);
 }
 
 /*
@@ -629,16 +631,8 @@ omap_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num)
 	if (r < 0)
 		goto out;
 
-	/*
-	 * When waiting for completion of a i2c transfer, we need to
-	 * set a wake up latency constraint for the MPU. This is to
-	 * ensure quick enough wakeup from idle, when transfer
-	 * completes.
-	 */
-	if (dev->latency)
-		pm_qos_add_request(&dev->pm_qos_request,
-				   PM_QOS_CPU_DMA_LATENCY,
-				   dev->latency);
+	if (dev->set_mpu_wkup_lat != NULL)
+		dev->set_mpu_wkup_lat(dev->dev, dev->latency);
 
 	for (i = 0; i < num; i++) {
 		r = omap_i2c_xfer_msg(adap, &msgs[i], (i == (num - 1)));
@@ -646,8 +640,8 @@ omap_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num)
 			break;
 	}
 
-	if (dev->latency)
-		pm_qos_remove_request(&dev->pm_qos_request);
+	if (dev->set_mpu_wkup_lat != NULL)
+		dev->set_mpu_wkup_lat(dev->dev, -1);
 
 	if (r == 0)
 		r = num;
@@ -1104,6 +1098,7 @@ omap_i2c_probe(struct platform_device *pdev)
 	} else if (pdata != NULL) {
 		dev->speed = pdata->clkrate;
 		dev->flags = pdata->flags;
+		dev->set_mpu_wkup_lat = pdata->set_mpu_wkup_lat;
 		dev->dtrev = pdata->rev;
 	}
 
@@ -1159,8 +1154,9 @@ omap_i2c_probe(struct platform_device *pdev)
 			dev->b_hw = 1; /* Enable hardware fixes */
 
 		/* calculate wakeup latency constraint for MPU */
-		dev->latency = (1000000 * dev->fifo_size) /
-			       (1000 * dev->speed / 8);
+		if (dev->set_mpu_wkup_lat != NULL)
+			dev->latency = (1000000 * dev->fifo_size) /
+				       (1000 * dev->speed / 8);
 	}
 
 	/* reset ASAP, clearing any IRQs */
diff --git a/include/linux/i2c-omap.h b/include/linux/i2c-omap.h
index df804ba73e0b..92a0dc75bc74 100644
--- a/include/linux/i2c-omap.h
+++ b/include/linux/i2c-omap.h
@@ -34,6 +34,7 @@ struct omap_i2c_bus_platform_data {
 	u32		clkrate;
 	u32		rev;
 	u32		flags;
+	void		(*set_mpu_wkup_lat)(struct device *dev, long set);
 };
 
 #endif
-- 
cgit v1.2.3-55-g7522


From 45aa2c27ada4829bc91bd80455bc67059ac06bc5 Mon Sep 17 00:00:00 2001
From: Josh Cartwright
Date: Tue, 13 Nov 2012 17:26:48 -0600
Subject: clk: Add support for fundamental zynq clks

Provide simplified models for the necessary clocks on the zynq-7000
platform.  Currently, the PLLs, the CPU clock network, and the basic
peripheral clock networks (for SDIO, SMC, SPI, QSPI, UART) are modelled.

OF bindings are also provided and documented.

Signed-off-by: Josh Cartwright <josh.cartwright@ni.com>
Signed-off-by: Soren Brinkmann <soren.brinkmann@xilinx.com>
Acked-by: Mike Turquette <mturquette@linaro.org>
Acked-by: Michal Simek <michal.simek@xilinx.com>
---
 .../devicetree/bindings/clock/zynq-7000.txt        |  55 +++
 drivers/clk/clk-zynq.c                             | 383 +++++++++++++++++++++
 include/linux/clk/zynq.h                           |  24 ++
 3 files changed, 462 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/zynq-7000.txt
 create mode 100644 drivers/clk/clk-zynq.c
 create mode 100644 include/linux/clk/zynq.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/zynq-7000.txt b/Documentation/devicetree/bindings/clock/zynq-7000.txt
new file mode 100644
index 000000000000..23ae1db1bc13
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/zynq-7000.txt
@@ -0,0 +1,55 @@
+Device Tree Clock bindings for the Zynq 7000 EPP
+
+The Zynq EPP has several different clk providers, each with there own bindings.
+The purpose of this document is to document their usage.
+
+See clock_bindings.txt for more information on the generic clock bindings.
+See Chapter 25 of Zynq TRM for more information about Zynq clocks.
+
+== PLLs ==
+
+Used to describe the ARM_PLL, DDR_PLL, and IO_PLL.
+
+Required properties:
+- #clock-cells : shall be 0 (only one clock is output from this node)
+- compatible : "xlnx,zynq-pll"
+- reg : pair of u32 values, which are the address offsets within the SLCR
+        of the relevant PLL_CTRL register and PLL_CFG register respectively
+- clocks : phandle for parent clock.  should be the phandle for ps_clk
+
+Optional properties:
+- clock-output-names : name of the output clock
+
+Example:
+	armpll: armpll {
+		#clock-cells = <0>;
+		compatible = "xlnx,zynq-pll";
+		clocks = <&ps_clk>;
+		reg = <0x100 0x110>;
+		clock-output-names = "armpll";
+	};
+
+== Peripheral clocks ==
+
+Describes clock node for the SDIO, SMC, SPI, QSPI, and UART clocks.
+
+Required properties:
+- #clock-cells : shall be 1
+- compatible : "xlnx,zynq-periph-clock"
+- reg : a single u32 value, describing the offset within the SLCR where
+        the CLK_CTRL register is found for this peripheral
+- clocks : phandle for parent clocks.  should hold phandles for
+           the IO_PLL, ARM_PLL, and DDR_PLL in order
+- clock-output-names : names of the output clock(s).  For peripherals that have
+                       two output clocks (for example, the UART), two clocks
+                       should be listed.
+
+Example:
+	uart_clk: uart_clk {
+		#clock-cells = <1>;
+		compatible = "xlnx,zynq-periph-clock";
+		clocks = <&iopll &armpll &ddrpll>;
+		reg = <0x154>;
+		clock-output-names = "uart0_ref_clk",
+				     "uart1_ref_clk";
+	};
diff --git a/drivers/clk/clk-zynq.c b/drivers/clk/clk-zynq.c
new file mode 100644
index 000000000000..37a30514fd66
--- /dev/null
+++ b/drivers/clk/clk-zynq.c
@@ -0,0 +1,383 @@
+/*
+ * Copyright (c) 2012 National Instruments
+ *
+ * Josh Cartwright <josh.cartwright@ni.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/clk-provider.h>
+
+static void __iomem *slcr_base;
+
+struct zynq_pll_clk {
+	struct clk_hw	hw;
+	void __iomem	*pll_ctrl;
+	void __iomem	*pll_cfg;
+};
+
+#define to_zynq_pll_clk(hw)	container_of(hw, struct zynq_pll_clk, hw)
+
+#define CTRL_PLL_FDIV(x)	((x) >> 12)
+
+static unsigned long zynq_pll_recalc_rate(struct clk_hw *hw,
+					  unsigned long parent_rate)
+{
+	struct zynq_pll_clk *pll = to_zynq_pll_clk(hw);
+	return parent_rate * CTRL_PLL_FDIV(ioread32(pll->pll_ctrl));
+}
+
+static const struct clk_ops zynq_pll_clk_ops = {
+	.recalc_rate	= zynq_pll_recalc_rate,
+};
+
+static void __init zynq_pll_clk_setup(struct device_node *np)
+{
+	struct clk_init_data init;
+	struct zynq_pll_clk *pll;
+	const char *parent_name;
+	struct clk *clk;
+	u32 regs[2];
+	int ret;
+
+	ret = of_property_read_u32_array(np, "reg", regs, ARRAY_SIZE(regs));
+	if (WARN_ON(ret))
+		return;
+
+	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
+	if (WARN_ON(!pll))
+		return;
+
+	pll->pll_ctrl = slcr_base + regs[0];
+	pll->pll_cfg  = slcr_base + regs[1];
+
+	of_property_read_string(np, "clock-output-names", &init.name);
+
+	init.ops = &zynq_pll_clk_ops;
+	parent_name = of_clk_get_parent_name(np, 0);
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+
+	pll->hw.init = &init;
+
+	clk = clk_register(NULL, &pll->hw);
+	if (WARN_ON(IS_ERR(clk)))
+		return;
+
+	ret = of_clk_add_provider(np, of_clk_src_simple_get, clk);
+	if (WARN_ON(ret))
+		return;
+}
+
+struct zynq_periph_clk {
+	struct clk_hw		hw;
+	struct clk_onecell_data	onecell_data;
+	struct clk		*gates[2];
+	void __iomem		*clk_ctrl;
+	spinlock_t		clkact_lock;
+};
+
+#define to_zynq_periph_clk(hw)	container_of(hw, struct zynq_periph_clk, hw)
+
+static const u8 periph_clk_parent_map[] = {
+	0, 0, 1, 2
+};
+#define PERIPH_CLK_CTRL_SRC(x)	(periph_clk_parent_map[((x) & 0x30) >> 4])
+#define PERIPH_CLK_CTRL_DIV(x)	(((x) & 0x3F00) >> 8)
+
+static unsigned long zynq_periph_recalc_rate(struct clk_hw *hw,
+					     unsigned long parent_rate)
+{
+	struct zynq_periph_clk *periph = to_zynq_periph_clk(hw);
+	return parent_rate / PERIPH_CLK_CTRL_DIV(ioread32(periph->clk_ctrl));
+}
+
+static u8 zynq_periph_get_parent(struct clk_hw *hw)
+{
+	struct zynq_periph_clk *periph = to_zynq_periph_clk(hw);
+	return PERIPH_CLK_CTRL_SRC(ioread32(periph->clk_ctrl));
+}
+
+static const struct clk_ops zynq_periph_clk_ops = {
+	.recalc_rate	= zynq_periph_recalc_rate,
+	.get_parent	= zynq_periph_get_parent,
+};
+
+static void __init zynq_periph_clk_setup(struct device_node *np)
+{
+	struct zynq_periph_clk *periph;
+	const char *parent_names[3];
+	struct clk_init_data init;
+	int clk_num = 0, err;
+	const char *name;
+	struct clk *clk;
+	u32 reg;
+	int i;
+
+	err = of_property_read_u32(np, "reg", &reg);
+	if (WARN_ON(err))
+		return;
+
+	periph = kzalloc(sizeof(*periph), GFP_KERNEL);
+	if (WARN_ON(!periph))
+		return;
+
+	periph->clk_ctrl = slcr_base + reg;
+	spin_lock_init(&periph->clkact_lock);
+
+	init.name = np->name;
+	init.ops = &zynq_periph_clk_ops;
+	for (i = 0; i < ARRAY_SIZE(parent_names); i++)
+		parent_names[i] = of_clk_get_parent_name(np, i);
+	init.parent_names = parent_names;
+	init.num_parents = ARRAY_SIZE(parent_names);
+
+	periph->hw.init = &init;
+
+	clk = clk_register(NULL, &periph->hw);
+	if (WARN_ON(IS_ERR(clk)))
+		return;
+
+	err = of_clk_add_provider(np, of_clk_src_simple_get, clk);
+	if (WARN_ON(err))
+		return;
+
+	err = of_property_read_string_index(np, "clock-output-names", 0,
+					    &name);
+	if (WARN_ON(err))
+		return;
+
+	periph->gates[0] = clk_register_gate(NULL, name, np->name, 0,
+					     periph->clk_ctrl, 0, 0,
+					     &periph->clkact_lock);
+	if (WARN_ON(IS_ERR(periph->gates[0])))
+		return;
+	clk_num++;
+
+	/* some periph clks have 2 downstream gates */
+	err = of_property_read_string_index(np, "clock-output-names", 1,
+					    &name);
+	if (err != -ENODATA) {
+		periph->gates[1] = clk_register_gate(NULL, name, np->name, 0,
+						     periph->clk_ctrl, 1, 0,
+						     &periph->clkact_lock);
+		if (WARN_ON(IS_ERR(periph->gates[1])))
+			return;
+		clk_num++;
+	}
+
+	periph->onecell_data.clks = periph->gates;
+	periph->onecell_data.clk_num = clk_num;
+
+	err = of_clk_add_provider(np, of_clk_src_onecell_get,
+				  &periph->onecell_data);
+	if (WARN_ON(err))
+		return;
+}
+
+/* CPU Clock domain is modelled as a mux with 4 children subclks, whose
+ * derivative rates depend on CLK_621_TRUE
+ */
+
+struct zynq_cpu_clk {
+	struct clk_hw		hw;
+	struct clk_onecell_data	onecell_data;
+	struct clk		*subclks[4];
+	void __iomem		*clk_ctrl;
+	spinlock_t		clkact_lock;
+};
+
+#define to_zynq_cpu_clk(hw)	container_of(hw, struct zynq_cpu_clk, hw)
+
+static const u8 zynq_cpu_clk_parent_map[] = {
+	1, 1, 2, 0
+};
+#define CPU_CLK_SRCSEL(x)	(zynq_cpu_clk_parent_map[(((x) & 0x30) >> 4)])
+#define CPU_CLK_CTRL_DIV(x)	(((x) & 0x3F00) >> 8)
+
+static u8 zynq_cpu_clk_get_parent(struct clk_hw *hw)
+{
+	struct zynq_cpu_clk *cpuclk = to_zynq_cpu_clk(hw);
+	return CPU_CLK_SRCSEL(ioread32(cpuclk->clk_ctrl));
+}
+
+static unsigned long zynq_cpu_clk_recalc_rate(struct clk_hw *hw,
+					      unsigned long parent_rate)
+{
+	struct zynq_cpu_clk *cpuclk = to_zynq_cpu_clk(hw);
+	return parent_rate / CPU_CLK_CTRL_DIV(ioread32(cpuclk->clk_ctrl));
+}
+
+static const struct clk_ops zynq_cpu_clk_ops = {
+	.get_parent	= zynq_cpu_clk_get_parent,
+	.recalc_rate	= zynq_cpu_clk_recalc_rate,
+};
+
+struct zynq_cpu_subclk {
+	struct clk_hw	hw;
+	void __iomem	*clk_621;
+	enum {
+		CPU_SUBCLK_6X4X,
+		CPU_SUBCLK_3X2X,
+		CPU_SUBCLK_2X,
+		CPU_SUBCLK_1X,
+	} which;
+};
+
+#define CLK_621_TRUE(x)	((x) & 1)
+
+#define to_zynq_cpu_subclk(hw)	container_of(hw, struct zynq_cpu_subclk, hw);
+
+static unsigned long zynq_cpu_subclk_recalc_rate(struct clk_hw *hw,
+						 unsigned long parent_rate)
+{
+	unsigned long uninitialized_var(rate);
+	struct zynq_cpu_subclk *subclk;
+	bool is_621;
+
+	subclk = to_zynq_cpu_subclk(hw)
+	is_621 = CLK_621_TRUE(ioread32(subclk->clk_621));
+
+	switch (subclk->which) {
+	case CPU_SUBCLK_6X4X:
+		rate = parent_rate;
+		break;
+	case CPU_SUBCLK_3X2X:
+		rate = parent_rate / 2;
+		break;
+	case CPU_SUBCLK_2X:
+		rate = parent_rate / (is_621 ? 3 : 2);
+		break;
+	case CPU_SUBCLK_1X:
+		rate = parent_rate / (is_621 ? 6 : 4);
+		break;
+	};
+
+	return rate;
+}
+
+static const struct clk_ops zynq_cpu_subclk_ops = {
+	.recalc_rate	= zynq_cpu_subclk_recalc_rate,
+};
+
+static struct clk *zynq_cpu_subclk_setup(struct device_node *np, u8 which,
+					 void __iomem *clk_621)
+{
+	struct zynq_cpu_subclk *subclk;
+	struct clk_init_data init;
+	struct clk *clk;
+	int err;
+
+	err = of_property_read_string_index(np, "clock-output-names",
+					    which, &init.name);
+	if (WARN_ON(err))
+		goto err_read_output_name;
+
+	subclk = kzalloc(sizeof(*subclk), GFP_KERNEL);
+	if (!subclk)
+		goto err_subclk_alloc;
+
+	subclk->clk_621 = clk_621;
+	subclk->which = which;
+
+	init.ops = &zynq_cpu_subclk_ops;
+	init.parent_names = &np->name;
+	init.num_parents = 1;
+
+	subclk->hw.init = &init;
+
+	clk = clk_register(NULL, &subclk->hw);
+	if (WARN_ON(IS_ERR(clk)))
+		goto err_clk_register;
+
+	return clk;
+
+err_clk_register:
+	kfree(subclk);
+err_subclk_alloc:
+err_read_output_name:
+	return ERR_PTR(-EINVAL);
+}
+
+static void __init zynq_cpu_clk_setup(struct device_node *np)
+{
+	struct zynq_cpu_clk *cpuclk;
+	const char *parent_names[3];
+	struct clk_init_data init;
+	void __iomem *clk_621;
+	struct clk *clk;
+	u32 reg[2];
+	int err;
+	int i;
+
+	err = of_property_read_u32_array(np, "reg", reg, ARRAY_SIZE(reg));
+	if (WARN_ON(err))
+		return;
+
+	cpuclk = kzalloc(sizeof(*cpuclk), GFP_KERNEL);
+	if (WARN_ON(!cpuclk))
+		return;
+
+	cpuclk->clk_ctrl = slcr_base + reg[0];
+	clk_621 = slcr_base + reg[1];
+	spin_lock_init(&cpuclk->clkact_lock);
+
+	init.name = np->name;
+	init.ops = &zynq_cpu_clk_ops;
+	for (i = 0; i < ARRAY_SIZE(parent_names); i++)
+		parent_names[i] = of_clk_get_parent_name(np, i);
+	init.parent_names = parent_names;
+	init.num_parents = ARRAY_SIZE(parent_names);
+
+	cpuclk->hw.init = &init;
+
+	clk = clk_register(NULL, &cpuclk->hw);
+	if (WARN_ON(IS_ERR(clk)))
+		return;
+
+	err = of_clk_add_provider(np, of_clk_src_simple_get, clk);
+	if (WARN_ON(err))
+		return;
+
+	for (i = 0; i < 4; i++) {
+		cpuclk->subclks[i] = zynq_cpu_subclk_setup(np, i, clk_621);
+		if (WARN_ON(IS_ERR(cpuclk->subclks[i])))
+			return;
+	}
+
+	cpuclk->onecell_data.clks = cpuclk->subclks;
+	cpuclk->onecell_data.clk_num = i;
+
+	err = of_clk_add_provider(np, of_clk_src_onecell_get,
+				  &cpuclk->onecell_data);
+	if (WARN_ON(err))
+		return;
+}
+
+static const __initconst struct of_device_id zynq_clk_match[] = {
+	{ .compatible = "fixed-clock", .data = of_fixed_clk_setup, },
+	{ .compatible = "xlnx,zynq-pll", .data = zynq_pll_clk_setup, },
+	{ .compatible = "xlnx,zynq-periph-clock",
+		.data = zynq_periph_clk_setup, },
+	{ .compatible = "xlnx,zynq-cpu-clock", .data = zynq_cpu_clk_setup, },
+	{}
+};
+
+void __init xilinx_zynq_clocks_init(void __iomem *slcr)
+{
+	slcr_base = slcr;
+	of_clk_init(zynq_clk_match);
+}
diff --git a/include/linux/clk/zynq.h b/include/linux/clk/zynq.h
new file mode 100644
index 000000000000..56be7cd9aa8b
--- /dev/null
+++ b/include/linux/clk/zynq.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 National Instruments
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef __LINUX_CLK_ZYNQ_H_
+#define __LINUX_CLK_ZYNQ_H_
+
+void __init xilinx_zynq_clocks_init(void __iomem *slcr);
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 2c88ab8c5af7d637d2a9d14b607fa6100fa64236 Mon Sep 17 00:00:00 2001
From: Shubhrajyoti D
Date: Mon, 5 Nov 2012 17:53:39 +0530
Subject: ARM: i2c: omap: Remove the i207 errata flag

The commit [i2c: omap: use revision check for OMAP_I2C_FLAG_APPLY_ERRATA_I207]
uses the revision id instead of the flag. So the flag can be safely removed.

Reviewed-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Shubhrajyoti D <shubhrajyoti@ti.com>
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
---
 arch/arm/mach-omap2/omap_hwmod_2430_data.c | 3 +--
 arch/arm/mach-omap2/omap_hwmod_3xxx_data.c | 9 +++------
 drivers/i2c/busses/i2c-omap.c              | 3 +--
 include/linux/i2c-omap.h                   | 1 -
 4 files changed, 5 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/omap_hwmod_2430_data.c b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
index c455e41b0237..b79ccf6efbe8 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2430_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
@@ -76,8 +76,7 @@ static struct omap_hwmod_class i2c_class = {
 
 static struct omap_i2c_dev_attr i2c_dev_attr = {
 	.fifo_depth	= 8, /* bytes */
-	.flags		= OMAP_I2C_FLAG_APPLY_ERRATA_I207 |
-			  OMAP_I2C_FLAG_BUS_SHIFT_2 |
+	.flags		= OMAP_I2C_FLAG_BUS_SHIFT_2 |
 			  OMAP_I2C_FLAG_FORCE_19200_INT_CLK,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index f67b7ee07dd4..943222c40489 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -791,8 +791,7 @@ static struct omap_hwmod omap3xxx_dss_venc_hwmod = {
 /* I2C1 */
 static struct omap_i2c_dev_attr i2c1_dev_attr = {
 	.fifo_depth	= 8, /* bytes */
-	.flags		= OMAP_I2C_FLAG_APPLY_ERRATA_I207 |
-			  OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
+	.flags		= OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
 			  OMAP_I2C_FLAG_BUS_SHIFT_2,
 };
 
@@ -818,8 +817,7 @@ static struct omap_hwmod omap3xxx_i2c1_hwmod = {
 /* I2C2 */
 static struct omap_i2c_dev_attr i2c2_dev_attr = {
 	.fifo_depth	= 8, /* bytes */
-	.flags = OMAP_I2C_FLAG_APPLY_ERRATA_I207 |
-		 OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
+	.flags = OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
 		 OMAP_I2C_FLAG_BUS_SHIFT_2,
 };
 
@@ -845,8 +843,7 @@ static struct omap_hwmod omap3xxx_i2c2_hwmod = {
 /* I2C3 */
 static struct omap_i2c_dev_attr i2c3_dev_attr = {
 	.fifo_depth	= 64, /* bytes */
-	.flags = OMAP_I2C_FLAG_APPLY_ERRATA_I207 |
-		 OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
+	.flags = OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
 		 OMAP_I2C_FLAG_BUS_SHIFT_2,
 };
 
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 0ca50e71731b..11e645ab1e79 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1028,8 +1028,7 @@ static const struct i2c_algorithm omap_i2c_algo = {
 #ifdef CONFIG_OF
 static struct omap_i2c_bus_platform_data omap3_pdata = {
 	.rev = OMAP_I2C_IP_VERSION_1,
-	.flags = OMAP_I2C_FLAG_APPLY_ERRATA_I207 |
-		 OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
+	.flags = OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
 		 OMAP_I2C_FLAG_BUS_SHIFT_2,
 };
 
diff --git a/include/linux/i2c-omap.h b/include/linux/i2c-omap.h
index 92a0dc75bc74..1b25c04f82d9 100644
--- a/include/linux/i2c-omap.h
+++ b/include/linux/i2c-omap.h
@@ -21,7 +21,6 @@
 #define OMAP_I2C_FLAG_SIMPLE_CLOCK		BIT(1)
 #define OMAP_I2C_FLAG_16BIT_DATA_REG		BIT(2)
 #define OMAP_I2C_FLAG_RESET_REGS_POSTIDLE	BIT(3)
-#define OMAP_I2C_FLAG_APPLY_ERRATA_I207	BIT(4)
 #define OMAP_I2C_FLAG_ALWAYS_ARMXOR_CLK	BIT(5)
 #define OMAP_I2C_FLAG_FORCE_19200_INT_CLK	BIT(6)
 /* how the CPU address bus must be translated for I2C unit access */
-- 
cgit v1.2.3-55-g7522


From bdda27fb98463244f056852f800bbce7db67dc4a Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Fri, 26 Oct 2012 13:40:04 +0200
Subject: ACPI / PM: Fix device PM kernedoc comments and #ifdefs

The kerneldoc comments for acpi_pm_device_sleep_state(),
acpi_pm_device_run_wake(), and acpi_pm_device_sleep_wake() are
outdated or otherwise inaccurate and/or don't follow the common
kerneldoc patterns, so fix them.

Additionally, notice that acpi_pm_device_run_wake() should be under
CONFIG_PM_RUNTIME rather than under CONFIG_PM_SLEEP, so fix that too.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/sleep.c    | 53 ++++++++++++++++++++++---------------------------
 include/acpi/acpi_bus.h |  8 ++++++--
 2 files changed, 30 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 69134653909c..4defa0297ee4 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -684,28 +684,21 @@ int acpi_suspend(u32 acpi_state)
 
 #ifdef CONFIG_PM
 /**
- *	acpi_pm_device_sleep_state - return preferred power state of ACPI device
- *		in the system sleep state given by %acpi_target_sleep_state
- *	@dev: device to examine; its driver model wakeup flags control
- *		whether it should be able to wake up the system
- *	@d_min_p: used to store the upper limit of allowed states range
- *	@d_max_in: specify the lowest allowed states
- *	Return value: preferred power state of the device on success, -ENODEV
- *	(ie. if there's no 'struct acpi_device' for @dev) or -EINVAL on failure
+ * acpi_pm_device_sleep_state - Get preferred power state of ACPI device.
+ * @dev: Device whose preferred target power state to return.
+ * @d_min_p: Location to store the upper limit of the allowed states range.
+ * @d_max_in: Deepest low-power state to take into consideration.
+ * Return value: Preferred power state of the device on success, -ENODEV
+ * (if there's no 'struct acpi_device' for @dev) or -EINVAL on failure
  *
- *	Find the lowest power (highest number) ACPI device power state that
- *	device @dev can be in while the system is in the sleep state represented
- *	by %acpi_target_sleep_state.  If @wake is nonzero, the device should be
- *	able to wake up the system from this sleep state.  If @d_min_p is set,
- *	the highest power (lowest number) device power state of @dev allowed
- *	in this system sleep state is stored at the location pointed to by it.
+ * Find the lowest power (highest number) ACPI device power state that the
+ * device can be in while the system is in the sleep state represented
+ * by %acpi_target_sleep_state.  If @d_min_p is set, the highest power (lowest
+ * number) device power state that @dev can be in for the given system sleep
+ * state is stored at the location pointed to by it.
  *
- *	The caller must ensure that @dev is valid before using this function.
- *	The caller is also responsible for figuring out if the device is
- *	supposed to be able to wake up the system and passing this information
- *	via @wake.
+ * The caller must ensure that @dev is valid before using this function.
  */
-
 int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p, int d_max_in)
 {
 	acpi_handle handle = DEVICE_ACPI_HANDLE(dev);
@@ -797,14 +790,15 @@ int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p, int d_max_in)
 EXPORT_SYMBOL(acpi_pm_device_sleep_state);
 #endif /* CONFIG_PM */
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM_RUNTIME
 /**
- * acpi_pm_device_run_wake - Enable/disable wake-up for given device.
- * @phys_dev: Device to enable/disable the platform to wake-up the system for.
- * @enable: Whether enable or disable the wake-up functionality.
+ * acpi_pm_device_run_wake - Enable/disable remote wakeup for given device.
+ * @phys_dev: Device to enable/disable the platform to wake up.
+ * @enable: Whether to enable or disable the wakeup functionality.
  *
- * Find the ACPI device object corresponding to @pci_dev and try to
- * enable/disable the GPE associated with it.
+ * Find the ACPI device object corresponding to @phys_dev and try to
+ * enable/disable the GPE associated with it, so that it can generate
+ * wakeup signals for the device in response to external (remote) events.
  */
 int acpi_pm_device_run_wake(struct device *phys_dev, bool enable)
 {
@@ -832,12 +826,13 @@ int acpi_pm_device_run_wake(struct device *phys_dev, bool enable)
 	return 0;
 }
 EXPORT_SYMBOL(acpi_pm_device_run_wake);
+#endif /* CONFIG_PM_RUNTIME */
 
+#ifdef CONFIG_PM_SLEEP
 /**
- *	acpi_pm_device_sleep_wake - enable or disable the system wake-up
- *                                  capability of given device
- *	@dev: device to handle
- *	@enable: 'true' - enable, 'false' - disable the wake-up capability
+ * acpi_pm_device_sleep_wake - Enable or disable device to wake up the system.
+ * @dev: Device to enable/desible to wake up the system from sleep states.
+ * @enable: Whether to enable or disable @dev to wake up the system.
  */
 int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
 {
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 0daa0fbd8654..72053db9c2ec 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -426,14 +426,18 @@ static inline int acpi_pm_device_sleep_state(struct device *d, int *p, int m)
 }
 #endif
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM_RUNTIME
 int acpi_pm_device_run_wake(struct device *, bool);
-int acpi_pm_device_sleep_wake(struct device *, bool);
 #else
 static inline int acpi_pm_device_run_wake(struct device *dev, bool enable)
 {
 	return -ENODEV;
 }
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+int acpi_pm_device_sleep_wake(struct device *, bool);
+#else
 static inline int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
 {
 	return -ENODEV;
-- 
cgit v1.2.3-55-g7522


From ec2cd81ccfc055155ef4ca673f207168f516d287 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Fri, 2 Nov 2012 01:40:09 +0100
Subject: ACPI / PM: Move routines for adding/removing device wakeup notifiers

ACPI routines for adding and removing device wakeup notifiers are
currently defined in a PCI-specific file, but they will be necessary
for non-PCI devices too, so move them to a separate file under
drivers/acpi and rename them to indicate their ACPI origins.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/Makefile    |  3 +-
 drivers/acpi/device_pm.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/pci/pci-acpi.c   | 71 +++----------------------------------
 include/acpi/acpi_bus.h  | 15 ++++++++
 4 files changed, 112 insertions(+), 68 deletions(-)
 create mode 100644 drivers/acpi/device_pm.c

(limited to 'include')

diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 82422fe90f81..a2711fae62d8 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -21,9 +21,10 @@ obj-y				+= acpi.o \
 acpi-y				+= osl.o utils.o reboot.o
 acpi-y				+= nvs.o
 
-# sleep related files
+# Power management related files
 acpi-y				+= wakeup.o
 acpi-y				+= sleep.o
+acpi-$(CONFIG_PM)		+= device_pm.o
 acpi-$(CONFIG_ACPI_SLEEP)	+= proc.o
 
 
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
new file mode 100644
index 000000000000..2d2e0bc8891b
--- /dev/null
+++ b/drivers/acpi/device_pm.c
@@ -0,0 +1,91 @@
+/*
+ * drivers/acpi/device_pm.c - ACPI device power management routines.
+ *
+ * Copyright (C) 2012, Intel Corp.
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as published
+ *  by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/device.h>
+#include <linux/mutex.h>
+
+#include <acpi/acpi.h>
+#include <acpi/acpi_bus.h>
+
+static DEFINE_MUTEX(acpi_pm_notifier_lock);
+
+/**
+ * acpi_add_pm_notifier - Register PM notifier for given ACPI device.
+ * @adev: ACPI device to add the notifier for.
+ * @context: Context information to pass to the notifier routine.
+ *
+ * NOTE: @adev need not be a run-wake or wakeup device to be a valid source of
+ * PM wakeup events.  For example, wakeup events may be generated for bridges
+ * if one of the devices below the bridge is signaling wakeup, even if the
+ * bridge itself doesn't have a wakeup GPE associated with it.
+ */
+acpi_status acpi_add_pm_notifier(struct acpi_device *adev,
+				 acpi_notify_handler handler, void *context)
+{
+	acpi_status status = AE_ALREADY_EXISTS;
+
+	mutex_lock(&acpi_pm_notifier_lock);
+
+	if (adev->wakeup.flags.notifier_present)
+		goto out;
+
+	status = acpi_install_notify_handler(adev->handle,
+					     ACPI_SYSTEM_NOTIFY,
+					     handler, context);
+	if (ACPI_FAILURE(status))
+		goto out;
+
+	adev->wakeup.flags.notifier_present = true;
+
+ out:
+	mutex_unlock(&acpi_pm_notifier_lock);
+	return status;
+}
+
+/**
+ * acpi_remove_pm_notifier - Unregister PM notifier from given ACPI device.
+ * @adev: ACPI device to remove the notifier from.
+ */
+acpi_status acpi_remove_pm_notifier(struct acpi_device *adev,
+				    acpi_notify_handler handler)
+{
+	acpi_status status = AE_BAD_PARAMETER;
+
+	mutex_lock(&acpi_pm_notifier_lock);
+
+	if (!adev->wakeup.flags.notifier_present)
+		goto out;
+
+	status = acpi_remove_notify_handler(adev->handle,
+					    ACPI_SYSTEM_NOTIFY,
+					    handler);
+	if (ACPI_FAILURE(status))
+		goto out;
+
+	adev->wakeup.flags.notifier_present = false;
+
+ out:
+	mutex_unlock(&acpi_pm_notifier_lock);
+	return status;
+}
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 63d6618a4804..1af4008182fd 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -20,8 +20,6 @@
 #include <linux/pm_qos.h>
 #include "pci.h"
 
-static DEFINE_MUTEX(pci_acpi_pm_notify_mtx);
-
 /**
  * pci_acpi_wake_bus - Wake-up notification handler for root buses.
  * @handle: ACPI handle of a device the notification is for.
@@ -68,67 +66,6 @@ static void pci_acpi_wake_dev(acpi_handle handle, u32 event, void *context)
 		pci_pme_wakeup_bus(pci_dev->subordinate);
 }
 
-/**
- * add_pm_notifier - Register PM notifier for given ACPI device.
- * @dev: ACPI device to add the notifier for.
- * @context: PCI device or bus to check for PME status if an event is signaled.
- *
- * NOTE: @dev need not be a run-wake or wake-up device to be a valid source of
- * PM wake-up events.  For example, wake-up events may be generated for bridges
- * if one of the devices below the bridge is signaling PME, even if the bridge
- * itself doesn't have a wake-up GPE associated with it.
- */
-static acpi_status add_pm_notifier(struct acpi_device *dev,
-				   acpi_notify_handler handler,
-				   void *context)
-{
-	acpi_status status = AE_ALREADY_EXISTS;
-
-	mutex_lock(&pci_acpi_pm_notify_mtx);
-
-	if (dev->wakeup.flags.notifier_present)
-		goto out;
-
-	status = acpi_install_notify_handler(dev->handle,
-					     ACPI_SYSTEM_NOTIFY,
-					     handler, context);
-	if (ACPI_FAILURE(status))
-		goto out;
-
-	dev->wakeup.flags.notifier_present = true;
-
- out:
-	mutex_unlock(&pci_acpi_pm_notify_mtx);
-	return status;
-}
-
-/**
- * remove_pm_notifier - Unregister PM notifier from given ACPI device.
- * @dev: ACPI device to remove the notifier from.
- */
-static acpi_status remove_pm_notifier(struct acpi_device *dev,
-				      acpi_notify_handler handler)
-{
-	acpi_status status = AE_BAD_PARAMETER;
-
-	mutex_lock(&pci_acpi_pm_notify_mtx);
-
-	if (!dev->wakeup.flags.notifier_present)
-		goto out;
-
-	status = acpi_remove_notify_handler(dev->handle,
-					    ACPI_SYSTEM_NOTIFY,
-					    handler);
-	if (ACPI_FAILURE(status))
-		goto out;
-
-	dev->wakeup.flags.notifier_present = false;
-
- out:
-	mutex_unlock(&pci_acpi_pm_notify_mtx);
-	return status;
-}
-
 /**
  * pci_acpi_add_bus_pm_notifier - Register PM notifier for given PCI bus.
  * @dev: ACPI device to add the notifier for.
@@ -137,7 +74,7 @@ static acpi_status remove_pm_notifier(struct acpi_device *dev,
 acpi_status pci_acpi_add_bus_pm_notifier(struct acpi_device *dev,
 					 struct pci_bus *pci_bus)
 {
-	return add_pm_notifier(dev, pci_acpi_wake_bus, pci_bus);
+	return acpi_add_pm_notifier(dev, pci_acpi_wake_bus, pci_bus);
 }
 
 /**
@@ -146,7 +83,7 @@ acpi_status pci_acpi_add_bus_pm_notifier(struct acpi_device *dev,
  */
 acpi_status pci_acpi_remove_bus_pm_notifier(struct acpi_device *dev)
 {
-	return remove_pm_notifier(dev, pci_acpi_wake_bus);
+	return acpi_remove_pm_notifier(dev, pci_acpi_wake_bus);
 }
 
 /**
@@ -157,7 +94,7 @@ acpi_status pci_acpi_remove_bus_pm_notifier(struct acpi_device *dev)
 acpi_status pci_acpi_add_pm_notifier(struct acpi_device *dev,
 				     struct pci_dev *pci_dev)
 {
-	return add_pm_notifier(dev, pci_acpi_wake_dev, pci_dev);
+	return acpi_add_pm_notifier(dev, pci_acpi_wake_dev, pci_dev);
 }
 
 /**
@@ -166,7 +103,7 @@ acpi_status pci_acpi_add_pm_notifier(struct acpi_device *dev,
  */
 acpi_status pci_acpi_remove_pm_notifier(struct acpi_device *dev)
 {
-	return remove_pm_notifier(dev, pci_acpi_wake_dev);
+	return acpi_remove_pm_notifier(dev, pci_acpi_wake_dev);
 }
 
 phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle)
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 72053db9c2ec..6983272f9d02 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -416,8 +416,23 @@ int acpi_enable_wakeup_device_power(struct acpi_device *dev, int state);
 int acpi_disable_wakeup_device_power(struct acpi_device *dev);
 
 #ifdef CONFIG_PM
+acpi_status acpi_add_pm_notifier(struct acpi_device *adev,
+				 acpi_notify_handler handler, void *context);
+acpi_status acpi_remove_pm_notifier(struct acpi_device *adev,
+				    acpi_notify_handler handler);
 int acpi_pm_device_sleep_state(struct device *, int *, int);
 #else
+static inline acpi_status acpi_add_pm_notifier(struct acpi_device *adev,
+					       acpi_notify_handler handler,
+					       void *context)
+{
+	return AE_SUPPORT;
+}
+static inline acpi_status acpi_remove_pm_notifier(struct acpi_device *adev,
+						  acpi_notify_handler handler)
+{
+	return AE_SUPPORT;
+}
 static inline int acpi_pm_device_sleep_state(struct device *d, int *p, int m)
 {
 	if (p)
-- 
cgit v1.2.3-55-g7522


From 86b3832c64b6d01092216d84dc6a6b300875d0bb Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Fri, 2 Nov 2012 01:40:18 +0100
Subject: ACPI / PM: Move device power state selection routine to device_pm.c

The ACPI function for choosing device power state is now located
in drivers/acpi/sleep.c, but drivers/acpi/device_pm.c is a more
logical place for it, so move it there.

However, instead of moving the function entirely, move its core only
under a different name and with a different list of arguments, so
that it is more flexible, and leave a wrapper around it in the
original location.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/device_pm.c | 107 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/acpi/sleep.c     |  88 ++------------------------------------
 include/acpi/acpi_bus.h  |  15 ++++++-
 3 files changed, 124 insertions(+), 86 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 2d2e0bc8891b..c017b801171c 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -23,7 +23,9 @@
  */
 
 #include <linux/device.h>
+#include <linux/export.h>
 #include <linux/mutex.h>
+#include <linux/pm_qos.h>
 
 #include <acpi/acpi.h>
 #include <acpi/acpi_bus.h>
@@ -89,3 +91,108 @@ acpi_status acpi_remove_pm_notifier(struct acpi_device *adev,
 	mutex_unlock(&acpi_pm_notifier_lock);
 	return status;
 }
+
+/**
+ * acpi_device_power_state - Get preferred power state of ACPI device.
+ * @dev: Device whose preferred target power state to return.
+ * @adev: ACPI device node corresponding to @dev.
+ * @target_state: System state to match the resultant device state.
+ * @d_max_in: Deepest low-power state to take into consideration.
+ * @d_min_p: Location to store the upper limit of the allowed states range.
+ * Return value: Preferred power state of the device on success, -ENODEV
+ * (if there's no 'struct acpi_device' for @dev) or -EINVAL on failure
+ *
+ * Find the lowest power (highest number) ACPI device power state that the
+ * device can be in while the system is in the state represented by
+ * @target_state.  If @d_min_p is set, the highest power (lowest number) device
+ * power state that @dev can be in for the given system sleep state is stored
+ * at the location pointed to by it.
+ *
+ * Callers must ensure that @dev and @adev are valid pointers and that @adev
+ * actually corresponds to @dev before using this function.
+ */
+int acpi_device_power_state(struct device *dev, struct acpi_device *adev,
+			    u32 target_state, int d_max_in, int *d_min_p)
+{
+	char acpi_method[] = "_SxD";
+	unsigned long long d_min, d_max;
+	bool wakeup = false;
+
+	if (d_max_in < ACPI_STATE_D0 || d_max_in > ACPI_STATE_D3)
+		return -EINVAL;
+
+	if (d_max_in > ACPI_STATE_D3_HOT) {
+		enum pm_qos_flags_status stat;
+
+		stat = dev_pm_qos_flags(dev, PM_QOS_FLAG_NO_POWER_OFF);
+		if (stat == PM_QOS_FLAGS_ALL)
+			d_max_in = ACPI_STATE_D3_HOT;
+	}
+
+	acpi_method[2] = '0' + target_state;
+	/*
+	 * If the sleep state is S0, the lowest limit from ACPI is D3,
+	 * but if the device has _S0W, we will use the value from _S0W
+	 * as the lowest limit from ACPI.  Finally, we will constrain
+	 * the lowest limit with the specified one.
+	 */
+	d_min = ACPI_STATE_D0;
+	d_max = ACPI_STATE_D3;
+
+	/*
+	 * If present, _SxD methods return the minimum D-state (highest power
+	 * state) we can use for the corresponding S-states.  Otherwise, the
+	 * minimum D-state is D0 (ACPI 3.x).
+	 *
+	 * NOTE: We rely on acpi_evaluate_integer() not clobbering the integer
+	 * provided -- that's our fault recovery, we ignore retval.
+	 */
+	if (target_state > ACPI_STATE_S0) {
+		acpi_evaluate_integer(adev->handle, acpi_method, NULL, &d_min);
+		wakeup = device_may_wakeup(dev) && adev->wakeup.flags.valid
+			&& adev->wakeup.sleep_state >= target_state;
+	} else if (dev_pm_qos_flags(dev, PM_QOS_FLAG_REMOTE_WAKEUP) !=
+			PM_QOS_FLAGS_NONE) {
+		wakeup = adev->wakeup.flags.valid;
+	}
+
+	/*
+	 * If _PRW says we can wake up the system from the target sleep state,
+	 * the D-state returned by _SxD is sufficient for that (we assume a
+	 * wakeup-aware driver if wake is set).  Still, if _SxW exists
+	 * (ACPI 3.x), it should return the maximum (lowest power) D-state that
+	 * can wake the system.  _S0W may be valid, too.
+	 */
+	if (wakeup) {
+		acpi_status status;
+
+		acpi_method[3] = 'W';
+		status = acpi_evaluate_integer(adev->handle, acpi_method, NULL,
+						&d_max);
+		if (ACPI_FAILURE(status)) {
+			if (target_state != ACPI_STATE_S0 ||
+			    status != AE_NOT_FOUND)
+				d_max = d_min;
+		} else if (d_max < d_min) {
+			/* Warn the user of the broken DSDT */
+			printk(KERN_WARNING "ACPI: Wrong value from %s\n",
+				acpi_method);
+			/* Sanitize it */
+			d_min = d_max;
+		}
+	}
+
+	if (d_max_in < d_min)
+		return -EINVAL;
+	if (d_min_p)
+		*d_min_p = d_min;
+	/* constrain d_max with specified lowest limit (max number) */
+	if (d_max > d_max_in) {
+		for (d_max = d_max_in; d_max > d_min; d_max--) {
+			if (adev->power.states[d_max].flags.valid)
+				break;
+		}
+	}
+	return d_max;
+}
+EXPORT_SYMBOL_GPL(acpi_device_power_state);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 4defa0297ee4..fa20d0171887 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -19,7 +19,6 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
-#include <linux/pm_qos.h>
 
 #include <asm/io.h>
 
@@ -691,101 +690,20 @@ int acpi_suspend(u32 acpi_state)
  * Return value: Preferred power state of the device on success, -ENODEV
  * (if there's no 'struct acpi_device' for @dev) or -EINVAL on failure
  *
- * Find the lowest power (highest number) ACPI device power state that the
- * device can be in while the system is in the sleep state represented
- * by %acpi_target_sleep_state.  If @d_min_p is set, the highest power (lowest
- * number) device power state that @dev can be in for the given system sleep
- * state is stored at the location pointed to by it.
- *
  * The caller must ensure that @dev is valid before using this function.
  */
 int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p, int d_max_in)
 {
 	acpi_handle handle = DEVICE_ACPI_HANDLE(dev);
 	struct acpi_device *adev;
-	char acpi_method[] = "_SxD";
-	unsigned long long d_min, d_max;
-	bool wakeup = false;
 
-	if (d_max_in < ACPI_STATE_D0 || d_max_in > ACPI_STATE_D3)
-		return -EINVAL;
 	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &adev))) {
-		printk(KERN_DEBUG "ACPI handle has no context!\n");
+		dev_dbg(dev, "ACPI handle without context in %s!\n", __func__);
 		return -ENODEV;
 	}
-	if (d_max_in > ACPI_STATE_D3_HOT) {
-		enum pm_qos_flags_status stat;
-
-		stat = dev_pm_qos_flags(dev, PM_QOS_FLAG_NO_POWER_OFF);
-		if (stat == PM_QOS_FLAGS_ALL)
-			d_max_in = ACPI_STATE_D3_HOT;
-	}
-
-	acpi_method[2] = '0' + acpi_target_sleep_state;
-	/*
-	 * If the sleep state is S0, the lowest limit from ACPI is D3,
-	 * but if the device has _S0W, we will use the value from _S0W
-	 * as the lowest limit from ACPI.  Finally, we will constrain
-	 * the lowest limit with the specified one.
-	 */
-	d_min = ACPI_STATE_D0;
-	d_max = ACPI_STATE_D3;
-
-	/*
-	 * If present, _SxD methods return the minimum D-state (highest power
-	 * state) we can use for the corresponding S-states.  Otherwise, the
-	 * minimum D-state is D0 (ACPI 3.x).
-	 *
-	 * NOTE: We rely on acpi_evaluate_integer() not clobbering the integer
-	 * provided -- that's our fault recovery, we ignore retval.
-	 */
-	if (acpi_target_sleep_state > ACPI_STATE_S0) {
-		acpi_evaluate_integer(handle, acpi_method, NULL, &d_min);
-		wakeup = device_may_wakeup(dev) && adev->wakeup.flags.valid
-			&& adev->wakeup.sleep_state >= acpi_target_sleep_state;
-	} else if (dev_pm_qos_flags(dev, PM_QOS_FLAG_REMOTE_WAKEUP) !=
-			PM_QOS_FLAGS_NONE) {
-		wakeup = adev->wakeup.flags.valid;
-	}
-
-	/*
-	 * If _PRW says we can wake up the system from the target sleep state,
-	 * the D-state returned by _SxD is sufficient for that (we assume a
-	 * wakeup-aware driver if wake is set).  Still, if _SxW exists
-	 * (ACPI 3.x), it should return the maximum (lowest power) D-state that
-	 * can wake the system.  _S0W may be valid, too.
-	 */
-	if (wakeup) {
-		acpi_status status;
-
-		acpi_method[3] = 'W';
-		status = acpi_evaluate_integer(handle, acpi_method, NULL,
-						&d_max);
-		if (ACPI_FAILURE(status)) {
-			if (acpi_target_sleep_state != ACPI_STATE_S0 ||
-			    status != AE_NOT_FOUND)
-				d_max = d_min;
-		} else if (d_max < d_min) {
-			/* Warn the user of the broken DSDT */
-			printk(KERN_WARNING "ACPI: Wrong value from %s\n",
-				acpi_method);
-			/* Sanitize it */
-			d_min = d_max;
-		}
-	}
 
-	if (d_max_in < d_min)
-		return -EINVAL;
-	if (d_min_p)
-		*d_min_p = d_min;
-	/* constrain d_max with specified lowest limit (max number) */
-	if (d_max > d_max_in) {
-		for (d_max = d_max_in; d_max > d_min; d_max--) {
-			if (adev->power.states[d_max].flags.valid)
-				break;
-		}
-	}
-	return d_max;
+	return acpi_device_power_state(dev, adev, acpi_target_sleep_state,
+				       d_max_in, d_min_p);
 }
 EXPORT_SYMBOL(acpi_pm_device_sleep_state);
 #endif /* CONFIG_PM */
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 6983272f9d02..a8080dfe7183 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -420,6 +420,8 @@ acpi_status acpi_add_pm_notifier(struct acpi_device *adev,
 				 acpi_notify_handler handler, void *context);
 acpi_status acpi_remove_pm_notifier(struct acpi_device *adev,
 				    acpi_notify_handler handler);
+int acpi_device_power_state(struct device *dev, struct acpi_device *adev,
+			    u32 target_state, int d_max_in, int *d_min_p);
 int acpi_pm_device_sleep_state(struct device *, int *, int);
 #else
 static inline acpi_status acpi_add_pm_notifier(struct acpi_device *adev,
@@ -433,12 +435,23 @@ static inline acpi_status acpi_remove_pm_notifier(struct acpi_device *adev,
 {
 	return AE_SUPPORT;
 }
-static inline int acpi_pm_device_sleep_state(struct device *d, int *p, int m)
+static inline int __acpi_device_power_state(int m, int *p)
 {
 	if (p)
 		*p = ACPI_STATE_D0;
 	return (m >= ACPI_STATE_D0 && m <= ACPI_STATE_D3) ? m : ACPI_STATE_D0;
 }
+static inline int acpi_device_power_state(struct device *dev,
+					  struct acpi_device *adev,
+					  u32 target_state, int d_max_in,
+					  int *d_min_p)
+{
+	return __acpi_device_power_state(d_max_in, d_min_p);
+}
+static inline int acpi_pm_device_sleep_state(struct device *d, int *p, int m)
+{
+	return __acpi_device_power_state(m, p);
+}
 #endif
 
 #ifdef CONFIG_PM_RUNTIME
-- 
cgit v1.2.3-55-g7522


From dee8370cc87e505ef39567f0974e73d59e75d76b Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Fri, 2 Nov 2012 01:40:36 +0100
Subject: ACPI / PM: Split device wakeup management routines

Two device wakeup management routines in device_pm.c and sleep.c,
acpi_pm_device_run_wake() and acpi_pm_device_sleep_wake(), take a
device pointer argument and use it to obtain the ACPI handle of the
corresponding ACPI namespace node.  That handle is then used to get
the address of the struct acpi_device object corresponding to the
struct device passed as the argument.

Unfortunately, that last operation may be costly, because it involves
taking the global ACPI namespace mutex, so it shouldn't be carried
out too often.  However, the callers of those routines usually call
them in a row with acpi_pm_device_sleep_state() which also takes that
mutex for the same reason, so it would be more efficient if they ran
acpi_bus_get_device() themselves to obtain a pointer to the struct
acpi_device object in question and then passed that pointer to the
appropriate PM routines.

To make that possible, split each of the PM routines mentioned above
in two parts, one taking a struct acpi_device pointer argument and
the other implementing the current interface for compatibility.

Additionally, change acpi_pm_device_run_wake() to actually return
an error code if there is an error while setting up runtime remote
wakeup for the device.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/device_pm.c | 74 +++++++++++++++++++++++++++++++++++++-----------
 drivers/acpi/sleep.c     |  8 ++----
 include/acpi/acpi_bus.h  | 11 +++++++
 3 files changed, 71 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 81052981045e..b4f03f91b0b0 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -200,38 +200,78 @@ EXPORT_SYMBOL_GPL(acpi_device_power_state);
 
 #ifdef CONFIG_PM_RUNTIME
 /**
- * acpi_pm_device_run_wake - Enable/disable remote wakeup for given device.
- * @phys_dev: Device to enable/disable the platform to wake up.
+ * __acpi_device_run_wake - Enable/disable runtime remote wakeup for device.
+ * @adev: ACPI device to enable/disable the remote wakeup for.
  * @enable: Whether to enable or disable the wakeup functionality.
  *
- * Find the ACPI device object corresponding to @phys_dev and try to
- * enable/disable the GPE associated with it, so that it can generate
- * wakeup signals for the device in response to external (remote) events.
+ * Enable/disable the GPE associated with @adev so that it can generate
+ * wakeup signals for the device in response to external (remote) events and
+ * enable/disable device wakeup power.
+ *
+ * Callers must ensure that @adev is a valid ACPI device node before executing
+ * this function.
+ */
+int __acpi_device_run_wake(struct acpi_device *adev, bool enable)
+{
+	struct acpi_device_wakeup *wakeup = &adev->wakeup;
+
+	if (enable) {
+		acpi_status res;
+		int error;
+
+		error = acpi_enable_wakeup_device_power(adev, ACPI_STATE_S0);
+		if (error)
+			return error;
+
+		res = acpi_enable_gpe(wakeup->gpe_device, wakeup->gpe_number);
+		if (ACPI_FAILURE(res)) {
+			acpi_disable_wakeup_device_power(adev);
+			return -EIO;
+		}
+	} else {
+		acpi_disable_gpe(wakeup->gpe_device, wakeup->gpe_number);
+		acpi_disable_wakeup_device_power(adev);
+	}
+	return 0;
+}
+
+/**
+ * acpi_pm_device_run_wake - Enable/disable remote wakeup for given device.
+ * @dev: Device to enable/disable the platform to wake up.
+ * @enable: Whether to enable or disable the wakeup functionality.
  */
 int acpi_pm_device_run_wake(struct device *phys_dev, bool enable)
 {
-	struct acpi_device *dev;
+	struct acpi_device *adev;
 	acpi_handle handle;
 
 	if (!device_run_wake(phys_dev))
 		return -EINVAL;
 
 	handle = DEVICE_ACPI_HANDLE(phys_dev);
-	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &dev))) {
-		dev_dbg(phys_dev, "ACPI handle has no context in %s!\n",
+	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &adev))) {
+		dev_dbg(phys_dev, "ACPI handle without context in %s!\n",
 			__func__);
 		return -ENODEV;
 	}
 
-	if (enable) {
-		acpi_enable_wakeup_device_power(dev, ACPI_STATE_S0);
-		acpi_enable_gpe(dev->wakeup.gpe_device, dev->wakeup.gpe_number);
-	} else {
-		acpi_disable_gpe(dev->wakeup.gpe_device, dev->wakeup.gpe_number);
-		acpi_disable_wakeup_device_power(dev);
-	}
-
-	return 0;
+	return __acpi_device_run_wake(adev, enable);
 }
 EXPORT_SYMBOL(acpi_pm_device_run_wake);
 #endif /* CONFIG_PM_RUNTIME */
+
+ #ifdef CONFIG_PM_SLEEP
+/**
+ * __acpi_device_sleep_wake - Enable or disable device to wake up the system.
+ * @dev: Device to enable/desible to wake up the system.
+ * @target_state: System state the device is supposed to wake up from.
+ * @enable: Whether to enable or disable @dev to wake up the system.
+ */
+int __acpi_device_sleep_wake(struct acpi_device *adev, u32 target_state,
+			     bool enable)
+{
+	return enable ?
+		acpi_enable_wakeup_device_power(adev, target_state) :
+		acpi_disable_wakeup_device_power(adev);
+}
+#endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 241304ee4068..77c517f6f6d0 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -724,15 +724,13 @@ int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
 
 	handle = DEVICE_ACPI_HANDLE(dev);
 	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &adev))) {
-		dev_dbg(dev, "ACPI handle has no context in %s!\n", __func__);
+		dev_dbg(dev, "ACPI handle without context in %s!\n", __func__);
 		return -ENODEV;
 	}
 
-	error = enable ?
-		acpi_enable_wakeup_device_power(adev, acpi_target_sleep_state) :
-		acpi_disable_wakeup_device_power(adev);
+	error = __acpi_device_sleep_wake(adev, acpi_target_sleep_state, enable);
 	if (!error)
-		dev_info(dev, "wake-up capability %s by ACPI\n",
+		dev_info(dev, "System wakeup %s by ACPI\n",
 				enable ? "enabled" : "disabled");
 
 	return error;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index a8080dfe7183..a635942bcd51 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -455,8 +455,13 @@ static inline int acpi_pm_device_sleep_state(struct device *d, int *p, int m)
 #endif
 
 #ifdef CONFIG_PM_RUNTIME
+int __acpi_device_run_wake(struct acpi_device *, bool);
 int acpi_pm_device_run_wake(struct device *, bool);
 #else
+static inline int __acpi_device_run_wake(struct acpi_device *adev, bool en)
+{
+	return -ENODEV;
+}
 static inline int acpi_pm_device_run_wake(struct device *dev, bool enable)
 {
 	return -ENODEV;
@@ -464,8 +469,14 @@ static inline int acpi_pm_device_run_wake(struct device *dev, bool enable)
 #endif
 
 #ifdef CONFIG_PM_SLEEP
+int __acpi_device_sleep_wake(struct acpi_device *, u32, bool);
 int acpi_pm_device_sleep_wake(struct device *, bool);
 #else
+static inline int __acpi_device_sleep_wake(struct acpi_device *adev,
+					   u32 target_state, bool enable)
+{
+	return -ENODEV;
+}
 static inline int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
 {
 	return -ENODEV;
-- 
cgit v1.2.3-55-g7522


From 078eb12648c2f8bba48921f60ec2cec3e1bbc051 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Fri, 2 Nov 2012 01:40:45 +0100
Subject: ACPI / PM: Provide device PM functions operating on struct
 acpi_device

If the caller of acpi_bus_set_power() already has a pointer to the
struct acpi_device object corresponding to the device in question, it
doesn't make sense for it to go through acpi_bus_get_device(), which
may be costly, because it involves acquiring the global ACPI
namespace mutex.

For this reason, export the function operating on struct acpi_device
objects used internally by acpi_bus_set_power(), so that it may be
called instead of acpi_bus_set_power() in the above case, and change
its name to acpi_device_set_power().

Additionally, introduce two inline wrappers for checking ACPI PM
capabilities of devices represented by struct acpi_device objects.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/bus.c      | 15 ++++++++++++---
 include/acpi/acpi_bus.h | 11 +++++++++++
 2 files changed, 23 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index d59175efc428..07a20ee3e690 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -257,7 +257,15 @@ static int __acpi_bus_get_power(struct acpi_device *device, int *state)
 }
 
 
-static int __acpi_bus_set_power(struct acpi_device *device, int state)
+/**
+ * acpi_device_set_power - Set power state of an ACPI device.
+ * @device: Device to set the power state of.
+ * @state: New power state to set.
+ *
+ * Callers must ensure that the device is power manageable before using this
+ * function.
+ */
+int acpi_device_set_power(struct acpi_device *device, int state)
 {
 	int result = 0;
 	acpi_status status = AE_OK;
@@ -341,6 +349,7 @@ static int __acpi_bus_set_power(struct acpi_device *device, int state)
 
 	return result;
 }
+EXPORT_SYMBOL(acpi_device_set_power);
 
 
 int acpi_bus_set_power(acpi_handle handle, int state)
@@ -359,7 +368,7 @@ int acpi_bus_set_power(acpi_handle handle, int state)
 		return -ENODEV;
 	}
 
-	return __acpi_bus_set_power(device, state);
+	return acpi_device_set_power(device, state);
 }
 EXPORT_SYMBOL(acpi_bus_set_power);
 
@@ -402,7 +411,7 @@ int acpi_bus_update_power(acpi_handle handle, int *state_p)
 	if (result)
 		return result;
 
-	result = __acpi_bus_set_power(device, state);
+	result = acpi_device_set_power(device, state);
 	if (!result && state_p)
 		*state_p = state;
 
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index a635942bcd51..35812b6e0427 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -339,6 +339,7 @@ acpi_status acpi_bus_get_status_handle(acpi_handle handle,
 				       unsigned long long *sta);
 int acpi_bus_get_status(struct acpi_device *device);
 int acpi_bus_set_power(acpi_handle handle, int state);
+int acpi_device_set_power(struct acpi_device *device, int state);
 int acpi_bus_update_power(acpi_handle handle, int *state_p);
 bool acpi_bus_power_manageable(acpi_handle handle);
 bool acpi_bus_can_wakeup(acpi_handle handle);
@@ -483,6 +484,16 @@ static inline int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
 }
 #endif
 
+static inline bool acpi_device_power_manageable(struct acpi_device *adev)
+{
+	return adev->flags.power_manageable;
+}
+
+static inline bool acpi_device_can_wakeup(struct acpi_device *adev)
+{
+	return adev->wakeup.flags.valid;
+}
+
 #else	/* CONFIG_ACPI */
 
 static inline int register_acpi_bus_type(void *bus) { return 0; }
-- 
cgit v1.2.3-55-g7522


From a6ae7594b1b157e0e7976ed105a7be27d69a5361 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Fri, 2 Nov 2012 01:40:53 +0100
Subject: ACPI / PM: Move device PM functions related to sleep states

Introduce helper function returning the target sleep state of the
system and use it to move the remaining device power management
functions from sleep.c to device_pm.c.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/device_pm.c | 54 +++++++++++++++++++++++++++++++++++++++++
 drivers/acpi/sleep.c     | 63 +++++-------------------------------------------
 include/acpi/acpi_bus.h  |  2 ++
 3 files changed, 62 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index b4f03f91b0b0..7ddd93463a2e 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -198,6 +198,31 @@ int acpi_device_power_state(struct device *dev, struct acpi_device *adev,
 }
 EXPORT_SYMBOL_GPL(acpi_device_power_state);
 
+/**
+ * acpi_pm_device_sleep_state - Get preferred power state of ACPI device.
+ * @dev: Device whose preferred target power state to return.
+ * @d_min_p: Location to store the upper limit of the allowed states range.
+ * @d_max_in: Deepest low-power state to take into consideration.
+ * Return value: Preferred power state of the device on success, -ENODEV
+ * (if there's no 'struct acpi_device' for @dev) or -EINVAL on failure
+ *
+ * The caller must ensure that @dev is valid before using this function.
+ */
+int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p, int d_max_in)
+{
+	acpi_handle handle = DEVICE_ACPI_HANDLE(dev);
+	struct acpi_device *adev;
+
+	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &adev))) {
+		dev_dbg(dev, "ACPI handle without context in %s!\n", __func__);
+		return -ENODEV;
+	}
+
+	return acpi_device_power_state(dev, adev, acpi_target_system_state(),
+				       d_max_in, d_min_p);
+}
+EXPORT_SYMBOL(acpi_pm_device_sleep_state);
+
 #ifdef CONFIG_PM_RUNTIME
 /**
  * __acpi_device_run_wake - Enable/disable runtime remote wakeup for device.
@@ -274,4 +299,33 @@ int __acpi_device_sleep_wake(struct acpi_device *adev, u32 target_state,
 		acpi_enable_wakeup_device_power(adev, target_state) :
 		acpi_disable_wakeup_device_power(adev);
 }
+
+/**
+ * acpi_pm_device_sleep_wake - Enable or disable device to wake up the system.
+ * @dev: Device to enable/desible to wake up the system from sleep states.
+ * @enable: Whether to enable or disable @dev to wake up the system.
+ */
+int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
+{
+	acpi_handle handle;
+	struct acpi_device *adev;
+	int error;
+
+	if (!device_can_wakeup(dev))
+		return -EINVAL;
+
+	handle = DEVICE_ACPI_HANDLE(dev);
+	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &adev))) {
+		dev_dbg(dev, "ACPI handle without context in %s!\n", __func__);
+		return -ENODEV;
+	}
+
+	error = __acpi_device_sleep_wake(adev, acpi_target_system_state(),
+					 enable);
+	if (!error)
+		dev_info(dev, "System wakeup %s by ACPI\n",
+				enable ? "enabled" : "disabled");
+
+	return error;
+}
 #endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 77c517f6f6d0..13a285dffaca 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -80,6 +80,12 @@ static int acpi_sleep_prepare(u32 acpi_state)
 
 #ifdef CONFIG_ACPI_SLEEP
 static u32 acpi_target_sleep_state = ACPI_STATE_S0;
+
+u32 acpi_target_system_state(void)
+{
+	return acpi_target_sleep_state;
+}
+
 static bool pwr_btn_event_pending;
 
 /*
@@ -680,63 +686,6 @@ int acpi_suspend(u32 acpi_state)
 	return -EINVAL;
 }
 
-#ifdef CONFIG_PM
-/**
- * acpi_pm_device_sleep_state - Get preferred power state of ACPI device.
- * @dev: Device whose preferred target power state to return.
- * @d_min_p: Location to store the upper limit of the allowed states range.
- * @d_max_in: Deepest low-power state to take into consideration.
- * Return value: Preferred power state of the device on success, -ENODEV
- * (if there's no 'struct acpi_device' for @dev) or -EINVAL on failure
- *
- * The caller must ensure that @dev is valid before using this function.
- */
-int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p, int d_max_in)
-{
-	acpi_handle handle = DEVICE_ACPI_HANDLE(dev);
-	struct acpi_device *adev;
-
-	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &adev))) {
-		dev_dbg(dev, "ACPI handle without context in %s!\n", __func__);
-		return -ENODEV;
-	}
-
-	return acpi_device_power_state(dev, adev, acpi_target_sleep_state,
-				       d_max_in, d_min_p);
-}
-EXPORT_SYMBOL(acpi_pm_device_sleep_state);
-#endif /* CONFIG_PM */
-
-#ifdef CONFIG_PM_SLEEP
-/**
- * acpi_pm_device_sleep_wake - Enable or disable device to wake up the system.
- * @dev: Device to enable/desible to wake up the system from sleep states.
- * @enable: Whether to enable or disable @dev to wake up the system.
- */
-int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
-{
-	acpi_handle handle;
-	struct acpi_device *adev;
-	int error;
-
-	if (!device_can_wakeup(dev))
-		return -EINVAL;
-
-	handle = DEVICE_ACPI_HANDLE(dev);
-	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &adev))) {
-		dev_dbg(dev, "ACPI handle without context in %s!\n", __func__);
-		return -ENODEV;
-	}
-
-	error = __acpi_device_sleep_wake(adev, acpi_target_sleep_state, enable);
-	if (!error)
-		dev_info(dev, "System wakeup %s by ACPI\n",
-				enable ? "enabled" : "disabled");
-
-	return error;
-}
-#endif  /* CONFIG_PM_SLEEP */
-
 static void acpi_power_off_prepare(void)
 {
 	/* Prepare to power off the system */
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 35812b6e0427..bf8709a1844d 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -470,9 +470,11 @@ static inline int acpi_pm_device_run_wake(struct device *dev, bool enable)
 #endif
 
 #ifdef CONFIG_PM_SLEEP
+u32 acpi_target_system_state(void);
 int __acpi_device_sleep_wake(struct acpi_device *, u32, bool);
 int acpi_pm_device_sleep_wake(struct device *, bool);
 #else
+static inline u32 acpi_target_system_state(void) { return ACPI_STATE_S0; }
 static inline int __acpi_device_sleep_wake(struct acpi_device *adev,
 					   u32 target_state, bool enable)
 {
-- 
cgit v1.2.3-55-g7522


From e5cc8ef31267317f3e177415c84e3f3602e5bfc9 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Fri, 2 Nov 2012 01:41:01 +0100
Subject: ACPI / PM: Provide ACPI PM callback routines for subsystems

Some bus types don't support power management natively, but generally
there may be device nodes in ACPI tables corresponding to the devices
whose bus types they are (under ACPI 5 those bus types may be SPI,
I2C and platform).  If that is the case, standard ACPI power
management may be applied to those devices, although currently the
kernel has no means for that.

For this reason, provide a set of routines that may be used as power
management callbacks for such devices.  This may be done in three
different ways.

 (1) Device drivers handling the devices in question may run
     acpi_dev_pm_attach() in their .probe() routines, which (on
     success) will cause the devices to be added to the general ACPI
     PM domain and ACPI power management will be used for them going
     forward.  Then, acpi_dev_pm_detach() may be used to remove the
     devices from the general ACPI PM domain if ACPI power management
     is not necessary for them any more.

 (2) The devices' subsystems may use acpi_subsys_runtime_suspend(),
     acpi_subsys_runtime_resume(), acpi_subsys_prepare(),
     acpi_subsys_suspend_late(), acpi_subsys_resume_early() as their
     power management callbacks in the same way as the general ACPI
     PM domain does that.

 (3) The devices' drivers may execute acpi_dev_suspend_late(),
     acpi_dev_resume_early(), acpi_dev_runtime_suspend(),
     acpi_dev_runtime_resume() from their power management callbacks
     as appropriate, if that's absolutely necessary, but it is not
     recommended to do that, because such drivers may not work
     without ACPI support as a result.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/device_pm.c | 317 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/acpi.h     |  34 +++++
 2 files changed, 351 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 7ddd93463a2e..a8e059f69d50 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -224,6 +224,22 @@ int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p, int d_max_in)
 EXPORT_SYMBOL(acpi_pm_device_sleep_state);
 
 #ifdef CONFIG_PM_RUNTIME
+/**
+ * acpi_wakeup_device - Wakeup notification handler for ACPI devices.
+ * @handle: ACPI handle of the device the notification is for.
+ * @event: Type of the signaled event.
+ * @context: Device corresponding to @handle.
+ */
+static void acpi_wakeup_device(acpi_handle handle, u32 event, void *context)
+{
+	struct device *dev = context;
+
+	if (event == ACPI_NOTIFY_DEVICE_WAKE && dev) {
+		pm_wakeup_event(dev, 0);
+		pm_runtime_resume(dev);
+	}
+}
+
 /**
  * __acpi_device_run_wake - Enable/disable runtime remote wakeup for device.
  * @adev: ACPI device to enable/disable the remote wakeup for.
@@ -283,6 +299,9 @@ int acpi_pm_device_run_wake(struct device *phys_dev, bool enable)
 	return __acpi_device_run_wake(adev, enable);
 }
 EXPORT_SYMBOL(acpi_pm_device_run_wake);
+#else
+static inline void acpi_wakeup_device(acpi_handle handle, u32 event,
+				      void *context) {}
 #endif /* CONFIG_PM_RUNTIME */
 
  #ifdef CONFIG_PM_SLEEP
@@ -329,3 +348,301 @@ int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
 	return error;
 }
 #endif /* CONFIG_PM_SLEEP */
+
+/**
+ * acpi_dev_pm_get_node - Get ACPI device node for the given physical device.
+ * @dev: Device to get the ACPI node for.
+ */
+static struct acpi_device *acpi_dev_pm_get_node(struct device *dev)
+{
+	acpi_handle handle = DEVICE_ACPI_HANDLE(dev);
+	struct acpi_device *adev;
+
+	return handle && ACPI_SUCCESS(acpi_bus_get_device(handle, &adev)) ?
+		adev : NULL;
+}
+
+/**
+ * acpi_dev_pm_low_power - Put ACPI device into a low-power state.
+ * @dev: Device to put into a low-power state.
+ * @adev: ACPI device node corresponding to @dev.
+ * @system_state: System state to choose the device state for.
+ */
+static int acpi_dev_pm_low_power(struct device *dev, struct acpi_device *adev,
+				 u32 system_state)
+{
+	int power_state;
+
+	if (!acpi_device_power_manageable(adev))
+		return 0;
+
+	power_state = acpi_device_power_state(dev, adev, system_state,
+					      ACPI_STATE_D3, NULL);
+	if (power_state < ACPI_STATE_D0 || power_state > ACPI_STATE_D3)
+		return -EIO;
+
+	return acpi_device_set_power(adev, power_state);
+}
+
+/**
+ * acpi_dev_pm_full_power - Put ACPI device into the full-power state.
+ * @adev: ACPI device node to put into the full-power state.
+ */
+static int acpi_dev_pm_full_power(struct acpi_device *adev)
+{
+	return acpi_device_power_manageable(adev) ?
+		acpi_device_set_power(adev, ACPI_STATE_D0) : 0;
+}
+
+#ifdef CONFIG_PM_RUNTIME
+/**
+ * acpi_dev_runtime_suspend - Put device into a low-power state using ACPI.
+ * @dev: Device to put into a low-power state.
+ *
+ * Put the given device into a runtime low-power state using the standard ACPI
+ * mechanism.  Set up remote wakeup if desired, choose the state to put the
+ * device into (this checks if remote wakeup is expected to work too), and set
+ * the power state of the device.
+ */
+int acpi_dev_runtime_suspend(struct device *dev)
+{
+	struct acpi_device *adev = acpi_dev_pm_get_node(dev);
+	bool remote_wakeup;
+	int error;
+
+	if (!adev)
+		return 0;
+
+	remote_wakeup = dev_pm_qos_flags(dev, PM_QOS_FLAG_REMOTE_WAKEUP) >
+				PM_QOS_FLAGS_NONE;
+	error = __acpi_device_run_wake(adev, remote_wakeup);
+	if (remote_wakeup && error)
+		return -EAGAIN;
+
+	error = acpi_dev_pm_low_power(dev, adev, ACPI_STATE_S0);
+	if (error)
+		__acpi_device_run_wake(adev, false);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_runtime_suspend);
+
+/**
+ * acpi_dev_runtime_resume - Put device into the full-power state using ACPI.
+ * @dev: Device to put into the full-power state.
+ *
+ * Put the given device into the full-power state using the standard ACPI
+ * mechanism at run time.  Set the power state of the device to ACPI D0 and
+ * disable remote wakeup.
+ */
+int acpi_dev_runtime_resume(struct device *dev)
+{
+	struct acpi_device *adev = acpi_dev_pm_get_node(dev);
+	int error;
+
+	if (!adev)
+		return 0;
+
+	error = acpi_dev_pm_full_power(adev);
+	__acpi_device_run_wake(adev, false);
+	return error;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_runtime_resume);
+
+/**
+ * acpi_subsys_runtime_suspend - Suspend device using ACPI.
+ * @dev: Device to suspend.
+ *
+ * Carry out the generic runtime suspend procedure for @dev and use ACPI to put
+ * it into a runtime low-power state.
+ */
+int acpi_subsys_runtime_suspend(struct device *dev)
+{
+	int ret = pm_generic_runtime_suspend(dev);
+	return ret ? ret : acpi_dev_runtime_suspend(dev);
+}
+EXPORT_SYMBOL_GPL(acpi_subsys_runtime_suspend);
+
+/**
+ * acpi_subsys_runtime_resume - Resume device using ACPI.
+ * @dev: Device to Resume.
+ *
+ * Use ACPI to put the given device into the full-power state and carry out the
+ * generic runtime resume procedure for it.
+ */
+int acpi_subsys_runtime_resume(struct device *dev)
+{
+	int ret = acpi_dev_runtime_resume(dev);
+	return ret ? ret : pm_generic_runtime_resume(dev);
+}
+EXPORT_SYMBOL_GPL(acpi_subsys_runtime_resume);
+#endif /* CONFIG_PM_RUNTIME */
+
+#ifdef CONFIG_PM_SLEEP
+/**
+ * acpi_dev_suspend_late - Put device into a low-power state using ACPI.
+ * @dev: Device to put into a low-power state.
+ *
+ * Put the given device into a low-power state during system transition to a
+ * sleep state using the standard ACPI mechanism.  Set up system wakeup if
+ * desired, choose the state to put the device into (this checks if system
+ * wakeup is expected to work too), and set the power state of the device.
+ */
+int acpi_dev_suspend_late(struct device *dev)
+{
+	struct acpi_device *adev = acpi_dev_pm_get_node(dev);
+	u32 target_state;
+	bool wakeup;
+	int error;
+
+	if (!adev)
+		return 0;
+
+	target_state = acpi_target_system_state();
+	wakeup = device_may_wakeup(dev);
+	error = __acpi_device_sleep_wake(adev, target_state, wakeup);
+	if (wakeup && error)
+		return error;
+
+	error = acpi_dev_pm_low_power(dev, adev, target_state);
+	if (error)
+		__acpi_device_sleep_wake(adev, ACPI_STATE_UNKNOWN, false);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_suspend_late);
+
+/**
+ * acpi_dev_resume_early - Put device into the full-power state using ACPI.
+ * @dev: Device to put into the full-power state.
+ *
+ * Put the given device into the full-power state using the standard ACPI
+ * mechanism during system transition to the working state.  Set the power
+ * state of the device to ACPI D0 and disable remote wakeup.
+ */
+int acpi_dev_resume_early(struct device *dev)
+{
+	struct acpi_device *adev = acpi_dev_pm_get_node(dev);
+	int error;
+
+	if (!adev)
+		return 0;
+
+	error = acpi_dev_pm_full_power(adev);
+	__acpi_device_sleep_wake(adev, ACPI_STATE_UNKNOWN, false);
+	return error;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_resume_early);
+
+/**
+ * acpi_subsys_prepare - Prepare device for system transition to a sleep state.
+ * @dev: Device to prepare.
+ */
+int acpi_subsys_prepare(struct device *dev)
+{
+	/*
+	 * Follow PCI and resume devices suspended at run time before running
+	 * their system suspend callbacks.
+	 */
+	pm_runtime_resume(dev);
+	return pm_generic_prepare(dev);
+}
+EXPORT_SYMBOL_GPL(acpi_subsys_prepare);
+
+/**
+ * acpi_subsys_suspend_late - Suspend device using ACPI.
+ * @dev: Device to suspend.
+ *
+ * Carry out the generic late suspend procedure for @dev and use ACPI to put
+ * it into a low-power state during system transition into a sleep state.
+ */
+int acpi_subsys_suspend_late(struct device *dev)
+{
+	int ret = pm_generic_suspend_late(dev);
+	return ret ? ret : acpi_dev_suspend_late(dev);
+}
+EXPORT_SYMBOL_GPL(acpi_subsys_suspend_late);
+
+/**
+ * acpi_subsys_resume_early - Resume device using ACPI.
+ * @dev: Device to Resume.
+ *
+ * Use ACPI to put the given device into the full-power state and carry out the
+ * generic early resume procedure for it during system transition into the
+ * working state.
+ */
+int acpi_subsys_resume_early(struct device *dev)
+{
+	int ret = acpi_dev_resume_early(dev);
+	return ret ? ret : pm_generic_resume_early(dev);
+}
+EXPORT_SYMBOL_GPL(acpi_subsys_resume_early);
+#endif /* CONFIG_PM_SLEEP */
+
+static struct dev_pm_domain acpi_general_pm_domain = {
+	.ops = {
+#ifdef CONFIG_PM_RUNTIME
+		.runtime_suspend = acpi_subsys_runtime_suspend,
+		.runtime_resume = acpi_subsys_runtime_resume,
+		.runtime_idle = pm_generic_runtime_idle,
+#endif
+#ifdef CONFIG_PM_SLEEP
+		.prepare = acpi_subsys_prepare,
+		.suspend_late = acpi_subsys_suspend_late,
+		.resume_early = acpi_subsys_resume_early,
+		.poweroff_late = acpi_subsys_suspend_late,
+		.restore_early = acpi_subsys_resume_early,
+#endif
+	},
+};
+
+/**
+ * acpi_dev_pm_attach - Prepare device for ACPI power management.
+ * @dev: Device to prepare.
+ *
+ * If @dev has a valid ACPI handle that has a valid struct acpi_device object
+ * attached to it, install a wakeup notification handler for the device and
+ * add it to the general ACPI PM domain.
+ *
+ * This assumes that the @dev's bus type uses generic power management callbacks
+ * (or doesn't use any power management callbacks at all).
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ */
+int acpi_dev_pm_attach(struct device *dev)
+{
+	struct acpi_device *adev = acpi_dev_pm_get_node(dev);
+
+	if (!adev)
+		return -ENODEV;
+
+	if (dev->pm_domain)
+		return -EEXIST;
+
+	acpi_add_pm_notifier(adev, acpi_wakeup_device, dev);
+	dev->pm_domain = &acpi_general_pm_domain;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
+
+/**
+ * acpi_dev_pm_detach - Remove ACPI power management from the device.
+ * @dev: Device to take care of.
+ *
+ * Remove the device from the general ACPI PM domain and remove its wakeup
+ * notifier.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ */
+void acpi_dev_pm_detach(struct device *dev)
+{
+	struct acpi_device *adev = acpi_dev_pm_get_node(dev);
+
+	if (adev && dev->pm_domain == &acpi_general_pm_domain) {
+		dev->pm_domain = NULL;
+		acpi_remove_pm_notifier(adev, acpi_wakeup_device);
+	}
+}
+EXPORT_SYMBOL_GPL(acpi_dev_pm_detach);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 90be98981102..0676b6ac57fa 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -430,4 +430,38 @@ acpi_status acpi_os_prepare_sleep(u8 sleep_state,
 #define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0)
 #endif
 
+#if defined(CONFIG_ACPI) && defined(CONFIG_PM_RUNTIME)
+int acpi_dev_runtime_suspend(struct device *dev);
+int acpi_dev_runtime_resume(struct device *dev);
+int acpi_subsys_runtime_suspend(struct device *dev);
+int acpi_subsys_runtime_resume(struct device *dev);
+#else
+static inline int acpi_dev_runtime_suspend(struct device *dev) { return 0; }
+static inline int acpi_dev_runtime_resume(struct device *dev) { return 0; }
+static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; }
+static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; }
+#endif
+
+#ifdef CONFIG_ACPI_SLEEP
+int acpi_dev_suspend_late(struct device *dev);
+int acpi_dev_resume_early(struct device *dev);
+int acpi_subsys_prepare(struct device *dev);
+int acpi_subsys_suspend_late(struct device *dev);
+int acpi_subsys_resume_early(struct device *dev);
+#else
+static inline int acpi_dev_suspend_late(struct device *dev) { return 0; }
+static inline int acpi_dev_resume_early(struct device *dev) { return 0; }
+static inline int acpi_subsys_prepare(struct device *dev) { return 0; }
+static inline int acpi_subsys_suspend_late(struct device *dev) { return 0; }
+static inline int acpi_subsys_resume_early(struct device *dev) { return 0; }
+#endif
+
+#if defined(CONFIG_ACPI) && defined(CONFIG_PM)
+int acpi_dev_pm_attach(struct device *dev);
+int acpi_dev_pm_detach(struct device *dev);
+#else
+static inline int acpi_dev_pm_attach(struct device *dev) { return -ENODEV; }
+static inline void acpi_dev_pm_detach(struct device *dev) {}
+#endif
+
 #endif	/*_LINUX_ACPI_H*/
-- 
cgit v1.2.3-55-g7522


From 99926a8cd36b6088448fec41aed4a3b5b05b3679 Mon Sep 17 00:00:00 2001
From: David Rientjes
Date: Sat, 10 Nov 2012 22:48:33 +0100
Subject: ACPI / PM: Fix build problem related to acpi_target_system_state()

Commit b87b49cd0efd ("ACPI / PM: Move device PM functions related to sleep
states") declared acpi_target_system_state() for CONFIG_PM_SLEEP whereas
it is only defined for CONFIG_ACPI_SLEEP, resulting in the following link
error:

drivers/built-in.o: In function `acpi_pm_device_sleep_wake':
drivers/acpi/device_pm.c:342: undefined reference to `acpi_target_system_state'
drivers/built-in.o: In function `acpi_dev_suspend_late':
drivers/acpi/device_pm.c:501: undefined reference to `acpi_target_system_state'
drivers/built-in.o: In function `acpi_pm_device_sleep_state':
drivers/acpi/device_pm.c:221: undefined reference to `acpi_target_system_state'

Define it only for CONFIG_ACPI_SLEEP and fallback to a dummy definition
for other configs.

[rjw: The problem only occurs for exotic .configs in which
 HIBERNATE_CALLBACKS is selected by XEN_SAVE_RESTORE and neither
 SUSPEND nor HIBERNATION is set.]

Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpi_bus.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index bf8709a1844d..80155fda517f 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -470,11 +470,9 @@ static inline int acpi_pm_device_run_wake(struct device *dev, bool enable)
 #endif
 
 #ifdef CONFIG_PM_SLEEP
-u32 acpi_target_system_state(void);
 int __acpi_device_sleep_wake(struct acpi_device *, u32, bool);
 int acpi_pm_device_sleep_wake(struct device *, bool);
 #else
-static inline u32 acpi_target_system_state(void) { return ACPI_STATE_S0; }
 static inline int __acpi_device_sleep_wake(struct acpi_device *adev,
 					   u32 target_state, bool enable)
 {
@@ -486,6 +484,12 @@ static inline int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
 }
 #endif
 
+#ifdef CONFIG_ACPI_SLEEP
+u32 acpi_target_system_state(void);
+#else
+static inline u32 acpi_target_system_state(void) { return ACPI_STATE_S0; }
+#endif
+
 static inline bool acpi_device_power_manageable(struct acpi_device *adev)
 {
 	return adev->flags.power_manageable;
-- 
cgit v1.2.3-55-g7522


From f4fa0e018a175ea92a3187ade8f678599dc5980a Mon Sep 17 00:00:00 2001
From: Toshi Kani
Date: Fri, 26 Oct 2012 13:39:06 +0200
Subject: ACPI: Remove unused lockable in acpi_device_flags

Removed lockable in struct acpi_device_flags since it is no
longer used by any code. acpi_bus_hot_remove_device() cannot
use this flag because acpi_bus_trim() frees up its acpi_device
object. Furthermore, the dock driver calls _LCK method without
using this lockable flag.

Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/scan.c     | 5 -----
 include/acpi/acpi_bus.h | 3 +--
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index ed87f433cec2..19d3d4a1274a 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1017,11 +1017,6 @@ static int acpi_bus_get_flags(struct acpi_device *device)
 			device->flags.ejectable = 1;
 	}
 
-	/* Presence of _LCK indicates 'lockable' */
-	status = acpi_get_handle(device->handle, "_LCK", &temp);
-	if (ACPI_SUCCESS(status))
-		device->flags.lockable = 1;
-
 	/* Power resources cannot be power manageable. */
 	if (device->device_type == ACPI_BUS_TYPE_POWER)
 		return 0;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 0daa0fbd8654..e8b2877aea33 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -144,12 +144,11 @@ struct acpi_device_flags {
 	u32 bus_address:1;
 	u32 removable:1;
 	u32 ejectable:1;
-	u32 lockable:1;
 	u32 suprise_removal_ok:1;
 	u32 power_manageable:1;
 	u32 performance_manageable:1;
 	u32 eject_pending:1;
-	u32 reserved:23;
+	u32 reserved:24;
 };
 
 /* File System */
-- 
cgit v1.2.3-55-g7522


From 1bad2f19f7f79d1ec9e6c48168fd7ce8dc1c305f Mon Sep 17 00:00:00 2001
From: Kristen Carlson Accardi
Date: Fri, 26 Oct 2012 13:39:15 +0200
Subject: ACPI / Sleep: add acpi_sleep=nonvs_s3 parameter

The ACPI specificiation would like us to save NVS at hibernation time,
but makes no mention of saving NVS over S3.  Not all versions of
Windows do this either, and it is clear that not all machines need NVS
saved/restored over S3.  Allow the user to improve their suspend/resume
time by disabling the NVS save/restore at S3 time, but continue to do
the NVS save/restore for S4 as specified.

Signed-off-by: Kristen Carlson Accardi <kristen@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/kernel/acpi/sleep.c |  2 ++
 drivers/acpi/sleep.c         | 17 ++++++++++++++++-
 include/linux/acpi.h         |  1 +
 3 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 11676cf65aee..d5e0d717005a 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -101,6 +101,8 @@ static int __init acpi_sleep_setup(char *str)
 #endif
 		if (strncmp(str, "nonvs", 5) == 0)
 			acpi_nvs_nosave();
+		if (strncmp(str, "nonvs_s3", 8) == 0)
+			acpi_nvs_nosave_s3();
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
 		str = strchr(str, ',');
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index fdcdbb652915..8640782944cc 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -97,6 +97,21 @@ void __init acpi_nvs_nosave(void)
 	nvs_nosave = true;
 }
 
+/*
+ * The ACPI specification wants us to save NVS memory regions during hibernation
+ * but says nothing about saving NVS during S3.  Not all versions of Windows
+ * save NVS on S3 suspend either, and it is clear that not all systems need
+ * NVS to be saved at S3 time.  To improve suspend/resume time, allow the
+ * user to disable saving NVS on S3 if their system does not require it, but
+ * continue to save/restore NVS for S4 as specified.
+ */
+static bool nvs_nosave_s3;
+
+void __init acpi_nvs_nosave_s3(void)
+{
+	nvs_nosave_s3 = true;
+}
+
 /*
  * ACPI 1.0 wants us to execute _PTS before suspending devices, so we allow the
  * user to request that behavior by using the 'acpi_old_suspend_ordering'
@@ -243,7 +258,7 @@ static int acpi_suspend_begin(suspend_state_t pm_state)
 	u32 acpi_state = acpi_suspend_states[pm_state];
 	int error = 0;
 
-	error = nvs_nosave ? 0 : suspend_nvs_alloc();
+	error = (nvs_nosave || nvs_nosave_s3) ? 0 : suspend_nvs_alloc();
 	if (error)
 		return error;
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 90be98981102..3cf93491125c 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -261,6 +261,7 @@ int acpi_resources_are_enforced(void);
 void __init acpi_no_s4_hw_signature(void);
 void __init acpi_old_suspend_ordering(void);
 void __init acpi_nvs_nosave(void);
+void __init acpi_nvs_nosave_s3(void);
 #endif /* CONFIG_PM_SLEEP */
 
 struct acpi_osc_context {
-- 
cgit v1.2.3-55-g7522


From 9743fdea9f9473cd2440741342a5ed8e19eb51bd Mon Sep 17 00:00:00 2001
From: Yuanhan Liu
Date: Fri, 26 Oct 2012 13:39:24 +0200
Subject: ACPI: move acpi_no_s4_hw_signature() declaration into #ifdef
 CONFIG_HIBERNATION

acpi_no_s4_hw_signature is defined in #ifdef CONFIG_HIBERNATION block,
but the current code put the declaration in #ifdef CONFIG_PM_SLEEP block.

I happened to meet this issue when I turned off PM_SLEEP config manually:
arch/x86/kernel/acpi/sleep.c:100:4: error: implicit declaration of function ‘acpi_no_s4_hw_signature’ [-Werror=implicit-function-declaration]

Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 3cf93491125c..87edfcc0ab62 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -257,8 +257,11 @@ int acpi_check_region(resource_size_t start, resource_size_t n,
 
 int acpi_resources_are_enforced(void);
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_HIBERNATION
 void __init acpi_no_s4_hw_signature(void);
+#endif
+
+#ifdef CONFIG_PM_SLEEP
 void __init acpi_old_suspend_ordering(void);
 void __init acpi_nvs_nosave(void);
 void __init acpi_nvs_nosave_s3(void);
-- 
cgit v1.2.3-55-g7522


From 06f64c8f239a47b359c60301914c783b56b32c13 Mon Sep 17 00:00:00 2001
From: Mika Westerberg
Date: Wed, 31 Oct 2012 22:44:33 +0100
Subject: driver core / ACPI: Move ACPI support to core device and driver types

With ACPI 5 we are starting to see devices that don't natively support
discovery but can be enumerated with the help of the ACPI namespace.
Typically, these devices can be represented in the Linux device driver
model as platform devices or some serial bus devices, like SPI or I2C
devices.

Since we want to re-use existing drivers for those devices, we need a
way for drivers to specify the ACPI IDs of supported devices, so that
they can be matched against device nodes in the ACPI namespace.  To
this end, it is sufficient to add a pointer to an array of supported
ACPI device IDs, that can be provided by the driver, to struct device.

Moreover, things like ACPI power management need to have access to
the ACPI handle of each supported device, because that handle is used
to invoke AML methods associated with the corresponding ACPI device
node.  The ACPI handles of devices are now stored in the archdata
member structure of struct device whose definition depends on the
architecture and includes the ACPI handle only on x86 and ia64. Since
the pointer to an array of supported ACPI IDs is added to struct
device_driver in an architecture-independent way, it is logical to
move the ACPI handle from archdata to struct device itself at the same
time.  This also makes code more straightforward in some places and
follows the example of Device Trees that have a poiter to struct
device_node in there too.

This changeset is based on Mika Westerberg's work.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/ia64/include/asm/device.h |  3 ---
 arch/x86/include/asm/device.h  |  3 ---
 drivers/acpi/glue.c            | 14 ++++++--------
 include/acpi/acpi_bus.h        |  2 +-
 include/linux/device.h         |  4 ++++
 5 files changed, 11 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/include/asm/device.h b/arch/ia64/include/asm/device.h
index d05e78f6db94..f69c32ffbe6a 100644
--- a/arch/ia64/include/asm/device.h
+++ b/arch/ia64/include/asm/device.h
@@ -7,9 +7,6 @@
 #define _ASM_IA64_DEVICE_H
 
 struct dev_archdata {
-#ifdef CONFIG_ACPI
-	void	*acpi_handle;
-#endif
 #ifdef CONFIG_INTEL_IOMMU
 	void *iommu; /* hook for IOMMU specific extension */
 #endif
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 93e1c55f14ab..03dd72957d2f 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -2,9 +2,6 @@
 #define _ASM_X86_DEVICE_H
 
 struct dev_archdata {
-#ifdef CONFIG_ACPI
-	void	*acpi_handle;
-#endif
 #ifdef CONFIG_X86_DEV_DMA_OPS
 	struct dma_map_ops *dma_ops;
 #endif
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 08373086cd7e..2f3849aedc97 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -134,7 +134,7 @@ static int acpi_bind_one(struct device *dev, acpi_handle handle)
 	char physical_node_name[sizeof(PHYSICAL_NODE_STRING) + 2];
 	int retval = -EINVAL;
 
-	if (dev->archdata.acpi_handle) {
+	if (dev->acpi_handle) {
 		dev_warn(dev, "Drivers changed 'acpi_handle'\n");
 		return -EINVAL;
 	}
@@ -169,7 +169,7 @@ static int acpi_bind_one(struct device *dev, acpi_handle handle)
 	acpi_dev->physical_node_count++;
 	mutex_unlock(&acpi_dev->physical_node_lock);
 
-	dev->archdata.acpi_handle = handle;
+	dev->acpi_handle = handle;
 
 	if (!physical_node->node_id)
 		strcpy(physical_node_name, PHYSICAL_NODE_STRING);
@@ -198,11 +198,10 @@ static int acpi_unbind_one(struct device *dev)
 	acpi_status status;
 	struct list_head *node, *next;
 
-	if (!dev->archdata.acpi_handle)
+	if (!dev->acpi_handle)
 		return 0;
 
-	status = acpi_bus_get_device(dev->archdata.acpi_handle,
-		&acpi_dev);
+	status = acpi_bus_get_device(dev->acpi_handle, &acpi_dev);
 	if (ACPI_FAILURE(status))
 		goto err;
 
@@ -228,7 +227,7 @@ static int acpi_unbind_one(struct device *dev)
 
 		sysfs_remove_link(&acpi_dev->dev.kobj, physical_node_name);
 		sysfs_remove_link(&dev->kobj, "firmware_node");
-		dev->archdata.acpi_handle = NULL;
+		dev->acpi_handle = NULL;
 		/* acpi_bind_one increase refcnt by one */
 		put_device(dev);
 		kfree(entry);
@@ -269,8 +268,7 @@ static int acpi_platform_notify(struct device *dev)
 	if (!ret) {
 		struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 
-		acpi_get_name(dev->archdata.acpi_handle,
-			      ACPI_FULL_PATHNAME, &buffer);
+		acpi_get_name(dev->acpi_handle, ACPI_FULL_PATHNAME, &buffer);
 		DBG("Device %s -> %s\n", dev_name(dev), (char *)buffer.pointer);
 		kfree(buffer.pointer);
 	} else
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 0daa0fbd8654..bb1537c5e672 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -410,7 +410,7 @@ acpi_handle acpi_get_child(acpi_handle, u64);
 int acpi_is_root_bridge(acpi_handle);
 acpi_handle acpi_get_pci_rootbridge_handle(unsigned int, unsigned int);
 struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle);
-#define DEVICE_ACPI_HANDLE(dev) ((acpi_handle)((dev)->archdata.acpi_handle))
+#define DEVICE_ACPI_HANDLE(dev) ((acpi_handle)((dev)->acpi_handle))
 
 int acpi_enable_wakeup_device_power(struct acpi_device *dev, int state);
 int acpi_disable_wakeup_device_power(struct acpi_device *dev);
diff --git a/include/linux/device.h b/include/linux/device.h
index 86ef6ab553b1..cc3aee57a46e 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -190,6 +190,7 @@ extern struct klist *bus_get_device_klist(struct bus_type *bus);
  * @mod_name:	Used for built-in modules.
  * @suppress_bind_attrs: Disables bind/unbind via sysfs.
  * @of_match_table: The open firmware table.
+ * @acpi_match_table: The ACPI match table.
  * @probe:	Called to query the existence of a specific device,
  *		whether this driver can work with it, and bind the driver
  *		to a specific device.
@@ -223,6 +224,7 @@ struct device_driver {
 	bool suppress_bind_attrs;	/* disables bind/unbind via sysfs */
 
 	const struct of_device_id	*of_match_table;
+	const struct acpi_device_id	*acpi_match_table;
 
 	int (*probe) (struct device *dev);
 	int (*remove) (struct device *dev);
@@ -616,6 +618,7 @@ struct device_dma_parameters {
  * @dma_mem:	Internal for coherent mem override.
  * @archdata:	For arch-specific additions.
  * @of_node:	Associated device tree node.
+ * @acpi_handle: Associated ACPI device node's namespace handle.
  * @devt:	For creating the sysfs "dev".
  * @id:		device instance
  * @devres_lock: Spinlock to protect the resource of the device.
@@ -680,6 +683,7 @@ struct device {
 	struct dev_archdata	archdata;
 
 	struct device_node	*of_node; /* associated device tree node */
+	void			*acpi_handle; /* associated ACPI device node */
 
 	dev_t			devt;	/* dev_t, creates the sysfs "dev" */
 	u32			id;	/* device instance */
-- 
cgit v1.2.3-55-g7522


From cf761af9ee0f2c172710ad2b7ca029016b5d4c45 Mon Sep 17 00:00:00 2001
From: Mika Westerberg
Date: Wed, 31 Oct 2012 22:44:41 +0100
Subject: ACPI: Provide generic functions for matching ACPI device nodes

Introduce function acpi_match_device() allowing callers to match
struct device objects with populated acpi_handle fields against
arrays of ACPI device IDs.  Also introduce function
acpi_driver_match_device() using acpi_match_device() internally and
allowing callers to match a struct device object against an array of
ACPI device IDs provided by a device driver.

Additionally, introduce macro ACPI_PTR() that may be used by device
drivers to escape pointers to data structures whose definitions
depend on CONFIG_ACPI.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/scan.c  | 40 +++++++++++++++++++++++++++++++++++-----
 include/linux/acpi.h | 28 ++++++++++++++++++++++++++++
 2 files changed, 63 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 1fcb8678665c..a0dfdffe54d4 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -340,8 +340,8 @@ static void acpi_device_remove_files(struct acpi_device *dev)
 			ACPI Bus operations
    -------------------------------------------------------------------------- */
 
-int acpi_match_device_ids(struct acpi_device *device,
-			  const struct acpi_device_id *ids)
+static const struct acpi_device_id *__acpi_match_device(
+	struct acpi_device *device, const struct acpi_device_id *ids)
 {
 	const struct acpi_device_id *id;
 	struct acpi_hardware_id *hwid;
@@ -351,14 +351,44 @@ int acpi_match_device_ids(struct acpi_device *device,
 	 * driver for it.
 	 */
 	if (!device->status.present)
-		return -ENODEV;
+		return NULL;
 
 	for (id = ids; id->id[0]; id++)
 		list_for_each_entry(hwid, &device->pnp.ids, list)
 			if (!strcmp((char *) id->id, hwid->id))
-				return 0;
+				return id;
+
+	return NULL;
+}
 
-	return -ENOENT;
+/**
+ * acpi_match_device - Match a struct device against a given list of ACPI IDs
+ * @ids: Array of struct acpi_device_id object to match against.
+ * @dev: The device structure to match.
+ *
+ * Check if @dev has a valid ACPI handle and if there is a struct acpi_device
+ * object for that handle and use that object to match against a given list of
+ * device IDs.
+ *
+ * Return a pointer to the first matching ID on success or %NULL on failure.
+ */
+const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
+					       const struct device *dev)
+{
+	struct acpi_device *adev;
+
+	if (!ids || !dev->acpi_handle
+	    || ACPI_FAILURE(acpi_bus_get_device(dev->acpi_handle, &adev)))
+		return NULL;
+
+	return __acpi_match_device(adev, ids);
+}
+EXPORT_SYMBOL_GPL(acpi_match_device);
+
+int acpi_match_device_ids(struct acpi_device *device,
+			  const struct acpi_device_id *ids)
+{
+	return __acpi_match_device(device, ids) ? 0 : -ENOENT;
 }
 EXPORT_SYMBOL(acpi_match_device_ids);
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 90be98981102..48761cb481db 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -26,6 +26,7 @@
 #define _LINUX_ACPI_H
 
 #include <linux/ioport.h>	/* for struct resource */
+#include <linux/device.h>
 
 #ifdef	CONFIG_ACPI
 
@@ -364,6 +365,17 @@ extern int acpi_nvs_register(__u64 start, __u64 size);
 extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *),
 				    void *data);
 
+const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
+					       const struct device *dev);
+
+static inline bool acpi_driver_match_device(struct device *dev,
+					    const struct device_driver *drv)
+{
+	return !!acpi_match_device(drv->acpi_match_table, dev);
+}
+
+#define ACPI_PTR(_ptr)	(_ptr)
+
 #else	/* !CONFIG_ACPI */
 
 #define acpi_disabled 1
@@ -418,6 +430,22 @@ static inline int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *),
 	return 0;
 }
 
+struct acpi_device_id;
+
+static inline const struct acpi_device_id *acpi_match_device(
+	const struct acpi_device_id *ids, const struct device *dev)
+{
+	return NULL;
+}
+
+static inline bool acpi_driver_match_device(struct device *dev,
+					    const struct device_driver *drv)
+{
+	return false;
+}
+
+#define ACPI_PTR(_ptr)	(NULL)
+
 #endif	/* !CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI
-- 
cgit v1.2.3-55-g7522


From 046d9ce6820e99087e81511284045eada94950e8 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Thu, 15 Nov 2012 00:30:01 +0100
Subject: ACPI: Move device resources interpretation code from PNP to ACPI core

Move some code used for parsing ACPI device resources from the PNP
subsystem to the ACPI core, so that other bus types (platform, SPI,
I2C) can use the same routines for parsing resources in a consistent
way, without duplicating code.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/acpi/Makefile          |   1 +
 drivers/acpi/resource.c        | 393 +++++++++++++++++++++++++++++++++++++++++
 drivers/pnp/base.h             |   2 +
 drivers/pnp/pnpacpi/rsparser.c | 296 ++++---------------------------
 drivers/pnp/resource.c         |  16 ++
 include/linux/acpi.h           |  10 ++
 6 files changed, 454 insertions(+), 264 deletions(-)
 create mode 100644 drivers/acpi/resource.c

(limited to 'include')

diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 227c82bbe9a1..3223edfb23b6 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -32,6 +32,7 @@ acpi-$(CONFIG_ACPI_SLEEP)	+= proc.o
 #
 acpi-y				+= bus.o glue.o
 acpi-y				+= scan.o
+acpi-y				+= resource.o
 acpi-y				+= processor_core.o
 acpi-y				+= ec.o
 acpi-$(CONFIG_ACPI_DOCK)	+= dock.o
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
new file mode 100644
index 000000000000..3e7fd349e29d
--- /dev/null
+++ b/drivers/acpi/resource.c
@@ -0,0 +1,393 @@
+/*
+ * drivers/acpi/resource.c - ACPI device resources interpretation.
+ *
+ * Copyright (C) 2012, Intel Corp.
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as published
+ *  by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/ioport.h>
+
+#ifdef CONFIG_X86
+#define valid_IRQ(i) (((i) != 0) && ((i) != 2))
+#else
+#define valid_IRQ(i) (true)
+#endif
+
+static unsigned long acpi_dev_memresource_flags(u64 len, u8 write_protect,
+						bool window)
+{
+	unsigned long flags = IORESOURCE_MEM;
+
+	if (len == 0)
+		flags |= IORESOURCE_DISABLED;
+
+	if (write_protect == ACPI_READ_WRITE_MEMORY)
+		flags |= IORESOURCE_MEM_WRITEABLE;
+
+	if (window)
+		flags |= IORESOURCE_WINDOW;
+
+	return flags;
+}
+
+static void acpi_dev_get_memresource(struct resource *res, u64 start, u64 len,
+				     u8 write_protect)
+{
+	res->start = start;
+	res->end = start + len - 1;
+	res->flags = acpi_dev_memresource_flags(len, write_protect, false);
+}
+
+/**
+ * acpi_dev_resource_memory - Extract ACPI memory resource information.
+ * @ares: Input ACPI resource object.
+ * @res: Output generic resource object.
+ *
+ * Check if the given ACPI resource object represents a memory resource and
+ * if that's the case, use the information in it to populate the generic
+ * resource object pointed to by @res.
+ */
+bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res)
+{
+	struct acpi_resource_memory24 *memory24;
+	struct acpi_resource_memory32 *memory32;
+	struct acpi_resource_fixed_memory32 *fixed_memory32;
+
+	switch (ares->type) {
+	case ACPI_RESOURCE_TYPE_MEMORY24:
+		memory24 = &ares->data.memory24;
+		acpi_dev_get_memresource(res, memory24->minimum,
+					 memory24->address_length,
+					 memory24->write_protect);
+		break;
+	case ACPI_RESOURCE_TYPE_MEMORY32:
+		memory32 = &ares->data.memory32;
+		acpi_dev_get_memresource(res, memory32->minimum,
+					 memory32->address_length,
+					 memory32->write_protect);
+		break;
+	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
+		fixed_memory32 = &ares->data.fixed_memory32;
+		acpi_dev_get_memresource(res, fixed_memory32->address,
+					 fixed_memory32->address_length,
+					 fixed_memory32->write_protect);
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_resource_memory);
+
+static unsigned int acpi_dev_ioresource_flags(u64 start, u64 end, u8 io_decode,
+					      bool window)
+{
+	int flags = IORESOURCE_IO;
+
+	if (io_decode == ACPI_DECODE_16)
+		flags |= IORESOURCE_IO_16BIT_ADDR;
+
+	if (start > end || end >= 0x10003)
+		flags |= IORESOURCE_DISABLED;
+
+	if (window)
+		flags |= IORESOURCE_WINDOW;
+
+	return flags;
+}
+
+static void acpi_dev_get_ioresource(struct resource *res, u64 start, u64 len,
+				    u8 io_decode)
+{
+	u64 end = start + len - 1;
+
+	res->start = start;
+	res->end = end;
+	res->flags = acpi_dev_ioresource_flags(start, end, io_decode, false);
+}
+
+/**
+ * acpi_dev_resource_io - Extract ACPI I/O resource information.
+ * @ares: Input ACPI resource object.
+ * @res: Output generic resource object.
+ *
+ * Check if the given ACPI resource object represents an I/O resource and
+ * if that's the case, use the information in it to populate the generic
+ * resource object pointed to by @res.
+ */
+bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res)
+{
+	struct acpi_resource_io *io;
+	struct acpi_resource_fixed_io *fixed_io;
+
+	switch (ares->type) {
+	case ACPI_RESOURCE_TYPE_IO:
+		io = &ares->data.io;
+		acpi_dev_get_ioresource(res, io->minimum,
+					io->address_length,
+					io->io_decode);
+		break;
+	case ACPI_RESOURCE_TYPE_FIXED_IO:
+		fixed_io = &ares->data.fixed_io;
+		acpi_dev_get_ioresource(res, fixed_io->address,
+					fixed_io->address_length,
+					ACPI_DECODE_10);
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_resource_io);
+
+/**
+ * acpi_dev_resource_address_space - Extract ACPI address space information.
+ * @ares: Input ACPI resource object.
+ * @res: Output generic resource object.
+ *
+ * Check if the given ACPI resource object represents an address space resource
+ * and if that's the case, use the information in it to populate the generic
+ * resource object pointed to by @res.
+ */
+bool acpi_dev_resource_address_space(struct acpi_resource *ares,
+				     struct resource *res)
+{
+	acpi_status status;
+	struct acpi_resource_address64 addr;
+	bool window;
+	u64 len;
+	u8 io_decode;
+
+	switch (ares->type) {
+	case ACPI_RESOURCE_TYPE_ADDRESS16:
+	case ACPI_RESOURCE_TYPE_ADDRESS32:
+	case ACPI_RESOURCE_TYPE_ADDRESS64:
+		break;
+	default:
+		return false;
+	}
+
+	status = acpi_resource_to_address64(ares, &addr);
+	if (ACPI_FAILURE(status))
+		return true;
+
+	res->start = addr.minimum;
+	res->end = addr.maximum;
+	window = addr.producer_consumer == ACPI_PRODUCER;
+
+	switch(addr.resource_type) {
+	case ACPI_MEMORY_RANGE:
+		len = addr.maximum - addr.minimum + 1;
+		res->flags = acpi_dev_memresource_flags(len,
+						addr.info.mem.write_protect,
+						window);
+		break;
+	case ACPI_IO_RANGE:
+		io_decode = addr.granularity == 0xfff ?
+				ACPI_DECODE_10 : ACPI_DECODE_16;
+		res->flags = acpi_dev_ioresource_flags(addr.minimum,
+						       addr.maximum,
+						       io_decode, window);
+		break;
+	case ACPI_BUS_NUMBER_RANGE:
+		res->flags = IORESOURCE_BUS;
+		break;
+	default:
+		res->flags = 0;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_resource_address_space);
+
+/**
+ * acpi_dev_resource_ext_address_space - Extract ACPI address space information.
+ * @ares: Input ACPI resource object.
+ * @res: Output generic resource object.
+ *
+ * Check if the given ACPI resource object represents an extended address space
+ * resource and if that's the case, use the information in it to populate the
+ * generic resource object pointed to by @res.
+ */
+bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares,
+					 struct resource *res)
+{
+	struct acpi_resource_extended_address64 *ext_addr;
+	bool window;
+	u64 len;
+	u8 io_decode;
+
+	if (ares->type != ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64)
+		return false;
+
+	ext_addr = &ares->data.ext_address64;
+
+	res->start = ext_addr->minimum;
+	res->end = ext_addr->maximum;
+	window = ext_addr->producer_consumer == ACPI_PRODUCER;
+
+	switch(ext_addr->resource_type) {
+	case ACPI_MEMORY_RANGE:
+		len = ext_addr->maximum - ext_addr->minimum + 1;
+		res->flags = acpi_dev_memresource_flags(len,
+					ext_addr->info.mem.write_protect,
+					window);
+		break;
+	case ACPI_IO_RANGE:
+		io_decode = ext_addr->granularity == 0xfff ?
+				ACPI_DECODE_10 : ACPI_DECODE_16;
+		res->flags = acpi_dev_ioresource_flags(ext_addr->minimum,
+						       ext_addr->maximum,
+						       io_decode, window);
+		break;
+	case ACPI_BUS_NUMBER_RANGE:
+		res->flags = IORESOURCE_BUS;
+		break;
+	default:
+		res->flags = 0;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_resource_ext_address_space);
+
+/**
+ * acpi_dev_irq_flags - Determine IRQ resource flags.
+ * @triggering: Triggering type as provided by ACPI.
+ * @polarity: Interrupt polarity as provided by ACPI.
+ * @shareable: Whether or not the interrupt is shareable.
+ */
+unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable)
+{
+	unsigned long flags;
+
+	if (triggering == ACPI_LEVEL_SENSITIVE)
+		flags = polarity == ACPI_ACTIVE_LOW ?
+			IORESOURCE_IRQ_LOWLEVEL : IORESOURCE_IRQ_HIGHLEVEL;
+	else
+		flags = polarity == ACPI_ACTIVE_LOW ?
+			IORESOURCE_IRQ_LOWEDGE : IORESOURCE_IRQ_HIGHEDGE;
+
+	if (shareable == ACPI_SHARED)
+		flags |= IORESOURCE_IRQ_SHAREABLE;
+
+	return flags | IORESOURCE_IRQ;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_irq_flags);
+
+static void acpi_dev_irqresource_disabled(struct resource *res, u32 gsi)
+{
+	res->start = gsi;
+	res->end = gsi;
+	res->flags = IORESOURCE_IRQ | IORESOURCE_DISABLED;
+}
+
+static void acpi_dev_get_irqresource(struct resource *res, u32 gsi,
+				     u8 triggering, u8 polarity, u8 shareable)
+{
+	int irq, p, t;
+
+	if (!valid_IRQ(gsi)) {
+		acpi_dev_irqresource_disabled(res, gsi);
+		return;
+	}
+
+	/*
+	 * In IO-APIC mode, use overrided attribute. Two reasons:
+	 * 1. BIOS bug in DSDT
+	 * 2. BIOS uses IO-APIC mode Interrupt Source Override
+	 */
+	if (!acpi_get_override_irq(gsi, &t, &p)) {
+		u8 trig = t ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+		u8 pol = p ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
+
+		if (triggering != trig || polarity != pol) {
+			pr_warning("ACPI: IRQ %d override to %s, %s\n", gsi,
+				   t ? "edge" : "level", p ? "low" : "high");
+			triggering = trig;
+			polarity = pol;
+		}
+	}
+
+	res->flags = acpi_dev_irq_flags(triggering, polarity, shareable);
+	irq = acpi_register_gsi(NULL, gsi, triggering, polarity);
+	if (irq >= 0) {
+		res->start = irq;
+		res->end = irq;
+	} else {
+		acpi_dev_irqresource_disabled(res, gsi);
+	}
+}
+
+/**
+ * acpi_dev_resource_interrupt - Extract ACPI interrupt resource information.
+ * @ares: Input ACPI resource object.
+ * @index: Index into the array of GSIs represented by the resource.
+ * @res: Output generic resource object.
+ *
+ * Check if the given ACPI resource object represents an interrupt resource
+ * and @index does not exceed the resource's interrupt count (true is returned
+ * in that case regardless of the results of the other checks)).  If that's the
+ * case, register the GSI corresponding to @index from the array of interrupts
+ * represented by the resource and populate the generic resource object pointed
+ * to by @res accordingly.  If the registration of the GSI is not successful,
+ * IORESOURCE_DISABLED will be set it that object's flags.
+ */
+bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
+				 struct resource *res)
+{
+	struct acpi_resource_irq *irq;
+	struct acpi_resource_extended_irq *ext_irq;
+
+	switch (ares->type) {
+	case ACPI_RESOURCE_TYPE_IRQ:
+		/*
+		 * Per spec, only one interrupt per descriptor is allowed in
+		 * _CRS, but some firmware violates this, so parse them all.
+		 */
+		irq = &ares->data.irq;
+		if (index >= irq->interrupt_count) {
+			acpi_dev_irqresource_disabled(res, 0);
+			return false;
+		}
+		acpi_dev_get_irqresource(res, irq->interrupts[index],
+					 irq->triggering, irq->polarity,
+					 irq->sharable);
+		break;
+	case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
+		ext_irq = &ares->data.extended_irq;
+		if (index >= ext_irq->interrupt_count) {
+			acpi_dev_irqresource_disabled(res, 0);
+			return false;
+		}
+		acpi_dev_get_irqresource(res, ext_irq->interrupts[index],
+					 ext_irq->triggering, ext_irq->polarity,
+					 ext_irq->sharable);
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_resource_interrupt);
diff --git a/drivers/pnp/base.h b/drivers/pnp/base.h
index fa4e0a5db3f8..ffd53e3eb92f 100644
--- a/drivers/pnp/base.h
+++ b/drivers/pnp/base.h
@@ -159,6 +159,8 @@ struct pnp_resource {
 
 void pnp_free_resource(struct pnp_resource *pnp_res);
 
+struct pnp_resource *pnp_add_resource(struct pnp_dev *dev,
+				      struct resource *res);
 struct pnp_resource *pnp_add_irq_resource(struct pnp_dev *dev, int irq,
 					  int flags);
 struct pnp_resource *pnp_add_dma_resource(struct pnp_dev *dev, int dma,
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 5be4a392a3ae..b8f4ea7b27fc 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -28,37 +28,6 @@
 #include "../base.h"
 #include "pnpacpi.h"
 
-#ifdef CONFIG_IA64
-#define valid_IRQ(i) (1)
-#else
-#define valid_IRQ(i) (((i) != 0) && ((i) != 2))
-#endif
-
-/*
- * Allocated Resources
- */
-static int irq_flags(int triggering, int polarity, int shareable)
-{
-	int flags;
-
-	if (triggering == ACPI_LEVEL_SENSITIVE) {
-		if (polarity == ACPI_ACTIVE_LOW)
-			flags = IORESOURCE_IRQ_LOWLEVEL;
-		else
-			flags = IORESOURCE_IRQ_HIGHLEVEL;
-	} else {
-		if (polarity == ACPI_ACTIVE_LOW)
-			flags = IORESOURCE_IRQ_LOWEDGE;
-		else
-			flags = IORESOURCE_IRQ_HIGHEDGE;
-	}
-
-	if (shareable == ACPI_SHARED)
-		flags |= IORESOURCE_IRQ_SHAREABLE;
-
-	return flags;
-}
-
 static void decode_irq_flags(struct pnp_dev *dev, int flags, int *triggering,
 			     int *polarity, int *shareable)
 {
@@ -94,45 +63,6 @@ static void decode_irq_flags(struct pnp_dev *dev, int flags, int *triggering,
 		*shareable = ACPI_EXCLUSIVE;
 }
 
-static void pnpacpi_parse_allocated_irqresource(struct pnp_dev *dev,
-						u32 gsi, int triggering,
-						int polarity, int shareable)
-{
-	int irq, flags;
-	int p, t;
-
-	if (!valid_IRQ(gsi)) {
-		pnp_add_irq_resource(dev, gsi, IORESOURCE_DISABLED);
-		return;
-	}
-
-	/*
-	 * in IO-APIC mode, use overrided attribute. Two reasons:
-	 * 1. BIOS bug in DSDT
-	 * 2. BIOS uses IO-APIC mode Interrupt Source Override
-	 */
-	if (!acpi_get_override_irq(gsi, &t, &p)) {
-		t = t ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
-		p = p ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
-
-		if (triggering != t || polarity != p) {
-			dev_warn(&dev->dev, "IRQ %d override to %s, %s\n",
-				gsi, t ? "edge":"level", p ? "low":"high");
-			triggering = t;
-			polarity = p;
-		}
-	}
-
-	flags = irq_flags(triggering, polarity, shareable);
-	irq = acpi_register_gsi(&dev->dev, gsi, triggering, polarity);
-	if (irq >= 0)
-		pcibios_penalize_isa_irq(irq, 1);
-	else
-		flags |= IORESOURCE_DISABLED;
-
-	pnp_add_irq_resource(dev, irq, flags);
-}
-
 static int dma_flags(struct pnp_dev *dev, int type, int bus_master,
 		     int transfer)
 {
@@ -177,21 +107,16 @@ static int dma_flags(struct pnp_dev *dev, int type, int bus_master,
 	return flags;
 }
 
-static void pnpacpi_parse_allocated_ioresource(struct pnp_dev *dev, u64 start,
-					       u64 len, int io_decode,
-					       int window)
-{
-	int flags = 0;
-	u64 end = start + len - 1;
+/*
+ * Allocated Resources
+ */
 
-	if (io_decode == ACPI_DECODE_16)
-		flags |= IORESOURCE_IO_16BIT_ADDR;
-	if (len == 0 || end >= 0x10003)
-		flags |= IORESOURCE_DISABLED;
-	if (window)
-		flags |= IORESOURCE_WINDOW;
+static void pnpacpi_add_irqresource(struct pnp_dev *dev, struct resource *r)
+{
+	if (!(r->flags & IORESOURCE_DISABLED))
+		pcibios_penalize_isa_irq(r->start, 1);
 
-	pnp_add_io_resource(dev, start, end, flags);
+	pnp_add_resource(dev, r);
 }
 
 /*
@@ -249,130 +174,49 @@ static void pnpacpi_parse_allocated_vendor(struct pnp_dev *dev,
 	}
 }
 
-static void pnpacpi_parse_allocated_memresource(struct pnp_dev *dev,
-						u64 start, u64 len,
-						int write_protect, int window)
-{
-	int flags = 0;
-	u64 end = start + len - 1;
-
-	if (len == 0)
-		flags |= IORESOURCE_DISABLED;
-	if (write_protect == ACPI_READ_WRITE_MEMORY)
-		flags |= IORESOURCE_MEM_WRITEABLE;
-	if (window)
-		flags |= IORESOURCE_WINDOW;
-
-	pnp_add_mem_resource(dev, start, end, flags);
-}
-
-static void pnpacpi_parse_allocated_busresource(struct pnp_dev *dev,
-						u64 start, u64 len)
-{
-	u64 end = start + len - 1;
-
-	pnp_add_bus_resource(dev, start, end);
-}
-
-static void pnpacpi_parse_allocated_address_space(struct pnp_dev *dev,
-						  struct acpi_resource *res)
-{
-	struct acpi_resource_address64 addr, *p = &addr;
-	acpi_status status;
-	int window;
-	u64 len;
-
-	status = acpi_resource_to_address64(res, p);
-	if (!ACPI_SUCCESS(status)) {
-		dev_warn(&dev->dev, "failed to convert resource type %d\n",
-			 res->type);
-		return;
-	}
-
-	/* Windows apparently computes length rather than using _LEN */
-	len = p->maximum - p->minimum + 1;
-	window = (p->producer_consumer == ACPI_PRODUCER) ? 1 : 0;
-
-	if (p->resource_type == ACPI_MEMORY_RANGE)
-		pnpacpi_parse_allocated_memresource(dev, p->minimum, len,
-			p->info.mem.write_protect, window);
-	else if (p->resource_type == ACPI_IO_RANGE)
-		pnpacpi_parse_allocated_ioresource(dev, p->minimum, len,
-			p->granularity == 0xfff ? ACPI_DECODE_10 :
-				ACPI_DECODE_16, window);
-	else if (p->resource_type == ACPI_BUS_NUMBER_RANGE)
-		pnpacpi_parse_allocated_busresource(dev, p->minimum, len);
-}
-
-static void pnpacpi_parse_allocated_ext_address_space(struct pnp_dev *dev,
-						      struct acpi_resource *res)
-{
-	struct acpi_resource_extended_address64 *p = &res->data.ext_address64;
-	int window;
-	u64 len;
-
-	/* Windows apparently computes length rather than using _LEN */
-	len = p->maximum - p->minimum + 1;
-	window = (p->producer_consumer == ACPI_PRODUCER) ? 1 : 0;
-
-	if (p->resource_type == ACPI_MEMORY_RANGE)
-		pnpacpi_parse_allocated_memresource(dev, p->minimum, len,
-			p->info.mem.write_protect, window);
-	else if (p->resource_type == ACPI_IO_RANGE)
-		pnpacpi_parse_allocated_ioresource(dev, p->minimum, len,
-			p->granularity == 0xfff ? ACPI_DECODE_10 :
-				ACPI_DECODE_16, window);
-	else if (p->resource_type == ACPI_BUS_NUMBER_RANGE)
-		pnpacpi_parse_allocated_busresource(dev, p->minimum, len);
-}
-
 static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res,
 					      void *data)
 {
 	struct pnp_dev *dev = data;
-	struct acpi_resource_irq *irq;
 	struct acpi_resource_dma *dma;
-	struct acpi_resource_io *io;
-	struct acpi_resource_fixed_io *fixed_io;
 	struct acpi_resource_vendor_typed *vendor_typed;
-	struct acpi_resource_memory24 *memory24;
-	struct acpi_resource_memory32 *memory32;
-	struct acpi_resource_fixed_memory32 *fixed_memory32;
-	struct acpi_resource_extended_irq *extended_irq;
+	struct resource r;
 	int i, flags;
 
-	switch (res->type) {
-	case ACPI_RESOURCE_TYPE_IRQ:
-		/*
-		 * Per spec, only one interrupt per descriptor is allowed in
-		 * _CRS, but some firmware violates this, so parse them all.
-		 */
-		irq = &res->data.irq;
-		if (irq->interrupt_count == 0)
-			pnp_add_irq_resource(dev, 0, IORESOURCE_DISABLED);
-		else {
-			for (i = 0; i < irq->interrupt_count; i++) {
-				pnpacpi_parse_allocated_irqresource(dev,
-					irq->interrupts[i],
-					irq->triggering,
-					irq->polarity,
-				    irq->sharable);
-			}
+	if (acpi_dev_resource_memory(res, &r)
+	    || acpi_dev_resource_io(res, &r)
+	    || acpi_dev_resource_address_space(res, &r)
+	    || acpi_dev_resource_ext_address_space(res, &r)) {
+		pnp_add_resource(dev, &r);
+		return AE_OK;
+	}
 
+	r.flags = 0;
+	if (acpi_dev_resource_interrupt(res, 0, &r)) {
+		pnpacpi_add_irqresource(dev, &r);
+		for (i = 1; acpi_dev_resource_interrupt(res, i, &r); i++)
+			pnpacpi_add_irqresource(dev, &r);
+
+		if (i > 1) {
 			/*
 			 * The IRQ encoder puts a single interrupt in each
 			 * descriptor, so if a _CRS descriptor has more than
 			 * one interrupt, we won't be able to re-encode it.
 			 */
-			if (pnp_can_write(dev) && irq->interrupt_count > 1) {
+			if (pnp_can_write(dev)) {
 				dev_warn(&dev->dev, "multiple interrupts in "
 					 "_CRS descriptor; configuration can't "
 					 "be changed\n");
 				dev->capabilities &= ~PNP_WRITE;
 			}
 		}
-		break;
+		return AE_OK;
+	} else if (r.flags & IORESOURCE_DISABLED) {
+		pnp_add_irq_resource(dev, 0, IORESOURCE_DISABLED);
+		return AE_OK;
+	}
 
+	switch (res->type) {
 	case ACPI_RESOURCE_TYPE_DMA:
 		dma = &res->data.dma;
 		if (dma->channel_count > 0 && dma->channels[0] != (u8) -1)
@@ -383,26 +227,10 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res,
 		pnp_add_dma_resource(dev, dma->channels[0], flags);
 		break;
 
-	case ACPI_RESOURCE_TYPE_IO:
-		io = &res->data.io;
-		pnpacpi_parse_allocated_ioresource(dev,
-			io->minimum,
-			io->address_length,
-			io->io_decode, 0);
-		break;
-
 	case ACPI_RESOURCE_TYPE_START_DEPENDENT:
 	case ACPI_RESOURCE_TYPE_END_DEPENDENT:
 		break;
 
-	case ACPI_RESOURCE_TYPE_FIXED_IO:
-		fixed_io = &res->data.fixed_io;
-		pnpacpi_parse_allocated_ioresource(dev,
-			fixed_io->address,
-			fixed_io->address_length,
-			ACPI_DECODE_10, 0);
-		break;
-
 	case ACPI_RESOURCE_TYPE_VENDOR:
 		vendor_typed = &res->data.vendor_typed;
 		pnpacpi_parse_allocated_vendor(dev, vendor_typed);
@@ -411,66 +239,6 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res,
 	case ACPI_RESOURCE_TYPE_END_TAG:
 		break;
 
-	case ACPI_RESOURCE_TYPE_MEMORY24:
-		memory24 = &res->data.memory24;
-		pnpacpi_parse_allocated_memresource(dev,
-			memory24->minimum,
-			memory24->address_length,
-			memory24->write_protect, 0);
-		break;
-	case ACPI_RESOURCE_TYPE_MEMORY32:
-		memory32 = &res->data.memory32;
-		pnpacpi_parse_allocated_memresource(dev,
-			memory32->minimum,
-			memory32->address_length,
-			memory32->write_protect, 0);
-		break;
-	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
-		fixed_memory32 = &res->data.fixed_memory32;
-		pnpacpi_parse_allocated_memresource(dev,
-			fixed_memory32->address,
-			fixed_memory32->address_length,
-			fixed_memory32->write_protect, 0);
-		break;
-	case ACPI_RESOURCE_TYPE_ADDRESS16:
-	case ACPI_RESOURCE_TYPE_ADDRESS32:
-	case ACPI_RESOURCE_TYPE_ADDRESS64:
-		pnpacpi_parse_allocated_address_space(dev, res);
-		break;
-
-	case ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64:
-		pnpacpi_parse_allocated_ext_address_space(dev, res);
-		break;
-
-	case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
-		extended_irq = &res->data.extended_irq;
-
-		if (extended_irq->interrupt_count == 0)
-			pnp_add_irq_resource(dev, 0, IORESOURCE_DISABLED);
-		else {
-			for (i = 0; i < extended_irq->interrupt_count; i++) {
-				pnpacpi_parse_allocated_irqresource(dev,
-					extended_irq->interrupts[i],
-					extended_irq->triggering,
-					extended_irq->polarity,
-					extended_irq->sharable);
-			}
-
-			/*
-			 * The IRQ encoder puts a single interrupt in each
-			 * descriptor, so if a _CRS descriptor has more than
-			 * one interrupt, we won't be able to re-encode it.
-			 */
-			if (pnp_can_write(dev) &&
-			    extended_irq->interrupt_count > 1) {
-				dev_warn(&dev->dev, "multiple interrupts in "
-					 "_CRS descriptor; configuration can't "
-					 "be changed\n");
-				dev->capabilities &= ~PNP_WRITE;
-			}
-		}
-		break;
-
 	case ACPI_RESOURCE_TYPE_GENERIC_REGISTER:
 		break;
 
@@ -531,7 +299,7 @@ static __init void pnpacpi_parse_irq_option(struct pnp_dev *dev,
 		if (p->interrupts[i])
 			__set_bit(p->interrupts[i], map.bits);
 
-	flags = irq_flags(p->triggering, p->polarity, p->sharable);
+	flags = acpi_dev_irq_flags(p->triggering, p->polarity, p->sharable);
 	pnp_register_irq_resource(dev, option_flags, &map, flags);
 }
 
@@ -555,7 +323,7 @@ static __init void pnpacpi_parse_ext_irq_option(struct pnp_dev *dev,
 		}
 	}
 
-	flags = irq_flags(p->triggering, p->polarity, p->sharable);
+	flags = acpi_dev_irq_flags(p->triggering, p->polarity, p->sharable);
 	pnp_register_irq_resource(dev, option_flags, &map, flags);
 }
 
diff --git a/drivers/pnp/resource.c b/drivers/pnp/resource.c
index b0ecacbe53b1..3e6db1c1dc29 100644
--- a/drivers/pnp/resource.c
+++ b/drivers/pnp/resource.c
@@ -503,6 +503,22 @@ static struct pnp_resource *pnp_new_resource(struct pnp_dev *dev)
 	return pnp_res;
 }
 
+struct pnp_resource *pnp_add_resource(struct pnp_dev *dev,
+				      struct resource *res)
+{
+	struct pnp_resource *pnp_res;
+
+	pnp_res = pnp_new_resource(dev);
+	if (!pnp_res) {
+		dev_err(&dev->dev, "can't add resource %pR\n", res);
+		return NULL;
+	}
+
+	pnp_res->res = *res;
+	dev_dbg(&dev->dev, "%pR\n", res);
+	return pnp_res;
+}
+
 struct pnp_resource *pnp_add_irq_resource(struct pnp_dev *dev, int irq,
 					  int flags)
 {
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 48761cb481db..16fcaf8dad3d 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -251,6 +251,16 @@ extern int pnpacpi_disabled;
 
 #define PXM_INVAL	(-1)
 
+bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res);
+bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res);
+bool acpi_dev_resource_address_space(struct acpi_resource *ares,
+				     struct resource *res);
+bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares,
+					 struct resource *res);
+unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable);
+bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
+				 struct resource *res);
+
 int acpi_check_resource_conflict(const struct resource *res);
 
 int acpi_check_region(resource_size_t start, resource_size_t n,
-- 
cgit v1.2.3-55-g7522


From 8e345c991c8c7a3c081199ef77deada79e37618a Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Thu, 15 Nov 2012 00:30:21 +0100
Subject: ACPI: Centralized processing of ACPI device resources

Currently, whoever wants to use ACPI device resources has to call
acpi_walk_resources() to browse the buffer returned by the _CRS
method for the given device and create filters passed to that
routine to apply to the individual resource items.  This generally
is cumbersome, time-consuming and inefficient.  Moreover, it may
be problematic if resource conflicts need to be resolved, because
the different users of _CRS will need to do that in a consistent
way.  However, if there are resource conflicts, the ACPI core
should be able to resolve them centrally instead of relying on
various users of acpi_walk_resources() to handle them correctly
together.

For this reason, introduce a new function, acpi_dev_get_resources(),
that can be used by subsystems to obtain a list of struct resource
objects corresponding to the ACPI device resources returned by
_CRS and, if necessary, to apply additional preprocessing routine
to the ACPI resources before converting them to the struct resource
format.

Make the ACPI code that creates platform device objects use
acpi_dev_get_resources() for resource processing instead of executing
acpi_walk_resources() twice by itself, which causes it to be much
more straightforward and easier to follow.

In the future, acpi_dev_get_resources() can be extended to meet
the needs of the ACPI PNP subsystem and other users of _CRS in
the kernel.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/acpi/acpi_platform.c |  94 ++++++------------------------
 drivers/acpi/resource.c      | 134 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/acpi.h         |  10 ++++
 3 files changed, 161 insertions(+), 77 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index bcbb00ce6d99..7ac20d8b8f07 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -19,61 +19,6 @@
 
 ACPI_MODULE_NAME("platform");
 
-struct resource_info {
-	struct device *dev;
-	struct resource *res;
-	size_t n, cur;
-};
-
-static acpi_status acpi_platform_count_resources(struct acpi_resource *res,
-						 void *data)
-{
-	struct acpi_resource_extended_irq *acpi_xirq;
-	struct acpi_resource_irq *acpi_irq;
-	struct resource_info *ri = data;
-
-	switch (res->type) {
-	case ACPI_RESOURCE_TYPE_IRQ:
-		acpi_irq = &res->data.irq;
-		ri->n += acpi_irq->interrupt_count;
-		break;
-	case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
-		acpi_xirq = &res->data.extended_irq;
-		ri->n += acpi_xirq->interrupt_count;
-		break;
-	default:
-		ri->n++;
-	}
-
-	return AE_OK;
-}
-
-static acpi_status acpi_platform_add_resources(struct acpi_resource *res,
-					       void *data)
-{
-	struct resource_info *ri = data;
-	struct resource *r;
-
-	r = ri->res + ri->cur;
-	if (acpi_dev_resource_memory(res, r)
-	    || acpi_dev_resource_io(res, r)
-	    || acpi_dev_resource_address_space(res, r)
-	    || acpi_dev_resource_ext_address_space(res, r)) {
-		ri->cur++;
-		return AE_OK;
-	}
-	if (acpi_dev_resource_interrupt(res, 0, r)) {
-		int i;
-
-		r++;
-		for (i = 1; acpi_dev_resource_interrupt(res, i, r); i++)
-			r++;
-
-		ri->cur += i;
-	}
-	return AE_OK;
-}
-
 /**
  * acpi_create_platform_device - Create platform device for ACPI device node
  * @adev: ACPI device node to create a platform device for.
@@ -89,35 +34,31 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 	struct platform_device *pdev = NULL;
 	struct acpi_device *acpi_parent;
 	struct device *parent = NULL;
-	struct resource_info ri;
-	acpi_status status;
+	struct resource_list_entry *rentry;
+	struct list_head resource_list;
+	struct resource *resources;
+	int count;
 
 	/* If the ACPI node already has a physical device attached, skip it. */
 	if (adev->physical_node_count)
 		return NULL;
 
-	memset(&ri, 0, sizeof(ri));
-	/* First, count the resources. */
-	status = acpi_walk_resources(adev->handle, METHOD_NAME__CRS,
-				     acpi_platform_count_resources, &ri);
-	if (ACPI_FAILURE(status) || !ri.n)
+	INIT_LIST_HEAD(&resource_list);
+	count = acpi_dev_get_resources(adev, &resource_list, NULL, NULL);
+	if (count <= 0)
 		return NULL;
 
-	/* Next, allocate memory for all the resources and populate it. */
-	ri.dev = &adev->dev;
-	ri.res = kzalloc(ri.n * sizeof(struct resource), GFP_KERNEL);
-	if (!ri.res) {
-		dev_err(&adev->dev,
-			"failed to allocate memory for resources\n");
+	resources = kmalloc(count * sizeof(struct resource), GFP_KERNEL);
+	if (!resources) {
+		dev_err(&adev->dev, "No memory for resources\n");
+		acpi_dev_free_resource_list(&resource_list);
 		return NULL;
 	}
+	count = 0;
+	list_for_each_entry(rentry, &resource_list, node)
+		resources[count++] = rentry->res;
 
-	status = acpi_walk_resources(adev->handle, METHOD_NAME__CRS,
-				     acpi_platform_add_resources, &ri);
-	if (ACPI_FAILURE(status)) {
-		dev_err(&adev->dev, "failed to walk resources\n");
-		goto out;
-	}
+	acpi_dev_free_resource_list(&resource_list);
 
 	/*
 	 * If the ACPI node has a parent and that parent has a physical device
@@ -140,7 +81,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 		mutex_unlock(&acpi_parent->physical_node_lock);
 	}
 	pdev = platform_device_register_resndata(parent, dev_name(&adev->dev),
-						 -1, ri.res, ri.cur, NULL, 0);
+						 -1, resources, count, NULL, 0);
 	if (IS_ERR(pdev)) {
 		dev_err(&adev->dev, "platform device creation failed: %ld\n",
 			PTR_ERR(pdev));
@@ -150,8 +91,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 			dev_name(&pdev->dev));
 	}
 
- out:
-	kfree(ri.res);
+	kfree(resources);
 	return pdev;
 }
 
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 3e7fd349e29d..2bafc25482b3 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -26,6 +26,7 @@
 #include <linux/device.h>
 #include <linux/export.h>
 #include <linux/ioport.h>
+#include <linux/slab.h>
 
 #ifdef CONFIG_X86
 #define valid_IRQ(i) (((i) != 0) && ((i) != 2))
@@ -391,3 +392,136 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
 	return true;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_resource_interrupt);
+
+/**
+ * acpi_dev_free_resource_list - Free resource from %acpi_dev_get_resources().
+ * @list: The head of the resource list to free.
+ */
+void acpi_dev_free_resource_list(struct list_head *list)
+{
+	struct resource_list_entry *rentry, *re;
+
+	list_for_each_entry_safe(rentry, re, list, node) {
+		list_del(&rentry->node);
+		kfree(rentry);
+	}
+}
+EXPORT_SYMBOL_GPL(acpi_dev_free_resource_list);
+
+struct res_proc_context {
+	struct list_head *list;
+	int (*preproc)(struct acpi_resource *, void *);
+	void *preproc_data;
+	int count;
+	int error;
+};
+
+static acpi_status acpi_dev_new_resource_entry(struct resource *r,
+					       struct res_proc_context *c)
+{
+	struct resource_list_entry *rentry;
+
+	rentry = kmalloc(sizeof(*rentry), GFP_KERNEL);
+	if (!rentry) {
+		c->error = -ENOMEM;
+		return AE_NO_MEMORY;
+	}
+	INIT_LIST_HEAD(&rentry->node);
+	rentry->res = *r;
+	list_add_tail(&rentry->node, c->list);
+	c->count++;
+	return AE_OK;
+}
+
+static acpi_status acpi_dev_process_resource(struct acpi_resource *ares,
+					     void *context)
+{
+	struct res_proc_context *c = context;
+	struct resource r;
+	int i;
+
+	if (c->preproc) {
+		int ret;
+
+		ret = c->preproc(ares, c->preproc_data);
+		if (ret < 0) {
+			c->error = ret;
+			return AE_ABORT_METHOD;
+		} else if (ret > 0) {
+			return AE_OK;
+		}
+	}
+
+	memset(&r, 0, sizeof(r));
+
+	if (acpi_dev_resource_memory(ares, &r)
+	    || acpi_dev_resource_io(ares, &r)
+	    || acpi_dev_resource_address_space(ares, &r)
+	    || acpi_dev_resource_ext_address_space(ares, &r))
+		return acpi_dev_new_resource_entry(&r, c);
+
+	for (i = 0; acpi_dev_resource_interrupt(ares, i, &r); i++) {
+		acpi_status status;
+
+		status = acpi_dev_new_resource_entry(&r, c);
+		if (ACPI_FAILURE(status))
+			return status;
+	}
+
+	return AE_OK;
+}
+
+/**
+ * acpi_dev_get_resources - Get current resources of a device.
+ * @adev: ACPI device node to get the resources for.
+ * @list: Head of the resultant list of resources (must be empty).
+ * @preproc: The caller's preprocessing routine.
+ * @preproc_data: Pointer passed to the caller's preprocessing routine.
+ *
+ * Evaluate the _CRS method for the given device node and process its output by
+ * (1) executing the @preproc() rountine provided by the caller, passing the
+ * resource pointer and @preproc_data to it as arguments, for each ACPI resource
+ * returned and (2) converting all of the returned ACPI resources into struct
+ * resource objects if possible.  If the return value of @preproc() in step (1)
+ * is different from 0, step (2) is not applied to the given ACPI resource and
+ * if that value is negative, the whole processing is aborted and that value is
+ * returned as the final error code.
+ *
+ * The resultant struct resource objects are put on the list pointed to by
+ * @list, that must be empty initially, as members of struct resource_list_entry
+ * objects.  Callers of this routine should use %acpi_dev_free_resource_list() to
+ * free that list.
+ *
+ * The number of resources in the output list is returned on success, an error
+ * code reflecting the error condition is returned otherwise.
+ */
+int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list,
+			   int (*preproc)(struct acpi_resource *, void *),
+			   void *preproc_data)
+{
+	struct res_proc_context c;
+	acpi_handle not_used;
+	acpi_status status;
+
+	if (!adev || !adev->handle || !list_empty(list))
+		return -EINVAL;
+
+	status = acpi_get_handle(adev->handle, METHOD_NAME__CRS, &not_used);
+	if (ACPI_FAILURE(status))
+		return 0;
+
+	c.list = list;
+	c.preproc = preproc;
+	c.preproc_data = preproc_data;
+	c.count = 0;
+	c.error = 0;
+	status = acpi_walk_resources(adev->handle, METHOD_NAME__CRS,
+				     acpi_dev_process_resource, &c);
+	if (ACPI_FAILURE(status)) {
+		acpi_dev_free_resource_list(list);
+		return c.error ? c.error : -EIO;
+	}
+
+	return c.count;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_get_resources);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 16fcaf8dad3d..32fbc4e73a56 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -261,6 +261,16 @@ unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable);
 bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
 				 struct resource *res);
 
+struct resource_list_entry {
+	struct list_head node;
+	struct resource res;
+};
+
+void acpi_dev_free_resource_list(struct list_head *list);
+int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list,
+			   int (*preproc)(struct acpi_resource *, void *),
+			   void *preproc_data);
+
 int acpi_check_resource_conflict(const struct resource *res);
 
 int acpi_check_region(resource_size_t start, resource_size_t n,
-- 
cgit v1.2.3-55-g7522


From f540fadf29a6987efbfa7daf10976935fd59ae7c Mon Sep 17 00:00:00 2001
From: Lv Zheng
Date: Wed, 31 Oct 2012 02:25:15 +0000
Subject: ACPICA: Fix unmerged debugger divergences.

Debugger improvements in ACPICA are always ignored by ACPICA Linux
release.  This will lead to divergences between Linux and ACPICA.
This patch fixes such unmerged debugger updates.

Following patches are included:
1. Fixed a couple compiler warnings for extra extern
   Wed, 14 Mar 2007 21:12:19 +0000
2. Cleanup for internal Reference Object.
   Wed, 27 Aug 2008 10:11:30 -0700
3. Debugger: Lock method args for multithread command.
   Fri, 24 Apr 2009 12:28:49 -0700
4. Debugger: Add max count argument for Batch command.
   Tue, 29 Sep 2009 12:31:58 -0700
5. Add new host interfaces for _OSI support.
   Thu, 5 Aug 2010 14:18:28 -0700
6. Increase debugger buffer size for method return objects.
   Wed, 17 Nov 2010 13:48:30 -0800
7. Debugger: Add command to display status of global handlers.
   Tue, 25 Jan 2011 13:47:58 -0800
8. Debugger: Split large dbcmds.c file.
   Wed, 26 Jan 2011 13:03:41 -0800
9. Debugger/AcpiExec: Add support to pass complex args to methods.
   Tue, 17 May 2011 13:33:39 -0700
10.Debugger: Add Template command to dump resource templates.
   Fri, 28 Oct 2011 14:18:51 -0700
11.Support for custom ACPICA build for ACPI 5.0 reduced hardware.
   Wed, 1 Feb 2012 13:18:17 -0800
12.Debugger: Improve command help support.
   Wed, 15 Feb 2012 07:59:26 -0800
13.Update ACPI_HW_DEPENDENT* macro invocations.
   Wed, 15 Feb 2012 08:14:08 -0800
14.Debugger: Rename function to simplify source code conversion.
   Wed, 13 Jun 2012 14:23:06 -0700
15.Debugger: Enhance "Tables" and "Unload" commands.
   Fri, 29 Jun 2012 13:10:58 -0700
16.Debugger: update prototype for AcpiDbSleep function.
   Fri, 17 Aug 2012 13:43:02 -0700

This patch will not affect the generated vmlinx binary.
This will decrease 264 lines of 20120913 divergence.diff.

Signed-off-by: Robert Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acdebug.h  | 94 ++++++++++++++++++++++++++++--------------
 drivers/acpi/acpica/acglobal.h | 69 ++++++++++++++++---------------
 drivers/acpi/acpica/aclocal.h  |  2 +
 include/acpi/acconfig.h        |  1 +
 4 files changed, 101 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index 5e8abb07724f..432a318c9ed1 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -44,17 +44,28 @@
 #ifndef __ACDEBUG_H__
 #define __ACDEBUG_H__
 
-#define ACPI_DEBUG_BUFFER_SIZE  4196
+#define ACPI_DEBUG_BUFFER_SIZE  0x4000	/* 16K buffer for return objects */
 
-struct command_info {
+struct acpi_db_command_info {
 	char *name;		/* Command Name */
 	u8 min_args;		/* Minimum arguments required */
 };
 
-struct argument_info {
+struct acpi_db_command_help {
+	u8 line_count;		/* Number of help lines */
+	char *invocation;	/* Command Invocation */
+	char *description;	/* Command Description */
+};
+
+struct acpi_db_argument_info {
 	char *name;		/* Argument Name */
 };
 
+struct acpi_db_execute_walk {
+	u32 count;
+	u32 max_count;
+};
+
 #define PARAM_LIST(pl)                  pl
 #define DBTEST_OUTPUT_LEVEL(lvl)        if (acpi_gbl_db_opt_verbose)
 #define VERBOSE_PRINT(fp)               DBTEST_OUTPUT_LEVEL(lvl) {\
@@ -77,59 +88,71 @@ acpi_db_single_step(struct acpi_walk_state *walk_state,
 /*
  * dbcmds - debug commands and output routines
  */
-acpi_status acpi_db_disassemble_method(char *name);
+struct acpi_namespace_node *acpi_db_convert_to_node(char *in_string);
 
 void acpi_db_display_table_info(char *table_arg);
 
-void acpi_db_unload_acpi_table(char *table_arg, char *instance_arg);
+void acpi_db_display_template(char *buffer_arg);
 
-void
-acpi_db_set_method_breakpoint(char *location,
-			      struct acpi_walk_state *walk_state,
-			      union acpi_parse_object *op);
+void acpi_db_unload_acpi_table(char *name);
 
-void acpi_db_set_method_call_breakpoint(union acpi_parse_object *op);
+void acpi_db_send_notify(char *name, u32 value);
 
-void acpi_db_get_bus_info(void);
+void acpi_db_display_interfaces(char *action_arg, char *interface_name_arg);
 
-void acpi_db_disassemble_aml(char *statements, union acpi_parse_object *op);
+acpi_status acpi_db_sleep(char *object_arg);
 
-void acpi_db_dump_namespace(char *start_arg, char *depth_arg);
+void acpi_db_display_locks(void);
 
-void acpi_db_dump_namespace_by_owner(char *owner_arg, char *depth_arg);
+void acpi_db_display_resources(char *object_arg);
 
-void acpi_db_send_notify(char *name, u32 value);
+ACPI_HW_DEPENDENT_RETURN_VOID(void acpi_db_display_gpes(void))
+
+void acpi_db_display_handlers(void);
+
+ACPI_HW_DEPENDENT_RETURN_VOID(void
+			      acpi_db_generate_gpe(char *gpe_arg,
+						   char *block_arg))
+
+/*
+ * dbmethod - control method commands
+ */
+void
+acpi_db_set_method_breakpoint(char *location,
+			      struct acpi_walk_state *walk_state,
+			      union acpi_parse_object *op);
+
+void acpi_db_set_method_call_breakpoint(union acpi_parse_object *op);
 
 void acpi_db_set_method_data(char *type_arg, char *index_arg, char *value_arg);
 
-acpi_status
-acpi_db_display_objects(char *obj_type_arg, char *display_count_arg);
+acpi_status acpi_db_disassemble_method(char *name);
 
-void acpi_db_display_interfaces(char *action_arg, char *interface_name_arg);
+void acpi_db_disassemble_aml(char *statements, union acpi_parse_object *op);
 
-acpi_status acpi_db_find_name_in_namespace(char *name_arg);
+void acpi_db_batch_execute(char *count_arg);
 
+/*
+ * dbnames - namespace commands
+ */
 void acpi_db_set_scope(char *name);
 
-ACPI_HW_DEPENDENT_RETURN_OK(acpi_status acpi_db_sleep(char *object_arg))
+void acpi_db_dump_namespace(char *start_arg, char *depth_arg);
 
-void acpi_db_find_references(char *object_arg);
+void acpi_db_dump_namespace_by_owner(char *owner_arg, char *depth_arg);
 
-void acpi_db_display_locks(void);
+acpi_status acpi_db_find_name_in_namespace(char *name_arg);
 
-void acpi_db_display_resources(char *object_arg);
+void acpi_db_check_predefined_names(void);
 
-ACPI_HW_DEPENDENT_RETURN_VOID(void acpi_db_display_gpes(void))
+acpi_status
+acpi_db_display_objects(char *obj_type_arg, char *display_count_arg);
 
 void acpi_db_check_integrity(void);
 
-ACPI_HW_DEPENDENT_RETURN_VOID(void
-			      acpi_db_generate_gpe(char *gpe_arg,
-						   char *block_arg))
-
-void acpi_db_check_predefined_names(void);
+void acpi_db_find_references(char *object_arg);
 
-void acpi_db_batch_execute(void);
+void acpi_db_get_bus_info(void);
 
 /*
  * dbdisply - debug display commands
@@ -161,7 +184,8 @@ acpi_db_display_argument_object(union acpi_operand_object *obj_desc,
 /*
  * dbexec - debugger control method execution
  */
-void acpi_db_execute(char *name, char **args, u32 flags);
+void
+acpi_db_execute(char *name, char **args, acpi_object_type * types, u32 flags);
 
 void
 acpi_db_create_execution_threads(char *num_threads_arg,
@@ -175,7 +199,8 @@ u32 acpi_db_get_cache_info(struct acpi_memory_list *cache);
  * dbfileio - Debugger file I/O commands
  */
 acpi_object_type
-acpi_db_match_argument(char *user_argument, struct argument_info *arguments);
+acpi_db_match_argument(char *user_argument,
+		       struct acpi_db_argument_info *arguments);
 
 void acpi_db_close_debug_file(void);
 
@@ -208,6 +233,11 @@ acpi_db_command_dispatch(char *input_buffer,
 
 void ACPI_SYSTEM_XFACE acpi_db_execute_thread(void *context);
 
+acpi_status acpi_db_user_commands(char prompt, union acpi_parse_object *op);
+
+char *acpi_db_get_next_token(char *string,
+			     char **next, acpi_object_type * return_type);
+
 /*
  * dbstats - Generation and display of ACPI table statistics
  */
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index ce79100fb5eb..fe20e186ca10 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -153,26 +153,6 @@ u8 acpi_gbl_reduced_hardware;
 
 ACPI_EXTERN u8 ACPI_INIT_GLOBAL(acpi_gbl_no_resource_disassembly, FALSE);
 
-/*****************************************************************************
- *
- * Debug support
- *
- ****************************************************************************/
-
-/* Procedure nesting level for debug output */
-
-extern u32 acpi_gbl_nesting_level;
-
-ACPI_EXTERN u32 acpi_gpe_count;
-ACPI_EXTERN u32 acpi_fixed_event_count[ACPI_NUM_FIXED_EVENTS];
-
-/* Support for dynamic control method tracing mechanism */
-
-ACPI_EXTERN u32 acpi_gbl_original_dbg_level;
-ACPI_EXTERN u32 acpi_gbl_original_dbg_layer;
-ACPI_EXTERN u32 acpi_gbl_trace_dbg_level;
-ACPI_EXTERN u32 acpi_gbl_trace_dbg_layer;
-
 /*****************************************************************************
  *
  * ACPI Table globals
@@ -259,15 +239,6 @@ ACPI_EXTERN acpi_spinlock acpi_gbl_hardware_lock;	/* For ACPI H/W except GPE reg
  *
  ****************************************************************************/
 
-#ifdef ACPI_DBG_TRACK_ALLOCATIONS
-
-/* Lists for tracking memory allocations */
-
-ACPI_EXTERN struct acpi_memory_list *acpi_gbl_global_list;
-ACPI_EXTERN struct acpi_memory_list *acpi_gbl_ns_node_list;
-ACPI_EXTERN u8 acpi_gbl_display_final_mem_stats;
-#endif
-
 /* Object caches */
 
 ACPI_EXTERN acpi_cache_t *acpi_gbl_namespace_cache;
@@ -326,6 +297,15 @@ extern const char *acpi_gbl_region_types[ACPI_NUM_PREDEFINED_REGIONS];
 
 #endif
 
+#ifdef ACPI_DBG_TRACK_ALLOCATIONS
+
+/* Lists for tracking memory allocations */
+
+ACPI_EXTERN struct acpi_memory_list *acpi_gbl_global_list;
+ACPI_EXTERN struct acpi_memory_list *acpi_gbl_ns_node_list;
+ACPI_EXTERN u8 acpi_gbl_display_final_mem_stats;
+#endif
+
 /*****************************************************************************
  *
  * Namespace globals
@@ -401,6 +381,28 @@ ACPI_EXTERN void *acpi_gbl_global_event_handler_context;
 
 #endif				/* !ACPI_REDUCED_HARDWARE */
 
+/*****************************************************************************
+ *
+ * Debug support
+ *
+ ****************************************************************************/
+
+/* Procedure nesting level for debug output */
+
+extern u32 acpi_gbl_nesting_level;
+
+/* Event counters */
+
+ACPI_EXTERN u32 acpi_gpe_count;
+ACPI_EXTERN u32 acpi_fixed_event_count[ACPI_NUM_FIXED_EVENTS];
+
+/* Support for dynamic control method tracing mechanism */
+
+ACPI_EXTERN u32 acpi_gbl_original_dbg_level;
+ACPI_EXTERN u32 acpi_gbl_original_dbg_layer;
+ACPI_EXTERN u32 acpi_gbl_trace_dbg_level;
+ACPI_EXTERN u32 acpi_gbl_trace_dbg_layer;
+
 /*****************************************************************************
  *
  * Debugger globals
@@ -426,10 +428,11 @@ ACPI_EXTERN u8 acpi_gbl_db_opt_stats;
 ACPI_EXTERN u8 acpi_gbl_db_opt_ini_methods;
 
 ACPI_EXTERN char *acpi_gbl_db_args[ACPI_DEBUGGER_MAX_ARGS];
-ACPI_EXTERN char acpi_gbl_db_line_buf[80];
-ACPI_EXTERN char acpi_gbl_db_parsed_buf[80];
-ACPI_EXTERN char acpi_gbl_db_scope_buf[40];
-ACPI_EXTERN char acpi_gbl_db_debug_filename[40];
+ACPI_EXTERN acpi_object_type acpi_gbl_db_arg_types[ACPI_DEBUGGER_MAX_ARGS];
+ACPI_EXTERN char acpi_gbl_db_line_buf[ACPI_DB_LINE_BUFFER_SIZE];
+ACPI_EXTERN char acpi_gbl_db_parsed_buf[ACPI_DB_LINE_BUFFER_SIZE];
+ACPI_EXTERN char acpi_gbl_db_scope_buf[80];
+ACPI_EXTERN char acpi_gbl_db_debug_filename[80];
 ACPI_EXTERN u8 acpi_gbl_db_output_to_file;
 ACPI_EXTERN char *acpi_gbl_db_buffer;
 ACPI_EXTERN char *acpi_gbl_db_filename;
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index c816ee675094..b5a4651cf2b7 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -1031,6 +1031,7 @@ struct acpi_db_method_info {
 	acpi_handle method;
 	acpi_handle main_thread_gate;
 	acpi_handle thread_complete_gate;
+	acpi_handle info_gate;
 	acpi_thread_id *threads;
 	u32 num_threads;
 	u32 num_created;
@@ -1041,6 +1042,7 @@ struct acpi_db_method_info {
 	u32 num_loops;
 	char pathname[128];
 	char **args;
+	acpi_object_type *types;
 
 	/*
 	 * Arguments to be passed to method for the command
diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h
index 03f14856bd09..0943457e0fa5 100644
--- a/include/acpi/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -241,6 +241,7 @@
  *****************************************************************************/
 
 #define ACPI_DEBUGGER_MAX_ARGS          8	/* Must be max method args + 1 */
+#define ACPI_DB_LINE_BUFFER_SIZE	512
 
 #define ACPI_DEBUGGER_COMMAND_PROMPT    '-'
 #define ACPI_DEBUGGER_EXECUTE_PROMPT    '%'
-- 
cgit v1.2.3-55-g7522


From 78e25fef2751434f38c7f711ecbf8762f79f7318 Mon Sep 17 00:00:00 2001
From: Lv Zheng
Date: Wed, 31 Oct 2012 02:25:24 +0000
Subject: ACPICA: Fix divergences of definition conflicts.

There are conflicts in the "acpi_device_id*" definitions between the
Linux and the ACPICA.  The definitions of acpi_device_id* in ACPICA
have been changed to the "acpi_pnp_device_id*".  This patch changes
the corresponding "acpica_device_id*" definitiions in the Linux.

This patch will not affect the generated vmlinx binary.
This will decrease 298 lines of 20120913 divergence.diff.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acutils.h  |  6 +++---
 drivers/acpi/acpica/evrgnini.c |  4 ++--
 drivers/acpi/acpica/nsxfeval.c |  4 ++--
 drivers/acpi/acpica/nsxfname.c | 28 ++++++++++++++--------------
 drivers/acpi/acpica/utids.c    | 37 ++++++++++++++++++++-----------------
 drivers/acpi/scan.c            |  2 +-
 include/acpi/actypes.h         | 12 ++++++------
 7 files changed, 48 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 82d6025332e9..d94b41776575 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -355,15 +355,15 @@ acpi_ut_execute_power_methods(struct acpi_namespace_node *device_node,
  */
 acpi_status
 acpi_ut_execute_HID(struct acpi_namespace_node *device_node,
-		    struct acpica_device_id ** return_id);
+		    struct acpi_pnp_device_id ** return_id);
 
 acpi_status
 acpi_ut_execute_UID(struct acpi_namespace_node *device_node,
-		    struct acpica_device_id ** return_id);
+		    struct acpi_pnp_device_id ** return_id);
 
 acpi_status
 acpi_ut_execute_CID(struct acpi_namespace_node *device_node,
-		    struct acpica_device_id_list ** return_cid_list);
+		    struct acpi_pnp_device_id_list ** return_cid_list);
 
 /*
  * utlock - reader/writer locks
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index 4c1c8261166f..6786f00042cd 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -350,8 +350,8 @@ acpi_ev_pci_config_region_setup(acpi_handle handle,
 static u8 acpi_ev_is_pci_root_bridge(struct acpi_namespace_node *node)
 {
 	acpi_status status;
-	struct acpica_device_id *hid;
-	struct acpica_device_id_list *cid;
+	struct acpi_pnp_device_id *hid;
+	struct acpi_pnp_device_id_list *cid;
 	u32 i;
 	u8 match;
 
diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c
index 9692e6702333..494f2ebd623a 100644
--- a/drivers/acpi/acpica/nsxfeval.c
+++ b/drivers/acpi/acpica/nsxfeval.c
@@ -542,8 +542,8 @@ acpi_ns_get_device_callback(acpi_handle obj_handle,
 	acpi_status status;
 	struct acpi_namespace_node *node;
 	u32 flags;
-	struct acpica_device_id *hid;
-	struct acpica_device_id_list *cid;
+	struct acpi_pnp_device_id *hid;
+	struct acpi_pnp_device_id_list *cid;
 	u32 i;
 	u8 found;
 	int no_match;
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index 08e9610b34ca..7bc4985146f8 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -53,8 +53,8 @@
 ACPI_MODULE_NAME("nsxfname")
 
 /* Local prototypes */
-static char *acpi_ns_copy_device_id(struct acpica_device_id *dest,
-				    struct acpica_device_id *source,
+static char *acpi_ns_copy_device_id(struct acpi_pnp_device_id *dest,
+				    struct acpi_pnp_device_id *source,
 				    char *string_area);
 
 /******************************************************************************
@@ -219,20 +219,20 @@ ACPI_EXPORT_SYMBOL(acpi_get_name)
  *
  * FUNCTION:    acpi_ns_copy_device_id
  *
- * PARAMETERS:  dest                - Pointer to the destination DEVICE_ID
- *              source              - Pointer to the source DEVICE_ID
+ * PARAMETERS:  dest                - Pointer to the destination PNP_DEVICE_ID
+ *              source              - Pointer to the source PNP_DEVICE_ID
  *              string_area         - Pointer to where to copy the dest string
  *
  * RETURN:      Pointer to the next string area
  *
- * DESCRIPTION: Copy a single DEVICE_ID, including the string data.
+ * DESCRIPTION: Copy a single PNP_DEVICE_ID, including the string data.
  *
  ******************************************************************************/
-static char *acpi_ns_copy_device_id(struct acpica_device_id *dest,
-				    struct acpica_device_id *source,
+static char *acpi_ns_copy_device_id(struct acpi_pnp_device_id *dest,
+				    struct acpi_pnp_device_id *source,
 				    char *string_area)
 {
-	/* Create the destination DEVICE_ID */
+	/* Create the destination PNP_DEVICE_ID */
 
 	dest->string = string_area;
 	dest->length = source->length;
@@ -269,9 +269,9 @@ acpi_get_object_info(acpi_handle handle,
 {
 	struct acpi_namespace_node *node;
 	struct acpi_device_info *info;
-	struct acpica_device_id_list *cid_list = NULL;
-	struct acpica_device_id *hid = NULL;
-	struct acpica_device_id *uid = NULL;
+	struct acpi_pnp_device_id_list *cid_list = NULL;
+	struct acpi_pnp_device_id *hid = NULL;
+	struct acpi_pnp_device_id *uid = NULL;
 	char *next_id_string;
 	acpi_object_type type;
 	acpi_name name;
@@ -348,7 +348,7 @@ acpi_get_object_info(acpi_handle handle,
 
 			info_size +=
 			    (cid_list->list_size -
-			     sizeof(struct acpica_device_id_list));
+			     sizeof(struct acpi_pnp_device_id_list));
 			valid |= ACPI_VALID_CID;
 		}
 	}
@@ -418,11 +418,11 @@ acpi_get_object_info(acpi_handle handle,
 	next_id_string = ACPI_CAST_PTR(char, info->compatible_id_list.ids);
 	if (cid_list) {
 
-		/* Point past the CID DEVICE_ID array */
+		/* Point past the CID PNP_DEVICE_ID array */
 
 		next_id_string +=
 		    ((acpi_size) cid_list->count *
-		     sizeof(struct acpica_device_id));
+		     sizeof(struct acpi_pnp_device_id));
 	}
 
 	/*
diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c
index 5d84e1954575..f18ac81c8399 100644
--- a/drivers/acpi/acpica/utids.c
+++ b/drivers/acpi/acpica/utids.c
@@ -67,10 +67,10 @@ ACPI_MODULE_NAME("utids")
  ******************************************************************************/
 acpi_status
 acpi_ut_execute_HID(struct acpi_namespace_node *device_node,
-		    struct acpica_device_id **return_id)
+		    struct acpi_pnp_device_id **return_id)
 {
 	union acpi_operand_object *obj_desc;
-	struct acpica_device_id *hid;
+	struct acpi_pnp_device_id *hid;
 	u32 length;
 	acpi_status status;
 
@@ -94,16 +94,17 @@ acpi_ut_execute_HID(struct acpi_namespace_node *device_node,
 	/* Allocate a buffer for the HID */
 
 	hid =
-	    ACPI_ALLOCATE_ZEROED(sizeof(struct acpica_device_id) +
+	    ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_pnp_device_id) +
 				 (acpi_size) length);
 	if (!hid) {
 		status = AE_NO_MEMORY;
 		goto cleanup;
 	}
 
-	/* Area for the string starts after DEVICE_ID struct */
+	/* Area for the string starts after PNP_DEVICE_ID struct */
 
-	hid->string = ACPI_ADD_PTR(char, hid, sizeof(struct acpica_device_id));
+	hid->string =
+	    ACPI_ADD_PTR(char, hid, sizeof(struct acpi_pnp_device_id));
 
 	/* Convert EISAID to a string or simply copy existing string */
 
@@ -144,10 +145,10 @@ cleanup:
 
 acpi_status
 acpi_ut_execute_UID(struct acpi_namespace_node *device_node,
-		    struct acpica_device_id **return_id)
+		    struct acpi_pnp_device_id **return_id)
 {
 	union acpi_operand_object *obj_desc;
-	struct acpica_device_id *uid;
+	struct acpi_pnp_device_id *uid;
 	u32 length;
 	acpi_status status;
 
@@ -171,16 +172,17 @@ acpi_ut_execute_UID(struct acpi_namespace_node *device_node,
 	/* Allocate a buffer for the UID */
 
 	uid =
-	    ACPI_ALLOCATE_ZEROED(sizeof(struct acpica_device_id) +
+	    ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_pnp_device_id) +
 				 (acpi_size) length);
 	if (!uid) {
 		status = AE_NO_MEMORY;
 		goto cleanup;
 	}
 
-	/* Area for the string starts after DEVICE_ID struct */
+	/* Area for the string starts after PNP_DEVICE_ID struct */
 
-	uid->string = ACPI_ADD_PTR(char, uid, sizeof(struct acpica_device_id));
+	uid->string =
+	    ACPI_ADD_PTR(char, uid, sizeof(struct acpi_pnp_device_id));
 
 	/* Convert an Integer to string, or just copy an existing string */
 
@@ -226,11 +228,11 @@ cleanup:
 
 acpi_status
 acpi_ut_execute_CID(struct acpi_namespace_node *device_node,
-		    struct acpica_device_id_list **return_cid_list)
+		    struct acpi_pnp_device_id_list **return_cid_list)
 {
 	union acpi_operand_object **cid_objects;
 	union acpi_operand_object *obj_desc;
-	struct acpica_device_id_list *cid_list;
+	struct acpi_pnp_device_id_list *cid_list;
 	char *next_id_string;
 	u32 string_area_size;
 	u32 length;
@@ -288,11 +290,12 @@ acpi_ut_execute_CID(struct acpi_namespace_node *device_node,
 	/*
 	 * Now that we know the length of the CIDs, allocate return buffer:
 	 * 1) Size of the base structure +
-	 * 2) Size of the CID DEVICE_ID array +
+	 * 2) Size of the CID PNP_DEVICE_ID array +
 	 * 3) Size of the actual CID strings
 	 */
-	cid_list_size = sizeof(struct acpica_device_id_list) +
-	    ((count - 1) * sizeof(struct acpica_device_id)) + string_area_size;
+	cid_list_size = sizeof(struct acpi_pnp_device_id_list) +
+	    ((count - 1) * sizeof(struct acpi_pnp_device_id)) +
+	    string_area_size;
 
 	cid_list = ACPI_ALLOCATE_ZEROED(cid_list_size);
 	if (!cid_list) {
@@ -300,10 +303,10 @@ acpi_ut_execute_CID(struct acpi_namespace_node *device_node,
 		goto cleanup;
 	}
 
-	/* Area for CID strings starts after the CID DEVICE_ID array */
+	/* Area for CID strings starts after the CID PNP_DEVICE_ID array */
 
 	next_id_string = ACPI_CAST_PTR(char, cid_list->ids) +
-	    ((acpi_size) count * sizeof(struct acpica_device_id));
+	    ((acpi_size) count * sizeof(struct acpi_pnp_device_id));
 
 	/* Copy/convert the CIDs to the return buffer */
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 1fcb8678665c..db127100bd9d 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1185,7 +1185,7 @@ static void acpi_device_set_id(struct acpi_device *device)
 {
 	acpi_status status;
 	struct acpi_device_info *info;
-	struct acpica_device_id_list *cid_list;
+	struct acpi_pnp_device_id_list *cid_list;
 	int i;
 
 	switch (device->device_type) {
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index a85bae968262..7520f420e4ee 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -1020,15 +1020,15 @@ u32 (*acpi_interface_handler) (acpi_string interface_name, u32 supported);
 
 /* Structures used for device/processor HID, UID, CID */
 
-struct acpica_device_id {
+struct acpi_pnp_device_id {
 	u32 length;		/* Length of string + null */
 	char *string;
 };
 
-struct acpica_device_id_list {
+struct acpi_pnp_device_id_list {
 	u32 count;		/* Number of IDs in Ids array */
 	u32 list_size;		/* Size of list, including ID strings */
-	struct acpica_device_id ids[1];	/* ID array */
+	struct acpi_pnp_device_id ids[1];	/* ID array */
 };
 
 /*
@@ -1046,9 +1046,9 @@ struct acpi_device_info {
 	u8 lowest_dstates[5];	/* _sx_w values: 0xFF indicates not valid */
 	u32 current_status;	/* _STA value */
 	u64 address;	/* _ADR value */
-	struct acpica_device_id hardware_id;	/* _HID value */
-	struct acpica_device_id unique_id;	/* _UID value */
-	struct acpica_device_id_list compatible_id_list;	/* _CID list <must be last> */
+	struct acpi_pnp_device_id hardware_id;	/* _HID value */
+	struct acpi_pnp_device_id unique_id;	/* _UID value */
+	struct acpi_pnp_device_id_list compatible_id_list;	/* _CID list <must be last> */
 };
 
 /* Values for Flags field above (acpi_get_object_info) */
-- 
cgit v1.2.3-55-g7522


From 644ef74e6d187ca2e8a23ff41a513964de36f93e Mon Sep 17 00:00:00 2001
From: Lv Zheng
Date: Wed, 31 Oct 2012 02:25:36 +0000
Subject: ACPICA: Fix AcpiSrc caused divergences.

There are definitions that can been converted into new styles by
the recent AcpiSrc while they remain the old styles in the Linux.
This patch fixes those definitions that will be converted by the
AcpiSrc.

This patch will not affect the generated vmlinux binary.
This will decrease 97 lines of 20120913 divergence.diff.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acglobal.h | 2 +-
 drivers/acpi/acpica/aclocal.h  | 4 ++--
 drivers/acpi/acpica/acobject.h | 2 +-
 drivers/acpi/acpica/dswexec.c  | 2 +-
 drivers/acpi/acpica/evxface.c  | 2 +-
 drivers/acpi/sysfs.c           | 4 ++--
 include/acpi/acpixf.h          | 2 +-
 include/acpi/actypes.h         | 8 ++++----
 8 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index fe20e186ca10..35006d193d51 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -376,7 +376,7 @@ ACPI_EXTERN struct acpi_gpe_block_info
 #if (!ACPI_REDUCED_HARDWARE)
 
 ACPI_EXTERN u8 acpi_gbl_all_gpes_initialized;
-ACPI_EXTERN ACPI_GBL_EVENT_HANDLER acpi_gbl_global_event_handler;
+ACPI_EXTERN acpi_gbl_event_handler acpi_gbl_global_event_handler;
 ACPI_EXTERN void *acpi_gbl_global_event_handler_context;
 
 #endif				/* !ACPI_REDUCED_HARDWARE */
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index b5a4651cf2b7..564f2abf5904 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -262,7 +262,7 @@ struct acpi_create_field_info {
 };
 
 typedef
-acpi_status(*ACPI_INTERNAL_METHOD) (struct acpi_walk_state * walk_state);
+acpi_status(*acpi_internal_method) (struct acpi_walk_state * walk_state);
 
 /*
  * Bitmapped ACPI types.  Used internally only
@@ -645,7 +645,7 @@ union acpi_generic_state {
  *
  ****************************************************************************/
 
-typedef acpi_status(*ACPI_EXECUTE_OP) (struct acpi_walk_state * walk_state);
+typedef acpi_status(*acpi_execute_op) (struct acpi_walk_state * walk_state);
 
 /* Address Range info block */
 
diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index 364a1303fb8f..ac4269fb1a37 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -179,7 +179,7 @@ struct acpi_object_method {
 	union acpi_operand_object *mutex;
 	u8 *aml_start;
 	union {
-		ACPI_INTERNAL_METHOD implementation;
+		acpi_internal_method implementation;
 		union acpi_operand_object *handler;
 	} dispatch;
 
diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c
index 642f3c053e87..fa44609aba33 100644
--- a/drivers/acpi/acpica/dswexec.c
+++ b/drivers/acpi/acpica/dswexec.c
@@ -57,7 +57,7 @@ ACPI_MODULE_NAME("dswexec")
 /*
  * Dispatch table for opcode classes
  */
-static ACPI_EXECUTE_OP acpi_gbl_op_type_dispatch[] = {
+static acpi_execute_op acpi_gbl_op_type_dispatch[] = {
 	acpi_ex_opcode_0A_0T_1R,
 	acpi_ex_opcode_1A_0T_0R,
 	acpi_ex_opcode_1A_0T_1R,
diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index 7587eb6c9584..ae668f32cf16 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -398,7 +398,7 @@ ACPI_EXPORT_SYMBOL(acpi_install_exception_handler)
  *
  ******************************************************************************/
 acpi_status
-acpi_install_global_event_handler(ACPI_GBL_EVENT_HANDLER handler, void *context)
+acpi_install_global_event_handler(acpi_gbl_event_handler handler, void *context)
 {
 	acpi_status status;
 
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 7c3f98ba4afe..ea61ca9129cd 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -476,7 +476,7 @@ static void fixed_event_count(u32 event_number)
 	return;
 }
 
-static void acpi_gbl_event_handler(u32 event_type, acpi_handle device,
+static void acpi_global_event_handler(u32 event_type, acpi_handle device,
 	u32 event_number, void *context)
 {
 	if (event_type == ACPI_EVENT_TYPE_GPE)
@@ -638,7 +638,7 @@ void acpi_irq_stats_init(void)
 	if (all_counters == NULL)
 		goto fail;
 
-	status = acpi_install_global_event_handler(acpi_gbl_event_handler, NULL);
+	status = acpi_install_global_event_handler(acpi_global_event_handler, NULL);
 	if (ACPI_FAILURE(status))
 		goto fail;
 
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 8b891dbead66..352fd1a38321 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -274,7 +274,7 @@ acpi_install_initialization_handler(acpi_init_handler handler, u32 function);
 
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_install_global_event_handler
-				(ACPI_GBL_EVENT_HANDLER handler, void *context))
+				(acpi_gbl_event_handler handler, void *context))
 
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_install_fixed_event_handler(u32
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 7520f420e4ee..ea50a314e552 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -796,11 +796,11 @@ typedef u8 acpi_adr_space_type;
 
 /* Sleep function dispatch */
 
-typedef acpi_status(*ACPI_SLEEP_FUNCTION) (u8 sleep_state);
+typedef acpi_status(*acpi_sleep_function) (u8 sleep_state);
 
 struct acpi_sleep_functions {
-	ACPI_SLEEP_FUNCTION legacy_function;
-	ACPI_SLEEP_FUNCTION extended_function;
+	acpi_sleep_function legacy_function;
+	acpi_sleep_function extended_function;
 };
 
 /*
@@ -931,7 +931,7 @@ typedef void
  * Various handlers and callback procedures
  */
 typedef
-void (*ACPI_GBL_EVENT_HANDLER) (u32 event_type,
+void (*acpi_gbl_event_handler) (u32 event_type,
 			       acpi_handle device,
 			       u32 event_number, void *context);
 
-- 
cgit v1.2.3-55-g7522


From 1f86e8c1c9f129d450fd75e42d25ddba69a522ac Mon Sep 17 00:00:00 2001
From: Lv Zheng
Date: Wed, 31 Oct 2012 02:25:45 +0000
Subject: ACPICA: Fix indent caused divergences.

New version of "indent" program will generate different outputs that
will lead to the divergences between the Linux and the ACPICA.
This patch fixes such divergences caused by the "indent" program.
The version of the "indent" used for this patch is "GNU indent 2.2.11".

This patch will not affect the generated vmlinux binary.
This will decrease 581 lines of 20120913 divergence.diff.

Signed-off-by: Robert Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acdispat.h  | 11 +++++++----
 drivers/acpi/acpica/acevents.h  |  6 ++++--
 drivers/acpi/acpica/aclocal.h   |  6 ++++--
 drivers/acpi/acpica/acparser.h  |  3 +--
 drivers/acpi/acpica/acpredef.h  | 11 ++++++-----
 drivers/acpi/acpica/dsopcode.c  |  3 ++-
 drivers/acpi/acpica/dsutils.c   |  3 ++-
 drivers/acpi/acpica/dswstate.c  | 14 +++++++++-----
 drivers/acpi/acpica/evgpe.c     | 20 ++++++++++++--------
 drivers/acpi/acpica/evgpeblk.c  |  3 ++-
 drivers/acpi/acpica/evgpeutil.c |  3 ++-
 drivers/acpi/acpica/evrgnini.c  |  3 +--
 drivers/acpi/acpica/evxfgpe.c   |  9 +++++----
 drivers/acpi/acpica/exconvrt.c  |  4 ++--
 drivers/acpi/acpica/excreate.c  |  3 +--
 drivers/acpi/acpica/exdump.c    |  9 ++++++---
 drivers/acpi/acpica/exfldio.c   |  3 +--
 drivers/acpi/acpica/exnames.c   |  6 +++---
 drivers/acpi/acpica/exresop.c   |  3 ++-
 drivers/acpi/acpica/hwgpe.c     |  3 ++-
 drivers/acpi/acpica/hwtimer.c   |  3 +--
 drivers/acpi/acpica/hwxfsleep.c | 12 ++++--------
 drivers/acpi/acpica/nsaccess.c  |  3 +--
 drivers/acpi/acpica/nsinit.c    |  4 ++--
 drivers/acpi/acpica/psopcode.c  | 23 ++++++++++++++---------
 drivers/acpi/acpica/psparse.c   |  5 +++--
 drivers/acpi/acpica/rscalc.c    |  3 +--
 include/acpi/acpixf.h           | 13 +++++--------
 include/acpi/actypes.h          |  6 ++++--
 29 files changed, 109 insertions(+), 89 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acdispat.h b/drivers/acpi/acpica/acdispat.h
index 5935ba6707e2..ed33ebcdaebe 100644
--- a/drivers/acpi/acpica/acdispat.h
+++ b/drivers/acpi/acpica/acdispat.h
@@ -309,10 +309,13 @@ acpi_ds_obj_stack_push(void *object, struct acpi_walk_state *walk_state);
 acpi_status
 acpi_ds_obj_stack_pop(u32 pop_count, struct acpi_walk_state *walk_state);
 
-struct acpi_walk_state *acpi_ds_create_walk_state(acpi_owner_id owner_id, union acpi_parse_object
-						  *origin, union acpi_operand_object
-						  *mth_desc, struct acpi_thread_state
-						  *thread);
+struct acpi_walk_state * acpi_ds_create_walk_state(acpi_owner_id owner_id,
+						   union acpi_parse_object
+						   *origin,
+						   union acpi_operand_object
+						   *mth_desc,
+						   struct acpi_thread_state
+						   *thread);
 
 acpi_status
 acpi_ds_init_aml_walk(struct acpi_walk_state *walk_state,
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index c0a43b38c6a3..e975c6720448 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -84,9 +84,11 @@ acpi_ev_update_gpe_enable_mask(struct acpi_gpe_event_info *gpe_event_info);
 
 acpi_status acpi_ev_enable_gpe(struct acpi_gpe_event_info *gpe_event_info);
 
-acpi_status acpi_ev_add_gpe_reference(struct acpi_gpe_event_info *gpe_event_info);
+acpi_status
+acpi_ev_add_gpe_reference(struct acpi_gpe_event_info *gpe_event_info);
 
-acpi_status acpi_ev_remove_gpe_reference(struct acpi_gpe_event_info *gpe_event_info);
+acpi_status
+acpi_ev_remove_gpe_reference(struct acpi_gpe_event_info *gpe_event_info);
 
 struct acpi_gpe_event_info *acpi_ev_get_gpe_event_info(acpi_handle gpe_device,
 						       u32 gpe_number);
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 564f2abf5904..5b5be40a1997 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -486,8 +486,10 @@ struct acpi_gpe_device_info {
 	struct acpi_namespace_node *gpe_device;
 };
 
-typedef acpi_status(*acpi_gpe_callback) (struct acpi_gpe_xrupt_info *gpe_xrupt_info,
-		struct acpi_gpe_block_info *gpe_block, void *context);
+typedef acpi_status(*acpi_gpe_callback) (struct acpi_gpe_xrupt_info *
+					 gpe_xrupt_info,
+					 struct acpi_gpe_block_info *gpe_block,
+					 void *context);
 
 /* Information about each particular fixed event */
 
diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h
index b725d780d34d..eefcf47a61a0 100644
--- a/drivers/acpi/acpica/acparser.h
+++ b/drivers/acpi/acpica/acparser.h
@@ -150,8 +150,7 @@ u8 acpi_ps_has_completed_scope(struct acpi_parse_state *parser_state);
 
 void
 acpi_ps_pop_scope(struct acpi_parse_state *parser_state,
-		  union acpi_parse_object **op,
-		  u32 * arg_list, u32 * arg_count);
+		  union acpi_parse_object **op, u32 *arg_list, u32 *arg_count);
 
 acpi_status
 acpi_ps_push_scope(struct acpi_parse_state *parser_state,
diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h
index 3080c017f5ba..9dfa1c83bd4e 100644
--- a/drivers/acpi/acpica/acpredef.h
+++ b/drivers/acpi/acpica/acpredef.h
@@ -150,8 +150,7 @@ enum acpi_return_package_types {
  * is saved here (rather than in a separate table) in order to minimize the
  * overall size of the stored data.
  */
-static const union acpi_predefined_info predefined_names[] =
-{
+static const union acpi_predefined_info predefined_names[] = {
 	{{"_AC0", 0, ACPI_RTYPE_INTEGER}},
 	{{"_AC1", 0, ACPI_RTYPE_INTEGER}},
 	{{"_AC2", 0, ACPI_RTYPE_INTEGER}},
@@ -538,7 +537,8 @@ static const union acpi_predefined_info predefined_names[] =
 
 	/* Acpi 1.0 defined _WAK with no return value. Later, it was changed to return a package */
 
-	{{"_WAK", 1, ACPI_RTYPE_NONE | ACPI_RTYPE_INTEGER | ACPI_RTYPE_PACKAGE}},
+	{{"_WAK", 1,
+          ACPI_RTYPE_NONE | ACPI_RTYPE_INTEGER | ACPI_RTYPE_PACKAGE}},
 			  {{{ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 2,0}, 0,0}}, /* Fixed-length (2 Int), but is optional */
 
 	/* _WDG/_WED are MS extensions defined by "Windows Instrumentation" */
@@ -551,11 +551,12 @@ static const union acpi_predefined_info predefined_names[] =
 };
 
 #if 0
+
 	/* This is an internally implemented control method, no need to check */
-	{{"_OSI", 1, ACPI_RTYPE_INTEGER}},
+{ {
+"_OSI", 1, ACPI_RTYPE_INTEGER}},
 
 	/* TBD: */
-
 	_PRT - currently ignore reversed entries. attempt to fix here?
 	think about possibly fixing package elements like _BIF, etc.
 #endif
diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c
index aa34d8984d34..0df024e5fb63 100644
--- a/drivers/acpi/acpica/dsopcode.c
+++ b/drivers/acpi/acpica/dsopcode.c
@@ -649,7 +649,8 @@ acpi_ds_eval_data_object_operands(struct acpi_walk_state *walk_state,
 		    ((op->common.parent->common.aml_opcode != AML_PACKAGE_OP) &&
 		     (op->common.parent->common.aml_opcode !=
 		      AML_VAR_PACKAGE_OP)
-		     && (op->common.parent->common.aml_opcode != AML_NAME_OP))) {
+		     && (op->common.parent->common.aml_opcode !=
+			 AML_NAME_OP))) {
 			walk_state->result_obj = obj_desc;
 		}
 	}
diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c
index 73a5447475f5..4bbdd6c7a3d0 100644
--- a/drivers/acpi/acpica/dsutils.c
+++ b/drivers/acpi/acpica/dsutils.c
@@ -560,7 +560,8 @@ acpi_ds_create_operand(struct acpi_walk_state *walk_state,
 					 * indicate this to the interpreter, set the
 					 * object to the root
 					 */
-					obj_desc = ACPI_CAST_PTR(union
+					obj_desc =
+					    ACPI_CAST_PTR(union
 								 acpi_operand_object,
 								 acpi_gbl_root_node);
 					status = AE_OK;
diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c
index d0e6555061e4..9bb7fa45e240 100644
--- a/drivers/acpi/acpica/dswstate.c
+++ b/drivers/acpi/acpica/dswstate.c
@@ -51,8 +51,9 @@
 ACPI_MODULE_NAME("dswstate")
 
   /* Local prototypes */
-static acpi_status acpi_ds_result_stack_push(struct acpi_walk_state *ws);
-static acpi_status acpi_ds_result_stack_pop(struct acpi_walk_state *ws);
+static acpi_status
+acpi_ds_result_stack_push(struct acpi_walk_state *walk_state);
+static acpi_status acpi_ds_result_stack_pop(struct acpi_walk_state *walk_state);
 
 /*******************************************************************************
  *
@@ -536,9 +537,12 @@ struct acpi_walk_state *acpi_ds_pop_walk_state(struct acpi_thread_state *thread)
  *
  ******************************************************************************/
 
-struct acpi_walk_state *acpi_ds_create_walk_state(acpi_owner_id owner_id, union acpi_parse_object
-						  *origin, union acpi_operand_object
-						  *method_desc, struct acpi_thread_state
+struct acpi_walk_state *acpi_ds_create_walk_state(acpi_owner_id owner_id,
+						  union acpi_parse_object
+						  *origin,
+						  union acpi_operand_object
+						  *method_desc,
+						  struct acpi_thread_state
 						  *thread)
 {
 	struct acpi_walk_state *walk_state;
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index ef0193d74b5d..36d120574423 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -89,7 +89,8 @@ acpi_ev_update_gpe_enable_mask(struct acpi_gpe_event_info *gpe_event_info)
 	/* Set the mask bit only if there are references to this GPE */
 
 	if (gpe_event_info->runtime_count) {
-		ACPI_SET_BIT(gpe_register_info->enable_for_run, (u8)register_bit);
+		ACPI_SET_BIT(gpe_register_info->enable_for_run,
+			     (u8)register_bit);
 	}
 
 	return_ACPI_STATUS(AE_OK);
@@ -106,8 +107,7 @@ acpi_ev_update_gpe_enable_mask(struct acpi_gpe_event_info *gpe_event_info)
  * DESCRIPTION: Clear a GPE of stale events and enable it.
  *
  ******************************************************************************/
-acpi_status
-acpi_ev_enable_gpe(struct acpi_gpe_event_info *gpe_event_info)
+acpi_status acpi_ev_enable_gpe(struct acpi_gpe_event_info *gpe_event_info)
 {
 	acpi_status status;
 
@@ -131,8 +131,8 @@ acpi_ev_enable_gpe(struct acpi_gpe_event_info *gpe_event_info)
 	}
 
 	/* Enable the requested GPE */
-	status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE);
 
+	status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE);
 	return_ACPI_STATUS(status);
 }
 
@@ -150,7 +150,8 @@ acpi_ev_enable_gpe(struct acpi_gpe_event_info *gpe_event_info)
  *
  ******************************************************************************/
 
-acpi_status acpi_ev_add_gpe_reference(struct acpi_gpe_event_info *gpe_event_info)
+acpi_status
+acpi_ev_add_gpe_reference(struct acpi_gpe_event_info *gpe_event_info)
 {
 	acpi_status status = AE_OK;
 
@@ -191,7 +192,8 @@ acpi_status acpi_ev_add_gpe_reference(struct acpi_gpe_event_info *gpe_event_info
  *
  ******************************************************************************/
 
-acpi_status acpi_ev_remove_gpe_reference(struct acpi_gpe_event_info *gpe_event_info)
+acpi_status
+acpi_ev_remove_gpe_reference(struct acpi_gpe_event_info *gpe_event_info)
 {
 	acpi_status status = AE_OK;
 
@@ -208,7 +210,8 @@ acpi_status acpi_ev_remove_gpe_reference(struct acpi_gpe_event_info *gpe_event_i
 
 		status = acpi_ev_update_gpe_enable_mask(gpe_event_info);
 		if (ACPI_SUCCESS(status)) {
-			status = acpi_hw_low_set_gpe(gpe_event_info,
+			status =
+			    acpi_hw_low_set_gpe(gpe_event_info,
 						     ACPI_GPE_DISABLE);
 		}
 
@@ -306,7 +309,8 @@ struct acpi_gpe_event_info *acpi_ev_get_gpe_event_info(acpi_handle gpe_device,
 
 	/* A Non-NULL gpe_device means this is a GPE Block Device */
 
-	obj_desc = acpi_ns_get_attached_object((struct acpi_namespace_node *)
+	obj_desc =
+	    acpi_ns_get_attached_object((struct acpi_namespace_node *)
 					       gpe_device);
 	if (!obj_desc || !obj_desc->device.gpe_block) {
 		return (NULL);
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index 8cf4c104c7b7..1571a61a7833 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -486,7 +486,8 @@ acpi_ev_initialize_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 			if (ACPI_FAILURE(status)) {
 				ACPI_EXCEPTION((AE_INFO, status,
 					"Could not enable GPE 0x%02X",
-					gpe_index + gpe_block->block_base_number));
+					gpe_index +
+					gpe_block->block_base_number));
 				continue;
 			}
 
diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c
index cb50dd91bc18..228a0c3b1d49 100644
--- a/drivers/acpi/acpica/evgpeutil.c
+++ b/drivers/acpi/acpica/evgpeutil.c
@@ -374,7 +374,8 @@ acpi_ev_delete_gpe_handlers(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 				gpe_event_info->dispatch.handler = NULL;
 				gpe_event_info->flags &=
 				    ~ACPI_GPE_DISPATCH_MASK;
-			} else if ((gpe_event_info->
+			} else
+			    if ((gpe_event_info->
 				 flags & ACPI_GPE_DISPATCH_MASK) ==
 				ACPI_GPE_DISPATCH_NOTIFY) {
 
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index 6786f00042cd..1474241bfc7e 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -227,8 +227,7 @@ acpi_ev_pci_config_region_setup(acpi_handle handle,
 
 				/* Install a handler for this PCI root bridge */
 
-				status =
-				    acpi_install_address_space_handler((acpi_handle) pci_root_node, ACPI_ADR_SPACE_PCI_CONFIG, ACPI_DEFAULT_HANDLER, NULL, NULL);
+				status = acpi_install_address_space_handler((acpi_handle) pci_root_node, ACPI_ADR_SPACE_PCI_CONFIG, ACPI_DEFAULT_HANDLER, NULL, NULL);
 				if (ACPI_FAILURE(status)) {
 					if (status == AE_SAME_HANDLER) {
 						/*
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index 87c5f2332260..d36f99739376 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -221,7 +221,8 @@ acpi_setup_gpe_for_wake(acpi_handle wake_device,
 	if (wake_device == ACPI_ROOT_OBJECT) {
 		device_node = acpi_gbl_root_node;
 	} else {
-		device_node = ACPI_CAST_PTR(struct acpi_namespace_node, wake_device);
+		device_node =
+		    ACPI_CAST_PTR(struct acpi_namespace_node, wake_device);
 	}
 
 	/* Validate WakeDevice is of type Device */
@@ -324,7 +325,8 @@ ACPI_EXPORT_SYMBOL(acpi_setup_gpe_for_wake)
  *
  ******************************************************************************/
 
-acpi_status acpi_set_gpe_wake_mask(acpi_handle gpe_device, u32 gpe_number, u8 action)
+acpi_status
+acpi_set_gpe_wake_mask(acpi_handle gpe_device, u32 gpe_number, u8 action)
 {
 	acpi_status status = AE_OK;
 	struct acpi_gpe_event_info *gpe_event_info;
@@ -694,8 +696,7 @@ ACPI_EXPORT_SYMBOL(acpi_remove_gpe_block)
  *              the FADT-defined gpe blocks. Otherwise, the GPE block device.
  *
  ******************************************************************************/
-acpi_status
-acpi_get_gpe_device(u32 index, acpi_handle *gpe_device)
+acpi_status acpi_get_gpe_device(u32 index, acpi_handle * gpe_device)
 {
 	struct acpi_gpe_device_info info;
 	acpi_status status;
diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c
index bfb062e4c4b4..4492a4e03022 100644
--- a/drivers/acpi/acpica/exconvrt.c
+++ b/drivers/acpi/acpica/exconvrt.c
@@ -516,8 +516,8 @@ acpi_ex_convert_to_string(union acpi_operand_object * obj_desc,
 			string_length--;
 		}
 
-		return_desc = acpi_ut_create_string_object((acpi_size)
-							   string_length);
+		return_desc =
+		    acpi_ut_create_string_object((acpi_size) string_length);
 		if (!return_desc) {
 			return_ACPI_STATUS(AE_NO_MEMORY);
 		}
diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c
index 691d4763102c..9f152701bc0f 100644
--- a/drivers/acpi/acpica/excreate.c
+++ b/drivers/acpi/acpica/excreate.c
@@ -243,8 +243,7 @@ acpi_status acpi_ex_create_mutex(struct acpi_walk_state *walk_state)
 
 	/* Init object and attach to NS node */
 
-	obj_desc->mutex.sync_level =
-	    (u8) walk_state->operands[1]->integer.value;
+	obj_desc->mutex.sync_level = (u8)walk_state->operands[1]->integer.value;
 	obj_desc->mutex.node =
 	    (struct acpi_namespace_node *)walk_state->operands[0];
 
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index 213c081776fc..40608b3e28f7 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -464,7 +464,8 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 
 	ACPI_FUNCTION_NAME(ex_dump_operand)
 
-	    if (!((ACPI_LV_EXEC & acpi_dbg_level)
+	    if (!
+		((ACPI_LV_EXEC & acpi_dbg_level)
 		  && (_COMPONENT & acpi_dbg_layer))) {
 		return;
 	}
@@ -810,7 +811,8 @@ void acpi_ex_dump_namespace_node(struct acpi_namespace_node *node, u32 flags)
 	ACPI_FUNCTION_ENTRY();
 
 	if (!flags) {
-		if (!((ACPI_LV_OBJECTS & acpi_dbg_level)
+		if (!
+		    ((ACPI_LV_OBJECTS & acpi_dbg_level)
 		      && (_COMPONENT & acpi_dbg_layer))) {
 			return;
 		}
@@ -996,7 +998,8 @@ acpi_ex_dump_object_descriptor(union acpi_operand_object *obj_desc, u32 flags)
 	}
 
 	if (!flags) {
-		if (!((ACPI_LV_OBJECTS & acpi_dbg_level)
+		if (!
+		    ((ACPI_LV_OBJECTS & acpi_dbg_level)
 		      && (_COMPONENT & acpi_dbg_layer))) {
 			return_VOID;
 		}
diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c
index a7784152ed30..419148a66e71 100644
--- a/drivers/acpi/acpica/exfldio.c
+++ b/drivers/acpi/acpica/exfldio.c
@@ -54,8 +54,7 @@ ACPI_MODULE_NAME("exfldio")
 /* Local prototypes */
 static acpi_status
 acpi_ex_field_datum_io(union acpi_operand_object *obj_desc,
-		       u32 field_datum_byte_offset,
-		       u64 *value, u32 read_write);
+		       u32 field_datum_byte_offset, u64 *value, u32 read_write);
 
 static u8
 acpi_ex_register_overflow(union acpi_operand_object *obj_desc, u64 value);
diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c
index fcc75fa27d32..6d19bd42d297 100644
--- a/drivers/acpi/acpica/exnames.c
+++ b/drivers/acpi/acpica/exnames.c
@@ -53,8 +53,7 @@ ACPI_MODULE_NAME("exnames")
 /* Local prototypes */
 static char *acpi_ex_allocate_name_string(u32 prefix_count, u32 num_name_segs);
 
-static acpi_status
-acpi_ex_name_segment(u8 ** in_aml_address, char *name_string);
+static acpi_status acpi_ex_name_segment(u8 **in_aml_address, char *name_string);
 
 /*******************************************************************************
  *
@@ -178,7 +177,8 @@ static acpi_status acpi_ex_name_segment(u8 ** in_aml_address, char *name_string)
 
 	ACPI_DEBUG_PRINT((ACPI_DB_LOAD, "Bytes from stream:\n"));
 
-	for (index = 0; (index < ACPI_NAME_SIZE)
+	for (index = 0;
+	     (index < ACPI_NAME_SIZE)
 	     && (acpi_ut_valid_acpi_char(*aml_address, 0)); index++) {
 		char_buf[index] = *aml_address++;
 		ACPI_DEBUG_PRINT((ACPI_DB_LOAD, "%c\n", char_buf[index]));
diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c
index f232fbabdea8..17dc218cd392 100644
--- a/drivers/acpi/acpica/exresop.c
+++ b/drivers/acpi/acpica/exresop.c
@@ -337,7 +337,8 @@ acpi_ex_resolve_operands(u16 opcode,
 			if ((opcode == AML_STORE_OP) &&
 			    ((*stack_ptr)->common.type ==
 			     ACPI_TYPE_LOCAL_REFERENCE)
-			    && ((*stack_ptr)->reference.class == ACPI_REFCLASS_INDEX)) {
+			    && ((*stack_ptr)->reference.class ==
+				ACPI_REFCLASS_INDEX)) {
 				goto next_operand;
 			}
 			break;
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index db4076580e2b..3b3b5e45847c 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -339,7 +339,8 @@ acpi_hw_clear_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 
 acpi_status
 acpi_hw_enable_runtime_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
-				 struct acpi_gpe_block_info *gpe_block, void *context)
+				 struct acpi_gpe_block_info * gpe_block,
+				 void *context)
 {
 	u32 i;
 	acpi_status status;
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index b6411f16832f..438004a1dd85 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -101,8 +101,7 @@ acpi_status acpi_get_timer(u32 * ticks)
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
-	status =
-	    acpi_hw_read(ticks, &acpi_gbl_FADT.xpm_timer_block);
+	status = acpi_hw_read(ticks, &acpi_gbl_FADT.xpm_timer_block);
 
 	return_ACPI_STATUS(status);
 }
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index 0ff1ecea5c3a..ae443fe2ebf6 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -49,8 +49,7 @@
 ACPI_MODULE_NAME("hwxfsleep")
 
 /* Local prototypes */
-static acpi_status
-acpi_hw_sleep_dispatch(u8 sleep_state, u32 function_id);
+static acpi_status acpi_hw_sleep_dispatch(u8 sleep_state, u32 function_id);
 
 /*
  * Dispatch table used to efficiently branch to the various sleep
@@ -234,8 +233,7 @@ ACPI_EXPORT_SYMBOL(acpi_enter_sleep_state_s4bios)
  *              function.
  *
  ******************************************************************************/
-static acpi_status
-acpi_hw_sleep_dispatch(u8 sleep_state, u32 function_id)
+static acpi_status acpi_hw_sleep_dispatch(u8 sleep_state, u32 function_id)
 {
 	acpi_status status;
 	struct acpi_sleep_functions *sleep_functions =
@@ -369,8 +367,7 @@ acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state)
 		return_ACPI_STATUS(AE_AML_OPERAND_VALUE);
 	}
 
-	status =
-	    acpi_hw_sleep_dispatch(sleep_state, ACPI_SLEEP_FUNCTION_ID);
+	status = acpi_hw_sleep_dispatch(sleep_state, ACPI_SLEEP_FUNCTION_ID);
 	return_ACPI_STATUS(status);
 }
 
@@ -396,8 +393,7 @@ acpi_status acpi_leave_sleep_state_prep(u8 sleep_state)
 	ACPI_FUNCTION_TRACE(acpi_leave_sleep_state_prep);
 
 	status =
-	    acpi_hw_sleep_dispatch(sleep_state,
-				   ACPI_WAKE_PREP_FUNCTION_ID);
+	    acpi_hw_sleep_dispatch(sleep_state, ACPI_WAKE_PREP_FUNCTION_ID);
 	return_ACPI_STATUS(status);
 }
 
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index 23db53ce2293..fc168e62c1c9 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -179,8 +179,7 @@ acpi_status acpi_ns_root_initialize(void)
 
 				/* Build an object around the static string */
 
-				obj_desc->string.length =
-				    (u32) ACPI_STRLEN(val);
+				obj_desc->string.length = (u32)ACPI_STRLEN(val);
 				obj_desc->string.pointer = val;
 				obj_desc->common.flags |= AOPOBJ_STATIC_POINTER;
 				break;
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index 95ffe8dfa1f1..4328e2adfeb9 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -96,8 +96,8 @@ acpi_status acpi_ns_initialize_objects(void)
 	/* Walk entire namespace from the supplied root */
 
 	status = acpi_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT,
-				     ACPI_UINT32_MAX, acpi_ns_init_one_object, NULL,
-				     &info, NULL);
+				     ACPI_UINT32_MAX, acpi_ns_init_one_object,
+				     NULL, &info, NULL);
 	if (ACPI_FAILURE(status)) {
 		ACPI_EXCEPTION((AE_INFO, status, "During WalkNamespace"));
 	}
diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c
index ed1d457bd5ca..e5572a78bdb8 100644
--- a/drivers/acpi/acpica/psopcode.c
+++ b/drivers/acpi/acpica/psopcode.c
@@ -392,10 +392,12 @@ const struct acpi_opcode_info acpi_gbl_aml_op_info[AML_NUM_OPCODES] = {
 		 AML_FLAGS_EXEC_1A_0T_1R | AML_NO_OPERAND_RESOLVE),
 /* 38 */ ACPI_OP("LAnd", ARGP_LAND_OP, ARGI_LAND_OP, ACPI_TYPE_ANY,
 		 AML_CLASS_EXECUTE, AML_TYPE_EXEC_2A_0T_1R,
-		 AML_FLAGS_EXEC_2A_0T_1R | AML_LOGICAL_NUMERIC | AML_CONSTANT),
+			 AML_FLAGS_EXEC_2A_0T_1R | AML_LOGICAL_NUMERIC |
+			 AML_CONSTANT),
 /* 39 */ ACPI_OP("LOr", ARGP_LOR_OP, ARGI_LOR_OP, ACPI_TYPE_ANY,
 		 AML_CLASS_EXECUTE, AML_TYPE_EXEC_2A_0T_1R,
-		 AML_FLAGS_EXEC_2A_0T_1R | AML_LOGICAL_NUMERIC | AML_CONSTANT),
+		 	 AML_FLAGS_EXEC_2A_0T_1R | AML_LOGICAL_NUMERIC |
+			 AML_CONSTANT),
 /* 3A */ ACPI_OP("LNot", ARGP_LNOT_OP, ARGI_LNOT_OP, ACPI_TYPE_ANY,
 		 AML_CLASS_EXECUTE, AML_TYPE_EXEC_1A_0T_1R,
 		 AML_FLAGS_EXEC_1A_0T_1R | AML_CONSTANT),
@@ -495,7 +497,8 @@ const struct acpi_opcode_info acpi_gbl_aml_op_info[AML_NUM_OPCODES] = {
 		 AML_NSNODE | AML_NAMED | AML_DEFER),
 /* 59 */ ACPI_OP("Field", ARGP_FIELD_OP, ARGI_FIELD_OP, ACPI_TYPE_ANY,
 		 AML_CLASS_NAMED_OBJECT, AML_TYPE_NAMED_FIELD,
-		 AML_HAS_ARGS | AML_NSOBJECT | AML_NSOPCODE | AML_FIELD),
+			 AML_HAS_ARGS | AML_NSOBJECT | AML_NSOPCODE |
+			 AML_FIELD),
 /* 5A */ ACPI_OP("Device", ARGP_DEVICE_OP, ARGI_DEVICE_OP,
 		 ACPI_TYPE_DEVICE, AML_CLASS_NAMED_OBJECT,
 		 AML_TYPE_NAMED_NO_OBJ,
@@ -519,12 +522,13 @@ const struct acpi_opcode_info acpi_gbl_aml_op_info[AML_NUM_OPCODES] = {
 /* 5E */ ACPI_OP("IndexField", ARGP_INDEX_FIELD_OP, ARGI_INDEX_FIELD_OP,
 		 ACPI_TYPE_ANY, AML_CLASS_NAMED_OBJECT,
 		 AML_TYPE_NAMED_FIELD,
-		 AML_HAS_ARGS | AML_NSOBJECT | AML_NSOPCODE | AML_FIELD),
+		 	 AML_HAS_ARGS | AML_NSOBJECT | AML_NSOPCODE |
+			 AML_FIELD),
 /* 5F */ ACPI_OP("BankField", ARGP_BANK_FIELD_OP, ARGI_BANK_FIELD_OP,
-		 ACPI_TYPE_LOCAL_BANK_FIELD, AML_CLASS_NAMED_OBJECT,
-		 AML_TYPE_NAMED_FIELD,
-		 AML_HAS_ARGS | AML_NSOBJECT | AML_NSOPCODE | AML_FIELD |
-		 AML_DEFER),
+		 	 ACPI_TYPE_LOCAL_BANK_FIELD,
+			 AML_CLASS_NAMED_OBJECT, AML_TYPE_NAMED_FIELD,
+		 	 AML_HAS_ARGS | AML_NSOBJECT | AML_NSOPCODE |
+			 AML_FIELD | AML_DEFER),
 
 /* Internal opcodes that map to invalid AML opcodes */
 
@@ -632,7 +636,8 @@ const struct acpi_opcode_info acpi_gbl_aml_op_info[AML_NUM_OPCODES] = {
 /* 7D */ ACPI_OP("[EvalSubTree]", ARGP_SCOPE_OP, ARGI_SCOPE_OP,
 		 ACPI_TYPE_ANY, AML_CLASS_NAMED_OBJECT,
 		 AML_TYPE_NAMED_NO_OBJ,
-		 AML_HAS_ARGS | AML_NSOBJECT | AML_NSOPCODE | AML_NSNODE),
+		 	 AML_HAS_ARGS | AML_NSOBJECT | AML_NSOPCODE |
+			 AML_NSNODE),
 
 /* ACPI 3.0 opcodes */
 
diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c
index 01985703bb98..dfdda00c6fff 100644
--- a/drivers/acpi/acpica/psparse.c
+++ b/drivers/acpi/acpica/psparse.c
@@ -459,8 +459,9 @@ acpi_status acpi_ps_parse_aml(struct acpi_walk_state *walk_state)
 
 			/* Executing a control method - additional cleanup */
 
-			acpi_ds_terminate_control_method(
-				walk_state->method_desc, walk_state);
+			acpi_ds_terminate_control_method(walk_state->
+							 method_desc,
+							 walk_state);
 		}
 
 		acpi_ds_delete_walk_state(walk_state);
diff --git a/drivers/acpi/acpica/rscalc.c b/drivers/acpi/acpica/rscalc.c
index de12469d1c9c..42745676ecdc 100644
--- a/drivers/acpi/acpica/rscalc.c
+++ b/drivers/acpi/acpica/rscalc.c
@@ -664,8 +664,7 @@ acpi_rs_get_pci_routing_table_length(union acpi_operand_object *package_object,
 						     (*sub_object_list)->string.
 						     length + 1);
 			} else {
-				temp_size_needed +=
-				    acpi_ns_get_pathname_length((*sub_object_list)->reference.node);
+				temp_size_needed += acpi_ns_get_pathname_length((*sub_object_list)->reference.node);
 			}
 		} else {
 			/*
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 352fd1a38321..fe84aee5df47 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -178,8 +178,7 @@ acpi_status acpi_unload_table_id(acpi_owner_id id);
 
 acpi_status
 acpi_get_table_header(acpi_string signature,
-		      u32 instance,
-		      struct acpi_table_header *out_table_header);
+		      u32 instance, struct acpi_table_header *out_table_header);
 
 acpi_status
 acpi_get_table_with_size(acpi_string signature,
@@ -190,8 +189,7 @@ acpi_get_table(acpi_string signature,
 	       u32 instance, struct acpi_table_header **out_table);
 
 acpi_status
-acpi_get_table_by_index(u32 table_index,
-			struct acpi_table_header **out_table);
+acpi_get_table_by_index(u32 table_index, struct acpi_table_header **out_table);
 
 acpi_status
 acpi_install_table_handler(acpi_tbl_handler handler, void *context);
@@ -300,10 +298,9 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 							 u32 gpe_number,
 							 acpi_gpe_handler
 							 address))
-acpi_status
-acpi_install_notify_handler(acpi_handle device,
-			    u32 handler_type,
-			    acpi_notify_handler handler, void *context);
+acpi_status acpi_install_notify_handler(acpi_handle device, u32 handler_type,
+					acpi_notify_handler handler,
+					void *context);
 
 acpi_status
 acpi_remove_notify_handler(acpi_handle device,
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index ea50a314e552..1fa6ba123071 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -922,7 +922,8 @@ struct acpi_system_info {
 /*
  * Types specific to the OS service interfaces
  */
-typedef u32(ACPI_SYSTEM_XFACE * acpi_osd_handler) (void *context);
+typedef u32
+ (ACPI_SYSTEM_XFACE * acpi_osd_handler) (void *context);
 
 typedef void
  (ACPI_SYSTEM_XFACE * acpi_osd_exec_callback) (void *context);
@@ -938,7 +939,8 @@ void (*acpi_gbl_event_handler) (u32 event_type,
 #define ACPI_EVENT_TYPE_GPE         0
 #define ACPI_EVENT_TYPE_FIXED       1
 
-typedef u32(*acpi_event_handler) (void *context);
+typedef
+u32(*acpi_event_handler) (void *context);
 
 typedef
 u32 (*acpi_gpe_handler) (acpi_handle gpe_device, u32 gpe_number, void *context);
-- 
cgit v1.2.3-55-g7522


From 4f3ca640e97ba54df42789a7c3085c75630e863c Mon Sep 17 00:00:00 2001
From: Bob Moore
Date: Wed, 31 Oct 2012 02:26:11 +0000
Subject: ACPICA: ACPICA core: Cleanup empty lines at file start and end

Maintenance for source code consistency.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acobject.h | 1 -
 drivers/acpi/acpica/amlresrc.h | 1 -
 drivers/acpi/acpica/exmisc.c   | 1 -
 drivers/acpi/acpica/exmutex.c  | 1 -
 drivers/acpi/acpica/exnames.c  | 1 -
 drivers/acpi/acpica/exoparg1.c | 1 -
 drivers/acpi/acpica/exoparg3.c | 1 -
 drivers/acpi/acpica/exoparg6.c | 1 -
 drivers/acpi/acpica/exprep.c   | 1 -
 drivers/acpi/acpica/exregion.c | 1 -
 drivers/acpi/acpica/exresnte.c | 1 -
 drivers/acpi/acpica/exresolv.c | 1 -
 drivers/acpi/acpica/exresop.c  | 1 -
 drivers/acpi/acpica/exstoren.c | 1 -
 drivers/acpi/acpica/exstorob.c | 1 -
 drivers/acpi/acpica/exsystem.c | 1 -
 drivers/acpi/acpica/exutils.c  | 1 -
 drivers/acpi/acpica/hwacpi.c   | 1 -
 drivers/acpi/acpica/hwgpe.c    | 1 -
 drivers/acpi/acpica/hwregs.c   | 1 -
 drivers/acpi/acpica/hwtimer.c  | 1 -
 drivers/acpi/acpica/hwvalid.c  | 1 -
 drivers/acpi/acpica/hwxface.c  | 1 -
 include/acpi/acpiosxf.h        | 1 -
 include/acpi/acpixf.h          | 1 -
 25 files changed, 25 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index ac4269fb1a37..b83e46aebb17 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Name: acobject.h - Definition of union acpi_operand_object  (Internal object only)
diff --git a/drivers/acpi/acpica/amlresrc.h b/drivers/acpi/acpica/amlresrc.h
index af4947956ec2..968449685e06 100644
--- a/drivers/acpi/acpica/amlresrc.h
+++ b/drivers/acpi/acpica/amlresrc.h
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: amlresrc.h - AML resource descriptors
diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c
index 271c0c57ea10..15e1abd19136 100644
--- a/drivers/acpi/acpica/exmisc.c
+++ b/drivers/acpi/acpica/exmisc.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exmisc - ACPI AML (p-code) execution - specific opcodes
diff --git a/drivers/acpi/acpica/exmutex.c b/drivers/acpi/acpica/exmutex.c
index 9099783eb857..4723974a4cf5 100644
--- a/drivers/acpi/acpica/exmutex.c
+++ b/drivers/acpi/acpica/exmutex.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exmutex - ASL Mutex Acquire/Release functions
diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c
index 6d19bd42d297..a41c82fe2d3d 100644
--- a/drivers/acpi/acpica/exnames.c
+++ b/drivers/acpi/acpica/exnames.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exnames - interpreter/scanner name load/execute
diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c
index 9ba8c73cea16..c6490d609194 100644
--- a/drivers/acpi/acpica/exoparg1.c
+++ b/drivers/acpi/acpica/exoparg1.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exoparg1 - AML execution - opcodes with 1 argument
diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c
index 71fcc65c9ffa..00b19bfe5b5d 100644
--- a/drivers/acpi/acpica/exoparg3.c
+++ b/drivers/acpi/acpica/exoparg3.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exoparg3 - AML execution - opcodes with 3 arguments
diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c
index ab68dc532c7f..98188555e781 100644
--- a/drivers/acpi/acpica/exoparg6.c
+++ b/drivers/acpi/acpica/exoparg6.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exoparg6 - AML execution - opcodes with 6 arguments
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index 81eca60d2748..958924808766 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exprep - ACPI AML (p-code) execution - field prep utilities
diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c
index 1f1ce0c3d2f8..b41e333eb8f3 100644
--- a/drivers/acpi/acpica/exregion.c
+++ b/drivers/acpi/acpica/exregion.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exregion - ACPI default op_region (address space) handlers
diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c
index fa50e77e64a8..1cb057fe8172 100644
--- a/drivers/acpi/acpica/exresnte.c
+++ b/drivers/acpi/acpica/exresnte.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exresnte - AML Interpreter object resolution
diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c
index bbf40ac27585..ae199e7cdfbb 100644
--- a/drivers/acpi/acpica/exresolv.c
+++ b/drivers/acpi/acpica/exresolv.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exresolv - AML Interpreter object resolution
diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c
index 17dc218cd392..04b70b38ebd5 100644
--- a/drivers/acpi/acpica/exresop.c
+++ b/drivers/acpi/acpica/exresop.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exresop - AML Interpreter operand/object resolution
diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c
index b35bed52e061..6fe6eacb3724 100644
--- a/drivers/acpi/acpica/exstoren.c
+++ b/drivers/acpi/acpica/exstoren.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exstoren - AML Interpreter object store support,
diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c
index 53c248473547..b9ac30c11b5d 100644
--- a/drivers/acpi/acpica/exstorob.c
+++ b/drivers/acpi/acpica/exstorob.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exstorob - AML Interpreter object store support, store to object
diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c
index b760641e2fc6..2d6d8bc12edb 100644
--- a/drivers/acpi/acpica/exsystem.c
+++ b/drivers/acpi/acpica/exsystem.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exsystem - Interface to OS services
diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c
index d1ab7917eed7..ff291e626ec9 100644
--- a/drivers/acpi/acpica/exutils.c
+++ b/drivers/acpi/acpica/exutils.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: exutils - interpreter/scanner utilities
diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c
index a1e71d0ef57b..bcf931ca1927 100644
--- a/drivers/acpi/acpica/hwacpi.c
+++ b/drivers/acpi/acpica/hwacpi.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: hwacpi - ACPI Hardware Initialization/Mode Interface
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index 3b3b5e45847c..64560045052d 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: hwgpe - Low level GPE enable/disable/clear functions
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index 4af6d20ef077..f4e57503576b 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -1,4 +1,3 @@
-
 /*******************************************************************************
  *
  * Module Name: hwregs - Read/write access functions for the various ACPI
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index 438004a1dd85..19f6cce95f16 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Name: hwtimer.c - ACPI Power Management Timer Interface
diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c
index c99d546b217f..b6aae58299dc 100644
--- a/drivers/acpi/acpica/hwvalid.c
+++ b/drivers/acpi/acpica/hwvalid.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: hwvalid - I/O request validation
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index 7bfd649d1996..05a154c3c9ac 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Module Name: hwxface - Public ACPICA hardware interfaces
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 1222ba93d80a..64e2c8b830ab 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Name: acpiosxf.h - All interfaces to the OS Services Layer (OSL).  These
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index fe84aee5df47..2596de109ff7 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -1,4 +1,3 @@
-
 /******************************************************************************
  *
  * Name: acpixf.h - External interfaces to the ACPI subsystem
-- 
cgit v1.2.3-55-g7522


From 73a3090a2160fb01317f5a44af6ee5a064a29625 Mon Sep 17 00:00:00 2001
From: Bob Moore
Date: Wed, 31 Oct 2012 02:26:55 +0000
Subject: ACPICA: Remove extra spaces after periods within comments

This makes all comments consistent.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acglobal.h  |  2 +-
 drivers/acpi/acpica/aclocal.h   |  4 ++--
 drivers/acpi/acpica/acobject.h  |  4 ++--
 drivers/acpi/acpica/acopcode.h  |  6 +++---
 drivers/acpi/acpica/acstruct.h  |  2 +-
 drivers/acpi/acpica/dscontrol.c |  2 +-
 drivers/acpi/acpica/dsfield.c   |  2 +-
 drivers/acpi/acpica/dsmethod.c  |  6 +++---
 drivers/acpi/acpica/dsmthdat.c  | 14 +++++++-------
 drivers/acpi/acpica/dsobject.c  |  6 +++---
 drivers/acpi/acpica/dsutils.c   | 30 +++++++++++++++---------------
 drivers/acpi/acpica/dswexec.c   |  8 ++++----
 drivers/acpi/acpica/dswstate.c  |  8 ++++----
 drivers/acpi/acpica/excreate.c  |  6 +++---
 drivers/acpi/acpica/exdump.c    |  2 +-
 drivers/acpi/acpica/exfield.c   |  4 ++--
 drivers/acpi/acpica/exfldio.c   | 12 ++++++------
 drivers/acpi/acpica/exmisc.c    |  4 ++--
 drivers/acpi/acpica/exnames.c   |  2 +-
 drivers/acpi/acpica/exoparg1.c  | 10 +++++-----
 drivers/acpi/acpica/exoparg2.c  |  2 +-
 drivers/acpi/acpica/exoparg3.c  |  2 +-
 drivers/acpi/acpica/exoparg6.c  |  2 +-
 drivers/acpi/acpica/exprep.c    | 12 ++++++------
 drivers/acpi/acpica/exregion.c  |  2 +-
 drivers/acpi/acpica/exresnte.c  |  8 ++++----
 drivers/acpi/acpica/exresolv.c  |  2 +-
 drivers/acpi/acpica/exresop.c   |  4 ++--
 drivers/acpi/acpica/exstore.c   |  4 ++--
 drivers/acpi/acpica/exstoren.c  | 10 +++++-----
 drivers/acpi/acpica/exstorob.c  |  4 ++--
 drivers/acpi/acpica/exsystem.c  |  8 ++++----
 drivers/acpi/acpica/exutils.c   |  4 ++--
 drivers/acpi/acpica/hwacpi.c    |  2 +-
 drivers/acpi/acpica/hwtimer.c   |  2 +-
 drivers/acpi/acpica/nsalloc.c   |  4 ++--
 drivers/acpi/acpica/nsdump.c    |  2 +-
 drivers/acpi/acpica/nsload.c    | 10 +++++-----
 drivers/acpi/acpica/nsobject.c  |  8 ++++----
 drivers/acpi/acpica/nsparse.c   |  8 ++++----
 drivers/acpi/acpica/nsutils.c   |  6 +++---
 drivers/acpi/acpica/nswalk.c    | 10 +++++-----
 drivers/acpi/acpica/nsxfeval.c  | 14 +++++++-------
 drivers/acpi/acpica/nsxfname.c  |  6 +++---
 drivers/acpi/acpica/nsxfobj.c   |  4 ++--
 drivers/acpi/acpica/psargs.c    |  8 ++++----
 drivers/acpi/acpica/psopcode.c  |  6 +++---
 drivers/acpi/acpica/psparse.c   |  8 ++++----
 drivers/acpi/acpica/psutils.c   |  4 ++--
 drivers/acpi/acpica/rscalc.c    |  2 +-
 drivers/acpi/acpica/tbxfroot.c  |  2 +-
 drivers/acpi/acpica/utcache.c   |  6 +++---
 drivers/acpi/acpica/utdebug.c   | 18 +++++++++---------
 drivers/acpi/acpica/utmath.c    |  2 +-
 drivers/acpi/acpica/utmisc.c    | 14 +++++++-------
 drivers/acpi/acpica/utmutex.c   | 12 ++++++------
 drivers/acpi/acpica/utobject.c  |  8 ++++----
 drivers/acpi/acpica/utstate.c   |  2 +-
 drivers/acpi/acpica/uttrack.c   |  6 +++---
 drivers/acpi/acpica/utxface.c   |  2 +-
 include/acpi/acexcep.h          |  2 +-
 61 files changed, 188 insertions(+), 188 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 35006d193d51..64472e4ec329 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -70,7 +70,7 @@
 
 /*
  * Enable "slack" in the AML interpreter?  Default is FALSE, and the
- * interpreter strictly follows the ACPI specification.  Setting to TRUE
+ * interpreter strictly follows the ACPI specification. Setting to TRUE
  * allows the interpreter to ignore certain errors and/or bad AML constructs.
  *
  * Currently, these features are enabled by this flag:
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 5b5be40a1997..ff8bd0061e8b 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -265,7 +265,7 @@ typedef
 acpi_status(*acpi_internal_method) (struct acpi_walk_state * walk_state);
 
 /*
- * Bitmapped ACPI types.  Used internally only
+ * Bitmapped ACPI types. Used internally only
  */
 #define ACPI_BTYPE_ANY                  0x00000000
 #define ACPI_BTYPE_INTEGER              0x00000001
@@ -584,7 +584,7 @@ struct acpi_pscope_state {
 };
 
 /*
- * Thread state - one per thread across multiple walk states.  Multiple walk
+ * Thread state - one per thread across multiple walk states. Multiple walk
  * states are created when there are nested control methods executing.
  */
 struct acpi_thread_state {
diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index b83e46aebb17..24eb9eac9514 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -197,7 +197,7 @@ struct acpi_object_method {
 
 /******************************************************************************
  *
- * Objects that can be notified.  All share a common notify_info area.
+ * Objects that can be notified. All share a common notify_info area.
  *
  *****************************************************************************/
 
@@ -234,7 +234,7 @@ ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_NOTIFY_INFO};
 
 /******************************************************************************
  *
- * Fields.  All share a common header/info field.
+ * Fields. All share a common header/info field.
  *
  *****************************************************************************/
 
diff --git a/drivers/acpi/acpica/acopcode.h b/drivers/acpi/acpica/acopcode.h
index 9440d053fbb3..d786a5128b78 100644
--- a/drivers/acpi/acpica/acopcode.h
+++ b/drivers/acpi/acpica/acopcode.h
@@ -54,7 +54,7 @@
 #define _UNK                        0x6B
 
 /*
- * Reserved ASCII characters.  Do not use any of these for
+ * Reserved ASCII characters. Do not use any of these for
  * internal opcodes, since they are used to differentiate
  * name strings from AML opcodes
  */
@@ -63,7 +63,7 @@
 #define _PFX                        0x6D
 
 /*
- * All AML opcodes and the parse-time arguments for each.  Used by the AML
+ * All AML opcodes and the parse-time arguments for each. Used by the AML
  * parser  Each list is compressed into a 32-bit number and stored in the
  * master opcode table (in psopcode.c).
  */
@@ -193,7 +193,7 @@
 #define ARGP_ZERO_OP                    ARG_NONE
 
 /*
- * All AML opcodes and the runtime arguments for each.  Used by the AML
+ * All AML opcodes and the runtime arguments for each. Used by the AML
  * interpreter  Each list is compressed into a 32-bit number and stored
  * in the master opcode table (in psopcode.c).
  *
diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h
index f196e2c9a71f..937e66c65d1e 100644
--- a/drivers/acpi/acpica/acstruct.h
+++ b/drivers/acpi/acpica/acstruct.h
@@ -53,7 +53,7 @@
  ****************************************************************************/
 
 /*
- * Walk state - current state of a parse tree walk.  Used for both a leisurely
+ * Walk state - current state of a parse tree walk. Used for both a leisurely
  * stroll through the tree (for whatever reason), and for control method
  * execution.
  */
diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c
index 465f02134b89..57895db3231a 100644
--- a/drivers/acpi/acpica/dscontrol.c
+++ b/drivers/acpi/acpica/dscontrol.c
@@ -280,7 +280,7 @@ acpi_ds_exec_end_control_op(struct acpi_walk_state * walk_state,
 
 			/*
 			 * Get the return value and save as the last result
-			 * value.  This is the only place where walk_state->return_desc
+			 * value. This is the only place where walk_state->return_desc
 			 * is set to anything other than zero!
 			 */
 			walk_state->return_desc = walk_state->operands[0];
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index 3da6fd8530c5..b5b904ee815f 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -277,7 +277,7 @@ acpi_ds_create_buffer_field(union acpi_parse_object *op,
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Process all named fields in a field declaration.  Names are
+ * DESCRIPTION: Process all named fields in a field declaration. Names are
  *              entered into the namespace.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index aa9a5d4e4052..52eb4e01622a 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -170,7 +170,7 @@ acpi_ds_create_method_mutex(union acpi_operand_object *method_desc)
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Prepare a method for execution.  Parses the method if necessary,
+ * DESCRIPTION: Prepare a method for execution. Parses the method if necessary,
  *              increments the thread count, and waits at the method semaphore
  *              for clearance to execute.
  *
@@ -444,7 +444,7 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
  * RETURN:      Status
  *
  * DESCRIPTION: Restart a method that was preempted by another (nested) method
- *              invocation.  Handle the return value (if any) from the callee.
+ *              invocation. Handle the return value (if any) from the callee.
  *
  ******************************************************************************/
 
@@ -530,7 +530,7 @@ acpi_ds_restart_control_method(struct acpi_walk_state *walk_state,
  *
  * RETURN:      None
  *
- * DESCRIPTION: Terminate a control method.  Delete everything that the method
+ * DESCRIPTION: Terminate a control method. Delete everything that the method
  *              created, delete all locals and arguments, and delete the parse
  *              tree if requested.
  *
diff --git a/drivers/acpi/acpica/dsmthdat.c b/drivers/acpi/acpica/dsmthdat.c
index 8d55cebaa656..9a83b7e0f3ba 100644
--- a/drivers/acpi/acpica/dsmthdat.c
+++ b/drivers/acpi/acpica/dsmthdat.c
@@ -76,7 +76,7 @@ acpi_ds_method_data_get_type(u16 opcode,
  * RETURN:      Status
  *
  * DESCRIPTION: Initialize the data structures that hold the method's arguments
- *              and locals.  The data struct is an array of namespace nodes for
+ *              and locals. The data struct is an array of namespace nodes for
  *              each - this allows ref_of and de_ref_of to work properly for these
  *              special data types.
  *
@@ -129,7 +129,7 @@ void acpi_ds_method_data_init(struct acpi_walk_state *walk_state)
  *
  * RETURN:      None
  *
- * DESCRIPTION: Delete method locals and arguments.  Arguments are only
+ * DESCRIPTION: Delete method locals and arguments. Arguments are only
  *              deleted if this method was called from another method.
  *
  ******************************************************************************/
@@ -183,7 +183,7 @@ void acpi_ds_method_data_delete_all(struct acpi_walk_state *walk_state)
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Initialize arguments for a method.  The parameter list is a list
+ * DESCRIPTION: Initialize arguments for a method. The parameter list is a list
  *              of ACPI operand objects, either null terminated or whose length
  *              is defined by max_param_count.
  *
@@ -401,7 +401,7 @@ acpi_ds_method_data_get_value(u8 type,
 		 * This means that either 1) The expected argument was
 		 * not passed to the method, or 2) A local variable
 		 * was referenced by the method (via the ASL)
-		 * before it was initialized.  Either case is an error.
+		 * before it was initialized. Either case is an error.
 		 */
 
 		/* If slack enabled, init the local_x/arg_x to an Integer of value zero */
@@ -465,7 +465,7 @@ acpi_ds_method_data_get_value(u8 type,
  *
  * RETURN:      None
  *
- * DESCRIPTION: Delete the entry at Opcode:Index.  Inserts
+ * DESCRIPTION: Delete the entry at Opcode:Index. Inserts
  *              a null into the stack slot after the object is deleted.
  *
  ******************************************************************************/
@@ -523,7 +523,7 @@ acpi_ds_method_data_delete_value(u8 type,
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Store a value in an Arg or Local.  The obj_desc is installed
+ * DESCRIPTION: Store a value in an Arg or Local. The obj_desc is installed
  *              as the new value for the Arg or Local and the reference count
  *              for obj_desc is incremented.
  *
@@ -566,7 +566,7 @@ acpi_ds_store_object_to_local(u8 type,
 
 	/*
 	 * If the reference count on the object is more than one, we must
-	 * take a copy of the object before we store.  A reference count
+	 * take a copy of the object before we store. A reference count
 	 * of exactly 1 means that the object was just created during the
 	 * evaluation of an expression, and we can safely use it since it
 	 * is not used anywhere else.
diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c
index 68592dd34960..c9f15d3a3686 100644
--- a/drivers/acpi/acpica/dsobject.c
+++ b/drivers/acpi/acpica/dsobject.c
@@ -293,7 +293,7 @@ acpi_ds_build_internal_buffer_obj(struct acpi_walk_state *walk_state,
 
 	/*
 	 * Second arg is the buffer data (optional) byte_list can be either
-	 * individual bytes or a string initializer.  In either case, a
+	 * individual bytes or a string initializer. In either case, a
 	 * byte_list appears in the AML.
 	 */
 	arg = op->common.value.arg;	/* skip first arg */
@@ -568,7 +568,7 @@ acpi_ds_create_node(struct acpi_walk_state *walk_state,
 
 	/*
 	 * Because of the execution pass through the non-control-method
-	 * parts of the table, we can arrive here twice.  Only init
+	 * parts of the table, we can arrive here twice. Only init
 	 * the named object node the first time through
 	 */
 	if (acpi_ns_get_attached_object(node)) {
@@ -618,7 +618,7 @@ acpi_ds_create_node(struct acpi_walk_state *walk_state,
  * RETURN:      Status
  *
  * DESCRIPTION: Initialize a namespace object from a parser Op and its
- *              associated arguments.  The namespace object is a more compact
+ *              associated arguments. The namespace object is a more compact
  *              representation of the Op and its arguments.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c
index 4bbdd6c7a3d0..afeb99f49482 100644
--- a/drivers/acpi/acpica/dsutils.c
+++ b/drivers/acpi/acpica/dsutils.c
@@ -61,7 +61,7 @@ ACPI_MODULE_NAME("dsutils")
  *
  * RETURN:      None.
  *
- * DESCRIPTION: Clear and remove a reference on an implicit return value.  Used
+ * DESCRIPTION: Clear and remove a reference on an implicit return value. Used
  *              to delete "stale" return values (if enabled, the return value
  *              from every operator is saved at least momentarily, in case the
  *              parent method exits.)
@@ -107,7 +107,7 @@ void acpi_ds_clear_implicit_return(struct acpi_walk_state *walk_state)
  *
  * DESCRIPTION: Implements the optional "implicit return".  We save the result
  *              of every ASL operator and control method invocation in case the
- *              parent method exit.  Before storing a new return value, we
+ *              parent method exit. Before storing a new return value, we
  *              delete the previous return value.
  *
  ******************************************************************************/
@@ -198,7 +198,7 @@ acpi_ds_is_result_used(union acpi_parse_object * op,
 	 *
 	 * If there is no parent, or the parent is a scope_op, we are executing
 	 * at the method level. An executing method typically has no parent,
-	 * since each method is parsed separately.  A method invoked externally
+	 * since each method is parsed separately. A method invoked externally
 	 * via execute_control_method has a scope_op as the parent.
 	 */
 	if ((!op->common.parent) ||
@@ -223,7 +223,7 @@ acpi_ds_is_result_used(union acpi_parse_object * op,
 	}
 
 	/*
-	 * Decide what to do with the result based on the parent.  If
+	 * Decide what to do with the result based on the parent. If
 	 * the parent opcode will not use the result, delete the object.
 	 * Otherwise leave it as is, it will be deleted when it is used
 	 * as an operand later.
@@ -266,7 +266,7 @@ acpi_ds_is_result_used(union acpi_parse_object * op,
 
 		/*
 		 * These opcodes allow term_arg(s) as operands and therefore
-		 * the operands can be method calls.  The result is used.
+		 * the operands can be method calls. The result is used.
 		 */
 		goto result_used;
 
@@ -284,7 +284,7 @@ acpi_ds_is_result_used(union acpi_parse_object * op,
 			AML_BANK_FIELD_OP)) {
 			/*
 			 * These opcodes allow term_arg(s) as operands and therefore
-			 * the operands can be method calls.  The result is used.
+			 * the operands can be method calls. The result is used.
 			 */
 			goto result_used;
 		}
@@ -329,9 +329,9 @@ acpi_ds_is_result_used(union acpi_parse_object * op,
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Used after interpretation of an opcode.  If there is an internal
+ * DESCRIPTION: Used after interpretation of an opcode. If there is an internal
  *              result descriptor, check if the parent opcode will actually use
- *              this result.  If not, delete the result now so that it will
+ *              this result. If not, delete the result now so that it will
  *              not become orphaned.
  *
  ******************************************************************************/
@@ -376,7 +376,7 @@ acpi_ds_delete_result_if_not_used(union acpi_parse_object *op,
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Resolve all operands to their values.  Used to prepare
+ * DESCRIPTION: Resolve all operands to their values. Used to prepare
  *              arguments to a control method invocation (a call from one
  *              method to another.)
  *
@@ -391,7 +391,7 @@ acpi_status acpi_ds_resolve_operands(struct acpi_walk_state *walk_state)
 
 	/*
 	 * Attempt to resolve each of the valid operands
-	 * Method arguments are passed by reference, not by value.  This means
+	 * Method arguments are passed by reference, not by value. This means
 	 * that the actual objects are passed, not copies of the objects.
 	 */
 	for (i = 0; i < walk_state->num_operands; i++) {
@@ -451,7 +451,7 @@ void acpi_ds_clear_operands(struct acpi_walk_state *walk_state)
  * RETURN:      Status
  *
  * DESCRIPTION: Translate a parse tree object that is an argument to an AML
- *              opcode to the equivalent interpreter object.  This may include
+ *              opcode to the equivalent interpreter object. This may include
  *              looking up a name or entering a new name into the internal
  *              namespace.
  *
@@ -496,9 +496,9 @@ acpi_ds_create_operand(struct acpi_walk_state *walk_state,
 		/*
 		 * Special handling for buffer_field declarations. This is a deferred
 		 * opcode that unfortunately defines the field name as the last
-		 * parameter instead of the first.  We get here when we are performing
+		 * parameter instead of the first. We get here when we are performing
 		 * the deferred execution, so the actual name of the field is already
-		 * in the namespace.  We don't want to attempt to look it up again
+		 * in the namespace. We don't want to attempt to look it up again
 		 * because we may be executing in a different scope than where the
 		 * actual opcode exists.
 		 */
@@ -605,8 +605,8 @@ acpi_ds_create_operand(struct acpi_walk_state *walk_state,
 			/*
 			 * If the name is null, this means that this is an
 			 * optional result parameter that was not specified
-			 * in the original ASL.  Create a Zero Constant for a
-			 * placeholder.  (Store to a constant is a Noop.)
+			 * in the original ASL. Create a Zero Constant for a
+			 * placeholder. (Store to a constant is a Noop.)
 			 */
 			opcode = AML_ZERO_OP;	/* Has no arguments! */
 
diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c
index fa44609aba33..58593931be96 100644
--- a/drivers/acpi/acpica/dswexec.c
+++ b/drivers/acpi/acpica/dswexec.c
@@ -204,7 +204,7 @@ acpi_ds_get_predicate_value(struct acpi_walk_state *walk_state,
  * RETURN:      Status
  *
  * DESCRIPTION: Descending callback used during the execution of control
- *              methods.  This is where most operators and operands are
+ *              methods. This is where most operators and operands are
  *              dispatched to the interpreter.
  *
  ****************************************************************************/
@@ -297,7 +297,7 @@ acpi_ds_exec_begin_op(struct acpi_walk_state *walk_state,
 		if (walk_state->walk_type & ACPI_WALK_METHOD) {
 			/*
 			 * Found a named object declaration during method execution;
-			 * we must enter this object into the namespace.  The created
+			 * we must enter this object into the namespace. The created
 			 * object is temporary and will be deleted upon completion of
 			 * the execution of this method.
 			 *
@@ -348,7 +348,7 @@ acpi_ds_exec_begin_op(struct acpi_walk_state *walk_state,
  * RETURN:      Status
  *
  * DESCRIPTION: Ascending callback used during the execution of control
- *              methods.  The only thing we really need to do here is to
+ *              methods. The only thing we really need to do here is to
  *              notice the beginning of IF, ELSE, and WHILE blocks.
  *
  ****************************************************************************/
@@ -432,7 +432,7 @@ acpi_status acpi_ds_exec_end_op(struct acpi_walk_state *walk_state)
 		if (ACPI_SUCCESS(status)) {
 			/*
 			 * Dispatch the request to the appropriate interpreter handler
-			 * routine.  There is one routine per opcode "type" based upon the
+			 * routine. There is one routine per opcode "type" based upon the
 			 * number of opcode arguments and return type.
 			 */
 			status =
diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c
index 8e6267980aaf..3e65a15a735f 100644
--- a/drivers/acpi/acpica/dswstate.c
+++ b/drivers/acpi/acpica/dswstate.c
@@ -348,7 +348,7 @@ acpi_ds_obj_stack_push(void *object, struct acpi_walk_state * walk_state)
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Pop this walk's object stack.  Objects on the stack are NOT
+ * DESCRIPTION: Pop this walk's object stack. Objects on the stack are NOT
  *              deleted by this routine.
  *
  ******************************************************************************/
@@ -492,7 +492,7 @@ acpi_ds_push_walk_state(struct acpi_walk_state *walk_state,
  * RETURN:      A walk_state object popped from the thread's stack
  *
  * DESCRIPTION: Remove and return the walkstate object that is at the head of
- *              the walk stack for the given walk list.  NULL indicates that
+ *              the walk stack for the given walk list. NULL indicates that
  *              the list is empty.
  *
  ******************************************************************************/
@@ -532,7 +532,7 @@ struct acpi_walk_state *acpi_ds_pop_walk_state(struct acpi_thread_state *thread)
  *
  * RETURN:      Pointer to the new walk state.
  *
- * DESCRIPTION: Allocate and initialize a new walk state.  The current walk
+ * DESCRIPTION: Allocate and initialize a new walk state. The current walk
  *              state is set to this new state.
  *
  ******************************************************************************/
@@ -657,7 +657,7 @@ acpi_ds_init_aml_walk(struct acpi_walk_state *walk_state,
 		/*
 		 * Setup the current scope.
 		 * Find a Named Op that has a namespace node associated with it.
-		 * search upwards from this Op.  Current scope is the first
+		 * search upwards from this Op. Current scope is the first
 		 * Op with a namespace node.
 		 */
 		extra_op = parser_state->start_op;
diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c
index 9f152701bc0f..66554bc6f9a8 100644
--- a/drivers/acpi/acpica/excreate.c
+++ b/drivers/acpi/acpica/excreate.c
@@ -78,7 +78,7 @@ acpi_status acpi_ex_create_alias(struct acpi_walk_state *walk_state)
 	    (target_node->type == ACPI_TYPE_LOCAL_METHOD_ALIAS)) {
 		/*
 		 * Dereference an existing alias so that we don't create a chain
-		 * of aliases.  With this code, we guarantee that an alias is
+		 * of aliases. With this code, we guarantee that an alias is
 		 * always exactly one level of indirection away from the
 		 * actual aliased name.
 		 */
@@ -90,7 +90,7 @@ acpi_status acpi_ex_create_alias(struct acpi_walk_state *walk_state)
 	/*
 	 * For objects that can never change (i.e., the NS node will
 	 * permanently point to the same object), we can simply attach
-	 * the object to the new NS node.  For other objects (such as
+	 * the object to the new NS node. For other objects (such as
 	 * Integers, buffers, etc.), we have to point the Alias node
 	 * to the original Node.
 	 */
@@ -139,7 +139,7 @@ acpi_status acpi_ex_create_alias(struct acpi_walk_state *walk_state)
 
 		/*
 		 * The new alias assumes the type of the target, and it points
-		 * to the same object.  The reference count of the object has an
+		 * to the same object. The reference count of the object has an
 		 * additional reference to prevent deletion out from under either the
 		 * target node or the alias Node
 		 */
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index 40608b3e28f7..3157f3bb8de7 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -778,7 +778,7 @@ acpi_ex_dump_operands(union acpi_operand_object **operands,
  * PARAMETERS:  title               - Descriptive text
  *              value               - Value to be displayed
  *
- * DESCRIPTION: Object dump output formatting functions.  These functions
+ * DESCRIPTION: Object dump output formatting functions. These functions
  *              reduce the number of format strings required and keeps them
  *              all in one place for easy modification.
  *
diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c
index dc092f5b35d6..ebc55fbf3ff7 100644
--- a/drivers/acpi/acpica/exfield.c
+++ b/drivers/acpi/acpica/exfield.c
@@ -59,7 +59,7 @@ ACPI_MODULE_NAME("exfield")
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Read from a named field.  Returns either an Integer or a
+ * DESCRIPTION: Read from a named field. Returns either an Integer or a
  *              Buffer, depending on the size of the field.
  *
  ******************************************************************************/
@@ -149,7 +149,7 @@ acpi_ex_read_data_from_field(struct acpi_walk_state *walk_state,
 	 * Allocate a buffer for the contents of the field.
 	 *
 	 * If the field is larger than the current integer width, create
-	 * a BUFFER to hold it.  Otherwise, use an INTEGER.  This allows
+	 * a BUFFER to hold it. Otherwise, use an INTEGER. This allows
 	 * the use of arithmetic operators on the returned value if the
 	 * field size is equal or smaller than an Integer.
 	 *
diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c
index 419148a66e71..aa2ccfb7cb61 100644
--- a/drivers/acpi/acpica/exfldio.c
+++ b/drivers/acpi/acpica/exfldio.c
@@ -154,7 +154,7 @@ acpi_ex_setup_region(union acpi_operand_object *obj_desc,
 #endif
 
 	/*
-	 * Validate the request.  The entire request from the byte offset for a
+	 * Validate the request. The entire request from the byte offset for a
 	 * length of one field datum (access width) must fit within the region.
 	 * (Region length is specified in bytes)
 	 */
@@ -182,7 +182,7 @@ acpi_ex_setup_region(union acpi_operand_object *obj_desc,
 		    obj_desc->common_field.access_byte_width) {
 			/*
 			 * This is the case where the access_type (acc_word, etc.) is wider
-			 * than the region itself.  For example, a region of length one
+			 * than the region itself. For example, a region of length one
 			 * byte, and a field with Dword access specified.
 			 */
 			ACPI_ERROR((AE_INFO,
@@ -320,7 +320,7 @@ acpi_ex_access_region(union acpi_operand_object *obj_desc,
  *
  * DESCRIPTION: Check if a value is out of range of the field being written.
  *              Used to check if the values written to Index and Bank registers
- *              are out of range.  Normally, the value is simply truncated
+ *              are out of range. Normally, the value is simply truncated
  *              to fit the field, but this case is most likely a serious
  *              coding error in the ASL.
  *
@@ -369,7 +369,7 @@ acpi_ex_register_overflow(union acpi_operand_object *obj_desc, u64 value)
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Read or Write a single datum of a field.  The field_type is
+ * DESCRIPTION: Read or Write a single datum of a field. The field_type is
  *              demultiplexed here to handle the different types of fields
  *              (buffer_field, region_field, index_field, bank_field)
  *
@@ -859,7 +859,7 @@ acpi_ex_insert_into_field(union acpi_operand_object *obj_desc,
 	    ACPI_ROUND_BITS_UP_TO_BYTES(obj_desc->common_field.bit_length);
 	/*
 	 * We must have a buffer that is at least as long as the field
-	 * we are writing to.  This is because individual fields are
+	 * we are writing to. This is because individual fields are
 	 * indivisible and partial writes are not supported -- as per
 	 * the ACPI specification.
 	 */
@@ -874,7 +874,7 @@ acpi_ex_insert_into_field(union acpi_operand_object *obj_desc,
 
 		/*
 		 * Copy the original data to the new buffer, starting
-		 * at Byte zero.  All unused (upper) bytes of the
+		 * at Byte zero. All unused (upper) bytes of the
 		 * buffer will be 0.
 		 */
 		ACPI_MEMCPY((char *)new_buffer, (char *)buffer, buffer_length);
diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c
index 15e1abd19136..84058705ed12 100644
--- a/drivers/acpi/acpica/exmisc.c
+++ b/drivers/acpi/acpica/exmisc.c
@@ -253,7 +253,7 @@ acpi_ex_do_concatenate(union acpi_operand_object *operand0,
 	ACPI_FUNCTION_TRACE(ex_do_concatenate);
 
 	/*
-	 * Convert the second operand if necessary.  The first operand
+	 * Convert the second operand if necessary. The first operand
 	 * determines the type of the second operand, (See the Data Types
 	 * section of the ACPI specification.)  Both object types are
 	 * guaranteed to be either Integer/String/Buffer by the operand
@@ -572,7 +572,7 @@ acpi_ex_do_logical_op(u16 opcode,
 	ACPI_FUNCTION_TRACE(ex_do_logical_op);
 
 	/*
-	 * Convert the second operand if necessary.  The first operand
+	 * Convert the second operand if necessary. The first operand
 	 * determines the type of the second operand, (See the Data Types
 	 * section of the ACPI 3.0+ specification.)  Both object types are
 	 * guaranteed to be either Integer/String/Buffer by the operand
diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c
index a41c82fe2d3d..2ff578a16adc 100644
--- a/drivers/acpi/acpica/exnames.c
+++ b/drivers/acpi/acpica/exnames.c
@@ -62,7 +62,7 @@ static acpi_status acpi_ex_name_segment(u8 **in_aml_address, char *name_string);
  *                                    (-1)==root,  0==none
  *              num_name_segs       - count of 4-character name segments
  *
- * RETURN:      A pointer to the allocated string segment.  This segment must
+ * RETURN:      A pointer to the allocated string segment. This segment must
  *              be deleted by the caller.
  *
  * DESCRIPTION: Allocate a buffer for a name string. Ensure allocated name
diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c
index c6490d609194..bbf01e9bf057 100644
--- a/drivers/acpi/acpica/exoparg1.c
+++ b/drivers/acpi/acpica/exoparg1.c
@@ -605,7 +605,7 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 		}
 
 		/*
-		 * Set result to ONES (TRUE) if Value == 0.  Note:
+		 * Set result to ONES (TRUE) if Value == 0. Note:
 		 * return_desc->Integer.Value is initially == 0 (FALSE) from above.
 		 */
 		if (!operand[0]->integer.value) {
@@ -617,7 +617,7 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 	case AML_INCREMENT_OP:	/* Increment (Operand)  */
 
 		/*
-		 * Create a new integer.  Can't just get the base integer and
+		 * Create a new integer. Can't just get the base integer and
 		 * increment it because it may be an Arg or Field.
 		 */
 		return_desc = acpi_ut_create_internal_object(ACPI_TYPE_INTEGER);
@@ -685,7 +685,7 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 
 		/*
 		 * Note: The operand is not resolved at this point because we want to
-		 * get the associated object, not its value.  For example, we don't
+		 * get the associated object, not its value. For example, we don't
 		 * want to resolve a field_unit to its value, we want the actual
 		 * field_unit object.
 		 */
@@ -726,7 +726,7 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 
 		/*
 		 * The type of the base object must be integer, buffer, string, or
-		 * package.  All others are not supported.
+		 * package. All others are not supported.
 		 *
 		 * NOTE: Integer is not specifically supported by the ACPI spec,
 		 * but is supported implicitly via implicit operand conversion.
@@ -964,7 +964,7 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 				case ACPI_TYPE_PACKAGE:
 
 					/*
-					 * Return the referenced element of the package.  We must
+					 * Return the referenced element of the package. We must
 					 * add another reference to the referenced object, however.
 					 */
 					return_desc =
diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c
index 879e8a277b94..ee5634a074c4 100644
--- a/drivers/acpi/acpica/exoparg2.c
+++ b/drivers/acpi/acpica/exoparg2.c
@@ -123,7 +123,7 @@ acpi_status acpi_ex_opcode_2A_0T_0R(struct acpi_walk_state *walk_state)
 		/*
 		 * Dispatch the notify to the appropriate handler
 		 * NOTE: the request is queued for execution after this method
-		 * completes.  The notify handlers are NOT invoked synchronously
+		 * completes. The notify handlers are NOT invoked synchronously
 		 * from this thread -- because handlers may in turn run other
 		 * control methods.
 		 */
diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c
index 00b19bfe5b5d..2c89b4651f08 100644
--- a/drivers/acpi/acpica/exoparg3.c
+++ b/drivers/acpi/acpica/exoparg3.c
@@ -157,7 +157,7 @@ acpi_status acpi_ex_opcode_3A_1T_1R(struct acpi_walk_state *walk_state)
 	case AML_MID_OP:	/* Mid (Source[0], Index[1], Length[2], Result[3]) */
 
 		/*
-		 * Create the return object.  The Source operand is guaranteed to be
+		 * Create the return object. The Source operand is guaranteed to be
 		 * either a String or a Buffer, so just use its type.
 		 */
 		return_desc = acpi_ut_create_internal_object((operand[0])->
diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c
index 98188555e781..3e08695c3b30 100644
--- a/drivers/acpi/acpica/exoparg6.c
+++ b/drivers/acpi/acpica/exoparg6.c
@@ -268,7 +268,7 @@ acpi_status acpi_ex_opcode_6A_0T_1R(struct acpi_walk_state * walk_state)
 		 * and the next should be examined.
 		 *
 		 * Upon finding a match, the loop will terminate via "break" at
-		 * the bottom.  If it terminates "normally", match_value will be
+		 * the bottom. If it terminates "normally", match_value will be
 		 * ACPI_UINT64_MAX (Ones) (its initial value) indicating that no
 		 * match was found.
 		 */
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index 958924808766..ba9db4de7c89 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -77,8 +77,8 @@ acpi_ex_generate_access(u32 field_bit_offset,
  *              any_acc keyword.
  *
  * NOTE: Need to have the region_length in order to check for boundary
- *       conditions (end-of-region).  However, the region_length is a deferred
- *       operation.  Therefore, to complete this implementation, the generation
+ *       conditions (end-of-region). However, the region_length is a deferred
+ *       operation. Therefore, to complete this implementation, the generation
  *       of this access width must be deferred until the region length has
  *       been evaluated.
  *
@@ -307,7 +307,7 @@ acpi_ex_decode_field_access(union acpi_operand_object *obj_desc,
  * RETURN:      Status
  *
  * DESCRIPTION: Initialize the areas of the field object that are common
- *              to the various types of fields.  Note: This is very "sensitive"
+ *              to the various types of fields. Note: This is very "sensitive"
  *              code because we are solving the general case for field
  *              alignment.
  *
@@ -335,13 +335,13 @@ acpi_ex_prep_common_field_object(union acpi_operand_object *obj_desc,
 	obj_desc->common_field.bit_length = field_bit_length;
 
 	/*
-	 * Decode the access type so we can compute offsets.  The access type gives
+	 * Decode the access type so we can compute offsets. The access type gives
 	 * two pieces of information - the width of each field access and the
 	 * necessary byte_alignment (address granularity) of the access.
 	 *
 	 * For any_acc, the access_bit_width is the largest width that is both
 	 * necessary and possible in an attempt to access the whole field in one
-	 * I/O operation.  However, for any_acc, the byte_alignment is always one
+	 * I/O operation. However, for any_acc, the byte_alignment is always one
 	 * byte.
 	 *
 	 * For all Buffer Fields, the byte_alignment is always one byte.
@@ -362,7 +362,7 @@ acpi_ex_prep_common_field_object(union acpi_operand_object *obj_desc,
 
 	/*
 	 * base_byte_offset is the address of the start of the field within the
-	 * region.  It is the byte address of the first *datum* (field-width data
+	 * region. It is the byte address of the first *datum* (field-width data
 	 * unit) of the field. (i.e., the first datum that contains at least the
 	 * first *bit* of the field.)
 	 *
diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c
index b41e333eb8f3..1db2c0bfde0b 100644
--- a/drivers/acpi/acpica/exregion.c
+++ b/drivers/acpi/acpica/exregion.c
@@ -201,7 +201,7 @@ acpi_ex_system_memory_space_handler(u32 function,
 	 * Perform the memory read or write
 	 *
 	 * Note: For machines that do not support non-aligned transfers, the target
-	 * address was checked for alignment above.  We do not attempt to break the
+	 * address was checked for alignment above. We do not attempt to break the
 	 * transfer up into smaller (byte-size) chunks because the AML specifically
 	 * asked for a transfer width that the hardware may require.
 	 */
diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c
index 1cb057fe8172..6239956786eb 100644
--- a/drivers/acpi/acpica/exresnte.c
+++ b/drivers/acpi/acpica/exresnte.c
@@ -57,8 +57,8 @@ ACPI_MODULE_NAME("exresnte")
  * PARAMETERS:  object_ptr      - Pointer to a location that contains
  *                                a pointer to a NS node, and will receive a
  *                                pointer to the resolved object.
- *              walk_state      - Current state.  Valid only if executing AML
- *                                code.  NULL if simply resolving an object
+ *              walk_state      - Current state. Valid only if executing AML
+ *                                code. NULL if simply resolving an object
  *
  * RETURN:      Status
  *
@@ -66,7 +66,7 @@ ACPI_MODULE_NAME("exresnte")
  *
  * Note: for some of the data types, the pointer attached to the Node
  * can be either a pointer to an actual internal object or a pointer into the
- * AML stream itself.  These types are currently:
+ * AML stream itself. These types are currently:
  *
  *      ACPI_TYPE_INTEGER
  *      ACPI_TYPE_STRING
@@ -88,7 +88,7 @@ acpi_ex_resolve_node_to_value(struct acpi_namespace_node **object_ptr,
 	ACPI_FUNCTION_TRACE(ex_resolve_node_to_value);
 
 	/*
-	 * The stack pointer points to a struct acpi_namespace_node (Node).  Get the
+	 * The stack pointer points to a struct acpi_namespace_node (Node). Get the
 	 * object that is attached to the Node.
 	 */
 	node = *object_ptr;
diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c
index ae199e7cdfbb..cc176b245e22 100644
--- a/drivers/acpi/acpica/exresolv.c
+++ b/drivers/acpi/acpica/exresolv.c
@@ -326,7 +326,7 @@ acpi_ex_resolve_object_to_value(union acpi_operand_object **stack_ptr,
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Return the base object and type.  Traverse a reference list if
+ * DESCRIPTION: Return the base object and type. Traverse a reference list if
  *              necessary to get to the base object.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c
index 04b70b38ebd5..b9ebff2f6a09 100644
--- a/drivers/acpi/acpica/exresop.c
+++ b/drivers/acpi/acpica/exresop.c
@@ -86,7 +86,7 @@ acpi_ex_check_object_type(acpi_object_type type_needed,
 	if (type_needed == ACPI_TYPE_LOCAL_REFERENCE) {
 		/*
 		 * Allow the AML "Constant" opcodes (Zero, One, etc.) to be reference
-		 * objects and thus allow them to be targets.  (As per the ACPI
+		 * objects and thus allow them to be targets. (As per the ACPI
 		 * specification, a store to a constant is a noop.)
 		 */
 		if ((this_type == ACPI_TYPE_INTEGER) &&
@@ -638,7 +638,7 @@ acpi_ex_resolve_operands(u16 opcode,
 				if (acpi_gbl_enable_interpreter_slack) {
 					/*
 					 * Enable original behavior of Store(), allowing any and all
-					 * objects as the source operand.  The ACPI spec does not
+					 * objects as the source operand. The ACPI spec does not
 					 * allow this, however.
 					 */
 					break;
diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c
index 5fffe7ab5ece..90431f12f831 100644
--- a/drivers/acpi/acpica/exstore.c
+++ b/drivers/acpi/acpica/exstore.c
@@ -374,7 +374,7 @@ acpi_ex_store_object_to_index(union acpi_operand_object *source_desc,
  *              with the input value.
  *
  *              When storing into an object the data is converted to the
- *              target object type then stored in the object.  This means
+ *              target object type then stored in the object. This means
  *              that the target object type (for an initialized target) will
  *              not be changed by a store operation.
  *
@@ -491,7 +491,7 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc,
 				  acpi_ut_get_object_type_name(source_desc),
 				  source_desc, node));
 
-		/* No conversions for all other types.  Just attach the source object */
+		/* No conversions for all other types. Just attach the source object */
 
 		status = acpi_ns_attach_object(node, source_desc,
 					       source_desc->common.type);
diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c
index 6fe6eacb3724..87153bbc4b43 100644
--- a/drivers/acpi/acpica/exstoren.c
+++ b/drivers/acpi/acpica/exstoren.c
@@ -60,7 +60,7 @@ ACPI_MODULE_NAME("exstoren")
  *
  * RETURN:      Status, resolved object in source_desc_ptr.
  *
- * DESCRIPTION: Resolve an object.  If the object is a reference, dereference
+ * DESCRIPTION: Resolve an object. If the object is a reference, dereference
  *              it and return the actual object in the source_desc_ptr.
  *
  ******************************************************************************/
@@ -92,7 +92,7 @@ acpi_ex_resolve_object(union acpi_operand_object **source_desc_ptr,
 
 		/*
 		 * Stores into a Field/Region or into a Integer/Buffer/String
-		 * are all essentially the same.  This case handles the
+		 * are all essentially the same. This case handles the
 		 * "interchangeable" types Integer, String, and Buffer.
 		 */
 		if (source_desc->common.type == ACPI_TYPE_LOCAL_REFERENCE) {
@@ -166,7 +166,7 @@ acpi_ex_resolve_object(union acpi_operand_object **source_desc_ptr,
  *
  * RETURN:      Status
  *
- * DESCRIPTION: "Store" an object to another object.  This may include
+ * DESCRIPTION: "Store" an object to another object. This may include
  *              converting the source type to the target type (implicit
  *              conversion), and a copy of the value of the source to
  *              the target.
@@ -177,14 +177,14 @@ acpi_ex_resolve_object(union acpi_operand_object **source_desc_ptr,
  *              with the input value.
  *
  *              When storing into an object the data is converted to the
- *              target object type then stored in the object.  This means
+ *              target object type then stored in the object. This means
  *              that the target object type (for an initialized target) will
  *              not be changed by a store operation.
  *
  *              This module allows destination types of Number, String,
  *              Buffer, and Package.
  *
- *              Assumes parameters are already validated.  NOTE: source_desc
+ *              Assumes parameters are already validated. NOTE: source_desc
  *              resolution (from a reference object) must be performed by
  *              the caller if necessary.
  *
diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c
index b9ac30c11b5d..b5f339cb1305 100644
--- a/drivers/acpi/acpica/exstorob.c
+++ b/drivers/acpi/acpica/exstorob.c
@@ -107,7 +107,7 @@ acpi_ex_store_buffer_to_buffer(union acpi_operand_object *source_desc,
 #ifdef ACPI_OBSOLETE_BEHAVIOR
 		/*
 		 * NOTE: ACPI versions up to 3.0 specified that the buffer must be
-		 * truncated if the string is smaller than the buffer.  However, "other"
+		 * truncated if the string is smaller than the buffer. However, "other"
 		 * implementations of ACPI never did this and thus became the defacto
 		 * standard. ACPI 3.0A changes this behavior such that the buffer
 		 * is no longer truncated.
@@ -116,7 +116,7 @@ acpi_ex_store_buffer_to_buffer(union acpi_operand_object *source_desc,
 		/*
 		 * OBSOLETE BEHAVIOR:
 		 * If the original source was a string, we must truncate the buffer,
-		 * according to the ACPI spec.  Integer-to-Buffer and Buffer-to-Buffer
+		 * according to the ACPI spec. Integer-to-Buffer and Buffer-to-Buffer
 		 * copy must not truncate the original buffer.
 		 */
 		if (original_src_type == ACPI_TYPE_STRING) {
diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c
index 2d6d8bc12edb..c8a0ad5c1f55 100644
--- a/drivers/acpi/acpica/exsystem.c
+++ b/drivers/acpi/acpica/exsystem.c
@@ -58,7 +58,7 @@ ACPI_MODULE_NAME("exsystem")
  * RETURN:      Status
  *
  * DESCRIPTION: Implements a semaphore wait with a check to see if the
- *              semaphore is available immediately.  If it is not, the
+ *              semaphore is available immediately. If it is not, the
  *              interpreter is released before waiting.
  *
  ******************************************************************************/
@@ -103,7 +103,7 @@ acpi_status acpi_ex_system_wait_semaphore(acpi_semaphore semaphore, u16 timeout)
  * RETURN:      Status
  *
  * DESCRIPTION: Implements a mutex wait with a check to see if the
- *              mutex is available immediately.  If it is not, the
+ *              mutex is available immediately. If it is not, the
  *              interpreter is released before waiting.
  *
  ******************************************************************************/
@@ -151,7 +151,7 @@ acpi_status acpi_ex_system_wait_mutex(acpi_mutex mutex, u16 timeout)
  * DESCRIPTION: Suspend running thread for specified amount of time.
  *              Note: ACPI specification requires that Stall() does not
  *              relinquish the processor, and delays longer than 100 usec
- *              should use Sleep() instead.  We allow stalls up to 255 usec
+ *              should use Sleep() instead. We allow stalls up to 255 usec
  *              for compatibility with other interpreters and existing BIOSs.
  *
  ******************************************************************************/
@@ -253,7 +253,7 @@ acpi_status acpi_ex_system_signal_event(union acpi_operand_object * obj_desc)
  * RETURN:      Status
  *
  * DESCRIPTION: Provides an access point to perform synchronization operations
- *              within the AML.  This operation is a request to wait for an
+ *              within the AML. This operation is a request to wait for an
  *              event.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c
index ff291e626ec9..264d22d8018c 100644
--- a/drivers/acpi/acpica/exutils.c
+++ b/drivers/acpi/acpica/exutils.c
@@ -44,12 +44,12 @@
 /*
  * DEFINE_AML_GLOBALS is tested in amlcode.h
  * to determine whether certain global names should be "defined" or only
- * "declared" in the current compilation.  This enhances maintainability
+ * "declared" in the current compilation. This enhances maintainability
  * by enabling a single header file to embody all knowledge of the names
  * in question.
  *
  * Exactly one module of any executable should #define DEFINE_GLOBALS
- * before #including the header files which use this convention.  The
+ * before #including the header files which use this convention. The
  * names in question will be defined and initialized in that module,
  * and declared as extern in all other modules which #include those
  * header files.
diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c
index bcf931ca1927..90a9aea1cee9 100644
--- a/drivers/acpi/acpica/hwacpi.c
+++ b/drivers/acpi/acpica/hwacpi.c
@@ -135,7 +135,7 @@ acpi_status acpi_hw_set_mode(u32 mode)
  *
  * RETURN:      SYS_MODE_ACPI or SYS_MODE_LEGACY
  *
- * DESCRIPTION: Return current operating state of system.  Determined by
+ * DESCRIPTION: Return current operating state of system. Determined by
  *              querying the SCI_EN bit.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index 19f6cce95f16..bfdce22f3798 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -127,7 +127,7 @@ ACPI_EXPORT_SYMBOL(acpi_get_timer)
  *              a versatile and accurate timer.
  *
  *              Note that this function accommodates only a single timer
- *              rollover.  Thus for 24-bit timers, this function should only
+ *              rollover. Thus for 24-bit timers, this function should only
  *              be used for calculating durations less than ~4.6 seconds
  *              (~20 minutes for 32-bit timers) -- calculations below:
  *
diff --git a/drivers/acpi/acpica/nsalloc.c b/drivers/acpi/acpica/nsalloc.c
index ac389e5bb594..15143c44f5e5 100644
--- a/drivers/acpi/acpica/nsalloc.c
+++ b/drivers/acpi/acpica/nsalloc.c
@@ -332,7 +332,7 @@ void acpi_ns_delete_children(struct acpi_namespace_node *parent_node)
  *
  * RETURN:      None.
  *
- * DESCRIPTION: Delete a subtree of the namespace.  This includes all objects
+ * DESCRIPTION: Delete a subtree of the namespace. This includes all objects
  *              stored within the subtree.
  *
  ******************************************************************************/
@@ -418,7 +418,7 @@ void acpi_ns_delete_namespace_subtree(struct acpi_namespace_node *parent_node)
  * RETURN:      Status
  *
  * DESCRIPTION: Delete entries within the namespace that are owned by a
- *              specific ID.  Used to delete entire ACPI tables.  All
+ *              specific ID. Used to delete entire ACPI tables. All
  *              reference counts are updated.
  *
  * MUTEX:       Locks namespace during deletion walk.
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index 993b12417e7f..924b3c71473a 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -692,7 +692,7 @@ void acpi_ns_dump_entry(acpi_handle handle, u32 debug_level)
  *
  * PARAMETERS:  search_base         - Root of subtree to be dumped, or
  *                                    NS_ALL to dump the entire namespace
- *              max_depth           - Maximum depth of dump.  Use INT_MAX
+ *              max_depth           - Maximum depth of dump. Use INT_MAX
  *                                    for an effectively unlimited depth.
  *
  * RETURN:      None
diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c
index 76935ff29289..911f99127b99 100644
--- a/drivers/acpi/acpica/nsload.c
+++ b/drivers/acpi/acpica/nsload.c
@@ -80,8 +80,8 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
 
 	/*
 	 * Parse the table and load the namespace with all named
-	 * objects found within.  Control methods are NOT parsed
-	 * at this time.  In fact, the control methods cannot be
+	 * objects found within. Control methods are NOT parsed
+	 * at this time. In fact, the control methods cannot be
 	 * parsed until the entire namespace is loaded, because
 	 * if a control method makes a forward reference (call)
 	 * to another control method, we can't continue parsing
@@ -122,7 +122,7 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
 	}
 
 	/*
-	 * Now we can parse the control methods.  We always parse
+	 * Now we can parse the control methods. We always parse
 	 * them here for a sanity check, and if configured for
 	 * just-in-time parsing, we delete the control method
 	 * parse trees.
@@ -166,7 +166,7 @@ acpi_status acpi_ns_load_namespace(void)
 	}
 
 	/*
-	 * Load the namespace.  The DSDT is required,
+	 * Load the namespace. The DSDT is required,
 	 * but the SSDT and PSDT tables are optional.
 	 */
 	status = acpi_ns_load_table_by_type(ACPI_TABLE_ID_DSDT);
@@ -283,7 +283,7 @@ static acpi_status acpi_ns_delete_subtree(acpi_handle start_handle)
  *  RETURN:         Status
  *
  *  DESCRIPTION:    Shrinks the namespace, typically in response to an undocking
- *                  event.  Deletes an entire subtree starting from (and
+ *                  event. Deletes an entire subtree starting from (and
  *                  including) the given handle.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/nsobject.c b/drivers/acpi/acpica/nsobject.c
index d6c9a3cc6716..e69f7fa2579d 100644
--- a/drivers/acpi/acpica/nsobject.c
+++ b/drivers/acpi/acpica/nsobject.c
@@ -61,7 +61,7 @@ ACPI_MODULE_NAME("nsobject")
  * RETURN:      Status
  *
  * DESCRIPTION: Record the given object as the value associated with the
- *              name whose acpi_handle is passed.  If Object is NULL
+ *              name whose acpi_handle is passed. If Object is NULL
  *              and Type is ACPI_TYPE_ANY, set the name as having no value.
  *              Note: Future may require that the Node->Flags field be passed
  *              as a parameter.
@@ -133,7 +133,7 @@ acpi_ns_attach_object(struct acpi_namespace_node *node,
 		 ((struct acpi_namespace_node *)object)->object) {
 		/*
 		 * Value passed is a name handle and that name has a
-		 * non-null value.  Use that name's value and type.
+		 * non-null value. Use that name's value and type.
 		 */
 		obj_desc = ((struct acpi_namespace_node *)object)->object;
 		object_type = ((struct acpi_namespace_node *)object)->type;
@@ -321,7 +321,7 @@ union acpi_operand_object *acpi_ns_get_secondary_object(union
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Low-level attach data.  Create and attach a Data object.
+ * DESCRIPTION: Low-level attach data. Create and attach a Data object.
  *
  ******************************************************************************/
 
@@ -377,7 +377,7 @@ acpi_ns_attach_data(struct acpi_namespace_node *node,
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Low-level detach data.  Delete the data node, but the caller
+ * DESCRIPTION: Low-level detach data. Delete the data node, but the caller
  *              is responsible for the actual data.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index ec7ba2d3463c..233f756d5cfa 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -168,11 +168,11 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
 	/*
 	 * AML Parse, pass 1
 	 *
-	 * In this pass, we load most of the namespace.  Control methods
-	 * are not parsed until later.  A parse tree is not created.  Instead,
-	 * each Parser Op subtree is deleted when it is finished.  This saves
+	 * In this pass, we load most of the namespace. Control methods
+	 * are not parsed until later. A parse tree is not created. Instead,
+	 * each Parser Op subtree is deleted when it is finished. This saves
 	 * a great deal of memory, and allows a small cache of parse objects
-	 * to service the entire parse.  The second pass of the parse then
+	 * to service the entire parse. The second pass of the parse then
 	 * performs another complete parse of the AML.
 	 */
 	ACPI_DEBUG_PRINT((ACPI_DB_PARSE, "**** Start pass 1\n"));
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index ef753a41e087..16b3da80b92d 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -530,7 +530,7 @@ acpi_ns_externalize_name(u32 internal_name_length,
 	    ((num_segments > 0) ? (num_segments - 1) : 0) + 1;
 
 	/*
-	 * Check to see if we're still in bounds.  If not, there's a problem
+	 * Check to see if we're still in bounds. If not, there's a problem
 	 * with internal_name (invalid format).
 	 */
 	if (required_length > internal_name_length) {
@@ -681,7 +681,7 @@ u32 acpi_ns_opens_scope(acpi_object_type type)
  *                            \ (backslash) and ^ (carat) prefixes, and the
  *                            . (period) to separate segments are supported.
  *              prefix_node  - Root of subtree to be searched, or NS_ALL for the
- *                            root of the name space.  If Name is fully
+ *                            root of the name space. If Name is fully
  *                            qualified (first s8 is '\'), the passed value
  *                            of Scope will not be accessed.
  *              flags       - Used to indicate whether to perform upsearch or
@@ -689,7 +689,7 @@ u32 acpi_ns_opens_scope(acpi_object_type type)
  *              return_node - Where the Node is returned
  *
  * DESCRIPTION: Look up a name relative to a given scope and return the
- *              corresponding Node.  NOTE: Scope can be null.
+ *              corresponding Node. NOTE: Scope can be null.
  *
  * MUTEX:       Locks namespace
  *
diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c
index 730bccc5e7f7..0483877f26b8 100644
--- a/drivers/acpi/acpica/nswalk.c
+++ b/drivers/acpi/acpica/nswalk.c
@@ -60,8 +60,8 @@ ACPI_MODULE_NAME("nswalk")
  * RETURN:      struct acpi_namespace_node - Pointer to the NEXT child or NULL if
  *                                    none is found.
  *
- * DESCRIPTION: Return the next peer node within the namespace.  If Handle
- *              is valid, Scope is ignored.  Otherwise, the first node
+ * DESCRIPTION: Return the next peer node within the namespace. If Handle
+ *              is valid, Scope is ignored. Otherwise, the first node
  *              within Scope is returned.
  *
  ******************************************************************************/
@@ -97,8 +97,8 @@ struct acpi_namespace_node *acpi_ns_get_next_node(struct acpi_namespace_node
  * RETURN:      struct acpi_namespace_node - Pointer to the NEXT child or NULL if
  *                                    none is found.
  *
- * DESCRIPTION: Return the next peer node within the namespace.  If Handle
- *              is valid, Scope is ignored.  Otherwise, the first node
+ * DESCRIPTION: Return the next peer node within the namespace. If Handle
+ *              is valid, Scope is ignored. Otherwise, the first node
  *              within Scope is returned.
  *
  ******************************************************************************/
@@ -305,7 +305,7 @@ acpi_ns_walk_namespace(acpi_object_type type,
 
 		/*
 		 * Depth first search: Attempt to go down another level in the
-		 * namespace if we are allowed to.  Don't go any further if we have
+		 * namespace if we are allowed to. Don't go any further if we have
 		 * reached the caller specified maximum depth or if the user
 		 * function has specified that the maximum depth has been reached.
 		 */
diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c
index ee4d873f9f0a..d6a9f77972b6 100644
--- a/drivers/acpi/acpica/nsxfeval.c
+++ b/drivers/acpi/acpica/nsxfeval.c
@@ -61,16 +61,16 @@ static void acpi_ns_resolve_references(struct acpi_evaluate_info *info);
  * PARAMETERS:  handle              - Object handle (optional)
  *              pathname            - Object pathname (optional)
  *              external_params     - List of parameters to pass to method,
- *                                    terminated by NULL.  May be NULL
+ *                                    terminated by NULL. May be NULL
  *                                    if no parameters are being passed.
  *              return_buffer       - Where to put method's return value (if
- *                                    any).  If NULL, no value is returned.
+ *                                    any). If NULL, no value is returned.
  *              return_type         - Expected type of return object
  *
  * RETURN:      Status
  *
  * DESCRIPTION: Find and evaluate the given object, passing the given
- *              parameters if necessary.  One of "Handle" or "Pathname" must
+ *              parameters if necessary. One of "Handle" or "Pathname" must
  *              be valid (non-null)
  *
  ******************************************************************************/
@@ -155,15 +155,15 @@ ACPI_EXPORT_SYMBOL(acpi_evaluate_object_typed)
  * PARAMETERS:  handle              - Object handle (optional)
  *              pathname            - Object pathname (optional)
  *              external_params     - List of parameters to pass to method,
- *                                    terminated by NULL.  May be NULL
+ *                                    terminated by NULL. May be NULL
  *                                    if no parameters are being passed.
  *              return_buffer       - Where to put method's return value (if
- *                                    any).  If NULL, no value is returned.
+ *                                    any). If NULL, no value is returned.
  *
  * RETURN:      Status
  *
  * DESCRIPTION: Find and evaluate the given object, passing the given
- *              parameters if necessary.  One of "Handle" or "Pathname" must
+ *              parameters if necessary. One of "Handle" or "Pathname" must
  *              be valid (non-null)
  *
  ******************************************************************************/
@@ -656,7 +656,7 @@ acpi_ns_get_device_callback(acpi_handle obj_handle,
  * DESCRIPTION: Performs a modified depth-first walk of the namespace tree,
  *              starting (and ending) at the object specified by start_handle.
  *              The user_function is called whenever an object of type
- *              Device is found.  If the user function returns
+ *              Device is found. If the user function returns
  *              a non-zero value, the search is terminated immediately and this
  *              value is returned to the caller.
  *
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index 7bc4985146f8..ce8789771176 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -69,8 +69,8 @@ static char *acpi_ns_copy_device_id(struct acpi_pnp_device_id *dest,
  * RETURN:      Status
  *
  * DESCRIPTION: This routine will search for a caller specified name in the
- *              name space.  The caller can restrict the search region by
- *              specifying a non NULL parent.  The parent value is itself a
+ *              name space. The caller can restrict the search region by
+ *              specifying a non NULL parent. The parent value is itself a
  *              namespace handle.
  *
  ******************************************************************************/
@@ -149,7 +149,7 @@ ACPI_EXPORT_SYMBOL(acpi_get_handle)
  * RETURN:      Pointer to a string containing the fully qualified Name.
  *
  * DESCRIPTION: This routine returns the fully qualified name associated with
- *              the Handle parameter.  This and the acpi_pathname_to_handle are
+ *              the Handle parameter. This and the acpi_pathname_to_handle are
  *              complementary functions.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/nsxfobj.c b/drivers/acpi/acpica/nsxfobj.c
index 6766fc4f088f..9d029dac6b64 100644
--- a/drivers/acpi/acpica/nsxfobj.c
+++ b/drivers/acpi/acpica/nsxfobj.c
@@ -220,8 +220,8 @@ ACPI_EXPORT_SYMBOL(acpi_get_parent)
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Return the next peer object within the namespace.  If Handle is
- *              valid, Scope is ignored.  Otherwise, the first object within
+ * DESCRIPTION: Return the next peer object within the namespace. If Handle is
+ *              valid, Scope is ignored. Otherwise, the first object within
  *              Scope is returned.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c
index 844464c4f901..cb79e2d4d743 100644
--- a/drivers/acpi/acpica/psargs.c
+++ b/drivers/acpi/acpica/psargs.c
@@ -120,7 +120,7 @@ acpi_ps_get_next_package_length(struct acpi_parse_state *parser_state)
  * RETURN:      Pointer to end-of-package +1
  *
  * DESCRIPTION: Get next package length and return a pointer past the end of
- *              the package.  Consumes the package length field
+ *              the package. Consumes the package length field
  *
  ******************************************************************************/
 
@@ -147,8 +147,8 @@ u8 *acpi_ps_get_next_package_end(struct acpi_parse_state *parser_state)
  * RETURN:      Pointer to the start of the name string (pointer points into
  *              the AML.
  *
- * DESCRIPTION: Get next raw namestring within the AML stream.  Handles all name
- *              prefix characters.  Set parser state to point past the string.
+ * DESCRIPTION: Get next raw namestring within the AML stream. Handles all name
+ *              prefix characters. Set parser state to point past the string.
  *              (Name is consumed from the AML.)
  *
  ******************************************************************************/
@@ -220,7 +220,7 @@ char *acpi_ps_get_next_namestring(struct acpi_parse_state *parser_state)
  *
  * DESCRIPTION: Get next name (if method call, return # of required args).
  *              Names are looked up in the internal namespace to determine
- *              if the name represents a control method.  If a method
+ *              if the name represents a control method. If a method
  *              is found, the number of arguments to the method is returned.
  *              This information is critical for parsing to continue correctly.
  *
diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c
index e5572a78bdb8..1793d934aa30 100644
--- a/drivers/acpi/acpica/psopcode.c
+++ b/drivers/acpi/acpica/psopcode.c
@@ -59,7 +59,7 @@ static const u8 acpi_gbl_argument_count[] =
  *
  * DESCRIPTION: Opcode table. Each entry contains <opcode, type, name, operands>
  *              The name is a simple ascii string, the operand specifier is an
- *              ascii string with one letter per operand.  The letter specifies
+ *              ascii string with one letter per operand. The letter specifies
  *              the operand type.
  *
  ******************************************************************************/
@@ -183,7 +183,7 @@ static const u8 acpi_gbl_argument_count[] =
  ******************************************************************************/
 
 /*
- * Master Opcode information table.  A summary of everything we know about each
+ * Master Opcode information table. A summary of everything we know about each
  * opcode, all in one place.
  */
 const struct acpi_opcode_info acpi_gbl_aml_op_info[AML_NUM_OPCODES] = {
@@ -700,7 +700,7 @@ static const u8 acpi_gbl_short_op_index[256] = {
 
 /*
  * This table is indexed by the second opcode of the extended opcode
- * pair.  It returns an index into the opcode table (acpi_gbl_aml_op_info)
+ * pair. It returns an index into the opcode table (acpi_gbl_aml_op_info)
  */
 static const u8 acpi_gbl_long_op_index[NUM_EXTENDED_OPCODE] = {
 /*              0     1     2     3     4     5     6     7  */
diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c
index dfdda00c6fff..2494caf47755 100644
--- a/drivers/acpi/acpica/psparse.c
+++ b/drivers/acpi/acpica/psparse.c
@@ -43,9 +43,9 @@
 
 /*
  * Parse the AML and build an operation tree as most interpreters,
- * like Perl, do.  Parsing is done by hand rather than with a YACC
+ * like Perl, do. Parsing is done by hand rather than with a YACC
  * generated parser to tightly constrain stack and dynamic memory
- * usage.  At the same time, parsing is kept flexible and the code
+ * usage. At the same time, parsing is kept flexible and the code
  * fairly compact by parsing based on a list of AML opcode
  * templates in aml_op_info[]
  */
@@ -379,7 +379,7 @@ acpi_ps_next_parse_state(struct acpi_walk_state *walk_state,
 	case AE_CTRL_FALSE:
 		/*
 		 * Either an IF/WHILE Predicate was false or we encountered a BREAK
-		 * opcode.  In both cases, we do not execute the rest of the
+		 * opcode. In both cases, we do not execute the rest of the
 		 * package;  We simply close out the parent (finishing the walk of
 		 * this branch of the tree) and continue execution at the parent
 		 * level.
@@ -488,7 +488,7 @@ acpi_status acpi_ps_parse_aml(struct acpi_walk_state *walk_state)
 	acpi_gbl_current_walk_list = thread;
 
 	/*
-	 * Execute the walk loop as long as there is a valid Walk State.  This
+	 * Execute the walk loop as long as there is a valid Walk State. This
 	 * handles nested control method invocations without recursion.
 	 */
 	ACPI_DEBUG_PRINT((ACPI_DB_PARSE, "State=%p\n", walk_state));
diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c
index 8736ad5f04d3..4137dcb352d1 100644
--- a/drivers/acpi/acpica/psutils.c
+++ b/drivers/acpi/acpica/psutils.c
@@ -108,7 +108,7 @@ void acpi_ps_init_op(union acpi_parse_object *op, u16 opcode)
  * RETURN:      Pointer to the new Op, null on failure
  *
  * DESCRIPTION: Allocate an acpi_op, choose op type (and thus size) based on
- *              opcode.  A cache of opcodes is available for the pure
+ *              opcode. A cache of opcodes is available for the pure
  *              GENERIC_OP, since this is by far the most commonly used.
  *
  ******************************************************************************/
@@ -164,7 +164,7 @@ union acpi_parse_object *acpi_ps_alloc_op(u16 opcode)
  *
  * RETURN:      None.
  *
- * DESCRIPTION: Free an Op object.  Either put it on the GENERIC_OP cache list
+ * DESCRIPTION: Free an Op object. Either put it on the GENERIC_OP cache list
  *              or actually free it.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/rscalc.c b/drivers/acpi/acpica/rscalc.c
index 42745676ecdc..685177985509 100644
--- a/drivers/acpi/acpica/rscalc.c
+++ b/drivers/acpi/acpica/rscalc.c
@@ -601,7 +601,7 @@ acpi_rs_get_pci_routing_table_length(union acpi_operand_object *package_object,
 	/*
 	 * Calculate the size of the return buffer.
 	 * The base size is the number of elements * the sizes of the
-	 * structures.  Additional space for the strings is added below.
+	 * structures. Additional space for the strings is added below.
 	 * The minus one is to subtract the size of the u8 Source[1]
 	 * member because it is added below.
 	 *
diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c
index f8ee9b35b999..28f330230f99 100644
--- a/drivers/acpi/acpica/tbxfroot.c
+++ b/drivers/acpi/acpica/tbxfroot.c
@@ -107,7 +107,7 @@ static acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp *rsdp)
  * RETURN:      Status, RSDP physical address
  *
  * DESCRIPTION: Search lower 1Mbyte of memory for the root system descriptor
- *              pointer structure.  If it is found, set *RSDP to point to it.
+ *              pointer structure. If it is found, set *RSDP to point to it.
  *
  * NOTE1:       The RSDP must be either in the first 1K of the Extended
  *              BIOS Data Area or between E0000 and FFFFF (From ACPI Spec.)
diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c
index eacb9ba2b9e0..e1d40ed26390 100644
--- a/drivers/acpi/acpica/utcache.c
+++ b/drivers/acpi/acpica/utcache.c
@@ -183,7 +183,7 @@ acpi_status acpi_os_delete_cache(struct acpi_memory_list * cache)
  *
  * RETURN:      None
  *
- * DESCRIPTION: Release an object to the specified cache.  If cache is full,
+ * DESCRIPTION: Release an object to the specified cache. If cache is full,
  *              the object is deleted.
  *
  ******************************************************************************/
@@ -240,9 +240,9 @@ acpi_os_release_object(struct acpi_memory_list * cache, void *object)
  *
  * PARAMETERS:  cache           - Handle to cache object
  *
- * RETURN:      the acquired object.  NULL on error
+ * RETURN:      the acquired object. NULL on error
  *
- * DESCRIPTION: Get an object from the specified cache.  If cache is empty,
+ * DESCRIPTION: Get an object from the specified cache. If cache is empty,
  *              the object is allocated.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c
index 2c2179917649..7a3327067f20 100644
--- a/drivers/acpi/acpica/utdebug.c
+++ b/drivers/acpi/acpica/utdebug.c
@@ -223,7 +223,7 @@ ACPI_EXPORT_SYMBOL(acpi_debug_print)
  *
  * RETURN:      None
  *
- * DESCRIPTION: Print message with no headers.  Has same interface as
+ * DESCRIPTION: Print message with no headers. Has same interface as
  *              debug_print so that the same macros can be used.
  *
  ******************************************************************************/
@@ -259,7 +259,7 @@ ACPI_EXPORT_SYMBOL(acpi_debug_print_raw)
  *
  * RETURN:      None
  *
- * DESCRIPTION: Function entry trace.  Prints only if TRACE_FUNCTIONS bit is
+ * DESCRIPTION: Function entry trace. Prints only if TRACE_FUNCTIONS bit is
  *              set in debug_level
  *
  ******************************************************************************/
@@ -291,7 +291,7 @@ ACPI_EXPORT_SYMBOL(acpi_ut_trace)
  *
  * RETURN:      None
  *
- * DESCRIPTION: Function entry trace.  Prints only if TRACE_FUNCTIONS bit is
+ * DESCRIPTION: Function entry trace. Prints only if TRACE_FUNCTIONS bit is
  *              set in debug_level
  *
  ******************************************************************************/
@@ -321,7 +321,7 @@ acpi_ut_trace_ptr(u32 line_number,
  *
  * RETURN:      None
  *
- * DESCRIPTION: Function entry trace.  Prints only if TRACE_FUNCTIONS bit is
+ * DESCRIPTION: Function entry trace. Prints only if TRACE_FUNCTIONS bit is
  *              set in debug_level
  *
  ******************************************************************************/
@@ -352,7 +352,7 @@ acpi_ut_trace_str(u32 line_number,
  *
  * RETURN:      None
  *
- * DESCRIPTION: Function entry trace.  Prints only if TRACE_FUNCTIONS bit is
+ * DESCRIPTION: Function entry trace. Prints only if TRACE_FUNCTIONS bit is
  *              set in debug_level
  *
  ******************************************************************************/
@@ -382,7 +382,7 @@ acpi_ut_trace_u32(u32 line_number,
  *
  * RETURN:      None
  *
- * DESCRIPTION: Function exit trace.  Prints only if TRACE_FUNCTIONS bit is
+ * DESCRIPTION: Function exit trace. Prints only if TRACE_FUNCTIONS bit is
  *              set in debug_level
  *
  ******************************************************************************/
@@ -414,7 +414,7 @@ ACPI_EXPORT_SYMBOL(acpi_ut_exit)
  *
  * RETURN:      None
  *
- * DESCRIPTION: Function exit trace.  Prints only if TRACE_FUNCTIONS bit is
+ * DESCRIPTION: Function exit trace. Prints only if TRACE_FUNCTIONS bit is
  *              set in debug_level. Prints exit status also.
  *
  ******************************************************************************/
@@ -455,7 +455,7 @@ ACPI_EXPORT_SYMBOL(acpi_ut_status_exit)
  *
  * RETURN:      None
  *
- * DESCRIPTION: Function exit trace.  Prints only if TRACE_FUNCTIONS bit is
+ * DESCRIPTION: Function exit trace. Prints only if TRACE_FUNCTIONS bit is
  *              set in debug_level. Prints exit value also.
  *
  ******************************************************************************/
@@ -487,7 +487,7 @@ ACPI_EXPORT_SYMBOL(acpi_ut_value_exit)
  *
  * RETURN:      None
  *
- * DESCRIPTION: Function exit trace.  Prints only if TRACE_FUNCTIONS bit is
+ * DESCRIPTION: Function exit trace. Prints only if TRACE_FUNCTIONS bit is
  *              set in debug_level. Prints exit value also.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/utmath.c b/drivers/acpi/acpica/utmath.c
index d88a8aaab2a6..49563674833a 100644
--- a/drivers/acpi/acpica/utmath.c
+++ b/drivers/acpi/acpica/utmath.c
@@ -81,7 +81,7 @@ typedef union uint64_overlay {
  * RETURN:      Status (Checks for divide-by-zero)
  *
  * DESCRIPTION: Perform a short (maximum 64 bits divided by 32 bits)
- *              divide and modulo.  The result is a 64-bit quotient and a
+ *              divide and modulo. The result is a 64-bit quotient and a
  *              32-bit remainder.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/utmisc.c b/drivers/acpi/acpica/utmisc.c
index 0fed4bcc84b6..7ba197298ef8 100644
--- a/drivers/acpi/acpica/utmisc.c
+++ b/drivers/acpi/acpica/utmisc.c
@@ -250,7 +250,7 @@ acpi_status acpi_ut_allocate_owner_id(acpi_owner_id * owner_id)
  *              control method or unloading a table. Either way, we would
  *              ignore any error anyway.
  *
- * DESCRIPTION: Release a table or method owner ID.  Valid IDs are 1 - 255
+ * DESCRIPTION: Release a table or method owner ID. Valid IDs are 1 - 255
  *
  ******************************************************************************/
 
@@ -534,8 +534,8 @@ u32 acpi_ut_dword_byte_swap(u32 value)
  * RETURN:      None
  *
  * DESCRIPTION: Set the global integer bit width based upon the revision
- *              of the DSDT.  For Revision 1 and 0, Integers are 32 bits.
- *              For Revision 2 and above, Integers are 64 bits.  Yes, this
+ *              of the DSDT. For Revision 1 and 0, Integers are 32 bits.
+ *              For Revision 2 and above, Integers are 64 bits. Yes, this
  *              makes a difference.
  *
  ******************************************************************************/
@@ -671,7 +671,7 @@ u8 acpi_ut_valid_acpi_char(char character, u32 position)
  *
  * RETURN:      TRUE if the name is valid, FALSE otherwise
  *
- * DESCRIPTION: Check for a valid ACPI name.  Each character must be one of:
+ * DESCRIPTION: Check for a valid ACPI name. Each character must be one of:
  *              1) Upper case alpha
  *              2) numeric
  *              3) underscore
@@ -1010,10 +1010,10 @@ acpi_ut_walk_package_tree(union acpi_operand_object *source_object,
 
 		/*
 		 * Check for:
-		 * 1) An uninitialized package element.  It is completely
+		 * 1) An uninitialized package element. It is completely
 		 *    legal to declare a package and leave it uninitialized
 		 * 2) Not an internal object - can be a namespace node instead
-		 * 3) Any type other than a package.  Packages are handled in else
+		 * 3) Any type other than a package. Packages are handled in else
 		 *    case below.
 		 */
 		if ((!this_source_obj) ||
@@ -1032,7 +1032,7 @@ acpi_ut_walk_package_tree(union acpi_operand_object *source_object,
 			       state->pkg.source_object->package.count) {
 				/*
 				 * We've handled all of the objects at this level,  This means
-				 * that we have just completed a package.  That package may
+				 * that we have just completed a package. That package may
 				 * have contained one or more packages itself.
 				 *
 				 * Delete this state and pop the previous state (package).
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index 93a119199335..5ccf57c0d87e 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -228,9 +228,9 @@ acpi_status acpi_ut_acquire_mutex(acpi_mutex_handle mutex_id)
 		/*
 		 * Mutex debug code, for internal debugging only.
 		 *
-		 * Deadlock prevention.  Check if this thread owns any mutexes of value
-		 * greater than or equal to this one.  If so, the thread has violated
-		 * the mutex ordering rule.  This indicates a coding error somewhere in
+		 * Deadlock prevention. Check if this thread owns any mutexes of value
+		 * greater than or equal to this one. If so, the thread has violated
+		 * the mutex ordering rule. This indicates a coding error somewhere in
 		 * the ACPI subsystem code.
 		 */
 		for (i = mutex_id; i < ACPI_NUM_MUTEX; i++) {
@@ -321,9 +321,9 @@ acpi_status acpi_ut_release_mutex(acpi_mutex_handle mutex_id)
 		/*
 		 * Mutex debug code, for internal debugging only.
 		 *
-		 * Deadlock prevention.  Check if this thread owns any mutexes of value
-		 * greater than this one.  If so, the thread has violated the mutex
-		 * ordering rule.  This indicates a coding error somewhere in
+		 * Deadlock prevention. Check if this thread owns any mutexes of value
+		 * greater than this one. If so, the thread has violated the mutex
+		 * ordering rule. This indicates a coding error somewhere in
 		 * the ACPI subsystem code.
 		 */
 		for (i = mutex_id; i < ACPI_NUM_MUTEX; i++) {
diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c
index 655f0799a391..5c52ca78f6fa 100644
--- a/drivers/acpi/acpica/utobject.c
+++ b/drivers/acpi/acpica/utobject.c
@@ -77,7 +77,7 @@ acpi_ut_get_element_length(u8 object_type,
  *
  * NOTE:        We always allocate the worst-case object descriptor because
  *              these objects are cached, and we want them to be
- *              one-size-satisifies-any-request.  This in itself may not be
+ *              one-size-satisifies-any-request. This in itself may not be
  *              the most memory efficient, but the efficiency of the object
  *              cache should more than make up for this!
  *
@@ -370,9 +370,9 @@ u8 acpi_ut_valid_internal_object(void *object)
  *              line_number         - Caller's line number (for error output)
  *              component_id        - Caller's component ID (for error output)
  *
- * RETURN:      Pointer to newly allocated object descriptor.  Null on error
+ * RETURN:      Pointer to newly allocated object descriptor. Null on error
  *
- * DESCRIPTION: Allocate a new object descriptor.  Gracefully handle
+ * DESCRIPTION: Allocate a new object descriptor. Gracefully handle
  *              error conditions.
  *
  ******************************************************************************/
@@ -554,7 +554,7 @@ acpi_ut_get_simple_object_size(union acpi_operand_object *internal_object,
 
 	/*
 	 * Account for the space required by the object rounded up to the next
-	 * multiple of the machine word size.  This keeps each object aligned
+	 * multiple of the machine word size. This keeps each object aligned
 	 * on a machine word boundary. (preventing alignment faults on some
 	 * machines.)
 	 */
diff --git a/drivers/acpi/acpica/utstate.c b/drivers/acpi/acpica/utstate.c
index a1c988260073..cee0473ba813 100644
--- a/drivers/acpi/acpica/utstate.c
+++ b/drivers/acpi/acpica/utstate.c
@@ -147,7 +147,7 @@ union acpi_generic_state *acpi_ut_pop_generic_state(union acpi_generic_state
  *
  * RETURN:      The new state object. NULL on failure.
  *
- * DESCRIPTION: Create a generic state object.  Attempt to obtain one from
+ * DESCRIPTION: Create a generic state object. Attempt to obtain one from
  *              the global state cache;  If none available, create a new one.
  *
  ******************************************************************************/
diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c
index e79c49d44d08..79f311c3d1c4 100644
--- a/drivers/acpi/acpica/uttrack.c
+++ b/drivers/acpi/acpica/uttrack.c
@@ -45,9 +45,9 @@
  * These procedures are used for tracking memory leaks in the subsystem, and
  * they get compiled out when the ACPI_DBG_TRACK_ALLOCATIONS is not set.
  *
- * Each memory allocation is tracked via a doubly linked list.  Each
+ * Each memory allocation is tracked via a doubly linked list. Each
  * element contains the caller's component, module name, function name, and
- * line number.  acpi_ut_allocate and acpi_ut_allocate_zeroed call
+ * line number. acpi_ut_allocate and acpi_ut_allocate_zeroed call
  * acpi_ut_track_allocation to add an element to the list; deletion
  * occurs in the body of acpi_ut_free.
  */
@@ -499,7 +499,7 @@ void acpi_ut_dump_allocation_info(void)
  * FUNCTION:    acpi_ut_dump_allocations
  *
  * PARAMETERS:  component           - Component(s) to dump info for.
- *              module              - Module to dump info for.  NULL means all.
+ *              module              - Module to dump info for. NULL means all.
  *
  * RETURN:      None
  *
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 0c98d42fb2fd..390db0ca5e2e 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -147,7 +147,7 @@ ACPI_EXPORT_SYMBOL(acpi_subsystem_status)
  * RETURN:      status          - the status of the call
  *
  * DESCRIPTION: This function is called to get information about the current
- *              state of the ACPI subsystem.  It will return system information
+ *              state of the ACPI subsystem. It will return system information
  *              in the out_buffer.
  *
  *              If the function fails an appropriate status will be returned
diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h
index 19503449814f..6c3890e02140 100644
--- a/include/acpi/acexcep.h
+++ b/include/acpi/acexcep.h
@@ -122,7 +122,7 @@
 #define AE_CODE_TBL_MAX                 0x0005
 
 /*
- * AML exceptions.  These are caused by problems with
+ * AML exceptions. These are caused by problems with
  * the actual AML byte stream
  */
 #define AE_AML_BAD_OPCODE               (acpi_status) (0x0001 | AE_CODE_AML)
-- 
cgit v1.2.3-55-g7522


From abf95c362929ce0af7dd413f981597c5386f749d Mon Sep 17 00:00:00 2001
From: Bob Moore
Date: Wed, 31 Oct 2012 02:27:04 +0000
Subject: ACPICA: Remove extra spaces after periods in the Intel license

For consistency with the rest of the source code.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpiosxf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 64e2c8b830ab..43152742b46f 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -1,6 +1,6 @@
 /******************************************************************************
  *
- * Name: acpiosxf.h - All interfaces to the OS Services Layer (OSL).  These
+ * Name: acpiosxf.h - All interfaces to the OS Services Layer (OSL). These
  *                    interfaces must be implemented by OSL to interface the
  *                    ACPI components to the host operating system.
  *
-- 
cgit v1.2.3-55-g7522


From ff60027174cf94bab6d4f45ab5c5da1de63b7d1b Mon Sep 17 00:00:00 2001
From: Bob Moore
Date: Wed, 31 Oct 2012 02:27:40 +0000
Subject: ACPICA: Add ACPI_MOVE_NAME macro to optimize 4-byte ACPI_NAME copies

Resolves to a 32-bit move for the normal case, strncpy on machines
that do not support misaligned transfers.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actypes.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 1fa6ba123071..d1fb674fd393 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -453,10 +453,14 @@ typedef u64 acpi_integer;
 #define ACPI_PHYSADDR_TO_PTR(i)         ACPI_TO_POINTER(i)
 #define ACPI_PTR_TO_PHYSADDR(i)         ACPI_TO_INTEGER(i)
 
+/* Optimizations for 4-character (32-bit) acpi_name manipulation */
+
 #ifndef ACPI_MISALIGNMENT_NOT_SUPPORTED
 #define ACPI_COMPARE_NAME(a,b)          (*ACPI_CAST_PTR (u32, (a)) == *ACPI_CAST_PTR (u32, (b)))
+#define ACPI_MOVE_NAME(dest,src)        (*ACPI_CAST_PTR (u32, (dest)) = *ACPI_CAST_PTR (u32, (src)))
 #else
 #define ACPI_COMPARE_NAME(a,b)          (!ACPI_STRNCMP (ACPI_CAST_PTR (char, (a)), ACPI_CAST_PTR (char, (b)), ACPI_NAME_SIZE))
+#define ACPI_MOVE_NAME(dest,src)        (ACPI_STRNCPY (ACPI_CAST_PTR (char, (dest)), ACPI_CAST_PTR (char, (src)), ACPI_NAME_SIZE))
 #endif
 
 /*******************************************************************************
-- 
cgit v1.2.3-55-g7522


From 2d2dd50880d018e42076252f9fff16e11c567de0 Mon Sep 17 00:00:00 2001
From: Bob Moore
Date: Wed, 31 Oct 2012 02:27:56 +0000
Subject: ACPICA: Update support for ACPI 5 MPST table

Fixes some problems introduced by late changes to the table as it
was added to the ACPI 5.0 specification.  Both the table compiler
and the disassembler and the main header support for the table.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actbl3.h | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h
index 8c61b5fe42a4..6585141e4b97 100644
--- a/include/acpi/actbl3.h
+++ b/include/acpi/actbl3.h
@@ -277,10 +277,10 @@ struct acpi_table_gtdt {
  ******************************************************************************/
 
 #define ACPI_MPST_CHANNEL_INFO \
-	u16                             reserved1; \
 	u8                              channel_id; \
-	u8                              reserved2; \
-	u16                             power_node_count;
+	u8                              reserved1[3]; \
+	u16                             power_node_count; \
+	u16                             reserved2;
 
 /* Main table */
 
@@ -304,9 +304,8 @@ struct acpi_mpst_power_node {
 	u32 length;
 	u64 range_address;
 	u64 range_length;
-	u8 num_power_states;
-	u8 num_physical_components;
-	u16 reserved2;
+	u32 num_power_states;
+	u32 num_physical_components;
 };
 
 /* Values for Flags field above */
@@ -332,10 +331,11 @@ struct acpi_mpst_component {
 
 struct acpi_mpst_data_hdr {
 	u16 characteristics_count;
+	u16 reserved;
 };
 
 struct acpi_mpst_power_data {
-	u8 revision;
+	u8 structure_id;
 	u8 flags;
 	u16 reserved1;
 	u32 average_power;
@@ -356,10 +356,10 @@ struct acpi_mpst_shared {
 	u32 signature;
 	u16 pcc_command;
 	u16 pcc_status;
-	u16 command_register;
-	u16 status_register;
-	u16 power_state_id;
-	u16 power_node_id;
+	u32 command_register;
+	u32 status_register;
+	u32 power_state_id;
+	u32 power_node_id;
 	u64 energy_consumed;
 	u64 average_power;
 };
-- 
cgit v1.2.3-55-g7522


From 413fc3f592c65977858f8adce2e7af0e82aa1191 Mon Sep 17 00:00:00 2001
From: Bob Moore
Date: Wed, 31 Oct 2012 02:28:38 +0000
Subject: ACPICA: AcpiGetObjectInfo: Add support for ACPI 5 _SUB method

Now calls _SUB in addition to the other ID methods: _HID, _CID,
and _UID.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acutils.h  |  4 +++
 drivers/acpi/acpica/nsxfname.c | 29 ++++++++++++++----
 drivers/acpi/acpica/utids.c    | 67 ++++++++++++++++++++++++++++++++++++++++++
 include/acpi/acnames.h         |  1 +
 include/acpi/actypes.h         | 12 ++++----
 5 files changed, 103 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 5a6aa581e244..b0f5f92b674a 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -362,6 +362,10 @@ acpi_status
 acpi_ut_execute_UID(struct acpi_namespace_node *device_node,
 		    struct acpi_pnp_device_id ** return_id);
 
+acpi_status
+acpi_ut_execute_SUB(struct acpi_namespace_node *device_node,
+		    struct acpi_pnp_device_id **return_id);
+
 acpi_status
 acpi_ut_execute_CID(struct acpi_namespace_node *device_node,
 		    struct acpi_pnp_device_id_list ** return_cid_list);
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index 2d10df2ef660..811c6f13f476 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -231,6 +231,7 @@ static char *acpi_ns_copy_device_id(struct acpi_pnp_device_id *dest,
 				    struct acpi_pnp_device_id *source,
 				    char *string_area)
 {
+
 	/* Create the destination PNP_DEVICE_ID */
 
 	dest->string = string_area;
@@ -255,8 +256,8 @@ static char *acpi_ns_copy_device_id(struct acpi_pnp_device_id *dest,
  *              namespace node and possibly by running several standard
  *              control methods (Such as in the case of a device.)
  *
- * For Device and Processor objects, run the Device _HID, _UID, _CID, _STA,
- * _ADR, _sx_w, and _sx_d methods.
+ * For Device and Processor objects, run the Device _HID, _UID, _CID, _SUB,
+ * _STA, _ADR, _sx_w, and _sx_d methods.
  *
  * Note: Allocates the return buffer, must be freed by the caller.
  *
@@ -271,6 +272,7 @@ acpi_get_object_info(acpi_handle handle,
 	struct acpi_pnp_device_id_list *cid_list = NULL;
 	struct acpi_pnp_device_id *hid = NULL;
 	struct acpi_pnp_device_id *uid = NULL;
+	struct acpi_pnp_device_id *sub = NULL;
 	char *next_id_string;
 	acpi_object_type type;
 	acpi_name name;
@@ -315,7 +317,7 @@ acpi_get_object_info(acpi_handle handle,
 	if ((type == ACPI_TYPE_DEVICE) || (type == ACPI_TYPE_PROCESSOR)) {
 		/*
 		 * Get extra info for ACPI Device/Processor objects only:
-		 * Run the Device _HID, _UID, and _CID methods.
+		 * Run the Device _HID, _UID, _SUB, and _CID methods.
 		 *
 		 * Note: none of these methods are required, so they may or may
 		 * not be present for this device. The Info->Valid bitfield is used
@@ -338,6 +340,14 @@ acpi_get_object_info(acpi_handle handle,
 			valid |= ACPI_VALID_UID;
 		}
 
+		/* Execute the Device._SUB method */
+
+		status = acpi_ut_execute_SUB(node, &sub);
+		if (ACPI_SUCCESS(status)) {
+			info_size += sub->length;
+			valid |= ACPI_VALID_SUB;
+		}
+
 		/* Execute the Device._CID method */
 
 		status = acpi_ut_execute_CID(node, &cid_list);
@@ -425,8 +435,9 @@ acpi_get_object_info(acpi_handle handle,
 	}
 
 	/*
-	 * Copy the HID, UID, and CIDs to the return buffer. The variable-length
-	 * strings are copied to the reserved area at the end of the buffer.
+	 * Copy the HID, UID, SUB, and CIDs to the return buffer.
+	 * The variable-length strings are copied to the reserved area
+	 * at the end of the buffer.
 	 *
 	 * For HID and CID, check if the ID is a PCI Root Bridge.
 	 */
@@ -444,6 +455,11 @@ acpi_get_object_info(acpi_handle handle,
 							uid, next_id_string);
 	}
 
+	if (sub) {
+		next_id_string = acpi_ns_copy_device_id(&info->subsystem_id,
+							sub, next_id_string);
+	}
+
 	if (cid_list) {
 		info->compatible_id_list.count = cid_list->count;
 		info->compatible_id_list.list_size = cid_list->list_size;
@@ -480,6 +496,9 @@ acpi_get_object_info(acpi_handle handle,
 	if (uid) {
 		ACPI_FREE(uid);
 	}
+	if (sub) {
+		ACPI_FREE(sub);
+	}
 	if (cid_list) {
 		ACPI_FREE(cid_list);
 	}
diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c
index f18ac81c8399..774c3aefbf5d 100644
--- a/drivers/acpi/acpica/utids.c
+++ b/drivers/acpi/acpica/utids.c
@@ -125,6 +125,73 @@ cleanup:
 	return_ACPI_STATUS(status);
 }
 
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_execute_SUB
+ *
+ * PARAMETERS:  device_node         - Node for the device
+ *              return_id           - Where the _SUB is returned
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Executes the _SUB control method that returns the subsystem
+ *              ID of the device. The _SUB value is always a string containing
+ *              either a valid PNP or ACPI ID.
+ *
+ *              NOTE: Internal function, no parameter validation
+ *
+ ******************************************************************************/
+
+acpi_status
+acpi_ut_execute_SUB(struct acpi_namespace_node *device_node,
+		    struct acpi_pnp_device_id **return_id)
+{
+	union acpi_operand_object *obj_desc;
+	struct acpi_pnp_device_id *sub;
+	u32 length;
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(ut_execute_SUB);
+
+	status = acpi_ut_evaluate_object(device_node, METHOD_NAME__SUB,
+					 ACPI_BTYPE_STRING, &obj_desc);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Get the size of the String to be returned, includes null terminator */
+
+	length = obj_desc->string.length + 1;
+
+	/* Allocate a buffer for the SUB */
+
+	sub =
+	    ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_pnp_device_id) +
+				 (acpi_size) length);
+	if (!sub) {
+		status = AE_NO_MEMORY;
+		goto cleanup;
+	}
+
+	/* Area for the string starts after PNP_DEVICE_ID struct */
+
+	sub->string =
+	    ACPI_ADD_PTR(char, sub, sizeof(struct acpi_pnp_device_id));
+
+	/* Simply copy existing string */
+
+	ACPI_STRCPY(sub->string, obj_desc->string.pointer);
+	sub->length = length;
+	*return_id = sub;
+
+      cleanup:
+
+	/* On exit, we must delete the return object */
+
+	acpi_ut_remove_reference(obj_desc);
+	return_ACPI_STATUS(status);
+}
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ut_execute_UID
diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h
index 745dd24e3cb5..7665df663284 100644
--- a/include/acpi/acnames.h
+++ b/include/acpi/acnames.h
@@ -50,6 +50,7 @@
 #define METHOD_NAME__HID        "_HID"
 #define METHOD_NAME__CID        "_CID"
 #define METHOD_NAME__UID        "_UID"
+#define METHOD_NAME__SUB        "_SUB"
 #define METHOD_NAME__ADR        "_ADR"
 #define METHOD_NAME__INI        "_INI"
 #define METHOD_NAME__STA        "_STA"
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index d1fb674fd393..4f43f1fba132 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -1024,7 +1024,7 @@ u32 (*acpi_interface_handler) (acpi_string interface_name, u32 supported);
 
 #define ACPI_UUID_LENGTH                16
 
-/* Structures used for device/processor HID, UID, CID */
+/* Structures used for device/processor HID, UID, CID, and SUB */
 
 struct acpi_pnp_device_id {
 	u32 length;		/* Length of string + null */
@@ -1054,6 +1054,7 @@ struct acpi_device_info {
 	u64 address;	/* _ADR value */
 	struct acpi_pnp_device_id hardware_id;	/* _HID value */
 	struct acpi_pnp_device_id unique_id;	/* _UID value */
+	struct acpi_pnp_device_id subsystem_id;	/* _SUB value */
 	struct acpi_pnp_device_id_list compatible_id_list;	/* _CID list <must be last> */
 };
 
@@ -1067,11 +1068,12 @@ struct acpi_device_info {
 #define ACPI_VALID_ADR                  0x02
 #define ACPI_VALID_HID                  0x04
 #define ACPI_VALID_UID                  0x08
-#define ACPI_VALID_CID                  0x10
-#define ACPI_VALID_SXDS                 0x20
-#define ACPI_VALID_SXWS                 0x40
+#define ACPI_VALID_SUB                  0x10
+#define ACPI_VALID_CID                  0x20
+#define ACPI_VALID_SXDS                 0x40
+#define ACPI_VALID_SXWS                 0x80
 
-/* Flags for _STA method */
+/* Flags for _STA return value (current_status above) */
 
 #define ACPI_STA_DEVICE_PRESENT         0x01
 #define ACPI_STA_DEVICE_ENABLED         0x02
-- 
cgit v1.2.3-55-g7522


From a19ec8a607f82885aa150836a72dec12d3c9aca5 Mon Sep 17 00:00:00 2001
From: Bob Moore
Date: Wed, 31 Oct 2012 02:28:46 +0000
Subject: ACPICA: Update version to 20121018

Version 20121018.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpixf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 2596de109ff7..3d88395d4d6f 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -46,7 +46,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20120913
+#define ACPI_CA_VERSION                 0x20121018
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
-- 
cgit v1.2.3-55-g7522


From 4b972f0b04eaae645b22d99479b9aea43c3d64e7 Mon Sep 17 00:00:00 2001
From: viresh kumar
Date: Tue, 23 Oct 2012 01:23:43 +0200
Subject: cpufreq / core: Fix printing of governor and driver name

Arrays for governer and driver name are of size CPUFREQ_NAME_LEN or 16.
i.e. 15 bytes for name and 1 for trailing '\0'.

When cpufreq driver print these names (for sysfs), it includes '\n' or ' ' in
the fmt string and still passes length as CPUFREQ_NAME_LEN. If the driver or
governor names are using all 15 fields allocated to them, then the trailing '\n'
or ' ' will never be printed. And so commands like:

root@linaro-developer# cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_driver

will print something like:

cpufreq_foodrvroot@linaro-developer#

Fix this by increasing print length by one character.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 6 +++---
 include/linux/cpufreq.h   | 2 ++
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 021973b7dc56..db6e337ad337 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -445,7 +445,7 @@ static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
 	else if (policy->policy == CPUFREQ_POLICY_PERFORMANCE)
 		return sprintf(buf, "performance\n");
 	else if (policy->governor)
-		return scnprintf(buf, CPUFREQ_NAME_LEN, "%s\n",
+		return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n",
 				policy->governor->name);
 	return -EINVAL;
 }
@@ -491,7 +491,7 @@ static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
  */
 static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf)
 {
-	return scnprintf(buf, CPUFREQ_NAME_LEN, "%s\n", cpufreq_driver->name);
+	return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", cpufreq_driver->name);
 }
 
 /**
@@ -512,7 +512,7 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
 		if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char))
 		    - (CPUFREQ_NAME_LEN + 2)))
 			goto out;
-		i += scnprintf(&buf[i], CPUFREQ_NAME_LEN, "%s ", t->name);
+		i += scnprintf(&buf[i], CPUFREQ_NAME_PLEN, "%s ", t->name);
 	}
 out:
 	i += sprintf(&buf[i], "\n");
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index b60f6ba01d0c..fc4b78510151 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -22,6 +22,8 @@
 #include <asm/div64.h>
 
 #define CPUFREQ_NAME_LEN 16
+/* Print length for names. Extra 1 space for accomodating '\n' in prints */
+#define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1)
 
 
 /*********************************************************************
-- 
cgit v1.2.3-55-g7522


From 2aacdfff9c6958723aa5076003247933cefc32ea Mon Sep 17 00:00:00 2001
From: viresh kumar
Date: Tue, 23 Oct 2012 01:28:05 +0200
Subject: cpufreq: Move common part from governors to separate file, v2

Multiple cpufreq governers have defined similar get_cpu_idle_time_***()
routines. These routines must be moved to some common place, so that all
governors can use them.

So moving them to cpufreq_governor.c, which seems to be a better place for
keeping these routines.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/Makefile               |  4 +--
 drivers/cpufreq/cpufreq_conservative.c | 34 ----------------------
 drivers/cpufreq/cpufreq_governor.c     | 52 ++++++++++++++++++++++++++++++++++
 drivers/cpufreq/cpufreq_ondemand.c     | 34 ----------------------
 include/linux/cpufreq.h                |  5 ++++
 5 files changed, 59 insertions(+), 70 deletions(-)
 create mode 100644 drivers/cpufreq/cpufreq_governor.c

(limited to 'include')

diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 1bc90e1306d8..5b1413e47216 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -7,8 +7,8 @@ obj-$(CONFIG_CPU_FREQ_STAT)             += cpufreq_stats.o
 obj-$(CONFIG_CPU_FREQ_GOV_PERFORMANCE)	+= cpufreq_performance.o
 obj-$(CONFIG_CPU_FREQ_GOV_POWERSAVE)	+= cpufreq_powersave.o
 obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE)	+= cpufreq_userspace.o
-obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND)	+= cpufreq_ondemand.o
-obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
+obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND)	+= cpufreq_ondemand.o cpufreq_governor.o
+obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o cpufreq_governor.o
 
 # CPUfreq cross-arch helpers
 obj-$(CONFIG_CPU_FREQ_TABLE)		+= freq_table.o
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index a152af7e1991..181abad07266 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -95,40 +95,6 @@ static struct dbs_tuners {
 	.freq_step = 5,
 };
 
-static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
-{
-	u64 idle_time;
-	u64 cur_wall_time;
-	u64 busy_time;
-
-	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
-
-	busy_time  = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
-
-	idle_time = cur_wall_time - busy_time;
-	if (wall)
-		*wall = jiffies_to_usecs(cur_wall_time);
-
-	return jiffies_to_usecs(idle_time);
-}
-
-static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
-{
-	u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
-
-	if (idle_time == -1ULL)
-		return get_cpu_idle_time_jiffy(cpu, wall);
-	else
-		idle_time += get_cpu_iowait_time_us(cpu, wall);
-
-	return idle_time;
-}
-
 /* keep track of frequency transitions */
 static int
 dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
new file mode 100644
index 000000000000..0001071cdcdb
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -0,0 +1,52 @@
+/*
+ * drivers/cpufreq/cpufreq_governor.c
+ *
+ * CPUFREQ governors common code
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/cputime.h>
+#include <linux/export.h>
+#include <linux/kernel_stat.h>
+#include <linux/tick.h>
+#include <linux/types.h>
+/*
+ * Code picked from earlier governer implementations
+ */
+static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
+{
+	u64 idle_time;
+	u64 cur_wall_time;
+	u64 busy_time;
+
+	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
+
+	busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
+
+	idle_time = cur_wall_time - busy_time;
+	if (wall)
+		*wall = jiffies_to_usecs(cur_wall_time);
+
+	return jiffies_to_usecs(idle_time);
+}
+
+cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
+{
+	u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
+
+	if (idle_time == -1ULL)
+		return get_cpu_idle_time_jiffy(cpu, wall);
+	else
+		idle_time += get_cpu_iowait_time_us(cpu, wall);
+
+	return idle_time;
+}
+EXPORT_SYMBOL_GPL(get_cpu_idle_time);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 396322f2a83f..d7f774bb49dd 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -119,40 +119,6 @@ static struct dbs_tuners {
 	.powersave_bias = 0,
 };
 
-static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
-{
-	u64 idle_time;
-	u64 cur_wall_time;
-	u64 busy_time;
-
-	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
-
-	busy_time  = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
-
-	idle_time = cur_wall_time - busy_time;
-	if (wall)
-		*wall = jiffies_to_usecs(cur_wall_time);
-
-	return jiffies_to_usecs(idle_time);
-}
-
-static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
-{
-	u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
-
-	if (idle_time == -1ULL)
-		return get_cpu_idle_time_jiffy(cpu, wall);
-	else
-		idle_time += get_cpu_iowait_time_us(cpu, wall);
-
-	return idle_time;
-}
-
 static inline cputime64_t get_cpu_iowait_time(unsigned int cpu, cputime64_t *wall)
 {
 	u64 iowait_time = get_cpu_iowait_time_us(cpu, wall);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index fc4b78510151..d03c21993052 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -11,6 +11,7 @@
 #ifndef _LINUX_CPUFREQ_H
 #define _LINUX_CPUFREQ_H
 
+#include <asm/cputime.h>
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 #include <linux/threads.h>
@@ -407,5 +408,9 @@ void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
 
 void cpufreq_frequency_table_put_attr(unsigned int cpu);
 
+/*********************************************************************
+ *                     Governor Helpers				     *
+ *********************************************************************/
+cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall);
 
 #endif /* _LINUX_CPUFREQ_H */
-- 
cgit v1.2.3-55-g7522


From 4471a34f9a1f2da220272e823bdb8e8fa83a7661 Mon Sep 17 00:00:00 2001
From: Viresh Kumar
Date: Fri, 26 Oct 2012 00:47:42 +0200
Subject: cpufreq: governors: remove redundant code

Initially ondemand governor was written and then using its code conservative
governor is written. It used a lot of code from ondemand governor, but copy of
code was created instead of using the same routines from both governors. Which
increased code redundancy, which is difficult to manage.

This patch is an attempt to move common part of both the governors to
cpufreq_governor.c file to come over above mentioned issues.

This shouldn't change anything from functionality point of view.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq_conservative.c | 548 ++++++++------------------
 drivers/cpufreq/cpufreq_governor.c     | 276 ++++++++++++-
 drivers/cpufreq/cpufreq_governor.h     | 177 +++++++++
 drivers/cpufreq/cpufreq_ondemand.c     | 698 +++++++++++----------------------
 include/linux/cpufreq.h                |   6 -
 5 files changed, 832 insertions(+), 873 deletions(-)
 create mode 100644 drivers/cpufreq/cpufreq_governor.h

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 181abad07266..64ef737e7e72 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -11,83 +11,30 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
 #include <linux/cpufreq.h>
-#include <linux/cpu.h>
-#include <linux/jiffies.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/kernel_stat.h>
+#include <linux/kobject.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/hrtimer.h>
-#include <linux/tick.h>
-#include <linux/ktime.h>
-#include <linux/sched.h>
+#include <linux/notifier.h>
+#include <linux/percpu-defs.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
 
-/*
- * dbs is used in this file as a shortform for demandbased switching
- * It helps to keep variable names smaller, simpler
- */
+#include "cpufreq_governor.h"
 
+/* Conservative governor macors */
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_FREQUENCY_DOWN_THRESHOLD		(20)
-
-/*
- * The polling frequency of this governor depends on the capability of
- * the processor. Default polling frequency is 1000 times the transition
- * latency of the processor. The governor will work on any processor with
- * transition latency <= 10mS, using appropriate sampling
- * rate.
- * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
- * this governor will not work.
- * All times here are in uS.
- */
-#define MIN_SAMPLING_RATE_RATIO			(2)
-
-static unsigned int min_sampling_rate;
-
-#define LATENCY_MULTIPLIER			(1000)
-#define MIN_LATENCY_MULTIPLIER			(100)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(10)
-#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)
-
-static void do_dbs_timer(struct work_struct *work);
-
-struct cpu_dbs_info_s {
-	cputime64_t prev_cpu_idle;
-	cputime64_t prev_cpu_wall;
-	cputime64_t prev_cpu_nice;
-	struct cpufreq_policy *cur_policy;
-	struct delayed_work work;
-	unsigned int down_skip;
-	unsigned int requested_freq;
-	int cpu;
-	unsigned int enable:1;
-	/*
-	 * percpu mutex that serializes governor limit change with
-	 * do_dbs_timer invocation. We do not want do_dbs_timer to run
-	 * when user is changing the governor or limits.
-	 */
-	struct mutex timer_mutex;
-};
-static DEFINE_PER_CPU(struct cpu_dbs_info_s, cs_cpu_dbs_info);
 
-static unsigned int dbs_enable;	/* number of CPUs using this policy */
+static struct dbs_data cs_dbs_data;
+static DEFINE_PER_CPU(struct cs_cpu_dbs_info_s, cs_cpu_dbs_info);
 
-/*
- * dbs_mutex protects dbs_enable in governor start/stop.
- */
-static DEFINE_MUTEX(dbs_mutex);
-
-static struct dbs_tuners {
-	unsigned int sampling_rate;
-	unsigned int sampling_down_factor;
-	unsigned int up_threshold;
-	unsigned int down_threshold;
-	unsigned int ignore_nice;
-	unsigned int freq_step;
-} dbs_tuners_ins = {
+static struct cs_dbs_tuners cs_tuners = {
 	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
 	.down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD,
 	.sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR,
@@ -95,61 +42,121 @@ static struct dbs_tuners {
 	.freq_step = 5,
 };
 
-/* keep track of frequency transitions */
-static int
-dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-		     void *data)
+/*
+ * Every sampling_rate, we check, if current idle time is less than 20%
+ * (default), then we try to increase frequency Every sampling_rate *
+ * sampling_down_factor, we check, if current idle time is more than 80%, then
+ * we try to decrease frequency
+ *
+ * Any frequency increase takes it to the maximum frequency. Frequency reduction
+ * happens at minimum steps of 5% (default) of maximum frequency
+ */
+static void cs_check_cpu(int cpu, unsigned int load)
 {
-	struct cpufreq_freqs *freq = data;
-	struct cpu_dbs_info_s *this_dbs_info = &per_cpu(cs_cpu_dbs_info,
-							freq->cpu);
+	struct cs_cpu_dbs_info_s *dbs_info = &per_cpu(cs_cpu_dbs_info, cpu);
+	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
+	unsigned int freq_target;
+
+	/*
+	 * break out if we 'cannot' reduce the speed as the user might
+	 * want freq_step to be zero
+	 */
+	if (cs_tuners.freq_step == 0)
+		return;
+
+	/* Check for frequency increase */
+	if (load > cs_tuners.up_threshold) {
+		dbs_info->down_skip = 0;
+
+		/* if we are already at full speed then break out early */
+		if (dbs_info->requested_freq == policy->max)
+			return;
+
+		freq_target = (cs_tuners.freq_step * policy->max) / 100;
+
+		/* max freq cannot be less than 100. But who knows.... */
+		if (unlikely(freq_target == 0))
+			freq_target = 5;
+
+		dbs_info->requested_freq += freq_target;
+		if (dbs_info->requested_freq > policy->max)
+			dbs_info->requested_freq = policy->max;
 
+		__cpufreq_driver_target(policy, dbs_info->requested_freq,
+			CPUFREQ_RELATION_H);
+		return;
+	}
+
+	/*
+	 * The optimal frequency is the frequency that is the lowest that can
+	 * support the current CPU usage without triggering the up policy. To be
+	 * safe, we focus 10 points under the threshold.
+	 */
+	if (load < (cs_tuners.down_threshold - 10)) {
+		freq_target = (cs_tuners.freq_step * policy->max) / 100;
+
+		dbs_info->requested_freq -= freq_target;
+		if (dbs_info->requested_freq < policy->min)
+			dbs_info->requested_freq = policy->min;
+
+		/*
+		 * if we cannot reduce the frequency anymore, break out early
+		 */
+		if (policy->cur == policy->min)
+			return;
+
+		__cpufreq_driver_target(policy, dbs_info->requested_freq,
+				CPUFREQ_RELATION_H);
+		return;
+	}
+}
+
+static void cs_dbs_timer(struct work_struct *work)
+{
+	struct cs_cpu_dbs_info_s *dbs_info = container_of(work,
+			struct cs_cpu_dbs_info_s, cdbs.work.work);
+	unsigned int cpu = dbs_info->cdbs.cpu;
+	int delay = delay_for_sampling_rate(cs_tuners.sampling_rate);
+
+	mutex_lock(&dbs_info->cdbs.timer_mutex);
+
+	dbs_check_cpu(&cs_dbs_data, cpu);
+
+	schedule_delayed_work_on(cpu, &dbs_info->cdbs.work, delay);
+	mutex_unlock(&dbs_info->cdbs.timer_mutex);
+}
+
+static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+		void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	struct cs_cpu_dbs_info_s *dbs_info =
+					&per_cpu(cs_cpu_dbs_info, freq->cpu);
 	struct cpufreq_policy *policy;
 
-	if (!this_dbs_info->enable)
+	if (!dbs_info->enable)
 		return 0;
 
-	policy = this_dbs_info->cur_policy;
+	policy = dbs_info->cdbs.cur_policy;
 
 	/*
-	 * we only care if our internally tracked freq moves outside
-	 * the 'valid' ranges of freqency available to us otherwise
-	 * we do not change it
+	 * we only care if our internally tracked freq moves outside the 'valid'
+	 * ranges of freqency available to us otherwise we do not change it
 	*/
-	if (this_dbs_info->requested_freq > policy->max
-			|| this_dbs_info->requested_freq < policy->min)
-		this_dbs_info->requested_freq = freq->new;
+	if (dbs_info->requested_freq > policy->max
+			|| dbs_info->requested_freq < policy->min)
+		dbs_info->requested_freq = freq->new;
 
 	return 0;
 }
 
-static struct notifier_block dbs_cpufreq_notifier_block = {
-	.notifier_call = dbs_cpufreq_notifier
-};
-
 /************************** sysfs interface ************************/
 static ssize_t show_sampling_rate_min(struct kobject *kobj,
 				      struct attribute *attr, char *buf)
 {
-	return sprintf(buf, "%u\n", min_sampling_rate);
+	return sprintf(buf, "%u\n", cs_dbs_data.min_sampling_rate);
 }
 
-define_one_global_ro(sampling_rate_min);
-
-/* cpufreq_conservative Governor Tunables */
-#define show_one(file_name, object)					\
-static ssize_t show_##file_name						\
-(struct kobject *kobj, struct attribute *attr, char *buf)		\
-{									\
-	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
-}
-show_one(sampling_rate, sampling_rate);
-show_one(sampling_down_factor, sampling_down_factor);
-show_one(up_threshold, up_threshold);
-show_one(down_threshold, down_threshold);
-show_one(ignore_nice_load, ignore_nice);
-show_one(freq_step, freq_step);
-
 static ssize_t store_sampling_down_factor(struct kobject *a,
 					  struct attribute *b,
 					  const char *buf, size_t count)
@@ -161,7 +168,7 @@ static ssize_t store_sampling_down_factor(struct kobject *a,
 	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
 		return -EINVAL;
 
-	dbs_tuners_ins.sampling_down_factor = input;
+	cs_tuners.sampling_down_factor = input;
 	return count;
 }
 
@@ -175,7 +182,7 @@ static ssize_t store_sampling_rate(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
-	dbs_tuners_ins.sampling_rate = max(input, min_sampling_rate);
+	cs_tuners.sampling_rate = max(input, cs_dbs_data.min_sampling_rate);
 	return count;
 }
 
@@ -186,11 +193,10 @@ static ssize_t store_up_threshold(struct kobject *a, struct attribute *b,
 	int ret;
 	ret = sscanf(buf, "%u", &input);
 
-	if (ret != 1 || input > 100 ||
-			input <= dbs_tuners_ins.down_threshold)
+	if (ret != 1 || input > 100 || input <= cs_tuners.down_threshold)
 		return -EINVAL;
 
-	dbs_tuners_ins.up_threshold = input;
+	cs_tuners.up_threshold = input;
 	return count;
 }
 
@@ -203,21 +209,19 @@ static ssize_t store_down_threshold(struct kobject *a, struct attribute *b,
 
 	/* cannot be lower than 11 otherwise freq will not fall */
 	if (ret != 1 || input < 11 || input > 100 ||
-			input >= dbs_tuners_ins.up_threshold)
+			input >= cs_tuners.up_threshold)
 		return -EINVAL;
 
-	dbs_tuners_ins.down_threshold = input;
+	cs_tuners.down_threshold = input;
 	return count;
 }
 
 static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
 				      const char *buf, size_t count)
 {
-	unsigned int input;
+	unsigned int input, j;
 	int ret;
 
-	unsigned int j;
-
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
@@ -225,19 +229,20 @@ static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
 	if (input > 1)
 		input = 1;
 
-	if (input == dbs_tuners_ins.ignore_nice) /* nothing to do */
+	if (input == cs_tuners.ignore_nice) /* nothing to do */
 		return count;
 
-	dbs_tuners_ins.ignore_nice = input;
+	cs_tuners.ignore_nice = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
 	for_each_online_cpu(j) {
-		struct cpu_dbs_info_s *dbs_info;
+		struct cs_cpu_dbs_info_s *dbs_info;
 		dbs_info = &per_cpu(cs_cpu_dbs_info, j);
-		dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
-						&dbs_info->prev_cpu_wall);
-		if (dbs_tuners_ins.ignore_nice)
-			dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
+						&dbs_info->cdbs.prev_cpu_wall);
+		if (cs_tuners.ignore_nice)
+			dbs_info->cdbs.prev_cpu_nice =
+				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 	}
 	return count;
 }
@@ -255,18 +260,28 @@ static ssize_t store_freq_step(struct kobject *a, struct attribute *b,
 	if (input > 100)
 		input = 100;
 
-	/* no need to test here if freq_step is zero as the user might actually
-	 * want this, they would be crazy though :) */
-	dbs_tuners_ins.freq_step = input;
+	/*
+	 * no need to test here if freq_step is zero as the user might actually
+	 * want this, they would be crazy though :)
+	 */
+	cs_tuners.freq_step = input;
 	return count;
 }
 
+show_one(cs, sampling_rate, sampling_rate);
+show_one(cs, sampling_down_factor, sampling_down_factor);
+show_one(cs, up_threshold, up_threshold);
+show_one(cs, down_threshold, down_threshold);
+show_one(cs, ignore_nice_load, ignore_nice);
+show_one(cs, freq_step, freq_step);
+
 define_one_global_rw(sampling_rate);
 define_one_global_rw(sampling_down_factor);
 define_one_global_rw(up_threshold);
 define_one_global_rw(down_threshold);
 define_one_global_rw(ignore_nice_load);
 define_one_global_rw(freq_step);
+define_one_global_ro(sampling_rate_min);
 
 static struct attribute *dbs_attributes[] = {
 	&sampling_rate_min.attr,
@@ -279,283 +294,38 @@ static struct attribute *dbs_attributes[] = {
 	NULL
 };
 
-static struct attribute_group dbs_attr_group = {
+static struct attribute_group cs_attr_group = {
 	.attrs = dbs_attributes,
 	.name = "conservative",
 };
 
 /************************** sysfs end ************************/
 
-static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
-{
-	unsigned int load = 0;
-	unsigned int max_load = 0;
-	unsigned int freq_target;
-
-	struct cpufreq_policy *policy;
-	unsigned int j;
-
-	policy = this_dbs_info->cur_policy;
-
-	/*
-	 * Every sampling_rate, we check, if current idle time is less
-	 * than 20% (default), then we try to increase frequency
-	 * Every sampling_rate*sampling_down_factor, we check, if current
-	 * idle time is more than 80%, then we try to decrease frequency
-	 *
-	 * Any frequency increase takes it to the maximum frequency.
-	 * Frequency reduction happens at minimum steps of
-	 * 5% (default) of maximum frequency
-	 */
-
-	/* Get Absolute Load */
-	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_info_s *j_dbs_info;
-		cputime64_t cur_wall_time, cur_idle_time;
-		unsigned int idle_time, wall_time;
-
-		j_dbs_info = &per_cpu(cs_cpu_dbs_info, j);
-
-		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
-
-		wall_time = (unsigned int)
-			(cur_wall_time - j_dbs_info->prev_cpu_wall);
-		j_dbs_info->prev_cpu_wall = cur_wall_time;
-
-		idle_time = (unsigned int)
-			(cur_idle_time - j_dbs_info->prev_cpu_idle);
-		j_dbs_info->prev_cpu_idle = cur_idle_time;
-
-		if (dbs_tuners_ins.ignore_nice) {
-			u64 cur_nice;
-			unsigned long cur_nice_jiffies;
-
-			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
-					 j_dbs_info->prev_cpu_nice;
-			/*
-			 * Assumption: nice time between sampling periods will
-			 * be less than 2^32 jiffies for 32 bit sys
-			 */
-			cur_nice_jiffies = (unsigned long)
-					cputime64_to_jiffies64(cur_nice);
-
-			j_dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-			idle_time += jiffies_to_usecs(cur_nice_jiffies);
-		}
-
-		if (unlikely(!wall_time || wall_time < idle_time))
-			continue;
-
-		load = 100 * (wall_time - idle_time) / wall_time;
-
-		if (load > max_load)
-			max_load = load;
-	}
+define_get_cpu_dbs_routines(cs_cpu_dbs_info);
 
-	/*
-	 * break out if we 'cannot' reduce the speed as the user might
-	 * want freq_step to be zero
-	 */
-	if (dbs_tuners_ins.freq_step == 0)
-		return;
-
-	/* Check for frequency increase */
-	if (max_load > dbs_tuners_ins.up_threshold) {
-		this_dbs_info->down_skip = 0;
-
-		/* if we are already at full speed then break out early */
-		if (this_dbs_info->requested_freq == policy->max)
-			return;
-
-		freq_target = (dbs_tuners_ins.freq_step * policy->max) / 100;
-
-		/* max freq cannot be less than 100. But who knows.... */
-		if (unlikely(freq_target == 0))
-			freq_target = 5;
-
-		this_dbs_info->requested_freq += freq_target;
-		if (this_dbs_info->requested_freq > policy->max)
-			this_dbs_info->requested_freq = policy->max;
-
-		__cpufreq_driver_target(policy, this_dbs_info->requested_freq,
-			CPUFREQ_RELATION_H);
-		return;
-	}
-
-	/*
-	 * The optimal frequency is the frequency that is the lowest that
-	 * can support the current CPU usage without triggering the up
-	 * policy. To be safe, we focus 10 points under the threshold.
-	 */
-	if (max_load < (dbs_tuners_ins.down_threshold - 10)) {
-		freq_target = (dbs_tuners_ins.freq_step * policy->max) / 100;
-
-		this_dbs_info->requested_freq -= freq_target;
-		if (this_dbs_info->requested_freq < policy->min)
-			this_dbs_info->requested_freq = policy->min;
-
-		/*
-		 * if we cannot reduce the frequency anymore, break out early
-		 */
-		if (policy->cur == policy->min)
-			return;
-
-		__cpufreq_driver_target(policy, this_dbs_info->requested_freq,
-				CPUFREQ_RELATION_H);
-		return;
-	}
-}
-
-static void do_dbs_timer(struct work_struct *work)
-{
-	struct cpu_dbs_info_s *dbs_info =
-		container_of(work, struct cpu_dbs_info_s, work.work);
-	unsigned int cpu = dbs_info->cpu;
-
-	/* We want all CPUs to do sampling nearly on same jiffy */
-	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
-
-	delay -= jiffies % delay;
-
-	mutex_lock(&dbs_info->timer_mutex);
-
-	dbs_check_cpu(dbs_info);
-
-	schedule_delayed_work_on(cpu, &dbs_info->work, delay);
-	mutex_unlock(&dbs_info->timer_mutex);
-}
-
-static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info)
-{
-	/* We want all CPUs to do sampling nearly on same jiffy */
-	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
-	delay -= jiffies % delay;
+static struct notifier_block cs_cpufreq_notifier_block = {
+	.notifier_call = dbs_cpufreq_notifier,
+};
 
-	dbs_info->enable = 1;
-	INIT_DEFERRABLE_WORK(&dbs_info->work, do_dbs_timer);
-	schedule_delayed_work_on(dbs_info->cpu, &dbs_info->work, delay);
-}
+static struct cs_ops cs_ops = {
+	.notifier_block = &cs_cpufreq_notifier_block,
+};
 
-static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
-{
-	dbs_info->enable = 0;
-	cancel_delayed_work_sync(&dbs_info->work);
-}
+static struct dbs_data cs_dbs_data = {
+	.governor = GOV_CONSERVATIVE,
+	.attr_group = &cs_attr_group,
+	.tuners = &cs_tuners,
+	.get_cpu_cdbs = get_cpu_cdbs,
+	.get_cpu_dbs_info_s = get_cpu_dbs_info_s,
+	.gov_dbs_timer = cs_dbs_timer,
+	.gov_check_cpu = cs_check_cpu,
+	.gov_ops = &cs_ops,
+};
 
-static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
+static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
 				   unsigned int event)
 {
-	unsigned int cpu = policy->cpu;
-	struct cpu_dbs_info_s *this_dbs_info;
-	unsigned int j;
-	int rc;
-
-	this_dbs_info = &per_cpu(cs_cpu_dbs_info, cpu);
-
-	switch (event) {
-	case CPUFREQ_GOV_START:
-		if ((!cpu_online(cpu)) || (!policy->cur))
-			return -EINVAL;
-
-		mutex_lock(&dbs_mutex);
-
-		for_each_cpu(j, policy->cpus) {
-			struct cpu_dbs_info_s *j_dbs_info;
-			j_dbs_info = &per_cpu(cs_cpu_dbs_info, j);
-			j_dbs_info->cur_policy = policy;
-
-			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
-						&j_dbs_info->prev_cpu_wall);
-			if (dbs_tuners_ins.ignore_nice)
-				j_dbs_info->prev_cpu_nice =
-						kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-		}
-		this_dbs_info->cpu = cpu;
-		this_dbs_info->down_skip = 0;
-		this_dbs_info->requested_freq = policy->cur;
-
-		mutex_init(&this_dbs_info->timer_mutex);
-		dbs_enable++;
-		/*
-		 * Start the timerschedule work, when this governor
-		 * is used for first time
-		 */
-		if (dbs_enable == 1) {
-			unsigned int latency;
-			/* policy latency is in nS. Convert it to uS first */
-			latency = policy->cpuinfo.transition_latency / 1000;
-			if (latency == 0)
-				latency = 1;
-
-			rc = sysfs_create_group(cpufreq_global_kobject,
-						&dbs_attr_group);
-			if (rc) {
-				mutex_unlock(&dbs_mutex);
-				return rc;
-			}
-
-			/*
-			 * conservative does not implement micro like ondemand
-			 * governor, thus we are bound to jiffes/HZ
-			 */
-			min_sampling_rate =
-				MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10);
-			/* Bring kernel and HW constraints together */
-			min_sampling_rate = max(min_sampling_rate,
-					MIN_LATENCY_MULTIPLIER * latency);
-			dbs_tuners_ins.sampling_rate =
-				max(min_sampling_rate,
-				    latency * LATENCY_MULTIPLIER);
-
-			cpufreq_register_notifier(
-					&dbs_cpufreq_notifier_block,
-					CPUFREQ_TRANSITION_NOTIFIER);
-		}
-		mutex_unlock(&dbs_mutex);
-
-		dbs_timer_init(this_dbs_info);
-
-		break;
-
-	case CPUFREQ_GOV_STOP:
-		dbs_timer_exit(this_dbs_info);
-
-		mutex_lock(&dbs_mutex);
-		dbs_enable--;
-		mutex_destroy(&this_dbs_info->timer_mutex);
-
-		/*
-		 * Stop the timerschedule work, when this governor
-		 * is used for first time
-		 */
-		if (dbs_enable == 0)
-			cpufreq_unregister_notifier(
-					&dbs_cpufreq_notifier_block,
-					CPUFREQ_TRANSITION_NOTIFIER);
-
-		mutex_unlock(&dbs_mutex);
-		if (!dbs_enable)
-			sysfs_remove_group(cpufreq_global_kobject,
-					   &dbs_attr_group);
-
-		break;
-
-	case CPUFREQ_GOV_LIMITS:
-		mutex_lock(&this_dbs_info->timer_mutex);
-		if (policy->max < this_dbs_info->cur_policy->cur)
-			__cpufreq_driver_target(
-					this_dbs_info->cur_policy,
-					policy->max, CPUFREQ_RELATION_H);
-		else if (policy->min > this_dbs_info->cur_policy->cur)
-			__cpufreq_driver_target(
-					this_dbs_info->cur_policy,
-					policy->min, CPUFREQ_RELATION_L);
-		dbs_check_cpu(this_dbs_info);
-		mutex_unlock(&this_dbs_info->timer_mutex);
-
-		break;
-	}
-	return 0;
+	return cpufreq_governor_dbs(&cs_dbs_data, policy, event);
 }
 
 #ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
@@ -563,13 +333,14 @@ static
 #endif
 struct cpufreq_governor cpufreq_gov_conservative = {
 	.name			= "conservative",
-	.governor		= cpufreq_governor_dbs,
+	.governor		= cs_cpufreq_governor_dbs,
 	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
 	.owner			= THIS_MODULE,
 };
 
 static int __init cpufreq_gov_dbs_init(void)
 {
+	mutex_init(&cs_dbs_data.mutex);
 	return cpufreq_register_governor(&cpufreq_gov_conservative);
 }
 
@@ -578,7 +349,6 @@ static void __exit cpufreq_gov_dbs_exit(void)
 	cpufreq_unregister_governor(&cpufreq_gov_conservative);
 }
 
-
 MODULE_AUTHOR("Alexander Clouter <alex@digriz.org.uk>");
 MODULE_DESCRIPTION("'cpufreq_conservative' - A dynamic cpufreq governor for "
 		"Low Latency Frequency Transition capable processors "
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 679842a8d34a..5ea2c829a796 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -3,19 +3,31 @@
  *
  * CPUFREQ governors common code
  *
+ * Copyright	(C) 2001 Russell King
+ *		(C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
+ *		(C) 2003 Jun Nakajima <jun.nakajima@intel.com>
+ *		(C) 2009 Alexander Clouter <alex@digriz.org.uk>
+ *		(c) 2012 Viresh Kumar <viresh.kumar@linaro.org>
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <asm/cputime.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
 #include <linux/export.h>
 #include <linux/kernel_stat.h>
+#include <linux/mutex.h>
 #include <linux/tick.h>
 #include <linux/types.h>
-/*
- * Code picked from earlier governer implementations
- */
+#include <linux/workqueue.h>
+
+#include "cpufreq_governor.h"
+
 static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
 	u64 idle_time;
@@ -33,9 +45,9 @@ static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 
 	idle_time = cur_wall_time - busy_time;
 	if (wall)
-		*wall = cputime_to_usecs(cur_wall_time);
+		*wall = jiffies_to_usecs(cur_wall_time);
 
-	return cputime_to_usecs(idle_time);
+	return jiffies_to_usecs(idle_time);
 }
 
 cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
@@ -50,3 +62,257 @@ cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
 	return idle_time;
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
+
+void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
+{
+	struct cpu_dbs_common_info *cdbs = dbs_data->get_cpu_cdbs(cpu);
+	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+	struct cpufreq_policy *policy;
+	unsigned int max_load = 0;
+	unsigned int ignore_nice;
+	unsigned int j;
+
+	if (dbs_data->governor == GOV_ONDEMAND)
+		ignore_nice = od_tuners->ignore_nice;
+	else
+		ignore_nice = cs_tuners->ignore_nice;
+
+	policy = cdbs->cur_policy;
+
+	/* Get Absolute Load (in terms of freq for ondemand gov) */
+	for_each_cpu(j, policy->cpus) {
+		struct cpu_dbs_common_info *j_cdbs;
+		cputime64_t cur_wall_time, cur_idle_time, cur_iowait_time;
+		unsigned int idle_time, wall_time, iowait_time;
+		unsigned int load;
+
+		j_cdbs = dbs_data->get_cpu_cdbs(j);
+
+		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
+
+		wall_time = (unsigned int)
+			(cur_wall_time - j_cdbs->prev_cpu_wall);
+		j_cdbs->prev_cpu_wall = cur_wall_time;
+
+		idle_time = (unsigned int)
+			(cur_idle_time - j_cdbs->prev_cpu_idle);
+		j_cdbs->prev_cpu_idle = cur_idle_time;
+
+		if (ignore_nice) {
+			u64 cur_nice;
+			unsigned long cur_nice_jiffies;
+
+			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
+					 cdbs->prev_cpu_nice;
+			/*
+			 * Assumption: nice time between sampling periods will
+			 * be less than 2^32 jiffies for 32 bit sys
+			 */
+			cur_nice_jiffies = (unsigned long)
+					cputime64_to_jiffies64(cur_nice);
+
+			cdbs->prev_cpu_nice =
+				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+			idle_time += jiffies_to_usecs(cur_nice_jiffies);
+		}
+
+		if (dbs_data->governor == GOV_ONDEMAND) {
+			struct od_cpu_dbs_info_s *od_j_dbs_info =
+				dbs_data->get_cpu_dbs_info_s(cpu);
+
+			cur_iowait_time = get_cpu_iowait_time_us(j,
+					&cur_wall_time);
+			if (cur_iowait_time == -1ULL)
+				cur_iowait_time = 0;
+
+			iowait_time = (unsigned int) (cur_iowait_time -
+					od_j_dbs_info->prev_cpu_iowait);
+			od_j_dbs_info->prev_cpu_iowait = cur_iowait_time;
+
+			/*
+			 * For the purpose of ondemand, waiting for disk IO is
+			 * an indication that you're performance critical, and
+			 * not that the system is actually idle. So subtract the
+			 * iowait time from the cpu idle time.
+			 */
+			if (od_tuners->io_is_busy && idle_time >= iowait_time)
+				idle_time -= iowait_time;
+		}
+
+		if (unlikely(!wall_time || wall_time < idle_time))
+			continue;
+
+		load = 100 * (wall_time - idle_time) / wall_time;
+
+		if (dbs_data->governor == GOV_ONDEMAND) {
+			int freq_avg = __cpufreq_driver_getavg(policy, j);
+			if (freq_avg <= 0)
+				freq_avg = policy->cur;
+
+			load *= freq_avg;
+		}
+
+		if (load > max_load)
+			max_load = load;
+	}
+
+	dbs_data->gov_check_cpu(cpu, max_load);
+}
+EXPORT_SYMBOL_GPL(dbs_check_cpu);
+
+static inline void dbs_timer_init(struct dbs_data *dbs_data,
+		struct cpu_dbs_common_info *cdbs, unsigned int sampling_rate)
+{
+	int delay = delay_for_sampling_rate(sampling_rate);
+
+	INIT_DEFERRABLE_WORK(&cdbs->work, dbs_data->gov_dbs_timer);
+	schedule_delayed_work_on(cdbs->cpu, &cdbs->work, delay);
+}
+
+static inline void dbs_timer_exit(struct cpu_dbs_common_info *cdbs)
+{
+	cancel_delayed_work_sync(&cdbs->work);
+}
+
+int cpufreq_governor_dbs(struct dbs_data *dbs_data,
+		struct cpufreq_policy *policy, unsigned int event)
+{
+	struct od_cpu_dbs_info_s *od_dbs_info = NULL;
+	struct cs_cpu_dbs_info_s *cs_dbs_info = NULL;
+	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+	struct cpu_dbs_common_info *cpu_cdbs;
+	unsigned int *sampling_rate, latency, ignore_nice, j, cpu = policy->cpu;
+	int rc;
+
+	cpu_cdbs = dbs_data->get_cpu_cdbs(cpu);
+
+	if (dbs_data->governor == GOV_CONSERVATIVE) {
+		cs_dbs_info = dbs_data->get_cpu_dbs_info_s(cpu);
+		sampling_rate = &cs_tuners->sampling_rate;
+		ignore_nice = cs_tuners->ignore_nice;
+	} else {
+		od_dbs_info = dbs_data->get_cpu_dbs_info_s(cpu);
+		sampling_rate = &od_tuners->sampling_rate;
+		ignore_nice = od_tuners->ignore_nice;
+	}
+
+	switch (event) {
+	case CPUFREQ_GOV_START:
+		if ((!cpu_online(cpu)) || (!policy->cur))
+			return -EINVAL;
+
+		mutex_lock(&dbs_data->mutex);
+
+		dbs_data->enable++;
+		cpu_cdbs->cpu = cpu;
+		for_each_cpu(j, policy->cpus) {
+			struct cpu_dbs_common_info *j_cdbs;
+			j_cdbs = dbs_data->get_cpu_cdbs(j);
+
+			j_cdbs->cur_policy = policy;
+			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j,
+					&j_cdbs->prev_cpu_wall);
+			if (ignore_nice)
+				j_cdbs->prev_cpu_nice =
+					kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+		}
+
+		/*
+		 * Start the timerschedule work, when this governor is used for
+		 * first time
+		 */
+		if (dbs_data->enable != 1)
+			goto second_time;
+
+		rc = sysfs_create_group(cpufreq_global_kobject,
+				dbs_data->attr_group);
+		if (rc) {
+			mutex_unlock(&dbs_data->mutex);
+			return rc;
+		}
+
+		/* policy latency is in nS. Convert it to uS first */
+		latency = policy->cpuinfo.transition_latency / 1000;
+		if (latency == 0)
+			latency = 1;
+
+		/*
+		 * conservative does not implement micro like ondemand
+		 * governor, thus we are bound to jiffes/HZ
+		 */
+		if (dbs_data->governor == GOV_CONSERVATIVE) {
+			struct cs_ops *ops = dbs_data->gov_ops;
+
+			cpufreq_register_notifier(ops->notifier_block,
+					CPUFREQ_TRANSITION_NOTIFIER);
+
+			dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
+				jiffies_to_usecs(10);
+		} else {
+			struct od_ops *ops = dbs_data->gov_ops;
+
+			od_tuners->io_is_busy = ops->io_busy();
+		}
+
+		/* Bring kernel and HW constraints together */
+		dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate,
+				MIN_LATENCY_MULTIPLIER * latency);
+		*sampling_rate = max(dbs_data->min_sampling_rate, latency *
+				LATENCY_MULTIPLIER);
+
+second_time:
+		if (dbs_data->governor == GOV_CONSERVATIVE) {
+			cs_dbs_info->down_skip = 0;
+			cs_dbs_info->enable = 1;
+			cs_dbs_info->requested_freq = policy->cur;
+		} else {
+			struct od_ops *ops = dbs_data->gov_ops;
+			od_dbs_info->rate_mult = 1;
+			od_dbs_info->sample_type = OD_NORMAL_SAMPLE;
+			ops->powersave_bias_init_cpu(cpu);
+		}
+		mutex_unlock(&dbs_data->mutex);
+
+		mutex_init(&cpu_cdbs->timer_mutex);
+		dbs_timer_init(dbs_data, cpu_cdbs, *sampling_rate);
+		break;
+
+	case CPUFREQ_GOV_STOP:
+		if (dbs_data->governor == GOV_CONSERVATIVE)
+			cs_dbs_info->enable = 0;
+
+		dbs_timer_exit(cpu_cdbs);
+
+		mutex_lock(&dbs_data->mutex);
+		mutex_destroy(&cpu_cdbs->timer_mutex);
+		dbs_data->enable--;
+		if (!dbs_data->enable) {
+			struct cs_ops *ops = dbs_data->gov_ops;
+
+			sysfs_remove_group(cpufreq_global_kobject,
+					dbs_data->attr_group);
+			if (dbs_data->governor == GOV_CONSERVATIVE)
+				cpufreq_unregister_notifier(ops->notifier_block,
+						CPUFREQ_TRANSITION_NOTIFIER);
+		}
+		mutex_unlock(&dbs_data->mutex);
+
+		break;
+
+	case CPUFREQ_GOV_LIMITS:
+		mutex_lock(&cpu_cdbs->timer_mutex);
+		if (policy->max < cpu_cdbs->cur_policy->cur)
+			__cpufreq_driver_target(cpu_cdbs->cur_policy,
+					policy->max, CPUFREQ_RELATION_H);
+		else if (policy->min > cpu_cdbs->cur_policy->cur)
+			__cpufreq_driver_target(cpu_cdbs->cur_policy,
+					policy->min, CPUFREQ_RELATION_L);
+		dbs_check_cpu(dbs_data, cpu);
+		mutex_unlock(&cpu_cdbs->timer_mutex);
+		break;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cpufreq_governor_dbs);
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
new file mode 100644
index 000000000000..34e14adfc3f9
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -0,0 +1,177 @@
+/*
+ * drivers/cpufreq/cpufreq_governor.h
+ *
+ * Header file for CPUFreq governors common code
+ *
+ * Copyright	(C) 2001 Russell King
+ *		(C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
+ *		(C) 2003 Jun Nakajima <jun.nakajima@intel.com>
+ *		(C) 2009 Alexander Clouter <alex@digriz.org.uk>
+ *		(c) 2012 Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _CPUFREQ_GOVERNER_H
+#define _CPUFREQ_GOVERNER_H
+
+#include <asm/cputime.h>
+#include <linux/cpufreq.h>
+#include <linux/kobject.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/sysfs.h>
+
+/*
+ * The polling frequency depends on the capability of the processor. Default
+ * polling frequency is 1000 times the transition latency of the processor. The
+ * governor will work on any processor with transition latency <= 10mS, using
+ * appropriate sampling rate.
+ *
+ * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
+ * this governor will not work. All times here are in uS.
+ */
+#define MIN_SAMPLING_RATE_RATIO			(2)
+#define LATENCY_MULTIPLIER			(1000)
+#define MIN_LATENCY_MULTIPLIER			(100)
+#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)
+
+/* Ondemand Sampling types */
+enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
+
+/* Macro creating sysfs show routines */
+#define show_one(_gov, file_name, object)				\
+static ssize_t show_##file_name						\
+(struct kobject *kobj, struct attribute *attr, char *buf)		\
+{									\
+	return sprintf(buf, "%u\n", _gov##_tuners.object);		\
+}
+
+#define define_get_cpu_dbs_routines(_dbs_info)				\
+static struct cpu_dbs_common_info *get_cpu_cdbs(int cpu)		\
+{									\
+	return &per_cpu(_dbs_info, cpu).cdbs;				\
+}									\
+									\
+static void *get_cpu_dbs_info_s(int cpu)				\
+{									\
+	return &per_cpu(_dbs_info, cpu);				\
+}
+
+/*
+ * Abbreviations:
+ * dbs: used as a shortform for demand based switching It helps to keep variable
+ *	names smaller, simpler
+ * cdbs: common dbs
+ * on_*: On-demand governor
+ * cs_*: Conservative governor
+ */
+
+/* Per cpu structures */
+struct cpu_dbs_common_info {
+	int cpu;
+	cputime64_t prev_cpu_idle;
+	cputime64_t prev_cpu_wall;
+	cputime64_t prev_cpu_nice;
+	struct cpufreq_policy *cur_policy;
+	struct delayed_work work;
+	/*
+	 * percpu mutex that serializes governor limit change with gov_dbs_timer
+	 * invocation. We do not want gov_dbs_timer to run when user is changing
+	 * the governor or limits.
+	 */
+	struct mutex timer_mutex;
+};
+
+struct od_cpu_dbs_info_s {
+	struct cpu_dbs_common_info cdbs;
+	cputime64_t prev_cpu_iowait;
+	struct cpufreq_frequency_table *freq_table;
+	unsigned int freq_lo;
+	unsigned int freq_lo_jiffies;
+	unsigned int freq_hi_jiffies;
+	unsigned int rate_mult;
+	unsigned int sample_type:1;
+};
+
+struct cs_cpu_dbs_info_s {
+	struct cpu_dbs_common_info cdbs;
+	unsigned int down_skip;
+	unsigned int requested_freq;
+	unsigned int enable:1;
+};
+
+/* Governers sysfs tunables */
+struct od_dbs_tuners {
+	unsigned int ignore_nice;
+	unsigned int sampling_rate;
+	unsigned int sampling_down_factor;
+	unsigned int up_threshold;
+	unsigned int down_differential;
+	unsigned int powersave_bias;
+	unsigned int io_is_busy;
+};
+
+struct cs_dbs_tuners {
+	unsigned int ignore_nice;
+	unsigned int sampling_rate;
+	unsigned int sampling_down_factor;
+	unsigned int up_threshold;
+	unsigned int down_threshold;
+	unsigned int freq_step;
+};
+
+/* Per Governer data */
+struct dbs_data {
+	/* Common across governors */
+	#define GOV_ONDEMAND		0
+	#define GOV_CONSERVATIVE	1
+	int governor;
+	unsigned int min_sampling_rate;
+	unsigned int enable; /* number of CPUs using this policy */
+	struct attribute_group *attr_group;
+	void *tuners;
+
+	/* dbs_mutex protects dbs_enable in governor start/stop */
+	struct mutex mutex;
+
+	struct cpu_dbs_common_info *(*get_cpu_cdbs)(int cpu);
+	void *(*get_cpu_dbs_info_s)(int cpu);
+	void (*gov_dbs_timer)(struct work_struct *work);
+	void (*gov_check_cpu)(int cpu, unsigned int load);
+
+	/* Governor specific ops, see below */
+	void *gov_ops;
+};
+
+/* Governor specific ops, will be passed to dbs_data->gov_ops */
+struct od_ops {
+	int (*io_busy)(void);
+	void (*powersave_bias_init_cpu)(int cpu);
+	unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
+			unsigned int freq_next, unsigned int relation);
+	void (*freq_increase)(struct cpufreq_policy *p, unsigned int freq);
+};
+
+struct cs_ops {
+	struct notifier_block *notifier_block;
+};
+
+static inline int delay_for_sampling_rate(unsigned int sampling_rate)
+{
+	int delay = usecs_to_jiffies(sampling_rate);
+
+	/* We want all CPUs to do sampling nearly on same jiffy */
+	if (num_online_cpus() > 1)
+		delay -= jiffies % delay;
+
+	return delay;
+}
+
+cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall);
+void dbs_check_cpu(struct dbs_data *dbs_data, int cpu);
+int cpufreq_governor_dbs(struct dbs_data *dbs_data,
+		struct cpufreq_policy *policy, unsigned int event);
+#endif /* _CPUFREQ_GOVERNER_H */
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index d7f774bb49dd..bdaab9206303 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -10,24 +10,23 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/cpufreq.h>
-#include <linux/cpu.h>
-#include <linux/jiffies.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/kernel_stat.h>
+#include <linux/kobject.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/hrtimer.h>
+#include <linux/percpu-defs.h>
+#include <linux/sysfs.h>
 #include <linux/tick.h>
-#include <linux/ktime.h>
-#include <linux/sched.h>
+#include <linux/types.h>
 
-/*
- * dbs is used in this file as a shortform for demandbased switching
- * It helps to keep variable names smaller, simpler
- */
+#include "cpufreq_governor.h"
 
+/* On-demand governor macors */
 #define DEF_FREQUENCY_DOWN_DIFFERENTIAL		(10)
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
@@ -38,80 +37,10 @@
 #define MIN_FREQUENCY_UP_THRESHOLD		(11)
 #define MAX_FREQUENCY_UP_THRESHOLD		(100)
 
-/*
- * The polling frequency of this governor depends on the capability of
- * the processor. Default polling frequency is 1000 times the transition
- * latency of the processor. The governor will work on any processor with
- * transition latency <= 10mS, using appropriate sampling
- * rate.
- * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
- * this governor will not work.
- * All times here are in uS.
- */
-#define MIN_SAMPLING_RATE_RATIO			(2)
-
-static unsigned int min_sampling_rate;
-
-#define LATENCY_MULTIPLIER			(1000)
-#define MIN_LATENCY_MULTIPLIER			(100)
-#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)
-
-static void do_dbs_timer(struct work_struct *work);
-static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-				unsigned int event);
-
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
-static
-#endif
-struct cpufreq_governor cpufreq_gov_ondemand = {
-       .name                   = "ondemand",
-       .governor               = cpufreq_governor_dbs,
-       .max_transition_latency = TRANSITION_LATENCY_LIMIT,
-       .owner                  = THIS_MODULE,
-};
-
-/* Sampling types */
-enum {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE};
-
-struct cpu_dbs_info_s {
-	cputime64_t prev_cpu_idle;
-	cputime64_t prev_cpu_iowait;
-	cputime64_t prev_cpu_wall;
-	cputime64_t prev_cpu_nice;
-	struct cpufreq_policy *cur_policy;
-	struct delayed_work work;
-	struct cpufreq_frequency_table *freq_table;
-	unsigned int freq_lo;
-	unsigned int freq_lo_jiffies;
-	unsigned int freq_hi_jiffies;
-	unsigned int rate_mult;
-	int cpu;
-	unsigned int sample_type:1;
-	/*
-	 * percpu mutex that serializes governor limit change with
-	 * do_dbs_timer invocation. We do not want do_dbs_timer to run
-	 * when user is changing the governor or limits.
-	 */
-	struct mutex timer_mutex;
-};
-static DEFINE_PER_CPU(struct cpu_dbs_info_s, od_cpu_dbs_info);
-
-static unsigned int dbs_enable;	/* number of CPUs using this policy */
+static struct dbs_data od_dbs_data;
+static DEFINE_PER_CPU(struct od_cpu_dbs_info_s, od_cpu_dbs_info);
 
-/*
- * dbs_mutex protects dbs_enable in governor start/stop.
- */
-static DEFINE_MUTEX(dbs_mutex);
-
-static struct dbs_tuners {
-	unsigned int sampling_rate;
-	unsigned int up_threshold;
-	unsigned int down_differential;
-	unsigned int ignore_nice;
-	unsigned int sampling_down_factor;
-	unsigned int powersave_bias;
-	unsigned int io_is_busy;
-} dbs_tuners_ins = {
+static struct od_dbs_tuners od_tuners = {
 	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
 	.sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR,
 	.down_differential = DEF_FREQUENCY_DOWN_DIFFERENTIAL,
@@ -119,14 +48,35 @@ static struct dbs_tuners {
 	.powersave_bias = 0,
 };
 
-static inline cputime64_t get_cpu_iowait_time(unsigned int cpu, cputime64_t *wall)
+static void ondemand_powersave_bias_init_cpu(int cpu)
 {
-	u64 iowait_time = get_cpu_iowait_time_us(cpu, wall);
+	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 
-	if (iowait_time == -1ULL)
-		return 0;
+	dbs_info->freq_table = cpufreq_frequency_get_table(cpu);
+	dbs_info->freq_lo = 0;
+}
 
-	return iowait_time;
+/*
+ * Not all CPUs want IO time to be accounted as busy; this depends on how
+ * efficient idling at a higher frequency/voltage is.
+ * Pavel Machek says this is not so for various generations of AMD and old
+ * Intel systems.
+ * Mike Chan (androidlcom) calis this is also not true for ARM.
+ * Because of this, whitelist specific known (series) of CPUs by default, and
+ * leave all others up to the user.
+ */
+static int should_io_be_busy(void)
+{
+#if defined(CONFIG_X86)
+	/*
+	 * For Intel, Core 2 (model 15) andl later have an efficient idle.
+	 */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+			boot_cpu_data.x86 == 6 &&
+			boot_cpu_data.x86_model >= 15)
+		return 1;
+#endif
+	return 0;
 }
 
 /*
@@ -135,14 +85,13 @@ static inline cputime64_t get_cpu_iowait_time(unsigned int cpu, cputime64_t *wal
  * freq_lo, and freq_lo_jiffies in percpu area for averaging freqs.
  */
 static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
-					  unsigned int freq_next,
-					  unsigned int relation)
+		unsigned int freq_next, unsigned int relation)
 {
 	unsigned int freq_req, freq_reduc, freq_avg;
 	unsigned int freq_hi, freq_lo;
 	unsigned int index = 0;
 	unsigned int jiffies_total, jiffies_hi, jiffies_lo;
-	struct cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
+	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
 						   policy->cpu);
 
 	if (!dbs_info->freq_table) {
@@ -154,7 +103,7 @@ static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
 	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_next,
 			relation, &index);
 	freq_req = dbs_info->freq_table[index].frequency;
-	freq_reduc = freq_req * dbs_tuners_ins.powersave_bias / 1000;
+	freq_reduc = freq_req * od_tuners.powersave_bias / 1000;
 	freq_avg = freq_req - freq_reduc;
 
 	/* Find freq bounds for freq_avg in freq_table */
@@ -173,7 +122,7 @@ static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
 		dbs_info->freq_lo_jiffies = 0;
 		return freq_lo;
 	}
-	jiffies_total = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
+	jiffies_total = usecs_to_jiffies(od_tuners.sampling_rate);
 	jiffies_hi = (freq_avg - freq_lo) * jiffies_total;
 	jiffies_hi += ((freq_hi - freq_lo) / 2);
 	jiffies_hi /= (freq_hi - freq_lo);
@@ -184,13 +133,6 @@ static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
 	return freq_hi;
 }
 
-static void ondemand_powersave_bias_init_cpu(int cpu)
-{
-	struct cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-	dbs_info->freq_table = cpufreq_frequency_get_table(cpu);
-	dbs_info->freq_lo = 0;
-}
-
 static void ondemand_powersave_bias_init(void)
 {
 	int i;
@@ -199,53 +141,138 @@ static void ondemand_powersave_bias_init(void)
 	}
 }
 
-/************************** sysfs interface ************************/
+static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
+{
+	if (od_tuners.powersave_bias)
+		freq = powersave_bias_target(p, freq, CPUFREQ_RELATION_H);
+	else if (p->cur == p->max)
+		return;
 
-static ssize_t show_sampling_rate_min(struct kobject *kobj,
-				      struct attribute *attr, char *buf)
+	__cpufreq_driver_target(p, freq, od_tuners.powersave_bias ?
+			CPUFREQ_RELATION_L : CPUFREQ_RELATION_H);
+}
+
+/*
+ * Every sampling_rate, we check, if current idle time is less than 20%
+ * (default), then we try to increase frequency Every sampling_rate, we look for
+ * a the lowest frequency which can sustain the load while keeping idle time
+ * over 30%. If such a frequency exist, we try to decrease to this frequency.
+ *
+ * Any frequency increase takes it to the maximum frequency. Frequency reduction
+ * happens at minimum steps of 5% (default) of current frequency
+ */
+static void od_check_cpu(int cpu, unsigned int load_freq)
 {
-	return sprintf(buf, "%u\n", min_sampling_rate);
+	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
+	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
+
+	dbs_info->freq_lo = 0;
+
+	/* Check for frequency increase */
+	if (load_freq > od_tuners.up_threshold * policy->cur) {
+		/* If switching to max speed, apply sampling_down_factor */
+		if (policy->cur < policy->max)
+			dbs_info->rate_mult =
+				od_tuners.sampling_down_factor;
+		dbs_freq_increase(policy, policy->max);
+		return;
+	}
+
+	/* Check for frequency decrease */
+	/* if we cannot reduce the frequency anymore, break out early */
+	if (policy->cur == policy->min)
+		return;
+
+	/*
+	 * The optimal frequency is the frequency that is the lowest that can
+	 * support the current CPU usage without triggering the up policy. To be
+	 * safe, we focus 10 points under the threshold.
+	 */
+	if (load_freq < (od_tuners.up_threshold - od_tuners.down_differential) *
+			policy->cur) {
+		unsigned int freq_next;
+		freq_next = load_freq / (od_tuners.up_threshold -
+				od_tuners.down_differential);
+
+		/* No longer fully busy, reset rate_mult */
+		dbs_info->rate_mult = 1;
+
+		if (freq_next < policy->min)
+			freq_next = policy->min;
+
+		if (!od_tuners.powersave_bias) {
+			__cpufreq_driver_target(policy, freq_next,
+					CPUFREQ_RELATION_L);
+		} else {
+			int freq = powersave_bias_target(policy, freq_next,
+					CPUFREQ_RELATION_L);
+			__cpufreq_driver_target(policy, freq,
+					CPUFREQ_RELATION_L);
+		}
+	}
 }
 
-define_one_global_ro(sampling_rate_min);
+static void od_dbs_timer(struct work_struct *work)
+{
+	struct od_cpu_dbs_info_s *dbs_info =
+		container_of(work, struct od_cpu_dbs_info_s, cdbs.work.work);
+	unsigned int cpu = dbs_info->cdbs.cpu;
+	int delay, sample_type = dbs_info->sample_type;
 
-/* cpufreq_ondemand Governor Tunables */
-#define show_one(file_name, object)					\
-static ssize_t show_##file_name						\
-(struct kobject *kobj, struct attribute *attr, char *buf)              \
-{									\
-	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
+	mutex_lock(&dbs_info->cdbs.timer_mutex);
+
+	/* Common NORMAL_SAMPLE setup */
+	dbs_info->sample_type = OD_NORMAL_SAMPLE;
+	if (sample_type == OD_SUB_SAMPLE) {
+		delay = dbs_info->freq_lo_jiffies;
+		__cpufreq_driver_target(dbs_info->cdbs.cur_policy,
+			dbs_info->freq_lo, CPUFREQ_RELATION_H);
+	} else {
+		dbs_check_cpu(&od_dbs_data, cpu);
+		if (dbs_info->freq_lo) {
+			/* Setup timer for SUB_SAMPLE */
+			dbs_info->sample_type = OD_SUB_SAMPLE;
+			delay = dbs_info->freq_hi_jiffies;
+		} else {
+			delay = delay_for_sampling_rate(dbs_info->rate_mult);
+		}
+	}
+
+	schedule_delayed_work_on(cpu, &dbs_info->cdbs.work, delay);
+	mutex_unlock(&dbs_info->cdbs.timer_mutex);
+}
+
+/************************** sysfs interface ************************/
+
+static ssize_t show_sampling_rate_min(struct kobject *kobj,
+				      struct attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", od_dbs_data.min_sampling_rate);
 }
-show_one(sampling_rate, sampling_rate);
-show_one(io_is_busy, io_is_busy);
-show_one(up_threshold, up_threshold);
-show_one(sampling_down_factor, sampling_down_factor);
-show_one(ignore_nice_load, ignore_nice);
-show_one(powersave_bias, powersave_bias);
 
 /**
  * update_sampling_rate - update sampling rate effective immediately if needed.
  * @new_rate: new sampling rate
  *
  * If new rate is smaller than the old, simply updaing
- * dbs_tuners_int.sampling_rate might not be appropriate. For example,
- * if the original sampling_rate was 1 second and the requested new sampling
- * rate is 10 ms because the user needs immediate reaction from ondemand
- * governor, but not sure if higher frequency will be required or not,
- * then, the governor may change the sampling rate too late; up to 1 second
- * later. Thus, if we are reducing the sampling rate, we need to make the
- * new value effective immediately.
+ * dbs_tuners_int.sampling_rate might not be appropriate. For example, if the
+ * original sampling_rate was 1 second and the requested new sampling rate is 10
+ * ms because the user needs immediate reaction from ondemand governor, but not
+ * sure if higher frequency will be required or not, then, the governor may
+ * change the sampling rate too late; up to 1 second later. Thus, if we are
+ * reducing the sampling rate, we need to make the new value effective
+ * immediately.
  */
 static void update_sampling_rate(unsigned int new_rate)
 {
 	int cpu;
 
-	dbs_tuners_ins.sampling_rate = new_rate
-				     = max(new_rate, min_sampling_rate);
+	od_tuners.sampling_rate = new_rate = max(new_rate,
+			od_dbs_data.min_sampling_rate);
 
 	for_each_online_cpu(cpu) {
 		struct cpufreq_policy *policy;
-		struct cpu_dbs_info_s *dbs_info;
+		struct od_cpu_dbs_info_s *dbs_info;
 		unsigned long next_sampling, appointed_at;
 
 		policy = cpufreq_cpu_get(cpu);
@@ -254,28 +281,28 @@ static void update_sampling_rate(unsigned int new_rate)
 		dbs_info = &per_cpu(od_cpu_dbs_info, policy->cpu);
 		cpufreq_cpu_put(policy);
 
-		mutex_lock(&dbs_info->timer_mutex);
+		mutex_lock(&dbs_info->cdbs.timer_mutex);
 
-		if (!delayed_work_pending(&dbs_info->work)) {
-			mutex_unlock(&dbs_info->timer_mutex);
+		if (!delayed_work_pending(&dbs_info->cdbs.work)) {
+			mutex_unlock(&dbs_info->cdbs.timer_mutex);
 			continue;
 		}
 
-		next_sampling  = jiffies + usecs_to_jiffies(new_rate);
-		appointed_at = dbs_info->work.timer.expires;
-
+		next_sampling = jiffies + usecs_to_jiffies(new_rate);
+		appointed_at = dbs_info->cdbs.work.timer.expires;
 
 		if (time_before(next_sampling, appointed_at)) {
 
-			mutex_unlock(&dbs_info->timer_mutex);
-			cancel_delayed_work_sync(&dbs_info->work);
-			mutex_lock(&dbs_info->timer_mutex);
+			mutex_unlock(&dbs_info->cdbs.timer_mutex);
+			cancel_delayed_work_sync(&dbs_info->cdbs.work);
+			mutex_lock(&dbs_info->cdbs.timer_mutex);
 
-			schedule_delayed_work_on(dbs_info->cpu, &dbs_info->work,
-						 usecs_to_jiffies(new_rate));
+			schedule_delayed_work_on(dbs_info->cdbs.cpu,
+					&dbs_info->cdbs.work,
+					usecs_to_jiffies(new_rate));
 
 		}
-		mutex_unlock(&dbs_info->timer_mutex);
+		mutex_unlock(&dbs_info->cdbs.timer_mutex);
 	}
 }
 
@@ -300,7 +327,7 @@ static ssize_t store_io_is_busy(struct kobject *a, struct attribute *b,
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
-	dbs_tuners_ins.io_is_busy = !!input;
+	od_tuners.io_is_busy = !!input;
 	return count;
 }
 
@@ -315,7 +342,7 @@ static ssize_t store_up_threshold(struct kobject *a, struct attribute *b,
 			input < MIN_FREQUENCY_UP_THRESHOLD) {
 		return -EINVAL;
 	}
-	dbs_tuners_ins.up_threshold = input;
+	od_tuners.up_threshold = input;
 	return count;
 }
 
@@ -328,12 +355,12 @@ static ssize_t store_sampling_down_factor(struct kobject *a,
 
 	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
 		return -EINVAL;
-	dbs_tuners_ins.sampling_down_factor = input;
+	od_tuners.sampling_down_factor = input;
 
 	/* Reset down sampling multiplier in case it was active */
 	for_each_online_cpu(j) {
-		struct cpu_dbs_info_s *dbs_info;
-		dbs_info = &per_cpu(od_cpu_dbs_info, j);
+		struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
+				j);
 		dbs_info->rate_mult = 1;
 	}
 	return count;
@@ -354,19 +381,20 @@ static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
 	if (input > 1)
 		input = 1;
 
-	if (input == dbs_tuners_ins.ignore_nice) { /* nothing to do */
+	if (input == od_tuners.ignore_nice) { /* nothing to do */
 		return count;
 	}
-	dbs_tuners_ins.ignore_nice = input;
+	od_tuners.ignore_nice = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
 	for_each_online_cpu(j) {
-		struct cpu_dbs_info_s *dbs_info;
+		struct od_cpu_dbs_info_s *dbs_info;
 		dbs_info = &per_cpu(od_cpu_dbs_info, j);
-		dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
-						&dbs_info->prev_cpu_wall);
-		if (dbs_tuners_ins.ignore_nice)
-			dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
+						&dbs_info->cdbs.prev_cpu_wall);
+		if (od_tuners.ignore_nice)
+			dbs_info->cdbs.prev_cpu_nice =
+				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
 	}
 	return count;
@@ -385,17 +413,25 @@ static ssize_t store_powersave_bias(struct kobject *a, struct attribute *b,
 	if (input > 1000)
 		input = 1000;
 
-	dbs_tuners_ins.powersave_bias = input;
+	od_tuners.powersave_bias = input;
 	ondemand_powersave_bias_init();
 	return count;
 }
 
+show_one(od, sampling_rate, sampling_rate);
+show_one(od, io_is_busy, io_is_busy);
+show_one(od, up_threshold, up_threshold);
+show_one(od, sampling_down_factor, sampling_down_factor);
+show_one(od, ignore_nice_load, ignore_nice);
+show_one(od, powersave_bias, powersave_bias);
+
 define_one_global_rw(sampling_rate);
 define_one_global_rw(io_is_busy);
 define_one_global_rw(up_threshold);
 define_one_global_rw(sampling_down_factor);
 define_one_global_rw(ignore_nice_load);
 define_one_global_rw(powersave_bias);
+define_one_global_ro(sampling_rate_min);
 
 static struct attribute *dbs_attributes[] = {
 	&sampling_rate_min.attr,
@@ -408,354 +444,71 @@ static struct attribute *dbs_attributes[] = {
 	NULL
 };
 
-static struct attribute_group dbs_attr_group = {
+static struct attribute_group od_attr_group = {
 	.attrs = dbs_attributes,
 	.name = "ondemand",
 };
 
 /************************** sysfs end ************************/
 
-static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
-{
-	if (dbs_tuners_ins.powersave_bias)
-		freq = powersave_bias_target(p, freq, CPUFREQ_RELATION_H);
-	else if (p->cur == p->max)
-		return;
-
-	__cpufreq_driver_target(p, freq, dbs_tuners_ins.powersave_bias ?
-			CPUFREQ_RELATION_L : CPUFREQ_RELATION_H);
-}
-
-static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
-{
-	unsigned int max_load_freq;
-
-	struct cpufreq_policy *policy;
-	unsigned int j;
-
-	this_dbs_info->freq_lo = 0;
-	policy = this_dbs_info->cur_policy;
-
-	/*
-	 * Every sampling_rate, we check, if current idle time is less
-	 * than 20% (default), then we try to increase frequency
-	 * Every sampling_rate, we look for a the lowest
-	 * frequency which can sustain the load while keeping idle time over
-	 * 30%. If such a frequency exist, we try to decrease to this frequency.
-	 *
-	 * Any frequency increase takes it to the maximum frequency.
-	 * Frequency reduction happens at minimum steps of
-	 * 5% (default) of current frequency
-	 */
-
-	/* Get Absolute Load - in terms of freq */
-	max_load_freq = 0;
-
-	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_info_s *j_dbs_info;
-		cputime64_t cur_wall_time, cur_idle_time, cur_iowait_time;
-		unsigned int idle_time, wall_time, iowait_time;
-		unsigned int load, load_freq;
-		int freq_avg;
-
-		j_dbs_info = &per_cpu(od_cpu_dbs_info, j);
-
-		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
-		cur_iowait_time = get_cpu_iowait_time(j, &cur_wall_time);
-
-		wall_time = (unsigned int)
-			(cur_wall_time - j_dbs_info->prev_cpu_wall);
-		j_dbs_info->prev_cpu_wall = cur_wall_time;
-
-		idle_time = (unsigned int)
-			(cur_idle_time - j_dbs_info->prev_cpu_idle);
-		j_dbs_info->prev_cpu_idle = cur_idle_time;
-
-		iowait_time = (unsigned int)
-			(cur_iowait_time - j_dbs_info->prev_cpu_iowait);
-		j_dbs_info->prev_cpu_iowait = cur_iowait_time;
-
-		if (dbs_tuners_ins.ignore_nice) {
-			u64 cur_nice;
-			unsigned long cur_nice_jiffies;
-
-			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
-					 j_dbs_info->prev_cpu_nice;
-			/*
-			 * Assumption: nice time between sampling periods will
-			 * be less than 2^32 jiffies for 32 bit sys
-			 */
-			cur_nice_jiffies = (unsigned long)
-					cputime64_to_jiffies64(cur_nice);
-
-			j_dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-			idle_time += jiffies_to_usecs(cur_nice_jiffies);
-		}
-
-		/*
-		 * For the purpose of ondemand, waiting for disk IO is an
-		 * indication that you're performance critical, and not that
-		 * the system is actually idle. So subtract the iowait time
-		 * from the cpu idle time.
-		 */
-
-		if (dbs_tuners_ins.io_is_busy && idle_time >= iowait_time)
-			idle_time -= iowait_time;
+define_get_cpu_dbs_routines(od_cpu_dbs_info);
 
-		if (unlikely(!wall_time || wall_time < idle_time))
-			continue;
-
-		load = 100 * (wall_time - idle_time) / wall_time;
-
-		freq_avg = __cpufreq_driver_getavg(policy, j);
-		if (freq_avg <= 0)
-			freq_avg = policy->cur;
-
-		load_freq = load * freq_avg;
-		if (load_freq > max_load_freq)
-			max_load_freq = load_freq;
-	}
-
-	/* Check for frequency increase */
-	if (max_load_freq > dbs_tuners_ins.up_threshold * policy->cur) {
-		/* If switching to max speed, apply sampling_down_factor */
-		if (policy->cur < policy->max)
-			this_dbs_info->rate_mult =
-				dbs_tuners_ins.sampling_down_factor;
-		dbs_freq_increase(policy, policy->max);
-		return;
-	}
-
-	/* Check for frequency decrease */
-	/* if we cannot reduce the frequency anymore, break out early */
-	if (policy->cur == policy->min)
-		return;
-
-	/*
-	 * The optimal frequency is the frequency that is the lowest that
-	 * can support the current CPU usage without triggering the up
-	 * policy. To be safe, we focus 10 points under the threshold.
-	 */
-	if (max_load_freq <
-	    (dbs_tuners_ins.up_threshold - dbs_tuners_ins.down_differential) *
-	     policy->cur) {
-		unsigned int freq_next;
-		freq_next = max_load_freq /
-				(dbs_tuners_ins.up_threshold -
-				 dbs_tuners_ins.down_differential);
-
-		/* No longer fully busy, reset rate_mult */
-		this_dbs_info->rate_mult = 1;
-
-		if (freq_next < policy->min)
-			freq_next = policy->min;
-
-		if (!dbs_tuners_ins.powersave_bias) {
-			__cpufreq_driver_target(policy, freq_next,
-					CPUFREQ_RELATION_L);
-		} else {
-			int freq = powersave_bias_target(policy, freq_next,
-					CPUFREQ_RELATION_L);
-			__cpufreq_driver_target(policy, freq,
-				CPUFREQ_RELATION_L);
-		}
-	}
-}
-
-static void do_dbs_timer(struct work_struct *work)
-{
-	struct cpu_dbs_info_s *dbs_info =
-		container_of(work, struct cpu_dbs_info_s, work.work);
-	unsigned int cpu = dbs_info->cpu;
-	int sample_type = dbs_info->sample_type;
-
-	int delay;
-
-	mutex_lock(&dbs_info->timer_mutex);
-
-	/* Common NORMAL_SAMPLE setup */
-	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
-	if (!dbs_tuners_ins.powersave_bias ||
-	    sample_type == DBS_NORMAL_SAMPLE) {
-		dbs_check_cpu(dbs_info);
-		if (dbs_info->freq_lo) {
-			/* Setup timer for SUB_SAMPLE */
-			dbs_info->sample_type = DBS_SUB_SAMPLE;
-			delay = dbs_info->freq_hi_jiffies;
-		} else {
-			/* We want all CPUs to do sampling nearly on
-			 * same jiffy
-			 */
-			delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate
-				* dbs_info->rate_mult);
-
-			if (num_online_cpus() > 1)
-				delay -= jiffies % delay;
-		}
-	} else {
-		__cpufreq_driver_target(dbs_info->cur_policy,
-			dbs_info->freq_lo, CPUFREQ_RELATION_H);
-		delay = dbs_info->freq_lo_jiffies;
-	}
-	schedule_delayed_work_on(cpu, &dbs_info->work, delay);
-	mutex_unlock(&dbs_info->timer_mutex);
-}
-
-static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info)
-{
-	/* We want all CPUs to do sampling nearly on same jiffy */
-	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
-
-	if (num_online_cpus() > 1)
-		delay -= jiffies % delay;
+static struct od_ops od_ops = {
+	.io_busy = should_io_be_busy,
+	.powersave_bias_init_cpu = ondemand_powersave_bias_init_cpu,
+	.powersave_bias_target = powersave_bias_target,
+	.freq_increase = dbs_freq_increase,
+};
 
-	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
-	INIT_DEFERRABLE_WORK(&dbs_info->work, do_dbs_timer);
-	schedule_delayed_work_on(dbs_info->cpu, &dbs_info->work, delay);
-}
+static struct dbs_data od_dbs_data = {
+	.governor = GOV_ONDEMAND,
+	.attr_group = &od_attr_group,
+	.tuners = &od_tuners,
+	.get_cpu_cdbs = get_cpu_cdbs,
+	.get_cpu_dbs_info_s = get_cpu_dbs_info_s,
+	.gov_dbs_timer = od_dbs_timer,
+	.gov_check_cpu = od_check_cpu,
+	.gov_ops = &od_ops,
+};
 
-static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
+static int od_cpufreq_governor_dbs(struct cpufreq_policy *policy,
+		unsigned int event)
 {
-	cancel_delayed_work_sync(&dbs_info->work);
+	return cpufreq_governor_dbs(&od_dbs_data, policy, event);
 }
 
-/*
- * Not all CPUs want IO time to be accounted as busy; this dependson how
- * efficient idling at a higher frequency/voltage is.
- * Pavel Machek says this is not so for various generations of AMD and old
- * Intel systems.
- * Mike Chan (androidlcom) calis this is also not true for ARM.
- * Because of this, whitelist specific known (series) of CPUs by default, and
- * leave all others up to the user.
- */
-static int should_io_be_busy(void)
-{
-#if defined(CONFIG_X86)
-	/*
-	 * For Intel, Core 2 (model 15) andl later have an efficient idle.
-	 */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_data.x86 == 6 &&
-	    boot_cpu_data.x86_model >= 15)
-		return 1;
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
+static
 #endif
-	return 0;
-}
-
-static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-				   unsigned int event)
-{
-	unsigned int cpu = policy->cpu;
-	struct cpu_dbs_info_s *this_dbs_info;
-	unsigned int j;
-	int rc;
-
-	this_dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-
-	switch (event) {
-	case CPUFREQ_GOV_START:
-		if ((!cpu_online(cpu)) || (!policy->cur))
-			return -EINVAL;
-
-		mutex_lock(&dbs_mutex);
-
-		dbs_enable++;
-		for_each_cpu(j, policy->cpus) {
-			struct cpu_dbs_info_s *j_dbs_info;
-			j_dbs_info = &per_cpu(od_cpu_dbs_info, j);
-			j_dbs_info->cur_policy = policy;
-
-			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
-						&j_dbs_info->prev_cpu_wall);
-			if (dbs_tuners_ins.ignore_nice)
-				j_dbs_info->prev_cpu_nice =
-						kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-		}
-		this_dbs_info->cpu = cpu;
-		this_dbs_info->rate_mult = 1;
-		ondemand_powersave_bias_init_cpu(cpu);
-		/*
-		 * Start the timerschedule work, when this governor
-		 * is used for first time
-		 */
-		if (dbs_enable == 1) {
-			unsigned int latency;
-
-			rc = sysfs_create_group(cpufreq_global_kobject,
-						&dbs_attr_group);
-			if (rc) {
-				mutex_unlock(&dbs_mutex);
-				return rc;
-			}
-
-			/* policy latency is in nS. Convert it to uS first */
-			latency = policy->cpuinfo.transition_latency / 1000;
-			if (latency == 0)
-				latency = 1;
-			/* Bring kernel and HW constraints together */
-			min_sampling_rate = max(min_sampling_rate,
-					MIN_LATENCY_MULTIPLIER * latency);
-			dbs_tuners_ins.sampling_rate =
-				max(min_sampling_rate,
-				    latency * LATENCY_MULTIPLIER);
-			dbs_tuners_ins.io_is_busy = should_io_be_busy();
-		}
-		mutex_unlock(&dbs_mutex);
-
-		mutex_init(&this_dbs_info->timer_mutex);
-		dbs_timer_init(this_dbs_info);
-		break;
-
-	case CPUFREQ_GOV_STOP:
-		dbs_timer_exit(this_dbs_info);
-
-		mutex_lock(&dbs_mutex);
-		mutex_destroy(&this_dbs_info->timer_mutex);
-		dbs_enable--;
-		mutex_unlock(&dbs_mutex);
-		if (!dbs_enable)
-			sysfs_remove_group(cpufreq_global_kobject,
-					   &dbs_attr_group);
-
-		break;
-
-	case CPUFREQ_GOV_LIMITS:
-		mutex_lock(&this_dbs_info->timer_mutex);
-		if (policy->max < this_dbs_info->cur_policy->cur)
-			__cpufreq_driver_target(this_dbs_info->cur_policy,
-				policy->max, CPUFREQ_RELATION_H);
-		else if (policy->min > this_dbs_info->cur_policy->cur)
-			__cpufreq_driver_target(this_dbs_info->cur_policy,
-				policy->min, CPUFREQ_RELATION_L);
-		dbs_check_cpu(this_dbs_info);
-		mutex_unlock(&this_dbs_info->timer_mutex);
-		break;
-	}
-	return 0;
-}
+struct cpufreq_governor cpufreq_gov_ondemand = {
+	.name			= "ondemand",
+	.governor		= od_cpufreq_governor_dbs,
+	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
+	.owner			= THIS_MODULE,
+};
 
 static int __init cpufreq_gov_dbs_init(void)
 {
 	u64 idle_time;
 	int cpu = get_cpu();
 
+	mutex_init(&od_dbs_data.mutex);
 	idle_time = get_cpu_idle_time_us(cpu, NULL);
 	put_cpu();
 	if (idle_time != -1ULL) {
 		/* Idle micro accounting is supported. Use finer thresholds */
-		dbs_tuners_ins.up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
-		dbs_tuners_ins.down_differential =
-					MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
+		od_tuners.up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
+		od_tuners.down_differential = MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
 		/*
 		 * In nohz/micro accounting case we set the minimum frequency
 		 * not depending on HZ, but fixed (very low). The deferred
 		 * timer might skip some samples if idle/sleeping as needed.
 		*/
-		min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
+		od_dbs_data.min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
 	} else {
 		/* For correct statistics, we need 10 ticks for each measure */
-		min_sampling_rate =
-			MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10);
+		od_dbs_data.min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
+			jiffies_to_usecs(10);
 	}
 
 	return cpufreq_register_governor(&cpufreq_gov_ondemand);
@@ -766,7 +519,6 @@ static void __exit cpufreq_gov_dbs_exit(void)
 	cpufreq_unregister_governor(&cpufreq_gov_ondemand);
 }
 
-
 MODULE_AUTHOR("Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>");
 MODULE_AUTHOR("Alexey Starikovskiy <alexey.y.starikovskiy@intel.com>");
 MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for "
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index d03c21993052..a55b88eaf96a 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -407,10 +407,4 @@ void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
 				      unsigned int cpu);
 
 void cpufreq_frequency_table_put_attr(unsigned int cpu);
-
-/*********************************************************************
- *                     Governor Helpers				     *
- *********************************************************************/
-cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall);
-
 #endif /* _LINUX_CPUFREQ_H */
-- 
cgit v1.2.3-55-g7522


From 69a37beabf1f0a6705c08e879bdd5d82ff6486c4 Mon Sep 17 00:00:00 2001
From: Youquan Song
Date: Fri, 26 Oct 2012 12:26:41 +0200
Subject: cpuidle: Quickly notice prediction failure for repeat mode

The prediction for future is difficult and when the cpuidle governor prediction
fails and govenor possibly choose the shallower C-state than it should. How to
quickly notice and find the failure becomes important for power saving.

cpuidle menu governor has a method to predict the repeat pattern if there are 8
C-states residency which are continuous and the same or very close, so it will
predict the next C-states residency will keep same residency time.

There is a real case that turbostat utility (tools/power/x86/turbostat)
at kernel 3.3 or early. turbostat utility will read 10 registers one by one at
Sandybridge, so it will generate 10 IPIs to wake up idle CPUs. So cpuidle menu
 governor will predict it is repeat mode and there is another IPI wake up idle
 CPU soon, so it keeps idle CPU stay at C1 state even though CPU is totally
idle. However, in the turbostat, following 10 registers reading is sleep 5
seconds by default, so the idle CPU will keep at C1 for a long time though it is
 idle until break event occurs.
In a idle Sandybridge system, run "./turbostat -v", we will notice that deep
C-state dangles between "70% ~ 99%". After patched the kernel, we will notice
deep C-state stays at >99.98%.

In the patch, a timer is added when menu governor detects a repeat mode and
choose a shallow C-state. The timer is set to a time out value that greater
than predicted time, and we conclude repeat mode prediction failure if timer is
triggered. When repeat mode happens as expected, the timer is not triggered
and CPU waken up from C-states and it will cancel the timer initiatively.
When repeat mode does not happen, the timer will be time out and menu governor
will quickly notice that the repeat mode prediction fails and then re-evaluates
deeper C-states possibility.

Below is another case which will clearly show the patch much benefit:

#include <stdlib.h>
#include <stdio.h>
#include <unistd.h>
#include <signal.h>
#include <sys/time.h>
#include <time.h>
#include <pthread.h>

volatile int * shutdown;
volatile long * count;
int delay = 20;
int loop = 8;

void usage(void)
{
	fprintf(stderr,
		"Usage: idle_predict [options]\n"
		"  --help	-h  Print this help\n"
		"  --thread	-n  Thread number\n"
		"  --loop     	-l  Loop times in shallow Cstate\n"
		"  --delay	-t  Sleep time (uS)in shallow Cstate\n");
}

void *simple_loop() {
	int idle_num = 1;
	while (!(*shutdown)) {
		*count = *count + 1;

		if (idle_num % loop)
			usleep(delay);
		else {
			/* sleep 1 second */
			usleep(1000000);
			idle_num = 0;
		}
		idle_num++;
	}

}

static void sighand(int sig)
{
	*shutdown = 1;
}

int main(int argc, char *argv[])
{
	sigset_t sigset;
	int signum = SIGALRM;
	int i, c, er = 0, thread_num = 8;
	pthread_t pt[1024];

	static char optstr[] = "n:l:t:h:";

	while ((c = getopt(argc, argv, optstr)) != EOF)
		switch (c) {
			case 'n':
				thread_num = atoi(optarg);
				break;
			case 'l':
				loop = atoi(optarg);
				break;
			case 't':
				delay = atoi(optarg);
				break;
			case 'h':
			default:
				usage();
				exit(1);
		}

	printf("thread=%d,loop=%d,delay=%d\n",thread_num,loop,delay);
	count = malloc(sizeof(long));
	shutdown = malloc(sizeof(int));
	*count = 0;
	*shutdown = 0;

	sigemptyset(&sigset);
	sigaddset(&sigset, signum);
	sigprocmask (SIG_BLOCK, &sigset, NULL);
	signal(SIGINT, sighand);
	signal(SIGTERM, sighand);

	for(i = 0; i < thread_num ; i++)
		pthread_create(&pt[i], NULL, simple_loop, NULL);

	for (i = 0; i < thread_num; i++)
		pthread_join(pt[i], NULL);

	exit(0);
}

Get powertop V2 from git://github.com/fenrus75/powertop, build powertop.
After build the above test application, then run it.
Test plaform can be Intel Sandybridge or other recent platforms.
#./idle_predict -l 10 &
#./powertop

We will find that deep C-state will dangle between 40%~100% and much time spent
on C1 state. It is because menu governor wrongly predict that repeat mode
is kept, so it will choose the C1 shallow C-state even though it has chance to
sleep 1 second in deep C-state.

While after patched the kernel, we find that deep C-state will keep >99.6%.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Youquan Song <youquan.song@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpuidle/governors/menu.c | 75 +++++++++++++++++++++++++++++++++++++---
 include/linux/tick.h             |  6 ++++
 kernel/time/tick-sched.c         |  4 +++
 3 files changed, 80 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 5b1f2c372c1f..37c0ff6c805c 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -28,6 +28,13 @@
 #define MAX_INTERESTING 50000
 #define STDDEV_THRESH 400
 
+/* 60 * 60 > STDDEV_THRESH * INTERVALS = 400 * 8 */
+#define MAX_DEVIATION 60
+
+static DEFINE_PER_CPU(struct hrtimer, menu_hrtimer);
+static DEFINE_PER_CPU(int, hrtimer_status);
+/* menu hrtimer mode */
+enum {MENU_HRTIMER_STOP, MENU_HRTIMER_REPEAT};
 
 /*
  * Concepts and ideas behind the menu governor
@@ -191,17 +198,42 @@ static u64 div_round64(u64 dividend, u32 divisor)
 	return div_u64(dividend + (divisor / 2), divisor);
 }
 
+/* Cancel the hrtimer if it is not triggered yet */
+void menu_hrtimer_cancel(void)
+{
+	int cpu = smp_processor_id();
+	struct hrtimer *hrtmr = &per_cpu(menu_hrtimer, cpu);
+
+	/* The timer is still not time out*/
+	if (per_cpu(hrtimer_status, cpu)) {
+		hrtimer_cancel(hrtmr);
+		per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_STOP;
+	}
+}
+EXPORT_SYMBOL_GPL(menu_hrtimer_cancel);
+
+/* Call back for hrtimer is triggered */
+static enum hrtimer_restart menu_hrtimer_notify(struct hrtimer *hrtimer)
+{
+	int cpu = smp_processor_id();
+
+	per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_STOP;
+
+	return HRTIMER_NORESTART;
+}
+
 /*
  * Try detecting repeating patterns by keeping track of the last 8
  * intervals, and checking if the standard deviation of that set
  * of points is below a threshold. If it is... then use the
  * average of these 8 points as the estimated value.
  */
-static void detect_repeating_patterns(struct menu_device *data)
+static int detect_repeating_patterns(struct menu_device *data)
 {
 	int i;
 	uint64_t avg = 0;
 	uint64_t stddev = 0; /* contains the square of the std deviation */
+	int ret = 0;
 
 	/* first calculate average and standard deviation of the past */
 	for (i = 0; i < INTERVALS; i++)
@@ -210,7 +242,7 @@ static void detect_repeating_patterns(struct menu_device *data)
 
 	/* if the avg is beyond the known next tick, it's worthless */
 	if (avg > data->expected_us)
-		return;
+		return 0;
 
 	for (i = 0; i < INTERVALS; i++)
 		stddev += (data->intervals[i] - avg) *
@@ -223,8 +255,12 @@ static void detect_repeating_patterns(struct menu_device *data)
 	 * repeating pattern and predict we keep doing this.
 	 */
 
-	if (avg && stddev < STDDEV_THRESH)
+	if (avg && stddev < STDDEV_THRESH) {
 		data->predicted_us = avg;
+		ret = 1;
+	}
+
+	return ret;
 }
 
 /**
@@ -240,6 +276,9 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	int i;
 	int multiplier;
 	struct timespec t;
+	int repeat = 0, low_predicted = 0;
+	int cpu = smp_processor_id();
+	struct hrtimer *hrtmr = &per_cpu(menu_hrtimer, cpu);
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
@@ -274,7 +313,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	data->predicted_us = div_round64(data->expected_us * data->correction_factor[data->bucket],
 					 RESOLUTION * DECAY);
 
-	detect_repeating_patterns(data);
+	repeat = detect_repeating_patterns(data);
 
 	/*
 	 * We want to default to C1 (hlt), not to busy polling
@@ -295,8 +334,10 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 		if (s->disabled || su->disable)
 			continue;
-		if (s->target_residency > data->predicted_us)
+		if (s->target_residency > data->predicted_us) {
+			low_predicted = 1;
 			continue;
+		}
 		if (s->exit_latency > latency_req)
 			continue;
 		if (s->exit_latency * multiplier > data->predicted_us)
@@ -309,6 +350,27 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		}
 	}
 
+	/* not deepest C-state chosen for low predicted residency */
+	if (low_predicted) {
+		unsigned int timer_us = 0;
+
+		/*
+		 * Set a timer to detect whether this sleep is much
+		 * longer than repeat mode predicted.  If the timer
+		 * triggers, the code will evaluate whether to put
+		 * the CPU into a deeper C-state.
+		 * The timer is cancelled on CPU wakeup.
+		 */
+		timer_us = 2 * (data->predicted_us + MAX_DEVIATION);
+
+		if (repeat && (4 * timer_us < data->expected_us)) {
+			hrtimer_start(hrtmr, ns_to_ktime(1000 * timer_us),
+				HRTIMER_MODE_REL_PINNED);
+			/* In repeat case, menu hrtimer is started */
+			per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_REPEAT;
+		}
+	}
+
 	return data->last_state_idx;
 }
 
@@ -399,6 +461,9 @@ static int menu_enable_device(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev)
 {
 	struct menu_device *data = &per_cpu(menu_devices, dev->cpu);
+	struct hrtimer *t = &per_cpu(menu_hrtimer, dev->cpu);
+	hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	t->function = menu_hrtimer_notify;
 
 	memset(data, 0, sizeof(struct menu_device));
 
diff --git a/include/linux/tick.h b/include/linux/tick.h
index f37fceb69b73..1a6567b48492 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -142,4 +142,10 @@ static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 # endif /* !NO_HZ */
 
+# ifdef CONFIG_CPU_IDLE_GOV_MENU
+extern void menu_hrtimer_cancel(void);
+# else
+static inline void menu_hrtimer_cancel(void) {}
+# endif /* CONFIG_CPU_IDLE_GOV_MENU */
+
 #endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a40260885265..6f337068dc4c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -526,6 +526,8 @@ void tick_nohz_irq_exit(void)
 	if (!ts->inidle)
 		return;
 
+	/* Cancel the timer because CPU already waken up from the C-states*/
+	menu_hrtimer_cancel();
 	__tick_nohz_idle_enter(ts);
 }
 
@@ -621,6 +623,8 @@ void tick_nohz_idle_exit(void)
 
 	ts->inidle = 0;
 
+	/* Cancel the timer because CPU already waken up from the C-states*/
+	menu_hrtimer_cancel();
 	if (ts->idle_active || ts->tick_stopped)
 		now = ktime_get();
 
-- 
cgit v1.2.3-55-g7522


From 349631e0e411fefa2fed7e0a30b97704562dbd6b Mon Sep 17 00:00:00 2001
From: Daniel Lezcano
Date: Wed, 31 Oct 2012 01:05:16 +0100
Subject: cpuidle / sysfs: move structure declaration into the sysfs.c file

The structure cpuidle_state_kobj is not used anywhere except
in the sysfs.c file. The definition of this structure is not
needed in the cpuidle header file. This patch moves it to the
sysfs.c file in order to encapsulate the code a bit more.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpuidle/sysfs.c | 7 +++++++
 include/linux/cpuidle.h | 7 -------
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index ed87399bb02b..f15c1e56e16f 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -297,6 +297,13 @@ static struct attribute *cpuidle_state_default_attrs[] = {
 	NULL
 };
 
+struct cpuidle_state_kobj {
+	struct cpuidle_state *state;
+	struct cpuidle_state_usage *state_usage;
+	struct completion kobj_unregister;
+	struct kobject kobj;
+};
+
 #define kobj_to_state_obj(k) container_of(k, struct cpuidle_state_kobj, kobj)
 #define kobj_to_state(k) (kobj_to_state_obj(k)->state)
 #define kobj_to_state_usage(k) (kobj_to_state_obj(k)->state_usage)
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 279b1eaa8b73..7daf0e3b93bd 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -82,13 +82,6 @@ cpuidle_set_statedata(struct cpuidle_state_usage *st_usage, void *data)
 	st_usage->driver_data = data;
 }
 
-struct cpuidle_state_kobj {
-	struct cpuidle_state *state;
-	struct cpuidle_state_usage *state_usage;
-	struct completion kobj_unregister;
-	struct kobject kobj;
-};
-
 struct cpuidle_device {
 	unsigned int		registered:1;
 	unsigned int		enabled:1;
-- 
cgit v1.2.3-55-g7522


From 42f67f2acab2b7179c0d1ab234869e391448dfa6 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano
Date: Wed, 31 Oct 2012 16:44:45 +0000
Subject: cpuidle: move driver's refcount to cpuidle

We want to support different cpuidle drivers co-existing together.
In this case we should move the refcount to the cpuidle_driver
structure to handle several drivers at a time.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpuidle/driver.c | 13 ++++++++-----
 include/linux/cpuidle.h  |  1 +
 2 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 87db3877fead..39ba8e181e96 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -16,7 +16,6 @@
 
 static struct cpuidle_driver *cpuidle_curr_driver;
 DEFINE_SPINLOCK(cpuidle_driver_lock);
-int cpuidle_driver_refcount;
 
 static void set_power_states(struct cpuidle_driver *drv)
 {
@@ -61,6 +60,8 @@ int cpuidle_register_driver(struct cpuidle_driver *drv)
 	if (!drv->power_specified)
 		set_power_states(drv);
 
+	drv->refcnt = 0;
+
 	cpuidle_curr_driver = drv;
 
 	spin_unlock(&cpuidle_driver_lock);
@@ -92,7 +93,7 @@ void cpuidle_unregister_driver(struct cpuidle_driver *drv)
 
 	spin_lock(&cpuidle_driver_lock);
 
-	if (!WARN_ON(cpuidle_driver_refcount > 0))
+	if (!WARN_ON(drv->refcnt > 0))
 		cpuidle_curr_driver = NULL;
 
 	spin_unlock(&cpuidle_driver_lock);
@@ -106,7 +107,7 @@ struct cpuidle_driver *cpuidle_driver_ref(void)
 	spin_lock(&cpuidle_driver_lock);
 
 	drv = cpuidle_curr_driver;
-	cpuidle_driver_refcount++;
+	drv->refcnt++;
 
 	spin_unlock(&cpuidle_driver_lock);
 	return drv;
@@ -114,10 +115,12 @@ struct cpuidle_driver *cpuidle_driver_ref(void)
 
 void cpuidle_driver_unref(void)
 {
+	struct cpuidle_driver *drv = cpuidle_curr_driver;
+
 	spin_lock(&cpuidle_driver_lock);
 
-	if (!WARN_ON(cpuidle_driver_refcount <= 0))
-		cpuidle_driver_refcount--;
+	if (drv && !WARN_ON(drv->refcnt <= 0))
+		drv->refcnt--;
 
 	spin_unlock(&cpuidle_driver_lock);
 }
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 7daf0e3b93bd..d08e1afa4919 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -124,6 +124,7 @@ static inline int cpuidle_get_last_residency(struct cpuidle_device *dev)
 struct cpuidle_driver {
 	const char		*name;
 	struct module 		*owner;
+	int                     refcnt;
 
 	unsigned int		power_specified:1;
 	/* set to 1 to use the core cpuidle time keeping (for all states). */
-- 
cgit v1.2.3-55-g7522


From bf4d1b5ddb78f86078ac6ae0415802d5f0c68f92 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano
Date: Wed, 31 Oct 2012 16:44:48 +0000
Subject: cpuidle: support multiple drivers

With the tegra3 and the big.LITTLE [1] new architectures, several cpus
with different characteristics (latencies and states) can co-exists on the
system.

The cpuidle framework has the limitation of handling only identical cpus.

This patch removes this limitation by introducing the multiple driver support
for cpuidle.

This option is configurable at compile time and should be enabled for the
architectures mentioned above. So there is no impact for the other platforms
if the option is disabled. The option defaults to 'n'. Note the multiple drivers
support is also compatible with the existing drivers, even if just one driver is
needed, all the cpu will be tied to this driver using an extra small chunk of
processor memory.

The multiple driver support use a per-cpu driver pointer instead of a global
variable and the accessor to this variable are done from a cpu context.

In order to keep the compatibility with the existing drivers, the function
'cpuidle_register_driver' and 'cpuidle_unregister_driver' will register
the specified driver for all the cpus.

The semantic for the output of /sys/devices/system/cpu/cpuidle/current_driver
remains the same except the driver name will be related to the current cpu.

The /sys/devices/system/cpu/cpu[0-9]/cpuidle/driver/name files are added
allowing to read the per cpu driver name.

[1] http://lwn.net/Articles/481055/

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpuidle/Kconfig   |   9 +++
 drivers/cpuidle/cpuidle.c |  36 ++++++----
 drivers/cpuidle/cpuidle.h |   4 +-
 drivers/cpuidle/driver.c  | 166 ++++++++++++++++++++++++++++++++++++++-----
 drivers/cpuidle/sysfs.c   | 174 ++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/cpuidle.h   |   7 +-
 6 files changed, 356 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index a76b689e553b..234ae651b38f 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -9,6 +9,15 @@ config CPU_IDLE
 
 	  If you're using an ACPI-enabled platform, you should say Y here.
 
+config CPU_IDLE_MULTIPLE_DRIVERS
+        bool "Support multiple cpuidle drivers"
+        depends on CPU_IDLE
+        default n
+        help
+         Allows the cpuidle framework to use different drivers for each CPU.
+         This is useful if you have a system with different CPU latencies and
+         states. If unsure say N.
+
 config CPU_IDLE_GOV_LADDER
 	bool
 	depends on CPU_IDLE
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index ce4cac706dd1..711dd83fd3ba 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -68,7 +68,7 @@ static cpuidle_enter_t cpuidle_enter_ops;
 int cpuidle_play_dead(void)
 {
 	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
-	struct cpuidle_driver *drv = cpuidle_get_driver();
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 	int i, dead_state = -1;
 	int power_usage = -1;
 
@@ -128,7 +128,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 int cpuidle_idle_call(void)
 {
 	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
-	struct cpuidle_driver *drv = cpuidle_get_driver();
+	struct cpuidle_driver *drv;
 	int next_state, entered_state;
 
 	if (off)
@@ -141,6 +141,8 @@ int cpuidle_idle_call(void)
 	if (!dev || !dev->enabled)
 		return -EBUSY;
 
+	drv = cpuidle_get_cpu_driver(dev);
+
 	/* ask the governor for the next state */
 	next_state = cpuidle_curr_governor->select(drv, dev);
 	if (need_resched()) {
@@ -312,15 +314,19 @@ static void poll_idle_init(struct cpuidle_driver *drv) {}
 int cpuidle_enable_device(struct cpuidle_device *dev)
 {
 	int ret, i;
-	struct cpuidle_driver *drv = cpuidle_get_driver();
+	struct cpuidle_driver *drv;
 
 	if (!dev)
 		return -EINVAL;
 
 	if (dev->enabled)
 		return 0;
+
+	drv = cpuidle_get_cpu_driver(dev);
+
 	if (!drv || !cpuidle_curr_governor)
 		return -EIO;
+
 	if (!dev->state_count)
 		dev->state_count = drv->state_count;
 
@@ -335,7 +341,8 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
 
 	poll_idle_init(drv);
 
-	if ((ret = cpuidle_add_state_sysfs(dev)))
+	ret = cpuidle_add_device_sysfs(dev);
+	if (ret)
 		return ret;
 
 	if (cpuidle_curr_governor->enable &&
@@ -356,7 +363,7 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
 	return 0;
 
 fail_sysfs:
-	cpuidle_remove_state_sysfs(dev);
+	cpuidle_remove_device_sysfs(dev);
 
 	return ret;
 }
@@ -372,17 +379,20 @@ EXPORT_SYMBOL_GPL(cpuidle_enable_device);
  */
 void cpuidle_disable_device(struct cpuidle_device *dev)
 {
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+
 	if (!dev || !dev->enabled)
 		return;
-	if (!cpuidle_get_driver() || !cpuidle_curr_governor)
+
+	if (!drv || !cpuidle_curr_governor)
 		return;
 
 	dev->enabled = 0;
 
 	if (cpuidle_curr_governor->disable)
-		cpuidle_curr_governor->disable(cpuidle_get_driver(), dev);
+		cpuidle_curr_governor->disable(drv, dev);
 
-	cpuidle_remove_state_sysfs(dev);
+	cpuidle_remove_device_sysfs(dev);
 	enabled_devices--;
 }
 
@@ -398,9 +408,9 @@ EXPORT_SYMBOL_GPL(cpuidle_disable_device);
 static int __cpuidle_register_device(struct cpuidle_device *dev)
 {
 	int ret;
-	struct cpuidle_driver *cpuidle_driver = cpuidle_get_driver();
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 
-	if (!try_module_get(cpuidle_driver->owner))
+	if (!try_module_get(drv->owner))
 		return -EINVAL;
 
 	per_cpu(cpuidle_devices, dev->cpu) = dev;
@@ -421,7 +431,7 @@ err_coupled:
 err_sysfs:
 	list_del(&dev->device_list);
 	per_cpu(cpuidle_devices, dev->cpu) = NULL;
-	module_put(cpuidle_driver->owner);
+	module_put(drv->owner);
 	return ret;
 }
 
@@ -460,7 +470,7 @@ EXPORT_SYMBOL_GPL(cpuidle_register_device);
  */
 void cpuidle_unregister_device(struct cpuidle_device *dev)
 {
-	struct cpuidle_driver *cpuidle_driver = cpuidle_get_driver();
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 
 	if (dev->registered == 0)
 		return;
@@ -477,7 +487,7 @@ void cpuidle_unregister_device(struct cpuidle_device *dev)
 
 	cpuidle_resume_and_unlock();
 
-	module_put(cpuidle_driver->owner);
+	module_put(drv->owner);
 }
 
 EXPORT_SYMBOL_GPL(cpuidle_unregister_device);
diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h
index f6b0923c2253..ee97e9672ecf 100644
--- a/drivers/cpuidle/cpuidle.h
+++ b/drivers/cpuidle/cpuidle.h
@@ -28,8 +28,8 @@ struct device;
 
 extern int cpuidle_add_interface(struct device *dev);
 extern void cpuidle_remove_interface(struct device *dev);
-extern int cpuidle_add_state_sysfs(struct cpuidle_device *device);
-extern void cpuidle_remove_state_sysfs(struct cpuidle_device *device);
+extern int cpuidle_add_device_sysfs(struct cpuidle_device *device);
+extern void cpuidle_remove_device_sysfs(struct cpuidle_device *device);
 extern int cpuidle_add_sysfs(struct cpuidle_device *dev);
 extern void cpuidle_remove_sysfs(struct cpuidle_device *dev);
 
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 8246662f594a..3af841fb397a 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -14,9 +14,11 @@
 
 #include "cpuidle.h"
 
-static struct cpuidle_driver *cpuidle_curr_driver;
 DEFINE_SPINLOCK(cpuidle_driver_lock);
 
+static void __cpuidle_set_cpu_driver(struct cpuidle_driver *drv, int cpu);
+static struct cpuidle_driver * __cpuidle_get_cpu_driver(int cpu);
+
 static void set_power_states(struct cpuidle_driver *drv)
 {
 	int i;
@@ -47,12 +49,7 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv)
 		set_power_states(drv);
 }
 
-static void cpuidle_set_driver(struct cpuidle_driver *drv)
-{
-	cpuidle_curr_driver = drv;
-}
-
-static int __cpuidle_register_driver(struct cpuidle_driver *drv)
+static int __cpuidle_register_driver(struct cpuidle_driver *drv, int cpu)
 {
 	if (!drv || !drv->state_count)
 		return -EINVAL;
@@ -60,23 +57,84 @@ static int __cpuidle_register_driver(struct cpuidle_driver *drv)
 	if (cpuidle_disabled())
 		return -ENODEV;
 
-	if (cpuidle_get_driver())
+	if (__cpuidle_get_cpu_driver(cpu))
 		return -EBUSY;
 
 	__cpuidle_driver_init(drv);
 
-	cpuidle_set_driver(drv);
+	__cpuidle_set_cpu_driver(drv, cpu);
 
 	return 0;
 }
 
-static void __cpuidle_unregister_driver(struct cpuidle_driver *drv)
+static void __cpuidle_unregister_driver(struct cpuidle_driver *drv, int cpu)
 {
-	if (drv != cpuidle_get_driver())
+	if (drv != __cpuidle_get_cpu_driver(cpu))
 		return;
 
 	if (!WARN_ON(drv->refcnt > 0))
-		cpuidle_set_driver(NULL);
+		__cpuidle_set_cpu_driver(NULL, cpu);
+}
+
+#ifdef CONFIG_CPU_IDLE_MULTIPLE_DRIVERS
+
+static DEFINE_PER_CPU(struct cpuidle_driver *, cpuidle_drivers);
+
+static void __cpuidle_set_cpu_driver(struct cpuidle_driver *drv, int cpu)
+{
+	per_cpu(cpuidle_drivers, cpu) = drv;
+}
+
+static struct cpuidle_driver *__cpuidle_get_cpu_driver(int cpu)
+{
+	return per_cpu(cpuidle_drivers, cpu);
+}
+
+static void __cpuidle_unregister_all_cpu_driver(struct cpuidle_driver *drv)
+{
+	int cpu;
+	for_each_present_cpu(cpu)
+		__cpuidle_unregister_driver(drv, cpu);
+}
+
+static int __cpuidle_register_all_cpu_driver(struct cpuidle_driver *drv)
+{
+	int ret = 0;
+	int i, cpu;
+
+	for_each_present_cpu(cpu) {
+		ret = __cpuidle_register_driver(drv, cpu);
+		if (ret)
+			break;
+	}
+
+	if (ret)
+		for_each_present_cpu(i) {
+			if (i == cpu)
+				break;
+			__cpuidle_unregister_driver(drv, i);
+		}
+
+
+	return ret;
+}
+
+int cpuidle_register_cpu_driver(struct cpuidle_driver *drv, int cpu)
+{
+	int ret;
+
+	spin_lock(&cpuidle_driver_lock);
+	ret = __cpuidle_register_driver(drv, cpu);
+	spin_unlock(&cpuidle_driver_lock);
+
+	return ret;
+}
+
+void cpuidle_unregister_cpu_driver(struct cpuidle_driver *drv, int cpu)
+{
+	spin_lock(&cpuidle_driver_lock);
+	__cpuidle_unregister_driver(drv, cpu);
+	spin_unlock(&cpuidle_driver_lock);
 }
 
 /**
@@ -88,7 +146,7 @@ int cpuidle_register_driver(struct cpuidle_driver *drv)
 	int ret;
 
 	spin_lock(&cpuidle_driver_lock);
-	ret = __cpuidle_register_driver(drv);
+	ret = __cpuidle_register_all_cpu_driver(drv);
 	spin_unlock(&cpuidle_driver_lock);
 
 	return ret;
@@ -96,13 +154,48 @@ int cpuidle_register_driver(struct cpuidle_driver *drv)
 EXPORT_SYMBOL_GPL(cpuidle_register_driver);
 
 /**
- * cpuidle_get_driver - return the current driver
+ * cpuidle_unregister_driver - unregisters a driver
+ * @drv: the driver
  */
-struct cpuidle_driver *cpuidle_get_driver(void)
+void cpuidle_unregister_driver(struct cpuidle_driver *drv)
+{
+	spin_lock(&cpuidle_driver_lock);
+	__cpuidle_unregister_all_cpu_driver(drv);
+	spin_unlock(&cpuidle_driver_lock);
+}
+EXPORT_SYMBOL_GPL(cpuidle_unregister_driver);
+
+#else
+
+static struct cpuidle_driver *cpuidle_curr_driver;
+
+static inline void __cpuidle_set_cpu_driver(struct cpuidle_driver *drv, int cpu)
+{
+	cpuidle_curr_driver = drv;
+}
+
+static inline struct cpuidle_driver *__cpuidle_get_cpu_driver(int cpu)
 {
 	return cpuidle_curr_driver;
 }
-EXPORT_SYMBOL_GPL(cpuidle_get_driver);
+
+/**
+ * cpuidle_register_driver - registers a driver
+ * @drv: the driver
+ */
+int cpuidle_register_driver(struct cpuidle_driver *drv)
+{
+	int ret, cpu;
+
+	cpu = get_cpu();
+	spin_lock(&cpuidle_driver_lock);
+	ret = __cpuidle_register_driver(drv, cpu);
+	spin_unlock(&cpuidle_driver_lock);
+	put_cpu();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpuidle_register_driver);
 
 /**
  * cpuidle_unregister_driver - unregisters a driver
@@ -110,11 +203,50 @@ EXPORT_SYMBOL_GPL(cpuidle_get_driver);
  */
 void cpuidle_unregister_driver(struct cpuidle_driver *drv)
 {
+	int cpu;
+
+	cpu = get_cpu();
 	spin_lock(&cpuidle_driver_lock);
-	__cpuidle_unregister_driver(drv);
+	__cpuidle_unregister_driver(drv, cpu);
 	spin_unlock(&cpuidle_driver_lock);
+	put_cpu();
 }
 EXPORT_SYMBOL_GPL(cpuidle_unregister_driver);
+#endif
+
+/**
+ * cpuidle_get_driver - return the current driver
+ */
+struct cpuidle_driver *cpuidle_get_driver(void)
+{
+	struct cpuidle_driver *drv;
+	int cpu;
+
+	cpu = get_cpu();
+	drv = __cpuidle_get_cpu_driver(cpu);
+	put_cpu();
+
+	return drv;
+}
+EXPORT_SYMBOL_GPL(cpuidle_get_driver);
+
+/**
+ * cpuidle_get_cpu_driver - return the driver tied with a cpu
+ */
+struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev)
+{
+	struct cpuidle_driver *drv;
+
+	if (!dev)
+		return NULL;
+
+	spin_lock(&cpuidle_driver_lock);
+	drv = __cpuidle_get_cpu_driver(dev->cpu);
+	spin_unlock(&cpuidle_driver_lock);
+
+	return drv;
+}
+EXPORT_SYMBOL_GPL(cpuidle_get_cpu_driver);
 
 struct cpuidle_driver *cpuidle_driver_ref(void)
 {
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 49b1f4bcc1b3..340942946106 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -364,17 +364,17 @@ static inline void cpuidle_free_state_kobj(struct cpuidle_device *device, int i)
 }
 
 /**
- * cpuidle_add_driver_sysfs - adds driver-specific sysfs attributes
+ * cpuidle_add_state_sysfs - adds cpuidle states sysfs attributes
  * @device: the target device
  */
-int cpuidle_add_state_sysfs(struct cpuidle_device *device)
+static int cpuidle_add_state_sysfs(struct cpuidle_device *device)
 {
 	int i, ret = -ENOMEM;
 	struct cpuidle_state_kobj *kobj;
-	struct cpuidle_driver *drv = cpuidle_get_driver();
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device);
 
 	/* state statistics */
-	for (i = 0; i < device->state_count; i++) {
+	for (i = 0; i < drv->state_count; i++) {
 		kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL);
 		if (!kobj)
 			goto error_state;
@@ -401,10 +401,10 @@ error_state:
 }
 
 /**
- * cpuidle_remove_driver_sysfs - removes driver-specific sysfs attributes
+ * cpuidle_remove_driver_sysfs - removes the cpuidle states sysfs attributes
  * @device: the target device
  */
-void cpuidle_remove_state_sysfs(struct cpuidle_device *device)
+static void cpuidle_remove_state_sysfs(struct cpuidle_device *device)
 {
 	int i;
 
@@ -412,6 +412,168 @@ void cpuidle_remove_state_sysfs(struct cpuidle_device *device)
 		cpuidle_free_state_kobj(device, i);
 }
 
+#ifdef CONFIG_CPU_IDLE_MULTIPLE_DRIVERS
+#define kobj_to_driver_kobj(k) container_of(k, struct cpuidle_driver_kobj, kobj)
+#define attr_to_driver_attr(a) container_of(a, struct cpuidle_driver_attr, attr)
+
+#define define_one_driver_ro(_name, show)                       \
+	static struct cpuidle_driver_attr attr_driver_##_name = \
+		__ATTR(_name, 0644, show, NULL)
+
+struct cpuidle_driver_kobj {
+	struct cpuidle_driver *drv;
+	struct completion kobj_unregister;
+	struct kobject kobj;
+};
+
+struct cpuidle_driver_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct cpuidle_driver *, char *);
+	ssize_t (*store)(struct cpuidle_driver *, const char *, size_t);
+};
+
+static ssize_t show_driver_name(struct cpuidle_driver *drv, char *buf)
+{
+	ssize_t ret;
+
+	spin_lock(&cpuidle_driver_lock);
+	ret = sprintf(buf, "%s\n", drv ? drv->name : "none");
+	spin_unlock(&cpuidle_driver_lock);
+
+	return ret;
+}
+
+static void cpuidle_driver_sysfs_release(struct kobject *kobj)
+{
+	struct cpuidle_driver_kobj *driver_kobj = kobj_to_driver_kobj(kobj);
+	complete(&driver_kobj->kobj_unregister);
+}
+
+static ssize_t cpuidle_driver_show(struct kobject *kobj, struct attribute * attr,
+				   char * buf)
+{
+	int ret = -EIO;
+	struct cpuidle_driver_kobj *driver_kobj = kobj_to_driver_kobj(kobj);
+	struct cpuidle_driver_attr *dattr = attr_to_driver_attr(attr);
+
+	if (dattr->show)
+		ret = dattr->show(driver_kobj->drv, buf);
+
+	return ret;
+}
+
+static ssize_t cpuidle_driver_store(struct kobject *kobj, struct attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret = -EIO;
+	struct cpuidle_driver_kobj *driver_kobj = kobj_to_driver_kobj(kobj);
+	struct cpuidle_driver_attr *dattr = attr_to_driver_attr(attr);
+
+	if (dattr->store)
+		ret = dattr->store(driver_kobj->drv, buf, size);
+
+	return ret;
+}
+
+define_one_driver_ro(name, show_driver_name);
+
+static const struct sysfs_ops cpuidle_driver_sysfs_ops = {
+	.show = cpuidle_driver_show,
+	.store = cpuidle_driver_store,
+};
+
+static struct attribute *cpuidle_driver_default_attrs[] = {
+	&attr_driver_name.attr,
+	NULL
+};
+
+static struct kobj_type ktype_driver_cpuidle = {
+	.sysfs_ops = &cpuidle_driver_sysfs_ops,
+	.default_attrs = cpuidle_driver_default_attrs,
+	.release = cpuidle_driver_sysfs_release,
+};
+
+/**
+ * cpuidle_add_driver_sysfs - adds the driver name sysfs attribute
+ * @device: the target device
+ */
+static int cpuidle_add_driver_sysfs(struct cpuidle_device *dev)
+{
+	struct cpuidle_driver_kobj *kdrv;
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	int ret;
+
+	kdrv = kzalloc(sizeof(*kdrv), GFP_KERNEL);
+	if (!kdrv)
+		return -ENOMEM;
+
+	kdrv->drv = drv;
+	init_completion(&kdrv->kobj_unregister);
+
+	ret = kobject_init_and_add(&kdrv->kobj, &ktype_driver_cpuidle,
+				   &dev->kobj, "driver");
+	if (ret) {
+		kfree(kdrv);
+		return ret;
+	}
+
+	kobject_uevent(&kdrv->kobj, KOBJ_ADD);
+	dev->kobj_driver = kdrv;
+
+	return ret;
+}
+
+/**
+ * cpuidle_remove_driver_sysfs - removes the driver name sysfs attribute
+ * @device: the target device
+ */
+static void cpuidle_remove_driver_sysfs(struct cpuidle_device *dev)
+{
+	struct cpuidle_driver_kobj *kdrv = dev->kobj_driver;
+	kobject_put(&kdrv->kobj);
+	wait_for_completion(&kdrv->kobj_unregister);
+	kfree(kdrv);
+}
+#else
+static inline int cpuidle_add_driver_sysfs(struct cpuidle_device *dev)
+{
+	return 0;
+}
+
+static inline void cpuidle_remove_driver_sysfs(struct cpuidle_device *dev)
+{
+	;
+}
+#endif
+
+/**
+ * cpuidle_add_device_sysfs - adds device specific sysfs attributes
+ * @device: the target device
+ */
+int cpuidle_add_device_sysfs(struct cpuidle_device *device)
+{
+	int ret;
+
+	ret = cpuidle_add_state_sysfs(device);
+	if (ret)
+		return ret;
+
+	ret = cpuidle_add_driver_sysfs(device);
+	if (ret)
+		cpuidle_remove_state_sysfs(device);
+	return ret;
+}
+
+/**
+ * cpuidle_remove_device_sysfs : removes device specific sysfs attributes
+ * @device : the target device
+ */
+void cpuidle_remove_device_sysfs(struct cpuidle_device *device)
+{
+	cpuidle_remove_driver_sysfs(device);
+	cpuidle_remove_state_sysfs(device);
+}
+
 /**
  * cpuidle_add_sysfs - creates a sysfs instance for the target device
  * @dev: the target device
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index d08e1afa4919..3711b34dc4f9 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -91,7 +91,7 @@ struct cpuidle_device {
 	int			state_count;
 	struct cpuidle_state_usage	states_usage[CPUIDLE_STATE_MAX];
 	struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX];
-
+	struct cpuidle_driver_kobj *kobj_driver;
 	struct list_head 	device_list;
 	struct kobject		kobj;
 	struct completion	kobj_unregister;
@@ -157,6 +157,10 @@ extern int cpuidle_wrap_enter(struct cpuidle_device *dev,
 					struct cpuidle_driver *drv, int index));
 extern int cpuidle_play_dead(void);
 
+extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev);
+extern int cpuidle_register_cpu_driver(struct cpuidle_driver *drv, int cpu);
+extern void cpuidle_unregister_cpu_driver(struct cpuidle_driver *drv, int cpu);
+
 #else
 static inline void disable_cpuidle(void) { }
 static inline int cpuidle_idle_call(void) { return -ENODEV; }
@@ -183,7 +187,6 @@ static inline int cpuidle_wrap_enter(struct cpuidle_device *dev,
 					struct cpuidle_driver *drv, int index))
 { return -ENODEV; }
 static inline int cpuidle_play_dead(void) {return -ENODEV; }
-
 #endif
 
 #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
-- 
cgit v1.2.3-55-g7522


From 7e6fdd4bad033fa2d73716377b184fa975b0d985 Mon Sep 17 00:00:00 2001
From: Rajagopal Venkat
Date: Fri, 26 Oct 2012 01:50:09 +0200
Subject: PM / devfreq: Core updates to support devices which can idle

Prepare devfreq core framework to support devices which
can idle. When device idleness is detected perhaps through
runtime-pm, need some mechanism to suspend devfreq load
monitoring and resume back when device is online. Present
code continues monitoring unless device is removed from
devfreq core.

This patch introduces following design changes,

 - use per device work instead of global work to monitor device
   load. This enables suspend/resume of device devfreq and
   reduces monitoring code complexity.
 - decouple delayed work based load monitoring logic from core
   by introducing helpers functions to be used by governors. This
   provides flexibility for governors either to use delayed work
   based monitoring functions or to implement their own mechanism.
 - devfreq core interacts with governors via events to perform
   specific actions. These events include start/stop devfreq.
   This sets ground for adding suspend/resume events.

The devfreq apis are not modified and are kept intact.

Signed-off-by: Rajagopal Venkat <rajagopal.venkat@linaro.org>
Acked-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/ABI/testing/sysfs-class-devfreq |   8 -
 drivers/devfreq/devfreq.c                     | 442 +++++++++++---------------
 drivers/devfreq/governor.h                    |  11 +
 drivers/devfreq/governor_performance.c        |  16 +-
 drivers/devfreq/governor_powersave.c          |  16 +-
 drivers/devfreq/governor_simpleondemand.c     |  24 ++
 drivers/devfreq/governor_userspace.c          |  23 +-
 include/linux/devfreq.h                       |  34 +-
 8 files changed, 278 insertions(+), 296 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
index 23d78b5aab11..89283b1b0240 100644
--- a/Documentation/ABI/testing/sysfs-class-devfreq
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -21,14 +21,6 @@ Description:
 		The /sys/class/devfreq/.../cur_freq shows the current
 		frequency of the corresponding devfreq object.
 
-What:		/sys/class/devfreq/.../central_polling
-Date:		September 2011
-Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
-Description:
-		The /sys/class/devfreq/.../central_polling shows whether
-		the devfreq ojbect is using devfreq-provided central
-		polling mechanism or not.
-
 What:		/sys/class/devfreq/.../polling_interval
 Date:		September 2011
 Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index b146d76f04cf..1aaf1aeb1f1d 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -30,17 +30,11 @@
 struct class *devfreq_class;
 
 /*
- * devfreq_work periodically monitors every registered device.
- * The minimum polling interval is one jiffy. The polling interval is
- * determined by the minimum polling period among all polling devfreq
- * devices. The resolution of polling interval is one jiffy.
+ * devfreq core provides delayed work based load monitoring helper
+ * functions. Governors can use these or can implement their own
+ * monitoring mechanism.
  */
-static bool polling;
 static struct workqueue_struct *devfreq_wq;
-static struct delayed_work devfreq_work;
-
-/* wait removing if this is to be removed */
-static struct devfreq *wait_remove_device;
 
 /* The list of all device-devfreq */
 static LIST_HEAD(devfreq_list);
@@ -72,6 +66,8 @@ static struct devfreq *find_device_devfreq(struct device *dev)
 	return ERR_PTR(-ENODEV);
 }
 
+/* Load monitoring helper functions for governors use */
+
 /**
  * update_devfreq() - Reevaluate the device and configure frequency.
  * @devfreq:	the devfreq instance.
@@ -120,6 +116,152 @@ int update_devfreq(struct devfreq *devfreq)
 	return err;
 }
 
+/**
+ * devfreq_monitor() - Periodically poll devfreq objects.
+ * @work:	the work struct used to run devfreq_monitor periodically.
+ *
+ */
+static void devfreq_monitor(struct work_struct *work)
+{
+	int err;
+	struct devfreq *devfreq = container_of(work,
+					struct devfreq, work.work);
+
+	mutex_lock(&devfreq->lock);
+	err = update_devfreq(devfreq);
+	if (err)
+		dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err);
+
+	queue_delayed_work(devfreq_wq, &devfreq->work,
+				msecs_to_jiffies(devfreq->profile->polling_ms));
+	mutex_unlock(&devfreq->lock);
+}
+
+/**
+ * devfreq_monitor_start() - Start load monitoring of devfreq instance
+ * @devfreq:	the devfreq instance.
+ *
+ * Helper function for starting devfreq device load monitoing. By
+ * default delayed work based monitoring is supported. Function
+ * to be called from governor in response to DEVFREQ_GOV_START
+ * event when device is added to devfreq framework.
+ */
+void devfreq_monitor_start(struct devfreq *devfreq)
+{
+	INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
+	if (devfreq->profile->polling_ms)
+		queue_delayed_work(devfreq_wq, &devfreq->work,
+			msecs_to_jiffies(devfreq->profile->polling_ms));
+}
+
+/**
+ * devfreq_monitor_stop() - Stop load monitoring of a devfreq instance
+ * @devfreq:	the devfreq instance.
+ *
+ * Helper function to stop devfreq device load monitoing. Function
+ * to be called from governor in response to DEVFREQ_GOV_STOP
+ * event when device is removed from devfreq framework.
+ */
+void devfreq_monitor_stop(struct devfreq *devfreq)
+{
+	cancel_delayed_work_sync(&devfreq->work);
+}
+
+/**
+ * devfreq_monitor_suspend() - Suspend load monitoring of a devfreq instance
+ * @devfreq:	the devfreq instance.
+ *
+ * Helper function to suspend devfreq device load monitoing. Function
+ * to be called from governor in response to DEVFREQ_GOV_SUSPEND
+ * event or when polling interval is set to zero.
+ *
+ * Note: Though this function is same as devfreq_monitor_stop(),
+ * intentionally kept separate to provide hooks for collecting
+ * transition statistics.
+ */
+void devfreq_monitor_suspend(struct devfreq *devfreq)
+{
+	mutex_lock(&devfreq->lock);
+	if (devfreq->stop_polling) {
+		mutex_unlock(&devfreq->lock);
+		return;
+	}
+
+	devfreq->stop_polling = true;
+	mutex_unlock(&devfreq->lock);
+	cancel_delayed_work_sync(&devfreq->work);
+}
+
+/**
+ * devfreq_monitor_resume() - Resume load monitoring of a devfreq instance
+ * @devfreq:    the devfreq instance.
+ *
+ * Helper function to resume devfreq device load monitoing. Function
+ * to be called from governor in response to DEVFREQ_GOV_RESUME
+ * event or when polling interval is set to non-zero.
+ */
+void devfreq_monitor_resume(struct devfreq *devfreq)
+{
+	mutex_lock(&devfreq->lock);
+	if (!devfreq->stop_polling)
+		goto out;
+
+	if (!delayed_work_pending(&devfreq->work) &&
+			devfreq->profile->polling_ms)
+		queue_delayed_work(devfreq_wq, &devfreq->work,
+			msecs_to_jiffies(devfreq->profile->polling_ms));
+	devfreq->stop_polling = false;
+
+out:
+	mutex_unlock(&devfreq->lock);
+}
+
+/**
+ * devfreq_interval_update() - Update device devfreq monitoring interval
+ * @devfreq:    the devfreq instance.
+ * @delay:      new polling interval to be set.
+ *
+ * Helper function to set new load monitoring polling interval. Function
+ * to be called from governor in response to DEVFREQ_GOV_INTERVAL event.
+ */
+void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
+{
+	unsigned int cur_delay = devfreq->profile->polling_ms;
+	unsigned int new_delay = *delay;
+
+	mutex_lock(&devfreq->lock);
+	devfreq->profile->polling_ms = new_delay;
+
+	if (devfreq->stop_polling)
+		goto out;
+
+	/* if new delay is zero, stop polling */
+	if (!new_delay) {
+		mutex_unlock(&devfreq->lock);
+		cancel_delayed_work_sync(&devfreq->work);
+		return;
+	}
+
+	/* if current delay is zero, start polling with new delay */
+	if (!cur_delay) {
+		queue_delayed_work(devfreq_wq, &devfreq->work,
+			msecs_to_jiffies(devfreq->profile->polling_ms));
+		goto out;
+	}
+
+	/* if current delay is greater than new delay, restart polling */
+	if (cur_delay > new_delay) {
+		mutex_unlock(&devfreq->lock);
+		cancel_delayed_work_sync(&devfreq->work);
+		mutex_lock(&devfreq->lock);
+		if (!devfreq->stop_polling)
+			queue_delayed_work(devfreq_wq, &devfreq->work,
+			      msecs_to_jiffies(devfreq->profile->polling_ms));
+	}
+out:
+	mutex_unlock(&devfreq->lock);
+}
+
 /**
  * devfreq_notifier_call() - Notify that the device frequency requirements
  *			   has been changed out of devfreq framework.
@@ -143,59 +285,32 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type,
 }
 
 /**
- * _remove_devfreq() - Remove devfreq from the device.
+ * _remove_devfreq() - Remove devfreq from the list and release its resources.
  * @devfreq:	the devfreq struct
  * @skip:	skip calling device_unregister().
- *
- * Note that the caller should lock devfreq->lock before calling
- * this. _remove_devfreq() will unlock it and free devfreq
- * internally. devfreq_list_lock should be locked by the caller
- * as well (not relased at return)
- *
- * Lock usage:
- * devfreq->lock: locked before call.
- *		  unlocked at return (and freed)
- * devfreq_list_lock: locked before call.
- *		      kept locked at return.
- *		      if devfreq is centrally polled.
- *
- * Freed memory:
- * devfreq
  */
 static void _remove_devfreq(struct devfreq *devfreq, bool skip)
 {
-	if (!mutex_is_locked(&devfreq->lock)) {
-		WARN(true, "devfreq->lock must be locked by the caller.\n");
-		return;
-	}
-	if (!devfreq->governor->no_central_polling &&
-	    !mutex_is_locked(&devfreq_list_lock)) {
-		WARN(true, "devfreq_list_lock must be locked by the caller.\n");
+	mutex_lock(&devfreq_list_lock);
+	if (IS_ERR(find_device_devfreq(devfreq->dev.parent))) {
+		mutex_unlock(&devfreq_list_lock);
+		dev_warn(&devfreq->dev, "releasing devfreq which doesn't exist\n");
 		return;
 	}
+	list_del(&devfreq->node);
+	mutex_unlock(&devfreq_list_lock);
 
-	if (devfreq->being_removed)
-		return;
-
-	devfreq->being_removed = true;
+	devfreq->governor->event_handler(devfreq, DEVFREQ_GOV_STOP, NULL);
 
 	if (devfreq->profile->exit)
 		devfreq->profile->exit(devfreq->dev.parent);
 
-	if (devfreq->governor->exit)
-		devfreq->governor->exit(devfreq);
-
 	if (!skip && get_device(&devfreq->dev)) {
 		device_unregister(&devfreq->dev);
 		put_device(&devfreq->dev);
 	}
 
-	if (!devfreq->governor->no_central_polling)
-		list_del(&devfreq->node);
-
-	mutex_unlock(&devfreq->lock);
 	mutex_destroy(&devfreq->lock);
-
 	kfree(devfreq);
 }
 
@@ -210,130 +325,8 @@ static void _remove_devfreq(struct devfreq *devfreq, bool skip)
 static void devfreq_dev_release(struct device *dev)
 {
 	struct devfreq *devfreq = to_devfreq(dev);
-	bool central_polling = !devfreq->governor->no_central_polling;
-
-	/*
-	 * If devfreq_dev_release() was called by device_unregister() of
-	 * _remove_devfreq(), we cannot mutex_lock(&devfreq->lock) and
-	 * being_removed is already set. This also partially checks the case
-	 * where devfreq_dev_release() is called from a thread other than
-	 * the one called _remove_devfreq(); however, this case is
-	 * dealt completely with another following being_removed check.
-	 *
-	 * Because being_removed is never being
-	 * unset, we do not need to worry about race conditions on
-	 * being_removed.
-	 */
-	if (devfreq->being_removed)
-		return;
 
-	if (central_polling)
-		mutex_lock(&devfreq_list_lock);
-
-	mutex_lock(&devfreq->lock);
-
-	/*
-	 * Check being_removed flag again for the case where
-	 * devfreq_dev_release() was called in a thread other than the one
-	 * possibly called _remove_devfreq().
-	 */
-	if (devfreq->being_removed) {
-		mutex_unlock(&devfreq->lock);
-		goto out;
-	}
-
-	/* devfreq->lock is unlocked and removed in _removed_devfreq() */
 	_remove_devfreq(devfreq, true);
-
-out:
-	if (central_polling)
-		mutex_unlock(&devfreq_list_lock);
-}
-
-/**
- * devfreq_monitor() - Periodically poll devfreq objects.
- * @work: the work struct used to run devfreq_monitor periodically.
- *
- */
-static void devfreq_monitor(struct work_struct *work)
-{
-	static unsigned long last_polled_at;
-	struct devfreq *devfreq, *tmp;
-	int error;
-	unsigned long jiffies_passed;
-	unsigned long next_jiffies = ULONG_MAX, now = jiffies;
-	struct device *dev;
-
-	/* Initially last_polled_at = 0, polling every device at bootup */
-	jiffies_passed = now - last_polled_at;
-	last_polled_at = now;
-	if (jiffies_passed == 0)
-		jiffies_passed = 1;
-
-	mutex_lock(&devfreq_list_lock);
-	list_for_each_entry_safe(devfreq, tmp, &devfreq_list, node) {
-		mutex_lock(&devfreq->lock);
-		dev = devfreq->dev.parent;
-
-		/* Do not remove tmp for a while */
-		wait_remove_device = tmp;
-
-		if (devfreq->governor->no_central_polling ||
-		    devfreq->next_polling == 0) {
-			mutex_unlock(&devfreq->lock);
-			continue;
-		}
-		mutex_unlock(&devfreq_list_lock);
-
-		/*
-		 * Reduce more next_polling if devfreq_wq took an extra
-		 * delay. (i.e., CPU has been idled.)
-		 */
-		if (devfreq->next_polling <= jiffies_passed) {
-			error = update_devfreq(devfreq);
-
-			/* Remove a devfreq with an error. */
-			if (error && error != -EAGAIN) {
-
-				dev_err(dev, "Due to update_devfreq error(%d), devfreq(%s) is removed from the device\n",
-					error, devfreq->governor->name);
-
-				/*
-				 * Unlock devfreq before locking the list
-				 * in order to avoid deadlock with
-				 * find_device_devfreq or others
-				 */
-				mutex_unlock(&devfreq->lock);
-				mutex_lock(&devfreq_list_lock);
-				/* Check if devfreq is already removed */
-				if (IS_ERR(find_device_devfreq(dev)))
-					continue;
-				mutex_lock(&devfreq->lock);
-				/* This unlocks devfreq->lock and free it */
-				_remove_devfreq(devfreq, false);
-				continue;
-			}
-			devfreq->next_polling = devfreq->polling_jiffies;
-		} else {
-			devfreq->next_polling -= jiffies_passed;
-		}
-
-		if (devfreq->next_polling)
-			next_jiffies = (next_jiffies > devfreq->next_polling) ?
-					devfreq->next_polling : next_jiffies;
-
-		mutex_unlock(&devfreq->lock);
-		mutex_lock(&devfreq_list_lock);
-	}
-	wait_remove_device = NULL;
-	mutex_unlock(&devfreq_list_lock);
-
-	if (next_jiffies > 0 && next_jiffies < ULONG_MAX) {
-		polling = true;
-		queue_delayed_work(devfreq_wq, &devfreq_work, next_jiffies);
-	} else {
-		polling = false;
-	}
 }
 
 /**
@@ -357,16 +350,13 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
-
-	if (!governor->no_central_polling) {
-		mutex_lock(&devfreq_list_lock);
-		devfreq = find_device_devfreq(dev);
-		mutex_unlock(&devfreq_list_lock);
-		if (!IS_ERR(devfreq)) {
-			dev_err(dev, "%s: Unable to create devfreq for the device. It already has one.\n", __func__);
-			err = -EINVAL;
-			goto err_out;
-		}
+	mutex_lock(&devfreq_list_lock);
+	devfreq = find_device_devfreq(dev);
+	mutex_unlock(&devfreq_list_lock);
+	if (!IS_ERR(devfreq)) {
+		dev_err(dev, "%s: Unable to create devfreq for the device. It already has one.\n", __func__);
+		err = -EINVAL;
+		goto err_out;
 	}
 
 	devfreq = kzalloc(sizeof(struct devfreq), GFP_KERNEL);
@@ -386,48 +376,41 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->governor = governor;
 	devfreq->previous_freq = profile->initial_freq;
 	devfreq->data = data;
-	devfreq->next_polling = devfreq->polling_jiffies
-			      = msecs_to_jiffies(devfreq->profile->polling_ms);
 	devfreq->nb.notifier_call = devfreq_notifier_call;
 
 	dev_set_name(&devfreq->dev, dev_name(dev));
 	err = device_register(&devfreq->dev);
 	if (err) {
 		put_device(&devfreq->dev);
+		mutex_unlock(&devfreq->lock);
 		goto err_dev;
 	}
 
-	if (governor->init)
-		err = governor->init(devfreq);
-	if (err)
-		goto err_init;
-
 	mutex_unlock(&devfreq->lock);
 
-	if (governor->no_central_polling)
-		goto out;
-
 	mutex_lock(&devfreq_list_lock);
-
 	list_add(&devfreq->node, &devfreq_list);
+	mutex_unlock(&devfreq_list_lock);
 
-	if (devfreq_wq && devfreq->next_polling && !polling) {
-		polling = true;
-		queue_delayed_work(devfreq_wq, &devfreq_work,
-				   devfreq->next_polling);
+	err = devfreq->governor->event_handler(devfreq,
+				DEVFREQ_GOV_START, NULL);
+	if (err) {
+		dev_err(dev, "%s: Unable to start governor for the device\n",
+			__func__);
+		goto err_init;
 	}
-	mutex_unlock(&devfreq_list_lock);
-out:
+
 	return devfreq;
 
 err_init:
+	list_del(&devfreq->node);
 	device_unregister(&devfreq->dev);
 err_dev:
-	mutex_unlock(&devfreq->lock);
 	kfree(devfreq);
 err_out:
 	return ERR_PTR(err);
 }
+EXPORT_SYMBOL(devfreq_add_device);
 
 /**
  * devfreq_remove_device() - Remove devfreq feature from a device.
@@ -435,30 +418,14 @@ err_out:
  */
 int devfreq_remove_device(struct devfreq *devfreq)
 {
-	bool central_polling;
-
 	if (!devfreq)
 		return -EINVAL;
 
-	central_polling = !devfreq->governor->no_central_polling;
-
-	if (central_polling) {
-		mutex_lock(&devfreq_list_lock);
-		while (wait_remove_device == devfreq) {
-			mutex_unlock(&devfreq_list_lock);
-			schedule();
-			mutex_lock(&devfreq_list_lock);
-		}
-	}
-
-	mutex_lock(&devfreq->lock);
-	_remove_devfreq(devfreq, false); /* it unlocks devfreq->lock */
-
-	if (central_polling)
-		mutex_unlock(&devfreq_list_lock);
+	_remove_devfreq(devfreq, false);
 
 	return 0;
 }
+EXPORT_SYMBOL(devfreq_remove_device);
 
 static ssize_t show_governor(struct device *dev,
 			     struct device_attribute *attr, char *buf)
@@ -490,35 +457,13 @@ static ssize_t store_polling_interval(struct device *dev,
 	if (ret != 1)
 		goto out;
 
-	mutex_lock(&df->lock);
-	df->profile->polling_ms = value;
-	df->next_polling = df->polling_jiffies
-			 = msecs_to_jiffies(value);
-	mutex_unlock(&df->lock);
-
+	df->governor->event_handler(df, DEVFREQ_GOV_INTERVAL, &value);
 	ret = count;
 
-	if (df->governor->no_central_polling)
-		goto out;
-
-	mutex_lock(&devfreq_list_lock);
-	if (df->next_polling > 0 && !polling) {
-		polling = true;
-		queue_delayed_work(devfreq_wq, &devfreq_work,
-				   df->next_polling);
-	}
-	mutex_unlock(&devfreq_list_lock);
 out:
 	return ret;
 }
 
-static ssize_t show_central_polling(struct device *dev,
-				    struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "%d\n",
-		       !to_devfreq(dev)->governor->no_central_polling);
-}
-
 static ssize_t store_min_freq(struct device *dev, struct device_attribute *attr,
 			      const char *buf, size_t count)
 {
@@ -590,7 +535,6 @@ static ssize_t show_max_freq(struct device *dev, struct device_attribute *attr,
 static struct device_attribute devfreq_attrs[] = {
 	__ATTR(governor, S_IRUGO, show_governor, NULL),
 	__ATTR(cur_freq, S_IRUGO, show_freq, NULL),
-	__ATTR(central_polling, S_IRUGO, show_central_polling, NULL),
 	__ATTR(polling_interval, S_IRUGO | S_IWUSR, show_polling_interval,
 	       store_polling_interval),
 	__ATTR(min_freq, S_IRUGO | S_IWUSR, show_min_freq, store_min_freq),
@@ -598,23 +542,6 @@ static struct device_attribute devfreq_attrs[] = {
 	{ },
 };
 
-/**
- * devfreq_start_polling() - Initialize data structure for devfreq framework and
- *			   start polling registered devfreq devices.
- */
-static int __init devfreq_start_polling(void)
-{
-	mutex_lock(&devfreq_list_lock);
-	polling = false;
-	devfreq_wq = create_freezable_workqueue("devfreq_wq");
-	INIT_DEFERRABLE_WORK(&devfreq_work, devfreq_monitor);
-	mutex_unlock(&devfreq_list_lock);
-
-	devfreq_monitor(&devfreq_work.work);
-	return 0;
-}
-late_initcall(devfreq_start_polling);
-
 static int __init devfreq_init(void)
 {
 	devfreq_class = class_create(THIS_MODULE, "devfreq");
@@ -622,7 +549,15 @@ static int __init devfreq_init(void)
 		pr_err("%s: couldn't create class\n", __FILE__);
 		return PTR_ERR(devfreq_class);
 	}
+
+	devfreq_wq = create_freezable_workqueue("devfreq_wq");
+	if (IS_ERR(devfreq_wq)) {
+		class_destroy(devfreq_class);
+		pr_err("%s: couldn't create workqueue\n", __FILE__);
+		return PTR_ERR(devfreq_wq);
+	}
 	devfreq_class->dev_attrs = devfreq_attrs;
+
 	return 0;
 }
 subsys_initcall(devfreq_init);
@@ -630,6 +565,7 @@ subsys_initcall(devfreq_init);
 static void __exit devfreq_exit(void)
 {
 	class_destroy(devfreq_class);
+	destroy_workqueue(devfreq_wq);
 }
 module_exit(devfreq_exit);
 
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index ea7f13c58ded..bb3aff32d627 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -18,7 +18,18 @@
 
 #define to_devfreq(DEV)	container_of((DEV), struct devfreq, dev)
 
+/* Devfreq events */
+#define DEVFREQ_GOV_START			0x1
+#define DEVFREQ_GOV_STOP			0x2
+#define DEVFREQ_GOV_INTERVAL			0x3
+
 /* Caution: devfreq->lock must be locked before calling update_devfreq */
 extern int update_devfreq(struct devfreq *devfreq);
 
+extern void devfreq_monitor_start(struct devfreq *devfreq);
+extern void devfreq_monitor_stop(struct devfreq *devfreq);
+extern void devfreq_monitor_suspend(struct devfreq *devfreq);
+extern void devfreq_monitor_resume(struct devfreq *devfreq);
+extern void devfreq_interval_update(struct devfreq *devfreq,
+					unsigned int *delay);
 #endif /* _GOVERNOR_H */
diff --git a/drivers/devfreq/governor_performance.c b/drivers/devfreq/governor_performance.c
index af75ddd4f158..eea3f9bd7894 100644
--- a/drivers/devfreq/governor_performance.c
+++ b/drivers/devfreq/governor_performance.c
@@ -26,14 +26,22 @@ static int devfreq_performance_func(struct devfreq *df,
 	return 0;
 }
 
-static int performance_init(struct devfreq *devfreq)
+static int devfreq_performance_handler(struct devfreq *devfreq,
+				unsigned int event, void *data)
 {
-	return update_devfreq(devfreq);
+	int ret = 0;
+
+	if (event == DEVFREQ_GOV_START) {
+		mutex_lock(&devfreq->lock);
+		ret = update_devfreq(devfreq);
+		mutex_unlock(&devfreq->lock);
+	}
+
+	return ret;
 }
 
 const struct devfreq_governor devfreq_performance = {
 	.name = "performance",
-	.init = performance_init,
 	.get_target_freq = devfreq_performance_func,
-	.no_central_polling = true,
+	.event_handler = devfreq_performance_handler,
 };
diff --git a/drivers/devfreq/governor_powersave.c b/drivers/devfreq/governor_powersave.c
index fec0cdbd2477..2868d98ed3e2 100644
--- a/drivers/devfreq/governor_powersave.c
+++ b/drivers/devfreq/governor_powersave.c
@@ -23,14 +23,22 @@ static int devfreq_powersave_func(struct devfreq *df,
 	return 0;
 }
 
-static int powersave_init(struct devfreq *devfreq)
+static int devfreq_powersave_handler(struct devfreq *devfreq,
+				unsigned int event, void *data)
 {
-	return update_devfreq(devfreq);
+	int ret = 0;
+
+	if (event == DEVFREQ_GOV_START) {
+		mutex_lock(&devfreq->lock);
+		ret = update_devfreq(devfreq);
+		mutex_unlock(&devfreq->lock);
+	}
+
+	return ret;
 }
 
 const struct devfreq_governor devfreq_powersave = {
 	.name = "powersave",
-	.init = powersave_init,
 	.get_target_freq = devfreq_powersave_func,
-	.no_central_polling = true,
+	.event_handler = devfreq_powersave_handler,
 };
diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c
index a2e3eae79011..3716a659122b 100644
--- a/drivers/devfreq/governor_simpleondemand.c
+++ b/drivers/devfreq/governor_simpleondemand.c
@@ -12,6 +12,7 @@
 #include <linux/errno.h>
 #include <linux/devfreq.h>
 #include <linux/math64.h>
+#include "governor.h"
 
 /* Default constants for DevFreq-Simple-Ondemand (DFSO) */
 #define DFSO_UPTHRESHOLD	(90)
@@ -88,7 +89,30 @@ static int devfreq_simple_ondemand_func(struct devfreq *df,
 	return 0;
 }
 
+static int devfreq_simple_ondemand_handler(struct devfreq *devfreq,
+				unsigned int event, void *data)
+{
+	switch (event) {
+	case DEVFREQ_GOV_START:
+		devfreq_monitor_start(devfreq);
+		break;
+
+	case DEVFREQ_GOV_STOP:
+		devfreq_monitor_stop(devfreq);
+		break;
+
+	case DEVFREQ_GOV_INTERVAL:
+		devfreq_interval_update(devfreq, (unsigned int *)data);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 const struct devfreq_governor devfreq_simple_ondemand = {
 	.name = "simple_ondemand",
 	.get_target_freq = devfreq_simple_ondemand_func,
+	.event_handler = devfreq_simple_ondemand_handler,
 };
diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c
index 0681246fc89d..7067555bd444 100644
--- a/drivers/devfreq/governor_userspace.c
+++ b/drivers/devfreq/governor_userspace.c
@@ -116,10 +116,27 @@ static void userspace_exit(struct devfreq *devfreq)
 	devfreq->data = NULL;
 }
 
+static int devfreq_userspace_handler(struct devfreq *devfreq,
+			unsigned int event, void *data)
+{
+	int ret = 0;
+
+	switch (event) {
+	case DEVFREQ_GOV_START:
+		ret = userspace_init(devfreq);
+		break;
+	case DEVFREQ_GOV_STOP:
+		userspace_exit(devfreq);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 const struct devfreq_governor devfreq_userspace = {
 	.name = "userspace",
 	.get_target_freq = devfreq_userspace_func,
-	.init = userspace_init,
-	.exit = userspace_exit,
-	.no_central_polling = true,
+	.event_handler = devfreq_userspace_handler,
 };
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 281c72a3b9d5..9cdffde74bb5 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -91,25 +91,18 @@ struct devfreq_dev_profile {
  *			status of the device (load = busy_time / total_time).
  *			If no_central_polling is set, this callback is called
  *			only with update_devfreq() notified by OPP.
- * @init		Called when the devfreq is being attached to a device
- * @exit		Called when the devfreq is being removed from a
- *			device. Governor should stop any internal routines
- *			before return because related data may be
- *			freed after exit().
- * @no_central_polling	Do not use devfreq's central polling mechanism.
- *			When this is set, devfreq will not call
- *			get_target_freq with devfreq_monitor(). However,
- *			devfreq will call get_target_freq with
- *			devfreq_update() notified by OPP framework.
+ * @event_handler       Callback for devfreq core framework to notify events
+ *                      to governors. Events include per device governor
+ *                      init and exit, opp changes out of devfreq, suspend
+ *                      and resume of per device devfreq during device idle.
  *
  * Note that the callbacks are called with devfreq->lock locked by devfreq.
  */
 struct devfreq_governor {
 	const char name[DEVFREQ_NAME_LEN];
 	int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
-	int (*init)(struct devfreq *this);
-	void (*exit)(struct devfreq *this);
-	const bool no_central_polling;
+	int (*event_handler)(struct devfreq *devfreq,
+				unsigned int event, void *data);
 };
 
 /**
@@ -124,18 +117,13 @@ struct devfreq_governor {
  * @nb		notifier block used to notify devfreq object that it should
  *		reevaluate operable frequencies. Devfreq users may use
  *		devfreq.nb to the corresponding register notifier call chain.
- * @polling_jiffies	interval in jiffies.
+ * @work	delayed work for load monitoring.
  * @previous_freq	previously configured frequency value.
- * @next_polling	the number of remaining jiffies to poll with
- *			"devfreq_monitor" executions to reevaluate
- *			frequency/voltage of the device. Set by
- *			profile's polling_ms interval.
  * @data	Private data of the governor. The devfreq framework does not
  *		touch this.
- * @being_removed	a flag to mark that this object is being removed in
- *			order to prevent trying to remove the object multiple times.
  * @min_freq	Limit minimum frequency requested by user (0: none)
  * @max_freq	Limit maximum frequency requested by user (0: none)
+ * @stop_polling	 devfreq polling status of a device.
  *
  * This structure stores the devfreq information for a give device.
  *
@@ -153,17 +141,15 @@ struct devfreq {
 	struct devfreq_dev_profile *profile;
 	const struct devfreq_governor *governor;
 	struct notifier_block nb;
+	struct delayed_work work;
 
-	unsigned long polling_jiffies;
 	unsigned long previous_freq;
-	unsigned int next_polling;
 
 	void *data; /* private data for governors */
 
-	bool being_removed;
-
 	unsigned long min_freq;
 	unsigned long max_freq;
+	bool stop_polling;
 };
 
 #if defined(CONFIG_PM_DEVFREQ)
-- 
cgit v1.2.3-55-g7522


From 206c30cfeb7c05dfb9fdfd81b1deb933627e43c1 Mon Sep 17 00:00:00 2001
From: Rajagopal Venkat
Date: Fri, 26 Oct 2012 01:50:18 +0200
Subject: PM / devfreq: Add suspend and resume apis

Add devfreq suspend/resume apis for devfreq users. This patch
supports suspend and resume of devfreq load monitoring, required
for devices which can idle.

Signed-off-by: Rajagopal Venkat <rajagopal.venkat@linaro.org>
Acked-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/devfreq/devfreq.c                 | 28 ++++++++++++++++++++++++++++
 drivers/devfreq/governor.h                |  2 ++
 drivers/devfreq/governor_simpleondemand.c |  9 +++++++++
 include/linux/devfreq.h                   | 12 ++++++++++++
 4 files changed, 51 insertions(+)

(limited to 'include')

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 1aaf1aeb1f1d..999600da21c7 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -427,6 +427,34 @@ int devfreq_remove_device(struct devfreq *devfreq)
 }
 EXPORT_SYMBOL(devfreq_remove_device);
 
+/**
+ * devfreq_suspend_device() - Suspend devfreq of a device.
+ * @devfreq: the devfreq instance to be suspended
+ */
+int devfreq_suspend_device(struct devfreq *devfreq)
+{
+	if (!devfreq)
+		return -EINVAL;
+
+	return devfreq->governor->event_handler(devfreq,
+				DEVFREQ_GOV_SUSPEND, NULL);
+}
+EXPORT_SYMBOL(devfreq_suspend_device);
+
+/**
+ * devfreq_resume_device() - Resume devfreq of a device.
+ * @devfreq: the devfreq instance to be resumed
+ */
+int devfreq_resume_device(struct devfreq *devfreq)
+{
+	if (!devfreq)
+		return -EINVAL;
+
+	return devfreq->governor->event_handler(devfreq,
+				DEVFREQ_GOV_RESUME, NULL);
+}
+EXPORT_SYMBOL(devfreq_resume_device);
+
 static ssize_t show_governor(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index bb3aff32d627..26432ac0a398 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -22,6 +22,8 @@
 #define DEVFREQ_GOV_START			0x1
 #define DEVFREQ_GOV_STOP			0x2
 #define DEVFREQ_GOV_INTERVAL			0x3
+#define DEVFREQ_GOV_SUSPEND			0x4
+#define DEVFREQ_GOV_RESUME			0x5
 
 /* Caution: devfreq->lock must be locked before calling update_devfreq */
 extern int update_devfreq(struct devfreq *devfreq);
diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c
index 3716a659122b..b5cf0fb24efe 100644
--- a/drivers/devfreq/governor_simpleondemand.c
+++ b/drivers/devfreq/governor_simpleondemand.c
@@ -104,6 +104,15 @@ static int devfreq_simple_ondemand_handler(struct devfreq *devfreq,
 	case DEVFREQ_GOV_INTERVAL:
 		devfreq_interval_update(devfreq, (unsigned int *)data);
 		break;
+
+	case DEVFREQ_GOV_SUSPEND:
+		devfreq_monitor_suspend(devfreq);
+		break;
+
+	case DEVFREQ_GOV_RESUME:
+		devfreq_monitor_resume(devfreq);
+		break;
+
 	default:
 		break;
 	}
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 9cdffde74bb5..ee243a3229b8 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -158,6 +158,8 @@ extern struct devfreq *devfreq_add_device(struct device *dev,
 				  const struct devfreq_governor *governor,
 				  void *data);
 extern int devfreq_remove_device(struct devfreq *devfreq);
+extern int devfreq_suspend_device(struct devfreq *devfreq);
+extern int devfreq_resume_device(struct devfreq *devfreq);
 
 /* Helper functions for devfreq user device driver with OPP. */
 extern struct opp *devfreq_recommended_opp(struct device *dev,
@@ -211,6 +213,16 @@ static int devfreq_remove_device(struct devfreq *devfreq)
 	return 0;
 }
 
+static int devfreq_suspend_device(struct devfreq *devfreq)
+{
+	return 0;
+}
+
+static int devfreq_resume_device(struct devfreq *devfreq)
+{
+	return 0;
+}
+
 static struct opp *devfreq_recommended_opp(struct device *dev,
 					   unsigned long *freq, u32 flags)
 {
-- 
cgit v1.2.3-55-g7522


From 7f98a905dca6e4f144cdd4462edeac00c2bdc379 Mon Sep 17 00:00:00 2001
From: Rajagopal Venkat
Date: Fri, 26 Oct 2012 01:50:26 +0200
Subject: PM / devfreq: Add current freq callback in device profile

Devfreq returns governor predicted frequency as current frequency
via sysfs interface. But device may not support all frequencies
that governor predicts. So add a callback in device profile to get
current freq from driver. Also add a new sysfs node to expose
governor predicted next target frequency.

Signed-off-by: Rajagopal Venkat <rajagopal.venkat@linaro.org>
Acked-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/ABI/testing/sysfs-class-devfreq | 11 ++++++++++-
 drivers/devfreq/devfreq.c                     | 14 ++++++++++++++
 include/linux/devfreq.h                       |  3 +++
 3 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
index 89283b1b0240..e6cf08e6734d 100644
--- a/Documentation/ABI/testing/sysfs-class-devfreq
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -19,7 +19,16 @@ Date:		September 2011
 Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
 Description:
 		The /sys/class/devfreq/.../cur_freq shows the current
-		frequency of the corresponding devfreq object.
+		frequency of the corresponding devfreq object. Same as
+		target_freq when get_cur_freq() is not implemented by
+		devfreq driver.
+
+What:		/sys/class/devfreq/.../target_freq
+Date:		September 2012
+Contact:	Rajagopal Venkat <rajagopal.venkat@linaro.org>
+Description:
+		The /sys/class/devfreq/.../target_freq shows the next governor
+		predicted target frequency of the corresponding devfreq object.
 
 What:		/sys/class/devfreq/.../polling_interval
 Date:		September 2011
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 999600da21c7..f2f8a976c465 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -463,6 +463,19 @@ static ssize_t show_governor(struct device *dev,
 
 static ssize_t show_freq(struct device *dev,
 			 struct device_attribute *attr, char *buf)
+{
+	unsigned long freq;
+	struct devfreq *devfreq = to_devfreq(dev);
+
+	if (devfreq->profile->get_cur_freq &&
+		!devfreq->profile->get_cur_freq(devfreq->dev.parent, &freq))
+			return sprintf(buf, "%lu\n", freq);
+
+	return sprintf(buf, "%lu\n", devfreq->previous_freq);
+}
+
+static ssize_t show_target_freq(struct device *dev,
+			struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%lu\n", to_devfreq(dev)->previous_freq);
 }
@@ -563,6 +576,7 @@ static ssize_t show_max_freq(struct device *dev, struct device_attribute *attr,
 static struct device_attribute devfreq_attrs[] = {
 	__ATTR(governor, S_IRUGO, show_governor, NULL),
 	__ATTR(cur_freq, S_IRUGO, show_freq, NULL),
+	__ATTR(target_freq, S_IRUGO, show_target_freq, NULL),
 	__ATTR(polling_interval, S_IRUGO | S_IWUSR, show_polling_interval,
 	       store_polling_interval),
 	__ATTR(min_freq, S_IRUGO | S_IWUSR, show_min_freq, store_min_freq),
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index ee243a3229b8..7e2e2ea4a70f 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -66,6 +66,8 @@ struct devfreq_dev_status {
  *			explained above with "DEVFREQ_FLAG_*" macros.
  * @get_dev_status	The device should provide the current performance
  *			status to devfreq, which is used by governors.
+ * @get_cur_freq	The device should provide the current frequency
+ *			at which it is operating.
  * @exit		An optional callback that is called when devfreq
  *			is removing the devfreq object due to error or
  *			from devfreq_remove_device() call. If the user
@@ -79,6 +81,7 @@ struct devfreq_dev_profile {
 	int (*target)(struct device *dev, unsigned long *freq, u32 flags);
 	int (*get_dev_status)(struct device *dev,
 			      struct devfreq_dev_status *stat);
+	int (*get_cur_freq)(struct device *dev, unsigned long *freq);
 	void (*exit)(struct device *dev);
 };
 
-- 
cgit v1.2.3-55-g7522


From aa0010f880ab542da3ad0e72992f2dc518ac68a0 Mon Sep 17 00:00:00 2001
From: Amerigo Wang
Date: Sun, 11 Nov 2012 21:52:33 +0000
Subject: net: convert __IPTUNNEL_XMIT() to an inline function

__IPTUNNEL_XMIT() is an ugly macro, convert it to a static
inline function, so make it more readable.

IPTUNNEL_XMIT() is unused, just remove it.

Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c       |  2 +-
 include/linux/if_tunnel.h | 10 ++++++++++
 include/net/ipip.h        | 40 +++++++++++++++++++++-------------------
 net/ipv4/ip_gre.c         | 14 +-------------
 net/ipv4/ip_vti.c         |  9 ---------
 net/ipv4/ipip.c           | 14 +-------------
 net/ipv6/ip6_gre.c        |  9 ---------
 net/ipv6/ip6_tunnel.c     |  8 --------
 net/ipv6/sit.c            | 14 +-------------
 9 files changed, 35 insertions(+), 85 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 8aca888734da..9814d67237f1 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -769,7 +769,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	vxlan_set_owner(dev, skb);
 
-	/* See __IPTUNNEL_XMIT */
+	/* See iptunnel_xmit() */
 	skb->ip_summed = CHECKSUM_NONE;
 	ip_select_ident(iph, &rt->dst, NULL);
 
diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h
index 1cc595a67cc9..06d1d5badd36 100644
--- a/include/linux/if_tunnel.h
+++ b/include/linux/if_tunnel.h
@@ -4,5 +4,15 @@
 #include <linux/ip.h>
 #include <linux/in6.h>
 #include <uapi/linux/if_tunnel.h>
+#include <linux/u64_stats_sync.h>
+
+/* often modified stats are per cpu, other are shared (netdev->stats) */
+struct pcpu_tstats {
+	u64	rx_packets;
+	u64	rx_bytes;
+	u64	tx_packets;
+	u64	tx_bytes;
+	struct u64_stats_sync	syncp;
+};
 
 #endif /* _IF_TUNNEL_H_ */
diff --git a/include/net/ipip.h b/include/net/ipip.h
index ddc077c51f32..21947cf4fa46 100644
--- a/include/net/ipip.h
+++ b/include/net/ipip.h
@@ -48,25 +48,27 @@ struct ip_tunnel_prl_entry {
 	struct rcu_head			rcu_head;
 };
 
-#define __IPTUNNEL_XMIT(stats1, stats2) do {				\
-	int err;							\
-	int pkt_len = skb->len - skb_transport_offset(skb);		\
-									\
-	skb->ip_summed = CHECKSUM_NONE;					\
-	ip_select_ident(iph, &rt->dst, NULL);				\
-									\
-	err = ip_local_out(skb);					\
-	if (likely(net_xmit_eval(err) == 0)) {				\
-		u64_stats_update_begin(&(stats1)->syncp);		\
-		(stats1)->tx_bytes += pkt_len;				\
-		(stats1)->tx_packets++;					\
-		u64_stats_update_end(&(stats1)->syncp);			\
-	} else {							\
-		(stats2)->tx_errors++;					\
-		(stats2)->tx_aborted_errors++;				\
-	}								\
-} while (0)
+static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	int err;
+	struct iphdr *iph = ip_hdr(skb);
+	int pkt_len = skb->len - skb_transport_offset(skb);
+	struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats);
 
-#define IPTUNNEL_XMIT() __IPTUNNEL_XMIT(txq, stats)
+	nf_reset(skb);
+	skb->ip_summed = CHECKSUM_NONE;
+	ip_select_ident(iph, skb_dst(skb), NULL);
+
+	err = ip_local_out(skb);
+	if (likely(net_xmit_eval(err) == 0)) {
+		u64_stats_update_begin(&tstats->syncp);
+		tstats->tx_bytes += pkt_len;
+		tstats->tx_packets++;
+		u64_stats_update_end(&tstats->syncp);
+	} else {
+		dev->stats.tx_errors++;
+		dev->stats.tx_aborted_errors++;
+	}
+}
 
 #endif
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7240f8e2dd45..37000ae24c55 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -171,15 +171,6 @@ struct ipgre_net {
 #define for_each_ip_tunnel_rcu(start) \
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
-/* often modified stats are per cpu, other are shared (netdev->stats) */
-struct pcpu_tstats {
-	u64	rx_packets;
-	u64	rx_bytes;
-	u64	tx_packets;
-	u64	tx_bytes;
-	struct u64_stats_sync	syncp;
-};
-
 static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev,
 						   struct rtnl_link_stats64 *tot)
 {
@@ -753,7 +744,6 @@ drop:
 static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct pcpu_tstats *tstats;
 	const struct iphdr  *old_iph = ip_hdr(skb);
 	const struct iphdr  *tiph;
 	struct flowi4 fl4;
@@ -977,9 +967,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 		}
 	}
 
-	nf_reset(skb);
-	tstats = this_cpu_ptr(dev->tstats);
-	__IPTUNNEL_XMIT(tstats, &dev->stats);
+	iptunnel_xmit(skb, dev);
 	return NETDEV_TX_OK;
 
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1831092f999f..e0f2c88f03c1 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -71,15 +71,6 @@ static int vti_tunnel_bind_dev(struct net_device *dev);
 #define for_each_ip_tunnel_rcu(start) \
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
-/* often modified stats are per cpu, other are shared (netdev->stats) */
-struct pcpu_tstats {
-	u64	rx_packets;
-	u64	rx_bytes;
-	u64	tx_packets;
-	u64	tx_bytes;
-	struct	u64_stats_sync	syncp;
-};
-
 #define VTI_XMIT(stats1, stats2) do {				\
 	int err;						\
 	int pkt_len = skb->len;					\
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 720855e41100..3a4ad7d82f67 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -147,15 +147,6 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly;
 #define for_each_ip_tunnel_rcu(start) \
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
-/* often modified stats are per cpu, other are shared (netdev->stats) */
-struct pcpu_tstats {
-	u64	rx_packets;
-	u64	rx_bytes;
-	u64	tx_packets;
-	u64	tx_bytes;
-	struct u64_stats_sync	syncp;
-};
-
 static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev,
 						  struct rtnl_link_stats64 *tot)
 {
@@ -465,7 +456,6 @@ drop:
 static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct pcpu_tstats *tstats;
 	const struct iphdr  *tiph = &tunnel->parms.iph;
 	u8     tos = tunnel->parms.iph.tos;
 	__be16 df = tiph->frag_off;
@@ -592,9 +582,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	if ((iph->ttl = tiph->ttl) == 0)
 		iph->ttl	=	old_iph->ttl;
 
-	nf_reset(skb);
-	tstats = this_cpu_ptr(dev->tstats);
-	__IPTUNNEL_XMIT(tstats, &dev->stats);
+	iptunnel_xmit(skb, dev);
 	return NETDEV_TX_OK;
 
 tx_error_icmp:
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 12aa473e9793..672101db71ee 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -116,15 +116,6 @@ static u32 HASH_ADDR(const struct in6_addr *addr)
 #define for_each_ip_tunnel_rcu(start) \
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
-/* often modified stats are per cpu, other are shared (netdev->stats) */
-struct pcpu_tstats {
-	u64	rx_packets;
-	u64	rx_bytes;
-	u64	tx_packets;
-	u64	tx_bytes;
-	struct u64_stats_sync	syncp;
-};
-
 static struct rtnl_link_stats64 *ip6gre_get_stats64(struct net_device *dev,
 		struct rtnl_link_stats64 *tot)
 {
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 424ed45ef122..8db4d9b7ab14 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -95,14 +95,6 @@ struct ip6_tnl_net {
 	struct ip6_tnl __rcu **tnls[2];
 };
 
-/* often modified stats are per cpu, other are shared (netdev->stats) */
-struct pcpu_tstats {
-	unsigned long	rx_packets;
-	unsigned long	rx_bytes;
-	unsigned long	tx_packets;
-	unsigned long	tx_bytes;
-} __attribute__((aligned(4*sizeof(unsigned long))));
-
 static struct net_device_stats *ip6_get_stats(struct net_device *dev)
 {
 	struct pcpu_tstats sum = { 0 };
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b543c56cad28..ffe83ef70cf7 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -88,15 +88,6 @@ struct sit_net {
 #define for_each_ip_tunnel_rcu(start) \
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
-/* often modified stats are per cpu, other are shared (netdev->stats) */
-struct pcpu_tstats {
-	u64	rx_packets;
-	u64	rx_bytes;
-	u64	tx_packets;
-	u64	tx_bytes;
-	struct u64_stats_sync	syncp;
-};
-
 static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev,
 						   struct rtnl_link_stats64 *tot)
 {
@@ -685,7 +676,6 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 				     struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct pcpu_tstats *tstats;
 	const struct iphdr  *tiph = &tunnel->parms.iph;
 	const struct ipv6hdr *iph6 = ipv6_hdr(skb);
 	u8     tos = tunnel->parms.iph.tos;
@@ -866,9 +856,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	if ((iph->ttl = tiph->ttl) == 0)
 		iph->ttl	=	iph6->hop_limit;
 
-	nf_reset(skb);
-	tstats = this_cpu_ptr(dev->tstats);
-	__IPTUNNEL_XMIT(tstats, &dev->stats);
+	iptunnel_xmit(skb, dev);
 	return NETDEV_TX_OK;
 
 tx_error_icmp:
-- 
cgit v1.2.3-55-g7522


From e086cadc08e259150b2ab8f7f4a16dbf9e3c2f22 Mon Sep 17 00:00:00 2001
From: Amerigo Wang
Date: Sun, 11 Nov 2012 21:52:34 +0000
Subject: net: unify for_each_ip_tunnel_rcu()

The defitions of for_each_ip_tunnel_rcu() are same,
so unify it. Also, don't hide the parameter 't'.

Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_tunnel.h |  7 +++++++
 net/ipv4/ip_gre.c         | 14 ++++----------
 net/ipv4/ip_vti.c         | 13 ++++---------
 net/ipv4/ipip.c           | 13 +++----------
 net/ipv6/ip6_gre.c        | 14 ++++----------
 net/ipv6/sit.c            | 13 +++----------
 6 files changed, 25 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h
index 06d1d5badd36..f4e56ecd0b1a 100644
--- a/include/linux/if_tunnel.h
+++ b/include/linux/if_tunnel.h
@@ -6,6 +6,13 @@
 #include <uapi/linux/if_tunnel.h>
 #include <linux/u64_stats_sync.h>
 
+/*
+ * Locking : hash tables are protected by RCU and RTNL
+ */
+
+#define for_each_ip_tunnel_rcu(pos, start) \
+	for (pos = rcu_dereference(start); pos; pos = rcu_dereference(pos->next))
+
 /* often modified stats are per cpu, other are shared (netdev->stats) */
 struct pcpu_tstats {
 	u64	rx_packets;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 37000ae24c55..127f2a1e67f5 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -164,12 +164,6 @@ struct ipgre_net {
 #define tunnels_r	tunnels[2]
 #define tunnels_l	tunnels[1]
 #define tunnels_wc	tunnels[0]
-/*
- * Locking : hash tables are protected by RCU and RTNL
- */
-
-#define for_each_ip_tunnel_rcu(start) \
-	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
 static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev,
 						   struct rtnl_link_stats64 *tot)
@@ -241,7 +235,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev,
 		       ARPHRD_ETHER : ARPHRD_IPGRE;
 	int score, cand_score = 4;
 
-	for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) {
+	for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) {
 		if (local != t->parms.iph.saddr ||
 		    remote != t->parms.iph.daddr ||
 		    !(t->dev->flags & IFF_UP))
@@ -268,7 +262,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev,
 		}
 	}
 
-	for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) {
+	for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) {
 		if (remote != t->parms.iph.daddr ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
@@ -294,7 +288,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev,
 		}
 	}
 
-	for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) {
+	for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) {
 		if ((local != t->parms.iph.saddr &&
 		     (local != t->parms.iph.daddr ||
 		      !ipv4_is_multicast(local))) ||
@@ -322,7 +316,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev,
 		}
 	}
 
-	for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) {
+	for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) {
 		if (t->parms.i_key != key ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index e0f2c88f03c1..516188b0dc1e 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -66,11 +66,6 @@ static void vti_tunnel_setup(struct net_device *dev);
 static void vti_dev_free(struct net_device *dev);
 static int vti_tunnel_bind_dev(struct net_device *dev);
 
-/* Locking : hash tables are protected by RCU and RTNL */
-
-#define for_each_ip_tunnel_rcu(start) \
-	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
-
 #define VTI_XMIT(stats1, stats2) do {				\
 	int err;						\
 	int pkt_len = skb->len;					\
@@ -133,19 +128,19 @@ static struct ip_tunnel *vti_tunnel_lookup(struct net *net,
 	struct ip_tunnel *t;
 	struct vti_net *ipn = net_generic(net, vti_net_id);
 
-	for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1])
+	for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1])
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
 			return t;
-	for_each_ip_tunnel_rcu(ipn->tunnels_r[h0])
+	for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0])
 		if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
 			return t;
 
-	for_each_ip_tunnel_rcu(ipn->tunnels_l[h1])
+	for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1])
 		if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
 			return t;
 
-	for_each_ip_tunnel_rcu(ipn->tunnels_wc[0])
+	for_each_ip_tunnel_rcu(t, ipn->tunnels_wc[0])
 		if (t && (t->dev->flags&IFF_UP))
 			return t;
 	return NULL;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 3a4ad7d82f67..099fc1c428b4 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -140,13 +140,6 @@ static void ipip_tunnel_setup(struct net_device *dev);
 static void ipip_dev_free(struct net_device *dev);
 static struct rtnl_link_ops ipip_link_ops __read_mostly;
 
-/*
- * Locking : hash tables are protected by RCU and RTNL
- */
-
-#define for_each_ip_tunnel_rcu(start) \
-	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
-
 static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev,
 						  struct rtnl_link_stats64 *tot)
 {
@@ -189,16 +182,16 @@ static struct ip_tunnel *ipip_tunnel_lookup(struct net *net,
 	struct ip_tunnel *t;
 	struct ipip_net *ipn = net_generic(net, ipip_net_id);
 
-	for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1])
+	for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1])
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
 			return t;
 
-	for_each_ip_tunnel_rcu(ipn->tunnels_r[h0])
+	for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0])
 		if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
 			return t;
 
-	for_each_ip_tunnel_rcu(ipn->tunnels_l[h1])
+	for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1])
 		if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
 			return t;
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 672101db71ee..823fd64d0136 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -109,12 +109,6 @@ static u32 HASH_ADDR(const struct in6_addr *addr)
 #define tunnels_r	tunnels[2]
 #define tunnels_l	tunnels[1]
 #define tunnels_wc	tunnels[0]
-/*
- * Locking : hash tables are protected by RCU and RTNL
- */
-
-#define for_each_ip_tunnel_rcu(start) \
-	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
 static struct rtnl_link_stats64 *ip6gre_get_stats64(struct net_device *dev,
 		struct rtnl_link_stats64 *tot)
@@ -172,7 +166,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 		       ARPHRD_ETHER : ARPHRD_IP6GRE;
 	int score, cand_score = 4;
 
-	for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) {
+	for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) {
 		if (!ipv6_addr_equal(local, &t->parms.laddr) ||
 		    !ipv6_addr_equal(remote, &t->parms.raddr) ||
 		    key != t->parms.i_key ||
@@ -197,7 +191,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 		}
 	}
 
-	for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) {
+	for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) {
 		if (!ipv6_addr_equal(remote, &t->parms.raddr) ||
 		    key != t->parms.i_key ||
 		    !(t->dev->flags & IFF_UP))
@@ -221,7 +215,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 		}
 	}
 
-	for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) {
+	for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) {
 		if ((!ipv6_addr_equal(local, &t->parms.laddr) &&
 			  (!ipv6_addr_equal(local, &t->parms.raddr) ||
 				 !ipv6_addr_is_multicast(local))) ||
@@ -247,7 +241,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 		}
 	}
 
-	for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) {
+	for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) {
 		if (t->parms.i_key != key ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index ffe83ef70cf7..5bce2f698044 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -81,13 +81,6 @@ struct sit_net {
 	struct net_device *fb_tunnel_dev;
 };
 
-/*
- * Locking : hash tables are protected by RCU and RTNL
- */
-
-#define for_each_ip_tunnel_rcu(start) \
-	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
-
 static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev,
 						   struct rtnl_link_stats64 *tot)
 {
@@ -133,20 +126,20 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net,
 	struct ip_tunnel *t;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
-	for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) {
+	for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
 		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
-	for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) {
+	for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) {
 		if (remote == t->parms.iph.daddr &&
 		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
-	for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) {
+	for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) {
 		if (local == t->parms.iph.saddr &&
 		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
-- 
cgit v1.2.3-55-g7522


From 25c71c75ac87508528db053b818944f3650dd7a6 Mon Sep 17 00:00:00 2001
From: stephen hemminger
Date: Tue, 13 Nov 2012 07:53:05 +0000
Subject: bridge: bridge port parameters over netlink

Expose bridge port parameter over netlink. By switching to a nested
message, this can be used for other bridge parameters.

This changes IFLA_PROTINFO attribute from one byte to a full nested
set of attributes. This is safe for application interface because the
old message used IFLA_PROTINFO and new one uses
 IFLA_PROTINFO | NLA_F_NESTED.

The code adapts to old format requests, and therefore stays
compatible with user mode RSTP daemon. Since the type field
for nested and unnested attributes are different, and the old
code in libnetlink doesn't do the mask, it is also safe to use
with old versions of bridge monitor command.

Note: although mode is only a boolean, treating it as a
full byte since in the future someone will probably want to add more
values (like macvlan has).

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h |  15 ++++
 net/bridge/br_netlink.c      | 165 ++++++++++++++++++++++++++++++++++---------
 2 files changed, 147 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 5c80cb11518b..96f7cf49367b 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -205,6 +205,21 @@ enum {
 
 #define IFLA_INET6_MAX	(__IFLA_INET6_MAX - 1)
 
+enum {
+	BRIDGE_MODE_UNSPEC,
+	BRIDGE_MODE_HAIRPIN,
+};
+
+enum {
+	IFLA_BRPORT_UNSPEC,
+	IFLA_BRPORT_STATE,	/* Spanning tree state     */
+	IFLA_BRPORT_PRIORITY,	/* "             priority  */
+	IFLA_BRPORT_COST,	/* "             cost      */
+	IFLA_BRPORT_MODE,	/* mode (hairpin)          */
+	__IFLA_BRPORT_MAX
+};
+#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
+
 struct ifla_cacheinfo {
 	__u32	max_reasm_len;
 	__u32	tstamp;		/* ipv6InterfaceTable updated timestamp */
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 14b065cbd214..0188a2f706c4 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -20,16 +20,39 @@
 #include "br_private.h"
 #include "br_private_stp.h"
 
+static inline size_t br_port_info_size(void)
+{
+	return nla_total_size(1)	/* IFLA_BRPORT_STATE  */
+		+ nla_total_size(2)	/* IFLA_BRPORT_PRIORITY */
+		+ nla_total_size(4)	/* IFLA_BRPORT_COST */
+		+ nla_total_size(1)	/* IFLA_BRPORT_MODE */
+		+ 0;
+}
+
 static inline size_t br_nlmsg_size(void)
 {
 	return NLMSG_ALIGN(sizeof(struct ifinfomsg))
-	       + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
-	       + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
-	       + nla_total_size(4) /* IFLA_MASTER */
-	       + nla_total_size(4) /* IFLA_MTU */
-	       + nla_total_size(4) /* IFLA_LINK */
-	       + nla_total_size(1) /* IFLA_OPERSTATE */
-	       + nla_total_size(1); /* IFLA_PROTINFO */
+		+ nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
+		+ nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
+		+ nla_total_size(4) /* IFLA_MASTER */
+		+ nla_total_size(4) /* IFLA_MTU */
+		+ nla_total_size(4) /* IFLA_LINK */
+		+ nla_total_size(1) /* IFLA_OPERSTATE */
+		+ nla_total_size(br_port_info_size()); /* IFLA_PROTINFO */
+}
+
+static int br_port_fill_attrs(struct sk_buff *skb,
+			      const struct net_bridge_port *p)
+{
+	u8 mode = !!(p->flags & BR_HAIRPIN_MODE);
+
+	if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) ||
+	    nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) ||
+	    nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) ||
+	    nla_put_u8(skb, IFLA_BRPORT_MODE, mode))
+		return -EMSGSIZE;
+
+	return 0;
 }
 
 /*
@@ -67,10 +90,18 @@ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *por
 	    (dev->addr_len &&
 	     nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
 	    (dev->ifindex != dev->iflink &&
-	     nla_put_u32(skb, IFLA_LINK, dev->iflink)) ||
-	    (event == RTM_NEWLINK &&
-	     nla_put_u8(skb, IFLA_PROTINFO, port->state)))
+	     nla_put_u32(skb, IFLA_LINK, dev->iflink)))
 		goto nla_put_failure;
+
+	if (event == RTM_NEWLINK) {
+		struct nlattr *nest
+			= nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
+
+		if (nest == NULL || br_port_fill_attrs(skb, port) < 0)
+			goto nla_put_failure;
+		nla_nest_end(skb, nest);
+	}
+
 	return nlmsg_end(skb, nlh);
 
 nla_put_failure:
@@ -126,47 +157,115 @@ out:
 	return err;
 }
 
-/*
- * Change state of port (ie from forwarding to blocking etc)
- * Used by spanning tree in user space.
- */
+static const struct nla_policy ifla_brport_policy[IFLA_BRPORT_MAX + 1] = {
+	[IFLA_BRPORT_STATE]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_COST]	= { .type = NLA_U32 },
+	[IFLA_BRPORT_PRIORITY]	= { .type = NLA_U16 },
+	[IFLA_BRPORT_MODE]	= { .type = NLA_U8 },
+};
+
+/* Change the state of the port and notify spanning tree */
+static int br_set_port_state(struct net_bridge_port *p, u8 state)
+{
+	if (state > BR_STATE_BLOCKING)
+		return -EINVAL;
+
+	/* if kernel STP is running, don't allow changes */
+	if (p->br->stp_enabled == BR_KERNEL_STP)
+		return -EBUSY;
+
+	if (!netif_running(p->dev) ||
+	    (!netif_carrier_ok(p->dev) && state != BR_STATE_DISABLED))
+		return -ENETDOWN;
+
+	p->state = state;
+	br_log_state(p);
+	br_port_state_selection(p->br);
+	return 0;
+}
+
+/* Set/clear or port flags based on attribute */
+static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[],
+			   int attrtype, unsigned long mask)
+{
+	if (tb[attrtype]) {
+		u8 flag = nla_get_u8(tb[attrtype]);
+		if (flag)
+			p->flags |= mask;
+		else
+			p->flags &= ~mask;
+	}
+}
+
+/* Process bridge protocol info on port */
+static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
+{
+	int err;
+
+	br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
+
+	if (tb[IFLA_BRPORT_COST]) {
+		err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRPORT_PRIORITY]) {
+		err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY]));
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRPORT_STATE]) {
+		err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE]));
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+/* Change state and parameters on port. */
 int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
 {
 	struct ifinfomsg *ifm;
 	struct nlattr *protinfo;
 	struct net_bridge_port *p;
-	u8 new_state;
+	struct nlattr *tb[IFLA_BRPORT_MAX];
+	int err;
 
 	ifm = nlmsg_data(nlh);
 
 	protinfo = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_PROTINFO);
-	if (!protinfo || nla_len(protinfo) < sizeof(u8))
-		return -EINVAL;
-
-	new_state = nla_get_u8(protinfo);
-	if (new_state > BR_STATE_BLOCKING)
-		return -EINVAL;
+	if (!protinfo)
+		return 0;
 
 	p = br_port_get_rtnl(dev);
 	if (!p)
 		return -EINVAL;
 
-	/* if kernel STP is running, don't allow changes */
-	if (p->br->stp_enabled == BR_KERNEL_STP)
-		return -EBUSY;
+	if (protinfo->nla_type & NLA_F_NESTED) {
+		err = nla_parse_nested(tb, IFLA_BRPORT_MAX,
+				       protinfo, ifla_brport_policy);
+		if (err)
+			return err;
 
-	if (!netif_running(dev) ||
-	    (!netif_carrier_ok(dev) && new_state != BR_STATE_DISABLED))
-		return -ENETDOWN;
+		spin_lock_bh(&p->br->lock);
+		err = br_setport(p, tb);
+		spin_unlock_bh(&p->br->lock);
+	} else {
+		/* Binary compatability with old RSTP */
+		if (nla_len(protinfo) < sizeof(u8))
+			return -EINVAL;
 
-	p->state = new_state;
-	br_log_state(p);
+		spin_lock_bh(&p->br->lock);
+		err = br_set_port_state(p, nla_get_u8(protinfo));
+		spin_unlock_bh(&p->br->lock);
+	}
 
-	spin_lock_bh(&p->br->lock);
-	br_port_state_selection(p->br);
-	spin_unlock_bh(&p->br->lock);
+	if (err == 0)
+		br_ifinfo_notify(RTM_NEWLINK, p);
 
-	return 0;
+	return err;
 }
 
 static int br_validate(struct nlattr *tb[], struct nlattr *data[])
-- 
cgit v1.2.3-55-g7522


From a2e01a65cd7135dab26d27d4b589b2e5358bec99 Mon Sep 17 00:00:00 2001
From: stephen hemminger
Date: Tue, 13 Nov 2012 07:53:07 +0000
Subject: bridge: implement BPDU blocking

This is Linux bridge implementation of STP protection
(Cisco BPDU guard/Juniper BPDU block). BPDU block disables
the bridge port if a STP BPDU packet is received.

Why would you want to do this?
If running Spanning Tree on bridge, hostile devices on the network
may send BPDU and cause network failure. Enabling bpdu block
will detect and stop this.

How to recover the port?
The port will be restarted if link is brought down, or
removed and reattached.  For example:
 # ip li set dev eth0 down; ip li set dev eth0 up

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h | 1 +
 net/bridge/br_netlink.c      | 6 +++++-
 net/bridge/br_private.h      | 1 +
 net/bridge/br_stp_bpdu.c     | 7 +++++++
 net/bridge/br_sysfs_if.c     | 2 ++
 5 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 96f7cf49367b..5e871e4d923f 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -216,6 +216,7 @@ enum {
 	IFLA_BRPORT_PRIORITY,	/* "             priority  */
 	IFLA_BRPORT_COST,	/* "             cost      */
 	IFLA_BRPORT_MODE,	/* mode (hairpin)          */
+	IFLA_BRPORT_GUARD,	/* bpdu guard              */
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 0188a2f706c4..c331e28c7880 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -26,6 +26,7 @@ static inline size_t br_port_info_size(void)
 		+ nla_total_size(2)	/* IFLA_BRPORT_PRIORITY */
 		+ nla_total_size(4)	/* IFLA_BRPORT_COST */
 		+ nla_total_size(1)	/* IFLA_BRPORT_MODE */
+		+ nla_total_size(1)	/* IFLA_BRPORT_GUARD */
 		+ 0;
 }
 
@@ -49,7 +50,8 @@ static int br_port_fill_attrs(struct sk_buff *skb,
 	if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) ||
 	    nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) ||
 	    nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) ||
-	    nla_put_u8(skb, IFLA_BRPORT_MODE, mode))
+	    nla_put_u8(skb, IFLA_BRPORT_MODE, mode) ||
+	    nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)))
 		return -EMSGSIZE;
 
 	return 0;
@@ -162,6 +164,7 @@ static const struct nla_policy ifla_brport_policy[IFLA_BRPORT_MAX + 1] = {
 	[IFLA_BRPORT_COST]	= { .type = NLA_U32 },
 	[IFLA_BRPORT_PRIORITY]	= { .type = NLA_U16 },
 	[IFLA_BRPORT_MODE]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_GUARD]	= { .type = NLA_U8 },
 };
 
 /* Change the state of the port and notify spanning tree */
@@ -203,6 +206,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 	int err;
 
 	br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
+	br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
 
 	if (tb[IFLA_BRPORT_COST]) {
 		err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 22111ffd68df..c92b0804ff2d 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -135,6 +135,7 @@ struct net_bridge_port
 
 	unsigned long 			flags;
 #define BR_HAIRPIN_MODE		0x00000001
+#define BR_BPDU_GUARD           0x00000002
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	u32				multicast_startup_queries_sent;
diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index fd30a6022dea..7f884e3fb955 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -170,6 +170,13 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
 	if (!ether_addr_equal(dest, br->group_addr))
 		goto out;
 
+	if (p->flags & BR_BPDU_GUARD) {
+		br_notice(br, "BPDU received on blocked port %u(%s)\n",
+			  (unsigned int) p->port_no, p->dev->name);
+		br_stp_disable_port(p);
+		goto out;
+	}
+
 	buf = skb_pull(skb, 3);
 
 	if (buf[0] == BPDU_TYPE_CONFIG) {
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index f26173d33d8d..d1dfa4026185 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -156,6 +156,7 @@ static int store_flush(struct net_bridge_port *p, unsigned long v)
 static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush);
 
 BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE);
+BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -189,6 +190,7 @@ static const struct brport_attribute *brport_attrs[] = {
 	&brport_attr_hold_timer,
 	&brport_attr_flush,
 	&brport_attr_hairpin_mode,
+	&brport_attr_bpdu_guard,
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	&brport_attr_multicast_router,
 #endif
-- 
cgit v1.2.3-55-g7522


From 1007dd1aa50b0403df370834f647abef1722925c Mon Sep 17 00:00:00 2001
From: stephen hemminger
Date: Tue, 13 Nov 2012 07:53:08 +0000
Subject: bridge: add root port blocking

This is Linux bridge implementation of root port guard.
If BPDU is received from a leaf (edge) port, it should not
be elected as root port.

Why would you want to do this?
If using STP on a bridge and the downstream bridges are not fully
trusted; this prevents a hostile guest for rerouting traffic.

Why not just use netfilter?
Netfilter does not track of follow spanning tree decisions.
It would be difficult and error prone to try and mirror STP
resolution in netfilter module.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h |  1 +
 net/bridge/br_netlink.c      |  5 ++++-
 net/bridge/br_private.h      |  1 +
 net/bridge/br_stp.c          | 22 +++++++++++++++++++++-
 net/bridge/br_sysfs_if.c     |  2 ++
 5 files changed, 29 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 5e871e4d923f..7aae0179ae44 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -217,6 +217,7 @@ enum {
 	IFLA_BRPORT_COST,	/* "             cost      */
 	IFLA_BRPORT_MODE,	/* mode (hairpin)          */
 	IFLA_BRPORT_GUARD,	/* bpdu guard              */
+	IFLA_BRPORT_PROTECT,	/* root port protection    */
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index c331e28c7880..65429b99a2a3 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -27,6 +27,7 @@ static inline size_t br_port_info_size(void)
 		+ nla_total_size(4)	/* IFLA_BRPORT_COST */
 		+ nla_total_size(1)	/* IFLA_BRPORT_MODE */
 		+ nla_total_size(1)	/* IFLA_BRPORT_GUARD */
+		+ nla_total_size(1)	/* IFLA_BRPORT_PROTECT */
 		+ 0;
 }
 
@@ -51,7 +52,8 @@ static int br_port_fill_attrs(struct sk_buff *skb,
 	    nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) ||
 	    nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) ||
 	    nla_put_u8(skb, IFLA_BRPORT_MODE, mode) ||
-	    nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)))
+	    nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) ||
+	    nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)))
 		return -EMSGSIZE;
 
 	return 0;
@@ -165,6 +167,7 @@ static const struct nla_policy ifla_brport_policy[IFLA_BRPORT_MAX + 1] = {
 	[IFLA_BRPORT_PRIORITY]	= { .type = NLA_U16 },
 	[IFLA_BRPORT_MODE]	= { .type = NLA_U8 },
 	[IFLA_BRPORT_GUARD]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_PROTECT]	= { .type = NLA_U8 },
 };
 
 /* Change the state of the port and notify spanning tree */
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index c92b0804ff2d..eb9cd42146a5 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -136,6 +136,7 @@ struct net_bridge_port
 	unsigned long 			flags;
 #define BR_HAIRPIN_MODE		0x00000001
 #define BR_BPDU_GUARD           0x00000002
+#define BR_ROOT_BLOCK		0x00000004
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	u32				multicast_startup_queries_sent;
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index af9a12099ba4..b01849a74310 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -100,6 +100,21 @@ static int br_should_become_root_port(const struct net_bridge_port *p,
 	return 0;
 }
 
+static void br_root_port_block(const struct net_bridge *br,
+			       struct net_bridge_port *p)
+{
+
+	br_notice(br, "port %u(%s) tried to become root port (blocked)",
+		  (unsigned int) p->port_no, p->dev->name);
+
+	p->state = BR_STATE_LISTENING;
+	br_log_state(p);
+	br_ifinfo_notify(RTM_NEWLINK, p);
+
+	if (br->forward_delay > 0)
+		mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay);
+}
+
 /* called under bridge lock */
 static void br_root_selection(struct net_bridge *br)
 {
@@ -107,7 +122,12 @@ static void br_root_selection(struct net_bridge *br)
 	u16 root_port = 0;
 
 	list_for_each_entry(p, &br->port_list, list) {
-		if (br_should_become_root_port(p, root_port))
+		if (!br_should_become_root_port(p, root_port))
+			continue;
+
+		if (p->flags & BR_ROOT_BLOCK)
+			br_root_port_block(br, p);
+		else
 			root_port = p->port_no;
 	}
 
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index d1dfa4026185..80a4fc5d96ab 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -157,6 +157,7 @@ static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush);
 
 BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE);
 BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
+BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK);
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -191,6 +192,7 @@ static const struct brport_attribute *brport_attrs[] = {
 	&brport_attr_flush,
 	&brport_attr_hairpin_mode,
 	&brport_attr_bpdu_guard,
+	&brport_attr_root_block,
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	&brport_attr_multicast_router,
 #endif
-- 
cgit v1.2.3-55-g7522


From 1cf3d8b3d24cd383ddfd5442c83ec5c355ffc2f7 Mon Sep 17 00:00:00 2001
From: Nathan Fontenot
Date: Tue, 2 Oct 2012 16:57:57 +0000
Subject: powerpc+of: Add of node/property notification chain for adds and
 removes

This patch moves the notification chain for updates to the device tree
from the powerpc/pseries code to the base OF code. This makes this
functionality available to all architectures.

Additionally the notification chain is updated to allow notifications
for property add/remove/update. To make this work a pointer to a new
struct (of_prop_reconfig) is passed to the routines in the notification chain.
The of_prop_reconfig property contains a pointer to the node containing the
property and a pointer to the property itself. In the case of property
updates, the property pointer refers to the new property.

Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Acked-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pSeries_reconfig.h     | 32 -----------
 arch/powerpc/kernel/prom.c                      |  6 +-
 arch/powerpc/platforms/pseries/dlpar.c          | 14 +++--
 arch/powerpc/platforms/pseries/hotplug-cpu.c    |  8 +--
 arch/powerpc/platforms/pseries/hotplug-memory.c | 60 ++++++++++++++------
 arch/powerpc/platforms/pseries/iommu.c          |  6 +-
 arch/powerpc/platforms/pseries/reconfig.c       | 68 ++---------------------
 arch/powerpc/platforms/pseries/setup.c          |  6 +-
 drivers/crypto/nx/nx-842.c                      | 20 +++----
 drivers/crypto/nx/nx.c                          |  1 -
 drivers/of/base.c                               | 74 +++++++++++++++++++++++--
 include/linux/of.h                              | 22 ++++++--
 12 files changed, 163 insertions(+), 154 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/pSeries_reconfig.h b/arch/powerpc/include/asm/pSeries_reconfig.h
index c07edfe98b98..adc00d2e75b0 100644
--- a/arch/powerpc/include/asm/pSeries_reconfig.h
+++ b/arch/powerpc/include/asm/pSeries_reconfig.h
@@ -2,43 +2,11 @@
 #define _PPC64_PSERIES_RECONFIG_H
 #ifdef __KERNEL__
 
-#include <linux/notifier.h>
-
-/*
- * Use this API if your code needs to know about OF device nodes being
- * added or removed on pSeries systems.
- */
-
-#define PSERIES_RECONFIG_ADD		0x0001
-#define PSERIES_RECONFIG_REMOVE		0x0002
-#define PSERIES_DRCONF_MEM_ADD		0x0003
-#define PSERIES_DRCONF_MEM_REMOVE	0x0004
-#define PSERIES_UPDATE_PROPERTY		0x0005
-
-/**
- * pSeries_reconfig_notify - Notifier value structure for OFDT property updates
- *
- * @node: Device tree node which owns the property being updated
- * @property: Updated property
- */
-struct pSeries_reconfig_prop_update {
-	struct device_node *node;
-	struct property *property;
-};
-
 #ifdef CONFIG_PPC_PSERIES
-extern int pSeries_reconfig_notifier_register(struct notifier_block *);
-extern void pSeries_reconfig_notifier_unregister(struct notifier_block *);
-extern int pSeries_reconfig_notify(unsigned long action, void *p);
 /* Not the best place to put this, will be fixed when we move some
  * of the rtas suspend-me stuff to pseries */
 extern void pSeries_coalesce_init(void);
 #else /* !CONFIG_PPC_PSERIES */
-static inline int pSeries_reconfig_notifier_register(struct notifier_block *nb)
-{
-	return 0;
-}
-static inline void pSeries_reconfig_notifier_unregister(struct notifier_block *nb) { }
 static inline void pSeries_coalesce_init(void) { }
 #endif /* CONFIG_PPC_PSERIES */
 
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 37725e86651e..6feb60c3c6e3 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -32,6 +32,7 @@
 #include <linux/debugfs.h>
 #include <linux/irq.h>
 #include <linux/memblock.h>
+#include <linux/of.h>
 
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -49,7 +50,6 @@
 #include <asm/btext.h>
 #include <asm/sections.h>
 #include <asm/machdep.h>
-#include <asm/pSeries_reconfig.h>
 #include <asm/pci-bridge.h>
 #include <asm/kexec.h>
 #include <asm/opal.h>
@@ -802,7 +802,7 @@ static int prom_reconfig_notifier(struct notifier_block *nb,
 	int err;
 
 	switch (action) {
-	case PSERIES_RECONFIG_ADD:
+	case OF_RECONFIG_ATTACH_NODE:
 		err = of_finish_dynamic_node(node);
 		if (err < 0)
 			printk(KERN_ERR "finish_node returned %d\n", err);
@@ -821,7 +821,7 @@ static struct notifier_block prom_reconfig_nb = {
 
 static int __init prom_reconfig_setup(void)
 {
-	return pSeries_reconfig_notifier_register(&prom_reconfig_nb);
+	return of_reconfig_notifier_register(&prom_reconfig_nb);
 }
 __initcall(prom_reconfig_setup);
 #endif
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index e36789bd4e6c..a1a7b9a67ffd 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -16,13 +16,13 @@
 #include <linux/spinlock.h>
 #include <linux/cpu.h>
 #include <linux/slab.h>
+#include <linux/of.h>
 #include "offline_states.h"
 
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/uaccess.h>
 #include <asm/rtas.h>
-#include <asm/pSeries_reconfig.h>
 
 struct cc_workarea {
 	u32	drc_index;
@@ -262,24 +262,26 @@ int dlpar_attach_node(struct device_node *dn)
 	if (!dn->parent)
 		return -ENOMEM;
 
-	rc = pSeries_reconfig_notify(PSERIES_RECONFIG_ADD, dn);
+	rc = of_attach_node(dn);
 	if (rc) {
 		printk(KERN_ERR "Failed to add device node %s\n",
 		       dn->full_name);
 		return rc;
 	}
 
-	of_attach_node(dn);
 	of_node_put(dn->parent);
 	return 0;
 }
 
 int dlpar_detach_node(struct device_node *dn)
 {
-	pSeries_reconfig_notify(PSERIES_RECONFIG_REMOVE, dn);
-	of_detach_node(dn);
-	of_node_put(dn); /* Must decrement the refcount */
+	int rc;
+
+	rc = of_detach_node(dn);
+	if (rc)
+		return rc;
 
+	of_node_put(dn); /* Must decrement the refcount */
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 64c97d8ac0c5..a38956269fbf 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -23,12 +23,12 @@
 #include <linux/delay.h>
 #include <linux/sched.h>	/* for idle_task_exit */
 #include <linux/cpu.h>
+#include <linux/of.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
 #include <asm/firmware.h>
 #include <asm/machdep.h>
 #include <asm/vdso_datapage.h>
-#include <asm/pSeries_reconfig.h>
 #include <asm/xics.h>
 #include "plpar_wrappers.h"
 #include "offline_states.h"
@@ -333,10 +333,10 @@ static int pseries_smp_notifier(struct notifier_block *nb,
 	int err = 0;
 
 	switch (action) {
-	case PSERIES_RECONFIG_ADD:
+	case OF_RECONFIG_ATTACH_NODE:
 		err = pseries_add_processor(node);
 		break;
-	case PSERIES_RECONFIG_REMOVE:
+	case OF_RECONFIG_DETACH_NODE:
 		pseries_remove_processor(node);
 		break;
 	}
@@ -399,7 +399,7 @@ static int __init pseries_cpu_hotplug_init(void)
 
 	/* Processors can be added/removed only on LPAR */
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
-		pSeries_reconfig_notifier_register(&pseries_smp_nb);
+		of_reconfig_notifier_register(&pseries_smp_nb);
 		cpu_maps_update_begin();
 		if (cede_offline_enabled && parse_cede_parameters() == 0) {
 			default_offline_state = CPU_STATE_INACTIVE;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index ecdb0a6b3171..2372c609fa2b 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -16,7 +16,6 @@
 
 #include <asm/firmware.h>
 #include <asm/machdep.h>
-#include <asm/pSeries_reconfig.h>
 #include <asm/sparsemem.h>
 
 static unsigned long get_memblock_size(void)
@@ -187,42 +186,69 @@ static int pseries_add_memory(struct device_node *np)
 	return (ret < 0) ? -EINVAL : 0;
 }
 
-static int pseries_drconf_memory(unsigned long *base, unsigned int action)
+static int pseries_update_drconf_memory(struct of_prop_reconfig *pr)
 {
+	struct of_drconf_cell *new_drmem, *old_drmem;
 	unsigned long memblock_size;
-	int rc;
+	u32 entries;
+	u32 *p;
+	int i, rc = -EINVAL;
 
 	memblock_size = get_memblock_size();
 	if (!memblock_size)
 		return -EINVAL;
 
-	if (action == PSERIES_DRCONF_MEM_ADD) {
-		rc = memblock_add(*base, memblock_size);
-		rc = (rc < 0) ? -EINVAL : 0;
-	} else if (action == PSERIES_DRCONF_MEM_REMOVE) {
-		rc = pseries_remove_memblock(*base, memblock_size);
-	} else {
-		rc = -EINVAL;
+	p = (u32 *)of_get_property(pr->dn, "ibm,dynamic-memory", NULL);
+	if (!p)
+		return -EINVAL;
+
+	/* The first int of the property is the number of lmb's described
+	 * by the property. This is followed by an array of of_drconf_cell
+	 * entries. Get the niumber of entries and skip to the array of
+	 * of_drconf_cell's.
+	 */
+	entries = *p++;
+	old_drmem = (struct of_drconf_cell *)p;
+
+	p = (u32 *)pr->prop->value;
+	p++;
+	new_drmem = (struct of_drconf_cell *)p;
+
+	for (i = 0; i < entries; i++) {
+		if ((old_drmem[i].flags & DRCONF_MEM_ASSIGNED) &&
+		    (!(new_drmem[i].flags & DRCONF_MEM_ASSIGNED))) {
+			rc = pseries_remove_memblock(old_drmem[i].base_addr,
+						     memblock_size);
+			break;
+		} else if ((!(old_drmem[i].flags & DRCONF_MEM_ASSIGNED)) &&
+			   (new_drmem[i].flags & DRCONF_MEM_ASSIGNED)) {
+			rc = memblock_add(old_drmem[i].base_addr,
+					  memblock_size);
+			rc = (rc < 0) ? -EINVAL : 0;
+			break;
+		}
 	}
 
 	return rc;
 }
 
 static int pseries_memory_notifier(struct notifier_block *nb,
-				unsigned long action, void *node)
+				   unsigned long action, void *node)
 {
+	struct of_prop_reconfig *pr;
 	int err = 0;
 
 	switch (action) {
-	case PSERIES_RECONFIG_ADD:
+	case OF_RECONFIG_ATTACH_NODE:
 		err = pseries_add_memory(node);
 		break;
-	case PSERIES_RECONFIG_REMOVE:
+	case OF_RECONFIG_DETACH_NODE:
 		err = pseries_remove_memory(node);
 		break;
-	case PSERIES_DRCONF_MEM_ADD:
-	case PSERIES_DRCONF_MEM_REMOVE:
-		err = pseries_drconf_memory(node, action);
+	case OF_RECONFIG_UPDATE_PROPERTY:
+		pr = (struct of_prop_reconfig *)node;
+		if (!strcmp(pr->prop->name, "ibm,dynamic-memory"))
+			err = pseries_update_drconf_memory(pr);
 		break;
 	}
 	return notifier_from_errno(err);
@@ -235,7 +261,7 @@ static struct notifier_block pseries_mem_nb = {
 static int __init pseries_memory_hotplug_init(void)
 {
 	if (firmware_has_feature(FW_FEATURE_LPAR))
-		pSeries_reconfig_notifier_register(&pseries_mem_nb);
+		of_reconfig_notifier_register(&pseries_mem_nb);
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 6153eea27ce7..da5594c441e4 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -36,13 +36,13 @@
 #include <linux/dma-mapping.h>
 #include <linux/crash_dump.h>
 #include <linux/memory.h>
+#include <linux/of.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
 #include <asm/iommu.h>
 #include <asm/pci-bridge.h>
 #include <asm/machdep.h>
-#include <asm/pSeries_reconfig.h>
 #include <asm/firmware.h>
 #include <asm/tce.h>
 #include <asm/ppc-pci.h>
@@ -1294,7 +1294,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
 	struct direct_window *window;
 
 	switch (action) {
-	case PSERIES_RECONFIG_REMOVE:
+	case OF_RECONFIG_DETACH_NODE:
 		if (pci && pci->iommu_table)
 			iommu_free_table(pci->iommu_table, np->full_name);
 
@@ -1357,7 +1357,7 @@ void iommu_init_early_pSeries(void)
 	}
 
 
-	pSeries_reconfig_notifier_register(&iommu_reconfig_nb);
+	of_reconfig_notifier_register(&iommu_reconfig_nb);
 	register_memory_notifier(&iommu_mem_nb);
 
 	set_pci_dma_ops(&dma_iommu_ops);
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index f99f1ca8035b..720a0cc2e69f 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -16,11 +16,11 @@
 #include <linux/notifier.h>
 #include <linux/proc_fs.h>
 #include <linux/slab.h>
+#include <linux/of.h>
 
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/uaccess.h>
-#include <asm/pSeries_reconfig.h>
 #include <asm/mmu.h>
 
 /**
@@ -55,28 +55,6 @@ static struct device_node *derive_parent(const char *path)
 	return parent;
 }
 
-static BLOCKING_NOTIFIER_HEAD(pSeries_reconfig_chain);
-
-int pSeries_reconfig_notifier_register(struct notifier_block *nb)
-{
-	return blocking_notifier_chain_register(&pSeries_reconfig_chain, nb);
-}
-EXPORT_SYMBOL_GPL(pSeries_reconfig_notifier_register);
-
-void pSeries_reconfig_notifier_unregister(struct notifier_block *nb)
-{
-	blocking_notifier_chain_unregister(&pSeries_reconfig_chain, nb);
-}
-EXPORT_SYMBOL_GPL(pSeries_reconfig_notifier_unregister);
-
-int pSeries_reconfig_notify(unsigned long action, void *p)
-{
-	int err = blocking_notifier_call_chain(&pSeries_reconfig_chain,
-						action, p);
-
-	return notifier_to_errno(err);
-}
-
 static int pSeries_reconfig_add_node(const char *path, struct property *proplist)
 {
 	struct device_node *np;
@@ -100,13 +78,12 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist
 		goto out_err;
 	}
 
-	err = pSeries_reconfig_notify(PSERIES_RECONFIG_ADD, np);
+	err = of_attach_node(np);
 	if (err) {
 		printk(KERN_ERR "Failed to add device node %s\n", path);
 		goto out_err;
 	}
 
-	of_attach_node(np);
 	of_node_put(np->parent);
 
 	return 0;
@@ -134,9 +111,7 @@ static int pSeries_reconfig_remove_node(struct device_node *np)
 		return -EBUSY;
 	}
 
-	pSeries_reconfig_notify(PSERIES_RECONFIG_REMOVE, np);
 	of_detach_node(np);
-
 	of_node_put(parent);
 	of_node_put(np); /* Must decrement the refcount */
 	return 0;
@@ -381,10 +356,9 @@ static int do_remove_property(char *buf, size_t bufsize)
 static int do_update_property(char *buf, size_t bufsize)
 {
 	struct device_node *np;
-	struct pSeries_reconfig_prop_update upd_value;
 	unsigned char *value;
 	char *name, *end, *next_prop;
-	int rc, length;
+	int length;
 	struct property *newprop;
 	buf = parse_node(buf, bufsize, &np);
 	end = buf + bufsize;
@@ -406,41 +380,7 @@ static int do_update_property(char *buf, size_t bufsize)
 	if (!strcmp(name, "slb-size") || !strcmp(name, "ibm,slb-size"))
 		slb_set_size(*(int *)value);
 
-	upd_value.node = np;
-	upd_value.property = newprop;
-	pSeries_reconfig_notify(PSERIES_UPDATE_PROPERTY, &upd_value);
-
-	rc = prom_update_property(np, newprop);
-	if (rc)
-		return rc;
-
-	/* For memory under the ibm,dynamic-reconfiguration-memory node
-	 * of the device tree, adding and removing memory is just an update
-	 * to the ibm,dynamic-memory property instead of adding/removing a
-	 * memory node in the device tree.  For these cases we still need to
-	 * involve the notifier chain.
-	 */
-	if (!strcmp(name, "ibm,dynamic-memory")) {
-		int action;
-
-		next_prop = parse_next_property(next_prop, end, &name,
-						&length, &value);
-		if (!next_prop)
-			return -EINVAL;
-
-		if (!strcmp(name, "add"))
-			action = PSERIES_DRCONF_MEM_ADD;
-		else
-			action = PSERIES_DRCONF_MEM_REMOVE;
-
-		rc = pSeries_reconfig_notify(action, value);
-		if (rc) {
-			prom_update_property(np, newprop);
-			return rc;
-		}
-	}
-
-	return 0;
+	return prom_update_property(np, newprop);
 }
 
 /**
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index e3cb7ae61658..e1a5b8a32d25 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -40,6 +40,7 @@
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
 #include <linux/cpuidle.h>
+#include <linux/of.h>
 
 #include <asm/mmu.h>
 #include <asm/processor.h>
@@ -63,7 +64,6 @@
 #include <asm/smp.h>
 #include <asm/firmware.h>
 #include <asm/eeh.h>
-#include <asm/pSeries_reconfig.h>
 
 #include "plpar_wrappers.h"
 #include "pseries.h"
@@ -258,7 +258,7 @@ static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long act
 	int err = NOTIFY_OK;
 
 	switch (action) {
-	case PSERIES_RECONFIG_ADD:
+	case OF_RECONFIG_ATTACH_NODE:
 		pci = np->parent->data;
 		if (pci) {
 			update_dn_pci_info(np, pci->phb);
@@ -389,7 +389,7 @@ static void __init pSeries_setup_arch(void)
 	/* Find and initialize PCI host bridges */
 	init_pci_config_tokens();
 	find_and_init_phbs();
-	pSeries_reconfig_notifier_register(&pci_dn_reconfig_nb);
+	of_reconfig_notifier_register(&pci_dn_reconfig_nb);
 
 	pSeries_nvram_init();
 
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 0ce625738677..6c4c000671c5 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -28,7 +28,6 @@
 #include <linux/slab.h>
 
 #include <asm/page.h>
-#include <asm/pSeries_reconfig.h>
 #include <asm/vio.h>
 
 #include "nx_csbcpb.h" /* struct nx_csbcpb */
@@ -1014,26 +1013,23 @@ error_out:
  *	NOTIFY_BAD encoded with error number on failure, use
  *		notifier_to_errno() to decode this value
  */
-static int nx842_OF_notifier(struct notifier_block *np,
-					unsigned long action,
-					void *update)
+static int nx842_OF_notifier(struct notifier_block *np, unsigned long action,
+			     void *update)
 {
-	struct pSeries_reconfig_prop_update *upd;
+	struct of_prop_reconfig *upd = update;
 	struct nx842_devdata *local_devdata;
 	struct device_node *node = NULL;
 
-	upd = (struct pSeries_reconfig_prop_update *)update;
-
 	rcu_read_lock();
 	local_devdata = rcu_dereference(devdata);
 	if (local_devdata)
 		node = local_devdata->dev->of_node;
 
 	if (local_devdata &&
-			action == PSERIES_UPDATE_PROPERTY &&
-			!strcmp(upd->node->name, node->name)) {
+			action == OF_RECONFIG_UPDATE_PROPERTY &&
+			!strcmp(upd->dn->name, node->name)) {
 		rcu_read_unlock();
-		nx842_OF_upd(upd->property);
+		nx842_OF_upd(upd->prop);
 	} else
 		rcu_read_unlock();
 
@@ -1182,7 +1178,7 @@ static int __init nx842_probe(struct vio_dev *viodev,
 	synchronize_rcu();
 	kfree(old_devdata);
 
-	pSeries_reconfig_notifier_register(&nx842_of_nb);
+	of_reconfig_notifier_register(&nx842_of_nb);
 
 	ret = nx842_OF_upd(NULL);
 	if (ret && ret != -ENODEV) {
@@ -1228,7 +1224,7 @@ static int __exit nx842_remove(struct vio_dev *viodev)
 	spin_lock_irqsave(&devdata_mutex, flags);
 	old_devdata = rcu_dereference_check(devdata,
 			lockdep_is_held(&devdata_mutex));
-	pSeries_reconfig_notifier_unregister(&nx842_of_nb);
+	of_reconfig_notifier_unregister(&nx842_of_nb);
 	rcu_assign_pointer(devdata, NULL);
 	spin_unlock_irqrestore(&devdata_mutex, flags);
 	synchronize_rcu();
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index 638110efae9b..f7a8a16aa7d3 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -33,7 +33,6 @@
 #include <linux/scatterlist.h>
 #include <linux/device.h>
 #include <linux/of.h>
-#include <asm/pSeries_reconfig.h>
 #include <asm/hvcall.h>
 #include <asm/vio.h>
 
diff --git a/drivers/of/base.c b/drivers/of/base.c
index bbd073f53c9f..87b63850e8dc 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1028,6 +1028,24 @@ int of_parse_phandle_with_args(struct device_node *np, const char *list_name,
 }
 EXPORT_SYMBOL(of_parse_phandle_with_args);
 
+#if defined(CONFIG_OF_DYNAMIC)
+static int of_property_notify(int action, struct device_node *np,
+			      struct property *prop)
+{
+	struct of_prop_reconfig pr;
+
+	pr.dn = np;
+	pr.prop = prop;
+	return of_reconfig_notify(action, &pr);
+}
+#else
+static int of_property_notify(int action, struct device_node *np,
+			      struct property *prop)
+{
+	return 0;
+}
+#endif
+
 /**
  * prom_add_property - Add a property to a node
  */
@@ -1035,6 +1053,11 @@ int prom_add_property(struct device_node *np, struct property *prop)
 {
 	struct property **next;
 	unsigned long flags;
+	int rc;
+
+	rc = of_property_notify(OF_RECONFIG_ADD_PROPERTY, np, prop);
+	if (rc)
+		return rc;
 
 	prop->next = NULL;
 	write_lock_irqsave(&devtree_lock, flags);
@@ -1072,6 +1095,11 @@ int prom_remove_property(struct device_node *np, struct property *prop)
 	struct property **next;
 	unsigned long flags;
 	int found = 0;
+	int rc;
+
+	rc = of_property_notify(OF_RECONFIG_REMOVE_PROPERTY, np, prop);
+	if (rc)
+		return rc;
 
 	write_lock_irqsave(&devtree_lock, flags);
 	next = &np->properties;
@@ -1114,7 +1142,11 @@ int prom_update_property(struct device_node *np,
 {
 	struct property **next, *oldprop;
 	unsigned long flags;
-	int found = 0;
+	int rc, found = 0;
+
+	rc = of_property_notify(OF_RECONFIG_UPDATE_PROPERTY, np, newprop);
+	if (rc)
+		return rc;
 
 	if (!newprop->name)
 		return -EINVAL;
@@ -1160,6 +1192,26 @@ int prom_update_property(struct device_node *np,
  * device tree nodes.
  */
 
+static BLOCKING_NOTIFIER_HEAD(of_reconfig_chain);
+
+int of_reconfig_notifier_register(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&of_reconfig_chain, nb);
+}
+
+int of_reconfig_notifier_unregister(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&of_reconfig_chain, nb);
+}
+
+int of_reconfig_notify(unsigned long action, void *p)
+{
+	int rc;
+
+	rc = blocking_notifier_call_chain(&of_reconfig_chain, action, p);
+	return notifier_to_errno(rc);
+}
+
 #ifdef CONFIG_PROC_DEVICETREE
 static void of_add_proc_dt_entry(struct device_node *dn)
 {
@@ -1179,9 +1231,14 @@ static void of_add_proc_dt_entry(struct device_node *dn)
 /**
  * of_attach_node - Plug a device node into the tree and global list.
  */
-void of_attach_node(struct device_node *np)
+int of_attach_node(struct device_node *np)
 {
 	unsigned long flags;
+	int rc;
+
+	rc = of_reconfig_notify(OF_RECONFIG_ATTACH_NODE, np);
+	if (rc)
+		return rc;
 
 	write_lock_irqsave(&devtree_lock, flags);
 	np->sibling = np->parent->child;
@@ -1191,6 +1248,7 @@ void of_attach_node(struct device_node *np)
 	write_unlock_irqrestore(&devtree_lock, flags);
 
 	of_add_proc_dt_entry(np);
+	return 0;
 }
 
 #ifdef CONFIG_PROC_DEVICETREE
@@ -1220,23 +1278,28 @@ static void of_remove_proc_dt_entry(struct device_node *dn)
  * The caller must hold a reference to the node.  The memory associated with
  * the node is not freed until its refcount goes to zero.
  */
-void of_detach_node(struct device_node *np)
+int of_detach_node(struct device_node *np)
 {
 	struct device_node *parent;
 	unsigned long flags;
+	int rc = 0;
+
+	rc = of_reconfig_notify(OF_RECONFIG_DETACH_NODE, np);
+	if (rc)
+		return rc;
 
 	write_lock_irqsave(&devtree_lock, flags);
 
 	if (of_node_check_flag(np, OF_DETACHED)) {
 		/* someone already detached it */
 		write_unlock_irqrestore(&devtree_lock, flags);
-		return;
+		return rc;
 	}
 
 	parent = np->parent;
 	if (!parent) {
 		write_unlock_irqrestore(&devtree_lock, flags);
-		return;
+		return rc;
 	}
 
 	if (allnodes == np)
@@ -1265,6 +1328,7 @@ void of_detach_node(struct device_node *np)
 	write_unlock_irqrestore(&devtree_lock, flags);
 
 	of_remove_proc_dt_entry(np);
+	return rc;
 }
 #endif /* defined(CONFIG_OF_DYNAMIC) */
 
diff --git a/include/linux/of.h b/include/linux/of.h
index 72843b72a2b2..fb5d87b66e3e 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -22,6 +22,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/spinlock.h>
 #include <linux/topology.h>
+#include <linux/notifier.h>
 
 #include <asm/byteorder.h>
 #include <asm/errno.h>
@@ -272,11 +273,24 @@ extern int prom_remove_property(struct device_node *np, struct property *prop);
 extern int prom_update_property(struct device_node *np,
 				struct property *newprop);
 
-#if defined(CONFIG_OF_DYNAMIC)
 /* For updating the device tree at runtime */
-extern void of_attach_node(struct device_node *);
-extern void of_detach_node(struct device_node *);
-#endif
+#define OF_RECONFIG_ATTACH_NODE		0x0001
+#define OF_RECONFIG_DETACH_NODE		0x0002
+#define OF_RECONFIG_ADD_PROPERTY	0x0003
+#define OF_RECONFIG_REMOVE_PROPERTY	0x0004
+#define OF_RECONFIG_UPDATE_PROPERTY	0x0005
+
+struct of_prop_reconfig {
+	struct device_node	*dn;
+	struct property		*prop;
+};
+
+extern int of_reconfig_notifier_register(struct notifier_block *);
+extern int of_reconfig_notifier_unregister(struct notifier_block *);
+extern int of_reconfig_notify(unsigned long, void *);
+
+extern int of_attach_node(struct device_node *);
+extern int of_detach_node(struct device_node *);
 
 #define of_match_ptr(_ptr)	(_ptr)
 
-- 
cgit v1.2.3-55-g7522


From 79d1c712958f94372482ad74578b00f44e744c12 Mon Sep 17 00:00:00 2001
From: Nathan Fontenot
Date: Tue, 2 Oct 2012 16:58:46 +0000
Subject: powerpc+of: Rename the drivers/of prom_* functions to of_*

Rename the prom_*_property routines of the generic OF code to of_*_property.
This brings them in line with the naming used by the rest of the OF code.

Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Acked-by: Geoff Levand <geoff@infradead.org>
Acked-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/arm/mach-mxs/mach-mxs.c              |  2 +-
 arch/powerpc/kernel/machine_kexec.c       | 14 +++++++-------
 arch/powerpc/kernel/machine_kexec_64.c    |  8 ++++----
 arch/powerpc/kernel/pci_32.c              |  2 +-
 arch/powerpc/platforms/85xx/p1022_ds.c    |  6 +++---
 arch/powerpc/platforms/ps3/os-area.c      |  6 +++---
 arch/powerpc/platforms/pseries/iommu.c    |  4 ++--
 arch/powerpc/platforms/pseries/mobility.c |  4 ++--
 arch/powerpc/platforms/pseries/reconfig.c |  6 +++---
 drivers/macintosh/smu.c                   |  2 +-
 drivers/of/base.c                         | 15 +++++++--------
 include/linux/of.h                        |  7 +++----
 12 files changed, 37 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c
index 4748ec551a68..d61b915ce52c 100644
--- a/arch/arm/mach-mxs/mach-mxs.c
+++ b/arch/arm/mach-mxs/mach-mxs.c
@@ -211,7 +211,7 @@ static void __init update_fec_mac_prop(enum mac_oui oui)
 		macaddr[4] = (val >> 8) & 0xff;
 		macaddr[5] = (val >> 0) & 0xff;
 
-		prom_update_property(np, newmac);
+		of_update_property(np, newmac);
 	}
 }
 
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index fa9f6c72f557..e1ec57e87b3b 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -218,23 +218,23 @@ static void __init export_crashk_values(struct device_node *node)
 	 * be sure what's in them, so remove them. */
 	prop = of_find_property(node, "linux,crashkernel-base", NULL);
 	if (prop)
-		prom_remove_property(node, prop);
+		of_remove_property(node, prop);
 
 	prop = of_find_property(node, "linux,crashkernel-size", NULL);
 	if (prop)
-		prom_remove_property(node, prop);
+		of_remove_property(node, prop);
 
 	if (crashk_res.start != 0) {
-		prom_add_property(node, &crashk_base_prop);
+		of_add_property(node, &crashk_base_prop);
 		crashk_size = resource_size(&crashk_res);
-		prom_add_property(node, &crashk_size_prop);
+		of_add_property(node, &crashk_size_prop);
 	}
 
 	/*
 	 * memory_limit is required by the kexec-tools to limit the
 	 * crash regions to the actual memory used.
 	 */
-	prom_update_property(node, &memory_limit_prop);
+	of_update_property(node, &memory_limit_prop);
 }
 
 static int __init kexec_setup(void)
@@ -249,11 +249,11 @@ static int __init kexec_setup(void)
 	/* remove any stale properties so ours can be found */
 	prop = of_find_property(node, kernel_end_prop.name, NULL);
 	if (prop)
-		prom_remove_property(node, prop);
+		of_remove_property(node, prop);
 
 	/* information needed by userspace when using default_machine_kexec */
 	kernel_end = __pa(_end);
-	prom_add_property(node, &kernel_end_prop);
+	of_add_property(node, &kernel_end_prop);
 
 	export_crashk_values(node);
 
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index d7f609086a99..7206701b1ff1 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -389,14 +389,14 @@ static int __init export_htab_values(void)
 	/* remove any stale propertys so ours can be found */
 	prop = of_find_property(node, htab_base_prop.name, NULL);
 	if (prop)
-		prom_remove_property(node, prop);
+		of_remove_property(node, prop);
 	prop = of_find_property(node, htab_size_prop.name, NULL);
 	if (prop)
-		prom_remove_property(node, prop);
+		of_remove_property(node, prop);
 
 	htab_base = __pa(htab_address);
-	prom_add_property(node, &htab_base_prop);
-	prom_add_property(node, &htab_size_prop);
+	of_add_property(node, &htab_base_prop);
+	of_add_property(node, &htab_size_prop);
 
 	of_node_put(node);
 	return 0;
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 4b06ec5a502e..64f526a321f5 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -208,7 +208,7 @@ pci_create_OF_bus_map(void)
 		of_prop->name = "pci-OF-bus-map";
 		of_prop->length = 256;
 		of_prop->value = &of_prop[1];
-		prom_add_property(dn, of_prop);
+		of_add_property(dn, of_prop);
 		of_node_put(dn);
 	}
 }
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 848a3e98e1c1..8fb12570b2f5 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -539,7 +539,7 @@ static void __init p1022_ds_setup_arch(void)
 				};
 
 				/*
-				 * prom_update_property() is called before
+				 * of_update_property() is called before
 				 * kmalloc() is available, so the 'new' object
 				 * should be allocated in the global area.
 				 * The easiest way is to do that is to
@@ -548,7 +548,7 @@ static void __init p1022_ds_setup_arch(void)
 				 */
 				pr_info("p1022ds: disabling %s node",
 					np2->full_name);
-				prom_update_property(np2, &nor_status);
+				of_update_property(np2, &nor_status);
 				of_node_put(np2);
 			}
 
@@ -564,7 +564,7 @@ static void __init p1022_ds_setup_arch(void)
 
 				pr_info("p1022ds: disabling %s node",
 					np2->full_name);
-				prom_update_property(np2, &nand_status);
+				of_update_property(np2, &nand_status);
 				of_node_put(np2);
 			}
 
diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c
index 56d26bc4fd41..09787139834d 100644
--- a/arch/powerpc/platforms/ps3/os-area.c
+++ b/arch/powerpc/platforms/ps3/os-area.c
@@ -280,13 +280,13 @@ static void os_area_set_property(struct device_node *node,
 
 	if (tmp) {
 		pr_debug("%s:%d found %s\n", __func__, __LINE__, prop->name);
-		prom_remove_property(node, tmp);
+		of_remove_property(node, tmp);
 	}
 
-	result = prom_add_property(node, prop);
+	result = of_add_property(node, prop);
 
 	if (result)
-		pr_debug("%s:%d prom_set_property failed\n", __func__,
+		pr_debug("%s:%d of_set_property failed\n", __func__,
 			__LINE__);
 }
 
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index da5594c441e4..e2685badb5db 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -760,7 +760,7 @@ static void remove_ddw(struct device_node *np)
 	__remove_ddw(np, ddw_avail, liobn);
 
 delprop:
-	ret = prom_remove_property(np, win64);
+	ret = of_remove_property(np, win64);
 	if (ret)
 		pr_warning("%s: failed to remove direct window property: %d\n",
 			np->full_name, ret);
@@ -1070,7 +1070,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		goto out_free_window;
 	}
 
-	ret = prom_add_property(pdn, win64);
+	ret = of_add_property(pdn, win64);
 	if (ret) {
 		dev_err(&dev->dev, "unable to add dma window property for %s: %d",
 			 pdn->full_name, ret);
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index dd30b12edfe4..6573808cc5f3 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -116,7 +116,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop,
 	}
 
 	if (!more) {
-		prom_update_property(dn, new_prop);
+		of_update_property(dn, new_prop);
 		new_prop = NULL;
 	}
 
@@ -172,7 +172,7 @@ static int update_dt_node(u32 phandle)
 
 			case 0x80000000:
 				prop = of_find_property(dn, prop_name, NULL);
-				prom_remove_property(dn, prop);
+				of_remove_property(dn, prop);
 				prop = NULL;
 				break;
 
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 720a0cc2e69f..30b358dc2beb 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -326,7 +326,7 @@ static int do_add_property(char *buf, size_t bufsize)
 	if (!prop)
 		return -ENOMEM;
 
-	prom_add_property(np, prop);
+	of_add_property(np, prop);
 
 	return 0;
 }
@@ -350,7 +350,7 @@ static int do_remove_property(char *buf, size_t bufsize)
 
 	prop = of_find_property(np, buf, NULL);
 
-	return prom_remove_property(np, prop);
+	return of_remove_property(np, prop);
 }
 
 static int do_update_property(char *buf, size_t bufsize)
@@ -380,7 +380,7 @@ static int do_update_property(char *buf, size_t bufsize)
 	if (!strcmp(name, "slb-size") || !strcmp(name, "ibm,slb-size"))
 		slb_set_size(*(int *)value);
 
-	return prom_update_property(np, newprop);
+	return of_update_property(np, newprop);
 }
 
 /**
diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index 7d5a6b40b31c..5b939509db3b 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -997,7 +997,7 @@ static struct smu_sdbp_header *smu_create_sdb_partition(int id)
 		       "%02x !\n", id, hdr->id);
 		goto failure;
 	}
-	if (prom_add_property(smu->of_node, prop)) {
+	if (of_add_property(smu->of_node, prop)) {
 		printk(KERN_DEBUG "SMU: Failed creating sdb-partition-%02x "
 		       "property !\n", id);
 		goto failure;
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 87b63850e8dc..02d94c4ea83c 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1047,9 +1047,9 @@ static int of_property_notify(int action, struct device_node *np,
 #endif
 
 /**
- * prom_add_property - Add a property to a node
+ * of_add_property - Add a property to a node
  */
-int prom_add_property(struct device_node *np, struct property *prop)
+int of_add_property(struct device_node *np, struct property *prop)
 {
 	struct property **next;
 	unsigned long flags;
@@ -1083,14 +1083,14 @@ int prom_add_property(struct device_node *np, struct property *prop)
 }
 
 /**
- * prom_remove_property - Remove a property from a node.
+ * of_remove_property - Remove a property from a node.
  *
  * Note that we don't actually remove it, since we have given out
  * who-knows-how-many pointers to the data using get-property.
  * Instead we just move the property to the "dead properties"
  * list, so it won't be found any more.
  */
-int prom_remove_property(struct device_node *np, struct property *prop)
+int of_remove_property(struct device_node *np, struct property *prop)
 {
 	struct property **next;
 	unsigned long flags;
@@ -1129,7 +1129,7 @@ int prom_remove_property(struct device_node *np, struct property *prop)
 }
 
 /*
- * prom_update_property - Update a property in a node, if the property does
+ * of_update_property - Update a property in a node, if the property does
  * not exist, add it.
  *
  * Note that we don't actually remove it, since we have given out
@@ -1137,8 +1137,7 @@ int prom_remove_property(struct device_node *np, struct property *prop)
  * Instead we just move the property to the "dead properties" list,
  * and add the new property to the property list
  */
-int prom_update_property(struct device_node *np,
-			 struct property *newprop)
+int of_update_property(struct device_node *np, struct property *newprop)
 {
 	struct property **next, *oldprop;
 	unsigned long flags;
@@ -1153,7 +1152,7 @@ int prom_update_property(struct device_node *np,
 
 	oldprop = of_find_property(np, newprop->name, NULL);
 	if (!oldprop)
-		return prom_add_property(np, newprop);
+		return of_add_property(np, newprop);
 
 	write_lock_irqsave(&devtree_lock, flags);
 	next = &np->properties;
diff --git a/include/linux/of.h b/include/linux/of.h
index fb5d87b66e3e..a093b2fe5dfb 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -268,10 +268,9 @@ extern int of_alias_get_id(struct device_node *np, const char *stem);
 
 extern int of_machine_is_compatible(const char *compat);
 
-extern int prom_add_property(struct device_node* np, struct property* prop);
-extern int prom_remove_property(struct device_node *np, struct property *prop);
-extern int prom_update_property(struct device_node *np,
-				struct property *newprop);
+extern int of_add_property(struct device_node *np, struct property *prop);
+extern int of_remove_property(struct device_node *np, struct property *prop);
+extern int of_update_property(struct device_node *np, struct property *newprop);
 
 /* For updating the device tree at runtime */
 #define OF_RECONFIG_ATTACH_NODE		0x0001
-- 
cgit v1.2.3-55-g7522


From cfa323b6b98f44ddf46cc987f74a23dcab697134 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Wed, 14 Nov 2012 05:13:58 +0000
Subject: ip6tnl/rtnl: add IFLA_IPTUN_PROTO on dump

IPv6 tunnels can have three mode: 4in6, 6in6 and xin6.
This information was missing in the netlink message.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_tunnel.h | 1 +
 net/ipv6/ip6_tunnel.c          | 5 ++++-
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index c1bf0b5a8da1..f5ea6b7b651f 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -47,6 +47,7 @@ enum {
 	IFLA_IPTUN_ENCAP_LIMIT,
 	IFLA_IPTUN_FLOWINFO,
 	IFLA_IPTUN_FLAGS,
+	IFLA_IPTUN_PROTO,
 	__IFLA_IPTUN_MAX,
 };
 #define IFLA_IPTUN_MAX	(__IFLA_IPTUN_MAX - 1)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 8db4d9b7ab14..929ba0b5cc9b 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1515,6 +1515,8 @@ static size_t ip6_get_size(const struct net_device *dev)
 		nla_total_size(4) +
 		/* IFLA_IPTUN_FLAGS */
 		nla_total_size(4) +
+		/* IFLA_IPTUN_PROTO */
+		nla_total_size(1) +
 		0;
 }
 
@@ -1531,7 +1533,8 @@ static int ip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) ||
 	    nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) ||
 	    nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) ||
-	    nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags))
+	    nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) ||
+	    nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto))
 		goto nla_put_failure;
 	return 0;
 
-- 
cgit v1.2.3-55-g7522


From befe2aa1b2c7b9b7e20e97906f99b58475608867 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Wed, 14 Nov 2012 05:14:02 +0000
Subject: ipip/rtnl: add IFLA_IPTUN_PMTUDISC on dump

This parameter was missing in the dump.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_tunnel.h | 1 +
 net/ipv4/ipip.c                | 6 +++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index f5ea6b7b651f..5ab0c8ddc2bc 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -48,6 +48,7 @@ enum {
 	IFLA_IPTUN_FLOWINFO,
 	IFLA_IPTUN_FLAGS,
 	IFLA_IPTUN_PROTO,
+	IFLA_IPTUN_PMTUDISC,
 	__IFLA_IPTUN_MAX,
 };
 #define IFLA_IPTUN_MAX	(__IFLA_IPTUN_MAX - 1)
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 4be88cc98957..1fc0ea4786b9 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -835,6 +835,8 @@ static size_t ipip_get_size(const struct net_device *dev)
 		nla_total_size(1) +
 		/* IFLA_IPTUN_TOS */
 		nla_total_size(1) +
+		/* IFLA_IPTUN_PMTUDISC */
+		nla_total_size(1) +
 		0;
 }
 
@@ -847,7 +849,9 @@ static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
 	    nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) ||
-	    nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos))
+	    nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) ||
+	    nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
+		       !!(parm->iph.frag_off & htons(IP_DF))))
 		goto nla_put_failure;
 	return 0;
 
-- 
cgit v1.2.3-55-g7522


From 3d567e0e291c4ffd041cf653aea3c38a1d5f4620 Mon Sep 17 00:00:00 2001
From: Nithin Nayak Sujir
Date: Wed, 14 Nov 2012 14:44:26 +0000
Subject: tg3: Set 10_100_ONLY flag for additional 10/100 Mbps devices

- Also refactor the conditional to use the existing tg3_pci_tbl array.
- Set flags in the driver_data field of the pci_device_id structure to
identify these devices.
- Add PCI_DEVICE_SUB() to pci.h to declare PCI 4-part IDs to match these
devices.

Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 87 +++++++++++++++++++++++++------------
 drivers/net/ethernet/broadcom/tg3.h |  5 +++
 include/linux/pci.h                 | 14 ++++++
 3 files changed, 79 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 038ce0215e3e..8d4581bdba3c 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -226,6 +226,9 @@ static int tg3_debug = -1;	/* -1 == use TG3_DEF_MSG_ENABLE as value */
 module_param(tg3_debug, int, 0);
 MODULE_PARM_DESC(tg3_debug, "Tigon3 bitmapped debugging message enable value");
 
+#define TG3_DRV_DATA_FLAG_10_100_ONLY	0x0001
+#define TG3_DRV_DATA_FLAG_5705_10_100	0x0002
+
 static DEFINE_PCI_DEVICE_TABLE(tg3_pci_tbl) = {
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5700)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5701)},
@@ -245,20 +248,28 @@ static DEFINE_PCI_DEVICE_TABLE(tg3_pci_tbl) = {
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5782)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5788)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5789)},
-	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5901)},
-	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5901_2)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5901),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY |
+			TG3_DRV_DATA_FLAG_5705_10_100},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5901_2),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY |
+			TG3_DRV_DATA_FLAG_5705_10_100},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5704S_2)},
-	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705F)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705F),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY |
+			TG3_DRV_DATA_FLAG_5705_10_100},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5721)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5722)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5751)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5751M)},
-	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5751F)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5751F),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5752)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5752M)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5753)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5753M)},
-	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5753F)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5753F),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5754)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5754M)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5755)},
@@ -266,8 +277,13 @@ static DEFINE_PCI_DEVICE_TABLE(tg3_pci_tbl) = {
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5756)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5786)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5787)},
+	{PCI_DEVICE_SUB(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5787M,
+			PCI_VENDOR_ID_LENOVO,
+			TG3PCI_SUBDEVICE_ID_LENOVO_5787M),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5787M)},
-	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5787F)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5787F),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5714)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5714S)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5715)},
@@ -286,9 +302,16 @@ static DEFINE_PCI_DEVICE_TABLE(tg3_pci_tbl) = {
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5761SE)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5785_G)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5785_F)},
+	{PCI_DEVICE_SUB(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57780,
+			PCI_VENDOR_ID_AI, TG3PCI_SUBDEVICE_ID_ACER_57780_A),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY},
+	{PCI_DEVICE_SUB(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57780,
+			PCI_VENDOR_ID_AI, TG3PCI_SUBDEVICE_ID_ACER_57780_B),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57780)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57760)},
-	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57790)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57790),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57788)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5717)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5717_C)},
@@ -297,8 +320,10 @@ static DEFINE_PCI_DEVICE_TABLE(tg3_pci_tbl) = {
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57785)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57761)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57765)},
-	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57791)},
-	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57795)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57791),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57795),
+	 .driver_data = TG3_DRV_DATA_FLAG_10_100_ONLY},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5719)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5720)},
 	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57762)},
@@ -14466,7 +14491,30 @@ static void __devinit tg3_detect_asic_rev(struct tg3 *tp, u32 misc_ctrl_reg)
 		tg3_flag_set(tp, 5705_PLUS);
 }
 
-static int __devinit tg3_get_invariants(struct tg3 *tp)
+static bool tg3_10_100_only_device(struct tg3 *tp,
+				   const struct pci_device_id *ent)
+{
+	u32 grc_misc_cfg = tr32(GRC_MISC_CFG) & GRC_MISC_CFG_BOARD_ID_MASK;
+
+	if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5703 &&
+	    (grc_misc_cfg == 0x8000 || grc_misc_cfg == 0x4000)) ||
+	    (tp->phy_flags & TG3_PHYFLG_IS_FET))
+		return true;
+
+	if (ent->driver_data & TG3_DRV_DATA_FLAG_10_100_ONLY) {
+		if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5705) {
+			if (ent->driver_data & TG3_DRV_DATA_FLAG_5705_10_100)
+				return true;
+		} else {
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static int __devinit tg3_get_invariants(struct tg3 *tp,
+					const struct pci_device_id *ent)
 {
 	u32 misc_ctrl_reg;
 	u32 pci_state_reg, grc_misc_cfg;
@@ -15145,22 +15193,7 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
 	else
 		tp->mac_mode = 0;
 
-	/* these are limited to 10/100 only */
-	if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5703 &&
-	     (grc_misc_cfg == 0x8000 || grc_misc_cfg == 0x4000)) ||
-	    (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5705 &&
-	     tp->pdev->vendor == PCI_VENDOR_ID_BROADCOM &&
-	     (tp->pdev->device == PCI_DEVICE_ID_TIGON3_5901 ||
-	      tp->pdev->device == PCI_DEVICE_ID_TIGON3_5901_2 ||
-	      tp->pdev->device == PCI_DEVICE_ID_TIGON3_5705F)) ||
-	    (tp->pdev->vendor == PCI_VENDOR_ID_BROADCOM &&
-	     (tp->pdev->device == PCI_DEVICE_ID_TIGON3_5751F ||
-	      tp->pdev->device == PCI_DEVICE_ID_TIGON3_5753F ||
-	      tp->pdev->device == PCI_DEVICE_ID_TIGON3_5787F)) ||
-	    tp->pdev->device == TG3PCI_DEVICE_TIGON3_57790 ||
-	    tp->pdev->device == TG3PCI_DEVICE_TIGON3_57791 ||
-	    tp->pdev->device == TG3PCI_DEVICE_TIGON3_57795 ||
-	    (tp->phy_flags & TG3_PHYFLG_IS_FET))
+	if (tg3_10_100_only_device(tp, ent))
 		tp->phy_flags |= TG3_PHYFLG_10_100_ONLY;
 
 	err = tg3_phy_probe(tp);
@@ -16039,7 +16072,7 @@ static int __devinit tg3_init_one(struct pci_dev *pdev,
 	dev->netdev_ops = &tg3_netdev_ops;
 	dev->irq = pdev->irq;
 
-	err = tg3_get_invariants(tp);
+	err = tg3_get_invariants(tp, ent);
 	if (err) {
 		dev_err(&pdev->dev,
 			"Problem fetching invariants of chip, aborting\n");
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index b3c2bf2c082f..6ff9964d2ea1 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -44,6 +44,7 @@
 #define  TG3PCI_DEVICE_TIGON3_5761S	 0x1688
 #define  TG3PCI_DEVICE_TIGON3_5761SE	 0x1689
 #define  TG3PCI_DEVICE_TIGON3_57780	 0x1692
+#define  TG3PCI_DEVICE_TIGON3_5787M	 0x1693
 #define  TG3PCI_DEVICE_TIGON3_57760	 0x1690
 #define  TG3PCI_DEVICE_TIGON3_57790	 0x1694
 #define  TG3PCI_DEVICE_TIGON3_57788	 0x1691
@@ -96,6 +97,10 @@
 #define TG3PCI_SUBDEVICE_ID_COMPAQ_NC7780_2	0x0099
 #define TG3PCI_SUBVENDOR_ID_IBM			PCI_VENDOR_ID_IBM
 #define TG3PCI_SUBDEVICE_ID_IBM_5703SAX2	0x0281
+#define TG3PCI_SUBDEVICE_ID_ACER_57780_A	0x0601
+#define TG3PCI_SUBDEVICE_ID_ACER_57780_B	0x0612
+#define TG3PCI_SUBDEVICE_ID_LENOVO_5787M	0x3056
+
 /* 0x30 --> 0x64 unused */
 #define TG3PCI_MSI_DATA			0x00000064
 /* 0x66 --> 0x68 unused */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index ee2179546c63..9cbd6705d033 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -603,6 +603,20 @@ struct pci_driver {
 	.vendor = (vend), .device = (dev), \
 	.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID
 
+/**
+ * PCI_DEVICE_SUB - macro used to describe a specific pci device with subsystem
+ * @vend: the 16 bit PCI Vendor ID
+ * @dev: the 16 bit PCI Device ID
+ * @subvend: the 16 bit PCI Subvendor ID
+ * @subdev: the 16 bit PCI Subdevice ID
+ *
+ * This macro is used to create a struct pci_device_id that matches a
+ * specific device with subsystem information.
+ */
+#define PCI_DEVICE_SUB(vend, dev, subvend, subdev) \
+	.vendor = (vend), .device = (dev), \
+	.subvendor = (subvend), .subdevice = (subdev)
+
 /**
  * PCI_DEVICE_CLASS - macro used to describe a specific pci device class
  * @dev_class: the class, subclass, prog-if triple for this device
-- 
cgit v1.2.3-55-g7522


From 549985ee9c723fea8fd7759b5046fb8249896d50 Mon Sep 17 00:00:00 2001
From: Richard Cochran
Date: Wed, 14 Nov 2012 09:07:56 +0000
Subject: cpsw: simplify the setup of the register pointers

Instead of having a host of different register offsets in the device tree,
this patch simplifies the CPSW code by letting the driver set the proper
register offsets automatically, based on the CPSW version.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/cpsw.txt |  42 +----
 drivers/net/ethernet/ti/cpsw.c                 | 242 +++++++++++--------------
 include/linux/platform_data/cpsw.h             |  21 +--
 3 files changed, 108 insertions(+), 197 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index 221460714c56..6ddd0286a9b7 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -9,15 +9,7 @@ Required properties:
 			  number
 - interrupt-parent	: The parent interrupt controller
 - cpdma_channels 	: Specifies number of channels in CPDMA
-- host_port_no		: Specifies host port shift
-- cpdma_reg_ofs		: Specifies CPDMA submodule register offset
-- cpdma_sram_ofs	: Specifies CPDMA SRAM offset
-- ale_reg_ofs		: Specifies ALE submodule register offset
 - ale_entries		: Specifies No of entries ALE can hold
-- host_port_reg_ofs	: Specifies host port register offset
-- hw_stats_reg_ofs	: Specifies hardware statistics register offset
-- cpts_reg_ofs		: Specifies the offset of the CPTS registers
-- bd_ram_ofs		: Specifies internal desciptor RAM offset
 - bd_ram_size		: Specifies internal descriptor RAM size
 - rx_descs		: Specifies number of Rx descriptors
 - mac_control		: Specifies Default MAC control register content
@@ -26,8 +18,6 @@ Required properties:
 - cpts_active_slave	: Specifies the slave to use for time stamping
 - cpts_clock_mult	: Numerator to convert input clock ticks into nanoseconds
 - cpts_clock_shift	: Denominator to convert input clock ticks into nanoseconds
-- slave_reg_ofs		: Specifies slave register offset
-- sliver_reg_ofs	: Specifies slave sliver register offset
 - phy_id		: Specifies slave phy id
 - mac-address		: Specifies slave MAC address
 
@@ -49,15 +39,7 @@ Examples:
 		interrupts = <55 0x4>;
 		interrupt-parent = <&intc>;
 		cpdma_channels = <8>;
-		host_port_no = <0>;
-		cpdma_reg_ofs = <0x800>;
-		cpdma_sram_ofs = <0xa00>;
-		ale_reg_ofs = <0xd00>;
 		ale_entries = <1024>;
-		host_port_reg_ofs = <0x108>;
-		hw_stats_reg_ofs = <0x900>;
-		cpts_reg_ofs = <0xc00>;
-		bd_ram_ofs = <0x2000>;
 		bd_ram_size = <0x2000>;
 		no_bd_ram = <0>;
 		rx_descs = <64>;
@@ -67,16 +49,12 @@ Examples:
 		cpts_clock_mult = <0x80000000>;
 		cpts_clock_shift = <29>;
 		cpsw_emac0: slave@0 {
-			slave_reg_ofs = <0x200>;
-			sliver_reg_ofs = <0xd80>;
-			phy_id = "davinci_mdio.16:00";
+			phy_id = <&davinci_mdio>, <0>;
 			/* Filled in by U-Boot */
 			mac-address = [ 00 00 00 00 00 00 ];
 		};
 		cpsw_emac1: slave@1 {
-			slave_reg_ofs = <0x300>;
-			sliver_reg_ofs = <0xdc0>;
-			phy_id = "davinci_mdio.16:01";
+			phy_id = <&davinci_mdio>, <1>;
 			/* Filled in by U-Boot */
 			mac-address = [ 00 00 00 00 00 00 ];
 		};
@@ -87,15 +65,7 @@ Examples:
 		compatible = "ti,cpsw";
 		ti,hwmods = "cpgmac0";
 		cpdma_channels = <8>;
-		host_port_no = <0>;
-		cpdma_reg_ofs = <0x800>;
-		cpdma_sram_ofs = <0xa00>;
-		ale_reg_ofs = <0xd00>;
 		ale_entries = <1024>;
-		host_port_reg_ofs = <0x108>;
-		hw_stats_reg_ofs = <0x900>;
-		cpts_reg_ofs = <0xc00>;
-		bd_ram_ofs = <0x2000>;
 		bd_ram_size = <0x2000>;
 		no_bd_ram = <0>;
 		rx_descs = <64>;
@@ -105,16 +75,12 @@ Examples:
 		cpts_clock_mult = <0x80000000>;
 		cpts_clock_shift = <29>;
 		cpsw_emac0: slave@0 {
-			slave_reg_ofs = <0x200>;
-			sliver_reg_ofs = <0xd80>;
-			phy_id = "davinci_mdio.16:00";
+			phy_id = <&davinci_mdio>, <0>;
 			/* Filled in by U-Boot */
 			mac-address = [ 00 00 00 00 00 00 ];
 		};
 		cpsw_emac1: slave@1 {
-			slave_reg_ofs = <0x300>;
-			sliver_reg_ofs = <0xdc0>;
-			phy_id = "davinci_mdio.16:01";
+			phy_id = <&davinci_mdio>, <1>;
 			/* Filled in by U-Boot */
 			mac-address = [ 00 00 00 00 00 00 ];
 		};
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 7007abaf8c82..0da9c753c567 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -80,6 +80,29 @@ do {								\
 
 #define CPSW_VERSION_1		0x19010a
 #define CPSW_VERSION_2		0x19010c
+
+#define HOST_PORT_NUM		0
+#define SLIVER_SIZE		0x40
+
+#define CPSW1_HOST_PORT_OFFSET	0x028
+#define CPSW1_SLAVE_OFFSET	0x050
+#define CPSW1_SLAVE_SIZE	0x040
+#define CPSW1_CPDMA_OFFSET	0x100
+#define CPSW1_STATERAM_OFFSET	0x200
+#define CPSW1_CPTS_OFFSET	0x500
+#define CPSW1_ALE_OFFSET	0x600
+#define CPSW1_SLIVER_OFFSET	0x700
+
+#define CPSW2_HOST_PORT_OFFSET	0x108
+#define CPSW2_SLAVE_OFFSET	0x200
+#define CPSW2_SLAVE_SIZE	0x100
+#define CPSW2_CPDMA_OFFSET	0x800
+#define CPSW2_STATERAM_OFFSET	0xa00
+#define CPSW2_CPTS_OFFSET	0xc00
+#define CPSW2_ALE_OFFSET	0xd00
+#define CPSW2_SLIVER_OFFSET	0xd80
+#define CPSW2_BD_OFFSET		0x2000
+
 #define CPDMA_RXTHRESH		0x0c0
 #define CPDMA_RXFREE		0x0e0
 #define CPDMA_TXHDP		0x00
@@ -87,21 +110,6 @@ do {								\
 #define CPDMA_TXCP		0x40
 #define CPDMA_RXCP		0x60
 
-#define cpsw_dma_regs(base, offset)		\
-	(void __iomem *)((base) + (offset))
-#define cpsw_dma_rxthresh(base, offset)		\
-	(void __iomem *)((base) + (offset) + CPDMA_RXTHRESH)
-#define cpsw_dma_rxfree(base, offset)		\
-	(void __iomem *)((base) + (offset) + CPDMA_RXFREE)
-#define cpsw_dma_txhdp(base, offset)		\
-	(void __iomem *)((base) + (offset) + CPDMA_TXHDP)
-#define cpsw_dma_rxhdp(base, offset)		\
-	(void __iomem *)((base) + (offset) + CPDMA_RXHDP)
-#define cpsw_dma_txcp(base, offset)		\
-	(void __iomem *)((base) + (offset) + CPDMA_TXCP)
-#define cpsw_dma_rxcp(base, offset)		\
-	(void __iomem *)((base) + (offset) + CPDMA_RXCP)
-
 #define CPSW_POLL_WEIGHT	64
 #define CPSW_MIN_PACKET_SIZE	60
 #define CPSW_MAX_PACKET_SIZE	(1500 + 14 + 4 + 4)
@@ -629,8 +637,7 @@ static int cpsw_ndo_open(struct net_device *ndev)
 
 	pm_runtime_get_sync(&priv->pdev->dev);
 
-	reg = __raw_readl(&priv->regs->id_ver);
-	priv->version = reg;
+	reg = priv->version;
 
 	dev_info(priv->dev, "initializing cpsw version %d.%d (%d)\n",
 		 CPSW_MAJOR_VERSION(reg), CPSW_MINOR_VERSION(reg),
@@ -995,15 +1002,16 @@ static const struct ethtool_ops cpsw_ethtool_ops = {
 	.get_ts_info	= cpsw_get_ts_info,
 };
 
-static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv)
+static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv,
+			    u32 slave_reg_ofs, u32 sliver_reg_ofs)
 {
 	void __iomem		*regs = priv->regs;
 	int			slave_num = slave->slave_num;
 	struct cpsw_slave_data	*data = priv->data.slave_data + slave_num;
 
 	slave->data	= data;
-	slave->regs	= regs + data->slave_reg_ofs;
-	slave->sliver	= regs + data->sliver_reg_ofs;
+	slave->regs	= regs + slave_reg_ofs;
+	slave->sliver	= regs + sliver_reg_ofs;
 }
 
 static int cpsw_probe_dt(struct cpsw_platform_data *data,
@@ -1051,8 +1059,6 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		return -EINVAL;
 	}
 
-	data->no_bd_ram = of_property_read_bool(node, "no_bd_ram");
-
 	if (of_property_read_u32(node, "cpdma_channels", &prop)) {
 		pr_err("Missing cpdma_channels property in the DT.\n");
 		ret = -EINVAL;
@@ -1060,34 +1066,6 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 	}
 	data->channels = prop;
 
-	if (of_property_read_u32(node, "host_port_no", &prop)) {
-		pr_err("Missing host_port_no property in the DT.\n");
-		ret = -EINVAL;
-		goto error_ret;
-	}
-	data->host_port_num = prop;
-
-	if (of_property_read_u32(node, "cpdma_reg_ofs", &prop)) {
-		pr_err("Missing cpdma_reg_ofs property in the DT.\n");
-		ret = -EINVAL;
-		goto error_ret;
-	}
-	data->cpdma_reg_ofs = prop;
-
-	if (of_property_read_u32(node, "cpdma_sram_ofs", &prop)) {
-		pr_err("Missing cpdma_sram_ofs property in the DT.\n");
-		ret = -EINVAL;
-		goto error_ret;
-	}
-	data->cpdma_sram_ofs = prop;
-
-	if (of_property_read_u32(node, "ale_reg_ofs", &prop)) {
-		pr_err("Missing ale_reg_ofs property in the DT.\n");
-		ret = -EINVAL;
-		goto error_ret;
-	}
-	data->ale_reg_ofs = prop;
-
 	if (of_property_read_u32(node, "ale_entries", &prop)) {
 		pr_err("Missing ale_entries property in the DT.\n");
 		ret = -EINVAL;
@@ -1095,34 +1073,6 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 	}
 	data->ale_entries = prop;
 
-	if (of_property_read_u32(node, "host_port_reg_ofs", &prop)) {
-		pr_err("Missing host_port_reg_ofs property in the DT.\n");
-		ret = -EINVAL;
-		goto error_ret;
-	}
-	data->host_port_reg_ofs = prop;
-
-	if (of_property_read_u32(node, "hw_stats_reg_ofs", &prop)) {
-		pr_err("Missing hw_stats_reg_ofs property in the DT.\n");
-		ret = -EINVAL;
-		goto error_ret;
-	}
-	data->hw_stats_reg_ofs = prop;
-
-	if (of_property_read_u32(node, "cpts_reg_ofs", &prop)) {
-		pr_err("Missing cpts_reg_ofs property in the DT.\n");
-		ret = -EINVAL;
-		goto error_ret;
-	}
-	data->cpts_reg_ofs = prop;
-
-	if (of_property_read_u32(node, "bd_ram_ofs", &prop)) {
-		pr_err("Missing bd_ram_ofs property in the DT.\n");
-		ret = -EINVAL;
-		goto error_ret;
-	}
-	data->bd_ram_ofs = prop;
-
 	if (of_property_read_u32(node, "bd_ram_size", &prop)) {
 		pr_err("Missing bd_ram_size property in the DT.\n");
 		ret = -EINVAL;
@@ -1144,33 +1094,34 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 	}
 	data->mac_control = prop;
 
+	/*
+	 * Populate all the child nodes here...
+	 */
+	ret = of_platform_populate(node, NULL, NULL, &pdev->dev);
+	/* We do not want to force this, as in some cases may not have child */
+	if (ret)
+		pr_warn("Doesn't have any child node\n");
+
 	for_each_node_by_name(slave_node, "slave") {
 		struct cpsw_slave_data *slave_data = data->slave_data + i;
-		const char *phy_id = NULL;
 		const void *mac_addr = NULL;
-
-		if (of_property_read_string(slave_node, "phy_id", &phy_id)) {
+		u32 phyid;
+		int lenp;
+		const __be32 *parp;
+		struct device_node *mdio_node;
+		struct platform_device *mdio;
+
+		parp = of_get_property(slave_node, "phy_id", &lenp);
+		if ((parp == NULL) && (lenp != (sizeof(void *) * 2))) {
 			pr_err("Missing slave[%d] phy_id property\n", i);
 			ret = -EINVAL;
 			goto error_ret;
 		}
-		slave_data->phy_id = phy_id;
-
-		if (of_property_read_u32(slave_node, "slave_reg_ofs", &prop)) {
-			pr_err("Missing slave[%d] slave_reg_ofs property\n", i);
-			ret = -EINVAL;
-			goto error_ret;
-		}
-		slave_data->slave_reg_ofs = prop;
-
-		if (of_property_read_u32(slave_node, "sliver_reg_ofs",
-					 &prop)) {
-			pr_err("Missing slave[%d] sliver_reg_ofs property\n",
-				i);
-			ret = -EINVAL;
-			goto error_ret;
-		}
-		slave_data->sliver_reg_ofs = prop;
+		mdio_node = of_find_node_by_phandle(be32_to_cpup(parp));
+		phyid = be32_to_cpup(parp+1);
+		mdio = of_find_device_by_node(mdio_node);
+		snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
+			 PHY_ID_FMT, mdio->name, phyid);
 
 		mac_addr = of_get_mac_address(slave_node);
 		if (mac_addr)
@@ -1179,14 +1130,6 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		i++;
 	}
 
-	/*
-	 * Populate all the child nodes here...
-	 */
-	ret = of_platform_populate(node, NULL, NULL, &pdev->dev);
-	/* We do not want to force this, as in some cases may not have child */
-	if (ret)
-		pr_warn("Doesn't have any child node\n");
-
 	return 0;
 
 error_ret:
@@ -1201,8 +1144,9 @@ static int __devinit cpsw_probe(struct platform_device *pdev)
 	struct cpsw_priv		*priv;
 	struct cpdma_params		dma_params;
 	struct cpsw_ale_params		ale_params;
-	void __iomem			*regs;
+	void __iomem			*ss_regs, *wr_regs;
 	struct resource			*res;
+	u32 slave_offset, sliver_offset, slave_size;
 	int ret = 0, i, k = 0;
 
 	ndev = alloc_etherdev(sizeof(struct cpsw_priv));
@@ -1270,15 +1214,14 @@ static int __devinit cpsw_probe(struct platform_device *pdev)
 		ret = -ENXIO;
 		goto clean_clk_ret;
 	}
-	regs = ioremap(priv->cpsw_res->start, resource_size(priv->cpsw_res));
-	if (!regs) {
+	ss_regs = ioremap(priv->cpsw_res->start, resource_size(priv->cpsw_res));
+	if (!ss_regs) {
 		dev_err(priv->dev, "unable to map i/o region\n");
 		goto clean_cpsw_iores_ret;
 	}
-	priv->regs = regs;
-	priv->host_port = data->host_port_num;
-	priv->host_port_regs = regs + data->host_port_reg_ofs;
-	priv->cpts.reg = regs + data->cpts_reg_ofs;
+	priv->regs = ss_regs;
+	priv->version = __raw_readl(&priv->regs->id_ver);
+	priv->host_port = HOST_PORT_NUM;
 
 	priv->cpsw_wr_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	if (!priv->cpsw_wr_res) {
@@ -1292,32 +1235,59 @@ static int __devinit cpsw_probe(struct platform_device *pdev)
 		ret = -ENXIO;
 		goto clean_iomap_ret;
 	}
-	regs = ioremap(priv->cpsw_wr_res->start,
+	wr_regs = ioremap(priv->cpsw_wr_res->start,
 				resource_size(priv->cpsw_wr_res));
-	if (!regs) {
+	if (!wr_regs) {
 		dev_err(priv->dev, "unable to map i/o region\n");
 		goto clean_cpsw_wr_iores_ret;
 	}
-	priv->wr_regs = regs;
-
-	for_each_slave(priv, cpsw_slave_init, priv);
+	priv->wr_regs = wr_regs;
 
 	memset(&dma_params, 0, sizeof(dma_params));
+	memset(&ale_params, 0, sizeof(ale_params));
+
+	switch (priv->version) {
+	case CPSW_VERSION_1:
+		priv->host_port_regs = ss_regs + CPSW1_HOST_PORT_OFFSET;
+		priv->cpts.reg       = ss_regs + CPSW1_CPTS_OFFSET;
+		dma_params.dmaregs   = ss_regs + CPSW1_CPDMA_OFFSET;
+		dma_params.txhdp     = ss_regs + CPSW1_STATERAM_OFFSET;
+		ale_params.ale_regs  = ss_regs + CPSW1_ALE_OFFSET;
+		slave_offset         = CPSW1_SLAVE_OFFSET;
+		slave_size           = CPSW1_SLAVE_SIZE;
+		sliver_offset        = CPSW1_SLIVER_OFFSET;
+		dma_params.desc_mem_phys = 0;
+		break;
+	case CPSW_VERSION_2:
+		priv->host_port_regs = ss_regs + CPSW2_HOST_PORT_OFFSET;
+		priv->cpts.reg       = ss_regs + CPSW2_CPTS_OFFSET;
+		dma_params.dmaregs   = ss_regs + CPSW2_CPDMA_OFFSET;
+		dma_params.txhdp     = ss_regs + CPSW2_STATERAM_OFFSET;
+		ale_params.ale_regs  = ss_regs + CPSW2_ALE_OFFSET;
+		slave_offset         = CPSW2_SLAVE_OFFSET;
+		slave_size           = CPSW2_SLAVE_SIZE;
+		sliver_offset        = CPSW2_SLIVER_OFFSET;
+		dma_params.desc_mem_phys =
+			(u32 __force) priv->cpsw_res->start + CPSW2_BD_OFFSET;
+		break;
+	default:
+		dev_err(priv->dev, "unknown version 0x%08x\n", priv->version);
+		ret = -ENODEV;
+		goto clean_cpsw_wr_iores_ret;
+	}
+	for (i = 0; i < priv->data.slaves; i++) {
+		struct cpsw_slave *slave = &priv->slaves[i];
+		cpsw_slave_init(slave, priv, slave_offset, sliver_offset);
+		slave_offset  += slave_size;
+		sliver_offset += SLIVER_SIZE;
+	}
+
 	dma_params.dev		= &pdev->dev;
-	dma_params.dmaregs	= cpsw_dma_regs((u32)priv->regs,
-						data->cpdma_reg_ofs);
-	dma_params.rxthresh	= cpsw_dma_rxthresh((u32)priv->regs,
-						    data->cpdma_reg_ofs);
-	dma_params.rxfree	= cpsw_dma_rxfree((u32)priv->regs,
-						  data->cpdma_reg_ofs);
-	dma_params.txhdp	= cpsw_dma_txhdp((u32)priv->regs,
-						 data->cpdma_sram_ofs);
-	dma_params.rxhdp	= cpsw_dma_rxhdp((u32)priv->regs,
-						 data->cpdma_sram_ofs);
-	dma_params.txcp		= cpsw_dma_txcp((u32)priv->regs,
-						data->cpdma_sram_ofs);
-	dma_params.rxcp		= cpsw_dma_rxcp((u32)priv->regs,
-						data->cpdma_sram_ofs);
+	dma_params.rxthresh	= dma_params.dmaregs + CPDMA_RXTHRESH;
+	dma_params.rxfree	= dma_params.dmaregs + CPDMA_RXFREE;
+	dma_params.rxhdp	= dma_params.txhdp + CPDMA_RXHDP;
+	dma_params.txcp		= dma_params.txhdp + CPDMA_TXCP;
+	dma_params.rxcp		= dma_params.txhdp + CPDMA_RXCP;
 
 	dma_params.num_chan		= data->channels;
 	dma_params.has_soft_reset	= true;
@@ -1325,10 +1295,7 @@ static int __devinit cpsw_probe(struct platform_device *pdev)
 	dma_params.desc_mem_size	= data->bd_ram_size;
 	dma_params.desc_align		= 16;
 	dma_params.has_ext_regs		= true;
-	dma_params.desc_mem_phys        = data->no_bd_ram ? 0 :
-			(u32 __force)priv->cpsw_res->start + data->bd_ram_ofs;
-	dma_params.desc_hw_addr         = data->hw_ram_addr ?
-			data->hw_ram_addr : dma_params.desc_mem_phys ;
+	dma_params.desc_hw_addr         = dma_params.desc_mem_phys;
 
 	priv->dma = cpdma_ctlr_create(&dma_params);
 	if (!priv->dma) {
@@ -1348,10 +1315,7 @@ static int __devinit cpsw_probe(struct platform_device *pdev)
 		goto clean_dma_ret;
 	}
 
-	memset(&ale_params, 0, sizeof(ale_params));
 	ale_params.dev			= &ndev->dev;
-	ale_params.ale_regs		= (void *)((u32)priv->regs) +
-						((u32)data->ale_reg_ofs);
 	ale_params.ale_ageout		= ale_ageout;
 	ale_params.ale_entries		= data->ale_entries;
 	ale_params.ale_ports		= data->slaves;
diff --git a/include/linux/platform_data/cpsw.h b/include/linux/platform_data/cpsw.h
index b5c16c3df458..24368a2e8b87 100644
--- a/include/linux/platform_data/cpsw.h
+++ b/include/linux/platform_data/cpsw.h
@@ -18,9 +18,7 @@
 #include <linux/if_ether.h>
 
 struct cpsw_slave_data {
-	u32		slave_reg_ofs;
-	u32		sliver_reg_ofs;
-	const char	*phy_id;
+	char		phy_id[MII_BUS_ID_SIZE];
 	int		phy_if;
 	u8		mac_addr[ETH_ALEN];
 };
@@ -28,31 +26,14 @@ struct cpsw_slave_data {
 struct cpsw_platform_data {
 	u32	ss_reg_ofs;	/* Subsystem control register offset */
 	u32	channels;	/* number of cpdma channels (symmetric) */
-	u32	cpdma_reg_ofs;	/* cpdma register offset */
-	u32	cpdma_sram_ofs;	/* cpdma sram offset */
-
 	u32	slaves;		/* number of slave cpgmac ports */
 	struct cpsw_slave_data	*slave_data;
 	u32	cpts_active_slave; /* time stamping slave */
 	u32	cpts_clock_mult;  /* convert input clock ticks to nanoseconds */
 	u32	cpts_clock_shift; /* convert input clock ticks to nanoseconds */
-
-	u32	ale_reg_ofs;	/* address lookup engine reg offset */
 	u32	ale_entries;	/* ale table size */
-
-	u32	host_port_reg_ofs; /* cpsw cpdma host port registers */
-	u32     host_port_num; /* The port number for the host port */
-
-	u32	hw_stats_reg_ofs;  /* cpsw hardware statistics counters */
-	u32	cpts_reg_ofs;      /* cpts registers */
-
-	u32	bd_ram_ofs;   /* embedded buffer descriptor RAM offset*/
 	u32	bd_ram_size;  /*buffer descriptor ram size */
-	u32	hw_ram_addr; /*if the HW address for BD RAM is different */
-	bool	no_bd_ram; /* no embedded BD ram*/
-
 	u32	rx_descs;	/* Number of Rx Descriptios */
-
 	u32	mac_control;	/* Mac control register */
 };
 
-- 
cgit v1.2.3-55-g7522


From 64e481603ab46bcd1466fdaffca50f25bf123f83 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Thu, 18 Oct 2012 19:36:09 +0530
Subject: mfd: tps6586x: move regulator dt parsing to regulator driver

Moving regulator node parsing to regulator driver in place
of parsing it on mfd driver.
The motivation for this change are:
- MFD core driver should not depends on regulator and able
  to instantiate device without regulator.
- The API for matching regulators are in regulator core and
  it is good that regulator driver only calls this API.
- Regulator specific support should be in regulator driver only
  to ease any enhancement/modification for regulators.
- The regulator driver is now registered as mfd sub device and
  all regulator registration is done from single probe call.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/mfd/Kconfig                    |   1 -
 drivers/mfd/tps6586x.c                 |  76 ++------------
 drivers/regulator/tps6586x-regulator.c | 181 ++++++++++++++++++++++++++++-----
 include/linux/mfd/tps6586x.h           |   3 +
 4 files changed, 166 insertions(+), 95 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index acab3ef8a310..05acef8c7641 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -201,7 +201,6 @@ config MFD_TPS6586X
 	depends on I2C=y && GENERIC_HARDIRQS
 	select MFD_CORE
 	select REGMAP_I2C
-	depends on REGULATOR
 	help
 	  If you say yes here you get support for the TPS6586X series of
 	  Power Management chips.
diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c
index 467464368773..9d67bd92edf8 100644
--- a/drivers/mfd/tps6586x.c
+++ b/drivers/mfd/tps6586x.c
@@ -24,8 +24,6 @@
 #include <linux/err.h>
 #include <linux/i2c.h>
 #include <linux/regmap.h>
-#include <linux/regulator/of_regulator.h>
-#include <linux/regulator/machine.h>
 
 #include <linux/mfd/core.h>
 #include <linux/mfd/tps6586x.h>
@@ -98,6 +96,9 @@ static struct mfd_cell tps6586x_cell[] = {
 	{
 		.name = "tps6586x-gpio",
 	},
+	{
+		.name = "tps6586x-pmic",
+	},
 	{
 		.name = "tps6586x-rtc",
 	},
@@ -350,80 +351,19 @@ failed:
 }
 
 #ifdef CONFIG_OF
-static struct of_regulator_match tps6586x_matches[] = {
-	{ .name = "sys",     .driver_data = (void *)TPS6586X_ID_SYS     },
-	{ .name = "sm0",     .driver_data = (void *)TPS6586X_ID_SM_0    },
-	{ .name = "sm1",     .driver_data = (void *)TPS6586X_ID_SM_1    },
-	{ .name = "sm2",     .driver_data = (void *)TPS6586X_ID_SM_2    },
-	{ .name = "ldo0",    .driver_data = (void *)TPS6586X_ID_LDO_0   },
-	{ .name = "ldo1",    .driver_data = (void *)TPS6586X_ID_LDO_1   },
-	{ .name = "ldo2",    .driver_data = (void *)TPS6586X_ID_LDO_2   },
-	{ .name = "ldo3",    .driver_data = (void *)TPS6586X_ID_LDO_3   },
-	{ .name = "ldo4",    .driver_data = (void *)TPS6586X_ID_LDO_4   },
-	{ .name = "ldo5",    .driver_data = (void *)TPS6586X_ID_LDO_5   },
-	{ .name = "ldo6",    .driver_data = (void *)TPS6586X_ID_LDO_6   },
-	{ .name = "ldo7",    .driver_data = (void *)TPS6586X_ID_LDO_7   },
-	{ .name = "ldo8",    .driver_data = (void *)TPS6586X_ID_LDO_8   },
-	{ .name = "ldo9",    .driver_data = (void *)TPS6586X_ID_LDO_9   },
-	{ .name = "ldo_rtc", .driver_data = (void *)TPS6586X_ID_LDO_RTC },
-};
-
 static struct tps6586x_platform_data *tps6586x_parse_dt(struct i2c_client *client)
 {
-	const unsigned int num = ARRAY_SIZE(tps6586x_matches);
 	struct device_node *np = client->dev.of_node;
 	struct tps6586x_platform_data *pdata;
-	struct tps6586x_subdev_info *devs;
-	struct device_node *regs;
-	const char *sys_rail_name = NULL;
-	unsigned int count;
-	unsigned int i, j;
-	int err;
-
-	regs = of_find_node_by_name(np, "regulators");
-	if (!regs)
-		return NULL;
-
-	err = of_regulator_match(&client->dev, regs, tps6586x_matches, num);
-	if (err < 0) {
-		of_node_put(regs);
-		return NULL;
-	}
-
-	of_node_put(regs);
-	count = err;
-
-	devs = devm_kzalloc(&client->dev, count * sizeof(*devs), GFP_KERNEL);
-	if (!devs)
-		return NULL;
-
-	for (i = 0, j = 0; i < num && j < count; i++) {
-		struct regulator_init_data *reg_idata;
-
-		if (!tps6586x_matches[i].init_data)
-			continue;
-
-		reg_idata  = tps6586x_matches[i].init_data;
-		devs[j].name = "tps6586x-regulator";
-		devs[j].platform_data = tps6586x_matches[i].init_data;
-		devs[j].id = (int)tps6586x_matches[i].driver_data;
-		if (devs[j].id == TPS6586X_ID_SYS)
-			sys_rail_name = reg_idata->constraints.name;
-
-		if ((devs[j].id == TPS6586X_ID_LDO_5) ||
-			(devs[j].id == TPS6586X_ID_LDO_RTC))
-			reg_idata->supply_regulator = sys_rail_name;
-
-		devs[j].of_node = tps6586x_matches[i].of_node;
-		j++;
-	}
 
 	pdata = devm_kzalloc(&client->dev, sizeof(*pdata), GFP_KERNEL);
-	if (!pdata)
+	if (!pdata) {
+		dev_err(&client->dev, "Memory allocation failed\n");
 		return NULL;
+	}
 
-	pdata->num_subdevs = count;
-	pdata->subdevs = devs;
+	pdata->num_subdevs = 0;
+	pdata->subdevs = NULL;
 	pdata->gpio_base = -1;
 	pdata->irq_base = -1;
 	pdata->pm_off = of_property_read_bool(np, "ti,system-power-controller");
diff --git a/drivers/regulator/tps6586x-regulator.c b/drivers/regulator/tps6586x-regulator.c
index ce1e7cb8d513..913c903bc3ee 100644
--- a/drivers/regulator/tps6586x-regulator.c
+++ b/drivers/regulator/tps6586x-regulator.c
@@ -17,10 +17,12 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/err.h>
+#include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
+#include <linux/regulator/of_regulator.h>
 #include <linux/mfd/tps6586x.h>
 
 /* supply control and voltage setting  */
@@ -255,10 +257,10 @@ static inline int tps6586x_regulator_preinit(struct device *parent,
 				 1 << ri->enable_bit[1]);
 }
 
-static int tps6586x_regulator_set_slew_rate(struct platform_device *pdev)
+static int tps6586x_regulator_set_slew_rate(struct platform_device *pdev,
+			int id, struct regulator_init_data *p)
 {
 	struct device *parent = pdev->dev.parent;
-	struct regulator_init_data *p = pdev->dev.platform_data;
 	struct tps6586x_settings *setting = p->driver_data;
 	uint8_t reg;
 
@@ -269,7 +271,7 @@ static int tps6586x_regulator_set_slew_rate(struct platform_device *pdev)
 		return 0;
 
 	/* only SM0 and SM1 can have the slew rate settings */
-	switch (pdev->id) {
+	switch (id) {
 	case TPS6586X_ID_SM_0:
 		reg = TPS6586X_SM0SL;
 		break;
@@ -298,54 +300,181 @@ static inline struct tps6586x_regulator *find_regulator_info(int id)
 	return NULL;
 }
 
+#ifdef CONFIG_OF
+static struct of_regulator_match tps6586x_matches[] = {
+	{ .name = "sys",     .driver_data = (void *)TPS6586X_ID_SYS     },
+	{ .name = "sm0",     .driver_data = (void *)TPS6586X_ID_SM_0    },
+	{ .name = "sm1",     .driver_data = (void *)TPS6586X_ID_SM_1    },
+	{ .name = "sm2",     .driver_data = (void *)TPS6586X_ID_SM_2    },
+	{ .name = "ldo0",    .driver_data = (void *)TPS6586X_ID_LDO_0   },
+	{ .name = "ldo1",    .driver_data = (void *)TPS6586X_ID_LDO_1   },
+	{ .name = "ldo2",    .driver_data = (void *)TPS6586X_ID_LDO_2   },
+	{ .name = "ldo3",    .driver_data = (void *)TPS6586X_ID_LDO_3   },
+	{ .name = "ldo4",    .driver_data = (void *)TPS6586X_ID_LDO_4   },
+	{ .name = "ldo5",    .driver_data = (void *)TPS6586X_ID_LDO_5   },
+	{ .name = "ldo6",    .driver_data = (void *)TPS6586X_ID_LDO_6   },
+	{ .name = "ldo7",    .driver_data = (void *)TPS6586X_ID_LDO_7   },
+	{ .name = "ldo8",    .driver_data = (void *)TPS6586X_ID_LDO_8   },
+	{ .name = "ldo9",    .driver_data = (void *)TPS6586X_ID_LDO_9   },
+	{ .name = "ldo_rtc", .driver_data = (void *)TPS6586X_ID_LDO_RTC },
+};
+
+static struct tps6586x_platform_data *tps6586x_parse_regulator_dt(
+		struct platform_device *pdev,
+		struct of_regulator_match **tps6586x_reg_matches)
+{
+	const unsigned int num = ARRAY_SIZE(tps6586x_matches);
+	struct device_node *np = pdev->dev.parent->of_node;
+	struct device_node *regs;
+	const char *sys_rail = NULL;
+	unsigned int i;
+	struct tps6586x_platform_data *pdata;
+	int err;
+
+	regs = of_find_node_by_name(np, "regulators");
+	if (!regs) {
+		dev_err(&pdev->dev, "regulator node not found\n");
+		return NULL;
+	}
+
+	err = of_regulator_match(&pdev->dev, regs, tps6586x_matches, num);
+	if (err < 0) {
+		dev_err(&pdev->dev, "Regulator match failed, e %d\n", err);
+		of_node_put(regs);
+		return NULL;
+	}
+
+	of_node_put(regs);
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata) {
+		dev_err(&pdev->dev, "Memory alloction failed\n");
+		return NULL;
+	}
+
+	for (i = 0; i < num; i++) {
+		int id;
+		if (!tps6586x_matches[i].init_data)
+			continue;
+
+		pdata->reg_init_data[i] = tps6586x_matches[i].init_data;
+		id = (int)tps6586x_matches[i].driver_data;
+		if (id == TPS6586X_ID_SYS)
+			sys_rail = pdata->reg_init_data[i]->constraints.name;
+
+		if ((id == TPS6586X_ID_LDO_5) || (id == TPS6586X_ID_LDO_RTC))
+			pdata->reg_init_data[i]->supply_regulator = sys_rail;
+	}
+	*tps6586x_reg_matches = tps6586x_matches;
+	return pdata;
+}
+#else
+static struct tps6586x_platform_data *tps6586x_parse_regulator_dt(
+		struct platform_device *pdev,
+		struct of_regulator_match **tps6586x_reg_matches)
+{
+	*tps6586x_reg_matches = NULL;
+	return NULL;
+}
+#endif
+
 static int __devinit tps6586x_regulator_probe(struct platform_device *pdev)
 {
 	struct tps6586x_regulator *ri = NULL;
 	struct regulator_config config = { };
-	struct regulator_dev *rdev;
-	int id = pdev->id;
+	struct regulator_dev **rdev;
+	struct regulator_init_data *reg_data;
+	struct tps6586x_platform_data *pdata;
+	struct of_regulator_match *tps6586x_reg_matches = NULL;
+	int id;
 	int err;
 
 	dev_dbg(&pdev->dev, "Probing regulator %d\n", id);
 
-	ri = find_regulator_info(id);
-	if (ri == NULL) {
-		dev_err(&pdev->dev, "invalid regulator ID specified\n");
-		return -EINVAL;
-	}
+	pdata = dev_get_platdata(pdev->dev.parent);
+	if ((!pdata) && (pdev->dev.parent->of_node))
+		pdata = tps6586x_parse_regulator_dt(pdev,
+					&tps6586x_reg_matches);
 
-	err = tps6586x_regulator_preinit(pdev->dev.parent, ri);
-	if (err)
-		return err;
+	if (!pdata) {
+		dev_err(&pdev->dev, "Platform data not available, exiting\n");
+		return -ENODEV;
+	}
 
-	config.dev = pdev->dev.parent;
-	config.of_node = pdev->dev.of_node;
-	config.init_data = pdev->dev.platform_data;
-	config.driver_data = ri;
+	rdev = devm_kzalloc(&pdev->dev, TPS6586X_ID_MAX_REGULATOR *
+				sizeof(*rdev), GFP_KERNEL);
+	if (!rdev) {
+		dev_err(&pdev->dev, "Mmemory alloc failed\n");
+		return -ENOMEM;
+	}
 
-	rdev = regulator_register(&ri->desc, &config);
-	if (IS_ERR(rdev)) {
-		dev_err(&pdev->dev, "failed to register regulator %s\n",
-				ri->desc.name);
-		return PTR_ERR(rdev);
+	for (id = 0; id < TPS6586X_ID_MAX_REGULATOR; ++id) {
+		reg_data = pdata->reg_init_data[id];
+
+		ri = find_regulator_info(id);
+		if (!ri) {
+			dev_err(&pdev->dev, "invalid regulator ID specified\n");
+			err = -EINVAL;
+			goto fail;
+		}
+
+		err = tps6586x_regulator_preinit(pdev->dev.parent, ri);
+		if (err) {
+			dev_err(&pdev->dev,
+				"regulator %d preinit failed, e %d\n", id, err);
+			goto fail;
+		}
+
+		config.dev = pdev->dev.parent;
+		config.init_data = reg_data;
+		config.driver_data = ri;
+
+		if (tps6586x_reg_matches)
+			config.of_node = tps6586x_reg_matches[id].of_node;
+
+		rdev[id] = regulator_register(&ri->desc, &config);
+		if (IS_ERR(rdev[id])) {
+			dev_err(&pdev->dev, "failed to register regulator %s\n",
+					ri->desc.name);
+			err = PTR_ERR(rdev[id]);
+			goto fail;
+		}
+
+		if (reg_data) {
+			err = tps6586x_regulator_set_slew_rate(pdev, id,
+					reg_data);
+			if (err < 0) {
+				dev_err(&pdev->dev,
+					"Slew rate config failed, e %d\n", err);
+				regulator_unregister(rdev[id]);
+				goto fail;
+			}
+		}
 	}
 
 	platform_set_drvdata(pdev, rdev);
+	return 0;
 
-	return tps6586x_regulator_set_slew_rate(pdev);
+fail:
+	while (--id >= 0)
+		regulator_unregister(rdev[id]);
+	return err;
 }
 
 static int __devexit tps6586x_regulator_remove(struct platform_device *pdev)
 {
-	struct regulator_dev *rdev = platform_get_drvdata(pdev);
+	struct regulator_dev **rdev = platform_get_drvdata(pdev);
+	int id = TPS6586X_ID_MAX_REGULATOR;
+
+	while (--id >= 0)
+		regulator_unregister(rdev[id]);
 
-	regulator_unregister(rdev);
 	return 0;
 }
 
 static struct platform_driver tps6586x_regulator_driver = {
 	.driver	= {
-		.name	= "tps6586x-regulator",
+		.name	= "tps6586x-pmic",
 		.owner	= THIS_MODULE,
 	},
 	.probe		= tps6586x_regulator_probe,
diff --git a/include/linux/mfd/tps6586x.h b/include/linux/mfd/tps6586x.h
index 2dd123194958..f8da0e152567 100644
--- a/include/linux/mfd/tps6586x.h
+++ b/include/linux/mfd/tps6586x.h
@@ -29,6 +29,7 @@ enum {
 	TPS6586X_ID_LDO_8,
 	TPS6586X_ID_LDO_9,
 	TPS6586X_ID_LDO_RTC,
+	TPS6586X_ID_MAX_REGULATOR,
 };
 
 enum {
@@ -79,6 +80,8 @@ struct tps6586x_platform_data {
 	int gpio_base;
 	int irq_base;
 	bool pm_off;
+
+	struct regulator_init_data *reg_init_data[TPS6586X_ID_MAX_REGULATOR];
 };
 
 /*
-- 
cgit v1.2.3-55-g7522


From f6130be652d0b4fbf710d83a816298c007e59ed1 Mon Sep 17 00:00:00 2001
From: Ashish Jangam
Date: Thu, 1 Nov 2012 13:57:56 +0530
Subject: regulator: DA9055 regulator driver

This is the Regulator patch for the DA9055 PMIC and has got dependency on
the DA9055 MFD core.

This patch support all of the DA9055 regulators. The output voltages are
fully programmable through I2C interface only. The platform data with regulation
constraints is passed down from the board to the regulator.

This patch is functionaly tested on SMDK6410 board. DA9055 Evaluation board
was connected to the SMDK6410 board.

Signed-off-by: David Dajun Chen <dchen@diasemi.com>
Signed-off-by: Ashish Jangam <ashish.jangam@kpitcummins.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/regulator/Kconfig            |  10 +
 drivers/regulator/Makefile           |   1 +
 drivers/regulator/da9055-regulator.c | 663 +++++++++++++++++++++++++++++++++++
 include/linux/mfd/da9055/pdata.h     |  27 +-
 4 files changed, 698 insertions(+), 3 deletions(-)
 create mode 100644 drivers/regulator/da9055-regulator.c

(limited to 'include')

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 67d47b59a66d..a162573d4944 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -109,6 +109,16 @@ config REGULATOR_DA9052
 	  This driver supports the voltage regulators of DA9052-BC and
 	  DA9053-AA/Bx PMIC.
 
+config REGULATOR_DA9055
+	tristate "Dialog Semiconductor DA9055 regulators"
+	depends on MFD_DA9055
+	help
+	  Say y here to support the BUCKs and LDOs regulators found on
+	  Dialog Semiconductor DA9055 PMIC.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called da9055-regulator.
+
 config REGULATOR_FAN53555
 	tristate "Fairchild FAN53555 Regulator"
 	depends on I2C
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index e431eed8a878..4b754e958aed 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_REGULATOR_ANATOP) += anatop-regulator.o
 obj-$(CONFIG_REGULATOR_ARIZONA) += arizona-micsupp.o arizona-ldo1.o
 obj-$(CONFIG_REGULATOR_DA903X)	+= da903x.o
 obj-$(CONFIG_REGULATOR_DA9052)	+= da9052-regulator.o
+obj-$(CONFIG_REGULATOR_DA9055)	+= da9055-regulator.o
 obj-$(CONFIG_REGULATOR_DBX500_PRCMU) += dbx500-prcmu.o
 obj-$(CONFIG_REGULATOR_DB8500_PRCMU) += db8500-prcmu.o
 obj-$(CONFIG_REGULATOR_FAN53555) += fan53555.o
diff --git a/drivers/regulator/da9055-regulator.c b/drivers/regulator/da9055-regulator.c
new file mode 100644
index 000000000000..8994178b371c
--- /dev/null
+++ b/drivers/regulator/da9055-regulator.c
@@ -0,0 +1,663 @@
+/*
+* Regulator driver for DA9055 PMIC
+*
+* Copyright(c) 2012 Dialog Semiconductor Ltd.
+*
+* Author: David Dajun Chen <dchen@diasemi.com>
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License as published by
+* the Free Software Foundation; either version 2 of the License, or
+* (at your option) any later version.
+*
+*/
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/gpio.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+
+#include <linux/mfd/da9055/core.h>
+#include <linux/mfd/da9055/reg.h>
+#include <linux/mfd/da9055/pdata.h>
+
+#define DA9055_MIN_UA		0
+#define DA9055_MAX_UA		3
+
+#define DA9055_LDO_MODE_SYNC	0
+#define DA9055_LDO_MODE_SLEEP	1
+
+#define DA9055_BUCK_MODE_SLEEP	1
+#define DA9055_BUCK_MODE_SYNC	2
+#define DA9055_BUCK_MODE_AUTO	3
+
+/* DA9055 REGULATOR IDs */
+#define DA9055_ID_BUCK1	0
+#define DA9055_ID_BUCK2	1
+#define DA9055_ID_LDO1		2
+#define DA9055_ID_LDO2		3
+#define DA9055_ID_LDO3		4
+#define DA9055_ID_LDO4		5
+#define DA9055_ID_LDO5		6
+#define DA9055_ID_LDO6		7
+
+/* DA9055 BUCK current limit */
+static const int da9055_current_limits[] = { 500000, 600000, 700000, 800000 };
+
+struct da9055_conf_reg {
+	int reg;
+	int sel_mask;
+	int en_mask;
+};
+
+struct da9055_volt_reg {
+	int reg_a;
+	int reg_b;
+	int sl_shift;
+	int v_offset;
+	int v_mask;
+	int v_shift;
+};
+
+struct da9055_mode_reg {
+	int reg;
+	int mask;
+	int shift;
+};
+
+struct da9055_regulator_info {
+	struct regulator_desc reg_desc;
+	struct da9055_conf_reg conf;
+	struct da9055_volt_reg volt;
+	struct da9055_mode_reg mode;
+};
+
+struct da9055_regulator {
+	struct da9055 *da9055;
+	struct da9055_regulator_info *info;
+	struct regulator_dev *rdev;
+	enum gpio_select reg_rselect;
+};
+
+static unsigned int da9055_buck_get_mode(struct regulator_dev *rdev)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+	int ret, mode = 0;
+
+	ret = da9055_reg_read(regulator->da9055, info->mode.reg);
+	if (ret < 0)
+		return ret;
+
+	switch ((ret & info->mode.mask) >> info->mode.shift) {
+	case DA9055_BUCK_MODE_SYNC:
+		mode = REGULATOR_MODE_FAST;
+		break;
+	case DA9055_BUCK_MODE_AUTO:
+		mode = REGULATOR_MODE_NORMAL;
+		break;
+	case DA9055_BUCK_MODE_SLEEP:
+		mode = REGULATOR_MODE_STANDBY;
+		break;
+	}
+
+	return mode;
+}
+
+static int da9055_buck_set_mode(struct regulator_dev *rdev,
+					unsigned int mode)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+	int val = 0;
+
+	switch (mode) {
+	case REGULATOR_MODE_FAST:
+		val = DA9055_BUCK_MODE_SYNC << info->mode.shift;
+		break;
+	case REGULATOR_MODE_NORMAL:
+		val = DA9055_BUCK_MODE_AUTO << info->mode.shift;
+		break;
+	case REGULATOR_MODE_STANDBY:
+		val = DA9055_BUCK_MODE_SLEEP << info->mode.shift;
+		break;
+	}
+
+	return da9055_reg_update(regulator->da9055, info->mode.reg,
+				 info->mode.mask, val);
+}
+
+static unsigned int da9055_ldo_get_mode(struct regulator_dev *rdev)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+	int ret;
+
+	ret = da9055_reg_read(regulator->da9055, info->volt.reg_b);
+	if (ret < 0)
+		return ret;
+
+	if (ret >> info->volt.sl_shift)
+		return REGULATOR_MODE_STANDBY;
+	else
+		return REGULATOR_MODE_NORMAL;
+}
+
+static int da9055_ldo_set_mode(struct regulator_dev *rdev, unsigned int mode)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+	struct da9055_volt_reg volt = info->volt;
+	int val = 0;
+
+	switch (mode) {
+	case REGULATOR_MODE_NORMAL:
+	case REGULATOR_MODE_FAST:
+		val = DA9055_LDO_MODE_SYNC;
+		break;
+	case REGULATOR_MODE_STANDBY:
+		val = DA9055_LDO_MODE_SLEEP;
+		break;
+	}
+
+	return da9055_reg_update(regulator->da9055, volt.reg_b,
+				 1 << volt.sl_shift,
+				 val << volt.sl_shift);
+}
+
+static int da9055_buck_get_current_limit(struct regulator_dev *rdev)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+	int ret;
+
+	ret = da9055_reg_read(regulator->da9055, DA9055_REG_BUCK_LIM);
+	if (ret < 0)
+		return ret;
+
+	ret &= info->mode.mask;
+	return da9055_current_limits[ret >> info->mode.shift];
+}
+
+static int da9055_buck_set_current_limit(struct regulator_dev *rdev, int min_uA,
+					 int max_uA)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+	int i, val = 0;
+
+	if (min_uA > da9055_current_limits[DA9055_MAX_UA] ||
+	    max_uA < da9055_current_limits[DA9055_MIN_UA])
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(da9055_current_limits); i++) {
+		if (min_uA <= da9055_current_limits[i]) {
+			val = i;
+			break;
+		}
+	}
+
+	return da9055_reg_update(regulator->da9055, DA9055_REG_BUCK_LIM,
+				info->mode.mask, val << info->mode.shift);
+}
+
+static int da9055_regulator_get_voltage_sel(struct regulator_dev *rdev)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+	struct da9055_volt_reg volt = info->volt;
+	int ret, sel;
+
+	/*
+	 * There are two voltage register set A & B for voltage ramping but
+	 * either one of then can be active therefore we first determine
+	 * the active register set.
+	 */
+	ret = da9055_reg_read(regulator->da9055, info->conf.reg);
+	if (ret < 0)
+		return ret;
+
+	ret &= info->conf.sel_mask;
+
+	/* Get the voltage for the active register set A/B */
+	if (ret == DA9055_REGUALTOR_SET_A)
+		ret = da9055_reg_read(regulator->da9055, volt.reg_a);
+	else
+		ret = da9055_reg_read(regulator->da9055, volt.reg_b);
+
+	if (ret < 0)
+		return ret;
+
+	sel = (ret & volt.v_mask);
+	if (sel <= volt.v_offset)
+		return 0;
+	else
+		return sel;
+}
+
+static int da9055_regulator_set_voltage_bits(struct regulator_dev *rdev,
+					     unsigned int reg,
+					     unsigned int selector)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+
+	/* Takes care of voltage range that does not start with 0 offset. */
+	selector += info->volt.v_offset;
+
+	/* Set the voltage */
+	return da9055_reg_update(regulator->da9055, reg, info->volt.v_mask,
+				 selector);
+
+}
+
+static int da9055_regulator_set_voltage_sel(struct regulator_dev *rdev,
+					    unsigned int selector)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+	int ret;
+
+	/*
+	 * Regulator register set A/B is not selected through GPIO therefore
+	 * we use default register set A for voltage ramping.
+	 */
+	if (regulator->reg_rselect == NO_GPIO) {
+		/* Select register set A */
+		ret = da9055_reg_update(regulator->da9055, info->conf.reg,
+					info->conf.sel_mask, DA9055_SEL_REG_A);
+		if (ret < 0)
+			return ret;
+
+		/* Set the voltage */
+		return da9055_regulator_set_voltage_bits(rdev, info->volt.reg_a,
+							 selector);
+	}
+
+	/*
+	 * Here regulator register set A/B is selected through GPIO.
+	 * Therefore we first determine the selected register set A/B and
+	 * then set the desired voltage for that register set A/B.
+	 */
+	ret = da9055_reg_read(regulator->da9055, info->conf.reg);
+	if (ret < 0)
+		return ret;
+
+	ret &= info->conf.sel_mask;
+
+	/* Set the voltage */
+	if (ret == DA9055_REGUALTOR_SET_A)
+		return da9055_regulator_set_voltage_bits(rdev, info->volt.reg_a,
+							 selector);
+	else
+		return da9055_regulator_set_voltage_bits(rdev, info->volt.reg_b,
+						 selector);
+}
+
+static int da9055_regulator_set_suspend_voltage(struct regulator_dev *rdev,
+						int uV)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+	int ret;
+
+	/* Select register set B for suspend voltage ramping. */
+	if (regulator->reg_rselect == NO_GPIO) {
+		ret = da9055_reg_update(regulator->da9055, info->conf.reg,
+					info->conf.sel_mask, DA9055_SEL_REG_B);
+		if (ret < 0)
+			return ret;
+	}
+
+	ret = regulator_map_voltage_linear(rdev, uV, uV);
+	if (ret < 0)
+		return ret;
+
+	return da9055_regulator_set_voltage_bits(rdev, info->volt.reg_b, ret);
+}
+
+static int da9055_suspend_enable(struct regulator_dev *rdev)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+
+	/* Select register set B for voltage ramping. */
+	if (regulator->reg_rselect == NO_GPIO)
+		return da9055_reg_update(regulator->da9055, info->conf.reg,
+					info->conf.sel_mask, DA9055_SEL_REG_B);
+	else
+		return 0;
+}
+
+static int da9055_suspend_disable(struct regulator_dev *rdev)
+{
+	struct da9055_regulator *regulator = rdev_get_drvdata(rdev);
+	struct da9055_regulator_info *info = regulator->info;
+
+	/* Diselect register set B. */
+	if (regulator->reg_rselect == NO_GPIO)
+		return da9055_reg_update(regulator->da9055, info->conf.reg,
+					info->conf.sel_mask, DA9055_SEL_REG_A);
+	else
+		return 0;
+}
+
+static struct regulator_ops da9055_buck_ops = {
+	.get_mode = da9055_buck_get_mode,
+	.set_mode = da9055_buck_set_mode,
+
+	.get_current_limit = da9055_buck_get_current_limit,
+	.set_current_limit = da9055_buck_set_current_limit,
+
+	.get_voltage_sel = da9055_regulator_get_voltage_sel,
+	.set_voltage_sel = da9055_regulator_set_voltage_sel,
+	.list_voltage = regulator_list_voltage_linear,
+	.map_voltage = regulator_map_voltage_linear,
+	.is_enabled = regulator_is_enabled_regmap,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+
+	.set_suspend_voltage = da9055_regulator_set_suspend_voltage,
+	.set_suspend_enable = da9055_suspend_enable,
+	.set_suspend_disable = da9055_suspend_disable,
+	.set_suspend_mode = da9055_buck_set_mode,
+};
+
+static struct regulator_ops da9055_ldo_ops = {
+	.get_mode = da9055_ldo_get_mode,
+	.set_mode = da9055_ldo_set_mode,
+
+	.get_voltage_sel = da9055_regulator_get_voltage_sel,
+	.set_voltage_sel = da9055_regulator_set_voltage_sel,
+	.list_voltage = regulator_list_voltage_linear,
+	.map_voltage = regulator_map_voltage_linear,
+	.is_enabled = regulator_is_enabled_regmap,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+
+	.set_suspend_voltage = da9055_regulator_set_suspend_voltage,
+	.set_suspend_enable = da9055_suspend_enable,
+	.set_suspend_disable = da9055_suspend_disable,
+	.set_suspend_mode = da9055_ldo_set_mode,
+
+};
+
+#define DA9055_LDO(_id, step, min, max, vbits, voffset) \
+{\
+	.reg_desc = {\
+		.name = #_id,\
+		.ops = &da9055_ldo_ops,\
+		.type = REGULATOR_VOLTAGE,\
+		.id = DA9055_ID_##_id,\
+		.n_voltages = (max - min) / step + 1, \
+		.enable_reg = DA9055_REG_BCORE_CONT + DA9055_ID_##_id, \
+		.enable_mask = 1, \
+		.min_uV = (min) * 1000,\
+		.uV_step = (step) * 1000,\
+		.owner = THIS_MODULE,\
+	},\
+	.conf = {\
+		.reg = DA9055_REG_BCORE_CONT + DA9055_ID_##_id, \
+		.sel_mask = (1 << 4),\
+		.en_mask = 1,\
+	},\
+	.volt = {\
+		.reg_a = DA9055_REG_VBCORE_A + DA9055_ID_##_id, \
+		.reg_b = DA9055_REG_VBCORE_B + DA9055_ID_##_id, \
+		.sl_shift = 7,\
+		.v_offset = (voffset),\
+		.v_mask = (1 << (vbits)) - 1,\
+		.v_shift = (vbits),\
+	},\
+}
+
+#define DA9055_BUCK(_id, step, min, max, vbits, voffset, mbits, sbits) \
+{\
+	.reg_desc = {\
+		.name = #_id,\
+		.ops = &da9055_buck_ops,\
+		.type = REGULATOR_VOLTAGE,\
+		.id = DA9055_ID_##_id,\
+		.n_voltages = (max - min) / step + 1, \
+		.enable_reg = DA9055_REG_BCORE_CONT + DA9055_ID_##_id, \
+		.enable_mask = 1,\
+		.min_uV = (min) * 1000,\
+		.uV_step = (step) * 1000,\
+		.owner = THIS_MODULE,\
+	},\
+	.conf = {\
+		.reg = DA9055_REG_BCORE_CONT + DA9055_ID_##_id, \
+		.sel_mask = (1 << 4),\
+		.en_mask = 1,\
+	},\
+	.volt = {\
+		.reg_a = DA9055_REG_VBCORE_A + DA9055_ID_##_id, \
+		.reg_b = DA9055_REG_VBCORE_B + DA9055_ID_##_id, \
+		.sl_shift = 7,\
+		.v_offset = (voffset),\
+		.v_mask = (1 << (vbits)) - 1,\
+		.v_shift = (vbits),\
+	},\
+	.mode = {\
+		.reg = DA9055_REG_BCORE_MODE,\
+		.mask = (mbits),\
+		.shift = (sbits),\
+	},\
+}
+
+static struct da9055_regulator_info da9055_regulator_info[] = {
+	DA9055_BUCK(BUCK1, 25, 725, 2075, 6, 9, 0xc, 2),
+	DA9055_BUCK(BUCK2, 25, 925, 2500, 6, 0, 3, 0),
+	DA9055_LDO(LDO1, 50, 900, 3300, 6, 2),
+	DA9055_LDO(LDO2, 50, 900, 3300, 6, 3),
+	DA9055_LDO(LDO3, 50, 900, 3300, 6, 2),
+	DA9055_LDO(LDO4, 50, 900, 3300, 6, 2),
+	DA9055_LDO(LDO5, 50, 900, 2750, 6, 2),
+	DA9055_LDO(LDO6, 20, 900, 3300, 7, 0),
+};
+
+/*
+ * Configures regulator to be controlled either through GPIO 1 or 2.
+ * GPIO can control regulator state and/or select the regulator register
+ * set A/B for voltage ramping.
+ */
+static __devinit int da9055_gpio_init(struct da9055_regulator *regulator,
+				      struct regulator_config *config,
+				      struct da9055_pdata *pdata, int id)
+{
+	struct da9055_regulator_info *info = regulator->info;
+	int ret = 0;
+
+	if (pdata->gpio_ren && pdata->gpio_ren[id]) {
+		char name[18];
+		int gpio_mux = pdata->gpio_ren[id];
+
+		config->ena_gpio = pdata->ena_gpio[id];
+		config->ena_gpio_flags = GPIOF_OUT_INIT_HIGH;
+		config->ena_gpio_invert = 1;
+
+		/*
+		 * GPI pin is muxed with regulator to control the
+		 * regulator state.
+		 */
+		sprintf(name, "DA9055 GPI %d", gpio_mux);
+		ret = devm_gpio_request_one(config->dev, gpio_mux, GPIOF_DIR_IN,
+					    name);
+		if (ret < 0)
+			goto err;
+
+		/*
+		 * Let the regulator know that its state is controlled
+		 * through GPI.
+		 */
+		ret = da9055_reg_update(regulator->da9055, info->conf.reg,
+					DA9055_E_GPI_MASK,
+					pdata->reg_ren[id]
+					<< DA9055_E_GPI_SHIFT);
+		if (ret < 0)
+			goto err;
+	}
+
+	if (pdata->gpio_rsel && pdata->gpio_ren[id]) {
+		char name[18];
+		int gpio_mux = pdata->gpio_rsel[id];
+
+		regulator->reg_rselect = pdata->reg_rsel[id];
+
+		/*
+		 * GPI pin is muxed with regulator to select the
+		 * regulator register set A/B for voltage ramping.
+		 */
+		sprintf(name, "DA9055 GPI %d", gpio_mux);
+		ret = devm_gpio_request_one(config->dev, gpio_mux, GPIOF_DIR_IN,
+					    name);
+		if (ret < 0)
+			goto err;
+
+		/*
+		 * Let the regulator know that its register set A/B
+		 * will be selected through GPI for voltage ramping.
+		 */
+		ret = da9055_reg_update(regulator->da9055, info->conf.reg,
+					DA9055_V_GPI_MASK,
+					pdata->reg_rsel[id]
+					<< DA9055_V_GPI_SHIFT);
+	}
+
+err:
+	return ret;
+}
+
+static irqreturn_t da9055_ldo5_6_oc_irq(int irq, void *data)
+{
+	struct da9055_regulator *regulator = data;
+
+	regulator_notifier_call_chain(regulator->rdev,
+				      REGULATOR_EVENT_OVER_CURRENT, NULL);
+
+	return IRQ_HANDLED;
+}
+
+static inline struct da9055_regulator_info *find_regulator_info(int id)
+{
+	struct da9055_regulator_info *info;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(da9055_regulator_info); i++) {
+		info = &da9055_regulator_info[i];
+		if (info->reg_desc.id == id)
+			return info;
+	}
+
+	return NULL;
+}
+
+static int __devinit da9055_regulator_probe(struct platform_device *pdev)
+{
+	struct regulator_config config = { };
+	struct da9055_regulator *regulator;
+	struct da9055 *da9055 = dev_get_drvdata(pdev->dev.parent);
+	struct da9055_pdata *pdata = da9055->dev->platform_data;
+	int ret, irq;
+
+	if (pdata == NULL || pdata->regulators[pdev->id] == NULL)
+		return -ENODEV;
+
+	regulator = devm_kzalloc(&pdev->dev, sizeof(struct da9055_regulator),
+				 GFP_KERNEL);
+	if (!regulator)
+		return -ENOMEM;
+
+	regulator->info = find_regulator_info(pdev->id);
+	if (regulator->info == NULL) {
+		dev_err(&pdev->dev, "invalid regulator ID specified\n");
+		return -EINVAL;
+	}
+
+	regulator->da9055 = da9055;
+	config.dev = &pdev->dev;
+	config.driver_data = regulator;
+	config.regmap = da9055->regmap;
+
+	if (pdata && pdata->regulators)
+		config.init_data = pdata->regulators[pdev->id];
+
+	ret = da9055_gpio_init(regulator, &config, pdata, pdev->id);
+	if (ret < 0)
+		return ret;
+
+	regulator->rdev = regulator_register(&regulator->info->reg_desc,
+					     &config);
+	if (IS_ERR(regulator->rdev)) {
+		dev_err(&pdev->dev, "Failed to register regulator %s\n",
+			regulator->info->reg_desc.name);
+		ret = PTR_ERR(regulator->rdev);
+		return ret;
+	}
+
+	/* Only LDO 5 and 6 has got the over current interrupt */
+	if (pdev->id == DA9055_ID_LDO5 || pdev->id ==  DA9055_ID_LDO6) {
+		irq = platform_get_irq_byname(pdev, "REGULATOR");
+		irq = regmap_irq_get_virq(da9055->irq_data, irq);
+		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
+						da9055_ldo5_6_oc_irq,
+						IRQF_TRIGGER_HIGH |
+						IRQF_ONESHOT |
+						IRQF_PROBE_SHARED,
+						pdev->name, regulator);
+		if (ret != 0) {
+			if (ret != -EBUSY) {
+				dev_err(&pdev->dev,
+				"Failed to request Regulator IRQ %d: %d\n",
+				irq, ret);
+				goto err_regulator;
+			}
+		}
+	}
+
+	platform_set_drvdata(pdev, regulator);
+
+	return 0;
+
+err_regulator:
+	regulator_unregister(regulator->rdev);
+	return ret;
+}
+
+static int __devexit da9055_regulator_remove(struct platform_device *pdev)
+{
+	struct da9055_regulator *regulator = platform_get_drvdata(pdev);
+
+	regulator_unregister(regulator->rdev);
+
+	return 0;
+}
+
+static struct platform_driver da9055_regulator_driver = {
+	.probe = da9055_regulator_probe,
+	.remove = __devexit_p(da9055_regulator_remove),
+	.driver = {
+		.name = "da9055-regulator",
+		.owner = THIS_MODULE,
+	},
+};
+
+static int __init da9055_regulator_init(void)
+{
+	return platform_driver_register(&da9055_regulator_driver);
+}
+subsys_initcall(da9055_regulator_init);
+
+static void __exit da9055_regulator_exit(void)
+{
+	platform_driver_unregister(&da9055_regulator_driver);
+}
+module_exit(da9055_regulator_exit);
+
+MODULE_AUTHOR("David Dajun Chen <dchen@diasemi.com>");
+MODULE_DESCRIPTION("Power Regulator driver for Dialog DA9055 PMIC");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:da9055-regulator");
diff --git a/include/linux/mfd/da9055/pdata.h b/include/linux/mfd/da9055/pdata.h
index 147293b4471d..f87a6c172a91 100644
--- a/include/linux/mfd/da9055/pdata.h
+++ b/include/linux/mfd/da9055/pdata.h
@@ -25,8 +25,29 @@ struct da9055_pdata {
 	int gpio_base;
 
 	struct regulator_init_data *regulators[DA9055_MAX_REGULATORS];
-	bool reset_enable;		/* Enable RTC in RESET Mode */
-	enum gpio_select *gpio_rsel;	/* Select regulator set thru GPIO 1/2 */
-	enum gpio_select *gpio_ren;	/* Enable regulator thru GPIO 1/2 */
+	/* Enable RTC in RESET Mode */
+	bool reset_enable;
+	/*
+	 * GPI muxed pin to control
+	 * regulator state A/B, 0 if not available.
+	 */
+	int *gpio_ren;
+	/*
+	 * GPI muxed pin to control
+	 * regulator set, 0 if not available.
+	 */
+	int *gpio_rsel;
+	/*
+	 * Regulator mode control bits value (GPI offset) that
+	 * that controls the regulator state, 0 if not available.
+	 */
+	enum gpio_select *reg_ren;
+	/*
+	 * Regulator mode control bits value (GPI offset) that
+	 * controls the regulator set A/B, 0 if  not available.
+	 */
+	enum gpio_select *reg_rsel;
+	/* GPIOs to enable regulator, 0 if not available */
+	int *ena_gpio;
 };
 #endif /* __DA9055_PDATA_H */
-- 
cgit v1.2.3-55-g7522


From 37cf6e6fc34e2fca4e7c565697e7cd5c317bc316 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires
Date: Wed, 14 Nov 2012 16:59:13 +0100
Subject: HID: export hidinput_calc_abs_res

Exporting the function allows us to calculate the resolution in third
party drivers like hid-multitouch.
This patch also complete the function with additional valid axes.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@gmail.com>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-input.c      | 9 ++++++++-
 drivers/hid/hid-multitouch.c | 1 +
 include/linux/hid.h          | 1 +
 3 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index d917c0d53685..d1ec571bdb3b 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -208,7 +208,7 @@ static int hidinput_setkeycode(struct input_dev *dev,
  * Only exponent 1 length units are processed. Centimeters and inches are
  * converted to millimeters. Degrees are converted to radians.
  */
-static __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code)
+__s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code)
 {
 	__s32 unit_exponent = field->unit_exponent;
 	__s32 logical_extents = field->logical_maximum -
@@ -229,6 +229,12 @@ static __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code)
 	case ABS_X:
 	case ABS_Y:
 	case ABS_Z:
+	case ABS_MT_POSITION_X:
+	case ABS_MT_POSITION_Y:
+	case ABS_MT_TOOL_X:
+	case ABS_MT_TOOL_Y:
+	case ABS_MT_TOUCH_MAJOR:
+	case ABS_MT_TOUCH_MINOR:
 		if (field->unit == 0x11) {		/* If centimeters */
 			/* Convert to millimeters */
 			unit_exponent += 1;
@@ -283,6 +289,7 @@ static __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code)
 	/* Calculate resolution */
 	return logical_extents / physical_extents;
 }
+EXPORT_SYMBOL_GPL(hidinput_calc_abs_res);
 
 #ifdef CONFIG_HID_BATTERY_STRENGTH
 static enum power_supply_property hidinput_battery_props[] = {
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 7867d69f0efe..3687f797b731 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -297,6 +297,7 @@ static void set_abs(struct input_dev *input, unsigned int code,
 	int fmax = field->logical_maximum;
 	int fuzz = snratio ? (fmax - fmin) / snratio : 0;
 	input_set_abs_params(input, code, fmin, fmax, fuzz, 0);
+	input_abs_set_res(input, code, hidinput_calc_abs_res(field, code));
 }
 
 static void mt_store_field(struct hid_usage *usage, struct mt_device *td,
diff --git a/include/linux/hid.h b/include/linux/hid.h
index c076041a069e..c6bef8f54a82 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -706,6 +706,7 @@ int hid_input_report(struct hid_device *, int type, u8 *, int, int);
 int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field);
 struct hid_field *hidinput_get_led_field(struct hid_device *hid);
 unsigned int hidinput_count_leds(struct hid_device *hid);
+__s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code);
 void hid_output_report(struct hid_report *report, __u8 *data);
 struct hid_device *hid_allocate_device(void);
 struct hid_report *hid_register_report(struct hid_device *device, unsigned type, unsigned id);
-- 
cgit v1.2.3-55-g7522


From 774638386826621c984ab6994439f474709cac5e Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires
Date: Wed, 14 Nov 2012 16:59:15 +0100
Subject: HID: fix unit exponent parsing

HID spec details special values for the HID field unit exponent.
Basically, the range [0x8..0xf] correspond to [-8..-1], so this is
a standard two's complement on a half-byte.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@gmail.com>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-core.c  | 16 +++++++++++++++-
 drivers/hid/hid-input.c | 13 +++++++++----
 include/linux/hid.h     |  1 +
 3 files changed, 25 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index f4109fd657ff..f5004e2ca0c5 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -315,6 +315,7 @@ static s32 item_sdata(struct hid_item *item)
 
 static int hid_parser_global(struct hid_parser *parser, struct hid_item *item)
 {
+	__u32 raw_value;
 	switch (item->tag) {
 	case HID_GLOBAL_ITEM_TAG_PUSH:
 
@@ -365,7 +366,14 @@ static int hid_parser_global(struct hid_parser *parser, struct hid_item *item)
 		return 0;
 
 	case HID_GLOBAL_ITEM_TAG_UNIT_EXPONENT:
-		parser->global.unit_exponent = item_sdata(item);
+		/* Units exponent negative numbers are given through a
+		 * two's complement.
+		 * See "6.2.2.7 Global Items" for more information. */
+		raw_value = item_udata(item);
+		if (!(raw_value & 0xfffffff0))
+			parser->global.unit_exponent = hid_snto32(raw_value, 4);
+		else
+			parser->global.unit_exponent = raw_value;
 		return 0;
 
 	case HID_GLOBAL_ITEM_TAG_UNIT:
@@ -865,6 +873,12 @@ static s32 snto32(__u32 value, unsigned n)
 	return value & (1 << (n - 1)) ? value | (-1 << n) : value;
 }
 
+s32 hid_snto32(__u32 value, unsigned n)
+{
+	return snto32(value, n);
+}
+EXPORT_SYMBOL_GPL(hid_snto32);
+
 /*
  * Convert a signed 32-bit integer to a signed n-bit integer.
  */
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 1b0adc3f7803..007a9433bfa7 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -192,7 +192,6 @@ static int hidinput_setkeycode(struct input_dev *dev,
 	return -EINVAL;
 }
 
-
 /**
  * hidinput_calc_abs_res - calculate an absolute axis resolution
  * @field: the HID report field to calculate resolution for
@@ -235,17 +234,23 @@ __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code)
 	case ABS_MT_TOOL_Y:
 	case ABS_MT_TOUCH_MAJOR:
 	case ABS_MT_TOUCH_MINOR:
-		if (field->unit == 0x11) {		/* If centimeters */
+		if (field->unit & 0xffffff00)		/* Not a length */
+			return 0;
+		unit_exponent += hid_snto32(field->unit >> 4, 4) - 1;
+		switch (field->unit & 0xf) {
+		case 0x1:				/* If centimeters */
 			/* Convert to millimeters */
 			unit_exponent += 1;
-		} else if (field->unit == 0x13) {	/* If inches */
+			break;
+		case 0x3:				/* If inches */
 			/* Convert to millimeters */
 			prev = physical_extents;
 			physical_extents *= 254;
 			if (physical_extents < prev)
 				return 0;
 			unit_exponent -= 1;
-		} else {
+			break;
+		default:
 			return 0;
 		}
 		break;
diff --git a/include/linux/hid.h b/include/linux/hid.h
index c6bef8f54a82..4161bf2c0b5b 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -717,6 +717,7 @@ int hid_connect(struct hid_device *hid, unsigned int connect_mask);
 void hid_disconnect(struct hid_device *hid);
 const struct hid_device_id *hid_match_id(struct hid_device *hdev,
 					 const struct hid_device_id *id);
+s32 hid_snto32(__u32 value, unsigned n);
 
 /**
  * hid_map_usage - map usage input bits
-- 
cgit v1.2.3-55-g7522


From f262d1fa2c651a5e2f92b6aee8779597631cd5d4 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires
Date: Wed, 14 Nov 2012 16:59:16 +0100
Subject: HID: add usage_index in struct hid_usage.

Currently, there is no way to know the index of the current field
in the .input_mapping and .event callbacks  when this field is inside
an array of HID fields.
This patch adds this index to the struct hid_usage so that this
information is available to input_mapping and event callbacks.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@gmail.com>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-core.c | 4 ++++
 include/linux/hid.h    | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index f5004e2ca0c5..b5974cd45968 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -92,6 +92,7 @@ EXPORT_SYMBOL_GPL(hid_register_report);
 static struct hid_field *hid_register_field(struct hid_report *report, unsigned usages, unsigned values)
 {
 	struct hid_field *field;
+	int i;
 
 	if (report->maxfield == HID_MAX_FIELDS) {
 		hid_err(report->device, "too many fields in report\n");
@@ -110,6 +111,9 @@ static struct hid_field *hid_register_field(struct hid_report *report, unsigned
 	field->value = (s32 *)(field->usage + usages);
 	field->report = report;
 
+	for (i = 0; i < usages; i++)
+		field->usage[i].usage_index = i;
+
 	return field;
 }
 
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 4161bf2c0b5b..d2c42dd222c1 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -342,6 +342,7 @@ struct hid_collection {
 struct hid_usage {
 	unsigned  hid;			/* hid usage code */
 	unsigned  collection_index;	/* index into collection array */
+	unsigned  usage_index;		/* index into usage array */
 	/* hidinput data */
 	__u16     code;			/* input driver code */
 	__u8      type;			/* input driver type */
-- 
cgit v1.2.3-55-g7522


From af8036dd749fbf4e732161ff0f3874759b73be40 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires
Date: Wed, 14 Nov 2012 16:59:21 +0100
Subject: Input: introduce EV_MSC Timestamp

Some devices provides the actual timestamp (hid_dg_scan_time in win8 ones)
computed by the hardware itself. This value is global to the frame and is
not specific to the multitouch protocol.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@gmail.com>
Reviewed-by: Henrik Rydberg <rydberg@euromail.se>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 Documentation/input/event-codes.txt | 11 +++++++++++
 include/uapi/linux/input.h          |  1 +
 2 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/Documentation/input/event-codes.txt b/Documentation/input/event-codes.txt
index 53305bd08182..f1ea2c69648d 100644
--- a/Documentation/input/event-codes.txt
+++ b/Documentation/input/event-codes.txt
@@ -196,6 +196,17 @@ EV_MSC:
 EV_MSC events are used for input and output events that do not fall under other
 categories.
 
+A few EV_MSC codes have special meaning:
+
+* MSC_TIMESTAMP:
+  - Used to report the number of microseconds since the last reset. This event
+    should be coded as an uint32 value, which is allowed to wrap around with
+    no special consequence. It is assumed that the time difference between two
+    consecutive events is reliable on a reasonable time scale (hours).
+    A reset to zero can happen, in which case the time since the last event is
+    unknown.  If the device does not provide this information, the driver must
+    not provide it to user space.
+
 EV_LED:
 ----------
 EV_LED events are used for input and output to set and query the state of
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index 558828590a69..935119c698ac 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -851,6 +851,7 @@ struct input_keymap_entry {
 #define MSC_GESTURE		0x02
 #define MSC_RAW			0x03
 #define MSC_SCAN		0x04
+#define MSC_TIMESTAMP		0x05
 #define MSC_MAX			0x07
 #define MSC_CNT			(MSC_MAX+1)
 
-- 
cgit v1.2.3-55-g7522


From 29807d1e24b7cd696442d2f600057230f084b3c7 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires
Date: Wed, 14 Nov 2012 16:59:22 +0100
Subject: Input: mt: add input_mt_is_used

This patch extracts the test (slot->frame == mt->frame) so that it can
be used in third party drivers.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@gmail.com>
Reviewed-by: Henrik Rydberg <rydberg@euromail.se>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/input/input-mt.c | 2 +-
 include/linux/input/mt.h | 6 ++++++
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/input/input-mt.c b/drivers/input/input-mt.c
index c0ec7d42c3be..475b9d424eed 100644
--- a/drivers/input/input-mt.c
+++ b/drivers/input/input-mt.c
@@ -247,7 +247,7 @@ void input_mt_sync_frame(struct input_dev *dev)
 
 	if (mt->flags & INPUT_MT_DROP_UNUSED) {
 		for (s = mt->slots; s != mt->slots + mt->num_slots; s++) {
-			if (s->frame == mt->frame)
+			if (input_mt_is_used(mt, s))
 				continue;
 			input_mt_slot(dev, s - mt->slots);
 			input_event(dev, EV_ABS, ABS_MT_TRACKING_ID, -1);
diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h
index cc5cca774bab..2e86bd0bfba1 100644
--- a/include/linux/input/mt.h
+++ b/include/linux/input/mt.h
@@ -69,6 +69,12 @@ static inline bool input_mt_is_active(const struct input_mt_slot *slot)
 	return input_mt_get_value(slot, ABS_MT_TRACKING_ID) >= 0;
 }
 
+static inline bool input_mt_is_used(const struct input_mt *mt,
+				    const struct input_mt_slot *slot)
+{
+	return slot->frame == mt->frame;
+}
+
 int input_mt_init_slots(struct input_dev *dev, unsigned int num_slots,
 			unsigned int flags);
 void input_mt_destroy_slots(struct input_dev *dev);
-- 
cgit v1.2.3-55-g7522


From 5133375bb46a0d6c3fba07097caed7aa5e629ccd Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Thu, 15 Nov 2012 13:15:37 +0100
Subject: ACPI / PM: Fix build problem when CONFIG_ACPI or CONFIG_PM is not set

Commit e5cc8ef (ACPI / PM: Provide ACPI PM callback routines for
subsystems) introduced a build problem occuring if CONFIG_ACPI is
unset or CONFIG_PM is unset and errno.h is not included before
acpi.h, because in that case ENODEV used in acpi.h is undefined.

Fix the issue by making acpi.h include errno.h.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 0676b6ac57fa..5fdd87271518 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -25,6 +25,7 @@
 #ifndef _LINUX_ACPI_H
 #define _LINUX_ACPI_H
 
+#include <linux/errno.h>
 #include <linux/ioport.h>	/* for struct resource */
 
 #ifdef	CONFIG_ACPI
-- 
cgit v1.2.3-55-g7522


From 621eb19ce1ec216e03ad354cb0c4061736b2a436 Mon Sep 17 00:00:00 2001
From: J. Bruce Fields
Date: Wed, 14 Nov 2012 10:48:05 -0500
Subject: svcrpc: Revert "sunrpc/cache.h: replace simple_strtoul"

Commit bbf43dc888833ac0539e437dbaeb28bfd4fbab9f "sunrpc/cache.h: replace
simple_strtoul" introduced new range-checking which could cause get_int
to fail on unsigned integers too large to be represented as an int.

We could parse them as unsigned instead--but it turns out svcgssd is
actually passing down "-1" in some cases.  Which is perhaps stupid, but
there's nothing we can do about it now.

So just revert back to the previous "sloppy" behavior that accepts
either representation.

Cc: stable@vger.kernel.org
Reported-by: Sven Geggus <lists@fuchsschwanzdomain.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/cache.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index f792794f6634..5dc9ee4d616e 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -217,6 +217,8 @@ extern int qword_get(char **bpp, char *dest, int bufsize);
 static inline int get_int(char **bpp, int *anint)
 {
 	char buf[50];
+	char *ep;
+	int rv;
 	int len = qword_get(bpp, buf, sizeof(buf));
 
 	if (len < 0)
@@ -224,9 +226,11 @@ static inline int get_int(char **bpp, int *anint)
 	if (len == 0)
 		return -ENOENT;
 
-	if (kstrtoint(buf, 0, anint))
+	rv = simple_strtol(buf, &ep, 0);
+	if (*ep)
 		return -EINVAL;
 
+	*anint = rv;
 	return 0;
 }
 
-- 
cgit v1.2.3-55-g7522


From aa1acb0451bb27add173d9641d0b74c58889e693 Mon Sep 17 00:00:00 2001
From: hongbo.zhang
Date: Thu, 15 Nov 2012 18:56:42 +0800
Subject: Thermal: Add ST-Ericsson DB8500 thermal driver.

This driver is based on the thermal management framework in thermal_sys.c. A
thermal zone device is created with the trip points to which cooling devices
can be bound, the current cooling device is cpufreq, e.g. CPU frequency is
clipped down to cool the CPU, and other cooling devices can be added and bound
to the trip points dynamically.  The platform specific PRCMU interrupts are
used to active thermal update when trip points are reached.

Signed-off-by: hongbo.zhang <hongbo.zhang@linaro.com>
Reviewed-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Francesco Lavra <francescolavra.fl@gmail.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 .../devicetree/bindings/thermal/db8500-thermal.txt |  44 ++
 drivers/thermal/Kconfig                            |  20 +
 drivers/thermal/Makefile                           |   2 +
 drivers/thermal/db8500_cpufreq_cooling.c           | 108 +++++
 drivers/thermal/db8500_thermal.c                   | 531 +++++++++++++++++++++
 include/linux/platform_data/db8500_thermal.h       |  38 ++
 6 files changed, 743 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/thermal/db8500-thermal.txt
 create mode 100644 drivers/thermal/db8500_cpufreq_cooling.c
 create mode 100644 drivers/thermal/db8500_thermal.c
 create mode 100644 include/linux/platform_data/db8500_thermal.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/thermal/db8500-thermal.txt b/Documentation/devicetree/bindings/thermal/db8500-thermal.txt
new file mode 100644
index 000000000000..2e1c06fad81f
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/db8500-thermal.txt
@@ -0,0 +1,44 @@
+* ST-Ericsson DB8500 Thermal
+
+** Thermal node properties:
+
+- compatible : "stericsson,db8500-thermal";
+- reg : address range of the thermal sensor registers;
+- interrupts : interrupts generated from PRCMU;
+- interrupt-names : "IRQ_HOTMON_LOW" and "IRQ_HOTMON_HIGH";
+- num-trips : number of total trip points, this is required, set it 0 if none,
+  if greater than 0, the following properties must be defined;
+- tripN-temp : temperature of trip point N, should be in ascending order;
+- tripN-type : type of trip point N, should be one of "active" "passive" "hot"
+  "critical";
+- tripN-cdev-num : number of the cooling devices which can be bound to trip
+  point N, this is required if trip point N is defined, set it 0 if none,
+  otherwise the following cooling device names must be defined;
+- tripN-cdev-nameM : name of the No. M cooling device of trip point N;
+
+Usually the num-trips and tripN-*** are separated in board related dts files.
+
+Example:
+thermal@801573c0 {
+	compatible = "stericsson,db8500-thermal";
+	reg = <0x801573c0 0x40>;
+	interrupts = <21 0x4>, <22 0x4>;
+	interrupt-names = "IRQ_HOTMON_LOW", "IRQ_HOTMON_HIGH";
+
+	num-trips = <3>;
+
+	trip0-temp = <75000>;
+	trip0-type = "active";
+	trip0-cdev-num = <1>;
+	trip0-cdev-name0 = "thermal-cpufreq-0";
+
+	trip1-temp = <80000>;
+	trip1-type = "active";
+	trip1-cdev-num = <2>;
+	trip1-cdev-name0 = "thermal-cpufreq-0";
+	trip1-cdev-name1 = "thermal-fan";
+
+	trip2-temp = <85000>;
+	trip2-type = "critical";
+	trip2-cdev-num = <0>;
+}
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 99b6587ab8b3..d96da075c9f6 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -101,5 +101,25 @@ config EXYNOS_THERMAL
 	  If you say yes here you get support for TMU (Thermal Managment
 	  Unit) on SAMSUNG EXYNOS series of SoC.
 
+config DB8500_THERMAL
+	bool "DB8500 thermal management"
+	depends on ARCH_U8500
+	default y
+	help
+	  Adds DB8500 thermal management implementation according to the thermal
+	  management framework. A thermal zone with several trip points will be
+	  created. Cooling devices can be bound to the trip points to cool this
+	  thermal zone if trip points reached.
+
+config DB8500_CPUFREQ_COOLING
+	tristate "DB8500 cpufreq cooling"
+	depends on ARCH_U8500
+	depends on CPU_THERMAL
+	default y
+	help
+	  Adds DB8500 cpufreq cooling devices, and these cooling devices can be
+	  bound to thermal zone trip points. When a trip point reached, the
+	  bound cpufreq cooling device turns active to set CPU frequency low to
+	  cool down the CPU.
 
 endif
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 0b6b048f236d..d8da683245fc 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -16,3 +16,5 @@ obj-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
 obj-$(CONFIG_SPEAR_THERMAL)	+= spear_thermal.o
 obj-$(CONFIG_RCAR_THERMAL)	+= rcar_thermal.o
 obj-$(CONFIG_EXYNOS_THERMAL)	+= exynos_thermal.o
+obj-$(CONFIG_DB8500_THERMAL)	+= db8500_thermal.o
+obj-$(CONFIG_DB8500_CPUFREQ_COOLING)	+= db8500_cpufreq_cooling.o
diff --git a/drivers/thermal/db8500_cpufreq_cooling.c b/drivers/thermal/db8500_cpufreq_cooling.c
new file mode 100644
index 000000000000..4cf8e72af90a
--- /dev/null
+++ b/drivers/thermal/db8500_cpufreq_cooling.c
@@ -0,0 +1,108 @@
+/*
+ * db8500_cpufreq_cooling.c - DB8500 cpufreq works as cooling device.
+ *
+ * Copyright (C) 2012 ST-Ericsson
+ * Copyright (C) 2012 Linaro Ltd.
+ *
+ * Author: Hongbo Zhang <hongbo.zhang@linaro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/cpu_cooling.h>
+#include <linux/cpufreq.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+static int db8500_cpufreq_cooling_probe(struct platform_device *pdev)
+{
+	struct thermal_cooling_device *cdev;
+	struct cpumask mask_val;
+
+	/* make sure cpufreq driver has been initialized */
+	if (!cpufreq_frequency_get_table(0))
+		return -EPROBE_DEFER;
+
+	cpumask_set_cpu(0, &mask_val);
+	cdev = cpufreq_cooling_register(&mask_val);
+
+	if (IS_ERR_OR_NULL(cdev)) {
+		dev_err(&pdev->dev, "Failed to register cooling device\n");
+		return PTR_ERR(cdev);
+	}
+
+	platform_set_drvdata(pdev, cdev);
+
+	dev_info(&pdev->dev, "Cooling device registered: %s\n",	cdev->type);
+
+	return 0;
+}
+
+static int db8500_cpufreq_cooling_remove(struct platform_device *pdev)
+{
+	struct thermal_cooling_device *cdev = platform_get_drvdata(pdev);
+
+	cpufreq_cooling_unregister(cdev);
+
+	return 0;
+}
+
+static int db8500_cpufreq_cooling_suspend(struct platform_device *pdev,
+		pm_message_t state)
+{
+	return -ENOSYS;
+}
+
+static int db8500_cpufreq_cooling_resume(struct platform_device *pdev)
+{
+	return -ENOSYS;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id db8500_cpufreq_cooling_match[] = {
+	{ .compatible = "stericsson,db8500-cpufreq-cooling" },
+	{},
+};
+#else
+#define db8500_cpufreq_cooling_match NULL
+#endif
+
+static struct platform_driver db8500_cpufreq_cooling_driver = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "db8500-cpufreq-cooling",
+		.of_match_table = db8500_cpufreq_cooling_match,
+	},
+	.probe = db8500_cpufreq_cooling_probe,
+	.suspend = db8500_cpufreq_cooling_suspend,
+	.resume = db8500_cpufreq_cooling_resume,
+	.remove = db8500_cpufreq_cooling_remove,
+};
+
+static int __init db8500_cpufreq_cooling_init(void)
+{
+	return platform_driver_register(&db8500_cpufreq_cooling_driver);
+}
+
+static void __exit db8500_cpufreq_cooling_exit(void)
+{
+	platform_driver_unregister(&db8500_cpufreq_cooling_driver);
+}
+
+/* Should be later than db8500_cpufreq_register */
+late_initcall(db8500_cpufreq_cooling_init);
+module_exit(db8500_cpufreq_cooling_exit);
+
+MODULE_AUTHOR("Hongbo Zhang <hongbo.zhang@stericsson.com>");
+MODULE_DESCRIPTION("DB8500 cpufreq cooling driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/thermal/db8500_thermal.c b/drivers/thermal/db8500_thermal.c
new file mode 100644
index 000000000000..ec71ade3e317
--- /dev/null
+++ b/drivers/thermal/db8500_thermal.c
@@ -0,0 +1,531 @@
+/*
+ * db8500_thermal.c - DB8500 Thermal Management Implementation
+ *
+ * Copyright (C) 2012 ST-Ericsson
+ * Copyright (C) 2012 Linaro Ltd.
+ *
+ * Author: Hongbo Zhang <hongbo.zhang@linaro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/cpu_cooling.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/dbx500-prcmu.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_data/db8500_thermal.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+
+#define PRCMU_DEFAULT_MEASURE_TIME	0xFFF
+#define PRCMU_DEFAULT_LOW_TEMP		0
+
+struct db8500_thermal_zone {
+	struct thermal_zone_device *therm_dev;
+	struct mutex th_lock;
+	struct work_struct therm_work;
+	struct db8500_thsens_platform_data *trip_tab;
+	enum thermal_device_mode mode;
+	enum thermal_trend trend;
+	unsigned long cur_temp_pseudo;
+	unsigned int cur_index;
+};
+
+/* Local function to check if thermal zone matches cooling devices */
+static int db8500_thermal_match_cdev(struct thermal_cooling_device *cdev,
+		struct db8500_trip_point *trip_point)
+{
+	int i;
+
+	if (!strlen(cdev->type))
+		return -EINVAL;
+
+	for (i = 0; i < COOLING_DEV_MAX; i++) {
+		if (!strcmp(trip_point->cdev_name[i], cdev->type))
+			return 0;
+	}
+
+	return -ENODEV;
+}
+
+/* Callback to bind cooling device to thermal zone */
+static int db8500_cdev_bind(struct thermal_zone_device *thermal,
+		struct thermal_cooling_device *cdev)
+{
+	struct db8500_thermal_zone *pzone = thermal->devdata;
+	struct db8500_thsens_platform_data *ptrips = pzone->trip_tab;
+	unsigned long max_state, upper, lower;
+	int i, ret = -EINVAL;
+
+	cdev->ops->get_max_state(cdev, &max_state);
+
+	for (i = 0; i < ptrips->num_trips; i++) {
+		if (db8500_thermal_match_cdev(cdev, &ptrips->trip_points[i]))
+			continue;
+
+		upper = lower = i > max_state ? max_state : i;
+
+		ret = thermal_zone_bind_cooling_device(thermal, i, cdev,
+			upper, lower);
+
+		dev_info(&cdev->device, "%s bind to %d: %d-%s\n", cdev->type,
+			i, ret, ret ? "fail" : "succeed");
+	}
+
+	return ret;
+}
+
+/* Callback to unbind cooling device from thermal zone */
+static int db8500_cdev_unbind(struct thermal_zone_device *thermal,
+		struct thermal_cooling_device *cdev)
+{
+	struct db8500_thermal_zone *pzone = thermal->devdata;
+	struct db8500_thsens_platform_data *ptrips = pzone->trip_tab;
+	int i, ret = -EINVAL;
+
+	for (i = 0; i < ptrips->num_trips; i++) {
+		if (db8500_thermal_match_cdev(cdev, &ptrips->trip_points[i]))
+			continue;
+
+		ret = thermal_zone_unbind_cooling_device(thermal, i, cdev);
+
+		dev_info(&cdev->device, "%s unbind from %d: %s\n", cdev->type,
+			i, ret ? "fail" : "succeed");
+	}
+
+	return ret;
+}
+
+/* Callback to get current temperature */
+static int db8500_sys_get_temp(struct thermal_zone_device *thermal,
+		unsigned long *temp)
+{
+	struct db8500_thermal_zone *pzone = thermal->devdata;
+
+	/*
+	 * TODO: There is no PRCMU interface to get temperature data currently,
+	 * so a pseudo temperature is returned , it works for thermal framework
+	 * and this will be fixed when the PRCMU interface is available.
+	 */
+	*temp = pzone->cur_temp_pseudo;
+
+	return 0;
+}
+
+/* Callback to get temperature changing trend */
+static int db8500_sys_get_trend(struct thermal_zone_device *thermal,
+		int trip, enum thermal_trend *trend)
+{
+	struct db8500_thermal_zone *pzone = thermal->devdata;
+
+	*trend = pzone->trend;
+
+	return 0;
+}
+
+/* Callback to get thermal zone mode */
+static int db8500_sys_get_mode(struct thermal_zone_device *thermal,
+		enum thermal_device_mode *mode)
+{
+	struct db8500_thermal_zone *pzone = thermal->devdata;
+
+	mutex_lock(&pzone->th_lock);
+	*mode = pzone->mode;
+	mutex_unlock(&pzone->th_lock);
+
+	return 0;
+}
+
+/* Callback to set thermal zone mode */
+static int db8500_sys_set_mode(struct thermal_zone_device *thermal,
+		enum thermal_device_mode mode)
+{
+	struct db8500_thermal_zone *pzone = thermal->devdata;
+
+	mutex_lock(&pzone->th_lock);
+
+	pzone->mode = mode;
+	if (mode == THERMAL_DEVICE_ENABLED)
+		schedule_work(&pzone->therm_work);
+
+	mutex_unlock(&pzone->th_lock);
+
+	return 0;
+}
+
+/* Callback to get trip point type */
+static int db8500_sys_get_trip_type(struct thermal_zone_device *thermal,
+		int trip, enum thermal_trip_type *type)
+{
+	struct db8500_thermal_zone *pzone = thermal->devdata;
+	struct db8500_thsens_platform_data *ptrips = pzone->trip_tab;
+
+	if (trip >= ptrips->num_trips)
+		return -EINVAL;
+
+	*type = ptrips->trip_points[trip].type;
+
+	return 0;
+}
+
+/* Callback to get trip point temperature */
+static int db8500_sys_get_trip_temp(struct thermal_zone_device *thermal,
+		int trip, unsigned long *temp)
+{
+	struct db8500_thermal_zone *pzone = thermal->devdata;
+	struct db8500_thsens_platform_data *ptrips = pzone->trip_tab;
+
+	if (trip >= ptrips->num_trips)
+		return -EINVAL;
+
+	*temp = ptrips->trip_points[trip].temp;
+
+	return 0;
+}
+
+/* Callback to get critical trip point temperature */
+static int db8500_sys_get_crit_temp(struct thermal_zone_device *thermal,
+		unsigned long *temp)
+{
+	struct db8500_thermal_zone *pzone = thermal->devdata;
+	struct db8500_thsens_platform_data *ptrips = pzone->trip_tab;
+	int i;
+
+	for (i = ptrips->num_trips - 1; i > 0; i--) {
+		if (ptrips->trip_points[i].type == THERMAL_TRIP_CRITICAL) {
+			*temp = ptrips->trip_points[i].temp;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static struct thermal_zone_device_ops thdev_ops = {
+	.bind = db8500_cdev_bind,
+	.unbind = db8500_cdev_unbind,
+	.get_temp = db8500_sys_get_temp,
+	.get_trend = db8500_sys_get_trend,
+	.get_mode = db8500_sys_get_mode,
+	.set_mode = db8500_sys_set_mode,
+	.get_trip_type = db8500_sys_get_trip_type,
+	.get_trip_temp = db8500_sys_get_trip_temp,
+	.get_crit_temp = db8500_sys_get_crit_temp,
+};
+
+static void db8500_thermal_update_config(struct db8500_thermal_zone *pzone,
+		unsigned int idx, enum thermal_trend trend,
+		unsigned long next_low, unsigned long next_high)
+{
+	prcmu_stop_temp_sense();
+
+	pzone->cur_index = idx;
+	pzone->cur_temp_pseudo = (next_low + next_high)/2;
+	pzone->trend = trend;
+
+	prcmu_config_hotmon((u8)(next_low/1000), (u8)(next_high/1000));
+	prcmu_start_temp_sense(PRCMU_DEFAULT_MEASURE_TIME);
+}
+
+static irqreturn_t prcmu_low_irq_handler(int irq, void *irq_data)
+{
+	struct db8500_thermal_zone *pzone = irq_data;
+	struct db8500_thsens_platform_data *ptrips = pzone->trip_tab;
+	unsigned int idx = pzone->cur_index;
+	unsigned long next_low, next_high;
+
+	if (unlikely(idx == 0))
+		/* Meaningless for thermal management, ignoring it */
+		return IRQ_HANDLED;
+
+	if (idx == 1) {
+		next_high = ptrips->trip_points[0].temp;
+		next_low = PRCMU_DEFAULT_LOW_TEMP;
+	} else {
+		next_high = ptrips->trip_points[idx-1].temp;
+		next_low = ptrips->trip_points[idx-2].temp;
+	}
+	idx -= 1;
+
+	db8500_thermal_update_config(pzone, idx, THERMAL_TREND_DROPPING,
+		next_low, next_high);
+
+	dev_dbg(&pzone->therm_dev->device,
+		"PRCMU set max %ld, min %ld\n", next_high, next_low);
+
+	schedule_work(&pzone->therm_work);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t prcmu_high_irq_handler(int irq, void *irq_data)
+{
+	struct db8500_thermal_zone *pzone = irq_data;
+	struct db8500_thsens_platform_data *ptrips = pzone->trip_tab;
+	unsigned int idx = pzone->cur_index;
+	unsigned long next_low, next_high;
+
+	if (idx < ptrips->num_trips - 1) {
+		next_high = ptrips->trip_points[idx+1].temp;
+		next_low = ptrips->trip_points[idx].temp;
+		idx += 1;
+
+		db8500_thermal_update_config(pzone, idx, THERMAL_TREND_RAISING,
+			next_low, next_high);
+
+		dev_dbg(&pzone->therm_dev->device,
+		"PRCMU set max %ld, min %ld\n", next_high, next_low);
+	} else if (idx == ptrips->num_trips - 1)
+		pzone->cur_temp_pseudo = ptrips->trip_points[idx].temp + 1;
+
+	schedule_work(&pzone->therm_work);
+
+	return IRQ_HANDLED;
+}
+
+static void db8500_thermal_work(struct work_struct *work)
+{
+	enum thermal_device_mode cur_mode;
+	struct db8500_thermal_zone *pzone;
+
+	pzone = container_of(work, struct db8500_thermal_zone, therm_work);
+
+	mutex_lock(&pzone->th_lock);
+	cur_mode = pzone->mode;
+	mutex_unlock(&pzone->th_lock);
+
+	if (cur_mode == THERMAL_DEVICE_DISABLED)
+		return;
+
+	thermal_zone_device_update(pzone->therm_dev);
+	dev_dbg(&pzone->therm_dev->device, "thermal work finished.\n");
+}
+
+#ifdef CONFIG_OF
+static struct db8500_thsens_platform_data*
+		db8500_thermal_parse_dt(struct platform_device *pdev)
+{
+	struct db8500_thsens_platform_data *ptrips;
+	struct device_node *np = pdev->dev.of_node;
+	char prop_name[32];
+	const char *tmp_str;
+	u32 tmp_data;
+	int i, j;
+
+	ptrips = devm_kzalloc(&pdev->dev, sizeof(*ptrips), GFP_KERNEL);
+	if (!ptrips)
+		return NULL;
+
+	if (of_property_read_u32(np, "num-trips", &tmp_data))
+		goto err_parse_dt;
+
+	if (tmp_data > THERMAL_MAX_TRIPS)
+		goto err_parse_dt;
+
+	ptrips->num_trips = tmp_data;
+
+	for (i = 0; i < ptrips->num_trips; i++) {
+		sprintf(prop_name, "trip%d-temp", i);
+		if (of_property_read_u32(np, prop_name, &tmp_data))
+			goto err_parse_dt;
+
+		ptrips->trip_points[i].temp = tmp_data;
+
+		sprintf(prop_name, "trip%d-type", i);
+		if (of_property_read_string(np, prop_name, &tmp_str))
+			goto err_parse_dt;
+
+		if (!strcmp(tmp_str, "active"))
+			ptrips->trip_points[i].type = THERMAL_TRIP_ACTIVE;
+		else if (!strcmp(tmp_str, "passive"))
+			ptrips->trip_points[i].type = THERMAL_TRIP_PASSIVE;
+		else if (!strcmp(tmp_str, "hot"))
+			ptrips->trip_points[i].type = THERMAL_TRIP_HOT;
+		else if (!strcmp(tmp_str, "critical"))
+			ptrips->trip_points[i].type = THERMAL_TRIP_CRITICAL;
+		else
+			goto err_parse_dt;
+
+		sprintf(prop_name, "trip%d-cdev-num", i);
+		if (of_property_read_u32(np, prop_name, &tmp_data))
+			goto err_parse_dt;
+
+		if (tmp_data > COOLING_DEV_MAX)
+			goto err_parse_dt;
+
+		for (j = 0; j < tmp_data; j++) {
+			sprintf(prop_name, "trip%d-cdev-name%d", i, j);
+			if (of_property_read_string(np, prop_name, &tmp_str))
+				goto err_parse_dt;
+
+			if (strlen(tmp_str) >= THERMAL_NAME_LENGTH)
+				goto err_parse_dt;
+
+			strcpy(ptrips->trip_points[i].cdev_name[j], tmp_str);
+		}
+	}
+	return ptrips;
+
+err_parse_dt:
+	dev_err(&pdev->dev, "Parsing device tree data error.\n");
+	return NULL;
+}
+#else
+static inline struct db8500_thsens_platform_data*
+		db8500_thermal_parse_dt(struct platform_device *pdev)
+{
+	return NULL;
+}
+#endif
+
+static int db8500_thermal_probe(struct platform_device *pdev)
+{
+	struct db8500_thermal_zone *pzone = NULL;
+	struct db8500_thsens_platform_data *ptrips = NULL;
+	struct device_node *np = pdev->dev.of_node;
+	int low_irq, high_irq, ret = 0;
+	unsigned long dft_low, dft_high;
+
+	if (np)
+		ptrips = db8500_thermal_parse_dt(pdev);
+	else
+		ptrips = dev_get_platdata(&pdev->dev);
+
+	if (!ptrips)
+		return -EINVAL;
+
+	pzone = devm_kzalloc(&pdev->dev, sizeof(*pzone), GFP_KERNEL);
+	if (!pzone)
+		return -ENOMEM;
+
+	mutex_init(&pzone->th_lock);
+	mutex_lock(&pzone->th_lock);
+
+	pzone->mode = THERMAL_DEVICE_DISABLED;
+	pzone->trip_tab = ptrips;
+
+	INIT_WORK(&pzone->therm_work, db8500_thermal_work);
+
+	low_irq = platform_get_irq_byname(pdev, "IRQ_HOTMON_LOW");
+	if (low_irq < 0) {
+		dev_err(&pdev->dev, "Get IRQ_HOTMON_LOW failed.\n");
+		return low_irq;
+	}
+
+	ret = devm_request_threaded_irq(&pdev->dev, low_irq, NULL,
+		prcmu_low_irq_handler, IRQF_NO_SUSPEND | IRQF_ONESHOT,
+		"dbx500_temp_low", pzone);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to allocate temp low irq.\n");
+		return ret;
+	}
+
+	high_irq = platform_get_irq_byname(pdev, "IRQ_HOTMON_HIGH");
+	if (high_irq < 0) {
+		dev_err(&pdev->dev, "Get IRQ_HOTMON_HIGH failed.\n");
+		return high_irq;
+	}
+
+	ret = devm_request_threaded_irq(&pdev->dev, high_irq, NULL,
+		prcmu_high_irq_handler, IRQF_NO_SUSPEND | IRQF_ONESHOT,
+		"dbx500_temp_high", pzone);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to allocate temp high irq.\n");
+		return ret;
+	}
+
+	pzone->therm_dev = thermal_zone_device_register("db8500_thermal_zone",
+		ptrips->num_trips, 0, pzone, &thdev_ops, NULL, 0, 0);
+
+	if (IS_ERR_OR_NULL(pzone->therm_dev)) {
+		dev_err(&pdev->dev, "Register thermal zone device failed.\n");
+		return PTR_ERR(pzone->therm_dev);
+	}
+	dev_info(&pdev->dev, "Thermal zone device registered.\n");
+
+	dft_low = PRCMU_DEFAULT_LOW_TEMP;
+	dft_high = ptrips->trip_points[0].temp;
+
+	db8500_thermal_update_config(pzone, 0, THERMAL_TREND_STABLE,
+		dft_low, dft_high);
+
+	platform_set_drvdata(pdev, pzone);
+	pzone->mode = THERMAL_DEVICE_ENABLED;
+	mutex_unlock(&pzone->th_lock);
+
+	return 0;
+}
+
+static int db8500_thermal_remove(struct platform_device *pdev)
+{
+	struct db8500_thermal_zone *pzone = platform_get_drvdata(pdev);
+
+	thermal_zone_device_unregister(pzone->therm_dev);
+	cancel_work_sync(&pzone->therm_work);
+	mutex_destroy(&pzone->th_lock);
+
+	return 0;
+}
+
+static int db8500_thermal_suspend(struct platform_device *pdev,
+		pm_message_t state)
+{
+	struct db8500_thermal_zone *pzone = platform_get_drvdata(pdev);
+
+	flush_work(&pzone->therm_work);
+	prcmu_stop_temp_sense();
+
+	return 0;
+}
+
+static int db8500_thermal_resume(struct platform_device *pdev)
+{
+	struct db8500_thermal_zone *pzone = platform_get_drvdata(pdev);
+	struct db8500_thsens_platform_data *ptrips = pzone->trip_tab;
+	unsigned long dft_low, dft_high;
+
+	dft_low = PRCMU_DEFAULT_LOW_TEMP;
+	dft_high = ptrips->trip_points[0].temp;
+
+	db8500_thermal_update_config(pzone, 0, THERMAL_TREND_STABLE,
+		dft_low, dft_high);
+
+	return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id db8500_thermal_match[] = {
+	{ .compatible = "stericsson,db8500-thermal" },
+	{},
+};
+#else
+#define db8500_thermal_match NULL
+#endif
+
+static struct platform_driver db8500_thermal_driver = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "db8500-thermal",
+		.of_match_table = db8500_thermal_match,
+	},
+	.probe = db8500_thermal_probe,
+	.suspend = db8500_thermal_suspend,
+	.resume = db8500_thermal_resume,
+	.remove = db8500_thermal_remove,
+};
+
+module_platform_driver(db8500_thermal_driver);
+
+MODULE_AUTHOR("Hongbo Zhang <hongbo.zhang@stericsson.com>");
+MODULE_DESCRIPTION("DB8500 thermal driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/platform_data/db8500_thermal.h b/include/linux/platform_data/db8500_thermal.h
new file mode 100644
index 000000000000..3bf60902e902
--- /dev/null
+++ b/include/linux/platform_data/db8500_thermal.h
@@ -0,0 +1,38 @@
+/*
+ * db8500_thermal.h - DB8500 Thermal Management Implementation
+ *
+ * Copyright (C) 2012 ST-Ericsson
+ * Copyright (C) 2012 Linaro Ltd.
+ *
+ * Author: Hongbo Zhang <hongbo.zhang@linaro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DB8500_THERMAL_H_
+#define _DB8500_THERMAL_H_
+
+#include <linux/thermal.h>
+
+#define COOLING_DEV_MAX 8
+
+struct db8500_trip_point {
+	unsigned long temp;
+	enum thermal_trip_type type;
+	char cdev_name[COOLING_DEV_MAX][THERMAL_NAME_LENGTH];
+};
+
+struct db8500_thsens_platform_data {
+	struct db8500_trip_point trip_points[THERMAL_MAX_TRIPS];
+	int num_trips;
+};
+
+#endif /* _DB8500_THERMAL_H_ */
-- 
cgit v1.2.3-55-g7522


From fc05d5a30dc19dd4c6d161e551719a8c597c7890 Mon Sep 17 00:00:00 2001
From: Linus Walleij
Date: Thu, 4 Oct 2012 09:28:49 +0200
Subject: mtd: delete nomadik_nand driver

The nomadik_nand driver is really just a subset of the FSMC
NAND driver, and there are no users anymore so let's delete
it.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 drivers/mtd/nand/Kconfig                       |   6 -
 drivers/mtd/nand/Makefile                      |   1 -
 drivers/mtd/nand/nomadik_nand.c                | 235 -------------------------
 include/linux/platform_data/mtd-nomadik-nand.h |  16 --
 4 files changed, 258 deletions(-)
 delete mode 100644 drivers/mtd/nand/nomadik_nand.c
 delete mode 100644 include/linux/platform_data/mtd-nomadik-nand.h

(limited to 'include')

diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index ee803d611e4e..a803d9ba55bd 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -526,12 +526,6 @@ config MTD_NAND_MXC
 	  This enables the driver for the NAND flash controller on the
 	  MXC processors.
 
-config MTD_NAND_NOMADIK
-	tristate "ST Nomadik 8815 NAND support"
-	depends on ARCH_NOMADIK
-	help
-	  Driver for the NAND flash controller on the Nomadik, with ECC.
-
 config MTD_NAND_SH_FLCTL
 	tristate "Support for NAND on Renesas SuperH FLCTL"
 	depends on SUPERH || ARCH_SHMOBILE
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 38358c90771e..44fca0553365 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -49,7 +49,6 @@ obj-$(CONFIG_MTD_NAND_MXC)		+= mxc_nand.o
 obj-$(CONFIG_MTD_NAND_SOCRATES)		+= socrates_nand.o
 obj-$(CONFIG_MTD_NAND_TXX9NDFMC)	+= txx9ndfmc.o
 obj-$(CONFIG_MTD_NAND_NUC900)		+= nuc900_nand.o
-obj-$(CONFIG_MTD_NAND_NOMADIK)		+= nomadik_nand.o
 obj-$(CONFIG_MTD_NAND_MPC5121_NFC)	+= mpc5121_nfc.o
 obj-$(CONFIG_MTD_NAND_RICOH)		+= r852.o
 obj-$(CONFIG_MTD_NAND_JZ4740)		+= jz4740_nand.o
diff --git a/drivers/mtd/nand/nomadik_nand.c b/drivers/mtd/nand/nomadik_nand.c
deleted file mode 100644
index 9ee0c4edfacf..000000000000
--- a/drivers/mtd/nand/nomadik_nand.c
+++ /dev/null
@@ -1,235 +0,0 @@
-/*
- *  drivers/mtd/nand/nomadik_nand.c
- *
- *  Overview:
- *  	Driver for on-board NAND flash on Nomadik Platforms
- *
- * Copyright © 2007 STMicroelectronics Pvt. Ltd.
- * Author: Sachin Verma <sachin.verma@st.com>
- *
- * Copyright © 2009 Alessandro Rubini
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/nand.h>
-#include <linux/mtd/nand_ecc.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/partitions.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/platform_data/mtd-nomadik-nand.h>
-#include <mach/fsmc.h>
-
-#include <mtd/mtd-abi.h>
-
-struct nomadik_nand_host {
-	struct mtd_info		mtd;
-	struct nand_chip	nand;
-	void __iomem *data_va;
-	void __iomem *cmd_va;
-	void __iomem *addr_va;
-	struct nand_bbt_descr *bbt_desc;
-};
-
-static struct nand_ecclayout nomadik_ecc_layout = {
-	.eccbytes = 3 * 4,
-	.eccpos = { /* each subpage has 16 bytes: pos 2,3,4 hosts ECC */
-		0x02, 0x03, 0x04,
-		0x12, 0x13, 0x14,
-		0x22, 0x23, 0x24,
-		0x32, 0x33, 0x34},
-	/* let's keep bytes 5,6,7 for us, just in case we change ECC algo */
-	.oobfree = { {0x08, 0x08}, {0x18, 0x08}, {0x28, 0x08}, {0x38, 0x08} },
-};
-
-static void nomadik_ecc_control(struct mtd_info *mtd, int mode)
-{
-	/* No need to enable hw ecc, it's on by default */
-}
-
-static void nomadik_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
-{
-	struct nand_chip *nand = mtd->priv;
-	struct nomadik_nand_host *host = nand->priv;
-
-	if (cmd == NAND_CMD_NONE)
-		return;
-
-	if (ctrl & NAND_CLE)
-		writeb(cmd, host->cmd_va);
-	else
-		writeb(cmd, host->addr_va);
-}
-
-static int nomadik_nand_probe(struct platform_device *pdev)
-{
-	struct nomadik_nand_platform_data *pdata = pdev->dev.platform_data;
-	struct nomadik_nand_host *host;
-	struct mtd_info *mtd;
-	struct nand_chip *nand;
-	struct resource *res;
-	int ret = 0;
-
-	/* Allocate memory for the device structure (and zero it) */
-	host = kzalloc(sizeof(struct nomadik_nand_host), GFP_KERNEL);
-	if (!host) {
-		dev_err(&pdev->dev, "Failed to allocate device structure.\n");
-		return -ENOMEM;
-	}
-
-	/* Call the client's init function, if any */
-	if (pdata->init)
-		ret = pdata->init();
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Init function failed\n");
-		goto err;
-	}
-
-	/* ioremap three regions */
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_addr");
-	if (!res) {
-		ret = -EIO;
-		goto err_unmap;
-	}
-	host->addr_va = ioremap(res->start, resource_size(res));
-
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data");
-	if (!res) {
-		ret = -EIO;
-		goto err_unmap;
-	}
-	host->data_va = ioremap(res->start, resource_size(res));
-
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_cmd");
-	if (!res) {
-		ret = -EIO;
-		goto err_unmap;
-	}
-	host->cmd_va = ioremap(res->start, resource_size(res));
-
-	if (!host->addr_va || !host->data_va || !host->cmd_va) {
-		ret = -ENOMEM;
-		goto err_unmap;
-	}
-
-	/* Link all private pointers */
-	mtd = &host->mtd;
-	nand = &host->nand;
-	mtd->priv = nand;
-	nand->priv = host;
-
-	host->mtd.owner = THIS_MODULE;
-	nand->IO_ADDR_R = host->data_va;
-	nand->IO_ADDR_W = host->data_va;
-	nand->cmd_ctrl = nomadik_cmd_ctrl;
-
-	/*
-	 * This stanza declares ECC_HW but uses soft routines. It's because
-	 * HW claims to make the calculation but not the correction. However,
-	 * I haven't managed to get the desired data out of it until now.
-	 */
-	nand->ecc.mode = NAND_ECC_SOFT;
-	nand->ecc.layout = &nomadik_ecc_layout;
-	nand->ecc.hwctl = nomadik_ecc_control;
-	nand->ecc.size = 512;
-	nand->ecc.bytes = 3;
-
-	nand->options = pdata->options;
-
-	/*
-	 * Scan to find existence of the device
-	 */
-	if (nand_scan(&host->mtd, 1)) {
-		ret = -ENXIO;
-		goto err_unmap;
-	}
-
-	mtd_device_register(&host->mtd, pdata->parts, pdata->nparts);
-
-	platform_set_drvdata(pdev, host);
-	return 0;
-
- err_unmap:
-	if (host->cmd_va)
-		iounmap(host->cmd_va);
-	if (host->data_va)
-		iounmap(host->data_va);
-	if (host->addr_va)
-		iounmap(host->addr_va);
- err:
-	kfree(host);
-	return ret;
-}
-
-/*
- * Clean up routine
- */
-static int nomadik_nand_remove(struct platform_device *pdev)
-{
-	struct nomadik_nand_host *host = platform_get_drvdata(pdev);
-	struct nomadik_nand_platform_data *pdata = pdev->dev.platform_data;
-
-	if (pdata->exit)
-		pdata->exit();
-
-	if (host) {
-		nand_release(&host->mtd);
-		iounmap(host->cmd_va);
-		iounmap(host->data_va);
-		iounmap(host->addr_va);
-		kfree(host);
-	}
-	return 0;
-}
-
-static int nomadik_nand_suspend(struct device *dev)
-{
-	struct nomadik_nand_host *host = dev_get_drvdata(dev);
-	int ret = 0;
-	if (host)
-		ret = mtd_suspend(&host->mtd);
-	return ret;
-}
-
-static int nomadik_nand_resume(struct device *dev)
-{
-	struct nomadik_nand_host *host = dev_get_drvdata(dev);
-	if (host)
-		mtd_resume(&host->mtd);
-	return 0;
-}
-
-static const struct dev_pm_ops nomadik_nand_pm_ops = {
-	.suspend = nomadik_nand_suspend,
-	.resume = nomadik_nand_resume,
-};
-
-static struct platform_driver nomadik_nand_driver = {
-	.probe = nomadik_nand_probe,
-	.remove = nomadik_nand_remove,
-	.driver = {
-		.owner = THIS_MODULE,
-		.name = "nomadik_nand",
-		.pm = &nomadik_nand_pm_ops,
-	},
-};
-
-module_platform_driver(nomadik_nand_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("ST Microelectronics (sachin.verma@st.com)");
-MODULE_DESCRIPTION("NAND driver for Nomadik Platform");
diff --git a/include/linux/platform_data/mtd-nomadik-nand.h b/include/linux/platform_data/mtd-nomadik-nand.h
deleted file mode 100644
index c3c8254c22a5..000000000000
--- a/include/linux/platform_data/mtd-nomadik-nand.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __ASM_ARCH_NAND_H
-#define __ASM_ARCH_NAND_H
-
-struct nomadik_nand_platform_data {
-	struct mtd_partition *parts;
-	int nparts;
-	int options;
-	int (*init) (void);
-	int (*exit) (void);
-};
-
-#define NAND_IO_DATA	0x40000000
-#define NAND_IO_CMD	0x40800000
-#define NAND_IO_ADDR	0x41000000
-
-#endif				/* __ASM_ARCH_NAND_H */
-- 
cgit v1.2.3-55-g7522


From 6d7b42a447f92eb3e7e410bbf62042693eb040f7 Mon Sep 17 00:00:00 2001
From: Jean-Christophe PLAGNIOL-VILLARD
Date: Thu, 4 Oct 2012 15:14:16 +0200
Subject: mtd: fsmc_nand: pass the ale and cmd resource via resource

Do not use the platform_data to pass resource and be smart in the drivers.
Just pass it via resource

Switch to devm_request_and_ioremap at the sametime

Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-By: Vipin Kumar <vipin.kumar@st.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 .../devicetree/bindings/mtd/fsmc-nand.txt          | 12 +++---
 arch/arm/boot/dts/spear13xx.dtsi                   | 10 ++---
 arch/arm/boot/dts/spear300.dtsi                    |  8 ++--
 arch/arm/boot/dts/spear310.dtsi                    |  8 ++--
 arch/arm/boot/dts/spear320.dtsi                    |  8 ++--
 arch/arm/boot/dts/spear600.dtsi                    |  8 ++--
 arch/arm/mach-u300/core.c                          | 14 ++++++-
 drivers/mtd/nand/fsmc_nand.c                       | 44 ++++++----------------
 include/linux/mtd/fsmc.h                           |  3 --
 9 files changed, 49 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/mtd/fsmc-nand.txt b/Documentation/devicetree/bindings/mtd/fsmc-nand.txt
index e2c663b354d2..e3ea32e7de3e 100644
--- a/Documentation/devicetree/bindings/mtd/fsmc-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/fsmc-nand.txt
@@ -3,9 +3,7 @@
 Required properties:
 - compatible : "st,spear600-fsmc-nand"
 - reg : Address range of the mtd chip
-- reg-names: Should contain the reg names "fsmc_regs" and "nand_data"
-- st,ale-off : Chip specific offset to ALE
-- st,cle-off : Chip specific offset to CLE
+- reg-names: Should contain the reg names "fsmc_regs", "nand_data", "nand_addr" and "nand_cmd"
 
 Optional properties:
 - bank-width : Width (in bytes) of the device.  If not present, the width
@@ -19,10 +17,10 @@ Example:
 		#address-cells = <1>;
 		#size-cells = <1>;
 		reg = <0xd1800000 0x1000	/* FSMC Register */
-		       0xd2000000 0x4000>;	/* NAND Base */
-		reg-names = "fsmc_regs", "nand_data";
-		st,ale-off = <0x20000>;
-		st,cle-off = <0x10000>;
+		       0xd2000000 0x0010	/* NAND Base DATA */
+		       0xd2020000 0x0010	/* NAND Base ADDR */
+		       0xd2010000 0x0010>;	/* NAND Base CMD */
+		reg-names = "fsmc_regs", "nand_data", "nand_addr", "nand_cmd";
 
 		bank-width = <1>;
 		nand-skip-bbtscan;
diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi
index f7b84aced654..14a6d15c2a81 100644
--- a/arch/arm/boot/dts/spear13xx.dtsi
+++ b/arch/arm/boot/dts/spear13xx.dtsi
@@ -104,15 +104,15 @@
 			compatible = "st,spear600-fsmc-nand";
 			#address-cells = <1>;
 			#size-cells = <1>;
-			reg = <0xb0000000 0x1000	/* FSMC Register */
-			       0xb0800000 0x0010>;	/* NAND Base */
-			reg-names = "fsmc_regs", "nand_data";
+			reg = <0xb0000000 0x1000	/* FSMC Register*/
+			       0xb0800000 0x0010	/* NAND Base DATA */
+			       0xb0820000 0x0010	/* NAND Base ADDR */
+			       0xb0810000 0x0010>;	/* NAND Base CMD */
+			reg-names = "fsmc_regs", "nand_data", "nand_addr", "nand_cmd";
 			interrupts = <0 20 0x4
 				      0 21 0x4
 				      0 22 0x4
 				      0 23 0x4>;
-			st,ale-off = <0x20000>;
-			st,cle-off = <0x10000>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/spear300.dtsi b/arch/arm/boot/dts/spear300.dtsi
index ed3627c116cc..bc436387d7f9 100644
--- a/arch/arm/boot/dts/spear300.dtsi
+++ b/arch/arm/boot/dts/spear300.dtsi
@@ -38,10 +38,10 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			reg = <0x94000000 0x1000	/* FSMC Register */
-			       0x80000000 0x0010>;	/* NAND Base */
-			reg-names = "fsmc_regs", "nand_data";
-			st,ale-off = <0x20000>;
-			st,cle-off = <0x10000>;
+			       0x80000000 0x0010	/* NAND Base DATA */
+			       0x80020000 0x0010	/* NAND Base ADDR */
+			       0x80010000 0x0010>;	/* NAND Base CMD */
+			reg-names = "fsmc_regs", "nand_data", "nand_addr", "nand_cmd";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/spear310.dtsi b/arch/arm/boot/dts/spear310.dtsi
index 62fc4fb3e5f9..7840e529aba2 100644
--- a/arch/arm/boot/dts/spear310.dtsi
+++ b/arch/arm/boot/dts/spear310.dtsi
@@ -32,10 +32,10 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			reg = <0x44000000 0x1000	/* FSMC Register */
-			       0x40000000 0x0010>;	/* NAND Base */
-			reg-names = "fsmc_regs", "nand_data";
-			st,ale-off = <0x10000>;
-			st,cle-off = <0x20000>;
+			       0x40000000 0x0010	/* NAND Base DATA */
+			       0x40020000 0x0010	/* NAND Base ADDR */
+			       0x40010000 0x0010>;	/* NAND Base CMD */
+			reg-names = "fsmc_regs", "nand_data", "nand_addr", "nand_cmd";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/spear320.dtsi b/arch/arm/boot/dts/spear320.dtsi
index 1f49d69595a0..5ad820641ac0 100644
--- a/arch/arm/boot/dts/spear320.dtsi
+++ b/arch/arm/boot/dts/spear320.dtsi
@@ -38,10 +38,10 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			reg = <0x4c000000 0x1000	/* FSMC Register */
-			       0x50000000 0x0010>;	/* NAND Base */
-			reg-names = "fsmc_regs", "nand_data";
-			st,ale-off = <0x20000>;
-			st,cle-off = <0x10000>;
+			       0x50000000 0x0010	/* NAND Base DATA */
+			       0x50020000 0x0010	/* NAND Base ADDR */
+			       0x50010000 0x0010>;	/* NAND Base CMD */
+			reg-names = "fsmc_regs", "nand_data", "nand_addr", "nand_cmd";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/spear600.dtsi b/arch/arm/boot/dts/spear600.dtsi
index a3c36e47d7ef..4ecc66f5ac88 100644
--- a/arch/arm/boot/dts/spear600.dtsi
+++ b/arch/arm/boot/dts/spear600.dtsi
@@ -67,10 +67,10 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			reg = <0xd1800000 0x1000	/* FSMC Register */
-			       0xd2000000 0x4000>;	/* NAND Base */
-			reg-names = "fsmc_regs", "nand_data";
-			st,ale-off = <0x20000>;
-			st,cle-off = <0x10000>;
+			       0xd2000000 0x0010	/* NAND Base DATA */
+			       0xd2020000 0x0010	/* NAND Base ADDR */
+			       0xd2010000 0x0010>;	/* NAND Base CMD */
+			reg-names = "fsmc_regs", "nand_data", "nand_addr", "nand_cmd";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/mach-u300/core.c b/arch/arm/mach-u300/core.c
index b8efac4daed8..f642a1552346 100644
--- a/arch/arm/mach-u300/core.c
+++ b/arch/arm/mach-u300/core.c
@@ -251,6 +251,18 @@ static struct resource rtc_resources[] = {
  * but these are not yet used by the driver.
  */
 static struct resource fsmc_resources[] = {
+	{
+		.name  = "nand_addr",
+		.start = U300_NAND_CS0_PHYS_BASE + PLAT_NAND_ALE,
+		.end   = U300_NAND_CS0_PHYS_BASE + PLAT_NAND_ALE + SZ_16K - 1,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name  = "nand_cmd",
+		.start = U300_NAND_CS0_PHYS_BASE + PLAT_NAND_CLE,
+		.end   = U300_NAND_CS0_PHYS_BASE + PLAT_NAND_CLE + SZ_16K - 1,
+		.flags = IORESOURCE_MEM,
+	},
 	{
 		.name  = "nand_data",
 		.start = U300_NAND_CS0_PHYS_BASE,
@@ -1496,8 +1508,6 @@ static struct fsmc_nand_platform_data nand_platform_data = {
 	.nr_partitions = ARRAY_SIZE(u300_partitions),
 	.options = NAND_SKIP_BBTSCAN,
 	.width = FSMC_NAND_BW8,
-	.ale_off = PLAT_NAND_ALE,
-	.cle_off = PLAT_NAND_CLE,
 };
 
 static struct platform_device nand_device = {
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index 38d26240d8b1..cb8645087151 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -876,8 +876,6 @@ static int __devinit fsmc_nand_probe_config_dt(struct platform_device *pdev,
 			return -EINVAL;
 		}
 	}
-	of_property_read_u32(np, "st,ale-off", &pdata->ale_off);
-	of_property_read_u32(np, "st,cle-off", &pdata->cle_off);
 	if (of_get_property(np, "nand-skip-bbtscan", NULL))
 		pdata->options = NAND_SKIP_BBTSCAN;
 
@@ -935,41 +933,28 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	if (!res)
 		return -EINVAL;
 
-	if (!devm_request_mem_region(&pdev->dev, res->start, resource_size(res),
-				pdev->name)) {
-		dev_err(&pdev->dev, "Failed to get memory data resourse\n");
-		return -ENOENT;
-	}
-
-	host->data_pa = (dma_addr_t)res->start;
-	host->data_va = devm_ioremap(&pdev->dev, res->start,
-			resource_size(res));
+	host->data_va = devm_request_and_ioremap(&pdev->dev, res);
 	if (!host->data_va) {
 		dev_err(&pdev->dev, "data ioremap failed\n");
 		return -ENOMEM;
 	}
+	host->data_pa = (dma_addr_t)res->start;
 
-	if (!devm_request_mem_region(&pdev->dev, res->start + pdata->ale_off,
-			resource_size(res), pdev->name)) {
-		dev_err(&pdev->dev, "Failed to get memory ale resourse\n");
-		return -ENOENT;
-	}
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_addr");
+	if (!res)
+		return -EINVAL;
 
-	host->addr_va = devm_ioremap(&pdev->dev, res->start + pdata->ale_off,
-			resource_size(res));
+	host->addr_va = devm_request_and_ioremap(&pdev->dev, res);
 	if (!host->addr_va) {
 		dev_err(&pdev->dev, "ale ioremap failed\n");
 		return -ENOMEM;
 	}
 
-	if (!devm_request_mem_region(&pdev->dev, res->start + pdata->cle_off,
-			resource_size(res), pdev->name)) {
-		dev_err(&pdev->dev, "Failed to get memory cle resourse\n");
-		return -ENOENT;
-	}
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_cmd");
+	if (!res)
+		return -EINVAL;
 
-	host->cmd_va = devm_ioremap(&pdev->dev, res->start + pdata->cle_off,
-			resource_size(res));
+	host->cmd_va = devm_request_and_ioremap(&pdev->dev, res);
 	if (!host->cmd_va) {
 		dev_err(&pdev->dev, "ale ioremap failed\n");
 		return -ENOMEM;
@@ -979,14 +964,7 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	if (!res)
 		return -EINVAL;
 
-	if (!devm_request_mem_region(&pdev->dev, res->start, resource_size(res),
-			pdev->name)) {
-		dev_err(&pdev->dev, "Failed to get memory regs resourse\n");
-		return -ENOENT;
-	}
-
-	host->regs_va = devm_ioremap(&pdev->dev, res->start,
-			resource_size(res));
+	host->regs_va = devm_request_and_ioremap(&pdev->dev, res);
 	if (!host->regs_va) {
 		dev_err(&pdev->dev, "regs ioremap failed\n");
 		return -ENOMEM;
diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h
index b20029221fb1..d6ed61ef451d 100644
--- a/include/linux/mtd/fsmc.h
+++ b/include/linux/mtd/fsmc.h
@@ -155,9 +155,6 @@ struct fsmc_nand_platform_data {
 	unsigned int		width;
 	unsigned int		bank;
 
-	/* CLE, ALE offsets */
-	unsigned int		cle_off;
-	unsigned int		ale_off;
 	enum access_mode	mode;
 
 	void			(*select_bank)(uint32_t bank, uint32_t busw);
-- 
cgit v1.2.3-55-g7522


From 2f25ae97fe4b424d88d765797c46456c7c0f1bae Mon Sep 17 00:00:00 2001
From: Vipin Kumar
Date: Tue, 9 Oct 2012 16:14:53 +0530
Subject: mtd: nand: Increase the ecc placement locations to 640

Few devices like H27UBG8T2CTR have a writesize/oobsize of 8KB/640B.
This means that the maximum oobsize has gone up to 640 bytes and consequently
the maximum ecc placement locations have also gone up to 640.

Signed-off-by: Vipin Kumar <vipin.kumar@st.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 include/linux/mtd/mtd.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 81d61e704599..f9ac2897b86b 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -98,7 +98,7 @@ struct mtd_oob_ops {
 };
 
 #define MTD_MAX_OOBFREE_ENTRIES_LARGE	32
-#define MTD_MAX_ECCPOS_ENTRIES_LARGE	448
+#define MTD_MAX_ECCPOS_ENTRIES_LARGE	640
 /*
  * Internal ECC layout control structure. For historical reasons, there is a
  * similar, smaller struct nand_ecclayout_user (in mtd-abi.h) that is retained
-- 
cgit v1.2.3-55-g7522


From 5de0b52ea8f8f5149502867acff2efb5efaf1fc2 Mon Sep 17 00:00:00 2001
From: Huang Shijie
Date: Sat, 13 Oct 2012 13:03:29 -0400
Subject: mtd: gpmi: remove unneccessary header

The whole gpmi-nand driver has turned to pure devicetree supported.
So the linux/mtd/gpmi-nand.h is not neccessary now. Just remove it,
and move some macros to the gpmi-nand driver itself.

Signed-off-by: Huang Shijie <shijie8@gmail.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 drivers/mtd/nand/gpmi-nand/gpmi-lib.c  |  1 -
 drivers/mtd/nand/gpmi-nand/gpmi-nand.c |  7 +++-
 drivers/mtd/nand/gpmi-nand/gpmi-nand.h |  1 -
 include/linux/mtd/gpmi-nand.h          | 68 ----------------------------------
 4 files changed, 6 insertions(+), 71 deletions(-)
 delete mode 100644 include/linux/mtd/gpmi-nand.h

(limited to 'include')

diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
index 3502accd4bc3..1585c5b1c8bf 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
@@ -18,7 +18,6 @@
  * with this program; if not, write to the Free Software Foundation, Inc.,
  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
-#include <linux/mtd/gpmi-nand.h>
 #include <linux/delay.h>
 #include <linux/clk.h>
 
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index e2c56fc4574b..d37619882fa6 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -25,7 +25,6 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
-#include <linux/mtd/gpmi-nand.h>
 #include <linux/mtd/partitions.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/of.h>
@@ -33,6 +32,12 @@
 #include <linux/of_mtd.h>
 #include "gpmi-nand.h"
 
+/* Resource names for the GPMI NAND driver. */
+#define GPMI_NAND_GPMI_REGS_ADDR_RES_NAME  "gpmi-nand"
+#define GPMI_NAND_BCH_REGS_ADDR_RES_NAME   "bch"
+#define GPMI_NAND_BCH_INTERRUPT_RES_NAME   "bch"
+#define GPMI_NAND_DMA_INTERRUPT_RES_NAME   "gpmi-dma"
+
 /* add our owner bbt descriptor */
 static uint8_t scan_ff_pattern[] = { 0xff };
 static struct nand_bbt_descr gpmi_bbt_descr = {
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
index 7ac25c1e58f9..3d93a5e39090 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
@@ -130,7 +130,6 @@ struct gpmi_nand_data {
 	/* System Interface */
 	struct device		*dev;
 	struct platform_device	*pdev;
-	struct gpmi_nand_platform_data	*pdata;
 
 	/* Resources */
 	struct resources	resources;
diff --git a/include/linux/mtd/gpmi-nand.h b/include/linux/mtd/gpmi-nand.h
deleted file mode 100644
index ed3c4e09f3d1..000000000000
--- a/include/linux/mtd/gpmi-nand.h
+++ /dev/null
@@ -1,68 +0,0 @@
-/*
- * Copyright (C) 2011 Freescale Semiconductor, Inc. All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- */
-
-#ifndef __MACH_MXS_GPMI_NAND_H__
-#define __MACH_MXS_GPMI_NAND_H__
-
-/* The size of the resources is fixed. */
-#define GPMI_NAND_RES_SIZE	6
-
-/* Resource names for the GPMI NAND driver. */
-#define GPMI_NAND_GPMI_REGS_ADDR_RES_NAME  "gpmi-nand"
-#define GPMI_NAND_GPMI_INTERRUPT_RES_NAME  "GPMI NAND GPMI Interrupt"
-#define GPMI_NAND_BCH_REGS_ADDR_RES_NAME   "bch"
-#define GPMI_NAND_BCH_INTERRUPT_RES_NAME   "bch"
-#define GPMI_NAND_DMA_CHANNELS_RES_NAME    "GPMI NAND DMA Channels"
-#define GPMI_NAND_DMA_INTERRUPT_RES_NAME   "gpmi-dma"
-
-/**
- * struct gpmi_nand_platform_data - GPMI NAND driver platform data.
- *
- * This structure communicates platform-specific information to the GPMI NAND
- * driver that can't be expressed as resources.
- *
- * @platform_init:           A pointer to a function the driver will call to
- *                           initialize the platform (e.g., set up the pin mux).
- * @min_prop_delay_in_ns:    Minimum propagation delay of GPMI signals to and
- *                           from the NAND Flash device, in nanoseconds.
- * @max_prop_delay_in_ns:    Maximum propagation delay of GPMI signals to and
- *                           from the NAND Flash device, in nanoseconds.
- * @max_chip_count:          The maximum number of chips for which the driver
- *                           should configure the hardware. This value most
- *                           likely reflects the number of pins that are
- *                           connected to a NAND Flash device. If this is
- *                           greater than the SoC hardware can support, the
- *                           driver will print a message and fail to initialize.
- * @partitions:              An optional pointer to an array of partition
- *                           descriptions.
- * @partition_count:         The number of elements in the partitions array.
- */
-struct gpmi_nand_platform_data {
-	/* SoC hardware information. */
-	int		(*platform_init)(void);
-
-	/* NAND Flash information. */
-	unsigned int	min_prop_delay_in_ns;
-	unsigned int	max_prop_delay_in_ns;
-	unsigned int	max_chip_count;
-
-	/* Medium information. */
-	struct		mtd_partition *partitions;
-	unsigned	partition_count;
-};
-#endif
-- 
cgit v1.2.3-55-g7522


From e8a9d8f31c592eea89f1b0d3fd425e7a96944e88 Mon Sep 17 00:00:00 2001
From: Bastian Hecht
Date: Fri, 19 Oct 2012 12:15:34 +0200
Subject: mtd: sh_flctl: Minor cleanups

Some small fixes to avoid sparse and smatch complain. Other cosmetic fixes
as well.

- Change of the type of the member index in struct sh_flctl from signed
to unsigned. We use index by addressing array members, so unsigned is more
concise here. Adapt functions relying on sh_flctl::index.
- Remove a blurring cast in write_fiforeg().
- Apply consistent naming scheme when refering to the data buffer.
- Shorten some unnecessarily verbose functions.
- Remove spaces at start of lines.

Signed-off-by: Bastian Hecht <hechtb@gmail.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 drivers/mtd/nand/sh_flctl.c  | 37 ++++++++++++++++---------------------
 include/linux/mtd/sh_flctl.h |  2 +-
 2 files changed, 17 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index 4fbfe96e37a1..78d18c0f132f 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -225,7 +225,7 @@ static enum flctl_ecc_res_t wait_recfifo_ready
 
 		for (i = 0; i < 3; i++) {
 			uint8_t org;
-			int index;
+			unsigned int index;
 
 			data = readl(ecc_reg[i]);
 
@@ -305,28 +305,29 @@ static enum flctl_ecc_res_t read_ecfiforeg
 	return res;
 }
 
-static void write_fiforeg(struct sh_flctl *flctl, int rlen, int offset)
+static void write_fiforeg(struct sh_flctl *flctl, int rlen,
+						unsigned int offset)
 {
 	int i, len_4align;
-	unsigned long *data = (unsigned long *)&flctl->done_buff[offset];
-	void *fifo_addr = (void *)FLDTFIFO(flctl);
+	unsigned long *buf = (unsigned long *)&flctl->done_buff[offset];
 
 	len_4align = (rlen + 3) / 4;
 	for (i = 0; i < len_4align; i++) {
 		wait_wfifo_ready(flctl);
-		writel(cpu_to_be32(data[i]), fifo_addr);
+		writel(cpu_to_be32(buf[i]), FLDTFIFO(flctl));
 	}
 }
 
-static void write_ec_fiforeg(struct sh_flctl *flctl, int rlen, int offset)
+static void write_ec_fiforeg(struct sh_flctl *flctl, int rlen,
+						unsigned int offset)
 {
 	int i, len_4align;
-	unsigned long *data = (unsigned long *)&flctl->done_buff[offset];
+	unsigned long *buf = (unsigned long *)&flctl->done_buff[offset];
 
 	len_4align = (rlen + 3) / 4;
 	for (i = 0; i < len_4align; i++) {
 		wait_wecfifo_ready(flctl);
-		writel(cpu_to_be32(data[i]), FLECFIFO(flctl));
+		writel(cpu_to_be32(buf[i]), FLECFIFO(flctl));
 	}
 }
 
@@ -748,41 +749,35 @@ static void flctl_select_chip(struct mtd_info *mtd, int chipnr)
 static void flctl_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 {
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
-	int index = flctl->index;
 
-	memcpy(&flctl->done_buff[index], buf, len);
+	memcpy(&flctl->done_buff[flctl->index], buf, len);
 	flctl->index += len;
 }
 
 static uint8_t flctl_read_byte(struct mtd_info *mtd)
 {
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
-	int index = flctl->index;
 	uint8_t data;
 
-	data = flctl->done_buff[index];
+	data = flctl->done_buff[flctl->index];
 	flctl->index++;
 	return data;
 }
 
 static uint16_t flctl_read_word(struct mtd_info *mtd)
 {
-       struct sh_flctl *flctl = mtd_to_flctl(mtd);
-       int index = flctl->index;
-       uint16_t data;
-       uint16_t *buf = (uint16_t *)&flctl->done_buff[index];
+	struct sh_flctl *flctl = mtd_to_flctl(mtd);
+	uint16_t *buf = (uint16_t *)&flctl->done_buff[flctl->index];
 
-       data = *buf;
-       flctl->index += 2;
-       return data;
+	flctl->index += 2;
+	return *buf;
 }
 
 static void flctl_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
-	int index = flctl->index;
 
-	memcpy(buf, &flctl->done_buff[index], len);
+	memcpy(buf, &flctl->done_buff[flctl->index], len);
 	flctl->index += len;
 }
 
diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h
index 01e4b15b280e..481557688d05 100644
--- a/include/linux/mtd/sh_flctl.h
+++ b/include/linux/mtd/sh_flctl.h
@@ -147,7 +147,7 @@ struct sh_flctl {
 
 	uint8_t	done_buff[2048 + 64];	/* max size 2048 + 64 */
 	int	read_bytes;
-	int	index;
+	unsigned int index;
 	int	seqin_column;		/* column in SEQIN cmd */
 	int	seqin_page_addr;	/* page_addr in SEQIN cmd */
 	uint32_t seqin_read_cmd;		/* read cmd in SEQIN cmd */
-- 
cgit v1.2.3-55-g7522


From 83738d87e3a0a4096e1419a65b8228130d183df6 Mon Sep 17 00:00:00 2001
From: Bastian Hecht
Date: Fri, 19 Oct 2012 12:15:35 +0200
Subject: mtd: sh_flctl: Add DMA capabilty

The code probes if DMA channels can get allocated and tears them down at
removal/failure if needed.
If available it uses them to transfer the data part (not ECC). On
failure we fall back to PIO mode.

Based on Guennadi Liakhovetski's code from the sh_mmcif driver.

Signed-off-by: Bastian Hecht <hechtb@gmail.com>
Reviewed-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 drivers/mtd/nand/sh_flctl.c  | 173 ++++++++++++++++++++++++++++++++++++++++++-
 include/linux/mtd/sh_flctl.h |  12 +++
 2 files changed, 183 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index 78d18c0f132f..6dc0369aa44b 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -23,11 +23,15 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/completion.h>
 #include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/sh_dma.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 
@@ -106,6 +110,84 @@ static void wait_completion(struct sh_flctl *flctl)
 	writeb(0x0, FLTRCR(flctl));
 }
 
+static void flctl_dma_complete(void *param)
+{
+	struct sh_flctl *flctl = param;
+
+	complete(&flctl->dma_complete);
+}
+
+static void flctl_release_dma(struct sh_flctl *flctl)
+{
+	if (flctl->chan_fifo0_rx) {
+		dma_release_channel(flctl->chan_fifo0_rx);
+		flctl->chan_fifo0_rx = NULL;
+	}
+	if (flctl->chan_fifo0_tx) {
+		dma_release_channel(flctl->chan_fifo0_tx);
+		flctl->chan_fifo0_tx = NULL;
+	}
+}
+
+static void flctl_setup_dma(struct sh_flctl *flctl)
+{
+	dma_cap_mask_t mask;
+	struct dma_slave_config cfg;
+	struct platform_device *pdev = flctl->pdev;
+	struct sh_flctl_platform_data *pdata = pdev->dev.platform_data;
+	int ret;
+
+	if (!pdata)
+		return;
+
+	if (pdata->slave_id_fifo0_tx <= 0 || pdata->slave_id_fifo0_rx <= 0)
+		return;
+
+	/* We can only either use DMA for both Tx and Rx or not use it at all */
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	flctl->chan_fifo0_tx = dma_request_channel(mask, shdma_chan_filter,
+					    (void *)pdata->slave_id_fifo0_tx);
+	dev_dbg(&pdev->dev, "%s: TX: got channel %p\n", __func__,
+		flctl->chan_fifo0_tx);
+
+	if (!flctl->chan_fifo0_tx)
+		return;
+
+	memset(&cfg, 0, sizeof(cfg));
+	cfg.slave_id = pdata->slave_id_fifo0_tx;
+	cfg.direction = DMA_MEM_TO_DEV;
+	cfg.dst_addr = (dma_addr_t)FLDTFIFO(flctl);
+	cfg.src_addr = 0;
+	ret = dmaengine_slave_config(flctl->chan_fifo0_tx, &cfg);
+	if (ret < 0)
+		goto err;
+
+	flctl->chan_fifo0_rx = dma_request_channel(mask, shdma_chan_filter,
+					    (void *)pdata->slave_id_fifo0_rx);
+	dev_dbg(&pdev->dev, "%s: RX: got channel %p\n", __func__,
+		flctl->chan_fifo0_rx);
+
+	if (!flctl->chan_fifo0_rx)
+		goto err;
+
+	cfg.slave_id = pdata->slave_id_fifo0_rx;
+	cfg.direction = DMA_DEV_TO_MEM;
+	cfg.dst_addr = 0;
+	cfg.src_addr = (dma_addr_t)FLDTFIFO(flctl);
+	ret = dmaengine_slave_config(flctl->chan_fifo0_rx, &cfg);
+	if (ret < 0)
+		goto err;
+
+	init_completion(&flctl->dma_complete);
+
+	return;
+
+err:
+	flctl_release_dma(flctl);
+}
+
 static void set_addr(struct mtd_info *mtd, int column, int page_addr)
 {
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
@@ -261,6 +343,70 @@ static void wait_wecfifo_ready(struct sh_flctl *flctl)
 	timeout_error(flctl, __func__);
 }
 
+static int flctl_dma_fifo0_transfer(struct sh_flctl *flctl, unsigned long *buf,
+					int len, enum dma_data_direction dir)
+{
+	struct dma_async_tx_descriptor *desc = NULL;
+	struct dma_chan *chan;
+	enum dma_transfer_direction tr_dir;
+	dma_addr_t dma_addr;
+	dma_cookie_t cookie = -EINVAL;
+	uint32_t reg;
+	int ret;
+
+	if (dir == DMA_FROM_DEVICE) {
+		chan = flctl->chan_fifo0_rx;
+		tr_dir = DMA_DEV_TO_MEM;
+	} else {
+		chan = flctl->chan_fifo0_tx;
+		tr_dir = DMA_MEM_TO_DEV;
+	}
+
+	dma_addr = dma_map_single(chan->device->dev, buf, len, dir);
+
+	if (dma_addr)
+		desc = dmaengine_prep_slave_single(chan, dma_addr, len,
+			tr_dir, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+
+	if (desc) {
+		reg = readl(FLINTDMACR(flctl));
+		reg |= DREQ0EN;
+		writel(reg, FLINTDMACR(flctl));
+
+		desc->callback = flctl_dma_complete;
+		desc->callback_param = flctl;
+		cookie = dmaengine_submit(desc);
+
+		dma_async_issue_pending(chan);
+	} else {
+		/* DMA failed, fall back to PIO */
+		flctl_release_dma(flctl);
+		dev_warn(&flctl->pdev->dev,
+			 "DMA failed, falling back to PIO\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	ret =
+	wait_for_completion_timeout(&flctl->dma_complete,
+				msecs_to_jiffies(3000));
+
+	if (ret <= 0) {
+		chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+		dev_err(&flctl->pdev->dev, "wait_for_completion_timeout\n");
+	}
+
+out:
+	reg = readl(FLINTDMACR(flctl));
+	reg &= ~DREQ0EN;
+	writel(reg, FLINTDMACR(flctl));
+
+	dma_unmap_single(chan->device->dev, dma_addr, len, dir);
+
+	/* ret > 0 is success */
+	return ret;
+}
+
 static void read_datareg(struct sh_flctl *flctl, int offset)
 {
 	unsigned long data;
@@ -279,11 +425,20 @@ static void read_fiforeg(struct sh_flctl *flctl, int rlen, int offset)
 
 	len_4align = (rlen + 3) / 4;
 
+	/* initiate DMA transfer */
+	if (flctl->chan_fifo0_rx && rlen >= 32 &&
+		flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_DEV_TO_MEM) > 0)
+			goto convert;	/* DMA success */
+
+	/* do polling transfer */
 	for (i = 0; i < len_4align; i++) {
 		wait_rfifo_ready(flctl);
 		buf[i] = readl(FLDTFIFO(flctl));
-		buf[i] = be32_to_cpu(buf[i]);
 	}
+
+convert:
+	for (i = 0; i < len_4align; i++)
+		buf[i] = be32_to_cpu(buf[i]);
 }
 
 static enum flctl_ecc_res_t read_ecfiforeg
@@ -325,9 +480,19 @@ static void write_ec_fiforeg(struct sh_flctl *flctl, int rlen,
 	unsigned long *buf = (unsigned long *)&flctl->done_buff[offset];
 
 	len_4align = (rlen + 3) / 4;
+
+	for (i = 0; i < len_4align; i++)
+		buf[i] = cpu_to_be32(buf[i]);
+
+	/* initiate DMA transfer */
+	if (flctl->chan_fifo0_tx && rlen >= 32 &&
+		flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_MEM_TO_DEV) > 0)
+			return;	/* DMA success */
+
+	/* do polling transfer */
 	for (i = 0; i < len_4align; i++) {
 		wait_wecfifo_ready(flctl);
-		writel(cpu_to_be32(buf[i]), FLECFIFO(flctl));
+		writel(buf[i], FLECFIFO(flctl));
 	}
 }
 
@@ -925,6 +1090,8 @@ static int __devinit flctl_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_resume(&pdev->dev);
 
+	flctl_setup_dma(flctl);
+
 	ret = nand_scan_ident(flctl_mtd, 1, NULL);
 	if (ret)
 		goto err_chip;
@@ -942,6 +1109,7 @@ static int __devinit flctl_probe(struct platform_device *pdev)
 	return 0;
 
 err_chip:
+	flctl_release_dma(flctl);
 	pm_runtime_disable(&pdev->dev);
 	free_irq(irq, flctl);
 err_flste:
@@ -955,6 +1123,7 @@ static int __devexit flctl_remove(struct platform_device *pdev)
 {
 	struct sh_flctl *flctl = platform_get_drvdata(pdev);
 
+	flctl_release_dma(flctl);
 	nand_release(&flctl->mtd);
 	pm_runtime_disable(&pdev->dev);
 	free_irq(platform_get_irq(pdev, 0), flctl);
diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h
index 481557688d05..1c28f8879b1c 100644
--- a/include/linux/mtd/sh_flctl.h
+++ b/include/linux/mtd/sh_flctl.h
@@ -20,6 +20,7 @@
 #ifndef __SH_FLCTL_H__
 #define __SH_FLCTL_H__
 
+#include <linux/completion.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
@@ -107,6 +108,7 @@
 #define ESTERINTE	(0x1 << 24)	/* ECC error interrupt enable */
 #define AC1CLR		(0x1 << 19)	/* ECC FIFO clear */
 #define AC0CLR		(0x1 << 18)	/* Data FIFO clear */
+#define DREQ0EN		(0x1 << 16)	/* FLDTFIFODMA Request Enable */
 #define ECERB		(0x1 << 9)	/* ECC error */
 #define STERB		(0x1 << 8)	/* Status error */
 #define STERINTE	(0x1 << 4)	/* Status error enable */
@@ -138,6 +140,8 @@ enum flctl_ecc_res_t {
 	FL_TIMEOUT
 };
 
+struct dma_chan;
+
 struct sh_flctl {
 	struct mtd_info		mtd;
 	struct nand_chip	chip;
@@ -161,6 +165,11 @@ struct sh_flctl {
 	unsigned hwecc:1;	/* Hardware ECC (0 = disabled, 1 = enabled) */
 	unsigned holden:1;	/* Hardware has FLHOLDCR and HOLDEN is set */
 	unsigned qos_request:1;	/* QoS request to prevent deep power shutdown */
+
+	/* DMA related objects */
+	struct dma_chan		*chan_fifo0_rx;
+	struct dma_chan		*chan_fifo0_tx;
+	struct completion	dma_complete;
 };
 
 struct sh_flctl_platform_data {
@@ -170,6 +179,9 @@ struct sh_flctl_platform_data {
 
 	unsigned has_hwecc:1;
 	unsigned use_holden:1;
+
+	unsigned int            slave_id_fifo0_tx;
+	unsigned int            slave_id_fifo0_rx;
 };
 
 static inline struct sh_flctl *mtd_to_flctl(struct mtd_info *mtdinfo)
-- 
cgit v1.2.3-55-g7522


From 9ef525a9141b14d23613faad303cf48a20814f1b Mon Sep 17 00:00:00 2001
From: Robert P. J. Day
Date: Thu, 25 Oct 2012 09:43:10 -0400
Subject: mtd: Fix kernel-doc content to avoid warning.

Add missing colons to fix kernel-doc generation warnings.

Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 include/linux/mtd/nand.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 24e915957e4f..9d8a6048aacd 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -471,8 +471,8 @@ struct nand_buffers {
  *			non 0 if ONFI supported.
  * @onfi_params:	[INTERN] holds the ONFI page parameter when ONFI is
  *			supported, 0 otherwise.
- * @onfi_set_features	[REPLACEABLE] set the features for ONFI nand
- * @onfi_get_features	[REPLACEABLE] get the features for ONFI nand
+ * @onfi_set_features:	[REPLACEABLE] set the features for ONFI nand
+ * @onfi_get_features:	[REPLACEABLE] get the features for ONFI nand
  * @ecclayout:		[REPLACEABLE] the default ECC placement scheme
  * @bbt:		[INTERN] bad block table pointer
  * @bbt_td:		[REPLACEABLE] bad block table descriptor for flash
-- 
cgit v1.2.3-55-g7522


From 3e9ce49e0ef95e22790a74720f0068696b2477c9 Mon Sep 17 00:00:00 2001
From: Viresh Kumar
Date: Mon, 29 Oct 2012 22:47:26 +0530
Subject: mtd: map: Fix compilation warning

This patch is an attempt to fix following compilation warning.

In file included from drivers/mtd/chips/cfi_cmdset_0001.c:35:0:
drivers/mtd/chips/cfi_cmdset_0001.c: In function 'cfi_intelext_write_words':
include/linux/mtd/map.h:331:11: warning: 'r.x[0]' may be used uninitialized in this function [-Wmaybe-uninitialized]

I could have used uninitialized_var() too, but didn't used it as the final else
part of map_word_load() is missing. So there is a chance that it might be passed
uninitialized. Better initialize to zero.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 include/linux/mtd/map.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 3595a0236b0f..56c7936e0c65 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -328,7 +328,7 @@ static inline int map_word_bitsset(struct map_info *map, map_word val1, map_word
 
 static inline map_word map_word_load(struct map_info *map, const void *ptr)
 {
-	map_word r;
+	map_word r = {{0} };
 
 	if (map_bankwidth_is_1(map))
 		r.x[0] = *(unsigned char *)ptr;
-- 
cgit v1.2.3-55-g7522


From cd063bef414c51d79b9c6ea7a8ef8f9d319529bc Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger
Date: Wed, 7 Nov 2012 20:01:10 -0800
Subject: target/sbc: Seperate WRITE_SAME based on UNMAP flag in sbc_ops

This patch adds a new sbc_ops->execute_write_same_unmap() caller for use
with WRITE_SAME w/ UNMAP=1, and performs the ->execute_cmd() setup based
this bit within sbc_setup_write_same() code.

Also, makes the changes in sbc_parse_cdb() to handle a sense_reason_t
return from sbc_setup_write_same() on error.

Reported-by: Christoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_sbc.c     | 51 ++++++++++++++++--------------------
 include/target/target_core_backend.h |  1 +
 2 files changed, 24 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index b8024219cd4f..a5a8f463004b 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -235,26 +235,30 @@ static inline unsigned long long transport_lba_64_ext(unsigned char *cdb)
 	return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32;
 }
 
-static int sbc_write_same_supported(struct se_device *dev,
-		unsigned char *flags)
+static sense_reason_t
+sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *ops)
 {
 	if ((flags[0] & 0x04) || (flags[0] & 0x02)) {
 		pr_err("WRITE_SAME PBDATA and LBDATA"
 			" bits not supported for Block Discard"
 			" Emulation\n");
-		return -ENOSYS;
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
 	}
-
 	/*
-	 * Currently for the emulated case we only accept
-	 * tpws with the UNMAP=1 bit set.
+	 * Special case for WRITE_SAME w/ UNMAP=1 that ends up getting
+	 * translated into block discard requests within backend code.
 	 */
-	if (!(flags[0] & 0x08)) {
-		pr_err("WRITE_SAME w/o UNMAP bit not"
-			" supported for Block Discard Emulation\n");
-		return -ENOSYS;
+	if (flags[0] & 0x08) {
+		if (!ops->execute_write_same_unmap)
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+
+		cmd->execute_cmd = ops->execute_write_same_unmap;
+		return 0;
 	}
+	if (!ops->execute_write_same)
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
 
+	cmd->execute_cmd = ops->execute_write_same;
 	return 0;
 }
 
@@ -418,9 +422,6 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 				cmd->se_cmd_flags |= SCF_FUA;
 			break;
 		case WRITE_SAME_32:
-			if (!ops->execute_write_same)
-				return TCM_UNSUPPORTED_SCSI_OPCODE;
-
 			sectors = transport_get_sectors_32(cdb);
 			if (!sectors) {
 				pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not"
@@ -431,9 +432,9 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 			size = sbc_get_size(cmd, 1);
 			cmd->t_task_lba = get_unaligned_be64(&cdb[12]);
 
-			if (sbc_write_same_supported(dev, &cdb[10]) < 0)
-				return TCM_UNSUPPORTED_SCSI_OPCODE;
-			cmd->execute_cmd = ops->execute_write_same;
+			ret = sbc_setup_write_same(cmd, &cdb[10], ops);
+			if (ret < 0)
+				return ret;
 			break;
 		default:
 			pr_err("VARIABLE_LENGTH_CMD service action"
@@ -495,9 +496,6 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		cmd->execute_cmd = ops->execute_unmap;
 		break;
 	case WRITE_SAME_16:
-		if (!ops->execute_write_same)
-			return TCM_UNSUPPORTED_SCSI_OPCODE;
-
 		sectors = transport_get_sectors_16(cdb);
 		if (!sectors) {
 			pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not supported\n");
@@ -507,14 +505,11 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		size = sbc_get_size(cmd, 1);
 		cmd->t_task_lba = get_unaligned_be64(&cdb[2]);
 
-		if (sbc_write_same_supported(dev, &cdb[1]) < 0)
-			return TCM_UNSUPPORTED_SCSI_OPCODE;
-		cmd->execute_cmd = ops->execute_write_same;
+		ret = sbc_setup_write_same(cmd, &cdb[1], ops);
+		if (ret < 0)
+			return ret;
 		break;
 	case WRITE_SAME:
-		if (!ops->execute_write_same)
-			return TCM_UNSUPPORTED_SCSI_OPCODE;
-
 		sectors = transport_get_sectors_10(cdb);
 		if (!sectors) {
 			pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not supported\n");
@@ -528,9 +523,9 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		 * Follow sbcr26 with WRITE_SAME (10) and check for the existence
 		 * of byte 1 bit 3 UNMAP instead of original reserved field
 		 */
-		if (sbc_write_same_supported(dev, &cdb[1]) < 0)
-			return TCM_UNSUPPORTED_SCSI_OPCODE;
-		cmd->execute_cmd = ops->execute_write_same;
+		ret = sbc_setup_write_same(cmd, &cdb[1], ops);
+		if (ret < 0)
+			return ret;
 		break;
 	case VERIFY:
 		size = 0;
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index aa868090b9ab..3393ab10766c 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -41,6 +41,7 @@ struct sbc_ops {
 	sense_reason_t (*execute_rw)(struct se_cmd *cmd);
 	sense_reason_t (*execute_sync_cache)(struct se_cmd *cmd);
 	sense_reason_t (*execute_write_same)(struct se_cmd *cmd);
+	sense_reason_t (*execute_write_same_unmap)(struct se_cmd *cmd);
 	sense_reason_t (*execute_unmap)(struct se_cmd *cmd);
 };
 
-- 
cgit v1.2.3-55-g7522


From 773cbaf7460aa58c67d4dca83c3f8bca10323bbe Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger
Date: Thu, 15 Nov 2012 11:02:49 -0800
Subject: target: Add/check max_write_same_len device attribute + update block
 limits VPD

This patch adds a new max_write_same_len device attribute for use with
WRITE_SAME w/ UNMAP=0 backend emulation.  This can be useful for
lowering the default backend value (IBLOCK uses 0xFFFF).

Also, update block limits VPD emulation code in spc_emulate_evpd_b0() to
report MAXIMUM WRITE SAME LENGTH, and enforce max_write_same_len during
sbc_parse() -> sbc_setup_write_same() CDB sanity checking for all emulated
WRITE_SAME w/ UNMAP=0 cases.

(Robert: Move max_write_same_len check in sbc_setup_write_same() to
         check both WRITE_SAME w/ UNMAP=1 and w/ UNMAP=0 cases)

Cc: Christoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Robert Elliott <Elliott@hp.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_configfs.c |  4 ++++
 drivers/target/target_core_device.c   | 11 +++++++++++
 drivers/target/target_core_internal.h |  1 +
 drivers/target/target_core_sbc.c      |  7 +++++++
 drivers/target/target_core_spc.c      |  8 +++++++-
 include/target/target_core_base.h     |  3 +++
 6 files changed, 33 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 7b473b66da7b..2b141643f06e 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -676,6 +676,9 @@ SE_DEV_ATTR(unmap_granularity, S_IRUGO | S_IWUSR);
 DEF_DEV_ATTRIB(unmap_granularity_alignment);
 SE_DEV_ATTR(unmap_granularity_alignment, S_IRUGO | S_IWUSR);
 
+DEF_DEV_ATTRIB(max_write_same_len);
+SE_DEV_ATTR(max_write_same_len, S_IRUGO | S_IWUSR);
+
 CONFIGFS_EATTR_OPS(target_core_dev_attrib, se_dev_attrib, da_group);
 
 static struct configfs_attribute *target_core_dev_attrib_attrs[] = {
@@ -701,6 +704,7 @@ static struct configfs_attribute *target_core_dev_attrib_attrs[] = {
 	&target_core_dev_attrib_max_unmap_block_desc_count.attr,
 	&target_core_dev_attrib_unmap_granularity.attr,
 	&target_core_dev_attrib_unmap_granularity_alignment.attr,
+	&target_core_dev_attrib_max_write_same_len.attr,
 	NULL,
 };
 
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 599374e6d245..54439bc42dab 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -706,6 +706,16 @@ int se_dev_set_unmap_granularity_alignment(
 	return 0;
 }
 
+int se_dev_set_max_write_same_len(
+	struct se_device *dev,
+	u32 max_write_same_len)
+{
+	dev->dev_attrib.max_write_same_len = max_write_same_len;
+	pr_debug("dev[%p]: Set max_write_same_len: %u\n",
+			dev, dev->dev_attrib.max_write_same_len);
+	return 0;
+}
+
 int se_dev_set_emulate_dpo(struct se_device *dev, int flag)
 {
 	if (flag != 0 && flag != 1) {
@@ -1393,6 +1403,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	dev->dev_attrib.unmap_granularity = DA_UNMAP_GRANULARITY_DEFAULT;
 	dev->dev_attrib.unmap_granularity_alignment =
 				DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT;
+	dev->dev_attrib.max_write_same_len = DA_MAX_WRITE_SAME_LEN;
 	dev->dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS;
 	dev->dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS;
 
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index bc9c52284845..93e9c1f580b0 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -24,6 +24,7 @@ int	se_dev_set_max_unmap_lba_count(struct se_device *, u32);
 int	se_dev_set_max_unmap_block_desc_count(struct se_device *, u32);
 int	se_dev_set_unmap_granularity(struct se_device *, u32);
 int	se_dev_set_unmap_granularity_alignment(struct se_device *, u32);
+int	se_dev_set_max_write_same_len(struct se_device *, u32);
 int	se_dev_set_emulate_dpo(struct se_device *, int);
 int	se_dev_set_emulate_fua_write(struct se_device *, int);
 int	se_dev_set_emulate_fua_read(struct se_device *, int);
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index a5a8f463004b..45e11d0e38c4 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -238,12 +238,19 @@ static inline unsigned long long transport_lba_64_ext(unsigned char *cdb)
 static sense_reason_t
 sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *ops)
 {
+	unsigned int sectors = spc_get_write_same_sectors(cmd);
+
 	if ((flags[0] & 0x04) || (flags[0] & 0x02)) {
 		pr_err("WRITE_SAME PBDATA and LBDATA"
 			" bits not supported for Block Discard"
 			" Emulation\n");
 		return TCM_UNSUPPORTED_SCSI_OPCODE;
 	}
+	if (sectors > cmd->se_dev->dev_attrib.max_write_same_len) {
+		pr_warn("WRITE_SAME sectors: %u exceeds max_write_same_len: %u\n",
+			sectors, cmd->se_dev->dev_attrib.max_write_same_len);
+		return TCM_INVALID_CDB_FIELD;
+	}
 	/*
 	 * Special case for WRITE_SAME w/ UNMAP=1 that ends up getting
 	 * translated into block discard requests within backend code.
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 4b3c18305ec8..cf1b8bb310c4 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -465,7 +465,7 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 	 * Exit now if we don't support TP.
 	 */
 	if (!have_tp)
-		return 0;
+		goto max_write_same;
 
 	/*
 	 * Set MAXIMUM UNMAP LBA COUNT
@@ -491,6 +491,12 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 	if (dev->dev_attrib.unmap_granularity_alignment != 0)
 		buf[32] |= 0x80; /* Set the UGAVALID bit */
 
+	/*
+	 * MAXIMUM WRITE SAME LENGTH
+	 */
+max_write_same:
+	put_unaligned_be64(dev->dev_attrib.max_write_same_len, &buf[36]);
+
 	return 0;
 }
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 5350f6e580f0..645d90ac6097 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -71,6 +71,8 @@
 #define DA_UNMAP_GRANULARITY_DEFAULT		0
 /* Default unmap_granularity_alignment */
 #define DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT	0
+/* Default max_write_same_len, disabled by default */
+#define DA_MAX_WRITE_SAME_LEN			0
 /* Default max transfer length */
 #define DA_FABRIC_MAX_SECTORS			8192
 /* Emulation for Direct Page Out */
@@ -609,6 +611,7 @@ struct se_dev_attrib {
 	u32		max_unmap_block_desc_count;
 	u32		unmap_granularity;
 	u32		unmap_granularity_alignment;
+	u32		max_write_same_len;
 	struct se_device *da_dev;
 	struct config_group da_group;
 };
-- 
cgit v1.2.3-55-g7522


From 62532da9d5f47a7ced3b965aa73ffd5b1afbeb79 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich
Date: Thu, 15 Nov 2012 08:49:10 +0000
Subject: net: Add generic packet offload infrastructure.

Create a new data structure to contain the GRO/GSO callbacks and add
a new registration mechanism.

Singed-off-by: Vlad Yasevich <vyasevic@redhat.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 14 +++++++++
 net/core/dev.c            | 80 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 94 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7bf867c97043..d45a58db4ba3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1521,6 +1521,17 @@ struct packet_type {
 	struct list_head	list;
 };
 
+struct packet_offload {
+	__be16			type;	/* This is really htons(ether_type). */
+	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
+						netdev_features_t features);
+	int			(*gso_send_check)(struct sk_buff *skb);
+	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
+					       struct sk_buff *skb);
+	int			(*gro_complete)(struct sk_buff *skb);
+	struct list_head	list;
+};
+
 #include <linux/notifier.h>
 
 /* netdevice notifier chain. Please remember to update the rtnetlink
@@ -1615,6 +1626,9 @@ extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short
 extern void		dev_add_pack(struct packet_type *pt);
 extern void		dev_remove_pack(struct packet_type *pt);
 extern void		__dev_remove_pack(struct packet_type *pt);
+extern void		dev_add_offload(struct packet_offload *po);
+extern void		dev_remove_offload(struct packet_offload *po);
+extern void		__dev_remove_offload(struct packet_offload *po);
 
 extern struct net_device	*dev_get_by_flags_rcu(struct net *net, unsigned short flags,
 						      unsigned short mask);
diff --git a/net/core/dev.c b/net/core/dev.c
index 83232a1be1e7..6884f8783bdd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -176,8 +176,10 @@
 #define PTYPE_HASH_MASK	(PTYPE_HASH_SIZE - 1)
 
 static DEFINE_SPINLOCK(ptype_lock);
+static DEFINE_SPINLOCK(offload_lock);
 static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
 static struct list_head ptype_all __read_mostly;	/* Taps */
+static struct list_head offload_base __read_mostly;
 
 /*
  * The @dev_base_head list is protected by @dev_base_lock and the rtnl
@@ -470,6 +472,82 @@ void dev_remove_pack(struct packet_type *pt)
 }
 EXPORT_SYMBOL(dev_remove_pack);
 
+
+/**
+ *	dev_add_offload - register offload handlers
+ *	@po: protocol offload declaration
+ *
+ *	Add protocol offload handlers to the networking stack. The passed
+ *	&proto_offload is linked into kernel lists and may not be freed until
+ *	it has been removed from the kernel lists.
+ *
+ *	This call does not sleep therefore it can not
+ *	guarantee all CPU's that are in middle of receiving packets
+ *	will see the new offload handlers (until the next received packet).
+ */
+void dev_add_offload(struct packet_offload *po)
+{
+	struct list_head *head = &offload_base;
+
+	spin_lock(&offload_lock);
+	list_add_rcu(&po->list, head);
+	spin_unlock(&offload_lock);
+}
+EXPORT_SYMBOL(dev_add_offload);
+
+/**
+ *	__dev_remove_offload	 - remove offload handler
+ *	@po: packet offload declaration
+ *
+ *	Remove a protocol offload handler that was previously added to the
+ *	kernel offload handlers by dev_add_offload(). The passed &offload_type
+ *	is removed from the kernel lists and can be freed or reused once this
+ *	function returns.
+ *
+ *      The packet type might still be in use by receivers
+ *	and must not be freed until after all the CPU's have gone
+ *	through a quiescent state.
+ */
+void __dev_remove_offload(struct packet_offload *po)
+{
+	struct list_head *head = &offload_base;
+	struct packet_offload *po1;
+
+	spin_lock(&ptype_lock);
+
+	list_for_each_entry(po1, head, list) {
+		if (po == po1) {
+			list_del_rcu(&po->list);
+			goto out;
+		}
+	}
+
+	pr_warn("dev_remove_offload: %p not found\n", po);
+out:
+	spin_unlock(&ptype_lock);
+}
+EXPORT_SYMBOL(__dev_remove_offload);
+
+/**
+ *	dev_remove_offload	 - remove packet offload handler
+ *	@po: packet offload declaration
+ *
+ *	Remove a packet offload handler that was previously added to the kernel
+ *	offload handlers by dev_add_offload(). The passed &offload_type is
+ *	removed from the kernel lists and can be freed or reused once this
+ *	function returns.
+ *
+ *	This call sleeps to guarantee that no CPU is looking at the packet
+ *	type after return.
+ */
+void dev_remove_offload(struct packet_offload *po)
+{
+	__dev_remove_offload(po);
+
+	synchronize_net();
+}
+EXPORT_SYMBOL(dev_remove_offload);
+
 /******************************************************************************
 
 		      Device Boot-time Settings Routines
@@ -6661,6 +6739,8 @@ static int __init net_dev_init(void)
 	for (i = 0; i < PTYPE_HASH_SIZE; i++)
 		INIT_LIST_HEAD(&ptype_base[i]);
 
+	INIT_LIST_HEAD(&offload_base);
+
 	if (register_pernet_subsys(&netdev_net_ops))
 		goto out;
 
-- 
cgit v1.2.3-55-g7522


From 22061d8014455b01eb018bd6c35a1b3040ccc230 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich
Date: Thu, 15 Nov 2012 08:49:11 +0000
Subject: net: Switch to using the new packet offload infrustructure

Convert to using the new GSO/GRO registration mechanism and new
packet offload structure.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  6 ------
 net/core/dev.c            | 19 +++++++++----------
 net/ipv4/af_inet.c        |  5 +++++
 net/ipv6/af_inet6.c       |  6 ++++++
 4 files changed, 20 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d45a58db4ba3..61bc8483031f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1509,12 +1509,6 @@ struct packet_type {
 					 struct net_device *,
 					 struct packet_type *,
 					 struct net_device *);
-	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
-						netdev_features_t features);
-	int			(*gso_send_check)(struct sk_buff *skb);
-	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
-					       struct sk_buff *skb);
-	int			(*gro_complete)(struct sk_buff *skb);
 	bool			(*id_match)(struct packet_type *ptype,
 					    struct sock *sk);
 	void			*af_packet_priv;
diff --git a/net/core/dev.c b/net/core/dev.c
index 6884f8783bdd..cf843a256cc6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2072,7 +2072,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb,
 	netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
-	struct packet_type *ptype;
+	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
 	int vlan_depth = ETH_HLEN;
 	int err;
@@ -2101,9 +2101,8 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb,
 	}
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ptype,
-			&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
-		if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
+	list_for_each_entry_rcu(ptype, &offload_base, list) {
+		if (ptype->type == type && ptype->gso_segment) {
 			if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
 				err = ptype->gso_send_check(skb);
 				segs = ERR_PTR(err);
@@ -3522,9 +3521,9 @@ static void flush_backlog(void *arg)
 
 static int napi_gro_complete(struct sk_buff *skb)
 {
-	struct packet_type *ptype;
+	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
-	struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
+	struct list_head *head = &offload_base;
 	int err = -ENOENT;
 
 	if (NAPI_GRO_CB(skb)->count == 1) {
@@ -3534,7 +3533,7 @@ static int napi_gro_complete(struct sk_buff *skb)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
-		if (ptype->type != type || ptype->dev || !ptype->gro_complete)
+		if (ptype->type != type || !ptype->gro_complete)
 			continue;
 
 		err = ptype->gro_complete(skb);
@@ -3584,9 +3583,9 @@ EXPORT_SYMBOL(napi_gro_flush);
 enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct sk_buff **pp = NULL;
-	struct packet_type *ptype;
+	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
-	struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
+	struct list_head *head = &offload_base;
 	int same_flow;
 	int mac_len;
 	enum gro_result ret;
@@ -3599,7 +3598,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
-		if (ptype->type != type || ptype->dev || !ptype->gro_receive)
+		if (ptype->type != type || !ptype->gro_receive)
 			continue;
 
 		skb_set_network_header(skb, skb_gro_offset(skb));
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 766c59658563..4c99c5fdba3f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1662,6 +1662,10 @@ static int ipv4_proc_init(void);
 static struct packet_type ip_packet_type __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IP),
 	.func = ip_rcv,
+};
+
+static struct packet_offload ip_packet_offload __read_mostly = {
+	.type = cpu_to_be16(ETH_P_IP),
 	.gso_send_check = inet_gso_send_check,
 	.gso_segment = inet_gso_segment,
 	.gro_receive = inet_gro_receive,
@@ -1781,6 +1785,7 @@ static int __init inet_init(void)
 
 	ipfrag_init();
 
+	dev_add_offload(&ip_packet_offload);
 	dev_add_pack(&ip_packet_type);
 
 	rc = 0;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index a974247a9ae4..6e245177608c 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -938,6 +938,10 @@ out_unlock:
 static struct packet_type ipv6_packet_type __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IPV6),
 	.func = ipv6_rcv,
+};
+
+static struct packet_offload ipv6_packet_offload __read_mostly = {
+	.type = cpu_to_be16(ETH_P_IPV6),
 	.gso_send_check = ipv6_gso_send_check,
 	.gso_segment = ipv6_gso_segment,
 	.gro_receive = ipv6_gro_receive,
@@ -946,6 +950,7 @@ static struct packet_type ipv6_packet_type __read_mostly = {
 
 static int __init ipv6_packet_init(void)
 {
+	dev_add_offload(&ipv6_packet_offload);
 	dev_add_pack(&ipv6_packet_type);
 	return 0;
 }
@@ -953,6 +958,7 @@ static int __init ipv6_packet_init(void)
 static void ipv6_packet_cleanup(void)
 {
 	dev_remove_pack(&ipv6_packet_type);
+	dev_remove_offload(&ipv6_packet_offload);
 }
 
 static int __net_init ipv6_init_mibs(struct net *net)
-- 
cgit v1.2.3-55-g7522


From de27d001d187721de775ed9e0c485aa6f517c745 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich
Date: Thu, 15 Nov 2012 08:49:12 +0000
Subject: net: Add net protocol offload registration infrustructure

Create a new data structure for IPv4 protocols that holds GRO/GSO
callbacks and a new array to track the protocols that register GRO/GSO.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/protocol.h | 12 ++++++++++++
 net/ipv4/af_inet.c     | 12 ++++++++++++
 net/ipv4/protocol.c    | 21 +++++++++++++++++++++
 3 files changed, 45 insertions(+)

(limited to 'include')

diff --git a/include/net/protocol.h b/include/net/protocol.h
index 929528c73fe8..d8ecb17b1231 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -77,6 +77,15 @@ struct inet6_protocol {
 #define INET6_PROTO_GSO_EXTHDR	0x4
 #endif
 
+struct net_offload {
+	int			(*gso_send_check)(struct sk_buff *skb);
+	struct sk_buff	       *(*gso_segment)(struct sk_buff *skb,
+					       netdev_features_t features);
+	struct sk_buff	      **(*gro_receive)(struct sk_buff **head,
+					       struct sk_buff *skb);
+	int			(*gro_complete)(struct sk_buff *skb);
+};
+
 /* This is used to register socket interfaces for IP protocols.  */
 struct inet_protosw {
 	struct list_head list;
@@ -96,6 +105,7 @@ struct inet_protosw {
 #define INET_PROTOSW_ICSK      0x04  /* Is this an inet_connection_sock? */
 
 extern const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
+extern const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS];
 
 #if IS_ENABLED(CONFIG_IPV6)
 extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
@@ -103,6 +113,8 @@ extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
 
 extern int	inet_add_protocol(const struct net_protocol *prot, unsigned char num);
 extern int	inet_del_protocol(const struct net_protocol *prot, unsigned char num);
+extern int	inet_add_offload(const struct net_offload *prot, unsigned char num);
+extern int	inet_del_offload(const struct net_offload *prot, unsigned char num);
 extern void	inet_register_protosw(struct inet_protosw *p);
 extern void	inet_unregister_protosw(struct inet_protosw *p);
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4c99c5fdba3f..3918d869d6d4 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1566,6 +1566,13 @@ static const struct net_protocol tcp_protocol = {
 	.netns_ok	=	1,
 };
 
+static const struct net_offload tcp_offload = {
+	.gso_send_check	=	tcp_v4_gso_send_check,
+	.gso_segment	=	tcp_tso_segment,
+	.gro_receive	=	tcp4_gro_receive,
+	.gro_complete	=	tcp4_gro_complete,
+};
+
 static const struct net_protocol udp_protocol = {
 	.handler =	udp_rcv,
 	.err_handler =	udp_err,
@@ -1575,6 +1582,11 @@ static const struct net_protocol udp_protocol = {
 	.netns_ok =	1,
 };
 
+static const struct net_offload udp_offload = {
+	.gso_send_check = udp4_ufo_send_check,
+	.gso_segment = udp4_ufo_fragment,
+};
+
 static const struct net_protocol icmp_protocol = {
 	.handler =	icmp_rcv,
 	.err_handler =	ping_err,
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 8918eff1426d..0f9d09f54bd9 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -29,6 +29,7 @@
 #include <net/protocol.h>
 
 const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
+const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
 
 /*
  *	Add a protocol handler to the hash tables
@@ -41,6 +42,13 @@ int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
 }
 EXPORT_SYMBOL(inet_add_protocol);
 
+int inet_add_offload(const struct net_offload *prot, unsigned char protocol)
+{
+	return !cmpxchg((const struct net_offload **)&inet_offloads[protocol],
+			NULL, prot) ? 0 : -1;
+}
+EXPORT_SYMBOL(inet_add_offload);
+
 /*
  *	Remove a protocol from the hash tables.
  */
@@ -57,3 +65,16 @@ int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol)
 	return ret;
 }
 EXPORT_SYMBOL(inet_del_protocol);
+
+int inet_del_offload(const struct net_offload *prot, unsigned char protocol)
+{
+	int ret;
+
+	ret = (cmpxchg((const struct net_offload **)&inet_offloads[protocol],
+		       prot, NULL) == prot) ? 0 : -1;
+
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL(inet_del_offload);
-- 
cgit v1.2.3-55-g7522


From 8ca896cfdd17f32f5aa2747644733ebf3725360d Mon Sep 17 00:00:00 2001
From: Vlad Yasevich
Date: Thu, 15 Nov 2012 08:49:13 +0000
Subject: ipv6: Add new offload registration infrastructure.

Create a new data structure for IPv6 protocols that holds GRO/GSO
callbacks and a new array to track the protocols that register GRO/GSO.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/protocol.h |  4 ++++
 net/ipv6/exthdrs.c     |  8 ++++++++
 net/ipv6/protocol.c    | 21 +++++++++++++++++++++
 net/ipv6/tcp_ipv6.c    |  7 +++++++
 net/ipv6/udp.c         |  5 +++++
 5 files changed, 45 insertions(+)

(limited to 'include')

diff --git a/include/net/protocol.h b/include/net/protocol.h
index d8ecb17b1231..637e1bb6a76e 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -84,6 +84,7 @@ struct net_offload {
 	struct sk_buff	      **(*gro_receive)(struct sk_buff **head,
 					       struct sk_buff *skb);
 	int			(*gro_complete)(struct sk_buff *skb);
+	unsigned int		flags;	/* Flags used by IPv6 for now */
 };
 
 /* This is used to register socket interfaces for IP protocols.  */
@@ -109,6 +110,7 @@ extern const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS];
 
 #if IS_ENABLED(CONFIG_IPV6)
 extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
+extern const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS];
 #endif
 
 extern int	inet_add_protocol(const struct net_protocol *prot, unsigned char num);
@@ -121,6 +123,8 @@ extern void	inet_unregister_protosw(struct inet_protosw *p);
 #if IS_ENABLED(CONFIG_IPV6)
 extern int	inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num);
 extern int	inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num);
+extern int	inet6_add_offload(const struct net_offload *prot, unsigned char num);
+extern int	inet6_del_offload(const struct net_offload *prot, unsigned char num);
 extern int	inet6_register_protosw(struct inet_protosw *p);
 extern void	inet6_unregister_protosw(struct inet_protosw *p);
 #endif
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index f005acc58b2a..cb6f0828ca44 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -531,11 +531,19 @@ static const struct inet6_protocol rthdr_protocol = {
 	.flags		=	INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR,
 };
 
+static const struct net_offload rthdr_offload = {
+	.flags		=	INET6_PROTO_GSO_EXTHDR,
+};
+
 static const struct inet6_protocol destopt_protocol = {
 	.handler	=	ipv6_destopt_rcv,
 	.flags		=	INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR,
 };
 
+static const struct net_offload dstopt_offload = {
+	.flags		=	INET6_PROTO_GSO_EXTHDR,
+};
+
 static const struct inet6_protocol nodata_protocol = {
 	.handler	=	dst_discard,
 	.flags		=	INET6_PROTO_NOPOLICY,
diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c
index 053082dfc93e..f7c53a7d5cb0 100644
--- a/net/ipv6/protocol.c
+++ b/net/ipv6/protocol.c
@@ -26,6 +26,7 @@
 #include <net/protocol.h>
 
 const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly;
+const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS] __read_mostly;
 
 int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol)
 {
@@ -34,6 +35,13 @@ int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol
 }
 EXPORT_SYMBOL(inet6_add_protocol);
 
+int inet6_add_offload(const struct net_offload *prot, unsigned char protocol)
+{
+	return !cmpxchg((const struct net_offload **)&inet6_offloads[protocol],
+			NULL, prot) ? 0 : -1;
+}
+EXPORT_SYMBOL(inet6_add_offload);
+
 /*
  *	Remove a protocol from the hash tables.
  */
@@ -50,3 +58,16 @@ int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol
 	return ret;
 }
 EXPORT_SYMBOL(inet6_del_protocol);
+
+int inet6_del_offload(const struct net_offload *prot, unsigned char protocol)
+{
+	int ret;
+
+	ret = (cmpxchg((const struct net_offload **)&inet6_offloads[protocol],
+		       prot, NULL) == prot) ? 0 : -1;
+
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL(inet6_del_offload);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c73d0ebde9c8..6884a95be433 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2073,6 +2073,13 @@ static const struct inet6_protocol tcpv6_protocol = {
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
+static const struct net_offload tcpv6_offload = {
+	.gso_send_check	=	tcp_v6_gso_send_check,
+	.gso_segment	=	tcp_tso_segment,
+	.gro_receive	=	tcp6_gro_receive,
+	.gro_complete	=	tcp6_gro_complete,
+};
+
 static struct inet_protosw tcpv6_protosw = {
 	.type		=	SOCK_STREAM,
 	.protocol	=	IPPROTO_TCP,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index fc9997260a6b..3ad44e176503 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1443,6 +1443,11 @@ static const struct inet6_protocol udpv6_protocol = {
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
+static const struct net_offload udpv6_offload = {
+	.gso_send_check =	udp6_ufo_send_check,
+	.gso_segment	=	udp6_ufo_fragment,
+};
+
 /* ------------------------------------------------------------------------ */
 #ifdef CONFIG_PROC_FS
 
-- 
cgit v1.2.3-55-g7522


From bca49f843eac59cbb1ddd1f4a5d65fcc23b62efd Mon Sep 17 00:00:00 2001
From: Vlad Yasevich
Date: Thu, 15 Nov 2012 08:49:14 +0000
Subject: ipv4: Switch to using the new offload infrastructure.

Switch IPv4 code base to using the new GRO/GSO calls and data.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/protocol.h |  6 ------
 net/ipv4/af_inet.c     | 30 ++++++++++++++++--------------
 2 files changed, 16 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/protocol.h b/include/net/protocol.h
index 637e1bb6a76e..3bb70510b686 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -40,12 +40,6 @@ struct net_protocol {
 	void			(*early_demux)(struct sk_buff *skb);
 	int			(*handler)(struct sk_buff *skb);
 	void			(*err_handler)(struct sk_buff *skb, u32 info);
-	int			(*gso_send_check)(struct sk_buff *skb);
-	struct sk_buff	       *(*gso_segment)(struct sk_buff *skb,
-					       netdev_features_t features);
-	struct sk_buff	      **(*gro_receive)(struct sk_buff **head,
-					       struct sk_buff *skb);
-	int			(*gro_complete)(struct sk_buff *skb);
 	unsigned int		no_policy:1,
 				netns_ok:1;
 };
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 3918d869d6d4..66f63ce07ac8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1251,7 +1251,7 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
 
 static int inet_gso_send_check(struct sk_buff *skb)
 {
-	const struct net_protocol *ops;
+	const struct net_offload *ops;
 	const struct iphdr *iph;
 	int proto;
 	int ihl;
@@ -1275,7 +1275,7 @@ static int inet_gso_send_check(struct sk_buff *skb)
 	err = -EPROTONOSUPPORT;
 
 	rcu_read_lock();
-	ops = rcu_dereference(inet_protos[proto]);
+	ops = rcu_dereference(inet_offloads[proto]);
 	if (likely(ops && ops->gso_send_check))
 		err = ops->gso_send_check(skb);
 	rcu_read_unlock();
@@ -1288,7 +1288,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
-	const struct net_protocol *ops;
+	const struct net_offload *ops;
 	struct iphdr *iph;
 	int proto;
 	int ihl;
@@ -1325,7 +1325,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	segs = ERR_PTR(-EPROTONOSUPPORT);
 
 	rcu_read_lock();
-	ops = rcu_dereference(inet_protos[proto]);
+	ops = rcu_dereference(inet_offloads[proto]);
 	if (likely(ops && ops->gso_segment))
 		segs = ops->gso_segment(skb, features);
 	rcu_read_unlock();
@@ -1356,7 +1356,7 @@ out:
 static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 					 struct sk_buff *skb)
 {
-	const struct net_protocol *ops;
+	const struct net_offload *ops;
 	struct sk_buff **pp = NULL;
 	struct sk_buff *p;
 	const struct iphdr *iph;
@@ -1378,7 +1378,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 	proto = iph->protocol;
 
 	rcu_read_lock();
-	ops = rcu_dereference(inet_protos[proto]);
+	ops = rcu_dereference(inet_offloads[proto]);
 	if (!ops || !ops->gro_receive)
 		goto out_unlock;
 
@@ -1435,7 +1435,7 @@ static int inet_gro_complete(struct sk_buff *skb)
 {
 	__be16 newlen = htons(skb->len - skb_network_offset(skb));
 	struct iphdr *iph = ip_hdr(skb);
-	const struct net_protocol *ops;
+	const struct net_offload *ops;
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
@@ -1443,7 +1443,7 @@ static int inet_gro_complete(struct sk_buff *skb)
 	iph->tot_len = newlen;
 
 	rcu_read_lock();
-	ops = rcu_dereference(inet_protos[proto]);
+	ops = rcu_dereference(inet_offloads[proto]);
 	if (WARN_ON(!ops || !ops->gro_complete))
 		goto out_unlock;
 
@@ -1558,10 +1558,6 @@ static const struct net_protocol tcp_protocol = {
 	.early_demux	=	tcp_v4_early_demux,
 	.handler	=	tcp_v4_rcv,
 	.err_handler	=	tcp_v4_err,
-	.gso_send_check	=	tcp_v4_gso_send_check,
-	.gso_segment	=	tcp_tso_segment,
-	.gro_receive	=	tcp4_gro_receive,
-	.gro_complete	=	tcp4_gro_complete,
 	.no_policy	=	1,
 	.netns_ok	=	1,
 };
@@ -1576,8 +1572,6 @@ static const struct net_offload tcp_offload = {
 static const struct net_protocol udp_protocol = {
 	.handler =	udp_rcv,
 	.err_handler =	udp_err,
-	.gso_send_check = udp4_ufo_send_check,
-	.gso_segment = udp4_ufo_fragment,
 	.no_policy =	1,
 	.netns_ok =	1,
 };
@@ -1725,6 +1719,14 @@ static int __init inet_init(void)
 
 	tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
 
+	/*
+	 * Add offloads
+	 */
+	if (inet_add_offload(&udp_offload, IPPROTO_UDP) < 0)
+		pr_crit("%s: Cannot add UDP protocol offload\n", __func__);
+	if (inet_add_offload(&tcp_offload, IPPROTO_TCP) < 0)
+		pr_crit("%s: Cannot add TCP protocol offlaod\n", __func__);
+
 	/*
 	 *	Add all the base protocols.
 	 */
-- 
cgit v1.2.3-55-g7522


From 3336288a9feaa809839adbaf05778dc2f16665dc Mon Sep 17 00:00:00 2001
From: Vlad Yasevich
Date: Thu, 15 Nov 2012 08:49:15 +0000
Subject: ipv6: Switch to using new offload infrastructure.

Switch IPv6 protocol to using the new GRO/GSO calls and data.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/protocol.h |  8 --------
 net/ipv6/af_inet6.c    | 22 +++++++++++-----------
 net/ipv6/exthdrs.c     | 38 +++++++++++++++++++++++++++++++++++---
 net/ipv6/tcp_ipv6.c    | 17 ++++++++++-------
 net/ipv6/udp.c         | 11 ++++++++---
 5 files changed, 64 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/net/protocol.h b/include/net/protocol.h
index 3bb70510b686..7019c1637848 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -54,14 +54,6 @@ struct inet6_protocol {
 			       struct inet6_skb_parm *opt,
 			       u8 type, u8 code, int offset,
 			       __be32 info);
-
-	int	(*gso_send_check)(struct sk_buff *skb);
-	struct sk_buff *(*gso_segment)(struct sk_buff *skb,
-				       netdev_features_t features);
-	struct sk_buff **(*gro_receive)(struct sk_buff **head,
-					struct sk_buff *skb);
-	int	(*gro_complete)(struct sk_buff *skb);
-
 	unsigned int	flags;	/* INET6_PROTO_xxx */
 };
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 6e245177608c..eb63dac68728 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -701,14 +701,14 @@ EXPORT_SYMBOL_GPL(ipv6_opt_accepted);
 
 static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
 {
-	const struct inet6_protocol *ops = NULL;
+	const struct net_offload *ops = NULL;
 
 	for (;;) {
 		struct ipv6_opt_hdr *opth;
 		int len;
 
 		if (proto != NEXTHDR_HOP) {
-			ops = rcu_dereference(inet6_protos[proto]);
+			ops = rcu_dereference(inet6_offloads[proto]);
 
 			if (unlikely(!ops))
 				break;
@@ -736,7 +736,7 @@ static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
 static int ipv6_gso_send_check(struct sk_buff *skb)
 {
 	const struct ipv6hdr *ipv6h;
-	const struct inet6_protocol *ops;
+	const struct net_offload *ops;
 	int err = -EINVAL;
 
 	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
@@ -747,7 +747,7 @@ static int ipv6_gso_send_check(struct sk_buff *skb)
 	err = -EPROTONOSUPPORT;
 
 	rcu_read_lock();
-	ops = rcu_dereference(inet6_protos[
+	ops = rcu_dereference(inet6_offloads[
 		ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]);
 
 	if (likely(ops && ops->gso_send_check)) {
@@ -765,7 +765,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct ipv6hdr *ipv6h;
-	const struct inet6_protocol *ops;
+	const struct net_offload *ops;
 	int proto;
 	struct frag_hdr *fptr;
 	unsigned int unfrag_ip6hlen;
@@ -792,7 +792,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 	proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
 	rcu_read_lock();
-	ops = rcu_dereference(inet6_protos[proto]);
+	ops = rcu_dereference(inet6_offloads[proto]);
 	if (likely(ops && ops->gso_segment)) {
 		skb_reset_transport_header(skb);
 		segs = ops->gso_segment(skb, features);
@@ -825,7 +825,7 @@ out:
 static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 					 struct sk_buff *skb)
 {
-	const struct inet6_protocol *ops;
+	const struct net_offload *ops;
 	struct sk_buff **pp = NULL;
 	struct sk_buff *p;
 	struct ipv6hdr *iph;
@@ -852,7 +852,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 
 	rcu_read_lock();
 	proto = iph->nexthdr;
-	ops = rcu_dereference(inet6_protos[proto]);
+	ops = rcu_dereference(inet6_offloads[proto]);
 	if (!ops || !ops->gro_receive) {
 		__pskb_pull(skb, skb_gro_offset(skb));
 		proto = ipv6_gso_pull_exthdrs(skb, proto);
@@ -860,7 +860,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 		skb_reset_transport_header(skb);
 		__skb_push(skb, skb_gro_offset(skb));
 
-		ops = rcu_dereference(inet6_protos[proto]);
+		ops = rcu_dereference(inet6_offloads[proto]);
 		if (!ops || !ops->gro_receive)
 			goto out_unlock;
 
@@ -915,7 +915,7 @@ out:
 
 static int ipv6_gro_complete(struct sk_buff *skb)
 {
-	const struct inet6_protocol *ops;
+	const struct net_offload *ops;
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	int err = -ENOSYS;
 
@@ -923,7 +923,7 @@ static int ipv6_gro_complete(struct sk_buff *skb)
 				 sizeof(*iph));
 
 	rcu_read_lock();
-	ops = rcu_dereference(inet6_protos[NAPI_GRO_CB(skb)->proto]);
+	ops = rcu_dereference(inet6_offloads[NAPI_GRO_CB(skb)->proto]);
 	if (WARN_ON(!ops || !ops->gro_complete))
 		goto out_unlock;
 
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index cb6f0828ca44..de6559e3aa0a 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -549,14 +549,44 @@ static const struct inet6_protocol nodata_protocol = {
 	.flags		=	INET6_PROTO_NOPOLICY,
 };
 
+static int ipv6_exthdrs_offload_init(void)
+{
+	int ret;
+
+	ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING);
+	if (!ret)
+		goto out;
+
+	ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS);
+	if (!ret)
+		goto out_rt;
+
+out:
+	return ret;
+
+out_rt:
+	inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
+	goto out;
+}
+
+static void ipv6_exthdrs_offload_exit(void)
+{
+	inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
+	inet_del_offload(&rthdr_offload, IPPROTO_DSTOPTS);
+}
+
 int __init ipv6_exthdrs_init(void)
 {
 	int ret;
 
-	ret = inet6_add_protocol(&rthdr_protocol, IPPROTO_ROUTING);
+	ret = ipv6_exthdrs_offload_init();
 	if (ret)
 		goto out;
 
+	ret = inet6_add_protocol(&rthdr_protocol, IPPROTO_ROUTING);
+	if (ret)
+		goto out_offload;
+
 	ret = inet6_add_protocol(&destopt_protocol, IPPROTO_DSTOPTS);
 	if (ret)
 		goto out_rthdr;
@@ -567,10 +597,12 @@ int __init ipv6_exthdrs_init(void)
 
 out:
 	return ret;
-out_rthdr:
-	inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING);
 out_destopt:
 	inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS);
+out_rthdr:
+	inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING);
+out_offload:
+	ipv6_exthdrs_offload_exit();
 	goto out;
 };
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6884a95be433..635206e8987e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2066,10 +2066,6 @@ static const struct inet6_protocol tcpv6_protocol = {
 	.early_demux	=	tcp_v6_early_demux,
 	.handler	=	tcp_v6_rcv,
 	.err_handler	=	tcp_v6_err,
-	.gso_send_check	=	tcp_v6_gso_send_check,
-	.gso_segment	=	tcp_tso_segment,
-	.gro_receive	=	tcp6_gro_receive,
-	.gro_complete	=	tcp6_gro_complete,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
@@ -2116,10 +2112,14 @@ int __init tcpv6_init(void)
 {
 	int ret;
 
-	ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP);
+	ret = inet6_add_offload(&tcpv6_offload, IPPROTO_TCP);
 	if (ret)
 		goto out;
 
+	ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP);
+	if (ret)
+		goto out_offload;
+
 	/* register inet6 protocol */
 	ret = inet6_register_protosw(&tcpv6_protosw);
 	if (ret)
@@ -2131,10 +2131,12 @@ int __init tcpv6_init(void)
 out:
 	return ret;
 
-out_tcpv6_protocol:
-	inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
 out_tcpv6_protosw:
 	inet6_unregister_protosw(&tcpv6_protosw);
+out_tcpv6_protocol:
+	inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
+out_offload:
+	inet6_del_offload(&tcpv6_offload, IPPROTO_TCP);
 	goto out;
 }
 
@@ -2143,4 +2145,5 @@ void tcpv6_exit(void)
 	unregister_pernet_subsys(&tcpv6_net_ops);
 	inet6_unregister_protosw(&tcpv6_protosw);
 	inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
+	inet6_del_offload(&tcpv6_offload, IPPROTO_TCP);
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 3ad44e176503..e4cc1f41012d 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1438,8 +1438,6 @@ out:
 static const struct inet6_protocol udpv6_protocol = {
 	.handler	=	udpv6_rcv,
 	.err_handler	=	udpv6_err,
-	.gso_send_check =	udp6_ufo_send_check,
-	.gso_segment	=	udp6_ufo_fragment,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
@@ -1570,10 +1568,14 @@ int __init udpv6_init(void)
 {
 	int ret;
 
-	ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP);
+	ret = inet6_add_offload(&udpv6_offload, IPPROTO_UDP);
 	if (ret)
 		goto out;
 
+	ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP);
+	if (ret)
+		goto out_offload;
+
 	ret = inet6_register_protosw(&udpv6_protosw);
 	if (ret)
 		goto out_udpv6_protocol;
@@ -1582,6 +1584,8 @@ out:
 
 out_udpv6_protocol:
 	inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP);
+out_offload:
+	inet6_del_offload(&udpv6_offload, IPPROTO_UDP);
 	goto out;
 }
 
@@ -1589,4 +1593,5 @@ void udpv6_exit(void)
 {
 	inet6_unregister_protosw(&udpv6_protosw);
 	inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP);
+	inet6_del_offload(&udpv6_offload, IPPROTO_UDP);
 }
-- 
cgit v1.2.3-55-g7522


From 8663e02aba154e04679c9bb1665af52021d32547 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich
Date: Thu, 15 Nov 2012 08:49:17 +0000
Subject: ipv6: Separate tcp offload functionality

Pull TCPv6 offload functionality into its won file in preparation
for moving it out of the module.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_checksum.h |  35 ++++++++++++++
 net/ipv6/Makefile          |   2 +-
 net/ipv6/ip6_offload.h     |   3 ++
 net/ipv6/tcp_ipv6.c        | 113 ++-------------------------------------------
 net/ipv6/tcpv6_offload.c   |  98 +++++++++++++++++++++++++++++++++++++++
 5 files changed, 141 insertions(+), 110 deletions(-)
 create mode 100644 net/ipv6/tcpv6_offload.c

(limited to 'include')

diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h
index bc1b0fda2b04..652d3d309357 100644
--- a/include/net/ip6_checksum.h
+++ b/include/net/ip6_checksum.h
@@ -31,6 +31,8 @@
 #include <net/ip.h>
 #include <asm/checksum.h>
 #include <linux/in6.h>
+#include <linux/tcp.h>
+#include <linux/ipv6.h>
 
 #ifndef _HAVE_ARCH_IPV6_CSUM
 
@@ -91,4 +93,37 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 }
 
 #endif
+
+static __inline__ __sum16 tcp_v6_check(int len,
+				   const struct in6_addr *saddr,
+				   const struct in6_addr *daddr,
+				   __wsum base)
+{
+	return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base);
+}
+
+static inline void __tcp_v6_send_check(struct sk_buff *skb,
+				       const struct in6_addr *saddr,
+				       const struct in6_addr *daddr)
+{
+	struct tcphdr *th = tcp_hdr(skb);
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0);
+		skb->csum_start = skb_transport_header(skb) - skb->head;
+		skb->csum_offset = offsetof(struct tcphdr, check);
+	} else {
+		th->check = tcp_v6_check(skb->len, saddr, daddr,
+					 csum_partial(th, th->doff << 2,
+						      skb->csum));
+	}
+}
+
+static inline void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	__tcp_v6_send_check(skb, &np->saddr, &np->daddr);
+}
+
 #endif
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 45bd9cdd9244..f47ad9f6ea2c 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -10,7 +10,7 @@ ipv6-objs :=	af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
 		raw.o protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \
 		exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o
 
-ipv6-offload :=	ip6_offload.o
+ipv6-offload :=	ip6_offload.o tcpv6_offload.o
 
 ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o
 ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o
diff --git a/net/ipv6/ip6_offload.h b/net/ipv6/ip6_offload.h
index c09614eaa929..1891946ceedb 100644
--- a/net/ipv6/ip6_offload.h
+++ b/net/ipv6/ip6_offload.h
@@ -11,6 +11,9 @@
 #ifndef __ip6_offload_h
 #define __ip6_offload_h
 
+int tcpv6_offload_init(void);
+void tcpv6_offload_cleanup(void);
+
 extern void ipv6_offload_init(void);
 extern void ipv6_offload_cleanup(void);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 635206e8987e..5bed594b429d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -71,15 +71,13 @@
 
 #include <linux/crypto.h>
 #include <linux/scatterlist.h>
+#include "ip6_offload.h"
 
 static void	tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb);
 static void	tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 				      struct request_sock *req);
 
 static int	tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
-static void	__tcp_v6_send_check(struct sk_buff *skb,
-				    const struct in6_addr *saddr,
-				    const struct in6_addr *daddr);
 
 static const struct inet_connection_sock_af_ops ipv6_mapped;
 static const struct inet_connection_sock_af_ops ipv6_specific;
@@ -119,14 +117,6 @@ static void tcp_v6_hash(struct sock *sk)
 	}
 }
 
-static __inline__ __sum16 tcp_v6_check(int len,
-				   const struct in6_addr *saddr,
-				   const struct in6_addr *daddr,
-				   __wsum base)
-{
-	return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base);
-}
-
 static __u32 tcp_v6_init_sequence(const struct sk_buff *skb)
 {
 	return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
@@ -722,94 +712,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 };
 #endif
 
-static void __tcp_v6_send_check(struct sk_buff *skb,
-				const struct in6_addr *saddr, const struct in6_addr *daddr)
-{
-	struct tcphdr *th = tcp_hdr(skb);
-
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0);
-		skb->csum_start = skb_transport_header(skb) - skb->head;
-		skb->csum_offset = offsetof(struct tcphdr, check);
-	} else {
-		th->check = tcp_v6_check(skb->len, saddr, daddr,
-					 csum_partial(th, th->doff << 2,
-						      skb->csum));
-	}
-}
-
-static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
-{
-	struct ipv6_pinfo *np = inet6_sk(sk);
-
-	__tcp_v6_send_check(skb, &np->saddr, &np->daddr);
-}
-
-static int tcp_v6_gso_send_check(struct sk_buff *skb)
-{
-	const struct ipv6hdr *ipv6h;
-	struct tcphdr *th;
-
-	if (!pskb_may_pull(skb, sizeof(*th)))
-		return -EINVAL;
-
-	ipv6h = ipv6_hdr(skb);
-	th = tcp_hdr(skb);
-
-	th->check = 0;
-	skb->ip_summed = CHECKSUM_PARTIAL;
-	__tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr);
-	return 0;
-}
-
-static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
-{
-	const struct ipv6hdr *iph = skb_gro_network_header(skb);
-	__wsum wsum;
-	__sum16 sum;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr,
-				  skb->csum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			break;
-		}
-flush:
-		NAPI_GRO_CB(skb)->flush = 1;
-		return NULL;
-
-	case CHECKSUM_NONE:
-		wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr,
-						    skb_gro_len(skb),
-						    IPPROTO_TCP, 0));
-		sum = csum_fold(skb_checksum(skb,
-					     skb_gro_offset(skb),
-					     skb_gro_len(skb),
-					     wsum));
-		if (sum)
-			goto flush;
-
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		break;
-	}
-
-	return tcp_gro_receive(head, skb);
-}
-
-static int tcp6_gro_complete(struct sk_buff *skb)
-{
-	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct tcphdr *th = tcp_hdr(skb);
-
-	th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb),
-				  &iph->saddr, &iph->daddr, 0);
-	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
-
-	return tcp_gro_complete(skb);
-}
-
 static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 				 u32 ts, struct tcp_md5sig_key *key, int rst, u8 tclass)
 {
@@ -2069,13 +1971,6 @@ static const struct inet6_protocol tcpv6_protocol = {
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
-static const struct net_offload tcpv6_offload = {
-	.gso_send_check	=	tcp_v6_gso_send_check,
-	.gso_segment	=	tcp_tso_segment,
-	.gro_receive	=	tcp6_gro_receive,
-	.gro_complete	=	tcp6_gro_complete,
-};
-
 static struct inet_protosw tcpv6_protosw = {
 	.type		=	SOCK_STREAM,
 	.protocol	=	IPPROTO_TCP,
@@ -2112,7 +2007,7 @@ int __init tcpv6_init(void)
 {
 	int ret;
 
-	ret = inet6_add_offload(&tcpv6_offload, IPPROTO_TCP);
+	ret = tcpv6_offload_init();
 	if (ret)
 		goto out;
 
@@ -2136,7 +2031,7 @@ out_tcpv6_protosw:
 out_tcpv6_protocol:
 	inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
 out_offload:
-	inet6_del_offload(&tcpv6_offload, IPPROTO_TCP);
+	tcpv6_offload_cleanup();
 	goto out;
 }
 
@@ -2145,5 +2040,5 @@ void tcpv6_exit(void)
 	unregister_pernet_subsys(&tcpv6_net_ops);
 	inet6_unregister_protosw(&tcpv6_protosw);
 	inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
-	inet6_del_offload(&tcpv6_offload, IPPROTO_TCP);
+	tcpv6_offload_cleanup();
 }
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
new file mode 100644
index 000000000000..edeafedba470
--- /dev/null
+++ b/net/ipv6/tcpv6_offload.c
@@ -0,0 +1,98 @@
+/*
+ *	IPV6 GSO/GRO offload support
+ *	Linux INET6 implementation
+ *
+ *	This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ *
+ *      TCPv6 GSO/GRO support
+ */
+#include <linux/skbuff.h>
+#include <net/protocol.h>
+#include <net/tcp.h>
+#include <net/ip6_checksum.h>
+#include "ip6_offload.h"
+
+static int tcp_v6_gso_send_check(struct sk_buff *skb)
+{
+	const struct ipv6hdr *ipv6h;
+	struct tcphdr *th;
+
+	if (!pskb_may_pull(skb, sizeof(*th)))
+		return -EINVAL;
+
+	ipv6h = ipv6_hdr(skb);
+	th = tcp_hdr(skb);
+
+	th->check = 0;
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	__tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr);
+	return 0;
+}
+
+static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	const struct ipv6hdr *iph = skb_gro_network_header(skb);
+	__wsum wsum;
+	__sum16 sum;
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr,
+				  skb->csum)) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			break;
+		}
+flush:
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+
+	case CHECKSUM_NONE:
+		wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr,
+						    skb_gro_len(skb),
+						    IPPROTO_TCP, 0));
+		sum = csum_fold(skb_checksum(skb,
+					     skb_gro_offset(skb),
+					     skb_gro_len(skb),
+					     wsum));
+		if (sum)
+			goto flush;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		break;
+	}
+
+	return tcp_gro_receive(head, skb);
+}
+
+static int tcp6_gro_complete(struct sk_buff *skb)
+{
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct tcphdr *th = tcp_hdr(skb);
+
+	th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb),
+				  &iph->saddr, &iph->daddr, 0);
+	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+
+	return tcp_gro_complete(skb);
+}
+
+static const struct net_offload tcpv6_offload = {
+	.gso_send_check	=	tcp_v6_gso_send_check,
+	.gso_segment	=	tcp_tso_segment,
+	.gro_receive	=	tcp6_gro_receive,
+	.gro_complete	=	tcp6_gro_complete,
+};
+
+int __init tcpv6_offload_init(void)
+{
+	return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP);
+}
+
+void tcpv6_offload_cleanup(void)
+{
+	inet6_del_offload(&tcpv6_offload, IPPROTO_TCP);
+}
-- 
cgit v1.2.3-55-g7522


From c6b641a4c6b32f39db678c2441cb1ef824110d74 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich
Date: Thu, 15 Nov 2012 08:49:22 +0000
Subject: ipv6: Pull IPv6 GSO registration out of the module

Sing GSO support is now separate, pull it out of the module
and make it its own init call.
Remove the cleanup functions as they are no longer called.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/protocol.h     | 11 ++++++-----
 net/ipv6/Makefile          |  6 +++---
 net/ipv6/af_inet6.c        |  3 ---
 net/ipv6/exthdrs.c         | 10 +---------
 net/ipv6/exthdrs_offload.c |  6 ------
 net/ipv6/ip6_offload.c     | 17 ++++++++++++-----
 net/ipv6/ip6_offload.h     |  8 --------
 net/ipv6/protocol.c        | 20 ++++++++++++--------
 net/ipv6/tcp_ipv6.c        | 10 +---------
 net/ipv6/tcpv6_offload.c   |  5 -----
 net/ipv6/udp.c             | 10 +---------
 net/ipv6/udp_offload.c     |  5 -----
 12 files changed, 36 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/include/net/protocol.h b/include/net/protocol.h
index 7019c1637848..2c90794c139d 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -25,6 +25,7 @@
 #define _PROTOCOL_H
 
 #include <linux/in6.h>
+#include <linux/skbuff.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <linux/ipv6.h>
 #endif
@@ -59,8 +60,6 @@ struct inet6_protocol {
 
 #define INET6_PROTO_NOPOLICY	0x1
 #define INET6_PROTO_FINAL	0x2
-/* This should be set for any extension header which is compatible with GSO. */
-#define INET6_PROTO_GSO_EXTHDR	0x4
 #endif
 
 struct net_offload {
@@ -72,6 +71,8 @@ struct net_offload {
 	int			(*gro_complete)(struct sk_buff *skb);
 	unsigned int		flags;	/* Flags used by IPv6 for now */
 };
+/* This should be set for any extension header which is compatible with GSO. */
+#define INET6_PROTO_GSO_EXTHDR	0x1
 
 /* This is used to register socket interfaces for IP protocols.  */
 struct inet_protosw {
@@ -93,10 +94,10 @@ struct inet_protosw {
 
 extern const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
 extern const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS];
+extern const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS];
 
 #if IS_ENABLED(CONFIG_IPV6)
 extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
-extern const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS];
 #endif
 
 extern int	inet_add_protocol(const struct net_protocol *prot, unsigned char num);
@@ -109,10 +110,10 @@ extern void	inet_unregister_protosw(struct inet_protosw *p);
 #if IS_ENABLED(CONFIG_IPV6)
 extern int	inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num);
 extern int	inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num);
-extern int	inet6_add_offload(const struct net_offload *prot, unsigned char num);
-extern int	inet6_del_offload(const struct net_offload *prot, unsigned char num);
 extern int	inet6_register_protosw(struct inet_protosw *p);
 extern void	inet6_unregister_protosw(struct inet_protosw *p);
 #endif
+extern int	inet6_add_offload(const struct net_offload *prot, unsigned char num);
+extern int	inet6_del_offload(const struct net_offload *prot, unsigned char num);
 
 #endif	/* _PROTOCOL_H */
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index cdca302f395c..04a475df98ad 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_IPV6) += ipv6.o
 ipv6-objs :=	af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
 		addrlabel.o \
 		route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
-		raw.o protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \
+		raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o \
 		exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o
 
 ipv6-offload :=	ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o
@@ -23,7 +23,6 @@ ipv6-$(CONFIG_PROC_FS) += proc.o
 ipv6-$(CONFIG_SYN_COOKIES) += syncookies.o
 
 ipv6-objs += $(ipv6-y)
-ipv6-objs += $(ipv6-offload)
 
 obj-$(CONFIG_INET6_AH) += ah6.o
 obj-$(CONFIG_INET6_ESP) += esp6.o
@@ -41,6 +40,7 @@ obj-$(CONFIG_IPV6_SIT) += sit.o
 obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
 obj-$(CONFIG_IPV6_GRE) += ip6_gre.o
 
-obj-y += addrconf_core.o exthdrs_core.o output_core.o
+obj-y += addrconf_core.o exthdrs_core.o output_core.o protocol.o
+obj-y += $(ipv6-offload)
 
 obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c84d5ba60cdd..7bafc51cda11 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -62,7 +62,6 @@
 
 #include <asm/uaccess.h>
 #include <linux/mroute6.h>
-#include "ip6_offload.h"
 
 MODULE_AUTHOR("Cast of dozens");
 MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
@@ -707,14 +706,12 @@ static struct packet_type ipv6_packet_type __read_mostly = {
 
 static int __init ipv6_packet_init(void)
 {
-	ipv6_offload_init();
 	dev_add_pack(&ipv6_packet_type);
 	return 0;
 }
 
 static void ipv6_packet_cleanup(void)
 {
-	ipv6_offload_cleanup();
 	dev_remove_pack(&ipv6_packet_type);
 }
 
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index a786a20ad823..473f628f9f20 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -48,7 +48,6 @@
 #endif
 
 #include <asm/uaccess.h>
-#include "ip6_offload.h"
 
 /*
  *	Parsing tlv encoded headers.
@@ -502,13 +501,9 @@ int __init ipv6_exthdrs_init(void)
 {
 	int ret;
 
-	ret = ipv6_exthdrs_offload_init();
-	if (ret)
-		goto out;
-
 	ret = inet6_add_protocol(&rthdr_protocol, IPPROTO_ROUTING);
 	if (ret)
-		goto out_offload;
+		goto out;
 
 	ret = inet6_add_protocol(&destopt_protocol, IPPROTO_DSTOPTS);
 	if (ret)
@@ -524,14 +519,11 @@ out_destopt:
 	inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS);
 out_rthdr:
 	inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING);
-out_offload:
-	ipv6_exthdrs_offload_exit();
 	goto out;
 };
 
 void ipv6_exthdrs_exit(void)
 {
-	ipv6_exthdrs_offload_exit();
 	inet6_del_protocol(&nodata_protocol, IPPROTO_NONE);
 	inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS);
 	inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING);
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index 271bf4a97023..cf77f3abfd06 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -39,9 +39,3 @@ out_rt:
 	inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
 	goto out;
 }
-
-void ipv6_exthdrs_offload_exit(void)
-{
-	inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
-	inet_del_offload(&rthdr_offload, IPPROTO_DSTOPTS);
-}
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 01cf9835a581..63d79d9005bd 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -12,6 +12,7 @@
 #include <linux/socket.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <linux/printk.h>
 
 #include <net/protocol.h>
 #include <net/ipv6.h>
@@ -262,12 +263,18 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
 	.gro_complete = ipv6_gro_complete,
 };
 
-void __init ipv6_offload_init(void)
+static int __init ipv6_offload_init(void)
 {
+
+	if (tcpv6_offload_init() < 0)
+		pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
+	if (udp_offload_init() < 0)
+		pr_crit("%s: Cannot add UDP protocol offload\n", __func__);
+	if (ipv6_exthdrs_offload_init() < 0)
+		pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__);
+
 	dev_add_offload(&ipv6_packet_offload);
+	return 0;
 }
 
-void ipv6_offload_cleanup(void)
-{
-	dev_remove_offload(&ipv6_packet_offload);
-}
+fs_initcall(ipv6_offload_init);
diff --git a/net/ipv6/ip6_offload.h b/net/ipv6/ip6_offload.h
index 4e88ddb52a2c..2e155c651b35 100644
--- a/net/ipv6/ip6_offload.h
+++ b/net/ipv6/ip6_offload.h
@@ -12,15 +12,7 @@
 #define __ip6_offload_h
 
 int ipv6_exthdrs_offload_init(void);
-void ipv6_exthdrs_offload_exit(void);
-
 int udp_offload_init(void);
-void udp_offload_cleanup(void);
-
 int tcpv6_offload_init(void);
-void tcpv6_offload_cleanup(void);
-
-extern void ipv6_offload_init(void);
-extern void ipv6_offload_cleanup(void);
 
 #endif
diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c
index f7c53a7d5cb0..22d1bd4670da 100644
--- a/net/ipv6/protocol.c
+++ b/net/ipv6/protocol.c
@@ -25,8 +25,9 @@
 #include <linux/spinlock.h>
 #include <net/protocol.h>
 
+#if IS_ENABLED(CONFIG_IPV6)
 const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly;
-const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS] __read_mostly;
+EXPORT_SYMBOL(inet6_protos);
 
 int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol)
 {
@@ -35,13 +36,6 @@ int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol
 }
 EXPORT_SYMBOL(inet6_add_protocol);
 
-int inet6_add_offload(const struct net_offload *prot, unsigned char protocol)
-{
-	return !cmpxchg((const struct net_offload **)&inet6_offloads[protocol],
-			NULL, prot) ? 0 : -1;
-}
-EXPORT_SYMBOL(inet6_add_offload);
-
 /*
  *	Remove a protocol from the hash tables.
  */
@@ -58,6 +52,16 @@ int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol
 	return ret;
 }
 EXPORT_SYMBOL(inet6_del_protocol);
+#endif
+
+const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS] __read_mostly;
+
+int inet6_add_offload(const struct net_offload *prot, unsigned char protocol)
+{
+	return !cmpxchg((const struct net_offload **)&inet6_offloads[protocol],
+			NULL, prot) ? 0 : -1;
+}
+EXPORT_SYMBOL(inet6_add_offload);
 
 int inet6_del_offload(const struct net_offload *prot, unsigned char protocol)
 {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5bed594b429d..6c0f2526f3f1 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -71,7 +71,6 @@
 
 #include <linux/crypto.h>
 #include <linux/scatterlist.h>
-#include "ip6_offload.h"
 
 static void	tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb);
 static void	tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
@@ -2007,13 +2006,9 @@ int __init tcpv6_init(void)
 {
 	int ret;
 
-	ret = tcpv6_offload_init();
-	if (ret)
-		goto out;
-
 	ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP);
 	if (ret)
-		goto out_offload;
+		goto out;
 
 	/* register inet6 protocol */
 	ret = inet6_register_protosw(&tcpv6_protosw);
@@ -2030,8 +2025,6 @@ out_tcpv6_protosw:
 	inet6_unregister_protosw(&tcpv6_protosw);
 out_tcpv6_protocol:
 	inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
-out_offload:
-	tcpv6_offload_cleanup();
 	goto out;
 }
 
@@ -2040,5 +2033,4 @@ void tcpv6_exit(void)
 	unregister_pernet_subsys(&tcpv6_net_ops);
 	inet6_unregister_protosw(&tcpv6_protosw);
 	inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
-	tcpv6_offload_cleanup();
 }
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index edeafedba470..3a27fe685c8e 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -91,8 +91,3 @@ int __init tcpv6_offload_init(void)
 {
 	return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP);
 }
-
-void tcpv6_offload_cleanup(void)
-{
-	inet6_del_offload(&tcpv6_offload, IPPROTO_TCP);
-}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 013fef740d51..dfaa29b8b293 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -50,7 +50,6 @@
 #include <linux/seq_file.h>
 #include <trace/events/skb.h>
 #include "udp_impl.h"
-#include "ip6_offload.h"
 
 int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 {
@@ -1472,13 +1471,9 @@ int __init udpv6_init(void)
 {
 	int ret;
 
-	ret = udp_offload_init();
-	if (ret)
-		goto out;
-
 	ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP);
 	if (ret)
-		goto out_offload;
+		goto out;
 
 	ret = inet6_register_protosw(&udpv6_protosw);
 	if (ret)
@@ -1488,8 +1483,6 @@ out:
 
 out_udpv6_protocol:
 	inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP);
-out_offload:
-	udp_offload_cleanup();
 	goto out;
 }
 
@@ -1497,5 +1490,4 @@ void udpv6_exit(void)
 {
 	inet6_unregister_protosw(&udpv6_protosw);
 	inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP);
-	udp_offload_cleanup();
 }
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index f964d2b366c8..979e4ab63a8b 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -115,8 +115,3 @@ int __init udp_offload_init(void)
 {
 	return inet6_add_offload(&udpv6_offload, IPPROTO_UDP);
 }
-
-void udp_offload_cleanup(void)
-{
-	inet6_del_offload(&udpv6_offload, IPPROTO_UDP);
-}
-- 
cgit v1.2.3-55-g7522


From f191a1d17f227032c159e5499809f545402b6dc6 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich
Date: Thu, 15 Nov 2012 08:49:23 +0000
Subject: net: Remove code duplication between offload structures

Move the offload callbacks into its own structure.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 10 +++++++---
 include/net/protocol.h    | 10 +++-------
 net/core/dev.c            | 14 +++++++-------
 net/ipv4/af_inet.c        | 42 ++++++++++++++++++++++++------------------
 net/ipv6/ip6_offload.c    | 28 +++++++++++++++-------------
 net/ipv6/tcpv6_offload.c  | 10 ++++++----
 net/ipv6/udp_offload.c    |  6 ++++--
 7 files changed, 66 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 61bc8483031f..e46c830c88d8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1515,15 +1515,19 @@ struct packet_type {
 	struct list_head	list;
 };
 
-struct packet_offload {
-	__be16			type;	/* This is really htons(ether_type). */
+struct offload_callbacks {
 	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
 						netdev_features_t features);
 	int			(*gso_send_check)(struct sk_buff *skb);
 	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
 					       struct sk_buff *skb);
 	int			(*gro_complete)(struct sk_buff *skb);
-	struct list_head	list;
+};
+
+struct packet_offload {
+	__be16			 type;	/* This is really htons(ether_type). */
+	struct offload_callbacks callbacks;
+	struct list_head	 list;
 };
 
 #include <linux/notifier.h>
diff --git a/include/net/protocol.h b/include/net/protocol.h
index 2c90794c139d..047c0476c0a0 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -29,6 +29,7 @@
 #if IS_ENABLED(CONFIG_IPV6)
 #include <linux/ipv6.h>
 #endif
+#include <linux/netdevice.h>
 
 /* This is one larger than the largest protocol value that can be
  * found in an ipv4 or ipv6 header.  Since in both cases the protocol
@@ -63,13 +64,8 @@ struct inet6_protocol {
 #endif
 
 struct net_offload {
-	int			(*gso_send_check)(struct sk_buff *skb);
-	struct sk_buff	       *(*gso_segment)(struct sk_buff *skb,
-					       netdev_features_t features);
-	struct sk_buff	      **(*gro_receive)(struct sk_buff **head,
-					       struct sk_buff *skb);
-	int			(*gro_complete)(struct sk_buff *skb);
-	unsigned int		flags;	/* Flags used by IPv6 for now */
+	struct offload_callbacks callbacks;
+	unsigned int		 flags;	/* Flags used by IPv6 for now */
 };
 /* This should be set for any extension header which is compatible with GSO. */
 #define INET6_PROTO_GSO_EXTHDR	0x1
diff --git a/net/core/dev.c b/net/core/dev.c
index cf843a256cc6..cf105e886cca 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2102,16 +2102,16 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb,
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, &offload_base, list) {
-		if (ptype->type == type && ptype->gso_segment) {
+		if (ptype->type == type && ptype->callbacks.gso_segment) {
 			if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
-				err = ptype->gso_send_check(skb);
+				err = ptype->callbacks.gso_send_check(skb);
 				segs = ERR_PTR(err);
 				if (err || skb_gso_ok(skb, features))
 					break;
 				__skb_push(skb, (skb->data -
 						 skb_network_header(skb)));
 			}
-			segs = ptype->gso_segment(skb, features);
+			segs = ptype->callbacks.gso_segment(skb, features);
 			break;
 		}
 	}
@@ -3533,10 +3533,10 @@ static int napi_gro_complete(struct sk_buff *skb)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
-		if (ptype->type != type || !ptype->gro_complete)
+		if (ptype->type != type || !ptype->callbacks.gro_complete)
 			continue;
 
-		err = ptype->gro_complete(skb);
+		err = ptype->callbacks.gro_complete(skb);
 		break;
 	}
 	rcu_read_unlock();
@@ -3598,7 +3598,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
-		if (ptype->type != type || !ptype->gro_receive)
+		if (ptype->type != type || !ptype->callbacks.gro_receive)
 			continue;
 
 		skb_set_network_header(skb, skb_gro_offset(skb));
@@ -3608,7 +3608,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
 
-		pp = ptype->gro_receive(&napi->gro_list, skb);
+		pp = ptype->callbacks.gro_receive(&napi->gro_list, skb);
 		break;
 	}
 	rcu_read_unlock();
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9f2e7fd8bea8..d5e5a054123c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1276,8 +1276,8 @@ static int inet_gso_send_check(struct sk_buff *skb)
 
 	rcu_read_lock();
 	ops = rcu_dereference(inet_offloads[proto]);
-	if (likely(ops && ops->gso_send_check))
-		err = ops->gso_send_check(skb);
+	if (likely(ops && ops->callbacks.gso_send_check))
+		err = ops->callbacks.gso_send_check(skb);
 	rcu_read_unlock();
 
 out:
@@ -1326,8 +1326,8 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 
 	rcu_read_lock();
 	ops = rcu_dereference(inet_offloads[proto]);
-	if (likely(ops && ops->gso_segment))
-		segs = ops->gso_segment(skb, features);
+	if (likely(ops && ops->callbacks.gso_segment))
+		segs = ops->callbacks.gso_segment(skb, features);
 	rcu_read_unlock();
 
 	if (!segs || IS_ERR(segs))
@@ -1379,7 +1379,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 
 	rcu_read_lock();
 	ops = rcu_dereference(inet_offloads[proto]);
-	if (!ops || !ops->gro_receive)
+	if (!ops || !ops->callbacks.gro_receive)
 		goto out_unlock;
 
 	if (*(u8 *)iph != 0x45)
@@ -1420,7 +1420,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 	skb_gro_pull(skb, sizeof(*iph));
 	skb_set_transport_header(skb, skb_gro_offset(skb));
 
-	pp = ops->gro_receive(head, skb);
+	pp = ops->callbacks.gro_receive(head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -1444,10 +1444,10 @@ static int inet_gro_complete(struct sk_buff *skb)
 
 	rcu_read_lock();
 	ops = rcu_dereference(inet_offloads[proto]);
-	if (WARN_ON(!ops || !ops->gro_complete))
+	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
 		goto out_unlock;
 
-	err = ops->gro_complete(skb);
+	err = ops->callbacks.gro_complete(skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -1563,10 +1563,12 @@ static const struct net_protocol tcp_protocol = {
 };
 
 static const struct net_offload tcp_offload = {
-	.gso_send_check	=	tcp_v4_gso_send_check,
-	.gso_segment	=	tcp_tso_segment,
-	.gro_receive	=	tcp4_gro_receive,
-	.gro_complete	=	tcp4_gro_complete,
+	.callbacks = {
+		.gso_send_check	=	tcp_v4_gso_send_check,
+		.gso_segment	=	tcp_tso_segment,
+		.gro_receive	=	tcp4_gro_receive,
+		.gro_complete	=	tcp4_gro_complete,
+	},
 };
 
 static const struct net_protocol udp_protocol = {
@@ -1577,8 +1579,10 @@ static const struct net_protocol udp_protocol = {
 };
 
 static const struct net_offload udp_offload = {
-	.gso_send_check = udp4_ufo_send_check,
-	.gso_segment = udp4_ufo_fragment,
+	.callbacks = {
+		.gso_send_check = udp4_ufo_send_check,
+		.gso_segment = udp4_ufo_fragment,
+	},
 };
 
 static const struct net_protocol icmp_protocol = {
@@ -1667,10 +1671,12 @@ static int ipv4_proc_init(void);
 
 static struct packet_offload ip_packet_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IP),
-	.gso_send_check = inet_gso_send_check,
-	.gso_segment = inet_gso_segment,
-	.gro_receive = inet_gro_receive,
-	.gro_complete = inet_gro_complete,
+	.callbacks = {
+		.gso_send_check = inet_gso_send_check,
+		.gso_segment = inet_gso_segment,
+		.gro_receive = inet_gro_receive,
+		.gro_complete = inet_gro_complete,
+	},
 };
 
 static int __init ipv4_offload_init(void)
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 63d79d9005bd..f26f0da7f095 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -70,9 +70,9 @@ static int ipv6_gso_send_check(struct sk_buff *skb)
 	ops = rcu_dereference(inet6_offloads[
 		ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]);
 
-	if (likely(ops && ops->gso_send_check)) {
+	if (likely(ops && ops->callbacks.gso_send_check)) {
 		skb_reset_transport_header(skb);
-		err = ops->gso_send_check(skb);
+		err = ops->callbacks.gso_send_check(skb);
 	}
 	rcu_read_unlock();
 
@@ -113,9 +113,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
 	rcu_read_lock();
 	ops = rcu_dereference(inet6_offloads[proto]);
-	if (likely(ops && ops->gso_segment)) {
+	if (likely(ops && ops->callbacks.gso_segment)) {
 		skb_reset_transport_header(skb);
-		segs = ops->gso_segment(skb, features);
+		segs = ops->callbacks.gso_segment(skb, features);
 	}
 	rcu_read_unlock();
 
@@ -173,7 +173,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	rcu_read_lock();
 	proto = iph->nexthdr;
 	ops = rcu_dereference(inet6_offloads[proto]);
-	if (!ops || !ops->gro_receive) {
+	if (!ops || !ops->callbacks.gro_receive) {
 		__pskb_pull(skb, skb_gro_offset(skb));
 		proto = ipv6_gso_pull_exthdrs(skb, proto);
 		skb_gro_pull(skb, -skb_transport_offset(skb));
@@ -181,7 +181,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 		__skb_push(skb, skb_gro_offset(skb));
 
 		ops = rcu_dereference(inet6_offloads[proto]);
-		if (!ops || !ops->gro_receive)
+		if (!ops || !ops->callbacks.gro_receive)
 			goto out_unlock;
 
 		iph = ipv6_hdr(skb);
@@ -220,7 +220,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	csum = skb->csum;
 	skb_postpull_rcsum(skb, iph, skb_network_header_len(skb));
 
-	pp = ops->gro_receive(head, skb);
+	pp = ops->callbacks.gro_receive(head, skb);
 
 	skb->csum = csum;
 
@@ -244,10 +244,10 @@ static int ipv6_gro_complete(struct sk_buff *skb)
 
 	rcu_read_lock();
 	ops = rcu_dereference(inet6_offloads[NAPI_GRO_CB(skb)->proto]);
-	if (WARN_ON(!ops || !ops->gro_complete))
+	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
 		goto out_unlock;
 
-	err = ops->gro_complete(skb);
+	err = ops->callbacks.gro_complete(skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -257,10 +257,12 @@ out_unlock:
 
 static struct packet_offload ipv6_packet_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IPV6),
-	.gso_send_check = ipv6_gso_send_check,
-	.gso_segment = ipv6_gso_segment,
-	.gro_receive = ipv6_gro_receive,
-	.gro_complete = ipv6_gro_complete,
+	.callbacks = {
+		.gso_send_check = ipv6_gso_send_check,
+		.gso_segment = ipv6_gso_segment,
+		.gro_receive = ipv6_gro_receive,
+		.gro_complete = ipv6_gro_complete,
+	},
 };
 
 static int __init ipv6_offload_init(void)
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 3a27fe685c8e..2ec6bf6a0aa0 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -81,10 +81,12 @@ static int tcp6_gro_complete(struct sk_buff *skb)
 }
 
 static const struct net_offload tcpv6_offload = {
-	.gso_send_check	=	tcp_v6_gso_send_check,
-	.gso_segment	=	tcp_tso_segment,
-	.gro_receive	=	tcp6_gro_receive,
-	.gro_complete	=	tcp6_gro_complete,
+	.callbacks = {
+		.gso_send_check	=	tcp_v6_gso_send_check,
+		.gso_segment	=	tcp_tso_segment,
+		.gro_receive	=	tcp6_gro_receive,
+		.gro_complete	=	tcp6_gro_complete,
+	},
 };
 
 int __init tcpv6_offload_init(void)
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 979e4ab63a8b..8e01c44a987c 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -107,8 +107,10 @@ out:
 	return segs;
 }
 static const struct net_offload udpv6_offload = {
-	.gso_send_check =	udp6_ufo_send_check,
-	.gso_segment	=	udp6_ufo_fragment,
+	.callbacks = {
+		.gso_send_check =	udp6_ufo_send_check,
+		.gso_segment	=	udp6_ufo_fragment,
+	},
 };
 
 int __init udp_offload_init(void)
-- 
cgit v1.2.3-55-g7522


From 997071bcb34005f42e0fe5bc7930e895b070f251 Mon Sep 17 00:00:00 2001
From: K. Y. Srinivasan
Date: Thu, 15 Nov 2012 14:34:42 -0800
Subject: mm: export a function to get vm committed memory

It will be useful to be able to access global memory commitment from
device drivers.  On the Hyper-V platform, the host has a policy engine to
balance the available physical memory amongst all competing virtual
machines hosted on a given node.  This policy engine is driven by a number
of metrics including the memory commitment reported by the guests.  The
balloon driver for Linux on Hyper-V will use this function to retrieve
guest memory commitment.  This function is also used in Xen self
ballooning code.

[akpm@linux-foundation.org: coding-style tweak]
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/xen/xen-selfballoon.c |  2 +-
 include/linux/mman.h          |  2 ++
 mm/mmap.c                     | 14 ++++++++++++++
 mm/nommu.c                    | 15 +++++++++++++++
 4 files changed, 32 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c
index 7d041cb6da26..2552d3e0a70f 100644
--- a/drivers/xen/xen-selfballoon.c
+++ b/drivers/xen/xen-selfballoon.c
@@ -222,7 +222,7 @@ static void selfballoon_process(struct work_struct *work)
 	if (xen_selfballooning_enabled) {
 		cur_pages = totalram_pages;
 		tgt_pages = cur_pages; /* default is no change */
-		goal_pages = percpu_counter_read_positive(&vm_committed_as) +
+		goal_pages = vm_memory_committed() +
 				totalreserve_pages +
 				MB2PAGES(selfballoon_reserved_mb);
 #ifdef CONFIG_FRONTSWAP
diff --git a/include/linux/mman.h b/include/linux/mman.h
index d09dde1e57fb..9aa863da287f 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -11,6 +11,8 @@ extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
 extern struct percpu_counter vm_committed_as;
 
+unsigned long vm_memory_committed(void);
+
 static inline void vm_acct_memory(long pages)
 {
 	percpu_counter_add(&vm_committed_as, pages);
diff --git a/mm/mmap.c b/mm/mmap.c
index 2d942353d681..b064822be82e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -88,6 +88,20 @@ int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
  */
 struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp;
 
+/*
+ * The global memory commitment made in the system can be a metric
+ * that can be used to drive ballooning decisions when Linux is hosted
+ * as a guest. On Hyper-V, the host implements a policy engine for dynamically
+ * balancing memory across competing virtual machines that are hosted.
+ * Several metrics drive this policy engine including the guest reported
+ * memory commitment.
+ */
+unsigned long vm_memory_committed(void)
+{
+	return percpu_counter_read_positive(&vm_committed_as);
+}
+EXPORT_SYMBOL_GPL(vm_memory_committed);
+
 /*
  * Check that a process has enough memory to allocate a new virtual
  * mapping. 0 means there is enough memory for the allocation to
diff --git a/mm/nommu.c b/mm/nommu.c
index 45131b41bcdb..79c3cac87afa 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -66,6 +66,21 @@ int heap_stack_gap = 0;
 
 atomic_long_t mmap_pages_allocated;
 
+/*
+ * The global memory commitment made in the system can be a metric
+ * that can be used to drive ballooning decisions when Linux is hosted
+ * as a guest. On Hyper-V, the host implements a policy engine for dynamically
+ * balancing memory across competing virtual machines that are hosted.
+ * Several metrics drive this policy engine including the guest reported
+ * memory commitment.
+ */
+unsigned long vm_memory_committed(void)
+{
+	return percpu_counter_read_positive(&vm_committed_as);
+}
+
+EXPORT_SYMBOL_GPL(vm_memory_committed);
+
 EXPORT_SYMBOL(mem_map);
 EXPORT_SYMBOL(num_physpages);
 
-- 
cgit v1.2.3-55-g7522


From de274bfe0fc81def6ddb8a17020a9a4b56477cc4 Mon Sep 17 00:00:00 2001
From: Jiri Slaby
Date: Thu, 15 Nov 2012 09:49:54 +0100
Subject: TTY: introduce tty_port_destroy

After commit "TTY: move tty buffers to tty_port", the tty buffers are
not freed in some drivers. This is because tty_port_destructor is not
called whenever a tty_port is freed. This was an assumption I counted
with but was unfortunately untrue.

Those using refcounting are safe now, but for those which do not we
introduce a function to be called right before the tty_port is freed
by the drivers.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_port.c | 16 +++++++++++++++-
 include/linux/tty.h    |  1 +
 2 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index fdc42c2d565f..b7ff59d3db88 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -122,12 +122,26 @@ void tty_port_free_xmit_buf(struct tty_port *port)
 }
 EXPORT_SYMBOL(tty_port_free_xmit_buf);
 
+/**
+ * tty_port_destroy -- destroy inited port
+ * @port: tty port to be doestroyed
+ *
+ * When a port was initialized using tty_port_init, one has to destroy the
+ * port by this function. Either indirectly by using tty_port refcounting
+ * (tty_port_put) or directly if refcounting is not used.
+ */
+void tty_port_destroy(struct tty_port *port)
+{
+	tty_buffer_free_all(port);
+}
+EXPORT_SYMBOL(tty_port_destroy);
+
 static void tty_port_destructor(struct kref *kref)
 {
 	struct tty_port *port = container_of(kref, struct tty_port, kref);
 	if (port->xmit_buf)
 		free_page((unsigned long)port->xmit_buf);
-	tty_buffer_free_all(port);
+	tty_port_destroy(port);
 	if (port->ops && port->ops->destruct)
 		port->ops->destruct(port);
 	else
diff --git a/include/linux/tty.h b/include/linux/tty.h
index d7ff88fb8967..8db1b569c37a 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -455,6 +455,7 @@ extern struct device *tty_port_register_device_attr(struct tty_port *port,
 		const struct attribute_group **attr_grp);
 extern int tty_port_alloc_xmit_buf(struct tty_port *port);
 extern void tty_port_free_xmit_buf(struct tty_port *port);
+extern void tty_port_destroy(struct tty_port *port);
 extern void tty_port_put(struct tty_port *port);
 
 static inline struct tty_port *tty_port_get(struct tty_port *port)
-- 
cgit v1.2.3-55-g7522


From 67d16a4686c9b94c8f52a66afe7521909aeb75b4 Mon Sep 17 00:00:00 2001
From: Wei WANG
Date: Fri, 9 Nov 2012 20:53:33 +0800
Subject: drivers/mfd: Add realtek pcie card reader driver

Realtek PCI-E card reader driver adapts requests from upper-level
sdmmc/memstick layer to the real physical card reader.

Signed-off-by: Wei WANG <wei_wang@realsil.com.cn>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/mfd/Kconfig             |    9 +
 drivers/mfd/Makefile            |    3 +
 drivers/mfd/rtl8411.c           |  251 ++++++++
 drivers/mfd/rts5209.c           |  223 +++++++
 drivers/mfd/rts5229.c           |  205 +++++++
 drivers/mfd/rtsx_pcr.c          | 1251 +++++++++++++++++++++++++++++++++++++++
 drivers/mfd/rtsx_pcr.h          |   32 +
 include/linux/mfd/rtsx_common.h |   48 ++
 include/linux/mfd/rtsx_pci.h    |  794 +++++++++++++++++++++++++
 9 files changed, 2816 insertions(+)
 create mode 100644 drivers/mfd/rtl8411.c
 create mode 100644 drivers/mfd/rts5209.c
 create mode 100644 drivers/mfd/rts5229.c
 create mode 100644 drivers/mfd/rtsx_pcr.c
 create mode 100644 drivers/mfd/rtsx_pcr.h
 create mode 100644 include/linux/mfd/rtsx_common.h
 create mode 100644 include/linux/mfd/rtsx_pci.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index acab3ef8a310..867af072d482 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -63,6 +63,15 @@ config MFD_SM501_GPIO
 	 lines on the SM501. The platform data is used to supply the
 	 base number for the first GPIO line to register.
 
+config MFD_RTSX_PCI
+	tristate "Support for Realtek PCI-E card reader"
+	depends on PCI
+	help
+	  This supports for Realtek PCI-Express card reader including rts5209,
+	  rts5229, rtl8411, etc. Realtek card reader supports access to many
+	  types of memory cards, such as Memory Stick, Memory Stick Pro,
+	  Secure Digital and MultiMediaCard.
+
 config MFD_ASIC3
 	bool "Support for Compaq ASIC3"
 	depends on GENERIC_HARDIRQS && GPIOLIB && ARM
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index d8ccb630ddb0..b53db06d1b46 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -9,6 +9,9 @@ obj-$(CONFIG_MFD_88PM805)	+= 88pm805.o 88pm80x.o
 obj-$(CONFIG_MFD_SM501)		+= sm501.o
 obj-$(CONFIG_MFD_ASIC3)		+= asic3.o tmio_core.o
 
+rtsx_pci-objs			:= rtsx_pcr.o rts5209.o rts5229.o rtl8411.o
+obj-$(CONFIG_MFD_RTSX_PCI)	+= rtsx_pci.o
+
 obj-$(CONFIG_HTC_EGPIO)		+= htc-egpio.o
 obj-$(CONFIG_HTC_PASIC3)	+= htc-pasic3.o
 obj-$(CONFIG_HTC_I2CPLD)	+= htc-i2cpld.o
diff --git a/drivers/mfd/rtl8411.c b/drivers/mfd/rtl8411.c
new file mode 100644
index 000000000000..89f046ca9e41
--- /dev/null
+++ b/drivers/mfd/rtl8411.c
@@ -0,0 +1,251 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/mfd/rtsx_pci.h>
+
+#include "rtsx_pcr.h"
+
+static u8 rtl8411_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	rtsx_pci_read_register(pcr, SYS_VER, &val);
+	return val & 0x0F;
+}
+
+static int rtl8411_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CD_PAD_CTL,
+			CD_DISABLE_MASK | CD_AUTO_DISABLE, CD_ENABLE);
+}
+
+static int rtl8411_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_GPIO, 0x01, 0x00);
+}
+
+static int rtl8411_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_GPIO, 0x01, 0x01);
+}
+
+static int rtl8411_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_AUTO_BLINK, 0xFF, 0x0D);
+}
+
+static int rtl8411_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_AUTO_BLINK, 0x08, 0x00);
+}
+
+static int rtl8411_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	int err;
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			BPP_POWER_MASK, BPP_POWER_5_PERCENT_ON);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, LDO_CTL,
+			BPP_LDO_POWB, BPP_LDO_SUSPEND);
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	/* To avoid too large in-rush current */
+	udelay(150);
+
+	err = rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+			BPP_POWER_MASK, BPP_POWER_10_PERCENT_ON);
+	if (err < 0)
+		return err;
+
+	udelay(150);
+
+	err = rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+			BPP_POWER_MASK, BPP_POWER_15_PERCENT_ON);
+	if (err < 0)
+		return err;
+
+	udelay(150);
+
+	err = rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+			BPP_POWER_MASK, BPP_POWER_ON);
+	if (err < 0)
+		return err;
+
+	return rtsx_pci_write_register(pcr, LDO_CTL, BPP_LDO_POWB, BPP_LDO_ON);
+}
+
+static int rtl8411_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	int err;
+
+	err = rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+			BPP_POWER_MASK, BPP_POWER_OFF);
+	if (err < 0)
+		return err;
+
+	return rtsx_pci_write_register(pcr, LDO_CTL,
+			BPP_LDO_POWB, BPP_LDO_SUSPEND);
+}
+
+static unsigned int rtl8411_cd_deglitch(struct rtsx_pcr *pcr)
+{
+	unsigned int card_exist;
+
+	card_exist = rtsx_pci_readl(pcr, RTSX_BIPR);
+	card_exist &= CARD_EXIST;
+	if (!card_exist) {
+		/* Enable card CD */
+		rtsx_pci_write_register(pcr, CD_PAD_CTL,
+				CD_DISABLE_MASK, CD_ENABLE);
+		/* Enable card interrupt */
+		rtsx_pci_write_register(pcr, EFUSE_CONTENT, 0xe0, 0x00);
+		return 0;
+	}
+
+	if (hweight32(card_exist) > 1) {
+		rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+				BPP_POWER_MASK, BPP_POWER_5_PERCENT_ON);
+		msleep(100);
+
+		card_exist = rtsx_pci_readl(pcr, RTSX_BIPR);
+		if (card_exist & MS_EXIST)
+			card_exist = MS_EXIST;
+		else if (card_exist & SD_EXIST)
+			card_exist = SD_EXIST;
+		else
+			card_exist = 0;
+
+		rtsx_pci_write_register(pcr, CARD_PWR_CTL,
+				BPP_POWER_MASK, BPP_POWER_OFF);
+
+		dev_dbg(&(pcr->pci->dev),
+				"After CD deglitch, card_exist = 0x%x\n",
+				card_exist);
+	}
+
+	if (card_exist & MS_EXIST) {
+		/* Disable SD interrupt */
+		rtsx_pci_write_register(pcr, EFUSE_CONTENT, 0xe0, 0x40);
+		rtsx_pci_write_register(pcr, CD_PAD_CTL,
+				CD_DISABLE_MASK, MS_CD_EN_ONLY);
+	} else if (card_exist & SD_EXIST) {
+		/* Disable MS interrupt */
+		rtsx_pci_write_register(pcr, EFUSE_CONTENT, 0xe0, 0x80);
+		rtsx_pci_write_register(pcr, CD_PAD_CTL,
+				CD_DISABLE_MASK, SD_CD_EN_ONLY);
+	}
+
+	return card_exist;
+}
+
+static const struct pcr_ops rtl8411_pcr_ops = {
+	.extra_init_hw = rtl8411_extra_init_hw,
+	.optimize_phy = NULL,
+	.turn_on_led = rtl8411_turn_on_led,
+	.turn_off_led = rtl8411_turn_off_led,
+	.enable_auto_blink = rtl8411_enable_auto_blink,
+	.disable_auto_blink = rtl8411_disable_auto_blink,
+	.card_power_on = rtl8411_card_power_on,
+	.card_power_off = rtl8411_card_power_off,
+	.cd_deglitch = rtl8411_cd_deglitch,
+};
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rtl8411_sd_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xA9),
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x09),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x09),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x04),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rtl8411_sd_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0x65),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0x95),
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x09),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x05),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x04),
+	0,
+};
+
+/* MS Pull Control Enable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rtl8411_ms_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0x65),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0x95),
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x05),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x05),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x04),
+	0,
+};
+
+/* MS Pull Control Disable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rtl8411_ms_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0x65),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0x95),
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x09),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x05),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x04),
+	0,
+};
+
+void rtl8411_init_params(struct rtsx_pcr *pcr)
+{
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104;
+	pcr->num_slots = 2;
+	pcr->ops = &rtl8411_pcr_ops;
+
+	pcr->ic_version = rtl8411_get_ic_version(pcr);
+	pcr->sd_pull_ctl_enable_tbl = rtl8411_sd_pull_ctl_enable_tbl;
+	pcr->sd_pull_ctl_disable_tbl = rtl8411_sd_pull_ctl_disable_tbl;
+	pcr->ms_pull_ctl_enable_tbl = rtl8411_ms_pull_ctl_enable_tbl;
+	pcr->ms_pull_ctl_disable_tbl = rtl8411_ms_pull_ctl_disable_tbl;
+}
diff --git a/drivers/mfd/rts5209.c b/drivers/mfd/rts5209.c
new file mode 100644
index 000000000000..283a4f148084
--- /dev/null
+++ b/drivers/mfd/rts5209.c
@@ -0,0 +1,223 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/mfd/rtsx_pci.h>
+
+#include "rtsx_pcr.h"
+
+static u8 rts5209_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	val = rtsx_pci_readb(pcr, 0x1C);
+	return val & 0x0F;
+}
+
+static void rts5209_init_vendor_cfg(struct rtsx_pcr *pcr)
+{
+	u32 val;
+
+	rtsx_pci_read_config_dword(pcr, 0x724, &val);
+	dev_dbg(&(pcr->pci->dev), "Cfg 0x724: 0x%x\n", val);
+
+	if (!(val & 0x80)) {
+		if (val & 0x08)
+			pcr->ms_pmos = false;
+		else
+			pcr->ms_pmos = true;
+	}
+}
+
+static int rts5209_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_init_cmd(pcr);
+
+	/* Turn off LED */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_GPIO, 0xFF, 0x03);
+	/* Configure GPIO as output */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_GPIO_DIR, 0xFF, 0x03);
+
+	return rtsx_pci_send_cmd(pcr, 100);
+}
+
+static int rts5209_optimize_phy(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_phy_register(pcr, 0x00, 0xB966);
+}
+
+static int rts5209_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_GPIO, 0x01, 0x00);
+}
+
+static int rts5209_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_GPIO, 0x01, 0x01);
+}
+
+static int rts5209_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_AUTO_BLINK, 0xFF, 0x0D);
+}
+
+static int rts5209_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, CARD_AUTO_BLINK, 0x08, 0x00);
+}
+
+static int rts5209_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	int err;
+	u8 pwr_mask, partial_pwr_on, pwr_on;
+
+	pwr_mask = SD_POWER_MASK;
+	partial_pwr_on = SD_PARTIAL_POWER_ON;
+	pwr_on = SD_POWER_ON;
+
+	if (pcr->ms_pmos && (card == RTSX_MS_CARD)) {
+		pwr_mask = MS_POWER_MASK;
+		partial_pwr_on = MS_PARTIAL_POWER_ON;
+		pwr_on = MS_POWER_ON;
+	}
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			pwr_mask, partial_pwr_on);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0x04);
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	/* To avoid too large in-rush current */
+	udelay(150);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL, pwr_mask, pwr_on);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0x00);
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int rts5209_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	u8 pwr_mask, pwr_off;
+
+	pwr_mask = SD_POWER_MASK;
+	pwr_off = SD_POWER_OFF;
+
+	if (pcr->ms_pmos && (card == RTSX_MS_CARD)) {
+		pwr_mask = MS_POWER_MASK;
+		pwr_off = MS_POWER_OFF;
+	}
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			pwr_mask | PMOS_STRG_MASK, pwr_off | PMOS_STRG_400mA);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0X06);
+	return rtsx_pci_send_cmd(pcr, 100);
+}
+
+static const struct pcr_ops rts5209_pcr_ops = {
+	.extra_init_hw = rts5209_extra_init_hw,
+	.optimize_phy = rts5209_optimize_phy,
+	.turn_on_led = rts5209_turn_on_led,
+	.turn_off_led = rts5209_turn_off_led,
+	.enable_auto_blink = rts5209_enable_auto_blink,
+	.disable_auto_blink = rts5209_disable_auto_blink,
+	.card_power_on = rts5209_card_power_on,
+	.card_power_off = rts5209_card_power_off,
+	.cd_deglitch = NULL,
+};
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5209_sd_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE9),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5209_sd_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL1, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD5),
+	0,
+};
+
+/* MS Pull Control Enable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rts5209_ms_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x15),
+	0,
+};
+
+/* MS Pull Control Disable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rts5209_ms_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL4, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x15),
+	0,
+};
+
+void rts5209_init_params(struct rtsx_pcr *pcr)
+{
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 |
+		EXTRA_CAPS_SD_SDR104 | EXTRA_CAPS_MMC_8BIT;
+	pcr->num_slots = 2;
+	pcr->ops = &rts5209_pcr_ops;
+
+	rts5209_init_vendor_cfg(pcr);
+
+	pcr->ic_version = rts5209_get_ic_version(pcr);
+	pcr->sd_pull_ctl_enable_tbl = rts5209_sd_pull_ctl_enable_tbl;
+	pcr->sd_pull_ctl_disable_tbl = rts5209_sd_pull_ctl_disable_tbl;
+	pcr->ms_pull_ctl_enable_tbl = rts5209_ms_pull_ctl_enable_tbl;
+	pcr->ms_pull_ctl_disable_tbl = rts5209_ms_pull_ctl_disable_tbl;
+}
diff --git a/drivers/mfd/rts5229.c b/drivers/mfd/rts5229.c
new file mode 100644
index 000000000000..b9dbab266fda
--- /dev/null
+++ b/drivers/mfd/rts5229.c
@@ -0,0 +1,205 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/mfd/rtsx_pci.h>
+
+#include "rtsx_pcr.h"
+
+static u8 rts5229_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	rtsx_pci_read_register(pcr, DUMMY_REG_RESET_0, &val);
+	return val & 0x0F;
+}
+
+static int rts5229_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_init_cmd(pcr);
+
+	/* Configure GPIO as output */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, GPIO_CTL, 0x02, 0x02);
+	/* Switch LDO3318 source from DV33 to card_3v3 */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, LDO_PWR_SEL, 0x03, 0x00);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, LDO_PWR_SEL, 0x03, 0x01);
+	/* LED shine disabled, set initial shine cycle period */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, OLT_LED_CTL, 0x0F, 0x02);
+
+	return rtsx_pci_send_cmd(pcr, 100);
+}
+
+static int rts5229_optimize_phy(struct rtsx_pcr *pcr)
+{
+	/* Optimize RX sensitivity */
+	return rtsx_pci_write_phy_register(pcr, 0x00, 0xBA42);
+}
+
+static int rts5229_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL, 0x02, 0x02);
+}
+
+static int rts5229_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL, 0x02, 0x00);
+}
+
+static int rts5229_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL, 0x08, 0x08);
+}
+
+static int rts5229_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL, 0x08, 0x00);
+}
+
+static int rts5229_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	int err;
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			SD_POWER_MASK, SD_PARTIAL_POWER_ON);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0x02);
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	/* To avoid too large in-rush current */
+	udelay(150);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			SD_POWER_MASK, SD_POWER_ON);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0x06);
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int rts5229_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_PWR_CTL,
+			SD_POWER_MASK | PMOS_STRG_MASK,
+			SD_POWER_OFF | PMOS_STRG_400mA);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PWR_GATE_CTRL,
+			LDO3318_PWR_MASK, 0X00);
+	return rtsx_pci_send_cmd(pcr, 100);
+}
+
+static const struct pcr_ops rts5229_pcr_ops = {
+	.extra_init_hw = rts5229_extra_init_hw,
+	.optimize_phy = rts5229_optimize_phy,
+	.turn_on_led = rts5229_turn_on_led,
+	.turn_off_led = rts5229_turn_off_led,
+	.enable_auto_blink = rts5229_enable_auto_blink,
+	.disable_auto_blink = rts5229_disable_auto_blink,
+	.card_power_on = rts5229_card_power_on,
+	.card_power_off = rts5229_card_power_off,
+	.cd_deglitch = NULL,
+};
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5229_sd_pull_ctl_enable_tbl1[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE9),
+	0,
+};
+
+/* For RTS5229 version C */
+static const u32 rts5229_sd_pull_ctl_enable_tbl2[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD9),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5229_sd_pull_ctl_disable_tbl1[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD5),
+	0,
+};
+
+/* For RTS5229 version C */
+static const u32 rts5229_sd_pull_ctl_disable_tbl2[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE5),
+	0,
+};
+
+/* MS Pull Control Enable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rts5229_ms_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x15),
+	0,
+};
+
+/* MS Pull Control Disable:
+ *     MS CD       ==> pull up
+ *     others      ==> pull down
+ */
+static const u32 rts5229_ms_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL5, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL6, 0x15),
+	0,
+};
+
+void rts5229_init_params(struct rtsx_pcr *pcr)
+{
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104;
+	pcr->num_slots = 2;
+	pcr->ops = &rts5229_pcr_ops;
+
+	pcr->ic_version = rts5229_get_ic_version(pcr);
+	if (pcr->ic_version == IC_VER_C) {
+		pcr->sd_pull_ctl_enable_tbl = rts5229_sd_pull_ctl_enable_tbl2;
+		pcr->sd_pull_ctl_disable_tbl = rts5229_sd_pull_ctl_disable_tbl2;
+	} else {
+		pcr->sd_pull_ctl_enable_tbl = rts5229_sd_pull_ctl_enable_tbl1;
+		pcr->sd_pull_ctl_disable_tbl = rts5229_sd_pull_ctl_disable_tbl1;
+	}
+	pcr->ms_pull_ctl_enable_tbl = rts5229_ms_pull_ctl_enable_tbl;
+	pcr->ms_pull_ctl_disable_tbl = rts5229_ms_pull_ctl_disable_tbl;
+}
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
new file mode 100644
index 000000000000..56d4377c62c2
--- /dev/null
+++ b/drivers/mfd/rtsx_pcr.c
@@ -0,0 +1,1251 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+#include <linux/highmem.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/idr.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/rtsx_pci.h>
+#include <asm/unaligned.h>
+
+#include "rtsx_pcr.h"
+
+static bool msi_en = true;
+module_param(msi_en, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(msi_en, "Enable MSI");
+
+static DEFINE_IDR(rtsx_pci_idr);
+static DEFINE_SPINLOCK(rtsx_pci_lock);
+
+static struct mfd_cell rtsx_pcr_cells[] = {
+	[RTSX_SD_CARD] = {
+		.name = DRV_NAME_RTSX_PCI_SDMMC,
+	},
+	[RTSX_MS_CARD] = {
+		.name = DRV_NAME_RTSX_PCI_MS,
+	},
+};
+
+static DEFINE_PCI_DEVICE_TABLE(rtsx_pci_ids) = {
+	{ PCI_DEVICE(0x10EC, 0x5209), PCI_CLASS_OTHERS << 16, 0xFF0000 },
+	{ PCI_DEVICE(0x10EC, 0x5229), PCI_CLASS_OTHERS << 16, 0xFF0000 },
+	{ PCI_DEVICE(0x10EC, 0x5289), PCI_CLASS_OTHERS << 16, 0xFF0000 },
+	{ 0, }
+};
+
+MODULE_DEVICE_TABLE(pci, rtsx_pci_ids);
+
+void rtsx_pci_start_run(struct rtsx_pcr *pcr)
+{
+	/* If pci device removed, don't queue idle work any more */
+	if (pcr->remove_pci)
+		return;
+
+	if (pcr->state != PDEV_STAT_RUN) {
+		pcr->state = PDEV_STAT_RUN;
+		if (pcr->ops->enable_auto_blink)
+			pcr->ops->enable_auto_blink(pcr);
+	}
+
+	mod_delayed_work(system_wq, &pcr->idle_work, msecs_to_jiffies(200));
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_start_run);
+
+int rtsx_pci_write_register(struct rtsx_pcr *pcr, u16 addr, u8 mask, u8 data)
+{
+	int i;
+	u32 val = HAIMR_WRITE_START;
+
+	val |= (u32)(addr & 0x3FFF) << 16;
+	val |= (u32)mask << 8;
+	val |= (u32)data;
+
+	rtsx_pci_writel(pcr, RTSX_HAIMR, val);
+
+	for (i = 0; i < MAX_RW_REG_CNT; i++) {
+		val = rtsx_pci_readl(pcr, RTSX_HAIMR);
+		if ((val & HAIMR_TRANS_END) == 0) {
+			if (data != (u8)val)
+				return -EIO;
+			return 0;
+		}
+	}
+
+	return -ETIMEDOUT;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_write_register);
+
+int rtsx_pci_read_register(struct rtsx_pcr *pcr, u16 addr, u8 *data)
+{
+	u32 val = HAIMR_READ_START;
+	int i;
+
+	val |= (u32)(addr & 0x3FFF) << 16;
+	rtsx_pci_writel(pcr, RTSX_HAIMR, val);
+
+	for (i = 0; i < MAX_RW_REG_CNT; i++) {
+		val = rtsx_pci_readl(pcr, RTSX_HAIMR);
+		if ((val & HAIMR_TRANS_END) == 0)
+			break;
+	}
+
+	if (i >= MAX_RW_REG_CNT)
+		return -ETIMEDOUT;
+
+	if (data)
+		*data = (u8)(val & 0xFF);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_read_register);
+
+int rtsx_pci_write_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 val)
+{
+	int err, i, finished = 0;
+	u8 tmp;
+
+	rtsx_pci_init_cmd(pcr);
+
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYDATA0, 0xFF, (u8)val);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYDATA1, 0xFF, (u8)(val >> 8));
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYADDR, 0xFF, addr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYRWCTL, 0xFF, 0x81);
+
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i < 100000; i++) {
+		err = rtsx_pci_read_register(pcr, PHYRWCTL, &tmp);
+		if (err < 0)
+			return err;
+
+		if (!(tmp & 0x80)) {
+			finished = 1;
+			break;
+		}
+	}
+
+	if (!finished)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_write_phy_register);
+
+int rtsx_pci_read_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 *val)
+{
+	int err, i, finished = 0;
+	u16 data;
+	u8 *ptr, tmp;
+
+	rtsx_pci_init_cmd(pcr);
+
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYADDR, 0xFF, addr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PHYRWCTL, 0xFF, 0x80);
+
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i < 100000; i++) {
+		err = rtsx_pci_read_register(pcr, PHYRWCTL, &tmp);
+		if (err < 0)
+			return err;
+
+		if (!(tmp & 0x80)) {
+			finished = 1;
+			break;
+		}
+	}
+
+	if (!finished)
+		return -ETIMEDOUT;
+
+	rtsx_pci_init_cmd(pcr);
+
+	rtsx_pci_add_cmd(pcr, READ_REG_CMD, PHYDATA0, 0, 0);
+	rtsx_pci_add_cmd(pcr, READ_REG_CMD, PHYDATA1, 0, 0);
+
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	ptr = rtsx_pci_get_cmd_data(pcr);
+	data = ((u16)ptr[1] << 8) | ptr[0];
+
+	if (val)
+		*val = data;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_read_phy_register);
+
+void rtsx_pci_stop_cmd(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, STOP_CMD);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, STOP_DMA);
+
+	rtsx_pci_write_register(pcr, DMACTL, 0x80, 0x80);
+	rtsx_pci_write_register(pcr, RBCTL, 0x80, 0x80);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_stop_cmd);
+
+void rtsx_pci_add_cmd(struct rtsx_pcr *pcr,
+		u8 cmd_type, u16 reg_addr, u8 mask, u8 data)
+{
+	unsigned long flags;
+	u32 val = 0;
+	u32 *ptr = (u32 *)(pcr->host_cmds_ptr);
+
+	val |= (u32)(cmd_type & 0x03) << 30;
+	val |= (u32)(reg_addr & 0x3FFF) << 16;
+	val |= (u32)mask << 8;
+	val |= (u32)data;
+
+	spin_lock_irqsave(&pcr->lock, flags);
+	ptr += pcr->ci;
+	if (pcr->ci < (HOST_CMDS_BUF_LEN / 4)) {
+		put_unaligned_le32(val, ptr);
+		ptr++;
+		pcr->ci++;
+	}
+	spin_unlock_irqrestore(&pcr->lock, flags);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_add_cmd);
+
+void rtsx_pci_send_cmd_no_wait(struct rtsx_pcr *pcr)
+{
+	u32 val = 1 << 31;
+
+	rtsx_pci_writel(pcr, RTSX_HCBAR, pcr->host_cmds_addr);
+
+	val |= (u32)(pcr->ci * 4) & 0x00FFFFFF;
+	/* Hardware Auto Response */
+	val |= 0x40000000;
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, val);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_send_cmd_no_wait);
+
+int rtsx_pci_send_cmd(struct rtsx_pcr *pcr, int timeout)
+{
+	struct completion trans_done;
+	u32 val = 1 << 31;
+	long timeleft;
+	unsigned long flags;
+	int err = 0;
+
+	spin_lock_irqsave(&pcr->lock, flags);
+
+	/* set up data structures for the wakeup system */
+	pcr->done = &trans_done;
+	pcr->trans_result = TRANS_NOT_READY;
+	init_completion(&trans_done);
+
+	rtsx_pci_writel(pcr, RTSX_HCBAR, pcr->host_cmds_addr);
+
+	val |= (u32)(pcr->ci * 4) & 0x00FFFFFF;
+	/* Hardware Auto Response */
+	val |= 0x40000000;
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, val);
+
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	/* Wait for TRANS_OK_INT */
+	timeleft = wait_for_completion_interruptible_timeout(
+			&trans_done, msecs_to_jiffies(timeout));
+	if (timeleft <= 0) {
+		dev_dbg(&(pcr->pci->dev), "Timeout (%s %d)\n",
+				__func__, __LINE__);
+		err = -ETIMEDOUT;
+		goto finish_send_cmd;
+	}
+
+	spin_lock_irqsave(&pcr->lock, flags);
+	if (pcr->trans_result == TRANS_RESULT_FAIL)
+		err = -EINVAL;
+	else if (pcr->trans_result == TRANS_RESULT_OK)
+		err = 0;
+	else if (pcr->trans_result == TRANS_NO_DEVICE)
+		err = -ENODEV;
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+finish_send_cmd:
+	spin_lock_irqsave(&pcr->lock, flags);
+	pcr->done = NULL;
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	if ((err < 0) && (err != -ENODEV))
+		rtsx_pci_stop_cmd(pcr);
+
+	if (pcr->finish_me)
+		complete(pcr->finish_me);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_send_cmd);
+
+static void rtsx_pci_add_sg_tbl(struct rtsx_pcr *pcr,
+		dma_addr_t addr, unsigned int len, int end)
+{
+	u64 *ptr = (u64 *)(pcr->host_sg_tbl_ptr) + pcr->sgi;
+	u64 val;
+	u8 option = SG_VALID | SG_TRANS_DATA;
+
+	dev_dbg(&(pcr->pci->dev), "DMA addr: 0x%x, Len: 0x%x\n",
+			(unsigned int)addr, len);
+
+	if (end)
+		option |= SG_END;
+	val = ((u64)addr << 32) | ((u64)len << 12) | option;
+
+	put_unaligned_le64(val, ptr);
+	ptr++;
+	pcr->sgi++;
+}
+
+int rtsx_pci_transfer_data(struct rtsx_pcr *pcr, struct scatterlist *sglist,
+		int num_sg, bool read, int timeout)
+{
+	struct completion trans_done;
+	u8 dir;
+	int err = 0, i, count;
+	long timeleft;
+	unsigned long flags;
+	struct scatterlist *sg;
+	enum dma_data_direction dma_dir;
+	u32 val;
+	dma_addr_t addr;
+	unsigned int len;
+
+	dev_dbg(&(pcr->pci->dev), "--> %s: num_sg = %d\n", __func__, num_sg);
+
+	/* don't transfer data during abort processing */
+	if (pcr->remove_pci)
+		return -EINVAL;
+
+	if ((sglist == NULL) || (num_sg <= 0))
+		return -EINVAL;
+
+	if (read) {
+		dir = DEVICE_TO_HOST;
+		dma_dir = DMA_FROM_DEVICE;
+	} else {
+		dir = HOST_TO_DEVICE;
+		dma_dir = DMA_TO_DEVICE;
+	}
+
+	count = dma_map_sg(&(pcr->pci->dev), sglist, num_sg, dma_dir);
+	if (count < 1) {
+		dev_err(&(pcr->pci->dev), "scatterlist map failed\n");
+		return -EINVAL;
+	}
+	dev_dbg(&(pcr->pci->dev), "DMA mapping count: %d\n", count);
+
+	val = ((u32)(dir & 0x01) << 29) | TRIG_DMA | ADMA_MODE;
+	pcr->sgi = 0;
+	for_each_sg(sglist, sg, count, i) {
+		addr = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+		rtsx_pci_add_sg_tbl(pcr, addr, len, i == count - 1);
+	}
+
+	spin_lock_irqsave(&pcr->lock, flags);
+
+	pcr->done = &trans_done;
+	pcr->trans_result = TRANS_NOT_READY;
+	init_completion(&trans_done);
+	rtsx_pci_writel(pcr, RTSX_HDBAR, pcr->host_sg_tbl_addr);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, val);
+
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	timeleft = wait_for_completion_interruptible_timeout(
+			&trans_done, msecs_to_jiffies(timeout));
+	if (timeleft <= 0) {
+		dev_dbg(&(pcr->pci->dev), "Timeout (%s %d)\n",
+				__func__, __LINE__);
+		err = -ETIMEDOUT;
+		goto out;
+	}
+
+	spin_lock_irqsave(&pcr->lock, flags);
+
+	if (pcr->trans_result == TRANS_RESULT_FAIL)
+		err = -EINVAL;
+	else if (pcr->trans_result == TRANS_NO_DEVICE)
+		err = -ENODEV;
+
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+out:
+	spin_lock_irqsave(&pcr->lock, flags);
+	pcr->done = NULL;
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	dma_unmap_sg(&(pcr->pci->dev), sglist, num_sg, dma_dir);
+
+	if ((err < 0) && (err != -ENODEV))
+		rtsx_pci_stop_cmd(pcr);
+
+	if (pcr->finish_me)
+		complete(pcr->finish_me);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_transfer_data);
+
+int rtsx_pci_read_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len)
+{
+	int err;
+	int i, j;
+	u16 reg;
+	u8 *ptr;
+
+	if (buf_len > 512)
+		buf_len = 512;
+
+	ptr = buf;
+	reg = PPBUF_BASE2;
+	for (i = 0; i < buf_len / 256; i++) {
+		rtsx_pci_init_cmd(pcr);
+
+		for (j = 0; j < 256; j++)
+			rtsx_pci_add_cmd(pcr, READ_REG_CMD, reg++, 0, 0);
+
+		err = rtsx_pci_send_cmd(pcr, 250);
+		if (err < 0)
+			return err;
+
+		memcpy(ptr, rtsx_pci_get_cmd_data(pcr), 256);
+		ptr += 256;
+	}
+
+	if (buf_len % 256) {
+		rtsx_pci_init_cmd(pcr);
+
+		for (j = 0; j < buf_len % 256; j++)
+			rtsx_pci_add_cmd(pcr, READ_REG_CMD, reg++, 0, 0);
+
+		err = rtsx_pci_send_cmd(pcr, 250);
+		if (err < 0)
+			return err;
+	}
+
+	memcpy(ptr, rtsx_pci_get_cmd_data(pcr), buf_len % 256);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_read_ppbuf);
+
+int rtsx_pci_write_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len)
+{
+	int err;
+	int i, j;
+	u16 reg;
+	u8 *ptr;
+
+	if (buf_len > 512)
+		buf_len = 512;
+
+	ptr = buf;
+	reg = PPBUF_BASE2;
+	for (i = 0; i < buf_len / 256; i++) {
+		rtsx_pci_init_cmd(pcr);
+
+		for (j = 0; j < 256; j++) {
+			rtsx_pci_add_cmd(pcr, WRITE_REG_CMD,
+					reg++, 0xFF, *ptr);
+			ptr++;
+		}
+
+		err = rtsx_pci_send_cmd(pcr, 250);
+		if (err < 0)
+			return err;
+	}
+
+	if (buf_len % 256) {
+		rtsx_pci_init_cmd(pcr);
+
+		for (j = 0; j < buf_len % 256; j++) {
+			rtsx_pci_add_cmd(pcr, WRITE_REG_CMD,
+					reg++, 0xFF, *ptr);
+			ptr++;
+		}
+
+		err = rtsx_pci_send_cmd(pcr, 250);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_write_ppbuf);
+
+static int rtsx_pci_set_pull_ctl(struct rtsx_pcr *pcr, const u32 *tbl)
+{
+	int err;
+
+	rtsx_pci_init_cmd(pcr);
+
+	while (*tbl & 0xFFFF0000) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD,
+				(u16)(*tbl >> 16), 0xFF, (u8)(*tbl));
+		tbl++;
+	}
+
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+int rtsx_pci_card_pull_ctl_enable(struct rtsx_pcr *pcr, int card)
+{
+	const u32 *tbl;
+
+	if (card == RTSX_SD_CARD)
+		tbl = pcr->sd_pull_ctl_enable_tbl;
+	else if (card == RTSX_MS_CARD)
+		tbl = pcr->ms_pull_ctl_enable_tbl;
+	else
+		return -EINVAL;
+
+	return rtsx_pci_set_pull_ctl(pcr, tbl);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_card_pull_ctl_enable);
+
+int rtsx_pci_card_pull_ctl_disable(struct rtsx_pcr *pcr, int card)
+{
+	const u32 *tbl;
+
+	if (card == RTSX_SD_CARD)
+		tbl = pcr->sd_pull_ctl_disable_tbl;
+	else if (card == RTSX_MS_CARD)
+		tbl = pcr->ms_pull_ctl_disable_tbl;
+	else
+		return -EINVAL;
+
+
+	return rtsx_pci_set_pull_ctl(pcr, tbl);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_card_pull_ctl_disable);
+
+static void rtsx_pci_enable_bus_int(struct rtsx_pcr *pcr)
+{
+	pcr->bier = TRANS_OK_INT_EN | TRANS_FAIL_INT_EN | SD_INT_EN;
+
+	if (pcr->num_slots > 1)
+		pcr->bier |= MS_INT_EN;
+
+	/* Enable Bus Interrupt */
+	rtsx_pci_writel(pcr, RTSX_BIER, pcr->bier);
+
+	dev_dbg(&(pcr->pci->dev), "RTSX_BIER: 0x%08x\n", pcr->bier);
+}
+
+static inline u8 double_ssc_depth(u8 depth)
+{
+	return ((depth > 1) ? (depth - 1) : depth);
+}
+
+static u8 revise_ssc_depth(u8 ssc_depth, u8 div)
+{
+	if (div > CLK_DIV_1) {
+		if (ssc_depth > (div - 1))
+			ssc_depth -= (div - 1);
+		else
+			ssc_depth = SSC_DEPTH_4M;
+	}
+
+	return ssc_depth;
+}
+
+int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk)
+{
+	int err, clk;
+	u8 N, min_N, max_N, clk_divider;
+	u8 mcu_cnt, div, max_div;
+	u8 depth[] = {
+		[RTSX_SSC_DEPTH_4M] = SSC_DEPTH_4M,
+		[RTSX_SSC_DEPTH_2M] = SSC_DEPTH_2M,
+		[RTSX_SSC_DEPTH_1M] = SSC_DEPTH_1M,
+		[RTSX_SSC_DEPTH_500K] = SSC_DEPTH_500K,
+		[RTSX_SSC_DEPTH_250K] = SSC_DEPTH_250K,
+	};
+
+	if (initial_mode) {
+		/* We use 250k(around) here, in initial stage */
+		clk_divider = SD_CLK_DIVIDE_128;
+		card_clock = 30000000;
+	} else {
+		clk_divider = SD_CLK_DIVIDE_0;
+	}
+	err = rtsx_pci_write_register(pcr, SD_CFG1,
+			SD_CLK_DIVIDE_MASK, clk_divider);
+	if (err < 0)
+		return err;
+
+	card_clock /= 1000000;
+	dev_dbg(&(pcr->pci->dev), "Switch card clock to %dMHz\n", card_clock);
+
+	min_N = 80;
+	max_N = 208;
+	max_div = CLK_DIV_8;
+
+	clk = card_clock;
+	if (!initial_mode && double_clk)
+		clk = card_clock * 2;
+	dev_dbg(&(pcr->pci->dev),
+			"Internal SSC clock: %dMHz (cur_clock = %d)\n",
+			clk, pcr->cur_clock);
+
+	if (clk == pcr->cur_clock)
+		return 0;
+
+	N = (u8)(clk - 2);
+	if ((clk <= 2) || (N > max_N))
+		return -EINVAL;
+
+	mcu_cnt = (u8)(125/clk + 3);
+	if (mcu_cnt > 15)
+		mcu_cnt = 15;
+
+	/* Make sure that the SSC clock div_n is equal or greater than min_N */
+	div = CLK_DIV_1;
+	while ((N < min_N) && (div < max_div)) {
+		N = (N + 2) * 2 - 2;
+		div++;
+	}
+	dev_dbg(&(pcr->pci->dev), "N = %d, div = %d\n", N, div);
+
+	ssc_depth = depth[ssc_depth];
+	if (double_clk)
+		ssc_depth = double_ssc_depth(ssc_depth);
+
+	ssc_depth = revise_ssc_depth(ssc_depth, div);
+	dev_dbg(&(pcr->pci->dev), "ssc_depth = %d\n", ssc_depth);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL,
+			CLK_LOW_FREQ, CLK_LOW_FREQ);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_DIV,
+			0xFF, (div << 4) | mcu_cnt);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2,
+			SSC_DEPTH_MASK, ssc_depth);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_DIV_N_0, 0xFF, N);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, SSC_RSTB);
+	if (vpclk) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+	}
+
+	err = rtsx_pci_send_cmd(pcr, 2000);
+	if (err < 0)
+		return err;
+
+	/* Wait SSC clock stable */
+	udelay(10);
+	err = rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0);
+	if (err < 0)
+		return err;
+
+	pcr->cur_clock = clk;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_switch_clock);
+
+int rtsx_pci_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	if (pcr->ops->card_power_on)
+		return pcr->ops->card_power_on(pcr, card);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_card_power_on);
+
+int rtsx_pci_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	if (pcr->ops->card_power_off)
+		return pcr->ops->card_power_off(pcr, card);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_card_power_off);
+
+unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr)
+{
+	unsigned int val;
+
+	val = rtsx_pci_readl(pcr, RTSX_BIPR);
+	if (pcr->ops->cd_deglitch)
+		val = pcr->ops->cd_deglitch(pcr);
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_card_exist);
+
+void rtsx_pci_complete_unfinished_transfer(struct rtsx_pcr *pcr)
+{
+	struct completion finish;
+
+	pcr->finish_me = &finish;
+	init_completion(&finish);
+
+	if (pcr->done)
+		complete(pcr->done);
+
+	if (!pcr->remove_pci)
+		rtsx_pci_stop_cmd(pcr);
+
+	wait_for_completion_interruptible_timeout(&finish,
+			msecs_to_jiffies(2));
+	pcr->finish_me = NULL;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_complete_unfinished_transfer);
+
+static void rtsx_pci_card_detect(struct work_struct *work)
+{
+	struct delayed_work *dwork;
+	struct rtsx_pcr *pcr;
+	unsigned long flags;
+	unsigned int card_detect = 0;
+	u32 irq_status;
+
+	dwork = to_delayed_work(work);
+	pcr = container_of(dwork, struct rtsx_pcr, carddet_work);
+
+	dev_dbg(&(pcr->pci->dev), "--> %s\n", __func__);
+
+	spin_lock_irqsave(&pcr->lock, flags);
+
+	irq_status = rtsx_pci_readl(pcr, RTSX_BIPR);
+	dev_dbg(&(pcr->pci->dev), "irq_status: 0x%08x\n", irq_status);
+
+	if (pcr->card_inserted || pcr->card_removed) {
+		dev_dbg(&(pcr->pci->dev),
+				"card_inserted: 0x%x, card_removed: 0x%x\n",
+				pcr->card_inserted, pcr->card_removed);
+
+		if (pcr->ops->cd_deglitch)
+			pcr->card_inserted = pcr->ops->cd_deglitch(pcr);
+
+		card_detect = pcr->card_inserted | pcr->card_removed;
+		pcr->card_inserted = 0;
+		pcr->card_removed = 0;
+	}
+
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	if (card_detect & SD_EXIST)
+		pcr->slots[RTSX_SD_CARD].card_event(
+				pcr->slots[RTSX_SD_CARD].p_dev);
+	if (card_detect & MS_EXIST)
+		pcr->slots[RTSX_MS_CARD].card_event(
+				pcr->slots[RTSX_MS_CARD].p_dev);
+}
+
+static irqreturn_t rtsx_pci_isr(int irq, void *dev_id)
+{
+	struct rtsx_pcr *pcr = dev_id;
+	u32 int_reg;
+
+	if (!pcr)
+		return IRQ_NONE;
+
+	spin_lock(&pcr->lock);
+
+	int_reg = rtsx_pci_readl(pcr, RTSX_BIPR);
+	/* Clear interrupt flag */
+	rtsx_pci_writel(pcr, RTSX_BIPR, int_reg);
+	if ((int_reg & pcr->bier) == 0) {
+		spin_unlock(&pcr->lock);
+		return IRQ_NONE;
+	}
+	if (int_reg == 0xFFFFFFFF) {
+		spin_unlock(&pcr->lock);
+		return IRQ_HANDLED;
+	}
+
+	int_reg &= (pcr->bier | 0x7FFFFF);
+
+	if (int_reg & SD_INT) {
+		if (int_reg & SD_EXIST) {
+			pcr->card_inserted |= SD_EXIST;
+		} else {
+			pcr->card_removed |= SD_EXIST;
+			pcr->card_inserted &= ~SD_EXIST;
+		}
+	}
+
+	if (int_reg & MS_INT) {
+		if (int_reg & MS_EXIST) {
+			pcr->card_inserted |= MS_EXIST;
+		} else {
+			pcr->card_removed |= MS_EXIST;
+			pcr->card_inserted &= ~MS_EXIST;
+		}
+	}
+
+	if (pcr->card_inserted || pcr->card_removed)
+		schedule_delayed_work(&pcr->carddet_work,
+				msecs_to_jiffies(200));
+
+	if (int_reg & (NEED_COMPLETE_INT | DELINK_INT)) {
+		if (int_reg & (TRANS_FAIL_INT | DELINK_INT)) {
+			pcr->trans_result = TRANS_RESULT_FAIL;
+			if (pcr->done)
+				complete(pcr->done);
+		} else if (int_reg & TRANS_OK_INT) {
+			pcr->trans_result = TRANS_RESULT_OK;
+			if (pcr->done)
+				complete(pcr->done);
+		}
+	}
+
+	spin_unlock(&pcr->lock);
+	return IRQ_HANDLED;
+}
+
+static int rtsx_pci_acquire_irq(struct rtsx_pcr *pcr)
+{
+	dev_info(&(pcr->pci->dev), "%s: pcr->msi_en = %d, pci->irq = %d\n",
+			__func__, pcr->msi_en, pcr->pci->irq);
+
+	if (request_irq(pcr->pci->irq, rtsx_pci_isr,
+			pcr->msi_en ? 0 : IRQF_SHARED,
+			DRV_NAME_RTSX_PCI, pcr)) {
+		dev_err(&(pcr->pci->dev),
+			"rtsx_sdmmc: unable to grab IRQ %d, disabling device\n",
+			pcr->pci->irq);
+		return -1;
+	}
+
+	pcr->irq = pcr->pci->irq;
+	pci_intx(pcr->pci, !pcr->msi_en);
+
+	return 0;
+}
+
+static void rtsx_pci_idle_work(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct rtsx_pcr *pcr = container_of(dwork, struct rtsx_pcr, idle_work);
+
+	dev_dbg(&(pcr->pci->dev), "--> %s\n", __func__);
+
+	mutex_lock(&pcr->pcr_mutex);
+
+	pcr->state = PDEV_STAT_IDLE;
+
+	if (pcr->ops->disable_auto_blink)
+		pcr->ops->disable_auto_blink(pcr);
+	if (pcr->ops->turn_off_led)
+		pcr->ops->turn_off_led(pcr);
+
+	mutex_unlock(&pcr->pcr_mutex);
+}
+
+static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
+{
+	int err;
+
+	rtsx_pci_writel(pcr, RTSX_HCBAR, pcr->host_cmds_addr);
+
+	rtsx_pci_enable_bus_int(pcr);
+
+	/* Power on SSC */
+	err = rtsx_pci_write_register(pcr, FPDCTL, SSC_POWER_DOWN, 0);
+	if (err < 0)
+		return err;
+
+	/* Wait SSC power stable */
+	udelay(200);
+
+	if (pcr->ops->optimize_phy) {
+		err = pcr->ops->optimize_phy(pcr);
+		if (err < 0)
+			return err;
+	}
+
+	rtsx_pci_init_cmd(pcr);
+
+	/* Set mcu_cnt to 7 to ensure data can be sampled properly */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_DIV, 0x07, 0x07);
+
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, HOST_SLEEP_STATE, 0x03, 0x00);
+	/* Disable card clock */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CARD_CLK_EN, 0x1E, 0);
+	/* Reset ASPM state to default value */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, ASPM_FORCE_CTL, 0x3F, 0);
+	/* Reset delink mode */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CHANGE_LINK_STATE, 0x0A, 0);
+	/* Card driving select */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD30_DRIVE_SEL,
+			0x07, DRIVER_TYPE_D);
+	/* Enable SSC Clock */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1,
+			0xFF, SSC_8X_EN | SSC_SEL_4M);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF, 0x12);
+	/* Disable cd_pwr_save */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CHANGE_LINK_STATE, 0x16, 0x10);
+	/* Clear Link Ready Interrupt */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, IRQSTAT0,
+			LINK_RDY_INT, LINK_RDY_INT);
+	/* Enlarge the estimation window of PERST# glitch
+	 * to reduce the chance of invalid card interrupt
+	 */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PERST_GLITCH_WIDTH, 0xFF, 0x80);
+	/* Update RC oscillator to 400k
+	 * bit[0] F_HIGH: for RC oscillator, Rst_value is 1'b1
+	 *                1: 2M  0: 400k
+	 */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, RCCTL, 0x01, 0x00);
+	/* Set interrupt write clear
+	 * bit 1: U_elbi_if_rd_clr_en
+	 *	1: Enable ELBI interrupt[31:22] & [7:0] flag read clear
+	 *	0: ELBI interrupt flag[31:22] & [7:0] only can be write clear
+	 */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, NFTS_TX_CTRL, 0x02, 0);
+	/* Force CLKREQ# PIN to drive 0 to request clock */
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, 0x08, 0x08);
+
+	err = rtsx_pci_send_cmd(pcr, 100);
+	if (err < 0)
+		return err;
+
+	/* Enable clk_request_n to enable clock power management */
+	rtsx_pci_write_config_byte(pcr, 0x81, 1);
+	/* Enter L1 when host tx idle */
+	rtsx_pci_write_config_byte(pcr, 0x70F, 0x5B);
+
+	if (pcr->ops->extra_init_hw) {
+		err = pcr->ops->extra_init_hw(pcr);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
+static int rtsx_pci_init_chip(struct rtsx_pcr *pcr)
+{
+	int err;
+
+	spin_lock_init(&pcr->lock);
+	mutex_init(&pcr->pcr_mutex);
+
+	switch (PCI_PID(pcr)) {
+	default:
+	case 0x5209:
+		rts5209_init_params(pcr);
+		break;
+
+	case 0x5229:
+		rts5229_init_params(pcr);
+		break;
+
+	case 0x5289:
+		rtl8411_init_params(pcr);
+		break;
+	}
+
+	dev_dbg(&(pcr->pci->dev), "PID: 0x%04x, IC version: 0x%02x\n",
+			PCI_PID(pcr), pcr->ic_version);
+
+	pcr->slots = kcalloc(pcr->num_slots, sizeof(struct rtsx_slot),
+			GFP_KERNEL);
+	if (!pcr->slots)
+		return -ENOMEM;
+
+	pcr->state = PDEV_STAT_IDLE;
+	err = rtsx_pci_init_hw(pcr);
+	if (err < 0) {
+		kfree(pcr->slots);
+		return err;
+	}
+
+	return 0;
+}
+
+static int __devinit rtsx_pci_probe(struct pci_dev *pcidev,
+				    const struct pci_device_id *id)
+{
+	struct rtsx_pcr *pcr;
+	struct pcr_handle *handle;
+	u32 base, len;
+	int ret, i;
+
+	dev_dbg(&(pcidev->dev),
+		": Realtek PCI-E Card Reader found at %s [%04x:%04x] (rev %x)\n",
+		pci_name(pcidev), (int)pcidev->vendor, (int)pcidev->device,
+		(int)pcidev->revision);
+
+	ret = pci_enable_device(pcidev);
+	if (ret)
+		return ret;
+
+	ret = pci_request_regions(pcidev, DRV_NAME_RTSX_PCI);
+	if (ret)
+		goto disable;
+
+	pcr = kzalloc(sizeof(*pcr), GFP_KERNEL);
+	if (!pcr) {
+		ret = -ENOMEM;
+		goto release_pci;
+	}
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle) {
+		ret = -ENOMEM;
+		goto free_pcr;
+	}
+	handle->pcr = pcr;
+
+	if (!idr_pre_get(&rtsx_pci_idr, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto free_handle;
+	}
+
+	spin_lock(&rtsx_pci_lock);
+	ret = idr_get_new(&rtsx_pci_idr, pcr, &pcr->id);
+	spin_unlock(&rtsx_pci_lock);
+	if (ret)
+		goto free_handle;
+
+	pcr->pci = pcidev;
+	dev_set_drvdata(&pcidev->dev, handle);
+
+	len = pci_resource_len(pcidev, 0);
+	base = pci_resource_start(pcidev, 0);
+	pcr->remap_addr = ioremap_nocache(base, len);
+	if (!pcr->remap_addr) {
+		ret = -ENOMEM;
+		goto free_host;
+	}
+
+	pcr->rtsx_resv_buf = dma_alloc_coherent(&(pcidev->dev),
+			RTSX_RESV_BUF_LEN, &(pcr->rtsx_resv_buf_addr),
+			GFP_KERNEL);
+	if (pcr->rtsx_resv_buf == NULL) {
+		ret = -ENXIO;
+		goto unmap;
+	}
+	pcr->host_cmds_ptr = pcr->rtsx_resv_buf;
+	pcr->host_cmds_addr = pcr->rtsx_resv_buf_addr;
+	pcr->host_sg_tbl_ptr = pcr->rtsx_resv_buf + HOST_CMDS_BUF_LEN;
+	pcr->host_sg_tbl_addr = pcr->rtsx_resv_buf_addr + HOST_CMDS_BUF_LEN;
+
+	pcr->card_inserted = 0;
+	pcr->card_removed = 0;
+	INIT_DELAYED_WORK(&pcr->carddet_work, rtsx_pci_card_detect);
+	INIT_DELAYED_WORK(&pcr->idle_work, rtsx_pci_idle_work);
+
+	pcr->msi_en = msi_en;
+	if (pcr->msi_en) {
+		ret = pci_enable_msi(pcidev);
+		if (ret < 0)
+			pcr->msi_en = false;
+	}
+
+	ret = rtsx_pci_acquire_irq(pcr);
+	if (ret < 0)
+		goto free_dma;
+
+	pci_set_master(pcidev);
+	synchronize_irq(pcr->irq);
+
+	ret = rtsx_pci_init_chip(pcr);
+	if (ret < 0)
+		goto disable_irq;
+
+	for (i = 0; i < ARRAY_SIZE(rtsx_pcr_cells); i++) {
+		rtsx_pcr_cells[i].platform_data = handle;
+		rtsx_pcr_cells[i].pdata_size = sizeof(*handle);
+	}
+	ret = mfd_add_devices(&pcidev->dev, pcr->id, rtsx_pcr_cells,
+			ARRAY_SIZE(rtsx_pcr_cells), NULL, 0, NULL);
+	if (ret < 0)
+		goto disable_irq;
+
+	schedule_delayed_work(&pcr->idle_work, msecs_to_jiffies(200));
+
+	return 0;
+
+disable_irq:
+	free_irq(pcr->irq, (void *)pcr);
+free_dma:
+	dma_free_coherent(&(pcr->pci->dev), RTSX_RESV_BUF_LEN,
+			pcr->rtsx_resv_buf, pcr->rtsx_resv_buf_addr);
+unmap:
+	iounmap(pcr->remap_addr);
+free_host:
+	dev_set_drvdata(&pcidev->dev, NULL);
+free_handle:
+	kfree(handle);
+free_pcr:
+	kfree(pcr);
+release_pci:
+	pci_release_regions(pcidev);
+disable:
+	pci_disable_device(pcidev);
+
+	return ret;
+}
+
+static void __devexit rtsx_pci_remove(struct pci_dev *pcidev)
+{
+	struct pcr_handle *handle = pci_get_drvdata(pcidev);
+	struct rtsx_pcr *pcr = handle->pcr;
+
+	pcr->remove_pci = true;
+
+	cancel_delayed_work(&pcr->carddet_work);
+	cancel_delayed_work(&pcr->idle_work);
+
+	mfd_remove_devices(&pcidev->dev);
+
+	dma_free_coherent(&(pcr->pci->dev), RTSX_RESV_BUF_LEN,
+			pcr->rtsx_resv_buf, pcr->rtsx_resv_buf_addr);
+	free_irq(pcr->irq, (void *)pcr);
+	if (pcr->msi_en)
+		pci_disable_msi(pcr->pci);
+	iounmap(pcr->remap_addr);
+
+	dev_set_drvdata(&pcidev->dev, NULL);
+	pci_release_regions(pcidev);
+	pci_disable_device(pcidev);
+
+	spin_lock(&rtsx_pci_lock);
+	idr_remove(&rtsx_pci_idr, pcr->id);
+	spin_unlock(&rtsx_pci_lock);
+
+	kfree(pcr->slots);
+	kfree(pcr);
+	kfree(handle);
+
+	dev_dbg(&(pcidev->dev),
+		": Realtek PCI-E Card Reader at %s [%04x:%04x] has been removed\n",
+		pci_name(pcidev), (int)pcidev->vendor, (int)pcidev->device);
+}
+
+#ifdef CONFIG_PM
+
+static int rtsx_pci_suspend(struct pci_dev *pcidev, pm_message_t state)
+{
+	struct pcr_handle *handle;
+	struct rtsx_pcr *pcr;
+	int ret = 0;
+
+	dev_dbg(&(pcidev->dev), "--> %s\n", __func__);
+
+	handle = pci_get_drvdata(pcidev);
+	pcr = handle->pcr;
+
+	cancel_delayed_work(&pcr->carddet_work);
+	cancel_delayed_work(&pcr->idle_work);
+
+	mutex_lock(&pcr->pcr_mutex);
+
+	if (pcr->ops->turn_off_led)
+		pcr->ops->turn_off_led(pcr);
+
+	rtsx_pci_writel(pcr, RTSX_BIER, 0);
+	pcr->bier = 0;
+
+	rtsx_pci_write_register(pcr, PETXCFG, 0x08, 0x08);
+	rtsx_pci_write_register(pcr, HOST_SLEEP_STATE, 0x03, 0x02);
+
+	pci_save_state(pcidev);
+	pci_enable_wake(pcidev, pci_choose_state(pcidev, state), 0);
+	pci_disable_device(pcidev);
+	pci_set_power_state(pcidev, pci_choose_state(pcidev, state));
+
+	mutex_unlock(&pcr->pcr_mutex);
+	return ret;
+}
+
+static int rtsx_pci_resume(struct pci_dev *pcidev)
+{
+	struct pcr_handle *handle;
+	struct rtsx_pcr *pcr;
+	int ret = 0;
+
+	dev_dbg(&(pcidev->dev), "--> %s\n", __func__);
+
+	handle = pci_get_drvdata(pcidev);
+	pcr = handle->pcr;
+
+	mutex_lock(&pcr->pcr_mutex);
+
+	pci_set_power_state(pcidev, PCI_D0);
+	pci_restore_state(pcidev);
+	ret = pci_enable_device(pcidev);
+	if (ret)
+		goto out;
+	pci_set_master(pcidev);
+
+	ret = rtsx_pci_write_register(pcr, HOST_SLEEP_STATE, 0x03, 0x00);
+	if (ret)
+		goto out;
+
+	ret = rtsx_pci_init_hw(pcr);
+	if (ret)
+		goto out;
+
+	schedule_delayed_work(&pcr->idle_work, msecs_to_jiffies(200));
+
+out:
+	mutex_unlock(&pcr->pcr_mutex);
+	return ret;
+}
+
+#else /* CONFIG_PM */
+
+#define rtsx_pci_suspend NULL
+#define rtsx_pci_resume NULL
+
+#endif /* CONFIG_PM */
+
+static struct pci_driver rtsx_pci_driver = {
+	.name = DRV_NAME_RTSX_PCI,
+	.id_table = rtsx_pci_ids,
+	.probe = rtsx_pci_probe,
+	.remove = __devexit_p(rtsx_pci_remove),
+	.suspend = rtsx_pci_suspend,
+	.resume = rtsx_pci_resume,
+};
+module_pci_driver(rtsx_pci_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Wei WANG <wei_wang@realsil.com.cn>");
+MODULE_DESCRIPTION("Realtek PCI-E Card Reader Driver");
diff --git a/drivers/mfd/rtsx_pcr.h b/drivers/mfd/rtsx_pcr.h
new file mode 100644
index 000000000000..12462c1df1a9
--- /dev/null
+++ b/drivers/mfd/rtsx_pcr.h
@@ -0,0 +1,32 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#ifndef __RTSX_PCR_H
+#define __RTSX_PCR_H
+
+#include <linux/mfd/rtsx_pci.h>
+
+void rts5209_init_params(struct rtsx_pcr *pcr);
+void rts5229_init_params(struct rtsx_pcr *pcr);
+void rtl8411_init_params(struct rtsx_pcr *pcr);
+
+#endif
diff --git a/include/linux/mfd/rtsx_common.h b/include/linux/mfd/rtsx_common.h
new file mode 100644
index 000000000000..a8d393e3066b
--- /dev/null
+++ b/include/linux/mfd/rtsx_common.h
@@ -0,0 +1,48 @@
+/* Driver for Realtek driver-based card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#ifndef __RTSX_COMMON_H
+#define __RTSX_COMMON_H
+
+#define DRV_NAME_RTSX_PCI		"rtsx_pci"
+#define DRV_NAME_RTSX_PCI_SDMMC		"rtsx_pci_sdmmc"
+#define DRV_NAME_RTSX_PCI_MS		"rtsx_pci_ms"
+
+#define RTSX_REG_PAIR(addr, val)	(((u32)(addr) << 16) | (u8)(val))
+
+#define RTSX_SSC_DEPTH_4M		0x01
+#define RTSX_SSC_DEPTH_2M		0x02
+#define RTSX_SSC_DEPTH_1M		0x03
+#define RTSX_SSC_DEPTH_500K		0x04
+#define RTSX_SSC_DEPTH_250K		0x05
+
+#define RTSX_SD_CARD			0
+#define RTSX_MS_CARD			1
+
+struct platform_device;
+
+struct rtsx_slot {
+	struct platform_device	*p_dev;
+	void			(*card_event)(struct platform_device *p_dev);
+};
+
+#endif
diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
new file mode 100644
index 000000000000..060b721fcbfb
--- /dev/null
+++ b/include/linux/mfd/rtsx_pci.h
@@ -0,0 +1,794 @@
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ *   No. 450, Shenhu Road, Suzhou Industry Park, Suzhou, China
+ */
+
+#ifndef __RTSX_PCI_H
+#define __RTSX_PCI_H
+
+#include <linux/sched.h>
+#include <linux/pci.h>
+
+#include "rtsx_common.h"
+
+#define MAX_RW_REG_CNT			1024
+
+/* PCI Operation Register Address */
+#define RTSX_HCBAR			0x00
+#define RTSX_HCBCTLR			0x04
+#define RTSX_HDBAR			0x08
+#define RTSX_HDBCTLR			0x0C
+#define RTSX_HAIMR			0x10
+#define RTSX_BIPR			0x14
+#define RTSX_BIER			0x18
+
+/* Host command buffer control register */
+#define STOP_CMD			(0x01 << 28)
+
+/* Host data buffer control register */
+#define SDMA_MODE			0x00
+#define ADMA_MODE			(0x02 << 26)
+#define STOP_DMA			(0x01 << 28)
+#define TRIG_DMA			(0x01 << 31)
+
+/* Host access internal memory register */
+#define HAIMR_TRANS_START		(0x01 << 31)
+#define HAIMR_READ			0x00
+#define HAIMR_WRITE			(0x01 << 30)
+#define HAIMR_READ_START		(HAIMR_TRANS_START | HAIMR_READ)
+#define HAIMR_WRITE_START		(HAIMR_TRANS_START | HAIMR_WRITE)
+#define HAIMR_TRANS_END			(HAIMR_TRANS_START)
+
+/* Bus interrupt pending register */
+#define CMD_DONE_INT			(1 << 31)
+#define DATA_DONE_INT			(1 << 30)
+#define TRANS_OK_INT			(1 << 29)
+#define TRANS_FAIL_INT			(1 << 28)
+#define XD_INT				(1 << 27)
+#define MS_INT				(1 << 26)
+#define SD_INT				(1 << 25)
+#define GPIO0_INT			(1 << 24)
+#define OC_INT				(1 << 23)
+#define SD_WRITE_PROTECT		(1 << 19)
+#define XD_EXIST			(1 << 18)
+#define MS_EXIST			(1 << 17)
+#define SD_EXIST			(1 << 16)
+#define DELINK_INT			GPIO0_INT
+#define MS_OC_INT			(1 << 23)
+#define SD_OC_INT			(1 << 22)
+
+#define CARD_INT		(XD_INT | MS_INT | SD_INT)
+#define NEED_COMPLETE_INT	(DATA_DONE_INT | TRANS_OK_INT | TRANS_FAIL_INT)
+#define RTSX_INT		(CMD_DONE_INT | NEED_COMPLETE_INT | \
+					CARD_INT | GPIO0_INT | OC_INT)
+
+#define CARD_EXIST		(XD_EXIST | MS_EXIST | SD_EXIST)
+
+/* Bus interrupt enable register */
+#define CMD_DONE_INT_EN		(1 << 31)
+#define DATA_DONE_INT_EN	(1 << 30)
+#define TRANS_OK_INT_EN		(1 << 29)
+#define TRANS_FAIL_INT_EN	(1 << 28)
+#define XD_INT_EN		(1 << 27)
+#define MS_INT_EN		(1 << 26)
+#define SD_INT_EN		(1 << 25)
+#define GPIO0_INT_EN		(1 << 24)
+#define OC_INT_EN		(1 << 23)
+#define DELINK_INT_EN		GPIO0_INT_EN
+#define MS_OC_INT_EN		(1 << 23)
+#define SD_OC_INT_EN		(1 << 22)
+
+#define READ_REG_CMD		0
+#define WRITE_REG_CMD		1
+#define CHECK_REG_CMD		2
+
+/*
+ * macros for easy use
+ */
+#define rtsx_pci_writel(pcr, reg, value) \
+	iowrite32(value, (pcr)->remap_addr + reg)
+#define rtsx_pci_readl(pcr, reg) \
+	ioread32((pcr)->remap_addr + reg)
+#define rtsx_pci_writew(pcr, reg, value) \
+	iowrite16(value, (pcr)->remap_addr + reg)
+#define rtsx_pci_readw(pcr, reg) \
+	ioread16((pcr)->remap_addr + reg)
+#define rtsx_pci_writeb(pcr, reg, value) \
+	iowrite8(value, (pcr)->remap_addr + reg)
+#define rtsx_pci_readb(pcr, reg) \
+	ioread8((pcr)->remap_addr + reg)
+
+#define rtsx_pci_read_config_byte(pcr, where, val) \
+	pci_read_config_byte((pcr)->pci, where, val)
+
+#define rtsx_pci_write_config_byte(pcr, where, val) \
+	pci_write_config_byte((pcr)->pci, where, val)
+
+#define rtsx_pci_read_config_dword(pcr, where, val) \
+	pci_read_config_dword((pcr)->pci, where, val)
+
+#define rtsx_pci_write_config_dword(pcr, where, val) \
+	pci_write_config_dword((pcr)->pci, where, val)
+
+#define STATE_TRANS_NONE	0
+#define STATE_TRANS_CMD		1
+#define STATE_TRANS_BUF		2
+#define STATE_TRANS_SG		3
+
+#define TRANS_NOT_READY		0
+#define TRANS_RESULT_OK		1
+#define TRANS_RESULT_FAIL	2
+#define TRANS_NO_DEVICE		3
+
+#define RTSX_RESV_BUF_LEN	4096
+#define HOST_CMDS_BUF_LEN	1024
+#define HOST_SG_TBL_BUF_LEN	(RTSX_RESV_BUF_LEN - HOST_CMDS_BUF_LEN)
+#define HOST_SG_TBL_ITEMS	(HOST_SG_TBL_BUF_LEN / 8)
+#define MAX_SG_ITEM_LEN		0x80000
+
+#define HOST_TO_DEVICE		0
+#define DEVICE_TO_HOST		1
+
+#define MAX_PHASE		31
+#define RX_TUNING_CNT		3
+
+/* SG descriptor */
+#define SG_INT			0x04
+#define SG_END			0x02
+#define SG_VALID		0x01
+
+#define SG_NO_OP		0x00
+#define SG_TRANS_DATA		(0x02 << 4)
+#define SG_LINK_DESC		(0x03 << 4)
+
+/* SD bank voltage */
+#define SD_IO_3V3		0
+#define SD_IO_1V8		1
+
+
+/* Card Clock Enable Register */
+#define SD_CLK_EN			0x04
+#define MS_CLK_EN			0x08
+
+/* Card Select Register */
+#define SD_MOD_SEL			2
+#define MS_MOD_SEL			3
+
+/* Card Output Enable Register */
+#define SD_OUTPUT_EN			0x04
+#define MS_OUTPUT_EN			0x08
+
+/* CARD_SHARE_MODE */
+#define CARD_SHARE_MASK			0x0F
+#define CARD_SHARE_MULTI_LUN		0x00
+#define	CARD_SHARE_NORMAL		0x00
+#define	CARD_SHARE_48_SD		0x04
+#define	CARD_SHARE_48_MS		0x08
+/* CARD_SHARE_MODE for barossa */
+#define CARD_SHARE_BAROSSA_SD		0x01
+#define CARD_SHARE_BAROSSA_MS		0x02
+
+/* SD30_DRIVE_SEL */
+#define DRIVER_TYPE_A			0x05
+#define DRIVER_TYPE_B			0x03
+#define DRIVER_TYPE_C			0x02
+#define DRIVER_TYPE_D			0x01
+
+/* FPDCTL */
+#define SSC_POWER_DOWN			0x01
+#define SD_OC_POWER_DOWN		0x02
+#define ALL_POWER_DOWN			0x07
+#define OC_POWER_DOWN			0x06
+
+/* CLK_CTL */
+#define CHANGE_CLK			0x01
+
+/* LDO_CTL */
+#define BPP_LDO_POWB			0x03
+#define BPP_LDO_ON			0x00
+#define BPP_LDO_SUSPEND			0x02
+#define BPP_LDO_OFF			0x03
+
+/* CD_PAD_CTL */
+#define CD_DISABLE_MASK			0x07
+#define MS_CD_DISABLE			0x04
+#define SD_CD_DISABLE			0x02
+#define XD_CD_DISABLE			0x01
+#define CD_DISABLE			0x07
+#define CD_ENABLE			0x00
+#define MS_CD_EN_ONLY			0x03
+#define SD_CD_EN_ONLY			0x05
+#define XD_CD_EN_ONLY			0x06
+#define FORCE_CD_LOW_MASK		0x38
+#define FORCE_CD_XD_LOW			0x08
+#define FORCE_CD_SD_LOW			0x10
+#define FORCE_CD_MS_LOW			0x20
+#define CD_AUTO_DISABLE			0x40
+
+/* SD_STAT1 */
+#define	SD_CRC7_ERR			0x80
+#define	SD_CRC16_ERR			0x40
+#define	SD_CRC_WRITE_ERR		0x20
+#define	SD_CRC_WRITE_ERR_MASK		0x1C
+#define	GET_CRC_TIME_OUT		0x02
+#define	SD_TUNING_COMPARE_ERR		0x01
+
+/* SD_STAT2 */
+#define	SD_RSP_80CLK_TIMEOUT		0x01
+
+/* SD_BUS_STAT */
+#define	SD_CLK_TOGGLE_EN		0x80
+#define	SD_CLK_FORCE_STOP	        0x40
+#define	SD_DAT3_STATUS		        0x10
+#define	SD_DAT2_STATUS		        0x08
+#define	SD_DAT1_STATUS		        0x04
+#define	SD_DAT0_STATUS		        0x02
+#define	SD_CMD_STATUS			0x01
+
+/* SD_PAD_CTL */
+#define	SD_IO_USING_1V8		        0x80
+#define	SD_IO_USING_3V3		        0x7F
+#define	TYPE_A_DRIVING		        0x00
+#define	TYPE_B_DRIVING			0x01
+#define	TYPE_C_DRIVING			0x02
+#define	TYPE_D_DRIVING		        0x03
+
+/* SD_SAMPLE_POINT_CTL */
+#define	DDR_FIX_RX_DAT			0x00
+#define	DDR_VAR_RX_DAT			0x80
+#define	DDR_FIX_RX_DAT_EDGE		0x00
+#define	DDR_FIX_RX_DAT_14_DELAY		0x40
+#define	DDR_FIX_RX_CMD			0x00
+#define	DDR_VAR_RX_CMD			0x20
+#define	DDR_FIX_RX_CMD_POS_EDGE		0x00
+#define	DDR_FIX_RX_CMD_14_DELAY		0x10
+#define	SD20_RX_POS_EDGE		0x00
+#define	SD20_RX_14_DELAY		0x08
+#define SD20_RX_SEL_MASK		0x08
+
+/* SD_PUSH_POINT_CTL */
+#define	DDR_FIX_TX_CMD_DAT		0x00
+#define	DDR_VAR_TX_CMD_DAT		0x80
+#define	DDR_FIX_TX_DAT_14_TSU		0x00
+#define	DDR_FIX_TX_DAT_12_TSU		0x40
+#define	DDR_FIX_TX_CMD_NEG_EDGE		0x00
+#define	DDR_FIX_TX_CMD_14_AHEAD		0x20
+#define	SD20_TX_NEG_EDGE		0x00
+#define	SD20_TX_14_AHEAD		0x10
+#define SD20_TX_SEL_MASK		0x10
+#define	DDR_VAR_SDCLK_POL_SWAP		0x01
+
+/* SD_TRANSFER */
+#define	SD_TRANSFER_START		0x80
+#define	SD_TRANSFER_END			0x40
+#define SD_STAT_IDLE			0x20
+#define	SD_TRANSFER_ERR			0x10
+/* SD Transfer Mode definition */
+#define	SD_TM_NORMAL_WRITE		0x00
+#define	SD_TM_AUTO_WRITE_3		0x01
+#define	SD_TM_AUTO_WRITE_4		0x02
+#define	SD_TM_AUTO_READ_3		0x05
+#define	SD_TM_AUTO_READ_4		0x06
+#define	SD_TM_CMD_RSP			0x08
+#define	SD_TM_AUTO_WRITE_1		0x09
+#define	SD_TM_AUTO_WRITE_2		0x0A
+#define	SD_TM_NORMAL_READ		0x0C
+#define	SD_TM_AUTO_READ_1		0x0D
+#define	SD_TM_AUTO_READ_2		0x0E
+#define	SD_TM_AUTO_TUNING		0x0F
+
+/* SD_VPTX_CTL / SD_VPRX_CTL */
+#define PHASE_CHANGE			0x80
+#define PHASE_NOT_RESET			0x40
+
+/* SD_DCMPS_TX_CTL / SD_DCMPS_RX_CTL */
+#define DCMPS_CHANGE			0x80
+#define DCMPS_CHANGE_DONE		0x40
+#define DCMPS_ERROR			0x20
+#define DCMPS_CURRENT_PHASE		0x1F
+
+/* SD Configure 1 Register */
+#define SD_CLK_DIVIDE_0			0x00
+#define	SD_CLK_DIVIDE_256		0xC0
+#define	SD_CLK_DIVIDE_128		0x80
+#define	SD_BUS_WIDTH_1BIT		0x00
+#define	SD_BUS_WIDTH_4BIT		0x01
+#define	SD_BUS_WIDTH_8BIT		0x02
+#define	SD_ASYNC_FIFO_NOT_RST		0x10
+#define	SD_20_MODE			0x00
+#define	SD_DDR_MODE			0x04
+#define	SD_30_MODE			0x08
+
+#define SD_CLK_DIVIDE_MASK		0xC0
+
+/* SD_CMD_STATE */
+#define SD_CMD_IDLE			0x80
+
+/* SD_DATA_STATE */
+#define SD_DATA_IDLE			0x80
+
+/* DCM_DRP_CTL */
+#define DCM_RESET			0x08
+#define DCM_LOCKED			0x04
+#define DCM_208M			0x00
+#define DCM_TX			        0x01
+#define DCM_RX			        0x02
+
+/* DCM_DRP_TRIG */
+#define DRP_START			0x80
+#define DRP_DONE			0x40
+
+/* DCM_DRP_CFG */
+#define DRP_WRITE			0x80
+#define DRP_READ			0x00
+#define DCM_WRITE_ADDRESS_50		0x50
+#define DCM_WRITE_ADDRESS_51		0x51
+#define DCM_READ_ADDRESS_00		0x00
+#define DCM_READ_ADDRESS_51		0x51
+
+/* IRQSTAT0 */
+#define DMA_DONE_INT			0x80
+#define SUSPEND_INT			0x40
+#define LINK_RDY_INT			0x20
+#define LINK_DOWN_INT			0x10
+
+/* DMACTL */
+#define DMA_RST				0x80
+#define DMA_BUSY			0x04
+#define DMA_DIR_TO_CARD			0x00
+#define DMA_DIR_FROM_CARD		0x02
+#define DMA_EN				0x01
+#define DMA_128				(0 << 4)
+#define DMA_256				(1 << 4)
+#define DMA_512				(2 << 4)
+#define DMA_1024			(3 << 4)
+#define DMA_PACK_SIZE_MASK		0x30
+
+/* SSC_CTL1 */
+#define SSC_RSTB			0x80
+#define SSC_8X_EN			0x40
+#define SSC_FIX_FRAC			0x20
+#define SSC_SEL_1M			0x00
+#define SSC_SEL_2M			0x08
+#define SSC_SEL_4M			0x10
+#define SSC_SEL_8M			0x18
+
+/* SSC_CTL2 */
+#define SSC_DEPTH_MASK			0x07
+#define SSC_DEPTH_DISALBE		0x00
+#define SSC_DEPTH_4M			0x01
+#define SSC_DEPTH_2M			0x02
+#define SSC_DEPTH_1M			0x03
+#define SSC_DEPTH_500K			0x04
+#define SSC_DEPTH_250K			0x05
+
+/* System Clock Control Register */
+#define CLK_LOW_FREQ			0x01
+
+/* System Clock Divider Register */
+#define CLK_DIV_1			0x01
+#define CLK_DIV_2			0x02
+#define CLK_DIV_4			0x03
+#define CLK_DIV_8			0x04
+
+/* MS_CFG */
+#define	SAMPLE_TIME_RISING		0x00
+#define	SAMPLE_TIME_FALLING		0x80
+#define	PUSH_TIME_DEFAULT		0x00
+#define	PUSH_TIME_ODD			0x40
+#define	NO_EXTEND_TOGGLE		0x00
+#define	EXTEND_TOGGLE_CHK		0x20
+#define	MS_BUS_WIDTH_1			0x00
+#define	MS_BUS_WIDTH_4			0x10
+#define	MS_BUS_WIDTH_8			0x18
+#define	MS_2K_SECTOR_MODE		0x04
+#define	MS_512_SECTOR_MODE		0x00
+#define	MS_TOGGLE_TIMEOUT_EN		0x00
+#define	MS_TOGGLE_TIMEOUT_DISEN		0x01
+#define MS_NO_CHECK_INT			0x02
+
+/* MS_TRANS_CFG */
+#define	WAIT_INT			0x80
+#define	NO_WAIT_INT			0x00
+#define	NO_AUTO_READ_INT_REG		0x00
+#define	AUTO_READ_INT_REG		0x40
+#define	MS_CRC16_ERR			0x20
+#define	MS_RDY_TIMEOUT			0x10
+#define	MS_INT_CMDNK			0x08
+#define	MS_INT_BREQ			0x04
+#define	MS_INT_ERR			0x02
+#define	MS_INT_CED			0x01
+
+/* MS_TRANSFER */
+#define	MS_TRANSFER_START		0x80
+#define	MS_TRANSFER_END			0x40
+#define	MS_TRANSFER_ERR			0x20
+#define	MS_BS_STATE			0x10
+#define	MS_TM_READ_BYTES		0x00
+#define	MS_TM_NORMAL_READ		0x01
+#define	MS_TM_WRITE_BYTES		0x04
+#define	MS_TM_NORMAL_WRITE		0x05
+#define	MS_TM_AUTO_READ			0x08
+#define	MS_TM_AUTO_WRITE		0x0C
+
+/* SD Configure 2 Register */
+#define	SD_CALCULATE_CRC7		0x00
+#define	SD_NO_CALCULATE_CRC7		0x80
+#define	SD_CHECK_CRC16			0x00
+#define	SD_NO_CHECK_CRC16		0x40
+#define SD_NO_CHECK_WAIT_CRC_TO		0x20
+#define	SD_WAIT_BUSY_END		0x08
+#define	SD_NO_WAIT_BUSY_END		0x00
+#define	SD_CHECK_CRC7			0x00
+#define	SD_NO_CHECK_CRC7		0x04
+#define	SD_RSP_LEN_0			0x00
+#define	SD_RSP_LEN_6			0x01
+#define	SD_RSP_LEN_17			0x02
+/* SD/MMC Response Type Definition */
+#define	SD_RSP_TYPE_R0			0x04
+#define	SD_RSP_TYPE_R1			0x01
+#define	SD_RSP_TYPE_R1b			0x09
+#define	SD_RSP_TYPE_R2			0x02
+#define	SD_RSP_TYPE_R3			0x05
+#define	SD_RSP_TYPE_R4			0x05
+#define	SD_RSP_TYPE_R5			0x01
+#define	SD_RSP_TYPE_R6			0x01
+#define	SD_RSP_TYPE_R7			0x01
+
+/* SD_CONFIURE3 */
+#define	SD_RSP_80CLK_TIMEOUT_EN		0x01
+
+/* Card Transfer Reset Register */
+#define SPI_STOP			0x01
+#define XD_STOP				0x02
+#define SD_STOP				0x04
+#define MS_STOP				0x08
+#define SPI_CLR_ERR			0x10
+#define XD_CLR_ERR			0x20
+#define SD_CLR_ERR			0x40
+#define MS_CLR_ERR			0x80
+
+/* Card Data Source Register */
+#define PINGPONG_BUFFER			0x01
+#define RING_BUFFER			0x00
+
+/* Card Power Control Register */
+#define PMOS_STRG_MASK			0x10
+#define PMOS_STRG_800mA			0x10
+#define PMOS_STRG_400mA			0x00
+#define SD_POWER_OFF			0x03
+#define SD_PARTIAL_POWER_ON		0x01
+#define SD_POWER_ON			0x00
+#define SD_POWER_MASK			0x03
+#define MS_POWER_OFF			0x0C
+#define MS_PARTIAL_POWER_ON		0x04
+#define MS_POWER_ON			0x00
+#define MS_POWER_MASK			0x0C
+#define BPP_POWER_OFF			0x0F
+#define BPP_POWER_5_PERCENT_ON		0x0E
+#define BPP_POWER_10_PERCENT_ON		0x0C
+#define BPP_POWER_15_PERCENT_ON		0x08
+#define BPP_POWER_ON			0x00
+#define BPP_POWER_MASK			0x0F
+
+/* PWR_GATE_CTRL */
+#define PWR_GATE_EN			0x01
+#define LDO3318_PWR_MASK		0x06
+#define LDO_ON				0x00
+#define LDO_SUSPEND			0x04
+#define LDO_OFF				0x06
+
+/* CARD_CLK_SOURCE */
+#define CRC_FIX_CLK			(0x00 << 0)
+#define CRC_VAR_CLK0			(0x01 << 0)
+#define CRC_VAR_CLK1			(0x02 << 0)
+#define SD30_FIX_CLK			(0x00 << 2)
+#define SD30_VAR_CLK0			(0x01 << 2)
+#define SD30_VAR_CLK1			(0x02 << 2)
+#define SAMPLE_FIX_CLK			(0x00 << 4)
+#define SAMPLE_VAR_CLK0			(0x01 << 4)
+#define SAMPLE_VAR_CLK1			(0x02 << 4)
+
+#define MS_CFG				0xFD40
+#define MS_TPC				0xFD41
+#define MS_TRANS_CFG			0xFD42
+#define MS_TRANSFER			0xFD43
+#define MS_INT_REG			0xFD44
+#define MS_BYTE_CNT			0xFD45
+#define MS_SECTOR_CNT_L			0xFD46
+#define MS_SECTOR_CNT_H			0xFD47
+#define MS_DBUS_H			0xFD48
+
+#define SD_CFG1				0xFDA0
+#define SD_CFG2				0xFDA1
+#define SD_CFG3				0xFDA2
+#define SD_STAT1			0xFDA3
+#define SD_STAT2			0xFDA4
+#define SD_BUS_STAT			0xFDA5
+#define SD_PAD_CTL			0xFDA6
+#define SD_SAMPLE_POINT_CTL		0xFDA7
+#define SD_PUSH_POINT_CTL		0xFDA8
+#define SD_CMD0				0xFDA9
+#define SD_CMD1				0xFDAA
+#define SD_CMD2				0xFDAB
+#define SD_CMD3				0xFDAC
+#define SD_CMD4				0xFDAD
+#define SD_CMD5				0xFDAE
+#define SD_BYTE_CNT_L			0xFDAF
+#define SD_BYTE_CNT_H			0xFDB0
+#define SD_BLOCK_CNT_L			0xFDB1
+#define SD_BLOCK_CNT_H			0xFDB2
+#define SD_TRANSFER			0xFDB3
+#define SD_CMD_STATE			0xFDB5
+#define SD_DATA_STATE			0xFDB6
+
+#define SRCTL				0xFC13
+
+#define	DCM_DRP_CTL			0xFC23
+#define	DCM_DRP_TRIG			0xFC24
+#define	DCM_DRP_CFG			0xFC25
+#define	DCM_DRP_WR_DATA_L		0xFC26
+#define	DCM_DRP_WR_DATA_H		0xFC27
+#define	DCM_DRP_RD_DATA_L		0xFC28
+#define	DCM_DRP_RD_DATA_H		0xFC29
+#define SD_VPCLK0_CTL			0xFC2A
+#define SD_VPCLK1_CTL			0xFC2B
+#define SD_DCMPS0_CTL			0xFC2C
+#define SD_DCMPS1_CTL			0xFC2D
+#define SD_VPTX_CTL			SD_VPCLK0_CTL
+#define SD_VPRX_CTL			SD_VPCLK1_CTL
+#define SD_DCMPS_TX_CTL			SD_DCMPS0_CTL
+#define SD_DCMPS_RX_CTL			SD_DCMPS1_CTL
+#define CARD_CLK_SOURCE			0xFC2E
+
+#define CARD_PWR_CTL			0xFD50
+#define CARD_CLK_SWITCH			0xFD51
+#define CARD_SHARE_MODE			0xFD52
+#define CARD_DRIVE_SEL			0xFD53
+#define CARD_STOP			0xFD54
+#define CARD_OE				0xFD55
+#define CARD_AUTO_BLINK			0xFD56
+#define CARD_GPIO_DIR			0xFD57
+#define CARD_GPIO			0xFD58
+#define CARD_DATA_SOURCE		0xFD5B
+#define CARD_SELECT			0xFD5C
+#define SD30_DRIVE_SEL			0xFD5E
+#define CARD_CLK_EN			0xFD69
+#define SDIO_CTRL			0xFD6B
+#define CD_PAD_CTL			0xFD73
+
+#define FPDCTL				0xFC00
+#define PDINFO				0xFC01
+
+#define CLK_CTL				0xFC02
+#define CLK_DIV				0xFC03
+#define CLK_SEL				0xFC04
+
+#define SSC_DIV_N_0			0xFC0F
+#define SSC_DIV_N_1			0xFC10
+#define SSC_CTL1			0xFC11
+#define SSC_CTL2			0xFC12
+
+#define RCCTL				0xFC14
+
+#define FPGA_PULL_CTL			0xFC1D
+#define OLT_LED_CTL			0xFC1E
+#define GPIO_CTL			0xFC1F
+
+#define LDO_CTL				0xFC1E
+#define SYS_VER				0xFC32
+
+#define CARD_PULL_CTL1			0xFD60
+#define CARD_PULL_CTL2			0xFD61
+#define CARD_PULL_CTL3			0xFD62
+#define CARD_PULL_CTL4			0xFD63
+#define CARD_PULL_CTL5			0xFD64
+#define CARD_PULL_CTL6			0xFD65
+
+/* PCI Express Related Registers */
+#define IRQEN0				0xFE20
+#define IRQSTAT0			0xFE21
+#define IRQEN1				0xFE22
+#define IRQSTAT1			0xFE23
+#define TLPRIEN				0xFE24
+#define TLPRISTAT			0xFE25
+#define TLPTIEN				0xFE26
+#define TLPTISTAT			0xFE27
+#define DMATC0				0xFE28
+#define DMATC1				0xFE29
+#define DMATC2				0xFE2A
+#define DMATC3				0xFE2B
+#define DMACTL				0xFE2C
+#define BCTL				0xFE2D
+#define RBBC0				0xFE2E
+#define RBBC1				0xFE2F
+#define RBDAT				0xFE30
+#define RBCTL				0xFE34
+#define CFGADDR0			0xFE35
+#define CFGADDR1			0xFE36
+#define CFGDATA0			0xFE37
+#define CFGDATA1			0xFE38
+#define CFGDATA2			0xFE39
+#define CFGDATA3			0xFE3A
+#define CFGRWCTL			0xFE3B
+#define PHYRWCTL			0xFE3C
+#define PHYDATA0			0xFE3D
+#define PHYDATA1			0xFE3E
+#define PHYADDR				0xFE3F
+#define MSGRXDATA0			0xFE40
+#define MSGRXDATA1			0xFE41
+#define MSGRXDATA2			0xFE42
+#define MSGRXDATA3			0xFE43
+#define MSGTXDATA0			0xFE44
+#define MSGTXDATA1			0xFE45
+#define MSGTXDATA2			0xFE46
+#define MSGTXDATA3			0xFE47
+#define MSGTXCTL			0xFE48
+#define PETXCFG				0xFE49
+
+#define CDRESUMECTL			0xFE52
+#define WAKE_SEL_CTL			0xFE54
+#define PME_FORCE_CTL			0xFE56
+#define ASPM_FORCE_CTL			0xFE57
+#define PM_CLK_FORCE_CTL		0xFE58
+#define PERST_GLITCH_WIDTH		0xFE5C
+#define CHANGE_LINK_STATE		0xFE5B
+#define RESET_LOAD_REG			0xFE5E
+#define EFUSE_CONTENT			0xFE5F
+#define HOST_SLEEP_STATE		0xFE60
+#define SDIO_CFG			0xFE70
+
+#define NFTS_TX_CTRL			0xFE72
+
+#define PWR_GATE_CTRL			0xFE75
+#define PWD_SUSPEND_EN			0xFE76
+#define LDO_PWR_SEL			0xFE78
+
+#define DUMMY_REG_RESET_0		0xFE90
+
+/* Memory mapping */
+#define SRAM_BASE			0xE600
+#define RBUF_BASE			0xF400
+#define PPBUF_BASE1			0xF800
+#define PPBUF_BASE2			0xFA00
+#define IMAGE_FLAG_ADDR0		0xCE80
+#define IMAGE_FLAG_ADDR1		0xCE81
+
+#define rtsx_pci_init_cmd(pcr)		((pcr)->ci = 0)
+
+struct rtsx_pcr;
+
+struct pcr_handle {
+	struct rtsx_pcr			*pcr;
+};
+
+struct pcr_ops {
+	int		(*extra_init_hw)(struct rtsx_pcr *pcr);
+	int		(*optimize_phy)(struct rtsx_pcr *pcr);
+	int		(*turn_on_led)(struct rtsx_pcr *pcr);
+	int		(*turn_off_led)(struct rtsx_pcr *pcr);
+	int		(*enable_auto_blink)(struct rtsx_pcr *pcr);
+	int		(*disable_auto_blink)(struct rtsx_pcr *pcr);
+	int		(*card_power_on)(struct rtsx_pcr *pcr, int card);
+	int		(*card_power_off)(struct rtsx_pcr *pcr, int card);
+	unsigned int	(*cd_deglitch)(struct rtsx_pcr *pcr);
+};
+
+enum PDEV_STAT  {PDEV_STAT_IDLE, PDEV_STAT_RUN};
+
+struct rtsx_pcr {
+	struct pci_dev			*pci;
+	unsigned int			id;
+
+	/* pci resources */
+	unsigned long			addr;
+	void __iomem			*remap_addr;
+	int				irq;
+
+	/* host reserved buffer */
+	void				*rtsx_resv_buf;
+	dma_addr_t			rtsx_resv_buf_addr;
+
+	void				*host_cmds_ptr;
+	dma_addr_t			host_cmds_addr;
+	int				ci;
+
+	void				*host_sg_tbl_ptr;
+	dma_addr_t			host_sg_tbl_addr;
+	int				sgi;
+
+	u32				bier;
+	char				trans_result;
+
+	unsigned int			card_inserted;
+	unsigned int			card_removed;
+
+	struct delayed_work		carddet_work;
+	struct delayed_work		idle_work;
+
+	spinlock_t			lock;
+	struct mutex			pcr_mutex;
+	struct completion		*done;
+	struct completion		*finish_me;
+
+	unsigned int			cur_clock;
+	bool				ms_pmos;
+	bool				remove_pci;
+	bool				msi_en;
+
+#define EXTRA_CAPS_SD_SDR50		(1 << 0)
+#define EXTRA_CAPS_SD_SDR104		(1 << 1)
+#define EXTRA_CAPS_SD_DDR50		(1 << 2)
+#define EXTRA_CAPS_MMC_HSDDR		(1 << 3)
+#define EXTRA_CAPS_MMC_HS200		(1 << 4)
+#define EXTRA_CAPS_MMC_8BIT		(1 << 5)
+	u32				extra_caps;
+
+#define IC_VER_A			0
+#define IC_VER_B			1
+#define IC_VER_C			2
+#define IC_VER_D			3
+	u8				ic_version;
+
+	const u32			*sd_pull_ctl_enable_tbl;
+	const u32			*sd_pull_ctl_disable_tbl;
+	const u32			*ms_pull_ctl_enable_tbl;
+	const u32			*ms_pull_ctl_disable_tbl;
+
+	const struct pcr_ops		*ops;
+	enum PDEV_STAT			state;
+
+	int				num_slots;
+	struct rtsx_slot		*slots;
+};
+
+#define CHK_PCI_PID(pcr, pid)		((pcr)->pci->device == (pid))
+#define PCI_VID(pcr)			((pcr)->pci->vendor)
+#define PCI_PID(pcr)			((pcr)->pci->device)
+
+void rtsx_pci_start_run(struct rtsx_pcr *pcr);
+int rtsx_pci_write_register(struct rtsx_pcr *pcr, u16 addr, u8 mask, u8 data);
+int rtsx_pci_read_register(struct rtsx_pcr *pcr, u16 addr, u8 *data);
+int rtsx_pci_write_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 val);
+int rtsx_pci_read_phy_register(struct rtsx_pcr *pcr, u8 addr, u16 *val);
+void rtsx_pci_stop_cmd(struct rtsx_pcr *pcr);
+void rtsx_pci_add_cmd(struct rtsx_pcr *pcr,
+		u8 cmd_type, u16 reg_addr, u8 mask, u8 data);
+void rtsx_pci_send_cmd_no_wait(struct rtsx_pcr *pcr);
+int rtsx_pci_send_cmd(struct rtsx_pcr *pcr, int timeout);
+int rtsx_pci_transfer_data(struct rtsx_pcr *pcr, struct scatterlist *sglist,
+		int num_sg, bool read, int timeout);
+int rtsx_pci_read_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len);
+int rtsx_pci_write_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len);
+int rtsx_pci_card_pull_ctl_enable(struct rtsx_pcr *pcr, int card);
+int rtsx_pci_card_pull_ctl_disable(struct rtsx_pcr *pcr, int card);
+int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk);
+int rtsx_pci_card_power_on(struct rtsx_pcr *pcr, int card);
+int rtsx_pci_card_power_off(struct rtsx_pcr *pcr, int card);
+unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr);
+void rtsx_pci_complete_unfinished_transfer(struct rtsx_pcr *pcr);
+
+static inline u8 *rtsx_pci_get_cmd_data(struct rtsx_pcr *pcr)
+{
+	return (u8 *)(pcr->host_cmds_ptr);
+}
+
+#endif
-- 
cgit v1.2.3-55-g7522


From ac96511bb5cf92bad97ffc2249f75e45eb70301d Mon Sep 17 00:00:00 2001
From: Peter Chen
Date: Fri, 9 Nov 2012 09:44:44 +0800
Subject: usb: phy: change phy notify connect/disconnect API

The old parameter "port" is useless for phy notify, as one usb
phy is only for one usb port. New parameter "speed" stands for
the device's speed which is on the port, this "speed" parameter
is needed at some platforms which will do some phy operations
according to device's speed.

Signed-off-by: Peter Chen <peter.chen@freescale.com>
Tested-by: Mike Thompson <mpthompson@gmail.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c    |  4 ++--
 drivers/usb/otg/mxs-phy.c | 22 ++++++++++++++--------
 include/linux/usb/phy.h   | 15 +++++++++------
 3 files changed, 25 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 8391538d688b..a815fd2cc5e7 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -4039,7 +4039,7 @@ hub_port_init (struct usb_hub *hub, struct usb_device *udev, int port1,
 		goto fail;
 
 	if (hcd->phy && !hdev->parent)
-		usb_phy_notify_connect(hcd->phy, port1);
+		usb_phy_notify_connect(hcd->phy, udev->speed);
 
 	/*
 	 * Some superspeed devices have finished the link training process
@@ -4238,7 +4238,7 @@ static void hub_port_connect_change(struct usb_hub *hub, int port1,
 	if (udev) {
 		if (hcd->phy && !hdev->parent &&
 				!(portstatus & USB_PORT_STAT_CONNECTION))
-			usb_phy_notify_disconnect(hcd->phy, port1);
+			usb_phy_notify_disconnect(hcd->phy, udev->speed);
 		usb_disconnect(&hub->ports[port1 - 1]->child);
 	}
 	clear_bit(port1, hub->change_bits);
diff --git a/drivers/usb/otg/mxs-phy.c b/drivers/usb/otg/mxs-phy.c
index 5b09f3339ded..9a3caeecc508 100644
--- a/drivers/usb/otg/mxs-phy.c
+++ b/drivers/usb/otg/mxs-phy.c
@@ -76,22 +76,28 @@ static void mxs_phy_shutdown(struct usb_phy *phy)
 	clk_disable_unprepare(mxs_phy->clk);
 }
 
-static int mxs_phy_on_connect(struct usb_phy *phy, int port)
+static int mxs_phy_on_connect(struct usb_phy *phy,
+		enum usb_device_speed speed)
 {
-	dev_dbg(phy->dev, "Connect on port %d\n", port);
+	dev_dbg(phy->dev, "%s speed device has connected\n",
+		(speed == USB_SPEED_HIGH) ? "high" : "non-high");
 
-	writel_relaxed(BM_USBPHY_CTRL_ENHOSTDISCONDETECT,
-			phy->io_priv + HW_USBPHY_CTRL_SET);
+	if (speed == USB_SPEED_HIGH)
+		writel_relaxed(BM_USBPHY_CTRL_ENHOSTDISCONDETECT,
+				phy->io_priv + HW_USBPHY_CTRL_SET);
 
 	return 0;
 }
 
-static int mxs_phy_on_disconnect(struct usb_phy *phy, int port)
+static int mxs_phy_on_disconnect(struct usb_phy *phy,
+		enum usb_device_speed speed)
 {
-	dev_dbg(phy->dev, "Disconnect on port %d\n", port);
+	dev_dbg(phy->dev, "%s speed device has disconnected\n",
+		(speed == USB_SPEED_HIGH) ? "high" : "non-high");
 
-	writel_relaxed(BM_USBPHY_CTRL_ENHOSTDISCONDETECT,
-			phy->io_priv + HW_USBPHY_CTRL_CLR);
+	if (speed == USB_SPEED_HIGH)
+		writel_relaxed(BM_USBPHY_CTRL_ENHOSTDISCONDETECT,
+				phy->io_priv + HW_USBPHY_CTRL_CLR);
 
 	return 0;
 }
diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h
index 06b5bae35b29..a29ae1eb9346 100644
--- a/include/linux/usb/phy.h
+++ b/include/linux/usb/phy.h
@@ -10,6 +10,7 @@
 #define __LINUX_USB_PHY_H
 
 #include <linux/notifier.h>
+#include <linux/usb.h>
 
 enum usb_phy_events {
 	USB_EVENT_NONE,         /* no events or cable disconnected */
@@ -99,8 +100,10 @@ struct usb_phy {
 				int suspend);
 
 	/* notify phy connect status change */
-	int	(*notify_connect)(struct usb_phy *x, int port);
-	int	(*notify_disconnect)(struct usb_phy *x, int port);
+	int	(*notify_connect)(struct usb_phy *x,
+			enum usb_device_speed speed);
+	int	(*notify_disconnect)(struct usb_phy *x,
+			enum usb_device_speed speed);
 };
 
 
@@ -189,19 +192,19 @@ usb_phy_set_suspend(struct usb_phy *x, int suspend)
 }
 
 static inline int
-usb_phy_notify_connect(struct usb_phy *x, int port)
+usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed)
 {
 	if (x->notify_connect)
-		return x->notify_connect(x, port);
+		return x->notify_connect(x, speed);
 	else
 		return 0;
 }
 
 static inline int
-usb_phy_notify_disconnect(struct usb_phy *x, int port)
+usb_phy_notify_disconnect(struct usb_phy *x, enum usb_device_speed speed)
 {
 	if (x->notify_disconnect)
-		return x->notify_disconnect(x, port);
+		return x->notify_disconnect(x, speed);
 	else
 		return 0;
 }
-- 
cgit v1.2.3-55-g7522


From bb74ac23b10820d8722c3e1f4add9ef59e703f63 Mon Sep 17 00:00:00 2001
From: Yasuaki Ishimatsu
Date: Fri, 16 Nov 2012 02:56:59 +0100
Subject: ACPI: create _SUN sysfs file

_SUN method provides the slot unique-ID in the ACPI namespace. And The value
is written in Advanced Configuration and Power Interface Specification as
follows:

"The _SUN value is required to be unique among the slots ofthe same type.
It is also recommended that this number match the slot number printed on
the physical slot whenever possible."

So if we can know the value, we can identify the physical position of the
slot in the system.

The patch creates "sun" file in sysfs for identifying physical position
of the slot.

Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Reviewed-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/ABI/testing/sysfs-devices-sun | 14 ++++++++++++++
 drivers/acpi/scan.c                         | 24 ++++++++++++++++++++++++
 include/acpi/acpi_bus.h                     |  1 +
 3 files changed, 39 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-devices-sun

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-devices-sun b/Documentation/ABI/testing/sysfs-devices-sun
new file mode 100644
index 000000000000..86be9848a77e
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-sun
@@ -0,0 +1,14 @@
+Whatt:		/sys/devices/.../sun
+Date:		October 2012
+Contact:	Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
+Description:
+		The file contains a Slot-unique ID which provided by the _SUN
+		method in the ACPI namespace. The value is written in Advanced
+		Configuration and Power Interface Specification as follows:
+
+		"The _SUN value is required to be unique among the slots of
+		the same type. It is also recommended that this number match
+		the slot number printed on the physical slot whenever possible."
+
+		So reading the sysfs file, we can identify a physical position
+		of the slot in the system.
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 9d43532d69b1..d0b38ab47ab5 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -283,11 +283,21 @@ static ssize_t description_show(struct device *dev,
 }
 static DEVICE_ATTR(description, 0444, description_show, NULL);
 
+static ssize_t
+acpi_device_sun_show(struct device *dev, struct device_attribute *attr,
+		     char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+
+	return sprintf(buf, "%lu\n", acpi_dev->pnp.sun);
+}
+static DEVICE_ATTR(sun, 0444, acpi_device_sun_show, NULL);
+
 static int acpi_device_setup_files(struct acpi_device *dev)
 {
 	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
 	acpi_status status;
 	acpi_handle temp;
+	unsigned long long sun;
 	int result = 0;
 
 	/*
@@ -329,6 +339,16 @@ static int acpi_device_setup_files(struct acpi_device *dev)
 	if (dev->pnp.unique_id)
 		result = device_create_file(&dev->dev, &dev_attr_uid);
 
+	status = acpi_evaluate_integer(dev->handle, "_SUN", NULL, &sun);
+	if (ACPI_SUCCESS(status)) {
+		dev->pnp.sun = (unsigned long)sun;
+		result = device_create_file(&dev->dev, &dev_attr_sun);
+		if (result)
+			goto end;
+	} else {
+		dev->pnp.sun = (unsigned long)-1;
+	}
+
         /*
          * If device has _EJ0, 'eject' file is created that is used to trigger
          * hot-removal function from userland.
@@ -360,6 +380,10 @@ static void acpi_device_remove_files(struct acpi_device *dev)
 	if (ACPI_SUCCESS(status))
 		device_remove_file(&dev->dev, &dev_attr_eject);
 
+	status = acpi_get_handle(dev->handle, "_SUN", &temp);
+	if (ACPI_SUCCESS(status))
+		device_remove_file(&dev->dev, &dev_attr_sun);
+
 	if (dev->pnp.unique_id)
 		device_remove_file(&dev->dev, &dev_attr_uid);
 	if (dev->flags.bus_address)
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index e8b2877aea33..6f385e5909db 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -179,6 +179,7 @@ struct acpi_device_pnp {
 	acpi_device_name device_name;	/* Driver-determined */
 	acpi_device_class device_class;	/*        "          */
 	union acpi_object *str_obj;	/* unicode string for _STR method */
+	unsigned long sun;		/* _SUN */
 };
 
 #define acpi_device_bid(d)	((d)->pnp.bus_id)
-- 
cgit v1.2.3-55-g7522


From 130cd273d4a46a3011b1cc739f5d2af78779d666 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Mon, 5 Nov 2012 05:28:18 +0000
Subject: ipv6: export IP6_RT_PRIO_* to userland

The kernel uses some default metric when routes are managed. For example, a
static route added with a metric set to 0 is inserted in the kernel with
metric 1024 (IP6_RT_PRIO_USER).
It is useful for routing daemons to know these values, to be able to set routes
without interfering with what the kernel does.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h         | 3 ---
 include/uapi/linux/ipv6_route.h | 3 +++
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 5fa2af00634a..27d83183e615 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -1,9 +1,6 @@
 #ifndef _NET_IP6_ROUTE_H
 #define _NET_IP6_ROUTE_H
 
-#define IP6_RT_PRIO_USER	1024
-#define IP6_RT_PRIO_ADDRCONF	256
-
 struct route_info {
 	__u8			type;
 	__u8			length;
diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h
index 0459664c2636..2be7bd174751 100644
--- a/include/uapi/linux/ipv6_route.h
+++ b/include/uapi/linux/ipv6_route.h
@@ -55,4 +55,7 @@ struct in6_rtmsg {
 #define RTMSG_NEWROUTE		0x21
 #define RTMSG_DELROUTE		0x22
 
+#define IP6_RT_PRIO_USER	1024
+#define IP6_RT_PRIO_ADDRCONF	256
+
 #endif /* _UAPI_LINUX_IPV6_ROUTE_H */
-- 
cgit v1.2.3-55-g7522


From ebd5ac165f2aaefb767c53112c2010b0ff3df688 Mon Sep 17 00:00:00 2001
From: Shinya Kuribayashi
Date: Wed, 24 Oct 2012 19:58:10 +0900
Subject: i2c: i2c-sh_mobile: support I2C hardware block with a faster
 operating clock

On newer SH-/R-Mobile SoCs, a clock supply to the I2C hardware block,
which is used to generate the SCL clock output, is getting faster than
before, while on the other hand, the SCL clock control registers, ICCH
and ICCL, stay unchanged in 9-bit-wide (8+1).

On such silicons, the internal SCL clock counter gets incremented every
2 clocks of the operating clock.

This patch makes it configurable through platform data.

Signed-off-by: Shinya Kuribayashi <shinya.kuribayashi.px@renesas.com>
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
---
 drivers/i2c/busses/i2c-sh_mobile.c | 5 +++++
 include/linux/i2c/i2c-sh_mobile.h  | 1 +
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c
index 4dc0cc3611c2..4c283583bea0 100644
--- a/drivers/i2c/busses/i2c-sh_mobile.c
+++ b/drivers/i2c/busses/i2c-sh_mobile.c
@@ -120,6 +120,7 @@ struct sh_mobile_i2c_data {
 	void __iomem *reg;
 	struct i2c_adapter adap;
 	unsigned long bus_speed;
+	unsigned int clks_per_count;
 	struct clk *clk;
 	u_int8_t icic;
 	u_int8_t flags;
@@ -231,6 +232,7 @@ static void sh_mobile_i2c_init(struct sh_mobile_i2c_data *pd)
 	/* Get clock rate after clock is enabled */
 	clk_enable(pd->clk);
 	i2c_clk_khz = clk_get_rate(pd->clk) / 1000;
+	i2c_clk_khz /= pd->clks_per_count;
 
 	if (pd->bus_speed == STANDARD_MODE) {
 		tLOW	= 47;	/* tLOW = 4.7 us */
@@ -658,6 +660,9 @@ static int sh_mobile_i2c_probe(struct platform_device *dev)
 	pd->bus_speed = STANDARD_MODE;
 	if (pdata && pdata->bus_speed)
 		pd->bus_speed = pdata->bus_speed;
+	pd->clks_per_count = 1;
+	if (pdata && pdata->clks_per_count)
+		pd->clks_per_count = pdata->clks_per_count;
 
 	/* The IIC blocks on SH-Mobile ARM processors
 	 * come with two new bits in ICIC.
diff --git a/include/linux/i2c/i2c-sh_mobile.h b/include/linux/i2c/i2c-sh_mobile.h
index beda7081aead..06e3089795fb 100644
--- a/include/linux/i2c/i2c-sh_mobile.h
+++ b/include/linux/i2c/i2c-sh_mobile.h
@@ -5,6 +5,7 @@
 
 struct i2c_sh_mobile_platform_data {
 	unsigned long bus_speed;
+	unsigned int clks_per_count;
 };
 
 #endif /* __I2C_SH_MOBILE_H__ */
-- 
cgit v1.2.3-55-g7522


From d611d41b46c96195b9a168a21992782458826e07 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann
Date: Tue, 6 Nov 2012 22:55:27 +0100
Subject: mtd: diskonchip: use inline functions for DocRead/DocWrite

The diskonchip drivers traditionally use home-grown macros for
doing MMIO accesses, which cause a lot of warnings, at least
on ARM machines:

drivers/mtd/devices/doc2000.c: In function 'doc_write':
drivers/mtd/devices/doc2000.c:854:5: warning: value computed is not used [-Wunused-value]
drivers/mtd/devices/doc2000.c: In function 'doc_erase':
drivers/mtd/devices/doc2000.c:1123:5: warning: value computed is not used [-Wunused-value
drivers/mtd/nand/diskonchip.c: In function 'doc2000_read_byte':
drivers/mtd/nand/diskonchip.c:318:3: warning: value computed is not used [-Wunused-value]

A nicer solution is to use the architecture-defined I/O accessors.
Here, we use the __raw_readl/__raw_writel style, instead of the
proper readl/writel ones, in order to preserve the odd semantics
of the existing macros that have their own barrier implementation
and no byte swap. It would be nice to fix this properly and use
the correct accessors as well as make the word size independent
from the architecture, but I guess the hardware is obsolete
enough that we should better not mess the driver an more than
necessary.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 include/linux/mtd/doc2000.h | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/mtd/doc2000.h b/include/linux/mtd/doc2000.h
index 0f6fea73a1f6..407d1e556c39 100644
--- a/include/linux/mtd/doc2000.h
+++ b/include/linux/mtd/doc2000.h
@@ -92,12 +92,26 @@
  * Others use readb/writeb
  */
 #if defined(__arm__)
-#define ReadDOC_(adr, reg)      ((unsigned char)(*(volatile __u32 *)(((unsigned long)adr)+((reg)<<2))))
-#define WriteDOC_(d, adr, reg)  do{ *(volatile __u32 *)(((unsigned long)adr)+((reg)<<2)) = (__u32)d; wmb();} while(0)
+static inline u8 ReadDOC_(u32 __iomem *addr, unsigned long reg)
+{
+	return __raw_readl(addr + reg);
+}
+static inline void WriteDOC_(u8 data, u32 __iomem *addr, unsigned long reg)
+{
+	__raw_writel(data, addr + reg);
+	wmb();
+}
 #define DOC_IOREMAP_LEN 0x8000
 #elif defined(__ppc__)
-#define ReadDOC_(adr, reg)      ((unsigned char)(*(volatile __u16 *)(((unsigned long)adr)+((reg)<<1))))
-#define WriteDOC_(d, adr, reg)  do{ *(volatile __u16 *)(((unsigned long)adr)+((reg)<<1)) = (__u16)d; wmb();} while(0)
+static inline u8 ReadDOC_(u16 __iomem *addr, unsigned long reg)
+{
+	return __raw_readw(addr + reg);
+}
+static inline void WriteDOC_(u8 data, u16 __iomem *addr, unsigned long reg)
+{
+	__raw_writew(data, addr + reg);
+	wmb();
+}
 #define DOC_IOREMAP_LEN 0x4000
 #else
 #define ReadDOC_(adr, reg)      readb((void __iomem *)(adr) + (reg))
-- 
cgit v1.2.3-55-g7522


From 5d27aa5af04f58f3020de1c224dcf8a62151fd58 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann
Date: Tue, 6 Nov 2012 22:55:28 +0100
Subject: mtd: uninitialized variable warning in map.h

The map_word_load() function initializes exactly
as many words in the buffer as required, but gcc
cannot figure this out and gives a misleading
warning. Marking the local variable as
uninitialized_var shuts up that warning.

Without this patch, building acs5k_defconfig results in:

drivers/mtd/chips/cfi_cmdset_0002.c: In function 'cfi_amdstd_panic_write':
include/linux/mtd/map.h:331:11: warning: 'r.x[0]' may be used uninitialized in this function [-Wuninitialized]
drivers/mtd/chips/cfi_cmdset_0002.c: In function 'cfi_amdstd_write_words':
include/linux/mtd/map.h:331:11: warning: 'r.x[0]' may be used uninitialized in this function [-Wuninitialized]
drivers/mtd/chips/cfi_cmdset_0001.c: In function 'cfi_intelext_write_words':
include/linux/mtd/map.h:331:11: warning: 'r.x[0]' may be used uninitialized in this function [-Wuninitialized]

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 include/linux/mtd/map.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 56c7936e0c65..f6eb4332ac92 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -391,7 +391,7 @@ static inline map_word map_word_ff(struct map_info *map)
 
 static inline map_word inline_map_read(struct map_info *map, unsigned long ofs)
 {
-	map_word r;
+	map_word uninitialized_var(r);
 
 	if (map_bankwidth_is_1(map))
 		r.x[0] = __raw_readb(map->virt + ofs);
-- 
cgit v1.2.3-55-g7522


From 6920b5a791bbb54810159fbf6acf2c6ae14cdd22 Mon Sep 17 00:00:00 2001
From: Russell King
Date: Fri, 21 Sep 2012 10:18:58 +0100
Subject: ARM: move serial_sa1100.h header file to linux/platform_data

This is really driver platform data, so move it to the appropriate
directory.

Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/mach/serial_sa1100.h   | 31 ---------------------------
 arch/arm/mach-sa1100/assabet.c              |  2 +-
 arch/arm/mach-sa1100/badge4.c               |  2 +-
 arch/arm/mach-sa1100/cerf.c                 |  2 +-
 arch/arm/mach-sa1100/collie.c               |  2 +-
 arch/arm/mach-sa1100/h3xxx.c                |  2 +-
 arch/arm/mach-sa1100/hackkit.c              |  2 +-
 arch/arm/mach-sa1100/jornada720.c           |  2 +-
 arch/arm/mach-sa1100/lart.c                 |  2 +-
 arch/arm/mach-sa1100/nanoengine.c           |  2 +-
 arch/arm/mach-sa1100/neponset.c             |  2 +-
 arch/arm/mach-sa1100/pleb.c                 |  2 +-
 arch/arm/mach-sa1100/shannon.c              |  2 +-
 arch/arm/mach-sa1100/simpad.c               |  2 +-
 drivers/tty/serial/sa1100.c                 |  2 +-
 include/linux/platform_data/sa11x0-serial.h | 33 +++++++++++++++++++++++++++++
 16 files changed, 47 insertions(+), 45 deletions(-)
 delete mode 100644 arch/arm/include/asm/mach/serial_sa1100.h
 create mode 100644 include/linux/platform_data/sa11x0-serial.h

(limited to 'include')

diff --git a/arch/arm/include/asm/mach/serial_sa1100.h b/arch/arm/include/asm/mach/serial_sa1100.h
deleted file mode 100644
index d09064bf95a0..000000000000
--- a/arch/arm/include/asm/mach/serial_sa1100.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- *  arch/arm/include/asm/mach/serial_sa1100.h
- *
- *  Author: Nicolas Pitre
- *
- * Moved and changed lots, Russell King
- *
- * Low level machine dependent UART functions.
- */
-
-struct uart_port;
-struct uart_info;
-
-/*
- * This is a temporary structure for registering these
- * functions; it is intended to be discarded after boot.
- */
-struct sa1100_port_fns {
-	void	(*set_mctrl)(struct uart_port *, u_int);
-	u_int	(*get_mctrl)(struct uart_port *);
-	void	(*pm)(struct uart_port *, u_int, u_int);
-	int	(*set_wake)(struct uart_port *, u_int);
-};
-
-#ifdef CONFIG_SERIAL_SA1100
-void sa1100_register_uart_fns(struct sa1100_port_fns *fns);
-void sa1100_register_uart(int idx, int port);
-#else
-#define sa1100_register_uart_fns(fns) do { } while (0)
-#define sa1100_register_uart(idx,port) do { } while (0)
-#endif
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index 6a7ad3c2a3fc..9a23739f7026 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/serial_core.h>
 #include <linux/mfd/ucb1x00.h>
 #include <linux/mtd/mtd.h>
@@ -37,7 +38,6 @@
 #include <asm/mach/flash.h>
 #include <asm/mach/irda.h>
 #include <asm/mach/map.h>
-#include <asm/mach/serial_sa1100.h>
 #include <mach/assabet.h>
 #include <linux/platform_data/mfd-mcp-sa11x0.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-sa1100/badge4.c b/arch/arm/mach-sa1100/badge4.c
index 038df4894b0f..b2dadf3ea3df 100644
--- a/arch/arm/mach-sa1100/badge4.c
+++ b/arch/arm/mach-sa1100/badge4.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/tty.h>
@@ -34,7 +35,6 @@
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
 #include <asm/hardware/sa1111.h>
-#include <asm/mach/serial_sa1100.h>
 
 #include <mach/badge4.h>
 
diff --git a/arch/arm/mach-sa1100/cerf.c b/arch/arm/mach-sa1100/cerf.c
index ad0eb08ea077..304bca4a07c0 100644
--- a/arch/arm/mach-sa1100/cerf.c
+++ b/arch/arm/mach-sa1100/cerf.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/tty.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/platform_device.h>
 #include <linux/irq.h>
 #include <linux/mtd/mtd.h>
@@ -27,7 +28,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
-#include <asm/mach/serial_sa1100.h>
 
 #include <mach/cerf.h>
 #include <linux/platform_data/mfd-mcp-sa11x0.h>
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index 170cb6107f68..45f424f5fca6 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/tty.h>
 #include <linux/delay.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/ucb1x00.h>
 #include <linux/mtd/mtd.h>
@@ -40,7 +41,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
-#include <asm/mach/serial_sa1100.h>
 
 #include <asm/hardware/scoop.h>
 #include <asm/mach/sharpsl_param.h>
diff --git a/arch/arm/mach-sa1100/h3xxx.c b/arch/arm/mach-sa1100/h3xxx.c
index 63150e1ffe9e..f17e7382242a 100644
--- a/arch/arm/mach-sa1100/h3xxx.c
+++ b/arch/arm/mach-sa1100/h3xxx.c
@@ -17,12 +17,12 @@
 #include <linux/mfd/htc-egpio.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/platform_device.h>
 #include <linux/serial_core.h>
 
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
-#include <asm/mach/serial_sa1100.h>
 
 #include <mach/h3xxx.h>
 
diff --git a/arch/arm/mach-sa1100/hackkit.c b/arch/arm/mach-sa1100/hackkit.c
index fc106aab7c7e..d005939c41fc 100644
--- a/arch/arm/mach-sa1100/hackkit.c
+++ b/arch/arm/mach-sa1100/hackkit.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/cpufreq.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/serial_core.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
@@ -35,7 +36,6 @@
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
 #include <asm/mach/irq.h>
-#include <asm/mach/serial_sa1100.h>
 
 #include <mach/hardware.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-sa1100/jornada720.c b/arch/arm/mach-sa1100/jornada720.c
index e3084f47027d..35cfc428b4d4 100644
--- a/arch/arm/mach-sa1100/jornada720.c
+++ b/arch/arm/mach-sa1100/jornada720.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/tty.h>
 #include <linux/delay.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/platform_device.h>
 #include <linux/ioport.h>
 #include <linux/mtd/mtd.h>
@@ -30,7 +31,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
-#include <asm/mach/serial_sa1100.h>
 
 #include <mach/hardware.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-sa1100/lart.c b/arch/arm/mach-sa1100/lart.c
index 3048b17e84c5..f69f78fc3ddd 100644
--- a/arch/arm/mach-sa1100/lart.c
+++ b/arch/arm/mach-sa1100/lart.c
@@ -4,6 +4,7 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/tty.h>
 #include <linux/gpio.h>
 #include <linux/leds.h>
@@ -18,7 +19,6 @@
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
-#include <asm/mach/serial_sa1100.h>
 #include <linux/platform_data/mfd-mcp-sa11x0.h>
 #include <mach/irqs.h>
 
diff --git a/arch/arm/mach-sa1100/nanoengine.c b/arch/arm/mach-sa1100/nanoengine.c
index 41f69d97066f..102e08f7b109 100644
--- a/arch/arm/mach-sa1100/nanoengine.c
+++ b/arch/arm/mach-sa1100/nanoengine.c
@@ -13,6 +13,7 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/root_dev.h>
@@ -24,7 +25,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
-#include <asm/mach/serial_sa1100.h>
 
 #include <mach/hardware.h>
 #include <mach/nanoengine.h>
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index 266db873a4e4..88be0474f3d7 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -7,6 +7,7 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <linux/serial_core.h>
@@ -14,7 +15,6 @@
 
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
-#include <asm/mach/serial_sa1100.h>
 #include <asm/hardware/sa1111.h>
 #include <asm/sizes.h>
 
diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c
index 37fe0a0a5369..c51bb63f90fb 100644
--- a/arch/arm/mach-sa1100/pleb.c
+++ b/arch/arm/mach-sa1100/pleb.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/tty.h>
 #include <linux/ioport.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/platform_device.h>
 #include <linux/irq.h>
 #include <linux/io.h>
@@ -18,7 +19,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/flash.h>
-#include <asm/mach/serial_sa1100.h>
 #include <mach/irqs.h>
 
 #include "generic.h"
diff --git a/arch/arm/mach-sa1100/shannon.c b/arch/arm/mach-sa1100/shannon.c
index ff6b7b35bca9..6460d25fbb88 100644
--- a/arch/arm/mach-sa1100/shannon.c
+++ b/arch/arm/mach-sa1100/shannon.c
@@ -5,6 +5,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/tty.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
@@ -18,7 +19,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
-#include <asm/mach/serial_sa1100.h>
 #include <linux/platform_data/mfd-mcp-sa11x0.h>
 #include <mach/shannon.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c
index 71790e581d93..6d65f65fcb23 100644
--- a/arch/arm/mach-sa1100/simpad.c
+++ b/arch/arm/mach-sa1100/simpad.c
@@ -9,6 +9,7 @@
 #include <linux/proc_fs.h>
 #include <linux/string.h>
 #include <linux/pm.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/ucb1x00.h>
 #include <linux/mtd/mtd.h>
@@ -23,7 +24,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
-#include <asm/mach/serial_sa1100.h>
 #include <linux/platform_data/mfd-mcp-sa11x0.h>
 #include <mach/simpad.h>
 #include <mach/irqs.h>
diff --git a/drivers/tty/serial/sa1100.c b/drivers/tty/serial/sa1100.c
index 2ca5959ec3fa..ecc1e16be623 100644
--- a/drivers/tty/serial/sa1100.c
+++ b/drivers/tty/serial/sa1100.c
@@ -29,6 +29,7 @@
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/sysrq.h>
+#include <linux/platform_data/sa11x0-serial.h>
 #include <linux/platform_device.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
@@ -39,7 +40,6 @@
 #include <asm/irq.h>
 #include <mach/hardware.h>
 #include <mach/irqs.h>
-#include <asm/mach/serial_sa1100.h>
 
 /* We've been assigned a range on the "Low-density serial ports" major */
 #define SERIAL_SA1100_MAJOR	204
diff --git a/include/linux/platform_data/sa11x0-serial.h b/include/linux/platform_data/sa11x0-serial.h
new file mode 100644
index 000000000000..4504d5d592f0
--- /dev/null
+++ b/include/linux/platform_data/sa11x0-serial.h
@@ -0,0 +1,33 @@
+/*
+ *  Author: Nicolas Pitre
+ *
+ * Moved and changed lots, Russell King
+ *
+ * Low level machine dependent UART functions.
+ */
+#ifndef SA11X0_SERIAL_H
+#define SA11X0_SERIAL_H
+
+struct uart_port;
+struct uart_info;
+
+/*
+ * This is a temporary structure for registering these
+ * functions; it is intended to be discarded after boot.
+ */
+struct sa1100_port_fns {
+	void	(*set_mctrl)(struct uart_port *, u_int);
+	u_int	(*get_mctrl)(struct uart_port *);
+	void	(*pm)(struct uart_port *, u_int, u_int);
+	int	(*set_wake)(struct uart_port *, u_int);
+};
+
+#ifdef CONFIG_SERIAL_SA1100
+void sa1100_register_uart_fns(struct sa1100_port_fns *fns);
+void sa1100_register_uart(int idx, int port);
+#else
+#define sa1100_register_uart_fns(fns) do { } while (0)
+#define sa1100_register_uart(idx,port) do { } while (0)
+#endif
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 46000065a631c6d21452d533baf086175c384ba4 Mon Sep 17 00:00:00 2001
From: Russell King
Date: Fri, 21 Sep 2012 10:23:44 +0100
Subject: ARM: move udc_pxa2xx.h to linux/platform_data

Move the PXA2xx/IXP4xx UDC header file into linux/platform_data as it
only contains a driver platform data structure.

Acked-by: Felipe Balbi <balbi@ti.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Krzysztof Halasa <khc@pm.waw.pl>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/mach/udc_pxa2xx.h   | 26 --------------------------
 arch/arm/mach-ixp4xx/include/mach/udc.h  |  2 +-
 arch/arm/mach-pxa/include/mach/udc.h     |  2 +-
 drivers/usb/gadget/pxa25x_udc.c          |  4 +---
 include/linux/platform_data/pxa2xx_udc.h | 27 +++++++++++++++++++++++++++
 5 files changed, 30 insertions(+), 31 deletions(-)
 delete mode 100644 arch/arm/include/asm/mach/udc_pxa2xx.h
 create mode 100644 include/linux/platform_data/pxa2xx_udc.h

(limited to 'include')

diff --git a/arch/arm/include/asm/mach/udc_pxa2xx.h b/arch/arm/include/asm/mach/udc_pxa2xx.h
deleted file mode 100644
index ea297ac70bc6..000000000000
--- a/arch/arm/include/asm/mach/udc_pxa2xx.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * arch/arm/include/asm/mach/udc_pxa2xx.h
- *
- * This supports machine-specific differences in how the PXA2xx
- * USB Device Controller (UDC) is wired.
- *
- * It is set in linux/arch/arm/mach-pxa/<machine>.c or in
- * linux/arch/mach-ixp4xx/<machine>.c and used in
- * the probe routine of linux/drivers/usb/gadget/pxa2xx_udc.c
- */
-
-struct pxa2xx_udc_mach_info {
-        int  (*udc_is_connected)(void);		/* do we see host? */
-        void (*udc_command)(int cmd);
-#define	PXA2XX_UDC_CMD_CONNECT		0	/* let host see us */
-#define	PXA2XX_UDC_CMD_DISCONNECT	1	/* so host won't see us */
-
-	/* Boards following the design guidelines in the developer's manual,
-	 * with on-chip GPIOs not Lubbock's weird hardware, can have a sane
-	 * VBUS IRQ and omit the methods above.  Store the GPIO number
-	 * here.  Note that sometimes the signals go through inverters...
-	 */
-	bool	gpio_pullup_inverted;
-	int	gpio_pullup;			/* high == pullup activated */
-};
-
diff --git a/arch/arm/mach-ixp4xx/include/mach/udc.h b/arch/arm/mach-ixp4xx/include/mach/udc.h
index 80d6da2eafac..7bd8b96c8843 100644
--- a/arch/arm/mach-ixp4xx/include/mach/udc.h
+++ b/arch/arm/mach-ixp4xx/include/mach/udc.h
@@ -2,7 +2,7 @@
  * arch/arm/mach-ixp4xx/include/mach/udc.h
  *
  */
-#include <asm/mach/udc_pxa2xx.h>
+#include <linux/platform_data/pxa2xx_udc.h>
 
 extern void ixp4xx_set_udc_info(struct pxa2xx_udc_mach_info *info);
 
diff --git a/arch/arm/mach-pxa/include/mach/udc.h b/arch/arm/mach-pxa/include/mach/udc.h
index 2f82332e81a0..9a827e32db98 100644
--- a/arch/arm/mach-pxa/include/mach/udc.h
+++ b/arch/arm/mach-pxa/include/mach/udc.h
@@ -2,7 +2,7 @@
  * arch/arm/mach-pxa/include/mach/udc.h
  *
  */
-#include <asm/mach/udc_pxa2xx.h>
+#include <linux/platform_data/pxa2xx_udc.h>
 
 extern void pxa_set_udc_info(struct pxa2xx_udc_mach_info *info);
 
diff --git a/drivers/usb/gadget/pxa25x_udc.c b/drivers/usb/gadget/pxa25x_udc.c
index 8efbf08c3561..d4ca9f1f7f24 100644
--- a/drivers/usb/gadget/pxa25x_udc.c
+++ b/drivers/usb/gadget/pxa25x_udc.c
@@ -29,6 +29,7 @@
 #include <linux/list.h>
 #include <linux/interrupt.h>
 #include <linux/mm.h>
+#include <linux/platform_data/pxa2xx_udc.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/irq.h>
@@ -59,9 +60,6 @@
 #include <mach/lubbock.h>
 #endif
 
-#include <asm/mach/udc_pxa2xx.h>
-
-
 /*
  * This driver handles the USB Device Controller (UDC) in Intel's PXA 25x
  * series processors.  The UDC for the IXP 4xx series is very similar.
diff --git a/include/linux/platform_data/pxa2xx_udc.h b/include/linux/platform_data/pxa2xx_udc.h
new file mode 100644
index 000000000000..c6c5e98b5b82
--- /dev/null
+++ b/include/linux/platform_data/pxa2xx_udc.h
@@ -0,0 +1,27 @@
+/*
+ * This supports machine-specific differences in how the PXA2xx
+ * USB Device Controller (UDC) is wired.
+ *
+ * It is set in linux/arch/arm/mach-pxa/<machine>.c or in
+ * linux/arch/mach-ixp4xx/<machine>.c and used in
+ * the probe routine of linux/drivers/usb/gadget/pxa2xx_udc.c
+ */
+#ifndef PXA2XX_UDC_H
+#define PXA2XX_UDC_H
+
+struct pxa2xx_udc_mach_info {
+        int  (*udc_is_connected)(void);		/* do we see host? */
+        void (*udc_command)(int cmd);
+#define	PXA2XX_UDC_CMD_CONNECT		0	/* let host see us */
+#define	PXA2XX_UDC_CMD_DISCONNECT	1	/* so host won't see us */
+
+	/* Boards following the design guidelines in the developer's manual,
+	 * with on-chip GPIOs not Lubbock's weird hardware, can have a sane
+	 * VBUS IRQ and omit the methods above.  Store the GPIO number
+	 * here.  Note that sometimes the signals go through inverters...
+	 */
+	bool	gpio_pullup_inverted;
+	int	gpio_pullup;			/* high == pullup activated */
+};
+
+#endif
-- 
cgit v1.2.3-55-g7522


From ed71871bed7198ca4aa6a79b7a93b73ad6408e98 Mon Sep 17 00:00:00 2001
From: Noam Camus
Date: Fri, 16 Nov 2012 07:03:05 +0200
Subject: tty/8250_early: Turn serial_in/serial_out into weak symbols.

Allows overriding default methods serial_in/serial_out.

In such platform specific replacement it is possible to use
other regshift, biased register offset, any other manipulation
that is not covered with common default methods.

Overriding default methods may be useful for platforms which got
serial peripheral with registers represented in big endian.
In this situation and assuming that 32 bit operations / alignment
is required then it may be useful to swab words before/after
accessing the serial registers.

Signed-off-by: Noam Camus <noamc@ezchip.com>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_early.c | 42 ++++++++++++++++++------------------
 include/linux/serial_8250.h          |  2 ++
 2 files changed, 23 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c
index 843a150ba105..f53a7db4350d 100644
--- a/drivers/tty/serial/8250/8250_early.c
+++ b/drivers/tty/serial/8250/8250_early.c
@@ -48,7 +48,7 @@ struct early_serial8250_device {
 
 static struct early_serial8250_device early_device;
 
-static unsigned int __init serial_in(struct uart_port *port, int offset)
+unsigned int __weak __init serial8250_early_in(struct uart_port *port, int offset)
 {
 	switch (port->iotype) {
 	case UPIO_MEM:
@@ -62,7 +62,7 @@ static unsigned int __init serial_in(struct uart_port *port, int offset)
 	}
 }
 
-static void __init serial_out(struct uart_port *port, int offset, int value)
+void __weak __init serial8250_early_out(struct uart_port *port, int offset, int value)
 {
 	switch (port->iotype) {
 	case UPIO_MEM:
@@ -84,7 +84,7 @@ static void __init wait_for_xmitr(struct uart_port *port)
 	unsigned int status;
 
 	for (;;) {
-		status = serial_in(port, UART_LSR);
+		status = serial8250_early_in(port, UART_LSR);
 		if ((status & BOTH_EMPTY) == BOTH_EMPTY)
 			return;
 		cpu_relax();
@@ -94,7 +94,7 @@ static void __init wait_for_xmitr(struct uart_port *port)
 static void __init serial_putc(struct uart_port *port, int c)
 {
 	wait_for_xmitr(port);
-	serial_out(port, UART_TX, c);
+	serial8250_early_out(port, UART_TX, c);
 }
 
 static void __init early_serial8250_write(struct console *console,
@@ -104,14 +104,14 @@ static void __init early_serial8250_write(struct console *console,
 	unsigned int ier;
 
 	/* Save the IER and disable interrupts */
-	ier = serial_in(port, UART_IER);
-	serial_out(port, UART_IER, 0);
+	ier = serial8250_early_in(port, UART_IER);
+	serial8250_early_out(port, UART_IER, 0);
 
 	uart_console_write(port, s, count, serial_putc);
 
 	/* Wait for transmitter to become empty and restore the IER */
 	wait_for_xmitr(port);
-	serial_out(port, UART_IER, ier);
+	serial8250_early_out(port, UART_IER, ier);
 }
 
 static unsigned int __init probe_baud(struct uart_port *port)
@@ -119,11 +119,11 @@ static unsigned int __init probe_baud(struct uart_port *port)
 	unsigned char lcr, dll, dlm;
 	unsigned int quot;
 
-	lcr = serial_in(port, UART_LCR);
-	serial_out(port, UART_LCR, lcr | UART_LCR_DLAB);
-	dll = serial_in(port, UART_DLL);
-	dlm = serial_in(port, UART_DLM);
-	serial_out(port, UART_LCR, lcr);
+	lcr = serial8250_early_in(port, UART_LCR);
+	serial8250_early_out(port, UART_LCR, lcr | UART_LCR_DLAB);
+	dll = serial8250_early_in(port, UART_DLL);
+	dlm = serial8250_early_in(port, UART_DLM);
+	serial8250_early_out(port, UART_LCR, lcr);
 
 	quot = (dlm << 8) | dll;
 	return (port->uartclk / 16) / quot;
@@ -135,17 +135,17 @@ static void __init init_port(struct early_serial8250_device *device)
 	unsigned int divisor;
 	unsigned char c;
 
-	serial_out(port, UART_LCR, 0x3);	/* 8n1 */
-	serial_out(port, UART_IER, 0);		/* no interrupt */
-	serial_out(port, UART_FCR, 0);		/* no fifo */
-	serial_out(port, UART_MCR, 0x3);	/* DTR + RTS */
+	serial8250_early_out(port, UART_LCR, 0x3);	/* 8n1 */
+	serial8250_early_out(port, UART_IER, 0);	/* no interrupt */
+	serial8250_early_out(port, UART_FCR, 0);	/* no fifo */
+	serial8250_early_out(port, UART_MCR, 0x3);	/* DTR + RTS */
 
 	divisor = DIV_ROUND_CLOSEST(port->uartclk, 16 * device->baud);
-	c = serial_in(port, UART_LCR);
-	serial_out(port, UART_LCR, c | UART_LCR_DLAB);
-	serial_out(port, UART_DLL, divisor & 0xff);
-	serial_out(port, UART_DLM, (divisor >> 8) & 0xff);
-	serial_out(port, UART_LCR, c & ~UART_LCR_DLAB);
+	c = serial8250_early_in(port, UART_LCR);
+	serial8250_early_out(port, UART_LCR, c | UART_LCR_DLAB);
+	serial8250_early_out(port, UART_DLL, divisor & 0xff);
+	serial8250_early_out(port, UART_DLM, (divisor >> 8) & 0xff);
+	serial8250_early_out(port, UART_LCR, c & ~UART_LCR_DLAB);
 }
 
 static int __init parse_options(struct early_serial8250_device *device,
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index c174c90fb3fb..c490d20b3fb8 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -105,6 +105,8 @@ extern int early_serial_setup(struct uart_port *port);
 
 extern int serial8250_find_port(struct uart_port *p);
 extern int serial8250_find_port_for_earlycon(void);
+extern unsigned int serial8250_early_in(struct uart_port *port, int offset);
+extern void serial8250_early_out(struct uart_port *port, int offset, int value);
 extern int setup_early_serial8250_console(char *cmdline);
 extern void serial8250_do_set_termios(struct uart_port *port,
 		struct ktermios *termios, struct ktermios *old);
-- 
cgit v1.2.3-55-g7522


From 32cdba1e05418909708a17e52505e8b2ba4381d1 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov
Date: Wed, 14 Nov 2012 19:03:42 +0100
Subject: uprobes: Use percpu_rw_semaphore to fix register/unregister vs
 dup_mmap() race

This was always racy, but 268720903f87e0b84b161626c4447b81671b5d18
"uprobes: Rework register_for_each_vma() to make it O(n)" should be
blamed anyway, it made everything worse and I didn't notice.

register/unregister call build_map_info() and then do install/remove
breakpoint for every mm which mmaps inode/offset. This can obviously
race with fork()->dup_mmap() in between and we can miss the child.

uprobe_register() could be easily fixed but unregister is much worse,
the new mm inherits "int3" from parent and there is no way to detect
this if uprobe goes away.

So this patch simply adds percpu_down_read/up_read around dup_mmap(),
and percpu_down_write/up_write into register_for_each_vma().

This adds 2 new hooks into dup_mmap() but we can kill uprobe_dup_mmap()
and fold it into uprobe_end_dup_mmap().

Reported-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/uprobes.h |  8 ++++++++
 kernel/events/uprobes.c | 26 +++++++++++++++++++++++---
 kernel/fork.c           |  2 ++
 3 files changed, 33 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 2615c4d7788d..4f628a6fc5b4 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -97,6 +97,8 @@ extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_con
 extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_mmap(struct vm_area_struct *vma);
 extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+extern void uprobe_start_dup_mmap(void);
+extern void uprobe_end_dup_mmap(void);
 extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm);
 extern void uprobe_free_utask(struct task_struct *t);
 extern void uprobe_copy_process(struct task_struct *t);
@@ -127,6 +129,12 @@ static inline void
 uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
 }
+static inline void uprobe_start_dup_mmap(void)
+{
+}
+static inline void uprobe_end_dup_mmap(void)
+{
+}
 static inline void
 uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
 {
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 5ce99cfd2e6e..dea7acfbb071 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -33,6 +33,7 @@
 #include <linux/ptrace.h>	/* user_enable_single_step */
 #include <linux/kdebug.h>	/* notifier mechanism */
 #include "../../mm/internal.h"	/* munlock_vma_page */
+#include <linux/percpu-rwsem.h>
 
 #include <linux/uprobes.h>
 
@@ -71,6 +72,8 @@ static struct mutex uprobes_mutex[UPROBES_HASH_SZ];
 static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
 #define uprobes_mmap_hash(v)	(&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ])
 
+static struct percpu_rw_semaphore dup_mmap_sem;
+
 /*
  * uprobe_events allows us to skip the uprobe_mmap if there are no uprobe
  * events active at this time.  Probably a fine grained per inode count is
@@ -766,10 +769,13 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
 	struct map_info *info;
 	int err = 0;
 
+	percpu_down_write(&dup_mmap_sem);
 	info = build_map_info(uprobe->inode->i_mapping,
 					uprobe->offset, is_register);
-	if (IS_ERR(info))
-		return PTR_ERR(info);
+	if (IS_ERR(info)) {
+		err = PTR_ERR(info);
+		goto out;
+	}
 
 	while (info) {
 		struct mm_struct *mm = info->mm;
@@ -799,7 +805,8 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
 		mmput(mm);
 		info = free_map_info(info);
 	}
-
+ out:
+	percpu_up_write(&dup_mmap_sem);
 	return err;
 }
 
@@ -1131,6 +1138,16 @@ void uprobe_clear_state(struct mm_struct *mm)
 	kfree(area);
 }
 
+void uprobe_start_dup_mmap(void)
+{
+	percpu_down_read(&dup_mmap_sem);
+}
+
+void uprobe_end_dup_mmap(void)
+{
+	percpu_up_read(&dup_mmap_sem);
+}
+
 void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
 {
 	newmm->uprobes_state.xol_area = NULL;
@@ -1597,6 +1614,9 @@ static int __init init_uprobes(void)
 		mutex_init(&uprobes_mmap_mutex[i]);
 	}
 
+	if (percpu_init_rwsem(&dup_mmap_sem))
+		return -ENOMEM;
+
 	return register_die_notifier(&uprobe_exception_nb);
 }
 module_init(init_uprobes);
diff --git a/kernel/fork.c b/kernel/fork.c
index 8b20ab7d3aa2..c497e57aa654 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -352,6 +352,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	unsigned long charge;
 	struct mempolicy *pol;
 
+	uprobe_start_dup_mmap();
 	down_write(&oldmm->mmap_sem);
 	flush_cache_dup_mm(oldmm);
 	uprobe_dup_mmap(oldmm, mm);
@@ -469,6 +470,7 @@ out:
 	up_write(&mm->mmap_sem);
 	flush_tlb_mm(oldmm);
 	up_write(&oldmm->mmap_sem);
+	uprobe_end_dup_mmap();
 	return retval;
 fail_nomem_anon_vma_fork:
 	mpol_put(pol);
-- 
cgit v1.2.3-55-g7522


From 40fc3bb56ed125aa22c0a85c816ae0f923519146 Mon Sep 17 00:00:00 2001
From: Jon Hunter
Date: Fri, 28 Sep 2012 11:34:49 -0500
Subject: ARM: OMAP: Add platform data header for DMTIMERs

Move definition of dmtimer platform data structure in to its own header
under <linux/platform_data>.

Signed-off-by: Jon Hunter <jon-hunter@ti.com>
---
 arch/arm/mach-omap1/timer.c                |  1 +
 arch/arm/mach-omap2/timer.c                |  2 ++
 arch/arm/plat-omap/dmtimer.c               |  2 ++
 arch/arm/plat-omap/include/plat/dmtimer.h  |  8 --------
 include/linux/platform_data/dmtimer-omap.h | 31 ++++++++++++++++++++++++++++++
 5 files changed, 36 insertions(+), 8 deletions(-)
 create mode 100644 include/linux/platform_data/dmtimer-omap.h

(limited to 'include')

diff --git a/arch/arm/mach-omap1/timer.c b/arch/arm/mach-omap1/timer.c
index cdeb9d3ef640..bde7a35e5000 100644
--- a/arch/arm/mach-omap1/timer.c
+++ b/arch/arm/mach-omap1/timer.c
@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/dmtimer-omap.h>
 
 #include <mach/irqs.h>
 
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 1a662dfdda11..4daa8b41c522 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -39,6 +39,8 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/dmtimer-omap.h>
 
 #include <asm/mach/time.h>
 #include <asm/smp_twd.h>
diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c
index efe47744b491..89585c293554 100644
--- a/arch/arm/plat-omap/dmtimer.c
+++ b/arch/arm/plat-omap/dmtimer.c
@@ -43,6 +43,8 @@
 #include <linux/pm_runtime.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/dmtimer-omap.h>
 
 #include <plat/dmtimer.h>
 
diff --git a/arch/arm/plat-omap/include/plat/dmtimer.h b/arch/arm/plat-omap/include/plat/dmtimer.h
index b3cd91b60a2e..a3fbc48c332e 100644
--- a/arch/arm/plat-omap/include/plat/dmtimer.h
+++ b/arch/arm/plat-omap/include/plat/dmtimer.h
@@ -124,14 +124,6 @@ struct omap_dm_timer {
 	struct list_head node;
 };
 
-struct dmtimer_platform_data {
-	/* set_timer_src - Only used for OMAP1 devices */
-	int (*set_timer_src)(struct platform_device *pdev, int source);
-	u32 timer_errata;
-	u32 timer_capability;
-	int (*get_context_loss_count)(struct device *);
-};
-
 int omap_dm_timer_reserve_systimer(int id);
 struct omap_dm_timer *omap_dm_timer_request(void);
 struct omap_dm_timer *omap_dm_timer_request_specific(int timer_id);
diff --git a/include/linux/platform_data/dmtimer-omap.h b/include/linux/platform_data/dmtimer-omap.h
new file mode 100644
index 000000000000..a19b78d826e9
--- /dev/null
+++ b/include/linux/platform_data/dmtimer-omap.h
@@ -0,0 +1,31 @@
+/*
+ * DMTIMER platform data for TI OMAP platforms
+ *
+ * Copyright (C) 2012 Texas Instruments
+ * Author: Jon Hunter <jon-hunter@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __PLATFORM_DATA_DMTIMER_OMAP_H__
+#define __PLATFORM_DATA_DMTIMER_OMAP_H__
+
+struct dmtimer_platform_data {
+	/* set_timer_src - Only used for OMAP1 devices */
+	int (*set_timer_src)(struct platform_device *pdev, int source);
+	u32 timer_capability;
+	u32 timer_errata;
+	int (*get_context_loss_count)(struct device *);
+};
+
+#endif /* __PLATFORM_DATA_DMTIMER_OMAP_H__ */
-- 
cgit v1.2.3-55-g7522


From 3fbfbf7a3b66ec424042d909f14ba2ddf4372ea8 Mon Sep 17 00:00:00 2001
From: Paul E. McKenney
Date: Sun, 19 Aug 2012 21:35:53 -0700
Subject: rcu: Add callback-free CPUs

RCU callback execution can add significant OS jitter and also can
degrade both scheduling latency and, in asymmetric multiprocessors,
energy efficiency.  This commit therefore adds the ability for selected
CPUs ("rcu_nocbs=" boot parameter) to have their callbacks offloaded
to kthreads.  If the "rcu_nocb_poll" boot parameter is also specified,
these kthreads will do polling, removing the need for the offloaded
CPUs to do wakeups.  At least one CPU must be doing normal callback
processing: currently CPU 0 cannot be selected as a no-CBs CPU.
In addition, attempts to offline the last normal-CBs CPU will fail.

This feature was inspired by Jim Houston's and Joe Korty's JRCU, and
this commit includes fixes to problems located by Fengguang Wu's
kbuild test robot.

[ paulmck: Added gfp.h include file as suggested by Fengguang Wu. ]

Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/kernel-parameters.txt |  21 ++
 include/trace/events/rcu.h          |   1 +
 init/Kconfig                        |  22 ++
 kernel/rcutree.c                    |  63 ++++--
 kernel/rcutree.h                    |  47 +++++
 kernel/rcutree_plugin.h             | 397 +++++++++++++++++++++++++++++++++++-
 kernel/rcutree_trace.c              |   7 +-
 7 files changed, 542 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 9776f068306b..9d2e5cb3a95f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2394,6 +2394,27 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	ramdisk_size=	[RAM] Sizes of RAM disks in kilobytes
 			See Documentation/blockdev/ramdisk.txt.
 
+	rcu_nocbs=	[KNL,BOOT]
+			In kernels built with CONFIG_RCU_NOCB_CPU=y, set
+			the specified list of CPUs to be no-callback CPUs.
+			Invocation of these CPUs' RCU callbacks will
+			be offloaded to "rcuoN" kthreads created for
+			that purpose.  This reduces OS jitter on the
+			offloaded CPUs, which can be useful for HPC and
+			real-time workloads.  It can also improve energy
+			efficiency for asymmetric multiprocessors.
+
+	rcu_nocbs_poll	[KNL,BOOT]
+			Rather than requiring that offloaded CPUs
+			(specified by rcu_nocbs= above) explicitly
+			awaken the corresponding "rcuoN" kthreads,
+			make these kthreads poll for callbacks.
+			This improves the real-time response for the
+			offloaded CPUs by relieving them of the need to
+			wake up the corresponding kthread, but degrades
+			energy efficiency by requiring that the kthreads
+			periodically wake up to do the polling.
+
 	rcutree.blimit=	[KNL,BOOT]
 			Set maximum number of finished RCU callbacks to process
 			in one batch.
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 5bde94d8585b..d4f559b1ec34 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -549,6 +549,7 @@ TRACE_EVENT(rcu_torture_read,
  *	"EarlyExit": rcu_barrier_callback() piggybacked, thus early exit.
  *	"Inc1": rcu_barrier_callback() piggyback check counter incremented.
  *	"Offline": rcu_barrier_callback() found offline CPU
+ *	"OnlineNoCB": rcu_barrier_callback() found online no-CBs CPU.
  *	"OnlineQ": rcu_barrier_callback() found online CPU with callbacks.
  *	"OnlineNQ": rcu_barrier_callback() found online CPU, no callbacks.
  *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.
diff --git a/init/Kconfig b/init/Kconfig
index ec62139207d3..5ac6ee094225 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -654,6 +654,28 @@ config RCU_BOOST_DELAY
 
 	  Accept the default if unsure.
 
+config RCU_NOCB_CPU
+	bool "Offload RCU callback processing from boot-selected CPUs"
+	depends on TREE_RCU || TREE_PREEMPT_RCU
+	default n
+	help
+	  Use this option to reduce OS jitter for aggressive HPC or
+	  real-time workloads.	It can also be used to offload RCU
+	  callback invocation to energy-efficient CPUs in battery-powered
+	  asymmetric multiprocessors.
+
+	  This option offloads callback invocation from the set of
+	  CPUs specified at boot time by the rcu_nocbs parameter.
+	  For each such CPU, a kthread ("rcuoN") will be created to
+	  invoke callbacks, where the "N" is the CPU being offloaded.
+	  Nothing prevents this kthread from running on the specified
+	  CPUs, but (1) the kthreads may be preempted between each
+	  callback, and (2) affinity or cgroups can be used to force
+	  the kthreads to run on whatever set of CPUs is desired.
+
+	  Say Y here if you want reduced OS jitter on selected CPUs.
+	  Say N here if you are unsure.
+
 endmenu # "RCU Subsystem"
 
 config IKCONFIG
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 5ffadcc3bb26..7733eb56e156 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -303,7 +303,8 @@ EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
 static int
 cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
 {
-	return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL];
+	return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] &&
+	       rdp->nxttail[RCU_DONE_TAIL] != NULL;
 }
 
 /*
@@ -312,8 +313,11 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
 static int
 cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	return *rdp->nxttail[RCU_DONE_TAIL +
-			     (ACCESS_ONCE(rsp->completed) != rdp->completed)] &&
+	struct rcu_head **ntp;
+
+	ntp = rdp->nxttail[RCU_DONE_TAIL +
+			   (ACCESS_ONCE(rsp->completed) != rdp->completed)];
+	return rdp->nxttail[RCU_DONE_TAIL] && ntp && *ntp &&
 	       !rcu_gp_in_progress(rsp);
 }
 
@@ -1123,6 +1127,7 @@ static void init_callback_list(struct rcu_data *rdp)
 	rdp->nxtlist = NULL;
 	for (i = 0; i < RCU_NEXT_SIZE; i++)
 		rdp->nxttail[i] = &rdp->nxtlist;
+	init_nocb_callback_list(rdp);
 }
 
 /*
@@ -1633,6 +1638,10 @@ static void
 rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
 			  struct rcu_node *rnp, struct rcu_data *rdp)
 {
+	/* No-CBs CPUs do not have orphanable callbacks. */
+	if (is_nocb_cpu(rdp->cpu))
+		return;
+
 	/*
 	 * Orphan the callbacks.  First adjust the counts.  This is safe
 	 * because _rcu_barrier() excludes CPU-hotplug operations, so it
@@ -1684,6 +1693,10 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
 	int i;
 	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
 
+	/* No-CBs CPUs are handled specially. */
+	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
+		return;
+
 	/* Do the accounting first. */
 	rdp->qlen_lazy += rsp->qlen_lazy;
 	rdp->qlen += rsp->qlen;
@@ -2162,9 +2175,15 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 	}
 }
 
+/*
+ * Helper function for call_rcu() and friends.  The cpu argument will
+ * normally be -1, indicating "currently running CPU".  It may specify
+ * a CPU only if that CPU is a no-CBs CPU.  Currently, only _rcu_barrier()
+ * is expected to specify a CPU.
+ */
 static void
 __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
-	   struct rcu_state *rsp, bool lazy)
+	   struct rcu_state *rsp, int cpu, bool lazy)
 {
 	unsigned long flags;
 	struct rcu_data *rdp;
@@ -2184,9 +2203,14 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	rdp = this_cpu_ptr(rsp->rda);
 
 	/* Add the callback to our list. */
-	if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL)) {
+	if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL) || cpu != -1) {
+		int offline;
+
+		if (cpu != -1)
+			rdp = per_cpu_ptr(rsp->rda, cpu);
+		offline = !__call_rcu_nocb(rdp, head, lazy);
+		WARN_ON_ONCE(offline);
 		/* _call_rcu() is illegal on offline CPU; leak the callback. */
-		WARN_ON_ONCE(1);
 		local_irq_restore(flags);
 		return;
 	}
@@ -2215,7 +2239,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
  */
 void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_sched_state, 0);
+	__call_rcu(head, func, &rcu_sched_state, -1, 0);
 }
 EXPORT_SYMBOL_GPL(call_rcu_sched);
 
@@ -2224,7 +2248,7 @@ EXPORT_SYMBOL_GPL(call_rcu_sched);
  */
 void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_bh_state, 0);
+	__call_rcu(head, func, &rcu_bh_state, -1, 0);
 }
 EXPORT_SYMBOL_GPL(call_rcu_bh);
 
@@ -2676,9 +2700,17 @@ static void _rcu_barrier(struct rcu_state *rsp)
 	 * When that callback is invoked, we will know that all of the
 	 * corresponding CPU's preceding callbacks have been invoked.
 	 */
-	for_each_online_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
+		if (!cpu_online(cpu) && !is_nocb_cpu(cpu))
+			continue;
 		rdp = per_cpu_ptr(rsp->rda, cpu);
-		if (ACCESS_ONCE(rdp->qlen)) {
+		if (is_nocb_cpu(cpu)) {
+			_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
+					   rsp->n_barrier_done);
+			atomic_inc(&rsp->barrier_cpu_count);
+			__call_rcu(&rdp->barrier_head, rcu_barrier_callback,
+				   rsp, cpu, 0);
+		} else if (ACCESS_ONCE(rdp->qlen)) {
 			_rcu_barrier_trace(rsp, "OnlineQ", cpu,
 					   rsp->n_barrier_done);
 			smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
@@ -2752,6 +2784,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 #endif
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
+	rcu_boot_init_nocb_percpu_data(rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
@@ -2833,6 +2866,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;
 	struct rcu_state *rsp;
+	int ret = NOTIFY_OK;
 
 	trace_rcu_utilization("Start CPU hotplug");
 	switch (action) {
@@ -2846,7 +2880,10 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 		rcu_boost_kthread_setaffinity(rnp, -1);
 		break;
 	case CPU_DOWN_PREPARE:
-		rcu_boost_kthread_setaffinity(rnp, cpu);
+		if (nocb_cpu_expendable(cpu))
+			rcu_boost_kthread_setaffinity(rnp, cpu);
+		else
+			ret = NOTIFY_BAD;
 		break;
 	case CPU_DYING:
 	case CPU_DYING_FROZEN:
@@ -2870,7 +2907,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 		break;
 	}
 	trace_rcu_utilization("End CPU hotplug");
-	return NOTIFY_OK;
+	return ret;
 }
 
 /*
@@ -2890,6 +2927,7 @@ static int __init rcu_spawn_gp_kthread(void)
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rsp->gp_kthread = t;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		rcu_spawn_nocb_kthreads(rsp);
 	}
 	return 0;
 }
@@ -3085,6 +3123,7 @@ void __init rcu_init(void)
 	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
 	__rcu_init_preempt();
+	rcu_init_nocb();
 	 open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
 	/*
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index d274af357210..488f2ec6b663 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -317,6 +317,18 @@ struct rcu_data {
 	struct rcu_head oom_head;
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 
+	/* 7) Callback offloading. */
+#ifdef CONFIG_RCU_NOCB_CPU
+	struct rcu_head *nocb_head;	/* CBs waiting for kthread. */
+	struct rcu_head **nocb_tail;
+	atomic_long_t nocb_q_count;	/* # CBs waiting for kthread */
+	atomic_long_t nocb_q_count_lazy; /*  (approximate). */
+	int nocb_p_count;		/* # CBs being invoked by kthread */
+	int nocb_p_count_lazy;		/*  (approximate). */
+	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
+	struct task_struct *nocb_kthread;
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
+
 	int cpu;
 	struct rcu_state *rsp;
 };
@@ -369,6 +381,12 @@ struct rcu_state {
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	void (*call)(struct rcu_head *head,	/* call_rcu() flavor. */
 		     void (*func)(struct rcu_head *head));
+#ifdef CONFIG_RCU_NOCB_CPU
+	void (*call_remote)(struct rcu_head *head,
+		     void (*func)(struct rcu_head *head));
+						/* call_rcu() flavor, but for */
+						/*  placing on remote CPU. */
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* The following fields are guarded by the root rcu_node's lock. */
 
@@ -439,6 +457,8 @@ struct rcu_state {
 #define RCU_GP_FLAG_FQS  0x2	/* Need grace-period quiescent-state forcing. */
 
 extern struct list_head rcu_struct_flavors;
+
+/* Sequence through rcu_state structures for each RCU flavor. */
 #define for_each_rcu_flavor(rsp) \
 	list_for_each_entry((rsp), &rcu_struct_flavors, flavors)
 
@@ -515,5 +535,32 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static void increment_cpu_stall_ticks(void);
+static bool is_nocb_cpu(int cpu);
+static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
+			    bool lazy);
+static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+				      struct rcu_data *rdp);
+static bool nocb_cpu_expendable(int cpu);
+static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
+static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
+static void init_nocb_callback_list(struct rcu_data *rdp);
+static void __init rcu_init_nocb(void);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
+
+#ifdef CONFIG_RCU_TRACE
+#ifdef CONFIG_RCU_NOCB_CPU
+/* Sum up queue lengths for tracing. */
+static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
+{
+	*ql = atomic_long_read(&rdp->nocb_q_count) + rdp->nocb_p_count;
+	*qll = atomic_long_read(&rdp->nocb_q_count_lazy) + rdp->nocb_p_count_lazy;
+}
+#else /* #ifdef CONFIG_RCU_NOCB_CPU */
+static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
+{
+	*ql = 0;
+	*qll = 0;
+}
+#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
+#endif /* #ifdef CONFIG_RCU_TRACE */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 5ce3352505e9..6cdc372de34c 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -25,6 +25,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/gfp.h>
 #include <linux/oom.h>
 #include <linux/smpboot.h>
 
@@ -36,6 +37,14 @@
 #define RCU_BOOST_PRIO RCU_KTHREAD_PRIO
 #endif
 
+#ifdef CONFIG_RCU_NOCB_CPU
+static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
+static bool have_rcu_nocb_mask;	    /* Was rcu_nocb_mask allocated? */
+static bool rcu_nocb_poll;	    /* Offload kthread are to poll. */
+module_param(rcu_nocb_poll, bool, 0444);
+static char __initdata nocb_buf[NR_CPUS * 5];
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
+
 /*
  * Check the RCU kernel configuration parameters and print informative
  * messages about anything out of the ordinary.  If you like #ifdef, you
@@ -76,6 +85,18 @@ static void __init rcu_bootup_announce_oddness(void)
 		printk(KERN_INFO "\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		printk(KERN_INFO "\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
+#ifdef CONFIG_RCU_NOCB_CPU
+	if (have_rcu_nocb_mask) {
+		if (cpumask_test_cpu(0, rcu_nocb_mask)) {
+			cpumask_clear_cpu(0, rcu_nocb_mask);
+			pr_info("\tCPU 0: illegal no-CBs CPU (cleared).\n");
+		}
+		cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
+		pr_info("\tExperimental no-CBs CPUs: %s.\n", nocb_buf);
+		if (rcu_nocb_poll)
+			pr_info("\tExperimental polled no-CBs CPUs.\n");
+	}
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 }
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
@@ -642,7 +663,7 @@ static void rcu_preempt_do_callbacks(void)
  */
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_preempt_state, 0);
+	__call_rcu(head, func, &rcu_preempt_state, -1, 0);
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
@@ -656,7 +677,7 @@ EXPORT_SYMBOL_GPL(call_rcu);
 void kfree_call_rcu(struct rcu_head *head,
 		    void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_preempt_state, 1);
+	__call_rcu(head, func, &rcu_preempt_state, -1, 1);
 }
 EXPORT_SYMBOL_GPL(kfree_call_rcu);
 
@@ -1025,7 +1046,7 @@ static void rcu_preempt_check_callbacks(int cpu)
 void kfree_call_rcu(struct rcu_head *head,
 		    void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_sched_state, 1);
+	__call_rcu(head, func, &rcu_sched_state, -1, 1);
 }
 EXPORT_SYMBOL_GPL(kfree_call_rcu);
 
@@ -2104,3 +2125,373 @@ static void increment_cpu_stall_ticks(void)
 }
 
 #endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */
+
+#ifdef CONFIG_RCU_NOCB_CPU
+
+/*
+ * Offload callback processing from the boot-time-specified set of CPUs
+ * specified by rcu_nocb_mask.  For each CPU in the set, there is a
+ * kthread created that pulls the callbacks from the corresponding CPU,
+ * waits for a grace period to elapse, and invokes the callbacks.
+ * The no-CBs CPUs do a wake_up() on their kthread when they insert
+ * a callback into any empty list, unless the rcu_nocb_poll boot parameter
+ * has been specified, in which case each kthread actively polls its
+ * CPU.  (Which isn't so great for energy efficiency, but which does
+ * reduce RCU's overhead on that CPU.)
+ *
+ * This is intended to be used in conjunction with Frederic Weisbecker's
+ * adaptive-idle work, which would seriously reduce OS jitter on CPUs
+ * running CPU-bound user-mode computations.
+ *
+ * Offloading of callback processing could also in theory be used as
+ * an energy-efficiency measure because CPUs with no RCU callbacks
+ * queued are more aggressive about entering dyntick-idle mode.
+ */
+
+
+/* Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. */
+static int __init rcu_nocb_setup(char *str)
+{
+	alloc_bootmem_cpumask_var(&rcu_nocb_mask);
+	have_rcu_nocb_mask = true;
+	cpulist_parse(str, rcu_nocb_mask);
+	return 1;
+}
+__setup("rcu_nocbs=", rcu_nocb_setup);
+
+/* Is the specified CPU a no-CPUs CPU? */
+static bool is_nocb_cpu(int cpu)
+{
+	if (have_rcu_nocb_mask)
+		return cpumask_test_cpu(cpu, rcu_nocb_mask);
+	return false;
+}
+
+/*
+ * Enqueue the specified string of rcu_head structures onto the specified
+ * CPU's no-CBs lists.  The CPU is specified by rdp, the head of the
+ * string by rhp, and the tail of the string by rhtp.  The non-lazy/lazy
+ * counts are supplied by rhcount and rhcount_lazy.
+ *
+ * If warranted, also wake up the kthread servicing this CPUs queues.
+ */
+static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
+				    struct rcu_head *rhp,
+				    struct rcu_head **rhtp,
+				    int rhcount, int rhcount_lazy)
+{
+	int len;
+	struct rcu_head **old_rhpp;
+	struct task_struct *t;
+
+	/* Enqueue the callback on the nocb list and update counts. */
+	old_rhpp = xchg(&rdp->nocb_tail, rhtp);
+	ACCESS_ONCE(*old_rhpp) = rhp;
+	atomic_long_add(rhcount, &rdp->nocb_q_count);
+	atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy);
+
+	/* If we are not being polled and there is a kthread, awaken it ... */
+	t = ACCESS_ONCE(rdp->nocb_kthread);
+	if (rcu_nocb_poll | !t)
+		return;
+	len = atomic_long_read(&rdp->nocb_q_count);
+	if (old_rhpp == &rdp->nocb_head) {
+		wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */
+		rdp->qlen_last_fqs_check = 0;
+	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
+		wake_up_process(t); /* ... or if many callbacks queued. */
+		rdp->qlen_last_fqs_check = LONG_MAX / 2;
+	}
+	return;
+}
+
+/*
+ * This is a helper for __call_rcu(), which invokes this when the normal
+ * callback queue is inoperable.  If this is not a no-CBs CPU, this
+ * function returns failure back to __call_rcu(), which can complain
+ * appropriately.
+ *
+ * Otherwise, this function queues the callback where the corresponding
+ * "rcuo" kthread can find it.
+ */
+static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
+			    bool lazy)
+{
+
+	if (!is_nocb_cpu(rdp->cpu))
+		return 0;
+	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy);
+	return 1;
+}
+
+/*
+ * Adopt orphaned callbacks on a no-CBs CPU, or return 0 if this is
+ * not a no-CBs CPU.
+ */
+static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+						     struct rcu_data *rdp)
+{
+	long ql = rsp->qlen;
+	long qll = rsp->qlen_lazy;
+
+	/* If this is not a no-CBs CPU, tell the caller to do it the old way. */
+	if (!is_nocb_cpu(smp_processor_id()))
+		return 0;
+	rsp->qlen = 0;
+	rsp->qlen_lazy = 0;
+
+	/* First, enqueue the donelist, if any.  This preserves CB ordering. */
+	if (rsp->orphan_donelist != NULL) {
+		__call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
+					rsp->orphan_donetail, ql, qll);
+		ql = qll = 0;
+		rsp->orphan_donelist = NULL;
+		rsp->orphan_donetail = &rsp->orphan_donelist;
+	}
+	if (rsp->orphan_nxtlist != NULL) {
+		__call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
+					rsp->orphan_nxttail, ql, qll);
+		ql = qll = 0;
+		rsp->orphan_nxtlist = NULL;
+		rsp->orphan_nxttail = &rsp->orphan_nxtlist;
+	}
+	return 1;
+}
+
+/*
+ * There must be at least one non-no-CBs CPU in operation at any given
+ * time, because no-CBs CPUs are not capable of initiating grace periods
+ * independently.  This function therefore complains if the specified
+ * CPU is the last non-no-CBs CPU, allowing the CPU-hotplug system to
+ * avoid offlining the last such CPU.  (Recursion is a wonderful thing,
+ * but you have to have a base case!)
+ */
+static bool nocb_cpu_expendable(int cpu)
+{
+	cpumask_var_t non_nocb_cpus;
+	int ret;
+
+	/*
+	 * If there are no no-CB CPUs or if this CPU is not a no-CB CPU,
+	 * then offlining this CPU is harmless.  Let it happen.
+	 */
+	if (!have_rcu_nocb_mask || is_nocb_cpu(cpu))
+		return 1;
+
+	/* If no memory, play it safe and keep the CPU around. */
+	if (!alloc_cpumask_var(&non_nocb_cpus, GFP_NOIO))
+		return 0;
+	cpumask_andnot(non_nocb_cpus, cpu_online_mask, rcu_nocb_mask);
+	cpumask_clear_cpu(cpu, non_nocb_cpus);
+	ret = !cpumask_empty(non_nocb_cpus);
+	free_cpumask_var(non_nocb_cpus);
+	return ret;
+}
+
+/*
+ * Helper structure for remote registry of RCU callbacks.
+ * This is needed for when a no-CBs CPU needs to start a grace period.
+ * If it just invokes call_rcu(), the resulting callback will be queued,
+ * which can result in deadlock.
+ */
+struct rcu_head_remote {
+	struct rcu_head *rhp;
+	call_rcu_func_t *crf;
+	void (*func)(struct rcu_head *rhp);
+};
+
+/*
+ * Register a callback as specified by the rcu_head_remote struct.
+ * This function is intended to be invoked via smp_call_function_single().
+ */
+static void call_rcu_local(void *arg)
+{
+	struct rcu_head_remote *rhrp =
+		container_of(arg, struct rcu_head_remote, rhp);
+
+	rhrp->crf(rhrp->rhp, rhrp->func);
+}
+
+/*
+ * Set up an rcu_head_remote structure and the invoke call_rcu_local()
+ * on CPU 0 (which is guaranteed to be a non-no-CBs CPU) via
+ * smp_call_function_single().
+ */
+static void invoke_crf_remote(struct rcu_head *rhp,
+			      void (*func)(struct rcu_head *rhp),
+			      call_rcu_func_t crf)
+{
+	struct rcu_head_remote rhr;
+
+	rhr.rhp = rhp;
+	rhr.crf = crf;
+	rhr.func = func;
+	smp_call_function_single(0, call_rcu_local, &rhr, 1);
+}
+
+/*
+ * Helper functions to be passed to wait_rcu_gp(), each of which
+ * invokes invoke_crf_remote() to register a callback appropriately.
+ */
+static void __maybe_unused
+call_rcu_preempt_remote(struct rcu_head *rhp,
+			void (*func)(struct rcu_head *rhp))
+{
+	invoke_crf_remote(rhp, func, call_rcu);
+}
+static void call_rcu_bh_remote(struct rcu_head *rhp,
+			       void (*func)(struct rcu_head *rhp))
+{
+	invoke_crf_remote(rhp, func, call_rcu_bh);
+}
+static void call_rcu_sched_remote(struct rcu_head *rhp,
+				  void (*func)(struct rcu_head *rhp))
+{
+	invoke_crf_remote(rhp, func, call_rcu_sched);
+}
+
+/*
+ * Per-rcu_data kthread, but only for no-CBs CPUs.  Each kthread invokes
+ * callbacks queued by the corresponding no-CBs CPU.
+ */
+static int rcu_nocb_kthread(void *arg)
+{
+	int c, cl;
+	struct rcu_head *list;
+	struct rcu_head *next;
+	struct rcu_head **tail;
+	struct rcu_data *rdp = arg;
+
+	/* Each pass through this loop invokes one batch of callbacks */
+	for (;;) {
+		/* If not polling, wait for next batch of callbacks. */
+		if (!rcu_nocb_poll)
+			wait_event(rdp->nocb_wq, rdp->nocb_head);
+		list = ACCESS_ONCE(rdp->nocb_head);
+		if (!list) {
+			schedule_timeout_interruptible(1);
+			continue;
+		}
+
+		/*
+		 * Extract queued callbacks, update counts, and wait
+		 * for a grace period to elapse.
+		 */
+		ACCESS_ONCE(rdp->nocb_head) = NULL;
+		tail = xchg(&rdp->nocb_tail, &rdp->nocb_head);
+		c = atomic_long_xchg(&rdp->nocb_q_count, 0);
+		cl = atomic_long_xchg(&rdp->nocb_q_count_lazy, 0);
+		ACCESS_ONCE(rdp->nocb_p_count) += c;
+		ACCESS_ONCE(rdp->nocb_p_count_lazy) += cl;
+		wait_rcu_gp(rdp->rsp->call_remote);
+
+		/* Each pass through the following loop invokes a callback. */
+		trace_rcu_batch_start(rdp->rsp->name, cl, c, -1);
+		c = cl = 0;
+		while (list) {
+			next = list->next;
+			/* Wait for enqueuing to complete, if needed. */
+			while (next == NULL && &list->next != tail) {
+				schedule_timeout_interruptible(1);
+				next = list->next;
+			}
+			debug_rcu_head_unqueue(list);
+			local_bh_disable();
+			if (__rcu_reclaim(rdp->rsp->name, list))
+				cl++;
+			c++;
+			local_bh_enable();
+			list = next;
+		}
+		trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1);
+		ACCESS_ONCE(rdp->nocb_p_count) -= c;
+		ACCESS_ONCE(rdp->nocb_p_count_lazy) -= cl;
+		rdp->n_cbs_invoked += c;
+	}
+	return 0;
+}
+
+/* Initialize per-rcu_data variables for no-CBs CPUs. */
+static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
+{
+	rdp->nocb_tail = &rdp->nocb_head;
+	init_waitqueue_head(&rdp->nocb_wq);
+}
+
+/* Create a kthread for each RCU flavor for each no-CBs CPU. */
+static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
+{
+	int cpu;
+	struct rcu_data *rdp;
+	struct task_struct *t;
+
+	if (rcu_nocb_mask == NULL)
+		return;
+	for_each_cpu(cpu, rcu_nocb_mask) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		t = kthread_run(rcu_nocb_kthread, rdp, "rcuo%d", cpu);
+		BUG_ON(IS_ERR(t));
+		ACCESS_ONCE(rdp->nocb_kthread) = t;
+	}
+}
+
+/* Prevent __call_rcu() from enqueuing callbacks on no-CBs CPUs */
+static void init_nocb_callback_list(struct rcu_data *rdp)
+{
+	if (rcu_nocb_mask == NULL ||
+	    !cpumask_test_cpu(rdp->cpu, rcu_nocb_mask))
+		return;
+	rdp->nxttail[RCU_NEXT_TAIL] = NULL;
+}
+
+/* Initialize the ->call_remote fields in the rcu_state structures. */
+static void __init rcu_init_nocb(void)
+{
+#ifdef CONFIG_PREEMPT_RCU
+	rcu_preempt_state.call_remote = call_rcu_preempt_remote;
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+	rcu_bh_state.call_remote = call_rcu_bh_remote;
+	rcu_sched_state.call_remote = call_rcu_sched_remote;
+}
+
+#else /* #ifdef CONFIG_RCU_NOCB_CPU */
+
+static bool is_nocb_cpu(int cpu)
+{
+	return false;
+}
+
+static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
+			    bool lazy)
+{
+	return 0;
+}
+
+static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+						     struct rcu_data *rdp)
+{
+	return 0;
+}
+
+static bool nocb_cpu_expendable(int cpu)
+{
+	return 1;
+}
+
+static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
+{
+}
+
+static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
+{
+}
+
+static void init_nocb_callback_list(struct rcu_data *rdp)
+{
+}
+
+static void __init rcu_init_nocb(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index f9512687a6e5..3189f9aa3e84 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -113,6 +113,8 @@ static char convert_kthread_status(unsigned int kthread_status)
 
 static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 {
+	long ql, qll;
+
 	if (!rdp->beenonline)
 		return;
 	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d qp=%d",
@@ -126,8 +128,11 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
 	seq_printf(m, " of=%lu", rdp->offline_fqs);
+	rcu_nocb_q_lengths(rdp, &ql, &qll);
+	qll += rdp->qlen_lazy;
+	ql += rdp->qlen;
 	seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c",
-		   rdp->qlen_lazy, rdp->qlen,
+		   qll, ql,
 		   ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
 			rdp->nxttail[RCU_NEXT_TAIL]],
 		   ".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
-- 
cgit v1.2.3-55-g7522


From 7583fe778f77cbeb37f54ff5b9afd96119fcab43 Mon Sep 17 00:00:00 2001
From: Piotr Haber
Date: Thu, 8 Nov 2012 09:47:27 +0100
Subject: ssb: fix SPROM offset

Offset for temperature compensation
values is wrong in ssb SPROMv8 map.

Reviewed-by: Pieter-Paul Giesberts <pieterpg@broadcom.com>
Reviewed-by: Arend van Spriel <arend@broadcom.com>
Signed-off-by: Piotr Haber <phaber@broadcom.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/linux/ssb/ssb_regs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h
index a0525019e1d1..6ecfa02ddbac 100644
--- a/include/linux/ssb/ssb_regs.h
+++ b/include/linux/ssb/ssb_regs.h
@@ -485,7 +485,7 @@
 #define  SSB_SPROM8_HWIQ_IQSWP_IQCAL_SWP_SHIFT	4
 #define  SSB_SPROM8_HWIQ_IQSWP_HW_IQCAL	0x0020
 #define  SSB_SPROM8_HWIQ_IQSWP_HW_IQCAL_SHIFT	5
-#define SSB_SPROM8_TEMPDELTA		0x00BA
+#define SSB_SPROM8_TEMPDELTA		0x00BC
 #define  SSB_SPROM8_TEMPDELTA_PHYCAL	0x00ff
 #define  SSB_SPROM8_TEMPDELTA_PHYCAL_SHIFT	0
 #define  SSB_SPROM8_TEMPDELTA_PERIOD	0x0f00
-- 
cgit v1.2.3-55-g7522


From 7dbce021a6df9d4812385d11729140829abc3f95 Mon Sep 17 00:00:00 2001
From: Samuel Iglesias Gonsalvez
Date: Fri, 16 Nov 2012 19:33:45 +0100
Subject: ipack: move header files to include/linux

Move ipack header files to include/linux/ directory where they belong.

Signed-off-by: Samuel Iglesias Gonsalvez <siglesias@igalia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/ipack/carriers/tpci200.h |   3 +-
 drivers/ipack/devices/ipoctal.c  |   3 +-
 drivers/ipack/ipack.c            |   3 +-
 drivers/ipack/ipack.h            | 215 ---------------------------------------
 include/linux/ipack.h            | 213 ++++++++++++++++++++++++++++++++++++++
 5 files changed, 218 insertions(+), 219 deletions(-)
 delete mode 100644 drivers/ipack/ipack.h
 create mode 100644 include/linux/ipack.h

(limited to 'include')

diff --git a/drivers/ipack/carriers/tpci200.h b/drivers/ipack/carriers/tpci200.h
index 8d9be277b34d..a7a151dab83c 100644
--- a/drivers/ipack/carriers/tpci200.h
+++ b/drivers/ipack/carriers/tpci200.h
@@ -20,8 +20,7 @@
 #include <linux/spinlock.h>
 #include <linux/swab.h>
 #include <linux/io.h>
-
-#include "../ipack.h"
+#include <linux/ipack.h>
 
 #define TPCI200_NB_SLOT               0x4
 #define TPCI200_NB_BAR                0x6
diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c
index 783f120338d1..7f568e268a1e 100644
--- a/drivers/ipack/devices/ipoctal.c
+++ b/drivers/ipack/devices/ipoctal.c
@@ -22,7 +22,8 @@
 #include <linux/slab.h>
 #include <linux/atomic.h>
 #include <linux/io.h>
-#include "../ipack.h"
+#include <linux/ipack.h>
+#include "../ipack_ids.h"
 #include "ipoctal.h"
 #include "scc2698.h"
 
diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c
index 6d5079de52b9..cc5498347acb 100644
--- a/drivers/ipack/ipack.c
+++ b/drivers/ipack/ipack.c
@@ -13,7 +13,8 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/io.h>
-#include "ipack.h"
+#include <linux/ipack.h>
+#include "ipack_ids.h"
 
 #define to_ipack_dev(device) container_of(device, struct ipack_device, dev)
 #define to_ipack_driver(drv) container_of(drv, struct ipack_driver, driver)
diff --git a/drivers/ipack/ipack.h b/drivers/ipack/ipack.h
deleted file mode 100644
index 6760bfaf0ac4..000000000000
--- a/drivers/ipack/ipack.h
+++ /dev/null
@@ -1,215 +0,0 @@
-/*
- * Industry-pack bus.
- *
- * Copyright (C) 2011-2012 CERN (www.cern.ch)
- * Author: Samuel Iglesias Gonsalvez <siglesias@igalia.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; version 2 of the License.
- */
-
-#include <linux/mod_devicetable.h>
-#include <linux/device.h>
-#include <linux/interrupt.h>
-
-#include "ipack_ids.h"
-
-#define IPACK_IDPROM_OFFSET_I			0x01
-#define IPACK_IDPROM_OFFSET_P			0x03
-#define IPACK_IDPROM_OFFSET_A			0x05
-#define IPACK_IDPROM_OFFSET_C			0x07
-#define IPACK_IDPROM_OFFSET_MANUFACTURER_ID	0x09
-#define IPACK_IDPROM_OFFSET_MODEL		0x0B
-#define IPACK_IDPROM_OFFSET_REVISION		0x0D
-#define IPACK_IDPROM_OFFSET_RESERVED		0x0F
-#define IPACK_IDPROM_OFFSET_DRIVER_ID_L		0x11
-#define IPACK_IDPROM_OFFSET_DRIVER_ID_H		0x13
-#define IPACK_IDPROM_OFFSET_NUM_BYTES		0x15
-#define IPACK_IDPROM_OFFSET_CRC			0x17
-
-struct ipack_bus_ops;
-struct ipack_driver;
-
-enum ipack_space {
-	IPACK_IO_SPACE    = 0,
-	IPACK_ID_SPACE,
-	IPACK_INT_SPACE,
-	IPACK_MEM8_SPACE,
-	IPACK_MEM16_SPACE,
-	/* Dummy for counting the number of entries.  Must remain the last
-	 * entry */
-	IPACK_SPACE_COUNT,
-};
-
-/**
- */
-struct ipack_region {
-	phys_addr_t start;
-	size_t      size;
-};
-
-/**
- *	struct ipack_device
- *
- *	@slot: Slot where the device is plugged in the carrier board
- *	@bus: ipack_bus_device where the device is plugged to.
- *	@id_space: Virtual address to ID space.
- *	@io_space: Virtual address to IO space.
- *	@mem_space: Virtual address to MEM space.
- *	@dev: device in kernel representation.
- *
- * Warning: Direct access to mapped memory is possible but the endianness
- * is not the same with PCI carrier or VME carrier. The endianness is managed
- * by the carrier board throught bus->ops.
- */
-struct ipack_device {
-	unsigned int slot;
-	struct ipack_bus_device *bus;
-	struct device dev;
-	void (*release) (struct ipack_device *dev);
-	struct ipack_region      region[IPACK_SPACE_COUNT];
-	u8                      *id;
-	size_t			 id_avail;
-	u32			 id_vendor;
-	u32			 id_device;
-	u8			 id_format;
-	unsigned int		 id_crc_correct:1;
-	unsigned int		 speed_8mhz:1;
-	unsigned int		 speed_32mhz:1;
-};
-
-/**
- * struct ipack_driver_ops -- Callbacks to IPack device driver
- *
- * @probe:  Probe function
- * @remove: Prepare imminent removal of the device.  Services provided by the
- *          device should be revoked.
- */
-
-struct ipack_driver_ops {
-	int (*probe) (struct ipack_device *dev);
-	void (*remove) (struct ipack_device *dev);
-};
-
-/**
- * struct ipack_driver -- Specific data to each ipack device driver
- *
- * @driver: Device driver kernel representation
- * @ops:    Callbacks provided by the IPack device driver
- */
-struct ipack_driver {
-	struct device_driver driver;
-	const struct ipack_device_id *id_table;
-	const struct ipack_driver_ops *ops;
-};
-
-/**
- *	struct ipack_bus_ops - available operations on a bridge module
- *
- *	@map_space: map IP address space
- *	@unmap_space: unmap IP address space
- *	@request_irq: request IRQ
- *	@free_irq: free IRQ
- *	@get_clockrate: Returns the clockrate the carrier is currently
- *		communicating with the device at.
- *	@set_clockrate: Sets the clock-rate for carrier / module communication.
- *		Should return -EINVAL if the requested speed is not supported.
- *	@get_error: Returns the error state for the slot the device is attached
- *		to.
- *	@get_timeout: Returns 1 if the communication with the device has
- *		previously timed out.
- *	@reset_timeout: Resets the state returned by get_timeout.
- */
-struct ipack_bus_ops {
-	int (*request_irq) (struct ipack_device *dev,
-			    irqreturn_t (*handler)(void *), void *arg);
-	int (*free_irq) (struct ipack_device *dev);
-	int (*get_clockrate) (struct ipack_device *dev);
-	int (*set_clockrate) (struct ipack_device *dev, int mherz);
-	int (*get_error) (struct ipack_device *dev);
-	int (*get_timeout) (struct ipack_device *dev);
-	int (*reset_timeout) (struct ipack_device *dev);
-};
-
-/**
- *	struct ipack_bus_device
- *
- *	@dev: pointer to carrier device
- *	@slots: number of slots available
- *	@bus_nr: ipack bus number
- *	@ops: bus operations for the mezzanine drivers
- */
-struct ipack_bus_device {
-	struct device *parent;
-	int slots;
-	int bus_nr;
-	const struct ipack_bus_ops *ops;
-};
-
-/**
- *	ipack_bus_register -- register a new ipack bus
- *
- * @parent: pointer to the parent device, if any.
- * @slots: number of slots available in the bus device.
- * @ops: bus operations for the mezzanine drivers.
- *
- * The carrier board device should call this function to register itself as
- * available bus device in ipack.
- */
-struct ipack_bus_device *ipack_bus_register(struct device *parent, int slots,
-					    const struct ipack_bus_ops *ops);
-
-/**
- *	ipack_bus_unregister -- unregister an ipack bus
- */
-int ipack_bus_unregister(struct ipack_bus_device *bus);
-
-/**
- * ipack_driver_register -- Register a new ipack device driver
- *
- * Called by a ipack driver to register itself as a driver
- * that can manage ipack devices.
- */
-int ipack_driver_register(struct ipack_driver *edrv, struct module *owner,
-			  const char *name);
-void ipack_driver_unregister(struct ipack_driver *edrv);
-
-/**
- *	ipack_device_register -- register an IPack device with the kernel
- *	@dev: the new device to register.
- *
- *	Register a new IPack device ("module" in IndustryPack jargon). The call
- *	is done by the carrier driver.  The carrier should populate the fields
- *	bus and slot as well as the region array of @dev prior to calling this
- *	function.  The rest of the fields will be allocated and populated
- *	during registration.
- *
- *	Return zero on success or error code on failure.
- */
-int ipack_device_register(struct ipack_device *dev);
-void ipack_device_unregister(struct ipack_device *dev);
-
-/**
- * DEFINE_IPACK_DEVICE_TABLE - macro used to describe a IndustryPack table
- * @_table: device table name
- *
- * This macro is used to create a struct ipack_device_id array (a device table)
- * in a generic manner.
- */
-#define DEFINE_IPACK_DEVICE_TABLE(_table) \
-	const struct ipack_device_id _table[] __devinitconst
-
-/**
- * IPACK_DEVICE - macro used to describe a specific IndustryPack device
- * @_format: the format version (currently either 1 or 2, 8 bit value)
- * @vend:    the 8 or 24 bit IndustryPack Vendor ID
- * @dev:     the 8 or 16  bit IndustryPack Device ID
- *
- * This macro is used to create a struct ipack_device_id that matches a specific
- * device.
- */
-#define IPACK_DEVICE(_format, vend, dev) \
-	 .format = (_format), \
-	 .vendor = (vend), \
-	 .device = (dev)
diff --git a/include/linux/ipack.h b/include/linux/ipack.h
new file mode 100644
index 000000000000..7a0a3085ab5b
--- /dev/null
+++ b/include/linux/ipack.h
@@ -0,0 +1,213 @@
+/*
+ * Industry-pack bus.
+ *
+ * Copyright (C) 2011-2012 CERN (www.cern.ch)
+ * Author: Samuel Iglesias Gonsalvez <siglesias@igalia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; version 2 of the License.
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+
+#define IPACK_IDPROM_OFFSET_I			0x01
+#define IPACK_IDPROM_OFFSET_P			0x03
+#define IPACK_IDPROM_OFFSET_A			0x05
+#define IPACK_IDPROM_OFFSET_C			0x07
+#define IPACK_IDPROM_OFFSET_MANUFACTURER_ID	0x09
+#define IPACK_IDPROM_OFFSET_MODEL		0x0B
+#define IPACK_IDPROM_OFFSET_REVISION		0x0D
+#define IPACK_IDPROM_OFFSET_RESERVED		0x0F
+#define IPACK_IDPROM_OFFSET_DRIVER_ID_L		0x11
+#define IPACK_IDPROM_OFFSET_DRIVER_ID_H		0x13
+#define IPACK_IDPROM_OFFSET_NUM_BYTES		0x15
+#define IPACK_IDPROM_OFFSET_CRC			0x17
+
+struct ipack_bus_ops;
+struct ipack_driver;
+
+enum ipack_space {
+	IPACK_IO_SPACE    = 0,
+	IPACK_ID_SPACE,
+	IPACK_INT_SPACE,
+	IPACK_MEM8_SPACE,
+	IPACK_MEM16_SPACE,
+	/* Dummy for counting the number of entries.  Must remain the last
+	 * entry */
+	IPACK_SPACE_COUNT,
+};
+
+/**
+ */
+struct ipack_region {
+	phys_addr_t start;
+	size_t      size;
+};
+
+/**
+ *	struct ipack_device
+ *
+ *	@slot: Slot where the device is plugged in the carrier board
+ *	@bus: ipack_bus_device where the device is plugged to.
+ *	@id_space: Virtual address to ID space.
+ *	@io_space: Virtual address to IO space.
+ *	@mem_space: Virtual address to MEM space.
+ *	@dev: device in kernel representation.
+ *
+ * Warning: Direct access to mapped memory is possible but the endianness
+ * is not the same with PCI carrier or VME carrier. The endianness is managed
+ * by the carrier board throught bus->ops.
+ */
+struct ipack_device {
+	unsigned int slot;
+	struct ipack_bus_device *bus;
+	struct device dev;
+	void (*release) (struct ipack_device *dev);
+	struct ipack_region      region[IPACK_SPACE_COUNT];
+	u8                      *id;
+	size_t			 id_avail;
+	u32			 id_vendor;
+	u32			 id_device;
+	u8			 id_format;
+	unsigned int		 id_crc_correct:1;
+	unsigned int		 speed_8mhz:1;
+	unsigned int		 speed_32mhz:1;
+};
+
+/**
+ * struct ipack_driver_ops -- Callbacks to IPack device driver
+ *
+ * @probe:  Probe function
+ * @remove: Prepare imminent removal of the device.  Services provided by the
+ *          device should be revoked.
+ */
+
+struct ipack_driver_ops {
+	int (*probe) (struct ipack_device *dev);
+	void (*remove) (struct ipack_device *dev);
+};
+
+/**
+ * struct ipack_driver -- Specific data to each ipack device driver
+ *
+ * @driver: Device driver kernel representation
+ * @ops:    Callbacks provided by the IPack device driver
+ */
+struct ipack_driver {
+	struct device_driver driver;
+	const struct ipack_device_id *id_table;
+	const struct ipack_driver_ops *ops;
+};
+
+/**
+ *	struct ipack_bus_ops - available operations on a bridge module
+ *
+ *	@map_space: map IP address space
+ *	@unmap_space: unmap IP address space
+ *	@request_irq: request IRQ
+ *	@free_irq: free IRQ
+ *	@get_clockrate: Returns the clockrate the carrier is currently
+ *		communicating with the device at.
+ *	@set_clockrate: Sets the clock-rate for carrier / module communication.
+ *		Should return -EINVAL if the requested speed is not supported.
+ *	@get_error: Returns the error state for the slot the device is attached
+ *		to.
+ *	@get_timeout: Returns 1 if the communication with the device has
+ *		previously timed out.
+ *	@reset_timeout: Resets the state returned by get_timeout.
+ */
+struct ipack_bus_ops {
+	int (*request_irq) (struct ipack_device *dev,
+			    irqreturn_t (*handler)(void *), void *arg);
+	int (*free_irq) (struct ipack_device *dev);
+	int (*get_clockrate) (struct ipack_device *dev);
+	int (*set_clockrate) (struct ipack_device *dev, int mherz);
+	int (*get_error) (struct ipack_device *dev);
+	int (*get_timeout) (struct ipack_device *dev);
+	int (*reset_timeout) (struct ipack_device *dev);
+};
+
+/**
+ *	struct ipack_bus_device
+ *
+ *	@dev: pointer to carrier device
+ *	@slots: number of slots available
+ *	@bus_nr: ipack bus number
+ *	@ops: bus operations for the mezzanine drivers
+ */
+struct ipack_bus_device {
+	struct device *parent;
+	int slots;
+	int bus_nr;
+	const struct ipack_bus_ops *ops;
+};
+
+/**
+ *	ipack_bus_register -- register a new ipack bus
+ *
+ * @parent: pointer to the parent device, if any.
+ * @slots: number of slots available in the bus device.
+ * @ops: bus operations for the mezzanine drivers.
+ *
+ * The carrier board device should call this function to register itself as
+ * available bus device in ipack.
+ */
+struct ipack_bus_device *ipack_bus_register(struct device *parent, int slots,
+					    const struct ipack_bus_ops *ops);
+
+/**
+ *	ipack_bus_unregister -- unregister an ipack bus
+ */
+int ipack_bus_unregister(struct ipack_bus_device *bus);
+
+/**
+ * ipack_driver_register -- Register a new ipack device driver
+ *
+ * Called by a ipack driver to register itself as a driver
+ * that can manage ipack devices.
+ */
+int ipack_driver_register(struct ipack_driver *edrv, struct module *owner,
+			  const char *name);
+void ipack_driver_unregister(struct ipack_driver *edrv);
+
+/**
+ *	ipack_device_register -- register an IPack device with the kernel
+ *	@dev: the new device to register.
+ *
+ *	Register a new IPack device ("module" in IndustryPack jargon). The call
+ *	is done by the carrier driver.  The carrier should populate the fields
+ *	bus and slot as well as the region array of @dev prior to calling this
+ *	function.  The rest of the fields will be allocated and populated
+ *	during registration.
+ *
+ *	Return zero on success or error code on failure.
+ */
+int ipack_device_register(struct ipack_device *dev);
+void ipack_device_unregister(struct ipack_device *dev);
+
+/**
+ * DEFINE_IPACK_DEVICE_TABLE - macro used to describe a IndustryPack table
+ * @_table: device table name
+ *
+ * This macro is used to create a struct ipack_device_id array (a device table)
+ * in a generic manner.
+ */
+#define DEFINE_IPACK_DEVICE_TABLE(_table) \
+	const struct ipack_device_id _table[] __devinitconst
+
+/**
+ * IPACK_DEVICE - macro used to describe a specific IndustryPack device
+ * @_format: the format version (currently either 1 or 2, 8 bit value)
+ * @vend:    the 8 or 24 bit IndustryPack Vendor ID
+ * @dev:     the 8 or 16  bit IndustryPack Device ID
+ *
+ * This macro is used to create a struct ipack_device_id that matches a specific
+ * device.
+ */
+#define IPACK_DEVICE(_format, vend, dev) \
+	 .format = (_format), \
+	 .vendor = (vend), \
+	 .device = (dev)
-- 
cgit v1.2.3-55-g7522


From 27cf2d1b873fc50a2c0388253ec666fa4c61bfd4 Mon Sep 17 00:00:00 2001
From: Samuel Iglesias Gonsalvez
Date: Fri, 16 Nov 2012 19:33:46 +0100
Subject: ipack: remove ipack_ids.h file

Its contents are merged into ipack.h. So this file is not needed.

Doing that, it simplifies the ipack-related driver development.

Signed-off-by: Samuel Iglesias Gonsalvez <siglesias@igalia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/ipack/devices/ipoctal.c |  1 -
 drivers/ipack/ipack.c           |  1 -
 drivers/ipack/ipack_ids.h       | 32 --------------------------------
 include/linux/ipack.h           | 33 +++++++++++++++++++++++++++++++++
 4 files changed, 33 insertions(+), 34 deletions(-)
 delete mode 100644 drivers/ipack/ipack_ids.h

(limited to 'include')

diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c
index 7f568e268a1e..c06ab396e84f 100644
--- a/drivers/ipack/devices/ipoctal.c
+++ b/drivers/ipack/devices/ipoctal.c
@@ -23,7 +23,6 @@
 #include <linux/atomic.h>
 #include <linux/io.h>
 #include <linux/ipack.h>
-#include "../ipack_ids.h"
 #include "ipoctal.h"
 #include "scc2698.h"
 
diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c
index cc5498347acb..7ec6b208b1cb 100644
--- a/drivers/ipack/ipack.c
+++ b/drivers/ipack/ipack.c
@@ -14,7 +14,6 @@
 #include <linux/idr.h>
 #include <linux/io.h>
 #include <linux/ipack.h>
-#include "ipack_ids.h"
 
 #define to_ipack_dev(device) container_of(device, struct ipack_device, dev)
 #define to_ipack_driver(drv) container_of(drv, struct ipack_driver, driver)
diff --git a/drivers/ipack/ipack_ids.h b/drivers/ipack/ipack_ids.h
deleted file mode 100644
index 8153fee3f2f7..000000000000
--- a/drivers/ipack/ipack_ids.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * IndustryPack Fromat, Vendor and Device IDs.
- */
-
-/* ID section format versions */
-#define IPACK_ID_VERSION_INVALID	0x00
-#define IPACK_ID_VERSION_1		0x01
-#define IPACK_ID_VERSION_2		0x02
-
-/* Vendors and devices. Sort key: vendor first, device next. */
-#define IPACK1_VENDOR_ID_RESERVED1	0x00
-#define IPACK1_VENDOR_ID_RESERVED2	0xFF
-#define IPACK1_VENDOR_ID_UNREGISTRED01	0x01
-#define IPACK1_VENDOR_ID_UNREGISTRED02	0x02
-#define IPACK1_VENDOR_ID_UNREGISTRED03	0x03
-#define IPACK1_VENDOR_ID_UNREGISTRED04	0x04
-#define IPACK1_VENDOR_ID_UNREGISTRED05	0x05
-#define IPACK1_VENDOR_ID_UNREGISTRED06	0x06
-#define IPACK1_VENDOR_ID_UNREGISTRED07	0x07
-#define IPACK1_VENDOR_ID_UNREGISTRED08	0x08
-#define IPACK1_VENDOR_ID_UNREGISTRED09	0x09
-#define IPACK1_VENDOR_ID_UNREGISTRED10	0x0A
-#define IPACK1_VENDOR_ID_UNREGISTRED11	0x0B
-#define IPACK1_VENDOR_ID_UNREGISTRED12	0x0C
-#define IPACK1_VENDOR_ID_UNREGISTRED13	0x0D
-#define IPACK1_VENDOR_ID_UNREGISTRED14	0x0E
-#define IPACK1_VENDOR_ID_UNREGISTRED15	0x0F
-
-#define IPACK1_VENDOR_ID_SBS            0xF0
-#define IPACK1_DEVICE_ID_SBS_OCTAL_232  0x22
-#define IPACK1_DEVICE_ID_SBS_OCTAL_422  0x2A
-#define IPACK1_DEVICE_ID_SBS_OCTAL_485  0x48
diff --git a/include/linux/ipack.h b/include/linux/ipack.h
index 7a0a3085ab5b..a360c73129a6 100644
--- a/include/linux/ipack.h
+++ b/include/linux/ipack.h
@@ -26,6 +26,39 @@
 #define IPACK_IDPROM_OFFSET_NUM_BYTES		0x15
 #define IPACK_IDPROM_OFFSET_CRC			0x17
 
+/*
+ * IndustryPack Fromat, Vendor and Device IDs.
+ */
+
+/* ID section format versions */
+#define IPACK_ID_VERSION_INVALID	0x00
+#define IPACK_ID_VERSION_1		0x01
+#define IPACK_ID_VERSION_2		0x02
+
+/* Vendors and devices. Sort key: vendor first, device next. */
+#define IPACK1_VENDOR_ID_RESERVED1	0x00
+#define IPACK1_VENDOR_ID_RESERVED2	0xFF
+#define IPACK1_VENDOR_ID_UNREGISTRED01	0x01
+#define IPACK1_VENDOR_ID_UNREGISTRED02	0x02
+#define IPACK1_VENDOR_ID_UNREGISTRED03	0x03
+#define IPACK1_VENDOR_ID_UNREGISTRED04	0x04
+#define IPACK1_VENDOR_ID_UNREGISTRED05	0x05
+#define IPACK1_VENDOR_ID_UNREGISTRED06	0x06
+#define IPACK1_VENDOR_ID_UNREGISTRED07	0x07
+#define IPACK1_VENDOR_ID_UNREGISTRED08	0x08
+#define IPACK1_VENDOR_ID_UNREGISTRED09	0x09
+#define IPACK1_VENDOR_ID_UNREGISTRED10	0x0A
+#define IPACK1_VENDOR_ID_UNREGISTRED11	0x0B
+#define IPACK1_VENDOR_ID_UNREGISTRED12	0x0C
+#define IPACK1_VENDOR_ID_UNREGISTRED13	0x0D
+#define IPACK1_VENDOR_ID_UNREGISTRED14	0x0E
+#define IPACK1_VENDOR_ID_UNREGISTRED15	0x0F
+
+#define IPACK1_VENDOR_ID_SBS            0xF0
+#define IPACK1_DEVICE_ID_SBS_OCTAL_232  0x22
+#define IPACK1_DEVICE_ID_SBS_OCTAL_422  0x2A
+#define IPACK1_DEVICE_ID_SBS_OCTAL_485  0x48
+
 struct ipack_bus_ops;
 struct ipack_driver;
 
-- 
cgit v1.2.3-55-g7522


From 404525d5a7ecc847b5ac178dad96402f1e102ccc Mon Sep 17 00:00:00 2001
From: Maxime Ripard
Date: Fri, 16 Nov 2012 21:21:43 +0100
Subject: clk: sunxi: Add dummy fixed rate clock for Allwinner A1X SoCs

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Cc: Mike Turquette <mturquette@ti.com>
---
 drivers/clk/Makefile      |  1 +
 drivers/clk/clk-sunxi.c   | 30 ++++++++++++++++++++++++++++++
 include/linux/clk/sunxi.h | 22 ++++++++++++++++++++++
 3 files changed, 53 insertions(+)
 create mode 100644 drivers/clk/clk-sunxi.c
 create mode 100644 include/linux/clk/sunxi.h

(limited to 'include')

diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 71a25b91de00..9c300a828ede 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -19,6 +19,7 @@ endif
 obj-$(CONFIG_MACH_LOONGSON1)	+= clk-ls1x.o
 obj-$(CONFIG_ARCH_U8500)	+= ux500/
 obj-$(CONFIG_ARCH_VT8500)	+= clk-vt8500.o
+obj-$(CONFIG_ARCH_SUNXI)	+= clk-sunxi.o
 
 # Chip specific
 obj-$(CONFIG_COMMON_CLK_WM831X) += clk-wm831x.o
diff --git a/drivers/clk/clk-sunxi.c b/drivers/clk/clk-sunxi.c
new file mode 100644
index 000000000000..0e831b584ba7
--- /dev/null
+++ b/drivers/clk/clk-sunxi.c
@@ -0,0 +1,30 @@
+/*
+ * Copyright 2012 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/clk/sunxi.h>
+#include <linux/of.h>
+
+static const __initconst struct of_device_id clk_match[] = {
+	{ .compatible = "fixed-clock", .data = of_fixed_clk_setup, },
+	{}
+};
+
+void __init sunxi_init_clocks(void)
+{
+	of_clk_init(clk_match);
+}
diff --git a/include/linux/clk/sunxi.h b/include/linux/clk/sunxi.h
new file mode 100644
index 000000000000..e074fdd5a236
--- /dev/null
+++ b/include/linux/clk/sunxi.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright 2012 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_CLK_SUNXI_H_
+#define __LINUX_CLK_SUNXI_H_
+
+void __init sunxi_init_clocks(void);
+
+#endif
-- 
cgit v1.2.3-55-g7522


From b2ac5d7549710173ea0217bf8c7b3f71da5220d4 Mon Sep 17 00:00:00 2001
From: Maxime Ripard
Date: Mon, 12 Nov 2012 15:07:50 +0100
Subject: clocksource: sunxi: Add Allwinner A1X Timer Driver

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: John Stultz <johnstul@us.ibm.com>
---
 .../bindings/timer/allwinner,sunxi-timer.txt       |  17 +++
 drivers/clocksource/Kconfig                        |   3 +
 drivers/clocksource/Makefile                       |   1 +
 drivers/clocksource/sunxi_timer.c                  | 170 +++++++++++++++++++++
 include/linux/sunxi_timer.h                        |  24 +++
 5 files changed, 215 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/timer/allwinner,sunxi-timer.txt
 create mode 100644 drivers/clocksource/sunxi_timer.c
 create mode 100644 include/linux/sunxi_timer.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/timer/allwinner,sunxi-timer.txt b/Documentation/devicetree/bindings/timer/allwinner,sunxi-timer.txt
new file mode 100644
index 000000000000..0c7b64e95a61
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/allwinner,sunxi-timer.txt
@@ -0,0 +1,17 @@
+Allwinner A1X SoCs Timer Controller
+
+Required properties:
+
+- compatible : should be "allwinner,sunxi-timer"
+- reg : Specifies base physical address and size of the registers.
+- interrupts : The interrupt of the first timer
+- clocks: phandle to the source clock (usually a 24 MHz fixed clock)
+
+Example:
+
+timer {
+	compatible = "allwinner,sunxi-timer";
+	reg = <0x01c20c00 0x400>;
+	interrupts = <22>;
+	clocks = <&osc>;
+};
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 6a78073c3808..a0985732f1e2 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -22,6 +22,9 @@ config DW_APB_TIMER_OF
 config ARMADA_370_XP_TIMER
 	bool
 
+config SUNXI_TIMER
+	bool
+
 config CLKSRC_DBX500_PRCMU
 	bool "Clocksource PRCMU Timer"
 	depends on UX500_SOC_DB8500
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 603be366f762..36f06de4c5ab 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -14,5 +14,6 @@ obj-$(CONFIG_DW_APB_TIMER_OF)	+= dw_apb_timer_of.o
 obj-$(CONFIG_CLKSRC_DBX500_PRCMU)	+= clksrc-dbx500-prcmu.o
 obj-$(CONFIG_ARMADA_370_XP_TIMER)	+= time-armada-370-xp.o
 obj-$(CONFIG_ARCH_BCM2835)	+= bcm2835_timer.o
+obj-$(CONFIG_SUNXI_TIMER)	+= sunxi_timer.o
 
 obj-$(CONFIG_CLKSRC_ARM_GENERIC)	+= arm_generic.o
diff --git a/drivers/clocksource/sunxi_timer.c b/drivers/clocksource/sunxi_timer.c
new file mode 100644
index 000000000000..3c46434b64cb
--- /dev/null
+++ b/drivers/clocksource/sunxi_timer.c
@@ -0,0 +1,170 @@
+/*
+ * Allwinner A1X SoCs timer handling.
+ *
+ * Copyright (C) 2012 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * Based on code from
+ * Allwinner Technology Co., Ltd. <www.allwinnertech.com>
+ * Benn Huang <benn@allwinnertech.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqreturn.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/sunxi_timer.h>
+#include <linux/clk/sunxi.h>
+
+#define TIMER_CTL_REG		0x00
+#define TIMER_CTL_ENABLE		(1 << 0)
+#define TIMER_IRQ_ST_REG	0x04
+#define TIMER0_CTL_REG		0x10
+#define TIMER0_CTL_ENABLE		(1 << 0)
+#define TIMER0_CTL_AUTORELOAD		(1 << 1)
+#define TIMER0_CTL_ONESHOT		(1 << 7)
+#define TIMER0_INTVAL_REG	0x14
+#define TIMER0_CNTVAL_REG	0x18
+
+#define TIMER_SCAL		16
+
+static void __iomem *timer_base;
+
+static void sunxi_clkevt_mode(enum clock_event_mode mode,
+			      struct clock_event_device *clk)
+{
+	u32 u = readl(timer_base + TIMER0_CTL_REG);
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		u &= ~(TIMER0_CTL_ONESHOT);
+		writel(u | TIMER0_CTL_ENABLE, timer_base + TIMER0_CTL_REG);
+		break;
+
+	case CLOCK_EVT_MODE_ONESHOT:
+		writel(u | TIMER0_CTL_ONESHOT, timer_base + TIMER0_CTL_REG);
+		break;
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	default:
+		writel(u & ~(TIMER0_CTL_ENABLE), timer_base + TIMER0_CTL_REG);
+		break;
+	}
+}
+
+static int sunxi_clkevt_next_event(unsigned long evt,
+				   struct clock_event_device *unused)
+{
+	u32 u = readl(timer_base + TIMER0_CTL_REG);
+	writel(evt, timer_base + TIMER0_CNTVAL_REG);
+	writel(u | TIMER0_CTL_ENABLE | TIMER0_CTL_AUTORELOAD,
+	       timer_base + TIMER0_CTL_REG);
+
+	return 0;
+}
+
+static struct clock_event_device sunxi_clockevent = {
+	.name = "sunxi_tick",
+	.shift = 32,
+	.rating = 300,
+	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_mode = sunxi_clkevt_mode,
+	.set_next_event = sunxi_clkevt_next_event,
+};
+
+
+static irqreturn_t sunxi_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = (struct clock_event_device *)dev_id;
+
+	writel(0x1, timer_base + TIMER_IRQ_ST_REG);
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction sunxi_timer_irq = {
+	.name = "sunxi_timer0",
+	.flags = IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.handler = sunxi_timer_interrupt,
+	.dev_id = &sunxi_clockevent,
+};
+
+static struct of_device_id sunxi_timer_dt_ids[] = {
+	{ .compatible = "allwinner,sunxi-timer" },
+};
+
+static void __init sunxi_timer_init(void)
+{
+	struct device_node *node;
+	unsigned long rate = 0;
+	struct clk *clk;
+	int ret, irq;
+	u32 val;
+
+	node = of_find_matching_node(NULL, sunxi_timer_dt_ids);
+	if (!node)
+		panic("No sunxi timer node");
+
+	timer_base = of_iomap(node, 0);
+	if (!timer_base)
+		panic("Can't map registers");
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (irq <= 0)
+		panic("Can't parse IRQ");
+
+	sunxi_init_clocks();
+
+	clk = of_clk_get(node, 0);
+	if (IS_ERR(clk))
+		panic("Can't get timer clock");
+
+	rate = clk_get_rate(clk);
+
+	writel(rate / (TIMER_SCAL * HZ),
+	       timer_base + TIMER0_INTVAL_REG);
+
+	/* set clock source to HOSC, 16 pre-division */
+	val = readl(timer_base + TIMER0_CTL_REG);
+	val &= ~(0x07 << 4);
+	val &= ~(0x03 << 2);
+	val |= (4 << 4) | (1 << 2);
+	writel(val, timer_base + TIMER0_CTL_REG);
+
+	/* set mode to auto reload */
+	val = readl(timer_base + TIMER0_CTL_REG);
+	writel(val | TIMER0_CTL_AUTORELOAD, timer_base + TIMER0_CTL_REG);
+
+	ret = setup_irq(irq, &sunxi_timer_irq);
+	if (ret)
+		pr_warn("failed to setup irq %d\n", irq);
+
+	/* Enable timer0 interrupt */
+	val = readl(timer_base + TIMER_CTL_REG);
+	writel(val | TIMER_CTL_ENABLE, timer_base + TIMER_CTL_REG);
+
+	sunxi_clockevent.mult = div_sc(rate / TIMER_SCAL,
+				NSEC_PER_SEC,
+				sunxi_clockevent.shift);
+	sunxi_clockevent.max_delta_ns = clockevent_delta2ns(0xff,
+							    &sunxi_clockevent);
+	sunxi_clockevent.min_delta_ns = clockevent_delta2ns(0x1,
+							    &sunxi_clockevent);
+	sunxi_clockevent.cpumask = cpumask_of(0);
+
+	clockevents_register_device(&sunxi_clockevent);
+}
+
+struct sys_timer sunxi_timer = {
+	.init = sunxi_timer_init,
+};
diff --git a/include/linux/sunxi_timer.h b/include/linux/sunxi_timer.h
new file mode 100644
index 000000000000..b9165bba6e61
--- /dev/null
+++ b/include/linux/sunxi_timer.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright 2012 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __SUNXI_TIMER_H
+#define __SUNXI_TIMER_H
+
+#include <asm/mach/time.h>
+
+extern struct sys_timer sunxi_timer;
+
+#endif
-- 
cgit v1.2.3-55-g7522


From afd24e146826cec0f46929263a0c874406a19cd8 Mon Sep 17 00:00:00 2001
From: Maxime Ripard
Date: Wed, 14 Nov 2012 09:59:14 +0100
Subject: irqchip: sunxi: Add irq controller driver

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
CC: Thomas Gleixner <tglx@linutronix.de>
---
 .../interrupt-controller/allwinner,sunxi-ic.txt    | 104 ++++++++++++++
 drivers/irqchip/Makefile                           |   1 +
 drivers/irqchip/irq-sunxi.c                        | 150 +++++++++++++++++++++
 include/linux/irqchip/sunxi.h                      |  27 ++++
 4 files changed, 282 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-ic.txt
 create mode 100644 drivers/irqchip/irq-sunxi.c
 create mode 100644 include/linux/irqchip/sunxi.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-ic.txt b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-ic.txt
new file mode 100644
index 000000000000..7f9fb85f5456
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-ic.txt
@@ -0,0 +1,104 @@
+Allwinner Sunxi Interrupt Controller
+
+Required properties:
+
+- compatible : should be "allwinner,sunxi-ic"
+- reg : Specifies base physical address and size of the registers.
+- interrupt-controller : Identifies the node as an interrupt controller
+- #interrupt-cells : Specifies the number of cells needed to encode an
+  interrupt source. The value shall be 1.
+
+The interrupt sources are as follows:
+
+0: ENMI
+1: UART0
+2: UART1
+3: UART2
+4: UART3
+5: IR0
+6: IR1
+7: I2C0
+8: I2C1
+9: I2C2
+10: SPI0
+11: SPI1
+12: SPI2
+13: SPDIF
+14: AC97
+15: TS
+16: I2S
+17: UART4
+18: UART5
+19: UART6
+20: UART7
+21: KEYPAD
+22: TIMER0
+23: TIMER1
+24: TIMER2
+25: TIMER3
+26: CAN
+27: DMA
+28: PIO
+29: TOUCH_PANEL
+30: AUDIO_CODEC
+31: LRADC
+32: SDMC0
+33: SDMC1
+34: SDMC2
+35: SDMC3
+36: MEMSTICK
+37: NAND
+38: USB0
+39: USB1
+40: USB2
+41: SCR
+42: CSI0
+43: CSI1
+44: LCDCTRL0
+45: LCDCTRL1
+46: MP
+47: DEFEBE0
+48: DEFEBE1
+49: PMU
+50: SPI3
+51: TZASC
+52: PATA
+53: VE
+54: SS
+55: EMAC
+56: SATA
+57: GPS
+58: HDMI
+59: TVE
+60: ACE
+61: TVD
+62: PS2_0
+63: PS2_1
+64: USB3
+65: USB4
+66: PLE_PFM
+67: TIMER4
+68: TIMER5
+69: GPU_GP
+70: GPU_GPMMU
+71: GPU_PP0
+72: GPU_PPMMU0
+73: GPU_PMU
+74: GPU_RSV0
+75: GPU_RSV1
+76: GPU_RSV2
+77: GPU_RSV3
+78: GPU_RSV4
+79: GPU_RSV5
+80: GPU_RSV6
+82: SYNC_TIMER0
+83: SYNC_TIMER1
+
+Example:
+
+intc: interrupt-controller {
+	compatible = "allwinner,sunxi-ic";
+	reg = <0x01c20400 0x400>;
+	interrupt-controller;
+	#interrupt-cells = <2>;
+};
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 054321db4350..2444d07544cd 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -1 +1,2 @@
 obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2835.o
+obj-$(CONFIG_ARCH_SUNXI)   += irq-sunxi.o
diff --git a/drivers/irqchip/irq-sunxi.c b/drivers/irqchip/irq-sunxi.c
new file mode 100644
index 000000000000..eef41a49acae
--- /dev/null
+++ b/drivers/irqchip/irq-sunxi.c
@@ -0,0 +1,150 @@
+/*
+ * Allwinner A1X SoCs IRQ chip driver.
+ *
+ * Copyright (C) 2012 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * Based on code from
+ * Allwinner Technology Co., Ltd. <www.allwinnertech.com>
+ * Benn Huang <benn@allwinnertech.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#include <linux/irqchip/sunxi.h>
+
+#define SUNXI_IRQ_VECTOR_REG		0x00
+#define SUNXI_IRQ_PROTECTION_REG	0x08
+#define SUNXI_IRQ_NMI_CTRL_REG		0x0c
+#define SUNXI_IRQ_PENDING_REG(x)	(0x10 + 0x4 * x)
+#define SUNXI_IRQ_FIQ_PENDING_REG(x)	(0x20 + 0x4 * x)
+#define SUNXI_IRQ_ENABLE_REG(x)		(0x40 + 0x4 * x)
+#define SUNXI_IRQ_MASK_REG(x)		(0x50 + 0x4 * x)
+
+static void __iomem *sunxi_irq_base;
+static struct irq_domain *sunxi_irq_domain;
+
+void sunxi_irq_ack(struct irq_data *irqd)
+{
+	unsigned int irq = irqd_to_hwirq(irqd);
+	unsigned int irq_off = irq % 32;
+	int reg = irq / 32;
+	u32 val;
+
+	val = readl(sunxi_irq_base + SUNXI_IRQ_PENDING_REG(reg));
+	writel(val | (1 << irq_off),
+	       sunxi_irq_base + SUNXI_IRQ_PENDING_REG(reg));
+}
+
+static void sunxi_irq_mask(struct irq_data *irqd)
+{
+	unsigned int irq = irqd_to_hwirq(irqd);
+	unsigned int irq_off = irq % 32;
+	int reg = irq / 32;
+	u32 val;
+
+	val = readl(sunxi_irq_base + SUNXI_IRQ_ENABLE_REG(reg));
+	writel(val & ~(1 << irq_off),
+	       sunxi_irq_base + SUNXI_IRQ_ENABLE_REG(reg));
+}
+
+static void sunxi_irq_unmask(struct irq_data *irqd)
+{
+	unsigned int irq = irqd_to_hwirq(irqd);
+	unsigned int irq_off = irq % 32;
+	int reg = irq / 32;
+	u32 val;
+
+	val = readl(sunxi_irq_base + SUNXI_IRQ_ENABLE_REG(reg));
+	writel(val | (1 << irq_off),
+	       sunxi_irq_base + SUNXI_IRQ_ENABLE_REG(reg));
+}
+
+static struct irq_chip sunxi_irq_chip = {
+	.name		= "sunxi_irq",
+	.irq_ack	= sunxi_irq_ack,
+	.irq_mask	= sunxi_irq_mask,
+	.irq_unmask	= sunxi_irq_unmask,
+};
+
+static int sunxi_irq_map(struct irq_domain *d, unsigned int virq,
+			 irq_hw_number_t hw)
+{
+	irq_set_chip_and_handler(virq, &sunxi_irq_chip,
+				 handle_level_irq);
+	set_irq_flags(virq, IRQF_VALID | IRQF_PROBE);
+
+	return 0;
+}
+
+static struct irq_domain_ops sunxi_irq_ops = {
+	.map = sunxi_irq_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int __init sunxi_of_init(struct device_node *node,
+				struct device_node *parent)
+{
+	sunxi_irq_base = of_iomap(node, 0);
+	if (!sunxi_irq_base)
+		panic("%s: unable to map IC registers\n",
+			node->full_name);
+
+	/* Disable all interrupts */
+	writel(0, sunxi_irq_base + SUNXI_IRQ_ENABLE_REG(0));
+	writel(0, sunxi_irq_base + SUNXI_IRQ_ENABLE_REG(1));
+	writel(0, sunxi_irq_base + SUNXI_IRQ_ENABLE_REG(2));
+
+	/* Mask all the interrupts */
+	writel(0, sunxi_irq_base + SUNXI_IRQ_MASK_REG(0));
+	writel(0, sunxi_irq_base + SUNXI_IRQ_MASK_REG(1));
+	writel(0, sunxi_irq_base + SUNXI_IRQ_MASK_REG(2));
+
+	/* Clear all the pending interrupts */
+	writel(0xffffffff, sunxi_irq_base + SUNXI_IRQ_PENDING_REG(0));
+	writel(0xffffffff, sunxi_irq_base + SUNXI_IRQ_PENDING_REG(1));
+	writel(0xffffffff, sunxi_irq_base + SUNXI_IRQ_PENDING_REG(2));
+
+	/* Enable protection mode */
+	writel(0x01, sunxi_irq_base + SUNXI_IRQ_PROTECTION_REG);
+
+	/* Configure the external interrupt source type */
+	writel(0x00, sunxi_irq_base + SUNXI_IRQ_NMI_CTRL_REG);
+
+	sunxi_irq_domain = irq_domain_add_linear(node, 3 * 32,
+						 &sunxi_irq_ops, NULL);
+	if (!sunxi_irq_domain)
+		panic("%s: unable to create IRQ domain\n", node->full_name);
+
+	return 0;
+}
+
+static struct of_device_id sunxi_irq_dt_ids[] __initconst = {
+	{ .compatible = "allwinner,sunxi-ic", .data = sunxi_of_init }
+};
+
+void __init sunxi_init_irq(void)
+{
+	of_irq_init(sunxi_irq_dt_ids);
+}
+
+asmlinkage void __exception_irq_entry sunxi_handle_irq(struct pt_regs *regs)
+{
+	u32 irq, hwirq;
+
+	hwirq = readl(sunxi_irq_base + SUNXI_IRQ_VECTOR_REG) >> 2;
+	while (hwirq != 0) {
+		irq = irq_find_mapping(sunxi_irq_domain, hwirq);
+		handle_IRQ(irq, regs);
+		hwirq = readl(sunxi_irq_base + SUNXI_IRQ_VECTOR_REG) >> 2;
+	}
+}
diff --git a/include/linux/irqchip/sunxi.h b/include/linux/irqchip/sunxi.h
new file mode 100644
index 000000000000..1fe2c2260e2b
--- /dev/null
+++ b/include/linux/irqchip/sunxi.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright 2012 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_IRQCHIP_SUNXI_H
+#define __LINUX_IRQCHIP_SUNXI_H
+
+#include <asm/exception.h>
+
+extern void sunxi_init_irq(void);
+
+extern asmlinkage void __exception_irq_entry sunxi_handle_irq(
+	struct pt_regs *regs);
+
+#endif
-- 
cgit v1.2.3-55-g7522


From c22618a11d1ba2966bd2cfd5e4918ed4f2dad13e Mon Sep 17 00:00:00 2001
From: Grant Likely
Date: Wed, 14 Nov 2012 22:37:12 +0000
Subject: drivers/of: Constify device_node->name and ->path_component_name

Neither of these should ever be changed once set. Make them const and
fix up the users that try to modify it in-place. In one case
kmalloc+memcpy is replaced with kstrdup() to avoid modifying the string.

Build tested with defconfigs on ARM, PowerPC, Sparc, MIPS, x86 among
others.

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Julian Calaby <julian.calaby@gmail.com>
---
 arch/powerpc/platforms/powermac/pfunc_core.c |  2 +-
 arch/powerpc/platforms/pseries/reconfig.c    |  3 +--
 arch/powerpc/sysdev/fsl_pci.c                |  2 +-
 arch/sparc/kernel/pci_impl.h                 |  2 +-
 drivers/of/fdt.c                             | 10 +++++-----
 include/linux/of.h                           |  4 ++--
 6 files changed, 11 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/platforms/powermac/pfunc_core.c b/arch/powerpc/platforms/powermac/pfunc_core.c
index b0c3777528a1..d588e48dff74 100644
--- a/arch/powerpc/platforms/powermac/pfunc_core.c
+++ b/arch/powerpc/platforms/powermac/pfunc_core.c
@@ -686,7 +686,7 @@ static int pmf_add_functions(struct pmf_device *dev, void *driverdata)
 	int count = 0;
 
 	for (pp = dev->node->properties; pp != 0; pp = pp->next) {
-		char *name;
+		const char *name;
 		if (strncmp(pp->name, PP_PREFIX, plen) != 0)
 			continue;
 		name = pp->name + plen;
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 39f71fba9b38..2f4668136b20 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -281,12 +281,11 @@ static struct property *new_property(const char *name, const int length,
 	if (!new)
 		return NULL;
 
-	if (!(new->name = kmalloc(strlen(name) + 1, GFP_KERNEL)))
+	if (!(new->name = kstrdup(name, GFP_KERNEL)))
 		goto cleanup;
 	if (!(new->value = kmalloc(length + 1, GFP_KERNEL)))
 		goto cleanup;
 
-	strcpy(new->name, name);
 	memcpy(new->value, value, length);
 	*(((char *)new->value) + length) = 0;
 	new->length = length;
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index ffb93ae9379b..01b62a62c635 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -136,7 +136,7 @@ static void __init setup_pci_atmu(struct pci_controller *hose,
 	u32 pcicsrbar = 0, pcicsrbar_sz;
 	u32 piwar = PIWAR_EN | PIWAR_PF | PIWAR_TGI_LOCAL |
 			PIWAR_READ_SNOOP | PIWAR_WRITE_SNOOP;
-	char *name = hose->dn->full_name;
+	const char *name = hose->dn->full_name;
 	const u64 *reg;
 	int len;
 
diff --git a/arch/sparc/kernel/pci_impl.h b/arch/sparc/kernel/pci_impl.h
index 918a2031c8bb..5f688531f48c 100644
--- a/arch/sparc/kernel/pci_impl.h
+++ b/arch/sparc/kernel/pci_impl.h
@@ -88,7 +88,7 @@ struct pci_pbm_info {
 	int				chip_revision;
 
 	/* Name used for top-level resources. */
-	char				*name;
+	const char			*name;
 
 	/* OBP specific information. */
 	struct platform_device		*op;
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index c2b08dcdbc53..c8be32644c85 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -199,10 +199,10 @@ static unsigned long unflatten_dt_node(struct boot_param_header *blob,
 	np = unflatten_dt_alloc(&mem, sizeof(struct device_node) + allocl,
 				__alignof__(struct device_node));
 	if (allnextpp) {
+		char *fn;
 		memset(np, 0, sizeof(*np));
-		np->full_name = ((char *)np) + sizeof(struct device_node);
+		np->full_name = fn = ((char *)np) + sizeof(*np);
 		if (new_format) {
-			char *fn = np->full_name;
 			/* rebuild full path for new format */
 			if (dad && dad->parent) {
 				strcpy(fn, dad->full_name);
@@ -216,9 +216,9 @@ static unsigned long unflatten_dt_node(struct boot_param_header *blob,
 				fn += strlen(fn);
 			}
 			*(fn++) = '/';
-			memcpy(fn, pathp, l);
-		} else
-			memcpy(np->full_name, pathp, l);
+		}
+		memcpy(fn, pathp, l);
+
 		prev_pp = &np->properties;
 		**allnextpp = np;
 		*allnextpp = &np->allnext;
diff --git a/include/linux/of.h b/include/linux/of.h
index b4e50d56fc74..857dde984a6e 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -46,7 +46,7 @@ struct device_node {
 	const char *name;
 	const char *type;
 	phandle phandle;
-	char	*full_name;
+	const char *full_name;
 
 	struct	property *properties;
 	struct	property *deadprops;	/* removed properties */
@@ -60,7 +60,7 @@ struct device_node {
 	unsigned long _flags;
 	void	*data;
 #if defined(CONFIG_SPARC)
-	char	*path_component_name;
+	const char *path_component_name;
 	unsigned int unique_id;
 	struct of_irq_controller *irq_trans;
 #endif
-- 
cgit v1.2.3-55-g7522


From ea2ce92e44dc83b7a69c2aedd9c52bfe7fee1a62 Mon Sep 17 00:00:00 2001
From: Ramakrishna Pallala
Date: Tue, 9 Oct 2012 22:25:29 +0530
Subject: power_supply: Add support for CHARGE_CONTROL_* attributes

Add support for power supply attributes CHARGE_CONTROL_LIMIT
and CHARGE_CONTROL_LIMIT_MAX.

These new attributes will enable the user space to implement
custom charging algorithms based on platform state.

Signed-off-by: Ramakrishna Pallala <ramakrishna.pallala@intel.com>
Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
---
 Documentation/power/power_supply_class.txt | 3 +++
 drivers/power/power_supply_sysfs.c         | 2 ++
 include/linux/power_supply.h               | 2 ++
 3 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/Documentation/power/power_supply_class.txt b/Documentation/power/power_supply_class.txt
index 9c647bd7c5a9..3f10b39b0346 100644
--- a/Documentation/power/power_supply_class.txt
+++ b/Documentation/power/power_supply_class.txt
@@ -123,6 +123,9 @@ CONSTANT_CHARGE_VOLTAGE - constant charge voltage programmed by charger.
 CONSTANT_CHARGE_VOLTAGE_MAX - maximum charge voltage supported by the
 power supply object.
 
+CHARGE_CONTROL_LIMIT - current charge control limit setting
+CHARGE_CONTROL_LIMIT_MAX - maximum charge control limit setting
+
 ENERGY_FULL, ENERGY_EMPTY - same as above but for energy.
 
 CAPACITY - capacity in percents.
diff --git a/drivers/power/power_supply_sysfs.c b/drivers/power/power_supply_sysfs.c
index 395c2cfa16c0..40fa3b7cae54 100644
--- a/drivers/power/power_supply_sysfs.c
+++ b/drivers/power/power_supply_sysfs.c
@@ -164,6 +164,8 @@ static struct device_attribute power_supply_attrs[] = {
 	POWER_SUPPLY_ATTR(constant_charge_current_max),
 	POWER_SUPPLY_ATTR(constant_charge_voltage),
 	POWER_SUPPLY_ATTR(constant_charge_voltage_max),
+	POWER_SUPPLY_ATTR(charge_control_limit),
+	POWER_SUPPLY_ATTR(charge_control_limit_max),
 	POWER_SUPPLY_ATTR(energy_full_design),
 	POWER_SUPPLY_ATTR(energy_empty_design),
 	POWER_SUPPLY_ATTR(energy_full),
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index e5ef45834c3c..445b4b249af5 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -114,6 +114,8 @@ enum power_supply_property {
 	POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX,
 	POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE,
 	POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX,
+	POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT,
+	POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX,
 	POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN,
 	POWER_SUPPLY_PROP_ENERGY_EMPTY_DESIGN,
 	POWER_SUPPLY_PROP_ENERGY_FULL,
-- 
cgit v1.2.3-55-g7522


From 952aeeb3ee28bc12a70744e40636de40688eb60d Mon Sep 17 00:00:00 2001
From: Ramakrishna Pallala
Date: Tue, 9 Oct 2012 22:25:59 +0530
Subject: power_supply: Register power supply for thermal cooling device

This patch registers the power supply as a cooling device if the power
supply has support for charge throttling.

Now with this change low level drivers need not register with thermal
framework as it is automatically done by power supply framework.

Signed-off-by: Ramakrishna Pallala <ramakrishna.pallala@intel.com>
Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
---
 drivers/power/power_supply_core.c | 96 +++++++++++++++++++++++++++++++++++++++
 include/linux/power_supply.h      |  1 +
 2 files changed, 97 insertions(+)

(limited to 'include')

diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index 2436f1350013..f984da1066ec 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -216,6 +216,86 @@ static void psy_unregister_thermal(struct power_supply *psy)
 		return;
 	thermal_zone_device_unregister(psy->tzd);
 }
+
+/* thermal cooling device callbacks */
+static int ps_get_max_charge_cntl_limit(struct thermal_cooling_device *tcd,
+					unsigned long *state)
+{
+	struct power_supply *psy;
+	union power_supply_propval val;
+	int ret;
+
+	psy = tcd->devdata;
+	ret = psy->get_property(psy,
+		POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val);
+	if (!ret)
+		*state = val.intval;
+
+	return ret;
+}
+
+static int ps_get_cur_chrage_cntl_limit(struct thermal_cooling_device *tcd,
+					unsigned long *state)
+{
+	struct power_supply *psy;
+	union power_supply_propval val;
+	int ret;
+
+	psy = tcd->devdata;
+	ret = psy->get_property(psy,
+		POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val);
+	if (!ret)
+		*state = val.intval;
+
+	return ret;
+}
+
+static int ps_set_cur_charge_cntl_limit(struct thermal_cooling_device *tcd,
+					unsigned long state)
+{
+	struct power_supply *psy;
+	union power_supply_propval val;
+	int ret;
+
+	psy = tcd->devdata;
+	val.intval = state;
+	ret = psy->set_property(psy,
+		POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val);
+
+	return ret;
+}
+
+static struct thermal_cooling_device_ops psy_tcd_ops = {
+	.get_max_state = ps_get_max_charge_cntl_limit,
+	.get_cur_state = ps_get_cur_chrage_cntl_limit,
+	.set_cur_state = ps_set_cur_charge_cntl_limit,
+};
+
+static int psy_register_cooler(struct power_supply *psy)
+{
+	int i;
+
+	/* Register for cooling device if psy can control charging */
+	for (i = 0; i < psy->num_properties; i++) {
+		if (psy->properties[i] ==
+				POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT) {
+			psy->tcd = thermal_cooling_device_register(
+							(char *)psy->name,
+							psy, &psy_tcd_ops);
+			if (IS_ERR(psy->tcd))
+				return PTR_ERR(psy->tcd);
+			break;
+		}
+	}
+	return 0;
+}
+
+static void psy_unregister_cooler(struct power_supply *psy)
+{
+	if (IS_ERR_OR_NULL(psy->tcd))
+		return;
+	thermal_cooling_device_unregister(psy->tcd);
+}
 #else
 static int psy_register_thermal(struct power_supply *psy)
 {
@@ -225,6 +305,15 @@ static int psy_register_thermal(struct power_supply *psy)
 static void psy_unregister_thermal(struct power_supply *psy)
 {
 }
+
+static int psy_register_cooler(struct power_supply *psy)
+{
+	return 0;
+}
+
+static void psy_unregister_cooler(struct power_supply *psy)
+{
+}
 #endif
 
 int power_supply_register(struct device *parent, struct power_supply *psy)
@@ -259,6 +348,10 @@ int power_supply_register(struct device *parent, struct power_supply *psy)
 	if (rc)
 		goto register_thermal_failed;
 
+	rc = psy_register_cooler(psy);
+	if (rc)
+		goto register_cooler_failed;
+
 	rc = power_supply_create_triggers(psy);
 	if (rc)
 		goto create_triggers_failed;
@@ -268,6 +361,8 @@ int power_supply_register(struct device *parent, struct power_supply *psy)
 	goto success;
 
 create_triggers_failed:
+	psy_unregister_cooler(psy);
+register_cooler_failed:
 	psy_unregister_thermal(psy);
 register_thermal_failed:
 	device_del(dev);
@@ -284,6 +379,7 @@ void power_supply_unregister(struct power_supply *psy)
 	cancel_work_sync(&psy->changed_work);
 	sysfs_remove_link(&psy->dev->kobj, "powers");
 	power_supply_remove_triggers(psy);
+	psy_unregister_cooler(psy);
 	psy_unregister_thermal(psy);
 	device_unregister(psy->dev);
 }
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 445b4b249af5..1f0ab90aff00 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -188,6 +188,7 @@ struct power_supply {
 	struct work_struct changed_work;
 #ifdef CONFIG_THERMAL
 	struct thermal_zone_device *tzd;
+	struct thermal_cooling_device *tcd;
 #endif
 
 #ifdef CONFIG_LEDS_TRIGGERS
-- 
cgit v1.2.3-55-g7522


From 08d816b8cb09de1fd8268c8f1dbc97c3cc435d67 Mon Sep 17 00:00:00 2001
From: Kim, Milo
Date: Mon, 22 Oct 2012 00:18:54 +0000
Subject: lp8788-charger: Fix ADC channel names

The name of ADC channel is configurable in the platform side. This name is
referenced in the IIO consumer driver. To get the IIO channel, specific
name in the platform data is used as an parameter of the
iio_channel_get(). Thus, lp8788_adc_id platform data are replaced with
specific names.

Signed-off-by: Milo(Woogyom) Kim <milo.kim@ti.com>
Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
---
 drivers/power/lp8788-charger.c | 44 ++++++------------------------------------
 include/linux/mfd/lp8788.h     |  8 ++++----
 2 files changed, 10 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/power/lp8788-charger.c b/drivers/power/lp8788-charger.c
index 1afa5f7a5359..fb592bfbec6e 100644
--- a/drivers/power/lp8788-charger.c
+++ b/drivers/power/lp8788-charger.c
@@ -584,50 +584,18 @@ static void lp8788_setup_adc_channel(const char *consumer_name,
 				struct lp8788_charger *pchg)
 {
 	struct lp8788_charger_platform_data *pdata = pchg->pdata;
-	struct device *dev = pchg->lp->dev;
 	struct iio_channel *chan;
-	enum lp8788_adc_id id;
-	const char *chan_name[LPADC_MAX] = {
-		[LPADC_VBATT_5P5] = "vbatt-5p5",
-		[LPADC_VBATT_6P0] = "vbatt-6p0",
-		[LPADC_VBATT_5P0] = "vbatt-5p0",
-		[LPADC_ADC1]      = "adc1",
-		[LPADC_ADC2]      = "adc2",
-		[LPADC_ADC3]      = "adc3",
-		[LPADC_ADC4]      = "adc4",
-	};
 
 	if (!pdata)
 		return;
 
-	id = pdata->vbatt_adc;
-	switch (id) {
-	case LPADC_VBATT_5P5:
-	case LPADC_VBATT_6P0:
-	case LPADC_VBATT_5P0:
-		chan = iio_channel_get(consumer_name, chan_name[id]);
-		pchg->chan[LP8788_VBATT] = IS_ERR(chan) ? NULL : chan;
-		break;
-	default:
-		dev_err(dev, "invalid ADC id for VBATT: %d\n", id);
-		pchg->chan[LP8788_VBATT] = NULL;
-		break;
-	}
+	/* ADC channel for battery voltage */
+	chan = iio_channel_get(consumer_name, pdata->adc_vbatt);
+	pchg->chan[LP8788_VBATT] = IS_ERR(chan) ? NULL : chan;
 
-	id = pdata->batt_temp_adc;
-	switch (id) {
-	case LPADC_ADC1:
-	case LPADC_ADC2:
-	case LPADC_ADC3:
-	case LPADC_ADC4:
-		chan = iio_channel_get(consumer_name, chan_name[id]);
-		pchg->chan[LP8788_BATT_TEMP] = IS_ERR(chan) ? NULL : chan;
-		break;
-	default:
-		dev_err(dev, "invalid ADC id for BATT_TEMP : %d\n", id);
-		pchg->chan[LP8788_BATT_TEMP] = NULL;
-		break;
-	}
+	/* ADC channel for battery temperature */
+	chan = iio_channel_get(consumer_name, pdata->adc_batt_temp);
+	pchg->chan[LP8788_BATT_TEMP] = IS_ERR(chan) ? NULL : chan;
 }
 
 static void lp8788_release_adc_channel(struct lp8788_charger *pchg)
diff --git a/include/linux/mfd/lp8788.h b/include/linux/mfd/lp8788.h
index cec364bdccfa..2a32b16f79cb 100644
--- a/include/linux/mfd/lp8788.h
+++ b/include/linux/mfd/lp8788.h
@@ -211,16 +211,16 @@ struct lp8788_chg_param {
 
 /*
  * struct lp8788_charger_platform_data
- * @vbatt_adc         : adc selection id for battery voltage
- * @batt_temp_adc     : adc selection id for battery temperature
+ * @adc_vbatt         : adc channel name for battery voltage
+ * @adc_batt_temp     : adc channel name for battery temperature
  * @max_vbatt_mv      : used for calculating battery capacity
  * @chg_params        : initial charging parameters
  * @num_chg_params    : numbers of charging parameters
  * @charger_event     : the charger event can be reported to the platform side
  */
 struct lp8788_charger_platform_data {
-	enum lp8788_adc_id vbatt_adc;
-	enum lp8788_adc_id batt_temp_adc;
+	const char *adc_vbatt;
+	const char *adc_batt_temp;
 	unsigned int max_vbatt_mv;
 	struct lp8788_chg_param *chg_params;
 	int num_chg_params;
-- 
cgit v1.2.3-55-g7522


From 0bc98cc6155205b615a9d29a2d54d1b839521c04 Mon Sep 17 00:00:00 2001
From: Pali Rohár
Date: Fri, 2 Nov 2012 20:18:11 +0100
Subject: power_supply: Add bq2415x charger driver

The bq2415x charger driver is needed for example on Nokia N900 for
charging battery. Driver is part of open source project to replace
proprietary battery management.

Signed-off-by: Pali Rohár <pali.rohar@gmail.com>
Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
---
 drivers/power/bq2415x_charger.c       | 1644 +++++++++++++++++++++++++++++++++
 include/linux/power/bq2415x_charger.h |   90 ++
 2 files changed, 1734 insertions(+)
 create mode 100644 drivers/power/bq2415x_charger.c
 create mode 100644 include/linux/power/bq2415x_charger.h

(limited to 'include')

diff --git a/drivers/power/bq2415x_charger.c b/drivers/power/bq2415x_charger.c
new file mode 100644
index 000000000000..017b3c27f769
--- /dev/null
+++ b/drivers/power/bq2415x_charger.c
@@ -0,0 +1,1644 @@
+/*
+    bq2415x_charger.c - bq2415x charger driver
+    Copyright (C) 2011-2012  Pali Rohár <pali.rohar@gmail.com>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+*/
+
+/*
+  Datasheets:
+  http://www.ti.com/product/bq24150
+  http://www.ti.com/product/bq24150a
+  http://www.ti.com/product/bq24152
+  http://www.ti.com/product/bq24153
+  http://www.ti.com/product/bq24153a
+  http://www.ti.com/product/bq24155
+*/
+
+#include <linux/version.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/param.h>
+#include <linux/err.h>
+#include <linux/workqueue.h>
+#include <linux/sysfs.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/idr.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+
+#include <linux/power/bq2415x_charger.h>
+
+/* timeout for resetting chip timer */
+#define BQ2415X_TIMER_TIMEOUT		10
+
+#define BQ2415X_REG_STATUS		0x00
+#define BQ2415X_REG_CONTROL		0x01
+#define BQ2415X_REG_VOLTAGE		0x02
+#define BQ2415X_REG_VENDER		0x03
+#define BQ2415X_REG_CURRENT		0x04
+
+/* reset state for all registers */
+#define BQ2415X_RESET_STATUS		BIT(6)
+#define BQ2415X_RESET_CONTROL		(BIT(4)|BIT(5))
+#define BQ2415X_RESET_VOLTAGE		(BIT(1)|BIT(3))
+#define BQ2415X_RESET_CURRENT		(BIT(0)|BIT(3)|BIT(7))
+
+/* status register */
+#define BQ2415X_BIT_TMR_RST		7
+#define BQ2415X_BIT_OTG			7
+#define BQ2415X_BIT_EN_STAT		6
+#define BQ2415X_MASK_STAT		(BIT(4)|BIT(5))
+#define BQ2415X_SHIFT_STAT		4
+#define BQ2415X_BIT_BOOST		3
+#define BQ2415X_MASK_FAULT		(BIT(0)|BIT(1)|BIT(2))
+#define BQ2415X_SHIFT_FAULT		0
+
+/* control register */
+#define BQ2415X_MASK_LIMIT		(BIT(6)|BIT(7))
+#define BQ2415X_SHIFT_LIMIT		6
+#define BQ2415X_MASK_VLOWV		(BIT(4)|BIT(5))
+#define BQ2415X_SHIFT_VLOWV		4
+#define BQ2415X_BIT_TE			3
+#define BQ2415X_BIT_CE			2
+#define BQ2415X_BIT_HZ_MODE		1
+#define BQ2415X_BIT_OPA_MODE		0
+
+/* voltage register */
+#define BQ2415X_MASK_VO		(BIT(2)|BIT(3)|BIT(4)|BIT(5)|BIT(6)|BIT(7))
+#define BQ2415X_SHIFT_VO		2
+#define BQ2415X_BIT_OTG_PL		1
+#define BQ2415X_BIT_OTG_EN		0
+
+/* vender register */
+#define BQ2415X_MASK_VENDER		(BIT(5)|BIT(6)|BIT(7))
+#define BQ2415X_SHIFT_VENDER		5
+#define BQ2415X_MASK_PN			(BIT(3)|BIT(4))
+#define BQ2415X_SHIFT_PN		3
+#define BQ2415X_MASK_REVISION		(BIT(0)|BIT(1)|BIT(2))
+#define BQ2415X_SHIFT_REVISION		0
+
+/* current register */
+#define BQ2415X_MASK_RESET		BIT(7)
+#define BQ2415X_MASK_VI_CHRG		(BIT(4)|BIT(5)|BIT(6))
+#define BQ2415X_SHIFT_VI_CHRG		4
+/* N/A					BIT(3) */
+#define BQ2415X_MASK_VI_TERM		(BIT(0)|BIT(1)|BIT(2))
+#define BQ2415X_SHIFT_VI_TERM		0
+
+
+enum bq2415x_command {
+	BQ2415X_TIMER_RESET,
+	BQ2415X_OTG_STATUS,
+	BQ2415X_STAT_PIN_STATUS,
+	BQ2415X_STAT_PIN_ENABLE,
+	BQ2415X_STAT_PIN_DISABLE,
+	BQ2415X_CHARGE_STATUS,
+	BQ2415X_BOOST_STATUS,
+	BQ2415X_FAULT_STATUS,
+
+	BQ2415X_CHARGE_TERMINATION_STATUS,
+	BQ2415X_CHARGE_TERMINATION_ENABLE,
+	BQ2415X_CHARGE_TERMINATION_DISABLE,
+	BQ2415X_CHARGER_STATUS,
+	BQ2415X_CHARGER_ENABLE,
+	BQ2415X_CHARGER_DISABLE,
+	BQ2415X_HIGH_IMPEDANCE_STATUS,
+	BQ2415X_HIGH_IMPEDANCE_ENABLE,
+	BQ2415X_HIGH_IMPEDANCE_DISABLE,
+	BQ2415X_BOOST_MODE_STATUS,
+	BQ2415X_BOOST_MODE_ENABLE,
+	BQ2415X_BOOST_MODE_DISABLE,
+
+	BQ2415X_OTG_LEVEL,
+	BQ2415X_OTG_ACTIVATE_HIGH,
+	BQ2415X_OTG_ACTIVATE_LOW,
+	BQ2415X_OTG_PIN_STATUS,
+	BQ2415X_OTG_PIN_ENABLE,
+	BQ2415X_OTG_PIN_DISABLE,
+
+	BQ2415X_VENDER_CODE,
+	BQ2415X_PART_NUMBER,
+	BQ2415X_REVISION,
+};
+
+enum bq2415x_chip {
+	BQUNKNOWN,
+	BQ24150,
+	BQ24150A,
+	BQ24151,
+	BQ24151A,
+	BQ24152,
+	BQ24153,
+	BQ24153A,
+	BQ24155,
+	BQ24156,
+	BQ24156A,
+	BQ24158,
+};
+
+static char *bq2415x_chip_name[] = {
+	"unknown",
+	"bq24150",
+	"bq24150a",
+	"bq24151",
+	"bq24151a",
+	"bq24152",
+	"bq24153",
+	"bq24153a",
+	"bq24155",
+	"bq24156",
+	"bq24156a",
+	"bq24158",
+};
+
+struct bq2415x_device {
+	struct device *dev;
+	struct bq2415x_platform_data init_data;
+	struct power_supply charger;
+	struct delayed_work work;
+	enum bq2415x_mode reported_mode;/* mode reported by hook function */
+	enum bq2415x_mode mode;		/* current configured mode */
+	enum bq2415x_chip chip;
+	const char *timer_error;
+	char *model;
+	char *name;
+	int autotimer;	/* 1 - if driver automatically reset timer, 0 - not */
+	int automode;	/* 1 - enabled, 0 - disabled; -1 - not supported */
+	int id;
+};
+
+/* each registered chip must have unique id */
+static DEFINE_IDR(bq2415x_id);
+
+static DEFINE_MUTEX(bq2415x_id_mutex);
+static DEFINE_MUTEX(bq2415x_timer_mutex);
+static DEFINE_MUTEX(bq2415x_i2c_mutex);
+
+/**** i2c read functions ****/
+
+/* read value from register */
+static int bq2415x_i2c_read(struct bq2415x_device *bq, u8 reg)
+{
+	struct i2c_client *client = to_i2c_client(bq->dev);
+	struct i2c_msg msg[2];
+	u8 val;
+	int ret;
+
+	if (!client->adapter)
+		return -ENODEV;
+
+	msg[0].addr = client->addr;
+	msg[0].flags = 0;
+	msg[0].buf = &reg;
+	msg[0].len = sizeof(reg);
+	msg[1].addr = client->addr;
+	msg[1].flags = I2C_M_RD;
+	msg[1].buf = &val;
+	msg[1].len = sizeof(val);
+
+	mutex_lock(&bq2415x_i2c_mutex);
+	ret = i2c_transfer(client->adapter, msg, ARRAY_SIZE(msg));
+	mutex_unlock(&bq2415x_i2c_mutex);
+
+	if (ret < 0)
+		return ret;
+
+	return val;
+}
+
+/* read value from register, apply mask and right shift it */
+static int bq2415x_i2c_read_mask(struct bq2415x_device *bq, u8 reg,
+				u8 mask, u8 shift)
+{
+	int ret;
+
+	if (shift > 8)
+		return -EINVAL;
+
+	ret = bq2415x_i2c_read(bq, reg);
+	if (ret < 0)
+		return ret;
+	else
+		return (ret & mask) >> shift;
+}
+
+/* read value from register and return one specified bit */
+static int bq2415x_i2c_read_bit(struct bq2415x_device *bq, u8 reg, u8 bit)
+{
+	if (bit > 8)
+		return -EINVAL;
+	else
+		return bq2415x_i2c_read_mask(bq, reg, BIT(bit), bit);
+}
+
+/**** i2c write functions ****/
+
+/* write value to register */
+static int bq2415x_i2c_write(struct bq2415x_device *bq, u8 reg, u8 val)
+{
+	struct i2c_client *client = to_i2c_client(bq->dev);
+	struct i2c_msg msg[1];
+	u8 data[2];
+	int ret;
+
+	data[0] = reg;
+	data[1] = val;
+
+	msg[0].addr = client->addr;
+	msg[0].flags = 0;
+	msg[0].buf = data;
+	msg[0].len = ARRAY_SIZE(data);
+
+	mutex_lock(&bq2415x_i2c_mutex);
+	ret = i2c_transfer(client->adapter, msg, ARRAY_SIZE(msg));
+	mutex_unlock(&bq2415x_i2c_mutex);
+
+	/* i2c_transfer returns number of messages transferred */
+	if (ret < 0)
+		return ret;
+	else if (ret != 1)
+		return -EIO;
+
+	return 0;
+}
+
+/* read value from register, change it with mask left shifted and write back */
+static int bq2415x_i2c_write_mask(struct bq2415x_device *bq, u8 reg, u8 val,
+				u8 mask, u8 shift)
+{
+	int ret;
+
+	if (shift > 8)
+		return -EINVAL;
+
+	ret = bq2415x_i2c_read(bq, reg);
+	if (ret < 0)
+		return ret;
+
+	ret &= ~mask;
+	ret |= val << shift;
+
+	return bq2415x_i2c_write(bq, reg, ret);
+}
+
+/* change only one bit in register */
+static int bq2415x_i2c_write_bit(struct bq2415x_device *bq, u8 reg,
+				bool val, u8 bit)
+{
+	if (bit > 8)
+		return -EINVAL;
+	else
+		return bq2415x_i2c_write_mask(bq, reg, val, BIT(bit), bit);
+}
+
+/**** global functions ****/
+
+/* exec command function */
+static int bq2415x_exec_command(struct bq2415x_device *bq,
+				enum bq2415x_command command)
+{
+	int ret;
+	switch (command) {
+	case BQ2415X_TIMER_RESET:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_STATUS,
+				1, BQ2415X_BIT_TMR_RST);
+	case BQ2415X_OTG_STATUS:
+		return bq2415x_i2c_read_bit(bq, BQ2415X_REG_STATUS,
+				BQ2415X_BIT_OTG);
+	case BQ2415X_STAT_PIN_STATUS:
+		return bq2415x_i2c_read_bit(bq, BQ2415X_REG_STATUS,
+				BQ2415X_BIT_EN_STAT);
+	case BQ2415X_STAT_PIN_ENABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_STATUS, 1,
+				BQ2415X_BIT_EN_STAT);
+	case BQ2415X_STAT_PIN_DISABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_STATUS, 0,
+				BQ2415X_BIT_EN_STAT);
+	case BQ2415X_CHARGE_STATUS:
+		return bq2415x_i2c_read_mask(bq, BQ2415X_REG_STATUS,
+				BQ2415X_MASK_STAT, BQ2415X_SHIFT_STAT);
+	case BQ2415X_BOOST_STATUS:
+		return bq2415x_i2c_read_bit(bq, BQ2415X_REG_STATUS,
+				BQ2415X_BIT_BOOST);
+	case BQ2415X_FAULT_STATUS:
+		return bq2415x_i2c_read_mask(bq, BQ2415X_REG_STATUS,
+			BQ2415X_MASK_FAULT, BQ2415X_SHIFT_FAULT);
+
+	case BQ2415X_CHARGE_TERMINATION_STATUS:
+		return bq2415x_i2c_read_bit(bq, BQ2415X_REG_CONTROL,
+				BQ2415X_BIT_TE);
+	case BQ2415X_CHARGE_TERMINATION_ENABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_CONTROL,
+				1, BQ2415X_BIT_TE);
+	case BQ2415X_CHARGE_TERMINATION_DISABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_CONTROL,
+				0, BQ2415X_BIT_TE);
+	case BQ2415X_CHARGER_STATUS:
+		ret = bq2415x_i2c_read_bit(bq, BQ2415X_REG_CONTROL,
+			BQ2415X_BIT_CE);
+		if (ret < 0)
+			return ret;
+		else
+			return ret > 0 ? 0 : 1;
+	case BQ2415X_CHARGER_ENABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_CONTROL,
+				0, BQ2415X_BIT_CE);
+	case BQ2415X_CHARGER_DISABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_CONTROL,
+				1, BQ2415X_BIT_CE);
+	case BQ2415X_HIGH_IMPEDANCE_STATUS:
+		return bq2415x_i2c_read_bit(bq, BQ2415X_REG_CONTROL,
+				BQ2415X_BIT_HZ_MODE);
+	case BQ2415X_HIGH_IMPEDANCE_ENABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_CONTROL,
+				1, BQ2415X_BIT_HZ_MODE);
+	case BQ2415X_HIGH_IMPEDANCE_DISABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_CONTROL,
+				0, BQ2415X_BIT_HZ_MODE);
+	case BQ2415X_BOOST_MODE_STATUS:
+		return bq2415x_i2c_read_bit(bq, BQ2415X_REG_CONTROL,
+				BQ2415X_BIT_OPA_MODE);
+	case BQ2415X_BOOST_MODE_ENABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_CONTROL,
+				1, BQ2415X_BIT_OPA_MODE);
+	case BQ2415X_BOOST_MODE_DISABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_CONTROL,
+				0, BQ2415X_BIT_OPA_MODE);
+
+	case BQ2415X_OTG_LEVEL:
+		return bq2415x_i2c_read_bit(bq, BQ2415X_REG_VOLTAGE,
+				BQ2415X_BIT_OTG_PL);
+	case BQ2415X_OTG_ACTIVATE_HIGH:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_VOLTAGE,
+				1, BQ2415X_BIT_OTG_PL);
+	case BQ2415X_OTG_ACTIVATE_LOW:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_VOLTAGE,
+				0, BQ2415X_BIT_OTG_PL);
+	case BQ2415X_OTG_PIN_STATUS:
+		return bq2415x_i2c_read_bit(bq, BQ2415X_REG_VOLTAGE,
+				BQ2415X_BIT_OTG_EN);
+	case BQ2415X_OTG_PIN_ENABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_VOLTAGE,
+				1, BQ2415X_BIT_OTG_EN);
+	case BQ2415X_OTG_PIN_DISABLE:
+		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_VOLTAGE,
+				0, BQ2415X_BIT_OTG_EN);
+
+	case BQ2415X_VENDER_CODE:
+		return bq2415x_i2c_read_mask(bq, BQ2415X_REG_VENDER,
+			BQ2415X_MASK_VENDER, BQ2415X_SHIFT_VENDER);
+	case BQ2415X_PART_NUMBER:
+		return bq2415x_i2c_read_mask(bq, BQ2415X_REG_VENDER,
+				BQ2415X_MASK_PN, BQ2415X_SHIFT_PN);
+	case BQ2415X_REVISION:
+		return bq2415x_i2c_read_mask(bq, BQ2415X_REG_VENDER,
+			BQ2415X_MASK_REVISION, BQ2415X_SHIFT_REVISION);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+/* detect chip type */
+static enum bq2415x_chip bq2415x_detect_chip(struct bq2415x_device *bq)
+{
+	struct i2c_client *client = to_i2c_client(bq->dev);
+	int ret = bq2415x_exec_command(bq, BQ2415X_PART_NUMBER);
+
+	if (ret < 0)
+		return ret;
+
+	switch (client->addr) {
+	case 0x6b:
+		switch (ret) {
+		case 0:
+			if (bq->chip == BQ24151A)
+				return bq->chip;
+			else
+				return BQ24151;
+		case 1:
+			if (bq->chip == BQ24150A ||
+				bq->chip == BQ24152 ||
+				bq->chip == BQ24155)
+				return bq->chip;
+			else
+				return BQ24150;
+		case 2:
+			if (bq->chip == BQ24153A)
+				return bq->chip;
+			else
+				return BQ24153;
+		default:
+			return BQUNKNOWN;
+		}
+		break;
+
+	case 0x6a:
+		switch (ret) {
+		case 0:
+			if (bq->chip == BQ24156A)
+				return bq->chip;
+			else
+				return BQ24156;
+		case 2:
+			return BQ24158;
+		default:
+			return BQUNKNOWN;
+		}
+		break;
+	}
+
+	return BQUNKNOWN;
+}
+
+/* detect chip revision */
+static int bq2415x_detect_revision(struct bq2415x_device *bq)
+{
+	int ret = bq2415x_exec_command(bq, BQ2415X_REVISION);
+	int chip = bq2415x_detect_chip(bq);
+	if (ret < 0 || chip < 0)
+		return -1;
+
+	switch (chip) {
+	case BQ24150:
+	case BQ24150A:
+	case BQ24151:
+	case BQ24151A:
+	case BQ24152:
+		if (ret >= 0 && ret <= 3)
+			return ret;
+		else
+			return -1;
+
+	case BQ24153:
+	case BQ24153A:
+	case BQ24156:
+	case BQ24156A:
+	case BQ24158:
+		if (ret == 3)
+			return 0;
+		else if (ret == 1)
+			return 1;
+		else
+			return -1;
+
+	case BQ24155:
+		if (ret == 3)
+			return 3;
+		else
+			return -1;
+
+	case BQUNKNOWN:
+		return -1;
+	}
+
+	return -1;
+}
+
+/* return chip vender code */
+static int bq2415x_get_vender_code(struct bq2415x_device *bq)
+{
+	int ret = bq2415x_exec_command(bq, BQ2415X_VENDER_CODE);
+	if (ret < 0)
+		return 0;
+	else /* convert to binary */
+		return (ret & 0x1) +
+			((ret >> 1) & 0x1) * 10 +
+			((ret >> 2) & 0x1) * 100;
+}
+
+/* reset all chip registers to default state */
+static void bq2415x_reset_chip(struct bq2415x_device *bq)
+{
+	bq2415x_i2c_write(bq, BQ2415X_REG_CURRENT, BQ2415X_RESET_CURRENT);
+	bq2415x_i2c_write(bq, BQ2415X_REG_VOLTAGE, BQ2415X_RESET_VOLTAGE);
+	bq2415x_i2c_write(bq, BQ2415X_REG_CONTROL, BQ2415X_RESET_CONTROL);
+	bq2415x_i2c_write(bq, BQ2415X_REG_STATUS, BQ2415X_RESET_STATUS);
+	bq->timer_error = NULL;
+}
+
+/**** properties functions ****/
+
+/* set current limit in mA */
+static int bq2415x_set_current_limit(struct bq2415x_device *bq, int mA)
+{
+	int val;
+	if (mA <= 100)
+		val = 0;
+	else if (mA <= 500)
+		val = 1;
+	else if (mA <= 800)
+		val = 2;
+	else
+		val = 3;
+	return bq2415x_i2c_write_mask(bq, BQ2415X_REG_CONTROL, val,
+			BQ2415X_MASK_LIMIT, BQ2415X_SHIFT_LIMIT);
+}
+
+/* get current limit in mA */
+static int bq2415x_get_current_limit(struct bq2415x_device *bq)
+{
+	int ret = bq2415x_i2c_read_mask(bq, BQ2415X_REG_CONTROL,
+			BQ2415X_MASK_LIMIT, BQ2415X_SHIFT_LIMIT);
+	if (ret < 0)
+		return ret;
+	else if (ret == 0)
+		return 100;
+	else if (ret == 1)
+		return 500;
+	else if (ret == 2)
+		return 800;
+	else if (ret == 3)
+		return 1800;
+	else
+		return -EINVAL;
+}
+
+/* set weak battery voltage in mV */
+static int bq2415x_set_weak_battery_voltage(struct bq2415x_device *bq, int mV)
+{
+	/* round to 100mV */
+	int val;
+	if (mV <= 3400 + 50)
+		val = 0;
+	else if (mV <= 3500 + 50)
+		val = 1;
+	else if (mV <= 3600 + 50)
+		val = 2;
+	else
+		val = 3;
+	return bq2415x_i2c_write_mask(bq, BQ2415X_REG_CONTROL, val,
+			BQ2415X_MASK_VLOWV, BQ2415X_SHIFT_VLOWV);
+}
+
+/* get weak battery voltage in mV */
+static int bq2415x_get_weak_battery_voltage(struct bq2415x_device *bq)
+{
+	int ret = bq2415x_i2c_read_mask(bq, BQ2415X_REG_CONTROL,
+			BQ2415X_MASK_VLOWV, BQ2415X_SHIFT_VLOWV);
+	if (ret < 0)
+		return ret;
+	else
+		return 100 * (34 + ret);
+}
+
+/* set battery regulation voltage in mV */
+static int bq2415x_set_battery_regulation_voltage(struct bq2415x_device *bq,
+						int mV)
+{
+	int val = (mV/10 - 350) / 2;
+
+	if (val < 0)
+		val = 0;
+	else if (val > 94) /* FIXME: Max is 94 or 122 ? Set max value ? */
+		return -EINVAL;
+
+	return bq2415x_i2c_write_mask(bq, BQ2415X_REG_VOLTAGE, val,
+			BQ2415X_MASK_VO, BQ2415X_SHIFT_VO);
+}
+
+/* get battery regulation voltage in mV */
+static int bq2415x_get_battery_regulation_voltage(struct bq2415x_device *bq)
+{
+	int ret = bq2415x_i2c_read_mask(bq, BQ2415X_REG_VOLTAGE,
+			BQ2415X_MASK_VO, BQ2415X_SHIFT_VO);
+	if (ret < 0)
+		return ret;
+	else
+		return 10 * (350 + 2*ret);
+}
+
+/* set charge current in mA (platform data must provide resistor sense) */
+static int bq2415x_set_charge_current(struct bq2415x_device *bq, int mA)
+{
+	int val;
+	if (bq->init_data.resistor_sense <= 0)
+		return -ENOSYS;
+
+	val = (mA * bq->init_data.resistor_sense - 37400) / 6800;
+
+	if (val < 0)
+		val = 0;
+	else if (val > 7)
+		val = 7;
+
+	return bq2415x_i2c_write_mask(bq, BQ2415X_REG_CURRENT, val,
+			BQ2415X_MASK_VI_CHRG | BQ2415X_MASK_RESET,
+			BQ2415X_SHIFT_VI_CHRG);
+}
+
+/* get charge current in mA (platform data must provide resistor sense) */
+static int bq2415x_get_charge_current(struct bq2415x_device *bq)
+{
+	int ret;
+	if (bq->init_data.resistor_sense <= 0)
+		return -ENOSYS;
+
+	ret = bq2415x_i2c_read_mask(bq, BQ2415X_REG_CURRENT,
+			BQ2415X_MASK_VI_CHRG, BQ2415X_SHIFT_VI_CHRG);
+	if (ret < 0)
+		return ret;
+	else
+		return (37400 + 6800*ret) / bq->init_data.resistor_sense;
+}
+
+/* set termination current in mA (platform data must provide resistor sense) */
+static int bq2415x_set_termination_current(struct bq2415x_device *bq, int mA)
+{
+	int val;
+	if (bq->init_data.resistor_sense <= 0)
+		return -ENOSYS;
+
+	val = (mA * bq->init_data.resistor_sense - 3400) / 3400;
+
+	if (val < 0)
+		val = 0;
+	else if (val > 7)
+		val = 7;
+
+	return bq2415x_i2c_write_mask(bq, BQ2415X_REG_CURRENT, val,
+			BQ2415X_MASK_VI_TERM | BQ2415X_MASK_RESET,
+			BQ2415X_SHIFT_VI_TERM);
+}
+
+/* get termination current in mA (platform data must provide resistor sense) */
+static int bq2415x_get_termination_current(struct bq2415x_device *bq)
+{
+	int ret;
+	if (bq->init_data.resistor_sense <= 0)
+		return -ENOSYS;
+
+	ret = bq2415x_i2c_read_mask(bq, BQ2415X_REG_CURRENT,
+			BQ2415X_MASK_VI_TERM, BQ2415X_SHIFT_VI_TERM);
+	if (ret < 0)
+		return ret;
+	else
+		return (3400 + 3400*ret) / bq->init_data.resistor_sense;
+}
+
+/* set default value of property */
+#define bq2415x_set_default_value(bq, prop) \
+	do { \
+		int ret = 0; \
+		if (bq->init_data.prop != -1) \
+			ret = bq2415x_set_##prop(bq, bq->init_data.prop); \
+		if (ret < 0) \
+			return ret; \
+	} while (0)
+
+/* set default values of all properties */
+static int bq2415x_set_defaults(struct bq2415x_device *bq)
+{
+	bq2415x_exec_command(bq, BQ2415X_BOOST_MODE_DISABLE);
+	bq2415x_exec_command(bq, BQ2415X_CHARGER_DISABLE);
+	bq2415x_exec_command(bq, BQ2415X_CHARGE_TERMINATION_DISABLE);
+	bq2415x_set_default_value(bq, current_limit);
+	bq2415x_set_default_value(bq, weak_battery_voltage);
+	bq2415x_set_default_value(bq, battery_regulation_voltage);
+	if (bq->init_data.resistor_sense > 0) {
+		bq2415x_set_default_value(bq, charge_current);
+		bq2415x_set_default_value(bq, termination_current);
+		bq2415x_exec_command(bq, BQ2415X_CHARGE_TERMINATION_ENABLE);
+	}
+	bq2415x_exec_command(bq, BQ2415X_CHARGER_ENABLE);
+	return 0;
+}
+
+/**** charger mode functions ****/
+
+/* set charger mode */
+static int bq2415x_set_mode(struct bq2415x_device *bq, enum bq2415x_mode mode)
+{
+	int ret = 0;
+	int charger = 0;
+	int boost = 0;
+
+	if (mode == BQ2415X_MODE_HOST_CHARGER ||
+		mode == BQ2415X_MODE_DEDICATED_CHARGER)
+			charger = 1;
+
+	if (mode == BQ2415X_MODE_BOOST)
+		boost = 1;
+
+	if (!charger)
+		ret = bq2415x_exec_command(bq, BQ2415X_CHARGER_DISABLE);
+
+	if (!boost)
+		ret = bq2415x_exec_command(bq, BQ2415X_BOOST_MODE_DISABLE);
+
+	if (ret < 0)
+		return ret;
+
+	switch (mode) {
+	case BQ2415X_MODE_NONE:
+		dev_dbg(bq->dev, "changing mode to: N/A\n");
+		ret = bq2415x_set_current_limit(bq, 100);
+		break;
+	case BQ2415X_MODE_HOST_CHARGER:
+		dev_dbg(bq->dev, "changing mode to: Host/HUB charger\n");
+		ret = bq2415x_set_current_limit(bq, 500);
+		break;
+	case BQ2415X_MODE_DEDICATED_CHARGER:
+		dev_dbg(bq->dev, "changing mode to: Dedicated charger\n");
+		ret = bq2415x_set_current_limit(bq, 1800);
+		break;
+	case BQ2415X_MODE_BOOST: /* Boost mode */
+		dev_dbg(bq->dev, "changing mode to: Boost\n");
+		ret = bq2415x_set_current_limit(bq, 100);
+		break;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	if (charger)
+		ret = bq2415x_exec_command(bq, BQ2415X_CHARGER_ENABLE);
+	else if (boost)
+		ret = bq2415x_exec_command(bq, BQ2415X_BOOST_MODE_ENABLE);
+
+	if (ret < 0)
+		return ret;
+
+	bq2415x_set_default_value(bq, weak_battery_voltage);
+	bq2415x_set_default_value(bq, battery_regulation_voltage);
+
+	bq->mode = mode;
+	sysfs_notify(&bq->charger.dev->kobj, NULL, "mode");
+
+	return 0;
+
+}
+
+/* hook function called by other driver which set reported mode */
+static void bq2415x_hook_function(enum bq2415x_mode mode, void *data)
+{
+	struct bq2415x_device *bq = data;
+
+	if (!bq)
+		return;
+
+	dev_dbg(bq->dev, "hook function was called\n");
+	bq->reported_mode = mode;
+
+	/* if automode is not enabled do not tell about reported_mode */
+	if (bq->automode < 1)
+		return;
+
+	sysfs_notify(&bq->charger.dev->kobj, NULL, "reported_mode");
+	bq2415x_set_mode(bq, bq->reported_mode);
+
+}
+
+/**** timer functions ****/
+
+/* enable/disable auto resetting chip timer */
+static void bq2415x_set_autotimer(struct bq2415x_device *bq, int state)
+{
+	mutex_lock(&bq2415x_timer_mutex);
+
+	if (bq->autotimer == state) {
+		mutex_unlock(&bq2415x_timer_mutex);
+		return;
+	}
+
+	bq->autotimer = state;
+
+	if (state) {
+		schedule_delayed_work(&bq->work, BQ2415X_TIMER_TIMEOUT * HZ);
+		bq2415x_exec_command(bq, BQ2415X_TIMER_RESET);
+		bq->timer_error = NULL;
+	} else {
+		cancel_delayed_work_sync(&bq->work);
+	}
+
+	mutex_unlock(&bq2415x_timer_mutex);
+}
+
+/* called by bq2415x_timer_work on timer error */
+static void bq2415x_timer_error(struct bq2415x_device *bq, const char *msg)
+{
+	bq->timer_error = msg;
+	sysfs_notify(&bq->charger.dev->kobj, NULL, "timer");
+	dev_err(bq->dev, "%s\n", msg);
+	if (bq->automode > 0)
+		bq->automode = 0;
+	bq2415x_set_mode(bq, BQ2415X_MODE_NONE);
+	bq2415x_set_autotimer(bq, 0);
+}
+
+/* delayed work function for auto resetting chip timer */
+static void bq2415x_timer_work(struct work_struct *work)
+{
+	struct bq2415x_device *bq = container_of(work, struct bq2415x_device,
+						work.work);
+	int ret, error, boost;
+
+	if (!bq->autotimer)
+		return;
+
+	ret = bq2415x_exec_command(bq, BQ2415X_TIMER_RESET);
+	if (ret < 0) {
+		bq2415x_timer_error(bq, "Resetting timer failed");
+		return;
+	}
+
+	boost = bq2415x_exec_command(bq, BQ2415X_BOOST_MODE_STATUS);
+	if (boost < 0) {
+		bq2415x_timer_error(bq, "Unknown error");
+		return;
+	}
+
+	error = bq2415x_exec_command(bq, BQ2415X_FAULT_STATUS);
+	if (error < 0) {
+		bq2415x_timer_error(bq, "Unknown error");
+		return;
+	}
+
+	if (boost) {
+		switch (error) {
+		/* Non fatal errors, chip is OK */
+		case 0: /* No error */
+			break;
+		case 6: /* Timer expired */
+			dev_err(bq->dev, "Timer expired\n");
+			break;
+		case 3: /* Battery voltage too low */
+			dev_err(bq->dev, "Battery voltage to low\n");
+			break;
+
+		/* Fatal errors, disable and reset chip */
+		case 1: /* Overvoltage protection (chip fried) */
+			bq2415x_timer_error(bq,
+				"Overvoltage protection (chip fried)");
+			return;
+		case 2: /* Overload */
+			bq2415x_timer_error(bq, "Overload");
+			return;
+		case 4: /* Battery overvoltage protection */
+			bq2415x_timer_error(bq,
+				"Battery overvoltage protection");
+			return;
+		case 5: /* Thermal shutdown (too hot) */
+			bq2415x_timer_error(bq,
+					"Thermal shutdown (too hot)");
+			return;
+		case 7: /* N/A */
+			bq2415x_timer_error(bq, "Unknown error");
+			return;
+		}
+	} else {
+		switch (error) {
+		/* Non fatal errors, chip is OK */
+		case 0: /* No error */
+			break;
+		case 2: /* Sleep mode */
+			dev_err(bq->dev, "Sleep mode\n");
+			break;
+		case 3: /* Poor input source */
+			dev_err(bq->dev, "Poor input source\n");
+			break;
+		case 6: /* Timer expired */
+			dev_err(bq->dev, "Timer expired\n");
+			break;
+		case 7: /* No battery */
+			dev_err(bq->dev, "No battery\n");
+			break;
+
+		/* Fatal errors, disable and reset chip */
+		case 1: /* Overvoltage protection (chip fried) */
+			bq2415x_timer_error(bq,
+				"Overvoltage protection (chip fried)");
+			return;
+		case 4: /* Battery overvoltage protection */
+			bq2415x_timer_error(bq,
+				"Battery overvoltage protection");
+			return;
+		case 5: /* Thermal shutdown (too hot) */
+			bq2415x_timer_error(bq,
+				"Thermal shutdown (too hot)");
+			return;
+		}
+	}
+
+	schedule_delayed_work(&bq->work, BQ2415X_TIMER_TIMEOUT * HZ);
+}
+
+/**** power supply interface code ****/
+
+static enum power_supply_property bq2415x_power_supply_props[] = {
+	/* TODO: maybe add more power supply properties */
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_MODEL_NAME,
+};
+
+static int bq2415x_power_supply_get_property(struct power_supply *psy,
+	enum power_supply_property psp, union power_supply_propval *val)
+{
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	int ret;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_STATUS:
+		ret = bq2415x_exec_command(bq, BQ2415X_CHARGE_STATUS);
+		if (ret < 0)
+			return ret;
+		else if (ret == 0) /* Ready */
+			val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING;
+		else if (ret == 1) /* Charge in progress */
+			val->intval = POWER_SUPPLY_STATUS_CHARGING;
+		else if (ret == 2) /* Charge done */
+			val->intval = POWER_SUPPLY_STATUS_FULL;
+		else
+			val->intval = POWER_SUPPLY_STATUS_UNKNOWN;
+		break;
+	case POWER_SUPPLY_PROP_MODEL_NAME:
+		val->strval = bq->model;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int bq2415x_power_supply_init(struct bq2415x_device *bq)
+{
+	int ret;
+	int chip;
+	char revstr[8];
+
+	bq->charger.name = bq->name;
+	bq->charger.type = POWER_SUPPLY_TYPE_USB;
+	bq->charger.properties = bq2415x_power_supply_props;
+	bq->charger.num_properties = ARRAY_SIZE(bq2415x_power_supply_props);
+	bq->charger.get_property = bq2415x_power_supply_get_property;
+
+	ret = bq2415x_detect_chip(bq);
+	if (ret < 0)
+		chip = BQUNKNOWN;
+	else
+		chip = ret;
+
+	ret = bq2415x_detect_revision(bq);
+	if (ret < 0)
+		strcpy(revstr, "unknown");
+	else
+		sprintf(revstr, "1.%d", ret);
+
+	bq->model = kasprintf(GFP_KERNEL,
+				"chip %s, revision %s, vender code %.3d",
+				bq2415x_chip_name[chip], revstr,
+				bq2415x_get_vender_code(bq));
+	if (!bq->model) {
+		dev_err(bq->dev, "failed to allocate model name\n");
+		return -ENOMEM;
+	}
+
+	ret = power_supply_register(bq->dev, &bq->charger);
+	if (ret) {
+		kfree(bq->model);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void bq2415x_power_supply_exit(struct bq2415x_device *bq)
+{
+	bq->autotimer = 0;
+	if (bq->automode > 0)
+		bq->automode = 0;
+	cancel_delayed_work_sync(&bq->work);
+	power_supply_unregister(&bq->charger);
+	kfree(bq->model);
+}
+
+/**** additional sysfs entries for power supply interface ****/
+
+/* show *_status entries */
+static ssize_t bq2415x_sysfs_show_status(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	enum bq2415x_command command;
+	int ret;
+
+	if (strcmp(attr->attr.name, "otg_status") == 0)
+		command = BQ2415X_OTG_STATUS;
+	else if (strcmp(attr->attr.name, "charge_status") == 0)
+		command = BQ2415X_CHARGE_STATUS;
+	else if (strcmp(attr->attr.name, "boost_status") == 0)
+		command = BQ2415X_BOOST_STATUS;
+	else if (strcmp(attr->attr.name, "fault_status") == 0)
+		command = BQ2415X_FAULT_STATUS;
+	else
+		return -EINVAL;
+
+	ret = bq2415x_exec_command(bq, command);
+	if (ret < 0)
+		return ret;
+	else
+		return sprintf(buf, "%d\n", ret);
+}
+
+/* set timer entry:
+     auto - enable auto mode
+     off - disable auto mode
+     (other values) - reset chip timer
+*/
+static ssize_t bq2415x_sysfs_set_timer(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	int ret = 0;
+
+	if (strncmp(buf, "auto", 4) == 0)
+		bq2415x_set_autotimer(bq, 1);
+	else if (strncmp(buf, "off", 3) == 0)
+		bq2415x_set_autotimer(bq, 0);
+	else
+		ret = bq2415x_exec_command(bq, BQ2415X_TIMER_RESET);
+
+	if (ret < 0)
+		return ret;
+	else
+		return count;
+}
+
+/* show timer entry (auto or off) */
+static ssize_t bq2415x_sysfs_show_timer(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+
+	if (bq->timer_error)
+		return sprintf(buf, "%s\n", bq->timer_error);
+
+	if (bq->autotimer)
+		return sprintf(buf, "auto\n");
+	else
+		return sprintf(buf, "off\n");
+}
+
+/* set mode entry:
+     auto - if automode is supported, enable it and set mode to reported
+     none - disable charger and boost mode
+     host - charging mode for host/hub chargers (current limit 500mA)
+     dedicated - charging mode for dedicated chargers (unlimited current limit)
+     boost - disable charger and enable boost mode
+*/
+static ssize_t bq2415x_sysfs_set_mode(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	enum bq2415x_mode mode;
+	int ret = 0;
+
+	if (strncmp(buf, "auto", 4) == 0) {
+		if (bq->automode < 0)
+			return -ENOSYS;
+		bq->automode = 1;
+		mode = bq->reported_mode;
+	} else if (strncmp(buf, "none", 4) == 0) {
+		if (bq->automode > 0)
+			bq->automode = 0;
+		mode = BQ2415X_MODE_NONE;
+	} else if (strncmp(buf, "host", 4) == 0) {
+		if (bq->automode > 0)
+			bq->automode = 0;
+		mode = BQ2415X_MODE_HOST_CHARGER;
+	} else if (strncmp(buf, "dedicated", 9) == 0) {
+		if (bq->automode > 0)
+			bq->automode = 0;
+		mode = BQ2415X_MODE_DEDICATED_CHARGER;
+	} else if (strncmp(buf, "boost", 5) == 0) {
+		if (bq->automode > 0)
+			bq->automode = 0;
+		mode = BQ2415X_MODE_BOOST;
+	} else if (strncmp(buf, "reset", 5) == 0) {
+		bq2415x_reset_chip(bq);
+		bq2415x_set_defaults(bq);
+		if (bq->automode <= 0)
+			return count;
+		bq->automode = 1;
+		mode = bq->reported_mode;
+	} else
+		return -EINVAL;
+
+	ret = bq2415x_set_mode(bq, mode);
+	if (ret < 0)
+		return ret;
+	else
+		return count;
+}
+
+/* show mode entry (auto, none, host, dedicated or boost) */
+static ssize_t bq2415x_sysfs_show_mode(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	ssize_t ret = 0;
+
+	if (bq->automode > 0)
+		ret += sprintf(buf+ret, "auto (");
+
+	switch (bq->mode) {
+	case BQ2415X_MODE_NONE:
+		ret += sprintf(buf+ret, "none");
+		break;
+	case BQ2415X_MODE_HOST_CHARGER:
+		ret += sprintf(buf+ret, "host");
+		break;
+	case BQ2415X_MODE_DEDICATED_CHARGER:
+		ret += sprintf(buf+ret, "dedicated");
+		break;
+	case BQ2415X_MODE_BOOST:
+		ret += sprintf(buf+ret, "boost");
+		break;
+	}
+
+	if (bq->automode > 0)
+		ret += sprintf(buf+ret, ")");
+
+	ret += sprintf(buf+ret, "\n");
+	return ret;
+}
+
+/* show reported_mode entry (none, host, dedicated or boost) */
+static ssize_t bq2415x_sysfs_show_reported_mode(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+
+	if (bq->automode < 0)
+		return -EINVAL;
+
+	switch (bq->reported_mode) {
+	case BQ2415X_MODE_NONE:
+		return sprintf(buf, "none\n");
+	case BQ2415X_MODE_HOST_CHARGER:
+		return sprintf(buf, "host\n");
+	case BQ2415X_MODE_DEDICATED_CHARGER:
+		return sprintf(buf, "dedicated\n");
+	case BQ2415X_MODE_BOOST:
+		return sprintf(buf, "boost\n");
+	}
+
+	return -EINVAL;
+}
+
+/* directly set raw value to chip register, format: 'register value' */
+static ssize_t bq2415x_sysfs_set_registers(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	ssize_t ret = 0;
+	unsigned int reg;
+	unsigned int val;
+
+	if (sscanf(buf, "%x %x", &reg, &val) != 2)
+		return -EINVAL;
+
+	if (reg > 4 || val > 255)
+		return -EINVAL;
+
+	ret = bq2415x_i2c_write(bq, reg, val);
+	if (ret < 0)
+		return ret;
+	else
+		return count;
+}
+
+/* print value of chip register, format: 'register=value' */
+static ssize_t bq2415x_sysfs_print_reg(struct bq2415x_device *bq,
+					u8 reg, char *buf)
+{
+	int ret = bq2415x_i2c_read(bq, reg);
+	if (ret < 0)
+		return sprintf(buf, "%#.2x=error %d\n", reg, ret);
+	else
+		return sprintf(buf, "%#.2x=%#.2x\n", reg, ret);
+}
+
+/* show all raw values of chip register, format per line: 'register=value' */
+static ssize_t bq2415x_sysfs_show_registers(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	ssize_t ret = 0;
+
+	ret += bq2415x_sysfs_print_reg(bq, BQ2415X_REG_STATUS, buf+ret);
+	ret += bq2415x_sysfs_print_reg(bq, BQ2415X_REG_CONTROL, buf+ret);
+	ret += bq2415x_sysfs_print_reg(bq, BQ2415X_REG_VOLTAGE, buf+ret);
+	ret += bq2415x_sysfs_print_reg(bq, BQ2415X_REG_VENDER, buf+ret);
+	ret += bq2415x_sysfs_print_reg(bq, BQ2415X_REG_CURRENT, buf+ret);
+	return ret;
+}
+
+/* set current and voltage limit entries (in mA or mV) */
+static ssize_t bq2415x_sysfs_set_limit(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	long val;
+	int ret;
+
+	if (kstrtol(buf, 10, &val) < 0)
+		return -EINVAL;
+
+	if (strcmp(attr->attr.name, "current_limit") == 0)
+		ret = bq2415x_set_current_limit(bq, val);
+	else if (strcmp(attr->attr.name, "weak_battery_voltage") == 0)
+		ret = bq2415x_set_weak_battery_voltage(bq, val);
+	else if (strcmp(attr->attr.name, "battery_regulation_voltage") == 0)
+		ret = bq2415x_set_battery_regulation_voltage(bq, val);
+	else if (strcmp(attr->attr.name, "charge_current") == 0)
+		ret = bq2415x_set_charge_current(bq, val);
+	else if (strcmp(attr->attr.name, "termination_current") == 0)
+		ret = bq2415x_set_termination_current(bq, val);
+	else
+		return -EINVAL;
+
+	if (ret < 0)
+		return ret;
+	else
+		return count;
+}
+
+/* show current and voltage limit entries (in mA or mV) */
+static ssize_t bq2415x_sysfs_show_limit(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	int ret;
+
+	if (strcmp(attr->attr.name, "current_limit") == 0)
+		ret = bq2415x_get_current_limit(bq);
+	else if (strcmp(attr->attr.name, "weak_battery_voltage") == 0)
+		ret = bq2415x_get_weak_battery_voltage(bq);
+	else if (strcmp(attr->attr.name, "battery_regulation_voltage") == 0)
+		ret = bq2415x_get_battery_regulation_voltage(bq);
+	else if (strcmp(attr->attr.name, "charge_current") == 0)
+		ret = bq2415x_get_charge_current(bq);
+	else if (strcmp(attr->attr.name, "termination_current") == 0)
+		ret = bq2415x_get_termination_current(bq);
+	else
+		return -EINVAL;
+
+	if (ret < 0)
+		return ret;
+	else
+		return sprintf(buf, "%d\n", ret);
+}
+
+/* set *_enable entries */
+static ssize_t bq2415x_sysfs_set_enable(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	enum bq2415x_command command;
+	long val;
+	int ret;
+
+	if (kstrtol(buf, 10, &val) < 0)
+		return -EINVAL;
+
+	if (strcmp(attr->attr.name, "charge_termination_enable") == 0)
+		command = val ? BQ2415X_CHARGE_TERMINATION_ENABLE :
+			BQ2415X_CHARGE_TERMINATION_DISABLE;
+	else if (strcmp(attr->attr.name, "high_impedance_enable") == 0)
+		command = val ? BQ2415X_HIGH_IMPEDANCE_ENABLE :
+			BQ2415X_HIGH_IMPEDANCE_DISABLE;
+	else if (strcmp(attr->attr.name, "otg_pin_enable") == 0)
+		command = val ? BQ2415X_OTG_PIN_ENABLE :
+			BQ2415X_OTG_PIN_DISABLE;
+	else if (strcmp(attr->attr.name, "stat_pin_enable") == 0)
+		command = val ? BQ2415X_STAT_PIN_ENABLE :
+			BQ2415X_STAT_PIN_DISABLE;
+	else
+		return -EINVAL;
+
+	ret = bq2415x_exec_command(bq, command);
+	if (ret < 0)
+		return ret;
+	else
+		return count;
+}
+
+/* show *_enable entries */
+static ssize_t bq2415x_sysfs_show_enable(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
+						charger);
+	enum bq2415x_command command;
+	int ret;
+
+	if (strcmp(attr->attr.name, "charge_termination_enable") == 0)
+		command = BQ2415X_CHARGE_TERMINATION_STATUS;
+	else if (strcmp(attr->attr.name, "high_impedance_enable") == 0)
+		command = BQ2415X_HIGH_IMPEDANCE_STATUS;
+	else if (strcmp(attr->attr.name, "otg_pin_enable") == 0)
+		command = BQ2415X_OTG_PIN_STATUS;
+	else if (strcmp(attr->attr.name, "stat_pin_enable") == 0)
+		command = BQ2415X_STAT_PIN_STATUS;
+	else
+		return -EINVAL;
+
+	ret = bq2415x_exec_command(bq, command);
+	if (ret < 0)
+		return ret;
+	else
+		return sprintf(buf, "%d\n", ret);
+}
+
+static DEVICE_ATTR(current_limit, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_limit, bq2415x_sysfs_set_limit);
+static DEVICE_ATTR(weak_battery_voltage, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_limit, bq2415x_sysfs_set_limit);
+static DEVICE_ATTR(battery_regulation_voltage, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_limit, bq2415x_sysfs_set_limit);
+static DEVICE_ATTR(charge_current, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_limit, bq2415x_sysfs_set_limit);
+static DEVICE_ATTR(termination_current, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_limit, bq2415x_sysfs_set_limit);
+
+static DEVICE_ATTR(charge_termination_enable, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_enable, bq2415x_sysfs_set_enable);
+static DEVICE_ATTR(high_impedance_enable, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_enable, bq2415x_sysfs_set_enable);
+static DEVICE_ATTR(otg_pin_enable, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_enable, bq2415x_sysfs_set_enable);
+static DEVICE_ATTR(stat_pin_enable, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_enable, bq2415x_sysfs_set_enable);
+
+static DEVICE_ATTR(reported_mode, S_IRUGO,
+		bq2415x_sysfs_show_reported_mode, NULL);
+static DEVICE_ATTR(mode, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_mode, bq2415x_sysfs_set_mode);
+static DEVICE_ATTR(timer, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_timer, bq2415x_sysfs_set_timer);
+
+static DEVICE_ATTR(registers, S_IWUSR | S_IRUGO,
+		bq2415x_sysfs_show_registers, bq2415x_sysfs_set_registers);
+
+static DEVICE_ATTR(otg_status, S_IRUGO, bq2415x_sysfs_show_status, NULL);
+static DEVICE_ATTR(charge_status, S_IRUGO, bq2415x_sysfs_show_status, NULL);
+static DEVICE_ATTR(boost_status, S_IRUGO, bq2415x_sysfs_show_status, NULL);
+static DEVICE_ATTR(fault_status, S_IRUGO, bq2415x_sysfs_show_status, NULL);
+
+static struct attribute *bq2415x_sysfs_attributes[] = {
+	&dev_attr_current_limit.attr,
+	&dev_attr_weak_battery_voltage.attr,
+	&dev_attr_battery_regulation_voltage.attr,
+	&dev_attr_charge_current.attr,
+	&dev_attr_termination_current.attr,
+
+	&dev_attr_charge_termination_enable.attr,
+	&dev_attr_high_impedance_enable.attr,
+	&dev_attr_otg_pin_enable.attr,
+	&dev_attr_stat_pin_enable.attr,
+
+	&dev_attr_reported_mode.attr,
+	&dev_attr_mode.attr,
+	&dev_attr_timer.attr,
+
+	&dev_attr_registers.attr,
+
+	&dev_attr_otg_status.attr,
+	&dev_attr_charge_status.attr,
+	&dev_attr_boost_status.attr,
+	&dev_attr_fault_status.attr,
+	NULL,
+};
+
+static const struct attribute_group bq2415x_sysfs_attr_group = {
+	.attrs = bq2415x_sysfs_attributes,
+};
+
+static int bq2415x_sysfs_init(struct bq2415x_device *bq)
+{
+	return sysfs_create_group(&bq->charger.dev->kobj,
+			&bq2415x_sysfs_attr_group);
+}
+
+static void bq2415x_sysfs_exit(struct bq2415x_device *bq)
+{
+	sysfs_remove_group(&bq->charger.dev->kobj, &bq2415x_sysfs_attr_group);
+}
+
+/* main bq2415x probe function */
+static int bq2415x_probe(struct i2c_client *client,
+		const struct i2c_device_id *id)
+{
+	int ret;
+	int num;
+	char *name;
+	struct bq2415x_device *bq;
+
+	if (!client->dev.platform_data) {
+		dev_err(&client->dev, "platform data not set\n");
+		return -ENODEV;
+	}
+
+	/* Get new ID for the new device */
+	ret = idr_pre_get(&bq2415x_id, GFP_KERNEL);
+	if (ret == 0)
+		return -ENOMEM;
+
+	mutex_lock(&bq2415x_id_mutex);
+	ret = idr_get_new(&bq2415x_id, client, &num);
+	mutex_unlock(&bq2415x_id_mutex);
+
+	if (ret < 0)
+		return ret;
+
+	name = kasprintf(GFP_KERNEL, "%s-%d", id->name, num);
+	if (!name) {
+		dev_err(&client->dev, "failed to allocate device name\n");
+		ret = -ENOMEM;
+		goto error_1;
+	}
+
+	bq = kzalloc(sizeof(*bq), GFP_KERNEL);
+	if (!bq) {
+		dev_err(&client->dev, "failed to allocate device data\n");
+		ret = -ENOMEM;
+		goto error_2;
+	}
+
+	i2c_set_clientdata(client, bq);
+
+	bq->id = num;
+	bq->dev = &client->dev;
+	bq->chip = id->driver_data;
+	bq->name = name;
+	bq->mode = BQ2415X_MODE_NONE;
+	bq->reported_mode = BQ2415X_MODE_NONE;
+	bq->autotimer = 0;
+	bq->automode = 0;
+
+	memcpy(&bq->init_data, client->dev.platform_data,
+			sizeof(bq->init_data));
+
+	bq2415x_reset_chip(bq);
+
+	ret = bq2415x_power_supply_init(bq);
+	if (ret) {
+		dev_err(bq->dev, "failed to register power supply: %d\n", ret);
+		goto error_3;
+	}
+
+	ret = bq2415x_sysfs_init(bq);
+	if (ret) {
+		dev_err(bq->dev, "failed to create sysfs entries: %d\n", ret);
+		goto error_4;
+	}
+
+	ret = bq2415x_set_defaults(bq);
+	if (ret) {
+		dev_err(bq->dev, "failed to set default values: %d\n", ret);
+		goto error_5;
+	}
+
+	if (bq->init_data.set_mode_hook) {
+		if (bq->init_data.set_mode_hook(
+				bq2415x_hook_function, bq)) {
+			bq->automode = 1;
+			bq2415x_set_mode(bq, bq->reported_mode);
+			dev_info(bq->dev, "automode enabled\n");
+		} else {
+			bq->automode = -1;
+			dev_info(bq->dev, "automode failed\n");
+		}
+	} else {
+		bq->automode = -1;
+		dev_info(bq->dev, "automode not supported\n");
+	}
+
+	INIT_DELAYED_WORK(&bq->work, bq2415x_timer_work);
+	bq2415x_set_autotimer(bq, 1);
+
+	dev_info(bq->dev, "driver registered\n");
+	return 0;
+
+error_5:
+	bq2415x_sysfs_exit(bq);
+error_4:
+	bq2415x_power_supply_exit(bq);
+error_3:
+	kfree(bq);
+error_2:
+	kfree(name);
+error_1:
+	mutex_lock(&bq2415x_id_mutex);
+	idr_remove(&bq2415x_id, num);
+	mutex_unlock(&bq2415x_id_mutex);
+
+	return ret;
+}
+
+/* main bq2415x remove function */
+
+static int bq2415x_remove(struct i2c_client *client)
+{
+	struct bq2415x_device *bq = i2c_get_clientdata(client);
+
+	if (bq->init_data.set_mode_hook)
+		bq->init_data.set_mode_hook(NULL, NULL);
+
+	bq2415x_sysfs_exit(bq);
+	bq2415x_power_supply_exit(bq);
+
+	bq2415x_reset_chip(bq);
+
+	mutex_lock(&bq2415x_id_mutex);
+	idr_remove(&bq2415x_id, bq->id);
+	mutex_unlock(&bq2415x_id_mutex);
+
+	dev_info(bq->dev, "driver unregistered\n");
+
+	kfree(bq->name);
+	kfree(bq);
+
+	return 0;
+}
+
+static const struct i2c_device_id bq2415x_i2c_id_table[] = {
+	{ "bq2415x", BQUNKNOWN },
+	{ "bq24150", BQ24150 },
+	{ "bq24150a", BQ24150A },
+	{ "bq24151", BQ24151 },
+	{ "bq24151a", BQ24151A },
+	{ "bq24152", BQ24152 },
+	{ "bq24153", BQ24153 },
+	{ "bq24153a", BQ24153A },
+	{ "bq24155", BQ24155 },
+	{ "bq24156", BQ24156 },
+	{ "bq24156a", BQ24156A },
+	{ "bq24158", BQ24158 },
+	{},
+};
+MODULE_DEVICE_TABLE(i2c, bq2415x_i2c_id_table);
+
+static struct i2c_driver bq2415x_driver = {
+	.driver = {
+		.name = "bq2415x-charger",
+	},
+	.probe = bq2415x_probe,
+	.remove = bq2415x_remove,
+	.id_table = bq2415x_i2c_id_table,
+};
+
+static int __init bq2415x_init(void)
+{
+	return i2c_add_driver(&bq2415x_driver);
+}
+module_init(bq2415x_init);
+
+static void __exit bq2415x_exit(void)
+{
+	i2c_del_driver(&bq2415x_driver);
+}
+module_exit(bq2415x_exit);
+
+MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>");
+MODULE_DESCRIPTION("bq2415x charger driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/power/bq2415x_charger.h b/include/linux/power/bq2415x_charger.h
new file mode 100644
index 000000000000..fb6bf4d8aea8
--- /dev/null
+++ b/include/linux/power/bq2415x_charger.h
@@ -0,0 +1,90 @@
+/*
+    bq2415x_charger.h - bq2415x charger driver
+    Copyright (C) 2011-2012  Pali Rohár <pali.rohar@gmail.com>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+*/
+
+#ifndef BQ2415X_CHARGER_H
+#define BQ2415X_CHARGER_H
+
+/*
+  This is platform data for bq2415x chip. It contains default board voltages
+  and currents which can be also later configured via sysfs. If value is -1
+  then default chip value (specified in datasheet) will be used.
+
+  Value resistor_sense is needed for for configuring charge and termination
+  current. It it is less or equal to zero, configuring charge and termination
+  current will not be possible.
+
+  Function set_mode_hook is needed for automode (setting correct current limit
+  when charger is connected/disconnected or setting boost mode). When is NULL,
+  automode function is disabled. When is not NULL, it must have this prototype:
+
+    int (*set_mode_hook)(
+      void (*hook)(enum bq2415x_mode mode, void *data),
+      void *data)
+
+  hook is hook function (see below) and data is pointer to driver private data
+
+  bq2415x driver will call it as:
+
+    platform_data->set_mode_hook(bq2415x_hook_function, bq2415x_device);
+
+  Board/platform function set_mode_hook return non zero value when hook
+  function was successful registered. Platform code should call that hook
+  function (which get from pointer, with data) every time when charger was
+  connected/disconnected or require to enable boost mode. bq2415x driver then
+  will set correct current limit, enable/disable charger or boost mode.
+
+  Hook function has this prototype:
+
+    void hook(enum bq2415x_mode mode, void *data);
+
+  mode is bq2415x mode (charger or boost)
+  data is pointer to driver private data (which get from set_charger_type_hook)
+
+  When bq driver is being unloaded, it call function:
+
+    platform_data->set_mode_hook(NULL, NULL);
+
+  (hook function and driver private data are NULL)
+
+  After that board/platform code must not call driver hook function! It is
+  possible that pointer to hook function will not be valid and calling will
+  cause undefined result.
+
+*/
+
+/* Supported modes with maximal current limit */
+enum bq2415x_mode {
+	BQ2415X_MODE_NONE,		/* unknown or no charger (100mA) */
+	BQ2415X_MODE_HOST_CHARGER,	/* usb host/hub charger (500mA) */
+	BQ2415X_MODE_DEDICATED_CHARGER, /* dedicated charger (unlimited) */
+	BQ2415X_MODE_BOOST,		/* boost mode (charging disabled) */
+};
+
+struct bq2415x_platform_data {
+	int current_limit;		/* mA */
+	int weak_battery_voltage;	/* mV */
+	int battery_regulation_voltage;	/* mV */
+	int charge_current;		/* mA */
+	int termination_current;	/* mA */
+	int resistor_sense;		/* m ohm */
+	int (*set_mode_hook)(void (*hook)(enum bq2415x_mode mode, void *data),
+			     void *data);
+};
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 6c47a3e00c6e4f3cdac7566c1480de34d9e32e07 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov
Date: Sun, 18 Nov 2012 15:35:32 -0800
Subject: bq2415x_charger: Fix style issues

I hate doing these style fixups myself, but I also hate inconsitent code.
Normally I just ask to resubmit the patch with the issues fixed, but N900
is special: I have a selfish interest in it. :)

Signed-off-by: Anton Vorontsov <cbouatmailru@gmail.com>
---
 drivers/power/bq2415x_charger.c       | 268 +++++++++++++++++++---------------
 include/linux/power/bq2415x_charger.h | 131 +++++++++--------
 2 files changed, 215 insertions(+), 184 deletions(-)

(limited to 'include')

diff --git a/drivers/power/bq2415x_charger.c b/drivers/power/bq2415x_charger.c
index 017b3c27f769..ee842b37f462 100644
--- a/drivers/power/bq2415x_charger.c
+++ b/drivers/power/bq2415x_charger.c
@@ -1,31 +1,32 @@
 /*
-    bq2415x_charger.c - bq2415x charger driver
-    Copyright (C) 2011-2012  Pali Rohár <pali.rohar@gmail.com>
-
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License along
-    with this program; if not, write to the Free Software Foundation, Inc.,
-    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
-*/
+ * bq2415x charger driver
+ *
+ * Copyright (C) 2011-2012  Pali Rohár <pali.rohar@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
 
 /*
-  Datasheets:
-  http://www.ti.com/product/bq24150
-  http://www.ti.com/product/bq24150a
-  http://www.ti.com/product/bq24152
-  http://www.ti.com/product/bq24153
-  http://www.ti.com/product/bq24153a
-  http://www.ti.com/product/bq24155
-*/
+ * Datasheets:
+ * http://www.ti.com/product/bq24150
+ * http://www.ti.com/product/bq24150a
+ * http://www.ti.com/product/bq24152
+ * http://www.ti.com/product/bq24153
+ * http://www.ti.com/product/bq24153a
+ * http://www.ti.com/product/bq24155
+ */
 
 #include <linux/version.h>
 #include <linux/kernel.h>
@@ -222,7 +223,7 @@ static int bq2415x_i2c_read(struct bq2415x_device *bq, u8 reg)
 
 /* read value from register, apply mask and right shift it */
 static int bq2415x_i2c_read_mask(struct bq2415x_device *bq, u8 reg,
-				u8 mask, u8 shift)
+				 u8 mask, u8 shift)
 {
 	int ret;
 
@@ -232,8 +233,7 @@ static int bq2415x_i2c_read_mask(struct bq2415x_device *bq, u8 reg,
 	ret = bq2415x_i2c_read(bq, reg);
 	if (ret < 0)
 		return ret;
-	else
-		return (ret & mask) >> shift;
+	return (ret & mask) >> shift;
 }
 
 /* read value from register and return one specified bit */
@@ -241,8 +241,7 @@ static int bq2415x_i2c_read_bit(struct bq2415x_device *bq, u8 reg, u8 bit)
 {
 	if (bit > 8)
 		return -EINVAL;
-	else
-		return bq2415x_i2c_read_mask(bq, reg, BIT(bit), bit);
+	return bq2415x_i2c_read_mask(bq, reg, BIT(bit), bit);
 }
 
 /**** i2c write functions ****/
@@ -278,7 +277,7 @@ static int bq2415x_i2c_write(struct bq2415x_device *bq, u8 reg, u8 val)
 
 /* read value from register, change it with mask left shifted and write back */
 static int bq2415x_i2c_write_mask(struct bq2415x_device *bq, u8 reg, u8 val,
-				u8 mask, u8 shift)
+				  u8 mask, u8 shift)
 {
 	int ret;
 
@@ -297,12 +296,11 @@ static int bq2415x_i2c_write_mask(struct bq2415x_device *bq, u8 reg, u8 val,
 
 /* change only one bit in register */
 static int bq2415x_i2c_write_bit(struct bq2415x_device *bq, u8 reg,
-				bool val, u8 bit)
+				 bool val, u8 bit)
 {
 	if (bit > 8)
 		return -EINVAL;
-	else
-		return bq2415x_i2c_write_mask(bq, reg, val, BIT(bit), bit);
+	return bq2415x_i2c_write_mask(bq, reg, val, BIT(bit), bit);
 }
 
 /**** global functions ****/
@@ -312,6 +310,7 @@ static int bq2415x_exec_command(struct bq2415x_device *bq,
 				enum bq2415x_command command)
 {
 	int ret;
+
 	switch (command) {
 	case BQ2415X_TIMER_RESET:
 		return bq2415x_i2c_write_bit(bq, BQ2415X_REG_STATUS,
@@ -407,10 +406,8 @@ static int bq2415x_exec_command(struct bq2415x_device *bq,
 	case BQ2415X_REVISION:
 		return bq2415x_i2c_read_mask(bq, BQ2415X_REG_VENDER,
 			BQ2415X_MASK_REVISION, BQ2415X_SHIFT_REVISION);
-
-	default:
-		return -EINVAL;
 	}
+	return -EINVAL;
 }
 
 /* detect chip type */
@@ -470,6 +467,7 @@ static int bq2415x_detect_revision(struct bq2415x_device *bq)
 {
 	int ret = bq2415x_exec_command(bq, BQ2415X_REVISION);
 	int chip = bq2415x_detect_chip(bq);
+
 	if (ret < 0 || chip < 0)
 		return -1;
 
@@ -483,7 +481,6 @@ static int bq2415x_detect_revision(struct bq2415x_device *bq)
 			return ret;
 		else
 			return -1;
-
 	case BQ24153:
 	case BQ24153A:
 	case BQ24156:
@@ -495,13 +492,11 @@ static int bq2415x_detect_revision(struct bq2415x_device *bq)
 			return 1;
 		else
 			return -1;
-
 	case BQ24155:
 		if (ret == 3)
 			return 3;
 		else
 			return -1;
-
 	case BQUNKNOWN:
 		return -1;
 	}
@@ -512,13 +507,16 @@ static int bq2415x_detect_revision(struct bq2415x_device *bq)
 /* return chip vender code */
 static int bq2415x_get_vender_code(struct bq2415x_device *bq)
 {
-	int ret = bq2415x_exec_command(bq, BQ2415X_VENDER_CODE);
+	int ret;
+
+	ret = bq2415x_exec_command(bq, BQ2415X_VENDER_CODE);
 	if (ret < 0)
 		return 0;
-	else /* convert to binary */
-		return (ret & 0x1) +
-			((ret >> 1) & 0x1) * 10 +
-			((ret >> 2) & 0x1) * 100;
+
+	/* convert to binary */
+	return (ret & 0x1) +
+	       ((ret >> 1) & 0x1) * 10 +
+	       ((ret >> 2) & 0x1) * 100;
 }
 
 /* reset all chip registers to default state */
@@ -537,6 +535,7 @@ static void bq2415x_reset_chip(struct bq2415x_device *bq)
 static int bq2415x_set_current_limit(struct bq2415x_device *bq, int mA)
 {
 	int val;
+
 	if (mA <= 100)
 		val = 0;
 	else if (mA <= 500)
@@ -545,6 +544,7 @@ static int bq2415x_set_current_limit(struct bq2415x_device *bq, int mA)
 		val = 2;
 	else
 		val = 3;
+
 	return bq2415x_i2c_write_mask(bq, BQ2415X_REG_CONTROL, val,
 			BQ2415X_MASK_LIMIT, BQ2415X_SHIFT_LIMIT);
 }
@@ -552,7 +552,9 @@ static int bq2415x_set_current_limit(struct bq2415x_device *bq, int mA)
 /* get current limit in mA */
 static int bq2415x_get_current_limit(struct bq2415x_device *bq)
 {
-	int ret = bq2415x_i2c_read_mask(bq, BQ2415X_REG_CONTROL,
+	int ret;
+
+	ret = bq2415x_i2c_read_mask(bq, BQ2415X_REG_CONTROL,
 			BQ2415X_MASK_LIMIT, BQ2415X_SHIFT_LIMIT);
 	if (ret < 0)
 		return ret;
@@ -564,15 +566,15 @@ static int bq2415x_get_current_limit(struct bq2415x_device *bq)
 		return 800;
 	else if (ret == 3)
 		return 1800;
-	else
-		return -EINVAL;
+	return -EINVAL;
 }
 
 /* set weak battery voltage in mV */
 static int bq2415x_set_weak_battery_voltage(struct bq2415x_device *bq, int mV)
 {
-	/* round to 100mV */
 	int val;
+
+	/* round to 100mV */
 	if (mV <= 3400 + 50)
 		val = 0;
 	else if (mV <= 3500 + 50)
@@ -581,6 +583,7 @@ static int bq2415x_set_weak_battery_voltage(struct bq2415x_device *bq, int mV)
 		val = 2;
 	else
 		val = 3;
+
 	return bq2415x_i2c_write_mask(bq, BQ2415X_REG_CONTROL, val,
 			BQ2415X_MASK_VLOWV, BQ2415X_SHIFT_VLOWV);
 }
@@ -588,17 +591,18 @@ static int bq2415x_set_weak_battery_voltage(struct bq2415x_device *bq, int mV)
 /* get weak battery voltage in mV */
 static int bq2415x_get_weak_battery_voltage(struct bq2415x_device *bq)
 {
-	int ret = bq2415x_i2c_read_mask(bq, BQ2415X_REG_CONTROL,
+	int ret;
+
+	ret = bq2415x_i2c_read_mask(bq, BQ2415X_REG_CONTROL,
 			BQ2415X_MASK_VLOWV, BQ2415X_SHIFT_VLOWV);
 	if (ret < 0)
 		return ret;
-	else
-		return 100 * (34 + ret);
+	return 100 * (34 + ret);
 }
 
 /* set battery regulation voltage in mV */
 static int bq2415x_set_battery_regulation_voltage(struct bq2415x_device *bq,
-						int mV)
+						  int mV)
 {
 	int val = (mV/10 - 350) / 2;
 
@@ -616,21 +620,21 @@ static int bq2415x_get_battery_regulation_voltage(struct bq2415x_device *bq)
 {
 	int ret = bq2415x_i2c_read_mask(bq, BQ2415X_REG_VOLTAGE,
 			BQ2415X_MASK_VO, BQ2415X_SHIFT_VO);
+
 	if (ret < 0)
 		return ret;
-	else
-		return 10 * (350 + 2*ret);
+	return 10 * (350 + 2*ret);
 }
 
 /* set charge current in mA (platform data must provide resistor sense) */
 static int bq2415x_set_charge_current(struct bq2415x_device *bq, int mA)
 {
 	int val;
+
 	if (bq->init_data.resistor_sense <= 0)
 		return -ENOSYS;
 
 	val = (mA * bq->init_data.resistor_sense - 37400) / 6800;
-
 	if (val < 0)
 		val = 0;
 	else if (val > 7)
@@ -645,6 +649,7 @@ static int bq2415x_set_charge_current(struct bq2415x_device *bq, int mA)
 static int bq2415x_get_charge_current(struct bq2415x_device *bq)
 {
 	int ret;
+
 	if (bq->init_data.resistor_sense <= 0)
 		return -ENOSYS;
 
@@ -652,19 +657,18 @@ static int bq2415x_get_charge_current(struct bq2415x_device *bq)
 			BQ2415X_MASK_VI_CHRG, BQ2415X_SHIFT_VI_CHRG);
 	if (ret < 0)
 		return ret;
-	else
-		return (37400 + 6800*ret) / bq->init_data.resistor_sense;
+	return (37400 + 6800*ret) / bq->init_data.resistor_sense;
 }
 
 /* set termination current in mA (platform data must provide resistor sense) */
 static int bq2415x_set_termination_current(struct bq2415x_device *bq, int mA)
 {
 	int val;
+
 	if (bq->init_data.resistor_sense <= 0)
 		return -ENOSYS;
 
 	val = (mA * bq->init_data.resistor_sense - 3400) / 3400;
-
 	if (val < 0)
 		val = 0;
 	else if (val > 7)
@@ -679,6 +683,7 @@ static int bq2415x_set_termination_current(struct bq2415x_device *bq, int mA)
 static int bq2415x_get_termination_current(struct bq2415x_device *bq)
 {
 	int ret;
+
 	if (bq->init_data.resistor_sense <= 0)
 		return -ENOSYS;
 
@@ -686,8 +691,7 @@ static int bq2415x_get_termination_current(struct bq2415x_device *bq)
 			BQ2415X_MASK_VI_TERM, BQ2415X_SHIFT_VI_TERM);
 	if (ret < 0)
 		return ret;
-	else
-		return (3400 + 3400*ret) / bq->init_data.resistor_sense;
+	return (3400 + 3400*ret) / bq->init_data.resistor_sense;
 }
 
 /* set default value of property */
@@ -706,14 +710,17 @@ static int bq2415x_set_defaults(struct bq2415x_device *bq)
 	bq2415x_exec_command(bq, BQ2415X_BOOST_MODE_DISABLE);
 	bq2415x_exec_command(bq, BQ2415X_CHARGER_DISABLE);
 	bq2415x_exec_command(bq, BQ2415X_CHARGE_TERMINATION_DISABLE);
+
 	bq2415x_set_default_value(bq, current_limit);
 	bq2415x_set_default_value(bq, weak_battery_voltage);
 	bq2415x_set_default_value(bq, battery_regulation_voltage);
+
 	if (bq->init_data.resistor_sense > 0) {
 		bq2415x_set_default_value(bq, charge_current);
 		bq2415x_set_default_value(bq, termination_current);
 		bq2415x_exec_command(bq, BQ2415X_CHARGE_TERMINATION_ENABLE);
 	}
+
 	bq2415x_exec_command(bq, BQ2415X_CHARGER_ENABLE);
 	return 0;
 }
@@ -844,8 +851,10 @@ static void bq2415x_timer_error(struct bq2415x_device *bq, const char *msg)
 static void bq2415x_timer_work(struct work_struct *work)
 {
 	struct bq2415x_device *bq = container_of(work, struct bq2415x_device,
-						work.work);
-	int ret, error, boost;
+						 work.work);
+	int ret;
+	int error;
+	int boost;
 
 	if (!bq->autotimer)
 		return;
@@ -946,10 +955,11 @@ static enum power_supply_property bq2415x_power_supply_props[] = {
 };
 
 static int bq2415x_power_supply_get_property(struct power_supply *psy,
-	enum power_supply_property psp, union power_supply_propval *val)
+					     enum power_supply_property psp,
+					     union power_supply_propval *val)
 {
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
-						charger);
+						 charger);
 	int ret;
 
 	switch (psp) {
@@ -1031,7 +1041,8 @@ static void bq2415x_power_supply_exit(struct bq2415x_device *bq)
 
 /* show *_status entries */
 static ssize_t bq2415x_sysfs_show_status(struct device *dev,
-		struct device_attribute *attr, char *buf)
+					 struct device_attribute *attr,
+					 char *buf)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
@@ -1053,17 +1064,19 @@ static ssize_t bq2415x_sysfs_show_status(struct device *dev,
 	ret = bq2415x_exec_command(bq, command);
 	if (ret < 0)
 		return ret;
-	else
-		return sprintf(buf, "%d\n", ret);
+	return sprintf(buf, "%d\n", ret);
 }
 
-/* set timer entry:
-     auto - enable auto mode
-     off - disable auto mode
-     (other values) - reset chip timer
-*/
+/*
+ * set timer entry:
+ *    auto - enable auto mode
+ *    off - disable auto mode
+ *    (other values) - reset chip timer
+ */
 static ssize_t bq2415x_sysfs_set_timer(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+				       struct device_attribute *attr,
+				       const char *buf,
+				       size_t count)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
@@ -1079,40 +1092,42 @@ static ssize_t bq2415x_sysfs_set_timer(struct device *dev,
 
 	if (ret < 0)
 		return ret;
-	else
-		return count;
+	return count;
 }
 
 /* show timer entry (auto or off) */
 static ssize_t bq2415x_sysfs_show_timer(struct device *dev,
-		struct device_attribute *attr, char *buf)
+					struct device_attribute *attr,
+					char *buf)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
-						charger);
+						 charger);
 
 	if (bq->timer_error)
 		return sprintf(buf, "%s\n", bq->timer_error);
 
 	if (bq->autotimer)
 		return sprintf(buf, "auto\n");
-	else
-		return sprintf(buf, "off\n");
+	return sprintf(buf, "off\n");
 }
 
-/* set mode entry:
-     auto - if automode is supported, enable it and set mode to reported
-     none - disable charger and boost mode
-     host - charging mode for host/hub chargers (current limit 500mA)
-     dedicated - charging mode for dedicated chargers (unlimited current limit)
-     boost - disable charger and enable boost mode
-*/
+/*
+ * set mode entry:
+ *    auto - if automode is supported, enable it and set mode to reported
+ *    none - disable charger and boost mode
+ *    host - charging mode for host/hub chargers (current limit 500mA)
+ *    dedicated - charging mode for dedicated chargers (unlimited current limit)
+ *    boost - disable charger and enable boost mode
+ */
 static ssize_t bq2415x_sysfs_set_mode(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+				      struct device_attribute *attr,
+				      const char *buf,
+				      size_t count)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
-						charger);
+						 charger);
 	enum bq2415x_mode mode;
 	int ret = 0;
 
@@ -1144,19 +1159,20 @@ static ssize_t bq2415x_sysfs_set_mode(struct device *dev,
 			return count;
 		bq->automode = 1;
 		mode = bq->reported_mode;
-	} else
+	} else {
 		return -EINVAL;
+	}
 
 	ret = bq2415x_set_mode(bq, mode);
 	if (ret < 0)
 		return ret;
-	else
-		return count;
+	return count;
 }
 
 /* show mode entry (auto, none, host, dedicated or boost) */
 static ssize_t bq2415x_sysfs_show_mode(struct device *dev,
-		struct device_attribute *attr, char *buf)
+				       struct device_attribute *attr,
+				       char *buf)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
@@ -1190,11 +1206,12 @@ static ssize_t bq2415x_sysfs_show_mode(struct device *dev,
 
 /* show reported_mode entry (none, host, dedicated or boost) */
 static ssize_t bq2415x_sysfs_show_reported_mode(struct device *dev,
-		struct device_attribute *attr, char *buf)
+						struct device_attribute *attr,
+						char *buf)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
-						charger);
+						 charger);
 
 	if (bq->automode < 0)
 		return -EINVAL;
@@ -1215,11 +1232,13 @@ static ssize_t bq2415x_sysfs_show_reported_mode(struct device *dev,
 
 /* directly set raw value to chip register, format: 'register value' */
 static ssize_t bq2415x_sysfs_set_registers(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+					   struct device_attribute *attr,
+					   const char *buf,
+					   size_t count)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
-						charger);
+						 charger);
 	ssize_t ret = 0;
 	unsigned int reg;
 	unsigned int val;
@@ -1233,28 +1252,29 @@ static ssize_t bq2415x_sysfs_set_registers(struct device *dev,
 	ret = bq2415x_i2c_write(bq, reg, val);
 	if (ret < 0)
 		return ret;
-	else
-		return count;
+	return count;
 }
 
 /* print value of chip register, format: 'register=value' */
 static ssize_t bq2415x_sysfs_print_reg(struct bq2415x_device *bq,
-					u8 reg, char *buf)
+				       u8 reg,
+				       char *buf)
 {
 	int ret = bq2415x_i2c_read(bq, reg);
+
 	if (ret < 0)
 		return sprintf(buf, "%#.2x=error %d\n", reg, ret);
-	else
-		return sprintf(buf, "%#.2x=%#.2x\n", reg, ret);
+	return sprintf(buf, "%#.2x=%#.2x\n", reg, ret);
 }
 
 /* show all raw values of chip register, format per line: 'register=value' */
 static ssize_t bq2415x_sysfs_show_registers(struct device *dev,
-		struct device_attribute *attr, char *buf)
+					    struct device_attribute *attr,
+					    char *buf)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
-						charger);
+						 charger);
 	ssize_t ret = 0;
 
 	ret += bq2415x_sysfs_print_reg(bq, BQ2415X_REG_STATUS, buf+ret);
@@ -1267,11 +1287,13 @@ static ssize_t bq2415x_sysfs_show_registers(struct device *dev,
 
 /* set current and voltage limit entries (in mA or mV) */
 static ssize_t bq2415x_sysfs_set_limit(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+				       struct device_attribute *attr,
+				       const char *buf,
+				       size_t count)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
-						charger);
+						 charger);
 	long val;
 	int ret;
 
@@ -1293,17 +1315,17 @@ static ssize_t bq2415x_sysfs_set_limit(struct device *dev,
 
 	if (ret < 0)
 		return ret;
-	else
-		return count;
+	return count;
 }
 
 /* show current and voltage limit entries (in mA or mV) */
 static ssize_t bq2415x_sysfs_show_limit(struct device *dev,
-		struct device_attribute *attr, char *buf)
+					struct device_attribute *attr,
+					char *buf)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
-						charger);
+						 charger);
 	int ret;
 
 	if (strcmp(attr->attr.name, "current_limit") == 0)
@@ -1321,17 +1343,18 @@ static ssize_t bq2415x_sysfs_show_limit(struct device *dev,
 
 	if (ret < 0)
 		return ret;
-	else
-		return sprintf(buf, "%d\n", ret);
+	return sprintf(buf, "%d\n", ret);
 }
 
 /* set *_enable entries */
 static ssize_t bq2415x_sysfs_set_enable(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+					struct device_attribute *attr,
+					const char *buf,
+					size_t count)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
-						charger);
+						 charger);
 	enum bq2415x_command command;
 	long val;
 	int ret;
@@ -1357,17 +1380,17 @@ static ssize_t bq2415x_sysfs_set_enable(struct device *dev,
 	ret = bq2415x_exec_command(bq, command);
 	if (ret < 0)
 		return ret;
-	else
-		return count;
+	return count;
 }
 
 /* show *_enable entries */
 static ssize_t bq2415x_sysfs_show_enable(struct device *dev,
-		struct device_attribute *attr, char *buf)
+					 struct device_attribute *attr,
+					 char *buf)
 {
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct bq2415x_device *bq = container_of(psy, struct bq2415x_device,
-						charger);
+						 charger);
 	enum bq2415x_command command;
 	int ret;
 
@@ -1385,8 +1408,7 @@ static ssize_t bq2415x_sysfs_show_enable(struct device *dev,
 	ret = bq2415x_exec_command(bq, command);
 	if (ret < 0)
 		return ret;
-	else
-		return sprintf(buf, "%d\n", ret);
+	return sprintf(buf, "%d\n", ret);
 }
 
 static DEVICE_ATTR(current_limit, S_IWUSR | S_IRUGO,
@@ -1425,6 +1447,10 @@ static DEVICE_ATTR(boost_status, S_IRUGO, bq2415x_sysfs_show_status, NULL);
 static DEVICE_ATTR(fault_status, S_IRUGO, bq2415x_sysfs_show_status, NULL);
 
 static struct attribute *bq2415x_sysfs_attributes[] = {
+	/*
+	 * TODO: some (appropriate) of these attrs should be switched to
+	 * use power supply class props.
+	 */
 	&dev_attr_current_limit.attr,
 	&dev_attr_weak_battery_voltage.attr,
 	&dev_attr_battery_regulation_voltage.attr,
@@ -1466,7 +1492,7 @@ static void bq2415x_sysfs_exit(struct bq2415x_device *bq)
 
 /* main bq2415x probe function */
 static int bq2415x_probe(struct i2c_client *client,
-		const struct i2c_device_id *id)
+			 const struct i2c_device_id *id)
 {
 	int ret;
 	int num;
diff --git a/include/linux/power/bq2415x_charger.h b/include/linux/power/bq2415x_charger.h
index fb6bf4d8aea8..97a1665eaeaf 100644
--- a/include/linux/power/bq2415x_charger.h
+++ b/include/linux/power/bq2415x_charger.h
@@ -1,72 +1,77 @@
 /*
-    bq2415x_charger.h - bq2415x charger driver
-    Copyright (C) 2011-2012  Pali Rohár <pali.rohar@gmail.com>
-
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License along
-    with this program; if not, write to the Free Software Foundation, Inc.,
-    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
-*/
+ * bq2415x charger driver
+ *
+ * Copyright (C) 2011-2012  Pali Rohár <pali.rohar@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
 
 #ifndef BQ2415X_CHARGER_H
 #define BQ2415X_CHARGER_H
 
 /*
-  This is platform data for bq2415x chip. It contains default board voltages
-  and currents which can be also later configured via sysfs. If value is -1
-  then default chip value (specified in datasheet) will be used.
-
-  Value resistor_sense is needed for for configuring charge and termination
-  current. It it is less or equal to zero, configuring charge and termination
-  current will not be possible.
-
-  Function set_mode_hook is needed for automode (setting correct current limit
-  when charger is connected/disconnected or setting boost mode). When is NULL,
-  automode function is disabled. When is not NULL, it must have this prototype:
-
-    int (*set_mode_hook)(
-      void (*hook)(enum bq2415x_mode mode, void *data),
-      void *data)
-
-  hook is hook function (see below) and data is pointer to driver private data
-
-  bq2415x driver will call it as:
-
-    platform_data->set_mode_hook(bq2415x_hook_function, bq2415x_device);
-
-  Board/platform function set_mode_hook return non zero value when hook
-  function was successful registered. Platform code should call that hook
-  function (which get from pointer, with data) every time when charger was
-  connected/disconnected or require to enable boost mode. bq2415x driver then
-  will set correct current limit, enable/disable charger or boost mode.
-
-  Hook function has this prototype:
-
-    void hook(enum bq2415x_mode mode, void *data);
-
-  mode is bq2415x mode (charger or boost)
-  data is pointer to driver private data (which get from set_charger_type_hook)
-
-  When bq driver is being unloaded, it call function:
-
-    platform_data->set_mode_hook(NULL, NULL);
-
-  (hook function and driver private data are NULL)
-
-  After that board/platform code must not call driver hook function! It is
-  possible that pointer to hook function will not be valid and calling will
-  cause undefined result.
-
-*/
+ * This is platform data for bq2415x chip. It contains default board
+ * voltages and currents which can be also later configured via sysfs. If
+ * value is -1 then default chip value (specified in datasheet) will be
+ * used.
+ *
+ * Value resistor_sense is needed for for configuring charge and
+ * termination current. It it is less or equal to zero, configuring charge
+ * and termination current will not be possible.
+ *
+ * Function set_mode_hook is needed for automode (setting correct current
+ * limit when charger is connected/disconnected or setting boost mode).
+ * When is NULL, automode function is disabled. When is not NULL, it must
+ * have this prototype:
+ *
+ *    int (*set_mode_hook)(
+ *      void (*hook)(enum bq2415x_mode mode, void *data),
+ *      void *data)
+ *
+ * hook is hook function (see below) and data is pointer to driver private
+ * data
+ *
+ * bq2415x driver will call it as:
+ *
+ *    platform_data->set_mode_hook(bq2415x_hook_function, bq2415x_device);
+ *
+ * Board/platform function set_mode_hook return non zero value when hook
+ * function was successful registered. Platform code should call that hook
+ * function (which get from pointer, with data) every time when charger
+ * was connected/disconnected or require to enable boost mode. bq2415x
+ * driver then will set correct current limit, enable/disable charger or
+ * boost mode.
+ *
+ * Hook function has this prototype:
+ *
+ *    void hook(enum bq2415x_mode mode, void *data);
+ *
+ * mode is bq2415x mode (charger or boost)
+ * data is pointer to driver private data (which get from
+ * set_charger_type_hook)
+ *
+ * When bq driver is being unloaded, it call function:
+ *
+ *    platform_data->set_mode_hook(NULL, NULL);
+ *
+ * (hook function and driver private data are NULL)
+ *
+ * After that board/platform code must not call driver hook function! It
+ * is possible that pointer to hook function will not be valid and calling
+ * will cause undefined result.
+ */
 
 /* Supported modes with maximal current limit */
 enum bq2415x_mode {
-- 
cgit v1.2.3-55-g7522


From bbaf444a89dd7dd7effd8ed2f4e4ec64da3cc1da Mon Sep 17 00:00:00 2001
From: Johan Hedberg
Date: Thu, 8 Nov 2012 01:22:59 +0100
Subject: Bluetooth: Use proper invalid value for tx_power

The core specification defines 127 as the "not available" value (well,
"reserved" for BR/EDR and "not available" for LE - but essentially the
same). Therefore, instead of testing for 0 (which is in fact a valid
value) we should be using this invalid value to test if the tx_power is
available.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h | 3 +++
 net/bluetooth/hci_core.c    | 2 ++
 net/bluetooth/hci_event.c   | 2 ++
 net/bluetooth/mgmt.c        | 2 +-
 4 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 6c414f4302fe..344fea0a7244 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -319,6 +319,9 @@ enum {
 #define HCI_FLOW_CTL_MODE_PACKET_BASED	0x00
 #define HCI_FLOW_CTL_MODE_BLOCK_BASED	0x01
 
+/* The core spec defines 127 as the "not available" value */
+#define HCI_TX_POWER_INVALID	127
+
 /* Extended Inquiry Response field types */
 #define EIR_FLAGS		0x01 /* flags */
 #define EIR_UUID16_SOME		0x02 /* 16-bit UUID, more available */
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 515d0c394f35..9713a2917ddc 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1606,6 +1606,8 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->esco_type = (ESCO_HV1);
 	hdev->link_mode = (HCI_LM_ACCEPT);
 	hdev->io_capability = 0x03; /* No Input No Output */
+	hdev->inq_tx_power = HCI_TX_POWER_INVALID;
+	hdev->adv_tx_power = HCI_TX_POWER_INVALID;
 
 	hdev->sniff_max_interval = 800;
 	hdev->sniff_min_interval = 80;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index c08ac7c03711..09c65712e8cc 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -202,6 +202,8 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb)
 			     BIT(HCI_PERIODIC_INQ));
 
 	hdev->discovery.state = DISCOVERY_STOPPED;
+	hdev->inq_tx_power = HCI_TX_POWER_INVALID;
+	hdev->adv_tx_power = HCI_TX_POWER_INVALID;
 }
 
 static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb)
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index a1a62baaaafb..dedbb1d8b2d2 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -484,7 +484,7 @@ static void create_eir(struct hci_dev *hdev, u8 *data)
 		ptr += (name_len + 2);
 	}
 
-	if (hdev->inq_tx_power) {
+	if (hdev->inq_tx_power != HCI_TX_POWER_INVALID) {
 		ptr[0] = 2;
 		ptr[1] = EIR_TX_POWER;
 		ptr[2] = (u8) hdev->inq_tx_power;
-- 
cgit v1.2.3-55-g7522


From 3f0f524bafcd2025c12e215f13207c7be0a13bf9 Mon Sep 17 00:00:00 2001
From: Johan Hedberg
Date: Thu, 8 Nov 2012 01:23:00 +0100
Subject: Bluetooth: Add support for setting LE advertising data

This patch adds support for setting basing LE advertising data. The
three elements supported for now are the advertising flags, the TX power
and the friendly name.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h      | 15 +++++++
 include/net/bluetooth/hci_core.h |  4 ++
 net/bluetooth/hci_core.c         | 94 ++++++++++++++++++++++++++++++++++++++++
 net/bluetooth/hci_event.c        | 11 ++++-
 4 files changed, 123 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 344fea0a7244..7306078e547c 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -338,6 +338,13 @@ enum {
 #define EIR_SSP_RAND_R		0x0F /* Simple Pairing Randomizer R */
 #define EIR_DEVICE_ID		0x10 /* device ID */
 
+/* Low Energy Advertising Flags */
+#define LE_AD_LIMITED		0x01 /* Limited Discoverable */
+#define LE_AD_GENERAL		0x02 /* General Discoverable */
+#define LE_AD_NO_BREDR		0x04 /* BR/EDR not supported */
+#define LE_AD_SIM_LE_BREDR_CTRL	0x08 /* Simultaneous LE & BR/EDR Controller */
+#define LE_AD_SIM_LE_BREDR_HOST	0x10 /* Simultaneous LE & BR/EDR Host */
+
 /* -----  HCI Commands ---- */
 #define HCI_OP_NOP			0x0000
 
@@ -942,6 +949,14 @@ struct hci_rp_le_read_adv_tx_power {
 	__s8	tx_power;
 } __packed;
 
+#define HCI_MAX_AD_LENGTH		31
+
+#define HCI_OP_LE_SET_ADV_DATA		0x2008
+struct hci_cp_le_set_adv_data {
+	__u8	length;
+	__u8	data[HCI_MAX_AD_LENGTH];
+} __packed;
+
 #define HCI_OP_LE_SET_SCAN_PARAM	0x200b
 struct hci_cp_le_set_scan_param {
 	__u8    type;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ce6dbeb6dfb6..ef5b85dac3f7 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -279,6 +279,8 @@ struct hci_dev {
 	struct le_scan_params	le_scan_params;
 
 	__s8			adv_tx_power;
+	__u8			adv_data[HCI_MAX_AD_LENGTH];
+	__u8			adv_data_len;
 
 	int (*open)(struct hci_dev *hdev);
 	int (*close)(struct hci_dev *hdev);
@@ -734,6 +736,8 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash,
 								u8 *randomizer);
 int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr);
 
+int hci_update_ad(struct hci_dev *hdev);
+
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
 
 int hci_recv_frame(struct sk_buff *skb);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 9713a2917ddc..e3a49db9cfcb 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -594,6 +594,99 @@ done:
 	return err;
 }
 
+static u8 create_ad(struct hci_dev *hdev, u8 *ptr)
+{
+	u8 ad_len = 0, flags = 0;
+	size_t name_len;
+
+	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags))
+		flags |= LE_AD_GENERAL;
+
+	if (!lmp_bredr_capable(hdev))
+		flags |= LE_AD_NO_BREDR;
+
+	if (lmp_le_br_capable(hdev))
+		flags |= LE_AD_SIM_LE_BREDR_CTRL;
+
+	if (lmp_host_le_br_capable(hdev))
+		flags |= LE_AD_SIM_LE_BREDR_HOST;
+
+	if (flags) {
+		BT_DBG("adv flags 0x%02x", flags);
+
+		ptr[0] = 2;
+		ptr[1] = EIR_FLAGS;
+		ptr[2] = flags;
+
+		ad_len += 3;
+		ptr += 3;
+	}
+
+	if (hdev->adv_tx_power != HCI_TX_POWER_INVALID) {
+		ptr[0] = 2;
+		ptr[1] = EIR_TX_POWER;
+		ptr[2] = (u8) hdev->adv_tx_power;
+
+		ad_len += 3;
+		ptr += 3;
+	}
+
+	name_len = strlen(hdev->dev_name);
+	if (name_len > 0) {
+		size_t max_len = HCI_MAX_AD_LENGTH - ad_len - 2;
+
+		if (name_len > max_len) {
+			name_len = max_len;
+			ptr[1] = EIR_NAME_SHORT;
+		} else
+			ptr[1] = EIR_NAME_COMPLETE;
+
+		ptr[0] = name_len + 1;
+
+		memcpy(ptr + 2, hdev->dev_name, name_len);
+
+		ad_len += (name_len + 2);
+		ptr += (name_len + 2);
+	}
+
+	return ad_len;
+}
+
+int hci_update_ad(struct hci_dev *hdev)
+{
+	struct hci_cp_le_set_adv_data cp;
+	u8 len;
+	int err;
+
+	hci_dev_lock(hdev);
+
+	if (!lmp_le_capable(hdev)) {
+		err = -EINVAL;
+		goto unlock;
+	}
+
+	memset(&cp, 0, sizeof(cp));
+
+	len = create_ad(hdev, cp.data);
+
+	if (hdev->adv_data_len == len &&
+	    memcmp(cp.data, hdev->adv_data, len) == 0) {
+		err = 0;
+		goto unlock;
+	}
+
+	memcpy(hdev->adv_data, cp.data, sizeof(cp.data));
+	hdev->adv_data_len = len;
+
+	cp.length = len;
+	err = hci_send_cmd(hdev, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp);
+
+unlock:
+	hci_dev_unlock(hdev);
+
+	return err;
+}
+
 /* ---- HCI ioctl helpers ---- */
 
 int hci_dev_open(__u16 dev)
@@ -651,6 +744,7 @@ int hci_dev_open(__u16 dev)
 		hci_dev_hold(hdev);
 		set_bit(HCI_UP, &hdev->flags);
 		hci_notify(hdev, HCI_DEV_UP);
+		hci_update_ad(hdev);
 		if (!test_bit(HCI_SETUP, &hdev->dev_flags) &&
 		    mgmt_valid_hdev(hdev)) {
 			hci_dev_lock(hdev);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 09c65712e8cc..7caea1af557b 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -204,6 +204,9 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb)
 	hdev->discovery.state = DISCOVERY_STOPPED;
 	hdev->inq_tx_power = HCI_TX_POWER_INVALID;
 	hdev->adv_tx_power = HCI_TX_POWER_INVALID;
+
+	memset(hdev->adv_data, 0, sizeof(hdev->adv_data));
+	hdev->adv_data_len = 0;
 }
 
 static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb)
@@ -226,6 +229,9 @@ static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_dev_unlock(hdev);
 
+	if (!status && !test_bit(HCI_INIT, &hdev->flags))
+		hci_update_ad(hdev);
+
 	hci_req_complete(hdev, HCI_OP_WRITE_LOCAL_NAME, status);
 }
 
@@ -1091,8 +1097,11 @@ static void hci_cc_le_read_adv_tx_power(struct hci_dev *hdev,
 
 	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
 
-	if (!rp->status)
+	if (!rp->status) {
 		hdev->adv_tx_power = rp->tx_power;
+		if (!test_bit(HCI_INIT, &hdev->flags))
+			hci_update_ad(hdev);
+	}
 
 	hci_req_complete(hdev, HCI_OP_LE_READ_ADV_TX_POWER, rp->status);
 }
-- 
cgit v1.2.3-55-g7522


From c1d5dc4ac15be45c7061e207f06ad8dfba0c2170 Mon Sep 17 00:00:00 2001
From: Johan Hedberg
Date: Thu, 8 Nov 2012 01:23:01 +0100
Subject: Bluetooth: Fix updating advertising state flags and data

This patch adds a callback for the HCI_LE_Set_Advertise_Enable command.
The callback is responsible for updating the HCI_LE_PERIPHERAL flag
updating as well as updating the advertising data flags field to
indicate undirected connectable advertising.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h |  2 ++
 net/bluetooth/hci_event.c   | 31 +++++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 7306078e547c..4bbabd85f5e5 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -957,6 +957,8 @@ struct hci_cp_le_set_adv_data {
 	__u8	data[HCI_MAX_AD_LENGTH];
 } __packed;
 
+#define HCI_OP_LE_SET_ADV_ENABLE	0x200a
+
 #define HCI_OP_LE_SET_SCAN_PARAM	0x200b
 struct hci_cp_le_set_scan_param {
 	__u8    type;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 7caea1af557b..9f5c5f244502 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1190,6 +1190,33 @@ static void hci_cc_read_local_oob_data_reply(struct hci_dev *hdev,
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	__u8 *sent, status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_ENABLE);
+	if (!sent)
+		return;
+
+	hci_dev_lock(hdev);
+
+	if (!status) {
+		if (*sent)
+			set_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+		else
+			clear_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+	}
+
+	hci_dev_unlock(hdev);
+
+	if (!test_bit(HCI_INIT, &hdev->flags))
+		hci_update_ad(hdev);
+
+	hci_req_complete(hdev, HCI_OP_LE_SET_ADV_ENABLE, status);
+}
+
 static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 status = *((__u8 *) skb->data);
@@ -2585,6 +2612,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_le_set_scan_param(hdev, skb);
 		break;
 
+	case HCI_OP_LE_SET_ADV_ENABLE:
+		hci_cc_le_set_adv_enable(hdev, skb);
+		break;
+
 	case HCI_OP_LE_SET_SCAN_ENABLE:
 		hci_cc_le_set_scan_enable(hdev, skb);
 		break;
-- 
cgit v1.2.3-55-g7522


From 2407dc25f741cf73853e0521ce9257531c9fc61d Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Fri, 16 Nov 2012 03:02:56 +0000
Subject: netns: Deduplicate and fix copy_net_ns when !CONFIG_NET_NS

The copy of copy_net_ns used when the network stack is not
built is broken as it does not return -EINVAL when attempting
to create a new network namespace.  We don't even have
a previous network namespace.

Since we need a copy of copy_net_ns in net/net_namespace.h that is
available when the networking stack is not built at all move the
correct version of copy_net_ns from net_namespace.c into net_namespace.h
Leaving us with just 2 versions of copy_net_ns.  One version for when
we compile in network namespace suport and another stub for all other
occasions.

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h | 15 +++++++++------
 net/core/net_namespace.c    |  7 -------
 2 files changed, 9 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 95e646641184..32dcb6085ebe 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -126,16 +126,19 @@ struct net {
 /* Init's network namespace */
 extern struct net init_net;
 
-#ifdef CONFIG_NET
+#ifdef CONFIG_NET_NS
 extern struct net *copy_net_ns(unsigned long flags, struct net *net_ns);
 
-#else /* CONFIG_NET */
-static inline struct net *copy_net_ns(unsigned long flags, struct net *net_ns)
+#else /* CONFIG_NET_NS */
+#include <linux/sched.h>
+#include <linux/nsproxy.h>
+static inline struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 {
-	/* There is nothing to copy so this is a noop */
-	return net_ns;
+	if (flags & CLONE_NEWNET)
+		return ERR_PTR(-EINVAL);
+	return old_net;
 }
-#endif /* CONFIG_NET */
+#endif /* CONFIG_NET_NS */
 
 
 extern struct list_head net_namespace_list;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 42f1e1c7514f..2c1c59091685 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -347,13 +347,6 @@ struct net *get_net_ns_by_fd(int fd)
 }
 
 #else
-struct net *copy_net_ns(unsigned long flags, struct net *old_net)
-{
-	if (flags & CLONE_NEWNET)
-		return ERR_PTR(-EINVAL);
-	return old_net;
-}
-
 struct net *get_net_ns_by_fd(int fd)
 {
 	return ERR_PTR(-EINVAL);
-- 
cgit v1.2.3-55-g7522


From d328b836823cd4a76611a45f52e208f8ce3d75d7 Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Fri, 16 Nov 2012 03:02:57 +0000
Subject: userns: make each net (net_ns) belong to a user_ns

The user namespace which creates a new network namespace owns that
namespace and all resources created in it.  This way we can target
capability checks for privileged operations against network resources to
the user_ns which created the network namespace in which the resource
lives.  Privilege to the user namespace which owns the network
namespace, or any parent user namespace thereof, provides the same
privilege to the network resource.

This patch is reworked from a version originally by
Serge E. Hallyn <serge.hallyn@canonical.com>

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h |  9 +++++++--
 kernel/nsproxy.c            |  2 +-
 net/core/net_namespace.c    | 16 ++++++++++++----
 3 files changed, 20 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 32dcb6085ebe..c5a43f56b796 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -23,6 +23,7 @@
 #endif
 #include <net/netns/xfrm.h>
 
+struct user_namespace;
 struct proc_dir_entry;
 struct net_device;
 struct sock;
@@ -53,6 +54,8 @@ struct net {
 	struct list_head	cleanup_list;	/* namespaces on death row */
 	struct list_head	exit_list;	/* Use only net_mutex */
 
+	struct user_namespace   *user_ns;	/* Owning user namespace */
+
 	struct proc_dir_entry 	*proc_net;
 	struct proc_dir_entry 	*proc_net_stat;
 
@@ -127,12 +130,14 @@ struct net {
 extern struct net init_net;
 
 #ifdef CONFIG_NET_NS
-extern struct net *copy_net_ns(unsigned long flags, struct net *net_ns);
+extern struct net *copy_net_ns(unsigned long flags,
+	struct user_namespace *user_ns, struct net *old_net);
 
 #else /* CONFIG_NET_NS */
 #include <linux/sched.h>
 #include <linux/nsproxy.h>
-static inline struct net *copy_net_ns(unsigned long flags, struct net *old_net)
+static inline struct net *copy_net_ns(unsigned long flags,
+	struct user_namespace *user_ns, struct net *old_net)
 {
 	if (flags & CLONE_NEWNET)
 		return ERR_PTR(-EINVAL);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index b576f7f14bc6..7e1c3de1ce45 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -90,7 +90,7 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 		goto out_pid;
 	}
 
-	new_nsp->net_ns = copy_net_ns(flags, tsk->nsproxy->net_ns);
+	new_nsp->net_ns = copy_net_ns(flags, task_cred_xxx(tsk, user_ns), tsk->nsproxy->net_ns);
 	if (IS_ERR(new_nsp->net_ns)) {
 		err = PTR_ERR(new_nsp->net_ns);
 		goto out_net;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 2c1c59091685..6456439cbbd9 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -13,6 +13,7 @@
 #include <linux/proc_fs.h>
 #include <linux/file.h>
 #include <linux/export.h>
+#include <linux/user_namespace.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
@@ -145,7 +146,7 @@ static void ops_free_list(const struct pernet_operations *ops,
 /*
  * setup_net runs the initializers for the network namespace object.
  */
-static __net_init int setup_net(struct net *net)
+static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 {
 	/* Must be called with net_mutex held */
 	const struct pernet_operations *ops, *saved_ops;
@@ -155,6 +156,7 @@ static __net_init int setup_net(struct net *net)
 	atomic_set(&net->count, 1);
 	atomic_set(&net->passive, 1);
 	net->dev_base_seq = 1;
+	net->user_ns = user_ns;
 
 #ifdef NETNS_REFCNT_DEBUG
 	atomic_set(&net->use_count, 0);
@@ -232,7 +234,8 @@ void net_drop_ns(void *p)
 		net_free(ns);
 }
 
-struct net *copy_net_ns(unsigned long flags, struct net *old_net)
+struct net *copy_net_ns(unsigned long flags,
+			struct user_namespace *user_ns, struct net *old_net)
 {
 	struct net *net;
 	int rv;
@@ -243,8 +246,11 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 	net = net_alloc();
 	if (!net)
 		return ERR_PTR(-ENOMEM);
+
+	get_user_ns(user_ns);
+
 	mutex_lock(&net_mutex);
-	rv = setup_net(net);
+	rv = setup_net(net, user_ns);
 	if (rv == 0) {
 		rtnl_lock();
 		list_add_tail_rcu(&net->list, &net_namespace_list);
@@ -252,6 +258,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 	}
 	mutex_unlock(&net_mutex);
 	if (rv < 0) {
+		put_user_ns(user_ns);
 		net_drop_ns(net);
 		return ERR_PTR(rv);
 	}
@@ -308,6 +315,7 @@ static void cleanup_net(struct work_struct *work)
 	/* Finally it is safe to free my network namespace structure */
 	list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
 		list_del_init(&net->exit_list);
+		put_user_ns(net->user_ns);
 		net_drop_ns(net);
 	}
 }
@@ -395,7 +403,7 @@ static int __init net_ns_init(void)
 	rcu_assign_pointer(init_net.gen, ng);
 
 	mutex_lock(&net_mutex);
-	if (setup_net(&init_net))
+	if (setup_net(&init_net, &init_user_ns))
 		panic("Could not setup the initial network namespace");
 
 	rtnl_lock();
-- 
cgit v1.2.3-55-g7522


From 73f7ef435934e952c1d70d83d69921ea5d1f6bd4 Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Fri, 16 Nov 2012 03:02:58 +0000
Subject: sysctl: Pass useful parameters to sysctl permissions

- Current is implicitly avaiable so passing current->nsproxy isn't useful.
- The ctl_table_header is needed to find how the sysctl table is connected
  to the rest of sysctl.
- ctl_table_root is avaiable in the ctl_table_header so no need to it.

With these changes it becomes possible to write a version of
net_sysctl_permission that takes into account the network namespace of
the sysctl table, an important feature in extending the user namespace.

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/proc/proc_sysctl.c  | 9 +++++----
 include/linux/sysctl.h | 3 +--
 net/sysctl_net.c       | 3 +--
 3 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index a781bdf06694..701580ddfcc3 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -378,12 +378,13 @@ static int test_perm(int mode, int op)
 	return -EACCES;
 }
 
-static int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
+static int sysctl_perm(struct ctl_table_header *head, struct ctl_table *table, int op)
 {
+	struct ctl_table_root *root = head->root;
 	int mode;
 
 	if (root->permissions)
-		mode = root->permissions(root, current->nsproxy, table);
+		mode = root->permissions(head, table);
 	else
 		mode = table->mode;
 
@@ -491,7 +492,7 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
 	 * and won't be until we finish.
 	 */
 	error = -EPERM;
-	if (sysctl_perm(head->root, table, write ? MAY_WRITE : MAY_READ))
+	if (sysctl_perm(head, table, write ? MAY_WRITE : MAY_READ))
 		goto out;
 
 	/* if that can happen at all, it should be -EINVAL, not -EISDIR */
@@ -717,7 +718,7 @@ static int proc_sys_permission(struct inode *inode, int mask)
 	if (!table) /* global root - r-xr-xr-x */
 		error = mask & MAY_WRITE ? -EACCES : 0;
 	else /* Use the permissions on the sysctl table entry */
-		error = sysctl_perm(head->root, table, mask & ~MAY_NOT_BLOCK);
+		error = sysctl_perm(head, table, mask & ~MAY_NOT_BLOCK);
 
 	sysctl_head_finish(head);
 	return error;
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index cd844a6a8d5f..14a8ff2de11e 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -158,8 +158,7 @@ struct ctl_table_root {
 	struct ctl_table_set default_set;
 	struct ctl_table_set *(*lookup)(struct ctl_table_root *root,
 					   struct nsproxy *namespaces);
-	int (*permissions)(struct ctl_table_root *root,
-			struct nsproxy *namespaces, struct ctl_table *table);
+	int (*permissions)(struct ctl_table_header *head, struct ctl_table *table);
 };
 
 /* struct ctl_path describes where in the hierarchy a table is added */
diff --git a/net/sysctl_net.c b/net/sysctl_net.c
index e3a6e37cd1c5..e98f3932bdfb 100644
--- a/net/sysctl_net.c
+++ b/net/sysctl_net.c
@@ -38,8 +38,7 @@ static int is_seen(struct ctl_table_set *set)
 }
 
 /* Return standard mode bits for table entry. */
-static int net_ctl_permissions(struct ctl_table_root *root,
-			       struct nsproxy *nsproxy,
+static int net_ctl_permissions(struct ctl_table_header *head,
 			       struct ctl_table *table)
 {
 	/* Allow network administrator to have same access as root. */
-- 
cgit v1.2.3-55-g7522


From e0f1abeba5c2d8a2183566717d99294fd1a29c2e Mon Sep 17 00:00:00 2001
From: Rajanikanth H.V
Date: Sun, 18 Nov 2012 18:45:41 -0800
Subject: ab8500: Add devicetree support for fuelgauge

- This patch adds device tree support for fuelgauge driver
- optimize bm devices platform_data usage and of_probe(...)
  Note: of_probe() routine for battery managed devices is made
  common across all bm drivers.
- test status:
  - interrupt numbers assigned differs between legacy and FDT mode.

Signed-off-by: Rajanikanth H.V <rajanikanth.hv@stericsson.com>
Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
---
 Documentation/devicetree/bindings/mfd/ab8500.txt   |   7 +-
 .../devicetree/bindings/power_supply/ab8500/fg.txt |  58 +++
 arch/arm/boot/dts/dbx5x0.dtsi                      |  12 +-
 drivers/mfd/ab8500-core.c                          |   5 +
 drivers/power/Makefile                             |   2 +-
 drivers/power/ab8500_bmdata.c                      | 521 +++++++++++++++++++++
 drivers/power/ab8500_btemp.c                       |  16 +-
 drivers/power/ab8500_charger.c                     |  16 +-
 drivers/power/ab8500_fg.c                          |  82 ++--
 drivers/power/abx500_chargalg.c                    |   8 +-
 include/linux/mfd/abx500.h                         |  36 +-
 11 files changed, 667 insertions(+), 96 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/power_supply/ab8500/fg.txt
 create mode 100644 drivers/power/ab8500_bmdata.c

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/mfd/ab8500.txt b/Documentation/devicetree/bindings/mfd/ab8500.txt
index ce83c8d3c00e..6ca8d817ef92 100644
--- a/Documentation/devicetree/bindings/mfd/ab8500.txt
+++ b/Documentation/devicetree/bindings/mfd/ab8500.txt
@@ -24,7 +24,12 @@ ab8500-bm                :                      :              : Battery Manager
 ab8500-btemp             :                      :              : Battery Temperature
 ab8500-charger           :                      :              : Battery Charger
 ab8500-codec             :                      :              : Audio Codec
-ab8500-fg                :                      :              : Fuel Gauge
+ab8500-fg                : 			: vddadc       : Fuel Gauge
+			 : NCONV_ACCU           :	       : Accumulate N Sample Conversion
+			 : BATT_OVV		:	       : Battery Over Voltage
+			 : LOW_BAT_F		:	       : LOW threshold battery voltage
+			 : CC_INT_CALIB		:	       : Coulomb Counter Internal Calibration
+			 : CCEOC		:	       : Coulomb Counter End of Conversion
 ab8500-gpadc             : HW_CONV_END          : vddadc       : Analogue to Digital Converter
                            SW_CONV_END          :              :
 ab8500-gpio              :                      :              : GPIO Controller
diff --git a/Documentation/devicetree/bindings/power_supply/ab8500/fg.txt b/Documentation/devicetree/bindings/power_supply/ab8500/fg.txt
new file mode 100644
index 000000000000..ccafcb9112fb
--- /dev/null
+++ b/Documentation/devicetree/bindings/power_supply/ab8500/fg.txt
@@ -0,0 +1,58 @@
+=== AB8500 Fuel Gauge Driver ===
+
+AB8500 is a mixed signal multimedia and power management
+device comprising: power and energy-management-module,
+wall-charger, usb-charger, audio codec, general purpose adc,
+tvout, clock management and sim card interface.
+
+Fuelgauge support is part of energy-management-modules, other
+components of this module are:
+main-charger, usb-combo-charger and battery-temperature-monitoring.
+
+The properties below describes the node for fuelgauge driver.
+
+Required Properties:
+- compatible = This shall be: "stericsson,ab8500-fg"
+- battery = Shall be battery specific information
+	Example:
+	ab8500_fg {
+		compatible = "stericsson,ab8500-fg";
+		battery	   = <&ab8500_battery>;
+	};
+
+dependent node:
+	ab8500_battery: ab8500_battery {
+	};
+	This node will provide information on 'thermistor interface' and
+	'battery technology type' used.
+
+Properties of this node are:
+thermistor-on-batctrl:
+	A boolean value indicating thermistor interface	to battery
+
+	Note:
+	'btemp' and 'batctrl' are the pins interfaced for battery temperature
+	measurement, 'btemp' signal is used when NTC(negative temperature
+	coefficient) resister is interfaced external to battery whereas
+	'batctrl' pin is used when NTC resister is internal to battery.
+
+	Example:
+	ab8500_battery: ab8500_battery {
+		thermistor-on-batctrl;
+	};
+	indicates: NTC resister is internal to battery, 'batctrl' is used
+		for thermal measurement.
+
+	The absence of property 'thermal-on-batctrl' indicates
+	NTC resister is external to battery and  'btemp' signal is used
+	for thermal measurement.
+
+battery-type:
+	This shall be the battery manufacturing technology type,
+	allowed types are:
+		"UNKNOWN" "NiMH" "LION" "LIPO" "LiFe" "NiCd" "LiMn"
+	Example:
+	ab8500_battery: ab8500_battery {
+		stericsson,battery-type = "LIPO";
+	}
+
diff --git a/arch/arm/boot/dts/dbx5x0.dtsi b/arch/arm/boot/dts/dbx5x0.dtsi
index 4b0e0ca08f40..0c81986904c5 100644
--- a/arch/arm/boot/dts/dbx5x0.dtsi
+++ b/arch/arm/boot/dts/dbx5x0.dtsi
@@ -352,7 +352,17 @@
 					vddadc-supply = <&ab8500_ldo_tvout_reg>;
 				};
 
-				ab8500-usb {
+				ab8500_battery: ab8500_battery {
+					stericsson,battery-type = "LIPO";
+					thermistor-on-batctrl;
+				};
+
+				ab8500_fg {
+					compatible = "stericsson,ab8500-fg";
+					battery	   = <&ab8500_battery>;
+				};
+
+				ab8500_usb {
 					compatible = "stericsson,ab8500-usb";
 					interrupts = < 90 0x4
 						       96 0x4
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index 1667c77b5cde..7c3017ba73e4 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -1051,8 +1051,13 @@ static struct mfd_cell __devinitdata ab8500_bm_devs[] = {
 	},
 	{
 		.name = "ab8500-fg",
+		.of_compatible = "stericsson,ab8500-fg",
 		.num_resources = ARRAY_SIZE(ab8500_fg_resources),
 		.resources = ab8500_fg_resources,
+#ifndef CONFIG_OF
+		.platform_data = &ab8500_bm_data,
+		.pdata_size = sizeof(ab8500_bm_data),
+#endif
 	},
 	{
 		.name = "ab8500-chargalg",
diff --git a/drivers/power/Makefile b/drivers/power/Makefile
index 74dfd9570154..696e3a960b3e 100644
--- a/drivers/power/Makefile
+++ b/drivers/power/Makefile
@@ -38,7 +38,7 @@ obj-$(CONFIG_CHARGER_PCF50633)	+= pcf50633-charger.o
 obj-$(CONFIG_BATTERY_JZ4740)	+= jz4740-battery.o
 obj-$(CONFIG_BATTERY_INTEL_MID)	+= intel_mid_battery.o
 obj-$(CONFIG_BATTERY_RX51)	+= rx51_battery.o
-obj-$(CONFIG_AB8500_BM)		+= ab8500_charger.o ab8500_btemp.o ab8500_fg.o abx500_chargalg.o
+obj-$(CONFIG_AB8500_BM)		+= ab8500_bmdata.o ab8500_charger.o ab8500_btemp.o ab8500_fg.o abx500_chargalg.o
 obj-$(CONFIG_CHARGER_ISP1704)	+= isp1704_charger.o
 obj-$(CONFIG_CHARGER_MAX8903)	+= max8903_charger.o
 obj-$(CONFIG_CHARGER_TWL4030)	+= twl4030_charger.o
diff --git a/drivers/power/ab8500_bmdata.c b/drivers/power/ab8500_bmdata.c
new file mode 100644
index 000000000000..e7639b6659f7
--- /dev/null
+++ b/drivers/power/ab8500_bmdata.c
@@ -0,0 +1,521 @@
+#include <linux/export.h>
+#include <linux/power_supply.h>
+#include <linux/of.h>
+#include <linux/mfd/abx500.h>
+#include <linux/mfd/abx500/ab8500.h>
+#include <linux/mfd/abx500/ab8500-bm.h>
+
+/*
+ * These are the defined batteries that uses a NTC and ID resistor placed
+ * inside of the battery pack.
+ * Note that the res_to_temp table must be strictly sorted by falling resistance
+ * values to work.
+ */
+static struct abx500_res_to_temp temp_tbl_A_thermistor[] = {
+	{-5, 53407},
+	{ 0, 48594},
+	{ 5, 43804},
+	{10, 39188},
+	{15, 34870},
+	{20, 30933},
+	{25, 27422},
+	{30, 24347},
+	{35, 21694},
+	{40, 19431},
+	{45, 17517},
+	{50, 15908},
+	{55, 14561},
+	{60, 13437},
+	{65, 12500},
+};
+
+static struct abx500_res_to_temp temp_tbl_B_thermistor[] = {
+	{-5, 165418},
+	{ 0, 159024},
+	{ 5, 151921},
+	{10, 144300},
+	{15, 136424},
+	{20, 128565},
+	{25, 120978},
+	{30, 113875},
+	{35, 107397},
+	{40, 101629},
+	{45,  96592},
+	{50,  92253},
+	{55,  88569},
+	{60,  85461},
+	{65,  82869},
+};
+
+static struct abx500_v_to_cap cap_tbl_A_thermistor[] = {
+	{4171,	100},
+	{4114,	 95},
+	{4009,	 83},
+	{3947,	 74},
+	{3907,	 67},
+	{3863,	 59},
+	{3830,	 56},
+	{3813,	 53},
+	{3791,	 46},
+	{3771,	 33},
+	{3754,	 25},
+	{3735,	 20},
+	{3717,	 17},
+	{3681,	 13},
+	{3664,	  8},
+	{3651,	  6},
+	{3635,	  5},
+	{3560,	  3},
+	{3408,    1},
+	{3247,	  0},
+};
+
+static struct abx500_v_to_cap cap_tbl_B_thermistor[] = {
+	{4161,	100},
+	{4124,	 98},
+	{4044,	 90},
+	{4003,	 85},
+	{3966,	 80},
+	{3933,	 75},
+	{3888,	 67},
+	{3849,	 60},
+	{3813,	 55},
+	{3787,	 47},
+	{3772,	 30},
+	{3751,	 25},
+	{3718,	 20},
+	{3681,	 16},
+	{3660,	 14},
+	{3589,	 10},
+	{3546,	  7},
+	{3495,	  4},
+	{3404,	  2},
+	{3250,	  0},
+};
+
+static struct abx500_v_to_cap cap_tbl[] = {
+	{4186,	100},
+	{4163,	 99},
+	{4114,	 95},
+	{4068,	 90},
+	{3990,	 80},
+	{3926,	 70},
+	{3898,	 65},
+	{3866,	 60},
+	{3833,	 55},
+	{3812,	 50},
+	{3787,	 40},
+	{3768,	 30},
+	{3747,	 25},
+	{3730,	 20},
+	{3705,	 15},
+	{3699,	 14},
+	{3684,	 12},
+	{3672,	  9},
+	{3657,	  7},
+	{3638,	  6},
+	{3556,	  4},
+	{3424,	  2},
+	{3317,	  1},
+	{3094,	  0},
+};
+
+/*
+ * Note that the res_to_temp table must be strictly sorted by falling
+ * resistance values to work.
+ */
+static struct abx500_res_to_temp temp_tbl[] = {
+	{-5, 214834},
+	{ 0, 162943},
+	{ 5, 124820},
+	{10,  96520},
+	{15,  75306},
+	{20,  59254},
+	{25,  47000},
+	{30,  37566},
+	{35,  30245},
+	{40,  24520},
+	{45,  20010},
+	{50,  16432},
+	{55,  13576},
+	{60,  11280},
+	{65,   9425},
+};
+
+/*
+ * Note that the batres_vs_temp table must be strictly sorted by falling
+ * temperature values to work.
+ */
+static struct batres_vs_temp temp_to_batres_tbl_thermistor[] = {
+	{ 40, 120},
+	{ 30, 135},
+	{ 20, 165},
+	{ 10, 230},
+	{ 00, 325},
+	{-10, 445},
+	{-20, 595},
+};
+
+/*
+ * Note that the batres_vs_temp table must be strictly sorted by falling
+ * temperature values to work.
+ */
+static struct batres_vs_temp temp_to_batres_tbl_ext_thermistor[] = {
+	{ 60, 300},
+	{ 30, 300},
+	{ 20, 300},
+	{ 10, 300},
+	{ 00, 300},
+	{-10, 300},
+	{-20, 300},
+};
+
+/* battery resistance table for LI ION 9100 battery */
+static struct batres_vs_temp temp_to_batres_tbl_9100[] = {
+	{ 60, 180},
+	{ 30, 180},
+	{ 20, 180},
+	{ 10, 180},
+	{ 00, 180},
+	{-10, 180},
+	{-20, 180},
+};
+
+static struct abx500_battery_type bat_type_thermistor[] = {
+[BATTERY_UNKNOWN] = {
+	/* First element always represent the UNKNOWN battery */
+	.name = POWER_SUPPLY_TECHNOLOGY_UNKNOWN,
+	.resis_high = 0,
+	.resis_low = 0,
+	.battery_resistance = 300,
+	.charge_full_design = 612,
+	.nominal_voltage = 3700,
+	.termination_vol = 4050,
+	.termination_curr = 200,
+	.recharge_vol = 3990,
+	.normal_cur_lvl = 400,
+	.normal_vol_lvl = 4100,
+	.maint_a_cur_lvl = 400,
+	.maint_a_vol_lvl = 4050,
+	.maint_a_chg_timer_h = 60,
+	.maint_b_cur_lvl = 400,
+	.maint_b_vol_lvl = 4000,
+	.maint_b_chg_timer_h = 200,
+	.low_high_cur_lvl = 300,
+	.low_high_vol_lvl = 4000,
+	.n_temp_tbl_elements = ARRAY_SIZE(temp_tbl),
+	.r_to_t_tbl = temp_tbl,
+	.n_v_cap_tbl_elements = ARRAY_SIZE(cap_tbl),
+	.v_to_cap_tbl = cap_tbl,
+	.n_batres_tbl_elements = ARRAY_SIZE(temp_to_batres_tbl_thermistor),
+	.batres_tbl = temp_to_batres_tbl_thermistor,
+},
+{
+	.name = POWER_SUPPLY_TECHNOLOGY_LIPO,
+	.resis_high = 53407,
+	.resis_low = 12500,
+	.battery_resistance = 300,
+	.charge_full_design = 900,
+	.nominal_voltage = 3600,
+	.termination_vol = 4150,
+	.termination_curr = 80,
+	.recharge_vol = 4130,
+	.normal_cur_lvl = 700,
+	.normal_vol_lvl = 4200,
+	.maint_a_cur_lvl = 600,
+	.maint_a_vol_lvl = 4150,
+	.maint_a_chg_timer_h = 60,
+	.maint_b_cur_lvl = 600,
+	.maint_b_vol_lvl = 4100,
+	.maint_b_chg_timer_h = 200,
+	.low_high_cur_lvl = 300,
+	.low_high_vol_lvl = 4000,
+	.n_temp_tbl_elements = ARRAY_SIZE(temp_tbl_A_thermistor),
+	.r_to_t_tbl = temp_tbl_A_thermistor,
+	.n_v_cap_tbl_elements = ARRAY_SIZE(cap_tbl_A_thermistor),
+	.v_to_cap_tbl = cap_tbl_A_thermistor,
+	.n_batres_tbl_elements = ARRAY_SIZE(temp_to_batres_tbl_thermistor),
+	.batres_tbl = temp_to_batres_tbl_thermistor,
+
+},
+{
+	.name = POWER_SUPPLY_TECHNOLOGY_LIPO,
+	.resis_high = 165418,
+	.resis_low = 82869,
+	.battery_resistance = 300,
+	.charge_full_design = 900,
+	.nominal_voltage = 3600,
+	.termination_vol = 4150,
+	.termination_curr = 80,
+	.recharge_vol = 4130,
+	.normal_cur_lvl = 700,
+	.normal_vol_lvl = 4200,
+	.maint_a_cur_lvl = 600,
+	.maint_a_vol_lvl = 4150,
+	.maint_a_chg_timer_h = 60,
+	.maint_b_cur_lvl = 600,
+	.maint_b_vol_lvl = 4100,
+	.maint_b_chg_timer_h = 200,
+	.low_high_cur_lvl = 300,
+	.low_high_vol_lvl = 4000,
+	.n_temp_tbl_elements = ARRAY_SIZE(temp_tbl_B_thermistor),
+	.r_to_t_tbl = temp_tbl_B_thermistor,
+	.n_v_cap_tbl_elements = ARRAY_SIZE(cap_tbl_B_thermistor),
+	.v_to_cap_tbl = cap_tbl_B_thermistor,
+	.n_batres_tbl_elements = ARRAY_SIZE(temp_to_batres_tbl_thermistor),
+	.batres_tbl = temp_to_batres_tbl_thermistor,
+},
+};
+
+static struct abx500_battery_type bat_type_ext_thermistor[] = {
+[BATTERY_UNKNOWN] = {
+	/* First element always represent the UNKNOWN battery */
+	.name = POWER_SUPPLY_TECHNOLOGY_UNKNOWN,
+	.resis_high = 0,
+	.resis_low = 0,
+	.battery_resistance = 300,
+	.charge_full_design = 612,
+	.nominal_voltage = 3700,
+	.termination_vol = 4050,
+	.termination_curr = 200,
+	.recharge_vol = 3990,
+	.normal_cur_lvl = 400,
+	.normal_vol_lvl = 4100,
+	.maint_a_cur_lvl = 400,
+	.maint_a_vol_lvl = 4050,
+	.maint_a_chg_timer_h = 60,
+	.maint_b_cur_lvl = 400,
+	.maint_b_vol_lvl = 4000,
+	.maint_b_chg_timer_h = 200,
+	.low_high_cur_lvl = 300,
+	.low_high_vol_lvl = 4000,
+	.n_temp_tbl_elements = ARRAY_SIZE(temp_tbl),
+	.r_to_t_tbl = temp_tbl,
+	.n_v_cap_tbl_elements = ARRAY_SIZE(cap_tbl),
+	.v_to_cap_tbl = cap_tbl,
+	.n_batres_tbl_elements = ARRAY_SIZE(temp_to_batres_tbl_thermistor),
+	.batres_tbl = temp_to_batres_tbl_thermistor,
+},
+/*
+ * These are the batteries that doesn't have an internal NTC resistor to measure
+ * its temperature. The temperature in this case is measure with a NTC placed
+ * near the battery but on the PCB.
+ */
+{
+	.name = POWER_SUPPLY_TECHNOLOGY_LIPO,
+	.resis_high = 76000,
+	.resis_low = 53000,
+	.battery_resistance = 300,
+	.charge_full_design = 900,
+	.nominal_voltage = 3700,
+	.termination_vol = 4150,
+	.termination_curr = 100,
+	.recharge_vol = 4130,
+	.normal_cur_lvl = 700,
+	.normal_vol_lvl = 4200,
+	.maint_a_cur_lvl = 600,
+	.maint_a_vol_lvl = 4150,
+	.maint_a_chg_timer_h = 60,
+	.maint_b_cur_lvl = 600,
+	.maint_b_vol_lvl = 4100,
+	.maint_b_chg_timer_h = 200,
+	.low_high_cur_lvl = 300,
+	.low_high_vol_lvl = 4000,
+	.n_temp_tbl_elements = ARRAY_SIZE(temp_tbl),
+	.r_to_t_tbl = temp_tbl,
+	.n_v_cap_tbl_elements = ARRAY_SIZE(cap_tbl),
+	.v_to_cap_tbl = cap_tbl,
+	.n_batres_tbl_elements = ARRAY_SIZE(temp_to_batres_tbl_thermistor),
+	.batres_tbl = temp_to_batres_tbl_thermistor,
+},
+{
+	.name = POWER_SUPPLY_TECHNOLOGY_LION,
+	.resis_high = 30000,
+	.resis_low = 10000,
+	.battery_resistance = 300,
+	.charge_full_design = 950,
+	.nominal_voltage = 3700,
+	.termination_vol = 4150,
+	.termination_curr = 100,
+	.recharge_vol = 4130,
+	.normal_cur_lvl = 700,
+	.normal_vol_lvl = 4200,
+	.maint_a_cur_lvl = 600,
+	.maint_a_vol_lvl = 4150,
+	.maint_a_chg_timer_h = 60,
+	.maint_b_cur_lvl = 600,
+	.maint_b_vol_lvl = 4100,
+	.maint_b_chg_timer_h = 200,
+	.low_high_cur_lvl = 300,
+	.low_high_vol_lvl = 4000,
+	.n_temp_tbl_elements = ARRAY_SIZE(temp_tbl),
+	.r_to_t_tbl = temp_tbl,
+	.n_v_cap_tbl_elements = ARRAY_SIZE(cap_tbl),
+	.v_to_cap_tbl = cap_tbl,
+	.n_batres_tbl_elements = ARRAY_SIZE(temp_to_batres_tbl_thermistor),
+	.batres_tbl = temp_to_batres_tbl_thermistor,
+},
+{
+	.name = POWER_SUPPLY_TECHNOLOGY_LION,
+	.resis_high = 95000,
+	.resis_low = 76001,
+	.battery_resistance = 300,
+	.charge_full_design = 950,
+	.nominal_voltage = 3700,
+	.termination_vol = 4150,
+	.termination_curr = 100,
+	.recharge_vol = 4130,
+	.normal_cur_lvl = 700,
+	.normal_vol_lvl = 4200,
+	.maint_a_cur_lvl = 600,
+	.maint_a_vol_lvl = 4150,
+	.maint_a_chg_timer_h = 60,
+	.maint_b_cur_lvl = 600,
+	.maint_b_vol_lvl = 4100,
+	.maint_b_chg_timer_h = 200,
+	.low_high_cur_lvl = 300,
+	.low_high_vol_lvl = 4000,
+	.n_temp_tbl_elements = ARRAY_SIZE(temp_tbl),
+	.r_to_t_tbl = temp_tbl,
+	.n_v_cap_tbl_elements = ARRAY_SIZE(cap_tbl),
+	.v_to_cap_tbl = cap_tbl,
+	.n_batres_tbl_elements = ARRAY_SIZE(temp_to_batres_tbl_thermistor),
+	.batres_tbl = temp_to_batres_tbl_thermistor,
+},
+};
+
+static const struct abx500_bm_capacity_levels cap_levels = {
+	.critical	= 2,
+	.low		= 10,
+	.normal		= 70,
+	.high		= 95,
+	.full		= 100,
+};
+
+static const struct abx500_fg_parameters fg = {
+	.recovery_sleep_timer = 10,
+	.recovery_total_time = 100,
+	.init_timer = 1,
+	.init_discard_time = 5,
+	.init_total_time = 40,
+	.high_curr_time = 60,
+	.accu_charging = 30,
+	.accu_high_curr = 30,
+	.high_curr_threshold = 50,
+	.lowbat_threshold = 3100,
+	.battok_falling_th_sel0 = 2860,
+	.battok_raising_th_sel1 = 2860,
+	.user_cap_limit = 15,
+	.maint_thres = 97,
+};
+
+static const struct abx500_maxim_parameters maxi_params = {
+	.ena_maxi = true,
+	.chg_curr = 910,
+	.wait_cycles = 10,
+	.charger_curr_step = 100,
+};
+
+static const struct abx500_bm_charger_parameters chg = {
+	.usb_volt_max		= 5500,
+	.usb_curr_max		= 1500,
+	.ac_volt_max		= 7500,
+	.ac_curr_max		= 1500,
+};
+
+struct abx500_bm_data ab8500_bm_data = {
+	.temp_under		= 3,
+	.temp_low		= 8,
+	.temp_high		= 43,
+	.temp_over		= 48,
+	.main_safety_tmr_h	= 4,
+	.temp_interval_chg	= 20,
+	.temp_interval_nochg	= 120,
+	.usb_safety_tmr_h	= 4,
+	.bkup_bat_v		= BUP_VCH_SEL_2P6V,
+	.bkup_bat_i		= BUP_ICH_SEL_150UA,
+	.no_maintenance		= false,
+	.adc_therm		= ABx500_ADC_THERM_BATCTRL,
+	.chg_unknown_bat	= false,
+	.enable_overshoot	= false,
+	.fg_res			= 100,
+	.cap_levels		= &cap_levels,
+	.bat_type		= bat_type_thermistor,
+	.n_btypes		= 3,
+	.batt_id		= 0,
+	.interval_charging	= 5,
+	.interval_not_charging	= 120,
+	.temp_hysteresis	= 3,
+	.gnd_lift_resistance	= 34,
+	.maxi			= &maxi_params,
+	.chg_params		= &chg,
+	.fg_params		= &fg,
+};
+
+int __devinit
+bmdevs_of_probe(struct device *dev,
+		struct device_node *np,
+		struct abx500_bm_data **battery)
+{
+	struct	abx500_battery_type *btype;
+	struct  device_node *np_bat_supply;
+	struct	abx500_bm_data *bat;
+	const char *btech;
+	char bat_tech[8];
+	int i, thermistor;
+
+	*battery = &ab8500_bm_data;
+
+	/* get phandle to 'battery-info' node */
+	np_bat_supply = of_parse_phandle(np, "battery", 0);
+	if (!np_bat_supply) {
+		dev_err(dev, "missing property battery\n");
+		return -EINVAL;
+	}
+	if (of_property_read_bool(np_bat_supply,
+			"thermistor-on-batctrl"))
+		thermistor = NTC_INTERNAL;
+	else
+		thermistor = NTC_EXTERNAL;
+
+	bat = *battery;
+	if (thermistor == NTC_EXTERNAL) {
+		bat->n_btypes  = 4;
+		bat->bat_type  = bat_type_ext_thermistor;
+		bat->adc_therm = ABx500_ADC_THERM_BATTEMP;
+	}
+	btech = of_get_property(np_bat_supply,
+		"stericsson,battery-type", NULL);
+	if (!btech) {
+		dev_warn(dev, "missing property battery-name/type\n");
+		strcpy(bat_tech, "UNKNOWN");
+	} else {
+		strcpy(bat_tech, btech);
+	}
+
+	if (strncmp(bat_tech, "LION", 4) == 0) {
+		bat->no_maintenance  = true;
+		bat->chg_unknown_bat = true;
+		bat->bat_type[BATTERY_UNKNOWN].charge_full_design = 2600;
+		bat->bat_type[BATTERY_UNKNOWN].termination_vol    = 4150;
+		bat->bat_type[BATTERY_UNKNOWN].recharge_vol	  = 4130;
+		bat->bat_type[BATTERY_UNKNOWN].normal_cur_lvl	  = 520;
+		bat->bat_type[BATTERY_UNKNOWN].normal_vol_lvl	  = 4200;
+	}
+	/* select the battery resolution table */
+	for (i = 0; i < bat->n_btypes; ++i) {
+		btype = (bat->bat_type + i);
+		if (thermistor == NTC_EXTERNAL) {
+			btype->batres_tbl =
+				temp_to_batres_tbl_ext_thermistor;
+		} else if (strncmp(bat_tech, "LION", 4) == 0) {
+			btype->batres_tbl =
+				temp_to_batres_tbl_9100;
+		} else {
+			btype->batres_tbl =
+				temp_to_batres_tbl_thermistor;
+		}
+	}
+	of_node_put(np_bat_supply);
+	return 0;
+}
diff --git a/drivers/power/ab8500_btemp.c b/drivers/power/ab8500_btemp.c
index e3b6395b20dd..abc2abc16a5d 100644
--- a/drivers/power/ab8500_btemp.c
+++ b/drivers/power/ab8500_btemp.c
@@ -93,7 +93,7 @@ struct ab8500_btemp {
 	struct ab8500 *parent;
 	struct ab8500_gpadc *gpadc;
 	struct ab8500_fg *fg;
-	struct abx500_btemp_platform_data *pdata;
+	struct abx500_bmdevs_plat_data *pdata;
 	struct abx500_bm_data *bat;
 	struct power_supply btemp_psy;
 	struct ab8500_btemp_events events;
@@ -962,10 +962,10 @@ static int __devexit ab8500_btemp_remove(struct platform_device *pdev)
 
 static int __devinit ab8500_btemp_probe(struct platform_device *pdev)
 {
+	struct abx500_bmdevs_plat_data *plat_data = pdev->dev.platform_data;
+	struct ab8500_btemp *di;
 	int irq, i, ret = 0;
 	u8 val;
-	struct abx500_bm_plat_data *plat_data = pdev->dev.platform_data;
-	struct ab8500_btemp *di;
 
 	if (!plat_data) {
 		dev_err(&pdev->dev, "No platform data\n");
@@ -982,21 +982,13 @@ static int __devinit ab8500_btemp_probe(struct platform_device *pdev)
 	di->gpadc = ab8500_gpadc_get("ab8500-gpadc.0");
 
 	/* get btemp specific platform data */
-	di->pdata = plat_data->btemp;
+	di->pdata = plat_data;
 	if (!di->pdata) {
 		dev_err(di->dev, "no btemp platform data supplied\n");
 		ret = -EINVAL;
 		goto free_device_info;
 	}
 
-	/* get battery specific platform data */
-	di->bat = plat_data->battery;
-	if (!di->bat) {
-		dev_err(di->dev, "no battery platform data supplied\n");
-		ret = -EINVAL;
-		goto free_device_info;
-	}
-
 	/* BTEMP supply */
 	di->btemp_psy.name = "ab8500_btemp";
 	di->btemp_psy.type = POWER_SUPPLY_TYPE_BATTERY;
diff --git a/drivers/power/ab8500_charger.c b/drivers/power/ab8500_charger.c
index 26ff759e2220..723edb47b1d8 100644
--- a/drivers/power/ab8500_charger.c
+++ b/drivers/power/ab8500_charger.c
@@ -220,7 +220,7 @@ struct ab8500_charger {
 	bool autopower;
 	struct ab8500 *parent;
 	struct ab8500_gpadc *gpadc;
-	struct abx500_charger_platform_data *pdata;
+	struct abx500_bmdevs_plat_data *pdata;
 	struct abx500_bm_data *bat;
 	struct ab8500_charger_event_flags flags;
 	struct ab8500_charger_usb_state usb_state;
@@ -2533,9 +2533,9 @@ static int __devexit ab8500_charger_remove(struct platform_device *pdev)
 
 static int __devinit ab8500_charger_probe(struct platform_device *pdev)
 {
-	int irq, i, charger_status, ret = 0;
-	struct abx500_bm_plat_data *plat_data = pdev->dev.platform_data;
+	struct abx500_bmdevs_plat_data *plat_data = pdev->dev.platform_data;
 	struct ab8500_charger *di;
+	int irq, i, charger_status, ret = 0;
 
 	if (!plat_data) {
 		dev_err(&pdev->dev, "No platform data\n");
@@ -2555,21 +2555,13 @@ static int __devinit ab8500_charger_probe(struct platform_device *pdev)
 	spin_lock_init(&di->usb_state.usb_lock);
 
 	/* get charger specific platform data */
-	di->pdata = plat_data->charger;
+	di->pdata = plat_data;
 	if (!di->pdata) {
 		dev_err(di->dev, "no charger platform data supplied\n");
 		ret = -EINVAL;
 		goto free_device_info;
 	}
 
-	/* get battery specific platform data */
-	di->bat = plat_data->battery;
-	if (!di->bat) {
-		dev_err(di->dev, "no battery platform data supplied\n");
-		ret = -EINVAL;
-		goto free_device_info;
-	}
-
 	di->autopower = false;
 
 	/* AC supply */
diff --git a/drivers/power/ab8500_fg.c b/drivers/power/ab8500_fg.c
index 2db8cc254399..ed62ef788eb5 100644
--- a/drivers/power/ab8500_fg.c
+++ b/drivers/power/ab8500_fg.c
@@ -22,15 +22,16 @@
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
 #include <linux/kobject.h>
-#include <linux/mfd/abx500/ab8500.h>
-#include <linux/mfd/abx500.h>
 #include <linux/slab.h>
-#include <linux/mfd/abx500/ab8500-bm.h>
 #include <linux/delay.h>
-#include <linux/mfd/abx500/ab8500-gpadc.h>
-#include <linux/mfd/abx500.h>
 #include <linux/time.h>
+#include <linux/of.h>
 #include <linux/completion.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/abx500.h>
+#include <linux/mfd/abx500/ab8500.h>
+#include <linux/mfd/abx500/ab8500-bm.h>
+#include <linux/mfd/abx500/ab8500-gpadc.h>
 
 #define MILLI_TO_MICRO			1000
 #define FG_LSB_IN_MA			1627
@@ -172,7 +173,6 @@ struct inst_curr_result_list {
  * @avg_cap:		Average capacity filter
  * @parent:		Pointer to the struct ab8500
  * @gpadc:		Pointer to the struct gpadc
- * @pdata:		Pointer to the abx500_fg platform data
  * @bat:		Pointer to the abx500_bm platform data
  * @fg_psy:		Structure that holds the FG specific battery properties
  * @fg_wq:		Work queue for running the FG algorithm
@@ -212,7 +212,6 @@ struct ab8500_fg {
 	struct ab8500_fg_avg_cap avg_cap;
 	struct ab8500 *parent;
 	struct ab8500_gpadc *gpadc;
-	struct abx500_fg_platform_data *pdata;
 	struct abx500_bm_data *bat;
 	struct power_supply fg_psy;
 	struct workqueue_struct *fg_wq;
@@ -2429,7 +2428,6 @@ static int __devexit ab8500_fg_remove(struct platform_device *pdev)
 	flush_scheduled_work();
 	power_supply_unregister(&di->fg_psy);
 	platform_set_drvdata(pdev, NULL);
-	kfree(di);
 	return ret;
 }
 
@@ -2442,21 +2440,39 @@ static struct ab8500_fg_interrupts ab8500_fg_irq[] = {
 	{"CCEOC", ab8500_fg_cc_data_end_handler},
 };
 
+static char *supply_interface[] = {
+	"ab8500_chargalg",
+	"ab8500_usb",
+};
+
 static int __devinit ab8500_fg_probe(struct platform_device *pdev)
 {
+	struct device_node *np = pdev->dev.of_node;
+	struct ab8500_fg *di;
 	int i, irq;
 	int ret = 0;
-	struct abx500_bm_plat_data *plat_data = pdev->dev.platform_data;
-	struct ab8500_fg *di;
-
-	if (!plat_data) {
-		dev_err(&pdev->dev, "No platform data\n");
-		return -EINVAL;
-	}
 
-	di = kzalloc(sizeof(*di), GFP_KERNEL);
-	if (!di)
+	di = devm_kzalloc(&pdev->dev, sizeof(*di), GFP_KERNEL);
+	if (!di) {
+		dev_err(&pdev->dev, "%s no mem for ab8500_fg\n", __func__);
 		return -ENOMEM;
+	}
+	di->bat = pdev->mfd_cell->platform_data;
+	if (!di->bat) {
+		if (np) {
+			ret = bmdevs_of_probe(&pdev->dev, np, &di->bat);
+			if (ret) {
+				dev_err(&pdev->dev,
+					"failed to get battery information\n");
+				return ret;
+			}
+		} else {
+			dev_err(&pdev->dev, "missing dt node for ab8500_fg\n");
+			return -EINVAL;
+		}
+	} else {
+		dev_info(&pdev->dev, "falling back to legacy platform data\n");
+	}
 
 	mutex_init(&di->cc_lock);
 
@@ -2465,29 +2481,13 @@ static int __devinit ab8500_fg_probe(struct platform_device *pdev)
 	di->parent = dev_get_drvdata(pdev->dev.parent);
 	di->gpadc = ab8500_gpadc_get("ab8500-gpadc.0");
 
-	/* get fg specific platform data */
-	di->pdata = plat_data->fg;
-	if (!di->pdata) {
-		dev_err(di->dev, "no fg platform data supplied\n");
-		ret = -EINVAL;
-		goto free_device_info;
-	}
-
-	/* get battery specific platform data */
-	di->bat = plat_data->battery;
-	if (!di->bat) {
-		dev_err(di->dev, "no battery platform data supplied\n");
-		ret = -EINVAL;
-		goto free_device_info;
-	}
-
 	di->fg_psy.name = "ab8500_fg";
 	di->fg_psy.type = POWER_SUPPLY_TYPE_BATTERY;
 	di->fg_psy.properties = ab8500_fg_props;
 	di->fg_psy.num_properties = ARRAY_SIZE(ab8500_fg_props);
 	di->fg_psy.get_property = ab8500_fg_get_property;
-	di->fg_psy.supplied_to = di->pdata->supplied_to;
-	di->fg_psy.num_supplicants = di->pdata->num_supplicants;
+	di->fg_psy.supplied_to = supply_interface;
+	di->fg_psy.num_supplicants = ARRAY_SIZE(supply_interface),
 	di->fg_psy.external_power_changed = ab8500_fg_external_power_changed;
 
 	di->bat_cap.max_mah_design = MILLI_TO_MICRO *
@@ -2506,8 +2506,7 @@ static int __devinit ab8500_fg_probe(struct platform_device *pdev)
 	di->fg_wq = create_singlethread_workqueue("ab8500_fg_wq");
 	if (di->fg_wq == NULL) {
 		dev_err(di->dev, "failed to create work queue\n");
-		ret = -ENOMEM;
-		goto free_device_info;
+		return -ENOMEM;
 	}
 
 	/* Init work for running the fg algorithm instantly */
@@ -2606,12 +2605,14 @@ free_irq:
 	}
 free_inst_curr_wq:
 	destroy_workqueue(di->fg_wq);
-free_device_info:
-	kfree(di);
-
 	return ret;
 }
 
+static const struct of_device_id ab8500_fg_match[] = {
+	{ .compatible = "stericsson,ab8500-fg", },
+	{ },
+};
+
 static struct platform_driver ab8500_fg_driver = {
 	.probe = ab8500_fg_probe,
 	.remove = __devexit_p(ab8500_fg_remove),
@@ -2620,6 +2621,7 @@ static struct platform_driver ab8500_fg_driver = {
 	.driver = {
 		.name = "ab8500-fg",
 		.owner = THIS_MODULE,
+		.of_match_table = ab8500_fg_match,
 	},
 };
 
diff --git a/drivers/power/abx500_chargalg.c b/drivers/power/abx500_chargalg.c
index 4d302803ffcc..758ea76de2f8 100644
--- a/drivers/power/abx500_chargalg.c
+++ b/drivers/power/abx500_chargalg.c
@@ -231,7 +231,7 @@ struct abx500_chargalg {
 	struct abx500_chargalg_charger_info chg_info;
 	struct abx500_chargalg_battery_data batt_data;
 	struct abx500_chargalg_suspension_status susp_status;
-	struct abx500_chargalg_platform_data *pdata;
+	struct abx500_bmdevs_plat_data *pdata;
 	struct abx500_bm_data *bat;
 	struct power_supply chargalg_psy;
 	struct ux500_charger *ac_chg;
@@ -1802,7 +1802,7 @@ static int __devexit abx500_chargalg_remove(struct platform_device *pdev)
 
 static int __devinit abx500_chargalg_probe(struct platform_device *pdev)
 {
-	struct abx500_bm_plat_data *plat_data;
+	struct abx500_bmdevs_plat_data *plat_data;
 	int ret = 0;
 
 	struct abx500_chargalg *di =
@@ -1812,10 +1812,8 @@ static int __devinit abx500_chargalg_probe(struct platform_device *pdev)
 
 	/* get device struct */
 	di->dev = &pdev->dev;
-
 	plat_data = pdev->dev.platform_data;
-	di->pdata = plat_data->chargalg;
-	di->bat = plat_data->battery;
+	di->pdata = plat_data;
 
 	/* chargalg supply */
 	di->chargalg_psy.name = "abx500_chargalg";
diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h
index 5d5298d56026..33f2c58554f4 100644
--- a/include/linux/mfd/abx500.h
+++ b/include/linux/mfd/abx500.h
@@ -267,39 +267,27 @@ struct abx500_bm_data {
 	int gnd_lift_resistance;
 	const struct abx500_maxim_parameters *maxi;
 	const struct abx500_bm_capacity_levels *cap_levels;
-	const struct abx500_battery_type *bat_type;
+	struct abx500_battery_type *bat_type;
 	const struct abx500_bm_charger_parameters *chg_params;
 	const struct abx500_fg_parameters *fg_params;
 };
 
-struct abx500_chargalg_platform_data {
-	char **supplied_to;
-	size_t num_supplicants;
-};
-
-struct abx500_charger_platform_data {
-	char **supplied_to;
-	size_t num_supplicants;
-	bool autopower_cfg;
-};
+extern struct abx500_bm_data ab8500_bm_data;
 
-struct abx500_btemp_platform_data {
-	char **supplied_to;
-	size_t num_supplicants;
+struct abx500_bmdevs_plat_data {
+	char	**supplied_to;
+	size_t	num_supplicants;
+	bool	autopower_cfg;
 };
 
-struct abx500_fg_platform_data {
-	char **supplied_to;
-	size_t num_supplicants;
+enum {
+	NTC_EXTERNAL = 0,
+	NTC_INTERNAL,
 };
 
-struct abx500_bm_plat_data {
-	struct abx500_bm_data *battery;
-	struct abx500_charger_platform_data *charger;
-	struct abx500_btemp_platform_data *btemp;
-	struct abx500_fg_platform_data *fg;
-	struct abx500_chargalg_platform_data *chargalg;
-};
+int bmdevs_of_probe(struct device *dev,
+		struct device_node *np,
+		struct abx500_bm_data **battery);
 
 int abx500_set_register_interruptible(struct device *dev, u8 bank, u8 reg,
 	u8 value);
-- 
cgit v1.2.3-55-g7522


From a12810ab9fcf0c9fd5e50b5e350a3ffbeaa571be Mon Sep 17 00:00:00 2001
From: Rajanikanth H.V
Date: Wed, 31 Oct 2012 15:40:33 +0000
Subject: ab8500: Add devicetree support for chargalg

This patch adds device tree support for charging algorithm driver

Signed-off-by: Rajanikanth H.V <rajanikanth.hv@stericsson.com>
Signed-off-by: Anton Vorontsov <anton.vorontsov@linaro.org>
---
 .../bindings/power_supply/ab8500/chargalg.txt      | 16 +++++++
 arch/arm/boot/dts/dbx5x0.dtsi                      |  5 ++
 drivers/mfd/ab8500-core.c                          |  5 ++
 drivers/power/abx500_chargalg.c                    | 54 +++++++++++++++-------
 include/linux/mfd/abx500.h                         |  6 ---
 5 files changed, 64 insertions(+), 22 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/power_supply/ab8500/chargalg.txt

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/power_supply/ab8500/chargalg.txt b/Documentation/devicetree/bindings/power_supply/ab8500/chargalg.txt
new file mode 100644
index 000000000000..ef5328371122
--- /dev/null
+++ b/Documentation/devicetree/bindings/power_supply/ab8500/chargalg.txt
@@ -0,0 +1,16 @@
+=== AB8500 Charging Algorithm Driver ===
+
+The properties below describes the node for chargalg driver.
+
+Required Properties:
+- compatible = Shall be: "stericsson,ab8500-chargalg"
+- battery = Shall be battery specific information
+
+Example:
+ab8500_chargalg {
+	compatible = "stericsson,ab8500-chargalg";
+	battery	   = <&ab8500_battery>;
+};
+
+For information on battery specific node, Ref:
+Documentation/devicetree/bindings/power_supply/ab8500/fg.txt
diff --git a/arch/arm/boot/dts/dbx5x0.dtsi b/arch/arm/boot/dts/dbx5x0.dtsi
index 1d4ad3098aeb..12a68af44903 100644
--- a/arch/arm/boot/dts/dbx5x0.dtsi
+++ b/arch/arm/boot/dts/dbx5x0.dtsi
@@ -373,6 +373,11 @@
 					vddadc-supply	= <&ab8500_ldo_tvout_reg>;
 				};
 
+				ab8500_chargalg {
+					compatible	= "stericsson,ab8500-chargalg";
+					battery		= <&ab8500_battery>;
+				};
+
 				ab8500_usb {
 					compatible = "stericsson,ab8500-usb";
 					interrupts = < 90 0x4
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index c7a120bfd50a..5ec70f26b9d5 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -1071,8 +1071,13 @@ static struct mfd_cell __devinitdata ab8500_bm_devs[] = {
 	},
 	{
 		.name = "ab8500-chargalg",
+		.of_compatible = "stericsson,ab8500-chargalg",
 		.num_resources = ARRAY_SIZE(ab8500_chargalg_resources),
 		.resources = ab8500_chargalg_resources,
+#ifndef CONFIG_OF
+		.platform_data = &ab8500_bm_data,
+		.pdata_size = sizeof(ab8500_bm_data),
+#endif
 	},
 };
 
diff --git a/drivers/power/abx500_chargalg.c b/drivers/power/abx500_chargalg.c
index 758ea76de2f8..dcdc4393b9e7 100644
--- a/drivers/power/abx500_chargalg.c
+++ b/drivers/power/abx500_chargalg.c
@@ -21,6 +21,8 @@
 #include <linux/completion.h>
 #include <linux/workqueue.h>
 #include <linux/kobject.h>
+#include <linux/of.h>
+#include <linux/mfd/core.h>
 #include <linux/mfd/abx500.h>
 #include <linux/mfd/abx500/ux500_chargalg.h>
 #include <linux/mfd/abx500/ab8500-bm.h>
@@ -205,7 +207,6 @@ enum maxim_ret {
  * @chg_info:		information about connected charger types
  * @batt_data:		data of the battery
  * @susp_status:	current charger suspension status
- * @pdata:		pointer to the abx500_chargalg platform data
  * @bat:		pointer to the abx500_bm platform data
  * @chargalg_psy:	structure that holds the battery properties exposed by
  *			the charging algorithm
@@ -231,7 +232,6 @@ struct abx500_chargalg {
 	struct abx500_chargalg_charger_info chg_info;
 	struct abx500_chargalg_battery_data batt_data;
 	struct abx500_chargalg_suspension_status susp_status;
-	struct abx500_bmdevs_plat_data *pdata;
 	struct abx500_bm_data *bat;
 	struct power_supply chargalg_psy;
 	struct ux500_charger *ac_chg;
@@ -1795,25 +1795,44 @@ static int __devexit abx500_chargalg_remove(struct platform_device *pdev)
 	flush_scheduled_work();
 	power_supply_unregister(&di->chargalg_psy);
 	platform_set_drvdata(pdev, NULL);
-	kfree(di);
 
 	return 0;
 }
 
+static char *supply_interface[] = {
+	"ab8500_fg",
+};
+
 static int __devinit abx500_chargalg_probe(struct platform_device *pdev)
 {
-	struct abx500_bmdevs_plat_data *plat_data;
+	struct device_node *np = pdev->dev.of_node;
+	struct abx500_chargalg *di;
 	int ret = 0;
 
-	struct abx500_chargalg *di =
-		kzalloc(sizeof(struct abx500_chargalg), GFP_KERNEL);
-	if (!di)
+	di = devm_kzalloc(&pdev->dev, sizeof(*di), GFP_KERNEL);
+	if (!di) {
+		dev_err(&pdev->dev, "%s no mem for ab8500_chargalg\n", __func__);
 		return -ENOMEM;
+	}
+	di->bat = pdev->mfd_cell->platform_data;
+	if (!di->bat) {
+		if (np) {
+			ret = bmdevs_of_probe(&pdev->dev, np, &di->bat);
+			if (ret) {
+				dev_err(&pdev->dev,
+					"failed to get battery information\n");
+				return ret;
+			}
+		} else {
+			dev_err(&pdev->dev, "missing dt node for ab8500_chargalg\n");
+			return -EINVAL;
+		}
+	} else {
+		dev_info(&pdev->dev, "falling back to legacy platform data\n");
+	}
 
 	/* get device struct */
 	di->dev = &pdev->dev;
-	plat_data = pdev->dev.platform_data;
-	di->pdata = plat_data;
 
 	/* chargalg supply */
 	di->chargalg_psy.name = "abx500_chargalg";
@@ -1821,8 +1840,8 @@ static int __devinit abx500_chargalg_probe(struct platform_device *pdev)
 	di->chargalg_psy.properties = abx500_chargalg_props;
 	di->chargalg_psy.num_properties = ARRAY_SIZE(abx500_chargalg_props);
 	di->chargalg_psy.get_property = abx500_chargalg_get_property;
-	di->chargalg_psy.supplied_to = di->pdata->supplied_to;
-	di->chargalg_psy.num_supplicants = di->pdata->num_supplicants;
+	di->chargalg_psy.supplied_to = supply_interface;
+	di->chargalg_psy.num_supplicants = ARRAY_SIZE(supply_interface),
 	di->chargalg_psy.external_power_changed =
 		abx500_chargalg_external_power_changed;
 
@@ -1842,7 +1861,7 @@ static int __devinit abx500_chargalg_probe(struct platform_device *pdev)
 		create_singlethread_workqueue("abx500_chargalg_wq");
 	if (di->chargalg_wq == NULL) {
 		dev_err(di->dev, "failed to create work queue\n");
-		goto free_device_info;
+		return -ENOMEM;
 	}
 
 	/* Init work for chargalg */
@@ -1883,20 +1902,23 @@ free_psy:
 	power_supply_unregister(&di->chargalg_psy);
 free_chargalg_wq:
 	destroy_workqueue(di->chargalg_wq);
-free_device_info:
-	kfree(di);
-
 	return ret;
 }
 
+static const struct of_device_id ab8500_chargalg_match[] = {
+	{ .compatible = "stericsson,ab8500-chargalg", },
+	{ },
+};
+
 static struct platform_driver abx500_chargalg_driver = {
 	.probe = abx500_chargalg_probe,
 	.remove = __devexit_p(abx500_chargalg_remove),
 	.suspend = abx500_chargalg_suspend,
 	.resume = abx500_chargalg_resume,
 	.driver = {
-		.name = "abx500-chargalg",
+		.name = "ab8500-chargalg",
 		.owner = THIS_MODULE,
+		.of_match_table = ab8500_chargalg_match,
 	},
 };
 
diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h
index 33f2c58554f4..2138bd33021a 100644
--- a/include/linux/mfd/abx500.h
+++ b/include/linux/mfd/abx500.h
@@ -274,12 +274,6 @@ struct abx500_bm_data {
 
 extern struct abx500_bm_data ab8500_bm_data;
 
-struct abx500_bmdevs_plat_data {
-	char	**supplied_to;
-	size_t	num_supplicants;
-	bool	autopower_cfg;
-};
-
 enum {
 	NTC_EXTERNAL = 0,
 	NTC_INTERNAL,
-- 
cgit v1.2.3-55-g7522


From d727abcb2355566a3372ee1810f156fba75112b7 Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Thu, 14 Jun 2012 02:16:42 -0700
Subject: netns: Deduplicate and fix copy_net_ns when !CONFIG_NET_NS

The copy of copy_net_ns used when the network stack is not
built is broken as it does not return -EINVAL when attempting
to create a new network namespace.  We don't even have
a previous network namespace.

Since we need a copy of copy_net_ns in net/net_namespace.h that is
available when the networking stack is not built at all move the
correct version of copy_net_ns from net_namespace.c into net_namespace.h
Leaving us with just 2 versions of copy_net_ns.  One version for when
we compile in network namespace suport and another stub for all other
occasions.

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 include/net/net_namespace.h | 15 +++++++++------
 net/core/net_namespace.c    |  7 -------
 2 files changed, 9 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 95e646641184..32dcb6085ebe 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -126,16 +126,19 @@ struct net {
 /* Init's network namespace */
 extern struct net init_net;
 
-#ifdef CONFIG_NET
+#ifdef CONFIG_NET_NS
 extern struct net *copy_net_ns(unsigned long flags, struct net *net_ns);
 
-#else /* CONFIG_NET */
-static inline struct net *copy_net_ns(unsigned long flags, struct net *net_ns)
+#else /* CONFIG_NET_NS */
+#include <linux/sched.h>
+#include <linux/nsproxy.h>
+static inline struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 {
-	/* There is nothing to copy so this is a noop */
-	return net_ns;
+	if (flags & CLONE_NEWNET)
+		return ERR_PTR(-EINVAL);
+	return old_net;
 }
-#endif /* CONFIG_NET */
+#endif /* CONFIG_NET_NS */
 
 
 extern struct list_head net_namespace_list;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 42f1e1c7514f..2c1c59091685 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -347,13 +347,6 @@ struct net *get_net_ns_by_fd(int fd)
 }
 
 #else
-struct net *copy_net_ns(unsigned long flags, struct net *old_net)
-{
-	if (flags & CLONE_NEWNET)
-		return ERR_PTR(-EINVAL);
-	return old_net;
-}
-
 struct net *get_net_ns_by_fd(int fd)
 {
 	return ERR_PTR(-EINVAL);
-- 
cgit v1.2.3-55-g7522


From 038e7332b8d4c0629a2965e3ede1a92e8e427bd6 Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Thu, 14 Jun 2012 02:31:10 -0700
Subject: userns: make each net (net_ns) belong to a user_ns

The user namespace which creates a new network namespace owns that
namespace and all resources created in it.  This way we can target
capability checks for privileged operations against network resources to
the user_ns which created the network namespace in which the resource
lives.  Privilege to the user namespace which owns the network
namespace, or any parent user namespace thereof, provides the same
privilege to the network resource.

This patch is reworked from a version originally by
Serge E. Hallyn <serge.hallyn@canonical.com>

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 include/net/net_namespace.h |  9 +++++++--
 kernel/nsproxy.c            |  2 +-
 net/core/net_namespace.c    | 16 ++++++++++++----
 3 files changed, 20 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 32dcb6085ebe..c5a43f56b796 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -23,6 +23,7 @@
 #endif
 #include <net/netns/xfrm.h>
 
+struct user_namespace;
 struct proc_dir_entry;
 struct net_device;
 struct sock;
@@ -53,6 +54,8 @@ struct net {
 	struct list_head	cleanup_list;	/* namespaces on death row */
 	struct list_head	exit_list;	/* Use only net_mutex */
 
+	struct user_namespace   *user_ns;	/* Owning user namespace */
+
 	struct proc_dir_entry 	*proc_net;
 	struct proc_dir_entry 	*proc_net_stat;
 
@@ -127,12 +130,14 @@ struct net {
 extern struct net init_net;
 
 #ifdef CONFIG_NET_NS
-extern struct net *copy_net_ns(unsigned long flags, struct net *net_ns);
+extern struct net *copy_net_ns(unsigned long flags,
+	struct user_namespace *user_ns, struct net *old_net);
 
 #else /* CONFIG_NET_NS */
 #include <linux/sched.h>
 #include <linux/nsproxy.h>
-static inline struct net *copy_net_ns(unsigned long flags, struct net *old_net)
+static inline struct net *copy_net_ns(unsigned long flags,
+	struct user_namespace *user_ns, struct net *old_net)
 {
 	if (flags & CLONE_NEWNET)
 		return ERR_PTR(-EINVAL);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index b576f7f14bc6..7e1c3de1ce45 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -90,7 +90,7 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 		goto out_pid;
 	}
 
-	new_nsp->net_ns = copy_net_ns(flags, tsk->nsproxy->net_ns);
+	new_nsp->net_ns = copy_net_ns(flags, task_cred_xxx(tsk, user_ns), tsk->nsproxy->net_ns);
 	if (IS_ERR(new_nsp->net_ns)) {
 		err = PTR_ERR(new_nsp->net_ns);
 		goto out_net;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 2c1c59091685..6456439cbbd9 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -13,6 +13,7 @@
 #include <linux/proc_fs.h>
 #include <linux/file.h>
 #include <linux/export.h>
+#include <linux/user_namespace.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
@@ -145,7 +146,7 @@ static void ops_free_list(const struct pernet_operations *ops,
 /*
  * setup_net runs the initializers for the network namespace object.
  */
-static __net_init int setup_net(struct net *net)
+static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 {
 	/* Must be called with net_mutex held */
 	const struct pernet_operations *ops, *saved_ops;
@@ -155,6 +156,7 @@ static __net_init int setup_net(struct net *net)
 	atomic_set(&net->count, 1);
 	atomic_set(&net->passive, 1);
 	net->dev_base_seq = 1;
+	net->user_ns = user_ns;
 
 #ifdef NETNS_REFCNT_DEBUG
 	atomic_set(&net->use_count, 0);
@@ -232,7 +234,8 @@ void net_drop_ns(void *p)
 		net_free(ns);
 }
 
-struct net *copy_net_ns(unsigned long flags, struct net *old_net)
+struct net *copy_net_ns(unsigned long flags,
+			struct user_namespace *user_ns, struct net *old_net)
 {
 	struct net *net;
 	int rv;
@@ -243,8 +246,11 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 	net = net_alloc();
 	if (!net)
 		return ERR_PTR(-ENOMEM);
+
+	get_user_ns(user_ns);
+
 	mutex_lock(&net_mutex);
-	rv = setup_net(net);
+	rv = setup_net(net, user_ns);
 	if (rv == 0) {
 		rtnl_lock();
 		list_add_tail_rcu(&net->list, &net_namespace_list);
@@ -252,6 +258,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 	}
 	mutex_unlock(&net_mutex);
 	if (rv < 0) {
+		put_user_ns(user_ns);
 		net_drop_ns(net);
 		return ERR_PTR(rv);
 	}
@@ -308,6 +315,7 @@ static void cleanup_net(struct work_struct *work)
 	/* Finally it is safe to free my network namespace structure */
 	list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
 		list_del_init(&net->exit_list);
+		put_user_ns(net->user_ns);
 		net_drop_ns(net);
 	}
 }
@@ -395,7 +403,7 @@ static int __init net_ns_init(void)
 	rcu_assign_pointer(init_net.gen, ng);
 
 	mutex_lock(&net_mutex);
-	if (setup_net(&init_net))
+	if (setup_net(&init_net, &init_user_ns))
 		panic("Could not setup the initial network namespace");
 
 	rtnl_lock();
-- 
cgit v1.2.3-55-g7522


From 5928f5389664fffa295c39bbe23de73069124451 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Mon, 19 Nov 2012 06:58:29 +0530
Subject: regulator: max8973: add regulator driver support

The MAXIM MAX8973 high-efficiency, three phase, DC-DC step-down
switching regulator delievers up to 9A of output current. Each
phase operates at a 2MHz fixed frequency with a 120 deg shift
from the adjacent phase, allowing the use of small magnetic
component.

Add regulator driver for this device.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/regulator/Kconfig                   |  10 +
 drivers/regulator/Makefile                  |   1 +
 drivers/regulator/max8973-regulator.c       | 505 ++++++++++++++++++++++++++++
 include/linux/regulator/max8973-regulator.h |  72 ++++
 4 files changed, 588 insertions(+)
 create mode 100644 drivers/regulator/max8973-regulator.c
 create mode 100644 include/linux/regulator/max8973-regulator.h

(limited to 'include')

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 67d47b59a66d..2b8031235125 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -204,6 +204,16 @@ config REGULATOR_MAX8952
 	  via I2C bus. Maxim 8952 has one voltage output and supports 4 DVS
 	  modes ranging from 0.77V to 1.40V by 0.01V steps.
 
+config REGULATOR_MAX8973
+	tristate "Maxim MAX8973 voltage regulator "
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  The MAXIM MAX8973 high-efficiency. three phase, DC-DC step-down
+	  switching regulator delievers up to 9A of output current. Each
+	  phase operates at a 2MHz fixed frequency with a 120 deg shift
+	  from the adjacent phase, allowing the use of small magnetic component.
+
 config REGULATOR_MAX8997
 	tristate "Maxim 8997/8966 regulator"
 	depends on MFD_MAX8997
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index e431eed8a878..3b51e0de33da 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_REGULATOR_MAX8660) += max8660.o
 obj-$(CONFIG_REGULATOR_MAX8907) += max8907-regulator.o
 obj-$(CONFIG_REGULATOR_MAX8925) += max8925-regulator.o
 obj-$(CONFIG_REGULATOR_MAX8952) += max8952.o
+obj-$(CONFIG_REGULATOR_MAX8973) += max8973-regulator.o
 obj-$(CONFIG_REGULATOR_MAX8997) += max8997.o
 obj-$(CONFIG_REGULATOR_MAX8998) += max8998.o
 obj-$(CONFIG_REGULATOR_MAX77686) += max77686.o
diff --git a/drivers/regulator/max8973-regulator.c b/drivers/regulator/max8973-regulator.c
new file mode 100644
index 000000000000..e6328f935767
--- /dev/null
+++ b/drivers/regulator/max8973-regulator.c
@@ -0,0 +1,505 @@
+/*
+ * max8973-regulator.c -- Maxim max8973
+ *
+ * Regulator driver for MAXIM 8973 DC-DC step-down switching regulator.
+ *
+ * Copyright (c) 2012, NVIDIA Corporation.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind,
+ * whether express or implied; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ * 02111-1307, USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/max8973-regulator.h>
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/regmap.h>
+
+/* Register definitions */
+#define MAX8973_VOUT					0x0
+#define MAX8973_VOUT_DVS				0x1
+#define MAX8973_CONTROL1				0x2
+#define MAX8973_CONTROL2				0x3
+#define MAX8973_CHIPID1					0x4
+#define MAX8973_CHIPID2					0x5
+
+#define MAX8973_MAX_VOUT_REG				2
+
+/* MAX8973_VOUT */
+#define MAX8973_VOUT_ENABLE				BIT(7)
+#define MAX8973_VOUT_MASK				0x7F
+
+/* MAX8973_VOUT_DVS */
+#define MAX8973_DVS_VOUT_MASK				0x7F
+
+/* MAX8973_CONTROL1 */
+#define MAX8973_SNS_ENABLE				BIT(7)
+#define MAX8973_FPWM_EN_M				BIT(6)
+#define MAX8973_NFSR_ENABLE				BIT(5)
+#define MAX8973_AD_ENABLE				BIT(4)
+#define MAX8973_BIAS_ENABLE				BIT(3)
+#define MAX8973_FREQSHIFT_9PER				BIT(2)
+
+#define MAX8973_RAMP_12mV_PER_US			0x0
+#define MAX8973_RAMP_25mV_PER_US			0x1
+#define MAX8973_RAMP_50mV_PER_US			0x2
+#define MAX8973_RAMP_200mV_PER_US			0x3
+
+/* MAX8973_CONTROL2 */
+#define MAX8973_WDTMR_ENABLE				BIT(6)
+#define MAX8973_DISCH_ENBABLE				BIT(5)
+#define MAX8973_FT_ENABLE				BIT(4)
+
+#define MAX8973_CKKADV_TRIP_DISABLE			0xC
+#define MAX8973_CKKADV_TRIP_75mV_PER_US			0x0
+#define MAX8973_CKKADV_TRIP_150mV_PER_US		0x4
+#define MAX8973_CKKADV_TRIP_75mV_PER_US_HIST_DIS	0x8
+#define MAX8973_CONTROL_CLKADV_TRIP_MASK		0x00030000
+
+#define MAX8973_INDUCTOR_MIN_30_PER			0x0
+#define MAX8973_INDUCTOR_NOMINAL			0x1
+#define MAX8973_INDUCTOR_PLUS_30_PER			0x2
+#define MAX8973_INDUCTOR_PLUS_60_PER			0x3
+#define MAX8973_CONTROL_INDUCTOR_VALUE_MASK		0x00300000
+
+#define MAX8973_MIN_VOLATGE				606250
+#define MAX8973_MAX_VOLATGE				1400000
+#define MAX8973_VOLATGE_STEP				6250
+#define MAX8973_BUCK_N_VOLTAGE				0x80
+
+/* Maxim 8973 chip information */
+struct max8973_chip {
+	struct device *dev;
+	struct regulator_desc desc;
+	struct regulator_dev *rdev;
+	struct regmap *regmap;
+	bool enable_external_control;
+	int dvs_gpio;
+	int lru_index[MAX8973_MAX_VOUT_REG];
+	int curr_vout_val[MAX8973_MAX_VOUT_REG];
+	int curr_vout_reg;
+	int curr_gpio_val;
+	bool valid_dvs_gpio;
+};
+
+/*
+ * find_voltage_set_register: Find new voltage configuration register (VOUT).
+ * The finding of the new VOUT register will be based on the LRU mechanism.
+ * Each VOUT register will have different voltage configured . This
+ * Function will look if any of the VOUT register have requested voltage set
+ * or not.
+ *     - If it is already there then it will make that register as most
+ *       recently used and return as found so that caller need not to set
+ *       the VOUT register but need to set the proper gpios to select this
+ *       VOUT register.
+ *     - If requested voltage is not found then it will use the least
+ *       recently mechanism to get new VOUT register for new configuration
+ *       and will return not_found so that caller need to set new VOUT
+ *       register and then gpios (both).
+ */
+static bool find_voltage_set_register(struct max8973_chip *tps,
+		int req_vsel, int *vout_reg, int *gpio_val)
+{
+	int i;
+	bool found = false;
+	int new_vout_reg = tps->lru_index[MAX8973_MAX_VOUT_REG - 1];
+	int found_index = MAX8973_MAX_VOUT_REG - 1;
+
+	for (i = 0; i < MAX8973_MAX_VOUT_REG; ++i) {
+		if (tps->curr_vout_val[tps->lru_index[i]] == req_vsel) {
+			new_vout_reg = tps->lru_index[i];
+			found_index = i;
+			found = true;
+			goto update_lru_index;
+		}
+	}
+
+update_lru_index:
+	for (i = found_index; i > 0; i--)
+		tps->lru_index[i] = tps->lru_index[i - 1];
+
+	tps->lru_index[0] = new_vout_reg;
+	*gpio_val = new_vout_reg;
+	*vout_reg = MAX8973_VOUT + new_vout_reg;
+	return found;
+}
+
+static int max8973_dcdc_get_voltage_sel(struct regulator_dev *rdev)
+{
+	struct max8973_chip *max = rdev_get_drvdata(rdev);
+	unsigned int data;
+	int ret;
+
+	ret = regmap_read(max->regmap, max->curr_vout_reg, &data);
+	if (ret < 0) {
+		dev_err(max->dev, "register %d read failed, err = %d\n",
+			max->curr_vout_reg, ret);
+		return ret;
+	}
+	return data & MAX8973_VOUT_MASK;
+}
+
+static int max8973_dcdc_set_voltage_sel(struct regulator_dev *rdev,
+	     unsigned vsel)
+{
+	struct max8973_chip *max = rdev_get_drvdata(rdev);
+	int ret;
+	bool found = false;
+	int vout_reg = max->curr_vout_reg;
+	int gpio_val = max->curr_gpio_val;
+
+	/*
+	 * If gpios are available to select the VOUT register then least
+	 * recently used register for new configuration.
+	 */
+	if (max->valid_dvs_gpio)
+		found = find_voltage_set_register(max, vsel,
+					&vout_reg, &gpio_val);
+
+	if (!found) {
+		ret = regmap_update_bits(max->regmap, vout_reg,
+					MAX8973_VOUT_MASK, vsel);
+		if (ret < 0) {
+			dev_err(max->dev, "register %d update failed, err %d\n",
+				 vout_reg, ret);
+			return ret;
+		}
+		max->curr_vout_reg = vout_reg;
+		max->curr_vout_val[gpio_val] = vsel;
+	}
+
+	/* Select proper VOUT register vio gpios */
+	if (max->valid_dvs_gpio) {
+		gpio_set_value_cansleep(max->dvs_gpio, gpio_val & 0x1);
+		max->curr_gpio_val = gpio_val;
+	}
+	return 0;
+}
+
+static int max8973_dcdc_set_mode(struct regulator_dev *rdev, unsigned int mode)
+{
+	struct max8973_chip *max = rdev_get_drvdata(rdev);
+	int ret;
+	int pwm;
+
+	/* Enable force PWM mode in FAST mode only. */
+	switch (mode) {
+	case REGULATOR_MODE_FAST:
+		pwm = MAX8973_FPWM_EN_M;
+		break;
+
+	case REGULATOR_MODE_NORMAL:
+		pwm = 0;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	ret = regmap_update_bits(max->regmap, MAX8973_CONTROL1,
+				MAX8973_FPWM_EN_M, pwm);
+	if (ret < 0)
+		dev_err(max->dev, "register %d update failed, err %d\n",
+				MAX8973_CONTROL1, ret);
+	return ret;
+}
+
+static unsigned int max8973_dcdc_get_mode(struct regulator_dev *rdev)
+{
+	struct max8973_chip *max = rdev_get_drvdata(rdev);
+	unsigned int data;
+	int ret;
+
+	ret = regmap_read(max->regmap, MAX8973_CONTROL1, &data);
+	if (ret < 0) {
+		dev_err(max->dev, "register %d read failed, err %d\n",
+				MAX8973_CONTROL1, ret);
+		return ret;
+	}
+	return (data & MAX8973_FPWM_EN_M) ?
+		REGULATOR_MODE_FAST : REGULATOR_MODE_NORMAL;
+}
+
+static struct regulator_ops max8973_dcdc_ops = {
+	.get_voltage_sel	= max8973_dcdc_get_voltage_sel,
+	.set_voltage_sel	= max8973_dcdc_set_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear,
+	.set_mode		= max8973_dcdc_set_mode,
+	.get_mode		= max8973_dcdc_get_mode,
+};
+
+static int __devinit max8973_init_dcdc(struct max8973_chip *max,
+		struct max8973_regulator_platform_data *pdata)
+{
+	int ret;
+	uint8_t	control1 = 0;
+	uint8_t control2 = 0;
+
+	if (pdata->control_flags & MAX8973_CONTROL_REMOTE_SENSE_ENABLE)
+		control1 |= MAX8973_SNS_ENABLE;
+
+	if (!(pdata->control_flags & MAX8973_CONTROL_FALLING_SLEW_RATE_ENABLE))
+		control1 |= MAX8973_NFSR_ENABLE;
+
+	if (pdata->control_flags & MAX8973_CONTROL_OUTPUT_ACTIVE_DISCH_ENABLE)
+		control1 |= MAX8973_AD_ENABLE;
+
+	if (pdata->control_flags & MAX8973_CONTROL_BIAS_ENABLE)
+		control1 |= MAX8973_BIAS_ENABLE;
+
+	if (pdata->control_flags & MAX8973_CONTROL_FREQ_SHIFT_9PER_ENABLE)
+		control1 |= MAX8973_FREQSHIFT_9PER;
+
+	/* Set ramp delay */
+	if (pdata->reg_init_data &&
+			pdata->reg_init_data->constraints.ramp_delay) {
+		if (pdata->reg_init_data->constraints.ramp_delay < 25000)
+			control1 = MAX8973_RAMP_12mV_PER_US;
+		else if (pdata->reg_init_data->constraints.ramp_delay < 50000)
+			control1 = MAX8973_RAMP_25mV_PER_US;
+		else if (pdata->reg_init_data->constraints.ramp_delay < 200000)
+			control1 = MAX8973_RAMP_50mV_PER_US;
+		else
+			control1 = MAX8973_RAMP_200mV_PER_US;
+	} else {
+		control1 = MAX8973_RAMP_12mV_PER_US;
+		max->desc.ramp_delay = 12500;
+	}
+
+	if (!(pdata->control_flags & MAX8973_CONTROL_PULL_DOWN_ENABLE))
+		control2 |= MAX8973_DISCH_ENBABLE;
+
+	/*  Clock advance trip configuration */
+	switch (pdata->control_flags & MAX8973_CONTROL_CLKADV_TRIP_MASK) {
+	case MAX8973_CONTROL_CLKADV_TRIP_DISABLED:
+		control2 |= MAX8973_CKKADV_TRIP_DISABLE;
+		break;
+
+	case MAX8973_CONTROL_CLKADV_TRIP_75mV_PER_US:
+		control2 |= MAX8973_CKKADV_TRIP_75mV_PER_US;
+		break;
+
+	case MAX8973_CONTROL_CLKADV_TRIP_150mV_PER_US:
+		control2 |= MAX8973_CKKADV_TRIP_150mV_PER_US;
+		break;
+
+	case MAX8973_CONTROL_CLKADV_TRIP_75mV_PER_US_HIST_DIS:
+		control2 |= MAX8973_CKKADV_TRIP_75mV_PER_US_HIST_DIS;
+		break;
+	}
+
+	/* Configure inductor value */
+	switch (pdata->control_flags & MAX8973_CONTROL_INDUCTOR_VALUE_MASK) {
+	case MAX8973_CONTROL_INDUCTOR_VALUE_NOMINAL:
+		control2 |= MAX8973_INDUCTOR_NOMINAL;
+		break;
+
+	case MAX8973_CONTROL_INDUCTOR_VALUE_MINUS_30_PER:
+		control2 |= MAX8973_INDUCTOR_MIN_30_PER;
+		break;
+
+	case MAX8973_CONTROL_INDUCTOR_VALUE_PLUS_30_PER:
+		control2 |= MAX8973_INDUCTOR_PLUS_30_PER;
+		break;
+
+	case MAX8973_CONTROL_INDUCTOR_VALUE_PLUS_60_PER:
+		control2 |= MAX8973_INDUCTOR_PLUS_60_PER;
+		break;
+	}
+
+	ret = regmap_write(max->regmap, MAX8973_CONTROL1, control1);
+	if (ret < 0) {
+		dev_err(max->dev, "register %d write failed, err = %d",
+				MAX8973_CONTROL1, ret);
+		return ret;
+	}
+
+	ret = regmap_write(max->regmap, MAX8973_CONTROL2, control2);
+	if (ret < 0) {
+		dev_err(max->dev, "register %d write failed, err = %d",
+				MAX8973_CONTROL2, ret);
+		return ret;
+	}
+
+	/* If external control is enabled then disable EN bit */
+	if (max->enable_external_control) {
+		ret = regmap_update_bits(max->regmap, MAX8973_VOUT,
+						MAX8973_VOUT_ENABLE, 0);
+		if (ret < 0)
+			dev_err(max->dev, "register %d update failed, err = %d",
+				MAX8973_VOUT, ret);
+	}
+	return ret;
+}
+
+static const struct regmap_config max8973_regmap_config = {
+	.reg_bits		= 8,
+	.val_bits		= 8,
+	.max_register		= MAX8973_CHIPID2,
+	.cache_type		= REGCACHE_RBTREE,
+};
+
+static int __devinit max8973_probe(struct i2c_client *client,
+				     const struct i2c_device_id *id)
+{
+	struct max8973_regulator_platform_data *pdata;
+	struct regulator_config config = { };
+	struct regulator_dev *rdev;
+	struct max8973_chip *max;
+	int ret;
+
+	pdata = client->dev.platform_data;
+	if (!pdata) {
+		dev_err(&client->dev, "No Platform data");
+		return -EIO;
+	}
+
+	max = devm_kzalloc(&client->dev, sizeof(*max), GFP_KERNEL);
+	if (!max) {
+		dev_err(&client->dev, "Memory allocation for max failed\n");
+		return -ENOMEM;
+	}
+
+	max->regmap = devm_regmap_init_i2c(client, &max8973_regmap_config);
+	if (IS_ERR(max->regmap)) {
+		ret = PTR_ERR(max->regmap);
+		dev_err(&client->dev, "regmap init failed, err %d\n", ret);
+		return ret;
+	}
+
+	i2c_set_clientdata(client, max);
+	max->dev = &client->dev;
+	max->desc.name = id->name;
+	max->desc.id = 0;
+	max->desc.ops = &max8973_dcdc_ops;
+	max->desc.type = REGULATOR_VOLTAGE;
+	max->desc.owner = THIS_MODULE;
+	max->desc.min_uV = MAX8973_MIN_VOLATGE;
+	max->desc.uV_step = MAX8973_VOLATGE_STEP;
+	max->desc.n_voltages = MAX8973_BUCK_N_VOLTAGE;
+
+	if (pdata->enable_ext_control) {
+		max->desc.enable_reg = MAX8973_VOUT;
+		max->desc.enable_mask = MAX8973_VOUT_ENABLE;
+		max8973_dcdc_ops.enable = regulator_is_enabled_regmap;
+		max8973_dcdc_ops.disable = regulator_disable_regmap;
+		max8973_dcdc_ops.is_enabled = regulator_is_enabled_regmap;
+	}
+
+	max->enable_external_control = pdata->enable_ext_control;
+	max->dvs_gpio = pdata->dvs_gpio;
+	max->curr_gpio_val = pdata->dvs_def_state;
+	max->curr_vout_reg = MAX8973_VOUT + pdata->dvs_def_state;
+	max->lru_index[0] = max->curr_vout_reg;
+	max->valid_dvs_gpio = false;
+
+	if (gpio_is_valid(max->dvs_gpio)) {
+		int gpio_flags;
+		int i;
+
+		gpio_flags = (pdata->dvs_def_state) ?
+				GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW;
+		ret = devm_gpio_request_one(&client->dev, max->dvs_gpio,
+				gpio_flags, "max8973-dvs");
+		if (ret) {
+			dev_err(&client->dev,
+				"gpio_request for gpio %d failed, err = %d\n",
+				max->dvs_gpio, ret);
+			return ret;
+		}
+		max->valid_dvs_gpio = true;
+
+		/*
+		 * Initialize the lru index with vout_reg id
+		 * The index 0 will be most recently used and
+		 * set with the max->curr_vout_reg */
+		for (i = 0; i < MAX8973_MAX_VOUT_REG; ++i)
+			max->lru_index[i] = i;
+		max->lru_index[0] = max->curr_vout_reg;
+		max->lru_index[max->curr_vout_reg] = 0;
+	}
+
+	ret = max8973_init_dcdc(max, pdata);
+	if (ret < 0) {
+		dev_err(max->dev, "Max8973 Init failed, err = %d\n", ret);
+		return ret;
+	}
+
+	config.dev = &client->dev;
+	config.init_data = pdata->reg_init_data;
+	config.driver_data = max;
+	config.of_node = client->dev.of_node;
+	config.regmap = max->regmap;
+
+	/* Register the regulators */
+	rdev = regulator_register(&max->desc, &config);
+	if (IS_ERR(rdev)) {
+		ret = PTR_ERR(rdev);
+		dev_err(max->dev, "regulator register failed, err %d\n", ret);
+		return ret;
+	}
+
+	max->rdev = rdev;
+	return 0;
+}
+
+static int __devexit max8973_remove(struct i2c_client *client)
+{
+	struct max8973_chip *max = i2c_get_clientdata(client);
+
+	regulator_unregister(max->rdev);
+	return 0;
+}
+
+static const struct i2c_device_id max8973_id[] = {
+	{.name = "max8973",},
+	{},
+};
+
+MODULE_DEVICE_TABLE(i2c, max8973_id);
+
+static struct i2c_driver max8973_i2c_driver = {
+	.driver = {
+		.name = "max8973",
+		.owner = THIS_MODULE,
+	},
+	.probe = max8973_probe,
+	.remove = __devexit_p(max8973_remove),
+	.id_table = max8973_id,
+};
+
+static int __init max8973_init(void)
+{
+	return i2c_add_driver(&max8973_i2c_driver);
+}
+subsys_initcall(max8973_init);
+
+static void __exit max8973_cleanup(void)
+{
+	i2c_del_driver(&max8973_i2c_driver);
+}
+module_exit(max8973_cleanup);
+
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_DESCRIPTION("MAX8973 voltage regulator driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/regulator/max8973-regulator.h b/include/linux/regulator/max8973-regulator.h
new file mode 100644
index 000000000000..f8acc052e353
--- /dev/null
+++ b/include/linux/regulator/max8973-regulator.h
@@ -0,0 +1,72 @@
+/*
+ * max8973-regulator.h -- MAXIM 8973 regulator
+ *
+ * Interface for regulator driver for MAXIM 8973 DC-DC step-down
+ * switching regulator.
+ *
+ * Copyright (C) 2012 NVIDIA Corporation
+
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA	02110-1301, USA.
+ *
+ */
+
+#ifndef __LINUX_REGULATOR_MAX8973_H
+#define __LINUX_REGULATOR_MAX8973_H
+
+/*
+ * Control flags for configuration of the device.
+ * Client need to pass this information with ORed
+ */
+#define MAX8973_CONTROL_REMOTE_SENSE_ENABLE			0x00000001
+#define MAX8973_CONTROL_FALLING_SLEW_RATE_ENABLE		0x00000002
+#define MAX8973_CONTROL_OUTPUT_ACTIVE_DISCH_ENABLE		0x00000004
+#define MAX8973_CONTROL_BIAS_ENABLE				0x00000008
+#define MAX8973_CONTROL_PULL_DOWN_ENABLE			0x00000010
+#define MAX8973_CONTROL_FREQ_SHIFT_9PER_ENABLE			0x00000020
+
+#define MAX8973_CONTROL_CLKADV_TRIP_DISABLED			0x00000000
+#define MAX8973_CONTROL_CLKADV_TRIP_75mV_PER_US			0x00010000
+#define MAX8973_CONTROL_CLKADV_TRIP_150mV_PER_US		0x00020000
+#define MAX8973_CONTROL_CLKADV_TRIP_75mV_PER_US_HIST_DIS	0x00030000
+
+#define MAX8973_CONTROL_INDUCTOR_VALUE_NOMINAL			0x00000000
+#define MAX8973_CONTROL_INDUCTOR_VALUE_MINUS_30_PER		0x00100000
+#define MAX8973_CONTROL_INDUCTOR_VALUE_PLUS_30_PER		0x00200000
+#define MAX8973_CONTROL_INDUCTOR_VALUE_PLUS_60_PER		0x00300000
+
+/*
+ * struct max8973_regulator_platform_data - max8973 regulator platform data.
+ *
+ * @reg_init_data: The regulator init data.
+ * @control_flags: Control flags which are ORed value of above flags to
+ *		configure device.
+ * @enable_ext_control: Enable the voltage enable/disable through external
+ *		control signal from EN input pin. If it is false then
+ *		voltage output will be enabled/disabled through EN bit of
+ *		device register.
+ * @dvs_gpio: GPIO for dvs. It should be -1 if this is tied with fixed logic.
+ * @dvs_def_state: Default state of dvs. 1 if it is high else 0.
+ */
+struct max8973_regulator_platform_data {
+	struct regulator_init_data *reg_init_data;
+	unsigned long control_flags;
+	bool enable_ext_control;
+	int dvs_gpio;
+	unsigned dvs_def_state:1;
+};
+
+#endif /* __LINUX_REGULATOR_MAX8973_H */
-- 
cgit v1.2.3-55-g7522


From 0857ba3c24c308f42a242fe8a1894772750230ce Mon Sep 17 00:00:00 2001
From: Aaro Koskinen
Date: Sun, 18 Nov 2012 18:36:19 +0200
Subject: i2c: i2c-cbus-gpio: introduce driver

Add i2c driver to enable access to devices behind CBUS on Nokia Internet
Tablets.

The patch also adds CBUS I2C configuration for N8x0 which is one of the
users of this driver.

Acked-by: Felipe Balbi <balbi@ti.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
---
 .../devicetree/bindings/i2c/i2c-cbus-gpio.txt      |  27 ++
 arch/arm/mach-omap2/board-n8x0.c                   |  42 +++
 drivers/i2c/busses/Kconfig                         |  10 +
 drivers/i2c/busses/Makefile                        |   1 +
 drivers/i2c/busses/i2c-cbus-gpio.c                 | 300 +++++++++++++++++++++
 include/linux/platform_data/i2c-cbus-gpio.h        |  27 ++
 6 files changed, 407 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/i2c/i2c-cbus-gpio.txt
 create mode 100644 drivers/i2c/busses/i2c-cbus-gpio.c
 create mode 100644 include/linux/platform_data/i2c-cbus-gpio.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/i2c/i2c-cbus-gpio.txt b/Documentation/devicetree/bindings/i2c/i2c-cbus-gpio.txt
new file mode 100644
index 000000000000..8ce9cd2855b5
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/i2c-cbus-gpio.txt
@@ -0,0 +1,27 @@
+Device tree bindings for i2c-cbus-gpio driver
+
+Required properties:
+	- compatible = "i2c-cbus-gpio";
+	- gpios: clk, dat, sel
+	- #address-cells = <1>;
+	- #size-cells = <0>;
+
+Optional properties:
+	- child nodes conforming to i2c bus binding
+
+Example:
+
+i2c@0 {
+	compatible = "i2c-cbus-gpio";
+	gpios = <&gpio 66 0 /* clk */
+		 &gpio 65 0 /* dat */
+		 &gpio 64 0 /* sel */
+		>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	retu-mfd: retu@1 {
+		compatible = "retu-mfd";
+		reg = <0x1>;
+	};
+};
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index d95f727ca39a..bbfd74263c42 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -16,10 +16,12 @@
 #include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/stddef.h>
 #include <linux/i2c.h>
 #include <linux/spi/spi.h>
 #include <linux/usb/musb.h>
+#include <linux/platform_data/i2c-cbus-gpio.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 #include <linux/platform_data/mtd-onenand-omap2.h>
 #include <sound/tlv320aic3x.h>
@@ -39,6 +41,45 @@
 #define TUSB6010_GPIO_ENABLE	0
 #define TUSB6010_DMACHAN	0x3f
 
+#if defined(CONFIG_I2C_CBUS_GPIO) || defined(CONFIG_I2C_CBUS_GPIO_MODULE)
+static struct i2c_cbus_platform_data n8x0_cbus_data = {
+	.clk_gpio = 66,
+	.dat_gpio = 65,
+	.sel_gpio = 64,
+};
+
+static struct platform_device n8x0_cbus_device = {
+	.name	= "i2c-cbus-gpio",
+	.id	= 3,
+	.dev	= {
+		.platform_data = &n8x0_cbus_data,
+	},
+};
+
+static struct i2c_board_info n8x0_i2c_board_info_3[] __initdata = {
+	{
+		I2C_BOARD_INFO("retu-mfd", 0x01),
+	},
+};
+
+static void __init n8x0_cbus_init(void)
+{
+	const int retu_irq_gpio = 108;
+
+	if (gpio_request_one(retu_irq_gpio, GPIOF_IN, "Retu IRQ"))
+		return;
+	irq_set_irq_type(gpio_to_irq(retu_irq_gpio), IRQ_TYPE_EDGE_RISING);
+	n8x0_i2c_board_info_3[0].irq = gpio_to_irq(retu_irq_gpio);
+	i2c_register_board_info(3, n8x0_i2c_board_info_3,
+				ARRAY_SIZE(n8x0_i2c_board_info_3));
+	platform_device_register(&n8x0_cbus_device);
+}
+#else /* CONFIG_I2C_CBUS_GPIO */
+static void __init n8x0_cbus_init(void)
+{
+}
+#endif /* CONFIG_I2C_CBUS_GPIO */
+
 #if defined(CONFIG_USB_MUSB_TUSB6010) || defined(CONFIG_USB_MUSB_TUSB6010_MODULE)
 /*
  * Enable or disable power to TUSB6010. When enabling, turn on 3.3 V and
@@ -677,6 +718,7 @@ static void __init n8x0_init_machine(void)
 	gpmc_onenand_init(board_onenand_data);
 	n8x0_mmc_init();
 	n8x0_usb_init();
+	n8x0_cbus_init();
 }
 
 MACHINE_START(NOKIA_N800, "Nokia N800")
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index e9df4612b7eb..e949edf644d4 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -337,6 +337,16 @@ config I2C_BLACKFIN_TWI_CLK_KHZ
 	help
 	  The unit of the TWI clock is kHz.
 
+config I2C_CBUS_GPIO
+	tristate "CBUS I2C driver"
+	depends on GENERIC_GPIO
+	help
+	  Support for CBUS access using I2C API. Mostly relevant for Nokia
+	  Internet Tablets (770, N800 and N810).
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called i2c-cbus-gpio.
+
 config I2C_CPM
 	tristate "Freescale CPM1 or CPM2 (MPC8xx/826x)"
 	depends on (CPM1 || CPM2) && OF_I2C
diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile
index 395b516ffa08..f9e3e0b5c827 100644
--- a/drivers/i2c/busses/Makefile
+++ b/drivers/i2c/busses/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_I2C_POWERMAC)	+= i2c-powermac.o
 obj-$(CONFIG_I2C_AT91)		+= i2c-at91.o
 obj-$(CONFIG_I2C_AU1550)	+= i2c-au1550.o
 obj-$(CONFIG_I2C_BLACKFIN_TWI)	+= i2c-bfin-twi.o
+obj-$(CONFIG_I2C_CBUS_GPIO)	+= i2c-cbus-gpio.o
 obj-$(CONFIG_I2C_CPM)		+= i2c-cpm.o
 obj-$(CONFIG_I2C_DAVINCI)	+= i2c-davinci.o
 obj-$(CONFIG_I2C_DESIGNWARE_CORE)	+= i2c-designware-core.o
diff --git a/drivers/i2c/busses/i2c-cbus-gpio.c b/drivers/i2c/busses/i2c-cbus-gpio.c
new file mode 100644
index 000000000000..98386d659318
--- /dev/null
+++ b/drivers/i2c/busses/i2c-cbus-gpio.c
@@ -0,0 +1,300 @@
+/*
+ * CBUS I2C driver for Nokia Internet Tablets.
+ *
+ * Copyright (C) 2004-2010 Nokia Corporation
+ *
+ * Based on code written by Juha Yrjölä, David Weinehall, Mikko Ylinen and
+ * Felipe Balbi. Converted to I2C driver by Aaro Koskinen.
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file "COPYING" in the main directory of this
+ * archive for more details.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/io.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_gpio.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/i2c-cbus-gpio.h>
+
+/*
+ * Bit counts are derived from Nokia implementation. These should be checked
+ * if other CBUS implementations appear.
+ */
+#define CBUS_ADDR_BITS	3
+#define CBUS_REG_BITS	5
+
+struct cbus_host {
+	spinlock_t	lock;		/* host lock */
+	struct device	*dev;
+	int		clk_gpio;
+	int		dat_gpio;
+	int		sel_gpio;
+};
+
+/**
+ * cbus_send_bit - sends one bit over the bus
+ * @host: the host we're using
+ * @bit: one bit of information to send
+ */
+static void cbus_send_bit(struct cbus_host *host, unsigned bit)
+{
+	gpio_set_value(host->dat_gpio, bit ? 1 : 0);
+	gpio_set_value(host->clk_gpio, 1);
+	gpio_set_value(host->clk_gpio, 0);
+}
+
+/**
+ * cbus_send_data - sends @len amount of data over the bus
+ * @host: the host we're using
+ * @data: the data to send
+ * @len: size of the transfer
+ */
+static void cbus_send_data(struct cbus_host *host, unsigned data, unsigned len)
+{
+	int i;
+
+	for (i = len; i > 0; i--)
+		cbus_send_bit(host, data & (1 << (i - 1)));
+}
+
+/**
+ * cbus_receive_bit - receives one bit from the bus
+ * @host: the host we're using
+ */
+static int cbus_receive_bit(struct cbus_host *host)
+{
+	int ret;
+
+	gpio_set_value(host->clk_gpio, 1);
+	ret = gpio_get_value(host->dat_gpio);
+	gpio_set_value(host->clk_gpio, 0);
+	return ret;
+}
+
+/**
+ * cbus_receive_word - receives 16-bit word from the bus
+ * @host: the host we're using
+ */
+static int cbus_receive_word(struct cbus_host *host)
+{
+	int ret = 0;
+	int i;
+
+	for (i = 16; i > 0; i--) {
+		int bit = cbus_receive_bit(host);
+
+		if (bit < 0)
+			return bit;
+
+		if (bit)
+			ret |= 1 << (i - 1);
+	}
+	return ret;
+}
+
+/**
+ * cbus_transfer - transfers data over the bus
+ * @host: the host we're using
+ * @rw: read/write flag
+ * @dev: device address
+ * @reg: register address
+ * @data: if @rw == I2C_SBUS_WRITE data to send otherwise 0
+ */
+static int cbus_transfer(struct cbus_host *host, char rw, unsigned dev,
+			 unsigned reg, unsigned data)
+{
+	unsigned long flags;
+	int ret;
+
+	/* We don't want interrupts disturbing our transfer */
+	spin_lock_irqsave(&host->lock, flags);
+
+	/* Reset state and start of transfer, SEL stays down during transfer */
+	gpio_set_value(host->sel_gpio, 0);
+
+	/* Set the DAT pin to output */
+	gpio_direction_output(host->dat_gpio, 1);
+
+	/* Send the device address */
+	cbus_send_data(host, dev, CBUS_ADDR_BITS);
+
+	/* Send the rw flag */
+	cbus_send_bit(host, rw == I2C_SMBUS_READ);
+
+	/* Send the register address */
+	cbus_send_data(host, reg, CBUS_REG_BITS);
+
+	if (rw == I2C_SMBUS_WRITE) {
+		cbus_send_data(host, data, 16);
+		ret = 0;
+	} else {
+		ret = gpio_direction_input(host->dat_gpio);
+		if (ret) {
+			dev_dbg(host->dev, "failed setting direction\n");
+			goto out;
+		}
+		gpio_set_value(host->clk_gpio, 1);
+
+		ret = cbus_receive_word(host);
+		if (ret < 0) {
+			dev_dbg(host->dev, "failed receiving data\n");
+			goto out;
+		}
+	}
+
+	/* Indicate end of transfer, SEL goes up until next transfer */
+	gpio_set_value(host->sel_gpio, 1);
+	gpio_set_value(host->clk_gpio, 1);
+	gpio_set_value(host->clk_gpio, 0);
+
+out:
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	return ret;
+}
+
+static int cbus_i2c_smbus_xfer(struct i2c_adapter	*adapter,
+			       u16			addr,
+			       unsigned short		flags,
+			       char			read_write,
+			       u8			command,
+			       int			size,
+			       union i2c_smbus_data	*data)
+{
+	struct cbus_host *chost = i2c_get_adapdata(adapter);
+	int ret;
+
+	if (size != I2C_SMBUS_WORD_DATA)
+		return -EINVAL;
+
+	ret = cbus_transfer(chost, read_write == I2C_SMBUS_READ, addr,
+			    command, data->word);
+	if (ret < 0)
+		return ret;
+
+	if (read_write == I2C_SMBUS_READ)
+		data->word = ret;
+
+	return 0;
+}
+
+static u32 cbus_i2c_func(struct i2c_adapter *adapter)
+{
+	return I2C_FUNC_SMBUS_READ_WORD_DATA | I2C_FUNC_SMBUS_WRITE_WORD_DATA;
+}
+
+static const struct i2c_algorithm cbus_i2c_algo = {
+	.smbus_xfer	= cbus_i2c_smbus_xfer,
+	.functionality	= cbus_i2c_func,
+};
+
+static int cbus_i2c_remove(struct platform_device *pdev)
+{
+	struct i2c_adapter *adapter = platform_get_drvdata(pdev);
+
+	return i2c_del_adapter(adapter);
+}
+
+static int cbus_i2c_probe(struct platform_device *pdev)
+{
+	struct i2c_adapter *adapter;
+	struct cbus_host *chost;
+	int ret;
+
+	adapter = devm_kzalloc(&pdev->dev, sizeof(struct i2c_adapter),
+			       GFP_KERNEL);
+	if (!adapter)
+		return -ENOMEM;
+
+	chost = devm_kzalloc(&pdev->dev, sizeof(*chost), GFP_KERNEL);
+	if (!chost)
+		return -ENOMEM;
+
+	if (pdev->dev.of_node) {
+		struct device_node *dnode = pdev->dev.of_node;
+		if (of_gpio_count(dnode) != 3)
+			return -ENODEV;
+		chost->clk_gpio = of_get_gpio(dnode, 0);
+		chost->dat_gpio = of_get_gpio(dnode, 1);
+		chost->sel_gpio = of_get_gpio(dnode, 2);
+	} else if (pdev->dev.platform_data) {
+		struct i2c_cbus_platform_data *pdata = pdev->dev.platform_data;
+		chost->clk_gpio = pdata->clk_gpio;
+		chost->dat_gpio = pdata->dat_gpio;
+		chost->sel_gpio = pdata->sel_gpio;
+	} else {
+		return -ENODEV;
+	}
+
+	adapter->owner		= THIS_MODULE;
+	adapter->class		= I2C_CLASS_HWMON;
+	adapter->dev.parent	= &pdev->dev;
+	adapter->nr		= pdev->id;
+	adapter->timeout	= HZ;
+	adapter->algo		= &cbus_i2c_algo;
+	strlcpy(adapter->name, "CBUS I2C adapter", sizeof(adapter->name));
+
+	spin_lock_init(&chost->lock);
+	chost->dev = &pdev->dev;
+
+	ret = devm_gpio_request_one(&pdev->dev, chost->clk_gpio,
+				    GPIOF_OUT_INIT_LOW, "CBUS clk");
+	if (ret)
+		return ret;
+
+	ret = devm_gpio_request_one(&pdev->dev, chost->dat_gpio, GPIOF_IN,
+				    "CBUS data");
+	if (ret)
+		return ret;
+
+	ret = devm_gpio_request_one(&pdev->dev, chost->sel_gpio,
+				    GPIOF_OUT_INIT_HIGH, "CBUS sel");
+	if (ret)
+		return ret;
+
+	i2c_set_adapdata(adapter, chost);
+	platform_set_drvdata(pdev, adapter);
+
+	return i2c_add_numbered_adapter(adapter);
+}
+
+#if defined(CONFIG_OF)
+static const struct of_device_id i2c_cbus_dt_ids[] = {
+	{ .compatible = "i2c-cbus-gpio", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, i2c_cbus_dt_ids);
+#endif
+
+static struct platform_driver cbus_i2c_driver = {
+	.probe	= cbus_i2c_probe,
+	.remove	= cbus_i2c_remove,
+	.driver	= {
+		.owner	= THIS_MODULE,
+		.name	= "i2c-cbus-gpio",
+	},
+};
+module_platform_driver(cbus_i2c_driver);
+
+MODULE_ALIAS("platform:i2c-cbus-gpio");
+MODULE_DESCRIPTION("CBUS I2C driver");
+MODULE_AUTHOR("Juha Yrjölä");
+MODULE_AUTHOR("David Weinehall");
+MODULE_AUTHOR("Mikko Ylinen");
+MODULE_AUTHOR("Felipe Balbi");
+MODULE_AUTHOR("Aaro Koskinen <aaro.koskinen@iki.fi>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/platform_data/i2c-cbus-gpio.h b/include/linux/platform_data/i2c-cbus-gpio.h
new file mode 100644
index 000000000000..6faa992a9502
--- /dev/null
+++ b/include/linux/platform_data/i2c-cbus-gpio.h
@@ -0,0 +1,27 @@
+/*
+ * i2c-cbus-gpio.h - CBUS I2C platform_data definition
+ *
+ * Copyright (C) 2004-2009 Nokia Corporation
+ *
+ * Written by Felipe Balbi and Aaro Koskinen.
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file "COPYING" in the main directory of this
+ * archive for more details.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __INCLUDE_LINUX_I2C_CBUS_GPIO_H
+#define __INCLUDE_LINUX_I2C_CBUS_GPIO_H
+
+struct i2c_cbus_platform_data {
+	int dat_gpio;
+	int clk_gpio;
+	int sel_gpio;
+};
+
+#endif /* __INCLUDE_LINUX_I2C_CBUS_GPIO_H */
-- 
cgit v1.2.3-55-g7522


From 4a200c3b9a40242652b5734630bdd0bcf3aca75f Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires
Date: Mon, 12 Nov 2012 15:42:59 +0100
Subject: HID: i2c-hid: introduce HID over i2c specification implementation

Microsoft published the protocol specification of HID over i2c:
http://msdn.microsoft.com/en-us/library/windows/hardware/hh852380.aspx

This patch introduces an implementation of this protocol.

This implementation does not includes the ACPI part of the specification.
This will come when ACPI 5.0 devices enumeration will be available.

Once the ACPI part is done, OEM will not have to declare HID over I2C
devices in their platform specific driver.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/Kconfig           |   2 +
 drivers/hid/Makefile          |   1 +
 drivers/hid/i2c-hid/Kconfig   |  21 +
 drivers/hid/i2c-hid/Makefile  |   5 +
 drivers/hid/i2c-hid/i2c-hid.c | 974 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/i2c/i2c-hid.h   |  35 ++
 6 files changed, 1038 insertions(+)
 create mode 100644 drivers/hid/i2c-hid/Kconfig
 create mode 100644 drivers/hid/i2c-hid/Makefile
 create mode 100644 drivers/hid/i2c-hid/i2c-hid.c
 create mode 100644 include/linux/i2c/i2c-hid.h

(limited to 'include')

diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 1630150ad2b1..95cfe9181bf2 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -728,4 +728,6 @@ endif # HID
 
 source "drivers/hid/usbhid/Kconfig"
 
+source "drivers/hid/i2c-hid/Kconfig"
+
 endmenu
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index cef68ca859d3..a1a28befac72 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -118,3 +118,4 @@ obj-$(CONFIG_USB_HID)		+= usbhid/
 obj-$(CONFIG_USB_MOUSE)		+= usbhid/
 obj-$(CONFIG_USB_KBD)		+= usbhid/
 
+obj-$(CONFIG_I2C_HID)		+= i2c-hid/
diff --git a/drivers/hid/i2c-hid/Kconfig b/drivers/hid/i2c-hid/Kconfig
new file mode 100644
index 000000000000..5b7d4d87a143
--- /dev/null
+++ b/drivers/hid/i2c-hid/Kconfig
@@ -0,0 +1,21 @@
+menu "I2C HID support"
+	depends on I2C
+
+config I2C_HID
+	tristate "HID over I2C transport layer"
+	default n
+	depends on I2C && INPUT
+	select HID
+	---help---
+	  Say Y here if you want to use the HID over i2c protocol
+	  implementation.
+
+	  If unsure, say N.
+
+	  This support is also available as a module.  If so, the module
+	  will be called i2c-hid.
+
+comment "Input core support is needed for HID over I2C input layer"
+	depends on I2C_HID && INPUT=n
+
+endmenu
diff --git a/drivers/hid/i2c-hid/Makefile b/drivers/hid/i2c-hid/Makefile
new file mode 100644
index 000000000000..832d8f9aaba2
--- /dev/null
+++ b/drivers/hid/i2c-hid/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the I2C input drivers
+#
+
+obj-$(CONFIG_I2C_HID)				+= i2c-hid.o
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
new file mode 100644
index 000000000000..11140bdae660
--- /dev/null
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -0,0 +1,974 @@
+/*
+ * HID over I2C protocol implementation
+ *
+ * Copyright (c) 2012 Benjamin Tissoires <benjamin.tissoires@gmail.com>
+ * Copyright (c) 2012 Ecole Nationale de l'Aviation Civile, France
+ * Copyright (c) 2012 Red Hat, Inc
+ *
+ * This code is partly based on "USB HID support for Linux":
+ *
+ *  Copyright (c) 1999 Andreas Gal
+ *  Copyright (c) 2000-2005 Vojtech Pavlik <vojtech@suse.cz>
+ *  Copyright (c) 2005 Michael Haboustak <mike-@cinci.rr.com> for Concept2, Inc
+ *  Copyright (c) 2007-2008 Oliver Neukum
+ *  Copyright (c) 2006-2010 Jiri Kosina
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive for
+ * more details.
+ */
+
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/input.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/pm.h>
+#include <linux/device.h>
+#include <linux/wait.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/list.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/bug.h>
+#include <linux/hid.h>
+
+#include <linux/i2c/i2c-hid.h>
+
+/* flags */
+#define I2C_HID_STARTED		(1 << 0)
+#define I2C_HID_RESET_PENDING	(1 << 1)
+#define I2C_HID_READ_PENDING	(1 << 2)
+
+#define I2C_HID_PWR_ON		0x00
+#define I2C_HID_PWR_SLEEP	0x01
+
+/* debug option */
+static bool debug = false;
+module_param(debug, bool, 0444);
+MODULE_PARM_DESC(debug, "print a lot of debug information");
+
+#define i2c_hid_dbg(ihid, fmt, arg...)	\
+	if (debug)			\
+		dev_printk(KERN_DEBUG, &(ihid)->client->dev, fmt, ##arg)
+
+struct i2c_hid_desc {
+	__le16 wHIDDescLength;
+	__le16 bcdVersion;
+	__le16 wReportDescLength;
+	__le16 wReportDescRegister;
+	__le16 wInputRegister;
+	__le16 wMaxInputLength;
+	__le16 wOutputRegister;
+	__le16 wMaxOutputLength;
+	__le16 wCommandRegister;
+	__le16 wDataRegister;
+	__le16 wVendorID;
+	__le16 wProductID;
+	__le16 wVersionID;
+} __packed;
+
+struct i2c_hid_cmd {
+	unsigned int registerIndex;
+	__u8 opcode;
+	unsigned int length;
+	bool wait;
+};
+
+union command {
+	u8 data[0];
+	struct cmd {
+		__le16 reg;
+		__u8 reportTypeID;
+		__u8 opcode;
+	} __packed c;
+};
+
+#define I2C_HID_CMD(opcode_) \
+	.opcode = opcode_, .length = 4, \
+	.registerIndex = offsetof(struct i2c_hid_desc, wCommandRegister)
+
+/* fetch HID descriptor */
+static const struct i2c_hid_cmd hid_descr_cmd = { .length = 2 };
+/* fetch report descriptors */
+static const struct i2c_hid_cmd hid_report_descr_cmd = {
+		.registerIndex = offsetof(struct i2c_hid_desc,
+			wReportDescRegister),
+		.opcode = 0x00,
+		.length = 2 };
+/* commands */
+static const struct i2c_hid_cmd hid_reset_cmd =		{ I2C_HID_CMD(0x01),
+							  .wait = true };
+static const struct i2c_hid_cmd hid_get_report_cmd =	{ I2C_HID_CMD(0x02) };
+static const struct i2c_hid_cmd hid_set_report_cmd =	{ I2C_HID_CMD(0x03) };
+static const struct i2c_hid_cmd hid_get_idle_cmd =	{ I2C_HID_CMD(0x04) };
+static const struct i2c_hid_cmd hid_set_idle_cmd =	{ I2C_HID_CMD(0x05) };
+static const struct i2c_hid_cmd hid_get_protocol_cmd =	{ I2C_HID_CMD(0x06) };
+static const struct i2c_hid_cmd hid_set_protocol_cmd =	{ I2C_HID_CMD(0x07) };
+static const struct i2c_hid_cmd hid_set_power_cmd =	{ I2C_HID_CMD(0x08) };
+/* read/write data register */
+static const struct i2c_hid_cmd hid_data_cmd = {
+		.registerIndex = offsetof(struct i2c_hid_desc, wDataRegister),
+		.opcode = 0x00,
+		.length = 2 };
+/* write output reports */
+static const struct i2c_hid_cmd hid_out_cmd = {
+		.registerIndex = offsetof(struct i2c_hid_desc,
+			wOutputRegister),
+		.opcode = 0x00,
+		.length = 2 };
+
+/* The main device structure */
+struct i2c_hid {
+	struct i2c_client	*client;	/* i2c client */
+	struct hid_device	*hid;	/* pointer to corresponding HID dev */
+	union {
+		__u8 hdesc_buffer[sizeof(struct i2c_hid_desc)];
+		struct i2c_hid_desc hdesc;	/* the HID Descriptor */
+	};
+	__le16			wHIDDescRegister; /* location of the i2c
+						   * register of the HID
+						   * descriptor. */
+	unsigned int		bufsize;	/* i2c buffer size */
+	char			*inbuf;		/* Input buffer */
+	char			*cmdbuf;	/* Command buffer */
+	char			*argsbuf;	/* Command arguments buffer */
+
+	unsigned long		flags;		/* device flags */
+
+	int			irq;		/* the interrupt line irq */
+
+	wait_queue_head_t	wait;		/* For waiting the interrupt */
+};
+
+static int __i2c_hid_command(struct i2c_client *client,
+		const struct i2c_hid_cmd *command, u8 reportID,
+		u8 reportType, u8 *args, int args_len,
+		unsigned char *buf_recv, int data_len)
+{
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	union command *cmd = (union command *)ihid->cmdbuf;
+	int ret;
+	struct i2c_msg msg[2];
+	int msg_num = 1;
+
+	int length = command->length;
+	bool wait = command->wait;
+	unsigned int registerIndex = command->registerIndex;
+
+	/* special case for hid_descr_cmd */
+	if (command == &hid_descr_cmd) {
+		cmd->c.reg = ihid->wHIDDescRegister;
+	} else {
+		cmd->data[0] = ihid->hdesc_buffer[registerIndex];
+		cmd->data[1] = ihid->hdesc_buffer[registerIndex + 1];
+	}
+
+	if (length > 2) {
+		cmd->c.opcode = command->opcode;
+		cmd->c.reportTypeID = reportID | reportType << 4;
+	}
+
+	memcpy(cmd->data + length, args, args_len);
+	length += args_len;
+
+	i2c_hid_dbg(ihid, "%s: cmd=%*ph\n", __func__, length, cmd->data);
+
+	msg[0].addr = client->addr;
+	msg[0].flags = client->flags & I2C_M_TEN;
+	msg[0].len = length;
+	msg[0].buf = cmd->data;
+	if (data_len > 0) {
+		msg[1].addr = client->addr;
+		msg[1].flags = client->flags & I2C_M_TEN;
+		msg[1].flags |= I2C_M_RD;
+		msg[1].len = data_len;
+		msg[1].buf = buf_recv;
+		msg_num = 2;
+		set_bit(I2C_HID_READ_PENDING, &ihid->flags);
+	}
+
+	if (wait)
+		set_bit(I2C_HID_RESET_PENDING, &ihid->flags);
+
+	ret = i2c_transfer(client->adapter, msg, msg_num);
+
+	if (data_len > 0)
+		clear_bit(I2C_HID_READ_PENDING, &ihid->flags);
+
+	if (ret != msg_num)
+		return ret < 0 ? ret : -EIO;
+
+	ret = 0;
+
+	if (wait) {
+		i2c_hid_dbg(ihid, "%s: waiting...\n", __func__);
+		if (!wait_event_timeout(ihid->wait,
+				!test_bit(I2C_HID_RESET_PENDING, &ihid->flags),
+				msecs_to_jiffies(5000)))
+			ret = -ENODATA;
+		i2c_hid_dbg(ihid, "%s: finished.\n", __func__);
+	}
+
+	return ret;
+}
+
+static int i2c_hid_command(struct i2c_client *client,
+		const struct i2c_hid_cmd *command,
+		unsigned char *buf_recv, int data_len)
+{
+	return __i2c_hid_command(client, command, 0, 0, NULL, 0,
+				buf_recv, data_len);
+}
+
+static int i2c_hid_get_report(struct i2c_client *client, u8 reportType,
+		u8 reportID, unsigned char *buf_recv, int data_len)
+{
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	u8 args[3];
+	int ret;
+	int args_len = 0;
+	u16 readRegister = le16_to_cpu(ihid->hdesc.wDataRegister);
+
+	i2c_hid_dbg(ihid, "%s\n", __func__);
+
+	if (reportID >= 0x0F) {
+		args[args_len++] = reportID;
+		reportID = 0x0F;
+	}
+
+	args[args_len++] = readRegister & 0xFF;
+	args[args_len++] = readRegister >> 8;
+
+	ret = __i2c_hid_command(client, &hid_get_report_cmd, reportID,
+		reportType, args, args_len, buf_recv, data_len);
+	if (ret) {
+		dev_err(&client->dev,
+			"failed to retrieve report from device.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int i2c_hid_set_report(struct i2c_client *client, u8 reportType,
+		u8 reportID, unsigned char *buf, size_t data_len)
+{
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	u8 *args = ihid->argsbuf;
+	int ret;
+	u16 dataRegister = le16_to_cpu(ihid->hdesc.wDataRegister);
+
+	/* hidraw already checked that data_len < HID_MAX_BUFFER_SIZE */
+	u16 size =	2			/* size */ +
+			(reportID ? 1 : 0)	/* reportID */ +
+			data_len		/* buf */;
+	int args_len =	(reportID >= 0x0F ? 1 : 0) /* optional third byte */ +
+			2			/* dataRegister */ +
+			size			/* args */;
+	int index = 0;
+
+	i2c_hid_dbg(ihid, "%s\n", __func__);
+
+	if (reportID >= 0x0F) {
+		args[index++] = reportID;
+		reportID = 0x0F;
+	}
+
+	args[index++] = dataRegister & 0xFF;
+	args[index++] = dataRegister >> 8;
+
+	args[index++] = size & 0xFF;
+	args[index++] = size >> 8;
+
+	if (reportID)
+		args[index++] = reportID;
+
+	memcpy(&args[index], buf, data_len);
+
+	ret = __i2c_hid_command(client, &hid_set_report_cmd, reportID,
+		reportType, args, args_len, NULL, 0);
+	if (ret) {
+		dev_err(&client->dev, "failed to set a report to device.\n");
+		return -EINVAL;
+	}
+
+	return data_len;
+}
+
+static int i2c_hid_set_power(struct i2c_client *client, int power_state)
+{
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	int ret;
+
+	i2c_hid_dbg(ihid, "%s\n", __func__);
+
+	ret = __i2c_hid_command(client, &hid_set_power_cmd, power_state,
+		0, NULL, 0, NULL, 0);
+	if (ret)
+		dev_err(&client->dev, "failed to change power setting.\n");
+
+	return ret;
+}
+
+static int i2c_hid_hwreset(struct i2c_client *client)
+{
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	int ret;
+
+	i2c_hid_dbg(ihid, "%s\n", __func__);
+
+	ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
+	if (ret)
+		return ret;
+
+	i2c_hid_dbg(ihid, "resetting...\n");
+
+	ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0);
+	if (ret) {
+		dev_err(&client->dev, "failed to reset device.\n");
+		i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int i2c_hid_get_input(struct i2c_hid *ihid)
+{
+	int ret, ret_size;
+	int size = le16_to_cpu(ihid->hdesc.wMaxInputLength);
+
+	ret = i2c_master_recv(ihid->client, ihid->inbuf, size);
+	if (ret != size) {
+		if (ret < 0)
+			return ret;
+
+		dev_err(&ihid->client->dev, "%s: got %d data instead of %d\n",
+			__func__, ret, size);
+		return ret;
+	}
+
+	ret_size = ihid->inbuf[0] | ihid->inbuf[1] << 8;
+
+	if (!ret_size) {
+		/* host or device initiated RESET completed */
+		if (test_and_clear_bit(I2C_HID_RESET_PENDING, &ihid->flags))
+			wake_up(&ihid->wait);
+		return 0;
+	}
+
+	if (ret_size > size) {
+		dev_err(&ihid->client->dev, "%s: incomplete report (%d/%d)\n",
+			__func__, size, ret_size);
+		return -EIO;
+	}
+
+	i2c_hid_dbg(ihid, "input: %*ph\n", ret_size, ihid->inbuf);
+
+	if (test_bit(I2C_HID_STARTED, &ihid->flags))
+		hid_input_report(ihid->hid, HID_INPUT_REPORT, ihid->inbuf + 2,
+				ret_size - 2, 1);
+
+	return 0;
+}
+
+static irqreturn_t i2c_hid_irq(int irq, void *dev_id)
+{
+	struct i2c_hid *ihid = dev_id;
+
+	if (test_bit(I2C_HID_READ_PENDING, &ihid->flags))
+		return IRQ_HANDLED;
+
+	i2c_hid_get_input(ihid);
+
+	return IRQ_HANDLED;
+}
+
+static int i2c_hid_get_report_length(struct hid_report *report)
+{
+	return ((report->size - 1) >> 3) + 1 +
+		report->device->report_enum[report->type].numbered + 2;
+}
+
+static void i2c_hid_init_report(struct hid_report *report, u8 *buffer,
+	size_t bufsize)
+{
+	struct hid_device *hid = report->device;
+	struct i2c_client *client = hid->driver_data;
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	unsigned int size, ret_size;
+
+	size = i2c_hid_get_report_length(report);
+	i2c_hid_get_report(client,
+			report->type == HID_FEATURE_REPORT ? 0x03 : 0x01,
+			report->id, buffer, size);
+
+	i2c_hid_dbg(ihid, "report (len=%d): %*ph\n", size, size, ihid->inbuf);
+
+	ret_size = buffer[0] | (buffer[1] << 8);
+
+	if (ret_size != size) {
+		dev_err(&client->dev, "error in %s size:%d / ret_size:%d\n",
+			__func__, size, ret_size);
+		return;
+	}
+
+	/* hid->driver_lock is held as we are in probe function,
+	 * we just need to setup the input fields, so using
+	 * hid_report_raw_event is safe. */
+	hid_report_raw_event(hid, report->type, buffer + 2, size - 2, 1);
+}
+
+/*
+ * Initialize all reports
+ */
+static void i2c_hid_init_reports(struct hid_device *hid)
+{
+	struct hid_report *report;
+	struct i2c_client *client = hid->driver_data;
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	u8 *inbuf = kzalloc(ihid->bufsize, GFP_KERNEL);
+
+	if (!inbuf)
+		return;
+
+	list_for_each_entry(report,
+		&hid->report_enum[HID_INPUT_REPORT].report_list, list)
+		i2c_hid_init_report(report, inbuf, ihid->bufsize);
+
+	list_for_each_entry(report,
+		&hid->report_enum[HID_FEATURE_REPORT].report_list, list)
+		i2c_hid_init_report(report, inbuf, ihid->bufsize);
+
+	kfree(inbuf);
+}
+
+/*
+ * Traverse the supplied list of reports and find the longest
+ */
+static void i2c_hid_find_max_report(struct hid_device *hid, unsigned int type,
+		unsigned int *max)
+{
+	struct hid_report *report;
+	unsigned int size;
+
+	/* We should not rely on wMaxInputLength, as some devices may set it to
+	 * a wrong length. */
+	list_for_each_entry(report, &hid->report_enum[type].report_list, list) {
+		size = i2c_hid_get_report_length(report);
+		if (*max < size)
+			*max = size;
+	}
+}
+
+static int i2c_hid_alloc_buffers(struct i2c_hid *ihid)
+{
+	/* the worst case is computed from the set_report command with a
+	 * reportID > 15 and the maximum report length */
+	int args_len = sizeof(__u8) + /* optional ReportID byte */
+		       sizeof(__u16) + /* data register */
+		       sizeof(__u16) + /* size of the report */
+		       ihid->bufsize; /* report */
+
+	ihid->inbuf = kzalloc(ihid->bufsize, GFP_KERNEL);
+
+	if (!ihid->inbuf)
+		return -ENOMEM;
+
+	ihid->argsbuf = kzalloc(args_len, GFP_KERNEL);
+
+	if (!ihid->argsbuf) {
+		kfree(ihid->inbuf);
+		return -ENOMEM;
+	}
+
+	ihid->cmdbuf = kzalloc(sizeof(union command) + args_len, GFP_KERNEL);
+
+	if (!ihid->cmdbuf) {
+		kfree(ihid->inbuf);
+		kfree(ihid->argsbuf);
+		ihid->inbuf = NULL;
+		ihid->argsbuf = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void i2c_hid_free_buffers(struct i2c_hid *ihid)
+{
+	kfree(ihid->inbuf);
+	kfree(ihid->argsbuf);
+	kfree(ihid->cmdbuf);
+	ihid->inbuf = NULL;
+	ihid->cmdbuf = NULL;
+	ihid->argsbuf = NULL;
+}
+
+static int i2c_hid_get_raw_report(struct hid_device *hid,
+		unsigned char report_number, __u8 *buf, size_t count,
+		unsigned char report_type)
+{
+	struct i2c_client *client = hid->driver_data;
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	int ret;
+
+	if (report_type == HID_OUTPUT_REPORT)
+		return -EINVAL;
+
+	if (count > ihid->bufsize)
+		count = ihid->bufsize;
+
+	ret = i2c_hid_get_report(client,
+			report_type == HID_FEATURE_REPORT ? 0x03 : 0x01,
+			report_number, ihid->inbuf, count);
+
+	if (ret < 0)
+		return ret;
+
+	count = ihid->inbuf[0] | (ihid->inbuf[1] << 8);
+
+	memcpy(buf, ihid->inbuf + 2, count);
+
+	return count;
+}
+
+static int i2c_hid_output_raw_report(struct hid_device *hid, __u8 *buf,
+		size_t count, unsigned char report_type)
+{
+	struct i2c_client *client = hid->driver_data;
+	int report_id = buf[0];
+
+	if (report_type == HID_INPUT_REPORT)
+		return -EINVAL;
+
+	return i2c_hid_set_report(client,
+				report_type == HID_FEATURE_REPORT ? 0x03 : 0x02,
+				report_id, buf, count);
+}
+
+static int i2c_hid_parse(struct hid_device *hid)
+{
+	struct i2c_client *client = hid->driver_data;
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	struct i2c_hid_desc *hdesc = &ihid->hdesc;
+	unsigned int rsize;
+	char *rdesc;
+	int ret;
+	int tries = 3;
+
+	i2c_hid_dbg(ihid, "entering %s\n", __func__);
+
+	rsize = le16_to_cpu(hdesc->wReportDescLength);
+	if (!rsize || rsize > HID_MAX_DESCRIPTOR_SIZE) {
+		dbg_hid("weird size of report descriptor (%u)\n", rsize);
+		return -EINVAL;
+	}
+
+	do {
+		ret = i2c_hid_hwreset(client);
+		if (ret)
+			msleep(1000);
+	} while (tries-- > 0 && ret);
+
+	if (ret)
+		return ret;
+
+	rdesc = kzalloc(rsize, GFP_KERNEL);
+
+	if (!rdesc) {
+		dbg_hid("couldn't allocate rdesc memory\n");
+		return -ENOMEM;
+	}
+
+	i2c_hid_dbg(ihid, "asking HID report descriptor\n");
+
+	ret = i2c_hid_command(client, &hid_report_descr_cmd, rdesc, rsize);
+	if (ret) {
+		hid_err(hid, "reading report descriptor failed\n");
+		kfree(rdesc);
+		return -EIO;
+	}
+
+	i2c_hid_dbg(ihid, "Report Descriptor: %*ph\n", rsize, rdesc);
+
+	ret = hid_parse_report(hid, rdesc, rsize);
+	kfree(rdesc);
+	if (ret) {
+		dbg_hid("parsing report descriptor failed\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int i2c_hid_start(struct hid_device *hid)
+{
+	struct i2c_client *client = hid->driver_data;
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	int ret;
+	int old_bufsize = ihid->bufsize;
+
+	ihid->bufsize = HID_MIN_BUFFER_SIZE;
+	i2c_hid_find_max_report(hid, HID_INPUT_REPORT, &ihid->bufsize);
+	i2c_hid_find_max_report(hid, HID_OUTPUT_REPORT, &ihid->bufsize);
+	i2c_hid_find_max_report(hid, HID_FEATURE_REPORT, &ihid->bufsize);
+
+	if (ihid->bufsize > old_bufsize || !ihid->inbuf || !ihid->cmdbuf) {
+		i2c_hid_free_buffers(ihid);
+
+		ret = i2c_hid_alloc_buffers(ihid);
+
+		if (ret) {
+			ihid->bufsize = old_bufsize;
+			return ret;
+		}
+	}
+
+	if (!(hid->quirks & HID_QUIRK_NO_INIT_REPORTS))
+		i2c_hid_init_reports(hid);
+
+	return 0;
+}
+
+static void i2c_hid_stop(struct hid_device *hid)
+{
+	struct i2c_client *client = hid->driver_data;
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+
+	hid->claimed = 0;
+
+	i2c_hid_free_buffers(ihid);
+}
+
+static int i2c_hid_open(struct hid_device *hid)
+{
+	struct i2c_client *client = hid->driver_data;
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	int ret;
+
+	if (!hid->open++) {
+		ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
+		if (ret) {
+			hid->open--;
+			return -EIO;
+		}
+		set_bit(I2C_HID_STARTED, &ihid->flags);
+	}
+	return 0;
+}
+
+static void i2c_hid_close(struct hid_device *hid)
+{
+	struct i2c_client *client = hid->driver_data;
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+
+	/* protecting hid->open to make sure we don't restart
+	 * data acquistion due to a resumption we no longer
+	 * care about
+	 */
+	if (!--hid->open) {
+		clear_bit(I2C_HID_STARTED, &ihid->flags);
+
+		/* Save some power */
+		i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
+	}
+}
+
+static int i2c_hid_power(struct hid_device *hid, int lvl)
+{
+	struct i2c_client *client = hid->driver_data;
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	int ret = 0;
+
+	i2c_hid_dbg(ihid, "%s lvl:%d\n", __func__, lvl);
+
+	switch (lvl) {
+	case PM_HINT_FULLON:
+		ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
+		break;
+	case PM_HINT_NORMAL:
+		ret = i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
+		break;
+	}
+	return ret;
+}
+
+static int i2c_hid_hidinput_input_event(struct input_dev *dev,
+		unsigned int type, unsigned int code, int value)
+{
+	struct hid_device *hid = input_get_drvdata(dev);
+	struct hid_field *field;
+	int offset;
+
+	if (type == EV_FF)
+		return input_ff_event(dev, type, code, value);
+
+	if (type != EV_LED)
+		return -1;
+
+	offset = hidinput_find_field(hid, type, code, &field);
+
+	if (offset == -1) {
+		hid_warn(dev, "event field not found\n");
+		return -1;
+	}
+
+	hid_set_field(field, offset, value);
+
+	return 0;
+}
+
+static struct hid_ll_driver i2c_hid_ll_driver = {
+	.parse = i2c_hid_parse,
+	.start = i2c_hid_start,
+	.stop = i2c_hid_stop,
+	.open = i2c_hid_open,
+	.close = i2c_hid_close,
+	.power = i2c_hid_power,
+	.hidinput_input_event = i2c_hid_hidinput_input_event,
+};
+
+static int __devinit i2c_hid_init_irq(struct i2c_client *client)
+{
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	int ret;
+
+	dev_dbg(&client->dev, "Requesting IRQ: %d\n", client->irq);
+
+	ret = request_threaded_irq(client->irq, NULL, i2c_hid_irq,
+			IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+			client->name, ihid);
+	if (ret < 0) {
+		dev_dbg(&client->dev,
+			"Could not register for %s interrupt, irq = %d,"
+			" ret = %d\n",
+		client->name, client->irq, ret);
+
+		return ret;
+	}
+
+	ihid->irq = client->irq;
+
+	return 0;
+}
+
+static int __devinit i2c_hid_fetch_hid_descriptor(struct i2c_hid *ihid)
+{
+	struct i2c_client *client = ihid->client;
+	struct i2c_hid_desc *hdesc = &ihid->hdesc;
+	unsigned int dsize;
+	int ret;
+
+	/* Fetch the length of HID description, retrieve the 4 first bytes:
+	 * bytes 0-1 -> length
+	 * bytes 2-3 -> bcdVersion (has to be 1.00) */
+	ret = i2c_hid_command(client, &hid_descr_cmd, ihid->hdesc_buffer, 4);
+
+	i2c_hid_dbg(ihid, "%s, ihid->hdesc_buffer: %*ph\n",
+			__func__, 4, ihid->hdesc_buffer);
+
+	if (ret) {
+		dev_err(&client->dev, "HID_DESCR_LENGTH_CMD Fail (ret=%d)\n",
+			ret);
+		return -ENODEV;
+	}
+
+	dsize = le16_to_cpu(hdesc->wHIDDescLength);
+	if (!dsize || dsize > HID_MAX_DESCRIPTOR_SIZE) {
+		dev_err(&client->dev, "weird size of HID descriptor (%u)\n",
+			dsize);
+		return -ENODEV;
+	}
+
+	/* check bcdVersion == 1.0 */
+	if (le16_to_cpu(hdesc->bcdVersion) != 0x0100) {
+		dev_err(&client->dev,
+			"unexpected HID descriptor bcdVersion (0x%04x)\n",
+			le16_to_cpu(hdesc->bcdVersion));
+		return -ENODEV;
+	}
+
+	i2c_hid_dbg(ihid, "Fetching the HID descriptor\n");
+
+	ret = i2c_hid_command(client, &hid_descr_cmd, ihid->hdesc_buffer,
+				dsize);
+	if (ret) {
+		dev_err(&client->dev, "hid_descr_cmd Fail\n");
+		return -ENODEV;
+	}
+
+	i2c_hid_dbg(ihid, "HID Descriptor: %*ph\n", dsize, ihid->hdesc_buffer);
+
+	return 0;
+}
+
+static int __devinit i2c_hid_probe(struct i2c_client *client,
+		const struct i2c_device_id *dev_id)
+{
+	int ret;
+	struct i2c_hid *ihid;
+	struct hid_device *hid;
+	__u16 hidRegister;
+	struct i2c_hid_platform_data *platform_data = client->dev.platform_data;
+
+	dbg_hid("HID probe called for i2c 0x%02x\n", client->addr);
+
+	if (!platform_data) {
+		dev_err(&client->dev, "HID register address not provided\n");
+		return -EINVAL;
+	}
+
+	if (!client->irq) {
+		dev_err(&client->dev,
+			"HID over i2c has not been provided an Int IRQ\n");
+		return -EINVAL;
+	}
+
+	ihid = kzalloc(sizeof(struct i2c_hid), GFP_KERNEL);
+	if (!ihid)
+		return -ENOMEM;
+
+	i2c_set_clientdata(client, ihid);
+
+	ihid->client = client;
+
+	hidRegister = platform_data->hid_descriptor_address;
+	ihid->wHIDDescRegister = cpu_to_le16(hidRegister);
+
+	init_waitqueue_head(&ihid->wait);
+
+	/* we need to allocate the command buffer without knowing the maximum
+	 * size of the reports. Let's use HID_MIN_BUFFER_SIZE, then we do the
+	 * real computation later. */
+	ihid->bufsize = HID_MIN_BUFFER_SIZE;
+	i2c_hid_alloc_buffers(ihid);
+
+	ret = i2c_hid_fetch_hid_descriptor(ihid);
+	if (ret < 0)
+		goto err;
+
+	ret = i2c_hid_init_irq(client);
+	if (ret < 0)
+		goto err;
+
+	hid = hid_allocate_device();
+	if (IS_ERR(hid)) {
+		ret = PTR_ERR(hid);
+		goto err;
+	}
+
+	ihid->hid = hid;
+
+	hid->driver_data = client;
+	hid->ll_driver = &i2c_hid_ll_driver;
+	hid->hid_get_raw_report = i2c_hid_get_raw_report;
+	hid->hid_output_raw_report = i2c_hid_output_raw_report;
+	hid->dev.parent = &client->dev;
+	hid->bus = BUS_I2C;
+	hid->version = le16_to_cpu(ihid->hdesc.bcdVersion);
+	hid->vendor = le16_to_cpu(ihid->hdesc.wVendorID);
+	hid->product = le16_to_cpu(ihid->hdesc.wProductID);
+
+	snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X",
+		 client->name, hid->vendor, hid->product);
+
+	ret = hid_add_device(hid);
+	if (ret) {
+		if (ret != -ENODEV)
+			hid_err(client, "can't add hid device: %d\n", ret);
+		goto err_mem_free;
+	}
+
+	return 0;
+
+err_mem_free:
+	hid_destroy_device(hid);
+
+err:
+	if (ihid->irq)
+		free_irq(ihid->irq, ihid);
+
+	kfree(ihid);
+	return ret;
+}
+
+static int __devexit i2c_hid_remove(struct i2c_client *client)
+{
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+	struct hid_device *hid;
+
+	if (WARN_ON(!ihid))
+		return -1;
+
+	hid = ihid->hid;
+	hid_destroy_device(hid);
+
+	free_irq(client->irq, ihid);
+
+	kfree(ihid);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int i2c_hid_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct i2c_hid *ihid = i2c_get_clientdata(client);
+
+	if (device_may_wakeup(&client->dev))
+		enable_irq_wake(ihid->irq);
+
+	/* Save some power */
+	i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
+
+	return 0;
+}
+
+static int i2c_hid_resume(struct device *dev)
+{
+	int ret;
+	struct i2c_client *client = to_i2c_client(dev);
+
+	ret = i2c_hid_hwreset(client);
+	if (ret)
+		return ret;
+
+	if (device_may_wakeup(&client->dev))
+		disable_irq_wake(client->irq);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(i2c_hid_pm, i2c_hid_suspend, i2c_hid_resume);
+
+static const struct i2c_device_id i2c_hid_id_table[] = {
+	{ "i2c_hid", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(i2c, i2c_hid_id_table);
+
+
+static struct i2c_driver i2c_hid_driver = {
+	.driver = {
+		.name	= "i2c_hid",
+		.owner	= THIS_MODULE,
+		.pm	= &i2c_hid_pm,
+	},
+
+	.probe		= i2c_hid_probe,
+	.remove		= __devexit_p(i2c_hid_remove),
+
+	.id_table	= i2c_hid_id_table,
+};
+
+module_i2c_driver(i2c_hid_driver);
+
+MODULE_DESCRIPTION("HID over I2C core driver");
+MODULE_AUTHOR("Benjamin Tissoires <benjamin.tissoires@gmail.com>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/i2c/i2c-hid.h b/include/linux/i2c/i2c-hid.h
new file mode 100644
index 000000000000..60e411d764d4
--- /dev/null
+++ b/include/linux/i2c/i2c-hid.h
@@ -0,0 +1,35 @@
+/*
+ * HID over I2C protocol implementation
+ *
+ * Copyright (c) 2012 Benjamin Tissoires <benjamin.tissoires@gmail.com>
+ * Copyright (c) 2012 Ecole Nationale de l'Aviation Civile, France
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive for
+ * more details.
+ */
+
+#ifndef __LINUX_I2C_HID_H
+#define __LINUX_I2C_HID_H
+
+#include <linux/types.h>
+
+/**
+ * struct i2chid_platform_data - used by hid over i2c implementation.
+ * @hid_descriptor_address: i2c register where the HID descriptor is stored.
+ *
+ * Note that it is the responsibility of the platform driver (or the acpi 5.0
+ * driver) to setup the irq related to the gpio in the struct i2c_board_info.
+ * The platform driver should also setup the gpio according to the device:
+ *
+ * A typical example is the following:
+ *	irq = gpio_to_irq(intr_gpio);
+ *	hkdk4412_i2c_devs5[0].irq = irq; // store the irq in i2c_board_info
+ *	gpio_request(intr_gpio, "elan-irq");
+ *	s3c_gpio_setpull(intr_gpio, S3C_GPIO_PULL_UP);
+ */
+struct i2c_hid_platform_data {
+	u16 hid_descriptor_address;
+};
+
+#endif /* __LINUX_I2C_HID_H */
-- 
cgit v1.2.3-55-g7522


From 02582e9bcc36ed503ffede46e104a885dea222fb Mon Sep 17 00:00:00 2001
From: Masanari Iida
Date: Wed, 22 Aug 2012 19:11:26 +0900
Subject: treewide: fix typo of "suport" in various comments and Kconfig

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 Documentation/hwmon/pmbus                      | 2 +-
 Documentation/video4linux/bttv/Sound-FAQ       | 2 +-
 arch/mips/txx9/generic/pci.c                   | 2 +-
 arch/powerpc/include/asm/oprofile_impl.h       | 2 +-
 arch/sh/boards/board-espt.c                    | 2 +-
 drivers/acpi/acpica/dsopcode.c                 | 2 +-
 drivers/net/bonding/bonding.h                  | 2 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c | 2 +-
 drivers/net/ethernet/micrel/ksz884x.c          | 2 +-
 drivers/net/wireless/atmel.c                   | 2 +-
 drivers/net/wireless/ipw2x00/ipw2100.h         | 2 +-
 drivers/regulator/palmas-regulator.c           | 2 +-
 drivers/scsi/libsas/sas_expander.c             | 2 +-
 drivers/staging/comedi/drivers/usbdux.c        | 2 +-
 drivers/staging/csr/netdev.c                   | 2 +-
 drivers/staging/tidspbridge/rmgr/node.c        | 2 +-
 drivers/usb/core/driver.c                      | 2 +-
 fs/cifs/README                                 | 2 +-
 fs/notify/fanotify/Kconfig                     | 2 +-
 include/linux/stmmac.h                         | 2 +-
 net/ipv4/tcp_cong.c                            | 2 +-
 net/mac80211/driver-ops.h                      | 2 +-
 net/sctp/endpointola.c                         | 2 +-
 net/sctp/sm_statefuns.c                        | 2 +-
 sound/pci/ice1712/delta.c                      | 2 +-
 25 files changed, 25 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/Documentation/hwmon/pmbus b/Documentation/hwmon/pmbus
index f90f99920cc5..3d3a0f97f966 100644
--- a/Documentation/hwmon/pmbus
+++ b/Documentation/hwmon/pmbus
@@ -138,7 +138,7 @@ Sysfs entries
 
 When probing the chip, the driver identifies which PMBus registers are
 supported, and determines available sensors from this information.
-Attribute files only exist if respective sensors are suported by the chip.
+Attribute files only exist if respective sensors are supported by the chip.
 Labels are provided to inform the user about the sensor associated with
 a given sysfs entry.
 
diff --git a/Documentation/video4linux/bttv/Sound-FAQ b/Documentation/video4linux/bttv/Sound-FAQ
index 395f6c6fdd98..d3f1d7783d1c 100644
--- a/Documentation/video4linux/bttv/Sound-FAQ
+++ b/Documentation/video4linux/bttv/Sound-FAQ
@@ -82,7 +82,7 @@ card installed, you might to check out if you can read these registers
 values used by the windows driver.  A tool to do this is available
 from ftp://telepresence.dmem.strath.ac.uk/pub/bt848/winutil, but it
 does'nt work with bt878 boards according to some reports I received.
-Another one with bt878 suport is available from
+Another one with bt878 support is available from
 http://btwincap.sourceforge.net/Files/btspy2.00.zip
 
 You might also dig around in the *.ini files of the Windows applications.
diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c
index 4efd9185f294..b14ee53581a9 100644
--- a/arch/mips/txx9/generic/pci.c
+++ b/arch/mips/txx9/generic/pci.c
@@ -341,7 +341,7 @@ static void __devinit quirk_slc90e66_ide(struct pci_dev *dev)
 
 static void __devinit tc35815_fixup(struct pci_dev *dev)
 {
-	/* This device may have PM registers but not they are not suported. */
+	/* This device may have PM registers but not they are not supported. */
 	if (dev->pm_cap) {
 		dev_info(&dev->dev, "PM disabled\n");
 		dev->pm_cap = 0;
diff --git a/arch/powerpc/include/asm/oprofile_impl.h b/arch/powerpc/include/asm/oprofile_impl.h
index 639dc96077ab..d697b08994c9 100644
--- a/arch/powerpc/include/asm/oprofile_impl.h
+++ b/arch/powerpc/include/asm/oprofile_impl.h
@@ -34,7 +34,7 @@ struct op_system_config {
 	unsigned long mmcra;
 #ifdef CONFIG_OPROFILE_CELL
 	/* Register for oprofile user tool to check cell kernel profiling
-	 * suport.
+	 * support.
 	 */
 	unsigned long cell_support;
 #endif
diff --git a/arch/sh/boards/board-espt.c b/arch/sh/boards/board-espt.c
index 6cba0a7068bc..d71a0bcf8145 100644
--- a/arch/sh/boards/board-espt.c
+++ b/arch/sh/boards/board-espt.c
@@ -1,5 +1,5 @@
 /*
- * Data Technology Inc. ESPT-GIGA board suport
+ * Data Technology Inc. ESPT-GIGA board support
  *
  * Copyright (C) 2008, 2009 Renesas Solutions Corp.
  * Copyright (C) 2008, 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c
index aa34d8984d34..4fbb45fadb1e 100644
--- a/drivers/acpi/acpica/dsopcode.c
+++ b/drivers/acpi/acpica/dsopcode.c
@@ -1,6 +1,6 @@
 /******************************************************************************
  *
- * Module Name: dsopcode - Dispatcher suport for regions and fields
+ * Module Name: dsopcode - Dispatcher support for regions and fields
  *
  *****************************************************************************/
 
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index f8af2fcd3d16..486b1cbd8da8 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -244,7 +244,7 @@ struct bonding {
 	struct   delayed_work ad_work;
 	struct   delayed_work mcast_work;
 #ifdef CONFIG_DEBUG_FS
-	/* debugging suport via debugfs */
+	/* debugging support via debugfs */
 	struct	 dentry *debug_dir;
 #endif /* CONFIG_DEBUG_FS */
 };
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 614981c02264..a4fb5c0207be 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -4318,7 +4318,7 @@ static int bnx2x_queue_comp_cmd(struct bnx2x *bp,
 
 	if (o->next_tx_only >= o->max_cos)
 		/* >= becuase tx only must always be smaller than cos since the
-		 * primary connection suports COS 0
+		 * primary connection supports COS 0
 		 */
 		BNX2X_ERR("illegal value for next tx_only: %d. max cos was %d",
 			   o->next_tx_only, o->max_cos);
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index 318fee91c79d..693a88dddb48 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -6767,7 +6767,7 @@ static int stp;
 /*
  * This enables fast aging in the KSZ8842 switch.  Not sure what situation
  * needs that.  However, fast aging is used to flush the dynamic MAC table when
- * STP suport is enabled.
+ * STP support is enabled.
  */
 static int fast_aging;
 
diff --git a/drivers/net/wireless/atmel.c b/drivers/net/wireless/atmel.c
index 4a4e98f71807..4374079dfc2a 100644
--- a/drivers/net/wireless/atmel.c
+++ b/drivers/net/wireless/atmel.c
@@ -2963,7 +2963,7 @@ static void send_association_request(struct atmel_private *priv, int is_reassoc)
 	ssid_el_p[1] = priv->SSID_size;
 	memcpy(ssid_el_p + 2, priv->SSID, priv->SSID_size);
 	ssid_el_p[2 + priv->SSID_size] = WLAN_EID_SUPP_RATES;
-	ssid_el_p[3 + priv->SSID_size] = 4; /* len of suported rates */
+	ssid_el_p[3 + priv->SSID_size] = 4; /* len of supported rates */
 	memcpy(ssid_el_p + 4 + priv->SSID_size, atmel_basic_rates, 4);
 
 	atmel_transmit_management_frame(priv, &header, (void *)&body, bodysize);
diff --git a/drivers/net/wireless/ipw2x00/ipw2100.h b/drivers/net/wireless/ipw2x00/ipw2100.h
index 973125242490..5fe17cbab1f3 100644
--- a/drivers/net/wireless/ipw2x00/ipw2100.h
+++ b/drivers/net/wireless/ipw2x00/ipw2100.h
@@ -1045,7 +1045,7 @@ typedef enum _ORDINAL_TABLE_1 {	// NS - means Not Supported by FW
 	IPW_ORD_POWER_MGMT_MODE,	// Power mode - 0=CAM, 1=PSP
 	IPW_ORD_POWER_MGMT_INDEX,	//NS //
 	IPW_ORD_COUNTRY_CODE,	// IEEE country code as recv'd from beacon
-	IPW_ORD_COUNTRY_CHANNELS,	// channels suported by country
+	IPW_ORD_COUNTRY_CHANNELS,	// channels supported by country
 // IPW_ORD_COUNTRY_CHANNELS:
 // For 11b the lower 2-byte are used for channels from 1-14
 //   and the higher 2-byte are not used.
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index 07aee694ba92..08fec06dba50 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -773,7 +773,7 @@ static __devinit int palmas_probe(struct platform_device *pdev)
 		/*
 		 * read and store the RANGE bit for later use
 		 * This must be done before regulator is probed otherwise
-		 * we error in probe with unsuportable ranges.
+		 * we error in probe with unsupportable ranges.
 		 */
 		if (id != PALMAS_REG_SMPS10) {
 			addr = palmas_regs_info[id].vsel_addr;
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index efc6e72f09f3..aec2e0da5016 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -1800,7 +1800,7 @@ out:
  * @dev:domain device to be detect.
  * @src_dev: the device which originated BROADCAST(CHANGE).
  *
- * Add self-configuration expander suport. Suppose two expander cascading,
+ * Add self-configuration expander support. Suppose two expander cascading,
  * when the first level expander is self-configuring, hotplug the disks in
  * second level expander, BROADCAST(CHANGE) will not only be originated
  * in the second level expander, but also be originated in the first level
diff --git a/drivers/staging/comedi/drivers/usbdux.c b/drivers/staging/comedi/drivers/usbdux.c
index b536bba74351..c484a7352940 100644
--- a/drivers/staging/comedi/drivers/usbdux.c
+++ b/drivers/staging/comedi/drivers/usbdux.c
@@ -73,7 +73,7 @@ sampling rate. If you sample two channels you get 4kHz and so on.
  *       And loads of cleaning up, in particular streamlining the
  *       bulk transfers.
  * 1.1:  moved EP4 transfers to EP1 to make space for a PWM output on EP4
- * 1.2:  added PWM suport via EP4
+ * 1.2:  added PWM support via EP4
  * 2.0:  PWM seems to be stable and is not interfering with the other functions
  * 2.1:  changed PWM API
  * 2.2:  added firmware kernel request to fix an udev problem
diff --git a/drivers/staging/csr/netdev.c b/drivers/staging/csr/netdev.c
index 9a52ab408e1a..fc43cc22629c 100644
--- a/drivers/staging/csr/netdev.c
+++ b/drivers/staging/csr/netdev.c
@@ -55,7 +55,7 @@
 #include <net/pkt_sched.h>
 
 
-/* Wext handler is suported only if CSR_SUPPORT_WEXT is defined */
+/* Wext handler is supported only if CSR_SUPPORT_WEXT is defined */
 #ifdef CSR_SUPPORT_WEXT
 extern struct iw_handler_def unifi_iw_handler_def;
 #endif /* CSR_SUPPORT_WEXT */
diff --git a/drivers/staging/tidspbridge/rmgr/node.c b/drivers/staging/tidspbridge/rmgr/node.c
index 294e9b40f516..737f4a9d86a3 100644
--- a/drivers/staging/tidspbridge/rmgr/node.c
+++ b/drivers/staging/tidspbridge/rmgr/node.c
@@ -736,7 +736,7 @@ DBAPI node_alloc_msg_buf(struct node_object *hnode, u32 usize,
 		case 4:
 			break;
 		default:
-			/* alignment value not suportted */
+			/* alignment value not supportted */
 			status = -EPERM;
 			break;
 		}
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 6056db7af410..263c5035eabf 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -238,7 +238,7 @@ static int usb_probe_device(struct device *dev)
 	/* TODO: Add real matching code */
 
 	/* The device should always appear to be in use
-	 * unless the driver suports autosuspend.
+	 * unless the driver supports autosuspend.
 	 */
 	if (!udriver->supports_autosuspend)
 		error = usb_autoresume_device(udev);
diff --git a/fs/cifs/README b/fs/cifs/README
index 22ab7b5b8da7..2d5622f60e11 100644
--- a/fs/cifs/README
+++ b/fs/cifs/README
@@ -480,7 +480,7 @@ A partial list of the supported mount options follows:
 		Unicode on the wire.
  nomapchars     Do not translate any of these seven characters (default).
  nocase         Request case insensitive path name matching (case
-		sensitive is the default if the server suports it).
+		sensitive is the default if the server supports it).
 		(mount option "ignorecase" is identical to "nocase")
  posixpaths     If CIFS Unix extensions are supported, attempt to
 		negotiate posix path name support which allows certain
diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig
index 7dceff005a67..e5f911bd80d2 100644
--- a/fs/notify/fanotify/Kconfig
+++ b/fs/notify/fanotify/Kconfig
@@ -4,7 +4,7 @@ config FANOTIFY
 	select ANON_INODES
 	default n
 	---help---
-	   Say Y here to enable fanotify suport.  fanotify is a file access
+	   Say Y here to enable fanotify support.  fanotify is a file access
 	   notification system which differs from inotify in that it sends
 	   an open file descriptor to the userspace listener along with
 	   the event.
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index a1547ea3920d..a619f7025cc9 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -61,7 +61,7 @@
 #define STMMAC_CSR_I_16		0xE	/* clk_csr_i/16 */
 #define STMMAC_CSR_I_18		0xF	/* clk_csr_i/18 */
 
-/* AXI DMA Burst length suported */
+/* AXI DMA Burst length supported */
 #define DMA_AXI_BLEN_4		(1 << 1)
 #define DMA_AXI_BLEN_8		(1 << 2)
 #define DMA_AXI_BLEN_16		(1 << 3)
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 1432cdb0644c..701a7f6fb9b1 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -1,7 +1,7 @@
 /*
  * Plugable TCP congestion control support and newReno
  * congestion control.
- * Based on ideas from I/O scheduler suport and Web100.
+ * Based on ideas from I/O scheduler support and Web100.
  *
  * Copyright (C) 2005 Stephen Hemminger <shemminger@osdl.org>
  */
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index da9003b20004..f28772443bd3 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -602,7 +602,7 @@ static inline void drv_reset_tsf(struct ieee80211_local *local,
 
 static inline int drv_tx_last_beacon(struct ieee80211_local *local)
 {
-	int ret = 0; /* default unsuported op for less congestion */
+	int ret = 0; /* default unsupported op for less congestion */
 
 	might_sleep();
 
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 1859e2bc83d1..bd7e6a6a815a 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -163,7 +163,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 
 	list_add(&null_key->key_list, &ep->endpoint_shared_keys);
 
-	/* Allocate and initialize transorms arrays for suported HMACs. */
+	/* Allocate and initialize transorms arrays for supported HMACs. */
 	err = sctp_auth_init_hmacs(ep, gfp);
 	if (err)
 		goto nomem_hmacs;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index b6adef8a1e93..49493f335861 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3994,7 +3994,7 @@ static sctp_ierror_t sctp_sf_authenticate(struct net *net,
 	chunk->subh.auth_hdr = auth_hdr;
 	skb_pull(chunk->skb, sizeof(struct sctp_authhdr));
 
-	/* Make sure that we suport the HMAC algorithm from the auth
+	/* Make sure that we support the HMAC algorithm from the auth
 	 * chunk.
 	 */
 	if (!sctp_auth_asoc_verify_hmac_id(asoc, auth_hdr->hmac_id))
diff --git a/sound/pci/ice1712/delta.c b/sound/pci/ice1712/delta.c
index 20c6b079d0df..d09239cf7961 100644
--- a/sound/pci/ice1712/delta.c
+++ b/sound/pci/ice1712/delta.c
@@ -617,7 +617,7 @@ static int __devinit snd_ice1712_delta_init(struct snd_ice1712 *ice)
 		ice->num_total_dacs = 4;	/* two AK4324 codecs */
 		break;
 	case ICE1712_SUBDEVICE_VX442:
-	case ICE1712_SUBDEVICE_DELTA66E:	/* omni not suported yet */
+	case ICE1712_SUBDEVICE_DELTA66E:	/* omni not supported yet */
 		ice->num_total_dacs = 4;
 		ice->num_total_adcs = 4;
 		break;
-- 
cgit v1.2.3-55-g7522


From d93cf0687c9853bf91b1b9a5124ab97ebc47e00c Mon Sep 17 00:00:00 2001
From: Adam Buchbinder
Date: Wed, 19 Sep 2012 21:47:58 -0400
Subject: various: Fix spelling of "registered" in comments.

Some comments misspell "registered"; this fixes them. No code changes.

Signed-off-by: Adam Buchbinder <adam.buchbinder@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 arch/cris/include/arch-v10/arch/irq.h | 2 +-
 arch/cris/include/arch-v32/arch/irq.h | 2 +-
 include/linux/netdevice.h             | 2 +-
 include/net/irda/irlmp.h              | 2 +-
 net/netfilter/nf_log.c                | 2 +-
 sound/core/seq/seq_device.c           | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/cris/include/arch-v10/arch/irq.h b/arch/cris/include/arch-v10/arch/irq.h
index 7d345947b3ee..ca2675ae08ed 100644
--- a/arch/cris/include/arch-v10/arch/irq.h
+++ b/arch/cris/include/arch-v10/arch/irq.h
@@ -142,7 +142,7 @@ __asm__ ( \
  * it here, we would not get the multiple_irq at all.
  *
  * The non-blocking here is based on the knowledge that the timer interrupt is 
- * registred as a fast interrupt (IRQF_DISABLED) so that we _know_ there will not
+ * registered as a fast interrupt (IRQF_DISABLED) so that we _know_ there will not
  * be an sti() before the timer irq handler is run to acknowledge the interrupt.
  */
 
diff --git a/arch/cris/include/arch-v32/arch/irq.h b/arch/cris/include/arch-v32/arch/irq.h
index b31e9984f849..fe3cdd22bed4 100644
--- a/arch/cris/include/arch-v32/arch/irq.h
+++ b/arch/cris/include/arch-v32/arch/irq.h
@@ -103,7 +103,7 @@ __asm__ (				\
  * if we had BLOCK'edit here, we would not get the multiple_irq at all.
  *
  * The non-blocking here is based on the knowledge that the timer interrupt is
- * registred as a fast interrupt (IRQF_DISABLED) so that we _know_ there will not
+ * registered as a fast interrupt (IRQF_DISABLED) so that we _know_ there will not
  * be an sti() before the timer irq handler is run to acknowledge the interrupt.
  */
 #define BUILD_TIMER_IRQ(nr, mask) 	\
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f8eda0276f03..b2056e6e2acc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -369,7 +369,7 @@ typedef enum gro_result gro_result_t;
  *
  * If the rx_handler consider the skb should be ignored, it should return
  * RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that
- * are registred on exact device (ptype->dev == skb->dev).
+ * are registered on exact device (ptype->dev == skb->dev).
  *
  * If the rx_handler didn't changed skb->dev, but want the skb to be normally
  * delivered, it should return RX_HANDLER_PASS.
diff --git a/include/net/irda/irlmp.h b/include/net/irda/irlmp.h
index fff11b7fe8a4..591f78631f13 100644
--- a/include/net/irda/irlmp.h
+++ b/include/net/irda/irlmp.h
@@ -134,7 +134,7 @@ typedef struct {
 } CACHE_ENTRY;
 
 /*
- *  Information about each registred IrLAP layer
+ *  Information about each registered IrLAP layer
  */
 struct lap_cb {
 	irda_queue_t queue; /* Must be first */
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 703fb26aa48d..9e312695c818 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -32,7 +32,7 @@ static struct nf_logger *__find_logger(int pf, const char *str_logger)
 	return NULL;
 }
 
-/* return EEXIST if the same logger is registred, 0 on success. */
+/* return EEXIST if the same logger is registered, 0 on success. */
 int nf_log_register(u_int8_t pf, struct nf_logger *logger)
 {
 	const struct nf_logger *llog;
diff --git a/sound/core/seq/seq_device.c b/sound/core/seq/seq_device.c
index 60e8fc1b3440..040c60e1da28 100644
--- a/sound/core/seq/seq_device.c
+++ b/sound/core/seq/seq_device.c
@@ -66,7 +66,7 @@ struct ops_list {
 	/* operators */
 	struct snd_seq_dev_ops ops;
 
-	/* registred devices */
+	/* registered devices */
 	struct list_head dev_list;	/* list of devices */
 	int num_devices;	/* number of associated devices */
 	int num_init_devices;	/* number of initialized devices */
-- 
cgit v1.2.3-55-g7522


From 48fc7f7e787dd65ffe88521bce31f4062ba273eb Mon Sep 17 00:00:00 2001
From: Adam Buchbinder
Date: Wed, 19 Sep 2012 21:48:00 -0400
Subject: Fix misspellings of "whether" in comments.

"Whether" is misspelled in various comments across the tree; this
fixes them. No code changes.

Signed-off-by: Adam Buchbinder <adam.buchbinder@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 arch/arm/mach-s3c24xx/include/mach/bast-map.h                   | 2 +-
 arch/arm/mach-s3c24xx/include/mach/dma.h                        | 2 +-
 arch/arm/mach-s3c24xx/include/mach/vr1000-map.h                 | 2 +-
 arch/arm/mach-s3c24xx/pm.c                                      | 2 +-
 arch/arm/plat-s3c24xx/dma.c                                     | 2 +-
 arch/m68k/math-emu/fp_log.c                                     | 2 +-
 arch/powerpc/include/asm/pte-hash64-64k.h                       | 2 +-
 arch/powerpc/include/asm/smu.h                                  | 4 ++--
 arch/powerpc/kernel/legacy_serial.c                             | 2 +-
 arch/powerpc/kernel/of_platform.c                               | 2 +-
 arch/powerpc/kernel/signal_64.c                                 | 2 +-
 arch/powerpc/mm/slice.c                                         | 2 +-
 arch/powerpc/platforms/52xx/mpc52xx_gpt.c                       | 2 +-
 arch/powerpc/platforms/cell/iommu.c                             | 2 +-
 arch/powerpc/platforms/cell/spider-pic.c                        | 6 +++---
 arch/powerpc/platforms/powermac/pic.c                           | 2 +-
 drivers/gpu/drm/radeon/evergreen.c                              | 2 +-
 drivers/gpu/drm/radeon/ni.c                                     | 4 ++--
 drivers/gpu/drm/radeon/si.c                                     | 6 +++---
 drivers/i2c/busses/i2c-nuc900.c                                 | 2 +-
 drivers/i2c/busses/i2c-s3c2410.c                                | 4 ++--
 drivers/mtd/maps/plat-ram.c                                     | 2 +-
 drivers/mtd/nand/s3c2410.c                                      | 2 +-
 drivers/net/ethernet/8390/ax88796.c                             | 2 +-
 drivers/net/ethernet/myricom/myri10ge/myri10ge_mcp_gen_header.h | 2 +-
 drivers/net/sungem_phy.c                                        | 8 ++++----
 drivers/rtc/rtc-isl1208.c                                       | 2 +-
 drivers/rtc/rtc-s3c.c                                           | 2 +-
 drivers/s390/block/dasd_devmap.c                                | 2 +-
 drivers/usb/storage/realtek_cr.c                                | 2 +-
 drivers/watchdog/booke_wdt.c                                    | 2 +-
 fs/btrfs/extent-tree.c                                          | 2 +-
 fs/btrfs/ordered-data.h                                         | 2 +-
 fs/ext4/ext4.h                                                  | 2 +-
 fs/fhandle.c                                                    | 4 ++--
 fs/jbd/transaction.c                                            | 2 +-
 fs/jbd2/transaction.c                                           | 2 +-
 fs/logfs/inode.c                                                | 2 +-
 include/linux/lru_cache.h                                       | 4 ++--
 include/linux/vgaarb.h                                          | 4 ++--
 include/linux/watchdog.h                                        | 2 +-
 include/net/sock.h                                              | 2 +-
 net/can/proc.c                                                  | 2 +-
 sound/pci/es1968.c                                              | 2 +-
 sound/usb/quirks.c                                              | 2 +-
 45 files changed, 58 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-s3c24xx/include/mach/bast-map.h b/arch/arm/mach-s3c24xx/include/mach/bast-map.h
index 6e7dc9d0cf0e..eecea2a50f8f 100644
--- a/arch/arm/mach-s3c24xx/include/mach/bast-map.h
+++ b/arch/arm/mach-s3c24xx/include/mach/bast-map.h
@@ -74,7 +74,7 @@
 
 
 /* 0xE0000000 contains the IO space that is split by speed and
- * wether the access is for 8 or 16bit IO... this ensures that
+ * whether the access is for 8 or 16bit IO... this ensures that
  * the correct access is made
  *
  * 0x10000000 of space, partitioned as so:
diff --git a/arch/arm/mach-s3c24xx/include/mach/dma.h b/arch/arm/mach-s3c24xx/include/mach/dma.h
index ee99fd56c043..6b72d5a4b377 100644
--- a/arch/arm/mach-s3c24xx/include/mach/dma.h
+++ b/arch/arm/mach-s3c24xx/include/mach/dma.h
@@ -88,7 +88,7 @@ enum s3c2410_dma_state {
  *
  * This represents the state of the DMA engine, wrt to the loaded / running
  * transfers. Since we don't have any way of knowing exactly the state of
- * the DMA transfers, we need to know the state to make decisions on wether
+ * the DMA transfers, we need to know the state to make decisions on whether
  * we can
  *
  * S3C2410_DMA_NONE
diff --git a/arch/arm/mach-s3c24xx/include/mach/vr1000-map.h b/arch/arm/mach-s3c24xx/include/mach/vr1000-map.h
index 99612fcc4eb2..28376e56dd3b 100644
--- a/arch/arm/mach-s3c24xx/include/mach/vr1000-map.h
+++ b/arch/arm/mach-s3c24xx/include/mach/vr1000-map.h
@@ -51,7 +51,7 @@
 #define VR1000_VA_PC104_IRQMASK VR1000_IOADDR(0x00600000)
 
 /* 0xE0000000 contains the IO space that is split by speed and
- * wether the access is for 8 or 16bit IO... this ensures that
+ * whether the access is for 8 or 16bit IO... this ensures that
  * the correct access is made
  *
  * 0x10000000 of space, partitioned as so:
diff --git a/arch/arm/mach-s3c24xx/pm.c b/arch/arm/mach-s3c24xx/pm.c
index 60627e63a254..724755f0b0f5 100644
--- a/arch/arm/mach-s3c24xx/pm.c
+++ b/arch/arm/mach-s3c24xx/pm.c
@@ -121,7 +121,7 @@ void s3c_pm_configure_extint(void)
 	int pin;
 
 	/* for each of the external interrupts (EINT0..EINT15) we
-	 * need to check wether it is an external interrupt source,
+	 * need to check whether it is an external interrupt source,
 	 * and then configure it as an input if it is not
 	*/
 
diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c
index db98e7021f0d..3eb5139656af 100644
--- a/arch/arm/plat-s3c24xx/dma.c
+++ b/arch/arm/plat-s3c24xx/dma.c
@@ -325,7 +325,7 @@ static int s3c2410_dma_start(struct s3c2410_dma_chan *chan)
 
 	chan->state = S3C2410_DMA_RUNNING;
 
-	/* check wether there is anything to load, and if not, see
+	/* check whether there is anything to load, and if not, see
 	 * if we can find anything to load
 	 */
 
diff --git a/arch/m68k/math-emu/fp_log.c b/arch/m68k/math-emu/fp_log.c
index 3384a5244fbd..0663067870f2 100644
--- a/arch/m68k/math-emu/fp_log.c
+++ b/arch/m68k/math-emu/fp_log.c
@@ -50,7 +50,7 @@ fp_fsqrt(struct fp_ext *dest, struct fp_ext *src)
 	 * sqrt(m*2^e) =
 	 *		 sqrt(2*m) * 2^(p)	, if e = 2*p + 1
 	 *
-	 * So we use the last bit of the exponent to decide wether to
+	 * So we use the last bit of the exponent to decide whether to
 	 * use the m or 2*m.
 	 *
 	 * Since only the fractional part of the mantissa is stored and
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index eedf427c9124..3e13e23e4fdf 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -23,7 +23,7 @@
 
 /* Note the full page bits must be in the same location as for normal
  * 4k pages as the same assembly will be used to insert 64K pages
- * wether the kernel has CONFIG_PPC_64K_PAGES or not
+ * whether the kernel has CONFIG_PPC_64K_PAGES or not
  */
 #define _PAGE_F_SECOND  0x00008000 /* full page: hidx bits */
 #define _PAGE_F_GIX     0x00007000 /* full page: hidx bits */
diff --git a/arch/powerpc/include/asm/smu.h b/arch/powerpc/include/asm/smu.h
index ae20ce1af4c7..6e909f3e6a46 100644
--- a/arch/powerpc/include/asm/smu.h
+++ b/arch/powerpc/include/asm/smu.h
@@ -132,7 +132,7 @@
   *
   * At this point, the OF driver seems to have a limitation on transfer
   * sizes of 0xd bytes on reads and 0x5 bytes on writes. I do not know
-  * wether this is just an OF limit due to some temporary buffer size
+  * whether this is just an OF limit due to some temporary buffer size
   * or if this is an SMU imposed limit. This driver has the same limitation
   * for now as I use a 0x10 bytes temporary buffer as well
   *
@@ -236,7 +236,7 @@
  *   3 (optional): enable nmi? [0x00 or 0x01]
  *
  * Returns:
- *   If parameter 2 is 0x00 and parameter 3 is not specified, returns wether
+ *   If parameter 2 is 0x00 and parameter 3 is not specified, returns whether
  *   NMI is enabled. Otherwise unknown.
  */
 #define   SMU_CMD_MISC_df_NMI_OPTION		0x04
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index bedd12e1cfbc..0733b05eb856 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -387,7 +387,7 @@ void __init find_legacy_serial_ports(void)
 			of_node_put(parent);
 			continue;
 		}
-		/* Check for known pciclass, and also check wether we have
+		/* Check for known pciclass, and also check whether we have
 		 * a device with child nodes for ports or not
 		 */
 		if (of_device_is_compatible(np, "pciclass,0700") ||
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index 2049f2d00ffe..9db8ec07ec94 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -82,7 +82,7 @@ static int __devinit of_pci_phb_probe(struct platform_device *dev)
 		return -ENXIO;
 
 	/* Claim resources. This might need some rework as well depending
-	 * wether we are doing probe-only or not, like assigning unassigned
+	 * whether we are doing probe-only or not, like assigning unassigned
 	 * resources etc...
 	 */
 	pcibios_claim_one_bus(phb->bus);
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index d183f8719a50..1ca045d44324 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -83,7 +83,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	 * the context). This is very important because we must ensure we
 	 * don't lose the VRSAVE content that may have been set prior to
 	 * the process doing its first vector operation
-	 * Userland shall check AT_HWCAP to know wether it can rely on the
+	 * Userland shall check AT_HWCAP to know whether it can rely on the
 	 * v_regs pointer or not
 	 */
 #ifdef CONFIG_ALTIVEC
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 5829d2a950d4..cf9dada734b6 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -722,7 +722,7 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 }
 
 /*
- * is_hugepage_only_range() is used by generic code to verify wether
+ * is_hugepage_only_range() is used by generic code to verify whether
  * a normal mmap mapping (non hugetlbfs) is valid on a given area.
  *
  * until the generic code provides a more generic hook and/or starts
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 028470b95886..a51cb07bd663 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -526,7 +526,7 @@ EXPORT_SYMBOL(mpc52xx_gpt_timer_period);
 
 #define WDT_IDENTITY	    "mpc52xx watchdog on GPT0"
 
-/* wdt_is_active stores wether or not the /dev/watchdog device is opened */
+/* wdt_is_active stores whether or not the /dev/watchdog device is opened */
 static unsigned long wdt_is_active;
 
 /* wdt-capable gpt */
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index dca213666747..e56bb651da1a 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -728,7 +728,7 @@ static struct cbe_iommu * __init cell_iommu_alloc(struct device_node *np)
 		 nid, np->full_name);
 
 	/* XXX todo: If we can have multiple windows on the same IOMMU, which
-	 * isn't the case today, we probably want here to check wether the
+	 * isn't the case today, we probably want here to check whether the
 	 * iommu for that node is already setup.
 	 * However, there might be issue with getting the size right so let's
 	 * ignore that for now. We might want to completely get rid of the
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index d8b7cc8a66ca..8e299447127e 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -148,7 +148,7 @@ static int spider_set_irq_type(struct irq_data *d, unsigned int type)
 
 	/* Configure the source. One gross hack that was there before and
 	 * that I've kept around is the priority to the BE which I set to
-	 * be the same as the interrupt source number. I don't know wether
+	 * be the same as the interrupt source number. I don't know whether
 	 * that's supposed to make any kind of sense however, we'll have to
 	 * decide that, but for now, I'm not changing the behaviour.
 	 */
@@ -220,7 +220,7 @@ static void spider_irq_cascade(unsigned int irq, struct irq_desc *desc)
 /* For hooking up the cascace we have a problem. Our device-tree is
  * crap and we don't know on which BE iic interrupt we are hooked on at
  * least not the "standard" way. We can reconstitute it based on two
- * informations though: which BE node we are connected to and wether
+ * informations though: which BE node we are connected to and whether
  * we are connected to IOIF0 or IOIF1. Right now, we really only care
  * about the IBM cell blade and we know that its firmware gives us an
  * interrupt-map property which is pretty strange.
@@ -232,7 +232,7 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic)
 	int imaplen, intsize, unit;
 	struct device_node *iic;
 
-	/* First, we check wether we have a real "interrupts" in the device
+	/* First, we check whether we have a real "interrupts" in the device
 	 * tree in case the device-tree is ever fixed
 	 */
 	struct of_irq oirq;
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index c4e630576ff2..31036b56670e 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -529,7 +529,7 @@ static int __init pmac_pic_probe_mpic(void)
 void __init pmac_pic_init(void)
 {
 	/* We configure the OF parsing based on our oldworld vs. newworld
-	 * platform type and wether we were booted by BootX.
+	 * platform type and whether we were booted by BootX.
 	 */
 #ifdef CONFIG_PPC32
 	if (!pmac_newworld)
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 14313ad43b76..42509492717e 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1648,7 +1648,7 @@ static int evergreen_cp_resume(struct radeon_device *rdev)
 	ring->wptr = 0;
 	WREG32(CP_RB_WPTR, ring->wptr);
 
-	/* set the wb address wether it's enabled or not */
+	/* set the wb address whether it's enabled or not */
 	WREG32(CP_RB_RPTR_ADDR,
 	       ((rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC));
 	WREG32(CP_RB_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFF);
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 81e6a568c29d..cda01f808f12 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1059,7 +1059,7 @@ static int cayman_cp_resume(struct radeon_device *rdev)
 
 	WREG32(CP_DEBUG, (1 << 27));
 
-	/* set the wb address wether it's enabled or not */
+	/* set the wb address whether it's enabled or not */
 	WREG32(SCRATCH_ADDR, ((rdev->wb.gpu_addr + RADEON_WB_SCRATCH_OFFSET) >> 8) & 0xFFFFFFFF);
 	WREG32(SCRATCH_UMSK, 0xff);
 
@@ -1076,7 +1076,7 @@ static int cayman_cp_resume(struct radeon_device *rdev)
 #endif
 		WREG32(cp_rb_cntl[i], rb_cntl);
 
-		/* set the wb address wether it's enabled or not */
+		/* set the wb address whether it's enabled or not */
 		addr = rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET;
 		WREG32(cp_rb_rptr_addr[i], addr & 0xFFFFFFFC);
 		WREG32(cp_rb_rptr_addr_hi[i], upper_32_bits(addr) & 0xFF);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index b0db712060fb..ea4691f79ccd 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2007,7 +2007,7 @@ static int si_cp_resume(struct radeon_device *rdev)
 	ring->wptr = 0;
 	WREG32(CP_RB0_WPTR, ring->wptr);
 
-	/* set the wb address wether it's enabled or not */
+	/* set the wb address whether it's enabled or not */
 	WREG32(CP_RB0_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC);
 	WREG32(CP_RB0_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFF);
 
@@ -2040,7 +2040,7 @@ static int si_cp_resume(struct radeon_device *rdev)
 	ring->wptr = 0;
 	WREG32(CP_RB1_WPTR, ring->wptr);
 
-	/* set the wb address wether it's enabled or not */
+	/* set the wb address whether it's enabled or not */
 	WREG32(CP_RB1_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP1_RPTR_OFFSET) & 0xFFFFFFFC);
 	WREG32(CP_RB1_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP1_RPTR_OFFSET) & 0xFF);
 
@@ -2066,7 +2066,7 @@ static int si_cp_resume(struct radeon_device *rdev)
 	ring->wptr = 0;
 	WREG32(CP_RB2_WPTR, ring->wptr);
 
-	/* set the wb address wether it's enabled or not */
+	/* set the wb address whether it's enabled or not */
 	WREG32(CP_RB2_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP2_RPTR_OFFSET) & 0xFFFFFFFC);
 	WREG32(CP_RB2_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP2_RPTR_OFFSET) & 0xFF);
 
diff --git a/drivers/i2c/busses/i2c-nuc900.c b/drivers/i2c/busses/i2c-nuc900.c
index f41502ef3f55..a23b91b0b738 100644
--- a/drivers/i2c/busses/i2c-nuc900.c
+++ b/drivers/i2c/busses/i2c-nuc900.c
@@ -304,7 +304,7 @@ retry_write:
 
 	case STATE_READ:
 		/* we have a byte of data in the data register, do
-		 * something with it, and then work out wether we are
+		 * something with it, and then work out whether we are
 		 * going to do any more read/write
 		 */
 
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index 3e0335f1fc60..de9e1fa0aa0e 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -208,7 +208,7 @@ static void s3c24xx_i2c_message_start(struct s3c24xx_i2c *i2c,
 	if (msg->flags & I2C_M_REV_DIR_ADDR)
 		addr ^= 1;
 
-	/* todo - check for wether ack wanted or not */
+	/* todo - check for whether ack wanted or not */
 	s3c24xx_i2c_enable_ack(i2c);
 
 	iiccon = readl(i2c->regs + S3C2410_IICCON);
@@ -397,7 +397,7 @@ static int i2c_s3c_irq_nextbyte(struct s3c24xx_i2c *i2c, unsigned long iicstat)
 
 	case STATE_READ:
 		/* we have a byte of data in the data register, do
-		 * something with it, and then work out wether we are
+		 * something with it, and then work out whether we are
 		 * going to do any more read/write
 		 */
 
diff --git a/drivers/mtd/maps/plat-ram.c b/drivers/mtd/maps/plat-ram.c
index 891558de3ec1..2de66b062f0d 100644
--- a/drivers/mtd/maps/plat-ram.c
+++ b/drivers/mtd/maps/plat-ram.c
@@ -219,7 +219,7 @@ static int platram_probe(struct platform_device *pdev)
 
 	platram_setrw(info, PLATRAM_RW);
 
-	/* check to see if there are any available partitions, or wether
+	/* check to see if there are any available partitions, or whether
 	 * to add this device whole */
 
 	err = mtd_device_parse_register(info->mtd, pdata->probes, NULL,
diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c
index 295e4bedad96..79ded48e7427 100644
--- a/drivers/mtd/nand/s3c2410.c
+++ b/drivers/mtd/nand/s3c2410.c
@@ -879,7 +879,7 @@ static void s3c2410_nand_update_chip(struct s3c2410_nand_info *info,
 	if (chip->ecc.mode != NAND_ECC_HW)
 		return;
 
-		/* change the behaviour depending on wether we are using
+		/* change the behaviour depending on whether we are using
 		 * the large or small page nand device */
 
 	if (chip->page_shift > 10) {
diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c
index 203ff9dccadb..846381c31185 100644
--- a/drivers/net/ethernet/8390/ax88796.c
+++ b/drivers/net/ethernet/8390/ax88796.c
@@ -109,7 +109,7 @@ static inline struct ax_device *to_ax_dev(struct net_device *dev)
 /*
  * ax_initial_check
  *
- * do an initial probe for the card to check wether it exists
+ * do an initial probe for the card to check whether it exists
  * and is functional
  */
 static int ax_initial_check(struct net_device *dev)
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge_mcp_gen_header.h b/drivers/net/ethernet/myricom/myri10ge/myri10ge_mcp_gen_header.h
index 7ec4b864a550..75ec5e7cf50d 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge_mcp_gen_header.h
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge_mcp_gen_header.h
@@ -27,7 +27,7 @@ struct mcp_gen_header {
 	 *
 	 * Fields below this comment are extensions added in later versions
 	 * of this struct, drivers should compare the header_length against
-	 * offsetof(field) to check wether a given MCP implements them.
+	 * offsetof(field) to check whether a given MCP implements them.
 	 *
 	 * Never remove any field.  Keep everything naturally align.
 	 */
diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c
index 58f13adaa549..ae7cd7f3656d 100644
--- a/drivers/net/sungem_phy.c
+++ b/drivers/net/sungem_phy.c
@@ -608,7 +608,7 @@ static int bcm5421_poll_link(struct mii_phy* phy)
 	if ( mode == BCM54XX_COPPER)
 		return genmii_poll_link(phy);
 
-	/* try to find out wether we have a link */
+	/* try to find out whether we have a link */
 	phy_write(phy, MII_NCONFIG, 0x2000);
 	phy_reg = phy_read(phy, MII_NCONFIG);
 
@@ -634,7 +634,7 @@ static int bcm5421_read_link(struct mii_phy* phy)
 
 	phy->speed = SPEED_1000;
 
-	/* find out wether we are running half- or full duplex */
+	/* find out whether we are running half- or full duplex */
 	phy_write(phy, MII_NCONFIG, 0x2000);
 	phy_reg = phy_read(phy, MII_NCONFIG);
 
@@ -681,7 +681,7 @@ static int bcm5461_poll_link(struct mii_phy* phy)
 	if ( mode == BCM54XX_COPPER)
 		return genmii_poll_link(phy);
 
-	/* find out wether we have a link */
+	/* find out whether we have a link */
 	phy_write(phy, MII_NCONFIG, 0x7000);
 	phy_reg = phy_read(phy, MII_NCONFIG);
 
@@ -710,7 +710,7 @@ static int bcm5461_read_link(struct mii_phy* phy)
 
 	phy->speed = SPEED_1000;
 
-	/* find out wether we are running half- or full duplex */
+	/* find out whether we are running half- or full duplex */
 	phy_write(phy, MII_NCONFIG, 0x7000);
 	phy_reg = phy_read(phy, MII_NCONFIG);
 
diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c
index 26c81f233606..afb7cfa85ccc 100644
--- a/drivers/rtc/rtc-isl1208.c
+++ b/drivers/rtc/rtc-isl1208.c
@@ -118,7 +118,7 @@ isl1208_i2c_set_regs(struct i2c_client *client, u8 reg, u8 const buf[],
 	return ret;
 }
 
-/* simple check to see wether we have a isl1208 */
+/* simple check to see whether we have a isl1208 */
 static int
 isl1208_i2c_validate_client(struct i2c_client *client)
 {
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 77823d21d314..a7a2a998fa91 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -186,7 +186,7 @@ static int s3c_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
 	rtc_tm->tm_year = readb(base + S3C2410_RTCYEAR);
 	rtc_tm->tm_sec  = readb(base + S3C2410_RTCSEC);
 
-	/* the only way to work out wether the system was mid-update
+	/* the only way to work out whether the system was mid-update
 	 * when we read it is to check the second counter, and if it
 	 * is zero, then we re-try the entire read
 	 */
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index b2b8c18eeced..20cfd028edcf 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -1344,7 +1344,7 @@ dasd_get_feature(struct ccw_device *cdev, int feature)
 
 /*
  * Set / reset given feature.
- * Flag indicates wether to set (!=0) or the reset (=0) the feature.
+ * Flag indicates whether to set (!=0) or the reset (=0) the feature.
  */
 int
 dasd_set_feature(struct ccw_device *cdev, int feature, int flag)
diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c
index d36446dd7ae8..73c93cf364c8 100644
--- a/drivers/usb/storage/realtek_cr.c
+++ b/drivers/usb/storage/realtek_cr.c
@@ -883,7 +883,7 @@ static void rts51x_invoke_transport(struct scsi_cmnd *srb, struct us_data *us)
 		} else {
 			US_DEBUGP("%s: NOT working scsi, not SS\n", __func__);
 			chip->proto_handler_backup(srb, us);
-			/* Check wether card is plugged in */
+			/* Check whether card is plugged in */
 			if (srb->cmnd[0] == TEST_UNIT_READY) {
 				if (srb->result == SAM_STAT_GOOD) {
 					SET_LUN_READY(chip, srb->device->lun);
diff --git a/drivers/watchdog/booke_wdt.c b/drivers/watchdog/booke_wdt.c
index 5b06d31ab6a9..c0bc92d8e438 100644
--- a/drivers/watchdog/booke_wdt.c
+++ b/drivers/watchdog/booke_wdt.c
@@ -212,7 +212,7 @@ static long booke_wdt_ioctl(struct file *file,
 	return 0;
 }
 
-/* wdt_is_active stores wether or not the /dev/watchdog device is opened */
+/* wdt_is_active stores whether or not the /dev/watchdog device is opened */
 static unsigned long wdt_is_active;
 
 static int booke_wdt_open(struct inode *inode, struct file *file)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3d3e2c17d8d1..06b2635073f3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3888,7 +3888,7 @@ static int flush_space(struct btrfs_root *root,
  * @root - the root we're allocating for
  * @block_rsv - the block_rsv we're allocating for
  * @orig_bytes - the number of bytes we want
- * @flush - wether or not we can flush to make our reservation
+ * @flush - whether or not we can flush to make our reservation
  *
  * This will reserve orgi_bytes number of bytes from the space info associated
  * with the block_rsv.  If there is not enough space it will make an attempt to
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index dd27a0b46a37..853fc7beedfa 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -76,7 +76,7 @@ struct btrfs_ordered_sum {
 
 #define BTRFS_ORDERED_IOERR 6 /* We had an io error when writing this out */
 
-#define BTRFS_ORDERED_UPDATED_ISIZE 7 /* indicates wether this ordered extent
+#define BTRFS_ORDERED_UPDATED_ISIZE 7 /* indicates whether this ordered extent
 				       * has done its due diligence in updating
 				       * the isize. */
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 3c20de1d59d0..df163da388c9 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2455,7 +2455,7 @@ TAS_BUFFER_FNS(Uninit, uninit)
 BUFFER_FNS(Da_Mapped, da_mapped)
 
 /*
- * Add new method to test wether block and inode bitmaps are properly
+ * Add new method to test whether block and inode bitmaps are properly
  * initialized. With uninit_bg reading the block from disk is not enough
  * to mark the bitmap uptodate. We need to also zero-out the bitmap
  */
diff --git a/fs/fhandle.c b/fs/fhandle.c
index f775bfdd6e4a..cccdc874bb55 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -22,7 +22,7 @@ static long do_sys_name_to_handle(struct path *path,
 	struct file_handle *handle = NULL;
 
 	/*
-	 * We need t make sure wether the file system
+	 * We need to make sure whether the file system
 	 * support decoding of the file handle
 	 */
 	if (!path->dentry->d_sb->s_export_op ||
@@ -40,7 +40,7 @@ static long do_sys_name_to_handle(struct path *path,
 	if (!handle)
 		return -ENOMEM;
 
-	/* convert handle size to  multiple of sizeof(u32) */
+	/* convert handle size to multiple of sizeof(u32) */
 	handle_dwords = f_handle.handle_bytes >> 2;
 
 	/* we ask for a non connected handle */
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 78b7f84241d4..8b472c8bbf7a 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -1259,7 +1259,7 @@ int journal_forget (handle_t *handle, struct buffer_head *bh)
 		goto not_jbd;
 	}
 
-	/* keep track of wether or not this transaction modified us */
+	/* keep track of whether or not this transaction modified us */
 	was_modified = jh->b_modified;
 
 	/*
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index a74ba4659549..d8da40e99d84 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1261,7 +1261,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 		goto not_jbd;
 	}
 
-	/* keep track of wether or not this transaction modified us */
+	/* keep track of whether or not this transaction modified us */
 	was_modified = jh->b_modified;
 
 	/*
diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c
index adb90116d36b..af49e2d6941a 100644
--- a/fs/logfs/inode.c
+++ b/fs/logfs/inode.c
@@ -33,7 +33,7 @@
  * are being written out - and waiting for GC to make progress, naturally.
  *
  * So we cannot just call iget() or some variant of it, but first have to check
- * wether the inode in question might be in I_FREEING state.  Therefore we
+ * whether the inode in question might be in I_FREEING state.  Therefore we
  * maintain our own per-sb list of "almost deleted" inodes and check against
  * that list first.  Normally this should be at most 1-2 entries long.
  *
diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h
index 7a71ffad037c..cafc7f99e124 100644
--- a/include/linux/lru_cache.h
+++ b/include/linux/lru_cache.h
@@ -52,8 +52,8 @@ We replicate IO (more or less synchronously) to local and remote disk.
 
 For crash recovery after replication node failure,
   we need to resync all regions that have been target of in-flight WRITE IO
-  (in use, or "hot", regions), as we don't know wether or not those WRITEs have
-  made it to stable storage.
+  (in use, or "hot", regions), as we don't know whether or not those WRITEs
+  have made it to stable storage.
 
   To avoid a "full resync", we need to persistently track these regions.
 
diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h
index 0ee42d9acdc0..2c02f3a8d2ba 100644
--- a/include/linux/vgaarb.h
+++ b/include/linux/vgaarb.h
@@ -78,7 +78,7 @@ extern void vga_set_legacy_decoding(struct pci_dev *pdev,
  *     This function acquires VGA resources for the given
  *     card and mark those resources locked. If the resource requested
  *     are "normal" (and not legacy) resources, the arbiter will first check
- *     wether the card is doing legacy decoding for that type of resource. If
+ *     whether the card is doing legacy decoding for that type of resource. If
  *     yes, the lock is "converted" into a legacy resource lock.
  *     The arbiter will first look for all VGA cards that might conflict
  *     and disable their IOs and/or Memory access, including VGA forwarding
@@ -89,7 +89,7 @@ extern void vga_set_legacy_decoding(struct pci_dev *pdev,
  *     This function will block if some conflicting card is already locking
  *     one of the required resources (or any resource on a different bus
  *     segment, since P2P bridges don't differenciate VGA memory and IO
- *     afaik). You can indicate wether this blocking should be interruptible
+ *     afaik). You can indicate whether this blocking should be interruptible
  *     by a signal (for userland interface) or not.
  *     Must not be called at interrupt time or in atomic context.
  *     If the card already owns the resources, the function succeeds.
diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h
index b7f45d48b2de..87490ac4bd87 100644
--- a/include/linux/watchdog.h
+++ b/include/linux/watchdog.h
@@ -105,7 +105,7 @@ struct watchdog_device {
 #define WATCHDOG_NOWAYOUT_INIT_STATUS	0
 #endif
 
-/* Use the following function to check wether or not the watchdog is active */
+/* Use the following function to check whether or not the watchdog is active */
 static inline bool watchdog_active(struct watchdog_device *wdd)
 {
 	return test_bit(WDOG_ACTIVE, &wdd->status);
diff --git a/include/net/sock.h b/include/net/sock.h
index c945fba4f543..a95e0756e56e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -213,7 +213,7 @@ struct cg_proto;
   *	@sk_sndbuf: size of send buffer in bytes
   *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
   *		   %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
-  *	@sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
+  *	@sk_no_check: %SO_NO_CHECK setting, whether or not checkup packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
   *	@sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
   *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
diff --git a/net/can/proc.c b/net/can/proc.c
index 3b6dd3180492..ae566902d2bf 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -397,7 +397,7 @@ static inline void can_rcvlist_sff_proc_show_one(struct seq_file *m,
 	int i;
 	int all_empty = 1;
 
-	/* check wether at least one list is non-empty */
+	/* check whether at least one list is non-empty */
 	for (i = 0; i < 0x800; i++)
 		if (!hlist_empty(&d->rx_sff[i])) {
 			all_empty = 0;
diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c
index 5d0e568fdea1..dc14234fea29 100644
--- a/sound/pci/es1968.c
+++ b/sound/pci/es1968.c
@@ -2291,7 +2291,7 @@ static void snd_es1968_chip_init(struct es1968 *chip)
 	outb(0x88, iobase+0x1f);
 
 	/* it appears some maestros (dell 7500) only work if these are set,
-	   regardless of wether we use the assp or not. */
+	   regardless of whether we use the assp or not. */
 
 	outb(0, iobase + ASSP_CONTROL_B);
 	outb(3, iobase + ASSP_CONTROL_A);	/* M: Reserved bits... */
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 0f58b4b6d702..007fcecdf5cd 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -675,7 +675,7 @@ int snd_usb_apply_boot_quirk(struct usb_device *dev,
  */
 int snd_usb_is_big_endian_format(struct snd_usb_audio *chip, struct audioformat *fp)
 {
-	/* it depends on altsetting wether the device is big-endian or not */
+	/* it depends on altsetting whether the device is big-endian or not */
 	switch (chip->usb_id) {
 	case USB_ID(0x0763, 0x2001): /* M-Audio Quattro: captured data only */
 		if (fp->altsetting == 2 || fp->altsetting == 3 ||
-- 
cgit v1.2.3-55-g7522


From b3834be5c42a5d2fd85ff4b819fa38983b1450e6 Mon Sep 17 00:00:00 2001
From: Adam Buchbinder
Date: Wed, 19 Sep 2012 21:48:02 -0400
Subject: various: Fix spelling of "asynchronous" in comments.

"Asynchronous" is misspelled in some comments. No code changes.

Signed-off-by: Adam Buchbinder <adam.buchbinder@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/char/ipmi/ipmi_msghandler.c     | 2 +-
 drivers/char/ipmi/ipmi_si_intf.c        | 2 +-
 drivers/firewire/init_ohci1394_dma.c    | 4 ++--
 drivers/firewire/ohci.c                 | 2 +-
 drivers/net/ethernet/mellanox/mlx4/eq.c | 2 +-
 drivers/tty/ipwireless/setup_protocol.h | 2 +-
 fs/notify/notification.c                | 2 +-
 include/linux/dlm.h                     | 2 +-
 include/linux/ipmi_smi.h                | 2 +-
 mm/memory_hotplug.c                     | 6 +++---
 sound/pci/sis7019.c                     | 2 +-
 11 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index a0c84bb30856..053201b062a4 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -3789,7 +3789,7 @@ static int handle_one_recv_msg(ipmi_smi_t          intf,
 
 	} else if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2))
 		   && (msg->rsp[1] == IPMI_READ_EVENT_MSG_BUFFER_CMD)) {
-		/* It's an asyncronous event. */
+		/* It's an asynchronous event. */
 		requeue = handle_read_event_rsp(intf, msg);
 	} else {
 		/* It's a response from the local BMC. */
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 32a6c7e256bd..c9c3501784e0 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -155,7 +155,7 @@ enum si_stat_indexes {
 	/* Number of watchdog pretimeouts. */
 	SI_STAT_watchdog_pretimeouts,
 
-	/* Number of asyncronous messages received. */
+	/* Number of asynchronous messages received. */
 	SI_STAT_incoming_messages,
 
 
diff --git a/drivers/firewire/init_ohci1394_dma.c b/drivers/firewire/init_ohci1394_dma.c
index a9a347adb353..2cc89ce745c9 100644
--- a/drivers/firewire/init_ohci1394_dma.c
+++ b/drivers/firewire/init_ohci1394_dma.c
@@ -149,10 +149,10 @@ static inline void __init init_ohci1394_initialize(struct ohci *ohci)
 	reg_write(ohci, OHCI1394_IsoXmitIntMaskClear, 0xffffffff);
 	reg_write(ohci, OHCI1394_IsoXmitIntEventClear, 0xffffffff);
 
-	/* Accept asyncronous transfer requests from all nodes for now */
+	/* Accept asynchronous transfer requests from all nodes for now */
 	reg_write(ohci, OHCI1394_AsReqFilterHiSet, 0x80000000);
 
-	/* Specify asyncronous transfer retries */
+	/* Specify asynchronous transfer retries */
 	reg_write(ohci, OHCI1394_ATRetries,
 		  OHCI1394_MAX_AT_REQ_RETRIES |
 		  (OHCI1394_MAX_AT_RESP_RETRIES<<4) |
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 834e71d2324d..961e4398664b 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -1281,7 +1281,7 @@ static int at_context_queue_packet(struct context *ctx,
 	d[0].res_count = cpu_to_le16(packet->timestamp);
 
 	/*
-	 * The DMA format for asyncronous link packets is different
+	 * The DMA format for asynchronous link packets is different
 	 * from the IEEE1394 layout, so shift the fields around
 	 * accordingly.
 	 */
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index b84a88bc44dc..c48cf6f6529c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -1267,7 +1267,7 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 		/* Temporary use polling for command completions */
 		mlx4_cmd_use_polling(dev);
 
-		/* Map the new eq to handle all asyncronous events */
+		/* Map the new eq to handle all asynchronous events */
 		err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
 				  priv->eq_table.eq[i].eqn);
 		if (err) {
diff --git a/drivers/tty/ipwireless/setup_protocol.h b/drivers/tty/ipwireless/setup_protocol.h
index 9d6bcc77c73c..002c34e72521 100644
--- a/drivers/tty/ipwireless/setup_protocol.h
+++ b/drivers/tty/ipwireless/setup_protocol.h
@@ -59,7 +59,7 @@ struct tl_setup_config_done_msg {
 	unsigned char sig_no;		/* TL_SETUP_SIGNO_CONFIG_DONE_MSG */
 } __attribute__ ((__packed__));
 
-/* Asyncronous messages */
+/* Asynchronous messages */
 struct tl_setup_open_msg {
 	unsigned char sig_no;		/* TL_SETUP_SIGNO_OPEN_MSG */
 	unsigned char port_no;
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index c887b1378f7e..48cb994e4922 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -18,7 +18,7 @@
 
 /*
  * Basic idea behind the notification queue: An fsnotify group (like inotify)
- * sends the userspace notification about events asyncronously some time after
+ * sends the userspace notification about events asynchronously some time after
  * the event happened.  When inotify gets an event it will need to add that
  * event to the group notify queue.  Since a single event might need to be on
  * multiple group's notification queues we can't add the event directly to each
diff --git a/include/linux/dlm.h b/include/linux/dlm.h
index 1d47dcce11e1..d02da2c6fc1a 100644
--- a/include/linux/dlm.h
+++ b/include/linux/dlm.h
@@ -98,7 +98,7 @@ int dlm_release_lockspace(dlm_lockspace_t *lockspace, int force);
 /*
  * dlm_lock
  *
- * Make an asyncronous request to acquire or convert a lock on a named
+ * Make an asynchronous request to acquire or convert a lock on a named
  * resource.
  *
  * lockspace: context for the request
diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h
index fcb5d44ea635..8ea3fe0b9759 100644
--- a/include/linux/ipmi_smi.h
+++ b/include/linux/ipmi_smi.h
@@ -216,7 +216,7 @@ int ipmi_unregister_smi(ipmi_smi_t intf);
 
 /*
  * The lower layer reports received messages through this interface.
- * The data_size should be zero if this is an asyncronous message.  If
+ * The data_size should be zero if this is an asynchronous message.  If
  * the lower layer gets an error sending a message, it should format
  * an error response in the message response.
  */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 56b758ae57d2..bb81b7f417a8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -950,10 +950,10 @@ repeat:
 			goto repeat;
 		}
 	}
-	/* drain all zone's lru pagevec, this is asyncronous... */
+	/* drain all zone's lru pagevec, this is asynchronous... */
 	lru_add_drain_all();
 	yield();
-	/* drain pcp pages , this is synchrouns. */
+	/* drain pcp pages, this is synchronous. */
 	drain_all_pages();
 	/* check again */
 	offlined_pages = check_pages_isolated(start_pfn, end_pfn);
@@ -962,7 +962,7 @@ repeat:
 		goto failed_removal;
 	}
 	printk(KERN_INFO "Offlined Pages %ld\n", offlined_pages);
-	/* Ok, all of our target is islaoted.
+	/* Ok, all of our target is isolated.
 	   We cannot do rollback at this point. */
 	offline_isolated_pages(start_pfn, end_pfn);
 	/* reset pagetype flags and makes migrate type to be MOVABLE */
diff --git a/sound/pci/sis7019.c b/sound/pci/sis7019.c
index 51e43407ebc5..9024545ebb86 100644
--- a/sound/pci/sis7019.c
+++ b/sound/pci/sis7019.c
@@ -1171,7 +1171,7 @@ static int sis_chip_init(struct sis7019 *sis)
 	outl(SIS_DMA_CSR_PCI_SETTINGS, io + SIS_DMA_CSR);
 
 	/* Reset the synchronization groups for all of the channels
-	 * to be asyncronous. If we start doing SPDIF or 5.1 sound, etc.
+	 * to be asynchronous. If we start doing SPDIF or 5.1 sound, etc.
 	 * we'll need to change how we handle these. Until then, we just
 	 * assign sub-mixer 0 to all playback channels, and avoid any
 	 * attenuation on the audio.
-- 
cgit v1.2.3-55-g7522


From 49f4d8b93ccf9454284b6f524b96c66d8d7fbccc Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Thu, 2 Aug 2012 04:25:10 -0700
Subject: pidns: Capture the user namespace and filter ns_last_pid

- Capture the the user namespace that creates the pid namespace
- Use that user namespace to test if it is ok to write to
  /proc/sys/kernel/ns_last_pid.

Zhao Hongjiang <zhaohongjiang@huawei.com> noticed I was missing a put_user_ns
in when destroying a pid_ns.  I have foloded his patch into this one
so that bisects will work properly.

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/pid_namespace.h |  8 +++++---
 kernel/nsproxy.c              |  2 +-
 kernel/pid.c                  |  1 +
 kernel/pid_namespace.c        | 17 ++++++++++++-----
 4 files changed, 19 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 65e3e87eacc5..c89c9cfcd247 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -31,6 +31,7 @@ struct pid_namespace {
 #ifdef CONFIG_BSD_PROCESS_ACCT
 	struct bsd_acct_struct *bacct;
 #endif
+	struct user_namespace *user_ns;
 	kgid_t pid_gid;
 	int hide_pid;
 	int reboot;	/* group exit code if this pidns was rebooted */
@@ -46,7 +47,8 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 	return ns;
 }
 
-extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *ns);
+extern struct pid_namespace *copy_pid_ns(unsigned long flags,
+	struct user_namespace *user_ns, struct pid_namespace *ns);
 extern void zap_pid_ns_processes(struct pid_namespace *pid_ns);
 extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd);
 extern void put_pid_ns(struct pid_namespace *ns);
@@ -59,8 +61,8 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 	return ns;
 }
 
-static inline struct pid_namespace *
-copy_pid_ns(unsigned long flags, struct pid_namespace *ns)
+static inline struct pid_namespace *copy_pid_ns(unsigned long flags,
+	struct user_namespace *user_ns, struct pid_namespace *ns)
 {
 	if (flags & CLONE_NEWPID)
 		ns = ERR_PTR(-EINVAL);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 7e1c3de1ce45..ca27d2c5264d 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -84,7 +84,7 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 		goto out_ipc;
 	}
 
-	new_nsp->pid_ns = copy_pid_ns(flags, task_active_pid_ns(tsk));
+	new_nsp->pid_ns = copy_pid_ns(flags, task_cred_xxx(tsk, user_ns), task_active_pid_ns(tsk));
 	if (IS_ERR(new_nsp->pid_ns)) {
 		err = PTR_ERR(new_nsp->pid_ns);
 		goto out_pid;
diff --git a/kernel/pid.c b/kernel/pid.c
index aebd4f5aaf41..2a624f1486e1 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -78,6 +78,7 @@ struct pid_namespace init_pid_ns = {
 	.last_pid = 0,
 	.level = 0,
 	.child_reaper = &init_task,
+	.user_ns = &init_user_ns,
 };
 EXPORT_SYMBOL_GPL(init_pid_ns);
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 7b07cc0dfb75..b2604950aa50 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -10,6 +10,7 @@
 
 #include <linux/pid.h>
 #include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
 #include <linux/syscalls.h>
 #include <linux/err.h>
 #include <linux/acct.h>
@@ -74,7 +75,8 @@ err_alloc:
 /* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
 #define MAX_PID_NS_LEVEL 32
 
-static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns)
+static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns,
+	struct pid_namespace *parent_pid_ns)
 {
 	struct pid_namespace *ns;
 	unsigned int level = parent_pid_ns->level + 1;
@@ -102,6 +104,7 @@ static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_p
 	kref_init(&ns->kref);
 	ns->level = level;
 	ns->parent = get_pid_ns(parent_pid_ns);
+	ns->user_ns = get_user_ns(user_ns);
 
 	set_bit(0, ns->pidmap[0].page);
 	atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
@@ -117,6 +120,7 @@ static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_p
 
 out_put_parent_pid_ns:
 	put_pid_ns(parent_pid_ns);
+	put_user_ns(user_ns);
 out_free_map:
 	kfree(ns->pidmap[0].page);
 out_free:
@@ -131,16 +135,18 @@ static void destroy_pid_namespace(struct pid_namespace *ns)
 
 	for (i = 0; i < PIDMAP_ENTRIES; i++)
 		kfree(ns->pidmap[i].page);
+	put_user_ns(ns->user_ns);
 	kmem_cache_free(pid_ns_cachep, ns);
 }
 
-struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns)
+struct pid_namespace *copy_pid_ns(unsigned long flags,
+	struct user_namespace *user_ns, struct pid_namespace *old_ns)
 {
 	if (!(flags & CLONE_NEWPID))
 		return get_pid_ns(old_ns);
 	if (flags & (CLONE_THREAD|CLONE_PARENT))
 		return ERR_PTR(-EINVAL);
-	return create_pid_namespace(old_ns);
+	return create_pid_namespace(user_ns, old_ns);
 }
 
 static void free_pid_ns(struct kref *kref)
@@ -239,9 +245,10 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 static int pid_ns_ctl_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct pid_namespace *pid_ns = task_active_pid_ns(current);
 	struct ctl_table tmp = *table;
 
-	if (write && !capable(CAP_SYS_ADMIN))
+	if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/*
@@ -250,7 +257,7 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
 	 * it should synchronize its usage with external means.
 	 */
 
-	tmp.data = &current->nsproxy->pid_ns->last_pid;
+	tmp.data = &pid_ns->last_pid;
 	return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 }
 
-- 
cgit v1.2.3-55-g7522


From 0a01f2cc390e10633a54f72c608cc3fe19a50c3d Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Wed, 1 Aug 2012 10:33:47 -0700
Subject: pidns: Make the pidns proc mount/umount logic obvious.

Track the number of pids in the proc hash table.  When the number of
pids goes to 0 schedule work to unmount the kernel mount of proc.

Move the mount of proc into alloc_pid when we allocate the pid for
init.

Remove the surprising calls of pid_ns_release proc in fork and
proc_flush_task.  Those code paths really shouldn't know about proc
namespace implementation details and people have demonstrated several
times that finding and understanding those code paths is difficult and
non-obvious.

Because of the call path detach pid is alwasy called with the
rtnl_lock held free_pid is not allowed to sleep, so the work to
unmounting proc is moved to a work queue.  This has the side benefit
of not blocking the entire world waiting for the unnecessary
rcu_barrier in deactivate_locked_super.

In the process of making the code clear and obvious this fixes a bug
reported by Gao feng <gaofeng@cn.fujitsu.com> where we would leak a
mount of proc during clone(CLONE_NEWPID|CLONE_NEWNET) if copy_pid_ns
succeeded and copy_net_ns failed.

Acked-by: "Serge E. Hallyn" <serge@hallyn.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/proc/base.c                |  4 ----
 fs/proc/root.c                |  5 -----
 include/linux/pid_namespace.h |  2 ++
 kernel/fork.c                 |  2 --
 kernel/pid.c                  | 21 +++++++++++++++++----
 kernel/pid_namespace.c        | 14 +++++++-------
 6 files changed, 26 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 6177fc238fdb..7621dc51cff8 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2590,10 +2590,6 @@ void proc_flush_task(struct task_struct *task)
 		proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
 					tgid->numbers[i].nr);
 	}
-
-	upid = &pid->numbers[pid->level];
-	if (upid->nr == 1)
-		pid_ns_release_proc(upid->ns);
 }
 
 static struct dentry *proc_pid_instantiate(struct inode *dir,
diff --git a/fs/proc/root.c b/fs/proc/root.c
index fc1609321a78..f2f251158d35 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -155,11 +155,6 @@ void __init proc_root_init(void)
 	err = register_filesystem(&proc_fs_type);
 	if (err)
 		return;
-	err = pid_ns_prepare_proc(&init_pid_ns);
-	if (err) {
-		unregister_filesystem(&proc_fs_type);
-		return;
-	}
 
 	proc_self_init();
 	proc_symlink("mounts", NULL, "self/mounts");
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index c89c9cfcd247..4c96acdb2489 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -21,6 +21,7 @@ struct pid_namespace {
 	struct kref kref;
 	struct pidmap pidmap[PIDMAP_ENTRIES];
 	int last_pid;
+	int nr_hashed;
 	struct task_struct *child_reaper;
 	struct kmem_cache *pid_cachep;
 	unsigned int level;
@@ -32,6 +33,7 @@ struct pid_namespace {
 	struct bsd_acct_struct *bacct;
 #endif
 	struct user_namespace *user_ns;
+	struct work_struct proc_work;
 	kgid_t pid_gid;
 	int hide_pid;
 	int reboot;	/* group exit code if this pidns was rebooted */
diff --git a/kernel/fork.c b/kernel/fork.c
index 7798c247f4b9..666dc8b06606 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1476,8 +1476,6 @@ bad_fork_cleanup_io:
 	if (p->io_context)
 		exit_io_context(p);
 bad_fork_cleanup_namespaces:
-	if (unlikely(clone_flags & CLONE_NEWPID))
-		pid_ns_release_proc(p->nsproxy->pid_ns);
 	exit_task_namespaces(p);
 bad_fork_cleanup_mm:
 	if (p->mm)
diff --git a/kernel/pid.c b/kernel/pid.c
index 3a5f238c1ca0..e957f8b09136 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -36,6 +36,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/init_task.h>
 #include <linux/syscalls.h>
+#include <linux/proc_fs.h>
 
 #define pid_hashfn(nr, ns)	\
 	hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
@@ -270,8 +271,12 @@ void free_pid(struct pid *pid)
 	unsigned long flags;
 
 	spin_lock_irqsave(&pidmap_lock, flags);
-	for (i = 0; i <= pid->level; i++)
-		hlist_del_rcu(&pid->numbers[i].pid_chain);
+	for (i = 0; i <= pid->level; i++) {
+		struct upid *upid = pid->numbers + i;
+		hlist_del_rcu(&upid->pid_chain);
+		if (--upid->ns->nr_hashed == 0)
+			schedule_work(&upid->ns->proc_work);
+	}
 	spin_unlock_irqrestore(&pidmap_lock, flags);
 
 	for (i = 0; i <= pid->level; i++)
@@ -293,6 +298,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 		goto out;
 
 	tmp = ns;
+	pid->level = ns->level;
 	for (i = ns->level; i >= 0; i--) {
 		nr = alloc_pidmap(tmp);
 		if (nr < 0)
@@ -303,17 +309,23 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 		tmp = tmp->parent;
 	}
 
+	if (unlikely(is_child_reaper(pid))) {
+		if (pid_ns_prepare_proc(ns))
+			goto out_free;
+	}
+
 	get_pid_ns(ns);
-	pid->level = ns->level;
 	atomic_set(&pid->count, 1);
 	for (type = 0; type < PIDTYPE_MAX; ++type)
 		INIT_HLIST_HEAD(&pid->tasks[type]);
 
 	upid = pid->numbers + ns->level;
 	spin_lock_irq(&pidmap_lock);
-	for ( ; upid >= pid->numbers; --upid)
+	for ( ; upid >= pid->numbers; --upid) {
 		hlist_add_head_rcu(&upid->pid_chain,
 				&pid_hash[pid_hashfn(upid->nr, upid->ns)]);
+		upid->ns->nr_hashed++;
+	}
 	spin_unlock_irq(&pidmap_lock);
 
 out:
@@ -570,6 +582,7 @@ void __init pidmap_init(void)
 	/* Reserve PID 0. We never call free_pidmap(0) */
 	set_bit(0, init_pid_ns.pidmap[0].page);
 	atomic_dec(&init_pid_ns.pidmap[0].nr_free);
+	init_pid_ns.nr_hashed = 1;
 
 	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
 			SLAB_HWCACHE_ALIGN | SLAB_PANIC);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index b2604950aa50..84591cfeefc1 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -72,6 +72,12 @@ err_alloc:
 	return NULL;
 }
 
+static void proc_cleanup_work(struct work_struct *work)
+{
+	struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work);
+	pid_ns_release_proc(ns);
+}
+
 /* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
 #define MAX_PID_NS_LEVEL 32
 
@@ -105,6 +111,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	ns->level = level;
 	ns->parent = get_pid_ns(parent_pid_ns);
 	ns->user_ns = get_user_ns(user_ns);
+	INIT_WORK(&ns->proc_work, proc_cleanup_work);
 
 	set_bit(0, ns->pidmap[0].page);
 	atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
@@ -112,15 +119,8 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	for (i = 1; i < PIDMAP_ENTRIES; i++)
 		atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
 
-	err = pid_ns_prepare_proc(ns);
-	if (err)
-		goto out_put_parent_pid_ns;
-
 	return ns;
 
-out_put_parent_pid_ns:
-	put_pid_ns(parent_pid_ns);
-	put_user_ns(user_ns);
 out_free_map:
 	kfree(ns->pidmap[0].page);
 out_free:
-- 
cgit v1.2.3-55-g7522


From 57e8391d327609cbf12d843259c968b9e5c1838f Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Sun, 7 Mar 2010 18:17:03 -0800
Subject: pidns: Add setns support

- Pid namespaces are designed to be inescapable so verify that the
  passed in pid namespace is a child of the currently active
  pid namespace or the currently active pid namespace itself.

  Allowing the currently active pid namespace is important so
  the effects of an earlier setns can be cancelled.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/proc/namespaces.c    |  3 +++
 include/linux/proc_fs.h |  1 +
 kernel/pid_namespace.c  | 54 +++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 58 insertions(+)

(limited to 'include')

diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index b178ed733c36..85ca047e35f1 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -24,6 +24,9 @@ static const struct proc_ns_operations *ns_entries[] = {
 #ifdef CONFIG_IPC_NS
 	&ipcns_operations,
 #endif
+#ifdef CONFIG_PID_NS
+	&pidns_operations,
+#endif
 };
 
 static const struct file_operations ns_file_operations = {
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 3fd2e871ff1b..acaafcd40aa5 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -251,6 +251,7 @@ struct proc_ns_operations {
 extern const struct proc_ns_operations netns_operations;
 extern const struct proc_ns_operations utsns_operations;
 extern const struct proc_ns_operations ipcns_operations;
+extern const struct proc_ns_operations pidns_operations;
 
 union proc_op {
 	int (*proc_get_link)(struct dentry *, struct path *);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 0dbbc66b6ec6..f78fc48c86bc 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -301,6 +301,60 @@ int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
 	return 0;
 }
 
+static void *pidns_get(struct task_struct *task)
+{
+	struct pid_namespace *ns;
+
+	rcu_read_lock();
+	ns = get_pid_ns(task_active_pid_ns(task));
+	rcu_read_unlock();
+
+	return ns;
+}
+
+static void pidns_put(void *ns)
+{
+	put_pid_ns(ns);
+}
+
+static int pidns_install(struct nsproxy *nsproxy, void *ns)
+{
+	struct pid_namespace *active = task_active_pid_ns(current);
+	struct pid_namespace *ancestor, *new = ns;
+
+	if (!ns_capable(new->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/*
+	 * Only allow entering the current active pid namespace
+	 * or a child of the current active pid namespace.
+	 *
+	 * This is required for fork to return a usable pid value and
+	 * this maintains the property that processes and their
+	 * children can not escape their current pid namespace.
+	 */
+	if (new->level < active->level)
+		return -EINVAL;
+
+	ancestor = new;
+	while (ancestor->level > active->level)
+		ancestor = ancestor->parent;
+	if (ancestor != active)
+		return -EINVAL;
+
+	put_pid_ns(nsproxy->pid_ns);
+	nsproxy->pid_ns = get_pid_ns(new);
+	return 0;
+}
+
+const struct proc_ns_operations pidns_operations = {
+	.name		= "pid",
+	.type		= CLONE_NEWPID,
+	.get		= pidns_get,
+	.put		= pidns_put,
+	.install	= pidns_install,
+};
+
 static __init int pid_namespaces_init(void)
 {
 	pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
-- 
cgit v1.2.3-55-g7522


From 8823c079ba7136dc1948d6f6dcb5f8022bde438e Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Sun, 7 Mar 2010 18:49:36 -0800
Subject: vfs: Add setns support for the mount namespace

setns support for the mount namespace is a little tricky as an
arbitrary decision must be made about what to set fs->root and
fs->pwd to, as there is no expectation of a relationship between
the two mount namespaces.  Therefore I arbitrarily find the root
mount point, and follow every mount on top of it to find the top
of the mount stack.  Then I set fs->root and fs->pwd to that
location.  The topmost root of the mount stack seems like a
reasonable place to be.

Bind mount support for the mount namespace inodes has the
possibility of creating circular dependencies between mount
namespaces.  Circular dependencies can result in loops that
prevent mount namespaces from every being freed.  I avoid
creating those circular dependencies by adding a sequence number
to the mount namespace and require all bind mounts be of a
younger mount namespace into an older mount namespace.

Add a helper function proc_ns_inode so it is possible to
detect when we are attempting to bind mound a namespace inode.

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/mount.h              |  1 +
 fs/namespace.c          | 95 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/proc/namespaces.c    |  5 +++
 include/linux/proc_fs.h |  7 ++++
 4 files changed, 108 insertions(+)

(limited to 'include')

diff --git a/fs/mount.h b/fs/mount.h
index 4f291f9de641..e9c37dd3d00d 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -6,6 +6,7 @@ struct mnt_namespace {
 	atomic_t		count;
 	struct mount *	root;
 	struct list_head	list;
+	u64			seq;	/* Sequence number to prevent loops */
 	wait_queue_head_t poll;
 	int event;
 };
diff --git a/fs/namespace.c b/fs/namespace.c
index 24960626bb6b..d287e7e74644 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -20,6 +20,7 @@
 #include <linux/fs_struct.h>	/* get_fs_root et.al. */
 #include <linux/fsnotify.h>	/* fsnotify_vfsmount_delete */
 #include <linux/uaccess.h>
+#include <linux/proc_fs.h>
 #include "pnode.h"
 #include "internal.h"
 
@@ -1308,6 +1309,26 @@ static int mount_is_safe(struct path *path)
 #endif
 }
 
+static bool mnt_ns_loop(struct path *path)
+{
+	/* Could bind mounting the mount namespace inode cause a
+	 * mount namespace loop?
+	 */
+	struct inode *inode = path->dentry->d_inode;
+	struct proc_inode *ei;
+	struct mnt_namespace *mnt_ns;
+
+	if (!proc_ns_inode(inode))
+		return false;
+
+	ei = PROC_I(inode);
+	if (ei->ns_ops != &mntns_operations)
+		return false;
+
+	mnt_ns = ei->ns;
+	return current->nsproxy->mnt_ns->seq >= mnt_ns->seq;
+}
+
 struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 					int flag)
 {
@@ -1655,6 +1676,10 @@ static int do_loopback(struct path *path, const char *old_name,
 	if (err)
 		return err;
 
+	err = -EINVAL;
+	if (mnt_ns_loop(&old_path))
+		goto out; 
+
 	err = lock_mount(path);
 	if (err)
 		goto out;
@@ -2261,6 +2286,15 @@ dput_out:
 	return retval;
 }
 
+/*
+ * Assign a sequence number so we can detect when we attempt to bind
+ * mount a reference to an older mount namespace into the current
+ * mount namespace, preventing reference counting loops.  A 64bit
+ * number incrementing at 10Ghz will take 12,427 years to wrap which
+ * is effectively never, so we can ignore the possibility.
+ */
+static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1);
+
 static struct mnt_namespace *alloc_mnt_ns(void)
 {
 	struct mnt_namespace *new_ns;
@@ -2268,6 +2302,7 @@ static struct mnt_namespace *alloc_mnt_ns(void)
 	new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
 	if (!new_ns)
 		return ERR_PTR(-ENOMEM);
+	new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
 	atomic_set(&new_ns->count, 1);
 	new_ns->root = NULL;
 	INIT_LIST_HEAD(&new_ns->list);
@@ -2681,3 +2716,63 @@ bool our_mnt(struct vfsmount *mnt)
 {
 	return check_mnt(real_mount(mnt));
 }
+
+static void *mntns_get(struct task_struct *task)
+{
+	struct mnt_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	rcu_read_lock();
+	nsproxy = task_nsproxy(task);
+	if (nsproxy) {
+		ns = nsproxy->mnt_ns;
+		get_mnt_ns(ns);
+	}
+	rcu_read_unlock();
+
+	return ns;
+}
+
+static void mntns_put(void *ns)
+{
+	put_mnt_ns(ns);
+}
+
+static int mntns_install(struct nsproxy *nsproxy, void *ns)
+{
+	struct fs_struct *fs = current->fs;
+	struct mnt_namespace *mnt_ns = ns;
+	struct path root;
+
+	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_CHROOT))
+		return -EINVAL;
+
+	if (fs->users != 1)
+		return -EINVAL;
+
+	get_mnt_ns(mnt_ns);
+	put_mnt_ns(nsproxy->mnt_ns);
+	nsproxy->mnt_ns = mnt_ns;
+
+	/* Find the root */
+	root.mnt    = &mnt_ns->root->mnt;
+	root.dentry = mnt_ns->root->mnt.mnt_root;
+	path_get(&root);
+	while(d_mountpoint(root.dentry) && follow_down_one(&root))
+		;
+
+	/* Update the pwd and root */
+	set_fs_pwd(fs, &root);
+	set_fs_root(fs, &root);
+
+	path_put(&root);
+	return 0;
+}
+
+const struct proc_ns_operations mntns_operations = {
+	.name		= "mnt",
+	.type		= CLONE_NEWNS,
+	.get		= mntns_get,
+	.put		= mntns_put,
+	.install	= mntns_install,
+};
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 85ca047e35f1..2a17fd9ae6a9 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -27,6 +27,7 @@ static const struct proc_ns_operations *ns_entries[] = {
 #ifdef CONFIG_PID_NS
 	&pidns_operations,
 #endif
+	&mntns_operations,
 };
 
 static const struct file_operations ns_file_operations = {
@@ -201,3 +202,7 @@ out_invalid:
 	return ERR_PTR(-EINVAL);
 }
 
+bool proc_ns_inode(struct inode *inode)
+{
+	return inode->i_fop == &ns_file_operations;
+}
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index acaafcd40aa5..9014c041e752 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -174,6 +174,7 @@ extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
 	struct proc_dir_entry *parent);
 
 extern struct file *proc_ns_fget(int fd);
+extern bool proc_ns_inode(struct inode *inode);
 
 #else
 
@@ -229,6 +230,11 @@ static inline struct file *proc_ns_fget(int fd)
 	return ERR_PTR(-EINVAL);
 }
 
+static inline bool proc_ns_inode(struct inode *inode)
+{
+	return false;
+}
+
 #endif /* CONFIG_PROC_FS */
 
 #if !defined(CONFIG_PROC_KCORE)
@@ -252,6 +258,7 @@ extern const struct proc_ns_operations netns_operations;
 extern const struct proc_ns_operations utsns_operations;
 extern const struct proc_ns_operations ipcns_operations;
 extern const struct proc_ns_operations pidns_operations;
+extern const struct proc_ns_operations mntns_operations;
 
 union proc_op {
 	int (*proc_get_link)(struct dentry *, struct path *);
-- 
cgit v1.2.3-55-g7522


From 771b1371686e0a63e938ada28de020b9a0040f55 Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Thu, 26 Jul 2012 21:08:32 -0700
Subject: vfs: Add a user namespace reference from struct mnt_namespace

This will allow for support for unprivileged mounts in a new user namespace.

Acked-by: "Serge E. Hallyn" <serge@hallyn.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/mount.h                    |  1 +
 fs/namespace.c                | 24 ++++++++++++++++--------
 include/linux/mnt_namespace.h |  3 ++-
 kernel/nsproxy.c              |  2 +-
 4 files changed, 20 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/mount.h b/fs/mount.h
index e9c37dd3d00d..630fafc616bb 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -6,6 +6,7 @@ struct mnt_namespace {
 	atomic_t		count;
 	struct mount *	root;
 	struct list_head	list;
+	struct user_namespace	*user_ns;
 	u64			seq;	/* Sequence number to prevent loops */
 	wait_queue_head_t poll;
 	int event;
diff --git a/fs/namespace.c b/fs/namespace.c
index d287e7e74644..207c7ba84ad3 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -12,6 +12,7 @@
 #include <linux/export.h>
 #include <linux/capability.h>
 #include <linux/mnt_namespace.h>
+#include <linux/user_namespace.h>
 #include <linux/namei.h>
 #include <linux/security.h>
 #include <linux/idr.h>
@@ -2286,6 +2287,12 @@ dput_out:
 	return retval;
 }
 
+static void free_mnt_ns(struct mnt_namespace *ns)
+{
+	put_user_ns(ns->user_ns);
+	kfree(ns);
+}
+
 /*
  * Assign a sequence number so we can detect when we attempt to bind
  * mount a reference to an older mount namespace into the current
@@ -2295,7 +2302,7 @@ dput_out:
  */
 static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1);
 
-static struct mnt_namespace *alloc_mnt_ns(void)
+static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
 {
 	struct mnt_namespace *new_ns;
 
@@ -2308,6 +2315,7 @@ static struct mnt_namespace *alloc_mnt_ns(void)
 	INIT_LIST_HEAD(&new_ns->list);
 	init_waitqueue_head(&new_ns->poll);
 	new_ns->event = 0;
+	new_ns->user_ns = get_user_ns(user_ns);
 	return new_ns;
 }
 
@@ -2316,7 +2324,7 @@ static struct mnt_namespace *alloc_mnt_ns(void)
  * copied from the namespace of the passed in task structure.
  */
 static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
-		struct fs_struct *fs)
+		struct user_namespace *user_ns, struct fs_struct *fs)
 {
 	struct mnt_namespace *new_ns;
 	struct vfsmount *rootmnt = NULL, *pwdmnt = NULL;
@@ -2324,7 +2332,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	struct mount *old = mnt_ns->root;
 	struct mount *new;
 
-	new_ns = alloc_mnt_ns();
+	new_ns = alloc_mnt_ns(user_ns);
 	if (IS_ERR(new_ns))
 		return new_ns;
 
@@ -2333,7 +2341,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	new = copy_tree(old, old->mnt.mnt_root, CL_COPY_ALL | CL_EXPIRE);
 	if (IS_ERR(new)) {
 		up_write(&namespace_sem);
-		kfree(new_ns);
+		free_mnt_ns(new_ns);
 		return ERR_CAST(new);
 	}
 	new_ns->root = new;
@@ -2374,7 +2382,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 }
 
 struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
-		struct fs_struct *new_fs)
+		struct user_namespace *user_ns, struct fs_struct *new_fs)
 {
 	struct mnt_namespace *new_ns;
 
@@ -2384,7 +2392,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 	if (!(flags & CLONE_NEWNS))
 		return ns;
 
-	new_ns = dup_mnt_ns(ns, new_fs);
+	new_ns = dup_mnt_ns(ns, user_ns, new_fs);
 
 	put_mnt_ns(ns);
 	return new_ns;
@@ -2396,7 +2404,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
  */
 static struct mnt_namespace *create_mnt_ns(struct vfsmount *m)
 {
-	struct mnt_namespace *new_ns = alloc_mnt_ns();
+	struct mnt_namespace *new_ns = alloc_mnt_ns(&init_user_ns);
 	if (!IS_ERR(new_ns)) {
 		struct mount *mnt = real_mount(m);
 		mnt->mnt_ns = new_ns;
@@ -2682,7 +2690,7 @@ void put_mnt_ns(struct mnt_namespace *ns)
 	br_write_unlock(&vfsmount_lock);
 	up_write(&namespace_sem);
 	release_mounts(&umount_list);
-	kfree(ns);
+	free_mnt_ns(ns);
 }
 
 struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
index 5a8e3903d770..12b2ab510323 100644
--- a/include/linux/mnt_namespace.h
+++ b/include/linux/mnt_namespace.h
@@ -4,9 +4,10 @@
 
 struct mnt_namespace;
 struct fs_struct;
+struct user_namespace;
 
 extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
-		struct fs_struct *);
+		struct user_namespace *, struct fs_struct *);
 extern void put_mnt_ns(struct mnt_namespace *ns);
 
 extern const struct file_operations proc_mounts_operations;
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index b8d4d8709d70..7f8b051fc19f 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -66,7 +66,7 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 	if (!new_nsp)
 		return ERR_PTR(-ENOMEM);
 
-	new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, new_fs);
+	new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, task_cred_xxx(tsk, user_ns), new_fs);
 	if (IS_ERR(new_nsp->mnt_ns)) {
 		err = PTR_ERR(new_nsp->mnt_ns);
 		goto out_ns;
-- 
cgit v1.2.3-55-g7522


From 0c55cfc4166d9a0f38de779bd4d75a90afbe7734 Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Thu, 26 Jul 2012 21:42:03 -0700
Subject: vfs: Allow unprivileged manipulation of the mount namespace.

- Add a filesystem flag to mark filesystems that are safe to mount as
  an unprivileged user.

- Add a filesystem flag to mark filesystems that don't need MNT_NODEV
  when mounted by an unprivileged user.

- Relax the permission checks to allow unprivileged users that have
  CAP_SYS_ADMIN permissions in the user namespace referred to by the
  current mount namespace to be allowed to mount, unmount, and move
  filesystems.

Acked-by: "Serge E. Hallyn" <serge@hallyn.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/namespace.c     | 69 ++++++++++++++++++++++++++++++++++--------------------
 include/linux/fs.h |  2 ++
 2 files changed, 45 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index 4dfcaf05d17c..9ddc86f93221 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1269,7 +1269,7 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
 		goto dput_and_out;
 
 	retval = -EPERM;
-	if (!capable(CAP_SYS_ADMIN))
+	if (!ns_capable(mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
 		goto dput_and_out;
 
 	retval = do_umount(mnt, flags);
@@ -1295,7 +1295,7 @@ SYSCALL_DEFINE1(oldumount, char __user *, name)
 
 static int mount_is_safe(struct path *path)
 {
-	if (capable(CAP_SYS_ADMIN))
+	if (ns_capable(real_mount(path->mnt)->mnt_ns->user_ns, CAP_SYS_ADMIN))
 		return 0;
 	return -EPERM;
 #ifdef notyet
@@ -1633,7 +1633,7 @@ static int do_change_type(struct path *path, int flag)
 	int type;
 	int err = 0;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!ns_capable(mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	if (path->dentry != path->mnt->mnt_root)
@@ -1797,7 +1797,7 @@ static int do_move_mount(struct path *path, const char *old_name)
 	struct mount *p;
 	struct mount *old;
 	int err = 0;
-	if (!capable(CAP_SYS_ADMIN))
+	if (!ns_capable(real_mount(path->mnt)->mnt_ns->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 	if (!old_name || !*old_name)
 		return -EINVAL;
@@ -1884,21 +1884,6 @@ static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
 	return ERR_PTR(err);
 }
 
-static struct vfsmount *
-do_kern_mount(const char *fstype, int flags, const char *name, void *data)
-{
-	struct file_system_type *type = get_fs_type(fstype);
-	struct vfsmount *mnt;
-	if (!type)
-		return ERR_PTR(-ENODEV);
-	mnt = vfs_kern_mount(type, flags, name, data);
-	if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
-	    !mnt->mnt_sb->s_subtype)
-		mnt = fs_set_subtype(mnt, fstype);
-	put_filesystem(type);
-	return mnt;
-}
-
 /*
  * add a mount into a namespace's mount tree
  */
@@ -1944,20 +1929,46 @@ unlock:
  * create a new mount for userspace and request it to be added into the
  * namespace's tree
  */
-static int do_new_mount(struct path *path, const char *type, int flags,
+static int do_new_mount(struct path *path, const char *fstype, int flags,
 			int mnt_flags, const char *name, void *data)
 {
+	struct file_system_type *type;
+	struct user_namespace *user_ns;
 	struct vfsmount *mnt;
 	int err;
 
-	if (!type)
+	if (!fstype)
 		return -EINVAL;
 
 	/* we need capabilities... */
-	if (!capable(CAP_SYS_ADMIN))
+	user_ns = real_mount(path->mnt)->mnt_ns->user_ns;
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	mnt = do_kern_mount(type, flags, name, data);
+	type = get_fs_type(fstype);
+	if (!type)
+		return -ENODEV;
+
+	if (user_ns != &init_user_ns) {
+		if (!(type->fs_flags & FS_USERNS_MOUNT)) {
+			put_filesystem(type);
+			return -EPERM;
+		}
+		/* Only in special cases allow devices from mounts
+		 * created outside the initial user namespace.
+		 */
+		if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) {
+			flags |= MS_NODEV;
+			mnt_flags |= MNT_NODEV;
+		}
+	}
+
+	mnt = vfs_kern_mount(type, flags, name, data);
+	if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
+	    !mnt->mnt_sb->s_subtype)
+		mnt = fs_set_subtype(mnt, fstype);
+
+	put_filesystem(type);
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);
 
@@ -2549,7 +2560,7 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	struct mount *new_mnt, *root_mnt;
 	int error;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	error = user_path_dir(new_root, &new);
@@ -2631,8 +2642,13 @@ static void __init init_mount_tree(void)
 	struct vfsmount *mnt;
 	struct mnt_namespace *ns;
 	struct path root;
+	struct file_system_type *type;
 
-	mnt = do_kern_mount("rootfs", 0, "rootfs", NULL);
+	type = get_fs_type("rootfs");
+	if (!type)
+		panic("Can't find rootfs type");
+	mnt = vfs_kern_mount(type, 0, "rootfs", NULL);
+	put_filesystem(type);
 	if (IS_ERR(mnt))
 		panic("Can't create rootfs");
 
@@ -2757,7 +2773,8 @@ static int mntns_install(struct nsproxy *nsproxy, void *ns)
 	struct mnt_namespace *mnt_ns = ns;
 	struct path root;
 
-	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_CHROOT))
+	if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) ||
+	    !nsown_capable(CAP_SYS_CHROOT))
 		return -EINVAL;
 
 	if (fs->users != 1)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b33cfc97b9ca..5037aa6817fd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1812,6 +1812,8 @@ struct file_system_type {
 #define FS_REQUIRES_DEV		1 
 #define FS_BINARY_MOUNTDATA	2
 #define FS_HAS_SUBTYPE		4
+#define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
+#define FS_USERNS_DEV_MOUNT	16 /* A userns mount does not imply MNT_NODEV */
 #define FS_REVAL_DOT		16384	/* Check the paths ".", ".." for staleness */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	struct dentry *(*mount) (struct file_system_type *, int,
-- 
cgit v1.2.3-55-g7522


From 5a306f5887d5fd840beb8ea872897fa89e8fcdef Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Wed, 14 Nov 2012 23:22:21 +0100
Subject: mac80211: introduce IEEE80211_NUM_TIDS and use it

Introduce IEEE80211_NUM_TIDS in the generic 802.11
header file and use it in place of STA_TID_NUM and
NUM_RX_DATA_QUEUES which are both really the number
of TIDs.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  |  2 ++
 net/mac80211/agg-rx.c      |  2 +-
 net/mac80211/agg-tx.c      | 12 ++++++------
 net/mac80211/debugfs_key.c |  6 +++---
 net/mac80211/debugfs_sta.c | 10 +++++-----
 net/mac80211/ht.c          |  4 ++--
 net/mac80211/key.c         | 10 +++++-----
 net/mac80211/key.h         |  8 +++-----
 net/mac80211/rx.c          |  4 ++--
 net/mac80211/sta_info.c    | 10 +++++-----
 net/mac80211/sta_info.h    | 19 +++++++++----------
 11 files changed, 43 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 4530d4960953..d68790903b9e 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -131,6 +131,8 @@
 
 #define IEEE80211_MAX_MESH_ID_LEN	32
 
+#define IEEE80211_NUM_TIDS		16
+
 #define IEEE80211_QOS_CTL_LEN		2
 /* 1d tag mask */
 #define IEEE80211_QOS_CTL_TAG1D_MASK		0x0007
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 186d9919b043..808338a1bce5 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -118,7 +118,7 @@ void ieee80211_stop_rx_ba_session(struct ieee80211_vif *vif, u16 ba_rx_bitmap,
 		return;
 	}
 
-	for (i = 0; i < STA_TID_NUM; i++)
+	for (i = 0; i < IEEE80211_NUM_TIDS; i++)
 		if (ba_rx_bitmap & BIT(i))
 			set_bit(i, sta->ampdu_mlme.tid_rx_stop_requested);
 
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 3195a6307f50..4152ed1034b8 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -448,7 +448,7 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid,
 	if (WARN_ON(!local->ops->ampdu_action))
 		return -EINVAL;
 
-	if ((tid >= STA_TID_NUM) ||
+	if ((tid >= IEEE80211_NUM_TIDS) ||
 	    !(local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION) ||
 	    (local->hw.flags & IEEE80211_HW_TX_AMPDU_SETUP_IN_HW))
 		return -EINVAL;
@@ -605,9 +605,9 @@ void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid)
 
 	trace_api_start_tx_ba_cb(sdata, ra, tid);
 
-	if (tid >= STA_TID_NUM) {
+	if (tid >= IEEE80211_NUM_TIDS) {
 		ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n",
-		       tid, STA_TID_NUM);
+		       tid, IEEE80211_NUM_TIDS);
 		return;
 	}
 
@@ -687,7 +687,7 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid)
 	if (!local->ops->ampdu_action)
 		return -EINVAL;
 
-	if (tid >= STA_TID_NUM)
+	if (tid >= IEEE80211_NUM_TIDS)
 		return -EINVAL;
 
 	spin_lock_bh(&sta->lock);
@@ -722,9 +722,9 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid)
 
 	trace_api_stop_tx_ba_cb(sdata, ra, tid);
 
-	if (tid >= STA_TID_NUM) {
+	if (tid >= IEEE80211_NUM_TIDS) {
 		ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n",
-		       tid, STA_TID_NUM);
+		       tid, IEEE80211_NUM_TIDS);
 		return;
 	}
 
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index 090d08ff22c4..2d4235497f1b 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -116,7 +116,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
 				size_t count, loff_t *ppos)
 {
 	struct ieee80211_key *key = file->private_data;
-	char buf[14*NUM_RX_DATA_QUEUES+1], *p = buf;
+	char buf[14*IEEE80211_NUM_TIDS+1], *p = buf;
 	int i, len;
 	const u8 *rpn;
 
@@ -126,7 +126,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
 		len = scnprintf(buf, sizeof(buf), "\n");
 		break;
 	case WLAN_CIPHER_SUITE_TKIP:
-		for (i = 0; i < NUM_RX_DATA_QUEUES; i++)
+		for (i = 0; i < IEEE80211_NUM_TIDS; i++)
 			p += scnprintf(p, sizeof(buf)+buf-p,
 				       "%08x %04x\n",
 				       key->u.tkip.rx[i].iv32,
@@ -134,7 +134,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
 		len = p - buf;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
-		for (i = 0; i < NUM_RX_DATA_QUEUES + 1; i++) {
+		for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) {
 			rpn = key->u.ccmp.rx_pn[i];
 			p += scnprintf(p, sizeof(buf)+buf-p,
 				       "%02x%02x%02x%02x%02x%02x\n",
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 5ccec2c1e9f6..3d103929d41a 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -131,10 +131,10 @@ STA_OPS(connected_time);
 static ssize_t sta_last_seq_ctrl_read(struct file *file, char __user *userbuf,
 				      size_t count, loff_t *ppos)
 {
-	char buf[15*NUM_RX_DATA_QUEUES], *p = buf;
+	char buf[15*IEEE80211_NUM_TIDS], *p = buf;
 	int i;
 	struct sta_info *sta = file->private_data;
-	for (i = 0; i < NUM_RX_DATA_QUEUES; i++)
+	for (i = 0; i < IEEE80211_NUM_TIDS; i++)
 		p += scnprintf(p, sizeof(buf)+buf-p, "%x ",
 			       le16_to_cpu(sta->last_seq_ctrl[i]));
 	p += scnprintf(p, sizeof(buf)+buf-p, "\n");
@@ -145,7 +145,7 @@ STA_OPS(last_seq_ctrl);
 static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
 					size_t count, loff_t *ppos)
 {
-	char buf[71 + STA_TID_NUM * 40], *p = buf;
+	char buf[71 + IEEE80211_NUM_TIDS * 40], *p = buf;
 	int i;
 	struct sta_info *sta = file->private_data;
 	struct tid_ampdu_rx *tid_rx;
@@ -158,7 +158,7 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
 	p += scnprintf(p, sizeof(buf) + buf - p,
 		       "TID\t\tRX active\tDTKN\tSSN\t\tTX\tDTKN\tpending\n");
 
-	for (i = 0; i < STA_TID_NUM; i++) {
+	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
 		tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[i]);
 		tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[i]);
 
@@ -220,7 +220,7 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu
 
 	tid = simple_strtoul(buf, NULL, 0);
 
-	if (tid >= STA_TID_NUM)
+	if (tid >= IEEE80211_NUM_TIDS)
 		return -EINVAL;
 
 	if (tx) {
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index 4b4538d63925..a71d891794a4 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -185,7 +185,7 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, bool tx)
 
 	cancel_work_sync(&sta->ampdu_mlme.work);
 
-	for (i = 0; i <  STA_TID_NUM; i++) {
+	for (i = 0; i <  IEEE80211_NUM_TIDS; i++) {
 		__ieee80211_stop_tx_ba_session(sta, i, WLAN_BACK_INITIATOR, tx);
 		__ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT,
 					       WLAN_REASON_QSTA_LEAVE_QBSS, tx);
@@ -209,7 +209,7 @@ void ieee80211_ba_session_work(struct work_struct *work)
 		return;
 
 	mutex_lock(&sta->ampdu_mlme.mtx);
-	for (tid = 0; tid < STA_TID_NUM; tid++) {
+	for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) {
 		if (test_and_clear_bit(tid, sta->ampdu_mlme.tid_rx_timer_expired))
 			___ieee80211_stop_rx_ba_session(
 				sta, tid, WLAN_BACK_RECIPIENT,
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 0f18ef59392d..619c5d697999 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -339,7 +339,7 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 		key->conf.iv_len = TKIP_IV_LEN;
 		key->conf.icv_len = TKIP_ICV_LEN;
 		if (seq) {
-			for (i = 0; i < NUM_RX_DATA_QUEUES; i++) {
+			for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
 				key->u.tkip.rx[i].iv32 =
 					get_unaligned_le32(&seq[2]);
 				key->u.tkip.rx[i].iv16 =
@@ -352,7 +352,7 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 		key->conf.iv_len = CCMP_HDR_LEN;
 		key->conf.icv_len = CCMP_MIC_LEN;
 		if (seq) {
-			for (i = 0; i < NUM_RX_DATA_QUEUES + 1; i++)
+			for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++)
 				for (j = 0; j < CCMP_PN_LEN; j++)
 					key->u.ccmp.rx_pn[i][j] =
 						seq[CCMP_PN_LEN - j - 1];
@@ -655,16 +655,16 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf,
 
 	switch (key->conf.cipher) {
 	case WLAN_CIPHER_SUITE_TKIP:
-		if (WARN_ON(tid < 0 || tid >= NUM_RX_DATA_QUEUES))
+		if (WARN_ON(tid < 0 || tid >= IEEE80211_NUM_TIDS))
 			return;
 		seq->tkip.iv32 = key->u.tkip.rx[tid].iv32;
 		seq->tkip.iv16 = key->u.tkip.rx[tid].iv16;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
-		if (WARN_ON(tid < -1 || tid >= NUM_RX_DATA_QUEUES))
+		if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS))
 			return;
 		if (tid < 0)
-			pn = key->u.ccmp.rx_pn[NUM_RX_DATA_QUEUES];
+			pn = key->u.ccmp.rx_pn[IEEE80211_NUM_TIDS];
 		else
 			pn = key->u.ccmp.rx_pn[tid];
 		memcpy(seq->ccmp.pn, pn, CCMP_PN_LEN);
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index 7d4e31f037d7..7cff0d3a519c 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -30,8 +30,6 @@
 #define TKIP_ICV_LEN		4
 #define CMAC_PN_LEN		6
 
-#define NUM_RX_DATA_QUEUES	16
-
 struct ieee80211_local;
 struct ieee80211_sub_if_data;
 struct sta_info;
@@ -82,17 +80,17 @@ struct ieee80211_key {
 			struct tkip_ctx tx;
 
 			/* last received RSC */
-			struct tkip_ctx rx[NUM_RX_DATA_QUEUES];
+			struct tkip_ctx rx[IEEE80211_NUM_TIDS];
 		} tkip;
 		struct {
 			atomic64_t tx_pn;
 			/*
 			 * Last received packet number. The first
-			 * NUM_RX_DATA_QUEUES counters are used with Data
+			 * IEEE80211_NUM_TIDS counters are used with Data
 			 * frames and the last counter is used with Robust
 			 * Management frames.
 			 */
-			u8 rx_pn[NUM_RX_DATA_QUEUES + 1][CCMP_PN_LEN];
+			u8 rx_pn[IEEE80211_NUM_TIDS + 1][CCMP_PN_LEN];
 			struct crypto_cipher *tfm;
 			u32 replays; /* dot11RSNAStatsCCMPReplays */
 		} ccmp;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index e3daee8fdf7a..8480bbf1a707 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -408,10 +408,10 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx)
 		 *
 		 * We also use that counter for non-QoS STAs.
 		 */
-		seqno_idx = NUM_RX_DATA_QUEUES;
+		seqno_idx = IEEE80211_NUM_TIDS;
 		security_idx = 0;
 		if (ieee80211_is_mgmt(hdr->frame_control))
-			security_idx = NUM_RX_DATA_QUEUES;
+			security_idx = IEEE80211_NUM_TIDS;
 		tid = 0;
 	}
 
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index f7bb54f9ab72..a0836d7187c1 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -142,7 +142,7 @@ static void free_sta_work(struct work_struct *wk)
 	 * drivers have to handle aggregation stop being requested, followed
 	 * directly by station destruction.
 	 */
-	for (i = 0; i < STA_TID_NUM; i++) {
+	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
 		tid_tx = rcu_dereference_raw(sta->ampdu_mlme.tid_tx[i]);
 		if (!tid_tx)
 			continue;
@@ -330,7 +330,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 		return NULL;
 	}
 
-	for (i = 0; i < STA_TID_NUM; i++) {
+	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
 		/*
 		 * timer_to_tid must be initialized with identity mapping
 		 * to enable session_timer's data differentiation. See
@@ -343,7 +343,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 		skb_queue_head_init(&sta->tx_filtered[i]);
 	}
 
-	for (i = 0; i < NUM_RX_DATA_QUEUES; i++)
+	for (i = 0; i < IEEE80211_NUM_TIDS; i++)
 		sta->last_seq_ctrl[i] = cpu_to_le16(USHRT_MAX);
 
 	sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr);
@@ -985,7 +985,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 
 	clear_sta_flag(sta, WLAN_STA_SP);
 
-	BUILD_BUG_ON(BITS_TO_LONGS(STA_TID_NUM) > 1);
+	BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1);
 	sta->driver_buffered_tids = 0;
 
 	if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS))
@@ -1369,7 +1369,7 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta,
 {
 	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
 
-	if (WARN_ON(tid >= STA_TID_NUM))
+	if (WARN_ON(tid >= IEEE80211_NUM_TIDS))
 		return;
 
 	if (buffered)
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index c88f161f8118..776f3d0b4a47 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -80,7 +80,6 @@ enum ieee80211_sta_info_flags {
 	WLAN_STA_TOFFSET_KNOWN,
 };
 
-#define STA_TID_NUM 16
 #define ADDBA_RESP_INTERVAL HZ
 #define HT_AGG_MAX_RETRIES		15
 #define HT_AGG_BURST_RETRIES		3
@@ -197,15 +196,15 @@ struct tid_ampdu_rx {
 struct sta_ampdu_mlme {
 	struct mutex mtx;
 	/* rx */
-	struct tid_ampdu_rx __rcu *tid_rx[STA_TID_NUM];
-	unsigned long tid_rx_timer_expired[BITS_TO_LONGS(STA_TID_NUM)];
-	unsigned long tid_rx_stop_requested[BITS_TO_LONGS(STA_TID_NUM)];
+	struct tid_ampdu_rx __rcu *tid_rx[IEEE80211_NUM_TIDS];
+	unsigned long tid_rx_timer_expired[BITS_TO_LONGS(IEEE80211_NUM_TIDS)];
+	unsigned long tid_rx_stop_requested[BITS_TO_LONGS(IEEE80211_NUM_TIDS)];
 	/* tx */
 	struct work_struct work;
-	struct tid_ampdu_tx __rcu *tid_tx[STA_TID_NUM];
-	struct tid_ampdu_tx *tid_start_tx[STA_TID_NUM];
-	unsigned long last_addba_req_time[STA_TID_NUM];
-	u8 addba_req_num[STA_TID_NUM];
+	struct tid_ampdu_tx __rcu *tid_tx[IEEE80211_NUM_TIDS];
+	struct tid_ampdu_tx *tid_start_tx[IEEE80211_NUM_TIDS];
+	unsigned long last_addba_req_time[IEEE80211_NUM_TIDS];
+	u8 addba_req_num[IEEE80211_NUM_TIDS];
 	u8 dialog_token_allocator;
 };
 
@@ -330,7 +329,7 @@ struct sta_info {
 	int last_signal;
 	struct ewma avg_signal;
 	/* Plus 1 for non-QoS frames */
-	__le16 last_seq_ctrl[NUM_RX_DATA_QUEUES + 1];
+	__le16 last_seq_ctrl[IEEE80211_NUM_TIDS + 1];
 
 	/* Updated from TX status path only, no locking requirements */
 	unsigned long tx_filtered_count;
@@ -351,7 +350,7 @@ struct sta_info {
 	 * Aggregation information, locked with lock.
 	 */
 	struct sta_ampdu_mlme ampdu_mlme;
-	u8 timer_to_tid[STA_TID_NUM];
+	u8 timer_to_tid[IEEE80211_NUM_TIDS];
 
 #ifdef CONFIG_MAC80211_MESH
 	/*
-- 
cgit v1.2.3-55-g7522


From 90b9e446fbb64630c72cab48c007d7081aec2533 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Fri, 16 Nov 2012 10:09:08 +0100
Subject: mac80211: support radiotap vendor namespace RX data

In some cases, in particular for experimentation, it
can be useful to be able to add vendor namespace data
to received frames in addition to the normal radiotap
data.

Allow doing this through mac80211 by adding fields to
the RX status descriptor that describe the data while
the data itself is prepended to the frame.

Also add some example code to hwsim, but don't enable
it because it doesn't use a proper OUI identifier.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c | 33 +++++++++++++++-
 include/net/mac80211.h                | 12 ++++++
 net/mac80211/rx.c                     | 71 +++++++++++++++++++++++++++++------
 3 files changed, 103 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index ce522aa93af7..c242f5a9b8bc 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -751,7 +751,11 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw,
 				continue;
 		}
 
-		nskb = skb_copy(skb, GFP_ATOMIC);
+		/*
+		 * reserve some space for our vendor and the normal
+		 * radiotap header, since we're copying anyway
+		 */
+		nskb = skb_copy_expand(skb, 64, 0, GFP_ATOMIC);
 		if (nskb == NULL)
 			continue;
 
@@ -769,6 +773,33 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw,
 				(data->tsf_offset - data2->tsf_offset) +
 				24 * 8 * 10 / txrate->bitrate);
 
+#if 0
+		/*
+		 * Don't enable this code by default as the OUI 00:00:00
+		 * is registered to Xerox so we shouldn't use it here, it
+		 * might find its way into pcap files.
+		 * Note that this code requires the headroom in the SKB
+		 * that was allocated earlier.
+		 */
+		rx_status.vendor_radiotap_oui[0] = 0x00;
+		rx_status.vendor_radiotap_oui[1] = 0x00;
+		rx_status.vendor_radiotap_oui[2] = 0x00;
+		rx_status.vendor_radiotap_subns = 127;
+		/*
+		 * Radiotap vendor namespaces can (and should) also be
+		 * split into fields by using the standard radiotap
+		 * presence bitmap mechanism. Use just BIT(0) here for
+		 * the presence bitmap.
+		 */
+		rx_status.vendor_radiotap_bitmap = BIT(0);
+		/* We have 8 bytes of (dummy) data */
+		rx_status.vendor_radiotap_len = 8;
+		/* For testing, also require it to be aligned */
+		rx_status.vendor_radiotap_align = 8;
+		/* push the data */
+		memcpy(skb_push(nskb, 8), "ABCDEFGH", 8);
+#endif
+
 		memcpy(IEEE80211_SKB_RXCB(nskb), &rx_status, sizeof(rx_status));
 		ieee80211_rx_irqsafe(data2->hw, nskb);
 	}
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index b484a6569eac..dd08fbb3cf28 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -789,12 +789,21 @@ enum mac80211_rx_flags {
  * @ampdu_reference: A-MPDU reference number, must be a different value for
  *	each A-MPDU but the same for each subframe within one A-MPDU
  * @ampdu_delimiter_crc: A-MPDU delimiter CRC
+ * @vendor_radiotap_bitmap: radiotap vendor namespace presence bitmap
+ * @vendor_radiotap_len: radiotap vendor namespace length
+ * @vendor_radiotap_align: radiotap vendor namespace alignment. Note
+ *	that the actual data must be at the start of the SKB data
+ *	already.
+ * @vendor_radiotap_oui: radiotap vendor namespace OUI
+ * @vendor_radiotap_subns: radiotap vendor sub namespace
  */
 struct ieee80211_rx_status {
 	u64 mactime;
 	u32 device_timestamp;
 	u32 ampdu_reference;
 	u32 flag;
+	u32 vendor_radiotap_bitmap;
+	u16 vendor_radiotap_len;
 	u16 freq;
 	u8 rate_idx;
 	u8 rx_flags;
@@ -802,6 +811,9 @@ struct ieee80211_rx_status {
 	u8 antenna;
 	s8 signal;
 	u8 ampdu_delimiter_crc;
+	u8 vendor_radiotap_align;
+	u8 vendor_radiotap_oui[3];
+	u8 vendor_radiotap_subns;
 };
 
 /**
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 8480bbf1a707..ec15a4929f7a 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -40,6 +40,8 @@
 static struct sk_buff *remove_monitor_info(struct ieee80211_local *local,
 					   struct sk_buff *skb)
 {
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+
 	if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) {
 		if (likely(skb->len > FCS_LEN))
 			__pskb_trim(skb, skb->len - FCS_LEN);
@@ -51,6 +53,9 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local,
 		}
 	}
 
+	if (status->vendor_radiotap_len)
+		__pskb_pull(skb, status->vendor_radiotap_len);
+
 	return skb;
 }
 
@@ -73,32 +78,48 @@ static inline int should_drop_frame(struct sk_buff *skb, int present_fcs_len)
 }
 
 static int
-ieee80211_rx_radiotap_len(struct ieee80211_local *local,
-			  struct ieee80211_rx_status *status)
+ieee80211_rx_radiotap_space(struct ieee80211_local *local,
+			    struct ieee80211_rx_status *status)
 {
 	int len;
 
 	/* always present fields */
 	len = sizeof(struct ieee80211_radiotap_header) + 9;
 
-	if (ieee80211_have_rx_timestamp(status))
+	/* allocate extra bitmap */
+	if (status->vendor_radiotap_len)
+		len += 4;
+
+	if (ieee80211_have_rx_timestamp(status)) {
+		len = ALIGN(len, 8);
 		len += 8;
+	}
 	if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM)
 		len += 1;
 
-	if (len & 1) /* padding for RX_FLAGS if necessary */
-		len++;
+	/* padding for RX_FLAGS if necessary */
+	len = ALIGN(len, 2);
 
 	if (status->flag & RX_FLAG_HT) /* HT info */
 		len += 3;
 
 	if (status->flag & RX_FLAG_AMPDU_DETAILS) {
-		/* padding */
-		while (len & 3)
-			len++;
+		len = ALIGN(len, 4);
 		len += 8;
 	}
 
+	if (status->vendor_radiotap_len) {
+		if (WARN_ON_ONCE(status->vendor_radiotap_align == 0))
+			status->vendor_radiotap_align = 1;
+		/* align standard part of vendor namespace */
+		len = ALIGN(len, 2);
+		/* allocate standard part of vendor namespace */
+		len += 6;
+		/* align vendor-defined part */
+		len = ALIGN(len, status->vendor_radiotap_align);
+		/* vendor-defined part is already in skb */
+	}
+
 	return len;
 }
 
@@ -132,14 +153,25 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 			    (1 << IEEE80211_RADIOTAP_CHANNEL) |
 			    (1 << IEEE80211_RADIOTAP_ANTENNA) |
 			    (1 << IEEE80211_RADIOTAP_RX_FLAGS));
-	rthdr->it_len = cpu_to_le16(rtap_len);
+	rthdr->it_len = cpu_to_le16(rtap_len + status->vendor_radiotap_len);
 
 	pos = (unsigned char *)(rthdr + 1);
 
+	if (status->vendor_radiotap_len) {
+		rthdr->it_present |=
+			cpu_to_le32(BIT(IEEE80211_RADIOTAP_VENDOR_NAMESPACE)) |
+			cpu_to_le32(BIT(IEEE80211_RADIOTAP_EXT));
+		put_unaligned_le32(status->vendor_radiotap_bitmap, pos);
+		pos += 4;
+	}
+
 	/* the order of the following fields is important */
 
 	/* IEEE80211_RADIOTAP_TSFT */
 	if (ieee80211_have_rx_timestamp(status)) {
+		/* padding */
+		while ((pos - (u8 *)rthdr) & 7)
+			*pos++ = 0;
 		put_unaligned_le64(
 			ieee80211_calculate_rx_timestamp(local, status,
 							 mpdulen, 0),
@@ -211,7 +243,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	/* IEEE80211_RADIOTAP_RX_FLAGS */
 	/* ensure 2 byte alignment for the 2 byte field as required */
 	if ((pos - (u8 *)rthdr) & 1)
-		pos++;
+		*pos++ = 0;
 	if (status->flag & RX_FLAG_FAILED_PLCP_CRC)
 		rx_flags |= IEEE80211_RADIOTAP_F_RX_BADPLCP;
 	put_unaligned_le16(rx_flags, pos);
@@ -261,6 +293,21 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 			*pos++ = 0;
 		*pos++ = 0;
 	}
+
+	if (status->vendor_radiotap_len) {
+		/* ensure 2 byte alignment for the vendor field as required */
+		if ((pos - (u8 *)rthdr) & 1)
+			*pos++ = 0;
+		*pos++ = status->vendor_radiotap_oui[0];
+		*pos++ = status->vendor_radiotap_oui[1];
+		*pos++ = status->vendor_radiotap_oui[2];
+		*pos++ = status->vendor_radiotap_subns;
+		put_unaligned_le16(status->vendor_radiotap_len, pos);
+		pos += 2;
+		/* align the actual payload as requested */
+		while ((pos - (u8 *)rthdr) & (status->vendor_radiotap_align - 1))
+			*pos++ = 0;
+	}
 }
 
 /*
@@ -289,7 +336,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 	 */
 
 	/* room for the radiotap header based on driver features */
-	needed_headroom = ieee80211_rx_radiotap_len(local, status);
+	needed_headroom = ieee80211_rx_radiotap_space(local, status);
 
 	if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS)
 		present_fcs_len = FCS_LEN;
@@ -2593,7 +2640,7 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx,
 		goto out_free_skb;
 
 	/* room for the radiotap header based on driver features */
-	needed_headroom = ieee80211_rx_radiotap_len(local, status);
+	needed_headroom = ieee80211_rx_radiotap_space(local, status);
 
 	if (skb_headroom(skb) < needed_headroom &&
 	    pskb_expand_head(skb, needed_headroom, 0, GFP_ATOMIC))
-- 
cgit v1.2.3-55-g7522


From 3475b0946bd2057497628790d4b4fce4bfdcc304 Mon Sep 17 00:00:00 2001
From: Jouni Malinen
Date: Fri, 16 Nov 2012 22:49:57 +0200
Subject: cfg80211: Add TDLS event to allow drivers to request operations

The NL80211_CMD_TDLS_OPER command was previously used only for userspace
request for the kernel code to perform TDLS operations. However, there
are also cases where the driver may need to request operations from
userspace, e.g., when using security on the AP path. Add a new cfg80211
function for generating a TDLS operation event for drivers to request a
new link to be set up (NL80211_TDLS_SETUP) or an existing link to be
torn down (NL80211_TDLS_TEARDOWN). Drivers can optionally use these
events, e.g., based on noticing data traffic being sent to a peer
station that is seen with good signal strength.

Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 19 ++++++++++++++++++
 include/uapi/linux/nl80211.h |  6 ++++++
 net/wireless/nl80211.c       | 47 ++++++++++++++++++++++++++++++++++++++++++++
 net/wireless/trace.h         | 23 ++++++++++++++++++++++
 4 files changed, 95 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 81d725038f97..8a1aec54e68f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3593,6 +3593,25 @@ bool cfg80211_can_beacon_sec_chan(struct wiphy *wiphy,
 void cfg80211_ch_switch_notify(struct net_device *dev, int freq,
 			       enum nl80211_channel_type type);
 
+/*
+ * cfg80211_tdls_oper_request - request userspace to perform TDLS operation
+ * @dev: the device on which the operation is requested
+ * @peer: the MAC address of the peer device
+ * @oper: the requested TDLS operation (NL80211_TDLS_SETUP or
+ *	NL80211_TDLS_TEARDOWN)
+ * @reason_code: the reason code for teardown request
+ * @gfp: allocation flags
+ *
+ * This function is used to request userspace to perform TDLS operation that
+ * requires knowledge of keys, i.e., link setup or teardown when the AP
+ * connection uses encryption. This is optional mechanism for the driver to use
+ * if it can automatically determine when a TDLS link could be useful (e.g.,
+ * based on traffic and signal strength for a peer).
+ */
+void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer,
+				enum nl80211_tdls_operation oper,
+				u16 reason_code, gfp_t gfp);
+
 /*
  * cfg80211_calculate_bitrate - calculate actual bitrate (in 100Kbps units)
  * @rate: given rate_info to calculate bitrate from
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 06ddc89f026c..1a9a819cfab0 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -526,6 +526,12 @@
  *	of PMKSA caching dandidates.
  *
  * @NL80211_CMD_TDLS_OPER: Perform a high-level TDLS command (e.g. link setup).
+ *	In addition, this can be used as an event to request userspace to take
+ *	actions on TDLS links (set up a new link or tear down an existing one).
+ *	In such events, %NL80211_ATTR_TDLS_OPERATION indicates the requested
+ *	operation, %NL80211_ATTR_MAC contains the peer MAC address, and
+ *	%NL80211_ATTR_REASON_CODE the reason code to be used (only with
+ *	%NL80211_TDLS_TEARDOWN).
  * @NL80211_CMD_TDLS_MGMT: Send a TDLS management frame.
  *
  * @NL80211_CMD_UNEXPECTED_FRAME: Used by an application controlling an AP
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c18b2fc9d492..4c427fa5c450 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -9027,6 +9027,53 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy,
 }
 EXPORT_SYMBOL(cfg80211_report_obss_beacon);
 
+void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer,
+				enum nl80211_tdls_operation oper,
+				u16 reason_code, gfp_t gfp)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct sk_buff *msg;
+	void *hdr;
+	int err;
+
+	trace_cfg80211_tdls_oper_request(wdev->wiphy, dev, peer, oper,
+					 reason_code);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
+	if (!msg)
+		return;
+
+	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_TDLS_OPER);
+	if (!hdr) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
+	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
+	    nla_put_u8(msg, NL80211_ATTR_TDLS_OPERATION, oper) ||
+	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, peer) ||
+	    (reason_code > 0 &&
+	     nla_put_u16(msg, NL80211_ATTR_REASON_CODE, reason_code)))
+		goto nla_put_failure;
+
+	err = genlmsg_end(msg, hdr);
+	if (err < 0) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+				nl80211_mlme_mcgrp.id, gfp);
+	return;
+
+ nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL(cfg80211_tdls_oper_request);
+
 static int nl80211_netlink_notify(struct notifier_block * nb,
 				  unsigned long state,
 				  void *_notify)
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 8e03c6382a8a..f264c20a7090 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2157,6 +2157,29 @@ TRACE_EVENT(cfg80211_report_obss_beacon,
 		  WIPHY_PR_ARG, __entry->freq, __entry->sig_dbm)
 );
 
+TRACE_EVENT(cfg80211_tdls_oper_request,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *peer,
+		 enum nl80211_tdls_operation oper, u16 reason_code),
+	TP_ARGS(wiphy, netdev, peer, oper, reason_code),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(peer)
+		__field(enum nl80211_tdls_operation, oper)
+		__field(u16, reason_code)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(peer, peer);
+		__entry->oper = oper;
+		__entry->reason_code = reason_code;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT ", oper: %d, reason_code %u",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->oper,
+		  __entry->reason_code)
+	);
+
 TRACE_EVENT(cfg80211_scan_done,
 	TP_PROTO(struct cfg80211_scan_request *request, bool aborted),
 	TP_ARGS(request, aborted),
-- 
cgit v1.2.3-55-g7522


From 49884568628db47a1f8c1f596c6ab3b8db81b73c Mon Sep 17 00:00:00 2001
From: Eliad Peller
Date: Mon, 19 Nov 2012 17:05:09 +0200
Subject: mac80211: make remain_on_channel() op pass vif param

Drivers (e.g. wl12xx) might need to know the vif
to roc on (mainly in order to configure the
rx filters correctly).

Add the vif to the op params, and update the current
users (iwlwifi) to use the new api.

Signed-off-by: Eliad Peller <eliad@wizery.com>
[fix hwsim]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/iwlwifi/dvm/mac80211.c |  1 +
 drivers/net/wireless/mac80211_hwsim.c       |  1 +
 include/net/mac80211.h                      |  1 +
 net/mac80211/cfg.c                          |  6 ++++--
 net/mac80211/driver-ops.h                   |  7 ++++---
 net/mac80211/offchannel.c                   |  2 +-
 net/mac80211/trace.h                        | 13 +++++++++----
 7 files changed, 21 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
index ff8162d4c454..e75d80341f28 100644
--- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
@@ -1032,6 +1032,7 @@ done:
 }
 
 static int iwlagn_mac_remain_on_channel(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif,
 				     struct ieee80211_channel *channel,
 				     enum nl80211_channel_type channel_type,
 				     int duration)
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index c242f5a9b8bc..3baa51f1bb83 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1453,6 +1453,7 @@ static void hw_roc_done(struct work_struct *work)
 }
 
 static int mac80211_hwsim_roc(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
 			      struct ieee80211_channel *chan,
 			      enum nl80211_channel_type channel_type,
 			      int duration)
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index dd08fbb3cf28..d11037b5b854 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2530,6 +2530,7 @@ struct ieee80211_ops {
 	int (*get_antenna)(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant);
 
 	int (*remain_on_channel)(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif,
 				 struct ieee80211_channel *chan,
 				 enum nl80211_channel_type channel_type,
 				 int duration);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 80e0618b25ba..18926aea480c 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2287,7 +2287,8 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 	if (!duration)
 		duration = 10;
 
-	ret = drv_remain_on_channel(local, channel, channel_type, duration);
+	ret = drv_remain_on_channel(local, sdata, channel, channel_type,
+				    duration);
 	if (ret) {
 		kfree(roc);
 		return ret;
@@ -2298,7 +2299,8 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 
  out_check_combine:
 	list_for_each_entry(tmp, &local->roc_list, list) {
-		if (tmp->chan != channel || tmp->chan_type != channel_type)
+		if (tmp->chan != channel || tmp->chan_type != channel_type ||
+		    tmp->sdata != sdata)
 			continue;
 
 		/*
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 4dc2577886ff..284dd02385e4 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -704,6 +704,7 @@ static inline int drv_get_antenna(struct ieee80211_local *local,
 }
 
 static inline int drv_remain_on_channel(struct ieee80211_local *local,
+					struct ieee80211_sub_if_data *sdata,
 					struct ieee80211_channel *chan,
 					enum nl80211_channel_type chantype,
 					unsigned int duration)
@@ -712,9 +713,9 @@ static inline int drv_remain_on_channel(struct ieee80211_local *local,
 
 	might_sleep();
 
-	trace_drv_remain_on_channel(local, chan, chantype, duration);
-	ret = local->ops->remain_on_channel(&local->hw, chan, chantype,
-					    duration);
+	trace_drv_remain_on_channel(local, sdata, chan, chantype, duration);
+	ret = local->ops->remain_on_channel(&local->hw, &sdata->vif,
+					    chan, chantype, duration);
 	trace_drv_return_int(local, ret);
 
 	return ret;
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 0cd42d52880c..7f8a36510813 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -283,7 +283,7 @@ void ieee80211_start_next_roc(struct ieee80211_local *local)
 		if (!duration)
 			duration = 10;
 
-		ret = drv_remain_on_channel(local, roc->chan,
+		ret = drv_remain_on_channel(local, roc->sdata, roc->chan,
 					    roc->chan_type,
 					    duration);
 
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 758836c85a80..e9579b7a2cd0 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -1019,13 +1019,16 @@ TRACE_EVENT(drv_get_antenna,
 );
 
 TRACE_EVENT(drv_remain_on_channel,
-	TP_PROTO(struct ieee80211_local *local, struct ieee80211_channel *chan,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_channel *chan,
 		 enum nl80211_channel_type chantype, unsigned int duration),
 
-	TP_ARGS(local, chan, chantype, duration),
+	TP_ARGS(local, sdata, chan, chantype, duration),
 
 	TP_STRUCT__entry(
 		LOCAL_ENTRY
+		VIF_ENTRY
 		__field(int, center_freq)
 		__field(int, channel_type)
 		__field(unsigned int, duration)
@@ -1033,14 +1036,16 @@ TRACE_EVENT(drv_remain_on_channel,
 
 	TP_fast_assign(
 		LOCAL_ASSIGN;
+		VIF_ASSIGN;
 		__entry->center_freq = chan->center_freq;
 		__entry->channel_type = chantype;
 		__entry->duration = duration;
 	),
 
 	TP_printk(
-		LOCAL_PR_FMT " freq:%dMHz duration:%dms",
-		LOCAL_PR_ARG, __entry->center_freq, __entry->duration
+		LOCAL_PR_FMT  VIF_PR_FMT " freq:%dMHz duration:%dms",
+		LOCAL_PR_ARG, VIF_PR_ARG,
+		__entry->center_freq, __entry->duration
 	)
 );
 
-- 
cgit v1.2.3-55-g7522


From fd25b4c2f226de818e1d2b71e3e681d28bcaf5ba Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Tue, 13 Nov 2012 18:21:22 +0100
Subject: vtime: Remove the underscore prefix invasion

Prepending irq-unsafe vtime APIs with underscores was actually
a bad idea as the result is a big mess in the API namespace that
is even waiting to be further extended. Also these helpers
are always called from irq safe callers except kvm. Just
provide a vtime_account_system_irqsafe() for this specific
case so that we can remove the underscore prefix on other
vtime functions.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 arch/ia64/kernel/time.c    |  8 ++++----
 arch/powerpc/kernel/time.c |  4 ++--
 arch/s390/kernel/vtime.c   |  4 ++--
 include/linux/kvm_host.h   |  4 ++--
 include/linux/vtime.h      |  8 ++++----
 kernel/sched/cputime.c     | 12 ++++++------
 6 files changed, 20 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 5e4850305d3f..f6388216080d 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -106,9 +106,9 @@ void vtime_task_switch(struct task_struct *prev)
 	struct thread_info *ni = task_thread_info(current);
 
 	if (idle_task(smp_processor_id()) != prev)
-		__vtime_account_system(prev);
+		vtime_account_system(prev);
 	else
-		__vtime_account_idle(prev);
+		vtime_account_idle(prev);
 
 	vtime_account_user(prev);
 
@@ -135,14 +135,14 @@ static cputime_t vtime_delta(struct task_struct *tsk)
 	return delta_stime;
 }
 
-void __vtime_account_system(struct task_struct *tsk)
+void vtime_account_system(struct task_struct *tsk)
 {
 	cputime_t delta = vtime_delta(tsk);
 
 	account_system_time(tsk, 0, delta, delta);
 }
 
-void __vtime_account_idle(struct task_struct *tsk)
+void vtime_account_idle(struct task_struct *tsk)
 {
 	account_idle_time(vtime_delta(tsk));
 }
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 0db456f30d45..ce4cb772dc78 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -336,7 +336,7 @@ static u64 vtime_delta(struct task_struct *tsk,
 	return delta;
 }
 
-void __vtime_account_system(struct task_struct *tsk)
+void vtime_account_system(struct task_struct *tsk)
 {
 	u64 delta, sys_scaled, stolen;
 
@@ -346,7 +346,7 @@ void __vtime_account_system(struct task_struct *tsk)
 		account_steal_time(stolen);
 }
 
-void __vtime_account_idle(struct task_struct *tsk)
+void vtime_account_idle(struct task_struct *tsk)
 {
 	u64 delta, sys_scaled, stolen;
 
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 783e988c4e1e..80d1dbc5d42e 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -140,9 +140,9 @@ void vtime_account(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(vtime_account);
 
-void __vtime_account_system(struct task_struct *tsk)
+void vtime_account_system(struct task_struct *tsk)
 __attribute__((alias("vtime_account")));
-EXPORT_SYMBOL_GPL(__vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void __kprobes vtime_stop_cpu(void)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 0e2212fe4784..f17158bdd4fc 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -741,7 +741,7 @@ static inline void kvm_guest_enter(void)
 	 * This is running in ioctl context so we can avoid
 	 * the call to vtime_account() with its unnecessary idle check.
 	 */
-	vtime_account_system(current);
+	vtime_account_system_irqsafe(current);
 	current->flags |= PF_VCPU;
 	/* KVM does not hold any references to rcu protected data when it
 	 * switches CPU into a guest mode. In fact switching to a guest mode
@@ -759,7 +759,7 @@ static inline void kvm_guest_exit(void)
 	 * This is running in ioctl context so we can avoid
 	 * the call to vtime_account() with its unnecessary idle check.
 	 */
-	vtime_account_system(current);
+	vtime_account_system_irqsafe(current);
 	current->flags &= ~PF_VCPU;
 }
 
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 0c2a2d303020..5ad13c325deb 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -5,14 +5,14 @@ struct task_struct;
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 extern void vtime_task_switch(struct task_struct *prev);
-extern void __vtime_account_system(struct task_struct *tsk);
 extern void vtime_account_system(struct task_struct *tsk);
-extern void __vtime_account_idle(struct task_struct *tsk);
+extern void vtime_account_system_irqsafe(struct task_struct *tsk);
+extern void vtime_account_idle(struct task_struct *tsk);
 extern void vtime_account(struct task_struct *tsk);
 #else
 static inline void vtime_task_switch(struct task_struct *prev) { }
-static inline void __vtime_account_system(struct task_struct *tsk) { }
 static inline void vtime_account_system(struct task_struct *tsk) { }
+static inline void vtime_account_system_irqsafe(struct task_struct *tsk) { }
 static inline void vtime_account(struct task_struct *tsk) { }
 #endif
 
@@ -40,7 +40,7 @@ static inline void vtime_account_irq_enter(struct task_struct *tsk)
 static inline void vtime_account_irq_exit(struct task_struct *tsk)
 {
 	/* On hard|softirq exit we always account to hard|softirq cputime */
-	__vtime_account_system(tsk);
+	vtime_account_system(tsk);
 	irqtime_account_irq(tsk);
 }
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 8d859dae5bed..c0aa1ba752ea 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -433,20 +433,20 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	*st = cputime.stime;
 }
 
-void vtime_account_system(struct task_struct *tsk)
+void vtime_account_system_irqsafe(struct task_struct *tsk)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__vtime_account_system(tsk);
+	vtime_account_system(tsk);
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_system_irqsafe);
 
 /*
  * Archs that account the whole time spent in the idle task
  * (outside irq) as idle time can rely on this and just implement
- * __vtime_account_system() and __vtime_account_idle(). Archs that
+ * vtime_account_system() and vtime_account_idle(). Archs that
  * have other meaning of the idle time (s390 only includes the
  * time spent by the CPU when it's in low power mode) must override
  * vtime_account().
@@ -459,9 +459,9 @@ void vtime_account(struct task_struct *tsk)
 	local_irq_save(flags);
 
 	if (in_interrupt() || !is_idle_task(tsk))
-		__vtime_account_system(tsk);
+		vtime_account_system(tsk);
 	else
-		__vtime_account_idle(tsk);
+		vtime_account_idle(tsk);
 
 	local_irq_restore(flags);
 }
-- 
cgit v1.2.3-55-g7522


From bcebdf846522056a84ba0b0cba5f5413868c9394 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Tue, 13 Nov 2012 23:51:06 +0100
Subject: vtime: Explicitly account pending user time on process tick

All vtime implementations just flush the user time on process
tick. Consolidate that in generic code by calling a user time
accounting helper. This avoids an indirect call in ia64 and
prepare to also consolidate vtime context switch code.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 arch/ia64/kernel/time.c     | 11 +----------
 arch/powerpc/kernel/time.c  | 14 +++++++-------
 arch/s390/kernel/vtime.c    |  7 ++++++-
 include/linux/kernel_stat.h |  8 ++++++++
 include/linux/vtime.h       |  1 +
 5 files changed, 23 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index f6388216080d..834c78bd3b5f 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -83,7 +83,7 @@ static struct clocksource *itc_clocksource;
 
 extern cputime_t cycle_to_cputime(u64 cyc);
 
-static void vtime_account_user(struct task_struct *tsk)
+void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t delta_utime;
 	struct thread_info *ti = task_thread_info(tsk);
@@ -147,15 +147,6 @@ void vtime_account_idle(struct task_struct *tsk)
 	account_idle_time(vtime_delta(tsk));
 }
 
-/*
- * Called from the timer interrupt handler to charge accumulated user time
- * to the current process.  Must be called with interrupts disabled.
- */
-void account_process_tick(struct task_struct *p, int user_tick)
-{
-	vtime_account_user(p);
-}
-
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
 static irqreturn_t
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index ce4cb772dc78..a667aaf85846 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -355,15 +355,15 @@ void vtime_account_idle(struct task_struct *tsk)
 }
 
 /*
- * Transfer the user and system times accumulated in the paca
- * by the exception entry and exit code to the generic process
- * user and system time records.
+ * Transfer the user time accumulated in the paca
+ * by the exception entry and exit code to the generic
+ * process user time records.
  * Must be called with interrupts disabled.
- * Assumes that vtime_account() has been called recently
- * (i.e. since the last entry from usermode) so that
+ * Assumes that vtime_account_system/idle() has been called
+ * recently (i.e. since the last entry from usermode) so that
  * get_paca()->user_time_scaled is up to date.
  */
-void account_process_tick(struct task_struct *tsk, int user_tick)
+void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t utime, utimescaled;
 
@@ -378,7 +378,7 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 void vtime_task_switch(struct task_struct *prev)
 {
 	vtime_account(prev);
-	account_process_tick(prev, 0);
+	vtime_account_user(prev);
 }
 
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 80d1dbc5d42e..7c6d861a1a40 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -112,7 +112,12 @@ void vtime_task_switch(struct task_struct *prev)
 	S390_lowcore.system_timer = ti->system_timer;
 }
 
-void account_process_tick(struct task_struct *tsk, int user_tick)
+/*
+ * In s390, accounting pending user time also implies
+ * accounting system time in order to correctly compute
+ * the stolen time accounting.
+ */
+void vtime_account_user(struct task_struct *tsk)
 {
 	if (do_account_vtime(tsk, HARDIRQ_OFFSET))
 		virt_timer_expire();
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 1865b1f29770..66b70780e910 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -127,7 +127,15 @@ extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t)
 extern void account_steal_time(cputime_t);
 extern void account_idle_time(cputime_t);
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+static inline void account_process_tick(struct task_struct *tsk, int user)
+{
+	vtime_account_user(tsk);
+}
+#else
 extern void account_process_tick(struct task_struct *, int user);
+#endif
+
 extern void account_steal_ticks(unsigned long ticks);
 extern void account_idle_ticks(unsigned long ticks);
 
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 5ad13c325deb..ae30ab58431a 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -8,6 +8,7 @@ extern void vtime_task_switch(struct task_struct *prev);
 extern void vtime_account_system(struct task_struct *tsk);
 extern void vtime_account_system_irqsafe(struct task_struct *tsk);
 extern void vtime_account_idle(struct task_struct *tsk);
+extern void vtime_account_user(struct task_struct *tsk);
 extern void vtime_account(struct task_struct *tsk);
 #else
 static inline void vtime_task_switch(struct task_struct *prev) { }
-- 
cgit v1.2.3-55-g7522


From febfcef60d4f9457785b45aab548bc7ee5ea158f Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 19 Nov 2012 08:13:36 -0800
Subject: cgroup: cgroup->dentry isn't a RCU pointer

cgroup->dentry is marked and used as a RCU pointer; however, it isn't
one - the final dentry put doesn't go through call_rcu().  cgroup and
dentry share the same RCU freeing rule via synchronize_rcu() in
cgroup_diput() (kfree_rcu() used on cgrp is unnecessary).  If cgrp is
accessible under RCU read lock, so is its dentry and dereferencing
cgrp->dentry doesn't need any further RCU protection or annotation.

While not being accurate, before the previous patch, the RCU accessors
served a purpose as memory barriers - cgroup->dentry used to be
assigned after the cgroup was made visible to cgroup_path(), so the
assignment and dereferencing in cgroup_path() needed the memory
barrier pair.  Now that list_add_tail_rcu() happens after
cgroup->dentry is assigned, this no longer is necessary.

Remove the now unnecessary and misleading RCU annotations from
cgroup->dentry.  To make up for the removal of rcu_dereference_check()
in cgroup_path(), add an explicit rcu_lockdep_assert(), which asserts
the dereference rule of @cgrp, not cgrp->dentry.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  2 +-
 kernel/cgroup.c        | 11 ++++++-----
 2 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 8f64b459fbd4..d605857c4bf3 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -165,7 +165,7 @@ struct cgroup {
 	struct list_head files;		/* my files */
 
 	struct cgroup *parent;		/* my parent */
-	struct dentry __rcu *dentry;	/* cgroup fs entry, RCU protected */
+	struct dentry *dentry;		/* cgroup fs entry, RCU protected */
 
 	/* Private pointers for each registered subsystem */
 	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index d62a529db2f7..affc76d7f739 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1756,9 +1756,11 @@ static struct kobject *cgroup_kobj;
  */
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
+	struct dentry *dentry = cgrp->dentry;
 	char *start;
-	struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
-						      cgroup_lock_is_held());
+
+	rcu_lockdep_assert(rcu_read_lock_held() || cgroup_lock_is_held(),
+			   "cgroup_path() called without proper locking");
 
 	if (!dentry || cgrp == dummytop) {
 		/*
@@ -1782,8 +1784,7 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 		if (!cgrp)
 			break;
 
-		dentry = rcu_dereference_check(cgrp->dentry,
-					       cgroup_lock_is_held());
+		dentry = cgrp->dentry;
 		if (!cgrp->parent)
 			continue;
 		if (--start < buf)
@@ -4124,7 +4125,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
 	/* allocation complete, commit to creation */
 	dentry->d_fsdata = cgrp;
-	rcu_assign_pointer(cgrp->dentry, dentry);
+	cgrp->dentry = dentry;
 	list_add_tail(&cgrp->allcg_node, &root->allcg_list);
 	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
 	root->number_of_cgroups++;
-- 
cgit v1.2.3-55-g7522


From 38b53abaa3e0c7e750ef73eee919cf42eee6b134 Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 19 Nov 2012 08:13:36 -0800
Subject: cgroup: make CSS_* flags bit masks instead of bit positions

Currently, CSS_* flags are defined as bit positions and manipulated
using atomic bitops.  There's no reason to use atomic bitops for them
and bit positions are clunkier to deal with than bit masks.  Make
CSS_* bit masks instead and use the usual C bitwise operators to
access them.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h | 8 ++++----
 kernel/cgroup.c        | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index d605857c4bf3..a0fc64167129 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -81,7 +81,7 @@ struct cgroup_subsys_state {
 
 /* bits in struct cgroup_subsys_state flags field */
 enum {
-	CSS_ROOT, /* This CSS is the root of the subsystem */
+	CSS_ROOT	= (1 << 0), /* this CSS is the root of the subsystem */
 };
 
 /* Caller must verify that the css is not for root cgroup */
@@ -100,7 +100,7 @@ static inline void __css_get(struct cgroup_subsys_state *css, int count)
 static inline void css_get(struct cgroup_subsys_state *css)
 {
 	/* We don't need to reference count the root state */
-	if (!test_bit(CSS_ROOT, &css->flags))
+	if (!(css->flags & CSS_ROOT))
 		__css_get(css, 1);
 }
 
@@ -113,7 +113,7 @@ static inline void css_get(struct cgroup_subsys_state *css)
 extern bool __css_tryget(struct cgroup_subsys_state *css);
 static inline bool css_tryget(struct cgroup_subsys_state *css)
 {
-	if (test_bit(CSS_ROOT, &css->flags))
+	if (css->flags & CSS_ROOT)
 		return true;
 	return __css_tryget(css);
 }
@@ -126,7 +126,7 @@ static inline bool css_tryget(struct cgroup_subsys_state *css)
 extern void __css_put(struct cgroup_subsys_state *css);
 static inline void css_put(struct cgroup_subsys_state *css)
 {
-	if (!test_bit(CSS_ROOT, &css->flags))
+	if (!(css->flags & CSS_ROOT))
 		__css_put(css);
 }
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index affc76d7f739..82ad8785fafe 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4020,7 +4020,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	css->flags = 0;
 	css->id = NULL;
 	if (cgrp == dummytop)
-		set_bit(CSS_ROOT, &css->flags);
+		css->flags |= CSS_ROOT;
 	BUG_ON(cgrp->subsys[ss->subsys_id]);
 	cgrp->subsys[ss->subsys_id] = css;
 
-- 
cgit v1.2.3-55-g7522


From a31f2d3ff7fe20cbe2a143515a7d7c408b29dd0d Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 19 Nov 2012 08:13:37 -0800
Subject: cgroup: introduce CSS_ONLINE flag and on/offline_css() helpers

New helpers on/offline_css() respectively wrap ->post_create() and
->pre_destroy() invocations.  online_css() sets CSS_ONLINE after
->post_create() is complete and offline_css() invokes ->pre_destroy()
iff CSS_ONLINE is set and clears it while also handling the temporary
dropping of cgroup_mutex.

This patch doesn't introduce any behavior change at the moment but
will be used to improve cgroup_create() failure path and allow
->post_create() to fail.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  1 +
 kernel/cgroup.c        | 65 ++++++++++++++++++++++++++++++++------------------
 2 files changed, 43 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index a0fc64167129..f4a9c9836906 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -82,6 +82,7 @@ struct cgroup_subsys_state {
 /* bits in struct cgroup_subsys_state flags field */
 enum {
 	CSS_ROOT	= (1 << 0), /* this CSS is the root of the subsystem */
+	CSS_ONLINE	= (1 << 1), /* between ->post_create() and ->pre_destroy() */
 };
 
 /* Caller must verify that the css is not for root cgroup */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 4412d9694f13..78a3d5c0968e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4035,6 +4035,42 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	INIT_WORK(&css->dput_work, css_dput_fn);
 }
 
+/* invoke ->post_create() on a new CSS and mark it online */
+static void online_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	lockdep_assert_held(&cgroup_mutex);
+
+	if (ss->post_create)
+		ss->post_create(cgrp);
+	cgrp->subsys[ss->subsys_id]->flags |= CSS_ONLINE;
+}
+
+/* if the CSS is online, invoke ->pre_destory() on it and mark it offline */
+static void offline_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
+	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
+{
+	struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	if (!(css->flags & CSS_ONLINE))
+		return;
+
+	/*
+	 * pre_destroy() should be called with cgroup_mutex unlocked.  See
+	 * 3fa59dfbc3 ("cgroup: fix potential deadlock in pre_destroy") for
+	 * details.  This temporary unlocking should go away once
+	 * cgroup_mutex is unexported from controllers.
+	 */
+	if (ss->pre_destroy) {
+		mutex_unlock(&cgroup_mutex);
+		ss->pre_destroy(cgrp);
+		mutex_lock(&cgroup_mutex);
+	}
+
+	cgrp->subsys[ss->subsys_id]->flags &= ~CSS_ONLINE;
+}
+
 /*
  * cgroup_create - create a cgroup
  * @parent: cgroup that will be parent of the new cgroup
@@ -4137,8 +4173,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 		dget(dentry);
 
 		/* creation succeeded, notify subsystems */
-		if (ss->post_create)
-			ss->post_create(cgrp);
+		online_css(ss, cgrp);
 	}
 
 	err = cgroup_populate_dir(cgrp, true, root->subsys_mask);
@@ -4240,18 +4275,9 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	}
 	set_bit(CGRP_REMOVED, &cgrp->flags);
 
-	/*
-	 * Tell subsystems to initate destruction.  pre_destroy() should be
-	 * called with cgroup_mutex unlocked.  See 3fa59dfbc3 ("cgroup: fix
-	 * potential deadlock in pre_destroy") for details.  This temporary
-	 * unlocking should go away once cgroup_mutex is unexported from
-	 * controllers.
-	 */
-	mutex_unlock(&cgroup_mutex);
+	/* tell subsystems to initate destruction */
 	for_each_subsys(cgrp->root, ss)
-		if (ss->pre_destroy)
-			ss->pre_destroy(cgrp);
-	mutex_lock(&cgroup_mutex);
+		offline_css(ss, cgrp);
 
 	/*
 	 * Put all the base refs.  Each css holds an extra reference to the
@@ -4354,9 +4380,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	BUG_ON(!list_empty(&init_task.tasks));
 
 	ss->active = 1;
-
-	if (ss->post_create)
-		ss->post_create(dummytop);
+	online_css(ss, dummytop);
 
 	mutex_unlock(&cgroup_mutex);
 
@@ -4469,9 +4493,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	write_unlock(&css_set_lock);
 
 	ss->active = 1;
-
-	if (ss->post_create)
-		ss->post_create(dummytop);
+	online_css(ss, dummytop);
 
 	/* success! */
 	mutex_unlock(&cgroup_mutex);
@@ -4501,12 +4523,9 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	 */
 	BUG_ON(ss->root != &rootnode);
 
-	/* ->pre_destroy() should be called outside cgroup_mutex for now */
-	if (ss->pre_destroy)
-		ss->pre_destroy(dummytop);
-
 	mutex_lock(&cgroup_mutex);
 
+	offline_css(ss, dummytop);
 	ss->active = 0;
 
 	if (ss->use_id) {
-- 
cgit v1.2.3-55-g7522


From b1929db42f8a649d9a9e397119f628c27fd4021f Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 19 Nov 2012 08:13:38 -0800
Subject: cgroup: allow ->post_create() to fail

There could be cases where controllers want to do initialization
operations which may fail from ->post_create().  This patch makes
->post_create() return -errno to indicate failure and online_css()
relay such failures.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Glauber Costa <glommer@parallels.com>
---
 include/linux/cgroup.h  |  2 +-
 kernel/cgroup.c         | 29 +++++++++++++++++++----------
 kernel/cgroup_freezer.c |  4 +++-
 3 files changed, 23 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f4a9c9836906..03d8a92786da 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -440,7 +440,7 @@ int cgroup_taskset_size(struct cgroup_taskset *tset);
 
 struct cgroup_subsys {
 	struct cgroup_subsys_state *(*create)(struct cgroup *cgrp);
-	void (*post_create)(struct cgroup *cgrp);
+	int (*post_create)(struct cgroup *cgrp);
 	void (*pre_destroy)(struct cgroup *cgrp);
 	void (*destroy)(struct cgroup *cgrp);
 	int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 027b66e66698..c389f4258681 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4041,14 +4041,18 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	INIT_WORK(&css->dput_work, css_dput_fn);
 }
 
-/* invoke ->post_create() on a new CSS and mark it online */
-static void online_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
+/* invoke ->post_create() on a new CSS and mark it online if successful */
+static int online_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
 {
+	int ret = 0;
+
 	lockdep_assert_held(&cgroup_mutex);
 
 	if (ss->post_create)
-		ss->post_create(cgrp);
-	cgrp->subsys[ss->subsys_id]->flags |= CSS_ONLINE;
+		ret = ss->post_create(cgrp);
+	if (!ret)
+		cgrp->subsys[ss->subsys_id]->flags |= CSS_ONLINE;
+	return ret;
 }
 
 /* if the CSS is online, invoke ->pre_destory() on it and mark it offline */
@@ -4174,12 +4178,15 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
 	root->number_of_cgroups++;
 
-	for_each_subsys(root, ss) {
-		/* each css holds a ref to the cgroup's dentry */
+	/* each css holds a ref to the cgroup's dentry */
+	for_each_subsys(root, ss)
 		dget(dentry);
 
-		/* creation succeeded, notify subsystems */
-		online_css(ss, cgrp);
+	/* creation succeeded, notify subsystems */
+	for_each_subsys(root, ss) {
+		err = online_css(ss, cgrp);
+		if (err)
+			goto err_destroy;
 	}
 
 	err = cgroup_populate_dir(cgrp, true, root->subsys_mask);
@@ -4393,7 +4400,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	BUG_ON(!list_empty(&init_task.tasks));
 
 	ss->active = 1;
-	online_css(ss, dummytop);
+	BUG_ON(online_css(ss, dummytop));
 
 	mutex_unlock(&cgroup_mutex);
 
@@ -4500,7 +4507,9 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	write_unlock(&css_set_lock);
 
 	ss->active = 1;
-	online_css(ss, dummytop);
+	ret = online_css(ss, dummytop);
+	if (ret)
+		goto err_unload;
 
 	/* success! */
 	mutex_unlock(&cgroup_mutex);
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 670a4af7dc94..ee8bb671688c 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -112,7 +112,7 @@ static struct cgroup_subsys_state *freezer_create(struct cgroup *cgroup)
  * parent's freezing state while holding both parent's and our
  * freezer->lock.
  */
-static void freezer_post_create(struct cgroup *cgroup)
+static int freezer_post_create(struct cgroup *cgroup)
 {
 	struct freezer *freezer = cgroup_freezer(cgroup);
 	struct freezer *parent = parent_freezer(freezer);
@@ -136,6 +136,8 @@ static void freezer_post_create(struct cgroup *cgroup)
 	spin_unlock(&freezer->lock);
 	if (parent)
 		spin_unlock_irq(&parent->lock);
+
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3-55-g7522


From 92fb97487a7e41b222c1417cabd1d1ab7cc3a48c Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 19 Nov 2012 08:13:38 -0800
Subject: cgroup: rename ->create/post_create/pre_destroy/destroy() to
 ->css_alloc/online/offline/free()

Rename cgroup_subsys css lifetime related callbacks to better describe
what their roles are.  Also, update documentation.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 Documentation/cgroups/cgroups.txt | 49 ++++++++++++++++++++++---------------
 block/blk-cgroup.c                | 14 +++++------
 include/linux/cgroup.h            | 35 ++++++++++++++-------------
 kernel/cgroup.c                   | 51 ++++++++++++++++++++-------------------
 kernel/cgroup_freezer.c           | 20 +++++++--------
 kernel/cpuset.c                   | 10 ++++----
 kernel/events/core.c              |  8 +++---
 kernel/sched/core.c               | 16 ++++++------
 mm/hugetlb_cgroup.c               | 14 +++++------
 mm/memcontrol.c                   | 12 ++++-----
 net/core/netprio_cgroup.c         |  8 +++---
 net/sched/cls_cgroup.c            |  8 +++---
 security/device_cgroup.c          |  8 +++---
 13 files changed, 132 insertions(+), 121 deletions(-)

(limited to 'include')

diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 9e04196c4d78..b06eea217403 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -553,16 +553,16 @@ call to cgroup_unload_subsys(). It should also set its_subsys.module =
 THIS_MODULE in its .c file.
 
 Each subsystem may export the following methods. The only mandatory
-methods are create/destroy. Any others that are null are presumed to
+methods are css_alloc/free. Any others that are null are presumed to
 be successful no-ops.
 
-struct cgroup_subsys_state *create(struct cgroup *cgrp)
+struct cgroup_subsys_state *css_alloc(struct cgroup *cgrp)
 (cgroup_mutex held by caller)
 
-Called to create a subsystem state object for a cgroup. The
+Called to allocate a subsystem state object for a cgroup. The
 subsystem should allocate its subsystem state object for the passed
 cgroup, returning a pointer to the new object on success or a
-negative error code. On success, the subsystem pointer should point to
+ERR_PTR() value. On success, the subsystem pointer should point to
 a structure of type cgroup_subsys_state (typically embedded in a
 larger subsystem-specific object), which will be initialized by the
 cgroup system. Note that this will be called at initialization to
@@ -571,24 +571,33 @@ identified by the passed cgroup object having a NULL parent (since
 it's the root of the hierarchy) and may be an appropriate place for
 initialization code.
 
-void destroy(struct cgroup *cgrp)
+int css_online(struct cgroup *cgrp)
 (cgroup_mutex held by caller)
 
-The cgroup system is about to destroy the passed cgroup; the subsystem
-should do any necessary cleanup and free its subsystem state
-object. By the time this method is called, the cgroup has already been
-unlinked from the file system and from the child list of its parent;
-cgroup->parent is still valid. (Note - can also be called for a
-newly-created cgroup if an error occurs after this subsystem's
-create() method has been called for the new cgroup).
-
-int pre_destroy(struct cgroup *cgrp);
-
-Called before checking the reference count on each subsystem. This may
-be useful for subsystems which have some extra references even if
-there are not tasks in the cgroup. If pre_destroy() returns error code,
-rmdir() will fail with it. From this behavior, pre_destroy() can be
-called multiple times against a cgroup.
+Called after @cgrp successfully completed all allocations and made
+visible to cgroup_for_each_child/descendant_*() iterators. The
+subsystem may choose to fail creation by returning -errno. This
+callback can be used to implement reliable state sharing and
+propagation along the hierarchy. See the comment on
+cgroup_for_each_descendant_pre() for details.
+
+void css_offline(struct cgroup *cgrp);
+
+This is the counterpart of css_online() and called iff css_online()
+has succeeded on @cgrp. This signifies the beginning of the end of
+@cgrp. @cgrp is being removed and the subsystem should start dropping
+all references it's holding on @cgrp. When all references are dropped,
+cgroup removal will proceed to the next step - css_free(). After this
+callback, @cgrp should be considered dead to the subsystem.
+
+void css_free(struct cgroup *cgrp)
+(cgroup_mutex held by caller)
+
+The cgroup system is about to free @cgrp; the subsystem should free
+its subsystem state object. By the time this method is called, @cgrp
+is completely unused; @cgrp->parent is still valid. (Note - can also
+be called for a newly-created cgroup if an error occurs after this
+subsystem's create() method has been called for the new cgroup).
 
 int can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 (cgroup_mutex held by caller)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 3dc60fc441cb..3f6d39d23bb6 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -600,7 +600,7 @@ struct cftype blkcg_files[] = {
 };
 
 /**
- * blkcg_pre_destroy - cgroup pre_destroy callback
+ * blkcg_css_offline - cgroup css_offline callback
  * @cgroup: cgroup of interest
  *
  * This function is called when @cgroup is about to go away and responsible
@@ -610,7 +610,7 @@ struct cftype blkcg_files[] = {
  *
  * This is the blkcg counterpart of ioc_release_fn().
  */
-static void blkcg_pre_destroy(struct cgroup *cgroup)
+static void blkcg_css_offline(struct cgroup *cgroup)
 {
 	struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
 
@@ -634,7 +634,7 @@ static void blkcg_pre_destroy(struct cgroup *cgroup)
 	spin_unlock_irq(&blkcg->lock);
 }
 
-static void blkcg_destroy(struct cgroup *cgroup)
+static void blkcg_css_free(struct cgroup *cgroup)
 {
 	struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
 
@@ -642,7 +642,7 @@ static void blkcg_destroy(struct cgroup *cgroup)
 		kfree(blkcg);
 }
 
-static struct cgroup_subsys_state *blkcg_create(struct cgroup *cgroup)
+static struct cgroup_subsys_state *blkcg_css_alloc(struct cgroup *cgroup)
 {
 	static atomic64_t id_seq = ATOMIC64_INIT(0);
 	struct blkcg *blkcg;
@@ -739,10 +739,10 @@ static int blkcg_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 
 struct cgroup_subsys blkio_subsys = {
 	.name = "blkio",
-	.create = blkcg_create,
+	.css_alloc = blkcg_css_alloc,
+	.css_offline = blkcg_css_offline,
+	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,
-	.pre_destroy = blkcg_pre_destroy,
-	.destroy = blkcg_destroy,
 	.subsys_id = blkio_subsys_id,
 	.base_cftypes = blkcg_files,
 	.module = THIS_MODULE,
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 03d8a92786da..7a2189ca8327 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -82,7 +82,7 @@ struct cgroup_subsys_state {
 /* bits in struct cgroup_subsys_state flags field */
 enum {
 	CSS_ROOT	= (1 << 0), /* this CSS is the root of the subsystem */
-	CSS_ONLINE	= (1 << 1), /* between ->post_create() and ->pre_destroy() */
+	CSS_ONLINE	= (1 << 1), /* between ->css_online() and ->css_offline() */
 };
 
 /* Caller must verify that the css is not for root cgroup */
@@ -439,10 +439,11 @@ int cgroup_taskset_size(struct cgroup_taskset *tset);
  */
 
 struct cgroup_subsys {
-	struct cgroup_subsys_state *(*create)(struct cgroup *cgrp);
-	int (*post_create)(struct cgroup *cgrp);
-	void (*pre_destroy)(struct cgroup *cgrp);
-	void (*destroy)(struct cgroup *cgrp);
+	struct cgroup_subsys_state *(*css_alloc)(struct cgroup *cgrp);
+	int (*css_online)(struct cgroup *cgrp);
+	void (*css_offline)(struct cgroup *cgrp);
+	void (*css_free)(struct cgroup *cgrp);
+
 	int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
 	void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset);
@@ -541,13 +542,13 @@ static inline struct cgroup* task_cgroup(struct task_struct *task,
  * @cgroup: cgroup whose children to walk
  *
  * Walk @cgroup's children.  Must be called under rcu_read_lock().  A child
- * cgroup which hasn't finished ->post_create() or already has finished
- * ->pre_destroy() may show up during traversal and it's each subsystem's
+ * cgroup which hasn't finished ->css_online() or already has finished
+ * ->css_offline() may show up during traversal and it's each subsystem's
  * responsibility to verify that each @pos is alive.
  *
- * If a subsystem synchronizes against the parent in its ->post_create()
- * and before starting iterating, a cgroup which finished ->post_create()
- * is guaranteed to be visible in the future iterations.
+ * If a subsystem synchronizes against the parent in its ->css_online() and
+ * before starting iterating, a cgroup which finished ->css_online() is
+ * guaranteed to be visible in the future iterations.
  */
 #define cgroup_for_each_child(pos, cgroup)				\
 	list_for_each_entry_rcu(pos, &(cgroup)->children, sibling)
@@ -561,19 +562,19 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
  * @cgroup: cgroup whose descendants to walk
  *
  * Walk @cgroup's descendants.  Must be called under rcu_read_lock().  A
- * descendant cgroup which hasn't finished ->post_create() or already has
- * finished ->pre_destroy() may show up during traversal and it's each
+ * descendant cgroup which hasn't finished ->css_online() or already has
+ * finished ->css_offline() may show up during traversal and it's each
  * subsystem's responsibility to verify that each @pos is alive.
  *
- * If a subsystem synchronizes against the parent in its ->post_create()
- * and before starting iterating, and synchronizes against @pos on each
- * iteration, any descendant cgroup which finished ->post_create() is
+ * If a subsystem synchronizes against the parent in its ->css_online() and
+ * before starting iterating, and synchronizes against @pos on each
+ * iteration, any descendant cgroup which finished ->css_offline() is
  * guaranteed to be visible in the future iterations.
  *
  * In other words, the following guarantees that a descendant can't escape
  * state updates of its ancestors.
  *
- * my_post_create(@cgrp)
+ * my_online(@cgrp)
  * {
  *	Lock @cgrp->parent and @cgrp;
  *	Inherit state from @cgrp->parent;
@@ -606,7 +607,7 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
  * iteration should lock and unlock both @pos->parent and @pos.
  *
  * Alternatively, a subsystem may choose to use a single global lock to
- * synchronize ->post_create() and ->pre_destroy() against tree-walking
+ * synchronize ->css_online() and ->css_offline() against tree-walking
  * operations.
  */
 #define cgroup_for_each_descendant_pre(pos, cgroup)			\
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c389f4258681..d35463bab487 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -876,7 +876,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		 * Release the subsystem state objects.
 		 */
 		for_each_subsys(cgrp->root, ss)
-			ss->destroy(cgrp);
+			ss->css_free(cgrp);
 
 		cgrp->root->number_of_cgroups--;
 		mutex_unlock(&cgroup_mutex);
@@ -4048,8 +4048,8 @@ static int online_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	if (ss->post_create)
-		ret = ss->post_create(cgrp);
+	if (ss->css_online)
+		ret = ss->css_online(cgrp);
 	if (!ret)
 		cgrp->subsys[ss->subsys_id]->flags |= CSS_ONLINE;
 	return ret;
@@ -4067,14 +4067,14 @@ static void offline_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
 		return;
 
 	/*
-	 * pre_destroy() should be called with cgroup_mutex unlocked.  See
+	 * css_offline() should be called with cgroup_mutex unlocked.  See
 	 * 3fa59dfbc3 ("cgroup: fix potential deadlock in pre_destroy") for
 	 * details.  This temporary unlocking should go away once
 	 * cgroup_mutex is unexported from controllers.
 	 */
-	if (ss->pre_destroy) {
+	if (ss->css_offline) {
 		mutex_unlock(&cgroup_mutex);
-		ss->pre_destroy(cgrp);
+		ss->css_offline(cgrp);
 		mutex_lock(&cgroup_mutex);
 	}
 
@@ -4136,7 +4136,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	for_each_subsys(root, ss) {
 		struct cgroup_subsys_state *css;
 
-		css = ss->create(cgrp);
+		css = ss->css_alloc(cgrp);
 		if (IS_ERR(css)) {
 			err = PTR_ERR(css);
 			goto err_free_all;
@@ -4147,7 +4147,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 			if (err)
 				goto err_free_all;
 		}
-		/* At error, ->destroy() callback has to free assigned ID. */
+		/* At error, ->css_free() callback has to free assigned ID. */
 		if (clone_children(parent) && ss->post_clone)
 			ss->post_clone(cgrp);
 
@@ -4201,7 +4201,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 err_free_all:
 	for_each_subsys(root, ss) {
 		if (cgrp->subsys[ss->subsys_id])
-			ss->destroy(cgrp);
+			ss->css_free(cgrp);
 	}
 	mutex_unlock(&cgroup_mutex);
 	/* Release the reference count that we took on the superblock */
@@ -4381,7 +4381,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	/* Create the top cgroup state for this subsystem */
 	list_add(&ss->sibling, &rootnode.subsys_list);
 	ss->root = &rootnode;
-	css = ss->create(dummytop);
+	css = ss->css_alloc(dummytop);
 	/* We don't handle early failures gracefully */
 	BUG_ON(IS_ERR(css));
 	init_cgroup_css(css, ss, dummytop);
@@ -4425,7 +4425,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 
 	/* check name and function validity */
 	if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
-	    ss->create == NULL || ss->destroy == NULL)
+	    ss->css_alloc == NULL || ss->css_free == NULL)
 		return -EINVAL;
 
 	/*
@@ -4454,10 +4454,11 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	subsys[ss->subsys_id] = ss;
 
 	/*
-	 * no ss->create seems to need anything important in the ss struct, so
-	 * this can happen first (i.e. before the rootnode attachment).
+	 * no ss->css_alloc seems to need anything important in the ss
+	 * struct, so this can happen first (i.e. before the rootnode
+	 * attachment).
 	 */
-	css = ss->create(dummytop);
+	css = ss->css_alloc(dummytop);
 	if (IS_ERR(css)) {
 		/* failure case - need to deassign the subsys[] slot. */
 		subsys[ss->subsys_id] = NULL;
@@ -4577,12 +4578,12 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	write_unlock(&css_set_lock);
 
 	/*
-	 * remove subsystem's css from the dummytop and free it - need to free
-	 * before marking as null because ss->destroy needs the cgrp->subsys
-	 * pointer to find their state. note that this also takes care of
-	 * freeing the css_id.
+	 * remove subsystem's css from the dummytop and free it - need to
+	 * free before marking as null because ss->css_free needs the
+	 * cgrp->subsys pointer to find their state. note that this also
+	 * takes care of freeing the css_id.
 	 */
-	ss->destroy(dummytop);
+	ss->css_free(dummytop);
 	dummytop->subsys[ss->subsys_id] = NULL;
 
 	mutex_unlock(&cgroup_mutex);
@@ -4626,8 +4627,8 @@ int __init cgroup_init_early(void)
 
 		BUG_ON(!ss->name);
 		BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
-		BUG_ON(!ss->create);
-		BUG_ON(!ss->destroy);
+		BUG_ON(!ss->css_alloc);
+		BUG_ON(!ss->css_free);
 		if (ss->subsys_id != i) {
 			printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
 			       ss->name, ss->subsys_id);
@@ -5439,7 +5440,7 @@ struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
 }
 
 #ifdef CONFIG_CGROUP_DEBUG
-static struct cgroup_subsys_state *debug_create(struct cgroup *cont)
+static struct cgroup_subsys_state *debug_css_alloc(struct cgroup *cont)
 {
 	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
 
@@ -5449,7 +5450,7 @@ static struct cgroup_subsys_state *debug_create(struct cgroup *cont)
 	return css;
 }
 
-static void debug_destroy(struct cgroup *cont)
+static void debug_css_free(struct cgroup *cont)
 {
 	kfree(cont->subsys[debug_subsys_id]);
 }
@@ -5578,8 +5579,8 @@ static struct cftype debug_files[] =  {
 
 struct cgroup_subsys debug_subsys = {
 	.name = "debug",
-	.create = debug_create,
-	.destroy = debug_destroy,
+	.css_alloc = debug_css_alloc,
+	.css_free = debug_css_free,
 	.subsys_id = debug_subsys_id,
 	.base_cftypes = debug_files,
 };
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index ee8bb671688c..75dda1ea5026 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -92,7 +92,7 @@ static const char *freezer_state_strs(unsigned int state)
 
 struct cgroup_subsys freezer_subsys;
 
-static struct cgroup_subsys_state *freezer_create(struct cgroup *cgroup)
+static struct cgroup_subsys_state *freezer_css_alloc(struct cgroup *cgroup)
 {
 	struct freezer *freezer;
 
@@ -105,14 +105,14 @@ static struct cgroup_subsys_state *freezer_create(struct cgroup *cgroup)
 }
 
 /**
- * freezer_post_create - commit creation of a freezer cgroup
+ * freezer_css_online - commit creation of a freezer cgroup
  * @cgroup: cgroup being created
  *
  * We're committing to creation of @cgroup.  Mark it online and inherit
  * parent's freezing state while holding both parent's and our
  * freezer->lock.
  */
-static int freezer_post_create(struct cgroup *cgroup)
+static int freezer_css_online(struct cgroup *cgroup)
 {
 	struct freezer *freezer = cgroup_freezer(cgroup);
 	struct freezer *parent = parent_freezer(freezer);
@@ -141,13 +141,13 @@ static int freezer_post_create(struct cgroup *cgroup)
 }
 
 /**
- * freezer_pre_destroy - initiate destruction of @cgroup
+ * freezer_css_offline - initiate destruction of @cgroup
  * @cgroup: cgroup being destroyed
  *
  * @cgroup is going away.  Mark it dead and decrement system_freezing_count
  * if it was holding one.
  */
-static void freezer_pre_destroy(struct cgroup *cgroup)
+static void freezer_css_offline(struct cgroup *cgroup)
 {
 	struct freezer *freezer = cgroup_freezer(cgroup);
 
@@ -161,7 +161,7 @@ static void freezer_pre_destroy(struct cgroup *cgroup)
 	spin_unlock_irq(&freezer->lock);
 }
 
-static void freezer_destroy(struct cgroup *cgroup)
+static void freezer_css_free(struct cgroup *cgroup)
 {
 	kfree(cgroup_freezer(cgroup));
 }
@@ -477,10 +477,10 @@ static struct cftype files[] = {
 
 struct cgroup_subsys freezer_subsys = {
 	.name		= "freezer",
-	.create		= freezer_create,
-	.post_create	= freezer_post_create,
-	.pre_destroy	= freezer_pre_destroy,
-	.destroy	= freezer_destroy,
+	.css_alloc	= freezer_css_alloc,
+	.css_online	= freezer_css_online,
+	.css_offline	= freezer_css_offline,
+	.css_free	= freezer_css_free,
 	.subsys_id	= freezer_subsys_id,
 	.attach		= freezer_attach,
 	.fork		= freezer_fork,
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f33c7153b6d7..06931337c4e5 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1821,11 +1821,11 @@ static void cpuset_post_clone(struct cgroup *cgroup)
 }
 
 /*
- *	cpuset_create - create a cpuset
+ *	cpuset_css_alloc - allocate a cpuset css
  *	cont:	control group that the new cpuset will be part of
  */
 
-static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
+static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cont)
 {
 	struct cpuset *cs;
 	struct cpuset *parent;
@@ -1864,7 +1864,7 @@ static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
  * will call async_rebuild_sched_domains().
  */
 
-static void cpuset_destroy(struct cgroup *cont)
+static void cpuset_css_free(struct cgroup *cont)
 {
 	struct cpuset *cs = cgroup_cs(cont);
 
@@ -1878,8 +1878,8 @@ static void cpuset_destroy(struct cgroup *cont)
 
 struct cgroup_subsys cpuset_subsys = {
 	.name = "cpuset",
-	.create = cpuset_create,
-	.destroy = cpuset_destroy,
+	.css_alloc = cpuset_css_alloc,
+	.css_free = cpuset_css_free,
 	.can_attach = cpuset_can_attach,
 	.attach = cpuset_attach,
 	.post_clone = cpuset_post_clone,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dbccf83c134d..f9ff5493171d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7434,7 +7434,7 @@ unlock:
 device_initcall(perf_event_sysfs_init);
 
 #ifdef CONFIG_CGROUP_PERF
-static struct cgroup_subsys_state *perf_cgroup_create(struct cgroup *cont)
+static struct cgroup_subsys_state *perf_cgroup_css_alloc(struct cgroup *cont)
 {
 	struct perf_cgroup *jc;
 
@@ -7451,7 +7451,7 @@ static struct cgroup_subsys_state *perf_cgroup_create(struct cgroup *cont)
 	return &jc->css;
 }
 
-static void perf_cgroup_destroy(struct cgroup *cont)
+static void perf_cgroup_css_free(struct cgroup *cont)
 {
 	struct perf_cgroup *jc;
 	jc = container_of(cgroup_subsys_state(cont, perf_subsys_id),
@@ -7492,8 +7492,8 @@ static void perf_cgroup_exit(struct cgroup *cgrp, struct cgroup *old_cgrp,
 struct cgroup_subsys perf_subsys = {
 	.name		= "perf_event",
 	.subsys_id	= perf_subsys_id,
-	.create		= perf_cgroup_create,
-	.destroy	= perf_cgroup_destroy,
+	.css_alloc	= perf_cgroup_css_alloc,
+	.css_free	= perf_cgroup_css_free,
 	.exit		= perf_cgroup_exit,
 	.attach		= perf_cgroup_attach,
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d8927fda712..6f20c8fb2326 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7468,7 +7468,7 @@ static inline struct task_group *cgroup_tg(struct cgroup *cgrp)
 			    struct task_group, css);
 }
 
-static struct cgroup_subsys_state *cpu_cgroup_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp)
 {
 	struct task_group *tg, *parent;
 
@@ -7485,7 +7485,7 @@ static struct cgroup_subsys_state *cpu_cgroup_create(struct cgroup *cgrp)
 	return &tg->css;
 }
 
-static void cpu_cgroup_destroy(struct cgroup *cgrp)
+static void cpu_cgroup_css_free(struct cgroup *cgrp)
 {
 	struct task_group *tg = cgroup_tg(cgrp);
 
@@ -7845,8 +7845,8 @@ static struct cftype cpu_files[] = {
 
 struct cgroup_subsys cpu_cgroup_subsys = {
 	.name		= "cpu",
-	.create		= cpu_cgroup_create,
-	.destroy	= cpu_cgroup_destroy,
+	.css_alloc	= cpu_cgroup_css_alloc,
+	.css_free	= cpu_cgroup_css_free,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,
@@ -7869,7 +7869,7 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 struct cpuacct root_cpuacct;
 
 /* create a new cpu accounting group */
-static struct cgroup_subsys_state *cpuacct_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
 {
 	struct cpuacct *ca;
 
@@ -7899,7 +7899,7 @@ out:
 }
 
 /* destroy an existing cpu accounting group */
-static void cpuacct_destroy(struct cgroup *cgrp)
+static void cpuacct_css_free(struct cgroup *cgrp)
 {
 	struct cpuacct *ca = cgroup_ca(cgrp);
 
@@ -8070,8 +8070,8 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 
 struct cgroup_subsys cpuacct_subsys = {
 	.name = "cpuacct",
-	.create = cpuacct_create,
-	.destroy = cpuacct_destroy,
+	.css_alloc = cpuacct_css_alloc,
+	.css_free = cpuacct_css_free,
 	.subsys_id = cpuacct_subsys_id,
 	.base_cftypes = files,
 };
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index 0d3a1a317731..b5bde7a5c017 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -77,7 +77,7 @@ static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg)
 	return false;
 }
 
-static struct cgroup_subsys_state *hugetlb_cgroup_create(struct cgroup *cgroup)
+static struct cgroup_subsys_state *hugetlb_cgroup_css_alloc(struct cgroup *cgroup)
 {
 	int idx;
 	struct cgroup *parent_cgroup;
@@ -101,7 +101,7 @@ static struct cgroup_subsys_state *hugetlb_cgroup_create(struct cgroup *cgroup)
 	return &h_cgroup->css;
 }
 
-static void hugetlb_cgroup_destroy(struct cgroup *cgroup)
+static void hugetlb_cgroup_css_free(struct cgroup *cgroup)
 {
 	struct hugetlb_cgroup *h_cgroup;
 
@@ -155,7 +155,7 @@ out:
  * Force the hugetlb cgroup to empty the hugetlb resources by moving them to
  * the parent cgroup.
  */
-static void hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
+static void hugetlb_cgroup_css_offline(struct cgroup *cgroup)
 {
 	struct hstate *h;
 	struct page *page;
@@ -404,8 +404,8 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
 
 struct cgroup_subsys hugetlb_subsys = {
 	.name = "hugetlb",
-	.create     = hugetlb_cgroup_create,
-	.pre_destroy = hugetlb_cgroup_pre_destroy,
-	.destroy    = hugetlb_cgroup_destroy,
-	.subsys_id  = hugetlb_subsys_id,
+	.css_alloc	= hugetlb_cgroup_css_alloc,
+	.css_offline	= hugetlb_cgroup_css_offline,
+	.css_free	= hugetlb_cgroup_css_free,
+	.subsys_id	= hugetlb_subsys_id,
 };
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 08adaaae6fcc..8b0b2b028e23 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4922,7 +4922,7 @@ err_cleanup:
 }
 
 static struct cgroup_subsys_state * __ref
-mem_cgroup_create(struct cgroup *cont)
+mem_cgroup_css_alloc(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg, *parent;
 	long error = -ENOMEM;
@@ -5003,14 +5003,14 @@ free_out:
 	return ERR_PTR(error);
 }
 
-static void mem_cgroup_pre_destroy(struct cgroup *cont)
+static void mem_cgroup_css_offline(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
 	mem_cgroup_reparent_charges(memcg);
 }
 
-static void mem_cgroup_destroy(struct cgroup *cont)
+static void mem_cgroup_css_free(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
@@ -5600,9 +5600,9 @@ static void mem_cgroup_move_task(struct cgroup *cont,
 struct cgroup_subsys mem_cgroup_subsys = {
 	.name = "memory",
 	.subsys_id = mem_cgroup_subsys_id,
-	.create = mem_cgroup_create,
-	.pre_destroy = mem_cgroup_pre_destroy,
-	.destroy = mem_cgroup_destroy,
+	.css_alloc = mem_cgroup_css_alloc,
+	.css_offline = mem_cgroup_css_offline,
+	.css_free = mem_cgroup_css_free,
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.attach = mem_cgroup_move_task,
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 79285a36035f..f0b6b0d572c1 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -108,7 +108,7 @@ static int write_update_netdev_table(struct net_device *dev)
 	return ret;
 }
 
-static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
 {
 	struct cgroup_netprio_state *cs;
 	int ret = -EINVAL;
@@ -132,7 +132,7 @@ out:
 	return ERR_PTR(ret);
 }
 
-static void cgrp_destroy(struct cgroup *cgrp)
+static void cgrp_css_free(struct cgroup *cgrp)
 {
 	struct cgroup_netprio_state *cs;
 	struct net_device *dev;
@@ -276,8 +276,8 @@ static struct cftype ss_files[] = {
 
 struct cgroup_subsys net_prio_subsys = {
 	.name		= "net_prio",
-	.create		= cgrp_create,
-	.destroy	= cgrp_destroy,
+	.css_alloc	= cgrp_css_alloc,
+	.css_free	= cgrp_css_free,
 	.attach		= net_prio_attach,
 	.subsys_id	= net_prio_subsys_id,
 	.base_cftypes	= ss_files,
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 2ecde225ae60..8cdc18e075fb 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -34,7 +34,7 @@ static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p)
 			    struct cgroup_cls_state, css);
 }
 
-static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
 {
 	struct cgroup_cls_state *cs;
 
@@ -48,7 +48,7 @@ static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
 	return &cs->css;
 }
 
-static void cgrp_destroy(struct cgroup *cgrp)
+static void cgrp_css_free(struct cgroup *cgrp)
 {
 	kfree(cgrp_cls_state(cgrp));
 }
@@ -75,8 +75,8 @@ static struct cftype ss_files[] = {
 
 struct cgroup_subsys net_cls_subsys = {
 	.name		= "net_cls",
-	.create		= cgrp_create,
-	.destroy	= cgrp_destroy,
+	.css_alloc	= cgrp_css_alloc,
+	.css_free	= cgrp_css_free,
 	.subsys_id	= net_cls_subsys_id,
 	.base_cftypes	= ss_files,
 	.module		= THIS_MODULE,
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 78a16f5b7275..19ecc8de9e6b 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -180,7 +180,7 @@ static void dev_exception_clean(struct dev_cgroup *dev_cgroup)
 /*
  * called from kernel/cgroup.c with cgroup_lock() held.
  */
-static struct cgroup_subsys_state *devcgroup_create(struct cgroup *cgroup)
+static struct cgroup_subsys_state *devcgroup_css_alloc(struct cgroup *cgroup)
 {
 	struct dev_cgroup *dev_cgroup, *parent_dev_cgroup;
 	struct cgroup *parent_cgroup;
@@ -210,7 +210,7 @@ static struct cgroup_subsys_state *devcgroup_create(struct cgroup *cgroup)
 	return &dev_cgroup->css;
 }
 
-static void devcgroup_destroy(struct cgroup *cgroup)
+static void devcgroup_css_free(struct cgroup *cgroup)
 {
 	struct dev_cgroup *dev_cgroup;
 
@@ -564,8 +564,8 @@ static struct cftype dev_cgroup_files[] = {
 struct cgroup_subsys devices_subsys = {
 	.name = "devices",
 	.can_attach = devcgroup_can_attach,
-	.create = devcgroup_create,
-	.destroy = devcgroup_destroy,
+	.css_alloc = devcgroup_css_alloc,
+	.css_free = devcgroup_css_free,
 	.subsys_id = devices_subsys_id,
 	.base_cftypes = dev_cgroup_files,
 
-- 
cgit v1.2.3-55-g7522


From 2260e7fc1f18ad815324605c1ce7d5c6fd9b19a2 Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 19 Nov 2012 08:13:38 -0800
Subject: cgroup: s/CGRP_CLONE_CHILDREN/CGRP_CPUSET_CLONE_CHILDREN/

clone_children is only meaningful for cpuset and will stay that way.
Rename the flag to reflect that and update documentation.  Also, drop
clone_children() wrapper in cgroup.c.  The thin wrapper is used only a
few times and one of them will go away soon.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Glauber Costa <glommer@parallels.com>
---
 Documentation/cgroups/cgroups.txt |  8 +++-----
 include/linux/cgroup.h            |  6 ++++--
 kernel/cgroup.c                   | 28 ++++++++++++----------------
 3 files changed, 19 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index b06eea217403..24cdf76bd20c 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -299,11 +299,9 @@ a cgroup hierarchy's release_agent path is empty.
 1.5 What does clone_children do ?
 ---------------------------------
 
-If the clone_children flag is enabled (1) in a cgroup, then all
-cgroups created beneath will call the post_clone callbacks for each
-subsystem of the newly created cgroup. Usually when this callback is
-implemented for a subsystem, it copies the values of the parent
-subsystem, this is the case for the cpuset.
+This flag only affects the cpuset controller. If the clone_children
+flag is enabled (1) in a cgroup, a new cpuset cgroup will copy its
+configuration from the parent during initialization.
 
 1.6 How do I use cgroups ?
 --------------------------
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 7a2189ca8327..d2f82979f6c1 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -143,9 +143,11 @@ enum {
 	/* Control Group requires release notifications to userspace */
 	CGRP_NOTIFY_ON_RELEASE,
 	/*
-	 * Clone cgroup values when creating a new child cgroup
+	 * Clone the parent's configuration when creating a new child
+	 * cpuset cgroup.  For historical reasons, this option can be
+	 * specified at mount time and thus is implemented here.
 	 */
-	CGRP_CLONE_CHILDREN,
+	CGRP_CPUSET_CLONE_CHILDREN,
 };
 
 struct cgroup {
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index d35463bab487..2895880e6800 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -296,11 +296,6 @@ static int notify_on_release(const struct cgroup *cgrp)
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 }
 
-static int clone_children(const struct cgroup *cgrp)
-{
-	return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
-}
-
 /*
  * for_each_subsys() allows you to iterate on each subsystem attached to
  * an active hierarchy
@@ -1101,7 +1096,7 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",xattr");
 	if (strlen(root->release_agent_path))
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
-	if (clone_children(&root->top_cgroup))
+	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags))
 		seq_puts(seq, ",clone_children");
 	if (strlen(root->name))
 		seq_printf(seq, ",name=%s", root->name);
@@ -1113,7 +1108,7 @@ struct cgroup_sb_opts {
 	unsigned long subsys_mask;
 	unsigned long flags;
 	char *release_agent;
-	bool clone_children;
+	bool cpuset_clone_children;
 	char *name;
 	/* User explicitly requested empty subsystem */
 	bool none;
@@ -1164,7 +1159,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			continue;
 		}
 		if (!strcmp(token, "clone_children")) {
-			opts->clone_children = true;
+			opts->cpuset_clone_children = true;
 			continue;
 		}
 		if (!strcmp(token, "xattr")) {
@@ -1474,8 +1469,8 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 		strcpy(root->release_agent_path, opts->release_agent);
 	if (opts->name)
 		strcpy(root->name, opts->name);
-	if (opts->clone_children)
-		set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
+	if (opts->cpuset_clone_children)
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags);
 	return root;
 }
 
@@ -3905,7 +3900,7 @@ fail:
 static u64 cgroup_clone_children_read(struct cgroup *cgrp,
 				    struct cftype *cft)
 {
-	return clone_children(cgrp);
+	return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 }
 
 static int cgroup_clone_children_write(struct cgroup *cgrp,
@@ -3913,9 +3908,9 @@ static int cgroup_clone_children_write(struct cgroup *cgrp,
 				     u64 val)
 {
 	if (val)
-		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 	else
-		clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+		clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 	return 0;
 }
 
@@ -4130,8 +4125,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 
-	if (clone_children(parent))
-		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 
 	for_each_subsys(root, ss) {
 		struct cgroup_subsys_state *css;
@@ -4148,7 +4143,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 				goto err_free_all;
 		}
 		/* At error, ->css_free() callback has to free assigned ID. */
-		if (clone_children(parent) && ss->post_clone)
+		if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags) &&
+		    ss->post_clone)
 			ss->post_clone(cgrp);
 
 		if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
-- 
cgit v1.2.3-55-g7522


From 033fa1c5f5f73833598a0beb022c0048fb769dad Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 19 Nov 2012 08:13:39 -0800
Subject: cgroup, cpuset: remove cgroup_subsys->post_clone()

Currently CGRP_CPUSET_CLONE_CHILDREN triggers ->post_clone().  Now
that clone_children is cpuset specific, there's no reason to have this
rather odd option activation mechanism in cgroup core.  cpuset can
check the flag from its ->css_allocate() and take the necessary
action.

Move cpuset_post_clone() logic to the end of cpuset_css_alloc() and
remove cgroup_subsys->post_clone().

Loosely based on Glauber's "generalize post_clone into post_create"
patch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Original-patch-by: Glauber Costa <glommer@parallels.com>
Original-patch: <1351686554-22592-2-git-send-email-glommer@parallels.com>
Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Glauber Costa <glommer@parallels.com>
---
 Documentation/cgroups/cgroups.txt |  8 ----
 include/linux/cgroup.h            |  1 -
 kernel/cgroup.c                   |  4 --
 kernel/cpuset.c                   | 80 ++++++++++++++++++---------------------
 4 files changed, 36 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 24cdf76bd20c..bcf1a00b06a1 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -642,14 +642,6 @@ void exit(struct task_struct *task)
 
 Called during task exit.
 
-void post_clone(struct cgroup *cgrp)
-(cgroup_mutex held by caller)
-
-Called during cgroup_create() to do any parameter
-initialization which might be required before a task could attach.  For
-example, in cpusets, no task may attach before 'cpus' and 'mems' are set
-up.
-
 void bind(struct cgroup *root)
 (cgroup_mutex held by caller)
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index d2f82979f6c1..c798997e5011 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -452,7 +452,6 @@ struct cgroup_subsys {
 	void (*fork)(struct task_struct *task);
 	void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp,
 		     struct task_struct *task);
-	void (*post_clone)(struct cgroup *cgrp);
 	void (*bind)(struct cgroup *root);
 
 	int subsys_id;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2895880e6800..96719f73e95d 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4142,10 +4142,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 			if (err)
 				goto err_free_all;
 		}
-		/* At error, ->css_free() callback has to free assigned ID. */
-		if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags) &&
-		    ss->post_clone)
-			ss->post_clone(cgrp);
 
 		if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
 		    parent->parent) {
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 06931337c4e5..b017887d632f 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1783,43 +1783,6 @@ static struct cftype files[] = {
 	{ }	/* terminate */
 };
 
-/*
- * post_clone() is called during cgroup_create() when the
- * clone_children mount argument was specified.  The cgroup
- * can not yet have any tasks.
- *
- * Currently we refuse to set up the cgroup - thereby
- * refusing the task to be entered, and as a result refusing
- * the sys_unshare() or clone() which initiated it - if any
- * sibling cpusets have exclusive cpus or mem.
- *
- * If this becomes a problem for some users who wish to
- * allow that scenario, then cpuset_post_clone() could be
- * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
- * (and likewise for mems) to the new cgroup. Called with cgroup_mutex
- * held.
- */
-static void cpuset_post_clone(struct cgroup *cgroup)
-{
-	struct cgroup *parent, *child;
-	struct cpuset *cs, *parent_cs;
-
-	parent = cgroup->parent;
-	list_for_each_entry(child, &parent->children, sibling) {
-		cs = cgroup_cs(child);
-		if (is_mem_exclusive(cs) || is_cpu_exclusive(cs))
-			return;
-	}
-	cs = cgroup_cs(cgroup);
-	parent_cs = cgroup_cs(parent);
-
-	mutex_lock(&callback_mutex);
-	cs->mems_allowed = parent_cs->mems_allowed;
-	cpumask_copy(cs->cpus_allowed, parent_cs->cpus_allowed);
-	mutex_unlock(&callback_mutex);
-	return;
-}
-
 /*
  *	cpuset_css_alloc - allocate a cpuset css
  *	cont:	control group that the new cpuset will be part of
@@ -1827,13 +1790,14 @@ static void cpuset_post_clone(struct cgroup *cgroup)
 
 static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cont)
 {
-	struct cpuset *cs;
-	struct cpuset *parent;
+	struct cgroup *parent_cg = cont->parent;
+	struct cgroup *tmp_cg;
+	struct cpuset *parent, *cs;
 
-	if (!cont->parent) {
+	if (!parent_cg)
 		return &top_cpuset.css;
-	}
-	parent = cgroup_cs(cont->parent);
+	parent = cgroup_cs(parent_cg);
+
 	cs = kmalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
@@ -1855,7 +1819,36 @@ static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cont)
 
 	cs->parent = parent;
 	number_of_cpusets++;
-	return &cs->css ;
+
+	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cont->flags))
+		goto skip_clone;
+
+	/*
+	 * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is
+	 * set.  This flag handling is implemented in cgroup core for
+	 * histrical reasons - the flag may be specified during mount.
+	 *
+	 * Currently, if any sibling cpusets have exclusive cpus or mem, we
+	 * refuse to clone the configuration - thereby refusing the task to
+	 * be entered, and as a result refusing the sys_unshare() or
+	 * clone() which initiated it.  If this becomes a problem for some
+	 * users who wish to allow that scenario, then this could be
+	 * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
+	 * (and likewise for mems) to the new cgroup.
+	 */
+	list_for_each_entry(tmp_cg, &parent_cg->children, sibling) {
+		struct cpuset *tmp_cs = cgroup_cs(tmp_cg);
+
+		if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs))
+			goto skip_clone;
+	}
+
+	mutex_lock(&callback_mutex);
+	cs->mems_allowed = parent->mems_allowed;
+	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+	mutex_unlock(&callback_mutex);
+skip_clone:
+	return &cs->css;
 }
 
 /*
@@ -1882,7 +1875,6 @@ struct cgroup_subsys cpuset_subsys = {
 	.css_free = cpuset_css_free,
 	.can_attach = cpuset_can_attach,
 	.attach = cpuset_attach,
-	.post_clone = cpuset_post_clone,
 	.subsys_id = cpuset_subsys_id,
 	.base_cftypes = files,
 	.early_init = 1,
-- 
cgit v1.2.3-55-g7522


From 2abb74eaf6e73cb42e87bdc9e9c2535ce485e614 Mon Sep 17 00:00:00 2001
From: Jean-Christophe PLAGNIOL-VILLARD
Date: Sat, 17 Nov 2012 23:05:06 +0100
Subject: atmel: move ATMEL_MAX_UART to platform_data/atmel.h

Modify both AT91 and AVR32 platforms.
Use 7 for it as the sam9260 or the sam9g25 have 7 of them DBGU included.

Reported-by: Joachim Eastwood <joachim.eastwood@jotron.com>
Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
---
 arch/arm/mach-at91/include/mach/hardware.h  | 3 ---
 arch/avr32/mach-at32ap/include/mach/board.h | 1 -
 include/linux/platform_data/atmel.h         | 6 ++++++
 3 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-at91/include/mach/hardware.h b/arch/arm/mach-at91/include/mach/hardware.h
index 711a7892d331..a832e0707611 100644
--- a/arch/arm/mach-at91/include/mach/hardware.h
+++ b/arch/arm/mach-at91/include/mach/hardware.h
@@ -90,9 +90,6 @@
 #define AT91_SRAM_MAX		SZ_1M
 #define AT91_VIRT_BASE		(AT91_IO_VIRT_BASE - AT91_SRAM_MAX)
 
-/* Serial ports */
-#define ATMEL_MAX_UART		7		/* 6 USART3's and one DBGU port (SAM9260) */
-
 /* External Memory Map */
 #define AT91_CHIPSELECT_0	0x10000000
 #define AT91_CHIPSELECT_1	0x20000000
diff --git a/arch/avr32/mach-at32ap/include/mach/board.h b/arch/avr32/mach-at32ap/include/mach/board.h
index dca93450cb0e..d485b0391357 100644
--- a/arch/avr32/mach-at32ap/include/mach/board.h
+++ b/arch/avr32/mach-at32ap/include/mach/board.h
@@ -26,7 +26,6 @@ static inline void __deprecated at32_add_system_devices(void)
 
 }
 
-#define ATMEL_MAX_UART	4
 extern struct platform_device *atmel_default_console_device;
 
 /* Flags for selecting USART extra pins */
diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h
index dbd6d53cc270..6a293b7fff3b 100644
--- a/include/linux/platform_data/atmel.h
+++ b/include/linux/platform_data/atmel.h
@@ -19,6 +19,12 @@
 #include <linux/serial.h>
 #include <linux/platform_data/macb.h>
 
+/*
+ * at91: 6 USARTs and one DBGU port (SAM9260)
+ * avr32: 4
+ */
+#define ATMEL_MAX_UART	7
+
  /* USB Device */
 struct at91_udc_data {
 	int	vbus_pin;		/* high == host powering us */
-- 
cgit v1.2.3-55-g7522


From 0a950f65e1e64f4e82b4b5507773848ea88bcb8e Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Mon, 19 Nov 2012 09:02:12 -0800
Subject: cgroup: add cgroup->id

With the introduction of generic cgroup hierarchy iterators, css_id is
being phased out.  It was unnecessarily complex, id'ing the wrong
thing (cgroups need IDs, not CSSes) and has other oddities like not
being available at ->css_alloc().

This patch adds cgroup->id, which is a simple per-hierarchy
ida-allocated ID which is assigned before ->css_alloc() and released
after ->css_free().

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
---
 include/linux/cgroup.h |  2 ++
 kernel/cgroup.c        | 15 ++++++++++++++-
 2 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c798997e5011..82cf9e6fc77b 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -159,6 +159,8 @@ struct cgroup {
 	 */
 	atomic_t count;
 
+	int id;				/* ida allocated in-hierarchy ID */
+
 	/*
 	 * We link our 'sibling' struct into our parent's 'children'.
 	 * Our children link their 'sibling' into our 'children'.
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 96719f73e95d..6db01417d39a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -138,6 +138,9 @@ struct cgroupfs_root {
 	/* Hierarchy-specific flags */
 	unsigned long flags;
 
+	/* IDs for cgroups in this hierarchy */
+	struct ida cgroup_ida;
+
 	/* The path to use for release notifications. */
 	char release_agent_path[PATH_MAX];
 
@@ -890,6 +893,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 
 		simple_xattrs_free(&cgrp->xattrs);
 
+		ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
 		kfree_rcu(cgrp, rcu_head);
 	} else {
 		struct cfent *cfe = __d_cfe(dentry);
@@ -1465,6 +1469,7 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 
 	root->subsys_mask = opts->subsys_mask;
 	root->flags = opts->flags;
+	ida_init(&root->cgroup_ida);
 	if (opts->release_agent)
 		strcpy(root->release_agent_path, opts->release_agent);
 	if (opts->name)
@@ -1483,6 +1488,7 @@ static void cgroup_drop_root(struct cgroupfs_root *root)
 	spin_lock(&hierarchy_id_lock);
 	ida_remove(&hierarchy_ida, root->hierarchy_id);
 	spin_unlock(&hierarchy_id_lock);
+	ida_destroy(&root->cgroup_ida);
 	kfree(root);
 }
 
@@ -4093,10 +4099,15 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	struct cgroup_subsys *ss;
 	struct super_block *sb = root->sb;
 
+	/* allocate the cgroup and its ID, 0 is reserved for the root */
 	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
 	if (!cgrp)
 		return -ENOMEM;
 
+	cgrp->id = ida_simple_get(&root->cgroup_ida, 1, 0, GFP_KERNEL);
+	if (cgrp->id < 0)
+		goto err_free_cgrp;
+
 	/*
 	 * Only live parents can have children.  Note that the liveliness
 	 * check isn't strictly necessary because cgroup_mkdir() and
@@ -4106,7 +4117,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	 */
 	if (!cgroup_lock_live_group(parent)) {
 		err = -ENODEV;
-		goto err_free_cgrp;
+		goto err_free_id;
 	}
 
 	/* Grab a reference on the superblock so the hierarchy doesn't
@@ -4198,6 +4209,8 @@ err_free_all:
 	mutex_unlock(&cgroup_mutex);
 	/* Release the reference count that we took on the superblock */
 	deactivate_super(sb);
+err_free_id:
+	ida_simple_remove(&root->cgroup_ida, cgrp->id);
 err_free_cgrp:
 	kfree(cgrp);
 	return err;
-- 
cgit v1.2.3-55-g7522


From a514b17fab51c1433db920d76cf8ddda959e5da0 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Wed, 14 Nov 2012 17:39:30 +0200
Subject: Bluetooth: Refactor locking in amp_physical_cfm

Remove locking from l2cap_physical_cfm and lock chan inside
amp_physical_cfm.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h | 2 +-
 net/bluetooth/amp.c           | 6 +++++-
 net/bluetooth/l2cap_core.c    | 7 ++-----
 3 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index d65db459c843..f57fab04e7c5 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -811,6 +811,6 @@ void l2cap_send_conn_req(struct l2cap_chan *chan);
 void l2cap_move_start(struct l2cap_chan *chan);
 void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
 		       u8 status);
-void l2cap_physical_cfm(struct l2cap_chan *chan, int result);
+void __l2cap_physical_cfm(struct l2cap_chan *chan, int result);
 
 #endif /* __L2CAP_H */
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 4b2fea6c1c2a..eaf473ffeef9 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -386,13 +386,17 @@ void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon)
 
 	bredr_chan = mgr->bredr_chan;
 
+	l2cap_chan_lock(bredr_chan);
+
 	set_bit(FLAG_EFS_ENABLE, &bredr_chan->flags);
 	bredr_chan->remote_amp_id = hs_hcon->remote_id;
 	bredr_chan->hs_hcon = hs_hcon;
 	bredr_chan->conn->mtu = hs_hcon->hdev->block_mtu;
 	bredr_chan->fcs = L2CAP_FCS_NONE;
 
-	l2cap_physical_cfm(bredr_chan, 0);
+	__l2cap_physical_cfm(bredr_chan, 0);
+
+	l2cap_chan_unlock(bredr_chan);
 
 	hci_dev_put(bredr_hdev);
 }
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index e4f52a7f08c6..22c4ef926b0d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4611,7 +4611,8 @@ static void l2cap_do_move_cancel(struct l2cap_chan *chan, int result)
 	l2cap_ertm_send(chan);
 }
 
-void l2cap_physical_cfm(struct l2cap_chan *chan, int result)
+/* Invoke with locked chan */
+void __l2cap_physical_cfm(struct l2cap_chan *chan, int result)
 {
 	u8 local_amp_id = chan->local_amp_id;
 	u8 remote_amp_id = chan->remote_amp_id;
@@ -4619,8 +4620,6 @@ void l2cap_physical_cfm(struct l2cap_chan *chan, int result)
 	BT_DBG("chan %p, result %d, local_amp_id %d, remote_amp_id %d",
 	       chan, result, local_amp_id, remote_amp_id);
 
-	l2cap_chan_lock(chan);
-
 	if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) {
 		l2cap_chan_unlock(chan);
 		return;
@@ -4644,8 +4643,6 @@ void l2cap_physical_cfm(struct l2cap_chan *chan, int result)
 			break;
 		}
 	}
-
-	l2cap_chan_unlock(chan);
 }
 
 static inline int l2cap_move_channel_req(struct l2cap_conn *conn,
-- 
cgit v1.2.3-55-g7522


From d1244adc4281eb983a7f41b753164233a7b16b55 Mon Sep 17 00:00:00 2001
From: Szymon Janc
Date: Mon, 12 Nov 2012 11:01:05 +0100
Subject: Bluetooth: Increase HCI command tx timeout

Read Local OOB Data command can take more than 1 second on some chips.
e.g. on CSR 0a12:0001 first call to Read Local OOB Data after reset
takes about 1300ms resulting in tx timeout error.

[27698.368655] Bluetooth: hci0 command 0x0c57 tx timeout

2012-10-31 15:53:36.178585 < HCI Command: Read Local OOB Data (0x03|0x0057) plen 0
2012-10-31 15:53:37.496996 > HCI Event: Command Complete (0x0e) plen 36
    Read Local OOB Data (0x03|0x0057) ncmd 1
    status 0x00
    hash 0x92219d9b447f2aa9dc12dda2ae7bae6a
    randomizer 0xb1948d0febe4ea38ce85c4e66313beba

Signed-off-by: Szymon Janc <szymon.janc@tieto.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 4bbabd85f5e5..45eee08157bb 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -154,7 +154,7 @@ enum {
 #define HCI_DISCONN_TIMEOUT	msecs_to_jiffies(2000)	/* 2 seconds */
 #define HCI_PAIRING_TIMEOUT	msecs_to_jiffies(60000)	/* 60 seconds */
 #define HCI_INIT_TIMEOUT	msecs_to_jiffies(10000)	/* 10 seconds */
-#define HCI_CMD_TIMEOUT		msecs_to_jiffies(1000)	/* 1 second */
+#define HCI_CMD_TIMEOUT		msecs_to_jiffies(2000)	/* 2 seconds */
 #define HCI_ACL_TX_TIMEOUT	msecs_to_jiffies(45000)	/* 45 seconds */
 #define HCI_AUTO_OFF_TIMEOUT	msecs_to_jiffies(2000)	/* 2 seconds */
 
-- 
cgit v1.2.3-55-g7522


From 50d69b5184169caeb85e082f627200da9b0e1677 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Tue, 13 Nov 2012 11:48:00 +0000
Subject: iio: Fix iio_buffer_register stub signature

Match the iio_buffer_register stub signature up to the real function and make
the second parameter const. This fixes a the following warnings if
CONFIG_IIO_BUFFER is disabled:

	drivers/staging/iio/accel/adis16201_core.c: In function ‘adis16201_probe’:
	drivers/staging/iio/accel/adis16201_core.c:536: warning: passing argument 2 of ‘iio_buffer_register’ discards qualifiers from pointer target type
	drivers/staging/iio/accel/adis16203_core.c: In function ‘adis16203_probe’:
	drivers/staging/iio/accel/adis16203_core.c:468: warning: passing argument 2 of ‘iio_buffer_register’ discards qualifiers from pointer target type
	drivers/staging/iio/accel/adis16204_core.c: In function ‘adis16204_probe’:
	drivers/staging/iio/accel/adis16204_core.c:527: warning: passing argument 2 of ‘iio_buffer_register’ discards qualifiers from pointer target type
	drivers/staging/iio/accel/adis16209_core.c: In function ‘adis16209_probe’:
	drivers/staging/iio/accel/adis16209_core.c:542: warning: passing argument 2 of ‘iio_buffer_register’ discards qualifiers from pointer target type
	drivers/staging/iio/accel/adis16240_core.c: In function ‘adis16240_probe’:
	drivers/staging/iio/accel/adis16240_core.c:588: warning: passing argument 2 of ‘iio_buffer_register’ discards qualifiers from pointer target type

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 include/linux/iio/buffer.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h
index 027040569180..f3eea18fdf46 100644
--- a/include/linux/iio/buffer.h
+++ b/include/linux/iio/buffer.h
@@ -195,7 +195,7 @@ bool iio_validate_scan_mask_onehot(struct iio_dev *indio_dev,
 #else /* CONFIG_IIO_BUFFER */
 
 static inline int iio_buffer_register(struct iio_dev *indio_dev,
-					   struct iio_chan_spec *channels,
+					   const struct iio_chan_spec *channels,
 					   int num_channels)
 {
 	return 0;
-- 
cgit v1.2.3-55-g7522


From ec04cb048d79cd778c06e28f34395a46d774800d Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Tue, 13 Nov 2012 13:28:00 +0000
Subject: staging:iio: Move adis library out of staging

Now that the adis library no longer depends on the sw_ring buffer implementation
we can move it out of staging.

While we are at it also sort the entries in the iio Kconfig and Makefile to be
in alphabetical order.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/Kconfig                        |   7 +-
 drivers/iio/Makefile                       |   7 +-
 drivers/iio/imu/Kconfig                    |  11 +
 drivers/iio/imu/Makefile                   |   8 +
 drivers/iio/imu/adis.c                     | 337 ++++++++++++++++++++++++++++
 drivers/iio/imu/adis_buffer.c              | 159 ++++++++++++++
 drivers/iio/imu/adis_trigger.c             |  89 ++++++++
 drivers/staging/iio/accel/adis16201_core.c |   2 +-
 drivers/staging/iio/accel/adis16203_core.c |   2 +-
 drivers/staging/iio/accel/adis16204_core.c |   2 +-
 drivers/staging/iio/accel/adis16209_core.c |   2 +-
 drivers/staging/iio/accel/adis16220.h      |   2 +-
 drivers/staging/iio/accel/adis16240_core.c |   2 +-
 drivers/staging/iio/gyro/adis16260.h       |   2 +-
 drivers/staging/iio/imu/Kconfig            |  12 -
 drivers/staging/iio/imu/Makefile           |   5 -
 drivers/staging/iio/imu/adis.c             | 338 -----------------------------
 drivers/staging/iio/imu/adis.h             | 186 ----------------
 drivers/staging/iio/imu/adis_buffer.c      | 160 --------------
 drivers/staging/iio/imu/adis_trigger.c     |  90 --------
 include/linux/iio/imu/adis.h               | 186 ++++++++++++++++
 21 files changed, 805 insertions(+), 804 deletions(-)
 create mode 100644 drivers/iio/imu/Kconfig
 create mode 100644 drivers/iio/imu/Makefile
 create mode 100644 drivers/iio/imu/adis.c
 create mode 100644 drivers/iio/imu/adis_buffer.c
 create mode 100644 drivers/iio/imu/adis_trigger.c
 delete mode 100644 drivers/staging/iio/imu/adis.c
 delete mode 100644 drivers/staging/iio/imu/adis.h
 delete mode 100644 drivers/staging/iio/imu/adis_buffer.c
 delete mode 100644 drivers/staging/iio/imu/adis_trigger.c
 create mode 100644 include/linux/iio/imu/adis.h

(limited to 'include')

diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig
index 65ae734c607d..b2f963be3993 100644
--- a/drivers/iio/Kconfig
+++ b/drivers/iio/Kconfig
@@ -63,11 +63,12 @@ config IIO_CONSUMERS_PER_TRIGGER
 source "drivers/iio/accel/Kconfig"
 source "drivers/iio/adc/Kconfig"
 source "drivers/iio/amplifiers/Kconfig"
-source "drivers/iio/light/Kconfig"
-source "drivers/iio/frequency/Kconfig"
-source "drivers/iio/dac/Kconfig"
 source "drivers/iio/common/Kconfig"
+source "drivers/iio/dac/Kconfig"
+source "drivers/iio/frequency/Kconfig"
 source "drivers/iio/gyro/Kconfig"
+source "drivers/iio/imu/Kconfig"
+source "drivers/iio/light/Kconfig"
 source "drivers/iio/magnetometer/Kconfig"
 
 endif # IIO
diff --git a/drivers/iio/Makefile b/drivers/iio/Makefile
index 31d76a07ec65..a0e8cdd67e4d 100644
--- a/drivers/iio/Makefile
+++ b/drivers/iio/Makefile
@@ -14,9 +14,10 @@ obj-$(CONFIG_IIO_KFIFO_BUF) += kfifo_buf.o
 obj-y += accel/
 obj-y += adc/
 obj-y += amplifiers/
-obj-y += light/
-obj-y += frequency/
-obj-y += dac/
 obj-y += common/
+obj-y += dac/
 obj-y += gyro/
+obj-y += frequency/
+obj-y += imu/
+obj-y += light/
 obj-y += magnetometer/
diff --git a/drivers/iio/imu/Kconfig b/drivers/iio/imu/Kconfig
new file mode 100644
index 000000000000..c24410c873c7
--- /dev/null
+++ b/drivers/iio/imu/Kconfig
@@ -0,0 +1,11 @@
+config IIO_ADIS_LIB
+	tristate
+	help
+	  A set of IO helper functions for the Analog Devices ADIS* device family.
+
+config IIO_ADIS_LIB_BUFFER
+	bool
+	select IIO_TRIGGERED_BUFFER
+	help
+	  A set of buffer helper functions for the Analog Devices ADIS* device
+	  family.
diff --git a/drivers/iio/imu/Makefile b/drivers/iio/imu/Makefile
new file mode 100644
index 000000000000..97676ab5723d
--- /dev/null
+++ b/drivers/iio/imu/Makefile
@@ -0,0 +1,8 @@
+#
+# Makefile for Inertial Measurement Units
+#
+
+adis_lib-y += adis.o
+adis_lib-$(CONFIG_IIO_ADIS_LIB_BUFFER) += adis_trigger.o
+adis_lib-$(CONFIG_IIO_ADIS_LIB_BUFFER) += adis_buffer.o
+obj-$(CONFIG_IIO_ADIS_LIB) += adis_lib.o
diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c
new file mode 100644
index 000000000000..8259b774078f
--- /dev/null
+++ b/drivers/iio/imu/adis.c
@@ -0,0 +1,337 @@
+/*
+ * Common library for ADIS16XXX devices
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *   Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/delay.h>
+#include <linux/mutex.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/spi/spi.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/module.h>
+#include <asm/unaligned.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/imu/adis.h>
+
+#define ADIS_MSC_CTRL_DATA_RDY_EN	BIT(2)
+#define ADIS_MSC_CTRL_DATA_RDY_POL_HIGH	BIT(1)
+#define ADIS_MSC_CTRL_DATA_RDY_DIO2	BIT(0)
+#define ADIS_GLOB_CMD_SW_RESET		BIT(7)
+
+/**
+ * adis_write_reg_8() - Write single byte to a register
+ * @adis: The adis device
+ * @reg: The address of the register to be written
+ * @val: The value to write
+ */
+int adis_write_reg_8(struct adis *adis, unsigned int reg, uint8_t val)
+{
+	int ret;
+
+	mutex_lock(&adis->txrx_lock);
+	adis->tx[0] = ADIS_WRITE_REG(reg);
+	adis->tx[1] = val;
+
+	ret = spi_write(adis->spi, adis->tx, 2);
+	mutex_unlock(&adis->txrx_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adis_write_reg_8);
+
+/**
+ * adis_write_reg_16() - Write 2 bytes to a pair of registers
+ * @adis: The adis device
+ * @reg: The address of the lower of the two registers
+ * @val: Value to be written
+ */
+int adis_write_reg_16(struct adis *adis, unsigned int reg, uint16_t value)
+{
+	int ret;
+	struct spi_message msg;
+	struct spi_transfer xfers[] = {
+		{
+			.tx_buf = adis->tx,
+			.bits_per_word = 8,
+			.len = 2,
+			.cs_change = 1,
+			.delay_usecs = adis->data->write_delay,
+		}, {
+			.tx_buf = adis->tx + 2,
+			.bits_per_word = 8,
+			.len = 2,
+			.delay_usecs = adis->data->write_delay,
+		},
+	};
+
+	mutex_lock(&adis->txrx_lock);
+	adis->tx[0] = ADIS_WRITE_REG(reg);
+	adis->tx[1] = value & 0xff;
+	adis->tx[2] = ADIS_WRITE_REG(reg + 1);
+	adis->tx[3] = (value >> 8) & 0xff;
+
+	spi_message_init(&msg);
+	spi_message_add_tail(&xfers[0], &msg);
+	spi_message_add_tail(&xfers[1], &msg);
+	ret = spi_sync(adis->spi, &msg);
+	mutex_unlock(&adis->txrx_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adis_write_reg_16);
+
+/**
+ * adis_read_reg_16() - read 2 bytes from a 16-bit register
+ * @adis: The adis device
+ * @reg: The address of the lower of the two registers
+ * @val: The value read back from the device
+ */
+int adis_read_reg_16(struct adis *adis, unsigned int reg, uint16_t *val)
+{
+	struct spi_message msg;
+	int ret;
+	struct spi_transfer xfers[] = {
+		{
+			.tx_buf = adis->tx,
+			.bits_per_word = 8,
+			.len = 2,
+			.cs_change = 1,
+			.delay_usecs = adis->data->read_delay,
+		}, {
+			.rx_buf = adis->rx,
+			.bits_per_word = 8,
+			.len = 2,
+			.delay_usecs = adis->data->read_delay,
+		},
+	};
+
+	mutex_lock(&adis->txrx_lock);
+	adis->tx[0] = ADIS_READ_REG(reg);
+	adis->tx[1] = 0;
+
+	spi_message_init(&msg);
+	spi_message_add_tail(&xfers[0], &msg);
+	spi_message_add_tail(&xfers[1], &msg);
+	ret = spi_sync(adis->spi, &msg);
+	if (ret) {
+		dev_err(&adis->spi->dev, "Failed to read 16 bit register 0x%02X: %d\n",
+				reg, ret);
+		goto error_ret;
+	}
+	*val = get_unaligned_be16(adis->rx);
+
+error_ret:
+	mutex_unlock(&adis->txrx_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adis_read_reg_16);
+
+/**
+ * adis_enable_irq() - Enable or disable data ready IRQ
+ * @adis: The adis device
+ * @enable: Whether to enable the IRQ
+ *
+ * Returns 0 on success, negative error code otherwise
+ */
+int adis_enable_irq(struct adis *adis, bool enable)
+{
+	int ret = 0;
+	uint16_t msc;
+
+	ret = adis_read_reg_16(adis, adis->data->msc_ctrl_reg, &msc);
+	if (ret)
+		goto error_ret;
+
+	msc |= ADIS_MSC_CTRL_DATA_RDY_POL_HIGH;
+	msc &= ~ADIS_MSC_CTRL_DATA_RDY_DIO2;
+	if (enable)
+		msc |= ADIS_MSC_CTRL_DATA_RDY_EN;
+	else
+		msc &= ~ADIS_MSC_CTRL_DATA_RDY_EN;
+
+	ret = adis_write_reg_16(adis, adis->data->msc_ctrl_reg, msc);
+
+error_ret:
+	return ret;
+}
+EXPORT_SYMBOL(adis_enable_irq);
+
+/**
+ * adis_check_status() - Check the device for error conditions
+ * @adis: The adis device
+ *
+ * Returns 0 on success, a negative error code otherwise
+ */
+int adis_check_status(struct adis *adis)
+{
+	uint16_t status;
+	int ret;
+	int i;
+
+	ret = adis_read_reg_16(adis, adis->data->diag_stat_reg, &status);
+	if (ret < 0)
+		return ret;
+
+	status &= adis->data->status_error_mask;
+
+	if (status == 0)
+		return 0;
+
+	for (i = 0; i < 16; ++i) {
+		if (status & BIT(i)) {
+			dev_err(&adis->spi->dev, "%s.\n",
+				adis->data->status_error_msgs[i]);
+		}
+	}
+
+	return -EIO;
+}
+EXPORT_SYMBOL_GPL(adis_check_status);
+
+/**
+ * adis_reset() - Reset the device
+ * @adis: The adis device
+ *
+ * Returns 0 on success, a negative error code otherwise
+ */
+int adis_reset(struct adis *adis)
+{
+	int ret;
+
+	ret = adis_write_reg_8(adis, adis->data->glob_cmd_reg,
+			ADIS_GLOB_CMD_SW_RESET);
+	if (ret)
+		dev_err(&adis->spi->dev, "Failed to reset device: %d\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adis_reset);
+
+static int adis_self_test(struct adis *adis)
+{
+	int ret;
+
+	ret = adis_write_reg_16(adis, adis->data->msc_ctrl_reg,
+			adis->data->self_test_mask);
+	if (ret) {
+		dev_err(&adis->spi->dev, "Failed to initiate self test: %d\n",
+			ret);
+		return ret;
+	}
+
+	msleep(adis->data->startup_delay);
+
+	return adis_check_status(adis);
+}
+
+/**
+ * adis_inital_startup() - Performs device self-test
+ * @adis: The adis device
+ *
+ * Returns 0 if the device is operational, a negative error code otherwise.
+ *
+ * This function should be called early on in the device initialization sequence
+ * to ensure that the device is in a sane and known state and that it is usable.
+ */
+int adis_initial_startup(struct adis *adis)
+{
+	int ret;
+
+	ret = adis_self_test(adis);
+	if (ret) {
+		dev_err(&adis->spi->dev, "Self-test failed, trying reset.\n");
+		adis_reset(adis);
+		msleep(adis->data->startup_delay);
+		ret = adis_self_test(adis);
+		if (ret) {
+			dev_err(&adis->spi->dev, "Second self-test failed, giving up.\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adis_initial_startup);
+
+/**
+ * adis_single_conversion() - Performs a single sample conversion
+ * @indio_dev: The IIO device
+ * @chan: The IIO channel
+ * @error_mask: Mask for the error bit
+ * @val: Result of the conversion
+ *
+ * Returns IIO_VAL_INT on success, a negative error code otherwise.
+ *
+ * The function performs a single conversion on a given channel and post
+ * processes the value accordingly to the channel spec. If a error_mask is given
+ * the function will check if the mask is set in the returned raw value. If it
+ * is set the function will perform a self-check. If the device does not report
+ * a error bit in the channels raw value set error_mask to 0.
+ */
+int adis_single_conversion(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, unsigned int error_mask, int *val)
+{
+	struct adis *adis = iio_device_get_drvdata(indio_dev);
+	uint16_t val16;
+	int ret;
+
+	mutex_lock(&indio_dev->mlock);
+
+	ret = adis_read_reg_16(adis, chan->address, &val16);
+	if (ret)
+		goto err_unlock;
+
+	if (val16 & error_mask) {
+		ret = adis_check_status(adis);
+		if (ret)
+			goto err_unlock;
+	}
+
+	if (chan->scan_type.sign == 's')
+		*val = sign_extend32(val16, chan->scan_type.realbits - 1);
+	else
+		*val = val16 & ((1 << chan->scan_type.realbits) - 1);
+
+	ret = IIO_VAL_INT;
+err_unlock:
+	mutex_unlock(&indio_dev->mlock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adis_single_conversion);
+
+/**
+ * adis_init() - Initialize adis device structure
+ * @adis:	The adis device
+ * @indio_dev:	The iio device
+ * @spi:	The spi device
+ * @data:	Chip specific data
+ *
+ * Returns 0 on success, a negative error code otherwise.
+ *
+ * This function must be called, before any other adis helper function may be
+ * called.
+ */
+int adis_init(struct adis *adis, struct iio_dev *indio_dev,
+	struct spi_device *spi, const struct adis_data *data)
+{
+	mutex_init(&adis->txrx_lock);
+	adis->spi = spi;
+	adis->data = data;
+	iio_device_set_drvdata(indio_dev, adis);
+
+	return adis_enable_irq(adis, false);
+}
+EXPORT_SYMBOL_GPL(adis_init);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("Common library code for ADIS16XXX devices");
diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
new file mode 100644
index 000000000000..a91b4cbdc73a
--- /dev/null
+++ b/drivers/iio/imu/adis_buffer.c
@@ -0,0 +1,159 @@
+/*
+ * Common library for ADIS16XXX devices
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *   Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/export.h>
+#include <linux/interrupt.h>
+#include <linux/mutex.h>
+#include <linux/kernel.h>
+#include <linux/spi/spi.h>
+#include <linux/slab.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
+#include <linux/iio/imu/adis.h>
+
+int adis_update_scan_mode(struct iio_dev *indio_dev,
+	const unsigned long *scan_mask)
+{
+	struct adis *adis = iio_device_get_drvdata(indio_dev);
+	const struct iio_chan_spec *chan;
+	unsigned int scan_count;
+	unsigned int i, j;
+	__be16 *tx, *rx;
+
+	kfree(adis->xfer);
+	kfree(adis->buffer);
+
+	scan_count = indio_dev->scan_bytes / 2;
+
+	adis->xfer = kcalloc(scan_count + 1, sizeof(*adis->xfer), GFP_KERNEL);
+	if (!adis->xfer)
+		return -ENOMEM;
+
+	adis->buffer = kzalloc(indio_dev->scan_bytes * 2, GFP_KERNEL);
+	if (!adis->buffer)
+		return -ENOMEM;
+
+	rx = adis->buffer;
+	tx = rx + indio_dev->scan_bytes;
+
+	spi_message_init(&adis->msg);
+
+	for (j = 0; j <= scan_count; j++) {
+		adis->xfer[j].bits_per_word = 8;
+		if (j != scan_count)
+			adis->xfer[j].cs_change = 1;
+		adis->xfer[j].len = 2;
+		adis->xfer[j].delay_usecs = adis->data->read_delay;
+		if (j < scan_count)
+			adis->xfer[j].tx_buf = &tx[j];
+		if (j >= 1)
+			adis->xfer[j].rx_buf = &rx[j - 1];
+		spi_message_add_tail(&adis->xfer[j], &adis->msg);
+	}
+
+	chan = indio_dev->channels;
+	for (i = 0; i < indio_dev->num_channels; i++, chan++) {
+		if (!test_bit(chan->scan_index, scan_mask))
+			continue;
+		*tx++ = cpu_to_be16(chan->address << 8);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adis_update_scan_mode);
+
+static irqreturn_t adis_trigger_handler(int irq, void *p)
+{
+	struct iio_poll_func *pf = p;
+	struct iio_dev *indio_dev = pf->indio_dev;
+	struct adis *adis = iio_device_get_drvdata(indio_dev);
+	int ret;
+
+	if (!adis->buffer)
+		return -ENOMEM;
+
+	ret = spi_sync(adis->spi, &adis->msg);
+	if (ret)
+		dev_err(&adis->spi->dev, "Failed to read data: %d", ret);
+
+	/* Guaranteed to be aligned with 8 byte boundary */
+	if (indio_dev->scan_timestamp) {
+		void *b = adis->buffer + indio_dev->scan_bytes - sizeof(s64);
+		*(s64 *)b = pf->timestamp;
+	}
+
+	iio_push_to_buffers(indio_dev, adis->buffer);
+
+	iio_trigger_notify_done(indio_dev->trig);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * adis_setup_buffer_and_trigger() - Sets up buffer and trigger for the adis device
+ * @adis: The adis device.
+ * @indio_dev: The IIO device.
+ * @trigger_handler: Optional trigger handler, may be NULL.
+ *
+ * Returns 0 on success, a negative error code otherwise.
+ *
+ * This function sets up the buffer and trigger for a adis devices.  If
+ * 'trigger_handler' is NULL the default trigger handler will be used. The
+ * default trigger handler will simply read the registers assigned to the
+ * currently active channels.
+ *
+ * adis_cleanup_buffer_and_trigger() should be called to free the resources
+ * allocated by this function.
+ */
+int adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
+	irqreturn_t (*trigger_handler)(int, void *))
+{
+	int ret;
+
+	if (!trigger_handler)
+		trigger_handler = adis_trigger_handler;
+
+	ret = iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+		trigger_handler, NULL);
+	if (ret)
+		return ret;
+
+	if (adis->spi->irq) {
+		ret = adis_probe_trigger(adis, indio_dev);
+		if (ret)
+			goto error_buffer_cleanup;
+	}
+	return 0;
+
+error_buffer_cleanup:
+	iio_triggered_buffer_cleanup(indio_dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adis_setup_buffer_and_trigger);
+
+/**
+ * adis_cleanup_buffer_and_trigger() - Free buffer and trigger resources
+ * @adis: The adis device.
+ * @indio_dev: The IIO device.
+ *
+ * Frees resources allocated by adis_setup_buffer_and_trigger()
+ */
+void adis_cleanup_buffer_and_trigger(struct adis *adis,
+	struct iio_dev *indio_dev)
+{
+	if (adis->spi->irq)
+		adis_remove_trigger(adis);
+	kfree(adis->buffer);
+	kfree(adis->xfer);
+	iio_triggered_buffer_cleanup(indio_dev);
+}
+EXPORT_SYMBOL_GPL(adis_cleanup_buffer_and_trigger);
diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c
new file mode 100644
index 000000000000..5a24c9cac343
--- /dev/null
+++ b/drivers/iio/imu/adis_trigger.c
@@ -0,0 +1,89 @@
+/*
+ * Common library for ADIS16XXX devices
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *   Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/spi/spi.h>
+#include <linux/export.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/imu/adis.h>
+
+static int adis_data_rdy_trigger_set_state(struct iio_trigger *trig,
+						bool state)
+{
+	struct adis *adis = trig->private_data;
+
+	return adis_enable_irq(adis, state);
+}
+
+static const struct iio_trigger_ops adis_trigger_ops = {
+	.owner = THIS_MODULE,
+	.set_trigger_state = &adis_data_rdy_trigger_set_state,
+};
+
+/**
+ * adis_probe_trigger() - Sets up trigger for a adis device
+ * @adis: The adis device
+ * @indio_dev: The IIO device
+ *
+ * Returns 0 on success or a negative error code
+ *
+ * adis_remove_trigger() should be used to free the trigger.
+ */
+int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev)
+{
+	int ret;
+
+	adis->trig = iio_trigger_alloc("%s-dev%d", indio_dev->name,
+					indio_dev->id);
+	if (adis->trig == NULL)
+		return -ENOMEM;
+
+	ret = request_irq(adis->spi->irq,
+			  &iio_trigger_generic_data_rdy_poll,
+			  IRQF_TRIGGER_RISING,
+			  indio_dev->name,
+			  adis->trig);
+	if (ret)
+		goto error_free_trig;
+
+	adis->trig->dev.parent = &adis->spi->dev;
+	adis->trig->ops = &adis_trigger_ops;
+	adis->trig->private_data = adis;
+	ret = iio_trigger_register(adis->trig);
+
+	indio_dev->trig = adis->trig;
+	if (ret)
+		goto error_free_irq;
+
+	return 0;
+
+error_free_irq:
+	free_irq(adis->spi->irq, adis->trig);
+error_free_trig:
+	iio_trigger_free(adis->trig);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adis_probe_trigger);
+
+/**
+ * adis_remove_trigger() - Remove trigger for a adis devices
+ * @adis: The adis device
+ *
+ * Removes the trigger previously registered with adis_probe_trigger().
+ */
+void adis_remove_trigger(struct adis *adis)
+{
+	iio_trigger_unregister(adis->trig);
+	free_irq(adis->spi->irq, adis->trig);
+	iio_trigger_free(adis->trig);
+}
+EXPORT_SYMBOL_GPL(adis_remove_trigger);
diff --git a/drivers/staging/iio/accel/adis16201_core.c b/drivers/staging/iio/accel/adis16201_core.c
index 833dd6b73bc3..ccdc8d23f6a3 100644
--- a/drivers/staging/iio/accel/adis16201_core.c
+++ b/drivers/staging/iio/accel/adis16201_core.c
@@ -18,9 +18,9 @@
 #include <linux/iio/iio.h>
 #include <linux/iio/sysfs.h>
 #include <linux/iio/buffer.h>
+#include <linux/iio/imu/adis.h>
 
 #include "adis16201.h"
-#include "../imu/adis.h"
 
 static const u8 adis16201_addresses[] = {
 	[ADIS16201_SCAN_ACC_X] = ADIS16201_XACCL_OFFS,
diff --git a/drivers/staging/iio/accel/adis16203_core.c b/drivers/staging/iio/accel/adis16203_core.c
index f631e578fbd1..202985ea3531 100644
--- a/drivers/staging/iio/accel/adis16203_core.c
+++ b/drivers/staging/iio/accel/adis16203_core.c
@@ -18,9 +18,9 @@
 #include <linux/iio/iio.h>
 #include <linux/iio/sysfs.h>
 #include <linux/iio/buffer.h>
+#include <linux/iio/imu/adis.h>
 
 #include "adis16203.h"
-#include "../imu/adis.h"
 
 #define DRIVER_NAME		"adis16203"
 
diff --git a/drivers/staging/iio/accel/adis16204_core.c b/drivers/staging/iio/accel/adis16204_core.c
index dbec841ce30c..6dafad67cd23 100644
--- a/drivers/staging/iio/accel/adis16204_core.c
+++ b/drivers/staging/iio/accel/adis16204_core.c
@@ -21,9 +21,9 @@
 #include <linux/iio/iio.h>
 #include <linux/iio/sysfs.h>
 #include <linux/iio/buffer.h>
+#include <linux/iio/imu/adis.h>
 
 #include "adis16204.h"
-#include "../imu/adis.h"
 
 /* Unique to this driver currently */
 
diff --git a/drivers/staging/iio/accel/adis16209_core.c b/drivers/staging/iio/accel/adis16209_core.c
index f9f9d582b32d..d2921c30a8bb 100644
--- a/drivers/staging/iio/accel/adis16209_core.c
+++ b/drivers/staging/iio/accel/adis16209_core.c
@@ -19,9 +19,9 @@
 #include <linux/iio/iio.h>
 #include <linux/iio/sysfs.h>
 #include <linux/iio/buffer.h>
+#include <linux/iio/imu/adis.h>
 
 #include "adis16209.h"
-#include "../imu/adis.h"
 
 static const u8 adis16209_addresses[8][1] = {
 	[ADIS16209_SCAN_SUPPLY] = { },
diff --git a/drivers/staging/iio/accel/adis16220.h b/drivers/staging/iio/accel/adis16220.h
index 7cc4d2f3ec28..a894ad7fb26d 100644
--- a/drivers/staging/iio/accel/adis16220.h
+++ b/drivers/staging/iio/accel/adis16220.h
@@ -1,7 +1,7 @@
 #ifndef SPI_ADIS16220_H_
 #define SPI_ADIS16220_H_
 
-#include "../imu/adis.h"
+#include <linux/iio/imu/adis.h>
 
 #define ADIS16220_STARTUP_DELAY	220 /* ms */
 
diff --git a/drivers/staging/iio/accel/adis16240_core.c b/drivers/staging/iio/accel/adis16240_core.c
index 3d1a8a9921ad..d098b49cc18b 100644
--- a/drivers/staging/iio/accel/adis16240_core.c
+++ b/drivers/staging/iio/accel/adis16240_core.c
@@ -22,9 +22,9 @@
 #include <linux/iio/iio.h>
 #include <linux/iio/sysfs.h>
 #include <linux/iio/buffer.h>
+#include <linux/iio/imu/adis.h>
 
 #include "adis16240.h"
-#include "../imu/adis.h"
 
 static ssize_t adis16240_spi_read_signed(struct device *dev,
 		struct device_attribute *attr,
diff --git a/drivers/staging/iio/gyro/adis16260.h b/drivers/staging/iio/gyro/adis16260.h
index ea5eba205bbf..df3c0b7e954a 100644
--- a/drivers/staging/iio/gyro/adis16260.h
+++ b/drivers/staging/iio/gyro/adis16260.h
@@ -2,7 +2,7 @@
 #define SPI_ADIS16260_H_
 
 #include "adis16260_platform_data.h"
-#include "../imu/adis.h"
+#include <linux/iio/imu/adis.h>
 
 #define ADIS16260_STARTUP_DELAY	220 /* ms */
 
diff --git a/drivers/staging/iio/imu/Kconfig b/drivers/staging/iio/imu/Kconfig
index 2c564edeb172..2c2f47de2630 100644
--- a/drivers/staging/iio/imu/Kconfig
+++ b/drivers/staging/iio/imu/Kconfig
@@ -15,15 +15,3 @@ config ADIS16400
 	  (adis16400 series also have magnetometers).
 
 endmenu
-
-config IIO_ADIS_LIB
-	tristate
-	help
-	  A set of IO helper functions for the Analog Devices ADIS* device family.
-
-config IIO_ADIS_LIB_BUFFER
-	bool
-	select IIO_TRIGGERED_BUFFER
-	help
-	  A set of buffer helper functions for the Analog Devices ADIS* device
-	  family.
diff --git a/drivers/staging/iio/imu/Makefile b/drivers/staging/iio/imu/Makefile
index 65dafba1e5df..3400a13d1522 100644
--- a/drivers/staging/iio/imu/Makefile
+++ b/drivers/staging/iio/imu/Makefile
@@ -5,8 +5,3 @@
 adis16400-y             := adis16400_core.o
 adis16400-$(CONFIG_IIO_BUFFER) += adis16400_ring.o adis16400_trigger.o
 obj-$(CONFIG_ADIS16400) += adis16400.o
-
-adis_lib-y += adis.o
-adis_lib-$(CONFIG_IIO_ADIS_LIB_BUFFER) += adis_trigger.o
-adis_lib-$(CONFIG_IIO_ADIS_LIB_BUFFER) += adis_buffer.o
-obj-$(CONFIG_IIO_ADIS_LIB) += adis_lib.o
diff --git a/drivers/staging/iio/imu/adis.c b/drivers/staging/iio/imu/adis.c
deleted file mode 100644
index 0bd21022e4c0..000000000000
--- a/drivers/staging/iio/imu/adis.c
+++ /dev/null
@@ -1,338 +0,0 @@
-/*
- * Common library for ADIS16XXX devices
- *
- * Copyright 2012 Analog Devices Inc.
- *   Author: Lars-Peter Clausen <lars@metafoo.de>
- *
- * Licensed under the GPL-2 or later.
- */
-
-#include <linux/delay.h>
-#include <linux/mutex.h>
-#include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/spi/spi.h>
-#include <linux/slab.h>
-#include <linux/sysfs.h>
-#include <linux/module.h>
-#include <asm/unaligned.h>
-
-#include <linux/iio/iio.h>
-#include <linux/iio/sysfs.h>
-#include <linux/iio/buffer.h>
-
-#include "adis.h"
-
-#define ADIS_MSC_CTRL_DATA_RDY_EN	BIT(2)
-#define ADIS_MSC_CTRL_DATA_RDY_POL_HIGH	BIT(1)
-#define ADIS_MSC_CTRL_DATA_RDY_DIO2	BIT(0)
-#define ADIS_GLOB_CMD_SW_RESET		BIT(7)
-
-/**
- * adis_write_reg_8() - Write single byte to a register
- * @adis: The adis device
- * @reg: The address of the register to be written
- * @val: The value to write
- */
-int adis_write_reg_8(struct adis *adis, unsigned int reg, uint8_t val)
-{
-	int ret;
-
-	mutex_lock(&adis->txrx_lock);
-	adis->tx[0] = ADIS_WRITE_REG(reg);
-	adis->tx[1] = val;
-
-	ret = spi_write(adis->spi, adis->tx, 2);
-	mutex_unlock(&adis->txrx_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_write_reg_8);
-
-/**
- * adis_write_reg_16() - Write 2 bytes to a pair of registers
- * @adis: The adis device
- * @reg: The address of the lower of the two registers
- * @val: Value to be written
- */
-int adis_write_reg_16(struct adis *adis, unsigned int reg, uint16_t value)
-{
-	int ret;
-	struct spi_message msg;
-	struct spi_transfer xfers[] = {
-		{
-			.tx_buf = adis->tx,
-			.bits_per_word = 8,
-			.len = 2,
-			.cs_change = 1,
-			.delay_usecs = adis->data->write_delay,
-		}, {
-			.tx_buf = adis->tx + 2,
-			.bits_per_word = 8,
-			.len = 2,
-			.delay_usecs = adis->data->write_delay,
-		},
-	};
-
-	mutex_lock(&adis->txrx_lock);
-	adis->tx[0] = ADIS_WRITE_REG(reg);
-	adis->tx[1] = value & 0xff;
-	adis->tx[2] = ADIS_WRITE_REG(reg + 1);
-	adis->tx[3] = (value >> 8) & 0xff;
-
-	spi_message_init(&msg);
-	spi_message_add_tail(&xfers[0], &msg);
-	spi_message_add_tail(&xfers[1], &msg);
-	ret = spi_sync(adis->spi, &msg);
-	mutex_unlock(&adis->txrx_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_write_reg_16);
-
-/**
- * adis_read_reg_16() - read 2 bytes from a 16-bit register
- * @adis: The adis device
- * @reg: The address of the lower of the two registers
- * @val: The value read back from the device
- */
-int adis_read_reg_16(struct adis *adis, unsigned int reg, uint16_t *val)
-{
-	struct spi_message msg;
-	int ret;
-	struct spi_transfer xfers[] = {
-		{
-			.tx_buf = adis->tx,
-			.bits_per_word = 8,
-			.len = 2,
-			.cs_change = 1,
-			.delay_usecs = adis->data->read_delay,
-		}, {
-			.rx_buf = adis->rx,
-			.bits_per_word = 8,
-			.len = 2,
-			.delay_usecs = adis->data->read_delay,
-		},
-	};
-
-	mutex_lock(&adis->txrx_lock);
-	adis->tx[0] = ADIS_READ_REG(reg);
-	adis->tx[1] = 0;
-
-	spi_message_init(&msg);
-	spi_message_add_tail(&xfers[0], &msg);
-	spi_message_add_tail(&xfers[1], &msg);
-	ret = spi_sync(adis->spi, &msg);
-	if (ret) {
-		dev_err(&adis->spi->dev, "Failed to read 16 bit register 0x%02X: %d\n",
-				reg, ret);
-		goto error_ret;
-	}
-	*val = get_unaligned_be16(adis->rx);
-
-error_ret:
-	mutex_unlock(&adis->txrx_lock);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_read_reg_16);
-
-/**
- * adis_enable_irq() - Enable or disable data ready IRQ
- * @adis: The adis device
- * @enable: Whether to enable the IRQ
- *
- * Returns 0 on success, negative error code otherwise
- */
-int adis_enable_irq(struct adis *adis, bool enable)
-{
-	int ret = 0;
-	uint16_t msc;
-
-	ret = adis_read_reg_16(adis, adis->data->msc_ctrl_reg, &msc);
-	if (ret)
-		goto error_ret;
-
-	msc |= ADIS_MSC_CTRL_DATA_RDY_POL_HIGH;
-	msc &= ~ADIS_MSC_CTRL_DATA_RDY_DIO2;
-	if (enable)
-		msc |= ADIS_MSC_CTRL_DATA_RDY_EN;
-	else
-		msc &= ~ADIS_MSC_CTRL_DATA_RDY_EN;
-
-	ret = adis_write_reg_16(adis, adis->data->msc_ctrl_reg, msc);
-
-error_ret:
-	return ret;
-}
-EXPORT_SYMBOL(adis_enable_irq);
-
-/**
- * adis_check_status() - Check the device for error conditions
- * @adis: The adis device
- *
- * Returns 0 on success, a negative error code otherwise
- */
-int adis_check_status(struct adis *adis)
-{
-	uint16_t status;
-	int ret;
-	int i;
-
-	ret = adis_read_reg_16(adis, adis->data->diag_stat_reg, &status);
-	if (ret < 0)
-		return ret;
-
-	status &= adis->data->status_error_mask;
-
-	if (status == 0)
-		return 0;
-
-	for (i = 0; i < 16; ++i) {
-		if (status & BIT(i)) {
-			dev_err(&adis->spi->dev, "%s.\n",
-				adis->data->status_error_msgs[i]);
-		}
-	}
-
-	return -EIO;
-}
-EXPORT_SYMBOL_GPL(adis_check_status);
-
-/**
- * adis_reset() - Reset the device
- * @adis: The adis device
- *
- * Returns 0 on success, a negative error code otherwise
- */
-int adis_reset(struct adis *adis)
-{
-	int ret;
-
-	ret = adis_write_reg_8(adis, adis->data->glob_cmd_reg,
-			ADIS_GLOB_CMD_SW_RESET);
-	if (ret)
-		dev_err(&adis->spi->dev, "Failed to reset device: %d\n", ret);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_reset);
-
-static int adis_self_test(struct adis *adis)
-{
-	int ret;
-
-	ret = adis_write_reg_16(adis, adis->data->msc_ctrl_reg,
-			adis->data->self_test_mask);
-	if (ret) {
-		dev_err(&adis->spi->dev, "Failed to initiate self test: %d\n",
-			ret);
-		return ret;
-	}
-
-	msleep(adis->data->startup_delay);
-
-	return adis_check_status(adis);
-}
-
-/**
- * adis_inital_startup() - Performs device self-test
- * @adis: The adis device
- *
- * Returns 0 if the device is operational, a negative error code otherwise.
- *
- * This function should be called early on in the device initialization sequence
- * to ensure that the device is in a sane and known state and that it is usable.
- */
-int adis_initial_startup(struct adis *adis)
-{
-	int ret;
-
-	ret = adis_self_test(adis);
-	if (ret) {
-		dev_err(&adis->spi->dev, "Self-test failed, trying reset.\n");
-		adis_reset(adis);
-		msleep(adis->data->startup_delay);
-		ret = adis_self_test(adis);
-		if (ret) {
-			dev_err(&adis->spi->dev, "Second self-test failed, giving up.\n");
-			return ret;
-		}
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(adis_initial_startup);
-
-/**
- * adis_single_conversion() - Performs a single sample conversion
- * @indio_dev: The IIO device
- * @chan: The IIO channel
- * @error_mask: Mask for the error bit
- * @val: Result of the conversion
- *
- * Returns IIO_VAL_INT on success, a negative error code otherwise.
- *
- * The function performs a single conversion on a given channel and post
- * processes the value accordingly to the channel spec. If a error_mask is given
- * the function will check if the mask is set in the returned raw value. If it
- * is set the function will perform a self-check. If the device does not report
- * a error bit in the channels raw value set error_mask to 0.
- */
-int adis_single_conversion(struct iio_dev *indio_dev,
-	const struct iio_chan_spec *chan, unsigned int error_mask, int *val)
-{
-	struct adis *adis = iio_device_get_drvdata(indio_dev);
-	uint16_t val16;
-	int ret;
-
-	mutex_lock(&indio_dev->mlock);
-
-	ret = adis_read_reg_16(adis, chan->address, &val16);
-	if (ret)
-		goto err_unlock;
-
-	if (val16 & error_mask) {
-		ret = adis_check_status(adis);
-		if (ret)
-			goto err_unlock;
-	}
-
-	if (chan->scan_type.sign == 's')
-		*val = sign_extend32(val16, chan->scan_type.realbits - 1);
-	else
-		*val = val16 & ((1 << chan->scan_type.realbits) - 1);
-
-	ret = IIO_VAL_INT;
-err_unlock:
-	mutex_unlock(&indio_dev->mlock);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_single_conversion);
-
-/**
- * adis_init() - Initialize adis device structure
- * @adis:	The adis device
- * @indio_dev:	The iio device
- * @spi:	The spi device
- * @data:	Chip specific data
- *
- * Returns 0 on success, a negative error code otherwise.
- *
- * This function must be called, before any other adis helper function may be
- * called.
- */
-int adis_init(struct adis *adis, struct iio_dev *indio_dev,
-	struct spi_device *spi, const struct adis_data *data)
-{
-	mutex_init(&adis->txrx_lock);
-	adis->spi = spi;
-	adis->data = data;
-	iio_device_set_drvdata(indio_dev, adis);
-
-	return adis_enable_irq(adis, false);
-}
-EXPORT_SYMBOL_GPL(adis_init);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
-MODULE_DESCRIPTION("Common library code for ADIS16XXX devices");
diff --git a/drivers/staging/iio/imu/adis.h b/drivers/staging/iio/imu/adis.h
deleted file mode 100644
index 8c3304d44b97..000000000000
--- a/drivers/staging/iio/imu/adis.h
+++ /dev/null
@@ -1,186 +0,0 @@
-/*
- * Common library for ADIS16XXX devices
- *
- * Copyright 2012 Analog Devices Inc.
- *   Author: Lars-Peter Clausen <lars@metafoo.de>
- *
- * Licensed under the GPL-2 or later.
- */
-
-#ifndef __IIO_ADIS_H__
-#define __IIO_ADIS_H__
-
-#include <linux/spi/spi.h>
-#include <linux/interrupt.h>
-#include <linux/iio/types.h>
-
-#define ADIS_WRITE_REG(reg) (0x80 | (reg))
-#define ADIS_READ_REG(reg) (reg)
-
-/**
- * struct adis_data - ADIS chip variant specific data
- * @read_delay: SPI delay for read operations in us
- * @write_delay: SPI delay for write operations in us
- * @glob_cmd_reg: Register address of the GLOB_CMD register
- * @msc_ctrl_reg: Register address of the MSC_CTRL register
- * @diag_stat_reg: Register address of the DIAG_STAT register
- * @status_error_msgs: Array of error messgaes
- * @status_error_mask:
- */
-struct adis_data {
-	unsigned int read_delay;
-	unsigned int write_delay;
-
-	unsigned int glob_cmd_reg;
-	unsigned int msc_ctrl_reg;
-	unsigned int diag_stat_reg;
-
-	unsigned int self_test_mask;
-	unsigned int startup_delay;
-
-	const char * const *status_error_msgs;
-	unsigned int status_error_mask;
-};
-
-struct adis {
-	struct spi_device	*spi;
-	struct iio_trigger	*trig;
-
-	const struct adis_data	*data;
-
-	struct mutex		txrx_lock;
-	struct spi_message	msg;
-	struct spi_transfer	*xfer;
-	void			*buffer;
-
-	uint8_t			tx[8] ____cacheline_aligned;
-	uint8_t			rx[4];
-};
-
-int adis_init(struct adis *adis, struct iio_dev *indio_dev,
-	struct spi_device *spi, const struct adis_data *data);
-int adis_reset(struct adis *adis);
-
-int adis_write_reg_8(struct adis *adis, unsigned int reg, uint8_t val);
-int adis_write_reg_16(struct adis *adis, unsigned int reg, uint16_t val);
-int adis_read_reg_16(struct adis *adis, unsigned int reg, uint16_t *val);
-
-int adis_enable_irq(struct adis *adis, bool enable);
-int adis_check_status(struct adis *adis);
-
-int adis_initial_startup(struct adis *adis);
-
-int adis_single_conversion(struct iio_dev *indio_dev,
-	const struct iio_chan_spec *chan, unsigned int error_mask,
-	int *val);
-
-#define ADIS_VOLTAGE_CHAN(addr, si, chan, name, bits) { \
-	.type = IIO_VOLTAGE, \
-	.indexed = 1, \
-	.channel = (chan), \
-	.extend_name = name, \
-	.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \
-		IIO_CHAN_INFO_SCALE_SEPARATE_BIT, \
-	.address = (addr), \
-	.scan_index = (si), \
-	.scan_type = { \
-		.sign = 'u', \
-		.realbits = (bits), \
-		.storagebits = 16, \
-		.endianness = IIO_BE, \
-	}, \
-}
-
-#define ADIS_SUPPLY_CHAN(addr, si, bits) \
-	ADIS_VOLTAGE_CHAN(addr, si, 0, "supply", bits)
-
-#define ADIS_AUX_ADC_CHAN(addr, si, bits) \
-	ADIS_VOLTAGE_CHAN(addr, si, 1, NULL, bits)
-
-#define ADIS_TEMP_CHAN(addr, si, bits) { \
-	.type = IIO_TEMP, \
-	.indexed = 1, \
-	.channel = 0, \
-	.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \
-		IIO_CHAN_INFO_SCALE_SEPARATE_BIT | \
-		IIO_CHAN_INFO_OFFSET_SEPARATE_BIT, \
-	.address = (addr), \
-	.scan_index = (si), \
-	.scan_type = { \
-		.sign = 'u', \
-		.realbits = (bits), \
-		.storagebits = 16, \
-		.endianness = IIO_BE, \
-	}, \
-}
-
-#define ADIS_MOD_CHAN(_type, mod, addr, si, info, bits) { \
-	.type = (_type), \
-	.modified = 1, \
-	.channel2 = IIO_MOD_ ## mod, \
-	.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \
-		 IIO_CHAN_INFO_SCALE_SHARED_BIT | \
-		 info, \
-	.address = (addr), \
-	.scan_index = (si), \
-	.scan_type = { \
-		.sign = 's', \
-		.realbits = (bits), \
-		.storagebits = 16, \
-		.endianness = IIO_BE, \
-	}, \
-}
-
-#define ADIS_ACCEL_CHAN(mod, addr, si, info, bits) \
-	ADIS_MOD_CHAN(IIO_ACCEL, mod, addr, si, info, bits)
-
-#define ADIS_GYRO_CHAN(mod, addr, si, info, bits) \
-	ADIS_MOD_CHAN(IIO_ANGL_VEL, mod, addr, si, info, bits)
-
-#define ADIS_INCLI_CHAN(mod, addr, si, info, bits) \
-	ADIS_MOD_CHAN(IIO_INCLI, mod, addr, si, info, bits)
-
-#define ADIS_ROT_CHAN(mod, addr, si, info, bits) \
-	ADIS_MOD_CHAN(IIO_ROT, mod, addr, si, info, bits)
-
-#ifdef CONFIG_IIO_ADIS_LIB_BUFFER
-
-int adis_setup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *));
-void adis_cleanup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev);
-
-int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev);
-void adis_remove_trigger(struct adis *adis);
-
-int adis_update_scan_mode(struct iio_dev *indio_dev,
-	const unsigned long *scan_mask);
-
-#else /* CONFIG_IIO_BUFFER */
-
-static inline int adis_setup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *))
-{
-	return 0;
-}
-
-static inline void adis_cleanup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev)
-{
-}
-
-static inline int adis_probe_trigger(struct adis *adis,
-	struct iio_dev *indio_dev)
-{
-	return 0;
-}
-
-static inline void adis_remove_trigger(struct adis *adis)
-{
-}
-
-#define adis_update_scan_mode NULL
-
-#endif /* CONFIG_IIO_BUFFER */
-
-#endif
diff --git a/drivers/staging/iio/imu/adis_buffer.c b/drivers/staging/iio/imu/adis_buffer.c
deleted file mode 100644
index 342758c14d2b..000000000000
--- a/drivers/staging/iio/imu/adis_buffer.c
+++ /dev/null
@@ -1,160 +0,0 @@
-/*
- * Common library for ADIS16XXX devices
- *
- * Copyright 2012 Analog Devices Inc.
- *   Author: Lars-Peter Clausen <lars@metafoo.de>
- *
- * Licensed under the GPL-2 or later.
- */
-
-#include <linux/export.h>
-#include <linux/interrupt.h>
-#include <linux/mutex.h>
-#include <linux/kernel.h>
-#include <linux/spi/spi.h>
-#include <linux/slab.h>
-
-#include <linux/iio/iio.h>
-#include <linux/iio/buffer.h>
-#include <linux/iio/trigger_consumer.h>
-#include <linux/iio/triggered_buffer.h>
-
-#include  "adis.h"
-
-int adis_update_scan_mode(struct iio_dev *indio_dev,
-	const unsigned long *scan_mask)
-{
-	struct adis *adis = iio_device_get_drvdata(indio_dev);
-	const struct iio_chan_spec *chan;
-	unsigned int scan_count;
-	unsigned int i, j;
-	__be16 *tx, *rx;
-
-	kfree(adis->xfer);
-	kfree(adis->buffer);
-
-	scan_count = indio_dev->scan_bytes / 2;
-
-	adis->xfer = kcalloc(scan_count + 1, sizeof(*adis->xfer), GFP_KERNEL);
-	if (!adis->xfer)
-		return -ENOMEM;
-
-	adis->buffer = kzalloc(indio_dev->scan_bytes * 2, GFP_KERNEL);
-	if (!adis->buffer)
-		return -ENOMEM;
-
-	rx = adis->buffer;
-	tx = rx + indio_dev->scan_bytes;
-
-	spi_message_init(&adis->msg);
-
-	for (j = 0; j <= scan_count; j++) {
-		adis->xfer[j].bits_per_word = 8;
-		if (j != scan_count)
-			adis->xfer[j].cs_change = 1;
-		adis->xfer[j].len = 2;
-		adis->xfer[j].delay_usecs = adis->data->read_delay;
-		if (j < scan_count)
-			adis->xfer[j].tx_buf = &tx[j];
-		if (j >= 1)
-			adis->xfer[j].rx_buf = &rx[j - 1];
-		spi_message_add_tail(&adis->xfer[j], &adis->msg);
-	}
-
-	chan = indio_dev->channels;
-	for (i = 0; i < indio_dev->num_channels; i++, chan++) {
-		if (!test_bit(chan->scan_index, scan_mask))
-			continue;
-		*tx++ = cpu_to_be16(chan->address << 8);
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(adis_update_scan_mode);
-
-static irqreturn_t adis_trigger_handler(int irq, void *p)
-{
-	struct iio_poll_func *pf = p;
-	struct iio_dev *indio_dev = pf->indio_dev;
-	struct adis *adis = iio_device_get_drvdata(indio_dev);
-	int ret;
-
-	if (!adis->buffer)
-		return -ENOMEM;
-
-	ret = spi_sync(adis->spi, &adis->msg);
-	if (ret)
-		dev_err(&adis->spi->dev, "Failed to read data: %d", ret);
-
-	/* Guaranteed to be aligned with 8 byte boundary */
-	if (indio_dev->scan_timestamp) {
-		void *b = adis->buffer + indio_dev->scan_bytes - sizeof(s64);
-		*(s64 *)b = pf->timestamp;
-	}
-
-	iio_push_to_buffers(indio_dev, adis->buffer);
-
-	iio_trigger_notify_done(indio_dev->trig);
-
-	return IRQ_HANDLED;
-}
-
-/**
- * adis_setup_buffer_and_trigger() - Sets up buffer and trigger for the adis device
- * @adis: The adis device.
- * @indio_dev: The IIO device.
- * @trigger_handler: Optional trigger handler, may be NULL.
- *
- * Returns 0 on success, a negative error code otherwise.
- *
- * This function sets up the buffer and trigger for a adis devices.  If
- * 'trigger_handler' is NULL the default trigger handler will be used. The
- * default trigger handler will simply read the registers assigned to the
- * currently active channels.
- *
- * adis_cleanup_buffer_and_trigger() should be called to free the resources
- * allocated by this function.
- */
-int adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
-	irqreturn_t (*trigger_handler)(int, void *))
-{
-	int ret;
-
-	if (!trigger_handler)
-		trigger_handler = adis_trigger_handler;
-
-	ret = iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
-		trigger_handler, NULL);
-	if (ret)
-		return ret;
-
-	if (adis->spi->irq) {
-		ret = adis_probe_trigger(adis, indio_dev);
-		if (ret)
-			goto error_buffer_cleanup;
-	}
-	return 0;
-
-error_buffer_cleanup:
-	iio_triggered_buffer_cleanup(indio_dev);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_setup_buffer_and_trigger);
-
-/**
- * adis_cleanup_buffer_and_trigger() - Free buffer and trigger resources
- * @adis: The adis device.
- * @indio_dev: The IIO device.
- *
- * Frees resources allocated by adis_setup_buffer_and_trigger()
- */
-void adis_cleanup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev)
-{
-	if (adis->spi->irq)
-		adis_remove_trigger(adis);
-	kfree(adis->buffer);
-	kfree(adis->xfer);
-	iio_triggered_buffer_cleanup(indio_dev);
-}
-EXPORT_SYMBOL_GPL(adis_cleanup_buffer_and_trigger);
diff --git a/drivers/staging/iio/imu/adis_trigger.c b/drivers/staging/iio/imu/adis_trigger.c
deleted file mode 100644
index 3e89b2e83708..000000000000
--- a/drivers/staging/iio/imu/adis_trigger.c
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * Common library for ADIS16XXX devices
- *
- * Copyright 2012 Analog Devices Inc.
- *   Author: Lars-Peter Clausen <lars@metafoo.de>
- *
- * Licensed under the GPL-2 or later.
- */
-
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/spi/spi.h>
-#include <linux/export.h>
-
-#include <linux/iio/iio.h>
-#include <linux/iio/trigger.h>
-
-#include "adis.h"
-
-static int adis_data_rdy_trigger_set_state(struct iio_trigger *trig,
-						bool state)
-{
-	struct adis *adis = trig->private_data;
-
-	return adis_enable_irq(adis, state);
-}
-
-static const struct iio_trigger_ops adis_trigger_ops = {
-	.owner = THIS_MODULE,
-	.set_trigger_state = &adis_data_rdy_trigger_set_state,
-};
-
-/**
- * adis_probe_trigger() - Sets up trigger for a adis device
- * @adis: The adis device
- * @indio_dev: The IIO device
- *
- * Returns 0 on success or a negative error code
- *
- * adis_remove_trigger() should be used to free the trigger.
- */
-int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev)
-{
-	int ret;
-
-	adis->trig = iio_trigger_alloc("%s-dev%d", indio_dev->name,
-					indio_dev->id);
-	if (adis->trig == NULL)
-		return -ENOMEM;
-
-	ret = request_irq(adis->spi->irq,
-			  &iio_trigger_generic_data_rdy_poll,
-			  IRQF_TRIGGER_RISING,
-			  indio_dev->name,
-			  adis->trig);
-	if (ret)
-		goto error_free_trig;
-
-	adis->trig->dev.parent = &adis->spi->dev;
-	adis->trig->ops = &adis_trigger_ops;
-	adis->trig->private_data = adis;
-	ret = iio_trigger_register(adis->trig);
-
-	indio_dev->trig = adis->trig;
-	if (ret)
-		goto error_free_irq;
-
-	return 0;
-
-error_free_irq:
-	free_irq(adis->spi->irq, adis->trig);
-error_free_trig:
-	iio_trigger_free(adis->trig);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_probe_trigger);
-
-/**
- * adis_remove_trigger() - Remove trigger for a adis devices
- * @adis: The adis device
- *
- * Removes the trigger previously registered with adis_probe_trigger().
- */
-void adis_remove_trigger(struct adis *adis)
-{
-	iio_trigger_unregister(adis->trig);
-	free_irq(adis->spi->irq, adis->trig);
-	iio_trigger_free(adis->trig);
-}
-EXPORT_SYMBOL_GPL(adis_remove_trigger);
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
new file mode 100644
index 000000000000..8c3304d44b97
--- /dev/null
+++ b/include/linux/iio/imu/adis.h
@@ -0,0 +1,186 @@
+/*
+ * Common library for ADIS16XXX devices
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *   Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#ifndef __IIO_ADIS_H__
+#define __IIO_ADIS_H__
+
+#include <linux/spi/spi.h>
+#include <linux/interrupt.h>
+#include <linux/iio/types.h>
+
+#define ADIS_WRITE_REG(reg) (0x80 | (reg))
+#define ADIS_READ_REG(reg) (reg)
+
+/**
+ * struct adis_data - ADIS chip variant specific data
+ * @read_delay: SPI delay for read operations in us
+ * @write_delay: SPI delay for write operations in us
+ * @glob_cmd_reg: Register address of the GLOB_CMD register
+ * @msc_ctrl_reg: Register address of the MSC_CTRL register
+ * @diag_stat_reg: Register address of the DIAG_STAT register
+ * @status_error_msgs: Array of error messgaes
+ * @status_error_mask:
+ */
+struct adis_data {
+	unsigned int read_delay;
+	unsigned int write_delay;
+
+	unsigned int glob_cmd_reg;
+	unsigned int msc_ctrl_reg;
+	unsigned int diag_stat_reg;
+
+	unsigned int self_test_mask;
+	unsigned int startup_delay;
+
+	const char * const *status_error_msgs;
+	unsigned int status_error_mask;
+};
+
+struct adis {
+	struct spi_device	*spi;
+	struct iio_trigger	*trig;
+
+	const struct adis_data	*data;
+
+	struct mutex		txrx_lock;
+	struct spi_message	msg;
+	struct spi_transfer	*xfer;
+	void			*buffer;
+
+	uint8_t			tx[8] ____cacheline_aligned;
+	uint8_t			rx[4];
+};
+
+int adis_init(struct adis *adis, struct iio_dev *indio_dev,
+	struct spi_device *spi, const struct adis_data *data);
+int adis_reset(struct adis *adis);
+
+int adis_write_reg_8(struct adis *adis, unsigned int reg, uint8_t val);
+int adis_write_reg_16(struct adis *adis, unsigned int reg, uint16_t val);
+int adis_read_reg_16(struct adis *adis, unsigned int reg, uint16_t *val);
+
+int adis_enable_irq(struct adis *adis, bool enable);
+int adis_check_status(struct adis *adis);
+
+int adis_initial_startup(struct adis *adis);
+
+int adis_single_conversion(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, unsigned int error_mask,
+	int *val);
+
+#define ADIS_VOLTAGE_CHAN(addr, si, chan, name, bits) { \
+	.type = IIO_VOLTAGE, \
+	.indexed = 1, \
+	.channel = (chan), \
+	.extend_name = name, \
+	.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \
+		IIO_CHAN_INFO_SCALE_SEPARATE_BIT, \
+	.address = (addr), \
+	.scan_index = (si), \
+	.scan_type = { \
+		.sign = 'u', \
+		.realbits = (bits), \
+		.storagebits = 16, \
+		.endianness = IIO_BE, \
+	}, \
+}
+
+#define ADIS_SUPPLY_CHAN(addr, si, bits) \
+	ADIS_VOLTAGE_CHAN(addr, si, 0, "supply", bits)
+
+#define ADIS_AUX_ADC_CHAN(addr, si, bits) \
+	ADIS_VOLTAGE_CHAN(addr, si, 1, NULL, bits)
+
+#define ADIS_TEMP_CHAN(addr, si, bits) { \
+	.type = IIO_TEMP, \
+	.indexed = 1, \
+	.channel = 0, \
+	.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \
+		IIO_CHAN_INFO_SCALE_SEPARATE_BIT | \
+		IIO_CHAN_INFO_OFFSET_SEPARATE_BIT, \
+	.address = (addr), \
+	.scan_index = (si), \
+	.scan_type = { \
+		.sign = 'u', \
+		.realbits = (bits), \
+		.storagebits = 16, \
+		.endianness = IIO_BE, \
+	}, \
+}
+
+#define ADIS_MOD_CHAN(_type, mod, addr, si, info, bits) { \
+	.type = (_type), \
+	.modified = 1, \
+	.channel2 = IIO_MOD_ ## mod, \
+	.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \
+		 IIO_CHAN_INFO_SCALE_SHARED_BIT | \
+		 info, \
+	.address = (addr), \
+	.scan_index = (si), \
+	.scan_type = { \
+		.sign = 's', \
+		.realbits = (bits), \
+		.storagebits = 16, \
+		.endianness = IIO_BE, \
+	}, \
+}
+
+#define ADIS_ACCEL_CHAN(mod, addr, si, info, bits) \
+	ADIS_MOD_CHAN(IIO_ACCEL, mod, addr, si, info, bits)
+
+#define ADIS_GYRO_CHAN(mod, addr, si, info, bits) \
+	ADIS_MOD_CHAN(IIO_ANGL_VEL, mod, addr, si, info, bits)
+
+#define ADIS_INCLI_CHAN(mod, addr, si, info, bits) \
+	ADIS_MOD_CHAN(IIO_INCLI, mod, addr, si, info, bits)
+
+#define ADIS_ROT_CHAN(mod, addr, si, info, bits) \
+	ADIS_MOD_CHAN(IIO_ROT, mod, addr, si, info, bits)
+
+#ifdef CONFIG_IIO_ADIS_LIB_BUFFER
+
+int adis_setup_buffer_and_trigger(struct adis *adis,
+	struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *));
+void adis_cleanup_buffer_and_trigger(struct adis *adis,
+	struct iio_dev *indio_dev);
+
+int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev);
+void adis_remove_trigger(struct adis *adis);
+
+int adis_update_scan_mode(struct iio_dev *indio_dev,
+	const unsigned long *scan_mask);
+
+#else /* CONFIG_IIO_BUFFER */
+
+static inline int adis_setup_buffer_and_trigger(struct adis *adis,
+	struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *))
+{
+	return 0;
+}
+
+static inline void adis_cleanup_buffer_and_trigger(struct adis *adis,
+	struct iio_dev *indio_dev)
+{
+}
+
+static inline int adis_probe_trigger(struct adis *adis,
+	struct iio_dev *indio_dev)
+{
+	return 0;
+}
+
+static inline void adis_remove_trigger(struct adis *adis)
+{
+}
+
+#define adis_update_scan_mode NULL
+
+#endif /* CONFIG_IIO_BUFFER */
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 709ab36e9559ff5c7df6e6f2d9e3c4a4410f8d49 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Sat, 17 Nov 2012 11:42:59 +0000
Subject: staging:iio: Move the ad7298 driver out of staging

The driver does not expose any custom API to userspace and none of the standard
static code checker tools report any issues, so move it out of staging.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/adc/Kconfig              |  12 ++
 drivers/iio/adc/Makefile             |   1 +
 drivers/iio/adc/ad7298.c             | 408 +++++++++++++++++++++++++++++++++++
 drivers/staging/iio/adc/Kconfig      |  12 --
 drivers/staging/iio/adc/Makefile     |   2 -
 drivers/staging/iio/adc/ad7298.c     | 408 -----------------------------------
 drivers/staging/iio/adc/ad7298.h     |  20 --
 include/linux/platform_data/ad7298.h |  20 ++
 8 files changed, 441 insertions(+), 442 deletions(-)
 create mode 100644 drivers/iio/adc/ad7298.c
 delete mode 100644 drivers/staging/iio/adc/ad7298.c
 delete mode 100644 drivers/staging/iio/adc/ad7298.h
 create mode 100644 include/linux/platform_data/ad7298.h

(limited to 'include')

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index ef5200a6850e..cd5eed60be28 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -18,6 +18,18 @@ config AD7266
 	  Say yes here to build support for Analog Devices AD7265 and AD7266
 	  ADCs.
 
+config AD7298
+	tristate "Analog Devices AD7298 ADC driver"
+	depends on SPI
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
+	help
+	  Say yes here to build support for Analog Devices AD7298
+	  8 Channel ADC with temperature sensor.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ad7298.
+
 config AD7791
 	tristate "Analog Devices AD7791 ADC driver"
 	depends on SPI
diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile
index 54ac7bbcd01b..3256dc64a466 100644
--- a/drivers/iio/adc/Makefile
+++ b/drivers/iio/adc/Makefile
@@ -4,6 +4,7 @@
 
 obj-$(CONFIG_AD_SIGMA_DELTA) += ad_sigma_delta.o
 obj-$(CONFIG_AD7266) += ad7266.o
+obj-$(CONFIG_AD7298) += ad7298.o
 obj-$(CONFIG_AD7476) += ad7476.o
 obj-$(CONFIG_AD7791) += ad7791.o
 obj-$(CONFIG_AD7887) += ad7887.o
diff --git a/drivers/iio/adc/ad7298.c b/drivers/iio/adc/ad7298.c
new file mode 100644
index 000000000000..441a9a265c12
--- /dev/null
+++ b/drivers/iio/adc/ad7298.c
@@ -0,0 +1,408 @@
+/*
+ * AD7298 SPI ADC driver
+ *
+ * Copyright 2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/spi/spi.h>
+#include <linux/regulator/consumer.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
+
+#include <linux/platform_data/ad7298.h>
+
+#define AD7298_WRITE	(1 << 15) /* write to the control register */
+#define AD7298_REPEAT	(1 << 14) /* repeated conversion enable */
+#define AD7298_CH(x)	(1 << (13 - (x))) /* channel select */
+#define AD7298_TSENSE	(1 << 5) /* temperature conversion enable */
+#define AD7298_EXTREF	(1 << 2) /* external reference enable */
+#define AD7298_TAVG	(1 << 1) /* temperature sensor averaging enable */
+#define AD7298_PDD	(1 << 0) /* partial power down enable */
+
+#define AD7298_MAX_CHAN		8
+#define AD7298_BITS		12
+#define AD7298_STORAGE_BITS	16
+#define AD7298_INTREF_mV	2500
+
+#define AD7298_CH_TEMP		9
+
+#define RES_MASK(bits)	((1 << (bits)) - 1)
+
+struct ad7298_state {
+	struct spi_device		*spi;
+	struct regulator		*reg;
+	unsigned			ext_ref;
+	struct spi_transfer		ring_xfer[10];
+	struct spi_transfer		scan_single_xfer[3];
+	struct spi_message		ring_msg;
+	struct spi_message		scan_single_msg;
+	/*
+	 * DMA (thus cache coherency maintenance) requires the
+	 * transfer buffers to live in their own cache lines.
+	 */
+	unsigned short			rx_buf[12] ____cacheline_aligned;
+	unsigned short			tx_buf[2];
+};
+
+#define AD7298_V_CHAN(index)						\
+	{								\
+		.type = IIO_VOLTAGE,					\
+		.indexed = 1,						\
+		.channel = index,					\
+		.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT |		\
+		IIO_CHAN_INFO_SCALE_SHARED_BIT,				\
+		.address = index,					\
+		.scan_index = index,					\
+		.scan_type = {						\
+			.sign = 'u',					\
+			.realbits = 12,					\
+			.storagebits = 16,				\
+			.endianness = IIO_BE,				\
+		},							\
+	}
+
+static const struct iio_chan_spec ad7298_channels[] = {
+	{
+		.type = IIO_TEMP,
+		.indexed = 1,
+		.channel = 0,
+		.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT |
+			IIO_CHAN_INFO_SCALE_SEPARATE_BIT |
+			IIO_CHAN_INFO_OFFSET_SEPARATE_BIT,
+		.address = AD7298_CH_TEMP,
+		.scan_index = -1,
+		.scan_type = {
+			.sign = 's',
+			.realbits = 32,
+			.storagebits = 32,
+		},
+	},
+	AD7298_V_CHAN(0),
+	AD7298_V_CHAN(1),
+	AD7298_V_CHAN(2),
+	AD7298_V_CHAN(3),
+	AD7298_V_CHAN(4),
+	AD7298_V_CHAN(5),
+	AD7298_V_CHAN(6),
+	AD7298_V_CHAN(7),
+	IIO_CHAN_SOFT_TIMESTAMP(8),
+};
+
+/**
+ * ad7298_update_scan_mode() setup the spi transfer buffer for the new scan mask
+ **/
+static int ad7298_update_scan_mode(struct iio_dev *indio_dev,
+	const unsigned long *active_scan_mask)
+{
+	struct ad7298_state *st = iio_priv(indio_dev);
+	int i, m;
+	unsigned short command;
+	int scan_count;
+
+	/* Now compute overall size */
+	scan_count = bitmap_weight(active_scan_mask, indio_dev->masklength);
+
+	command = AD7298_WRITE | st->ext_ref;
+
+	for (i = 0, m = AD7298_CH(0); i < AD7298_MAX_CHAN; i++, m >>= 1)
+		if (test_bit(i, active_scan_mask))
+			command |= m;
+
+	st->tx_buf[0] = cpu_to_be16(command);
+
+	/* build spi ring message */
+	st->ring_xfer[0].tx_buf = &st->tx_buf[0];
+	st->ring_xfer[0].len = 2;
+	st->ring_xfer[0].cs_change = 1;
+	st->ring_xfer[1].tx_buf = &st->tx_buf[1];
+	st->ring_xfer[1].len = 2;
+	st->ring_xfer[1].cs_change = 1;
+
+	spi_message_init(&st->ring_msg);
+	spi_message_add_tail(&st->ring_xfer[0], &st->ring_msg);
+	spi_message_add_tail(&st->ring_xfer[1], &st->ring_msg);
+
+	for (i = 0; i < scan_count; i++) {
+		st->ring_xfer[i + 2].rx_buf = &st->rx_buf[i];
+		st->ring_xfer[i + 2].len = 2;
+		st->ring_xfer[i + 2].cs_change = 1;
+		spi_message_add_tail(&st->ring_xfer[i + 2], &st->ring_msg);
+	}
+	/* make sure last transfer cs_change is not set */
+	st->ring_xfer[i + 1].cs_change = 0;
+
+	return 0;
+}
+
+/**
+ * ad7298_trigger_handler() bh of trigger launched polling to ring buffer
+ *
+ * Currently there is no option in this driver to disable the saving of
+ * timestamps within the ring.
+ **/
+static irqreturn_t ad7298_trigger_handler(int irq, void *p)
+{
+	struct iio_poll_func *pf = p;
+	struct iio_dev *indio_dev = pf->indio_dev;
+	struct ad7298_state *st = iio_priv(indio_dev);
+	s64 time_ns = 0;
+	int b_sent;
+
+	b_sent = spi_sync(st->spi, &st->ring_msg);
+	if (b_sent)
+		goto done;
+
+	if (indio_dev->scan_timestamp) {
+		time_ns = iio_get_time_ns();
+		memcpy((u8 *)st->rx_buf + indio_dev->scan_bytes - sizeof(s64),
+			&time_ns, sizeof(time_ns));
+	}
+
+	iio_push_to_buffers(indio_dev, (u8 *)st->rx_buf);
+
+done:
+	iio_trigger_notify_done(indio_dev->trig);
+
+	return IRQ_HANDLED;
+}
+
+static int ad7298_scan_direct(struct ad7298_state *st, unsigned ch)
+{
+	int ret;
+	st->tx_buf[0] = cpu_to_be16(AD7298_WRITE | st->ext_ref |
+				   (AD7298_CH(0) >> ch));
+
+	ret = spi_sync(st->spi, &st->scan_single_msg);
+	if (ret)
+		return ret;
+
+	return be16_to_cpu(st->rx_buf[0]);
+}
+
+static int ad7298_scan_temp(struct ad7298_state *st, int *val)
+{
+	int ret;
+	__be16 buf;
+
+	buf = cpu_to_be16(AD7298_WRITE | AD7298_TSENSE |
+			  AD7298_TAVG | st->ext_ref);
+
+	ret = spi_write(st->spi, (u8 *)&buf, 2);
+	if (ret)
+		return ret;
+
+	buf = cpu_to_be16(0);
+
+	ret = spi_write(st->spi, (u8 *)&buf, 2);
+	if (ret)
+		return ret;
+
+	usleep_range(101, 1000); /* sleep > 100us */
+
+	ret = spi_read(st->spi, (u8 *)&buf, 2);
+	if (ret)
+		return ret;
+
+	*val = sign_extend32(be16_to_cpu(buf), 11);
+
+	return 0;
+}
+
+static int ad7298_get_ref_voltage(struct ad7298_state *st)
+{
+	int vref;
+
+	if (st->ext_ref) {
+		vref = regulator_get_voltage(st->reg);
+		if (vref < 0)
+			return vref;
+
+		return vref / 1000;
+	} else {
+		return AD7298_INTREF_mV;
+	}
+}
+
+static int ad7298_read_raw(struct iio_dev *indio_dev,
+			   struct iio_chan_spec const *chan,
+			   int *val,
+			   int *val2,
+			   long m)
+{
+	int ret;
+	struct ad7298_state *st = iio_priv(indio_dev);
+
+	switch (m) {
+	case IIO_CHAN_INFO_RAW:
+		mutex_lock(&indio_dev->mlock);
+		if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED) {
+			ret = -EBUSY;
+		} else {
+			if (chan->address == AD7298_CH_TEMP)
+				ret = ad7298_scan_temp(st, val);
+			else
+				ret = ad7298_scan_direct(st, chan->address);
+		}
+		mutex_unlock(&indio_dev->mlock);
+
+		if (ret < 0)
+			return ret;
+
+		if (chan->address != AD7298_CH_TEMP)
+			*val = ret & RES_MASK(AD7298_BITS);
+
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_SCALE:
+		switch (chan->type) {
+		case IIO_VOLTAGE:
+			*val = ad7298_get_ref_voltage(st);
+			*val2 = chan->scan_type.realbits;
+			return IIO_VAL_FRACTIONAL_LOG2;
+		case IIO_TEMP:
+			*val = ad7298_get_ref_voltage(st);
+			*val2 = 10;
+			return IIO_VAL_FRACTIONAL;
+		default:
+			return -EINVAL;
+		}
+	case IIO_CHAN_INFO_OFFSET:
+		*val = 1093 - 2732500 / ad7298_get_ref_voltage(st);
+		return IIO_VAL_INT;
+	}
+	return -EINVAL;
+}
+
+static const struct iio_info ad7298_info = {
+	.read_raw = &ad7298_read_raw,
+	.update_scan_mode = ad7298_update_scan_mode,
+	.driver_module = THIS_MODULE,
+};
+
+static int __devinit ad7298_probe(struct spi_device *spi)
+{
+	struct ad7298_platform_data *pdata = spi->dev.platform_data;
+	struct ad7298_state *st;
+	struct iio_dev *indio_dev = iio_device_alloc(sizeof(*st));
+	int ret;
+
+	if (indio_dev == NULL)
+		return -ENOMEM;
+
+	st = iio_priv(indio_dev);
+
+	if (pdata && pdata->ext_ref)
+		st->ext_ref = AD7298_EXTREF;
+
+	if (st->ext_ref) {
+		st->reg = regulator_get(&spi->dev, "vref");
+		if (IS_ERR(st->reg)) {
+			ret = PTR_ERR(st->reg);
+			goto error_free;
+		}
+		ret = regulator_enable(st->reg);
+		if (ret)
+			goto error_put_reg;
+	}
+
+	spi_set_drvdata(spi, indio_dev);
+
+	st->spi = spi;
+
+	indio_dev->name = spi_get_device_id(spi)->name;
+	indio_dev->dev.parent = &spi->dev;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = ad7298_channels;
+	indio_dev->num_channels = ARRAY_SIZE(ad7298_channels);
+	indio_dev->info = &ad7298_info;
+
+	/* Setup default message */
+
+	st->scan_single_xfer[0].tx_buf = &st->tx_buf[0];
+	st->scan_single_xfer[0].len = 2;
+	st->scan_single_xfer[0].cs_change = 1;
+	st->scan_single_xfer[1].tx_buf = &st->tx_buf[1];
+	st->scan_single_xfer[1].len = 2;
+	st->scan_single_xfer[1].cs_change = 1;
+	st->scan_single_xfer[2].rx_buf = &st->rx_buf[0];
+	st->scan_single_xfer[2].len = 2;
+
+	spi_message_init(&st->scan_single_msg);
+	spi_message_add_tail(&st->scan_single_xfer[0], &st->scan_single_msg);
+	spi_message_add_tail(&st->scan_single_xfer[1], &st->scan_single_msg);
+	spi_message_add_tail(&st->scan_single_xfer[2], &st->scan_single_msg);
+
+	ret = iio_triggered_buffer_setup(indio_dev, NULL,
+			&ad7298_trigger_handler, NULL);
+	if (ret)
+		goto error_disable_reg;
+
+	ret = iio_device_register(indio_dev);
+	if (ret)
+		goto error_cleanup_ring;
+
+	return 0;
+
+error_cleanup_ring:
+	iio_triggered_buffer_cleanup(indio_dev);
+error_disable_reg:
+	if (st->ext_ref)
+		regulator_disable(st->reg);
+error_put_reg:
+	if (st->ext_ref)
+		regulator_put(st->reg);
+error_free:
+	iio_device_free(indio_dev);
+
+	return ret;
+}
+
+static int __devexit ad7298_remove(struct spi_device *spi)
+{
+	struct iio_dev *indio_dev = spi_get_drvdata(spi);
+	struct ad7298_state *st = iio_priv(indio_dev);
+
+	iio_device_unregister(indio_dev);
+	iio_triggered_buffer_cleanup(indio_dev);
+	if (st->ext_ref) {
+		regulator_disable(st->reg);
+		regulator_put(st->reg);
+	}
+	iio_device_free(indio_dev);
+
+	return 0;
+}
+
+static const struct spi_device_id ad7298_id[] = {
+	{"ad7298", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(spi, ad7298_id);
+
+static struct spi_driver ad7298_driver = {
+	.driver = {
+		.name	= "ad7298",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= ad7298_probe,
+	.remove		= __devexit_p(ad7298_remove),
+	.id_table	= ad7298_id,
+};
+module_spi_driver(ad7298_driver);
+
+MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>");
+MODULE_DESCRIPTION("Analog Devices AD7298 ADC");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/staging/iio/adc/Kconfig b/drivers/staging/iio/adc/Kconfig
index 5086a46b8e9a..dc8582b95b61 100644
--- a/drivers/staging/iio/adc/Kconfig
+++ b/drivers/staging/iio/adc/Kconfig
@@ -10,18 +10,6 @@ config AD7291
 	  Say yes here to build support for Analog Devices AD7291
 	  8 Channel ADC with temperature sensor.
 
-config AD7298
-	tristate "Analog Devices AD7298 ADC driver"
-	depends on SPI
-	select IIO_BUFFER
-	select IIO_TRIGGERED_BUFFER
-	help
-	  Say yes here to build support for Analog Devices AD7298
-	  8 Channel ADC with temperature sensor.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called ad7298.
-
 config AD7606
 	tristate "Analog Devices AD7606 ADC driver"
 	depends on GPIOLIB
diff --git a/drivers/staging/iio/adc/Makefile b/drivers/staging/iio/adc/Makefile
index 4beaa588256b..7281451a613a 100644
--- a/drivers/staging/iio/adc/Makefile
+++ b/drivers/staging/iio/adc/Makefile
@@ -12,8 +12,6 @@ ad799x-y := ad799x_core.o
 ad799x-$(CONFIG_AD799X_RING_BUFFER) += ad799x_ring.o
 obj-$(CONFIG_AD799X) += ad799x.o
 
-obj-$(CONFIG_AD7298) += ad7298.o
-
 obj-$(CONFIG_AD7291) += ad7291.o
 obj-$(CONFIG_AD7780) += ad7780.o
 obj-$(CONFIG_AD7793) += ad7793.o
diff --git a/drivers/staging/iio/adc/ad7298.c b/drivers/staging/iio/adc/ad7298.c
deleted file mode 100644
index 2742a9de05db..000000000000
--- a/drivers/staging/iio/adc/ad7298.c
+++ /dev/null
@@ -1,408 +0,0 @@
-/*
- * AD7298 SPI ADC driver
- *
- * Copyright 2011 Analog Devices Inc.
- *
- * Licensed under the GPL-2.
- */
-
-#include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/sysfs.h>
-#include <linux/spi/spi.h>
-#include <linux/regulator/consumer.h>
-#include <linux/err.h>
-#include <linux/delay.h>
-#include <linux/module.h>
-#include <linux/interrupt.h>
-
-#include <linux/iio/iio.h>
-#include <linux/iio/sysfs.h>
-#include <linux/iio/buffer.h>
-#include <linux/iio/trigger_consumer.h>
-#include <linux/iio/triggered_buffer.h>
-
-#include "ad7298.h"
-
-#define AD7298_WRITE	(1 << 15) /* write to the control register */
-#define AD7298_REPEAT	(1 << 14) /* repeated conversion enable */
-#define AD7298_CH(x)	(1 << (13 - (x))) /* channel select */
-#define AD7298_TSENSE	(1 << 5) /* temperature conversion enable */
-#define AD7298_EXTREF	(1 << 2) /* external reference enable */
-#define AD7298_TAVG	(1 << 1) /* temperature sensor averaging enable */
-#define AD7298_PDD	(1 << 0) /* partial power down enable */
-
-#define AD7298_MAX_CHAN		8
-#define AD7298_BITS		12
-#define AD7298_STORAGE_BITS	16
-#define AD7298_INTREF_mV	2500
-
-#define AD7298_CH_TEMP		9
-
-#define RES_MASK(bits)	((1 << (bits)) - 1)
-
-struct ad7298_state {
-	struct spi_device		*spi;
-	struct regulator		*reg;
-	unsigned			ext_ref;
-	struct spi_transfer		ring_xfer[10];
-	struct spi_transfer		scan_single_xfer[3];
-	struct spi_message		ring_msg;
-	struct spi_message		scan_single_msg;
-	/*
-	 * DMA (thus cache coherency maintenance) requires the
-	 * transfer buffers to live in their own cache lines.
-	 */
-	unsigned short			rx_buf[12] ____cacheline_aligned;
-	unsigned short			tx_buf[2];
-};
-
-#define AD7298_V_CHAN(index)						\
-	{								\
-		.type = IIO_VOLTAGE,					\
-		.indexed = 1,						\
-		.channel = index,					\
-		.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT |		\
-		IIO_CHAN_INFO_SCALE_SHARED_BIT,				\
-		.address = index,					\
-		.scan_index = index,					\
-		.scan_type = {						\
-			.sign = 'u',					\
-			.realbits = 12,					\
-			.storagebits = 16,				\
-			.endianness = IIO_BE,				\
-		},							\
-	}
-
-static const struct iio_chan_spec ad7298_channels[] = {
-	{
-		.type = IIO_TEMP,
-		.indexed = 1,
-		.channel = 0,
-		.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT |
-			IIO_CHAN_INFO_SCALE_SEPARATE_BIT |
-			IIO_CHAN_INFO_OFFSET_SEPARATE_BIT,
-		.address = AD7298_CH_TEMP,
-		.scan_index = -1,
-		.scan_type = {
-			.sign = 's',
-			.realbits = 32,
-			.storagebits = 32,
-		},
-	},
-	AD7298_V_CHAN(0),
-	AD7298_V_CHAN(1),
-	AD7298_V_CHAN(2),
-	AD7298_V_CHAN(3),
-	AD7298_V_CHAN(4),
-	AD7298_V_CHAN(5),
-	AD7298_V_CHAN(6),
-	AD7298_V_CHAN(7),
-	IIO_CHAN_SOFT_TIMESTAMP(8),
-};
-
-/**
- * ad7298_update_scan_mode() setup the spi transfer buffer for the new scan mask
- **/
-static int ad7298_update_scan_mode(struct iio_dev *indio_dev,
-	const unsigned long *active_scan_mask)
-{
-	struct ad7298_state *st = iio_priv(indio_dev);
-	int i, m;
-	unsigned short command;
-	int scan_count;
-
-	/* Now compute overall size */
-	scan_count = bitmap_weight(active_scan_mask, indio_dev->masklength);
-
-	command = AD7298_WRITE | st->ext_ref;
-
-	for (i = 0, m = AD7298_CH(0); i < AD7298_MAX_CHAN; i++, m >>= 1)
-		if (test_bit(i, active_scan_mask))
-			command |= m;
-
-	st->tx_buf[0] = cpu_to_be16(command);
-
-	/* build spi ring message */
-	st->ring_xfer[0].tx_buf = &st->tx_buf[0];
-	st->ring_xfer[0].len = 2;
-	st->ring_xfer[0].cs_change = 1;
-	st->ring_xfer[1].tx_buf = &st->tx_buf[1];
-	st->ring_xfer[1].len = 2;
-	st->ring_xfer[1].cs_change = 1;
-
-	spi_message_init(&st->ring_msg);
-	spi_message_add_tail(&st->ring_xfer[0], &st->ring_msg);
-	spi_message_add_tail(&st->ring_xfer[1], &st->ring_msg);
-
-	for (i = 0; i < scan_count; i++) {
-		st->ring_xfer[i + 2].rx_buf = &st->rx_buf[i];
-		st->ring_xfer[i + 2].len = 2;
-		st->ring_xfer[i + 2].cs_change = 1;
-		spi_message_add_tail(&st->ring_xfer[i + 2], &st->ring_msg);
-	}
-	/* make sure last transfer cs_change is not set */
-	st->ring_xfer[i + 1].cs_change = 0;
-
-	return 0;
-}
-
-/**
- * ad7298_trigger_handler() bh of trigger launched polling to ring buffer
- *
- * Currently there is no option in this driver to disable the saving of
- * timestamps within the ring.
- **/
-static irqreturn_t ad7298_trigger_handler(int irq, void *p)
-{
-	struct iio_poll_func *pf = p;
-	struct iio_dev *indio_dev = pf->indio_dev;
-	struct ad7298_state *st = iio_priv(indio_dev);
-	s64 time_ns = 0;
-	int b_sent;
-
-	b_sent = spi_sync(st->spi, &st->ring_msg);
-	if (b_sent)
-		goto done;
-
-	if (indio_dev->scan_timestamp) {
-		time_ns = iio_get_time_ns();
-		memcpy((u8 *)st->rx_buf + indio_dev->scan_bytes - sizeof(s64),
-			&time_ns, sizeof(time_ns));
-	}
-
-	iio_push_to_buffers(indio_dev, (u8 *)st->rx_buf);
-
-done:
-	iio_trigger_notify_done(indio_dev->trig);
-
-	return IRQ_HANDLED;
-}
-
-static int ad7298_scan_direct(struct ad7298_state *st, unsigned ch)
-{
-	int ret;
-	st->tx_buf[0] = cpu_to_be16(AD7298_WRITE | st->ext_ref |
-				   (AD7298_CH(0) >> ch));
-
-	ret = spi_sync(st->spi, &st->scan_single_msg);
-	if (ret)
-		return ret;
-
-	return be16_to_cpu(st->rx_buf[0]);
-}
-
-static int ad7298_scan_temp(struct ad7298_state *st, int *val)
-{
-	int ret;
-	__be16 buf;
-
-	buf = cpu_to_be16(AD7298_WRITE | AD7298_TSENSE |
-			  AD7298_TAVG | st->ext_ref);
-
-	ret = spi_write(st->spi, (u8 *)&buf, 2);
-	if (ret)
-		return ret;
-
-	buf = cpu_to_be16(0);
-
-	ret = spi_write(st->spi, (u8 *)&buf, 2);
-	if (ret)
-		return ret;
-
-	usleep_range(101, 1000); /* sleep > 100us */
-
-	ret = spi_read(st->spi, (u8 *)&buf, 2);
-	if (ret)
-		return ret;
-
-	*val = sign_extend32(be16_to_cpu(buf), 11);
-
-	return 0;
-}
-
-static int ad7298_get_ref_voltage(struct ad7298_state *st)
-{
-	int vref;
-
-	if (st->ext_ref) {
-		vref = regulator_get_voltage(st->reg);
-		if (vref < 0)
-			return vref;
-
-		return vref / 1000;
-	} else {
-		return AD7298_INTREF_mV;
-	}
-}
-
-static int ad7298_read_raw(struct iio_dev *indio_dev,
-			   struct iio_chan_spec const *chan,
-			   int *val,
-			   int *val2,
-			   long m)
-{
-	int ret;
-	struct ad7298_state *st = iio_priv(indio_dev);
-
-	switch (m) {
-	case IIO_CHAN_INFO_RAW:
-		mutex_lock(&indio_dev->mlock);
-		if (indio_dev->currentmode == INDIO_BUFFER_TRIGGERED) {
-			ret = -EBUSY;
-		} else {
-			if (chan->address == AD7298_CH_TEMP)
-				ret = ad7298_scan_temp(st, val);
-			else
-				ret = ad7298_scan_direct(st, chan->address);
-		}
-		mutex_unlock(&indio_dev->mlock);
-
-		if (ret < 0)
-			return ret;
-
-		if (chan->address != AD7298_CH_TEMP)
-			*val = ret & RES_MASK(AD7298_BITS);
-
-		return IIO_VAL_INT;
-	case IIO_CHAN_INFO_SCALE:
-		switch (chan->type) {
-		case IIO_VOLTAGE:
-			*val = ad7298_get_ref_voltage(st);
-			*val2 = chan->scan_type.realbits;
-			return IIO_VAL_FRACTIONAL_LOG2;
-		case IIO_TEMP:
-			*val = ad7298_get_ref_voltage(st);
-			*val2 = 10;
-			return IIO_VAL_FRACTIONAL;
-		default:
-			return -EINVAL;
-		}
-	case IIO_CHAN_INFO_OFFSET:
-		*val = 1093 - 2732500 / ad7298_get_ref_voltage(st);
-		return IIO_VAL_INT;
-	}
-	return -EINVAL;
-}
-
-static const struct iio_info ad7298_info = {
-	.read_raw = &ad7298_read_raw,
-	.update_scan_mode = ad7298_update_scan_mode,
-	.driver_module = THIS_MODULE,
-};
-
-static int __devinit ad7298_probe(struct spi_device *spi)
-{
-	struct ad7298_platform_data *pdata = spi->dev.platform_data;
-	struct ad7298_state *st;
-	struct iio_dev *indio_dev = iio_device_alloc(sizeof(*st));
-	int ret;
-
-	if (indio_dev == NULL)
-		return -ENOMEM;
-
-	st = iio_priv(indio_dev);
-
-	if (pdata && pdata->ext_ref)
-		st->ext_ref = AD7298_EXTREF;
-
-	if (st->ext_ref) {
-		st->reg = regulator_get(&spi->dev, "vref");
-		if (IS_ERR(st->reg)) {
-			ret = PTR_ERR(st->reg);
-			goto error_free;
-		}
-		ret = regulator_enable(st->reg);
-		if (ret)
-			goto error_put_reg;
-	}
-
-	spi_set_drvdata(spi, indio_dev);
-
-	st->spi = spi;
-
-	indio_dev->name = spi_get_device_id(spi)->name;
-	indio_dev->dev.parent = &spi->dev;
-	indio_dev->modes = INDIO_DIRECT_MODE;
-	indio_dev->channels = ad7298_channels;
-	indio_dev->num_channels = ARRAY_SIZE(ad7298_channels);
-	indio_dev->info = &ad7298_info;
-
-	/* Setup default message */
-
-	st->scan_single_xfer[0].tx_buf = &st->tx_buf[0];
-	st->scan_single_xfer[0].len = 2;
-	st->scan_single_xfer[0].cs_change = 1;
-	st->scan_single_xfer[1].tx_buf = &st->tx_buf[1];
-	st->scan_single_xfer[1].len = 2;
-	st->scan_single_xfer[1].cs_change = 1;
-	st->scan_single_xfer[2].rx_buf = &st->rx_buf[0];
-	st->scan_single_xfer[2].len = 2;
-
-	spi_message_init(&st->scan_single_msg);
-	spi_message_add_tail(&st->scan_single_xfer[0], &st->scan_single_msg);
-	spi_message_add_tail(&st->scan_single_xfer[1], &st->scan_single_msg);
-	spi_message_add_tail(&st->scan_single_xfer[2], &st->scan_single_msg);
-
-	ret = iio_triggered_buffer_setup(indio_dev, NULL,
-			&ad7298_trigger_handler, NULL);
-	if (ret)
-		goto error_disable_reg;
-
-	ret = iio_device_register(indio_dev);
-	if (ret)
-		goto error_cleanup_ring;
-
-	return 0;
-
-error_cleanup_ring:
-	iio_triggered_buffer_cleanup(indio_dev);
-error_disable_reg:
-	if (st->ext_ref)
-		regulator_disable(st->reg);
-error_put_reg:
-	if (st->ext_ref)
-		regulator_put(st->reg);
-error_free:
-	iio_device_free(indio_dev);
-
-	return ret;
-}
-
-static int __devexit ad7298_remove(struct spi_device *spi)
-{
-	struct iio_dev *indio_dev = spi_get_drvdata(spi);
-	struct ad7298_state *st = iio_priv(indio_dev);
-
-	iio_device_unregister(indio_dev);
-	iio_triggered_buffer_cleanup(indio_dev);
-	if (st->ext_ref) {
-		regulator_disable(st->reg);
-		regulator_put(st->reg);
-	}
-	iio_device_free(indio_dev);
-
-	return 0;
-}
-
-static const struct spi_device_id ad7298_id[] = {
-	{"ad7298", 0},
-	{}
-};
-MODULE_DEVICE_TABLE(spi, ad7298_id);
-
-static struct spi_driver ad7298_driver = {
-	.driver = {
-		.name	= "ad7298",
-		.owner	= THIS_MODULE,
-	},
-	.probe		= ad7298_probe,
-	.remove		= __devexit_p(ad7298_remove),
-	.id_table	= ad7298_id,
-};
-module_spi_driver(ad7298_driver);
-
-MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>");
-MODULE_DESCRIPTION("Analog Devices AD7298 ADC");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/staging/iio/adc/ad7298.h b/drivers/staging/iio/adc/ad7298.h
deleted file mode 100644
index c8ac969ec016..000000000000
--- a/drivers/staging/iio/adc/ad7298.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * AD7298 SPI ADC driver
- *
- * Copyright 2011 Analog Devices Inc.
- *
- * Licensed under the GPL-2.
- */
-
-#ifndef IIO_ADC_AD7298_H_
-#define IIO_ADC_AD7298_H_
-
-/**
- * struct ad7298_platform_data - Platform data for the ad7298 ADC driver
- * @ext_ref: Whether to use an external reference voltage.
- **/
-struct ad7298_platform_data {
-	bool ext_ref;
-};
-
-#endif /* IIO_ADC_AD7298_H_ */
diff --git a/include/linux/platform_data/ad7298.h b/include/linux/platform_data/ad7298.h
new file mode 100644
index 000000000000..fbf8adf1363a
--- /dev/null
+++ b/include/linux/platform_data/ad7298.h
@@ -0,0 +1,20 @@
+/*
+ * AD7298 SPI ADC driver
+ *
+ * Copyright 2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2.
+ */
+
+#ifndef __LINUX_PLATFORM_DATA_AD7298_H__
+#define __LINUX_PLATFORM_DATA_AD7298_H__
+
+/**
+ * struct ad7298_platform_data - Platform data for the ad7298 ADC driver
+ * @ext_ref: Whether to use an external reference voltage.
+ **/
+struct ad7298_platform_data {
+	bool ext_ref;
+};
+
+#endif /* IIO_ADC_AD7298_H_ */
-- 
cgit v1.2.3-55-g7522


From 84d4819033972f6bae2b34a8ba07c5c2e836e989 Mon Sep 17 00:00:00 2001
From: Eric Lapuyade
Date: Wed, 17 Oct 2012 16:50:10 +0200
Subject: NFC: Export nfc_hci_result_to_errno as it can be needed by HCI
 drivers

Signed-off-by: Eric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/hci.h | 2 ++
 net/nfc/hci/core.c    | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 639f50af42df..150e3caddbcf 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -149,6 +149,8 @@ void *nfc_hci_get_clientdata(struct nfc_hci_dev *hdev);
 
 void nfc_hci_driver_failure(struct nfc_hci_dev *hdev, int err);
 
+int nfc_hci_result_to_errno(u8 result);
+
 /* Host IDs */
 #define NFC_HCI_HOST_CONTROLLER_ID	0x00
 #define NFC_HCI_TERMINAL_HOST_ID	0x01
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 38d5f96dfd10..6825a200c4bb 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -33,7 +33,7 @@
 /* Largest headroom needed for outgoing HCI commands */
 #define HCI_CMDS_HEADROOM 1
 
-static int nfc_hci_result_to_errno(u8 result)
+int nfc_hci_result_to_errno(u8 result)
 {
 	switch (result) {
 	case NFC_HCI_ANY_OK:
@@ -46,6 +46,7 @@ static int nfc_hci_result_to_errno(u8 result)
 		return -1;
 	}
 }
+EXPORT_SYMBOL(nfc_hci_result_to_errno);
 
 static void nfc_hci_msg_tx_work(struct work_struct *work)
 {
-- 
cgit v1.2.3-55-g7522


From 9c5121a034b1414d83c553e9961bda823e2e65b4 Mon Sep 17 00:00:00 2001
From: Eric Lapuyade
Date: Tue, 23 Oct 2012 11:37:43 +0200
Subject: NFC: Export nfc_hci_sak_to_protocol()

Some HCI drivers will need it.

Signed-off-by: Eric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/hci.h | 1 +
 net/nfc/hci/core.c    | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 150e3caddbcf..671953e11575 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -237,5 +237,6 @@ int nfc_hci_send_response(struct nfc_hci_dev *hdev, u8 gate, u8 response,
 int nfc_hci_send_event(struct nfc_hci_dev *hdev, u8 gate, u8 event,
 		       const u8 *param, size_t param_len);
 int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate);
+u32 nfc_hci_sak_to_protocol(u8 sak);
 
 #endif /* __NET_HCI_H */
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 6825a200c4bb..7bea574d5934 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -170,7 +170,7 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 	kfree_skb(skb);
 }
 
-static u32 nfc_hci_sak_to_protocol(u8 sak)
+u32 nfc_hci_sak_to_protocol(u8 sak)
 {
 	switch (NFC_HCI_TYPE_A_SEL_PROT(sak)) {
 	case NFC_HCI_TYPE_A_SEL_PROT_MIFARE:
@@ -185,6 +185,7 @@ static u32 nfc_hci_sak_to_protocol(u8 sak)
 		return 0xffffffff;
 	}
 }
+EXPORT_SYMBOL(nfc_hci_sak_to_protocol);
 
 int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate)
 {
-- 
cgit v1.2.3-55-g7522


From d962ec4922493da48bb0fd33b26200de039b0d75 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann
Date: Wed, 24 Oct 2012 11:45:12 -0700
Subject: NFC: Remove unused details from pn544.h header file

The majority of the defines and structures from pn544.h are no
longer in use. So just remove them.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/linux/nfc/pn544.h | 60 -----------------------------------------------
 1 file changed, 60 deletions(-)

(limited to 'include')

diff --git a/include/linux/nfc/pn544.h b/include/linux/nfc/pn544.h
index 9890bbaf4328..713bfd703342 100644
--- a/include/linux/nfc/pn544.h
+++ b/include/linux/nfc/pn544.h
@@ -25,65 +25,6 @@
 
 #include <linux/i2c.h>
 
-#define PN544_DRIVER_NAME	"pn544"
-#define PN544_MAXWINDOW_SIZE	7
-#define PN544_WINDOW_SIZE	4
-#define PN544_RETRIES		10
-#define PN544_MAX_I2C_TRANSFER	0x0400
-#define PN544_MSG_MAX_SIZE	0x21 /* at normal HCI mode */
-
-/* ioctl */
-#define PN544_CHAR_BASE		'P'
-#define PN544_IOR(num, dtype)	_IOR(PN544_CHAR_BASE, num, dtype)
-#define PN544_IOW(num, dtype)	_IOW(PN544_CHAR_BASE, num, dtype)
-#define PN544_GET_FW_MODE	PN544_IOW(1, unsigned int)
-#define PN544_SET_FW_MODE	PN544_IOW(2, unsigned int)
-#define PN544_GET_DEBUG		PN544_IOW(3, unsigned int)
-#define PN544_SET_DEBUG		PN544_IOW(4, unsigned int)
-
-/* Timing restrictions (ms) */
-#define PN544_RESETVEN_TIME	30 /* 7 */
-#define PN544_PVDDVEN_TIME	0
-#define PN544_VBATVEN_TIME	0
-#define PN544_GPIO4VEN_TIME	0
-#define PN544_WAKEUP_ACK	5
-#define PN544_WAKEUP_GUARD	(PN544_WAKEUP_ACK + 1)
-#define PN544_INACTIVITY_TIME	1000
-#define PN544_INTERFRAME_DELAY	200 /* us */
-#define PN544_BAUDRATE_CHANGE	150 /* us */
-
-/* Debug bits */
-#define PN544_DEBUG_BUF		0x01
-#define PN544_DEBUG_READ	0x02
-#define PN544_DEBUG_WRITE	0x04
-#define PN544_DEBUG_IRQ		0x08
-#define PN544_DEBUG_CALLS	0x10
-#define PN544_DEBUG_MODE	0x20
-
-/* Normal (HCI) mode */
-#define PN544_LLC_HCI_OVERHEAD	3 /* header + crc (to length) */
-#define PN544_LLC_MIN_SIZE	(1 + PN544_LLC_HCI_OVERHEAD) /* length + */
-#define PN544_LLC_MAX_DATA	(PN544_MSG_MAX_SIZE - 2)
-#define PN544_LLC_MAX_HCI_SIZE	(PN544_LLC_MAX_DATA - 2)
-
-struct pn544_llc_packet {
-	unsigned char length; /* of rest of packet */
-	unsigned char header;
-	unsigned char data[PN544_LLC_MAX_DATA]; /* includes crc-ccitt */
-};
-
-/* Firmware upgrade mode */
-#define PN544_FW_HEADER_SIZE	3
-/* max fw transfer is 1024bytes, but I2C limits it to 0xC0 */
-#define PN544_MAX_FW_DATA	(PN544_MAX_I2C_TRANSFER - PN544_FW_HEADER_SIZE)
-
-struct pn544_fw_packet {
-	unsigned char command; /* status in answer */
-	unsigned char length[2]; /* big-endian order (msf) */
-	unsigned char data[PN544_MAX_FW_DATA];
-};
-
-#ifdef __KERNEL__
 enum {
 	NFC_GPIO_ENABLE,
 	NFC_GPIO_FW_RESET,
@@ -99,6 +40,5 @@ struct pn544_nfc_platform_data {
 	void (*disable) (void);
 	int (*get_gpio)(int type);
 };
-#endif /* __KERNEL__ */
 
 #endif /* _PN544_H_ */
-- 
cgit v1.2.3-55-g7522


From 61cdb01853c99e78d8b54db1b77e524c0dce585d Mon Sep 17 00:00:00 2001
From: Marcel Holtmann
Date: Wed, 24 Oct 2012 11:45:26 -0700
Subject: NFC: Move pn544.h to linux/platform_data/

The pn544.h just provides the platform data struct and defines and
nothing else. So move it to to linux/platform_data/ now.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/pn544/i2c.c             |  2 +-
 include/linux/nfc/pn544.h           | 44 -------------------------------------
 include/linux/platform_data/pn544.h | 44 +++++++++++++++++++++++++++++++++++++
 3 files changed, 45 insertions(+), 45 deletions(-)
 delete mode 100644 include/linux/nfc/pn544.h
 create mode 100644 include/linux/platform_data/pn544.h

(limited to 'include')

diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
index fb430d882352..7da9071b68b6 100644
--- a/drivers/nfc/pn544/i2c.c
+++ b/drivers/nfc/pn544/i2c.c
@@ -26,7 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 
-#include <linux/nfc/pn544.h>
+#include <linux/platform_data/pn544.h>
 
 #include <net/nfc/hci.h>
 #include <net/nfc/llc.h>
diff --git a/include/linux/nfc/pn544.h b/include/linux/nfc/pn544.h
deleted file mode 100644
index 713bfd703342..000000000000
--- a/include/linux/nfc/pn544.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- * Driver include for the PN544 NFC chip.
- *
- * Copyright (C) Nokia Corporation
- *
- * Author: Jari Vanhala <ext-jari.vanhala@nokia.com>
- * Contact: Matti Aaltoenn <matti.j.aaltonen@nokia.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef _PN544_H_
-#define _PN544_H_
-
-#include <linux/i2c.h>
-
-enum {
-	NFC_GPIO_ENABLE,
-	NFC_GPIO_FW_RESET,
-	NFC_GPIO_IRQ
-};
-
-/* board config */
-struct pn544_nfc_platform_data {
-	int (*request_resources) (struct i2c_client *client);
-	void (*free_resources) (void);
-	void (*enable) (int fw);
-	int (*test) (void);
-	void (*disable) (void);
-	int (*get_gpio)(int type);
-};
-
-#endif /* _PN544_H_ */
diff --git a/include/linux/platform_data/pn544.h b/include/linux/platform_data/pn544.h
new file mode 100644
index 000000000000..713bfd703342
--- /dev/null
+++ b/include/linux/platform_data/pn544.h
@@ -0,0 +1,44 @@
+/*
+ * Driver include for the PN544 NFC chip.
+ *
+ * Copyright (C) Nokia Corporation
+ *
+ * Author: Jari Vanhala <ext-jari.vanhala@nokia.com>
+ * Contact: Matti Aaltoenn <matti.j.aaltonen@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _PN544_H_
+#define _PN544_H_
+
+#include <linux/i2c.h>
+
+enum {
+	NFC_GPIO_ENABLE,
+	NFC_GPIO_FW_RESET,
+	NFC_GPIO_IRQ
+};
+
+/* board config */
+struct pn544_nfc_platform_data {
+	int (*request_resources) (struct i2c_client *client);
+	void (*free_resources) (void);
+	void (*enable) (int fw);
+	int (*test) (void);
+	void (*disable) (void);
+	int (*get_gpio)(int type);
+};
+
+#endif /* _PN544_H_ */
-- 
cgit v1.2.3-55-g7522


From a4799037c3234830e9feb1823d87f905fb4d080a Mon Sep 17 00:00:00 2001
From: Stephane Marchesin
Date: Fri, 9 Nov 2012 16:21:05 +0000
Subject: drm: get cea video id code for a given display mode

This patch adds support for getting CEA Video ID Code for a given
display mode after matching with edid_cea_modes list. Its index in
the list added with one, gives the desired code.

This exported function will be used by hdmi drivers for composing
AVI info frame data.

Signed-off-by: Stephane Marchesin <marcheu@chromium.org>
Signed-off-by: Rahul Sharma <rahul.sharma@samsung.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_edid.c | 20 ++++++++++++++++++++
 include/drm/drm_crtc.h     |  1 +
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index fadcd44ff196..856dcd91b3d4 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -1516,6 +1516,26 @@ u8 *drm_find_cea_extension(struct edid *edid)
 }
 EXPORT_SYMBOL(drm_find_cea_extension);
 
+/*
+ * Looks for a CEA mode matching given drm_display_mode.
+ * Returns its CEA Video ID code, or 0 if not found.
+ */
+u8 drm_match_cea_mode(struct drm_display_mode *to_match)
+{
+	struct drm_display_mode *cea_mode;
+	u8 mode;
+
+	for (mode = 0; mode < drm_num_cea_modes; mode++) {
+		cea_mode = (struct drm_display_mode *)&edid_cea_modes[mode];
+
+		if (drm_mode_equal(to_match, cea_mode))
+			return mode + 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(drm_match_cea_mode);
+
+
 static int
 do_cea_modes (struct drm_connector *connector, u8 *db, u8 len)
 {
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 49dd8c2eea7d..1f5f1d642a98 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -1037,6 +1037,7 @@ extern int drm_mode_gamma_get_ioctl(struct drm_device *dev,
 extern int drm_mode_gamma_set_ioctl(struct drm_device *dev,
 				    void *data, struct drm_file *file_priv);
 extern u8 *drm_find_cea_extension(struct edid *edid);
+extern u8 drm_match_cea_mode(struct drm_display_mode *to_match);
 extern bool drm_detect_hdmi_monitor(struct edid *edid);
 extern bool drm_detect_monitor_audio(struct edid *edid);
 extern int drm_mode_page_flip_ioctl(struct drm_device *dev,
-- 
cgit v1.2.3-55-g7522


From c6eefa1750ec0308956895027c3a79eee2ef9726 Mon Sep 17 00:00:00 2001
From: Rob Clark
Date: Tue, 16 Oct 2012 22:48:40 +0000
Subject: drm: add drm_send_vblank_event() helper (v5)

A helper that drivers can use to send vblank event after a pageflip.
If the driver doesn't support proper vblank irq based time/seqn then
just pass -1 for the pipe # to get do_gettimestamp() behavior (since
there are a lot of drivers that don't use drm_vblank_count_and_time())

Also an internal send_vblank_event() helper for the various other code
paths within drm_irq that also need to send vblank events.

v1: original
v2: add back 'vblwait->reply.sequence = seq' which should not have
    been deleted
v3: add WARN_ON() in case lock is not held and comments
v4: use WARN_ON_SMP() instead to fix issue with !SMP && !DEBUG_SPINLOCK
    as pointed out by Marcin Slusarz
v5: update docbook

Signed-off-by: Rob Clark <rob@ti.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 Documentation/DocBook/drm.tmpl | 20 +++---------
 drivers/gpu/drm/drm_irq.c      | 74 +++++++++++++++++++++++++++++-------------
 include/drm/drmP.h             |  2 ++
 3 files changed, 59 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index b0300529ab13..c9cbb3fe0e6a 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -1141,23 +1141,13 @@ int max_width, max_height;</synopsis>
             the <methodname>page_flip</methodname> operation will be called with a
             non-NULL <parameter>event</parameter> argument pointing to a
             <structname>drm_pending_vblank_event</structname> instance. Upon page
-            flip completion the driver must fill the
-            <parameter>event</parameter>::<structfield>event</structfield>
-            <structfield>sequence</structfield>, <structfield>tv_sec</structfield>
-            and <structfield>tv_usec</structfield> fields with the associated
-            vertical blanking count and timestamp, add the event to the
-            <parameter>drm_file</parameter> list of events to be signaled, and wake
-            up any waiting process. This can be performed with
+            flip completion the driver must call <methodname>drm_send_vblank_event</methodname>
+            to fill in the event and send to wake up any waiting processes.
+            This can be performed with
             <programlisting><![CDATA[
-            struct timeval now;
-
-            event->event.sequence = drm_vblank_count_and_time(..., &now);
-            event->event.tv_sec = now.tv_sec;
-            event->event.tv_usec = now.tv_usec;
-
             spin_lock_irqsave(&dev->event_lock, flags);
-            list_add_tail(&event->base.link, &event->base.file_priv->event_list);
-            wake_up_interruptible(&event->base.file_priv->event_wait);
+            ...
+            drm_send_vblank_event(dev, pipe, event);
             spin_unlock_irqrestore(&dev->event_lock, flags);
             ]]></programlisting>
           </para>
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 3a3d0ce891b9..44602ef55afc 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -802,6 +802,46 @@ u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc,
 }
 EXPORT_SYMBOL(drm_vblank_count_and_time);
 
+static void send_vblank_event(struct drm_device *dev,
+		struct drm_pending_vblank_event *e,
+		unsigned long seq, struct timeval *now)
+{
+	WARN_ON_SMP(!spin_is_locked(&dev->event_lock));
+	e->event.sequence = seq;
+	e->event.tv_sec = now->tv_sec;
+	e->event.tv_usec = now->tv_usec;
+
+	list_add_tail(&e->base.link,
+		      &e->base.file_priv->event_list);
+	wake_up_interruptible(&e->base.file_priv->event_wait);
+	trace_drm_vblank_event_delivered(e->base.pid, e->pipe,
+					 e->event.sequence);
+}
+
+/**
+ * drm_send_vblank_event - helper to send vblank event after pageflip
+ * @dev: DRM device
+ * @crtc: CRTC in question
+ * @e: the event to send
+ *
+ * Updates sequence # and timestamp on event, and sends it to userspace.
+ * Caller must hold event lock.
+ */
+void drm_send_vblank_event(struct drm_device *dev, int crtc,
+		struct drm_pending_vblank_event *e)
+{
+	struct timeval now;
+	unsigned int seq;
+	if (crtc >= 0) {
+		seq = drm_vblank_count_and_time(dev, crtc, &now);
+	} else {
+		seq = 0;
+		do_gettimeofday(&now);
+	}
+	send_vblank_event(dev, e, seq, &now);
+}
+EXPORT_SYMBOL(drm_send_vblank_event);
+
 /**
  * drm_update_vblank_count - update the master vblank counter
  * @dev: DRM device
@@ -936,6 +976,13 @@ void drm_vblank_put(struct drm_device *dev, int crtc)
 }
 EXPORT_SYMBOL(drm_vblank_put);
 
+/**
+ * drm_vblank_off - disable vblank events on a CRTC
+ * @dev: DRM device
+ * @crtc: CRTC in question
+ *
+ * Caller must hold event lock.
+ */
 void drm_vblank_off(struct drm_device *dev, int crtc)
 {
 	struct drm_pending_vblank_event *e, *t;
@@ -955,15 +1002,9 @@ void drm_vblank_off(struct drm_device *dev, int crtc)
 		DRM_DEBUG("Sending premature vblank event on disable: \
 			  wanted %d, current %d\n",
 			  e->event.sequence, seq);
-
-		e->event.sequence = seq;
-		e->event.tv_sec = now.tv_sec;
-		e->event.tv_usec = now.tv_usec;
+		list_del(&e->base.link);
 		drm_vblank_put(dev, e->pipe);
-		list_move_tail(&e->base.link, &e->base.file_priv->event_list);
-		wake_up_interruptible(&e->base.file_priv->event_wait);
-		trace_drm_vblank_event_delivered(e->base.pid, e->pipe,
-						 e->event.sequence);
+		send_vblank_event(dev, e, seq, &now);
 	}
 
 	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
@@ -1107,15 +1148,9 @@ static int drm_queue_vblank_event(struct drm_device *dev, int pipe,
 
 	e->event.sequence = vblwait->request.sequence;
 	if ((seq - vblwait->request.sequence) <= (1 << 23)) {
-		e->event.sequence = seq;
-		e->event.tv_sec = now.tv_sec;
-		e->event.tv_usec = now.tv_usec;
 		drm_vblank_put(dev, pipe);
-		list_add_tail(&e->base.link, &e->base.file_priv->event_list);
-		wake_up_interruptible(&e->base.file_priv->event_wait);
+		send_vblank_event(dev, e, seq, &now);
 		vblwait->reply.sequence = seq;
-		trace_drm_vblank_event_delivered(current->pid, pipe,
-						 vblwait->request.sequence);
 	} else {
 		/* drm_handle_vblank_events will call drm_vblank_put */
 		list_add_tail(&e->base.link, &dev->vblank_event_list);
@@ -1256,14 +1291,9 @@ static void drm_handle_vblank_events(struct drm_device *dev, int crtc)
 		DRM_DEBUG("vblank event on %d, current %d\n",
 			  e->event.sequence, seq);
 
-		e->event.sequence = seq;
-		e->event.tv_sec = now.tv_sec;
-		e->event.tv_usec = now.tv_usec;
+		list_del(&e->base.link);
 		drm_vblank_put(dev, e->pipe);
-		list_move_tail(&e->base.link, &e->base.file_priv->event_list);
-		wake_up_interruptible(&e->base.file_priv->event_wait);
-		trace_drm_vblank_event_delivered(e->base.pid, e->pipe,
-						 e->event.sequence);
+		send_vblank_event(dev, e, seq, &now);
 	}
 
 	spin_unlock_irqrestore(&dev->event_lock, flags);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 3fd82809b2d4..29eb23799aa4 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1431,6 +1431,8 @@ extern int drm_vblank_wait(struct drm_device *dev, unsigned int *vbl_seq);
 extern u32 drm_vblank_count(struct drm_device *dev, int crtc);
 extern u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc,
 				     struct timeval *vblanktime);
+extern void drm_send_vblank_event(struct drm_device *dev, int crtc,
+				     struct drm_pending_vblank_event *e);
 extern bool drm_handle_vblank(struct drm_device *dev, int crtc);
 extern int drm_vblank_get(struct drm_device *dev, int crtc);
 extern void drm_vblank_put(struct drm_device *dev, int crtc);
-- 
cgit v1.2.3-55-g7522


From 3d3683f04a32da16df71e3b089da8f5a13059ef4 Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Tue, 23 Oct 2012 18:23:32 +0000
Subject: drm: extract drm_kms_helper_hotplug_event

Useful if drivers want to be slightly more clever about hotplug
handling.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_crtc_helper.c | 17 +++++++++++------
 include/drm/drm_crtc_helper.h     |  1 +
 2 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index b04cf5332599..760a67534c6c 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -936,6 +936,15 @@ int drm_helper_resume_force_mode(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_helper_resume_force_mode);
 
+void drm_kms_helper_hotplug_event(struct drm_device *dev)
+{
+	/* send a uevent + call fbdev */
+	drm_sysfs_hotplug_event(dev);
+	if (dev->mode_config.funcs->output_poll_changed)
+		dev->mode_config.funcs->output_poll_changed(dev);
+}
+EXPORT_SYMBOL(drm_kms_helper_hotplug_event);
+
 #define DRM_OUTPUT_POLL_PERIOD (10*HZ)
 static void output_poll_execute(struct work_struct *work)
 {
@@ -978,12 +987,8 @@ static void output_poll_execute(struct work_struct *work)
 
 	mutex_unlock(&dev->mode_config.mutex);
 
-	if (changed) {
-		/* send a uevent + call fbdev */
-		drm_sysfs_hotplug_event(dev);
-		if (dev->mode_config.funcs->output_poll_changed)
-			dev->mode_config.funcs->output_poll_changed(dev);
-	}
+	if (changed)
+		drm_kms_helper_hotplug_event(dev);
 
 	if (repoll)
 		schedule_delayed_work(delayed_work, DRM_OUTPUT_POLL_PERIOD);
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index defee28f6b95..f43d556bf40b 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -164,6 +164,7 @@ extern int drm_helper_resume_force_mode(struct drm_device *dev);
 extern void drm_kms_helper_poll_init(struct drm_device *dev);
 extern void drm_kms_helper_poll_fini(struct drm_device *dev);
 extern void drm_helper_hpd_irq_event(struct drm_device *dev);
+extern void drm_kms_helper_hotplug_event(struct drm_device *dev);
 
 extern void drm_kms_helper_poll_disable(struct drm_device *dev);
 extern void drm_kms_helper_poll_enable(struct drm_device *dev);
-- 
cgit v1.2.3-55-g7522


From 816da85a0990c2b52cfffa77637d1c770d6790e9 Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Tue, 23 Oct 2012 18:23:33 +0000
Subject: drm: handle HPD and polled connectors separately

Instead of reusing the polling code for hpd handling, split them up.
This has a few consequences:
- Don't touch HPD capable connectors in the poll loop.
- Only touch HPD capable connectors in drm_helper_hpd_irq_event.
- We could run the HPD handling directly (because all callers already
  use their own work item), but for easier bisect that happens in it's
  own patch.

The ultimate goal is that drivers grow some smarts about which
connectors have received a hotplug event and only call the detect code
of that connector. But that's a second step.

v2: s/hdp/hpd/, noticed by Adam Jackson. I can't type.

v3: Split out the work item removal as requested by Dave Airlie. This
results in a temporary mode_config.hpd_irq_work item to keep things
the same.

v4: In the hpd_irq_event handler don't bail out if other bits than HPD
are set. This is useful where e.g. hpd is unreliably, but mostly
works. Drivers can then set both HPD and POLL flags, and users get the
best of both worlds: Quick hotplug feedback if the hpd works, but
still reliable detection with the polling. The poll loop already works
the same, and doesn't bail if HPD is set.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_crtc_helper.c | 51 ++++++++++++++++++++++++++++++++-------
 include/drm/drm_crtc.h            |  1 +
 2 files changed, 43 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 760a67534c6c..9adbd2b311d0 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -960,9 +960,9 @@ static void output_poll_execute(struct work_struct *work)
 	mutex_lock(&dev->mode_config.mutex);
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 
-		/* if this is HPD or polled don't check it -
-		   TV out for instance */
-		if (!connector->polled)
+		/* Ignore HPD capable connectors and connectors where we don't
+		 * want any hotplug detection at all for polling. */
+		if (!connector->polled || connector->polled == DRM_CONNECTOR_POLL_HPD)
 			continue;
 
 		else if (connector->polled & (DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT))
@@ -972,8 +972,7 @@ static void output_poll_execute(struct work_struct *work)
 		/* if we are connected and don't want to poll for disconnect
 		   skip it */
 		if (old_status == connector_status_connected &&
-		    !(connector->polled & DRM_CONNECTOR_POLL_DISCONNECT) &&
-		    !(connector->polled & DRM_CONNECTOR_POLL_HPD))
+		    !(connector->polled & DRM_CONNECTOR_POLL_DISCONNECT))
 			continue;
 
 		connector->status = connector->funcs->detect(connector, false);
@@ -1020,9 +1019,12 @@ void drm_kms_helper_poll_enable(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_kms_helper_poll_enable);
 
+static void hpd_irq_event_execute(struct work_struct *work);
+
 void drm_kms_helper_poll_init(struct drm_device *dev)
 {
 	INIT_DELAYED_WORK(&dev->mode_config.output_poll_work, output_poll_execute);
+	INIT_DELAYED_WORK(&dev->mode_config.hpd_irq_work, hpd_irq_event_execute);
 	dev->mode_config.poll_enabled = true;
 
 	drm_kms_helper_poll_enable(dev);
@@ -1035,14 +1037,45 @@ void drm_kms_helper_poll_fini(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_kms_helper_poll_fini);
 
-void drm_helper_hpd_irq_event(struct drm_device *dev)
+static void hpd_irq_event_execute(struct work_struct *work)
 {
+	struct delayed_work *delayed_work = to_delayed_work(work);
+	struct drm_device *dev = container_of(delayed_work, struct drm_device, mode_config.hpd_irq_work);
+	struct drm_connector *connector;
+	enum drm_connector_status old_status;
+	bool changed = false;
+
 	if (!dev->mode_config.poll_enabled)
 		return;
 
-	/* kill timer and schedule immediate execution, this doesn't block */
-	cancel_delayed_work(&dev->mode_config.output_poll_work);
+	mutex_lock(&dev->mode_config.mutex);
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+
+		/* Only handle HPD capable connectors. */
+		if (!(connector->polled & DRM_CONNECTOR_POLL_HPD))
+			continue;
+
+		old_status = connector->status;
+
+		connector->status = connector->funcs->detect(connector, false);
+		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %d to %d\n",
+			      connector->base.id,
+			      drm_get_connector_name(connector),
+			      old_status, connector->status);
+		if (old_status != connector->status)
+			changed = true;
+	}
+
+	mutex_unlock(&dev->mode_config.mutex);
+
+	if (changed)
+		drm_kms_helper_hotplug_event(dev);
+}
+
+void drm_helper_hpd_irq_event(struct drm_device *dev)
+{
+	cancel_delayed_work(&dev->mode_config.hpd_irq_work);
 	if (drm_kms_helper_poll)
-		schedule_delayed_work(&dev->mode_config.output_poll_work, 0);
+		schedule_delayed_work(&dev->mode_config.hpd_irq_work, 0);
 }
 EXPORT_SYMBOL(drm_helper_hpd_irq_event);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 1f5f1d642a98..ccff8c9b3780 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -793,6 +793,7 @@ struct drm_mode_config {
 	/* output poll support */
 	bool poll_enabled;
 	struct delayed_work output_poll_work;
+	struct delayed_work hpd_irq_work;
 
 	/* pointers to standard properties */
 	struct list_head property_blob_list;
-- 
cgit v1.2.3-55-g7522


From 69787f7da6b2adc4054357a661aaa1701a9ca76f Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Tue, 23 Oct 2012 18:23:34 +0000
Subject: drm: run the hpd irq event code directly

All drivers already have a work item to run the hpd code, so we don't
need to launch a new one in the helper code. Dave Airlie mentioned
that the cancel+re-queue might paper over DP related hpd ping-pongs,
hence why this is split out.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_crtc_helper.c | 14 +-------------
 include/drm/drm_crtc.h            |  1 -
 2 files changed, 1 insertion(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 9adbd2b311d0..a8a61e43f93b 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -1019,12 +1019,9 @@ void drm_kms_helper_poll_enable(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_kms_helper_poll_enable);
 
-static void hpd_irq_event_execute(struct work_struct *work);
-
 void drm_kms_helper_poll_init(struct drm_device *dev)
 {
 	INIT_DELAYED_WORK(&dev->mode_config.output_poll_work, output_poll_execute);
-	INIT_DELAYED_WORK(&dev->mode_config.hpd_irq_work, hpd_irq_event_execute);
 	dev->mode_config.poll_enabled = true;
 
 	drm_kms_helper_poll_enable(dev);
@@ -1037,10 +1034,8 @@ void drm_kms_helper_poll_fini(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_kms_helper_poll_fini);
 
-static void hpd_irq_event_execute(struct work_struct *work)
+void drm_helper_hpd_irq_event(struct drm_device *dev)
 {
-	struct delayed_work *delayed_work = to_delayed_work(work);
-	struct drm_device *dev = container_of(delayed_work, struct drm_device, mode_config.hpd_irq_work);
 	struct drm_connector *connector;
 	enum drm_connector_status old_status;
 	bool changed = false;
@@ -1071,11 +1066,4 @@ static void hpd_irq_event_execute(struct work_struct *work)
 	if (changed)
 		drm_kms_helper_hotplug_event(dev);
 }
-
-void drm_helper_hpd_irq_event(struct drm_device *dev)
-{
-	cancel_delayed_work(&dev->mode_config.hpd_irq_work);
-	if (drm_kms_helper_poll)
-		schedule_delayed_work(&dev->mode_config.hpd_irq_work, 0);
-}
 EXPORT_SYMBOL(drm_helper_hpd_irq_event);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index ccff8c9b3780..1f5f1d642a98 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -793,7 +793,6 @@ struct drm_mode_config {
 	/* output poll support */
 	bool poll_enabled;
 	struct delayed_work output_poll_work;
-	struct delayed_work hpd_irq_work;
 
 	/* pointers to standard properties */
 	struct list_head property_blob_list;
-- 
cgit v1.2.3-55-g7522


From 905bc9ff6575f78aab24c0261e8785425b5a0397 Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Tue, 23 Oct 2012 18:23:36 +0000
Subject: drm: don't start the poll engine in probe_single_connector

Actually there's a reason this stuff is there, and it's called

commit e58f637bb96d5a0ae0919b9998b891d1ba7e47c9
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Fri Aug 20 09:13:36 2010 +0100

    drm/kms: Add a module parameter to disable polling

The idea has been that users can enable/disable polling at runtime. So
the quick hack has been to just re-enable the output polling if xrandr
asks for the latest state of the connectors.

The problem with that hack is that when we force connectors to another
state than what would be detected, we nicely ping-pong:
- Userspace calls probe, gets the forced state, but polling starts
  again.
- Polling notices that the state is actually different, wakes up
  userspace.
- Repeat.

As that commit already explains, the right fix would be to make the
locking more fine-grained, so that hotplug detection on one output
does not interfere with cursor updates on another crtc.

But that is way too much work. So let's just safe this gross hack by
caching the last-seen state of drm_kms_helper_poll for that driver,
and only fire up the poll engine again if it changed from off to on.

v2: Fixup the edge detection of drm_kms_helper_poll.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=49907
Tested-by: Tvrtko Ursulin <tvrtko.ursulin@onelan.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_crtc_helper.c | 7 ++++++-
 include/drm/drm_crtc.h            | 1 +
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index a8a61e43f93b..5ee192885c97 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -127,9 +127,14 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 			connector->funcs->force(connector);
 	} else {
 		connector->status = connector->funcs->detect(connector, true);
-		drm_kms_helper_poll_enable(dev);
 	}
 
+	/* Re-enable polling in case the global poll config changed. */
+	if (drm_kms_helper_poll != dev->mode_config.poll_running)
+		drm_kms_helper_poll_enable(dev);
+
+	dev->mode_config.poll_running = drm_kms_helper_poll;
+
 	if (connector->status == connector_status_disconnected) {
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n",
 			connector->base.id, drm_get_connector_name(connector));
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 1f5f1d642a98..c0635b7f8696 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -792,6 +792,7 @@ struct drm_mode_config {
 
 	/* output poll support */
 	bool poll_enabled;
+	bool poll_running;
 	struct delayed_work output_poll_work;
 
 	/* pointers to standard properties */
-- 
cgit v1.2.3-55-g7522


From c61eef726a78ae77b6ce223d01ea2130f465fe5c Mon Sep 17 00:00:00 2001
From: Imre Deak
Date: Tue, 23 Oct 2012 18:53:26 +0000
Subject: drm: add support for monotonic vblank timestamps

Jumps in the vblank and page flip event timestamps cause trouble for
clients, so we should avoid them. The timestamp we get currently with
gettimeofday can jump, so use instead monotonic timestamps.

For backward compatibility use a module flag to revert back to using
gettimeofday timestamps. Add also a DRM_CAP_TIMESTAMP_MONOTONIC flag
that is simply a read only version of the module flag, so that clients
can query this without depending on sysfs.

Signed-off-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_ioctl.c |  3 +++
 drivers/gpu/drm/drm_irq.c   | 25 ++++++++++++++++++++-----
 drivers/gpu/drm/drm_stub.c  |  8 ++++++++
 include/drm/drmP.h          |  1 +
 include/uapi/drm/drm.h      |  1 +
 5 files changed, 33 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 23dd97506f28..e77bd8b57df2 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -287,6 +287,9 @@ int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 		req->value |= dev->driver->prime_fd_to_handle ? DRM_PRIME_CAP_IMPORT : 0;
 		req->value |= dev->driver->prime_handle_to_fd ? DRM_PRIME_CAP_EXPORT : 0;
 		break;
+	case DRM_CAP_TIMESTAMP_MONOTONIC:
+		req->value = drm_timestamp_monotonic;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index ef5b5f70735e..c0f0046d8078 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -633,7 +633,8 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 
 		/* Get system timestamp after query. */
 		etime = ktime_get();
-		mono_time_offset = ktime_get_monotonic_offset();
+		if (!drm_timestamp_monotonic)
+			mono_time_offset = ktime_get_monotonic_offset();
 
 		preempt_enable();
 
@@ -691,7 +692,9 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 		vbl_status |= 0x8;
 	}
 
-	etime = ktime_sub(etime, mono_time_offset);
+	if (!drm_timestamp_monotonic)
+		etime = ktime_sub(etime, mono_time_offset);
+
 	/* save this only for debugging purposes */
 	tv_etime = ktime_to_timeval(etime);
 	/* Subtract time delta from raw timestamp to get final
@@ -714,6 +717,17 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 }
 EXPORT_SYMBOL(drm_calc_vbltimestamp_from_scanoutpos);
 
+static struct timeval get_drm_timestamp(void)
+{
+	ktime_t now;
+
+	now = ktime_get();
+	if (!drm_timestamp_monotonic)
+		now = ktime_sub(now, ktime_get_monotonic_offset());
+
+	return ktime_to_timeval(now);
+}
+
 /**
  * drm_get_last_vbltimestamp - retrieve raw timestamp for the most recent
  * vblank interval.
@@ -751,9 +765,9 @@ u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
 	}
 
 	/* GPU high precision timestamp query unsupported or failed.
-	 * Return gettimeofday timestamp as best estimate.
+	 * Return current monotonic/gettimeofday timestamp as best estimate.
 	 */
-	do_gettimeofday(tvblank);
+	*tvblank = get_drm_timestamp();
 
 	return 0;
 }
@@ -842,7 +856,8 @@ void drm_send_vblank_event(struct drm_device *dev, int crtc,
 		seq = drm_vblank_count_and_time(dev, crtc, &now);
 	} else {
 		seq = 0;
-		do_gettimeofday(&now);
+
+		now = get_drm_timestamp();
 	}
 	send_vblank_event(dev, e, seq, &now);
 }
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 6fcdd8ebcb3d..200e104f1fa0 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -46,16 +46,24 @@ EXPORT_SYMBOL(drm_vblank_offdelay);
 unsigned int drm_timestamp_precision = 20;  /* Default to 20 usecs. */
 EXPORT_SYMBOL(drm_timestamp_precision);
 
+/*
+ * Default to use monotonic timestamps for wait-for-vblank and page-flip
+ * complete events.
+ */
+unsigned int drm_timestamp_monotonic = 1;
+
 MODULE_AUTHOR(CORE_AUTHOR);
 MODULE_DESCRIPTION(CORE_DESC);
 MODULE_LICENSE("GPL and additional rights");
 MODULE_PARM_DESC(debug, "Enable debug output");
 MODULE_PARM_DESC(vblankoffdelay, "Delay until vblank irq auto-disable [msecs]");
 MODULE_PARM_DESC(timestamp_precision_usec, "Max. error on timestamps [usecs]");
+MODULE_PARM_DESC(timestamp_monotonic, "Use monotonic timestamps");
 
 module_param_named(debug, drm_debug, int, 0600);
 module_param_named(vblankoffdelay, drm_vblank_offdelay, int, 0600);
 module_param_named(timestamp_precision_usec, drm_timestamp_precision, int, 0600);
+module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600);
 
 struct idr drm_minors_idr;
 
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 29eb23799aa4..fad21c927a38 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1505,6 +1505,7 @@ extern unsigned int drm_debug;
 
 extern unsigned int drm_vblank_offdelay;
 extern unsigned int drm_timestamp_precision;
+extern unsigned int drm_timestamp_monotonic;
 
 extern struct class *drm_class;
 extern struct proc_dir_entry *drm_proc_root;
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 1e3481edf062..8d1e2bbee83a 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -778,6 +778,7 @@ struct drm_event_vblank {
 #define DRM_CAP_DUMB_PREFERRED_DEPTH 0x3
 #define DRM_CAP_DUMB_PREFER_SHADOW 0x4
 #define DRM_CAP_PRIME 0x5
+#define DRM_CAP_TIMESTAMP_MONOTONIC 0x6
 
 #define DRM_PRIME_CAP_IMPORT 0x1
 #define DRM_PRIME_CAP_EXPORT 0x2
-- 
cgit v1.2.3-55-g7522


From 0b91c4a1cd7cc368763de2fe25b8ea64ea803c08 Mon Sep 17 00:00:00 2001
From: Marcin Slusarz
Date: Tue, 6 Nov 2012 21:49:51 +0000
Subject: drm/ttm: remove ttm_buffer_object->buffer_start

All drivers set it to 0 and nothing uses it.

Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/ast/ast_ttm.c            | 2 +-
 drivers/gpu/drm/cirrus/cirrus_ttm.c      | 2 +-
 drivers/gpu/drm/mgag200/mgag200_ttm.c    | 2 +-
 drivers/gpu/drm/nouveau/nouveau_bo.c     | 2 +-
 drivers/gpu/drm/radeon/radeon_object.c   | 2 +-
 drivers/gpu/drm/ttm/ttm_bo.c             | 8 ++------
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c      | 2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 4 ++--
 include/drm/ttm/ttm_bo_api.h             | 9 ---------
 9 files changed, 10 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 1a026ac2dfb4..0a54f65a8ebb 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -356,7 +356,7 @@ int ast_bo_create(struct drm_device *dev, int size, int align,
 
 	ret = ttm_bo_init(&ast->ttm.bdev, &astbo->bo, size,
 			  ttm_bo_type_device, &astbo->placement,
-			  align >> PAGE_SHIFT, 0, false, NULL, acc_size,
+			  align >> PAGE_SHIFT, false, NULL, acc_size,
 			  NULL, ast_bo_ttm_destroy);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index bc83f835c830..90d770143cc2 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -361,7 +361,7 @@ int cirrus_bo_create(struct drm_device *dev, int size, int align,
 
 	ret = ttm_bo_init(&cirrus->ttm.bdev, &cirrusbo->bo, size,
 			  ttm_bo_type_device, &cirrusbo->placement,
-			  align >> PAGE_SHIFT, 0, false, NULL, acc_size,
+			  align >> PAGE_SHIFT, false, NULL, acc_size,
 			  NULL, cirrus_bo_ttm_destroy);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 1504699666c4..49d60a620122 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -355,7 +355,7 @@ int mgag200_bo_create(struct drm_device *dev, int size, int align,
 
 	ret = ttm_bo_init(&mdev->ttm.bdev, &mgabo->bo, size,
 			  ttm_bo_type_device, &mgabo->placement,
-			  align >> PAGE_SHIFT, 0, false, NULL, acc_size,
+			  align >> PAGE_SHIFT, false, NULL, acc_size,
 			  NULL, mgag200_bo_ttm_destroy);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 35ac57f0aab6..3cbf1a8cf551 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -225,7 +225,7 @@ nouveau_bo_new(struct drm_device *dev, int size, int align,
 
 	ret = ttm_bo_init(&drm->ttm.bdev, &nvbo->bo, size,
 			  type, &nvbo->placement,
-			  align >> PAGE_SHIFT, 0, false, NULL, acc_size, sg,
+			  align >> PAGE_SHIFT, false, NULL, acc_size, sg,
 			  nouveau_bo_del_ttm);
 	if (ret) {
 		/* ttm will call nouveau_bo_del_ttm if it fails.. */
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 65c55556fd3f..7c4b4bb05a36 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -140,7 +140,7 @@ int radeon_bo_create(struct radeon_device *rdev,
 	/* Kernel allocation are uninterruptible */
 	down_read(&rdev->pm.mclk_lock);
 	r = ttm_bo_init(&rdev->mman.bdev, &bo->tbo, size, type,
-			&bo->placement, page_align, 0, !kernel, NULL,
+			&bo->placement, page_align, !kernel, NULL,
 			acc_size, sg, &radeon_ttm_bo_destroy);
 	up_read(&rdev->pm.mclk_lock);
 	if (unlikely(r != 0)) {
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index e6bfcfdd3b60..f65182667825 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1179,7 +1179,6 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 		enum ttm_bo_type type,
 		struct ttm_placement *placement,
 		uint32_t page_alignment,
-		unsigned long buffer_start,
 		bool interruptible,
 		struct file *persistent_swap_storage,
 		size_t acc_size,
@@ -1200,7 +1199,6 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 		return -ENOMEM;
 	}
 
-	size += buffer_start & ~PAGE_MASK;
 	num_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (num_pages == 0) {
 		pr_err("Illegal buffer object size\n");
@@ -1233,7 +1231,6 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	bo->mem.page_alignment = page_alignment;
 	bo->mem.bus.io_reserved_vm = false;
 	bo->mem.bus.io_reserved_count = 0;
-	bo->buffer_start = buffer_start & PAGE_MASK;
 	bo->priv_flags = 0;
 	bo->mem.placement = (TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED);
 	bo->seq_valid = false;
@@ -1306,7 +1303,6 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 			enum ttm_bo_type type,
 			struct ttm_placement *placement,
 			uint32_t page_alignment,
-			unsigned long buffer_start,
 			bool interruptible,
 			struct file *persistent_swap_storage,
 			struct ttm_buffer_object **p_bo)
@@ -1321,8 +1317,8 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 
 	acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
 	ret = ttm_bo_init(bdev, bo, size, type, placement, page_alignment,
-				buffer_start, interruptible,
-			  persistent_swap_storage, acc_size, NULL, NULL);
+			  interruptible, persistent_swap_storage, acc_size,
+			  NULL, NULL);
 	if (likely(ret == 0))
 		*p_bo = bo;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index ed3c1e7ddde9..9f37b72a472c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -292,7 +292,7 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv)
 			     PAGE_SIZE,
 			     ttm_bo_type_device,
 			     &vmw_vram_sys_placement,
-			     0, 0, false, NULL,
+			     0, false, NULL,
 			     &dev_priv->dummy_query_bo);
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index da3c6b5b98a1..be87124a2769 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -954,7 +954,7 @@ int vmw_surface_evict(struct vmw_private *dev_priv,
 	if (!srf->backup) {
 		ret = ttm_bo_create(&dev_priv->bdev, srf->backup_size,
 				    ttm_bo_type_device,
-				    &vmw_srf_placement, 0, 0, true,
+				    &vmw_srf_placement, 0, true,
 				    NULL, &srf->backup);
 		if (unlikely(ret != 0))
 			return ret;
@@ -1566,7 +1566,7 @@ int vmw_dmabuf_init(struct vmw_private *dev_priv,
 
 	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
 			  ttm_bo_type_device, placement,
-			  0, 0, interruptible,
+			  0, interruptible,
 			  NULL, acc_size, NULL, bo_free);
 	return ret;
 }
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 36e8408e00fa..a554c2e22d56 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -141,8 +141,6 @@ struct ttm_tt;
  * struct ttm_buffer_object
  *
  * @bdev: Pointer to the buffer object device structure.
- * @buffer_start: The virtual user-space start address of ttm_bo_type_user
- * buffers.
  * @type: The bo type.
  * @destroy: Destruction function. If NULL, kfree is used.
  * @num_pages: Actual number of pages.
@@ -200,7 +198,6 @@ struct ttm_buffer_object {
 
 	struct ttm_bo_global *glob;
 	struct ttm_bo_device *bdev;
-	unsigned long buffer_start;
 	enum ttm_bo_type type;
 	void (*destroy) (struct ttm_buffer_object *);
 	unsigned long num_pages;
@@ -472,8 +469,6 @@ size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev,
  * @type: Requested type of buffer object.
  * @flags: Initial placement flags.
  * @page_alignment: Data alignment in pages.
- * @buffer_start: Virtual address of user space data backing a
- * user buffer object.
  * @interruptible: If needing to sleep to wait for GPU resources,
  * sleep interruptible.
  * @persistent_swap_storage: Usually the swap storage is deleted for buffers
@@ -505,7 +500,6 @@ extern int ttm_bo_init(struct ttm_bo_device *bdev,
 			enum ttm_bo_type type,
 			struct ttm_placement *placement,
 			uint32_t page_alignment,
-			unsigned long buffer_start,
 			bool interrubtible,
 			struct file *persistent_swap_storage,
 			size_t acc_size,
@@ -521,8 +515,6 @@ extern int ttm_bo_init(struct ttm_bo_device *bdev,
  * @type: Requested type of buffer object.
  * @flags: Initial placement flags.
  * @page_alignment: Data alignment in pages.
- * @buffer_start: Virtual address of user space data backing a
- * user buffer object.
  * @interruptible: If needing to sleep while waiting for GPU resources,
  * sleep interruptible.
  * @persistent_swap_storage: Usually the swap storage is deleted for buffers
@@ -545,7 +537,6 @@ extern int ttm_bo_create(struct ttm_bo_device *bdev,
 				enum ttm_bo_type type,
 				struct ttm_placement *placement,
 				uint32_t page_alignment,
-				unsigned long buffer_start,
 				bool interruptible,
 				struct file *persistent_swap_storage,
 				struct ttm_buffer_object **p_bo);
-- 
cgit v1.2.3-55-g7522


From 830e2837f5f6811b77cf3aa72e63343a8e6e9ef6 Mon Sep 17 00:00:00 2001
From: Marcin Slusarz
Date: Tue, 6 Nov 2012 21:49:53 +0000
Subject: drm/ttm: remove ttm_bo_device->nice_mode

It's unused.

Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c    | 1 -
 include/drm/ttm/ttm_bo_driver.h | 3 ---
 2 files changed, 4 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index f65182667825..4066e788cff8 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1573,7 +1573,6 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 		goto out_no_addr_mm;
 
 	INIT_DELAYED_WORK(&bdev->wq, ttm_bo_delayed_workqueue);
-	bdev->nice_mode = true;
 	INIT_LIST_HEAD(&bdev->ddestroy);
 	bdev->dev_mapping = NULL;
 	bdev->glob = glob;
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index d803b92b0324..95628e7da5bf 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -521,8 +521,6 @@ struct ttm_bo_global {
  * lru_lock: Spinlock that protects the buffer+device lru lists and
  * ddestroy lists.
  * @val_seq: Current validation sequence.
- * @nice_mode: Try nicely to wait for buffer idle when cleaning a manager.
- * If a GPU lockup has been detected, this is forced to 0.
  * @dev_mapping: A pointer to the struct address_space representing the
  * device address space.
  * @wq: Work queue structure for the delayed delete workqueue.
@@ -556,7 +554,6 @@ struct ttm_bo_device {
 	 * Protected by load / firstopen / lastclose /unload sync.
 	 */
 
-	bool nice_mode;
 	struct address_space *dev_mapping;
 
 	/*
-- 
cgit v1.2.3-55-g7522


From 91926741ecd28dc246875a39a908c2f6aadb2542 Mon Sep 17 00:00:00 2001
From: Marcin Slusarz
Date: Tue, 6 Nov 2012 21:49:54 +0000
Subject: drm/ttm: remove ttm_mem_global->queue

It's unused.

Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/ttm/ttm_memory.c | 1 -
 include/drm/ttm/ttm_memory.h     | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c
index 479c6b0467ca..dbc2def887cd 100644
--- a/drivers/gpu/drm/ttm/ttm_memory.c
+++ b/drivers/gpu/drm/ttm/ttm_memory.c
@@ -367,7 +367,6 @@ int ttm_mem_global_init(struct ttm_mem_global *glob)
 	spin_lock_init(&glob->lock);
 	glob->swap_queue = create_singlethread_workqueue("ttm_swap");
 	INIT_WORK(&glob->work, ttm_shrink_work);
-	init_waitqueue_head(&glob->queue);
 	ret = kobject_init_and_add(
 		&glob->kobj, &ttm_mem_glob_kobj_type, ttm_get_kobj(), "memory_accounting");
 	if (unlikely(ret != 0)) {
diff --git a/include/drm/ttm/ttm_memory.h b/include/drm/ttm/ttm_memory.h
index d6d1da468c97..72dcbe81dd07 100644
--- a/include/drm/ttm/ttm_memory.h
+++ b/include/drm/ttm/ttm_memory.h
@@ -60,7 +60,6 @@ struct ttm_mem_shrink {
  * for the GPU, and this will otherwise block other workqueue tasks(?)
  * At this point we use only a single-threaded workqueue.
  * @work: The workqueue callback for the shrink queue.
- * @queue: Wait queue for processes suspended waiting for memory.
  * @lock: Lock to protect the @shrink - and the memory accounting members,
  * that is, essentially the whole structure with some exceptions.
  * @zones: Array of pointers to accounting zones.
@@ -80,7 +79,6 @@ struct ttm_mem_global {
 	struct ttm_mem_shrink *shrink;
 	struct workqueue_struct *swap_queue;
 	struct work_struct work;
-	wait_queue_head_t queue;
 	spinlock_t lock;
 	struct ttm_mem_zone *zones[TTM_MEM_MAX_ZONES];
 	unsigned int num_zones;
-- 
cgit v1.2.3-55-g7522


From 5fb4ef0e36b4c6ecc7fb025aaacb3b63b1114e87 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst
Date: Fri, 12 Oct 2012 15:02:19 +0000
Subject: drm/ttm: remove sync_obj_arg member

vmwgfx was its only user and always sets it to the same..

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Reviewed-By: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c           | 13 ++++---------
 drivers/gpu/drm/ttm/ttm_bo_util.c      |  1 -
 drivers/gpu/drm/ttm/ttm_execbuf_util.c |  1 -
 include/drm/ttm/ttm_bo_api.h           |  2 --
 include/drm/ttm/ttm_execbuf_util.h     |  3 ---
 5 files changed, 4 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 4066e788cff8..4cb3f493da76 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -501,7 +501,6 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 	struct ttm_bo_global *glob = bo->glob;
 	struct ttm_bo_driver *driver;
 	void *sync_obj = NULL;
-	void *sync_obj_arg;
 	int put_count;
 	int ret;
 
@@ -537,7 +536,6 @@ queue:
 	driver = bdev->driver;
 	if (bo->sync_obj)
 		sync_obj = driver->sync_obj_ref(bo->sync_obj);
-	sync_obj_arg = bo->sync_obj_arg;
 
 	kref_get(&bo->list_kref);
 	list_add_tail(&bo->ddestroy, &bdev->ddestroy);
@@ -545,7 +543,7 @@ queue:
 	spin_unlock(&bdev->fence_lock);
 
 	if (sync_obj) {
-		driver->sync_obj_flush(sync_obj, sync_obj_arg);
+		driver->sync_obj_flush(sync_obj, NULL);
 		driver->sync_obj_unref(&sync_obj);
 	}
 	schedule_delayed_work(&bdev->wq,
@@ -1716,7 +1714,6 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 	struct ttm_bo_driver *driver = bo->bdev->driver;
 	struct ttm_bo_device *bdev = bo->bdev;
 	void *sync_obj;
-	void *sync_obj_arg;
 	int ret = 0;
 
 	if (likely(bo->sync_obj == NULL))
@@ -1724,7 +1721,7 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 
 	while (bo->sync_obj) {
 
-		if (driver->sync_obj_signaled(bo->sync_obj, bo->sync_obj_arg)) {
+		if (driver->sync_obj_signaled(bo->sync_obj, NULL)) {
 			void *tmp_obj = bo->sync_obj;
 			bo->sync_obj = NULL;
 			clear_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
@@ -1738,9 +1735,8 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 			return -EBUSY;
 
 		sync_obj = driver->sync_obj_ref(bo->sync_obj);
-		sync_obj_arg = bo->sync_obj_arg;
 		spin_unlock(&bdev->fence_lock);
-		ret = driver->sync_obj_wait(sync_obj, sync_obj_arg,
+		ret = driver->sync_obj_wait(sync_obj, NULL,
 					    lazy, interruptible);
 		if (unlikely(ret != 0)) {
 			driver->sync_obj_unref(&sync_obj);
@@ -1748,8 +1744,7 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 			return ret;
 		}
 		spin_lock(&bdev->fence_lock);
-		if (likely(bo->sync_obj == sync_obj &&
-			   bo->sync_obj_arg == sync_obj_arg)) {
+		if (likely(bo->sync_obj == sync_obj)) {
 			void *tmp_obj = bo->sync_obj;
 			bo->sync_obj = NULL;
 			clear_bit(TTM_BO_PRIV_FLAG_MOVING,
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 2026060f03e0..81c74f53ce4f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -630,7 +630,6 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		bo->sync_obj = NULL;
 	}
 	bo->sync_obj = driver->sync_obj_ref(sync_obj);
-	bo->sync_obj_arg = sync_obj_arg;
 	if (evict) {
 		ret = ttm_bo_wait(bo, false, false, false);
 		spin_unlock(&bdev->fence_lock);
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index 1937069432c5..b227a9961a07 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -223,7 +223,6 @@ void ttm_eu_fence_buffer_objects(struct list_head *list, void *sync_obj)
 		bo = entry->bo;
 		entry->old_sync_obj = bo->sync_obj;
 		bo->sync_obj = driver->sync_obj_ref(sync_obj);
-		bo->sync_obj_arg = entry->new_sync_obj_arg;
 		ttm_bo_unreserve_locked(bo);
 		entry->reserved = false;
 	}
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index a554c2e22d56..5ff938df5fce 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -170,7 +170,6 @@ struct ttm_tt;
  * @seq_valid: The value of @val_seq is valid. This value is protected by
  * the bo_device::lru_lock.
  * @reserved: Deadlock-free lock used for synchronization state transitions.
- * @sync_obj_arg: Opaque argument to synchronization object function.
  * @sync_obj: Pointer to a synchronization object.
  * @priv_flags: Flags describing buffer object internal state.
  * @vm_rb: Rb node for the vm rb tree.
@@ -252,7 +251,6 @@ struct ttm_buffer_object {
 	 * checking NULL while reserved but not holding the mentioned lock.
 	 */
 
-	void *sync_obj_arg;
 	void *sync_obj;
 	unsigned long priv_flags;
 
diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
index 1926cae373ba..547e19f06e57 100644
--- a/include/drm/ttm/ttm_execbuf_util.h
+++ b/include/drm/ttm/ttm_execbuf_util.h
@@ -39,8 +39,6 @@
  *
  * @head:           list head for thread-private list.
  * @bo:             refcounted buffer object pointer.
- * @new_sync_obj_arg: New sync_obj_arg for @bo, to be used once
- * adding a new sync object.
  * @reserved:       Indicates whether @bo has been reserved for validation.
  * @removed:        Indicates whether @bo has been removed from lru lists.
  * @put_count:      Number of outstanding references on bo::list_kref.
@@ -50,7 +48,6 @@
 struct ttm_validate_buffer {
 	struct list_head head;
 	struct ttm_buffer_object *bo;
-	void *new_sync_obj_arg;
 	bool reserved;
 	bool removed;
 	int put_count;
-- 
cgit v1.2.3-55-g7522


From b03640b1de2eb349c2453d060d0bd0b0486e29b8 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst
Date: Fri, 12 Oct 2012 15:03:11 +0000
Subject: drm/ttm: remove sync_obj_arg from ttm_bo_move_accel_cleanup

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Reviewed-By: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/nouveau/nouveau_bo.c | 2 +-
 drivers/gpu/drm/radeon/radeon_ttm.c  | 2 +-
 drivers/gpu/drm/ttm/ttm_bo_util.c    | 1 -
 include/drm/ttm/ttm_bo_driver.h      | 3 ---
 4 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 3cbf1a8cf551..6a2592f7daae 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -566,7 +566,7 @@ nouveau_bo_move_accel_cleanup(struct nouveau_channel *chan,
 	if (ret)
 		return ret;
 
-	ret = ttm_bo_move_accel_cleanup(&nvbo->bo, fence, NULL, evict,
+	ret = ttm_bo_move_accel_cleanup(&nvbo->bo, fence, evict,
 					no_wait_reserve, no_wait_gpu, new_mem);
 	nouveau_fence_unref(&fence);
 	return ret;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 5ebe1b3e5db2..929be87204da 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -265,7 +265,7 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 			new_mem->num_pages * (PAGE_SIZE / RADEON_GPU_PAGE_SIZE), /* GPU pages */
 			&fence);
 	/* FIXME: handle copy error */
-	r = ttm_bo_move_accel_cleanup(bo, (void *)fence, NULL,
+	r = ttm_bo_move_accel_cleanup(bo, (void *)fence,
 				      evict, no_wait_reserve, no_wait_gpu, new_mem);
 	radeon_fence_unref(&fence);
 	return r;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 81c74f53ce4f..b9c4e515b1d8 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -611,7 +611,6 @@ EXPORT_SYMBOL(ttm_bo_kunmap);
 
 int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			      void *sync_obj,
-			      void *sync_obj_arg,
 			      bool evict, bool no_wait_reserve,
 			      bool no_wait_gpu,
 			      struct ttm_mem_reg *new_mem)
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 95628e7da5bf..fc5fad09dae4 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -970,8 +970,6 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  *
  * @bo: A pointer to a struct ttm_buffer_object.
  * @sync_obj: A sync object that signals when moving is complete.
- * @sync_obj_arg: An argument to pass to the sync object idle / wait
- * functions.
  * @evict: This is an evict move. Don't return until the buffer is idle.
  * @no_wait_reserve: Return immediately if other buffers are busy.
  * @no_wait_gpu: Return immediately if the GPU is busy.
@@ -987,7 +985,6 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
 
 extern int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 				     void *sync_obj,
-				     void *sync_obj_arg,
 				     bool evict, bool no_wait_reserve,
 				     bool no_wait_gpu,
 				     struct ttm_mem_reg *new_mem);
-- 
cgit v1.2.3-55-g7522


From dedfdffd448aea2543b59fd504b92b8212ab3b7d Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst
Date: Fri, 12 Oct 2012 15:04:00 +0000
Subject: drm/ttm: remove sync_arg from driver functions

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Reviewed-By: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/nouveau/nouveau_bo.c   | 6 +++---
 drivers/gpu/drm/radeon/radeon_ttm.c    | 7 +++----
 drivers/gpu/drm/ttm/ttm_bo.c           | 6 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c | 7 +++----
 include/drm/ttm/ttm_bo_driver.h        | 6 +++---
 5 files changed, 15 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 6a2592f7daae..4c950b4cf416 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1472,19 +1472,19 @@ nouveau_bo_fence_ref(void *sync_obj)
 }
 
 static bool
-nouveau_bo_fence_signalled(void *sync_obj, void *sync_arg)
+nouveau_bo_fence_signalled(void *sync_obj)
 {
 	return nouveau_fence_done(sync_obj);
 }
 
 static int
-nouveau_bo_fence_wait(void *sync_obj, void *sync_arg, bool lazy, bool intr)
+nouveau_bo_fence_wait(void *sync_obj, bool lazy, bool intr)
 {
 	return nouveau_fence_wait(sync_obj, lazy, intr);
 }
 
 static int
-nouveau_bo_fence_flush(void *sync_obj, void *sync_arg)
+nouveau_bo_fence_flush(void *sync_obj)
 {
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 929be87204da..563c8edcb03b 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -471,13 +471,12 @@ static void radeon_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_re
 {
 }
 
-static int radeon_sync_obj_wait(void *sync_obj, void *sync_arg,
-				bool lazy, bool interruptible)
+static int radeon_sync_obj_wait(void *sync_obj, bool lazy, bool interruptible)
 {
 	return radeon_fence_wait((struct radeon_fence *)sync_obj, interruptible);
 }
 
-static int radeon_sync_obj_flush(void *sync_obj, void *sync_arg)
+static int radeon_sync_obj_flush(void *sync_obj)
 {
 	return 0;
 }
@@ -492,7 +491,7 @@ static void *radeon_sync_obj_ref(void *sync_obj)
 	return radeon_fence_ref((struct radeon_fence *)sync_obj);
 }
 
-static bool radeon_sync_obj_signaled(void *sync_obj, void *sync_arg)
+static bool radeon_sync_obj_signaled(void *sync_obj)
 {
 	return radeon_fence_signaled((struct radeon_fence *)sync_obj);
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 4cb3f493da76..d1e5326d442c 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -543,7 +543,7 @@ queue:
 	spin_unlock(&bdev->fence_lock);
 
 	if (sync_obj) {
-		driver->sync_obj_flush(sync_obj, NULL);
+		driver->sync_obj_flush(sync_obj);
 		driver->sync_obj_unref(&sync_obj);
 	}
 	schedule_delayed_work(&bdev->wq,
@@ -1721,7 +1721,7 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 
 	while (bo->sync_obj) {
 
-		if (driver->sync_obj_signaled(bo->sync_obj, NULL)) {
+		if (driver->sync_obj_signaled(bo->sync_obj)) {
 			void *tmp_obj = bo->sync_obj;
 			bo->sync_obj = NULL;
 			clear_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
@@ -1736,7 +1736,7 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 
 		sync_obj = driver->sync_obj_ref(bo->sync_obj);
 		spin_unlock(&bdev->fence_lock);
-		ret = driver->sync_obj_wait(sync_obj, NULL,
+		ret = driver->sync_obj_wait(sync_obj,
 					    lazy, interruptible);
 		if (unlikely(ret != 0)) {
 			driver->sync_obj_unref(&sync_obj);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
index da12922b6313..ef1109c8fec8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
@@ -310,21 +310,20 @@ static void vmw_sync_obj_unref(void **sync_obj)
 	vmw_fence_obj_unreference((struct vmw_fence_obj **) sync_obj);
 }
 
-static int vmw_sync_obj_flush(void *sync_obj, void *sync_arg)
+static int vmw_sync_obj_flush(void *sync_obj)
 {
 	vmw_fence_obj_flush((struct vmw_fence_obj *) sync_obj);
 	return 0;
 }
 
-static bool vmw_sync_obj_signaled(void *sync_obj, void *sync_arg)
+static bool vmw_sync_obj_signaled(void *sync_obj)
 {
 	return	vmw_fence_obj_signaled((struct vmw_fence_obj *) sync_obj,
 				       DRM_VMW_FENCE_FLAG_EXEC);
 
 }
 
-static int vmw_sync_obj_wait(void *sync_obj, void *sync_arg,
-			     bool lazy, bool interruptible)
+static int vmw_sync_obj_wait(void *sync_obj, bool lazy, bool interruptible)
 {
 	return vmw_fence_obj_wait((struct vmw_fence_obj *) sync_obj,
 				  DRM_VMW_FENCE_FLAG_EXEC,
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index fc5fad09dae4..4789beee3b77 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -422,10 +422,10 @@ struct ttm_bo_driver {
 	 * documentation.
 	 */
 
-	bool (*sync_obj_signaled) (void *sync_obj, void *sync_arg);
-	int (*sync_obj_wait) (void *sync_obj, void *sync_arg,
+	bool (*sync_obj_signaled) (void *sync_obj);
+	int (*sync_obj_wait) (void *sync_obj,
 			      bool lazy, bool interruptible);
-	int (*sync_obj_flush) (void *sync_obj, void *sync_arg);
+	int (*sync_obj_flush) (void *sync_obj);
 	void (*sync_obj_unref) (void **sync_obj);
 	void *(*sync_obj_ref) (void *sync_obj);
 
-- 
cgit v1.2.3-55-g7522


From ab6340c4ecc21c01a487e9be15754d5f934a003a Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto
Date: Fri, 16 Nov 2012 01:17:18 -0800
Subject: ASoC: fsi: master clock selection become independent from platform
 flags

Current FSI driver is using platform information pointer,
but it is not good design for DT support.
This patch makes master clock selection
independent from platform information pointer.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/sound/sh_fsi.h |  4 ++--
 sound/soc/sh/fsi.c     | 17 ++++++++---------
 2 files changed, 10 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/sound/sh_fsi.h b/include/sound/sh_fsi.h
index 27ee1dcc3e2e..cc1c919c6436 100644
--- a/include/sound/sh_fsi.h
+++ b/include/sound/sh_fsi.h
@@ -47,8 +47,8 @@
 
 /* D:  clock selecter if master mode */
 #define SH_FSI_CLK_MASK		0x0000F000
-#define SH_FSI_CLK_EXTERNAL	(1 << 12)
-#define SH_FSI_CLK_CPG		(2 << 12) /* FSIxCK + FSI-DIV */
+#define SH_FSI_CLK_EXTERNAL	(0 << 12)
+#define SH_FSI_CLK_CPG		(1 << 12) /* FSIxCK + FSI-DIV */
 
 /*
  * set_rate return value
diff --git a/sound/soc/sh/fsi.c b/sound/soc/sh/fsi.c
index cc81a4966df5..77747b075369 100644
--- a/sound/soc/sh/fsi.c
+++ b/sound/soc/sh/fsi.c
@@ -264,6 +264,7 @@ struct fsi_priv {
 
 	int chan_num:16;
 	int clk_master:1;
+	int clk_cpg:1;
 	int spdif:1;
 
 	long rate;
@@ -1779,7 +1780,6 @@ static int fsi_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 {
 	struct fsi_priv *fsi = fsi_get_priv_frm_dai(dai);
 	set_rate_func set_rate = fsi_get_info_set_rate(fsi);
-	u32 flags = fsi_get_info_flags(fsi);
 	int ret;
 
 	/* set master/slave audio interface */
@@ -1802,16 +1802,12 @@ static int fsi_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		if (set_rate)
 			dev_warn(dai->dev, "set_rate will be removed soon\n");
 
-		switch (flags & SH_FSI_CLK_MASK) {
-		case SH_FSI_CLK_EXTERNAL:
-			fsi_clk_init(dai->dev, fsi, 1, 1, 0,
-				     fsi_clk_set_rate_external);
-			break;
-		case SH_FSI_CLK_CPG:
+		if (fsi->clk_cpg)
 			fsi_clk_init(dai->dev, fsi, 0, 1, 1,
 				     fsi_clk_set_rate_cpg);
-			break;
-		}
+		else
+			fsi_clk_init(dai->dev, fsi, 1, 1, 0,
+				     fsi_clk_set_rate_external);
 	}
 
 	/* set format */
@@ -1989,6 +1985,9 @@ static void fsi_port_info_init(struct fsi_priv *fsi,
 {
 	if (info->flags & SH_FSI_FMT_SPDIF)
 		fsi->spdif = 1;
+
+	if (info->flags & SH_FSI_CLK_CPG)
+		fsi->clk_cpg = 1;
 }
 
 static void fsi_handler_init(struct fsi_priv *fsi,
-- 
cgit v1.2.3-55-g7522


From 4b20db3de8dab005b07c74161cb041db8c5ff3a7 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom
Date: Tue, 6 Nov 2012 11:31:49 +0000
Subject: kref: Implement kref_get_unless_zero v3

This function is intended to simplify locking around refcounting for
objects that can be looked up from a lookup structure, and which are
removed from that lookup structure in the object destructor.
Operations on such objects require at least a read lock around
lookup + kref_get, and a write lock around kref_put + remove from lookup
structure. Furthermore, RCU implementations become extremely tricky.
With a lookup followed by a kref_get_unless_zero *with return value check*
locking in the kref_put path can be deferred to the actual removal from
the lookup structure and RCU lookups become trivial.

v2: Formatting fixes.
v3: Invert the return value.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/linux/kref.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

(limited to 'include')

diff --git a/include/linux/kref.h b/include/linux/kref.h
index 65af6887872f..4972e6e9ca93 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -111,4 +111,25 @@ static inline int kref_put_mutex(struct kref *kref,
 	}
 	return 0;
 }
+
+/**
+ * kref_get_unless_zero - Increment refcount for object unless it is zero.
+ * @kref: object.
+ *
+ * Return non-zero if the increment succeeded. Otherwise return 0.
+ *
+ * This function is intended to simplify locking around refcounting for
+ * objects that can be looked up from a lookup structure, and which are
+ * removed from that lookup structure in the object destructor.
+ * Operations on such objects require at least a read lock around
+ * lookup + kref_get, and a write lock around kref_put + remove from lookup
+ * structure. Furthermore, RCU implementations become extremely tricky.
+ * With a lookup followed by a kref_get_unless_zero *with return value check*
+ * locking in the kref_put path can be deferred to the actual removal from
+ * the lookup structure and RCU lookups become trivial.
+ */
+static inline int __must_check kref_get_unless_zero(struct kref *kref)
+{
+	return atomic_add_unless(&kref->refcount, 1, 0);
+}
 #endif /* _KREF_H_ */
-- 
cgit v1.2.3-55-g7522


From cdad05216c2b2edfe92a9f87d6ae51aab277f3b2 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom
Date: Tue, 6 Nov 2012 11:31:50 +0000
Subject: drm/ttm, drm/vmwgfx: Use RCU locking for object lookups v3

The mostly used lookup+get put+potential_destroy path of TTM objects
is converted to use RCU locks. This will substantially decrease the amount
of locked bus cycles during normal operation.
Since we use kfree_rcu to free the objects, no rcu synchronization is needed
at module unload time.

v2: Don't touch include/linux/kref.h
v3: Adapt to kref_get_unless_zero return value change

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/ttm/ttm_object.c         | 30 +++++++++++-------------------
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c |  8 ++++----
 include/drm/ttm/ttm_object.h             |  4 ++++
 3 files changed, 19 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c
index c7857874956a..f18eeb458139 100644
--- a/drivers/gpu/drm/ttm/ttm_object.c
+++ b/drivers/gpu/drm/ttm/ttm_object.c
@@ -80,7 +80,7 @@ struct ttm_object_file {
  */
 
 struct ttm_object_device {
-	rwlock_t object_lock;
+	spinlock_t object_lock;
 	struct drm_open_hash object_hash;
 	atomic_t object_count;
 	struct ttm_mem_global *mem_glob;
@@ -157,12 +157,12 @@ int ttm_base_object_init(struct ttm_object_file *tfile,
 	base->refcount_release = refcount_release;
 	base->ref_obj_release = ref_obj_release;
 	base->object_type = object_type;
-	write_lock(&tdev->object_lock);
+	spin_lock(&tdev->object_lock);
 	kref_init(&base->refcount);
 	ret = drm_ht_just_insert_please(&tdev->object_hash,
 					&base->hash,
 					(unsigned long)base, 31, 0, 0);
-	write_unlock(&tdev->object_lock);
+	spin_unlock(&tdev->object_lock);
 	if (unlikely(ret != 0))
 		goto out_err0;
 
@@ -186,30 +186,22 @@ static void ttm_release_base(struct kref *kref)
 	    container_of(kref, struct ttm_base_object, refcount);
 	struct ttm_object_device *tdev = base->tfile->tdev;
 
+	spin_lock(&tdev->object_lock);
 	(void)drm_ht_remove_item(&tdev->object_hash, &base->hash);
-	write_unlock(&tdev->object_lock);
+	spin_unlock(&tdev->object_lock);
 	if (base->refcount_release) {
 		ttm_object_file_unref(&base->tfile);
 		base->refcount_release(&base);
 	}
-	write_lock(&tdev->object_lock);
 }
 
 void ttm_base_object_unref(struct ttm_base_object **p_base)
 {
 	struct ttm_base_object *base = *p_base;
-	struct ttm_object_device *tdev = base->tfile->tdev;
 
 	*p_base = NULL;
 
-	/*
-	 * Need to take the lock here to avoid racing with
-	 * users trying to look up the object.
-	 */
-
-	write_lock(&tdev->object_lock);
 	kref_put(&base->refcount, ttm_release_base);
-	write_unlock(&tdev->object_lock);
 }
 EXPORT_SYMBOL(ttm_base_object_unref);
 
@@ -221,14 +213,14 @@ struct ttm_base_object *ttm_base_object_lookup(struct ttm_object_file *tfile,
 	struct drm_hash_item *hash;
 	int ret;
 
-	read_lock(&tdev->object_lock);
+	rcu_read_lock();
 	ret = drm_ht_find_item(&tdev->object_hash, key, &hash);
 
 	if (likely(ret == 0)) {
 		base = drm_hash_entry(hash, struct ttm_base_object, hash);
-		kref_get(&base->refcount);
+		ret = kref_get_unless_zero(&base->refcount) ? 0 : -EINVAL;
 	}
-	read_unlock(&tdev->object_lock);
+	rcu_read_unlock();
 
 	if (unlikely(ret != 0))
 		return NULL;
@@ -426,7 +418,7 @@ struct ttm_object_device *ttm_object_device_init(struct ttm_mem_global
 		return NULL;
 
 	tdev->mem_glob = mem_glob;
-	rwlock_init(&tdev->object_lock);
+	spin_lock_init(&tdev->object_lock);
 	atomic_set(&tdev->object_count, 0);
 	ret = drm_ht_create(&tdev->object_hash, hash_order);
 
@@ -444,9 +436,9 @@ void ttm_object_device_release(struct ttm_object_device **p_tdev)
 
 	*p_tdev = NULL;
 
-	write_lock(&tdev->object_lock);
+	spin_lock(&tdev->object_lock);
 	drm_ht_remove(&tdev->object_hash);
-	write_unlock(&tdev->object_lock);
+	spin_unlock(&tdev->object_lock);
 
 	kfree(tdev);
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 596cef3c9189..292c988c54ea 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -351,7 +351,7 @@ static void vmw_user_context_free(struct vmw_resource *res)
 	    container_of(res, struct vmw_user_context, res);
 	struct vmw_private *dev_priv = res->dev_priv;
 
-	kfree(ctx);
+	ttm_base_object_kfree(ctx, base);
 	ttm_mem_global_free(vmw_mem_glob(dev_priv),
 			    vmw_user_context_size);
 }
@@ -1143,7 +1143,7 @@ static void vmw_user_surface_free(struct vmw_resource *res)
 	kfree(srf->offsets);
 	kfree(srf->sizes);
 	kfree(srf->snooper.image);
-	kfree(user_srf);
+	ttm_base_object_kfree(user_srf, base);
 	ttm_mem_global_free(vmw_mem_glob(dev_priv), size);
 }
 
@@ -1571,7 +1571,7 @@ static void vmw_user_dmabuf_destroy(struct ttm_buffer_object *bo)
 {
 	struct vmw_user_dma_buffer *vmw_user_bo = vmw_user_dma_buffer(bo);
 
-	kfree(vmw_user_bo);
+	ttm_base_object_kfree(vmw_user_bo, base);
 }
 
 static void vmw_user_dmabuf_release(struct ttm_base_object **p_base)
@@ -1759,7 +1759,7 @@ static void vmw_user_stream_free(struct vmw_resource *res)
 	    container_of(res, struct vmw_user_stream, stream.res);
 	struct vmw_private *dev_priv = res->dev_priv;
 
-	kfree(stream);
+	ttm_base_object_kfree(stream, base);
 	ttm_mem_global_free(vmw_mem_glob(dev_priv),
 			    vmw_user_stream_size);
 }
diff --git a/include/drm/ttm/ttm_object.h b/include/drm/ttm/ttm_object.h
index b01c563b2751..fc0cf0649901 100644
--- a/include/drm/ttm/ttm_object.h
+++ b/include/drm/ttm/ttm_object.h
@@ -40,6 +40,7 @@
 #include <linux/list.h>
 #include <drm/drm_hashtab.h>
 #include <linux/kref.h>
+#include <linux/rcupdate.h>
 #include <ttm/ttm_memory.h>
 
 /**
@@ -120,6 +121,7 @@ struct ttm_object_device;
  */
 
 struct ttm_base_object {
+	struct rcu_head rhead;
 	struct drm_hash_item hash;
 	enum ttm_object_type object_type;
 	bool shareable;
@@ -268,4 +270,6 @@ extern struct ttm_object_device *ttm_object_device_init
 
 extern void ttm_object_device_release(struct ttm_object_device **p_tdev);
 
+#define ttm_base_object_kfree(__object, __base)\
+	kfree_rcu(__object, __base.rhead)
 #endif
-- 
cgit v1.2.3-55-g7522


From 654aa79259a19f0d5e3cf9cb20aff56dc3b041b7 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst
Date: Tue, 6 Nov 2012 14:39:43 +0100
Subject: drm/ttm: alter cpu_writers to return -EBUSY in ttm_execbuf_util
 reservations

This is similar to other platforms that don't allow command submission
to buffers locked on the cpu.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c           | 13 +------------
 drivers/gpu/drm/ttm/ttm_execbuf_util.c |  5 +----
 include/drm/ttm/ttm_bo_api.h           |  5 +++--
 include/drm/ttm/ttm_bo_driver.h        | 14 --------------
 4 files changed, 5 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 5f61f133b419..7426fe59108e 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1053,16 +1053,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_mem_space);
 
-int ttm_bo_wait_cpu(struct ttm_buffer_object *bo, bool no_wait)
-{
-	if ((atomic_read(&bo->cpu_writers) > 0) && no_wait)
-		return -EBUSY;
-
-	return wait_event_interruptible(bo->event_queue,
-					atomic_read(&bo->cpu_writers) == 0);
-}
-EXPORT_SYMBOL(ttm_bo_wait_cpu);
-
 int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 			struct ttm_placement *placement,
 			bool interruptible, bool no_wait_reserve,
@@ -1788,8 +1778,7 @@ EXPORT_SYMBOL(ttm_bo_synccpu_write_grab);
 
 void ttm_bo_synccpu_write_release(struct ttm_buffer_object *bo)
 {
-	if (atomic_dec_and_test(&bo->cpu_writers))
-		wake_up_all(&bo->event_queue);
+	atomic_dec(&bo->cpu_writers);
 }
 EXPORT_SYMBOL(ttm_bo_synccpu_write_release);
 
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index b227a9961a07..1986d006c264 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -185,10 +185,7 @@ retry_this_bo:
 			ttm_eu_backoff_reservation_locked(list);
 			spin_unlock(&glob->lru_lock);
 			ttm_eu_list_ref_sub(list);
-			ret = ttm_bo_wait_cpu(bo, false);
-			if (ret)
-				return ret;
-			goto retry;
+			return -EBUSY;
 		}
 	}
 
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 5ff938df5fce..c6cae733ddef 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -424,8 +424,9 @@ extern void ttm_bo_unlock_delayed_workqueue(struct ttm_bo_device *bdev,
  * @no_wait: Return immediately if buffer is busy.
  *
  * Synchronizes a buffer object for CPU RW access. This means
- * blocking command submission that affects the buffer and
- * waiting for buffer idle. This lock is recursive.
+ * command submission that affects the buffer will return -EBUSY
+ * until ttm_bo_synccpu_write_release is called.
+ *
  * Returns
  * -EBUSY if the buffer is busy and no_wait is true.
  * -ERESTARTSYS if interrupted by a signal.
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 4789beee3b77..dd96442cdc2a 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -726,20 +726,6 @@ extern void ttm_bo_mem_put(struct ttm_buffer_object *bo,
 extern void ttm_bo_mem_put_locked(struct ttm_buffer_object *bo,
 				  struct ttm_mem_reg *mem);
 
-/**
- * ttm_bo_wait_for_cpu
- *
- * @bo: Pointer to a struct ttm_buffer_object.
- * @no_wait: Don't sleep while waiting.
- *
- * Wait until a buffer object is no longer sync'ed for CPU access.
- * Returns:
- * -EBUSY: Buffer object was sync'ed for CPU access. (only if no_wait == 1).
- * -ERESTARTSYS: An interruptible sleep was interrupted by a signal.
- */
-
-extern int ttm_bo_wait_cpu(struct ttm_buffer_object *bo, bool no_wait);
-
 extern void ttm_bo_global_release(struct drm_global_reference *ref);
 extern int ttm_bo_global_init(struct drm_global_reference *ref);
 
-- 
cgit v1.2.3-55-g7522


From e09651fcc295a7dc802f38d9494f5b860dd90bca Mon Sep 17 00:00:00 2001
From: Nishanth Menon
Date: Mon, 29 Oct 2012 08:02:23 -0500
Subject: PM / devfreq: documentation cleanups for devfreq header

struct parameters need to have ':' in documentation for
scripts/kernel-doc to parse appropriately.

Fix the errors reported by:
./scripts/kernel-doc include/linux/devfreq.h >/dev/null

Cc: Rajagopal Venkat <rajagopal.venkat@linaro.org>
Cc: MyungJoo Ham <myungjoo.ham@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Kevin Hilman <khilman@ti.com>
Cc: linux-pm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org

Signed-off-by: Nishanth Menon <nm@ti.com>
Acked-by: Randy Dunlap <rdunlap@xenotime.net>
Acked-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 include/linux/devfreq.h | 54 ++++++++++++++++++++++++-------------------------
 1 file changed, 27 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 7e2e2ea4a70f..1461fb2355ad 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -25,12 +25,12 @@ struct devfreq;
  * struct devfreq_dev_status - Data given from devfreq user device to
  *			     governors. Represents the performance
  *			     statistics.
- * @total_time		The total time represented by this instance of
+ * @total_time:		The total time represented by this instance of
  *			devfreq_dev_status
- * @busy_time		The time that the device was working among the
+ * @busy_time:		The time that the device was working among the
  *			total_time.
- * @current_frequency	The operating frequency.
- * @private_data	An entry not specified by the devfreq framework.
+ * @current_frequency:	The operating frequency.
+ * @private_data:	An entry not specified by the devfreq framework.
  *			A device and a specific governor may have their
  *			own protocol with private_data. However, because
  *			this is governor-specific, a governor using this
@@ -54,21 +54,21 @@ struct devfreq_dev_status {
 
 /**
  * struct devfreq_dev_profile - Devfreq's user device profile
- * @initial_freq	The operating frequency when devfreq_add_device() is
+ * @initial_freq:	The operating frequency when devfreq_add_device() is
  *			called.
- * @polling_ms		The polling interval in ms. 0 disables polling.
- * @target		The device should set its operating frequency at
+ * @polling_ms:		The polling interval in ms. 0 disables polling.
+ * @target:		The device should set its operating frequency at
  *			freq or lowest-upper-than-freq value. If freq is
  *			higher than any operable frequency, set maximum.
  *			Before returning, target function should set
  *			freq at the current frequency.
  *			The "flags" parameter's possible values are
  *			explained above with "DEVFREQ_FLAG_*" macros.
- * @get_dev_status	The device should provide the current performance
+ * @get_dev_status:	The device should provide the current performance
  *			status to devfreq, which is used by governors.
- * @get_cur_freq	The device should provide the current frequency
+ * @get_cur_freq:	The device should provide the current frequency
  *			at which it is operating.
- * @exit		An optional callback that is called when devfreq
+ * @exit:		An optional callback that is called when devfreq
  *			is removing the devfreq object due to error or
  *			from devfreq_remove_device() call. If the user
  *			has registered devfreq->nb at a notifier-head,
@@ -87,14 +87,14 @@ struct devfreq_dev_profile {
 
 /**
  * struct devfreq_governor - Devfreq policy governor
- * @name		Governor's name
- * @get_target_freq	Returns desired operating frequency for the device.
+ * @name:		Governor's name
+ * @get_target_freq:	Returns desired operating frequency for the device.
  *			Basically, get_target_freq will run
  *			devfreq_dev_profile.get_dev_status() to get the
  *			status of the device (load = busy_time / total_time).
  *			If no_central_polling is set, this callback is called
  *			only with update_devfreq() notified by OPP.
- * @event_handler       Callback for devfreq core framework to notify events
+ * @event_handler:      Callback for devfreq core framework to notify events
  *                      to governors. Events include per device governor
  *                      init and exit, opp changes out of devfreq, suspend
  *                      and resume of per device devfreq during device idle.
@@ -110,23 +110,23 @@ struct devfreq_governor {
 
 /**
  * struct devfreq - Device devfreq structure
- * @node	list node - contains the devices with devfreq that have been
+ * @node:	list node - contains the devices with devfreq that have been
  *		registered.
- * @lock	a mutex to protect accessing devfreq.
- * @dev		device registered by devfreq class. dev.parent is the device
+ * @lock:	a mutex to protect accessing devfreq.
+ * @dev:	device registered by devfreq class. dev.parent is the device
  *		using devfreq.
- * @profile	device-specific devfreq profile
- * @governor	method how to choose frequency based on the usage.
- * @nb		notifier block used to notify devfreq object that it should
+ * @profile:	device-specific devfreq profile
+ * @governor:	method how to choose frequency based on the usage.
+ * @nb:		notifier block used to notify devfreq object that it should
  *		reevaluate operable frequencies. Devfreq users may use
  *		devfreq.nb to the corresponding register notifier call chain.
- * @work	delayed work for load monitoring.
- * @previous_freq	previously configured frequency value.
- * @data	Private data of the governor. The devfreq framework does not
+ * @work:	delayed work for load monitoring.
+ * @previous_freq:	previously configured frequency value.
+ * @data:	Private data of the governor. The devfreq framework does not
  *		touch this.
- * @min_freq	Limit minimum frequency requested by user (0: none)
- * @max_freq	Limit maximum frequency requested by user (0: none)
- * @stop_polling	 devfreq polling status of a device.
+ * @min_freq:	Limit minimum frequency requested by user (0: none)
+ * @max_freq:	Limit maximum frequency requested by user (0: none)
+ * @stop_polling:	 devfreq polling status of a device.
  *
  * This structure stores the devfreq information for a give device.
  *
@@ -186,9 +186,9 @@ extern const struct devfreq_governor devfreq_simple_ondemand;
 /**
  * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq
  *	and devfreq_add_device
- * @ upthreshold	If the load is over this value, the frequency jumps.
+ * @upthreshold:	If the load is over this value, the frequency jumps.
  *			Specify 0 to use the default. Valid value = 0 to 100.
- * @ downdifferential	If the load is under upthreshold - downdifferential,
+ * @downdifferential:	If the load is under upthreshold - downdifferential,
  *			the governor may consider slowing the frequency down.
  *			Specify 0 to use the default. Valid value = 0 to 100.
  *			downdifferential < upthreshold must hold.
-- 
cgit v1.2.3-55-g7522


From d851718f65d646c5033a28fa60631440c6dc0d4f Mon Sep 17 00:00:00 2001
From: Chanwoo Choi
Date: Thu, 8 Nov 2012 18:39:41 +0900
Subject: extcon: Add missing header file to extcon.h

This patch add missing header file(sysfs.h/device.h) to extcon.h
because 'struct extcon_dev' define attribute field(attr_g_muex/
attrs_muex/d_attrs_mues) and device_type field(extcon_dev_type).

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Myungjoo Ham <myungjoo.ham@samsung.com>
---
 include/linux/extcon.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/extcon.h b/include/linux/extcon.h
index 2c26c14cd710..54c00ce9ce7a 100644
--- a/include/linux/extcon.h
+++ b/include/linux/extcon.h
@@ -23,7 +23,9 @@
 #ifndef __LINUX_EXTCON_H__
 #define __LINUX_EXTCON_H__
 
+#include <linux/device.h>
 #include <linux/notifier.h>
+#include <linux/sysfs.h>
 
 #define SUPPORTED_CABLE_MAX	32
 #define CABLE_NAME_MAX		30
-- 
cgit v1.2.3-55-g7522


From e552bbaf5b987f57c43e6981a452b8a3c700b1ae Mon Sep 17 00:00:00 2001
From: Jonghwa Lee
Date: Thu, 23 Aug 2012 20:00:46 +0900
Subject: PM / devfreq: Add sysfs node for representing frequency transition
 information.

This patch adds sysfs node which can be used to get information of frequency
transition. It represents transition table which contains total number of transition of
each freqeuncy state and time spent. It is inspired CPUFREQ's status driver.

Signed-off-by: Jonghwa Lee <jonghwa3.lee@samsung.com>
[Added Documentation/ABI entry, updated kernel-doc, and resolved merge conflict]
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 Documentation/ABI/testing/sysfs-class-devfreq |  11 +++
 drivers/devfreq/devfreq.c                     | 101 ++++++++++++++++++++++++++
 include/linux/devfreq.h                       |  15 ++++
 3 files changed, 127 insertions(+)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
index e672ccb02e7f..40f98a9428dc 100644
--- a/Documentation/ABI/testing/sysfs-class-devfreq
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -44,6 +44,17 @@ Description:
 		(/sys/class/devfreq/.../central_polling is 0), this value
 		may be useless.
 
+What:		/sys/class/devfreq/.../trans_stat
+Date:		October 2012
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Descrtiption:
+		This ABI shows the statistics of devfreq behavior on a
+		specific device. It shows the time spent in each state and
+		the number of transitions between states.
+		In order to activate this ABI, the devfreq target device
+		driver should provide the list of available frequencies
+		with its profile.
+
 What:		/sys/class/devfreq/.../userspace/set_freq
 Date:		September 2011
 Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index c44e562bdfe0..bf6de38190cf 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -66,6 +66,51 @@ static struct devfreq *find_device_devfreq(struct device *dev)
 	return ERR_PTR(-ENODEV);
 }
 
+/**
+ * devfreq_get_freq_level() - Lookup freq_table for the frequency
+ * @devfreq:	the devfreq instance
+ * @freq:	the target frequency
+ */
+static int devfreq_get_freq_level(struct devfreq *devfreq, unsigned long freq)
+{
+	int lev;
+
+	for (lev = 0; lev < devfreq->profile->max_state; lev++)
+		if (freq == devfreq->profile->freq_table[lev])
+			return lev;
+
+	return -EINVAL;
+}
+
+/**
+ * devfreq_update_status() - Update statistics of devfreq behavior
+ * @devfreq:	the devfreq instance
+ * @freq:	the update target frequency
+ */
+static int devfreq_update_status(struct devfreq *devfreq, unsigned long freq)
+{
+	int lev, prev_lev;
+	unsigned long cur_time;
+
+	lev = devfreq_get_freq_level(devfreq, freq);
+	if (lev < 0)
+		return lev;
+
+	cur_time = jiffies;
+	devfreq->time_in_state[lev] +=
+			 cur_time - devfreq->last_stat_updated;
+	if (freq != devfreq->previous_freq) {
+		prev_lev = devfreq_get_freq_level(devfreq,
+						devfreq->previous_freq);
+		devfreq->trans_table[(prev_lev *
+				devfreq->profile->max_state) + lev]++;
+		devfreq->total_trans++;
+	}
+	devfreq->last_stat_updated = cur_time;
+
+	return 0;
+}
+
 /* Load monitoring helper functions for governors use */
 
 /**
@@ -112,6 +157,11 @@ int update_devfreq(struct devfreq *devfreq)
 	if (err)
 		return err;
 
+	if (devfreq->profile->freq_table)
+		if (devfreq_update_status(devfreq, freq))
+			dev_err(&devfreq->dev,
+				"Couldn't update frequency transition information.\n");
+
 	devfreq->previous_freq = freq;
 	return err;
 }
@@ -378,6 +428,15 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->data = data;
 	devfreq->nb.notifier_call = devfreq_notifier_call;
 
+	devfreq->trans_table =	devm_kzalloc(dev, sizeof(unsigned int) *
+						devfreq->profile->max_state *
+						devfreq->profile->max_state,
+						GFP_KERNEL);
+	devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned int) *
+						devfreq->profile->max_state,
+						GFP_KERNEL);
+	devfreq->last_stat_updated = jiffies;
+
 	dev_set_name(&devfreq->dev, dev_name(dev));
 	err = device_register(&devfreq->dev);
 	if (err) {
@@ -601,6 +660,47 @@ static ssize_t show_available_freqs(struct device *d,
 	return count;
 }
 
+static ssize_t show_trans_table(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct devfreq *devfreq = to_devfreq(dev);
+	ssize_t len;
+	int i, j, err;
+	unsigned int max_state = devfreq->profile->max_state;
+
+	err = devfreq_update_status(devfreq, devfreq->previous_freq);
+	if (err)
+		return 0;
+
+	len = sprintf(buf, "   From  :   To\n");
+	len += sprintf(buf + len, "         :");
+	for (i = 0; i < max_state; i++)
+		len += sprintf(buf + len, "%8u",
+				devfreq->profile->freq_table[i]);
+
+	len += sprintf(buf + len, "   time(ms)\n");
+
+	for (i = 0; i < max_state; i++) {
+		if (devfreq->profile->freq_table[i]
+					== devfreq->previous_freq) {
+			len += sprintf(buf + len, "*");
+		} else {
+			len += sprintf(buf + len, " ");
+		}
+		len += sprintf(buf + len, "%8u:",
+				devfreq->profile->freq_table[i]);
+		for (j = 0; j < max_state; j++)
+			len += sprintf(buf + len, "%8u",
+				devfreq->trans_table[(i * max_state) + j]);
+		len += sprintf(buf + len, "%10u\n",
+			jiffies_to_msecs(devfreq->time_in_state[i]));
+	}
+
+	len += sprintf(buf + len, "Total transition : %u\n",
+					devfreq->total_trans);
+	return len;
+}
+
 static struct device_attribute devfreq_attrs[] = {
 	__ATTR(governor, S_IRUGO, show_governor, NULL),
 	__ATTR(cur_freq, S_IRUGO, show_freq, NULL),
@@ -610,6 +710,7 @@ static struct device_attribute devfreq_attrs[] = {
 	       store_polling_interval),
 	__ATTR(min_freq, S_IRUGO | S_IWUSR, show_min_freq, store_min_freq),
 	__ATTR(max_freq, S_IRUGO | S_IWUSR, show_max_freq, store_max_freq),
+	__ATTR(trans_stat, S_IRUGO, show_trans_table, NULL),
 	{ },
 };
 
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 1461fb2355ad..bc35c4aee6a3 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -73,6 +73,8 @@ struct devfreq_dev_status {
  *			from devfreq_remove_device() call. If the user
  *			has registered devfreq->nb at a notifier-head,
  *			this is the time to unregister it.
+ * @freq_table:	Optional list of frequencies to support statistics.
+ * @max_state:	The size of freq_table.
  */
 struct devfreq_dev_profile {
 	unsigned long initial_freq;
@@ -83,6 +85,9 @@ struct devfreq_dev_profile {
 			      struct devfreq_dev_status *stat);
 	int (*get_cur_freq)(struct device *dev, unsigned long *freq);
 	void (*exit)(struct device *dev);
+
+	unsigned int *freq_table;
+	unsigned int max_state;
 };
 
 /**
@@ -127,6 +132,10 @@ struct devfreq_governor {
  * @min_freq:	Limit minimum frequency requested by user (0: none)
  * @max_freq:	Limit maximum frequency requested by user (0: none)
  * @stop_polling:	 devfreq polling status of a device.
+ * @total_trans:	Number of devfreq transitions
+ * @trans_table:	Statistics of devfreq transitions
+ * @time_in_state:	Statistics of devfreq states
+ * @last_stat_updated:	The last time stat updated
  *
  * This structure stores the devfreq information for a give device.
  *
@@ -153,6 +162,12 @@ struct devfreq {
 	unsigned long min_freq;
 	unsigned long max_freq;
 	bool stop_polling;
+
+	/* information for device freqeuncy transition */
+	unsigned int total_trans;
+	unsigned int *trans_table;
+	unsigned long *time_in_state;
+	unsigned long last_stat_updated;
 };
 
 #if defined(CONFIG_PM_DEVFREQ)
-- 
cgit v1.2.3-55-g7522


From 31974361761b18e07e821d3b262e34f1a2d105cb Mon Sep 17 00:00:00 2001
From: Nicolas Ferre
Date: Tue, 20 Nov 2012 16:38:17 +0800
Subject: ASoC: atmel-ssc: add phybase in device structure

Useful for future dmaengine use.

Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/misc/atmel-ssc.c  | 2 ++
 include/linux/atmel-ssc.h | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/drivers/misc/atmel-ssc.c b/drivers/misc/atmel-ssc.c
index a769719e36bf..d07a9eda7fff 100644
--- a/drivers/misc/atmel-ssc.c
+++ b/drivers/misc/atmel-ssc.c
@@ -157,6 +157,8 @@ static int ssc_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	ssc->phybase = regs->start;
+
 	ssc->clk = devm_clk_get(&pdev->dev, "pclk");
 	if (IS_ERR(ssc->clk)) {
 		dev_dbg(&pdev->dev, "no pclk clock defined\n");
diff --git a/include/linux/atmel-ssc.h b/include/linux/atmel-ssc.h
index 1ca0e3292bc9..deb0ae58b99b 100644
--- a/include/linux/atmel-ssc.h
+++ b/include/linux/atmel-ssc.h
@@ -11,6 +11,7 @@ struct atmel_ssc_platform_data {
 
 struct ssc_device {
 	struct list_head	list;
+	resource_size_t		phybase;
 	void __iomem		*regs;
 	struct platform_device	*pdev;
 	struct atmel_ssc_platform_data *pdata;
-- 
cgit v1.2.3-55-g7522


From 3aa173b8db200bb96354481acc0a5b9e123119fe Mon Sep 17 00:00:00 2001
From: Nishanth Menon
Date: Mon, 29 Oct 2012 15:01:43 -0500
Subject: PM / devfreq: provide hooks for governors to be registered

Add devfreq_add_governor and devfreq_remove_governor which
can be invoked by governors to register with devfreq.

This sets up the stage to dynamically switch governors and
allow governors to be dynamically loaded as well.

Cc: Rajagopal Venkat <rajagopal.venkat@linaro.org>
Cc: MyungJoo Ham <myungjoo.ham@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Kevin Hilman <khilman@ti.com>
Cc: linux-pm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org

Signed-off-by: Nishanth Menon <nm@ti.com>
Acked-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 drivers/devfreq/devfreq.c  | 91 ++++++++++++++++++++++++++++++++++++++++++++++
 drivers/devfreq/governor.h |  4 ++
 include/linux/devfreq.h    |  3 ++
 3 files changed, 98 insertions(+)

(limited to 'include')

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index e0002c5cbadc..679ac424472f 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -36,6 +36,8 @@ static struct class *devfreq_class;
  */
 static struct workqueue_struct *devfreq_wq;
 
+/* The list of all device-devfreq governors */
+static LIST_HEAD(devfreq_governor_list);
 /* The list of all device-devfreq */
 static LIST_HEAD(devfreq_list);
 static DEFINE_MUTEX(devfreq_list_lock);
@@ -111,6 +113,32 @@ static int devfreq_update_status(struct devfreq *devfreq, unsigned long freq)
 	return 0;
 }
 
+/**
+ * find_devfreq_governor() - find devfreq governor from name
+ * @name:	name of the governor
+ *
+ * Search the list of devfreq governors and return the matched
+ * governor's pointer. devfreq_list_lock should be held by the caller.
+ */
+static struct devfreq_governor *find_devfreq_governor(const char *name)
+{
+	struct devfreq_governor *tmp_governor;
+
+	if (unlikely(IS_ERR_OR_NULL(name))) {
+		pr_err("DEVFREQ: %s: Invalid parameters\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+	WARN(!mutex_is_locked(&devfreq_list_lock),
+	     "devfreq_list_lock must be locked.");
+
+	list_for_each_entry(tmp_governor, &devfreq_governor_list, node) {
+		if (!strncmp(tmp_governor->name, name, DEVFREQ_NAME_LEN))
+			return tmp_governor;
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
 /* Load monitoring helper functions for governors use */
 
 /**
@@ -515,6 +543,69 @@ int devfreq_resume_device(struct devfreq *devfreq)
 }
 EXPORT_SYMBOL(devfreq_resume_device);
 
+/**
+ * devfreq_add_governor() - Add devfreq governor
+ * @governor:	the devfreq governor to be added
+ */
+int devfreq_add_governor(struct devfreq_governor *governor)
+{
+	struct devfreq_governor *g;
+	int err = 0;
+
+	if (!governor) {
+		pr_err("%s: Invalid parameters.\n", __func__);
+		return -EINVAL;
+	}
+
+	mutex_lock(&devfreq_list_lock);
+	g = find_devfreq_governor(governor->name);
+	if (!IS_ERR(g)) {
+		pr_err("%s: governor %s already registered\n", __func__,
+		       g->name);
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	list_add(&governor->node, &devfreq_governor_list);
+
+err_out:
+	mutex_unlock(&devfreq_list_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(devfreq_add_governor);
+
+/**
+ * devfreq_remove_device() - Remove devfreq feature from a device.
+ * @governor:	the devfreq governor to be removed
+ */
+int devfreq_remove_governor(struct devfreq_governor *governor)
+{
+	struct devfreq_governor *g;
+	int err = 0;
+
+	if (!governor) {
+		pr_err("%s: Invalid parameters.\n", __func__);
+		return -EINVAL;
+	}
+
+	mutex_lock(&devfreq_list_lock);
+	g = find_devfreq_governor(governor->name);
+	if (IS_ERR(g)) {
+		pr_err("%s: governor %s not registered\n", __func__,
+		       g->name);
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	list_del(&governor->node);
+err_out:
+	mutex_unlock(&devfreq_list_lock);
+
+	return err;
+}
+EXPORT_SYMBOL(devfreq_remove_governor);
+
 static ssize_t show_governor(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index 26432ac0a398..fad7d6321978 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -34,4 +34,8 @@ extern void devfreq_monitor_suspend(struct devfreq *devfreq);
 extern void devfreq_monitor_resume(struct devfreq *devfreq);
 extern void devfreq_interval_update(struct devfreq *devfreq,
 					unsigned int *delay);
+
+extern int devfreq_add_governor(struct devfreq_governor *governor);
+extern int devfreq_remove_governor(struct devfreq_governor *governor);
+
 #endif /* _GOVERNOR_H */
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index bc35c4aee6a3..6484a3f8dda8 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -92,6 +92,7 @@ struct devfreq_dev_profile {
 
 /**
  * struct devfreq_governor - Devfreq policy governor
+ * @node:		list node - contains registered devfreq governors
  * @name:		Governor's name
  * @get_target_freq:	Returns desired operating frequency for the device.
  *			Basically, get_target_freq will run
@@ -107,6 +108,8 @@ struct devfreq_dev_profile {
  * Note that the callbacks are called with devfreq->lock locked by devfreq.
  */
 struct devfreq_governor {
+	struct list_head node;
+
 	const char name[DEVFREQ_NAME_LEN];
 	int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
 	int (*event_handler)(struct devfreq *devfreq,
-- 
cgit v1.2.3-55-g7522


From 1b5c1be2c88e8445a20fa1929e26c37e7ca8c926 Mon Sep 17 00:00:00 2001
From: Nishanth Menon
Date: Mon, 29 Oct 2012 15:01:45 -0500
Subject: PM / devfreq: map devfreq drivers to governor using name

Allow devfreq drivers to register a preferred governor name
and when the devfreq governor loads itself at a later point
required drivers are managed appropriately, at the time of
unload of a devfreq governor, stop managing those drivers
as well.

Since the governor structures do not need to be exposed
anymore, remove the definitions and make them static

NOTE: devfreq_list_lock is now used to protect governor
start and stop - as this allows us to protect governors and
devfreq with the proper dependencies as needed.

As part of this change, change the registration of exynos
bus driver to request for ondemand using the governor name.

Cc: Rajagopal Venkat <rajagopal.venkat@linaro.org>
Cc: MyungJoo Ham <myungjoo.ham@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Kevin Hilman <khilman@ti.com>
Cc: linux-pm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org

Signed-off-by: Nishanth Menon <nm@ti.com>
[Merge conflict resolved by MyungJoo Ham]
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 drivers/devfreq/devfreq.c                 | 95 ++++++++++++++++++++++++++++---
 drivers/devfreq/exynos4_bus.c             |  2 +-
 drivers/devfreq/governor_performance.c    |  2 +-
 drivers/devfreq/governor_powersave.c      |  2 +-
 drivers/devfreq/governor_simpleondemand.c |  2 +-
 drivers/devfreq/governor_userspace.c      |  2 +-
 include/linux/devfreq.h                   | 21 ++-----
 7 files changed, 96 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 679ac424472f..0d7be03d561f 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -159,6 +159,9 @@ int update_devfreq(struct devfreq *devfreq)
 		return -EINVAL;
 	}
 
+	if (!devfreq->governor)
+		return -EINVAL;
+
 	/* Reevaluate the proper frequency */
 	err = devfreq->governor->get_target_freq(devfreq, &freq);
 	if (err)
@@ -379,7 +382,9 @@ static void _remove_devfreq(struct devfreq *devfreq, bool skip)
 	list_del(&devfreq->node);
 	mutex_unlock(&devfreq_list_lock);
 
-	devfreq->governor->event_handler(devfreq, DEVFREQ_GOV_STOP, NULL);
+	if (devfreq->governor)
+		devfreq->governor->event_handler(devfreq,
+						 DEVFREQ_GOV_STOP, NULL);
 
 	if (devfreq->profile->exit)
 		devfreq->profile->exit(devfreq->dev.parent);
@@ -412,19 +417,20 @@ static void devfreq_dev_release(struct device *dev)
  * devfreq_add_device() - Add devfreq feature to the device
  * @dev:	the device to add devfreq feature.
  * @profile:	device-specific profile to run devfreq.
- * @governor:	the policy to choose frequency.
+ * @governor_name:	name of the policy to choose frequency.
  * @data:	private data for the governor. The devfreq framework does not
  *		touch this value.
  */
 struct devfreq *devfreq_add_device(struct device *dev,
 				   struct devfreq_dev_profile *profile,
-				   const struct devfreq_governor *governor,
+				   const char *governor_name,
 				   void *data)
 {
 	struct devfreq *devfreq;
+	struct devfreq_governor *governor;
 	int err = 0;
 
-	if (!dev || !profile || !governor) {
+	if (!dev || !profile || !governor_name) {
 		dev_err(dev, "%s: Invalid parameters.\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
@@ -452,7 +458,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->dev.class = devfreq_class;
 	devfreq->dev.release = devfreq_dev_release;
 	devfreq->profile = profile;
-	devfreq->governor = governor;
+	strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN);
 	devfreq->previous_freq = profile->initial_freq;
 	devfreq->data = data;
 	devfreq->nb.notifier_call = devfreq_notifier_call;
@@ -478,10 +484,14 @@ struct devfreq *devfreq_add_device(struct device *dev,
 
 	mutex_lock(&devfreq_list_lock);
 	list_add(&devfreq->node, &devfreq_list);
-	mutex_unlock(&devfreq_list_lock);
 
-	err = devfreq->governor->event_handler(devfreq,
-				DEVFREQ_GOV_START, NULL);
+	governor = find_devfreq_governor(devfreq->governor_name);
+	if (!IS_ERR(governor))
+		devfreq->governor = governor;
+	if (devfreq->governor)
+		err = devfreq->governor->event_handler(devfreq,
+					DEVFREQ_GOV_START, NULL);
+	mutex_unlock(&devfreq_list_lock);
 	if (err) {
 		dev_err(dev, "%s: Unable to start governor for the device\n",
 			__func__);
@@ -524,6 +534,9 @@ int devfreq_suspend_device(struct devfreq *devfreq)
 	if (!devfreq)
 		return -EINVAL;
 
+	if (!devfreq->governor)
+		return 0;
+
 	return devfreq->governor->event_handler(devfreq,
 				DEVFREQ_GOV_SUSPEND, NULL);
 }
@@ -538,6 +551,9 @@ int devfreq_resume_device(struct devfreq *devfreq)
 	if (!devfreq)
 		return -EINVAL;
 
+	if (!devfreq->governor)
+		return 0;
+
 	return devfreq->governor->event_handler(devfreq,
 				DEVFREQ_GOV_RESUME, NULL);
 }
@@ -550,6 +566,7 @@ EXPORT_SYMBOL(devfreq_resume_device);
 int devfreq_add_governor(struct devfreq_governor *governor)
 {
 	struct devfreq_governor *g;
+	struct devfreq *devfreq;
 	int err = 0;
 
 	if (!governor) {
@@ -568,6 +585,38 @@ int devfreq_add_governor(struct devfreq_governor *governor)
 
 	list_add(&governor->node, &devfreq_governor_list);
 
+	list_for_each_entry(devfreq, &devfreq_list, node) {
+		int ret = 0;
+		struct device *dev = devfreq->dev.parent;
+
+		if (!strncmp(devfreq->governor_name, governor->name,
+			     DEVFREQ_NAME_LEN)) {
+			/* The following should never occur */
+			if (devfreq->governor) {
+				dev_warn(dev,
+					 "%s: Governor %s already present\n",
+					 __func__, devfreq->governor->name);
+				ret = devfreq->governor->event_handler(devfreq,
+							DEVFREQ_GOV_STOP, NULL);
+				if (ret) {
+					dev_warn(dev,
+						 "%s: Governor %s stop = %d\n",
+						 __func__,
+						 devfreq->governor->name, ret);
+				}
+				/* Fall through */
+			}
+			devfreq->governor = governor;
+			ret = devfreq->governor->event_handler(devfreq,
+						DEVFREQ_GOV_START, NULL);
+			if (ret) {
+				dev_warn(dev, "%s: Governor %s start=%d\n",
+					 __func__, devfreq->governor->name,
+					 ret);
+			}
+		}
+	}
+
 err_out:
 	mutex_unlock(&devfreq_list_lock);
 
@@ -582,6 +631,7 @@ EXPORT_SYMBOL(devfreq_add_governor);
 int devfreq_remove_governor(struct devfreq_governor *governor)
 {
 	struct devfreq_governor *g;
+	struct devfreq *devfreq;
 	int err = 0;
 
 	if (!governor) {
@@ -597,6 +647,29 @@ int devfreq_remove_governor(struct devfreq_governor *governor)
 		err = -EINVAL;
 		goto err_out;
 	}
+	list_for_each_entry(devfreq, &devfreq_list, node) {
+		int ret;
+		struct device *dev = devfreq->dev.parent;
+
+		if (!strncmp(devfreq->governor_name, governor->name,
+			     DEVFREQ_NAME_LEN)) {
+			/* we should have a devfreq governor! */
+			if (!devfreq->governor) {
+				dev_warn(dev, "%s: Governor %s NOT present\n",
+					 __func__, governor->name);
+				continue;
+				/* Fall through */
+			}
+			ret = devfreq->governor->event_handler(devfreq,
+						DEVFREQ_GOV_STOP, NULL);
+			if (ret) {
+				dev_warn(dev, "%s: Governor %s stop=%d\n",
+					 __func__, devfreq->governor->name,
+					 ret);
+			}
+			devfreq->governor = NULL;
+		}
+	}
 
 	list_del(&governor->node);
 err_out:
@@ -609,6 +682,9 @@ EXPORT_SYMBOL(devfreq_remove_governor);
 static ssize_t show_governor(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
+	if (!to_devfreq(dev)->governor)
+		return -EINVAL;
+
 	return sprintf(buf, "%s\n", to_devfreq(dev)->governor->name);
 }
 
@@ -645,6 +721,9 @@ static ssize_t store_polling_interval(struct device *dev,
 	unsigned int value;
 	int ret;
 
+	if (!df->governor)
+		return -EINVAL;
+
 	ret = sscanf(buf, "%u", &value);
 	if (ret != 1)
 		return -EINVAL;
diff --git a/drivers/devfreq/exynos4_bus.c b/drivers/devfreq/exynos4_bus.c
index 68145316c49c..b8ac28497b37 100644
--- a/drivers/devfreq/exynos4_bus.c
+++ b/drivers/devfreq/exynos4_bus.c
@@ -1040,7 +1040,7 @@ static __devinit int exynos4_busfreq_probe(struct platform_device *pdev)
 	busfreq_mon_reset(data);
 
 	data->devfreq = devfreq_add_device(dev, &exynos4_devfreq_profile,
-					   &devfreq_simple_ondemand, NULL);
+					   "simple_ondemand", NULL);
 	if (IS_ERR(data->devfreq))
 		return PTR_ERR(data->devfreq);
 
diff --git a/drivers/devfreq/governor_performance.c b/drivers/devfreq/governor_performance.c
index db8ff77dbed2..865a36956917 100644
--- a/drivers/devfreq/governor_performance.c
+++ b/drivers/devfreq/governor_performance.c
@@ -40,7 +40,7 @@ static int devfreq_performance_handler(struct devfreq *devfreq,
 	return ret;
 }
 
-const struct devfreq_governor devfreq_performance = {
+static struct devfreq_governor devfreq_performance = {
 	.name = "performance",
 	.get_target_freq = devfreq_performance_func,
 	.event_handler = devfreq_performance_handler,
diff --git a/drivers/devfreq/governor_powersave.c b/drivers/devfreq/governor_powersave.c
index 30f0fca8d635..8612c0f96b79 100644
--- a/drivers/devfreq/governor_powersave.c
+++ b/drivers/devfreq/governor_powersave.c
@@ -37,7 +37,7 @@ static int devfreq_powersave_handler(struct devfreq *devfreq,
 	return ret;
 }
 
-const struct devfreq_governor devfreq_powersave = {
+static struct devfreq_governor devfreq_powersave = {
 	.name = "powersave",
 	.get_target_freq = devfreq_powersave_func,
 	.event_handler = devfreq_powersave_handler,
diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c
index 85f9ed531b1e..a870a24bb56b 100644
--- a/drivers/devfreq/governor_simpleondemand.c
+++ b/drivers/devfreq/governor_simpleondemand.c
@@ -120,7 +120,7 @@ static int devfreq_simple_ondemand_handler(struct devfreq *devfreq,
 	return 0;
 }
 
-const struct devfreq_governor devfreq_simple_ondemand = {
+static struct devfreq_governor devfreq_simple_ondemand = {
 	.name = "simple_ondemand",
 	.get_target_freq = devfreq_simple_ondemand_func,
 	.event_handler = devfreq_simple_ondemand_handler,
diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c
index 110f178fec04..34fb80f50cf6 100644
--- a/drivers/devfreq/governor_userspace.c
+++ b/drivers/devfreq/governor_userspace.c
@@ -135,7 +135,7 @@ static int devfreq_userspace_handler(struct devfreq *devfreq,
 	return ret;
 }
 
-const struct devfreq_governor devfreq_userspace = {
+static struct devfreq_governor devfreq_userspace = {
 	.name = "userspace",
 	.get_target_freq = devfreq_userspace_func,
 	.event_handler = devfreq_userspace_handler,
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 6484a3f8dda8..235248cb2c93 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -125,6 +125,7 @@ struct devfreq_governor {
  *		using devfreq.
  * @profile:	device-specific devfreq profile
  * @governor:	method how to choose frequency based on the usage.
+ * @governor_name:	devfreq governor name for use with this devfreq
  * @nb:		notifier block used to notify devfreq object that it should
  *		reevaluate operable frequencies. Devfreq users may use
  *		devfreq.nb to the corresponding register notifier call chain.
@@ -155,6 +156,7 @@ struct devfreq {
 	struct device dev;
 	struct devfreq_dev_profile *profile;
 	const struct devfreq_governor *governor;
+	char governor_name[DEVFREQ_NAME_LEN];
 	struct notifier_block nb;
 	struct delayed_work work;
 
@@ -176,7 +178,7 @@ struct devfreq {
 #if defined(CONFIG_PM_DEVFREQ)
 extern struct devfreq *devfreq_add_device(struct device *dev,
 				  struct devfreq_dev_profile *profile,
-				  const struct devfreq_governor *governor,
+				  const char *governor_name,
 				  void *data);
 extern int devfreq_remove_device(struct devfreq *devfreq);
 extern int devfreq_suspend_device(struct devfreq *devfreq);
@@ -190,17 +192,7 @@ extern int devfreq_register_opp_notifier(struct device *dev,
 extern int devfreq_unregister_opp_notifier(struct device *dev,
 					   struct devfreq *devfreq);
 
-#ifdef CONFIG_DEVFREQ_GOV_POWERSAVE
-extern const struct devfreq_governor devfreq_powersave;
-#endif
-#ifdef CONFIG_DEVFREQ_GOV_PERFORMANCE
-extern const struct devfreq_governor devfreq_performance;
-#endif
-#ifdef CONFIG_DEVFREQ_GOV_USERSPACE
-extern const struct devfreq_governor devfreq_userspace;
-#endif
 #ifdef CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND
-extern const struct devfreq_governor devfreq_simple_ondemand;
 /**
  * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq
  *	and devfreq_add_device
@@ -223,7 +215,7 @@ struct devfreq_simple_ondemand_data {
 #else /* !CONFIG_PM_DEVFREQ */
 static struct devfreq *devfreq_add_device(struct device *dev,
 					  struct devfreq_dev_profile *profile,
-					  struct devfreq_governor *governor,
+					  const char *governor_name,
 					  void *data)
 {
 	return NULL;
@@ -262,11 +254,6 @@ static int devfreq_unregister_opp_notifier(struct device *dev,
 	return -EINVAL;
 }
 
-#define devfreq_powersave	NULL
-#define devfreq_performance	NULL
-#define devfreq_userspace	NULL
-#define devfreq_simple_ondemand	NULL
-
 #endif /* CONFIG_PM_DEVFREQ */
 
 #endif /* __LINUX_DEVFREQ_H__ */
-- 
cgit v1.2.3-55-g7522


From 43c1af0f4861b721def8c67ed6af2a69a4efcca3 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 13 Nov 2012 19:33:57 +0530
Subject: mfd: tps65910: Use regmap irq framework for interrupt support

Implement irq support of tps65910 with regmap irq framework
in place of implementing locally.
This reduces the code size significantly and easy to maintain.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/tps65910-irq.c   | 375 +++++++++++++++++++++----------------------
 include/linux/mfd/tps65910.h | 139 +++++++++++-----
 2 files changed, 278 insertions(+), 236 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/tps65910-irq.c b/drivers/mfd/tps65910-irq.c
index 09aab3e4776d..554543a584a1 100644
--- a/drivers/mfd/tps65910-irq.c
+++ b/drivers/mfd/tps65910-irq.c
@@ -24,171 +24,184 @@
 #include <linux/gpio.h>
 #include <linux/mfd/tps65910.h>
 
-/*
- * This is a threaded IRQ handler so can access I2C/SPI.  Since all
- * interrupts are clear on read the IRQ line will be reasserted and
- * the physical IRQ will be handled again if another interrupt is
- * asserted while we run - in the normal course of events this is a
- * rare occurrence so we save I2C/SPI reads.  We're also assuming that
- * it's rare to get lots of interrupts firing simultaneously so try to
- * minimise I/O.
- */
-static irqreturn_t tps65910_irq(int irq, void *irq_data)
-{
-	struct tps65910 *tps65910 = irq_data;
-	unsigned int reg;
-	u32 irq_sts;
-	u32 irq_mask;
-	int i;
-
-	tps65910_reg_read(tps65910, TPS65910_INT_STS, &reg);
-	irq_sts = reg;
-	tps65910_reg_read(tps65910, TPS65910_INT_STS2, &reg);
-	irq_sts |= reg << 8;
-	switch (tps65910_chip_id(tps65910)) {
-	case TPS65911:
-		tps65910_reg_read(tps65910, TPS65910_INT_STS3, &reg);
-		irq_sts |= reg << 16;
-	}
-
-	tps65910_reg_read(tps65910, TPS65910_INT_MSK, &reg);
-	irq_mask = reg;
-	tps65910_reg_read(tps65910, TPS65910_INT_MSK2, &reg);
-	irq_mask |= reg << 8;
-	switch (tps65910_chip_id(tps65910)) {
-	case TPS65911:
-		tps65910_reg_read(tps65910, TPS65910_INT_MSK3, &reg);
-		irq_mask |= reg << 16;
-	}
-
-	irq_sts &= ~irq_mask;
-
-	if (!irq_sts)
-		return IRQ_NONE;
-
-	for (i = 0; i < tps65910->irq_num; i++) {
-
-		if (!(irq_sts & (1 << i)))
-			continue;
-
-		handle_nested_irq(irq_find_mapping(tps65910->domain, i));
-	}
-
-	/* Write the STS register back to clear IRQs we handled */
-	reg = irq_sts & 0xFF;
-	irq_sts >>= 8;
-	tps65910_reg_write(tps65910, TPS65910_INT_STS, reg);
-	reg = irq_sts & 0xFF;
-	tps65910_reg_write(tps65910, TPS65910_INT_STS2, reg);
-	switch (tps65910_chip_id(tps65910)) {
-	case TPS65911:
-		reg = irq_sts >> 8;
-		tps65910_reg_write(tps65910, TPS65910_INT_STS3, reg);
-	}
-
-	return IRQ_HANDLED;
-}
-
-static void tps65910_irq_lock(struct irq_data *data)
-{
-	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
-
-	mutex_lock(&tps65910->irq_lock);
-}
-
-static void tps65910_irq_sync_unlock(struct irq_data *data)
-{
-	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
-	u32 reg_mask;
-	unsigned int reg;
-
-	tps65910_reg_read(tps65910, TPS65910_INT_MSK, &reg);
-	reg_mask = reg;
-	tps65910_reg_read(tps65910, TPS65910_INT_MSK2, &reg);
-	reg_mask |= reg << 8;
-	switch (tps65910_chip_id(tps65910)) {
-	case TPS65911:
-		tps65910_reg_read(tps65910, TPS65910_INT_MSK3, &reg);
-		reg_mask |= reg << 16;
-	}
 
-	if (tps65910->irq_mask != reg_mask) {
-		reg = tps65910->irq_mask & 0xFF;
-		tps65910_reg_write(tps65910, TPS65910_INT_MSK, reg);
-		reg = tps65910->irq_mask >> 8 & 0xFF;
-		tps65910_reg_write(tps65910, TPS65910_INT_MSK2, reg);
-		switch (tps65910_chip_id(tps65910)) {
-		case TPS65911:
-			reg = tps65910->irq_mask >> 16;
-			tps65910_reg_write(tps65910, TPS65910_INT_MSK3, reg);
-		}
-	}
-	mutex_unlock(&tps65910->irq_lock);
-}
-
-static void tps65910_irq_enable(struct irq_data *data)
-{
-	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
-
-	tps65910->irq_mask &= ~(1 << data->hwirq);
-}
-
-static void tps65910_irq_disable(struct irq_data *data)
-{
-	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
-
-	tps65910->irq_mask |= (1 << data->hwirq);
-}
+static const struct regmap_irq tps65911_irqs[] = {
+	/* INT_STS */
+	[TPS65911_IRQ_PWRHOLD_F] = {
+		.mask = INT_MSK_PWRHOLD_F_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_VBAT_VMHI] = {
+		.mask = INT_MSK_VMBHI_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_PWRON] = {
+		.mask = INT_MSK_PWRON_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_PWRON_LP] = {
+		.mask = INT_MSK_PWRON_LP_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_PWRHOLD_R] = {
+		.mask = INT_MSK_PWRHOLD_R_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_HOTDIE] = {
+		.mask = INT_MSK_HOTDIE_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_RTC_ALARM] = {
+		.mask = INT_MSK_RTC_ALARM_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_RTC_PERIOD] = {
+		.mask = INT_MSK_RTC_PERIOD_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+
+	/* INT_STS2 */
+	[TPS65911_IRQ_GPIO0_R] = {
+		.mask = INT_MSK2_GPIO0_R_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO0_F] = {
+		.mask = INT_MSK2_GPIO0_F_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO1_R] = {
+		.mask = INT_MSK2_GPIO1_R_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO1_F] = {
+		.mask = INT_MSK2_GPIO1_F_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO2_R] = {
+		.mask = INT_MSK2_GPIO2_R_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO2_F] = {
+		.mask = INT_MSK2_GPIO2_F_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO3_R] = {
+		.mask = INT_MSK2_GPIO3_R_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO3_F] = {
+		.mask = INT_MSK2_GPIO3_F_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+
+	/* INT_STS3 */
+	[TPS65911_IRQ_GPIO4_R] = {
+		.mask = INT_MSK3_GPIO4_R_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_GPIO4_F] = {
+		.mask = INT_MSK3_GPIO4_F_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_GPIO5_R] = {
+		.mask = INT_MSK3_GPIO5_R_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_GPIO5_F] = {
+		.mask = INT_MSK3_GPIO5_F_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_WTCHDG] = {
+		.mask = INT_MSK3_WTCHDG_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_VMBCH2_H] = {
+		.mask = INT_MSK3_VMBCH2_H_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_VMBCH2_L] = {
+		.mask = INT_MSK3_VMBCH2_L_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_PWRDN] = {
+		.mask = INT_MSK3_PWRDN_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+};
 
-#ifdef CONFIG_PM_SLEEP
-static int tps65910_irq_set_wake(struct irq_data *data, unsigned int enable)
-{
-	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
-	return irq_set_irq_wake(tps65910->chip_irq, enable);
-}
-#else
-#define tps65910_irq_set_wake NULL
-#endif
+static const struct regmap_irq tps65910_irqs[] = {
+	/* INT_STS */
+	[TPS65910_IRQ_VBAT_VMBDCH] = {
+		.mask = TPS65910_INT_MSK_VMBDCH_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_VBAT_VMHI] = {
+		.mask = TPS65910_INT_MSK_VMBHI_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_PWRON] = {
+		.mask = TPS65910_INT_MSK_PWRON_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_PWRON_LP] = {
+		.mask = TPS65910_INT_MSK_PWRON_LP_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_PWRHOLD] = {
+		.mask = TPS65910_INT_MSK_PWRHOLD_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_HOTDIE] = {
+		.mask = TPS65910_INT_MSK_HOTDIE_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_RTC_ALARM] = {
+		.mask = TPS65910_INT_MSK_RTC_ALARM_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_RTC_PERIOD] = {
+		.mask = TPS65910_INT_MSK_RTC_PERIOD_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+
+	/* INT_STS2 */
+	[TPS65910_IRQ_GPIO_R] = {
+		.mask = TPS65910_INT_MSK2_GPIO0_F_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65910_IRQ_GPIO_F] = {
+		.mask = TPS65910_INT_MSK2_GPIO0_R_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+};
 
-static struct irq_chip tps65910_irq_chip = {
+static struct regmap_irq_chip tps65911_irq_chip = {
 	.name = "tps65910",
-	.irq_bus_lock = tps65910_irq_lock,
-	.irq_bus_sync_unlock = tps65910_irq_sync_unlock,
-	.irq_disable = tps65910_irq_disable,
-	.irq_enable = tps65910_irq_enable,
-	.irq_set_wake = tps65910_irq_set_wake,
+	.irqs = tps65911_irqs,
+	.num_irqs = ARRAY_SIZE(tps65911_irqs),
+	.num_regs = 3,
+	.irq_reg_stride = 2,
+	.status_base = TPS65910_INT_STS,
+	.mask_base = TPS65910_INT_MSK,
+	.ack_base = TPS65910_INT_MSK,
 };
 
-static int tps65910_irq_map(struct irq_domain *h, unsigned int virq,
-				irq_hw_number_t hw)
-{
-	struct tps65910 *tps65910 = h->host_data;
-
-	irq_set_chip_data(virq, tps65910);
-	irq_set_chip_and_handler(virq, &tps65910_irq_chip, handle_edge_irq);
-	irq_set_nested_thread(virq, 1);
-
-	/* ARM needs us to explicitly flag the IRQ as valid
-	 * and will set them noprobe when we do so. */
-#ifdef CONFIG_ARM
-	set_irq_flags(virq, IRQF_VALID);
-#else
-	irq_set_noprobe(virq);
-#endif
-
-	return 0;
-}
-
-static struct irq_domain_ops tps65910_domain_ops = {
-	.map	= tps65910_irq_map,
-	.xlate	= irq_domain_xlate_twocell,
+static struct regmap_irq_chip tps65910_irq_chip = {
+	.name = "tps65910",
+	.irqs = tps65910_irqs,
+	.num_irqs = ARRAY_SIZE(tps65910_irqs),
+	.num_regs = 2,
+	.irq_reg_stride = 2,
+	.status_base = TPS65910_INT_STS,
+	.mask_base = TPS65910_INT_MSK,
+	.ack_base = TPS65910_INT_MSK,
 };
 
 int tps65910_irq_init(struct tps65910 *tps65910, int irq,
 		    struct tps65910_platform_data *pdata)
 {
-	int ret;
-	int flags = IRQF_ONESHOT;
+	int ret = 0;
+	static struct regmap_irq_chip *tps6591x_irqs_chip;
 
 	if (!irq) {
 		dev_warn(tps65910->dev, "No interrupt support, no core IRQ\n");
@@ -200,61 +213,31 @@ int tps65910_irq_init(struct tps65910 *tps65910, int irq,
 		return -EINVAL;
 	}
 
+
 	switch (tps65910_chip_id(tps65910)) {
 	case TPS65910:
-		tps65910->irq_num = TPS65910_NUM_IRQ;
+		tps6591x_irqs_chip = &tps65910_irq_chip;
 		break;
 	case TPS65911:
-		tps65910->irq_num = TPS65911_NUM_IRQ;
+		tps6591x_irqs_chip = &tps65911_irq_chip;
 		break;
 	}
 
-	if (pdata->irq_base > 0) {
-		pdata->irq_base = irq_alloc_descs(pdata->irq_base, 0,
-					tps65910->irq_num, -1);
-		if (pdata->irq_base < 0) {
-			dev_warn(tps65910->dev, "Failed to alloc IRQs: %d\n",
-					pdata->irq_base);
-			return pdata->irq_base;
-		}
-	}
-
-	tps65910->irq_mask = 0xFFFFFF;
-
-	mutex_init(&tps65910->irq_lock);
 	tps65910->chip_irq = irq;
-	tps65910->irq_base = pdata->irq_base;
-
-	if (pdata->irq_base > 0)
-		tps65910->domain = irq_domain_add_legacy(tps65910->dev->of_node,
-					tps65910->irq_num,
-					pdata->irq_base,
-					0,
-					&tps65910_domain_ops, tps65910);
-	else
-		tps65910->domain = irq_domain_add_linear(tps65910->dev->of_node,
-					tps65910->irq_num,
-					&tps65910_domain_ops, tps65910);
-
-	if (!tps65910->domain) {
-		dev_err(tps65910->dev, "Failed to create IRQ domain\n");
-		return -ENOMEM;
+	ret = regmap_add_irq_chip(tps65910->regmap, tps65910->chip_irq,
+		IRQF_ONESHOT, pdata->irq_base,
+		tps6591x_irqs_chip, &tps65910->irq_data);
+	if (ret < 0) {
+		dev_warn(tps65910->dev,
+				"Failed to add irq_chip %d\n", ret);
+		return ret;
 	}
-
-	ret = request_threaded_irq(irq, NULL, tps65910_irq, flags,
-				   "tps65910", tps65910);
-
-	irq_set_irq_type(irq, IRQ_TYPE_LEVEL_LOW);
-
-	if (ret != 0)
-		dev_err(tps65910->dev, "Failed to request IRQ: %d\n", ret);
-
 	return ret;
 }
 
 int tps65910_irq_exit(struct tps65910 *tps65910)
 {
-	if (tps65910->chip_irq)
-		free_irq(tps65910->chip_irq, tps65910);
+	if (tps65910->chip_irq > 0)
+		regmap_del_irq_chip(tps65910->chip_irq, tps65910->irq_data);
 	return 0;
 }
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index 02e894f3ff45..b564ac29590a 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -572,6 +572,49 @@
 #define SPARE_SPARE_MASK				0xFF
 #define SPARE_SPARE_SHIFT				0
 
+#define TPS65910_INT_STS_RTC_PERIOD_IT_MASK			0x80
+#define TPS65910_INT_STS_RTC_PERIOD_IT_SHIFT			7
+#define TPS65910_INT_STS_RTC_ALARM_IT_MASK			0x40
+#define TPS65910_INT_STS_RTC_ALARM_IT_SHIFT			6
+#define TPS65910_INT_STS_HOTDIE_IT_MASK				0x20
+#define TPS65910_INT_STS_HOTDIE_IT_SHIFT			5
+#define TPS65910_INT_STS_PWRHOLD_F_IT_MASK			0x10
+#define TPS65910_INT_STS_PWRHOLD_F_IT_SHIFT			4
+#define TPS65910_INT_STS_PWRON_LP_IT_MASK			0x08
+#define TPS65910_INT_STS_PWRON_LP_IT_SHIFT			3
+#define TPS65910_INT_STS_PWRON_IT_MASK				0x04
+#define TPS65910_INT_STS_PWRON_IT_SHIFT				2
+#define TPS65910_INT_STS_VMBHI_IT_MASK				0x02
+#define TPS65910_INT_STS_VMBHI_IT_SHIFT				1
+#define TPS65910_INT_STS_VMBDCH_IT_MASK				0x01
+#define TPS65910_INT_STS_VMBDCH_IT_SHIFT			0
+
+#define TPS65910_INT_MSK_RTC_PERIOD_IT_MSK_MASK			0x80
+#define TPS65910_INT_MSK_RTC_PERIOD_IT_MSK_SHIFT		7
+#define TPS65910_INT_MSK_RTC_ALARM_IT_MSK_MASK			0x40
+#define TPS65910_INT_MSK_RTC_ALARM_IT_MSK_SHIFT			6
+#define TPS65910_INT_MSK_HOTDIE_IT_MSK_MASK			0x20
+#define TPS65910_INT_MSK_HOTDIE_IT_MSK_SHIFT			5
+#define TPS65910_INT_MSK_PWRHOLD_IT_MSK_MASK			0x10
+#define TPS65910_INT_MSK_PWRHOLD_IT_MSK_SHIFT			4
+#define TPS65910_INT_MSK_PWRON_LP_IT_MSK_MASK			0x08
+#define TPS65910_INT_MSK_PWRON_LP_IT_MSK_SHIFT			3
+#define TPS65910_INT_MSK_PWRON_IT_MSK_MASK			0x04
+#define TPS65910_INT_MSK_PWRON_IT_MSK_SHIFT			2
+#define TPS65910_INT_MSK_VMBHI_IT_MSK_MASK			0x02
+#define TPS65910_INT_MSK_VMBHI_IT_MSK_SHIFT			1
+#define TPS65910_INT_MSK_VMBDCH_IT_MSK_MASK			0x01
+#define TPS65910_INT_MSK_VMBDCH_IT_MSK_SHIFT			0
+
+#define TPS65910_INT_STS2_GPIO0_F_IT_SHIFT			2
+#define TPS65910_INT_STS2_GPIO0_F_IT_MASK			0x02
+#define TPS65910_INT_STS2_GPIO0_R_IT_SHIFT			1
+#define TPS65910_INT_STS2_GPIO0_R_IT_MASK			0x01
+
+#define TPS65910_INT_MSK2_GPIO0_F_IT_MSK_SHIFT			2
+#define TPS65910_INT_MSK2_GPIO0_F_IT_MSK_MASK			0x02
+#define TPS65910_INT_MSK2_GPIO0_R_IT_MSK_SHIFT			1
+#define TPS65910_INT_MSK2_GPIO0_R_IT_MSK_MASK			0x01
 
 /*Register INT_STS  (0x80) register.RegisterDescription */
 #define INT_STS_RTC_PERIOD_IT_MASK			0x80
@@ -580,16 +623,16 @@
 #define INT_STS_RTC_ALARM_IT_SHIFT			6
 #define INT_STS_HOTDIE_IT_MASK				0x20
 #define INT_STS_HOTDIE_IT_SHIFT				5
-#define INT_STS_PWRHOLD_IT_MASK				0x10
-#define INT_STS_PWRHOLD_IT_SHIFT			4
+#define INT_STS_PWRHOLD_R_IT_MASK			0x10
+#define INT_STS_PWRHOLD_R_IT_SHIFT			4
 #define INT_STS_PWRON_LP_IT_MASK			0x08
 #define INT_STS_PWRON_LP_IT_SHIFT			3
 #define INT_STS_PWRON_IT_MASK				0x04
 #define INT_STS_PWRON_IT_SHIFT				2
 #define INT_STS_VMBHI_IT_MASK				0x02
 #define INT_STS_VMBHI_IT_SHIFT				1
-#define INT_STS_VMBDCH_IT_MASK				0x01
-#define INT_STS_VMBDCH_IT_SHIFT				0
+#define INT_STS_PWRHOLD_F_IT_MASK			0x01
+#define INT_STS_PWRHOLD_F_IT_SHIFT			0
 
 
 /*Register INT_MSK  (0x80) register.RegisterDescription */
@@ -599,16 +642,16 @@
 #define INT_MSK_RTC_ALARM_IT_MSK_SHIFT			6
 #define INT_MSK_HOTDIE_IT_MSK_MASK			0x20
 #define INT_MSK_HOTDIE_IT_MSK_SHIFT			5
-#define INT_MSK_PWRHOLD_IT_MSK_MASK			0x10
-#define INT_MSK_PWRHOLD_IT_MSK_SHIFT			4
+#define INT_MSK_PWRHOLD_R_IT_MSK_MASK			0x10
+#define INT_MSK_PWRHOLD_R_IT_MSK_SHIFT			4
 #define INT_MSK_PWRON_LP_IT_MSK_MASK			0x08
 #define INT_MSK_PWRON_LP_IT_MSK_SHIFT			3
 #define INT_MSK_PWRON_IT_MSK_MASK			0x04
 #define INT_MSK_PWRON_IT_MSK_SHIFT			2
 #define INT_MSK_VMBHI_IT_MSK_MASK			0x02
 #define INT_MSK_VMBHI_IT_MSK_SHIFT			1
-#define INT_MSK_VMBDCH_IT_MSK_MASK			0x01
-#define INT_MSK_VMBDCH_IT_MSK_SHIFT			0
+#define INT_MSK_PWRHOLD_F_IT_MSK_MASK			0x01
+#define INT_MSK_PWRHOLD_F_IT_MSK_SHIFT			0
 
 
 /*Register INT_STS2  (0x80) register.RegisterDescription */
@@ -650,6 +693,14 @@
 
 
 /*Register INT_STS3  (0x80) register.RegisterDescription */
+#define INT_STS3_PWRDN_IT_MASK				0x80
+#define INT_STS3_PWRDN_IT_SHIFT				7
+#define INT_STS3_VMBCH2_L_IT_MASK			0x40
+#define INT_STS3_VMBCH2_L_IT_SHIFT			6
+#define INT_STS3_VMBCH2_H_IT_MASK			0x20
+#define INT_STS3_VMBCH2_H_IT_SHIFT			5
+#define INT_STS3_WTCHDG_IT_MASK				0x10
+#define INT_STS3_WTCHDG_IT_SHIFT			4
 #define INT_STS3_GPIO5_F_IT_MASK			0x08
 #define INT_STS3_GPIO5_F_IT_SHIFT			3
 #define INT_STS3_GPIO5_R_IT_MASK			0x04
@@ -661,6 +712,14 @@
 
 
 /*Register INT_MSK3  (0x80) register.RegisterDescription */
+#define INT_MSK3_PWRDN_IT_MSK_MASK			0x80
+#define INT_MSK3_PWRDN_IT_MSK_SHIFT			7
+#define INT_MSK3_VMBCH2_L_IT_MSK_MASK			0x40
+#define INT_MSK3_VMBCH2_L_IT_MSK_SHIFT			6
+#define INT_MSK3_VMBCH2_H_IT_MSK_MASK			0x20
+#define INT_MSK3_VMBCH2_H_IT_MSK_SHIFT			5
+#define INT_MSK3_WTCHDG_IT_MSK_MASK			0x10
+#define INT_MSK3_WTCHDG_IT_MSK_SHIFT			4
 #define INT_MSK3_GPIO5_F_IT_MSK_MASK			0x08
 #define INT_MSK3_GPIO5_F_IT_MSK_SHIFT			3
 #define INT_MSK3_GPIO5_R_IT_MSK_MASK			0x04
@@ -721,34 +780,32 @@
 #define TPS65910_IRQ_GPIO_F				9
 #define TPS65910_NUM_IRQ				10
 
-#define TPS65911_IRQ_VBAT_VMBDCH			0
-#define TPS65911_IRQ_VBAT_VMBDCH2L			1
-#define TPS65911_IRQ_VBAT_VMBDCH2H			2
-#define TPS65911_IRQ_VBAT_VMHI				3
-#define TPS65911_IRQ_PWRON				4
-#define TPS65911_IRQ_PWRON_LP				5
-#define TPS65911_IRQ_PWRHOLD_F				6
-#define TPS65911_IRQ_PWRHOLD_R				7
-#define TPS65911_IRQ_HOTDIE				8
-#define TPS65911_IRQ_RTC_ALARM				9
-#define TPS65911_IRQ_RTC_PERIOD				10
-#define TPS65911_IRQ_GPIO0_R				11
-#define TPS65911_IRQ_GPIO0_F				12
-#define TPS65911_IRQ_GPIO1_R				13
-#define TPS65911_IRQ_GPIO1_F				14
-#define TPS65911_IRQ_GPIO2_R				15
-#define TPS65911_IRQ_GPIO2_F				16
-#define TPS65911_IRQ_GPIO3_R				17
-#define TPS65911_IRQ_GPIO3_F				18
-#define TPS65911_IRQ_GPIO4_R				19
-#define TPS65911_IRQ_GPIO4_F				20
-#define TPS65911_IRQ_GPIO5_R				21
-#define TPS65911_IRQ_GPIO5_F				22
-#define TPS65911_IRQ_WTCHDG				23
-#define TPS65911_IRQ_PWRDN				24
-
-#define TPS65911_NUM_IRQ				25
-
+#define TPS65911_IRQ_PWRHOLD_F				0
+#define TPS65911_IRQ_VBAT_VMHI				1
+#define TPS65911_IRQ_PWRON				2
+#define TPS65911_IRQ_PWRON_LP				3
+#define TPS65911_IRQ_PWRHOLD_R				4
+#define TPS65911_IRQ_HOTDIE				5
+#define TPS65911_IRQ_RTC_ALARM				6
+#define TPS65911_IRQ_RTC_PERIOD				7
+#define TPS65911_IRQ_GPIO0_R				8
+#define TPS65911_IRQ_GPIO0_F				9
+#define TPS65911_IRQ_GPIO1_R				10
+#define TPS65911_IRQ_GPIO1_F				11
+#define TPS65911_IRQ_GPIO2_R				12
+#define TPS65911_IRQ_GPIO2_F				13
+#define TPS65911_IRQ_GPIO3_R				14
+#define TPS65911_IRQ_GPIO3_F				15
+#define TPS65911_IRQ_GPIO4_R				16
+#define TPS65911_IRQ_GPIO4_F				17
+#define TPS65911_IRQ_GPIO5_R				18
+#define TPS65911_IRQ_GPIO5_F				19
+#define TPS65911_IRQ_WTCHDG				20
+#define TPS65911_IRQ_VMBCH2_H				21
+#define TPS65911_IRQ_VMBCH2_L				22
+#define TPS65911_IRQ_PWRDN				23
+
+#define TPS65911_NUM_IRQ				24
 
 /* GPIO Register Definitions */
 #define TPS65910_GPIO_DEB				BIT(2)
@@ -848,11 +905,8 @@ struct tps65910 {
 	struct tps65910_board *of_plat_data;
 
 	/* IRQ Handling */
-	struct mutex irq_lock;
 	int chip_irq;
-	int irq_base;
-	int irq_num;
-	u32 irq_mask;
+	struct regmap_irq_chip_data *irq_data;
 	struct irq_domain *domain;
 };
 
@@ -900,4 +954,9 @@ static inline int tps65910_reg_update_bits(struct tps65910 *tps65910, u8 reg,
 	return regmap_update_bits(tps65910->regmap, reg, mask, val);
 }
 
+static inline int tps65910_irq_get_virq(struct tps65910 *tps65910, int irq)
+{
+	return regmap_irq_get_virq(tps65910->irq_data, irq);
+}
+
 #endif /*  __LINUX_MFD_TPS65910_H */
-- 
cgit v1.2.3-55-g7522


From 4aab3fadad32ff4df05832beff7c16fd6ad938aa Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 13 Nov 2012 19:33:58 +0530
Subject: mfd: tps65910: Move interrupt implementation code to mfd file

In place of implementing the irq support in separate file,
moving implementation to main mfd file.
The irq files only contains the table and init steps only
and does not need extra file to have this only for this
purpose.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/Makefile         |   2 +-
 drivers/mfd/tps65910-irq.c   | 243 -------------------------------------------
 drivers/mfd/tps65910.c       | 216 ++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/tps65910.h |   4 -
 4 files changed, 217 insertions(+), 248 deletions(-)
 delete mode 100644 drivers/mfd/tps65910-irq.c

(limited to 'include')

diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 8a68fc7ea870..a30c49ecdd95 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -56,7 +56,7 @@ obj-$(CONFIG_TPS6105X)		+= tps6105x.o
 obj-$(CONFIG_TPS65010)		+= tps65010.o
 obj-$(CONFIG_TPS6507X)		+= tps6507x.o
 obj-$(CONFIG_MFD_TPS65217)	+= tps65217.o
-obj-$(CONFIG_MFD_TPS65910)	+= tps65910.o tps65910-irq.o
+obj-$(CONFIG_MFD_TPS65910)	+= tps65910.o
 tps65912-objs                   := tps65912-core.o tps65912-irq.o
 obj-$(CONFIG_MFD_TPS65912)	+= tps65912.o
 obj-$(CONFIG_MFD_TPS65912_I2C)	+= tps65912-i2c.o
diff --git a/drivers/mfd/tps65910-irq.c b/drivers/mfd/tps65910-irq.c
deleted file mode 100644
index 554543a584a1..000000000000
--- a/drivers/mfd/tps65910-irq.c
+++ /dev/null
@@ -1,243 +0,0 @@
-/*
- * tps65910-irq.c  --  TI TPS6591x
- *
- * Copyright 2010 Texas Instruments Inc.
- *
- * Author: Graeme Gregory <gg@slimlogic.co.uk>
- * Author: Jorge Eduardo Candelaria <jedu@slimlogic.co.uk>
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under  the terms of the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the License, or (at your
- *  option) any later version.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/bug.h>
-#include <linux/device.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/gpio.h>
-#include <linux/mfd/tps65910.h>
-
-
-static const struct regmap_irq tps65911_irqs[] = {
-	/* INT_STS */
-	[TPS65911_IRQ_PWRHOLD_F] = {
-		.mask = INT_MSK_PWRHOLD_F_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65911_IRQ_VBAT_VMHI] = {
-		.mask = INT_MSK_VMBHI_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65911_IRQ_PWRON] = {
-		.mask = INT_MSK_PWRON_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65911_IRQ_PWRON_LP] = {
-		.mask = INT_MSK_PWRON_LP_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65911_IRQ_PWRHOLD_R] = {
-		.mask = INT_MSK_PWRHOLD_R_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65911_IRQ_HOTDIE] = {
-		.mask = INT_MSK_HOTDIE_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65911_IRQ_RTC_ALARM] = {
-		.mask = INT_MSK_RTC_ALARM_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65911_IRQ_RTC_PERIOD] = {
-		.mask = INT_MSK_RTC_PERIOD_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-
-	/* INT_STS2 */
-	[TPS65911_IRQ_GPIO0_R] = {
-		.mask = INT_MSK2_GPIO0_R_IT_MSK_MASK,
-		.reg_offset = 1,
-	},
-	[TPS65911_IRQ_GPIO0_F] = {
-		.mask = INT_MSK2_GPIO0_F_IT_MSK_MASK,
-		.reg_offset = 1,
-	},
-	[TPS65911_IRQ_GPIO1_R] = {
-		.mask = INT_MSK2_GPIO1_R_IT_MSK_MASK,
-		.reg_offset = 1,
-	},
-	[TPS65911_IRQ_GPIO1_F] = {
-		.mask = INT_MSK2_GPIO1_F_IT_MSK_MASK,
-		.reg_offset = 1,
-	},
-	[TPS65911_IRQ_GPIO2_R] = {
-		.mask = INT_MSK2_GPIO2_R_IT_MSK_MASK,
-		.reg_offset = 1,
-	},
-	[TPS65911_IRQ_GPIO2_F] = {
-		.mask = INT_MSK2_GPIO2_F_IT_MSK_MASK,
-		.reg_offset = 1,
-	},
-	[TPS65911_IRQ_GPIO3_R] = {
-		.mask = INT_MSK2_GPIO3_R_IT_MSK_MASK,
-		.reg_offset = 1,
-	},
-	[TPS65911_IRQ_GPIO3_F] = {
-		.mask = INT_MSK2_GPIO3_F_IT_MSK_MASK,
-		.reg_offset = 1,
-	},
-
-	/* INT_STS3 */
-	[TPS65911_IRQ_GPIO4_R] = {
-		.mask = INT_MSK3_GPIO4_R_IT_MSK_MASK,
-		.reg_offset = 2,
-	},
-	[TPS65911_IRQ_GPIO4_F] = {
-		.mask = INT_MSK3_GPIO4_F_IT_MSK_MASK,
-		.reg_offset = 2,
-	},
-	[TPS65911_IRQ_GPIO5_R] = {
-		.mask = INT_MSK3_GPIO5_R_IT_MSK_MASK,
-		.reg_offset = 2,
-	},
-	[TPS65911_IRQ_GPIO5_F] = {
-		.mask = INT_MSK3_GPIO5_F_IT_MSK_MASK,
-		.reg_offset = 2,
-	},
-	[TPS65911_IRQ_WTCHDG] = {
-		.mask = INT_MSK3_WTCHDG_IT_MSK_MASK,
-		.reg_offset = 2,
-	},
-	[TPS65911_IRQ_VMBCH2_H] = {
-		.mask = INT_MSK3_VMBCH2_H_IT_MSK_MASK,
-		.reg_offset = 2,
-	},
-	[TPS65911_IRQ_VMBCH2_L] = {
-		.mask = INT_MSK3_VMBCH2_L_IT_MSK_MASK,
-		.reg_offset = 2,
-	},
-	[TPS65911_IRQ_PWRDN] = {
-		.mask = INT_MSK3_PWRDN_IT_MSK_MASK,
-		.reg_offset = 2,
-	},
-};
-
-static const struct regmap_irq tps65910_irqs[] = {
-	/* INT_STS */
-	[TPS65910_IRQ_VBAT_VMBDCH] = {
-		.mask = TPS65910_INT_MSK_VMBDCH_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65910_IRQ_VBAT_VMHI] = {
-		.mask = TPS65910_INT_MSK_VMBHI_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65910_IRQ_PWRON] = {
-		.mask = TPS65910_INT_MSK_PWRON_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65910_IRQ_PWRON_LP] = {
-		.mask = TPS65910_INT_MSK_PWRON_LP_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65910_IRQ_PWRHOLD] = {
-		.mask = TPS65910_INT_MSK_PWRHOLD_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65910_IRQ_HOTDIE] = {
-		.mask = TPS65910_INT_MSK_HOTDIE_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65910_IRQ_RTC_ALARM] = {
-		.mask = TPS65910_INT_MSK_RTC_ALARM_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-	[TPS65910_IRQ_RTC_PERIOD] = {
-		.mask = TPS65910_INT_MSK_RTC_PERIOD_IT_MSK_MASK,
-		.reg_offset = 0,
-	},
-
-	/* INT_STS2 */
-	[TPS65910_IRQ_GPIO_R] = {
-		.mask = TPS65910_INT_MSK2_GPIO0_F_IT_MSK_MASK,
-		.reg_offset = 1,
-	},
-	[TPS65910_IRQ_GPIO_F] = {
-		.mask = TPS65910_INT_MSK2_GPIO0_R_IT_MSK_MASK,
-		.reg_offset = 1,
-	},
-};
-
-static struct regmap_irq_chip tps65911_irq_chip = {
-	.name = "tps65910",
-	.irqs = tps65911_irqs,
-	.num_irqs = ARRAY_SIZE(tps65911_irqs),
-	.num_regs = 3,
-	.irq_reg_stride = 2,
-	.status_base = TPS65910_INT_STS,
-	.mask_base = TPS65910_INT_MSK,
-	.ack_base = TPS65910_INT_MSK,
-};
-
-static struct regmap_irq_chip tps65910_irq_chip = {
-	.name = "tps65910",
-	.irqs = tps65910_irqs,
-	.num_irqs = ARRAY_SIZE(tps65910_irqs),
-	.num_regs = 2,
-	.irq_reg_stride = 2,
-	.status_base = TPS65910_INT_STS,
-	.mask_base = TPS65910_INT_MSK,
-	.ack_base = TPS65910_INT_MSK,
-};
-
-int tps65910_irq_init(struct tps65910 *tps65910, int irq,
-		    struct tps65910_platform_data *pdata)
-{
-	int ret = 0;
-	static struct regmap_irq_chip *tps6591x_irqs_chip;
-
-	if (!irq) {
-		dev_warn(tps65910->dev, "No interrupt support, no core IRQ\n");
-		return -EINVAL;
-	}
-
-	if (!pdata) {
-		dev_warn(tps65910->dev, "No interrupt support, no pdata\n");
-		return -EINVAL;
-	}
-
-
-	switch (tps65910_chip_id(tps65910)) {
-	case TPS65910:
-		tps6591x_irqs_chip = &tps65910_irq_chip;
-		break;
-	case TPS65911:
-		tps6591x_irqs_chip = &tps65911_irq_chip;
-		break;
-	}
-
-	tps65910->chip_irq = irq;
-	ret = regmap_add_irq_chip(tps65910->regmap, tps65910->chip_irq,
-		IRQF_ONESHOT, pdata->irq_base,
-		tps6591x_irqs_chip, &tps65910->irq_data);
-	if (ret < 0) {
-		dev_warn(tps65910->dev,
-				"Failed to add irq_chip %d\n", ret);
-		return ret;
-	}
-	return ret;
-}
-
-int tps65910_irq_exit(struct tps65910 *tps65910)
-{
-	if (tps65910->chip_irq > 0)
-		regmap_del_irq_chip(tps65910->chip_irq, tps65910->irq_data);
-	return 0;
-}
diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index 27fbbe510101..d4d4eb5b5b6f 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -19,6 +19,9 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
 #include <linux/mfd/core.h>
 #include <linux/regmap.h>
 #include <linux/mfd/tps65910.h>
@@ -50,6 +53,219 @@ static struct mfd_cell tps65910s[] = {
 };
 
 
+static const struct regmap_irq tps65911_irqs[] = {
+	/* INT_STS */
+	[TPS65911_IRQ_PWRHOLD_F] = {
+		.mask = INT_MSK_PWRHOLD_F_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_VBAT_VMHI] = {
+		.mask = INT_MSK_VMBHI_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_PWRON] = {
+		.mask = INT_MSK_PWRON_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_PWRON_LP] = {
+		.mask = INT_MSK_PWRON_LP_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_PWRHOLD_R] = {
+		.mask = INT_MSK_PWRHOLD_R_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_HOTDIE] = {
+		.mask = INT_MSK_HOTDIE_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_RTC_ALARM] = {
+		.mask = INT_MSK_RTC_ALARM_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65911_IRQ_RTC_PERIOD] = {
+		.mask = INT_MSK_RTC_PERIOD_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+
+	/* INT_STS2 */
+	[TPS65911_IRQ_GPIO0_R] = {
+		.mask = INT_MSK2_GPIO0_R_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO0_F] = {
+		.mask = INT_MSK2_GPIO0_F_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO1_R] = {
+		.mask = INT_MSK2_GPIO1_R_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO1_F] = {
+		.mask = INT_MSK2_GPIO1_F_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO2_R] = {
+		.mask = INT_MSK2_GPIO2_R_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO2_F] = {
+		.mask = INT_MSK2_GPIO2_F_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO3_R] = {
+		.mask = INT_MSK2_GPIO3_R_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65911_IRQ_GPIO3_F] = {
+		.mask = INT_MSK2_GPIO3_F_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+
+	/* INT_STS2 */
+	[TPS65911_IRQ_GPIO4_R] = {
+		.mask = INT_MSK3_GPIO4_R_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_GPIO4_F] = {
+		.mask = INT_MSK3_GPIO4_F_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_GPIO5_R] = {
+		.mask = INT_MSK3_GPIO5_R_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_GPIO5_F] = {
+		.mask = INT_MSK3_GPIO5_F_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_WTCHDG] = {
+		.mask = INT_MSK3_WTCHDG_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_VMBCH2_H] = {
+		.mask = INT_MSK3_VMBCH2_H_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_VMBCH2_L] = {
+		.mask = INT_MSK3_VMBCH2_L_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+	[TPS65911_IRQ_PWRDN] = {
+		.mask = INT_MSK3_PWRDN_IT_MSK_MASK,
+		.reg_offset = 2,
+	},
+};
+
+static const struct regmap_irq tps65910_irqs[] = {
+	/* INT_STS */
+	[TPS65910_IRQ_VBAT_VMBDCH] = {
+		.mask = TPS65910_INT_MSK_VMBDCH_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_VBAT_VMHI] = {
+		.mask = TPS65910_INT_MSK_VMBHI_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_PWRON] = {
+		.mask = TPS65910_INT_MSK_PWRON_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_PWRON_LP] = {
+		.mask = TPS65910_INT_MSK_PWRON_LP_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_PWRHOLD] = {
+		.mask = TPS65910_INT_MSK_PWRHOLD_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_HOTDIE] = {
+		.mask = TPS65910_INT_MSK_HOTDIE_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_RTC_ALARM] = {
+		.mask = TPS65910_INT_MSK_RTC_ALARM_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+	[TPS65910_IRQ_RTC_PERIOD] = {
+		.mask = TPS65910_INT_MSK_RTC_PERIOD_IT_MSK_MASK,
+		.reg_offset = 0,
+	},
+
+	/* INT_STS2 */
+	[TPS65910_IRQ_GPIO_R] = {
+		.mask = TPS65910_INT_MSK2_GPIO0_F_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+	[TPS65910_IRQ_GPIO_F] = {
+		.mask = TPS65910_INT_MSK2_GPIO0_R_IT_MSK_MASK,
+		.reg_offset = 1,
+	},
+};
+
+static struct regmap_irq_chip tps65911_irq_chip = {
+	.name = "tps65910",
+	.irqs = tps65911_irqs,
+	.num_irqs = ARRAY_SIZE(tps65911_irqs),
+	.num_regs = 3,
+	.irq_reg_stride = 2,
+	.status_base = TPS65910_INT_STS,
+	.mask_base = TPS65910_INT_MSK,
+	.ack_base = TPS65910_INT_MSK,
+};
+
+static struct regmap_irq_chip tps65910_irq_chip = {
+	.name = "tps65910",
+	.irqs = tps65910_irqs,
+	.num_irqs = ARRAY_SIZE(tps65910_irqs),
+	.num_regs = 2,
+	.irq_reg_stride = 2,
+	.status_base = TPS65910_INT_STS,
+	.mask_base = TPS65910_INT_MSK,
+	.ack_base = TPS65910_INT_MSK,
+};
+
+static int tps65910_irq_init(struct tps65910 *tps65910, int irq,
+		    struct tps65910_platform_data *pdata)
+{
+	int ret = 0;
+	static struct regmap_irq_chip *tps6591x_irqs_chip;
+
+	if (!irq) {
+		dev_warn(tps65910->dev, "No interrupt support, no core IRQ\n");
+		return -EINVAL;
+	}
+
+	if (!pdata) {
+		dev_warn(tps65910->dev, "No interrupt support, no pdata\n");
+		return -EINVAL;
+	}
+
+	switch (tps65910_chip_id(tps65910)) {
+	case TPS65910:
+		tps6591x_irqs_chip = &tps65910_irq_chip;
+		break;
+	case TPS65911:
+		tps6591x_irqs_chip = &tps65911_irq_chip;
+		break;
+	}
+
+	tps65910->chip_irq = irq;
+	ret = regmap_add_irq_chip(tps65910->regmap, tps65910->chip_irq,
+		IRQF_ONESHOT, pdata->irq_base,
+		tps6591x_irqs_chip, &tps65910->irq_data);
+	if (ret < 0)
+		dev_warn(tps65910->dev, "Failed to add irq_chip %d\n", ret);
+	return ret;
+}
+
+static int tps65910_irq_exit(struct tps65910 *tps65910)
+{
+	if (tps65910->chip_irq > 0)
+		regmap_del_irq_chip(tps65910->chip_irq, tps65910->irq_data);
+	return 0;
+}
+
 static bool is_volatile_reg(struct device *dev, unsigned int reg)
 {
 	struct tps65910 *tps65910 = dev_get_drvdata(dev);
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index b564ac29590a..0b16903f7e88 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -915,10 +915,6 @@ struct tps65910_platform_data {
 	int irq_base;
 };
 
-int tps65910_irq_init(struct tps65910 *tps65910, int irq,
-		struct tps65910_platform_data *pdata);
-int tps65910_irq_exit(struct tps65910 *tps65910);
-
 static inline int tps65910_chip_id(struct tps65910 *tps65910)
 {
 	return tps65910->id;
-- 
cgit v1.2.3-55-g7522


From 8bad1abd6303476d6f77878aa8ea737d5d1b625c Mon Sep 17 00:00:00 2001
From: Fabio Estevam
Date: Thu, 4 Oct 2012 00:15:05 -0300
Subject: mfd: da9052: Introduce da9052-irq.c

Create a da9052-irq.c file so that it can handle interrupt related functions.

This is useful for allowing the da9052 drivers to use such functions
when dealing with da9052 interrupts.

Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/Makefile              |   1 +
 drivers/mfd/da9052-core.c         | 271 ++---------------------------------
 drivers/mfd/da9052-irq.c          | 288 ++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/da9052/da9052.h |  10 ++
 4 files changed, 307 insertions(+), 263 deletions(-)
 create mode 100644 drivers/mfd/da9052-irq.c

(limited to 'include')

diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index a30c49ecdd95..632cce09e407 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -90,6 +90,7 @@ obj-$(CONFIG_UCB1400_CORE)	+= ucb1400_core.o
 
 obj-$(CONFIG_PMIC_DA903X)	+= da903x.o
 
+obj-$(CONFIG_PMIC_DA9052)	+= da9052-irq.o
 obj-$(CONFIG_PMIC_DA9052)	+= da9052-core.o
 obj-$(CONFIG_MFD_DA9052_SPI)	+= da9052-spi.o
 obj-$(CONFIG_MFD_DA9052_I2C)	+= da9052-i2c.o
diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c
index c96cdbc0daff..2153f9bba9ef 100644
--- a/drivers/mfd/da9052-core.c
+++ b/drivers/mfd/da9052-core.c
@@ -15,7 +15,6 @@
 #include <linux/delay.h>
 #include <linux/input.h>
 #include <linux/interrupt.h>
-#include <linux/irq.h>
 #include <linux/mfd/core.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -24,16 +23,6 @@
 #include <linux/mfd/da9052/pdata.h>
 #include <linux/mfd/da9052/reg.h>
 
-#define DA9052_NUM_IRQ_REGS		4
-#define DA9052_IRQ_MASK_POS_1		0x01
-#define DA9052_IRQ_MASK_POS_2		0x02
-#define DA9052_IRQ_MASK_POS_3		0x04
-#define DA9052_IRQ_MASK_POS_4		0x08
-#define DA9052_IRQ_MASK_POS_5		0x10
-#define DA9052_IRQ_MASK_POS_6		0x20
-#define DA9052_IRQ_MASK_POS_7		0x40
-#define DA9052_IRQ_MASK_POS_8		0x80
-
 static bool da9052_reg_readable(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
@@ -425,15 +414,6 @@ err:
 }
 EXPORT_SYMBOL_GPL(da9052_adc_manual_read);
 
-static irqreturn_t da9052_auxadc_irq(int irq, void *irq_data)
-{
-	struct da9052 *da9052 = irq_data;
-
-	complete(&da9052->done);
-
-	return IRQ_HANDLED;
-}
-
 int da9052_adc_read_temp(struct da9052 *da9052)
 {
 	int tbat;
@@ -447,74 +427,6 @@ int da9052_adc_read_temp(struct da9052 *da9052)
 }
 EXPORT_SYMBOL_GPL(da9052_adc_read_temp);
 
-static struct resource da9052_rtc_resource = {
-	.name = "ALM",
-	.start = DA9052_IRQ_ALARM,
-	.end   = DA9052_IRQ_ALARM,
-	.flags = IORESOURCE_IRQ,
-};
-
-static struct resource da9052_onkey_resource = {
-	.name = "ONKEY",
-	.start = DA9052_IRQ_NONKEY,
-	.end   = DA9052_IRQ_NONKEY,
-	.flags = IORESOURCE_IRQ,
-};
-
-static struct resource da9052_bat_resources[] = {
-	{
-		.name = "BATT TEMP",
-		.start = DA9052_IRQ_TBAT,
-		.end   = DA9052_IRQ_TBAT,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "DCIN DET",
-		.start = DA9052_IRQ_DCIN,
-		.end   = DA9052_IRQ_DCIN,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "DCIN REM",
-		.start = DA9052_IRQ_DCINREM,
-		.end   = DA9052_IRQ_DCINREM,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "VBUS DET",
-		.start = DA9052_IRQ_VBUS,
-		.end   = DA9052_IRQ_VBUS,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "VBUS REM",
-		.start = DA9052_IRQ_VBUSREM,
-		.end   = DA9052_IRQ_VBUSREM,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "CHG END",
-		.start = DA9052_IRQ_CHGEND,
-		.end   = DA9052_IRQ_CHGEND,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource da9052_tsi_resources[] = {
-	{
-		.name = "PENDWN",
-		.start = DA9052_IRQ_PENDOWN,
-		.end   = DA9052_IRQ_PENDOWN,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "TSIRDY",
-		.start = DA9052_IRQ_TSIREADY,
-		.end   = DA9052_IRQ_TSIREADY,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
 static struct mfd_cell __devinitdata da9052_subdev_info[] = {
 	{
 		.name = "da9052-regulator",
@@ -574,13 +486,9 @@ static struct mfd_cell __devinitdata da9052_subdev_info[] = {
 	},
 	{
 		.name = "da9052-onkey",
-		.resources = &da9052_onkey_resource,
-		.num_resources = 1,
 	},
 	{
 		.name = "da9052-rtc",
-		.resources = &da9052_rtc_resource,
-		.num_resources = 1,
 	},
 	{
 		.name = "da9052-gpio",
@@ -602,160 +510,15 @@ static struct mfd_cell __devinitdata da9052_subdev_info[] = {
 	},
 	{
 		.name = "da9052-tsi",
-		.resources = da9052_tsi_resources,
-		.num_resources = ARRAY_SIZE(da9052_tsi_resources),
 	},
 	{
 		.name = "da9052-bat",
-		.resources = da9052_bat_resources,
-		.num_resources = ARRAY_SIZE(da9052_bat_resources),
 	},
 	{
 		.name = "da9052-watchdog",
 	},
 };
 
-static struct regmap_irq da9052_irqs[] = {
-	[DA9052_IRQ_DCIN] = {
-		.reg_offset = 0,
-		.mask = DA9052_IRQ_MASK_POS_1,
-	},
-	[DA9052_IRQ_VBUS] = {
-		.reg_offset = 0,
-		.mask = DA9052_IRQ_MASK_POS_2,
-	},
-	[DA9052_IRQ_DCINREM] = {
-		.reg_offset = 0,
-		.mask = DA9052_IRQ_MASK_POS_3,
-	},
-	[DA9052_IRQ_VBUSREM] = {
-		.reg_offset = 0,
-		.mask = DA9052_IRQ_MASK_POS_4,
-	},
-	[DA9052_IRQ_VDDLOW] = {
-		.reg_offset = 0,
-		.mask = DA9052_IRQ_MASK_POS_5,
-	},
-	[DA9052_IRQ_ALARM] = {
-		.reg_offset = 0,
-		.mask = DA9052_IRQ_MASK_POS_6,
-	},
-	[DA9052_IRQ_SEQRDY] = {
-		.reg_offset = 0,
-		.mask = DA9052_IRQ_MASK_POS_7,
-	},
-	[DA9052_IRQ_COMP1V2] = {
-		.reg_offset = 0,
-		.mask = DA9052_IRQ_MASK_POS_8,
-	},
-	[DA9052_IRQ_NONKEY] = {
-		.reg_offset = 1,
-		.mask = DA9052_IRQ_MASK_POS_1,
-	},
-	[DA9052_IRQ_IDFLOAT] = {
-		.reg_offset = 1,
-		.mask = DA9052_IRQ_MASK_POS_2,
-	},
-	[DA9052_IRQ_IDGND] = {
-		.reg_offset = 1,
-		.mask = DA9052_IRQ_MASK_POS_3,
-	},
-	[DA9052_IRQ_CHGEND] = {
-		.reg_offset = 1,
-		.mask = DA9052_IRQ_MASK_POS_4,
-	},
-	[DA9052_IRQ_TBAT] = {
-		.reg_offset = 1,
-		.mask = DA9052_IRQ_MASK_POS_5,
-	},
-	[DA9052_IRQ_ADC_EOM] = {
-		.reg_offset = 1,
-		.mask = DA9052_IRQ_MASK_POS_6,
-	},
-	[DA9052_IRQ_PENDOWN] = {
-		.reg_offset = 1,
-		.mask = DA9052_IRQ_MASK_POS_7,
-	},
-	[DA9052_IRQ_TSIREADY] = {
-		.reg_offset = 1,
-		.mask = DA9052_IRQ_MASK_POS_8,
-	},
-	[DA9052_IRQ_GPI0] = {
-		.reg_offset = 2,
-		.mask = DA9052_IRQ_MASK_POS_1,
-	},
-	[DA9052_IRQ_GPI1] = {
-		.reg_offset = 2,
-		.mask = DA9052_IRQ_MASK_POS_2,
-	},
-	[DA9052_IRQ_GPI2] = {
-		.reg_offset = 2,
-		.mask = DA9052_IRQ_MASK_POS_3,
-	},
-	[DA9052_IRQ_GPI3] = {
-		.reg_offset = 2,
-		.mask = DA9052_IRQ_MASK_POS_4,
-	},
-	[DA9052_IRQ_GPI4] = {
-		.reg_offset = 2,
-		.mask = DA9052_IRQ_MASK_POS_5,
-	},
-	[DA9052_IRQ_GPI5] = {
-		.reg_offset = 2,
-		.mask = DA9052_IRQ_MASK_POS_6,
-	},
-	[DA9052_IRQ_GPI6] = {
-		.reg_offset = 2,
-		.mask = DA9052_IRQ_MASK_POS_7,
-	},
-	[DA9052_IRQ_GPI7] = {
-		.reg_offset = 2,
-		.mask = DA9052_IRQ_MASK_POS_8,
-	},
-	[DA9052_IRQ_GPI8] = {
-		.reg_offset = 3,
-		.mask = DA9052_IRQ_MASK_POS_1,
-	},
-	[DA9052_IRQ_GPI9] = {
-		.reg_offset = 3,
-		.mask = DA9052_IRQ_MASK_POS_2,
-	},
-	[DA9052_IRQ_GPI10] = {
-		.reg_offset = 3,
-		.mask = DA9052_IRQ_MASK_POS_3,
-	},
-	[DA9052_IRQ_GPI11] = {
-		.reg_offset = 3,
-		.mask = DA9052_IRQ_MASK_POS_4,
-	},
-	[DA9052_IRQ_GPI12] = {
-		.reg_offset = 3,
-		.mask = DA9052_IRQ_MASK_POS_5,
-	},
-	[DA9052_IRQ_GPI13] = {
-		.reg_offset = 3,
-		.mask = DA9052_IRQ_MASK_POS_6,
-	},
-	[DA9052_IRQ_GPI14] = {
-		.reg_offset = 3,
-		.mask = DA9052_IRQ_MASK_POS_7,
-	},
-	[DA9052_IRQ_GPI15] = {
-		.reg_offset = 3,
-		.mask = DA9052_IRQ_MASK_POS_8,
-	},
-};
-
-static struct regmap_irq_chip da9052_regmap_irq_chip = {
-	.name = "da9052_irq",
-	.status_base = DA9052_EVENT_A_REG,
-	.mask_base = DA9052_IRQ_MASK_A_REG,
-	.ack_base = DA9052_EVENT_A_REG,
-	.num_regs = DA9052_NUM_IRQ_REGS,
-	.irqs = da9052_irqs,
-	.num_irqs = ARRAY_SIZE(da9052_irqs),
-};
-
 struct regmap_config da9052_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
@@ -769,15 +532,10 @@ struct regmap_config da9052_regmap_config = {
 };
 EXPORT_SYMBOL_GPL(da9052_regmap_config);
 
-static int da9052_map_irq(struct da9052 *da9052, int irq)
-{
-	return regmap_irq_get_virq(da9052->irq_data, irq);
-}
-
 int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id)
 {
 	struct da9052_pdata *pdata = da9052->dev->platform_data;
-	int ret, i;
+	int ret;
 
 	mutex_init(&da9052->auxadc_lock);
 	init_completion(&da9052->done);
@@ -787,22 +545,12 @@ int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id)
 
 	da9052->chip_id = chip_id;
 
-	ret = regmap_add_irq_chip(da9052->regmap, da9052->chip_irq,
-				  IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-				  -1, &da9052_regmap_irq_chip,
-				  &da9052->irq_data);
-	if (ret < 0) {
-		dev_err(da9052->dev, "regmap_add_irq_chip failed: %d\n", ret);
-		goto regmap_err;
+	ret = da9052_irq_init(da9052);
+	if (ret != 0) {
+		dev_err(da9052->dev, "da9052_irq_init failed: %d\n", ret);
+		return ret;
 	}
 
-	i = da9052_map_irq(da9052, DA9052_IRQ_ADC_EOM);
-	ret = request_threaded_irq(i, NULL, da9052_auxadc_irq,
-				   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-				   "adc-irq", da9052);
-	if (ret != 0)
-		dev_err(da9052->dev, "DA9052 ADC IRQ failed ret=%d\n", ret);
-
 	ret = mfd_add_devices(da9052->dev, -1, da9052_subdev_info,
 			      ARRAY_SIZE(da9052_subdev_info), NULL, 0, NULL);
 	if (ret) {
@@ -813,18 +561,15 @@ int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id)
 	return 0;
 
 err:
-	free_irq(da9052_map_irq(da9052, DA9052_IRQ_ADC_EOM), da9052);
-	regmap_del_irq_chip(da9052->chip_irq, da9052->irq_data);
-	mfd_remove_devices(da9052->dev);
-regmap_err:
+	da9052_irq_exit(da9052);
+
 	return ret;
 }
 
 void da9052_device_exit(struct da9052 *da9052)
 {
-	free_irq(da9052_map_irq(da9052, DA9052_IRQ_ADC_EOM), da9052);
-	regmap_del_irq_chip(da9052->chip_irq, da9052->irq_data);
 	mfd_remove_devices(da9052->dev);
+	da9052_irq_exit(da9052);
 }
 
 MODULE_AUTHOR("David Dajun Chen <dchen@diasemi.com>");
diff --git a/drivers/mfd/da9052-irq.c b/drivers/mfd/da9052-irq.c
new file mode 100644
index 000000000000..57ae7841f536
--- /dev/null
+++ b/drivers/mfd/da9052-irq.c
@@ -0,0 +1,288 @@
+/*
+ * DA9052 interrupt support
+ *
+ * Author: Fabio Estevam <fabio.estevam@freescale.com>
+ * Based on arizona-irq.c, which is:
+ *
+ * Copyright 2012 Wolfson Microelectronics plc
+ *
+ * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/device.h>
+#include <linux/delay.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+#include <linux/mfd/da9052/da9052.h>
+#include <linux/mfd/da9052/reg.h>
+
+#define DA9052_NUM_IRQ_REGS		4
+#define DA9052_IRQ_MASK_POS_1		0x01
+#define DA9052_IRQ_MASK_POS_2		0x02
+#define DA9052_IRQ_MASK_POS_3		0x04
+#define DA9052_IRQ_MASK_POS_4		0x08
+#define DA9052_IRQ_MASK_POS_5		0x10
+#define DA9052_IRQ_MASK_POS_6		0x20
+#define DA9052_IRQ_MASK_POS_7		0x40
+#define DA9052_IRQ_MASK_POS_8		0x80
+
+static struct regmap_irq da9052_irqs[] = {
+	[DA9052_IRQ_DCIN] = {
+		.reg_offset = 0,
+		.mask = DA9052_IRQ_MASK_POS_1,
+	},
+	[DA9052_IRQ_VBUS] = {
+		.reg_offset = 0,
+		.mask = DA9052_IRQ_MASK_POS_2,
+	},
+	[DA9052_IRQ_DCINREM] = {
+		.reg_offset = 0,
+		.mask = DA9052_IRQ_MASK_POS_3,
+	},
+	[DA9052_IRQ_VBUSREM] = {
+		.reg_offset = 0,
+		.mask = DA9052_IRQ_MASK_POS_4,
+	},
+	[DA9052_IRQ_VDDLOW] = {
+		.reg_offset = 0,
+		.mask = DA9052_IRQ_MASK_POS_5,
+	},
+	[DA9052_IRQ_ALARM] = {
+		.reg_offset = 0,
+		.mask = DA9052_IRQ_MASK_POS_6,
+	},
+	[DA9052_IRQ_SEQRDY] = {
+		.reg_offset = 0,
+		.mask = DA9052_IRQ_MASK_POS_7,
+	},
+	[DA9052_IRQ_COMP1V2] = {
+		.reg_offset = 0,
+		.mask = DA9052_IRQ_MASK_POS_8,
+	},
+	[DA9052_IRQ_NONKEY] = {
+		.reg_offset = 1,
+		.mask = DA9052_IRQ_MASK_POS_1,
+	},
+	[DA9052_IRQ_IDFLOAT] = {
+		.reg_offset = 1,
+		.mask = DA9052_IRQ_MASK_POS_2,
+	},
+	[DA9052_IRQ_IDGND] = {
+		.reg_offset = 1,
+		.mask = DA9052_IRQ_MASK_POS_3,
+	},
+	[DA9052_IRQ_CHGEND] = {
+		.reg_offset = 1,
+		.mask = DA9052_IRQ_MASK_POS_4,
+	},
+	[DA9052_IRQ_TBAT] = {
+		.reg_offset = 1,
+		.mask = DA9052_IRQ_MASK_POS_5,
+	},
+	[DA9052_IRQ_ADC_EOM] = {
+		.reg_offset = 1,
+		.mask = DA9052_IRQ_MASK_POS_6,
+	},
+	[DA9052_IRQ_PENDOWN] = {
+		.reg_offset = 1,
+		.mask = DA9052_IRQ_MASK_POS_7,
+	},
+	[DA9052_IRQ_TSIREADY] = {
+		.reg_offset = 1,
+		.mask = DA9052_IRQ_MASK_POS_8,
+	},
+	[DA9052_IRQ_GPI0] = {
+		.reg_offset = 2,
+		.mask = DA9052_IRQ_MASK_POS_1,
+	},
+	[DA9052_IRQ_GPI1] = {
+		.reg_offset = 2,
+		.mask = DA9052_IRQ_MASK_POS_2,
+	},
+	[DA9052_IRQ_GPI2] = {
+		.reg_offset = 2,
+		.mask = DA9052_IRQ_MASK_POS_3,
+	},
+	[DA9052_IRQ_GPI3] = {
+		.reg_offset = 2,
+		.mask = DA9052_IRQ_MASK_POS_4,
+	},
+	[DA9052_IRQ_GPI4] = {
+		.reg_offset = 2,
+		.mask = DA9052_IRQ_MASK_POS_5,
+	},
+	[DA9052_IRQ_GPI5] = {
+		.reg_offset = 2,
+		.mask = DA9052_IRQ_MASK_POS_6,
+	},
+	[DA9052_IRQ_GPI6] = {
+		.reg_offset = 2,
+		.mask = DA9052_IRQ_MASK_POS_7,
+	},
+	[DA9052_IRQ_GPI7] = {
+		.reg_offset = 2,
+		.mask = DA9052_IRQ_MASK_POS_8,
+	},
+	[DA9052_IRQ_GPI8] = {
+		.reg_offset = 3,
+		.mask = DA9052_IRQ_MASK_POS_1,
+	},
+	[DA9052_IRQ_GPI9] = {
+		.reg_offset = 3,
+		.mask = DA9052_IRQ_MASK_POS_2,
+	},
+	[DA9052_IRQ_GPI10] = {
+		.reg_offset = 3,
+		.mask = DA9052_IRQ_MASK_POS_3,
+	},
+	[DA9052_IRQ_GPI11] = {
+		.reg_offset = 3,
+		.mask = DA9052_IRQ_MASK_POS_4,
+	},
+	[DA9052_IRQ_GPI12] = {
+		.reg_offset = 3,
+		.mask = DA9052_IRQ_MASK_POS_5,
+	},
+	[DA9052_IRQ_GPI13] = {
+		.reg_offset = 3,
+		.mask = DA9052_IRQ_MASK_POS_6,
+	},
+	[DA9052_IRQ_GPI14] = {
+		.reg_offset = 3,
+		.mask = DA9052_IRQ_MASK_POS_7,
+	},
+	[DA9052_IRQ_GPI15] = {
+		.reg_offset = 3,
+		.mask = DA9052_IRQ_MASK_POS_8,
+	},
+};
+
+static struct regmap_irq_chip da9052_regmap_irq_chip = {
+	.name = "da9052_irq",
+	.status_base = DA9052_EVENT_A_REG,
+	.mask_base = DA9052_IRQ_MASK_A_REG,
+	.ack_base = DA9052_EVENT_A_REG,
+	.num_regs = DA9052_NUM_IRQ_REGS,
+	.irqs = da9052_irqs,
+	.num_irqs = ARRAY_SIZE(da9052_irqs),
+};
+
+static int da9052_map_irq(struct da9052 *da9052, int irq)
+{
+	return regmap_irq_get_virq(da9052->irq_data, irq);
+}
+
+int da9052_enable_irq(struct da9052 *da9052, int irq)
+{
+	irq = da9052_map_irq(da9052, irq);
+	if (irq < 0)
+		return irq;
+
+	enable_irq(irq);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(da9052_enable_irq);
+
+int da9052_disable_irq(struct da9052 *da9052, int irq)
+{
+	irq = da9052_map_irq(da9052, irq);
+	if (irq < 0)
+		return irq;
+
+	disable_irq(irq);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(da9052_disable_irq);
+
+int da9052_disable_irq_nosync(struct da9052 *da9052, int irq)
+{
+	irq = da9052_map_irq(da9052, irq);
+	if (irq < 0)
+		return irq;
+
+	disable_irq_nosync(irq);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(da9052_disable_irq_nosync);
+
+int da9052_request_irq(struct da9052 *da9052, int irq, char *name,
+			   irq_handler_t handler, void *data)
+{
+	irq = da9052_map_irq(da9052, irq);
+	if (irq < 0)
+		return irq;
+
+	return request_threaded_irq(irq, NULL, handler,
+				     IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+				     name, data);
+}
+EXPORT_SYMBOL_GPL(da9052_request_irq);
+
+void da9052_free_irq(struct da9052 *da9052, int irq, void *data)
+{
+	irq = da9052_map_irq(da9052, irq);
+	if (irq < 0)
+		return;
+
+	free_irq(irq, data);
+}
+EXPORT_SYMBOL_GPL(da9052_free_irq);
+
+static irqreturn_t da9052_auxadc_irq(int irq, void *irq_data)
+{
+	struct da9052 *da9052 = irq_data;
+
+	complete(&da9052->done);
+
+	return IRQ_HANDLED;
+}
+
+int da9052_irq_init(struct da9052 *da9052)
+{
+	int ret;
+
+	ret = regmap_add_irq_chip(da9052->regmap, da9052->chip_irq,
+				  IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+				  -1, &da9052_regmap_irq_chip,
+				  &da9052->irq_data);
+	if (ret < 0) {
+		dev_err(da9052->dev, "regmap_add_irq_chip failed: %d\n", ret);
+		goto regmap_err;
+	}
+
+	ret = da9052_request_irq(da9052, DA9052_IRQ_ADC_EOM, "adc-irq",
+			    da9052_auxadc_irq, da9052);
+
+	if (ret != 0) {
+		dev_err(da9052->dev, "DA9052_IRQ_ADC_EOM failed: %d\n", ret);
+		goto request_irq_err;
+	}
+
+	return 0;
+
+request_irq_err:
+	regmap_del_irq_chip(da9052->chip_irq, da9052->irq_data);
+regmap_err:
+	return ret;
+
+}
+
+int da9052_irq_exit(struct da9052 *da9052)
+{
+	da9052_free_irq(da9052, DA9052_IRQ_ADC_EOM , da9052);
+	regmap_del_irq_chip(da9052->chip_irq, da9052->irq_data);
+
+	return 0;
+}
diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index 0507c4c21a7d..86dd93de6ff2 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -146,4 +146,14 @@ void da9052_device_exit(struct da9052 *da9052);
 
 extern struct regmap_config da9052_regmap_config;
 
+int da9052_irq_init(struct da9052 *da9052);
+int da9052_irq_exit(struct da9052 *da9052);
+int da9052_request_irq(struct da9052 *da9052, int irq, char *name,
+			   irq_handler_t handler, void *data);
+void da9052_free_irq(struct da9052 *da9052, int irq, void *data);
+
+int da9052_enable_irq(struct da9052 *da9052, int irq);
+int da9052_disable_irq(struct da9052 *da9052, int irq);
+int da9052_disable_irq_nosync(struct da9052 *da9052, int irq);
+
 #endif /* __MFD_DA9052_DA9052_H */
-- 
cgit v1.2.3-55-g7522


From f01312d846016dbd38cc9865e580298fb61f2aa7 Mon Sep 17 00:00:00 2001
From: Lars Poeschel
Date: Mon, 5 Nov 2012 15:48:23 +0100
Subject: mfd: Add viperboard driver

Add mfd driver for Nano River Technologies viperboard.

Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/Kconfig            |  14 +++++
 drivers/mfd/Makefile           |   1 +
 drivers/mfd/viperboard.c       | 129 +++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/viperboard.h | 105 +++++++++++++++++++++++++++++++++
 4 files changed, 249 insertions(+)
 create mode 100644 drivers/mfd/viperboard.c
 create mode 100644 include/linux/mfd/viperboard.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 34242cada125..b280639a7634 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1065,6 +1065,20 @@ config MFD_PALMAS
 	  If you say yes here you get support for the Palmas
 	  series of PMIC chips from Texas Instruments.
 
+config MFD_VIPERBOARD
+        tristate "Support for Nano River Technologies Viperboard"
+	select MFD_CORE
+	depends on USB
+	default n
+	help
+	  Say yes here if you want support for Nano River Technologies
+	  Viperboard.
+	  There are mfd cell drivers available for i2c master, adc and
+	  both gpios found on the board. The spi part does not yet
+	  have a driver.
+	  You need to select the mfd cell drivers separately.
+	  The drivers do not support all features the board exposes.
+
 endmenu
 endif
 
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 632cce09e407..1c3ee7c76906 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -139,6 +139,7 @@ obj-$(CONFIG_MFD_TPS65090)	+= tps65090.o
 obj-$(CONFIG_MFD_AAT2870_CORE)	+= aat2870-core.o
 obj-$(CONFIG_MFD_INTEL_MSIC)	+= intel_msic.o
 obj-$(CONFIG_MFD_PALMAS)	+= palmas.o
+obj-$(CONFIG_MFD_VIPERBOARD)    += viperboard.o
 obj-$(CONFIG_MFD_RC5T583)	+= rc5t583.o rc5t583-irq.o
 obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o sec-irq.o
 obj-$(CONFIG_MFD_SYSCON)	+= syscon.o
diff --git a/drivers/mfd/viperboard.c b/drivers/mfd/viperboard.c
new file mode 100644
index 000000000000..cd1e2fe95647
--- /dev/null
+++ b/drivers/mfd/viperboard.c
@@ -0,0 +1,129 @@
+/*
+ *  Nano River Technologies viperboard driver
+ *
+ *  This is the core driver for the viperboard. There are cell drivers
+ *  available for I2C, ADC and both GPIOs. SPI is not yet supported.
+ *  The drivers do not support all features the board exposes. See user
+ *  manual of the viperboard.
+ *
+ *  (C) 2012 by Lemonage GmbH
+ *  Author: Lars Poeschel <poeschel@lemonage.de>
+ *  All rights reserved.
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+
+#include <linux/mfd/core.h>
+#include <linux/mfd/viperboard.h>
+
+#include <linux/usb.h>
+
+
+static const struct usb_device_id vprbrd_table[] = {
+	{ USB_DEVICE(0x2058, 0x1005) },   /* Nano River Technologies */
+	{ }                               /* Terminating entry */
+};
+
+MODULE_DEVICE_TABLE(usb, vprbrd_table);
+
+static struct mfd_cell vprbrd_devs[] = {
+};
+
+static int vprbrd_probe(struct usb_interface *interface,
+			      const struct usb_device_id *id)
+{
+	struct vprbrd *vb;
+
+	u16 version = 0;
+	int pipe, ret;
+	unsigned char buf[1];
+
+	/* allocate memory for our device state and initialize it */
+	vb = kzalloc(sizeof(*vb), GFP_KERNEL);
+	if (vb == NULL) {
+		dev_err(&interface->dev, "Out of memory\n");
+		return -ENOMEM;
+	}
+
+	mutex_init(&vb->lock);
+
+	vb->usb_dev = usb_get_dev(interface_to_usbdev(interface));
+
+	/* save our data pointer in this interface device */
+	usb_set_intfdata(interface, vb);
+	dev_set_drvdata(&vb->pdev.dev, vb);
+
+	/* get version information, major first, minor then */
+	pipe = usb_rcvctrlpipe(vb->usb_dev, 0);
+	ret = usb_control_msg(vb->usb_dev, pipe, VPRBRD_USB_REQUEST_MAJOR,
+		VPRBRD_USB_TYPE_IN, 0x0000, 0x0000, buf, 1,
+		VPRBRD_USB_TIMEOUT_MS);
+	if (ret == 1)
+		version = buf[0];
+
+	ret = usb_control_msg(vb->usb_dev, pipe, VPRBRD_USB_REQUEST_MINOR,
+		VPRBRD_USB_TYPE_IN, 0x0000, 0x0000, buf, 1,
+		VPRBRD_USB_TIMEOUT_MS);
+	if (ret == 1) {
+		version <<= 8;
+		version = version | buf[0];
+	}
+
+	dev_info(&interface->dev,
+		 "version %x.%02x found at bus %03d address %03d\n",
+		 version >> 8, version & 0xff,
+		 vb->usb_dev->bus->busnum, vb->usb_dev->devnum);
+
+	ret = mfd_add_devices(&interface->dev, -1, vprbrd_devs,
+				ARRAY_SIZE(vprbrd_devs), NULL, 0, NULL);
+	if (ret != 0) {
+		dev_err(&interface->dev, "Failed to add mfd devices to core.");
+		goto error;
+	}
+
+	return 0;
+
+error:
+	if (vb) {
+		usb_put_dev(vb->usb_dev);
+		kfree(vb);
+	}
+
+	return ret;
+}
+
+static void vprbrd_disconnect(struct usb_interface *interface)
+{
+	struct vprbrd *vb = usb_get_intfdata(interface);
+
+	mfd_remove_devices(&interface->dev);
+	usb_set_intfdata(interface, NULL);
+	usb_put_dev(vb->usb_dev);
+	kfree(vb);
+
+	dev_dbg(&interface->dev, "disconnected\n");
+}
+
+static struct usb_driver vprbrd_driver = {
+	.name		= "viperboard",
+	.probe		= vprbrd_probe,
+	.disconnect	= vprbrd_disconnect,
+	.id_table	= vprbrd_table,
+};
+
+module_usb_driver(vprbrd_driver);
+
+MODULE_DESCRIPTION("Nano River Technologies viperboard mfd core driver");
+MODULE_AUTHOR("Lars Poeschel <poeschel@lemonage.de>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/mfd/viperboard.h b/include/linux/mfd/viperboard.h
new file mode 100644
index 000000000000..0d1342466db5
--- /dev/null
+++ b/include/linux/mfd/viperboard.h
@@ -0,0 +1,105 @@
+/*
+ *  include/linux/mfd/viperboard.h
+ *
+ *  Nano River Technologies viperboard definitions
+ *
+ *  (C) 2012 by Lemonage GmbH
+ *  Author: Lars Poeschel <poeschel@lemonage.de>
+ *  All rights reserved.
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ *
+ */
+
+#ifndef __MFD_VIPERBOARD_H__
+#define __MFD_VIPERBOARD_H__
+
+#include <linux/types.h>
+#include <linux/usb.h>
+
+#define VPRBRD_EP_OUT               0x02
+#define VPRBRD_EP_IN                0x86
+
+#define VPRBRD_I2C_MSG_LEN          512 /* max length of a msg on USB level */
+
+#define VPRBRD_I2C_FREQ_6MHZ        1                        /*   6 MBit/s */
+#define VPRBRD_I2C_FREQ_3MHZ        2                        /*   3 MBit/s */
+#define VPRBRD_I2C_FREQ_1MHZ        3                        /*   1 MBit/s */
+#define VPRBRD_I2C_FREQ_FAST        4                        /* 400 kbit/s */
+#define VPRBRD_I2C_FREQ_400KHZ      VPRBRD_I2C_FREQ_FAST
+#define VPRBRD_I2C_FREQ_200KHZ      5                        /* 200 kbit/s */
+#define VPRBRD_I2C_FREQ_STD         6                        /* 100 kbit/s */
+#define VPRBRD_I2C_FREQ_100KHZ      VPRBRD_I2C_FREQ_STD
+#define VPRBRD_I2C_FREQ_10KHZ       7                        /*  10 kbit/s */
+
+#define VPRBRD_I2C_CMD_WRITE        0x00
+#define VPRBRD_I2C_CMD_READ         0x01
+#define VPRBRD_I2C_CMD_ADDR         0x02
+
+#define VPRBRD_USB_TYPE_OUT	    0x40
+#define VPRBRD_USB_TYPE_IN	    0xc0
+#define VPRBRD_USB_TIMEOUT_MS       100
+#define VPRBRD_USB_REQUEST_MAJOR    0xea
+#define VPRBRD_USB_REQUEST_MINOR    0xeb
+
+struct vprbrd_i2c_write_hdr {
+	u8 cmd;
+	u16 addr;
+	u8 len1;
+	u8 len2;
+	u8 last;
+	u8 chan;
+	u16 spi;
+} __packed;
+
+struct vprbrd_i2c_read_hdr {
+	u8 cmd;
+	u16 addr;
+	u8 len0;
+	u8 len1;
+	u8 len2;
+	u8 len3;
+	u8 len4;
+	u8 len5;
+	u16 tf1;                        /* transfer 1 length */
+	u16 tf2;                        /* transfer 2 length */
+} __packed;
+
+struct vprbrd_i2c_status {
+	u8 unknown[11];
+	u8 status;
+} __packed;
+
+struct vprbrd_i2c_write_msg {
+	struct vprbrd_i2c_write_hdr header;
+	u8 data[VPRBRD_I2C_MSG_LEN
+		- sizeof(struct vprbrd_i2c_write_hdr)];
+} __packed;
+
+struct vprbrd_i2c_read_msg {
+	struct vprbrd_i2c_read_hdr header;
+	u8 data[VPRBRD_I2C_MSG_LEN
+		- sizeof(struct vprbrd_i2c_read_hdr)];
+} __packed;
+
+struct vprbrd_i2c_addr_msg {
+	u8 cmd;
+	u8 addr;
+	u8 unknown1;
+	u16 len;
+	u8 unknown2;
+	u8 unknown3;
+} __packed;
+
+/* Structure to hold all device specific stuff */
+struct vprbrd {
+	struct usb_device *usb_dev; /* the usb device for this device */
+	struct mutex lock;
+	u8 buf[sizeof(struct vprbrd_i2c_write_msg)];
+	struct platform_device pdev;
+};
+
+#endif /* __MFD_VIPERBOARD_H__ */
-- 
cgit v1.2.3-55-g7522


From 9d5b72de0d1627b130fa69c5edf58b5b2df4ca50 Mon Sep 17 00:00:00 2001
From: Lars Poeschel
Date: Mon, 5 Nov 2012 15:48:24 +0100
Subject: gpio: Add viperboard gpio driver

This adds the mfd cell to use the gpio a and gpio b part
of the Nano River Technologies viperboard.

Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/gpio/Kconfig           |  13 ++
 drivers/gpio/Makefile          |   1 +
 drivers/gpio/gpio-viperboard.c | 517 +++++++++++++++++++++++++++++++++++++++++
 drivers/mfd/viperboard.c       |   3 +
 include/linux/mfd/viperboard.h |   2 +
 5 files changed, 536 insertions(+)
 create mode 100644 drivers/gpio/gpio-viperboard.c

(limited to 'include')

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index d055cee36942..c3bbd08bcdc3 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -649,4 +649,17 @@ config GPIO_MSIC
 	  Enable support for GPIO on intel MSIC controllers found in
 	  intel MID devices
 
+comment "USB GPIO expanders:"
+
+config GPIO_VIPERBOARD
+	tristate "Viperboard GPIO a & b support"
+	depends on MFD_VIPERBOARD && USB
+	help
+	  Say yes here to access the GPIO signals of Nano River
+	  Technologies Viperboard. There are two GPIO chips on the
+	  board: gpioa and gpiob.
+          See viperboard API specification and Nano
+          River Tech's viperboard.h for detailed meaning
+          of the module parameters.
+
 endif
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 9aeed6707326..16a1385226e9 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -71,6 +71,7 @@ obj-$(CONFIG_GPIO_TPS65912)	+= gpio-tps65912.o
 obj-$(CONFIG_GPIO_TWL4030)	+= gpio-twl4030.o
 obj-$(CONFIG_GPIO_TWL6040)	+= gpio-twl6040.o
 obj-$(CONFIG_GPIO_UCB1400)	+= gpio-ucb1400.o
+obj-$(CONFIG_GPIO_VIPERBOARD)	+= gpio-viperboard.o
 obj-$(CONFIG_GPIO_VR41XX)	+= gpio-vr41xx.o
 obj-$(CONFIG_GPIO_VT8500)	+= gpio-vt8500.o
 obj-$(CONFIG_GPIO_VX855)	+= gpio-vx855.o
diff --git a/drivers/gpio/gpio-viperboard.c b/drivers/gpio/gpio-viperboard.c
new file mode 100644
index 000000000000..13772996cf24
--- /dev/null
+++ b/drivers/gpio/gpio-viperboard.c
@@ -0,0 +1,517 @@
+/*
+ *  Nano River Technologies viperboard GPIO lib driver
+ *
+ *  (C) 2012 by Lemonage GmbH
+ *  Author: Lars Poeschel <poeschel@lemonage.de>
+ *  All rights reserved.
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the	License, or (at your
+ *  option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+
+#include <linux/usb.h>
+#include <linux/gpio.h>
+
+#include <linux/mfd/viperboard.h>
+
+#define VPRBRD_GPIOA_CLK_1MHZ		0
+#define VPRBRD_GPIOA_CLK_100KHZ		1
+#define VPRBRD_GPIOA_CLK_10KHZ		2
+#define VPRBRD_GPIOA_CLK_1KHZ		3
+#define VPRBRD_GPIOA_CLK_100HZ		4
+#define VPRBRD_GPIOA_CLK_10HZ		5
+
+#define VPRBRD_GPIOA_FREQ_DEFAULT	1000
+
+#define VPRBRD_GPIOA_CMD_CONT		0x00
+#define VPRBRD_GPIOA_CMD_PULSE		0x01
+#define VPRBRD_GPIOA_CMD_PWM		0x02
+#define VPRBRD_GPIOA_CMD_SETOUT		0x03
+#define VPRBRD_GPIOA_CMD_SETIN		0x04
+#define VPRBRD_GPIOA_CMD_SETINT		0x05
+#define VPRBRD_GPIOA_CMD_GETIN		0x06
+
+#define VPRBRD_GPIOB_CMD_SETDIR		0x00
+#define VPRBRD_GPIOB_CMD_SETVAL		0x01
+
+struct vprbrd_gpioa_msg {
+	u8 cmd;
+	u8 clk;
+	u8 offset;
+	u8 t1;
+	u8 t2;
+	u8 invert;
+	u8 pwmlevel;
+	u8 outval;
+	u8 risefall;
+	u8 answer;
+	u8 __fill;
+} __packed;
+
+struct vprbrd_gpiob_msg {
+	u8 cmd;
+	u16 val;
+	u16 mask;
+} __packed;
+
+struct vprbrd_gpio {
+	struct gpio_chip gpioa; /* gpio a related things */
+	u32 gpioa_out;
+	u32 gpioa_val;
+	struct gpio_chip gpiob; /* gpio b related things */
+	u32 gpiob_out;
+	u32 gpiob_val;
+	struct vprbrd *vb;
+};
+
+/* gpioa sampling clock module parameter */
+static unsigned char gpioa_clk;
+static unsigned int gpioa_freq = VPRBRD_GPIOA_FREQ_DEFAULT;
+module_param(gpioa_freq, uint, 0);
+MODULE_PARM_DESC(gpioa_freq,
+	"gpio-a sampling freq in Hz (default is 1000Hz) valid values: 10, 100, 1000, 10000, 100000, 1000000");
+
+/* ----- begin of gipo a chip -------------------------------------------- */
+
+static int vprbrd_gpioa_get(struct gpio_chip *chip,
+		unsigned offset)
+{
+	int ret, answer, error = 0;
+	struct vprbrd_gpio *gpio =
+			container_of(chip, struct vprbrd_gpio, gpioa);
+	struct vprbrd *vb = gpio->vb;
+	struct vprbrd_gpioa_msg *gamsg = (struct vprbrd_gpioa_msg *)vb->buf;
+
+	/* if io is set to output, just return the saved value */
+	if (gpio->gpioa_out & (1 << offset))
+		return gpio->gpioa_val & (1 << offset);
+
+	mutex_lock(&vb->lock);
+
+	gamsg->cmd = VPRBRD_GPIOA_CMD_GETIN;
+	gamsg->clk = 0x00;
+	gamsg->offset = offset;
+	gamsg->t1 = 0x00;
+	gamsg->t2 = 0x00;
+	gamsg->invert = 0x00;
+	gamsg->pwmlevel = 0x00;
+	gamsg->outval = 0x00;
+	gamsg->risefall = 0x00;
+	gamsg->answer = 0x00;
+	gamsg->__fill = 0x00;
+
+	ret = usb_control_msg(vb->usb_dev, usb_sndctrlpipe(vb->usb_dev, 0),
+		VPRBRD_USB_REQUEST_GPIOA, VPRBRD_USB_TYPE_OUT, 0x0000,
+		0x0000, gamsg, sizeof(struct vprbrd_gpioa_msg),
+		VPRBRD_USB_TIMEOUT_MS);
+	if (ret != sizeof(struct vprbrd_gpioa_msg))
+		error = -EREMOTEIO;
+
+	ret = usb_control_msg(vb->usb_dev, usb_rcvctrlpipe(vb->usb_dev, 0),
+		VPRBRD_USB_REQUEST_GPIOA, VPRBRD_USB_TYPE_IN, 0x0000,
+		0x0000, gamsg, sizeof(struct vprbrd_gpioa_msg),
+		VPRBRD_USB_TIMEOUT_MS);
+	answer = gamsg->answer & 0x01;
+
+	mutex_unlock(&vb->lock);
+
+	if (ret != sizeof(struct vprbrd_gpioa_msg))
+		error = -EREMOTEIO;
+
+	if (error)
+		return error;
+
+	return answer;
+}
+
+static void vprbrd_gpioa_set(struct gpio_chip *chip,
+		unsigned offset, int value)
+{
+	int ret;
+	struct vprbrd_gpio *gpio =
+			container_of(chip, struct vprbrd_gpio, gpioa);
+	struct vprbrd *vb = gpio->vb;
+	struct vprbrd_gpioa_msg *gamsg = (struct vprbrd_gpioa_msg *)vb->buf;
+
+	if (gpio->gpioa_out & (1 << offset)) {
+		if (value)
+			gpio->gpioa_val |= (1 << offset);
+		else
+			gpio->gpioa_val &= ~(1 << offset);
+
+		mutex_lock(&vb->lock);
+
+		gamsg->cmd = VPRBRD_GPIOA_CMD_SETOUT;
+		gamsg->clk = 0x00;
+		gamsg->offset = offset;
+		gamsg->t1 = 0x00;
+		gamsg->t2 = 0x00;
+		gamsg->invert = 0x00;
+		gamsg->pwmlevel = 0x00;
+		gamsg->outval = value;
+		gamsg->risefall = 0x00;
+		gamsg->answer = 0x00;
+		gamsg->__fill = 0x00;
+
+		ret = usb_control_msg(vb->usb_dev,
+			usb_sndctrlpipe(vb->usb_dev, 0),
+			VPRBRD_USB_REQUEST_GPIOA, VPRBRD_USB_TYPE_OUT,
+			0x0000,	0x0000, gamsg,
+			sizeof(struct vprbrd_gpioa_msg), VPRBRD_USB_TIMEOUT_MS);
+
+		mutex_unlock(&vb->lock);
+
+		if (ret != sizeof(struct vprbrd_gpioa_msg))
+			dev_err(chip->dev, "usb error setting pin value\n");
+	}
+}
+
+static int vprbrd_gpioa_direction_input(struct gpio_chip *chip,
+			unsigned offset)
+{
+	int ret;
+	struct vprbrd_gpio *gpio =
+			container_of(chip, struct vprbrd_gpio, gpioa);
+	struct vprbrd *vb = gpio->vb;
+	struct vprbrd_gpioa_msg *gamsg = (struct vprbrd_gpioa_msg *)vb->buf;
+
+	gpio->gpioa_out &= ~(1 << offset);
+
+	mutex_lock(&vb->lock);
+
+	gamsg->cmd = VPRBRD_GPIOA_CMD_SETIN;
+	gamsg->clk = gpioa_clk;
+	gamsg->offset = offset;
+	gamsg->t1 = 0x00;
+	gamsg->t2 = 0x00;
+	gamsg->invert = 0x00;
+	gamsg->pwmlevel = 0x00;
+	gamsg->outval = 0x00;
+	gamsg->risefall = 0x00;
+	gamsg->answer = 0x00;
+	gamsg->__fill = 0x00;
+
+	ret = usb_control_msg(vb->usb_dev, usb_sndctrlpipe(vb->usb_dev, 0),
+		VPRBRD_USB_REQUEST_GPIOA, VPRBRD_USB_TYPE_OUT, 0x0000,
+		0x0000, gamsg, sizeof(struct vprbrd_gpioa_msg),
+		VPRBRD_USB_TIMEOUT_MS);
+
+	mutex_unlock(&vb->lock);
+
+	if (ret != sizeof(struct vprbrd_gpioa_msg))
+		return -EREMOTEIO;
+
+	return 0;
+}
+
+static int vprbrd_gpioa_direction_output(struct gpio_chip *chip,
+			unsigned offset, int value)
+{
+	int ret;
+	struct vprbrd_gpio *gpio =
+			container_of(chip, struct vprbrd_gpio, gpioa);
+	struct vprbrd *vb = gpio->vb;
+	struct vprbrd_gpioa_msg *gamsg = (struct vprbrd_gpioa_msg *)vb->buf;
+
+	gpio->gpioa_out |= (1 << offset);
+	if (value)
+		gpio->gpioa_val |= (1 << offset);
+	else
+		gpio->gpioa_val &= ~(1 << offset);
+
+	mutex_lock(&vb->lock);
+
+	gamsg->cmd = VPRBRD_GPIOA_CMD_SETOUT;
+	gamsg->clk = 0x00;
+	gamsg->offset = offset;
+	gamsg->t1 = 0x00;
+	gamsg->t2 = 0x00;
+	gamsg->invert = 0x00;
+	gamsg->pwmlevel = 0x00;
+	gamsg->outval = value;
+	gamsg->risefall = 0x00;
+	gamsg->answer = 0x00;
+	gamsg->__fill = 0x00;
+
+	ret = usb_control_msg(vb->usb_dev, usb_sndctrlpipe(vb->usb_dev, 0),
+		VPRBRD_USB_REQUEST_GPIOA, VPRBRD_USB_TYPE_OUT, 0x0000,
+		0x0000, gamsg, sizeof(struct vprbrd_gpioa_msg),
+		VPRBRD_USB_TIMEOUT_MS);
+
+	mutex_unlock(&vb->lock);
+
+	if (ret != sizeof(struct vprbrd_gpioa_msg))
+		return -EREMOTEIO;
+
+	return 0;
+}
+
+/* ----- end of gpio a chip ---------------------------------------------- */
+
+/* ----- begin of gipo b chip -------------------------------------------- */
+
+static int vprbrd_gpiob_setdir(struct vprbrd *vb, unsigned offset,
+	unsigned dir)
+{
+	struct vprbrd_gpiob_msg *gbmsg = (struct vprbrd_gpiob_msg *)vb->buf;
+	int ret;
+
+	gbmsg->cmd = VPRBRD_GPIOB_CMD_SETDIR;
+	gbmsg->val = cpu_to_be16(dir << offset);
+	gbmsg->mask = cpu_to_be16(0x0001 << offset);
+
+	ret = usb_control_msg(vb->usb_dev, usb_sndctrlpipe(vb->usb_dev, 0),
+		VPRBRD_USB_REQUEST_GPIOB, VPRBRD_USB_TYPE_OUT, 0x0000,
+		0x0000, gbmsg, sizeof(struct vprbrd_gpiob_msg),
+		VPRBRD_USB_TIMEOUT_MS);
+
+	if (ret != sizeof(struct vprbrd_gpiob_msg))
+		return -EREMOTEIO;
+
+	return 0;
+}
+
+static int vprbrd_gpiob_get(struct gpio_chip *chip,
+		unsigned offset)
+{
+	int ret;
+	u16 val;
+	struct vprbrd_gpio *gpio =
+			container_of(chip, struct vprbrd_gpio, gpiob);
+	struct vprbrd *vb = gpio->vb;
+	struct vprbrd_gpiob_msg *gbmsg = (struct vprbrd_gpiob_msg *)vb->buf;
+
+	/* if io is set to output, just return the saved value */
+	if (gpio->gpiob_out & (1 << offset))
+		return gpio->gpiob_val & (1 << offset);
+
+	mutex_lock(&vb->lock);
+
+	ret = usb_control_msg(vb->usb_dev, usb_rcvctrlpipe(vb->usb_dev, 0),
+		VPRBRD_USB_REQUEST_GPIOB, VPRBRD_USB_TYPE_IN, 0x0000,
+		0x0000, gbmsg,	sizeof(struct vprbrd_gpiob_msg),
+		VPRBRD_USB_TIMEOUT_MS);
+	val = gbmsg->val;
+
+	mutex_unlock(&vb->lock);
+
+	if (ret != sizeof(struct vprbrd_gpiob_msg))
+		return ret;
+
+	/* cache the read values */
+	gpio->gpiob_val = be16_to_cpu(val);
+
+	return (gpio->gpiob_val >> offset) & 0x1;
+}
+
+static void vprbrd_gpiob_set(struct gpio_chip *chip,
+		unsigned offset, int value)
+{
+	int ret;
+	struct vprbrd_gpio *gpio =
+			container_of(chip, struct vprbrd_gpio, gpiob);
+	struct vprbrd *vb = gpio->vb;
+	struct vprbrd_gpiob_msg *gbmsg = (struct vprbrd_gpiob_msg *)vb->buf;
+
+	if (gpio->gpiob_out & (1 << offset)) {
+		if (value)
+			gpio->gpiob_val |= (1 << offset);
+		else
+			gpio->gpiob_val &= ~(1 << offset);
+
+		mutex_lock(&vb->lock);
+
+		gbmsg->cmd = VPRBRD_GPIOB_CMD_SETVAL;
+		gbmsg->val = cpu_to_be16(value << offset);
+		gbmsg->mask = cpu_to_be16(0x0001 << offset);
+
+		ret = usb_control_msg(vb->usb_dev,
+			usb_sndctrlpipe(vb->usb_dev, 0),
+			VPRBRD_USB_REQUEST_GPIOB, VPRBRD_USB_TYPE_OUT,
+			0x0000,	0x0000, gbmsg,
+			sizeof(struct vprbrd_gpiob_msg), VPRBRD_USB_TIMEOUT_MS);
+
+		mutex_unlock(&vb->lock);
+
+		if (ret != sizeof(struct vprbrd_gpiob_msg))
+			dev_err(chip->dev, "usb error setting pin value\n");
+	}
+}
+
+static int vprbrd_gpiob_direction_input(struct gpio_chip *chip,
+			unsigned offset)
+{
+	int ret;
+	struct vprbrd_gpio *gpio =
+			container_of(chip, struct vprbrd_gpio, gpiob);
+	struct vprbrd *vb = gpio->vb;
+
+	gpio->gpiob_out &= ~(1 << offset);
+
+	mutex_lock(&vb->lock);
+
+	ret = vprbrd_gpiob_setdir(vb, offset, 0);
+
+	mutex_unlock(&vb->lock);
+
+	if (ret)
+		dev_err(chip->dev, "usb error setting pin to input\n");
+
+	return ret;
+}
+
+static int vprbrd_gpiob_direction_output(struct gpio_chip *chip,
+			unsigned offset, int value)
+{
+	int ret;
+	struct vprbrd_gpio *gpio =
+			container_of(chip, struct vprbrd_gpio, gpiob);
+	struct vprbrd *vb = gpio->vb;
+
+	gpio->gpiob_out |= (1 << offset);
+	if (value)
+		gpio->gpiob_val |= (1 << offset);
+	else
+		gpio->gpiob_val &= ~(1 << offset);
+
+	mutex_lock(&vb->lock);
+
+	ret = vprbrd_gpiob_setdir(vb, offset, 1);
+	if (ret)
+		dev_err(chip->dev, "usb error setting pin to output\n");
+
+	mutex_unlock(&vb->lock);
+
+	vprbrd_gpiob_set(chip, offset, value);
+
+	return ret;
+}
+
+/* ----- end of gpio b chip ---------------------------------------------- */
+
+static int __devinit vprbrd_gpio_probe(struct platform_device *pdev)
+{
+	struct vprbrd *vb = dev_get_drvdata(pdev->dev.parent);
+	struct vprbrd_gpio *vb_gpio;
+	int ret;
+
+	vb_gpio = devm_kzalloc(&pdev->dev, sizeof(*vb_gpio), GFP_KERNEL);
+	if (vb_gpio == NULL)
+		return -ENOMEM;
+
+	vb_gpio->vb = vb;
+	/* registering gpio a */
+	vb_gpio->gpioa.label = "viperboard gpio a";
+	vb_gpio->gpioa.dev = &pdev->dev;
+	vb_gpio->gpioa.owner = THIS_MODULE;
+	vb_gpio->gpioa.base = -1;
+	vb_gpio->gpioa.ngpio = 16;
+	vb_gpio->gpioa.can_sleep = 1;
+	vb_gpio->gpioa.set = vprbrd_gpioa_set;
+	vb_gpio->gpioa.get = vprbrd_gpioa_get;
+	vb_gpio->gpioa.direction_input = vprbrd_gpioa_direction_input;
+	vb_gpio->gpioa.direction_output = vprbrd_gpioa_direction_output;
+	ret = gpiochip_add(&vb_gpio->gpioa);
+	if (ret < 0) {
+		dev_err(vb_gpio->gpioa.dev, "could not add gpio a");
+		goto err_gpioa;
+	}
+
+	/* registering gpio b */
+	vb_gpio->gpiob.label = "viperboard gpio b";
+	vb_gpio->gpiob.dev = &pdev->dev;
+	vb_gpio->gpiob.owner = THIS_MODULE;
+	vb_gpio->gpiob.base = -1;
+	vb_gpio->gpiob.ngpio = 16;
+	vb_gpio->gpiob.can_sleep = 1;
+	vb_gpio->gpiob.set = vprbrd_gpiob_set;
+	vb_gpio->gpiob.get = vprbrd_gpiob_get;
+	vb_gpio->gpiob.direction_input = vprbrd_gpiob_direction_input;
+	vb_gpio->gpiob.direction_output = vprbrd_gpiob_direction_output;
+	ret = gpiochip_add(&vb_gpio->gpiob);
+	if (ret < 0) {
+		dev_err(vb_gpio->gpiob.dev, "could not add gpio b");
+		goto err_gpiob;
+	}
+
+	platform_set_drvdata(pdev, vb_gpio);
+
+	return ret;
+
+err_gpiob:
+	ret = gpiochip_remove(&vb_gpio->gpioa);
+
+err_gpioa:
+	return ret;
+}
+
+static int __devexit vprbrd_gpio_remove(struct platform_device *pdev)
+{
+	struct vprbrd_gpio *vb_gpio = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = gpiochip_remove(&vb_gpio->gpiob);
+	if (ret == 0)
+		ret = gpiochip_remove(&vb_gpio->gpioa);
+
+	return ret;
+}
+
+static struct platform_driver vprbrd_gpio_driver = {
+	.driver.name	= "viperboard-gpio",
+	.driver.owner	= THIS_MODULE,
+	.probe		= vprbrd_gpio_probe,
+	.remove		= __devexit_p(vprbrd_gpio_remove),
+};
+
+static int __init vprbrd_gpio_init(void)
+{
+	switch (gpioa_freq) {
+	case 1000000:
+		gpioa_clk = VPRBRD_GPIOA_CLK_1MHZ;
+		break;
+	case 100000:
+		gpioa_clk = VPRBRD_GPIOA_CLK_100KHZ;
+		break;
+	case 10000:
+		gpioa_clk = VPRBRD_GPIOA_CLK_10KHZ;
+		break;
+	case 1000:
+		gpioa_clk = VPRBRD_GPIOA_CLK_1KHZ;
+		break;
+	case 100:
+		gpioa_clk = VPRBRD_GPIOA_CLK_100HZ;
+		break;
+	case 10:
+		gpioa_clk = VPRBRD_GPIOA_CLK_10HZ;
+		break;
+	default:
+		pr_warn("invalid gpioa_freq (%d)\n", gpioa_freq);
+		gpioa_clk = VPRBRD_GPIOA_CLK_1KHZ;
+	}
+
+	return platform_driver_register(&vprbrd_gpio_driver);
+}
+subsys_initcall(vprbrd_gpio_init);
+
+static void __exit vprbrd_gpio_exit(void)
+{
+	platform_driver_unregister(&vprbrd_gpio_driver);
+}
+module_exit(vprbrd_gpio_exit);
+
+MODULE_AUTHOR("Lars Poeschel <poeschel@lemonage.de>");
+MODULE_DESCRIPTION("GPIO driver for Nano River Techs Viperboard");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:viperboard-gpio");
diff --git a/drivers/mfd/viperboard.c b/drivers/mfd/viperboard.c
index cd1e2fe95647..c75ac08f639c 100644
--- a/drivers/mfd/viperboard.c
+++ b/drivers/mfd/viperboard.c
@@ -38,6 +38,9 @@ static const struct usb_device_id vprbrd_table[] = {
 MODULE_DEVICE_TABLE(usb, vprbrd_table);
 
 static struct mfd_cell vprbrd_devs[] = {
+	{
+		.name = "viperboard-gpio",
+	},
 };
 
 static int vprbrd_probe(struct usb_interface *interface,
diff --git a/include/linux/mfd/viperboard.h b/include/linux/mfd/viperboard.h
index 0d1342466db5..42d339fac3e5 100644
--- a/include/linux/mfd/viperboard.h
+++ b/include/linux/mfd/viperboard.h
@@ -44,6 +44,8 @@
 #define VPRBRD_USB_TIMEOUT_MS       100
 #define VPRBRD_USB_REQUEST_MAJOR    0xea
 #define VPRBRD_USB_REQUEST_MINOR    0xeb
+#define VPRBRD_USB_REQUEST_GPIOA    0xed
+#define VPRBRD_USB_REQUEST_GPIOB    0xdd
 
 struct vprbrd_i2c_write_hdr {
 	u8 cmd;
-- 
cgit v1.2.3-55-g7522


From 174a13aa8669331605b138aaf61569dd7189e453 Mon Sep 17 00:00:00 2001
From: Lars Poeschel
Date: Mon, 19 Nov 2012 16:36:04 +0100
Subject: i2c: Add viperboard i2c master driver

This adds the mfd cell to use the i2c part of the Nano River Technologies
viperboard as i2c master.

Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/i2c/busses/Kconfig          |  10 +
 drivers/i2c/busses/Makefile         |   1 +
 drivers/i2c/busses/i2c-viperboard.c | 480 ++++++++++++++++++++++++++++++++++++
 drivers/mfd/viperboard.c            |   3 +
 include/linux/mfd/viperboard.h      |   2 +
 5 files changed, 496 insertions(+)
 create mode 100644 drivers/i2c/busses/i2c-viperboard.c

(limited to 'include')

diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index e9df4612b7eb..c7bff51fe524 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -818,6 +818,16 @@ config I2C_TINY_USB
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-tiny-usb.
 
+config I2C_VIPERBOARD
+	tristate "Viperboard I2C master support"
+	depends on MFD_VIPERBOARD && USB
+	help
+	  Say yes here to access the I2C part of the Nano River
+	  Technologies Viperboard as I2C master.
+          See viperboard API specification and Nano
+          River Tech's viperboard.h for detailed meaning
+          of the module parameters.
+
 comment "Other I2C/SMBus bus drivers"
 
 config I2C_ACORN
diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile
index 395b516ffa08..e5cb209d276c 100644
--- a/drivers/i2c/busses/Makefile
+++ b/drivers/i2c/busses/Makefile
@@ -79,6 +79,7 @@ obj-$(CONFIG_I2C_PARPORT)	+= i2c-parport.o
 obj-$(CONFIG_I2C_PARPORT_LIGHT)	+= i2c-parport-light.o
 obj-$(CONFIG_I2C_TAOS_EVM)	+= i2c-taos-evm.o
 obj-$(CONFIG_I2C_TINY_USB)	+= i2c-tiny-usb.o
+obj-$(CONFIG_I2C_VIPERBOARD)	+= i2c-viperboard.o
 
 # Other I2C/SMBus bus drivers
 obj-$(CONFIG_I2C_ACORN)		+= i2c-acorn.o
diff --git a/drivers/i2c/busses/i2c-viperboard.c b/drivers/i2c/busses/i2c-viperboard.c
new file mode 100644
index 000000000000..f5fa20dea906
--- /dev/null
+++ b/drivers/i2c/busses/i2c-viperboard.c
@@ -0,0 +1,480 @@
+/*
+ *  Nano River Technologies viperboard i2c master driver
+ *
+ *  (C) 2012 by Lemonage GmbH
+ *  Author: Lars Poeschel <poeschel@lemonage.de>
+ *  All rights reserved.
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the	License, or (at your
+ *  option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+
+#include <linux/usb.h>
+#include <linux/i2c.h>
+
+#include <linux/mfd/viperboard.h>
+
+struct vprbrd_i2c {
+	struct i2c_adapter i2c;
+	u8 bus_freq_param;
+};
+
+/* i2c bus frequency module parameter */
+static u8 i2c_bus_param;
+static unsigned int i2c_bus_freq = 100;
+module_param(i2c_bus_freq, int, 0);
+MODULE_PARM_DESC(i2c_bus_freq,
+	"i2c bus frequency in khz (default is 100) valid values: 10, 100, 200, 400, 1000, 3000, 6000");
+
+static int vprbrd_i2c_status(struct i2c_adapter *i2c,
+	struct vprbrd_i2c_status *status, bool prev_error)
+{
+	u16 bytes_xfer;
+	int ret;
+	struct vprbrd *vb = (struct vprbrd *)i2c->algo_data;
+
+	/* check for protocol error */
+	bytes_xfer = sizeof(struct vprbrd_i2c_status);
+
+	ret = usb_control_msg(vb->usb_dev, usb_rcvctrlpipe(vb->usb_dev, 0),
+		VPRBRD_USB_REQUEST_I2C, VPRBRD_USB_TYPE_IN, 0x0000, 0x0000,
+		status, bytes_xfer, VPRBRD_USB_TIMEOUT_MS);
+
+	if (ret != bytes_xfer)
+		prev_error = true;
+
+	if (prev_error) {
+		dev_err(&i2c->dev, "failure in usb communication\n");
+		return -EREMOTEIO;
+	}
+
+	dev_dbg(&i2c->dev, "  status = %d\n", status->status);
+	if (status->status != 0x00) {
+		dev_err(&i2c->dev, "failure: i2c protocol error\n");
+		return -EPROTO;
+	}
+	return 0;
+}
+
+static int vprbrd_i2c_receive(struct usb_device *usb_dev,
+	struct vprbrd_i2c_read_msg *rmsg, int bytes_xfer)
+{
+	int ret, bytes_actual;
+	int error = 0;
+
+	/* send the read request */
+	ret = usb_bulk_msg(usb_dev,
+		usb_sndbulkpipe(usb_dev, VPRBRD_EP_OUT), rmsg,
+		sizeof(struct vprbrd_i2c_read_hdr), &bytes_actual,
+		VPRBRD_USB_TIMEOUT_MS);
+
+	if ((ret < 0)
+		|| (bytes_actual != sizeof(struct vprbrd_i2c_read_hdr))) {
+		dev_err(&usb_dev->dev, "failure transmitting usb\n");
+		error = -EREMOTEIO;
+	}
+
+	/* read the actual data */
+	ret = usb_bulk_msg(usb_dev,
+		usb_rcvbulkpipe(usb_dev, VPRBRD_EP_IN), rmsg,
+		bytes_xfer, &bytes_actual, VPRBRD_USB_TIMEOUT_MS);
+
+	if ((ret < 0) || (bytes_xfer != bytes_actual)) {
+		dev_err(&usb_dev->dev, "failure receiving usb\n");
+		error = -EREMOTEIO;
+	}
+	return error;
+}
+
+static int vprbrd_i2c_addr(struct usb_device *usb_dev,
+	struct vprbrd_i2c_addr_msg *amsg)
+{
+	int ret, bytes_actual;
+
+	ret = usb_bulk_msg(usb_dev,
+		usb_sndbulkpipe(usb_dev, VPRBRD_EP_OUT), amsg,
+		sizeof(struct vprbrd_i2c_addr_msg), &bytes_actual,
+		VPRBRD_USB_TIMEOUT_MS);
+
+	if ((ret < 0) ||
+			(sizeof(struct vprbrd_i2c_addr_msg) != bytes_actual)) {
+		dev_err(&usb_dev->dev, "failure transmitting usb\n");
+		return -EREMOTEIO;
+	}
+	return 0;
+}
+
+static int vprbrd_i2c_read(struct vprbrd *vb, struct i2c_msg *msg)
+{
+	int ret;
+	u16 remain_len, bytes_xfer, len1, len2,
+		start = 0x0000;
+	struct vprbrd_i2c_read_msg *rmsg =
+		(struct vprbrd_i2c_read_msg *)vb->buf;
+
+	remain_len = msg->len;
+	rmsg->header.cmd = VPRBRD_I2C_CMD_READ;
+	while (remain_len > 0) {
+		rmsg->header.addr = cpu_to_le16(start + 0x4000);
+		if (remain_len <= 255) {
+			len1 = remain_len;
+			len2 = 0x00;
+			rmsg->header.len0 = remain_len;
+			rmsg->header.len1 = 0x00;
+			rmsg->header.len2 = 0x00;
+			rmsg->header.len3 = 0x00;
+			rmsg->header.len4 = 0x00;
+			rmsg->header.len5 = 0x00;
+			remain_len = 0;
+		} else if (remain_len <= 510) {
+			len1 = remain_len;
+			len2 = 0x00;
+			rmsg->header.len0 = remain_len - 255;
+			rmsg->header.len1 = 0xff;
+			rmsg->header.len2 = 0x00;
+			rmsg->header.len3 = 0x00;
+			rmsg->header.len4 = 0x00;
+			rmsg->header.len5 = 0x00;
+			remain_len = 0;
+		} else if (remain_len <= 512) {
+			len1 = remain_len;
+			len2 = 0x00;
+			rmsg->header.len0 = remain_len - 510;
+			rmsg->header.len1 = 0xff;
+			rmsg->header.len2 = 0xff;
+			rmsg->header.len3 = 0x00;
+			rmsg->header.len4 = 0x00;
+			rmsg->header.len5 = 0x00;
+			remain_len = 0;
+		} else if (remain_len <= 767) {
+			len1 = 512;
+			len2 = remain_len - 512;
+			rmsg->header.len0 = 0x02;
+			rmsg->header.len1 = 0xff;
+			rmsg->header.len2 = 0xff;
+			rmsg->header.len3 = remain_len - 512;
+			rmsg->header.len4 = 0x00;
+			rmsg->header.len5 = 0x00;
+			bytes_xfer = remain_len;
+			remain_len = 0;
+		} else if (remain_len <= 1022) {
+			len1 = 512;
+			len2 = remain_len - 512;
+			rmsg->header.len0 = 0x02;
+			rmsg->header.len1 = 0xff;
+			rmsg->header.len2 = 0xff;
+			rmsg->header.len3 = remain_len - 767;
+			rmsg->header.len4 = 0xff;
+			rmsg->header.len5 = 0x00;
+			remain_len = 0;
+		} else if (remain_len <= 1024) {
+			len1 = 512;
+			len2 = remain_len - 512;
+			rmsg->header.len0 = 0x02;
+			rmsg->header.len1 = 0xff;
+			rmsg->header.len2 = 0xff;
+			rmsg->header.len3 = remain_len - 1022;
+			rmsg->header.len4 = 0xff;
+			rmsg->header.len5 = 0xff;
+			remain_len = 0;
+		} else {
+			len1 = 512;
+			len2 = 512;
+			rmsg->header.len0 = 0x02;
+			rmsg->header.len1 = 0xff;
+			rmsg->header.len2 = 0xff;
+			rmsg->header.len3 = 0x02;
+			rmsg->header.len4 = 0xff;
+			rmsg->header.len5 = 0xff;
+			remain_len -= 1024;
+			start += 1024;
+		}
+		rmsg->header.tf1 = cpu_to_le16(len1);
+		rmsg->header.tf2 = cpu_to_le16(len2);
+
+		/* first read transfer */
+		ret = vprbrd_i2c_receive(vb->usb_dev, rmsg, len1);
+		if (ret < 0)
+			return ret;
+		/* copy the received data */
+		memcpy(msg->buf + start, rmsg, len1);
+
+		/* second read transfer if neccessary */
+		if (len2 > 0) {
+			ret = vprbrd_i2c_receive(vb->usb_dev, rmsg, len2);
+			if (ret < 0)
+				return ret;
+			/* copy the received data */
+			memcpy(msg->buf + start + 512, rmsg, len2);
+		}
+	}
+	return 0;
+}
+
+static int vprbrd_i2c_write(struct vprbrd *vb, struct i2c_msg *msg)
+{
+	int ret, bytes_actual;
+	u16 remain_len, bytes_xfer,
+		start = 0x0000;
+	struct vprbrd_i2c_write_msg *wmsg =
+		(struct vprbrd_i2c_write_msg *)vb->buf;
+
+	remain_len = msg->len;
+	wmsg->header.cmd = VPRBRD_I2C_CMD_WRITE;
+	wmsg->header.last = 0x00;
+	wmsg->header.chan = 0x00;
+	wmsg->header.spi = 0x0000;
+	while (remain_len > 0) {
+		wmsg->header.addr = cpu_to_le16(start + 0x4000);
+		if (remain_len > 503) {
+			wmsg->header.len1 = 0xff;
+			wmsg->header.len2 = 0xf8;
+			remain_len -= 503;
+			bytes_xfer = 503 + sizeof(struct vprbrd_i2c_write_hdr);
+			start += 503;
+		} else if (remain_len > 255) {
+			wmsg->header.len1 = 0xff;
+			wmsg->header.len2 = (remain_len - 255);
+			bytes_xfer = remain_len +
+				sizeof(struct vprbrd_i2c_write_hdr);
+			remain_len = 0;
+		} else {
+			wmsg->header.len1 = remain_len;
+			wmsg->header.len2 = 0x00;
+			bytes_xfer = remain_len +
+				sizeof(struct vprbrd_i2c_write_hdr);
+			remain_len = 0;
+		}
+		memcpy(wmsg->data, msg->buf + start,
+			bytes_xfer - sizeof(struct vprbrd_i2c_write_hdr));
+
+		ret = usb_bulk_msg(vb->usb_dev,
+			usb_sndbulkpipe(vb->usb_dev,
+			VPRBRD_EP_OUT), wmsg,
+			bytes_xfer, &bytes_actual, VPRBRD_USB_TIMEOUT_MS);
+		if ((ret < 0) || (bytes_xfer != bytes_actual))
+			return -EREMOTEIO;
+	}
+	return 0;
+}
+
+static int vprbrd_i2c_xfer(struct i2c_adapter *i2c, struct i2c_msg *msgs,
+		int num)
+{
+	struct i2c_msg *pmsg;
+	int i, ret,
+		error = 0;
+	struct vprbrd *vb = (struct vprbrd *)i2c->algo_data;
+	struct vprbrd_i2c_addr_msg *amsg =
+		(struct vprbrd_i2c_addr_msg *)vb->buf;
+	struct vprbrd_i2c_status *smsg = (struct vprbrd_i2c_status *)vb->buf;
+
+	dev_dbg(&i2c->dev, "master xfer %d messages:\n", num);
+
+	for (i = 0 ; i < num ; i++) {
+		pmsg = &msgs[i];
+
+		dev_dbg(&i2c->dev,
+			"  %d: %s (flags %d) %d bytes to 0x%02x\n",
+			i, pmsg->flags & I2C_M_RD ? "read" : "write",
+			pmsg->flags, pmsg->len, pmsg->addr);
+
+		/* msgs longer than 2048 bytes are not supported by adapter */
+		if (pmsg->len > 2048)
+			return -EINVAL;
+
+		mutex_lock(&vb->lock);
+		/* directly send the message */
+		if (pmsg->flags & I2C_M_RD) {
+			/* read data */
+			amsg->cmd = VPRBRD_I2C_CMD_ADDR;
+			amsg->unknown2 = 0x00;
+			amsg->unknown3 = 0x00;
+			amsg->addr = pmsg->addr;
+			amsg->unknown1 = 0x01;
+			amsg->len = cpu_to_le16(pmsg->len);
+			/* send the addr and len, we're interested to board */
+			ret = vprbrd_i2c_addr(vb->usb_dev, amsg);
+			if (ret < 0)
+				error = ret;
+
+			ret = vprbrd_i2c_read(vb, pmsg);
+			if (ret < 0)
+				error = ret;
+
+			ret = vprbrd_i2c_status(i2c, smsg, error);
+			if (ret < 0)
+				error = ret;
+			/* in case of protocol error, return the error */
+			if (error < 0)
+				goto error;
+		} else {
+			/* write data */
+			ret = vprbrd_i2c_write(vb, pmsg);
+
+			amsg->cmd = VPRBRD_I2C_CMD_ADDR;
+			amsg->unknown2 = 0x00;
+			amsg->unknown3 = 0x00;
+			amsg->addr = pmsg->addr;
+			amsg->unknown1 = 0x00;
+			amsg->len = cpu_to_le16(pmsg->len);
+			/* send the addr, the data goes to to board */
+			ret = vprbrd_i2c_addr(vb->usb_dev, amsg);
+			if (ret < 0)
+				error = ret;
+
+			ret = vprbrd_i2c_status(i2c, smsg, error);
+			if (ret < 0)
+				error = ret;
+
+			if (error < 0)
+				goto error;
+		}
+		mutex_unlock(&vb->lock);
+	}
+	return 0;
+error:
+	mutex_unlock(&vb->lock);
+	return error;
+}
+
+static u32 vprbrd_i2c_func(struct i2c_adapter *i2c)
+{
+	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+}
+
+/* This is the actual algorithm we define */
+static const struct i2c_algorithm vprbrd_algorithm = {
+	.master_xfer	= vprbrd_i2c_xfer,
+	.functionality	= vprbrd_i2c_func,
+};
+
+static int __devinit vprbrd_i2c_probe(struct platform_device *pdev)
+{
+	struct vprbrd *vb = dev_get_drvdata(pdev->dev.parent);
+	struct vprbrd_i2c *vb_i2c;
+	int ret;
+	int pipe;
+
+	vb_i2c = kzalloc(sizeof(*vb_i2c), GFP_KERNEL);
+	if (vb_i2c == NULL)
+		return -ENOMEM;
+
+	/* setup i2c adapter description */
+	vb_i2c->i2c.owner = THIS_MODULE;
+	vb_i2c->i2c.class = I2C_CLASS_HWMON;
+	vb_i2c->i2c.algo = &vprbrd_algorithm;
+	vb_i2c->i2c.algo_data = vb;
+	/* save the param in usb capabable memory */
+	vb_i2c->bus_freq_param = i2c_bus_param;
+
+	snprintf(vb_i2c->i2c.name, sizeof(vb_i2c->i2c.name),
+		 "viperboard at bus %03d device %03d",
+		 vb->usb_dev->bus->busnum, vb->usb_dev->devnum);
+
+	/* setting the bus frequency */
+	if ((i2c_bus_param <= VPRBRD_I2C_FREQ_10KHZ)
+		&& (i2c_bus_param >= VPRBRD_I2C_FREQ_6MHZ)) {
+		pipe = usb_sndctrlpipe(vb->usb_dev, 0);
+		ret = usb_control_msg(vb->usb_dev, pipe,
+			VPRBRD_USB_REQUEST_I2C_FREQ, VPRBRD_USB_TYPE_OUT,
+			0x0000, 0x0000, &vb_i2c->bus_freq_param, 1,
+			VPRBRD_USB_TIMEOUT_MS);
+	    if (ret != 1) {
+		dev_err(&pdev->dev,
+			"failure setting i2c_bus_freq to %d\n", i2c_bus_freq);
+		ret = -EIO;
+		goto error;
+	    }
+	} else {
+		dev_err(&pdev->dev,
+			"invalid i2c_bus_freq setting:%d\n", i2c_bus_freq);
+		ret = -EIO;
+		goto error;
+	}
+
+	vb_i2c->i2c.dev.parent = &pdev->dev;
+
+	/* attach to i2c layer */
+	i2c_add_adapter(&vb_i2c->i2c);
+
+	platform_set_drvdata(pdev, vb_i2c);
+
+	return 0;
+
+error:
+	kfree(vb_i2c);
+	return ret;
+}
+
+static int __devexit vprbrd_i2c_remove(struct platform_device *pdev)
+{
+	struct vprbrd_i2c *vb_i2c = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = i2c_del_adapter(&vb_i2c->i2c);
+
+	return ret;
+}
+
+static struct platform_driver vprbrd_i2c_driver = {
+	.driver.name	= "viperboard-i2c",
+	.driver.owner	= THIS_MODULE,
+	.probe		= vprbrd_i2c_probe,
+	.remove		= __devexit_p(vprbrd_i2c_remove),
+};
+
+static int __init vprbrd_i2c_init(void)
+{
+	switch (i2c_bus_freq) {
+	case 6000:
+		i2c_bus_param = VPRBRD_I2C_FREQ_6MHZ;
+		break;
+	case 3000:
+		i2c_bus_param = VPRBRD_I2C_FREQ_3MHZ;
+		break;
+	case 1000:
+		i2c_bus_param = VPRBRD_I2C_FREQ_1MHZ;
+		break;
+	case 400:
+		i2c_bus_param = VPRBRD_I2C_FREQ_400KHZ;
+		break;
+	case 200:
+		i2c_bus_param = VPRBRD_I2C_FREQ_200KHZ;
+		break;
+	case 100:
+		i2c_bus_param = VPRBRD_I2C_FREQ_100KHZ;
+		break;
+	case 10:
+		i2c_bus_param = VPRBRD_I2C_FREQ_10KHZ;
+		break;
+	default:
+		pr_warn("invalid i2c_bus_freq (%d)\n", i2c_bus_freq);
+		i2c_bus_param = VPRBRD_I2C_FREQ_100KHZ;
+	}
+
+	return platform_driver_register(&vprbrd_i2c_driver);
+}
+subsys_initcall(vprbrd_i2c_init);
+
+static void __exit vprbrd_i2c_exit(void)
+{
+	platform_driver_unregister(&vprbrd_i2c_driver);
+}
+module_exit(vprbrd_i2c_exit);
+
+MODULE_AUTHOR("Lars Poeschel <poeschel@lemonage.de>");
+MODULE_DESCRIPTION("I2C master driver for Nano River Techs Viperboard");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:viperboard-i2c");
diff --git a/drivers/mfd/viperboard.c b/drivers/mfd/viperboard.c
index c75ac08f639c..4f74ec868a52 100644
--- a/drivers/mfd/viperboard.c
+++ b/drivers/mfd/viperboard.c
@@ -41,6 +41,9 @@ static struct mfd_cell vprbrd_devs[] = {
 	{
 		.name = "viperboard-gpio",
 	},
+	{
+		.name = "viperboard-i2c",
+	},
 };
 
 static int vprbrd_probe(struct usb_interface *interface,
diff --git a/include/linux/mfd/viperboard.h b/include/linux/mfd/viperboard.h
index 42d339fac3e5..ef7851430d86 100644
--- a/include/linux/mfd/viperboard.h
+++ b/include/linux/mfd/viperboard.h
@@ -42,6 +42,8 @@
 #define VPRBRD_USB_TYPE_OUT	    0x40
 #define VPRBRD_USB_TYPE_IN	    0xc0
 #define VPRBRD_USB_TIMEOUT_MS       100
+#define VPRBRD_USB_REQUEST_I2C_FREQ 0xe6
+#define VPRBRD_USB_REQUEST_I2C      0xe9
 #define VPRBRD_USB_REQUEST_MAJOR    0xea
 #define VPRBRD_USB_REQUEST_MINOR    0xeb
 #define VPRBRD_USB_REQUEST_GPIOA    0xed
-- 
cgit v1.2.3-55-g7522


From ffd8a6e7a77802dd09559be78dea63956aa8f1d5 Mon Sep 17 00:00:00 2001
From: Lars Poeschel
Date: Mon, 5 Nov 2012 15:48:26 +0100
Subject: iio: adc: Add viperboard adc driver

This adds the mfd cell to use the adc part of the Nano River Technologies
viperboard.

Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Reviewed-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/iio/adc/Kconfig          |   7 ++
 drivers/iio/adc/Makefile         |   1 +
 drivers/iio/adc/viperboard_adc.c | 181 +++++++++++++++++++++++++++++++++++++++
 drivers/mfd/viperboard.c         |   3 +
 include/linux/mfd/viperboard.h   |   1 +
 5 files changed, 193 insertions(+)
 create mode 100644 drivers/iio/adc/viperboard_adc.c

(limited to 'include')

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 1401ed1af39f..bb3053739c80 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -67,4 +67,11 @@ config TI_AM335X_ADC
 	  Say yes here to build support for Texas Instruments ADC
 	  driver which is also a MFD client.
 
+config VIPERBOARD_ADC
+	tristate "Viperboard ADC support"
+	depends on MFD_VIPERBOARD && USB
+	help
+	  Say yes here to access the ADC part of the Nano River
+	  Technologies Viperboard.
+
 endmenu
diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile
index 4410a90fc84b..4268fa987fe6 100644
--- a/drivers/iio/adc/Makefile
+++ b/drivers/iio/adc/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_AD7791) += ad7791.o
 obj-$(CONFIG_AT91_ADC) += at91_adc.o
 obj-$(CONFIG_LP8788_ADC) += lp8788_adc.o
 obj-$(CONFIG_TI_AM335X_ADC) += ti_am335x_adc.o
+obj-$(CONFIG_VIPERBOARD_ADC) += viperboard_adc.o
\ No newline at end of file
diff --git a/drivers/iio/adc/viperboard_adc.c b/drivers/iio/adc/viperboard_adc.c
new file mode 100644
index 000000000000..10136a8b20d4
--- /dev/null
+++ b/drivers/iio/adc/viperboard_adc.c
@@ -0,0 +1,181 @@
+/*
+ *  Nano River Technologies viperboard IIO ADC driver
+ *
+ *  (C) 2012 by Lemonage GmbH
+ *  Author: Lars Poeschel <poeschel@lemonage.de>
+ *  All rights reserved.
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the	License, or (at your
+ *  option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+
+#include <linux/usb.h>
+#include <linux/iio/iio.h>
+
+#include <linux/mfd/viperboard.h>
+
+#define VPRBRD_ADC_CMD_GET		0x00
+
+struct vprbrd_adc_msg {
+	u8 cmd;
+	u8 chan;
+	u8 val;
+} __packed;
+
+struct vprbrd_adc {
+	struct vprbrd *vb;
+};
+
+#define VPRBRD_ADC_CHANNEL(_index) {			\
+	.type = IIO_VOLTAGE,				\
+	.indexed = 1,					\
+	.channel = _index,				\
+	.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT,	\
+	.scan_index = _index,				\
+	.scan_type = {					\
+		.sign = 'u',				\
+		.realbits = 8,				\
+		.storagebits = 8,			\
+	},						\
+}
+
+static struct iio_chan_spec const vprbrd_adc_iio_channels[] = {
+	VPRBRD_ADC_CHANNEL(0),
+	VPRBRD_ADC_CHANNEL(1),
+	VPRBRD_ADC_CHANNEL(2),
+	VPRBRD_ADC_CHANNEL(3),
+};
+
+static int vprbrd_iio_read_raw(struct iio_dev *iio_dev,
+				struct iio_chan_spec const *chan,
+				int *val,
+				int *val2,
+				long info)
+{
+	int ret, error = 0;
+	struct vprbrd_adc *adc = iio_priv(iio_dev);
+	struct vprbrd *vb = adc->vb;
+	struct vprbrd_adc_msg *admsg = (struct vprbrd_adc_msg *)vb->buf;
+
+	switch (info) {
+	case IIO_CHAN_INFO_RAW:
+		mutex_lock(&vb->lock);
+
+		admsg->cmd = VPRBRD_ADC_CMD_GET;
+		admsg->chan = chan->scan_index;
+		admsg->val = 0x00;
+
+		ret = usb_control_msg(vb->usb_dev,
+			usb_sndctrlpipe(vb->usb_dev, 0), VPRBRD_USB_REQUEST_ADC,
+			VPRBRD_USB_TYPE_OUT, 0x0000, 0x0000, admsg,
+			sizeof(struct vprbrd_adc_msg), VPRBRD_USB_TIMEOUT_MS);
+		if (ret != sizeof(struct vprbrd_adc_msg)) {
+			dev_err(&iio_dev->dev, "usb send error on adc read\n");
+			error = -EREMOTEIO;
+		}
+
+		ret = usb_control_msg(vb->usb_dev,
+			usb_rcvctrlpipe(vb->usb_dev, 0), VPRBRD_USB_REQUEST_ADC,
+			VPRBRD_USB_TYPE_IN, 0x0000, 0x0000, admsg,
+			sizeof(struct vprbrd_adc_msg), VPRBRD_USB_TIMEOUT_MS);
+
+		*val = admsg->val;
+
+		mutex_unlock(&vb->lock);
+
+		if (ret != sizeof(struct vprbrd_adc_msg)) {
+			dev_err(&iio_dev->dev, "usb recv error on adc read\n");
+			error = -EREMOTEIO;
+		}
+
+		if (error)
+			goto error;
+
+		return IIO_VAL_INT;
+	default:
+		error = -EINVAL;
+		break;
+	}
+error:
+	return error;
+}
+
+static const struct iio_info vprbrd_adc_iio_info = {
+	.read_raw = &vprbrd_iio_read_raw,
+	.driver_module = THIS_MODULE,
+};
+
+static int __devinit vprbrd_adc_probe(struct platform_device *pdev)
+{
+	struct vprbrd *vb = dev_get_drvdata(pdev->dev.parent);
+	struct vprbrd_adc *adc;
+	struct iio_dev *indio_dev;
+	int ret;
+
+	/* registering iio */
+	indio_dev = iio_device_alloc(sizeof(*adc));
+	if (!indio_dev) {
+		dev_err(&pdev->dev, "failed allocating iio device\n");
+		return -ENOMEM;
+	}
+
+	adc = iio_priv(indio_dev);
+	adc->vb = vb;
+	indio_dev->name = "viperboard adc";
+	indio_dev->dev.parent = &pdev->dev;
+	indio_dev->info = &vprbrd_adc_iio_info;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = vprbrd_adc_iio_channels;
+	indio_dev->num_channels = ARRAY_SIZE(vprbrd_adc_iio_channels);
+
+	ret = iio_device_register(indio_dev);
+	if (ret) {
+		dev_err(&pdev->dev, "could not register iio (adc)");
+		goto error;
+	}
+
+	platform_set_drvdata(pdev, indio_dev);
+
+	return 0;
+
+error:
+	iio_device_free(indio_dev);
+	return ret;
+}
+
+static int __devexit vprbrd_adc_remove(struct platform_device *pdev)
+{
+	struct iio_dev *indio_dev = platform_get_drvdata(pdev);
+
+	iio_device_unregister(indio_dev);
+	iio_device_free(indio_dev);
+
+	return 0;
+}
+
+static struct platform_driver vprbrd_adc_driver = {
+	.driver = {
+		.name	= "viperboard-adc",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= vprbrd_adc_probe,
+	.remove		= __devexit_p(vprbrd_adc_remove),
+};
+
+module_platform_driver(vprbrd_adc_driver);
+
+MODULE_AUTHOR("Lars Poeschel <poeschel@lemonage.de>");
+MODULE_DESCRIPTION("IIO ADC driver for Nano River Techs Viperboard");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:viperboard-adc");
diff --git a/drivers/mfd/viperboard.c b/drivers/mfd/viperboard.c
index 4f74ec868a52..276122b37199 100644
--- a/drivers/mfd/viperboard.c
+++ b/drivers/mfd/viperboard.c
@@ -44,6 +44,9 @@ static struct mfd_cell vprbrd_devs[] = {
 	{
 		.name = "viperboard-i2c",
 	},
+	{
+		.name = "viperboard-adc",
+	},
 };
 
 static int vprbrd_probe(struct usb_interface *interface,
diff --git a/include/linux/mfd/viperboard.h b/include/linux/mfd/viperboard.h
index ef7851430d86..193452848c04 100644
--- a/include/linux/mfd/viperboard.h
+++ b/include/linux/mfd/viperboard.h
@@ -46,6 +46,7 @@
 #define VPRBRD_USB_REQUEST_I2C      0xe9
 #define VPRBRD_USB_REQUEST_MAJOR    0xea
 #define VPRBRD_USB_REQUEST_MINOR    0xeb
+#define VPRBRD_USB_REQUEST_ADC      0xec
 #define VPRBRD_USB_REQUEST_GPIOA    0xed
 #define VPRBRD_USB_REQUEST_GPIOB    0xdd
 
-- 
cgit v1.2.3-55-g7522


From 1950c7164646bfeeb82c34bc299d82119706afb5 Mon Sep 17 00:00:00 2001
From: Davide Ciminaghi
Date: Fri, 9 Nov 2012 15:19:52 +0100
Subject: mfd: sta2x11-mfd: Add apb-soc regs driver and factor out common code

A driver for the apb-soc registers is needed by the clock
infrastructure code to configure and control clocks on the sta2x11
chip.

Since some of the functions in sta2x11-mfd.c were almost identical
for the two existing platform devices, the following changes
have been performed to avoid further code duplication while
adding the apb-soc-regs driver:

* The sctl_regs and apbreg_regs fields in struct sta2x11_mfd
have been turned into just one array of pointers accessed by
device index.
* Platform probe methods have become one-liners invoking a
common probe with the device's index as second parameter.
* For loops have been inserted where the same operations
were performed for each of the two bars of a pci device.
* The apbreg_mask and sctl_mask functions were almost identical,
so they were turned into inline functions invoking a common
__sta2x11_mfd_mask() with the platform device's index as last
parameter. To do this, enum sta2x11_mfd_plat_dev has been declared in
sta2x11-mfd.h and more device types have been added to it.

Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Davide Ciminaghi <ciminaghi@gnudd.com>
Acked-by: Alessandro Rubini <rubini@gnudd.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/sta2x11-mfd.c       | 350 +++++++++++++++++++++++++++-------------
 include/linux/mfd/sta2x11-mfd.h | 156 +++++++++++++++++-
 2 files changed, 395 insertions(+), 111 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/sta2x11-mfd.c b/drivers/mfd/sta2x11-mfd.c
index d35da6820bea..9e01b84aa8bc 100644
--- a/drivers/mfd/sta2x11-mfd.c
+++ b/drivers/mfd/sta2x11-mfd.c
@@ -40,8 +40,7 @@ struct sta2x11_mfd {
 	struct sta2x11_instance *instance;
 	spinlock_t lock;
 	struct list_head list;
-	void __iomem *sctl_regs;
-	void __iomem *apbreg_regs;
+	void __iomem *regs[sta2x11_n_mfd_plat_devs];
 };
 
 static LIST_HEAD(sta2x11_mfd_list);
@@ -100,56 +99,33 @@ static int __devexit mfd_remove(struct pci_dev *pdev)
 	return 0;
 }
 
-/* These two functions are exported and are not expected to fail */
-u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
+/* This function is exported and is not expected to fail */
+u32 __sta2x11_mfd_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val,
+		       enum sta2x11_mfd_plat_dev index)
 {
 	struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev);
 	u32 r;
 	unsigned long flags;
+	void __iomem *regs = mfd->regs[index];
 
 	if (!mfd) {
 		dev_warn(&pdev->dev, ": can't access sctl regs\n");
 		return 0;
 	}
-	if (!mfd->sctl_regs) {
+	if (!regs) {
 		dev_warn(&pdev->dev, ": system ctl not initialized\n");
 		return 0;
 	}
 	spin_lock_irqsave(&mfd->lock, flags);
-	r = readl(mfd->sctl_regs + reg);
+	r = readl(regs + reg);
 	r &= ~mask;
 	r |= val;
 	if (mask)
-		writel(r, mfd->sctl_regs + reg);
+		writel(r, regs + reg);
 	spin_unlock_irqrestore(&mfd->lock, flags);
 	return r;
 }
-EXPORT_SYMBOL(sta2x11_sctl_mask);
-
-u32 sta2x11_apbreg_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
-{
-	struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev);
-	u32 r;
-	unsigned long flags;
-
-	if (!mfd) {
-		dev_warn(&pdev->dev, ": can't access apb regs\n");
-		return 0;
-	}
-	if (!mfd->apbreg_regs) {
-		dev_warn(&pdev->dev, ": apb bridge not initialized\n");
-		return 0;
-	}
-	spin_lock_irqsave(&mfd->lock, flags);
-	r = readl(mfd->apbreg_regs + reg);
-	r &= ~mask;
-	r |= val;
-	if (mask)
-		writel(r, mfd->apbreg_regs + reg);
-	spin_unlock_irqrestore(&mfd->lock, flags);
-	return r;
-}
-EXPORT_SYMBOL(sta2x11_apbreg_mask);
+EXPORT_SYMBOL(__sta2x11_mfd_mask);
 
 /* Two debugfs files, for our registers (FIXME: one instance only) */
 #define REG(regname) {.name = #regname, .offset = SCTL_ ## regname}
@@ -180,51 +156,103 @@ static struct debugfs_regset32 apbreg_regset = {
 	.nregs = ARRAY_SIZE(sta2x11_apbreg_regs),
 };
 
-static struct dentry *sta2x11_sctl_debugfs;
-static struct dentry *sta2x11_apbreg_debugfs;
+#define REG(regname) {.name = #regname, .offset = regname}
+static struct debugfs_reg32 sta2x11_apb_soc_regs_regs[] = {
+	REG(PCIE_EP1_FUNC3_0_INTR_REG), REG(PCIE_EP1_FUNC7_4_INTR_REG),
+	REG(PCIE_EP2_FUNC3_0_INTR_REG), REG(PCIE_EP2_FUNC7_4_INTR_REG),
+	REG(PCIE_EP3_FUNC3_0_INTR_REG), REG(PCIE_EP3_FUNC7_4_INTR_REG),
+	REG(PCIE_EP4_FUNC3_0_INTR_REG), REG(PCIE_EP4_FUNC7_4_INTR_REG),
+	REG(PCIE_INTR_ENABLE0_REG), REG(PCIE_INTR_ENABLE1_REG),
+	REG(PCIE_EP1_FUNC_TC_REG), REG(PCIE_EP2_FUNC_TC_REG),
+	REG(PCIE_EP3_FUNC_TC_REG), REG(PCIE_EP4_FUNC_TC_REG),
+	REG(PCIE_EP1_FUNC_F_REG), REG(PCIE_EP2_FUNC_F_REG),
+	REG(PCIE_EP3_FUNC_F_REG), REG(PCIE_EP4_FUNC_F_REG),
+	REG(PCIE_PAB_AMBA_SW_RST_REG), REG(PCIE_PM_STATUS_0_PORT_0_4),
+	REG(PCIE_PM_STATUS_7_0_EP1), REG(PCIE_PM_STATUS_7_0_EP2),
+	REG(PCIE_PM_STATUS_7_0_EP3), REG(PCIE_PM_STATUS_7_0_EP4),
+	REG(PCIE_DEV_ID_0_EP1_REG), REG(PCIE_CC_REV_ID_0_EP1_REG),
+	REG(PCIE_DEV_ID_1_EP1_REG), REG(PCIE_CC_REV_ID_1_EP1_REG),
+	REG(PCIE_DEV_ID_2_EP1_REG), REG(PCIE_CC_REV_ID_2_EP1_REG),
+	REG(PCIE_DEV_ID_3_EP1_REG), REG(PCIE_CC_REV_ID_3_EP1_REG),
+	REG(PCIE_DEV_ID_4_EP1_REG), REG(PCIE_CC_REV_ID_4_EP1_REG),
+	REG(PCIE_DEV_ID_5_EP1_REG), REG(PCIE_CC_REV_ID_5_EP1_REG),
+	REG(PCIE_DEV_ID_6_EP1_REG), REG(PCIE_CC_REV_ID_6_EP1_REG),
+	REG(PCIE_DEV_ID_7_EP1_REG), REG(PCIE_CC_REV_ID_7_EP1_REG),
+	REG(PCIE_DEV_ID_0_EP2_REG), REG(PCIE_CC_REV_ID_0_EP2_REG),
+	REG(PCIE_DEV_ID_1_EP2_REG), REG(PCIE_CC_REV_ID_1_EP2_REG),
+	REG(PCIE_DEV_ID_2_EP2_REG), REG(PCIE_CC_REV_ID_2_EP2_REG),
+	REG(PCIE_DEV_ID_3_EP2_REG), REG(PCIE_CC_REV_ID_3_EP2_REG),
+	REG(PCIE_DEV_ID_4_EP2_REG), REG(PCIE_CC_REV_ID_4_EP2_REG),
+	REG(PCIE_DEV_ID_5_EP2_REG), REG(PCIE_CC_REV_ID_5_EP2_REG),
+	REG(PCIE_DEV_ID_6_EP2_REG), REG(PCIE_CC_REV_ID_6_EP2_REG),
+	REG(PCIE_DEV_ID_7_EP2_REG), REG(PCIE_CC_REV_ID_7_EP2_REG),
+	REG(PCIE_DEV_ID_0_EP3_REG), REG(PCIE_CC_REV_ID_0_EP3_REG),
+	REG(PCIE_DEV_ID_1_EP3_REG), REG(PCIE_CC_REV_ID_1_EP3_REG),
+	REG(PCIE_DEV_ID_2_EP3_REG), REG(PCIE_CC_REV_ID_2_EP3_REG),
+	REG(PCIE_DEV_ID_3_EP3_REG), REG(PCIE_CC_REV_ID_3_EP3_REG),
+	REG(PCIE_DEV_ID_4_EP3_REG), REG(PCIE_CC_REV_ID_4_EP3_REG),
+	REG(PCIE_DEV_ID_5_EP3_REG), REG(PCIE_CC_REV_ID_5_EP3_REG),
+	REG(PCIE_DEV_ID_6_EP3_REG), REG(PCIE_CC_REV_ID_6_EP3_REG),
+	REG(PCIE_DEV_ID_7_EP3_REG), REG(PCIE_CC_REV_ID_7_EP3_REG),
+	REG(PCIE_DEV_ID_0_EP4_REG), REG(PCIE_CC_REV_ID_0_EP4_REG),
+	REG(PCIE_DEV_ID_1_EP4_REG), REG(PCIE_CC_REV_ID_1_EP4_REG),
+	REG(PCIE_DEV_ID_2_EP4_REG), REG(PCIE_CC_REV_ID_2_EP4_REG),
+	REG(PCIE_DEV_ID_3_EP4_REG), REG(PCIE_CC_REV_ID_3_EP4_REG),
+	REG(PCIE_DEV_ID_4_EP4_REG), REG(PCIE_CC_REV_ID_4_EP4_REG),
+	REG(PCIE_DEV_ID_5_EP4_REG), REG(PCIE_CC_REV_ID_5_EP4_REG),
+	REG(PCIE_DEV_ID_6_EP4_REG), REG(PCIE_CC_REV_ID_6_EP4_REG),
+	REG(PCIE_DEV_ID_7_EP4_REG), REG(PCIE_CC_REV_ID_7_EP4_REG),
+	REG(PCIE_SUBSYS_VEN_ID_REG), REG(PCIE_COMMON_CLOCK_CONFIG_0_4_0),
+	REG(PCIE_MIPHYP_SSC_EN_REG), REG(PCIE_MIPHYP_ADDR_REG),
+	REG(PCIE_L1_ASPM_READY_REG), REG(PCIE_EXT_CFG_RDY_REG),
+	REG(PCIE_SoC_INT_ROUTER_STATUS0_REG),
+	REG(PCIE_SoC_INT_ROUTER_STATUS1_REG),
+	REG(PCIE_SoC_INT_ROUTER_STATUS2_REG),
+	REG(PCIE_SoC_INT_ROUTER_STATUS3_REG),
+	REG(DMA_IP_CTRL_REG), REG(DISP_BRIDGE_PU_PD_CTRL_REG),
+	REG(VIP_PU_PD_CTRL_REG), REG(USB_MLB_PU_PD_CTRL_REG),
+	REG(SDIO_PU_PD_MISCFUNC_CTRL_REG1), REG(SDIO_PU_PD_MISCFUNC_CTRL_REG2),
+	REG(UART_PU_PD_CTRL_REG), REG(ARM_Lock), REG(SYS_IO_CHAR_REG1),
+	REG(SYS_IO_CHAR_REG2), REG(SATA_CORE_ID_REG), REG(SATA_CTRL_REG),
+	REG(I2C_HSFIX_MISC_REG), REG(SPARE2_RESERVED), REG(SPARE3_RESERVED),
+	REG(MASTER_LOCK_REG), REG(SYSTEM_CONFIG_STATUS_REG),
+	REG(MSP_CLK_CTRL_REG), REG(COMPENSATION_REG1), REG(COMPENSATION_REG2),
+	REG(COMPENSATION_REG3), REG(TEST_CTL_REG),
+};
+#undef REG
 
-/* Probe for the two platform devices */
-static int sta2x11_sctl_probe(struct platform_device *dev)
-{
-	struct pci_dev **pdev;
-	struct sta2x11_mfd *mfd;
-	struct resource *res;
+static struct debugfs_regset32 apb_soc_regs_regset = {
+	.regs = sta2x11_apb_soc_regs_regs,
+	.nregs = ARRAY_SIZE(sta2x11_apb_soc_regs_regs),
+};
 
-	pdev = dev->dev.platform_data;
-	mfd = sta2x11_mfd_find(*pdev);
-	if (!mfd)
-		return -ENODEV;
 
-	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENOMEM;
+static struct dentry *sta2x11_mfd_debugfs[sta2x11_n_mfd_plat_devs];
 
-	if (!request_mem_region(res->start, resource_size(res),
-				"sta2x11-sctl"))
-		return -EBUSY;
+static struct debugfs_regset32 *sta2x11_mfd_regset[sta2x11_n_mfd_plat_devs] = {
+	[sta2x11_sctl] = &sctl_regset,
+	[sta2x11_apbreg] = &apbreg_regset,
+	[sta2x11_apb_soc_regs] = &apb_soc_regs_regset,
+};
 
-	mfd->sctl_regs = ioremap(res->start, resource_size(res));
-	if (!mfd->sctl_regs) {
-		release_mem_region(res->start, resource_size(res));
-		return -ENOMEM;
-	}
-	sctl_regset.base = mfd->sctl_regs;
-	sta2x11_sctl_debugfs = debugfs_create_regset32("sta2x11-sctl",
-						  S_IFREG | S_IRUGO,
-						  NULL, &sctl_regset);
-	return 0;
-}
+static const char *sta2x11_mfd_names[sta2x11_n_mfd_plat_devs] = {
+	[sta2x11_sctl] = "sta2x11-sctl",
+	[sta2x11_apbreg] = "sta2x11-apbreg",
+	[sta2x11_apb_soc_regs] = "sta2x11-apb-soc-regs",
+};
 
-static int sta2x11_apbreg_probe(struct platform_device *dev)
+/* Probe for the three platform devices */
+
+static int sta2x11_mfd_platform_probe(struct platform_device *dev,
+				      enum sta2x11_mfd_plat_dev index)
 {
 	struct pci_dev **pdev;
 	struct sta2x11_mfd *mfd;
 	struct resource *res;
+	const char *name = sta2x11_mfd_names[index];
+	struct debugfs_regset32 *regset = sta2x11_mfd_regset[index];
 
 	pdev = dev->dev.platform_data;
-	dev_dbg(&dev->dev, "%s: pdata is %p\n", __func__, pdev);
-	dev_dbg(&dev->dev, "%s: *pdata is %p\n", __func__, *pdev);
-
 	mfd = sta2x11_mfd_find(*pdev);
 	if (!mfd)
 		return -ENODEV;
@@ -233,25 +261,37 @@ static int sta2x11_apbreg_probe(struct platform_device *dev)
 	if (!res)
 		return -ENOMEM;
 
-	if (!request_mem_region(res->start, resource_size(res),
-				"sta2x11-apbreg"))
+	if (!request_mem_region(res->start, resource_size(res), name))
 		return -EBUSY;
 
-	mfd->apbreg_regs = ioremap(res->start, resource_size(res));
-	if (!mfd->apbreg_regs) {
+	mfd->regs[index] = ioremap(res->start, resource_size(res));
+	if (!mfd->regs[index]) {
 		release_mem_region(res->start, resource_size(res));
 		return -ENOMEM;
 	}
-	dev_dbg(&dev->dev, "%s: regbase %p\n", __func__, mfd->apbreg_regs);
-
-	apbreg_regset.base = mfd->apbreg_regs;
-	sta2x11_apbreg_debugfs = debugfs_create_regset32("sta2x11-apbreg",
-						  S_IFREG | S_IRUGO,
-						  NULL, &apbreg_regset);
+	regset->base = mfd->regs[index];
+	sta2x11_mfd_debugfs[index] = debugfs_create_regset32(name,
+							     S_IFREG | S_IRUGO,
+							     NULL, regset);
 	return 0;
 }
 
-/* The two platform drivers */
+static int sta2x11_sctl_probe(struct platform_device *dev)
+{
+	return sta2x11_mfd_platform_probe(dev, sta2x11_sctl);
+}
+
+static int sta2x11_apbreg_probe(struct platform_device *dev)
+{
+	return sta2x11_mfd_platform_probe(dev, sta2x11_apbreg);
+}
+
+static int sta2x11_apb_soc_regs_probe(struct platform_device *dev)
+{
+	return sta2x11_mfd_platform_probe(dev, sta2x11_apb_soc_regs);
+}
+
+/* The three platform drivers */
 static struct platform_driver sta2x11_sctl_platform_driver = {
 	.driver = {
 		.name	= "sta2x11-sctl",
@@ -280,13 +320,29 @@ static int __init sta2x11_apbreg_init(void)
 	return platform_driver_register(&sta2x11_platform_driver);
 }
 
+static struct platform_driver sta2x11_apb_soc_regs_platform_driver = {
+	.driver = {
+		.name	= "sta2x11-apb-soc-regs",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= sta2x11_apb_soc_regs_probe,
+};
+
+static int __init sta2x11_apb_soc_regs_init(void)
+{
+	pr_info("%s\n", __func__);
+	return platform_driver_register(&sta2x11_apb_soc_regs_platform_driver);
+}
+
 /*
- * What follows is the PCI device that hosts the above two pdevs.
+ * What follows are the PCI devices that host the above pdevs.
  * Each logic block is 4kB and they are all consecutive: we use this info.
  */
 
-/* Bar 0 */
-enum bar0_cells {
+/* Mfd 0 device */
+
+/* Mfd 0, Bar 0 */
+enum mfd0_bar0_cells {
 	STA2X11_GPIO_0 = 0,
 	STA2X11_GPIO_1,
 	STA2X11_GPIO_2,
@@ -295,8 +351,8 @@ enum bar0_cells {
 	STA2X11_SCR,
 	STA2X11_TIME,
 };
-/* Bar 1 */
-enum bar1_cells {
+/* Mfd 0 , Bar 1 */
+enum mfd0_bar1_cells {
 	STA2X11_APBREG = 0,
 };
 #define CELL_4K(_name, _cell) { \
@@ -330,17 +386,46 @@ static const __devinitconst struct resource apbreg_resources[] = {
 #define DEV(_name, _r) \
 	{ .name = _name, .num_resources = ARRAY_SIZE(_r), .resources = _r, }
 
-static __devinitdata struct mfd_cell sta2x11_mfd_bar0[] = {
+static __devinitdata struct mfd_cell sta2x11_mfd0_bar0[] = {
 	DEV("sta2x11-gpio", gpio_resources), /* offset 0: we add pdata later */
 	DEV("sta2x11-sctl", sctl_resources),
 	DEV("sta2x11-scr", scr_resources),
 	DEV("sta2x11-time", time_resources),
 };
 
-static __devinitdata struct mfd_cell sta2x11_mfd_bar1[] = {
+static __devinitdata struct mfd_cell sta2x11_mfd0_bar1[] = {
 	DEV("sta2x11-apbreg", apbreg_resources),
 };
 
+/* Mfd 1 devices */
+
+/* Mfd 1, Bar 0 */
+enum mfd1_bar0_cells {
+	STA2X11_VIC = 0,
+};
+
+/* Mfd 1, Bar 1 */
+enum mfd1_bar1_cells {
+	STA2X11_APB_SOC_REGS = 0,
+};
+
+static const __devinitconst struct resource vic_resources[] = {
+	CELL_4K("sta2x11-vic", STA2X11_VIC),
+};
+
+static const __devinitconst struct resource apb_soc_regs_resources[] = {
+	CELL_4K("sta2x11-apb-soc-regs", STA2X11_APB_SOC_REGS),
+};
+
+static __devinitdata struct mfd_cell sta2x11_mfd1_bar0[] = {
+	DEV("sta2x11-vic", vic_resources),
+};
+
+static __devinitdata struct mfd_cell sta2x11_mfd1_bar1[] = {
+	DEV("sta2x11-apb-soc-regs", apb_soc_regs_resources),
+};
+
+
 static int sta2x11_mfd_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	pci_save_state(pdev);
@@ -363,10 +448,63 @@ static int sta2x11_mfd_resume(struct pci_dev *pdev)
 	return 0;
 }
 
+struct sta2x11_mfd_bar_setup_data {
+	struct mfd_cell *cells;
+	int ncells;
+};
+
+struct sta2x11_mfd_setup_data {
+	struct sta2x11_mfd_bar_setup_data bars[2];
+};
+
+#define STA2X11_MFD0 0
+#define STA2X11_MFD1 1
+
+static struct sta2x11_mfd_setup_data mfd_setup_data[] = {
+	/* Mfd 0: gpio, sctl, scr, timers / apbregs */
+	[STA2X11_MFD0] = {
+		.bars = {
+			[0] = {
+				.cells = sta2x11_mfd0_bar0,
+				.ncells = ARRAY_SIZE(sta2x11_mfd0_bar0),
+			},
+			[1] = {
+				.cells = sta2x11_mfd0_bar1,
+				.ncells = ARRAY_SIZE(sta2x11_mfd0_bar1),
+			},
+		},
+	},
+	/* Mfd 1: vic / apb-soc-regs */
+	[STA2X11_MFD1] = {
+		.bars = {
+			[0] = {
+				.cells = sta2x11_mfd1_bar0,
+				.ncells = ARRAY_SIZE(sta2x11_mfd1_bar0),
+			},
+			[1] = {
+				.cells = sta2x11_mfd1_bar1,
+				.ncells = ARRAY_SIZE(sta2x11_mfd1_bar1),
+			},
+		},
+	},
+};
+
+static void __devinit sta2x11_mfd_setup(struct pci_dev *pdev,
+					struct sta2x11_mfd_setup_data *sd)
+{
+	int i, j;
+	for (i = 0; i < ARRAY_SIZE(sd->bars); i++)
+		for (j = 0; j < sd->bars[i].ncells; j++) {
+			sd->bars[i].cells[j].pdata_size = sizeof(pdev);
+			sd->bars[i].cells[j].platform_data = &pdev;
+		}
+}
+
 static int __devinit sta2x11_mfd_probe(struct pci_dev *pdev,
 				       const struct pci_device_id *pci_id)
 {
 	int err, i;
+	struct sta2x11_mfd_setup_data *setup_data;
 	struct sta2x11_gpio_pdata *gpio_data;
 
 	dev_info(&pdev->dev, "%s\n", __func__);
@@ -381,6 +519,10 @@ static int __devinit sta2x11_mfd_probe(struct pci_dev *pdev,
 	if (err)
 		dev_info(&pdev->dev, "Enable msi failed\n");
 
+	setup_data = pci_id->device == PCI_DEVICE_ID_STMICRO_GPIO ?
+		&mfd_setup_data[STA2X11_MFD0] :
+		&mfd_setup_data[STA2X11_MFD1];
+
 	/* Read gpio config data as pci device's platform data */
 	gpio_data = dev_get_platdata(&pdev->dev);
 	if (!gpio_data)
@@ -392,35 +534,23 @@ static int __devinit sta2x11_mfd_probe(struct pci_dev *pdev,
 		pdev, &pdev);
 
 	/* platform data is the pci device for all of them */
-	for (i = 0; i < ARRAY_SIZE(sta2x11_mfd_bar0); i++) {
-		sta2x11_mfd_bar0[i].pdata_size = sizeof(pdev);
-		sta2x11_mfd_bar0[i].platform_data = &pdev;
-	}
-	sta2x11_mfd_bar1[0].pdata_size = sizeof(pdev);
-	sta2x11_mfd_bar1[0].platform_data = &pdev;
+	sta2x11_mfd_setup(pdev, setup_data);
 
 	/* Record this pdev before mfd_add_devices: their probe looks for it */
 	sta2x11_mfd_add(pdev, GFP_ATOMIC);
 
-
-	err = mfd_add_devices(&pdev->dev, -1,
-			      sta2x11_mfd_bar0,
-			      ARRAY_SIZE(sta2x11_mfd_bar0),
-			      &pdev->resource[0],
-			      0, NULL);
-	if (err) {
-		dev_err(&pdev->dev, "mfd_add_devices[0] failed: %d\n", err);
-		goto err_disable;
-	}
-
-	err = mfd_add_devices(&pdev->dev, -1,
-			      sta2x11_mfd_bar1,
-			      ARRAY_SIZE(sta2x11_mfd_bar1),
-			      &pdev->resource[1],
-			      0, NULL);
-	if (err) {
-		dev_err(&pdev->dev, "mfd_add_devices[1] failed: %d\n", err);
-		goto err_disable;
+	/* Just 2 bars for all mfd's at present */
+	for (i = 0; i < 2; i++) {
+		err = mfd_add_devices(&pdev->dev, -1,
+				      setup_data->bars[i].cells,
+				      setup_data->bars[i].ncells,
+				      &pdev->resource[i],
+				      0, NULL);
+		if (err) {
+			dev_err(&pdev->dev,
+				"mfd_add_devices[%d] failed: %d\n", i, err);
+			goto err_disable;
+		}
 	}
 
 	return 0;
@@ -434,6 +564,7 @@ err_disable:
 
 static DEFINE_PCI_DEVICE_TABLE(sta2x11_mfd_tbl) = {
 	{PCI_DEVICE(PCI_VENDOR_ID_STMICRO, PCI_DEVICE_ID_STMICRO_GPIO)},
+	{PCI_DEVICE(PCI_VENDOR_ID_STMICRO, PCI_DEVICE_ID_STMICRO_VIC)},
 	{0,},
 };
 
@@ -459,6 +590,7 @@ static int __init sta2x11_mfd_init(void)
  */
 subsys_initcall(sta2x11_apbreg_init);
 subsys_initcall(sta2x11_sctl_init);
+subsys_initcall(sta2x11_apb_soc_regs_init);
 rootfs_initcall(sta2x11_mfd_init);
 
 MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/sta2x11-mfd.h b/include/linux/mfd/sta2x11-mfd.h
index d179227e866f..4d858797d7e2 100644
--- a/include/linux/mfd/sta2x11-mfd.h
+++ b/include/linux/mfd/sta2x11-mfd.h
@@ -26,6 +26,20 @@
 #include <linux/types.h>
 #include <linux/pci.h>
 
+enum sta2x11_mfd_plat_dev {
+	sta2x11_sctl = 0,
+	sta2x11_gpio,
+	sta2x11_scr,
+	sta2x11_time,
+	sta2x11_apbreg,
+	sta2x11_apb_soc_regs,
+	sta2x11_vic,
+	sta2x11_n_mfd_plat_devs,
+};
+
+extern u32
+__sta2x11_mfd_mask(struct pci_dev *, u32, u32, u32, enum sta2x11_mfd_plat_dev);
+
 /*
  * The MFD PCI block includes the GPIO peripherals and other register blocks.
  * For GPIO, we have 32*4 bits (I use "gsta" for "gpio sta2x11".)
@@ -182,7 +196,11 @@ struct sta2x11_gpio_pdata {
  * The APB bridge has its own registers, needed by our users as well.
  * They are accessed with the following read/mask/write function.
  */
-u32 sta2x11_apbreg_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val);
+static inline u32
+sta2x11_apbreg_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
+{
+	return __sta2x11_mfd_mask(pdev, reg, mask, val, sta2x11_apbreg);
+}
 
 /* CAN and MLB */
 #define APBREG_BSR	0x00	/* Bridge Status Reg */
@@ -211,7 +229,11 @@ u32 sta2x11_apbreg_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val);
  * The system controller has its own registers. Some of these are accessed
  * by out users as well, using the following read/mask/write/function
  */
-u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val);
+static inline
+u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
+{
+	return __sta2x11_mfd_mask(pdev, reg, mask, val, sta2x11_sctl);
+}
 
 #define SCTL_SCCTL		0x00	/* System controller control register */
 #define SCTL_ARMCFG		0x04	/* ARM configuration register */
@@ -321,4 +343,134 @@ u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val);
 #define SCTL_SCPEREN1_I2C3		(1 << 16)
 #define SCTL_SCPEREN1_USB_PHY		(1 << 17)
 
+/*
+ * APB-SOC registers
+ */
+static inline
+u32 sta2x11_apb_soc_regs_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
+{
+	return __sta2x11_mfd_mask(pdev, reg, mask, val, sta2x11_apb_soc_regs);
+}
+
+#define PCIE_EP1_FUNC3_0_INTR_REG	0x000
+#define PCIE_EP1_FUNC7_4_INTR_REG	0x004
+#define PCIE_EP2_FUNC3_0_INTR_REG	0x008
+#define PCIE_EP2_FUNC7_4_INTR_REG	0x00c
+#define PCIE_EP3_FUNC3_0_INTR_REG	0x010
+#define PCIE_EP3_FUNC7_4_INTR_REG	0x014
+#define PCIE_EP4_FUNC3_0_INTR_REG	0x018
+#define PCIE_EP4_FUNC7_4_INTR_REG	0x01c
+#define PCIE_INTR_ENABLE0_REG		0x020
+#define PCIE_INTR_ENABLE1_REG		0x024
+#define PCIE_EP1_FUNC_TC_REG		0x028
+#define PCIE_EP2_FUNC_TC_REG		0x02c
+#define PCIE_EP3_FUNC_TC_REG		0x030
+#define PCIE_EP4_FUNC_TC_REG		0x034
+#define PCIE_EP1_FUNC_F_REG		0x038
+#define PCIE_EP2_FUNC_F_REG		0x03c
+#define PCIE_EP3_FUNC_F_REG		0x040
+#define PCIE_EP4_FUNC_F_REG		0x044
+#define PCIE_PAB_AMBA_SW_RST_REG	0x048
+#define PCIE_PM_STATUS_0_PORT_0_4	0x04c
+#define PCIE_PM_STATUS_7_0_EP1		0x050
+#define PCIE_PM_STATUS_7_0_EP2		0x054
+#define PCIE_PM_STATUS_7_0_EP3		0x058
+#define PCIE_PM_STATUS_7_0_EP4		0x05c
+#define PCIE_DEV_ID_0_EP1_REG		0x060
+#define PCIE_CC_REV_ID_0_EP1_REG	0x064
+#define PCIE_DEV_ID_1_EP1_REG		0x068
+#define PCIE_CC_REV_ID_1_EP1_REG	0x06c
+#define PCIE_DEV_ID_2_EP1_REG		0x070
+#define PCIE_CC_REV_ID_2_EP1_REG	0x074
+#define PCIE_DEV_ID_3_EP1_REG		0x078
+#define PCIE_CC_REV_ID_3_EP1_REG	0x07c
+#define PCIE_DEV_ID_4_EP1_REG		0x080
+#define PCIE_CC_REV_ID_4_EP1_REG	0x084
+#define PCIE_DEV_ID_5_EP1_REG		0x088
+#define PCIE_CC_REV_ID_5_EP1_REG	0x08c
+#define PCIE_DEV_ID_6_EP1_REG		0x090
+#define PCIE_CC_REV_ID_6_EP1_REG	0x094
+#define PCIE_DEV_ID_7_EP1_REG		0x098
+#define PCIE_CC_REV_ID_7_EP1_REG	0x09c
+#define PCIE_DEV_ID_0_EP2_REG		0x0a0
+#define PCIE_CC_REV_ID_0_EP2_REG	0x0a4
+#define PCIE_DEV_ID_1_EP2_REG		0x0a8
+#define PCIE_CC_REV_ID_1_EP2_REG	0x0ac
+#define PCIE_DEV_ID_2_EP2_REG		0x0b0
+#define PCIE_CC_REV_ID_2_EP2_REG	0x0b4
+#define PCIE_DEV_ID_3_EP2_REG		0x0b8
+#define PCIE_CC_REV_ID_3_EP2_REG	0x0bc
+#define PCIE_DEV_ID_4_EP2_REG		0x0c0
+#define PCIE_CC_REV_ID_4_EP2_REG	0x0c4
+#define PCIE_DEV_ID_5_EP2_REG		0x0c8
+#define PCIE_CC_REV_ID_5_EP2_REG	0x0cc
+#define PCIE_DEV_ID_6_EP2_REG		0x0d0
+#define PCIE_CC_REV_ID_6_EP2_REG	0x0d4
+#define PCIE_DEV_ID_7_EP2_REG		0x0d8
+#define PCIE_CC_REV_ID_7_EP2_REG	0x0dC
+#define PCIE_DEV_ID_0_EP3_REG		0x0e0
+#define PCIE_CC_REV_ID_0_EP3_REG	0x0e4
+#define PCIE_DEV_ID_1_EP3_REG		0x0e8
+#define PCIE_CC_REV_ID_1_EP3_REG	0x0ec
+#define PCIE_DEV_ID_2_EP3_REG		0x0f0
+#define PCIE_CC_REV_ID_2_EP3_REG	0x0f4
+#define PCIE_DEV_ID_3_EP3_REG		0x0f8
+#define PCIE_CC_REV_ID_3_EP3_REG	0x0fc
+#define PCIE_DEV_ID_4_EP3_REG		0x100
+#define PCIE_CC_REV_ID_4_EP3_REG	0x104
+#define PCIE_DEV_ID_5_EP3_REG		0x108
+#define PCIE_CC_REV_ID_5_EP3_REG	0x10c
+#define PCIE_DEV_ID_6_EP3_REG		0x110
+#define PCIE_CC_REV_ID_6_EP3_REG	0x114
+#define PCIE_DEV_ID_7_EP3_REG		0x118
+#define PCIE_CC_REV_ID_7_EP3_REG	0x11c
+#define PCIE_DEV_ID_0_EP4_REG		0x120
+#define PCIE_CC_REV_ID_0_EP4_REG	0x124
+#define PCIE_DEV_ID_1_EP4_REG		0x128
+#define PCIE_CC_REV_ID_1_EP4_REG	0x12c
+#define PCIE_DEV_ID_2_EP4_REG		0x130
+#define PCIE_CC_REV_ID_2_EP4_REG	0x134
+#define PCIE_DEV_ID_3_EP4_REG		0x138
+#define PCIE_CC_REV_ID_3_EP4_REG	0x13c
+#define PCIE_DEV_ID_4_EP4_REG		0x140
+#define PCIE_CC_REV_ID_4_EP4_REG	0x144
+#define PCIE_DEV_ID_5_EP4_REG		0x148
+#define PCIE_CC_REV_ID_5_EP4_REG	0x14c
+#define PCIE_DEV_ID_6_EP4_REG		0x150
+#define PCIE_CC_REV_ID_6_EP4_REG	0x154
+#define PCIE_DEV_ID_7_EP4_REG		0x158
+#define PCIE_CC_REV_ID_7_EP4_REG	0x15c
+#define PCIE_SUBSYS_VEN_ID_REG		0x160
+#define PCIE_COMMON_CLOCK_CONFIG_0_4_0	0x164
+#define PCIE_MIPHYP_SSC_EN_REG		0x168
+#define PCIE_MIPHYP_ADDR_REG		0x16c
+#define PCIE_L1_ASPM_READY_REG		0x170
+#define PCIE_EXT_CFG_RDY_REG		0x174
+#define PCIE_SoC_INT_ROUTER_STATUS0_REG 0x178
+#define PCIE_SoC_INT_ROUTER_STATUS1_REG 0x17c
+#define PCIE_SoC_INT_ROUTER_STATUS2_REG 0x180
+#define PCIE_SoC_INT_ROUTER_STATUS3_REG 0x184
+#define DMA_IP_CTRL_REG			0x324
+#define DISP_BRIDGE_PU_PD_CTRL_REG	0x328
+#define VIP_PU_PD_CTRL_REG		0x32c
+#define USB_MLB_PU_PD_CTRL_REG		0x330
+#define SDIO_PU_PD_MISCFUNC_CTRL_REG1	0x334
+#define SDIO_PU_PD_MISCFUNC_CTRL_REG2	0x338
+#define UART_PU_PD_CTRL_REG		0x33c
+#define ARM_Lock			0x340
+#define SYS_IO_CHAR_REG1		0x344
+#define SYS_IO_CHAR_REG2		0x348
+#define SATA_CORE_ID_REG		0x34c
+#define SATA_CTRL_REG			0x350
+#define I2C_HSFIX_MISC_REG		0x354
+#define SPARE2_RESERVED			0x358
+#define SPARE3_RESERVED			0x35c
+#define MASTER_LOCK_REG			0x368
+#define SYSTEM_CONFIG_STATUS_REG	0x36c
+#define MSP_CLK_CTRL_REG		0x39c
+#define COMPENSATION_REG1		0x3c4
+#define COMPENSATION_REG2		0x3c8
+#define COMPENSATION_REG3		0x3cc
+#define TEST_CTL_REG			0x3d0
+
 #endif /* __STA2X11_MFD_H */
-- 
cgit v1.2.3-55-g7522


From d94e25535a7979a6c81922496f475a5dd0e006b4 Mon Sep 17 00:00:00 2001
From: Davide Ciminaghi
Date: Fri, 9 Nov 2012 15:19:53 +0100
Subject: mfd: sta2x11-mfd: Add regmap support

Signed-off-by: Davide Ciminaghi <ciminaghi@gnudd.com>
Acked-by: Alessandro Rubini <rubini@gnudd.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/Kconfig             |   1 +
 drivers/mfd/sta2x11-mfd.c       | 234 ++++++++++++++++++++++------------------
 include/linux/mfd/sta2x11-mfd.h |   1 +
 3 files changed, 131 insertions(+), 105 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index b280639a7634..59359a7a2493 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1046,6 +1046,7 @@ config MFD_STA2X11
 	bool "STA2X11 multi function device support"
 	depends on STA2X11
 	select MFD_CORE
+	select REGMAP_MMIO
 
 config MFD_SYSCON
 	bool "System Controller Register R/W Based on Regmap"
diff --git a/drivers/mfd/sta2x11-mfd.c b/drivers/mfd/sta2x11-mfd.c
index 9e01b84aa8bc..0cac2013bbf6 100644
--- a/drivers/mfd/sta2x11-mfd.c
+++ b/drivers/mfd/sta2x11-mfd.c
@@ -27,17 +27,25 @@
 #include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/pci.h>
-#include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/sta2x11-mfd.h>
+#include <linux/regmap.h>
 
 #include <asm/sta2x11.h>
 
+static inline int __reg_within_range(unsigned int r,
+				     unsigned int start,
+				     unsigned int end)
+{
+	return ((r >= start) && (r <= end));
+}
+
 /* This describes STA2X11 MFD chip for us, we may have several */
 struct sta2x11_mfd {
 	struct sta2x11_instance *instance;
+	struct regmap *regmap[sta2x11_n_mfd_plat_devs];
 	spinlock_t lock;
 	struct list_head list;
 	void __iomem *regs[sta2x11_n_mfd_plat_devs];
@@ -127,118 +135,126 @@ u32 __sta2x11_mfd_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val,
 }
 EXPORT_SYMBOL(__sta2x11_mfd_mask);
 
-/* Two debugfs files, for our registers (FIXME: one instance only) */
-#define REG(regname) {.name = #regname, .offset = SCTL_ ## regname}
-static struct debugfs_reg32 sta2x11_sctl_regs[] = {
-	REG(SCCTL), REG(ARMCFG), REG(SCPLLCTL), REG(SCPLLFCTRL),
-	REG(SCRESFRACT), REG(SCRESCTRL1), REG(SCRESXTRL2), REG(SCPEREN0),
-	REG(SCPEREN1), REG(SCPEREN2), REG(SCGRST), REG(SCPCIPMCR1),
-	REG(SCPCIPMCR2), REG(SCPCIPMSR1), REG(SCPCIPMSR2), REG(SCPCIPMSR3),
-	REG(SCINTREN), REG(SCRISR), REG(SCCLKSTAT0), REG(SCCLKSTAT1),
-	REG(SCCLKSTAT2), REG(SCRSTSTA),
-};
-#undef REG
+/*
+ * Special sta2x11-mfd regmap lock/unlock functions
+ */
 
-static struct debugfs_regset32 sctl_regset = {
-	.regs = sta2x11_sctl_regs,
-	.nregs = ARRAY_SIZE(sta2x11_sctl_regs),
-};
+static void sta2x11_regmap_lock(void *__lock)
+{
+	spinlock_t *lock = __lock;
+	spin_lock(lock);
+}
 
-#define REG(regname) {.name = #regname, .offset = regname}
-static struct debugfs_reg32 sta2x11_apbreg_regs[] = {
-	REG(APBREG_BSR), REG(APBREG_PAER), REG(APBREG_PWAC), REG(APBREG_PRAC),
-	REG(APBREG_PCG), REG(APBREG_PUR), REG(APBREG_EMU_PCG),
-};
-#undef REG
+static void sta2x11_regmap_unlock(void *__lock)
+{
+	spinlock_t *lock = __lock;
+	spin_unlock(lock);
+}
 
-static struct debugfs_regset32 apbreg_regset = {
-	.regs = sta2x11_apbreg_regs,
-	.nregs = ARRAY_SIZE(sta2x11_apbreg_regs),
+static const char *sta2x11_mfd_names[sta2x11_n_mfd_plat_devs] = {
+	[sta2x11_sctl] = "sta2x11-sctl",
+	[sta2x11_apbreg] = "sta2x11-apbreg",
+	[sta2x11_apb_soc_regs] = "sta2x11-apb-soc-regs",
 };
 
-#define REG(regname) {.name = #regname, .offset = regname}
-static struct debugfs_reg32 sta2x11_apb_soc_regs_regs[] = {
-	REG(PCIE_EP1_FUNC3_0_INTR_REG), REG(PCIE_EP1_FUNC7_4_INTR_REG),
-	REG(PCIE_EP2_FUNC3_0_INTR_REG), REG(PCIE_EP2_FUNC7_4_INTR_REG),
-	REG(PCIE_EP3_FUNC3_0_INTR_REG), REG(PCIE_EP3_FUNC7_4_INTR_REG),
-	REG(PCIE_EP4_FUNC3_0_INTR_REG), REG(PCIE_EP4_FUNC7_4_INTR_REG),
-	REG(PCIE_INTR_ENABLE0_REG), REG(PCIE_INTR_ENABLE1_REG),
-	REG(PCIE_EP1_FUNC_TC_REG), REG(PCIE_EP2_FUNC_TC_REG),
-	REG(PCIE_EP3_FUNC_TC_REG), REG(PCIE_EP4_FUNC_TC_REG),
-	REG(PCIE_EP1_FUNC_F_REG), REG(PCIE_EP2_FUNC_F_REG),
-	REG(PCIE_EP3_FUNC_F_REG), REG(PCIE_EP4_FUNC_F_REG),
-	REG(PCIE_PAB_AMBA_SW_RST_REG), REG(PCIE_PM_STATUS_0_PORT_0_4),
-	REG(PCIE_PM_STATUS_7_0_EP1), REG(PCIE_PM_STATUS_7_0_EP2),
-	REG(PCIE_PM_STATUS_7_0_EP3), REG(PCIE_PM_STATUS_7_0_EP4),
-	REG(PCIE_DEV_ID_0_EP1_REG), REG(PCIE_CC_REV_ID_0_EP1_REG),
-	REG(PCIE_DEV_ID_1_EP1_REG), REG(PCIE_CC_REV_ID_1_EP1_REG),
-	REG(PCIE_DEV_ID_2_EP1_REG), REG(PCIE_CC_REV_ID_2_EP1_REG),
-	REG(PCIE_DEV_ID_3_EP1_REG), REG(PCIE_CC_REV_ID_3_EP1_REG),
-	REG(PCIE_DEV_ID_4_EP1_REG), REG(PCIE_CC_REV_ID_4_EP1_REG),
-	REG(PCIE_DEV_ID_5_EP1_REG), REG(PCIE_CC_REV_ID_5_EP1_REG),
-	REG(PCIE_DEV_ID_6_EP1_REG), REG(PCIE_CC_REV_ID_6_EP1_REG),
-	REG(PCIE_DEV_ID_7_EP1_REG), REG(PCIE_CC_REV_ID_7_EP1_REG),
-	REG(PCIE_DEV_ID_0_EP2_REG), REG(PCIE_CC_REV_ID_0_EP2_REG),
-	REG(PCIE_DEV_ID_1_EP2_REG), REG(PCIE_CC_REV_ID_1_EP2_REG),
-	REG(PCIE_DEV_ID_2_EP2_REG), REG(PCIE_CC_REV_ID_2_EP2_REG),
-	REG(PCIE_DEV_ID_3_EP2_REG), REG(PCIE_CC_REV_ID_3_EP2_REG),
-	REG(PCIE_DEV_ID_4_EP2_REG), REG(PCIE_CC_REV_ID_4_EP2_REG),
-	REG(PCIE_DEV_ID_5_EP2_REG), REG(PCIE_CC_REV_ID_5_EP2_REG),
-	REG(PCIE_DEV_ID_6_EP2_REG), REG(PCIE_CC_REV_ID_6_EP2_REG),
-	REG(PCIE_DEV_ID_7_EP2_REG), REG(PCIE_CC_REV_ID_7_EP2_REG),
-	REG(PCIE_DEV_ID_0_EP3_REG), REG(PCIE_CC_REV_ID_0_EP3_REG),
-	REG(PCIE_DEV_ID_1_EP3_REG), REG(PCIE_CC_REV_ID_1_EP3_REG),
-	REG(PCIE_DEV_ID_2_EP3_REG), REG(PCIE_CC_REV_ID_2_EP3_REG),
-	REG(PCIE_DEV_ID_3_EP3_REG), REG(PCIE_CC_REV_ID_3_EP3_REG),
-	REG(PCIE_DEV_ID_4_EP3_REG), REG(PCIE_CC_REV_ID_4_EP3_REG),
-	REG(PCIE_DEV_ID_5_EP3_REG), REG(PCIE_CC_REV_ID_5_EP3_REG),
-	REG(PCIE_DEV_ID_6_EP3_REG), REG(PCIE_CC_REV_ID_6_EP3_REG),
-	REG(PCIE_DEV_ID_7_EP3_REG), REG(PCIE_CC_REV_ID_7_EP3_REG),
-	REG(PCIE_DEV_ID_0_EP4_REG), REG(PCIE_CC_REV_ID_0_EP4_REG),
-	REG(PCIE_DEV_ID_1_EP4_REG), REG(PCIE_CC_REV_ID_1_EP4_REG),
-	REG(PCIE_DEV_ID_2_EP4_REG), REG(PCIE_CC_REV_ID_2_EP4_REG),
-	REG(PCIE_DEV_ID_3_EP4_REG), REG(PCIE_CC_REV_ID_3_EP4_REG),
-	REG(PCIE_DEV_ID_4_EP4_REG), REG(PCIE_CC_REV_ID_4_EP4_REG),
-	REG(PCIE_DEV_ID_5_EP4_REG), REG(PCIE_CC_REV_ID_5_EP4_REG),
-	REG(PCIE_DEV_ID_6_EP4_REG), REG(PCIE_CC_REV_ID_6_EP4_REG),
-	REG(PCIE_DEV_ID_7_EP4_REG), REG(PCIE_CC_REV_ID_7_EP4_REG),
-	REG(PCIE_SUBSYS_VEN_ID_REG), REG(PCIE_COMMON_CLOCK_CONFIG_0_4_0),
-	REG(PCIE_MIPHYP_SSC_EN_REG), REG(PCIE_MIPHYP_ADDR_REG),
-	REG(PCIE_L1_ASPM_READY_REG), REG(PCIE_EXT_CFG_RDY_REG),
-	REG(PCIE_SoC_INT_ROUTER_STATUS0_REG),
-	REG(PCIE_SoC_INT_ROUTER_STATUS1_REG),
-	REG(PCIE_SoC_INT_ROUTER_STATUS2_REG),
-	REG(PCIE_SoC_INT_ROUTER_STATUS3_REG),
-	REG(DMA_IP_CTRL_REG), REG(DISP_BRIDGE_PU_PD_CTRL_REG),
-	REG(VIP_PU_PD_CTRL_REG), REG(USB_MLB_PU_PD_CTRL_REG),
-	REG(SDIO_PU_PD_MISCFUNC_CTRL_REG1), REG(SDIO_PU_PD_MISCFUNC_CTRL_REG2),
-	REG(UART_PU_PD_CTRL_REG), REG(ARM_Lock), REG(SYS_IO_CHAR_REG1),
-	REG(SYS_IO_CHAR_REG2), REG(SATA_CORE_ID_REG), REG(SATA_CTRL_REG),
-	REG(I2C_HSFIX_MISC_REG), REG(SPARE2_RESERVED), REG(SPARE3_RESERVED),
-	REG(MASTER_LOCK_REG), REG(SYSTEM_CONFIG_STATUS_REG),
-	REG(MSP_CLK_CTRL_REG), REG(COMPENSATION_REG1), REG(COMPENSATION_REG2),
-	REG(COMPENSATION_REG3), REG(TEST_CTL_REG),
+static bool sta2x11_sctl_writeable_reg(struct device *dev, unsigned int reg)
+{
+	return !__reg_within_range(reg, SCTL_SCPCIECSBRST, SCTL_SCRSTSTA);
+}
+
+static struct regmap_config sta2x11_sctl_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.lock = sta2x11_regmap_lock,
+	.unlock = sta2x11_regmap_unlock,
+	.max_register = SCTL_SCRSTSTA,
+	.writeable_reg = sta2x11_sctl_writeable_reg,
 };
-#undef REG
 
-static struct debugfs_regset32 apb_soc_regs_regset = {
-	.regs = sta2x11_apb_soc_regs_regs,
-	.nregs = ARRAY_SIZE(sta2x11_apb_soc_regs_regs),
+static bool sta2x11_apbreg_readable_reg(struct device *dev, unsigned int reg)
+{
+	/* Two blocks (CAN and MLB, SARAC) 0x100 bytes apart */
+	if (reg >= APBREG_BSR_SARAC)
+		reg -= APBREG_BSR_SARAC;
+	switch (reg) {
+	case APBREG_BSR:
+	case APBREG_PAER:
+	case APBREG_PWAC:
+	case APBREG_PRAC:
+	case APBREG_PCG:
+	case APBREG_PUR:
+	case APBREG_EMU_PCG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool sta2x11_apbreg_writeable_reg(struct device *dev, unsigned int reg)
+{
+	if (reg >= APBREG_BSR_SARAC)
+		reg -= APBREG_BSR_SARAC;
+	if (!sta2x11_apbreg_readable_reg(dev, reg))
+		return false;
+	return reg != APBREG_PAER;
+}
+
+static struct regmap_config sta2x11_apbreg_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.lock = sta2x11_regmap_lock,
+	.unlock = sta2x11_regmap_unlock,
+	.max_register = APBREG_EMU_PCG_SARAC,
+	.readable_reg = sta2x11_apbreg_readable_reg,
+	.writeable_reg = sta2x11_apbreg_writeable_reg,
 };
 
+static bool sta2x11_apb_soc_regs_readable_reg(struct device *dev,
+					      unsigned int reg)
+{
+	return reg <= PCIE_SoC_INT_ROUTER_STATUS3_REG ||
+		__reg_within_range(reg, DMA_IP_CTRL_REG, SPARE3_RESERVED) ||
+		__reg_within_range(reg, MASTER_LOCK_REG,
+				   SYSTEM_CONFIG_STATUS_REG) ||
+		reg == MSP_CLK_CTRL_REG ||
+		__reg_within_range(reg, COMPENSATION_REG1, TEST_CTL_REG);
+}
 
-static struct dentry *sta2x11_mfd_debugfs[sta2x11_n_mfd_plat_devs];
+static bool sta2x11_apb_soc_regs_writeable_reg(struct device *dev,
+					       unsigned int reg)
+{
+	if (!sta2x11_apb_soc_regs_readable_reg(dev, reg))
+		return false;
+	switch (reg) {
+	case PCIE_COMMON_CLOCK_CONFIG_0_4_0:
+	case SYSTEM_CONFIG_STATUS_REG:
+	case COMPENSATION_REG1:
+	case PCIE_SoC_INT_ROUTER_STATUS0_REG...PCIE_SoC_INT_ROUTER_STATUS3_REG:
+	case PCIE_PM_STATUS_0_PORT_0_4...PCIE_PM_STATUS_7_0_EP4:
+		return false;
+	default:
+		return true;
+	}
+}
 
-static struct debugfs_regset32 *sta2x11_mfd_regset[sta2x11_n_mfd_plat_devs] = {
-	[sta2x11_sctl] = &sctl_regset,
-	[sta2x11_apbreg] = &apbreg_regset,
-	[sta2x11_apb_soc_regs] = &apb_soc_regs_regset,
+static struct regmap_config sta2x11_apb_soc_regs_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.lock = sta2x11_regmap_lock,
+	.unlock = sta2x11_regmap_unlock,
+	.max_register = TEST_CTL_REG,
+	.readable_reg = sta2x11_apb_soc_regs_readable_reg,
+	.writeable_reg = sta2x11_apb_soc_regs_writeable_reg,
 };
 
-static const char *sta2x11_mfd_names[sta2x11_n_mfd_plat_devs] = {
-	[sta2x11_sctl] = "sta2x11-sctl",
-	[sta2x11_apbreg] = "sta2x11-apbreg",
-	[sta2x11_apb_soc_regs] = "sta2x11-apb-soc-regs",
+static struct regmap_config *
+sta2x11_mfd_regmap_configs[sta2x11_n_mfd_plat_devs] = {
+	[sta2x11_sctl] = &sta2x11_sctl_regmap_config,
+	[sta2x11_apbreg] = &sta2x11_apbreg_regmap_config,
+	[sta2x11_apb_soc_regs] = &sta2x11_apb_soc_regs_regmap_config,
 };
 
 /* Probe for the three platform devices */
@@ -250,12 +266,14 @@ static int sta2x11_mfd_platform_probe(struct platform_device *dev,
 	struct sta2x11_mfd *mfd;
 	struct resource *res;
 	const char *name = sta2x11_mfd_names[index];
-	struct debugfs_regset32 *regset = sta2x11_mfd_regset[index];
+	struct regmap_config *regmap_config = sta2x11_mfd_regmap_configs[index];
 
 	pdev = dev->dev.platform_data;
 	mfd = sta2x11_mfd_find(*pdev);
 	if (!mfd)
 		return -ENODEV;
+	if (!regmap_config)
+		return -ENODEV;
 
 	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
 	if (!res)
@@ -269,10 +287,16 @@ static int sta2x11_mfd_platform_probe(struct platform_device *dev,
 		release_mem_region(res->start, resource_size(res));
 		return -ENOMEM;
 	}
-	regset->base = mfd->regs[index];
-	sta2x11_mfd_debugfs[index] = debugfs_create_regset32(name,
-							     S_IFREG | S_IRUGO,
-							     NULL, regset);
+	regmap_config->lock_arg = &mfd->lock;
+	/*
+	   No caching, registers could be reached both via regmap and via
+	   void __iomem *
+	*/
+	regmap_config->cache_type = REGCACHE_NONE;
+	mfd->regmap[index] = devm_regmap_init_mmio(&dev->dev, mfd->regs[index],
+						   regmap_config);
+	WARN_ON(!mfd->regmap[index]);
+
 	return 0;
 }
 
diff --git a/include/linux/mfd/sta2x11-mfd.h b/include/linux/mfd/sta2x11-mfd.h
index 4d858797d7e2..83344304f2cf 100644
--- a/include/linux/mfd/sta2x11-mfd.h
+++ b/include/linux/mfd/sta2x11-mfd.h
@@ -246,6 +246,7 @@ u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
 #define SCTL_SCPEREN1		0x20	/* Peripheral clock enable register 1 */
 #define SCTL_SCPEREN2		0x24	/* Peripheral clock enable register 2 */
 #define SCTL_SCGRST		0x28	/* Peripheral global reset */
+#define SCTL_SCPCIECSBRST       0x2c    /* PCIe PAB CSB reset status register */
 #define SCTL_SCPCIPMCR1		0x30	/* PCI power management control 1 */
 #define SCTL_SCPCIPMCR2		0x34	/* PCI power management control 2 */
 #define SCTL_SCPCIPMSR1		0x38	/* PCI power management status 1 */
-- 
cgit v1.2.3-55-g7522


From 29f5b5a326b44c55e81b15308255ba695fecb323 Mon Sep 17 00:00:00 2001
From: Davide Ciminaghi
Date: Fri, 9 Nov 2012 15:19:54 +0100
Subject: mfd: sta2x11-mfd: Add sta2x11_mfd_get_regs_data() function

A couple of predefined clocks (mux and gated) need to be
initialized with the virtual address of the clock's controlling
register and the address of a spinlock used to protect against
races.

This function exports such data for all the mfd cells.

Signed-off-by: Davide Ciminaghi <ciminaghi@gnudd.com>
Acked-by: Alessandro Rubini <rubini@gnudd.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/sta2x11-mfd.c       | 22 ++++++++++++++++++++++
 include/linux/mfd/sta2x11-mfd.h |  5 +++++
 2 files changed, 27 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/sta2x11-mfd.c b/drivers/mfd/sta2x11-mfd.c
index 0cac2013bbf6..6d12ab42aba3 100644
--- a/drivers/mfd/sta2x11-mfd.c
+++ b/drivers/mfd/sta2x11-mfd.c
@@ -135,6 +135,28 @@ u32 __sta2x11_mfd_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val,
 }
 EXPORT_SYMBOL(__sta2x11_mfd_mask);
 
+int sta2x11_mfd_get_regs_data(struct platform_device *dev,
+			      enum sta2x11_mfd_plat_dev index,
+			      void __iomem **regs,
+			      spinlock_t **lock)
+{
+	struct pci_dev *pdev = *(struct pci_dev **)(dev->dev.platform_data);
+	struct sta2x11_mfd *mfd;
+
+	if (!pdev)
+		return -ENODEV;
+	mfd = sta2x11_mfd_find(pdev);
+	if (!mfd)
+		return -ENODEV;
+	if (index >= sta2x11_n_mfd_plat_devs)
+		return -ENODEV;
+	*regs = mfd->regs[index];
+	*lock = &mfd->lock[index];
+	pr_debug("%s %d *regs = %p\n", __func__, __LINE__, *regs);
+	return *regs ? 0 : -ENODEV;
+}
+EXPORT_SYMBOL(sta2x11_mfd_get_regs_data);
+
 /*
  * Special sta2x11-mfd regmap lock/unlock functions
  */
diff --git a/include/linux/mfd/sta2x11-mfd.h b/include/linux/mfd/sta2x11-mfd.h
index 83344304f2cf..e813e5efbe4e 100644
--- a/include/linux/mfd/sta2x11-mfd.h
+++ b/include/linux/mfd/sta2x11-mfd.h
@@ -474,4 +474,9 @@ u32 sta2x11_apb_soc_regs_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
 #define COMPENSATION_REG3		0x3cc
 #define TEST_CTL_REG			0x3d0
 
+extern int sta2x11_mfd_get_regs_data(struct platform_device *pdev,
+				     enum sta2x11_mfd_plat_dev index,
+				     void __iomem **regs,
+				     spinlock_t **lock);
+
 #endif /* __STA2X11_MFD_H */
-- 
cgit v1.2.3-55-g7522


From b18adafccd497245a6bc5b867bf9cba7e01f8729 Mon Sep 17 00:00:00 2001
From: Davide Ciminaghi
Date: Fri, 9 Nov 2012 15:19:55 +0100
Subject: mfd: sta2x11-mfd: Use defines for platform devices' names

Since there are now many sta2x11-mfd platform devices, using defines
for their names looks like a better solution.

Signed-off-by: Davide Ciminaghi <ciminaghi@gnudd.com>
Acked-by: Alessandro Rubini <rubini@gnudd.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/sta2x11-mfd.c       | 42 +++++++++++++++++++++--------------------
 include/linux/mfd/sta2x11-mfd.h |  8 ++++++++
 2 files changed, 30 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/sta2x11-mfd.c b/drivers/mfd/sta2x11-mfd.c
index 6d12ab42aba3..8d38ef264722 100644
--- a/drivers/mfd/sta2x11-mfd.c
+++ b/drivers/mfd/sta2x11-mfd.c
@@ -174,9 +174,9 @@ static void sta2x11_regmap_unlock(void *__lock)
 }
 
 static const char *sta2x11_mfd_names[sta2x11_n_mfd_plat_devs] = {
-	[sta2x11_sctl] = "sta2x11-sctl",
-	[sta2x11_apbreg] = "sta2x11-apbreg",
-	[sta2x11_apb_soc_regs] = "sta2x11-apb-soc-regs",
+	[sta2x11_sctl] = STA2X11_MFD_SCTL_NAME,
+	[sta2x11_apbreg] = STA2X11_MFD_APBREG_NAME,
+	[sta2x11_apb_soc_regs] = STA2X11_MFD_APB_SOC_REGS_NAME,
 };
 
 static bool sta2x11_sctl_writeable_reg(struct device *dev, unsigned int reg)
@@ -340,7 +340,7 @@ static int sta2x11_apb_soc_regs_probe(struct platform_device *dev)
 /* The three platform drivers */
 static struct platform_driver sta2x11_sctl_platform_driver = {
 	.driver = {
-		.name	= "sta2x11-sctl",
+		.name	= STA2X11_MFD_SCTL_NAME,
 		.owner	= THIS_MODULE,
 	},
 	.probe		= sta2x11_sctl_probe,
@@ -354,7 +354,7 @@ static int __init sta2x11_sctl_init(void)
 
 static struct platform_driver sta2x11_platform_driver = {
 	.driver = {
-		.name	= "sta2x11-apbreg",
+		.name	= STA2X11_MFD_APBREG_NAME,
 		.owner	= THIS_MODULE,
 	},
 	.probe		= sta2x11_apbreg_probe,
@@ -368,7 +368,7 @@ static int __init sta2x11_apbreg_init(void)
 
 static struct platform_driver sta2x11_apb_soc_regs_platform_driver = {
 	.driver = {
-		.name	= "sta2x11-apb-soc-regs",
+		.name	= STA2X11_MFD_APB_SOC_REGS_NAME,
 		.owner	= THIS_MODULE,
 	},
 	.probe		= sta2x11_apb_soc_regs_probe,
@@ -409,38 +409,40 @@ enum mfd0_bar1_cells {
 
 static const __devinitconst struct resource gpio_resources[] = {
 	{
-		.name = "sta2x11_gpio", /* 4 consecutive cells, 1 driver */
+		/* 4 consecutive cells, 1 driver */
+		.name = STA2X11_MFD_GPIO_NAME,
 		.start = 0,
 		.end = (4 * 4096) - 1,
 		.flags = IORESOURCE_MEM,
 	}
 };
 static const __devinitconst struct resource sctl_resources[] = {
-	CELL_4K("sta2x11-sctl", STA2X11_SCTL),
+	CELL_4K(STA2X11_MFD_SCTL_NAME, STA2X11_SCTL),
 };
 static const __devinitconst struct resource scr_resources[] = {
-	CELL_4K("sta2x11-scr", STA2X11_SCR),
+	CELL_4K(STA2X11_MFD_SCR_NAME, STA2X11_SCR),
 };
 static const __devinitconst struct resource time_resources[] = {
-	CELL_4K("sta2x11-time", STA2X11_TIME),
+	CELL_4K(STA2X11_MFD_TIME_NAME, STA2X11_TIME),
 };
 
 static const __devinitconst struct resource apbreg_resources[] = {
-	CELL_4K("sta2x11-apbreg", STA2X11_APBREG),
+	CELL_4K(STA2X11_MFD_APBREG_NAME, STA2X11_APBREG),
 };
 
 #define DEV(_name, _r) \
 	{ .name = _name, .num_resources = ARRAY_SIZE(_r), .resources = _r, }
 
 static __devinitdata struct mfd_cell sta2x11_mfd0_bar0[] = {
-	DEV("sta2x11-gpio", gpio_resources), /* offset 0: we add pdata later */
-	DEV("sta2x11-sctl", sctl_resources),
-	DEV("sta2x11-scr", scr_resources),
-	DEV("sta2x11-time", time_resources),
+	/* offset 0: we add pdata later */
+	DEV(STA2X11_MFD_GPIO_NAME, gpio_resources),
+	DEV(STA2X11_MFD_SCTL_NAME, sctl_resources),
+	DEV(STA2X11_MFD_SCR_NAME,  scr_resources),
+	DEV(STA2X11_MFD_TIME_NAME, time_resources),
 };
 
 static __devinitdata struct mfd_cell sta2x11_mfd0_bar1[] = {
-	DEV("sta2x11-apbreg", apbreg_resources),
+	DEV(STA2X11_MFD_APBREG_NAME, apbreg_resources),
 };
 
 /* Mfd 1 devices */
@@ -456,19 +458,19 @@ enum mfd1_bar1_cells {
 };
 
 static const __devinitconst struct resource vic_resources[] = {
-	CELL_4K("sta2x11-vic", STA2X11_VIC),
+	CELL_4K(STA2X11_MFD_VIC_NAME, STA2X11_VIC),
 };
 
 static const __devinitconst struct resource apb_soc_regs_resources[] = {
-	CELL_4K("sta2x11-apb-soc-regs", STA2X11_APB_SOC_REGS),
+	CELL_4K(STA2X11_MFD_APB_SOC_REGS_NAME, STA2X11_APB_SOC_REGS),
 };
 
 static __devinitdata struct mfd_cell sta2x11_mfd1_bar0[] = {
-	DEV("sta2x11-vic", vic_resources),
+	DEV(STA2X11_MFD_VIC_NAME, vic_resources),
 };
 
 static __devinitdata struct mfd_cell sta2x11_mfd1_bar1[] = {
-	DEV("sta2x11-apb-soc-regs", apb_soc_regs_resources),
+	DEV(STA2X11_MFD_APB_SOC_REGS_NAME, apb_soc_regs_resources),
 };
 
 
diff --git a/include/linux/mfd/sta2x11-mfd.h b/include/linux/mfd/sta2x11-mfd.h
index e813e5efbe4e..058de2bacf76 100644
--- a/include/linux/mfd/sta2x11-mfd.h
+++ b/include/linux/mfd/sta2x11-mfd.h
@@ -37,6 +37,14 @@ enum sta2x11_mfd_plat_dev {
 	sta2x11_n_mfd_plat_devs,
 };
 
+#define STA2X11_MFD_SCTL_NAME	       "sta2x11-sctl"
+#define STA2X11_MFD_GPIO_NAME	       "sta2x11-gpio"
+#define STA2X11_MFD_SCR_NAME	       "sta2x11-scr"
+#define STA2X11_MFD_TIME_NAME	       "sta2x11-time"
+#define STA2X11_MFD_APBREG_NAME	       "sta2x11-apbreg"
+#define STA2X11_MFD_APB_SOC_REGS_NAME  "sta2x11-apb-soc-regs"
+#define STA2X11_MFD_VIC_NAME	       "sta2x11-vic"
+
 extern u32
 __sta2x11_mfd_mask(struct pci_dev *, u32, u32, u32, enum sta2x11_mfd_plat_dev);
 
-- 
cgit v1.2.3-55-g7522


From dba6c1aeea4dd0e251e41c3f585abf4a06a4f057 Mon Sep 17 00:00:00 2001
From: Davide Ciminaghi
Date: Fri, 9 Nov 2012 15:19:59 +0100
Subject: mfd: sta2x11-mfd: Add scr (otp registers) platform driver

Signed-off-by: Davide Ciminaghi <ciminaghi@gnudd.com>
Acked-by: Alessandro Rubini <rubini@gnudd.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/sta2x11-mfd.c       | 52 ++++++++++++++++++++++++++++++++++++++++-
 include/linux/mfd/sta2x11-mfd.h |  7 ++++++
 2 files changed, 58 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mfd/sta2x11-mfd.c b/drivers/mfd/sta2x11-mfd.c
index da65839f1d86..7365f0f89df2 100644
--- a/drivers/mfd/sta2x11-mfd.c
+++ b/drivers/mfd/sta2x11-mfd.c
@@ -175,10 +175,16 @@ static void sta2x11_regmap_unlock(void *__lock)
 	spin_unlock(lock);
 }
 
+/* OTP (one time programmable registers do not require locking */
+static void sta2x11_regmap_nolock(void *__lock)
+{
+}
+
 static const char *sta2x11_mfd_names[sta2x11_n_mfd_plat_devs] = {
 	[sta2x11_sctl] = STA2X11_MFD_SCTL_NAME,
 	[sta2x11_apbreg] = STA2X11_MFD_APBREG_NAME,
 	[sta2x11_apb_soc_regs] = STA2X11_MFD_APB_SOC_REGS_NAME,
+	[sta2x11_scr] = STA2X11_MFD_SCR_NAME,
 };
 
 static bool sta2x11_sctl_writeable_reg(struct device *dev, unsigned int reg)
@@ -196,6 +202,28 @@ static struct regmap_config sta2x11_sctl_regmap_config = {
 	.writeable_reg = sta2x11_sctl_writeable_reg,
 };
 
+static bool sta2x11_scr_readable_reg(struct device *dev, unsigned int reg)
+{
+	return (reg == STA2X11_SECR_CR) ||
+		__reg_within_range(reg, STA2X11_SECR_FVR0, STA2X11_SECR_FVR1);
+}
+
+static bool sta2x11_scr_writeable_reg(struct device *dev, unsigned int reg)
+{
+	return false;
+}
+
+static struct regmap_config sta2x11_scr_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.lock = sta2x11_regmap_nolock,
+	.unlock = sta2x11_regmap_nolock,
+	.max_register = STA2X11_SECR_FVR1,
+	.readable_reg = sta2x11_scr_readable_reg,
+	.writeable_reg = sta2x11_scr_writeable_reg,
+};
+
 static bool sta2x11_apbreg_readable_reg(struct device *dev, unsigned int reg)
 {
 	/* Two blocks (CAN and MLB, SARAC) 0x100 bytes apart */
@@ -279,9 +307,10 @@ sta2x11_mfd_regmap_configs[sta2x11_n_mfd_plat_devs] = {
 	[sta2x11_sctl] = &sta2x11_sctl_regmap_config,
 	[sta2x11_apbreg] = &sta2x11_apbreg_regmap_config,
 	[sta2x11_apb_soc_regs] = &sta2x11_apb_soc_regs_regmap_config,
+	[sta2x11_scr] = &sta2x11_scr_regmap_config,
 };
 
-/* Probe for the three platform devices */
+/* Probe for the four platform devices */
 
 static int sta2x11_mfd_platform_probe(struct platform_device *dev,
 				      enum sta2x11_mfd_plat_dev index)
@@ -339,6 +368,11 @@ static int sta2x11_apb_soc_regs_probe(struct platform_device *dev)
 	return sta2x11_mfd_platform_probe(dev, sta2x11_apb_soc_regs);
 }
 
+static int sta2x11_scr_probe(struct platform_device *dev)
+{
+	return sta2x11_mfd_platform_probe(dev, sta2x11_scr);
+}
+
 /* The three platform drivers */
 static struct platform_driver sta2x11_sctl_platform_driver = {
 	.driver = {
@@ -382,6 +416,21 @@ static int __init sta2x11_apb_soc_regs_init(void)
 	return platform_driver_register(&sta2x11_apb_soc_regs_platform_driver);
 }
 
+static struct platform_driver sta2x11_scr_platform_driver = {
+	.driver = {
+		.name = STA2X11_MFD_SCR_NAME,
+		.owner = THIS_MODULE,
+	},
+	.probe = sta2x11_scr_probe,
+};
+
+static int __init sta2x11_scr_init(void)
+{
+	pr_info("%s\n", __func__);
+	return platform_driver_register(&sta2x11_scr_platform_driver);
+}
+
+
 /*
  * What follows are the PCI devices that host the above pdevs.
  * Each logic block is 4kB and they are all consecutive: we use this info.
@@ -631,6 +680,7 @@ static int __init sta2x11_mfd_init(void)
 subsys_initcall(sta2x11_apbreg_init);
 subsys_initcall(sta2x11_sctl_init);
 subsys_initcall(sta2x11_apb_soc_regs_init);
+subsys_initcall(sta2x11_scr_init);
 rootfs_initcall(sta2x11_mfd_init);
 
 MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/sta2x11-mfd.h b/include/linux/mfd/sta2x11-mfd.h
index 058de2bacf76..08cad95758c6 100644
--- a/include/linux/mfd/sta2x11-mfd.h
+++ b/include/linux/mfd/sta2x11-mfd.h
@@ -482,6 +482,13 @@ u32 sta2x11_apb_soc_regs_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
 #define COMPENSATION_REG3		0x3cc
 #define TEST_CTL_REG			0x3d0
 
+/*
+ * SECR (OTP) registers
+ */
+#define STA2X11_SECR_CR			0x00
+#define STA2X11_SECR_FVR0		0x10
+#define STA2X11_SECR_FVR1		0x14
+
 extern int sta2x11_mfd_get_regs_data(struct platform_device *pdev,
 				     enum sta2x11_mfd_plat_dev index,
 				     void __iomem **regs,
-- 
cgit v1.2.3-55-g7522


From 818b5c2528b9e31101bb39018fd211dcf159a696 Mon Sep 17 00:00:00 2001
From: Davide Ciminaghi
Date: Fri, 9 Nov 2012 15:20:00 +0100
Subject: mfd: sta2x11-mfd: Add defines for some sta2x11 sctl registers

These are required for the clock infrastructure code to properly configure
and control the sta2x11 PLLs.

Signed-off-by: Davide Ciminaghi <ciminaghi@gnudd.com>
Acked-by: Alessandro Rubini <rubini@gnudd.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/linux/mfd/sta2x11-mfd.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

(limited to 'include')

diff --git a/include/linux/mfd/sta2x11-mfd.h b/include/linux/mfd/sta2x11-mfd.h
index 08cad95758c6..9a855ac11cbf 100644
--- a/include/linux/mfd/sta2x11-mfd.h
+++ b/include/linux/mfd/sta2x11-mfd.h
@@ -246,8 +246,29 @@ u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
 #define SCTL_SCCTL		0x00	/* System controller control register */
 #define SCTL_ARMCFG		0x04	/* ARM configuration register */
 #define SCTL_SCPLLCTL		0x08	/* PLL control status register */
+
+#define SCTL_SCPLLCTL_AUDIO_PLL_PD	     BIT(1)
+#define SCTL_SCPLLCTL_FRAC_CONTROL	     BIT(3)
+#define SCTL_SCPLLCTL_STRB_BYPASS	     BIT(6)
+#define SCTL_SCPLLCTL_STRB_INPUT	     BIT(8)
+
 #define SCTL_SCPLLFCTRL		0x0c	/* PLL frequency control register */
+
+#define SCTL_SCPLLFCTRL_AUDIO_PLL_NDIV_MASK	0xff
+#define SCTL_SCPLLFCTRL_AUDIO_PLL_NDIV_SHIFT	  10
+#define SCTL_SCPLLFCTRL_AUDIO_PLL_IDF_MASK	   7
+#define SCTL_SCPLLFCTRL_AUDIO_PLL_IDF_SHIFT	  21
+#define SCTL_SCPLLFCTRL_AUDIO_PLL_ODF_MASK	   7
+#define SCTL_SCPLLFCTRL_AUDIO_PLL_ODF_SHIFT	  18
+#define SCTL_SCPLLFCTRL_DITHER_DISABLE_MASK     0x03
+#define SCTL_SCPLLFCTRL_DITHER_DISABLE_SHIFT       4
+
+
 #define SCTL_SCRESFRACT		0x10	/* PLL fractional input register */
+
+#define SCTL_SCRESFRACT_MASK	0x0000ffff
+
+
 #define SCTL_SCRESCTRL1		0x14	/* Peripheral reset control 1 */
 #define SCTL_SCRESXTRL2		0x18	/* Peripheral reset control 2 */
 #define SCTL_SCPEREN0		0x1c	/* Peripheral clock enable register 0 */
-- 
cgit v1.2.3-55-g7522


From bcf58e725ddc45d31addbc6627d4f0edccc824c1 Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Thu, 26 Jul 2012 04:02:49 -0700
Subject: userns: Make create_new_namespaces take a user_ns parameter

Modify create_new_namespaces to explicitly take a user namespace
parameter, instead of implicitly through the task_struct.

This allows an implementation of unshare(CLONE_NEWUSER) where
the new user namespace is not stored onto the current task_struct
until after all of the namespaces are created.

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/ipc_namespace.h |  7 ++++---
 include/linux/utsname.h       |  6 +++---
 ipc/namespace.c               | 10 ++++------
 kernel/nsproxy.c              | 22 +++++++++++++---------
 kernel/utsname.c              |  9 ++++-----
 5 files changed, 28 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 5499c92a9153..f03af702a39d 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -133,7 +133,8 @@ static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; }
 
 #if defined(CONFIG_IPC_NS)
 extern struct ipc_namespace *copy_ipcs(unsigned long flags,
-				       struct task_struct *tsk);
+	struct user_namespace *user_ns, struct ipc_namespace *ns);
+
 static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 {
 	if (ns)
@@ -144,12 +145,12 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 extern void put_ipc_ns(struct ipc_namespace *ns);
 #else
 static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
-					      struct task_struct *tsk)
+	struct user_namespace *user_ns, struct ipc_namespace *ns)
 {
 	if (flags & CLONE_NEWIPC)
 		return ERR_PTR(-EINVAL);
 
-	return tsk->nsproxy->ipc_ns;
+	return ns;
 }
 
 static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
diff --git a/include/linux/utsname.h b/include/linux/utsname.h
index 2b345206722a..221f4a0a7502 100644
--- a/include/linux/utsname.h
+++ b/include/linux/utsname.h
@@ -33,7 +33,7 @@ static inline void get_uts_ns(struct uts_namespace *ns)
 }
 
 extern struct uts_namespace *copy_utsname(unsigned long flags,
-					  struct task_struct *tsk);
+	struct user_namespace *user_ns, struct uts_namespace *old_ns);
 extern void free_uts_ns(struct kref *kref);
 
 static inline void put_uts_ns(struct uts_namespace *ns)
@@ -50,12 +50,12 @@ static inline void put_uts_ns(struct uts_namespace *ns)
 }
 
 static inline struct uts_namespace *copy_utsname(unsigned long flags,
-						 struct task_struct *tsk)
+	struct user_namespace *user_ns, struct uts_namespace *old_ns)
 {
 	if (flags & CLONE_NEWUTS)
 		return ERR_PTR(-EINVAL);
 
-	return tsk->nsproxy->uts_ns;
+	return old_ns;
 }
 #endif
 
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 6ed33c05cb66..72c868277793 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -16,7 +16,7 @@
 
 #include "util.h"
 
-static struct ipc_namespace *create_ipc_ns(struct task_struct *tsk,
+static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 					   struct ipc_namespace *old_ns)
 {
 	struct ipc_namespace *ns;
@@ -46,19 +46,17 @@ static struct ipc_namespace *create_ipc_ns(struct task_struct *tsk,
 	ipcns_notify(IPCNS_CREATED);
 	register_ipcns_notifier(ns);
 
-	ns->user_ns = get_user_ns(task_cred_xxx(tsk, user_ns));
+	ns->user_ns = get_user_ns(user_ns);
 
 	return ns;
 }
 
 struct ipc_namespace *copy_ipcs(unsigned long flags,
-				struct task_struct *tsk)
+	struct user_namespace *user_ns, struct ipc_namespace *ns)
 {
-	struct ipc_namespace *ns = tsk->nsproxy->ipc_ns;
-
 	if (!(flags & CLONE_NEWIPC))
 		return get_ipc_ns(ns);
-	return create_ipc_ns(tsk, ns);
+	return create_ipc_ns(user_ns, ns);
 }
 
 /*
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 4357a0a7d17d..2ddd81657a2a 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -57,7 +57,8 @@ static inline struct nsproxy *create_nsproxy(void)
  * leave it to the caller to do proper locking and attach it to task.
  */
 static struct nsproxy *create_new_namespaces(unsigned long flags,
-			struct task_struct *tsk, struct fs_struct *new_fs)
+	struct task_struct *tsk, struct user_namespace *user_ns,
+	struct fs_struct *new_fs)
 {
 	struct nsproxy *new_nsp;
 	int err;
@@ -66,31 +67,31 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 	if (!new_nsp)
 		return ERR_PTR(-ENOMEM);
 
-	new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, task_cred_xxx(tsk, user_ns), new_fs);
+	new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs);
 	if (IS_ERR(new_nsp->mnt_ns)) {
 		err = PTR_ERR(new_nsp->mnt_ns);
 		goto out_ns;
 	}
 
-	new_nsp->uts_ns = copy_utsname(flags, tsk);
+	new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns);
 	if (IS_ERR(new_nsp->uts_ns)) {
 		err = PTR_ERR(new_nsp->uts_ns);
 		goto out_uts;
 	}
 
-	new_nsp->ipc_ns = copy_ipcs(flags, tsk);
+	new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns);
 	if (IS_ERR(new_nsp->ipc_ns)) {
 		err = PTR_ERR(new_nsp->ipc_ns);
 		goto out_ipc;
 	}
 
-	new_nsp->pid_ns = copy_pid_ns(flags, task_cred_xxx(tsk, user_ns), tsk->nsproxy->pid_ns);
+	new_nsp->pid_ns = copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns);
 	if (IS_ERR(new_nsp->pid_ns)) {
 		err = PTR_ERR(new_nsp->pid_ns);
 		goto out_pid;
 	}
 
-	new_nsp->net_ns = copy_net_ns(flags, task_cred_xxx(tsk, user_ns), tsk->nsproxy->net_ns);
+	new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
 	if (IS_ERR(new_nsp->net_ns)) {
 		err = PTR_ERR(new_nsp->net_ns);
 		goto out_net;
@@ -152,7 +153,8 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 		goto out;
 	}
 
-	new_ns = create_new_namespaces(flags, tsk, tsk->fs);
+	new_ns = create_new_namespaces(flags, tsk,
+				       task_cred_xxx(tsk, user_ns), tsk->fs);
 	if (IS_ERR(new_ns)) {
 		err = PTR_ERR(new_ns);
 		goto out;
@@ -186,6 +188,7 @@ void free_nsproxy(struct nsproxy *ns)
 int unshare_nsproxy_namespaces(unsigned long unshare_flags,
 		struct nsproxy **new_nsp, struct fs_struct *new_fs)
 {
+	struct user_namespace *user_ns;
 	int err = 0;
 
 	if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
@@ -195,7 +198,8 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
 	if (!nsown_capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	*new_nsp = create_new_namespaces(unshare_flags, current,
+	user_ns = current_user_ns();
+	*new_nsp = create_new_namespaces(unshare_flags, current, user_ns,
 				new_fs ? new_fs : current->fs);
 	if (IS_ERR(*new_nsp)) {
 		err = PTR_ERR(*new_nsp);
@@ -252,7 +256,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, nstype)
 	if (nstype && (ops->type != nstype))
 		goto out;
 
-	new_nsproxy = create_new_namespaces(0, tsk, tsk->fs);
+	new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs);
 	if (IS_ERR(new_nsproxy)) {
 		err = PTR_ERR(new_nsproxy);
 		goto out;
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 4a9362f9325d..fdc619eb61ef 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -32,7 +32,7 @@ static struct uts_namespace *create_uts_ns(void)
  * @old_ns: namespace to clone
  * Return NULL on error (failure to kmalloc), new ns otherwise
  */
-static struct uts_namespace *clone_uts_ns(struct task_struct *tsk,
+static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns,
 					  struct uts_namespace *old_ns)
 {
 	struct uts_namespace *ns;
@@ -43,7 +43,7 @@ static struct uts_namespace *clone_uts_ns(struct task_struct *tsk,
 
 	down_read(&uts_sem);
 	memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
-	ns->user_ns = get_user_ns(task_cred_xxx(tsk, user_ns));
+	ns->user_ns = get_user_ns(user_ns);
 	up_read(&uts_sem);
 	return ns;
 }
@@ -55,9 +55,8 @@ static struct uts_namespace *clone_uts_ns(struct task_struct *tsk,
  * versa.
  */
 struct uts_namespace *copy_utsname(unsigned long flags,
-				   struct task_struct *tsk)
+	struct user_namespace *user_ns, struct uts_namespace *old_ns)
 {
-	struct uts_namespace *old_ns = tsk->nsproxy->uts_ns;
 	struct uts_namespace *new_ns;
 
 	BUG_ON(!old_ns);
@@ -66,7 +65,7 @@ struct uts_namespace *copy_utsname(unsigned long flags,
 	if (!(flags & CLONE_NEWUTS))
 		return old_ns;
 
-	new_ns = clone_uts_ns(tsk, old_ns);
+	new_ns = clone_uts_ns(user_ns, old_ns);
 
 	put_uts_ns(old_ns);
 	return new_ns;
-- 
cgit v1.2.3-55-g7522


From 4c44aaafa8108f584831850ab48a975e971db2de Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Thu, 26 Jul 2012 05:05:21 -0700
Subject: userns: Kill task_user_ns

The task_user_ns function hides the fact that it is getting the user
namespace from struct cred on the task.  struct cred may go away as
soon as the rcu lock is released.  This leads to a race where we
can dereference a stale user namespace pointer.

To make it obvious a struct cred is involved kill task_user_ns.

To kill the race modify the users of task_user_ns to only
reference the user namespace while the rcu lock is held.

Cc: Kees Cook <keescook@chromium.org>
Cc: James Morris <james.l.morris@oracle.com>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/cred.h     |  2 --
 kernel/ptrace.c          | 10 ++++++++--
 kernel/sched/core.c      | 10 ++++++++--
 security/yama/yama_lsm.c | 12 +++++++++---
 4 files changed, 25 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/cred.h b/include/linux/cred.h
index ebbed2ce6637..856d2622d832 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -357,10 +357,8 @@ static inline void put_cred(const struct cred *_cred)
 extern struct user_namespace init_user_ns;
 #ifdef CONFIG_USER_NS
 #define current_user_ns()	(current_cred_xxx(user_ns))
-#define task_user_ns(task)	(task_cred_xxx((task), user_ns))
 #else
 #define current_user_ns()	(&init_user_ns)
-#define task_user_ns(task)	(&init_user_ns)
 #endif
 
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1f5e55dda955..7b09b88862cc 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -215,8 +215,12 @@ ok:
 	smp_rmb();
 	if (task->mm)
 		dumpable = get_dumpable(task->mm);
-	if (!dumpable  && !ptrace_has_cap(task_user_ns(task), mode))
+	rcu_read_lock();
+	if (!dumpable && !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
+		rcu_read_unlock();
 		return -EPERM;
+	}
+	rcu_read_unlock();
 
 	return security_ptrace_access_check(task, mode);
 }
@@ -280,8 +284,10 @@ static int ptrace_attach(struct task_struct *task, long request,
 
 	if (seize)
 		flags |= PT_SEIZED;
-	if (ns_capable(task_user_ns(task), CAP_SYS_PTRACE))
+	rcu_read_lock();
+	if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE))
 		flags |= PT_PTRACE_CAP;
+	rcu_read_unlock();
 	task->ptrace = flags;
 
 	__ptrace_link(task, current);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d8927fda712..2f5eb1838b3e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4029,8 +4029,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 		goto out_free_cpus_allowed;
 	}
 	retval = -EPERM;
-	if (!check_same_owner(p) && !ns_capable(task_user_ns(p), CAP_SYS_NICE))
-		goto out_unlock;
+	if (!check_same_owner(p)) {
+		rcu_read_lock();
+		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
+			rcu_read_unlock();
+			goto out_unlock;
+		}
+		rcu_read_unlock();
+	}
 
 	retval = security_task_setscheduler(p);
 	if (retval)
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index b4c29848b49d..0e72239aeb05 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -262,14 +262,18 @@ int yama_ptrace_access_check(struct task_struct *child,
 			/* No additional restrictions. */
 			break;
 		case YAMA_SCOPE_RELATIONAL:
+			rcu_read_lock();
 			if (!task_is_descendant(current, child) &&
 			    !ptracer_exception_found(current, child) &&
-			    !ns_capable(task_user_ns(child), CAP_SYS_PTRACE))
+			    !ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE))
 				rc = -EPERM;
+			rcu_read_unlock();
 			break;
 		case YAMA_SCOPE_CAPABILITY:
-			if (!ns_capable(task_user_ns(child), CAP_SYS_PTRACE))
+			rcu_read_lock();
+			if (!ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE))
 				rc = -EPERM;
+			rcu_read_unlock();
 			break;
 		case YAMA_SCOPE_NO_ATTACH:
 		default:
@@ -307,8 +311,10 @@ int yama_ptrace_traceme(struct task_struct *parent)
 	/* Only disallow PTRACE_TRACEME on more aggressive settings. */
 	switch (ptrace_scope) {
 	case YAMA_SCOPE_CAPABILITY:
-		if (!ns_capable(task_user_ns(parent), CAP_SYS_PTRACE))
+		rcu_read_lock();
+		if (!ns_capable(__task_cred(parent)->user_ns, CAP_SYS_PTRACE))
 			rc = -EPERM;
+		rcu_read_unlock();
 		break;
 	case YAMA_SCOPE_NO_ATTACH:
 		rc = -EPERM;
-- 
cgit v1.2.3-55-g7522


From cde1975bc242f3e1072bde623ef378e547b73f91 Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Thu, 26 Jul 2012 06:24:06 -0700
Subject: userns: Implent proc namespace operations

This allows entering a user namespace, and the ability
to store a reference to a user namespace with a bind
mount.

Addition of missing userns_ns_put in userns_install
from Gao feng <gaofeng@cn.fujitsu.com>

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/proc/namespaces.c    |  4 +++
 include/linux/proc_fs.h |  1 +
 kernel/user_namespace.c | 90 +++++++++++++++++++++++++++++++++++++++----------
 3 files changed, 78 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 2a17fd9ae6a9..030250c27d70 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -11,6 +11,7 @@
 #include <net/net_namespace.h>
 #include <linux/ipc_namespace.h>
 #include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
 #include "internal.h"
 
 
@@ -26,6 +27,9 @@ static const struct proc_ns_operations *ns_entries[] = {
 #endif
 #ifdef CONFIG_PID_NS
 	&pidns_operations,
+#endif
+#ifdef CONFIG_USER_NS
+	&userns_operations,
 #endif
 	&mntns_operations,
 };
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 9014c041e752..31447819bc55 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -258,6 +258,7 @@ extern const struct proc_ns_operations netns_operations;
 extern const struct proc_ns_operations utsns_operations;
 extern const struct proc_ns_operations ipcns_operations;
 extern const struct proc_ns_operations pidns_operations;
+extern const struct proc_ns_operations userns_operations;
 extern const struct proc_ns_operations mntns_operations;
 
 union proc_op {
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 49096d559e08..a9460774e77d 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -9,6 +9,7 @@
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/user_namespace.h>
+#include <linux/proc_fs.h>
 #include <linux/highuid.h>
 #include <linux/cred.h>
 #include <linux/securebits.h>
@@ -26,6 +27,24 @@ static struct kmem_cache *user_ns_cachep __read_mostly;
 static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *map);
 
+static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns)
+{
+	/* Start with the same capabilities as init but useless for doing
+	 * anything as the capabilities are bound to the new user namespace.
+	 */
+	cred->securebits = SECUREBITS_DEFAULT;
+	cred->cap_inheritable = CAP_EMPTY_SET;
+	cred->cap_permitted = CAP_FULL_SET;
+	cred->cap_effective = CAP_FULL_SET;
+	cred->cap_bset = CAP_FULL_SET;
+#ifdef CONFIG_KEYS
+	key_put(cred->request_key_auth);
+	cred->request_key_auth = NULL;
+#endif
+	/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
+	cred->user_ns = user_ns;
+}
+
 /*
  * Create a new user namespace, deriving the creator from the user in the
  * passed credentials, and replacing that user with the new root user for the
@@ -53,27 +72,12 @@ int create_user_ns(struct cred *new)
 		return -ENOMEM;
 
 	kref_init(&ns->kref);
+	/* Leave the new->user_ns reference with the new user namespace. */
 	ns->parent = parent_ns;
 	ns->owner = owner;
 	ns->group = group;
 
-	/* Start with the same capabilities as init but useless for doing
-	 * anything as the capabilities are bound to the new user namespace.
-	 */
-	new->securebits = SECUREBITS_DEFAULT;
-	new->cap_inheritable = CAP_EMPTY_SET;
-	new->cap_permitted = CAP_FULL_SET;
-	new->cap_effective = CAP_FULL_SET;
-	new->cap_bset = CAP_FULL_SET;
-#ifdef CONFIG_KEYS
-	key_put(new->request_key_auth);
-	new->request_key_auth = NULL;
-#endif
-	/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
-
-	/* Leave the new->user_ns reference with the new user namespace. */
-	/* Leave the reference to our user_ns with the new cred. */
-	new->user_ns = ns;
+	set_cred_user_ns(new, ns);
 
 	return 0;
 }
@@ -737,6 +741,58 @@ static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
 	return false;
 }
 
+static void *userns_get(struct task_struct *task)
+{
+	struct user_namespace *user_ns;
+
+	rcu_read_lock();
+	user_ns = get_user_ns(__task_cred(task)->user_ns);
+	rcu_read_unlock();
+
+	return user_ns;
+}
+
+static void userns_put(void *ns)
+{
+	put_user_ns(ns);
+}
+
+static int userns_install(struct nsproxy *nsproxy, void *ns)
+{
+	struct user_namespace *user_ns = ns;
+	struct cred *cred;
+
+	/* Don't allow gaining capabilities by reentering
+	 * the same user namespace.
+	 */
+	if (user_ns == current_user_ns())
+		return -EINVAL;
+
+	/* Threaded many not enter a different user namespace */
+	if (atomic_read(&current->mm->mm_users) > 1)
+		return -EINVAL;
+
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	cred = prepare_creds();
+	if (!cred)
+		return -ENOMEM;
+
+	put_user_ns(cred->user_ns);
+	set_cred_user_ns(cred, get_user_ns(user_ns));
+
+	return commit_creds(cred);
+}
+
+const struct proc_ns_operations userns_operations = {
+	.name		= "user",
+	.type		= CLONE_NEWUSER,
+	.get		= userns_get,
+	.put		= userns_put,
+	.install	= userns_install,
+};
+
 static __init int user_namespaces_init(void)
 {
 	user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC);
-- 
cgit v1.2.3-55-g7522


From b2e0d98705e60e45bbb3c0032c48824ad7ae0704 Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Thu, 26 Jul 2012 05:15:35 -0700
Subject: userns: Implement unshare of the user namespace

- Add CLONE_THREAD to the unshare flags if CLONE_NEWUSER is selected
  As changing user namespaces is only valid if all there is only
  a single thread.
- Restore the code to add CLONE_VM if CLONE_THREAD is selected and
  the code to addCLONE_SIGHAND if CLONE_VM is selected.
  Making the constraints in the code clear.

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/nsproxy.h        |  2 +-
 include/linux/user_namespace.h |  9 +++++++++
 kernel/fork.c                  | 25 ++++++++++++++++++++++---
 kernel/nsproxy.c               |  8 ++++----
 kernel/user_namespace.c        | 15 +++++++++++++++
 5 files changed, 51 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index cc37a55ad004..10e5947491c7 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -67,7 +67,7 @@ void exit_task_namespaces(struct task_struct *tsk);
 void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new);
 void free_nsproxy(struct nsproxy *ns);
 int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **,
-	struct fs_struct *);
+	struct cred *, struct fs_struct *);
 int __init nsproxy_cache_init(void);
 
 static inline void put_nsproxy(struct nsproxy *ns)
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 95142cae446a..17651f08d67f 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -39,6 +39,7 @@ static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
 }
 
 extern int create_user_ns(struct cred *new);
+extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred);
 extern void free_user_ns(struct kref *kref);
 
 static inline void put_user_ns(struct user_namespace *ns)
@@ -66,6 +67,14 @@ static inline int create_user_ns(struct cred *new)
 	return -EINVAL;
 }
 
+static inline int unshare_userns(unsigned long unshare_flags,
+				 struct cred **new_cred)
+{
+	if (unshare_flags & CLONE_NEWUSER)
+		return -EINVAL;
+	return 0;
+}
+
 static inline void put_user_ns(struct user_namespace *ns)
 {
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 8c29abb19014..38e53b87402c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1687,7 +1687,7 @@ static int check_unshare_flags(unsigned long unshare_flags)
 	if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
 				CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
 				CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET|
-				CLONE_NEWPID))
+				CLONE_NEWUSER|CLONE_NEWPID))
 		return -EINVAL;
 	/*
 	 * Not implemented, but pretend it works if there is nothing to
@@ -1754,10 +1754,16 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 {
 	struct fs_struct *fs, *new_fs = NULL;
 	struct files_struct *fd, *new_fd = NULL;
+	struct cred *new_cred = NULL;
 	struct nsproxy *new_nsproxy = NULL;
 	int do_sysvsem = 0;
 	int err;
 
+	/*
+	 * If unsharing a user namespace must also unshare the thread.
+	 */
+	if (unshare_flags & CLONE_NEWUSER)
+		unshare_flags |= CLONE_THREAD;
 	/*
 	 * If unsharing a pid namespace must also unshare the thread.
 	 */
@@ -1795,11 +1801,15 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	err = unshare_fd(unshare_flags, &new_fd);
 	if (err)
 		goto bad_unshare_cleanup_fs;
-	err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs);
+	err = unshare_userns(unshare_flags, &new_cred);
 	if (err)
 		goto bad_unshare_cleanup_fd;
+	err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
+					 new_cred, new_fs);
+	if (err)
+		goto bad_unshare_cleanup_cred;
 
-	if (new_fs || new_fd || do_sysvsem || new_nsproxy) {
+	if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) {
 		if (do_sysvsem) {
 			/*
 			 * CLONE_SYSVSEM is equivalent to sys_exit().
@@ -1832,11 +1842,20 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 		}
 
 		task_unlock(current);
+
+		if (new_cred) {
+			/* Install the new user namespace */
+			commit_creds(new_cred);
+			new_cred = NULL;
+		}
 	}
 
 	if (new_nsproxy)
 		put_nsproxy(new_nsproxy);
 
+bad_unshare_cleanup_cred:
+	if (new_cred)
+		put_cred(new_cred);
 bad_unshare_cleanup_fd:
 	if (new_fd)
 		put_files_struct(new_fd);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 2ddd81657a2a..78e2ecb20165 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -186,7 +186,7 @@ void free_nsproxy(struct nsproxy *ns)
  * On success, returns the new nsproxy.
  */
 int unshare_nsproxy_namespaces(unsigned long unshare_flags,
-		struct nsproxy **new_nsp, struct fs_struct *new_fs)
+	struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs)
 {
 	struct user_namespace *user_ns;
 	int err = 0;
@@ -195,12 +195,12 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
 			       CLONE_NEWNET | CLONE_NEWPID)))
 		return 0;
 
-	if (!nsown_capable(CAP_SYS_ADMIN))
+	user_ns = new_cred ? new_cred->user_ns : current_user_ns();
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	user_ns = current_user_ns();
 	*new_nsp = create_new_namespaces(unshare_flags, current, user_ns,
-				new_fs ? new_fs : current->fs);
+					 new_fs ? new_fs : current->fs);
 	if (IS_ERR(*new_nsp)) {
 		err = PTR_ERR(*new_nsp);
 		goto out;
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index a9460774e77d..ce92f7e6290a 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -82,6 +82,21 @@ int create_user_ns(struct cred *new)
 	return 0;
 }
 
+int unshare_userns(unsigned long unshare_flags, struct cred **new_cred)
+{
+	struct cred *cred;
+
+	if (!(unshare_flags & CLONE_NEWUSER))
+		return 0;
+
+	cred = prepare_creds();
+	if (!cred)
+		return -ENOMEM;
+
+	*new_cred = cred;
+	return create_user_ns(cred);
+}
+
 void free_user_ns(struct kref *kref)
 {
 	struct user_namespace *parent, *ns =
-- 
cgit v1.2.3-55-g7522


From 33d6dce607573b5fd7a43168e0d91221b3ca532b Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Fri, 17 Jun 2011 13:33:20 -0700
Subject: proc: Generalize proc inode allocation

Generalize the proc inode allocation so that it can be
used without having to having to create a proc_dir_entry.

This will allow namespace file descriptors to remain light
weight entitities but still have the same inode number
when the backing namespace is the same.

Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/proc/generic.c       | 26 +++++++++++++-------------
 include/linux/proc_fs.h | 10 ++++++++++
 2 files changed, 23 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 0d80cef4cfb9..7b3ae3cc0ef9 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -350,14 +350,14 @@ static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
  * Return an inode number between PROC_DYNAMIC_FIRST and
  * 0xffffffff, or zero on failure.
  */
-static unsigned int get_inode_number(void)
+int proc_alloc_inum(unsigned int *inum)
 {
 	unsigned int i;
 	int error;
 
 retry:
-	if (ida_pre_get(&proc_inum_ida, GFP_KERNEL) == 0)
-		return 0;
+	if (!ida_pre_get(&proc_inum_ida, GFP_KERNEL))
+		return -ENOMEM;
 
 	spin_lock(&proc_inum_lock);
 	error = ida_get_new(&proc_inum_ida, &i);
@@ -365,18 +365,19 @@ retry:
 	if (error == -EAGAIN)
 		goto retry;
 	else if (error)
-		return 0;
+		return error;
 
 	if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
 		spin_lock(&proc_inum_lock);
 		ida_remove(&proc_inum_ida, i);
 		spin_unlock(&proc_inum_lock);
-		return 0;
+		return -ENOSPC;
 	}
-	return PROC_DYNAMIC_FIRST + i;
+	*inum = PROC_DYNAMIC_FIRST + i;
+	return 0;
 }
 
-static void release_inode_number(unsigned int inum)
+void proc_free_inum(unsigned int inum)
 {
 	spin_lock(&proc_inum_lock);
 	ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
@@ -554,13 +555,12 @@ static const struct inode_operations proc_dir_inode_operations = {
 
 static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
 {
-	unsigned int i;
 	struct proc_dir_entry *tmp;
+	int ret;
 	
-	i = get_inode_number();
-	if (i == 0)
-		return -EAGAIN;
-	dp->low_ino = i;
+	ret = proc_alloc_inum(&dp->low_ino);
+	if (ret)
+		return ret;
 
 	if (S_ISDIR(dp->mode)) {
 		if (dp->proc_iops == NULL) {
@@ -764,7 +764,7 @@ EXPORT_SYMBOL(proc_create_data);
 
 static void free_proc_entry(struct proc_dir_entry *de)
 {
-	release_inode_number(de->low_ino);
+	proc_free_inum(de->low_ino);
 
 	if (S_ISLNK(de->mode))
 		kfree(de->data);
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 31447819bc55..bf1d000fbba6 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -176,6 +176,8 @@ extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
 extern struct file *proc_ns_fget(int fd);
 extern bool proc_ns_inode(struct inode *inode);
 
+extern int proc_alloc_inum(unsigned int *pino);
+extern void proc_free_inum(unsigned int inum);
 #else
 
 #define proc_net_fops_create(net, name, mode, fops)  ({ (void)(mode), NULL; })
@@ -235,6 +237,14 @@ static inline bool proc_ns_inode(struct inode *inode)
 	return false;
 }
 
+static inline int proc_alloc_inum(unsigned int *inum)
+{
+	*inum = 1;
+	return 0;
+}
+static inline void proc_free_inum(unsigned int inum)
+{
+}
 #endif /* CONFIG_PROC_FS */
 
 #if !defined(CONFIG_PROC_KCORE)
-- 
cgit v1.2.3-55-g7522


From 98f842e675f96ffac96e6c50315790912b2812be Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Wed, 15 Jun 2011 10:21:48 -0700
Subject: proc: Usable inode numbers for the namespace file descriptors.

Assign a unique proc inode to each namespace, and use that
inode number to ensure we only allocate at most one proc
inode for every namespace in proc.

A single proc inode per namespace allows userspace to test
to see if two processes are in the same namespace.

This has been a long requested feature and only blocked because
a naive implementation would put the id in a global space and
would ultimately require having a namespace for the names of
namespaces, making migration and certain virtualization tricks
impossible.

We still don't have per superblock inode numbers for proc, which
appears necessary for application unaware checkpoint/restart and
migrations (if the application is using namespace file descriptors)
but that is now allowd by the design if it becomes important.

I have preallocated the ipc and uts initial proc inode numbers so
their structures can be statically initialized.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/mount.h                     |  1 +
 fs/namespace.c                 | 14 ++++++++++++++
 fs/proc/namespaces.c           | 24 ++++++++++++++----------
 include/linux/ipc_namespace.h  |  2 ++
 include/linux/pid_namespace.h  |  1 +
 include/linux/proc_fs.h        |  7 ++++++-
 include/linux/user_namespace.h |  1 +
 include/linux/utsname.h        |  1 +
 include/net/net_namespace.h    |  2 ++
 init/version.c                 |  2 ++
 ipc/msgutil.c                  |  2 ++
 ipc/namespace.c                | 16 ++++++++++++++++
 kernel/pid.c                   |  1 +
 kernel/pid_namespace.c         | 12 ++++++++++++
 kernel/user.c                  |  2 ++
 kernel/user_namespace.c        | 15 +++++++++++++++
 kernel/utsname.c               | 17 ++++++++++++++++-
 net/core/net_namespace.c       | 24 ++++++++++++++++++++++++
 18 files changed, 132 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/mount.h b/fs/mount.h
index 630fafc616bb..cd5007980400 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -4,6 +4,7 @@
 
 struct mnt_namespace {
 	atomic_t		count;
+	unsigned int		proc_inum;
 	struct mount *	root;
 	struct list_head	list;
 	struct user_namespace	*user_ns;
diff --git a/fs/namespace.c b/fs/namespace.c
index cab78a74aca3..c1bbe86f4920 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2301,6 +2301,7 @@ dput_out:
 
 static void free_mnt_ns(struct mnt_namespace *ns)
 {
+	proc_free_inum(ns->proc_inum);
 	put_user_ns(ns->user_ns);
 	kfree(ns);
 }
@@ -2317,10 +2318,16 @@ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1);
 static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
 {
 	struct mnt_namespace *new_ns;
+	int ret;
 
 	new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
 	if (!new_ns)
 		return ERR_PTR(-ENOMEM);
+	ret = proc_alloc_inum(&new_ns->proc_inum);
+	if (ret) {
+		kfree(new_ns);
+		return ERR_PTR(ret);
+	}
 	new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
 	atomic_set(&new_ns->count, 1);
 	new_ns->root = NULL;
@@ -2799,10 +2806,17 @@ static int mntns_install(struct nsproxy *nsproxy, void *ns)
 	return 0;
 }
 
+static unsigned int mntns_inum(void *ns)
+{
+	struct mnt_namespace *mnt_ns = ns;
+	return mnt_ns->proc_inum;
+}
+
 const struct proc_ns_operations mntns_operations = {
 	.name		= "mnt",
 	.type		= CLONE_NEWNS,
 	.get		= mntns_get,
 	.put		= mntns_put,
 	.install	= mntns_install,
+	.inum		= mntns_inum,
 };
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 7a6d8d69cdb8..b7a47196c8c3 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -82,7 +82,7 @@ static struct dentry *proc_ns_get_dentry(struct super_block *sb,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	inode = new_inode(sb);
+	inode = iget_locked(sb, ns_ops->inum(ns));
 	if (!inode) {
 		dput(dentry);
 		ns_ops->put(ns);
@@ -90,13 +90,17 @@ static struct dentry *proc_ns_get_dentry(struct super_block *sb,
 	}
 
 	ei = PROC_I(inode);
-	inode->i_ino = get_next_ino();
-	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
-	inode->i_op = &ns_inode_operations;
-	inode->i_mode = S_IFREG | S_IRUGO;
-	inode->i_fop = &ns_file_operations;
-	ei->ns_ops = ns_ops;
-	ei->ns = ns;
+	if (inode->i_state & I_NEW) {
+		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+		inode->i_op = &ns_inode_operations;
+		inode->i_mode = S_IFREG | S_IRUGO;
+		inode->i_fop = &ns_file_operations;
+		ei->ns_ops = ns_ops;
+		ei->ns = ns;
+		unlock_new_inode(inode);
+	} else {
+		ns_ops->put(ns);
+	}
 
 	d_set_d_op(dentry, &ns_dentry_operations);
 	result = d_instantiate_unique(dentry, inode);
@@ -162,12 +166,12 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	if (!ns)
 		goto out_put_task;
 
-	snprintf(name, sizeof(name), "%s", ns_ops->name);
+	snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns));
 	len = strlen(name);
 
 	if (len > buflen)
 		len = buflen;
-	if (copy_to_user(buffer, ns_ops->name, len))
+	if (copy_to_user(buffer, name, len))
 		len = -EFAULT;
 
 	ns_ops->put(ns);
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index f03af702a39d..fe771978e877 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -67,6 +67,8 @@ struct ipc_namespace {
 
 	/* user_ns which owns the ipc ns */
 	struct user_namespace *user_ns;
+
+	unsigned int	proc_inum;
 };
 
 extern struct ipc_namespace init_ipc_ns;
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 4c96acdb2489..bf285999273a 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -37,6 +37,7 @@ struct pid_namespace {
 	kgid_t pid_gid;
 	int hide_pid;
 	int reboot;	/* group exit code if this pidns was rebooted */
+	unsigned int proc_inum;
 };
 
 extern struct pid_namespace init_pid_ns;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index bf1d000fbba6..2e24018b7cec 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -28,7 +28,11 @@ struct mm_struct;
  */
 
 enum {
-	PROC_ROOT_INO = 1,
+	PROC_ROOT_INO		= 1,
+	PROC_IPC_INIT_INO	= 0xEFFFFFFFU,
+	PROC_UTS_INIT_INO	= 0xEFFFFFFEU,
+	PROC_USER_INIT_INO	= 0xEFFFFFFDU,
+	PROC_PID_INIT_INO	= 0xEFFFFFFCU,
 };
 
 /*
@@ -263,6 +267,7 @@ struct proc_ns_operations {
 	void *(*get)(struct task_struct *task);
 	void (*put)(void *ns);
 	int (*install)(struct nsproxy *nsproxy, void *ns);
+	unsigned int (*inum)(void *ns);
 };
 extern const struct proc_ns_operations netns_operations;
 extern const struct proc_ns_operations utsns_operations;
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 17651f08d67f..b9bd2e6c73cc 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -25,6 +25,7 @@ struct user_namespace {
 	struct user_namespace	*parent;
 	kuid_t			owner;
 	kgid_t			group;
+	unsigned int		proc_inum;
 };
 
 extern struct user_namespace init_user_ns;
diff --git a/include/linux/utsname.h b/include/linux/utsname.h
index 221f4a0a7502..239e27733d6c 100644
--- a/include/linux/utsname.h
+++ b/include/linux/utsname.h
@@ -23,6 +23,7 @@ struct uts_namespace {
 	struct kref kref;
 	struct new_utsname name;
 	struct user_namespace *user_ns;
+	unsigned int proc_inum;
 };
 extern struct uts_namespace init_uts_ns;
 
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index c5a43f56b796..de644bcd8613 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -56,6 +56,8 @@ struct net {
 
 	struct user_namespace   *user_ns;	/* Owning user namespace */
 
+	unsigned int		proc_inum;
+
 	struct proc_dir_entry 	*proc_net;
 	struct proc_dir_entry 	*proc_net_stat;
 
diff --git a/init/version.c b/init/version.c
index 86fe0ccb997a..58170f18912d 100644
--- a/init/version.c
+++ b/init/version.c
@@ -12,6 +12,7 @@
 #include <linux/utsname.h>
 #include <generated/utsrelease.h>
 #include <linux/version.h>
+#include <linux/proc_fs.h>
 
 #ifndef CONFIG_KALLSYMS
 #define version(a) Version_ ## a
@@ -34,6 +35,7 @@ struct uts_namespace init_uts_ns = {
 		.domainname	= UTS_DOMAINNAME,
 	},
 	.user_ns = &init_user_ns,
+	.proc_inum = PROC_UTS_INIT_INO,
 };
 EXPORT_SYMBOL_GPL(init_uts_ns);
 
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 26143d377c95..6471f1bdae96 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -16,6 +16,7 @@
 #include <linux/msg.h>
 #include <linux/ipc_namespace.h>
 #include <linux/utsname.h>
+#include <linux/proc_fs.h>
 #include <asm/uaccess.h>
 
 #include "util.h"
@@ -30,6 +31,7 @@ DEFINE_SPINLOCK(mq_lock);
 struct ipc_namespace init_ipc_ns = {
 	.count		= ATOMIC_INIT(1),
 	.user_ns = &init_user_ns,
+	.proc_inum = PROC_IPC_INIT_INO,
 };
 
 atomic_t nr_ipc_ns = ATOMIC_INIT(1);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 72c868277793..cf3386a51de2 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -26,9 +26,16 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	if (ns == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	err = proc_alloc_inum(&ns->proc_inum);
+	if (err) {
+		kfree(ns);
+		return ERR_PTR(err);
+	}
+
 	atomic_set(&ns->count, 1);
 	err = mq_init_ns(ns);
 	if (err) {
+		proc_free_inum(ns->proc_inum);
 		kfree(ns);
 		return ERR_PTR(err);
 	}
@@ -111,6 +118,7 @@ static void free_ipc_ns(struct ipc_namespace *ns)
 	 */
 	ipcns_notify(IPCNS_REMOVED);
 	put_user_ns(ns->user_ns);
+	proc_free_inum(ns->proc_inum);
 	kfree(ns);
 }
 
@@ -172,10 +180,18 @@ static int ipcns_install(struct nsproxy *nsproxy, void *new)
 	return 0;
 }
 
+static unsigned int ipcns_inum(void *vp)
+{
+	struct ipc_namespace *ns = vp;
+
+	return ns->proc_inum;
+}
+
 const struct proc_ns_operations ipcns_operations = {
 	.name		= "ipc",
 	.type		= CLONE_NEWIPC,
 	.get		= ipcns_get,
 	.put		= ipcns_put,
 	.install	= ipcns_install,
+	.inum		= ipcns_inum,
 };
diff --git a/kernel/pid.c b/kernel/pid.c
index 6e8da291de49..3026ddae0a34 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -80,6 +80,7 @@ struct pid_namespace init_pid_ns = {
 	.level = 0,
 	.child_reaper = &init_task,
 	.user_ns = &init_user_ns,
+	.proc_inum = PROC_PID_INIT_INO,
 };
 EXPORT_SYMBOL_GPL(init_pid_ns);
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 68508d330634..560da0dab230 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -107,6 +107,10 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	if (ns->pid_cachep == NULL)
 		goto out_free_map;
 
+	err = proc_alloc_inum(&ns->proc_inum);
+	if (err)
+		goto out_free_map;
+
 	kref_init(&ns->kref);
 	ns->level = level;
 	ns->parent = get_pid_ns(parent_pid_ns);
@@ -133,6 +137,7 @@ static void destroy_pid_namespace(struct pid_namespace *ns)
 {
 	int i;
 
+	proc_free_inum(ns->proc_inum);
 	for (i = 0; i < PIDMAP_ENTRIES; i++)
 		kfree(ns->pidmap[i].page);
 	put_user_ns(ns->user_ns);
@@ -345,12 +350,19 @@ static int pidns_install(struct nsproxy *nsproxy, void *ns)
 	return 0;
 }
 
+static unsigned int pidns_inum(void *ns)
+{
+	struct pid_namespace *pid_ns = ns;
+	return pid_ns->proc_inum;
+}
+
 const struct proc_ns_operations pidns_operations = {
 	.name		= "pid",
 	.type		= CLONE_NEWPID,
 	.get		= pidns_get,
 	.put		= pidns_put,
 	.install	= pidns_install,
+	.inum		= pidns_inum,
 };
 
 static __init int pid_namespaces_init(void)
diff --git a/kernel/user.c b/kernel/user.c
index 750acffbe9ec..33acb5e53a5f 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,6 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/export.h>
 #include <linux/user_namespace.h>
+#include <linux/proc_fs.h>
 
 /*
  * userns count is 1 for root user, 1 for init_uts_ns,
@@ -51,6 +52,7 @@ struct user_namespace init_user_ns = {
 	},
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
+	.proc_inum = PROC_USER_INIT_INO,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 89f6eaed067a..f5975ccf9348 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -58,6 +58,7 @@ int create_user_ns(struct cred *new)
 	struct user_namespace *ns, *parent_ns = new->user_ns;
 	kuid_t owner = new->euid;
 	kgid_t group = new->egid;
+	int ret;
 
 	/* The creator needs a mapping in the parent user namespace
 	 * or else we won't be able to reasonably tell userspace who
@@ -71,6 +72,12 @@ int create_user_ns(struct cred *new)
 	if (!ns)
 		return -ENOMEM;
 
+	ret = proc_alloc_inum(&ns->proc_inum);
+	if (ret) {
+		kmem_cache_free(user_ns_cachep, ns);
+		return ret;
+	}
+
 	kref_init(&ns->kref);
 	/* Leave the new->user_ns reference with the new user namespace. */
 	ns->parent = parent_ns;
@@ -103,6 +110,7 @@ void free_user_ns(struct kref *kref)
 		container_of(kref, struct user_namespace, kref);
 
 	parent = ns->parent;
+	proc_free_inum(ns->proc_inum);
 	kmem_cache_free(user_ns_cachep, ns);
 	put_user_ns(parent);
 }
@@ -808,12 +816,19 @@ static int userns_install(struct nsproxy *nsproxy, void *ns)
 	return commit_creds(cred);
 }
 
+static unsigned int userns_inum(void *ns)
+{
+	struct user_namespace *user_ns = ns;
+	return user_ns->proc_inum;
+}
+
 const struct proc_ns_operations userns_operations = {
 	.name		= "user",
 	.type		= CLONE_NEWUSER,
 	.get		= userns_get,
 	.put		= userns_put,
 	.install	= userns_install,
+	.inum		= userns_inum,
 };
 
 static __init int user_namespaces_init(void)
diff --git a/kernel/utsname.c b/kernel/utsname.c
index fdc619eb61ef..f6336d51d64c 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -36,11 +36,18 @@ static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns,
 					  struct uts_namespace *old_ns)
 {
 	struct uts_namespace *ns;
+	int err;
 
 	ns = create_uts_ns();
 	if (!ns)
 		return ERR_PTR(-ENOMEM);
 
+	err = proc_alloc_inum(&ns->proc_inum);
+	if (err) {
+		kfree(ns);
+		return ERR_PTR(err);
+	}
+
 	down_read(&uts_sem);
 	memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
 	ns->user_ns = get_user_ns(user_ns);
@@ -77,6 +84,7 @@ void free_uts_ns(struct kref *kref)
 
 	ns = container_of(kref, struct uts_namespace, kref);
 	put_user_ns(ns->user_ns);
+	proc_free_inum(ns->proc_inum);
 	kfree(ns);
 }
 
@@ -114,11 +122,18 @@ static int utsns_install(struct nsproxy *nsproxy, void *new)
 	return 0;
 }
 
+static unsigned int utsns_inum(void *vp)
+{
+	struct uts_namespace *ns = vp;
+
+	return ns->proc_inum;
+}
+
 const struct proc_ns_operations utsns_operations = {
 	.name		= "uts",
 	.type		= CLONE_NEWUTS,
 	.get		= utsns_get,
 	.put		= utsns_put,
 	.install	= utsns_install,
+	.inum		= utsns_inum,
 };
-
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index ec2870b44c1f..2e9a3132b8dd 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -381,6 +381,21 @@ struct net *get_net_ns_by_pid(pid_t pid)
 }
 EXPORT_SYMBOL_GPL(get_net_ns_by_pid);
 
+static __net_init int net_ns_net_init(struct net *net)
+{
+	return proc_alloc_inum(&net->proc_inum);
+}
+
+static __net_exit void net_ns_net_exit(struct net *net)
+{
+	proc_free_inum(net->proc_inum);
+}
+
+static struct pernet_operations __net_initdata net_ns_ops = {
+	.init = net_ns_net_init,
+	.exit = net_ns_net_exit,
+};
+
 static int __init net_ns_init(void)
 {
 	struct net_generic *ng;
@@ -412,6 +427,8 @@ static int __init net_ns_init(void)
 
 	mutex_unlock(&net_mutex);
 
+	register_pernet_subsys(&net_ns_ops);
+
 	return 0;
 }
 
@@ -640,11 +657,18 @@ static int netns_install(struct nsproxy *nsproxy, void *ns)
 	return 0;
 }
 
+static unsigned int netns_inum(void *ns)
+{
+	struct net *net = ns;
+	return net->proc_inum;
+}
+
 const struct proc_ns_operations netns_operations = {
 	.name		= "net",
 	.type		= CLONE_NEWNET,
 	.get		= netns_get,
 	.put		= netns_put,
 	.install	= netns_install,
+	.inum		= netns_inum,
 };
 #endif
-- 
cgit v1.2.3-55-g7522


From 97fa4cf442ff2872000d9110686371775795a32b Mon Sep 17 00:00:00 2001
From: Sebastian Hesselbarth
Date: Sat, 17 Nov 2012 15:22:22 +0100
Subject: clk: mvebu: add mvebu core clocks.

This driver allows to provide DT clocks for core clocks found on
Marvell Kirkwood, Dove & 370/XP SoCs. The core clock frequencies and
ratios are determined by decoding the Sample-At-Reset registers.

Although technically correct, using a divider of 0 will lead to
div_by_zero panic. Let's use a ratio of 0/1 instead to fail later
with a zero clock.

Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by Gregory CLEMENT <gregory.clement@free-electrons.com>
---
 .../devicetree/bindings/clock/mvebu-core-clock.txt |  47 ++
 drivers/clk/Kconfig                                |   2 +
 drivers/clk/Makefile                               |   1 +
 drivers/clk/mvebu/Kconfig                          |   3 +
 drivers/clk/mvebu/Makefile                         |   1 +
 drivers/clk/mvebu/clk-core.c                       | 675 +++++++++++++++++++++
 drivers/clk/mvebu/clk-core.h                       |  18 +
 drivers/clk/mvebu/clk.c                            |  23 +
 include/linux/clk/mvebu.h                          |  22 +
 9 files changed, 792 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/mvebu-core-clock.txt
 create mode 100644 drivers/clk/mvebu/Kconfig
 create mode 100644 drivers/clk/mvebu/Makefile
 create mode 100644 drivers/clk/mvebu/clk-core.c
 create mode 100644 drivers/clk/mvebu/clk-core.h
 create mode 100644 drivers/clk/mvebu/clk.c
 create mode 100644 include/linux/clk/mvebu.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/mvebu-core-clock.txt b/Documentation/devicetree/bindings/clock/mvebu-core-clock.txt
new file mode 100644
index 000000000000..1e662948661e
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/mvebu-core-clock.txt
@@ -0,0 +1,47 @@
+* Core Clock bindings for Marvell MVEBU SoCs
+
+Marvell MVEBU SoCs usually allow to determine core clock frequencies by
+reading the Sample-At-Reset (SAR) register. The core clock consumer should
+specify the desired clock by having the clock ID in its "clocks" phandle cell.
+
+The following is a list of provided IDs and clock names on Armada 370/XP:
+ 0 = tclk    (Internal Bus clock)
+ 1 = cpuclk  (CPU clock)
+ 2 = nbclk   (L2 Cache clock)
+ 3 = hclk    (DRAM control clock)
+ 4 = dramclk (DDR clock)
+
+The following is a list of provided IDs and clock names on Kirkwood and Dove:
+ 0 = tclk   (Internal Bus clock)
+ 1 = cpuclk (CPU0 clock)
+ 2 = l2clk  (L2 Cache clock derived from CPU0 clock)
+ 3 = ddrclk (DDR controller clock derived from CPU0 clock)
+
+Required properties:
+- compatible : shall be one of the following:
+	"marvell,armada-370-core-clock" - For Armada 370 SoC core clocks
+	"marvell,armada-xp-core-clock" - For Armada XP SoC core clocks
+	"marvell,dove-core-clock" - for Dove SoC core clocks
+	"marvell,kirkwood-core-clock" - for Kirkwood SoC (except mv88f6180)
+	"marvell,mv88f6180-core-clock" - for Kirkwood MV88f6180 SoC
+- reg : shall be the register address of the Sample-At-Reset (SAR) register
+- #clock-cells : from common clock binding; shall be set to 1
+
+Optional properties:
+- clock-output-names : from common clock binding; allows overwrite default clock
+	output names ("tclk", "cpuclk", "l2clk", "ddrclk")
+
+Example:
+
+core_clk: core-clocks@d0214 {
+	compatible = "marvell,dove-core-clock";
+	reg = <0xd0214 0x4>;
+	#clock-cells = <1>;
+};
+
+spi0: spi@10600 {
+	compatible = "marvell,orion-spi";
+	/* ... */
+	/* get tclk from core clock provider */
+	clocks = <&core_clk 0>;
+};
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index bace9e98f75d..60427c0d23e6 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -54,3 +54,5 @@ config COMMON_CLK_MAX77686
 	  This driver supports Maxim 77686 crystal oscillator clock. 
 
 endmenu
+
+source "drivers/clk/mvebu/Kconfig"
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 71a25b91de00..d0a14ae8d49c 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_PLAT_SPEAR)	+= spear/
 obj-$(CONFIG_ARCH_U300)		+= clk-u300.o
 obj-$(CONFIG_COMMON_CLK_VERSATILE) += versatile/
 obj-$(CONFIG_ARCH_PRIMA2)	+= clk-prima2.o
+obj-$(CONFIG_PLAT_ORION)	+= mvebu/
 ifeq ($(CONFIG_COMMON_CLK), y)
 obj-$(CONFIG_ARCH_MMP)		+= mmp/
 endif
diff --git a/drivers/clk/mvebu/Kconfig b/drivers/clk/mvebu/Kconfig
new file mode 100644
index 000000000000..fd7bf97ff74d
--- /dev/null
+++ b/drivers/clk/mvebu/Kconfig
@@ -0,0 +1,3 @@
+config MVEBU_CLK_CORE
+       bool
+
diff --git a/drivers/clk/mvebu/Makefile b/drivers/clk/mvebu/Makefile
new file mode 100644
index 000000000000..de1d9617f75a
--- /dev/null
+++ b/drivers/clk/mvebu/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_MVEBU_CLK_CORE) 	+= clk.o clk-core.o
diff --git a/drivers/clk/mvebu/clk-core.c b/drivers/clk/mvebu/clk-core.c
new file mode 100644
index 000000000000..69056a7479e8
--- /dev/null
+++ b/drivers/clk/mvebu/clk-core.c
@@ -0,0 +1,675 @@
+/*
+ * Marvell EBU clock core handling defined at reset
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ * Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include "clk-core.h"
+
+struct core_ratio {
+	int id;
+	const char *name;
+};
+
+struct core_clocks {
+	u32 (*get_tclk_freq)(void __iomem *sar);
+	u32 (*get_cpu_freq)(void __iomem *sar);
+	void (*get_clk_ratio)(void __iomem *sar, int id, int *mult, int *div);
+	const struct core_ratio *ratios;
+	int num_ratios;
+};
+
+static struct clk_onecell_data clk_data;
+
+static void __init mvebu_clk_core_setup(struct device_node *np,
+				 struct core_clocks *coreclk)
+{
+	const char *tclk_name = "tclk";
+	const char *cpuclk_name = "cpuclk";
+	void __iomem *base;
+	unsigned long rate;
+	int n;
+
+	base = of_iomap(np, 0);
+	if (WARN_ON(!base))
+		return;
+
+	/*
+	 * Allocate struct for TCLK, cpu clk, and core ratio clocks
+	 */
+	clk_data.clk_num = 2 + coreclk->num_ratios;
+	clk_data.clks = kzalloc(clk_data.clk_num * sizeof(struct clk *),
+				GFP_KERNEL);
+	if (WARN_ON(!clk_data.clks))
+		return;
+
+	/*
+	 * Register TCLK
+	 */
+	of_property_read_string_index(np, "clock-output-names", 0,
+				      &tclk_name);
+	rate = coreclk->get_tclk_freq(base);
+	clk_data.clks[0] = clk_register_fixed_rate(NULL, tclk_name, NULL,
+						   CLK_IS_ROOT, rate);
+	WARN_ON(IS_ERR(clk_data.clks[0]));
+
+	/*
+	 * Register CPU clock
+	 */
+	of_property_read_string_index(np, "clock-output-names", 1,
+				      &cpuclk_name);
+	rate = coreclk->get_cpu_freq(base);
+	clk_data.clks[1] = clk_register_fixed_rate(NULL, cpuclk_name, NULL,
+						   CLK_IS_ROOT, rate);
+	WARN_ON(IS_ERR(clk_data.clks[1]));
+
+	/*
+	 * Register fixed-factor clocks derived from CPU clock
+	 */
+	for (n = 0; n < coreclk->num_ratios; n++) {
+		const char *rclk_name = coreclk->ratios[n].name;
+		int mult, div;
+
+		of_property_read_string_index(np, "clock-output-names",
+					      2+n, &rclk_name);
+		coreclk->get_clk_ratio(base, coreclk->ratios[n].id,
+				       &mult, &div);
+		clk_data.clks[2+n] = clk_register_fixed_factor(NULL, rclk_name,
+				       cpuclk_name, 0, mult, div);
+		WARN_ON(IS_ERR(clk_data.clks[2+n]));
+	};
+
+	/*
+	 * SAR register isn't needed anymore
+	 */
+	iounmap(base);
+
+	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
+}
+
+#ifdef CONFIG_MACH_ARMADA_370_XP
+/*
+ * Armada 370/XP Sample At Reset is a 64 bit bitfiled split in two
+ * register of 32 bits
+ */
+
+#define SARL				    0	/* Low part [0:31] */
+#define	    SARL_AXP_PCLK_FREQ_OPT	    21
+#define	    SARL_AXP_PCLK_FREQ_OPT_MASK	    0x7
+#define	    SARL_A370_PCLK_FREQ_OPT	    11
+#define	    SARL_A370_PCLK_FREQ_OPT_MASK    0xF
+#define	    SARL_AXP_FAB_FREQ_OPT	    24
+#define	    SARL_AXP_FAB_FREQ_OPT_MASK	    0xF
+#define	    SARL_A370_FAB_FREQ_OPT	    15
+#define	    SARL_A370_FAB_FREQ_OPT_MASK	    0x1F
+#define	    SARL_A370_TCLK_FREQ_OPT	    20
+#define	    SARL_A370_TCLK_FREQ_OPT_MASK    0x1
+#define SARH				    4	/* High part [32:63] */
+#define	    SARH_AXP_PCLK_FREQ_OPT	    (52-32)
+#define	    SARH_AXP_PCLK_FREQ_OPT_MASK	    0x1
+#define	    SARH_AXP_PCLK_FREQ_OPT_SHIFT    3
+#define	    SARH_AXP_FAB_FREQ_OPT	    (51-32)
+#define	    SARH_AXP_FAB_FREQ_OPT_MASK	    0x1
+#define	    SARH_AXP_FAB_FREQ_OPT_SHIFT	    4
+
+static const u32 __initconst armada_370_tclk_frequencies[] = {
+	16600000,
+	20000000,
+};
+
+static u32 __init armada_370_get_tclk_freq(void __iomem *sar)
+{
+	u8 tclk_freq_select = 0;
+
+	tclk_freq_select = ((readl(sar) >> SARL_A370_TCLK_FREQ_OPT) &
+			    SARL_A370_TCLK_FREQ_OPT_MASK);
+	return armada_370_tclk_frequencies[tclk_freq_select];
+}
+
+static const u32 __initconst armada_370_cpu_frequencies[] = {
+	400000000,
+	533000000,
+	667000000,
+	800000000,
+	1000000000,
+	1067000000,
+	1200000000,
+};
+
+static u32 __init armada_370_get_cpu_freq(void __iomem *sar)
+{
+	u32 cpu_freq;
+	u8 cpu_freq_select = 0;
+
+	cpu_freq_select = ((readl(sar) >> SARL_A370_PCLK_FREQ_OPT) &
+			   SARL_A370_PCLK_FREQ_OPT_MASK);
+	if (cpu_freq_select > ARRAY_SIZE(armada_370_cpu_frequencies)) {
+		pr_err("CPU freq select unsuported %d\n", cpu_freq_select);
+		cpu_freq = 0;
+	} else
+		cpu_freq = armada_370_cpu_frequencies[cpu_freq_select];
+
+	return cpu_freq;
+}
+
+enum { A370_XP_NBCLK, A370_XP_HCLK, A370_XP_DRAMCLK };
+
+static const struct core_ratio __initconst armada_370_xp_core_ratios[] = {
+	{ .id = A370_XP_NBCLK,	 .name = "nbclk" },
+	{ .id = A370_XP_HCLK,	 .name = "hclk" },
+	{ .id = A370_XP_DRAMCLK, .name = "dramclk" },
+};
+
+static const int __initconst armada_370_xp_nbclk_ratios[32][2] = {
+	{0, 1}, {1, 2}, {2, 2}, {2, 2},
+	{1, 2}, {1, 2}, {1, 1}, {2, 3},
+	{0, 1}, {1, 2}, {2, 4}, {0, 1},
+	{1, 2}, {0, 1}, {0, 1}, {2, 2},
+	{0, 1}, {0, 1}, {0, 1}, {1, 1},
+	{2, 3}, {0, 1}, {0, 1}, {0, 1},
+	{0, 1}, {0, 1}, {0, 1}, {1, 1},
+	{0, 1}, {0, 1}, {0, 1}, {0, 1},
+};
+
+static const int __initconst armada_370_xp_hclk_ratios[32][2] = {
+	{0, 1}, {1, 2}, {2, 6}, {2, 3},
+	{1, 3}, {1, 4}, {1, 2}, {2, 6},
+	{0, 1}, {1, 6}, {2, 10}, {0, 1},
+	{1, 4}, {0, 1}, {0, 1}, {2, 5},
+	{0, 1}, {0, 1}, {0, 1}, {1, 2},
+	{2, 6}, {0, 1}, {0, 1}, {0, 1},
+	{0, 1}, {0, 1}, {0, 1}, {1, 1},
+	{0, 1}, {0, 1}, {0, 1}, {0, 1},
+};
+
+static const int __initconst armada_370_xp_dramclk_ratios[32][2] = {
+	{0, 1}, {1, 2}, {2, 3}, {2, 3},
+	{1, 3}, {1, 2}, {1, 2}, {2, 6},
+	{0, 1}, {1, 3}, {2, 5}, {0, 1},
+	{1, 4}, {0, 1}, {0, 1}, {2, 5},
+	{0, 1}, {0, 1}, {0, 1}, {1, 1},
+	{2, 3}, {0, 1}, {0, 1}, {0, 1},
+	{0, 1}, {0, 1}, {0, 1}, {1, 1},
+	{0, 1}, {0, 1}, {0, 1}, {0, 1},
+};
+
+static void __init armada_370_xp_get_clk_ratio(u32 opt,
+	void __iomem *sar, int id, int *mult, int *div)
+{
+	switch (id) {
+	case A370_XP_NBCLK:
+		*mult = armada_370_xp_nbclk_ratios[opt][0];
+		*div = armada_370_xp_nbclk_ratios[opt][1];
+		break;
+	case A370_XP_HCLK:
+		*mult = armada_370_xp_hclk_ratios[opt][0];
+		*div = armada_370_xp_hclk_ratios[opt][1];
+		break;
+	case A370_XP_DRAMCLK:
+		*mult = armada_370_xp_dramclk_ratios[opt][0];
+		*div = armada_370_xp_dramclk_ratios[opt][1];
+		break;
+	}
+}
+
+static void __init armada_370_get_clk_ratio(
+	void __iomem *sar, int id, int *mult, int *div)
+{
+	u32 opt = ((readl(sar) >> SARL_A370_FAB_FREQ_OPT) &
+		SARL_A370_FAB_FREQ_OPT_MASK);
+
+	armada_370_xp_get_clk_ratio(opt, sar, id, mult, div);
+}
+
+
+static const struct core_clocks armada_370_core_clocks = {
+	.get_tclk_freq = armada_370_get_tclk_freq,
+	.get_cpu_freq = armada_370_get_cpu_freq,
+	.get_clk_ratio = armada_370_get_clk_ratio,
+	.ratios = armada_370_xp_core_ratios,
+	.num_ratios = ARRAY_SIZE(armada_370_xp_core_ratios),
+};
+
+static const u32 __initconst armada_xp_cpu_frequencies[] = {
+	1000000000,
+	1066000000,
+	1200000000,
+	1333000000,
+	1500000000,
+	1666000000,
+	1800000000,
+	2000000000,
+	667000000,
+	0,
+	800000000,
+	1600000000,
+};
+
+/* For Armada XP TCLK frequency is fix: 250MHz */
+static u32 __init armada_xp_get_tclk_freq(void __iomem *sar)
+{
+	return 250 * 1000 * 1000;
+}
+
+static u32 __init armada_xp_get_cpu_freq(void __iomem *sar)
+{
+	u32 cpu_freq;
+	u8 cpu_freq_select = 0;
+
+	cpu_freq_select = ((readl(sar) >> SARL_AXP_PCLK_FREQ_OPT) &
+			   SARL_AXP_PCLK_FREQ_OPT_MASK);
+	/*
+	 * The upper bit is not contiguous to the other ones and
+	 * located in the high part of the SAR registers
+	 */
+	cpu_freq_select |= (((readl(sar+4) >> SARH_AXP_PCLK_FREQ_OPT) &
+			     SARH_AXP_PCLK_FREQ_OPT_MASK)
+			    << SARH_AXP_PCLK_FREQ_OPT_SHIFT);
+	if (cpu_freq_select > ARRAY_SIZE(armada_xp_cpu_frequencies)) {
+		pr_err("CPU freq select unsuported: %d\n", cpu_freq_select);
+		cpu_freq = 0;
+	} else
+		cpu_freq = armada_xp_cpu_frequencies[cpu_freq_select];
+
+	return cpu_freq;
+}
+
+static void __init armada_xp_get_clk_ratio(
+	void __iomem *sar, int id, int *mult, int *div)
+{
+
+	u32 opt = ((readl(sar) >> SARL_AXP_FAB_FREQ_OPT) &
+	      SARL_AXP_FAB_FREQ_OPT_MASK);
+	/*
+	 * The upper bit is not contiguous to the other ones and
+	 * located in the high part of the SAR registers
+	 */
+	opt |= (((readl(sar+4) >> SARH_AXP_FAB_FREQ_OPT) &
+		SARH_AXP_FAB_FREQ_OPT_MASK)
+	       << SARH_AXP_FAB_FREQ_OPT_SHIFT);
+
+	armada_370_xp_get_clk_ratio(opt, sar, id, mult, div);
+}
+
+static const struct core_clocks armada_xp_core_clocks = {
+	.get_tclk_freq = armada_xp_get_tclk_freq,
+	.get_cpu_freq = armada_xp_get_cpu_freq,
+	.get_clk_ratio = armada_xp_get_clk_ratio,
+	.ratios = armada_370_xp_core_ratios,
+	.num_ratios = ARRAY_SIZE(armada_370_xp_core_ratios),
+};
+
+#endif /* CONFIG_MACH_ARMADA_370_XP */
+
+/*
+ * Dove PLL sample-at-reset configuration
+ *
+ * SAR0[8:5]   : CPU frequency
+ *		 5  = 1000 MHz
+ *		 6  =  933 MHz
+ *		 7  =  933 MHz
+ *		 8  =  800 MHz
+ *		 9  =  800 MHz
+ *		 10 =  800 MHz
+ *		 11 = 1067 MHz
+ *		 12 =  667 MHz
+ *		 13 =  533 MHz
+ *		 14 =  400 MHz
+ *		 15 =  333 MHz
+ *		 others reserved.
+ *
+ * SAR0[11:9]  : CPU to L2 Clock divider ratio
+ *		 0 = (1/1) * CPU
+ *		 2 = (1/2) * CPU
+ *		 4 = (1/3) * CPU
+ *		 6 = (1/4) * CPU
+ *		 others reserved.
+ *
+ * SAR0[15:12] : CPU to DDR DRAM Clock divider ratio
+ *		 0  = (1/1) * CPU
+ *		 2  = (1/2) * CPU
+ *		 3  = (2/5) * CPU
+ *		 4  = (1/3) * CPU
+ *		 6  = (1/4) * CPU
+ *		 8  = (1/5) * CPU
+ *		 10 = (1/6) * CPU
+ *		 12 = (1/7) * CPU
+ *		 14 = (1/8) * CPU
+ *		 15 = (1/10) * CPU
+ *		 others reserved.
+ *
+ * SAR0[24:23] : TCLK frequency
+ *		 0 = 166 MHz
+ *		 1 = 125 MHz
+ *		 others reserved.
+ */
+#ifdef CONFIG_ARCH_DOVE
+#define SAR_DOVE_CPU_FREQ		5
+#define SAR_DOVE_CPU_FREQ_MASK		0xf
+#define SAR_DOVE_L2_RATIO		9
+#define SAR_DOVE_L2_RATIO_MASK		0x7
+#define SAR_DOVE_DDR_RATIO		12
+#define SAR_DOVE_DDR_RATIO_MASK		0xf
+#define SAR_DOVE_TCLK_FREQ		23
+#define SAR_DOVE_TCLK_FREQ_MASK		0x3
+
+static const u32 __initconst dove_tclk_frequencies[] = {
+	166666667,
+	125000000,
+	0, 0
+};
+
+static u32 __init dove_get_tclk_freq(void __iomem *sar)
+{
+	u32 opt = (readl(sar) >> SAR_DOVE_TCLK_FREQ) &
+		SAR_DOVE_TCLK_FREQ_MASK;
+	return dove_tclk_frequencies[opt];
+}
+
+static const u32 __initconst dove_cpu_frequencies[] = {
+	0, 0, 0, 0, 0,
+	1000000000,
+	933333333, 933333333,
+	800000000, 800000000, 800000000,
+	1066666667,
+	666666667,
+	533333333,
+	400000000,
+	333333333
+};
+
+static u32 __init dove_get_cpu_freq(void __iomem *sar)
+{
+	u32 opt = (readl(sar) >> SAR_DOVE_CPU_FREQ) &
+		SAR_DOVE_CPU_FREQ_MASK;
+	return dove_cpu_frequencies[opt];
+}
+
+enum { DOVE_CPU_TO_L2, DOVE_CPU_TO_DDR };
+
+static const struct core_ratio __initconst dove_core_ratios[] = {
+	{ .id = DOVE_CPU_TO_L2, .name = "l2clk", },
+	{ .id = DOVE_CPU_TO_DDR, .name = "ddrclk", }
+};
+
+static const int __initconst dove_cpu_l2_ratios[8][2] = {
+	{ 1, 1 }, { 0, 1 }, { 1, 2 }, { 0, 1 },
+	{ 1, 3 }, { 0, 1 }, { 1, 4 }, { 0, 1 }
+};
+
+static const int __initconst dove_cpu_ddr_ratios[16][2] = {
+	{ 1, 1 }, { 0, 1 }, { 1, 2 }, { 2, 5 },
+	{ 1, 3 }, { 0, 1 }, { 1, 4 }, { 0, 1 },
+	{ 1, 5 }, { 0, 1 }, { 1, 6 }, { 0, 1 },
+	{ 1, 7 }, { 0, 1 }, { 1, 8 }, { 1, 10 }
+};
+
+static void __init dove_get_clk_ratio(
+	void __iomem *sar, int id, int *mult, int *div)
+{
+	switch (id) {
+	case DOVE_CPU_TO_L2:
+	{
+		u32 opt = (readl(sar) >> SAR_DOVE_L2_RATIO) &
+			SAR_DOVE_L2_RATIO_MASK;
+		*mult = dove_cpu_l2_ratios[opt][0];
+		*div = dove_cpu_l2_ratios[opt][1];
+		break;
+	}
+	case DOVE_CPU_TO_DDR:
+	{
+		u32 opt = (readl(sar) >> SAR_DOVE_DDR_RATIO) &
+			SAR_DOVE_DDR_RATIO_MASK;
+		*mult = dove_cpu_ddr_ratios[opt][0];
+		*div = dove_cpu_ddr_ratios[opt][1];
+		break;
+	}
+	}
+}
+
+static const struct core_clocks dove_core_clocks = {
+	.get_tclk_freq = dove_get_tclk_freq,
+	.get_cpu_freq = dove_get_cpu_freq,
+	.get_clk_ratio = dove_get_clk_ratio,
+	.ratios = dove_core_ratios,
+	.num_ratios = ARRAY_SIZE(dove_core_ratios),
+};
+#endif /* CONFIG_ARCH_DOVE */
+
+/*
+ * Kirkwood PLL sample-at-reset configuration
+ * (6180 has different SAR layout than other Kirkwood SoCs)
+ *
+ * SAR0[4:3,22,1] : CPU frequency (6281,6292,6282)
+ *	4  =  600 MHz
+ *	6  =  800 MHz
+ *	7  = 1000 MHz
+ *	9  = 1200 MHz
+ *	12 = 1500 MHz
+ *	13 = 1600 MHz
+ *	14 = 1800 MHz
+ *	15 = 2000 MHz
+ *	others reserved.
+ *
+ * SAR0[19,10:9] : CPU to L2 Clock divider ratio (6281,6292,6282)
+ *	1 = (1/2) * CPU
+ *	3 = (1/3) * CPU
+ *	5 = (1/4) * CPU
+ *	others reserved.
+ *
+ * SAR0[8:5] : CPU to DDR DRAM Clock divider ratio (6281,6292,6282)
+ *	2 = (1/2) * CPU
+ *	4 = (1/3) * CPU
+ *	6 = (1/4) * CPU
+ *	7 = (2/9) * CPU
+ *	8 = (1/5) * CPU
+ *	9 = (1/6) * CPU
+ *	others reserved.
+ *
+ * SAR0[4:2] : Kirkwood 6180 cpu/l2/ddr clock configuration (6180 only)
+ *	5 = [CPU =  600 MHz, L2 = (1/2) * CPU, DDR = 200 MHz = (1/3) * CPU]
+ *	6 = [CPU =  800 MHz, L2 = (1/2) * CPU, DDR = 200 MHz = (1/4) * CPU]
+ *	7 = [CPU = 1000 MHz, L2 = (1/2) * CPU, DDR = 200 MHz = (1/5) * CPU]
+ *	others reserved.
+ *
+ * SAR0[21] : TCLK frequency
+ *	0 = 200 MHz
+ *	1 = 166 MHz
+ *	others reserved.
+ */
+#ifdef CONFIG_ARCH_KIRKWOOD
+#define SAR_KIRKWOOD_CPU_FREQ(x)	\
+	(((x & (1 <<  1)) >>  1) |	\
+	 ((x & (1 << 22)) >> 21) |	\
+	 ((x & (3 <<  3)) >>  1))
+#define SAR_KIRKWOOD_L2_RATIO(x)	\
+	(((x & (3 <<  9)) >> 9) |	\
+	 (((x & (1 << 19)) >> 17)))
+#define SAR_KIRKWOOD_DDR_RATIO		5
+#define SAR_KIRKWOOD_DDR_RATIO_MASK	0xf
+#define SAR_MV88F6180_CLK		2
+#define SAR_MV88F6180_CLK_MASK		0x7
+#define SAR_KIRKWOOD_TCLK_FREQ		21
+#define SAR_KIRKWOOD_TCLK_FREQ_MASK	0x1
+
+enum { KIRKWOOD_CPU_TO_L2, KIRKWOOD_CPU_TO_DDR };
+
+static const struct core_ratio __initconst kirkwood_core_ratios[] = {
+	{ .id = KIRKWOOD_CPU_TO_L2, .name = "l2clk", },
+	{ .id = KIRKWOOD_CPU_TO_DDR, .name = "ddrclk", }
+};
+
+static u32 __init kirkwood_get_tclk_freq(void __iomem *sar)
+{
+	u32 opt = (readl(sar) >> SAR_KIRKWOOD_TCLK_FREQ) &
+		SAR_KIRKWOOD_TCLK_FREQ_MASK;
+	return (opt) ? 166666667 : 200000000;
+}
+
+static const u32 __initconst kirkwood_cpu_frequencies[] = {
+	0, 0, 0, 0,
+	600000000,
+	0,
+	800000000,
+	1000000000,
+	0,
+	1200000000,
+	0, 0,
+	1500000000,
+	1600000000,
+	1800000000,
+	2000000000
+};
+
+static u32 __init kirkwood_get_cpu_freq(void __iomem *sar)
+{
+	u32 opt = SAR_KIRKWOOD_CPU_FREQ(readl(sar));
+	return kirkwood_cpu_frequencies[opt];
+}
+
+static const int __initconst kirkwood_cpu_l2_ratios[8][2] = {
+	{ 0, 1 }, { 1, 2 }, { 0, 1 }, { 1, 3 },
+	{ 0, 1 }, { 1, 4 }, { 0, 1 }, { 0, 1 }
+};
+
+static const int __initconst kirkwood_cpu_ddr_ratios[16][2] = {
+	{ 0, 1 }, { 0, 1 }, { 1, 2 }, { 0, 1 },
+	{ 1, 3 }, { 0, 1 }, { 1, 4 }, { 2, 9 },
+	{ 1, 5 }, { 1, 6 }, { 0, 1 }, { 0, 1 },
+	{ 0, 1 }, { 0, 1 }, { 0, 1 }, { 0, 1 }
+};
+
+static void __init kirkwood_get_clk_ratio(
+	void __iomem *sar, int id, int *mult, int *div)
+{
+	switch (id) {
+	case KIRKWOOD_CPU_TO_L2:
+	{
+		u32 opt = SAR_KIRKWOOD_L2_RATIO(readl(sar));
+		*mult = kirkwood_cpu_l2_ratios[opt][0];
+		*div = kirkwood_cpu_l2_ratios[opt][1];
+		break;
+	}
+	case KIRKWOOD_CPU_TO_DDR:
+	{
+		u32 opt = (readl(sar) >> SAR_KIRKWOOD_DDR_RATIO) &
+			SAR_KIRKWOOD_DDR_RATIO_MASK;
+		*mult = kirkwood_cpu_ddr_ratios[opt][0];
+		*div = kirkwood_cpu_ddr_ratios[opt][1];
+		break;
+	}
+	}
+}
+
+static const struct core_clocks kirkwood_core_clocks = {
+	.get_tclk_freq = kirkwood_get_tclk_freq,
+	.get_cpu_freq = kirkwood_get_cpu_freq,
+	.get_clk_ratio = kirkwood_get_clk_ratio,
+	.ratios = kirkwood_core_ratios,
+	.num_ratios = ARRAY_SIZE(kirkwood_core_ratios),
+};
+
+static const u32 __initconst mv88f6180_cpu_frequencies[] = {
+	0, 0, 0, 0, 0,
+	600000000,
+	800000000,
+	1000000000
+};
+
+static u32 __init mv88f6180_get_cpu_freq(void __iomem *sar)
+{
+	u32 opt = (readl(sar) >> SAR_MV88F6180_CLK) & SAR_MV88F6180_CLK_MASK;
+	return mv88f6180_cpu_frequencies[opt];
+}
+
+static const int __initconst mv88f6180_cpu_ddr_ratios[8][2] = {
+	{ 0, 1 }, { 0, 1 }, { 0, 1 }, { 0, 1 },
+	{ 0, 1 }, { 1, 3 }, { 1, 4 }, { 1, 5 }
+};
+
+static void __init mv88f6180_get_clk_ratio(
+	void __iomem *sar, int id, int *mult, int *div)
+{
+	switch (id) {
+	case KIRKWOOD_CPU_TO_L2:
+	{
+		/* mv88f6180 has a fixed 1:2 CPU-to-L2 ratio */
+		*mult = 1;
+		*div = 2;
+		break;
+	}
+	case KIRKWOOD_CPU_TO_DDR:
+	{
+		u32 opt = (readl(sar) >> SAR_MV88F6180_CLK) &
+			SAR_MV88F6180_CLK_MASK;
+		*mult = mv88f6180_cpu_ddr_ratios[opt][0];
+		*div = mv88f6180_cpu_ddr_ratios[opt][1];
+		break;
+	}
+	}
+}
+
+static const struct core_clocks mv88f6180_core_clocks = {
+	.get_tclk_freq = kirkwood_get_tclk_freq,
+	.get_cpu_freq = mv88f6180_get_cpu_freq,
+	.get_clk_ratio = mv88f6180_get_clk_ratio,
+	.ratios = kirkwood_core_ratios,
+	.num_ratios = ARRAY_SIZE(kirkwood_core_ratios),
+};
+#endif /* CONFIG_ARCH_KIRKWOOD */
+
+static const __initdata struct of_device_id clk_core_match[] = {
+#ifdef CONFIG_MACH_ARMADA_370_XP
+	{
+		.compatible = "marvell,armada-370-core-clock",
+		.data = &armada_370_core_clocks,
+	},
+	{
+		.compatible = "marvell,armada-xp-core-clock",
+		.data = &armada_xp_core_clocks,
+	},
+#endif
+#ifdef CONFIG_ARCH_DOVE
+	{
+		.compatible = "marvell,dove-core-clock",
+		.data = &dove_core_clocks,
+	},
+#endif
+
+#ifdef CONFIG_ARCH_KIRKWOOD
+	{
+		.compatible = "marvell,kirkwood-core-clock",
+		.data = &kirkwood_core_clocks,
+	},
+	{
+		.compatible = "marvell,mv88f6180-core-clock",
+		.data = &mv88f6180_core_clocks,
+	},
+#endif
+
+	{ }
+};
+
+void __init mvebu_core_clk_init(void)
+{
+	struct device_node *np;
+
+	for_each_matching_node(np, clk_core_match) {
+		const struct of_device_id *match =
+			of_match_node(clk_core_match, np);
+		mvebu_clk_core_setup(np, (struct core_clocks *)match->data);
+	}
+}
diff --git a/drivers/clk/mvebu/clk-core.h b/drivers/clk/mvebu/clk-core.h
new file mode 100644
index 000000000000..28b5e02e9885
--- /dev/null
+++ b/drivers/clk/mvebu/clk-core.h
@@ -0,0 +1,18 @@
+/*
+ *  * Marvell EBU clock core handling defined at reset
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __MVEBU_CLK_CORE_H
+#define __MVEBU_CLK_CORE_H
+
+void __init mvebu_core_clk_init(void);
+
+#endif
diff --git a/drivers/clk/mvebu/clk.c b/drivers/clk/mvebu/clk.c
new file mode 100644
index 000000000000..e6742acf9880
--- /dev/null
+++ b/drivers/clk/mvebu/clk.c
@@ -0,0 +1,23 @@
+/*
+ * Marvell EBU SoC clock handling.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/of_address.h>
+#include <linux/clk/mvebu.h>
+#include <linux/of.h>
+#include "clk-core.h"
+
+void __init mvebu_clocks_init(void)
+{
+	mvebu_core_clk_init();
+}
diff --git a/include/linux/clk/mvebu.h b/include/linux/clk/mvebu.h
new file mode 100644
index 000000000000..8c4ae713b063
--- /dev/null
+++ b/include/linux/clk/mvebu.h
@@ -0,0 +1,22 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef __CLK_MVEBU_H_
+#define __CLK_MVEBU_H_
+
+void __init mvebu_clocks_init(void);
+
+#endif
-- 
cgit v1.2.3-55-g7522


From d0b2fdd2a51203f04ea0a5d716e033c15e0231af Mon Sep 17 00:00:00 2001
From: Tao Ma
Date: Tue, 20 Nov 2012 22:06:18 +0800
Subject: cgroup: remove obsolete guarantee from cgroup_task_migrate.

'guarantee' is already removed from cgroup_task_migrate, so remove
the corresponding comments. Some other typos in cgroup are also
changed.

Cc: Tejun Heo <tj@kernel.org>
Cc: Li Zefan <lizefan@huawei.com>
Signed-off-by: Tao Ma <boyu.mt@taobao.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h | 4 ++--
 kernel/cgroup.c        | 8 +++-----
 2 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 82cf9e6fc77b..7d73905dcba2 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -66,7 +66,7 @@ struct cgroup_subsys_state {
 	/*
 	 * State maintained by the cgroup system to allow subsystems
 	 * to be "busy". Should be accessed via css_get(),
-	 * css_tryget() and and css_put().
+	 * css_tryget() and css_put().
 	 */
 
 	atomic_t refcnt;
@@ -276,7 +276,7 @@ struct cgroup_map_cb {
 
 /* cftype->flags */
 #define CFTYPE_ONLY_ON_ROOT	(1U << 0)	/* only create on root cg */
-#define CFTYPE_NOT_ON_ROOT	(1U << 1)	/* don't create onp root cg */
+#define CFTYPE_NOT_ON_ROOT	(1U << 1)	/* don't create on root cg */
 
 #define MAX_CFTYPE_NAME		64
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 6db01417d39a..55a0a770a5a2 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -782,12 +782,12 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  *	The task_lock() exception
  *
  * The need for this exception arises from the action of
- * cgroup_attach_task(), which overwrites one tasks cgroup pointer with
+ * cgroup_attach_task(), which overwrites one task's cgroup pointer with
  * another.  It does so using cgroup_mutex, however there are
  * several performance critical places that need to reference
  * task->cgroup without the expense of grabbing a system global
  * mutex.  Therefore except as noted below, when dereferencing or, as
- * in cgroup_attach_task(), modifying a task'ss cgroup pointer we use
+ * in cgroup_attach_task(), modifying a task's cgroup pointer we use
  * task_lock(), which acts on a spinlock (task->alloc_lock) already in
  * the task_struct routinely used for such matters.
  *
@@ -1882,9 +1882,7 @@ EXPORT_SYMBOL_GPL(cgroup_taskset_size);
 /*
  * cgroup_task_migrate - move a task from one cgroup to another.
  *
- * 'guarantee' is set if the caller promises that a new css_set for the task
- * will already exist. If not set, this function might sleep, and can fail with
- * -ENOMEM. Must be called with cgroup_mutex and threadgroup locked.
+ * Must be called with cgroup_mutex and threadgroup locked.
  */
 static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
 				struct task_struct *tsk, struct css_set *newcg)
-- 
cgit v1.2.3-55-g7522


From 60d151f38799d5e15845ee04b73cbf3839f1b06c Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni
Date: Mon, 29 Oct 2012 16:54:49 +0100
Subject: dma: mv_xor: allow channels to be registered directly from the main
 device

Extend the XOR engine driver (currently called "mv_xor_shared") so
that XOR channels can be passed in the platform_data structure, and be
registered from there.

This will allow the users of the driver to be converted to the single
platform_driver variant of the mv_xor driver.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
---
 drivers/dma/mv_xor.c                     | 45 ++++++++++++++++++++++++++++++++
 drivers/dma/mv_xor.h                     |  8 +++---
 include/linux/platform_data/dma-mv_xor.h |  3 +++
 3 files changed, 53 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index f7b99193e884..6ed3162cccc9 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1292,7 +1292,9 @@ static int mv_xor_shared_probe(struct platform_device *pdev)
 {
 	const struct mbus_dram_target_info *dram;
 	struct mv_xor_shared_private *msp;
+	struct mv_xor_shared_platform_data *pdata = pdev->dev.platform_data;
 	struct resource *res;
+	int i, ret;
 
 	dev_notice(&pdev->dev, "Marvell shared XOR driver\n");
 
@@ -1334,12 +1336,55 @@ static int mv_xor_shared_probe(struct platform_device *pdev)
 	if (!IS_ERR(msp->clk))
 		clk_prepare_enable(msp->clk);
 
+	if (pdata && pdata->channels) {
+		for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
+			struct mv_xor_platform_data *cd;
+			int irq;
+
+			cd = &pdata->channels[i];
+			if (!cd) {
+				ret = -ENODEV;
+				goto err_channel_add;
+			}
+
+			irq = platform_get_irq(pdev, i);
+			if (irq < 0) {
+				ret = irq;
+				goto err_channel_add;
+			}
+
+			msp->channels[i] =
+				mv_xor_channel_add(msp, pdev, cd->hw_id,
+						   cd->cap_mask,
+						   cd->pool_size, irq);
+			if (IS_ERR(msp->channels[i])) {
+				ret = PTR_ERR(msp->channels[i]);
+				goto err_channel_add;
+			}
+		}
+	}
+
 	return 0;
+
+err_channel_add:
+	for (i = 0; i < MV_XOR_MAX_CHANNELS; i++)
+		if (msp->channels[i])
+			mv_xor_channel_remove(msp->channels[i]);
+
+	clk_disable_unprepare(msp->clk);
+	clk_put(msp->clk);
+	return ret;
 }
 
 static int mv_xor_shared_remove(struct platform_device *pdev)
 {
 	struct mv_xor_shared_private *msp = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
+		if (msp->channels[i])
+			mv_xor_channel_remove(msp->channels[i]);
+	}
 
 	if (!IS_ERR(msp->clk)) {
 		clk_disable_unprepare(msp->clk);
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index a0641aebbdef..686575f6b9f5 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -26,6 +26,7 @@
 #define USE_TIMER
 #define MV_XOR_SLOT_SIZE		64
 #define MV_XOR_THRESHOLD		1
+#define MV_XOR_MAX_CHANNELS             2
 
 #define XOR_OPERATION_MODE_XOR		0
 #define XOR_OPERATION_MODE_MEMCPY	2
@@ -53,9 +54,10 @@
 #define WINDOW_BAR_ENABLE(chan)	(0x240 + ((chan) << 2))
 
 struct mv_xor_shared_private {
-	void __iomem	*xor_base;
-	void __iomem	*xor_high_base;
-	struct clk	*clk;
+	void __iomem	     *xor_base;
+	void __iomem	     *xor_high_base;
+	struct clk	     *clk;
+	struct mv_xor_device *channels[MV_XOR_MAX_CHANNELS];
 };
 
 
diff --git a/include/linux/platform_data/dma-mv_xor.h b/include/linux/platform_data/dma-mv_xor.h
index 2ba1f7d76eef..f2aed978ca25 100644
--- a/include/linux/platform_data/dma-mv_xor.h
+++ b/include/linux/platform_data/dma-mv_xor.h
@@ -20,5 +20,8 @@ struct mv_xor_platform_data {
 	size_t				pool_size;
 };
 
+struct mv_xor_shared_platform_data {
+	struct mv_xor_platform_data    *channels;
+};
 
 #endif
-- 
cgit v1.2.3-55-g7522


From 18b2a02c7c8db8bb87a165d26c269968d3dd47bd Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni
Date: Tue, 30 Oct 2012 11:54:34 +0100
Subject: dma: mv_xor: remove sub-driver 'mv_xor'

Now that XOR channels are directly registered by the main
'mv_xor_shared' device ->probe() function and all users of the
'mv_xor' device have been removed, we can get rid of the latter.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
---
 drivers/dma/mv_xor.c                     | 49 +-------------------------------
 include/linux/platform_data/dma-mv_xor.h |  1 -
 2 files changed, 1 insertion(+), 49 deletions(-)

(limited to 'include')

diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 6ed3162cccc9..be3907bdef14 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1219,35 +1219,6 @@ mv_xor_channel_add(struct mv_xor_shared_private *msp,
 	return ERR_PTR(ret);
 }
 
-static int __devexit mv_xor_remove(struct platform_device *pdev)
-{
-	struct mv_xor_device *device = platform_get_drvdata(pdev);
-	return mv_xor_channel_remove(device);
-}
-
-static int __devinit mv_xor_probe(struct platform_device *pdev)
-{
-	struct mv_xor_platform_data *plat_data = pdev->dev.platform_data;
-	struct mv_xor_shared_private *msp =
-		platform_get_drvdata(plat_data->shared);
-	struct mv_xor_device *mv_xor_device;
-	int irq;
-
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return irq;
-
-	mv_xor_device = mv_xor_channel_add(msp, pdev, plat_data->hw_id,
-					   plat_data->cap_mask,
-					   plat_data->pool_size, irq);
-	if (IS_ERR(mv_xor_device))
-		return PTR_ERR(mv_xor_device);
-
-	platform_set_drvdata(pdev, mv_xor_device);
-
-	return 0;
-}
-
 static void
 mv_xor_conf_mbus_windows(struct mv_xor_shared_private *msp,
 			 const struct mbus_dram_target_info *dram)
@@ -1279,15 +1250,6 @@ mv_xor_conf_mbus_windows(struct mv_xor_shared_private *msp,
 	writel(win_enable, base + WINDOW_BAR_ENABLE(1));
 }
 
-static struct platform_driver mv_xor_driver = {
-	.probe		= mv_xor_probe,
-	.remove		= __devexit_p(mv_xor_remove),
-	.driver		= {
-		.owner	= THIS_MODULE,
-		.name	= MV_XOR_NAME,
-	},
-};
-
 static int mv_xor_shared_probe(struct platform_device *pdev)
 {
 	const struct mbus_dram_target_info *dram;
@@ -1406,15 +1368,7 @@ static struct platform_driver mv_xor_shared_driver = {
 
 static int __init mv_xor_init(void)
 {
-	int rc;
-
-	rc = platform_driver_register(&mv_xor_shared_driver);
-	if (!rc) {
-		rc = platform_driver_register(&mv_xor_driver);
-		if (rc)
-			platform_driver_unregister(&mv_xor_shared_driver);
-	}
-	return rc;
+	return platform_driver_register(&mv_xor_shared_driver);
 }
 module_init(mv_xor_init);
 
@@ -1422,7 +1376,6 @@ module_init(mv_xor_init);
 #if 0
 static void __exit mv_xor_exit(void)
 {
-	platform_driver_unregister(&mv_xor_driver);
 	platform_driver_unregister(&mv_xor_shared_driver);
 	return;
 }
diff --git a/include/linux/platform_data/dma-mv_xor.h b/include/linux/platform_data/dma-mv_xor.h
index f2aed978ca25..6abe5f9326b6 100644
--- a/include/linux/platform_data/dma-mv_xor.h
+++ b/include/linux/platform_data/dma-mv_xor.h
@@ -11,7 +11,6 @@
 #include <linux/mbus.h>
 
 #define MV_XOR_SHARED_NAME	"mv_xor_shared"
-#define MV_XOR_NAME		"mv_xor"
 
 struct mv_xor_platform_data {
 	struct platform_device		*shared;
-- 
cgit v1.2.3-55-g7522


From 2ccc469cfecee291707dd50e5842cbf206bc17d7 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni
Date: Wed, 31 Oct 2012 13:24:41 +0100
Subject: dma: mv_xor: remove 'shared' from mv_xor_platform_data

This member of the platform_data structure is no longer used, so get
rid of it.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
---
 arch/arm/plat-orion/common.c             | 8 --------
 include/linux/platform_data/dma-mv_xor.h | 1 -
 2 files changed, 9 deletions(-)

(limited to 'include')

diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index c6e6666986ff..5a66211d523c 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -625,16 +625,12 @@ static struct resource orion_xor0_shared_resources[] = {
 	},
 };
 
-static struct platform_device orion_xor0_shared;
-
 static struct mv_xor_platform_data orion_xor0_channels_pdata[2] = {
 	{
-		.shared		= &orion_xor0_shared,
 		.hw_id		= 0,
 		.pool_size	= PAGE_SIZE,
 	},
 	{
-		.shared		= &orion_xor0_shared,
 		.hw_id		= 1,
 		.pool_size	= PAGE_SIZE,
 	},
@@ -704,16 +700,12 @@ static struct resource orion_xor1_shared_resources[] = {
 	},
 };
 
-static struct platform_device orion_xor1_shared;
-
 static struct mv_xor_platform_data orion_xor1_channels_pdata[2] = {
 	{
-		.shared		= &orion_xor1_shared,
 		.hw_id		= 0,
 		.pool_size	= PAGE_SIZE,
 	},
 	{
-		.shared		= &orion_xor1_shared,
 		.hw_id		= 1,
 		.pool_size	= PAGE_SIZE,
 	},
diff --git a/include/linux/platform_data/dma-mv_xor.h b/include/linux/platform_data/dma-mv_xor.h
index 6abe5f9326b6..4a0980b14c9b 100644
--- a/include/linux/platform_data/dma-mv_xor.h
+++ b/include/linux/platform_data/dma-mv_xor.h
@@ -13,7 +13,6 @@
 #define MV_XOR_SHARED_NAME	"mv_xor_shared"
 
 struct mv_xor_platform_data {
-	struct platform_device		*shared;
 	int				hw_id;
 	dma_cap_mask_t			cap_mask;
 	size_t				pool_size;
-- 
cgit v1.2.3-55-g7522


From e39f6ec1f9c1d6a7011adf6d95d8d80bad0586b1 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni
Date: Tue, 30 Oct 2012 11:56:26 +0100
Subject: dma: mv_xor: rename mv_xor_platform_data to mv_xor_channel_data

mv_xor_platform_data used to be the platform_data structure associated
to the 'mv_xor' driver. This driver no longer exists, and this data
structure really contains the properties of each XOR channel part of a
given XOR engine. Therefore 'struct mv_xor_channel_data' is a more
appropriate name.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
---
 arch/arm/plat-orion/common.c             | 28 ++++++++++++++--------------
 drivers/dma/mv_xor.c                     |  2 +-
 include/linux/platform_data/dma-mv_xor.h |  4 ++--
 3 files changed, 17 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index 5a66211d523c..7ffbe77c52cb 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -625,7 +625,7 @@ static struct resource orion_xor0_shared_resources[] = {
 	},
 };
 
-static struct mv_xor_platform_data orion_xor0_channels_pdata[2] = {
+static struct mv_xor_channel_data orion_xor0_channels_data[2] = {
 	{
 		.hw_id		= 0,
 		.pool_size	= PAGE_SIZE,
@@ -637,7 +637,7 @@ static struct mv_xor_platform_data orion_xor0_channels_pdata[2] = {
 };
 
 static struct mv_xor_shared_platform_data orion_xor0_pdata = {
-	.channels = orion_xor0_channels_pdata,
+	.channels = orion_xor0_channels_data,
 };
 
 static struct platform_device orion_xor0_shared = {
@@ -671,12 +671,12 @@ void __init orion_xor0_init(unsigned long mapbase_low,
 	 * two engines can't do memset simultaneously, this limitation
 	 * satisfied by removing memset support from one of the engines.
 	 */
-	dma_cap_set(DMA_MEMCPY, orion_xor0_channels_pdata[0].cap_mask);
-	dma_cap_set(DMA_XOR, orion_xor0_channels_pdata[0].cap_mask);
+	dma_cap_set(DMA_MEMCPY, orion_xor0_channels_data[0].cap_mask);
+	dma_cap_set(DMA_XOR, orion_xor0_channels_data[0].cap_mask);
 
-	dma_cap_set(DMA_MEMSET, orion_xor0_channels_pdata[1].cap_mask);
-	dma_cap_set(DMA_MEMCPY, orion_xor0_channels_pdata[1].cap_mask);
-	dma_cap_set(DMA_XOR, orion_xor0_channels_pdata[1].cap_mask);
+	dma_cap_set(DMA_MEMSET, orion_xor0_channels_data[1].cap_mask);
+	dma_cap_set(DMA_MEMCPY, orion_xor0_channels_data[1].cap_mask);
+	dma_cap_set(DMA_XOR, orion_xor0_channels_data[1].cap_mask);
 
 	platform_device_register(&orion_xor0_shared);
 }
@@ -700,7 +700,7 @@ static struct resource orion_xor1_shared_resources[] = {
 	},
 };
 
-static struct mv_xor_platform_data orion_xor1_channels_pdata[2] = {
+static struct mv_xor_channel_data orion_xor1_channels_data[2] = {
 	{
 		.hw_id		= 0,
 		.pool_size	= PAGE_SIZE,
@@ -712,7 +712,7 @@ static struct mv_xor_platform_data orion_xor1_channels_pdata[2] = {
 };
 
 static struct mv_xor_shared_platform_data orion_xor1_pdata = {
-	.channels = orion_xor1_channels_pdata,
+	.channels = orion_xor1_channels_data,
 };
 
 static struct platform_device orion_xor1_shared = {
@@ -746,12 +746,12 @@ void __init orion_xor1_init(unsigned long mapbase_low,
 	 * two engines can't do memset simultaneously, this limitation
 	 * satisfied by removing memset support from one of the engines.
 	 */
-	dma_cap_set(DMA_MEMCPY, orion_xor1_channels_pdata[0].cap_mask);
-	dma_cap_set(DMA_XOR, orion_xor1_channels_pdata[0].cap_mask);
+	dma_cap_set(DMA_MEMCPY, orion_xor1_channels_data[0].cap_mask);
+	dma_cap_set(DMA_XOR, orion_xor1_channels_data[0].cap_mask);
 
-	dma_cap_set(DMA_MEMSET, orion_xor1_channels_pdata[1].cap_mask);
-	dma_cap_set(DMA_MEMCPY, orion_xor1_channels_pdata[1].cap_mask);
-	dma_cap_set(DMA_XOR, orion_xor1_channels_pdata[1].cap_mask);
+	dma_cap_set(DMA_MEMSET, orion_xor1_channels_data[1].cap_mask);
+	dma_cap_set(DMA_MEMCPY, orion_xor1_channels_data[1].cap_mask);
+	dma_cap_set(DMA_XOR, orion_xor1_channels_data[1].cap_mask);
 
 	platform_device_register(&orion_xor1_shared);
 }
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index be3907bdef14..c7926e417281 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1300,7 +1300,7 @@ static int mv_xor_shared_probe(struct platform_device *pdev)
 
 	if (pdata && pdata->channels) {
 		for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
-			struct mv_xor_platform_data *cd;
+			struct mv_xor_channel_data *cd;
 			int irq;
 
 			cd = &pdata->channels[i];
diff --git a/include/linux/platform_data/dma-mv_xor.h b/include/linux/platform_data/dma-mv_xor.h
index 4a0980b14c9b..40ea3d5f5b9f 100644
--- a/include/linux/platform_data/dma-mv_xor.h
+++ b/include/linux/platform_data/dma-mv_xor.h
@@ -12,14 +12,14 @@
 
 #define MV_XOR_SHARED_NAME	"mv_xor_shared"
 
-struct mv_xor_platform_data {
+struct mv_xor_channel_data {
 	int				hw_id;
 	dma_cap_mask_t			cap_mask;
 	size_t				pool_size;
 };
 
 struct mv_xor_shared_platform_data {
-	struct mv_xor_platform_data    *channels;
+	struct mv_xor_channel_data    *channels;
 };
 
 #endif
-- 
cgit v1.2.3-55-g7522


From 7dde453d628687c0e991cfc55c9fd299a804aee6 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni
Date: Tue, 30 Oct 2012 11:58:14 +0100
Subject: dma: mv_xor: rename mv_xor_shared_platform_data to
 mv_xor_platform_data

'struct mv_xor_shared_platform_data' used to be the platform_data
structure for the 'mv_xor_shared', but this driver is going to be
renamed simply 'mv_xor', so also rename its platform_data structure
accordingly.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
---
 arch/arm/plat-orion/common.c             | 4 ++--
 drivers/dma/mv_xor.c                     | 2 +-
 include/linux/platform_data/dma-mv_xor.h | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index 7ffbe77c52cb..edd57a68fa8c 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -636,7 +636,7 @@ static struct mv_xor_channel_data orion_xor0_channels_data[2] = {
 	},
 };
 
-static struct mv_xor_shared_platform_data orion_xor0_pdata = {
+static struct mv_xor_platform_data orion_xor0_pdata = {
 	.channels = orion_xor0_channels_data,
 };
 
@@ -711,7 +711,7 @@ static struct mv_xor_channel_data orion_xor1_channels_data[2] = {
 	},
 };
 
-static struct mv_xor_shared_platform_data orion_xor1_pdata = {
+static struct mv_xor_platform_data orion_xor1_pdata = {
 	.channels = orion_xor1_channels_data,
 };
 
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index c7926e417281..ac598168b21f 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1254,7 +1254,7 @@ static int mv_xor_shared_probe(struct platform_device *pdev)
 {
 	const struct mbus_dram_target_info *dram;
 	struct mv_xor_shared_private *msp;
-	struct mv_xor_shared_platform_data *pdata = pdev->dev.platform_data;
+	struct mv_xor_platform_data *pdata = pdev->dev.platform_data;
 	struct resource *res;
 	int i, ret;
 
diff --git a/include/linux/platform_data/dma-mv_xor.h b/include/linux/platform_data/dma-mv_xor.h
index 40ea3d5f5b9f..82a5f4b84afe 100644
--- a/include/linux/platform_data/dma-mv_xor.h
+++ b/include/linux/platform_data/dma-mv_xor.h
@@ -18,7 +18,7 @@ struct mv_xor_channel_data {
 	size_t				pool_size;
 };
 
-struct mv_xor_shared_platform_data {
+struct mv_xor_platform_data {
 	struct mv_xor_channel_data    *channels;
 };
 
-- 
cgit v1.2.3-55-g7522


From 0dddee7a7d42192267ebef0fe15be8b296b665c8 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni
Date: Tue, 30 Oct 2012 11:59:42 +0100
Subject: dma: mv_xor: change the driver name to 'mv_xor'

Since we got rid of the per-XOR channel 'mv_xor' driver, now the
per-XOR engine driver that used to be called 'mv_xor_shared' can
simply be named 'mv_xor'.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
---
 arch/arm/mach-dove/common.c              | 9 +++++----
 arch/arm/mach-kirkwood/board-dt.c        | 5 +++--
 arch/arm/mach-kirkwood/common.c          | 4 ++--
 arch/arm/plat-orion/common.c             | 4 ++--
 drivers/dma/mv_xor.c                     | 2 +-
 include/linux/platform_data/dma-mv_xor.h | 2 +-
 6 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c
index 6a2c4dc413a8..f4ac5b06014b 100644
--- a/arch/arm/mach-dove/common.c
+++ b/arch/arm/mach-dove/common.c
@@ -33,6 +33,7 @@
 #include <linux/irq.h>
 #include <plat/time.h>
 #include <linux/platform_data/usb-ehci-orion.h>
+#include <linux/platform_data/dma-mv_xor.h>
 #include <plat/irq.h>
 #include <plat/common.h>
 #include <plat/addr-map.h>
@@ -124,8 +125,8 @@ static void __init dove_clk_init(void)
 	orion_clkdev_add(NULL, "mv_crypto", crypto);
 	orion_clkdev_add(NULL, "dove-ac97", ac97);
 	orion_clkdev_add(NULL, "dove-pdma", pdma);
-	orion_clkdev_add(NULL, "mv_xor_shared.0", xor0);
-	orion_clkdev_add(NULL, "mv_xor_shared.1", xor1);
+	orion_clkdev_add(NULL, MV_XOR_NAME ".0", xor0);
+	orion_clkdev_add(NULL, MV_XOR_NAME ".1", xor1);
 }
 
 /*****************************************************************************
@@ -410,11 +411,11 @@ static void __init dove_legacy_clk_init(void)
 			 of_clk_get_from_provider(&clkspec));
 
 	clkspec.args[0] = CLOCK_GATING_BIT_XOR0;
-	orion_clkdev_add(NULL, "mv_xor_shared.0",
+	orion_clkdev_add(NULL, MV_XOR_NAME ".0",
 			 of_clk_get_from_provider(&clkspec));
 
 	clkspec.args[0] = CLOCK_GATING_BIT_XOR1;
-	orion_clkdev_add(NULL, "mv_xor_shared.1",
+	orion_clkdev_add(NULL, MV_XOR_NAME ".1",
 			 of_clk_get_from_provider(&clkspec));
 }
 
diff --git a/arch/arm/mach-kirkwood/board-dt.c b/arch/arm/mach-kirkwood/board-dt.c
index 8bdfaa4db091..294ad5a4fd98 100644
--- a/arch/arm/mach-kirkwood/board-dt.c
+++ b/arch/arm/mach-kirkwood/board-dt.c
@@ -21,6 +21,7 @@
 #include <asm/mach/map.h>
 #include <mach/bridge-regs.h>
 #include <linux/platform_data/usb-ehci-orion.h>
+#include <linux/platform_data/dma-mv_xor.h>
 #include <plat/irq.h>
 #include <plat/common.h>
 #include "common.h"
@@ -60,11 +61,11 @@ static void __init kirkwood_legacy_clk_init(void)
 			 of_clk_get_from_provider(&clkspec));
 
 	clkspec.args[0] = CGC_BIT_XOR0;
-	orion_clkdev_add(NULL, "mv_xor_shared.0",
+	orion_clkdev_add(NULL, MV_XOR_NAME ".0",
 			 of_clk_get_from_provider(&clkspec));
 
 	clkspec.args[0] = CGC_BIT_XOR1;
-	orion_clkdev_add(NULL, "mv_xor_shared.1",
+	orion_clkdev_add(NULL, MV_XOR_NAME ".1",
 			 of_clk_get_from_provider(&clkspec));
 
 	clkspec.args[0] = CGC_BIT_PEX1;
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index 2c6c218fb79e..401dac1a8d80 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -260,8 +260,8 @@ void __init kirkwood_clk_init(void)
 	orion_clkdev_add(NULL, "orion_nand", runit);
 	orion_clkdev_add(NULL, "mvsdio", sdio);
 	orion_clkdev_add(NULL, "mv_crypto", crypto);
-	orion_clkdev_add(NULL, MV_XOR_SHARED_NAME ".0", xor0);
-	orion_clkdev_add(NULL, MV_XOR_SHARED_NAME ".1", xor1);
+	orion_clkdev_add(NULL, MV_XOR_NAME ".0", xor0);
+	orion_clkdev_add(NULL, MV_XOR_NAME ".1", xor1);
 	orion_clkdev_add("0", "pcie", pex0);
 	orion_clkdev_add("1", "pcie", pex1);
 	orion_clkdev_add(NULL, "kirkwood-i2s", audio);
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index edd57a68fa8c..31517cef8c4d 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -641,7 +641,7 @@ static struct mv_xor_platform_data orion_xor0_pdata = {
 };
 
 static struct platform_device orion_xor0_shared = {
-	.name		= MV_XOR_SHARED_NAME,
+	.name		= MV_XOR_NAME,
 	.id		= 0,
 	.num_resources	= ARRAY_SIZE(orion_xor0_shared_resources),
 	.resource	= orion_xor0_shared_resources,
@@ -716,7 +716,7 @@ static struct mv_xor_platform_data orion_xor1_pdata = {
 };
 
 static struct platform_device orion_xor1_shared = {
-	.name		= MV_XOR_SHARED_NAME,
+	.name		= MV_XOR_NAME,
 	.id		= 1,
 	.num_resources	= ARRAY_SIZE(orion_xor1_shared_resources),
 	.resource	= orion_xor1_shared_resources,
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index ac598168b21f..0ed5183eb5a3 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1361,7 +1361,7 @@ static struct platform_driver mv_xor_shared_driver = {
 	.remove		= mv_xor_shared_remove,
 	.driver		= {
 		.owner	= THIS_MODULE,
-		.name	= MV_XOR_SHARED_NAME,
+		.name	= MV_XOR_NAME,
 	},
 };
 
diff --git a/include/linux/platform_data/dma-mv_xor.h b/include/linux/platform_data/dma-mv_xor.h
index 82a5f4b84afe..367bb216c4a7 100644
--- a/include/linux/platform_data/dma-mv_xor.h
+++ b/include/linux/platform_data/dma-mv_xor.h
@@ -10,7 +10,7 @@
 #include <linux/dmaengine.h>
 #include <linux/mbus.h>
 
-#define MV_XOR_SHARED_NAME	"mv_xor_shared"
+#define MV_XOR_NAME	"mv_xor"
 
 struct mv_xor_channel_data {
 	int				hw_id;
-- 
cgit v1.2.3-55-g7522


From 9aedbdbab39c8aa58c0b2a0791fb10df6eebc123 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni
Date: Thu, 15 Nov 2012 15:36:37 +0100
Subject: dma: mv_xor: remove hw_id field from platform_data

There is no need for the platform_data to give this ID, it is simply
the channel number, so we can compute it inside the driver when
registering the channels.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
---
 arch/arm/plat-orion/common.c             | 4 ----
 drivers/dma/mv_xor.c                     | 6 +++---
 include/linux/platform_data/dma-mv_xor.h | 1 -
 3 files changed, 3 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index 31517cef8c4d..09d836060bf4 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -627,11 +627,9 @@ static struct resource orion_xor0_shared_resources[] = {
 
 static struct mv_xor_channel_data orion_xor0_channels_data[2] = {
 	{
-		.hw_id		= 0,
 		.pool_size	= PAGE_SIZE,
 	},
 	{
-		.hw_id		= 1,
 		.pool_size	= PAGE_SIZE,
 	},
 };
@@ -702,11 +700,9 @@ static struct resource orion_xor1_shared_resources[] = {
 
 static struct mv_xor_channel_data orion_xor1_channels_data[2] = {
 	{
-		.hw_id		= 0,
 		.pool_size	= PAGE_SIZE,
 	},
 	{
-		.hw_id		= 1,
 		.pool_size	= PAGE_SIZE,
 	},
 };
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index a6a5a28574c4..fc983bf38438 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1088,7 +1088,7 @@ static int mv_xor_channel_remove(struct mv_xor_chan *mv_chan)
 static struct mv_xor_chan *
 mv_xor_channel_add(struct mv_xor_device *xordev,
 		   struct platform_device *pdev,
-		   int hw_id, dma_cap_mask_t cap_mask,
+		   int idx, dma_cap_mask_t cap_mask,
 		   size_t pool_size, int irq)
 {
 	int ret = 0;
@@ -1101,7 +1101,7 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 		goto err_free_dma;
 	}
 
-	mv_chan->idx = hw_id;
+	mv_chan->idx = idx;
 
 	dma_dev = &mv_chan->dmadev;
 
@@ -1295,7 +1295,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 			}
 
 			xordev->channels[i] =
-				mv_xor_channel_add(xordev, pdev, cd->hw_id,
+				mv_xor_channel_add(xordev, pdev, i,
 						   cd->cap_mask,
 						   cd->pool_size, irq);
 			if (IS_ERR(xordev->channels[i])) {
diff --git a/include/linux/platform_data/dma-mv_xor.h b/include/linux/platform_data/dma-mv_xor.h
index 367bb216c4a7..b18dc2496186 100644
--- a/include/linux/platform_data/dma-mv_xor.h
+++ b/include/linux/platform_data/dma-mv_xor.h
@@ -13,7 +13,6 @@
 #define MV_XOR_NAME	"mv_xor"
 
 struct mv_xor_channel_data {
-	int				hw_id;
 	dma_cap_mask_t			cap_mask;
 	size_t				pool_size;
 };
-- 
cgit v1.2.3-55-g7522


From b503fa01990f6875640339d8f4ba98dbc068f821 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni
Date: Thu, 15 Nov 2012 15:55:30 +0100
Subject: dma: mv_xor: remove the pool_size from platform_data

The pool_size is always PAGE_SIZE, and since it is a software
configuration paramter (and not a hardware description parameter), we
cannot make it part of the Device Tree binding, so we'd better remove
it from the platform_data as well.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
---
 arch/arm/plat-orion/common.c             | 18 ++----------------
 drivers/dma/mv_xor.c                     | 15 ++++++---------
 drivers/dma/mv_xor.h                     |  1 +
 include/linux/platform_data/dma-mv_xor.h |  1 -
 4 files changed, 9 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index 09d836060bf4..2d4b6414609f 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -625,14 +625,7 @@ static struct resource orion_xor0_shared_resources[] = {
 	},
 };
 
-static struct mv_xor_channel_data orion_xor0_channels_data[2] = {
-	{
-		.pool_size	= PAGE_SIZE,
-	},
-	{
-		.pool_size	= PAGE_SIZE,
-	},
-};
+static struct mv_xor_channel_data orion_xor0_channels_data[2];
 
 static struct mv_xor_platform_data orion_xor0_pdata = {
 	.channels = orion_xor0_channels_data,
@@ -698,14 +691,7 @@ static struct resource orion_xor1_shared_resources[] = {
 	},
 };
 
-static struct mv_xor_channel_data orion_xor1_channels_data[2] = {
-	{
-		.pool_size	= PAGE_SIZE,
-	},
-	{
-		.pool_size	= PAGE_SIZE,
-	},
-};
+static struct mv_xor_channel_data orion_xor1_channels_data[2];
 
 static struct mv_xor_platform_data orion_xor1_pdata = {
 	.channels = orion_xor1_channels_data,
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index fc983bf38438..ec741b4607e2 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -603,7 +603,7 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 	int idx;
 	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
 	struct mv_xor_desc_slot *slot = NULL;
-	int num_descs_in_pool = mv_chan->pool_size/MV_XOR_SLOT_SIZE;
+	int num_descs_in_pool = MV_XOR_POOL_SIZE/MV_XOR_SLOT_SIZE;
 
 	/* Allocate descriptor slots */
 	idx = mv_chan->slots_allocated;
@@ -1074,7 +1074,7 @@ static int mv_xor_channel_remove(struct mv_xor_chan *mv_chan)
 
 	dma_async_device_unregister(&mv_chan->dmadev);
 
-	dma_free_coherent(dev, mv_chan->pool_size,
+	dma_free_coherent(dev, MV_XOR_POOL_SIZE,
 			  mv_chan->dma_desc_pool_virt, mv_chan->dma_desc_pool);
 
 	list_for_each_entry_safe(chan, _chan, &mv_chan->dmadev.channels,
@@ -1088,8 +1088,7 @@ static int mv_xor_channel_remove(struct mv_xor_chan *mv_chan)
 static struct mv_xor_chan *
 mv_xor_channel_add(struct mv_xor_device *xordev,
 		   struct platform_device *pdev,
-		   int idx, dma_cap_mask_t cap_mask,
-		   size_t pool_size, int irq)
+		   int idx, dma_cap_mask_t cap_mask, int irq)
 {
 	int ret = 0;
 	struct mv_xor_chan *mv_chan;
@@ -1109,9 +1108,8 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	 * note: writecombine gives slightly better performance, but
 	 * requires that we explicitly flush the writes
 	 */
-	mv_chan->pool_size = pool_size;
 	mv_chan->dma_desc_pool_virt =
-	  dma_alloc_writecombine(&pdev->dev, mv_chan->pool_size,
+	  dma_alloc_writecombine(&pdev->dev, MV_XOR_POOL_SIZE,
 				 &mv_chan->dma_desc_pool, GFP_KERNEL);
 	if (!mv_chan->dma_desc_pool_virt)
 		return ERR_PTR(-ENOMEM);
@@ -1193,7 +1191,7 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	return mv_chan;
 
  err_free_dma:
-	dma_free_coherent(&pdev->dev, pool_size,
+	dma_free_coherent(&pdev->dev, MV_XOR_POOL_SIZE,
 			  mv_chan->dma_desc_pool_virt, mv_chan->dma_desc_pool);
 	return ERR_PTR(ret);
 }
@@ -1296,8 +1294,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 
 			xordev->channels[i] =
 				mv_xor_channel_add(xordev, pdev, i,
-						   cd->cap_mask,
-						   cd->pool_size, irq);
+						   cd->cap_mask, irq);
 			if (IS_ERR(xordev->channels[i])) {
 				ret = PTR_ERR(xordev->channels[i]);
 				goto err_channel_add;
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index dab9f30e564a..698b4487b348 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -24,6 +24,7 @@
 #include <linux/interrupt.h>
 
 #define USE_TIMER
+#define MV_XOR_POOL_SIZE		PAGE_SIZE
 #define MV_XOR_SLOT_SIZE		64
 #define MV_XOR_THRESHOLD		1
 #define MV_XOR_MAX_CHANNELS             2
diff --git a/include/linux/platform_data/dma-mv_xor.h b/include/linux/platform_data/dma-mv_xor.h
index b18dc2496186..8ec18f64e396 100644
--- a/include/linux/platform_data/dma-mv_xor.h
+++ b/include/linux/platform_data/dma-mv_xor.h
@@ -14,7 +14,6 @@
 
 struct mv_xor_channel_data {
 	dma_cap_mask_t			cap_mask;
-	size_t				pool_size;
 };
 
 struct mv_xor_platform_data {
-- 
cgit v1.2.3-55-g7522


From c8d35c84f5494d8d294205b598f927a11fd41f34 Mon Sep 17 00:00:00 2001
From: Tony Lindgren
Date: Fri, 2 Nov 2012 12:24:03 -0700
Subject: ARM: OMAP2+: Move plat/iovmm.h to include/linux/omap-iommu.h

Looks like the iommu framework does not have generic functions
exported for all the needs yet. The hardware specific functions
are defined in files like intel-iommu.h and amd-iommu.h. Follow
the same standard for omap-iommu.h.

This is needed because we are removing plat and mach includes
for ARM common zImage support. Further work should continue
in the iommu framework context as only pure platform data will
be communicated from arch/arm/*omap*/* code to the iommu
framework.

Cc: Ido Yariv <ido@wizery.com>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Omar Ramirez Luna <omar.luna@linaro.org>
Cc: linux-media@vger.kernel.org
Acked-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Acked-by: Ohad Ben-Cohen <ohad@wizery.com>
Acked-by: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/iommu2.c               |  1 +
 arch/arm/plat-omap/include/plat/iommu.h    | 10 +---
 arch/arm/plat-omap/include/plat/iovmm.h    | 89 ------------------------------
 drivers/iommu/omap-iommu-debug.c           |  2 +-
 drivers/iommu/omap-iommu.c                 |  1 +
 drivers/iommu/omap-iovmm.c                 | 46 ++++++++++++++-
 drivers/media/platform/omap3isp/isp.c      |  1 +
 drivers/media/platform/omap3isp/isp.h      |  4 +-
 drivers/media/platform/omap3isp/ispccdc.c  |  1 +
 drivers/media/platform/omap3isp/ispstat.c  |  1 +
 drivers/media/platform/omap3isp/ispvideo.c |  2 +-
 include/linux/omap-iommu.h                 | 52 +++++++++++++++++
 12 files changed, 107 insertions(+), 103 deletions(-)
 delete mode 100644 arch/arm/plat-omap/include/plat/iovmm.h
 create mode 100644 include/linux/omap-iommu.h

(limited to 'include')

diff --git a/arch/arm/mach-omap2/iommu2.c b/arch/arm/mach-omap2/iommu2.c
index eefc37912ef3..e8116cf58e15 100644
--- a/arch/arm/mach-omap2/iommu2.c
+++ b/arch/arm/mach-omap2/iommu2.c
@@ -15,6 +15,7 @@
 #include <linux/device.h>
 #include <linux/jiffies.h>
 #include <linux/module.h>
+#include <linux/omap-iommu.h>
 #include <linux/slab.h>
 #include <linux/stringify.h>
 
diff --git a/arch/arm/plat-omap/include/plat/iommu.h b/arch/arm/plat-omap/include/plat/iommu.h
index 7e8c7b66ee35..a4b71b14975a 100644
--- a/arch/arm/plat-omap/include/plat/iommu.h
+++ b/arch/arm/plat-omap/include/plat/iommu.h
@@ -216,13 +216,10 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev)
 #define MMU_RAM_PADDR_SHIFT	12
 #define MMU_RAM_PADDR_MASK \
 	((~0UL >> MMU_RAM_PADDR_SHIFT) << MMU_RAM_PADDR_SHIFT)
-#define MMU_RAM_ENDIAN_SHIFT	9
+
 #define MMU_RAM_ENDIAN_MASK	(1 << MMU_RAM_ENDIAN_SHIFT)
-#define MMU_RAM_ENDIAN_BIG	(1 << MMU_RAM_ENDIAN_SHIFT)
-#define MMU_RAM_ENDIAN_LITTLE	(0 << MMU_RAM_ENDIAN_SHIFT)
-#define MMU_RAM_ELSZ_SHIFT	7
 #define MMU_RAM_ELSZ_MASK	(3 << MMU_RAM_ELSZ_SHIFT)
-#define MMU_RAM_ELSZ_8		(0 << MMU_RAM_ELSZ_SHIFT)
+
 #define MMU_RAM_ELSZ_16		(1 << MMU_RAM_ELSZ_SHIFT)
 #define MMU_RAM_ELSZ_32		(2 << MMU_RAM_ELSZ_SHIFT)
 #define MMU_RAM_ELSZ_NONE	(3 << MMU_RAM_ELSZ_SHIFT)
@@ -269,9 +266,6 @@ extern int omap_iommu_set_isr(const char *name,
 				    void *priv),
 			 void *isr_priv);
 
-extern void omap_iommu_save_ctx(struct device *dev);
-extern void omap_iommu_restore_ctx(struct device *dev);
-
 extern int omap_install_iommu_arch(const struct iommu_functions *ops);
 extern void omap_uninstall_iommu_arch(const struct iommu_functions *ops);
 
diff --git a/arch/arm/plat-omap/include/plat/iovmm.h b/arch/arm/plat-omap/include/plat/iovmm.h
deleted file mode 100644
index 498e57cda6cd..000000000000
--- a/arch/arm/plat-omap/include/plat/iovmm.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/*
- * omap iommu: simple virtual address space management
- *
- * Copyright (C) 2008-2009 Nokia Corporation
- *
- * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __IOMMU_MMAP_H
-#define __IOMMU_MMAP_H
-
-#include <linux/iommu.h>
-
-struct iovm_struct {
-	struct omap_iommu	*iommu;	/* iommu object which this belongs to */
-	u32			da_start; /* area definition */
-	u32			da_end;
-	u32			flags; /* IOVMF_: see below */
-	struct list_head	list; /* linked in ascending order */
-	const struct sg_table	*sgt; /* keep 'page' <-> 'da' mapping */
-	void			*va; /* mpu side mapped address */
-};
-
-/*
- * IOVMF_FLAGS: attribute for iommu virtual memory area(iovma)
- *
- * lower 16 bit is used for h/w and upper 16 bit is for s/w.
- */
-#define IOVMF_SW_SHIFT		16
-
-/*
- * iovma: h/w flags derived from cam and ram attribute
- */
-#define IOVMF_CAM_MASK		(~((1 << 10) - 1))
-#define IOVMF_RAM_MASK		(~IOVMF_CAM_MASK)
-
-#define IOVMF_PGSZ_MASK		(3 << 0)
-#define IOVMF_PGSZ_1M		MMU_CAM_PGSZ_1M
-#define IOVMF_PGSZ_64K		MMU_CAM_PGSZ_64K
-#define IOVMF_PGSZ_4K		MMU_CAM_PGSZ_4K
-#define IOVMF_PGSZ_16M		MMU_CAM_PGSZ_16M
-
-#define IOVMF_ENDIAN_MASK	(1 << 9)
-#define IOVMF_ENDIAN_BIG	MMU_RAM_ENDIAN_BIG
-#define IOVMF_ENDIAN_LITTLE	MMU_RAM_ENDIAN_LITTLE
-
-#define IOVMF_ELSZ_MASK		(3 << 7)
-#define IOVMF_ELSZ_8		MMU_RAM_ELSZ_8
-#define IOVMF_ELSZ_16		MMU_RAM_ELSZ_16
-#define IOVMF_ELSZ_32		MMU_RAM_ELSZ_32
-#define IOVMF_ELSZ_NONE		MMU_RAM_ELSZ_NONE
-
-#define IOVMF_MIXED_MASK	(1 << 6)
-#define IOVMF_MIXED		MMU_RAM_MIXED
-
-/*
- * iovma: s/w flags, used for mapping and umapping internally.
- */
-#define IOVMF_MMIO		(1 << IOVMF_SW_SHIFT)
-#define IOVMF_ALLOC		(2 << IOVMF_SW_SHIFT)
-#define IOVMF_ALLOC_MASK	(3 << IOVMF_SW_SHIFT)
-
-/* "superpages" is supported just with physically linear pages */
-#define IOVMF_DISCONT		(1 << (2 + IOVMF_SW_SHIFT))
-#define IOVMF_LINEAR		(2 << (2 + IOVMF_SW_SHIFT))
-#define IOVMF_LINEAR_MASK	(3 << (2 + IOVMF_SW_SHIFT))
-
-#define IOVMF_DA_FIXED		(1 << (4 + IOVMF_SW_SHIFT))
-
-
-extern struct iovm_struct *omap_find_iovm_area(struct device *dev, u32 da);
-extern u32
-omap_iommu_vmap(struct iommu_domain *domain, struct device *dev, u32 da,
-			const struct sg_table *sgt, u32 flags);
-extern struct sg_table *omap_iommu_vunmap(struct iommu_domain *domain,
-				struct device *dev, u32 da);
-extern u32
-omap_iommu_vmalloc(struct iommu_domain *domain, struct device *dev,
-				u32 da, size_t bytes, u32 flags);
-extern void
-omap_iommu_vfree(struct iommu_domain *domain, struct device *dev,
-				const u32 da);
-extern void *omap_da_to_va(struct device *dev, u32 da);
-
-#endif /* __IOMMU_MMAP_H */
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
index 0cac372b0d43..cf4a0b5c1d82 100644
--- a/drivers/iommu/omap-iommu-debug.c
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -18,9 +18,9 @@
 #include <linux/uaccess.h>
 #include <linux/platform_device.h>
 #include <linux/debugfs.h>
+#include <linux/omap-iommu.h>
 
 #include <plat/iommu.h>
-#include <plat/iovmm.h>
 
 #include "omap-iopgtable.h"
 
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index f2bbfb0fd0e0..eadcfde757ee 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -19,6 +19,7 @@
 #include <linux/clk.h>
 #include <linux/platform_device.h>
 #include <linux/iommu.h>
+#include <linux/omap-iommu.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 
diff --git a/drivers/iommu/omap-iovmm.c b/drivers/iommu/omap-iovmm.c
index b332392397ce..9852101cf042 100644
--- a/drivers/iommu/omap-iovmm.c
+++ b/drivers/iommu/omap-iovmm.c
@@ -17,15 +17,59 @@
 #include <linux/device.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu.h>
+#include <linux/omap-iommu.h>
 
 #include <asm/cacheflush.h>
 #include <asm/mach/map.h>
 
 #include <plat/iommu.h>
-#include <plat/iovmm.h>
 
 #include "omap-iopgtable.h"
 
+/*
+ * IOVMF_FLAGS: attribute for iommu virtual memory area(iovma)
+ *
+ * lower 16 bit is used for h/w and upper 16 bit is for s/w.
+ */
+#define IOVMF_SW_SHIFT		16
+
+/*
+ * iovma: h/w flags derived from cam and ram attribute
+ */
+#define IOVMF_CAM_MASK		(~((1 << 10) - 1))
+#define IOVMF_RAM_MASK		(~IOVMF_CAM_MASK)
+
+#define IOVMF_PGSZ_MASK		(3 << 0)
+#define IOVMF_PGSZ_1M		MMU_CAM_PGSZ_1M
+#define IOVMF_PGSZ_64K		MMU_CAM_PGSZ_64K
+#define IOVMF_PGSZ_4K		MMU_CAM_PGSZ_4K
+#define IOVMF_PGSZ_16M		MMU_CAM_PGSZ_16M
+
+#define IOVMF_ENDIAN_MASK	(1 << 9)
+#define IOVMF_ENDIAN_BIG	MMU_RAM_ENDIAN_BIG
+
+#define IOVMF_ELSZ_MASK		(3 << 7)
+#define IOVMF_ELSZ_16		MMU_RAM_ELSZ_16
+#define IOVMF_ELSZ_32		MMU_RAM_ELSZ_32
+#define IOVMF_ELSZ_NONE		MMU_RAM_ELSZ_NONE
+
+#define IOVMF_MIXED_MASK	(1 << 6)
+#define IOVMF_MIXED		MMU_RAM_MIXED
+
+/*
+ * iovma: s/w flags, used for mapping and umapping internally.
+ */
+#define IOVMF_MMIO		(1 << IOVMF_SW_SHIFT)
+#define IOVMF_ALLOC		(2 << IOVMF_SW_SHIFT)
+#define IOVMF_ALLOC_MASK	(3 << IOVMF_SW_SHIFT)
+
+/* "superpages" is supported just with physically linear pages */
+#define IOVMF_DISCONT		(1 << (2 + IOVMF_SW_SHIFT))
+#define IOVMF_LINEAR		(2 << (2 + IOVMF_SW_SHIFT))
+#define IOVMF_LINEAR_MASK	(3 << (2 + IOVMF_SW_SHIFT))
+
+#define IOVMF_DA_FIXED		(1 << (4 + IOVMF_SW_SHIFT))
+
 static struct kmem_cache *iovm_area_cachep;
 
 /* return the offset of the first scatterlist entry in a sg table */
diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index 99640d8c1db0..7f182f0ff3da 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -61,6 +61,7 @@
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/omap-iommu.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
diff --git a/drivers/media/platform/omap3isp/isp.h b/drivers/media/platform/omap3isp/isp.h
index 8be7487c326f..8d6866942b85 100644
--- a/drivers/media/platform/omap3isp/isp.h
+++ b/drivers/media/platform/omap3isp/isp.h
@@ -31,11 +31,9 @@
 #include <media/v4l2-device.h>
 #include <linux/device.h>
 #include <linux/io.h>
+#include <linux/iommu.h>
 #include <linux/platform_device.h>
 #include <linux/wait.h>
-#include <linux/iommu.h>
-#include <plat/iommu.h>
-#include <plat/iovmm.h>
 
 #include "ispstat.h"
 #include "ispccdc.h"
diff --git a/drivers/media/platform/omap3isp/ispccdc.c b/drivers/media/platform/omap3isp/ispccdc.c
index 60181ab96063..6ae1ffb277e7 100644
--- a/drivers/media/platform/omap3isp/ispccdc.c
+++ b/drivers/media/platform/omap3isp/ispccdc.c
@@ -30,6 +30,7 @@
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/mm.h>
+#include <linux/omap-iommu.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <media/v4l2-event.h>
diff --git a/drivers/media/platform/omap3isp/ispstat.c b/drivers/media/platform/omap3isp/ispstat.c
index d7ac76b5c2ae..35c38237449d 100644
--- a/drivers/media/platform/omap3isp/ispstat.c
+++ b/drivers/media/platform/omap3isp/ispstat.c
@@ -26,6 +26,7 @@
  */
 
 #include <linux/dma-mapping.h>
+#include <linux/omap-iommu.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c
index a0b737fecf13..a4b829027d71 100644
--- a/drivers/media/platform/omap3isp/ispvideo.c
+++ b/drivers/media/platform/omap3isp/ispvideo.c
@@ -27,6 +27,7 @@
 #include <linux/clk.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/omap-iommu.h>
 #include <linux/pagemap.h>
 #include <linux/scatterlist.h>
 #include <linux/sched.h>
@@ -35,7 +36,6 @@
 #include <media/v4l2-dev.h>
 #include <media/v4l2-ioctl.h>
 #include <plat/iommu.h>
-#include <plat/iovmm.h>
 #include <plat/omap-pm.h>
 
 #include "ispvideo.h"
diff --git a/include/linux/omap-iommu.h b/include/linux/omap-iommu.h
new file mode 100644
index 000000000000..cac78de09c07
--- /dev/null
+++ b/include/linux/omap-iommu.h
@@ -0,0 +1,52 @@
+/*
+ * omap iommu: simple virtual address space management
+ *
+ * Copyright (C) 2008-2009 Nokia Corporation
+ *
+ * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _INTEL_IOMMU_H_
+#define _INTEL_IOMMU_H_
+
+struct iovm_struct {
+	struct omap_iommu	*iommu;	/* iommu object which this belongs to */
+	u32			da_start; /* area definition */
+	u32			da_end;
+	u32			flags; /* IOVMF_: see below */
+	struct list_head	list; /* linked in ascending order */
+	const struct sg_table	*sgt; /* keep 'page' <-> 'da' mapping */
+	void			*va; /* mpu side mapped address */
+};
+
+#define MMU_RAM_ENDIAN_SHIFT	9
+#define MMU_RAM_ENDIAN_LITTLE	(0 << MMU_RAM_ENDIAN_SHIFT)
+#define MMU_RAM_ELSZ_8		(0 << MMU_RAM_ELSZ_SHIFT)
+#define IOVMF_ENDIAN_LITTLE	MMU_RAM_ENDIAN_LITTLE
+#define MMU_RAM_ELSZ_SHIFT	7
+#define IOVMF_ELSZ_8		MMU_RAM_ELSZ_8
+
+struct iommu_domain;
+
+extern struct iovm_struct *omap_find_iovm_area(struct device *dev, u32 da);
+extern u32
+omap_iommu_vmap(struct iommu_domain *domain, struct device *dev, u32 da,
+			const struct sg_table *sgt, u32 flags);
+extern struct sg_table *omap_iommu_vunmap(struct iommu_domain *domain,
+				struct device *dev, u32 da);
+extern u32
+omap_iommu_vmalloc(struct iommu_domain *domain, struct device *dev,
+				u32 da, size_t bytes, u32 flags);
+extern void
+omap_iommu_vfree(struct iommu_domain *domain, struct device *dev,
+				const u32 da);
+extern void *omap_da_to_va(struct device *dev, u32 da);
+
+extern void omap_iommu_save_ctx(struct device *dev);
+extern void omap_iommu_restore_ctx(struct device *dev);
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 2ab7c84815cffd5fe4946a472fc67fefa8ac3c29 Mon Sep 17 00:00:00 2001
From: Tony Lindgren
Date: Fri, 2 Nov 2012 12:24:14 -0700
Subject: ARM: OMAP2+: Move iommu/iovmm headers to platform_data

Move iommu/iovmm headers from plat/ to platform_data/ as part of the
single zImage work.

Partially based on an earlier version by Ido Yariv <ido@wizery.com>.

Cc: Ido Yariv <ido@wizery.com>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Omar Ramirez Luna <omar.luna@linaro.org>
Acked-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Acked-by: Ohad Ben-Cohen <ohad@wizery.com>
Acked-by: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/devices.c              |  2 +-
 arch/arm/mach-omap2/omap-iommu.c           |  2 +-
 arch/arm/mach-omap2/omap_hwmod_3xxx_data.c |  2 +-
 arch/arm/mach-omap2/omap_hwmod_44xx_data.c |  2 +-
 arch/arm/plat-omap/include/plat/iommu.h    | 49 ------------------------------
 drivers/iommu/omap-iommu-debug.c           |  3 +-
 drivers/iommu/omap-iommu.c                 |  2 +-
 drivers/iommu/omap-iommu2.c                |  2 +-
 drivers/iommu/omap-iovmm.c                 |  3 +-
 drivers/media/platform/omap3isp/ispvideo.c |  1 -
 include/linux/platform_data/iommu-omap.h   | 49 ++++++++++++++++++++++++++++++
 11 files changed, 57 insertions(+), 60 deletions(-)
 delete mode 100644 arch/arm/plat-omap/include/plat/iommu.h
 create mode 100644 include/linux/platform_data/iommu-omap.h

(limited to 'include')

diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index c8c211731d26..6cd0c2a36a25 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -126,7 +126,7 @@ static struct platform_device omap2cam_device = {
 
 #if defined(CONFIG_IOMMU_API)
 
-#include <plat/iommu.h>
+#include <linux/platform_data/iommu-omap.h>
 
 static struct resource omap3isp_resources[] = {
 	{
diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c
index df298d46707c..a6a4ff8744b7 100644
--- a/arch/arm/mach-omap2/omap-iommu.c
+++ b/arch/arm/mach-omap2/omap-iommu.c
@@ -13,7 +13,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 
-#include <plat/iommu.h>
+#include <linux/platform_data/iommu-omap.h>
 
 #include "soc.h"
 #include "common.h"
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index f67b7ee07dd4..621bc7137233 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -26,8 +26,8 @@
 #include <plat/mmc.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
+#include <linux/platform_data/iommu-omap.h>
 #include <plat/dmtimer.h>
-#include <plat/iommu.h>
 
 #include "am35xx.h"
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 652d0285bd6d..5850b3e81512 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -27,10 +27,10 @@
 #include <plat/dma.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
+#include <linux/platform_data/iommu-omap.h>
 #include <plat/mmc.h>
 #include <plat/dmtimer.h>
 #include <plat/common.h>
-#include <plat/iommu.h>
 
 #include "omap_hwmod_common_data.h"
 #include "cm1_44xx.h"
diff --git a/arch/arm/plat-omap/include/plat/iommu.h b/arch/arm/plat-omap/include/plat/iommu.h
deleted file mode 100644
index c677b9f2fefa..000000000000
--- a/arch/arm/plat-omap/include/plat/iommu.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * omap iommu: main structures
- *
- * Copyright (C) 2008-2009 Nokia Corporation
- *
- * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#define MMU_REG_SIZE		256
-
-/**
- * struct iommu_arch_data - omap iommu private data
- * @name: name of the iommu device
- * @iommu_dev: handle of the iommu device
- *
- * This is an omap iommu private data object, which binds an iommu user
- * to its iommu device. This object should be placed at the iommu user's
- * dev_archdata so generic IOMMU API can be used without having to
- * utilize omap-specific plumbing anymore.
- */
-struct omap_iommu_arch_data {
-	const char *name;
-	struct omap_iommu *iommu_dev;
-};
-
-/**
- * struct omap_mmu_dev_attr - OMAP mmu device attributes for omap_hwmod
- * @da_start:		device address where the va space starts.
- * @da_end:		device address where the va space ends.
- * @nr_tlb_entries:	number of entries supported by the translation
- *			look-aside buffer (TLB).
- */
-struct omap_mmu_dev_attr {
-	u32 da_start;
-	u32 da_end;
-	int nr_tlb_entries;
-};
-
-struct iommu_platform_data {
-	const char *name;
-	const char *clk_name;
-	const int nr_tlb_entries;
-	u32 da_start;
-	u32 da_end;
-};
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
index d0427bd21361..d97fbe4fb9b1 100644
--- a/drivers/iommu/omap-iommu-debug.c
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -19,8 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/debugfs.h>
 #include <linux/omap-iommu.h>
-
-#include <plat/iommu.h>
+#include <linux/platform_data/iommu-omap.h>
 
 #include "omap-iopgtable.h"
 #include "omap-iommu.h"
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index df840870e2a1..badc17c2bcb4 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -26,7 +26,7 @@
 
 #include <asm/cacheflush.h>
 
-#include <plat/iommu.h>
+#include <linux/platform_data/iommu-omap.h>
 
 #include "omap-iopgtable.h"
 #include "omap-iommu.h"
diff --git a/drivers/iommu/omap-iommu2.c b/drivers/iommu/omap-iommu2.c
index 29e98a2af906..c02020292377 100644
--- a/drivers/iommu/omap-iommu2.c
+++ b/drivers/iommu/omap-iommu2.c
@@ -19,8 +19,8 @@
 #include <linux/omap-iommu.h>
 #include <linux/slab.h>
 #include <linux/stringify.h>
+#include <linux/platform_data/iommu-omap.h>
 
-#include <plat/iommu.h>
 #include "omap-iommu.h"
 
 /*
diff --git a/drivers/iommu/omap-iovmm.c b/drivers/iommu/omap-iovmm.c
index 3e3b2421b924..46d875690739 100644
--- a/drivers/iommu/omap-iovmm.c
+++ b/drivers/iommu/omap-iovmm.c
@@ -18,12 +18,11 @@
 #include <linux/scatterlist.h>
 #include <linux/iommu.h>
 #include <linux/omap-iommu.h>
+#include <linux/platform_data/iommu-omap.h>
 
 #include <asm/cacheflush.h>
 #include <asm/mach/map.h>
 
-#include <plat/iommu.h>
-
 #include "omap-iopgtable.h"
 #include "omap-iommu.h"
 
diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c
index a4b829027d71..21f7313e6999 100644
--- a/drivers/media/platform/omap3isp/ispvideo.c
+++ b/drivers/media/platform/omap3isp/ispvideo.c
@@ -35,7 +35,6 @@
 #include <linux/vmalloc.h>
 #include <media/v4l2-dev.h>
 #include <media/v4l2-ioctl.h>
-#include <plat/iommu.h>
 #include <plat/omap-pm.h>
 
 #include "ispvideo.h"
diff --git a/include/linux/platform_data/iommu-omap.h b/include/linux/platform_data/iommu-omap.h
new file mode 100644
index 000000000000..c677b9f2fefa
--- /dev/null
+++ b/include/linux/platform_data/iommu-omap.h
@@ -0,0 +1,49 @@
+/*
+ * omap iommu: main structures
+ *
+ * Copyright (C) 2008-2009 Nokia Corporation
+ *
+ * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define MMU_REG_SIZE		256
+
+/**
+ * struct iommu_arch_data - omap iommu private data
+ * @name: name of the iommu device
+ * @iommu_dev: handle of the iommu device
+ *
+ * This is an omap iommu private data object, which binds an iommu user
+ * to its iommu device. This object should be placed at the iommu user's
+ * dev_archdata so generic IOMMU API can be used without having to
+ * utilize omap-specific plumbing anymore.
+ */
+struct omap_iommu_arch_data {
+	const char *name;
+	struct omap_iommu *iommu_dev;
+};
+
+/**
+ * struct omap_mmu_dev_attr - OMAP mmu device attributes for omap_hwmod
+ * @da_start:		device address where the va space starts.
+ * @da_end:		device address where the va space ends.
+ * @nr_tlb_entries:	number of entries supported by the translation
+ *			look-aside buffer (TLB).
+ */
+struct omap_mmu_dev_attr {
+	u32 da_start;
+	u32 da_end;
+	int nr_tlb_entries;
+};
+
+struct iommu_platform_data {
+	const char *name;
+	const char *clk_name;
+	const int nr_tlb_entries;
+	u32 da_start;
+	u32 da_end;
+};
-- 
cgit v1.2.3-55-g7522


From e4f67addf158f98f8197e08974966b18480dc751 Mon Sep 17 00:00:00 2001
From: David Stevens
Date: Tue, 20 Nov 2012 02:50:14 +0000
Subject: add DOVE extensions for VXLAN

This patch provides extensions to VXLAN for supporting Distributed
Overlay Virtual Ethernet (DOVE) networks. The patch includes:

	+ a dove flag per VXLAN device to enable DOVE extensions
	+ ARP reduction, whereby a bridge-connected VXLAN tunnel endpoint
		answers ARP requests from the local bridge on behalf of
		remote DOVE clients
	+ route short-circuiting (aka L3 switching). Known destination IP
		addresses use the corresponding destination MAC address for
		switching rather than going to a (possibly remote) router first.
	+ netlink notification messages for forwarding table and L3 switching
		misses

Changes since v2
	- combined bools into "u32 flags"
	- replaced loop with !is_zero_ether_addr()

Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c          | 256 ++++++++++++++++++++++++++++++++++++++-----
 include/uapi/linux/if_link.h |   4 +
 2 files changed, 235 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a14df1ce99ff..ce77b8b693ae 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -29,6 +29,8 @@
 #include <linux/etherdevice.h>
 #include <linux/if_ether.h>
 #include <linux/hash.h>
+#include <net/arp.h>
+#include <net/ndisc.h>
 #include <net/ip.h>
 #include <net/icmp.h>
 #include <net/udp.h>
@@ -110,7 +112,7 @@ struct vxlan_dev {
 	__u16		  port_max;
 	__u8		  tos;		/* TOS override */
 	__u8		  ttl;
-	bool		  learn;
+	u32		  flags;	/* VXLAN_F_* below */
 
 	unsigned long	  age_interval;
 	struct timer_list age_timer;
@@ -121,6 +123,12 @@ struct vxlan_dev {
 	struct hlist_head fdb_head[FDB_HASH_SIZE];
 };
 
+#define VXLAN_F_LEARN	0x01
+#define VXLAN_F_PROXY	0x02
+#define VXLAN_F_RSC	0x04
+#define VXLAN_F_L2MISS	0x08
+#define VXLAN_F_L3MISS	0x10
+
 /* salt for hash table */
 static u32 vxlan_salt __read_mostly;
 
@@ -154,6 +162,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 	struct nda_cacheinfo ci;
 	struct nlmsghdr *nlh;
 	struct ndmsg *ndm;
+	bool send_ip, send_eth;
 
 	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
 	if (nlh == NULL)
@@ -161,16 +170,24 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 
 	ndm = nlmsg_data(nlh);
 	memset(ndm, 0, sizeof(*ndm));
-	ndm->ndm_family	= AF_BRIDGE;
+
+	send_eth = send_ip = true;
+
+	if (type == RTM_GETNEIGH) {
+		ndm->ndm_family	= AF_INET;
+		send_ip = fdb->remote_ip != 0;
+		send_eth = !is_zero_ether_addr(fdb->eth_addr);
+	} else
+		ndm->ndm_family	= AF_BRIDGE;
 	ndm->ndm_state = fdb->state;
 	ndm->ndm_ifindex = vxlan->dev->ifindex;
 	ndm->ndm_flags = NTF_SELF;
 	ndm->ndm_type = NDA_DST;
 
-	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
+	if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
 		goto nla_put_failure;
 
-	if (nla_put_be32(skb, NDA_DST, fdb->remote_ip))
+	if (send_ip && nla_put_be32(skb, NDA_DST, fdb->remote_ip))
 		goto nla_put_failure;
 
 	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
@@ -222,6 +239,29 @@ errout:
 		rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
 }
 
+static void vxlan_ip_miss(struct net_device *dev, __be32 ipa)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb f;
+
+	memset(&f, 0, sizeof f);
+	f.state = NUD_STALE;
+	f.remote_ip = ipa; /* goes to NDA_DST */
+
+	vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH);
+}
+
+static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN])
+{
+	struct vxlan_fdb	f;
+
+	memset(&f, 0, sizeof f);
+	f.state = NUD_STALE;
+	memcpy(f.eth_addr, eth_addr, ETH_ALEN);
+
+	vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH);
+}
+
 /* Hash Ethernet address */
 static u32 eth_hash(const unsigned char *addr)
 {
@@ -551,6 +591,8 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		goto drop;
 	}
 
+	skb_reset_mac_header(skb);
+
 	/* Re-examine inner Ethernet packet */
 	oip = ip_hdr(skb);
 	skb->protocol = eth_type_trans(skb, vxlan->dev);
@@ -560,7 +602,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 			       vxlan->dev->dev_addr) == 0)
 		goto drop;
 
-	if (vxlan->learn)
+	if (vxlan->flags & VXLAN_F_LEARN)
 		vxlan_snoop(skb->dev, oip->saddr, eth_hdr(skb)->h_source);
 
 	__skb_tunnel_rx(skb, vxlan->dev);
@@ -599,6 +641,117 @@ drop:
 	return 0;
 }
 
+static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct arphdr *parp;
+	u8 *arpptr, *sha;
+	__be32 sip, tip;
+	struct neighbour *n;
+
+	if (dev->flags & IFF_NOARP)
+		goto out;
+
+	if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
+		dev->stats.tx_dropped++;
+		goto out;
+	}
+	parp = arp_hdr(skb);
+
+	if ((parp->ar_hrd != htons(ARPHRD_ETHER) &&
+	     parp->ar_hrd != htons(ARPHRD_IEEE802)) ||
+	    parp->ar_pro != htons(ETH_P_IP) ||
+	    parp->ar_op != htons(ARPOP_REQUEST) ||
+	    parp->ar_hln != dev->addr_len ||
+	    parp->ar_pln != 4)
+		goto out;
+	arpptr = (u8 *)parp + sizeof(struct arphdr);
+	sha = arpptr;
+	arpptr += dev->addr_len;	/* sha */
+	memcpy(&sip, arpptr, sizeof(sip));
+	arpptr += sizeof(sip);
+	arpptr += dev->addr_len;	/* tha */
+	memcpy(&tip, arpptr, sizeof(tip));
+
+	if (ipv4_is_loopback(tip) ||
+	    ipv4_is_multicast(tip))
+		goto out;
+
+	n = neigh_lookup(&arp_tbl, &tip, dev);
+
+	if (n) {
+		struct vxlan_dev *vxlan = netdev_priv(dev);
+		struct vxlan_fdb *f;
+		struct sk_buff	*reply;
+
+		if (!(n->nud_state & NUD_CONNECTED)) {
+			neigh_release(n);
+			goto out;
+		}
+
+		f = vxlan_find_mac(vxlan, n->ha);
+		if (f && f->remote_ip == 0) {
+			/* bridge-local neighbor */
+			neigh_release(n);
+			goto out;
+		}
+
+		reply = arp_create(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha,
+				n->ha, sha);
+
+		neigh_release(n);
+
+		skb_reset_mac_header(reply);
+		__skb_pull(reply, skb_network_offset(reply));
+		reply->ip_summed = CHECKSUM_UNNECESSARY;
+		reply->pkt_type = PACKET_HOST;
+
+		if (netif_rx_ni(reply) == NET_RX_DROP)
+			dev->stats.rx_dropped++;
+	} else if (vxlan->flags & VXLAN_F_L3MISS)
+		vxlan_ip_miss(dev, tip);
+out:
+	consume_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct neighbour *n;
+	struct iphdr *pip;
+
+	if (is_multicast_ether_addr(eth_hdr(skb)->h_dest))
+		return false;
+
+	n = NULL;
+	switch (ntohs(eth_hdr(skb)->h_proto)) {
+	case ETH_P_IP:
+		if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+			return false;
+		pip = ip_hdr(skb);
+		n = neigh_lookup(&arp_tbl, &pip->daddr, dev);
+		break;
+	default:
+		return false;
+	}
+
+	if (n) {
+		bool diff;
+
+		diff = compare_ether_addr(eth_hdr(skb)->h_dest, n->ha) != 0;
+		if (diff) {
+			memcpy(eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
+				dev->addr_len);
+			memcpy(eth_hdr(skb)->h_dest, n->ha, dev->addr_len);
+		}
+		neigh_release(n);
+		return diff;
+	} else if (vxlan->flags & VXLAN_F_L3MISS)
+		vxlan_ip_miss(dev, pip->daddr);
+	return false;
+}
+
 /* Extract dsfield from inner protocol */
 static inline u8 vxlan_get_dsfield(const struct iphdr *iph,
 				   const struct sk_buff *skb)
@@ -621,22 +774,6 @@ static inline u8 vxlan_ecn_encap(u8 tos,
 	return INET_ECN_encapsulate(tos, inner);
 }
 
-static __be32 vxlan_find_dst(struct vxlan_dev *vxlan, struct sk_buff *skb)
-{
-	const struct ethhdr *eth = (struct ethhdr *) skb->data;
-	const struct vxlan_fdb *f;
-
-	if (is_multicast_ether_addr(eth->h_dest))
-		return vxlan->gaddr;
-
-	f = vxlan_find_mac(vxlan, eth->h_dest);
-	if (f)
-		return f->remote_ip;
-	else
-		return vxlan->gaddr;
-
-}
-
 static void vxlan_sock_free(struct sk_buff *skb)
 {
 	sock_put(skb->sk);
@@ -683,6 +820,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct rtable *rt;
 	const struct iphdr *old_iph;
+	struct ethhdr *eth;
 	struct iphdr *iph;
 	struct vxlanhdr *vxh;
 	struct udphdr *uh;
@@ -693,10 +831,50 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	__be16 df = 0;
 	__u8 tos, ttl;
 	int err;
+	bool did_rsc = false;
+	const struct vxlan_fdb *f;
+
+	skb_reset_mac_header(skb);
+	eth = eth_hdr(skb);
+
+	if ((vxlan->flags & VXLAN_F_PROXY) && ntohs(eth->h_proto) == ETH_P_ARP)
+		return arp_reduce(dev, skb);
+	else if ((vxlan->flags&VXLAN_F_RSC) && ntohs(eth->h_proto) == ETH_P_IP)
+		did_rsc = route_shortcircuit(dev, skb);
 
-	dst = vxlan_find_dst(vxlan, skb);
-	if (!dst)
+	f = vxlan_find_mac(vxlan, eth->h_dest);
+	if (f == NULL) {
+		did_rsc = false;
+		dst = vxlan->gaddr;
+		if (!dst && (vxlan->flags & VXLAN_F_L2MISS) &&
+		    !is_multicast_ether_addr(eth->h_dest))
+			vxlan_fdb_miss(vxlan, eth->h_dest);
+	} else
+		dst = f->remote_ip;
+
+	if (!dst) {
+		if (did_rsc) {
+			__skb_pull(skb, skb_network_offset(skb));
+			skb->ip_summed = CHECKSUM_NONE;
+			skb->pkt_type = PACKET_HOST;
+
+			/* short-circuited back to local bridge */
+			if (netif_rx(skb) == NET_RX_SUCCESS) {
+				struct vxlan_stats *stats =
+						this_cpu_ptr(vxlan->stats);
+
+				u64_stats_update_begin(&stats->syncp);
+				stats->tx_packets++;
+				stats->tx_bytes += pkt_len;
+				u64_stats_update_end(&stats->syncp);
+			} else {
+				dev->stats.tx_errors++;
+				dev->stats.tx_aborted_errors++;
+			}
+			return NETDEV_TX_OK;
+		}
 		goto drop;
+	}
 
 	/* Need space for new headers (invalidates iph ptr) */
 	if (skb_cow_head(skb, VXLAN_HEADROOM))
@@ -1019,6 +1197,10 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_AGEING]	= { .type = NLA_U32 },
 	[IFLA_VXLAN_LIMIT]	= { .type = NLA_U32 },
 	[IFLA_VXLAN_PORT_RANGE] = { .len  = sizeof(struct ifla_vxlan_port_range) },
+	[IFLA_VXLAN_PROXY]	= { .type = NLA_U8 },
+	[IFLA_VXLAN_RSC]	= { .type = NLA_U8 },
+	[IFLA_VXLAN_L2MISS]	= { .type = NLA_U8 },
+	[IFLA_VXLAN_L3MISS]	= { .type = NLA_U8 },
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1114,13 +1296,25 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 		vxlan->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]);
 
 	if (!data[IFLA_VXLAN_LEARNING] || nla_get_u8(data[IFLA_VXLAN_LEARNING]))
-		vxlan->learn = true;
+		vxlan->flags |= VXLAN_F_LEARN;
 
 	if (data[IFLA_VXLAN_AGEING])
 		vxlan->age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]);
 	else
 		vxlan->age_interval = FDB_AGE_DEFAULT;
 
+	if (data[IFLA_VXLAN_PROXY] && nla_get_u8(data[IFLA_VXLAN_PROXY]))
+		vxlan->flags |= VXLAN_F_PROXY;
+
+	if (data[IFLA_VXLAN_RSC] && nla_get_u8(data[IFLA_VXLAN_RSC]))
+		vxlan->flags |= VXLAN_F_RSC;
+
+	if (data[IFLA_VXLAN_L2MISS] && nla_get_u8(data[IFLA_VXLAN_L2MISS]))
+		vxlan->flags |= VXLAN_F_L2MISS;
+
+	if (data[IFLA_VXLAN_L3MISS] && nla_get_u8(data[IFLA_VXLAN_L3MISS]))
+		vxlan->flags |= VXLAN_F_L3MISS;
+
 	if (data[IFLA_VXLAN_LIMIT])
 		vxlan->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]);
 
@@ -1157,6 +1351,10 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TTL */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TOS */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_LEARNING */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_PROXY */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_RSC */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_L2MISS */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_L3MISS */
 		nla_total_size(sizeof(__u32)) +	/* IFLA_VXLAN_AGEING */
 		nla_total_size(sizeof(__u32)) +	/* IFLA_VXLAN_LIMIT */
 		nla_total_size(sizeof(struct ifla_vxlan_port_range)) +
@@ -1185,7 +1383,15 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) ||
 	    nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) ||
-	    nla_put_u8(skb, IFLA_VXLAN_LEARNING, vxlan->learn) ||
+	    nla_put_u8(skb, IFLA_VXLAN_LEARNING,
+			!!(vxlan->flags & VXLAN_F_LEARN)) ||
+	    nla_put_u8(skb, IFLA_VXLAN_PROXY,
+			!!(vxlan->flags & VXLAN_F_PROXY)) ||
+	    nla_put_u8(skb, IFLA_VXLAN_RSC, !!(vxlan->flags & VXLAN_F_RSC)) ||
+	    nla_put_u8(skb, IFLA_VXLAN_L2MISS,
+			!!(vxlan->flags & VXLAN_F_L2MISS)) ||
+	    nla_put_u8(skb, IFLA_VXLAN_L3MISS,
+			!!(vxlan->flags & VXLAN_F_L3MISS)) ||
 	    nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->age_interval) ||
 	    nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->addrmax))
 		goto nla_put_failure;
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 7aae0179ae44..bb58aeb7f34d 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -302,6 +302,10 @@ enum {
 	IFLA_VXLAN_AGEING,
 	IFLA_VXLAN_LIMIT,
 	IFLA_VXLAN_PORT_RANGE,
+	IFLA_VXLAN_PROXY,
+	IFLA_VXLAN_RSC,
+	IFLA_VXLAN_L2MISS,
+	IFLA_VXLAN_L3MISS,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
-- 
cgit v1.2.3-55-g7522


From e2f1f072db8db81e6b5bcbfcf409bb5c91dc9329 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Mon, 19 Nov 2012 22:41:45 +0000
Subject: sit: allow to configure 6rd tunnels via netlink

This patch add the support of 6RD tunnels management via netlink.
Note that netdev_state_change() is now called when 6RD parameters are updated.

6RD parameters are updated only if there is at least one 6RD attribute.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_tunnel.h |   4 ++
 net/ipv6/sit.c                 | 149 ++++++++++++++++++++++++++++++++++-------
 2 files changed, 128 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 5ab0c8ddc2bc..aee73d0611fb 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -49,6 +49,10 @@ enum {
 	IFLA_IPTUN_FLAGS,
 	IFLA_IPTUN_PROTO,
 	IFLA_IPTUN_PMTUDISC,
+	IFLA_IPTUN_6RD_PREFIX,
+	IFLA_IPTUN_6RD_RELAY_PREFIX,
+	IFLA_IPTUN_6RD_PREFIXLEN,
+	IFLA_IPTUN_6RD_RELAY_PREFIXLEN,
 	__IFLA_IPTUN_MAX,
 };
 #define IFLA_IPTUN_MAX	(__IFLA_IPTUN_MAX - 1)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index fee21c6c3ebf..80cb3829831c 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -936,6 +936,38 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
 	netdev_state_change(t->dev);
 }
 
+#ifdef CONFIG_IPV6_SIT_6RD
+static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
+				   struct ip_tunnel_6rd *ip6rd)
+{
+	struct in6_addr prefix;
+	__be32 relay_prefix;
+
+	if (ip6rd->relay_prefixlen > 32 ||
+	    ip6rd->prefixlen + (32 - ip6rd->relay_prefixlen) > 64)
+		return -EINVAL;
+
+	ipv6_addr_prefix(&prefix, &ip6rd->prefix, ip6rd->prefixlen);
+	if (!ipv6_addr_equal(&prefix, &ip6rd->prefix))
+		return -EINVAL;
+	if (ip6rd->relay_prefixlen)
+		relay_prefix = ip6rd->relay_prefix &
+			       htonl(0xffffffffUL <<
+				     (32 - ip6rd->relay_prefixlen));
+	else
+		relay_prefix = 0;
+	if (relay_prefix != ip6rd->relay_prefix)
+		return -EINVAL;
+
+	t->ip6rd.prefix = prefix;
+	t->ip6rd.relay_prefix = relay_prefix;
+	t->ip6rd.prefixlen = ip6rd->prefixlen;
+	t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen;
+	netdev_state_change(t->dev);
+	return 0;
+}
+#endif
+
 static int
 ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 {
@@ -1105,31 +1137,9 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		t = netdev_priv(dev);
 
 		if (cmd != SIOCDEL6RD) {
-			struct in6_addr prefix;
-			__be32 relay_prefix;
-
-			err = -EINVAL;
-			if (ip6rd.relay_prefixlen > 32 ||
-			    ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64)
-				goto done;
-
-			ipv6_addr_prefix(&prefix, &ip6rd.prefix,
-					 ip6rd.prefixlen);
-			if (!ipv6_addr_equal(&prefix, &ip6rd.prefix))
+			err = ipip6_tunnel_update_6rd(t, &ip6rd);
+			if (err < 0)
 				goto done;
-			if (ip6rd.relay_prefixlen)
-				relay_prefix = ip6rd.relay_prefix &
-					       htonl(0xffffffffUL <<
-						     (32 - ip6rd.relay_prefixlen));
-			else
-				relay_prefix = 0;
-			if (relay_prefix != ip6rd.relay_prefix)
-				goto done;
-
-			t->ip6rd.prefix = prefix;
-			t->ip6rd.relay_prefix = relay_prefix;
-			t->ip6rd.prefixlen = ip6rd.prefixlen;
-			t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen;
 		} else
 			ipip6_tunnel_clone_6rd(dev, sitn);
 
@@ -1261,11 +1271,53 @@ static void ipip6_netlink_parms(struct nlattr *data[],
 		parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]);
 }
 
+#ifdef CONFIG_IPV6_SIT_6RD
+/* This function returns true when 6RD attributes are present in the nl msg */
+static bool ipip6_netlink_6rd_parms(struct nlattr *data[],
+				    struct ip_tunnel_6rd *ip6rd)
+{
+	bool ret = false;
+	memset(ip6rd, 0, sizeof(*ip6rd));
+
+	if (!data)
+		return ret;
+
+	if (data[IFLA_IPTUN_6RD_PREFIX]) {
+		ret = true;
+		nla_memcpy(&ip6rd->prefix, data[IFLA_IPTUN_6RD_PREFIX],
+			   sizeof(struct in6_addr));
+	}
+
+	if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) {
+		ret = true;
+		ip6rd->relay_prefix =
+			nla_get_be32(data[IFLA_IPTUN_6RD_RELAY_PREFIX]);
+	}
+
+	if (data[IFLA_IPTUN_6RD_PREFIXLEN]) {
+		ret = true;
+		ip6rd->prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_PREFIXLEN]);
+	}
+
+	if (data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]) {
+		ret = true;
+		ip6rd->relay_prefixlen =
+			nla_get_u16(data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]);
+	}
+
+	return ret;
+}
+#endif
+
 static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net *net = dev_net(dev);
 	struct ip_tunnel *nt;
+#ifdef CONFIG_IPV6_SIT_6RD
+	struct ip_tunnel_6rd ip6rd;
+#endif
+	int err;
 
 	nt = netdev_priv(dev);
 	ipip6_netlink_parms(data, &nt->parms);
@@ -1273,7 +1325,16 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 	if (ipip6_tunnel_locate(net, &nt->parms, 0))
 		return -EEXIST;
 
-	return ipip6_tunnel_create(dev);
+	err = ipip6_tunnel_create(dev);
+	if (err < 0)
+		return err;
+
+#ifdef CONFIG_IPV6_SIT_6RD
+	if (ipip6_netlink_6rd_parms(data, &ip6rd))
+		err = ipip6_tunnel_update_6rd(nt, &ip6rd);
+#endif
+
+	return err;
 }
 
 static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
@@ -1283,6 +1344,9 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct ip_tunnel_parm p;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
+#ifdef CONFIG_IPV6_SIT_6RD
+	struct ip_tunnel_6rd ip6rd;
+#endif
 
 	if (dev == sitn->fb_tunnel_dev)
 		return -EINVAL;
@@ -1302,6 +1366,12 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 		t = netdev_priv(dev);
 
 	ipip6_tunnel_update(t, &p);
+
+#ifdef CONFIG_IPV6_SIT_6RD
+	if (ipip6_netlink_6rd_parms(data, &ip6rd))
+		return ipip6_tunnel_update_6rd(t, &ip6rd);
+#endif
+
 	return 0;
 }
 
@@ -1322,6 +1392,16 @@ static size_t ipip6_get_size(const struct net_device *dev)
 		nla_total_size(1) +
 		/* IFLA_IPTUN_FLAGS */
 		nla_total_size(2) +
+#ifdef CONFIG_IPV6_SIT_6RD
+		/* IFLA_IPTUN_6RD_PREFIX */
+		nla_total_size(sizeof(struct in6_addr)) +
+		/* IFLA_IPTUN_6RD_RELAY_PREFIX */
+		nla_total_size(4) +
+		/* IFLA_IPTUN_6RD_PREFIXLEN */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */
+		nla_total_size(2) +
+#endif
 		0;
 }
 
@@ -1339,6 +1419,19 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		       !!(parm->iph.frag_off & htons(IP_DF))) ||
 	    nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags))
 		goto nla_put_failure;
+
+#ifdef CONFIG_IPV6_SIT_6RD
+	if (nla_put(skb, IFLA_IPTUN_6RD_PREFIX, sizeof(struct in6_addr),
+		    &tunnel->ip6rd.prefix) ||
+	    nla_put_be32(skb, IFLA_IPTUN_6RD_RELAY_PREFIX,
+			 tunnel->ip6rd.relay_prefix) ||
+	    nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN,
+			tunnel->ip6rd.prefixlen) ||
+	    nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN,
+			tunnel->ip6rd.relay_prefixlen))
+		goto nla_put_failure;
+#endif
+
 	return 0;
 
 nla_put_failure:
@@ -1353,6 +1446,12 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_TOS]		= { .type = NLA_U8 },
 	[IFLA_IPTUN_PMTUDISC]		= { .type = NLA_U8 },
 	[IFLA_IPTUN_FLAGS]		= { .type = NLA_U16 },
+#ifdef CONFIG_IPV6_SIT_6RD
+	[IFLA_IPTUN_6RD_PREFIX]		= { .len = sizeof(struct in6_addr) },
+	[IFLA_IPTUN_6RD_RELAY_PREFIX]	= { .type = NLA_U32 },
+	[IFLA_IPTUN_6RD_PREFIXLEN]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 },
+#endif
 };
 
 static struct rtnl_link_ops sit_link_ops __read_mostly = {
-- 
cgit v1.2.3-55-g7522


From 78026a6fde8f7b0ca77c059da11f476d69dfde3b Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Tue, 20 Nov 2012 13:36:00 +0000
Subject: iio:imu:adis: Add debugfs register access support

Provide a IIO debugfs register access function for the ADIS library. This
function can be used by individual drivers to allow raw register access via
debugfs.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/imu/adis.c       | 23 +++++++++++++++++++++++
 include/linux/iio/imu/adis.h | 11 +++++++++++
 2 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c
index 8259b774078f..28d4df2fe76a 100644
--- a/drivers/iio/imu/adis.c
+++ b/drivers/iio/imu/adis.c
@@ -135,6 +135,29 @@ error_ret:
 }
 EXPORT_SYMBOL_GPL(adis_read_reg_16);
 
+#ifdef CONFIG_DEBUG_FS
+
+int adis_debugfs_reg_access(struct iio_dev *indio_dev,
+	unsigned int reg, unsigned int writeval, unsigned int *readval)
+{
+	struct adis *adis = iio_device_get_drvdata(indio_dev);
+
+	if (readval) {
+		uint16_t val16;
+		int ret;
+
+		ret = adis_read_reg_16(adis, reg, &val16);
+		*readval = val16;
+
+		return ret;
+	} else {
+		return adis_write_reg_16(adis, reg, writeval);
+	}
+}
+EXPORT_SYMBOL(adis_debugfs_reg_access);
+
+#endif
+
 /**
  * adis_enable_irq() - Enable or disable data ready IRQ
  * @adis: The adis device
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index 8c3304d44b97..fce7bc3ba0b5 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -183,4 +183,15 @@ static inline void adis_remove_trigger(struct adis *adis)
 
 #endif /* CONFIG_IIO_BUFFER */
 
+#ifdef CONFIG_DEBUG_FS
+
+int adis_debugfs_reg_access(struct iio_dev *indio_dev,
+	unsigned int reg, unsigned int writeval, unsigned int *readval);
+
+#else
+
+#define adis_debugfs_reg_access NULL
+
+#endif
+
 #endif
-- 
cgit v1.2.3-55-g7522


From 57a1228a06b7a5939a8b0078a92b44fa30855bcb Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Tue, 20 Nov 2012 13:36:00 +0000
Subject: iio:imu:adis: Add support for 32bit registers

Some of the newer generation devices from the ADIS16XXX family have 32bit wide
register which spans two 16bit wide registers. This patch adds support for
reading and writing a 32bit wide register.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/imu/adis.c        | 145 +++++++++++++++++++++++++++---------------
 drivers/iio/imu/adis_buffer.c |   2 +
 include/linux/iio/imu/adis.h  |  81 +++++++++++++++++++++--
 3 files changed, 171 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c
index 28d4df2fe76a..280a49584adf 100644
--- a/drivers/iio/imu/adis.c
+++ b/drivers/iio/imu/adis.c
@@ -27,36 +27,10 @@
 #define ADIS_MSC_CTRL_DATA_RDY_DIO2	BIT(0)
 #define ADIS_GLOB_CMD_SW_RESET		BIT(7)
 
-/**
- * adis_write_reg_8() - Write single byte to a register
- * @adis: The adis device
- * @reg: The address of the register to be written
- * @val: The value to write
- */
-int adis_write_reg_8(struct adis *adis, unsigned int reg, uint8_t val)
-{
-	int ret;
-
-	mutex_lock(&adis->txrx_lock);
-	adis->tx[0] = ADIS_WRITE_REG(reg);
-	adis->tx[1] = val;
-
-	ret = spi_write(adis->spi, adis->tx, 2);
-	mutex_unlock(&adis->txrx_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_write_reg_8);
-
-/**
- * adis_write_reg_16() - Write 2 bytes to a pair of registers
- * @adis: The adis device
- * @reg: The address of the lower of the two registers
- * @val: Value to be written
- */
-int adis_write_reg_16(struct adis *adis, unsigned int reg, uint16_t value)
+int adis_write_reg(struct adis *adis, unsigned int reg,
+	unsigned int value, unsigned int size)
 {
-	int ret;
+	int ret, i;
 	struct spi_message msg;
 	struct spi_transfer xfers[] = {
 		{
@@ -69,33 +43,69 @@ int adis_write_reg_16(struct adis *adis, unsigned int reg, uint16_t value)
 			.tx_buf = adis->tx + 2,
 			.bits_per_word = 8,
 			.len = 2,
+			.cs_change = 1,
+			.delay_usecs = adis->data->write_delay,
+		}, {
+			.tx_buf = adis->tx + 4,
+			.bits_per_word = 8,
+			.len = 2,
+			.cs_change = 1,
+			.delay_usecs = adis->data->write_delay,
+		}, {
+			.tx_buf = adis->tx + 6,
+			.bits_per_word = 8,
+			.len = 2,
 			.delay_usecs = adis->data->write_delay,
 		},
 	};
 
 	mutex_lock(&adis->txrx_lock);
-	adis->tx[0] = ADIS_WRITE_REG(reg);
-	adis->tx[1] = value & 0xff;
-	adis->tx[2] = ADIS_WRITE_REG(reg + 1);
-	adis->tx[3] = (value >> 8) & 0xff;
 
 	spi_message_init(&msg);
-	spi_message_add_tail(&xfers[0], &msg);
-	spi_message_add_tail(&xfers[1], &msg);
+	switch (size) {
+	case 4:
+		adis->tx[6] = ADIS_WRITE_REG(reg + 3);
+		adis->tx[7] = (value >> 24) & 0xff;
+		adis->tx[4] = ADIS_WRITE_REG(reg + 2);
+		adis->tx[5] = (value >> 16) & 0xff;
+	case 2:
+		adis->tx[2] = ADIS_WRITE_REG(reg + 1);
+		adis->tx[3] = (value >> 8) & 0xff;
+	case 1:
+		adis->tx[0] = ADIS_WRITE_REG(reg);
+		adis->tx[1] = value & 0xff;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	xfers[size - 1].cs_change = 0;
+
+	for (i = 0; i < size; i++)
+		spi_message_add_tail(&xfers[i], &msg);
+
 	ret = spi_sync(adis->spi, &msg);
+	if (ret) {
+		dev_err(&adis->spi->dev, "Failed to write register 0x%02X: %d\n",
+				reg, ret);
+	}
+
+out_unlock:
 	mutex_unlock(&adis->txrx_lock);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(adis_write_reg_16);
+EXPORT_SYMBOL_GPL(adis_write_reg);
 
 /**
- * adis_read_reg_16() - read 2 bytes from a 16-bit register
+ * adis_read_reg() - read 2 bytes from a 16-bit register
  * @adis: The adis device
  * @reg: The address of the lower of the two registers
  * @val: The value read back from the device
  */
-int adis_read_reg_16(struct adis *adis, unsigned int reg, uint16_t *val)
+int adis_read_reg(struct adis *adis, unsigned int reg,
+	unsigned int *val, unsigned int size)
 {
 	struct spi_message msg;
 	int ret;
@@ -107,33 +117,61 @@ int adis_read_reg_16(struct adis *adis, unsigned int reg, uint16_t *val)
 			.cs_change = 1,
 			.delay_usecs = adis->data->read_delay,
 		}, {
+			.tx_buf = adis->tx + 2,
 			.rx_buf = adis->rx,
 			.bits_per_word = 8,
 			.len = 2,
+			.cs_change = 1,
+			.delay_usecs = adis->data->read_delay,
+		}, {
+			.rx_buf = adis->rx + 2,
+			.bits_per_word = 8,
+			.len = 2,
 			.delay_usecs = adis->data->read_delay,
 		},
 	};
 
 	mutex_lock(&adis->txrx_lock);
-	adis->tx[0] = ADIS_READ_REG(reg);
-	adis->tx[1] = 0;
-
 	spi_message_init(&msg);
-	spi_message_add_tail(&xfers[0], &msg);
-	spi_message_add_tail(&xfers[1], &msg);
+
+	switch (size) {
+	case 4:
+		adis->tx[0] = ADIS_READ_REG(reg + 2);
+		adis->tx[1] = 0;
+		spi_message_add_tail(&xfers[0], &msg);
+	case 2:
+		adis->tx[2] = ADIS_READ_REG(reg);
+		adis->tx[3] = 0;
+		spi_message_add_tail(&xfers[1], &msg);
+		spi_message_add_tail(&xfers[2], &msg);
+		break;
+	default:
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	ret = spi_sync(adis->spi, &msg);
 	if (ret) {
-		dev_err(&adis->spi->dev, "Failed to read 16 bit register 0x%02X: %d\n",
+		dev_err(&adis->spi->dev, "Failed to read register 0x%02X: %d\n",
 				reg, ret);
-		goto error_ret;
+		goto out_unlock;
 	}
-	*val = get_unaligned_be16(adis->rx);
 
-error_ret:
+	switch (size) {
+	case 4:
+		*val = get_unaligned_be32(adis->rx);
+		break;
+	case 2:
+		*val = get_unaligned_be16(adis->rx + 2);
+		break;
+	}
+
+out_unlock:
 	mutex_unlock(&adis->txrx_lock);
+
 	return ret;
 }
-EXPORT_SYMBOL_GPL(adis_read_reg_16);
+EXPORT_SYMBOL_GPL(adis_read_reg);
 
 #ifdef CONFIG_DEBUG_FS
 
@@ -304,25 +342,26 @@ int adis_single_conversion(struct iio_dev *indio_dev,
 	const struct iio_chan_spec *chan, unsigned int error_mask, int *val)
 {
 	struct adis *adis = iio_device_get_drvdata(indio_dev);
-	uint16_t val16;
+	unsigned int uval;
 	int ret;
 
 	mutex_lock(&indio_dev->mlock);
 
-	ret = adis_read_reg_16(adis, chan->address, &val16);
+	ret = adis_read_reg(adis, chan->address, &uval,
+			chan->scan_type.storagebits / 8);
 	if (ret)
 		goto err_unlock;
 
-	if (val16 & error_mask) {
+	if (uval & error_mask) {
 		ret = adis_check_status(adis);
 		if (ret)
 			goto err_unlock;
 	}
 
 	if (chan->scan_type.sign == 's')
-		*val = sign_extend32(val16, chan->scan_type.realbits - 1);
+		*val = sign_extend32(uval, chan->scan_type.realbits - 1);
 	else
-		*val = val16 & ((1 << chan->scan_type.realbits) - 1);
+		*val = uval & ((1 << chan->scan_type.realbits) - 1);
 
 	ret = IIO_VAL_INT;
 err_unlock:
diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
index a91b4cbdc73a..785713349e9f 100644
--- a/drivers/iio/imu/adis_buffer.c
+++ b/drivers/iio/imu/adis_buffer.c
@@ -64,6 +64,8 @@ int adis_update_scan_mode(struct iio_dev *indio_dev,
 	for (i = 0; i < indio_dev->num_channels; i++, chan++) {
 		if (!test_bit(chan->scan_index, scan_mask))
 			continue;
+		if (chan->scan_type.storagebits == 32)
+			*tx++ = cpu_to_be16((chan->address + 2) << 8);
 		*tx++ = cpu_to_be16(chan->address << 8);
 	}
 
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index fce7bc3ba0b5..6402a08c0e65 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -53,7 +53,7 @@ struct adis {
 	struct spi_transfer	*xfer;
 	void			*buffer;
 
-	uint8_t			tx[8] ____cacheline_aligned;
+	uint8_t			tx[10] ____cacheline_aligned;
 	uint8_t			rx[4];
 };
 
@@ -61,9 +61,82 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev,
 	struct spi_device *spi, const struct adis_data *data);
 int adis_reset(struct adis *adis);
 
-int adis_write_reg_8(struct adis *adis, unsigned int reg, uint8_t val);
-int adis_write_reg_16(struct adis *adis, unsigned int reg, uint16_t val);
-int adis_read_reg_16(struct adis *adis, unsigned int reg, uint16_t *val);
+int adis_write_reg(struct adis *adis, unsigned int reg,
+	unsigned int val, unsigned int size);
+int adis_read_reg(struct adis *adis, unsigned int reg,
+	unsigned int *val, unsigned int size);
+
+/**
+ * adis_write_reg_8() - Write single byte to a register
+ * @adis: The adis device
+ * @reg: The address of the register to be written
+ * @value: The value to write
+ */
+static inline int adis_write_reg_8(struct adis *adis, unsigned int reg,
+	uint8_t val)
+{
+	return adis_write_reg(adis, reg, val, 1);
+}
+
+/**
+ * adis_write_reg_16() - Write 2 bytes to a pair of registers
+ * @adis: The adis device
+ * @reg: The address of the lower of the two registers
+ * @value: Value to be written
+ */
+static inline int adis_write_reg_16(struct adis *adis, unsigned int reg,
+	uint16_t val)
+{
+	return adis_write_reg(adis, reg, val, 2);
+}
+
+/**
+ * adis_write_reg_32() - write 4 bytes to four registers
+ * @adis: The adis device
+ * @reg: The address of the lower of the four register
+ * @value: Value to be written
+ */
+static inline int adis_write_reg_32(struct adis *adis, unsigned int reg,
+	uint32_t val)
+{
+	return adis_write_reg(adis, reg, val, 4);
+}
+
+/**
+ * adis_read_reg_16() - read 2 bytes from a 16-bit register
+ * @adis: The adis device
+ * @reg: The address of the lower of the two registers
+ * @val: The value read back from the device
+ */
+static inline int adis_read_reg_16(struct adis *adis, unsigned int reg,
+	uint16_t *val)
+{
+	unsigned int tmp;
+	int ret;
+
+	ret = adis_read_reg(adis, reg, &tmp, 2);
+	*val = tmp;
+
+	return ret;
+}
+
+/**
+ * adis_read_reg_32() - read 4 bytes from a 32-bit register
+ * @adis: The adis device
+ * @reg: The address of the lower of the two registers
+ * @val: The value read back from the device
+ */
+static inline int adis_read_reg_32(struct adis *adis, unsigned int reg,
+	uint32_t *val)
+{
+	unsigned int tmp;
+	int ret;
+
+	ret = adis_read_reg(adis, reg, &tmp, 4);
+	*val = tmp;
+
+	return ret;
+}
 
 int adis_enable_irq(struct adis *adis, bool enable);
 int adis_check_status(struct adis *adis);
-- 
cgit v1.2.3-55-g7522


From de4594a51c904ddcd6c3a6cdd100f7c1d94d3239 Mon Sep 17 00:00:00 2001
From: Neil Horman
Date: Tue, 20 Nov 2012 10:14:30 +0000
Subject: sctp: send abort chunk when max_retrans exceeded

In the event that an association exceeds its max_retrans attempts, we should
send an ABORT chunk indicating that we are closing the assocation as a result.
Because of the nature of the error, its unlikely to be received, but its a nice
clean way to close the association if it does make it through, and it will give
anyone watching via tcpdump a clue as to what happened.

Change notes:
v2)
	* Removed erroneous changes from sctp_make_violation_parmlen

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Vlad Yasevich <vyasevich@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: linux-sctp@vger.kernel.org
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sm.h    |  2 ++
 net/sctp/sm_make_chunk.c | 19 +++++++++++++++++++
 net/sctp/sm_sideeffect.c |  9 ++++++++-
 3 files changed, 29 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index b5887e1677e4..2a82d1384706 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -234,6 +234,8 @@ struct sctp_chunk *sctp_make_abort_violation(const struct sctp_association *,
 struct sctp_chunk *sctp_make_violation_paramlen(const struct sctp_association *,
 				   const struct sctp_chunk *,
 				   struct sctp_paramhdr *);
+struct sctp_chunk *sctp_make_violation_max_retrans(const struct sctp_association *,
+						   const struct sctp_chunk *);
 struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *,
 				  const struct sctp_transport *);
 struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *,
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index fbe1636309a7..e0f01a4e8cd6 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1090,6 +1090,25 @@ nodata:
 	return retval;
 }
 
+struct sctp_chunk *sctp_make_violation_max_retrans(
+	const struct sctp_association *asoc,
+	const struct sctp_chunk *chunk)
+{
+	struct sctp_chunk *retval;
+	static const char error[] = "Association exceeded its max_retans count";
+	size_t payload_len = sizeof(error) + sizeof(sctp_errhdr_t);
+
+	retval = sctp_make_abort(asoc, chunk, payload_len);
+	if (!retval)
+		goto nodata;
+
+	sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, sizeof(error));
+	sctp_addto_chunk(retval, sizeof(error), error);
+
+nodata:
+	return retval;
+}
+
 /* Make a HEARTBEAT chunk.  */
 struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
 				  const struct sctp_transport *transport)
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 6eecf7e6338d..c0769569b05d 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -577,7 +577,7 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands,
 				  unsigned int error)
 {
 	struct sctp_ulpevent *event;
-
+	struct sctp_chunk *abort;
 	/* Cancel any partial delivery in progress. */
 	sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC);
 
@@ -593,6 +593,13 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands,
 		sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
 				SCTP_ULPEVENT(event));
 
+	if (asoc->overall_error_count >= asoc->max_retrans) {
+		abort = sctp_make_violation_max_retrans(asoc, chunk);
+		if (abort)
+			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
+					SCTP_CHUNK(abort));
+	}
+
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
 			SCTP_STATE(SCTP_STATE_CLOSED));
 
-- 
cgit v1.2.3-55-g7522


From 484a0bf091c93c379e6524a17bb037c33c898e01 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Tue, 20 Nov 2012 13:36:00 +0000
Subject: iio:imu:adis: Add paging support

Some of the newer generation devices from the ADIS16XXX series have more
registers than what can be supported with the current register addressing
scheme. These devices implement register paging to support a larger register
range. Each page is 128 registers large and the currently active page can be
selected via register 0x00 in each page. This patch implements transparent
paging inside the common adis library. The register read/write interface stays
the same and when a register is accessed the library automatically switches to
the correct page if it is not already selected. The page number is encoded in
the upper bits of the register number, e.g. register 0x5 of page 1 is 0x85.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/imu/adis.c        | 70 +++++++++++++++++++++++++++++++++----------
 drivers/iio/imu/adis_buffer.c | 15 ++++++++++
 include/linux/iio/imu/adis.h  | 10 +++++--
 3 files changed, 77 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c
index 280a49584adf..c4ea04ffa60e 100644
--- a/drivers/iio/imu/adis.c
+++ b/drivers/iio/imu/adis.c
@@ -30,6 +30,7 @@
 int adis_write_reg(struct adis *adis, unsigned int reg,
 	unsigned int value, unsigned int size)
 {
+	unsigned int page = reg / ADIS_PAGE_SIZE;
 	int ret, i;
 	struct spi_message msg;
 	struct spi_transfer xfers[] = {
@@ -56,39 +57,53 @@ int adis_write_reg(struct adis *adis, unsigned int reg,
 			.bits_per_word = 8,
 			.len = 2,
 			.delay_usecs = adis->data->write_delay,
+		}, {
+			.tx_buf = adis->tx + 8,
+			.bits_per_word = 8,
+			.len = 2,
+			.delay_usecs = adis->data->write_delay,
 		},
 	};
 
 	mutex_lock(&adis->txrx_lock);
 
 	spi_message_init(&msg);
+
+	if (adis->current_page != page) {
+		adis->tx[0] = ADIS_WRITE_REG(ADIS_REG_PAGE_ID);
+		adis->tx[1] = page;
+		spi_message_add_tail(&xfers[0], &msg);
+	}
+
 	switch (size) {
 	case 4:
-		adis->tx[6] = ADIS_WRITE_REG(reg + 3);
-		adis->tx[7] = (value >> 24) & 0xff;
-		adis->tx[4] = ADIS_WRITE_REG(reg + 2);
-		adis->tx[5] = (value >> 16) & 0xff;
+		adis->tx[8] = ADIS_WRITE_REG(reg + 3);
+		adis->tx[9] = (value >> 24) & 0xff;
+		adis->tx[6] = ADIS_WRITE_REG(reg + 2);
+		adis->tx[7] = (value >> 16) & 0xff;
 	case 2:
-		adis->tx[2] = ADIS_WRITE_REG(reg + 1);
-		adis->tx[3] = (value >> 8) & 0xff;
+		adis->tx[4] = ADIS_WRITE_REG(reg + 1);
+		adis->tx[5] = (value >> 8) & 0xff;
 	case 1:
-		adis->tx[0] = ADIS_WRITE_REG(reg);
-		adis->tx[1] = value & 0xff;
+		adis->tx[2] = ADIS_WRITE_REG(reg);
+		adis->tx[3] = value & 0xff;
 		break;
 	default:
 		ret = -EINVAL;
 		goto out_unlock;
 	}
 
-	xfers[size - 1].cs_change = 0;
+	xfers[size].cs_change = 0;
 
-	for (i = 0; i < size; i++)
+	for (i = 1; i <= size; i++)
 		spi_message_add_tail(&xfers[i], &msg);
 
 	ret = spi_sync(adis->spi, &msg);
 	if (ret) {
 		dev_err(&adis->spi->dev, "Failed to write register 0x%02X: %d\n",
 				reg, ret);
+	} else {
+		adis->current_page = page;
 	}
 
 out_unlock:
@@ -107,6 +122,7 @@ EXPORT_SYMBOL_GPL(adis_write_reg);
 int adis_read_reg(struct adis *adis, unsigned int reg,
 	unsigned int *val, unsigned int size)
 {
+	unsigned int page = reg / ADIS_PAGE_SIZE;
 	struct spi_message msg;
 	int ret;
 	struct spi_transfer xfers[] = {
@@ -115,9 +131,15 @@ int adis_read_reg(struct adis *adis, unsigned int reg,
 			.bits_per_word = 8,
 			.len = 2,
 			.cs_change = 1,
-			.delay_usecs = adis->data->read_delay,
+			.delay_usecs = adis->data->write_delay,
 		}, {
 			.tx_buf = adis->tx + 2,
+			.bits_per_word = 8,
+			.len = 2,
+			.cs_change = 1,
+			.delay_usecs = adis->data->read_delay,
+		}, {
+			.tx_buf = adis->tx + 4,
 			.rx_buf = adis->rx,
 			.bits_per_word = 8,
 			.len = 2,
@@ -134,16 +156,22 @@ int adis_read_reg(struct adis *adis, unsigned int reg,
 	mutex_lock(&adis->txrx_lock);
 	spi_message_init(&msg);
 
+	if (adis->current_page != page) {
+		adis->tx[0] = ADIS_WRITE_REG(ADIS_REG_PAGE_ID);
+		adis->tx[1] = page;
+		spi_message_add_tail(&xfers[0], &msg);
+	}
+
 	switch (size) {
 	case 4:
-		adis->tx[0] = ADIS_READ_REG(reg + 2);
-		adis->tx[1] = 0;
-		spi_message_add_tail(&xfers[0], &msg);
-	case 2:
-		adis->tx[2] = ADIS_READ_REG(reg);
+		adis->tx[2] = ADIS_READ_REG(reg + 2);
 		adis->tx[3] = 0;
 		spi_message_add_tail(&xfers[1], &msg);
+	case 2:
+		adis->tx[4] = ADIS_READ_REG(reg);
+		adis->tx[5] = 0;
 		spi_message_add_tail(&xfers[2], &msg);
+		spi_message_add_tail(&xfers[3], &msg);
 		break;
 	default:
 		ret = -EINVAL;
@@ -155,6 +183,8 @@ int adis_read_reg(struct adis *adis, unsigned int reg,
 		dev_err(&adis->spi->dev, "Failed to read register 0x%02X: %d\n",
 				reg, ret);
 		goto out_unlock;
+	} else {
+		adis->current_page = page;
 	}
 
 	switch (size) {
@@ -390,6 +420,14 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev,
 	adis->data = data;
 	iio_device_set_drvdata(indio_dev, adis);
 
+	if (data->has_paging) {
+		/* Need to set the page before first read/write */
+		adis->current_page = -1;
+	} else {
+		/* Page will always be 0 */
+		adis->current_page = 0;
+	}
+
 	return adis_enable_irq(adis, false);
 }
 EXPORT_SYMBOL_GPL(adis_init);
diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
index 785713349e9f..99d8e0b0dd34 100644
--- a/drivers/iio/imu/adis_buffer.c
+++ b/drivers/iio/imu/adis_buffer.c
@@ -83,10 +83,25 @@ static irqreturn_t adis_trigger_handler(int irq, void *p)
 	if (!adis->buffer)
 		return -ENOMEM;
 
+	if (adis->data->has_paging) {
+		mutex_lock(&adis->txrx_lock);
+		if (adis->current_page != 0) {
+			adis->tx[0] = ADIS_WRITE_REG(ADIS_REG_PAGE_ID);
+			adis->tx[1] = 0;
+			spi_write(adis->spi, adis->tx, 2);
+		}
+	}
+
 	ret = spi_sync(adis->spi, &adis->msg);
 	if (ret)
 		dev_err(&adis->spi->dev, "Failed to read data: %d", ret);
 
+
+	if (adis->data->has_paging) {
+		adis->current_page = 0;
+		mutex_unlock(&adis->txrx_lock);
+	}
+
 	/* Guaranteed to be aligned with 8 byte boundary */
 	if (indio_dev->scan_timestamp) {
 		void *b = adis->buffer + indio_dev->scan_bytes - sizeof(s64);
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index 6402a08c0e65..e82cd0827e91 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -14,8 +14,11 @@
 #include <linux/interrupt.h>
 #include <linux/iio/types.h>
 
-#define ADIS_WRITE_REG(reg) (0x80 | (reg))
-#define ADIS_READ_REG(reg) (reg)
+#define ADIS_WRITE_REG(reg) ((0x80 | (reg)))
+#define ADIS_READ_REG(reg) ((reg) & 0x7f)
+
+#define ADIS_PAGE_SIZE 0x80
+#define ADIS_REG_PAGE_ID 0x00
 
 /**
  * struct adis_data - ADIS chip variant specific data
@@ -40,6 +43,8 @@ struct adis_data {
 
 	const char * const *status_error_msgs;
 	unsigned int status_error_mask;
+
+	bool has_paging;
 };
 
 struct adis {
@@ -51,6 +56,7 @@ struct adis {
 	struct mutex		txrx_lock;
 	struct spi_message	msg;
 	struct spi_transfer	*xfer;
+	unsigned int		current_page;
 	void			*buffer;
 
 	uint8_t			tx[10] ____cacheline_aligned;
-- 
cgit v1.2.3-55-g7522


From c4f0c6936762ecd6b453275611a785dfdee0d417 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Tue, 20 Nov 2012 13:36:00 +0000
Subject: iio: Add pressure channel type

This patch adds support for a new IIO channel type for pressure measurements.
This can for example be used for barometric pressure sensors.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 Documentation/ABI/testing/sysfs-bus-iio | 24 ++++++++++++++++++++++++
 drivers/iio/industrialio-core.c         |  1 +
 include/linux/iio/types.h               |  1 +
 3 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 2f06d40fe07d..2e33dc6b2346 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -189,6 +189,14 @@ Description:
 		A computed peak value based on the sum squared magnitude of
 		the underlying value in the specified directions.
 
+What:		/sys/bus/iio/devices/iio:deviceX/in_pressureY_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_pressure_raw
+KernelVersion:	3.8
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Raw pressure measurement from channel Y. Units after
+		application of scale and offset are kilopascal.
+
 What:		/sys/bus/iio/devices/iio:deviceX/in_accel_offset
 What:		/sys/bus/iio/devices/iio:deviceX/in_accel_x_offset
 What:		/sys/bus/iio/devices/iio:deviceX/in_accel_y_offset
@@ -197,6 +205,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_voltageY_offset
 What:		/sys/bus/iio/devices/iio:deviceX/in_voltage_offset
 What:		/sys/bus/iio/devices/iio:deviceX/in_tempY_offset
 What:		/sys/bus/iio/devices/iio:deviceX/in_temp_offset
+What:		/sys/bus/iio/devices/iio:deviceX/in_pressureY_offset
+What:		/sys/bus/iio/devices/iio:deviceX/in_pressure_offset
 KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -226,6 +236,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_magn_scale
 What:		/sys/bus/iio/devices/iio:deviceX/in_magn_x_scale
 What:		/sys/bus/iio/devices/iio:deviceX/in_magn_y_scale
 What:		/sys/bus/iio/devices/iio:deviceX/in_magn_z_scale
+What:		/sys/bus/iio/devices/iio:deviceX/in_pressureY_scale
+What:		/sys/bus/iio/devices/iio:deviceX/in_pressure_scale
 KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -245,6 +257,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_anglvel_y_calibbias
 What:		/sys/bus/iio/devices/iio:deviceX/in_anglvel_z_calibbias
 What:		/sys/bus/iio/devices/iio:deviceX/in_illuminance0_calibbias
 What:		/sys/bus/iio/devices/iio:deviceX/in_proximity0_calibbias
+What:		/sys/bus/iio/devices/iio:deviceX/in_pressureY_calibbias
+What:		/sys/bus/iio/devices/iio:deviceX/in_pressure_calibbias
 KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -262,6 +276,8 @@ What		/sys/bus/iio/devices/iio:deviceX/in_anglvel_y_calibscale
 What		/sys/bus/iio/devices/iio:deviceX/in_anglvel_z_calibscale
 what		/sys/bus/iio/devices/iio:deviceX/in_illuminance0_calibscale
 what		/sys/bus/iio/devices/iio:deviceX/in_proximity0_calibscale
+What:		/sys/bus/iio/devices/iio:deviceX/in_pressureY_calibscale
+What:		/sys/bus/iio/devices/iio:deviceX/in_pressure_calibscale
 KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -275,6 +291,8 @@ What:		/sys/.../iio:deviceX/in_voltage-voltage_scale_available
 What:		/sys/.../iio:deviceX/out_voltageX_scale_available
 What:		/sys/.../iio:deviceX/out_altvoltageX_scale_available
 What:		/sys/.../iio:deviceX/in_capacitance_scale_available
+What:		/sys/.../iio:deviceX/in_pressure_scale_available
+What:		/sys/.../iio:deviceX/in_pressureY_scale_available
 KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -694,6 +712,8 @@ What:		/sys/.../buffer/scan_elements/in_voltageY_en
 What:		/sys/.../buffer/scan_elements/in_voltageY-voltageZ_en
 What:		/sys/.../buffer/scan_elements/in_incli_x_en
 What:		/sys/.../buffer/scan_elements/in_incli_y_en
+What:		/sys/.../buffer/scan_elements/in_pressureY_en
+What:		/sys/.../buffer/scan_elements/in_pressure_en
 KernelVersion:	2.6.37
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -707,6 +727,8 @@ What:		/sys/.../buffer/scan_elements/in_voltageY_type
 What:		/sys/.../buffer/scan_elements/in_voltage_type
 What:		/sys/.../buffer/scan_elements/in_voltageY_supply_type
 What:		/sys/.../buffer/scan_elements/in_timestamp_type
+What:		/sys/.../buffer/scan_elements/in_pressureY_type
+What:		/sys/.../buffer/scan_elements/in_pressure_type
 KernelVersion:	2.6.37
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -751,6 +773,8 @@ What:		/sys/.../buffer/scan_elements/in_magn_z_index
 What:		/sys/.../buffer/scan_elements/in_incli_x_index
 What:		/sys/.../buffer/scan_elements/in_incli_y_index
 What:		/sys/.../buffer/scan_elements/in_timestamp_index
+What:		/sys/.../buffer/scan_elements/in_pressureY_index
+What:		/sys/.../buffer/scan_elements/in_pressure_index
 KernelVersion:	2.6.37
 Contact:	linux-iio@vger.kernel.org
 Description:
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 060a4045be85..3dccd6c3a889 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -65,6 +65,7 @@ static const char * const iio_chan_type_name_spec[] = {
 	[IIO_CAPACITANCE] = "capacitance",
 	[IIO_ALTVOLTAGE] = "altvoltage",
 	[IIO_CCT] = "cct",
+	[IIO_PRESSURE] = "pressure",
 };
 
 static const char * const iio_modifier_names[] = {
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index 87b196a2d698..88bf0f0d27b4 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -28,6 +28,7 @@ enum iio_chan_type {
 	IIO_CAPACITANCE,
 	IIO_ALTVOLTAGE,
 	IIO_CCT,
+	IIO_PRESSURE,
 };
 
 enum iio_modifier {
-- 
cgit v1.2.3-55-g7522


From 6807d7211327dbdd8df3692f3d26ca711514ba71 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Tue, 20 Nov 2012 13:36:00 +0000
Subject: iio: Factor out fixed point number parsing into its own function

Factor out the code for parsing fixed point numbers into its own function and
make this function globally available. This allows us to reuse the code to parse
fixed point numbers in individual IIO drivers.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/industrialio-core.c | 98 ++++++++++++++++++++++++++---------------
 include/linux/iio/iio.h         |  3 ++
 2 files changed, 66 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 3dccd6c3a889..8848f16c547b 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -408,6 +408,64 @@ static ssize_t iio_read_channel_info(struct device *dev,
 	}
 }
 
+/**
+ * iio_str_to_fixpoint() - Parse a fixed-point number from a string
+ * @str: The string to parse
+ * @fract_mult: Multiplier for the first decimal place, should be a power of 10
+ * @integer: The integer part of the number
+ * @fract: The fractional part of the number
+ *
+ * Returns 0 on success, or a negative error code if the string could not be
+ * parsed.
+ */
+int iio_str_to_fixpoint(const char *str, int fract_mult,
+	int *integer, int *fract)
+{
+	int i = 0, f = 0;
+	bool integer_part = true, negative = false;
+
+	if (str[0] == '-') {
+		negative = true;
+		str++;
+	} else if (str[0] == '+') {
+		str++;
+	}
+
+	while (*str) {
+		if ('0' <= *str && *str <= '9') {
+			if (integer_part) {
+				i = i * 10 + *str - '0';
+			} else {
+				f += fract_mult * (*str - '0');
+				fract_mult /= 10;
+			}
+		} else if (*str == '\n') {
+			if (*(str + 1) == '\0')
+				break;
+			else
+				return -EINVAL;
+		} else if (*str == '.' && integer_part) {
+			integer_part = false;
+		} else {
+			return -EINVAL;
+		}
+		str++;
+	}
+
+	if (negative) {
+		if (i)
+			i = -i;
+		else
+			f = -f;
+	}
+
+	*integer = i;
+	*fract = f;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iio_str_to_fixpoint);
+
 static ssize_t iio_write_channel_info(struct device *dev,
 				      struct device_attribute *attr,
 				      const char *buf,
@@ -415,8 +473,8 @@ static ssize_t iio_write_channel_info(struct device *dev,
 {
 	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
 	struct iio_dev_attr *this_attr = to_iio_dev_attr(attr);
-	int ret, integer = 0, fract = 0, fract_mult = 100000;
-	bool integer_part = true, negative = false;
+	int ret, fract_mult = 100000;
+	int integer, fract;
 
 	/* Assumes decimal - precision based on number of digits */
 	if (!indio_dev->info->write_raw)
@@ -435,39 +493,9 @@ static ssize_t iio_write_channel_info(struct device *dev,
 			return -EINVAL;
 		}
 
-	if (buf[0] == '-') {
-		negative = true;
-		buf++;
-	} else if (buf[0] == '+') {
-		buf++;
-	}
-
-	while (*buf) {
-		if ('0' <= *buf && *buf <= '9') {
-			if (integer_part)
-				integer = integer*10 + *buf - '0';
-			else {
-				fract += fract_mult*(*buf - '0');
-				fract_mult /= 10;
-			}
-		} else if (*buf == '\n') {
-			if (*(buf + 1) == '\0')
-				break;
-			else
-				return -EINVAL;
-		} else if (*buf == '.' && integer_part) {
-			integer_part = false;
-		} else {
-			return -EINVAL;
-		}
-		buf++;
-	}
-	if (negative) {
-		if (integer)
-			integer = -integer;
-		else
-			fract = -fract;
-	}
+	ret = iio_str_to_fixpoint(buf, fract_mult, &integer, &fract);
+	if (ret)
+		return ret;
 
 	ret = indio_dev->info->write_raw(indio_dev, this_attr->c,
 					 integer, fract, this_attr->address);
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index adca93a999a7..da8c776ba0bd 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -620,6 +620,9 @@ static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev)
 };
 #endif
 
+int iio_str_to_fixpoint(const char *str, int fract_mult, int *integer,
+	int *fract);
+
 /**
  * IIO_DEGREE_TO_RAD() - Convert degree to rad
  * @deg: A value in degree
-- 
cgit v1.2.3-55-g7522


From 2f3abe6cbb6c963ac790b40936b6761c9f0497b4 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Tue, 20 Nov 2012 13:36:00 +0000
Subject: iio:imu: Add support for the ADIS16480 and similar IMUs

This patch adds support for the ADIS16375, ADIS16480, ADIS16485, ADIS16488 6
degree to 10 degree of freedom IMUs.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/imu/Kconfig      |  16 +
 drivers/iio/imu/Makefile     |   2 +
 drivers/iio/imu/adis.c       |   3 +
 drivers/iio/imu/adis16480.c  | 925 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/iio/imu/adis.h |   4 +
 5 files changed, 950 insertions(+)
 create mode 100644 drivers/iio/imu/adis16480.c

(limited to 'include')

diff --git a/drivers/iio/imu/Kconfig b/drivers/iio/imu/Kconfig
index c24410c873c7..3d79a40e916b 100644
--- a/drivers/iio/imu/Kconfig
+++ b/drivers/iio/imu/Kconfig
@@ -1,3 +1,19 @@
+#
+# IIO imu drivers configuration
+#
+menu "Inertial measurement units"
+
+config ADIS16480
+	tristate "Analog Devices ADIS16480 and similar IMU driver"
+	depends on SPI
+	select IIO_ADIS_LIB
+	select IIO_ADIS_LIB_BUFFER if IIO_BUFFER
+	help
+	  Say yes here to build support for Analog Devices ADIS16375, ADIS16480,
+	  ADIS16485, ADIS16488 inertial sensors.
+
+endmenu
+
 config IIO_ADIS_LIB
 	tristate
 	help
diff --git a/drivers/iio/imu/Makefile b/drivers/iio/imu/Makefile
index 97676ab5723d..cfe57638f6f9 100644
--- a/drivers/iio/imu/Makefile
+++ b/drivers/iio/imu/Makefile
@@ -2,6 +2,8 @@
 # Makefile for Inertial Measurement Units
 #
 
+obj-$(CONFIG_ADIS16480) += adis16480.o
+
 adis_lib-y += adis.o
 adis_lib-$(CONFIG_IIO_ADIS_LIB_BUFFER) += adis_trigger.o
 adis_lib-$(CONFIG_IIO_ADIS_LIB_BUFFER) += adis_buffer.o
diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c
index c4ea04ffa60e..911255d41c1a 100644
--- a/drivers/iio/imu/adis.c
+++ b/drivers/iio/imu/adis.c
@@ -238,6 +238,9 @@ int adis_enable_irq(struct adis *adis, bool enable)
 	int ret = 0;
 	uint16_t msc;
 
+	if (adis->data->enable_irq)
+		return adis->data->enable_irq(adis, enable);
+
 	ret = adis_read_reg_16(adis, adis->data->msc_ctrl_reg, &msc);
 	if (ret)
 		goto error_ret;
diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c
new file mode 100644
index 000000000000..a080b3515015
--- /dev/null
+++ b/drivers/iio/imu/adis16480.c
@@ -0,0 +1,925 @@
+/*
+ * ADIS16480 and similar IMUs driver
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/mutex.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/spi/spi.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/module.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/imu/adis.h>
+
+#include <linux/iio/iio.h>
+#include <linux/debugfs.h>
+
+#define ADIS16480_PAGE_SIZE 0x80
+
+#define ADIS16480_REG(page, reg) ((page) * ADIS16480_PAGE_SIZE + (reg))
+
+#define ADIS16480_REG_PAGE_ID 0x00 /* Same address on each page */
+#define ADIS16480_REG_SEQ_CNT			ADIS16480_REG(0x00, 0x06)
+#define ADIS16480_REG_SYS_E_FLA			ADIS16480_REG(0x00, 0x08)
+#define ADIS16480_REG_DIAG_STS			ADIS16480_REG(0x00, 0x0A)
+#define ADIS16480_REG_ALM_STS			ADIS16480_REG(0x00, 0x0C)
+#define ADIS16480_REG_TEMP_OUT			ADIS16480_REG(0x00, 0x0E)
+#define ADIS16480_REG_X_GYRO_OUT		ADIS16480_REG(0x00, 0x10)
+#define ADIS16480_REG_Y_GYRO_OUT		ADIS16480_REG(0x00, 0x14)
+#define ADIS16480_REG_Z_GYRO_OUT		ADIS16480_REG(0x00, 0x18)
+#define ADIS16480_REG_X_ACCEL_OUT		ADIS16480_REG(0x00, 0x1C)
+#define ADIS16480_REG_Y_ACCEL_OUT		ADIS16480_REG(0x00, 0x20)
+#define ADIS16480_REG_Z_ACCEL_OUT		ADIS16480_REG(0x00, 0x24)
+#define ADIS16480_REG_X_MAGN_OUT		ADIS16480_REG(0x00, 0x28)
+#define ADIS16480_REG_Y_MAGN_OUT		ADIS16480_REG(0x00, 0x2A)
+#define ADIS16480_REG_Z_MAGN_OUT		ADIS16480_REG(0x00, 0x2C)
+#define ADIS16480_REG_BAROM_OUT			ADIS16480_REG(0x00, 0x2E)
+#define ADIS16480_REG_X_DELTAANG_OUT		ADIS16480_REG(0x00, 0x40)
+#define ADIS16480_REG_Y_DELTAANG_OUT		ADIS16480_REG(0x00, 0x44)
+#define ADIS16480_REG_Z_DELTAANG_OUT		ADIS16480_REG(0x00, 0x48)
+#define ADIS16480_REG_X_DELTAVEL_OUT		ADIS16480_REG(0x00, 0x4C)
+#define ADIS16480_REG_Y_DELTAVEL_OUT		ADIS16480_REG(0x00, 0x50)
+#define ADIS16480_REG_Z_DELTAVEL_OUT		ADIS16480_REG(0x00, 0x54)
+#define ADIS16480_REG_PROD_ID			ADIS16480_REG(0x00, 0x7E)
+
+#define ADIS16480_REG_X_GYRO_SCALE		ADIS16480_REG(0x02, 0x04)
+#define ADIS16480_REG_Y_GYRO_SCALE		ADIS16480_REG(0x02, 0x06)
+#define ADIS16480_REG_Z_GYRO_SCALE		ADIS16480_REG(0x02, 0x08)
+#define ADIS16480_REG_X_ACCEL_SCALE		ADIS16480_REG(0x02, 0x0A)
+#define ADIS16480_REG_Y_ACCEL_SCALE		ADIS16480_REG(0x02, 0x0C)
+#define ADIS16480_REG_Z_ACCEL_SCALE		ADIS16480_REG(0x02, 0x0E)
+#define ADIS16480_REG_X_GYRO_BIAS		ADIS16480_REG(0x02, 0x10)
+#define ADIS16480_REG_Y_GYRO_BIAS		ADIS16480_REG(0x02, 0x14)
+#define ADIS16480_REG_Z_GYRO_BIAS		ADIS16480_REG(0x02, 0x18)
+#define ADIS16480_REG_X_ACCEL_BIAS		ADIS16480_REG(0x02, 0x1C)
+#define ADIS16480_REG_Y_ACCEL_BIAS		ADIS16480_REG(0x02, 0x20)
+#define ADIS16480_REG_Z_ACCEL_BIAS		ADIS16480_REG(0x02, 0x24)
+#define ADIS16480_REG_X_HARD_IRON		ADIS16480_REG(0x02, 0x28)
+#define ADIS16480_REG_Y_HARD_IRON		ADIS16480_REG(0x02, 0x2A)
+#define ADIS16480_REG_Z_HARD_IRON		ADIS16480_REG(0x02, 0x2C)
+#define ADIS16480_REG_BAROM_BIAS		ADIS16480_REG(0x02, 0x40)
+#define ADIS16480_REG_FLASH_CNT			ADIS16480_REG(0x02, 0x7C)
+
+#define ADIS16480_REG_GLOB_CMD			ADIS16480_REG(0x03, 0x02)
+#define ADIS16480_REG_FNCTIO_CTRL		ADIS16480_REG(0x03, 0x06)
+#define ADIS16480_REG_GPIO_CTRL			ADIS16480_REG(0x03, 0x08)
+#define ADIS16480_REG_CONFIG			ADIS16480_REG(0x03, 0x0A)
+#define ADIS16480_REG_DEC_RATE			ADIS16480_REG(0x03, 0x0C)
+#define ADIS16480_REG_SLP_CNT			ADIS16480_REG(0x03, 0x10)
+#define ADIS16480_REG_FILTER_BNK0		ADIS16480_REG(0x03, 0x16)
+#define ADIS16480_REG_FILTER_BNK1		ADIS16480_REG(0x03, 0x18)
+#define ADIS16480_REG_ALM_CNFG0			ADIS16480_REG(0x03, 0x20)
+#define ADIS16480_REG_ALM_CNFG1			ADIS16480_REG(0x03, 0x22)
+#define ADIS16480_REG_ALM_CNFG2			ADIS16480_REG(0x03, 0x24)
+#define ADIS16480_REG_XG_ALM_MAGN		ADIS16480_REG(0x03, 0x28)
+#define ADIS16480_REG_YG_ALM_MAGN		ADIS16480_REG(0x03, 0x2A)
+#define ADIS16480_REG_ZG_ALM_MAGN		ADIS16480_REG(0x03, 0x2C)
+#define ADIS16480_REG_XA_ALM_MAGN		ADIS16480_REG(0x03, 0x2E)
+#define ADIS16480_REG_YA_ALM_MAGN		ADIS16480_REG(0x03, 0x30)
+#define ADIS16480_REG_ZA_ALM_MAGN		ADIS16480_REG(0x03, 0x32)
+#define ADIS16480_REG_XM_ALM_MAGN		ADIS16480_REG(0x03, 0x34)
+#define ADIS16480_REG_YM_ALM_MAGN		ADIS16480_REG(0x03, 0x36)
+#define ADIS16480_REG_ZM_ALM_MAGN		ADIS16480_REG(0x03, 0x38)
+#define ADIS16480_REG_BR_ALM_MAGN		ADIS16480_REG(0x03, 0x3A)
+#define ADIS16480_REG_FIRM_REV			ADIS16480_REG(0x03, 0x78)
+#define ADIS16480_REG_FIRM_DM			ADIS16480_REG(0x03, 0x7A)
+#define ADIS16480_REG_FIRM_Y			ADIS16480_REG(0x03, 0x7C)
+
+#define ADIS16480_REG_SERIAL_NUM		ADIS16480_REG(0x04, 0x20)
+
+/* Each filter coefficent bank spans two pages */
+#define ADIS16480_FIR_COEF(page) (x < 60 ? ADIS16480_REG(page, (x) + 8) : \
+		ADIS16480_REG((page) + 1, (x) - 60 + 8))
+#define ADIS16480_FIR_COEF_A(x)			ADIS16480_FIR_COEF(0x05, (x))
+#define ADIS16480_FIR_COEF_B(x)			ADIS16480_FIR_COEF(0x07, (x))
+#define ADIS16480_FIR_COEF_C(x)			ADIS16480_FIR_COEF(0x09, (x))
+#define ADIS16480_FIR_COEF_D(x)			ADIS16480_FIR_COEF(0x0B, (x))
+
+struct adis16480_chip_info {
+	unsigned int num_channels;
+	const struct iio_chan_spec *channels;
+};
+
+struct adis16480 {
+	const struct adis16480_chip_info *chip_info;
+
+	struct adis adis;
+};
+
+#ifdef CONFIG_DEBUG_FS
+
+static ssize_t adis16480_show_firmware_revision(struct file *file,
+		char __user *userbuf, size_t count, loff_t *ppos)
+{
+	struct adis16480 *adis16480 = file->private_data;
+	char buf[6];
+	size_t len;
+	u16 rev;
+	int ret;
+
+	ret = adis_read_reg_16(&adis16480->adis, ADIS16480_REG_FIRM_REV, &rev);
+	if (ret < 0)
+		return ret;
+
+	len = snprintf(buf, sizeof(buf), "%x.%x\n", rev >> 8, rev & 0xff);
+
+	return simple_read_from_buffer(userbuf, count, ppos, buf, len);
+}
+
+static const struct file_operations adis16480_firmware_revision_fops = {
+	.open = simple_open,
+	.read = adis16480_show_firmware_revision,
+	.llseek = default_llseek,
+	.owner = THIS_MODULE,
+};
+
+static ssize_t adis16480_show_firmware_date(struct file *file,
+		char __user *userbuf, size_t count, loff_t *ppos)
+{
+	struct adis16480 *adis16480 = file->private_data;
+	u16 md, year;
+	char buf[12];
+	size_t len;
+	int ret;
+
+	ret = adis_read_reg_16(&adis16480->adis, ADIS16480_REG_FIRM_Y, &year);
+	if (ret < 0)
+		return ret;
+
+	ret = adis_read_reg_16(&adis16480->adis, ADIS16480_REG_FIRM_DM, &md);
+	if (ret < 0)
+		return ret;
+
+	len = snprintf(buf, sizeof(buf), "%.2x-%.2x-%.4x\n",
+			md >> 8, md & 0xff, year);
+
+	return simple_read_from_buffer(userbuf, count, ppos, buf, len);
+}
+
+static const struct file_operations adis16480_firmware_date_fops = {
+	.open = simple_open,
+	.read = adis16480_show_firmware_date,
+	.llseek = default_llseek,
+	.owner = THIS_MODULE,
+};
+
+static int adis16480_show_serial_number(void *arg, u64 *val)
+{
+	struct adis16480 *adis16480 = arg;
+	u16 serial;
+	int ret;
+
+	ret = adis_read_reg_16(&adis16480->adis, ADIS16480_REG_SERIAL_NUM,
+		&serial);
+	if (ret < 0)
+		return ret;
+
+	*val = serial;
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(adis16480_serial_number_fops,
+	adis16480_show_serial_number, NULL, "0x%.4llx\n");
+
+static int adis16480_show_product_id(void *arg, u64 *val)
+{
+	struct adis16480 *adis16480 = arg;
+	u16 prod_id;
+	int ret;
+
+	ret = adis_read_reg_16(&adis16480->adis, ADIS16480_REG_PROD_ID,
+		&prod_id);
+	if (ret < 0)
+		return ret;
+
+	*val = prod_id;
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(adis16480_product_id_fops,
+	adis16480_show_product_id, NULL, "%llu\n");
+
+static int adis16480_show_flash_count(void *arg, u64 *val)
+{
+	struct adis16480 *adis16480 = arg;
+	u32 flash_count;
+	int ret;
+
+	ret = adis_read_reg_32(&adis16480->adis, ADIS16480_REG_FLASH_CNT,
+		&flash_count);
+	if (ret < 0)
+		return ret;
+
+	*val = flash_count;
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(adis16480_flash_count_fops,
+	adis16480_show_flash_count, NULL, "%lld\n");
+
+static int adis16480_debugfs_init(struct iio_dev *indio_dev)
+{
+	struct adis16480 *adis16480 = iio_priv(indio_dev);
+
+	debugfs_create_file("firmware_revision", 0400,
+		indio_dev->debugfs_dentry, adis16480,
+		&adis16480_firmware_revision_fops);
+	debugfs_create_file("firmware_date", 0400, indio_dev->debugfs_dentry,
+		adis16480, &adis16480_firmware_date_fops);
+	debugfs_create_file("serial_number", 0400, indio_dev->debugfs_dentry,
+		adis16480, &adis16480_serial_number_fops);
+	debugfs_create_file("product_id", 0400, indio_dev->debugfs_dentry,
+		adis16480, &adis16480_product_id_fops);
+	debugfs_create_file("flash_count", 0400, indio_dev->debugfs_dentry,
+		adis16480, &adis16480_flash_count_fops);
+
+	return 0;
+}
+
+#else
+
+static int adis16480_debugfs_init(struct iio_dev *indio_dev)
+{
+	return 0;
+}
+
+#endif
+
+static int adis16480_set_freq(struct adis16480 *st, unsigned int freq)
+{
+	unsigned int t;
+
+	t = 2460000 / freq;
+	if (t > 2048)
+		t = 2048;
+
+	if (t != 0)
+		t--;
+
+	return adis_write_reg_16(&st->adis, ADIS16480_REG_DEC_RATE, t);
+}
+
+static int adis16480_get_freq(struct adis16480 *st, unsigned int *freq)
+{
+	uint16_t t;
+	int ret;
+
+	ret = adis_read_reg_16(&st->adis, ADIS16480_REG_DEC_RATE, &t);
+	if (ret < 0)
+		return ret;
+
+	*freq = 2460000 / (t + 1);
+
+	return 0;
+}
+
+static ssize_t adis16480_read_frequency(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct adis16480 *st = iio_priv(indio_dev);
+	unsigned int freq;
+	int ret;
+
+	ret = adis16480_get_freq(st, &freq);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d.%.3d\n", freq / 1000, freq % 1000);
+}
+
+static ssize_t adis16480_write_frequency(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t len)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct adis16480 *st = iio_priv(indio_dev);
+	int freq_int, freq_fract;
+	long val;
+	int ret;
+
+	ret = iio_str_to_fixpoint(buf, 100, &freq_int, &freq_fract);
+	if (ret)
+		return ret;
+
+	val = freq_int * 1000 + freq_fract;
+
+	if (val <= 0)
+		return -EINVAL;
+
+	ret = adis16480_set_freq(st, val);
+
+	return ret ? ret : len;
+}
+
+static IIO_DEV_ATTR_SAMP_FREQ(S_IWUSR | S_IRUGO,
+			      adis16480_read_frequency,
+			      adis16480_write_frequency);
+
+enum {
+	ADIS16480_SCAN_GYRO_X,
+	ADIS16480_SCAN_GYRO_Y,
+	ADIS16480_SCAN_GYRO_Z,
+	ADIS16480_SCAN_ACCEL_X,
+	ADIS16480_SCAN_ACCEL_Y,
+	ADIS16480_SCAN_ACCEL_Z,
+	ADIS16480_SCAN_MAGN_X,
+	ADIS16480_SCAN_MAGN_Y,
+	ADIS16480_SCAN_MAGN_Z,
+	ADIS16480_SCAN_BARO,
+	ADIS16480_SCAN_TEMP,
+};
+
+static const unsigned int adis16480_calibbias_regs[] = {
+	[ADIS16480_SCAN_GYRO_X] = ADIS16480_REG_X_GYRO_BIAS,
+	[ADIS16480_SCAN_GYRO_Y] = ADIS16480_REG_Y_GYRO_BIAS,
+	[ADIS16480_SCAN_GYRO_Z] = ADIS16480_REG_Z_GYRO_BIAS,
+	[ADIS16480_SCAN_ACCEL_X] = ADIS16480_REG_X_ACCEL_BIAS,
+	[ADIS16480_SCAN_ACCEL_Y] = ADIS16480_REG_Y_ACCEL_BIAS,
+	[ADIS16480_SCAN_ACCEL_Z] = ADIS16480_REG_Z_ACCEL_BIAS,
+	[ADIS16480_SCAN_MAGN_X] = ADIS16480_REG_X_HARD_IRON,
+	[ADIS16480_SCAN_MAGN_Y] = ADIS16480_REG_Y_HARD_IRON,
+	[ADIS16480_SCAN_MAGN_Z] = ADIS16480_REG_Z_HARD_IRON,
+	[ADIS16480_SCAN_BARO] = ADIS16480_REG_BAROM_BIAS,
+};
+
+static const unsigned int adis16480_calibscale_regs[] = {
+	[ADIS16480_SCAN_GYRO_X] = ADIS16480_REG_X_GYRO_SCALE,
+	[ADIS16480_SCAN_GYRO_Y] = ADIS16480_REG_Y_GYRO_SCALE,
+	[ADIS16480_SCAN_GYRO_Z] = ADIS16480_REG_Z_GYRO_SCALE,
+	[ADIS16480_SCAN_ACCEL_X] = ADIS16480_REG_X_ACCEL_SCALE,
+	[ADIS16480_SCAN_ACCEL_Y] = ADIS16480_REG_Y_ACCEL_SCALE,
+	[ADIS16480_SCAN_ACCEL_Z] = ADIS16480_REG_Z_ACCEL_SCALE,
+};
+
+static int adis16480_set_calibbias(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, int bias)
+{
+	unsigned int reg = adis16480_calibbias_regs[chan->scan_index];
+	struct adis16480 *st = iio_priv(indio_dev);
+
+	switch (chan->type) {
+	case IIO_MAGN:
+	case IIO_PRESSURE:
+		if (bias < -0x8000 || bias >= 0x8000)
+			return -EINVAL;
+		return adis_write_reg_16(&st->adis, reg, bias);
+	case IIO_ANGL_VEL:
+	case IIO_ACCEL:
+		return adis_write_reg_32(&st->adis, reg, bias);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static int adis16480_get_calibbias(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, int *bias)
+{
+	unsigned int reg = adis16480_calibbias_regs[chan->scan_index];
+	struct adis16480 *st = iio_priv(indio_dev);
+	uint16_t val16;
+	uint32_t val32;
+	int ret;
+
+	switch (chan->type) {
+	case IIO_MAGN:
+	case IIO_PRESSURE:
+		ret = adis_read_reg_16(&st->adis, reg, &val16);
+		*bias = sign_extend32(val16, 15);
+		break;
+	case IIO_ANGL_VEL:
+	case IIO_ACCEL:
+		ret = adis_read_reg_32(&st->adis, reg, &val32);
+		*bias = sign_extend32(val32, 31);
+		break;
+	default:
+			ret = -EINVAL;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	return IIO_VAL_INT;
+}
+
+static int adis16480_set_calibscale(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, int scale)
+{
+	unsigned int reg = adis16480_calibscale_regs[chan->scan_index];
+	struct adis16480 *st = iio_priv(indio_dev);
+
+	if (scale < -0x8000 || scale >= 0x8000)
+		return -EINVAL;
+
+	return adis_write_reg_16(&st->adis, reg, scale);
+}
+
+static int adis16480_get_calibscale(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, int *scale)
+{
+	unsigned int reg = adis16480_calibscale_regs[chan->scan_index];
+	struct adis16480 *st = iio_priv(indio_dev);
+	uint16_t val16;
+	int ret;
+
+	ret = adis_read_reg_16(&st->adis, reg, &val16);
+	if (ret < 0)
+		return ret;
+
+	*scale = sign_extend32(val16, 15);
+	return IIO_VAL_INT;
+}
+
+static const unsigned int adis16480_def_filter_freqs[] = {
+	310,
+	55,
+	275,
+	63,
+};
+
+static const unsigned int ad16480_filter_data[][2] = {
+	[ADIS16480_SCAN_GYRO_X]		= { ADIS16480_REG_FILTER_BNK0, 0 },
+	[ADIS16480_SCAN_GYRO_Y]		= { ADIS16480_REG_FILTER_BNK0, 3 },
+	[ADIS16480_SCAN_GYRO_Z]		= { ADIS16480_REG_FILTER_BNK0, 6 },
+	[ADIS16480_SCAN_ACCEL_X]	= { ADIS16480_REG_FILTER_BNK0, 9 },
+	[ADIS16480_SCAN_ACCEL_Y]	= { ADIS16480_REG_FILTER_BNK0, 12 },
+	[ADIS16480_SCAN_ACCEL_Z]	= { ADIS16480_REG_FILTER_BNK1, 0 },
+	[ADIS16480_SCAN_MAGN_X]		= { ADIS16480_REG_FILTER_BNK1, 3 },
+	[ADIS16480_SCAN_MAGN_Y]		= { ADIS16480_REG_FILTER_BNK1, 6 },
+	[ADIS16480_SCAN_MAGN_Z]		= { ADIS16480_REG_FILTER_BNK1, 9 },
+};
+
+static int adis16480_get_filter_freq(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, int *freq)
+{
+	struct adis16480 *st = iio_priv(indio_dev);
+	unsigned int enable_mask, offset, reg;
+	uint16_t val;
+	int ret;
+
+	reg = ad16480_filter_data[chan->scan_index][0];
+	offset = ad16480_filter_data[chan->scan_index][1];
+	enable_mask = BIT(offset + 2);
+
+	ret = adis_read_reg_16(&st->adis, reg, &val);
+	if (ret < 0)
+		return ret;
+
+	if (!(val & enable_mask))
+		*freq = 0;
+	else
+		*freq = adis16480_def_filter_freqs[(val >> offset) & 0x3];
+
+	return IIO_VAL_INT;
+}
+
+static int adis16480_set_filter_freq(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, unsigned int freq)
+{
+	struct adis16480 *st = iio_priv(indio_dev);
+	unsigned int enable_mask, offset, reg;
+	unsigned int diff, best_diff;
+	unsigned int i, best_freq;
+	uint16_t val;
+	int ret;
+
+	reg = ad16480_filter_data[chan->scan_index][0];
+	offset = ad16480_filter_data[chan->scan_index][1];
+	enable_mask = BIT(offset + 2);
+
+	ret = adis_read_reg_16(&st->adis, reg, &val);
+	if (ret < 0)
+		return ret;
+
+	if (freq == 0) {
+		val &= ~enable_mask;
+	} else {
+		best_freq = 0;
+		best_diff = 310;
+		for (i = 0; i < ARRAY_SIZE(adis16480_def_filter_freqs); i++) {
+			if (adis16480_def_filter_freqs[i] >= freq) {
+				diff = adis16480_def_filter_freqs[i] - freq;
+				if (diff < best_diff) {
+					best_diff = diff;
+					best_freq = i;
+				}
+			}
+		}
+
+		val &= ~(0x3 << offset);
+		val |= best_freq << offset;
+		val |= enable_mask;
+	}
+
+	return adis_write_reg_16(&st->adis, reg, val);
+}
+
+static int adis16480_read_raw(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, int *val, int *val2, long info)
+{
+	switch (info) {
+	case IIO_CHAN_INFO_RAW:
+		return adis_single_conversion(indio_dev, chan, 0, val);
+	case IIO_CHAN_INFO_SCALE:
+		switch (chan->type) {
+		case IIO_ANGL_VEL:
+			*val = 0;
+			*val2 = IIO_DEGREE_TO_RAD(20000); /* 0.02 degree/sec */
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_ACCEL:
+			*val = 0;
+			*val2 = IIO_G_TO_M_S_2(800); /* 0.8 mg */
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_MAGN:
+			*val = 0;
+			*val2 = 100; /* 0.0001 gauss */
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_TEMP:
+			*val = 5;
+			*val2 = 650000; /* 5.65 milli degree Celsius */
+			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_PRESSURE:
+			*val = 0;
+			*val2 = 4000; /* 40ubar = 0.004 kPa */
+			return IIO_VAL_INT_PLUS_MICRO;
+		default:
+			return -EINVAL;
+		}
+	case IIO_CHAN_INFO_OFFSET:
+		/* Only the temperature channel has a offset */
+		*val = 4425; /* 25 degree Celsius = 0x0000 */
+		return IIO_VAL_INT;
+	case IIO_CHAN_INFO_CALIBBIAS:
+		return adis16480_get_calibbias(indio_dev, chan, val);
+	case IIO_CHAN_INFO_CALIBSCALE:
+		return adis16480_get_calibscale(indio_dev, chan, val);
+	case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY:
+		return adis16480_get_filter_freq(indio_dev, chan, val);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int adis16480_write_raw(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, int val, int val2, long info)
+{
+	switch (info) {
+	case IIO_CHAN_INFO_CALIBBIAS:
+		return adis16480_set_calibbias(indio_dev, chan, val);
+	case IIO_CHAN_INFO_CALIBSCALE:
+		return adis16480_set_calibscale(indio_dev, chan, val);
+	case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY:
+		return adis16480_set_filter_freq(indio_dev, chan, val);
+	default:
+		return -EINVAL;
+	}
+}
+
+#define ADIS16480_MOD_CHANNEL(_type, _mod, _address, _si, _info, _bits) \
+	{ \
+		.type = (_type), \
+		.modified = 1, \
+		.channel2 = (_mod), \
+		.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \
+			IIO_CHAN_INFO_CALIBBIAS_SEPARATE_BIT | \
+			IIO_CHAN_INFO_SCALE_SHARED_BIT | \
+			_info, \
+		.address = (_address), \
+		.scan_index = (_si), \
+		.scan_type = { \
+			.sign = 's', \
+			.realbits = (_bits), \
+			.storagebits = (_bits), \
+			.endianness = IIO_BE, \
+		}, \
+	}
+
+#define ADIS16480_GYRO_CHANNEL(_mod) \
+	ADIS16480_MOD_CHANNEL(IIO_ANGL_VEL, IIO_MOD_ ## _mod, \
+	ADIS16480_REG_ ## _mod ## _GYRO_OUT, ADIS16480_SCAN_GYRO_ ## _mod, \
+	IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY_SEPARATE_BIT | \
+	IIO_CHAN_INFO_CALIBSCALE_SEPARATE_BIT, \
+	32)
+
+#define ADIS16480_ACCEL_CHANNEL(_mod) \
+	ADIS16480_MOD_CHANNEL(IIO_ACCEL, IIO_MOD_ ## _mod, \
+	ADIS16480_REG_ ## _mod ## _ACCEL_OUT, ADIS16480_SCAN_ACCEL_ ## _mod, \
+	IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY_SEPARATE_BIT | \
+	IIO_CHAN_INFO_CALIBSCALE_SEPARATE_BIT, \
+	32)
+
+#define ADIS16480_MAGN_CHANNEL(_mod) \
+	ADIS16480_MOD_CHANNEL(IIO_MAGN, IIO_MOD_ ## _mod, \
+	ADIS16480_REG_ ## _mod ## _MAGN_OUT, ADIS16480_SCAN_MAGN_ ## _mod, \
+	IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY_SEPARATE_BIT, \
+	16)
+
+#define ADIS16480_PRESSURE_CHANNEL() \
+	{ \
+		.type = IIO_PRESSURE, \
+		.indexed = 1, \
+		.channel = 0, \
+		.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \
+			IIO_CHAN_INFO_CALIBBIAS_SEPARATE_BIT | \
+			IIO_CHAN_INFO_SCALE_SEPARATE_BIT, \
+		.address = ADIS16480_REG_BAROM_OUT, \
+		.scan_index = ADIS16480_SCAN_BARO, \
+		.scan_type = { \
+			.sign = 's', \
+			.realbits = 32, \
+			.storagebits = 32, \
+			.endianness = IIO_BE, \
+		}, \
+	}
+
+#define ADIS16480_TEMP_CHANNEL() { \
+		.type = IIO_TEMP, \
+		.indexed = 1, \
+		.channel = 0, \
+		.info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \
+			IIO_CHAN_INFO_SCALE_SEPARATE_BIT | \
+			IIO_CHAN_INFO_OFFSET_SEPARATE_BIT, \
+		.address = ADIS16480_REG_TEMP_OUT, \
+		.scan_index = ADIS16480_SCAN_TEMP, \
+		.scan_type = { \
+			.sign = 's', \
+			.realbits = 16, \
+			.storagebits = 16, \
+			.endianness = IIO_BE, \
+		}, \
+	}
+
+static const struct iio_chan_spec adis16480_channels[] = {
+	ADIS16480_GYRO_CHANNEL(X),
+	ADIS16480_GYRO_CHANNEL(Y),
+	ADIS16480_GYRO_CHANNEL(Z),
+	ADIS16480_ACCEL_CHANNEL(X),
+	ADIS16480_ACCEL_CHANNEL(Y),
+	ADIS16480_ACCEL_CHANNEL(Z),
+	ADIS16480_MAGN_CHANNEL(X),
+	ADIS16480_MAGN_CHANNEL(Y),
+	ADIS16480_MAGN_CHANNEL(Z),
+	ADIS16480_PRESSURE_CHANNEL(),
+	ADIS16480_TEMP_CHANNEL(),
+	IIO_CHAN_SOFT_TIMESTAMP(11)
+};
+
+static const struct iio_chan_spec adis16485_channels[] = {
+	ADIS16480_GYRO_CHANNEL(X),
+	ADIS16480_GYRO_CHANNEL(Y),
+	ADIS16480_GYRO_CHANNEL(Z),
+	ADIS16480_ACCEL_CHANNEL(X),
+	ADIS16480_ACCEL_CHANNEL(Y),
+	ADIS16480_ACCEL_CHANNEL(Z),
+	ADIS16480_TEMP_CHANNEL(),
+	IIO_CHAN_SOFT_TIMESTAMP(7)
+};
+
+enum adis16480_variant {
+	ADIS16375,
+	ADIS16480,
+	ADIS16485,
+	ADIS16488,
+};
+
+static const struct adis16480_chip_info adis16480_chip_info[] = {
+	[ADIS16375] = {
+		.channels = adis16485_channels,
+		.num_channels = ARRAY_SIZE(adis16485_channels),
+	},
+	[ADIS16480] = {
+		.channels = adis16480_channels,
+		.num_channels = ARRAY_SIZE(adis16480_channels),
+	},
+	[ADIS16485] = {
+		.channels = adis16485_channels,
+		.num_channels = ARRAY_SIZE(adis16485_channels),
+	},
+	[ADIS16488] = {
+		.channels = adis16480_channels,
+		.num_channels = ARRAY_SIZE(adis16480_channels),
+	},
+};
+
+static struct attribute *adis16480_attributes[] = {
+	&iio_dev_attr_sampling_frequency.dev_attr.attr,
+	NULL
+};
+
+static const struct attribute_group adis16480_attribute_group = {
+	.attrs = adis16480_attributes,
+};
+
+static const struct iio_info adis16480_info = {
+	.attrs = &adis16480_attribute_group,
+	.read_raw = &adis16480_read_raw,
+	.write_raw = &adis16480_write_raw,
+	.update_scan_mode = adis_update_scan_mode,
+	.driver_module = THIS_MODULE,
+};
+
+static int adis16480_stop_device(struct iio_dev *indio_dev)
+{
+	struct adis16480 *st = iio_priv(indio_dev);
+	int ret;
+
+	ret = adis_write_reg_16(&st->adis, ADIS16480_REG_SLP_CNT, BIT(9));
+	if (ret)
+		dev_err(&indio_dev->dev,
+			"Could not power down device: %d\n", ret);
+
+	return ret;
+}
+
+static int adis16480_enable_irq(struct adis *adis, bool enable)
+{
+	return adis_write_reg_16(adis, ADIS16480_REG_FNCTIO_CTRL,
+		enable ? BIT(3) : 0);
+}
+
+static int adis16480_initial_setup(struct iio_dev *indio_dev)
+{
+	struct adis16480 *st = iio_priv(indio_dev);
+	uint16_t prod_id;
+	unsigned int device_id;
+	int ret;
+
+	adis_reset(&st->adis);
+	msleep(70);
+
+	ret = adis_write_reg_16(&st->adis, ADIS16480_REG_GLOB_CMD, BIT(1));
+	if (ret)
+		return ret;
+	msleep(30);
+
+	ret = adis_check_status(&st->adis);
+	if (ret)
+		return ret;
+
+	ret = adis_read_reg_16(&st->adis, ADIS16480_REG_PROD_ID, &prod_id);
+	if (ret)
+		return ret;
+
+	sscanf(indio_dev->name, "adis%u\n", &device_id);
+
+	if (prod_id != device_id)
+		dev_warn(&indio_dev->dev, "Device ID(%u) and product ID(%u) do not match.",
+				device_id, prod_id);
+
+	return 0;
+}
+
+#define ADIS16480_DIAG_STAT_XGYRO_FAIL 0
+#define ADIS16480_DIAG_STAT_YGYRO_FAIL 1
+#define ADIS16480_DIAG_STAT_ZGYRO_FAIL 2
+#define ADIS16480_DIAG_STAT_XACCL_FAIL 3
+#define ADIS16480_DIAG_STAT_YACCL_FAIL 4
+#define ADIS16480_DIAG_STAT_ZACCL_FAIL 5
+#define ADIS16480_DIAG_STAT_XMAGN_FAIL 8
+#define ADIS16480_DIAG_STAT_YMAGN_FAIL 9
+#define ADIS16480_DIAG_STAT_ZMAGN_FAIL 10
+#define ADIS16480_DIAG_STAT_BARO_FAIL 11
+
+static const char * const adis16480_status_error_msgs[] = {
+	[ADIS16480_DIAG_STAT_XGYRO_FAIL] = "X-axis gyroscope self-test failure",
+	[ADIS16480_DIAG_STAT_YGYRO_FAIL] = "Y-axis gyroscope self-test failure",
+	[ADIS16480_DIAG_STAT_ZGYRO_FAIL] = "Z-axis gyroscope self-test failure",
+	[ADIS16480_DIAG_STAT_XACCL_FAIL] = "X-axis accelerometer self-test failure",
+	[ADIS16480_DIAG_STAT_YACCL_FAIL] = "Y-axis accelerometer self-test failure",
+	[ADIS16480_DIAG_STAT_ZACCL_FAIL] = "Z-axis accelerometer self-test failure",
+	[ADIS16480_DIAG_STAT_XMAGN_FAIL] = "X-axis magnetometer self-test failure",
+	[ADIS16480_DIAG_STAT_YMAGN_FAIL] = "Y-axis magnetometer self-test failure",
+	[ADIS16480_DIAG_STAT_ZMAGN_FAIL] = "Z-axis magnetometer self-test failure",
+	[ADIS16480_DIAG_STAT_BARO_FAIL] = "Barometer self-test failure",
+};
+
+static const struct adis_data adis16480_data = {
+	.diag_stat_reg = ADIS16480_REG_DIAG_STS,
+	.glob_cmd_reg = ADIS16480_REG_GLOB_CMD,
+	.has_paging = true,
+
+	.read_delay = 5,
+	.write_delay = 5,
+
+	.status_error_msgs = adis16480_status_error_msgs,
+	.status_error_mask = BIT(ADIS16480_DIAG_STAT_XGYRO_FAIL) |
+		BIT(ADIS16480_DIAG_STAT_YGYRO_FAIL) |
+		BIT(ADIS16480_DIAG_STAT_ZGYRO_FAIL) |
+		BIT(ADIS16480_DIAG_STAT_XACCL_FAIL) |
+		BIT(ADIS16480_DIAG_STAT_YACCL_FAIL) |
+		BIT(ADIS16480_DIAG_STAT_ZACCL_FAIL) |
+		BIT(ADIS16480_DIAG_STAT_XMAGN_FAIL) |
+		BIT(ADIS16480_DIAG_STAT_YMAGN_FAIL) |
+		BIT(ADIS16480_DIAG_STAT_ZMAGN_FAIL) |
+		BIT(ADIS16480_DIAG_STAT_BARO_FAIL),
+
+	.enable_irq = adis16480_enable_irq,
+};
+
+static int adis16480_probe(struct spi_device *spi)
+{
+	const struct spi_device_id *id = spi_get_device_id(spi);
+	struct iio_dev *indio_dev;
+	struct adis16480 *st;
+	int ret;
+
+	indio_dev = iio_device_alloc(sizeof(*st));
+	if (indio_dev == NULL)
+		return -ENOMEM;
+
+	spi_set_drvdata(spi, indio_dev);
+
+	st = iio_priv(indio_dev);
+
+	st->chip_info = &adis16480_chip_info[id->driver_data];
+	indio_dev->dev.parent = &spi->dev;
+	indio_dev->name = spi_get_device_id(spi)->name;
+	indio_dev->channels = st->chip_info->channels;
+	indio_dev->num_channels = st->chip_info->num_channels;
+	indio_dev->info = &adis16480_info;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+
+	ret = adis_init(&st->adis, indio_dev, spi, &adis16480_data);
+	if (ret)
+		goto error_free_dev;
+
+	ret = adis_setup_buffer_and_trigger(&st->adis, indio_dev, NULL);
+	if (ret)
+		goto error_free_dev;
+
+	ret = adis16480_initial_setup(indio_dev);
+	if (ret)
+		goto error_cleanup_buffer;
+
+	ret = iio_device_register(indio_dev);
+	if (ret)
+		goto error_stop_device;
+
+	adis16480_debugfs_init(indio_dev);
+
+	return 0;
+
+error_stop_device:
+	adis16480_stop_device(indio_dev);
+error_cleanup_buffer:
+	adis_cleanup_buffer_and_trigger(&st->adis, indio_dev);
+error_free_dev:
+	iio_device_free(indio_dev);
+	return ret;
+}
+
+static int adis16480_remove(struct spi_device *spi)
+{
+	struct iio_dev *indio_dev = spi_get_drvdata(spi);
+	struct adis16480 *st = iio_priv(indio_dev);
+
+	iio_device_unregister(indio_dev);
+	adis16480_stop_device(indio_dev);
+
+	adis_cleanup_buffer_and_trigger(&st->adis, indio_dev);
+
+	iio_device_free(indio_dev);
+
+	return 0;
+}
+
+static const struct spi_device_id adis16480_ids[] = {
+	{ "adis16375", ADIS16375 },
+	{ "adis16480", ADIS16480 },
+	{ "adis16485", ADIS16485 },
+	{ "adis16488", ADIS16488 },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, adis16480_ids);
+
+static struct spi_driver adis16480_driver = {
+	.driver = {
+		.name = "adis16480",
+		.owner = THIS_MODULE,
+	},
+	.id_table = adis16480_ids,
+	.probe = adis16480_probe,
+	.remove = adis16480_remove,
+};
+module_spi_driver(adis16480_driver);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("Analog Devices ADIS16480 IMU driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index e82cd0827e91..ff781dca2e9a 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -20,6 +20,8 @@
 #define ADIS_PAGE_SIZE 0x80
 #define ADIS_REG_PAGE_ID 0x00
 
+struct adis;
+
 /**
  * struct adis_data - ADIS chip variant specific data
  * @read_delay: SPI delay for read operations in us
@@ -44,6 +46,8 @@ struct adis_data {
 	const char * const *status_error_msgs;
 	unsigned int status_error_mask;
 
+	int (*enable_irq)(struct adis *adis, bool enable);
+
 	bool has_paging;
 };
 
-- 
cgit v1.2.3-55-g7522


From 95f8a082b9b1ead0c2859f2a7b1ac91ff63d8765 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Wed, 21 Nov 2012 00:21:50 +0100
Subject: ACPI / driver core: Introduce struct acpi_dev_node and related macros

To avoid adding an ACPI handle pointer to struct device on
architectures that don't use ACPI, or generally when CONFIG_ACPI is
not set, in which cases that pointer is useless, define struct
acpi_dev_node that will contain the handle pointer if CONFIG_ACPI is
set and will be empty otherwise and use it to represent the ACPI
device node field in struct device.

In addition to that define macros for reading and setting the ACPI
handle of a device that don't generate code when CONFIG_ACPI is
unset.  Modify the ACPI subsystem to use those macros instead of
referring to the given device's ACPI handle directly.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/acpi/glue.c     | 16 ++++++++--------
 drivers/acpi/scan.c     |  4 ++--
 include/acpi/acpi_bus.h |  2 +-
 include/linux/device.h  | 18 ++++++++++++++++--
 4 files changed, 27 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 3e75d6e5a469..01551840d236 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -134,12 +134,12 @@ static int acpi_bind_one(struct device *dev, acpi_handle handle)
 	char physical_node_name[sizeof(PHYSICAL_NODE_STRING) + 2];
 	int retval = -EINVAL;
 
-	if (dev->acpi_handle) {
+	if (ACPI_HANDLE(dev)) {
 		if (handle) {
 			dev_warn(dev, "ACPI handle is already set\n");
 			return -EINVAL;
 		} else {
-			handle = dev->acpi_handle;
+			handle = ACPI_HANDLE(dev);
 		}
 	}
 	if (!handle)
@@ -181,8 +181,8 @@ static int acpi_bind_one(struct device *dev, acpi_handle handle)
 
 	mutex_unlock(&acpi_dev->physical_node_lock);
 
-	if (!dev->acpi_handle)
-		dev->acpi_handle = handle;
+	if (!ACPI_HANDLE(dev))
+		ACPI_HANDLE_SET(dev, acpi_dev->handle);
 
 	if (!physical_node->node_id)
 		strcpy(physical_node_name, PHYSICAL_NODE_STRING);
@@ -200,7 +200,7 @@ static int acpi_bind_one(struct device *dev, acpi_handle handle)
 	return 0;
 
  err:
-	dev->acpi_handle = NULL;
+	ACPI_HANDLE_SET(dev, NULL);
 	put_device(dev);
 	return retval;
 
@@ -217,10 +217,10 @@ static int acpi_unbind_one(struct device *dev)
 	acpi_status status;
 	struct list_head *node, *next;
 
-	if (!dev->acpi_handle)
+	if (!ACPI_HANDLE(dev))
 		return 0;
 
-	status = acpi_bus_get_device(dev->acpi_handle, &acpi_dev);
+	status = acpi_bus_get_device(ACPI_HANDLE(dev), &acpi_dev);
 	if (ACPI_FAILURE(status))
 		goto err;
 
@@ -246,7 +246,7 @@ static int acpi_unbind_one(struct device *dev)
 
 		sysfs_remove_link(&acpi_dev->dev.kobj, physical_node_name);
 		sysfs_remove_link(&dev->kobj, "firmware_node");
-		dev->acpi_handle = NULL;
+		ACPI_HANDLE_SET(dev, NULL);
 		/* acpi_bind_one increase refcnt by one */
 		put_device(dev);
 		kfree(entry);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index d842569395a9..e92ca67d0e46 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -386,8 +386,8 @@ const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
 {
 	struct acpi_device *adev;
 
-	if (!ids || !dev->acpi_handle
-	    || ACPI_FAILURE(acpi_bus_get_device(dev->acpi_handle, &adev)))
+	if (!ids || !ACPI_HANDLE(dev)
+	    || ACPI_FAILURE(acpi_bus_get_device(ACPI_HANDLE(dev), &adev)))
 		return NULL;
 
 	return __acpi_match_device(adev, ids);
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index bb1537c5e672..d1659904f2a0 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -410,7 +410,7 @@ acpi_handle acpi_get_child(acpi_handle, u64);
 int acpi_is_root_bridge(acpi_handle);
 acpi_handle acpi_get_pci_rootbridge_handle(unsigned int, unsigned int);
 struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle);
-#define DEVICE_ACPI_HANDLE(dev) ((acpi_handle)((dev)->acpi_handle))
+#define DEVICE_ACPI_HANDLE(dev) ((acpi_handle)ACPI_HANDLE(dev))
 
 int acpi_enable_wakeup_device_power(struct acpi_device *dev, int state);
 int acpi_disable_wakeup_device_power(struct acpi_device *dev);
diff --git a/include/linux/device.h b/include/linux/device.h
index cc3aee57a46e..05292e488346 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -578,6 +578,12 @@ struct device_dma_parameters {
 	unsigned long segment_boundary_mask;
 };
 
+struct acpi_dev_node {
+#ifdef CONFIG_ACPI
+	void	*handle;
+#endif
+};
+
 /**
  * struct device - The basic device structure
  * @parent:	The device's "parent" device, the device to which it is attached.
@@ -618,7 +624,7 @@ struct device_dma_parameters {
  * @dma_mem:	Internal for coherent mem override.
  * @archdata:	For arch-specific additions.
  * @of_node:	Associated device tree node.
- * @acpi_handle: Associated ACPI device node's namespace handle.
+ * @acpi_node:	Associated ACPI device node.
  * @devt:	For creating the sysfs "dev".
  * @id:		device instance
  * @devres_lock: Spinlock to protect the resource of the device.
@@ -683,7 +689,7 @@ struct device {
 	struct dev_archdata	archdata;
 
 	struct device_node	*of_node; /* associated device tree node */
-	void			*acpi_handle; /* associated ACPI device node */
+	struct acpi_dev_node	acpi_node; /* associated ACPI device node */
 
 	dev_t			devt;	/* dev_t, creates the sysfs "dev" */
 	u32			id;	/* device instance */
@@ -704,6 +710,14 @@ static inline struct device *kobj_to_dev(struct kobject *kobj)
 	return container_of(kobj, struct device, kobj);
 }
 
+#ifdef CONFIG_ACPI
+#define ACPI_HANDLE(dev)	((dev)->acpi_node.handle)
+#define ACPI_HANDLE_SET(dev, _handle_)	(dev)->acpi_node.handle = (_handle_)
+#else
+#define ACPI_HANDLE(dev)	(NULL)
+#define ACPI_HANDLE_SET(dev, _handle_)	do { } while (0)
+#endif
+
 /* Get the wakeup routines, which depend on struct device */
 #include <linux/pm_wakeup.h>
 
-- 
cgit v1.2.3-55-g7522


From 863f9f30e6c1e30cb19a0cd17c5cf8879257dfd7 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Wed, 21 Nov 2012 00:21:59 +0100
Subject: ACPI / platform: Initialize ACPI handles of platform devices in
 advance

The current platform device creation and registration code in
acpi_create_platform_device() is quite convoluted.  This function
takes an ACPI device node as an argument and eventually calls
platform_device_register_resndata() to create and register a
platform device object on the basis of the information contained
in that code.  However, it doesn't associate the new platform
device with the ACPI node directly, but instead it relies on
acpi_platform_notify(), called from within device_add(), to find
that ACPI node again with the help of acpi_platform_find_device()
and acpi_platform_match() and then attach the new platform device
to it.  This causes an additional ACPI namespace walk to happen and
is clearly suboptimal.

Use the observation that it is now possible to initialize the ACPI
handle of a device before calling device_add() for it to make this
code more straightforward.  Namely, add a new field to struct
platform_device_info allowing us to pass the ACPI handle of interest
to platform_device_register_full(), which will then use it to
initialize the new device's ACPI handle before registering it.
This will cause acpi_platform_notify() to use the ACPI handle from
the device structure directly instead of using the .find_device()
routine provided by the device's bus type.  In consequence,
acpi_platform_bus, acpi_platform_find_device(), and
acpi_platform_match() are not necessary any more, so remove them.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/acpi/acpi_platform.c    | 76 ++++++-----------------------------------
 drivers/base/platform.c         |  2 ++
 include/linux/platform_device.h |  1 +
 3 files changed, 13 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index 7ac20d8b8f07..b7df9b197bcf 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -33,7 +33,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 {
 	struct platform_device *pdev = NULL;
 	struct acpi_device *acpi_parent;
-	struct device *parent = NULL;
+	struct platform_device_info pdevinfo;
 	struct resource_list_entry *rentry;
 	struct list_head resource_list;
 	struct resource *resources;
@@ -60,11 +60,13 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 
 	acpi_dev_free_resource_list(&resource_list);
 
+	memset(&pdevinfo, 0, sizeof(pdevinfo));
 	/*
 	 * If the ACPI node has a parent and that parent has a physical device
 	 * attached to it, that physical device should be the parent of the
 	 * platform device we are about to create.
 	 */
+	pdevinfo.parent = NULL;
 	acpi_parent = adev->parent;
 	if (acpi_parent) {
 		struct acpi_device_physical_node *entry;
@@ -76,12 +78,16 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 			entry = list_first_entry(list,
 					struct acpi_device_physical_node,
 					node);
-			parent = entry->dev;
+			pdevinfo.parent = entry->dev;
 		}
 		mutex_unlock(&acpi_parent->physical_node_lock);
 	}
-	pdev = platform_device_register_resndata(parent, dev_name(&adev->dev),
-						 -1, resources, count, NULL, 0);
+	pdevinfo.name = dev_name(&adev->dev);
+	pdevinfo.id = -1;
+	pdevinfo.res = resources;
+	pdevinfo.num_res = count;
+	pdevinfo.acpi_node.handle = adev->handle;
+	pdev = platform_device_register_full(&pdevinfo);
 	if (IS_ERR(pdev)) {
 		dev_err(&adev->dev, "platform device creation failed: %ld\n",
 			PTR_ERR(pdev));
@@ -94,65 +100,3 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 	kfree(resources);
 	return pdev;
 }
-
-static acpi_status acpi_platform_match(acpi_handle handle, u32 depth,
-				       void *data, void **return_value)
-{
-	struct platform_device *pdev = data;
-	struct acpi_device *adev;
-	acpi_status status;
-
-	status = acpi_bus_get_device(handle, &adev);
-	if (ACPI_FAILURE(status))
-		return status;
-
-	/* Skip ACPI devices that have physical device attached */
-	if (adev->physical_node_count)
-		return AE_OK;
-
-	if (!strcmp(dev_name(&pdev->dev), dev_name(&adev->dev))) {
-		*(acpi_handle *)return_value = handle;
-		return AE_CTRL_TERMINATE;
-	}
-
-	return AE_OK;
-}
-
-static int acpi_platform_find_device(struct device *dev, acpi_handle *handle)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	char *name, *tmp, *hid;
-
-	/*
-	 * The platform device is named using the ACPI device name
-	 * _HID:INSTANCE so we strip the INSTANCE out in order to find the
-	 * correct device using its _HID.
-	 */
-	name = kstrdup(dev_name(dev), GFP_KERNEL);
-	if (!name)
-		return -ENOMEM;
-
-	tmp = name;
-	hid = strsep(&tmp, ":");
-	if (!hid) {
-		kfree(name);
-		return -ENODEV;
-	}
-
-	*handle = NULL;
-	acpi_get_devices(hid, acpi_platform_match, pdev, handle);
-
-	kfree(name);
-	return *handle ? 0 : -ENODEV;
-}
-
-static struct acpi_bus_type acpi_platform_bus = {
-	.bus = &platform_bus_type,
-	.find_device = acpi_platform_find_device,
-};
-
-static int __init acpi_platform_init(void)
-{
-	return register_acpi_bus_type(&acpi_platform_bus);
-}
-arch_initcall(acpi_platform_init);
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 7de29ebfce7f..49fd96e23460 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -437,6 +437,7 @@ struct platform_device *platform_device_register_full(
 		goto err_alloc;
 
 	pdev->dev.parent = pdevinfo->parent;
+	ACPI_HANDLE_SET(&pdev->dev, pdevinfo->acpi_node.handle);
 
 	if (pdevinfo->dma_mask) {
 		/*
@@ -467,6 +468,7 @@ struct platform_device *platform_device_register_full(
 	ret = platform_device_add(pdev);
 	if (ret) {
 err:
+		ACPI_HANDLE_SET(&pdev->dev, NULL);
 		kfree(pdev->dev.dma_mask);
 
 err_alloc:
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 5711e9525a2a..a9ded9a3c175 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -55,6 +55,7 @@ extern int platform_add_devices(struct platform_device **, int);
 
 struct platform_device_info {
 		struct device *parent;
+		struct acpi_dev_node acpi_node;
 
 		const char *name;
 		int id;
-- 
cgit v1.2.3-55-g7522


From 76aad392f75e6ce5be3f106554e16f7ff96543e5 Mon Sep 17 00:00:00 2001
From: Davide Ciminaghi
Date: Tue, 20 Nov 2012 15:20:30 +0100
Subject: regmap: introduce tables for readable/writeable/volatile/precious
 checks

Many of the regmap enabled drivers implementing one or more of the
readable, writeable, volatile and precious methods use the same code
pattern:

	return ((reg >= X && reg <= Y) || (reg >= W && reg <= Z) || ...)

Switch to a data driven approach, using tables to describe
readable/writeable/volatile and precious registers ranges instead.
The table based check can still be overridden by passing the usual function
pointers via struct regmap_config.

Signed-off-by: Davide Ciminaghi <ciminaghi@gnudd.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/base/regmap/internal.h |  4 ++
 drivers/base/regmap/regmap.c   | 46 +++++++++++++++++++++++
 include/linux/regmap.h         | 83 ++++++++++++++++++++++++++++++++++++------
 3 files changed, 122 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 2cd01b57b1c4..288e135fd5f8 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -55,6 +55,10 @@ struct regmap {
 	bool (*readable_reg)(struct device *dev, unsigned int reg);
 	bool (*volatile_reg)(struct device *dev, unsigned int reg);
 	bool (*precious_reg)(struct device *dev, unsigned int reg);
+	const struct regmap_access_table *wr_table;
+	const struct regmap_access_table *rd_table;
+	const struct regmap_access_table *volatile_table;
+	const struct regmap_access_table *precious_table;
 
 	u8 read_flag_mask;
 	u8 write_flag_mask;
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 64eb8350a074..96f7e8523ee8 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -34,6 +34,36 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg,
 			       unsigned int mask, unsigned int val,
 			       bool *change);
 
+bool regmap_reg_in_ranges(unsigned int reg,
+			  const struct regmap_range *ranges,
+			  unsigned int nranges)
+{
+	const struct regmap_range *r;
+	int i;
+
+	for (i = 0, r = ranges; i < nranges; i++, r++)
+		if (regmap_reg_in_range(reg, r))
+			return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(regmap_reg_in_ranges);
+
+static bool _regmap_check_range_table(struct regmap *map,
+				      unsigned int reg,
+				      const struct regmap_access_table *table)
+{
+	/* Check "no ranges" first */
+	if (regmap_reg_in_ranges(reg, table->no_ranges, table->n_no_ranges))
+		return false;
+
+	/* In case zero "yes ranges" are supplied, any reg is OK */
+	if (!table->n_yes_ranges)
+		return true;
+
+	return regmap_reg_in_ranges(reg, table->yes_ranges,
+				    table->n_yes_ranges);
+}
+
 bool regmap_writeable(struct regmap *map, unsigned int reg)
 {
 	if (map->max_register && reg > map->max_register)
@@ -42,6 +72,9 @@ bool regmap_writeable(struct regmap *map, unsigned int reg)
 	if (map->writeable_reg)
 		return map->writeable_reg(map->dev, reg);
 
+	if (map->wr_table)
+		return _regmap_check_range_table(map, reg, map->wr_table);
+
 	return true;
 }
 
@@ -56,6 +89,9 @@ bool regmap_readable(struct regmap *map, unsigned int reg)
 	if (map->readable_reg)
 		return map->readable_reg(map->dev, reg);
 
+	if (map->rd_table)
+		return _regmap_check_range_table(map, reg, map->rd_table);
+
 	return true;
 }
 
@@ -67,6 +103,9 @@ bool regmap_volatile(struct regmap *map, unsigned int reg)
 	if (map->volatile_reg)
 		return map->volatile_reg(map->dev, reg);
 
+	if (map->volatile_table)
+		return _regmap_check_range_table(map, reg, map->volatile_table);
+
 	return true;
 }
 
@@ -78,6 +117,9 @@ bool regmap_precious(struct regmap *map, unsigned int reg)
 	if (map->precious_reg)
 		return map->precious_reg(map->dev, reg);
 
+	if (map->precious_table)
+		return _regmap_check_range_table(map, reg, map->precious_table);
+
 	return false;
 }
 
@@ -370,6 +412,10 @@ struct regmap *regmap_init(struct device *dev,
 	map->bus = bus;
 	map->bus_context = bus_context;
 	map->max_register = config->max_register;
+	map->wr_table = config->wr_table;
+	map->rd_table = config->rd_table;
+	map->volatile_table = config->volatile_table;
+	map->precious_table = config->precious_table;
 	map->writeable_reg = config->writeable_reg;
 	map->readable_reg = config->readable_reg;
 	map->volatile_reg = config->volatile_reg;
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 0e819e3cebce..3bdb1f9a5b43 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -53,6 +53,36 @@ enum regmap_endian {
 	REGMAP_ENDIAN_NATIVE,
 };
 
+/**
+ * A register range, used for access related checks
+ * (readable/writeable/volatile/precious checks)
+ *
+ * @range_min: address of first register
+ * @range_max: address of last register
+ */
+struct regmap_range {
+	unsigned int range_min;
+	unsigned int range_max;
+};
+
+/*
+ * A table of ranges including some yes ranges and some no ranges.
+ * If a register belongs to a no_range, the corresponding check function
+ * will return false. If a register belongs to a yes range, the corresponding
+ * check function will return true. "no_ranges" are searched first.
+ *
+ * @yes_ranges : pointer to an array of regmap ranges used as "yes ranges"
+ * @n_yes_ranges: size of the above array
+ * @no_ranges: pointer to an array of regmap ranges used as "no ranges"
+ * @n_no_ranges: size of the above array
+ */
+struct regmap_access_table {
+	const struct regmap_range *yes_ranges;
+	unsigned int n_yes_ranges;
+	const struct regmap_range *no_ranges;
+	unsigned int n_no_ranges;
+};
+
 typedef void (*regmap_lock)(void *);
 typedef void (*regmap_unlock)(void *);
 
@@ -70,22 +100,39 @@ typedef void (*regmap_unlock)(void *);
  * @val_bits: Number of bits in a register value, mandatory.
  *
  * @writeable_reg: Optional callback returning true if the register
- *                 can be written to.
+ *		   can be written to. If this field is NULL but wr_table
+ *		   (see below) is not, the check is performed on such table
+ *                 (a register is writeable if it belongs to one of the ranges
+ *                  specified by wr_table).
  * @readable_reg: Optional callback returning true if the register
- *                can be read from.
+ *		  can be read from. If this field is NULL but rd_table
+ *		   (see below) is not, the check is performed on such table
+ *                 (a register is readable if it belongs to one of the ranges
+ *                  specified by rd_table).
  * @volatile_reg: Optional callback returning true if the register
- *                value can't be cached.
+ *		  value can't be cached. If this field is NULL but
+ *		  volatile_table (see below) is not, the check is performed on
+ *                such table (a register is volatile if it belongs to one of
+ *                the ranges specified by volatile_table).
  * @precious_reg: Optional callback returning true if the rgister
- *                should not be read outside of a call from the driver
- *                (eg, a clear on read interrupt status register).
- * @lock:         Optional lock callback (overrides regmap's default lock
- *                function, based on spinlock or mutex).
- * @unlock:       As above for unlocking.
- * @lock_arg:     this field is passed as the only argument of lock/unlock
- *                functions (ignored in case regular lock/unlock functions
- *                are not overridden).
+ *		  should not be read outside of a call from the driver
+ *		  (eg, a clear on read interrupt status register). If this
+ *                field is NULL but precious_table (see below) is not, the
+ *                check is performed on such table (a register is precious if
+ *                it belongs to one of the ranges specified by precious_table).
+ * @lock:	  Optional lock callback (overrides regmap's default lock
+ *		  function, based on spinlock or mutex).
+ * @unlock:	  As above for unlocking.
+ * @lock_arg:	  this field is passed as the only argument of lock/unlock
+ *		  functions (ignored in case regular lock/unlock functions
+ *		  are not overridden).
  *
  * @max_register: Optional, specifies the maximum valid register index.
+ * @wr_table:     Optional, points to a struct regmap_access_table specifying
+ *                valid ranges for write access.
+ * @rd_table:     As above, for read access.
+ * @volatile_table: As above, for volatile registers.
+ * @precious_table: As above, for precious registers.
  * @reg_defaults: Power on reset values for registers (for use with
  *                register cache support).
  * @num_reg_defaults: Number of elements in reg_defaults.
@@ -130,6 +177,10 @@ struct regmap_config {
 	void *lock_arg;
 
 	unsigned int max_register;
+	const struct regmap_access_table *wr_table;
+	const struct regmap_access_table *rd_table;
+	const struct regmap_access_table *volatile_table;
+	const struct regmap_access_table *precious_table;
 	const struct reg_default *reg_defaults;
 	unsigned int num_reg_defaults;
 	enum regcache_type cache_type;
@@ -280,6 +331,16 @@ void regcache_mark_dirty(struct regmap *map);
 int regmap_register_patch(struct regmap *map, const struct reg_default *regs,
 			  int num_regs);
 
+static inline bool regmap_reg_in_range(unsigned int reg,
+				       const struct regmap_range *range)
+{
+	return reg >= range->range_min && reg <= range->range_max;
+}
+
+bool regmap_reg_in_ranges(unsigned int reg,
+			  const struct regmap_range *ranges,
+			  unsigned int nranges);
+
 /**
  * Description of an IRQ for the generic regmap irq_chip.
  *
-- 
cgit v1.2.3-55-g7522


From be193249b4178158c0f697cb452b2bbf0cb16361 Mon Sep 17 00:00:00 2001
From: Viresh Kumar
Date: Tue, 20 Nov 2012 10:15:19 +0530
Subject: dt: add helper function to read u8 & u16 variables & arrays

This adds following helper routines:
- of_property_read_u8_array()
- of_property_read_u16_array()
- of_property_read_u8()
- of_property_read_u16()

This expects arrays from DT to be passed as:
- u8 array:
	property = /bits/ 8 <0x50 0x60 0x70>;
- u16 array:
	property = /bits/ 16 <0x5000 0x6000 0x7000>;

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
---
 drivers/of/base.c  | 77 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/of.h | 30 +++++++++++++++++++++
 2 files changed, 107 insertions(+)

(limited to 'include')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index af3b22ac7627..f564e3107b3e 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -670,6 +670,82 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 }
 EXPORT_SYMBOL(of_find_node_by_phandle);
 
+/**
+ * of_property_read_u8_array - Find and read an array of u8 from a property.
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @out_value:	pointer to return value, modified only if return value is 0.
+ * @sz:		number of array elements to read
+ *
+ * Search for a property in a device node and read 8-bit value(s) from
+ * it. Returns 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ *
+ * dts entry of array should be like:
+ *	property = /bits/ 8 <0x50 0x60 0x70>;
+ *
+ * The out_value is modified only if a valid u8 value can be decoded.
+ */
+int of_property_read_u8_array(const struct device_node *np,
+			const char *propname, u8 *out_values, size_t sz)
+{
+	struct property *prop = of_find_property(np, propname, NULL);
+	const u8 *val;
+
+	if (!prop)
+		return -EINVAL;
+	if (!prop->value)
+		return -ENODATA;
+	if ((sz * sizeof(*out_values)) > prop->length)
+		return -EOVERFLOW;
+
+	val = prop->value;
+	while (sz--)
+		*out_values++ = *val++;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_property_read_u8_array);
+
+/**
+ * of_property_read_u16_array - Find and read an array of u16 from a property.
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @out_value:	pointer to return value, modified only if return value is 0.
+ * @sz:		number of array elements to read
+ *
+ * Search for a property in a device node and read 16-bit value(s) from
+ * it. Returns 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ *
+ * dts entry of array should be like:
+ *	property = /bits/ 16 <0x5000 0x6000 0x7000>;
+ *
+ * The out_value is modified only if a valid u16 value can be decoded.
+ */
+int of_property_read_u16_array(const struct device_node *np,
+			const char *propname, u16 *out_values, size_t sz)
+{
+	struct property *prop = of_find_property(np, propname, NULL);
+	const __be16 *val;
+
+	if (!prop)
+		return -EINVAL;
+	if (!prop->value)
+		return -ENODATA;
+	if ((sz * sizeof(*out_values)) > prop->length)
+		return -EOVERFLOW;
+
+	val = prop->value;
+	while (sz--)
+		*out_values++ = be16_to_cpup(val++);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_property_read_u16_array);
+
 /**
  * of_property_read_u32_array - Find and read an array of 32 bit integers
  * from a property.
@@ -677,6 +753,7 @@ EXPORT_SYMBOL(of_find_node_by_phandle);
  * @np:		device node from which the property value is to be read.
  * @propname:	name of the property to be searched.
  * @out_value:	pointer to return value, modified only if return value is 0.
+ * @sz:		number of array elements to read
  *
  * Search for a property in a device node and read 32-bit value(s) from
  * it. Returns 0 on success, -EINVAL if the property does not exist,
diff --git a/include/linux/of.h b/include/linux/of.h
index 857dde984a6e..ab1af0e14659 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -223,6 +223,10 @@ extern struct device_node *of_find_node_with_property(
 extern struct property *of_find_property(const struct device_node *np,
 					 const char *name,
 					 int *lenp);
+extern int of_property_read_u8_array(const struct device_node *np,
+			const char *propname, u8 *out_values, size_t sz);
+extern int of_property_read_u16_array(const struct device_node *np,
+			const char *propname, u16 *out_values, size_t sz);
 extern int of_property_read_u32_array(const struct device_node *np,
 				      const char *propname,
 				      u32 *out_values,
@@ -364,6 +368,18 @@ static inline struct device_node *of_find_compatible_node(
 	return NULL;
 }
 
+static inline int of_property_read_u8_array(const struct device_node *np,
+			const char *propname, u8 *out_values, size_t sz)
+{
+	return -ENOSYS;
+}
+
+static inline int of_property_read_u16_array(const struct device_node *np,
+			const char *propname, u16 *out_values, size_t sz)
+{
+	return -ENOSYS;
+}
+
 static inline int of_property_read_u32_array(const struct device_node *np,
 					     const char *propname,
 					     u32 *out_values, size_t sz)
@@ -470,6 +486,20 @@ static inline bool of_property_read_bool(const struct device_node *np,
 	return prop ? true : false;
 }
 
+static inline int of_property_read_u8(const struct device_node *np,
+				       const char *propname,
+				       u8 *out_value)
+{
+	return of_property_read_u8_array(np, propname, out_value, 1);
+}
+
+static inline int of_property_read_u16(const struct device_node *np,
+				       const char *propname,
+				       u16 *out_value)
+{
+	return of_property_read_u16_array(np, propname, out_value, 1);
+}
+
 static inline int of_property_read_u32(const struct device_node *np,
 				       const char *propname,
 				       u32 *out_value)
-- 
cgit v1.2.3-55-g7522


From 50c8af4cf98fd97d6779f244215154e4c89699c7 Mon Sep 17 00:00:00 2001
From: Stephen Warren
Date: Tue, 20 Nov 2012 16:12:20 -0700
Subject: of: introduce for_each_matching_node_and_match()

The following pattern of code is tempting:

    for_each_matching_node(np, table) {
        match = of_match_node(table, np);

However, this results in iterating over table twice; the second time
inside of_match_node(). The implementation of for_each_matching_node()
already found the match, so this is redundant. Invent new function
of_find_matching_node_and_match() and macro
for_each_matching_node_and_match() to remove the double iteration,
thus transforming the above code to:

    for_each_matching_node_and_match(np, table, &match)

Signed-off-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
---
 drivers/of/base.c  | 18 +++++++++++++-----
 include/linux/of.h | 15 +++++++++++++--
 2 files changed, 26 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index f564e3107b3e..0ceb26a16050 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -594,27 +594,35 @@ const struct of_device_id *of_match_node(const struct of_device_id *matches,
 EXPORT_SYMBOL(of_match_node);
 
 /**
- *	of_find_matching_node - Find a node based on an of_device_id match
- *				table.
+ *	of_find_matching_node_and_match - Find a node based on an of_device_id
+ *					  match table.
  *	@from:		The node to start searching from or NULL, the node
  *			you pass will not be searched, only the next one
  *			will; typically, you pass what the previous call
  *			returned. of_node_put() will be called on it
  *	@matches:	array of of device match structures to search in
+ *	@match		Updated to point at the matches entry which matched
  *
  *	Returns a node pointer with refcount incremented, use
  *	of_node_put() on it when done.
  */
-struct device_node *of_find_matching_node(struct device_node *from,
-					  const struct of_device_id *matches)
+struct device_node *of_find_matching_node_and_match(struct device_node *from,
+					const struct of_device_id *matches,
+					const struct of_device_id **match)
 {
 	struct device_node *np;
 
+	if (match)
+		*match = NULL;
+
 	read_lock(&devtree_lock);
 	np = from ? from->allnext : allnodes;
 	for (; np; np = np->allnext) {
-		if (of_match_node(matches, np) && of_node_get(np))
+		if (of_match_node(matches, np) && of_node_get(np)) {
+			if (match)
+				*match = matches;
 			break;
+		}
 	}
 	of_node_put(from);
 	read_unlock(&devtree_lock);
diff --git a/include/linux/of.h b/include/linux/of.h
index ab1af0e14659..13e0aacb4d9f 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -179,11 +179,22 @@ extern struct device_node *of_find_compatible_node(struct device_node *from,
 #define for_each_compatible_node(dn, type, compatible) \
 	for (dn = of_find_compatible_node(NULL, type, compatible); dn; \
 	     dn = of_find_compatible_node(dn, type, compatible))
-extern struct device_node *of_find_matching_node(struct device_node *from,
-	const struct of_device_id *matches);
+extern struct device_node *of_find_matching_node_and_match(
+	struct device_node *from,
+	const struct of_device_id *matches,
+	const struct of_device_id **match);
+static inline struct device_node *of_find_matching_node(
+	struct device_node *from,
+	const struct of_device_id *matches)
+{
+	return of_find_matching_node_and_match(from, matches, NULL);
+}
 #define for_each_matching_node(dn, matches) \
 	for (dn = of_find_matching_node(NULL, matches); dn; \
 	     dn = of_find_matching_node(dn, matches))
+#define for_each_matching_node_and_match(dn, matches, match) \
+	for (dn = of_find_matching_node_and_match(NULL, matches, match); \
+	     dn; dn = of_find_matching_node_and_match(dn, matches, match))
 extern struct device_node *of_find_node_by_path(const char *path);
 extern struct device_node *of_find_node_by_phandle(phandle handle);
 extern struct device_node *of_get_parent(const struct device_node *node);
-- 
cgit v1.2.3-55-g7522


From 1a8f85d402a2bf3b86c08c696a0adf36656f770a Mon Sep 17 00:00:00 2001
From: Philip Rakity
Date: Tue, 20 Nov 2012 18:07:41 +0100
Subject: regulator: add missing prototype for regulator_is_supported_voltage

avoids needs for CONFIG_REGULATOR in sdhci.c

Signed-off-by: Philip Rakity <prakity@nvidia.com>
Reviewed-by: Eric Miao <eric.y.miao@gmail.com>
Signed-off-by: Eric Miao <eric.y.miao@gmail.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/linux/regulator/consumer.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index c43cd3556b1f..4e3ec91bc639 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -358,6 +358,10 @@ static inline void regulator_set_drvdata(struct regulator *regulator,
 {
 }
 
+static inline int regulator_count_voltages(struct regulator *regulator)
+{
+	return 0;
+}
 #endif
 
 static inline int regulator_set_voltage_tol(struct regulator *regulator,
-- 
cgit v1.2.3-55-g7522


From 77d2ece6fde80631193054edc9c9a3edad519565 Mon Sep 17 00:00:00 2001
From: Sujith Manoharan
Date: Tue, 20 Nov 2012 08:46:02 +0530
Subject: mac80211: Add debugfs callbacks for station addition/removal

Provide drivers with hooks to create debugfs files when
a new station is added. This would help drivers to take
advantage of mac80211's station list infrastructure and not maintain
tedious station management code internally.

Signed-off-by: Sujith Manoharan <c_manoha@qca.qualcomm.com>
[ifdef inline wrapper functions]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     | 18 ++++++++++++++++++
 net/mac80211/debugfs_sta.c |  9 +++++++++
 net/mac80211/driver-ops.h  | 32 ++++++++++++++++++++++++++++++++
 3 files changed, 59 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d11037b5b854..e1293c7e4d2c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2208,6 +2208,14 @@ enum ieee80211_rate_control_changed {
  * @sta_remove: Notifies low level driver about removal of an associated
  *	station, AP, IBSS/WDS/mesh peer etc. This callback can sleep.
  *
+ * @sta_add_debugfs: Drivers can use this callback to add debugfs files
+ *	when a station is added to mac80211's station list. This callback
+ *	and @sta_remove_debugfs should be within a CONFIG_MAC80211_DEBUGFS
+ *	conditional. This callback can sleep.
+ *
+ * @sta_remove_debugfs: Remove the debugfs files which were added using
+ *	@sta_add_debugfs. This callback can sleep.
+ *
  * @sta_notify: Notifies low level driver about power state transition of an
  *	associated station, AP,  IBSS/WDS/mesh peer etc. For a VIF operating
  *	in AP mode, this callback will not be called when the flag
@@ -2489,6 +2497,16 @@ struct ieee80211_ops {
 		       struct ieee80211_sta *sta);
 	int (*sta_remove)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			  struct ieee80211_sta *sta);
+#ifdef CONFIG_MAC80211_DEBUGFS
+	void (*sta_add_debugfs)(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif,
+				struct ieee80211_sta *sta,
+				struct dentry *dir);
+	void (*sta_remove_debugfs)(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif,
+				   struct ieee80211_sta *sta,
+				   struct dentry *dir);
+#endif
 	void (*sta_notify)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			enum sta_notify_cmd, struct ieee80211_sta *sta);
 	int (*sta_state)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 3d103929d41a..89281d24b094 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -14,6 +14,7 @@
 #include "debugfs.h"
 #include "debugfs_sta.h"
 #include "sta_info.h"
+#include "driver-ops.h"
 
 /* sta attributtes */
 
@@ -334,6 +335,8 @@ STA_OPS(ht_capa);
 
 void ieee80211_sta_debugfs_add(struct sta_info *sta)
 {
+	struct ieee80211_local *local = sta->local;
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct dentry *stations_dir = sta->sdata->debugfs.subdir_stations;
 	u8 mac[3*ETH_ALEN];
 
@@ -379,10 +382,16 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta)
 	DEBUGFS_ADD_COUNTER(tx_retry_failed, tx_retry_failed);
 	DEBUGFS_ADD_COUNTER(tx_retry_count, tx_retry_count);
 	DEBUGFS_ADD_COUNTER(wep_weak_iv_count, wep_weak_iv_count);
+
+	drv_sta_add_debugfs(local, sdata, &sta->sta, sta->debugfs.dir);
 }
 
 void ieee80211_sta_debugfs_remove(struct sta_info *sta)
 {
+	struct ieee80211_local *local = sta->local;
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+
+	drv_sta_remove_debugfs(local, sdata, &sta->sta, sta->debugfs.dir);
 	debugfs_remove_recursive(sta->debugfs.dir);
 	sta->debugfs.dir = NULL;
 }
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 284dd02385e4..68c27aaf5c93 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -490,6 +490,38 @@ static inline void drv_sta_remove(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+#ifdef CONFIG_MAC80211_DEBUGFS
+static inline void drv_sta_add_debugfs(struct ieee80211_local *local,
+				       struct ieee80211_sub_if_data *sdata,
+				       struct ieee80211_sta *sta,
+				       struct dentry *dir)
+{
+	might_sleep();
+
+	sdata = get_bss_sdata(sdata);
+	check_sdata_in_driver(sdata);
+
+	if (local->ops->sta_add_debugfs)
+		local->ops->sta_add_debugfs(&local->hw, &sdata->vif,
+					    sta, dir);
+}
+
+static inline void drv_sta_remove_debugfs(struct ieee80211_local *local,
+					  struct ieee80211_sub_if_data *sdata,
+					  struct ieee80211_sta *sta,
+					  struct dentry *dir)
+{
+	might_sleep();
+
+	sdata = get_bss_sdata(sdata);
+	check_sdata_in_driver(sdata);
+
+	if (local->ops->sta_remove_debugfs)
+		local->ops->sta_remove_debugfs(&local->hw, &sdata->vif,
+					       sta, dir);
+}
+#endif
+
 static inline __must_check
 int drv_sta_state(struct ieee80211_local *local,
 		  struct ieee80211_sub_if_data *sdata,
-- 
cgit v1.2.3-55-g7522


From ae72ae676045274c82f3c25159a9dd7cfcf5ffae Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Tue, 20 Nov 2012 11:02:55 -0500
Subject: NFSv4.1: Don't confuse CREATE_SESSION arguments and results

Don't store the target request and response sizes in the same
variables used to store the server's replies to those targets.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c         | 30 +++++++++++++++++-------------
 include/linux/nfs_fs_sb.h |  3 +++
 2 files changed, 20 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a32d953b08de..3e572dc316e4 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5807,8 +5807,8 @@ void nfs4_destroy_session(struct nfs4_session *session)
 static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
 {
 	struct nfs4_session *session = args->client->cl_session;
-	unsigned int mxrqst_sz = session->fc_attrs.max_rqst_sz,
-		     mxresp_sz = session->fc_attrs.max_resp_sz;
+	unsigned int mxrqst_sz = session->fc_target_max_rqst_sz,
+		     mxresp_sz = session->fc_target_max_resp_sz;
 
 	if (mxrqst_sz == 0)
 		mxrqst_sz = NFS_MAX_FILE_IO_SIZE;
@@ -6015,24 +6015,28 @@ int nfs4_init_session(struct nfs_server *server)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_session *session;
-	unsigned int rsize, wsize;
+	unsigned int target_max_rqst_sz = NFS_MAX_FILE_IO_SIZE;
+	unsigned int target_max_resp_sz = NFS_MAX_FILE_IO_SIZE;
 
 	if (!nfs4_has_session(clp))
 		return 0;
 
+	if (server->rsize != 0)
+		target_max_resp_sz = server->rsize;
+	target_max_resp_sz += nfs41_maxread_overhead;
+
+	if (server->wsize != 0)
+		target_max_rqst_sz = server->wsize;
+	target_max_rqst_sz += nfs41_maxwrite_overhead;
+
 	session = clp->cl_session;
 	spin_lock(&clp->cl_lock);
 	if (test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) {
-
-		rsize = server->rsize;
-		if (rsize == 0)
-			rsize = NFS_MAX_FILE_IO_SIZE;
-		wsize = server->wsize;
-		if (wsize == 0)
-			wsize = NFS_MAX_FILE_IO_SIZE;
-
-		session->fc_attrs.max_rqst_sz = wsize + nfs41_maxwrite_overhead;
-		session->fc_attrs.max_resp_sz = rsize + nfs41_maxread_overhead;
+		/* Initialise targets and channel attributes */
+		session->fc_target_max_rqst_sz = target_max_rqst_sz;
+		session->fc_attrs.max_rqst_sz = target_max_rqst_sz;
+		session->fc_target_max_resp_sz = target_max_resp_sz;
+		session->fc_attrs.max_resp_sz = target_max_resp_sz;
 	}
 	spin_unlock(&clp->cl_lock);
 
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index a9e76ee1adca..97c8f9191880 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -242,6 +242,9 @@ struct nfs4_session {
 	struct nfs4_channel_attrs	bc_attrs;
 	struct nfs4_slot_table		bc_slot_table;
 	struct nfs_client		*clp;
+	/* Create session arguments */
+	unsigned int			fc_target_max_rqst_sz;
+	unsigned int			fc_target_max_resp_sz;
 };
 
 #endif /* CONFIG_NFS_V4 */
-- 
cgit v1.2.3-55-g7522


From 933602e368c4452260c9bff4fbb3baba35cf987a Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Fri, 16 Nov 2012 12:12:38 -0500
Subject: NFSv4.1: Shrink struct nfs4_sequence_res by moving sr_renewal_time

Store the renewal time inside the session slot instead.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       | 15 +++++++++------
 include/linux/nfs_xdr.h |  2 +-
 2 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5e5cc5a5065f..14b39742b6e4 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -486,6 +486,7 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 
 static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
+	struct nfs4_slot *slot;
 	unsigned long timestamp;
 	struct nfs_client *clp;
 
@@ -502,12 +503,14 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 	if (!RPC_WAS_SENT(task))
 		goto out;
 
+	slot = res->sr_slot;
+
 	/* Check the SEQUENCE operation status */
 	switch (res->sr_status) {
 	case 0:
 		/* Update the slot's sequence and clientid lease timer */
-		++res->sr_slot->seq_nr;
-		timestamp = res->sr_renewal_time;
+		++slot->seq_nr;
+		timestamp = slot->renewal_time;
 		clp = res->sr_session->clp;
 		do_renew_lease(clp, timestamp);
 		/* Check sequence flags */
@@ -521,12 +524,12 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 		 */
 		dprintk("%s: slot=%td seq=%d: Operation in progress\n",
 			__func__,
-			res->sr_slot - res->sr_session->fc_slot_table.slots,
-			res->sr_slot->seq_nr);
+			slot - res->sr_session->fc_slot_table.slots,
+			slot->seq_nr);
 		goto out_retry;
 	default:
 		/* Just update the slot sequence no. */
-		++res->sr_slot->seq_nr;
+		++slot->seq_nr;
 	}
 out:
 	/* The session may be reset by one of the error handlers. */
@@ -637,6 +640,7 @@ int nfs41_setup_sequence(struct nfs4_session *session,
 
 	rpc_task_set_priority(task, RPC_PRIORITY_NORMAL);
 	slot = tbl->slots + slotid;
+	slot->renewal_time = jiffies;
 	args->sa_session = session;
 	args->sa_slotid = slotid;
 
@@ -644,7 +648,6 @@ int nfs41_setup_sequence(struct nfs4_session *session,
 
 	res->sr_session = session;
 	res->sr_slot = slot;
-	res->sr_renewal_time = jiffies;
 	res->sr_status_flags = 0;
 	/*
 	 * sr_status is only set in decode_sequence, and so will remain
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index a73ea89789d1..9cb1c63a70c2 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -187,6 +187,7 @@ struct nfs4_channel_attrs {
 
 /* nfs41 sessions slot seqid */
 struct nfs4_slot {
+	unsigned long		renewal_time;
 	u32		 	seq_nr;
 };
 
@@ -200,7 +201,6 @@ struct nfs4_sequence_res {
 	struct nfs4_session	*sr_session;
 	struct nfs4_slot	*sr_slot;	/* slot used to send request */
 	int			sr_status;	/* sequence operation status */
-	unsigned long		sr_renewal_time;
 	u32			sr_status_flags;
 };
 
-- 
cgit v1.2.3-55-g7522


From 50b1a7447749ab137c4827c7758836471e663582 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart
Date: Tue, 14 Aug 2012 12:17:55 +0200
Subject: fbdev: sh_mipi_dsi: Add channel field to platform data

The channel field stores the LCDC channel corresponding to the MIPI-DSI
transmitter. The information is currently obtained through the lcd_chan
field that will be removed.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
---
 include/video/sh_mipi_dsi.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/video/sh_mipi_dsi.h b/include/video/sh_mipi_dsi.h
index 06c67fbc4eee..eae71d94d241 100644
--- a/include/video/sh_mipi_dsi.h
+++ b/include/video/sh_mipi_dsi.h
@@ -48,6 +48,7 @@ struct sh_mobile_lcdc_chan_cfg;
 struct sh_mipi_dsi_info {
 	enum sh_mipi_dsi_data_fmt	data_format;
 	struct sh_mobile_lcdc_chan_cfg	*lcd_chan;
+	int				channel;
 	int				lane;
 	unsigned long			flags;
 	u32				clksrc;
-- 
cgit v1.2.3-55-g7522


From 074d0da486e2a5b8e80c35070ede7104f302f6da Mon Sep 17 00:00:00 2001
From: Laurent Pinchart
Date: Tue, 14 Aug 2012 12:21:17 +0200
Subject: fbdev: sh_mipi_dsi: Remove the unused sh_mipi_dsi_info lcd_chan field

The field is unused, remove it from the structure.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
---
 include/video/sh_mipi_dsi.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/video/sh_mipi_dsi.h b/include/video/sh_mipi_dsi.h
index eae71d94d241..a01f197e6ac1 100644
--- a/include/video/sh_mipi_dsi.h
+++ b/include/video/sh_mipi_dsi.h
@@ -25,8 +25,6 @@ enum sh_mipi_dsi_data_fmt {
 	MIPI_YUV420,
 };
 
-struct sh_mobile_lcdc_chan_cfg;
-
 #define SH_MIPI_DSI_HSABM	(1 << 0)
 #define SH_MIPI_DSI_HBPBM	(1 << 1)
 #define SH_MIPI_DSI_HFPBM	(1 << 2)
@@ -47,7 +45,6 @@ struct sh_mobile_lcdc_chan_cfg;
 
 struct sh_mipi_dsi_info {
 	enum sh_mipi_dsi_data_fmt	data_format;
-	struct sh_mobile_lcdc_chan_cfg	*lcd_chan;
 	int				channel;
 	int				lane;
 	unsigned long			flags;
-- 
cgit v1.2.3-55-g7522


From f70f4711df527b914486bf5381ec9a4911915c7d Mon Sep 17 00:00:00 2001
From: Laurent Pinchart
Date: Wed, 15 Aug 2012 18:13:26 +0200
Subject: fbdev: sh_mobile_lcdc: Remove unused get_brightness pdata callback

The callback isn't used anymore, remove it.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
---
 include/video/sh_mobile_lcdc.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/video/sh_mobile_lcdc.h b/include/video/sh_mobile_lcdc.h
index ff43ffc1aab2..2605fa8adb9c 100644
--- a/include/video/sh_mobile_lcdc.h
+++ b/include/video/sh_mobile_lcdc.h
@@ -163,7 +163,6 @@ struct sh_mobile_lcdc_bl_info {
 	const char *name;
 	int max_brightness;
 	int (*set_brightness)(int brightness);
-	int (*get_brightness)(void);
 };
 
 struct sh_mobile_lcdc_overlay_cfg {
-- 
cgit v1.2.3-55-g7522


From 22a8578fca5a47e643bb4f70c232d0ec84db9e4e Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia
Date: Sat, 10 Nov 2012 13:08:20 -0300
Subject: mtd: mtd_blkdevs: Replace request handler kthread with a workqueue

By replacing a kthread with a workqueue, the code is now a bit clearer.
There's also a slight reduction of code size (numbers apply for x86):
Before:
   text	   data	    bss	    dec	    hex	filename
   3248	     36	      0	   3284	    cd4	drivers/mtd/mtd_blkdevs.o

After:
   text	   data	    bss	    dec	    hex	filename
   3150	     36	      0	   3186	    c72	drivers/mtd/mtd_blkdevs.o

Due to lack of real hardware, tests have been performed on an emulated
environment with mtdswap and mtdblock over nandsim devices.
Some real testing should be done, before merging this patch.

Signed-off-by: Ezequiel Garcia <elezegarcia@gmail.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 drivers/mtd/mtd_blkdevs.c    | 47 ++++++++++++++------------------------------
 include/linux/mtd/blktrans.h |  4 +++-
 2 files changed, 18 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 26ef2a72bdae..5ad39bb5ab4c 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -32,7 +32,6 @@
 #include <linux/hdreg.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
-#include <linux/kthread.h>
 #include <asm/uaccess.h>
 
 #include "mtdcore.h"
@@ -121,16 +120,14 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 
 int mtd_blktrans_cease_background(struct mtd_blktrans_dev *dev)
 {
-	if (kthread_should_stop())
-		return 1;
-
 	return dev->bg_stop;
 }
 EXPORT_SYMBOL_GPL(mtd_blktrans_cease_background);
 
-static int mtd_blktrans_thread(void *arg)
+static void mtd_blktrans_work(struct work_struct *work)
 {
-	struct mtd_blktrans_dev *dev = arg;
+	struct mtd_blktrans_dev *dev =
+		container_of(work, struct mtd_blktrans_dev, work);
 	struct mtd_blktrans_ops *tr = dev->tr;
 	struct request_queue *rq = dev->rq;
 	struct request *req = NULL;
@@ -138,7 +135,7 @@ static int mtd_blktrans_thread(void *arg)
 
 	spin_lock_irq(rq->queue_lock);
 
-	while (!kthread_should_stop()) {
+	while (1) {
 		int res;
 
 		dev->bg_stop = false;
@@ -156,15 +153,7 @@ static int mtd_blktrans_thread(void *arg)
 				background_done = !dev->bg_stop;
 				continue;
 			}
-			set_current_state(TASK_INTERRUPTIBLE);
-
-			if (kthread_should_stop())
-				set_current_state(TASK_RUNNING);
-
-			spin_unlock_irq(rq->queue_lock);
-			schedule();
-			spin_lock_irq(rq->queue_lock);
-			continue;
+			break;
 		}
 
 		spin_unlock_irq(rq->queue_lock);
@@ -185,8 +174,6 @@ static int mtd_blktrans_thread(void *arg)
 		__blk_end_request_all(req, -EIO);
 
 	spin_unlock_irq(rq->queue_lock);
-
-	return 0;
 }
 
 static void mtd_blktrans_request(struct request_queue *rq)
@@ -199,10 +186,8 @@ static void mtd_blktrans_request(struct request_queue *rq)
 	if (!dev)
 		while ((req = blk_fetch_request(rq)) != NULL)
 			__blk_end_request_all(req, -ENODEV);
-	else {
-		dev->bg_stop = true;
-		wake_up_process(dev->thread);
-	}
+	else
+		queue_work(dev->wq, &dev->work);
 }
 
 static int blktrans_open(struct block_device *bdev, fmode_t mode)
@@ -437,14 +422,13 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 
 	gd->queue = new->rq;
 
-	/* Create processing thread */
-	/* TODO: workqueue ? */
-	new->thread = kthread_run(mtd_blktrans_thread, new,
-			"%s%d", tr->name, new->mtd->index);
-	if (IS_ERR(new->thread)) {
-		ret = PTR_ERR(new->thread);
+	/* Create processing workqueue */
+	new->wq = alloc_workqueue("%s%d", 0, 0,
+				  tr->name, new->mtd->index);
+	if (!new->wq)
 		goto error4;
-	}
+	INIT_WORK(&new->work, mtd_blktrans_work);
+
 	gd->driverfs_dev = &new->mtd->dev;
 
 	if (new->readonly)
@@ -484,9 +468,8 @@ int del_mtd_blktrans_dev(struct mtd_blktrans_dev *old)
 	/* Stop new requests to arrive */
 	del_gendisk(old->disk);
 
-
-	/* Stop the thread */
-	kthread_stop(old->thread);
+	/* Stop workqueue. This will perform any pending request. */
+	destroy_workqueue(old->wq);
 
 	/* Kill current requests */
 	spin_lock_irqsave(&old->queue_lock, flags);
diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h
index ed270bd2e4df..4eb0a50d0c55 100644
--- a/include/linux/mtd/blktrans.h
+++ b/include/linux/mtd/blktrans.h
@@ -23,6 +23,7 @@
 #include <linux/mutex.h>
 #include <linux/kref.h>
 #include <linux/sysfs.h>
+#include <linux/workqueue.h>
 
 struct hd_geometry;
 struct mtd_info;
@@ -43,7 +44,8 @@ struct mtd_blktrans_dev {
 	struct kref ref;
 	struct gendisk *disk;
 	struct attribute_group *disk_attributes;
-	struct task_struct *thread;
+	struct workqueue_struct *wq;
+	struct work_struct work;
 	struct request_queue *rq;
 	spinlock_t queue_lock;
 	void *priv;
-- 
cgit v1.2.3-55-g7522


From edd7eabc85e2f8d76a933b9639bebfe7f98861e4 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Wed, 14 Nov 2012 21:09:28 +0530
Subject: mfd: Add TI TPS80031 mfd core driver

TPS80031/ TPS80032 Fully Integrated Power Management with Power
Path and Battery Charger. The device provides five configurable
step-down converters, 11 general purpose LDOs, USB OTG Module,
ADC, RTC, 2 PWM, System Voltage Regulator/Battery Charger with
Power Path from USB, 32K clock generator.

Add the mfd core driver for TPS80031/TPS80032.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Reviwed-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/Kconfig          |  14 +
 drivers/mfd/Makefile         |   1 +
 drivers/mfd/tps80031.c       | 573 ++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/tps80031.h | 637 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 1225 insertions(+)
 create mode 100644 drivers/mfd/tps80031.c
 create mode 100644 include/linux/mfd/tps80031.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 59359a7a2493..ca633df7c330 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -265,6 +265,20 @@ config MFD_TPS65912_SPI
 	  If you say yes here you get support for the TPS65912 series of
 	  PM chips with SPI interface.
 
+config MFD_TPS80031
+	bool "TI TPS80031/TPS80032 Power Management chips"
+	depends on I2C=y && GENERIC_HARDIRQS
+	select MFD_CORE
+	select REGMAP_I2C
+	select IRQ_DOMAIN
+	help
+	  If you say yes here you get support for the Texas Instruments
+	  TPS80031/ TPS80032 Fully Integrated Power Management with Power
+	  Path and Battery Charger. The device provides five configurable
+	  step-down converters, 11 general purpose LDOs, USB OTG Module,
+	  ADC, RTC, 2 PWM, System Voltage Regulator/Battery Charger with
+	  Power Path from USB, 32K clock generator.
+
 config MENELAUS
 	bool "Texas Instruments TWL92330/Menelaus PM chip"
 	depends on I2C=y && ARCH_OMAP2
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 1c3ee7c76906..8072460e99d2 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -61,6 +61,7 @@ tps65912-objs                   := tps65912-core.o tps65912-irq.o
 obj-$(CONFIG_MFD_TPS65912)	+= tps65912.o
 obj-$(CONFIG_MFD_TPS65912_I2C)	+= tps65912-i2c.o
 obj-$(CONFIG_MFD_TPS65912_SPI)  += tps65912-spi.o
+obj-$(CONFIG_MFD_TPS80031)	+= tps80031.o
 obj-$(CONFIG_MENELAUS)		+= menelaus.o
 
 obj-$(CONFIG_TWL4030_CORE)	+= twl-core.o twl4030-irq.o twl6030-irq.o
diff --git a/drivers/mfd/tps80031.c b/drivers/mfd/tps80031.c
new file mode 100644
index 000000000000..f64005efa6fa
--- /dev/null
+++ b/drivers/mfd/tps80031.c
@@ -0,0 +1,573 @@
+/*
+ * tps80031.c -- TI TPS80031/TPS80032 mfd core driver.
+ *
+ * MFD core driver for TI TPS80031/TPS80032 Fully Integrated
+ * Power Management with Power Path and Battery Charger
+ *
+ * Copyright (c) 2012, NVIDIA Corporation.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind,
+ * whether express or implied; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ * 02111-1307, USA
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/tps80031.h>
+#include <linux/module.h>
+#include <linux/pm.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+static struct resource tps80031_rtc_resources[] = {
+	{
+		.start = TPS80031_INT_RTC_ALARM,
+		.end = TPS80031_INT_RTC_ALARM,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+/* TPS80031 sub mfd devices */
+static struct mfd_cell tps80031_cell[] = {
+	{
+		.name = "tps80031-pmic",
+	},
+	{
+		.name = "tps80031-clock",
+	},
+	{
+		.name = "tps80031-rtc",
+		.num_resources = ARRAY_SIZE(tps80031_rtc_resources),
+		.resources = tps80031_rtc_resources,
+	},
+	{
+		.name = "tps80031-gpadc",
+	},
+	{
+		.name = "tps80031-fuel-gauge",
+	},
+	{
+		.name = "tps80031-charger",
+	},
+};
+
+static int tps80031_slave_address[TPS80031_NUM_SLAVES] = {
+	TPS80031_I2C_ID0_ADDR,
+	TPS80031_I2C_ID1_ADDR,
+	TPS80031_I2C_ID2_ADDR,
+	TPS80031_I2C_ID3_ADDR,
+};
+
+struct tps80031_pupd_data {
+	u8	reg;
+	u8	pullup_bit;
+	u8	pulldown_bit;
+};
+
+#define TPS80031_IRQ(_reg, _mask)			\
+	{							\
+		.reg_offset = (TPS80031_INT_MSK_LINE_##_reg) -	\
+				TPS80031_INT_MSK_LINE_A,	\
+		.mask = BIT(_mask),				\
+	}
+
+static const struct regmap_irq tps80031_main_irqs[] = {
+	[TPS80031_INT_PWRON]		= TPS80031_IRQ(A, 0),
+	[TPS80031_INT_RPWRON]		= TPS80031_IRQ(A, 1),
+	[TPS80031_INT_SYS_VLOW]		= TPS80031_IRQ(A, 2),
+	[TPS80031_INT_RTC_ALARM]	= TPS80031_IRQ(A, 3),
+	[TPS80031_INT_RTC_PERIOD]	= TPS80031_IRQ(A, 4),
+	[TPS80031_INT_HOT_DIE]		= TPS80031_IRQ(A, 5),
+	[TPS80031_INT_VXX_SHORT]	= TPS80031_IRQ(A, 6),
+	[TPS80031_INT_SPDURATION]	= TPS80031_IRQ(A, 7),
+	[TPS80031_INT_WATCHDOG]		= TPS80031_IRQ(B, 0),
+	[TPS80031_INT_BAT]		= TPS80031_IRQ(B, 1),
+	[TPS80031_INT_SIM]		= TPS80031_IRQ(B, 2),
+	[TPS80031_INT_MMC]		= TPS80031_IRQ(B, 3),
+	[TPS80031_INT_RES]		= TPS80031_IRQ(B, 4),
+	[TPS80031_INT_GPADC_RT]		= TPS80031_IRQ(B, 5),
+	[TPS80031_INT_GPADC_SW2_EOC]	= TPS80031_IRQ(B, 6),
+	[TPS80031_INT_CC_AUTOCAL]	= TPS80031_IRQ(B, 7),
+	[TPS80031_INT_ID_WKUP]		= TPS80031_IRQ(C, 0),
+	[TPS80031_INT_VBUSS_WKUP]	= TPS80031_IRQ(C, 1),
+	[TPS80031_INT_ID]		= TPS80031_IRQ(C, 2),
+	[TPS80031_INT_VBUS]		= TPS80031_IRQ(C, 3),
+	[TPS80031_INT_CHRG_CTRL]	= TPS80031_IRQ(C, 4),
+	[TPS80031_INT_EXT_CHRG]		= TPS80031_IRQ(C, 5),
+	[TPS80031_INT_INT_CHRG]		= TPS80031_IRQ(C, 6),
+	[TPS80031_INT_RES2]		= TPS80031_IRQ(C, 7),
+};
+
+static struct regmap_irq_chip tps80031_irq_chip = {
+	.name = "tps80031",
+	.irqs = tps80031_main_irqs,
+	.num_irqs = ARRAY_SIZE(tps80031_main_irqs),
+	.num_regs = 3,
+	.status_base = TPS80031_INT_STS_A,
+	.mask_base = TPS80031_INT_MSK_LINE_A,
+};
+
+#define PUPD_DATA(_reg, _pulldown_bit, _pullup_bit)	\
+	{						\
+		.reg = TPS80031_CFG_INPUT_PUPD##_reg,	\
+		.pulldown_bit = _pulldown_bit,		\
+		.pullup_bit = _pullup_bit,		\
+	}
+
+static const struct tps80031_pupd_data tps80031_pupds[] = {
+	[TPS80031_PREQ1]		= PUPD_DATA(1, BIT(0),	BIT(1)),
+	[TPS80031_PREQ2A]		= PUPD_DATA(1, BIT(2),	BIT(3)),
+	[TPS80031_PREQ2B]		= PUPD_DATA(1, BIT(4),	BIT(5)),
+	[TPS80031_PREQ2C]		= PUPD_DATA(1, BIT(6),	BIT(7)),
+	[TPS80031_PREQ3]		= PUPD_DATA(2, BIT(0),	BIT(1)),
+	[TPS80031_NRES_WARM]		= PUPD_DATA(2, 0,	BIT(2)),
+	[TPS80031_PWM_FORCE]		= PUPD_DATA(2, BIT(5),	0),
+	[TPS80031_CHRG_EXT_CHRG_STATZ]	= PUPD_DATA(2, 0,	BIT(6)),
+	[TPS80031_SIM]			= PUPD_DATA(3, BIT(0),	BIT(1)),
+	[TPS80031_MMC]			= PUPD_DATA(3, BIT(2),	BIT(3)),
+	[TPS80031_GPADC_START]		= PUPD_DATA(3, BIT(4),	0),
+	[TPS80031_DVSI2C_SCL]		= PUPD_DATA(4, 0,	BIT(0)),
+	[TPS80031_DVSI2C_SDA]		= PUPD_DATA(4, 0,	BIT(1)),
+	[TPS80031_CTLI2C_SCL]		= PUPD_DATA(4, 0,	BIT(2)),
+	[TPS80031_CTLI2C_SDA]		= PUPD_DATA(4, 0,	BIT(3)),
+};
+static struct tps80031 *tps80031_power_off_dev;
+
+int tps80031_ext_power_req_config(struct device *dev,
+		unsigned long ext_ctrl_flag, int preq_bit,
+		int state_reg_add, int trans_reg_add)
+{
+	u8 res_ass_reg = 0;
+	int preq_mask_bit = 0;
+	int ret;
+
+	if (!(ext_ctrl_flag & TPS80031_EXT_PWR_REQ))
+		return 0;
+
+	if (ext_ctrl_flag & TPS80031_PWR_REQ_INPUT_PREQ1) {
+		res_ass_reg = TPS80031_PREQ1_RES_ASS_A + (preq_bit >> 3);
+		preq_mask_bit = 5;
+	} else if (ext_ctrl_flag & TPS80031_PWR_REQ_INPUT_PREQ2) {
+		res_ass_reg = TPS80031_PREQ2_RES_ASS_A + (preq_bit >> 3);
+		preq_mask_bit = 6;
+	} else if (ext_ctrl_flag & TPS80031_PWR_REQ_INPUT_PREQ3) {
+		res_ass_reg = TPS80031_PREQ3_RES_ASS_A + (preq_bit >> 3);
+		preq_mask_bit = 7;
+	}
+
+	/* Configure REQ_ASS registers */
+	ret = tps80031_set_bits(dev, TPS80031_SLAVE_ID1, res_ass_reg,
+					BIT(preq_bit & 0x7));
+	if (ret < 0) {
+		dev_err(dev, "reg 0x%02x setbit failed, err = %d\n",
+				res_ass_reg, ret);
+		return ret;
+	}
+
+	/* Unmask the PREQ */
+	ret = tps80031_clr_bits(dev, TPS80031_SLAVE_ID1,
+			TPS80031_PHOENIX_MSK_TRANSITION, BIT(preq_mask_bit));
+	if (ret < 0) {
+		dev_err(dev, "reg 0x%02x clrbit failed, err = %d\n",
+			TPS80031_PHOENIX_MSK_TRANSITION, ret);
+		return ret;
+	}
+
+	/* Switch regulator control to resource now */
+	if (ext_ctrl_flag & (TPS80031_PWR_REQ_INPUT_PREQ2 |
+					TPS80031_PWR_REQ_INPUT_PREQ3)) {
+		ret = tps80031_update(dev, TPS80031_SLAVE_ID1, state_reg_add,
+						0x0, TPS80031_STATE_MASK);
+		if (ret < 0)
+			dev_err(dev, "reg 0x%02x update failed, err = %d\n",
+				state_reg_add, ret);
+	} else {
+		ret = tps80031_update(dev, TPS80031_SLAVE_ID1, trans_reg_add,
+				TPS80031_TRANS_SLEEP_OFF,
+				TPS80031_TRANS_SLEEP_MASK);
+		if (ret < 0)
+			dev_err(dev, "reg 0x%02x update failed, err = %d\n",
+				trans_reg_add, ret);
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tps80031_ext_power_req_config);
+
+static void tps80031_power_off(void)
+{
+	dev_info(tps80031_power_off_dev->dev, "switching off PMU\n");
+	tps80031_write(tps80031_power_off_dev->dev, TPS80031_SLAVE_ID1,
+				TPS80031_PHOENIX_DEV_ON, TPS80031_DEVOFF);
+}
+
+static void tps80031_pupd_init(struct tps80031 *tps80031,
+			       struct tps80031_platform_data *pdata)
+{
+	struct tps80031_pupd_init_data *pupd_init_data = pdata->pupd_init_data;
+	int data_size = pdata->pupd_init_data_size;
+	int i;
+
+	for (i = 0; i < data_size; ++i) {
+		struct tps80031_pupd_init_data *pupd_init = &pupd_init_data[i];
+		const struct tps80031_pupd_data *pupd =
+			&tps80031_pupds[pupd_init->input_pin];
+		u8 update_value = 0;
+		u8 update_mask = pupd->pulldown_bit | pupd->pullup_bit;
+
+		if (pupd_init->setting == TPS80031_PUPD_PULLDOWN)
+			update_value = pupd->pulldown_bit;
+		else if (pupd_init->setting == TPS80031_PUPD_PULLUP)
+			update_value = pupd->pullup_bit;
+
+		tps80031_update(tps80031->dev, TPS80031_SLAVE_ID1, pupd->reg,
+				update_value, update_mask);
+	}
+}
+
+static int tps80031_init_ext_control(struct tps80031 *tps80031,
+			struct tps80031_platform_data *pdata)
+{
+	struct device *dev = tps80031->dev;
+	int ret;
+	int i;
+
+	/* Clear all external control for this rail */
+	for (i = 0; i < 9; ++i) {
+		ret = tps80031_write(dev, TPS80031_SLAVE_ID1,
+				TPS80031_PREQ1_RES_ASS_A + i, 0);
+		if (ret < 0) {
+			dev_err(dev, "reg 0x%02x write failed, err = %d\n",
+				TPS80031_PREQ1_RES_ASS_A + i, ret);
+			return ret;
+		}
+	}
+
+	/* Mask the PREQ */
+	ret = tps80031_set_bits(dev, TPS80031_SLAVE_ID1,
+			TPS80031_PHOENIX_MSK_TRANSITION, 0x7 << 5);
+	if (ret < 0) {
+		dev_err(dev, "reg 0x%02x set_bits failed, err = %d\n",
+			TPS80031_PHOENIX_MSK_TRANSITION, ret);
+		return ret;
+	}
+	return ret;
+}
+
+static int __devinit tps80031_irq_init(struct tps80031 *tps80031, int irq,
+				int irq_base)
+{
+	struct device *dev = tps80031->dev;
+	int i, ret;
+
+	/*
+	 * The MASK register used for updating status register when
+	 * interrupt occurs and LINE register used to pass the status
+	 * to actual interrupt line.  As per datasheet:
+	 * When INT_MSK_LINE [i] is set to 1, the associated interrupt
+	 * number i is INT line masked, which means that no interrupt is
+	 * generated on the INT line.
+	 * When INT_MSK_LINE [i] is set to 0, the associated interrupt
+	 * number i is  line enabled: An interrupt is generated on the
+	 * INT line.
+	 * In any case, the INT_STS [i] status bit may or may not be updated,
+	 * only linked to the INT_MSK_STS [i] configuration register bit.
+	 *
+	 * When INT_MSK_STS [i] is set to 1, the associated interrupt number
+	 * i is status masked, which means that no interrupt is stored in
+	 * the INT_STS[i] status bit. Note that no interrupt number i is
+	 * generated on the INT line, even if the INT_MSK_LINE [i] register
+	 * bit is set to 0.
+	 * When INT_MSK_STS [i] is set to 0, the associated interrupt number i
+	 * is status enabled: An interrupt status is updated in the INT_STS [i]
+	 * register. The interrupt may or may not be generated on the INT line,
+	 * depending on the INT_MSK_LINE [i] configuration register bit.
+	 */
+	for (i = 0; i < 3; i++)
+		tps80031_write(dev, TPS80031_SLAVE_ID2,
+				TPS80031_INT_MSK_STS_A + i, 0x00);
+
+	ret = regmap_add_irq_chip(tps80031->regmap[TPS80031_SLAVE_ID2], irq,
+			IRQF_ONESHOT, irq_base,
+			&tps80031_irq_chip, &tps80031->irq_data);
+	if (ret < 0) {
+		dev_err(dev, "add irq failed, err = %d\n", ret);
+		return ret;
+	}
+	return ret;
+}
+
+static bool rd_wr_reg_id0(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case TPS80031_SMPS1_CFG_FORCE ... TPS80031_SMPS2_CFG_VOLTAGE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool rd_wr_reg_id1(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case TPS80031_SECONDS_REG ... TPS80031_RTC_RESET_STATUS_REG:
+	case TPS80031_VALIDITY0 ... TPS80031_VALIDITY7:
+	case TPS80031_PHOENIX_START_CONDITION ... TPS80031_KEY_PRESS_DUR_CFG:
+	case TPS80031_SMPS4_CFG_TRANS ... TPS80031_SMPS3_CFG_VOLTAGE:
+	case TPS80031_BROADCAST_ADDR_ALL ... TPS80031_BROADCAST_ADDR_CLK_RST:
+	case TPS80031_VANA_CFG_TRANS ... TPS80031_LDO7_CFG_VOLTAGE:
+	case TPS80031_REGEN1_CFG_TRANS ... TPS80031_TMP_CFG_STATE:
+	case TPS80031_PREQ1_RES_ASS_A ... TPS80031_PREQ3_RES_ASS_C:
+	case TPS80031_SMPS_OFFSET ... TPS80031_BATDEBOUNCING:
+	case TPS80031_CFG_INPUT_PUPD1 ... TPS80031_CFG_SMPS_PD:
+	case TPS80031_BACKUP_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool is_volatile_reg_id1(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case TPS80031_SMPS4_CFG_TRANS ... TPS80031_SMPS3_CFG_VOLTAGE:
+	case TPS80031_VANA_CFG_TRANS ... TPS80031_LDO7_CFG_VOLTAGE:
+	case TPS80031_REGEN1_CFG_TRANS ... TPS80031_TMP_CFG_STATE:
+	case TPS80031_PREQ1_RES_ASS_A ... TPS80031_PREQ3_RES_ASS_C:
+	case TPS80031_SMPS_OFFSET ... TPS80031_BATDEBOUNCING:
+	case TPS80031_CFG_INPUT_PUPD1 ... TPS80031_CFG_SMPS_PD:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool rd_wr_reg_id2(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case TPS80031_USB_VENDOR_ID_LSB ... TPS80031_USB_OTG_REVISION:
+	case TPS80031_GPADC_CTRL ... TPS80031_CTRL_P1:
+	case TPS80031_RTCH0_LSB ... TPS80031_GPCH0_MSB:
+	case TPS80031_TOGGLE1 ... TPS80031_VIBMODE:
+	case TPS80031_PWM1ON ... TPS80031_PWM2OFF:
+	case TPS80031_FG_REG_00 ... TPS80031_FG_REG_11:
+	case TPS80031_INT_STS_A ... TPS80031_INT_MSK_STS_C:
+	case TPS80031_CONTROLLER_CTRL2 ... TPS80031_LED_PWM_CTRL2:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool rd_wr_reg_id3(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case TPS80031_GPADC_TRIM0 ... TPS80031_GPADC_TRIM18:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config tps80031_regmap_configs[] = {
+	{
+		.reg_bits = 8,
+		.val_bits = 8,
+		.writeable_reg = rd_wr_reg_id0,
+		.readable_reg = rd_wr_reg_id0,
+		.max_register = TPS80031_MAX_REGISTER,
+	},
+	{
+		.reg_bits = 8,
+		.val_bits = 8,
+		.writeable_reg = rd_wr_reg_id1,
+		.readable_reg = rd_wr_reg_id1,
+		.volatile_reg = is_volatile_reg_id1,
+		.max_register = TPS80031_MAX_REGISTER,
+	},
+	{
+		.reg_bits = 8,
+		.val_bits = 8,
+		.writeable_reg = rd_wr_reg_id2,
+		.readable_reg = rd_wr_reg_id2,
+		.max_register = TPS80031_MAX_REGISTER,
+	},
+	{
+		.reg_bits = 8,
+		.val_bits = 8,
+		.writeable_reg = rd_wr_reg_id3,
+		.readable_reg = rd_wr_reg_id3,
+		.max_register = TPS80031_MAX_REGISTER,
+	},
+};
+
+static int __devinit tps80031_probe(struct i2c_client *client,
+					const struct i2c_device_id *id)
+{
+	struct tps80031_platform_data *pdata = client->dev.platform_data;
+	struct tps80031 *tps80031;
+	int ret;
+	uint8_t es_version;
+	uint8_t ep_ver;
+	int i;
+
+	if (!pdata) {
+		dev_err(&client->dev, "tps80031 requires platform data\n");
+		return -EINVAL;
+	}
+
+	tps80031 = devm_kzalloc(&client->dev, sizeof(*tps80031), GFP_KERNEL);
+	if (!tps80031) {
+		dev_err(&client->dev, "Malloc failed for tps80031\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < TPS80031_NUM_SLAVES; i++) {
+		if (tps80031_slave_address[i] == client->addr)
+			tps80031->clients[i] = client;
+		else
+			tps80031->clients[i] = i2c_new_dummy(client->adapter,
+						tps80031_slave_address[i]);
+		if (!tps80031->clients[i]) {
+			dev_err(&client->dev, "can't attach client %d\n", i);
+			ret = -ENOMEM;
+			goto fail_client_reg;
+		}
+
+		i2c_set_clientdata(tps80031->clients[i], tps80031);
+		tps80031->regmap[i] = devm_regmap_init_i2c(tps80031->clients[i],
+					&tps80031_regmap_configs[i]);
+		if (IS_ERR(tps80031->regmap[i])) {
+			ret = PTR_ERR(tps80031->regmap[i]);
+			dev_err(&client->dev,
+				"regmap %d init failed, err %d\n", i, ret);
+			goto fail_client_reg;
+		}
+	}
+
+	ret = tps80031_read(&client->dev, TPS80031_SLAVE_ID3,
+			TPS80031_JTAGVERNUM, &es_version);
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"Silicon version number read failed: %d\n", ret);
+		goto fail_client_reg;
+	}
+
+	ret = tps80031_read(&client->dev, TPS80031_SLAVE_ID3,
+			TPS80031_EPROM_REV, &ep_ver);
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"Silicon eeprom version read failed: %d\n", ret);
+		goto fail_client_reg;
+	}
+
+	dev_info(&client->dev, "ES version 0x%02x and EPROM version 0x%02x\n",
+					es_version, ep_ver);
+	tps80031->es_version = es_version;
+	tps80031->dev = &client->dev;
+	i2c_set_clientdata(client, tps80031);
+	tps80031->chip_info = id->driver_data;
+
+	ret = tps80031_irq_init(tps80031, client->irq, pdata->irq_base);
+	if (ret) {
+		dev_err(&client->dev, "IRQ init failed: %d\n", ret);
+		goto fail_client_reg;
+	}
+
+	tps80031_pupd_init(tps80031, pdata);
+
+	tps80031_init_ext_control(tps80031, pdata);
+
+	ret = mfd_add_devices(tps80031->dev, -1,
+			tps80031_cell, ARRAY_SIZE(tps80031_cell),
+			NULL, 0,
+			regmap_irq_get_domain(tps80031->irq_data));
+	if (ret < 0) {
+		dev_err(&client->dev, "mfd_add_devices failed: %d\n", ret);
+		goto fail_mfd_add;
+	}
+
+	if (pdata->use_power_off && !pm_power_off) {
+		tps80031_power_off_dev = tps80031;
+		pm_power_off = tps80031_power_off;
+	}
+	return 0;
+
+fail_mfd_add:
+	regmap_del_irq_chip(client->irq, tps80031->irq_data);
+
+fail_client_reg:
+	for (i = 0; i < TPS80031_NUM_SLAVES; i++) {
+		if (tps80031->clients[i]  && (tps80031->clients[i] != client))
+			i2c_unregister_device(tps80031->clients[i]);
+	}
+	return ret;
+}
+
+static int __devexit tps80031_remove(struct i2c_client *client)
+{
+	struct tps80031 *tps80031 = i2c_get_clientdata(client);
+	int i;
+
+	if (tps80031_power_off_dev == tps80031) {
+		tps80031_power_off_dev = NULL;
+		pm_power_off = NULL;
+	}
+
+	mfd_remove_devices(tps80031->dev);
+
+	regmap_del_irq_chip(client->irq, tps80031->irq_data);
+
+	for (i = 0; i < TPS80031_NUM_SLAVES; i++) {
+		if (tps80031->clients[i] != client)
+			i2c_unregister_device(tps80031->clients[i]);
+	}
+	return 0;
+}
+
+static const struct i2c_device_id tps80031_id_table[] = {
+	{ "tps80031", TPS80031 },
+	{ "tps80032", TPS80032 },
+};
+MODULE_DEVICE_TABLE(i2c, tps80031_id_table);
+
+static struct i2c_driver tps80031_driver = {
+	.driver	= {
+		.name	= "tps80031",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= tps80031_probe,
+	.remove		= __devexit_p(tps80031_remove),
+	.id_table	= tps80031_id_table,
+};
+
+static int __init tps80031_init(void)
+{
+	return i2c_add_driver(&tps80031_driver);
+}
+subsys_initcall(tps80031_init);
+
+static void __exit tps80031_exit(void)
+{
+	i2c_del_driver(&tps80031_driver);
+}
+module_exit(tps80031_exit);
+
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_DESCRIPTION("TPS80031 core driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/tps80031.h b/include/linux/mfd/tps80031.h
new file mode 100644
index 000000000000..2c75c9c9318f
--- /dev/null
+++ b/include/linux/mfd/tps80031.h
@@ -0,0 +1,637 @@
+/*
+ * tps80031.h -- TI TPS80031 and TI TPS80032 PMIC driver.
+ *
+ * Copyright (c) 2012, NVIDIA Corporation.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind,
+ * whether express or implied; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ * 02111-1307, USA
+ */
+
+#ifndef __LINUX_MFD_TPS80031_H
+#define __LINUX_MFD_TPS80031_H
+
+#include <linux/device.h>
+#include <linux/regmap.h>
+
+/* Pull-ups/Pull-downs */
+#define TPS80031_CFG_INPUT_PUPD1			0xF0
+#define TPS80031_CFG_INPUT_PUPD2			0xF1
+#define TPS80031_CFG_INPUT_PUPD3			0xF2
+#define TPS80031_CFG_INPUT_PUPD4			0xF3
+#define TPS80031_CFG_LDO_PD1				0xF4
+#define TPS80031_CFG_LDO_PD2				0xF5
+#define TPS80031_CFG_SMPS_PD				0xF6
+
+/* Real Time Clock */
+#define TPS80031_SECONDS_REG				0x00
+#define TPS80031_MINUTES_REG				0x01
+#define TPS80031_HOURS_REG				0x02
+#define TPS80031_DAYS_REG				0x03
+#define TPS80031_MONTHS_REG				0x04
+#define TPS80031_YEARS_REG				0x05
+#define TPS80031_WEEKS_REG				0x06
+#define TPS80031_ALARM_SECONDS_REG			0x08
+#define TPS80031_ALARM_MINUTES_REG			0x09
+#define TPS80031_ALARM_HOURS_REG			0x0A
+#define TPS80031_ALARM_DAYS_REG				0x0B
+#define TPS80031_ALARM_MONTHS_REG			0x0C
+#define TPS80031_ALARM_YEARS_REG			0x0D
+#define TPS80031_RTC_CTRL_REG				0x10
+#define TPS80031_RTC_STATUS_REG				0x11
+#define TPS80031_RTC_INTERRUPTS_REG			0x12
+#define TPS80031_RTC_COMP_LSB_REG			0x13
+#define TPS80031_RTC_COMP_MSB_REG			0x14
+#define TPS80031_RTC_RESET_STATUS_REG			0x16
+
+/*PMC Master Module */
+#define TPS80031_PHOENIX_START_CONDITION		0x1F
+#define TPS80031_PHOENIX_MSK_TRANSITION			0x20
+#define TPS80031_STS_HW_CONDITIONS			0x21
+#define TPS80031_PHOENIX_LAST_TURNOFF_STS		0x22
+#define TPS80031_VSYSMIN_LO_THRESHOLD			0x23
+#define TPS80031_VSYSMIN_HI_THRESHOLD			0x24
+#define TPS80031_PHOENIX_DEV_ON				0x25
+#define TPS80031_STS_PWR_GRP_STATE			0x27
+#define TPS80031_PH_CFG_VSYSLOW				0x28
+#define TPS80031_PH_STS_BOOT				0x29
+#define TPS80031_PHOENIX_SENS_TRANSITION		0x2A
+#define TPS80031_PHOENIX_SEQ_CFG			0x2B
+#define TPS80031_PRIMARY_WATCHDOG_CFG			0X2C
+#define TPS80031_KEY_PRESS_DUR_CFG			0X2D
+#define TPS80031_SMPS_LDO_SHORT_STS			0x2E
+
+/* PMC Slave Module - Broadcast */
+#define TPS80031_BROADCAST_ADDR_ALL			0x31
+#define TPS80031_BROADCAST_ADDR_REF			0x32
+#define TPS80031_BROADCAST_ADDR_PROV			0x33
+#define TPS80031_BROADCAST_ADDR_CLK_RST			0x34
+
+/* PMC Slave Module  SMPS Regulators */
+#define TPS80031_SMPS4_CFG_TRANS			0x41
+#define TPS80031_SMPS4_CFG_STATE			0x42
+#define TPS80031_SMPS4_CFG_VOLTAGE			0x44
+#define TPS80031_VIO_CFG_TRANS				0x47
+#define TPS80031_VIO_CFG_STATE				0x48
+#define TPS80031_VIO_CFG_FORCE				0x49
+#define TPS80031_VIO_CFG_VOLTAGE			0x4A
+#define TPS80031_VIO_CFG_STEP				0x48
+#define TPS80031_SMPS1_CFG_TRANS			0x53
+#define TPS80031_SMPS1_CFG_STATE			0x54
+#define TPS80031_SMPS1_CFG_FORCE			0x55
+#define TPS80031_SMPS1_CFG_VOLTAGE			0x56
+#define TPS80031_SMPS1_CFG_STEP				0x57
+#define TPS80031_SMPS2_CFG_TRANS			0x59
+#define TPS80031_SMPS2_CFG_STATE			0x5A
+#define TPS80031_SMPS2_CFG_FORCE			0x5B
+#define TPS80031_SMPS2_CFG_VOLTAGE			0x5C
+#define TPS80031_SMPS2_CFG_STEP				0x5D
+#define TPS80031_SMPS3_CFG_TRANS			0x65
+#define TPS80031_SMPS3_CFG_STATE			0x66
+#define TPS80031_SMPS3_CFG_VOLTAGE			0x68
+
+/* PMC Slave Module  LDO Regulators */
+#define TPS80031_VANA_CFG_TRANS				0x81
+#define TPS80031_VANA_CFG_STATE				0x82
+#define TPS80031_VANA_CFG_VOLTAGE			0x83
+#define TPS80031_LDO2_CFG_TRANS				0x85
+#define TPS80031_LDO2_CFG_STATE				0x86
+#define TPS80031_LDO2_CFG_VOLTAGE			0x87
+#define TPS80031_LDO4_CFG_TRANS				0x89
+#define TPS80031_LDO4_CFG_STATE				0x8A
+#define TPS80031_LDO4_CFG_VOLTAGE			0x8B
+#define TPS80031_LDO3_CFG_TRANS				0x8D
+#define TPS80031_LDO3_CFG_STATE				0x8E
+#define TPS80031_LDO3_CFG_VOLTAGE			0x8F
+#define TPS80031_LDO6_CFG_TRANS				0x91
+#define TPS80031_LDO6_CFG_STATE				0x92
+#define TPS80031_LDO6_CFG_VOLTAGE			0x93
+#define TPS80031_LDOLN_CFG_TRANS			0x95
+#define TPS80031_LDOLN_CFG_STATE			0x96
+#define TPS80031_LDOLN_CFG_VOLTAGE			0x97
+#define TPS80031_LDO5_CFG_TRANS				0x99
+#define TPS80031_LDO5_CFG_STATE				0x9A
+#define TPS80031_LDO5_CFG_VOLTAGE			0x9B
+#define TPS80031_LDO1_CFG_TRANS				0x9D
+#define TPS80031_LDO1_CFG_STATE				0x9E
+#define TPS80031_LDO1_CFG_VOLTAGE			0x9F
+#define TPS80031_LDOUSB_CFG_TRANS			0xA1
+#define TPS80031_LDOUSB_CFG_STATE			0xA2
+#define TPS80031_LDOUSB_CFG_VOLTAGE			0xA3
+#define TPS80031_LDO7_CFG_TRANS				0xA5
+#define TPS80031_LDO7_CFG_STATE				0xA6
+#define TPS80031_LDO7_CFG_VOLTAGE			0xA7
+
+/* PMC Slave Module  External Control */
+#define TPS80031_REGEN1_CFG_TRANS			0xAE
+#define TPS80031_REGEN1_CFG_STATE			0xAF
+#define TPS80031_REGEN2_CFG_TRANS			0xB1
+#define TPS80031_REGEN2_CFG_STATE			0xB2
+#define TPS80031_SYSEN_CFG_TRANS			0xB4
+#define TPS80031_SYSEN_CFG_STATE			0xB5
+
+/* PMC Slave Module  Internal Control */
+#define TPS80031_NRESPWRON_CFG_TRANS			0xB7
+#define TPS80031_NRESPWRON_CFG_STATE			0xB8
+#define TPS80031_CLK32KAO_CFG_TRANS			0xBA
+#define TPS80031_CLK32KAO_CFG_STATE			0xBB
+#define TPS80031_CLK32KG_CFG_TRANS			0xBD
+#define TPS80031_CLK32KG_CFG_STATE			0xBE
+#define TPS80031_CLK32KAUDIO_CFG_TRANS			0xC0
+#define TPS80031_CLK32KAUDIO_CFG_STATE			0xC1
+#define TPS80031_VRTC_CFG_TRANS				0xC3
+#define TPS80031_VRTC_CFG_STATE				0xC4
+#define TPS80031_BIAS_CFG_TRANS				0xC6
+#define TPS80031_BIAS_CFG_STATE				0xC7
+#define TPS80031_VSYSMIN_HI_CFG_TRANS			0xC9
+#define TPS80031_VSYSMIN_HI_CFG_STATE			0xCA
+#define TPS80031_RC6MHZ_CFG_TRANS			0xCC
+#define TPS80031_RC6MHZ_CFG_STATE			0xCD
+#define TPS80031_TMP_CFG_TRANS				0xCF
+#define TPS80031_TMP_CFG_STATE				0xD0
+
+/* PMC Slave Module  resources assignment */
+#define TPS80031_PREQ1_RES_ASS_A			0xD7
+#define TPS80031_PREQ1_RES_ASS_B			0xD8
+#define TPS80031_PREQ1_RES_ASS_C			0xD9
+#define TPS80031_PREQ2_RES_ASS_A			0xDA
+#define TPS80031_PREQ2_RES_ASS_B			0xDB
+#define TPS80031_PREQ2_RES_ASS_C			0xDC
+#define TPS80031_PREQ3_RES_ASS_A			0xDD
+#define TPS80031_PREQ3_RES_ASS_B			0xDE
+#define TPS80031_PREQ3_RES_ASS_C			0xDF
+
+/* PMC Slave Module  Miscellaneous */
+#define TPS80031_SMPS_OFFSET				0xE0
+#define TPS80031_SMPS_MULT				0xE3
+#define TPS80031_MISC1					0xE4
+#define TPS80031_MISC2					0xE5
+#define TPS80031_BBSPOR_CFG				0xE6
+#define TPS80031_TMP_CFG				0xE7
+
+/* Battery Charging Controller and Indicator LED */
+#define TPS80031_CONTROLLER_CTRL2			0xDA
+#define TPS80031_CONTROLLER_VSEL_COMP			0xDB
+#define TPS80031_CHARGERUSB_VSYSREG			0xDC
+#define TPS80031_CHARGERUSB_VICHRG_PC			0xDD
+#define TPS80031_LINEAR_CHRG_STS			0xDE
+#define TPS80031_CONTROLLER_INT_MASK			0xE0
+#define TPS80031_CONTROLLER_CTRL1			0xE1
+#define TPS80031_CONTROLLER_WDG				0xE2
+#define TPS80031_CONTROLLER_STAT1			0xE3
+#define TPS80031_CHARGERUSB_INT_STATUS			0xE4
+#define TPS80031_CHARGERUSB_INT_MASK			0xE5
+#define TPS80031_CHARGERUSB_STATUS_INT1			0xE6
+#define TPS80031_CHARGERUSB_STATUS_INT2			0xE7
+#define TPS80031_CHARGERUSB_CTRL1			0xE8
+#define TPS80031_CHARGERUSB_CTRL2			0xE9
+#define TPS80031_CHARGERUSB_CTRL3			0xEA
+#define TPS80031_CHARGERUSB_STAT1			0xEB
+#define TPS80031_CHARGERUSB_VOREG			0xEC
+#define TPS80031_CHARGERUSB_VICHRG			0xED
+#define TPS80031_CHARGERUSB_CINLIMIT			0xEE
+#define TPS80031_CHARGERUSB_CTRLLIMIT1			0xEF
+#define TPS80031_CHARGERUSB_CTRLLIMIT2			0xF0
+#define TPS80031_LED_PWM_CTRL1				0xF4
+#define TPS80031_LED_PWM_CTRL2				0xF5
+
+/* USB On-The-Go  */
+#define TPS80031_BACKUP_REG				0xFA
+#define TPS80031_USB_VENDOR_ID_LSB			0x00
+#define TPS80031_USB_VENDOR_ID_MSB			0x01
+#define TPS80031_USB_PRODUCT_ID_LSB			0x02
+#define TPS80031_USB_PRODUCT_ID_MSB			0x03
+#define TPS80031_USB_VBUS_CTRL_SET			0x04
+#define TPS80031_USB_VBUS_CTRL_CLR			0x05
+#define TPS80031_USB_ID_CTRL_SET			0x06
+#define TPS80031_USB_ID_CTRL_CLR			0x07
+#define TPS80031_USB_VBUS_INT_SRC			0x08
+#define TPS80031_USB_VBUS_INT_LATCH_SET			0x09
+#define TPS80031_USB_VBUS_INT_LATCH_CLR			0x0A
+#define TPS80031_USB_VBUS_INT_EN_LO_SET			0x0B
+#define TPS80031_USB_VBUS_INT_EN_LO_CLR			0x0C
+#define TPS80031_USB_VBUS_INT_EN_HI_SET			0x0D
+#define TPS80031_USB_VBUS_INT_EN_HI_CLR			0x0E
+#define TPS80031_USB_ID_INT_SRC				0x0F
+#define TPS80031_USB_ID_INT_LATCH_SET			0x10
+#define TPS80031_USB_ID_INT_LATCH_CLR			0x11
+#define TPS80031_USB_ID_INT_EN_LO_SET			0x12
+#define TPS80031_USB_ID_INT_EN_LO_CLR			0x13
+#define TPS80031_USB_ID_INT_EN_HI_SET			0x14
+#define TPS80031_USB_ID_INT_EN_HI_CLR			0x15
+#define TPS80031_USB_OTG_ADP_CTRL			0x16
+#define TPS80031_USB_OTG_ADP_HIGH			0x17
+#define TPS80031_USB_OTG_ADP_LOW			0x18
+#define TPS80031_USB_OTG_ADP_RISE			0x19
+#define TPS80031_USB_OTG_REVISION			0x1A
+
+/* Gas Gauge */
+#define TPS80031_FG_REG_00				0xC0
+#define TPS80031_FG_REG_01				0xC1
+#define TPS80031_FG_REG_02				0xC2
+#define TPS80031_FG_REG_03				0xC3
+#define TPS80031_FG_REG_04				0xC4
+#define TPS80031_FG_REG_05				0xC5
+#define TPS80031_FG_REG_06				0xC6
+#define TPS80031_FG_REG_07				0xC7
+#define TPS80031_FG_REG_08				0xC8
+#define TPS80031_FG_REG_09				0xC9
+#define TPS80031_FG_REG_10				0xCA
+#define TPS80031_FG_REG_11				0xCB
+
+/* General Purpose ADC */
+#define TPS80031_GPADC_CTRL				0x2E
+#define TPS80031_GPADC_CTRL2				0x2F
+#define TPS80031_RTSELECT_LSB				0x32
+#define TPS80031_RTSELECT_ISB				0x33
+#define TPS80031_RTSELECT_MSB				0x34
+#define TPS80031_GPSELECT_ISB				0x35
+#define TPS80031_CTRL_P1				0x36
+#define TPS80031_RTCH0_LSB				0x37
+#define TPS80031_RTCH0_MSB				0x38
+#define TPS80031_RTCH1_LSB				0x39
+#define TPS80031_RTCH1_MSB				0x3A
+#define TPS80031_GPCH0_LSB				0x3B
+#define TPS80031_GPCH0_MSB				0x3C
+
+/* SIM, MMC and Battery Detection */
+#define TPS80031_SIMDEBOUNCING				0xEB
+#define TPS80031_SIMCTRL				0xEC
+#define TPS80031_MMCDEBOUNCING				0xED
+#define TPS80031_MMCCTRL				0xEE
+#define TPS80031_BATDEBOUNCING				0xEF
+
+/* Vibrator Driver and PWMs */
+#define TPS80031_VIBCTRL				0x9B
+#define TPS80031_VIBMODE				0x9C
+#define TPS80031_PWM1ON					0xBA
+#define TPS80031_PWM1OFF				0xBB
+#define TPS80031_PWM2ON					0xBD
+#define TPS80031_PWM2OFF				0xBE
+
+/* Control Interface */
+#define TPS80031_INT_STS_A				0xD0
+#define TPS80031_INT_STS_B				0xD1
+#define TPS80031_INT_STS_C				0xD2
+#define TPS80031_INT_MSK_LINE_A				0xD3
+#define TPS80031_INT_MSK_LINE_B				0xD4
+#define TPS80031_INT_MSK_LINE_C				0xD5
+#define TPS80031_INT_MSK_STS_A				0xD6
+#define TPS80031_INT_MSK_STS_B				0xD7
+#define TPS80031_INT_MSK_STS_C				0xD8
+#define TPS80031_TOGGLE1				0x90
+#define TPS80031_TOGGLE2				0x91
+#define TPS80031_TOGGLE3				0x92
+#define TPS80031_PWDNSTATUS1				0x93
+#define TPS80031_PWDNSTATUS2				0x94
+#define TPS80031_VALIDITY0				0x17
+#define TPS80031_VALIDITY1				0x18
+#define TPS80031_VALIDITY2				0x19
+#define TPS80031_VALIDITY3				0x1A
+#define TPS80031_VALIDITY4				0x1B
+#define TPS80031_VALIDITY5				0x1C
+#define TPS80031_VALIDITY6				0x1D
+#define TPS80031_VALIDITY7				0x1E
+
+/* Version number related register */
+#define TPS80031_JTAGVERNUM				0x87
+#define TPS80031_EPROM_REV				0xDF
+
+/* GPADC Trimming Bits. */
+#define TPS80031_GPADC_TRIM0				0xCC
+#define TPS80031_GPADC_TRIM1				0xCD
+#define TPS80031_GPADC_TRIM2				0xCE
+#define TPS80031_GPADC_TRIM3				0xCF
+#define TPS80031_GPADC_TRIM4				0xD0
+#define TPS80031_GPADC_TRIM5				0xD1
+#define TPS80031_GPADC_TRIM6				0xD2
+#define TPS80031_GPADC_TRIM7				0xD3
+#define TPS80031_GPADC_TRIM8				0xD4
+#define TPS80031_GPADC_TRIM9				0xD5
+#define TPS80031_GPADC_TRIM10				0xD6
+#define TPS80031_GPADC_TRIM11				0xD7
+#define TPS80031_GPADC_TRIM12				0xD8
+#define TPS80031_GPADC_TRIM13				0xD9
+#define TPS80031_GPADC_TRIM14				0xDA
+#define TPS80031_GPADC_TRIM15				0xDB
+#define TPS80031_GPADC_TRIM16				0xDC
+#define TPS80031_GPADC_TRIM17				0xDD
+#define TPS80031_GPADC_TRIM18				0xDE
+
+/* TPS80031_CONTROLLER_STAT1 bit fields */
+#define TPS80031_CONTROLLER_STAT1_BAT_TEMP		0
+#define TPS80031_CONTROLLER_STAT1_BAT_REMOVED		1
+#define TPS80031_CONTROLLER_STAT1_VBUS_DET		2
+#define TPS80031_CONTROLLER_STAT1_VAC_DET		3
+#define TPS80031_CONTROLLER_STAT1_FAULT_WDG		4
+#define TPS80031_CONTROLLER_STAT1_LINCH_GATED		6
+/* TPS80031_CONTROLLER_INT_MASK bit filed */
+#define TPS80031_CONTROLLER_INT_MASK_MVAC_DET		0
+#define TPS80031_CONTROLLER_INT_MASK_MVBUS_DET		1
+#define TPS80031_CONTROLLER_INT_MASK_MBAT_TEMP		2
+#define TPS80031_CONTROLLER_INT_MASK_MFAULT_WDG		3
+#define TPS80031_CONTROLLER_INT_MASK_MBAT_REMOVED	4
+#define TPS80031_CONTROLLER_INT_MASK_MLINCH_GATED	5
+
+#define TPS80031_CHARGE_CONTROL_SUB_INT_MASK		0x3F
+
+/* TPS80031_PHOENIX_DEV_ON bit field */
+#define TPS80031_DEVOFF					0x1
+
+#define TPS80031_EXT_CONTROL_CFG_TRANS			0
+#define TPS80031_EXT_CONTROL_CFG_STATE			1
+
+/* State register field */
+#define TPS80031_STATE_OFF				0x00
+#define TPS80031_STATE_ON				0x01
+#define TPS80031_STATE_MASK				0x03
+
+/* Trans register field */
+#define TPS80031_TRANS_ACTIVE_OFF			0x00
+#define TPS80031_TRANS_ACTIVE_ON			0x01
+#define TPS80031_TRANS_ACTIVE_MASK			0x03
+#define TPS80031_TRANS_SLEEP_OFF			0x00
+#define TPS80031_TRANS_SLEEP_ON				0x04
+#define TPS80031_TRANS_SLEEP_MASK			0x0C
+#define TPS80031_TRANS_OFF_OFF				0x00
+#define TPS80031_TRANS_OFF_ACTIVE			0x10
+#define TPS80031_TRANS_OFF_MASK				0x30
+
+#define TPS80031_EXT_PWR_REQ		(TPS80031_PWR_REQ_INPUT_PREQ1 | \
+					TPS80031_PWR_REQ_INPUT_PREQ2 | \
+					TPS80031_PWR_REQ_INPUT_PREQ3)
+
+/* TPS80031_BBSPOR_CFG bit field */
+#define TPS80031_BBSPOR_CHG_EN				0x8
+#define TPS80031_MAX_REGISTER				0xFF
+
+struct i2c_client;
+
+/* Supported chips */
+enum chips {
+	TPS80031 = 0x00000001,
+	TPS80032 = 0x00000002,
+};
+
+enum {
+	TPS80031_INT_PWRON,
+	TPS80031_INT_RPWRON,
+	TPS80031_INT_SYS_VLOW,
+	TPS80031_INT_RTC_ALARM,
+	TPS80031_INT_RTC_PERIOD,
+	TPS80031_INT_HOT_DIE,
+	TPS80031_INT_VXX_SHORT,
+	TPS80031_INT_SPDURATION,
+	TPS80031_INT_WATCHDOG,
+	TPS80031_INT_BAT,
+	TPS80031_INT_SIM,
+	TPS80031_INT_MMC,
+	TPS80031_INT_RES,
+	TPS80031_INT_GPADC_RT,
+	TPS80031_INT_GPADC_SW2_EOC,
+	TPS80031_INT_CC_AUTOCAL,
+	TPS80031_INT_ID_WKUP,
+	TPS80031_INT_VBUSS_WKUP,
+	TPS80031_INT_ID,
+	TPS80031_INT_VBUS,
+	TPS80031_INT_CHRG_CTRL,
+	TPS80031_INT_EXT_CHRG,
+	TPS80031_INT_INT_CHRG,
+	TPS80031_INT_RES2,
+	TPS80031_INT_BAT_TEMP_OVRANGE,
+	TPS80031_INT_BAT_REMOVED,
+	TPS80031_INT_VBUS_DET,
+	TPS80031_INT_VAC_DET,
+	TPS80031_INT_FAULT_WDG,
+	TPS80031_INT_LINCH_GATED,
+
+	/* Last interrupt id to get the end number */
+	TPS80031_INT_NR,
+};
+
+/* TPS80031 Slave IDs */
+#define TPS80031_NUM_SLAVES				4
+#define TPS80031_SLAVE_ID0				0
+#define TPS80031_SLAVE_ID1				1
+#define TPS80031_SLAVE_ID2				2
+#define TPS80031_SLAVE_ID3				3
+
+/* TPS80031 I2C addresses */
+#define TPS80031_I2C_ID0_ADDR				0x12
+#define TPS80031_I2C_ID1_ADDR				0x48
+#define TPS80031_I2C_ID2_ADDR				0x49
+#define TPS80031_I2C_ID3_ADDR				0x4A
+
+enum {
+	TPS80031_REGULATOR_VIO,
+	TPS80031_REGULATOR_SMPS1,
+	TPS80031_REGULATOR_SMPS2,
+	TPS80031_REGULATOR_SMPS3,
+	TPS80031_REGULATOR_SMPS4,
+	TPS80031_REGULATOR_VANA,
+	TPS80031_REGULATOR_LDO1,
+	TPS80031_REGULATOR_LDO2,
+	TPS80031_REGULATOR_LDO3,
+	TPS80031_REGULATOR_LDO4,
+	TPS80031_REGULATOR_LDO5,
+	TPS80031_REGULATOR_LDO6,
+	TPS80031_REGULATOR_LDO7,
+	TPS80031_REGULATOR_LDOLN,
+	TPS80031_REGULATOR_LDOUSB,
+	TPS80031_REGULATOR_VBUS,
+	TPS80031_REGULATOR_REGEN1,
+	TPS80031_REGULATOR_REGEN2,
+	TPS80031_REGULATOR_SYSEN,
+	TPS80031_REGULATOR_MAX,
+};
+
+/* Different configurations for the rails */
+enum {
+	/* USBLDO input selection */
+	TPS80031_USBLDO_INPUT_VSYS		= 0x00000001,
+	TPS80031_USBLDO_INPUT_PMID		= 0x00000002,
+
+	/* LDO3 output mode */
+	TPS80031_LDO3_OUTPUT_VIB		= 0x00000004,
+
+	/* VBUS configuration */
+	TPS80031_VBUS_DISCHRG_EN_PDN		= 0x00000004,
+	TPS80031_VBUS_SW_ONLY			= 0x00000008,
+	TPS80031_VBUS_SW_N_ID			= 0x00000010,
+};
+
+/* External controls requests */
+enum tps80031_ext_control {
+	TPS80031_PWR_REQ_INPUT_NONE		= 0x00000000,
+	TPS80031_PWR_REQ_INPUT_PREQ1		= 0x00000001,
+	TPS80031_PWR_REQ_INPUT_PREQ2		= 0x00000002,
+	TPS80031_PWR_REQ_INPUT_PREQ3		= 0x00000004,
+	TPS80031_PWR_OFF_ON_SLEEP		= 0x00000008,
+	TPS80031_PWR_ON_ON_SLEEP		= 0x00000010,
+};
+
+enum tps80031_pupd_pins {
+	TPS80031_PREQ1 = 0,
+	TPS80031_PREQ2A,
+	TPS80031_PREQ2B,
+	TPS80031_PREQ2C,
+	TPS80031_PREQ3,
+	TPS80031_NRES_WARM,
+	TPS80031_PWM_FORCE,
+	TPS80031_CHRG_EXT_CHRG_STATZ,
+	TPS80031_SIM,
+	TPS80031_MMC,
+	TPS80031_GPADC_START,
+	TPS80031_DVSI2C_SCL,
+	TPS80031_DVSI2C_SDA,
+	TPS80031_CTLI2C_SCL,
+	TPS80031_CTLI2C_SDA,
+};
+
+enum tps80031_pupd_settings {
+	TPS80031_PUPD_NORMAL,
+	TPS80031_PUPD_PULLDOWN,
+	TPS80031_PUPD_PULLUP,
+};
+
+struct tps80031 {
+	struct device		*dev;
+	unsigned long		chip_info;
+	int			es_version;
+	struct i2c_client	*clients[TPS80031_NUM_SLAVES];
+	struct regmap		*regmap[TPS80031_NUM_SLAVES];
+	struct regmap_irq_chip_data *irq_data;
+};
+
+struct tps80031_pupd_init_data {
+	int input_pin;
+	int setting;
+};
+
+/*
+ * struct tps80031_regulator_platform_data - tps80031 regulator platform data.
+ *
+ * @reg_init_data: The regulator init data.
+ * @ext_ctrl_flag: External control flag for sleep/power request control.
+ * @config_flags: Configuration flag to configure the rails.
+ *		  It should be ORed of config enums.
+ */
+
+struct tps80031_regulator_platform_data {
+	struct regulator_init_data *reg_init_data;
+	unsigned int ext_ctrl_flag;
+	unsigned int config_flags;
+};
+
+struct tps80031_platform_data {
+	int irq_base;
+	bool use_power_off;
+	struct tps80031_pupd_init_data *pupd_init_data;
+	int pupd_init_data_size;
+	struct tps80031_regulator_platform_data
+			*regulator_pdata[TPS80031_REGULATOR_MAX];
+};
+
+static inline int tps80031_write(struct device *dev, int sid,
+		int reg, uint8_t val)
+{
+	struct tps80031 *tps80031 = dev_get_drvdata(dev);
+
+	return regmap_write(tps80031->regmap[sid], reg, val);
+}
+
+static inline int tps80031_writes(struct device *dev, int sid, int reg,
+		int len, uint8_t *val)
+{
+	struct tps80031 *tps80031 = dev_get_drvdata(dev);
+
+	return regmap_bulk_write(tps80031->regmap[sid], reg, val, len);
+}
+
+static inline int tps80031_read(struct device *dev, int sid,
+		int reg, uint8_t *val)
+{
+	struct tps80031 *tps80031 = dev_get_drvdata(dev);
+	unsigned int ival;
+	int ret;
+
+	ret = regmap_read(tps80031->regmap[sid], reg, &ival);
+	if (ret < 0) {
+		dev_err(dev, "failed reading from reg 0x%02x\n", reg);
+		return ret;
+	}
+
+	*val = ival;
+	return ret;
+}
+
+static inline int tps80031_reads(struct device *dev, int sid,
+		int reg, int len, uint8_t *val)
+{
+	struct tps80031 *tps80031 = dev_get_drvdata(dev);
+
+	return regmap_bulk_read(tps80031->regmap[sid], reg, val, len);
+}
+
+static inline int tps80031_set_bits(struct device *dev, int sid,
+		int reg, uint8_t bit_mask)
+{
+	struct tps80031 *tps80031 = dev_get_drvdata(dev);
+
+	return regmap_update_bits(tps80031->regmap[sid], reg,
+				bit_mask, bit_mask);
+}
+
+static inline int tps80031_clr_bits(struct device *dev, int sid,
+		int reg, uint8_t bit_mask)
+{
+	struct tps80031 *tps80031 = dev_get_drvdata(dev);
+
+	return regmap_update_bits(tps80031->regmap[sid], reg, bit_mask, 0);
+}
+
+static inline int tps80031_update(struct device *dev, int sid,
+		int reg, uint8_t val, uint8_t mask)
+{
+	struct tps80031 *tps80031 = dev_get_drvdata(dev);
+
+	return regmap_update_bits(tps80031->regmap[sid], reg, mask, val);
+}
+
+static inline unsigned long tps80031_get_chip_info(struct device *dev)
+{
+	struct tps80031 *tps80031 = dev_get_drvdata(dev);
+
+	return tps80031->chip_info;
+}
+
+static inline int tps80031_get_pmu_version(struct device *dev)
+{
+	struct tps80031 *tps80031 = dev_get_drvdata(dev);
+
+	return tps80031->es_version;
+}
+
+static inline int tps80031_irq_get_virq(struct device *dev, int irq)
+{
+	struct tps80031 *tps80031 = dev_get_drvdata(dev);
+
+	return regmap_irq_get_virq(tps80031->irq_data, irq);
+}
+
+extern int tps80031_ext_power_req_config(struct device *dev,
+		unsigned long ext_ctrl_flag, int preq_bit,
+		int state_reg_add, int trans_reg_add);
+#endif /*__LINUX_MFD_TPS80031_H */
-- 
cgit v1.2.3-55-g7522


From 3863db3e800c64e21e4effcc3de0f72cdb9b0d77 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 20 Nov 2012 08:44:47 +0530
Subject: mfd: tps65090: Remove unused member of struct tps65090

Remove unused member from tps65090 data structure as
these are not used.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/tps65090.c       |  6 +-----
 include/linux/mfd/tps65090.h | 11 -----------
 2 files changed, 1 insertion(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/tps65090.c b/drivers/mfd/tps65090.c
index f95f7f6b846c..3cfc9dcbe9dc 100644
--- a/drivers/mfd/tps65090.c
+++ b/drivers/mfd/tps65090.c
@@ -269,12 +269,9 @@ static int __devinit tps65090_i2c_probe(struct i2c_client *client,
 		return -ENOMEM;
 	}
 
-	tps65090->client = client;
 	tps65090->dev = &client->dev;
 	i2c_set_clientdata(client, tps65090);
 
-	mutex_init(&tps65090->lock);
-
 	if (client->irq) {
 		ret = tps65090_irq_init(tps65090, client->irq, pdata->irq_base);
 		if (ret) {
@@ -284,8 +281,7 @@ static int __devinit tps65090_i2c_probe(struct i2c_client *client,
 		}
 	}
 
-	tps65090->rmap = devm_regmap_init_i2c(tps65090->client,
-					      &tps65090_regmap_config);
+	tps65090->rmap = devm_regmap_init_i2c(client, &tps65090_regmap_config);
 	if (IS_ERR(tps65090->rmap)) {
 		ret = PTR_ERR(tps65090->rmap);
 		dev_err(&client->dev, "regmap_init failed with err: %d\n", ret);
diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h
index 6bc31d854626..6c576224f637 100644
--- a/include/linux/mfd/tps65090.h
+++ b/include/linux/mfd/tps65090.h
@@ -25,26 +25,15 @@
 #include <linux/irq.h>
 
 struct tps65090 {
-	struct mutex		lock;
 	struct device		*dev;
-	struct i2c_client	*client;
 	struct regmap		*rmap;
 	struct irq_chip		irq_chip;
 	struct mutex		irq_lock;
 	int			irq_base;
-	unsigned int		id;
-};
-
-struct tps65090_subdev_info {
-	int		id;
-	const char	*name;
-	void		*platform_data;
 };
 
 struct tps65090_platform_data {
 	int irq_base;
-	int num_subdevs;
-	struct tps65090_subdev_info *subdevs;
 };
 
 /*
-- 
cgit v1.2.3-55-g7522


From b9c79323166530a14c1fa8c10337eeaa54e3f98d Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 20 Nov 2012 08:44:48 +0530
Subject: mfd: tps65090: Move register access APIs to header

Since tps65090 register is accessed via regmap, moving
the register access APIs to header and making it as inline.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/tps65090.c       | 34 ----------------------------------
 include/linux/mfd/tps65090.h | 39 +++++++++++++++++++++++++++++++++++----
 2 files changed, 35 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/tps65090.c b/drivers/mfd/tps65090.c
index 3cfc9dcbe9dc..355a07749454 100644
--- a/drivers/mfd/tps65090.c
+++ b/drivers/mfd/tps65090.c
@@ -25,7 +25,6 @@
 #include <linux/i2c.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/tps65090.h>
-#include <linux/regmap.h>
 #include <linux/err.h>
 
 #define NUM_INT_REG 2
@@ -78,39 +77,6 @@ static struct mfd_cell tps65090s[] = {
 	},
 };
 
-int tps65090_write(struct device *dev, int reg, uint8_t val)
-{
-	struct tps65090 *tps = dev_get_drvdata(dev);
-	return regmap_write(tps->rmap, reg, val);
-}
-EXPORT_SYMBOL_GPL(tps65090_write);
-
-int tps65090_read(struct device *dev, int reg, uint8_t *val)
-{
-	struct tps65090 *tps = dev_get_drvdata(dev);
-	unsigned int temp_val;
-	int ret;
-	ret = regmap_read(tps->rmap, reg, &temp_val);
-	if (!ret)
-		*val = temp_val;
-	return ret;
-}
-EXPORT_SYMBOL_GPL(tps65090_read);
-
-int tps65090_set_bits(struct device *dev, int reg, uint8_t bit_num)
-{
-	struct tps65090 *tps = dev_get_drvdata(dev);
-	return regmap_update_bits(tps->rmap, reg, BIT(bit_num), ~0u);
-}
-EXPORT_SYMBOL_GPL(tps65090_set_bits);
-
-int tps65090_clr_bits(struct device *dev, int reg, uint8_t bit_num)
-{
-	struct tps65090 *tps = dev_get_drvdata(dev);
-	return regmap_update_bits(tps->rmap, reg, BIT(bit_num), 0u);
-}
-EXPORT_SYMBOL_GPL(tps65090_clr_bits);
-
 static void tps65090_irq_lock(struct irq_data *data)
 {
 	struct tps65090 *tps65090 = irq_data_get_irq_chip_data(data);
diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h
index 6c576224f637..1a5f916b7383 100644
--- a/include/linux/mfd/tps65090.h
+++ b/include/linux/mfd/tps65090.h
@@ -23,6 +23,7 @@
 #define __LINUX_MFD_TPS65090_H
 
 #include <linux/irq.h>
+#include <linux/regmap.h>
 
 struct tps65090 {
 	struct device		*dev;
@@ -40,9 +41,39 @@ struct tps65090_platform_data {
  * NOTE: the functions below are not intended for use outside
  * of the TPS65090 sub-device drivers
  */
-extern int tps65090_write(struct device *dev, int reg, uint8_t val);
-extern int tps65090_read(struct device *dev, int reg, uint8_t *val);
-extern int tps65090_set_bits(struct device *dev, int reg, uint8_t bit_num);
-extern int tps65090_clr_bits(struct device *dev, int reg, uint8_t bit_num);
+static inline int tps65090_write(struct device *dev, int reg, uint8_t val)
+{
+	struct tps65090 *tps = dev_get_drvdata(dev);
+
+	return regmap_write(tps->rmap, reg, val);
+}
+
+static inline int tps65090_read(struct device *dev, int reg, uint8_t *val)
+{
+	struct tps65090 *tps = dev_get_drvdata(dev);
+	unsigned int temp_val;
+	int ret;
+
+	ret = regmap_read(tps->rmap, reg, &temp_val);
+	if (!ret)
+		*val = temp_val;
+	return ret;
+}
+
+static inline int tps65090_set_bits(struct device *dev, int reg,
+		uint8_t bit_num)
+{
+	struct tps65090 *tps = dev_get_drvdata(dev);
+
+	return regmap_update_bits(tps->rmap, reg, BIT(bit_num), ~0u);
+}
+
+static inline int tps65090_clr_bits(struct device *dev, int reg,
+		uint8_t bit_num)
+{
+	struct tps65090 *tps = dev_get_drvdata(dev);
+
+	return regmap_update_bits(tps->rmap, reg, BIT(bit_num), 0u);
+}
 
 #endif /*__LINUX_MFD_TPS65090_H */
-- 
cgit v1.2.3-55-g7522


From 759f2598ef3876637e40d99a4ceb7a3d83a4d8d3 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan
Date: Tue, 20 Nov 2012 08:44:49 +0530
Subject: mfd: tps65090: Use regmap irq framework for interrupt support

Use the regmap irq framework for implementing TPS65090 interrupt
support in place of implementing it locally.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/tps65090.c       | 263 ++++++++++++++++---------------------------
 include/linux/mfd/tps65090.h |  23 +++-
 2 files changed, 118 insertions(+), 168 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/tps65090.c b/drivers/mfd/tps65090.c
index 355a07749454..2eaae52cb5b8 100644
--- a/drivers/mfd/tps65090.c
+++ b/drivers/mfd/tps65090.c
@@ -38,35 +38,21 @@
 #define TPS65090_INT_MSK	0x2
 #define TPS65090_INT_MSK2	0x3
 
-struct tps65090_irq_data {
-	u8		mask_reg;
-	u8		mask_pos;
-};
-
-#define TPS65090_IRQ(_reg, _mask_pos)		\
-	{					\
-		.mask_reg	= (_reg),	\
-		.mask_pos	= (_mask_pos),	\
-	}
-
-static const struct tps65090_irq_data tps65090_irqs[] = {
-	[0]		= TPS65090_IRQ(0, 0),
-	[1]		= TPS65090_IRQ(0, 1),
-	[2]		= TPS65090_IRQ(0, 2),
-	[3]		= TPS65090_IRQ(0, 3),
-	[4]		= TPS65090_IRQ(0, 4),
-	[5]		= TPS65090_IRQ(0, 5),
-	[6]		= TPS65090_IRQ(0, 6),
-	[7]		= TPS65090_IRQ(0, 7),
-	[8]		= TPS65090_IRQ(1, 0),
-	[9]		= TPS65090_IRQ(1, 1),
-	[10]		= TPS65090_IRQ(1, 2),
-	[11]		= TPS65090_IRQ(1, 3),
-	[12]		= TPS65090_IRQ(1, 4),
-	[13]		= TPS65090_IRQ(1, 5),
-	[14]		= TPS65090_IRQ(1, 6),
-	[15]		= TPS65090_IRQ(1, 7),
-};
+#define TPS65090_INT1_MASK_VAC_STATUS_CHANGE		1
+#define TPS65090_INT1_MASK_VSYS_STATUS_CHANGE		2
+#define TPS65090_INT1_MASK_BAT_STATUS_CHANGE		3
+#define TPS65090_INT1_MASK_CHARGING_STATUS_CHANGE	4
+#define TPS65090_INT1_MASK_CHARGING_COMPLETE		5
+#define TPS65090_INT1_MASK_OVERLOAD_DCDC1		6
+#define TPS65090_INT1_MASK_OVERLOAD_DCDC2		7
+#define TPS65090_INT2_MASK_OVERLOAD_DCDC3		0
+#define TPS65090_INT2_MASK_OVERLOAD_FET1		1
+#define TPS65090_INT2_MASK_OVERLOAD_FET2		2
+#define TPS65090_INT2_MASK_OVERLOAD_FET3		3
+#define TPS65090_INT2_MASK_OVERLOAD_FET4		4
+#define TPS65090_INT2_MASK_OVERLOAD_FET5		5
+#define TPS65090_INT2_MASK_OVERLOAD_FET6		6
+#define TPS65090_INT2_MASK_OVERLOAD_FET7		7
 
 static struct mfd_cell tps65090s[] = {
 	{
@@ -77,132 +63,77 @@ static struct mfd_cell tps65090s[] = {
 	},
 };
 
-static void tps65090_irq_lock(struct irq_data *data)
-{
-	struct tps65090 *tps65090 = irq_data_get_irq_chip_data(data);
-
-	mutex_lock(&tps65090->irq_lock);
-}
-
-static void tps65090_irq_mask(struct irq_data *irq_data)
-{
-	struct tps65090 *tps65090 = irq_data_get_irq_chip_data(irq_data);
-	unsigned int __irq = irq_data->hwirq;
-	const struct tps65090_irq_data *data = &tps65090_irqs[__irq];
-
-	tps65090_set_bits(tps65090->dev, (TPS65090_INT_MSK + data->mask_reg),
-		data->mask_pos);
-}
-
-static void tps65090_irq_unmask(struct irq_data *irq_data)
-{
-	struct tps65090 *tps65090 = irq_data_get_irq_chip_data(irq_data);
-	unsigned int __irq = irq_data->irq - tps65090->irq_base;
-	const struct tps65090_irq_data *data = &tps65090_irqs[__irq];
-
-	tps65090_clr_bits(tps65090->dev, (TPS65090_INT_MSK + data->mask_reg),
-		data->mask_pos);
-}
-
-static void tps65090_irq_sync_unlock(struct irq_data *data)
-{
-	struct tps65090 *tps65090 = irq_data_get_irq_chip_data(data);
-
-	mutex_unlock(&tps65090->irq_lock);
-}
-
-static irqreturn_t tps65090_irq(int irq, void *data)
-{
-	struct tps65090 *tps65090 = data;
-	int ret = 0;
-	u8 status, mask;
-	unsigned long int acks = 0;
-	int i;
-
-	for (i = 0; i < NUM_INT_REG; i++) {
-		ret = tps65090_read(tps65090->dev, TPS65090_INT_MSK + i, &mask);
-		if (ret < 0) {
-			dev_err(tps65090->dev,
-				"failed to read mask reg [addr:%d]\n",
-				TPS65090_INT_MSK + i);
-			return IRQ_NONE;
-		}
-		ret = tps65090_read(tps65090->dev, TPS65090_INT_STS + i,
-			&status);
-		if (ret < 0) {
-			dev_err(tps65090->dev,
-				"failed to read status reg [addr:%d]\n",
-				 TPS65090_INT_STS + i);
-			return IRQ_NONE;
-		}
-		if (status) {
-			/* Ack only those interrupts which are not masked */
-			status &= (~mask);
-			ret = tps65090_write(tps65090->dev,
-					TPS65090_INT_STS + i, status);
-			if (ret < 0) {
-				dev_err(tps65090->dev,
-					"failed to write interrupt status\n");
-				return IRQ_NONE;
-			}
-			acks |= (status << (i * 8));
-		}
-	}
-
-	for_each_set_bit(i, &acks, ARRAY_SIZE(tps65090_irqs))
-		handle_nested_irq(tps65090->irq_base + i);
-	return acks ? IRQ_HANDLED : IRQ_NONE;
-}
-
-static int __devinit tps65090_irq_init(struct tps65090 *tps65090, int irq,
-	int irq_base)
-{
-	int i, ret;
-
-	if (!irq_base) {
-		dev_err(tps65090->dev, "IRQ base not set\n");
-		return -EINVAL;
-	}
-
-	mutex_init(&tps65090->irq_lock);
-
-	for (i = 0; i < NUM_INT_REG; i++)
-		tps65090_write(tps65090->dev, TPS65090_INT_MSK + i, 0xFF);
-
-	for (i = 0; i < NUM_INT_REG; i++)
-		tps65090_write(tps65090->dev, TPS65090_INT_STS + i, 0xff);
-
-	tps65090->irq_base = irq_base;
-	tps65090->irq_chip.name = "tps65090";
-	tps65090->irq_chip.irq_mask = tps65090_irq_mask;
-	tps65090->irq_chip.irq_unmask = tps65090_irq_unmask;
-	tps65090->irq_chip.irq_bus_lock = tps65090_irq_lock;
-	tps65090->irq_chip.irq_bus_sync_unlock = tps65090_irq_sync_unlock;
-
-	for (i = 0; i < ARRAY_SIZE(tps65090_irqs); i++) {
-		int __irq = i + tps65090->irq_base;
-		irq_set_chip_data(__irq, tps65090);
-		irq_set_chip_and_handler(__irq, &tps65090->irq_chip,
-					 handle_simple_irq);
-		irq_set_nested_thread(__irq, 1);
-#ifdef CONFIG_ARM
-		set_irq_flags(__irq, IRQF_VALID);
-#endif
-	}
-
-	ret = request_threaded_irq(irq, NULL, tps65090_irq, IRQF_ONESHOT,
-				"tps65090", tps65090);
-	if (!ret) {
-		device_init_wakeup(tps65090->dev, 1);
-		enable_irq_wake(irq);
-	}
+static const struct regmap_irq tps65090_irqs[] = {
+	/* INT1 IRQs*/
+	[TPS65090_IRQ_VAC_STATUS_CHANGE] = {
+			.mask = TPS65090_INT1_MASK_VAC_STATUS_CHANGE,
+	},
+	[TPS65090_IRQ_VSYS_STATUS_CHANGE] = {
+			.mask = TPS65090_INT1_MASK_VSYS_STATUS_CHANGE,
+	},
+	[TPS65090_IRQ_BAT_STATUS_CHANGE] = {
+			.mask = TPS65090_INT1_MASK_BAT_STATUS_CHANGE,
+	},
+	[TPS65090_IRQ_CHARGING_STATUS_CHANGE] = {
+			.mask = TPS65090_INT1_MASK_CHARGING_STATUS_CHANGE,
+	},
+	[TPS65090_IRQ_CHARGING_COMPLETE] = {
+			.mask = TPS65090_INT1_MASK_CHARGING_COMPLETE,
+	},
+	[TPS65090_IRQ_OVERLOAD_DCDC1] = {
+			.mask = TPS65090_INT1_MASK_OVERLOAD_DCDC1,
+	},
+	[TPS65090_IRQ_OVERLOAD_DCDC2] = {
+			.mask = TPS65090_INT1_MASK_OVERLOAD_DCDC2,
+	},
+	/* INT2 IRQs*/
+	[TPS65090_IRQ_OVERLOAD_DCDC3] = {
+			.reg_offset = 1,
+			.mask = TPS65090_INT2_MASK_OVERLOAD_DCDC3,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET1] = {
+			.reg_offset = 1,
+			.mask = TPS65090_INT2_MASK_OVERLOAD_FET1,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET2] = {
+			.reg_offset = 1,
+			.mask = TPS65090_INT2_MASK_OVERLOAD_FET2,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET3] = {
+			.reg_offset = 1,
+			.mask = TPS65090_INT2_MASK_OVERLOAD_FET3,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET4] = {
+			.reg_offset = 1,
+			.mask = TPS65090_INT2_MASK_OVERLOAD_FET4,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET5] = {
+			.reg_offset = 1,
+			.mask = TPS65090_INT2_MASK_OVERLOAD_FET5,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET6] = {
+			.reg_offset = 1,
+			.mask = TPS65090_INT2_MASK_OVERLOAD_FET6,
+	},
+	[TPS65090_IRQ_OVERLOAD_FET7] = {
+			.reg_offset = 1,
+			.mask = TPS65090_INT2_MASK_OVERLOAD_FET7,
+	},
+};
 
-	return ret;
-}
+static struct regmap_irq_chip tps65090_irq_chip = {
+	.name = "tps65090",
+	.irqs = tps65090_irqs,
+	.num_irqs = ARRAY_SIZE(tps65090_irqs),
+	.num_regs = NUM_INT_REG,
+	.status_base = TPS65090_INT_STS,
+	.mask_base = TPS65090_INT_MSK,
+	.mask_invert = true,
+};
 
 static bool is_volatile_reg(struct device *dev, unsigned int reg)
 {
-	if (reg == TPS65090_INT_STS)
+	if ((reg == TPS65090_INT_STS) || (reg == TPS65090_INT_STS2))
 		return true;
 	else
 		return false;
@@ -238,24 +169,27 @@ static int __devinit tps65090_i2c_probe(struct i2c_client *client,
 	tps65090->dev = &client->dev;
 	i2c_set_clientdata(client, tps65090);
 
-	if (client->irq) {
-		ret = tps65090_irq_init(tps65090, client->irq, pdata->irq_base);
-		if (ret) {
-			dev_err(&client->dev, "IRQ init failed with err: %d\n",
-				ret);
-			goto err_exit;
-		}
-	}
-
 	tps65090->rmap = devm_regmap_init_i2c(client, &tps65090_regmap_config);
 	if (IS_ERR(tps65090->rmap)) {
 		ret = PTR_ERR(tps65090->rmap);
 		dev_err(&client->dev, "regmap_init failed with err: %d\n", ret);
-		goto err_irq_exit;
+		return ret;
+	}
+
+	if (client->irq) {
+		ret = regmap_add_irq_chip(tps65090->rmap, client->irq,
+			IRQF_ONESHOT | IRQF_TRIGGER_LOW, pdata->irq_base,
+			&tps65090_irq_chip, &tps65090->irq_data);
+			if (ret) {
+				dev_err(&client->dev,
+					"IRQ init failed with err: %d\n", ret);
+			return ret;
+		}
 	}
 
 	ret = mfd_add_devices(tps65090->dev, -1, tps65090s,
-			      ARRAY_SIZE(tps65090s), NULL, 0, NULL);
+		ARRAY_SIZE(tps65090s), NULL,
+		regmap_irq_chip_get_base(tps65090->irq_data), NULL);
 	if (ret) {
 		dev_err(&client->dev, "add mfd devices failed with err: %d\n",
 			ret);
@@ -266,8 +200,7 @@ static int __devinit tps65090_i2c_probe(struct i2c_client *client,
 
 err_irq_exit:
 	if (client->irq)
-		free_irq(client->irq, tps65090);
-err_exit:
+		regmap_del_irq_chip(client->irq, tps65090->irq_data);
 	return ret;
 }
 
@@ -277,7 +210,7 @@ static int __devexit tps65090_i2c_remove(struct i2c_client *client)
 
 	mfd_remove_devices(tps65090->dev);
 	if (client->irq)
-		free_irq(client->irq, tps65090);
+		regmap_del_irq_chip(client->irq, tps65090->irq_data);
 
 	return 0;
 }
diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h
index 1a5f916b7383..4bbbb1350b91 100644
--- a/include/linux/mfd/tps65090.h
+++ b/include/linux/mfd/tps65090.h
@@ -25,12 +25,29 @@
 #include <linux/irq.h>
 #include <linux/regmap.h>
 
+/* TPS65090 IRQs */
+enum {
+	TPS65090_IRQ_VAC_STATUS_CHANGE,
+	TPS65090_IRQ_VSYS_STATUS_CHANGE,
+	TPS65090_IRQ_BAT_STATUS_CHANGE,
+	TPS65090_IRQ_CHARGING_STATUS_CHANGE,
+	TPS65090_IRQ_CHARGING_COMPLETE,
+	TPS65090_IRQ_OVERLOAD_DCDC1,
+	TPS65090_IRQ_OVERLOAD_DCDC2,
+	TPS65090_IRQ_OVERLOAD_DCDC3,
+	TPS65090_IRQ_OVERLOAD_FET1,
+	TPS65090_IRQ_OVERLOAD_FET2,
+	TPS65090_IRQ_OVERLOAD_FET3,
+	TPS65090_IRQ_OVERLOAD_FET4,
+	TPS65090_IRQ_OVERLOAD_FET5,
+	TPS65090_IRQ_OVERLOAD_FET6,
+	TPS65090_IRQ_OVERLOAD_FET7,
+};
+
 struct tps65090 {
 	struct device		*dev;
 	struct regmap		*rmap;
-	struct irq_chip		irq_chip;
-	struct mutex		irq_lock;
-	int			irq_base;
+	struct regmap_irq_chip_data *irq_data;
 };
 
 struct tps65090_platform_data {
-- 
cgit v1.2.3-55-g7522


From c7b76dce8ac95fd464bfae741b830d407884c274 Mon Sep 17 00:00:00 2001
From: Aaro Koskinen
Date: Sun, 18 Nov 2012 18:36:20 +0200
Subject: mfd: Introduce retu-mfd driver

Retu is a multi-function device found on Nokia Internet Tablets
implementing at least watchdog, RTC, headset detection and power button
functionality.

This patch implements minimum functionality providing register access,
IRQ handling and power off functions.

Acked-by: Felipe Balbi <balbi@ti.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/Kconfig      |   9 ++
 drivers/mfd/Makefile     |   1 +
 drivers/mfd/retu-mfd.c   | 264 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/retu.h |  22 ++++
 4 files changed, 296 insertions(+)
 create mode 100644 drivers/mfd/retu-mfd.c
 create mode 100644 include/linux/mfd/retu.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index ca633df7c330..f5b839b718aa 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1094,6 +1094,15 @@ config MFD_VIPERBOARD
 	  You need to select the mfd cell drivers separately.
 	  The drivers do not support all features the board exposes.
 
+config MFD_RETU
+	tristate "Support for Retu multi-function device"
+	select MFD_CORE
+	depends on I2C
+	select REGMAP_IRQ
+	help
+	  Retu is a multi-function device found on Nokia Internet Tablets
+	  (770, N800 and N810).
+
 endmenu
 endif
 
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 8072460e99d2..2689c8a0d781 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -145,3 +145,4 @@ obj-$(CONFIG_MFD_RC5T583)	+= rc5t583.o rc5t583-irq.o
 obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o sec-irq.o
 obj-$(CONFIG_MFD_SYSCON)	+= syscon.o
 obj-$(CONFIG_MFD_LM3533)	+= lm3533-core.o lm3533-ctrlbank.o
+obj-$(CONFIG_MFD_RETU)		+= retu-mfd.o
diff --git a/drivers/mfd/retu-mfd.c b/drivers/mfd/retu-mfd.c
new file mode 100644
index 000000000000..7ff4a37ab0c0
--- /dev/null
+++ b/drivers/mfd/retu-mfd.c
@@ -0,0 +1,264 @@
+/*
+ * Retu MFD driver
+ *
+ * Copyright (C) 2004, 2005 Nokia Corporation
+ *
+ * Based on code written by Juha Yrjölä, David Weinehall and Mikko Ylinen.
+ * Rewritten by Aaro Koskinen.
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file "COPYING" in the main directory of this
+ * archive for more details.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/retu.h>
+#include <linux/interrupt.h>
+#include <linux/moduleparam.h>
+
+/* Registers */
+#define RETU_REG_ASICR		0x00		/* ASIC ID and revision */
+#define RETU_REG_ASICR_VILMA	(1 << 7)	/* Bit indicating Vilma */
+#define RETU_REG_IDR		0x01		/* Interrupt ID */
+#define RETU_REG_IMR		0x02		/* Interrupt mask */
+
+/* Interrupt sources */
+#define RETU_INT_PWR		0		/* Power button */
+
+struct retu_dev {
+	struct regmap			*regmap;
+	struct device			*dev;
+	struct mutex			mutex;
+	struct regmap_irq_chip_data	*irq_data;
+};
+
+static struct resource retu_pwrbutton_res[] = {
+	{
+		.name	= "retu-pwrbutton",
+		.start	= RETU_INT_PWR,
+		.end	= RETU_INT_PWR,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct mfd_cell retu_devs[] = {
+	{
+		.name		= "retu-wdt"
+	},
+	{
+		.name		= "retu-pwrbutton",
+		.resources	= retu_pwrbutton_res,
+		.num_resources	= ARRAY_SIZE(retu_pwrbutton_res),
+	}
+};
+
+static struct regmap_irq retu_irqs[] = {
+	[RETU_INT_PWR] = {
+		.mask = 1 << RETU_INT_PWR,
+	}
+};
+
+static struct regmap_irq_chip retu_irq_chip = {
+	.name		= "RETU",
+	.irqs		= retu_irqs,
+	.num_irqs	= ARRAY_SIZE(retu_irqs),
+	.num_regs	= 1,
+	.status_base	= RETU_REG_IDR,
+	.mask_base	= RETU_REG_IMR,
+	.ack_base	= RETU_REG_IDR,
+};
+
+/* Retu device registered for the power off. */
+static struct retu_dev *retu_pm_power_off;
+
+int retu_read(struct retu_dev *rdev, u8 reg)
+{
+	int ret;
+	int value;
+
+	mutex_lock(&rdev->mutex);
+	ret = regmap_read(rdev->regmap, reg, &value);
+	mutex_unlock(&rdev->mutex);
+
+	return ret ? ret : value;
+}
+EXPORT_SYMBOL_GPL(retu_read);
+
+int retu_write(struct retu_dev *rdev, u8 reg, u16 data)
+{
+	int ret;
+
+	mutex_lock(&rdev->mutex);
+	ret = regmap_write(rdev->regmap, reg, data);
+	mutex_unlock(&rdev->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(retu_write);
+
+static void retu_power_off(void)
+{
+	struct retu_dev *rdev = retu_pm_power_off;
+	int reg;
+
+	mutex_lock(&retu_pm_power_off->mutex);
+
+	/* Ignore power button state */
+	regmap_read(rdev->regmap, RETU_REG_CC1, &reg);
+	regmap_write(rdev->regmap, RETU_REG_CC1, reg | 2);
+
+	/* Expire watchdog immediately */
+	regmap_write(rdev->regmap, RETU_REG_WATCHDOG, 0);
+
+	/* Wait for poweroff */
+	for (;;)
+		cpu_relax();
+
+	mutex_unlock(&retu_pm_power_off->mutex);
+}
+
+static int retu_regmap_read(void *context, const void *reg, size_t reg_size,
+			    void *val, size_t val_size)
+{
+	int ret;
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+
+	BUG_ON(reg_size != 1 || val_size != 2);
+
+	ret = i2c_smbus_read_word_data(i2c, *(u8 const *)reg);
+	if (ret < 0)
+		return ret;
+
+	*(u16 *)val = ret;
+	return 0;
+}
+
+static int retu_regmap_write(void *context, const void *data, size_t count)
+{
+	u8 reg;
+	u16 val;
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+
+	BUG_ON(count != sizeof(reg) + sizeof(val));
+	memcpy(&reg, data, sizeof(reg));
+	memcpy(&val, data + sizeof(reg), sizeof(val));
+	return i2c_smbus_write_word_data(i2c, reg, val);
+}
+
+static struct regmap_bus retu_bus = {
+	.read = retu_regmap_read,
+	.write = retu_regmap_write,
+	.val_format_endian_default = REGMAP_ENDIAN_NATIVE,
+};
+
+static struct regmap_config retu_config = {
+	.reg_bits = 8,
+	.val_bits = 16,
+};
+
+static int __devinit retu_probe(struct i2c_client *i2c,
+				const struct i2c_device_id *id)
+{
+	struct retu_dev *rdev;
+	int ret;
+
+	rdev = devm_kzalloc(&i2c->dev, sizeof(*rdev), GFP_KERNEL);
+	if (rdev == NULL)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, rdev);
+	rdev->dev = &i2c->dev;
+	mutex_init(&rdev->mutex);
+	rdev->regmap = devm_regmap_init(&i2c->dev, &retu_bus, &i2c->dev,
+					&retu_config);
+	if (IS_ERR(rdev->regmap))
+		return PTR_ERR(rdev->regmap);
+
+	ret = retu_read(rdev, RETU_REG_ASICR);
+	if (ret < 0) {
+		dev_err(rdev->dev, "could not read Retu revision: %d\n", ret);
+		return ret;
+	}
+
+	dev_info(rdev->dev, "Retu%s v%d.%d found\n",
+		 (ret & RETU_REG_ASICR_VILMA) ? " & Vilma" : "",
+		 (ret >> 4) & 0x7, ret & 0xf);
+
+	/* Mask all RETU interrupts. */
+	ret = retu_write(rdev, RETU_REG_IMR, 0xffff);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_add_irq_chip(rdev->regmap, i2c->irq, IRQF_ONESHOT, -1,
+				  &retu_irq_chip, &rdev->irq_data);
+	if (ret < 0)
+		return ret;
+
+	ret = mfd_add_devices(rdev->dev, -1, retu_devs, ARRAY_SIZE(retu_devs),
+			      NULL, regmap_irq_chip_get_base(rdev->irq_data),
+			      NULL);
+	if (ret < 0) {
+		regmap_del_irq_chip(i2c->irq, rdev->irq_data);
+		return ret;
+	}
+
+	if (!pm_power_off) {
+		retu_pm_power_off = rdev;
+		pm_power_off	  = retu_power_off;
+	}
+
+	return 0;
+}
+
+static int __devexit retu_remove(struct i2c_client *i2c)
+{
+	struct retu_dev *rdev = i2c_get_clientdata(i2c);
+
+	if (retu_pm_power_off == rdev) {
+		pm_power_off	  = NULL;
+		retu_pm_power_off = NULL;
+	}
+	mfd_remove_devices(rdev->dev);
+	regmap_del_irq_chip(i2c->irq, rdev->irq_data);
+
+	return 0;
+}
+
+static const struct i2c_device_id retu_id[] = {
+	{ "retu-mfd", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, retu_id);
+
+static struct i2c_driver retu_driver = {
+	.driver		= {
+		.name = "retu-mfd",
+		.owner = THIS_MODULE,
+	},
+	.probe		= retu_probe,
+	.remove		= retu_remove,
+	.id_table	= retu_id,
+};
+module_i2c_driver(retu_driver);
+
+MODULE_DESCRIPTION("Retu MFD driver");
+MODULE_AUTHOR("Juha Yrjölä");
+MODULE_AUTHOR("David Weinehall");
+MODULE_AUTHOR("Mikko Ylinen");
+MODULE_AUTHOR("Aaro Koskinen <aaro.koskinen@iki.fi>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/mfd/retu.h b/include/linux/mfd/retu.h
new file mode 100644
index 000000000000..1e2715d5b836
--- /dev/null
+++ b/include/linux/mfd/retu.h
@@ -0,0 +1,22 @@
+/*
+ * Retu MFD driver interface
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file "COPYING" in the main directory of this
+ * archive for more details.
+ */
+
+#ifndef __LINUX_MFD_RETU_H
+#define __LINUX_MFD_RETU_H
+
+struct retu_dev;
+
+int retu_read(struct retu_dev *, u8);
+int retu_write(struct retu_dev *, u8, u16);
+
+/* Registers */
+#define RETU_REG_WATCHDOG	0x17		/* Watchdog */
+#define RETU_REG_CC1		0x0d		/* Common control register 1 */
+#define RETU_REG_STATUS		0x16		/* Status register */
+
+#endif /* __LINUX_MFD_RETU_H */
-- 
cgit v1.2.3-55-g7522


From 0e8f1398a388bbaa5ca965711b9ed5ac4794332d Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi
Date: Tue, 13 Nov 2012 09:28:47 +0100
Subject: mfd: twl: Remove unused TWL_MODULE definitions

AUDIO and MADC only available on twl4030 series and the TWL_MODULE_* mapping
is not needed.

Acked-by: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/linux/i2c/twl.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h
index 9a5e28462324..7278c72479d1 100644
--- a/include/linux/i2c/twl.h
+++ b/include/linux/i2c/twl.h
@@ -73,9 +73,7 @@
 #define TWL4030_MODULE_SECURED_REG	0x17
 
 #define TWL_MODULE_USB		TWL4030_MODULE_USB
-#define TWL_MODULE_AUDIO_VOICE	TWL4030_MODULE_AUDIO_VOICE
 #define TWL_MODULE_PIH		TWL4030_MODULE_PIH
-#define TWL_MODULE_MADC		TWL4030_MODULE_MADC
 #define TWL_MODULE_MAIN_CHARGE	TWL4030_MODULE_MAIN_CHARGE
 #define TWL_MODULE_PM_MASTER	TWL4030_MODULE_PM_MASTER
 #define TWL_MODULE_PM_RECEIVER	TWL4030_MODULE_PM_RECEIVER
-- 
cgit v1.2.3-55-g7522


From da059ecfc9f9d98556607c6d6db065aa3b7f162d Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi
Date: Tue, 13 Nov 2012 09:28:48 +0100
Subject: mfd: twl: Convert module id definitions to enums

Use enum list for the module definitions (TWL4030_MODULE_*) which will ease
up future work with the IDs.
At the same time group the IDs in block of five so it is easier to find the
ID we are looking for (to count the number they stand for).

At the same time define TWL_MODULE_LED so client drivers can switch to use
it as soon as it is possible.

Acked-by: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/twl-core.c  |  9 +++----
 include/linux/i2c/twl.h | 65 +++++++++++++++++++++++++------------------------
 2 files changed, 36 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c
index d666c9d454cb..bb33b52cfa57 100644
--- a/drivers/mfd/twl-core.c
+++ b/drivers/mfd/twl-core.c
@@ -66,9 +66,6 @@
 
 /* Triton Core internal information (BEGIN) */
 
-/* Last - for index max*/
-#define TWL4030_MODULE_LAST		TWL4030_MODULE_SECURED_REG
-
 #define TWL_NUM_SLAVES		4
 
 #define SUB_CHIP_ID0 0
@@ -184,7 +181,7 @@ struct twl_mapping {
 };
 static struct twl_mapping *twl_map;
 
-static struct twl_mapping twl4030_map[TWL4030_MODULE_LAST + 1] = {
+static struct twl_mapping twl4030_map[] = {
 	/*
 	 * NOTE:  don't change this table without updating the
 	 * <linux/i2c/twl.h> defines for TWL4030_MODULE_*
@@ -327,7 +324,7 @@ int twl_i2c_write(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes)
 	int sid;
 	struct twl_client *twl;
 
-	if (unlikely(mod_no > TWL_MODULE_LAST)) {
+	if (unlikely(mod_no >= TWL_MODULE_LAST)) {
 		pr_err("%s: invalid module number %d\n", DRIVER_NAME, mod_no);
 		return -EPERM;
 	}
@@ -369,7 +366,7 @@ int twl_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes)
 	int sid;
 	struct twl_client *twl;
 
-	if (unlikely(mod_no > TWL_MODULE_LAST)) {
+	if (unlikely(mod_no >= TWL_MODULE_LAST)) {
 		pr_err("%s: invalid module number %d\n", DRIVER_NAME, mod_no);
 		return -EPERM;
 	}
diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h
index 7278c72479d1..b1c44cccef31 100644
--- a/include/linux/i2c/twl.h
+++ b/include/linux/i2c/twl.h
@@ -39,39 +39,39 @@
  * address each module uses within a given i2c slave.
  */
 
-/* Slave 0 (i2c address 0x48) */
-#define TWL4030_MODULE_USB		0x00
-
-/* Slave 1 (i2c address 0x49) */
-#define TWL4030_MODULE_AUDIO_VOICE	0x01
-#define TWL4030_MODULE_GPIO		0x02
-#define TWL4030_MODULE_INTBR		0x03
-#define TWL4030_MODULE_PIH		0x04
-#define TWL4030_MODULE_TEST		0x05
-
-/* Slave 2 (i2c address 0x4a) */
-#define TWL4030_MODULE_KEYPAD		0x06
-#define TWL4030_MODULE_MADC		0x07
-#define TWL4030_MODULE_INTERRUPTS	0x08
-#define TWL4030_MODULE_LED		0x09
-#define TWL4030_MODULE_MAIN_CHARGE	0x0A
-#define TWL4030_MODULE_PRECHARGE	0x0B
-#define TWL4030_MODULE_PWM0		0x0C
-#define TWL4030_MODULE_PWM1		0x0D
-#define TWL4030_MODULE_PWMA		0x0E
-#define TWL4030_MODULE_PWMB		0x0F
-
-#define TWL5031_MODULE_ACCESSORY	0x10
-#define TWL5031_MODULE_INTERRUPTS	0x11
-
-/* Slave 3 (i2c address 0x4b) */
-#define TWL4030_MODULE_BACKUP		0x12
-#define TWL4030_MODULE_INT		0x13
-#define TWL4030_MODULE_PM_MASTER	0x14
-#define TWL4030_MODULE_PM_RECEIVER	0x15
-#define TWL4030_MODULE_RTC		0x16
-#define TWL4030_MODULE_SECURED_REG	0x17
+enum twl4030_module_ids {
+	TWL4030_MODULE_USB = 0,		/* Slave 0 (i2c address 0x48) */
+	TWL4030_MODULE_AUDIO_VOICE,	/* Slave 1 (i2c address 0x49) */
+	TWL4030_MODULE_GPIO,
+	TWL4030_MODULE_INTBR,
+	TWL4030_MODULE_PIH,
+
+	TWL4030_MODULE_TEST,
+	TWL4030_MODULE_KEYPAD,		/* Slave 2 (i2c address 0x4a) */
+	TWL4030_MODULE_MADC,
+	TWL4030_MODULE_INTERRUPTS,
+	TWL4030_MODULE_LED,
+
+	TWL4030_MODULE_MAIN_CHARGE,
+	TWL4030_MODULE_PRECHARGE,
+	TWL4030_MODULE_PWM0,
+	TWL4030_MODULE_PWM1,
+	TWL4030_MODULE_PWMA,
+
+	TWL4030_MODULE_PWMB,
+	TWL5031_MODULE_ACCESSORY,
+	TWL5031_MODULE_INTERRUPTS,
+	TWL4030_MODULE_BACKUP,		/* Slave 3 (i2c address 0x4b) */
+	TWL4030_MODULE_INT,
+
+	TWL4030_MODULE_PM_MASTER,
+	TWL4030_MODULE_PM_RECEIVER,
+	TWL4030_MODULE_RTC,
+	TWL4030_MODULE_SECURED_REG,
+	TWL4030_MODULE_LAST,
+};
 
+/* Similar functionalities implemented in TWL4030/6030 */
 #define TWL_MODULE_USB		TWL4030_MODULE_USB
 #define TWL_MODULE_PIH		TWL4030_MODULE_PIH
 #define TWL_MODULE_MAIN_CHARGE	TWL4030_MODULE_MAIN_CHARGE
@@ -79,6 +79,7 @@
 #define TWL_MODULE_PM_RECEIVER	TWL4030_MODULE_PM_RECEIVER
 #define TWL_MODULE_RTC		TWL4030_MODULE_RTC
 #define TWL_MODULE_PWM		TWL4030_MODULE_PWM0
+#define TWL_MODULE_LED		TWL4030_MODULE_LED
 
 #define TWL6030_MODULE_ID0	0x0D
 #define TWL6030_MODULE_ID1	0x0E
-- 
cgit v1.2.3-55-g7522


From 04575d5a3dc15d762c7428d2745d30b2d448e443 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi
Date: Tue, 13 Nov 2012 09:28:49 +0100
Subject: mfd: twl: Use decimal numbers for TWL6030_MODULE_IDs

It is easier fro humans to understand decimal numbers than hexadecimals when
they are used as indexes.

Acked-by: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/linux/i2c/twl.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h
index b1c44cccef31..1ff54b114efc 100644
--- a/include/linux/i2c/twl.h
+++ b/include/linux/i2c/twl.h
@@ -81,9 +81,9 @@ enum twl4030_module_ids {
 #define TWL_MODULE_PWM		TWL4030_MODULE_PWM0
 #define TWL_MODULE_LED		TWL4030_MODULE_LED
 
-#define TWL6030_MODULE_ID0	0x0D
-#define TWL6030_MODULE_ID1	0x0E
-#define TWL6030_MODULE_ID2	0x0F
+#define TWL6030_MODULE_ID0	13
+#define TWL6030_MODULE_ID1	14
+#define TWL6030_MODULE_ID2	15
 
 #define GPIO_INTR_OFFSET	0
 #define KEYPAD_INTR_OFFSET	1
-- 
cgit v1.2.3-55-g7522


From 8c5dff905714446f8836b40a93bfeabd0aea8c82 Mon Sep 17 00:00:00 2001
From: Sakari Ailus
Date: Sun, 28 Oct 2012 06:44:17 -0300
Subject: [media] v4l, smiapp, smiapp-pll, adp1653: Update contact information

Update contact information to correspond my e-mail address changes.

Signed-off-by: Sakari Ailus <sakari.ailus@iki.fi>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/i2c/adp1653.c                | 4 ++--
 drivers/media/i2c/smiapp-pll.c             | 4 ++--
 drivers/media/i2c/smiapp-pll.h             | 2 +-
 drivers/media/i2c/smiapp/smiapp-core.c     | 6 +++---
 drivers/media/i2c/smiapp/smiapp-limits.c   | 2 +-
 drivers/media/i2c/smiapp/smiapp-limits.h   | 2 +-
 drivers/media/i2c/smiapp/smiapp-quirk.c    | 2 +-
 drivers/media/i2c/smiapp/smiapp-quirk.h    | 2 +-
 drivers/media/i2c/smiapp/smiapp-reg-defs.h | 2 +-
 drivers/media/i2c/smiapp/smiapp-reg.h      | 2 +-
 drivers/media/i2c/smiapp/smiapp-regs.c     | 2 +-
 drivers/media/i2c/smiapp/smiapp-regs.h     | 2 +-
 drivers/media/i2c/smiapp/smiapp.h          | 2 +-
 drivers/media/v4l2-core/v4l2-event.c       | 2 +-
 drivers/media/v4l2-core/v4l2-fh.c          | 2 +-
 include/media/adp1653.h                    | 4 ++--
 include/media/smiapp.h                     | 2 +-
 include/media/v4l2-event.h                 | 2 +-
 include/media/v4l2-fh.h                    | 2 +-
 19 files changed, 24 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/media/i2c/adp1653.c b/drivers/media/i2c/adp1653.c
index 18a38b38fcb8..df163800c8e1 100644
--- a/drivers/media/i2c/adp1653.c
+++ b/drivers/media/i2c/adp1653.c
@@ -3,10 +3,10 @@
  *
  * Copyright (C) 2008--2011 Nokia Corporation
  *
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * Contributors:
- *	Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ *	Sakari Ailus <sakari.ailus@iki.fi>
  *	Tuukka Toivonen <tuukkat76@gmail.com>
  *
  * This program is free software; you can redistribute it and/or
diff --git a/drivers/media/i2c/smiapp-pll.c b/drivers/media/i2c/smiapp-pll.c
index 61e2401c1b35..d8d5da7c52db 100644
--- a/drivers/media/i2c/smiapp-pll.c
+++ b/drivers/media/i2c/smiapp-pll.c
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2011--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -438,6 +438,6 @@ int smiapp_pll_calculate(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(smiapp_pll_calculate);
 
-MODULE_AUTHOR("Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>");
+MODULE_AUTHOR("Sakari Ailus <sakari.ailus@iki.fi>");
 MODULE_DESCRIPTION("Generic SMIA/SMIA++ PLL calculator");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/i2c/smiapp-pll.h b/drivers/media/i2c/smiapp-pll.h
index 9491a41fcce7..a4a649834a18 100644
--- a/drivers/media/i2c/smiapp-pll.h
+++ b/drivers/media/i2c/smiapp-pll.h
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index 81ec4ac5bcdd..83c7ed7ffcc2 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2010--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * Based on smiapp driver by Vimarsh Zutshi
  * Based on jt8ev1.c by Vimarsh Zutshi
@@ -991,7 +991,7 @@ static int smiapp_setup_flash_strobe(struct smiapp_sensor *sensor)
 	 * do not change, or if you do at least know what you're
 	 * doing. :-)
 	 *
-	 * Sakari Ailus <sakari.ailus@maxwell.research.nokia.com> 2010-10-25
+	 * Sakari Ailus <sakari.ailus@iki.fi> 2010-10-25
 	 *
 	 * flash_strobe_length [us] / 10^6 = (tFlash_strobe_width_ctrl
 	 *	/ EXTCLK freq [Hz]) * flash_strobe_adjustment
@@ -2887,6 +2887,6 @@ static struct i2c_driver smiapp_i2c_driver = {
 
 module_i2c_driver(smiapp_i2c_driver);
 
-MODULE_AUTHOR("Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>");
+MODULE_AUTHOR("Sakari Ailus <sakari.ailus@iki.fi>");
 MODULE_DESCRIPTION("Generic SMIA/SMIA++ camera module driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/i2c/smiapp/smiapp-limits.c b/drivers/media/i2c/smiapp/smiapp-limits.c
index fb2f81ad8c3b..847cb235e198 100644
--- a/drivers/media/i2c/smiapp/smiapp-limits.c
+++ b/drivers/media/i2c/smiapp/smiapp-limits.c
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2011--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/i2c/smiapp/smiapp-limits.h b/drivers/media/i2c/smiapp/smiapp-limits.h
index 9ae765e23ea5..343e9c3827fc 100644
--- a/drivers/media/i2c/smiapp/smiapp-limits.h
+++ b/drivers/media/i2c/smiapp/smiapp-limits.h
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2011--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/i2c/smiapp/smiapp-quirk.c b/drivers/media/i2c/smiapp/smiapp-quirk.c
index 725cf62836c6..bb8c506e0e3d 100644
--- a/drivers/media/i2c/smiapp/smiapp-quirk.c
+++ b/drivers/media/i2c/smiapp/smiapp-quirk.c
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2011--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/i2c/smiapp/smiapp-quirk.h b/drivers/media/i2c/smiapp/smiapp-quirk.h
index 86fd3e8bfb0f..504a6d80ced5 100644
--- a/drivers/media/i2c/smiapp/smiapp-quirk.h
+++ b/drivers/media/i2c/smiapp/smiapp-quirk.h
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2011--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/i2c/smiapp/smiapp-reg-defs.h b/drivers/media/i2c/smiapp/smiapp-reg-defs.h
index defa7c5adebf..3aa0ca948d87 100644
--- a/drivers/media/i2c/smiapp/smiapp-reg-defs.h
+++ b/drivers/media/i2c/smiapp/smiapp-reg-defs.h
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2011--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/i2c/smiapp/smiapp-reg.h b/drivers/media/i2c/smiapp/smiapp-reg.h
index 54568ca2fe6d..b0dcbb8fa5e2 100644
--- a/drivers/media/i2c/smiapp/smiapp-reg.h
+++ b/drivers/media/i2c/smiapp/smiapp-reg.h
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2011--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/i2c/smiapp/smiapp-regs.c b/drivers/media/i2c/smiapp/smiapp-regs.c
index 70e0d8db0130..4fac32cfcb3f 100644
--- a/drivers/media/i2c/smiapp/smiapp-regs.c
+++ b/drivers/media/i2c/smiapp/smiapp-regs.c
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2011--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/i2c/smiapp/smiapp-regs.h b/drivers/media/i2c/smiapp/smiapp-regs.h
index 7f9013b47971..eefc6c84d5fe 100644
--- a/drivers/media/i2c/smiapp/smiapp-regs.h
+++ b/drivers/media/i2c/smiapp/smiapp-regs.h
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2011--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/i2c/smiapp/smiapp.h b/drivers/media/i2c/smiapp/smiapp.h
index 4182a695ab53..7cc5aae662fd 100644
--- a/drivers/media/i2c/smiapp/smiapp.h
+++ b/drivers/media/i2c/smiapp/smiapp.h
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2010--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/v4l2-core/v4l2-event.c b/drivers/media/v4l2-core/v4l2-event.c
index 18a040b935a3..c72009218152 100644
--- a/drivers/media/v4l2-core/v4l2-event.c
+++ b/drivers/media/v4l2-core/v4l2-event.c
@@ -5,7 +5,7 @@
  *
  * Copyright (C) 2009--2010 Nokia Corporation.
  *
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/v4l2-core/v4l2-fh.c b/drivers/media/v4l2-core/v4l2-fh.c
index 9e3fc040ea20..e57c002b4150 100644
--- a/drivers/media/v4l2-core/v4l2-fh.c
+++ b/drivers/media/v4l2-core/v4l2-fh.c
@@ -5,7 +5,7 @@
  *
  * Copyright (C) 2009--2010 Nokia Corporation.
  *
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/include/media/adp1653.h b/include/media/adp1653.h
index 50a1af88aed0..1d9b48a3bd80 100644
--- a/include/media/adp1653.h
+++ b/include/media/adp1653.h
@@ -3,10 +3,10 @@
  *
  * Copyright (C) 2008--2011 Nokia Corporation
  *
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * Contributors:
- *	Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ *	Sakari Ailus <sakari.ailus@iki.fi>
  *	Tuukka Toivonen <tuukkat76@gmail.com>
  *
  * This program is free software; you can redistribute it and/or
diff --git a/include/media/smiapp.h b/include/media/smiapp.h
index 9ab07fd45d5c..07f96a89e189 100644
--- a/include/media/smiapp.h
+++ b/include/media/smiapp.h
@@ -4,7 +4,7 @@
  * Generic driver for SMIA/SMIA++ compliant camera modules
  *
  * Copyright (C) 2011--2012 Nokia Corporation
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/include/media/v4l2-event.h b/include/media/v4l2-event.h
index e7c5d170a9cd..eff85f934b24 100644
--- a/include/media/v4l2-event.h
+++ b/include/media/v4l2-event.h
@@ -5,7 +5,7 @@
  *
  * Copyright (C) 2009--2010 Nokia Corporation.
  *
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/include/media/v4l2-fh.h b/include/media/v4l2-fh.h
index 52513c225c18..a62ee18cb7b7 100644
--- a/include/media/v4l2-fh.h
+++ b/include/media/v4l2-fh.h
@@ -6,7 +6,7 @@
  *
  * Copyright (C) 2009--2010 Nokia Corporation.
  *
- * Contact: Sakari Ailus <sakari.ailus@maxwell.research.nokia.com>
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
-- 
cgit v1.2.3-55-g7522


From baa29837a76d5738837602ff249a0c371591d7c7 Mon Sep 17 00:00:00 2001
From: Lad, Prabhakar
Date: Fri, 9 Nov 2012 05:59:32 -0300
Subject: [media] media: davinci: vpbe: fix build warning

Warnings were generated because of the following commit changed data type for
address pointer
195bbca ARM: 7500/1: io: avoid writeback addressing modes for __raw_ accessors
add  __iomem annotation to fix following warnings
drivers/media/platform/davinci/vpbe_osd.c: In function ‘osd_read’:
drivers/media/platform/davinci/vpbe_osd.c:49:2: warning: passing
 argument 1 of ‘__raw_readl’ makes pointer from integer without a cast [enabled by default]
arch/arm/include/asm/io.h:104:19: note: expected ‘const volatile
 void *’ but argument is of type ‘long unsigned int’
This patch stores the ioremap_nocache() returned address in a
void __iomem * instead of a unsigned long and passes the same to
readl/writel functions which fixes the above warnings.

Signed-off-by: Lad, Prabhakar <prabhakar.lad@ti.com>
Signed-off-by: Manjunath Hadli <manjunath.hadli@ti.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/platform/davinci/vpbe_osd.c | 9 ++++-----
 include/media/davinci/vpbe_osd.h          | 2 +-
 2 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/media/platform/davinci/vpbe_osd.c b/drivers/media/platform/davinci/vpbe_osd.c
index bba299dbf396..707f243f810d 100644
--- a/drivers/media/platform/davinci/vpbe_osd.c
+++ b/drivers/media/platform/davinci/vpbe_osd.c
@@ -62,7 +62,7 @@ static inline u32 osd_set(struct osd_state *sd, u32 mask, u32 offset)
 {
 	struct osd_state *osd = sd;
 
-	u32 addr = osd->osd_base + offset;
+	void __iomem *addr = osd->osd_base + offset;
 	u32 val = readl(addr) | mask;
 
 	writel(val, addr);
@@ -74,7 +74,7 @@ static inline u32 osd_clear(struct osd_state *sd, u32 mask, u32 offset)
 {
 	struct osd_state *osd = sd;
 
-	u32 addr = osd->osd_base + offset;
+	void __iomem *addr = osd->osd_base + offset;
 	u32 val = readl(addr) & ~mask;
 
 	writel(val, addr);
@@ -87,7 +87,7 @@ static inline u32 osd_modify(struct osd_state *sd, u32 mask, u32 val,
 {
 	struct osd_state *osd = sd;
 
-	u32 addr = osd->osd_base + offset;
+	void __iomem *addr = osd->osd_base + offset;
 	u32 new_val = (readl(addr) & ~mask) | (val & mask);
 
 	writel(new_val, addr);
@@ -1559,8 +1559,7 @@ static int osd_probe(struct platform_device *pdev)
 		ret = -ENODEV;
 		goto free_mem;
 	}
-	osd->osd_base = (unsigned long)ioremap_nocache(res->start,
-							osd->osd_size);
+	osd->osd_base = ioremap_nocache(res->start, osd->osd_size);
 	if (!osd->osd_base) {
 		dev_err(osd->dev, "Unable to map the OSD region\n");
 		ret = -ENODEV;
diff --git a/include/media/davinci/vpbe_osd.h b/include/media/davinci/vpbe_osd.h
index d7e397a444e6..5ab0d8d41f68 100644
--- a/include/media/davinci/vpbe_osd.h
+++ b/include/media/davinci/vpbe_osd.h
@@ -357,7 +357,7 @@ struct osd_state {
 	spinlock_t lock;
 	struct device *dev;
 	dma_addr_t osd_base_phys;
-	unsigned long osd_base;
+	void __iomem *osd_base;
 	unsigned long osd_size;
 	/* 1-->the isr will toggle the VID0 ping-pong buffer */
 	int pingpong;
-- 
cgit v1.2.3-55-g7522


From 13fc23d3067e996c03d8b602266f47d27d205d36 Mon Sep 17 00:00:00 2001
From: Lad, Prabhakar
Date: Mon, 22 Oct 2012 09:27:13 -0300
Subject: [media] media: davinci: vpbe: migrate driver to videobuf2

This patch migrates VPBE display driver to videobuf2 framework.

Signed-off-by: Lad, Prabhakar <prabhakar.lad@ti.com>
Signed-off-by: Manjunath Hadli <manjunath.hadli@ti.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/platform/davinci/Kconfig        |   2 +-
 drivers/media/platform/davinci/vpbe_display.c | 294 +++++++++++++++-----------
 include/media/davinci/vpbe_display.h          |  15 +-
 3 files changed, 187 insertions(+), 124 deletions(-)

(limited to 'include')

diff --git a/drivers/media/platform/davinci/Kconfig b/drivers/media/platform/davinci/Kconfig
index 78e26d24f637..3c56037c82fc 100644
--- a/drivers/media/platform/davinci/Kconfig
+++ b/drivers/media/platform/davinci/Kconfig
@@ -101,7 +101,7 @@ config VIDEO_DM644X_VPBE
 	tristate "DM644X VPBE HW module"
 	depends on ARCH_DAVINCI_DM644x
 	select VIDEO_VPSS_SYSTEM
-	select VIDEOBUF_DMA_CONTIG
+	select VIDEOBUF2_DMA_CONTIG
 	help
 	    Enables VPBE modules used for display on a DM644x
 	    SoC.
diff --git a/drivers/media/platform/davinci/vpbe_display.c b/drivers/media/platform/davinci/vpbe_display.c
index 161c77650e2f..974957fd7f71 100644
--- a/drivers/media/platform/davinci/vpbe_display.c
+++ b/drivers/media/platform/davinci/vpbe_display.c
@@ -47,6 +47,9 @@ static int debug;
 
 module_param(debug, int, 0644);
 
+static int vpbe_set_osd_display_params(struct vpbe_display *disp_dev,
+			struct vpbe_layer *layer);
+
 static int venc_is_second_field(struct vpbe_display *disp_dev)
 {
 	struct vpbe_device *vpbe_dev = disp_dev->vpbe_dev;
@@ -73,10 +76,11 @@ static void vpbe_isr_even_field(struct vpbe_display *disp_obj,
 	if (layer->cur_frm == layer->next_frm)
 		return;
 	ktime_get_ts(&timevalue);
-	layer->cur_frm->ts.tv_sec = timevalue.tv_sec;
-	layer->cur_frm->ts.tv_usec = timevalue.tv_nsec / NSEC_PER_USEC;
-	layer->cur_frm->state = VIDEOBUF_DONE;
-	wake_up_interruptible(&layer->cur_frm->done);
+	layer->cur_frm->vb.v4l2_buf.timestamp.tv_sec =
+		timevalue.tv_sec;
+	layer->cur_frm->vb.v4l2_buf.timestamp.tv_usec =
+		timevalue.tv_nsec / NSEC_PER_USEC;
+	vb2_buffer_done(&layer->cur_frm->vb, VB2_BUF_STATE_DONE);
 	/* Make cur_frm pointing to next_frm */
 	layer->cur_frm = layer->next_frm;
 }
@@ -99,16 +103,14 @@ static void vpbe_isr_odd_field(struct vpbe_display *disp_obj,
 	 * otherwise hold on current frame
 	 * Get next from the buffer queue
 	 */
-	layer->next_frm = list_entry(
-				layer->dma_queue.next,
-				struct  videobuf_buffer,
-				queue);
+	layer->next_frm = list_entry(layer->dma_queue.next,
+			  struct  vpbe_disp_buffer, list);
 	/* Remove that from the buffer queue */
-	list_del(&layer->next_frm->queue);
+	list_del(&layer->next_frm->list);
 	spin_unlock(&disp_obj->dma_queue_lock);
 	/* Mark state of the frame to active */
-	layer->next_frm->state = VIDEOBUF_ACTIVE;
-	addr = videobuf_to_dma_contig(layer->next_frm);
+	layer->next_frm->vb.state = VB2_BUF_STATE_ACTIVE;
+	addr = vb2_dma_contig_plane_dma_addr(&layer->next_frm->vb, 0);
 	osd_device->ops.start_layer(osd_device,
 			layer->layer_info.id,
 			addr,
@@ -199,39 +201,29 @@ static irqreturn_t venc_isr(int irq, void *arg)
 
 /*
  * vpbe_buffer_prepare()
- * This is the callback function called from videobuf_qbuf() function
+ * This is the callback function called from vb2_qbuf() function
  * the buffer is prepared and user space virtual address is converted into
  * physical address
  */
-static int vpbe_buffer_prepare(struct videobuf_queue *q,
-				  struct videobuf_buffer *vb,
-				  enum v4l2_field field)
+static int vpbe_buffer_prepare(struct vb2_buffer *vb)
 {
-	struct vpbe_fh *fh = q->priv_data;
+	struct vpbe_fh *fh = vb2_get_drv_priv(vb->vb2_queue);
+	struct vb2_queue *q = vb->vb2_queue;
 	struct vpbe_layer *layer = fh->layer;
 	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
 	unsigned long addr;
-	int ret;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
 				"vpbe_buffer_prepare\n");
 
-	/* If buffer is not initialized, initialize it */
-	if (VIDEOBUF_NEEDS_INIT == vb->state) {
-		vb->width = layer->pix_fmt.width;
-		vb->height = layer->pix_fmt.height;
-		vb->size = layer->pix_fmt.sizeimage;
-		vb->field = field;
-
-		ret = videobuf_iolock(q, vb, NULL);
-		if (ret < 0) {
-			v4l2_err(&vpbe_dev->v4l2_dev, "Failed to map \
-				user address\n");
+	if (vb->state != VB2_BUF_STATE_ACTIVE &&
+		vb->state != VB2_BUF_STATE_PREPARED) {
+		vb2_set_plane_payload(vb, 0, layer->pix_fmt.sizeimage);
+		if (vb2_plane_vaddr(vb, 0) &&
+		vb2_get_plane_payload(vb, 0) > vb2_plane_size(vb, 0))
 			return -EINVAL;
-		}
-
-		addr = videobuf_to_dma_contig(vb);
 
+		addr = vb2_dma_contig_plane_dma_addr(vb, 0);
 		if (q->streaming) {
 			if (!IS_ALIGNED(addr, 8)) {
 				v4l2_err(&vpbe_dev->v4l2_dev,
@@ -240,7 +232,6 @@ static int vpbe_buffer_prepare(struct videobuf_queue *q,
 				return -EINVAL;
 			}
 		}
-		vb->state = VIDEOBUF_PREPARED;
 	}
 	return 0;
 }
@@ -249,22 +240,26 @@ static int vpbe_buffer_prepare(struct videobuf_queue *q,
  * vpbe_buffer_setup()
  * This function allocates memory for the buffers
  */
-static int vpbe_buffer_setup(struct videobuf_queue *q,
-				unsigned int *count,
-				unsigned int *size)
+static int
+vpbe_buffer_queue_setup(struct vb2_queue *vq, const struct v4l2_format *fmt,
+			unsigned int *nbuffers, unsigned int *nplanes,
+			unsigned int sizes[], void *alloc_ctxs[])
+
 {
 	/* Get the file handle object and layer object */
-	struct vpbe_fh *fh = q->priv_data;
+	struct vpbe_fh *fh = vb2_get_drv_priv(vq);
 	struct vpbe_layer *layer = fh->layer;
 	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "vpbe_buffer_setup\n");
 
-	*size = layer->pix_fmt.sizeimage;
-
 	/* Store number of buffers allocated in numbuffer member */
-	if (*count < VPBE_DEFAULT_NUM_BUFS)
-		*count = layer->numbuffers = VPBE_DEFAULT_NUM_BUFS;
+	if (*nbuffers < VPBE_DEFAULT_NUM_BUFS)
+		*nbuffers = layer->numbuffers = VPBE_DEFAULT_NUM_BUFS;
+
+	*nplanes = 1;
+	sizes[0] = layer->pix_fmt.sizeimage;
+	alloc_ctxs[0] = layer->alloc_ctx;
 
 	return 0;
 }
@@ -273,11 +268,12 @@ static int vpbe_buffer_setup(struct videobuf_queue *q,
  * vpbe_buffer_queue()
  * This function adds the buffer to DMA queue
  */
-static void vpbe_buffer_queue(struct videobuf_queue *q,
-				 struct videobuf_buffer *vb)
+static void vpbe_buffer_queue(struct vb2_buffer *vb)
 {
 	/* Get the file handle object and layer object */
-	struct vpbe_fh *fh = q->priv_data;
+	struct vpbe_fh *fh = vb2_get_drv_priv(vb->vb2_queue);
+	struct vpbe_disp_buffer *buf = container_of(vb,
+				struct vpbe_disp_buffer, vb);
 	struct vpbe_layer *layer = fh->layer;
 	struct vpbe_display *disp = fh->disp_dev;
 	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
@@ -288,39 +284,125 @@ static void vpbe_buffer_queue(struct videobuf_queue *q,
 
 	/* add the buffer to the DMA queue */
 	spin_lock_irqsave(&disp->dma_queue_lock, flags);
-	list_add_tail(&vb->queue, &layer->dma_queue);
+	list_add_tail(&buf->list, &layer->dma_queue);
 	spin_unlock_irqrestore(&disp->dma_queue_lock, flags);
-	/* Change state of the buffer */
-	vb->state = VIDEOBUF_QUEUED;
 }
 
 /*
- * vpbe_buffer_release()
- * This function is called from the videobuf layer to free memory allocated to
+ * vpbe_buf_cleanup()
+ * This function is called from the vb2 layer to free memory allocated to
  * the buffers
  */
-static void vpbe_buffer_release(struct videobuf_queue *q,
-				   struct videobuf_buffer *vb)
+static void vpbe_buf_cleanup(struct vb2_buffer *vb)
 {
 	/* Get the file handle object and layer object */
-	struct vpbe_fh *fh = q->priv_data;
+	struct vpbe_fh *fh = vb2_get_drv_priv(vb->vb2_queue);
 	struct vpbe_layer *layer = fh->layer;
 	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vpbe_disp_buffer *buf = container_of(vb,
+					struct vpbe_disp_buffer, vb);
+	unsigned long flags;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
-			"vpbe_buffer_release\n");
+			"vpbe_buf_cleanup\n");
+
+	spin_lock_irqsave(&layer->irqlock, flags);
+	if (vb->state == VB2_BUF_STATE_ACTIVE)
+		list_del_init(&buf->list);
+	spin_unlock_irqrestore(&layer->irqlock, flags);
+}
+
+static void vpbe_wait_prepare(struct vb2_queue *vq)
+{
+	struct vpbe_fh *fh = vb2_get_drv_priv(vq);
+	struct vpbe_layer *layer = fh->layer;
+
+	mutex_unlock(&layer->opslock);
+}
+
+static void vpbe_wait_finish(struct vb2_queue *vq)
+{
+	struct vpbe_fh *fh = vb2_get_drv_priv(vq);
+	struct vpbe_layer *layer = fh->layer;
+
+	mutex_lock(&layer->opslock);
+}
+
+static int vpbe_buffer_init(struct vb2_buffer *vb)
+{
+	struct vpbe_disp_buffer *buf = container_of(vb,
+					struct vpbe_disp_buffer, vb);
+
+	INIT_LIST_HEAD(&buf->list);
+	return 0;
+}
+
+static int vpbe_start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct vpbe_fh *fh = vb2_get_drv_priv(vq);
+	struct vpbe_layer *layer = fh->layer;
+	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	int ret;
+
+	/* If buffer queue is empty, return error */
+	if (list_empty(&layer->dma_queue)) {
+		v4l2_err(&vpbe_dev->v4l2_dev, "buffer queue is empty\n");
+		return -EINVAL;
+	}
+	/* Get the next frame from the buffer queue */
+	layer->next_frm = layer->cur_frm = list_entry(layer->dma_queue.next,
+				struct vpbe_disp_buffer, list);
+	/* Remove buffer from the buffer queue */
+	list_del(&layer->cur_frm->list);
+	/* Mark state of the current frame to active */
+	layer->cur_frm->vb.state = VB2_BUF_STATE_ACTIVE;
+	/* Initialize field_id and started member */
+	layer->field_id = 0;
+
+	/* Set parameters in OSD and VENC */
+	ret = vpbe_set_osd_display_params(fh->disp_dev, layer);
+	if (ret < 0)
+		return ret;
 
-	if (V4L2_MEMORY_USERPTR != layer->memory)
-		videobuf_dma_contig_free(q, vb);
+	/*
+	 * if request format is yuv420 semiplanar, need to
+	 * enable both video windows
+	 */
+	layer->started = 1;
+	layer->layer_first_int = 1;
+
+	return ret;
+}
+
+static int vpbe_stop_streaming(struct vb2_queue *vq)
+{
+	struct vpbe_fh *fh = vb2_get_drv_priv(vq);
+	struct vpbe_layer *layer = fh->layer;
+
+	if (!vb2_is_streaming(vq))
+		return 0;
+
+	/* release all active buffers */
+	while (!list_empty(&layer->dma_queue)) {
+		layer->next_frm = list_entry(layer->dma_queue.next,
+						struct vpbe_disp_buffer, list);
+		list_del(&layer->next_frm->list);
+		vb2_buffer_done(&layer->next_frm->vb, VB2_BUF_STATE_ERROR);
+	}
 
-	vb->state = VIDEOBUF_NEEDS_INIT;
+	return 0;
 }
 
-static struct videobuf_queue_ops video_qops = {
-	.buf_setup = vpbe_buffer_setup,
+static struct vb2_ops video_qops = {
+	.queue_setup = vpbe_buffer_queue_setup,
+	.wait_prepare = vpbe_wait_prepare,
+	.wait_finish = vpbe_wait_finish,
+	.buf_init = vpbe_buffer_init,
 	.buf_prepare = vpbe_buffer_prepare,
+	.start_streaming = vpbe_start_streaming,
+	.stop_streaming = vpbe_stop_streaming,
+	.buf_cleanup = vpbe_buf_cleanup,
 	.buf_queue = vpbe_buffer_queue,
-	.buf_release = vpbe_buffer_release,
 };
 
 static
@@ -345,7 +427,7 @@ static int vpbe_set_osd_display_params(struct vpbe_display *disp_dev,
 	unsigned long addr;
 	int ret;
 
-	addr = videobuf_to_dma_contig(layer->cur_frm);
+	addr = vb2_dma_contig_plane_dma_addr(&layer->cur_frm->vb, 0);
 	/* Set address in the display registers */
 	osd_device->ops.start_layer(osd_device,
 				    layer->layer_info.id,
@@ -1161,7 +1243,7 @@ static int vpbe_display_streamoff(struct file *file, void *priv,
 	osd_device->ops.disable_layer(osd_device,
 			layer->layer_info.id);
 	layer->started = 0;
-	ret = videobuf_streamoff(&layer->buffer_queue);
+	ret = vb2_streamoff(&layer->buffer_queue, buf_type);
 
 	return ret;
 }
@@ -1199,46 +1281,15 @@ static int vpbe_display_streamon(struct file *file, void *priv,
 	}
 
 	/*
-	 * Call videobuf_streamon to start streaming
+	 * Call vb2_streamon to start streaming
 	 * in videobuf
 	 */
-	ret = videobuf_streamon(&layer->buffer_queue);
+	ret = vb2_streamon(&layer->buffer_queue, buf_type);
 	if (ret) {
 		v4l2_err(&vpbe_dev->v4l2_dev,
-		"error in videobuf_streamon\n");
+		"error in vb2_streamon\n");
 		return ret;
 	}
-	/* If buffer queue is empty, return error */
-	if (list_empty(&layer->dma_queue)) {
-		v4l2_err(&vpbe_dev->v4l2_dev, "buffer queue is empty\n");
-		goto streamoff;
-	}
-	/* Get the next frame from the buffer queue */
-	layer->next_frm = layer->cur_frm = list_entry(layer->dma_queue.next,
-				struct videobuf_buffer, queue);
-	/* Remove buffer from the buffer queue */
-	list_del(&layer->cur_frm->queue);
-	/* Mark state of the current frame to active */
-	layer->cur_frm->state = VIDEOBUF_ACTIVE;
-	/* Initialize field_id and started member */
-	layer->field_id = 0;
-
-	/* Set parameters in OSD and VENC */
-	ret = vpbe_set_osd_display_params(disp_dev, layer);
-	if (ret < 0)
-		goto streamoff;
-
-	/*
-	 * if request format is yuv420 semiplanar, need to
-	 * enable both video windows
-	 */
-	layer->started = 1;
-
-	layer->layer_first_int = 1;
-
-	return ret;
-streamoff:
-	ret = videobuf_streamoff(&layer->buffer_queue);
 	return ret;
 }
 
@@ -1265,10 +1316,10 @@ static int vpbe_display_dqbuf(struct file *file, void *priv,
 	}
 	if (file->f_flags & O_NONBLOCK)
 		/* Call videobuf_dqbuf for non blocking mode */
-		ret = videobuf_dqbuf(&layer->buffer_queue, buf, 1);
+		ret = vb2_dqbuf(&layer->buffer_queue, buf, 1);
 	else
 		/* Call videobuf_dqbuf for blocking mode */
-		ret = videobuf_dqbuf(&layer->buffer_queue, buf, 0);
+		ret = vb2_dqbuf(&layer->buffer_queue, buf, 0);
 
 	return ret;
 }
@@ -1295,7 +1346,7 @@ static int vpbe_display_qbuf(struct file *file, void *priv,
 		return -EACCES;
 	}
 
-	return videobuf_qbuf(&layer->buffer_queue, p);
+	return vb2_qbuf(&layer->buffer_queue, p);
 }
 
 static int vpbe_display_querybuf(struct file *file, void *priv,
@@ -1304,7 +1355,6 @@ static int vpbe_display_querybuf(struct file *file, void *priv,
 	struct vpbe_fh *fh = file->private_data;
 	struct vpbe_layer *layer = fh->layer;
 	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
-	int ret;
 
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev,
 		"VIDIOC_QUERYBUF, layer id = %d\n",
@@ -1314,11 +1364,8 @@ static int vpbe_display_querybuf(struct file *file, void *priv,
 		v4l2_err(&vpbe_dev->v4l2_dev, "Invalid buffer type\n");
 		return -EINVAL;
 	}
-
-	/* Call videobuf_querybuf to get information */
-	ret = videobuf_querybuf(&layer->buffer_queue, buf);
-
-	return ret;
+	/* Call vb2_querybuf to get information */
+	return vb2_querybuf(&layer->buffer_queue, buf);
 }
 
 static int vpbe_display_reqbufs(struct file *file, void *priv,
@@ -1327,8 +1374,8 @@ static int vpbe_display_reqbufs(struct file *file, void *priv,
 	struct vpbe_fh *fh = file->private_data;
 	struct vpbe_layer *layer = fh->layer;
 	struct vpbe_device *vpbe_dev = fh->disp_dev->vpbe_dev;
+	struct vb2_queue *q;
 	int ret;
-
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "vpbe_display_reqbufs\n");
 
 	if (V4L2_BUF_TYPE_VIDEO_OUTPUT != req_buf->type) {
@@ -1342,15 +1389,26 @@ static int vpbe_display_reqbufs(struct file *file, void *priv,
 		return -EBUSY;
 	}
 	/* Initialize videobuf queue as per the buffer type */
-	videobuf_queue_dma_contig_init(&layer->buffer_queue,
-				&video_qops,
-				vpbe_dev->pdev,
-				&layer->irqlock,
-				V4L2_BUF_TYPE_VIDEO_OUTPUT,
-				layer->pix_fmt.field,
-				sizeof(struct videobuf_buffer),
-				fh, NULL);
+	layer->alloc_ctx = vb2_dma_contig_init_ctx(vpbe_dev->pdev);
+	if (!layer->alloc_ctx) {
+		v4l2_err(&vpbe_dev->v4l2_dev, "Failed to get the context\n");
+		return -EINVAL;
+	}
+	q = &layer->buffer_queue;
+	memset(q, 0, sizeof(*q));
+	q->type = V4L2_BUF_TYPE_VIDEO_OUTPUT;
+	q->io_modes = VB2_MMAP | VB2_USERPTR;
+	q->drv_priv = fh;
+	q->ops = &video_qops;
+	q->mem_ops = &vb2_dma_contig_memops;
+	q->buf_struct_size = sizeof(struct vpbe_disp_buffer);
 
+	ret = vb2_queue_init(q);
+	if (ret) {
+		v4l2_err(&vpbe_dev->v4l2_dev, "vb2_queue_init() failed\n");
+		vb2_dma_contig_cleanup_ctx(layer->alloc_ctx);
+		return ret;
+	}
 	/* Set io allowed member of file handle to TRUE */
 	fh->io_allowed = 1;
 	/* Increment io usrs member of layer object to 1 */
@@ -1360,9 +1418,7 @@ static int vpbe_display_reqbufs(struct file *file, void *priv,
 	/* Initialize buffer queue */
 	INIT_LIST_HEAD(&layer->dma_queue);
 	/* Allocate buffers */
-	ret = videobuf_reqbufs(&layer->buffer_queue, req_buf);
-
-	return ret;
+	return vb2_reqbufs(q, req_buf);
 }
 
 /*
@@ -1381,7 +1437,7 @@ static int vpbe_display_mmap(struct file *filep, struct vm_area_struct *vma)
 
 	if (mutex_lock_interruptible(&layer->opslock))
 		return -ERESTARTSYS;
-	ret = videobuf_mmap_mapper(&layer->buffer_queue, vma);
+	ret = vb2_mmap(&layer->buffer_queue, vma);
 	mutex_unlock(&layer->opslock);
 	return ret;
 }
@@ -1398,7 +1454,7 @@ static unsigned int vpbe_display_poll(struct file *filep, poll_table *wait)
 	v4l2_dbg(1, debug, &vpbe_dev->v4l2_dev, "vpbe_display_poll\n");
 	if (layer->started) {
 		mutex_lock(&layer->opslock);
-		err = videobuf_poll_stream(filep, &layer->buffer_queue, wait);
+		err = vb2_poll(&layer->buffer_queue, filep, wait);
 		mutex_unlock(&layer->opslock);
 	}
 	return err;
@@ -1488,8 +1544,8 @@ static int vpbe_display_release(struct file *file)
 				layer->layer_info.id);
 		layer->started = 0;
 		/* Free buffers allocated */
-		videobuf_queue_cancel(&layer->buffer_queue);
-		videobuf_mmap_free(&layer->buffer_queue);
+		vb2_queue_release(&layer->buffer_queue);
+		vb2_dma_contig_cleanup_ctx(&layer->buffer_queue);
 	}
 
 	/* Decrement layer usrs counter */
diff --git a/include/media/davinci/vpbe_display.h b/include/media/davinci/vpbe_display.h
index dbf6b37682cd..8dffffedbb59 100644
--- a/include/media/davinci/vpbe_display.h
+++ b/include/media/davinci/vpbe_display.h
@@ -16,7 +16,7 @@
 /* Header files */
 #include <linux/videodev2.h>
 #include <media/v4l2-common.h>
-#include <media/videobuf-dma-contig.h>
+#include <media/videobuf2-dma-contig.h>
 #include <media/davinci/vpbe_types.h>
 #include <media/davinci/vpbe_osd.h>
 #include <media/davinci/vpbe.h>
@@ -62,6 +62,11 @@ struct display_layer_info {
 	enum osd_v_exp_ratio v_exp;
 };
 
+struct vpbe_disp_buffer {
+	struct vb2_buffer vb;
+	struct list_head list;
+};
+
 /* vpbe display object structure */
 struct vpbe_layer {
 	/* number of buffers in fbuffers */
@@ -69,13 +74,15 @@ struct vpbe_layer {
 	/* Pointer to the vpbe_display */
 	struct vpbe_display *disp_dev;
 	/* Pointer pointing to current v4l2_buffer */
-	struct videobuf_buffer *cur_frm;
+	struct vpbe_disp_buffer *cur_frm;
 	/* Pointer pointing to next v4l2_buffer */
-	struct videobuf_buffer *next_frm;
+	struct vpbe_disp_buffer *next_frm;
 	/* videobuf specific parameters
 	 * Buffer queue used in video-buf
 	 */
-	struct videobuf_queue buffer_queue;
+	struct vb2_queue buffer_queue;
+	/* allocator-specific contexts for each plane */
+	struct vb2_alloc_ctx *alloc_ctx;
 	/* Queue of filled frames */
 	struct list_head dma_queue;
 	/* Used in video-buf */
-- 
cgit v1.2.3-55-g7522


From ef85fb28305fad7617f307383ebba554a3a891a2 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Tue, 20 Nov 2012 22:24:27 +0000
Subject: bcma: add locking around GPIO register accesses

The GPIOs are access through some registers in the chip common core.
We need locking around these GPIO accesses, all GPIOs are accessed
through the same registers and parallel writes will cause problems.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Patchwork: http://patchwork.linux-mips.org/patch/4585
Acked-by: Florian Fainelli <florian@openwrt.org>
---
 drivers/bcma/driver_chipcommon.c            | 47 ++++++++++++++++++++++++++---
 include/linux/bcma/bcma_driver_chipcommon.h |  3 ++
 2 files changed, 45 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c
index a4c3ebcc4c86..c9b63d9ff61d 100644
--- a/drivers/bcma/driver_chipcommon.c
+++ b/drivers/bcma/driver_chipcommon.c
@@ -30,6 +30,8 @@ void bcma_core_chipcommon_init(struct bcma_drv_cc *cc)
 	if (cc->setup_done)
 		return;
 
+	spin_lock_init(&cc->gpio_lock);
+
 	if (cc->core->id.rev >= 11)
 		cc->status = bcma_cc_read32(cc, BCMA_CC_CHIPSTAT);
 	cc->capabilities = bcma_cc_read32(cc, BCMA_CC_CAP);
@@ -84,28 +86,63 @@ u32 bcma_chipco_gpio_in(struct bcma_drv_cc *cc, u32 mask)
 
 u32 bcma_chipco_gpio_out(struct bcma_drv_cc *cc, u32 mask, u32 value)
 {
-	return bcma_cc_write32_masked(cc, BCMA_CC_GPIOOUT, mask, value);
+	unsigned long flags;
+	u32 res;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = bcma_cc_write32_masked(cc, BCMA_CC_GPIOOUT, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 
 u32 bcma_chipco_gpio_outen(struct bcma_drv_cc *cc, u32 mask, u32 value)
 {
-	return bcma_cc_write32_masked(cc, BCMA_CC_GPIOOUTEN, mask, value);
+	unsigned long flags;
+	u32 res;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = bcma_cc_write32_masked(cc, BCMA_CC_GPIOOUTEN, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 
 u32 bcma_chipco_gpio_control(struct bcma_drv_cc *cc, u32 mask, u32 value)
 {
-	return bcma_cc_write32_masked(cc, BCMA_CC_GPIOCTL, mask, value);
+	unsigned long flags;
+	u32 res;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = bcma_cc_write32_masked(cc, BCMA_CC_GPIOCTL, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 EXPORT_SYMBOL_GPL(bcma_chipco_gpio_control);
 
 u32 bcma_chipco_gpio_intmask(struct bcma_drv_cc *cc, u32 mask, u32 value)
 {
-	return bcma_cc_write32_masked(cc, BCMA_CC_GPIOIRQ, mask, value);
+	unsigned long flags;
+	u32 res;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = bcma_cc_write32_masked(cc, BCMA_CC_GPIOIRQ, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 
 u32 bcma_chipco_gpio_polarity(struct bcma_drv_cc *cc, u32 mask, u32 value)
 {
-	return bcma_cc_write32_masked(cc, BCMA_CC_GPIOPOL, mask, value);
+	unsigned long flags;
+	u32 res;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = bcma_cc_write32_masked(cc, BCMA_CC_GPIOPOL, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 
 #ifdef CONFIG_BCMA_DRIVER_MIPS
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index 1cf1749440ac..a085d986c804 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -567,6 +567,9 @@ struct bcma_drv_cc {
 	int nr_serial_ports;
 	struct bcma_serial_port serial_ports[4];
 #endif /* CONFIG_BCMA_DRIVER_MIPS */
+
+	/* Lock for GPIO register access. */
+	spinlock_t gpio_lock;
 };
 
 /* Register access */
-- 
cgit v1.2.3-55-g7522


From ea3488f4696fe22811eb19bee7088b732d3f8fe0 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Tue, 20 Nov 2012 22:24:28 +0000
Subject: bcma: add bcma_chipco_gpio_pull{up,down}

Add functions to access the GPIO registers for pullup and pulldown.
These are needed for handling gpio registration.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Patchwork: http://patchwork.linux-mips.org/patch/4586
Acked-by: Florian Fainelli <florian@openwrt.org>
---
 drivers/bcma/driver_chipcommon.c            | 30 +++++++++++++++++++++++++++++
 include/linux/bcma/bcma_driver_chipcommon.h |  2 ++
 2 files changed, 32 insertions(+)

(limited to 'include')

diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c
index c9b63d9ff61d..0945383c2271 100644
--- a/drivers/bcma/driver_chipcommon.c
+++ b/drivers/bcma/driver_chipcommon.c
@@ -145,6 +145,36 @@ u32 bcma_chipco_gpio_polarity(struct bcma_drv_cc *cc, u32 mask, u32 value)
 	return res;
 }
 
+u32 bcma_chipco_gpio_pullup(struct bcma_drv_cc *cc, u32 mask, u32 value)
+{
+	unsigned long flags;
+	u32 res;
+
+	if (cc->core->id.rev < 20)
+		return 0;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = bcma_cc_write32_masked(cc, BCMA_CC_GPIOPULLUP, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
+}
+
+u32 bcma_chipco_gpio_pulldown(struct bcma_drv_cc *cc, u32 mask, u32 value)
+{
+	unsigned long flags;
+	u32 res;
+
+	if (cc->core->id.rev < 20)
+		return 0;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = bcma_cc_write32_masked(cc, BCMA_CC_GPIOPULLDOWN, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
+}
+
 #ifdef CONFIG_BCMA_DRIVER_MIPS
 void bcma_chipco_serial_init(struct bcma_drv_cc *cc)
 {
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index a085d986c804..256702663b68 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -606,6 +606,8 @@ u32 bcma_chipco_gpio_outen(struct bcma_drv_cc *cc, u32 mask, u32 value);
 u32 bcma_chipco_gpio_control(struct bcma_drv_cc *cc, u32 mask, u32 value);
 u32 bcma_chipco_gpio_intmask(struct bcma_drv_cc *cc, u32 mask, u32 value);
 u32 bcma_chipco_gpio_polarity(struct bcma_drv_cc *cc, u32 mask, u32 value);
+u32 bcma_chipco_gpio_pullup(struct bcma_drv_cc *cc, u32 mask, u32 value);
+u32 bcma_chipco_gpio_pulldown(struct bcma_drv_cc *cc, u32 mask, u32 value);
 
 /* PMU support */
 extern void bcma_pmu_init(struct bcma_drv_cc *cc);
-- 
cgit v1.2.3-55-g7522


From cf0936b06d8e98a157630e99f647e2ff6d29d7ad Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Tue, 20 Nov 2012 22:24:30 +0000
Subject: bcma: add GPIO driver

Register a GPIO driver to access the GPIOs provided by the chip.
The GPIOs of the SoC should always start at 0 and the other GPIOs could
start at a random position. There is just one SoC in a system and when
they start at 0 the number is predictable.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Patchwork: http://patchwork.linux-mips.org/patch/4587
Acked-by: Florian Fainelli <florian@openwrt.org>
---
 drivers/bcma/Kconfig                        |  9 +++
 drivers/bcma/Makefile                       |  1 +
 drivers/bcma/bcma_private.h                 | 10 +++
 drivers/bcma/driver_gpio.c                  | 98 +++++++++++++++++++++++++++++
 drivers/bcma/main.c                         |  5 ++
 include/linux/bcma/bcma_driver_chipcommon.h |  5 ++
 6 files changed, 128 insertions(+)
 create mode 100644 drivers/bcma/driver_gpio.c

(limited to 'include')

diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig
index a533af218368..d7b56a88c9f4 100644
--- a/drivers/bcma/Kconfig
+++ b/drivers/bcma/Kconfig
@@ -65,6 +65,15 @@ config BCMA_DRIVER_GMAC_CMN
 
 	  If unsure, say N
 
+config BCMA_DRIVER_GPIO
+	bool "BCMA GPIO driver"
+	depends on BCMA
+	select GPIOLIB
+	help
+	  Driver to provide access to the GPIO pins of the bcma bus.
+
+	  If unsure, say N
+
 config BCMA_DEBUG
 	bool "BCMA debugging"
 	depends on BCMA
diff --git a/drivers/bcma/Makefile b/drivers/bcma/Makefile
index 8ad42d41b2f2..734b32f09c0a 100644
--- a/drivers/bcma/Makefile
+++ b/drivers/bcma/Makefile
@@ -6,6 +6,7 @@ bcma-y					+= driver_pci.o
 bcma-$(CONFIG_BCMA_DRIVER_PCI_HOSTMODE)	+= driver_pci_host.o
 bcma-$(CONFIG_BCMA_DRIVER_MIPS)		+= driver_mips.o
 bcma-$(CONFIG_BCMA_DRIVER_GMAC_CMN)	+= driver_gmac_cmn.o
+bcma-$(CONFIG_BCMA_DRIVER_GPIO)		+= driver_gpio.o
 bcma-$(CONFIG_BCMA_HOST_PCI)		+= host_pci.o
 bcma-$(CONFIG_BCMA_HOST_SOC)		+= host_soc.o
 obj-$(CONFIG_BCMA)			+= bcma.o
diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index 169fc58427d3..8cd80bff8e91 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -89,4 +89,14 @@ bool __devinit bcma_core_pci_is_in_hostmode(struct bcma_drv_pci *pc);
 void __devinit bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc);
 #endif /* CONFIG_BCMA_DRIVER_PCI_HOSTMODE */
 
+#ifdef CONFIG_BCMA_DRIVER_GPIO
+/* driver_gpio.c */
+int bcma_gpio_init(struct bcma_drv_cc *cc);
+#else
+static inline int bcma_gpio_init(struct bcma_drv_cc *cc)
+{
+	return -ENOTSUPP;
+}
+#endif /* CONFIG_BCMA_DRIVER_GPIO */
+
 #endif
diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c
new file mode 100644
index 000000000000..9a6f585da2d9
--- /dev/null
+++ b/drivers/bcma/driver_gpio.c
@@ -0,0 +1,98 @@
+/*
+ * Broadcom specific AMBA
+ * GPIO driver
+ *
+ * Copyright 2011, Broadcom Corporation
+ * Copyright 2012, Hauke Mehrtens <hauke@hauke-m.de>
+ *
+ * Licensed under the GNU/GPL. See COPYING for details.
+ */
+
+#include <linux/gpio.h>
+#include <linux/export.h>
+#include <linux/bcma/bcma.h>
+
+#include "bcma_private.h"
+
+static inline struct bcma_drv_cc *bcma_gpio_get_cc(struct gpio_chip *chip)
+{
+	return container_of(chip, struct bcma_drv_cc, gpio);
+}
+
+static int bcma_gpio_get_value(struct gpio_chip *chip, unsigned gpio)
+{
+	struct bcma_drv_cc *cc = bcma_gpio_get_cc(chip);
+
+	return !!bcma_chipco_gpio_in(cc, 1 << gpio);
+}
+
+static void bcma_gpio_set_value(struct gpio_chip *chip, unsigned gpio,
+				int value)
+{
+	struct bcma_drv_cc *cc = bcma_gpio_get_cc(chip);
+
+	bcma_chipco_gpio_out(cc, 1 << gpio, value ? 1 << gpio : 0);
+}
+
+static int bcma_gpio_direction_input(struct gpio_chip *chip, unsigned gpio)
+{
+	struct bcma_drv_cc *cc = bcma_gpio_get_cc(chip);
+
+	bcma_chipco_gpio_outen(cc, 1 << gpio, 0);
+	return 0;
+}
+
+static int bcma_gpio_direction_output(struct gpio_chip *chip, unsigned gpio,
+				      int value)
+{
+	struct bcma_drv_cc *cc = bcma_gpio_get_cc(chip);
+
+	bcma_chipco_gpio_outen(cc, 1 << gpio, 1 << gpio);
+	bcma_chipco_gpio_out(cc, 1 << gpio, value ? 1 << gpio : 0);
+	return 0;
+}
+
+static int bcma_gpio_request(struct gpio_chip *chip, unsigned gpio)
+{
+	struct bcma_drv_cc *cc = bcma_gpio_get_cc(chip);
+
+	bcma_chipco_gpio_control(cc, 1 << gpio, 0);
+	/* clear pulldown */
+	bcma_chipco_gpio_pulldown(cc, 1 << gpio, 0);
+	/* Set pullup */
+	bcma_chipco_gpio_pullup(cc, 1 << gpio, 1 << gpio);
+
+	return 0;
+}
+
+static void bcma_gpio_free(struct gpio_chip *chip, unsigned gpio)
+{
+	struct bcma_drv_cc *cc = bcma_gpio_get_cc(chip);
+
+	/* clear pullup */
+	bcma_chipco_gpio_pullup(cc, 1 << gpio, 0);
+}
+
+int bcma_gpio_init(struct bcma_drv_cc *cc)
+{
+	struct gpio_chip *chip = &cc->gpio;
+
+	chip->label		= "bcma_gpio";
+	chip->owner		= THIS_MODULE;
+	chip->request		= bcma_gpio_request;
+	chip->free		= bcma_gpio_free;
+	chip->get		= bcma_gpio_get_value;
+	chip->set		= bcma_gpio_set_value;
+	chip->direction_input	= bcma_gpio_direction_input;
+	chip->direction_output	= bcma_gpio_direction_output;
+	chip->ngpio		= 16;
+	/* There is just one SoC in one device and its GPIO addresses should be
+	 * deterministic to address them more easily. The other buses could get
+	 * a random base number. */
+	if (cc->core->bus->hosttype == BCMA_HOSTTYPE_SOC)
+		chip->base		= 0;
+	else
+		chip->base		= -1;
+
+	return gpiochip_add(chip);
+}
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index d865470bc951..478ba01ca0c2 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -152,6 +152,11 @@ static int bcma_register_cores(struct bcma_bus *bus)
 			bcma_err(bus, "Error registering NAND flash\n");
 	}
 #endif
+	err = bcma_gpio_init(&bus->drv_cc);
+	if (err == -ENOTSUPP)
+		bcma_debug(bus, "GPIO driver not activated\n");
+	else if (err)
+		bcma_err(bus, "Error registering GPIO driver: %i\n", err);
 
 	return 0;
 }
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index 256702663b68..7d662a988d24 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -1,6 +1,8 @@
 #ifndef LINUX_BCMA_DRIVER_CC_H_
 #define LINUX_BCMA_DRIVER_CC_H_
 
+#include <linux/gpio.h>
+
 /** ChipCommon core registers. **/
 #define BCMA_CC_ID			0x0000
 #define  BCMA_CC_ID_ID			0x0000FFFF
@@ -570,6 +572,9 @@ struct bcma_drv_cc {
 
 	/* Lock for GPIO register access. */
 	spinlock_t gpio_lock;
+#ifdef CONFIG_BCMA_DRIVER_GPIO
+	struct gpio_chip gpio;
+#endif
 };
 
 /* Register access */
-- 
cgit v1.2.3-55-g7522


From da22f22e91f0d14d996c7258101575a5a06ddf85 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Tue, 20 Nov 2012 22:24:31 +0000
Subject: ssb: add ssb_chipco_gpio_pull{up,down}

Add functions to access the GPIO registers for pullup and pulldown.
These are needed for handling gpio registration.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Patchwork: http://patchwork.linux-mips.org/patch/4589
Acked-by: Florian Fainelli <florian@openwrt.org>
---
 drivers/ssb/driver_chipcommon.c           | 16 ++++++++++++++++
 include/linux/ssb/ssb_driver_chipcommon.h |  2 ++
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/drivers/ssb/driver_chipcommon.c b/drivers/ssb/driver_chipcommon.c
index e9d2ca11283b..4df492665565 100644
--- a/drivers/ssb/driver_chipcommon.c
+++ b/drivers/ssb/driver_chipcommon.c
@@ -442,6 +442,22 @@ u32 ssb_chipco_gpio_polarity(struct ssb_chipcommon *cc, u32 mask, u32 value)
 	return chipco_write32_masked(cc, SSB_CHIPCO_GPIOPOL, mask, value);
 }
 
+u32 ssb_chipco_gpio_pullup(struct ssb_chipcommon *cc, u32 mask, u32 value)
+{
+	if (cc->dev->id.revision < 20)
+		return 0xffffffff;
+
+	return chipco_write32_masked(cc, SSB_CHIPCO_GPIOPULLUP, mask, value);
+}
+
+u32 ssb_chipco_gpio_pulldown(struct ssb_chipcommon *cc, u32 mask, u32 value)
+{
+	if (cc->dev->id.revision < 20)
+		return 0xffffffff;
+
+	return chipco_write32_masked(cc, SSB_CHIPCO_GPIOPULLDOWN, mask, value);
+}
+
 #ifdef CONFIG_SSB_SERIAL
 int ssb_chipco_serial_init(struct ssb_chipcommon *cc,
 			   struct ssb_serial_port *ports)
diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h
index c2b02a5c86ae..c8d07c95d76e 100644
--- a/include/linux/ssb/ssb_driver_chipcommon.h
+++ b/include/linux/ssb/ssb_driver_chipcommon.h
@@ -644,6 +644,8 @@ u32 ssb_chipco_gpio_outen(struct ssb_chipcommon *cc, u32 mask, u32 value);
 u32 ssb_chipco_gpio_control(struct ssb_chipcommon *cc, u32 mask, u32 value);
 u32 ssb_chipco_gpio_intmask(struct ssb_chipcommon *cc, u32 mask, u32 value);
 u32 ssb_chipco_gpio_polarity(struct ssb_chipcommon *cc, u32 mask, u32 value);
+u32 ssb_chipco_gpio_pullup(struct ssb_chipcommon *cc, u32 mask, u32 value);
+u32 ssb_chipco_gpio_pulldown(struct ssb_chipcommon *cc, u32 mask, u32 value);
 
 #ifdef CONFIG_SSB_SERIAL
 extern int ssb_chipco_serial_init(struct ssb_chipcommon *cc,
-- 
cgit v1.2.3-55-g7522


From 394bc7e38be79987ed15de203920c3cddb724cc1 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Tue, 20 Nov 2012 22:24:32 +0000
Subject: ssb: add locking around gpio register accesses

The GPIOs are access through some registers in the chip common core or
over extif. We need locking around these GPIO accesses, all GPIOs are
accessed through the same registers and parallel writes will cause
problems.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Patchwork: http://patchwork.linux-mips.org/patch/4590
Acked-by: Florian Fainelli <florian@openwrt.org>
---
 drivers/ssb/driver_chipcommon.c           | 66 +++++++++++++++++++++++++++----
 drivers/ssb/driver_extif.c                | 43 ++++++++++++++++++--
 drivers/ssb/main.c                        |  1 +
 drivers/ssb/ssb_private.h                 |  8 ++++
 include/linux/ssb/ssb_driver_chipcommon.h |  1 +
 include/linux/ssb/ssb_driver_extif.h      |  1 +
 6 files changed, 109 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/ssb/driver_chipcommon.c b/drivers/ssb/driver_chipcommon.c
index 4df492665565..24e02bb2ecd8 100644
--- a/drivers/ssb/driver_chipcommon.c
+++ b/drivers/ssb/driver_chipcommon.c
@@ -284,6 +284,9 @@ void ssb_chipcommon_init(struct ssb_chipcommon *cc)
 {
 	if (!cc->dev)
 		return; /* We don't have a ChipCommon */
+
+	spin_lock_init(&cc->gpio_lock);
+
 	if (cc->dev->id.revision >= 11)
 		cc->status = chipco_read32(cc, SSB_CHIPCO_CHIPSTAT);
 	ssb_dprintk(KERN_INFO PFX "chipcommon status is 0x%x\n", cc->status);
@@ -418,44 +421,93 @@ u32 ssb_chipco_gpio_in(struct ssb_chipcommon *cc, u32 mask)
 
 u32 ssb_chipco_gpio_out(struct ssb_chipcommon *cc, u32 mask, u32 value)
 {
-	return chipco_write32_masked(cc, SSB_CHIPCO_GPIOOUT, mask, value);
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = chipco_write32_masked(cc, SSB_CHIPCO_GPIOOUT, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 
 u32 ssb_chipco_gpio_outen(struct ssb_chipcommon *cc, u32 mask, u32 value)
 {
-	return chipco_write32_masked(cc, SSB_CHIPCO_GPIOOUTEN, mask, value);
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = chipco_write32_masked(cc, SSB_CHIPCO_GPIOOUTEN, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 
 u32 ssb_chipco_gpio_control(struct ssb_chipcommon *cc, u32 mask, u32 value)
 {
-	return chipco_write32_masked(cc, SSB_CHIPCO_GPIOCTL, mask, value);
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = chipco_write32_masked(cc, SSB_CHIPCO_GPIOCTL, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 EXPORT_SYMBOL(ssb_chipco_gpio_control);
 
 u32 ssb_chipco_gpio_intmask(struct ssb_chipcommon *cc, u32 mask, u32 value)
 {
-	return chipco_write32_masked(cc, SSB_CHIPCO_GPIOIRQ, mask, value);
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = chipco_write32_masked(cc, SSB_CHIPCO_GPIOIRQ, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 
 u32 ssb_chipco_gpio_polarity(struct ssb_chipcommon *cc, u32 mask, u32 value)
 {
-	return chipco_write32_masked(cc, SSB_CHIPCO_GPIOPOL, mask, value);
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = chipco_write32_masked(cc, SSB_CHIPCO_GPIOPOL, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 
 u32 ssb_chipco_gpio_pullup(struct ssb_chipcommon *cc, u32 mask, u32 value)
 {
+	unsigned long flags;
+	u32 res = 0;
+
 	if (cc->dev->id.revision < 20)
 		return 0xffffffff;
 
-	return chipco_write32_masked(cc, SSB_CHIPCO_GPIOPULLUP, mask, value);
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = chipco_write32_masked(cc, SSB_CHIPCO_GPIOPULLUP, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 
 u32 ssb_chipco_gpio_pulldown(struct ssb_chipcommon *cc, u32 mask, u32 value)
 {
+	unsigned long flags;
+	u32 res = 0;
+
 	if (cc->dev->id.revision < 20)
 		return 0xffffffff;
 
-	return chipco_write32_masked(cc, SSB_CHIPCO_GPIOPULLDOWN, mask, value);
+	spin_lock_irqsave(&cc->gpio_lock, flags);
+	res = chipco_write32_masked(cc, SSB_CHIPCO_GPIOPULLDOWN, mask, value);
+	spin_unlock_irqrestore(&cc->gpio_lock, flags);
+
+	return res;
 }
 
 #ifdef CONFIG_SSB_SERIAL
diff --git a/drivers/ssb/driver_extif.c b/drivers/ssb/driver_extif.c
index dc47f30e9cf7..e1d0bb8ad725 100644
--- a/drivers/ssb/driver_extif.c
+++ b/drivers/ssb/driver_extif.c
@@ -118,6 +118,13 @@ void ssb_extif_watchdog_timer_set(struct ssb_extif *extif,
 	extif_write32(extif, SSB_EXTIF_WATCHDOG, ticks);
 }
 
+void ssb_extif_init(struct ssb_extif *extif)
+{
+	if (!extif->dev)
+		return; /* We don't have a Extif core */
+	spin_lock_init(&extif->gpio_lock);
+}
+
 u32 ssb_extif_gpio_in(struct ssb_extif *extif, u32 mask)
 {
 	return extif_read32(extif, SSB_EXTIF_GPIO_IN) & mask;
@@ -125,22 +132,50 @@ u32 ssb_extif_gpio_in(struct ssb_extif *extif, u32 mask)
 
 u32 ssb_extif_gpio_out(struct ssb_extif *extif, u32 mask, u32 value)
 {
-	return extif_write32_masked(extif, SSB_EXTIF_GPIO_OUT(0),
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&extif->gpio_lock, flags);
+	res = extif_write32_masked(extif, SSB_EXTIF_GPIO_OUT(0),
 				   mask, value);
+	spin_unlock_irqrestore(&extif->gpio_lock, flags);
+
+	return res;
 }
 
 u32 ssb_extif_gpio_outen(struct ssb_extif *extif, u32 mask, u32 value)
 {
-	return extif_write32_masked(extif, SSB_EXTIF_GPIO_OUTEN(0),
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&extif->gpio_lock, flags);
+	res = extif_write32_masked(extif, SSB_EXTIF_GPIO_OUTEN(0),
 				   mask, value);
+	spin_unlock_irqrestore(&extif->gpio_lock, flags);
+
+	return res;
 }
 
 u32 ssb_extif_gpio_polarity(struct ssb_extif *extif, u32 mask, u32 value)
 {
-	return extif_write32_masked(extif, SSB_EXTIF_GPIO_INTPOL, mask, value);
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&extif->gpio_lock, flags);
+	res = extif_write32_masked(extif, SSB_EXTIF_GPIO_INTPOL, mask, value);
+	spin_unlock_irqrestore(&extif->gpio_lock, flags);
+
+	return res;
 }
 
 u32 ssb_extif_gpio_intmask(struct ssb_extif *extif, u32 mask, u32 value)
 {
-	return extif_write32_masked(extif, SSB_EXTIF_GPIO_INTMASK, mask, value);
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&extif->gpio_lock, flags);
+	res = extif_write32_masked(extif, SSB_EXTIF_GPIO_INTMASK, mask, value);
+	spin_unlock_irqrestore(&extif->gpio_lock, flags);
+
+	return res;
 }
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index df0f145c22fc..6fe2d102734a 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -796,6 +796,7 @@ static int __devinit ssb_bus_register(struct ssb_bus *bus,
 	if (err)
 		goto err_pcmcia_exit;
 	ssb_chipcommon_init(&bus->chipco);
+	ssb_extif_init(&bus->extif);
 	ssb_mipscore_init(&bus->mipscore);
 	err = ssb_fetch_invariants(bus, get_invariants);
 	if (err) {
diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h
index a305550b4b65..d6a1ba9394d9 100644
--- a/drivers/ssb/ssb_private.h
+++ b/drivers/ssb/ssb_private.h
@@ -211,4 +211,12 @@ static inline void b43_pci_ssb_bridge_exit(void)
 extern u32 ssb_pmu_get_cpu_clock(struct ssb_chipcommon *cc);
 extern u32 ssb_pmu_get_controlclock(struct ssb_chipcommon *cc);
 
+#ifdef CONFIG_SSB_DRIVER_EXTIF
+extern void ssb_extif_init(struct ssb_extif *extif);
+#else
+static inline void ssb_extif_init(struct ssb_extif *extif)
+{
+}
+#endif
+
 #endif /* LINUX_SSB_PRIVATE_H_ */
diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h
index c8d07c95d76e..30b694345d47 100644
--- a/include/linux/ssb/ssb_driver_chipcommon.h
+++ b/include/linux/ssb/ssb_driver_chipcommon.h
@@ -590,6 +590,7 @@ struct ssb_chipcommon {
 	u32 status;
 	/* Fast Powerup Delay constant */
 	u16 fast_pwrup_delay;
+	spinlock_t gpio_lock;
 	struct ssb_chipcommon_pmu pmu;
 };
 
diff --git a/include/linux/ssb/ssb_driver_extif.h b/include/linux/ssb/ssb_driver_extif.h
index 91161f0aa22b..bd2306854a91 100644
--- a/include/linux/ssb/ssb_driver_extif.h
+++ b/include/linux/ssb/ssb_driver_extif.h
@@ -158,6 +158,7 @@
 
 struct ssb_extif {
 	struct ssb_device *dev;
+	spinlock_t gpio_lock;
 };
 
 static inline bool ssb_extif_available(struct ssb_extif *extif)
-- 
cgit v1.2.3-55-g7522


From ec43b08b5733494ad88aa618ecdf534320dd8207 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Tue, 20 Nov 2012 22:24:33 +0000
Subject: ssb: add GPIO driver

Register a GPIO driver to access the GPIOs provided by the chip.
The GPIOs of the SoC should always start at 0 and the other GPIOs could
start at a random position. There is just one SoC in a system and when
they start at 0 the number is predictable.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Patchwork: http://patchwork.linux-mips.org/patch/4591
Acked-by: Florian Fainelli <florian@openwrt.org>
---
 drivers/ssb/Kconfig       |   9 +++
 drivers/ssb/Makefile      |   1 +
 drivers/ssb/driver_gpio.c | 176 ++++++++++++++++++++++++++++++++++++++++++++++
 drivers/ssb/main.c        |   6 ++
 drivers/ssb/ssb_private.h |   9 +++
 include/linux/ssb/ssb.h   |   4 ++
 6 files changed, 205 insertions(+)
 create mode 100644 drivers/ssb/driver_gpio.c

(limited to 'include')

diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig
index 42cdaa9a4d8a..ff3c8a21f10d 100644
--- a/drivers/ssb/Kconfig
+++ b/drivers/ssb/Kconfig
@@ -160,4 +160,13 @@ config SSB_DRIVER_GIGE
 
 	  If unsure, say N
 
+config SSB_DRIVER_GPIO
+	bool "SSB GPIO driver"
+	depends on SSB
+	select GPIOLIB
+	help
+	  Driver to provide access to the GPIO pins on the bus.
+
+	  If unsure, say N
+
 endmenu
diff --git a/drivers/ssb/Makefile b/drivers/ssb/Makefile
index 656e58b92618..9159ba77c388 100644
--- a/drivers/ssb/Makefile
+++ b/drivers/ssb/Makefile
@@ -15,6 +15,7 @@ ssb-$(CONFIG_SSB_DRIVER_MIPS)		+= driver_mipscore.o
 ssb-$(CONFIG_SSB_DRIVER_EXTIF)		+= driver_extif.o
 ssb-$(CONFIG_SSB_DRIVER_PCICORE)	+= driver_pcicore.o
 ssb-$(CONFIG_SSB_DRIVER_GIGE)		+= driver_gige.o
+ssb-$(CONFIG_SSB_DRIVER_GPIO)		+= driver_gpio.o
 
 # b43 pci-ssb-bridge driver
 # Not strictly a part of SSB, but kept here for convenience
diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c
new file mode 100644
index 000000000000..97ac0a38e3d0
--- /dev/null
+++ b/drivers/ssb/driver_gpio.c
@@ -0,0 +1,176 @@
+/*
+ * Sonics Silicon Backplane
+ * GPIO driver
+ *
+ * Copyright 2011, Broadcom Corporation
+ * Copyright 2012, Hauke Mehrtens <hauke@hauke-m.de>
+ *
+ * Licensed under the GNU/GPL. See COPYING for details.
+ */
+
+#include <linux/gpio.h>
+#include <linux/export.h>
+#include <linux/ssb/ssb.h>
+
+#include "ssb_private.h"
+
+static struct ssb_bus *ssb_gpio_get_bus(struct gpio_chip *chip)
+{
+	return container_of(chip, struct ssb_bus, gpio);
+}
+
+static int ssb_gpio_chipco_get_value(struct gpio_chip *chip, unsigned gpio)
+{
+	struct ssb_bus *bus = ssb_gpio_get_bus(chip);
+
+	return !!ssb_chipco_gpio_in(&bus->chipco, 1 << gpio);
+}
+
+static void ssb_gpio_chipco_set_value(struct gpio_chip *chip, unsigned gpio,
+				      int value)
+{
+	struct ssb_bus *bus = ssb_gpio_get_bus(chip);
+
+	ssb_chipco_gpio_out(&bus->chipco, 1 << gpio, value ? 1 << gpio : 0);
+}
+
+static int ssb_gpio_chipco_direction_input(struct gpio_chip *chip,
+					   unsigned gpio)
+{
+	struct ssb_bus *bus = ssb_gpio_get_bus(chip);
+
+	ssb_chipco_gpio_outen(&bus->chipco, 1 << gpio, 0);
+	return 0;
+}
+
+static int ssb_gpio_chipco_direction_output(struct gpio_chip *chip,
+					    unsigned gpio, int value)
+{
+	struct ssb_bus *bus = ssb_gpio_get_bus(chip);
+
+	ssb_chipco_gpio_outen(&bus->chipco, 1 << gpio, 1 << gpio);
+	ssb_chipco_gpio_out(&bus->chipco, 1 << gpio, value ? 1 << gpio : 0);
+	return 0;
+}
+
+static int ssb_gpio_chipco_request(struct gpio_chip *chip, unsigned gpio)
+{
+	struct ssb_bus *bus = ssb_gpio_get_bus(chip);
+
+	ssb_chipco_gpio_control(&bus->chipco, 1 << gpio, 0);
+	/* clear pulldown */
+	ssb_chipco_gpio_pulldown(&bus->chipco, 1 << gpio, 0);
+	/* Set pullup */
+	ssb_chipco_gpio_pullup(&bus->chipco, 1 << gpio, 1 << gpio);
+
+	return 0;
+}
+
+static void ssb_gpio_chipco_free(struct gpio_chip *chip, unsigned gpio)
+{
+	struct ssb_bus *bus = ssb_gpio_get_bus(chip);
+
+	/* clear pullup */
+	ssb_chipco_gpio_pullup(&bus->chipco, 1 << gpio, 0);
+}
+
+static int ssb_gpio_chipco_init(struct ssb_bus *bus)
+{
+	struct gpio_chip *chip = &bus->gpio;
+
+	chip->label		= "ssb_chipco_gpio";
+	chip->owner		= THIS_MODULE;
+	chip->request		= ssb_gpio_chipco_request;
+	chip->free		= ssb_gpio_chipco_free;
+	chip->get		= ssb_gpio_chipco_get_value;
+	chip->set		= ssb_gpio_chipco_set_value;
+	chip->direction_input	= ssb_gpio_chipco_direction_input;
+	chip->direction_output	= ssb_gpio_chipco_direction_output;
+	chip->ngpio		= 16;
+	/* There is just one SoC in one device and its GPIO addresses should be
+	 * deterministic to address them more easily. The other buses could get
+	 * a random base number. */
+	if (bus->bustype == SSB_BUSTYPE_SSB)
+		chip->base		= 0;
+	else
+		chip->base		= -1;
+
+	return gpiochip_add(chip);
+}
+
+#ifdef CONFIG_SSB_DRIVER_EXTIF
+
+static int ssb_gpio_extif_get_value(struct gpio_chip *chip, unsigned gpio)
+{
+	struct ssb_bus *bus = ssb_gpio_get_bus(chip);
+
+	return !!ssb_extif_gpio_in(&bus->extif, 1 << gpio);
+}
+
+static void ssb_gpio_extif_set_value(struct gpio_chip *chip, unsigned gpio,
+				     int value)
+{
+	struct ssb_bus *bus = ssb_gpio_get_bus(chip);
+
+	ssb_extif_gpio_out(&bus->extif, 1 << gpio, value ? 1 << gpio : 0);
+}
+
+static int ssb_gpio_extif_direction_input(struct gpio_chip *chip,
+					  unsigned gpio)
+{
+	struct ssb_bus *bus = ssb_gpio_get_bus(chip);
+
+	ssb_extif_gpio_outen(&bus->extif, 1 << gpio, 0);
+	return 0;
+}
+
+static int ssb_gpio_extif_direction_output(struct gpio_chip *chip,
+					   unsigned gpio, int value)
+{
+	struct ssb_bus *bus = ssb_gpio_get_bus(chip);
+
+	ssb_extif_gpio_outen(&bus->extif, 1 << gpio, 1 << gpio);
+	ssb_extif_gpio_out(&bus->extif, 1 << gpio, value ? 1 << gpio : 0);
+	return 0;
+}
+
+static int ssb_gpio_extif_init(struct ssb_bus *bus)
+{
+	struct gpio_chip *chip = &bus->gpio;
+
+	chip->label		= "ssb_extif_gpio";
+	chip->owner		= THIS_MODULE;
+	chip->get		= ssb_gpio_extif_get_value;
+	chip->set		= ssb_gpio_extif_set_value;
+	chip->direction_input	= ssb_gpio_extif_direction_input;
+	chip->direction_output	= ssb_gpio_extif_direction_output;
+	chip->ngpio		= 5;
+	/* There is just one SoC in one device and its GPIO addresses should be
+	 * deterministic to address them more easily. The other buses could get
+	 * a random base number. */
+	if (bus->bustype == SSB_BUSTYPE_SSB)
+		chip->base		= 0;
+	else
+		chip->base		= -1;
+
+	return gpiochip_add(chip);
+}
+
+#else
+static int ssb_gpio_extif_init(struct ssb_bus *bus)
+{
+	return -ENOTSUPP;
+}
+#endif
+
+int ssb_gpio_init(struct ssb_bus *bus)
+{
+	if (ssb_chipco_available(&bus->chipco))
+		return ssb_gpio_chipco_init(bus);
+	else if (ssb_extif_available(&bus->extif))
+		return ssb_gpio_extif_init(bus);
+	else
+		SSB_WARN_ON(1);
+
+	return -1;
+}
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 6fe2d102734a..87f0ddf4f3f3 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -798,6 +798,12 @@ static int __devinit ssb_bus_register(struct ssb_bus *bus,
 	ssb_chipcommon_init(&bus->chipco);
 	ssb_extif_init(&bus->extif);
 	ssb_mipscore_init(&bus->mipscore);
+	err = ssb_gpio_init(bus);
+	if (err == -ENOTSUPP)
+		ssb_dprintk(KERN_DEBUG PFX "GPIO driver not activated\n");
+	else if (err)
+		ssb_dprintk(KERN_ERR PFX
+			   "Error registering GPIO driver: %i\n", err);
 	err = ssb_fetch_invariants(bus, get_invariants);
 	if (err) {
 		ssb_bus_may_powerdown(bus);
diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h
index d6a1ba9394d9..463b76a2140b 100644
--- a/drivers/ssb/ssb_private.h
+++ b/drivers/ssb/ssb_private.h
@@ -219,4 +219,13 @@ static inline void ssb_extif_init(struct ssb_extif *extif)
 }
 #endif
 
+#ifdef CONFIG_SSB_DRIVER_GPIO
+extern int ssb_gpio_init(struct ssb_bus *bus);
+#else /* CONFIG_SSB_DRIVER_GPIO */
+static inline int ssb_gpio_init(struct ssb_bus *bus)
+{
+	return -ENOTSUPP;
+}
+#endif /* CONFIG_SSB_DRIVER_GPIO */
+
 #endif /* LINUX_SSB_PRIVATE_H_ */
diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h
index bb674c02f306..3862a5bbd73b 100644
--- a/include/linux/ssb/ssb.h
+++ b/include/linux/ssb/ssb.h
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
+#include <linux/gpio.h>
 #include <linux/mod_devicetable.h>
 #include <linux/dma-mapping.h>
 
@@ -433,6 +434,9 @@ struct ssb_bus {
 	/* Lock for GPIO register access. */
 	spinlock_t gpio_lock;
 #endif /* EMBEDDED */
+#ifdef CONFIG_SSB_DRIVER_GPIO
+	struct gpio_chip gpio;
+#endif /* DRIVER_GPIO */
 
 	/* Internal-only stuff follows. Do not touch. */
 	struct list_head list;
-- 
cgit v1.2.3-55-g7522


From fbfddae696572e57a441252abbd65f7220e06030 Mon Sep 17 00:00:00 2001
From: Toshi Kani
Date: Wed, 21 Nov 2012 01:36:28 +0000
Subject: ACPI: Add acpi_handle_<level>() interfaces

This patch introduces acpi_handle_<level>(), where <level> is
a kernel message level such as err/warn/info, to support improved
logging messages for ACPI, esp. hot-plug operations.
acpi_handle_<level>() appends "ACPI" prefix and ACPI object path
to the messages.  This improves diagnosis of hotplug operations
since an error message in a log file identifies an object that
caused an issue.  This interface acquires the global namespace
mutex to obtain an object path.  In interrupt context, it shows
the object path as <n/a>.

acpi_handle_<level>() takes acpi_handle as an argument, which is
passed to ACPI hotplug notify handlers from the ACPICA.  Therefore,
it is always available unlike other kernel objects, such as device.

For example:
  acpi_handle_err(handle, "Device don't exist, dropping EJECT\n");
logs an error message like this at KERN_ERR.
  ACPI: \_SB_.SCK4.CPU4: Device don't exist, dropping EJECT

ACPI hot-plug drivers can use acpi_handle_<level>() when they need
to identify a target ACPI object path in their messages, such as
error cases.  The usage model is similar to dev_<level>().
acpi_handle_<level>() can be used when a device is not created or
is invalid during hot-plug operations.  ACPI object path is also
consistent on the platform, unlike device name that gets incremented
over hotplug operations.

ACPI drivers should use dev_<level>() when a device object is valid.
Device name provides more user friendly information, and avoids
acquiring the global ACPI namespace mutex.  ACPI drivers also
continue to use pr_<level>() when they do not need to specify device
information, such as boot-up messages.

Note: ACPI_[WARNING|INFO|ERROR]() are intended for the ACPICA and
are not associated with the kernel message level.

Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Tested-by: Vijay Mohan Pandarathil <vijaymohan.pandarathil@hp.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/utils.c | 38 ++++++++++++++++++++++++++++++++++++++
 include/linux/acpi.h | 43 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 462f7e300363..744371304313 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -28,6 +28,8 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/types.h>
+#include <linux/hardirq.h>
+#include <linux/acpi.h>
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
 
@@ -457,3 +459,39 @@ acpi_evaluate_hotplug_ost(acpi_handle handle, u32 source_event,
 #endif
 }
 EXPORT_SYMBOL(acpi_evaluate_hotplug_ost);
+
+/**
+ * acpi_handle_printk: Print message with ACPI prefix and object path
+ *
+ * This function is called through acpi_handle_<level> macros and prints
+ * a message with ACPI prefix and object path.  This function acquires
+ * the global namespace mutex to obtain an object path.  In interrupt
+ * context, it shows the object path as <n/a>.
+ */
+void
+acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	struct acpi_buffer buffer = {
+		.length = ACPI_ALLOCATE_BUFFER,
+		.pointer = NULL
+	};
+	const char *path;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	if (in_interrupt() ||
+	    acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer) != AE_OK)
+		path = "<n/a>";
+	else
+		path = buffer.pointer;
+
+	printk("%sACPI: %s: %pV", level, path, &vaf);
+
+	va_end(args);
+	kfree(buffer.pointer);
+}
+EXPORT_SYMBOL(acpi_handle_printk);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 87edfcc0ab62..9201ac1f0511 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -434,4 +434,47 @@ acpi_status acpi_os_prepare_sleep(u8 sleep_state,
 #define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0)
 #endif
 
+#ifdef CONFIG_ACPI
+__printf(3, 4)
+void acpi_handle_printk(const char *level, acpi_handle handle,
+			const char *fmt, ...);
+#else	/* !CONFIG_ACPI */
+static inline __printf(3, 4) void
+acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {}
+#endif	/* !CONFIG_ACPI */
+
+/*
+ * acpi_handle_<level>: Print message with ACPI prefix and object path
+ *
+ * These interfaces acquire the global namespace mutex to obtain an object
+ * path.  In interrupt context, it shows the object path as <n/a>.
+ */
+#define acpi_handle_emerg(handle, fmt, ...)				\
+	acpi_handle_printk(KERN_EMERG, handle, fmt, ##__VA_ARGS__)
+#define acpi_handle_alert(handle, fmt, ...)				\
+	acpi_handle_printk(KERN_ALERT, handle, fmt, ##__VA_ARGS__)
+#define acpi_handle_crit(handle, fmt, ...)				\
+	acpi_handle_printk(KERN_CRIT, handle, fmt, ##__VA_ARGS__)
+#define acpi_handle_err(handle, fmt, ...)				\
+	acpi_handle_printk(KERN_ERR, handle, fmt, ##__VA_ARGS__)
+#define acpi_handle_warn(handle, fmt, ...)				\
+	acpi_handle_printk(KERN_WARNING, handle, fmt, ##__VA_ARGS__)
+#define acpi_handle_notice(handle, fmt, ...)				\
+	acpi_handle_printk(KERN_NOTICE, handle, fmt, ##__VA_ARGS__)
+#define acpi_handle_info(handle, fmt, ...)				\
+	acpi_handle_printk(KERN_INFO, handle, fmt, ##__VA_ARGS__)
+
+/* REVISIT: Support CONFIG_DYNAMIC_DEBUG when necessary */
+#if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
+#define acpi_handle_debug(handle, fmt, ...)				\
+	acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__)
+#else
+#define acpi_handle_debug(handle, fmt, ...)				\
+({									\
+	if (0)								\
+		acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__); \
+	0;								\
+})
+#endif
+
 #endif	/*_LINUX_ACPI_H*/
-- 
cgit v1.2.3-55-g7522


From 1399dfcdfe89898ccd791216f9679ba734aea910 Mon Sep 17 00:00:00 2001
From: Aaron Lu
Date: Wed, 21 Nov 2012 23:33:40 +0100
Subject: ACPI / PM: Introduce os_accessible flag for power_state

Currently we have valid flag to represent if this ACPI device power
state is valid. A device power state is valid does not necessarily
mean we, as OSPM, has a mean to put the device into that power state,
e.g. D3 cold is always a valid power state for any ACPI device, but if
there is no _PS3 or _PRx for this device, we can't really put that
device into D3 cold power state. The same is true for D0 power state.

So here comes the os_accessible flag, which is only set if the device
has provided us the required means to put it into that power state,
e.g. if we have _PS3 or _PRx, we can put the device into D3 cold state
and thus, D3 cold power state's os_accessible flag will be set in this
case.

And a new wrapper inline function is added to be used to check if
firmware has provided us a way to power off the device during runtime.

Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/scan.c     | 9 ++++++++-
 include/acpi/acpi_bus.h | 6 ++++++
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 1fcb8678665c..da1416af0c8b 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -965,8 +965,10 @@ static int acpi_bus_get_power_flags(struct acpi_device *device)
 		 * D3hot is only valid if _PR3 present.
 		 */
 		if (ps->resources.count ||
-		    (ps->flags.explicit_set && i < ACPI_STATE_D3_HOT))
+		    (ps->flags.explicit_set && i < ACPI_STATE_D3_HOT)) {
 			ps->flags.valid = 1;
+			ps->flags.os_accessible = 1;
+		}
 
 		ps->power = -1;	/* Unknown - driver assigned */
 		ps->latency = -1;	/* Unknown - driver assigned */
@@ -982,6 +984,11 @@ static int acpi_bus_get_power_flags(struct acpi_device *device)
 	if (device->power.states[ACPI_STATE_D3_HOT].flags.explicit_set)
 		device->power.states[ACPI_STATE_D3_COLD].flags.explicit_set = 1;
 
+	/* Presence of _PS3 or _PRx means we can put the device into D3 cold */
+	if (device->power.states[ACPI_STATE_D3_HOT].flags.explicit_set ||
+			device->power.flags.power_resources)
+		device->power.states[ACPI_STATE_D3_COLD].flags.os_accessible = 1;
+
 	acpi_bus_init_power(device);
 
 	return 0;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 80155fda517f..c3bc4511e0c0 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -201,6 +201,7 @@ struct acpi_device_power_flags {
 struct acpi_device_power_state {
 	struct {
 		u8 valid:1;
+		u8 os_accessible:1;
 		u8 explicit_set:1;	/* _PSx present? */
 		u8 reserved:6;
 	} flags;
@@ -500,6 +501,11 @@ static inline bool acpi_device_can_wakeup(struct acpi_device *adev)
 	return adev->wakeup.flags.valid;
 }
 
+static inline bool acpi_device_can_poweroff(struct acpi_device *adev)
+{
+	return adev->power.states[ACPI_STATE_D3_COLD].flags.os_accessible;
+}
+
 #else	/* CONFIG_ACPI */
 
 static inline int register_acpi_bus_type(void *bus) { return 0; }
-- 
cgit v1.2.3-55-g7522


From d79251f0fc2fdb7587c99617aae0bf52ff6c5510 Mon Sep 17 00:00:00 2001
From: Bill Pemberton
Date: Mon, 19 Nov 2012 13:25:25 -0500
Subject: ipack: remove use of __devinitconst

CONFIG_HOTPLUG is going away as an option so __devinitconst is no
longer needed.

Signed-off-by: Bill Pemberton <wfp5p@virginia.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/ipack.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipack.h b/include/linux/ipack.h
index a360c73129a6..fea12cbb2aeb 100644
--- a/include/linux/ipack.h
+++ b/include/linux/ipack.h
@@ -229,8 +229,7 @@ void ipack_device_unregister(struct ipack_device *dev);
  * in a generic manner.
  */
 #define DEFINE_IPACK_DEVICE_TABLE(_table) \
-	const struct ipack_device_id _table[] __devinitconst
-
+	const struct ipack_device_id _table[]
 /**
  * IPACK_DEVICE - macro used to describe a specific IndustryPack device
  * @_format: the format version (currently either 1 or 2, 8 bit value)
-- 
cgit v1.2.3-55-g7522


From 743179849015dc71bb2ea63d8cd4bfa7fdfb4bc6 Mon Sep 17 00:00:00 2001
From: Jean-Christophe PLAGNIOL-VILLARD
Date: Thu, 15 Nov 2012 20:19:57 +0100
Subject: of_spi: add generic binding support to specify cs gpio

This will allow to use gpio for chip select with no modification in the
driver binding

When use the cs-gpios, the gpio number will be passed via the cs_gpio field
and the number of chip select will automatically increased with max(hw cs, gpio cs).

So if for example the controller has 2 CS lines, and the cs-gpios
property looks like this:

cs-gpios = <&gpio1 0 0> <0> <&gpio1 1 0> <&gpio1 2 0>;

Then it should be configured so that num_chipselect = 4 with the
following mapping:

cs0 : &gpio1 0 0
cs1 : native
cs2 : &gpio1 1 0
cs3 : &gpio1 2 0

Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Cc: devicetree-discuss@lists.ozlabs.org
Cc: spi-devel-general@lists.sourceforge.net
Signed-off-by: Richard Genoud <richard.genoud@gmail.com>
[grant.likely: fixed up type of cs count so min() can do type checking]
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 Documentation/devicetree/bindings/spi/spi-bus.txt | 20 +++++++++
 drivers/spi/spi.c                                 | 54 +++++++++++++++++++++--
 include/linux/spi/spi.h                           |  3 ++
 3 files changed, 74 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/spi/spi-bus.txt b/Documentation/devicetree/bindings/spi/spi-bus.txt
index d2c33d0f533e..77a8b0d39b54 100644
--- a/Documentation/devicetree/bindings/spi/spi-bus.txt
+++ b/Documentation/devicetree/bindings/spi/spi-bus.txt
@@ -12,6 +12,7 @@ The SPI master node requires the following properties:
 - #size-cells     - should be zero.
 - compatible      - name of SPI bus controller following generic names
     		recommended practice.
+- cs-gpios	  - (optional) gpios chip select.
 No other properties are required in the SPI bus node.  It is assumed
 that a driver for an SPI bus device will understand that it is an SPI bus.
 However, the binding does not attempt to define the specific method for
@@ -24,6 +25,22 @@ support describing the chip select layout.
 Optional property:
 - num-cs : total number of chipselects
 
+If cs-gpios is used the number of chip select will automatically increased
+with max(cs-gpios > hw cs)
+
+So if for example the controller has 2 CS lines, and the cs-gpios
+property looks like this:
+
+cs-gpios = <&gpio1 0 0> <0> <&gpio1 1 0> <&gpio1 2 0>;
+
+Then it should be configured so that num_chipselect = 4 with the
+following mapping:
+
+cs0 : &gpio1 0 0
+cs1 : native
+cs2 : &gpio1 1 0
+cs3 : &gpio1 2 0
+
 SPI slave nodes must be children of the SPI master node and can
 contain the following properties.
 - reg             - (required) chip select address of device.
@@ -37,6 +54,9 @@ contain the following properties.
 - spi-cs-high     - (optional) Empty property indicating device requires
     		chip select active high
 
+If a gpio chipselect is used for the SPI slave the gpio number will be passed
+via the cs_gpio
+
 SPI example for an MPC5200 SPI bus:
 	spi@f00 {
 		#address-cells = <1>;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 84c2861d6f4d..1587a4a5ff41 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -30,6 +30,7 @@
 #include <linux/slab.h>
 #include <linux/mod_devicetable.h>
 #include <linux/spi/spi.h>
+#include <linux/of_gpio.h>
 #include <linux/pm_runtime.h>
 #include <linux/export.h>
 #include <linux/sched.h>
@@ -327,6 +328,7 @@ struct spi_device *spi_alloc_device(struct spi_master *master)
 	spi->dev.parent = &master->dev;
 	spi->dev.bus = &spi_bus_type;
 	spi->dev.release = spidev_release;
+	spi->cs_gpio = -EINVAL;
 	device_initialize(&spi->dev);
 	return spi;
 }
@@ -344,15 +346,16 @@ EXPORT_SYMBOL_GPL(spi_alloc_device);
 int spi_add_device(struct spi_device *spi)
 {
 	static DEFINE_MUTEX(spi_add_lock);
-	struct device *dev = spi->master->dev.parent;
+	struct spi_master *master = spi->master;
+	struct device *dev = master->dev.parent;
 	struct device *d;
 	int status;
 
 	/* Chipselects are numbered 0..max; validate. */
-	if (spi->chip_select >= spi->master->num_chipselect) {
+	if (spi->chip_select >= master->num_chipselect) {
 		dev_err(dev, "cs%d >= max %d\n",
 			spi->chip_select,
-			spi->master->num_chipselect);
+			master->num_chipselect);
 		return -EINVAL;
 	}
 
@@ -376,6 +379,9 @@ int spi_add_device(struct spi_device *spi)
 		goto done;
 	}
 
+	if (master->cs_gpios)
+		spi->cs_gpio = master->cs_gpios[spi->chip_select];
+
 	/* Drivers may modify this initial i/o setup, but will
 	 * normally rely on the device being setup.  Devices
 	 * using SPI_CS_HIGH can't coexist well otherwise...
@@ -946,6 +952,44 @@ struct spi_master *spi_alloc_master(struct device *dev, unsigned size)
 }
 EXPORT_SYMBOL_GPL(spi_alloc_master);
 
+#ifdef CONFIG_OF
+static int of_spi_register_master(struct spi_master *master)
+{
+	u16 nb;
+	int i, *cs;
+	struct device_node *np = master->dev.of_node;
+
+	if (!np)
+		return 0;
+
+	nb = of_gpio_named_count(np, "cs-gpios");
+	master->num_chipselect = max(nb, master->num_chipselect);
+
+	if (nb < 1)
+		return 0;
+
+	cs = devm_kzalloc(&master->dev,
+			  sizeof(int) * master->num_chipselect,
+			  GFP_KERNEL);
+	master->cs_gpios = cs;
+
+	if (!master->cs_gpios)
+		return -ENOMEM;
+
+	memset(cs, -EINVAL, master->num_chipselect);
+
+	for (i = 0; i < nb; i++)
+		cs[i] = of_get_named_gpio(np, "cs-gpios", i);
+
+	return 0;
+}
+#else
+static int of_spi_register_master(struct spi_master *master)
+{
+	return 0;
+}
+#endif
+
 /**
  * spi_register_master - register SPI master controller
  * @master: initialized master, originally from spi_alloc_master()
@@ -977,6 +1021,10 @@ int spi_register_master(struct spi_master *master)
 	if (!dev)
 		return -ENODEV;
 
+	status = of_spi_register_master(master);
+	if (status)
+		return status;
+
 	/* even if it's just one always-selected device, there must
 	 * be at least one chipselect
 	 */
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index fa702aeb5038..f62918946d86 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -90,6 +90,7 @@ struct spi_device {
 	void			*controller_state;
 	void			*controller_data;
 	char			modalias[SPI_NAME_SIZE];
+	int			cs_gpio;	/* chip select gpio */
 
 	/*
 	 * likely need more hooks for more protocol options affecting how
@@ -362,6 +363,8 @@ struct spi_master {
 	int (*transfer_one_message)(struct spi_master *master,
 				    struct spi_message *mesg);
 	int (*unprepare_transfer_hardware)(struct spi_master *master);
+	/* gpio chip select */
+	int			*cs_gpios;
 };
 
 static inline void *spi_master_get_devdata(struct spi_master *master)
-- 
cgit v1.2.3-55-g7522


From dc96efb72054985c0912f831da009a2da4e9f6dd Mon Sep 17 00:00:00 2001
From: Matt Schulte
Date: Mon, 19 Nov 2012 09:12:04 -0600
Subject: Serial: Add support for new devices: Exar's XR17V35x family of
 multi-port PCIe UARTs

Add support for new devices: Exar's XR17V35x family of multi-port PCIe UARTs.

Signed-off-by: Matt Schulte <matts@commtech-fastcom.com>
Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250.c     | 71 ++++++++++++++++++++++++++++
 drivers/tty/serial/8250/8250_pci.c | 96 ++++++++++++++++++++++++++++++++++++++
 include/linux/pci_ids.h            |  3 ++
 include/uapi/linux/serial_core.h   |  3 +-
 include/uapi/linux/serial_reg.h    |  6 +++
 5 files changed, 178 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250.c b/drivers/tty/serial/8250/8250.c
index 2af83a246499..3624df674a31 100644
--- a/drivers/tty/serial/8250/8250.c
+++ b/drivers/tty/serial/8250/8250.c
@@ -282,6 +282,15 @@ static const struct serial8250_config uart_config[] = {
 		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
 		.flags		= UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR,
 	},
+	[PORT_XR17V35X] = {
+		.name		= "XR17V35X",
+		.fifo_size	= 256,
+		.tx_loadsz	= 256,
+		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_11 |
+				  UART_FCR_T_TRIG_11,
+		.flags		= UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR |
+				  UART_CAP_SLEEP,
+	},
 	[PORT_LPC3220] = {
 		.name		= "LPC3220",
 		.fifo_size	= 64,
@@ -455,6 +464,7 @@ static void io_serial_out(struct uart_port *p, int offset, int value)
 }
 
 static int serial8250_default_handle_irq(struct uart_port *port);
+static int exar_handle_irq(struct uart_port *port);
 
 static void set_io_from_upio(struct uart_port *p)
 {
@@ -574,6 +584,18 @@ EXPORT_SYMBOL_GPL(serial8250_clear_and_reinit_fifos);
  */
 static void serial8250_set_sleep(struct uart_8250_port *p, int sleep)
 {
+	/*
+	 * Exar UARTs have a SLEEP register that enables or disables
+	 * each UART to enter sleep mode separately.  On the XR17V35x the
+	 * register is accessible to each UART at the UART_EXAR_SLEEP
+	 * offset but the UART channel may only write to the corresponding
+	 * bit.
+	 */
+	if (p->port.type == PORT_XR17V35X) {
+		serial_out(p, UART_EXAR_SLEEP, 0xff);
+		return;
+	}
+
 	if (p->capabilities & UART_CAP_SLEEP) {
 		if (p->capabilities & UART_CAP_EFR) {
 			serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B);
@@ -881,6 +903,27 @@ static void autoconfig_16550a(struct uart_8250_port *up)
 	up->port.type = PORT_16550A;
 	up->capabilities |= UART_CAP_FIFO;
 
+	/*
+	 * XR17V35x UARTs have an extra divisor register, DLD
+	 * that gets enabled with when DLAB is set which will
+	 * cause the device to incorrectly match and assign
+	 * port type to PORT_16650.  The EFR for this UART is
+	 * found at offset 0x09. Instead check the Deice ID (DVID)
+	 * register for a 2, 4 or 8 port UART.
+	 */
+	status1 = serial_in(up, UART_EXAR_DVID);
+	if (status1 == 0x82 || status1 == 0x84 || status1 == 0x88) {
+		if (up->port.flags & UPF_EXAR_EFR) {
+			DEBUG_AUTOCONF("Exar XR17V35x ");
+			up->port.type = PORT_XR17V35X;
+			up->capabilities |= UART_CAP_AFE | UART_CAP_EFR |
+						UART_CAP_SLEEP;
+
+			return;
+		}
+
+	}
+
 	/*
 	 * Check for presence of the EFR when DLAB is set.
 	 * Only ST16C650V1 UARTs pass this test.
@@ -1515,6 +1558,30 @@ static int serial8250_default_handle_irq(struct uart_port *port)
 	return serial8250_handle_irq(port, iir);
 }
 
+/*
+ * These Exar UARTs have an extra interrupt indicator that could
+ * fire for a few unimplemented interrupts.  One of which is a
+ * wakeup event when coming out of sleep.  Put this here just
+ * to be on the safe side that these interrupts don't go unhandled.
+ */
+static int exar_handle_irq(struct uart_port *port)
+{
+	unsigned char int0, int1, int2, int3;
+	unsigned int iir = serial_port_in(port, UART_IIR);
+	int ret;
+
+	ret = serial8250_handle_irq(port, iir);
+
+	if (port->type == PORT_XR17V35X) {
+		int0 = serial_port_in(port, 0x80);
+		int1 = serial_port_in(port, 0x81);
+		int2 = serial_port_in(port, 0x82);
+		int3 = serial_port_in(port, 0x83);
+	}
+
+	return ret;
+}
+
 /*
  * This is the serial driver's interrupt routine.
  *
@@ -2614,6 +2681,10 @@ static void serial8250_config_port(struct uart_port *port, int flags)
 		serial8250_release_rsa_resource(up);
 	if (port->type == PORT_UNKNOWN)
 		serial8250_release_std_resource(up);
+
+	/* Fixme: probably not the best place for this */
+	if (port->type == PORT_XR17V35X)
+		port->handle_irq = exar_handle_irq;
 }
 
 static int
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 97058c1d7d45..2285d3283b3b 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1164,6 +1164,39 @@ pci_xr17c154_setup(struct serial_private *priv,
 	return pci_default_setup(priv, board, port, idx);
 }
 
+static int
+pci_xr17v35x_setup(struct serial_private *priv,
+		  const struct pciserial_board *board,
+		  struct uart_8250_port *port, int idx)
+{
+	u8 __iomem *p;
+
+	p = pci_ioremap_bar(priv->dev, 0);
+
+	port->port.flags |= UPF_EXAR_EFR;
+
+	/*
+	 * Setup Multipurpose Input/Output pins.
+	 */
+	if (idx == 0) {
+		writeb(0x00, p + 0x8f); /*MPIOINT[7:0]*/
+		writeb(0x00, p + 0x90); /*MPIOLVL[7:0]*/
+		writeb(0x00, p + 0x91); /*MPIO3T[7:0]*/
+		writeb(0x00, p + 0x92); /*MPIOINV[7:0]*/
+		writeb(0x00, p + 0x93); /*MPIOSEL[7:0]*/
+		writeb(0x00, p + 0x94); /*MPIOOD[7:0]*/
+		writeb(0x00, p + 0x95); /*MPIOINT[15:8]*/
+		writeb(0x00, p + 0x96); /*MPIOLVL[15:8]*/
+		writeb(0x00, p + 0x97); /*MPIO3T[15:8]*/
+		writeb(0x00, p + 0x98); /*MPIOINV[15:8]*/
+		writeb(0x00, p + 0x99); /*MPIOSEL[15:8]*/
+		writeb(0x00, p + 0x9a); /*MPIOOD[15:8]*/
+	}
+	iounmap(p);
+
+	return pci_default_setup(priv, board, port, idx);
+}
+
 static int
 pci_wch_ch353_setup(struct serial_private *priv,
                     const struct pciserial_board *board,
@@ -1622,6 +1655,27 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = {
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_xr17c154_setup,
 	},
+	{
+		.vendor = PCI_VENDOR_ID_EXAR,
+		.device = PCI_DEVICE_ID_EXAR_XR17V352,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_xr17v35x_setup,
+	},
+	{
+		.vendor = PCI_VENDOR_ID_EXAR,
+		.device = PCI_DEVICE_ID_EXAR_XR17V354,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_xr17v35x_setup,
+	},
+	{
+		.vendor = PCI_VENDOR_ID_EXAR,
+		.device = PCI_DEVICE_ID_EXAR_XR17V358,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_xr17v35x_setup,
+	},
 	/*
 	 * Xircom cards
 	 */
@@ -1962,6 +2016,9 @@ enum pci_board_num_t {
 	pbn_exar_XR17C152,
 	pbn_exar_XR17C154,
 	pbn_exar_XR17C158,
+	pbn_exar_XR17V352,
+	pbn_exar_XR17V354,
+	pbn_exar_XR17V358,
 	pbn_exar_ibm_saturn,
 	pbn_pasemi_1682M,
 	pbn_ni8430_2,
@@ -2580,6 +2637,30 @@ static struct pciserial_board pci_boards[] = {
 		.base_baud	= 921600,
 		.uart_offset	= 0x200,
 	},
+	[pbn_exar_XR17V352] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 2,
+		.base_baud	= 7812500,
+		.uart_offset	= 0x400,
+		.reg_shift	= 0,
+		.first_offset	= 0,
+	},
+	[pbn_exar_XR17V354] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 4,
+		.base_baud	= 7812500,
+		.uart_offset	= 0x400,
+		.reg_shift	= 0,
+		.first_offset	= 0,
+	},
+	[pbn_exar_XR17V358] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 8,
+		.base_baud	= 7812500,
+		.uart_offset	= 0x400,
+		.reg_shift	= 0,
+		.first_offset	= 0,
+	},
 	[pbn_exar_ibm_saturn] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 1,
@@ -3826,6 +3907,21 @@ static struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID,
 		0,
 		0, pbn_exar_XR17C158 },
+	/*
+	 * Exar Corp. XR17V35[248] Dual/Quad/Octal PCIe UARTs
+	 */
+	{	PCI_VENDOR_ID_EXAR, PCI_DEVICE_ID_EXAR_XR17V352,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0,
+		0, pbn_exar_XR17V352 },
+	{	PCI_VENDOR_ID_EXAR, PCI_DEVICE_ID_EXAR_XR17V354,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0,
+		0, pbn_exar_XR17V354 },
+	{	PCI_VENDOR_ID_EXAR, PCI_DEVICE_ID_EXAR_XR17V358,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0,
+		0, pbn_exar_XR17V358 },
 
 	/*
 	 * Topic TP560 Data/Fax/Voice 56k modem (reported by Evan Clarke)
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 9d36b829533a..0199a7a76fcb 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1985,6 +1985,9 @@
 #define PCI_DEVICE_ID_EXAR_XR17C152	0x0152
 #define PCI_DEVICE_ID_EXAR_XR17C154	0x0154
 #define PCI_DEVICE_ID_EXAR_XR17C158	0x0158
+#define PCI_DEVICE_ID_EXAR_XR17V352	0x0352
+#define PCI_DEVICE_ID_EXAR_XR17V354	0x0354
+#define PCI_DEVICE_ID_EXAR_XR17V358	0x0358
 
 #define PCI_VENDOR_ID_MICROGATE		0x13c0
 #define PCI_DEVICE_ID_MICROGATE_USC	0x0010
diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h
index ebcc73f0418a..78f99d97475b 100644
--- a/include/uapi/linux/serial_core.h
+++ b/include/uapi/linux/serial_core.h
@@ -49,7 +49,8 @@
 #define PORT_XR17D15X	21	/* Exar XR17D15x UART */
 #define PORT_LPC3220	22	/* NXP LPC32xx SoC "Standard" UART */
 #define PORT_8250_CIR	23	/* CIR infrared port, has its own driver */
-#define PORT_MAX_8250	23	/* max port ID */
+#define PORT_XR17V35X	24	/* Exar XR17V35x UARTs */
+#define PORT_MAX_8250	24	/* max port ID */
 
 /*
  * ARM specific type numbers.  These are not currently guaranteed
diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h
index 5ed325e88a81..d0b47607b90b 100644
--- a/include/uapi/linux/serial_reg.h
+++ b/include/uapi/linux/serial_reg.h
@@ -367,5 +367,11 @@
 #define UART_OMAP_MDR1_CIR_MODE		0x06	/* CIR mode */
 #define UART_OMAP_MDR1_DISABLE		0x07	/* Disable (default state) */
 
+/*
+ * These are definitions for the XR17V35X and XR17D15X
+ */
+#define UART_EXAR_SLEEP		0x8b	/* Sleep mode */
+#define UART_EXAR_DVID		0x8d	/* Device identification */
+
 #endif /* _LINUX_SERIAL_REG_H */
 
-- 
cgit v1.2.3-55-g7522


From d02f81555362e0032080af62154dca00d5ec99e0 Mon Sep 17 00:00:00 2001
From: Matt Schulte
Date: Tue, 20 Nov 2012 11:21:17 -0600
Subject: Add register definitions used in several Exar PCI/PCIe UARTs

Add register definitions used in several Exar PCI/PCIe UARTs

Signed-off-by: Matt Schulte <matts@commtech-fastcom.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/serial_reg.h | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h
index d0b47607b90b..e6322605b138 100644
--- a/include/uapi/linux/serial_reg.h
+++ b/include/uapi/linux/serial_reg.h
@@ -368,10 +368,22 @@
 #define UART_OMAP_MDR1_DISABLE		0x07	/* Disable (default state) */
 
 /*
- * These are definitions for the XR17V35X and XR17D15X
+ * These are definitions for the Exar XR17V35X and XR17(C|D)15X
  */
+#define UART_EXAR_8XMODE	0x88	/* 8X sampling rate select */
 #define UART_EXAR_SLEEP		0x8b	/* Sleep mode */
 #define UART_EXAR_DVID		0x8d	/* Device identification */
 
+#define UART_EXAR_FCTR		0x08	/* Feature Control Register */
+#define UART_FCTR_EXAR_IRDA	0x08	/* IrDa data encode select */
+#define UART_FCTR_EXAR_485	0x10	/* Auto 485 half duplex dir ctl */
+#define UART_FCTR_EXAR_TRGA	0x00	/* FIFO trigger table A */
+#define UART_FCTR_EXAR_TRGB	0x60	/* FIFO trigger table B */
+#define UART_FCTR_EXAR_TRGC	0x80	/* FIFO trigger table C */
+#define UART_FCTR_EXAR_TRGD	0xc0	/* FIFO trigger table D programmable */
+
+#define UART_EXAR_TXTRG		0x0a	/* Tx FIFO trigger level write-only */
+#define UART_EXAR_RXTRG		0x0b	/* Rx FIFO trigger level write-only */
+
 #endif /* _LINUX_SERIAL_REG_H */
 
-- 
cgit v1.2.3-55-g7522


From 14faa8cce88e18ed4daf5c3643f0faa4198863f9 Mon Sep 17 00:00:00 2001
From: Matt Schulte
Date: Wed, 21 Nov 2012 10:35:15 -0600
Subject: tty/8250 Add support for Commtech's Fastcom Async-335 and Fastcom
 Async-PCIe cards

Add support for Commtech's Fastcom Async-335 and Fastcom Async-PCIe cards

Signed-off-by: Matt Schulte <matts@commtech-fastcom.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_pci.c | 163 +++++++++++++++++++++++++++++++++++++
 include/linux/pci_ids.h            |   2 +
 2 files changed, 165 insertions(+)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 089fd43e3784..a795bd971eaa 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1201,6 +1201,55 @@ pci_xr17v35x_setup(struct serial_private *priv,
 	return pci_default_setup(priv, board, port, idx);
 }
 
+#define PCI_DEVICE_ID_COMMTECH_4222PCI335 0x0004
+#define PCI_DEVICE_ID_COMMTECH_4224PCI335 0x0002
+#define PCI_DEVICE_ID_COMMTECH_2324PCI335 0x000a
+#define PCI_DEVICE_ID_COMMTECH_2328PCI335 0x000b
+
+static int
+pci_fastcom335_setup(struct serial_private *priv,
+		  const struct pciserial_board *board,
+		  struct uart_8250_port *port, int idx)
+{
+	u8 __iomem *p;
+
+	p = pci_ioremap_bar(priv->dev, 0);
+	if (p == NULL)
+		return -ENOMEM;
+
+	port->port.flags |= UPF_EXAR_EFR;
+
+	/*
+	 * Setup Multipurpose Input/Output pins.
+	 */
+	if (idx == 0) {
+		switch (priv->dev->device) {
+		case PCI_DEVICE_ID_COMMTECH_4222PCI335:
+		case PCI_DEVICE_ID_COMMTECH_4224PCI335:
+			writeb(0x78, p + 0x90); /* MPIOLVL[7:0] */
+			writeb(0x00, p + 0x92); /* MPIOINV[7:0] */
+			writeb(0x00, p + 0x93); /* MPIOSEL[7:0] */
+			break;
+		case PCI_DEVICE_ID_COMMTECH_2324PCI335:
+		case PCI_DEVICE_ID_COMMTECH_2328PCI335:
+			writeb(0x00, p + 0x90); /* MPIOLVL[7:0] */
+			writeb(0xc0, p + 0x92); /* MPIOINV[7:0] */
+			writeb(0xc0, p + 0x93); /* MPIOSEL[7:0] */
+			break;
+		}
+		writeb(0x00, p + 0x8f); /* MPIOINT[7:0] */
+		writeb(0x00, p + 0x91); /* MPIO3T[7:0] */
+		writeb(0x00, p + 0x94); /* MPIOOD[7:0] */
+	}
+	writeb(0x00, p + UART_EXAR_8XMODE);
+	writeb(UART_FCTR_EXAR_TRGD, p + UART_EXAR_FCTR);
+	writeb(32, p + UART_EXAR_TXTRG);
+	writeb(32, p + UART_EXAR_RXTRG);
+	iounmap(p);
+
+	return pci_default_setup(priv, board, port, idx);
+}
+
 static int
 pci_wch_ch353_setup(struct serial_private *priv,
                     const struct pciserial_board *board,
@@ -1250,6 +1299,10 @@ pci_wch_ch353_setup(struct serial_private *priv,
 #define PCI_VENDOR_ID_AGESTAR		0x5372
 #define PCI_DEVICE_ID_AGESTAR_9375	0x6872
 #define PCI_VENDOR_ID_ASIX		0x9710
+#define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0019
+#define PCI_DEVICE_ID_COMMTECH_4224PCIE	0x0020
+#define PCI_DEVICE_ID_COMMTECH_4228PCIE	0x0021
+
 
 /* Unknown vendors/cards - this should not be in linux/pci_ids.h */
 #define PCI_SUBDEVICE_ID_UNKNOWN_0x1584	0x1584
@@ -1845,6 +1898,59 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = {
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_asix_setup,
 	},
+	/*
+	 * Commtech, Inc. Fastcom adapters
+	 *
+	 */
+	{
+		.vendor = PCI_VENDOR_ID_COMMTECH,
+		.device = PCI_DEVICE_ID_COMMTECH_4222PCI335,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_fastcom335_setup,
+	},
+	{
+		.vendor = PCI_VENDOR_ID_COMMTECH,
+		.device = PCI_DEVICE_ID_COMMTECH_4224PCI335,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_fastcom335_setup,
+	},
+	{
+		.vendor = PCI_VENDOR_ID_COMMTECH,
+		.device = PCI_DEVICE_ID_COMMTECH_2324PCI335,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_fastcom335_setup,
+	},
+	{
+		.vendor = PCI_VENDOR_ID_COMMTECH,
+		.device = PCI_DEVICE_ID_COMMTECH_2328PCI335,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_fastcom335_setup,
+	},
+	{
+		.vendor = PCI_VENDOR_ID_COMMTECH,
+		.device = PCI_DEVICE_ID_COMMTECH_4222PCIE,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_xr17v35x_setup,
+	},
+	{
+		.vendor = PCI_VENDOR_ID_COMMTECH,
+		.device = PCI_DEVICE_ID_COMMTECH_4224PCIE,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_xr17v35x_setup,
+	},
+	{
+		.vendor = PCI_VENDOR_ID_COMMTECH,
+		.device = PCI_DEVICE_ID_COMMTECH_4228PCIE,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_xr17v35x_setup,
+	},
 	/*
 	 * Default "match everything" terminator entry
 	 */
@@ -1921,6 +2027,10 @@ enum pci_board_num_t {
 
 	pbn_b0_4_1152000,
 
+	pbn_b0_2_1152000_200,
+	pbn_b0_4_1152000_200,
+	pbn_b0_8_1152000_200,
+
 	pbn_b0_2_1843200,
 	pbn_b0_4_1843200,
 
@@ -2118,6 +2228,27 @@ static struct pciserial_board pci_boards[] = {
 		.uart_offset	= 8,
 	},
 
+	[pbn_b0_2_1152000_200] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 2,
+		.base_baud	= 1152000,
+		.uart_offset	= 0x200,
+	},
+
+	[pbn_b0_4_1152000_200] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 4,
+		.base_baud	= 1152000,
+		.uart_offset	= 0x200,
+	},
+
+	[pbn_b0_8_1152000_200] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 2,
+		.base_baud	= 1152000,
+		.uart_offset	= 0x200,
+	},
+
 	[pbn_b0_2_1843200] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 2,
@@ -4356,6 +4487,38 @@ static struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_b0_bt_2_115200 },
 
+	/*
+	 * Commtech, Inc. Fastcom adapters
+	 */
+	{	PCI_VENDOR_ID_COMMTECH, PCI_DEVICE_ID_COMMTECH_4222PCI335,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0,
+		0, pbn_b0_2_1152000_200 },
+	{	PCI_VENDOR_ID_COMMTECH, PCI_DEVICE_ID_COMMTECH_4224PCI335,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0,
+		0, pbn_b0_4_1152000_200 },
+	{	PCI_VENDOR_ID_COMMTECH, PCI_DEVICE_ID_COMMTECH_2324PCI335,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0,
+		0, pbn_b0_4_1152000_200 },
+	{	PCI_VENDOR_ID_COMMTECH, PCI_DEVICE_ID_COMMTECH_2328PCI335,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0,
+		0, pbn_b0_8_1152000_200 },
+	{	PCI_VENDOR_ID_COMMTECH, PCI_DEVICE_ID_COMMTECH_4222PCIE,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0,
+		0, pbn_exar_XR17V352 },
+	{	PCI_VENDOR_ID_COMMTECH, PCI_DEVICE_ID_COMMTECH_4224PCIE,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0,
+		0, pbn_exar_XR17V354 },
+	{	PCI_VENDOR_ID_COMMTECH, PCI_DEVICE_ID_COMMTECH_4228PCIE,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0,
+		0, pbn_exar_XR17V358 },
+
 	/*
 	 * These entries match devices with class COMMUNICATION_SERIAL,
 	 * COMMUNICATION_MODEM or COMMUNICATION_MULTISERIAL
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 0199a7a76fcb..0f8447376ddb 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2326,6 +2326,8 @@
 
 #define PCI_VENDOR_ID_TOPSPIN		0x1867
 
+#define PCI_VENDOR_ID_COMMTECH		0x18f7
+
 #define PCI_VENDOR_ID_SILAN		0x1904
 
 #define PCI_VENDOR_ID_RENESAS		0x1912
-- 
cgit v1.2.3-55-g7522


From df072eb97dcfb819390227649f6b7c07a90aa2df Mon Sep 17 00:00:00 2001
From: MyungJoo Ham
Date: Tue, 20 Nov 2012 19:22:33 +0900
Subject: extcon: kernel_doc style fix

Corrected kernel_doc entries.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 include/linux/extcon.h | 48 ++++++++++++++++++++++++------------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/extcon.h b/include/linux/extcon.h
index 54c00ce9ce7a..fcb51c88319f 100644
--- a/include/linux/extcon.h
+++ b/include/linux/extcon.h
@@ -76,12 +76,12 @@ struct extcon_cable;
 
 /**
  * struct extcon_dev - An extcon device represents one external connector.
- * @name	The name of this extcon device. Parent device name is used
+ * @name:	The name of this extcon device. Parent device name is used
  *		if NULL.
- * @supported_cable	Array of supported cable names ending with NULL.
+ * @supported_cable:	Array of supported cable names ending with NULL.
  *			If supported_cable is NULL, cable name related APIs
  *			are disabled.
- * @mutually_exclusive	Array of mutually exclusive set of cables that cannot
+ * @mutually_exclusive:	Array of mutually exclusive set of cables that cannot
  *			be attached simultaneously. The array should be
  *			ending with NULL or be NULL (no mutually exclusive
  *			cables). For example, if it is { 0x7, 0x30, 0}, then,
@@ -89,21 +89,21 @@ struct extcon_cable;
  *			be attached simulataneously. {0x7, 0} is equivalent to
  *			{0x3, 0x6, 0x5, 0}. If it is {0xFFFFFFFF, 0}, there
  *			can be no simultaneous connections.
- * @print_name	An optional callback to override the method to print the
+ * @print_name:	An optional callback to override the method to print the
  *		name of the extcon device.
- * @print_state	An optional callback to override the method to print the
+ * @print_state:	An optional callback to override the method to print the
  *		status of the extcon device.
- * @dev		Device of this extcon. Do not provide at register-time.
- * @state	Attach/detach state of this extcon. Do not provide at
+ * @dev:	Device of this extcon. Do not provide at register-time.
+ * @state:	Attach/detach state of this extcon. Do not provide at
  *		register-time
- * @nh	Notifier for the state change events from this extcon
- * @entry	To support list of extcon devices so that users can search
+ * @nh:	Notifier for the state change events from this extcon
+ * @entry:	To support list of extcon devices so that users can search
  *		for extcon devices based on the extcon name.
- * @lock
- * @max_supported	Internal value to store the number of cables.
- * @extcon_dev_type	Device_type struct to provide attribute_groups
+ * @lock:
+ * @max_supported:	Internal value to store the number of cables.
+ * @extcon_dev_type:	Device_type struct to provide attribute_groups
  *			customized for each extcon device.
- * @cables	Sysfs subdirectories. Each represents one cable.
+ * @cables:	Sysfs subdirectories. Each represents one cable.
  *
  * In most cases, users only need to provide "User initializing data" of
  * this struct when registering an extcon. In some exceptional cases,
@@ -139,12 +139,12 @@ struct extcon_dev {
 
 /**
  * struct extcon_cable	- An internal data for each cable of extcon device.
- * @edev	The extcon device
- * @cable_index	Index of this cable in the edev
- * @attr_g	Attribute group for the cable
- * @attr_name	"name" sysfs entry
- * @attr_state	"state" sysfs entry
- * @attrs	Array pointing to attr_name and attr_state for attr_g
+ * @edev:	The extcon device
+ * @cable_index:	Index of this cable in the edev
+ * @attr_g:	Attribute group for the cable
+ * @attr_name:	"name" sysfs entry
+ * @attr_state:	"state" sysfs entry
+ * @attrs:	Array pointing to attr_name and attr_state for attr_g
  */
 struct extcon_cable {
 	struct extcon_dev *edev;
@@ -160,11 +160,11 @@ struct extcon_cable {
 /**
  * struct extcon_specific_cable_nb - An internal data for
  *				extcon_register_interest().
- * @internal_nb	a notifier block bridging extcon notifier and cable notifier.
- * @user_nb	user provided notifier block for events from a specific cable.
- * @cable_index	the target cable.
- * @edev	the target extcon device.
- * @previous_value	the saved previous event value.
+ * @internal_nb:	a notifier block bridging extcon notifier and cable notifier.
+ * @user_nb:	user provided notifier block for events from a specific cable.
+ * @cable_index:	the target cable.
+ * @edev:	the target extcon device.
+ * @previous_value:	the saved previous event value.
  */
 struct extcon_specific_cable_nb {
 	struct notifier_block internal_nb;
-- 
cgit v1.2.3-55-g7522


From 8d4b9e3182634d8b5afb5a144a8c6c24b187bcc1 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki
Date: Mon, 12 Nov 2012 13:03:20 +0100
Subject: bcma: export PLL reading function

This is required by NAND flash driver for initializing wait counters.

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 drivers/bcma/driver_chipcommon_pmu.c | 3 ++-
 include/linux/bcma/bcma.h            | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/bcma/driver_chipcommon_pmu.c b/drivers/bcma/driver_chipcommon_pmu.c
index 201faf106b3f..657f23517481 100644
--- a/drivers/bcma/driver_chipcommon_pmu.c
+++ b/drivers/bcma/driver_chipcommon_pmu.c
@@ -13,12 +13,13 @@
 #include <linux/export.h>
 #include <linux/bcma/bcma.h>
 
-static u32 bcma_chipco_pll_read(struct bcma_drv_cc *cc, u32 offset)
+u32 bcma_chipco_pll_read(struct bcma_drv_cc *cc, u32 offset)
 {
 	bcma_cc_write32(cc, BCMA_CC_PLLCTL_ADDR, offset);
 	bcma_cc_read32(cc, BCMA_CC_PLLCTL_ADDR);
 	return bcma_cc_read32(cc, BCMA_CC_PLLCTL_DATA);
 }
+EXPORT_SYMBOL_GPL(bcma_chipco_pll_read);
 
 void bcma_chipco_pll_write(struct bcma_drv_cc *cc, u32 offset, u32 value)
 {
diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index 4180eb78d575..4fb6bd7941d7 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -345,6 +345,7 @@ extern void bcma_core_set_clockmode(struct bcma_device *core,
 				    enum bcma_clkmode clkmode);
 extern void bcma_core_pll_ctl(struct bcma_device *core, u32 req, u32 status,
 			      bool on);
+extern u32 bcma_chipco_pll_read(struct bcma_drv_cc *cc, u32 offset);
 #define BCMA_DMA_TRANSLATION_MASK	0xC0000000
 #define  BCMA_DMA_TRANSLATION_NONE	0x00000000
 #define  BCMA_DMA_TRANSLATION_DMA32_CMT	0x40000000 /* Client Mode Translation for 32-bit DMA */
-- 
cgit v1.2.3-55-g7522


From 3778ff5c709899a29cefe4b3077a926d0e1e9785 Mon Sep 17 00:00:00 2001
From: Eduardo Valentin
Date: Mon, 12 Nov 2012 15:58:50 +0000
Subject: thermal: cpu cooling: use const parameter while registering

There are predefined cpu_masks that are const data structures.
This patch changes the cpu cooling register function so that
those const cpu_masks can be used, without compilation warnings.

include/linux/cpumask.h

 * The following particular system cpumasks and operations manage
 * possible, present, active and online cpus.
 *
 *     cpu_possible_mask- has bit 'cpu' set iff cpu is populatable
 *     cpu_present_mask - has bit 'cpu' set iff cpu is populated
 *     cpu_online_mask  - has bit 'cpu' set iff cpu available to scheduler
 *     cpu_active_mask  - has bit 'cpu' set iff cpu available to migration
 *

Signed-off-by: Eduardo Valentin <eduardo.valentin@ti.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/thermal/cpu_cooling.c | 2 +-
 include/linux/cpu_cooling.h   | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 6f94c2cac1f0..836828e29a87 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -313,7 +313,7 @@ static struct notifier_block thermal_cpufreq_notifier_block = {
  * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
  */
 struct thermal_cooling_device *cpufreq_cooling_register(
-	struct cpumask *clip_cpus)
+	const struct cpumask *clip_cpus)
 {
 	struct thermal_cooling_device *cool_dev;
 	struct cpufreq_cooling_device *cpufreq_dev = NULL;
diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index 851530128e65..b30cc79c7a82 100644
--- a/include/linux/cpu_cooling.h
+++ b/include/linux/cpu_cooling.h
@@ -35,7 +35,7 @@
  * @clip_cpus: cpumask of cpus where the frequency constraints will happen
  */
 struct thermal_cooling_device *cpufreq_cooling_register(
-		struct cpumask *clip_cpus);
+		const struct cpumask *clip_cpus);
 
 /**
  * cpufreq_cooling_unregister - function to remove cpufreq cooling device.
@@ -44,7 +44,7 @@ struct thermal_cooling_device *cpufreq_cooling_register(
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev);
 #else /* !CONFIG_CPU_THERMAL */
 static inline struct thermal_cooling_device *cpufreq_cooling_register(
-	struct cpumask *clip_cpus)
+	const struct cpumask *clip_cpus)
 {
 	return NULL;
 }
-- 
cgit v1.2.3-55-g7522


From 4ba115b1e1ab6b717e08e0f4e766a1d16853d217 Mon Sep 17 00:00:00 2001
From: Eduardo Valentin
Date: Wed, 14 Nov 2012 15:23:30 +0000
Subject: thermal: cpu cooling: allow module builds

As thermal drivers can be built as modules and also
the thermal framework itself, building cpu cooling
only as built-in can cause linking errors. For instance:
* Generic Thermal sysfs driver
*
Generic Thermal sysfs driver (THERMAL) [M/n/y/?] m
  generic cpu cooling support (CPU_THERMAL) [N/y/?] (NEW) y

with the following drive:
CONFIG_OMAP_BANDGAP=m

generates:
ERROR: "cpufreq_cooling_unregister" [drivers/staging/omap-thermal/omap-thermal.ko] undefined!
ERROR: "cpufreq_cooling_register" [drivers/staging/omap-thermal/omap-thermal.ko] undefined!

This patch changes cpu cooling driver to allow it
to be built as module.

Reported-by: Enric Balletbo i Serra <eballetbo@gmail.com>
Signed-off-by: Eduardo Valentin <eduardo.valentin@ti.com>
Reviewed-by: Durgadoss R <durgadoss.r@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/thermal/Kconfig     | 2 +-
 include/linux/cpu_cooling.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index d96da075c9f6..8636fae1f7ec 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -67,7 +67,7 @@ config USER_SPACE
 	  Enable this to let the user space manage the platform thermals.
 
 config CPU_THERMAL
-	bool "generic cpu cooling support"
+	tristate "generic cpu cooling support"
 	depends on CPU_FREQ
 	select CPU_FREQ_TABLE
 	help
diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index b30cc79c7a82..40b4ef54cc7d 100644
--- a/include/linux/cpu_cooling.h
+++ b/include/linux/cpu_cooling.h
@@ -29,7 +29,7 @@
 #define CPUFREQ_COOLING_START		0
 #define CPUFREQ_COOLING_STOP		1
 
-#ifdef CONFIG_CPU_THERMAL
+#if defined(CONFIG_CPU_THERMAL) || defined(CONFIG_CPU_THERMAL_MODULE)
 /**
  * cpufreq_cooling_register - function to create cpufreq cooling device.
  * @clip_cpus: cpumask of cpus where the frequency constraints will happen
-- 
cgit v1.2.3-55-g7522


From 7235aa79f683db0d908dcb0c2b7062dfdd765196 Mon Sep 17 00:00:00 2001
From: David Howells
Date: Wed, 21 Nov 2012 15:47:40 +0000
Subject: UAPI: (Scripted) Disintegrate include/rdma

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Dave Jones <davej@redhat.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 include/rdma/Kbuild               |   6 -
 include/rdma/ib_user_cm.h         | 325 -----------------
 include/rdma/ib_user_mad.h        | 203 -----------
 include/rdma/ib_user_sa.h         |  76 ----
 include/rdma/ib_user_verbs.h      | 734 --------------------------------------
 include/rdma/rdma_netlink.h       |  36 +-
 include/rdma/rdma_user_cm.h       | 249 -------------
 include/uapi/rdma/Kbuild          |   6 +
 include/uapi/rdma/ib_user_cm.h    | 325 +++++++++++++++++
 include/uapi/rdma/ib_user_mad.h   | 203 +++++++++++
 include/uapi/rdma/ib_user_sa.h    |  76 ++++
 include/uapi/rdma/ib_user_verbs.h | 734 ++++++++++++++++++++++++++++++++++++++
 include/uapi/rdma/rdma_netlink.h  |  37 ++
 include/uapi/rdma/rdma_user_cm.h  | 249 +++++++++++++
 14 files changed, 1631 insertions(+), 1628 deletions(-)
 delete mode 100644 include/rdma/ib_user_cm.h
 delete mode 100644 include/rdma/ib_user_mad.h
 delete mode 100644 include/rdma/ib_user_sa.h
 delete mode 100644 include/rdma/ib_user_verbs.h
 delete mode 100644 include/rdma/rdma_user_cm.h
 create mode 100644 include/uapi/rdma/ib_user_cm.h
 create mode 100644 include/uapi/rdma/ib_user_mad.h
 create mode 100644 include/uapi/rdma/ib_user_sa.h
 create mode 100644 include/uapi/rdma/ib_user_verbs.h
 create mode 100644 include/uapi/rdma/rdma_netlink.h
 create mode 100644 include/uapi/rdma/rdma_user_cm.h

(limited to 'include')

diff --git a/include/rdma/Kbuild b/include/rdma/Kbuild
index ea56f76c0c22..e69de29bb2d1 100644
--- a/include/rdma/Kbuild
+++ b/include/rdma/Kbuild
@@ -1,6 +0,0 @@
-header-y += ib_user_cm.h
-header-y += ib_user_mad.h
-header-y += ib_user_sa.h
-header-y += ib_user_verbs.h
-header-y += rdma_netlink.h
-header-y += rdma_user_cm.h
diff --git a/include/rdma/ib_user_cm.h b/include/rdma/ib_user_cm.h
deleted file mode 100644
index f79014aa28f9..000000000000
--- a/include/rdma/ib_user_cm.h
+++ /dev/null
@@ -1,325 +0,0 @@
-/*
- * Copyright (c) 2005 Topspin Communications.  All rights reserved.
- * Copyright (c) 2005 Intel Corporation.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef IB_USER_CM_H
-#define IB_USER_CM_H
-
-#include <linux/types.h>
-#include <rdma/ib_user_sa.h>
-
-#define IB_USER_CM_ABI_VERSION 5
-
-enum {
-	IB_USER_CM_CMD_CREATE_ID,
-	IB_USER_CM_CMD_DESTROY_ID,
-	IB_USER_CM_CMD_ATTR_ID,
-
-	IB_USER_CM_CMD_LISTEN,
-	IB_USER_CM_CMD_NOTIFY,
-
-	IB_USER_CM_CMD_SEND_REQ,
-	IB_USER_CM_CMD_SEND_REP,
-	IB_USER_CM_CMD_SEND_RTU,
-	IB_USER_CM_CMD_SEND_DREQ,
-	IB_USER_CM_CMD_SEND_DREP,
-	IB_USER_CM_CMD_SEND_REJ,
-	IB_USER_CM_CMD_SEND_MRA,
-	IB_USER_CM_CMD_SEND_LAP,
-	IB_USER_CM_CMD_SEND_APR,
-	IB_USER_CM_CMD_SEND_SIDR_REQ,
-	IB_USER_CM_CMD_SEND_SIDR_REP,
-
-	IB_USER_CM_CMD_EVENT,
-	IB_USER_CM_CMD_INIT_QP_ATTR,
-};
-/*
- * command ABI structures.
- */
-struct ib_ucm_cmd_hdr {
-	__u32 cmd;
-	__u16 in;
-	__u16 out;
-};
-
-struct ib_ucm_create_id {
-	__u64 uid;
-	__u64 response;
-};
-
-struct ib_ucm_create_id_resp {
-	__u32 id;
-};
-
-struct ib_ucm_destroy_id {
-	__u64 response;
-	__u32 id;
-	__u32 reserved;
-};
-
-struct ib_ucm_destroy_id_resp {
-	__u32 events_reported;
-};
-
-struct ib_ucm_attr_id {
-	__u64 response;
-	__u32 id;
-	__u32 reserved;
-};
-
-struct ib_ucm_attr_id_resp {
-	__be64 service_id;
-	__be64 service_mask;
-	__be32 local_id;
-	__be32 remote_id;
-};
-
-struct ib_ucm_init_qp_attr {
-	__u64 response;
-	__u32 id;
-	__u32 qp_state;
-};
-
-struct ib_ucm_listen {
-	__be64 service_id;
-	__be64 service_mask;
-	__u32 id;
-	__u32 reserved;
-};
-
-struct ib_ucm_notify {
-	__u32 id;
-	__u32 event;
-};
-
-struct ib_ucm_private_data {
-	__u64 data;
-	__u32 id;
-	__u8  len;
-	__u8  reserved[3];
-};
-
-struct ib_ucm_req {
-	__u32 id;
-	__u32 qpn;
-	__u32 qp_type;
-	__u32 psn;
-	__be64 sid;
-	__u64 data;
-	__u64 primary_path;
-	__u64 alternate_path;
-	__u8  len;
-	__u8  peer_to_peer;
-	__u8  responder_resources;
-	__u8  initiator_depth;
-	__u8  remote_cm_response_timeout;
-	__u8  flow_control;
-	__u8  local_cm_response_timeout;
-	__u8  retry_count;
-	__u8  rnr_retry_count;
-	__u8  max_cm_retries;
-	__u8  srq;
-	__u8  reserved[5];
-};
-
-struct ib_ucm_rep {
-	__u64 uid;
-	__u64 data;
-	__u32 id;
-	__u32 qpn;
-	__u32 psn;
-	__u8  len;
-	__u8  responder_resources;
-	__u8  initiator_depth;
-	__u8  target_ack_delay;
-	__u8  failover_accepted;
-	__u8  flow_control;
-	__u8  rnr_retry_count;
-	__u8  srq;
-	__u8  reserved[4];
-};
-
-struct ib_ucm_info {
-	__u32 id;
-	__u32 status;
-	__u64 info;
-	__u64 data;
-	__u8  info_len;
-	__u8  data_len;
-	__u8  reserved[6];
-};
-
-struct ib_ucm_mra {
-	__u64 data;
-	__u32 id;
-	__u8  len;
-	__u8  timeout;
-	__u8  reserved[2];
-};
-
-struct ib_ucm_lap {
-	__u64 path;
-	__u64 data;
-	__u32 id;
-	__u8  len;
-	__u8  reserved[3];
-};
-
-struct ib_ucm_sidr_req {
-	__u32 id;
-	__u32 timeout;
-	__be64 sid;
-	__u64 data;
-	__u64 path;
-	__u16 reserved_pkey;
-	__u8  len;
-	__u8  max_cm_retries;
-	__u8  reserved[4];
-};
-
-struct ib_ucm_sidr_rep {
-	__u32 id;
-	__u32 qpn;
-	__u32 qkey;
-	__u32 status;
-	__u64 info;
-	__u64 data;
-	__u8  info_len;
-	__u8  data_len;
-	__u8  reserved[6];
-};
-/*
- * event notification ABI structures.
- */
-struct ib_ucm_event_get {
-	__u64 response;
-	__u64 data;
-	__u64 info;
-	__u8  data_len;
-	__u8  info_len;
-	__u8  reserved[6];
-};
-
-struct ib_ucm_req_event_resp {
-	struct ib_user_path_rec primary_path;
-	struct ib_user_path_rec alternate_path;
-	__be64                 remote_ca_guid;
-	__u32                  remote_qkey;
-	__u32                  remote_qpn;
-	__u32                  qp_type;
-	__u32                  starting_psn;
-	__u8  responder_resources;
-	__u8  initiator_depth;
-	__u8  local_cm_response_timeout;
-	__u8  flow_control;
-	__u8  remote_cm_response_timeout;
-	__u8  retry_count;
-	__u8  rnr_retry_count;
-	__u8  srq;
-	__u8  port;
-	__u8  reserved[7];
-};
-
-struct ib_ucm_rep_event_resp {
-	__be64 remote_ca_guid;
-	__u32 remote_qkey;
-	__u32 remote_qpn;
-	__u32 starting_psn;
-	__u8  responder_resources;
-	__u8  initiator_depth;
-	__u8  target_ack_delay;
-	__u8  failover_accepted;
-	__u8  flow_control;
-	__u8  rnr_retry_count;
-	__u8  srq;
-	__u8  reserved[5];
-};
-
-struct ib_ucm_rej_event_resp {
-	__u32 reason;
-	/* ari in ib_ucm_event_get info field. */
-};
-
-struct ib_ucm_mra_event_resp {
-	__u8  timeout;
-	__u8  reserved[3];
-};
-
-struct ib_ucm_lap_event_resp {
-	struct ib_user_path_rec path;
-};
-
-struct ib_ucm_apr_event_resp {
-	__u32 status;
-	/* apr info in ib_ucm_event_get info field. */
-};
-
-struct ib_ucm_sidr_req_event_resp {
-	__u16 pkey;
-	__u8  port;
-	__u8  reserved;
-};
-
-struct ib_ucm_sidr_rep_event_resp {
-	__u32 status;
-	__u32 qkey;
-	__u32 qpn;
-	/* info in ib_ucm_event_get info field. */
-};
-
-#define IB_UCM_PRES_DATA      0x01
-#define IB_UCM_PRES_INFO      0x02
-#define IB_UCM_PRES_PRIMARY   0x04
-#define IB_UCM_PRES_ALTERNATE 0x08
-
-struct ib_ucm_event_resp {
-	__u64 uid;
-	__u32 id;
-	__u32 event;
-	__u32 present;
-	__u32 reserved;
-	union {
-		struct ib_ucm_req_event_resp req_resp;
-		struct ib_ucm_rep_event_resp rep_resp;
-		struct ib_ucm_rej_event_resp rej_resp;
-		struct ib_ucm_mra_event_resp mra_resp;
-		struct ib_ucm_lap_event_resp lap_resp;
-		struct ib_ucm_apr_event_resp apr_resp;
-
-		struct ib_ucm_sidr_req_event_resp sidr_req_resp;
-		struct ib_ucm_sidr_rep_event_resp sidr_rep_resp;
-
-		__u32                             send_status;
-	} u;
-};
-
-#endif /* IB_USER_CM_H */
diff --git a/include/rdma/ib_user_mad.h b/include/rdma/ib_user_mad.h
deleted file mode 100644
index d6fce1cbdb90..000000000000
--- a/include/rdma/ib_user_mad.h
+++ /dev/null
@@ -1,203 +0,0 @@
-/*
- * Copyright (c) 2004 Topspin Communications.  All rights reserved.
- * Copyright (c) 2005 Voltaire, Inc. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef IB_USER_MAD_H
-#define IB_USER_MAD_H
-
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-/*
- * Increment this value if any changes that break userspace ABI
- * compatibility are made.
- */
-#define IB_USER_MAD_ABI_VERSION	5
-
-/*
- * Make sure that all structs defined in this file remain laid out so
- * that they pack the same way on 32-bit and 64-bit architectures (to
- * avoid incompatibility between 32-bit userspace and 64-bit kernels).
- */
-
-/**
- * ib_user_mad_hdr_old - Old version of MAD packet header without pkey_index
- * @id - ID of agent MAD received with/to be sent with
- * @status - 0 on successful receive, ETIMEDOUT if no response
- *   received (transaction ID in data[] will be set to TID of original
- *   request) (ignored on send)
- * @timeout_ms - Milliseconds to wait for response (unset on receive)
- * @retries - Number of automatic retries to attempt
- * @qpn - Remote QP number received from/to be sent to
- * @qkey - Remote Q_Key to be sent with (unset on receive)
- * @lid - Remote lid received from/to be sent to
- * @sl - Service level received with/to be sent with
- * @path_bits - Local path bits received with/to be sent with
- * @grh_present - If set, GRH was received/should be sent
- * @gid_index - Local GID index to send with (unset on receive)
- * @hop_limit - Hop limit in GRH
- * @traffic_class - Traffic class in GRH
- * @gid - Remote GID in GRH
- * @flow_label - Flow label in GRH
- */
-struct ib_user_mad_hdr_old {
-	__u32	id;
-	__u32	status;
-	__u32	timeout_ms;
-	__u32	retries;
-	__u32	length;
-	__be32	qpn;
-	__be32  qkey;
-	__be16	lid;
-	__u8	sl;
-	__u8	path_bits;
-	__u8	grh_present;
-	__u8	gid_index;
-	__u8	hop_limit;
-	__u8	traffic_class;
-	__u8	gid[16];
-	__be32	flow_label;
-};
-
-/**
- * ib_user_mad_hdr - MAD packet header
- *   This layout allows specifying/receiving the P_Key index.  To use
- *   this capability, an application must call the
- *   IB_USER_MAD_ENABLE_PKEY ioctl on the user MAD file handle before
- *   any other actions with the file handle.
- * @id - ID of agent MAD received with/to be sent with
- * @status - 0 on successful receive, ETIMEDOUT if no response
- *   received (transaction ID in data[] will be set to TID of original
- *   request) (ignored on send)
- * @timeout_ms - Milliseconds to wait for response (unset on receive)
- * @retries - Number of automatic retries to attempt
- * @qpn - Remote QP number received from/to be sent to
- * @qkey - Remote Q_Key to be sent with (unset on receive)
- * @lid - Remote lid received from/to be sent to
- * @sl - Service level received with/to be sent with
- * @path_bits - Local path bits received with/to be sent with
- * @grh_present - If set, GRH was received/should be sent
- * @gid_index - Local GID index to send with (unset on receive)
- * @hop_limit - Hop limit in GRH
- * @traffic_class - Traffic class in GRH
- * @gid - Remote GID in GRH
- * @flow_label - Flow label in GRH
- * @pkey_index - P_Key index
- */
-struct ib_user_mad_hdr {
-	__u32	id;
-	__u32	status;
-	__u32	timeout_ms;
-	__u32	retries;
-	__u32	length;
-	__be32	qpn;
-	__be32  qkey;
-	__be16	lid;
-	__u8	sl;
-	__u8	path_bits;
-	__u8	grh_present;
-	__u8	gid_index;
-	__u8	hop_limit;
-	__u8	traffic_class;
-	__u8	gid[16];
-	__be32	flow_label;
-	__u16	pkey_index;
-	__u8	reserved[6];
-};
-
-/**
- * ib_user_mad - MAD packet
- * @hdr - MAD packet header
- * @data - Contents of MAD
- *
- */
-struct ib_user_mad {
-	struct ib_user_mad_hdr hdr;
-	__u64	data[0];
-};
-
-/*
- * Earlier versions of this interface definition declared the
- * method_mask[] member as an array of __u32 but treated it as a
- * bitmap made up of longs in the kernel.  This ambiguity meant that
- * 32-bit big-endian applications that can run on both 32-bit and
- * 64-bit kernels had no consistent ABI to rely on, and 64-bit
- * big-endian applications that treated method_mask as being made up
- * of 32-bit words would have their bitmap misinterpreted.
- *
- * To clear up this confusion, we change the declaration of
- * method_mask[] to use unsigned long and handle the conversion from
- * 32-bit userspace to 64-bit kernel for big-endian systems in the
- * compat_ioctl method.  Unfortunately, to keep the structure layout
- * the same, we need the method_mask[] array to be aligned only to 4
- * bytes even when long is 64 bits, which forces us into this ugly
- * typedef.
- */
-typedef unsigned long __attribute__((aligned(4))) packed_ulong;
-#define IB_USER_MAD_LONGS_PER_METHOD_MASK (128 / (8 * sizeof (long)))
-
-/**
- * ib_user_mad_reg_req - MAD registration request
- * @id - Set by the kernel; used to identify agent in future requests.
- * @qpn - Queue pair number; must be 0 or 1.
- * @method_mask - The caller will receive unsolicited MADs for any method
- *   where @method_mask = 1.
- * @mgmt_class - Indicates which management class of MADs should be receive
- *   by the caller.  This field is only required if the user wishes to
- *   receive unsolicited MADs, otherwise it should be 0.
- * @mgmt_class_version - Indicates which version of MADs for the given
- *   management class to receive.
- * @oui: Indicates IEEE OUI when mgmt_class is a vendor class
- *   in the range from 0x30 to 0x4f. Otherwise not used.
- * @rmpp_version: If set, indicates the RMPP version used.
- *
- */
-struct ib_user_mad_reg_req {
-	__u32	id;
-	packed_ulong method_mask[IB_USER_MAD_LONGS_PER_METHOD_MASK];
-	__u8	qpn;
-	__u8	mgmt_class;
-	__u8	mgmt_class_version;
-	__u8    oui[3];
-	__u8	rmpp_version;
-};
-
-#define IB_IOCTL_MAGIC		0x1b
-
-#define IB_USER_MAD_REGISTER_AGENT	_IOWR(IB_IOCTL_MAGIC, 1, \
-					      struct ib_user_mad_reg_req)
-
-#define IB_USER_MAD_UNREGISTER_AGENT	_IOW(IB_IOCTL_MAGIC, 2, __u32)
-
-#define IB_USER_MAD_ENABLE_PKEY		_IO(IB_IOCTL_MAGIC, 3)
-
-#endif /* IB_USER_MAD_H */
diff --git a/include/rdma/ib_user_sa.h b/include/rdma/ib_user_sa.h
deleted file mode 100644
index cfc7c9ba781e..000000000000
--- a/include/rdma/ib_user_sa.h
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * Copyright (c) 2005 Intel Corporation.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef IB_USER_SA_H
-#define IB_USER_SA_H
-
-#include <linux/types.h>
-
-enum {
-	IB_PATH_GMP		= 1,
-	IB_PATH_PRIMARY		= (1<<1),
-	IB_PATH_ALTERNATE	= (1<<2),
-	IB_PATH_OUTBOUND	= (1<<3),
-	IB_PATH_INBOUND		= (1<<4),
-	IB_PATH_INBOUND_REVERSE = (1<<5),
-	IB_PATH_BIDIRECTIONAL	= IB_PATH_OUTBOUND | IB_PATH_INBOUND_REVERSE
-};
-
-struct ib_path_rec_data {
-	__u32	flags;
-	__u32	reserved;
-	__u32	path_rec[16];
-};
-
-struct ib_user_path_rec {
-	__u8	dgid[16];
-	__u8	sgid[16];
-	__be16	dlid;
-	__be16	slid;
-	__u32	raw_traffic;
-	__be32	flow_label;
-	__u32	reversible;
-	__u32	mtu;
-	__be16	pkey;
-	__u8	hop_limit;
-	__u8	traffic_class;
-	__u8	numb_path;
-	__u8	sl;
-	__u8	mtu_selector;
-	__u8	rate_selector;
-	__u8	rate;
-	__u8	packet_life_time_selector;
-	__u8	packet_life_time;
-	__u8	preference;
-};
-
-#endif /* IB_USER_SA_H */
diff --git a/include/rdma/ib_user_verbs.h b/include/rdma/ib_user_verbs.h
deleted file mode 100644
index 81aba3a73aa3..000000000000
--- a/include/rdma/ib_user_verbs.h
+++ /dev/null
@@ -1,734 +0,0 @@
-/*
- * Copyright (c) 2005 Topspin Communications.  All rights reserved.
- * Copyright (c) 2005, 2006 Cisco Systems.  All rights reserved.
- * Copyright (c) 2005 PathScale, Inc.  All rights reserved.
- * Copyright (c) 2006 Mellanox Technologies.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef IB_USER_VERBS_H
-#define IB_USER_VERBS_H
-
-#include <linux/types.h>
-
-/*
- * Increment this value if any changes that break userspace ABI
- * compatibility are made.
- */
-#define IB_USER_VERBS_ABI_VERSION	6
-
-enum {
-	IB_USER_VERBS_CMD_GET_CONTEXT,
-	IB_USER_VERBS_CMD_QUERY_DEVICE,
-	IB_USER_VERBS_CMD_QUERY_PORT,
-	IB_USER_VERBS_CMD_ALLOC_PD,
-	IB_USER_VERBS_CMD_DEALLOC_PD,
-	IB_USER_VERBS_CMD_CREATE_AH,
-	IB_USER_VERBS_CMD_MODIFY_AH,
-	IB_USER_VERBS_CMD_QUERY_AH,
-	IB_USER_VERBS_CMD_DESTROY_AH,
-	IB_USER_VERBS_CMD_REG_MR,
-	IB_USER_VERBS_CMD_REG_SMR,
-	IB_USER_VERBS_CMD_REREG_MR,
-	IB_USER_VERBS_CMD_QUERY_MR,
-	IB_USER_VERBS_CMD_DEREG_MR,
-	IB_USER_VERBS_CMD_ALLOC_MW,
-	IB_USER_VERBS_CMD_BIND_MW,
-	IB_USER_VERBS_CMD_DEALLOC_MW,
-	IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL,
-	IB_USER_VERBS_CMD_CREATE_CQ,
-	IB_USER_VERBS_CMD_RESIZE_CQ,
-	IB_USER_VERBS_CMD_DESTROY_CQ,
-	IB_USER_VERBS_CMD_POLL_CQ,
-	IB_USER_VERBS_CMD_PEEK_CQ,
-	IB_USER_VERBS_CMD_REQ_NOTIFY_CQ,
-	IB_USER_VERBS_CMD_CREATE_QP,
-	IB_USER_VERBS_CMD_QUERY_QP,
-	IB_USER_VERBS_CMD_MODIFY_QP,
-	IB_USER_VERBS_CMD_DESTROY_QP,
-	IB_USER_VERBS_CMD_POST_SEND,
-	IB_USER_VERBS_CMD_POST_RECV,
-	IB_USER_VERBS_CMD_ATTACH_MCAST,
-	IB_USER_VERBS_CMD_DETACH_MCAST,
-	IB_USER_VERBS_CMD_CREATE_SRQ,
-	IB_USER_VERBS_CMD_MODIFY_SRQ,
-	IB_USER_VERBS_CMD_QUERY_SRQ,
-	IB_USER_VERBS_CMD_DESTROY_SRQ,
-	IB_USER_VERBS_CMD_POST_SRQ_RECV,
-	IB_USER_VERBS_CMD_OPEN_XRCD,
-	IB_USER_VERBS_CMD_CLOSE_XRCD,
-	IB_USER_VERBS_CMD_CREATE_XSRQ,
-	IB_USER_VERBS_CMD_OPEN_QP
-};
-
-/*
- * Make sure that all structs defined in this file remain laid out so
- * that they pack the same way on 32-bit and 64-bit architectures (to
- * avoid incompatibility between 32-bit userspace and 64-bit kernels).
- * Specifically:
- *  - Do not use pointer types -- pass pointers in __u64 instead.
- *  - Make sure that any structure larger than 4 bytes is padded to a
- *    multiple of 8 bytes.  Otherwise the structure size will be
- *    different between 32-bit and 64-bit architectures.
- */
-
-struct ib_uverbs_async_event_desc {
-	__u64 element;
-	__u32 event_type;	/* enum ib_event_type */
-	__u32 reserved;
-};
-
-struct ib_uverbs_comp_event_desc {
-	__u64 cq_handle;
-};
-
-/*
- * All commands from userspace should start with a __u32 command field
- * followed by __u16 in_words and out_words fields (which give the
- * length of the command block and response buffer if any in 32-bit
- * words).  The kernel driver will read these fields first and read
- * the rest of the command struct based on these value.
- */
-
-struct ib_uverbs_cmd_hdr {
-	__u32 command;
-	__u16 in_words;
-	__u16 out_words;
-};
-
-struct ib_uverbs_get_context {
-	__u64 response;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_get_context_resp {
-	__u32 async_fd;
-	__u32 num_comp_vectors;
-};
-
-struct ib_uverbs_query_device {
-	__u64 response;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_query_device_resp {
-	__u64 fw_ver;
-	__be64 node_guid;
-	__be64 sys_image_guid;
-	__u64 max_mr_size;
-	__u64 page_size_cap;
-	__u32 vendor_id;
-	__u32 vendor_part_id;
-	__u32 hw_ver;
-	__u32 max_qp;
-	__u32 max_qp_wr;
-	__u32 device_cap_flags;
-	__u32 max_sge;
-	__u32 max_sge_rd;
-	__u32 max_cq;
-	__u32 max_cqe;
-	__u32 max_mr;
-	__u32 max_pd;
-	__u32 max_qp_rd_atom;
-	__u32 max_ee_rd_atom;
-	__u32 max_res_rd_atom;
-	__u32 max_qp_init_rd_atom;
-	__u32 max_ee_init_rd_atom;
-	__u32 atomic_cap;
-	__u32 max_ee;
-	__u32 max_rdd;
-	__u32 max_mw;
-	__u32 max_raw_ipv6_qp;
-	__u32 max_raw_ethy_qp;
-	__u32 max_mcast_grp;
-	__u32 max_mcast_qp_attach;
-	__u32 max_total_mcast_qp_attach;
-	__u32 max_ah;
-	__u32 max_fmr;
-	__u32 max_map_per_fmr;
-	__u32 max_srq;
-	__u32 max_srq_wr;
-	__u32 max_srq_sge;
-	__u16 max_pkeys;
-	__u8  local_ca_ack_delay;
-	__u8  phys_port_cnt;
-	__u8  reserved[4];
-};
-
-struct ib_uverbs_query_port {
-	__u64 response;
-	__u8  port_num;
-	__u8  reserved[7];
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_query_port_resp {
-	__u32 port_cap_flags;
-	__u32 max_msg_sz;
-	__u32 bad_pkey_cntr;
-	__u32 qkey_viol_cntr;
-	__u32 gid_tbl_len;
-	__u16 pkey_tbl_len;
-	__u16 lid;
-	__u16 sm_lid;
-	__u8  state;
-	__u8  max_mtu;
-	__u8  active_mtu;
-	__u8  lmc;
-	__u8  max_vl_num;
-	__u8  sm_sl;
-	__u8  subnet_timeout;
-	__u8  init_type_reply;
-	__u8  active_width;
-	__u8  active_speed;
-	__u8  phys_state;
-	__u8  link_layer;
-	__u8  reserved[2];
-};
-
-struct ib_uverbs_alloc_pd {
-	__u64 response;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_alloc_pd_resp {
-	__u32 pd_handle;
-};
-
-struct ib_uverbs_dealloc_pd {
-	__u32 pd_handle;
-};
-
-struct ib_uverbs_open_xrcd {
-	__u64 response;
-	__u32 fd;
-	__u32 oflags;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_open_xrcd_resp {
-	__u32 xrcd_handle;
-};
-
-struct ib_uverbs_close_xrcd {
-	__u32 xrcd_handle;
-};
-
-struct ib_uverbs_reg_mr {
-	__u64 response;
-	__u64 start;
-	__u64 length;
-	__u64 hca_va;
-	__u32 pd_handle;
-	__u32 access_flags;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_reg_mr_resp {
-	__u32 mr_handle;
-	__u32 lkey;
-	__u32 rkey;
-};
-
-struct ib_uverbs_dereg_mr {
-	__u32 mr_handle;
-};
-
-struct ib_uverbs_create_comp_channel {
-	__u64 response;
-};
-
-struct ib_uverbs_create_comp_channel_resp {
-	__u32 fd;
-};
-
-struct ib_uverbs_create_cq {
-	__u64 response;
-	__u64 user_handle;
-	__u32 cqe;
-	__u32 comp_vector;
-	__s32 comp_channel;
-	__u32 reserved;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_create_cq_resp {
-	__u32 cq_handle;
-	__u32 cqe;
-};
-
-struct ib_uverbs_resize_cq {
-	__u64 response;
-	__u32 cq_handle;
-	__u32 cqe;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_resize_cq_resp {
-	__u32 cqe;
-	__u32 reserved;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_poll_cq {
-	__u64 response;
-	__u32 cq_handle;
-	__u32 ne;
-};
-
-struct ib_uverbs_wc {
-	__u64 wr_id;
-	__u32 status;
-	__u32 opcode;
-	__u32 vendor_err;
-	__u32 byte_len;
-	union {
-		__u32 imm_data;
-		__u32 invalidate_rkey;
-	} ex;
-	__u32 qp_num;
-	__u32 src_qp;
-	__u32 wc_flags;
-	__u16 pkey_index;
-	__u16 slid;
-	__u8 sl;
-	__u8 dlid_path_bits;
-	__u8 port_num;
-	__u8 reserved;
-};
-
-struct ib_uverbs_poll_cq_resp {
-	__u32 count;
-	__u32 reserved;
-	struct ib_uverbs_wc wc[0];
-};
-
-struct ib_uverbs_req_notify_cq {
-	__u32 cq_handle;
-	__u32 solicited_only;
-};
-
-struct ib_uverbs_destroy_cq {
-	__u64 response;
-	__u32 cq_handle;
-	__u32 reserved;
-};
-
-struct ib_uverbs_destroy_cq_resp {
-	__u32 comp_events_reported;
-	__u32 async_events_reported;
-};
-
-struct ib_uverbs_global_route {
-	__u8  dgid[16];
-	__u32 flow_label;
-	__u8  sgid_index;
-	__u8  hop_limit;
-	__u8  traffic_class;
-	__u8  reserved;
-};
-
-struct ib_uverbs_ah_attr {
-	struct ib_uverbs_global_route grh;
-	__u16 dlid;
-	__u8  sl;
-	__u8  src_path_bits;
-	__u8  static_rate;
-	__u8  is_global;
-	__u8  port_num;
-	__u8  reserved;
-};
-
-struct ib_uverbs_qp_attr {
-	__u32	qp_attr_mask;
-	__u32	qp_state;
-	__u32	cur_qp_state;
-	__u32	path_mtu;
-	__u32	path_mig_state;
-	__u32	qkey;
-	__u32	rq_psn;
-	__u32	sq_psn;
-	__u32	dest_qp_num;
-	__u32	qp_access_flags;
-
-	struct ib_uverbs_ah_attr ah_attr;
-	struct ib_uverbs_ah_attr alt_ah_attr;
-
-	/* ib_qp_cap */
-	__u32	max_send_wr;
-	__u32	max_recv_wr;
-	__u32	max_send_sge;
-	__u32	max_recv_sge;
-	__u32	max_inline_data;
-
-	__u16	pkey_index;
-	__u16	alt_pkey_index;
-	__u8	en_sqd_async_notify;
-	__u8	sq_draining;
-	__u8	max_rd_atomic;
-	__u8	max_dest_rd_atomic;
-	__u8	min_rnr_timer;
-	__u8	port_num;
-	__u8	timeout;
-	__u8	retry_cnt;
-	__u8	rnr_retry;
-	__u8	alt_port_num;
-	__u8	alt_timeout;
-	__u8	reserved[5];
-};
-
-struct ib_uverbs_create_qp {
-	__u64 response;
-	__u64 user_handle;
-	__u32 pd_handle;
-	__u32 send_cq_handle;
-	__u32 recv_cq_handle;
-	__u32 srq_handle;
-	__u32 max_send_wr;
-	__u32 max_recv_wr;
-	__u32 max_send_sge;
-	__u32 max_recv_sge;
-	__u32 max_inline_data;
-	__u8  sq_sig_all;
-	__u8  qp_type;
-	__u8  is_srq;
-	__u8  reserved;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_open_qp {
-	__u64 response;
-	__u64 user_handle;
-	__u32 pd_handle;
-	__u32 qpn;
-	__u8  qp_type;
-	__u8  reserved[7];
-	__u64 driver_data[0];
-};
-
-/* also used for open response */
-struct ib_uverbs_create_qp_resp {
-	__u32 qp_handle;
-	__u32 qpn;
-	__u32 max_send_wr;
-	__u32 max_recv_wr;
-	__u32 max_send_sge;
-	__u32 max_recv_sge;
-	__u32 max_inline_data;
-	__u32 reserved;
-};
-
-/*
- * This struct needs to remain a multiple of 8 bytes to keep the
- * alignment of the modify QP parameters.
- */
-struct ib_uverbs_qp_dest {
-	__u8  dgid[16];
-	__u32 flow_label;
-	__u16 dlid;
-	__u16 reserved;
-	__u8  sgid_index;
-	__u8  hop_limit;
-	__u8  traffic_class;
-	__u8  sl;
-	__u8  src_path_bits;
-	__u8  static_rate;
-	__u8  is_global;
-	__u8  port_num;
-};
-
-struct ib_uverbs_query_qp {
-	__u64 response;
-	__u32 qp_handle;
-	__u32 attr_mask;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_query_qp_resp {
-	struct ib_uverbs_qp_dest dest;
-	struct ib_uverbs_qp_dest alt_dest;
-	__u32 max_send_wr;
-	__u32 max_recv_wr;
-	__u32 max_send_sge;
-	__u32 max_recv_sge;
-	__u32 max_inline_data;
-	__u32 qkey;
-	__u32 rq_psn;
-	__u32 sq_psn;
-	__u32 dest_qp_num;
-	__u32 qp_access_flags;
-	__u16 pkey_index;
-	__u16 alt_pkey_index;
-	__u8  qp_state;
-	__u8  cur_qp_state;
-	__u8  path_mtu;
-	__u8  path_mig_state;
-	__u8  sq_draining;
-	__u8  max_rd_atomic;
-	__u8  max_dest_rd_atomic;
-	__u8  min_rnr_timer;
-	__u8  port_num;
-	__u8  timeout;
-	__u8  retry_cnt;
-	__u8  rnr_retry;
-	__u8  alt_port_num;
-	__u8  alt_timeout;
-	__u8  sq_sig_all;
-	__u8  reserved[5];
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_modify_qp {
-	struct ib_uverbs_qp_dest dest;
-	struct ib_uverbs_qp_dest alt_dest;
-	__u32 qp_handle;
-	__u32 attr_mask;
-	__u32 qkey;
-	__u32 rq_psn;
-	__u32 sq_psn;
-	__u32 dest_qp_num;
-	__u32 qp_access_flags;
-	__u16 pkey_index;
-	__u16 alt_pkey_index;
-	__u8  qp_state;
-	__u8  cur_qp_state;
-	__u8  path_mtu;
-	__u8  path_mig_state;
-	__u8  en_sqd_async_notify;
-	__u8  max_rd_atomic;
-	__u8  max_dest_rd_atomic;
-	__u8  min_rnr_timer;
-	__u8  port_num;
-	__u8  timeout;
-	__u8  retry_cnt;
-	__u8  rnr_retry;
-	__u8  alt_port_num;
-	__u8  alt_timeout;
-	__u8  reserved[2];
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_modify_qp_resp {
-};
-
-struct ib_uverbs_destroy_qp {
-	__u64 response;
-	__u32 qp_handle;
-	__u32 reserved;
-};
-
-struct ib_uverbs_destroy_qp_resp {
-	__u32 events_reported;
-};
-
-/*
- * The ib_uverbs_sge structure isn't used anywhere, since we assume
- * the ib_sge structure is packed the same way on 32-bit and 64-bit
- * architectures in both kernel and user space.  It's just here to
- * document the ABI.
- */
-struct ib_uverbs_sge {
-	__u64 addr;
-	__u32 length;
-	__u32 lkey;
-};
-
-struct ib_uverbs_send_wr {
-	__u64 wr_id;
-	__u32 num_sge;
-	__u32 opcode;
-	__u32 send_flags;
-	union {
-		__u32 imm_data;
-		__u32 invalidate_rkey;
-	} ex;
-	union {
-		struct {
-			__u64 remote_addr;
-			__u32 rkey;
-			__u32 reserved;
-		} rdma;
-		struct {
-			__u64 remote_addr;
-			__u64 compare_add;
-			__u64 swap;
-			__u32 rkey;
-			__u32 reserved;
-		} atomic;
-		struct {
-			__u32 ah;
-			__u32 remote_qpn;
-			__u32 remote_qkey;
-			__u32 reserved;
-		} ud;
-	} wr;
-};
-
-struct ib_uverbs_post_send {
-	__u64 response;
-	__u32 qp_handle;
-	__u32 wr_count;
-	__u32 sge_count;
-	__u32 wqe_size;
-	struct ib_uverbs_send_wr send_wr[0];
-};
-
-struct ib_uverbs_post_send_resp {
-	__u32 bad_wr;
-};
-
-struct ib_uverbs_recv_wr {
-	__u64 wr_id;
-	__u32 num_sge;
-	__u32 reserved;
-};
-
-struct ib_uverbs_post_recv {
-	__u64 response;
-	__u32 qp_handle;
-	__u32 wr_count;
-	__u32 sge_count;
-	__u32 wqe_size;
-	struct ib_uverbs_recv_wr recv_wr[0];
-};
-
-struct ib_uverbs_post_recv_resp {
-	__u32 bad_wr;
-};
-
-struct ib_uverbs_post_srq_recv {
-	__u64 response;
-	__u32 srq_handle;
-	__u32 wr_count;
-	__u32 sge_count;
-	__u32 wqe_size;
-	struct ib_uverbs_recv_wr recv[0];
-};
-
-struct ib_uverbs_post_srq_recv_resp {
-	__u32 bad_wr;
-};
-
-struct ib_uverbs_create_ah {
-	__u64 response;
-	__u64 user_handle;
-	__u32 pd_handle;
-	__u32 reserved;
-	struct ib_uverbs_ah_attr attr;
-};
-
-struct ib_uverbs_create_ah_resp {
-	__u32 ah_handle;
-};
-
-struct ib_uverbs_destroy_ah {
-	__u32 ah_handle;
-};
-
-struct ib_uverbs_attach_mcast {
-	__u8  gid[16];
-	__u32 qp_handle;
-	__u16 mlid;
-	__u16 reserved;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_detach_mcast {
-	__u8  gid[16];
-	__u32 qp_handle;
-	__u16 mlid;
-	__u16 reserved;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_create_srq {
-	__u64 response;
-	__u64 user_handle;
-	__u32 pd_handle;
-	__u32 max_wr;
-	__u32 max_sge;
-	__u32 srq_limit;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_create_xsrq {
-	__u64 response;
-	__u64 user_handle;
-	__u32 srq_type;
-	__u32 pd_handle;
-	__u32 max_wr;
-	__u32 max_sge;
-	__u32 srq_limit;
-	__u32 reserved;
-	__u32 xrcd_handle;
-	__u32 cq_handle;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_create_srq_resp {
-	__u32 srq_handle;
-	__u32 max_wr;
-	__u32 max_sge;
-	__u32 srqn;
-};
-
-struct ib_uverbs_modify_srq {
-	__u32 srq_handle;
-	__u32 attr_mask;
-	__u32 max_wr;
-	__u32 srq_limit;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_query_srq {
-	__u64 response;
-	__u32 srq_handle;
-	__u32 reserved;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_query_srq_resp {
-	__u32 max_wr;
-	__u32 max_sge;
-	__u32 srq_limit;
-	__u32 reserved;
-};
-
-struct ib_uverbs_destroy_srq {
-	__u64 response;
-	__u32 srq_handle;
-	__u32 reserved;
-};
-
-struct ib_uverbs_destroy_srq_resp {
-	__u32 events_reported;
-};
-
-#endif /* IB_USER_VERBS_H */
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index bd3d8b24b420..e38de79eeb48 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -1,41 +1,9 @@
 #ifndef _RDMA_NETLINK_H
 #define _RDMA_NETLINK_H
 
-#include <linux/types.h>
-
-enum {
-	RDMA_NL_RDMA_CM = 1
-};
-
-#define RDMA_NL_GET_CLIENT(type) ((type & (((1 << 6) - 1) << 10)) >> 10)
-#define RDMA_NL_GET_OP(type) (type & ((1 << 10) - 1))
-#define RDMA_NL_GET_TYPE(client, op) ((client << 10) + op)
-
-enum {
-	RDMA_NL_RDMA_CM_ID_STATS = 0,
-	RDMA_NL_RDMA_CM_NUM_OPS
-};
-
-enum {
-	RDMA_NL_RDMA_CM_ATTR_SRC_ADDR = 1,
-	RDMA_NL_RDMA_CM_ATTR_DST_ADDR,
-	RDMA_NL_RDMA_CM_NUM_ATTR,
-};
-
-struct rdma_cm_id_stats {
-	__u32	qp_num;
-	__u32	bound_dev_if;
-	__u32	port_space;
-	__s32	pid;
-	__u8	cm_state;
-	__u8	node_type;
-	__u8	port_num;
-	__u8	qp_type;
-};
-
-#ifdef __KERNEL__
 
 #include <linux/netlink.h>
+#include <uapi/rdma/rdma_netlink.h>
 
 struct ibnl_client_cbs {
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
@@ -88,6 +56,4 @@ void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
 int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		  int len, void *data, int type);
 
-#endif /* __KERNEL__ */
-
 #endif /* _RDMA_NETLINK_H */
diff --git a/include/rdma/rdma_user_cm.h b/include/rdma/rdma_user_cm.h
deleted file mode 100644
index 1ee9239ff8c2..000000000000
--- a/include/rdma/rdma_user_cm.h
+++ /dev/null
@@ -1,249 +0,0 @@
-/*
- * Copyright (c) 2005-2006 Intel Corporation.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef RDMA_USER_CM_H
-#define RDMA_USER_CM_H
-
-#include <linux/types.h>
-#include <linux/in6.h>
-#include <rdma/ib_user_verbs.h>
-#include <rdma/ib_user_sa.h>
-
-#define RDMA_USER_CM_ABI_VERSION	4
-
-#define RDMA_MAX_PRIVATE_DATA		256
-
-enum {
-	RDMA_USER_CM_CMD_CREATE_ID,
-	RDMA_USER_CM_CMD_DESTROY_ID,
-	RDMA_USER_CM_CMD_BIND_ADDR,
-	RDMA_USER_CM_CMD_RESOLVE_ADDR,
-	RDMA_USER_CM_CMD_RESOLVE_ROUTE,
-	RDMA_USER_CM_CMD_QUERY_ROUTE,
-	RDMA_USER_CM_CMD_CONNECT,
-	RDMA_USER_CM_CMD_LISTEN,
-	RDMA_USER_CM_CMD_ACCEPT,
-	RDMA_USER_CM_CMD_REJECT,
-	RDMA_USER_CM_CMD_DISCONNECT,
-	RDMA_USER_CM_CMD_INIT_QP_ATTR,
-	RDMA_USER_CM_CMD_GET_EVENT,
-	RDMA_USER_CM_CMD_GET_OPTION,
-	RDMA_USER_CM_CMD_SET_OPTION,
-	RDMA_USER_CM_CMD_NOTIFY,
-	RDMA_USER_CM_CMD_JOIN_MCAST,
-	RDMA_USER_CM_CMD_LEAVE_MCAST,
-	RDMA_USER_CM_CMD_MIGRATE_ID
-};
-
-/*
- * command ABI structures.
- */
-struct rdma_ucm_cmd_hdr {
-	__u32 cmd;
-	__u16 in;
-	__u16 out;
-};
-
-struct rdma_ucm_create_id {
-	__u64 uid;
-	__u64 response;
-	__u16 ps;
-	__u8  qp_type;
-	__u8  reserved[5];
-};
-
-struct rdma_ucm_create_id_resp {
-	__u32 id;
-};
-
-struct rdma_ucm_destroy_id {
-	__u64 response;
-	__u32 id;
-	__u32 reserved;
-};
-
-struct rdma_ucm_destroy_id_resp {
-	__u32 events_reported;
-};
-
-struct rdma_ucm_bind_addr {
-	__u64 response;
-	struct sockaddr_in6 addr;
-	__u32 id;
-};
-
-struct rdma_ucm_resolve_addr {
-	struct sockaddr_in6 src_addr;
-	struct sockaddr_in6 dst_addr;
-	__u32 id;
-	__u32 timeout_ms;
-};
-
-struct rdma_ucm_resolve_route {
-	__u32 id;
-	__u32 timeout_ms;
-};
-
-struct rdma_ucm_query_route {
-	__u64 response;
-	__u32 id;
-	__u32 reserved;
-};
-
-struct rdma_ucm_query_route_resp {
-	__u64 node_guid;
-	struct ib_user_path_rec ib_route[2];
-	struct sockaddr_in6 src_addr;
-	struct sockaddr_in6 dst_addr;
-	__u32 num_paths;
-	__u8 port_num;
-	__u8 reserved[3];
-};
-
-struct rdma_ucm_conn_param {
-	__u32 qp_num;
-	__u32 reserved;
-	__u8  private_data[RDMA_MAX_PRIVATE_DATA];
-	__u8  private_data_len;
-	__u8  srq;
-	__u8  responder_resources;
-	__u8  initiator_depth;
-	__u8  flow_control;
-	__u8  retry_count;
-	__u8  rnr_retry_count;
-	__u8  valid;
-};
-
-struct rdma_ucm_ud_param {
-	__u32 qp_num;
-	__u32 qkey;
-	struct ib_uverbs_ah_attr ah_attr;
-	__u8  private_data[RDMA_MAX_PRIVATE_DATA];
-	__u8  private_data_len;
-	__u8  reserved[7];
-};
-
-struct rdma_ucm_connect {
-	struct rdma_ucm_conn_param conn_param;
-	__u32 id;
-	__u32 reserved;
-};
-
-struct rdma_ucm_listen {
-	__u32 id;
-	__u32 backlog;
-};
-
-struct rdma_ucm_accept {
-	__u64 uid;
-	struct rdma_ucm_conn_param conn_param;
-	__u32 id;
-	__u32 reserved;
-};
-
-struct rdma_ucm_reject {
-	__u32 id;
-	__u8  private_data_len;
-	__u8  reserved[3];
-	__u8  private_data[RDMA_MAX_PRIVATE_DATA];
-};
-
-struct rdma_ucm_disconnect {
-	__u32 id;
-};
-
-struct rdma_ucm_init_qp_attr {
-	__u64 response;
-	__u32 id;
-	__u32 qp_state;
-};
-
-struct rdma_ucm_notify {
-	__u32 id;
-	__u32 event;
-};
-
-struct rdma_ucm_join_mcast {
-	__u64 response;		/* rdma_ucm_create_id_resp */
-	__u64 uid;
-	struct sockaddr_in6 addr;
-	__u32 id;
-};
-
-struct rdma_ucm_get_event {
-	__u64 response;
-};
-
-struct rdma_ucm_event_resp {
-	__u64 uid;
-	__u32 id;
-	__u32 event;
-	__u32 status;
-	union {
-		struct rdma_ucm_conn_param conn;
-		struct rdma_ucm_ud_param   ud;
-	} param;
-};
-
-/* Option levels */
-enum {
-	RDMA_OPTION_ID		= 0,
-	RDMA_OPTION_IB		= 1
-};
-
-/* Option details */
-enum {
-	RDMA_OPTION_ID_TOS	 = 0,
-	RDMA_OPTION_ID_REUSEADDR = 1,
-	RDMA_OPTION_ID_AFONLY	 = 2,
-	RDMA_OPTION_IB_PATH	 = 1
-};
-
-struct rdma_ucm_set_option {
-	__u64 optval;
-	__u32 id;
-	__u32 level;
-	__u32 optname;
-	__u32 optlen;
-};
-
-struct rdma_ucm_migrate_id {
-	__u64 response;
-	__u32 id;
-	__u32 fd;
-};
-
-struct rdma_ucm_migrate_resp {
-	__u32 events_reported;
-};
-
-#endif /* RDMA_USER_CM_H */
diff --git a/include/uapi/rdma/Kbuild b/include/uapi/rdma/Kbuild
index aafaa5aa54d4..687ae332200f 100644
--- a/include/uapi/rdma/Kbuild
+++ b/include/uapi/rdma/Kbuild
@@ -1 +1,7 @@
 # UAPI Header export list
+header-y += ib_user_cm.h
+header-y += ib_user_mad.h
+header-y += ib_user_sa.h
+header-y += ib_user_verbs.h
+header-y += rdma_netlink.h
+header-y += rdma_user_cm.h
diff --git a/include/uapi/rdma/ib_user_cm.h b/include/uapi/rdma/ib_user_cm.h
new file mode 100644
index 000000000000..f79014aa28f9
--- /dev/null
+++ b/include/uapi/rdma/ib_user_cm.h
@@ -0,0 +1,325 @@
+/*
+ * Copyright (c) 2005 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005 Intel Corporation.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef IB_USER_CM_H
+#define IB_USER_CM_H
+
+#include <linux/types.h>
+#include <rdma/ib_user_sa.h>
+
+#define IB_USER_CM_ABI_VERSION 5
+
+enum {
+	IB_USER_CM_CMD_CREATE_ID,
+	IB_USER_CM_CMD_DESTROY_ID,
+	IB_USER_CM_CMD_ATTR_ID,
+
+	IB_USER_CM_CMD_LISTEN,
+	IB_USER_CM_CMD_NOTIFY,
+
+	IB_USER_CM_CMD_SEND_REQ,
+	IB_USER_CM_CMD_SEND_REP,
+	IB_USER_CM_CMD_SEND_RTU,
+	IB_USER_CM_CMD_SEND_DREQ,
+	IB_USER_CM_CMD_SEND_DREP,
+	IB_USER_CM_CMD_SEND_REJ,
+	IB_USER_CM_CMD_SEND_MRA,
+	IB_USER_CM_CMD_SEND_LAP,
+	IB_USER_CM_CMD_SEND_APR,
+	IB_USER_CM_CMD_SEND_SIDR_REQ,
+	IB_USER_CM_CMD_SEND_SIDR_REP,
+
+	IB_USER_CM_CMD_EVENT,
+	IB_USER_CM_CMD_INIT_QP_ATTR,
+};
+/*
+ * command ABI structures.
+ */
+struct ib_ucm_cmd_hdr {
+	__u32 cmd;
+	__u16 in;
+	__u16 out;
+};
+
+struct ib_ucm_create_id {
+	__u64 uid;
+	__u64 response;
+};
+
+struct ib_ucm_create_id_resp {
+	__u32 id;
+};
+
+struct ib_ucm_destroy_id {
+	__u64 response;
+	__u32 id;
+	__u32 reserved;
+};
+
+struct ib_ucm_destroy_id_resp {
+	__u32 events_reported;
+};
+
+struct ib_ucm_attr_id {
+	__u64 response;
+	__u32 id;
+	__u32 reserved;
+};
+
+struct ib_ucm_attr_id_resp {
+	__be64 service_id;
+	__be64 service_mask;
+	__be32 local_id;
+	__be32 remote_id;
+};
+
+struct ib_ucm_init_qp_attr {
+	__u64 response;
+	__u32 id;
+	__u32 qp_state;
+};
+
+struct ib_ucm_listen {
+	__be64 service_id;
+	__be64 service_mask;
+	__u32 id;
+	__u32 reserved;
+};
+
+struct ib_ucm_notify {
+	__u32 id;
+	__u32 event;
+};
+
+struct ib_ucm_private_data {
+	__u64 data;
+	__u32 id;
+	__u8  len;
+	__u8  reserved[3];
+};
+
+struct ib_ucm_req {
+	__u32 id;
+	__u32 qpn;
+	__u32 qp_type;
+	__u32 psn;
+	__be64 sid;
+	__u64 data;
+	__u64 primary_path;
+	__u64 alternate_path;
+	__u8  len;
+	__u8  peer_to_peer;
+	__u8  responder_resources;
+	__u8  initiator_depth;
+	__u8  remote_cm_response_timeout;
+	__u8  flow_control;
+	__u8  local_cm_response_timeout;
+	__u8  retry_count;
+	__u8  rnr_retry_count;
+	__u8  max_cm_retries;
+	__u8  srq;
+	__u8  reserved[5];
+};
+
+struct ib_ucm_rep {
+	__u64 uid;
+	__u64 data;
+	__u32 id;
+	__u32 qpn;
+	__u32 psn;
+	__u8  len;
+	__u8  responder_resources;
+	__u8  initiator_depth;
+	__u8  target_ack_delay;
+	__u8  failover_accepted;
+	__u8  flow_control;
+	__u8  rnr_retry_count;
+	__u8  srq;
+	__u8  reserved[4];
+};
+
+struct ib_ucm_info {
+	__u32 id;
+	__u32 status;
+	__u64 info;
+	__u64 data;
+	__u8  info_len;
+	__u8  data_len;
+	__u8  reserved[6];
+};
+
+struct ib_ucm_mra {
+	__u64 data;
+	__u32 id;
+	__u8  len;
+	__u8  timeout;
+	__u8  reserved[2];
+};
+
+struct ib_ucm_lap {
+	__u64 path;
+	__u64 data;
+	__u32 id;
+	__u8  len;
+	__u8  reserved[3];
+};
+
+struct ib_ucm_sidr_req {
+	__u32 id;
+	__u32 timeout;
+	__be64 sid;
+	__u64 data;
+	__u64 path;
+	__u16 reserved_pkey;
+	__u8  len;
+	__u8  max_cm_retries;
+	__u8  reserved[4];
+};
+
+struct ib_ucm_sidr_rep {
+	__u32 id;
+	__u32 qpn;
+	__u32 qkey;
+	__u32 status;
+	__u64 info;
+	__u64 data;
+	__u8  info_len;
+	__u8  data_len;
+	__u8  reserved[6];
+};
+/*
+ * event notification ABI structures.
+ */
+struct ib_ucm_event_get {
+	__u64 response;
+	__u64 data;
+	__u64 info;
+	__u8  data_len;
+	__u8  info_len;
+	__u8  reserved[6];
+};
+
+struct ib_ucm_req_event_resp {
+	struct ib_user_path_rec primary_path;
+	struct ib_user_path_rec alternate_path;
+	__be64                 remote_ca_guid;
+	__u32                  remote_qkey;
+	__u32                  remote_qpn;
+	__u32                  qp_type;
+	__u32                  starting_psn;
+	__u8  responder_resources;
+	__u8  initiator_depth;
+	__u8  local_cm_response_timeout;
+	__u8  flow_control;
+	__u8  remote_cm_response_timeout;
+	__u8  retry_count;
+	__u8  rnr_retry_count;
+	__u8  srq;
+	__u8  port;
+	__u8  reserved[7];
+};
+
+struct ib_ucm_rep_event_resp {
+	__be64 remote_ca_guid;
+	__u32 remote_qkey;
+	__u32 remote_qpn;
+	__u32 starting_psn;
+	__u8  responder_resources;
+	__u8  initiator_depth;
+	__u8  target_ack_delay;
+	__u8  failover_accepted;
+	__u8  flow_control;
+	__u8  rnr_retry_count;
+	__u8  srq;
+	__u8  reserved[5];
+};
+
+struct ib_ucm_rej_event_resp {
+	__u32 reason;
+	/* ari in ib_ucm_event_get info field. */
+};
+
+struct ib_ucm_mra_event_resp {
+	__u8  timeout;
+	__u8  reserved[3];
+};
+
+struct ib_ucm_lap_event_resp {
+	struct ib_user_path_rec path;
+};
+
+struct ib_ucm_apr_event_resp {
+	__u32 status;
+	/* apr info in ib_ucm_event_get info field. */
+};
+
+struct ib_ucm_sidr_req_event_resp {
+	__u16 pkey;
+	__u8  port;
+	__u8  reserved;
+};
+
+struct ib_ucm_sidr_rep_event_resp {
+	__u32 status;
+	__u32 qkey;
+	__u32 qpn;
+	/* info in ib_ucm_event_get info field. */
+};
+
+#define IB_UCM_PRES_DATA      0x01
+#define IB_UCM_PRES_INFO      0x02
+#define IB_UCM_PRES_PRIMARY   0x04
+#define IB_UCM_PRES_ALTERNATE 0x08
+
+struct ib_ucm_event_resp {
+	__u64 uid;
+	__u32 id;
+	__u32 event;
+	__u32 present;
+	__u32 reserved;
+	union {
+		struct ib_ucm_req_event_resp req_resp;
+		struct ib_ucm_rep_event_resp rep_resp;
+		struct ib_ucm_rej_event_resp rej_resp;
+		struct ib_ucm_mra_event_resp mra_resp;
+		struct ib_ucm_lap_event_resp lap_resp;
+		struct ib_ucm_apr_event_resp apr_resp;
+
+		struct ib_ucm_sidr_req_event_resp sidr_req_resp;
+		struct ib_ucm_sidr_rep_event_resp sidr_rep_resp;
+
+		__u32                             send_status;
+	} u;
+};
+
+#endif /* IB_USER_CM_H */
diff --git a/include/uapi/rdma/ib_user_mad.h b/include/uapi/rdma/ib_user_mad.h
new file mode 100644
index 000000000000..d6fce1cbdb90
--- /dev/null
+++ b/include/uapi/rdma/ib_user_mad.h
@@ -0,0 +1,203 @@
+/*
+ * Copyright (c) 2004 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005 Voltaire, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef IB_USER_MAD_H
+#define IB_USER_MAD_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * Increment this value if any changes that break userspace ABI
+ * compatibility are made.
+ */
+#define IB_USER_MAD_ABI_VERSION	5
+
+/*
+ * Make sure that all structs defined in this file remain laid out so
+ * that they pack the same way on 32-bit and 64-bit architectures (to
+ * avoid incompatibility between 32-bit userspace and 64-bit kernels).
+ */
+
+/**
+ * ib_user_mad_hdr_old - Old version of MAD packet header without pkey_index
+ * @id - ID of agent MAD received with/to be sent with
+ * @status - 0 on successful receive, ETIMEDOUT if no response
+ *   received (transaction ID in data[] will be set to TID of original
+ *   request) (ignored on send)
+ * @timeout_ms - Milliseconds to wait for response (unset on receive)
+ * @retries - Number of automatic retries to attempt
+ * @qpn - Remote QP number received from/to be sent to
+ * @qkey - Remote Q_Key to be sent with (unset on receive)
+ * @lid - Remote lid received from/to be sent to
+ * @sl - Service level received with/to be sent with
+ * @path_bits - Local path bits received with/to be sent with
+ * @grh_present - If set, GRH was received/should be sent
+ * @gid_index - Local GID index to send with (unset on receive)
+ * @hop_limit - Hop limit in GRH
+ * @traffic_class - Traffic class in GRH
+ * @gid - Remote GID in GRH
+ * @flow_label - Flow label in GRH
+ */
+struct ib_user_mad_hdr_old {
+	__u32	id;
+	__u32	status;
+	__u32	timeout_ms;
+	__u32	retries;
+	__u32	length;
+	__be32	qpn;
+	__be32  qkey;
+	__be16	lid;
+	__u8	sl;
+	__u8	path_bits;
+	__u8	grh_present;
+	__u8	gid_index;
+	__u8	hop_limit;
+	__u8	traffic_class;
+	__u8	gid[16];
+	__be32	flow_label;
+};
+
+/**
+ * ib_user_mad_hdr - MAD packet header
+ *   This layout allows specifying/receiving the P_Key index.  To use
+ *   this capability, an application must call the
+ *   IB_USER_MAD_ENABLE_PKEY ioctl on the user MAD file handle before
+ *   any other actions with the file handle.
+ * @id - ID of agent MAD received with/to be sent with
+ * @status - 0 on successful receive, ETIMEDOUT if no response
+ *   received (transaction ID in data[] will be set to TID of original
+ *   request) (ignored on send)
+ * @timeout_ms - Milliseconds to wait for response (unset on receive)
+ * @retries - Number of automatic retries to attempt
+ * @qpn - Remote QP number received from/to be sent to
+ * @qkey - Remote Q_Key to be sent with (unset on receive)
+ * @lid - Remote lid received from/to be sent to
+ * @sl - Service level received with/to be sent with
+ * @path_bits - Local path bits received with/to be sent with
+ * @grh_present - If set, GRH was received/should be sent
+ * @gid_index - Local GID index to send with (unset on receive)
+ * @hop_limit - Hop limit in GRH
+ * @traffic_class - Traffic class in GRH
+ * @gid - Remote GID in GRH
+ * @flow_label - Flow label in GRH
+ * @pkey_index - P_Key index
+ */
+struct ib_user_mad_hdr {
+	__u32	id;
+	__u32	status;
+	__u32	timeout_ms;
+	__u32	retries;
+	__u32	length;
+	__be32	qpn;
+	__be32  qkey;
+	__be16	lid;
+	__u8	sl;
+	__u8	path_bits;
+	__u8	grh_present;
+	__u8	gid_index;
+	__u8	hop_limit;
+	__u8	traffic_class;
+	__u8	gid[16];
+	__be32	flow_label;
+	__u16	pkey_index;
+	__u8	reserved[6];
+};
+
+/**
+ * ib_user_mad - MAD packet
+ * @hdr - MAD packet header
+ * @data - Contents of MAD
+ *
+ */
+struct ib_user_mad {
+	struct ib_user_mad_hdr hdr;
+	__u64	data[0];
+};
+
+/*
+ * Earlier versions of this interface definition declared the
+ * method_mask[] member as an array of __u32 but treated it as a
+ * bitmap made up of longs in the kernel.  This ambiguity meant that
+ * 32-bit big-endian applications that can run on both 32-bit and
+ * 64-bit kernels had no consistent ABI to rely on, and 64-bit
+ * big-endian applications that treated method_mask as being made up
+ * of 32-bit words would have their bitmap misinterpreted.
+ *
+ * To clear up this confusion, we change the declaration of
+ * method_mask[] to use unsigned long and handle the conversion from
+ * 32-bit userspace to 64-bit kernel for big-endian systems in the
+ * compat_ioctl method.  Unfortunately, to keep the structure layout
+ * the same, we need the method_mask[] array to be aligned only to 4
+ * bytes even when long is 64 bits, which forces us into this ugly
+ * typedef.
+ */
+typedef unsigned long __attribute__((aligned(4))) packed_ulong;
+#define IB_USER_MAD_LONGS_PER_METHOD_MASK (128 / (8 * sizeof (long)))
+
+/**
+ * ib_user_mad_reg_req - MAD registration request
+ * @id - Set by the kernel; used to identify agent in future requests.
+ * @qpn - Queue pair number; must be 0 or 1.
+ * @method_mask - The caller will receive unsolicited MADs for any method
+ *   where @method_mask = 1.
+ * @mgmt_class - Indicates which management class of MADs should be receive
+ *   by the caller.  This field is only required if the user wishes to
+ *   receive unsolicited MADs, otherwise it should be 0.
+ * @mgmt_class_version - Indicates which version of MADs for the given
+ *   management class to receive.
+ * @oui: Indicates IEEE OUI when mgmt_class is a vendor class
+ *   in the range from 0x30 to 0x4f. Otherwise not used.
+ * @rmpp_version: If set, indicates the RMPP version used.
+ *
+ */
+struct ib_user_mad_reg_req {
+	__u32	id;
+	packed_ulong method_mask[IB_USER_MAD_LONGS_PER_METHOD_MASK];
+	__u8	qpn;
+	__u8	mgmt_class;
+	__u8	mgmt_class_version;
+	__u8    oui[3];
+	__u8	rmpp_version;
+};
+
+#define IB_IOCTL_MAGIC		0x1b
+
+#define IB_USER_MAD_REGISTER_AGENT	_IOWR(IB_IOCTL_MAGIC, 1, \
+					      struct ib_user_mad_reg_req)
+
+#define IB_USER_MAD_UNREGISTER_AGENT	_IOW(IB_IOCTL_MAGIC, 2, __u32)
+
+#define IB_USER_MAD_ENABLE_PKEY		_IO(IB_IOCTL_MAGIC, 3)
+
+#endif /* IB_USER_MAD_H */
diff --git a/include/uapi/rdma/ib_user_sa.h b/include/uapi/rdma/ib_user_sa.h
new file mode 100644
index 000000000000..cfc7c9ba781e
--- /dev/null
+++ b/include/uapi/rdma/ib_user_sa.h
@@ -0,0 +1,76 @@
+/*
+ * Copyright (c) 2005 Intel Corporation.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef IB_USER_SA_H
+#define IB_USER_SA_H
+
+#include <linux/types.h>
+
+enum {
+	IB_PATH_GMP		= 1,
+	IB_PATH_PRIMARY		= (1<<1),
+	IB_PATH_ALTERNATE	= (1<<2),
+	IB_PATH_OUTBOUND	= (1<<3),
+	IB_PATH_INBOUND		= (1<<4),
+	IB_PATH_INBOUND_REVERSE = (1<<5),
+	IB_PATH_BIDIRECTIONAL	= IB_PATH_OUTBOUND | IB_PATH_INBOUND_REVERSE
+};
+
+struct ib_path_rec_data {
+	__u32	flags;
+	__u32	reserved;
+	__u32	path_rec[16];
+};
+
+struct ib_user_path_rec {
+	__u8	dgid[16];
+	__u8	sgid[16];
+	__be16	dlid;
+	__be16	slid;
+	__u32	raw_traffic;
+	__be32	flow_label;
+	__u32	reversible;
+	__u32	mtu;
+	__be16	pkey;
+	__u8	hop_limit;
+	__u8	traffic_class;
+	__u8	numb_path;
+	__u8	sl;
+	__u8	mtu_selector;
+	__u8	rate_selector;
+	__u8	rate;
+	__u8	packet_life_time_selector;
+	__u8	packet_life_time;
+	__u8	preference;
+};
+
+#endif /* IB_USER_SA_H */
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
new file mode 100644
index 000000000000..81aba3a73aa3
--- /dev/null
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -0,0 +1,734 @@
+/*
+ * Copyright (c) 2005 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005, 2006 Cisco Systems.  All rights reserved.
+ * Copyright (c) 2005 PathScale, Inc.  All rights reserved.
+ * Copyright (c) 2006 Mellanox Technologies.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef IB_USER_VERBS_H
+#define IB_USER_VERBS_H
+
+#include <linux/types.h>
+
+/*
+ * Increment this value if any changes that break userspace ABI
+ * compatibility are made.
+ */
+#define IB_USER_VERBS_ABI_VERSION	6
+
+enum {
+	IB_USER_VERBS_CMD_GET_CONTEXT,
+	IB_USER_VERBS_CMD_QUERY_DEVICE,
+	IB_USER_VERBS_CMD_QUERY_PORT,
+	IB_USER_VERBS_CMD_ALLOC_PD,
+	IB_USER_VERBS_CMD_DEALLOC_PD,
+	IB_USER_VERBS_CMD_CREATE_AH,
+	IB_USER_VERBS_CMD_MODIFY_AH,
+	IB_USER_VERBS_CMD_QUERY_AH,
+	IB_USER_VERBS_CMD_DESTROY_AH,
+	IB_USER_VERBS_CMD_REG_MR,
+	IB_USER_VERBS_CMD_REG_SMR,
+	IB_USER_VERBS_CMD_REREG_MR,
+	IB_USER_VERBS_CMD_QUERY_MR,
+	IB_USER_VERBS_CMD_DEREG_MR,
+	IB_USER_VERBS_CMD_ALLOC_MW,
+	IB_USER_VERBS_CMD_BIND_MW,
+	IB_USER_VERBS_CMD_DEALLOC_MW,
+	IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL,
+	IB_USER_VERBS_CMD_CREATE_CQ,
+	IB_USER_VERBS_CMD_RESIZE_CQ,
+	IB_USER_VERBS_CMD_DESTROY_CQ,
+	IB_USER_VERBS_CMD_POLL_CQ,
+	IB_USER_VERBS_CMD_PEEK_CQ,
+	IB_USER_VERBS_CMD_REQ_NOTIFY_CQ,
+	IB_USER_VERBS_CMD_CREATE_QP,
+	IB_USER_VERBS_CMD_QUERY_QP,
+	IB_USER_VERBS_CMD_MODIFY_QP,
+	IB_USER_VERBS_CMD_DESTROY_QP,
+	IB_USER_VERBS_CMD_POST_SEND,
+	IB_USER_VERBS_CMD_POST_RECV,
+	IB_USER_VERBS_CMD_ATTACH_MCAST,
+	IB_USER_VERBS_CMD_DETACH_MCAST,
+	IB_USER_VERBS_CMD_CREATE_SRQ,
+	IB_USER_VERBS_CMD_MODIFY_SRQ,
+	IB_USER_VERBS_CMD_QUERY_SRQ,
+	IB_USER_VERBS_CMD_DESTROY_SRQ,
+	IB_USER_VERBS_CMD_POST_SRQ_RECV,
+	IB_USER_VERBS_CMD_OPEN_XRCD,
+	IB_USER_VERBS_CMD_CLOSE_XRCD,
+	IB_USER_VERBS_CMD_CREATE_XSRQ,
+	IB_USER_VERBS_CMD_OPEN_QP
+};
+
+/*
+ * Make sure that all structs defined in this file remain laid out so
+ * that they pack the same way on 32-bit and 64-bit architectures (to
+ * avoid incompatibility between 32-bit userspace and 64-bit kernels).
+ * Specifically:
+ *  - Do not use pointer types -- pass pointers in __u64 instead.
+ *  - Make sure that any structure larger than 4 bytes is padded to a
+ *    multiple of 8 bytes.  Otherwise the structure size will be
+ *    different between 32-bit and 64-bit architectures.
+ */
+
+struct ib_uverbs_async_event_desc {
+	__u64 element;
+	__u32 event_type;	/* enum ib_event_type */
+	__u32 reserved;
+};
+
+struct ib_uverbs_comp_event_desc {
+	__u64 cq_handle;
+};
+
+/*
+ * All commands from userspace should start with a __u32 command field
+ * followed by __u16 in_words and out_words fields (which give the
+ * length of the command block and response buffer if any in 32-bit
+ * words).  The kernel driver will read these fields first and read
+ * the rest of the command struct based on these value.
+ */
+
+struct ib_uverbs_cmd_hdr {
+	__u32 command;
+	__u16 in_words;
+	__u16 out_words;
+};
+
+struct ib_uverbs_get_context {
+	__u64 response;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_get_context_resp {
+	__u32 async_fd;
+	__u32 num_comp_vectors;
+};
+
+struct ib_uverbs_query_device {
+	__u64 response;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_query_device_resp {
+	__u64 fw_ver;
+	__be64 node_guid;
+	__be64 sys_image_guid;
+	__u64 max_mr_size;
+	__u64 page_size_cap;
+	__u32 vendor_id;
+	__u32 vendor_part_id;
+	__u32 hw_ver;
+	__u32 max_qp;
+	__u32 max_qp_wr;
+	__u32 device_cap_flags;
+	__u32 max_sge;
+	__u32 max_sge_rd;
+	__u32 max_cq;
+	__u32 max_cqe;
+	__u32 max_mr;
+	__u32 max_pd;
+	__u32 max_qp_rd_atom;
+	__u32 max_ee_rd_atom;
+	__u32 max_res_rd_atom;
+	__u32 max_qp_init_rd_atom;
+	__u32 max_ee_init_rd_atom;
+	__u32 atomic_cap;
+	__u32 max_ee;
+	__u32 max_rdd;
+	__u32 max_mw;
+	__u32 max_raw_ipv6_qp;
+	__u32 max_raw_ethy_qp;
+	__u32 max_mcast_grp;
+	__u32 max_mcast_qp_attach;
+	__u32 max_total_mcast_qp_attach;
+	__u32 max_ah;
+	__u32 max_fmr;
+	__u32 max_map_per_fmr;
+	__u32 max_srq;
+	__u32 max_srq_wr;
+	__u32 max_srq_sge;
+	__u16 max_pkeys;
+	__u8  local_ca_ack_delay;
+	__u8  phys_port_cnt;
+	__u8  reserved[4];
+};
+
+struct ib_uverbs_query_port {
+	__u64 response;
+	__u8  port_num;
+	__u8  reserved[7];
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_query_port_resp {
+	__u32 port_cap_flags;
+	__u32 max_msg_sz;
+	__u32 bad_pkey_cntr;
+	__u32 qkey_viol_cntr;
+	__u32 gid_tbl_len;
+	__u16 pkey_tbl_len;
+	__u16 lid;
+	__u16 sm_lid;
+	__u8  state;
+	__u8  max_mtu;
+	__u8  active_mtu;
+	__u8  lmc;
+	__u8  max_vl_num;
+	__u8  sm_sl;
+	__u8  subnet_timeout;
+	__u8  init_type_reply;
+	__u8  active_width;
+	__u8  active_speed;
+	__u8  phys_state;
+	__u8  link_layer;
+	__u8  reserved[2];
+};
+
+struct ib_uverbs_alloc_pd {
+	__u64 response;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_alloc_pd_resp {
+	__u32 pd_handle;
+};
+
+struct ib_uverbs_dealloc_pd {
+	__u32 pd_handle;
+};
+
+struct ib_uverbs_open_xrcd {
+	__u64 response;
+	__u32 fd;
+	__u32 oflags;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_open_xrcd_resp {
+	__u32 xrcd_handle;
+};
+
+struct ib_uverbs_close_xrcd {
+	__u32 xrcd_handle;
+};
+
+struct ib_uverbs_reg_mr {
+	__u64 response;
+	__u64 start;
+	__u64 length;
+	__u64 hca_va;
+	__u32 pd_handle;
+	__u32 access_flags;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_reg_mr_resp {
+	__u32 mr_handle;
+	__u32 lkey;
+	__u32 rkey;
+};
+
+struct ib_uverbs_dereg_mr {
+	__u32 mr_handle;
+};
+
+struct ib_uverbs_create_comp_channel {
+	__u64 response;
+};
+
+struct ib_uverbs_create_comp_channel_resp {
+	__u32 fd;
+};
+
+struct ib_uverbs_create_cq {
+	__u64 response;
+	__u64 user_handle;
+	__u32 cqe;
+	__u32 comp_vector;
+	__s32 comp_channel;
+	__u32 reserved;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_create_cq_resp {
+	__u32 cq_handle;
+	__u32 cqe;
+};
+
+struct ib_uverbs_resize_cq {
+	__u64 response;
+	__u32 cq_handle;
+	__u32 cqe;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_resize_cq_resp {
+	__u32 cqe;
+	__u32 reserved;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_poll_cq {
+	__u64 response;
+	__u32 cq_handle;
+	__u32 ne;
+};
+
+struct ib_uverbs_wc {
+	__u64 wr_id;
+	__u32 status;
+	__u32 opcode;
+	__u32 vendor_err;
+	__u32 byte_len;
+	union {
+		__u32 imm_data;
+		__u32 invalidate_rkey;
+	} ex;
+	__u32 qp_num;
+	__u32 src_qp;
+	__u32 wc_flags;
+	__u16 pkey_index;
+	__u16 slid;
+	__u8 sl;
+	__u8 dlid_path_bits;
+	__u8 port_num;
+	__u8 reserved;
+};
+
+struct ib_uverbs_poll_cq_resp {
+	__u32 count;
+	__u32 reserved;
+	struct ib_uverbs_wc wc[0];
+};
+
+struct ib_uverbs_req_notify_cq {
+	__u32 cq_handle;
+	__u32 solicited_only;
+};
+
+struct ib_uverbs_destroy_cq {
+	__u64 response;
+	__u32 cq_handle;
+	__u32 reserved;
+};
+
+struct ib_uverbs_destroy_cq_resp {
+	__u32 comp_events_reported;
+	__u32 async_events_reported;
+};
+
+struct ib_uverbs_global_route {
+	__u8  dgid[16];
+	__u32 flow_label;
+	__u8  sgid_index;
+	__u8  hop_limit;
+	__u8  traffic_class;
+	__u8  reserved;
+};
+
+struct ib_uverbs_ah_attr {
+	struct ib_uverbs_global_route grh;
+	__u16 dlid;
+	__u8  sl;
+	__u8  src_path_bits;
+	__u8  static_rate;
+	__u8  is_global;
+	__u8  port_num;
+	__u8  reserved;
+};
+
+struct ib_uverbs_qp_attr {
+	__u32	qp_attr_mask;
+	__u32	qp_state;
+	__u32	cur_qp_state;
+	__u32	path_mtu;
+	__u32	path_mig_state;
+	__u32	qkey;
+	__u32	rq_psn;
+	__u32	sq_psn;
+	__u32	dest_qp_num;
+	__u32	qp_access_flags;
+
+	struct ib_uverbs_ah_attr ah_attr;
+	struct ib_uverbs_ah_attr alt_ah_attr;
+
+	/* ib_qp_cap */
+	__u32	max_send_wr;
+	__u32	max_recv_wr;
+	__u32	max_send_sge;
+	__u32	max_recv_sge;
+	__u32	max_inline_data;
+
+	__u16	pkey_index;
+	__u16	alt_pkey_index;
+	__u8	en_sqd_async_notify;
+	__u8	sq_draining;
+	__u8	max_rd_atomic;
+	__u8	max_dest_rd_atomic;
+	__u8	min_rnr_timer;
+	__u8	port_num;
+	__u8	timeout;
+	__u8	retry_cnt;
+	__u8	rnr_retry;
+	__u8	alt_port_num;
+	__u8	alt_timeout;
+	__u8	reserved[5];
+};
+
+struct ib_uverbs_create_qp {
+	__u64 response;
+	__u64 user_handle;
+	__u32 pd_handle;
+	__u32 send_cq_handle;
+	__u32 recv_cq_handle;
+	__u32 srq_handle;
+	__u32 max_send_wr;
+	__u32 max_recv_wr;
+	__u32 max_send_sge;
+	__u32 max_recv_sge;
+	__u32 max_inline_data;
+	__u8  sq_sig_all;
+	__u8  qp_type;
+	__u8  is_srq;
+	__u8  reserved;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_open_qp {
+	__u64 response;
+	__u64 user_handle;
+	__u32 pd_handle;
+	__u32 qpn;
+	__u8  qp_type;
+	__u8  reserved[7];
+	__u64 driver_data[0];
+};
+
+/* also used for open response */
+struct ib_uverbs_create_qp_resp {
+	__u32 qp_handle;
+	__u32 qpn;
+	__u32 max_send_wr;
+	__u32 max_recv_wr;
+	__u32 max_send_sge;
+	__u32 max_recv_sge;
+	__u32 max_inline_data;
+	__u32 reserved;
+};
+
+/*
+ * This struct needs to remain a multiple of 8 bytes to keep the
+ * alignment of the modify QP parameters.
+ */
+struct ib_uverbs_qp_dest {
+	__u8  dgid[16];
+	__u32 flow_label;
+	__u16 dlid;
+	__u16 reserved;
+	__u8  sgid_index;
+	__u8  hop_limit;
+	__u8  traffic_class;
+	__u8  sl;
+	__u8  src_path_bits;
+	__u8  static_rate;
+	__u8  is_global;
+	__u8  port_num;
+};
+
+struct ib_uverbs_query_qp {
+	__u64 response;
+	__u32 qp_handle;
+	__u32 attr_mask;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_query_qp_resp {
+	struct ib_uverbs_qp_dest dest;
+	struct ib_uverbs_qp_dest alt_dest;
+	__u32 max_send_wr;
+	__u32 max_recv_wr;
+	__u32 max_send_sge;
+	__u32 max_recv_sge;
+	__u32 max_inline_data;
+	__u32 qkey;
+	__u32 rq_psn;
+	__u32 sq_psn;
+	__u32 dest_qp_num;
+	__u32 qp_access_flags;
+	__u16 pkey_index;
+	__u16 alt_pkey_index;
+	__u8  qp_state;
+	__u8  cur_qp_state;
+	__u8  path_mtu;
+	__u8  path_mig_state;
+	__u8  sq_draining;
+	__u8  max_rd_atomic;
+	__u8  max_dest_rd_atomic;
+	__u8  min_rnr_timer;
+	__u8  port_num;
+	__u8  timeout;
+	__u8  retry_cnt;
+	__u8  rnr_retry;
+	__u8  alt_port_num;
+	__u8  alt_timeout;
+	__u8  sq_sig_all;
+	__u8  reserved[5];
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_modify_qp {
+	struct ib_uverbs_qp_dest dest;
+	struct ib_uverbs_qp_dest alt_dest;
+	__u32 qp_handle;
+	__u32 attr_mask;
+	__u32 qkey;
+	__u32 rq_psn;
+	__u32 sq_psn;
+	__u32 dest_qp_num;
+	__u32 qp_access_flags;
+	__u16 pkey_index;
+	__u16 alt_pkey_index;
+	__u8  qp_state;
+	__u8  cur_qp_state;
+	__u8  path_mtu;
+	__u8  path_mig_state;
+	__u8  en_sqd_async_notify;
+	__u8  max_rd_atomic;
+	__u8  max_dest_rd_atomic;
+	__u8  min_rnr_timer;
+	__u8  port_num;
+	__u8  timeout;
+	__u8  retry_cnt;
+	__u8  rnr_retry;
+	__u8  alt_port_num;
+	__u8  alt_timeout;
+	__u8  reserved[2];
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_modify_qp_resp {
+};
+
+struct ib_uverbs_destroy_qp {
+	__u64 response;
+	__u32 qp_handle;
+	__u32 reserved;
+};
+
+struct ib_uverbs_destroy_qp_resp {
+	__u32 events_reported;
+};
+
+/*
+ * The ib_uverbs_sge structure isn't used anywhere, since we assume
+ * the ib_sge structure is packed the same way on 32-bit and 64-bit
+ * architectures in both kernel and user space.  It's just here to
+ * document the ABI.
+ */
+struct ib_uverbs_sge {
+	__u64 addr;
+	__u32 length;
+	__u32 lkey;
+};
+
+struct ib_uverbs_send_wr {
+	__u64 wr_id;
+	__u32 num_sge;
+	__u32 opcode;
+	__u32 send_flags;
+	union {
+		__u32 imm_data;
+		__u32 invalidate_rkey;
+	} ex;
+	union {
+		struct {
+			__u64 remote_addr;
+			__u32 rkey;
+			__u32 reserved;
+		} rdma;
+		struct {
+			__u64 remote_addr;
+			__u64 compare_add;
+			__u64 swap;
+			__u32 rkey;
+			__u32 reserved;
+		} atomic;
+		struct {
+			__u32 ah;
+			__u32 remote_qpn;
+			__u32 remote_qkey;
+			__u32 reserved;
+		} ud;
+	} wr;
+};
+
+struct ib_uverbs_post_send {
+	__u64 response;
+	__u32 qp_handle;
+	__u32 wr_count;
+	__u32 sge_count;
+	__u32 wqe_size;
+	struct ib_uverbs_send_wr send_wr[0];
+};
+
+struct ib_uverbs_post_send_resp {
+	__u32 bad_wr;
+};
+
+struct ib_uverbs_recv_wr {
+	__u64 wr_id;
+	__u32 num_sge;
+	__u32 reserved;
+};
+
+struct ib_uverbs_post_recv {
+	__u64 response;
+	__u32 qp_handle;
+	__u32 wr_count;
+	__u32 sge_count;
+	__u32 wqe_size;
+	struct ib_uverbs_recv_wr recv_wr[0];
+};
+
+struct ib_uverbs_post_recv_resp {
+	__u32 bad_wr;
+};
+
+struct ib_uverbs_post_srq_recv {
+	__u64 response;
+	__u32 srq_handle;
+	__u32 wr_count;
+	__u32 sge_count;
+	__u32 wqe_size;
+	struct ib_uverbs_recv_wr recv[0];
+};
+
+struct ib_uverbs_post_srq_recv_resp {
+	__u32 bad_wr;
+};
+
+struct ib_uverbs_create_ah {
+	__u64 response;
+	__u64 user_handle;
+	__u32 pd_handle;
+	__u32 reserved;
+	struct ib_uverbs_ah_attr attr;
+};
+
+struct ib_uverbs_create_ah_resp {
+	__u32 ah_handle;
+};
+
+struct ib_uverbs_destroy_ah {
+	__u32 ah_handle;
+};
+
+struct ib_uverbs_attach_mcast {
+	__u8  gid[16];
+	__u32 qp_handle;
+	__u16 mlid;
+	__u16 reserved;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_detach_mcast {
+	__u8  gid[16];
+	__u32 qp_handle;
+	__u16 mlid;
+	__u16 reserved;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_create_srq {
+	__u64 response;
+	__u64 user_handle;
+	__u32 pd_handle;
+	__u32 max_wr;
+	__u32 max_sge;
+	__u32 srq_limit;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_create_xsrq {
+	__u64 response;
+	__u64 user_handle;
+	__u32 srq_type;
+	__u32 pd_handle;
+	__u32 max_wr;
+	__u32 max_sge;
+	__u32 srq_limit;
+	__u32 reserved;
+	__u32 xrcd_handle;
+	__u32 cq_handle;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_create_srq_resp {
+	__u32 srq_handle;
+	__u32 max_wr;
+	__u32 max_sge;
+	__u32 srqn;
+};
+
+struct ib_uverbs_modify_srq {
+	__u32 srq_handle;
+	__u32 attr_mask;
+	__u32 max_wr;
+	__u32 srq_limit;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_query_srq {
+	__u64 response;
+	__u32 srq_handle;
+	__u32 reserved;
+	__u64 driver_data[0];
+};
+
+struct ib_uverbs_query_srq_resp {
+	__u32 max_wr;
+	__u32 max_sge;
+	__u32 srq_limit;
+	__u32 reserved;
+};
+
+struct ib_uverbs_destroy_srq {
+	__u64 response;
+	__u32 srq_handle;
+	__u32 reserved;
+};
+
+struct ib_uverbs_destroy_srq_resp {
+	__u32 events_reported;
+};
+
+#endif /* IB_USER_VERBS_H */
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
new file mode 100644
index 000000000000..8297285b6288
--- /dev/null
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -0,0 +1,37 @@
+#ifndef _UAPI_RDMA_NETLINK_H
+#define _UAPI_RDMA_NETLINK_H
+
+#include <linux/types.h>
+
+enum {
+	RDMA_NL_RDMA_CM = 1
+};
+
+#define RDMA_NL_GET_CLIENT(type) ((type & (((1 << 6) - 1) << 10)) >> 10)
+#define RDMA_NL_GET_OP(type) (type & ((1 << 10) - 1))
+#define RDMA_NL_GET_TYPE(client, op) ((client << 10) + op)
+
+enum {
+	RDMA_NL_RDMA_CM_ID_STATS = 0,
+	RDMA_NL_RDMA_CM_NUM_OPS
+};
+
+enum {
+	RDMA_NL_RDMA_CM_ATTR_SRC_ADDR = 1,
+	RDMA_NL_RDMA_CM_ATTR_DST_ADDR,
+	RDMA_NL_RDMA_CM_NUM_ATTR,
+};
+
+struct rdma_cm_id_stats {
+	__u32	qp_num;
+	__u32	bound_dev_if;
+	__u32	port_space;
+	__s32	pid;
+	__u8	cm_state;
+	__u8	node_type;
+	__u8	port_num;
+	__u8	qp_type;
+};
+
+
+#endif /* _UAPI_RDMA_NETLINK_H */
diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h
new file mode 100644
index 000000000000..1ee9239ff8c2
--- /dev/null
+++ b/include/uapi/rdma/rdma_user_cm.h
@@ -0,0 +1,249 @@
+/*
+ * Copyright (c) 2005-2006 Intel Corporation.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef RDMA_USER_CM_H
+#define RDMA_USER_CM_H
+
+#include <linux/types.h>
+#include <linux/in6.h>
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_user_sa.h>
+
+#define RDMA_USER_CM_ABI_VERSION	4
+
+#define RDMA_MAX_PRIVATE_DATA		256
+
+enum {
+	RDMA_USER_CM_CMD_CREATE_ID,
+	RDMA_USER_CM_CMD_DESTROY_ID,
+	RDMA_USER_CM_CMD_BIND_ADDR,
+	RDMA_USER_CM_CMD_RESOLVE_ADDR,
+	RDMA_USER_CM_CMD_RESOLVE_ROUTE,
+	RDMA_USER_CM_CMD_QUERY_ROUTE,
+	RDMA_USER_CM_CMD_CONNECT,
+	RDMA_USER_CM_CMD_LISTEN,
+	RDMA_USER_CM_CMD_ACCEPT,
+	RDMA_USER_CM_CMD_REJECT,
+	RDMA_USER_CM_CMD_DISCONNECT,
+	RDMA_USER_CM_CMD_INIT_QP_ATTR,
+	RDMA_USER_CM_CMD_GET_EVENT,
+	RDMA_USER_CM_CMD_GET_OPTION,
+	RDMA_USER_CM_CMD_SET_OPTION,
+	RDMA_USER_CM_CMD_NOTIFY,
+	RDMA_USER_CM_CMD_JOIN_MCAST,
+	RDMA_USER_CM_CMD_LEAVE_MCAST,
+	RDMA_USER_CM_CMD_MIGRATE_ID
+};
+
+/*
+ * command ABI structures.
+ */
+struct rdma_ucm_cmd_hdr {
+	__u32 cmd;
+	__u16 in;
+	__u16 out;
+};
+
+struct rdma_ucm_create_id {
+	__u64 uid;
+	__u64 response;
+	__u16 ps;
+	__u8  qp_type;
+	__u8  reserved[5];
+};
+
+struct rdma_ucm_create_id_resp {
+	__u32 id;
+};
+
+struct rdma_ucm_destroy_id {
+	__u64 response;
+	__u32 id;
+	__u32 reserved;
+};
+
+struct rdma_ucm_destroy_id_resp {
+	__u32 events_reported;
+};
+
+struct rdma_ucm_bind_addr {
+	__u64 response;
+	struct sockaddr_in6 addr;
+	__u32 id;
+};
+
+struct rdma_ucm_resolve_addr {
+	struct sockaddr_in6 src_addr;
+	struct sockaddr_in6 dst_addr;
+	__u32 id;
+	__u32 timeout_ms;
+};
+
+struct rdma_ucm_resolve_route {
+	__u32 id;
+	__u32 timeout_ms;
+};
+
+struct rdma_ucm_query_route {
+	__u64 response;
+	__u32 id;
+	__u32 reserved;
+};
+
+struct rdma_ucm_query_route_resp {
+	__u64 node_guid;
+	struct ib_user_path_rec ib_route[2];
+	struct sockaddr_in6 src_addr;
+	struct sockaddr_in6 dst_addr;
+	__u32 num_paths;
+	__u8 port_num;
+	__u8 reserved[3];
+};
+
+struct rdma_ucm_conn_param {
+	__u32 qp_num;
+	__u32 reserved;
+	__u8  private_data[RDMA_MAX_PRIVATE_DATA];
+	__u8  private_data_len;
+	__u8  srq;
+	__u8  responder_resources;
+	__u8  initiator_depth;
+	__u8  flow_control;
+	__u8  retry_count;
+	__u8  rnr_retry_count;
+	__u8  valid;
+};
+
+struct rdma_ucm_ud_param {
+	__u32 qp_num;
+	__u32 qkey;
+	struct ib_uverbs_ah_attr ah_attr;
+	__u8  private_data[RDMA_MAX_PRIVATE_DATA];
+	__u8  private_data_len;
+	__u8  reserved[7];
+};
+
+struct rdma_ucm_connect {
+	struct rdma_ucm_conn_param conn_param;
+	__u32 id;
+	__u32 reserved;
+};
+
+struct rdma_ucm_listen {
+	__u32 id;
+	__u32 backlog;
+};
+
+struct rdma_ucm_accept {
+	__u64 uid;
+	struct rdma_ucm_conn_param conn_param;
+	__u32 id;
+	__u32 reserved;
+};
+
+struct rdma_ucm_reject {
+	__u32 id;
+	__u8  private_data_len;
+	__u8  reserved[3];
+	__u8  private_data[RDMA_MAX_PRIVATE_DATA];
+};
+
+struct rdma_ucm_disconnect {
+	__u32 id;
+};
+
+struct rdma_ucm_init_qp_attr {
+	__u64 response;
+	__u32 id;
+	__u32 qp_state;
+};
+
+struct rdma_ucm_notify {
+	__u32 id;
+	__u32 event;
+};
+
+struct rdma_ucm_join_mcast {
+	__u64 response;		/* rdma_ucm_create_id_resp */
+	__u64 uid;
+	struct sockaddr_in6 addr;
+	__u32 id;
+};
+
+struct rdma_ucm_get_event {
+	__u64 response;
+};
+
+struct rdma_ucm_event_resp {
+	__u64 uid;
+	__u32 id;
+	__u32 event;
+	__u32 status;
+	union {
+		struct rdma_ucm_conn_param conn;
+		struct rdma_ucm_ud_param   ud;
+	} param;
+};
+
+/* Option levels */
+enum {
+	RDMA_OPTION_ID		= 0,
+	RDMA_OPTION_IB		= 1
+};
+
+/* Option details */
+enum {
+	RDMA_OPTION_ID_TOS	 = 0,
+	RDMA_OPTION_ID_REUSEADDR = 1,
+	RDMA_OPTION_ID_AFONLY	 = 2,
+	RDMA_OPTION_IB_PATH	 = 1
+};
+
+struct rdma_ucm_set_option {
+	__u64 optval;
+	__u32 id;
+	__u32 level;
+	__u32 optname;
+	__u32 optlen;
+};
+
+struct rdma_ucm_migrate_id {
+	__u64 response;
+	__u32 id;
+	__u32 fd;
+};
+
+struct rdma_ucm_migrate_resp {
+	__u32 events_reported;
+};
+
+#endif /* RDMA_USER_CM_H */
-- 
cgit v1.2.3-55-g7522


From b6f50b49b9712f49c377e9e3587906e27bea39d0 Mon Sep 17 00:00:00 2001
From: Anatolij Gustschin
Date: Thu, 27 Sep 2012 19:05:27 -0300
Subject: [media] mt9v022: set y_skip_top field to zero as default

Set "y_skip_top" to zero and revise comment as I do not see this line
corruption on two different mt9v022 setups. The first read-out line
is perfectly fine. Add mt9v022 platform data configuring y_skip_top
for platforms that have issues with the first read-out line. Set
y_skip_top to 1 for pcm990 board.

Signed-off-by: Anatolij Gustschin <agust@denx.de>
Acked-by: Eric Miao <eric.y.miao@gmail.com>
Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 arch/arm/mach-pxa/pcm990-baseboard.c   |  6 ++++++
 drivers/media/i2c/soc_camera/mt9v022.c |  8 +++++---
 include/media/mt9v022.h                | 16 ++++++++++++++++
 3 files changed, 27 insertions(+), 3 deletions(-)
 create mode 100644 include/media/mt9v022.h

(limited to 'include')

diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c
index 113c57a03565..fb7f1d1627dc 100644
--- a/arch/arm/mach-pxa/pcm990-baseboard.c
+++ b/arch/arm/mach-pxa/pcm990-baseboard.c
@@ -26,6 +26,7 @@
 #include <linux/i2c/pxa-i2c.h>
 #include <linux/pwm_backlight.h>
 
+#include <media/mt9v022.h>
 #include <media/soc_camera.h>
 
 #include <linux/platform_data/camera-pxa.h>
@@ -468,6 +469,10 @@ static struct i2c_board_info __initdata pcm990_i2c_devices[] = {
 	},
 };
 
+static struct mt9v022_platform_data mt9v022_pdata = {
+	.y_skip_top = 1,
+};
+
 static struct i2c_board_info pcm990_camera_i2c[] = {
 	{
 		I2C_BOARD_INFO("mt9v022", 0x48),
@@ -480,6 +485,7 @@ static struct soc_camera_link iclink[] = {
 	{
 		.bus_id			= 0, /* Must match with the camera ID */
 		.board_info		= &pcm990_camera_i2c[0],
+		.priv			= &mt9v022_pdata,
 		.i2c_adapter_id		= 0,
 		.query_bus_param	= pcm990_camera_query_bus_param,
 		.set_bus_param		= pcm990_camera_set_bus_param,
diff --git a/drivers/media/i2c/soc_camera/mt9v022.c b/drivers/media/i2c/soc_camera/mt9v022.c
index 5bc5a9286fd5..84d204f82cb2 100644
--- a/drivers/media/i2c/soc_camera/mt9v022.c
+++ b/drivers/media/i2c/soc_camera/mt9v022.c
@@ -15,6 +15,7 @@
 #include <linux/log2.h>
 #include <linux/module.h>
 
+#include <media/mt9v022.h>
 #include <media/soc_camera.h>
 #include <media/soc_mediabus.h>
 #include <media/v4l2-subdev.h>
@@ -869,6 +870,7 @@ static int mt9v022_probe(struct i2c_client *client,
 	struct mt9v022 *mt9v022;
 	struct soc_camera_link *icl = soc_camera_i2c_to_link(client);
 	struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
+	struct mt9v022_platform_data *pdata = icl->priv;
 	int ret;
 
 	if (!icl) {
@@ -932,10 +934,10 @@ static int mt9v022_probe(struct i2c_client *client,
 	mt9v022->chip_control = MT9V022_CHIP_CONTROL_DEFAULT;
 
 	/*
-	 * MT9V022 _really_ corrupts the first read out line.
-	 * TODO: verify on i.MX31
+	 * On some platforms the first read out line is corrupted.
+	 * Workaround it by skipping if indicated by platform data.
 	 */
-	mt9v022->y_skip_top	= 1;
+	mt9v022->y_skip_top	= pdata ? pdata->y_skip_top : 0;
 	mt9v022->rect.left	= MT9V022_COLUMN_SKIP;
 	mt9v022->rect.top	= MT9V022_ROW_SKIP;
 	mt9v022->rect.width	= MT9V022_MAX_WIDTH;
diff --git a/include/media/mt9v022.h b/include/media/mt9v022.h
new file mode 100644
index 000000000000..40561801321a
--- /dev/null
+++ b/include/media/mt9v022.h
@@ -0,0 +1,16 @@
+/*
+ * mt9v022 sensor
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __MT9V022_H__
+#define __MT9V022_H__
+
+struct mt9v022_platform_data {
+	unsigned short y_skip_top;	/* Lines to skip at the top */
+};
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 88d642fa2ce87c125b84cfcf23c371618d8b08b4 Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Thu, 22 Nov 2012 07:32:47 -0800
Subject: netprio_cgroup: use cgroup->id instead of
 cgroup_netprio_state->prioidx

With priomap expansion no longer depending on knowing max id
allocated, netprio_cgroup can use cgroup->id insted of cs->prioidx.
Drop prioidx alloc/free logic and convert all uses to cgroup->id.

* In cgrp_css_alloc(), parent->id test is moved above @cs allocation
  to simplify error path.

* In cgrp_css_free(), @cs assignment is made initialization.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Tested-and-Acked-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Acked-by: David S. Miller <davem@davemloft.net>
---
 include/net/netprio_cgroup.h | 11 +++-----
 net/core/netprio_cgroup.c    | 65 ++++++++------------------------------------
 2 files changed, 15 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h
index 2760f4f4ae9b..1d04b6f0fbd4 100644
--- a/include/net/netprio_cgroup.h
+++ b/include/net/netprio_cgroup.h
@@ -27,7 +27,6 @@ struct netprio_map {
 
 struct cgroup_netprio_state {
 	struct cgroup_subsys_state css;
-	u32 prioidx;
 };
 
 extern void sock_update_netprioidx(struct sock *sk, struct task_struct *task);
@@ -36,13 +35,12 @@ extern void sock_update_netprioidx(struct sock *sk, struct task_struct *task);
 
 static inline u32 task_netprioidx(struct task_struct *p)
 {
-	struct cgroup_netprio_state *state;
+	struct cgroup_subsys_state *css;
 	u32 idx;
 
 	rcu_read_lock();
-	state = container_of(task_subsys_state(p, net_prio_subsys_id),
-			     struct cgroup_netprio_state, css);
-	idx = state->prioidx;
+	css = task_subsys_state(p, net_prio_subsys_id);
+	idx = css->cgroup->id;
 	rcu_read_unlock();
 	return idx;
 }
@@ -57,8 +55,7 @@ static inline u32 task_netprioidx(struct task_struct *p)
 	rcu_read_lock();
 	css = task_subsys_state(p, net_prio_subsys_id);
 	if (css)
-		idx = container_of(css,
-				   struct cgroup_netprio_state, css)->prioidx;
+		idx = css->cgroup->id;
 	rcu_read_unlock();
 	return idx;
 }
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 569d83da53d0..9409cdf9f268 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -28,10 +28,6 @@
 #include <linux/fdtable.h>
 
 #define PRIOMAP_MIN_SZ		128
-#define PRIOIDX_SZ 128
-
-static unsigned long prioidx_map[PRIOIDX_SZ];
-static DEFINE_SPINLOCK(prioidx_map_lock);
 
 static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp)
 {
@@ -39,32 +35,6 @@ static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgr
 			    struct cgroup_netprio_state, css);
 }
 
-static int get_prioidx(u32 *prio)
-{
-	unsigned long flags;
-	u32 prioidx;
-
-	spin_lock_irqsave(&prioidx_map_lock, flags);
-	prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ);
-	if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) {
-		spin_unlock_irqrestore(&prioidx_map_lock, flags);
-		return -ENOSPC;
-	}
-	set_bit(prioidx, prioidx_map);
-	spin_unlock_irqrestore(&prioidx_map_lock, flags);
-	*prio = prioidx;
-	return 0;
-}
-
-static void put_prioidx(u32 idx)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&prioidx_map_lock, flags);
-	clear_bit(idx, prioidx_map);
-	spin_unlock_irqrestore(&prioidx_map_lock, flags);
-}
-
 /*
  * Extend @dev->priomap so that it's large enough to accomodate
  * @target_idx.  @dev->priomap.priomap_len > @target_idx after successful
@@ -120,62 +90,50 @@ static int extend_netdev_table(struct net_device *dev, u32 target_idx)
 static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
 {
 	struct cgroup_netprio_state *cs;
-	int ret = -EINVAL;
+
+	if (cgrp->parent && cgrp->parent->id)
+		return ERR_PTR(-EINVAL);
 
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
 
-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
-		goto out;
-
-	ret = get_prioidx(&cs->prioidx);
-	if (ret < 0) {
-		pr_warn("No space in priority index array\n");
-		goto out;
-	}
-
 	return &cs->css;
-out:
-	kfree(cs);
-	return ERR_PTR(ret);
 }
 
 static void cgrp_css_free(struct cgroup *cgrp)
 {
-	struct cgroup_netprio_state *cs;
+	struct cgroup_netprio_state *cs = cgrp_netprio_state(cgrp);
 	struct net_device *dev;
 	struct netprio_map *map;
 
-	cs = cgrp_netprio_state(cgrp);
 	rtnl_lock();
 	for_each_netdev(&init_net, dev) {
 		map = rtnl_dereference(dev->priomap);
-		if (map && cs->prioidx < map->priomap_len)
-			map->priomap[cs->prioidx] = 0;
+		if (map && cgrp->id < map->priomap_len)
+			map->priomap[cgrp->id] = 0;
 	}
 	rtnl_unlock();
-	put_prioidx(cs->prioidx);
 	kfree(cs);
 }
 
 static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft)
 {
-	return (u64)cgrp_netprio_state(cgrp)->prioidx;
+	return cgrp->id;
 }
 
 static int read_priomap(struct cgroup *cont, struct cftype *cft,
 			struct cgroup_map_cb *cb)
 {
 	struct net_device *dev;
-	u32 prioidx = cgrp_netprio_state(cont)->prioidx;
+	u32 id = cont->id;
 	u32 priority;
 	struct netprio_map *map;
 
 	rcu_read_lock();
 	for_each_netdev_rcu(&init_net, dev) {
 		map = rcu_dereference(dev->priomap);
-		priority = (map && prioidx < map->priomap_len) ? map->priomap[prioidx] : 0;
+		priority = (map && id < map->priomap_len) ? map->priomap[id] : 0;
 		cb->fill(cb, dev->name, priority);
 	}
 	rcu_read_unlock();
@@ -185,7 +143,6 @@ static int read_priomap(struct cgroup *cont, struct cftype *cft,
 static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
 			 const char *buffer)
 {
-	u32 prioidx = cgrp_netprio_state(cgrp)->prioidx;
 	char devname[IFNAMSIZ + 1];
 	struct net_device *dev;
 	struct netprio_map *map;
@@ -201,13 +158,13 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
 
 	rtnl_lock();
 
-	ret = extend_netdev_table(dev, prioidx);
+	ret = extend_netdev_table(dev, cgrp->id);
 	if (ret)
 		goto out_unlock;
 
 	map = rtnl_dereference(dev->priomap);
 	if (map)
-		map->priomap[prioidx] = prio;
+		map->priomap[cgrp->id] = prio;
 out_unlock:
 	rtnl_unlock();
 	dev_put(dev);
-- 
cgit v1.2.3-55-g7522


From 0d144de9af28f23d28e4cdf28a08e25e9ad3b41c Mon Sep 17 00:00:00 2001
From: Takashi Iwai
Date: Thu, 22 Nov 2012 16:14:55 +0100
Subject: ALSA: vx: hard dependency on the standard fw loader

Yet again like previous two commits, drop the old hwdep user-space
firmware code from vx driver (snd-vxpocket and snd-vx222).

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/vx_core.h     |   6 --
 sound/drivers/Kconfig       |   1 +
 sound/drivers/vx/vx_hwdep.c | 139 --------------------------------------------
 3 files changed, 1 insertion(+), 145 deletions(-)

(limited to 'include')

diff --git a/include/sound/vx_core.h b/include/sound/vx_core.h
index 4f67c762cd74..f634f8f85db5 100644
--- a/include/sound/vx_core.h
+++ b/include/sound/vx_core.h
@@ -27,12 +27,6 @@
 #include <sound/hwdep.h>
 #include <linux/interrupt.h>
 
-#if defined(CONFIG_FW_LOADER) || defined(CONFIG_FW_LOADER_MODULE)
-#if !defined(CONFIG_USE_VXLOADER) && !defined(CONFIG_SND_VX_LIB) /* built-in kernel */
-#define SND_VX_FW_LOADER	/* use the standard firmware loader */
-#endif
-#endif
-
 struct firmware;
 struct device;
 
diff --git a/sound/drivers/Kconfig b/sound/drivers/Kconfig
index 5e4384137a76..7d02c322ed93 100644
--- a/sound/drivers/Kconfig
+++ b/sound/drivers/Kconfig
@@ -14,6 +14,7 @@ config SND_OPL4_LIB
 
 config SND_VX_LIB
 	tristate
+	select FW_LOADER
 	select SND_HWDEP
 	select SND_PCM
 
diff --git a/sound/drivers/vx/vx_hwdep.c b/sound/drivers/vx/vx_hwdep.c
index 4a1fae99ac55..3014b86362bd 100644
--- a/sound/drivers/vx/vx_hwdep.c
+++ b/sound/drivers/vx/vx_hwdep.c
@@ -29,8 +29,6 @@
 #include <sound/hwdep.h>
 #include <sound/vx_core.h>
 
-#ifdef SND_VX_FW_LOADER
-
 MODULE_FIRMWARE("vx/bx_1_vxp.b56");
 MODULE_FIRMWARE("vx/bx_1_vp4.b56");
 MODULE_FIRMWARE("vx/x1_1_vx2.xlx");
@@ -119,142 +117,5 @@ void snd_vx_free_firmware(struct vx_core *chip)
 #endif
 }
 
-#else /* old style firmware loading */
-
-static int vx_hwdep_dsp_status(struct snd_hwdep *hw,
-			       struct snd_hwdep_dsp_status *info)
-{
-	static char *type_ids[VX_TYPE_NUMS] = {
-		[VX_TYPE_BOARD] = "vxboard",
-		[VX_TYPE_V2] = "vx222",
-		[VX_TYPE_MIC] = "vx222",
-		[VX_TYPE_VXPOCKET] = "vxpocket",
-		[VX_TYPE_VXP440] = "vxp440",
-	};
-	struct vx_core *vx = hw->private_data;
-
-	if (snd_BUG_ON(!type_ids[vx->type]))
-		return -EINVAL;
-	strcpy(info->id, type_ids[vx->type]);
-	if (vx_is_pcmcia(vx))
-		info->num_dsps = 4;
-	else
-		info->num_dsps = 3;
-	if (vx->chip_status & VX_STAT_CHIP_INIT)
-		info->chip_ready = 1;
-	info->version = VX_DRIVER_VERSION;
-	return 0;
-}
-
-static void free_fw(const struct firmware *fw)
-{
-	if (fw) {
-		vfree(fw->data);
-		kfree(fw);
-	}
-}
-
-static int vx_hwdep_dsp_load(struct snd_hwdep *hw,
-			     struct snd_hwdep_dsp_image *dsp)
-{
-	struct vx_core *vx = hw->private_data;
-	int index, err;
-	struct firmware *fw;
-
-	if (snd_BUG_ON(!vx->ops->load_dsp))
-		return -ENXIO;
-
-	fw = kmalloc(sizeof(*fw), GFP_KERNEL);
-	if (! fw) {
-		snd_printk(KERN_ERR "cannot allocate firmware\n");
-		return -ENOMEM;
-	}
-	fw->size = dsp->length;
-	fw->data = vmalloc(fw->size);
-	if (! fw->data) {
-		snd_printk(KERN_ERR "cannot allocate firmware image (length=%d)\n",
-			   (int)fw->size);
-		kfree(fw);
-		return -ENOMEM;
-	}
-	if (copy_from_user((void *)fw->data, dsp->image, dsp->length)) {
-		free_fw(fw);
-		return -EFAULT;
-	}
-
-	index = dsp->index;
-	if (! vx_is_pcmcia(vx))
-		index++;
-	err = vx->ops->load_dsp(vx, index, fw);
-	if (err < 0) {
-		free_fw(fw);
-		return err;
-	}
-#ifdef CONFIG_PM
-	vx->firmware[index] = fw;
-#else
-	free_fw(fw);
-#endif
-
-	if (index == 1)
-		vx->chip_status |= VX_STAT_XILINX_LOADED;
-	if (index < 3)
-		return 0;
-
-	/* ok, we reached to the last one */
-	/* create the devices if not built yet */
-	if (! (vx->chip_status & VX_STAT_DEVICE_INIT)) {
-		if ((err = snd_vx_pcm_new(vx)) < 0)
-			return err;
-
-		if ((err = snd_vx_mixer_new(vx)) < 0)
-			return err;
-
-		if (vx->ops->add_controls)
-			if ((err = vx->ops->add_controls(vx)) < 0)
-				return err;
-
-		if ((err = snd_card_register(vx->card)) < 0)
-			return err;
-
-		vx->chip_status |= VX_STAT_DEVICE_INIT;
-	}
-	vx->chip_status |= VX_STAT_CHIP_INIT;
-	return 0;
-}
-
-
-/* exported */
-int snd_vx_setup_firmware(struct vx_core *chip)
-{
-	int err;
-	struct snd_hwdep *hw;
-
-	if ((err = snd_hwdep_new(chip->card, SND_VX_HWDEP_ID, 0, &hw)) < 0)
-		return err;
-
-	hw->iface = SNDRV_HWDEP_IFACE_VX;
-	hw->private_data = chip;
-	hw->ops.dsp_status = vx_hwdep_dsp_status;
-	hw->ops.dsp_load = vx_hwdep_dsp_load;
-	hw->exclusive = 1;
-	sprintf(hw->name, "VX Loader (%s)", chip->card->driver);
-	chip->hwdep = hw;
-
-	return snd_card_register(chip->card);
-}
-
-/* exported */
-void snd_vx_free_firmware(struct vx_core *chip)
-{
-#ifdef CONFIG_PM
-	int i;
-	for (i = 0; i < 4; i++)
-		free_fw(chip->firmware[i]);
-#endif
-}
-
-#endif /* SND_VX_FW_LOADER */
-
 EXPORT_SYMBOL(snd_vx_setup_firmware);
 EXPORT_SYMBOL(snd_vx_free_firmware);
-- 
cgit v1.2.3-55-g7522


From b209c4dfcd960ab176d4746ab7dc442a3edb4575 Mon Sep 17 00:00:00 2001
From: Takashi Iwai
Date: Thu, 22 Nov 2012 17:17:17 +0100
Subject: ALSA: emu10k1: cache emu1010 firmware

Instead of calling request_firmware() at each time, keep the obtained
firmware internally and reuse it.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/emu10k1.h          |  3 ++
 sound/pci/emu10k1/emu10k1_main.c | 88 ++++++++++++++++------------------------
 2 files changed, 39 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h
index 3707288ae9bf..9dc94b559c7d 100644
--- a/include/sound/emu10k1.h
+++ b/include/sound/emu10k1.h
@@ -32,6 +32,7 @@
 #include <sound/timer.h>
 #include <linux/interrupt.h>
 #include <linux/mutex.h>
+#include <linux/firmware.h>
 
 #include <asm/io.h>
 #include <uapi/sound/emu10k1.h>
@@ -1785,6 +1786,8 @@ struct snd_emu10k1 {
 	unsigned int efx_voices_mask[2];
 	unsigned int next_free_voice;
 
+	const struct firmware *firmware;
+
 #ifdef CONFIG_PM_SLEEP
 	unsigned int *saved_ptr;
 	unsigned int *saved_gpr;
diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c
index c21adb6ef1d5..1dfb94d16b8b 100644
--- a/sound/pci/emu10k1/emu10k1_main.c
+++ b/sound/pci/emu10k1/emu10k1_main.c
@@ -657,22 +657,17 @@ static int snd_emu10k1_cardbus_init(struct snd_emu10k1 *emu)
 	return 0;
 }
 
-static int snd_emu1010_load_firmware(struct snd_emu10k1 *emu, const char *filename)
+static int snd_emu1010_load_firmware(struct snd_emu10k1 *emu)
 {
-	int err;
 	int n, i;
 	int reg;
 	int value;
 	unsigned int write_post;
 	unsigned long flags;
-	const struct firmware *fw_entry;
+	const struct firmware *fw_entry = emu->firmware;
 
-	err = request_firmware(&fw_entry, filename, &emu->pci->dev);
-	if (err != 0) {
-		snd_printk(KERN_ERR "firmware: %s not found. Err = %d\n", filename, err);
-		return err;
-	}
-	snd_printk(KERN_INFO "firmware size = 0x%zx\n", fw_entry->size);
+	if (!fw_entry)
+		return -EIO;
 
 	/* The FPGA is a Xilinx Spartan IIE XC2S50E */
 	/* GPIO7 -> FPGA PGMN
@@ -705,7 +700,6 @@ static int snd_emu1010_load_firmware(struct snd_emu10k1 *emu, const char *filena
 	write_post = inl(emu->port + A_IOCFG);
 	spin_unlock_irqrestore(&emu->emu_lock, flags);
 
-	release_firmware(fw_entry);
 	return 0;
 }
 
@@ -727,22 +721,9 @@ static int emu1010_firmware_thread(void *data)
 			/* Return to Audio Dock programming mode */
 			snd_printk(KERN_INFO "emu1010: Loading Audio Dock Firmware\n");
 			snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, EMU_HANA_FPGA_CONFIG_AUDIODOCK);
-			if (emu->card_capabilities->emu_model ==
-			    EMU_MODEL_EMU1010) {
-				err = snd_emu1010_load_firmware(emu, DOCK_FILENAME);
-				if (err != 0)
-					continue;
-			} else if (emu->card_capabilities->emu_model ==
-				   EMU_MODEL_EMU1010B) {
-				err = snd_emu1010_load_firmware(emu, MICRO_DOCK_FILENAME);
-				if (err != 0)
-					continue;
-			} else if (emu->card_capabilities->emu_model ==
-				   EMU_MODEL_EMU1616) {
-				err = snd_emu1010_load_firmware(emu, MICRO_DOCK_FILENAME);
-				if (err != 0)
-					continue;
-			}
+			err = snd_emu1010_load_firmware(emu);
+			if (err != 0)
+				continue;
 
 			snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, 0);
 			snd_emu1010_fpga_read(emu, EMU_HANA_IRQ_STATUS, &reg);
@@ -807,7 +788,6 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu)
 	unsigned int i;
 	u32 tmp, tmp2, reg;
 	int err;
-	const char *filename = NULL;
 
 	snd_printk(KERN_INFO "emu1010: Special config.\n");
 	/* AC97 2.1, Any 16Meg of 4Gig address, Auto-Mute, EMU32 Slave,
@@ -849,31 +829,33 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu)
 		return -ENODEV;
 	}
 	snd_printk(KERN_INFO "emu1010: EMU_HANA_ID = 0x%x\n", reg);
-	switch (emu->card_capabilities->emu_model) {
-	case EMU_MODEL_EMU1010:
-		filename = HANA_FILENAME;
-		break;
-	case EMU_MODEL_EMU1010B:
-		filename = EMU1010B_FILENAME;
-		break;
-	case EMU_MODEL_EMU1616:
-		filename = EMU1010_NOTEBOOK_FILENAME;
-		break;
-	case EMU_MODEL_EMU0404:
-		filename = EMU0404_FILENAME;
-		break;
-	default:
-		filename = NULL;
-		return -ENODEV;
-		break;
-	}
-	snd_printk(KERN_INFO "emu1010: filename %s testing\n", filename);
-	err = snd_emu1010_load_firmware(emu, filename);
-	if (err != 0) {
-		snd_printk(
-			KERN_INFO "emu1010: Loading Firmware file %s failed\n",
-			filename);
-		return err;
+
+	if (!emu->firmware) {
+		const char *filename;
+		switch (emu->card_capabilities->emu_model) {
+		case EMU_MODEL_EMU1010:
+			filename = HANA_FILENAME;
+			break;
+		case EMU_MODEL_EMU1010B:
+			filename = EMU1010B_FILENAME;
+			break;
+		case EMU_MODEL_EMU1616:
+			filename = EMU1010_NOTEBOOK_FILENAME;
+			break;
+		case EMU_MODEL_EMU0404:
+			filename = EMU0404_FILENAME;
+			break;
+		default:
+			return -ENODEV;
+		}
+
+		err = request_firmware(&emu->firmware, filename, &emu->pci->dev);
+		if (err != 0) {
+			snd_printk(KERN_ERR "emu1010: firmware: %s not found. Err = %d\n", filename, err);
+			return err;
+		}
+		snd_printk(KERN_INFO "emu1010: firmware file = %s, size = 0x%zx\n",
+			   filename, emu->firmware->size);
 	}
 
 	/* ID, should read & 0x7f = 0x55 when FPGA programmed. */
@@ -1259,6 +1241,8 @@ static int snd_emu10k1_free(struct snd_emu10k1 *emu)
 	}
 	if (emu->emu1010.firmware_thread)
 		kthread_stop(emu->emu1010.firmware_thread);
+	if (emu->firmware)
+		release_firmware(emu->firmware);
 	if (emu->irq >= 0)
 		free_irq(emu->irq, emu);
 	/* remove reserved page */
-- 
cgit v1.2.3-55-g7522


From 4f86f120d9d65b3a8f17e48dca1f991d861b5cd7 Mon Sep 17 00:00:00 2001
From: Takashi Iwai
Date: Thu, 22 Nov 2012 17:18:49 +0100
Subject: ALSA: emu10k1: don't update firmware during suspend/resume

Add a flag to suppress the update in emu1010_firmware_thread() during
suspend/resume.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/emu10k1.h          | 1 +
 sound/pci/emu10k1/emu10k1.c      | 4 ++++
 sound/pci/emu10k1/emu10k1_main.c | 2 ++
 3 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h
index 9dc94b559c7d..f841ba4bacb8 100644
--- a/include/sound/emu10k1.h
+++ b/include/sound/emu10k1.h
@@ -1796,6 +1796,7 @@ struct snd_emu10k1 {
 	unsigned int *saved_icode;
 	unsigned int *p16v_saved;
 	unsigned int saved_a_iocfg, saved_hcfg;
+	bool suspend;
 #endif
 
 };
diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c
index b7c1875ba90e..a168138efc5e 100644
--- a/sound/pci/emu10k1/emu10k1.c
+++ b/sound/pci/emu10k1/emu10k1.c
@@ -215,6 +215,8 @@ static int snd_emu10k1_suspend(struct device *dev)
 
 	snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
 
+	emu->suspend = 1;
+
 	snd_pcm_suspend_all(emu->pcm);
 	snd_pcm_suspend_all(emu->pcm_mic);
 	snd_pcm_suspend_all(emu->pcm_efx);
@@ -260,6 +262,8 @@ static int snd_emu10k1_resume(struct device *dev)
 	if (emu->card_capabilities->ca0151_chip)
 		snd_p16v_resume(emu);
 
+	emu->suspend = 0;
+
 	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
 	return 0;
 }
diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c
index 1dfb94d16b8b..cfd6cf952d44 100644
--- a/sound/pci/emu10k1/emu10k1_main.c
+++ b/sound/pci/emu10k1/emu10k1_main.c
@@ -714,6 +714,8 @@ static int emu1010_firmware_thread(void *data)
 		msleep_interruptible(1000);
 		if (kthread_should_stop())
 			break;
+		if (emu->suspend)
+			continue;
 		snd_emu1010_fpga_read(emu, EMU_HANA_IRQ_STATUS, &tmp); /* IRQ Status */
 		snd_emu1010_fpga_read(emu, EMU_HANA_OPTION_CARDS, &reg); /* OPTIONS: Which cards are attached to the EMU */
 		if (reg & EMU_HANA_OPTION_DOCK_OFFLINE) {
-- 
cgit v1.2.3-55-g7522


From 83af24027b3df1af5c5a9aa9adcdcfeb3429d3be Mon Sep 17 00:00:00 2001
From: Philip, Avinash
Date: Wed, 21 Nov 2012 13:10:44 +0530
Subject: pwm: Device tree support for PWM polarity

Add support for encoding PWM properties in bit encoded form with
of_pwm_xlate_with_flags() function support. Platforms require platform
specific PWM properties has to populate in 3rd cell of the pwm-specifier
and PWM driver should also set .of_xlate support with this function.
Currently PWM property polarity encoded in bit position 0 of the third
cell in pwm-specifier.

Signed-off-by: Philip, Avinash <avinashphilip@ti.com>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Thierry Reding <thierry.reding@avionic-design.de>
---
 Documentation/devicetree/bindings/pwm/pwm.txt | 17 +++++++++++++---
 drivers/pwm/core.c                            | 28 +++++++++++++++++++++++++++
 include/linux/pwm.h                           |  3 +++
 3 files changed, 45 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/pwm/pwm.txt b/Documentation/devicetree/bindings/pwm/pwm.txt
index 73ec962bfe8c..06e67247859a 100644
--- a/Documentation/devicetree/bindings/pwm/pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/pwm.txt
@@ -37,10 +37,21 @@ device:
 		pwm-names = "backlight";
 	};
 
+Note that in the example above, specifying the "pwm-names" is redundant
+because the name "backlight" would be used as fallback anyway.
+
 pwm-specifier typically encodes the chip-relative PWM number and the PWM
-period in nanoseconds. Note that in the example above, specifying the
-"pwm-names" is redundant because the name "backlight" would be used as
-fallback anyway.
+period in nanoseconds.
+
+Optionally, the pwm-specifier can encode a number of flags in a third cell:
+- bit 0: PWM signal polarity (0: normal polarity, 1: inverse polarity)
+
+Example with optional PWM specifier for inverse polarity
+
+	bl: backlight {
+		pwms = <&pwm 0 5000000 1>;
+		pwm-names = "backlight";
+	};
 
 2) PWM controller nodes
 -----------------------
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index f5acdaa52707..780cb6b8a8f0 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -32,6 +32,9 @@
 
 #define MAX_PWMS 1024
 
+/* flags in the third cell of the DT PWM specifier */
+#define PWM_SPEC_POLARITY	(1 << 0)
+
 static DEFINE_MUTEX(pwm_lookup_lock);
 static LIST_HEAD(pwm_lookup_list);
 static DEFINE_MUTEX(pwm_lock);
@@ -129,6 +132,31 @@ static int pwm_device_request(struct pwm_device *pwm, const char *label)
 	return 0;
 }
 
+struct pwm_device *
+of_pwm_xlate_with_flags(struct pwm_chip *pc, const struct of_phandle_args *args)
+{
+	struct pwm_device *pwm;
+
+	if (pc->of_pwm_n_cells < 3)
+		return ERR_PTR(-EINVAL);
+
+	if (args->args[0] >= pc->npwm)
+		return ERR_PTR(-EINVAL);
+
+	pwm = pwm_request_from_chip(pc, args->args[0], NULL);
+	if (IS_ERR(pwm))
+		return pwm;
+
+	pwm_set_period(pwm, args->args[1]);
+
+	if (args->args[2] & PWM_SPEC_POLARITY)
+		pwm_set_polarity(pwm, PWM_POLARITY_INVERSED);
+	else
+		pwm_set_polarity(pwm, PWM_POLARITY_NORMAL);
+
+	return pwm;
+}
+
 static struct pwm_device *
 of_pwm_simple_xlate(struct pwm_chip *pc, const struct of_phandle_args *args)
 {
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 112b31436848..6d661f32e0e4 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -171,6 +171,9 @@ struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip,
 					 unsigned int index,
 					 const char *label);
 
+struct pwm_device *of_pwm_xlate_with_flags(struct pwm_chip *pc,
+		const struct of_phandle_args *args);
+
 struct pwm_device *pwm_get(struct device *dev, const char *consumer);
 void pwm_put(struct pwm_device *pwm);
 
-- 
cgit v1.2.3-55-g7522


From acad189b08456722ca4a8984218d6f38f4563cbc Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski
Date: Thu, 22 Nov 2012 11:12:04 +0100
Subject: mfd: Add an AS3711 PMIC MFD driver

AS3711 is a PMIC with multiple DCDC and LDO power supplies, GPIOs, an RTC,
a battery charger and a general purpose ADC. This patch adds support for
the MFD with support for a regulator driver and a backlight driver.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/Kconfig        |   9 ++
 drivers/mfd/Makefile       |   1 +
 drivers/mfd/as3711.c       | 217 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/as3711.h | 126 ++++++++++++++++++++++++++
 4 files changed, 353 insertions(+)
 create mode 100644 drivers/mfd/as3711.c
 create mode 100644 include/linux/mfd/as3711.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index f5b839b718aa..475c26696b95 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1103,6 +1103,15 @@ config MFD_RETU
 	  Retu is a multi-function device found on Nokia Internet Tablets
 	  (770, N800 and N810).
 
+config MFD_AS3711
+	bool "Support for AS3711"
+	select MFD_CORE
+	select REGMAP_I2C
+	select REGMAP_IRQ
+	depends on I2C=y
+	help
+	  Support for the AS3711 PMIC from AMS
+
 endmenu
 endif
 
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 2689c8a0d781..f2216dfd963c 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -146,3 +146,4 @@ obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o sec-irq.o
 obj-$(CONFIG_MFD_SYSCON)	+= syscon.o
 obj-$(CONFIG_MFD_LM3533)	+= lm3533-core.o lm3533-ctrlbank.o
 obj-$(CONFIG_MFD_RETU)		+= retu-mfd.o
+obj-$(CONFIG_MFD_AS3711)	+= as3711.o
diff --git a/drivers/mfd/as3711.c b/drivers/mfd/as3711.c
new file mode 100644
index 000000000000..e994c9691124
--- /dev/null
+++ b/drivers/mfd/as3711.c
@@ -0,0 +1,217 @@
+/*
+ * AS3711 PMIC MFC driver
+ *
+ * Copyright (C) 2012 Renesas Electronics Corporation
+ * Author: Guennadi Liakhovetski, <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License as
+ * published by the Free Software Foundation
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mfd/as3711.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+enum {
+	AS3711_REGULATOR,
+	AS3711_BACKLIGHT,
+};
+
+/*
+ * Ok to have it static: it is only used during probing and multiple I2C devices
+ * cannot be probed simultaneously. Just make sure to avoid stale data.
+ */
+static struct mfd_cell as3711_subdevs[] = {
+	[AS3711_REGULATOR] = {.name = "as3711-regulator",},
+	[AS3711_BACKLIGHT] = {.name = "as3711-backlight",},
+};
+
+static bool as3711_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case AS3711_GPIO_SIGNAL_IN:
+	case AS3711_INTERRUPT_STATUS_1:
+	case AS3711_INTERRUPT_STATUS_2:
+	case AS3711_INTERRUPT_STATUS_3:
+	case AS3711_CHARGER_STATUS_1:
+	case AS3711_CHARGER_STATUS_2:
+	case AS3711_REG_STATUS:
+		return true;
+	}
+	return false;
+}
+
+static bool as3711_precious_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case AS3711_INTERRUPT_STATUS_1:
+	case AS3711_INTERRUPT_STATUS_2:
+	case AS3711_INTERRUPT_STATUS_3:
+		return true;
+	}
+	return false;
+}
+
+static bool as3711_readable_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case AS3711_SD_1_VOLTAGE:
+	case AS3711_SD_2_VOLTAGE:
+	case AS3711_SD_3_VOLTAGE:
+	case AS3711_SD_4_VOLTAGE:
+	case AS3711_LDO_1_VOLTAGE:
+	case AS3711_LDO_2_VOLTAGE:
+	case AS3711_LDO_3_VOLTAGE:
+	case AS3711_LDO_4_VOLTAGE:
+	case AS3711_LDO_5_VOLTAGE:
+	case AS3711_LDO_6_VOLTAGE:
+	case AS3711_LDO_7_VOLTAGE:
+	case AS3711_LDO_8_VOLTAGE:
+	case AS3711_SD_CONTROL:
+	case AS3711_GPIO_SIGNAL_OUT:
+	case AS3711_GPIO_SIGNAL_IN:
+	case AS3711_SD_CONTROL_1:
+	case AS3711_SD_CONTROL_2:
+	case AS3711_CURR_CONTROL:
+	case AS3711_CURR1_VALUE:
+	case AS3711_CURR2_VALUE:
+	case AS3711_CURR3_VALUE:
+	case AS3711_STEPUP_CONTROL_1:
+	case AS3711_STEPUP_CONTROL_2:
+	case AS3711_STEPUP_CONTROL_4:
+	case AS3711_STEPUP_CONTROL_5:
+	case AS3711_REG_STATUS:
+	case AS3711_INTERRUPT_STATUS_1:
+	case AS3711_INTERRUPT_STATUS_2:
+	case AS3711_INTERRUPT_STATUS_3:
+	case AS3711_CHARGER_STATUS_1:
+	case AS3711_CHARGER_STATUS_2:
+	case AS3711_ASIC_ID_1:
+	case AS3711_ASIC_ID_2:
+		return true;
+	}
+	return false;
+}
+
+static const struct regmap_config as3711_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.volatile_reg = as3711_volatile_reg,
+	.readable_reg = as3711_readable_reg,
+	.precious_reg = as3711_precious_reg,
+	.max_register = AS3711_MAX_REGS,
+	.num_reg_defaults_raw = AS3711_MAX_REGS,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static int as3711_i2c_probe(struct i2c_client *client,
+			    const struct i2c_device_id *id)
+{
+	struct as3711 *as3711;
+	struct as3711_platform_data *pdata = client->dev.platform_data;
+	unsigned int id1, id2;
+	int ret;
+
+	if (!pdata)
+		dev_dbg(&client->dev, "Platform data not found\n");
+
+	as3711 = devm_kzalloc(&client->dev, sizeof(struct as3711), GFP_KERNEL);
+	if (!as3711) {
+		dev_err(&client->dev, "Memory allocation failed\n");
+		return -ENOMEM;
+	}
+
+	as3711->dev = &client->dev;
+	i2c_set_clientdata(client, as3711);
+
+	if (client->irq)
+		dev_notice(&client->dev, "IRQ not supported yet\n");
+
+	as3711->regmap = devm_regmap_init_i2c(client, &as3711_regmap_config);
+	if (IS_ERR(as3711->regmap)) {
+		ret = PTR_ERR(as3711->regmap);
+		dev_err(&client->dev, "regmap initialization failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_read(as3711->regmap, AS3711_ASIC_ID_1, &id1);
+	if (!ret)
+		ret = regmap_read(as3711->regmap, AS3711_ASIC_ID_2, &id2);
+	if (ret < 0) {
+		dev_err(&client->dev, "regmap_read() failed: %d\n", ret);
+		return ret;
+	}
+	if (id1 != 0x8b)
+		return -ENODEV;
+	dev_info(as3711->dev, "AS3711 detected: %x:%x\n", id1, id2);
+
+	/* We can reuse as3711_subdevs[], it will be copied in mfd_add_devices() */
+	if (pdata) {
+		as3711_subdevs[AS3711_REGULATOR].platform_data = &pdata->regulator;
+		as3711_subdevs[AS3711_REGULATOR].pdata_size = sizeof(pdata->regulator);
+		as3711_subdevs[AS3711_BACKLIGHT].platform_data = &pdata->backlight;
+		as3711_subdevs[AS3711_BACKLIGHT].pdata_size = sizeof(pdata->backlight);
+	} else {
+		as3711_subdevs[AS3711_REGULATOR].platform_data = NULL;
+		as3711_subdevs[AS3711_REGULATOR].pdata_size = 0;
+		as3711_subdevs[AS3711_BACKLIGHT].platform_data = NULL;
+		as3711_subdevs[AS3711_BACKLIGHT].pdata_size = 0;
+	}
+
+	ret = mfd_add_devices(as3711->dev, -1, as3711_subdevs,
+			      ARRAY_SIZE(as3711_subdevs), NULL, 0, NULL);
+	if (ret < 0)
+		dev_err(&client->dev, "add mfd devices failed: %d\n", ret);
+
+	return ret;
+}
+
+static int as3711_i2c_remove(struct i2c_client *client)
+{
+	struct as3711 *as3711 = i2c_get_clientdata(client);
+
+	mfd_remove_devices(as3711->dev);
+	return 0;
+}
+
+static const struct i2c_device_id as3711_i2c_id[] = {
+	{.name = "as3711", .driver_data = 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, as3711_i2c_id);
+
+static struct i2c_driver as3711_i2c_driver = {
+	.driver = {
+		   .name = "as3711",
+		   .owner = THIS_MODULE,
+		   },
+	.probe = as3711_i2c_probe,
+	.remove = as3711_i2c_remove,
+	.id_table = as3711_i2c_id,
+};
+
+static int __init as3711_i2c_init(void)
+{
+	return i2c_add_driver(&as3711_i2c_driver);
+}
+/* Initialise early */
+subsys_initcall(as3711_i2c_init);
+
+static void __exit as3711_i2c_exit(void)
+{
+	i2c_del_driver(&as3711_i2c_driver);
+}
+module_exit(as3711_i2c_exit);
+
+MODULE_AUTHOR("Guennadi Liakhovetski <g.liakhovetski@gmx.de>");
+MODULE_DESCRIPTION("AS3711 PMIC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/as3711.h b/include/linux/mfd/as3711.h
new file mode 100644
index 000000000000..38452ce1e892
--- /dev/null
+++ b/include/linux/mfd/as3711.h
@@ -0,0 +1,126 @@
+/*
+ * AS3711 PMIC MFC driver header
+ *
+ * Copyright (C) 2012 Renesas Electronics Corporation
+ * Author: Guennadi Liakhovetski, <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License as
+ * published by the Free Software Foundation
+ */
+
+#ifndef MFD_AS3711_H
+#define MFD_AS3711_H
+
+/*
+ * Client data
+ */
+
+/* Register addresses */
+#define AS3711_SD_1_VOLTAGE		0	/* Digital Step-Down */
+#define AS3711_SD_2_VOLTAGE		1
+#define AS3711_SD_3_VOLTAGE		2
+#define AS3711_SD_4_VOLTAGE		3
+#define AS3711_LDO_1_VOLTAGE		4	/* Analog LDO */
+#define AS3711_LDO_2_VOLTAGE		5
+#define AS3711_LDO_3_VOLTAGE		6	/* Digital LDO */
+#define AS3711_LDO_4_VOLTAGE		7
+#define AS3711_LDO_5_VOLTAGE		8
+#define AS3711_LDO_6_VOLTAGE		9
+#define AS3711_LDO_7_VOLTAGE		0xa
+#define AS3711_LDO_8_VOLTAGE		0xb
+#define AS3711_SD_CONTROL		0x10
+#define AS3711_GPIO_SIGNAL_OUT		0x20
+#define AS3711_GPIO_SIGNAL_IN		0x21
+#define AS3711_SD_CONTROL_1		0x30
+#define AS3711_SD_CONTROL_2		0x31
+#define AS3711_CURR_CONTROL		0x40
+#define AS3711_CURR1_VALUE		0x43
+#define AS3711_CURR2_VALUE		0x44
+#define AS3711_CURR3_VALUE		0x45
+#define AS3711_STEPUP_CONTROL_1		0x50
+#define AS3711_STEPUP_CONTROL_2		0x51
+#define AS3711_STEPUP_CONTROL_4		0x53
+#define AS3711_STEPUP_CONTROL_5		0x54
+#define AS3711_REG_STATUS		0x73
+#define AS3711_INTERRUPT_STATUS_1	0x77
+#define AS3711_INTERRUPT_STATUS_2	0x78
+#define AS3711_INTERRUPT_STATUS_3	0x79
+#define AS3711_CHARGER_STATUS_1		0x86
+#define AS3711_CHARGER_STATUS_2		0x87
+#define AS3711_ASIC_ID_1		0x90
+#define AS3711_ASIC_ID_2		0x91
+
+#define AS3711_MAX_REGS			0x92
+
+/* Regulators */
+enum {
+	AS3711_REGULATOR_SD_1,
+	AS3711_REGULATOR_SD_2,
+	AS3711_REGULATOR_SD_3,
+	AS3711_REGULATOR_SD_4,
+	AS3711_REGULATOR_LDO_1,
+	AS3711_REGULATOR_LDO_2,
+	AS3711_REGULATOR_LDO_3,
+	AS3711_REGULATOR_LDO_4,
+	AS3711_REGULATOR_LDO_5,
+	AS3711_REGULATOR_LDO_6,
+	AS3711_REGULATOR_LDO_7,
+	AS3711_REGULATOR_LDO_8,
+
+	AS3711_REGULATOR_MAX,
+};
+
+struct device;
+struct regmap;
+
+struct as3711 {
+	struct device *dev;
+	struct regmap *regmap;
+};
+
+#define AS3711_MAX_STEPDOWN 4
+#define AS3711_MAX_STEPUP 2
+#define AS3711_MAX_LDO 8
+
+enum as3711_su2_feedback {
+	AS3711_SU2_VOLTAGE,
+	AS3711_SU2_CURR1,
+	AS3711_SU2_CURR2,
+	AS3711_SU2_CURR3,
+	AS3711_SU2_CURR_AUTO,
+};
+
+enum as3711_su2_fbprot {
+	AS3711_SU2_LX_SD4,
+	AS3711_SU2_GPIO2,
+	AS3711_SU2_GPIO3,
+	AS3711_SU2_GPIO4,
+};
+
+/*
+ * Platform data
+ */
+
+struct as3711_regulator_pdata {
+	struct regulator_init_data *init_data[AS3711_REGULATOR_MAX];
+};
+
+struct as3711_bl_pdata {
+	const char *su1_fb;
+	int su1_max_uA;
+	const char *su2_fb;
+	int su2_max_uA;
+	enum as3711_su2_feedback su2_feedback;
+	enum as3711_su2_fbprot su2_fbprot;
+	bool su2_auto_curr1;
+	bool su2_auto_curr2;
+	bool su2_auto_curr3;
+};
+
+struct as3711_platform_data {
+	struct as3711_regulator_pdata regulator;
+	struct as3711_bl_pdata backlight;
+};
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 907ddf89d0bb7f57e1e21485900e6564a1ab512a Mon Sep 17 00:00:00 2001
From: Mika Westerberg
Date: Fri, 23 Nov 2012 12:23:40 +0100
Subject: i2c / ACPI: add ACPI enumeration support

ACPI 5 introduced I2cSerialBus resource that makes it possible to enumerate
and configure the I2C slave devices behind the I2C controller. This patch
adds helper functions to support I2C slave enumeration.

An ACPI enabled I2C controller driver only needs to call acpi_i2c_register_devices()
in order to get its slave devices enumerated, created and bound to the
corresponding ACPI handle.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/Kconfig    |   6 +++
 drivers/acpi/Makefile   |   1 +
 drivers/acpi/acpi_i2c.c | 103 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/i2c/i2c-core.c  |   6 +++
 include/linux/i2c.h     |   9 +++++
 5 files changed, 125 insertions(+)
 create mode 100644 drivers/acpi/acpi_i2c.c

(limited to 'include')

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 119d58db8342..0300bf612946 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -181,6 +181,12 @@ config ACPI_DOCK
 	  This driver supports ACPI-controlled docking stations and removable
 	  drive bays such as the IBM Ultrabay and the Dell Module Bay.
 
+config ACPI_I2C
+	def_tristate I2C
+	depends on I2C
+	help
+	  ACPI I2C enumeration support.
+
 config ACPI_PROCESSOR
 	tristate "Processor"
 	select THERMAL
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 3223edfb23b6..7198b6d6b763 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -69,6 +69,7 @@ obj-$(CONFIG_ACPI_HED)		+= hed.o
 obj-$(CONFIG_ACPI_EC_DEBUGFS)	+= ec_sys.o
 obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
 obj-$(CONFIG_ACPI_BGRT)		+= bgrt.o
+obj-$(CONFIG_ACPI_I2C)		+= acpi_i2c.o
 
 # processor has its own "processor." module_param namespace
 processor-y			:= processor_driver.o processor_throttling.o
diff --git a/drivers/acpi/acpi_i2c.c b/drivers/acpi/acpi_i2c.c
new file mode 100644
index 000000000000..82045e3f5cac
--- /dev/null
+++ b/drivers/acpi/acpi_i2c.c
@@ -0,0 +1,103 @@
+/*
+ * ACPI I2C enumeration support
+ *
+ * Copyright (C) 2012, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/i2c.h>
+#include <linux/ioport.h>
+
+ACPI_MODULE_NAME("i2c");
+
+static int acpi_i2c_add_resource(struct acpi_resource *ares, void *data)
+{
+	struct i2c_board_info *info = data;
+
+	if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) {
+		struct acpi_resource_i2c_serialbus *sb;
+
+		sb = &ares->data.i2c_serial_bus;
+		if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_I2C) {
+			info->addr = sb->slave_address;
+			if (sb->access_mode == ACPI_I2C_10BIT_MODE)
+				info->flags |= I2C_CLIENT_TEN;
+		}
+	} else if (info->irq < 0) {
+		struct resource r;
+
+		if (acpi_dev_resource_interrupt(ares, 0, &r))
+			info->irq = r.start;
+	}
+
+	/* Tell the ACPI core to skip this resource */
+	return 1;
+}
+
+static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level,
+				       void *data, void **return_value)
+{
+	struct i2c_adapter *adapter = data;
+	struct list_head resource_list;
+	struct i2c_board_info info;
+	struct acpi_device *adev;
+	int ret;
+
+	if (acpi_bus_get_device(handle, &adev))
+		return AE_OK;
+	if (acpi_bus_get_status(adev) || !adev->status.present)
+		return AE_OK;
+
+	memset(&info, 0, sizeof(info));
+	info.acpi_node.handle = handle;
+	info.irq = -1;
+
+	INIT_LIST_HEAD(&resource_list);
+	ret = acpi_dev_get_resources(adev, &resource_list,
+				     acpi_i2c_add_resource, &info);
+	acpi_dev_free_resource_list(&resource_list);
+
+	if (ret < 0 || !info.addr)
+		return AE_OK;
+
+	strlcpy(info.type, dev_name(&adev->dev), sizeof(info.type));
+	if (!i2c_new_device(adapter, &info)) {
+		dev_err(&adapter->dev,
+			"failed to add I2C device %s from ACPI\n",
+			dev_name(&adev->dev));
+	}
+
+	return AE_OK;
+}
+
+/**
+ * acpi_i2c_register_devices - enumerate I2C slave devices behind adapter
+ * @adapter: pointer to adapter
+ *
+ * Enumerate all I2C slave devices behind this adapter by walking the ACPI
+ * namespace. When a device is found it will be added to the Linux device
+ * model and bound to the corresponding ACPI handle.
+ */
+void acpi_i2c_register_devices(struct i2c_adapter *adapter)
+{
+	acpi_handle handle;
+	acpi_status status;
+
+	handle = ACPI_HANDLE(&adapter->dev);
+	if (!handle)
+		return;
+
+	status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
+				     acpi_i2c_add_device, NULL,
+				     adapter, NULL);
+	if (ACPI_FAILURE(status))
+		dev_warn(&adapter->dev, "failed to enumerate I2C slaves\n");
+}
+EXPORT_SYMBOL_GPL(acpi_i2c_register_devices);
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index a7edf987a339..e388590b44ab 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -39,6 +39,7 @@
 #include <linux/irqflags.h>
 #include <linux/rwsem.h>
 #include <linux/pm_runtime.h>
+#include <linux/acpi.h>
 #include <asm/uaccess.h>
 
 #include "i2c-core.h"
@@ -78,6 +79,10 @@ static int i2c_device_match(struct device *dev, struct device_driver *drv)
 	if (of_driver_match_device(dev, drv))
 		return 1;
 
+	/* Then ACPI style match */
+	if (acpi_driver_match_device(dev, drv))
+		return 1;
+
 	driver = to_i2c_driver(drv);
 	/* match on an id table if there is one */
 	if (driver->id_table)
@@ -539,6 +544,7 @@ i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
 	client->dev.bus = &i2c_bus_type;
 	client->dev.type = &i2c_client_type;
 	client->dev.of_node = info->of_node;
+	ACPI_HANDLE_SET(&client->dev, info->acpi_node.handle);
 
 	/* For 10-bit clients, add an arbitrary offset to avoid collisions */
 	dev_set_name(&client->dev, "%d-%04x", i2c_adapter_id(adap),
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 800de224336b..d0c4db7b4872 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -259,6 +259,7 @@ static inline void i2c_set_clientdata(struct i2c_client *dev, void *data)
  * @platform_data: stored in i2c_client.dev.platform_data
  * @archdata: copied into i2c_client.dev.archdata
  * @of_node: pointer to OpenFirmware device node
+ * @acpi_node: ACPI device node
  * @irq: stored in i2c_client.irq
  *
  * I2C doesn't actually support hardware probing, although controllers and
@@ -279,6 +280,7 @@ struct i2c_board_info {
 	void		*platform_data;
 	struct dev_archdata	*archdata;
 	struct device_node *of_node;
+	struct acpi_dev_node acpi_node;
 	int		irq;
 };
 
@@ -501,4 +503,11 @@ static inline int i2c_adapter_id(struct i2c_adapter *adap)
 			i2c_del_driver)
 
 #endif /* I2C */
+
+#if IS_ENABLED(CONFIG_ACPI_I2C)
+extern void acpi_i2c_register_devices(struct i2c_adapter *adap);
+#else
+static inline void acpi_i2c_register_devices(struct i2c_adapter *adap) {}
+#endif
+
 #endif /* _LINUX_I2C_H */
-- 
cgit v1.2.3-55-g7522


From a8a8fc287dd7497b3adb2f2952513849ab6506eb Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Mon, 8 Oct 2012 11:21:09 +0900
Subject: mfd: wm8994: Store platform data in device

This is better style as platform data is supposed to be discardable after
init (though hotplug usually prevents this) and will ease implementation
of device tree property bindings.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Acked-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/wm8994-core.c       | 35 +++++++++++++++++++----------------
 include/linux/mfd/wm8994/core.h |  4 ++++
 2 files changed, 23 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index 8fefc961ec06..45a20c573aa3 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -401,13 +401,19 @@ static const __devinitconst struct reg_default wm1811_reva_patch[] = {
  */
 static __devinit int wm8994_device_init(struct wm8994 *wm8994, int irq)
 {
-	struct wm8994_pdata *pdata = wm8994->dev->platform_data;
+	struct wm8994_pdata *pdata;
 	struct regmap_config *regmap_config;
 	const struct reg_default *regmap_patch = NULL;
 	const char *devname;
 	int ret, i, patch_regs;
 	int pulls = 0;
 
+	if (dev_get_platdata(wm8994->dev)) {
+		pdata = dev_get_platdata(wm8994->dev);
+		wm8994->pdata = *pdata;
+	}
+	pdata = &wm8994->pdata;
+
 	dev_set_drvdata(wm8994->dev, wm8994);
 
 	/* Add the on-chip regulators first for bootstrapping */
@@ -604,24 +610,21 @@ static __devinit int wm8994_device_init(struct wm8994 *wm8994, int irq)
 		}
 	}
 
-	if (pdata) {
-		wm8994->irq_base = pdata->irq_base;
-		wm8994->gpio_base = pdata->gpio_base;
-
-		/* GPIO configuration is only applied if it's non-zero */
-		for (i = 0; i < ARRAY_SIZE(pdata->gpio_defaults); i++) {
-			if (pdata->gpio_defaults[i]) {
-				wm8994_set_bits(wm8994, WM8994_GPIO_1 + i,
-						0xffff,
-						pdata->gpio_defaults[i]);
-			}
+	wm8994->irq_base = pdata->irq_base;
+	wm8994->gpio_base = pdata->gpio_base;
+
+	/* GPIO configuration is only applied if it's non-zero */
+	for (i = 0; i < ARRAY_SIZE(pdata->gpio_defaults); i++) {
+		if (pdata->gpio_defaults[i]) {
+			wm8994_set_bits(wm8994, WM8994_GPIO_1 + i,
+					0xffff, pdata->gpio_defaults[i]);
 		}
+	}
 
-		wm8994->ldo_ena_always_driven = pdata->ldo_ena_always_driven;
+	wm8994->ldo_ena_always_driven = pdata->ldo_ena_always_driven;
 
-		if (pdata->spkmode_pu)
-			pulls |= WM8994_SPKMODE_PU;
-	}
+	if (pdata->spkmode_pu)
+		pulls |= WM8994_SPKMODE_PU;
 
 	/* Disable unneeded pulls */
 	wm8994_set_bits(wm8994, WM8994_PULL_CONTROL_2,
diff --git a/include/linux/mfd/wm8994/core.h b/include/linux/mfd/wm8994/core.h
index 1f173306bf05..ae5c249530b4 100644
--- a/include/linux/mfd/wm8994/core.h
+++ b/include/linux/mfd/wm8994/core.h
@@ -19,6 +19,8 @@
 #include <linux/interrupt.h>
 #include <linux/regmap.h>
 
+#include <linux/mfd/wm8994/pdata.h>
+
 enum wm8994_type {
 	WM8994 = 0,
 	WM8958 = 1,
@@ -55,6 +57,8 @@ struct regulator_bulk_data;
 struct wm8994 {
 	struct mutex irq_lock;
 
+	struct wm8994_pdata pdata;
+
 	enum wm8994_type type;
 	int revision;
 	int cust_id;
-- 
cgit v1.2.3-55-g7522


From 1ad7e89940d5ac411928189e1a4a01901dbf590f Mon Sep 17 00:00:00 2001
From: Stephen Warren
Date: Thu, 8 Nov 2012 16:12:25 -0800
Subject: block: store partition_meta_info.uuid as a string

This will allow other types of UUID to be stored here, aside from true
UUIDs.  This also simplifies code that uses this field, since it's usually
constructed from a, used as a, or compared to other, strings.

Note: A simplistic approach here would be to set uuid_str[36]=0 whenever a
/PARTNROFF option was found to be present.  However, this modifies the
input string, and causes subsequent calls to devt_from_partuuid() not to
see the /PARTNROFF option, which causes different results.  In order to
avoid misleading future maintainers, this parameter is marked const.

Signed-off-by: Stephen Warren <swarren@nvidia.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Will Drewry <wad@chromium.org>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c          |  8 +-------
 block/partitions/efi.c |  7 +------
 include/linux/genhd.h  |  8 ++++++--
 init/do_mounts.c       | 28 +++++++++++++++++-----------
 4 files changed, 25 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/block/genhd.c b/block/genhd.c
index 6cace663a80e..b281f3a2d26a 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -743,7 +743,6 @@ void __init printk_all_partitions(void)
 		struct hd_struct *part;
 		char name_buf[BDEVNAME_SIZE];
 		char devt_buf[BDEVT_SIZE];
-		char uuid_buf[PARTITION_META_INFO_UUIDLTH * 2 + 5];
 
 		/*
 		 * Don't show empty devices or things that have been
@@ -762,16 +761,11 @@ void __init printk_all_partitions(void)
 		while ((part = disk_part_iter_next(&piter))) {
 			bool is_part0 = part == &disk->part0;
 
-			uuid_buf[0] = '\0';
-			if (part->info)
-				snprintf(uuid_buf, sizeof(uuid_buf), "%pU",
-					 part->info->uuid);
-
 			printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
 			       bdevt_str(part_devt(part), devt_buf),
 			       (unsigned long long)part_nr_sects_read(part) >> 1
 			       , disk_name(disk, part->partno, name_buf),
-			       uuid_buf);
+			       part->info ? part->info->uuid : "");
 			if (is_part0) {
 				if (disk->driverfs_dev != NULL &&
 				    disk->driverfs_dev->driver != NULL)
diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index 6296b403c67a..b62fb88b8711 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -620,7 +620,6 @@ int efi_partition(struct parsed_partitions *state)
 	gpt_entry *ptes = NULL;
 	u32 i;
 	unsigned ssz = bdev_logical_block_size(state->bdev) / 512;
-	u8 unparsed_guid[37];
 
 	if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) {
 		kfree(gpt);
@@ -649,11 +648,7 @@ int efi_partition(struct parsed_partitions *state)
 			state->parts[i + 1].flags = ADDPART_FLAG_RAID;
 
 		info = &state->parts[i + 1].info;
-		/* Instead of doing a manual swap to big endian, reuse the
-		 * common ASCII hex format as the interim.
-		 */
-		efi_guid_unparse(&ptes[i].unique_partition_guid, unparsed_guid);
-		part_pack_uuid(unparsed_guid, info->uuid);
+		efi_guid_unparse(&ptes[i].unique_partition_guid, info->uuid);
 
 		/* Naively convert UTF16-LE to 7 bits. */
 		label_max = min(sizeof(info->volname) - 1,
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 4f440b3e89fe..79b8bba19363 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -88,10 +88,14 @@ struct disk_stats {
 };
 
 #define PARTITION_META_INFO_VOLNAMELTH	64
-#define PARTITION_META_INFO_UUIDLTH	16
+/*
+ * Enough for the string representation of any kind of UUID plus NULL.
+ * EFI UUID is 36 characters. MSDOS UUID is 11 characters.
+ */
+#define PARTITION_META_INFO_UUIDLTH	37
 
 struct partition_meta_info {
-	u8 uuid[PARTITION_META_INFO_UUIDLTH];	/* always big endian */
+	char uuid[PARTITION_META_INFO_UUIDLTH];
 	u8 volname[PARTITION_META_INFO_VOLNAMELTH];
 };
 
diff --git a/init/do_mounts.c b/init/do_mounts.c
index f8a66424360d..b28ec5819325 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -69,23 +69,28 @@ __setup("ro", readonly);
 __setup("rw", readwrite);
 
 #ifdef CONFIG_BLOCK
+struct uuidcmp {
+	const char *uuid;
+	int len;
+};
+
 /**
  * match_dev_by_uuid - callback for finding a partition using its uuid
  * @dev:	device passed in by the caller
- * @data:	opaque pointer to a 36 byte char array with a UUID
+ * @data:	opaque pointer to the desired struct uuidcmp to match
  *
  * Returns 1 if the device matches, and 0 otherwise.
  */
 static int match_dev_by_uuid(struct device *dev, void *data)
 {
-	u8 *uuid = data;
+	struct uuidcmp *cmp = data;
 	struct hd_struct *part = dev_to_part(dev);
 
 	if (!part->info)
 		goto no_match;
 
-	if (memcmp(uuid, part->info->uuid, sizeof(part->info->uuid)))
-			goto no_match;
+	if (strncasecmp(cmp->uuid, part->info->uuid, cmp->len))
+		goto no_match;
 
 	return 1;
 no_match:
@@ -95,7 +100,7 @@ no_match:
 
 /**
  * devt_from_partuuid - looks up the dev_t of a partition by its UUID
- * @uuid:	min 36 byte char array containing a hex ascii UUID
+ * @uuid:	char array containing ascii UUID
  *
  * The function will return the first partition which contains a matching
  * UUID value in its partition_meta_info struct.  This does not search
@@ -106,11 +111,11 @@ no_match:
  *
  * Returns the matching dev_t on success or 0 on failure.
  */
-static dev_t devt_from_partuuid(char *uuid_str)
+static dev_t devt_from_partuuid(const char *uuid_str)
 {
 	dev_t res = 0;
+	struct uuidcmp cmp;
 	struct device *dev = NULL;
-	u8 uuid[16];
 	struct gendisk *disk;
 	struct hd_struct *part;
 	int offset = 0;
@@ -118,6 +123,9 @@ static dev_t devt_from_partuuid(char *uuid_str)
 	if (strlen(uuid_str) < 36)
 		goto done;
 
+	cmp.uuid = uuid_str;
+	cmp.len = 36;
+
 	/* Check for optional partition number offset attributes. */
 	if (uuid_str[36]) {
 		char c = 0;
@@ -134,10 +142,8 @@ static dev_t devt_from_partuuid(char *uuid_str)
 		}
 	}
 
-	/* Pack the requested UUID in the expected format. */
-	part_pack_uuid(uuid_str, uuid);
-
-	dev = class_find_device(&block_class, NULL, uuid, &match_dev_by_uuid);
+	dev = class_find_device(&block_class, NULL, &cmp,
+				&match_dev_by_uuid);
 	if (!dev)
 		goto done;
 
-- 
cgit v1.2.3-55-g7522


From 8d8be8389f1818b07505bbf2ec3fb2d556d84496 Mon Sep 17 00:00:00 2001
From: Neal Cardwell
Date: Thu, 22 Nov 2012 17:48:59 +0000
Subject: tcp: remove dead prototype for tcp_v4_get_peer()

This function no longer exists.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6feeccd83dd7..3202bde2a741 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -369,7 +369,6 @@ extern void tcp_shutdown (struct sock *sk, int how);
 extern void tcp_v4_early_demux(struct sk_buff *skb);
 extern int tcp_v4_rcv(struct sk_buff *skb);
 
-extern struct inet_peer *tcp_v4_get_peer(struct sock *sk);
 extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
 extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		       size_t size);
-- 
cgit v1.2.3-55-g7522


From 93272e07d8539cddce9a2a17b7b0de1326957599 Mon Sep 17 00:00:00 2001
From: Jean-Christophe PLAGNIOL-VILLARD
Date: Wed, 21 Nov 2012 05:38:07 +0000
Subject: net: add micrel KSZ8873MLL switch support

this will allow to detect the link between the switch and the soc

Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c   | 44 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/micrel_phy.h |  1 +
 2 files changed, 45 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 2165d5fdb8c0..b983596abcbb 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -127,6 +127,39 @@ static int ks8051_config_init(struct phy_device *phydev)
 	return 0;
 }
 
+#define KSZ8873MLL_GLOBAL_CONTROL_4	0x06
+#define KSZ8873MLL_GLOBAL_CONTROL_4_DUPLEX	(1 << 6)
+#define KSZ8873MLL_GLOBAL_CONTROL_4_SPEED	(1 << 4)
+int ksz8873mll_read_status(struct phy_device *phydev)
+{
+	int regval;
+
+	/* dummy read */
+	regval = phy_read(phydev, KSZ8873MLL_GLOBAL_CONTROL_4);
+
+	regval = phy_read(phydev, KSZ8873MLL_GLOBAL_CONTROL_4);
+
+	if (regval & KSZ8873MLL_GLOBAL_CONTROL_4_DUPLEX)
+		phydev->duplex = DUPLEX_HALF;
+	else
+		phydev->duplex = DUPLEX_FULL;
+
+	if (regval & KSZ8873MLL_GLOBAL_CONTROL_4_SPEED)
+		phydev->speed = SPEED_10;
+	else
+		phydev->speed = SPEED_100;
+
+	phydev->link = 1;
+	phydev->pause = phydev->asym_pause = 0;
+
+	return 0;
+}
+
+static int ksz8873mll_config_aneg(struct phy_device *phydev)
+{
+	return 0;
+}
+
 static struct phy_driver ksphy_driver[] = {
 {
 	.phy_id		= PHY_ID_KS8737,
@@ -204,6 +237,16 @@ static struct phy_driver ksphy_driver[] = {
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= ksz9021_config_intr,
 	.driver		= { .owner = THIS_MODULE, },
+}, {
+	.phy_id		= PHY_ID_KSZ8873MLL,
+	.phy_id_mask	= 0x00fffff0,
+	.name		= "Micrel KSZ8873MLL Switch",
+	.features	= (SUPPORTED_Pause | SUPPORTED_Asym_Pause),
+	.flags		= PHY_HAS_MAGICANEG,
+	.config_init	= kszphy_config_init,
+	.config_aneg	= ksz8873mll_config_aneg,
+	.read_status	= ksz8873mll_read_status,
+	.driver		= { .owner = THIS_MODULE, },
 } };
 
 static int __init ksphy_init(void)
@@ -232,6 +275,7 @@ static struct mdio_device_id __maybe_unused micrel_tbl[] = {
 	{ PHY_ID_KSZ8021, 0x00ffffff },
 	{ PHY_ID_KSZ8041, 0x00fffff0 },
 	{ PHY_ID_KSZ8051, 0x00fffff0 },
+	{ PHY_ID_KSZ8873MLL, 0x00fffff0 },
 	{ }
 };
 
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index de201203bc7c..adfe8c058f29 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -15,6 +15,7 @@
 
 #define MICREL_PHY_ID_MASK	0x00fffff0
 
+#define PHY_ID_KSZ8873MLL	0x000e7237
 #define PHY_ID_KSZ9021		0x00221610
 #define PHY_ID_KS8737		0x00221720
 #define PHY_ID_KSZ8021		0x00221555
-- 
cgit v1.2.3-55-g7522


From e5f5762177be52fde50ccba88938d66b5103c8e0 Mon Sep 17 00:00:00 2001
From: Li Haifeng
Date: Fri, 23 Nov 2012 21:55:19 +0100
Subject: PM / Freezer: Fixup compile error of try_to_freeze_nowarn()

If FREEZER is not defined, the error as following will be throw
when compiled.
arch/arm/kernel/signal.c:645: error: implicit declaration of function
'try_to_freeze_nowarn'

Signed-off-by: Haifeng Li <omycle@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/freezer.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index d09af4b67cf1..b90091af5798 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -177,6 +177,7 @@ static inline int freeze_kernel_threads(void) { return -ENOSYS; }
 static inline void thaw_processes(void) {}
 static inline void thaw_kernel_threads(void) {}
 
+static inline bool try_to_freeze_nowarn(void) { return false; }
 static inline bool try_to_freeze(void) { return false; }
 
 static inline void freezer_do_not_count(void) {}
-- 
cgit v1.2.3-55-g7522


From 051c7788bcb92f2e98ef86e86651e0420765b121 Mon Sep 17 00:00:00 2001
From: Sumit Semwal
Date: Thu, 14 Jun 2012 10:37:35 -0300
Subject: [media] v4l: Add DMABUF as a memory type

Adds DMABUF memory type to v4l framework. Also adds the related file
descriptor in v4l2_plane and v4l2_buffer.
   [original work in the PoC for buffer sharing]

Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Signed-off-by: Sumit Semwal <sumit.semwal@ti.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Tested-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c | 18 ++++++++++++++++++
 drivers/media/v4l2-core/v4l2-ioctl.c          |  1 +
 include/uapi/linux/videodev2.h                |  7 +++++++
 3 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index 83ffb6436baf..cc5998b31463 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -297,6 +297,7 @@ struct v4l2_plane32 {
 	union {
 		__u32		mem_offset;
 		compat_long_t	userptr;
+		__s32		fd;
 	} m;
 	__u32			data_offset;
 	__u32			reserved[11];
@@ -318,6 +319,7 @@ struct v4l2_buffer32 {
 		__u32           offset;
 		compat_long_t   userptr;
 		compat_caddr_t  planes;
+		__s32		fd;
 	} m;
 	__u32			length;
 	__u32			reserved2;
@@ -341,6 +343,9 @@ static int get_v4l2_plane32(struct v4l2_plane *up, struct v4l2_plane32 *up32,
 		up_pln = compat_ptr(p);
 		if (put_user((unsigned long)up_pln, &up->m.userptr))
 			return -EFAULT;
+	} else if (memory == V4L2_MEMORY_DMABUF) {
+		if (copy_in_user(&up->m.fd, &up32->m.fd, sizeof(int)))
+			return -EFAULT;
 	} else {
 		if (copy_in_user(&up->m.mem_offset, &up32->m.mem_offset,
 					sizeof(__u32)))
@@ -364,6 +369,11 @@ static int put_v4l2_plane32(struct v4l2_plane *up, struct v4l2_plane32 *up32,
 		if (copy_in_user(&up32->m.mem_offset, &up->m.mem_offset,
 					sizeof(__u32)))
 			return -EFAULT;
+	/* For DMABUF, driver might've set up the fd, so copy it back. */
+	if (memory == V4L2_MEMORY_DMABUF)
+		if (copy_in_user(&up32->m.fd, &up->m.fd,
+					sizeof(int)))
+			return -EFAULT;
 
 	return 0;
 }
@@ -446,6 +456,10 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 			if (get_user(kp->m.offset, &up->m.offset))
 				return -EFAULT;
 			break;
+		case V4L2_MEMORY_DMABUF:
+			if (get_user(kp->m.fd, &up->m.fd))
+				return -EFAULT;
+			break;
 		}
 	}
 
@@ -510,6 +524,10 @@ static int put_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 			if (put_user(kp->m.offset, &up->m.offset))
 				return -EFAULT;
 			break;
+		case V4L2_MEMORY_DMABUF:
+			if (put_user(kp->m.fd, &up->m.fd))
+				return -EFAULT;
+			break;
 		}
 	}
 
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 8f388ff31ebb..530a67e3fe0e 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -155,6 +155,7 @@ static const char *v4l2_memory_names[] = {
 	[V4L2_MEMORY_MMAP]    = "mmap",
 	[V4L2_MEMORY_USERPTR] = "userptr",
 	[V4L2_MEMORY_OVERLAY] = "overlay",
+	[V4L2_MEMORY_DMABUF] = "dmabuf",
 };
 
 #define prt_names(a, arr) (((unsigned)(a)) < ARRAY_SIZE(arr) ? arr[a] : "unknown")
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 2fff7ff3e05b..91ac83b21c20 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -186,6 +186,7 @@ enum v4l2_memory {
 	V4L2_MEMORY_MMAP             = 1,
 	V4L2_MEMORY_USERPTR          = 2,
 	V4L2_MEMORY_OVERLAY          = 3,
+	V4L2_MEMORY_DMABUF           = 4,
 };
 
 /* see also http://vektor.theorem.ca/graphics/ycbcr/ */
@@ -602,6 +603,8 @@ struct v4l2_requestbuffers {
  *			should be passed to mmap() called on the video node)
  * @userptr:		when memory is V4L2_MEMORY_USERPTR, a userspace pointer
  *			pointing to this plane
+ * @fd:			when memory is V4L2_MEMORY_DMABUF, a userspace file
+ *			descriptor associated with this plane
  * @data_offset:	offset in the plane to the start of data; usually 0,
  *			unless there is a header in front of the data
  *
@@ -616,6 +619,7 @@ struct v4l2_plane {
 	union {
 		__u32		mem_offset;
 		unsigned long	userptr;
+		__s32		fd;
 	} m;
 	__u32			data_offset;
 	__u32			reserved[11];
@@ -640,6 +644,8 @@ struct v4l2_plane {
  *		(or a "cookie" that should be passed to mmap() as offset)
  * @userptr:	for non-multiplanar buffers with memory == V4L2_MEMORY_USERPTR;
  *		a userspace pointer pointing to this buffer
+ * @fd:		for non-multiplanar buffers with memory == V4L2_MEMORY_DMABUF;
+ *		a userspace file descriptor associated with this buffer
  * @planes:	for multiplanar buffers; userspace pointer to the array of plane
  *		info structs for this buffer
  * @length:	size in bytes of the buffer (NOT its payload) for single-plane
@@ -666,6 +672,7 @@ struct v4l2_buffer {
 		__u32           offset;
 		unsigned long   userptr;
 		struct v4l2_plane *planes;
+		__s32		fd;
 	} m;
 	__u32			length;
 	__u32			reserved2;
-- 
cgit v1.2.3-55-g7522


From c538404869b69db543ce23cf041192c192a65330 Mon Sep 17 00:00:00 2001
From: Sumit Semwal
Date: Thu, 14 Jun 2012 10:37:37 -0300
Subject: [media] v4l: vb2: add support for shared buffer (dma_buf)

This patch adds support for DMABUF memory type in videobuf2. It calls relevant
APIs of dma_buf for v4l reqbuf / qbuf / dqbuf operations.
For this version, the support is for videobuf2 as a user of the shared buffer;
so the allocation of the buffer is done outside of V4L2. [A sample allocator of
dma-buf shared buffer is given at [1]]
[1]: Rob Clark's DRM:
   https://github.com/robclark/kernel-omap4/commits/drmplane-dmabuf
   [original work in the PoC for buffer sharing]

Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Signed-off-by: Sumit Semwal <sumit.semwal@ti.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Tested-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/v4l2-core/Kconfig          |   1 +
 drivers/media/v4l2-core/videobuf2-core.c | 206 ++++++++++++++++++++++++++++++-
 include/media/videobuf2-core.h           |  27 ++++
 3 files changed, 231 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/Kconfig b/drivers/media/v4l2-core/Kconfig
index 0c54e19d9944..2e787ccbbcd5 100644
--- a/drivers/media/v4l2-core/Kconfig
+++ b/drivers/media/v4l2-core/Kconfig
@@ -59,6 +59,7 @@ config VIDEOBUF_DVB
 
 # Used by drivers that need Videobuf2 modules
 config VIDEOBUF2_CORE
+	select DMA_SHARED_BUFFER
 	tristate
 
 config VIDEOBUF2_MEMOPS
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 432df119af27..a51dad6bd394 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -108,6 +108,36 @@ static void __vb2_buf_userptr_put(struct vb2_buffer *vb)
 	}
 }
 
+/**
+ * __vb2_plane_dmabuf_put() - release memory associated with
+ * a DMABUF shared plane
+ */
+static void __vb2_plane_dmabuf_put(struct vb2_queue *q, struct vb2_plane *p)
+{
+	if (!p->mem_priv)
+		return;
+
+	if (p->dbuf_mapped)
+		call_memop(q, unmap_dmabuf, p->mem_priv);
+
+	call_memop(q, detach_dmabuf, p->mem_priv);
+	dma_buf_put(p->dbuf);
+	memset(p, 0, sizeof(*p));
+}
+
+/**
+ * __vb2_buf_dmabuf_put() - release memory associated with
+ * a DMABUF shared buffer
+ */
+static void __vb2_buf_dmabuf_put(struct vb2_buffer *vb)
+{
+	struct vb2_queue *q = vb->vb2_queue;
+	unsigned int plane;
+
+	for (plane = 0; plane < vb->num_planes; ++plane)
+		__vb2_plane_dmabuf_put(q, &vb->planes[plane]);
+}
+
 /**
  * __setup_offsets() - setup unique offsets ("cookies") for every plane in
  * every buffer on the queue
@@ -230,6 +260,8 @@ static void __vb2_free_mem(struct vb2_queue *q, unsigned int buffers)
 		/* Free MMAP buffers or release USERPTR buffers */
 		if (q->memory == V4L2_MEMORY_MMAP)
 			__vb2_buf_mem_free(vb);
+		else if (q->memory == V4L2_MEMORY_DMABUF)
+			__vb2_buf_dmabuf_put(vb);
 		else
 			__vb2_buf_userptr_put(vb);
 	}
@@ -362,6 +394,8 @@ static void __fill_v4l2_buffer(struct vb2_buffer *vb, struct v4l2_buffer *b)
 			b->m.offset = vb->v4l2_planes[0].m.mem_offset;
 		else if (q->memory == V4L2_MEMORY_USERPTR)
 			b->m.userptr = vb->v4l2_planes[0].m.userptr;
+		else if (q->memory == V4L2_MEMORY_DMABUF)
+			b->m.fd = vb->v4l2_planes[0].m.fd;
 	}
 
 	/*
@@ -453,6 +487,20 @@ static int __verify_mmap_ops(struct vb2_queue *q)
 	return 0;
 }
 
+/**
+ * __verify_dmabuf_ops() - verify that all memory operations required for
+ * DMABUF queue type have been provided
+ */
+static int __verify_dmabuf_ops(struct vb2_queue *q)
+{
+	if (!(q->io_modes & VB2_DMABUF) || !q->mem_ops->attach_dmabuf ||
+	    !q->mem_ops->detach_dmabuf  || !q->mem_ops->map_dmabuf ||
+	    !q->mem_ops->unmap_dmabuf)
+		return -EINVAL;
+
+	return 0;
+}
+
 /**
  * __verify_memory_type() - Check whether the memory type and buffer type
  * passed to a buffer operation are compatible with the queue.
@@ -460,7 +508,8 @@ static int __verify_mmap_ops(struct vb2_queue *q)
 static int __verify_memory_type(struct vb2_queue *q,
 		enum v4l2_memory memory, enum v4l2_buf_type type)
 {
-	if (memory != V4L2_MEMORY_MMAP && memory != V4L2_MEMORY_USERPTR) {
+	if (memory != V4L2_MEMORY_MMAP && memory != V4L2_MEMORY_USERPTR &&
+	    memory != V4L2_MEMORY_DMABUF) {
 		dprintk(1, "reqbufs: unsupported memory type\n");
 		return -EINVAL;
 	}
@@ -484,6 +533,11 @@ static int __verify_memory_type(struct vb2_queue *q,
 		return -EINVAL;
 	}
 
+	if (memory == V4L2_MEMORY_DMABUF && __verify_dmabuf_ops(q)) {
+		dprintk(1, "reqbufs: DMABUF for current setup unsupported\n");
+		return -EINVAL;
+	}
+
 	/*
 	 * Place the busy tests at the end: -EBUSY can be ignored when
 	 * create_bufs is called with count == 0, but count == 0 should still
@@ -845,6 +899,16 @@ static void __fill_vb2_buffer(struct vb2_buffer *vb, const struct v4l2_buffer *b
 					b->m.planes[plane].length;
 			}
 		}
+		if (b->memory == V4L2_MEMORY_DMABUF) {
+			for (plane = 0; plane < vb->num_planes; ++plane) {
+				v4l2_planes[plane].m.fd =
+					b->m.planes[plane].m.fd;
+				v4l2_planes[plane].length =
+					b->m.planes[plane].length;
+				v4l2_planes[plane].data_offset =
+					b->m.planes[plane].data_offset;
+			}
+		}
 	} else {
 		/*
 		 * Single-planar buffers do not use planes array,
@@ -859,6 +923,13 @@ static void __fill_vb2_buffer(struct vb2_buffer *vb, const struct v4l2_buffer *b
 			v4l2_planes[0].m.userptr = b->m.userptr;
 			v4l2_planes[0].length = b->length;
 		}
+
+		if (b->memory == V4L2_MEMORY_DMABUF) {
+			v4l2_planes[0].m.fd = b->m.fd;
+			v4l2_planes[0].length = b->length;
+			v4l2_planes[0].data_offset = 0;
+		}
+
 	}
 
 	vb->v4l2_buf.field = b->field;
@@ -958,6 +1029,107 @@ static int __qbuf_mmap(struct vb2_buffer *vb, const struct v4l2_buffer *b)
 	return 0;
 }
 
+/**
+ * __qbuf_dmabuf() - handle qbuf of a DMABUF buffer
+ */
+static int __qbuf_dmabuf(struct vb2_buffer *vb, const struct v4l2_buffer *b)
+{
+	struct v4l2_plane planes[VIDEO_MAX_PLANES];
+	struct vb2_queue *q = vb->vb2_queue;
+	void *mem_priv;
+	unsigned int plane;
+	int ret;
+	int write = !V4L2_TYPE_IS_OUTPUT(q->type);
+
+	/* Verify and copy relevant information provided by the userspace */
+	__fill_vb2_buffer(vb, b, planes);
+
+	for (plane = 0; plane < vb->num_planes; ++plane) {
+		struct dma_buf *dbuf = dma_buf_get(planes[plane].m.fd);
+
+		if (IS_ERR_OR_NULL(dbuf)) {
+			dprintk(1, "qbuf: invalid dmabuf fd for plane %d\n",
+				plane);
+			ret = -EINVAL;
+			goto err;
+		}
+
+		/* use DMABUF size if length is not provided */
+		if (planes[plane].length == 0)
+			planes[plane].length = dbuf->size;
+
+		if (planes[plane].length < planes[plane].data_offset +
+		    q->plane_sizes[plane]) {
+			ret = -EINVAL;
+			goto err;
+		}
+
+		/* Skip the plane if already verified */
+		if (dbuf == vb->planes[plane].dbuf &&
+		    vb->v4l2_planes[plane].length == planes[plane].length) {
+			dma_buf_put(dbuf);
+			continue;
+		}
+
+		dprintk(1, "qbuf: buffer for plane %d changed\n", plane);
+
+		/* Release previously acquired memory if present */
+		__vb2_plane_dmabuf_put(q, &vb->planes[plane]);
+		memset(&vb->v4l2_planes[plane], 0, sizeof(struct v4l2_plane));
+
+		/* Acquire each plane's memory */
+		mem_priv = call_memop(q, attach_dmabuf, q->alloc_ctx[plane],
+			dbuf, planes[plane].length, write);
+		if (IS_ERR(mem_priv)) {
+			dprintk(1, "qbuf: failed to attach dmabuf\n");
+			ret = PTR_ERR(mem_priv);
+			dma_buf_put(dbuf);
+			goto err;
+		}
+
+		vb->planes[plane].dbuf = dbuf;
+		vb->planes[plane].mem_priv = mem_priv;
+	}
+
+	/* TODO: This pins the buffer(s) with  dma_buf_map_attachment()).. but
+	 * really we want to do this just before the DMA, not while queueing
+	 * the buffer(s)..
+	 */
+	for (plane = 0; plane < vb->num_planes; ++plane) {
+		ret = call_memop(q, map_dmabuf, vb->planes[plane].mem_priv);
+		if (ret) {
+			dprintk(1, "qbuf: failed to map dmabuf for plane %d\n",
+				plane);
+			goto err;
+		}
+		vb->planes[plane].dbuf_mapped = 1;
+	}
+
+	/*
+	 * Call driver-specific initialization on the newly acquired buffer,
+	 * if provided.
+	 */
+	ret = call_qop(q, buf_init, vb);
+	if (ret) {
+		dprintk(1, "qbuf: buffer initialization failed\n");
+		goto err;
+	}
+
+	/*
+	 * Now that everything is in order, copy relevant information
+	 * provided by userspace.
+	 */
+	for (plane = 0; plane < vb->num_planes; ++plane)
+		vb->v4l2_planes[plane] = planes[plane];
+
+	return 0;
+err:
+	/* In case of errors, release planes that were already acquired */
+	__vb2_buf_dmabuf_put(vb);
+
+	return ret;
+}
+
 /**
  * __enqueue_in_driver() - enqueue a vb2_buffer in driver for processing
  */
@@ -982,6 +1154,9 @@ static int __buf_prepare(struct vb2_buffer *vb, const struct v4l2_buffer *b)
 	case V4L2_MEMORY_USERPTR:
 		ret = __qbuf_userptr(vb, b);
 		break;
+	case V4L2_MEMORY_DMABUF:
+		ret = __qbuf_dmabuf(vb, b);
+		break;
 	default:
 		WARN(1, "Invalid queue type\n");
 		ret = -EINVAL;
@@ -1302,6 +1477,30 @@ int vb2_wait_for_all_buffers(struct vb2_queue *q)
 }
 EXPORT_SYMBOL_GPL(vb2_wait_for_all_buffers);
 
+/**
+ * __vb2_dqbuf() - bring back the buffer to the DEQUEUED state
+ */
+static void __vb2_dqbuf(struct vb2_buffer *vb)
+{
+	struct vb2_queue *q = vb->vb2_queue;
+	unsigned int i;
+
+	/* nothing to do if the buffer is already dequeued */
+	if (vb->state == VB2_BUF_STATE_DEQUEUED)
+		return;
+
+	vb->state = VB2_BUF_STATE_DEQUEUED;
+
+	/* unmap DMABUF buffer */
+	if (q->memory == V4L2_MEMORY_DMABUF)
+		for (i = 0; i < vb->num_planes; ++i) {
+			if (!vb->planes[i].dbuf_mapped)
+				continue;
+			call_memop(q, unmap_dmabuf, vb->planes[i].mem_priv);
+			vb->planes[i].dbuf_mapped = 0;
+		}
+}
+
 /**
  * vb2_dqbuf() - Dequeue a buffer to the userspace
  * @q:		videobuf2 queue
@@ -1363,11 +1562,12 @@ int vb2_dqbuf(struct vb2_queue *q, struct v4l2_buffer *b, bool nonblocking)
 	__fill_v4l2_buffer(vb, b);
 	/* Remove from videobuf queue */
 	list_del(&vb->queued_entry);
+	/* go back to dequeued state */
+	__vb2_dqbuf(vb);
 
 	dprintk(1, "dqbuf of buffer %d, with state %d\n",
 			vb->v4l2_buf.index, vb->state);
 
-	vb->state = VB2_BUF_STATE_DEQUEUED;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(vb2_dqbuf);
@@ -1406,7 +1606,7 @@ static void __vb2_queue_cancel(struct vb2_queue *q)
 	 * Reinitialize all buffers for next use.
 	 */
 	for (i = 0; i < q->num_buffers; ++i)
-		q->bufs[i]->state = VB2_BUF_STATE_DEQUEUED;
+		__vb2_dqbuf(q->bufs[i]);
 }
 
 /**
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index e04252a9fea6..689ae4ac2572 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -16,6 +16,7 @@
 #include <linux/mutex.h>
 #include <linux/poll.h>
 #include <linux/videodev2.h>
+#include <linux/dma-buf.h>
 
 struct vb2_alloc_ctx;
 struct vb2_fileio_data;
@@ -41,6 +42,20 @@ struct vb2_fileio_data;
  *		 argument to other ops in this structure
  * @put_userptr: inform the allocator that a USERPTR buffer will no longer
  *		 be used
+ * @attach_dmabuf: attach a shared struct dma_buf for a hardware operation;
+ *		   used for DMABUF memory types; alloc_ctx is the alloc context
+ *		   dbuf is the shared dma_buf; returns NULL on failure;
+ *		   allocator private per-buffer structure on success;
+ *		   this needs to be used for further accesses to the buffer
+ * @detach_dmabuf: inform the exporter of the buffer that the current DMABUF
+ *		   buffer is no longer used; the buf_priv argument is the
+ *		   allocator private per-buffer structure previously returned
+ *		   from the attach_dmabuf callback
+ * @map_dmabuf: request for access to the dmabuf from allocator; the allocator
+ *		of dmabuf is informed that this driver is going to use the
+ *		dmabuf
+ * @unmap_dmabuf: releases access control to the dmabuf - allocator is notified
+ *		  that this driver is done using the dmabuf for now
  * @vaddr:	return a kernel virtual address to a given memory buffer
  *		associated with the passed private structure or NULL if no
  *		such mapping exists
@@ -56,6 +71,8 @@ struct vb2_fileio_data;
  * Required ops for USERPTR types: get_userptr, put_userptr.
  * Required ops for MMAP types: alloc, put, num_users, mmap.
  * Required ops for read/write access types: alloc, put, num_users, vaddr
+ * Required ops for DMABUF types: attach_dmabuf, detach_dmabuf, map_dmabuf,
+ *				  unmap_dmabuf.
  */
 struct vb2_mem_ops {
 	void		*(*alloc)(void *alloc_ctx, unsigned long size);
@@ -65,6 +82,12 @@ struct vb2_mem_ops {
 					unsigned long size, int write);
 	void		(*put_userptr)(void *buf_priv);
 
+	void		*(*attach_dmabuf)(void *alloc_ctx, struct dma_buf *dbuf,
+				unsigned long size, int write);
+	void		(*detach_dmabuf)(void *buf_priv);
+	int		(*map_dmabuf)(void *buf_priv);
+	void		(*unmap_dmabuf)(void *buf_priv);
+
 	void		*(*vaddr)(void *buf_priv);
 	void		*(*cookie)(void *buf_priv);
 
@@ -75,6 +98,8 @@ struct vb2_mem_ops {
 
 struct vb2_plane {
 	void			*mem_priv;
+	struct dma_buf		*dbuf;
+	unsigned int		dbuf_mapped;
 };
 
 /**
@@ -83,12 +108,14 @@ struct vb2_plane {
  * @VB2_USERPTR:	driver supports USERPTR with streaming API
  * @VB2_READ:		driver supports read() style access
  * @VB2_WRITE:		driver supports write() style access
+ * @VB2_DMABUF:		driver supports DMABUF with streaming API
  */
 enum vb2_io_modes {
 	VB2_MMAP	= (1 << 0),
 	VB2_USERPTR	= (1 << 1),
 	VB2_READ	= (1 << 2),
 	VB2_WRITE	= (1 << 3),
+	VB2_DMABUF	= (1 << 4),
 };
 
 /**
-- 
cgit v1.2.3-55-g7522


From 3e0c2f2046665bf580273b69ab18d9c76a550e34 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski
Date: Thu, 14 Jun 2012 10:37:43 -0300
Subject: [media] v4l: vb2: add prepare/finish callbacks to allocators

This patch adds support for prepare/finish callbacks in VB2 allocators. These
callback are used for buffer flushing.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Tested-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/v4l2-core/videobuf2-core.c | 11 +++++++++++
 include/media/videobuf2-core.h           |  7 +++++++
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index a51dad6bd394..613dea16a304 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -844,6 +844,7 @@ void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state)
 {
 	struct vb2_queue *q = vb->vb2_queue;
 	unsigned long flags;
+	unsigned int plane;
 
 	if (vb->state != VB2_BUF_STATE_ACTIVE)
 		return;
@@ -854,6 +855,10 @@ void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state)
 	dprintk(4, "Done processing on buffer %d, state: %d\n",
 			vb->v4l2_buf.index, vb->state);
 
+	/* sync buffers */
+	for (plane = 0; plane < vb->num_planes; ++plane)
+		call_memop(q, finish, vb->planes[plane].mem_priv);
+
 	/* Add the buffer to the done buffers list */
 	spin_lock_irqsave(&q->done_lock, flags);
 	vb->state = state;
@@ -1136,9 +1141,15 @@ err:
 static void __enqueue_in_driver(struct vb2_buffer *vb)
 {
 	struct vb2_queue *q = vb->vb2_queue;
+	unsigned int plane;
 
 	vb->state = VB2_BUF_STATE_ACTIVE;
 	atomic_inc(&q->queued_count);
+
+	/* sync buffers */
+	for (plane = 0; plane < vb->num_planes; ++plane)
+		call_memop(q, prepare, vb->planes[plane].mem_priv);
+
 	q->ops->buf_queue(vb);
 }
 
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 689ae4ac2572..24b9c90194f2 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -56,6 +56,10 @@ struct vb2_fileio_data;
  *		dmabuf
  * @unmap_dmabuf: releases access control to the dmabuf - allocator is notified
  *		  that this driver is done using the dmabuf for now
+ * @prepare:	called every time the buffer is passed from userspace to the
+ *		driver, useful for cache synchronisation, optional
+ * @finish:	called every time the buffer is passed back from the driver
+ *		to the userspace, also optional
  * @vaddr:	return a kernel virtual address to a given memory buffer
  *		associated with the passed private structure or NULL if no
  *		such mapping exists
@@ -82,6 +86,9 @@ struct vb2_mem_ops {
 					unsigned long size, int write);
 	void		(*put_userptr)(void *buf_priv);
 
+	void		(*prepare)(void *buf_priv);
+	void		(*finish)(void *buf_priv);
+
 	void		*(*attach_dmabuf)(void *alloc_ctx, struct dma_buf *dbuf,
 				unsigned long size, int write);
 	void		(*detach_dmabuf)(void *buf_priv);
-- 
cgit v1.2.3-55-g7522


From c60520fa50cd86d64bc8ebb34300ddc4ca91393d Mon Sep 17 00:00:00 2001
From: Marek Szyprowski
Date: Thu, 14 Jun 2012 11:32:21 -0300
Subject: [media] v4l: vb2-dma-contig: let mmap method to use dma_mmap_coherent
 call

Let mmap method to use dma_mmap_coherent call.  Moreover, this patch removes
vb2_mmap_pfn_range from videobuf2 helpers as it was suggested by Laurent
Pinchart.  The function is no longer used in vb2 code.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/v4l2-core/videobuf2-dma-contig.c | 28 ++++++++++++++++--
 drivers/media/v4l2-core/videobuf2-memops.c     | 40 --------------------------
 include/media/videobuf2-memops.h               |  5 ----
 3 files changed, 26 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/videobuf2-dma-contig.c b/drivers/media/v4l2-core/videobuf2-dma-contig.c
index a5804cf12c7c..7fc71a0906db 100644
--- a/drivers/media/v4l2-core/videobuf2-dma-contig.c
+++ b/drivers/media/v4l2-core/videobuf2-dma-contig.c
@@ -178,14 +178,38 @@ static void *vb2_dc_alloc(void *alloc_ctx, unsigned long size)
 static int vb2_dc_mmap(void *buf_priv, struct vm_area_struct *vma)
 {
 	struct vb2_dc_buf *buf = buf_priv;
+	int ret;
 
 	if (!buf) {
 		printk(KERN_ERR "No buffer to map\n");
 		return -EINVAL;
 	}
 
-	return vb2_mmap_pfn_range(vma, buf->dma_addr, buf->size,
-				  &vb2_common_vm_ops, &buf->handler);
+	/*
+	 * dma_mmap_* uses vm_pgoff as in-buffer offset, but we want to
+	 * map whole buffer
+	 */
+	vma->vm_pgoff = 0;
+
+	ret = dma_mmap_coherent(buf->dev, vma, buf->vaddr,
+		buf->dma_addr, buf->size);
+
+	if (ret) {
+		pr_err("Remapping memory failed, error: %d\n", ret);
+		return ret;
+	}
+
+	vma->vm_flags		|= VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_private_data	= &buf->handler;
+	vma->vm_ops		= &vb2_common_vm_ops;
+
+	vma->vm_ops->open(vma);
+
+	pr_debug("%s: mapped dma addr 0x%08lx at 0x%08lx, size %ld\n",
+		__func__, (unsigned long)buf->dma_addr, vma->vm_start,
+		buf->size);
+
+	return 0;
 }
 
 /*********************************************/
diff --git a/drivers/media/v4l2-core/videobuf2-memops.c b/drivers/media/v4l2-core/videobuf2-memops.c
index 051ea3571b20..81c1ad8b2cf1 100644
--- a/drivers/media/v4l2-core/videobuf2-memops.c
+++ b/drivers/media/v4l2-core/videobuf2-memops.c
@@ -136,46 +136,6 @@ int vb2_get_contig_userptr(unsigned long vaddr, unsigned long size,
 }
 EXPORT_SYMBOL_GPL(vb2_get_contig_userptr);
 
-/**
- * vb2_mmap_pfn_range() - map physical pages to userspace
- * @vma:	virtual memory region for the mapping
- * @paddr:	starting physical address of the memory to be mapped
- * @size:	size of the memory to be mapped
- * @vm_ops:	vm operations to be assigned to the created area
- * @priv:	private data to be associated with the area
- *
- * Returns 0 on success.
- */
-int vb2_mmap_pfn_range(struct vm_area_struct *vma, unsigned long paddr,
-				unsigned long size,
-				const struct vm_operations_struct *vm_ops,
-				void *priv)
-{
-	int ret;
-
-	size = min_t(unsigned long, vma->vm_end - vma->vm_start, size);
-
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	ret = remap_pfn_range(vma, vma->vm_start, paddr >> PAGE_SHIFT,
-				size, vma->vm_page_prot);
-	if (ret) {
-		printk(KERN_ERR "Remapping memory failed, error: %d\n", ret);
-		return ret;
-	}
-
-	vma->vm_flags		|= VM_DONTEXPAND | VM_DONTDUMP;
-	vma->vm_private_data	= priv;
-	vma->vm_ops		= vm_ops;
-
-	vma->vm_ops->open(vma);
-
-	pr_debug("%s: mapped paddr 0x%08lx at 0x%08lx, size %ld\n",
-			__func__, paddr, vma->vm_start, size);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(vb2_mmap_pfn_range);
-
 /**
  * vb2_common_vm_open() - increase refcount of the vma
  * @vma:	virtual memory region for the mapping
diff --git a/include/media/videobuf2-memops.h b/include/media/videobuf2-memops.h
index 84e1f6c031c5..f05444ca8c0c 100644
--- a/include/media/videobuf2-memops.h
+++ b/include/media/videobuf2-memops.h
@@ -33,11 +33,6 @@ extern const struct vm_operations_struct vb2_common_vm_ops;
 int vb2_get_contig_userptr(unsigned long vaddr, unsigned long size,
 			   struct vm_area_struct **res_vma, dma_addr_t *res_pa);
 
-int vb2_mmap_pfn_range(struct vm_area_struct *vma, unsigned long paddr,
-				unsigned long size,
-				const struct vm_operations_struct *vm_ops,
-				void *priv);
-
 struct vm_area_struct *vb2_get_vma(struct vm_area_struct *vma);
 void vb2_put_vma(struct vm_area_struct *vma);
 
-- 
cgit v1.2.3-55-g7522


From b799d09a157da71566e8013a62073435550cab6d Mon Sep 17 00:00:00 2001
From: Tomasz Stanislawski
Date: Thu, 14 Jun 2012 11:32:23 -0300
Subject: [media] v4l: add buffer exporting via dmabuf

This patch adds extension to V4L2 api. A new ioctl VIDIOC_EXPBUF is added.  The
ioctl is used to export an mmap buffer as a DMABUF file descriptor.

Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Tested-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c |  1 +
 drivers/media/v4l2-core/v4l2-dev.c            |  1 +
 drivers/media/v4l2-core/v4l2-ioctl.c          | 10 ++++++++++
 include/media/v4l2-ioctl.h                    |  2 ++
 include/uapi/linux/videodev2.h                | 28 +++++++++++++++++++++++++++
 5 files changed, 42 insertions(+)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index cc5998b31463..7157af301b14 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -1018,6 +1018,7 @@ long v4l2_compat_ioctl32(struct file *file, unsigned int cmd, unsigned long arg)
 	case VIDIOC_S_FBUF32:
 	case VIDIOC_OVERLAY32:
 	case VIDIOC_QBUF32:
+	case VIDIOC_EXPBUF:
 	case VIDIOC_DQBUF32:
 	case VIDIOC_STREAMON32:
 	case VIDIOC_STREAMOFF32:
diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index a2df842e5100..98dcad9c8a3b 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -571,6 +571,7 @@ static void determine_valid_ioctls(struct video_device *vdev)
 	SET_VALID_IOCTL(ops, VIDIOC_REQBUFS, vidioc_reqbufs);
 	SET_VALID_IOCTL(ops, VIDIOC_QUERYBUF, vidioc_querybuf);
 	SET_VALID_IOCTL(ops, VIDIOC_QBUF, vidioc_qbuf);
+	SET_VALID_IOCTL(ops, VIDIOC_EXPBUF, vidioc_expbuf);
 	SET_VALID_IOCTL(ops, VIDIOC_DQBUF, vidioc_dqbuf);
 	SET_VALID_IOCTL(ops, VIDIOC_STREAMON, vidioc_streamon);
 	SET_VALID_IOCTL(ops, VIDIOC_STREAMOFF, vidioc_streamoff);
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 530a67e3fe0e..aa6e7c788db2 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -454,6 +454,15 @@ static void v4l_print_buffer(const void *arg, bool write_only)
 			tc->type, tc->flags, tc->frames, *(__u32 *)tc->userbits);
 }
 
+static void v4l_print_exportbuffer(const void *arg, bool write_only)
+{
+	const struct v4l2_exportbuffer *p = arg;
+
+	pr_cont("fd=%d, type=%s, index=%u, plane=%u, flags=0x%08x\n",
+		p->fd, prt_names(p->type, v4l2_type_names),
+		p->index, p->plane, p->flags);
+}
+
 static void v4l_print_create_buffers(const void *arg, bool write_only)
 {
 	const struct v4l2_create_buffers *p = arg;
@@ -1961,6 +1970,7 @@ static struct v4l2_ioctl_info v4l2_ioctls[] = {
 	IOCTL_INFO_STD(VIDIOC_S_FBUF, vidioc_s_fbuf, v4l_print_framebuffer, INFO_FL_PRIO),
 	IOCTL_INFO_FNC(VIDIOC_OVERLAY, v4l_overlay, v4l_print_u32, INFO_FL_PRIO),
 	IOCTL_INFO_FNC(VIDIOC_QBUF, v4l_qbuf, v4l_print_buffer, INFO_FL_QUEUE),
+	IOCTL_INFO_STD(VIDIOC_EXPBUF, vidioc_expbuf, v4l_print_exportbuffer, INFO_FL_QUEUE | INFO_FL_CLEAR(v4l2_exportbuffer, flags)),
 	IOCTL_INFO_FNC(VIDIOC_DQBUF, v4l_dqbuf, v4l_print_buffer, INFO_FL_QUEUE),
 	IOCTL_INFO_FNC(VIDIOC_STREAMON, v4l_streamon, v4l_print_buftype, INFO_FL_PRIO | INFO_FL_QUEUE),
 	IOCTL_INFO_FNC(VIDIOC_STREAMOFF, v4l_streamoff, v4l_print_buftype, INFO_FL_PRIO | INFO_FL_QUEUE),
diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h
index e48b571ca37d..4118ad1324c9 100644
--- a/include/media/v4l2-ioctl.h
+++ b/include/media/v4l2-ioctl.h
@@ -111,6 +111,8 @@ struct v4l2_ioctl_ops {
 	int (*vidioc_reqbufs) (struct file *file, void *fh, struct v4l2_requestbuffers *b);
 	int (*vidioc_querybuf)(struct file *file, void *fh, struct v4l2_buffer *b);
 	int (*vidioc_qbuf)    (struct file *file, void *fh, struct v4l2_buffer *b);
+	int (*vidioc_expbuf)  (struct file *file, void *fh,
+				struct v4l2_exportbuffer *e);
 	int (*vidioc_dqbuf)   (struct file *file, void *fh, struct v4l2_buffer *b);
 
 	int (*vidioc_create_bufs)(struct file *file, void *fh, struct v4l2_create_buffers *b);
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 91ac83b21c20..3cf3e946e331 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -694,6 +694,33 @@ struct v4l2_buffer {
 #define V4L2_BUF_FLAG_NO_CACHE_INVALIDATE	0x0800
 #define V4L2_BUF_FLAG_NO_CACHE_CLEAN		0x1000
 
+/**
+ * struct v4l2_exportbuffer - export of video buffer as DMABUF file descriptor
+ *
+ * @index:	id number of the buffer
+ * @type:	enum v4l2_buf_type; buffer type (type == *_MPLANE for
+ *		multiplanar buffers);
+ * @plane:	index of the plane to be exported, 0 for single plane queues
+ * @flags:	flags for newly created file, currently only O_CLOEXEC is
+ *		supported, refer to manual of open syscall for more details
+ * @fd:		file descriptor associated with DMABUF (set by driver)
+ *
+ * Contains data used for exporting a video buffer as DMABUF file descriptor.
+ * The buffer is identified by a 'cookie' returned by VIDIOC_QUERYBUF
+ * (identical to the cookie used to mmap() the buffer to userspace). All
+ * reserved fields must be set to zero. The field reserved0 is expected to
+ * become a structure 'type' allowing an alternative layout of the structure
+ * content. Therefore this field should not be used for any other extensions.
+ */
+struct v4l2_exportbuffer {
+	__u32		type; /* enum v4l2_buf_type */
+	__u32		index;
+	__u32		plane;
+	__u32		flags;
+	__s32		fd;
+	__u32		reserved[11];
+};
+
 /*
  *	O V E R L A Y   P R E V I E W
  */
@@ -1895,6 +1922,7 @@ struct v4l2_create_buffers {
 #define VIDIOC_S_FBUF		 _IOW('V', 11, struct v4l2_framebuffer)
 #define VIDIOC_OVERLAY		 _IOW('V', 14, int)
 #define VIDIOC_QBUF		_IOWR('V', 15, struct v4l2_buffer)
+#define VIDIOC_EXPBUF		_IOWR('V', 16, struct v4l2_exportbuffer)
 #define VIDIOC_DQBUF		_IOWR('V', 17, struct v4l2_buffer)
 #define VIDIOC_STREAMON		 _IOW('V', 18, int)
 #define VIDIOC_STREAMOFF	 _IOW('V', 19, int)
-- 
cgit v1.2.3-55-g7522


From 83ae7c5a1b5b5cd4380ff70797e4c5dcfb61a70d Mon Sep 17 00:00:00 2001
From: Tomasz Stanislawski
Date: Thu, 14 Jun 2012 11:32:24 -0300
Subject: [media] v4l: vb2: add buffer exporting via dmabuf

This patch adds extension to videobuf2-core. It allow to export an mmap buffer
as a DMABUF file descriptor.

Signed-off-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Tested-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/v4l2-core/v4l2-mem2mem.c   | 13 +++++
 drivers/media/v4l2-core/videobuf2-core.c | 83 ++++++++++++++++++++++++++++++++
 include/media/v4l2-mem2mem.h             |  3 ++
 include/media/videobuf2-core.h           |  4 ++
 4 files changed, 103 insertions(+)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index 017fed8ad2ab..438ea45d1074 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -368,6 +368,19 @@ int v4l2_m2m_dqbuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
 }
 EXPORT_SYMBOL_GPL(v4l2_m2m_dqbuf);
 
+/**
+ * v4l2_m2m_expbuf() - export a source or destination buffer, depending on
+ * the type
+ */
+int v4l2_m2m_expbuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
+		  struct v4l2_exportbuffer *eb)
+{
+	struct vb2_queue *vq;
+
+	vq = v4l2_m2m_get_vq(m2m_ctx, eb->type);
+	return vb2_expbuf(vq, eb);
+}
+EXPORT_SYMBOL_GPL(v4l2_m2m_expbuf);
 /**
  * v4l2_m2m_streamon() - turn on streaming for a video queue
  */
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 613dea16a304..9f81be23a81f 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -1750,6 +1750,79 @@ static int __find_plane_by_offset(struct vb2_queue *q, unsigned long off,
 	return -EINVAL;
 }
 
+/**
+ * vb2_expbuf() - Export a buffer as a file descriptor
+ * @q:		videobuf2 queue
+ * @eb:		export buffer structure passed from userspace to vidioc_expbuf
+ *		handler in driver
+ *
+ * The return values from this function are intended to be directly returned
+ * from vidioc_expbuf handler in driver.
+ */
+int vb2_expbuf(struct vb2_queue *q, struct v4l2_exportbuffer *eb)
+{
+	struct vb2_buffer *vb = NULL;
+	struct vb2_plane *vb_plane;
+	int ret;
+	struct dma_buf *dbuf;
+
+	if (q->memory != V4L2_MEMORY_MMAP) {
+		dprintk(1, "Queue is not currently set up for mmap\n");
+		return -EINVAL;
+	}
+
+	if (!q->mem_ops->get_dmabuf) {
+		dprintk(1, "Queue does not support DMA buffer exporting\n");
+		return -EINVAL;
+	}
+
+	if (eb->flags & ~O_CLOEXEC) {
+		dprintk(1, "Queue does support only O_CLOEXEC flag\n");
+		return -EINVAL;
+	}
+
+	if (eb->type != q->type) {
+		dprintk(1, "qbuf: invalid buffer type\n");
+		return -EINVAL;
+	}
+
+	if (eb->index >= q->num_buffers) {
+		dprintk(1, "buffer index out of range\n");
+		return -EINVAL;
+	}
+
+	vb = q->bufs[eb->index];
+
+	if (eb->plane >= vb->num_planes) {
+		dprintk(1, "buffer plane out of range\n");
+		return -EINVAL;
+	}
+
+	vb_plane = &vb->planes[eb->plane];
+
+	dbuf = call_memop(q, get_dmabuf, vb_plane->mem_priv);
+	if (IS_ERR_OR_NULL(dbuf)) {
+		dprintk(1, "Failed to export buffer %d, plane %d\n",
+			eb->index, eb->plane);
+		return -EINVAL;
+	}
+
+	ret = dma_buf_fd(dbuf, eb->flags);
+	if (ret < 0) {
+		dprintk(3, "buffer %d, plane %d failed to export (%d)\n",
+			eb->index, eb->plane, ret);
+		dma_buf_put(dbuf);
+		return ret;
+	}
+
+	dprintk(3, "buffer %d, plane %d exported as %d descriptor\n",
+		eb->index, eb->plane, ret);
+	eb->fd = ret;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vb2_expbuf);
+
 /**
  * vb2_mmap() - map video buffers into application address space
  * @q:		videobuf2 queue
@@ -2456,6 +2529,16 @@ int vb2_ioctl_streamoff(struct file *file, void *priv, enum v4l2_buf_type i)
 }
 EXPORT_SYMBOL_GPL(vb2_ioctl_streamoff);
 
+int vb2_ioctl_expbuf(struct file *file, void *priv, struct v4l2_exportbuffer *p)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vb2_queue_is_busy(vdev, file))
+		return -EBUSY;
+	return vb2_expbuf(vdev->queue, p);
+}
+EXPORT_SYMBOL_GPL(vb2_ioctl_expbuf);
+
 /* v4l2_file_operations helpers */
 
 int vb2_fop_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h
index 131cc4a53675..7e82d2b193d5 100644
--- a/include/media/v4l2-mem2mem.h
+++ b/include/media/v4l2-mem2mem.h
@@ -111,6 +111,9 @@ int v4l2_m2m_qbuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
 int v4l2_m2m_dqbuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
 		   struct v4l2_buffer *buf);
 
+int v4l2_m2m_expbuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
+		   struct v4l2_exportbuffer *eb);
+
 int v4l2_m2m_streamon(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
 		      enum v4l2_buf_type type);
 int v4l2_m2m_streamoff(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 24b9c90194f2..9cfd4ee9e56f 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -81,6 +81,7 @@ struct vb2_fileio_data;
 struct vb2_mem_ops {
 	void		*(*alloc)(void *alloc_ctx, unsigned long size);
 	void		(*put)(void *buf_priv);
+	struct dma_buf *(*get_dmabuf)(void *buf_priv);
 
 	void		*(*get_userptr)(void *alloc_ctx, unsigned long vaddr,
 					unsigned long size, int write);
@@ -363,6 +364,7 @@ int __must_check vb2_queue_init(struct vb2_queue *q);
 void vb2_queue_release(struct vb2_queue *q);
 
 int vb2_qbuf(struct vb2_queue *q, struct v4l2_buffer *b);
+int vb2_expbuf(struct vb2_queue *q, struct v4l2_exportbuffer *eb);
 int vb2_dqbuf(struct vb2_queue *q, struct v4l2_buffer *b, bool nonblocking);
 
 int vb2_streamon(struct vb2_queue *q, enum v4l2_buf_type type);
@@ -472,6 +474,8 @@ int vb2_ioctl_qbuf(struct file *file, void *priv, struct v4l2_buffer *p);
 int vb2_ioctl_dqbuf(struct file *file, void *priv, struct v4l2_buffer *p);
 int vb2_ioctl_streamon(struct file *file, void *priv, enum v4l2_buf_type i);
 int vb2_ioctl_streamoff(struct file *file, void *priv, enum v4l2_buf_type i);
+int vb2_ioctl_expbuf(struct file *file, void *priv,
+	struct v4l2_exportbuffer *p);
 
 /* struct v4l2_file_operations helpers */
 
-- 
cgit v1.2.3-55-g7522


From 36ff8d54ca6f3c251f0b7536bac3c38c57439e23 Mon Sep 17 00:00:00 2001
From: Jingoo Han
Date: Tue, 25 Sep 2012 15:37:45 +0900
Subject: video: s3c-fb: clean the bit definition for WINCON register

This patch cleans the bit definition for WINCON register.
The bit definition for WINCON1 and WINCON2 is removed, because
it is not used.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
---
 include/video/samsung_fimd.h | 76 ++++++++------------------------------------
 1 file changed, 13 insertions(+), 63 deletions(-)

(limited to 'include')

diff --git a/include/video/samsung_fimd.h b/include/video/samsung_fimd.h
index 7ae6c07f2ef8..bd0a04e478eb 100644
--- a/include/video/samsung_fimd.h
+++ b/include/video/samsung_fimd.h
@@ -173,18 +173,27 @@
 
 /* WINCONx */
 
-
+#define WINCON(_win)				(0x20 + ((_win) * 4))
+#define WINCONx_CSCWIDTH_MASK			(0x3 << 26)
+#define WINCONx_CSCWIDTH_SHIFT			(26)
+#define WINCONx_CSCWIDTH_WIDE			(0x0 << 26)
+#define WINCONx_CSCWIDTH_NARROW			(0x3 << 26)
+#define WINCONx_ENLOCAL				(1 << 22)
+#define WINCONx_BUFSTATUS			(1 << 21)
+#define WINCONx_BUFSEL				(1 << 20)
+#define WINCONx_BUFAUTOEN			(1 << 19)
 #define WINCONx_BITSWP				(1 << 18)
 #define WINCONx_BYTSWP				(1 << 17)
 #define WINCONx_HAWSWP				(1 << 16)
 #define WINCONx_WSWP				(1 << 15)
+#define WINCONx_YCbCr				(1 << 13)
 #define WINCONx_BURSTLEN_MASK			(0x3 << 9)
 #define WINCONx_BURSTLEN_SHIFT			(9)
 #define WINCONx_BURSTLEN_16WORD			(0x0 << 9)
 #define WINCONx_BURSTLEN_8WORD			(0x1 << 9)
 #define WINCONx_BURSTLEN_4WORD			(0x2 << 9)
-
 #define WINCONx_ENWIN				(1 << 0)
+
 #define WINCON0_BPPMODE_MASK			(0xf << 2)
 #define WINCON0_BPPMODE_SHIFT			(2)
 #define WINCON0_BPPMODE_1BPP			(0x0 << 2)
@@ -196,9 +205,8 @@
 #define WINCON0_BPPMODE_18BPP_666		(0x8 << 2)
 #define WINCON0_BPPMODE_24BPP_888		(0xb << 2)
 
+#define WINCON1_LOCALSEL_CAMIF			(1 << 23)
 #define WINCON1_BLD_PIX				(1 << 6)
-
-#define WINCON1_ALPHA_SEL			(1 << 1)
 #define WINCON1_BPPMODE_MASK			(0xf << 2)
 #define WINCON1_BPPMODE_SHIFT			(2)
 #define WINCON1_BPPMODE_1BPP			(0x0 << 2)
@@ -216,6 +224,7 @@
 #define WINCON1_BPPMODE_24BPP_A1887		(0xc << 2)
 #define WINCON1_BPPMODE_25BPP_A1888		(0xd << 2)
 #define WINCON1_BPPMODE_28BPP_A4888		(0xd << 2)
+#define WINCON1_ALPHA_SEL			(1 << 1)
 
 /* S5PV210 */
 #define SHADOWCON				(0x34)
@@ -401,71 +410,12 @@
 #define VIDTCON1				(0x14)
 #define VIDTCON2				(0x18)
 
-/* Window position controls */
-
-#define WINCON(_win)				(0x20 + ((_win) * 4))
-
 /* OSD1 and OSD4 do not have register D */
 
 #define VIDOSD_BASE				(0x40)
 
 #define VIDINTCON0				(0x130)
 
-/* WINCONx */
-
-#define WINCONx_CSCWIDTH_MASK			(0x3 << 26)
-#define WINCONx_CSCWIDTH_SHIFT			(26)
-#define WINCONx_CSCWIDTH_WIDE			(0x0 << 26)
-#define WINCONx_CSCWIDTH_NARROW			(0x3 << 26)
-
-#define WINCONx_ENLOCAL				(1 << 22)
-#define WINCONx_BUFSTATUS			(1 << 21)
-#define WINCONx_BUFSEL				(1 << 20)
-#define WINCONx_BUFAUTOEN			(1 << 19)
-#define WINCONx_YCbCr				(1 << 13)
-
-#define WINCON1_LOCALSEL_CAMIF			(1 << 23)
-
-#define WINCON2_LOCALSEL_CAMIF			(1 << 23)
-#define WINCON2_BLD_PIX				(1 << 6)
-
-#define WINCON2_ALPHA_SEL			(1 << 1)
-#define WINCON2_BPPMODE_MASK			(0xf << 2)
-#define WINCON2_BPPMODE_SHIFT			(2)
-#define WINCON2_BPPMODE_1BPP			(0x0 << 2)
-#define WINCON2_BPPMODE_2BPP			(0x1 << 2)
-#define WINCON2_BPPMODE_4BPP			(0x2 << 2)
-#define WINCON2_BPPMODE_8BPP_1232		(0x4 << 2)
-#define WINCON2_BPPMODE_16BPP_565		(0x5 << 2)
-#define WINCON2_BPPMODE_16BPP_A1555		(0x6 << 2)
-#define WINCON2_BPPMODE_16BPP_I1555		(0x7 << 2)
-#define WINCON2_BPPMODE_18BPP_666		(0x8 << 2)
-#define WINCON2_BPPMODE_18BPP_A1665		(0x9 << 2)
-#define WINCON2_BPPMODE_19BPP_A1666		(0xa << 2)
-#define WINCON2_BPPMODE_24BPP_888		(0xb << 2)
-#define WINCON2_BPPMODE_24BPP_A1887		(0xc << 2)
-#define WINCON2_BPPMODE_25BPP_A1888		(0xd << 2)
-#define WINCON2_BPPMODE_28BPP_A4888		(0xd << 2)
-
-#define WINCON3_BLD_PIX				(1 << 6)
-
-#define WINCON3_ALPHA_SEL			(1 << 1)
-#define WINCON3_BPPMODE_MASK			(0xf << 2)
-#define WINCON3_BPPMODE_SHIFT			(2)
-#define WINCON3_BPPMODE_1BPP			(0x0 << 2)
-#define WINCON3_BPPMODE_2BPP			(0x1 << 2)
-#define WINCON3_BPPMODE_4BPP			(0x2 << 2)
-#define WINCON3_BPPMODE_16BPP_565		(0x5 << 2)
-#define WINCON3_BPPMODE_16BPP_A1555		(0x6 << 2)
-#define WINCON3_BPPMODE_16BPP_I1555		(0x7 << 2)
-#define WINCON3_BPPMODE_18BPP_666		(0x8 << 2)
-#define WINCON3_BPPMODE_18BPP_A1665		(0x9 << 2)
-#define WINCON3_BPPMODE_19BPP_A1666		(0xa << 2)
-#define WINCON3_BPPMODE_24BPP_888		(0xb << 2)
-#define WINCON3_BPPMODE_24BPP_A1887		(0xc << 2)
-#define WINCON3_BPPMODE_25BPP_A1888		(0xd << 2)
-#define WINCON3_BPPMODE_28BPP_A4888		(0xd << 2)
-
 #define VIDINTCON0_FIFIOSEL_WINDOW2		(0x10 << 5)
 #define VIDINTCON0_FIFIOSEL_WINDOW3		(0x20 << 5)
 #define VIDINTCON0_FIFIOSEL_WINDOW4		(0x40 << 5)
-- 
cgit v1.2.3-55-g7522


From 9d07a0bf444c7bafc940ea8f3ba1b1bbbed09793 Mon Sep 17 00:00:00 2001
From: Jingoo Han
Date: Tue, 25 Sep 2012 15:48:20 +0900
Subject: video: s3c-fb: move the address definitions for VIDTCON registers

The address definitions for VIDTCON registers are moved to right
place.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
---
 include/video/samsung_fimd.h | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/video/samsung_fimd.h b/include/video/samsung_fimd.h
index bd0a04e478eb..bc22f3ccb7b1 100644
--- a/include/video/samsung_fimd.h
+++ b/include/video/samsung_fimd.h
@@ -116,6 +116,7 @@
 
 /* VIDTCON0 */
 
+#define VIDTCON0				(0x10)
 #define VIDTCON0_VBPDE_MASK			(0xff << 24)
 #define VIDTCON0_VBPDE_SHIFT			(24)
 #define VIDTCON0_VBPDE_LIMIT			(0xff)
@@ -138,6 +139,7 @@
 
 /* VIDTCON1 */
 
+#define VIDTCON1				(0x14)
 #define VIDTCON1_VFPDE_MASK			(0xff << 24)
 #define VIDTCON1_VFPDE_SHIFT			(24)
 #define VIDTCON1_VFPDE_LIMIT			(0xff)
@@ -158,6 +160,7 @@
 #define VIDTCON1_HSPW_LIMIT			(0xff)
 #define VIDTCON1_HSPW(_x)			((_x) << 0)
 
+#define VIDTCON2				(0x18)
 #define VIDTCON2				(0x18)
 #define VIDTCON2_LINEVAL_E(_x)			((((_x) & 0x800) >> 11) << 23)
 #define VIDTCON2_LINEVAL_MASK			(0x7ff << 11)
@@ -405,11 +408,6 @@
 #define S3C_FB_MAX_WIN (5)  /* number of hardware windows available. */
 #define VIDCON1_FSTATUS_EVEN	(1 << 15)
 
-/* Video timing controls */
-#define VIDTCON0				(0x10)
-#define VIDTCON1				(0x14)
-#define VIDTCON2				(0x18)
-
 /* OSD1 and OSD4 do not have register D */
 
 #define VIDOSD_BASE				(0x40)
-- 
cgit v1.2.3-55-g7522


From 99a2c61e639063803348c71c760c2fc272e83ec6 Mon Sep 17 00:00:00 2001
From: Jingoo Han
Date: Tue, 25 Sep 2012 16:43:16 +0900
Subject: video: s3c-fb: move the address definition for VIDOSD register

The address definition for VIDTCON VIDOSD is moved to right
place.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
---
 include/video/samsung_fimd.h | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/video/samsung_fimd.h b/include/video/samsung_fimd.h
index bc22f3ccb7b1..c398728cacfb 100644
--- a/include/video/samsung_fimd.h
+++ b/include/video/samsung_fimd.h
@@ -237,6 +237,9 @@
 /* Local input channels (windows 0-2) */
 #define SHADOWCON_CHx_LOCAL_ENABLE(_win)	(1 << (5 + (_win)))
 
+/* VIDOSDx */
+
+#define VIDOSD_BASE				(0x40)
 #define VIDOSDxA_TOPLEFT_X_E(_x)		((((_x) & 0x800) >> 11) << 23)
 #define VIDOSDxA_TOPLEFT_X_MASK			(0x7ff << 11)
 #define VIDOSDxA_TOPLEFT_X_SHIFT		(11)
@@ -408,10 +411,6 @@
 #define S3C_FB_MAX_WIN (5)  /* number of hardware windows available. */
 #define VIDCON1_FSTATUS_EVEN	(1 << 15)
 
-/* OSD1 and OSD4 do not have register D */
-
-#define VIDOSD_BASE				(0x40)
-
 #define VIDINTCON0				(0x130)
 
 #define VIDINTCON0_FIFIOSEL_WINDOW2		(0x10 << 5)
-- 
cgit v1.2.3-55-g7522


From 60eb8d83f0f70ddf023eb781d7eafffe54f9c5c5 Mon Sep 17 00:00:00 2001
From: Jingoo Han
Date: Tue, 25 Sep 2012 16:55:18 +0900
Subject: video: s3c-fb: move the bit definitions for VIDINTCON0 register

The bit definitions for VIDINTCON0 registers are moved to right
place.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
---
 include/video/samsung_fimd.h | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/video/samsung_fimd.h b/include/video/samsung_fimd.h
index c398728cacfb..7c9a9bcbcbbc 100644
--- a/include/video/samsung_fimd.h
+++ b/include/video/samsung_fimd.h
@@ -308,6 +308,7 @@
 
 /* Interrupt controls and status */
 
+#define VIDINTCON0				(0x130)
 #define VIDINTCON0_FIFOINTERVAL_MASK		(0x3f << 20)
 #define VIDINTCON0_FIFOINTERVAL_SHIFT		(20)
 #define VIDINTCON0_FIFOINTERVAL_LIMIT		(0x3f)
@@ -336,6 +337,9 @@
 #define VIDINTCON0_FIFIOSEL_SHIFT		(5)
 #define VIDINTCON0_FIFIOSEL_WINDOW0		(0x1 << 5)
 #define VIDINTCON0_FIFIOSEL_WINDOW1		(0x2 << 5)
+#define VIDINTCON0_FIFIOSEL_WINDOW2		(0x10 << 5)
+#define VIDINTCON0_FIFIOSEL_WINDOW3		(0x20 << 5)
+#define VIDINTCON0_FIFIOSEL_WINDOW4		(0x40 << 5)
 
 #define VIDINTCON0_FIFOLEVEL_MASK		(0x7 << 2)
 #define VIDINTCON0_FIFOLEVEL_SHIFT		(2)
@@ -411,12 +415,6 @@
 #define S3C_FB_MAX_WIN (5)  /* number of hardware windows available. */
 #define VIDCON1_FSTATUS_EVEN	(1 << 15)
 
-#define VIDINTCON0				(0x130)
-
-#define VIDINTCON0_FIFIOSEL_WINDOW2		(0x10 << 5)
-#define VIDINTCON0_FIFIOSEL_WINDOW3		(0x20 << 5)
-#define VIDINTCON0_FIFIOSEL_WINDOW4		(0x40 << 5)
-
 #define DITHMODE				(0x170)
 #define WINxMAP(_win)				(0x180 + ((_win) * 4))
 
-- 
cgit v1.2.3-55-g7522


From 22254540d4b1b22861c4afaeac13c6a43b56de44 Mon Sep 17 00:00:00 2001
From: Jingoo Han
Date: Tue, 25 Sep 2012 17:16:52 +0900
Subject: video: s3c-fb: move the bit definitions for WINxMAP and WPALCON
 register

The bit definitions for WINxMAP and WPALCON register are moved to
right place.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
---
 include/video/samsung_fimd.h | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/video/samsung_fimd.h b/include/video/samsung_fimd.h
index 7c9a9bcbcbbc..d5fe38b035b6 100644
--- a/include/video/samsung_fimd.h
+++ b/include/video/samsung_fimd.h
@@ -376,16 +376,20 @@
 #define WxKEYCON1_COLVAL_LIMIT			(0xffffff)
 #define WxKEYCON1_COLVAL(_x)			((_x) << 0)
 
-
 /* Window blanking (MAP) */
-
+#define WINxMAP(_win)				(0x180 + ((_win) * 4))
 #define WINxMAP_MAP				(1 << 24)
 #define WINxMAP_MAP_COLOUR_MASK			(0xffffff << 0)
 #define WINxMAP_MAP_COLOUR_SHIFT		(0)
 #define WINxMAP_MAP_COLOUR_LIMIT		(0xffffff)
 #define WINxMAP_MAP_COLOUR(_x)			((_x) << 0)
 
+/* Winodw palette control */
+#define WPALCON					(0x1A0)
 #define WPALCON_PAL_UPDATE			(1 << 9)
+#define WPALCON_W4PAL_16BPP_A555		(1 << 8)
+#define WPALCON_W3PAL_16BPP_A555		(1 << 7)
+#define WPALCON_W2PAL_16BPP_A555		(1 << 6)
 #define WPALCON_W1PAL_MASK			(0x7 << 3)
 #define WPALCON_W1PAL_SHIFT			(3)
 #define WPALCON_W1PAL_25BPP_A888		(0x0 << 3)
@@ -395,7 +399,6 @@
 #define WPALCON_W1PAL_18BPP			(0x4 << 3)
 #define WPALCON_W1PAL_16BPP_A555		(0x5 << 3)
 #define WPALCON_W1PAL_16BPP_565			(0x6 << 3)
-
 #define WPALCON_W0PAL_MASK			(0x7 << 0)
 #define WPALCON_W0PAL_SHIFT			(0)
 #define WPALCON_W0PAL_25BPP_A888		(0x0 << 0)
@@ -416,9 +419,6 @@
 #define VIDCON1_FSTATUS_EVEN	(1 << 15)
 
 #define DITHMODE				(0x170)
-#define WINxMAP(_win)				(0x180 + ((_win) * 4))
-
-
 #define DITHMODE_R_POS_MASK			(0x3 << 5)
 #define DITHMODE_R_POS_SHIFT			(5)
 #define DITHMODE_R_POS_8BIT			(0x0 << 5)
@@ -439,16 +439,6 @@
 
 #define DITHMODE_DITH_EN			(1 << 0)
 
-#define WPALCON					(0x1A0)
-
-/* Palette control */
-/* Note for S5PC100: you can still use those macros on WPALCON (aka WPALCON_L),
- * but make sure that WPALCON_H W2PAL-W4PAL entries are zeroed out */
-#define WPALCON_W4PAL_16BPP_A555		(1 << 8)
-#define WPALCON_W3PAL_16BPP_A555		(1 << 7)
-#define WPALCON_W2PAL_16BPP_A555		(1 << 6)
-
-
 /* Notes on per-window bpp settings
  *
  * Value	Win0	 Win1	  Win2	   Win3	    Win 4
-- 
cgit v1.2.3-55-g7522


From 31dd94f9591b5c4c8773468b9592e96dbb5a5a5f Mon Sep 17 00:00:00 2001
From: Jingoo Han
Date: Tue, 25 Sep 2012 17:30:36 +0900
Subject: video: s3c-fb: move the bit definitions for DITHMODE register

The bit definitions for DITHMODE registers are moved according to
address order. Also, the bit definition of VIDCON1_FSTATUS_EVEN
is moved.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
---
 include/video/samsung_fimd.h | 42 ++++++++++++++++++++----------------------
 1 file changed, 20 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/video/samsung_fimd.h b/include/video/samsung_fimd.h
index d5fe38b035b6..634b18b281a4 100644
--- a/include/video/samsung_fimd.h
+++ b/include/video/samsung_fimd.h
@@ -77,6 +77,7 @@
 #define VIDCON1_LINECNT_MASK			(0x7ff << 16)
 #define VIDCON1_LINECNT_SHIFT			(16)
 #define VIDCON1_LINECNT_GET(_v)			(((_v) >> 16) & 0x7ff)
+#define VIDCON1_FSTATUS_EVEN			(1 << 15)
 #define VIDCON1_VSTATUS_MASK			(0x3 << 13)
 #define VIDCON1_VSTATUS_SHIFT			(13)
 #define VIDCON1_VSTATUS_VSYNC			(0x0 << 13)
@@ -376,6 +377,25 @@
 #define WxKEYCON1_COLVAL_LIMIT			(0xffffff)
 #define WxKEYCON1_COLVAL(_x)			((_x) << 0)
 
+/* Dithering control */
+#define DITHMODE				(0x170)
+#define DITHMODE_R_POS_MASK			(0x3 << 5)
+#define DITHMODE_R_POS_SHIFT			(5)
+#define DITHMODE_R_POS_8BIT			(0x0 << 5)
+#define DITHMODE_R_POS_6BIT			(0x1 << 5)
+#define DITHMODE_R_POS_5BIT			(0x2 << 5)
+#define DITHMODE_G_POS_MASK			(0x3 << 3)
+#define DITHMODE_G_POS_SHIFT			(3)
+#define DITHMODE_G_POS_8BIT			(0x0 << 3)
+#define DITHMODE_G_POS_6BIT			(0x1 << 3)
+#define DITHMODE_G_POS_5BIT			(0x2 << 3)
+#define DITHMODE_B_POS_MASK			(0x3 << 1)
+#define DITHMODE_B_POS_SHIFT			(1)
+#define DITHMODE_B_POS_8BIT			(0x0 << 1)
+#define DITHMODE_B_POS_6BIT			(0x1 << 1)
+#define DITHMODE_B_POS_5BIT			(0x2 << 1)
+#define DITHMODE_DITH_EN			(1 << 0)
+
 /* Window blanking (MAP) */
 #define WINxMAP(_win)				(0x180 + ((_win) * 4))
 #define WINxMAP_MAP				(1 << 24)
@@ -416,28 +436,6 @@
 #define BLENDCON_NEW_4BIT_ALPHA_VALUE		(0 << 0)
 
 #define S3C_FB_MAX_WIN (5)  /* number of hardware windows available. */
-#define VIDCON1_FSTATUS_EVEN	(1 << 15)
-
-#define DITHMODE				(0x170)
-#define DITHMODE_R_POS_MASK			(0x3 << 5)
-#define DITHMODE_R_POS_SHIFT			(5)
-#define DITHMODE_R_POS_8BIT			(0x0 << 5)
-#define DITHMODE_R_POS_6BIT			(0x1 << 5)
-#define DITHMODE_R_POS_5BIT			(0x2 << 5)
-
-#define DITHMODE_G_POS_MASK			(0x3 << 3)
-#define DITHMODE_G_POS_SHIFT			(3)
-#define DITHMODE_G_POS_8BIT			(0x0 << 3)
-#define DITHMODE_G_POS_6BIT			(0x1 << 3)
-#define DITHMODE_G_POS_5BIT			(0x2 << 3)
-
-#define DITHMODE_B_POS_MASK			(0x3 << 1)
-#define DITHMODE_B_POS_SHIFT			(1)
-#define DITHMODE_B_POS_8BIT			(0x0 << 1)
-#define DITHMODE_B_POS_6BIT			(0x1 << 1)
-#define DITHMODE_B_POS_5BIT			(0x2 << 1)
-
-#define DITHMODE_DITH_EN			(1 << 0)
 
 /* Notes on per-window bpp settings
  *
-- 
cgit v1.2.3-55-g7522


From b4da9c9addcf9ba7bed6314884b904ee646aa171 Mon Sep 17 00:00:00 2001
From: Jingoo Han
Date: Tue, 25 Sep 2012 16:19:03 +0900
Subject: video: s3c-fb: add the bit definitions for VIDCON0_VIDOUT_WB

This patch adds the bit definitions for VIDCON0_VIDOUT_WB.
These definitions are used to support writeback for RGB and
i80 interface. Also, output format of writeback is YUV444.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
---
 include/video/samsung_fimd.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/video/samsung_fimd.h b/include/video/samsung_fimd.h
index 634b18b281a4..e7554486a2b7 100644
--- a/include/video/samsung_fimd.h
+++ b/include/video/samsung_fimd.h
@@ -24,12 +24,15 @@
 
 #define VIDCON0					(0x00)
 #define VIDCON0_INTERLACE			(1 << 29)
-#define VIDCON0_VIDOUT_MASK			(0x3 << 26)
+#define VIDCON0_VIDOUT_MASK			(0x7 << 26)
 #define VIDCON0_VIDOUT_SHIFT			(26)
 #define VIDCON0_VIDOUT_RGB			(0x0 << 26)
 #define VIDCON0_VIDOUT_TV			(0x1 << 26)
 #define VIDCON0_VIDOUT_I80_LDI0			(0x2 << 26)
 #define VIDCON0_VIDOUT_I80_LDI1			(0x3 << 26)
+#define VIDCON0_VIDOUT_WB_RGB			(0x4 << 26)
+#define VIDCON0_VIDOUT_WB_I80_LDI0		(0x6 << 26)
+#define VIDCON0_VIDOUT_WB_I80_LDI1		(0x7 << 26)
 
 #define VIDCON0_L1_DATA_MASK			(0x7 << 23)
 #define VIDCON0_L1_DATA_SHIFT			(23)
-- 
cgit v1.2.3-55-g7522


From b88ce2a41562d1a9554f209e0f31a32d9f473794 Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Mon, 26 Nov 2012 10:03:06 +0100
Subject: ACPI / PM: Allow attach/detach routines to change device power states

Make it possible to ask the routines used for adding/removing devices
to/from the general ACPI PM domain, acpi_dev_pm_attach() and
acpi_dev_pm_detach(), respectively, to change the power states of
devices so that they are put into the full-power state automatically
by acpi_dev_pm_attach() and into the lowest-power state available
automatically by acpi_dev_pm_detach().

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/acpi/device_pm.c | 28 ++++++++++++++++++++++++----
 include/linux/acpi.h     | 11 +++++++----
 2 files changed, 31 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index a8e059f69d50..f09dc987cf17 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -599,10 +599,12 @@ static struct dev_pm_domain acpi_general_pm_domain = {
 /**
  * acpi_dev_pm_attach - Prepare device for ACPI power management.
  * @dev: Device to prepare.
+ * @power_on: Whether or not to power on the device.
  *
  * If @dev has a valid ACPI handle that has a valid struct acpi_device object
  * attached to it, install a wakeup notification handler for the device and
- * add it to the general ACPI PM domain.
+ * add it to the general ACPI PM domain.  If @power_on is set, the device will
+ * be put into the ACPI D0 state before the function returns.
  *
  * This assumes that the @dev's bus type uses generic power management callbacks
  * (or doesn't use any power management callbacks at all).
@@ -610,7 +612,7 @@ static struct dev_pm_domain acpi_general_pm_domain = {
  * Callers must ensure proper synchronization of this function with power
  * management callbacks.
  */
-int acpi_dev_pm_attach(struct device *dev)
+int acpi_dev_pm_attach(struct device *dev, bool power_on)
 {
 	struct acpi_device *adev = acpi_dev_pm_get_node(dev);
 
@@ -622,6 +624,10 @@ int acpi_dev_pm_attach(struct device *dev)
 
 	acpi_add_pm_notifier(adev, acpi_wakeup_device, dev);
 	dev->pm_domain = &acpi_general_pm_domain;
+	if (power_on) {
+		acpi_dev_pm_full_power(adev);
+		__acpi_device_run_wake(adev, false);
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
@@ -629,20 +635,34 @@ EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
 /**
  * acpi_dev_pm_detach - Remove ACPI power management from the device.
  * @dev: Device to take care of.
+ * @power_off: Whether or not to try to remove power from the device.
  *
  * Remove the device from the general ACPI PM domain and remove its wakeup
- * notifier.
+ * notifier.  If @power_off is set, additionally remove power from the device if
+ * possible.
  *
  * Callers must ensure proper synchronization of this function with power
  * management callbacks.
  */
-void acpi_dev_pm_detach(struct device *dev)
+void acpi_dev_pm_detach(struct device *dev, bool power_off)
 {
 	struct acpi_device *adev = acpi_dev_pm_get_node(dev);
 
 	if (adev && dev->pm_domain == &acpi_general_pm_domain) {
 		dev->pm_domain = NULL;
 		acpi_remove_pm_notifier(adev, acpi_wakeup_device);
+		if (power_off) {
+			/*
+			 * If the device's PM QoS resume latency limit or flags
+			 * have been exposed to user space, they have to be
+			 * hidden at this point, so that they don't affect the
+			 * choice of the low-power state to put the device into.
+			 */
+			dev_pm_qos_hide_latency_limit(dev);
+			dev_pm_qos_hide_flags(dev);
+			__acpi_device_run_wake(adev, false);
+			acpi_dev_pm_low_power(dev, adev, ACPI_STATE_S0);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_detach);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 5fdd87271518..28ba643c92c1 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -458,11 +458,14 @@ static inline int acpi_subsys_resume_early(struct device *dev) { return 0; }
 #endif
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_PM)
-int acpi_dev_pm_attach(struct device *dev);
-int acpi_dev_pm_detach(struct device *dev);
+int acpi_dev_pm_attach(struct device *dev, bool power_on);
+int acpi_dev_pm_detach(struct device *dev, bool power_off);
 #else
-static inline int acpi_dev_pm_attach(struct device *dev) { return -ENODEV; }
-static inline void acpi_dev_pm_detach(struct device *dev) {}
+static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
+{
+	return -ENODEV;
+}
+static inline void acpi_dev_pm_detach(struct device *dev, bool power_off) {}
 #endif
 
 #endif	/*_LINUX_ACPI_H*/
-- 
cgit v1.2.3-55-g7522


From 883d588e556347c4b3221ac492a8acd8a75e730a Mon Sep 17 00:00:00 2001
From: MyungJoo Ham
Date: Wed, 21 Nov 2012 17:17:11 +0900
Subject: PM / devfreq: remove compiler error when a governor is module

With the intruction of patch, eff607fdb1f787da1fedf46ab6e64adc2afd1c5a,
it became possible to include a governor as a module.
Thus the #ifdef statement for a governor should become #if IS_ENABLED.

Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 include/linux/devfreq.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 235248cb2c93..e83ef39b3bea 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -192,7 +192,7 @@ extern int devfreq_register_opp_notifier(struct device *dev,
 extern int devfreq_unregister_opp_notifier(struct device *dev,
 					   struct devfreq *devfreq);
 
-#ifdef CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND
+#if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)
 /**
  * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq
  *	and devfreq_add_device
-- 
cgit v1.2.3-55-g7522


From c216e6417f473ab4666f539844652bf2f4129777 Mon Sep 17 00:00:00 2001
From: Arend van Spriel
Date: Sun, 25 Nov 2012 19:13:28 +0100
Subject: cfg80211: change function signature of cfg80211_get_p2p_attr()

The function cfg80211_get_p2p_attr() can fail and returns
a negative error code. However, the return type is unsigned
int. The largest positive number is determined by desired_len
variable in the function, which is u16. So changing the return
type to int to allow easy error checking. Also change the type
for the attribute to enum for improved type checking.

Signed-off-by: Arend van Spriel <arend@broadcom.com>
[fix indentation, don't use u8 attr variable]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 5 +++--
 net/wireless/util.c    | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 8a1aec54e68f..c2c185febb87 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3652,8 +3652,9 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev);
  * the data is malformed or the attribute can't be found (respectively),
  * or the length of the found attribute (which can be zero).
  */
-unsigned int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len,
-				   u8 attr, u8 *buf, unsigned int bufsize);
+int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len,
+			  enum ieee80211_p2p_attr_id attr,
+			  u8 *buf, unsigned int bufsize);
 
 /* Logging, debugging and troubleshooting/diagnostic helpers. */
 
diff --git a/net/wireless/util.c b/net/wireless/util.c
index b99f01cda1f6..db61fe8a6b6d 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -980,8 +980,9 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate)
 }
 EXPORT_SYMBOL(cfg80211_calculate_bitrate);
 
-unsigned int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len,
-				   u8 attr, u8 *buf, unsigned int bufsize)
+int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len,
+			  enum ieee80211_p2p_attr_id attr,
+			  u8 *buf, unsigned int bufsize)
 {
 	u8 *out = buf;
 	u16 attr_remaining = 0;
-- 
cgit v1.2.3-55-g7522


From 65821635d26d3173a3b22781e2c60d5e6fcaeb22 Mon Sep 17 00:00:00 2001
From: Marco Porsch
Date: Wed, 21 Nov 2012 18:40:30 -0800
Subject: mac80211: move Mesh Capability field definition to ieee80211.h

Signed-off-by: Marco Porsch <marco.porsch@etit.tu-chemnitz.de>
[prefix with IEEE80211_]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 15 +++++++++++++++
 net/mac80211/mesh.c       |  8 ++++----
 net/mac80211/mesh.h       | 14 --------------
 net/mac80211/mesh_sync.c  |  2 +-
 4 files changed, 20 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index d68790903b9e..65c6b0f3ef60 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -667,6 +667,21 @@ struct ieee80211_meshconf_ie {
 	u8 meshconf_cap;
 } __attribute__ ((packed));
 
+/**
+ * enum mesh_config_capab_flags - Mesh Configuration IE capability field flags
+ *
+ * @IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish
+ *	additional mesh peerings with other mesh STAs
+ * @IEEE80211_MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs
+ * @IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure
+ *	is ongoing
+ */
+enum mesh_config_capab_flags {
+	IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS		= 0x01,
+	IEEE80211_MESHCONF_CAPAB_FORWARDING		= 0x08,
+	IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING		= 0x20,
+};
+
 /**
  * struct ieee80211_rann_ie
  *
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index a350cab4b339..943694a52624 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -129,7 +129,7 @@ mismatch:
 bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie)
 {
 	return (ie->mesh_config->meshconf_cap &
-	    MESHCONF_CAPAB_ACCEPT_PLINKS) != 0;
+	    IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS) != 0;
 }
 
 /**
@@ -269,11 +269,11 @@ mesh_add_meshconf_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata)
 	neighbors = (neighbors > 15) ? 15 : neighbors;
 	*pos++ = neighbors << 1;
 	/* Mesh capability */
-	*pos = MESHCONF_CAPAB_FORWARDING;
+	*pos = IEEE80211_MESHCONF_CAPAB_FORWARDING;
 	*pos |= ifmsh->accepting_plinks ?
-	    MESHCONF_CAPAB_ACCEPT_PLINKS : 0x00;
+	    IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS : 0x00;
 	*pos++ |= ifmsh->adjusting_tbtt ?
-	    MESHCONF_CAPAB_TBTT_ADJUSTING : 0x00;
+	    IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING : 0x00;
 	*pos++ = 0x00;
 
 	return 0;
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index 9285f3f67e66..7c9215fb2ac8 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -18,20 +18,6 @@
 
 /* Data structures */
 
-/**
- * enum mesh_config_capab_flags - mesh config IE capability flags
- *
- * @MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish
- * additional mesh peerings with other mesh STAs
- * @MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs
- * @MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure is ongoing
- */
-enum mesh_config_capab_flags {
-	MESHCONF_CAPAB_ACCEPT_PLINKS = BIT(0),
-	MESHCONF_CAPAB_FORWARDING = BIT(3),
-	MESHCONF_CAPAB_TBTT_ADJUSTING = BIT(5),
-};
-
 /**
  * enum mesh_path_flags - mac80211 mesh path flags
  *
diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c
index 9c6ea9cfe1b3..0f40086cce18 100644
--- a/net/mac80211/mesh_sync.c
+++ b/net/mac80211/mesh_sync.c
@@ -43,7 +43,7 @@ struct sync_method {
 static bool mesh_peer_tbtt_adjusting(struct ieee802_11_elems *ie)
 {
 	return (ie->mesh_config->meshconf_cap &
-	    MESHCONF_CAPAB_TBTT_ADJUSTING) != 0;
+	    IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING) != 0;
 }
 
 void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata)
-- 
cgit v1.2.3-55-g7522


From 3f9be35bd9090eaa2f68ed9b24efdbf3abcf4b28 Mon Sep 17 00:00:00 2001
From: Axel Lin
Date: Tue, 20 Nov 2012 10:34:56 +0800
Subject: mfd: rc5t583: Fix array subscript is above array bounds

I got below build warning while compiling this driver.
It's obviously RC5T583_MAX_INTERRUPT_MASK_REGS is 9 but irq_en_add
array only has 8 elements.

  CC      drivers/mfd/rc5t583-irq.o
drivers/mfd/rc5t583-irq.c: In function 'rc5t583_irq_sync_unlock':
drivers/mfd/rc5t583-irq.c:227: warning: array subscript is above array bounds
drivers/mfd/rc5t583-irq.c: In function 'rc5t583_irq_init':
drivers/mfd/rc5t583-irq.c:349: warning: array subscript is above array bounds

Since the number of interrupt enable registers is 8, this patch adds
define for RC5T583_MAX_INTERRUPT_EN_REGS to fix this bug.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Acked-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/rc5t583-irq.c   | 2 +-
 include/linux/mfd/rc5t583.h | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/rc5t583-irq.c b/drivers/mfd/rc5t583-irq.c
index fe00cdd6f83d..b41db5968706 100644
--- a/drivers/mfd/rc5t583-irq.c
+++ b/drivers/mfd/rc5t583-irq.c
@@ -345,7 +345,7 @@ int rc5t583_irq_init(struct rc5t583 *rc5t583, int irq, int irq_base)
 	mutex_init(&rc5t583->irq_lock);
 
 	/* Initailize all int register to 0 */
-	for (i = 0; i < RC5T583_MAX_INTERRUPT_MASK_REGS; i++)  {
+	for (i = 0; i < RC5T583_MAX_INTERRUPT_EN_REGS; i++)  {
 		ret = rc5t583_write(rc5t583->dev, irq_en_add[i],
 				rc5t583->irq_en_reg[i]);
 		if (ret < 0)
diff --git a/include/linux/mfd/rc5t583.h b/include/linux/mfd/rc5t583.h
index 36c242e52ef1..fd413ccab915 100644
--- a/include/linux/mfd/rc5t583.h
+++ b/include/linux/mfd/rc5t583.h
@@ -33,6 +33,7 @@
 /* Maximum number of main interrupts */
 #define MAX_MAIN_INTERRUPT		5
 #define RC5T583_MAX_GPEDGE_REG		2
+#define RC5T583_MAX_INTERRUPT_EN_REGS	8
 #define RC5T583_MAX_INTERRUPT_MASK_REGS	9
 
 /* Interrupt enable register */
@@ -304,7 +305,7 @@ struct rc5t583 {
 	uint8_t		intc_inten_reg;
 
 	/* For group interrupt bits and address */
-	uint8_t		irq_en_reg[RC5T583_MAX_INTERRUPT_MASK_REGS];
+	uint8_t		irq_en_reg[RC5T583_MAX_INTERRUPT_EN_REGS];
 
 	/* For gpio edge */
 	uint8_t		gpedge_reg[RC5T583_MAX_GPEDGE_REG];
-- 
cgit v1.2.3-55-g7522


From df1590d9ae5e37e07e7cf91107e4c2c946ce8bf4 Mon Sep 17 00:00:00 2001
From: Viresh Kumar
Date: Mon, 12 Nov 2012 22:56:03 +0530
Subject: ARM: SPEAr3xx: Shirq: Move shirq controller out of plat/

This patch moves shirq interrupt controllers driver and header file out of
plat-spear directory. It is moved to drivers/irqchip/ directory.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 arch/arm/mach-spear3xx/spear3xx.c        |   2 +-
 arch/arm/plat-spear/Makefile             |   2 +-
 arch/arm/plat-spear/include/plat/shirq.h |  66 -------
 arch/arm/plat-spear/shirq.c              | 315 ------------------------------
 drivers/irqchip/Makefile                 |   3 +-
 drivers/irqchip/spear-shirq.c            | 316 +++++++++++++++++++++++++++++++
 include/linux/irqchip/spear-shirq.h      |  64 +++++++
 7 files changed, 384 insertions(+), 384 deletions(-)
 delete mode 100644 arch/arm/plat-spear/include/plat/shirq.h
 delete mode 100644 arch/arm/plat-spear/shirq.c
 create mode 100644 drivers/irqchip/spear-shirq.c
 create mode 100644 include/linux/irqchip/spear-shirq.h

(limited to 'include')

diff --git a/arch/arm/mach-spear3xx/spear3xx.c b/arch/arm/mach-spear3xx/spear3xx.c
index f1aaf5b168b2..38fe95db31a7 100644
--- a/arch/arm/mach-spear3xx/spear3xx.c
+++ b/arch/arm/mach-spear3xx/spear3xx.c
@@ -15,12 +15,12 @@
 
 #include <linux/amba/pl022.h>
 #include <linux/amba/pl08x.h>
+#include <linux/irqchip/spear-shirq.h>
 #include <linux/of_irq.h>
 #include <linux/io.h>
 #include <asm/hardware/pl080.h>
 #include <asm/hardware/vic.h>
 #include <plat/pl080.h>
-#include <plat/shirq.h>
 #include <mach/generic.h>
 #include <mach/spear.h>
 
diff --git a/arch/arm/plat-spear/Makefile b/arch/arm/plat-spear/Makefile
index 2607bd05c525..01e88532a5db 100644
--- a/arch/arm/plat-spear/Makefile
+++ b/arch/arm/plat-spear/Makefile
@@ -5,5 +5,5 @@
 # Common support
 obj-y	:= restart.o time.o
 
-obj-$(CONFIG_ARCH_SPEAR3XX)	+= pl080.o shirq.o
+obj-$(CONFIG_ARCH_SPEAR3XX)	+= pl080.o
 obj-$(CONFIG_ARCH_SPEAR6XX)	+= pl080.o
diff --git a/arch/arm/plat-spear/include/plat/shirq.h b/arch/arm/plat-spear/include/plat/shirq.h
deleted file mode 100644
index c51b355f00de..000000000000
--- a/arch/arm/plat-spear/include/plat/shirq.h
+++ /dev/null
@@ -1,66 +0,0 @@
-/*
- * arch/arm/plat-spear/include/plat/shirq.h
- *
- * SPEAr platform shared irq layer header file
- *
- * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __PLAT_SHIRQ_H
-#define __PLAT_SHIRQ_H
-
-#include <linux/irq.h>
-#include <linux/types.h>
-
-/*
- * struct shirq_regs: shared irq register configuration
- *
- * enb_reg: enable register offset
- * reset_to_enb: val 1 indicates, we need to clear bit for enabling interrupt
- * status_reg: status register offset
- * status_reg_mask: status register valid mask
- * clear_reg: clear register offset
- * reset_to_clear: val 1 indicates, we need to clear bit for clearing interrupt
- */
-struct shirq_regs {
-	u32 enb_reg;
-	u32 reset_to_enb;
-	u32 status_reg;
-	u32 clear_reg;
-	u32 reset_to_clear;
-};
-
-/*
- * struct spear_shirq: shared irq structure
- *
- * irq: hardware irq number
- * irq_base: base irq in linux domain
- * irq_nr: no. of shared interrupts in a particular block
- * irq_bit_off: starting bit offset in the status register
- * invalid_irq: irq group is currently disabled
- * base: base address of shared irq register
- * regs: register configuration for shared irq block
- */
-struct spear_shirq {
-	u32 irq;
-	u32 irq_base;
-	u32 irq_nr;
-	u32 irq_bit_off;
-	int invalid_irq;
-	void __iomem *base;
-	struct shirq_regs regs;
-};
-
-int __init spear300_shirq_of_init(struct device_node *np,
-		struct device_node *parent);
-int __init spear310_shirq_of_init(struct device_node *np,
-		struct device_node *parent);
-int __init spear320_shirq_of_init(struct device_node *np,
-		struct device_node *parent);
-
-#endif /* __PLAT_SHIRQ_H */
diff --git a/arch/arm/plat-spear/shirq.c b/arch/arm/plat-spear/shirq.c
deleted file mode 100644
index 955c7249a5c1..000000000000
--- a/arch/arm/plat-spear/shirq.c
+++ /dev/null
@@ -1,315 +0,0 @@
-/*
- * arch/arm/plat-spear/shirq.c
- *
- * SPEAr platform shared irq layer source file
- *
- * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/err.h>
-#include <linux/export.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/spinlock.h>
-#include <plat/shirq.h>
-
-static DEFINE_SPINLOCK(lock);
-
-/* spear300 shared irq registers offsets and masks */
-#define SPEAR300_INT_ENB_MASK_REG	0x54
-#define SPEAR300_INT_STS_MASK_REG	0x58
-
-static struct spear_shirq spear300_shirq_ras1 = {
-	.irq_nr = 9,
-	.irq_bit_off = 0,
-	.regs = {
-		.enb_reg = SPEAR300_INT_ENB_MASK_REG,
-		.status_reg = SPEAR300_INT_STS_MASK_REG,
-		.clear_reg = -1,
-	},
-};
-
-static struct spear_shirq *spear300_shirq_blocks[] = {
-	&spear300_shirq_ras1,
-};
-
-/* spear310 shared irq registers offsets and masks */
-#define SPEAR310_INT_STS_MASK_REG	0x04
-
-static struct spear_shirq spear310_shirq_ras1 = {
-	.irq_nr = 8,
-	.irq_bit_off = 0,
-	.regs = {
-		.enb_reg = -1,
-		.status_reg = SPEAR310_INT_STS_MASK_REG,
-		.clear_reg = -1,
-	},
-};
-
-static struct spear_shirq spear310_shirq_ras2 = {
-	.irq_nr = 5,
-	.irq_bit_off = 8,
-	.regs = {
-		.enb_reg = -1,
-		.status_reg = SPEAR310_INT_STS_MASK_REG,
-		.clear_reg = -1,
-	},
-};
-
-static struct spear_shirq spear310_shirq_ras3 = {
-	.irq_nr = 1,
-	.irq_bit_off = 13,
-	.regs = {
-		.enb_reg = -1,
-		.status_reg = SPEAR310_INT_STS_MASK_REG,
-		.clear_reg = -1,
-	},
-};
-
-static struct spear_shirq spear310_shirq_intrcomm_ras = {
-	.irq_nr = 3,
-	.irq_bit_off = 14,
-	.regs = {
-		.enb_reg = -1,
-		.status_reg = SPEAR310_INT_STS_MASK_REG,
-		.clear_reg = -1,
-	},
-};
-
-static struct spear_shirq *spear310_shirq_blocks[] = {
-	&spear310_shirq_ras1,
-	&spear310_shirq_ras2,
-	&spear310_shirq_ras3,
-	&spear310_shirq_intrcomm_ras,
-};
-
-/* spear320 shared irq registers offsets and masks */
-#define SPEAR320_INT_STS_MASK_REG		0x04
-#define SPEAR320_INT_CLR_MASK_REG		0x04
-#define SPEAR320_INT_ENB_MASK_REG		0x08
-
-static struct spear_shirq spear320_shirq_ras1 = {
-	.irq_nr = 3,
-	.irq_bit_off = 7,
-	.regs = {
-		.enb_reg = -1,
-		.status_reg = SPEAR320_INT_STS_MASK_REG,
-		.clear_reg = SPEAR320_INT_CLR_MASK_REG,
-		.reset_to_clear = 1,
-	},
-};
-
-static struct spear_shirq spear320_shirq_ras2 = {
-	.irq_nr = 1,
-	.irq_bit_off = 10,
-	.regs = {
-		.enb_reg = -1,
-		.status_reg = SPEAR320_INT_STS_MASK_REG,
-		.clear_reg = SPEAR320_INT_CLR_MASK_REG,
-		.reset_to_clear = 1,
-	},
-};
-
-static struct spear_shirq spear320_shirq_ras3 = {
-	.irq_nr = 3,
-	.irq_bit_off = 0,
-	.invalid_irq = 1,
-	.regs = {
-		.enb_reg = SPEAR320_INT_ENB_MASK_REG,
-		.reset_to_enb = 1,
-		.status_reg = SPEAR320_INT_STS_MASK_REG,
-		.clear_reg = SPEAR320_INT_CLR_MASK_REG,
-		.reset_to_clear = 1,
-	},
-};
-
-static struct spear_shirq spear320_shirq_intrcomm_ras = {
-	.irq_nr = 11,
-	.irq_bit_off = 11,
-	.regs = {
-		.enb_reg = -1,
-		.status_reg = SPEAR320_INT_STS_MASK_REG,
-		.clear_reg = SPEAR320_INT_CLR_MASK_REG,
-		.reset_to_clear = 1,
-	},
-};
-
-static struct spear_shirq *spear320_shirq_blocks[] = {
-	&spear320_shirq_ras3,
-	&spear320_shirq_ras1,
-	&spear320_shirq_ras2,
-	&spear320_shirq_intrcomm_ras,
-};
-
-static void shirq_irq_mask_unmask(struct irq_data *d, bool mask)
-{
-	struct spear_shirq *shirq = irq_data_get_irq_chip_data(d);
-	u32 val, offset = d->irq - shirq->irq_base;
-	unsigned long flags;
-
-	if (shirq->regs.enb_reg == -1)
-		return;
-
-	spin_lock_irqsave(&lock, flags);
-	val = readl(shirq->base + shirq->regs.enb_reg);
-
-	if (mask ^ shirq->regs.reset_to_enb)
-		val &= ~(0x1 << shirq->irq_bit_off << offset);
-	else
-		val |= 0x1 << shirq->irq_bit_off << offset;
-
-	writel(val, shirq->base + shirq->regs.enb_reg);
-	spin_unlock_irqrestore(&lock, flags);
-
-}
-
-static void shirq_irq_mask(struct irq_data *d)
-{
-	shirq_irq_mask_unmask(d, 1);
-}
-
-static void shirq_irq_unmask(struct irq_data *d)
-{
-	shirq_irq_mask_unmask(d, 0);
-}
-
-static struct irq_chip shirq_chip = {
-	.name		= "spear-shirq",
-	.irq_ack	= shirq_irq_mask,
-	.irq_mask	= shirq_irq_mask,
-	.irq_unmask	= shirq_irq_unmask,
-};
-
-static void shirq_handler(unsigned irq, struct irq_desc *desc)
-{
-	u32 i, j, val, mask, tmp;
-	struct irq_chip *chip;
-	struct spear_shirq *shirq = irq_get_handler_data(irq);
-
-	chip = irq_get_chip(irq);
-	chip->irq_ack(&desc->irq_data);
-
-	mask = ((0x1 << shirq->irq_nr) - 1) << shirq->irq_bit_off;
-	while ((val = readl(shirq->base + shirq->regs.status_reg) &
-				mask)) {
-
-		val >>= shirq->irq_bit_off;
-		for (i = 0, j = 1; i < shirq->irq_nr; i++, j <<= 1) {
-
-			if (!(j & val))
-				continue;
-
-			generic_handle_irq(shirq->irq_base + i);
-
-			/* clear interrupt */
-			if (shirq->regs.clear_reg == -1)
-				continue;
-
-			tmp = readl(shirq->base + shirq->regs.clear_reg);
-			if (shirq->regs.reset_to_clear)
-				tmp &= ~(j << shirq->irq_bit_off);
-			else
-				tmp |= (j << shirq->irq_bit_off);
-			writel(tmp, shirq->base + shirq->regs.clear_reg);
-		}
-	}
-	chip->irq_unmask(&desc->irq_data);
-}
-
-static void __init spear_shirq_register(struct spear_shirq *shirq)
-{
-	int i;
-
-	if (shirq->invalid_irq)
-		return;
-
-	irq_set_chained_handler(shirq->irq, shirq_handler);
-	for (i = 0; i < shirq->irq_nr; i++) {
-		irq_set_chip_and_handler(shirq->irq_base + i,
-					 &shirq_chip, handle_simple_irq);
-		set_irq_flags(shirq->irq_base + i, IRQF_VALID);
-		irq_set_chip_data(shirq->irq_base + i, shirq);
-	}
-
-	irq_set_handler_data(shirq->irq, shirq);
-}
-
-static int __init shirq_init(struct spear_shirq **shirq_blocks, int block_nr,
-		struct device_node *np)
-{
-	int i, irq_base, hwirq = 0, irq_nr = 0;
-	static struct irq_domain *shirq_domain;
-	void __iomem *base;
-
-	base = of_iomap(np, 0);
-	if (!base) {
-		pr_err("%s: failed to map shirq registers\n", __func__);
-		return -ENXIO;
-	}
-
-	for (i = 0; i < block_nr; i++)
-		irq_nr += shirq_blocks[i]->irq_nr;
-
-	irq_base = irq_alloc_descs(-1, 0, irq_nr, 0);
-	if (IS_ERR_VALUE(irq_base)) {
-		pr_err("%s: irq desc alloc failed\n", __func__);
-		goto err_unmap;
-	}
-
-	shirq_domain = irq_domain_add_legacy(np, irq_nr, irq_base, 0,
-			&irq_domain_simple_ops, NULL);
-	if (WARN_ON(!shirq_domain)) {
-		pr_warn("%s: irq domain init failed\n", __func__);
-		goto err_free_desc;
-	}
-
-	for (i = 0; i < block_nr; i++) {
-		shirq_blocks[i]->base = base;
-		shirq_blocks[i]->irq_base = irq_find_mapping(shirq_domain,
-				hwirq);
-		shirq_blocks[i]->irq = irq_of_parse_and_map(np, i);
-
-		spear_shirq_register(shirq_blocks[i]);
-		hwirq += shirq_blocks[i]->irq_nr;
-	}
-
-	return 0;
-
-err_free_desc:
-	irq_free_descs(irq_base, irq_nr);
-err_unmap:
-	iounmap(base);
-	return -ENXIO;
-}
-
-int __init spear300_shirq_of_init(struct device_node *np,
-		struct device_node *parent)
-{
-	return shirq_init(spear300_shirq_blocks,
-			ARRAY_SIZE(spear300_shirq_blocks), np);
-}
-
-int __init spear310_shirq_of_init(struct device_node *np,
-		struct device_node *parent)
-{
-	return shirq_init(spear310_shirq_blocks,
-			ARRAY_SIZE(spear310_shirq_blocks), np);
-}
-
-int __init spear320_shirq_of_init(struct device_node *np,
-		struct device_node *parent)
-{
-	return shirq_init(spear320_shirq_blocks,
-			ARRAY_SIZE(spear320_shirq_blocks), np);
-}
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 054321db4350..bf7b43696cdb 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -1 +1,2 @@
-obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2835.o
+obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2835.o
+obj-$(CONFIG_ARCH_SPEAR3XX)		+= spear-shirq.o
diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c
new file mode 100644
index 000000000000..80e1d2fd9d4c
--- /dev/null
+++ b/drivers/irqchip/spear-shirq.c
@@ -0,0 +1,316 @@
+/*
+ * SPEAr platform shared irq layer source file
+ *
+ * Copyright (C) 2009-2012 ST Microelectronics
+ * Viresh Kumar <viresh.linux@gmail.com>
+ *
+ * Copyright (C) 2012 ST Microelectronics
+ * Shiraz Hashim <shiraz.hashim@st.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip/spear-shirq.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/spinlock.h>
+
+static DEFINE_SPINLOCK(lock);
+
+/* spear300 shared irq registers offsets and masks */
+#define SPEAR300_INT_ENB_MASK_REG	0x54
+#define SPEAR300_INT_STS_MASK_REG	0x58
+
+static struct spear_shirq spear300_shirq_ras1 = {
+	.irq_nr = 9,
+	.irq_bit_off = 0,
+	.regs = {
+		.enb_reg = SPEAR300_INT_ENB_MASK_REG,
+		.status_reg = SPEAR300_INT_STS_MASK_REG,
+		.clear_reg = -1,
+	},
+};
+
+static struct spear_shirq *spear300_shirq_blocks[] = {
+	&spear300_shirq_ras1,
+};
+
+/* spear310 shared irq registers offsets and masks */
+#define SPEAR310_INT_STS_MASK_REG	0x04
+
+static struct spear_shirq spear310_shirq_ras1 = {
+	.irq_nr = 8,
+	.irq_bit_off = 0,
+	.regs = {
+		.enb_reg = -1,
+		.status_reg = SPEAR310_INT_STS_MASK_REG,
+		.clear_reg = -1,
+	},
+};
+
+static struct spear_shirq spear310_shirq_ras2 = {
+	.irq_nr = 5,
+	.irq_bit_off = 8,
+	.regs = {
+		.enb_reg = -1,
+		.status_reg = SPEAR310_INT_STS_MASK_REG,
+		.clear_reg = -1,
+	},
+};
+
+static struct spear_shirq spear310_shirq_ras3 = {
+	.irq_nr = 1,
+	.irq_bit_off = 13,
+	.regs = {
+		.enb_reg = -1,
+		.status_reg = SPEAR310_INT_STS_MASK_REG,
+		.clear_reg = -1,
+	},
+};
+
+static struct spear_shirq spear310_shirq_intrcomm_ras = {
+	.irq_nr = 3,
+	.irq_bit_off = 14,
+	.regs = {
+		.enb_reg = -1,
+		.status_reg = SPEAR310_INT_STS_MASK_REG,
+		.clear_reg = -1,
+	},
+};
+
+static struct spear_shirq *spear310_shirq_blocks[] = {
+	&spear310_shirq_ras1,
+	&spear310_shirq_ras2,
+	&spear310_shirq_ras3,
+	&spear310_shirq_intrcomm_ras,
+};
+
+/* spear320 shared irq registers offsets and masks */
+#define SPEAR320_INT_STS_MASK_REG		0x04
+#define SPEAR320_INT_CLR_MASK_REG		0x04
+#define SPEAR320_INT_ENB_MASK_REG		0x08
+
+static struct spear_shirq spear320_shirq_ras1 = {
+	.irq_nr = 3,
+	.irq_bit_off = 7,
+	.regs = {
+		.enb_reg = -1,
+		.status_reg = SPEAR320_INT_STS_MASK_REG,
+		.clear_reg = SPEAR320_INT_CLR_MASK_REG,
+		.reset_to_clear = 1,
+	},
+};
+
+static struct spear_shirq spear320_shirq_ras2 = {
+	.irq_nr = 1,
+	.irq_bit_off = 10,
+	.regs = {
+		.enb_reg = -1,
+		.status_reg = SPEAR320_INT_STS_MASK_REG,
+		.clear_reg = SPEAR320_INT_CLR_MASK_REG,
+		.reset_to_clear = 1,
+	},
+};
+
+static struct spear_shirq spear320_shirq_ras3 = {
+	.irq_nr = 3,
+	.irq_bit_off = 0,
+	.invalid_irq = 1,
+	.regs = {
+		.enb_reg = SPEAR320_INT_ENB_MASK_REG,
+		.reset_to_enb = 1,
+		.status_reg = SPEAR320_INT_STS_MASK_REG,
+		.clear_reg = SPEAR320_INT_CLR_MASK_REG,
+		.reset_to_clear = 1,
+	},
+};
+
+static struct spear_shirq spear320_shirq_intrcomm_ras = {
+	.irq_nr = 11,
+	.irq_bit_off = 11,
+	.regs = {
+		.enb_reg = -1,
+		.status_reg = SPEAR320_INT_STS_MASK_REG,
+		.clear_reg = SPEAR320_INT_CLR_MASK_REG,
+		.reset_to_clear = 1,
+	},
+};
+
+static struct spear_shirq *spear320_shirq_blocks[] = {
+	&spear320_shirq_ras3,
+	&spear320_shirq_ras1,
+	&spear320_shirq_ras2,
+	&spear320_shirq_intrcomm_ras,
+};
+
+static void shirq_irq_mask_unmask(struct irq_data *d, bool mask)
+{
+	struct spear_shirq *shirq = irq_data_get_irq_chip_data(d);
+	u32 val, offset = d->irq - shirq->irq_base;
+	unsigned long flags;
+
+	if (shirq->regs.enb_reg == -1)
+		return;
+
+	spin_lock_irqsave(&lock, flags);
+	val = readl(shirq->base + shirq->regs.enb_reg);
+
+	if (mask ^ shirq->regs.reset_to_enb)
+		val &= ~(0x1 << shirq->irq_bit_off << offset);
+	else
+		val |= 0x1 << shirq->irq_bit_off << offset;
+
+	writel(val, shirq->base + shirq->regs.enb_reg);
+	spin_unlock_irqrestore(&lock, flags);
+
+}
+
+static void shirq_irq_mask(struct irq_data *d)
+{
+	shirq_irq_mask_unmask(d, 1);
+}
+
+static void shirq_irq_unmask(struct irq_data *d)
+{
+	shirq_irq_mask_unmask(d, 0);
+}
+
+static struct irq_chip shirq_chip = {
+	.name		= "spear-shirq",
+	.irq_ack	= shirq_irq_mask,
+	.irq_mask	= shirq_irq_mask,
+	.irq_unmask	= shirq_irq_unmask,
+};
+
+static void shirq_handler(unsigned irq, struct irq_desc *desc)
+{
+	u32 i, j, val, mask, tmp;
+	struct irq_chip *chip;
+	struct spear_shirq *shirq = irq_get_handler_data(irq);
+
+	chip = irq_get_chip(irq);
+	chip->irq_ack(&desc->irq_data);
+
+	mask = ((0x1 << shirq->irq_nr) - 1) << shirq->irq_bit_off;
+	while ((val = readl(shirq->base + shirq->regs.status_reg) &
+				mask)) {
+
+		val >>= shirq->irq_bit_off;
+		for (i = 0, j = 1; i < shirq->irq_nr; i++, j <<= 1) {
+
+			if (!(j & val))
+				continue;
+
+			generic_handle_irq(shirq->irq_base + i);
+
+			/* clear interrupt */
+			if (shirq->regs.clear_reg == -1)
+				continue;
+
+			tmp = readl(shirq->base + shirq->regs.clear_reg);
+			if (shirq->regs.reset_to_clear)
+				tmp &= ~(j << shirq->irq_bit_off);
+			else
+				tmp |= (j << shirq->irq_bit_off);
+			writel(tmp, shirq->base + shirq->regs.clear_reg);
+		}
+	}
+	chip->irq_unmask(&desc->irq_data);
+}
+
+static void __init spear_shirq_register(struct spear_shirq *shirq)
+{
+	int i;
+
+	if (shirq->invalid_irq)
+		return;
+
+	irq_set_chained_handler(shirq->irq, shirq_handler);
+	for (i = 0; i < shirq->irq_nr; i++) {
+		irq_set_chip_and_handler(shirq->irq_base + i,
+					 &shirq_chip, handle_simple_irq);
+		set_irq_flags(shirq->irq_base + i, IRQF_VALID);
+		irq_set_chip_data(shirq->irq_base + i, shirq);
+	}
+
+	irq_set_handler_data(shirq->irq, shirq);
+}
+
+static int __init shirq_init(struct spear_shirq **shirq_blocks, int block_nr,
+		struct device_node *np)
+{
+	int i, irq_base, hwirq = 0, irq_nr = 0;
+	static struct irq_domain *shirq_domain;
+	void __iomem *base;
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("%s: failed to map shirq registers\n", __func__);
+		return -ENXIO;
+	}
+
+	for (i = 0; i < block_nr; i++)
+		irq_nr += shirq_blocks[i]->irq_nr;
+
+	irq_base = irq_alloc_descs(-1, 0, irq_nr, 0);
+	if (IS_ERR_VALUE(irq_base)) {
+		pr_err("%s: irq desc alloc failed\n", __func__);
+		goto err_unmap;
+	}
+
+	shirq_domain = irq_domain_add_legacy(np, irq_nr, irq_base, 0,
+			&irq_domain_simple_ops, NULL);
+	if (WARN_ON(!shirq_domain)) {
+		pr_warn("%s: irq domain init failed\n", __func__);
+		goto err_free_desc;
+	}
+
+	for (i = 0; i < block_nr; i++) {
+		shirq_blocks[i]->base = base;
+		shirq_blocks[i]->irq_base = irq_find_mapping(shirq_domain,
+				hwirq);
+		shirq_blocks[i]->irq = irq_of_parse_and_map(np, i);
+
+		spear_shirq_register(shirq_blocks[i]);
+		hwirq += shirq_blocks[i]->irq_nr;
+	}
+
+	return 0;
+
+err_free_desc:
+	irq_free_descs(irq_base, irq_nr);
+err_unmap:
+	iounmap(base);
+	return -ENXIO;
+}
+
+int __init spear300_shirq_of_init(struct device_node *np,
+		struct device_node *parent)
+{
+	return shirq_init(spear300_shirq_blocks,
+			ARRAY_SIZE(spear300_shirq_blocks), np);
+}
+
+int __init spear310_shirq_of_init(struct device_node *np,
+		struct device_node *parent)
+{
+	return shirq_init(spear310_shirq_blocks,
+			ARRAY_SIZE(spear310_shirq_blocks), np);
+}
+
+int __init spear320_shirq_of_init(struct device_node *np,
+		struct device_node *parent)
+{
+	return shirq_init(spear320_shirq_blocks,
+			ARRAY_SIZE(spear320_shirq_blocks), np);
+}
diff --git a/include/linux/irqchip/spear-shirq.h b/include/linux/irqchip/spear-shirq.h
new file mode 100644
index 000000000000..c8be16d213a3
--- /dev/null
+++ b/include/linux/irqchip/spear-shirq.h
@@ -0,0 +1,64 @@
+/*
+ * SPEAr platform shared irq layer header file
+ *
+ * Copyright (C) 2009-2012 ST Microelectronics
+ * Viresh Kumar <viresh.linux@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __SPEAR_SHIRQ_H
+#define __SPEAR_SHIRQ_H
+
+#include <linux/irq.h>
+#include <linux/types.h>
+
+/*
+ * struct shirq_regs: shared irq register configuration
+ *
+ * enb_reg: enable register offset
+ * reset_to_enb: val 1 indicates, we need to clear bit for enabling interrupt
+ * status_reg: status register offset
+ * status_reg_mask: status register valid mask
+ * clear_reg: clear register offset
+ * reset_to_clear: val 1 indicates, we need to clear bit for clearing interrupt
+ */
+struct shirq_regs {
+	u32 enb_reg;
+	u32 reset_to_enb;
+	u32 status_reg;
+	u32 clear_reg;
+	u32 reset_to_clear;
+};
+
+/*
+ * struct spear_shirq: shared irq structure
+ *
+ * irq: hardware irq number
+ * irq_base: base irq in linux domain
+ * irq_nr: no. of shared interrupts in a particular block
+ * irq_bit_off: starting bit offset in the status register
+ * invalid_irq: irq group is currently disabled
+ * base: base address of shared irq register
+ * regs: register configuration for shared irq block
+ */
+struct spear_shirq {
+	u32 irq;
+	u32 irq_base;
+	u32 irq_nr;
+	u32 irq_bit_off;
+	int invalid_irq;
+	void __iomem *base;
+	struct shirq_regs regs;
+};
+
+int __init spear300_shirq_of_init(struct device_node *np,
+		struct device_node *parent);
+int __init spear310_shirq_of_init(struct device_node *np,
+		struct device_node *parent);
+int __init spear320_shirq_of_init(struct device_node *np,
+		struct device_node *parent);
+
+#endif /* __SPEAR_SHIRQ_H */
-- 
cgit v1.2.3-55-g7522


From 42d97a599eb6b2aab3a401b3e5799a399d6c7652 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Thu, 8 Nov 2012 18:31:02 +0100
Subject: cfg80211: remove remain-on-channel channel type

As mwifiex (and mac80211 in the software case) are the
only drivers actually implementing remain-on-channel
with channel type, userspace can't be relying on it.
This is the case, as it's used only for P2P operations
right now.

Rather than adding a flag to tell userspace whether or
not it can actually rely on it, simplify all the code
by removing the ability to use different channel types.
Leave only the validation of the attribute, so that if
we extend it again later (with the needed capability
flag), it can't break userspace sending invalid data.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c  |  7 ++--
 drivers/net/wireless/ath/ath6kl/wmi.c       |  5 ++-
 drivers/net/wireless/iwlwifi/dvm/dev.h      |  1 -
 drivers/net/wireless/iwlwifi/dvm/mac80211.c |  2 --
 drivers/net/wireless/mac80211_hwsim.c       |  1 -
 drivers/net/wireless/mwifiex/cfg80211.c     | 16 +++------
 drivers/net/wireless/mwifiex/main.h         |  2 --
 drivers/net/wireless/mwifiex/sta_event.c    |  1 -
 drivers/net/wireless/mwifiex/sta_ioctl.c    |  3 +-
 include/net/cfg80211.h                      | 11 ++----
 include/net/mac80211.h                      |  1 -
 include/uapi/linux/nl80211.h                | 14 ++++----
 net/mac80211/cfg.c                          | 27 +++++----------
 net/mac80211/driver-ops.h                   |  5 ++-
 net/mac80211/ieee80211_i.h                  |  2 --
 net/mac80211/main.c                         |  2 +-
 net/mac80211/offchannel.c                   |  8 ++---
 net/mac80211/trace.h                        |  6 ++--
 net/wireless/core.h                         |  6 ++--
 net/wireless/mlme.c                         | 21 ++++--------
 net/wireless/nl80211.c                      | 36 ++++++++------------
 net/wireless/nl80211.h                      |  4 +--
 net/wireless/rdev-ops.h                     | 20 +++++------
 net/wireless/trace.h                        | 52 ++++++++++-------------------
 24 files changed, 81 insertions(+), 172 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index d615f9f7506a..74091d33ed6c 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -2976,7 +2976,6 @@ static int ath6kl_change_station(struct wiphy *wiphy, struct net_device *dev,
 static int ath6kl_remain_on_channel(struct wiphy *wiphy,
 				    struct wireless_dev *wdev,
 				    struct ieee80211_channel *chan,
-				    enum nl80211_channel_type channel_type,
 				    unsigned int duration,
 				    u64 *cookie)
 {
@@ -3135,10 +3134,8 @@ static bool ath6kl_is_p2p_go_ssid(const u8 *buf, size_t len)
 
 static int ath6kl_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 			  struct ieee80211_channel *chan, bool offchan,
-			  enum nl80211_channel_type channel_type,
-			  bool channel_type_valid, unsigned int wait,
-			  const u8 *buf, size_t len, bool no_cck,
-			  bool dont_wait_for_ack, u64 *cookie)
+			  unsigned int wait, const u8 *buf, size_t len,
+			  bool no_cck, bool dont_wait_for_ack, u64 *cookie)
 {
 	struct ath6kl_vif *vif = ath6kl_vif_from_wdev(wdev);
 	struct ath6kl *ar = ath6kl_priv(vif->ndev);
diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index c30ab4b11d61..0e05c41cdcfc 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -474,7 +474,7 @@ static int ath6kl_wmi_remain_on_chnl_event_rx(struct wmi *wmi, u8 *datap,
 		return -EINVAL;
 	}
 	id = vif->last_roc_id;
-	cfg80211_ready_on_channel(&vif->wdev, id, chan, NL80211_CHAN_NO_HT,
+	cfg80211_ready_on_channel(&vif->wdev, id, chan,
 				  dur, GFP_ATOMIC);
 
 	return 0;
@@ -513,8 +513,7 @@ static int ath6kl_wmi_cancel_remain_on_chnl_event_rx(struct wmi *wmi,
 	else
 		id = vif->last_roc_id; /* timeout on uncanceled r-o-c */
 	vif->last_cancel_roc_id = 0;
-	cfg80211_remain_on_channel_expired(&vif->wdev, id, chan,
-					   NL80211_CHAN_NO_HT, GFP_ATOMIC);
+	cfg80211_remain_on_channel_expired(&vif->wdev, id, chan, GFP_ATOMIC);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/iwlwifi/dvm/dev.h b/drivers/net/wireless/iwlwifi/dvm/dev.h
index 8141f91c3725..29c571a56251 100644
--- a/drivers/net/wireless/iwlwifi/dvm/dev.h
+++ b/drivers/net/wireless/iwlwifi/dvm/dev.h
@@ -789,7 +789,6 @@ struct iwl_priv {
 	/* remain-on-channel offload support */
 	struct ieee80211_channel *hw_roc_channel;
 	struct delayed_work hw_roc_disable_work;
-	enum nl80211_channel_type hw_roc_chantype;
 	int hw_roc_duration;
 	bool hw_roc_setup, hw_roc_start_notified;
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
index e75d80341f28..852edb02e5f6 100644
--- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
@@ -1034,7 +1034,6 @@ done:
 static int iwlagn_mac_remain_on_channel(struct ieee80211_hw *hw,
 				     struct ieee80211_vif *vif,
 				     struct ieee80211_channel *channel,
-				     enum nl80211_channel_type channel_type,
 				     int duration)
 {
 	struct iwl_priv *priv = IWL_MAC80211_GET_DVM(hw);
@@ -1066,7 +1065,6 @@ static int iwlagn_mac_remain_on_channel(struct ieee80211_hw *hw,
 	}
 
 	priv->hw_roc_channel = channel;
-	priv->hw_roc_chantype = channel_type;
 	/* convert from ms to TU */
 	priv->hw_roc_duration = DIV_ROUND_UP(1000 * duration, 1024);
 	priv->hw_roc_start_notified = false;
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 3baa51f1bb83..b0338543547b 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1455,7 +1455,6 @@ static void hw_roc_done(struct work_struct *work)
 static int mac80211_hwsim_roc(struct ieee80211_hw *hw,
 			      struct ieee80211_vif *vif,
 			      struct ieee80211_channel *chan,
-			      enum nl80211_channel_type channel_type,
 			      int duration)
 {
 	struct mac80211_hwsim_data *hwsim = hw->priv;
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index 8e829b251d83..f69190b492aa 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -180,10 +180,8 @@ mwifiex_form_mgmt_frame(struct sk_buff *skb, const u8 *buf, size_t len)
 static int
 mwifiex_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 			 struct ieee80211_channel *chan, bool offchan,
-			 enum nl80211_channel_type channel_type,
-			 bool channel_type_valid, unsigned int wait,
-			 const u8 *buf, size_t len, bool no_cck,
-			 bool dont_wait_for_ack, u64 *cookie)
+			 unsigned int wait, const u8 *buf, size_t len,
+			 bool no_cck, bool dont_wait_for_ack, u64 *cookie)
 {
 	struct sk_buff *skb;
 	u16 pkt_len;
@@ -253,7 +251,6 @@ static int
 mwifiex_cfg80211_remain_on_channel(struct wiphy *wiphy,
 				   struct wireless_dev *wdev,
 				   struct ieee80211_channel *chan,
-				   enum nl80211_channel_type channel_type,
 				   unsigned int duration, u64 *cookie)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(wdev->netdev);
@@ -271,15 +268,14 @@ mwifiex_cfg80211_remain_on_channel(struct wiphy *wiphy,
 	}
 
 	ret = mwifiex_remain_on_chan_cfg(priv, HostCmd_ACT_GEN_SET, chan,
-					 &channel_type, duration);
+					 duration);
 
 	if (!ret) {
 		*cookie = random32() | 1;
 		priv->roc_cfg.cookie = *cookie;
 		priv->roc_cfg.chan = *chan;
-		priv->roc_cfg.chan_type = channel_type;
 
-		cfg80211_ready_on_channel(wdev, *cookie, chan, channel_type,
+		cfg80211_ready_on_channel(wdev, *cookie, chan,
 					  duration, GFP_ATOMIC);
 
 		wiphy_dbg(wiphy, "info: ROC, cookie = 0x%llx\n", *cookie);
@@ -302,13 +298,11 @@ mwifiex_cfg80211_cancel_remain_on_channel(struct wiphy *wiphy,
 		return -ENOENT;
 
 	ret = mwifiex_remain_on_chan_cfg(priv, HostCmd_ACT_GEN_REMOVE,
-					 &priv->roc_cfg.chan,
-					 &priv->roc_cfg.chan_type, 0);
+					 &priv->roc_cfg.chan, 0);
 
 	if (!ret) {
 		cfg80211_remain_on_channel_expired(wdev, cookie,
 						   &priv->roc_cfg.chan,
-						   priv->roc_cfg.chan_type,
 						   GFP_ATOMIC);
 
 		memset(&priv->roc_cfg, 0, sizeof(struct mwifiex_roc_cfg));
diff --git a/drivers/net/wireless/mwifiex/main.h b/drivers/net/wireless/mwifiex/main.h
index 81f8772dcb07..771717df1c59 100644
--- a/drivers/net/wireless/mwifiex/main.h
+++ b/drivers/net/wireless/mwifiex/main.h
@@ -371,7 +371,6 @@ struct wps {
 struct mwifiex_roc_cfg {
 	u64 cookie;
 	struct ieee80211_channel chan;
-	enum nl80211_channel_type chan_type;
 };
 
 struct mwifiex_adapter;
@@ -1016,7 +1015,6 @@ int mwifiex_get_ver_ext(struct mwifiex_private *priv);
 
 int mwifiex_remain_on_chan_cfg(struct mwifiex_private *priv, u16 action,
 			       struct ieee80211_channel *chan,
-			       enum nl80211_channel_type *channel_type,
 			       unsigned int duration);
 
 int mwifiex_set_bss_role(struct mwifiex_private *priv, u8 bss_role);
diff --git a/drivers/net/wireless/mwifiex/sta_event.c b/drivers/net/wireless/mwifiex/sta_event.c
index 8132119e1a21..78dfa31c908c 100644
--- a/drivers/net/wireless/mwifiex/sta_event.c
+++ b/drivers/net/wireless/mwifiex/sta_event.c
@@ -424,7 +424,6 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 		cfg80211_remain_on_channel_expired(priv->wdev,
 						   priv->roc_cfg.cookie,
 						   &priv->roc_cfg.chan,
-						   priv->roc_cfg.chan_type,
 						   GFP_ATOMIC);
 
 		memset(&priv->roc_cfg, 0x00, sizeof(struct mwifiex_roc_cfg));
diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c
index 552d72ed055a..24af6ba7d8a1 100644
--- a/drivers/net/wireless/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/mwifiex/sta_ioctl.c
@@ -1046,7 +1046,6 @@ mwifiex_get_ver_ext(struct mwifiex_private *priv)
 int
 mwifiex_remain_on_chan_cfg(struct mwifiex_private *priv, u16 action,
 			   struct ieee80211_channel *chan,
-			   enum nl80211_channel_type *ct,
 			   unsigned int duration)
 {
 	struct host_cmd_ds_remain_on_chan roc_cfg;
@@ -1056,7 +1055,7 @@ mwifiex_remain_on_chan_cfg(struct mwifiex_private *priv, u16 action,
 	roc_cfg.action = cpu_to_le16(action);
 	if (action == HostCmd_ACT_GEN_SET) {
 		roc_cfg.band_cfg = chan->band;
-		sc = mwifiex_chan_type_to_sec_chan_offset(*ct);
+		sc = mwifiex_chan_type_to_sec_chan_offset(NL80211_CHAN_NO_HT);
 		roc_cfg.band_cfg |= (sc << 2);
 
 		roc_cfg.channel =
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index c2c185febb87..1effe0682d28 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1791,7 +1791,6 @@ struct cfg80211_ops {
 	int	(*remain_on_channel)(struct wiphy *wiphy,
 				     struct wireless_dev *wdev,
 				     struct ieee80211_channel *chan,
-				     enum nl80211_channel_type channel_type,
 				     unsigned int duration,
 				     u64 *cookie);
 	int	(*cancel_remain_on_channel)(struct wiphy *wiphy,
@@ -1800,10 +1799,8 @@ struct cfg80211_ops {
 
 	int	(*mgmt_tx)(struct wiphy *wiphy, struct wireless_dev *wdev,
 			  struct ieee80211_channel *chan, bool offchan,
-			  enum nl80211_channel_type channel_type,
-			  bool channel_type_valid, unsigned int wait,
-			  const u8 *buf, size_t len, bool no_cck,
-			  bool dont_wait_for_ack, u64 *cookie);
+			  unsigned int wait, const u8 *buf, size_t len,
+			  bool no_cck, bool dont_wait_for_ack, u64 *cookie);
 	int	(*mgmt_tx_cancel_wait)(struct wiphy *wiphy,
 				       struct wireless_dev *wdev,
 				       u64 cookie);
@@ -3350,14 +3347,12 @@ void cfg80211_disconnected(struct net_device *dev, u16 reason,
  * @wdev: wireless device
  * @cookie: the request cookie
  * @chan: The current channel (from remain_on_channel request)
- * @channel_type: Channel type
  * @duration: Duration in milliseconds that the driver intents to remain on the
  *	channel
  * @gfp: allocation flags
  */
 void cfg80211_ready_on_channel(struct wireless_dev *wdev, u64 cookie,
 			       struct ieee80211_channel *chan,
-			       enum nl80211_channel_type channel_type,
 			       unsigned int duration, gfp_t gfp);
 
 /**
@@ -3365,12 +3360,10 @@ void cfg80211_ready_on_channel(struct wireless_dev *wdev, u64 cookie,
  * @wdev: wireless device
  * @cookie: the request cookie
  * @chan: The current channel (from remain_on_channel request)
- * @channel_type: Channel type
  * @gfp: allocation flags
  */
 void cfg80211_remain_on_channel_expired(struct wireless_dev *wdev, u64 cookie,
 					struct ieee80211_channel *chan,
-					enum nl80211_channel_type channel_type,
 					gfp_t gfp);
 
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index e1293c7e4d2c..12093778b057 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2550,7 +2550,6 @@ struct ieee80211_ops {
 	int (*remain_on_channel)(struct ieee80211_hw *hw,
 				 struct ieee80211_vif *vif,
 				 struct ieee80211_channel *chan,
-				 enum nl80211_channel_type channel_type,
 				 int duration);
 	int (*cancel_remain_on_channel)(struct ieee80211_hw *hw);
 	int (*set_ringparam)(struct ieee80211_hw *hw, u32 tx, u32 rx);
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 1a9a819cfab0..43cd6fa084c5 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -401,8 +401,7 @@
  *	a response while being associated to an AP on another channel.
  *	%NL80211_ATTR_IFINDEX is used to specify which interface (and thus
  *	radio) is used. %NL80211_ATTR_WIPHY_FREQ is used to specify the
- *	frequency for the operation and %NL80211_ATTR_WIPHY_CHANNEL_TYPE may be
- *	optionally used to specify additional channel parameters.
+ *	frequency for the operation.
  *	%NL80211_ATTR_DURATION is used to specify the duration in milliseconds
  *	to remain on the channel. This command is also used as an event to
  *	notify when the requested duration starts (it may take a while for the
@@ -440,12 +439,11 @@
  *	as an event indicating reception of a frame that was not processed in
  *	kernel code, but is for us (i.e., which may need to be processed in a
  *	user space application). %NL80211_ATTR_FRAME is used to specify the
- *	frame contents (including header). %NL80211_ATTR_WIPHY_FREQ (and
- *	optionally %NL80211_ATTR_WIPHY_CHANNEL_TYPE) is used to indicate on
- *	which channel the frame is to be transmitted or was received. If this
- *	channel is not the current channel (remain-on-channel or the
- *	operational channel) the device will switch to the given channel and
- *	transmit the frame, optionally waiting for a response for the time
+ *	frame contents (including header). %NL80211_ATTR_WIPHY_FREQ is used
+ *	to indicate on which channel the frame is to be transmitted or was
+ *	received. If this channel is not the current channel (remain-on-channel
+ *	or the operational channel) the device will switch to the given channel
+ *	and transmit the frame, optionally waiting for a response for the time
  *	specified using %NL80211_ATTR_DURATION. When called, this operation
  *	returns a cookie (%NL80211_ATTR_COOKIE) that will be included with the
  *	TX status event pertaining to the TX request.
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 18926aea480c..ac0241e3539b 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2236,7 +2236,6 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy,
 static int ieee80211_start_roc_work(struct ieee80211_local *local,
 				    struct ieee80211_sub_if_data *sdata,
 				    struct ieee80211_channel *channel,
-				    enum nl80211_channel_type channel_type,
 				    unsigned int duration, u64 *cookie,
 				    struct sk_buff *txskb)
 {
@@ -2254,7 +2253,6 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 		return -ENOMEM;
 
 	roc->chan = channel;
-	roc->chan_type = channel_type;
 	roc->duration = duration;
 	roc->req_duration = duration;
 	roc->frame = txskb;
@@ -2287,8 +2285,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 	if (!duration)
 		duration = 10;
 
-	ret = drv_remain_on_channel(local, sdata, channel, channel_type,
-				    duration);
+	ret = drv_remain_on_channel(local, sdata, channel, duration);
 	if (ret) {
 		kfree(roc);
 		return ret;
@@ -2299,8 +2296,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 
  out_check_combine:
 	list_for_each_entry(tmp, &local->roc_list, list) {
-		if (tmp->chan != channel || tmp->chan_type != channel_type ||
-		    tmp->sdata != sdata)
+		if (tmp->chan != channel || tmp->sdata != sdata)
 			continue;
 
 		/*
@@ -2417,7 +2413,6 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 static int ieee80211_remain_on_channel(struct wiphy *wiphy,
 				       struct wireless_dev *wdev,
 				       struct ieee80211_channel *chan,
-				       enum nl80211_channel_type channel_type,
 				       unsigned int duration,
 				       u64 *cookie)
 {
@@ -2426,7 +2421,7 @@ static int ieee80211_remain_on_channel(struct wiphy *wiphy,
 	int ret;
 
 	mutex_lock(&local->mtx);
-	ret = ieee80211_start_roc_work(local, sdata, chan, channel_type,
+	ret = ieee80211_start_roc_work(local, sdata, chan,
 				       duration, cookie, NULL);
 	mutex_unlock(&local->mtx);
 
@@ -2519,10 +2514,8 @@ static int ieee80211_cancel_remain_on_channel(struct wiphy *wiphy,
 
 static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 			     struct ieee80211_channel *chan, bool offchan,
-			     enum nl80211_channel_type channel_type,
-			     bool channel_type_valid, unsigned int wait,
-			     const u8 *buf, size_t len, bool no_cck,
-			     bool dont_wait_for_ack, u64 *cookie)
+			     unsigned int wait, const u8 *buf, size_t len,
+			     bool no_cck, bool dont_wait_for_ack, u64 *cookie)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
 	struct ieee80211_local *local = sdata->local;
@@ -2591,14 +2584,10 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 		rcu_read_lock();
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 
-		if (chanctx_conf) {
+		if (chanctx_conf)
 			need_offchan = chan != chanctx_conf->channel;
-			if (channel_type_valid &&
-			    channel_type != chanctx_conf->channel_type)
-				need_offchan = true;
-		} else {
+		else
 			need_offchan = true;
-		}
 		rcu_read_unlock();
 	}
 
@@ -2633,7 +2622,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 			local->hw.offchannel_tx_hw_queue;
 
 	/* This will handle all kinds of coalescing and immediate TX */
-	ret = ieee80211_start_roc_work(local, sdata, chan, channel_type,
+	ret = ieee80211_start_roc_work(local, sdata, chan,
 				       wait, cookie, skb);
 	if (ret)
 		kfree_skb(skb);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 68c27aaf5c93..c6560cc7a9d6 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -738,16 +738,15 @@ static inline int drv_get_antenna(struct ieee80211_local *local,
 static inline int drv_remain_on_channel(struct ieee80211_local *local,
 					struct ieee80211_sub_if_data *sdata,
 					struct ieee80211_channel *chan,
-					enum nl80211_channel_type chantype,
 					unsigned int duration)
 {
 	int ret;
 
 	might_sleep();
 
-	trace_drv_remain_on_channel(local, sdata, chan, chantype, duration);
+	trace_drv_remain_on_channel(local, sdata, chan, duration);
 	ret = local->ops->remain_on_channel(&local->hw, &sdata->vif,
-					    chan, chantype, duration);
+					    chan, duration);
 	trace_drv_return_int(local, ret);
 
 	return ret;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index d5da0fe14318..fba4b1f425c1 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -348,7 +348,6 @@ struct ieee80211_roc_work {
 	struct ieee80211_sub_if_data *sdata;
 
 	struct ieee80211_channel *chan;
-	enum nl80211_channel_type chan_type;
 
 	bool started, abort, hw_begun, notified;
 
@@ -1048,7 +1047,6 @@ struct ieee80211_local {
 
 	/* Temporary remain-on-channel for off-channel operations */
 	struct ieee80211_channel *tmp_channel;
-	enum nl80211_channel_type tmp_channel_type;
 
 	/* channel contexts */
 	struct list_head chanctx_list;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 70e87600cacc..b229cded4567 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -115,7 +115,7 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local)
 			channel_type = NL80211_CHAN_NO_HT;
 	} else if (local->tmp_channel) {
 		chan = local->tmp_channel;
-		channel_type = local->tmp_channel_type;
+		channel_type = NL80211_CHAN_NO_HT;
 	} else {
 		chan = local->_oper_channel;
 		channel_type = local->_oper_channel_type;
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 7f8a36510813..5abddfe3e101 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -205,8 +205,8 @@ void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc)
 		}
 	} else {
 		cfg80211_ready_on_channel(&roc->sdata->wdev, roc->cookie,
-					  roc->chan, roc->chan_type,
-					  roc->req_duration, GFP_KERNEL);
+					  roc->chan, roc->req_duration,
+					  GFP_KERNEL);
 	}
 
 	roc->notified = true;
@@ -284,7 +284,6 @@ void ieee80211_start_next_roc(struct ieee80211_local *local)
 			duration = 10;
 
 		ret = drv_remain_on_channel(local, roc->sdata, roc->chan,
-					    roc->chan_type,
 					    duration);
 
 		roc->started = true;
@@ -321,7 +320,7 @@ void ieee80211_roc_notify_destroy(struct ieee80211_roc_work *roc)
 	if (!roc->mgmt_tx_cookie)
 		cfg80211_remain_on_channel_expired(&roc->sdata->wdev,
 						   roc->cookie, roc->chan,
-						   roc->chan_type, GFP_KERNEL);
+						   GFP_KERNEL);
 
 	list_for_each_entry_safe(dep, tmp, &roc->dependents, list)
 		ieee80211_roc_notify_destroy(dep);
@@ -359,7 +358,6 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 		ieee80211_recalc_idle(local);
 
 		local->tmp_channel = roc->chan;
-		local->tmp_channel_type = roc->chan_type;
 		ieee80211_hw_config(local, 0);
 
 		/* tell userspace or send frame */
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index e9579b7a2cd0..bc28346ba207 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -1022,15 +1022,14 @@ TRACE_EVENT(drv_remain_on_channel,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
 		 struct ieee80211_channel *chan,
-		 enum nl80211_channel_type chantype, unsigned int duration),
+		 unsigned int duration),
 
-	TP_ARGS(local, sdata, chan, chantype, duration),
+	TP_ARGS(local, sdata, chan, duration),
 
 	TP_STRUCT__entry(
 		LOCAL_ENTRY
 		VIF_ENTRY
 		__field(int, center_freq)
-		__field(int, channel_type)
 		__field(unsigned int, duration)
 	),
 
@@ -1038,7 +1037,6 @@ TRACE_EVENT(drv_remain_on_channel,
 		LOCAL_ASSIGN;
 		VIF_ASSIGN;
 		__entry->center_freq = chan->center_freq;
-		__entry->channel_type = chantype;
 		__entry->duration = duration;
 	),
 
diff --git a/net/wireless/core.h b/net/wireless/core.h
index e53831c876bb..b0a09cf56e06 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -378,10 +378,8 @@ void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev);
 int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev,
 			  struct wireless_dev *wdev,
 			  struct ieee80211_channel *chan, bool offchan,
-			  enum nl80211_channel_type channel_type,
-			  bool channel_type_valid, unsigned int wait,
-			  const u8 *buf, size_t len, bool no_cck,
-			  bool dont_wait_for_ack, u64 *cookie);
+			  unsigned int wait, const u8 *buf, size_t len,
+			  bool no_cck, bool dont_wait_for_ack, u64 *cookie);
 void cfg80211_oper_and_ht_capa(struct ieee80211_ht_cap *ht_capa,
 			       const struct ieee80211_ht_cap *ht_capa_mask);
 
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 4bfd14f7c592..a9646b53a095 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -579,31 +579,25 @@ void cfg80211_mlme_down(struct cfg80211_registered_device *rdev,
 
 void cfg80211_ready_on_channel(struct wireless_dev *wdev, u64 cookie,
 			       struct ieee80211_channel *chan,
-			       enum nl80211_channel_type channel_type,
 			       unsigned int duration, gfp_t gfp)
 {
 	struct wiphy *wiphy = wdev->wiphy;
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
 
-	trace_cfg80211_ready_on_channel(wdev, cookie, chan, channel_type,
-					duration);
-	nl80211_send_remain_on_channel(rdev, wdev, cookie, chan, channel_type,
-				       duration, gfp);
+	trace_cfg80211_ready_on_channel(wdev, cookie, chan, duration);
+	nl80211_send_remain_on_channel(rdev, wdev, cookie, chan, duration, gfp);
 }
 EXPORT_SYMBOL(cfg80211_ready_on_channel);
 
 void cfg80211_remain_on_channel_expired(struct wireless_dev *wdev, u64 cookie,
 					struct ieee80211_channel *chan,
-					enum nl80211_channel_type channel_type,
 					gfp_t gfp)
 {
 	struct wiphy *wiphy = wdev->wiphy;
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
 
-	trace_cfg80211_ready_on_channel_expired(wdev, cookie, chan,
-						channel_type);
-	nl80211_send_remain_on_channel_cancel(rdev, wdev, cookie, chan,
-					      channel_type, gfp);
+	trace_cfg80211_ready_on_channel_expired(wdev, cookie, chan);
+	nl80211_send_remain_on_channel_cancel(rdev, wdev, cookie, chan, gfp);
 }
 EXPORT_SYMBOL(cfg80211_remain_on_channel_expired);
 
@@ -758,10 +752,8 @@ void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev)
 int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev,
 			  struct wireless_dev *wdev,
 			  struct ieee80211_channel *chan, bool offchan,
-			  enum nl80211_channel_type channel_type,
-			  bool channel_type_valid, unsigned int wait,
-			  const u8 *buf, size_t len, bool no_cck,
-			  bool dont_wait_for_ack, u64 *cookie)
+			  unsigned int wait, const u8 *buf, size_t len,
+			  bool no_cck, bool dont_wait_for_ack, u64 *cookie)
 {
 	const struct ieee80211_mgmt *mgmt;
 	u16 stype;
@@ -855,7 +847,6 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev,
 
 	/* Transmit the Action frame as requested by user space */
 	return rdev_mgmt_tx(rdev, wdev, chan, offchan,
-			    channel_type, channel_type_valid,
 			    wait, buf, len, no_cck, dont_wait_for_ack,
 			    cookie);
 }
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 4c427fa5c450..e880f4494950 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5952,7 +5952,6 @@ static int nl80211_remain_on_channel(struct sk_buff *skb,
 	struct sk_buff *msg;
 	void *hdr;
 	u64 cookie;
-	enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT;
 	u32 freq, duration;
 	int err;
 
@@ -5975,11 +5974,11 @@ static int nl80211_remain_on_channel(struct sk_buff *skb,
 		return -EINVAL;
 
 	if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] &&
-	    !nl80211_valid_channel_type(info, &channel_type))
+	    !nl80211_valid_channel_type(info, NULL))
 		return -EINVAL;
 
 	freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]);
-	chan = rdev_freq_to_chan(rdev, freq, channel_type);
+	chan = rdev_freq_to_chan(rdev, freq, NL80211_CHAN_NO_HT);
 	if (chan == NULL)
 		return -EINVAL;
 
@@ -5995,8 +5994,7 @@ static int nl80211_remain_on_channel(struct sk_buff *skb,
 		goto free_msg;
 	}
 
-	err = rdev_remain_on_channel(rdev, wdev, chan, channel_type, duration,
-				     &cookie);
+	err = rdev_remain_on_channel(rdev, wdev, chan, duration, &cookie);
 
 	if (err)
 		goto free_msg;
@@ -6216,8 +6214,6 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct wireless_dev *wdev = info->user_ptr[1];
 	struct ieee80211_channel *chan;
-	enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT;
-	bool channel_type_valid = false;
 	u32 freq;
 	int err;
 	void *hdr = NULL;
@@ -6264,11 +6260,9 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 
 	}
 
-	if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) {
-		if (!nl80211_valid_channel_type(info, &channel_type))
-			return -EINVAL;
-		channel_type_valid = true;
-	}
+	if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] &&
+	    !nl80211_valid_channel_type(info, NULL))
+		return -EINVAL;
 
 	offchan = info->attrs[NL80211_ATTR_OFFCHANNEL_TX_OK];
 
@@ -6278,7 +6272,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 	no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]);
 
 	freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]);
-	chan = rdev_freq_to_chan(rdev, freq, channel_type);
+	chan = rdev_freq_to_chan(rdev, freq, NL80211_CHAN_NO_HT);
 	if (chan == NULL)
 		return -EINVAL;
 
@@ -6296,8 +6290,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	err = cfg80211_mlme_mgmt_tx(rdev, wdev, chan, offchan, channel_type,
-				    channel_type_valid, wait,
+	err = cfg80211_mlme_mgmt_tx(rdev, wdev, chan, offchan, wait,
 				    nla_data(info->attrs[NL80211_ATTR_FRAME]),
 				    nla_len(info->attrs[NL80211_ATTR_FRAME]),
 				    no_cck, dont_wait_for_ack, &cookie);
@@ -8395,7 +8388,6 @@ static void nl80211_send_remain_on_chan_event(
 	int cmd, struct cfg80211_registered_device *rdev,
 	struct wireless_dev *wdev, u64 cookie,
 	struct ieee80211_channel *chan,
-	enum nl80211_channel_type channel_type,
 	unsigned int duration, gfp_t gfp)
 {
 	struct sk_buff *msg;
@@ -8416,7 +8408,8 @@ static void nl80211_send_remain_on_chan_event(
 					 wdev->netdev->ifindex)) ||
 	    nla_put_u64(msg, NL80211_ATTR_WDEV, wdev_id(wdev)) ||
 	    nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, chan->center_freq) ||
-	    nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, channel_type) ||
+	    nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE,
+			NL80211_CHAN_NO_HT) ||
 	    nla_put_u64(msg, NL80211_ATTR_COOKIE, cookie))
 		goto nla_put_failure;
 
@@ -8438,23 +8431,20 @@ static void nl80211_send_remain_on_chan_event(
 void nl80211_send_remain_on_channel(struct cfg80211_registered_device *rdev,
 				    struct wireless_dev *wdev, u64 cookie,
 				    struct ieee80211_channel *chan,
-				    enum nl80211_channel_type channel_type,
 				    unsigned int duration, gfp_t gfp)
 {
 	nl80211_send_remain_on_chan_event(NL80211_CMD_REMAIN_ON_CHANNEL,
 					  rdev, wdev, cookie, chan,
-					  channel_type, duration, gfp);
+					  duration, gfp);
 }
 
 void nl80211_send_remain_on_channel_cancel(
 	struct cfg80211_registered_device *rdev,
 	struct wireless_dev *wdev,
-	u64 cookie, struct ieee80211_channel *chan,
-	enum nl80211_channel_type channel_type, gfp_t gfp)
+	u64 cookie, struct ieee80211_channel *chan, gfp_t gfp)
 {
 	nl80211_send_remain_on_chan_event(NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL,
-					  rdev, wdev, cookie, chan,
-					  channel_type, 0, gfp);
+					  rdev, wdev, cookie, chan, 0, gfp);
 }
 
 void nl80211_send_sta_event(struct cfg80211_registered_device *rdev,
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index f6153516068c..7adbd767dbfd 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -76,13 +76,11 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev,
 void nl80211_send_remain_on_channel(struct cfg80211_registered_device *rdev,
 				    struct wireless_dev *wdev, u64 cookie,
 				    struct ieee80211_channel *chan,
-				    enum nl80211_channel_type channel_type,
 				    unsigned int duration, gfp_t gfp);
 void nl80211_send_remain_on_channel_cancel(
 	struct cfg80211_registered_device *rdev,
 	struct wireless_dev *wdev,
-	u64 cookie, struct ieee80211_channel *chan,
-	enum nl80211_channel_type channel_type, gfp_t gfp);
+	u64 cookie, struct ieee80211_channel *chan, gfp_t gfp);
 
 void nl80211_send_sta_event(struct cfg80211_registered_device *rdev,
 			    struct net_device *dev, const u8 *mac_addr,
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 6e5fa659068d..ee54a5aa4381 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -600,14 +600,12 @@ static inline int
 rdev_remain_on_channel(struct cfg80211_registered_device *rdev,
 		       struct wireless_dev *wdev,
 		       struct ieee80211_channel *chan,
-		       enum nl80211_channel_type channel_type,
 		       unsigned int duration, u64 *cookie)
 {
 	int ret;
-	trace_rdev_remain_on_channel(&rdev->wiphy, wdev, chan, channel_type,
-				     duration);
+	trace_rdev_remain_on_channel(&rdev->wiphy, wdev, chan, duration);
 	ret = rdev->ops->remain_on_channel(&rdev->wiphy, wdev, chan,
-					    channel_type, duration, cookie);
+					   duration, cookie);
 	trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie);
 	return ret;
 }
@@ -626,17 +624,15 @@ rdev_cancel_remain_on_channel(struct cfg80211_registered_device *rdev,
 static inline int rdev_mgmt_tx(struct cfg80211_registered_device *rdev,
 			       struct wireless_dev *wdev,
 			       struct ieee80211_channel *chan, bool offchan,
-			       enum nl80211_channel_type channel_type,
-			       bool channel_type_valid, unsigned int wait,
-			       const u8 *buf, size_t len, bool no_cck,
-			       bool dont_wait_for_ack, u64 *cookie)
+			       unsigned int wait, const u8 *buf, size_t len,
+			       bool no_cck, bool dont_wait_for_ack, u64 *cookie)
 {
 	int ret;
-	trace_rdev_mgmt_tx(&rdev->wiphy, wdev, chan, offchan, channel_type,
-			   channel_type_valid, wait, no_cck, dont_wait_for_ack);
+	trace_rdev_mgmt_tx(&rdev->wiphy, wdev, chan, offchan,
+			   wait, no_cck, dont_wait_for_ack);
 	ret = rdev->ops->mgmt_tx(&rdev->wiphy, wdev, chan, offchan,
-				  channel_type, channel_type_valid, wait, buf,
-				  len, no_cck, dont_wait_for_ack, cookie);
+				  wait, buf, len, no_cck,
+				  dont_wait_for_ack, cookie);
 	trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie);
 	return ret;
 }
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index f264c20a7090..ed10833f9a3a 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1573,25 +1573,22 @@ DEFINE_EVENT(rdev_pmksa, rdev_del_pmksa,
 TRACE_EVENT(rdev_remain_on_channel,
 	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev,
 		 struct ieee80211_channel *chan,
-		 enum nl80211_channel_type channel_type, unsigned int duration),
-	TP_ARGS(wiphy, wdev, chan, channel_type, duration),
+		 unsigned int duration),
+	TP_ARGS(wiphy, wdev, chan, duration),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		WDEV_ENTRY
 		CHAN_ENTRY
-		__field(enum nl80211_channel_type, channel_type)
 		__field(unsigned int, duration)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		WDEV_ASSIGN;
 		CHAN_ASSIGN(chan);
-		__entry->channel_type = channel_type;
 		__entry->duration = duration;
 	),
-	TP_printk(WIPHY_PR_FMT WDEV_PR_FMT CHAN_PR_FMT ", channel type: %d, duration: %u",
-		  WIPHY_PR_ARG, WDEV_PR_ARG, CHAN_PR_ARG, __entry->channel_type,
-		  __entry->duration)
+	TP_printk(WIPHY_PR_FMT WDEV_PR_FMT CHAN_PR_FMT ", duration: %u",
+		  WIPHY_PR_ARG, WDEV_PR_ARG, CHAN_PR_ARG, __entry->duration)
 );
 
 TRACE_EVENT(rdev_return_int_cookie,
@@ -1631,18 +1628,13 @@ TRACE_EVENT(rdev_cancel_remain_on_channel,
 TRACE_EVENT(rdev_mgmt_tx,
 	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev,
 		 struct ieee80211_channel *chan, bool offchan,
-		 enum nl80211_channel_type channel_type,
-		 bool channel_type_valid, unsigned int wait, bool no_cck,
-		 bool dont_wait_for_ack),
-	TP_ARGS(wiphy, wdev, chan, offchan, channel_type, channel_type_valid,
-		wait, no_cck, dont_wait_for_ack),
+		 unsigned int wait, bool no_cck, bool dont_wait_for_ack),
+	TP_ARGS(wiphy, wdev, chan, offchan, wait, no_cck, dont_wait_for_ack),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		WDEV_ENTRY
 		CHAN_ENTRY
 		__field(bool, offchan)
-		__field(enum nl80211_channel_type, channel_type)
-		__field(bool, channel_type_valid)
 		__field(unsigned int, wait)
 		__field(bool, no_cck)
 		__field(bool, dont_wait_for_ack)
@@ -1652,18 +1644,14 @@ TRACE_EVENT(rdev_mgmt_tx,
 		WDEV_ASSIGN;
 		CHAN_ASSIGN(chan);
 		__entry->offchan = offchan;
-		__entry->channel_type = channel_type;
-		__entry->channel_type_valid = channel_type_valid;
 		__entry->wait = wait;
 		__entry->no_cck = no_cck;
 		__entry->dont_wait_for_ack = dont_wait_for_ack;
 	),
-	TP_printk(WIPHY_PR_FMT WDEV_PR_FMT CHAN_PR_FMT ", offchan: %s, "
-		  "channel type: %d, channel type valid: %s, wait: %u, "
-		  "no cck: %s, dont wait for ack: %s",
+	TP_printk(WIPHY_PR_FMT WDEV_PR_FMT CHAN_PR_FMT ", offchan: %s,"
+		  " wait: %u, no cck: %s, dont wait for ack: %s",
 		  WIPHY_PR_ARG, WDEV_PR_ARG, CHAN_PR_ARG,
-		  BOOL_TO_STR(__entry->offchan), __entry->channel_type,
-		  BOOL_TO_STR(__entry->channel_type_valid), __entry->wait,
+		  BOOL_TO_STR(__entry->offchan), __entry->wait,
 		  BOOL_TO_STR(__entry->no_cck),
 		  BOOL_TO_STR(__entry->dont_wait_for_ack))
 );
@@ -1894,47 +1882,41 @@ TRACE_EVENT(cfg80211_michael_mic_failure,
 TRACE_EVENT(cfg80211_ready_on_channel,
 	TP_PROTO(struct wireless_dev *wdev, u64 cookie,
 		 struct ieee80211_channel *chan,
-		 enum nl80211_channel_type channel_type, unsigned int duration),
-	TP_ARGS(wdev, cookie, chan, channel_type, duration),
+		 unsigned int duration),
+	TP_ARGS(wdev, cookie, chan, duration),
 	TP_STRUCT__entry(
 		WDEV_ENTRY
 		__field(u64, cookie)
 		CHAN_ENTRY
-		__field(enum nl80211_channel_type, channel_type)
 		__field(unsigned int, duration)
 	),
 	TP_fast_assign(
 		WDEV_ASSIGN;
 		__entry->cookie = cookie;
 		CHAN_ASSIGN(chan);
-		__entry->channel_type = channel_type;
 		__entry->duration = duration;
 	),
-	TP_printk(WDEV_PR_FMT ", cookie: %llu, " CHAN_PR_FMT ", channel type: %d, duration: %u",
+	TP_printk(WDEV_PR_FMT ", cookie: %llu, " CHAN_PR_FMT ", duration: %u",
 		  WDEV_PR_ARG, __entry->cookie, CHAN_PR_ARG,
-		  __entry->channel_type, __entry->duration)
+		  __entry->duration)
 );
 
 TRACE_EVENT(cfg80211_ready_on_channel_expired,
 	TP_PROTO(struct wireless_dev *wdev, u64 cookie,
-		 struct ieee80211_channel *chan,
-		 enum nl80211_channel_type channel_type),
-	TP_ARGS(wdev, cookie, chan, channel_type),
+		 struct ieee80211_channel *chan),
+	TP_ARGS(wdev, cookie, chan),
 	TP_STRUCT__entry(
 		WDEV_ENTRY
 		__field(u64, cookie)
 		CHAN_ENTRY
-		__field(enum nl80211_channel_type, channel_type)
 	),
 	TP_fast_assign(
 		WDEV_ASSIGN;
 		__entry->cookie = cookie;
 		CHAN_ASSIGN(chan);
-		__entry->channel_type = channel_type;
 	),
-	TP_printk(WDEV_PR_FMT ", cookie: %llu, " CHAN_PR_FMT ", channel type: %d",
-		  WDEV_PR_ARG, __entry->cookie, CHAN_PR_ARG,
-		  __entry->channel_type)
+	TP_printk(WDEV_PR_FMT ", cookie: %llu, " CHAN_PR_FMT,
+		  WDEV_PR_ARG, __entry->cookie, CHAN_PR_ARG)
 );
 
 TRACE_EVENT(cfg80211_new_sta,
-- 
cgit v1.2.3-55-g7522


From fe4b31810c06cc6518fb193efb9b3c3289b55832 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Thu, 8 Nov 2012 19:20:56 +0100
Subject: nl80211: add documentation for channel type

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 43cd6fa084c5..82b5ad38435b 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2438,6 +2438,15 @@ enum nl80211_ac {
 #define NL80211_TXQ_Q_BE	NL80211_AC_BE
 #define NL80211_TXQ_Q_BK	NL80211_AC_BK
 
+/**
+ * enum nl80211_channel_type - channel type
+ * @NL80211_CHAN_NO_HT: 20 MHz, non-HT channel
+ * @NL80211_CHAN_HT20: 20 MHz HT channel
+ * @NL80211_CHAN_HT40MINUS: HT40 channel, secondary channel
+ *	below the control channel
+ * @NL80211_CHAN_HT40PLUS: HT40 channel, secondary channel
+ *	above the control channel
+ */
 enum nl80211_channel_type {
 	NL80211_CHAN_NO_HT,
 	NL80211_CHAN_HT20,
-- 
cgit v1.2.3-55-g7522


From 683b6d3b31a51956ea540df00abb0b78894924c1 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Thu, 8 Nov 2012 21:25:48 +0100
Subject: cfg80211: pass a channel definition struct

Instead of passing a channel pointer and channel type
to all functions and driver methods, pass a new channel
definition struct. Right now, this struct contains just
the control channel and channel type, but for VHT this
will change.

Also, add a small inline cfg80211_get_chandef_type() so
that drivers don't need to use the _type field of the
new structure all the time, which will change.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c         |  22 +-
 .../net/wireless/brcm80211/brcmfmac/wl_cfg80211.c  |  11 +-
 drivers/net/wireless/libertas/cfg.c                |  24 +-
 drivers/net/wireless/mwifiex/cfg80211.c            |  30 ++-
 drivers/net/wireless/orinoco/cfg.c                 |  11 +-
 drivers/net/wireless/rndis_wlan.c                  |   2 +-
 include/net/cfg80211.h                             |  65 +++---
 net/mac80211/cfg.c                                 |  43 ++--
 net/mac80211/ibss.c                                |  21 +-
 net/wireless/chan.c                                |  59 +----
 net/wireless/core.h                                |  11 +-
 net/wireless/ibss.c                                |  27 ++-
 net/wireless/mesh.c                                |  49 ++--
 net/wireless/mlme.c                                |  15 +-
 net/wireless/nl80211.c                             | 253 +++++++++++----------
 net/wireless/nl80211.h                             |   4 +-
 net/wireless/rdev-ops.h                            |  22 +-
 net/wireless/trace.h                               | 100 ++++----
 net/wireless/wext-compat.c                         |  26 ++-
 net/wireless/wext-sme.c                            |  10 +-
 20 files changed, 403 insertions(+), 402 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 74091d33ed6c..c0cc2e59fe6c 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -1093,15 +1093,20 @@ out:
 void ath6kl_cfg80211_ch_switch_notify(struct ath6kl_vif *vif, int freq,
 				      enum wmi_phy_mode mode)
 {
-	enum nl80211_channel_type type;
+	struct cfg80211_chan_def chandef;
 
 	ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
 		   "channel switch notify nw_type %d freq %d mode %d\n",
 		   vif->nw_type, freq, mode);
 
-	type = (mode == WMI_11G_HT20) ? NL80211_CHAN_HT20 : NL80211_CHAN_NO_HT;
+	chandef.chan = ieee80211_get_channel(vif->ar->wiphy, freq);
+	if (WARN_ON(!chandef.chan))
+		return;
+
+	chandef._type = (mode == WMI_11G_HT20) ?
+		NL80211_CHAN_HT20 : NL80211_CHAN_NO_HT;
 
-	cfg80211_ch_switch_notify(vif->ndev, freq, type);
+	cfg80211_ch_switch_notify(vif->ndev, &chandef);
 }
 
 static int ath6kl_cfg80211_add_key(struct wiphy *wiphy, struct net_device *ndev,
@@ -1613,8 +1618,8 @@ static int ath6kl_cfg80211_join_ibss(struct wiphy *wiphy,
 	vif->ssid_len = ibss_param->ssid_len;
 	memcpy(vif->ssid, ibss_param->ssid, vif->ssid_len);
 
-	if (ibss_param->channel)
-		vif->ch_hint = ibss_param->channel->center_freq;
+	if (ibss_param->chandef.chan)
+		vif->ch_hint = ibss_param->chandef.chan->center_freq;
 
 	if (ibss_param->channel_fixed) {
 		/*
@@ -2856,7 +2861,7 @@ static int ath6kl_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	p.ssid_len = vif->ssid_len;
 	memcpy(p.ssid, vif->ssid, vif->ssid_len);
 	p.dot11_auth_mode = vif->dot11_auth_mode;
-	p.ch = cpu_to_le16(info->channel->center_freq);
+	p.ch = cpu_to_le16(info->chandef.chan->center_freq);
 
 	/* Enable uAPSD support by default */
 	res = ath6kl_wmi_ap_set_apsd(ar->wmi, vif->fw_vif_idx, true);
@@ -2880,8 +2885,9 @@ static int ath6kl_start_ap(struct wiphy *wiphy, struct net_device *dev,
 			return res;
 	}
 
-	if (ath6kl_set_htcap(vif, info->channel->band,
-			     info->channel_type != NL80211_CHAN_NO_HT))
+	if (ath6kl_set_htcap(vif, info->chandef.chan->band,
+			     cfg80211_get_chandef_type(&info->chandef)
+					!= NL80211_CHAN_NO_HT))
 		return -EIO;
 
 	/*
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
index 904c94121c13..b596ca4f22bd 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
@@ -1212,8 +1212,8 @@ brcmf_cfg80211_join_ibss(struct wiphy *wiphy, struct net_device *ndev,
 	else
 		WL_CONN("No BSSID specified\n");
 
-	if (params->channel)
-		WL_CONN("channel: %d\n", params->channel->center_freq);
+	if (params->chandef.chan)
+		WL_CONN("channel: %d\n", params->chandef.chan->center_freq);
 	else
 		WL_CONN("no channel specified\n");
 
@@ -1286,12 +1286,12 @@ brcmf_cfg80211_join_ibss(struct wiphy *wiphy, struct net_device *ndev,
 	}
 
 	/* Channel */
-	if (params->channel) {
+	if (params->chandef.chan) {
 		u32 target_channel;
 
 		cfg->channel =
 			ieee80211_frequency_to_channel(
-				params->channel->center_freq);
+				params->chandef.chan->center_freq);
 		if (params->channel_fixed) {
 			/* adding chanspec */
 			brcmf_ch_to_chanspec(cfg->channel,
@@ -3938,7 +3938,8 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 	s32 bssidx = 0;
 
 	WL_TRACE("channel_type=%d, beacon_interval=%d, dtim_period=%d,\n",
-		 settings->channel_type, settings->beacon_interval,
+		 cfg80211_get_chandef_type(&settings->chandef),
+		 settings->beacon_interval,
 		 settings->dtim_period);
 	WL_TRACE("ssid=%s(%d), auth_type=%d, inactivity_timeout=%d\n",
 		 settings->ssid, settings->ssid_len, settings->auth_type,
diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c
index 1c10b542ab23..ec36868f6fc5 100644
--- a/drivers/net/wireless/libertas/cfg.c
+++ b/drivers/net/wireless/libertas/cfg.c
@@ -436,19 +436,19 @@ static int lbs_add_wpa_tlv(u8 *tlv, const u8 *ie, u8 ie_len)
  */
 
 static int lbs_cfg_set_monitor_channel(struct wiphy *wiphy,
-				       struct ieee80211_channel *channel,
-				       enum nl80211_channel_type channel_type)
+				       struct cfg80211_chan_def *chandef)
 {
 	struct lbs_private *priv = wiphy_priv(wiphy);
 	int ret = -ENOTSUPP;
 
 	lbs_deb_enter_args(LBS_DEB_CFG80211, "freq %d, type %d",
-			   channel->center_freq, channel_type);
+			   chandef->chan->center_freq,
+			   cfg80211_get_chandef_type(chandef));
 
-	if (channel_type != NL80211_CHAN_NO_HT)
+	if (cfg80211_get_chandef_type(chandef) != NL80211_CHAN_NO_HT)
 		goto out;
 
-	ret = lbs_set_channel(priv, channel->hw_value);
+	ret = lbs_set_channel(priv, chandef->chan->hw_value);
 
  out:
 	lbs_deb_leave_args(LBS_DEB_CFG80211, "ret %d", ret);
@@ -1734,7 +1734,7 @@ static void lbs_join_post(struct lbs_private *priv,
 	/* Fake DS channel IE */
 	*fake++ = WLAN_EID_DS_PARAMS;
 	*fake++ = 1;
-	*fake++ = params->channel->hw_value;
+	*fake++ = params->chandef.chan->hw_value;
 	/* Fake IBSS params IE */
 	*fake++ = WLAN_EID_IBSS_PARAMS;
 	*fake++ = 2;
@@ -1755,7 +1755,7 @@ static void lbs_join_post(struct lbs_private *priv,
 	lbs_deb_hex(LBS_DEB_CFG80211, "IE", fake_ie, fake - fake_ie);
 
 	bss = cfg80211_inform_bss(priv->wdev->wiphy,
-				  params->channel,
+				  params->chandef.chan,
 				  bssid,
 				  0,
 				  capability,
@@ -1833,7 +1833,7 @@ static int lbs_ibss_join_existing(struct lbs_private *priv,
 	cmd.bss.beaconperiod = cpu_to_le16(params->beacon_interval);
 	cmd.bss.ds.header.id = WLAN_EID_DS_PARAMS;
 	cmd.bss.ds.header.len = 1;
-	cmd.bss.ds.channel = params->channel->hw_value;
+	cmd.bss.ds.channel = params->chandef.chan->hw_value;
 	cmd.bss.ibss.header.id = WLAN_EID_IBSS_PARAMS;
 	cmd.bss.ibss.header.len = 2;
 	cmd.bss.ibss.atimwindow = 0;
@@ -1942,7 +1942,7 @@ static int lbs_ibss_start_new(struct lbs_private *priv,
 	cmd.ibss.atimwindow = 0;
 	cmd.ds.header.id = WLAN_EID_DS_PARAMS;
 	cmd.ds.header.len = 1;
-	cmd.ds.channel = params->channel->hw_value;
+	cmd.ds.channel = params->chandef.chan->hw_value;
 	/* Only v8 and below support setting probe delay */
 	if (MRVL_FW_MAJOR_REV(priv->fwrelease) <= 8)
 		cmd.probedelay = cpu_to_le16(CMD_SCAN_PROBE_DELAY_TIME);
@@ -1987,18 +1987,18 @@ static int lbs_join_ibss(struct wiphy *wiphy, struct net_device *dev,
 
 	lbs_deb_enter(LBS_DEB_CFG80211);
 
-	if (!params->channel) {
+	if (!params->chandef.chan) {
 		ret = -ENOTSUPP;
 		goto out;
 	}
 
-	ret = lbs_set_channel(priv, params->channel->hw_value);
+	ret = lbs_set_channel(priv, params->chandef.chan->hw_value);
 	if (ret)
 		goto out;
 
 	/* Search if someone is beaconing. This assumes that the
 	 * bss list is populated already */
-	bss = cfg80211_get_bss(wiphy, params->channel, params->bssid,
+	bss = cfg80211_get_bss(wiphy, params->chandef.chan, params->bssid,
 		params->ssid, params->ssid_len,
 		WLAN_CAPABILITY_IBSS, WLAN_CAPABILITY_IBSS);
 
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index f69190b492aa..42be612faf0f 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -1291,21 +1291,23 @@ static int mwifiex_cfg80211_start_ap(struct wiphy *wiphy,
 		return -EINVAL;
 	}
 
-	bss_cfg->channel =
-	    (u8)ieee80211_frequency_to_channel(params->channel->center_freq);
+	bss_cfg->channel = ieee80211_frequency_to_channel(
+				params->chandef.chan->center_freq);
 
 	/* Set appropriate bands */
-	if (params->channel->band == IEEE80211_BAND_2GHZ) {
+	if (params->chandef.chan->band == IEEE80211_BAND_2GHZ) {
 		bss_cfg->band_cfg = BAND_CONFIG_BG;
 
-		if (params->channel_type == NL80211_CHAN_NO_HT)
+		if (cfg80211_get_chandef_type(&params->chandef) ==
+						NL80211_CHAN_NO_HT)
 			config_bands = BAND_B | BAND_G;
 		else
 			config_bands = BAND_B | BAND_G | BAND_GN;
 	} else {
 		bss_cfg->band_cfg = BAND_CONFIG_A;
 
-		if (params->channel_type == NL80211_CHAN_NO_HT)
+		if (cfg80211_get_chandef_type(&params->chandef) ==
+						NL80211_CHAN_NO_HT)
 			config_bands = BAND_A;
 		else
 			config_bands = BAND_AN | BAND_A;
@@ -1678,7 +1680,7 @@ static int mwifiex_set_ibss_params(struct mwifiex_private *priv,
 	int index = 0, i;
 	u8 config_bands = 0;
 
-	if (params->channel->band == IEEE80211_BAND_2GHZ) {
+	if (params->chandef.chan->band == IEEE80211_BAND_2GHZ) {
 		if (!params->basic_rates) {
 			config_bands = BAND_B | BAND_G;
 		} else {
@@ -1703,10 +1705,12 @@ static int mwifiex_set_ibss_params(struct mwifiex_private *priv,
 			}
 		}
 
-		if (params->channel_type != NL80211_CHAN_NO_HT)
+		if (cfg80211_get_chandef_type(&params->chandef) !=
+						NL80211_CHAN_NO_HT)
 			config_bands |= BAND_GN;
 	} else {
-		if (params->channel_type == NL80211_CHAN_NO_HT)
+		if (cfg80211_get_chandef_type(&params->chandef) !=
+						NL80211_CHAN_NO_HT)
 			config_bands = BAND_A;
 		else
 			config_bands = BAND_AN | BAND_A;
@@ -1723,9 +1727,10 @@ static int mwifiex_set_ibss_params(struct mwifiex_private *priv,
 	}
 
 	adapter->sec_chan_offset =
-		mwifiex_chan_type_to_sec_chan_offset(params->channel_type);
-	priv->adhoc_channel =
-		ieee80211_frequency_to_channel(params->channel->center_freq);
+		mwifiex_chan_type_to_sec_chan_offset(
+			cfg80211_get_chandef_type(&params->chandef));
+	priv->adhoc_channel = ieee80211_frequency_to_channel(
+				params->chandef.chan->center_freq);
 
 	wiphy_dbg(wiphy, "info: set ibss band %d, chan %d, chan offset %d\n",
 		  config_bands, priv->adhoc_channel, adapter->sec_chan_offset);
@@ -1759,7 +1764,8 @@ mwifiex_cfg80211_join_ibss(struct wiphy *wiphy, struct net_device *dev,
 
 	ret = mwifiex_cfg80211_assoc(priv, params->ssid_len, params->ssid,
 				     params->bssid, priv->bss_mode,
-				     params->channel, NULL, params->privacy);
+				     params->chandef.chan, NULL,
+				     params->privacy);
 done:
 	if (!ret) {
 		cfg80211_ibss_joined(priv->netdev, priv->cfg_bssid, GFP_KERNEL);
diff --git a/drivers/net/wireless/orinoco/cfg.c b/drivers/net/wireless/orinoco/cfg.c
index 7b751fba7e1f..d01edd2c50c5 100644
--- a/drivers/net/wireless/orinoco/cfg.c
+++ b/drivers/net/wireless/orinoco/cfg.c
@@ -161,24 +161,23 @@ static int orinoco_scan(struct wiphy *wiphy,
 }
 
 static int orinoco_set_monitor_channel(struct wiphy *wiphy,
-				       struct ieee80211_channel *chan,
-				       enum nl80211_channel_type channel_type)
+				       struct cfg80211_chan_def *chandef)
 {
 	struct orinoco_private *priv = wiphy_priv(wiphy);
 	int err = 0;
 	unsigned long flags;
 	int channel;
 
-	if (!chan)
+	if (!chandef->chan)
 		return -EINVAL;
 
-	if (channel_type != NL80211_CHAN_NO_HT)
+	if (cfg80211_get_chandef_type(chandef) != NL80211_CHAN_NO_HT)
 		return -EINVAL;
 
-	if (chan->band != IEEE80211_BAND_2GHZ)
+	if (chandef->chan->band != IEEE80211_BAND_2GHZ)
 		return -EINVAL;
 
-	channel = ieee80211_freq_to_dsss_chan(chan->center_freq);
+	channel = ieee80211_freq_to_dsss_chan(chandef->chan->center_freq);
 
 	if ((channel < 1) || (channel > NUM_CHANNELS) ||
 	     !(priv->channel_mask & (1 << (channel - 1))))
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 5390af36c064..abe1d039be81 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -2293,7 +2293,7 @@ static int rndis_join_ibss(struct wiphy *wiphy, struct net_device *dev,
 {
 	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
 	struct usbnet *usbdev = priv->usbdev;
-	struct ieee80211_channel *channel = params->channel;
+	struct ieee80211_channel *channel = params->chandef.chan;
 	struct ndis_80211_ssid ssid;
 	enum nl80211_auth_type auth_type;
 	int ret, alg, length, chan = -1;
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 1effe0682d28..86f777af79e8 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -305,6 +305,23 @@ struct key_params {
 	u32 cipher;
 };
 
+/**
+ * struct cfg80211_chan_def - channel definition
+ * @chan: the (control) channel
+ * @_type: the channel type, don't use this field,
+ *	use cfg80211_get_chandef_type() if needed.
+ */
+struct cfg80211_chan_def {
+	struct ieee80211_channel *chan;
+	enum nl80211_channel_type _type;
+};
+
+static inline enum nl80211_channel_type
+cfg80211_get_chandef_type(const struct cfg80211_chan_def *chandef)
+{
+	return chandef->_type;
+}
+
 /**
  * enum survey_info_flags - survey information flags
  *
@@ -426,8 +443,7 @@ struct cfg80211_beacon_data {
  *
  * Used to configure an AP interface.
  *
- * @channel: the channel to start the AP on
- * @channel_type: the channel type to use
+ * @chandef: defines the channel to use
  * @beacon: beacon data
  * @beacon_interval: beacon interval
  * @dtim_period: DTIM period
@@ -441,8 +457,7 @@ struct cfg80211_beacon_data {
  * @inactivity_timeout: time in seconds to determine station's inactivity.
  */
 struct cfg80211_ap_settings {
-	struct ieee80211_channel *channel;
-	enum nl80211_channel_type channel_type;
+	struct cfg80211_chan_def chandef;
 
 	struct cfg80211_beacon_data beacon;
 
@@ -909,8 +924,7 @@ struct mesh_config {
 
 /**
  * struct mesh_setup - 802.11s mesh setup configuration
- * @channel: the channel to start the mesh network on
- * @channel_type: the channel type to use
+ * @chandef: defines the channel to use
  * @mesh_id: the mesh ID
  * @mesh_id_len: length of the mesh ID, at least 1 and at most 32 bytes
  * @sync_method: which synchronization method to use
@@ -925,8 +939,7 @@ struct mesh_config {
  * These parameters are fixed when the mesh is created.
  */
 struct mesh_setup {
-	struct ieee80211_channel *channel;
-	enum nl80211_channel_type channel_type;
+	struct cfg80211_chan_def chandef;
 	const u8 *mesh_id;
 	u8 mesh_id_len;
 	u8 sync_method;
@@ -1266,8 +1279,7 @@ struct cfg80211_disassoc_request {
  * @ssid_len: The length of the SSID, will always be non-zero.
  * @bssid: Fixed BSSID requested, maybe be %NULL, if set do not
  *	search for IBSSs with a different BSSID.
- * @channel: The channel to use if no IBSS can be found to join.
- * @channel_type: channel type (HT mode)
+ * @chandef: defines the channel to use if no other IBSS to join can be found
  * @channel_fixed: The channel should be fixed -- do not search for
  *	IBSSs to join on other channels.
  * @ie: information element(s) to include in the beacon
@@ -1285,8 +1297,7 @@ struct cfg80211_disassoc_request {
 struct cfg80211_ibss_params {
 	u8 *ssid;
 	u8 *bssid;
-	struct ieee80211_channel *channel;
-	enum nl80211_channel_type channel_type;
+	struct cfg80211_chan_def chandef;
 	u8 *ie;
 	u8 ssid_len, ie_len;
 	u16 beacon_interval;
@@ -1728,8 +1739,7 @@ struct cfg80211_ops {
 					     struct ieee80211_channel *chan);
 
 	int	(*set_monitor_channel)(struct wiphy *wiphy,
-				       struct ieee80211_channel *chan,
-				       enum nl80211_channel_type channel_type);
+				       struct cfg80211_chan_def *chandef);
 
 	int	(*scan)(struct wiphy *wiphy,
 			struct cfg80211_scan_request *request);
@@ -1855,10 +1865,9 @@ struct cfg80211_ops {
 	void	(*get_et_strings)(struct wiphy *wiphy, struct net_device *dev,
 				  u32 sset, u8 *data);
 
-	struct ieee80211_channel *
-		(*get_channel)(struct wiphy *wiphy,
+	int	(*get_channel)(struct wiphy *wiphy,
 			       struct wireless_dev *wdev,
-			       enum nl80211_channel_type *type);
+			       struct cfg80211_chan_def *chandef);
 
 	int	(*start_p2p_device)(struct wiphy *wiphy,
 				    struct wireless_dev *wdev);
@@ -2466,8 +2475,7 @@ struct wireless_dev {
 	spinlock_t event_lock;
 
 	struct cfg80211_internal_bss *current_bss; /* associated / joined */
-	struct ieee80211_channel *preset_chan;
-	enum nl80211_channel_type preset_chantype;
+	struct cfg80211_chan_def preset_chandef;
 
 	/* for AP and mesh channel tracking */
 	struct ieee80211_channel *channel;
@@ -3563,28 +3571,25 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy,
 				 int freq, int sig_dbm);
 
 /**
- * cfg80211_can_beacon_sec_chan - test if ht40 on extension channel can be used
+ * cfg80211_reg_can_beacon - check if beaconing is allowed
  * @wiphy: the wiphy
- * @chan: main channel
- * @channel_type: HT mode
+ * @chandef: the channel definition
  *
  * This function returns true if there is no secondary channel or the secondary
- * channel can be used for beaconing (i.e. is not a radar channel etc.)
+ * channel(s) can be used for beaconing (i.e. is not a radar channel etc.)
  */
-bool cfg80211_can_beacon_sec_chan(struct wiphy *wiphy,
-				  struct ieee80211_channel *chan,
-				  enum nl80211_channel_type channel_type);
+bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
+			     struct cfg80211_chan_def *chandef);
 
 /*
  * cfg80211_ch_switch_notify - update wdev channel and notify userspace
  * @dev: the device which switched channels
- * @freq: new channel frequency (in MHz)
- * @type: channel type
+ * @chandef: the new channel definition
  *
  * Acquires wdev_lock, so must only be called from sleepable driver context!
  */
-void cfg80211_ch_switch_notify(struct net_device *dev, int freq,
-			       enum nl80211_channel_type type);
+void cfg80211_ch_switch_notify(struct net_device *dev,
+			       struct cfg80211_chan_def *chandef);
 
 /*
  * cfg80211_tdls_oper_request - request userspace to perform TDLS operation
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index ac0241e3539b..fbb2d072cb9e 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -735,14 +735,16 @@ static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
-					 struct ieee80211_channel *chan,
-					 enum nl80211_channel_type channel_type)
+					 struct cfg80211_chan_def *chandef)
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
 	struct ieee80211_sub_if_data *sdata;
+	enum nl80211_channel_type channel_type;
 	int ret = 0;
 
-	if (local->monitor_channel == chan &&
+	channel_type = cfg80211_get_chandef_type(chandef);
+
+	if (local->monitor_channel == chandef->chan &&
 	    local->monitor_channel_type == channel_type)
 		return 0;
 
@@ -754,17 +756,17 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
 		if (sdata) {
 			ieee80211_vif_release_channel(sdata);
 			ret = ieee80211_vif_use_channel(
-					sdata, chan, channel_type,
+					sdata, chandef->chan, channel_type,
 					IEEE80211_CHANCTX_EXCLUSIVE);
 		}
 	} else if (local->open_count == local->monitors) {
-		local->_oper_channel = chan;
+		local->_oper_channel = chandef->chan;
 		local->_oper_channel_type = channel_type;
 		ieee80211_hw_config(local, 0);
 	}
 
 	if (ret == 0) {
-		local->monitor_channel = chan;
+		local->monitor_channel = chandef->chan;
 		local->monitor_channel_type = channel_type;
 	}
 	mutex_unlock(&local->iflist_mtx);
@@ -888,9 +890,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 	sdata->needed_rx_chains = sdata->local->rx_chains;
 
-	err = ieee80211_vif_use_channel(sdata, params->channel,
-					params->channel_type,
-					IEEE80211_CHANCTX_SHARED);
+	err = ieee80211_vif_use_channel(
+		sdata, params->chandef.chan,
+		cfg80211_get_chandef_type(&params->chandef),
+		IEEE80211_CHANCTX_SHARED);
 	if (err)
 		return err;
 
@@ -1707,9 +1710,10 @@ static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev,
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 	sdata->needed_rx_chains = sdata->local->rx_chains;
 
-	err = ieee80211_vif_use_channel(sdata, setup->channel,
-					setup->channel_type,
-					IEEE80211_CHANCTX_SHARED);
+	err = ieee80211_vif_use_channel(
+		sdata, setup->chandef.chan,
+		cfg80211_get_chandef_type(&setup->chandef),
+		IEEE80211_CHANCTX_SHARED);
 	if (err)
 		return err;
 
@@ -3110,23 +3114,24 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
 	return 0;
 }
 
-static struct ieee80211_channel *
-ieee80211_cfg_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev,
-			  enum nl80211_channel_type *type)
+static int ieee80211_cfg_get_channel(struct wiphy *wiphy,
+				     struct wireless_dev *wdev,
+				     struct cfg80211_chan_def *chandef)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
 	struct ieee80211_chanctx_conf *chanctx_conf;
-	struct ieee80211_channel *chan = NULL;
+	int ret = -ENODATA;
 
 	rcu_read_lock();
 	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 	if (chanctx_conf) {
-		*type = chanctx_conf->channel_type;
-		chan = chanctx_conf->channel;
+		chandef->chan = chanctx_conf->channel;
+		chandef->_type = chanctx_conf->channel_type;
+		ret = 0;
 	}
 	rcu_read_unlock();
 
-	return chan;
+	return ret;
 }
 
 #ifdef CONFIG_PM
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 845973b67a73..bed616fd97e9 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -51,7 +51,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	struct cfg80211_bss *bss;
 	u32 bss_change;
 	u8 supp_rates[IEEE80211_MAX_SUPP_RATES];
-	enum nl80211_channel_type channel_type;
+	struct cfg80211_chan_def chandef;
 
 	lockdep_assert_held(&ifibss->mtx);
 
@@ -79,12 +79,13 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 
 	sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0;
 
-	channel_type = ifibss->channel_type;
-	if (!cfg80211_can_beacon_sec_chan(local->hw.wiphy, chan, channel_type))
-		channel_type = NL80211_CHAN_HT20;
+	chandef.chan = chan;
+	chandef._type = ifibss->channel_type;
+	if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef))
+		chandef._type = NL80211_CHAN_HT20;
 
 	ieee80211_vif_release_channel(sdata);
-	if (ieee80211_vif_use_channel(sdata, chan, channel_type,
+	if (ieee80211_vif_use_channel(sdata, chan, chandef._type,
 				      ifibss->fixed_channel ?
 					IEEE80211_CHANCTX_SHARED :
 					IEEE80211_CHANCTX_EXCLUSIVE)) {
@@ -158,7 +159,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 		       ifibss->ie, ifibss->ie_len);
 
 	/* add HT capability and information IEs */
-	if (channel_type && sband->ht_cap.ht_supported) {
+	if (chandef._type != NL80211_CHAN_NO_HT &&
+	    sband->ht_cap.ht_supported) {
 		pos = skb_put(skb, 4 +
 				   sizeof(struct ieee80211_ht_cap) +
 				   sizeof(struct ieee80211_ht_operation));
@@ -170,7 +172,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 		 * keep them at 0
 		 */
 		pos = ieee80211_ie_build_ht_oper(pos, &sband->ht_cap,
-						 chan, channel_type, 0);
+						 chan, chandef._type, 0);
 	}
 
 	if (local->hw.queues >= IEEE80211_NUM_ACS) {
@@ -1078,8 +1080,9 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 
 	sdata->vif.bss_conf.beacon_int = params->beacon_interval;
 
-	sdata->u.ibss.channel = params->channel;
-	sdata->u.ibss.channel_type = params->channel_type;
+	sdata->u.ibss.channel = params->chandef.chan;
+	sdata->u.ibss.channel_type =
+		cfg80211_get_chandef_type(&params->chandef);
 	sdata->u.ibss.fixed_channel = params->channel_fixed;
 
 	if (params->ie) {
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 48febd2160ba..e834422de40a 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -11,51 +11,15 @@
 #include "core.h"
 #include "rdev-ops.h"
 
-struct ieee80211_channel *
-rdev_freq_to_chan(struct cfg80211_registered_device *rdev,
-		  int freq, enum nl80211_channel_type channel_type)
-{
-	struct ieee80211_channel *chan;
-	struct ieee80211_sta_ht_cap *ht_cap;
-
-	chan = ieee80211_get_channel(&rdev->wiphy, freq);
-
-	/* Primary channel not allowed */
-	if (!chan || chan->flags & IEEE80211_CHAN_DISABLED)
-		return NULL;
-
-	if (channel_type == NL80211_CHAN_HT40MINUS &&
-	    chan->flags & IEEE80211_CHAN_NO_HT40MINUS)
-		return NULL;
-	else if (channel_type == NL80211_CHAN_HT40PLUS &&
-		 chan->flags & IEEE80211_CHAN_NO_HT40PLUS)
-		return NULL;
-
-	ht_cap = &rdev->wiphy.bands[chan->band]->ht_cap;
-
-	if (channel_type != NL80211_CHAN_NO_HT) {
-		if (!ht_cap->ht_supported)
-			return NULL;
-
-		if (channel_type != NL80211_CHAN_HT20 &&
-		    (!(ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) ||
-		    ht_cap->cap & IEEE80211_HT_CAP_40MHZ_INTOLERANT))
-			return NULL;
-	}
-
-	return chan;
-}
-
-bool cfg80211_can_beacon_sec_chan(struct wiphy *wiphy,
-				  struct ieee80211_channel *chan,
-				  enum nl80211_channel_type channel_type)
+bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
+			     struct cfg80211_chan_def *chandef)
 {
 	struct ieee80211_channel *sec_chan;
 	int diff;
 
-	trace_cfg80211_can_beacon_sec_chan(wiphy, chan, channel_type);
+	trace_cfg80211_reg_can_beacon(wiphy, chandef);
 
-	switch (channel_type) {
+	switch (chandef->_type) {
 	case NL80211_CHAN_HT40PLUS:
 		diff = 20;
 		break;
@@ -67,7 +31,8 @@ bool cfg80211_can_beacon_sec_chan(struct wiphy *wiphy,
 		return true;
 	}
 
-	sec_chan = ieee80211_get_channel(wiphy, chan->center_freq + diff);
+	sec_chan = ieee80211_get_channel(wiphy,
+					 chandef->chan->center_freq + diff);
 	if (!sec_chan) {
 		trace_cfg80211_return_bool(false);
 		return false;
@@ -84,23 +49,17 @@ bool cfg80211_can_beacon_sec_chan(struct wiphy *wiphy,
 	trace_cfg80211_return_bool(true);
 	return true;
 }
-EXPORT_SYMBOL(cfg80211_can_beacon_sec_chan);
+EXPORT_SYMBOL(cfg80211_reg_can_beacon);
 
 int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev,
-				 int freq, enum nl80211_channel_type chantype)
+				 struct cfg80211_chan_def *chandef)
 {
-	struct ieee80211_channel *chan;
-
 	if (!rdev->ops->set_monitor_channel)
 		return -EOPNOTSUPP;
 	if (!cfg80211_has_monitors_only(rdev))
 		return -EBUSY;
 
-	chan = rdev_freq_to_chan(rdev, freq, chantype);
-	if (!chan)
-		return -EINVAL;
-
-	return rdev_set_monitor_channel(rdev, chan, chantype);
+	return rdev_set_monitor_channel(rdev, chandef);
 }
 
 void
diff --git a/net/wireless/core.h b/net/wireless/core.h
index b0a09cf56e06..6183a0d25b8b 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -309,9 +309,9 @@ int cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 		       const struct mesh_config *conf);
 int cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
 			struct net_device *dev);
-int cfg80211_set_mesh_freq(struct cfg80211_registered_device *rdev,
-			   struct wireless_dev *wdev, int freq,
-			   enum nl80211_channel_type channel_type);
+int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
+			      struct wireless_dev *wdev,
+			      struct cfg80211_chan_def *chandef);
 
 /* AP */
 int cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
@@ -470,11 +470,8 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
 		        struct ieee80211_channel **chan,
 		        enum cfg80211_chan_mode *chanmode);
 
-struct ieee80211_channel *
-rdev_freq_to_chan(struct cfg80211_registered_device *rdev,
-		  int freq, enum nl80211_channel_type channel_type);
 int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev,
-				 int freq, enum nl80211_channel_type chantype);
+				 struct cfg80211_chan_def *chandef);
 
 int ieee80211_get_ratemask(struct ieee80211_supported_band *sband,
 			   const u8 *rates, unsigned int n_rates,
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index 27941d5db72b..ccc8865dfadb 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -100,9 +100,9 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 		* 11a for maximum compatibility.
 		*/
 		struct ieee80211_supported_band *sband =
-			rdev->wiphy.bands[params->channel->band];
+			rdev->wiphy.bands[params->chandef.chan->band];
 		int j;
-		u32 flag = params->channel->band == IEEE80211_BAND_5GHZ ?
+		u32 flag = params->chandef.chan->band == IEEE80211_BAND_5GHZ ?
 			IEEE80211_RATE_MANDATORY_A :
 			IEEE80211_RATE_MANDATORY_B;
 
@@ -118,11 +118,11 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 
 	wdev->ibss_fixed = params->channel_fixed;
 #ifdef CONFIG_CFG80211_WEXT
-	wdev->wext.ibss.channel = params->channel;
+	wdev->wext.ibss.chandef = params->chandef;
 #endif
 	wdev->sme_state = CFG80211_SME_CONNECTING;
 
-	err = cfg80211_can_use_chan(rdev, wdev, params->channel,
+	err = cfg80211_can_use_chan(rdev, wdev, params->chandef.chan,
 				    params->channel_fixed
 				    ? CHAN_MODE_SHARED
 				    : CHAN_MODE_EXCLUSIVE);
@@ -251,7 +251,9 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev,
 		wdev->wext.ibss.beacon_interval = 100;
 
 	/* try to find an IBSS channel if none requested ... */
-	if (!wdev->wext.ibss.channel) {
+	if (!wdev->wext.ibss.chandef.chan) {
+		wdev->wext.ibss.chandef._type = NL80211_CHAN_NO_HT;
+
 		for (band = 0; band < IEEE80211_NUM_BANDS; band++) {
 			struct ieee80211_supported_band *sband;
 			struct ieee80211_channel *chan;
@@ -266,15 +268,15 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev,
 					continue;
 				if (chan->flags & IEEE80211_CHAN_DISABLED)
 					continue;
-				wdev->wext.ibss.channel = chan;
+				wdev->wext.ibss.chandef.chan = chan;
 				break;
 			}
 
-			if (wdev->wext.ibss.channel)
+			if (wdev->wext.ibss.chandef.chan)
 				break;
 		}
 
-		if (!wdev->wext.ibss.channel)
+		if (!wdev->wext.ibss.chandef.chan)
 			return -EINVAL;
 	}
 
@@ -336,7 +338,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
 			return -EINVAL;
 	}
 
-	if (wdev->wext.ibss.channel == chan)
+	if (wdev->wext.ibss.chandef.chan == chan)
 		return 0;
 
 	wdev_lock(wdev);
@@ -349,7 +351,8 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
 		return err;
 
 	if (chan) {
-		wdev->wext.ibss.channel = chan;
+		wdev->wext.ibss.chandef.chan = chan;
+		wdev->wext.ibss.chandef._type = NL80211_CHAN_NO_HT;
 		wdev->wext.ibss.channel_fixed = true;
 	} else {
 		/* cfg80211_ibss_wext_join will pick one if needed */
@@ -379,8 +382,8 @@ int cfg80211_ibss_wext_giwfreq(struct net_device *dev,
 	wdev_lock(wdev);
 	if (wdev->current_bss)
 		chan = wdev->current_bss->pub.channel;
-	else if (wdev->wext.ibss.channel)
-		chan = wdev->wext.ibss.channel;
+	else if (wdev->wext.ibss.chandef.chan)
+		chan = wdev->wext.ibss.chandef.chan;
 	wdev_unlock(wdev);
 
 	if (chan) {
diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
index 966cfc4cd79d..12b5a570a306 100644
--- a/net/wireless/mesh.c
+++ b/net/wireless/mesh.c
@@ -73,8 +73,6 @@ const struct mesh_config default_mesh_config = {
 
 const struct mesh_setup default_mesh_setup = {
 	/* cfg80211_join_mesh() will pick a channel if needed */
-	.channel = NULL,
-	.channel_type = NL80211_CHAN_NO_HT,
 	.sync_method = IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET,
 	.path_sel_proto = IEEE80211_PATH_PROTOCOL_HWMP,
 	.path_metric = IEEE80211_PATH_METRIC_AIRTIME,
@@ -111,13 +109,12 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 	if (!rdev->ops->join_mesh)
 		return -EOPNOTSUPP;
 
-	if (!setup->channel) {
+	if (!setup->chandef.chan) {
 		/* if no channel explicitly given, use preset channel */
-		setup->channel = wdev->preset_chan;
-		setup->channel_type = wdev->preset_chantype;
+		setup->chandef = wdev->preset_chandef;
 	}
 
-	if (!setup->channel) {
+	if (!setup->chandef.chan) {
 		/* if we don't have that either, use the first usable channel */
 		enum ieee80211_band band;
 
@@ -137,26 +134,25 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 						   IEEE80211_CHAN_DISABLED |
 						   IEEE80211_CHAN_RADAR))
 					continue;
-				setup->channel = chan;
+				setup->chandef.chan = chan;
 				break;
 			}
 
-			if (setup->channel)
+			if (setup->chandef.chan)
 				break;
 		}
 
 		/* no usable channel ... */
-		if (!setup->channel)
+		if (!setup->chandef.chan)
 			return -EINVAL;
 
-		setup->channel_type = NL80211_CHAN_NO_HT;
+		setup->chandef._type = NL80211_CHAN_NO_HT;
 	}
 
-	if (!cfg80211_can_beacon_sec_chan(&rdev->wiphy, setup->channel,
-					  setup->channel_type))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &setup->chandef))
 		return -EINVAL;
 
-	err = cfg80211_can_use_chan(rdev, wdev, setup->channel,
+	err = cfg80211_can_use_chan(rdev, wdev, setup->chandef.chan,
 				    CHAN_MODE_SHARED);
 	if (err)
 		return err;
@@ -165,7 +161,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 	if (!err) {
 		memcpy(wdev->ssid, setup->mesh_id, setup->mesh_id_len);
 		wdev->mesh_id_len = setup->mesh_id_len;
-		wdev->channel = setup->channel;
+		wdev->channel = setup->chandef.chan;
 	}
 
 	return err;
@@ -188,20 +184,12 @@ int cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 	return err;
 }
 
-int cfg80211_set_mesh_freq(struct cfg80211_registered_device *rdev,
-			   struct wireless_dev *wdev, int freq,
-			   enum nl80211_channel_type channel_type)
+int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
+			      struct wireless_dev *wdev,
+			      struct cfg80211_chan_def *chandef)
 {
-	struct ieee80211_channel *channel;
 	int err;
 
-	channel = rdev_freq_to_chan(rdev, freq, channel_type);
-	if (!channel || !cfg80211_can_beacon_sec_chan(&rdev->wiphy,
-						      channel,
-						      channel_type)) {
-		return -EINVAL;
-	}
-
 	/*
 	 * Workaround for libertas (only!), it puts the interface
 	 * into mesh mode but doesn't implement join_mesh. Instead,
@@ -210,21 +198,21 @@ int cfg80211_set_mesh_freq(struct cfg80211_registered_device *rdev,
 	 * compatible with 802.11 mesh.
 	 */
 	if (rdev->ops->libertas_set_mesh_channel) {
-		if (channel_type != NL80211_CHAN_NO_HT)
+		if (chandef->_type != NL80211_CHAN_NO_HT)
 			return -EINVAL;
 
 		if (!netif_running(wdev->netdev))
 			return -ENETDOWN;
 
-		err = cfg80211_can_use_chan(rdev, wdev, channel,
+		err = cfg80211_can_use_chan(rdev, wdev, chandef->chan,
 					    CHAN_MODE_SHARED);
 		if (err)
 			return err;
 
 		err = rdev_libertas_set_mesh_channel(rdev, wdev->netdev,
-						     channel);
+						     chandef->chan);
 		if (!err)
-			wdev->channel = channel;
+			wdev->channel = chandef->chan;
 
 		return err;
 	}
@@ -232,8 +220,7 @@ int cfg80211_set_mesh_freq(struct cfg80211_registered_device *rdev,
 	if (wdev->mesh_id_len)
 		return -EBUSY;
 
-	wdev->preset_chan = channel;
-	wdev->preset_chantype = channel_type;
+	wdev->preset_chandef = *chandef;
 	return 0;
 }
 
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index a9646b53a095..5e8123ee63fd 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -988,15 +988,14 @@ void cfg80211_pmksa_candidate_notify(struct net_device *dev, int index,
 }
 EXPORT_SYMBOL(cfg80211_pmksa_candidate_notify);
 
-void cfg80211_ch_switch_notify(struct net_device *dev, int freq,
-			       enum nl80211_channel_type type)
+void cfg80211_ch_switch_notify(struct net_device *dev,
+			       struct cfg80211_chan_def *chandef)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
-	struct ieee80211_channel *chan;
 
-	trace_cfg80211_ch_switch_notify(dev, freq, type);
+	trace_cfg80211_ch_switch_notify(dev, chandef);
 
 	wdev_lock(wdev);
 
@@ -1004,12 +1003,8 @@ void cfg80211_ch_switch_notify(struct net_device *dev, int freq,
 		    wdev->iftype != NL80211_IFTYPE_P2P_GO))
 		goto out;
 
-	chan = rdev_freq_to_chan(rdev, freq, type);
-	if (WARN_ON(!chan))
-		goto out;
-
-	wdev->channel = chan;
-	nl80211_ch_switch_notify(rdev, dev, freq, type, GFP_KERNEL);
+	wdev->channel = chandef->chan;
+	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL);
 out:
 	wdev_unlock(wdev);
 	return;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e880f4494950..999108cd947c 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1381,30 +1381,82 @@ static bool nl80211_valid_channel_type(struct genl_info *info,
 	return true;
 }
 
+static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
+				 struct genl_info *info,
+				 struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_sta_ht_cap *ht_cap;
+	struct ieee80211_channel *sc;
+	u32 control_freq;
+	int offs;
+
+	if (!info->attrs[NL80211_ATTR_WIPHY_FREQ])
+		return -EINVAL;
+
+	control_freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]);
+
+	chandef->chan = ieee80211_get_channel(&rdev->wiphy, control_freq);
+	chandef->_type = NL80211_CHAN_NO_HT;
+
+	if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] &&
+	    !nl80211_valid_channel_type(info, &chandef->_type))
+		return -EINVAL;
+
+	/* Primary channel not allowed */
+	if (!chandef->chan || chandef->chan->flags & IEEE80211_CHAN_DISABLED)
+		return -EINVAL;
+
+	ht_cap = &rdev->wiphy.bands[chandef->chan->band]->ht_cap;
+
+	switch (chandef->_type) {
+	case NL80211_CHAN_NO_HT:
+		break;
+	case NL80211_CHAN_HT40MINUS:
+		if (chandef->chan->flags & IEEE80211_CHAN_NO_HT40MINUS)
+			return -EINVAL;
+		offs = -20;
+		/* fall through */
+	case NL80211_CHAN_HT40PLUS:
+		if (chandef->_type == NL80211_CHAN_HT40PLUS) {
+			if (chandef->chan->flags & IEEE80211_CHAN_NO_HT40PLUS)
+				return -EINVAL;
+			offs = 20;
+		}
+		if (!(ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) ||
+		    ht_cap->cap & IEEE80211_HT_CAP_40MHZ_INTOLERANT)
+			return -EINVAL;
+
+		sc = ieee80211_get_channel(&rdev->wiphy,
+					   chandef->chan->center_freq + offs);
+		if (!sc || sc->flags & IEEE80211_CHAN_DISABLED)
+			return -EINVAL;
+		/* fall through */
+	case NL80211_CHAN_HT20:
+		if (!ht_cap->ht_supported)
+			return -EINVAL;
+		break;
+	}
+
+	return 0;
+}
+
 static int __nl80211_set_channel(struct cfg80211_registered_device *rdev,
 				 struct wireless_dev *wdev,
 				 struct genl_info *info)
 {
-	struct ieee80211_channel *channel;
-	enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT;
-	u32 freq;
+	struct cfg80211_chan_def chandef;
 	int result;
 	enum nl80211_iftype iftype = NL80211_IFTYPE_MONITOR;
 
 	if (wdev)
 		iftype = wdev->iftype;
 
-	if (!info->attrs[NL80211_ATTR_WIPHY_FREQ])
-		return -EINVAL;
-
 	if (!nl80211_can_set_dev_channel(wdev))
 		return -EOPNOTSUPP;
 
-	if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] &&
-	    !nl80211_valid_channel_type(info, &channel_type))
-		return -EINVAL;
-
-	freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]);
+	result = nl80211_parse_chandef(rdev, info, &chandef);
+	if (result)
+		return result;
 
 	mutex_lock(&rdev->devlist_mtx);
 	switch (iftype) {
@@ -1414,22 +1466,18 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev,
 			result = -EBUSY;
 			break;
 		}
-		channel = rdev_freq_to_chan(rdev, freq, channel_type);
-		if (!channel || !cfg80211_can_beacon_sec_chan(&rdev->wiphy,
-							      channel,
-							      channel_type)) {
+		if (!cfg80211_reg_can_beacon(&rdev->wiphy, &chandef)) {
 			result = -EINVAL;
 			break;
 		}
-		wdev->preset_chan = channel;
-		wdev->preset_chantype = channel_type;
+		wdev->preset_chandef = chandef;
 		result = 0;
 		break;
 	case NL80211_IFTYPE_MESH_POINT:
-		result = cfg80211_set_mesh_freq(rdev, wdev, freq, channel_type);
+		result = cfg80211_set_mesh_channel(rdev, wdev, &chandef);
 		break;
 	case NL80211_IFTYPE_MONITOR:
-		result = cfg80211_set_monitor_channel(rdev, freq, channel_type);
+		result = cfg80211_set_monitor_channel(rdev, &chandef);
 		break;
 	default:
 		result = -EINVAL;
@@ -1749,6 +1797,17 @@ static inline u64 wdev_id(struct wireless_dev *wdev)
 	       ((u64)wiphy_to_dev(wdev->wiphy)->wiphy_idx << 32);
 }
 
+static int nl80211_send_chandef(struct sk_buff *msg,
+				 struct cfg80211_chan_def *chandef)
+{
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ,
+			chandef->chan->center_freq))
+		return -ENOBUFS;
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, chandef->_type))
+		return -ENOBUFS;
+	return 0;
+}
+
 static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags,
 			      struct cfg80211_registered_device *rdev,
 			      struct wireless_dev *wdev)
@@ -1775,16 +1834,14 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag
 		goto nla_put_failure;
 
 	if (rdev->ops->get_channel) {
-		struct ieee80211_channel *chan;
-		enum nl80211_channel_type channel_type;
-
-		chan = rdev_get_channel(rdev, wdev, &channel_type);
-		if (chan &&
-		    (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ,
-				 chan->center_freq) ||
-		     nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE,
-				 channel_type)))
-			goto nla_put_failure;
+		int ret;
+		struct cfg80211_chan_def chandef;
+
+		ret = rdev_get_channel(rdev, wdev, &chandef);
+		if (ret == 0) {
+			if (nl80211_send_chandef(msg, &chandef))
+				goto nla_put_failure;
+		}
 	}
 
 	if (wdev->ssid_len) {
@@ -2492,11 +2549,10 @@ static bool nl80211_get_ap_channel(struct cfg80211_registered_device *rdev,
 		    wdev->iftype != NL80211_IFTYPE_P2P_GO)
 			continue;
 
-		if (!wdev->preset_chan)
+		if (!wdev->preset_chandef.chan)
 			continue;
 
-		params->channel = wdev->preset_chan;
-		params->channel_type = wdev->preset_chantype;
+		params->chandef = wdev->preset_chandef;
 		ret = true;
 		break;
 	}
@@ -2618,30 +2674,19 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) {
-		enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT;
-
-		if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] &&
-		    !nl80211_valid_channel_type(info, &channel_type))
-			return -EINVAL;
-
-		params.channel = rdev_freq_to_chan(rdev,
-			nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]),
-			channel_type);
-		if (!params.channel)
-			return -EINVAL;
-		params.channel_type = channel_type;
-	} else if (wdev->preset_chan) {
-		params.channel = wdev->preset_chan;
-		params.channel_type = wdev->preset_chantype;
+		err = nl80211_parse_chandef(rdev, info, &params.chandef);
+		if (err)
+			return err;
+	} else if (wdev->preset_chandef.chan) {
+		params.chandef = wdev->preset_chandef;
 	} else if (!nl80211_get_ap_channel(rdev, &params))
 		return -EINVAL;
 
-	if (!cfg80211_can_beacon_sec_chan(&rdev->wiphy, params.channel,
-					  params.channel_type))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef))
 		return -EINVAL;
 
 	mutex_lock(&rdev->devlist_mtx);
-	err = cfg80211_can_use_chan(rdev, wdev, params.channel,
+	err = cfg80211_can_use_chan(rdev, wdev, params.chandef.chan,
 				    CHAN_MODE_SHARED);
 	mutex_unlock(&rdev->devlist_mtx);
 
@@ -2650,10 +2695,9 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 
 	err = rdev_start_ap(rdev, dev, &params);
 	if (!err) {
-		wdev->preset_chan = params.channel;
-		wdev->preset_chantype = params.channel_type;
+		wdev->preset_chandef = params.chandef;
 		wdev->beacon_interval = params.beacon_interval;
-		wdev->channel = params.channel;
+		wdev->channel = params.chandef.chan;
 		wdev->ssid_len = params.ssid_len;
 		memcpy(wdev->ssid, params.ssid, wdev->ssid_len);
 	}
@@ -5330,8 +5374,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 	if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE]))
 		return -EINVAL;
 
-	if (!info->attrs[NL80211_ATTR_WIPHY_FREQ] ||
-	    !info->attrs[NL80211_ATTR_SSID] ||
+	if (!info->attrs[NL80211_ATTR_SSID] ||
 	    !nla_len(info->attrs[NL80211_ATTR_SSID]))
 		return -EINVAL;
 
@@ -5366,34 +5409,11 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 		ibss.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]);
 	}
 
-	if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) {
-		enum nl80211_channel_type channel_type;
-
-		if (!nl80211_valid_channel_type(info, &channel_type))
-			return -EINVAL;
-
-		if (channel_type != NL80211_CHAN_NO_HT &&
-		    !(wiphy->features & NL80211_FEATURE_HT_IBSS))
-			return -EINVAL;
-
-		ibss.channel_type = channel_type;
-	} else {
-		ibss.channel_type = NL80211_CHAN_NO_HT;
-	}
-
-	ibss.channel = rdev_freq_to_chan(rdev,
-		nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]),
-		ibss.channel_type);
-	if (!ibss.channel ||
-	    ibss.channel->flags & IEEE80211_CHAN_NO_IBSS ||
-	    ibss.channel->flags & IEEE80211_CHAN_DISABLED)
-		return -EINVAL;
+	err = nl80211_parse_chandef(rdev, info, &ibss.chandef);
+	if (err)
+		return err;
 
-	/* Both channels should be able to initiate communication */
-	if ((ibss.channel_type == NL80211_CHAN_HT40PLUS ||
-	     ibss.channel_type == NL80211_CHAN_HT40MINUS) &&
-	    !cfg80211_can_beacon_sec_chan(&rdev->wiphy, ibss.channel,
-					  ibss.channel_type))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &ibss.chandef))
 		return -EINVAL;
 
 	ibss.channel_fixed = !!info->attrs[NL80211_ATTR_FREQ_FIXED];
@@ -5405,7 +5425,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 		int n_rates =
 			nla_len(info->attrs[NL80211_ATTR_BSS_BASIC_RATES]);
 		struct ieee80211_supported_band *sband =
-			wiphy->bands[ibss.channel->band];
+			wiphy->bands[ibss.chandef.chan->band];
 
 		err = ieee80211_get_ratemask(sband, rates, n_rates,
 					     &ibss.basic_rates);
@@ -5427,7 +5447,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 		if (IS_ERR(connkeys))
 			return PTR_ERR(connkeys);
 
-		if ((ibss.channel_type != NL80211_CHAN_NO_HT) && no_ht) {
+		if ((ibss.chandef._type != NL80211_CHAN_NO_HT) && no_ht) {
 			kfree(connkeys);
 			return -EINVAL;
 		}
@@ -5948,11 +5968,11 @@ static int nl80211_remain_on_channel(struct sk_buff *skb,
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct wireless_dev *wdev = info->user_ptr[1];
-	struct ieee80211_channel *chan;
+	struct cfg80211_chan_def chandef;
 	struct sk_buff *msg;
 	void *hdr;
 	u64 cookie;
-	u32 freq, duration;
+	u32 duration;
 	int err;
 
 	if (!info->attrs[NL80211_ATTR_WIPHY_FREQ] ||
@@ -5973,14 +5993,9 @@ static int nl80211_remain_on_channel(struct sk_buff *skb,
 	    duration > rdev->wiphy.max_remain_on_channel_duration)
 		return -EINVAL;
 
-	if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] &&
-	    !nl80211_valid_channel_type(info, NULL))
-		return -EINVAL;
-
-	freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]);
-	chan = rdev_freq_to_chan(rdev, freq, NL80211_CHAN_NO_HT);
-	if (chan == NULL)
-		return -EINVAL;
+	err = nl80211_parse_chandef(rdev, info, &chandef);
+	if (err)
+		return err;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
@@ -5994,7 +6009,8 @@ static int nl80211_remain_on_channel(struct sk_buff *skb,
 		goto free_msg;
 	}
 
-	err = rdev_remain_on_channel(rdev, wdev, chan, duration, &cookie);
+	err = rdev_remain_on_channel(rdev, wdev, chandef.chan,
+				     duration, &cookie);
 
 	if (err)
 		goto free_msg;
@@ -6213,8 +6229,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct wireless_dev *wdev = info->user_ptr[1];
-	struct ieee80211_channel *chan;
-	u32 freq;
+	struct cfg80211_chan_def chandef;
 	int err;
 	void *hdr = NULL;
 	u64 cookie;
@@ -6224,8 +6239,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 
 	dont_wait_for_ack = info->attrs[NL80211_ATTR_DONT_WAIT_FOR_ACK];
 
-	if (!info->attrs[NL80211_ATTR_FRAME] ||
-	    !info->attrs[NL80211_ATTR_WIPHY_FREQ])
+	if (!info->attrs[NL80211_ATTR_FRAME])
 		return -EINVAL;
 
 	if (!rdev->ops->mgmt_tx)
@@ -6260,10 +6274,6 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 
 	}
 
-	if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] &&
-	    !nl80211_valid_channel_type(info, NULL))
-		return -EINVAL;
-
 	offchan = info->attrs[NL80211_ATTR_OFFCHANNEL_TX_OK];
 
 	if (offchan && !(rdev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX))
@@ -6271,10 +6281,9 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 
 	no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]);
 
-	freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]);
-	chan = rdev_freq_to_chan(rdev, freq, NL80211_CHAN_NO_HT);
-	if (chan == NULL)
-		return -EINVAL;
+	err = nl80211_parse_chandef(rdev, info, &chandef);
+	if (err)
+		return err;
 
 	if (!dont_wait_for_ack) {
 		msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -6290,7 +6299,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	err = cfg80211_mlme_mgmt_tx(rdev, wdev, chan, offchan, wait,
+	err = cfg80211_mlme_mgmt_tx(rdev, wdev, chandef.chan, offchan, wait,
 				    nla_data(info->attrs[NL80211_ATTR_FRAME]),
 				    nla_len(info->attrs[NL80211_ATTR_FRAME]),
 				    no_cck, dont_wait_for_ack, &cookie);
@@ -6554,21 +6563,12 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) {
-		enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT;
-
-		if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] &&
-		    !nl80211_valid_channel_type(info, &channel_type))
-			return -EINVAL;
-
-		setup.channel = rdev_freq_to_chan(rdev,
-			nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]),
-			channel_type);
-		if (!setup.channel)
-			return -EINVAL;
-		setup.channel_type = channel_type;
+		err = nl80211_parse_chandef(rdev, info, &setup.chandef);
+		if (err)
+			return err;
 	} else {
 		/* cfg80211_join_mesh() will sort it out */
-		setup.channel = NULL;
+		setup.chandef.chan = NULL;
 	}
 
 	return cfg80211_join_mesh(rdev, dev, &setup, &cfg);
@@ -8800,8 +8800,8 @@ void nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev,
 }
 
 void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
-			      struct net_device *netdev, int freq,
-			      enum nl80211_channel_type type, gfp_t gfp)
+			      struct net_device *netdev,
+			      struct cfg80211_chan_def *chandef, gfp_t gfp)
 {
 	struct sk_buff *msg;
 	void *hdr;
@@ -8816,9 +8816,10 @@ void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 		return;
 	}
 
-	if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) ||
-	    nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, freq) ||
-	    nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, type))
+	if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex))
+		goto nla_put_failure;
+
+	if (nl80211_send_chandef(msg, chandef))
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index 7adbd767dbfd..2acba8477e9d 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -127,8 +127,8 @@ void nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev,
 				    const u8 *bssid, bool preauth, gfp_t gfp);
 
 void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
-			      struct net_device *dev, int freq,
-			      enum nl80211_channel_type type, gfp_t gfp);
+			      struct net_device *dev,
+			      struct cfg80211_chan_def *chandef, gfp_t gfp);
 
 bool nl80211_unexpected_frame(struct net_device *dev,
 			      const u8 *addr, gfp_t gfp);
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index ee54a5aa4381..6c0c8191f837 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -359,12 +359,11 @@ rdev_libertas_set_mesh_channel(struct cfg80211_registered_device *rdev,
 
 static inline int
 rdev_set_monitor_channel(struct cfg80211_registered_device *rdev,
-			 struct ieee80211_channel *chan,
-			 enum nl80211_channel_type channel_type)
+			 struct cfg80211_chan_def *chandef)
 {
 	int ret;
-	trace_rdev_set_monitor_channel(&rdev->wiphy, chan, channel_type);
-	ret = rdev->ops->set_monitor_channel(&rdev->wiphy, chan, channel_type);
+	trace_rdev_set_monitor_channel(&rdev->wiphy, chandef);
+	ret = rdev->ops->set_monitor_channel(&rdev->wiphy, chandef);
 	trace_rdev_return_int(&rdev->wiphy, ret);
 	return ret;
 }
@@ -844,14 +843,17 @@ static inline void rdev_get_et_strings(struct cfg80211_registered_device *rdev,
 	trace_rdev_return_void(&rdev->wiphy);
 }
 
-static inline struct ieee80211_channel
-*rdev_get_channel(struct cfg80211_registered_device *rdev,
-		  struct wireless_dev *wdev, enum nl80211_channel_type *type)
+static inline int
+rdev_get_channel(struct cfg80211_registered_device *rdev,
+		 struct wireless_dev *wdev,
+		 struct cfg80211_chan_def *chandef)
 {
-	struct ieee80211_channel *ret;
+	int ret;
+
 	trace_rdev_get_channel(&rdev->wiphy, wdev);
-	ret = rdev->ops->get_channel(&rdev->wiphy, wdev, type);
-	trace_rdev_return_channel(&rdev->wiphy, ret, *type);
+	ret = rdev->ops->get_channel(&rdev->wiphy, wdev, chandef);
+	trace_rdev_return_chandef(&rdev->wiphy, ret, chandef);
+
 	return ret;
 }
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index ed10833f9a3a..1370d52b1393 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -126,6 +126,26 @@
 #define CHAN_PR_FMT ", band: %d, freq: %u"
 #define CHAN_PR_ARG __entry->band, __entry->center_freq
 
+#define CHAN_DEF_ENTRY __field(enum ieee80211_band, band)	\
+		       __field(u16, center_freq)		\
+		       __field(u32, channel_type)
+#define CHAN_DEF_ASSIGN(chandef)					\
+	do {								\
+		if ((chandef) && (chandef)->chan) {			\
+			__entry->band = (chandef)->chan->band;		\
+			__entry->center_freq =				\
+				(chandef)->chan->center_freq;		\
+			__entry->channel_type = (chandef)->_type;	\
+		} else {						\
+			__entry->band = 0;				\
+			__entry->center_freq = 0;			\
+			__entry->channel_type = 0;			\
+		}							\
+	} while (0)
+#define CHAN_DEF_PR_FMT ", band: %d, freq: %u, chantype: %d"
+#define CHAN_DEF_PR_ARG __entry->band, __entry->center_freq,		\
+			__entry->channel_type
+
 #define SINFO_ENTRY __field(int, generation)	    \
 		    __field(u32, connected_time)    \
 		    __field(u32, inactive_time)	    \
@@ -433,7 +453,7 @@ TRACE_EVENT(rdev_start_ap,
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		NETDEV_ENTRY
-		CHAN_ENTRY
+		CHAN_DEF_ENTRY
 		__field(int, beacon_interval)
 		__field(int, dtim_period)
 		__array(char, ssid, IEEE80211_MAX_SSID_LEN + 1)
@@ -446,7 +466,7 @@ TRACE_EVENT(rdev_start_ap,
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		NETDEV_ASSIGN;
-		CHAN_ASSIGN(settings->channel);
+		CHAN_DEF_ASSIGN(&settings->chandef);
 		__entry->beacon_interval = settings->beacon_interval;
 		__entry->dtim_period = settings->dtim_period;
 		__entry->hidden_ssid = settings->hidden_ssid;
@@ -458,10 +478,10 @@ TRACE_EVENT(rdev_start_ap,
 		memcpy(__entry->ssid, settings->ssid, settings->ssid_len);
 	),
 	TP_printk(WIPHY_PR_FMT NETDEV_PR_FMT ", AP settings - ssid: %s, "
-		  CHAN_PR_FMT ", beacon interval: %d, dtim period: %d, "
+		  CHAN_DEF_PR_FMT ", beacon interval: %d, dtim period: %d, "
 		  "hidden ssid: %d, wpa versions: %u, privacy: %s, "
 		  "auth type: %d, inactivity timeout: %d",
-		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->ssid, CHAN_PR_ARG,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->ssid, CHAN_DEF_PR_ARG,
 		  __entry->beacon_interval, __entry->dtim_period,
 		  __entry->hidden_ssid, __entry->wpa_ver,
 		  BOOL_TO_STR(__entry->privacy), __entry->auth_type,
@@ -933,21 +953,19 @@ TRACE_EVENT(rdev_libertas_set_mesh_channel,
 );
 
 TRACE_EVENT(rdev_set_monitor_channel,
-	TP_PROTO(struct wiphy *wiphy, struct ieee80211_channel *chan,
-		 enum nl80211_channel_type chan_type),
-	TP_ARGS(wiphy, chan, chan_type),
+	TP_PROTO(struct wiphy *wiphy,
+		 struct cfg80211_chan_def *chandef),
+	TP_ARGS(wiphy, chandef),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
-		CHAN_ENTRY
-		__field(enum nl80211_channel_type, chan_type)
+		CHAN_DEF_ENTRY
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
-		CHAN_ASSIGN(chan);
-		__entry->chan_type = chan_type;
+		CHAN_DEF_ASSIGN(chandef);
 	),
-	TP_printk(WIPHY_PR_FMT CHAN_PR_FMT ", channel type : %d",
-		  WIPHY_PR_ARG, CHAN_PR_ARG, __entry->chan_type)
+	TP_printk(WIPHY_PR_FMT CHAN_DEF_PR_FMT,
+		  WIPHY_PR_ARG, CHAN_DEF_PR_ARG)
 );
 
 TRACE_EVENT(rdev_auth,
@@ -1713,22 +1731,25 @@ DEFINE_EVENT(wiphy_wdev_evt, rdev_get_channel,
 	TP_ARGS(wiphy, wdev)
 );
 
-TRACE_EVENT(rdev_return_channel,
-	TP_PROTO(struct wiphy *wiphy, struct ieee80211_channel *chan,
-		 enum nl80211_channel_type type),
-	TP_ARGS(wiphy, chan, type),
+TRACE_EVENT(rdev_return_chandef,
+	TP_PROTO(struct wiphy *wiphy, int ret,
+		 struct cfg80211_chan_def *chandef),
+	TP_ARGS(wiphy, ret, chandef),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
-		CHAN_ENTRY
-		__field(enum nl80211_channel_type, type)
+		__field(int, ret)
+		CHAN_DEF_ENTRY
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
-		CHAN_ASSIGN(chan);
-		__entry->type = type;
+		if (ret == 0)
+			CHAN_DEF_ASSIGN(chandef);
+		else
+			CHAN_DEF_ASSIGN((struct cfg80211_chan_def *)NULL);
+		__entry->ret = ret;
 	),
-	TP_printk(WIPHY_PR_FMT CHAN_PR_FMT ", channel type: %d",
-		  WIPHY_PR_ARG, CHAN_PR_ARG, __entry->type)
+	TP_printk(WIPHY_PR_FMT CHAN_DEF_PR_FMT ", ret: %d",
+		  WIPHY_PR_ARG, CHAN_DEF_PR_ARG, __entry->ret)
 );
 
 DEFINE_EVENT(wiphy_wdev_evt, rdev_start_p2p_device,
@@ -1992,40 +2013,35 @@ TRACE_EVENT(cfg80211_cqm_rssi_notify,
 		  NETDEV_PR_ARG, __entry->rssi_event)
 );
 
-TRACE_EVENT(cfg80211_can_beacon_sec_chan,
-	TP_PROTO(struct wiphy *wiphy, struct ieee80211_channel *channel,
-		 enum nl80211_channel_type channel_type),
-	TP_ARGS(wiphy, channel, channel_type),
+TRACE_EVENT(cfg80211_reg_can_beacon,
+	TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef),
+	TP_ARGS(wiphy, chandef),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
-		CHAN_ENTRY
-		__field(enum nl80211_channel_type, channel_type)
+		CHAN_DEF_ENTRY
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
-		CHAN_ASSIGN(channel);
-		__entry->channel_type = channel_type;
+		CHAN_DEF_ASSIGN(chandef);
 	),
-	TP_printk(WIPHY_PR_FMT CHAN_PR_FMT ", channel_type: %d",
-		  WIPHY_PR_ARG, CHAN_PR_ARG, __entry->channel_type)
+	TP_printk(WIPHY_PR_FMT CHAN_DEF_PR_FMT,
+		  WIPHY_PR_ARG, CHAN_DEF_PR_ARG)
 );
 
 TRACE_EVENT(cfg80211_ch_switch_notify,
-	TP_PROTO(struct net_device *netdev, int freq,
-		 enum nl80211_channel_type type),
-	TP_ARGS(netdev, freq, type),
+	TP_PROTO(struct net_device *netdev,
+		 struct cfg80211_chan_def *chandef),
+	TP_ARGS(netdev, chandef),
 	TP_STRUCT__entry(
 		NETDEV_ENTRY
-		__field(int, freq)
-		__field(enum nl80211_channel_type, type)
+		CHAN_DEF_ENTRY
 	),
 	TP_fast_assign(
 		NETDEV_ASSIGN;
-		__entry->freq = freq;
-		__entry->type = type;
+		CHAN_DEF_ASSIGN(chandef);
 	),
-	TP_printk(NETDEV_PR_FMT ", freq: %d, type: %d", NETDEV_PR_ARG,
-		  __entry->freq, __entry->type)
+	TP_printk(NETDEV_PR_FMT CHAN_DEF_PR_FMT,
+		  NETDEV_PR_ARG, CHAN_DEF_PR_ARG)
 );
 
 DECLARE_EVENT_CLASS(cfg80211_rx_evt,
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 742ab6ec4c9d..da3307f32362 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -784,6 +784,9 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_chan_def chandef = {
+		._type = NL80211_CHAN_NO_HT,
+	};
 	int freq, err;
 
 	switch (wdev->iftype) {
@@ -797,8 +800,11 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 			return freq;
 		if (freq == 0)
 			return -EINVAL;
+		chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq);
+		if (!chandef.chan)
+			return -EINVAL;
 		mutex_lock(&rdev->devlist_mtx);
-		err = cfg80211_set_monitor_channel(rdev, freq, NL80211_CHAN_NO_HT);
+		err = cfg80211_set_monitor_channel(rdev, &chandef);
 		mutex_unlock(&rdev->devlist_mtx);
 		return err;
 	case NL80211_IFTYPE_MESH_POINT:
@@ -807,9 +813,11 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 			return freq;
 		if (freq == 0)
 			return -EINVAL;
+		chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq);
+		if (!chandef.chan)
+			return -EINVAL;
 		mutex_lock(&rdev->devlist_mtx);
-		err = cfg80211_set_mesh_freq(rdev, wdev, freq,
-					     NL80211_CHAN_NO_HT);
+		err = cfg80211_set_mesh_channel(rdev, wdev, &chandef);
 		mutex_unlock(&rdev->devlist_mtx);
 		return err;
 	default:
@@ -823,8 +831,8 @@ static int cfg80211_wext_giwfreq(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
-	struct ieee80211_channel *chan;
-	enum nl80211_channel_type channel_type;
+	struct cfg80211_chan_def chandef;
+	int ret;
 
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_STATION:
@@ -835,10 +843,10 @@ static int cfg80211_wext_giwfreq(struct net_device *dev,
 		if (!rdev->ops->get_channel)
 			return -EINVAL;
 
-		chan = rdev_get_channel(rdev, wdev, &channel_type);
-		if (!chan)
-			return -EINVAL;
-		freq->m = chan->center_freq;
+		ret = rdev_get_channel(rdev, wdev, &chandef);
+		if (ret)
+			return ret;
+		freq->m = chandef.chan->center_freq;
 		freq->e = 6;
 		return 0;
 	default:
diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c
index 1f773f668d1a..e6e5dbf2f616 100644
--- a/net/wireless/wext-sme.c
+++ b/net/wireless/wext-sme.c
@@ -119,7 +119,15 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev,
 	 * channel we disconnected above and reconnect below.
 	 */
 	if (chan && !wdev->wext.connect.ssid_len) {
-		err = cfg80211_set_monitor_channel(rdev, freq, NL80211_CHAN_NO_HT);
+		struct cfg80211_chan_def chandef = {
+			._type = NL80211_CHAN_NO_HT,
+		};
+
+		chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq);
+		if (chandef.chan)
+			err = cfg80211_set_monitor_channel(rdev, &chandef);
+		else
+			err = -EINVAL;
 		goto out;
 	}
 
-- 
cgit v1.2.3-55-g7522


From 3d9d1d6656a73ea8407734cfb00b81d14ef62d4b Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Thu, 8 Nov 2012 23:14:50 +0100
Subject: nl80211/cfg80211: support VHT channel configuration

Change nl80211 to support specifying a VHT (or HT)
using the control channel frequency (as before) and
new attributes for the channel width and first and
second center frequency. The old channel type is of
course still supported for HT.

Also change the cfg80211 channel definition struct
to support these by adding the relevant fields to
it (and removing the _type field.)

This also adds new helper functions:
 - cfg80211_chandef_create to create a channel def
   struct given the control channel and channel type,
 - cfg80211_chandef_identical to check if two channel
   definitions are identical
 - cfg80211_chandef_compatible to check if the given
   channel definitions are compatible, and return the
   wider of the two

This isn't entirely complete, but that doesn't matter
until we have a driver using it. In particular, it's
missing
 - regulatory checks on the usable bandwidth (if that
   even makes sense)
 - regulatory TX power (database can't deal with it)
 - a proper channel compatibility calculation for the
   new channel types

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c |  10 +-
 include/net/cfg80211.h                     |  73 ++++++++-
 include/uapi/linux/nl80211.h               |  61 +++++--
 net/mac80211/cfg.c                         |   5 +-
 net/mac80211/ibss.c                        |  13 +-
 net/wireless/chan.c                        | 249 ++++++++++++++++++++++++++---
 net/wireless/core.h                        |   6 +
 net/wireless/ibss.c                        |   4 +-
 net/wireless/mesh.c                        |   4 +-
 net/wireless/nl80211.c                     | 160 ++++++++++++------
 net/wireless/trace.h                       |  28 ++--
 net/wireless/wext-compat.c                 |   4 +-
 net/wireless/wext-sme.c                    |   3 +-
 13 files changed, 507 insertions(+), 113 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index c0cc2e59fe6c..51bbe85c574c 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -1099,12 +1099,10 @@ void ath6kl_cfg80211_ch_switch_notify(struct ath6kl_vif *vif, int freq,
 		   "channel switch notify nw_type %d freq %d mode %d\n",
 		   vif->nw_type, freq, mode);
 
-	chandef.chan = ieee80211_get_channel(vif->ar->wiphy, freq);
-	if (WARN_ON(!chandef.chan))
-		return;
-
-	chandef._type = (mode == WMI_11G_HT20) ?
-		NL80211_CHAN_HT20 : NL80211_CHAN_NO_HT;
+	cfg80211_chandef_create(&chandef,
+				ieee80211_get_channel(vif->ar->wiphy, freq),
+				(mode == WMI_11G_HT20) ?
+					NL80211_CHAN_HT20 : NL80211_CHAN_NO_HT);
 
 	cfg80211_ch_switch_notify(vif->ndev, &chandef);
 }
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 86f777af79e8..977da58fb7ea 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -308,20 +308,85 @@ struct key_params {
 /**
  * struct cfg80211_chan_def - channel definition
  * @chan: the (control) channel
- * @_type: the channel type, don't use this field,
- *	use cfg80211_get_chandef_type() if needed.
+ * @width: channel width
+ * @center_freq1: center frequency of first segment
+ * @center_freq2: center frequency of second segment
+ *	(only with 80+80 MHz)
  */
 struct cfg80211_chan_def {
 	struct ieee80211_channel *chan;
-	enum nl80211_channel_type _type;
+	enum nl80211_chan_width width;
+	u32 center_freq1;
+	u32 center_freq2;
 };
 
+/**
+ * cfg80211_get_chandef_type - return old channel type from chandef
+ * @chandef: the channel definition
+ *
+ * Returns the old channel type (NOHT, HT20, HT40+/-) from a given
+ * chandef, which must have a bandwidth allowing this conversion.
+ */
 static inline enum nl80211_channel_type
 cfg80211_get_chandef_type(const struct cfg80211_chan_def *chandef)
 {
-	return chandef->_type;
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_20_NOHT:
+		return NL80211_CHAN_NO_HT;
+	case NL80211_CHAN_WIDTH_20:
+		return NL80211_CHAN_HT20;
+	case NL80211_CHAN_WIDTH_40:
+		if (chandef->center_freq1 > chandef->chan->center_freq)
+			return NL80211_CHAN_HT40PLUS;
+		return NL80211_CHAN_HT40MINUS;
+	default:
+		WARN_ON(1);
+		return NL80211_CHAN_NO_HT;
+	}
+}
+
+/**
+ * cfg80211_chandef_create - create channel definition using channel type
+ * @chandef: the channel definition struct to fill
+ * @channel: the control channel
+ * @chantype: the channel type
+ *
+ * Given a channel type, create a channel definition.
+ */
+void cfg80211_chandef_create(struct cfg80211_chan_def *chandef,
+			     struct ieee80211_channel *channel,
+			     enum nl80211_channel_type chantype);
+
+/**
+ * cfg80211_chandef_identical - check if two channel definitions are identical
+ * @chandef1: first channel definition
+ * @chandef2: second channel definition
+ *
+ * Returns %true if the channels defined by the channel definitions are
+ * identical, %false otherwise.
+ */
+static inline bool
+cfg80211_chandef_identical(const struct cfg80211_chan_def *chandef1,
+			   const struct cfg80211_chan_def *chandef2)
+{
+	return (chandef1->chan == chandef2->chan &&
+		chandef1->width == chandef2->width &&
+		chandef1->center_freq1 == chandef2->center_freq1 &&
+		chandef1->center_freq2 == chandef2->center_freq2);
 }
 
+/**
+ * cfg80211_chandef_compatible - check if two channel definitions are compatible
+ * @chandef1: first channel definition
+ * @chandef2: second channel definition
+ *
+ * Returns %NULL if the given channel definitions are incompatible,
+ * chandef1 or chandef2 otherwise.
+ */
+const struct cfg80211_chan_def *
+cfg80211_chandef_compatible(const struct cfg80211_chan_def *chandef1,
+			    const struct cfg80211_chan_def *chandef2);
+
 /**
  * enum survey_info_flags - survey information flags
  *
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 82b5ad38435b..84f9c7d84c69 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -118,8 +118,9 @@
  *	to get a list of all present wiphys.
  * @NL80211_CMD_SET_WIPHY: set wiphy parameters, needs %NL80211_ATTR_WIPHY or
  *	%NL80211_ATTR_IFINDEX; can be used to set %NL80211_ATTR_WIPHY_NAME,
- *	%NL80211_ATTR_WIPHY_TXQ_PARAMS, %NL80211_ATTR_WIPHY_FREQ,
- *	%NL80211_ATTR_WIPHY_CHANNEL_TYPE, %NL80211_ATTR_WIPHY_RETRY_SHORT,
+ *	%NL80211_ATTR_WIPHY_TXQ_PARAMS, %NL80211_ATTR_WIPHY_FREQ (and the
+ *	attributes determining the channel width; this is used for setting
+ *	monitor mode channel),  %NL80211_ATTR_WIPHY_RETRY_SHORT,
  *	%NL80211_ATTR_WIPHY_RETRY_LONG, %NL80211_ATTR_WIPHY_FRAG_THRESHOLD,
  *	and/or %NL80211_ATTR_WIPHY_RTS_THRESHOLD.
  *	However, for setting the channel, see %NL80211_CMD_SET_CHANNEL
@@ -171,7 +172,7 @@
  *	%NL80211_ATTR_AKM_SUITES, %NL80211_ATTR_PRIVACY,
  *	%NL80211_ATTR_AUTH_TYPE and %NL80211_ATTR_INACTIVITY_TIMEOUT.
  *	The channel to use can be set on the interface or be given using the
- *	%NL80211_ATTR_WIPHY_FREQ and %NL80211_ATTR_WIPHY_CHANNEL_TYPE attrs.
+ *	%NL80211_ATTR_WIPHY_FREQ and the attributes determining channel width.
  * @NL80211_CMD_NEW_BEACON: old alias for %NL80211_CMD_START_AP
  * @NL80211_CMD_STOP_AP: Stop AP operation on the given interface
  * @NL80211_CMD_DEL_BEACON: old alias for %NL80211_CMD_STOP_AP
@@ -471,8 +472,8 @@
  *	command is used as an event to indicate the that a trigger level was
  *	reached.
  * @NL80211_CMD_SET_CHANNEL: Set the channel (using %NL80211_ATTR_WIPHY_FREQ
- *	and %NL80211_ATTR_WIPHY_CHANNEL_TYPE) the given interface (identifed
- *	by %NL80211_ATTR_IFINDEX) shall operate on.
+ *	and the attributes determining channel width) the given interface
+ *	(identifed by %NL80211_ATTR_IFINDEX) shall operate on.
  *	In case multiple channels are supported by the device, the mechanism
  *	with which it switches channels is implementation-defined.
  *	When a monitor interface is given, it can only switch channel while
@@ -566,8 +567,8 @@
  *
  * @NL80211_CMD_CH_SWITCH_NOTIFY: An AP or GO may decide to switch channels
  *	independently of the userspace SME, send this event indicating
- *	%NL80211_ATTR_IFINDEX is now on %NL80211_ATTR_WIPHY_FREQ with
- *	%NL80211_ATTR_WIPHY_CHANNEL_TYPE.
+ *	%NL80211_ATTR_IFINDEX is now on %NL80211_ATTR_WIPHY_FREQ and the
+ *	attributes determining channel width.
  *
  * @NL80211_CMD_START_P2P_DEVICE: Start the given P2P Device, identified by
  *	its %NL80211_ATTR_WDEV identifier. It must have been created with
@@ -771,14 +772,26 @@ enum nl80211_commands {
  *	/sys/class/ieee80211/<phyname>/index
  * @NL80211_ATTR_WIPHY_NAME: wiphy name (used for renaming)
  * @NL80211_ATTR_WIPHY_TXQ_PARAMS: a nested array of TX queue parameters
- * @NL80211_ATTR_WIPHY_FREQ: frequency of the selected channel in MHz
+ * @NL80211_ATTR_WIPHY_FREQ: frequency of the selected channel in MHz,
+ *	defines the channel together with the (deprecated)
+ *	%NL80211_ATTR_WIPHY_CHANNEL_TYPE attribute or the attributes
+ *	%NL80211_ATTR_CHANNEL_WIDTH and if needed %NL80211_ATTR_CENTER_FREQ1
+ *	and %NL80211_ATTR_CENTER_FREQ2
+ * @NL80211_ATTR_CHANNEL_WIDTH: u32 attribute containing one of the values
+ *	of &enum nl80211_chan_width, describing the channel width. See the
+ *	documentation of the enum for more information.
+ * @NL80211_ATTR_CENTER_FREQ1: Center frequency of the first part of the
+ *	channel, used for anything but 20 MHz bandwidth
+ * @NL80211_ATTR_CENTER_FREQ2: Center frequency of the second part of the
+ *	channel, used only for 80+80 MHz bandwidth
  * @NL80211_ATTR_WIPHY_CHANNEL_TYPE: included with NL80211_ATTR_WIPHY_FREQ
- *	if HT20 or HT40 are allowed (i.e., 802.11n disabled if not included):
+ *	if HT20 or HT40 are to be used (i.e., HT disabled if not included):
  *	NL80211_CHAN_NO_HT = HT not allowed (i.e., same as not including
  *		this attribute)
  *	NL80211_CHAN_HT20 = HT20 only
  *	NL80211_CHAN_HT40MINUS = secondary channel is below the primary channel
  *	NL80211_CHAN_HT40PLUS = secondary channel is above the primary channel
+ *	This attribute is now deprecated.
  * @NL80211_ATTR_WIPHY_RETRY_SHORT: TX retry limit for frames whose length is
  *	less than or equal to the RTS threshold; allowed range: 1..255;
  *	dot11ShortRetryLimit; u8
@@ -1553,6 +1566,10 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_SCAN_FLAGS,
 
+	NL80211_ATTR_CHANNEL_WIDTH,
+	NL80211_ATTR_CENTER_FREQ1,
+	NL80211_ATTR_CENTER_FREQ2,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -2454,6 +2471,32 @@ enum nl80211_channel_type {
 	NL80211_CHAN_HT40PLUS
 };
 
+/**
+ * enum nl80211_chan_width - channel width definitions
+ *
+ * These values are used with the %NL80211_ATTR_CHANNEL_WIDTH
+ * attribute.
+ *
+ * @NL80211_CHAN_WIDTH_20_NOHT: 20 MHz, non-HT channel
+ * @NL80211_CHAN_WIDTH_20: 20 MHz HT channel
+ * @NL80211_CHAN_WIDTH_40: 40 MHz channel, the %NL80211_ATTR_CENTER_FREQ1
+ *	attribute must be provided as well
+ * @NL80211_CHAN_WIDTH_80: 80 MHz channel, the %NL80211_ATTR_CENTER_FREQ1
+ *	attribute must be provided as well
+ * @NL80211_CHAN_WIDTH_80P80: 80+80 MHz channel, the %NL80211_ATTR_CENTER_FREQ1
+ *	and %NL80211_ATTR_CENTER_FREQ2 attributes must be provided as well
+ * @NL80211_CHAN_WIDTH_160: 160 MHz channel, the %NL80211_ATTR_CENTER_FREQ1
+ *	attribute must be provided as well
+ */
+enum nl80211_chan_width {
+	NL80211_CHAN_WIDTH_20_NOHT,
+	NL80211_CHAN_WIDTH_20,
+	NL80211_CHAN_WIDTH_40,
+	NL80211_CHAN_WIDTH_80,
+	NL80211_CHAN_WIDTH_80P80,
+	NL80211_CHAN_WIDTH_160,
+};
+
 /**
  * enum nl80211_bss - netlink attributes for a BSS
  *
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index fbb2d072cb9e..7136b945798e 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3125,8 +3125,9 @@ static int ieee80211_cfg_get_channel(struct wiphy *wiphy,
 	rcu_read_lock();
 	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 	if (chanctx_conf) {
-		chandef->chan = chanctx_conf->channel;
-		chandef->_type = chanctx_conf->channel_type;
+		cfg80211_chandef_create(chandef,
+					chanctx_conf->channel,
+					chanctx_conf->channel_type);
 		ret = 0;
 	}
 	rcu_read_unlock();
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index bed616fd97e9..5648bbed240b 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -52,6 +52,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	u32 bss_change;
 	u8 supp_rates[IEEE80211_MAX_SUPP_RATES];
 	struct cfg80211_chan_def chandef;
+	enum nl80211_channel_type chan_type;
 
 	lockdep_assert_held(&ifibss->mtx);
 
@@ -79,13 +80,13 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 
 	sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0;
 
-	chandef.chan = chan;
-	chandef._type = ifibss->channel_type;
+	chan_type = ifibss->channel_type;
+	cfg80211_chandef_create(&chandef, chan, chan_type);
 	if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef))
-		chandef._type = NL80211_CHAN_HT20;
+		chan_type = NL80211_CHAN_HT20;
 
 	ieee80211_vif_release_channel(sdata);
-	if (ieee80211_vif_use_channel(sdata, chan, chandef._type,
+	if (ieee80211_vif_use_channel(sdata, chan, chan_type,
 				      ifibss->fixed_channel ?
 					IEEE80211_CHANCTX_SHARED :
 					IEEE80211_CHANCTX_EXCLUSIVE)) {
@@ -159,7 +160,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 		       ifibss->ie, ifibss->ie_len);
 
 	/* add HT capability and information IEs */
-	if (chandef._type != NL80211_CHAN_NO_HT &&
+	if (chan_type != NL80211_CHAN_NO_HT &&
 	    sband->ht_cap.ht_supported) {
 		pos = skb_put(skb, 4 +
 				   sizeof(struct ieee80211_ht_cap) +
@@ -172,7 +173,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 		 * keep them at 0
 		 */
 		pos = ieee80211_ie_build_ht_oper(pos, &sband->ht_cap,
-						 chan, chandef._type, 0);
+						 chan, chan_type, 0);
 	}
 
 	if (local->hw.queues >= IEEE80211_NUM_ACS) {
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index e834422de40a..bf2dfd54ff3b 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -11,43 +11,252 @@
 #include "core.h"
 #include "rdev-ops.h"
 
-bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
-			     struct cfg80211_chan_def *chandef)
+void cfg80211_chandef_create(struct cfg80211_chan_def *chandef,
+			     struct ieee80211_channel *chan,
+			     enum nl80211_channel_type chan_type)
 {
-	struct ieee80211_channel *sec_chan;
-	int diff;
+	if (WARN_ON(!chan))
+		return;
 
-	trace_cfg80211_reg_can_beacon(wiphy, chandef);
+	chandef->chan = chan;
+	chandef->center_freq2 = 0;
 
-	switch (chandef->_type) {
+	switch (chan_type) {
+	case NL80211_CHAN_NO_HT:
+		chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
+		chandef->center_freq1 = chan->center_freq;
+		break;
+	case NL80211_CHAN_HT20:
+		chandef->width = NL80211_CHAN_WIDTH_20;
+		chandef->center_freq1 = chan->center_freq;
+		break;
 	case NL80211_CHAN_HT40PLUS:
-		diff = 20;
+		chandef->width = NL80211_CHAN_WIDTH_40;
+		chandef->center_freq1 = chan->center_freq + 10;
 		break;
 	case NL80211_CHAN_HT40MINUS:
-		diff = -20;
+		chandef->width = NL80211_CHAN_WIDTH_40;
+		chandef->center_freq1 = chan->center_freq - 10;
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+EXPORT_SYMBOL(cfg80211_chandef_create);
+
+bool cfg80211_chan_def_valid(const struct cfg80211_chan_def *chandef)
+{
+	u32 control_freq;
+
+	if (!chandef->chan)
+		return false;
+
+	control_freq = chandef->chan->center_freq;
+
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_20:
+	case NL80211_CHAN_WIDTH_20_NOHT:
+		if (chandef->center_freq1 != control_freq)
+			return false;
+		if (chandef->center_freq2)
+			return false;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		if (chandef->center_freq1 != control_freq + 10 &&
+		    chandef->center_freq1 != control_freq - 10)
+			return false;
+		if (chandef->center_freq2)
+			return false;
+		break;
+	case NL80211_CHAN_WIDTH_80P80:
+		if (chandef->center_freq1 != control_freq + 30 &&
+		    chandef->center_freq1 != control_freq + 10 &&
+		    chandef->center_freq1 != control_freq - 10 &&
+		    chandef->center_freq1 != control_freq - 30)
+			return false;
+		if (!chandef->center_freq2)
+			return false;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		if (chandef->center_freq1 != control_freq + 30 &&
+		    chandef->center_freq1 != control_freq + 10 &&
+		    chandef->center_freq1 != control_freq - 10 &&
+		    chandef->center_freq1 != control_freq - 30)
+			return false;
+		if (chandef->center_freq2)
+			return false;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		if (chandef->center_freq1 != control_freq + 70 &&
+		    chandef->center_freq1 != control_freq + 50 &&
+		    chandef->center_freq1 != control_freq + 30 &&
+		    chandef->center_freq1 != control_freq + 10 &&
+		    chandef->center_freq1 != control_freq - 10 &&
+		    chandef->center_freq1 != control_freq - 30 &&
+		    chandef->center_freq1 != control_freq - 50 &&
+		    chandef->center_freq1 != control_freq - 70)
+			return false;
+		if (chandef->center_freq2)
+			return false;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+static void chandef_primary_freqs(const struct cfg80211_chan_def *c,
+				  int *pri40, int *pri80)
+{
+	int tmp;
+
+	switch (c->width) {
+	case NL80211_CHAN_WIDTH_40:
+		*pri40 = c->center_freq1;
+		*pri80 = 0;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+	case NL80211_CHAN_WIDTH_80P80:
+		*pri80 = c->center_freq1;
+		/* n_P20 */
+		tmp = (30 + c->chan->center_freq - c->center_freq1)/20;
+		/* n_P40 */
+		tmp /= 2;
+		/* freq_P40 */
+		*pri40 = c->center_freq1 - 20 + 40 * tmp;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		/* n_P20 */
+		tmp = (70 + c->chan->center_freq - c->center_freq1)/20;
+		/* n_P40 */
+		tmp /= 2;
+		/* freq_P40 */
+		*pri40 = c->center_freq1 - 60 + 40 * tmp;
+		/* n_P80 */
+		tmp /= 2;
+		*pri80 = c->center_freq1 - 40 + 80 * tmp;
 		break;
 	default:
-		trace_cfg80211_return_bool(true);
-		return true;
+		WARN_ON_ONCE(1);
 	}
+}
+
+const struct cfg80211_chan_def *
+cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1,
+			    const struct cfg80211_chan_def *c2)
+{
+	u32 c1_pri40, c1_pri80, c2_pri40, c2_pri80;
 
-	sec_chan = ieee80211_get_channel(wiphy,
-					 chandef->chan->center_freq + diff);
-	if (!sec_chan) {
+	/* If they are identical, return */
+	if (cfg80211_chandef_identical(c1, c2))
+		return c1;
+
+	/* otherwise, must have same control channel */
+	if (c1->chan != c2->chan)
+		return NULL;
+
+	/*
+	 * If they have the same width, but aren't identical,
+	 * then they can't be compatible.
+	 */
+	if (c1->width == c2->width)
+		return NULL;
+
+	if (c1->width == NL80211_CHAN_WIDTH_20_NOHT ||
+	    c1->width == NL80211_CHAN_WIDTH_20)
+		return c2;
+
+	if (c2->width == NL80211_CHAN_WIDTH_20_NOHT ||
+	    c2->width == NL80211_CHAN_WIDTH_20)
+		return c1;
+
+	chandef_primary_freqs(c1, &c1_pri40, &c1_pri80);
+	chandef_primary_freqs(c2, &c2_pri40, &c2_pri80);
+
+	if (c1_pri40 != c2_pri40)
+		return NULL;
+
+	WARN_ON(!c1_pri80 && !c2_pri80);
+	if (c1_pri80 && c2_pri80 && c1_pri80 != c2_pri80)
+		return NULL;
+
+	if (c1->width > c2->width)
+		return c1;
+	return c2;
+}
+EXPORT_SYMBOL(cfg80211_chandef_compatible);
+
+bool cfg80211_secondary_chans_ok(struct wiphy *wiphy,
+				 u32 center_freq, u32 bandwidth,
+				 u32 prohibited_flags)
+{
+	struct ieee80211_channel *c;
+	u32 freq;
+
+	for (freq = center_freq - bandwidth/2 + 10;
+	     freq <= center_freq + bandwidth/2 - 10;
+	     freq += 20) {
+		c = ieee80211_get_channel(wiphy, freq);
+		if (!c || c->flags & prohibited_flags)
+			return false;
+	}
+
+	return true;
+}
+
+static bool cfg80211_check_beacon_chans(struct wiphy *wiphy,
+					u32 center_freq, u32 bw)
+{
+	return cfg80211_secondary_chans_ok(wiphy, center_freq, bw,
+					   IEEE80211_CHAN_DISABLED |
+					   IEEE80211_CHAN_PASSIVE_SCAN |
+					   IEEE80211_CHAN_NO_IBSS |
+					   IEEE80211_CHAN_RADAR);
+}
+
+bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
+			     struct cfg80211_chan_def *chandef)
+{
+	u32 width;
+	bool res;
+
+	trace_cfg80211_reg_can_beacon(wiphy, chandef);
+
+	if (WARN_ON(!cfg80211_chan_def_valid(chandef))) {
 		trace_cfg80211_return_bool(false);
 		return false;
 	}
 
-	/* we'll need a DFS capability later */
-	if (sec_chan->flags & (IEEE80211_CHAN_DISABLED |
-			       IEEE80211_CHAN_PASSIVE_SCAN |
-			       IEEE80211_CHAN_NO_IBSS |
-			       IEEE80211_CHAN_RADAR)) {
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_20_NOHT:
+	case NL80211_CHAN_WIDTH_20:
+		width = 20;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		width = 40;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+	case NL80211_CHAN_WIDTH_80P80:
+		width = 80;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		width = 160;
+		break;
+	default:
+		WARN_ON_ONCE(1);
 		trace_cfg80211_return_bool(false);
 		return false;
 	}
-	trace_cfg80211_return_bool(true);
-	return true;
+
+	res = cfg80211_check_beacon_chans(wiphy, chandef->center_freq1, width);
+
+	if (res && chandef->center_freq2)
+		res = cfg80211_check_beacon_chans(wiphy, chandef->center_freq2,
+						  width);
+
+	trace_cfg80211_return_bool(res);
+	return res;
 }
 EXPORT_SYMBOL(cfg80211_reg_can_beacon);
 
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 6183a0d25b8b..a0c8decf6a47 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -483,6 +483,12 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
 void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev,
 			       enum nl80211_iftype iftype, int num);
 
+bool cfg80211_chan_def_valid(const struct cfg80211_chan_def *chandef);
+
+bool cfg80211_secondary_chans_ok(struct wiphy *wiphy,
+				 u32 center_freq, u32 bandwidth,
+				 u32 prohibited_flags);
+
 #define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10
 
 #ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index ccc8865dfadb..9b9551e4a6f9 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -252,7 +252,7 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev,
 
 	/* try to find an IBSS channel if none requested ... */
 	if (!wdev->wext.ibss.chandef.chan) {
-		wdev->wext.ibss.chandef._type = NL80211_CHAN_NO_HT;
+		wdev->wext.ibss.chandef.width = NL80211_CHAN_WIDTH_20_NOHT;
 
 		for (band = 0; band < IEEE80211_NUM_BANDS; band++) {
 			struct ieee80211_supported_band *sband;
@@ -352,7 +352,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
 
 	if (chan) {
 		wdev->wext.ibss.chandef.chan = chan;
-		wdev->wext.ibss.chandef._type = NL80211_CHAN_NO_HT;
+		wdev->wext.ibss.chandef.width = NL80211_CHAN_WIDTH_20_NOHT;
 		wdev->wext.ibss.channel_fixed = true;
 	} else {
 		/* cfg80211_ibss_wext_join will pick one if needed */
diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
index 12b5a570a306..3ee5a7282283 100644
--- a/net/wireless/mesh.c
+++ b/net/wireless/mesh.c
@@ -146,7 +146,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 		if (!setup->chandef.chan)
 			return -EINVAL;
 
-		setup->chandef._type = NL80211_CHAN_NO_HT;
+		setup->chandef.width = NL80211_CHAN_WIDTH_20_NOHT;;
 	}
 
 	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &setup->chandef))
@@ -198,7 +198,7 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
 	 * compatible with 802.11 mesh.
 	 */
 	if (rdev->ops->libertas_set_mesh_channel) {
-		if (chandef->_type != NL80211_CHAN_NO_HT)
+		if (chandef->width != NL80211_CHAN_WIDTH_20_NOHT)
 			return -EINVAL;
 
 		if (!netif_running(wdev->netdev))
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 999108cd947c..15158a3d64a3 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -223,8 +223,13 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_WIPHY_NAME] = { .type = NLA_NUL_STRING,
 				      .len = 20-1 },
 	[NL80211_ATTR_WIPHY_TXQ_PARAMS] = { .type = NLA_NESTED },
+
 	[NL80211_ATTR_WIPHY_FREQ] = { .type = NLA_U32 },
 	[NL80211_ATTR_WIPHY_CHANNEL_TYPE] = { .type = NLA_U32 },
+	[NL80211_ATTR_CHANNEL_WIDTH] = { .type = NLA_U32 },
+	[NL80211_ATTR_CENTER_FREQ1] = { .type = NLA_U32 },
+	[NL80211_ATTR_CENTER_FREQ2] = { .type = NLA_U32 },
+
 	[NL80211_ATTR_WIPHY_RETRY_SHORT] = { .type = NLA_U8 },
 	[NL80211_ATTR_WIPHY_RETRY_LONG] = { .type = NLA_U8 },
 	[NL80211_ATTR_WIPHY_FRAG_THRESHOLD] = { .type = NLA_U32 },
@@ -1360,35 +1365,13 @@ static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev)
 		wdev->iftype == NL80211_IFTYPE_P2P_GO;
 }
 
-static bool nl80211_valid_channel_type(struct genl_info *info,
-				       enum nl80211_channel_type *channel_type)
-{
-	enum nl80211_channel_type tmp;
-
-	if (!info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE])
-		return false;
-
-	tmp = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]);
-	if (tmp != NL80211_CHAN_NO_HT &&
-	    tmp != NL80211_CHAN_HT20 &&
-	    tmp != NL80211_CHAN_HT40PLUS &&
-	    tmp != NL80211_CHAN_HT40MINUS)
-		return false;
-
-	if (channel_type)
-		*channel_type = tmp;
-
-	return true;
-}
-
 static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
 				 struct genl_info *info,
 				 struct cfg80211_chan_def *chandef)
 {
 	struct ieee80211_sta_ht_cap *ht_cap;
-	struct ieee80211_channel *sc;
-	u32 control_freq;
-	int offs;
+	struct ieee80211_sta_vht_cap *vht_cap;
+	u32 control_freq, width;
 
 	if (!info->attrs[NL80211_ATTR_WIPHY_FREQ])
 		return -EINVAL;
@@ -1396,47 +1379,105 @@ static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
 	control_freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]);
 
 	chandef->chan = ieee80211_get_channel(&rdev->wiphy, control_freq);
-	chandef->_type = NL80211_CHAN_NO_HT;
-
-	if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] &&
-	    !nl80211_valid_channel_type(info, &chandef->_type))
-		return -EINVAL;
+	chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
+	chandef->center_freq1 = control_freq;
+	chandef->center_freq2 = 0;
 
 	/* Primary channel not allowed */
 	if (!chandef->chan || chandef->chan->flags & IEEE80211_CHAN_DISABLED)
 		return -EINVAL;
 
+	if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) {
+		enum nl80211_channel_type chantype;
+
+		chantype = nla_get_u32(
+				info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]);
+
+		switch (chantype) {
+		case NL80211_CHAN_NO_HT:
+		case NL80211_CHAN_HT20:
+		case NL80211_CHAN_HT40PLUS:
+		case NL80211_CHAN_HT40MINUS:
+			cfg80211_chandef_create(chandef, chandef->chan,
+						chantype);
+			break;
+		default:
+			return -EINVAL;
+		}
+	} else if (info->attrs[NL80211_ATTR_CHANNEL_WIDTH]) {
+		chandef->width =
+			nla_get_u32(info->attrs[NL80211_ATTR_CHANNEL_WIDTH]);
+		if (info->attrs[NL80211_ATTR_CENTER_FREQ1])
+			chandef->center_freq1 =
+				nla_get_u32(
+					info->attrs[NL80211_ATTR_CENTER_FREQ1]);
+		if (info->attrs[NL80211_ATTR_CENTER_FREQ2])
+			chandef->center_freq2 =
+				nla_get_u32(
+					info->attrs[NL80211_ATTR_CENTER_FREQ2]);
+	}
+
 	ht_cap = &rdev->wiphy.bands[chandef->chan->band]->ht_cap;
+	vht_cap = &rdev->wiphy.bands[chandef->chan->band]->vht_cap;
 
-	switch (chandef->_type) {
-	case NL80211_CHAN_NO_HT:
+	if (!cfg80211_chan_def_valid(chandef))
+		return -EINVAL;
+
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_20:
+		if (!ht_cap->ht_supported)
+			return -EINVAL;
+	case NL80211_CHAN_WIDTH_20_NOHT:
+		width = 20;
 		break;
-	case NL80211_CHAN_HT40MINUS:
-		if (chandef->chan->flags & IEEE80211_CHAN_NO_HT40MINUS)
+	case NL80211_CHAN_WIDTH_40:
+		width = 40;
+		/* quick early regulatory check */
+		if (chandef->center_freq1 < control_freq &&
+		    chandef->chan->flags & IEEE80211_CHAN_NO_HT40MINUS)
+			return -EINVAL;
+		if (chandef->center_freq1 > control_freq &&
+		    chandef->chan->flags & IEEE80211_CHAN_NO_HT40PLUS)
+			return -EINVAL;
+		if (!ht_cap->ht_supported)
 			return -EINVAL;
-		offs = -20;
-		/* fall through */
-	case NL80211_CHAN_HT40PLUS:
-		if (chandef->_type == NL80211_CHAN_HT40PLUS) {
-			if (chandef->chan->flags & IEEE80211_CHAN_NO_HT40PLUS)
-				return -EINVAL;
-			offs = 20;
-		}
 		if (!(ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) ||
 		    ht_cap->cap & IEEE80211_HT_CAP_40MHZ_INTOLERANT)
 			return -EINVAL;
-
-		sc = ieee80211_get_channel(&rdev->wiphy,
-					   chandef->chan->center_freq + offs);
-		if (!sc || sc->flags & IEEE80211_CHAN_DISABLED)
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		width = 80;
+		if (!vht_cap->vht_supported)
 			return -EINVAL;
-		/* fall through */
-	case NL80211_CHAN_HT20:
-		if (!ht_cap->ht_supported)
+		break;
+	case NL80211_CHAN_WIDTH_80P80:
+		width = 80;
+		if (!vht_cap->vht_supported)
+			return -EINVAL;
+		if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ))
+			return -EINVAL;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		width = 160;
+		if (!vht_cap->vht_supported)
+			return -EINVAL;
+		if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ))
 			return -EINVAL;
 		break;
+	default:
+		return -EINVAL;
 	}
 
+	if (!cfg80211_secondary_chans_ok(&rdev->wiphy, chandef->center_freq1,
+					 width, IEEE80211_CHAN_DISABLED))
+		return -EINVAL;
+	if (chandef->center_freq2 &&
+	    !cfg80211_secondary_chans_ok(&rdev->wiphy, chandef->center_freq2,
+					 width, IEEE80211_CHAN_DISABLED))
+		return -EINVAL;
+
+	/* TODO: missing regulatory check on bandwidth */
+
 	return 0;
 }
 
@@ -1800,10 +1841,28 @@ static inline u64 wdev_id(struct wireless_dev *wdev)
 static int nl80211_send_chandef(struct sk_buff *msg,
 				 struct cfg80211_chan_def *chandef)
 {
+	WARN_ON(!cfg80211_chan_def_valid(chandef));
+
 	if (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ,
 			chandef->chan->center_freq))
 		return -ENOBUFS;
-	if (nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, chandef->_type))
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_20_NOHT:
+	case NL80211_CHAN_WIDTH_20:
+	case NL80211_CHAN_WIDTH_40:
+		if (nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE,
+				cfg80211_get_chandef_type(chandef)))
+			return -ENOBUFS;
+		break;
+	default:
+		break;
+	}
+	if (nla_put_u32(msg, NL80211_ATTR_CHANNEL_WIDTH, chandef->width))
+		return -ENOBUFS;
+	if (nla_put_u32(msg, NL80211_ATTR_CENTER_FREQ1, chandef->center_freq1))
+		return -ENOBUFS;
+	if (chandef->center_freq2 &&
+	    nla_put_u32(msg, NL80211_ATTR_CENTER_FREQ2, chandef->center_freq2))
 		return -ENOBUFS;
 	return 0;
 }
@@ -5447,7 +5506,8 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 		if (IS_ERR(connkeys))
 			return PTR_ERR(connkeys);
 
-		if ((ibss.chandef._type != NL80211_CHAN_NO_HT) && no_ht) {
+		if ((ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT) &&
+		    no_ht) {
 			kfree(connkeys);
 			return -EINVAL;
 		}
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 1370d52b1393..3c7aa1221563 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -126,25 +126,33 @@
 #define CHAN_PR_FMT ", band: %d, freq: %u"
 #define CHAN_PR_ARG __entry->band, __entry->center_freq
 
-#define CHAN_DEF_ENTRY __field(enum ieee80211_band, band)	\
-		       __field(u16, center_freq)		\
-		       __field(u32, channel_type)
+#define CHAN_DEF_ENTRY __field(enum ieee80211_band, band)		\
+		       __field(u32, control_freq)			\
+		       __field(u32, width)				\
+		       __field(u32, center_freq1)			\
+		       __field(u32, center_freq2)
 #define CHAN_DEF_ASSIGN(chandef)					\
 	do {								\
 		if ((chandef) && (chandef)->chan) {			\
 			__entry->band = (chandef)->chan->band;		\
-			__entry->center_freq =				\
+			__entry->control_freq =				\
 				(chandef)->chan->center_freq;		\
-			__entry->channel_type = (chandef)->_type;	\
+			__entry->width = (chandef)->width;		\
+			__entry->center_freq1 = (chandef)->center_freq1;\
+			__entry->center_freq2 = (chandef)->center_freq2;\
 		} else {						\
 			__entry->band = 0;				\
-			__entry->center_freq = 0;			\
-			__entry->channel_type = 0;			\
+			__entry->control_freq = 0;			\
+			__entry->width = 0;				\
+			__entry->center_freq1 = 0;			\
+			__entry->center_freq2 = 0;			\
 		}							\
 	} while (0)
-#define CHAN_DEF_PR_FMT ", band: %d, freq: %u, chantype: %d"
-#define CHAN_DEF_PR_ARG __entry->band, __entry->center_freq,		\
-			__entry->channel_type
+#define CHAN_DEF_PR_FMT							\
+	", band: %d, control freq: %u, width: %d, cf1: %u, cf2: %u"
+#define CHAN_DEF_PR_ARG __entry->band, __entry->control_freq,		\
+			__entry->width, __entry->center_freq1,		\
+			__entry->center_freq2
 
 #define SINFO_ENTRY __field(int, generation)	    \
 		    __field(u32, connected_time)    \
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index da3307f32362..f9680c9cf9b3 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -785,7 +785,7 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
 	struct cfg80211_chan_def chandef = {
-		._type = NL80211_CHAN_NO_HT,
+		.width = NL80211_CHAN_WIDTH_20_NOHT,
 	};
 	int freq, err;
 
@@ -800,6 +800,7 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 			return freq;
 		if (freq == 0)
 			return -EINVAL;
+		chandef.center_freq1 = freq;
 		chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq);
 		if (!chandef.chan)
 			return -EINVAL;
@@ -813,6 +814,7 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 			return freq;
 		if (freq == 0)
 			return -EINVAL;
+		chandef.center_freq1 = freq;
 		chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq);
 		if (!chandef.chan)
 			return -EINVAL;
diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c
index e6e5dbf2f616..873af63187c0 100644
--- a/net/wireless/wext-sme.c
+++ b/net/wireless/wext-sme.c
@@ -120,7 +120,8 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev,
 	 */
 	if (chan && !wdev->wext.connect.ssid_len) {
 		struct cfg80211_chan_def chandef = {
-			._type = NL80211_CHAN_NO_HT,
+			.width = NL80211_CHAN_WIDTH_20_NOHT,
+			.center_freq1 = freq,
 		};
 
 		chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq);
-- 
cgit v1.2.3-55-g7522


From 4bf88530be971bf95a7830ca61b4120980bf4347 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Fri, 9 Nov 2012 11:39:59 +0100
Subject: mac80211: convert to channel definition struct

Convert mac80211 (and where necessary, some drivers a
little bit) to the new channel definition struct.

This will allow extending mac80211 for VHT, which is
currently restricted to channel contexts since there
are no drivers using that which makes it easier. As
I also don't care about VHT for drivers not using the
channel context API, I won't convert the previous API
to VHT support.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c |  33 +++++----
 drivers/net/wireless/ti/wlcore/main.c |   9 +--
 include/net/mac80211.h                |  17 ++---
 net/mac80211/cfg.c                    |  41 ++++-------
 net/mac80211/chan.c                   | 128 ++++++++++------------------------
 net/mac80211/debugfs_netdev.c         |   2 -
 net/mac80211/ibss.c                   |  34 ++++-----
 net/mac80211/ieee80211_i.h            |  18 +++--
 net/mac80211/iface.c                  |   5 +-
 net/mac80211/main.c                   |  21 ++++--
 net/mac80211/mesh.c                   |  28 +++-----
 net/mac80211/mesh_plink.c             |  19 ++---
 net/mac80211/mlme.c                   |  26 ++++---
 net/mac80211/rate.c                   |   5 +-
 net/mac80211/rate.h                   |   2 +-
 net/mac80211/sta_info.c               |   2 +-
 net/mac80211/sta_info.h               |   4 +-
 net/mac80211/trace.h                  |  23 +++---
 net/mac80211/tx.c                     |  20 +++---
 net/mac80211/util.c                   |  45 ++++++------
 20 files changed, 220 insertions(+), 262 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index b0338543547b..6be3faeaa59a 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -681,7 +681,7 @@ static void mac80211_hwsim_tx_iter(void *_data, u8 *addr,
 		return;
 
 	if (!hwsim_chans_compat(data->channel,
-				rcu_dereference(vif->chanctx_conf)->channel))
+				rcu_dereference(vif->chanctx_conf)->def.chan))
 		return;
 
 	data->receive = true;
@@ -832,7 +832,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw,
 	} else {
 		chanctx_conf = rcu_dereference(txi->control.vif->chanctx_conf);
 		if (chanctx_conf)
-			channel = chanctx_conf->channel;
+			channel = chanctx_conf->def.chan;
 		else
 			channel = NULL;
 	}
@@ -977,7 +977,7 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac,
 		return;
 
 	mac80211_hwsim_tx_frame(hw, skb,
-				rcu_dereference(vif->chanctx_conf)->channel);
+				rcu_dereference(vif->chanctx_conf)->def.chan);
 }
 
 
@@ -1107,9 +1107,8 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changed & BSS_CHANGED_HT) {
-		wiphy_debug(hw->wiphy, "  HT: op_mode=0x%x, chantype=%s\n",
-			    info->ht_operation_mode,
-			    hwsim_chantypes[info->channel_type]);
+		wiphy_debug(hw->wiphy, "  HT: op_mode=0x%x\n",
+			    info->ht_operation_mode);
 	}
 
 	if (changed & BSS_CHANGED_BASIC_RATES) {
@@ -1497,16 +1496,20 @@ static int mac80211_hwsim_add_chanctx(struct ieee80211_hw *hw,
 				      struct ieee80211_chanctx_conf *ctx)
 {
 	hwsim_set_chanctx_magic(ctx);
-	wiphy_debug(hw->wiphy, "add channel context %d MHz/%d\n",
-		    ctx->channel->center_freq, ctx->channel_type);
+	wiphy_debug(hw->wiphy,
+		    "add channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n",
+		    ctx->def.chan->center_freq, ctx->def.width,
+		    ctx->def.center_freq1, ctx->def.center_freq2);
 	return 0;
 }
 
 static void mac80211_hwsim_remove_chanctx(struct ieee80211_hw *hw,
 					  struct ieee80211_chanctx_conf *ctx)
 {
-	wiphy_debug(hw->wiphy, "remove channel context %d MHz/%d\n",
-		    ctx->channel->center_freq, ctx->channel_type);
+	wiphy_debug(hw->wiphy,
+		    "remove channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n",
+		    ctx->def.chan->center_freq, ctx->def.width,
+		    ctx->def.center_freq1, ctx->def.center_freq2);
 	hwsim_check_chanctx_magic(ctx);
 	hwsim_clear_chanctx_magic(ctx);
 }
@@ -1516,8 +1519,10 @@ static void mac80211_hwsim_change_chanctx(struct ieee80211_hw *hw,
 					  u32 changed)
 {
 	hwsim_check_chanctx_magic(ctx);
-	wiphy_debug(hw->wiphy, "change channel context %#x (%d MHz/%d)\n",
-		    changed, ctx->channel->center_freq, ctx->channel_type);
+	wiphy_debug(hw->wiphy,
+		    "change channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n",
+		    ctx->def.chan->center_freq, ctx->def.width,
+		    ctx->def.center_freq1, ctx->def.center_freq2);
 }
 
 static int mac80211_hwsim_assign_vif_chanctx(struct ieee80211_hw *hw,
@@ -1639,7 +1644,7 @@ static void hwsim_send_ps_poll(void *dat, u8 *mac, struct ieee80211_vif *vif)
 
 	rcu_read_lock();
 	mac80211_hwsim_tx_frame(data->hw, skb,
-				rcu_dereference(vif->chanctx_conf)->channel);
+				rcu_dereference(vif->chanctx_conf)->def.chan);
 	rcu_read_unlock();
 }
 
@@ -1671,7 +1676,7 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac,
 
 	rcu_read_lock();
 	mac80211_hwsim_tx_frame(data->hw, skb,
-				rcu_dereference(vif->chanctx_conf)->channel);
+				rcu_dereference(vif->chanctx_conf)->def.chan);
 	rcu_read_unlock();
 }
 
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 380cf1ff6cd1..4f1a05b92d2d 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -3791,7 +3791,7 @@ static void wl1271_bss_info_changed_ap(struct wl1271 *wl,
 
 	/* Handle HT information change */
 	if ((changed & BSS_CHANGED_HT) &&
-	    (bss_conf->channel_type != NL80211_CHAN_NO_HT)) {
+	    (bss_conf->chandef.width != NL80211_CHAN_WIDTH_20_NOHT)) {
 		ret = wl1271_acx_set_ht_information(wl, wlvif,
 					bss_conf->ht_operation_mode);
 		if (ret < 0) {
@@ -3905,7 +3905,8 @@ sta_not_found:
 			u32 rates;
 			int ieoffset;
 			wlvif->aid = bss_conf->aid;
-			wlvif->channel_type = bss_conf->channel_type;
+			wlvif->channel_type =
+				cfg80211_get_chandef_type(&bss_conf->chandef);
 			wlvif->beacon_int = bss_conf->beacon_int;
 			do_join = true;
 			set_assoc = true;
@@ -4071,7 +4072,7 @@ sta_not_found:
 	/* Handle new association with HT. Do this after join. */
 	if (sta_exists) {
 		if ((changed & BSS_CHANGED_HT) &&
-		    (bss_conf->channel_type != NL80211_CHAN_NO_HT)) {
+		    (bss_conf->chandef.width != NL80211_CHAN_WIDTH_20_NOHT)) {
 			ret = wl1271_acx_set_ht_capabilities(wl,
 							     &sta_ht_cap,
 							     true,
@@ -4098,7 +4099,7 @@ sta_not_found:
 
 	/* Handle HT information change. Done after join. */
 	if ((changed & BSS_CHANGED_HT) &&
-	    (bss_conf->channel_type != NL80211_CHAN_NO_HT)) {
+	    (bss_conf->chandef.width != NL80211_CHAN_WIDTH_20_NOHT)) {
 		ret = wl1271_acx_set_ht_information(wl, wlvif,
 					bss_conf->ht_operation_mode);
 		if (ret < 0) {
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 12093778b057..6af51328dcd1 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -145,11 +145,11 @@ struct ieee80211_low_level_stats {
 
 /**
  * enum ieee80211_chanctx_change - change flag for channel context
- * @IEEE80211_CHANCTX_CHANGE_CHANNEL_TYPE: The channel type was changed
+ * @IEEE80211_CHANCTX_CHANGE_WIDTH: The channel width changed
  * @IEEE80211_CHANCTX_CHANGE_RX_CHAINS: The number of RX chains changed
  */
 enum ieee80211_chanctx_change {
-	IEEE80211_CHANCTX_CHANGE_CHANNEL_TYPE	= BIT(0),
+	IEEE80211_CHANCTX_CHANGE_WIDTH		= BIT(0),
 	IEEE80211_CHANCTX_CHANGE_RX_CHAINS	= BIT(1),
 };
 
@@ -159,8 +159,7 @@ enum ieee80211_chanctx_change {
  * This is the driver-visible part. The ieee80211_chanctx
  * that contains it is visible in mac80211 only.
  *
- * @channel: the channel to tune to
- * @channel_type: the channel (HT) type
+ * @def: the channel definition
  * @rx_chains_static: The number of RX chains that must always be
  *	active on the channel to receive MIMO transmissions
  * @rx_chains_dynamic: The number of RX chains that must be enabled
@@ -170,8 +169,7 @@ enum ieee80211_chanctx_change {
  *	sizeof(void *), size is determined in hw information.
  */
 struct ieee80211_chanctx_conf {
-	struct ieee80211_channel *channel;
-	enum nl80211_channel_type channel_type;
+	struct cfg80211_chan_def def;
 
 	u8 rx_chains_static, rx_chains_dynamic;
 
@@ -288,9 +286,8 @@ enum ieee80211_rssi_event {
  * @mcast_rate: per-band multicast rate index + 1 (0: disabled)
  * @bssid: The BSSID for this BSS
  * @enable_beacon: whether beaconing should be enabled or not
- * @channel_type: Channel type for this BSS -- the hardware might be
- *	configured for HT40+ while this BSS only uses no-HT, for
- *	example.
+ * @chandef: Channel definition for this BSS -- the hardware might be
+ *	configured a higher bandwidth than this BSS uses, for example.
  * @ht_operation_mode: HT operation mode like in &struct ieee80211_ht_operation.
  *	This field is only valid when the channel type is one of the HT types.
  * @cqm_rssi_thold: Connection quality monitor RSSI threshold, a zero value
@@ -339,7 +336,7 @@ struct ieee80211_bss_conf {
 	u16 ht_operation_mode;
 	s32 cqm_rssi_thold;
 	u32 cqm_rssi_hyst;
-	enum nl80211_channel_type channel_type;
+	struct cfg80211_chan_def chandef;
 	__be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN];
 	u8 arp_addr_cnt;
 	bool arp_filter_enabled;
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 7136b945798e..b9702d16d608 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -615,7 +615,7 @@ do_survey:
 	rcu_read_lock();
 	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 	if (chanctx_conf)
-		channel = chanctx_conf->channel;
+		channel = chanctx_conf->def.chan;
 	else
 		channel = NULL;
 	rcu_read_unlock();
@@ -739,13 +739,9 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
 	struct ieee80211_sub_if_data *sdata;
-	enum nl80211_channel_type channel_type;
 	int ret = 0;
 
-	channel_type = cfg80211_get_chandef_type(chandef);
-
-	if (local->monitor_channel == chandef->chan &&
-	    local->monitor_channel_type == channel_type)
+	if (cfg80211_chandef_identical(&local->monitor_chandef, chandef))
 		return 0;
 
 	mutex_lock(&local->iflist_mtx);
@@ -755,20 +751,17 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
 				lockdep_is_held(&local->iflist_mtx));
 		if (sdata) {
 			ieee80211_vif_release_channel(sdata);
-			ret = ieee80211_vif_use_channel(
-					sdata, chandef->chan, channel_type,
+			ret = ieee80211_vif_use_channel(sdata, chandef,
 					IEEE80211_CHANCTX_EXCLUSIVE);
 		}
 	} else if (local->open_count == local->monitors) {
 		local->_oper_channel = chandef->chan;
-		local->_oper_channel_type = channel_type;
+		local->_oper_channel_type = cfg80211_get_chandef_type(chandef);
 		ieee80211_hw_config(local, 0);
 	}
 
-	if (ret == 0) {
-		local->monitor_channel = chandef->chan;
-		local->monitor_channel_type = channel_type;
-	}
+	if (ret == 0)
+		local->monitor_chandef = *chandef;
 	mutex_unlock(&local->iflist_mtx);
 
 	return ret;
@@ -890,10 +883,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 	sdata->needed_rx_chains = sdata->local->rx_chains;
 
-	err = ieee80211_vif_use_channel(
-		sdata, params->chandef.chan,
-		cfg80211_get_chandef_type(&params->chandef),
-		IEEE80211_CHANCTX_SHARED);
+	err = ieee80211_vif_use_channel(sdata, &params->chandef,
+					IEEE80211_CHANCTX_SHARED);
 	if (err)
 		return err;
 
@@ -1710,10 +1701,8 @@ static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev,
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 	sdata->needed_rx_chains = sdata->local->rx_chains;
 
-	err = ieee80211_vif_use_channel(
-		sdata, setup->chandef.chan,
-		cfg80211_get_chandef_type(&setup->chandef),
-		IEEE80211_CHANCTX_SHARED);
+	err = ieee80211_vif_use_channel(sdata, &setup->chandef,
+					IEEE80211_CHANCTX_SHARED);
 	if (err)
 		return err;
 
@@ -2133,7 +2122,7 @@ int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata,
 	 * the new value until we associate.
 	 */
 	if (!sdata->u.mgd.associated ||
-	    sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT)
+	    sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT)
 		return 0;
 
 	ap = sdata->u.mgd.associated->bssid;
@@ -2589,7 +2578,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 
 		if (chanctx_conf)
-			need_offchan = chan != chanctx_conf->channel;
+			need_offchan = chan != chanctx_conf->def.chan;
 		else
 			need_offchan = true;
 		rcu_read_unlock();
@@ -3057,7 +3046,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
 		rcu_read_unlock();
 		return -EINVAL;
 	}
-	band = chanctx_conf->channel->band;
+	band = chanctx_conf->def.chan->band;
 	sta = sta_info_get(sdata, peer);
 	if (sta) {
 		qos = test_sta_flag(sta, WLAN_STA_WME);
@@ -3125,9 +3114,7 @@ static int ieee80211_cfg_get_channel(struct wiphy *wiphy,
 	rcu_read_lock();
 	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 	if (chanctx_conf) {
-		cfg80211_chandef_create(chandef,
-					chanctx_conf->channel,
-					chanctx_conf->channel_type);
+		*chandef = chanctx_conf->def;
 		ret = 0;
 	}
 	rcu_read_unlock();
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index a2b06d40aebf..53f03120db55 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -8,93 +8,47 @@
 #include "ieee80211_i.h"
 #include "driver-ops.h"
 
-static bool
-ieee80211_channel_types_are_compatible(enum nl80211_channel_type chantype1,
-				       enum nl80211_channel_type chantype2,
-				       enum nl80211_channel_type *compat)
+static void ieee80211_change_chandef(struct ieee80211_local *local,
+				     struct ieee80211_chanctx *ctx,
+				     const struct cfg80211_chan_def *chandef)
 {
-	/*
-	 * start out with chantype1 being the result,
-	 * overwriting later if needed
-	 */
-	if (compat)
-		*compat = chantype1;
-
-	switch (chantype1) {
-	case NL80211_CHAN_NO_HT:
-		if (compat)
-			*compat = chantype2;
-		break;
-	case NL80211_CHAN_HT20:
-		/*
-		 * allow any change that doesn't go to no-HT
-		 * (if it already is no-HT no change is needed)
-		 */
-		if (chantype2 == NL80211_CHAN_NO_HT)
-			break;
-		if (compat)
-			*compat = chantype2;
-		break;
-	case NL80211_CHAN_HT40PLUS:
-	case NL80211_CHAN_HT40MINUS:
-		/* allow smaller bandwidth and same */
-		if (chantype2 == NL80211_CHAN_NO_HT)
-			break;
-		if (chantype2 == NL80211_CHAN_HT20)
-			break;
-		if (chantype2 == chantype1)
-			break;
-		return false;
-	}
-
-	return true;
-}
-
-static void ieee80211_change_chantype(struct ieee80211_local *local,
-				      struct ieee80211_chanctx *ctx,
-				      enum nl80211_channel_type chantype)
-{
-	if (chantype == ctx->conf.channel_type)
+	if (cfg80211_chandef_identical(&ctx->conf.def, chandef))
 		return;
 
-	ctx->conf.channel_type = chantype;
-	drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_CHANNEL_TYPE);
+	WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef));
+
+	ctx->conf.def = *chandef;
+	drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_WIDTH);
 
 	if (!local->use_chanctx) {
-		local->_oper_channel_type = chantype;
+		local->_oper_channel_type = cfg80211_get_chandef_type(chandef);
 		ieee80211_hw_config(local, 0);
 	}
 }
 
 static struct ieee80211_chanctx *
 ieee80211_find_chanctx(struct ieee80211_local *local,
-		       struct ieee80211_channel *channel,
-		       enum nl80211_channel_type channel_type,
+		       const struct cfg80211_chan_def *chandef,
 		       enum ieee80211_chanctx_mode mode)
 {
 	struct ieee80211_chanctx *ctx;
-	enum nl80211_channel_type compat_type;
 
 	lockdep_assert_held(&local->chanctx_mtx);
 
 	if (mode == IEEE80211_CHANCTX_EXCLUSIVE)
 		return NULL;
-	if (WARN_ON(!channel))
-		return NULL;
 
 	list_for_each_entry(ctx, &local->chanctx_list, list) {
-		compat_type = ctx->conf.channel_type;
+		const struct cfg80211_chan_def *compat;
 
 		if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE)
 			continue;
-		if (ctx->conf.channel != channel)
-			continue;
-		if (!ieee80211_channel_types_are_compatible(ctx->conf.channel_type,
-							    channel_type,
-							    &compat_type))
+
+		compat = cfg80211_chandef_compatible(&ctx->conf.def, chandef);
+		if (!compat)
 			continue;
 
-		ieee80211_change_chantype(local, ctx, compat_type);
+		ieee80211_change_chandef(local, ctx, compat);
 
 		return ctx;
 	}
@@ -104,8 +58,7 @@ ieee80211_find_chanctx(struct ieee80211_local *local,
 
 static struct ieee80211_chanctx *
 ieee80211_new_chanctx(struct ieee80211_local *local,
-		      struct ieee80211_channel *channel,
-		      enum nl80211_channel_type channel_type,
+		      const struct cfg80211_chan_def *chandef,
 		      enum ieee80211_chanctx_mode mode)
 {
 	struct ieee80211_chanctx *ctx;
@@ -117,15 +70,15 @@ ieee80211_new_chanctx(struct ieee80211_local *local,
 	if (!ctx)
 		return ERR_PTR(-ENOMEM);
 
-	ctx->conf.channel = channel;
-	ctx->conf.channel_type = channel_type;
+	ctx->conf.def = *chandef;
 	ctx->conf.rx_chains_static = 1;
 	ctx->conf.rx_chains_dynamic = 1;
 	ctx->mode = mode;
 
 	if (!local->use_chanctx) {
-		local->_oper_channel_type = channel_type;
-		local->_oper_channel = channel;
+		local->_oper_channel_type =
+			cfg80211_get_chandef_type(chandef);
+		local->_oper_channel = chandef->chan;
 		ieee80211_hw_config(local, 0);
 	} else {
 		err = drv_add_chanctx(local, ctx);
@@ -178,41 +131,37 @@ static int ieee80211_assign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
-static enum nl80211_channel_type
-ieee80211_calc_chantype(struct ieee80211_local *local,
-			struct ieee80211_chanctx *ctx)
+static void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local,
+					      struct ieee80211_chanctx *ctx)
 {
 	struct ieee80211_chanctx_conf *conf = &ctx->conf;
 	struct ieee80211_sub_if_data *sdata;
-	enum nl80211_channel_type result = NL80211_CHAN_NO_HT;
+	const struct cfg80211_chan_def *compat = NULL;
 
 	lockdep_assert_held(&local->chanctx_mtx);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+
 		if (!ieee80211_sdata_running(sdata))
 			continue;
 		if (rcu_access_pointer(sdata->vif.chanctx_conf) != conf)
 			continue;
 
-		WARN_ON_ONCE(!ieee80211_channel_types_are_compatible(
-					sdata->vif.bss_conf.channel_type,
-					result, &result));
+		if (!compat)
+			compat = &sdata->vif.bss_conf.chandef;
+
+		compat = cfg80211_chandef_compatible(
+				&sdata->vif.bss_conf.chandef, compat);
+		if (!compat)
+			break;
 	}
 	rcu_read_unlock();
 
-	return result;
-}
-
-static void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local,
-					      struct ieee80211_chanctx *ctx)
-{
-	enum nl80211_channel_type chantype;
-
-	lockdep_assert_held(&local->chanctx_mtx);
+	if (WARN_ON_ONCE(!compat))
+		return;
 
-	chantype = ieee80211_calc_chantype(local, ctx);
-	ieee80211_change_chantype(local, ctx, chantype);
+	ieee80211_change_chandef(local, ctx, compat);
 }
 
 static void ieee80211_unassign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
@@ -337,8 +286,7 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
 }
 
 int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
-			      struct ieee80211_channel *channel,
-			      enum nl80211_channel_type channel_type,
+			      const struct cfg80211_chan_def *chandef,
 			      enum ieee80211_chanctx_mode mode)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -350,15 +298,15 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 	mutex_lock(&local->chanctx_mtx);
 	__ieee80211_vif_release_channel(sdata);
 
-	ctx = ieee80211_find_chanctx(local, channel, channel_type, mode);
+	ctx = ieee80211_find_chanctx(local, chandef, mode);
 	if (!ctx)
-		ctx = ieee80211_new_chanctx(local, channel, channel_type, mode);
+		ctx = ieee80211_new_chanctx(local, chandef, mode);
 	if (IS_ERR(ctx)) {
 		ret = PTR_ERR(ctx);
 		goto out;
 	}
 
-	sdata->vif.bss_conf.channel_type = channel_type;
+	sdata->vif.bss_conf.chandef = *chandef;
 
 	ret = ieee80211_assign_vif_chanctx(sdata, ctx);
 	if (ret) {
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index ba9bd0ef119a..cbde5cc49a40 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -168,7 +168,6 @@ IEEE80211_IF_FILE(rc_rateidx_mcs_mask_5ghz,
 
 IEEE80211_IF_FILE(flags, flags, HEX);
 IEEE80211_IF_FILE(state, state, LHEX);
-IEEE80211_IF_FILE(channel_type, vif.bss_conf.channel_type, DEC);
 IEEE80211_IF_FILE(txpower, vif.bss_conf.txpower, DEC);
 IEEE80211_IF_FILE(ap_power_level, ap_power_level, DEC);
 IEEE80211_IF_FILE(user_power_level, user_power_level, DEC);
@@ -632,7 +631,6 @@ static void add_files(struct ieee80211_sub_if_data *sdata)
 
 	DEBUGFS_ADD(flags);
 	DEBUGFS_ADD(state);
-	DEBUGFS_ADD(channel_type);
 	DEBUGFS_ADD(txpower);
 	DEBUGFS_ADD(user_power_level);
 	DEBUGFS_ADD(ap_power_level);
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 5648bbed240b..11a6a1bde2fd 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -52,7 +52,6 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	u32 bss_change;
 	u8 supp_rates[IEEE80211_MAX_SUPP_RATES];
 	struct cfg80211_chan_def chandef;
-	enum nl80211_channel_type chan_type;
 
 	lockdep_assert_held(&ifibss->mtx);
 
@@ -80,13 +79,14 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 
 	sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0;
 
-	chan_type = ifibss->channel_type;
-	cfg80211_chandef_create(&chandef, chan, chan_type);
-	if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef))
-		chan_type = NL80211_CHAN_HT20;
+	cfg80211_chandef_create(&chandef, chan, ifibss->channel_type);
+	if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef)) {
+		chandef.width = NL80211_CHAN_WIDTH_20;
+		chandef.center_freq1 = chan->center_freq;
+	}
 
 	ieee80211_vif_release_channel(sdata);
-	if (ieee80211_vif_use_channel(sdata, chan, chan_type,
+	if (ieee80211_vif_use_channel(sdata, &chandef,
 				      ifibss->fixed_channel ?
 					IEEE80211_CHANCTX_SHARED :
 					IEEE80211_CHANCTX_EXCLUSIVE)) {
@@ -160,7 +160,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 		       ifibss->ie, ifibss->ie_len);
 
 	/* add HT capability and information IEs */
-	if (chan_type != NL80211_CHAN_NO_HT &&
+	if (chandef.width != NL80211_CHAN_WIDTH_20_NOHT &&
 	    sband->ht_cap.ht_supported) {
 		pos = skb_put(skb, 4 +
 				   sizeof(struct ieee80211_ht_cap) +
@@ -173,7 +173,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 		 * keep them at 0
 		 */
 		pos = ieee80211_ie_build_ht_oper(pos, &sband->ht_cap,
-						 chan, chan_type, 0);
+						 &chandef, 0);
 	}
 
 	if (local->hw.queues >= IEEE80211_NUM_ACS) {
@@ -329,7 +329,7 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata,
 	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 	if (WARN_ON_ONCE(!chanctx_conf))
 		return NULL;
-	band = chanctx_conf->channel->band;
+	band = chanctx_conf->def.chan->band;
 	rcu_read_unlock();
 
 	sta = sta_info_alloc(sdata, addr, GFP_KERNEL);
@@ -478,9 +478,11 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 		    sdata->u.ibss.channel_type != NL80211_CHAN_NO_HT) {
 			/* we both use HT */
 			struct ieee80211_sta_ht_cap sta_ht_cap_new;
-			enum nl80211_channel_type channel_type =
-				ieee80211_ht_oper_to_channel_type(
-							elems->ht_operation);
+			struct cfg80211_chan_def chandef;
+
+			ieee80211_ht_oper_to_chandef(channel,
+						     elems->ht_operation,
+						     &chandef);
 
 			ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband,
 							  elems->ht_cap_elem,
@@ -490,9 +492,9 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 			 * fall back to HT20 if we don't use or use
 			 * the other extension channel
 			 */
-			if (!(channel_type == NL80211_CHAN_HT40MINUS ||
-			      channel_type == NL80211_CHAN_HT40PLUS) ||
-			    channel_type != sdata->u.ibss.channel_type)
+			if (chandef.width != NL80211_CHAN_WIDTH_40 ||
+			    cfg80211_get_chandef_type(&chandef) !=
+						sdata->u.ibss.channel_type)
 				sta_ht_cap_new.cap &=
 					~IEEE80211_HT_CAP_SUP_WIDTH_20_40;
 
@@ -616,7 +618,7 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata,
 		rcu_read_unlock();
 		return;
 	}
-	band = chanctx_conf->channel->band;
+	band = chanctx_conf->def.chan->band;
 	rcu_read_unlock();
 
 	sta = sta_info_alloc(sdata, addr, GFP_ATOMIC);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index fba4b1f425c1..0a8f83d142f9 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -799,7 +799,7 @@ ieee80211_get_sdata_band(struct ieee80211_sub_if_data *sdata)
 	rcu_read_lock();
 	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 	if (!WARN_ON(!chanctx_conf))
-		band = chanctx_conf->channel->band;
+		band = chanctx_conf->def.chan->band;
 	rcu_read_unlock();
 
 	return band;
@@ -1156,8 +1156,7 @@ struct ieee80211_local {
 
 	/* virtual monitor interface */
 	struct ieee80211_sub_if_data __rcu *monitor_sdata;
-	struct ieee80211_channel *monitor_channel;
-	enum nl80211_channel_type monitor_channel_type;
+	struct cfg80211_chan_def monitor_chandef;
 };
 
 static inline struct ieee80211_sub_if_data *
@@ -1514,7 +1513,7 @@ static inline void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata,
 	}
 
 	__ieee80211_tx_skb_tid_band(sdata, skb, tid,
-				    chanctx_conf->channel->band);
+				    chanctx_conf->def.chan->band);
 	rcu_read_unlock();
 }
 
@@ -1603,8 +1602,7 @@ size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset);
 u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
 			      u16 cap);
 u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
-			       struct ieee80211_channel *channel,
-			       enum nl80211_channel_type channel_type,
+			       const struct cfg80211_chan_def *chandef,
 			       u16 prot_mode);
 u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 			       u32 cap);
@@ -1616,13 +1614,13 @@ int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata,
 				enum ieee80211_band band);
 
 /* channel management */
-enum nl80211_channel_type
-ieee80211_ht_oper_to_channel_type(struct ieee80211_ht_operation *ht_oper);
+void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan,
+				  struct ieee80211_ht_operation *ht_oper,
+				  struct cfg80211_chan_def *chandef);
 
 int __must_check
 ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
-			  struct ieee80211_channel *channel,
-			  enum nl80211_channel_type channel_type,
+			  const struct cfg80211_chan_def *chandef,
 			  enum ieee80211_chanctx_mode mode);
 void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata);
 
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 80ce90b29d9d..5331662489f7 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -54,7 +54,7 @@ bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
 		return false;
 	}
 
-	power = chanctx_conf->channel->max_power;
+	power = chanctx_conf->def.chan->max_power;
 	rcu_read_unlock();
 
 	if (sdata->user_power_level != IEEE80211_UNSET_POWER_LEVEL)
@@ -415,8 +415,7 @@ static int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
 		goto out_unlock;
 	}
 
-	ret = ieee80211_vif_use_channel(sdata, local->monitor_channel,
-					local->monitor_channel_type,
+	ret = ieee80211_vif_use_channel(sdata, &local->monitor_chandef,
 					IEEE80211_CHANCTX_EXCLUSIVE);
 	if (ret) {
 		drv_remove_interface(local, sdata);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index b229cded4567..6e933409979a 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -798,10 +798,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 			local->_oper_channel = &sband->channels[0];
 			local->hw.conf.channel_type = NL80211_CHAN_NO_HT;
 		}
-		if (!local->monitor_channel) {
-			local->monitor_channel = &sband->channels[0];
-			local->monitor_channel_type = NL80211_CHAN_NO_HT;
-		}
+		cfg80211_chandef_create(&local->monitor_chandef,
+					&sband->channels[0],
+					NL80211_CHAN_NO_HT);
 		channels += sband->n_channels;
 
 		if (max_bitrates < sband->n_bitrates)
@@ -884,10 +883,22 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	if (supp_ht)
 		local->scan_ies_len += 2 + sizeof(struct ieee80211_ht_cap);
 
-	if (supp_vht)
+	if (supp_vht) {
 		local->scan_ies_len +=
 			2 + sizeof(struct ieee80211_vht_cap);
 
+		/*
+		 * (for now at least), drivers wanting to use VHT must
+		 * support channel contexts, as they contain all the
+		 * necessary VHT information and the global hw config
+		 * doesn't (yet)
+		 */
+		if (WARN_ON(!local->use_chanctx)) {
+			result = -EINVAL;
+			goto fail_wiphy_register;
+		}
+	}
+
 	if (!local->ops->hw_scan) {
 		/* For hw_scan, driver needs to set these up. */
 		local->hw.wiphy->max_scan_ssids = 4;
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 943694a52624..1bf03f9ff3ba 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -76,7 +76,7 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
 	struct ieee80211_local *local = sdata->local;
 	u32 basic_rates = 0;
-	enum nl80211_channel_type sta_channel_type = NL80211_CHAN_NO_HT;
+	struct cfg80211_chan_def sta_chan_def;
 
 	/*
 	 * As support for each feature is added, check for matching
@@ -103,17 +103,11 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata,
 	if (sdata->vif.bss_conf.basic_rates != basic_rates)
 		goto mismatch;
 
-	if (ie->ht_operation)
-		sta_channel_type =
-			ieee80211_ht_oper_to_channel_type(ie->ht_operation);
-
-	/* Disallow HT40+/- mismatch */
-	if (ie->ht_operation &&
-	    (sdata->vif.bss_conf.channel_type == NL80211_CHAN_HT40MINUS ||
-	     sdata->vif.bss_conf.channel_type == NL80211_CHAN_HT40PLUS) &&
-	    (sta_channel_type == NL80211_CHAN_HT40MINUS ||
-	     sta_channel_type == NL80211_CHAN_HT40PLUS) &&
-	    sdata->vif.bss_conf.channel_type != sta_channel_type)
+	ieee80211_ht_oper_to_chandef(sdata->vif.bss_conf.chandef.chan,
+				     ie->ht_operation, &sta_chan_def);
+
+	if (!cfg80211_chandef_compatible(&sdata->vif.bss_conf.chandef,
+					 &sta_chan_def))
 		goto mismatch;
 
 	return true;
@@ -368,7 +362,7 @@ int mesh_add_ds_params_ie(struct sk_buff *skb,
 		rcu_read_unlock();
 		return -EINVAL;
 	}
-	chan = chanctx_conf->channel;
+	chan = chanctx_conf->def.chan;
 	rcu_read_unlock();
 
 	sband = local->hw.wiphy->bands[chan->band];
@@ -392,7 +386,7 @@ int mesh_add_ht_cap_ie(struct sk_buff *skb,
 
 	sband = local->hw.wiphy->bands[band];
 	if (!sband->ht_cap.ht_supported ||
-	    sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT)
+	    sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT)
 		return 0;
 
 	if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_ht_cap))
@@ -411,7 +405,7 @@ int mesh_add_ht_oper_ie(struct sk_buff *skb,
 	struct ieee80211_chanctx_conf *chanctx_conf;
 	struct ieee80211_channel *channel;
 	enum nl80211_channel_type channel_type =
-		sdata->vif.bss_conf.channel_type;
+		cfg80211_get_chandef_type(&sdata->vif.bss_conf.chandef);
 	struct ieee80211_supported_band *sband;
 	struct ieee80211_sta_ht_cap *ht_cap;
 	u8 *pos;
@@ -422,7 +416,7 @@ int mesh_add_ht_oper_ie(struct sk_buff *skb,
 		rcu_read_unlock();
 		return -EINVAL;
 	}
-	channel = chanctx_conf->channel;
+	channel = chanctx_conf->def.chan;
 	rcu_read_unlock();
 
 	sband = local->hw.wiphy->bands[channel->band];
@@ -435,7 +429,7 @@ int mesh_add_ht_oper_ie(struct sk_buff *skb,
 		return -ENOMEM;
 
 	pos = skb_put(skb, 2 + sizeof(struct ieee80211_ht_operation));
-	ieee80211_ie_build_ht_oper(pos, ht_cap, channel, channel_type,
+	ieee80211_ie_build_ht_oper(pos, ht_cap, &sdata->vif.bss_conf.chandef,
 				   sdata->vif.bss_conf.ht_operation_mode);
 
 	return 0;
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 7a47f4063d0a..ca52dfdd5375 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -111,7 +111,7 @@ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata)
 	u16 ht_opmode;
 	bool non_ht_sta = false, ht20_sta = false;
 
-	if (sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT)
+	if (sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT)
 		return 0;
 
 	rcu_read_lock();
@@ -120,14 +120,14 @@ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata)
 		    sta->plink_state != NL80211_PLINK_ESTAB)
 			continue;
 
-		switch (sta->ch_type) {
-		case NL80211_CHAN_NO_HT:
+		switch (sta->ch_width) {
+		case NL80211_CHAN_WIDTH_20_NOHT:
 			mpl_dbg(sdata,
 				"mesh_plink %pM: nonHT sta (%pM) is present\n",
 				sdata->vif.addr, sta->sta.addr);
 			non_ht_sta = true;
 			goto out;
-		case NL80211_CHAN_HT20:
+		case NL80211_CHAN_WIDTH_20:
 			mpl_dbg(sdata,
 				"mesh_plink %pM: HT20 sta (%pM) is present\n",
 				sdata->vif.addr, sta->sta.addr);
@@ -142,7 +142,7 @@ out:
 	if (non_ht_sta)
 		ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED;
 	else if (ht20_sta &&
-		 sdata->vif.bss_conf.channel_type > NL80211_CHAN_HT20)
+		 sdata->vif.bss_conf.chandef.width > NL80211_CHAN_WIDTH_20)
 		ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_20MHZ;
 	else
 		ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONE;
@@ -372,7 +372,7 @@ static struct sta_info *mesh_peer_init(struct ieee80211_sub_if_data *sdata,
 
 	sta->sta.supp_rates[band] = rates;
 	if (elems->ht_cap_elem &&
-	    sdata->vif.bss_conf.channel_type != NL80211_CHAN_NO_HT)
+	    sdata->vif.bss_conf.chandef.width != NL80211_CHAN_WIDTH_20_NOHT)
 		ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband,
 						  elems->ht_cap_elem,
 						  &sta->sta.ht_cap);
@@ -380,12 +380,15 @@ static struct sta_info *mesh_peer_init(struct ieee80211_sub_if_data *sdata,
 		memset(&sta->sta.ht_cap, 0, sizeof(sta->sta.ht_cap));
 
 	if (elems->ht_operation) {
+		struct cfg80211_chan_def chandef;
+
 		if (!(elems->ht_operation->ht_param &
 		      IEEE80211_HT_PARAM_CHAN_WIDTH_ANY))
 			sta->sta.ht_cap.cap &=
 					    ~IEEE80211_HT_CAP_SUP_WIDTH_20_40;
-		sta->ch_type =
-			ieee80211_ht_oper_to_channel_type(elems->ht_operation);
+		ieee80211_ht_oper_to_chandef(sdata->vif.bss_conf.chandef.chan,
+					     elems->ht_operation, &chandef);
+		sta->ch_width = chandef.width;
 	}
 
 	rate_control_rate_init(sta);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 2cec14cc02d1..d2a4f78b4b0f 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -191,17 +191,19 @@ static u32 ieee80211_config_ht_tx(struct ieee80211_sub_if_data *sdata,
 		rcu_read_unlock();
 		return 0;
 	}
-	chan = chanctx_conf->channel;
+	chan = chanctx_conf->def.chan;
 	rcu_read_unlock();
 	sband = local->hw.wiphy->bands[chan->band];
 
-	switch (sdata->vif.bss_conf.channel_type) {
-	case NL80211_CHAN_HT40PLUS:
-		if (chan->flags & IEEE80211_CHAN_NO_HT40PLUS)
+	switch (sdata->vif.bss_conf.chandef.width) {
+	case NL80211_CHAN_WIDTH_40:
+		if (sdata->vif.bss_conf.chandef.chan->center_freq >
+				sdata->vif.bss_conf.chandef.center_freq1 &&
+		    chan->flags & IEEE80211_CHAN_NO_HT40PLUS)
 			disable_40 = true;
-		break;
-	case NL80211_CHAN_HT40MINUS:
-		if (chan->flags & IEEE80211_CHAN_NO_HT40MINUS)
+		if (sdata->vif.bss_conf.chandef.chan->center_freq <
+				sdata->vif.bss_conf.chandef.center_freq1 &&
+		    chan->flags & IEEE80211_CHAN_NO_HT40MINUS)
 			disable_40 = true;
 		break;
 	default:
@@ -381,7 +383,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		rcu_read_unlock();
 		return;
 	}
-	chan = chanctx_conf->channel;
+	chan = chanctx_conf->def.chan;
 	rcu_read_unlock();
 	sband = local->hw.wiphy->bands[chan->band];
 
@@ -2476,11 +2478,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
-	if (rx_status->freq != chanctx_conf->channel->center_freq) {
+	if (rx_status->freq != chanctx_conf->def.chan->center_freq) {
 		rcu_read_unlock();
 		return;
 	}
-	chan = chanctx_conf->channel;
+	chan = chanctx_conf->def.chan;
 	rcu_read_unlock();
 
 	if (ifmgd->assoc_data && !ifmgd->assoc_data->have_beacon &&
@@ -3191,6 +3193,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	const u8 *ht_oper_ie;
 	const struct ieee80211_ht_operation *ht_oper = NULL;
 	struct ieee80211_supported_band *sband;
+	struct cfg80211_chan_def chandef;
 
 	sband = local->hw.wiphy->bands[cbss->channel->band];
 
@@ -3277,7 +3280,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 
 	ieee80211_vif_release_channel(sdata);
-	return ieee80211_vif_use_channel(sdata, cbss->channel, channel_type,
+	cfg80211_chandef_create(&chandef, cbss->channel, channel_type);
+	return ieee80211_vif_use_channel(sdata, &chandef,
 					 IEEE80211_CHANCTX_SHARED);
 }
 
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 3313c117b322..dd88381c53b7 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -391,7 +391,7 @@ static void rate_idx_match_mask(struct ieee80211_tx_rate *rate,
 			return;
 
 		/* if HT BSS, and we handle a data frame, also try HT rates */
-		if (txrc->bss_conf->channel_type == NL80211_CHAN_NO_HT)
+		if (txrc->bss_conf->chandef.width == NL80211_CHAN_WIDTH_20_NOHT)
 			return;
 
 		fc = hdr->frame_control;
@@ -408,8 +408,7 @@ static void rate_idx_match_mask(struct ieee80211_tx_rate *rate,
 
 		alt_rate.flags |= IEEE80211_TX_RC_MCS;
 
-		if ((txrc->bss_conf->channel_type == NL80211_CHAN_HT40MINUS) ||
-		    (txrc->bss_conf->channel_type == NL80211_CHAN_HT40PLUS))
+		if (txrc->bss_conf->chandef.width == NL80211_CHAN_WIDTH_40)
 			alt_rate.flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
 
 		if (rate_idx_match_mcs_mask(&alt_rate, mcs_mask)) {
diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h
index ec198ef6aa8a..301386dabf88 100644
--- a/net/mac80211/rate.h
+++ b/net/mac80211/rate.h
@@ -65,7 +65,7 @@ static inline void rate_control_rate_init(struct sta_info *sta)
 		return;
 	}
 
-	sband = local->hw.wiphy->bands[chanctx_conf->channel->band];
+	sband = local->hw.wiphy->bands[chanctx_conf->def.chan->band];
 	rcu_read_unlock();
 
 	ref->ops->rate_init(ref->priv, sband, ista, priv_sta);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index a0836d7187c1..dadcfcf29122 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1087,7 +1087,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
-	ieee80211_xmit(sdata, skb, chanctx_conf->channel->band);
+	ieee80211_xmit(sdata, skb, chanctx_conf->def.chan->band);
 	rcu_read_unlock();
 }
 
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 776f3d0b4a47..2b2d5aac2bb1 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -272,7 +272,7 @@ struct sta_ampdu_mlme {
  * @t_offset: timing offset relative to this host
  * @t_offset_setpoint: reference timing offset of this sta to be used when
  * 	calculating clockdrift
- * @ch_type: peer's channel type
+ * @ch_width: peer's channel width
  * @debugfs: debug filesystem info
  * @dead: set to true when sta is unlinked
  * @uploaded: set to true when sta is uploaded to the driver
@@ -368,7 +368,7 @@ struct sta_info {
 	struct timer_list plink_timer;
 	s64 t_offset;
 	s64 t_offset_setpoint;
-	enum nl80211_channel_type ch_type;
+	enum nl80211_chan_width ch_width;
 #endif
 
 #ifdef CONFIG_MAC80211_DEBUGFS
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index bc28346ba207..a8270b441a6f 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -28,16 +28,21 @@
 #define VIF_PR_FMT	" vif:%s(%d%s)"
 #define VIF_PR_ARG	__get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : ""
 
-#define CHANCTX_ENTRY	__field(int, freq)					\
-			__field(int, chantype)					\
+#define CHANCTX_ENTRY	__field(u32, control_freq)				\
+			__field(u32, chan_width)				\
+			__field(u32, center_freq1)				\
+			__field(u32, center_freq2)				\
 			__field(u8, rx_chains_static)				\
 			__field(u8, rx_chains_dynamic)
-#define CHANCTX_ASSIGN	__entry->freq = ctx->conf.channel->center_freq;		\
-			__entry->chantype = ctx->conf.channel_type;		\
+#define CHANCTX_ASSIGN	__entry->control_freq = ctx->conf.def.chan->center_freq;\
+			__entry->chan_width = ctx->conf.def.width;		\
+			__entry->center_freq1 = ctx->conf.def.center_freq1;	\
+			__entry->center_freq2 = ctx->conf.def.center_freq2;	\
 			__entry->rx_chains_static = ctx->conf.rx_chains_static;	\
 			__entry->rx_chains_dynamic = ctx->conf.rx_chains_dynamic
-#define CHANCTX_PR_FMT	" freq:%d MHz chantype:%d chains:%d/%d"
-#define CHANCTX_PR_ARG	__entry->freq, __entry->chantype,			\
+#define CHANCTX_PR_FMT	" control:%d MHz width:%d center: %d/%d MHz chains:%d/%d"
+#define CHANCTX_PR_ARG	__entry->control_freq, __entry->chan_width,		\
+			__entry->center_freq1, __entry->center_freq2,		\
 			__entry->rx_chains_static, __entry->rx_chains_dynamic
 
 
@@ -334,7 +339,8 @@ TRACE_EVENT(drv_bss_info_changed,
 		__field(u16, ht_operation_mode)
 		__field(s32, cqm_rssi_thold);
 		__field(s32, cqm_rssi_hyst);
-		__field(u32, channel_type);
+		__field(u32, channel_width);
+		__field(u32, channel_cfreq1);
 		__dynamic_array(u32, arp_addr_list, info->arp_addr_cnt);
 		__field(bool, arp_filter_enabled);
 		__field(bool, qos);
@@ -370,7 +376,8 @@ TRACE_EVENT(drv_bss_info_changed,
 		__entry->ht_operation_mode = info->ht_operation_mode;
 		__entry->cqm_rssi_thold = info->cqm_rssi_thold;
 		__entry->cqm_rssi_hyst = info->cqm_rssi_hyst;
-		__entry->channel_type = info->channel_type;
+		__entry->channel_width = info->chandef.width;
+		__entry->channel_cfreq1 = info->chandef.center_freq1;
 		memcpy(__get_dynamic_array(arp_addr_list), info->arp_addr_list,
 		       sizeof(u32) * info->arp_addr_cnt);
 		__entry->arp_filter_enabled = info->arp_filter_enabled;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index b5468876287e..d8ef3417bf2b 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1676,7 +1676,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 	if (!chanctx_conf)
 		goto fail_rcu;
 
-	chan = chanctx_conf->channel;
+	chan = chanctx_conf->def.chan;
 
 	/*
 	 * Frame injection is not allowed if beaconing is not allowed
@@ -1779,7 +1779,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 		chanctx_conf = rcu_dereference(ap_sdata->vif.chanctx_conf);
 		if (!chanctx_conf)
 			goto fail_rcu;
-		band = chanctx_conf->channel->band;
+		band = chanctx_conf->def.chan->band;
 		if (sta)
 			break;
 		/* fall through */
@@ -1794,7 +1794,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 			chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 		if (!chanctx_conf)
 			goto fail_rcu;
-		band = chanctx_conf->channel->band;
+		band = chanctx_conf->def.chan->band;
 		break;
 	case NL80211_IFTYPE_WDS:
 		fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS);
@@ -1871,7 +1871,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 		if (!chanctx_conf)
 			goto fail_rcu;
-		band = chanctx_conf->channel->band;
+		band = chanctx_conf->def.chan->band;
 		break;
 #endif
 	case NL80211_IFTYPE_STATION:
@@ -1930,7 +1930,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 		if (!chanctx_conf)
 			goto fail_rcu;
-		band = chanctx_conf->channel->band;
+		band = chanctx_conf->def.chan->band;
 		break;
 	case NL80211_IFTYPE_ADHOC:
 		/* DA SA BSSID */
@@ -1941,7 +1941,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 		if (!chanctx_conf)
 			goto fail_rcu;
-		band = chanctx_conf->channel->band;
+		band = chanctx_conf->def.chan->band;
 		break;
 	default:
 		goto fail_rcu;
@@ -2191,7 +2191,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 			return true;
 		}
 		result = ieee80211_tx(sdata, skb, true,
-				      chanctx_conf->channel->band);
+				      chanctx_conf->def.chan->band);
 	} else {
 		struct sk_buff_head skbs;
 
@@ -2455,7 +2455,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 		*pos++ = WLAN_EID_SSID;
 		*pos++ = 0x0;
 
-		band = chanctx_conf->channel->band;
+		band = chanctx_conf->def.chan->band;
 
 		if (ieee80211_add_srates_ie(sdata, skb, true, band) ||
 		    mesh_add_ds_params_ie(skb, sdata) ||
@@ -2474,7 +2474,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	band = chanctx_conf->channel->band;
+	band = chanctx_conf->def.chan->band;
 
 	info = IEEE80211_SKB_CB(skb);
 
@@ -2754,7 +2754,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw,
 	info = IEEE80211_SKB_CB(skb);
 
 	tx.flags |= IEEE80211_TX_PS_BUFFERED;
-	info->band = chanctx_conf->channel->band;
+	info->band = chanctx_conf->def.chan->band;
 
 	if (invoke_tx_handlers(&tx))
 		skb = NULL;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 2f08a7e09b7e..3b3dd32f121f 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -898,7 +898,7 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 	rcu_read_lock();
 	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 	use_11b = (chanctx_conf &&
-		   chanctx_conf->channel->band == IEEE80211_BAND_2GHZ) &&
+		   chanctx_conf->def.chan->band == IEEE80211_BAND_2GHZ) &&
 		 !(sdata->flags & IEEE80211_SDATA_OPERATING_GMODE);
 	rcu_read_unlock();
 
@@ -991,7 +991,7 @@ void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata,
 	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 
 	if (chanctx_conf &&
-	    chanctx_conf->channel->band == IEEE80211_BAND_2GHZ &&
+	    chanctx_conf->def.chan->band == IEEE80211_BAND_2GHZ &&
 	    have_higher_than_11mbit)
 		sdata->flags |= IEEE80211_SDATA_OPERATING_GMODE;
 	else
@@ -1871,8 +1871,7 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 }
 
 u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
-			       struct ieee80211_channel *channel,
-			       enum nl80211_channel_type channel_type,
+			       const struct cfg80211_chan_def *chandef,
 			       u16 prot_mode)
 {
 	struct ieee80211_ht_operation *ht_oper;
@@ -1880,23 +1879,25 @@ u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
 	*pos++ = WLAN_EID_HT_OPERATION;
 	*pos++ = sizeof(struct ieee80211_ht_operation);
 	ht_oper = (struct ieee80211_ht_operation *)pos;
-	ht_oper->primary_chan =
-			ieee80211_frequency_to_channel(channel->center_freq);
-	switch (channel_type) {
-	case NL80211_CHAN_HT40MINUS:
-		ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_BELOW;
-		break;
-	case NL80211_CHAN_HT40PLUS:
-		ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_ABOVE;
+	ht_oper->primary_chan = ieee80211_frequency_to_channel(
+					chandef->chan->center_freq);
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_160:
+	case NL80211_CHAN_WIDTH_80P80:
+	case NL80211_CHAN_WIDTH_80:
+	case NL80211_CHAN_WIDTH_40:
+		if (chandef->center_freq1 > chandef->chan->center_freq)
+			ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_ABOVE;
+		else
+			ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_BELOW;
 		break;
-	case NL80211_CHAN_HT20:
 	default:
 		ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_NONE;
 		break;
 	}
 	if (ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 &&
-	    channel_type != NL80211_CHAN_NO_HT &&
-	    channel_type != NL80211_CHAN_HT20)
+	    chandef->width != NL80211_CHAN_WIDTH_20_NOHT &&
+	    chandef->width != NL80211_CHAN_WIDTH_20)
 		ht_oper->ht_param |= IEEE80211_HT_PARAM_CHAN_WIDTH_ANY;
 
 	ht_oper->operation_mode = cpu_to_le16(prot_mode);
@@ -1910,13 +1911,17 @@ u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
 	return pos + sizeof(struct ieee80211_ht_operation);
 }
 
-enum nl80211_channel_type
-ieee80211_ht_oper_to_channel_type(struct ieee80211_ht_operation *ht_oper)
+void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan,
+				  struct ieee80211_ht_operation *ht_oper,
+				  struct cfg80211_chan_def *chandef)
 {
 	enum nl80211_channel_type channel_type;
 
-	if (!ht_oper)
-		return NL80211_CHAN_NO_HT;
+	if (!ht_oper) {
+		cfg80211_chandef_create(chandef, control_chan,
+					NL80211_CHAN_NO_HT);
+		return;
+	}
 
 	switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) {
 	case IEEE80211_HT_PARAM_CHA_SEC_NONE:
@@ -1932,7 +1937,7 @@ ieee80211_ht_oper_to_channel_type(struct ieee80211_ht_operation *ht_oper)
 		channel_type = NL80211_CHAN_NO_HT;
 	}
 
-	return channel_type;
+	cfg80211_chandef_create(chandef, control_chan, channel_type);
 }
 
 int ieee80211_add_srates_ie(struct ieee80211_sub_if_data *sdata,
-- 
cgit v1.2.3-55-g7522


From db9c64cf8d9d3fcbc34b09d037f266d1fc9f928c Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Fri, 9 Nov 2012 14:56:41 +0100
Subject: nl80211/cfg80211: add VHT MCS support

Add support for reporting and calculating VHT MCSes.

Note that I'm not completely sure that the bitrate
calculations are correct, nor that they can't be
simplified.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 24 +++++++++-----
 include/uapi/linux/nl80211.h | 12 ++++++-
 net/wireless/nl80211.c       | 58 +++++++++++++++++++++++++---------
 net/wireless/util.c          | 74 +++++++++++++++++++++++++++++++++++++++++++-
 4 files changed, 144 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 977da58fb7ea..e78db2cf3d1b 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -662,16 +662,24 @@ enum station_info_flags {
  * Used by the driver to indicate the specific rate transmission
  * type for 802.11n transmissions.
  *
- * @RATE_INFO_FLAGS_MCS: @tx_bitrate_mcs filled
- * @RATE_INFO_FLAGS_40_MHZ_WIDTH: 40 Mhz width transmission
+ * @RATE_INFO_FLAGS_MCS: mcs field filled with HT MCS
+ * @RATE_INFO_FLAGS_VHT_MCS: mcs field filled with VHT MCS
+ * @RATE_INFO_FLAGS_40_MHZ_WIDTH: 40 MHz width transmission
+ * @RATE_INFO_FLAGS_80_MHZ_WIDTH: 80 MHz width transmission
+ * @RATE_INFO_FLAGS_80P80_MHZ_WIDTH: 80+80 MHz width transmission
+ * @RATE_INFO_FLAGS_160_MHZ_WIDTH: 160 MHz width transmission
  * @RATE_INFO_FLAGS_SHORT_GI: 400ns guard interval
- * @RATE_INFO_FLAGS_60G: 60gHz MCS
+ * @RATE_INFO_FLAGS_60G: 60GHz MCS
  */
 enum rate_info_flags {
-	RATE_INFO_FLAGS_MCS		= 1<<0,
-	RATE_INFO_FLAGS_40_MHZ_WIDTH	= 1<<1,
-	RATE_INFO_FLAGS_SHORT_GI	= 1<<2,
-	RATE_INFO_FLAGS_60G		= 1<<3,
+	RATE_INFO_FLAGS_MCS			= BIT(0),
+	RATE_INFO_FLAGS_VHT_MCS			= BIT(1),
+	RATE_INFO_FLAGS_40_MHZ_WIDTH		= BIT(2),
+	RATE_INFO_FLAGS_80_MHZ_WIDTH		= BIT(3),
+	RATE_INFO_FLAGS_80P80_MHZ_WIDTH		= BIT(4),
+	RATE_INFO_FLAGS_160_MHZ_WIDTH		= BIT(5),
+	RATE_INFO_FLAGS_SHORT_GI		= BIT(6),
+	RATE_INFO_FLAGS_60G			= BIT(7),
 };
 
 /**
@@ -682,11 +690,13 @@ enum rate_info_flags {
  * @flags: bitflag of flags from &enum rate_info_flags
  * @mcs: mcs index if struct describes a 802.11n bitrate
  * @legacy: bitrate in 100kbit/s for 802.11abg
+ * @nss: number of streams (VHT only)
  */
 struct rate_info {
 	u8 flags;
 	u8 mcs;
 	u16 legacy;
+	u8 nss;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 84f9c7d84c69..33a417481ad8 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1734,10 +1734,15 @@ struct nl80211_sta_flag_update {
  * @__NL80211_RATE_INFO_INVALID: attribute number 0 is reserved
  * @NL80211_RATE_INFO_BITRATE: total bitrate (u16, 100kbit/s)
  * @NL80211_RATE_INFO_MCS: mcs index for 802.11n (u8)
- * @NL80211_RATE_INFO_40_MHZ_WIDTH: 40 Mhz dualchannel bitrate
+ * @NL80211_RATE_INFO_40_MHZ_WIDTH: 40 MHz dualchannel bitrate
  * @NL80211_RATE_INFO_SHORT_GI: 400ns guard interval
  * @NL80211_RATE_INFO_BITRATE32: total bitrate (u32, 100kbit/s)
  * @NL80211_RATE_INFO_MAX: highest rate_info number currently defined
+ * @NL80211_RATE_INFO_VHT_MCS: MCS index for VHT (u8)
+ * @NL80211_RATE_INFO_VHT_NSS: number of streams in VHT (u8)
+ * @NL80211_RATE_INFO_80_MHZ_WIDTH: 80 MHz VHT rate
+ * @NL80211_RATE_INFO_80P80_MHZ_WIDTH: 80+80 MHz VHT rate
+ * @NL80211_RATE_INFO_160_MHZ_WIDTH: 160 MHz VHT rate
  * @__NL80211_RATE_INFO_AFTER_LAST: internal use
  */
 enum nl80211_rate_info {
@@ -1747,6 +1752,11 @@ enum nl80211_rate_info {
 	NL80211_RATE_INFO_40_MHZ_WIDTH,
 	NL80211_RATE_INFO_SHORT_GI,
 	NL80211_RATE_INFO_BITRATE32,
+	NL80211_RATE_INFO_VHT_MCS,
+	NL80211_RATE_INFO_VHT_NSS,
+	NL80211_RATE_INFO_80_MHZ_WIDTH,
+	NL80211_RATE_INFO_80P80_MHZ_WIDTH,
+	NL80211_RATE_INFO_160_MHZ_WIDTH,
 
 	/* keep last */
 	__NL80211_RATE_INFO_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 15158a3d64a3..d038fa45ecd1 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2890,29 +2890,52 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 
 	rate = nla_nest_start(msg, attr);
 	if (!rate)
-		goto nla_put_failure;
+		return false;
 
 	/* cfg80211_calculate_bitrate will return 0 for mcs >= 32 */
 	bitrate = cfg80211_calculate_bitrate(info);
 	/* report 16-bit bitrate only if we can */
 	bitrate_compat = bitrate < (1UL << 16) ? bitrate : 0;
-	if ((bitrate > 0 &&
-	     nla_put_u32(msg, NL80211_RATE_INFO_BITRATE32, bitrate)) ||
-	    (bitrate_compat > 0 &&
-	     nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate_compat)) ||
-	    ((info->flags & RATE_INFO_FLAGS_MCS) &&
-	     nla_put_u8(msg, NL80211_RATE_INFO_MCS, info->mcs)) ||
-	    ((info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH) &&
-	     nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH)) ||
-	    ((info->flags & RATE_INFO_FLAGS_SHORT_GI) &&
-	     nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI)))
-		goto nla_put_failure;
+	if (bitrate > 0 &&
+	    nla_put_u32(msg, NL80211_RATE_INFO_BITRATE32, bitrate))
+		return false;
+	if (bitrate_compat > 0 &&
+	    nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate_compat))
+		return false;
+
+	if (info->flags & RATE_INFO_FLAGS_MCS) {
+		if (nla_put_u8(msg, NL80211_RATE_INFO_MCS, info->mcs))
+			return false;
+		if (info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH &&
+		    nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH))
+			return false;
+		if (info->flags & RATE_INFO_FLAGS_SHORT_GI &&
+		    nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))
+			return false;
+	} else if (info->flags & RATE_INFO_FLAGS_VHT_MCS) {
+		if (nla_put_u8(msg, NL80211_RATE_INFO_VHT_MCS, info->mcs))
+			return false;
+		if (nla_put_u8(msg, NL80211_RATE_INFO_VHT_NSS, info->nss))
+			return false;
+		if (info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH &&
+		    nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH))
+			return false;
+		if (info->flags & RATE_INFO_FLAGS_80_MHZ_WIDTH &&
+		    nla_put_flag(msg, NL80211_RATE_INFO_80_MHZ_WIDTH))
+			return false;
+		if (info->flags & RATE_INFO_FLAGS_80P80_MHZ_WIDTH &&
+		    nla_put_flag(msg, NL80211_RATE_INFO_80P80_MHZ_WIDTH))
+			return false;
+		if (info->flags & RATE_INFO_FLAGS_160_MHZ_WIDTH &&
+		    nla_put_flag(msg, NL80211_RATE_INFO_160_MHZ_WIDTH))
+			return false;
+		if (info->flags & RATE_INFO_FLAGS_SHORT_GI &&
+		    nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))
+			return false;
+	}
 
 	nla_nest_end(msg, rate);
 	return true;
-
-nla_put_failure:
-	return false;
 }
 
 static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq,
@@ -5475,6 +5498,11 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &ibss.chandef))
 		return -EINVAL;
 
+	if (ibss.chandef.width > NL80211_CHAN_WIDTH_40)
+		return -EINVAL;
+	if (ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT &&
+	    !(rdev->wiphy.features & NL80211_FEATURE_HT_IBSS))
+
 	ibss.channel_fixed = !!info->attrs[NL80211_ATTR_FREQ_FIXED];
 	ibss.privacy = !!info->attrs[NL80211_ATTR_PRIVACY];
 
diff --git a/net/wireless/util.c b/net/wireless/util.c
index db61fe8a6b6d..3cce6e486219 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -944,14 +944,86 @@ static u32 cfg80211_calculate_bitrate_60g(struct rate_info *rate)
 	return __mcs2bitrate[rate->mcs];
 }
 
+static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate)
+{
+	static const u32 base[4][10] = {
+		{   6500000,
+		   13000000,
+		   19500000,
+		   26000000,
+		   39000000,
+		   52000000,
+		   58500000,
+		   65000000,
+		   78000000,
+		   0,
+		},
+		{  13500000,
+		   27000000,
+		   40500000,
+		   54000000,
+		   81000000,
+		  108000000,
+		  121500000,
+		  135000000,
+		  162000000,
+		  180000000,
+		},
+		{  29300000,
+		   58500000,
+		   87800000,
+		  117000000,
+		  175500000,
+		  234000000,
+		  263300000,
+		  292500000,
+		  351000000,
+		  390000000,
+		},
+		{  58500000,
+		  117000000,
+		  175500000,
+		  234000000,
+		  351000000,
+		  468000000,
+		  526500000,
+		  585000000,
+		  702000000,
+		  780000000,
+		},
+	};
+	u32 bitrate;
+	int idx;
+
+	if (WARN_ON_ONCE(rate->mcs > 9))
+		return 0;
+
+	idx = rate->flags & (RATE_INFO_FLAGS_160_MHZ_WIDTH |
+			     RATE_INFO_FLAGS_80P80_MHZ_WIDTH) ? 3 :
+		  rate->flags & RATE_INFO_FLAGS_80_MHZ_WIDTH ? 2 :
+		  rate->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH ? 1 : 0;
+
+	bitrate = base[idx][rate->mcs];
+	bitrate *= rate->nss;
+
+	if (rate->flags & RATE_INFO_FLAGS_SHORT_GI)
+		bitrate = (bitrate / 9) * 10;
+
+	/* do NOT round down here */
+	return (bitrate + 50000) / 100000;
+}
+
 u32 cfg80211_calculate_bitrate(struct rate_info *rate)
 {
 	int modulation, streams, bitrate;
 
-	if (!(rate->flags & RATE_INFO_FLAGS_MCS))
+	if (!(rate->flags & RATE_INFO_FLAGS_MCS) &&
+	    !(rate->flags & RATE_INFO_FLAGS_VHT_MCS))
 		return rate->legacy;
 	if (rate->flags & RATE_INFO_FLAGS_60G)
 		return cfg80211_calculate_bitrate_60g(rate);
+	if (rate->flags & RATE_INFO_FLAGS_VHT_MCS)
+		return cfg80211_calculate_bitrate_vht(rate);
 
 	/* the formula below does only work for MCS values smaller than 32 */
 	if (WARN_ON_ONCE(rate->mcs >= 32))
-- 
cgit v1.2.3-55-g7522


From 5614618ec498320e3b686fea246e50b833865c34 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Fri, 9 Nov 2012 15:07:02 +0100
Subject: mac80211: support drivers reporting VHT RX

Add support to mac80211 for having drivers report
received VHT MCS information.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h  | 12 +++++++++++-
 net/mac80211/cfg.c      | 26 +++++++++++++++++++++++---
 net/mac80211/rx.c       | 20 +++++++++++++++-----
 net/mac80211/sta_info.h |  4 +++-
 net/mac80211/util.c     | 14 ++++++++++++++
 5 files changed, 66 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 6af51328dcd1..598ea215fc3b 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -717,7 +717,11 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	(including FCS) was received.
  * @RX_FLAG_SHORTPRE: Short preamble was used for this frame
  * @RX_FLAG_HT: HT MCS was used and rate_idx is MCS index
+ * @RX_FLAG_VHT: VHT MCS was used and rate_index is MCS index
  * @RX_FLAG_40MHZ: HT40 (40 MHz) was used
+ * @RX_FLAG_80MHZ: 80 MHz was used
+ * @RX_FLAG_80P80MHZ: 80+80 MHz was used
+ * @RX_FLAG_160MHZ: 160 MHz was used
  * @RX_FLAG_SHORT_GI: Short guard interval was used
  * @RX_FLAG_NO_SIGNAL_VAL: The signal strength value is not present.
  *	Valid only for data frames (mainly A-MPDU)
@@ -760,6 +764,10 @@ enum mac80211_rx_flags {
 	RX_FLAG_AMPDU_DELIM_CRC_ERROR	= BIT(19),
 	RX_FLAG_AMPDU_DELIM_CRC_KNOWN	= BIT(20),
 	RX_FLAG_MACTIME_END		= BIT(21),
+	RX_FLAG_VHT			= BIT(22),
+	RX_FLAG_80MHZ			= BIT(23),
+	RX_FLAG_80P80MHZ		= BIT(24),
+	RX_FLAG_160MHZ			= BIT(25),
 };
 
 /**
@@ -780,7 +788,8 @@ enum mac80211_rx_flags {
  *	@IEEE80211_HW_SIGNAL_*
  * @antenna: antenna used
  * @rate_idx: index of data rate into band's supported rates or MCS index if
- *	HT rates are use (RX_FLAG_HT)
+ *	HT or VHT is used (%RX_FLAG_HT/%RX_FLAG_VHT)
+ * @vht_nss: number of streams (VHT only)
  * @flag: %RX_FLAG_*
  * @rx_flags: internal RX flags for mac80211
  * @ampdu_reference: A-MPDU reference number, must be a different value for
@@ -803,6 +812,7 @@ struct ieee80211_rx_status {
 	u16 vendor_radiotap_len;
 	u16 freq;
 	u8 rate_idx;
+	u8 vht_nss;
 	u8 rx_flags;
 	u8 band;
 	u8 antenna;
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index b9702d16d608..0b9de4fa54a6 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -374,7 +374,8 @@ static void rate_idx_to_bitrate(struct rate_info *rate, struct sta_info *sta, in
 {
 	enum ieee80211_band band = ieee80211_get_sdata_band(sta->sdata);
 
-	if (!(rate->flags & RATE_INFO_FLAGS_MCS)) {
+	if (!(rate->flags & RATE_INFO_FLAGS_MCS) &&
+	    !(rate->flags & RATE_INFO_FLAGS_VHT_MCS)) {
 		struct ieee80211_supported_band *sband;
 		sband = sta->local->hw.wiphy->bands[band];
 		rate->legacy = sband->bitrates[idx].bitrate;
@@ -444,13 +445,32 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 	sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate);
 
 	sinfo->rxrate.flags = 0;
-	if (sta->last_rx_rate_flag & RX_FLAG_HT)
+	if (sta->last_rx_rate_flag & RX_FLAG_HT) {
 		sinfo->rxrate.flags |= RATE_INFO_FLAGS_MCS;
+		sinfo->rxrate.mcs = sta->last_rx_rate_idx;
+	} else if (sta->last_rx_rate_flag & RX_FLAG_VHT) {
+		sinfo->rxrate.flags |= RATE_INFO_FLAGS_VHT_MCS;
+		sinfo->rxrate.nss = sta->last_rx_rate_vht_nss;
+		sinfo->rxrate.mcs = sta->last_rx_rate_idx;
+	} else {
+		struct ieee80211_supported_band *sband;
+
+		sband = sta->local->hw.wiphy->bands[
+				ieee80211_get_sdata_band(sta->sdata)];
+		sinfo->rxrate.legacy =
+			sband->bitrates[sta->last_rx_rate_idx].bitrate;
+	}
+
 	if (sta->last_rx_rate_flag & RX_FLAG_40MHZ)
 		sinfo->rxrate.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
 	if (sta->last_rx_rate_flag & RX_FLAG_SHORT_GI)
 		sinfo->rxrate.flags |= RATE_INFO_FLAGS_SHORT_GI;
-	rate_idx_to_bitrate(&sinfo->rxrate, sta, sta->last_rx_rate_idx);
+	if (sta->last_rx_rate_flag & RX_FLAG_80MHZ)
+		sinfo->rxrate.flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
+	if (sta->last_rx_rate_flag & RX_FLAG_80P80MHZ)
+		sinfo->rxrate.flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH;
+	if (sta->last_rx_rate_flag & RX_FLAG_160MHZ)
+		sinfo->rxrate.flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
 
 	if (ieee80211_vif_is_mesh(&sdata->vif)) {
 #ifdef CONFIG_MAC80211_MESH
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index b2ae2baefc9a..825f33cf7bbc 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -193,7 +193,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	pos++;
 
 	/* IEEE80211_RADIOTAP_RATE */
-	if (!rate || status->flag & RX_FLAG_HT) {
+	if (!rate || status->flag & (RX_FLAG_HT | RX_FLAG_VHT)) {
 		/*
 		 * Without rate information don't add it. If we have,
 		 * MCS information is a separate field in radiotap,
@@ -213,7 +213,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	if (status->band == IEEE80211_BAND_5GHZ)
 		put_unaligned_le16(IEEE80211_CHAN_OFDM | IEEE80211_CHAN_5GHZ,
 				   pos);
-	else if (status->flag & RX_FLAG_HT)
+	else if (status->flag & (RX_FLAG_HT | RX_FLAG_VHT))
 		put_unaligned_le16(IEEE80211_CHAN_DYN | IEEE80211_CHAN_2GHZ,
 				   pos);
 	else if (rate && rate->flags & IEEE80211_RATE_ERP_G)
@@ -1356,6 +1356,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 			if (ieee80211_is_data(hdr->frame_control)) {
 				sta->last_rx_rate_idx = status->rate_idx;
 				sta->last_rx_rate_flag = status->flag;
+				sta->last_rx_rate_vht_nss = status->vht_nss;
 			}
 		}
 	} else if (!is_multicast_ether_addr(hdr->addr1)) {
@@ -1367,6 +1368,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 		if (ieee80211_is_data(hdr->frame_control)) {
 			sta->last_rx_rate_idx = status->rate_idx;
 			sta->last_rx_rate_flag = status->flag;
+			sta->last_rx_rate_vht_nss = status->vht_nss;
 		}
 	}
 
@@ -2710,7 +2712,8 @@ static void ieee80211_rx_handlers_result(struct ieee80211_rx_data *rx,
 		status = IEEE80211_SKB_RXCB((rx->skb));
 
 		sband = rx->local->hw.wiphy->bands[status->band];
-		if (!(status->flag & RX_FLAG_HT))
+		if (!(status->flag & RX_FLAG_HT) &&
+		    !(status->flag & RX_FLAG_VHT))
 			rate = &sband->bitrates[status->rate_idx];
 
 		ieee80211_rx_cooked_monitor(rx, rate);
@@ -2877,8 +2880,8 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx,
 			status->rx_flags &= ~IEEE80211_RX_RA_MATCH;
 		} else if (!rx->sta) {
 			int rate_idx;
-			if (status->flag & RX_FLAG_HT)
-				rate_idx = 0; /* TODO: HT rates */
+			if (status->flag & (RX_FLAG_HT | RX_FLAG_VHT))
+				rate_idx = 0; /* TODO: HT/VHT rates */
 			else
 				rate_idx = status->rate_idx;
 			ieee80211_ibss_rx_no_sta(sdata, bssid, hdr->addr2,
@@ -3154,6 +3157,13 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb)
 				 status->rate_idx,
 				 status->rate_idx))
 				goto drop;
+		} else if (status->flag & RX_FLAG_VHT) {
+			if (WARN_ONCE(status->rate_idx > 9 ||
+				      !status->vht_nss ||
+				      status->vht_nss > 8,
+				      "Rate marked as a VHT rate but data is invalid: MCS: %d, NSS: %d\n",
+				      status->rate_idx, status->vht_nss))
+				goto drop;
 		} else {
 			if (WARN_ON(status->rate_idx >= sband->n_bitrates))
 				goto drop;
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 2b2d5aac2bb1..6835cea4e402 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -227,6 +227,7 @@ struct sta_ampdu_mlme {
  *	"the" transmit rate
  * @last_rx_rate_idx: rx status rate index of the last data packet
  * @last_rx_rate_flag: rx status flag of the last data packet
+ * @last_rx_rate_vht_nss: rx status nss of last data packet
  * @lock: used for locking all fields that require locking, see comments
  *	in the header file.
  * @drv_unblock_wk: used for driver PS unblocking
@@ -343,7 +344,8 @@ struct sta_info {
 	unsigned long tx_fragments;
 	struct ieee80211_tx_rate last_tx_rate;
 	int last_rx_rate_idx;
-	int last_rx_rate_flag;
+	u32 last_rx_rate_flag;
+	u8 last_rx_rate_vht_nss;
 	u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1];
 
 	/*
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 3b3dd32f121f..dc7f6b264593 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2069,6 +2069,20 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 			ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
 		if (status->flag & RX_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
+	} else if (status->flag & RX_FLAG_VHT) {
+		ri.flags |= RATE_INFO_FLAGS_VHT_MCS;
+		ri.mcs = status->rate_idx;
+		ri.nss = status->vht_nss;
+		if (status->flag & RX_FLAG_40MHZ)
+			ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
+		if (status->flag & RX_FLAG_80MHZ)
+			ri.flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
+		if (status->flag & RX_FLAG_80P80MHZ)
+			ri.flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH;
+		if (status->flag & RX_FLAG_160MHZ)
+			ri.flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
+		if (status->flag & RX_FLAG_SHORT_GI)
+			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
 	} else {
 		struct ieee80211_supported_band *sband;
 
-- 
cgit v1.2.3-55-g7522


From 8bc83c24638b72421e783b96b5a05c1f4109a51d Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Fri, 9 Nov 2012 18:38:32 +0100
Subject: mac80211: support VHT rates in TX info

To achieve this, limit the number of retries to
31 (instead of 255) and use the three bits that
are then free for VHT flags.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 36 +++++++++++++++++++++++++++++++++---
 net/mac80211/cfg.c     | 41 ++++++++++++++++++++++++-----------------
 2 files changed, 57 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 598ea215fc3b..db7680acd0da 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -499,9 +499,14 @@ enum mac80211_tx_control_flags {
  *	This is set if the current BSS requires ERP protection.
  * @IEEE80211_TX_RC_USE_SHORT_PREAMBLE: Use short preamble.
  * @IEEE80211_TX_RC_MCS: HT rate.
+ * @IEEE80211_TX_RC_VHT_MCS: VHT MCS rate, in this case the idx field is split
+ *	into a higher 4 bits (Nss) and lower 4 bits (MCS number)
  * @IEEE80211_TX_RC_GREEN_FIELD: Indicates whether this rate should be used in
  *	Greenfield mode.
  * @IEEE80211_TX_RC_40_MHZ_WIDTH: Indicates if the Channel Width should be 40 MHz.
+ * @IEEE80211_TX_RC_80_MHZ_WIDTH: Indicates 80 MHz transmission
+ * @IEEE80211_TX_RC_160_MHZ_WIDTH: Indicates 160 MHz transmission
+ *	(80+80 isn't supported yet)
  * @IEEE80211_TX_RC_DUP_DATA: The frame should be transmitted on both of the
  *	adjacent 20 MHz channels, if the current channel type is
  *	NL80211_CHAN_HT40MINUS or NL80211_CHAN_HT40PLUS.
@@ -512,12 +517,15 @@ enum mac80211_rate_control_flags {
 	IEEE80211_TX_RC_USE_CTS_PROTECT		= BIT(1),
 	IEEE80211_TX_RC_USE_SHORT_PREAMBLE	= BIT(2),
 
-	/* rate index is an MCS rate number instead of an index */
+	/* rate index is an HT/VHT MCS instead of an index */
 	IEEE80211_TX_RC_MCS			= BIT(3),
 	IEEE80211_TX_RC_GREEN_FIELD		= BIT(4),
 	IEEE80211_TX_RC_40_MHZ_WIDTH		= BIT(5),
 	IEEE80211_TX_RC_DUP_DATA		= BIT(6),
 	IEEE80211_TX_RC_SHORT_GI		= BIT(7),
+	IEEE80211_TX_RC_VHT_MCS			= BIT(8),
+	IEEE80211_TX_RC_80_MHZ_WIDTH		= BIT(9),
+	IEEE80211_TX_RC_160_MHZ_WIDTH		= BIT(10),
 };
 
 
@@ -560,10 +568,32 @@ enum mac80211_rate_control_flags {
  */
 struct ieee80211_tx_rate {
 	s8 idx;
-	u8 count;
-	u8 flags;
+	u16 count:5,
+	    flags:11;
 } __packed;
 
+#define IEEE80211_MAX_TX_RETRY		31
+
+static inline void ieee80211_rate_set_vht(struct ieee80211_tx_rate *rate,
+					  u8 mcs, u8 nss)
+{
+	WARN_ON(mcs & ~0xF);
+	WARN_ON(nss & ~0x7);
+	rate->idx = (nss << 4) | mcs;
+}
+
+static inline u8
+ieee80211_rate_get_vht_mcs(const struct ieee80211_tx_rate *rate)
+{
+	return rate->idx & 0xF;
+}
+
+static inline u8
+ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate)
+{
+	return rate->idx >> 4;
+}
+
 /**
  * struct ieee80211_tx_info - skb transmit information
  *
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 0b9de4fa54a6..5d30e5f57ff0 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -370,31 +370,32 @@ static int ieee80211_config_default_mgmt_key(struct wiphy *wiphy,
 	return 0;
 }
 
-static void rate_idx_to_bitrate(struct rate_info *rate, struct sta_info *sta, int idx)
-{
-	enum ieee80211_band band = ieee80211_get_sdata_band(sta->sdata);
-
-	if (!(rate->flags & RATE_INFO_FLAGS_MCS) &&
-	    !(rate->flags & RATE_INFO_FLAGS_VHT_MCS)) {
-		struct ieee80211_supported_band *sband;
-		sband = sta->local->hw.wiphy->bands[band];
-		rate->legacy = sband->bitrates[idx].bitrate;
-	} else
-		rate->mcs = idx;
-}
-
 void sta_set_rate_info_tx(struct sta_info *sta,
 			  const struct ieee80211_tx_rate *rate,
 			  struct rate_info *rinfo)
 {
 	rinfo->flags = 0;
-	if (rate->flags & IEEE80211_TX_RC_MCS)
+	if (rate->flags & IEEE80211_TX_RC_MCS) {
 		rinfo->flags |= RATE_INFO_FLAGS_MCS;
+		rinfo->mcs = rate->idx;
+	} else if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+		rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS;
+		rinfo->mcs = ieee80211_rate_get_vht_mcs(rate);
+		rinfo->nss = ieee80211_rate_get_vht_nss(rate);
+	} else {
+		struct ieee80211_supported_band *sband;
+		sband = sta->local->hw.wiphy->bands[
+				ieee80211_get_sdata_band(sta->sdata)];
+		rinfo->legacy = sband->bitrates[rate->idx].bitrate;
+	}
 	if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
 		rinfo->flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
+	if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+		rinfo->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
+	if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH)
+		rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
 	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
 		rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
-	rate_idx_to_bitrate(rinfo, sta, rate->idx);
 }
 
 static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
@@ -2003,10 +2004,16 @@ static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed)
 			return err;
 	}
 
-	if (changed & WIPHY_PARAM_RETRY_SHORT)
+	if (changed & WIPHY_PARAM_RETRY_SHORT) {
+		if (wiphy->retry_short > IEEE80211_MAX_TX_RETRY)
+			return -EINVAL;
 		local->hw.conf.short_frame_max_tx_count = wiphy->retry_short;
-	if (changed & WIPHY_PARAM_RETRY_LONG)
+	}
+	if (changed & WIPHY_PARAM_RETRY_LONG) {
+		if (wiphy->retry_long > IEEE80211_MAX_TX_RETRY)
+			return -EINVAL;
 		local->hw.conf.long_frame_max_tx_count = wiphy->retry_long;
+	}
 	if (changed &
 	    (WIPHY_PARAM_RETRY_SHORT | WIPHY_PARAM_RETRY_LONG))
 		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_RETRY_LIMITS);
-- 
cgit v1.2.3-55-g7522


From 7173a1fa53dff94f771a66b93623500424376015 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Mon, 12 Nov 2012 11:44:18 +0100
Subject: wireless: add definitions for VHT MCS support

Add definitions for the VHT MCS support values that
are used to indicate, for each number of streams
(1 through 8) which MCSes are supported.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 65c6b0f3ef60..f9c5a787d350 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1163,11 +1163,13 @@ struct ieee80211_ht_operation {
  *	STA can receive. Rate expressed in units of 1 Mbps.
  *	If this field is 0 this value should not be used to
  *	consider the highest RX data rate supported.
+ *	The top 3 bits of this field are reserved.
  * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams
  * @tx_highest: Indicates highest long GI VHT PPDU data rate
  *	STA can transmit. Rate expressed in units of 1 Mbps.
  *	If this field is 0 this value should not be used to
  *	consider the highest TX data rate supported.
+ *	The top 3 bits of this field are reserved.
  */
 struct ieee80211_vht_mcs_info {
 	__le16 rx_mcs_map;
@@ -1176,6 +1178,27 @@ struct ieee80211_vht_mcs_info {
 	__le16 tx_highest;
 } __packed;
 
+/**
+ * enum ieee80211_vht_mcs_support - VHT MCS support definitions
+ * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the
+ *	number of streams
+ * @IEEE80211_VHT_MCS_SUPPORT_0_8: MCSes 0-8 are supported
+ * @IEEE80211_VHT_MCS_SUPPORT_0_9: MCSes 0-9 are supported
+ * @IEEE80211_VHT_MCS_NOT_SUPPORTED: This number of streams isn't supported
+ *
+ * These definitions are used in each 2-bit subfield of the @rx_mcs_map
+ * and @tx_mcs_map fields of &struct ieee80211_vht_mcs_info, which are
+ * both split into 8 subfields by number of streams. These values indicate
+ * which MCSes are supported for the number of streams the value appears
+ * for.
+ */
+enum ieee80211_vht_mcs_support {
+	IEEE80211_VHT_MCS_SUPPORT_0_7	= 0,
+	IEEE80211_VHT_MCS_SUPPORT_0_8	= 1,
+	IEEE80211_VHT_MCS_SUPPORT_0_9	= 2,
+	IEEE80211_VHT_MCS_NOT_SUPPORTED	= 3,
+};
+
 /**
  * struct ieee80211_vht_cap - VHT capabilities
  *
-- 
cgit v1.2.3-55-g7522


From 7cc17a31ff5ca3d8e1719af88907beec7b1fd24e Mon Sep 17 00:00:00 2001
From: Takashi Iwai
Date: Mon, 26 Nov 2012 16:18:59 +0100
Subject: ALSA: Extend chmap definitions for UAC2

USB audio class 2 has more channel map positions than we currently
have.  Let's add missing definitions.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/uapi/sound/asound.h | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 515b8fcd1ca9..1774a5c3ef10 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -492,7 +492,17 @@ enum {
 	SNDRV_CHMAP_TRL,	/* top rear left */
 	SNDRV_CHMAP_TRR,	/* top rear right */
 	SNDRV_CHMAP_TRC,	/* top rear center */
-	SNDRV_CHMAP_LAST = SNDRV_CHMAP_TRC,
+	/* new definitions for UAC2 */
+	SNDRV_CHMAP_TFLC,	/* top front left center */
+	SNDRV_CHMAP_TFRC,	/* top front right center */
+	SNDRV_CHMAP_TSL,	/* top side left */
+	SNDRV_CHMAP_TSR,	/* top side right */
+	SNDRV_CHMAP_LLFE,	/* left LFE */
+	SNDRV_CHMAP_RLFE,	/* right LFE */
+	SNDRV_CHMAP_BC,		/* bottom center */
+	SNDRV_CHMAP_BLC,	/* bottom left center */
+	SNDRV_CHMAP_BRC,	/* bottom right center */
+	SNDRV_CHMAP_LAST = SNDRV_CHMAP_BRC,
 };
 
 #define SNDRV_CHMAP_POSITION_MASK	0xffff
-- 
cgit v1.2.3-55-g7522


From 08ff32352d6ff7083533dc1c25618d42f92ec28e Mon Sep 17 00:00:00 2001
From: Or Gerlitz
Date: Sun, 21 Oct 2012 14:59:24 +0000
Subject: mlx4: 64-byte CQE/EQE support

ConnectX-3 devices can use either 64- or 32-byte completion queue
entries (CQEs) and event queue entries (EQEs).  Using 64-byte
EQEs/CQEs performs better because each entry is aligned to a complete
cacheline.  This patch queries the HCA's capabilities, and if it
supports 64-byte CQEs and EQES the driver will configure the HW to
work in 64-byte mode.

The 32-byte vs 64-byte mode is global per HCA and not per CQ or EQ.

Since this mode is global, userspace (libmlx4) must be updated to work
with the configured CQE size, and guests using SR-IOV virtual
functions need to know both EQE and CQE size.

In case one of the 64-byte CQE/EQE capabilities is activated, the
patch makes sure that older guest drivers that use the QUERY_DEV_FUNC
command (e.g as done in mlx4_core of Linux 3.3..3.6) will notice that
they need an update to be able to work with the PPF. This is done by
changing the returned pf_context_behaviour not to be zero any more. In
case none of these capabilities is activated that value remains zero
and older guest drivers can run OK.

The SRIOV related flow is as follows

1. the PPF does the detection of the new capabilities using
   QUERY_DEV_CAP command.

2. the PPF activates the new capabilities using INIT_HCA.

3. the VF detects if the PPF activated the capabilities using
   QUERY_HCA, and if this is the case activates them for itself too.

Note that the VF detects that it must be aware to the new PF behaviour
using QUERY_FUNC_CAP.  Steps 1 and 2 apply also for native mode.

User space notification is done through a new field introduced in
struct mlx4_ib_ucontext which holds device capabilities for which user
space must take action. This changes the binary interface so the ABI
towards libmlx4 exposed through uverbs is bumped from 3 to 4 but only
when **needed** i.e. only when the driver does use 64-byte CQEs or
future device capabilities which must be in sync by user space. This
practice allows to work with unmodified libmlx4 on older devices (e.g
A0, B0) which don't support 64-byte CQEs.

In order to keep existing systems functional when they update to a
newer kernel that contains these changes in VF and userspace ABI, a
module parameter enable_64b_cqe_eqe must be set to enable 64-byte
mode; the default is currently false.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx4/cq.c                | 34 +++++++++++++++++------
 drivers/infiniband/hw/mlx4/main.c              | 27 ++++++++++++++----
 drivers/infiniband/hw/mlx4/mlx4_ib.h           |  1 +
 drivers/infiniband/hw/mlx4/user.h              | 12 +++++++-
 drivers/net/ethernet/mellanox/mlx4/cmd.c       |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_cq.c     |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |  1 +
 drivers/net/ethernet/mellanox/mlx4/en_rx.c     |  5 ++--
 drivers/net/ethernet/mellanox/mlx4/en_tx.c     |  5 ++--
 drivers/net/ethernet/mellanox/mlx4/eq.c        | 26 ++++++++++++------
 drivers/net/ethernet/mellanox/mlx4/fw.c        | 30 +++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/fw.h        |  1 +
 drivers/net/ethernet/mellanox/mlx4/main.c      | 38 +++++++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  1 +
 include/linux/mlx4/device.h                    | 21 ++++++++++++++
 15 files changed, 175 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index c9eb6a6815ce..ae67df35dd4d 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -66,7 +66,7 @@ static void mlx4_ib_cq_event(struct mlx4_cq *cq, enum mlx4_event type)
 
 static void *get_cqe_from_buf(struct mlx4_ib_cq_buf *buf, int n)
 {
-	return mlx4_buf_offset(&buf->buf, n * sizeof (struct mlx4_cqe));
+	return mlx4_buf_offset(&buf->buf, n * buf->entry_size);
 }
 
 static void *get_cqe(struct mlx4_ib_cq *cq, int n)
@@ -77,8 +77,9 @@ static void *get_cqe(struct mlx4_ib_cq *cq, int n)
 static void *get_sw_cqe(struct mlx4_ib_cq *cq, int n)
 {
 	struct mlx4_cqe *cqe = get_cqe(cq, n & cq->ibcq.cqe);
+	struct mlx4_cqe *tcqe = ((cq->buf.entry_size == 64) ? (cqe + 1) : cqe);
 
-	return (!!(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK) ^
+	return (!!(tcqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK) ^
 		!!(n & (cq->ibcq.cqe + 1))) ? NULL : cqe;
 }
 
@@ -99,12 +100,13 @@ static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *
 {
 	int err;
 
-	err = mlx4_buf_alloc(dev->dev, nent * sizeof(struct mlx4_cqe),
+	err = mlx4_buf_alloc(dev->dev, nent * dev->dev->caps.cqe_size,
 			     PAGE_SIZE * 2, &buf->buf);
 
 	if (err)
 		goto out;
 
+	buf->entry_size = dev->dev->caps.cqe_size;
 	err = mlx4_mtt_init(dev->dev, buf->buf.npages, buf->buf.page_shift,
 				    &buf->mtt);
 	if (err)
@@ -120,8 +122,7 @@ err_mtt:
 	mlx4_mtt_cleanup(dev->dev, &buf->mtt);
 
 err_buf:
-	mlx4_buf_free(dev->dev, nent * sizeof(struct mlx4_cqe),
-			      &buf->buf);
+	mlx4_buf_free(dev->dev, nent * buf->entry_size, &buf->buf);
 
 out:
 	return err;
@@ -129,7 +130,7 @@ out:
 
 static void mlx4_ib_free_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *buf, int cqe)
 {
-	mlx4_buf_free(dev->dev, (cqe + 1) * sizeof(struct mlx4_cqe), &buf->buf);
+	mlx4_buf_free(dev->dev, (cqe + 1) * buf->entry_size, &buf->buf);
 }
 
 static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_ucontext *context,
@@ -137,8 +138,9 @@ static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_ucontext *cont
 			       u64 buf_addr, int cqe)
 {
 	int err;
+	int cqe_size = dev->dev->caps.cqe_size;
 
-	*umem = ib_umem_get(context, buf_addr, cqe * sizeof (struct mlx4_cqe),
+	*umem = ib_umem_get(context, buf_addr, cqe * cqe_size,
 			    IB_ACCESS_LOCAL_WRITE, 1);
 	if (IS_ERR(*umem))
 		return PTR_ERR(*umem);
@@ -331,16 +333,23 @@ static void mlx4_ib_cq_resize_copy_cqes(struct mlx4_ib_cq *cq)
 {
 	struct mlx4_cqe *cqe, *new_cqe;
 	int i;
+	int cqe_size = cq->buf.entry_size;
+	int cqe_inc = cqe_size == 64 ? 1 : 0;
 
 	i = cq->mcq.cons_index;
 	cqe = get_cqe(cq, i & cq->ibcq.cqe);
+	cqe += cqe_inc;
+
 	while ((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) != MLX4_CQE_OPCODE_RESIZE) {
 		new_cqe = get_cqe_from_buf(&cq->resize_buf->buf,
 					   (i + 1) & cq->resize_buf->cqe);
-		memcpy(new_cqe, get_cqe(cq, i & cq->ibcq.cqe), sizeof(struct mlx4_cqe));
+		memcpy(new_cqe, get_cqe(cq, i & cq->ibcq.cqe), cqe_size);
+		new_cqe += cqe_inc;
+
 		new_cqe->owner_sr_opcode = (cqe->owner_sr_opcode & ~MLX4_CQE_OWNER_MASK) |
 			(((i + 1) & (cq->resize_buf->cqe + 1)) ? MLX4_CQE_OWNER_MASK : 0);
 		cqe = get_cqe(cq, ++i & cq->ibcq.cqe);
+		cqe += cqe_inc;
 	}
 	++cq->mcq.cons_index;
 }
@@ -438,6 +447,7 @@ err_buf:
 
 out:
 	mutex_unlock(&cq->resize_mutex);
+
 	return err;
 }
 
@@ -586,6 +596,9 @@ repoll:
 	if (!cqe)
 		return -EAGAIN;
 
+	if (cq->buf.entry_size == 64)
+		cqe++;
+
 	++cq->mcq.cons_index;
 
 	/*
@@ -807,6 +820,7 @@ void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
 	int nfreed = 0;
 	struct mlx4_cqe *cqe, *dest;
 	u8 owner_bit;
+	int cqe_inc = cq->buf.entry_size == 64 ? 1 : 0;
 
 	/*
 	 * First we need to find the current producer index, so we
@@ -825,12 +839,16 @@ void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
 	 */
 	while ((int) --prod_index - (int) cq->mcq.cons_index >= 0) {
 		cqe = get_cqe(cq, prod_index & cq->ibcq.cqe);
+		cqe += cqe_inc;
+
 		if ((be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK) == qpn) {
 			if (srq && !(cqe->owner_sr_opcode & MLX4_CQE_IS_SEND_MASK))
 				mlx4_ib_free_srq_wqe(srq, be16_to_cpu(cqe->wqe_index));
 			++nfreed;
 		} else if (nfreed) {
 			dest = get_cqe(cq, (prod_index + nfreed) & cq->ibcq.cqe);
+			dest += cqe_inc;
+
 			owner_bit = dest->owner_sr_opcode & MLX4_CQE_OWNER_MASK;
 			memcpy(dest, cqe, sizeof *cqe);
 			dest->owner_sr_opcode = owner_bit |
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 718ec6b2bad2..e7d81c0d1ac5 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -563,15 +563,24 @@ static struct ib_ucontext *mlx4_ib_alloc_ucontext(struct ib_device *ibdev,
 {
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	struct mlx4_ib_ucontext *context;
+	struct mlx4_ib_alloc_ucontext_resp_v3 resp_v3;
 	struct mlx4_ib_alloc_ucontext_resp resp;
 	int err;
 
 	if (!dev->ib_active)
 		return ERR_PTR(-EAGAIN);
 
-	resp.qp_tab_size      = dev->dev->caps.num_qps;
-	resp.bf_reg_size      = dev->dev->caps.bf_reg_size;
-	resp.bf_regs_per_page = dev->dev->caps.bf_regs_per_page;
+	if (ibdev->uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION) {
+		resp_v3.qp_tab_size      = dev->dev->caps.num_qps;
+		resp_v3.bf_reg_size      = dev->dev->caps.bf_reg_size;
+		resp_v3.bf_regs_per_page = dev->dev->caps.bf_regs_per_page;
+	} else {
+		resp.dev_caps	      = dev->dev->caps.userspace_caps;
+		resp.qp_tab_size      = dev->dev->caps.num_qps;
+		resp.bf_reg_size      = dev->dev->caps.bf_reg_size;
+		resp.bf_regs_per_page = dev->dev->caps.bf_regs_per_page;
+		resp.cqe_size	      = dev->dev->caps.cqe_size;
+	}
 
 	context = kmalloc(sizeof *context, GFP_KERNEL);
 	if (!context)
@@ -586,7 +595,11 @@ static struct ib_ucontext *mlx4_ib_alloc_ucontext(struct ib_device *ibdev,
 	INIT_LIST_HEAD(&context->db_page_list);
 	mutex_init(&context->db_page_mutex);
 
-	err = ib_copy_to_udata(udata, &resp, sizeof resp);
+	if (ibdev->uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION)
+		err = ib_copy_to_udata(udata, &resp_v3, sizeof(resp_v3));
+	else
+		err = ib_copy_to_udata(udata, &resp, sizeof(resp));
+
 	if (err) {
 		mlx4_uar_free(to_mdev(ibdev)->dev, &context->uar);
 		kfree(context);
@@ -1342,7 +1355,11 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.num_comp_vectors	= dev->caps.num_comp_vectors;
 	ibdev->ib_dev.dma_device	= &dev->pdev->dev;
 
-	ibdev->ib_dev.uverbs_abi_ver	= MLX4_IB_UVERBS_ABI_VERSION;
+	if (dev->caps.userspace_caps)
+		ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_ABI_VERSION;
+	else
+		ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION;
+
 	ibdev->ib_dev.uverbs_cmd_mask	=
 		(1ull << IB_USER_VERBS_CMD_GET_CONTEXT)		|
 		(1ull << IB_USER_VERBS_CMD_QUERY_DEVICE)	|
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index e04cbc9a54a5..dcd845bc30f0 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -90,6 +90,7 @@ struct mlx4_ib_xrcd {
 struct mlx4_ib_cq_buf {
 	struct mlx4_buf		buf;
 	struct mlx4_mtt		mtt;
+	int			entry_size;
 };
 
 struct mlx4_ib_cq_resize {
diff --git a/drivers/infiniband/hw/mlx4/user.h b/drivers/infiniband/hw/mlx4/user.h
index 13beedeeef9f..07e6769ef43b 100644
--- a/drivers/infiniband/hw/mlx4/user.h
+++ b/drivers/infiniband/hw/mlx4/user.h
@@ -40,7 +40,9 @@
  * Increment this value if any changes that break userspace ABI
  * compatibility are made.
  */
-#define MLX4_IB_UVERBS_ABI_VERSION	3
+
+#define MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION	3
+#define MLX4_IB_UVERBS_ABI_VERSION		4
 
 /*
  * Make sure that all structs defined in this file remain laid out so
@@ -50,10 +52,18 @@
  * instead.
  */
 
+struct mlx4_ib_alloc_ucontext_resp_v3 {
+	__u32	qp_tab_size;
+	__u16	bf_reg_size;
+	__u16	bf_regs_per_page;
+};
+
 struct mlx4_ib_alloc_ucontext_resp {
+	__u32	dev_caps;
 	__u32	qp_tab_size;
 	__u16	bf_reg_size;
 	__u16	bf_regs_per_page;
+	__u32	cqe_size;
 };
 
 struct mlx4_ib_alloc_pd_resp {
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 3d1899ff1076..e791e705f7b1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1755,7 +1755,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 			spin_lock_init(&s_state->lock);
 		}
 
-		memset(&priv->mfunc.master.cmd_eqe, 0, sizeof(struct mlx4_eqe));
+		memset(&priv->mfunc.master.cmd_eqe, 0, dev->caps.eqe_size);
 		priv->mfunc.master.cmd_eqe.type = MLX4_EVENT_TYPE_CMD;
 		INIT_WORK(&priv->mfunc.master.comm_work,
 			  mlx4_master_comm_channel);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index aa9c2f6cf3c0..b8d0854a7ad1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -51,7 +51,7 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 	int err;
 
 	cq->size = entries;
-	cq->buf_size = cq->size * sizeof(struct mlx4_cqe);
+	cq->buf_size = cq->size * mdev->dev->caps.cqe_size;
 
 	cq->ring = ring;
 	cq->is_tx = mode;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index edd9cb8d3e1d..93a325669582 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1600,6 +1600,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		goto out;
 	}
 	priv->rx_ring_num = prof->rx_ring_num;
+	priv->cqe_factor = (mdev->dev->caps.cqe_size == 64) ? 1 : 0;
 	priv->mac_index = -1;
 	priv->msg_enable = MLX4_EN_MSG_LEVEL;
 	spin_lock_init(&priv->stats_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 5aba5ecdf1e2..6fa106f6c0ec 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -566,6 +566,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	struct ethhdr *ethh;
 	dma_addr_t dma;
 	u64 s_mac;
+	int factor = priv->cqe_factor;
 
 	if (!priv->port_up)
 		return 0;
@@ -574,7 +575,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	 * descriptor offset can be deduced from the CQE index instead of
 	 * reading 'cqe->index' */
 	index = cq->mcq.cons_index & ring->size_mask;
-	cqe = &cq->buf[index];
+	cqe = &cq->buf[(index << factor) + factor];
 
 	/* Process all completed CQEs */
 	while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
@@ -709,7 +710,7 @@ next:
 
 		++cq->mcq.cons_index;
 		index = (cq->mcq.cons_index) & ring->size_mask;
-		cqe = &cq->buf[index];
+		cqe = &cq->buf[(index << factor) + factor];
 		if (++polled == budget) {
 			/* We are here because we reached the NAPI budget -
 			 * flush only pending LRO sessions */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index b35094c590ba..25c157abdd92 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -315,12 +315,13 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 	struct mlx4_cqe *buf = cq->buf;
 	u32 packets = 0;
 	u32 bytes = 0;
+	int factor = priv->cqe_factor;
 
 	if (!priv->port_up)
 		return;
 
 	index = cons_index & size_mask;
-	cqe = &buf[index];
+	cqe = &buf[(index << factor) + factor];
 	ring_index = ring->cons & size_mask;
 
 	/* Process all completed CQEs */
@@ -349,7 +350,7 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 
 		++cons_index;
 		index = cons_index & size_mask;
-		cqe = &buf[index];
+		cqe = &buf[(index << factor) + factor];
 	}
 
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index b84a88bc44dc..c509a86db610 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -101,15 +101,21 @@ static void eq_set_ci(struct mlx4_eq *eq, int req_not)
 	mb();
 }
 
-static struct mlx4_eqe *get_eqe(struct mlx4_eq *eq, u32 entry)
+static struct mlx4_eqe *get_eqe(struct mlx4_eq *eq, u32 entry, u8 eqe_factor)
 {
-	unsigned long off = (entry & (eq->nent - 1)) * MLX4_EQ_ENTRY_SIZE;
-	return eq->page_list[off / PAGE_SIZE].buf + off % PAGE_SIZE;
+	/* (entry & (eq->nent - 1)) gives us a cyclic array */
+	unsigned long offset = (entry & (eq->nent - 1)) * (MLX4_EQ_ENTRY_SIZE << eqe_factor);
+	/* CX3 is capable of extending the EQE from 32 to 64 bytes.
+	 * When this feature is enabled, the first (in the lower addresses)
+	 * 32 bytes in the 64 byte EQE are reserved and the next 32 bytes
+	 * contain the legacy EQE information.
+	 */
+	return eq->page_list[offset / PAGE_SIZE].buf + (offset + (eqe_factor ? MLX4_EQ_ENTRY_SIZE : 0)) % PAGE_SIZE;
 }
 
-static struct mlx4_eqe *next_eqe_sw(struct mlx4_eq *eq)
+static struct mlx4_eqe *next_eqe_sw(struct mlx4_eq *eq, u8 eqe_factor)
 {
-	struct mlx4_eqe *eqe = get_eqe(eq, eq->cons_index);
+	struct mlx4_eqe *eqe = get_eqe(eq, eq->cons_index, eqe_factor);
 	return !!(eqe->owner & 0x80) ^ !!(eq->cons_index & eq->nent) ? NULL : eqe;
 }
 
@@ -177,7 +183,7 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe)
 		return;
 	}
 
-	memcpy(s_eqe, eqe, sizeof(struct mlx4_eqe) - 1);
+	memcpy(s_eqe, eqe, dev->caps.eqe_size - 1);
 	s_eqe->slave_id = slave;
 	/* ensure all information is written before setting the ownersip bit */
 	wmb();
@@ -441,7 +447,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 	int i;
 	enum slave_port_gen_event gen_event;
 
-	while ((eqe = next_eqe_sw(eq))) {
+	while ((eqe = next_eqe_sw(eq, dev->caps.eqe_factor))) {
 		/*
 		 * Make sure we read EQ entry contents after we've
 		 * checked the ownership bit.
@@ -864,7 +870,8 @@ static int mlx4_create_eq(struct mlx4_dev *dev, int nent,
 
 	eq->dev   = dev;
 	eq->nent  = roundup_pow_of_two(max(nent, 2));
-	npages = PAGE_ALIGN(eq->nent * MLX4_EQ_ENTRY_SIZE) / PAGE_SIZE;
+	/* CX3 is capable of extending the CQE/EQE from 32 to 64 bytes */
+	npages = PAGE_ALIGN(eq->nent * (MLX4_EQ_ENTRY_SIZE << dev->caps.eqe_factor)) / PAGE_SIZE;
 
 	eq->page_list = kmalloc(npages * sizeof *eq->page_list,
 				GFP_KERNEL);
@@ -966,8 +973,9 @@ static void mlx4_free_eq(struct mlx4_dev *dev,
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_cmd_mailbox *mailbox;
 	int err;
-	int npages = PAGE_ALIGN(MLX4_EQ_ENTRY_SIZE * eq->nent) / PAGE_SIZE;
 	int i;
+	/* CX3 is capable of extending the CQE/EQE from 32 to 64 bytes */
+	int npages = PAGE_ALIGN((MLX4_EQ_ENTRY_SIZE << dev->caps.eqe_factor) * eq->nent) / PAGE_SIZE;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 4f30b99324cf..9a9de51ecc91 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -110,6 +110,8 @@ static void dump_dev_cap_flags(struct mlx4_dev *dev, u64 flags)
 		[42] = "Multicast VEP steering support",
 		[48] = "Counters support",
 		[59] = "Port management change event support",
+		[61] = "64 byte EQE support",
+		[62] = "64 byte CQE support",
 	};
 	int i;
 
@@ -235,7 +237,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		field = dev->caps.num_ports;
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_NUM_PORTS_OFFSET);
 
-		size = 0; /* no PF behaviour is set for now */
+		size = dev->caps.function_caps; /* set PF behaviours */
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_PF_BHVR_OFFSET);
 
 		field = 0; /* protected FMR support not available as yet */
@@ -1237,6 +1239,24 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS)
 		*(inbox + INIT_HCA_FLAGS_OFFSET / 4) |= cpu_to_be32(1 << 4);
 
+	/* CX3 is capable of extending CQEs/EQEs from 32 to 64 bytes */
+	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_64B_EQE) {
+		*(inbox + INIT_HCA_EQE_CQE_OFFSETS / 4) |= cpu_to_be32(1 << 29);
+		dev->caps.eqe_size   = 64;
+		dev->caps.eqe_factor = 1;
+	} else {
+		dev->caps.eqe_size   = 32;
+		dev->caps.eqe_factor = 0;
+	}
+
+	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_64B_CQE) {
+		*(inbox + INIT_HCA_EQE_CQE_OFFSETS / 4) |= cpu_to_be32(1 << 30);
+		dev->caps.cqe_size   = 64;
+		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_64B_CQE;
+	} else {
+		dev->caps.cqe_size   = 32;
+	}
+
 	/* QPC/EEC/CQC/EQC/RDMARC attributes */
 
 	MLX4_PUT(inbox, param->qpc_base,      INIT_HCA_QPC_BASE_OFFSET);
@@ -1319,6 +1339,7 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	struct mlx4_cmd_mailbox *mailbox;
 	__be32 *outbox;
 	int err;
+	u8 byte_field;
 
 #define QUERY_HCA_GLOBAL_CAPS_OFFSET	0x04
 
@@ -1370,6 +1391,13 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 			 INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
 	}
 
+	/* CX3 is capable of extending CQEs/EQEs from 32 to 64 bytes */
+	MLX4_GET(byte_field, outbox, INIT_HCA_EQE_CQE_OFFSETS);
+	if (byte_field & 0x20) /* 64-bytes eqe enabled */
+		param->dev_cap_enabled |= MLX4_DEV_CAP_64B_EQE_ENABLED;
+	if (byte_field & 0x40) /* 64-bytes cqe enabled */
+		param->dev_cap_enabled |= MLX4_DEV_CAP_64B_CQE_ENABLED;
+
 	/* TPT attributes */
 
 	MLX4_GET(param->dmpt_base,  outbox, INIT_HCA_DMPT_BASE_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 85abe9c11a22..2c2e7ade2a34 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -172,6 +172,7 @@ struct mlx4_init_hca_param {
 	u8  log_uar_sz;
 	u8  uar_page_sz; /* log pg sz in 4k chunks */
 	u8  fs_hash_enable_bits;
+	u64 dev_cap_enabled;
 };
 
 struct mlx4_init_ib_param {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 2aa80afd98d2..4337f685175d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -95,8 +95,14 @@ MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
 					 " Not in use with device managed"
 					 " flow steering");
 
+static bool enable_64b_cqe_eqe;
+module_param(enable_64b_cqe_eqe, bool, 0444);
+MODULE_PARM_DESC(enable_64b_cqe_eqe,
+		 "Enable 64 byte CQEs/EQEs when the the FW supports this");
+
 #define HCA_GLOBAL_CAP_MASK            0
-#define PF_CONTEXT_BEHAVIOUR_MASK      0
+
+#define PF_CONTEXT_BEHAVIOUR_MASK	MLX4_FUNC_CAP_64B_EQE_CQE
 
 static char mlx4_version[] __devinitdata =
 	DRV_NAME ": Mellanox ConnectX core driver v"
@@ -386,6 +392,21 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH];
 
 	dev->caps.sqp_demux = (mlx4_is_master(dev)) ? MLX4_MAX_NUM_SLAVES : 0;
+
+	if (!enable_64b_cqe_eqe) {
+		if (dev_cap->flags &
+		    (MLX4_DEV_CAP_FLAG_64B_CQE | MLX4_DEV_CAP_FLAG_64B_EQE)) {
+			mlx4_warn(dev, "64B EQEs/CQEs supported by the device but not enabled\n");
+			dev->caps.flags &= ~MLX4_DEV_CAP_FLAG_64B_CQE;
+			dev->caps.flags &= ~MLX4_DEV_CAP_FLAG_64B_EQE;
+		}
+	}
+
+	if ((dev_cap->flags &
+	    (MLX4_DEV_CAP_FLAG_64B_CQE | MLX4_DEV_CAP_FLAG_64B_EQE)) &&
+	    mlx4_is_master(dev))
+		dev->caps.function_caps |= MLX4_FUNC_CAP_64B_EQE_CQE;
+
 	return 0;
 }
 /*The function checks if there are live vf, return the num of them*/
@@ -599,6 +620,21 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 		goto err_mem;
 	}
 
+	if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_64B_EQE_ENABLED) {
+		dev->caps.eqe_size   = 64;
+		dev->caps.eqe_factor = 1;
+	} else {
+		dev->caps.eqe_size   = 32;
+		dev->caps.eqe_factor = 0;
+	}
+
+	if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_64B_CQE_ENABLED) {
+		dev->caps.cqe_size   = 64;
+		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_64B_CQE;
+	} else {
+		dev->caps.cqe_size   = 32;
+	}
+
 	return 0;
 
 err_mem:
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 9d27e42264e2..73b5c2ac5bd5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -487,6 +487,7 @@ struct mlx4_en_priv {
 	int mac_index;
 	unsigned max_mtu;
 	int base_qpn;
+	int cqe_factor;
 
 	struct mlx4_en_rss_map rss_map;
 	__be32 ctrl_flags;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 6d1acb04cd17..21821da2abfd 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -142,6 +142,8 @@ enum {
 	MLX4_DEV_CAP_FLAG_COUNTERS	= 1LL << 48,
 	MLX4_DEV_CAP_FLAG_SENSE_SUPPORT	= 1LL << 55,
 	MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV = 1LL << 59,
+	MLX4_DEV_CAP_FLAG_64B_EQE	= 1LL << 61,
+	MLX4_DEV_CAP_FLAG_64B_CQE	= 1LL << 62
 };
 
 enum {
@@ -151,6 +153,20 @@ enum {
 	MLX4_DEV_CAP_FLAG2_FS_EN		= 1LL <<  3
 };
 
+enum {
+	MLX4_DEV_CAP_64B_EQE_ENABLED	= 1LL << 0,
+	MLX4_DEV_CAP_64B_CQE_ENABLED	= 1LL << 1
+};
+
+enum {
+	MLX4_USER_DEV_CAP_64B_CQE	= 1L << 0
+};
+
+enum {
+	MLX4_FUNC_CAP_64B_EQE_CQE	= 1L << 0
+};
+
+
 #define MLX4_ATTR_EXTENDED_PORT_INFO	cpu_to_be16(0xff90)
 
 enum {
@@ -419,6 +435,11 @@ struct mlx4_caps {
 	u32			max_counters;
 	u8			port_ib_mtu[MLX4_MAX_PORTS + 1];
 	u16			sqp_demux;
+	u32			eqe_size;
+	u32			cqe_size;
+	u8			eqe_factor;
+	u32			userspace_caps; /* userspace must be aware of these */
+	u32			function_caps;  /* VFs must be aware of these */
 };
 
 struct mlx4_buf_list {
-- 
cgit v1.2.3-55-g7522


From 39c7caebc94e851f58b84b54659156dd30522e8e Mon Sep 17 00:00:00 2001
From: Ansis Atteka
Date: Mon, 26 Nov 2012 11:24:11 -0800
Subject: openvswitch: add skb mark matching and set action

This patch adds support for skb mark matching and set action.

Signed-off-by: Ansis Atteka <aatteka@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
---
 include/linux/openvswitch.h |  1 +
 net/openvswitch/actions.c   |  4 ++++
 net/openvswitch/datapath.c  |  3 +++
 net/openvswitch/flow.c      | 19 ++++++++++++++++++-
 net/openvswitch/flow.h      |  8 +++++---
 5 files changed, 31 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h
index eb1efa54fe84..d42e174bd0c8 100644
--- a/include/linux/openvswitch.h
+++ b/include/linux/openvswitch.h
@@ -243,6 +243,7 @@ enum ovs_key_attr {
 	OVS_KEY_ATTR_ICMPV6,    /* struct ovs_key_icmpv6 */
 	OVS_KEY_ATTR_ARP,       /* struct ovs_key_arp */
 	OVS_KEY_ATTR_ND,        /* struct ovs_key_nd */
+	OVS_KEY_ATTR_SKB_MARK,  /* u32 skb mark */
 	__OVS_KEY_ATTR_MAX
 };
 
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index a58ed276f70d..ac2defeeba83 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -428,6 +428,10 @@ static int execute_set_action(struct sk_buff *skb,
 		skb->priority = nla_get_u32(nested_attr);
 		break;
 
+	case OVS_KEY_ATTR_SKB_MARK:
+		skb->mark = nla_get_u32(nested_attr);
+		break;
+
 	case OVS_KEY_ATTR_ETHERNET:
 		err = set_eth_addr(skb, nla_data(nested_attr));
 		break;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 7b1d6d2b0c1a..f996db343247 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -482,6 +482,7 @@ static int validate_set(const struct nlattr *a,
 	const struct ovs_key_ipv6 *ipv6_key;
 
 	case OVS_KEY_ATTR_PRIORITY:
+	case OVS_KEY_ATTR_SKB_MARK:
 	case OVS_KEY_ATTR_ETHERNET:
 		break;
 
@@ -695,6 +696,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 		goto err_flow_free;
 
 	err = ovs_flow_metadata_from_nlattrs(&flow->key.phy.priority,
+					     &flow->key.phy.skb_mark,
 					     &flow->key.phy.in_port,
 					     a[OVS_PACKET_ATTR_KEY]);
 	if (err)
@@ -714,6 +716,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 
 	OVS_CB(packet)->flow = flow;
 	packet->priority = flow->key.phy.priority;
+	packet->mark = flow->key.phy.skb_mark;
 
 	rcu_read_lock();
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index e6ce902e92e5..c3294cebc4f2 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -604,6 +604,7 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key,
 
 	key->phy.priority = skb->priority;
 	key->phy.in_port = in_port;
+	key->phy.skb_mark = skb->mark;
 
 	skb_reset_mac_header(skb);
 
@@ -803,6 +804,7 @@ const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 	[OVS_KEY_ATTR_ENCAP] = -1,
 	[OVS_KEY_ATTR_PRIORITY] = sizeof(u32),
 	[OVS_KEY_ATTR_IN_PORT] = sizeof(u32),
+	[OVS_KEY_ATTR_SKB_MARK] = sizeof(u32),
 	[OVS_KEY_ATTR_ETHERNET] = sizeof(struct ovs_key_ethernet),
 	[OVS_KEY_ATTR_VLAN] = sizeof(__be16),
 	[OVS_KEY_ATTR_ETHERTYPE] = sizeof(__be16),
@@ -988,6 +990,10 @@ int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
 	} else {
 		swkey->phy.in_port = DP_MAX_PORTS;
 	}
+	if (attrs & (1 << OVS_KEY_ATTR_SKB_MARK)) {
+		swkey->phy.skb_mark = nla_get_u32(a[OVS_KEY_ATTR_SKB_MARK]);
+		attrs &= ~(1 << OVS_KEY_ATTR_SKB_MARK);
+	}
 
 	/* Data attributes. */
 	if (!(attrs & (1 << OVS_KEY_ATTR_ETHERNET)))
@@ -1115,6 +1121,8 @@ int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
 
 /**
  * ovs_flow_metadata_from_nlattrs - parses Netlink attributes into a flow key.
+ * @priority: receives the skb priority
+ * @mark: receives the skb mark
  * @in_port: receives the extracted input port.
  * @key: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
  * sequence.
@@ -1124,7 +1132,7 @@ int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
  * get the metadata, that is, the parts of the flow key that cannot be
  * extracted from the packet itself.
  */
-int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port,
+int ovs_flow_metadata_from_nlattrs(u32 *priority, u32 *mark, u16 *in_port,
 			       const struct nlattr *attr)
 {
 	const struct nlattr *nla;
@@ -1132,6 +1140,7 @@ int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port,
 
 	*in_port = DP_MAX_PORTS;
 	*priority = 0;
+	*mark = 0;
 
 	nla_for_each_nested(nla, attr, rem) {
 		int type = nla_type(nla);
@@ -1150,6 +1159,10 @@ int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port,
 					return -EINVAL;
 				*in_port = nla_get_u32(nla);
 				break;
+
+			case OVS_KEY_ATTR_SKB_MARK:
+				*mark = nla_get_u32(nla);
+				break;
 			}
 		}
 	}
@@ -1171,6 +1184,10 @@ int ovs_flow_to_nlattrs(const struct sw_flow_key *swkey, struct sk_buff *skb)
 	    nla_put_u32(skb, OVS_KEY_ATTR_IN_PORT, swkey->phy.in_port))
 		goto nla_put_failure;
 
+	if (swkey->phy.skb_mark &&
+	    nla_put_u32(skb, OVS_KEY_ATTR_SKB_MARK, swkey->phy.skb_mark))
+		goto nla_put_failure;
+
 	nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
 	if (!nla)
 		goto nla_put_failure;
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 14a324eb017b..a7bb60ff3b5b 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -43,6 +43,7 @@ struct sw_flow_actions {
 struct sw_flow_key {
 	struct {
 		u32	priority;	/* Packet QoS priority. */
+		u32	skb_mark;	/* SKB mark. */
 		u16	in_port;	/* Input switch port (or DP_MAX_PORTS). */
 	} phy;
 	struct {
@@ -144,6 +145,7 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies);
  *                         ------  ---  ------  -----
  *  OVS_KEY_ATTR_PRIORITY      4    --     4      8
  *  OVS_KEY_ATTR_IN_PORT       4    --     4      8
+ *  OVS_KEY_ATTR_SKB_MARK      4    --     4      8
  *  OVS_KEY_ATTR_ETHERNET     12    --     4     16
  *  OVS_KEY_ATTR_ETHERTYPE     2     2     4      8  (outer VLAN ethertype)
  *  OVS_KEY_ATTR_8021Q         4    --     4      8
@@ -153,14 +155,14 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies);
  *  OVS_KEY_ATTR_ICMPV6        2     2     4      8
  *  OVS_KEY_ATTR_ND           28    --     4     32
  *  -------------------------------------------------
- *  total                                       144
+ *  total                                       152
  */
-#define FLOW_BUFSIZE 144
+#define FLOW_BUFSIZE 152
 
 int ovs_flow_to_nlattrs(const struct sw_flow_key *, struct sk_buff *);
 int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
 		      const struct nlattr *);
-int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port,
+int ovs_flow_metadata_from_nlattrs(u32 *priority, u32 *mark, u16 *in_port,
 			       const struct nlattr *);
 
 #define MAX_ACTIONS_BUFSIZE    (16 * 1024)
-- 
cgit v1.2.3-55-g7522


From e95c17e9caff4b106cc95b761f3e07964a5a0d9f Mon Sep 17 00:00:00 2001
From: Timur Tabi
Date: Tue, 16 Oct 2012 17:33:44 -0500
Subject: drivers/video: fsl-diu-fb: add support for set_gamma ioctls

The MPC5121 BSP comes with a gamma_set utility that initializes the gamma
table via an ioctl.  Unfortunately, the ioctl number that utility uses
is defined improperly, but we can still support it.

Signed-off-by: Timur Tabi <timur@freescale.com>
---
 drivers/video/fsl-diu-fb.c | 17 +++++++++++++++++
 include/linux/fsl-diu-fb.h |  9 +++++++++
 2 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/drivers/video/fsl-diu-fb.c b/drivers/video/fsl-diu-fb.c
index 5b12e1783fac..9c4054760627 100644
--- a/drivers/video/fsl-diu-fb.c
+++ b/drivers/video/fsl-diu-fb.c
@@ -1181,6 +1181,23 @@ static int fsl_diu_ioctl(struct fb_info *info, unsigned int cmd,
 			ad->ckmin_b = ck.blue_min;
 		}
 		break;
+#ifdef CONFIG_PPC_MPC512x
+	case MFB_SET_GAMMA: {
+		struct fsl_diu_data *data = mfbi->parent;
+
+		if (copy_from_user(data->gamma, buf, sizeof(data->gamma)))
+			return -EFAULT;
+		setbits32(&data->diu_reg->gamma, 0); /* Force table reload */
+		break;
+	}
+	case MFB_GET_GAMMA: {
+		struct fsl_diu_data *data = mfbi->parent;
+
+		if (copy_to_user(buf, data->gamma, sizeof(data->gamma)))
+			return -EFAULT;
+		break;
+	}
+#endif
 	default:
 		dev_err(info->dev, "unknown ioctl command (0x%08X)\n", cmd);
 		return -ENOIOCTLCMD;
diff --git a/include/linux/fsl-diu-fb.h b/include/linux/fsl-diu-fb.h
index 11c16a1fb9e3..a1e8277120c7 100644
--- a/include/linux/fsl-diu-fb.h
+++ b/include/linux/fsl-diu-fb.h
@@ -46,6 +46,15 @@ struct aoi_display_offset {
 #define MFB_SET_PIXFMT		_IOW('M', 8, __u32)
 #define MFB_GET_PIXFMT		_IOR('M', 8, __u32)
 
+/*
+ * The MPC5121 BSP comes with a gamma_set utility that initializes the
+ * gamma table.  Unfortunately, it uses bad values for the IOCTL commands,
+ * but there's nothing we can do about it now.  These ioctls are only
+ * supported on the MPC5121.
+ */
+#define MFB_SET_GAMMA		_IOW('M', 1, __u8)
+#define MFB_GET_GAMMA		_IOR('M', 1, __u8)
+
 /*
  * The original definitions of MFB_SET_PIXFMT and MFB_GET_PIXFMT used the
  * wrong value for 'size' field of the ioctl.  The current macros above use the
-- 
cgit v1.2.3-55-g7522


From 0751f8654602e4255f0b9c17784d8100d5896010 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Sat, 24 Nov 2012 19:34:17 +0100
Subject: bcma: add more package IDs

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/linux/bcma/bcma.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index fd15d9829705..93b1e091b1e9 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -157,6 +157,7 @@ struct bcma_host_ops {
 
 /* Chip IDs of SoCs */
 #define BCMA_CHIP_ID_BCM4706	0x5300
+#define  BCMA_PKG_ID_BCM4706L	1
 #define BCMA_CHIP_ID_BCM4716	0x4716
 #define  BCMA_PKG_ID_BCM4716	8
 #define  BCMA_PKG_ID_BCM4717	9
@@ -166,7 +167,11 @@ struct bcma_host_ops {
 #define BCMA_CHIP_ID_BCM4749	0x4749
 #define BCMA_CHIP_ID_BCM5356	0x5356
 #define BCMA_CHIP_ID_BCM5357	0x5357
+#define  BCMA_PKG_ID_BCM5358	9
+#define  BCMA_PKG_ID_BCM47186	10
+#define  BCMA_PKG_ID_BCM5357	11
 #define BCMA_CHIP_ID_BCM53572	53572
+#define  BCMA_PKG_ID_BCM47188	9
 
 struct bcma_device {
 	struct bcma_bus *bus;
-- 
cgit v1.2.3-55-g7522


From 92e3229dcdc80ff0b6304f14c578d76e7e10e226 Mon Sep 17 00:00:00 2001
From: Liu, Jinsong
Date: Thu, 8 Nov 2012 05:41:13 +0000
Subject: xen/acpi: ACPI PAD driver

PAD is acpi Processor Aggregator Device which provides a control point
that enables the platform to perform specific processor configuration
and control that applies to all processors in the platform.

This patch is to implement Xen acpi pad logic. When running under Xen
virt platform, native pad driver would not work. Instead Xen pad driver,
a self-contained and thin logic level, would take over acpi pad logic.

When acpi pad notify OSPM, xen pad logic intercept and parse _PUR object
to get the expected idle cpu number, and then hypercall to hypervisor.
Xen hypervisor would then do the rest work, say, core parking, to idle
specific number of cpus on its own policy.

Signed-off-by: Jan Beulich <JBeulich@suse.com>
Signed-off-by: Liu Jinsong <jinsong.liu@intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/Makefile             |   3 +-
 drivers/xen/xen-acpi-pad.c       | 181 +++++++++++++++++++++++++++++++++++++++
 include/xen/interface/platform.h |  17 ++++
 include/xen/interface/version.h  |  15 ++++
 4 files changed, 215 insertions(+), 1 deletion(-)
 create mode 100644 drivers/xen/xen-acpi-pad.c

(limited to 'include')

diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 0e8637035457..3c397170f39c 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -10,7 +10,8 @@ CFLAGS_features.o			:= $(nostackp)
 
 dom0-$(CONFIG_PCI) += pci.o
 dom0-$(CONFIG_USB_SUPPORT) += dbgp.o
-dom0-$(CONFIG_ACPI) += acpi.o
+dom0-$(CONFIG_ACPI) += acpi.o $(xen-pad-y)
+xen-pad-$(CONFIG_X86) += xen-acpi-pad.o
 dom0-$(CONFIG_X86) += pcpu.o
 obj-$(CONFIG_XEN_DOM0)			+= $(dom0-y)
 obj-$(CONFIG_BLOCK)			+= biomerge.o
diff --git a/drivers/xen/xen-acpi-pad.c b/drivers/xen/xen-acpi-pad.c
new file mode 100644
index 000000000000..f23ecf380088
--- /dev/null
+++ b/drivers/xen/xen-acpi-pad.c
@@ -0,0 +1,181 @@
+/*
+ * xen-acpi-pad.c - Xen pad interface
+ *
+ * Copyright (c) 2012, Intel Corporation.
+ *    Author: Liu, Jinsong <jinsong.liu@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <acpi/acpi_bus.h>
+#include <acpi/acpi_drivers.h>
+#include <asm/xen/hypercall.h>
+#include <xen/interface/version.h>
+
+#define ACPI_PROCESSOR_AGGREGATOR_CLASS	"acpi_pad"
+#define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator"
+#define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80
+static DEFINE_MUTEX(xen_cpu_lock);
+
+static int xen_acpi_pad_idle_cpus(unsigned int idle_nums)
+{
+	struct xen_platform_op op;
+
+	op.cmd = XENPF_core_parking;
+	op.u.core_parking.type = XEN_CORE_PARKING_SET;
+	op.u.core_parking.idle_nums = idle_nums;
+
+	return HYPERVISOR_dom0_op(&op);
+}
+
+static int xen_acpi_pad_idle_cpus_num(void)
+{
+	struct xen_platform_op op;
+
+	op.cmd = XENPF_core_parking;
+	op.u.core_parking.type = XEN_CORE_PARKING_GET;
+
+	return HYPERVISOR_dom0_op(&op)
+	       ?: op.u.core_parking.idle_nums;
+}
+
+/*
+ * Query firmware how many CPUs should be idle
+ * return -1 on failure
+ */
+static int acpi_pad_pur(acpi_handle handle)
+{
+	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
+	union acpi_object *package;
+	int num = -1;
+
+	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_PUR", NULL, &buffer)))
+		return num;
+
+	if (!buffer.length || !buffer.pointer)
+		return num;
+
+	package = buffer.pointer;
+
+	if (package->type == ACPI_TYPE_PACKAGE &&
+		package->package.count == 2 &&
+		package->package.elements[0].integer.value == 1) /* rev 1 */
+		num = package->package.elements[1].integer.value;
+
+	kfree(buffer.pointer);
+	return num;
+}
+
+/* Notify firmware how many CPUs are idle */
+static void acpi_pad_ost(acpi_handle handle, int stat,
+	uint32_t idle_nums)
+{
+	union acpi_object params[3] = {
+		{.type = ACPI_TYPE_INTEGER,},
+		{.type = ACPI_TYPE_INTEGER,},
+		{.type = ACPI_TYPE_BUFFER,},
+	};
+	struct acpi_object_list arg_list = {3, params};
+
+	params[0].integer.value = ACPI_PROCESSOR_AGGREGATOR_NOTIFY;
+	params[1].integer.value =  stat;
+	params[2].buffer.length = 4;
+	params[2].buffer.pointer = (void *)&idle_nums;
+	acpi_evaluate_object(handle, "_OST", &arg_list, NULL);
+}
+
+static void acpi_pad_handle_notify(acpi_handle handle)
+{
+	int idle_nums;
+
+	mutex_lock(&xen_cpu_lock);
+	idle_nums = acpi_pad_pur(handle);
+	if (idle_nums < 0) {
+		mutex_unlock(&xen_cpu_lock);
+		return;
+	}
+
+	idle_nums = xen_acpi_pad_idle_cpus(idle_nums)
+		    ?: xen_acpi_pad_idle_cpus_num();
+	if (idle_nums >= 0)
+		acpi_pad_ost(handle, 0, idle_nums);
+	mutex_unlock(&xen_cpu_lock);
+}
+
+static void acpi_pad_notify(acpi_handle handle, u32 event,
+	void *data)
+{
+	switch (event) {
+	case ACPI_PROCESSOR_AGGREGATOR_NOTIFY:
+		acpi_pad_handle_notify(handle);
+		break;
+	default:
+		pr_warn("Unsupported event [0x%x]\n", event);
+		break;
+	}
+}
+
+static int acpi_pad_add(struct acpi_device *device)
+{
+	acpi_status status;
+
+	strcpy(acpi_device_name(device), ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME);
+	strcpy(acpi_device_class(device), ACPI_PROCESSOR_AGGREGATOR_CLASS);
+
+	status = acpi_install_notify_handler(device->handle,
+		ACPI_DEVICE_NOTIFY, acpi_pad_notify, device);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	return 0;
+}
+
+static int acpi_pad_remove(struct acpi_device *device,
+	int type)
+{
+	mutex_lock(&xen_cpu_lock);
+	xen_acpi_pad_idle_cpus(0);
+	mutex_unlock(&xen_cpu_lock);
+
+	acpi_remove_notify_handler(device->handle,
+		ACPI_DEVICE_NOTIFY, acpi_pad_notify);
+	return 0;
+}
+
+static const struct acpi_device_id pad_device_ids[] = {
+	{"ACPI000C", 0},
+	{"", 0},
+};
+
+static struct acpi_driver acpi_pad_driver = {
+	.name = "processor_aggregator",
+	.class = ACPI_PROCESSOR_AGGREGATOR_CLASS,
+	.ids = pad_device_ids,
+	.ops = {
+		.add = acpi_pad_add,
+		.remove = acpi_pad_remove,
+	},
+};
+
+static int __init xen_acpi_pad_init(void)
+{
+	/* Only DOM0 is responsible for Xen acpi pad */
+	if (!xen_initial_domain())
+		return -ENODEV;
+
+	/* Only Xen4.2 or later support Xen acpi pad */
+	if (!xen_running_on_version_or_later(4, 2))
+		return -ENODEV;
+
+	return acpi_bus_register_driver(&acpi_pad_driver);
+}
+subsys_initcall(xen_acpi_pad_init);
diff --git a/include/xen/interface/platform.h b/include/xen/interface/platform.h
index 4755b5fac9c7..5e36932ab407 100644
--- a/include/xen/interface/platform.h
+++ b/include/xen/interface/platform.h
@@ -324,6 +324,22 @@ struct xenpf_cpu_ol {
 };
 DEFINE_GUEST_HANDLE_STRUCT(xenpf_cpu_ol);
 
+/*
+ * CMD 58 and 59 are reserved for cpu hotadd and memory hotadd,
+ * which are already occupied at Xen hypervisor side.
+ */
+#define XENPF_core_parking     60
+struct xenpf_core_parking {
+	/* IN variables */
+#define XEN_CORE_PARKING_SET   1
+#define XEN_CORE_PARKING_GET   2
+	uint32_t type;
+	/* IN variables:  set cpu nums expected to be idled */
+	/* OUT variables: get cpu nums actually be idled */
+	uint32_t idle_nums;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_core_parking);
+
 struct xen_platform_op {
 	uint32_t cmd;
 	uint32_t interface_version; /* XENPF_INTERFACE_VERSION */
@@ -341,6 +357,7 @@ struct xen_platform_op {
 		struct xenpf_set_processor_pminfo set_pminfo;
 		struct xenpf_pcpuinfo          pcpu_info;
 		struct xenpf_cpu_ol            cpu_ol;
+		struct xenpf_core_parking      core_parking;
 		uint8_t                        pad[128];
 	} u;
 };
diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h
index 7ff6498679a3..96d8d3deea6b 100644
--- a/include/xen/interface/version.h
+++ b/include/xen/interface/version.h
@@ -63,4 +63,19 @@ struct xen_feature_info {
 /* arg == xen_domain_handle_t. */
 #define XENVER_guest_handle 8
 
+/* Check if running on Xen version (major, minor) or later */
+static inline bool
+xen_running_on_version_or_later(unsigned int major, unsigned int minor)
+{
+	unsigned int version;
+
+	if (!xen_domain())
+		return false;
+
+	version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
+		((version >> 16) > major))
+		return true;
+	return false;
+}
 #endif /* __XEN_PUBLIC_VERSION_H__ */
-- 
cgit v1.2.3-55-g7522


From 918b4053184c0ca22236e70e299c5343eea35304 Mon Sep 17 00:00:00 2001
From: Vijay Mohan Pandarathil
Date: Sat, 17 Nov 2012 11:47:18 +0000
Subject: PCI/AER: Report success only when every device has AER-aware driver

When an error is detected on a PCIe device which does not have an
AER-aware driver, prevent AER infrastructure from reporting
successful error recovery.

This is because the report_error_detected() function that gets
called in the first phase of recovery process allows forward
progress even when the driver for the device does not have AER
capabilities. It seems that all callbacks (in pci_error_handlers
structure) registered by drivers that gets called during error
recovery are not mandatory. So the intention of the infrastructure
design seems to be to allow forward progress even when a specific
callback has not been registered by a driver. However, if error
handler structure itself has not been registered, it doesn't make
sense to allow forward progress.

As a result of the current design, in the case of a single device
having an AER-unaware driver or in the case of any function in a
multi-function card having an AER-unaware driver, a successful
recovery is reported.

Typical scenario this happens is when a PCI device is detached
from a KVM host and the pci-stub driver on the host claims the
device. The pci-stub driver does not have error handling capabilities
but the AER infrastructure still reports that the device recovered
successfully.

The changes proposed here leaves the device(s)in an unrecovered state
if the driver for the device or for any device in the subtree
does not have error handler structure registered. This reflects
the true state of the device and prevents any partial recovery (or no
recovery at all) reported as successful.

[bhelgaas: changelog]
Signed-off-by: Vijay Mohan Pandarathil <vijaymohan.pandarathil@hp.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Linas Vepstas <linasvepstas@gmail.com>
Reviewed-by: Myron Stowe <myron.stowe@redhat.com>---
 drivers/pci/pcie/aer/aerdrv.h      |  5 ++++-
 drivers/pci/pcie/aer/aerdrv_core.c | 21 ++++++++++++++++++---
 include/linux/pci.h                |  3 +++
 3 files changed, 25 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h
index 94a7598eb262..22f840f4dda1 100644
--- a/drivers/pci/pcie/aer/aerdrv.h
+++ b/drivers/pci/pcie/aer/aerdrv.h
@@ -87,6 +87,9 @@ struct aer_broadcast_data {
 static inline pci_ers_result_t merge_result(enum pci_ers_result orig,
 		enum pci_ers_result new)
 {
+	if (new == PCI_ERS_RESULT_NO_AER_DRIVER)
+		return PCI_ERS_RESULT_NO_AER_DRIVER;
+
 	if (new == PCI_ERS_RESULT_NONE)
 		return orig;
 
@@ -97,7 +100,7 @@ static inline pci_ers_result_t merge_result(enum pci_ers_result orig,
 		break;
 	case PCI_ERS_RESULT_DISCONNECT:
 		if (new == PCI_ERS_RESULT_NEED_RESET)
-			orig = new;
+			orig = PCI_ERS_RESULT_NEED_RESET;
 		break;
 	default:
 		break;
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 06bad96af415..eb2f19a9c3cd 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -231,11 +231,26 @@ static int report_error_detected(struct pci_dev *dev, void *data)
 				   dev->driver ?
 				   "no AER-aware driver" : "no driver");
 		}
-		return 0;
+
+		/*
+		 * If there's any device in the subtree that does not
+		 * have an error_detected callback, returning
+		 * PCI_ERS_RESULT_NO_AER_DRIVER prevents calling of
+		 * the subsequent mmio_enabled/slot_reset/resume
+		 * callbacks of "any" device in the subtree. All the
+		 * devices in the subtree are left in the error state
+		 * without recovery.
+		 */
+
+		if (!(dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
+			vote = PCI_ERS_RESULT_NO_AER_DRIVER;
+		else
+			vote = PCI_ERS_RESULT_NONE;
+	} else {
+		err_handler = dev->driver->err_handler;
+		vote = err_handler->error_detected(dev, result_data->state);
 	}
 
-	err_handler = dev->driver->err_handler;
-	vote = err_handler->error_detected(dev, result_data->state);
 	result_data->result = merge_result(result_data->result, vote);
 	return 0;
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index ee2179546c63..fb7e8699673d 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -538,6 +538,9 @@ enum pci_ers_result {
 
 	/* Device driver is fully recovered and operational */
 	PCI_ERS_RESULT_RECOVERED = (__force pci_ers_result_t) 5,
+
+	/* No AER capabilities registered for the driver */
+	PCI_ERS_RESULT_NO_AER_DRIVER = (__force pci_ers_result_t) 6,
 };
 
 /* PCI bus error event callbacks */
-- 
cgit v1.2.3-55-g7522


From 62a2ab935c8d0f8643d02d3696abc401b5da6206 Mon Sep 17 00:00:00 2001
From: Giuseppe CAVALLARO
Date: Sun, 25 Nov 2012 23:10:43 +0000
Subject: stmmac: add Rx watchdog support to mitigate the DMA irqs

GMAC devices newer than databook 3.40 has an embedded timer
that can be used for mitigating the number of interrupts.
So this patch adds this optimizations.

At any rate, the Rx watchdog can be disable (on bugged HW) by
passing from the platform the riwt_off field.

In this implementation the rx timer stored in the Reg9 is fixed
to the max value. This will be tuned by using ethtool.

V2: added a platform parameter to force to disable the rx-watchdog
for example on new core where it is bugged.

V3: do not disable NAPI when Rx watchdog is used.

V4: a new extra statistic field has been added to show the early
receive status in the interrupt handler.
This patch also adds an extra check to avoid to call
napi_schedule when the DMA_INTR_ENA_RIE bit is disabled in the
Interrupt Mask register.

Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h       | 17 +++++++++---
 drivers/net/ethernet/stmicro/stmmac/dwmac1000.h    |  3 ---
 .../net/ethernet/stmicro/stmmac/dwmac1000_dma.c    |  6 +++++
 drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h    |  5 +++-
 drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c    | 19 +++++++++++---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h       |  2 ++
 .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c   |  9 ++++---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  | 30 +++++++++++++++++-----
 include/linux/stmmac.h                             |  1 +
 9 files changed, 72 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 723e9035f275..186d14806122 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -48,6 +48,10 @@
 #define CHIP_DBG(fmt, args...)  do { } while (0)
 #endif
 
+/* Synopsys Core versions */
+#define	DWMAC_CORE_3_40	0x34
+#define	DWMAC_CORE_3_50	0x35
+
 #undef FRAME_FILTER_DEBUG
 /* #define FRAME_FILTER_DEBUG */
 
@@ -81,7 +85,7 @@ struct stmmac_extra_stats {
 	unsigned long rx_missed_cntr;
 	unsigned long rx_overflow_cntr;
 	unsigned long rx_vlan;
-	/* Tx/Rx IRQ errors */
+	/* Tx/Rx IRQ error info */
 	unsigned long tx_undeflow_irq;
 	unsigned long tx_process_stopped_irq;
 	unsigned long tx_jabber_irq;
@@ -91,7 +95,8 @@ struct stmmac_extra_stats {
 	unsigned long rx_watchdog_irq;
 	unsigned long tx_early_irq;
 	unsigned long fatal_bus_error_irq;
-	/* Extra info */
+	/* Tx/Rx IRQ Events */
+	unsigned long rx_early_irq;
 	unsigned long threshold;
 	unsigned long tx_pkt_n;
 	unsigned long rx_pkt_n;
@@ -101,11 +106,12 @@ struct stmmac_extra_stats {
 	unsigned long tx_normal_irq_n;
 	unsigned long tx_clean;
 	unsigned long tx_reset_ic_bit;
+	unsigned long irq_receive_pmt_irq_n;
+	/* MMC info */
 	unsigned long mmc_tx_irq_n;
 	unsigned long mmc_rx_irq_n;
 	unsigned long mmc_rx_csum_offload_irq_n;
 	/* EEE */
-	unsigned long irq_receive_pmt_irq_n;
 	unsigned long irq_tx_path_in_lpi_mode_n;
 	unsigned long irq_tx_path_exit_lpi_mode_n;
 	unsigned long irq_rx_path_in_lpi_mode_n;
@@ -165,6 +171,9 @@ struct stmmac_extra_stats {
 #define DMA_HW_FEAT_ACTPHYIF	0x70000000 /* Active/selected PHY interface */
 #define DEFAULT_DMA_PBL		8
 
+/* Max/Min RI Watchdog Timer count value */
+#define MAX_DMA_RIWT		0xff
+#define MIN_DMA_RIWT		0x20
 /* Tx coalesce parameters */
 #define STMMAC_COAL_TX_TIMER	40000
 #define STMMAC_MAX_COAL_TX_TICK	100000
@@ -306,6 +315,8 @@ struct stmmac_dma_ops {
 			      struct stmmac_extra_stats *x);
 	/* If supported then get the optional core features */
 	unsigned int (*get_hw_feature) (void __iomem *ioaddr);
+	/* Program the HW RX Watchdog */
+	void (*rx_watchdog) (void __iomem *ioaddr, u32 riwt);
 };
 
 struct stmmac_ops {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index 0e4cacedc1f0..7ad56afd6324 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -230,8 +230,5 @@ enum rtc_control {
 #define GMAC_MMC_TX_INTR   0x108
 #define GMAC_MMC_RX_CSUM_OFFLOAD   0x208
 
-/* Synopsys Core versions */
-#define	DWMAC_CORE_3_40	0x34
-
 extern const struct stmmac_dma_ops dwmac1000_dma_ops;
 #endif /* __DWMAC1000_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index 033500090f55..bf83c03bfd06 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -174,6 +174,11 @@ static unsigned int dwmac1000_get_hw_feature(void __iomem *ioaddr)
 	return readl(ioaddr + DMA_HW_FEATURE);
 }
 
+static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+{
+	writel(riwt, ioaddr + DMA_RX_WATCHDOG);
+}
+
 const struct stmmac_dma_ops dwmac1000_dma_ops = {
 	.init = dwmac1000_dma_init,
 	.dump_regs = dwmac1000_dump_dma_regs,
@@ -187,4 +192,5 @@ const struct stmmac_dma_ops dwmac1000_dma_ops = {
 	.stop_rx = dwmac_dma_stop_rx,
 	.dma_interrupt = dwmac_dma_interrupt,
 	.get_hw_feature = dwmac1000_get_hw_feature,
+	.rx_watchdog = dwmac1000_rx_watchdog,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
index e49c9a0fd6ff..807f30371e49 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -35,7 +35,10 @@
 #define DMA_CONTROL		0x00001018	/* Ctrl (Operational Mode) */
 #define DMA_INTR_ENA		0x0000101c	/* Interrupt Enable */
 #define DMA_MISSED_FRAME_CTR	0x00001020	/* Missed Frame Counter */
-#define DMA_AXI_BUS_MODE       0x00001028      /* AXI Bus Mode */
+/* Rx watchdog register */
+#define DMA_RX_WATCHDOG		0x00001024
+/* AXI Bus Mode */
+#define DMA_AXI_BUS_MODE	0x00001028
 #define DMA_CUR_TX_BUF_ADDR	0x00001050	/* Current Host Tx Buffer */
 #define DMA_CUR_RX_BUF_ADDR	0x00001054	/* Current Host Rx Buffer */
 #define DMA_HW_FEATURE		0x00001058	/* HW Feature Register */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index 73766e655011..491d7e930603 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -204,17 +204,28 @@ int dwmac_dma_interrupt(void __iomem *ioaddr,
 		}
 	}
 	/* TX/RX NORMAL interrupts */
-	if (intr_status & DMA_STATUS_NIS) {
+	if (likely(intr_status & DMA_STATUS_NIS)) {
 		x->normal_irq_n++;
-		if (likely(intr_status & DMA_STATUS_RI))
-			ret |= handle_rx;
-		if (intr_status & (DMA_STATUS_TI))
+		if (likely(intr_status & DMA_STATUS_RI)) {
+			u32 value = readl(ioaddr + DMA_INTR_ENA);
+			/* to schedule NAPI on real RIE event. */
+			if (likely(value & DMA_INTR_ENA_RIE)) {
+				x->rx_normal_irq_n++;
+				ret |= handle_rx;
+			}
+		}
+		if (likely(intr_status & DMA_STATUS_TI)) {
+			x->tx_normal_irq_n++;
 			ret |= handle_tx;
+		}
+		if (unlikely(intr_status & DMA_STATUS_ERI))
+			x->rx_early_irq++;
 	}
 	/* Optional hardware blocks, interrupts should be disabled */
 	if (unlikely(intr_status &
 		     (DMA_STATUS_GPI | DMA_STATUS_GMI | DMA_STATUS_GLI)))
 		pr_info("%s: unexpected status %08x\n", __func__, intr_status);
+
 	/* Clear the interrupt by writing a logic 1 to the CSR5[15-0] */
 	writel((intr_status & 0x1ffff), ioaddr + DMA_STATUS);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 01b34517ca8e..fe0535cd86cd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -91,6 +91,8 @@ struct stmmac_priv {
 	u32 tx_count_frames;
 	u32 tx_coal_frames;
 	u32 tx_coal_timer;
+	int use_riwt;
+	u32 rx_riwt;
 };
 
 extern int phyaddr;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 15cb6ee6ee41..7f7ccd217e4d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -76,7 +76,7 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
 	STMMAC_STAT(rx_missed_cntr),
 	STMMAC_STAT(rx_overflow_cntr),
 	STMMAC_STAT(rx_vlan),
-	/* Tx/Rx IRQ errors */
+	/* Tx/Rx IRQ error info */
 	STMMAC_STAT(tx_undeflow_irq),
 	STMMAC_STAT(tx_process_stopped_irq),
 	STMMAC_STAT(tx_jabber_irq),
@@ -86,7 +86,8 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
 	STMMAC_STAT(rx_watchdog_irq),
 	STMMAC_STAT(tx_early_irq),
 	STMMAC_STAT(fatal_bus_error_irq),
-	/* Extra info */
+	/* Tx/Rx IRQ Events */
+	STMMAC_STAT(rx_early_irq),
 	STMMAC_STAT(threshold),
 	STMMAC_STAT(tx_pkt_n),
 	STMMAC_STAT(rx_pkt_n),
@@ -96,10 +97,12 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
 	STMMAC_STAT(tx_normal_irq_n),
 	STMMAC_STAT(tx_clean),
 	STMMAC_STAT(tx_reset_ic_bit),
+	STMMAC_STAT(irq_receive_pmt_irq_n),
+	/* MMC info */
 	STMMAC_STAT(mmc_tx_irq_n),
 	STMMAC_STAT(mmc_rx_irq_n),
 	STMMAC_STAT(mmc_rx_csum_offload_irq_n),
-	STMMAC_STAT(irq_receive_pmt_irq_n),
+	/* EEE */
 	STMMAC_STAT(irq_tx_path_in_lpi_mode_n),
 	STMMAC_STAT(irq_tx_path_exit_lpi_mode_n),
 	STMMAC_STAT(irq_rx_path_in_lpi_mode_n),
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d9d68649bdaa..542edbcd92c7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -603,6 +603,8 @@ static void init_dma_desc_rings(struct net_device *dev)
 	priv->dirty_tx = 0;
 	priv->cur_tx = 0;
 
+	if (priv->use_riwt)
+		dis_ic = 1;
 	/* Clear the Rx/Tx descriptors */
 	priv->hw->desc->init_rx_desc(priv->dma_rx, rxsize, dis_ic);
 	priv->hw->desc->init_tx_desc(priv->dma_tx, txsize);
@@ -1106,6 +1108,11 @@ static int stmmac_open(struct net_device *dev)
 
 	stmmac_init_tx_coalesce(priv);
 
+	if ((priv->use_riwt) && (priv->hw->dma->rx_watchdog)) {
+		priv->rx_riwt = MAX_DMA_RIWT;
+		priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT);
+	}
+
 	napi_enable(&priv->napi);
 	netif_start_queue(dev);
 
@@ -1423,14 +1430,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 #endif
 			skb->protocol = eth_type_trans(skb, priv->dev);
 
-			if (unlikely(!priv->plat->rx_coe)) {
-				/* No RX COE for old mac10/100 devices */
+			if (unlikely(!priv->plat->rx_coe))
 				skb_checksum_none_assert(skb);
-				netif_receive_skb(skb);
-			} else {
+			else
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
-				napi_gro_receive(&priv->napi, skb);
-			}
+
+			napi_gro_receive(&priv->napi, skb);
 
 			priv->dev->stats.rx_packets++;
 			priv->dev->stats.rx_bytes += frame_len;
@@ -2001,6 +2006,16 @@ struct stmmac_priv *stmmac_dvr_probe(struct device *device,
 	if (flow_ctrl)
 		priv->flow_ctrl = FLOW_AUTO;	/* RX/TX pause on */
 
+	/* Rx Watchdog is available in the COREs newer than the 3.40.
+	 * In some case, for example on bugged HW this feature
+	 * has to be disable and this can be done by passing the
+	 * riwt_off field from the platform.
+	 */
+	if ((priv->synopsys_id >= DWMAC_CORE_3_50) && (!priv->plat->riwt_off)) {
+		priv->use_riwt = 1;
+		pr_info(" Enable RX Mitigation via HW Watchdog Timer\n");
+	}
+
 	netif_napi_add(ndev, &priv->napi, stmmac_poll, 64);
 
 	spin_lock_init(&priv->lock);
@@ -2092,6 +2107,9 @@ int stmmac_suspend(struct net_device *ndev)
 	netif_device_detach(ndev);
 	netif_stop_queue(ndev);
 
+	if (priv->use_riwt)
+		dis_ic = 1;
+
 	napi_disable(&priv->napi);
 
 	/* Stop TX/RX DMA */
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index a1547ea3920d..de5b2f8176ce 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -104,6 +104,7 @@ struct plat_stmmacenet_data {
 	int bugged_jumbo;
 	int pmt;
 	int force_sf_dma_mode;
+	int riwt_off;
 	void (*fix_mac_speed)(void *priv, unsigned int speed);
 	void (*bus_setup)(void __iomem *ioaddr);
 	int (*init)(struct platform_device *pdev);
-- 
cgit v1.2.3-55-g7522


From c91f6df2db4972d3cc983e6988b9abf1ad02f5f9 Mon Sep 17 00:00:00 2001
From: Brian Haley
Date: Mon, 26 Nov 2012 05:21:08 +0000
Subject: sockopt: Change getsockopt() of SO_BINDTODEVICE to return an
 interface name

Instead of having the getsockopt() of SO_BINDTODEVICE return an index, which
will then require another call like if_indextoname() to get the actual interface
name, have it return the name directly.

This also matches the existing man page description on socket(7) which mentions
the argument being an interface name.

If the value has not been set, zero is returned and optlen will be set to zero
to indicate there is no interface name present.

Added a seqlock to protect this code path, and dev_ifname(), from someone
changing the device name via dev_change_name().

v2: Added seqlock protection while copying device name.

v3: Fixed word wrap in patch.

Signed-off-by: Brian Haley <brian.haley@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            | 21 ++++++++++++++--
 net/core/sock.c           | 64 ++++++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 81 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e46c830c88d8..e9929abeb932 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1567,6 +1567,8 @@ extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
 
 extern rwlock_t				dev_base_lock;		/* Device list lock */
 
+extern seqlock_t	devnet_rename_seq;	/* Device rename lock */
+
 
 #define for_each_netdev(net, d)		\
 		list_for_each_entry(d, &(net)->dev_base_head, dev_list)
diff --git a/net/core/dev.c b/net/core/dev.c
index 7304ea8a1f13..2a5f55866429 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -203,6 +203,8 @@ static struct list_head offload_base __read_mostly;
 DEFINE_RWLOCK(dev_base_lock);
 EXPORT_SYMBOL(dev_base_lock);
 
+DEFINE_SEQLOCK(devnet_rename_seq);
+
 static inline void dev_base_seq_inc(struct net *net)
 {
 	while (++net->dev_base_seq == 0);
@@ -1091,22 +1093,31 @@ int dev_change_name(struct net_device *dev, const char *newname)
 	if (dev->flags & IFF_UP)
 		return -EBUSY;
 
-	if (strncmp(newname, dev->name, IFNAMSIZ) == 0)
+	write_seqlock(&devnet_rename_seq);
+
+	if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
+		write_sequnlock(&devnet_rename_seq);
 		return 0;
+	}
 
 	memcpy(oldname, dev->name, IFNAMSIZ);
 
 	err = dev_get_valid_name(net, dev, newname);
-	if (err < 0)
+	if (err < 0) {
+		write_sequnlock(&devnet_rename_seq);
 		return err;
+	}
 
 rollback:
 	ret = device_rename(&dev->dev, dev->name);
 	if (ret) {
 		memcpy(dev->name, oldname, IFNAMSIZ);
+		write_sequnlock(&devnet_rename_seq);
 		return ret;
 	}
 
+	write_sequnlock(&devnet_rename_seq);
+
 	write_lock_bh(&dev_base_lock);
 	hlist_del_rcu(&dev->name_hlist);
 	write_unlock_bh(&dev_base_lock);
@@ -1124,6 +1135,7 @@ rollback:
 		/* err >= 0 after dev_alloc_name() or stores the first errno */
 		if (err >= 0) {
 			err = ret;
+			write_seqlock(&devnet_rename_seq);
 			memcpy(dev->name, oldname, IFNAMSIZ);
 			goto rollback;
 		} else {
@@ -4148,6 +4160,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
 {
 	struct net_device *dev;
 	struct ifreq ifr;
+	unsigned seq;
 
 	/*
 	 *	Fetch the caller's info block.
@@ -4156,6 +4169,8 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
 	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
 		return -EFAULT;
 
+retry:
+	seq = read_seqbegin(&devnet_rename_seq);
 	rcu_read_lock();
 	dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex);
 	if (!dev) {
@@ -4165,6 +4180,8 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
 
 	strcpy(ifr.ifr_name, dev->name);
 	rcu_read_unlock();
+	if (read_seqretry(&devnet_rename_seq, seq))
+		goto retry;
 
 	if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
 		return -EFAULT;
diff --git a/net/core/sock.c b/net/core/sock.c
index d4f7b58b3866..a692ef49c9bb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -505,7 +505,8 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
 }
 EXPORT_SYMBOL(sk_dst_check);
 
-static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen)
+static int sock_setbindtodevice(struct sock *sk, char __user *optval,
+				int optlen)
 {
 	int ret = -ENOPROTOOPT;
 #ifdef CONFIG_NETDEVICES
@@ -562,6 +563,59 @@ out:
 	return ret;
 }
 
+static int sock_getbindtodevice(struct sock *sk, char __user *optval,
+				int __user *optlen, int len)
+{
+	int ret = -ENOPROTOOPT;
+#ifdef CONFIG_NETDEVICES
+	struct net *net = sock_net(sk);
+	struct net_device *dev;
+	char devname[IFNAMSIZ];
+	unsigned seq;
+
+	if (sk->sk_bound_dev_if == 0) {
+		len = 0;
+		goto zero;
+	}
+
+	ret = -EINVAL;
+	if (len < IFNAMSIZ)
+		goto out;
+
+retry:
+	seq = read_seqbegin(&devnet_rename_seq);
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
+	ret = -ENODEV;
+	if (!dev) {
+		rcu_read_unlock();
+		goto out;
+	}
+
+	strcpy(devname, dev->name);
+	rcu_read_unlock();
+	if (read_seqretry(&devnet_rename_seq, seq))
+		goto retry;
+
+	len = strlen(devname) + 1;
+
+	ret = -EFAULT;
+	if (copy_to_user(optval, devname, len))
+		goto out;
+
+zero:
+	ret = -EFAULT;
+	if (put_user(len, optlen))
+		goto out;
+
+	ret = 0;
+
+out:
+#endif
+
+	return ret;
+}
+
 static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
 {
 	if (valbool)
@@ -589,7 +643,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 	 */
 
 	if (optname == SO_BINDTODEVICE)
-		return sock_bindtodevice(sk, optval, optlen);
+		return sock_setbindtodevice(sk, optval, optlen);
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
@@ -1075,15 +1129,17 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 	case SO_NOFCS:
 		v.val = sock_flag(sk, SOCK_NOFCS);
 		break;
+
 	case SO_BINDTODEVICE:
-		v.val = sk->sk_bound_dev_if;
-		break;
+		return sock_getbindtodevice(sk, optval, optlen, len);
+
 	case SO_GET_FILTER:
 		len = sk_get_filter(sk, (struct sock_filter __user *)optval, len);
 		if (len < 0)
 			return len;
 
 		goto lenout;
+
 	default:
 		return -ENOPROTOOPT;
 	}
-- 
cgit v1.2.3-55-g7522


From a8df7b1ab70bfd6f261fa5e96985fca638299acc Mon Sep 17 00:00:00 2001
From: Fabio Baltieri
Date: Sun, 4 Nov 2012 01:54:34 -0800
Subject: leds: add led_trigger_rename function

Implements a "led_trigger_rename" function to rename a trigger with
proper locking.

This assumes that led name was originally allocated in non-constant
storage.

Signed-off-by: Fabio Baltieri <fabio.baltieri@gmail.com>
Cc: Kurt Van Dijck <kurt.van.dijck@eia.be>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
---
 drivers/leds/led-triggers.c | 13 +++++++++++++
 include/linux/leds.h        | 18 ++++++++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index 262eb4193710..a4fa4bf02d53 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -166,6 +166,19 @@ void led_trigger_set_default(struct led_classdev *led_cdev)
 }
 EXPORT_SYMBOL_GPL(led_trigger_set_default);
 
+void led_trigger_rename_static(const char *name, struct led_trigger *trig)
+{
+	/* new name must be on a temporary string to prevent races */
+	BUG_ON(name == trig->name);
+
+	down_write(&triggers_list_lock);
+	/* this assumes that trig->name was originaly allocated to
+	 * non constant storage */
+	strcpy((char *)trig->name, name);
+	up_write(&triggers_list_lock);
+}
+EXPORT_SYMBOL_GPL(led_trigger_rename_static);
+
 /* LED Trigger Interface */
 
 int led_trigger_register(struct led_trigger *trig)
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 6e53bb31c220..8107592cfc41 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -139,6 +139,24 @@ extern void led_blink_set_oneshot(struct led_classdev *led_cdev,
 extern void led_set_brightness(struct led_classdev *led_cdev,
 			       enum led_brightness brightness);
 
+/**
+ * led_trigger_rename_static - rename a trigger
+ * @name: the new trigger name
+ * @trig: the LED trigger to rename
+ *
+ * Change a LED trigger name by copying the string passed in
+ * name into current trigger name, which MUST be large
+ * enough for the new string.
+ *
+ * Note that name must NOT point to the same string used
+ * during LED registration, as that could lead to races.
+ *
+ * This is meant to be used on triggers with statically
+ * allocated name.
+ */
+extern void led_trigger_rename_static(const char *name,
+				      struct led_trigger *trig);
+
 /*
  * LED Triggers
  */
-- 
cgit v1.2.3-55-g7522


From 057407c732b7761cf417a1e6633a02d9d473340d Mon Sep 17 00:00:00 2001
From: Jingoo Han
Date: Sun, 18 Nov 2012 21:35:55 -0800
Subject: led: Add dependency on CONFIG_LEDS_TRIGGERS to
 led_trigger_rename_static()

This patch fixes build warnings when CONFIG_LEDS_TRIGGERS is
disabled as below:
include/linux/leds.h:158:18: warning: 'struct led_trigger' declared inside parameter list [enabled by default]
include/linux/leds.h:158:18: warning: its scope is only this definition or declaration, which is probably not what you want [enabled
by default]

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Acked-by: Fabio Baltieri <fabio.baltieri@gmail.com>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
---
 include/linux/leds.h | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/leds.h b/include/linux/leds.h
index 8107592cfc41..0d9b5eed714e 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -139,24 +139,6 @@ extern void led_blink_set_oneshot(struct led_classdev *led_cdev,
 extern void led_set_brightness(struct led_classdev *led_cdev,
 			       enum led_brightness brightness);
 
-/**
- * led_trigger_rename_static - rename a trigger
- * @name: the new trigger name
- * @trig: the LED trigger to rename
- *
- * Change a LED trigger name by copying the string passed in
- * name into current trigger name, which MUST be large
- * enough for the new string.
- *
- * Note that name must NOT point to the same string used
- * during LED registration, as that could lead to races.
- *
- * This is meant to be used on triggers with statically
- * allocated name.
- */
-extern void led_trigger_rename_static(const char *name,
-				      struct led_trigger *trig);
-
 /*
  * LED Triggers
  */
@@ -197,6 +179,23 @@ extern void led_trigger_blink_oneshot(struct led_trigger *trigger,
 				      unsigned long *delay_on,
 				      unsigned long *delay_off,
 				      int invert);
+/**
+ * led_trigger_rename_static - rename a trigger
+ * @name: the new trigger name
+ * @trig: the LED trigger to rename
+ *
+ * Change a LED trigger name by copying the string passed in
+ * name into current trigger name, which MUST be large
+ * enough for the new string.
+ *
+ * Note that name must NOT point to the same string used
+ * during LED registration, as that could lead to races.
+ *
+ * This is meant to be used on triggers with statically
+ * allocated name.
+ */
+extern void led_trigger_rename_static(const char *name,
+				      struct led_trigger *trig);
 
 #else
 
-- 
cgit v1.2.3-55-g7522


From e3725ec015dfbbeb896295cf2b3a995f28b0630e Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Fri, 16 Nov 2012 12:25:01 -0500
Subject: NFSv4.1: Shrink struct nfs4_sequence_res by moving the session
 pointer

Move the session pointer into the slot table, then have struct nfs4_slot
point to that slot table.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4_fs.h          |  3 ++-
 fs/nfs/nfs4proc.c         | 33 +++++++++++++++++++++++----------
 fs/nfs/nfs4state.c        |  2 +-
 fs/nfs/nfs4xdr.c          |  8 +++++---
 include/linux/nfs_fs_sb.h |  1 +
 include/linux/nfs_xdr.h   |  2 +-
 6 files changed, 33 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 36880b9aa91e..42c58691fb41 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -258,7 +258,8 @@ extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
 extern int nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data,
 				  bool sync);
 
-extern struct nfs4_slot *nfs4_alloc_slots(u32 max_slots, gfp_t gfp_flags);
+extern struct nfs4_slot *nfs4_alloc_slots(struct nfs4_slot_table *table,
+		u32 max_slots, gfp_t gfp_flags);
 
 static inline bool
 is_ds_only_client(struct nfs_client *clp)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 14b39742b6e4..5b61c4a83191 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -467,25 +467,28 @@ void nfs4_check_drain_bc_complete(struct nfs4_session *ses)
 
 static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 {
+	struct nfs4_session *session;
 	struct nfs4_slot_table *tbl;
 
-	tbl = &res->sr_session->fc_slot_table;
 	if (!res->sr_slot) {
 		/* just wake up the next guy waiting since
 		 * we may have not consumed a slot after all */
 		dprintk("%s: No slot\n", __func__);
 		return;
 	}
+	tbl = res->sr_slot->table;
+	session = tbl->session;
 
 	spin_lock(&tbl->slot_tbl_lock);
 	nfs4_free_slot(tbl, res->sr_slot - tbl->slots);
-	nfs4_check_drain_fc_complete(res->sr_session);
+	nfs4_check_drain_fc_complete(session);
 	spin_unlock(&tbl->slot_tbl_lock);
 	res->sr_slot = NULL;
 }
 
 static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
+	struct nfs4_session *session;
 	struct nfs4_slot *slot;
 	unsigned long timestamp;
 	struct nfs_client *clp;
@@ -504,6 +507,7 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 		goto out;
 
 	slot = res->sr_slot;
+	session = slot->table->session;
 
 	/* Check the SEQUENCE operation status */
 	switch (res->sr_status) {
@@ -511,7 +515,7 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 		/* Update the slot's sequence and clientid lease timer */
 		++slot->seq_nr;
 		timestamp = slot->renewal_time;
-		clp = res->sr_session->clp;
+		clp = session->clp;
 		do_renew_lease(clp, timestamp);
 		/* Check sequence flags */
 		if (res->sr_status_flags != 0)
@@ -524,7 +528,7 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 		 */
 		dprintk("%s: slot=%td seq=%d: Operation in progress\n",
 			__func__,
-			slot - res->sr_session->fc_slot_table.slots,
+			slot - session->fc_slot_table.slots,
 			slot->seq_nr);
 		goto out_retry;
 	default:
@@ -546,7 +550,7 @@ out_retry:
 static int nfs4_sequence_done(struct rpc_task *task,
 			       struct nfs4_sequence_res *res)
 {
-	if (res->sr_session == NULL)
+	if (res->sr_slot == NULL)
 		return 1;
 	return nfs41_sequence_done(task, res);
 }
@@ -591,7 +595,6 @@ static void nfs41_init_sequence(struct nfs4_sequence_args *args,
 	args->sa_cache_this = 0;
 	if (cache_reply)
 		args->sa_cache_this = 1;
-	res->sr_session = NULL;
 	res->sr_slot = NULL;
 }
 
@@ -646,7 +649,6 @@ int nfs41_setup_sequence(struct nfs4_session *session,
 
 	dprintk("<-- %s slotid=%d seqid=%d\n", __func__, slotid, slot->seq_nr);
 
-	res->sr_session = session;
 	res->sr_slot = slot;
 	res->sr_status_flags = 0;
 	/*
@@ -5659,9 +5661,18 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
 	return status;
 }
 
-struct nfs4_slot *nfs4_alloc_slots(u32 max_slots, gfp_t gfp_flags)
+struct nfs4_slot *nfs4_alloc_slots(struct nfs4_slot_table *table,
+		u32 max_slots, gfp_t gfp_flags)
 {
-	return kmalloc_array(max_slots, sizeof(struct nfs4_slot), gfp_flags);
+	struct nfs4_slot *tbl;
+	u32 i;
+
+	tbl = kmalloc_array(max_slots, sizeof(*tbl), gfp_flags);
+	if (tbl != NULL) {
+		for (i = 0; i < max_slots; i++)
+			tbl[i].table = table;
+	}
+	return tbl;
 }
 
 static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl,
@@ -5699,7 +5710,7 @@ static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl, u32 max_reqs,
 
 	/* Does the newly negotiated max_reqs match the existing slot table? */
 	if (max_reqs != tbl->max_slots) {
-		new = nfs4_alloc_slots(max_reqs, GFP_NOFS);
+		new = nfs4_alloc_slots(tbl, max_reqs, GFP_NOFS);
 		if (!new)
 			goto out;
 	}
@@ -5738,11 +5749,13 @@ static int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
 	dprintk("--> %s\n", __func__);
 	/* Fore channel */
 	tbl = &ses->fc_slot_table;
+	tbl->session = ses;
 	status = nfs4_realloc_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
 	if (status) /* -ENOMEM */
 		return status;
 	/* Back channel */
 	tbl = &ses->bc_slot_table;
+	tbl->session = ses;
 	status = nfs4_realloc_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
 	if (status && tbl->slots == NULL)
 		/* Fore and back channel share a connection so get
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 96fcbb97fd6a..9495789c425b 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2033,7 +2033,7 @@ static int nfs4_recall_slot(struct nfs_client *clp)
 		return 0;
 	nfs4_begin_drain_session(clp);
 	fc_tbl = &clp->cl_session->fc_slot_table;
-	new = nfs4_alloc_slots(fc_tbl->target_max_slots, GFP_NOFS);
+	new = nfs4_alloc_slots(fc_tbl, fc_tbl->target_max_slots, GFP_NOFS);
         if (!new)
 		return -ENOMEM;
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 672d9b0ef2c5..4126f054610a 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -5507,12 +5507,13 @@ static int decode_sequence(struct xdr_stream *xdr,
 			   struct rpc_rqst *rqstp)
 {
 #if defined(CONFIG_NFS_V4_1)
+	struct nfs4_session *session;
 	struct nfs4_sessionid id;
 	u32 dummy;
 	int status;
 	__be32 *p;
 
-	if (!res->sr_session)
+	if (res->sr_slot == NULL)
 		return 0;
 
 	status = decode_op_hdr(xdr, OP_SEQUENCE);
@@ -5526,8 +5527,9 @@ static int decode_sequence(struct xdr_stream *xdr,
 	 * sequence number, the server is looney tunes.
 	 */
 	status = -EREMOTEIO;
+	session = res->sr_slot->table->session;
 
-	if (memcmp(id.data, res->sr_session->sess_id.data,
+	if (memcmp(id.data, session->sess_id.data,
 		   NFS4_MAX_SESSIONID_LEN)) {
 		dprintk("%s Invalid session id\n", __func__);
 		goto out_err;
@@ -5545,7 +5547,7 @@ static int decode_sequence(struct xdr_stream *xdr,
 	}
 	/* slot id */
 	dummy = be32_to_cpup(p++);
-	if (dummy != res->sr_slot - res->sr_session->fc_slot_table.slots) {
+	if (dummy != res->sr_slot - session->fc_slot_table.slots) {
 		dprintk("%s Invalid slot id\n", __func__);
 		goto out_err;
 	}
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 97c8f9191880..b0412873d29c 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -209,6 +209,7 @@ struct nfs_server {
 /* Sessions */
 #define SLOT_TABLE_SZ DIV_ROUND_UP(NFS4_MAX_SLOT_TABLE, 8*sizeof(long))
 struct nfs4_slot_table {
+	struct nfs4_session *session;		/* Parent session */
 	struct nfs4_slot *slots;		/* seqid per slot */
 	unsigned long   used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */
 	spinlock_t	slot_tbl_lock;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9cb1c63a70c2..0fd88ab0e814 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -187,6 +187,7 @@ struct nfs4_channel_attrs {
 
 /* nfs41 sessions slot seqid */
 struct nfs4_slot {
+	struct nfs4_slot_table	*table;
 	unsigned long		renewal_time;
 	u32		 	seq_nr;
 };
@@ -198,7 +199,6 @@ struct nfs4_sequence_args {
 };
 
 struct nfs4_sequence_res {
-	struct nfs4_session	*sr_session;
 	struct nfs4_slot	*sr_slot;	/* slot used to send request */
 	int			sr_status;	/* sequence operation status */
 	u32			sr_status_flags;
-- 
cgit v1.2.3-55-g7522


From df2fabffbace8988f3265585ec793ff9deccdea7 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Fri, 16 Nov 2012 12:45:06 -0500
Subject: NFSv4.1: Label each entry in the session slot tables with its slot
 number

Instead of doing slot table pointer gymnastics every time we want to
know which slot we're using.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       | 12 +++++++-----
 fs/nfs/nfs4xdr.c        |  2 +-
 include/linux/nfs_xdr.h |  1 +
 3 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5b61c4a83191..4311dba49c58 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -526,9 +526,9 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 		 * returned NFS4ERR_DELAY as per Section 2.10.6.2
 		 * of RFC5661.
 		 */
-		dprintk("%s: slot=%td seq=%d: Operation in progress\n",
+		dprintk("%s: slot=%u seq=%u: Operation in progress\n",
 			__func__,
-			slot - session->fc_slot_table.slots,
+			slot->slot_nr,
 			slot->seq_nr);
 		goto out_retry;
 	default:
@@ -671,9 +671,9 @@ int nfs4_setup_sequence(const struct nfs_server *server,
 	if (session == NULL)
 		goto out;
 
-	dprintk("--> %s clp %p session %p sr_slot %td\n",
+	dprintk("--> %s clp %p session %p sr_slot %d\n",
 		__func__, session->clp, session, res->sr_slot ?
-			res->sr_slot - session->fc_slot_table.slots : -1);
+			res->sr_slot->slot_nr : -1);
 
 	ret = nfs41_setup_sequence(session, args, res, task);
 out:
@@ -5669,8 +5669,10 @@ struct nfs4_slot *nfs4_alloc_slots(struct nfs4_slot_table *table,
 
 	tbl = kmalloc_array(max_slots, sizeof(*tbl), gfp_flags);
 	if (tbl != NULL) {
-		for (i = 0; i < max_slots; i++)
+		for (i = 0; i < max_slots; i++) {
 			tbl[i].table = table;
+			tbl[i].slot_nr = i;
+		}
 	}
 	return tbl;
 }
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 4126f054610a..50bac7066160 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -5547,7 +5547,7 @@ static int decode_sequence(struct xdr_stream *xdr,
 	}
 	/* slot id */
 	dummy = be32_to_cpup(p++);
-	if (dummy != res->sr_slot - session->fc_slot_table.slots) {
+	if (dummy != res->sr_slot->slot_nr) {
 		dprintk("%s Invalid slot id\n", __func__);
 		goto out_err;
 	}
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 0fd88ab0e814..9c9b76c94b46 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -189,6 +189,7 @@ struct nfs4_channel_attrs {
 struct nfs4_slot {
 	struct nfs4_slot_table	*table;
 	unsigned long		renewal_time;
+	u32			slot_nr;
 	u32		 	seq_nr;
 };
 
-- 
cgit v1.2.3-55-g7522


From 2b2fa71723f955d5b4a0f4edd99cf3cd69ceafd1 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Fri, 16 Nov 2012 12:58:36 -0500
Subject: NFSv4.1: Simplify struct nfs4_sequence_args too

Replace the session pointer + slotid with a pointer to the
allocated slot.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       |  6 +++---
 fs/nfs/nfs4xdr.c        | 21 ++++++++++-----------
 include/linux/nfs_xdr.h |  3 +--
 3 files changed, 14 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4311dba49c58..6c41a34e34b4 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -591,7 +591,7 @@ out:
 static void nfs41_init_sequence(struct nfs4_sequence_args *args,
 		struct nfs4_sequence_res *res, int cache_reply)
 {
-	args->sa_session = NULL;
+	args->sa_slot = NULL;
 	args->sa_cache_this = 0;
 	if (cache_reply)
 		args->sa_cache_this = 1;
@@ -644,8 +644,8 @@ int nfs41_setup_sequence(struct nfs4_session *session,
 	rpc_task_set_priority(task, RPC_PRIORITY_NORMAL);
 	slot = tbl->slots + slotid;
 	slot->renewal_time = jiffies;
-	args->sa_session = session;
-	args->sa_slotid = slotid;
+
+	args->sa_slot = slot;
 
 	dprintk("<-- %s slotid=%d seqid=%d\n", __func__, slotid, slot->seq_nr);
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 50bac7066160..27b0fec1a6b0 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1833,18 +1833,16 @@ static void encode_sequence(struct xdr_stream *xdr,
 			    struct compound_hdr *hdr)
 {
 #if defined(CONFIG_NFS_V4_1)
-	struct nfs4_session *session = args->sa_session;
+	struct nfs4_session *session;
 	struct nfs4_slot_table *tp;
-	struct nfs4_slot *slot;
+	struct nfs4_slot *slot = args->sa_slot;
 	__be32 *p;
 
-	if (!session)
+	if (slot == NULL)
 		return;
 
-	tp = &session->fc_slot_table;
-
-	WARN_ON(args->sa_slotid == NFS4_MAX_SLOT_TABLE);
-	slot = tp->slots + args->sa_slotid;
+	tp = slot->table;
+	session = tp->session;
 
 	encode_op_hdr(xdr, OP_SEQUENCE, decode_sequence_maxsz, hdr);
 
@@ -1858,12 +1856,12 @@ static void encode_sequence(struct xdr_stream *xdr,
 		((u32 *)session->sess_id.data)[1],
 		((u32 *)session->sess_id.data)[2],
 		((u32 *)session->sess_id.data)[3],
-		slot->seq_nr, args->sa_slotid,
+		slot->seq_nr, slot->slot_nr,
 		tp->highest_used_slotid, args->sa_cache_this);
 	p = reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 16);
 	p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
 	*p++ = cpu_to_be32(slot->seq_nr);
-	*p++ = cpu_to_be32(args->sa_slotid);
+	*p++ = cpu_to_be32(slot->slot_nr);
 	*p++ = cpu_to_be32(tp->highest_used_slotid);
 	*p = cpu_to_be32(args->sa_cache_this);
 #endif /* CONFIG_NFS_V4_1 */
@@ -2025,8 +2023,9 @@ static void encode_free_stateid(struct xdr_stream *xdr,
 static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args)
 {
 #if defined(CONFIG_NFS_V4_1)
-	if (args->sa_session)
-		return args->sa_session->clp->cl_mvops->minor_version;
+
+	if (args->sa_slot)
+		return args->sa_slot->table->session->clp->cl_mvops->minor_version;
 #endif /* CONFIG_NFS_V4_1 */
 	return 0;
 }
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9c9b76c94b46..deb31bbbb857 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -194,8 +194,7 @@ struct nfs4_slot {
 };
 
 struct nfs4_sequence_args {
-	struct nfs4_session	*sa_session;
-	u32			sa_slotid;
+	struct nfs4_slot	*sa_slot;
 	u8			sa_cache_this;
 };
 
-- 
cgit v1.2.3-55-g7522


From d80a361d779a9f19498943d1ca84243209cd5647 Mon Sep 17 00:00:00 2001
From: Seiji Aguchi
Date: Wed, 14 Nov 2012 20:25:37 +0000
Subject: efi_pstore: Check remaining space with QueryVariableInfo() before
 writing data

[Issue]

As discussed in a thread below, Running out of space in EFI isn't a well-tested scenario.
And we wouldn't expect all firmware to handle it gracefully.
http://marc.info/?l=linux-kernel&m=134305325801789&w=2

On the other hand, current efi_pstore doesn't check a remaining space of storage at writing time.
Therefore, efi_pstore may not work if it tries to write a large amount of data.

[Patch Description]

To avoid handling the situation above, this patch checks if there is a space enough to log with
QueryVariableInfo() before writing data.

Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com>
Acked-by: Mike Waychison <mikew@google.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 drivers/firmware/efivars.c | 18 ++++++++++++++++++
 include/linux/efi.h        |  1 +
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index d10c9873dd9a..37ac21a08751 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -707,12 +707,29 @@ static int efi_pstore_write(enum pstore_type_id type,
 	struct efivars *efivars = psi->data;
 	struct efivar_entry *entry, *found = NULL;
 	int i, ret = 0;
+	u64 storage_space, remaining_space, max_variable_size;
+	efi_status_t status = EFI_NOT_FOUND;
 
 	sprintf(stub_name, "dump-type%u-%u-", type, part);
 	sprintf(name, "%s%lu", stub_name, get_seconds());
 
 	spin_lock(&efivars->lock);
 
+	/*
+	 * Check if there is a space enough to log.
+	 * size: a size of logging data
+	 * DUMP_NAME_LEN * 2: a maximum size of variable name
+	 */
+	status = efivars->ops->query_variable_info(PSTORE_EFI_ATTRIBUTES,
+						   &storage_space,
+						   &remaining_space,
+						   &max_variable_size);
+	if (status || remaining_space < size + DUMP_NAME_LEN * 2) {
+		spin_unlock(&efivars->lock);
+		*id = part;
+		return -ENOSPC;
+	}
+
 	for (i = 0; i < DUMP_NAME_LEN; i++)
 		efi_name[i] = stub_name[i];
 
@@ -1237,6 +1254,7 @@ efivars_init(void)
 	ops.get_variable = efi.get_variable;
 	ops.set_variable = efi.set_variable;
 	ops.get_next_variable = efi.get_next_variable;
+	ops.query_variable_info = efi.query_variable_info;
 	error = register_efivars(&__efivars, &ops, efi_kobj);
 	if (error)
 		goto err_put;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 8670eb1eb8cd..c47ec36f3f39 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -643,6 +643,7 @@ struct efivar_operations {
 	efi_get_variable_t *get_variable;
 	efi_get_next_variable_t *get_next_variable;
 	efi_set_variable_t *set_variable;
+	efi_query_variable_info_t *query_variable_info;
 };
 
 struct efivars {
-- 
cgit v1.2.3-55-g7522


From a9efd39cd547223597cfe7c53acec44c099b9264 Mon Sep 17 00:00:00 2001
From: Seiji Aguchi
Date: Wed, 14 Nov 2012 20:27:28 +0000
Subject: efi_pstore: Add ctime to argument of erase callback

[Issue]

Currently, a variable name, which is used to identify each log entry, consists of type,
id and ctime. But an erase callback does not use ctime.

If efi_pstore supported just one log, type and id were enough.
However, in case of supporting multiple logs, it doesn't work because
it can't distinguish each entry without ctime at erasing time.

 <Example>

 As you can see below, efi_pstore can't differentiate first event from second one without ctime.

 a variable name of first event: dump-type0-1-12345678
 a variable name of second event: dump-type0-1-23456789

  type:0
  id:1
  ctime:12345678, 23456789

[Solution]

This patch adds ctime to an argument of an erase callback.

It works across reboots because ctime of pstore means the date that the record was originally stored.
To do this, efi_pstore saves the ctime to variable name at writing time and passes it to pstore
at reading time.

Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com>
Acked-by: Mike Waychison <mikew@google.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 drivers/acpi/apei/erst.c   |  4 ++--
 drivers/firmware/efivars.c | 17 ++++++++---------
 fs/pstore/inode.c          |  3 ++-
 fs/pstore/ram.c            |  2 +-
 include/linux/pstore.h     |  2 +-
 5 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index e4d9d24eb73d..0bd6ae4a899f 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -938,7 +938,7 @@ static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
 		       u64 *id, unsigned int part,
 		       size_t size, struct pstore_info *psi);
 static int erst_clearer(enum pstore_type_id type, u64 id,
-			struct pstore_info *psi);
+			struct timespec time, struct pstore_info *psi);
 
 static struct pstore_info erst_info = {
 	.owner		= THIS_MODULE,
@@ -1102,7 +1102,7 @@ static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
 }
 
 static int erst_clearer(enum pstore_type_id type, u64 id,
-			struct pstore_info *psi)
+			struct timespec time, struct pstore_info *psi)
 {
 	return erst_clear(id);
 }
diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index fbe9202c2678..3803621c0d45 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -747,24 +747,25 @@ static int efi_pstore_write(enum pstore_type_id type,
 };
 
 static int efi_pstore_erase(enum pstore_type_id type, u64 id,
-			    struct pstore_info *psi)
+			    struct timespec time, struct pstore_info *psi)
 {
-	char stub_name[DUMP_NAME_LEN];
+	char name[DUMP_NAME_LEN];
 	efi_char16_t efi_name[DUMP_NAME_LEN];
 	efi_guid_t vendor = LINUX_EFI_CRASH_GUID;
 	struct efivars *efivars = psi->data;
 	struct efivar_entry *entry, *found = NULL;
 	int i;
 
-	sprintf(stub_name, "dump-type%u-%u-", type, (unsigned int)id);
+	sprintf(name, "dump-type%u-%u-%lu", type, (unsigned int)id,
+		time.tv_sec);
 
 	spin_lock(&efivars->lock);
 
 	for (i = 0; i < DUMP_NAME_LEN; i++)
-		efi_name[i] = stub_name[i];
+		efi_name[i] = name[i];
 
 	/*
-	 * Clean up any entries with the same name
+	 * Clean up an entry with the same name
 	 */
 
 	list_for_each_entry(entry, &efivars->list, list) {
@@ -775,9 +776,6 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id,
 		if (utf16_strncmp(entry->var.VariableName, efi_name,
 				  utf16_strlen(efi_name)))
 			continue;
-		/* Needs to be a prefix */
-		if (entry->var.VariableName[utf16_strlen(efi_name)] == 0)
-			continue;
 
 		/* found */
 		found = entry;
@@ -785,6 +783,7 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id,
 					   &entry->var.VendorGuid,
 					   PSTORE_EFI_ATTRIBUTES,
 					   0, NULL);
+		break;
 	}
 
 	if (found)
@@ -823,7 +822,7 @@ static int efi_pstore_write(enum pstore_type_id type,
 }
 
 static int efi_pstore_erase(enum pstore_type_id type, u64 id,
-			    struct pstore_info *psi)
+			    struct timespec time, struct pstore_info *psi)
 {
 	return 0;
 }
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 4ab572e6d277..4300af654710 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -175,7 +175,8 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry)
 	struct pstore_private *p = dentry->d_inode->i_private;
 
 	if (p->psi->erase)
-		p->psi->erase(p->type, p->id, p->psi);
+		p->psi->erase(p->type, p->id, dentry->d_inode->i_ctime,
+			      p->psi);
 
 	return simple_unlink(dir, dentry);
 }
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 1a4f6da58eab..749693fcb75a 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -237,7 +237,7 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
 }
 
 static int ramoops_pstore_erase(enum pstore_type_id type, u64 id,
-				struct pstore_info *psi)
+				struct timespec time, struct pstore_info *psi)
 {
 	struct ramoops_context *cxt = psi->data;
 	struct persistent_ram_zone *prz;
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index ee3034a40884..f6e93362d259 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -60,7 +60,7 @@ struct pstore_info {
 			unsigned int part, const char *buf, size_t size,
 			struct pstore_info *psi);
 	int		(*erase)(enum pstore_type_id type, u64 id,
-			struct pstore_info *psi);
+			struct timespec time, struct pstore_info *psi);
 	void		*data;
 };
 
-- 
cgit v1.2.3-55-g7522


From 755d4fe46529018ae45bc7c86df682de45ace764 Mon Sep 17 00:00:00 2001
From: Seiji Aguchi
Date: Mon, 26 Nov 2012 16:07:44 -0800
Subject: efi_pstore: Add a sequence counter to a variable name

[Issue]

Currently, a variable name, which identifies each entry, consists of type, id and ctime.
But if multiple events happens in a short time, a second/third event may fail to log because
efi_pstore can't distinguish each event with current variable name.

[Solution]

A reasonable way to identify all events precisely is introducing a sequence counter to
the variable name.

The sequence counter has already supported in a pstore layer with "oopscount".
So, this patch adds it to a variable name.
Also, it is passed to read/erase callbacks of platform drivers in accordance with
the modification of the variable name.

  <before applying this patch>
 a variable name of first event: dump-type0-1-12345678
 a variable name of second event: dump-type0-1-12345678

  type:0
  id:1
  ctime:12345678

 If multiple events happen in a short time, efi_pstore can't distinguish them because
 variable names are same among them.

  <after applying this patch>

 it can be distinguishable by adding a sequence counter as follows.

 a variable name of first event: dump-type0-1-1-12345678
 a variable name of Second event: dump-type0-1-2-12345678

  type:0
  id:1
  sequence counter: 1(first event), 2(second event)
  ctime:12345678

In case of a write callback executed in pstore_console_write(), "0" is added to
an argument of the write callback because it just logs all kernel messages and
doesn't need to care about multiple events.

Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Mike Waychison <mikew@google.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 drivers/acpi/apei/erst.c   | 12 ++++++------
 drivers/firmware/efivars.c | 23 ++++++++++++++---------
 fs/pstore/inode.c          |  8 +++++---
 fs/pstore/internal.h       |  2 +-
 fs/pstore/platform.c       | 13 +++++++------
 fs/pstore/ram.c            |  7 +++----
 include/linux/pstore.h     |  8 +++++---
 7 files changed, 41 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 0bd6ae4a899f..6d894bfd8b8f 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -931,13 +931,13 @@ static int erst_check_table(struct acpi_table_erst *erst_tab)
 
 static int erst_open_pstore(struct pstore_info *psi);
 static int erst_close_pstore(struct pstore_info *psi);
-static ssize_t erst_reader(u64 *id, enum pstore_type_id *type,
+static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count,
 			   struct timespec *time, char **buf,
 			   struct pstore_info *psi);
 static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
-		       u64 *id, unsigned int part,
+		       u64 *id, unsigned int part, int count,
 		       size_t size, struct pstore_info *psi);
-static int erst_clearer(enum pstore_type_id type, u64 id,
+static int erst_clearer(enum pstore_type_id type, u64 id, int count,
 			struct timespec time, struct pstore_info *psi);
 
 static struct pstore_info erst_info = {
@@ -987,7 +987,7 @@ static int erst_close_pstore(struct pstore_info *psi)
 	return 0;
 }
 
-static ssize_t erst_reader(u64 *id, enum pstore_type_id *type,
+static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count,
 			   struct timespec *time, char **buf,
 			   struct pstore_info *psi)
 {
@@ -1055,7 +1055,7 @@ out:
 }
 
 static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
-		       u64 *id, unsigned int part,
+		       u64 *id, unsigned int part, int count,
 		       size_t size, struct pstore_info *psi)
 {
 	struct cper_pstore_record *rcd = (struct cper_pstore_record *)
@@ -1101,7 +1101,7 @@ static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
 	return ret;
 }
 
-static int erst_clearer(enum pstore_type_id type, u64 id,
+static int erst_clearer(enum pstore_type_id type, u64 id, int count,
 			struct timespec time, struct pstore_info *psi)
 {
 	return erst_clear(id);
diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index 3803621c0d45..7ad3aae6e085 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -658,13 +658,14 @@ static int efi_pstore_close(struct pstore_info *psi)
 }
 
 static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
-			       struct timespec *timespec,
+			       int *count, struct timespec *timespec,
 			       char **buf, struct pstore_info *psi)
 {
 	efi_guid_t vendor = LINUX_EFI_CRASH_GUID;
 	struct efivars *efivars = psi->data;
 	char name[DUMP_NAME_LEN];
 	int i;
+	int cnt;
 	unsigned int part, size;
 	unsigned long time;
 
@@ -674,8 +675,10 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 			for (i = 0; i < DUMP_NAME_LEN; i++) {
 				name[i] = efivars->walk_entry->var.VariableName[i];
 			}
-			if (sscanf(name, "dump-type%u-%u-%lu", type, &part, &time) == 3) {
+			if (sscanf(name, "dump-type%u-%u-%d-%lu",
+				   type, &part, &cnt, &time) == 4) {
 				*id = part;
+				*count = cnt;
 				timespec->tv_sec = time;
 				timespec->tv_nsec = 0;
 				get_var_data_locked(efivars, &efivars->walk_entry->var);
@@ -698,7 +701,8 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 
 static int efi_pstore_write(enum pstore_type_id type,
 		enum kmsg_dump_reason reason, u64 *id,
-		unsigned int part, size_t size, struct pstore_info *psi)
+		unsigned int part, int count, size_t size,
+		struct pstore_info *psi)
 {
 	char name[DUMP_NAME_LEN];
 	efi_char16_t efi_name[DUMP_NAME_LEN];
@@ -725,7 +729,7 @@ static int efi_pstore_write(enum pstore_type_id type,
 		return -ENOSPC;
 	}
 
-	sprintf(name, "dump-type%u-%u-%lu", type, part,
+	sprintf(name, "dump-type%u-%u-%d-%lu", type, part, count,
 		get_seconds());
 
 	for (i = 0; i < DUMP_NAME_LEN; i++)
@@ -746,7 +750,7 @@ static int efi_pstore_write(enum pstore_type_id type,
 	return ret;
 };
 
-static int efi_pstore_erase(enum pstore_type_id type, u64 id,
+static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count,
 			    struct timespec time, struct pstore_info *psi)
 {
 	char name[DUMP_NAME_LEN];
@@ -756,7 +760,7 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id,
 	struct efivar_entry *entry, *found = NULL;
 	int i;
 
-	sprintf(name, "dump-type%u-%u-%lu", type, (unsigned int)id,
+	sprintf(name, "dump-type%u-%u-%d-%lu", type, (unsigned int)id, count,
 		time.tv_sec);
 
 	spin_lock(&efivars->lock);
@@ -807,7 +811,7 @@ static int efi_pstore_close(struct pstore_info *psi)
 	return 0;
 }
 
-static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
+static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, int *count,
 			       struct timespec *timespec,
 			       char **buf, struct pstore_info *psi)
 {
@@ -816,12 +820,13 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 
 static int efi_pstore_write(enum pstore_type_id type,
 		enum kmsg_dump_reason reason, u64 *id,
-		unsigned int part, size_t size, struct pstore_info *psi)
+		unsigned int part, int count, size_t size,
+		struct pstore_info *psi)
 {
 	return 0;
 }
 
-static int efi_pstore_erase(enum pstore_type_id type, u64 id,
+static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count,
 			    struct timespec time, struct pstore_info *psi)
 {
 	return 0;
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 4300af654710..ed1d8c7212da 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -49,6 +49,7 @@ struct pstore_private {
 	struct pstore_info *psi;
 	enum pstore_type_id type;
 	u64	id;
+	int	count;
 	ssize_t	size;
 	char	data[];
 };
@@ -175,8 +176,8 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry)
 	struct pstore_private *p = dentry->d_inode->i_private;
 
 	if (p->psi->erase)
-		p->psi->erase(p->type, p->id, dentry->d_inode->i_ctime,
-			      p->psi);
+		p->psi->erase(p->type, p->id, p->count,
+			      dentry->d_inode->i_ctime, p->psi);
 
 	return simple_unlink(dir, dentry);
 }
@@ -271,7 +272,7 @@ int pstore_is_mounted(void)
  * Load it up with "size" bytes of data from "buf".
  * Set the mtime & ctime to the date that this record was originally stored.
  */
-int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id,
+int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 		  char *data, size_t size, struct timespec time,
 		  struct pstore_info *psi)
 {
@@ -307,6 +308,7 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id,
 		goto fail_alloc;
 	private->type = type;
 	private->id = id;
+	private->count = count;
 	private->psi = psi;
 
 	switch (type) {
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index 4847f588b7d5..937d820f273c 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -50,7 +50,7 @@ extern struct pstore_info *psinfo;
 extern void	pstore_set_kmsg_bytes(int);
 extern void	pstore_get_records(int);
 extern int	pstore_mkfile(enum pstore_type_id, char *psname, u64 id,
-			      char *data, size_t size,
+			      int count, char *data, size_t size,
 			      struct timespec time, struct pstore_info *psi);
 extern int	pstore_is_mounted(void);
 
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 947fbe06c3b1..5ea2e77ff023 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -136,7 +136,7 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 			break;
 
 		ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part,
-				    hsize + len, psinfo);
+				    oopscount, hsize + len, psinfo);
 		if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted())
 			pstore_new_entry = 1;
 
@@ -173,7 +173,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
 			spin_lock_irqsave(&psinfo->buf_lock, flags);
 		}
 		memcpy(psinfo->buf, s, c);
-		psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, c, psinfo);
+		psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, 0, c, psinfo);
 		spin_unlock_irqrestore(&psinfo->buf_lock, flags);
 		s += c;
 		c = e - s;
@@ -197,7 +197,7 @@ static void pstore_register_console(void) {}
 
 static int pstore_write_compat(enum pstore_type_id type,
 			       enum kmsg_dump_reason reason,
-			       u64 *id, unsigned int part,
+			       u64 *id, unsigned int part, int count,
 			       size_t size, struct pstore_info *psi)
 {
 	return psi->write_buf(type, reason, id, part, psinfo->buf, size, psi);
@@ -267,6 +267,7 @@ void pstore_get_records(int quiet)
 	char			*buf = NULL;
 	ssize_t			size;
 	u64			id;
+	int			count;
 	enum pstore_type_id	type;
 	struct timespec		time;
 	int			failed = 0, rc;
@@ -278,9 +279,9 @@ void pstore_get_records(int quiet)
 	if (psi->open && psi->open(psi))
 		goto out;
 
-	while ((size = psi->read(&id, &type, &time, &buf, psi)) > 0) {
-		rc = pstore_mkfile(type, psi->name, id, buf, (size_t)size,
-				  time, psi);
+	while ((size = psi->read(&id, &type, &count, &time, &buf, psi)) > 0) {
+		rc = pstore_mkfile(type, psi->name, id, count, buf,
+				  (size_t)size, time, psi);
 		kfree(buf);
 		buf = NULL;
 		if (rc && (rc != -EEXIST || !quiet))
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 749693fcb75a..2bfa36e0ffe8 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -132,9 +132,8 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max,
 }
 
 static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
-				   struct timespec *time,
-				   char **buf,
-				   struct pstore_info *psi)
+				   int *count, struct timespec *time,
+				   char **buf, struct pstore_info *psi)
 {
 	ssize_t size;
 	struct ramoops_context *cxt = psi->data;
@@ -236,7 +235,7 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
 	return 0;
 }
 
-static int ramoops_pstore_erase(enum pstore_type_id type, u64 id,
+static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, int count,
 				struct timespec time, struct pstore_info *psi)
 {
 	struct ramoops_context *cxt = psi->data;
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index f6e93362d259..1788909d9a99 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -50,17 +50,19 @@ struct pstore_info {
 	int		(*open)(struct pstore_info *psi);
 	int		(*close)(struct pstore_info *psi);
 	ssize_t		(*read)(u64 *id, enum pstore_type_id *type,
-			struct timespec *time, char **buf,
+			int *count, struct timespec *time, char **buf,
 			struct pstore_info *psi);
 	int		(*write)(enum pstore_type_id type,
 			enum kmsg_dump_reason reason, u64 *id,
-			unsigned int part, size_t size, struct pstore_info *psi);
+			unsigned int part, int count, size_t size,
+			struct pstore_info *psi);
 	int		(*write_buf)(enum pstore_type_id type,
 			enum kmsg_dump_reason reason, u64 *id,
 			unsigned int part, const char *buf, size_t size,
 			struct pstore_info *psi);
 	int		(*erase)(enum pstore_type_id type, u64 id,
-			struct timespec time, struct pstore_info *psi);
+			int count, struct timespec time,
+			struct pstore_info *psi);
 	void		*data;
 };
 
-- 
cgit v1.2.3-55-g7522


From 0dfa5b5d09a882a33f3aa433ad0b16898a3589ad Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk
Date: Mon, 26 Nov 2012 19:57:04 -0500
Subject: xen/acpi: Fix compile error by missing decleration for xen_domain.

Commit 92e3229dcdc80ff0b6304f14c578d76e7e10e226
("xen/acpi: ACPI PAD driver") adds a new function but forgets to
use the right header. Without it, we get:

In file included from drivers/xen/features.c:15:0:
include/xen/interface/version.h: In function ‘xen_running_on_version_or_later’:
include/xen/interface/version.h:72:2: error: implicit declaration of function ‘xen_domain’ [-Werror=implicit-function-declaration]

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 include/xen/interface/version.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h
index 96d8d3deea6b..53553f046497 100644
--- a/include/xen/interface/version.h
+++ b/include/xen/interface/version.h
@@ -63,6 +63,9 @@ struct xen_feature_info {
 /* arg == xen_domain_handle_t. */
 #define XENVER_guest_handle 8
 
+/* Declares the xen_domain() macros. */
+#include <xen/xen.h>
+
 /* Check if running on Xen version (major, minor) or later */
 static inline bool
 xen_running_on_version_or_later(unsigned int major, unsigned int minor)
-- 
cgit v1.2.3-55-g7522


From 53ad570be625045aba3ae7de8d82401364c655e1 Mon Sep 17 00:00:00 2001
From: Jason J. Herne
Date: Wed, 14 Nov 2012 17:03:22 -0500
Subject: [SCSI] sd: Use SCSI read/write(16) with > 32-bit LBA drives

Force large capacity (> 0xFFFFFFFF blocks) drives to use READ/WRITE(16) instead
of READ/WRITE(10). Some(most/all?) USB enclosures do not like READ(10) commands
when a large capacity drive is installed. This issue was reported and discussed
here: http://marc.info/?l=linux-usb&m=135247705222324

Signed-off-by: Jason J. Herne <hernejj@gmail.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
---
 drivers/scsi/sd.c          | 4 +++-
 include/scsi/scsi_device.h | 1 +
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index a45e12ac7e28..c5a189c50286 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1011,7 +1011,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 		SCpnt->cmnd[29] = (unsigned char) (this_count >> 16) & 0xff;
 		SCpnt->cmnd[30] = (unsigned char) (this_count >> 8) & 0xff;
 		SCpnt->cmnd[31] = (unsigned char) this_count & 0xff;
-	} else if (block > 0xffffffff) {
+	} else if (sdp->use_16_for_rw) {
 		SCpnt->cmnd[0] += READ_16 - READ_6;
 		SCpnt->cmnd[1] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0);
 		SCpnt->cmnd[2] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0;
@@ -2203,6 +2203,8 @@ got_data:
 		}
 	}
 
+	sdp->use_16_for_rw = (sdkp->capacity > 0xffffffff);
+
 	/* Rescale capacity to 512-byte units */
 	if (sector_size == 4096)
 		sdkp->capacity <<= 3;
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 55367b04dc94..e65c62e82c5a 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -137,6 +137,7 @@ struct scsi_device {
 	unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */
 	unsigned no_report_opcodes:1;	/* no REPORT SUPPORTED OPERATION CODES */
 	unsigned no_write_same:1;	/* no WRITE SAME command */
+	unsigned use_16_for_rw:1; /* Use read/write(16) over read/write(10) */
 	unsigned skip_ms_page_8:1;	/* do not use MODE SENSE page 0x08 */
 	unsigned skip_ms_page_3f:1;	/* do not use MODE SENSE page 0x3f */
 	unsigned skip_vpd_pages:1;	/* do not read VPD pages */
-- 
cgit v1.2.3-55-g7522


From 9f5e8f6efc7c2601136b27d9c7325c245f8fd19a Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Thu, 22 Nov 2012 16:59:45 +0100
Subject: cfg80211: rework chandef checking and export it

Some of the chandef checking that we do in cfg80211
to check if a channel is supported or not is also
needed in mac80211, so rework that a bit and export
the functions that are needed.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 21 ++++++++++--
 net/wireless/chan.c    | 92 ++++++++++++++++++++++++++++++++++----------------
 net/wireless/core.h    |  6 ----
 net/wireless/nl80211.c | 38 +++------------------
 4 files changed, 85 insertions(+), 72 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index e78db2cf3d1b..a238f41e55c2 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -58,6 +58,8 @@
  * structures here describe these capabilities in detail.
  */
 
+struct wiphy;
+
 /*
  * wireless hardware capability structures
  */
@@ -387,6 +389,22 @@ const struct cfg80211_chan_def *
 cfg80211_chandef_compatible(const struct cfg80211_chan_def *chandef1,
 			    const struct cfg80211_chan_def *chandef2);
 
+/**
+ * cfg80211_chandef_valid - check if a channel definition is valid
+ * @chandef: the channel definition to check
+ */
+bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef);
+
+/**
+ * cfg80211_chandef_usable - check if secondary channels can be used
+ * @wiphy: the wiphy to validate against
+ * @chandef: the channel definition to check
+ * @prohibited_flags: the regulatory chanenl flags that must not be set
+ */
+bool cfg80211_chandef_usable(struct wiphy *wiphy,
+			     const struct cfg80211_chan_def *chandef,
+			     u32 prohibited_flags);
+
 /**
  * enum survey_info_flags - survey information flags
  *
@@ -1045,9 +1063,6 @@ struct ieee80211_txq_params {
 	u8 aifs;
 };
 
-/* from net/wireless.h */
-struct wiphy;
-
 /**
  * DOC: Scanning and BSS list handling
  *
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index bf2dfd54ff3b..b5f69831e318 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -44,7 +44,7 @@ void cfg80211_chandef_create(struct cfg80211_chan_def *chandef,
 }
 EXPORT_SYMBOL(cfg80211_chandef_create);
 
-bool cfg80211_chan_def_valid(const struct cfg80211_chan_def *chandef)
+bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef)
 {
 	u32 control_freq;
 
@@ -105,6 +105,7 @@ bool cfg80211_chan_def_valid(const struct cfg80211_chan_def *chandef)
 
 	return true;
 }
+EXPORT_SYMBOL(cfg80211_chandef_valid);
 
 static void chandef_primary_freqs(const struct cfg80211_chan_def *c,
 				  int *pri40, int *pri80)
@@ -187,9 +188,9 @@ cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1,
 }
 EXPORT_SYMBOL(cfg80211_chandef_compatible);
 
-bool cfg80211_secondary_chans_ok(struct wiphy *wiphy,
-				 u32 center_freq, u32 bandwidth,
-				 u32 prohibited_flags)
+static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy,
+					u32 center_freq, u32 bandwidth,
+					u32 prohibited_flags)
 {
 	struct ieee80211_channel *c;
 	u32 freq;
@@ -205,55 +206,88 @@ bool cfg80211_secondary_chans_ok(struct wiphy *wiphy,
 	return true;
 }
 
-static bool cfg80211_check_beacon_chans(struct wiphy *wiphy,
-					u32 center_freq, u32 bw)
+bool cfg80211_chandef_usable(struct wiphy *wiphy,
+			     const struct cfg80211_chan_def *chandef,
+			     u32 prohibited_flags)
 {
-	return cfg80211_secondary_chans_ok(wiphy, center_freq, bw,
-					   IEEE80211_CHAN_DISABLED |
-					   IEEE80211_CHAN_PASSIVE_SCAN |
-					   IEEE80211_CHAN_NO_IBSS |
-					   IEEE80211_CHAN_RADAR);
-}
+	struct ieee80211_sta_ht_cap *ht_cap;
+	struct ieee80211_sta_vht_cap *vht_cap;
+	u32 width, control_freq;
 
-bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
-			     struct cfg80211_chan_def *chandef)
-{
-	u32 width;
-	bool res;
+	if (WARN_ON(!cfg80211_chandef_valid(chandef)))
+		return false;
 
-	trace_cfg80211_reg_can_beacon(wiphy, chandef);
+	ht_cap = &wiphy->bands[chandef->chan->band]->ht_cap;
+	vht_cap = &wiphy->bands[chandef->chan->band]->vht_cap;
 
-	if (WARN_ON(!cfg80211_chan_def_valid(chandef))) {
-		trace_cfg80211_return_bool(false);
-		return false;
-	}
+	control_freq = chandef->chan->center_freq;
 
 	switch (chandef->width) {
-	case NL80211_CHAN_WIDTH_20_NOHT:
 	case NL80211_CHAN_WIDTH_20:
+		if (!ht_cap->ht_supported)
+			return false;
+	case NL80211_CHAN_WIDTH_20_NOHT:
 		width = 20;
 		break;
 	case NL80211_CHAN_WIDTH_40:
 		width = 40;
+		if (!ht_cap->ht_supported)
+			return false;
+		if (!(ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) ||
+		    ht_cap->cap & IEEE80211_HT_CAP_40MHZ_INTOLERANT)
+			return false;
+		if (chandef->center_freq1 < control_freq &&
+		    chandef->chan->flags & IEEE80211_CHAN_NO_HT40MINUS)
+			return false;
+		if (chandef->center_freq1 > control_freq &&
+		    chandef->chan->flags & IEEE80211_CHAN_NO_HT40PLUS)
+			return false;
 		break;
-	case NL80211_CHAN_WIDTH_80:
 	case NL80211_CHAN_WIDTH_80P80:
+		if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ))
+			return false;
+	case NL80211_CHAN_WIDTH_80:
+		if (!vht_cap->vht_supported)
+			return false;
 		width = 80;
 		break;
 	case NL80211_CHAN_WIDTH_160:
+		if (!vht_cap->vht_supported)
+			return false;
+		if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ))
+			return false;
 		width = 160;
 		break;
 	default:
 		WARN_ON_ONCE(1);
-		trace_cfg80211_return_bool(false);
 		return false;
 	}
 
-	res = cfg80211_check_beacon_chans(wiphy, chandef->center_freq1, width);
+	/* TODO: missing regulatory check on 80/160 bandwidth */
+
+	if (!cfg80211_secondary_chans_ok(wiphy, chandef->center_freq1,
+					 width, prohibited_flags))
+		return false;
+
+	if (!chandef->center_freq2)
+		return true;
+	return cfg80211_secondary_chans_ok(wiphy, chandef->center_freq2,
+					   width, prohibited_flags);
+}
+EXPORT_SYMBOL(cfg80211_chandef_usable);
+
+bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
+			     struct cfg80211_chan_def *chandef)
+{
+	bool res;
+
+	trace_cfg80211_reg_can_beacon(wiphy, chandef);
 
-	if (res && chandef->center_freq2)
-		res = cfg80211_check_beacon_chans(wiphy, chandef->center_freq2,
-						  width);
+	res = cfg80211_chandef_usable(wiphy, chandef,
+				      IEEE80211_CHAN_DISABLED |
+				      IEEE80211_CHAN_PASSIVE_SCAN |
+				      IEEE80211_CHAN_NO_IBSS |
+				      IEEE80211_CHAN_RADAR);
 
 	trace_cfg80211_return_bool(res);
 	return res;
diff --git a/net/wireless/core.h b/net/wireless/core.h
index a0c8decf6a47..6183a0d25b8b 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -483,12 +483,6 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
 void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev,
 			       enum nl80211_iftype iftype, int num);
 
-bool cfg80211_chan_def_valid(const struct cfg80211_chan_def *chandef);
-
-bool cfg80211_secondary_chans_ok(struct wiphy *wiphy,
-				 u32 center_freq, u32 bandwidth,
-				 u32 prohibited_flags);
-
 #define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10
 
 #ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d038fa45ecd1..eb0aa71a02b3 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1420,63 +1420,33 @@ static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
 	ht_cap = &rdev->wiphy.bands[chandef->chan->band]->ht_cap;
 	vht_cap = &rdev->wiphy.bands[chandef->chan->band]->vht_cap;
 
-	if (!cfg80211_chan_def_valid(chandef))
+	if (!cfg80211_chandef_valid(chandef))
 		return -EINVAL;
 
 	switch (chandef->width) {
 	case NL80211_CHAN_WIDTH_20:
-		if (!ht_cap->ht_supported)
-			return -EINVAL;
 	case NL80211_CHAN_WIDTH_20_NOHT:
 		width = 20;
 		break;
 	case NL80211_CHAN_WIDTH_40:
 		width = 40;
-		/* quick early regulatory check */
-		if (chandef->center_freq1 < control_freq &&
-		    chandef->chan->flags & IEEE80211_CHAN_NO_HT40MINUS)
-			return -EINVAL;
-		if (chandef->center_freq1 > control_freq &&
-		    chandef->chan->flags & IEEE80211_CHAN_NO_HT40PLUS)
-			return -EINVAL;
-		if (!ht_cap->ht_supported)
-			return -EINVAL;
-		if (!(ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) ||
-		    ht_cap->cap & IEEE80211_HT_CAP_40MHZ_INTOLERANT)
-			return -EINVAL;
 		break;
 	case NL80211_CHAN_WIDTH_80:
 		width = 80;
-		if (!vht_cap->vht_supported)
-			return -EINVAL;
 		break;
 	case NL80211_CHAN_WIDTH_80P80:
 		width = 80;
-		if (!vht_cap->vht_supported)
-			return -EINVAL;
-		if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ))
-			return -EINVAL;
 		break;
 	case NL80211_CHAN_WIDTH_160:
 		width = 160;
-		if (!vht_cap->vht_supported)
-			return -EINVAL;
-		if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ))
-			return -EINVAL;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	if (!cfg80211_secondary_chans_ok(&rdev->wiphy, chandef->center_freq1,
-					 width, IEEE80211_CHAN_DISABLED))
+	if (!cfg80211_chandef_usable(&rdev->wiphy, chandef,
+				     IEEE80211_CHAN_DISABLED))
 		return -EINVAL;
-	if (chandef->center_freq2 &&
-	    !cfg80211_secondary_chans_ok(&rdev->wiphy, chandef->center_freq2,
-					 width, IEEE80211_CHAN_DISABLED))
-		return -EINVAL;
-
-	/* TODO: missing regulatory check on bandwidth */
 
 	return 0;
 }
@@ -1841,7 +1811,7 @@ static inline u64 wdev_id(struct wireless_dev *wdev)
 static int nl80211_send_chandef(struct sk_buff *msg,
 				 struct cfg80211_chan_def *chandef)
 {
-	WARN_ON(!cfg80211_chan_def_valid(chandef));
+	WARN_ON(!cfg80211_chandef_valid(chandef));
 
 	if (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ,
 			chandef->chan->center_freq))
-- 
cgit v1.2.3-55-g7522


From f772fabdf72aec5ef05988dd82dfd150e58f7aa3 Mon Sep 17 00:00:00 2001
From: Manjunathappa, Prakash
Date: Tue, 16 Oct 2012 10:23:15 +0530
Subject: da8xx-fb: adopt fb_videomode data for panel information

Adopt fb_videomode data instead of defining driver private
structure to hold panel information. This is the way standard FB
drivers maintain the panel information.

Signed-off-by: Manjunathappa, Prakash <prakash.pm@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/da8xx-fb.c | 130 ++++++++++++++++++++++-------------------------
 include/video/da8xx-fb.h |   3 ++
 2 files changed, 63 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 80665f66ac1a..c3db0366d59f 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -213,62 +213,50 @@ static struct fb_fix_screeninfo da8xx_fb_fix __devinitdata = {
 	.accel = FB_ACCEL_NONE
 };
 
-struct da8xx_panel {
-	const char	name[25];	/* Full name <vendor>_<model> */
-	unsigned short	width;
-	unsigned short	height;
-	int		hfp;		/* Horizontal front porch */
-	int		hbp;		/* Horizontal back porch */
-	int		hsw;		/* Horizontal Sync Pulse Width */
-	int		vfp;		/* Vertical front porch */
-	int		vbp;		/* Vertical back porch */
-	int		vsw;		/* Vertical Sync Pulse Width */
-	unsigned int	pxl_clk;	/* Pixel clock */
-	unsigned char	invert_pxl_clk;	/* Invert Pixel clock */
-};
-
-static struct da8xx_panel known_lcd_panels[] = {
+static struct fb_videomode known_lcd_panels[] = {
 	/* Sharp LCD035Q3DG01 */
 	[0] = {
-		.name = "Sharp_LCD035Q3DG01",
-		.width = 320,
-		.height = 240,
-		.hfp = 8,
-		.hbp = 6,
-		.hsw = 0,
-		.vfp = 2,
-		.vbp = 2,
-		.vsw = 0,
-		.pxl_clk = 4608000,
-		.invert_pxl_clk = 1,
+		.name           = "Sharp_LCD035Q3DG01",
+		.xres           = 320,
+		.yres           = 240,
+		.pixclock       = 4608000,
+		.left_margin    = 6,
+		.right_margin   = 8,
+		.upper_margin   = 2,
+		.lower_margin   = 2,
+		.hsync_len      = 0,
+		.vsync_len      = 0,
+		.sync           = FB_SYNC_CLK_INVERT,
 	},
 	/* Sharp LK043T1DG01 */
 	[1] = {
-		.name = "Sharp_LK043T1DG01",
-		.width = 480,
-		.height = 272,
-		.hfp = 2,
-		.hbp = 2,
-		.hsw = 41,
-		.vfp = 2,
-		.vbp = 2,
-		.vsw = 10,
-		.pxl_clk = 7833600,
-		.invert_pxl_clk = 0,
+		.name           = "Sharp_LK043T1DG01",
+		.xres           = 480,
+		.yres           = 272,
+		.pixclock       = 7833600,
+		.left_margin    = 2,
+		.right_margin   = 2,
+		.upper_margin   = 2,
+		.lower_margin   = 2,
+		.hsync_len      = 41,
+		.vsync_len      = 10,
+		.sync           = 0,
+		.flag           = 0,
 	},
 	[2] = {
 		/* Hitachi SP10Q010 */
-		.name = "SP10Q010",
-		.width = 320,
-		.height = 240,
-		.hfp = 10,
-		.hbp = 10,
-		.hsw = 10,
-		.vfp = 10,
-		.vbp = 10,
-		.vsw = 10,
-		.pxl_clk = 7833600,
-		.invert_pxl_clk = 0,
+		.name           = "SP10Q010",
+		.xres           = 320,
+		.yres           = 240,
+		.pixclock       = 7833600,
+		.left_margin    = 10,
+		.right_margin   = 10,
+		.upper_margin   = 10,
+		.lower_margin   = 10,
+		.hsync_len      = 10,
+		.vsync_len      = 10,
+		.sync           = 0,
+		.flag           = 0,
 	},
 };
 
@@ -728,7 +716,7 @@ static void lcd_calc_clk_divider(struct da8xx_fb_par *par)
 }
 
 static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
-		struct da8xx_panel *panel)
+		struct fb_videomode *panel)
 {
 	u32 bpp;
 	int ret = 0;
@@ -738,7 +726,7 @@ static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
 	/* Calculate the divider */
 	lcd_calc_clk_divider(par);
 
-	if (panel->invert_pxl_clk)
+	if (panel->sync & FB_SYNC_CLK_INVERT)
 		lcdc_write((lcdc_read(LCD_RASTER_TIMING_2_REG) |
 			LCD_INVERT_PIXEL_CLOCK), LCD_RASTER_TIMING_2_REG);
 	else
@@ -754,8 +742,10 @@ static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
 	lcd_cfg_ac_bias(cfg->ac_bias, cfg->ac_bias_intrpt);
 
 	/* Configure the vertical and horizontal sync properties. */
-	lcd_cfg_vertical_sync(panel->vbp, panel->vsw, panel->vfp);
-	lcd_cfg_horizontal_sync(panel->hbp, panel->hsw, panel->hfp);
+	lcd_cfg_vertical_sync(panel->lower_margin, panel->vsync_len,
+			panel->upper_margin);
+	lcd_cfg_horizontal_sync(panel->right_margin, panel->hsync_len,
+			panel->left_margin);
 
 	/* Configure for disply */
 	ret = lcd_cfg_display(cfg);
@@ -772,8 +762,8 @@ static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
 		bpp = cfg->p_disp_panel->max_bpp;
 	if (bpp == 12)
 		bpp = 16;
-	ret = lcd_cfg_frame_buffer(par, (unsigned int)panel->width,
-				(unsigned int)panel->height, bpp,
+	ret = lcd_cfg_frame_buffer(par, (unsigned int)panel->xres,
+				(unsigned int)panel->yres, bpp,
 				cfg->raster_order);
 	if (ret < 0)
 		return ret;
@@ -1235,7 +1225,7 @@ static int __devinit fb_probe(struct platform_device *device)
 	struct da8xx_lcdc_platform_data *fb_pdata =
 						device->dev.platform_data;
 	struct lcd_ctrl_config *lcd_cfg;
-	struct da8xx_panel *lcdc_info;
+	struct fb_videomode *lcdc_info;
 	struct fb_info *da8xx_fb_info;
 	struct clk *fb_clk = NULL;
 	struct da8xx_fb_par *par;
@@ -1323,7 +1313,7 @@ static int __devinit fb_probe(struct platform_device *device)
 #ifdef CONFIG_CPU_FREQ
 	par->lcd_fck_rate = clk_get_rate(fb_clk);
 #endif
-	par->pxl_clk = lcdc_info->pxl_clk;
+	par->pxl_clk = lcdc_info->pixclock;
 	if (fb_pdata->panel_power_ctrl) {
 		par->panel_power_ctrl = fb_pdata->panel_power_ctrl;
 		par->panel_power_ctrl(1);
@@ -1336,8 +1326,8 @@ static int __devinit fb_probe(struct platform_device *device)
 	}
 
 	/* allocate frame buffer */
-	par->vram_size = lcdc_info->width * lcdc_info->height * lcd_cfg->bpp;
-	ulcm = lcm((lcdc_info->width * lcd_cfg->bpp)/8, PAGE_SIZE);
+	par->vram_size = lcdc_info->xres * lcdc_info->yres * lcd_cfg->bpp;
+	ulcm = lcm((lcdc_info->xres * lcd_cfg->bpp)/8, PAGE_SIZE);
 	par->vram_size = roundup(par->vram_size/8, ulcm);
 	par->vram_size = par->vram_size * LCD_NUM_BUFFERS;
 
@@ -1355,10 +1345,10 @@ static int __devinit fb_probe(struct platform_device *device)
 	da8xx_fb_info->screen_base = (char __iomem *) par->vram_virt;
 	da8xx_fb_fix.smem_start    = par->vram_phys;
 	da8xx_fb_fix.smem_len      = par->vram_size;
-	da8xx_fb_fix.line_length   = (lcdc_info->width * lcd_cfg->bpp) / 8;
+	da8xx_fb_fix.line_length   = (lcdc_info->xres * lcd_cfg->bpp) / 8;
 
 	par->dma_start = par->vram_phys;
-	par->dma_end   = par->dma_start + lcdc_info->height *
+	par->dma_end   = par->dma_start + lcdc_info->yres *
 		da8xx_fb_fix.line_length - 1;
 
 	/* allocate palette buffer */
@@ -1384,22 +1374,22 @@ static int __devinit fb_probe(struct platform_device *device)
 	/* Initialize par */
 	da8xx_fb_info->var.bits_per_pixel = lcd_cfg->bpp;
 
-	da8xx_fb_var.xres = lcdc_info->width;
-	da8xx_fb_var.xres_virtual = lcdc_info->width;
+	da8xx_fb_var.xres = lcdc_info->xres;
+	da8xx_fb_var.xres_virtual = lcdc_info->xres;
 
-	da8xx_fb_var.yres         = lcdc_info->height;
-	da8xx_fb_var.yres_virtual = lcdc_info->height * LCD_NUM_BUFFERS;
+	da8xx_fb_var.yres         = lcdc_info->yres;
+	da8xx_fb_var.yres_virtual = lcdc_info->yres * LCD_NUM_BUFFERS;
 
 	da8xx_fb_var.grayscale =
 	    lcd_cfg->p_disp_panel->panel_shade == MONOCHROME ? 1 : 0;
 	da8xx_fb_var.bits_per_pixel = lcd_cfg->bpp;
 
-	da8xx_fb_var.hsync_len = lcdc_info->hsw;
-	da8xx_fb_var.vsync_len = lcdc_info->vsw;
-	da8xx_fb_var.right_margin = lcdc_info->hfp;
-	da8xx_fb_var.left_margin  = lcdc_info->hbp;
-	da8xx_fb_var.lower_margin = lcdc_info->vfp;
-	da8xx_fb_var.upper_margin = lcdc_info->vbp;
+	da8xx_fb_var.hsync_len = lcdc_info->hsync_len;
+	da8xx_fb_var.vsync_len = lcdc_info->vsync_len;
+	da8xx_fb_var.right_margin = lcdc_info->right_margin;
+	da8xx_fb_var.left_margin  = lcdc_info->left_margin;
+	da8xx_fb_var.lower_margin = lcdc_info->lower_margin;
+	da8xx_fb_var.upper_margin = lcdc_info->upper_margin;
 	da8xx_fb_var.pixclock = da8xxfb_pixel_clk_period(par);
 
 	/* Initialize fbinfo */
diff --git a/include/video/da8xx-fb.h b/include/video/da8xx-fb.h
index 5a0e4f9efb53..12e4e1de5e3c 100644
--- a/include/video/da8xx-fb.h
+++ b/include/video/da8xx-fb.h
@@ -103,5 +103,8 @@ struct lcd_sync_arg {
 #define FBIPUT_HSYNC		_IOW('F', 9, int)
 #define FBIPUT_VSYNC		_IOW('F', 10, int)
 
+/* Proprietary FB_SYNC_ flags */
+#define FB_SYNC_CLK_INVERT 0x40000000
+
 #endif  /* ifndef DA8XX_FB_H */
 
-- 
cgit v1.2.3-55-g7522


From 3b43ad201dea06be1636e4809278d63837f8d292 Mon Sep 17 00:00:00 2001
From: Manjunathappa, Prakash
Date: Tue, 16 Oct 2012 10:23:16 +0530
Subject: da8xx-fb: cleanup LCDC configurations

Configure below LCDC configurations to optimal values, also have an
option configure these optional parameters for platform.
1) AC bias configuration: Required only for passive panels
2) Dma_burst_size:
3) FIFO_DMA_DELAY:
4) FIFO threshold: Does not apply for da830 LCDC.

Patch is verified for 16bpp and 24bpp configurations on da830, da850 and
am335x EVMs.

Signed-off-by: Manjunathappa, Prakash <prakash.pm@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 arch/arm/mach-davinci/devices-da8xx.c | 22 +-----------------
 drivers/video/da8xx-fb.c              | 43 ++++++++++++++---------------------
 include/video/da8xx-fb.h              | 22 +-----------------
 3 files changed, 19 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index bd2f72b414bc..fcb30d3ae24e 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -518,29 +518,9 @@ void __init da8xx_register_mcasp(int id, struct snd_platform_data *pdata)
 	}
 }
 
-static const struct display_panel disp_panel = {
-	QVGA,
-	16,
-	16,
-	COLOR_ACTIVE,
-};
-
 static struct lcd_ctrl_config lcd_cfg = {
-	&disp_panel,
-	.ac_bias		= 255,
-	.ac_bias_intrpt		= 0,
-	.dma_burst_sz		= 16,
+	.panel_shade		= COLOR_ACTIVE,
 	.bpp			= 16,
-	.fdd			= 255,
-	.tft_alt_mode		= 0,
-	.stn_565_mode		= 0,
-	.mono_8bit_mode		= 0,
-	.invert_line_clock	= 1,
-	.invert_frm_clock	= 1,
-	.sync_edge		= 0,
-	.sync_ctrl		= 1,
-	.raster_order		= 0,
-	.fifo_th		= 6,
 };
 
 struct da8xx_lcdc_platform_data sharp_lcd035q3dg01_pdata = {
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index c3db0366d59f..3fd9ec5f993a 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -226,7 +226,8 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 2,
 		.hsync_len      = 0,
 		.vsync_len      = 0,
-		.sync           = FB_SYNC_CLK_INVERT,
+		.sync           = FB_SYNC_CLK_INVERT |
+			FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
 	},
 	/* Sharp LK043T1DG01 */
 	[1] = {
@@ -240,7 +241,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 2,
 		.hsync_len      = 41,
 		.vsync_len      = 10,
-		.sync           = 0,
+		.sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
 		.flag           = 0,
 	},
 	[2] = {
@@ -255,7 +256,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 10,
 		.hsync_len      = 10,
 		.vsync_len      = 10,
-		.sync           = 0,
+		.sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
 		.flag           = 0,
 	},
 };
@@ -387,10 +388,9 @@ static int lcd_cfg_dma(int burst_size, int fifo_th)
 		reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_8);
 		break;
 	case 16:
+	default:
 		reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_16);
 		break;
-	default:
-		return -EINVAL;
 	}
 
 	reg |= (fifo_th << 8);
@@ -435,7 +435,8 @@ static void lcd_cfg_vertical_sync(int back_porch, int pulse_width,
 	lcdc_write(reg, LCD_RASTER_TIMING_1_REG);
 }
 
-static int lcd_cfg_display(const struct lcd_ctrl_config *cfg)
+static int lcd_cfg_display(const struct lcd_ctrl_config *cfg,
+		struct fb_videomode *panel)
 {
 	u32 reg;
 	u32 reg_int;
@@ -444,7 +445,7 @@ static int lcd_cfg_display(const struct lcd_ctrl_config *cfg)
 						LCD_MONO_8BIT_MODE |
 						LCD_MONOCHROME_MODE);
 
-	switch (cfg->p_disp_panel->panel_shade) {
+	switch (cfg->panel_shade) {
 	case MONOCHROME:
 		reg |= LCD_MONOCHROME_MODE;
 		if (cfg->mono_8bit_mode)
@@ -457,7 +458,9 @@ static int lcd_cfg_display(const struct lcd_ctrl_config *cfg)
 		break;
 
 	case COLOR_PASSIVE:
-		if (cfg->stn_565_mode)
+		/* AC bias applicable only for Pasive panels */
+		lcd_cfg_ac_bias(cfg->ac_bias, cfg->ac_bias_intrpt);
+		if (cfg->bpp == 12 && cfg->stn_565_mode)
 			reg |= LCD_STN_565_ENABLE;
 		break;
 
@@ -478,22 +481,19 @@ static int lcd_cfg_display(const struct lcd_ctrl_config *cfg)
 
 	reg = lcdc_read(LCD_RASTER_TIMING_2_REG);
 
-	if (cfg->sync_ctrl)
-		reg |= LCD_SYNC_CTRL;
-	else
-		reg &= ~LCD_SYNC_CTRL;
+	reg |= LCD_SYNC_CTRL;
 
 	if (cfg->sync_edge)
 		reg |= LCD_SYNC_EDGE;
 	else
 		reg &= ~LCD_SYNC_EDGE;
 
-	if (cfg->invert_line_clock)
+	if (panel->sync & FB_SYNC_HOR_HIGH_ACT)
 		reg |= LCD_INVERT_LINE_CLOCK;
 	else
 		reg &= ~LCD_INVERT_LINE_CLOCK;
 
-	if (cfg->invert_frm_clock)
+	if (panel->sync & FB_SYNC_VERT_HIGH_ACT)
 		reg |= LCD_INVERT_FRAME_CLOCK;
 	else
 		reg &= ~LCD_INVERT_FRAME_CLOCK;
@@ -738,9 +738,6 @@ static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
 	if (ret < 0)
 		return ret;
 
-	/* Configure the AC bias properties. */
-	lcd_cfg_ac_bias(cfg->ac_bias, cfg->ac_bias_intrpt);
-
 	/* Configure the vertical and horizontal sync properties. */
 	lcd_cfg_vertical_sync(panel->lower_margin, panel->vsync_len,
 			panel->upper_margin);
@@ -748,18 +745,12 @@ static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
 			panel->left_margin);
 
 	/* Configure for disply */
-	ret = lcd_cfg_display(cfg);
+	ret = lcd_cfg_display(cfg, panel);
 	if (ret < 0)
 		return ret;
 
-	if (QVGA != cfg->p_disp_panel->panel_type)
-		return -EINVAL;
+	bpp = cfg->bpp;
 
-	if (cfg->bpp <= cfg->p_disp_panel->max_bpp &&
-	    cfg->bpp >= cfg->p_disp_panel->min_bpp)
-		bpp = cfg->bpp;
-	else
-		bpp = cfg->p_disp_panel->max_bpp;
 	if (bpp == 12)
 		bpp = 16;
 	ret = lcd_cfg_frame_buffer(par, (unsigned int)panel->xres,
@@ -1381,7 +1372,7 @@ static int __devinit fb_probe(struct platform_device *device)
 	da8xx_fb_var.yres_virtual = lcdc_info->yres * LCD_NUM_BUFFERS;
 
 	da8xx_fb_var.grayscale =
-	    lcd_cfg->p_disp_panel->panel_shade == MONOCHROME ? 1 : 0;
+	    lcd_cfg->panel_shade == MONOCHROME ? 1 : 0;
 	da8xx_fb_var.bits_per_pixel = lcd_cfg->bpp;
 
 	da8xx_fb_var.hsync_len = lcdc_info->hsync_len;
diff --git a/include/video/da8xx-fb.h b/include/video/da8xx-fb.h
index 12e4e1de5e3c..f88825928dd1 100644
--- a/include/video/da8xx-fb.h
+++ b/include/video/da8xx-fb.h
@@ -12,10 +12,6 @@
 #ifndef DA8XX_FB_H
 #define DA8XX_FB_H
 
-enum panel_type {
-	QVGA = 0
-};
-
 enum panel_shade {
 	MONOCHROME = 0,
 	COLOR_ACTIVE,
@@ -27,13 +23,6 @@ enum raster_load_mode {
 	LOAD_PALETTE,
 };
 
-struct display_panel {
-	enum panel_type panel_type; /* QVGA */
-	int max_bpp;
-	int min_bpp;
-	enum panel_shade panel_shade;
-};
-
 struct da8xx_lcdc_platform_data {
 	const char manu_name[10];
 	void *controller_data;
@@ -42,7 +31,7 @@ struct da8xx_lcdc_platform_data {
 };
 
 struct lcd_ctrl_config {
-	const struct display_panel *p_disp_panel;
+	enum panel_shade panel_shade;
 
 	/* AC Bias Pin Frequency */
 	int ac_bias;
@@ -68,18 +57,9 @@ struct lcd_ctrl_config {
 	/* Mono 8-bit Mode: 1=D0-D7 or 0=D0-D3 */
 	unsigned char mono_8bit_mode;
 
-	/* Invert line clock */
-	unsigned char invert_line_clock;
-
-	/* Invert frame clock  */
-	unsigned char invert_frm_clock;
-
 	/* Horizontal and Vertical Sync Edge: 0=rising 1=falling */
 	unsigned char sync_edge;
 
-	/* Horizontal and Vertical Sync: Control: 0=ignore */
-	unsigned char sync_ctrl;
-
 	/* Raster Data Order Select: 1=Most-to-least 0=Least-to-most */
 	unsigned char raster_order;
 
-- 
cgit v1.2.3-55-g7522


From f2d9d270c15ae0139b54a7e7466d738327e97e03 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Thu, 22 Nov 2012 14:11:39 +0100
Subject: mac80211: support VHT association

Determine the VHT channel from the AP's VHT operation IE
(if present) and configure the hardware to that channel
if it is supported. If channel contexts cause a channel
to not be usable, try a smaller bandwidth.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  |  15 ++
 net/mac80211/ieee80211_i.h |   2 +
 net/mac80211/mlme.c        | 368 ++++++++++++++++++++++++++++++++++++---------
 3 files changed, 313 insertions(+), 72 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index f9c5a787d350..8f690e53dd89 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1212,6 +1212,21 @@ struct ieee80211_vht_cap {
 	struct ieee80211_vht_mcs_info supp_mcs;
 } __packed;
 
+/**
+ * enum ieee80211_vht_chanwidth - VHT channel width
+ * @IEEE80211_VHT_CHANWIDTH_USE_HT: use the HT operation IE to
+ *	determine the channel width (20 or 40 MHz)
+ * @IEEE80211_VHT_CHANWIDTH_80MHZ: 80 MHz bandwidth
+ * @IEEE80211_VHT_CHANWIDTH_160MHZ: 160 MHz bandwidth
+ * @IEEE80211_VHT_CHANWIDTH_80P80MHZ: 80+80 MHz bandwidth
+ */
+enum ieee80211_vht_chanwidth {
+	IEEE80211_VHT_CHANWIDTH_USE_HT		= 0,
+	IEEE80211_VHT_CHANWIDTH_80MHZ		= 1,
+	IEEE80211_VHT_CHANWIDTH_160MHZ		= 2,
+	IEEE80211_VHT_CHANWIDTH_80P80MHZ	= 3,
+};
+
 /**
  * struct ieee80211_vht_operation - VHT operation IE
  *
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 0a8f83d142f9..8d8bf7136386 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -371,6 +371,8 @@ enum ieee80211_sta_flags {
 	IEEE80211_STA_RESET_SIGNAL_AVE	= BIT(9),
 	IEEE80211_STA_DISABLE_40MHZ	= BIT(10),
 	IEEE80211_STA_DISABLE_VHT	= BIT(11),
+	IEEE80211_STA_DISABLE_80P80MHZ	= BIT(12),
+	IEEE80211_STA_DISABLE_160MHZ	= BIT(13),
 };
 
 struct ieee80211_mgd_auth_data {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index d2a4f78b4b0f..35d8cffc973a 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -354,6 +354,16 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata,
 	/* determine capability flags */
 	cap = vht_cap.cap;
 
+	if (sdata->u.mgd.flags & IEEE80211_STA_DISABLE_80P80MHZ) {
+		cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ;
+		cap |= IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ;
+	}
+
+	if (sdata->u.mgd.flags & IEEE80211_STA_DISABLE_160MHZ) {
+		cap &= ~IEEE80211_VHT_CAP_SHORT_GI_160;
+		cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ;
+	}
+
 	/* reserve and fill IE */
 	pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2);
 	ieee80211_ie_build_vht_cap(pos, &vht_cap, cap);
@@ -543,6 +553,10 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		offset = noffset;
 	}
 
+	if (WARN_ON_ONCE((ifmgd->flags & IEEE80211_STA_DISABLE_HT) &&
+			 !(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)))
+		ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
+
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT))
 		ieee80211_add_ht_ie(sdata, skb, assoc_data->ap_ht_param,
 				    sband, chan, sdata->smps_mode);
@@ -3183,23 +3197,270 @@ int ieee80211_max_network_latency(struct notifier_block *nb,
 	return 0;
 }
 
+static u32 chandef_downgrade(struct cfg80211_chan_def *c)
+{
+	u32 ret;
+	int tmp;
+
+	switch (c->width) {
+	case NL80211_CHAN_WIDTH_20:
+		c->width = NL80211_CHAN_WIDTH_20_NOHT;
+		ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		c->width = NL80211_CHAN_WIDTH_20;
+		c->center_freq1 = c->chan->center_freq;
+		ret = IEEE80211_STA_DISABLE_40MHZ |
+		      IEEE80211_STA_DISABLE_VHT;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		tmp = (30 + c->chan->center_freq - c->center_freq1)/20;
+		/* n_P40 */
+		tmp /= 2;
+		/* freq_P40 */
+		c->center_freq1 = c->center_freq1 - 20 + 40 * tmp;
+		c->width = NL80211_CHAN_WIDTH_40;
+		ret = IEEE80211_STA_DISABLE_VHT;
+		break;
+	case NL80211_CHAN_WIDTH_80P80:
+		c->center_freq2 = 0;
+		c->width = NL80211_CHAN_WIDTH_80;
+		ret = IEEE80211_STA_DISABLE_80P80MHZ |
+		      IEEE80211_STA_DISABLE_160MHZ;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		/* n_P20 */
+		tmp = (70 + c->chan->center_freq - c->center_freq1)/20;
+		/* n_P80 */
+		tmp /= 4;
+		c->center_freq1 = c->center_freq1 - 40 + 80 * tmp;
+		c->width = NL80211_CHAN_WIDTH_80;
+		ret = IEEE80211_STA_DISABLE_80P80MHZ |
+		      IEEE80211_STA_DISABLE_160MHZ;
+		break;
+	default:
+	case NL80211_CHAN_WIDTH_20_NOHT:
+		WARN_ON_ONCE(1);
+		c->width = NL80211_CHAN_WIDTH_20_NOHT;
+		ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT;
+		break;
+	}
+
+	WARN_ON_ONCE(!cfg80211_chandef_valid(c));
+
+	return ret;
+}
+
+static u32
+ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
+			     struct ieee80211_supported_band *sband,
+			     struct ieee80211_channel *channel,
+			     const struct ieee80211_ht_operation *ht_oper,
+			     const struct ieee80211_vht_operation *vht_oper,
+			     struct cfg80211_chan_def *chandef)
+{
+	struct cfg80211_chan_def vht_chandef;
+	u32 ht_cfreq, ret;
+
+	chandef->chan = channel;
+	chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
+	chandef->center_freq1 = channel->center_freq;
+	chandef->center_freq2 = 0;
+
+	if (!ht_oper || !sband->ht_cap.ht_supported) {
+		ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT;
+		goto out;
+	}
+
+	chandef->width = NL80211_CHAN_WIDTH_20;
+
+	ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan,
+						  channel->band);
+	/* check that channel matches the right operating channel */
+	if (channel->center_freq != ht_cfreq) {
+		/*
+		 * It's possible that some APs are confused here;
+		 * Netgear WNDR3700 sometimes reports 4 higher than
+		 * the actual channel in association responses, but
+		 * since we look at probe response/beacon data here
+		 * it should be OK.
+		 */
+		sdata_info(sdata,
+			   "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n",
+			   channel->center_freq, ht_cfreq,
+			   ht_oper->primary_chan, channel->band);
+		ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT;
+		goto out;
+	}
+
+	/* check 40 MHz support, if we have it */
+	if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) {
+		switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) {
+		case IEEE80211_HT_PARAM_CHA_SEC_ABOVE:
+			chandef->width = NL80211_CHAN_WIDTH_40;
+			chandef->center_freq1 += 10;
+			break;
+		case IEEE80211_HT_PARAM_CHA_SEC_BELOW:
+			chandef->width = NL80211_CHAN_WIDTH_40;
+			chandef->center_freq1 -= 10;
+			break;
+		}
+	} else {
+		/* 40 MHz (and 80 MHz) must be supported for VHT */
+		ret = IEEE80211_STA_DISABLE_VHT;
+		goto out;
+	}
+
+	if (!vht_oper || !sband->vht_cap.vht_supported) {
+		ret = IEEE80211_STA_DISABLE_VHT;
+		goto out;
+	}
+
+	vht_chandef.chan = channel;
+	vht_chandef.center_freq1 =
+		ieee80211_channel_to_frequency(vht_oper->center_freq_seg1_idx,
+					       channel->band);
+	vht_chandef.center_freq2 = 0;
+
+	if (vht_oper->center_freq_seg2_idx)
+		vht_chandef.center_freq2 =
+			ieee80211_channel_to_frequency(
+				vht_oper->center_freq_seg2_idx,
+				channel->band);
+
+	switch (vht_oper->chan_width) {
+	case IEEE80211_VHT_CHANWIDTH_USE_HT:
+		vht_chandef.width = chandef->width;
+		break;
+	case IEEE80211_VHT_CHANWIDTH_80MHZ:
+		vht_chandef.width = NL80211_CHAN_WIDTH_80;
+		break;
+	case IEEE80211_VHT_CHANWIDTH_160MHZ:
+		vht_chandef.width = NL80211_CHAN_WIDTH_160;
+		break;
+	case IEEE80211_VHT_CHANWIDTH_80P80MHZ:
+		vht_chandef.width = NL80211_CHAN_WIDTH_80P80;
+		break;
+	default:
+		sdata_info(sdata,
+			   "AP VHT operation IE has invalid channel width (%d), disable VHT\n",
+			   vht_oper->chan_width);
+		ret = IEEE80211_STA_DISABLE_VHT;
+		goto out;
+	}
+
+	if (!cfg80211_chandef_valid(&vht_chandef)) {
+		sdata_info(sdata,
+			   "AP VHT information is invalid, disable VHT\n");
+		ret = IEEE80211_STA_DISABLE_VHT;
+		goto out;
+	}
+
+	if (cfg80211_chandef_identical(chandef, &vht_chandef)) {
+		ret = 0;
+		goto out;
+	}
+
+	if (!cfg80211_chandef_compatible(chandef, &vht_chandef)) {
+		sdata_info(sdata,
+			   "AP VHT information doesn't match HT, disable VHT\n");
+		ret = IEEE80211_STA_DISABLE_VHT;
+		goto out;
+	}
+
+	*chandef = vht_chandef;
+
+	ret = 0;
+
+	while (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef,
+					IEEE80211_CHAN_DISABLED)) {
+		if (WARN_ON(chandef->width == NL80211_CHAN_WIDTH_20_NOHT)) {
+			ret = IEEE80211_STA_DISABLE_HT |
+			      IEEE80211_STA_DISABLE_VHT;
+			goto out;
+		}
+
+		ret = chandef_downgrade(chandef);
+	}
+
+	if (chandef->width != vht_chandef.width)
+		sdata_info(sdata,
+			   "local regulatory prevented using AP HT/VHT configuration, downgraded\n");
+
+out:
+	WARN_ON_ONCE(!cfg80211_chandef_valid(chandef));
+	return ret;
+}
+
+static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata,
+				     struct cfg80211_bss *cbss)
+{
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	const u8 *ht_cap_ie, *vht_cap_ie;
+	const struct ieee80211_ht_cap *ht_cap;
+	const struct ieee80211_vht_cap *vht_cap;
+	u8 chains = 1;
+
+	if (ifmgd->flags & IEEE80211_STA_DISABLE_HT)
+		return chains;
+
+	ht_cap_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY,
+				     cbss->information_elements,
+				     cbss->len_information_elements);
+	if (ht_cap_ie && ht_cap_ie[1] >= sizeof(*ht_cap)) {
+		ht_cap = (void *)(ht_cap_ie + 2);
+		chains = ieee80211_mcs_to_chains(&ht_cap->mcs);
+		/*
+		 * TODO: use "Tx Maximum Number Spatial Streams Supported" and
+		 *	 "Tx Unequal Modulation Supported" fields.
+		 */
+	}
+
+	if (ifmgd->flags & IEEE80211_STA_DISABLE_VHT)
+		return chains;
+
+	vht_cap_ie = cfg80211_find_ie(WLAN_EID_VHT_CAPABILITY,
+				      cbss->information_elements,
+				      cbss->len_information_elements);
+	if (vht_cap_ie && vht_cap_ie[1] >= sizeof(*vht_cap)) {
+		u8 nss;
+		u16 tx_mcs_map;
+
+		vht_cap = (void *)(vht_cap_ie + 2);
+		tx_mcs_map = le16_to_cpu(vht_cap->supp_mcs.tx_mcs_map);
+		for (nss = 8; nss > 0; nss--) {
+			if (((tx_mcs_map >> (2 * (nss - 1))) & 3) !=
+					IEEE80211_VHT_MCS_NOT_SUPPORTED)
+				break;
+		}
+		/* TODO: use "Tx Highest Supported Long GI Data Rate" field? */
+		chains = max(chains, nss);
+	}
+
+	return chains;
+}
+
 static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 				  struct cfg80211_bss *cbss)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
-	int ht_cfreq;
-	enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT;
-	const u8 *ht_oper_ie;
 	const struct ieee80211_ht_operation *ht_oper = NULL;
+	const struct ieee80211_vht_operation *vht_oper = NULL;
 	struct ieee80211_supported_band *sband;
 	struct cfg80211_chan_def chandef;
+	int ret;
 
 	sband = local->hw.wiphy->bands[cbss->channel->band];
 
-	ifmgd->flags &= ~IEEE80211_STA_DISABLE_40MHZ;
+	ifmgd->flags &= ~(IEEE80211_STA_DISABLE_40MHZ |
+			  IEEE80211_STA_DISABLE_80P80MHZ |
+			  IEEE80211_STA_DISABLE_160MHZ);
+
+	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT) &&
+	    sband->ht_cap.ht_supported) {
+		const u8 *ht_oper_ie;
 
-	if (sband->ht_cap.ht_supported) {
 		ht_oper_ie = cfg80211_find_ie(WLAN_EID_HT_OPERATION,
 					      cbss->information_elements,
 					      cbss->len_information_elements);
@@ -3207,82 +3468,45 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 			ht_oper = (void *)(ht_oper_ie + 2);
 	}
 
-	if (ht_oper) {
-		ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan,
-							  cbss->channel->band);
-		/* check that channel matches the right operating channel */
-		if (cbss->channel->center_freq != ht_cfreq) {
-			/*
-			 * It's possible that some APs are confused here;
-			 * Netgear WNDR3700 sometimes reports 4 higher than
-			 * the actual channel in association responses, but
-			 * since we look at probe response/beacon data here
-			 * it should be OK.
-			 */
+	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT) &&
+	    sband->vht_cap.vht_supported) {
+		const u8 *vht_oper_ie;
+
+		vht_oper_ie = cfg80211_find_ie(WLAN_EID_VHT_OPERATION,
+					       cbss->information_elements,
+					       cbss->len_information_elements);
+		if (vht_oper_ie && vht_oper_ie[1] >= sizeof(*vht_oper))
+			vht_oper = (void *)(vht_oper_ie + 2);
+		if (vht_oper && !ht_oper) {
+			vht_oper = NULL;
 			sdata_info(sdata,
-				   "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n",
-				   cbss->channel->center_freq,
-				   ht_cfreq, ht_oper->primary_chan,
-				   cbss->channel->band);
-			ht_oper = NULL;
+				   "AP advertised VHT without HT, disabling both\n");
+			sdata->flags |= IEEE80211_STA_DISABLE_HT;
+			sdata->flags |= IEEE80211_STA_DISABLE_VHT;
 		}
 	}
 
-	if (ht_oper) {
-		/*
-		 * cfg80211 already verified that the channel itself can
-		 * be used, but it didn't check that we can do the right
-		 * HT type, so do that here as well. If HT40 isn't allowed
-		 * on this channel, disable 40 MHz operation.
-		 */
-		const u8 *ht_cap_ie;
-		const struct ieee80211_ht_cap *ht_cap;
-		u8 chains = 1;
-
-		channel_type = NL80211_CHAN_HT20;
-
-		if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) {
-			switch (ht_oper->ht_param &
-					IEEE80211_HT_PARAM_CHA_SEC_OFFSET) {
-			case IEEE80211_HT_PARAM_CHA_SEC_ABOVE:
-				if (cbss->channel->flags &
-						IEEE80211_CHAN_NO_HT40PLUS)
-					ifmgd->flags |=
-						IEEE80211_STA_DISABLE_40MHZ;
-				else
-					channel_type = NL80211_CHAN_HT40PLUS;
-				break;
-			case IEEE80211_HT_PARAM_CHA_SEC_BELOW:
-				if (cbss->channel->flags &
-						IEEE80211_CHAN_NO_HT40MINUS)
-					ifmgd->flags |=
-						IEEE80211_STA_DISABLE_40MHZ;
-				else
-					channel_type = NL80211_CHAN_HT40MINUS;
-				break;
-			}
-		}
+	ifmgd->flags |= ieee80211_determine_chantype(sdata, sband,
+						     cbss->channel,
+						     ht_oper, vht_oper,
+						     &chandef);
 
-		ht_cap_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY,
-					     cbss->information_elements,
-					     cbss->len_information_elements);
-		if (ht_cap_ie && ht_cap_ie[1] >= sizeof(*ht_cap)) {
-			ht_cap = (void *)(ht_cap_ie + 2);
-			chains = ieee80211_mcs_to_chains(&ht_cap->mcs);
-		}
-		sdata->needed_rx_chains = min(chains, local->rx_chains);
-	} else {
-		sdata->needed_rx_chains = 1;
-		sdata->u.mgd.flags |= IEEE80211_STA_DISABLE_HT;
-	}
+	sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
+				      local->rx_chains);
 
 	/* will change later if needed */
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 
-	ieee80211_vif_release_channel(sdata);
-	cfg80211_chandef_create(&chandef, cbss->channel, channel_type);
-	return ieee80211_vif_use_channel(sdata, &chandef,
-					 IEEE80211_CHANCTX_SHARED);
+	/*
+	 * If this fails (possibly due to channel context sharing
+	 * on incompatible channels, e.g. 80+80 and 160 sharing the
+	 * same control channel) try to use a smaller bandwidth.
+	 */
+	ret = ieee80211_vif_use_channel(sdata, &chandef,
+					IEEE80211_CHANCTX_SHARED);
+	while (ret && chandef.width != NL80211_CHAN_WIDTH_20_NOHT)
+		ifmgd->flags |= chandef_downgrade(&chandef);
+	return ret;
 }
 
 static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
-- 
cgit v1.2.3-55-g7522


From 5164892184d1b9ce19e45e97e9ca405ea8b9ceb2 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Thu, 22 Nov 2012 23:00:18 +0100
Subject: mac80211: support (partial) VHT radiotap information

Add some information that we have about VHT to radiotap.
This at least lets one see the MCS and NSS information.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/ieee80211_radiotap.h | 24 ++++++++++++++++++++++++
 include/net/mac80211.h           |  5 +++++
 net/mac80211/main.c              |  2 ++
 net/mac80211/rx.c                | 40 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 71 insertions(+)

(limited to 'include')

diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index 7f0df133d119..c3999632e616 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -186,6 +186,10 @@ struct ieee80211_radiotap_header {
  * IEEE80211_RADIOTAP_AMPDU_STATUS	u32, u16, u8, u8	unitless
  *
  *	Contains the AMPDU information for the subframe.
+ *
+ * IEEE80211_RADIOTAP_VHT	u16, u8, u8, u8[4], u8, u8, u16
+ *
+ *	Contains VHT information about this frame.
  */
 enum ieee80211_radiotap_type {
 	IEEE80211_RADIOTAP_TSFT = 0,
@@ -209,6 +213,7 @@ enum ieee80211_radiotap_type {
 
 	IEEE80211_RADIOTAP_MCS = 19,
 	IEEE80211_RADIOTAP_AMPDU_STATUS = 20,
+	IEEE80211_RADIOTAP_VHT = 21,
 
 	/* valid in every it_present bitmap, even vendor namespaces */
 	IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29,
@@ -282,6 +287,25 @@ enum ieee80211_radiotap_type {
 #define IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_ERR		0x0010
 #define IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_KNOWN	0x0020
 
+/* For IEEE80211_RADIOTAP_VHT */
+#define IEEE80211_RADIOTAP_VHT_KNOWN_STBC			0x0001
+#define IEEE80211_RADIOTAP_VHT_KNOWN_TXOP_PS_NA			0x0002
+#define IEEE80211_RADIOTAP_VHT_KNOWN_GI				0x0004
+#define IEEE80211_RADIOTAP_VHT_KNOWN_SGI_NSYM_DIS		0x0008
+#define IEEE80211_RADIOTAP_VHT_KNOWN_LDPC_EXTRA_OFDM_SYM	0x0010
+#define IEEE80211_RADIOTAP_VHT_KNOWN_BEAMFORMED			0x0020
+#define IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH			0x0040
+#define IEEE80211_RADIOTAP_VHT_KNOWN_GROUP_ID			0x0080
+#define IEEE80211_RADIOTAP_VHT_KNOWN_PARTIAL_AID		0x0100
+
+#define IEEE80211_RADIOTAP_VHT_FLAG_STBC			0x01
+#define IEEE80211_RADIOTAP_VHT_FLAG_TXOP_PS_NA			0x02
+#define IEEE80211_RADIOTAP_VHT_FLAG_SGI				0x04
+#define IEEE80211_RADIOTAP_VHT_FLAG_SGI_NSYM_M10_9		0x08
+#define IEEE80211_RADIOTAP_VHT_FLAG_LDPC_EXTRA_OFDM_SYM		0x10
+#define IEEE80211_RADIOTAP_VHT_FLAG_BEAMFORMED			0x20
+
+
 /* helpers */
 static inline int ieee80211_get_radiotap_len(unsigned char *data)
 {
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index db7680acd0da..e806f1d81f66 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1473,6 +1473,10 @@ enum ieee80211_hw_flags {
  *	include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_* values, only
  *	adding _BW is supported today.
  *
+ * @radiotap_vht_details: lists which VHT MCS information the HW reports,
+ *	the default is _GI | _BANDWIDTH.
+ *	Use the %IEEE80211_RADIOTAP_VHT_KNOWN_* values.
+ *
  * @netdev_features: netdev features to be set in each netdev created
  *	from this HW. Note only HW checksum features are currently
  *	compatible with mac80211. Other feature bits will be rejected.
@@ -1499,6 +1503,7 @@ struct ieee80211_hw {
 	u8 max_tx_aggregation_subframes;
 	u8 offchannel_tx_hw_queue;
 	u8 radiotap_mcs_details;
+	u16 radiotap_vht_details;
 	netdev_features_t netdev_features;
 };
 
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 6e933409979a..c4ed83b74e52 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -638,6 +638,8 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	local->hw.radiotap_mcs_details = IEEE80211_RADIOTAP_MCS_HAVE_MCS |
 					 IEEE80211_RADIOTAP_MCS_HAVE_GI |
 					 IEEE80211_RADIOTAP_MCS_HAVE_BW;
+	local->hw.radiotap_vht_details = IEEE80211_RADIOTAP_VHT_KNOWN_GI |
+					 IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH;
 	local->user_power_level = IEEE80211_UNSET_POWER_LEVEL;
 	wiphy->ht_capa_mod_mask = &mac80211_ht_capa_mod_mask;
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 825f33cf7bbc..9b13b8b24245 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -111,6 +111,11 @@ ieee80211_rx_radiotap_space(struct ieee80211_local *local,
 		len += 8;
 	}
 
+	if (status->flag & RX_FLAG_VHT) {
+		len = ALIGN(len, 2);
+		len += 12;
+	}
+
 	if (status->vendor_radiotap_len) {
 		if (WARN_ON_ONCE(status->vendor_radiotap_align == 0))
 			status->vendor_radiotap_align = 1;
@@ -297,6 +302,41 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		*pos++ = 0;
 	}
 
+	if (status->flag & RX_FLAG_VHT) {
+		u16 known = local->hw.radiotap_vht_details;
+
+		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT);
+		/* known field - how to handle 80+80? */
+		if (status->flag & RX_FLAG_80P80MHZ)
+			known &= ~IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH;
+		put_unaligned_le16(known, pos);
+		pos += 2;
+		/* flags */
+		if (status->flag & RX_FLAG_SHORT_GI)
+			*pos |= IEEE80211_RADIOTAP_VHT_FLAG_SGI;
+		pos++;
+		/* bandwidth */
+		if (status->flag & RX_FLAG_80MHZ)
+			*pos++ = 4;
+		else if (status->flag & RX_FLAG_80P80MHZ)
+			*pos++ = 0; /* marked not known above */
+		else if (status->flag & RX_FLAG_160MHZ)
+			*pos++ = 11;
+		else if (status->flag & RX_FLAG_40MHZ)
+			*pos++ = 1;
+		else /* 20 MHz */
+			*pos++ = 0;
+		/* MCS/NSS */
+		*pos = (status->rate_idx << 4) | status->vht_nss;
+		pos += 4;
+		/* coding field */
+		pos++;
+		/* group ID */
+		pos++;
+		/* partial_aid */
+		pos += 2;
+	}
+
 	if (status->vendor_radiotap_len) {
 		/* ensure 2 byte alignment for the vendor field as required */
 		if ((pos - (u8 *)rthdr) & 1)
-- 
cgit v1.2.3-55-g7522


From 53cabad70ecf0c245b41285de64a74a6c3ee9933 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Wed, 14 Nov 2012 15:17:28 +0100
Subject: nl80211: support P2P GO powersave configuration

If a driver supports P2P GO powersave, allow it to
set the new feature flags for it and allow userspace
to configure the parameters for it. This can be done
at GO startup and later changed with SET_BSS.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  7 ++++++
 include/uapi/linux/nl80211.h | 16 +++++++++++++
 net/wireless/nl80211.c       | 56 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 79 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index a238f41e55c2..731b48fa238b 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -538,6 +538,8 @@ struct cfg80211_beacon_data {
  * @privacy: the BSS uses privacy
  * @auth_type: Authentication type (algorithm)
  * @inactivity_timeout: time in seconds to determine station's inactivity.
+ * @p2p_ctwindow: P2P CT Window
+ * @p2p_opp_ps: P2P opportunistic PS
  */
 struct cfg80211_ap_settings {
 	struct cfg80211_chan_def chandef;
@@ -552,6 +554,8 @@ struct cfg80211_ap_settings {
 	bool privacy;
 	enum nl80211_auth_type auth_type;
 	int inactivity_timeout;
+	u8 p2p_ctwindow;
+	bool p2p_opp_ps;
 };
 
 /**
@@ -913,6 +917,8 @@ struct mpath_info {
  * @ap_isolate: do not forward packets between connected stations
  * @ht_opmode: HT Operation mode
  * 	(u16 = opmode, -1 = do not change)
+ * @p2p_ctwindow: P2P CT Window (-1 = no change)
+ * @p2p_opp_ps: P2P opportunistic PS (-1 = no change)
  */
 struct bss_parameters {
 	int use_cts_prot;
@@ -922,6 +928,7 @@ struct bss_parameters {
 	u8 basic_rates_len;
 	int ap_isolate;
 	int ht_opmode;
+	s8 p2p_ctwindow, p2p_opp_ps;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 33a417481ad8..e3e19f8b16f2 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1303,6 +1303,13 @@ enum nl80211_commands {
  *
  * @NL80211_ATTR_SCAN_FLAGS: scan request control flags (u32)
  *
+ * @NL80211_ATTR_P2P_CTWINDOW: P2P GO Client Traffic Window (u8), used with
+ *	the START_AP and SET_BSS commands
+ * @NL80211_ATTR_P2P_OPPPS: P2P GO opportunistic PS (u8), used with the
+ *	START_AP and SET_BSS commands. This can have the values 0 or 1;
+ *	if not given in START_AP 0 is assumed, if not given in SET_BSS
+ *	no change is made.
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1570,6 +1577,9 @@ enum nl80211_attrs {
 	NL80211_ATTR_CENTER_FREQ1,
 	NL80211_ATTR_CENTER_FREQ2,
 
+	NL80211_ATTR_P2P_CTWINDOW,
+	NL80211_ATTR_P2P_OPPPS,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -3126,6 +3136,10 @@ enum nl80211_ap_sme_features {
  * @NL80211_FEATURE_NEED_OBSS_SCAN: The driver expects userspace to perform
  *	OBSS scans and generate 20/40 BSS coex reports. This flag is used only
  *	for drivers implementing the CONNECT API, for AUTH/ASSOC it is implied.
+ * @NL80211_FEATURE_P2P_GO_CTWIN: P2P GO implementation supports CT Window
+ *	setting
+ * @NL80211_FEATURE_P2P_GO_OPPPS: P2P GO implementation supports opportunistic
+ *	powersave
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -3139,6 +3153,8 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_AP_SCAN				= 1 << 8,
 	NL80211_FEATURE_VIF_TXPOWER			= 1 << 9,
 	NL80211_FEATURE_NEED_OBSS_SCAN			= 1 << 10,
+	NL80211_FEATURE_P2P_GO_CTWIN			= 1 << 11,
+	NL80211_FEATURE_P2P_GO_OPPPS			= 1 << 12,
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index eb0aa71a02b3..7f53aafd47f7 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -363,6 +363,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_SAE_DATA] = { .type = NLA_BINARY, },
 	[NL80211_ATTR_VHT_CAPABILITY] = { .len = NL80211_VHT_CAPABILITY_LEN },
 	[NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 },
+	[NL80211_ATTR_P2P_CTWINDOW] = { .type = NLA_U8 },
+	[NL80211_ATTR_P2P_OPPPS] = { .type = NLA_U8 },
 };
 
 /* policy for the key attributes */
@@ -2702,6 +2704,32 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 			info->attrs[NL80211_ATTR_INACTIVITY_TIMEOUT]);
 	}
 
+	if (info->attrs[NL80211_ATTR_P2P_CTWINDOW]) {
+		if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO)
+			return -EINVAL;
+		params.p2p_ctwindow =
+			nla_get_u8(info->attrs[NL80211_ATTR_P2P_CTWINDOW]);
+		if (params.p2p_ctwindow > 127)
+			return -EINVAL;
+		if (params.p2p_ctwindow != 0 &&
+		    !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_CTWIN))
+			return -EINVAL;
+	}
+
+	if (info->attrs[NL80211_ATTR_P2P_OPPPS]) {
+		u8 tmp;
+
+		if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO)
+			return -EINVAL;
+		tmp = nla_get_u8(info->attrs[NL80211_ATTR_P2P_OPPPS]);
+		if (tmp > 1)
+			return -EINVAL;
+		params.p2p_opp_ps = tmp;
+		if (params.p2p_opp_ps != 0 &&
+		    !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_OPPPS))
+			return -EINVAL;
+	}
+
 	if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) {
 		err = nl80211_parse_chandef(rdev, info, &params.chandef);
 		if (err)
@@ -3668,6 +3696,8 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info)
 	params.use_short_slot_time = -1;
 	params.ap_isolate = -1;
 	params.ht_opmode = -1;
+	params.p2p_ctwindow = -1;
+	params.p2p_opp_ps = -1;
 
 	if (info->attrs[NL80211_ATTR_BSS_CTS_PROT])
 		params.use_cts_prot =
@@ -3690,6 +3720,32 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info)
 		params.ht_opmode =
 			nla_get_u16(info->attrs[NL80211_ATTR_BSS_HT_OPMODE]);
 
+	if (info->attrs[NL80211_ATTR_P2P_CTWINDOW]) {
+		if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO)
+			return -EINVAL;
+		params.p2p_ctwindow =
+			nla_get_s8(info->attrs[NL80211_ATTR_P2P_CTWINDOW]);
+		if (params.p2p_ctwindow < 0)
+			return -EINVAL;
+		if (params.p2p_ctwindow != 0 &&
+		    !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_CTWIN))
+			return -EINVAL;
+	}
+
+	if (info->attrs[NL80211_ATTR_P2P_OPPPS]) {
+		u8 tmp;
+
+		if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO)
+			return -EINVAL;
+		tmp = nla_get_u8(info->attrs[NL80211_ATTR_P2P_OPPPS]);
+		if (tmp > 1)
+			return -EINVAL;
+		params.p2p_opp_ps = tmp;
+		if (params.p2p_opp_ps &&
+		    !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_OPPPS))
+			return -EINVAL;
+	}
+
 	if (!rdev->ops->change_bss)
 		return -EOPNOTSUPP;
 
-- 
cgit v1.2.3-55-g7522


From 77b71b370ed06c75bdebef09be438d5275f70fc1 Mon Sep 17 00:00:00 2001
From: Thomas Abraham
Date: Tue, 27 Nov 2012 14:04:32 +0530
Subject: regulator: add device tree support for max8997

Add device tree based discovery support for max8997.

Signed-off-by: Thomas Abraham <thomas.abraham@linaro.org>
Acked-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Reviewed-by: Tomasz Figa <t.figa@samsung.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 .../bindings/regulator/max8997-regulator.txt       | 146 ++++++++++++++++++++
 drivers/mfd/max8997.c                              |  73 +++++++++-
 drivers/regulator/max8997.c                        | 148 ++++++++++++++++++++-
 include/linux/mfd/max8997-private.h                |   1 +
 include/linux/mfd/max8997.h                        |   1 +
 5 files changed, 366 insertions(+), 3 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/regulator/max8997-regulator.txt

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/regulator/max8997-regulator.txt b/Documentation/devicetree/bindings/regulator/max8997-regulator.txt
new file mode 100644
index 000000000000..9fd69a18b0ba
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/max8997-regulator.txt
@@ -0,0 +1,146 @@
+* Maxim MAX8997 Voltage and Current Regulator
+
+The Maxim MAX8997 is a multi-function device which includes volatage and
+current regulators, rtc, charger controller and other sub-blocks. It is
+interfaced to the host controller using a i2c interface. Each sub-block is
+addressed by the host system using different i2c slave address. This document
+describes the bindings for 'pmic' sub-block of max8997.
+
+Required properties:
+- compatible: Should be "maxim,max8997-pmic".
+- reg: Specifies the i2c slave address of the pmic block. It should be 0x66.
+
+- max8997,pmic-buck1-dvs-voltage: A set of 8 voltage values in micro-volt (uV)
+  units for buck1 when changing voltage using gpio dvs. Refer to [1] below
+  for additional information.
+
+- max8997,pmic-buck2-dvs-voltage: A set of 8 voltage values in micro-volt (uV)
+  units for buck2 when changing voltage using gpio dvs. Refer to [1] below
+  for additional information.
+
+- max8997,pmic-buck5-dvs-voltage: A set of 8 voltage values in micro-volt (uV)
+  units for buck5 when changing voltage using gpio dvs. Refer to [1] below
+  for additional information.
+
+[1] If none of the 'max8997,pmic-buck[1/2/5]-uses-gpio-dvs' optional
+    property is specified, the 'max8997,pmic-buck[1/2/5]-dvs-voltage'
+    property should specify atleast one voltage level (which would be a
+    safe operating voltage).
+
+    If either of the 'max8997,pmic-buck[1/2/5]-uses-gpio-dvs' optional
+    property is specified, then all the eigth voltage values for the
+    'max8997,pmic-buck[1/2/5]-dvs-voltage' should be specified.
+
+Optional properties:
+- interrupt-parent: Specifies the phandle of the interrupt controller to which
+  the interrupts from max8997 are delivered to.
+- interrupts: Interrupt specifiers for two interrupt sources.
+  - First interrupt specifier is for 'irq1' interrupt.
+  - Second interrupt specifier is for 'alert' interrupt.
+- max8997,pmic-buck1-uses-gpio-dvs: 'buck1' can be controlled by gpio dvs.
+- max8997,pmic-buck2-uses-gpio-dvs: 'buck2' can be controlled by gpio dvs.
+- max8997,pmic-buck5-uses-gpio-dvs: 'buck5' can be controlled by gpio dvs.
+
+Additional properties required if either of the optional properties are used:
+- max8997,pmic-ignore-gpiodvs-side-effect: When GPIO-DVS mode is used for
+  multiple bucks, changing the voltage value of one of the bucks may affect
+  that of another buck, which is the side effect of the change (set_voltage).
+  Use this property to ignore such side effects and change the voltage.
+
+- max8997,pmic-buck125-default-dvs-idx: Default voltage setting selected from
+  the possible 8 options selectable by the dvs gpios. The value of this
+  property should be between 0 and 7. If not specified or if out of range, the
+  default value of this property is set to 0.
+
+- max8997,pmic-buck125-dvs-gpios: GPIO specifiers for three host gpio's used
+  for dvs. The format of the gpio specifier depends in the gpio controller.
+
+Regulators: The regulators of max8997 that have to be instantiated should be
+included in a sub-node named 'regulators'. Regulator nodes included in this
+sub-node should be of the format as listed below.
+
+	regulator_name {
+		standard regulator bindings here
+	};
+
+The following are the names of the regulators that the max8997 pmic block
+supports. Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number
+as per the datasheet of max8997.
+
+	- LDOn
+		  - valid values for n are 1 to 18 and 21
+		  - Example: LDO0, LD01, LDO2, LDO21
+	- BUCKn
+		  - valid values for n are 1 to 7.
+		  - Example: BUCK1, BUCK2, BUCK3, BUCK7
+
+	- ENVICHG: Battery Charging Current Monitor Output. This is a fixed
+		   voltage type regulator
+
+	- ESAFEOUT1: (ldo19)
+	- ESAFEOUT2: (ld020)
+
+	- CHARGER_CV: main battery charger voltage control
+	- CHARGER: main battery charger current control
+	- CHARGER_TOPOFF: end of charge current threshold level
+
+The bindings inside the regulator nodes use the standard regulator bindings
+which are documented elsewhere.
+
+Example:
+
+	max8997_pmic@66 {
+		compatible = "maxim,max8997-pmic";
+		interrupt-parent = <&wakeup_eint>;
+		reg = <0x66>;
+		interrupts = <4 0>, <3 0>;
+
+		max8997,pmic-buck1-uses-gpio-dvs;
+		max8997,pmic-buck2-uses-gpio-dvs;
+		max8997,pmic-buck5-uses-gpio-dvs;
+
+		max8997,pmic-ignore-gpiodvs-side-effect;
+		max8997,pmic-buck125-default-dvs-idx = <0>;
+
+		max8997,pmic-buck125-dvs-gpios = <&gpx0 0 1 0 0>, /* SET1 */
+						 <&gpx0 1 1 0 0>, /* SET2 */
+						 <&gpx0 2 1 0 0>; /* SET3 */
+
+		max8997,pmic-buck1-dvs-voltage = <1350000>, <1300000>,
+						 <1250000>, <1200000>,
+						 <1150000>, <1100000>,
+						 <1000000>, <950000>;
+
+		max8997,pmic-buck2-dvs-voltage = <1100000>, <1100000>,
+						 <1100000>, <1100000>,
+						 <1000000>, <1000000>,
+						 <1000000>, <1000000>;
+
+		max8997,pmic-buck5-dvs-voltage = <1200000>, <1200000>,
+						 <1200000>, <1200000>,
+						 <1200000>, <1200000>,
+						 <1200000>, <1200000>;
+
+		regulators {
+			ldo1_reg: LDO1 {
+				regulator-name = "VDD_ABB_3.3V";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			ldo2_reg: LDO2 {
+				regulator-name = "VDD_ALIVE_1.1V";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-always-on;
+			};
+
+			buck1_reg: BUCK1 {
+				regulator-name = "VDD_ARM_1.2V";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+		};
+	};
diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c
index f123517065ec..abd5c80c7cf5 100644
--- a/drivers/mfd/max8997.c
+++ b/drivers/mfd/max8997.c
@@ -21,8 +21,10 @@
  * This driver is based on max8998.c
  */
 
+#include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
+#include <linux/of_irq.h>
 #include <linux/interrupt.h>
 #include <linux/pm_runtime.h>
 #include <linux/module.h>
@@ -47,6 +49,13 @@ static struct mfd_cell max8997_devs[] = {
 	{ .name = "max8997-led", .id = 2 },
 };
 
+#ifdef CONFIG_OF
+static struct of_device_id __devinitdata max8997_pmic_dt_match[] = {
+	{ .compatible = "maxim,max8997-pmic", .data = TYPE_MAX8997 },
+	{},
+};
+#endif
+
 int max8997_read_reg(struct i2c_client *i2c, u8 reg, u8 *dest)
 {
 	struct max8997_dev *max8997 = i2c_get_clientdata(i2c);
@@ -123,6 +132,58 @@ int max8997_update_reg(struct i2c_client *i2c, u8 reg, u8 val, u8 mask)
 }
 EXPORT_SYMBOL_GPL(max8997_update_reg);
 
+#ifdef CONFIG_OF
+/*
+ * Only the common platform data elements for max8997 are parsed here from the
+ * device tree. Other sub-modules of max8997 such as pmic, rtc and others have
+ * to parse their own platform data elements from device tree.
+ *
+ * The max8997 platform data structure is instantiated here and the drivers for
+ * the sub-modules need not instantiate another instance while parsing their
+ * platform data.
+ */
+static struct max8997_platform_data *max8997_i2c_parse_dt_pdata(
+					struct device *dev)
+{
+	struct max8997_platform_data *pd;
+
+	pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL);
+	if (!pd) {
+		dev_err(dev, "could not allocate memory for pdata\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	pd->ono = irq_of_parse_and_map(dev->of_node, 1);
+
+	/*
+	 * ToDo: the 'wakeup' member in the platform data is more of a linux
+	 * specfic information. Hence, there is no binding for that yet and
+	 * not parsed here.
+	 */
+
+	return pd;
+}
+#else
+static struct max8997_platform_data *max8997_i2c_parse_dt_pdata(
+					struct device *dev)
+{
+	return 0;
+}
+#endif
+
+static inline int max8997_i2c_get_driver_data(struct i2c_client *i2c,
+						const struct i2c_device_id *id)
+{
+#ifdef CONFIG_OF
+	if (i2c->dev.of_node) {
+		const struct of_device_id *match;
+		match = of_match_node(max8997_pmic_dt_match, i2c->dev.of_node);
+		return (int)match->data;
+	}
+#endif
+	return (int)id->driver_data;
+}
+
 static int max8997_i2c_probe(struct i2c_client *i2c,
 			    const struct i2c_device_id *id)
 {
@@ -137,12 +198,21 @@ static int max8997_i2c_probe(struct i2c_client *i2c,
 	i2c_set_clientdata(i2c, max8997);
 	max8997->dev = &i2c->dev;
 	max8997->i2c = i2c;
-	max8997->type = id->driver_data;
+	max8997->type = max8997_i2c_get_driver_data(i2c, id);
 	max8997->irq = i2c->irq;
 
+	if (max8997->dev->of_node) {
+		pdata = max8997_i2c_parse_dt_pdata(max8997->dev);
+		if (IS_ERR(pdata)) {
+			ret = PTR_ERR(pdata);
+			goto err;
+		}
+	}
+
 	if (!pdata)
 		goto err;
 
+	max8997->pdata = pdata;
 	max8997->ono = pdata->ono;
 
 	mutex_init(&max8997->iolock);
@@ -434,6 +504,7 @@ static struct i2c_driver max8997_i2c_driver = {
 		   .name = "max8997",
 		   .owner = THIS_MODULE,
 		   .pm = &max8997_pm,
+		   .of_match_table = of_match_ptr(max8997_pmic_dt_match),
 	},
 	.probe = max8997_i2c_probe,
 	.remove = max8997_i2c_remove,
diff --git a/drivers/regulator/max8997.c b/drivers/regulator/max8997.c
index 64cf2ee38f6c..b56c4326853d 100644
--- a/drivers/regulator/max8997.c
+++ b/drivers/regulator/max8997.c
@@ -24,6 +24,7 @@
 #include <linux/bug.h>
 #include <linux/err.h>
 #include <linux/gpio.h>
+#include <linux/of_gpio.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -31,6 +32,7 @@
 #include <linux/regulator/machine.h>
 #include <linux/mfd/max8997.h>
 #include <linux/mfd/max8997-private.h>
+#include <linux/regulator/of_regulator.h>
 
 struct max8997_data {
 	struct device *dev;
@@ -933,10 +935,145 @@ static struct regulator_desc regulators[] = {
 				  max8997_charger_fixedstate_ops),
 };
 
+#ifdef CONFIG_OF
+static int max8997_pmic_dt_parse_dvs_gpio(struct max8997_dev *iodev,
+			struct max8997_platform_data *pdata,
+			struct device_node *pmic_np)
+{
+	int i, gpio;
+
+	for (i = 0; i < 3; i++) {
+		gpio = of_get_named_gpio(pmic_np,
+					"max8997,pmic-buck125-dvs-gpios", i);
+		if (!gpio_is_valid(gpio)) {
+			dev_err(iodev->dev, "invalid gpio[%d]: %d\n", i, gpio);
+			return -EINVAL;
+		}
+		pdata->buck125_gpios[i] = gpio;
+	}
+	return 0;
+}
+
+static int max8997_pmic_dt_parse_pdata(struct max8997_dev *iodev,
+					struct max8997_platform_data *pdata)
+{
+	struct device_node *pmic_np, *regulators_np, *reg_np;
+	struct max8997_regulator_data *rdata;
+	unsigned int i, dvs_voltage_nr = 1, ret;
+
+	pmic_np = iodev->dev->of_node;
+	if (!pmic_np) {
+		dev_err(iodev->dev, "could not find pmic sub-node\n");
+		return -ENODEV;
+	}
+
+	regulators_np = of_find_node_by_name(pmic_np, "regulators");
+	if (!regulators_np) {
+		dev_err(iodev->dev, "could not find regulators sub-node\n");
+		return -EINVAL;
+	}
+
+	/* count the number of regulators to be supported in pmic */
+	pdata->num_regulators = 0;
+	for_each_child_of_node(regulators_np, reg_np)
+		pdata->num_regulators++;
+
+	rdata = devm_kzalloc(iodev->dev, sizeof(*rdata) *
+				pdata->num_regulators, GFP_KERNEL);
+	if (!rdata) {
+		dev_err(iodev->dev, "could not allocate memory for "
+						"regulator data\n");
+		return -ENOMEM;
+	}
+
+	pdata->regulators = rdata;
+	for_each_child_of_node(regulators_np, reg_np) {
+		for (i = 0; i < ARRAY_SIZE(regulators); i++)
+			if (!of_node_cmp(reg_np->name, regulators[i].name))
+				break;
+
+		if (i == ARRAY_SIZE(regulators)) {
+			dev_warn(iodev->dev, "don't know how to configure "
+				"regulator %s\n", reg_np->name);
+			continue;
+		}
+
+		rdata->id = i;
+		rdata->initdata = of_get_regulator_init_data(
+						iodev->dev, reg_np);
+		rdata->reg_node = reg_np;
+		rdata++;
+	}
+
+	if (of_get_property(pmic_np, "max8997,pmic-buck1-uses-gpio-dvs", NULL))
+		pdata->buck1_gpiodvs = true;
+
+	if (of_get_property(pmic_np, "max8997,pmic-buck2-uses-gpio-dvs", NULL))
+		pdata->buck2_gpiodvs = true;
+
+	if (of_get_property(pmic_np, "max8997,pmic-buck5-uses-gpio-dvs", NULL))
+		pdata->buck5_gpiodvs = true;
+
+	if (pdata->buck1_gpiodvs || pdata->buck2_gpiodvs ||
+						pdata->buck5_gpiodvs) {
+		ret = max8997_pmic_dt_parse_dvs_gpio(iodev, pdata, pmic_np);
+		if (ret)
+			return -EINVAL;
+
+		if (of_property_read_u32(pmic_np,
+				"max8997,pmic-buck125-default-dvs-idx",
+				&pdata->buck125_default_idx)) {
+			pdata->buck125_default_idx = 0;
+		} else {
+			if (pdata->buck125_default_idx >= 8) {
+				pdata->buck125_default_idx = 0;
+				dev_info(iodev->dev, "invalid value for "
+				"default dvs index, using 0 instead\n");
+			}
+		}
+
+		if (of_get_property(pmic_np,
+			"max8997,pmic-ignore-gpiodvs-side-effect", NULL))
+			pdata->ignore_gpiodvs_side_effect = true;
+
+		dvs_voltage_nr = 8;
+	}
+
+	if (of_property_read_u32_array(pmic_np,
+				"max8997,pmic-buck1-dvs-voltage",
+				pdata->buck1_voltage, dvs_voltage_nr)) {
+		dev_err(iodev->dev, "buck1 voltages not specified\n");
+		return -EINVAL;
+	}
+
+	if (of_property_read_u32_array(pmic_np,
+				"max8997,pmic-buck2-dvs-voltage",
+				pdata->buck2_voltage, dvs_voltage_nr)) {
+		dev_err(iodev->dev, "buck2 voltages not specified\n");
+		return -EINVAL;
+	}
+
+	if (of_property_read_u32_array(pmic_np,
+				"max8997,pmic-buck5-dvs-voltage",
+				pdata->buck5_voltage, dvs_voltage_nr)) {
+		dev_err(iodev->dev, "buck5 voltages not specified\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+#else
+static int max8997_pmic_dt_parse_pdata(struct max8997_dev *iodev,
+					struct max8997_platform_data *pdata)
+{
+	return 0;
+}
+#endif /* CONFIG_OF */
+
 static __devinit int max8997_pmic_probe(struct platform_device *pdev)
 {
 	struct max8997_dev *iodev = dev_get_drvdata(pdev->dev.parent);
-	struct max8997_platform_data *pdata = dev_get_platdata(iodev->dev);
+	struct max8997_platform_data *pdata = iodev->pdata;
 	struct regulator_config config = { };
 	struct regulator_dev **rdev;
 	struct max8997_data *max8997;
@@ -944,11 +1081,17 @@ static __devinit int max8997_pmic_probe(struct platform_device *pdev)
 	int i, ret, size, nr_dvs;
 	u8 max_buck1 = 0, max_buck2 = 0, max_buck5 = 0;
 
-	if (!pdata) {
+	if (IS_ERR_OR_NULL(pdata)) {
 		dev_err(pdev->dev.parent, "No platform init data supplied.\n");
 		return -ENODEV;
 	}
 
+	if (iodev->dev->of_node) {
+		ret = max8997_pmic_dt_parse_pdata(iodev, pdata);
+		if (ret)
+			return ret;
+	}
+
 	max8997 = devm_kzalloc(&pdev->dev, sizeof(struct max8997_data),
 			       GFP_KERNEL);
 	if (!max8997)
@@ -1104,6 +1247,7 @@ static __devinit int max8997_pmic_probe(struct platform_device *pdev)
 		config.dev = max8997->dev;
 		config.init_data = pdata->regulators[i].initdata;
 		config.driver_data = max8997;
+		config.of_node = pdata->regulators[i].reg_node;
 
 		rdev[i] = regulator_register(&regulators[id], &config);
 		if (IS_ERR(rdev[i])) {
diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h
index 830152cfae33..6ae21bf47d64 100644
--- a/include/linux/mfd/max8997-private.h
+++ b/include/linux/mfd/max8997-private.h
@@ -316,6 +316,7 @@ enum max8997_irq {
 #define MAX8997_NUM_GPIO	12
 struct max8997_dev {
 	struct device *dev;
+	struct max8997_platform_data *pdata;
 	struct i2c_client *i2c; /* 0xcc / PMIC, Battery Control, and FLASH */
 	struct i2c_client *rtc; /* slave addr 0x0c */
 	struct i2c_client *haptic; /* slave addr 0x90 */
diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h
index 328d8e24b533..1d4a4fe6ac33 100644
--- a/include/linux/mfd/max8997.h
+++ b/include/linux/mfd/max8997.h
@@ -75,6 +75,7 @@ enum max8998_regulators {
 struct max8997_regulator_data {
 	int id;
 	struct regulator_init_data *initdata;
+	struct device_node *reg_node;
 };
 
 enum max8997_muic_usb_type {
-- 
cgit v1.2.3-55-g7522


From 33234e791de2ac3ea915158e042907748191cabd Mon Sep 17 00:00:00 2001
From: Axel Lin
Date: Tue, 27 Nov 2012 10:24:33 +0800
Subject: regulator: core: Allow specific minimal selector for starting linear
 mapping

Some drivers (at least 3 drivers) have such variant of linear mapping that
the first few selectors are invalid and the reset are linear mapping.
Let's support this case in core.

This patch adds linear_min_sel in struct regulator_desc,
so we can allow specific minimal selector for starting linear mapping.
Then extends regulator_[map|list]_voltage_linear() to support this feature.

Note that for selectors less than min_linear_index, we need count them to
n_voltages so regulator_list_voltage() won't fail while checking the boundary
for selector before calling list_voltage callback.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/regulator/core.c         | 6 ++++++
 include/linux/regulator/driver.h | 2 ++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index e872c8be080e..02a249b024b3 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1897,6 +1897,10 @@ int regulator_list_voltage_linear(struct regulator_dev *rdev,
 {
 	if (selector >= rdev->desc->n_voltages)
 		return -EINVAL;
+	if (selector < rdev->desc->linear_min_sel)
+		return 0;
+
+	selector -= rdev->desc->linear_min_sel;
 
 	return rdev->desc->min_uV + (rdev->desc->uV_step * selector);
 }
@@ -2120,6 +2124,8 @@ int regulator_map_voltage_linear(struct regulator_dev *rdev,
 	if (ret < 0)
 		return ret;
 
+	ret += rdev->desc->linear_min_sel;
+
 	/* Map back into a voltage to verify we're still in bounds */
 	voltage = rdev->desc->ops->list_voltage(rdev, ret);
 	if (voltage < min_uV || voltage > max_uV)
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 7932a3bf21bd..d9ce98a5028b 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -185,6 +185,7 @@ enum regulator_type {
  *
  * @min_uV: Voltage given by the lowest selector (if linear mapping)
  * @uV_step: Voltage increase with each selector (if linear mapping)
+ * @linear_min_sel: Minimal selector for starting linear mapping
  * @ramp_delay: Time to settle down after voltage change (unit: uV/us)
  * @volt_table: Voltage mapping table (if table based mapping)
  *
@@ -207,6 +208,7 @@ struct regulator_desc {
 
 	unsigned int min_uV;
 	unsigned int uV_step;
+	unsigned int linear_min_sel;
 	unsigned int ramp_delay;
 
 	const unsigned int *volt_table;
-- 
cgit v1.2.3-55-g7522


From ec809bd817dfa1905283468e4c813684ed4efe78 Mon Sep 17 00:00:00 2001
From: Krzysztof Mazur
Date: Tue, 6 Nov 2012 23:16:57 +0100
Subject: atm: add owner of push() callback to atmvcc

The atm is using atmvcc->push(vcc, NULL) callback to notify protocol
that vcc will be closed and protocol must detach from it. This callback
is usually used by protocol to decrement module usage count by module_put(),
but it leaves small window then module is still used after module_put().

Now the owner of push() callback is kept in atmvcc and
module_put(atmvcc->owner) is called after the protocol is detached from vcc.

Signed-off-by: Krzysztof Mazur <krzysiek@podlesie.net>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Acked-by: Chas Williams <chas@cmf.nrl.navy.mil>
---
 include/linux/atmdev.h | 1 +
 net/atm/common.c       | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 22ef21c33d0c..72db2af902a8 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -106,6 +106,7 @@ struct atm_vcc {
 	void		*dev_data;	/* per-device data */
 	void		*proto_data;	/* per-protocol data */
 	struct k_atm_aal_stats *stats;	/* pointer to AAL stats group */
+	struct module *owner;		/* owner of ->push function */
 	/* SVC part --- may move later ------------------------------------- */
 	short		itf;		/* interface number */
 	struct sockaddr_atmsvc local;
diff --git a/net/atm/common.c b/net/atm/common.c
index 0c0ad930a632..24216642d696 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -156,6 +156,7 @@ int vcc_create(struct net *net, struct socket *sock, int protocol, int family)
 	atomic_set(&sk->sk_rmem_alloc, 0);
 	vcc->push = NULL;
 	vcc->pop = NULL;
+	vcc->owner = NULL;
 	vcc->push_oam = NULL;
 	vcc->vpi = vcc->vci = 0; /* no VCI/VPI yet */
 	vcc->atm_options = vcc->aal_options = 0;
@@ -175,6 +176,7 @@ static void vcc_destroy_socket(struct sock *sk)
 			vcc->dev->ops->close(vcc);
 		if (vcc->push)
 			vcc->push(vcc, NULL); /* atmarpd has no push */
+		module_put(vcc->owner);
 
 		while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
 			atm_return(vcc, skb->truesize);
-- 
cgit v1.2.3-55-g7522


From 582b336ec2c0f0076f5650a029fcc9abd4a906f7 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti
Date: Tue, 27 Nov 2012 23:28:54 -0200
Subject: sched: add notifier for cross-cpu migrations

Originally from Jeremy Fitzhardinge.

Acked-by: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 include/linux/sched.h |  8 ++++++++
 kernel/sched/core.c   | 15 +++++++++++++++
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a02df2e..6eb2ed819e36 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -107,6 +107,14 @@ extern unsigned long this_cpu_load(void);
 extern void calc_global_load(unsigned long ticks);
 extern void update_cpu_load_nohz(void);
 
+/* Notifier for when a task gets migrated to a new CPU */
+struct task_migration_notifier {
+	struct task_struct *task;
+	int from_cpu;
+	int to_cpu;
+};
+extern void register_task_migration_notifier(struct notifier_block *n);
+
 extern unsigned long get_parent_ip(unsigned long addr);
 
 struct seq_file;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d8927fda712..c86b8b6e70f4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -922,6 +922,13 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 		rq->skip_clock_update = 1;
 }
 
+static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
+
+void register_task_migration_notifier(struct notifier_block *n)
+{
+	atomic_notifier_chain_register(&task_migration_notifier, n);
+}
+
 #ifdef CONFIG_SMP
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
@@ -952,8 +959,16 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	trace_sched_migrate_task(p, new_cpu);
 
 	if (task_cpu(p) != new_cpu) {
+		struct task_migration_notifier tmn;
+
 		p->se.nr_migrations++;
 		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
+
+		tmn.task = p;
+		tmn.from_cpu = task_cpu(p);
+		tmn.to_cpu = new_cpu;
+
+		atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
 	}
 
 	__set_task_cpu(p, new_cpu);
-- 
cgit v1.2.3-55-g7522


From e0b306fef90556233797d2e1747bd6a3ae35ea93 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti
Date: Tue, 27 Nov 2012 23:28:59 -0200
Subject: time: export time information for KVM pvclock

As suggested by John, export time data similarly to how its
done by vsyscall support. This allows KVM to retrieve necessary
information to implement vsyscall support in KVM guests.

Acked-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 include/linux/pvclock_gtod.h |  9 ++++++++
 kernel/time/timekeeping.c    | 50 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)
 create mode 100644 include/linux/pvclock_gtod.h

(limited to 'include')

diff --git a/include/linux/pvclock_gtod.h b/include/linux/pvclock_gtod.h
new file mode 100644
index 000000000000..0ca75825b60d
--- /dev/null
+++ b/include/linux/pvclock_gtod.h
@@ -0,0 +1,9 @@
+#ifndef _PVCLOCK_GTOD_H
+#define _PVCLOCK_GTOD_H
+
+#include <linux/notifier.h>
+
+extern int pvclock_gtod_register_notifier(struct notifier_block *nb);
+extern int pvclock_gtod_unregister_notifier(struct notifier_block *nb);
+
+#endif /* _PVCLOCK_GTOD_H */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index e424970bb562..69f5342e8d1c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -21,6 +21,7 @@
 #include <linux/time.h>
 #include <linux/tick.h>
 #include <linux/stop_machine.h>
+#include <linux/pvclock_gtod.h>
 
 
 static struct timekeeper timekeeper;
@@ -180,6 +181,54 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
 	return nsec + arch_gettimeoffset();
 }
 
+static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);
+
+static void update_pvclock_gtod(struct timekeeper *tk)
+{
+	raw_notifier_call_chain(&pvclock_gtod_chain, 0, tk);
+}
+
+/**
+ * pvclock_gtod_register_notifier - register a pvclock timedata update listener
+ *
+ * Must hold write on timekeeper.lock
+ */
+int pvclock_gtod_register_notifier(struct notifier_block *nb)
+{
+	struct timekeeper *tk = &timekeeper;
+	unsigned long flags;
+	int ret;
+
+	write_seqlock_irqsave(&tk->lock, flags);
+	ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
+	/* update timekeeping data */
+	update_pvclock_gtod(tk);
+	write_sequnlock_irqrestore(&tk->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier);
+
+/**
+ * pvclock_gtod_unregister_notifier - unregister a pvclock
+ * timedata update listener
+ *
+ * Must hold write on timekeeper.lock
+ */
+int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
+{
+	struct timekeeper *tk = &timekeeper;
+	unsigned long flags;
+	int ret;
+
+	write_seqlock_irqsave(&tk->lock, flags);
+	ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb);
+	write_sequnlock_irqrestore(&tk->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
+
 /* must hold write on timekeeper.lock */
 static void timekeeping_update(struct timekeeper *tk, bool clearntp)
 {
@@ -188,6 +237,7 @@ static void timekeeping_update(struct timekeeper *tk, bool clearntp)
 		ntp_clear();
 	}
 	update_vsyscall(tk);
+	update_pvclock_gtod(tk);
 }
 
 /**
-- 
cgit v1.2.3-55-g7522


From d828199e84447795c6669ff0e6c6d55eb9beeff6 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti
Date: Tue, 27 Nov 2012 23:29:01 -0200
Subject: KVM: x86: implement PVCLOCK_TSC_STABLE_BIT pvclock flag

KVM added a global variable to guarantee monotonicity in the guest.
One of the reasons for that is that the time between

	1. ktime_get_ts(&timespec);
	2. rdtscll(tsc);

Is variable. That is, given a host with stable TSC, suppose that
two VCPUs read the same time via ktime_get_ts() above.

The time required to execute 2. is not the same on those two instances
executing in different VCPUS (cache misses, interrupts...).

If the TSC value that is used by the host to interpolate when
calculating the monotonic time is the same value used to calculate
the tsc_timestamp value stored in the pvclock data structure, and
a single <system_timestamp, tsc_timestamp> tuple is visible to all
vcpus simultaneously, this problem disappears. See comment on top
of pvclock_update_vm_gtod_copy for details.

Monotonicity is then guaranteed by synchronicity of the host TSCs
and guest TSCs.

Set TSC stable pvclock flag in that case, allowing the guest to read
clock from userspace.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |   7 ++
 arch/x86/kvm/trace.h            |  30 +++++
 arch/x86/kvm/x86.c              | 235 ++++++++++++++++++++++++++++++++++++++--
 include/linux/kvm_host.h        |   3 +
 virt/kvm/kvm_main.c             |   5 +
 5 files changed, 272 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d60535adec98..32f0e4a063b7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -22,6 +22,8 @@
 #include <linux/kvm_para.h>
 #include <linux/kvm_types.h>
 #include <linux/perf_event.h>
+#include <linux/pvclock_gtod.h>
+#include <linux/clocksource.h>
 
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
@@ -560,6 +562,11 @@ struct kvm_arch {
 	u64 cur_tsc_offset;
 	u8  cur_tsc_generation;
 
+	spinlock_t pvclock_gtod_sync_lock;
+	bool use_master_clock;
+	u64 master_kernel_ns;
+	cycle_t master_cycle_now;
+
 	struct kvm_xen_hvm_config xen_hvm_config;
 
 	/* fields used by HYPER-V emulation */
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index bca63f04dccb..1d6526856080 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -4,6 +4,7 @@
 #include <linux/tracepoint.h>
 #include <asm/vmx.h>
 #include <asm/svm.h>
+#include <asm/clocksource.h>
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
@@ -754,6 +755,35 @@ TRACE_EVENT(
 		  __entry->write ? "Write" : "Read",
 		  __entry->gpa_match ? "GPA" : "GVA")
 );
+
+#ifdef CONFIG_X86_64
+
+#define host_clocks					\
+	{VCLOCK_NONE, "none"},				\
+	{VCLOCK_TSC,  "tsc"},				\
+	{VCLOCK_HPET, "hpet"}				\
+
+TRACE_EVENT(kvm_update_master_clock,
+	TP_PROTO(bool use_master_clock, unsigned int host_clock),
+	TP_ARGS(use_master_clock, host_clock),
+
+	TP_STRUCT__entry(
+		__field(		bool,	use_master_clock	)
+		__field(	unsigned int,	host_clock		)
+	),
+
+	TP_fast_assign(
+		__entry->use_master_clock	= use_master_clock;
+		__entry->host_clock		= host_clock;
+	),
+
+	TP_printk("masterclock %d hostclock %s",
+		  __entry->use_master_clock,
+		  __print_symbolic(__entry->host_clock, host_clocks))
+);
+
+#endif /* CONFIG_X86_64 */
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c077b817d1c3..a7b97a49d8ad 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1048,7 +1048,9 @@ static inline u64 get_kernel_ns(void)
 	return timespec_to_ns(&ts);
 }
 
+#ifdef CONFIG_X86_64
 static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0);
+#endif
 
 static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
 unsigned long max_tsc_khz;
@@ -1190,21 +1192,170 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
 
 EXPORT_SYMBOL_GPL(kvm_write_tsc);
 
+#ifdef CONFIG_X86_64
+
+static cycle_t read_tsc(void)
+{
+	cycle_t ret;
+	u64 last;
+
+	/*
+	 * Empirically, a fence (of type that depends on the CPU)
+	 * before rdtsc is enough to ensure that rdtsc is ordered
+	 * with respect to loads.  The various CPU manuals are unclear
+	 * as to whether rdtsc can be reordered with later loads,
+	 * but no one has ever seen it happen.
+	 */
+	rdtsc_barrier();
+	ret = (cycle_t)vget_cycles();
+
+	last = pvclock_gtod_data.clock.cycle_last;
+
+	if (likely(ret >= last))
+		return ret;
+
+	/*
+	 * GCC likes to generate cmov here, but this branch is extremely
+	 * predictable (it's just a funciton of time and the likely is
+	 * very likely) and there's a data dependence, so force GCC
+	 * to generate a branch instead.  I don't barrier() because
+	 * we don't actually need a barrier, and if this function
+	 * ever gets inlined it will generate worse code.
+	 */
+	asm volatile ("");
+	return last;
+}
+
+static inline u64 vgettsc(cycle_t *cycle_now)
+{
+	long v;
+	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+
+	*cycle_now = read_tsc();
+
+	v = (*cycle_now - gtod->clock.cycle_last) & gtod->clock.mask;
+	return v * gtod->clock.mult;
+}
+
+static int do_monotonic(struct timespec *ts, cycle_t *cycle_now)
+{
+	unsigned long seq;
+	u64 ns;
+	int mode;
+	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+
+	ts->tv_nsec = 0;
+	do {
+		seq = read_seqcount_begin(&gtod->seq);
+		mode = gtod->clock.vclock_mode;
+		ts->tv_sec = gtod->monotonic_time_sec;
+		ns = gtod->monotonic_time_snsec;
+		ns += vgettsc(cycle_now);
+		ns >>= gtod->clock.shift;
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
+	timespec_add_ns(ts, ns);
+
+	return mode;
+}
+
+/* returns true if host is using tsc clocksource */
+static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now)
+{
+	struct timespec ts;
+
+	/* checked again under seqlock below */
+	if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
+		return false;
+
+	if (do_monotonic(&ts, cycle_now) != VCLOCK_TSC)
+		return false;
+
+	monotonic_to_bootbased(&ts);
+	*kernel_ns = timespec_to_ns(&ts);
+
+	return true;
+}
+#endif
+
+/*
+ *
+ * Assuming a stable TSC across physical CPUS, the following condition
+ * is possible. Each numbered line represents an event visible to both
+ * CPUs at the next numbered event.
+ *
+ * "timespecX" represents host monotonic time. "tscX" represents
+ * RDTSC value.
+ *
+ * 		VCPU0 on CPU0		|	VCPU1 on CPU1
+ *
+ * 1.  read timespec0,tsc0
+ * 2.					| timespec1 = timespec0 + N
+ * 					| tsc1 = tsc0 + M
+ * 3. transition to guest		| transition to guest
+ * 4. ret0 = timespec0 + (rdtsc - tsc0) |
+ * 5.				        | ret1 = timespec1 + (rdtsc - tsc1)
+ * 				        | ret1 = timespec0 + N + (rdtsc - (tsc0 + M))
+ *
+ * Since ret0 update is visible to VCPU1 at time 5, to obey monotonicity:
+ *
+ * 	- ret0 < ret1
+ *	- timespec0 + (rdtsc - tsc0) < timespec0 + N + (rdtsc - (tsc0 + M))
+ *		...
+ *	- 0 < N - M => M < N
+ *
+ * That is, when timespec0 != timespec1, M < N. Unfortunately that is not
+ * always the case (the difference between two distinct xtime instances
+ * might be smaller then the difference between corresponding TSC reads,
+ * when updating guest vcpus pvclock areas).
+ *
+ * To avoid that problem, do not allow visibility of distinct
+ * system_timestamp/tsc_timestamp values simultaneously: use a master
+ * copy of host monotonic time values. Update that master copy
+ * in lockstep.
+ *
+ * Rely on synchronization of host TSCs for monotonicity.
+ *
+ */
+
+static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
+{
+#ifdef CONFIG_X86_64
+	struct kvm_arch *ka = &kvm->arch;
+	int vclock_mode;
+
+	/*
+	 * If the host uses TSC clock, then passthrough TSC as stable
+	 * to the guest.
+	 */
+	ka->use_master_clock = kvm_get_time_and_clockread(
+					&ka->master_kernel_ns,
+					&ka->master_cycle_now);
+
+	if (ka->use_master_clock)
+		atomic_set(&kvm_guest_has_master_clock, 1);
+
+	vclock_mode = pvclock_gtod_data.clock.vclock_mode;
+	trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode);
+#endif
+}
+
 static int kvm_guest_time_update(struct kvm_vcpu *v)
 {
-	unsigned long flags;
+	unsigned long flags, this_tsc_khz;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
+	struct kvm_arch *ka = &v->kvm->arch;
 	void *shared_kaddr;
-	unsigned long this_tsc_khz;
 	s64 kernel_ns, max_kernel_ns;
-	u64 tsc_timestamp;
+	u64 tsc_timestamp, host_tsc;
 	struct pvclock_vcpu_time_info *guest_hv_clock;
 	u8 pvclock_flags;
+	bool use_master_clock;
+
+	kernel_ns = 0;
+	host_tsc = 0;
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
-	tsc_timestamp = kvm_x86_ops->read_l1_tsc(v, native_read_tsc());
-	kernel_ns = get_kernel_ns();
 	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
 	if (unlikely(this_tsc_khz == 0)) {
 		local_irq_restore(flags);
@@ -1212,6 +1363,24 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		return 1;
 	}
 
+	/*
+	 * If the host uses TSC clock, then passthrough TSC as stable
+	 * to the guest.
+	 */
+	spin_lock(&ka->pvclock_gtod_sync_lock);
+	use_master_clock = ka->use_master_clock;
+	if (use_master_clock) {
+		host_tsc = ka->master_cycle_now;
+		kernel_ns = ka->master_kernel_ns;
+	}
+	spin_unlock(&ka->pvclock_gtod_sync_lock);
+	if (!use_master_clock) {
+		host_tsc = native_read_tsc();
+		kernel_ns = get_kernel_ns();
+	}
+
+	tsc_timestamp = kvm_x86_ops->read_l1_tsc(v, host_tsc);
+
 	/*
 	 * We may have to catch up the TSC to match elapsed wall clock
 	 * time for two reasons, even if kvmclock is used.
@@ -1273,9 +1442,14 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		vcpu->hw_tsc_khz = this_tsc_khz;
 	}
 
-	if (max_kernel_ns > kernel_ns)
-		kernel_ns = max_kernel_ns;
-
+	/* with a master <monotonic time, tsc value> tuple,
+	 * pvclock clock reads always increase at the (scaled) rate
+	 * of guest TSC - no need to deal with sampling errors.
+	 */
+	if (!use_master_clock) {
+		if (max_kernel_ns > kernel_ns)
+			kernel_ns = max_kernel_ns;
+	}
 	/* With all the info we got, fill in the values */
 	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
 	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
@@ -1301,6 +1475,10 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		vcpu->pvclock_set_guest_stopped_request = false;
 	}
 
+	/* If the host uses TSC clocksource, then it is stable */
+	if (use_master_clock)
+		pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
+
 	vcpu->hv_clock.flags = pvclock_flags;
 
 	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
@@ -4912,6 +5090,17 @@ static void kvm_set_mmio_spte_mask(void)
 #ifdef CONFIG_X86_64
 static void pvclock_gtod_update_fn(struct work_struct *work)
 {
+	struct kvm *kvm;
+
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	raw_spin_lock(&kvm_lock);
+	list_for_each_entry(kvm, &vm_list, vm_list)
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
+	atomic_set(&kvm_guest_has_master_clock, 0);
+	raw_spin_unlock(&kvm_lock);
 }
 
 static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
@@ -5303,6 +5492,29 @@ static void process_nmi(struct kvm_vcpu *vcpu)
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 
+static void kvm_gen_update_masterclock(struct kvm *kvm)
+{
+#ifdef CONFIG_X86_64
+	int i;
+	struct kvm_vcpu *vcpu;
+	struct kvm_arch *ka = &kvm->arch;
+
+	spin_lock(&ka->pvclock_gtod_sync_lock);
+	kvm_make_mclock_inprogress_request(kvm);
+	/* no guest entries from this point */
+	pvclock_update_vm_gtod_copy(kvm);
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+
+	/* guest entries allowed */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests);
+
+	spin_unlock(&ka->pvclock_gtod_sync_lock);
+#endif
+}
+
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -5315,6 +5527,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_mmu_unload(vcpu);
 		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
 			__kvm_migrate_timers(vcpu);
+		if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu))
+			kvm_gen_update_masterclock(vcpu->kvm);
 		if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) {
 			r = kvm_guest_time_update(vcpu);
 			if (unlikely(r))
@@ -6219,6 +6433,8 @@ int kvm_arch_hardware_enable(void *garbage)
 			kvm_for_each_vcpu(i, vcpu, kvm) {
 				vcpu->arch.tsc_offset_adjustment += delta_cyc;
 				vcpu->arch.last_host_tsc = local_tsc;
+				set_bit(KVM_REQ_MASTERCLOCK_UPDATE,
+					&vcpu->requests);
 			}
 
 			/*
@@ -6356,6 +6572,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	raw_spin_lock_init(&kvm->arch.tsc_write_lock);
 	mutex_init(&kvm->arch.apic_map_lock);
+	spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
+
+	pvclock_update_vm_gtod_copy(kvm);
 
 	return 0;
 }
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 99a47627e046..c94c9985dee0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -131,6 +131,8 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_PMU               16
 #define KVM_REQ_PMI               17
 #define KVM_REQ_WATCHDOG          18
+#define KVM_REQ_MASTERCLOCK_UPDATE 19
+#define KVM_REQ_MCLOCK_INPROGRESS 20
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
@@ -540,6 +542,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
 
 void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_reload_remote_mmus(struct kvm *kvm);
+void kvm_make_mclock_inprogress_request(struct kvm *kvm);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e3f5b143158e..be3e7bb73b10 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -212,6 +212,11 @@ void kvm_reload_remote_mmus(struct kvm *kvm)
 	make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
 }
 
+void kvm_make_mclock_inprogress_request(struct kvm *kvm)
+{
+	make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
+}
+
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 {
 	struct page *page;
-- 
cgit v1.2.3-55-g7522


From 42897d866b120547777ae1fd316680ec53356d9c Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti
Date: Tue, 27 Nov 2012 23:29:02 -0200
Subject: KVM: x86: add kvm_arch_vcpu_postcreate callback, move TSC
 initialization

TSC initialization will soon make use of online_vcpus.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/ia64/kvm/kvm-ia64.c   |  5 +++++
 arch/powerpc/kvm/powerpc.c |  5 +++++
 arch/s390/kvm/kvm-s390.c   |  5 +++++
 arch/x86/kvm/svm.c         |  1 -
 arch/x86/kvm/vmx.c         |  2 --
 arch/x86/kvm/x86.c         | 13 +++++++++++++
 include/linux/kvm_host.h   |  1 +
 virt/kvm/kvm_main.c        |  1 +
 8 files changed, 30 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index c71acd7f9a13..83b54530916e 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1330,6 +1330,11 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	return -EINVAL;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index deb0d596d815..f9ab12aea829 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -439,6 +439,11 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	return vcpu;
 }
 
+int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	/* Make sure we're not using the vcpu anymore */
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 38883f0bf27e..731ddeee32e4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -355,6 +355,11 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 }
 
+int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 94f5ceba7e1e..161a5fa66d82 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1251,7 +1251,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
 	svm->asid_generation = 0;
 	init_vmcb(svm);
-	kvm_write_tsc(&svm->vcpu, 0);
 
 	err = fx_init(&svm->vcpu);
 	if (err)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 896efd4842e7..bb18923bf632 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3896,8 +3896,6 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
 	set_cr4_guest_host_mask(vmx);
 
-	kvm_write_tsc(&vmx->vcpu, 0);
-
 	return 0;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a7b97a49d8ad..f3c069efc72a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6320,6 +6320,19 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	return r;
 }
 
+int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
+{
+	int r;
+
+	r = vcpu_load(vcpu);
+	if (r)
+		return r;
+	kvm_write_tsc(vcpu, 0);
+	vcpu_put(vcpu);
+
+	return r;
+}
+
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	int r;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c94c9985dee0..8e5c7b651655 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -596,6 +596,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id);
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
+int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
 int kvm_arch_hardware_enable(void *garbage);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index be3e7bb73b10..e6cfd4344d28 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1853,6 +1853,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	atomic_inc(&kvm->online_vcpus);
 
 	mutex_unlock(&kvm->lock);
+	kvm_arch_vcpu_postcreate(vcpu);
 	return r;
 
 unlock_vcpu_destroy:
-- 
cgit v1.2.3-55-g7522


From ffe0067544f93c0e71c793d7f17240486d091a3c Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger
Date: Tue, 27 Nov 2012 19:07:52 -0800
Subject: target: Make spc_get_write_same_sectors return sector_t

We already expect TFO->get_blocks() to return sector_t for zero value case
when doing WRITE_SAME to the end of the backend device, so go ahead and return
sector_t from spc_get_write_same_sectors() to handle this case properly.

Also, update the single iblock_execute_write_same() caller of this code.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_iblock.c  | 2 +-
 drivers/target/target_core_sbc.c     | 2 +-
 include/target/target_core_backend.h | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 34f258b4d37f..b526d23dcd4f 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -481,7 +481,7 @@ iblock_execute_write_same(struct se_cmd *cmd)
 	struct bio *bio;
 	struct bio_list list;
 	sector_t block_lba = cmd->t_task_lba;
-	unsigned int sectors = spc_get_write_same_sectors(cmd);
+	sector_t sectors = spc_get_write_same_sectors(cmd);
 
 	sg = &cmd->t_data_sg[0];
 
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 94fd004ea3fc..26a6d183ccb1 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -107,7 +107,7 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 	return 0;
 }
 
-int spc_get_write_same_sectors(struct se_cmd *cmd)
+sector_t spc_get_write_same_sectors(struct se_cmd *cmd)
 {
 	u32 num_blocks;
 
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 3393ab10766c..507910992c59 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -52,7 +52,7 @@ void	target_complete_cmd(struct se_cmd *, u8);
 
 sense_reason_t	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
 sense_reason_t	spc_emulate_report_luns(struct se_cmd *cmd);
-int	spc_get_write_same_sectors(struct se_cmd *cmd);
+sector_t	spc_get_write_same_sectors(struct se_cmd *cmd);
 
 sense_reason_t	sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops);
 u32	sbc_get_device_rev(struct se_device *dev);
-- 
cgit v1.2.3-55-g7522


From 31fbcda71489d8cbe2b82819eaab4818524e3a49 Mon Sep 17 00:00:00 2001
From: Lee Jones
Date: Fri, 28 Sep 2012 10:29:07 +0100
Subject: Input: bu21013_ts - move GPIO init and exit functions into the driver

These GPIO init and exit functions have no place in platform data, they
should be part of the driver instead,

Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 arch/arm/mach-ux500/board-mop500-stuib.c | 71 +-------------------------------
 drivers/input/touchscreen/bu21013_ts.c   | 69 ++++++++++++++++++++++---------
 include/linux/input/bu21013.h            | 10 +----
 3 files changed, 53 insertions(+), 97 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-ux500/board-mop500-stuib.c b/arch/arm/mach-ux500/board-mop500-stuib.c
index 564f57d5d8a7..7e1f294f0434 100644
--- a/arch/arm/mach-ux500/board-mop500-stuib.c
+++ b/arch/arm/mach-ux500/board-mop500-stuib.c
@@ -77,9 +77,6 @@ static struct i2c_board_info __initdata mop500_i2c0_devices_stuib[] = {
  * BU21013 ROHM touchscreen interface on the STUIBs
  */
 
-/* tracks number of bu21013 devices being enabled */
-static int bu21013_devices;
-
 #define TOUCH_GPIO_PIN  84
 
 #define TOUCH_XMAX	384
@@ -88,73 +85,8 @@ static int bu21013_devices;
 #define PRCMU_CLOCK_OCR		0x1CC
 #define TSC_EXT_CLOCK_9_6MHZ	0x840000
 
-/**
- * bu21013_gpio_board_init : configures the touch panel.
- * @reset_pin: reset pin number
- * This function can be used to configures
- * the voltage and reset the touch panel controller.
- */
-static int bu21013_gpio_board_init(int reset_pin)
-{
-	int retval = 0;
-
-	bu21013_devices++;
-	if (bu21013_devices == 1) {
-		retval = gpio_request(reset_pin, "touchp_reset");
-		if (retval) {
-			printk(KERN_ERR "Unable to request gpio reset_pin");
-			return retval;
-		}
-		retval = gpio_direction_output(reset_pin, 1);
-		if (retval < 0) {
-			printk(KERN_ERR "%s: gpio direction failed\n",
-					__func__);
-			return retval;
-		}
-	}
-
-	return retval;
-}
-
-/**
- * bu21013_gpio_board_exit : deconfigures the touch panel controller
- * @reset_pin: reset pin number
- * This function can be used to deconfigures the chip selection
- * for touch panel controller.
- */
-static int bu21013_gpio_board_exit(int reset_pin)
-{
-	int retval = 0;
-
-	if (bu21013_devices == 1) {
-		retval = gpio_direction_output(reset_pin, 0);
-		if (retval < 0) {
-			printk(KERN_ERR "%s: gpio direction failed\n",
-					__func__);
-			return retval;
-		}
-		gpio_set_value(reset_pin, 0);
-	}
-	bu21013_devices--;
-
-	return retval;
-}
-
-/**
- * bu21013_read_pin_val : get the interrupt pin value
- * This function can be used to get the interrupt pin value for touch panel
- * controller.
- */
-static int bu21013_read_pin_val(void)
-{
-	return gpio_get_value(TOUCH_GPIO_PIN);
-}
-
 static struct bu21013_platform_device tsc_plat_device = {
-	.cs_en = bu21013_gpio_board_init,
-	.cs_dis = bu21013_gpio_board_exit,
-	.irq_read_val = bu21013_read_pin_val,
-	.irq = NOMADIK_GPIO_TO_IRQ(TOUCH_GPIO_PIN),
+	.touch_pin = TOUCH_GPIO_PIN,
 	.touch_x_max = TOUCH_XMAX,
 	.touch_y_max = TOUCH_YMAX,
 	.ext_clk = false,
@@ -171,7 +103,6 @@ static struct i2c_board_info __initdata u8500_i2c3_devices_stuib[] = {
 		I2C_BOARD_INFO("bu21013_tp", 0x5D),
 		.platform_data = &tsc_plat_device,
 	},
-
 };
 
 void __init mop500_stuib_init(void)
diff --git a/drivers/input/touchscreen/bu21013_ts.c b/drivers/input/touchscreen/bu21013_ts.c
index 1e8cddd06c60..c6f6a04ec673 100644
--- a/drivers/input/touchscreen/bu21013_ts.c
+++ b/drivers/input/touchscreen/bu21013_ts.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/regulator/consumer.h>
 #include <linux/module.h>
+#include <linux/gpio.h>
 
 #define PEN_DOWN_INTR	0
 #define MAX_FINGERS	2
@@ -148,11 +149,12 @@
 struct bu21013_ts_data {
 	struct i2c_client *client;
 	wait_queue_head_t wait;
-	bool touch_stopped;
 	const struct bu21013_platform_device *chip;
 	struct input_dev *in_dev;
-	unsigned int intr_pin;
 	struct regulator *regulator;
+	unsigned int irq;
+	unsigned int intr_pin;
+	bool touch_stopped;
 };
 
 /**
@@ -262,7 +264,7 @@ static irqreturn_t bu21013_gpio_irq(int irq, void *device_data)
 			return IRQ_NONE;
 		}
 
-		data->intr_pin = data->chip->irq_read_val();
+		data->intr_pin = gpio_get_value(data->chip->touch_pin);
 		if (data->intr_pin == PEN_DOWN_INTR)
 			wait_event_timeout(data->wait, data->touch_stopped,
 					   msecs_to_jiffies(2));
@@ -418,9 +420,32 @@ static void bu21013_free_irq(struct bu21013_ts_data *bu21013_data)
 {
 	bu21013_data->touch_stopped = true;
 	wake_up(&bu21013_data->wait);
-	free_irq(bu21013_data->chip->irq, bu21013_data);
+	free_irq(bu21013_data->irq, bu21013_data);
 }
 
+/**
+ * bu21013_cs_disable() - deconfigures the touch panel controller
+ * @bu21013_data: device structure pointer
+ *
+ * This function is used to deconfigure the chip selection
+ * for touch panel controller.
+ */
+static void bu21013_cs_disable(struct bu21013_ts_data *bu21013_data)
+{
+	int error;
+
+	error = gpio_direction_output(bu21013_data->chip->cs_pin, 0);
+	if (error < 0)
+		dev_warn(&bu21013_data->client->dev,
+			 "%s: gpio direction failed, error: %d\n",
+			 __func__, error);
+	else
+		gpio_set_value(bu21013_data->chip->cs_pin, 0);
+
+	gpio_free(bu21013_data->chip->cs_pin);
+}
+
+
 /**
  * bu21013_probe() - initializes the i2c-client touchscreen driver
  * @client: i2c client structure pointer
@@ -430,7 +455,7 @@ static void bu21013_free_irq(struct bu21013_ts_data *bu21013_data)
  * driver and returns integer.
  */
 static int bu21013_probe(struct i2c_client *client,
-					const struct i2c_device_id *id)
+			 const struct i2c_device_id *id)
 {
 	struct bu21013_ts_data *bu21013_data;
 	struct input_dev *in_dev;
@@ -449,6 +474,11 @@ static int bu21013_probe(struct i2c_client *client,
 		return -EINVAL;
 	}
 
+	if (!gpio_is_valid(pdata->touch_pin)) {
+		dev_err(&client->dev, "invalid touch_pin supplied\n");
+		return -EINVAL;
+	}
+
 	bu21013_data = kzalloc(sizeof(struct bu21013_ts_data), GFP_KERNEL);
 	in_dev = input_allocate_device();
 	if (!bu21013_data || !in_dev) {
@@ -460,6 +490,7 @@ static int bu21013_probe(struct i2c_client *client,
 	bu21013_data->in_dev = in_dev;
 	bu21013_data->chip = pdata;
 	bu21013_data->client = client;
+	bu21013_data->irq = gpio_to_irq(pdata->touch_pin);
 
 	bu21013_data->regulator = regulator_get(&client->dev, "avdd");
 	if (IS_ERR(bu21013_data->regulator)) {
@@ -478,12 +509,11 @@ static int bu21013_probe(struct i2c_client *client,
 	init_waitqueue_head(&bu21013_data->wait);
 
 	/* configure the gpio pins */
-	if (pdata->cs_en) {
-		error = pdata->cs_en(pdata->cs_pin);
-		if (error < 0) {
-			dev_err(&client->dev, "chip init failed\n");
-			goto err_disable_regulator;
-		}
+	error = gpio_request_one(pdata->cs_pin, GPIOF_OUT_INIT_HIGH,
+				 "touchp_reset");
+	if (error < 0) {
+		dev_err(&client->dev, "Unable to request gpio reset_pin\n");
+		goto err_disable_regulator;
 	}
 
 	/* configure the touch panel controller */
@@ -508,12 +538,13 @@ static int bu21013_probe(struct i2c_client *client,
 						pdata->touch_y_max, 0, 0);
 	input_set_drvdata(in_dev, bu21013_data);
 
-	error = request_threaded_irq(pdata->irq, NULL, bu21013_gpio_irq,
+	error = request_threaded_irq(bu21013_data->irq, NULL, bu21013_gpio_irq,
 				     IRQF_TRIGGER_FALLING | IRQF_SHARED |
 					IRQF_ONESHOT,
 				     DRIVER_TP, bu21013_data);
 	if (error) {
-		dev_err(&client->dev, "request irq %d failed\n", pdata->irq);
+		dev_err(&client->dev, "request irq %d failed\n",
+			bu21013_data->irq);
 		goto err_cs_disable;
 	}
 
@@ -531,7 +562,7 @@ static int bu21013_probe(struct i2c_client *client,
 err_free_irq:
 	bu21013_free_irq(bu21013_data);
 err_cs_disable:
-	pdata->cs_dis(pdata->cs_pin);
+	bu21013_cs_disable(bu21013_data);
 err_disable_regulator:
 	regulator_disable(bu21013_data->regulator);
 err_put_regulator:
@@ -555,7 +586,7 @@ static int bu21013_remove(struct i2c_client *client)
 
 	bu21013_free_irq(bu21013_data);
 
-	bu21013_data->chip->cs_dis(bu21013_data->chip->cs_pin);
+	bu21013_cs_disable(bu21013_data);
 
 	input_unregister_device(bu21013_data->in_dev);
 
@@ -584,9 +615,9 @@ static int bu21013_suspend(struct device *dev)
 
 	bu21013_data->touch_stopped = true;
 	if (device_may_wakeup(&client->dev))
-		enable_irq_wake(bu21013_data->chip->irq);
+		enable_irq_wake(bu21013_data->irq);
 	else
-		disable_irq(bu21013_data->chip->irq);
+		disable_irq(bu21013_data->irq);
 
 	regulator_disable(bu21013_data->regulator);
 
@@ -621,9 +652,9 @@ static int bu21013_resume(struct device *dev)
 	bu21013_data->touch_stopped = false;
 
 	if (device_may_wakeup(&client->dev))
-		disable_irq_wake(bu21013_data->chip->irq);
+		disable_irq_wake(bu21013_data->irq);
 	else
-		enable_irq(bu21013_data->chip->irq);
+		enable_irq(bu21013_data->irq);
 
 	return 0;
 }
diff --git a/include/linux/input/bu21013.h b/include/linux/input/bu21013.h
index 05e03284b92a..6230d76bde5d 100644
--- a/include/linux/input/bu21013.h
+++ b/include/linux/input/bu21013.h
@@ -9,13 +9,10 @@
 
 /**
  * struct bu21013_platform_device - Handle the platform data
- * @cs_en:	pointer to the cs enable function
- * @cs_dis:	pointer to the cs disable function
- * @irq_read_val:    pointer to read the pen irq value function
  * @touch_x_max: touch x max
  * @touch_y_max: touch y max
  * @cs_pin: chip select pin
- * @irq: irq pin
+ * @touch_pin: touch gpio pin
  * @ext_clk: external clock flag
  * @x_flip: x flip flag
  * @y_flip: y flip flag
@@ -24,13 +21,10 @@
  * This is used to handle the platform data
  */
 struct bu21013_platform_device {
-	int (*cs_en)(int reset_pin);
-	int (*cs_dis)(int reset_pin);
-	int (*irq_read_val)(void);
 	int touch_x_max;
 	int touch_y_max;
 	unsigned int cs_pin;
-	unsigned int irq;
+	unsigned int touch_pin;
 	bool ext_clk;
 	bool x_flip;
 	bool y_flip;
-- 
cgit v1.2.3-55-g7522


From 384cc2f9688994dfd505011ba3b08e0a702030b0 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom
Date: Tue, 20 Nov 2012 12:16:47 +0000
Subject: drm: Add a hash-tab rcu-safe API

While hashtab should now be RCU-safe, Add a drm_ht_xxx_api for consumers
to use to make it obvious what locking mechanism is used.

Document the way the rcu-safe interface should be used.

Don't use rcu-safe list traversal in modify operations where we should use
a spinlock / mutex anyway.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_hashtab.c | 26 ++++++++++++++++++++++----
 include/drm/drm_hashtab.h     | 14 ++++++++++++++
 2 files changed, 36 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_hashtab.c b/drivers/gpu/drm/drm_hashtab.c
index 5729e390aa4e..80254547a3f8 100644
--- a/drivers/gpu/drm/drm_hashtab.c
+++ b/drivers/gpu/drm/drm_hashtab.c
@@ -67,7 +67,7 @@ void drm_ht_verbose_list(struct drm_open_hash *ht, unsigned long key)
 	hashed_key = hash_long(key, ht->order);
 	DRM_DEBUG("Key is 0x%08lx, Hashed key is 0x%08x\n", key, hashed_key);
 	h_list = &ht->table[hashed_key];
-	hlist_for_each_entry_rcu(entry, list, h_list, head)
+	hlist_for_each_entry(entry, list, h_list, head)
 		DRM_DEBUG("count %d, key: 0x%08lx\n", count++, entry->key);
 }
 
@@ -81,7 +81,7 @@ static struct hlist_node *drm_ht_find_key(struct drm_open_hash *ht,
 
 	hashed_key = hash_long(key, ht->order);
 	h_list = &ht->table[hashed_key];
-	hlist_for_each_entry_rcu(entry, list, h_list, head) {
+	hlist_for_each_entry(entry, list, h_list, head) {
 		if (entry->key == key)
 			return list;
 		if (entry->key > key)
@@ -90,6 +90,24 @@ static struct hlist_node *drm_ht_find_key(struct drm_open_hash *ht,
 	return NULL;
 }
 
+static struct hlist_node *drm_ht_find_key_rcu(struct drm_open_hash *ht,
+					      unsigned long key)
+{
+	struct drm_hash_item *entry;
+	struct hlist_head *h_list;
+	struct hlist_node *list;
+	unsigned int hashed_key;
+
+	hashed_key = hash_long(key, ht->order);
+	h_list = &ht->table[hashed_key];
+	hlist_for_each_entry_rcu(entry, list, h_list, head) {
+		if (entry->key == key)
+			return list;
+		if (entry->key > key)
+			break;
+	}
+	return NULL;
+}
 
 int drm_ht_insert_item(struct drm_open_hash *ht, struct drm_hash_item *item)
 {
@@ -102,7 +120,7 @@ int drm_ht_insert_item(struct drm_open_hash *ht, struct drm_hash_item *item)
 	hashed_key = hash_long(key, ht->order);
 	h_list = &ht->table[hashed_key];
 	parent = NULL;
-	hlist_for_each_entry_rcu(entry, list, h_list, head) {
+	hlist_for_each_entry(entry, list, h_list, head) {
 		if (entry->key == key)
 			return -EINVAL;
 		if (entry->key > key)
@@ -152,7 +170,7 @@ int drm_ht_find_item(struct drm_open_hash *ht, unsigned long key,
 {
 	struct hlist_node *list;
 
-	list = drm_ht_find_key(ht, key);
+	list = drm_ht_find_key_rcu(ht, key);
 	if (!list)
 		return -EINVAL;
 
diff --git a/include/drm/drm_hashtab.h b/include/drm/drm_hashtab.h
index 3650d5d011ee..fce2ef3fdfff 100644
--- a/include/drm/drm_hashtab.h
+++ b/include/drm/drm_hashtab.h
@@ -61,5 +61,19 @@ extern int drm_ht_remove_key(struct drm_open_hash *ht, unsigned long key);
 extern int drm_ht_remove_item(struct drm_open_hash *ht, struct drm_hash_item *item);
 extern void drm_ht_remove(struct drm_open_hash *ht);
 
+/*
+ * RCU-safe interface
+ *
+ * The user of this API needs to make sure that two or more instances of the
+ * hash table manipulation functions are never run simultaneously.
+ * The lookup function drm_ht_find_item_rcu may, however, run simultaneously
+ * with any of the manipulation functions as long as it's called from within
+ * an RCU read-locked section.
+ */
+#define drm_ht_insert_item_rcu drm_ht_insert_item
+#define drm_ht_just_insert_please_rcu drm_ht_just_insert_please
+#define drm_ht_remove_key_rcu drm_ht_remove_key
+#define drm_ht_remove_item_rcu drm_ht_remove_item
+#define drm_ht_find_item_rcu drm_ht_find_item
 
 #endif
-- 
cgit v1.2.3-55-g7522


From 28164fdad85ec806f30c76fe98ed0e3abc91d2d7 Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Thu, 1 Nov 2012 14:45:18 +0100
Subject: drm/doc: add new dp helpers into drm DocBook

I didn't bother with documenting the really trivial new "extract
something from dpcd" helpers, but the i2c over aux ch is now
documented a bit.

v2: Clarify the comment for i2c_dp_aux_add_bus a bit.

v3: Fix more spelling fail spotted by Laurent Pinchart.

Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 Documentation/DocBook/drm.tmpl  |  6 ++++++
 drivers/gpu/drm/drm_dp_helper.c | 21 +++++++++++++++++++++
 include/drm/drm_dp_helper.h     |  8 ++++++++
 3 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index cb8024e62dfc..4ee2304f82f9 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -2105,6 +2105,12 @@ void intel_crt_init(struct drm_device *dev)
 !Pdrivers/gpu/drm/drm_fb_helper.c fbdev helpers
 !Edrivers/gpu/drm/drm_fb_helper.c
     </sect2>
+    <sect2>
+      <title>Display Port Helper Functions Reference</title>
+!Pdrivers/gpu/drm/drm_dp_helper.c dp helpers
+!Iinclude/drm/drm_dp_helper.h
+!Edrivers/gpu/drm/drm_dp_helper.c
+    </sect2>
   </sect1>
 
   <!-- Internals: vertical blanking -->
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 3c4cccd0d753..89e196627160 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -30,6 +30,15 @@
 #include <drm/drm_dp_helper.h>
 #include <drm/drmP.h>
 
+/**
+ * DOC: dp helpers
+ *
+ * These functions contain some common logic and helpers at various abstraction
+ * levels to deal with Display Port sink devices and related things like DP aux
+ * channel transfers, EDID reading over DP aux channels, decoding certain DPCD
+ * blocks, ...
+ */
+
 /* Run a single AUX_CH I2C transaction, writing/reading data as necessary */
 static int
 i2c_algo_dp_aux_transaction(struct i2c_adapter *adapter, int mode,
@@ -193,6 +202,18 @@ i2c_dp_aux_prepare_bus(struct i2c_adapter *adapter)
 	return 0;
 }
 
+/**
+ * i2c_dp_aux_add_bus() - register an i2c adapter using the aux ch helper
+ * @adapter: i2c adapter to register
+ *
+ * This registers an i2c adapater that uses dp aux channel as it's underlaying
+ * transport. The driver needs to fill out the &i2c_algo_dp_aux_data structure
+ * and store it in the algo_data member of the @adapter argument. This will be
+ * used by the i2c over dp aux algorithm to drive the hardware.
+ *
+ * RETURNS:
+ * 0 on success, -ERRNO on failure.
+ */
 int
 i2c_dp_aux_add_bus(struct i2c_adapter *adapter)
 {
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index c09d36741c94..e8e1417af3d9 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -312,6 +312,14 @@
 #define MODE_I2C_READ	4
 #define MODE_I2C_STOP	8
 
+/**
+ * struct i2c_algo_dp_aux_data - driver interface structure for i2c over dp
+ * 				 aux algorithm
+ * @running: set by the algo indicating whether an i2c is ongoing or whether
+ * 	     the i2c bus is quiescent
+ * @address: i2c target address for the currently ongoing transfer
+ * @aux_ch: driver callback to transfer a single byte of the i2c payload
+ */
 struct i2c_algo_dp_aux_data {
 	bool running;
 	u16 address;
-- 
cgit v1.2.3-55-g7522


From 972deb4f49b5b6703d9c6117ba0aeda2180d4447 Mon Sep 17 00:00:00 2001
From: Shubhrajyoti D
Date: Mon, 26 Nov 2012 15:25:11 +0530
Subject: i2c: omap: Remove the OMAP_I2C_FLAG_RESET_REGS_POSTIDLE flag

The OMAP_I2C_FLAG_RESET_REGS_POSTIDLE is not used anymore
in the i2c driver. Remove the flag.

Signed-off-by: Shubhrajyoti D <shubhrajyoti@ti.com>
Reviewed-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
---
 arch/arm/mach-omap2/omap_hwmod_33xx_data.c | 3 +--
 arch/arm/mach-omap2/omap_hwmod_3xxx_data.c | 9 +++------
 arch/arm/mach-omap2/omap_hwmod_44xx_data.c | 3 +--
 drivers/i2c/busses/i2c-omap.c              | 3 +--
 include/linux/i2c-omap.h                   | 1 -
 5 files changed, 6 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
index 59d5c1cd316d..c9a186bc6d40 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
@@ -1103,8 +1103,7 @@ static struct omap_hwmod_class i2c_class = {
 };
 
 static struct omap_i2c_dev_attr i2c_dev_attr = {
-	.flags = OMAP_I2C_FLAG_BUS_SHIFT_NONE |
-		  OMAP_I2C_FLAG_RESET_REGS_POSTIDLE,
+	.flags = OMAP_I2C_FLAG_BUS_SHIFT_NONE,
 };
 
 /* i2c1 */
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 943222c40489..36270bb637e4 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -791,8 +791,7 @@ static struct omap_hwmod omap3xxx_dss_venc_hwmod = {
 /* I2C1 */
 static struct omap_i2c_dev_attr i2c1_dev_attr = {
 	.fifo_depth	= 8, /* bytes */
-	.flags		= OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
-			  OMAP_I2C_FLAG_BUS_SHIFT_2,
+	.flags		= OMAP_I2C_FLAG_BUS_SHIFT_2,
 };
 
 static struct omap_hwmod omap3xxx_i2c1_hwmod = {
@@ -817,8 +816,7 @@ static struct omap_hwmod omap3xxx_i2c1_hwmod = {
 /* I2C2 */
 static struct omap_i2c_dev_attr i2c2_dev_attr = {
 	.fifo_depth	= 8, /* bytes */
-	.flags = OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
-		 OMAP_I2C_FLAG_BUS_SHIFT_2,
+	.flags = OMAP_I2C_FLAG_BUS_SHIFT_2,
 };
 
 static struct omap_hwmod omap3xxx_i2c2_hwmod = {
@@ -843,8 +841,7 @@ static struct omap_hwmod omap3xxx_i2c2_hwmod = {
 /* I2C3 */
 static struct omap_i2c_dev_attr i2c3_dev_attr = {
 	.fifo_depth	= 64, /* bytes */
-	.flags = OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
-		 OMAP_I2C_FLAG_BUS_SHIFT_2,
+	.flags = OMAP_I2C_FLAG_BUS_SHIFT_2,
 };
 
 static struct omap_hwmod_irq_info i2c3_mpu_irqs[] = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 652d0285bd6d..eb40dbc6688e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -1526,8 +1526,7 @@ static struct omap_hwmod_class omap44xx_i2c_hwmod_class = {
 };
 
 static struct omap_i2c_dev_attr i2c_dev_attr = {
-	.flags	= OMAP_I2C_FLAG_BUS_SHIFT_NONE |
-			OMAP_I2C_FLAG_RESET_REGS_POSTIDLE,
+	.flags	= OMAP_I2C_FLAG_BUS_SHIFT_NONE,
 };
 
 /* i2c1 */
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 248280136668..7a62acb7d262 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1038,8 +1038,7 @@ static const struct i2c_algorithm omap_i2c_algo = {
 #ifdef CONFIG_OF
 static struct omap_i2c_bus_platform_data omap3_pdata = {
 	.rev = OMAP_I2C_IP_VERSION_1,
-	.flags = OMAP_I2C_FLAG_RESET_REGS_POSTIDLE |
-		 OMAP_I2C_FLAG_BUS_SHIFT_2,
+	.flags = OMAP_I2C_FLAG_BUS_SHIFT_2,
 };
 
 static struct omap_i2c_bus_platform_data omap4_pdata = {
diff --git a/include/linux/i2c-omap.h b/include/linux/i2c-omap.h
index 1b25c04f82d9..babe0cf6d56b 100644
--- a/include/linux/i2c-omap.h
+++ b/include/linux/i2c-omap.h
@@ -20,7 +20,6 @@
 #define OMAP_I2C_FLAG_NO_FIFO			BIT(0)
 #define OMAP_I2C_FLAG_SIMPLE_CLOCK		BIT(1)
 #define OMAP_I2C_FLAG_16BIT_DATA_REG		BIT(2)
-#define OMAP_I2C_FLAG_RESET_REGS_POSTIDLE	BIT(3)
 #define OMAP_I2C_FLAG_ALWAYS_ARMXOR_CLK	BIT(5)
 #define OMAP_I2C_FLAG_FORCE_19200_INT_CLK	BIT(6)
 /* how the CPU address bus must be translated for I2C unit access */
-- 
cgit v1.2.3-55-g7522


From babde1c243b25592038dd7193867a49729e3d505 Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki
Date: Wed, 22 Aug 2012 20:09:18 -0300
Subject: [media] V4L: Add driver for S3C24XX/S3C64XX SoC series camera
 interface

This patch adds V4L2 driver for Samsung S3C24XX/S3C64XX SoC series
camera interface. The driver exposes a subdev device node for CAMIF
pixel resolution and crop control and two video capture nodes - for
the "codec" and "preview" data paths. It has been tested on Mini2440
(s3c2440) and Mini6410 (s3c6410) board with gstreamer and mplayer.

Signed-off-by: Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
Signed-off-by: Tomasz Figa <tomasz.figa@gmail.com>
Signed-off-by: Andrey Gusakov <dron0gus@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/platform/Kconfig                   |   12 +
 drivers/media/platform/Makefile                  |    1 +
 drivers/media/platform/s3c-camif/Makefile        |    5 +
 drivers/media/platform/s3c-camif/camif-capture.c | 1672 ++++++++++++++++++++++
 drivers/media/platform/s3c-camif/camif-core.c    |  662 +++++++++
 drivers/media/platform/s3c-camif/camif-core.h    |  393 +++++
 drivers/media/platform/s3c-camif/camif-regs.c    |  606 ++++++++
 drivers/media/platform/s3c-camif/camif-regs.h    |  269 ++++
 include/media/s3c_camif.h                        |   45 +
 9 files changed, 3665 insertions(+)
 create mode 100644 drivers/media/platform/s3c-camif/Makefile
 create mode 100644 drivers/media/platform/s3c-camif/camif-capture.c
 create mode 100644 drivers/media/platform/s3c-camif/camif-core.c
 create mode 100644 drivers/media/platform/s3c-camif/camif-core.h
 create mode 100644 drivers/media/platform/s3c-camif/camif-regs.c
 create mode 100644 drivers/media/platform/s3c-camif/camif-regs.h
 create mode 100644 include/media/s3c_camif.h

(limited to 'include')

diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 181c7686e412..3dcfea612c42 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -109,6 +109,18 @@ config VIDEO_OMAP3_DEBUG
 	---help---
 	  Enable debug messages on OMAP 3 camera controller driver.
 
+config VIDEO_S3C_CAMIF
+	tristate "Samsung S3C24XX/S3C64XX SoC Camera Interface driver"
+	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API
+	depends on (PLAT_S3C64XX || PLAT_S3C24XX) && PM_RUNTIME
+	select VIDEOBUF2_DMA_CONTIG
+	---help---
+	  This is a v4l2 driver for s3c24xx and s3c64xx SoC series camera
+	  host interface (CAMIF).
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called s3c-camif.
+
 source "drivers/media/platform/soc_camera/Kconfig"
 source "drivers/media/platform/s5p-fimc/Kconfig"
 source "drivers/media/platform/s5p-tv/Kconfig"
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index baaa55026c8e..4817d2802171 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_VIDEO_CODA) 		+= coda.o
 
 obj-$(CONFIG_VIDEO_MEM2MEM_DEINTERLACE)	+= m2m-deinterlace.o
 
+obj-$(CONFIG_VIDEO_S3C_CAMIF) 		+= s3c-camif/
 obj-$(CONFIG_VIDEO_SAMSUNG_S5P_FIMC) 	+= s5p-fimc/
 obj-$(CONFIG_VIDEO_SAMSUNG_S5P_JPEG)	+= s5p-jpeg/
 obj-$(CONFIG_VIDEO_SAMSUNG_S5P_MFC)	+= s5p-mfc/
diff --git a/drivers/media/platform/s3c-camif/Makefile b/drivers/media/platform/s3c-camif/Makefile
new file mode 100644
index 000000000000..50bf8c59b99c
--- /dev/null
+++ b/drivers/media/platform/s3c-camif/Makefile
@@ -0,0 +1,5 @@
+# Makefile for s3c244x/s3c64xx CAMIF driver
+
+s3c-camif-objs := camif-core.o camif-capture.o camif-regs.o
+
+obj-$(CONFIG_VIDEO_S3C_CAMIF) += s3c-camif.o
diff --git a/drivers/media/platform/s3c-camif/camif-capture.c b/drivers/media/platform/s3c-camif/camif-capture.c
new file mode 100644
index 000000000000..a55793c3d811
--- /dev/null
+++ b/drivers/media/platform/s3c-camif/camif-capture.c
@@ -0,0 +1,1672 @@
+/*
+ * s3c24xx/s3c64xx SoC series Camera Interface (CAMIF) driver
+ *
+ * Copyright (C) 2012 Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
+ * Copyright (C) 2012 Tomasz Figa <tomasz.figa@gmail.com>
+ *
+ * Based on drivers/media/platform/s5p-fimc,
+ * Copyright (C) 2010 - 2012 Samsung Electronics Co., Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+#define pr_fmt(fmt) "%s:%d " fmt, __func__, __LINE__
+
+#include <linux/bug.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/ratelimit.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/videodev2.h>
+
+#include <media/media-device.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-ioctl.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "camif-core.h"
+#include "camif-regs.h"
+
+static int debug;
+module_param(debug, int, 0644);
+
+/* Locking: called with vp->camif->slock spinlock held */
+static void camif_cfg_video_path(struct camif_vp *vp)
+{
+	WARN_ON(s3c_camif_get_scaler_config(vp, &vp->scaler));
+	camif_hw_set_scaler(vp);
+	camif_hw_set_flip(vp);
+	camif_hw_set_target_format(vp);
+	camif_hw_set_output_dma(vp);
+}
+
+static void camif_prepare_dma_offset(struct camif_vp *vp)
+{
+	struct camif_frame *f = &vp->out_frame;
+
+	f->dma_offset.initial = f->rect.top * f->f_width + f->rect.left;
+	f->dma_offset.line = f->f_width - (f->rect.left + f->rect.width);
+
+	pr_debug("dma_offset: initial: %d, line: %d\n",
+		 f->dma_offset.initial, f->dma_offset.line);
+}
+
+/* Locking: called with camif->slock spinlock held */
+static int s3c_camif_hw_init(struct camif_dev *camif, struct camif_vp *vp)
+{
+	const struct s3c_camif_variant *variant = camif->variant;
+
+	if (camif->sensor.sd == NULL || vp->out_fmt == NULL)
+		return -EINVAL;
+
+	if (variant->ip_revision == S3C244X_CAMIF_IP_REV)
+		camif_hw_clear_fifo_overflow(vp);
+	camif_hw_set_camera_bus(camif);
+	camif_hw_set_source_format(camif);
+	camif_hw_set_camera_crop(camif);
+	camif_hw_set_test_pattern(camif, camif->test_pattern);
+	if (variant->has_img_effect)
+		camif_hw_set_effect(camif, camif->colorfx,
+				camif->colorfx_cb, camif->colorfx_cr);
+	if (variant->ip_revision == S3C6410_CAMIF_IP_REV)
+		camif_hw_set_input_path(vp);
+	camif_cfg_video_path(vp);
+	vp->state &= ~ST_VP_CONFIG;
+
+	return 0;
+}
+
+/*
+ * Initialize the video path, only up from the scaler stage. The camera
+ * input interface set up is skipped. This is useful to enable one of the
+ * video paths when the other is already running.
+ * Locking: called with camif->slock spinlock held.
+ */
+static int s3c_camif_hw_vp_init(struct camif_dev *camif, struct camif_vp *vp)
+{
+	unsigned int ip_rev = camif->variant->ip_revision;
+
+	if (vp->out_fmt == NULL)
+		return -EINVAL;
+
+	camif_prepare_dma_offset(vp);
+	if (ip_rev == S3C244X_CAMIF_IP_REV)
+		camif_hw_clear_fifo_overflow(vp);
+	camif_cfg_video_path(vp);
+	vp->state &= ~ST_VP_CONFIG;
+	return 0;
+}
+
+static int sensor_set_power(struct camif_dev *camif, int on)
+{
+	struct cam_sensor *sensor = &camif->sensor;
+	int err = 0;
+
+	if (!on == camif->sensor.power_count)
+		err = v4l2_subdev_call(sensor->sd, core, s_power, on);
+	if (!err)
+		sensor->power_count += on ? 1 : -1;
+
+	pr_debug("on: %d, power_count: %d, err: %d\n",
+		 on, sensor->power_count, err);
+
+	return err;
+}
+
+static int sensor_set_streaming(struct camif_dev *camif, int on)
+{
+	struct cam_sensor *sensor = &camif->sensor;
+	int err = 0;
+
+	if (!on == camif->sensor.stream_count)
+		err = v4l2_subdev_call(sensor->sd, video, s_stream, on);
+	if (!err)
+		sensor->stream_count += on ? 1 : -1;
+
+	pr_debug("on: %d, stream_count: %d, err: %d\n",
+		 on, sensor->stream_count, err);
+
+	return err;
+}
+
+/*
+ * Reinitialize the driver so it is ready to start streaming again.
+ * Return any buffers to vb2, perform CAMIF software reset and
+ * turn off streaming at the data pipeline (sensor) if required.
+ */
+static int camif_reinitialize(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	struct camif_buffer *buf;
+	unsigned long flags;
+	bool streaming;
+
+	spin_lock_irqsave(&camif->slock, flags);
+	streaming = vp->state & ST_VP_SENSOR_STREAMING;
+
+	vp->state &= ~(ST_VP_PENDING | ST_VP_RUNNING | ST_VP_OFF |
+		       ST_VP_ABORTING | ST_VP_STREAMING |
+		       ST_VP_SENSOR_STREAMING | ST_VP_LASTIRQ);
+
+	/* Release unused buffers */
+	while (!list_empty(&vp->pending_buf_q)) {
+		buf = camif_pending_queue_pop(vp);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+	}
+
+	while (!list_empty(&vp->active_buf_q)) {
+		buf = camif_active_queue_pop(vp);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+	}
+
+	spin_unlock_irqrestore(&camif->slock, flags);
+
+	if (!streaming)
+		return 0;
+
+	return sensor_set_streaming(camif, 0);
+}
+
+static bool s3c_vp_active(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	unsigned long flags;
+	bool ret;
+
+	spin_lock_irqsave(&camif->slock, flags);
+	ret = (vp->state & ST_VP_RUNNING) || (vp->state & ST_VP_PENDING);
+	spin_unlock_irqrestore(&camif->slock, flags);
+
+	return ret;
+}
+
+static bool camif_is_streaming(struct camif_dev *camif)
+{
+	unsigned long flags;
+	bool status;
+
+	spin_lock_irqsave(&camif->slock, flags);
+	status = camif->stream_count > 0;
+	spin_unlock_irqrestore(&camif->slock, flags);
+
+	return status;
+}
+
+static int camif_stop_capture(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	unsigned long flags;
+	int ret;
+
+	if (!s3c_vp_active(vp))
+		return 0;
+
+	spin_lock_irqsave(&camif->slock, flags);
+	vp->state &= ~(ST_VP_OFF | ST_VP_LASTIRQ);
+	vp->state |= ST_VP_ABORTING;
+	spin_unlock_irqrestore(&camif->slock, flags);
+
+	ret = wait_event_timeout(vp->irq_queue,
+			   !(vp->state & ST_VP_ABORTING),
+			   msecs_to_jiffies(CAMIF_STOP_TIMEOUT));
+
+	spin_lock_irqsave(&camif->slock, flags);
+
+	if (ret == 0 && !(vp->state & ST_VP_OFF)) {
+		/* Timed out, forcibly stop capture */
+		vp->state &= ~(ST_VP_OFF | ST_VP_ABORTING |
+			       ST_VP_LASTIRQ);
+
+		camif_hw_disable_capture(vp);
+		camif_hw_enable_scaler(vp, false);
+	}
+
+	spin_unlock_irqrestore(&camif->slock, flags);
+
+	return camif_reinitialize(vp);
+}
+
+static int camif_prepare_addr(struct camif_vp *vp, struct vb2_buffer *vb,
+			      struct camif_addr *paddr)
+{
+	struct camif_frame *frame = &vp->out_frame;
+	u32 pix_size;
+
+	if (vb == NULL || frame == NULL)
+		return -EINVAL;
+
+	pix_size = frame->rect.width * frame->rect.height;
+
+	pr_debug("colplanes: %d, pix_size: %u\n",
+		 vp->out_fmt->colplanes, pix_size);
+
+	paddr->y = vb2_dma_contig_plane_dma_addr(vb, 0);
+
+	switch (vp->out_fmt->colplanes) {
+	case 1:
+		paddr->cb = 0;
+		paddr->cr = 0;
+		break;
+	case 2:
+		/* decompose Y into Y/Cb */
+		paddr->cb = (u32)(paddr->y + pix_size);
+		paddr->cr = 0;
+		break;
+	case 3:
+		paddr->cb = (u32)(paddr->y + pix_size);
+		/* decompose Y into Y/Cb/Cr */
+		if (vp->out_fmt->color == IMG_FMT_YCBCR422P)
+			paddr->cr = (u32)(paddr->cb + (pix_size >> 1));
+		else /* 420 */
+			paddr->cr = (u32)(paddr->cb + (pix_size >> 2));
+
+		if (vp->out_fmt->color == IMG_FMT_YCRCB420)
+			swap(paddr->cb, paddr->cr);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	pr_debug("DMA address: y: %#x  cb: %#x cr: %#x\n",
+		 paddr->y, paddr->cb, paddr->cr);
+
+	return 0;
+}
+
+irqreturn_t s3c_camif_irq_handler(int irq, void *priv)
+{
+	struct camif_vp *vp = priv;
+	struct camif_dev *camif = vp->camif;
+	unsigned int ip_rev = camif->variant->ip_revision;
+	unsigned int status;
+
+	spin_lock(&camif->slock);
+
+	if (ip_rev == S3C6410_CAMIF_IP_REV)
+		camif_hw_clear_pending_irq(vp);
+
+	status = camif_hw_get_status(vp);
+
+	if (ip_rev == S3C244X_CAMIF_IP_REV && (status & CISTATUS_OVF_MASK)) {
+		camif_hw_clear_fifo_overflow(vp);
+		goto unlock;
+	}
+
+	if (vp->state & ST_VP_ABORTING) {
+		if (vp->state & ST_VP_OFF) {
+			/* Last IRQ */
+			vp->state &= ~(ST_VP_OFF | ST_VP_ABORTING |
+				       ST_VP_LASTIRQ);
+			wake_up(&vp->irq_queue);
+			goto unlock;
+		} else if (vp->state & ST_VP_LASTIRQ) {
+			camif_hw_disable_capture(vp);
+			camif_hw_enable_scaler(vp, false);
+			camif_hw_set_lastirq(vp, false);
+			vp->state |= ST_VP_OFF;
+		} else {
+			/* Disable capture, enable last IRQ */
+			camif_hw_set_lastirq(vp, true);
+			vp->state |= ST_VP_LASTIRQ;
+		}
+	}
+
+	if (!list_empty(&vp->pending_buf_q) && (vp->state & ST_VP_RUNNING) &&
+	    !list_empty(&vp->active_buf_q)) {
+		unsigned int index;
+		struct camif_buffer *vbuf;
+		struct timeval *tv;
+		struct timespec ts;
+		/*
+		 * Get previous DMA write buffer index:
+		 * 0 => DMA buffer 0, 2;
+		 * 1 => DMA buffer 1, 3.
+		 */
+		index = (CISTATUS_FRAMECNT(status) + 2) & 1;
+
+		ktime_get_ts(&ts);
+		vbuf = camif_active_queue_peek(vp, index);
+
+		if (!WARN_ON(vbuf == NULL)) {
+			/* Dequeue a filled buffer */
+			tv = &vbuf->vb.v4l2_buf.timestamp;
+			tv->tv_sec = ts.tv_sec;
+			tv->tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+			vbuf->vb.v4l2_buf.sequence = vp->frame_sequence++;
+			vb2_buffer_done(&vbuf->vb, VB2_BUF_STATE_DONE);
+
+			/* Set up an empty buffer at the DMA engine */
+			vbuf = camif_pending_queue_pop(vp);
+			vbuf->index = index;
+			camif_hw_set_output_addr(vp, &vbuf->paddr, index);
+			camif_hw_set_output_addr(vp, &vbuf->paddr, index + 2);
+
+			/* Scheduled in H/W, add to the queue */
+			camif_active_queue_add(vp, vbuf);
+		}
+	} else if (!(vp->state & ST_VP_ABORTING) &&
+		   (vp->state & ST_VP_PENDING))  {
+		vp->state |= ST_VP_RUNNING;
+	}
+
+	if (vp->state & ST_VP_CONFIG) {
+		camif_prepare_dma_offset(vp);
+		camif_hw_set_camera_crop(camif);
+		camif_hw_set_scaler(vp);
+		camif_hw_set_flip(vp);
+		camif_hw_set_test_pattern(camif, camif->test_pattern);
+		if (camif->variant->has_img_effect)
+			camif_hw_set_effect(camif, camif->colorfx,
+				    camif->colorfx_cb, camif->colorfx_cr);
+		vp->state &= ~ST_VP_CONFIG;
+	}
+unlock:
+	spin_unlock(&camif->slock);
+	return IRQ_HANDLED;
+}
+
+static int start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct camif_vp *vp = vb2_get_drv_priv(vq);
+	struct camif_dev *camif = vp->camif;
+	unsigned long flags;
+	int ret;
+
+	/*
+	 * We assume the codec capture path is always activated
+	 * first, before the preview path starts streaming.
+	 * This is required to avoid internal FIFO overflow and
+	 * a need for CAMIF software reset.
+	 */
+	spin_lock_irqsave(&camif->slock, flags);
+
+	if (camif->stream_count == 0) {
+		camif_hw_reset(camif);
+		ret = s3c_camif_hw_init(camif, vp);
+	} else {
+		ret = s3c_camif_hw_vp_init(camif, vp);
+	}
+	spin_unlock_irqrestore(&camif->slock, flags);
+
+	if (ret < 0) {
+		camif_reinitialize(vp);
+		return ret;
+	}
+
+	spin_lock_irqsave(&camif->slock, flags);
+	vp->frame_sequence = 0;
+	vp->state |= ST_VP_PENDING;
+
+	if (!list_empty(&vp->pending_buf_q) &&
+	    (!(vp->state & ST_VP_STREAMING) ||
+	     !(vp->state & ST_VP_SENSOR_STREAMING))) {
+
+		camif_hw_enable_scaler(vp, vp->scaler.enable);
+		camif_hw_enable_capture(vp);
+		vp->state |= ST_VP_STREAMING;
+
+		if (!(vp->state & ST_VP_SENSOR_STREAMING)) {
+			vp->state |= ST_VP_SENSOR_STREAMING;
+			spin_unlock_irqrestore(&camif->slock, flags);
+			ret = sensor_set_streaming(camif, 1);
+			if (ret)
+				v4l2_err(&vp->vdev, "Sensor s_stream failed\n");
+			if (debug)
+				camif_hw_dump_regs(camif, __func__);
+
+			return ret;
+		}
+	}
+
+	spin_unlock_irqrestore(&camif->slock, flags);
+	return 0;
+}
+
+static int stop_streaming(struct vb2_queue *vq)
+{
+	struct camif_vp *vp = vb2_get_drv_priv(vq);
+	return camif_stop_capture(vp);
+}
+
+static int queue_setup(struct vb2_queue *vq, const struct v4l2_format *pfmt,
+		       unsigned int *num_buffers, unsigned int *num_planes,
+		       unsigned int sizes[], void *allocators[])
+{
+	const struct v4l2_pix_format *pix = NULL;
+	struct camif_vp *vp = vb2_get_drv_priv(vq);
+	struct camif_dev *camif = vp->camif;
+	struct camif_frame *frame = &vp->out_frame;
+	const struct camif_fmt *fmt = vp->out_fmt;
+	unsigned int size;
+
+	if (pfmt) {
+		pix = &pfmt->fmt.pix;
+		fmt = s3c_camif_find_format(vp, &pix->pixelformat, -1);
+		size = (pix->width * pix->height * fmt->depth) / 8;
+	} else {
+		size = (frame->f_width * frame->f_height * fmt->depth) / 8;
+	}
+
+	if (fmt == NULL)
+		return -EINVAL;
+	*num_planes = 1;
+
+	if (pix)
+		sizes[0] = max(size, pix->sizeimage);
+	else
+		sizes[0] = size;
+	allocators[0] = camif->alloc_ctx;
+
+	pr_debug("size: %u\n", sizes[0]);
+	return 0;
+}
+
+static int buffer_prepare(struct vb2_buffer *vb)
+{
+	struct camif_vp *vp = vb2_get_drv_priv(vb->vb2_queue);
+
+	if (vp->out_fmt == NULL)
+		return -EINVAL;
+
+	if (vb2_plane_size(vb, 0) < vp->payload) {
+		v4l2_err(&vp->vdev, "buffer too small: %lu, required: %u\n",
+			 vb2_plane_size(vb, 0), vp->payload);
+		return -EINVAL;
+	}
+	vb2_set_plane_payload(vb, 0, vp->payload);
+
+	return 0;
+}
+
+static void buffer_queue(struct vb2_buffer *vb)
+{
+	struct camif_buffer *buf = container_of(vb, struct camif_buffer, vb);
+	struct camif_vp *vp = vb2_get_drv_priv(vb->vb2_queue);
+	struct camif_dev *camif = vp->camif;
+	unsigned long flags;
+
+	spin_lock_irqsave(&camif->slock, flags);
+	WARN_ON(camif_prepare_addr(vp, &buf->vb, &buf->paddr));
+
+	if (!(vp->state & ST_VP_STREAMING) && vp->active_buffers < 2) {
+		/* Schedule an empty buffer in H/W */
+		buf->index = vp->buf_index;
+
+		camif_hw_set_output_addr(vp, &buf->paddr, buf->index);
+		camif_hw_set_output_addr(vp, &buf->paddr, buf->index + 2);
+
+		camif_active_queue_add(vp, buf);
+		vp->buf_index = !vp->buf_index;
+	} else {
+		camif_pending_queue_add(vp, buf);
+	}
+
+	if (vb2_is_streaming(&vp->vb_queue) && !list_empty(&vp->pending_buf_q)
+		&& !(vp->state & ST_VP_STREAMING)) {
+
+		vp->state |= ST_VP_STREAMING;
+		camif_hw_enable_scaler(vp, vp->scaler.enable);
+		camif_hw_enable_capture(vp);
+		spin_unlock_irqrestore(&camif->slock, flags);
+
+		if (!(vp->state & ST_VP_SENSOR_STREAMING)) {
+			if (sensor_set_streaming(camif, 1) == 0)
+				vp->state |= ST_VP_SENSOR_STREAMING;
+			else
+				v4l2_err(&vp->vdev, "Sensor s_stream failed\n");
+
+			if (debug)
+				camif_hw_dump_regs(camif, __func__);
+		}
+		return;
+	}
+	spin_unlock_irqrestore(&camif->slock, flags);
+}
+
+static void camif_lock(struct vb2_queue *vq)
+{
+	struct camif_vp *vp = vb2_get_drv_priv(vq);
+	mutex_lock(&vp->camif->lock);
+}
+
+static void camif_unlock(struct vb2_queue *vq)
+{
+	struct camif_vp *vp = vb2_get_drv_priv(vq);
+	mutex_unlock(&vp->camif->lock);
+}
+
+static const struct vb2_ops s3c_camif_qops = {
+	.queue_setup	 = queue_setup,
+	.buf_prepare	 = buffer_prepare,
+	.buf_queue	 = buffer_queue,
+	.wait_prepare	 = camif_unlock,
+	.wait_finish	 = camif_lock,
+	.start_streaming = start_streaming,
+	.stop_streaming	 = stop_streaming,
+};
+
+static int s3c_camif_open(struct file *file)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	struct camif_dev *camif = vp->camif;
+	int ret;
+
+	pr_debug("[vp%d] state: %#x,  owner: %p, pid: %d\n", vp->id,
+		 vp->state, vp->owner, task_pid_nr(current));
+
+	if (mutex_lock_interruptible(&camif->lock))
+		return -ERESTARTSYS;
+
+	ret = v4l2_fh_open(file);
+	if (ret < 0)
+		goto unlock;
+
+	ret = pm_runtime_get_sync(camif->dev);
+	if (ret < 0)
+		goto err_pm;
+
+	ret = sensor_set_power(camif, 1);
+	if (!ret)
+		goto unlock;
+
+	pm_runtime_put(camif->dev);
+err_pm:
+	v4l2_fh_release(file);
+unlock:
+	mutex_unlock(&camif->lock);
+	return ret;
+}
+
+static int s3c_camif_close(struct file *file)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	struct camif_dev *camif = vp->camif;
+	int ret;
+
+	pr_debug("[vp%d] state: %#x, owner: %p, pid: %d\n", vp->id,
+		 vp->state, vp->owner, task_pid_nr(current));
+
+	mutex_lock(&camif->lock);
+
+	if (vp->owner == file->private_data) {
+		camif_stop_capture(vp);
+		vb2_queue_release(&vp->vb_queue);
+		vp->owner = NULL;
+	}
+
+	sensor_set_power(camif, 0);
+
+	pm_runtime_put(camif->dev);
+	ret = v4l2_fh_release(file);
+
+	mutex_unlock(&camif->lock);
+	return ret;
+}
+
+static unsigned int s3c_camif_poll(struct file *file,
+				   struct poll_table_struct *wait)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	struct camif_dev *camif = vp->camif;
+	int ret;
+
+	mutex_lock(&camif->lock);
+	if (vp->owner && vp->owner != file->private_data)
+		ret = -EBUSY;
+	else
+		ret = vb2_poll(&vp->vb_queue, file, wait);
+
+	mutex_unlock(&camif->lock);
+	return ret;
+}
+
+static int s3c_camif_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	int ret;
+
+	if (vp->owner && vp->owner != file->private_data)
+		ret = -EBUSY;
+	else
+		ret = vb2_mmap(&vp->vb_queue, vma);
+
+	return ret;
+}
+
+static const struct v4l2_file_operations s3c_camif_fops = {
+	.owner		= THIS_MODULE,
+	.open		= s3c_camif_open,
+	.release	= s3c_camif_close,
+	.poll		= s3c_camif_poll,
+	.unlocked_ioctl	= video_ioctl2,
+	.mmap		= s3c_camif_mmap,
+};
+
+/*
+ * Video node IOCTLs
+ */
+
+static int s3c_camif_vidioc_querycap(struct file *file, void *priv,
+				     struct v4l2_capability *cap)
+{
+	struct camif_vp *vp = video_drvdata(file);
+
+	strlcpy(cap->driver, S3C_CAMIF_DRIVER_NAME, sizeof(cap->driver));
+	strlcpy(cap->card, S3C_CAMIF_DRIVER_NAME, sizeof(cap->card));
+	snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s.%d",
+		 dev_name(vp->camif->dev), vp->id);
+
+	cap->device_caps = V4L2_CAP_STREAMING | V4L2_CAP_VIDEO_CAPTURE;
+	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
+
+	return 0;
+}
+
+static int s3c_camif_vidioc_enum_input(struct file *file, void *priv,
+				       struct v4l2_input *input)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	struct v4l2_subdev *sensor = vp->camif->sensor.sd;
+
+	if (input->index || sensor == NULL)
+		return -EINVAL;
+
+	input->type = V4L2_INPUT_TYPE_CAMERA;
+	strlcpy(input->name, sensor->name, sizeof(input->name));
+	return 0;
+}
+
+static int s3c_camif_vidioc_s_input(struct file *file, void *priv,
+				    unsigned int i)
+{
+	return i == 0 ? 0 : -EINVAL;
+}
+
+static int s3c_camif_vidioc_g_input(struct file *file, void *priv,
+				    unsigned int *i)
+{
+	*i = 0;
+	return 0;
+}
+
+static int s3c_camif_vidioc_enum_fmt(struct file *file, void *priv,
+				     struct v4l2_fmtdesc *f)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	const struct camif_fmt *fmt;
+
+	fmt = s3c_camif_find_format(vp, NULL, f->index);
+	if (!fmt)
+		return -EINVAL;
+
+	strlcpy(f->description, fmt->name, sizeof(f->description));
+	f->pixelformat = fmt->fourcc;
+
+	pr_debug("fmt(%d): %s\n", f->index, f->description);
+	return 0;
+}
+
+static int s3c_camif_vidioc_g_fmt(struct file *file, void *priv,
+				  struct v4l2_format *f)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	struct v4l2_pix_format *pix = &f->fmt.pix;
+	struct camif_frame *frame = &vp->out_frame;
+	const struct camif_fmt *fmt = vp->out_fmt;
+
+	pix->bytesperline = frame->f_width * fmt->ybpp;
+	pix->sizeimage = vp->payload;
+
+	pix->pixelformat = fmt->fourcc;
+	pix->width = frame->f_width;
+	pix->height = frame->f_height;
+	pix->field = V4L2_FIELD_NONE;
+	pix->colorspace = V4L2_COLORSPACE_JPEG;
+
+	return 0;
+}
+
+static int __camif_video_try_format(struct camif_vp *vp,
+				    struct v4l2_pix_format *pix,
+				    const struct camif_fmt **ffmt)
+{
+	struct camif_dev *camif = vp->camif;
+	struct v4l2_rect *crop = &camif->camif_crop;
+	unsigned int wmin, hmin, sc_hrmax, sc_vrmax;
+	const struct vp_pix_limits *pix_lim;
+	const struct camif_fmt *fmt;
+
+	fmt = s3c_camif_find_format(vp, &pix->pixelformat, 0);
+
+	if (WARN_ON(fmt == NULL))
+		return -EINVAL;
+
+	if (ffmt)
+		*ffmt = fmt;
+
+	pix_lim = &camif->variant->vp_pix_limits[vp->id];
+
+	pr_debug("fmt: %ux%u, crop: %ux%u, bytesperline: %u\n",
+		 pix->width, pix->height, crop->width, crop->height,
+		 pix->bytesperline);
+	/*
+	 * Calculate minimum width and height according to the configured
+	 * camera input interface crop rectangle and the resizer's capabilities.
+	 */
+	sc_hrmax = min(SCALER_MAX_RATIO, 1 << (ffs(crop->width) - 3));
+	sc_vrmax = min(SCALER_MAX_RATIO, 1 << (ffs(crop->height) - 1));
+
+	wmin = max_t(u32, pix_lim->min_out_width, crop->width / sc_hrmax);
+	wmin = round_up(wmin, pix_lim->out_width_align);
+	hmin = max_t(u32, 8, crop->height / sc_vrmax);
+	hmin = round_up(hmin, 8);
+
+	v4l_bound_align_image(&pix->width, wmin, pix_lim->max_sc_out_width,
+			      ffs(pix_lim->out_width_align) - 1,
+			      &pix->height, hmin, pix_lim->max_height, 0, 0);
+
+	pix->bytesperline = pix->width * fmt->ybpp;
+	pix->sizeimage = (pix->width * pix->height * fmt->depth) / 8;
+	pix->pixelformat = fmt->fourcc;
+	pix->colorspace = V4L2_COLORSPACE_JPEG;
+	pix->field = V4L2_FIELD_NONE;
+
+	pr_debug("%ux%u, wmin: %d, hmin: %d, sc_hrmax: %d, sc_vrmax: %d\n",
+		 pix->width, pix->height, wmin, hmin, sc_hrmax, sc_vrmax);
+
+	return 0;
+}
+
+static int s3c_camif_vidioc_try_fmt(struct file *file, void *priv,
+				    struct v4l2_format *f)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	return __camif_video_try_format(vp, &f->fmt.pix, NULL);
+}
+
+static int s3c_camif_vidioc_s_fmt(struct file *file, void *priv,
+				  struct v4l2_format *f)
+{
+	struct v4l2_pix_format *pix = &f->fmt.pix;
+	struct camif_vp *vp = video_drvdata(file);
+	struct camif_frame *out_frame = &vp->out_frame;
+	const struct camif_fmt *fmt = NULL;
+	int ret;
+
+	pr_debug("[vp%d]\n", vp->id);
+
+	if (vb2_is_busy(&vp->vb_queue))
+		return -EBUSY;
+
+	ret = __camif_video_try_format(vp, &f->fmt.pix, &fmt);
+	if (ret < 0)
+		return ret;
+
+	vp->out_fmt = fmt;
+	vp->payload = pix->sizeimage;
+	out_frame->f_width = pix->width;
+	out_frame->f_height = pix->height;
+
+	/* Reset composition rectangle */
+	out_frame->rect.width = pix->width;
+	out_frame->rect.height = pix->height;
+	out_frame->rect.left = 0;
+	out_frame->rect.top = 0;
+
+	if (vp->owner == NULL)
+		vp->owner = priv;
+
+	pr_debug("%ux%u. payload: %u. fmt: %s. %d %d. sizeimage: %d. bpl: %d\n",
+		out_frame->f_width, out_frame->f_height, vp->payload, fmt->name,
+		pix->width * pix->height * fmt->depth, fmt->depth,
+		pix->sizeimage, pix->bytesperline);
+
+	return 0;
+}
+
+/* Only check pixel formats at the sensor and the camif subdev pads */
+static int camif_pipeline_validate(struct camif_dev *camif)
+{
+	struct v4l2_subdev_format src_fmt;
+	struct media_pad *pad;
+	int ret;
+
+	/* Retrieve format at the sensor subdev source pad */
+	pad = media_entity_remote_source(&camif->pads[0]);
+	if (!pad || media_entity_type(pad->entity) != MEDIA_ENT_T_V4L2_SUBDEV)
+		return -EPIPE;
+
+	src_fmt.pad = pad->index;
+	src_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	ret = v4l2_subdev_call(camif->sensor.sd, pad, get_fmt, NULL, &src_fmt);
+	if (ret < 0 && ret != -ENOIOCTLCMD)
+		return -EPIPE;
+
+	if (src_fmt.format.width != camif->mbus_fmt.width ||
+	    src_fmt.format.height != camif->mbus_fmt.height ||
+	    src_fmt.format.code != camif->mbus_fmt.code)
+		return -EPIPE;
+
+	return 0;
+}
+
+static int s3c_camif_streamon(struct file *file, void *priv,
+			      enum v4l2_buf_type type)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	struct camif_dev *camif = vp->camif;
+	struct media_entity *sensor = &camif->sensor.sd->entity;
+	int ret;
+
+	pr_debug("[vp%d]\n", vp->id);
+
+	if (type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
+	if (vp->owner && vp->owner != priv)
+		return -EBUSY;
+
+	if (s3c_vp_active(vp))
+		return 0;
+
+	ret = media_entity_pipeline_start(sensor, camif->m_pipeline);
+	if (ret < 0)
+		return ret;
+
+	ret = camif_pipeline_validate(camif);
+	if (ret < 0) {
+		media_entity_pipeline_stop(sensor);
+		return ret;
+	}
+
+	return vb2_streamon(&vp->vb_queue, type);
+}
+
+static int s3c_camif_streamoff(struct file *file, void *priv,
+			       enum v4l2_buf_type type)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	struct camif_dev *camif = vp->camif;
+	int ret;
+
+	pr_debug("[vp%d]\n", vp->id);
+
+	if (type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
+	if (vp->owner && vp->owner != priv)
+		return -EBUSY;
+
+	ret = vb2_streamoff(&vp->vb_queue, type);
+	if (ret == 0)
+		media_entity_pipeline_stop(&camif->sensor.sd->entity);
+	return ret;
+}
+
+static int s3c_camif_reqbufs(struct file *file, void *priv,
+			     struct v4l2_requestbuffers *rb)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	int ret;
+
+	pr_debug("[vp%d] rb count: %d, owner: %p, priv: %p\n",
+		 vp->id, rb->count, vp->owner, priv);
+
+	if (vp->owner && vp->owner != priv)
+		return -EBUSY;
+
+	if (rb->count)
+		rb->count = max_t(u32, CAMIF_REQ_BUFS_MIN, rb->count);
+	else
+		vp->owner = NULL;
+
+	ret = vb2_reqbufs(&vp->vb_queue, rb);
+	if (!ret) {
+		vp->reqbufs_count = rb->count;
+		if (vp->owner == NULL && rb->count > 0)
+			vp->owner = priv;
+	}
+
+	return ret;
+}
+
+static int s3c_camif_querybuf(struct file *file, void *priv,
+			      struct v4l2_buffer *buf)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	return vb2_querybuf(&vp->vb_queue, buf);
+}
+
+static int s3c_camif_qbuf(struct file *file, void *priv,
+			  struct v4l2_buffer *buf)
+{
+	struct camif_vp *vp = video_drvdata(file);
+
+	pr_debug("[vp%d]\n", vp->id);
+
+	if (vp->owner && vp->owner != priv)
+		return -EBUSY;
+
+	return vb2_qbuf(&vp->vb_queue, buf);
+}
+
+static int s3c_camif_dqbuf(struct file *file, void *priv,
+			   struct v4l2_buffer *buf)
+{
+	struct camif_vp *vp = video_drvdata(file);
+
+	pr_debug("[vp%d] sequence: %d\n", vp->id, vp->frame_sequence);
+
+	if (vp->owner && vp->owner != priv)
+		return -EBUSY;
+
+	return vb2_dqbuf(&vp->vb_queue, buf, file->f_flags & O_NONBLOCK);
+}
+
+static int s3c_camif_create_bufs(struct file *file, void *priv,
+				 struct v4l2_create_buffers *create)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	int ret;
+
+	if (vp->owner && vp->owner != priv)
+		return -EBUSY;
+
+	create->count = max_t(u32, 1, create->count);
+	ret = vb2_create_bufs(&vp->vb_queue, create);
+
+	if (!ret && vp->owner == NULL)
+		vp->owner = priv;
+
+	return ret;
+}
+
+static int s3c_camif_prepare_buf(struct file *file, void *priv,
+				 struct v4l2_buffer *b)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	return vb2_prepare_buf(&vp->vb_queue, b);
+}
+
+static int s3c_camif_g_selection(struct file *file, void *priv,
+				 struct v4l2_selection *sel)
+{
+	struct camif_vp *vp = video_drvdata(file);
+
+	if (sel->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
+	switch (sel->target) {
+	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
+	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
+		sel->r.left = 0;
+		sel->r.top = 0;
+		sel->r.width = vp->out_frame.f_width;
+		sel->r.height = vp->out_frame.f_height;
+		return 0;
+
+	case V4L2_SEL_TGT_COMPOSE:
+		sel->r = vp->out_frame.rect;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static void __camif_try_compose(struct camif_dev *camif, struct camif_vp *vp,
+				struct v4l2_rect *r)
+{
+	/* s3c244x doesn't support composition */
+	if (camif->variant->ip_revision == S3C244X_CAMIF_IP_REV) {
+		*r = vp->out_frame.rect;
+		return;
+	}
+
+	/* TODO: s3c64xx */
+}
+
+static int s3c_camif_s_selection(struct file *file, void *priv,
+				 struct v4l2_selection *sel)
+{
+	struct camif_vp *vp = video_drvdata(file);
+	struct camif_dev *camif = vp->camif;
+	struct v4l2_rect rect = sel->r;
+	unsigned long flags;
+
+	if (sel->type != V4L2_BUF_TYPE_VIDEO_CAPTURE ||
+	    sel->target != V4L2_SEL_TGT_COMPOSE)
+		return -EINVAL;
+
+	__camif_try_compose(camif, vp, &rect);
+
+	sel->r = rect;
+	spin_lock_irqsave(&camif->slock, flags);
+	vp->out_frame.rect = rect;
+	vp->state |= ST_VP_CONFIG;
+	spin_unlock_irqrestore(&camif->slock, flags);
+
+	pr_debug("type: %#x, target: %#x, flags: %#x, (%d,%d)/%dx%d\n",
+		sel->type, sel->target, sel->flags,
+		sel->r.left, sel->r.top, sel->r.width, sel->r.height);
+
+	return 0;
+}
+
+static const struct v4l2_ioctl_ops s3c_camif_ioctl_ops = {
+	.vidioc_querycap	  = s3c_camif_vidioc_querycap,
+	.vidioc_enum_input	  = s3c_camif_vidioc_enum_input,
+	.vidioc_g_input		  = s3c_camif_vidioc_g_input,
+	.vidioc_s_input		  = s3c_camif_vidioc_s_input,
+	.vidioc_enum_fmt_vid_cap  = s3c_camif_vidioc_enum_fmt,
+	.vidioc_try_fmt_vid_cap	  = s3c_camif_vidioc_try_fmt,
+	.vidioc_s_fmt_vid_cap	  = s3c_camif_vidioc_s_fmt,
+	.vidioc_g_fmt_vid_cap	  = s3c_camif_vidioc_g_fmt,
+	.vidioc_g_selection	  = s3c_camif_g_selection,
+	.vidioc_s_selection	  = s3c_camif_s_selection,
+	.vidioc_reqbufs		  = s3c_camif_reqbufs,
+	.vidioc_querybuf	  = s3c_camif_querybuf,
+	.vidioc_prepare_buf	  = s3c_camif_prepare_buf,
+	.vidioc_create_bufs	  = s3c_camif_create_bufs,
+	.vidioc_qbuf		  = s3c_camif_qbuf,
+	.vidioc_dqbuf		  = s3c_camif_dqbuf,
+	.vidioc_streamon	  = s3c_camif_streamon,
+	.vidioc_streamoff	  = s3c_camif_streamoff,
+	.vidioc_subscribe_event	  = v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+	.vidioc_log_status	  = v4l2_ctrl_log_status,
+};
+
+/*
+ * Video node controls
+ */
+static int s3c_camif_video_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct camif_vp *vp = ctrl->priv;
+	struct camif_dev *camif = vp->camif;
+	unsigned long flags;
+
+	pr_debug("[vp%d] ctrl: %s, value: %d\n", vp->id,
+		 ctrl->name, ctrl->val);
+
+	spin_lock_irqsave(&camif->slock, flags);
+
+	switch (ctrl->id) {
+	case V4L2_CID_HFLIP:
+		vp->hflip = ctrl->val;
+		break;
+
+	case V4L2_CID_VFLIP:
+		vp->vflip = ctrl->val;
+		break;
+	}
+
+	vp->state |= ST_VP_CONFIG;
+	spin_unlock_irqrestore(&camif->slock, flags);
+	return 0;
+}
+
+/* Codec and preview video node control ops */
+static const struct v4l2_ctrl_ops s3c_camif_video_ctrl_ops = {
+	.s_ctrl = s3c_camif_video_s_ctrl,
+};
+
+int s3c_camif_register_video_node(struct camif_dev *camif, int idx)
+{
+	struct camif_vp *vp = &camif->vp[idx];
+	struct vb2_queue *q = &vp->vb_queue;
+	struct video_device *vfd = &vp->vdev;
+	struct v4l2_ctrl *ctrl;
+	int ret;
+
+	memset(vfd, 0, sizeof(*vfd));
+	snprintf(vfd->name, sizeof(vfd->name), "camif-%s",
+		 vp->id == 0 ? "codec" : "preview");
+
+	vfd->fops = &s3c_camif_fops;
+	vfd->ioctl_ops = &s3c_camif_ioctl_ops;
+	vfd->v4l2_dev = &camif->v4l2_dev;
+	vfd->minor = -1;
+	vfd->release = video_device_release_empty;
+	vfd->lock = &camif->lock;
+	vp->reqbufs_count = 0;
+
+	INIT_LIST_HEAD(&vp->pending_buf_q);
+	INIT_LIST_HEAD(&vp->active_buf_q);
+
+	memset(q, 0, sizeof(*q));
+	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	q->io_modes = VB2_MMAP | VB2_USERPTR;
+	q->ops = &s3c_camif_qops;
+	q->mem_ops = &vb2_dma_contig_memops;
+	q->buf_struct_size = sizeof(struct camif_buffer);
+	q->drv_priv = vp;
+
+	ret = vb2_queue_init(q);
+	if (ret)
+		goto err_vd_rel;
+
+	vp->pad.flags = MEDIA_PAD_FL_SINK;
+	ret = media_entity_init(&vfd->entity, 1, &vp->pad, 0);
+	if (ret)
+		goto err_vd_rel;
+
+	video_set_drvdata(vfd, vp);
+	set_bit(V4L2_FL_USE_FH_PRIO, &vfd->flags);
+
+	v4l2_ctrl_handler_init(&vp->ctrl_handler, 1);
+	ctrl = v4l2_ctrl_new_std(&vp->ctrl_handler, &s3c_camif_video_ctrl_ops,
+				 V4L2_CID_HFLIP, 0, 1, 1, 0);
+	if (ctrl)
+		ctrl->priv = vp;
+	ctrl = v4l2_ctrl_new_std(&vp->ctrl_handler, &s3c_camif_video_ctrl_ops,
+				 V4L2_CID_VFLIP, 0, 1, 1, 0);
+	if (ctrl)
+		ctrl->priv = vp;
+
+	ret = vp->ctrl_handler.error;
+	if (ret < 0)
+		goto err_me_cleanup;
+
+	vfd->ctrl_handler = &vp->ctrl_handler;
+
+	ret = video_register_device(vfd, VFL_TYPE_GRABBER, -1);
+	if (ret)
+		goto err_ctrlh_free;
+
+	v4l2_info(&camif->v4l2_dev, "registered %s as /dev/%s\n",
+		  vfd->name, video_device_node_name(vfd));
+	return 0;
+
+err_ctrlh_free:
+	v4l2_ctrl_handler_free(&vp->ctrl_handler);
+err_me_cleanup:
+	media_entity_cleanup(&vfd->entity);
+err_vd_rel:
+	video_device_release(vfd);
+	return ret;
+}
+
+void s3c_camif_unregister_video_node(struct camif_dev *camif, int idx)
+{
+	struct video_device *vfd = &camif->vp[idx].vdev;
+
+	if (video_is_registered(vfd)) {
+		video_unregister_device(vfd);
+		media_entity_cleanup(&vfd->entity);
+		v4l2_ctrl_handler_free(vfd->ctrl_handler);
+	}
+}
+
+/* Media bus pixel formats supported at the camif input */
+static const enum v4l2_mbus_pixelcode camif_mbus_formats[] = {
+	V4L2_MBUS_FMT_YUYV8_2X8,
+	V4L2_MBUS_FMT_YVYU8_2X8,
+	V4L2_MBUS_FMT_UYVY8_2X8,
+	V4L2_MBUS_FMT_VYUY8_2X8,
+};
+
+/*
+ *  Camera input interface subdev operations
+ */
+
+static int s3c_camif_subdev_enum_mbus_code(struct v4l2_subdev *sd,
+					struct v4l2_subdev_fh *fh,
+					struct v4l2_subdev_mbus_code_enum *code)
+{
+	if (code->index >= ARRAY_SIZE(camif_mbus_formats))
+		return -EINVAL;
+
+	code->code = camif_mbus_formats[code->index];
+	return 0;
+}
+
+static int s3c_camif_subdev_get_fmt(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_fh *fh,
+				    struct v4l2_subdev_format *fmt)
+{
+	struct camif_dev *camif = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *mf = &fmt->format;
+
+	if (fmt->which == V4L2_SUBDEV_FORMAT_TRY) {
+		mf = v4l2_subdev_get_try_format(fh, fmt->pad);
+		fmt->format = *mf;
+		return 0;
+	}
+
+	mutex_lock(&camif->lock);
+
+	switch (fmt->pad) {
+	case CAMIF_SD_PAD_SINK:
+		/* full camera input pixel size */
+		*mf = camif->mbus_fmt;
+		break;
+
+	case CAMIF_SD_PAD_SOURCE_C...CAMIF_SD_PAD_SOURCE_P:
+		/* crop rectangle at camera interface input */
+		mf->width = camif->camif_crop.width;
+		mf->height = camif->camif_crop.height;
+		mf->code = camif->mbus_fmt.code;
+		break;
+	}
+
+	mutex_unlock(&camif->lock);
+	mf->colorspace = V4L2_COLORSPACE_JPEG;
+	return 0;
+}
+
+static void __camif_subdev_try_format(struct camif_dev *camif,
+				struct v4l2_mbus_framefmt *mf, int pad)
+{
+	const struct s3c_camif_variant *variant = camif->variant;
+	const struct vp_pix_limits *pix_lim;
+	int i = ARRAY_SIZE(camif_mbus_formats);
+
+	/* FIXME: constraints against codec or preview path ? */
+	pix_lim = &variant->vp_pix_limits[VP_CODEC];
+
+	while (i-- >= 0)
+		if (camif_mbus_formats[i] == mf->code)
+			break;
+
+	mf->code = camif_mbus_formats[i];
+
+	if (pad == CAMIF_SD_PAD_SINK) {
+		v4l_bound_align_image(&mf->width, 8, CAMIF_MAX_PIX_WIDTH,
+				      ffs(pix_lim->out_width_align) - 1,
+				      &mf->height, 8, CAMIF_MAX_PIX_HEIGHT, 0,
+				      0);
+	} else {
+		struct v4l2_rect *crop = &camif->camif_crop;
+		v4l_bound_align_image(&mf->width, 8, crop->width,
+				      ffs(pix_lim->out_width_align) - 1,
+				      &mf->height, 8, crop->height,
+				      0, 0);
+	}
+
+	v4l2_dbg(1, debug, &camif->subdev, "%ux%u\n", mf->width, mf->height);
+}
+
+static int s3c_camif_subdev_set_fmt(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_fh *fh,
+				    struct v4l2_subdev_format *fmt)
+{
+	struct camif_dev *camif = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *mf = &fmt->format;
+	struct v4l2_rect *crop = &camif->camif_crop;
+	int i;
+
+	v4l2_dbg(1, debug, sd, "pad%d: code: 0x%x, %ux%u\n",
+		 fmt->pad, mf->code, mf->width, mf->height);
+
+	mf->colorspace = V4L2_COLORSPACE_JPEG;
+	mutex_lock(&camif->lock);
+
+	/*
+	 * No pixel format change at the camera input is allowed
+	 * while streaming.
+	 */
+	if (vb2_is_busy(&camif->vp[VP_CODEC].vb_queue) ||
+	    vb2_is_busy(&camif->vp[VP_PREVIEW].vb_queue)) {
+		mutex_unlock(&camif->lock);
+		return -EBUSY;
+	}
+
+	__camif_subdev_try_format(camif, mf, fmt->pad);
+
+	if (fmt->which == V4L2_SUBDEV_FORMAT_TRY) {
+		mf = v4l2_subdev_get_try_format(fh, fmt->pad);
+		*mf = fmt->format;
+		mutex_unlock(&camif->lock);
+		return 0;
+	}
+
+	switch (fmt->pad) {
+	case CAMIF_SD_PAD_SINK:
+		camif->mbus_fmt = *mf;
+		/* Reset sink crop rectangle. */
+		crop->width = mf->width;
+		crop->height = mf->height;
+		crop->left = 0;
+		crop->top = 0;
+		/*
+		 * Reset source format (the camif's crop rectangle)
+		 * and the video output resolution.
+		 */
+		for (i = 0; i < CAMIF_VP_NUM; i++) {
+			struct camif_frame *frame = &camif->vp[i].out_frame;
+			frame->rect = *crop;
+			frame->f_width = mf->width;
+			frame->f_height = mf->height;
+		}
+		break;
+
+	case CAMIF_SD_PAD_SOURCE_C...CAMIF_SD_PAD_SOURCE_P:
+		/* Pixel format can be only changed on the sink pad. */
+		mf->code = camif->mbus_fmt.code;
+		mf->width = crop->width;
+		mf->height = crop->height;
+		break;
+	}
+
+	mutex_unlock(&camif->lock);
+	return 0;
+}
+
+static int s3c_camif_subdev_get_selection(struct v4l2_subdev *sd,
+					  struct v4l2_subdev_fh *fh,
+					  struct v4l2_subdev_selection *sel)
+{
+	struct camif_dev *camif = v4l2_get_subdevdata(sd);
+	struct v4l2_rect *crop = &camif->camif_crop;
+	struct v4l2_mbus_framefmt *mf = &camif->mbus_fmt;
+
+	if ((sel->target != V4L2_SEL_TGT_CROP &&
+	    sel->target != V4L2_SEL_TGT_CROP_BOUNDS) ||
+	    sel->pad != CAMIF_SD_PAD_SINK)
+		return -EINVAL;
+
+	if (sel->which == V4L2_SUBDEV_FORMAT_TRY) {
+		sel->r = *v4l2_subdev_get_try_crop(fh, sel->pad);
+		return 0;
+	}
+
+	mutex_lock(&camif->lock);
+
+	if (sel->target == V4L2_SEL_TGT_CROP) {
+		sel->r = *crop;
+	} else { /* crop bounds */
+		sel->r.width = mf->width;
+		sel->r.height = mf->height;
+		sel->r.left = 0;
+		sel->r.top = 0;
+	}
+
+	mutex_unlock(&camif->lock);
+
+	v4l2_dbg(1, debug, sd, "%s: crop: (%d,%d) %dx%d, size: %ux%u\n",
+		 __func__, crop->left, crop->top, crop->width,
+		 crop->height, mf->width, mf->height);
+
+	return 0;
+}
+
+static void __camif_try_crop(struct camif_dev *camif, struct v4l2_rect *r)
+{
+	struct v4l2_mbus_framefmt *mf = &camif->mbus_fmt;
+	const struct camif_pix_limits *pix_lim = &camif->variant->pix_limits;
+	unsigned int left = 2 * r->left;
+	unsigned int top = 2 * r->top;
+
+	/*
+	 * Following constraints must be met:
+	 *  - r->width + 2 * r->left = mf->width;
+	 *  - r->height + 2 * r->top = mf->height;
+	 *  - crop rectangle size and position must be aligned
+	 *    to 8 or 2 pixels, depending on SoC version.
+	 */
+	v4l_bound_align_image(&r->width, 0, mf->width,
+			      ffs(pix_lim->win_hor_offset_align) - 1,
+			      &r->height, 0, mf->height, 1, 0);
+
+	v4l_bound_align_image(&left, 0, mf->width - r->width,
+			      ffs(pix_lim->win_hor_offset_align),
+			      &top, 0, mf->height - r->height, 2, 0);
+
+	r->left = left / 2;
+	r->top = top / 2;
+	r->width = mf->width - left;
+	r->height = mf->height - top;
+	/*
+	 * Make sure we either downscale or upscale both the pixel
+	 * width and height. Just return current crop rectangle if
+	 * this scaler constraint is not met.
+	 */
+	if (camif->variant->ip_revision == S3C244X_CAMIF_IP_REV &&
+	    camif_is_streaming(camif)) {
+		unsigned int i;
+
+		for (i = 0; i < CAMIF_VP_NUM; i++) {
+			struct v4l2_rect *or = &camif->vp[i].out_frame.rect;
+			if ((or->width > r->width) == (or->height > r->height))
+				continue;
+			*r = camif->camif_crop;
+			pr_debug("Width/height scaling direction limitation\n");
+			break;
+		}
+	}
+
+	v4l2_dbg(1, debug, &camif->v4l2_dev, "crop: (%d,%d)/%dx%d, fmt: %ux%u\n",
+		 r->left, r->top, r->width, r->height, mf->width, mf->height);
+}
+
+static int s3c_camif_subdev_set_selection(struct v4l2_subdev *sd,
+					  struct v4l2_subdev_fh *fh,
+					  struct v4l2_subdev_selection *sel)
+{
+	struct camif_dev *camif = v4l2_get_subdevdata(sd);
+	struct v4l2_rect *crop = &camif->camif_crop;
+	struct camif_scaler scaler;
+
+	if (sel->target != V4L2_SEL_TGT_CROP || sel->pad != CAMIF_SD_PAD_SINK)
+		return -EINVAL;
+
+	mutex_lock(&camif->lock);
+	__camif_try_crop(camif, &sel->r);
+
+	if (sel->which == V4L2_SUBDEV_FORMAT_TRY) {
+		*v4l2_subdev_get_try_crop(fh, sel->pad) = sel->r;
+	} else {
+		unsigned long flags;
+		unsigned int i;
+
+		spin_lock_irqsave(&camif->slock, flags);
+		*crop = sel->r;
+
+		for (i = 0; i < CAMIF_VP_NUM; i++) {
+			struct camif_vp *vp = &camif->vp[i];
+			scaler = vp->scaler;
+			if (s3c_camif_get_scaler_config(vp, &scaler))
+				continue;
+			vp->scaler = scaler;
+			vp->state |= ST_VP_CONFIG;
+		}
+
+		spin_unlock_irqrestore(&camif->slock, flags);
+	}
+	mutex_unlock(&camif->lock);
+
+	v4l2_dbg(1, debug, sd, "%s: (%d,%d) %dx%d, f_w: %u, f_h: %u\n",
+		 __func__, crop->left, crop->top, crop->width, crop->height,
+		 camif->mbus_fmt.width, camif->mbus_fmt.height);
+
+	return 0;
+}
+
+static const struct v4l2_subdev_pad_ops s3c_camif_subdev_pad_ops = {
+	.enum_mbus_code = s3c_camif_subdev_enum_mbus_code,
+	.get_selection = s3c_camif_subdev_get_selection,
+	.set_selection = s3c_camif_subdev_set_selection,
+	.get_fmt = s3c_camif_subdev_get_fmt,
+	.set_fmt = s3c_camif_subdev_set_fmt,
+};
+
+static struct v4l2_subdev_ops s3c_camif_subdev_ops = {
+	.pad = &s3c_camif_subdev_pad_ops,
+};
+
+static int s3c_camif_subdev_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct camif_dev *camif = container_of(ctrl->handler, struct camif_dev,
+					       ctrl_handler);
+	unsigned long flags;
+
+	spin_lock_irqsave(&camif->slock, flags);
+
+	switch (ctrl->id) {
+	case V4L2_CID_COLORFX:
+		camif->colorfx = camif->ctrl_colorfx->val;
+		/* Set Cb, Cr */
+		switch (ctrl->val) {
+		case V4L2_COLORFX_SEPIA:
+			camif->colorfx_cb = 115;
+			camif->colorfx_cr = 145;
+			break;
+		case V4L2_COLORFX_SET_CBCR:
+			camif->colorfx_cb = camif->ctrl_colorfx_cbcr->val >> 8;
+			camif->colorfx_cr = camif->ctrl_colorfx_cbcr->val & 0xff;
+			break;
+		default:
+			/* for V4L2_COLORFX_BW and others */
+			camif->colorfx_cb = 128;
+			camif->colorfx_cr = 128;
+		}
+		break;
+	case V4L2_CID_TEST_PATTERN:
+		camif->test_pattern = camif->ctrl_test_pattern->val;
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	camif->vp[VP_CODEC].state |= ST_VP_CONFIG;
+	camif->vp[VP_PREVIEW].state |= ST_VP_CONFIG;
+	spin_unlock_irqrestore(&camif->slock, flags);
+
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops s3c_camif_subdev_ctrl_ops = {
+	.s_ctrl	= s3c_camif_subdev_s_ctrl,
+};
+
+static const char * const s3c_camif_test_pattern_menu[] = {
+	"Disabled",
+	"Color bars",
+	"Horizontal increment",
+	"Vertical increment",
+};
+
+int s3c_camif_create_subdev(struct camif_dev *camif)
+{
+	struct v4l2_ctrl_handler *handler = &camif->ctrl_handler;
+	struct v4l2_subdev *sd = &camif->subdev;
+	int ret;
+
+	v4l2_subdev_init(sd, &s3c_camif_subdev_ops);
+	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	strlcpy(sd->name, "S3C-CAMIF", sizeof(sd->name));
+
+	camif->pads[CAMIF_SD_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
+	camif->pads[CAMIF_SD_PAD_SOURCE_C].flags = MEDIA_PAD_FL_SOURCE;
+	camif->pads[CAMIF_SD_PAD_SOURCE_P].flags = MEDIA_PAD_FL_SOURCE;
+
+	ret = media_entity_init(&sd->entity, CAMIF_SD_PADS_NUM,
+				camif->pads, 0);
+	if (ret)
+		return ret;
+
+	v4l2_ctrl_handler_init(handler, 3);
+	camif->ctrl_test_pattern = v4l2_ctrl_new_std_menu_items(handler,
+			&s3c_camif_subdev_ctrl_ops, V4L2_CID_TEST_PATTERN,
+			ARRAY_SIZE(s3c_camif_test_pattern_menu) - 1, 0, 0,
+			s3c_camif_test_pattern_menu);
+
+	camif->ctrl_colorfx = v4l2_ctrl_new_std_menu(handler,
+				&s3c_camif_subdev_ctrl_ops,
+				V4L2_CID_COLORFX, V4L2_COLORFX_SET_CBCR,
+				~0x981f, V4L2_COLORFX_NONE);
+
+	camif->ctrl_colorfx_cbcr = v4l2_ctrl_new_std(handler,
+				&s3c_camif_subdev_ctrl_ops,
+				V4L2_CID_COLORFX_CBCR, 0, 0xffff, 1, 0);
+	if (handler->error) {
+		v4l2_ctrl_handler_free(handler);
+		media_entity_cleanup(&sd->entity);
+		return handler->error;
+	}
+
+	v4l2_ctrl_auto_cluster(2, &camif->ctrl_colorfx,
+			       V4L2_COLORFX_SET_CBCR, false);
+	if (!camif->variant->has_img_effect) {
+		camif->ctrl_colorfx->flags |= V4L2_CTRL_FLAG_DISABLED;
+		camif->ctrl_colorfx_cbcr->flags |= V4L2_CTRL_FLAG_DISABLED;
+	}
+	sd->ctrl_handler = handler;
+	v4l2_set_subdevdata(sd, camif);
+
+	return 0;
+}
+
+void s3c_camif_unregister_subdev(struct camif_dev *camif)
+{
+	struct v4l2_subdev *sd = &camif->subdev;
+
+	/* Return if not registered */
+	if (v4l2_get_subdevdata(sd) == NULL)
+		return;
+
+	v4l2_device_unregister_subdev(sd);
+	media_entity_cleanup(&sd->entity);
+	v4l2_ctrl_handler_free(&camif->ctrl_handler);
+	v4l2_set_subdevdata(sd, NULL);
+}
+
+int s3c_camif_set_defaults(struct camif_dev *camif)
+{
+	unsigned int ip_rev = camif->variant->ip_revision;
+	int i;
+
+	for (i = 0; i < CAMIF_VP_NUM; i++) {
+		struct camif_vp *vp = &camif->vp[i];
+		struct camif_frame *f = &vp->out_frame;
+
+		vp->camif = camif;
+		vp->id = i;
+		vp->offset = camif->variant->vp_offset;
+
+		if (ip_rev == S3C244X_CAMIF_IP_REV)
+			vp->fmt_flags = i ? FMT_FL_S3C24XX_PREVIEW :
+					FMT_FL_S3C24XX_CODEC;
+		else
+			vp->fmt_flags = FMT_FL_S3C64XX;
+
+		vp->out_fmt = s3c_camif_find_format(vp, NULL, 0);
+		BUG_ON(vp->out_fmt == NULL);
+
+		memset(f, 0, sizeof(*f));
+		f->f_width = CAMIF_DEF_WIDTH;
+		f->f_height = CAMIF_DEF_HEIGHT;
+		f->rect.width = CAMIF_DEF_WIDTH;
+		f->rect.height = CAMIF_DEF_HEIGHT;
+
+		/* Scaler is always enabled */
+		vp->scaler.enable = 1;
+
+		vp->payload = (f->f_width * f->f_height *
+			       vp->out_fmt->depth) / 8;
+	}
+
+	memset(&camif->mbus_fmt, 0, sizeof(camif->mbus_fmt));
+	camif->mbus_fmt.width = CAMIF_DEF_WIDTH;
+	camif->mbus_fmt.height = CAMIF_DEF_HEIGHT;
+	camif->mbus_fmt.code  = camif_mbus_formats[0];
+
+	memset(&camif->camif_crop, 0, sizeof(camif->camif_crop));
+	camif->camif_crop.width = CAMIF_DEF_WIDTH;
+	camif->camif_crop.height = CAMIF_DEF_HEIGHT;
+
+	return 0;
+}
diff --git a/drivers/media/platform/s3c-camif/camif-core.c b/drivers/media/platform/s3c-camif/camif-core.c
new file mode 100644
index 000000000000..0dd65376c067
--- /dev/null
+++ b/drivers/media/platform/s3c-camif/camif-core.c
@@ -0,0 +1,662 @@
+/*
+ * s3c24xx/s3c64xx SoC series Camera Interface (CAMIF) driver
+ *
+ * Copyright (C) 2012 Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
+ * Copyright (C) 2012 Tomasz Figa <tomasz.figa@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation, either version 2 of the License,
+ * or (at your option) any later version.
+ */
+#define pr_fmt(fmt) "%s:%d " fmt, __func__, __LINE__
+
+#include <linux/bug.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <media/media-device.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-ioctl.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "camif-core.h"
+
+static char *camif_clocks[CLK_MAX_NUM] = {
+	/* HCLK CAMIF clock */
+	[CLK_GATE]	= "camif",
+	/* CAMIF / external camera sensor master clock */
+	[CLK_CAM]	= "camera",
+};
+
+static const struct camif_fmt camif_formats[] = {
+	{
+		.name		= "YUV 4:2:2 planar, Y/Cb/Cr",
+		.fourcc		= V4L2_PIX_FMT_YUV422P,
+		.depth		= 16,
+		.ybpp		= 1,
+		.color		= IMG_FMT_YCBCR422P,
+		.colplanes	= 3,
+		.flags		= FMT_FL_S3C24XX_CODEC |
+				  FMT_FL_S3C64XX,
+	}, {
+		.name		= "YUV 4:2:0 planar, Y/Cb/Cr",
+		.fourcc		= V4L2_PIX_FMT_YUV420,
+		.depth		= 12,
+		.ybpp		= 1,
+		.color		= IMG_FMT_YCBCR420,
+		.colplanes	= 3,
+		.flags		= FMT_FL_S3C24XX_CODEC |
+				  FMT_FL_S3C64XX,
+	}, {
+		.name		= "YVU 4:2:0 planar, Y/Cr/Cb",
+		.fourcc		= V4L2_PIX_FMT_YVU420,
+		.depth		= 12,
+		.ybpp		= 1,
+		.color		= IMG_FMT_YCRCB420,
+		.colplanes	= 3,
+		.flags		= FMT_FL_S3C24XX_CODEC |
+				  FMT_FL_S3C64XX,
+	}, {
+		.name		= "RGB565, 16 bpp",
+		.fourcc		= V4L2_PIX_FMT_RGB565X,
+		.depth		= 16,
+		.ybpp		= 2,
+		.color		= IMG_FMT_RGB565,
+		.colplanes	= 1,
+		.flags		= FMT_FL_S3C24XX_PREVIEW |
+				  FMT_FL_S3C64XX,
+	}, {
+		.name		= "XRGB8888, 32 bpp",
+		.fourcc		= V4L2_PIX_FMT_RGB32,
+		.depth		= 32,
+		.ybpp		= 4,
+		.color		= IMG_FMT_XRGB8888,
+		.colplanes	= 1,
+		.flags		= FMT_FL_S3C24XX_PREVIEW |
+				  FMT_FL_S3C64XX,
+	}, {
+		.name		= "BGR666",
+		.fourcc		= V4L2_PIX_FMT_BGR666,
+		.depth		= 32,
+		.ybpp		= 4,
+		.color		= IMG_FMT_RGB666,
+		.colplanes	= 1,
+		.flags		= FMT_FL_S3C64XX,
+	}
+};
+
+/**
+ * s3c_camif_find_format() - lookup camif color format by fourcc or an index
+ * @pixelformat: fourcc to match, ignored if null
+ * @index: index to the camif_formats array, ignored if negative
+ */
+const struct camif_fmt *s3c_camif_find_format(struct camif_vp *vp,
+					      const u32 *pixelformat,
+					      int index)
+{
+	const struct camif_fmt *fmt, *def_fmt = NULL;
+	unsigned int i;
+	int id = 0;
+
+	if (index >= (int)ARRAY_SIZE(camif_formats))
+		return NULL;
+
+	for (i = 0; i < ARRAY_SIZE(camif_formats); ++i) {
+		fmt = &camif_formats[i];
+		if (vp && !(vp->fmt_flags & fmt->flags))
+			continue;
+		if (pixelformat && fmt->fourcc == *pixelformat)
+			return fmt;
+		if (index == id)
+			def_fmt = fmt;
+		id++;
+	}
+	return def_fmt;
+}
+
+static int camif_get_scaler_factor(u32 src, u32 tar, u32 *ratio, u32 *shift)
+{
+	unsigned int sh = 6;
+
+	if (src >= 64 * tar)
+		return -EINVAL;
+
+	while (sh--) {
+		unsigned int tmp = 1 << sh;
+		if (src >= tar * tmp) {
+			*shift = sh, *ratio = tmp;
+			return 0;
+		}
+	}
+	*shift = 0, *ratio = 1;
+	return 0;
+}
+
+int s3c_camif_get_scaler_config(struct camif_vp *vp,
+				struct camif_scaler *scaler)
+{
+	struct v4l2_rect *camif_crop = &vp->camif->camif_crop;
+	int source_x = camif_crop->width;
+	int source_y = camif_crop->height;
+	int target_x = vp->out_frame.rect.width;
+	int target_y = vp->out_frame.rect.height;
+	int ret;
+
+	if (vp->rotation == 90 || vp->rotation == 270)
+		swap(target_x, target_y);
+
+	ret = camif_get_scaler_factor(source_x, target_x, &scaler->pre_h_ratio,
+				      &scaler->h_shift);
+	if (ret < 0)
+		return ret;
+
+	ret = camif_get_scaler_factor(source_y, target_y, &scaler->pre_v_ratio,
+				      &scaler->v_shift);
+	if (ret < 0)
+		return ret;
+
+	scaler->pre_dst_width = source_x / scaler->pre_h_ratio;
+	scaler->pre_dst_height = source_y / scaler->pre_v_ratio;
+
+	scaler->main_h_ratio = (source_x << 8) / (target_x << scaler->h_shift);
+	scaler->main_v_ratio = (source_y << 8) / (target_y << scaler->v_shift);
+
+	scaler->scaleup_h = (target_x >= source_x);
+	scaler->scaleup_v = (target_y >= source_y);
+
+	scaler->copy = 0;
+
+	pr_debug("H: ratio: %u, shift: %u. V: ratio: %u, shift: %u.\n",
+		 scaler->pre_h_ratio, scaler->h_shift,
+		 scaler->pre_v_ratio, scaler->v_shift);
+
+	pr_debug("Source: %dx%d, Target: %dx%d, scaleup_h/v: %d/%d\n",
+		 source_x, source_y, target_x, target_y,
+		 scaler->scaleup_h, scaler->scaleup_v);
+
+	return 0;
+}
+
+static int camif_register_sensor(struct camif_dev *camif)
+{
+	struct s3c_camif_sensor_info *sensor = &camif->pdata.sensor;
+	struct v4l2_device *v4l2_dev = &camif->v4l2_dev;
+	struct i2c_adapter *adapter;
+	struct v4l2_subdev_format format;
+	struct v4l2_subdev *sd;
+	int ret;
+
+	camif->sensor.sd = NULL;
+
+	if (sensor->i2c_board_info.addr == 0)
+		return -EINVAL;
+
+	adapter = i2c_get_adapter(sensor->i2c_bus_num);
+	if (adapter == NULL) {
+		v4l2_warn(v4l2_dev, "failed to get I2C adapter %d\n",
+			  sensor->i2c_bus_num);
+		return -EPROBE_DEFER;
+	}
+
+	sd = v4l2_i2c_new_subdev_board(v4l2_dev, adapter,
+				       &sensor->i2c_board_info, NULL);
+	if (sd == NULL) {
+		i2c_put_adapter(adapter);
+		v4l2_warn(v4l2_dev, "failed to acquire subdev %s\n",
+			  sensor->i2c_board_info.type);
+		return -EPROBE_DEFER;
+	}
+	camif->sensor.sd = sd;
+
+	v4l2_info(v4l2_dev, "registered sensor subdevice %s\n", sd->name);
+
+	/* Get initial pixel format and set it at the camif sink pad */
+	format.pad = 0;
+	format.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &format);
+
+	if (ret < 0)
+		return 0;
+
+	format.pad = CAMIF_SD_PAD_SINK;
+	v4l2_subdev_call(&camif->subdev, pad, set_fmt, NULL, &format);
+
+	v4l2_info(sd, "Initial format from sensor: %dx%d, %#x\n",
+		  format.format.width, format.format.height,
+		  format.format.code);
+	return 0;
+}
+
+static void camif_unregister_sensor(struct camif_dev *camif)
+{
+	struct v4l2_subdev *sd = camif->sensor.sd;
+	struct i2c_client *client = sd ? v4l2_get_subdevdata(sd) : NULL;
+	struct i2c_adapter *adapter;
+
+	if (client == NULL)
+		return;
+
+	adapter = client->adapter;
+	v4l2_device_unregister_subdev(sd);
+	camif->sensor.sd = NULL;
+	i2c_unregister_device(client);
+	if (adapter)
+		i2c_put_adapter(adapter);
+}
+
+static int camif_create_media_links(struct camif_dev *camif)
+{
+	int i, ret;
+
+	ret = media_entity_create_link(&camif->sensor.sd->entity, 0,
+				&camif->subdev.entity, CAMIF_SD_PAD_SINK,
+				MEDIA_LNK_FL_IMMUTABLE |
+				MEDIA_LNK_FL_ENABLED);
+	if (ret)
+		return ret;
+
+	for (i = 1; i < CAMIF_SD_PADS_NUM && !ret; i++) {
+		ret = media_entity_create_link(&camif->subdev.entity, i,
+				&camif->vp[i - 1].vdev.entity, 0,
+				MEDIA_LNK_FL_IMMUTABLE |
+				MEDIA_LNK_FL_ENABLED);
+	}
+
+	return ret;
+}
+
+static int camif_register_video_nodes(struct camif_dev *camif)
+{
+	int ret = s3c_camif_register_video_node(camif, VP_CODEC);
+	if (ret < 0)
+		return ret;
+
+	return s3c_camif_register_video_node(camif, VP_PREVIEW);
+}
+
+static void camif_unregister_video_nodes(struct camif_dev *camif)
+{
+	s3c_camif_unregister_video_node(camif, VP_CODEC);
+	s3c_camif_unregister_video_node(camif, VP_PREVIEW);
+}
+
+static void camif_unregister_media_entities(struct camif_dev *camif)
+{
+	camif_unregister_video_nodes(camif);
+	camif_unregister_sensor(camif);
+	s3c_camif_unregister_subdev(camif);
+}
+
+/*
+ * Media device
+ */
+static int camif_media_dev_register(struct camif_dev *camif)
+{
+	struct media_device *md = &camif->media_dev;
+	struct v4l2_device *v4l2_dev = &camif->v4l2_dev;
+	unsigned int ip_rev = camif->variant->ip_revision;
+	int ret;
+
+	memset(md, 0, sizeof(*md));
+	snprintf(md->model, sizeof(md->model), "SAMSUNG S3C%s CAMIF",
+		 ip_rev == S3C6410_CAMIF_IP_REV ? "6410" : "244X");
+	strlcpy(md->bus_info, "platform", sizeof(md->bus_info));
+	md->hw_revision = ip_rev;
+	md->driver_version = KERNEL_VERSION(1, 0, 0);
+
+	md->dev = camif->dev;
+
+	strlcpy(v4l2_dev->name, "s3c-camif", sizeof(v4l2_dev->name));
+	v4l2_dev->mdev = md;
+
+	ret = v4l2_device_register(camif->dev, v4l2_dev);
+	if (ret < 0)
+		return ret;
+
+	ret = media_device_register(md);
+	if (ret < 0)
+		v4l2_device_unregister(v4l2_dev);
+
+	return ret;
+}
+
+static void camif_clk_put(struct camif_dev *camif)
+{
+	int i;
+
+	for (i = 0; i < CLK_MAX_NUM; i++) {
+		if (IS_ERR_OR_NULL(camif->clock[i]))
+			continue;
+		clk_unprepare(camif->clock[i]);
+		clk_put(camif->clock[i]);
+	}
+}
+
+static int camif_clk_get(struct camif_dev *camif)
+{
+	int ret, i;
+
+	for (i = 0; i < CLK_MAX_NUM; i++) {
+		camif->clock[i] = clk_get(camif->dev, camif_clocks[i]);
+		if (IS_ERR(camif->clock[i])) {
+			ret = PTR_ERR(camif->clock[i]);
+			goto err;
+		}
+		ret = clk_prepare(camif->clock[i]);
+		if (ret < 0) {
+			clk_put(camif->clock[i]);
+			camif->clock[i] = NULL;
+			goto err;
+		}
+	}
+	return 0;
+err:
+	camif_clk_put(camif);
+	dev_err(camif->dev, "failed to get clock: %s\n",
+		camif_clocks[i]);
+	return ret;
+}
+
+/*
+ * The CAMIF device has two relatively independent data processing paths
+ * that can source data from memory or the common camera input frontend.
+ * Register interrupts for each data processing path (camif_vp).
+ */
+static int camif_request_irqs(struct platform_device *pdev,
+			      struct camif_dev *camif)
+{
+	int irq, ret, i;
+
+	for (i = 0; i < CAMIF_VP_NUM; i++) {
+		struct camif_vp *vp = &camif->vp[i];
+
+		init_waitqueue_head(&vp->irq_queue);
+
+		irq = platform_get_irq(pdev, i);
+		if (irq <= 0) {
+			dev_err(&pdev->dev, "failed to get IRQ %d\n", i);
+			return -ENXIO;
+		}
+
+		ret = devm_request_irq(&pdev->dev, irq, s3c_camif_irq_handler,
+				       0, dev_name(&pdev->dev), vp);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to install IRQ: %d\n", ret);
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static int s3c_camif_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct s3c_camif_plat_data *pdata = dev->platform_data;
+	struct s3c_camif_drvdata *drvdata;
+	struct camif_dev *camif;
+	struct resource *mres;
+	int ret = 0;
+
+	camif = devm_kzalloc(dev, sizeof(*camif), GFP_KERNEL);
+	if (!camif)
+		return -ENOMEM;
+
+	spin_lock_init(&camif->slock);
+	mutex_init(&camif->lock);
+
+	camif->dev = dev;
+
+	if (!pdata || !pdata->gpio_get || !pdata->gpio_put) {
+		dev_err(dev, "wrong platform data\n");
+		return -EINVAL;
+	}
+
+	camif->pdata = *pdata;
+	drvdata = (void *)platform_get_device_id(pdev)->driver_data;
+	camif->variant = drvdata->variant;
+
+	mres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	camif->io_base = devm_request_and_ioremap(dev, mres);
+	if (!camif->io_base) {
+		dev_err(dev, "failed to obtain I/O memory\n");
+		return -ENOENT;
+	}
+
+	ret = camif_request_irqs(pdev, camif);
+	if (ret < 0)
+		return ret;
+
+	ret = pdata->gpio_get();
+	if (ret < 0)
+		return ret;
+
+	ret = s3c_camif_create_subdev(camif);
+	if (ret < 0)
+		goto err_sd;
+
+	ret = camif_clk_get(camif);
+	if (ret < 0)
+		goto err_clk;
+
+	platform_set_drvdata(pdev, camif);
+	clk_set_rate(camif->clock[CLK_CAM],
+			camif->pdata.sensor.clock_frequency);
+
+	dev_info(dev, "sensor clock frequency: %lu\n",
+		 clk_get_rate(camif->clock[CLK_CAM]));
+	/*
+	 * Set initial pixel format, resolution and crop rectangle.
+	 * Must be done before a sensor subdev is registered as some
+	 * settings are overrode with values from sensor subdev.
+	 */
+	s3c_camif_set_defaults(camif);
+
+	pm_runtime_enable(dev);
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
+		goto err_pm;
+
+	/* Initialize contiguous memory allocator */
+	camif->alloc_ctx = vb2_dma_contig_init_ctx(dev);
+	if (IS_ERR(camif->alloc_ctx)) {
+		ret = PTR_ERR(camif->alloc_ctx);
+		goto err_alloc;
+	}
+
+	ret = camif_media_dev_register(camif);
+	if (ret < 0)
+		goto err_mdev;
+
+	ret = camif_register_sensor(camif);
+	if (ret < 0)
+		goto err_sens;
+
+	ret = v4l2_device_register_subdev(&camif->v4l2_dev, &camif->subdev);
+	if (ret < 0)
+		goto err_sens;
+
+	mutex_lock(&camif->media_dev.graph_mutex);
+
+	ret = v4l2_device_register_subdev_nodes(&camif->v4l2_dev);
+	if (ret < 0)
+		goto err_unlock;
+
+	ret = camif_register_video_nodes(camif);
+	if (ret < 0)
+		goto err_unlock;
+
+	ret = camif_create_media_links(camif);
+	if (ret < 0)
+		goto err_unlock;
+
+	mutex_unlock(&camif->media_dev.graph_mutex);
+	pm_runtime_put(dev);
+	return 0;
+
+err_unlock:
+	mutex_unlock(&camif->media_dev.graph_mutex);
+err_sens:
+	v4l2_device_unregister(&camif->v4l2_dev);
+	media_device_unregister(&camif->media_dev);
+	camif_unregister_media_entities(camif);
+err_mdev:
+	vb2_dma_contig_cleanup_ctx(camif->alloc_ctx);
+err_alloc:
+	pm_runtime_put(dev);
+	pm_runtime_disable(dev);
+err_pm:
+	camif_clk_put(camif);
+err_clk:
+	s3c_camif_unregister_subdev(camif);
+err_sd:
+	pdata->gpio_put();
+	return ret;
+}
+
+static int __devexit s3c_camif_remove(struct platform_device *pdev)
+{
+	struct camif_dev *camif = platform_get_drvdata(pdev);
+	struct s3c_camif_plat_data *pdata = &camif->pdata;
+
+	media_device_unregister(&camif->media_dev);
+	camif_unregister_media_entities(camif);
+	v4l2_device_unregister(&camif->v4l2_dev);
+
+	pm_runtime_disable(&pdev->dev);
+	camif_clk_put(camif);
+	pdata->gpio_put();
+
+	return 0;
+}
+
+static int s3c_camif_runtime_resume(struct device *dev)
+{
+	struct camif_dev *camif = dev_get_drvdata(dev);
+
+	clk_enable(camif->clock[CLK_GATE]);
+	/* null op on s3c244x */
+	clk_enable(camif->clock[CLK_CAM]);
+	return 0;
+}
+
+static int s3c_camif_runtime_suspend(struct device *dev)
+{
+	struct camif_dev *camif = dev_get_drvdata(dev);
+
+	/* null op on s3c244x */
+	clk_disable(camif->clock[CLK_CAM]);
+
+	clk_disable(camif->clock[CLK_GATE]);
+	return 0;
+}
+
+static const struct s3c_camif_variant s3c244x_camif_variant = {
+	.vp_pix_limits = {
+		[VP_CODEC] = {
+			.max_out_width		= 4096,
+			.max_sc_out_width	= 2048,
+			.out_width_align	= 16,
+			.min_out_width		= 16,
+			.max_height		= 4096,
+		},
+		[VP_PREVIEW] = {
+			.max_out_width		= 640,
+			.max_sc_out_width	= 640,
+			.out_width_align	= 16,
+			.min_out_width		= 16,
+			.max_height		= 480,
+		}
+	},
+	.pix_limits = {
+		.win_hor_offset_align	= 8,
+	},
+	.ip_revision = S3C244X_CAMIF_IP_REV,
+};
+
+static struct s3c_camif_drvdata s3c244x_camif_drvdata = {
+	.variant	= &s3c244x_camif_variant,
+	.bus_clk_freq	= 24000000UL,
+};
+
+static const struct s3c_camif_variant s3c6410_camif_variant = {
+	.vp_pix_limits = {
+		[VP_CODEC] = {
+			.max_out_width		= 4096,
+			.max_sc_out_width	= 2048,
+			.out_width_align	= 16,
+			.min_out_width		= 16,
+			.max_height		= 4096,
+		},
+		[VP_PREVIEW] = {
+			.max_out_width		= 4096,
+			.max_sc_out_width	= 720,
+			.out_width_align	= 16,
+			.min_out_width		= 16,
+			.max_height		= 4096,
+		}
+	},
+	.pix_limits = {
+		.win_hor_offset_align	= 8,
+	},
+	.ip_revision = S3C6410_CAMIF_IP_REV,
+	.has_img_effect = 1,
+	.vp_offset = 0x20,
+};
+
+static struct s3c_camif_drvdata s3c6410_camif_drvdata = {
+	.variant	= &s3c6410_camif_variant,
+	.bus_clk_freq	= 133000000UL,
+};
+
+static struct platform_device_id s3c_camif_driver_ids[] = {
+	{
+		.name		= "s3c2440-camif",
+		.driver_data	= (unsigned long)&s3c244x_camif_drvdata,
+	}, {
+		.name		= "s3c6410-camif",
+		.driver_data	= (unsigned long)&s3c6410_camif_drvdata,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(platform, s3c_camif_driver_ids);
+
+static const struct dev_pm_ops s3c_camif_pm_ops = {
+	.runtime_suspend	= s3c_camif_runtime_suspend,
+	.runtime_resume		= s3c_camif_runtime_resume,
+};
+
+static struct platform_driver s3c_camif_driver = {
+	.probe		= s3c_camif_probe,
+	.remove		= __devexit_p(s3c_camif_remove),
+	.id_table	= s3c_camif_driver_ids,
+	.driver = {
+		.name	= S3C_CAMIF_DRIVER_NAME,
+		.owner	= THIS_MODULE,
+		.pm	= &s3c_camif_pm_ops,
+	}
+};
+
+module_platform_driver(s3c_camif_driver);
+
+MODULE_AUTHOR("Sylwester Nawrocki <sylvester.nawrocki@gmail.com>");
+MODULE_AUTHOR("Tomasz Figa <tomasz.figa@gmail.com>");
+MODULE_DESCRIPTION("S3C24XX/S3C64XX SoC camera interface driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/platform/s3c-camif/camif-core.h b/drivers/media/platform/s3c-camif/camif-core.h
new file mode 100644
index 000000000000..261134baa655
--- /dev/null
+++ b/drivers/media/platform/s3c-camif/camif-core.h
@@ -0,0 +1,393 @@
+/*
+ * s3c24xx/s3c64xx SoC series Camera Interface (CAMIF) driver
+ *
+ * Copyright (C) 2012 Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
+ * Copyright (C) 2012 Tomasz Figa <tomasz.figa@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef CAMIF_CORE_H_
+#define CAMIF_CORE_H_
+
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/videodev2.h>
+
+#include <media/media-entity.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-dev.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-mediabus.h>
+#include <media/videobuf2-core.h>
+#include <media/s3c_camif.h>
+
+#define S3C_CAMIF_DRIVER_NAME	"s3c-camif"
+#define CAMIF_REQ_BUFS_MIN	3
+#define CAMIF_MAX_OUT_BUFS	4
+#define CAMIF_MAX_PIX_WIDTH	4096
+#define CAMIF_MAX_PIX_HEIGHT	4096
+#define SCALER_MAX_RATIO	64
+#define CAMIF_DEF_WIDTH		640
+#define CAMIF_DEF_HEIGHT	480
+#define CAMIF_STOP_TIMEOUT	1500 /* ms */
+
+#define S3C244X_CAMIF_IP_REV	0x20 /* 2.0 */
+#define S3C2450_CAMIF_IP_REV	0x30 /* 3.0 - not implemented, not tested */
+#define S3C6400_CAMIF_IP_REV	0x31 /* 3.1 - not implemented, not tested */
+#define S3C6410_CAMIF_IP_REV	0x32 /* 3.2 */
+
+/* struct camif_vp::state */
+
+#define ST_VP_PENDING		(1 << 0)
+#define ST_VP_RUNNING		(1 << 1)
+#define ST_VP_STREAMING		(1 << 2)
+#define ST_VP_SENSOR_STREAMING	(1 << 3)
+
+#define ST_VP_ABORTING		(1 << 4)
+#define ST_VP_OFF		(1 << 5)
+#define ST_VP_LASTIRQ		(1 << 6)
+
+#define ST_VP_CONFIG		(1 << 8)
+
+#define CAMIF_SD_PAD_SINK	0
+#define CAMIF_SD_PAD_SOURCE_C	1
+#define CAMIF_SD_PAD_SOURCE_P	2
+#define CAMIF_SD_PADS_NUM	3
+
+enum img_fmt {
+	IMG_FMT_RGB565 = 0x0010,
+	IMG_FMT_RGB666,
+	IMG_FMT_XRGB8888,
+	IMG_FMT_YCBCR420 = 0x0020,
+	IMG_FMT_YCRCB420,
+	IMG_FMT_YCBCR422P,
+	IMG_FMT_YCBYCR422 = 0x0040,
+	IMG_FMT_YCRYCB422,
+	IMG_FMT_CBYCRY422,
+	IMG_FMT_CRYCBY422,
+};
+
+#define img_fmt_is_rgb(x) ((x) & 0x10)
+#define img_fmt_is_ycbcr(x) ((x) & 0x60)
+
+/* Possible values for struct camif_fmt::flags */
+#define FMT_FL_S3C24XX_CODEC	(1 << 0)
+#define FMT_FL_S3C24XX_PREVIEW	(1 << 1)
+#define FMT_FL_S3C64XX		(1 << 2)
+
+/**
+ * struct camif_fmt - pixel format description
+ * @fourcc:    fourcc code for this format, 0 if not applicable
+ * @color:     a corresponding enum img_fmt
+ * @colplanes: number of physically contiguous data planes
+ * @flags:     indicate for which SoCs revisions this format is valid
+ * @depth:     bits per pixel (total)
+ * @ybpp:      number of luminance bytes per pixel
+ */
+struct camif_fmt {
+	char *name;
+	u32 fourcc;
+	u32 color;
+	u16 colplanes;
+	u16 flags;
+	u8 depth;
+	u8 ybpp;
+};
+
+/**
+ * struct camif_dma_offset - pixel offset information for DMA
+ * @initial: offset (in pixels) to first pixel
+ * @line: offset (in pixels) from end of line to start of next line
+ */
+struct camif_dma_offset {
+	int	initial;
+	int	line;
+};
+
+/**
+ * struct camif_frame - source/target frame properties
+ * @f_width: full pixel width
+ * @f_height: full pixel height
+ * @rect: crop/composition rectangle
+ * @dma_offset: DMA offset configuration
+ */
+struct camif_frame {
+	u16 f_width;
+	u16 f_height;
+	struct v4l2_rect rect;
+	struct camif_dma_offset dma_offset;
+};
+
+/* CAMIF clocks enumeration */
+enum {
+	CLK_GATE,
+	CLK_CAM,
+	CLK_MAX_NUM,
+};
+
+struct vp_pix_limits {
+	u16 max_out_width;
+	u16 max_sc_out_width;
+	u16 out_width_align;
+	u16 max_height;
+	u8 min_out_width;
+	u16 out_hor_offset_align;
+};
+
+struct camif_pix_limits {
+	u16 win_hor_offset_align;
+};
+
+/**
+ * struct s3c_camif_variant - CAMIF variant structure
+ * @vp_pix_limits:    pixel limits for the codec and preview paths
+ * @camif_pix_limits: pixel limits for the camera input interface
+ * @ip_revision:      the CAMIF IP revision: 0x20 for s3c244x, 0x32 for s3c6410
+ */
+struct s3c_camif_variant {
+	struct vp_pix_limits vp_pix_limits[2];
+	struct camif_pix_limits pix_limits;
+	u8 ip_revision;
+	u8 has_img_effect;
+	unsigned int vp_offset;
+};
+
+struct s3c_camif_drvdata {
+	const struct s3c_camif_variant *variant;
+	unsigned long bus_clk_freq;
+};
+
+struct camif_scaler {
+	u8 scaleup_h;
+	u8 scaleup_v;
+	u8 copy;
+	u8 enable;
+	u32 h_shift;
+	u32 v_shift;
+	u32 pre_h_ratio;
+	u32 pre_v_ratio;
+	u32 pre_dst_width;
+	u32 pre_dst_height;
+	u32 main_h_ratio;
+	u32 main_v_ratio;
+};
+
+struct camif_dev;
+
+/**
+ * struct camif_vp - CAMIF data processing path structure (codec/preview)
+ * @irq_queue:	    interrupt handling waitqueue
+ * @irq:	    interrupt number for this data path
+ * @camif:	    pointer to the camif structure
+ * @pad:	    media pad for the video node
+ * @vdev            video device
+ * @ctrl_handler:   video node controls handler
+ * @owner:	    file handle that own the streaming
+ * @pending_buf_q:  pending (empty) buffers queue head
+ * @active_buf_q:   active (being written) buffers queue head
+ * @active_buffers: counter of buffer set up at the DMA engine
+ * @buf_index:	    identifier of a last empty buffer set up in H/W
+ * @frame_sequence: image frame sequence counter
+ * @reqbufs_count:  the number of buffers requested
+ * @scaler:	    the scaler structure
+ * @out_fmt:	    pixel format at this video path output
+ * @payload:	    the output data frame payload size
+ * @out_frame:	    the output pixel resolution
+ * @state:	    the video path's state
+ * @fmt_flags:	    flags determining supported pixel formats
+ * @id:		    CAMIF id, 0 - codec, 1 - preview
+ * @rotation:	    current image rotation value
+ * @hflip:	    apply horizontal flip if set
+ * @vflip:	    apply vertical flip if set
+ */
+struct camif_vp {
+	wait_queue_head_t	irq_queue;
+	int			irq;
+	struct camif_dev	*camif;
+	struct media_pad	pad;
+	struct video_device	vdev;
+	struct v4l2_ctrl_handler ctrl_handler;
+	struct v4l2_fh		*owner;
+	struct vb2_queue	vb_queue;
+	struct list_head	pending_buf_q;
+	struct list_head	active_buf_q;
+	unsigned int		active_buffers;
+	unsigned int		buf_index;
+	unsigned int		frame_sequence;
+	unsigned int		reqbufs_count;
+	struct camif_scaler	scaler;
+	const struct camif_fmt	*out_fmt;
+	unsigned int		payload;
+	struct camif_frame	out_frame;
+	unsigned int		state;
+	u16			fmt_flags;
+	u8			id;
+	u8			rotation;
+	u8			hflip;
+	u8			vflip;
+	unsigned int		offset;
+};
+
+/* Video processing path enumeration */
+#define VP_CODEC	0
+#define VP_PREVIEW	1
+#define CAMIF_VP_NUM	2
+
+/**
+ * struct camif_dev - the CAMIF driver private data structure
+ * @media_dev:    top-level media device structure
+ * @v4l2_dev:	  root v4l2_device
+ * @subdev:       camera interface ("catchcam") subdev
+ * @mbus_fmt:	  camera input media bus format
+ * @camif_crop:   camera input interface crop rectangle
+ * @pads:	  the camif subdev's media pads
+ * @stream_count: the camera interface streaming reference counter
+ * @sensor:       image sensor data structure
+ * @m_pipeline:	  video entity pipeline description
+ * @ctrl_handler: v4l2 control handler (owned by @subdev)
+ * @test_pattern: test pattern controls
+ * @vp:           video path (DMA) description (codec/preview)
+ * @alloc_ctx:    memory buffer allocator context
+ * @variant:      variant information for this device
+ * @dev:	  pointer to the CAMIF device struct
+ * @pdata:	  a copy of the driver's platform data
+ * @clock:	  clocks required for the CAMIF operation
+ * @lock:	  mutex protecting this data structure
+ * @slock:	  spinlock protecting CAMIF registers
+ * @io_base:	  start address of the mmaped CAMIF registers
+ */
+struct camif_dev {
+	struct media_device		media_dev;
+	struct v4l2_device		v4l2_dev;
+	struct v4l2_subdev		subdev;
+	struct v4l2_mbus_framefmt	mbus_fmt;
+	struct v4l2_rect		camif_crop;
+	struct media_pad		pads[CAMIF_SD_PADS_NUM];
+	int				stream_count;
+
+	struct cam_sensor {
+		struct v4l2_subdev	*sd;
+		short			power_count;
+		short			stream_count;
+	} sensor;
+	struct media_pipeline		*m_pipeline;
+
+	struct v4l2_ctrl_handler	ctrl_handler;
+	struct v4l2_ctrl		*ctrl_test_pattern;
+	struct {
+		struct v4l2_ctrl	*ctrl_colorfx;
+		struct v4l2_ctrl	*ctrl_colorfx_cbcr;
+	};
+	u8				test_pattern;
+	u8				colorfx;
+	u8				colorfx_cb;
+	u8				colorfx_cr;
+
+	struct camif_vp			vp[CAMIF_VP_NUM];
+	struct vb2_alloc_ctx		*alloc_ctx;
+
+	const struct s3c_camif_variant	*variant;
+	struct device			*dev;
+	struct s3c_camif_plat_data	pdata;
+	struct clk			*clock[CLK_MAX_NUM];
+	struct mutex			lock;
+	spinlock_t			slock;
+	void __iomem			*io_base;
+};
+
+/**
+ * struct camif_addr - Y/Cb/Cr DMA start address structure
+ * @y:	 luminance plane dma address
+ * @cb:	 Cb plane dma address
+ * @cr:	 Cr plane dma address
+ */
+struct camif_addr {
+	dma_addr_t y;
+	dma_addr_t cb;
+	dma_addr_t cr;
+};
+
+/**
+ * struct camif_buffer - the camif video buffer structure
+ * @vb:    vb2 buffer
+ * @list:  list head for the buffers queue
+ * @paddr: DMA start addresses
+ * @index: an identifier of this buffer at the DMA engine
+ */
+struct camif_buffer {
+	struct vb2_buffer vb;
+	struct list_head list;
+	struct camif_addr paddr;
+	unsigned int index;
+};
+
+const struct camif_fmt *s3c_camif_find_format(struct camif_vp *vp,
+	      const u32 *pixelformat, int index);
+int s3c_camif_register_video_node(struct camif_dev *camif, int idx);
+void s3c_camif_unregister_video_node(struct camif_dev *camif, int idx);
+irqreturn_t s3c_camif_irq_handler(int irq, void *priv);
+int s3c_camif_create_subdev(struct camif_dev *camif);
+void s3c_camif_unregister_subdev(struct camif_dev *camif);
+int s3c_camif_set_defaults(struct camif_dev *camif);
+int s3c_camif_get_scaler_config(struct camif_vp *vp,
+				struct camif_scaler *scaler);
+
+static inline void camif_active_queue_add(struct camif_vp *vp,
+					  struct camif_buffer *buf)
+{
+	list_add_tail(&buf->list, &vp->active_buf_q);
+	vp->active_buffers++;
+}
+
+static inline struct camif_buffer *camif_active_queue_pop(
+					struct camif_vp *vp)
+{
+	struct camif_buffer *buf = list_first_entry(&vp->active_buf_q,
+					      struct camif_buffer, list);
+	list_del(&buf->list);
+	vp->active_buffers--;
+	return buf;
+}
+
+static inline struct camif_buffer *camif_active_queue_peek(
+			   struct camif_vp *vp, int index)
+{
+	struct camif_buffer *tmp, *buf;
+
+	if (WARN_ON(list_empty(&vp->active_buf_q)))
+		return NULL;
+
+	list_for_each_entry_safe(buf, tmp, &vp->active_buf_q, list) {
+		if (buf->index == index) {
+			list_del(&buf->list);
+			vp->active_buffers--;
+			return buf;
+		}
+	}
+
+	return NULL;
+}
+
+static inline void camif_pending_queue_add(struct camif_vp *vp,
+					   struct camif_buffer *buf)
+{
+	list_add_tail(&buf->list, &vp->pending_buf_q);
+}
+
+static inline struct camif_buffer *camif_pending_queue_pop(
+					struct camif_vp *vp)
+{
+	struct camif_buffer *buf = list_first_entry(&vp->pending_buf_q,
+					      struct camif_buffer, list);
+	list_del(&buf->list);
+	return buf;
+}
+
+#endif /* CAMIF_CORE_H_ */
diff --git a/drivers/media/platform/s3c-camif/camif-regs.c b/drivers/media/platform/s3c-camif/camif-regs.c
new file mode 100644
index 000000000000..1a3b4fc05ec6
--- /dev/null
+++ b/drivers/media/platform/s3c-camif/camif-regs.c
@@ -0,0 +1,606 @@
+/*
+ * Samsung s3c24xx/s3c64xx SoC CAMIF driver
+ *
+ * Copyright (C) 2012 Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
+ * Copyright (C) 2012 Tomasz Figa <tomasz.figa@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+#define pr_fmt(fmt) "%s:%d " fmt, __func__, __LINE__
+
+#include <linux/delay.h>
+#include "camif-regs.h"
+
+#define camif_write(_camif, _off, _val)	writel(_val, (_camif)->io_base + (_off))
+#define camif_read(_camif, _off)	readl((_camif)->io_base + (_off))
+
+void camif_hw_reset(struct camif_dev *camif)
+{
+	u32 cfg;
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CISRCFMT);
+	cfg |= CISRCFMT_ITU601_8BIT;
+	camif_write(camif, S3C_CAMIF_REG_CISRCFMT, cfg);
+
+	/* S/W reset */
+	cfg = camif_read(camif, S3C_CAMIF_REG_CIGCTRL);
+	cfg |= CIGCTRL_SWRST;
+	if (camif->variant->ip_revision == S3C6410_CAMIF_IP_REV)
+		cfg |= CIGCTRL_IRQ_LEVEL;
+	camif_write(camif, S3C_CAMIF_REG_CIGCTRL, cfg);
+	udelay(10);
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CIGCTRL);
+	cfg &= ~CIGCTRL_SWRST;
+	camif_write(camif, S3C_CAMIF_REG_CIGCTRL, cfg);
+	udelay(10);
+}
+
+void camif_hw_clear_pending_irq(struct camif_vp *vp)
+{
+	u32 cfg = camif_read(vp->camif, S3C_CAMIF_REG_CIGCTRL);
+	cfg |= CIGCTRL_IRQ_CLR(vp->id);
+	camif_write(vp->camif, S3C_CAMIF_REG_CIGCTRL, cfg);
+}
+
+/*
+ * Sets video test pattern (off, color bar, horizontal or vertical gradient).
+ * External sensor pixel clock must be active for the test pattern to work.
+ */
+void camif_hw_set_test_pattern(struct camif_dev *camif, unsigned int pattern)
+{
+	u32 cfg = camif_read(camif, S3C_CAMIF_REG_CIGCTRL);
+	cfg &= ~CIGCTRL_TESTPATTERN_MASK;
+	cfg |= (pattern << 27);
+	camif_write(camif, S3C_CAMIF_REG_CIGCTRL, cfg);
+}
+
+void camif_hw_set_effect(struct camif_dev *camif, unsigned int effect,
+			unsigned int cr, unsigned int cb)
+{
+	static const struct v4l2_control colorfx[] = {
+		{ V4L2_COLORFX_NONE,		CIIMGEFF_FIN_BYPASS },
+		{ V4L2_COLORFX_BW,		CIIMGEFF_FIN_ARBITRARY },
+		{ V4L2_COLORFX_SEPIA,		CIIMGEFF_FIN_ARBITRARY },
+		{ V4L2_COLORFX_NEGATIVE,	CIIMGEFF_FIN_NEGATIVE },
+		{ V4L2_COLORFX_ART_FREEZE,	CIIMGEFF_FIN_ARTFREEZE },
+		{ V4L2_COLORFX_EMBOSS,		CIIMGEFF_FIN_EMBOSSING },
+		{ V4L2_COLORFX_SILHOUETTE,	CIIMGEFF_FIN_SILHOUETTE },
+		{ V4L2_COLORFX_SET_CBCR,	CIIMGEFF_FIN_ARBITRARY },
+	};
+	unsigned int i, cfg;
+
+	for (i = 0; i < ARRAY_SIZE(colorfx); i++)
+		if (colorfx[i].id == effect)
+			break;
+
+	if (i == ARRAY_SIZE(colorfx))
+		return;
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CIIMGEFF(camif->vp->offset));
+	/* Set effect */
+	cfg &= ~CIIMGEFF_FIN_MASK;
+	cfg |= colorfx[i].value;
+	/* Set both paths */
+	if (camif->variant->ip_revision >= S3C6400_CAMIF_IP_REV) {
+		if (effect == V4L2_COLORFX_NONE)
+			cfg &= ~CIIMGEFF_IE_ENABLE_MASK;
+		else
+			cfg |= CIIMGEFF_IE_ENABLE_MASK;
+	}
+	cfg &= ~CIIMGEFF_PAT_CBCR_MASK;
+	cfg |= cr | (cb << 13);
+	camif_write(camif, S3C_CAMIF_REG_CIIMGEFF(camif->vp->offset), cfg);
+}
+
+static const u32 src_pixfmt_map[8][2] = {
+	{ V4L2_MBUS_FMT_YUYV8_2X8, CISRCFMT_ORDER422_YCBYCR },
+	{ V4L2_MBUS_FMT_YVYU8_2X8, CISRCFMT_ORDER422_YCRYCB },
+	{ V4L2_MBUS_FMT_UYVY8_2X8, CISRCFMT_ORDER422_CBYCRY },
+	{ V4L2_MBUS_FMT_VYUY8_2X8, CISRCFMT_ORDER422_CRYCBY },
+};
+
+/* Set camera input pixel format and resolution */
+void camif_hw_set_source_format(struct camif_dev *camif)
+{
+	struct v4l2_mbus_framefmt *mf = &camif->mbus_fmt;
+	unsigned int i = ARRAY_SIZE(src_pixfmt_map);
+	u32 cfg;
+
+	while (i-- >= 0) {
+		if (src_pixfmt_map[i][0] == mf->code)
+			break;
+	}
+
+	if (i == 0 && src_pixfmt_map[i][0] != mf->code) {
+		dev_err(camif->dev,
+			"Unsupported pixel code, falling back to %#08x\n",
+			src_pixfmt_map[i][0]);
+	}
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CISRCFMT);
+	cfg &= ~(CISRCFMT_ORDER422_MASK | CISRCFMT_SIZE_CAM_MASK);
+	cfg |= (mf->width << 16) | mf->height;
+	cfg |= src_pixfmt_map[i][1];
+	camif_write(camif, S3C_CAMIF_REG_CISRCFMT, cfg);
+}
+
+/* Set the camera host input window offsets (cropping) */
+void camif_hw_set_camera_crop(struct camif_dev *camif)
+{
+	struct v4l2_mbus_framefmt *mf = &camif->mbus_fmt;
+	struct v4l2_rect *crop = &camif->camif_crop;
+	u32 hoff2, voff2;
+	u32 cfg;
+
+	/* Note: s3c244x requirement: left = f_width - rect.width / 2 */
+	cfg = camif_read(camif, S3C_CAMIF_REG_CIWDOFST);
+	cfg &= ~(CIWDOFST_OFST_MASK | CIWDOFST_WINOFSEN);
+	cfg |= (crop->left << 16) | crop->top;
+	if (crop->left != 0 || crop->top != 0)
+		cfg |= CIWDOFST_WINOFSEN;
+	camif_write(camif, S3C_CAMIF_REG_CIWDOFST, cfg);
+
+	if (camif->variant->ip_revision == S3C6410_CAMIF_IP_REV) {
+		hoff2 = mf->width - crop->width - crop->left;
+		voff2 = mf->height - crop->height - crop->top;
+		cfg = (hoff2 << 16) | voff2;
+		camif_write(camif, S3C_CAMIF_REG_CIWDOFST2, cfg);
+	}
+}
+
+void camif_hw_clear_fifo_overflow(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	u32 cfg;
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CIWDOFST);
+	if (vp->id == 0)
+		cfg |= (CIWDOFST_CLROVCOFIY | CIWDOFST_CLROVCOFICB |
+			CIWDOFST_CLROVCOFICR);
+	else
+		cfg |= (/* CIWDOFST_CLROVPRFIY | */ CIWDOFST_CLROVPRFICB |
+			CIWDOFST_CLROVPRFICR);
+	camif_write(camif, S3C_CAMIF_REG_CIWDOFST, cfg);
+}
+
+/* Set video bus signals polarity */
+void camif_hw_set_camera_bus(struct camif_dev *camif)
+{
+	unsigned int flags = camif->pdata.sensor.flags;
+
+	u32 cfg = camif_read(camif, S3C_CAMIF_REG_CIGCTRL);
+
+	cfg &= ~(CIGCTRL_INVPOLPCLK | CIGCTRL_INVPOLVSYNC |
+		 CIGCTRL_INVPOLHREF | CIGCTRL_INVPOLFIELD);
+
+	if (flags & V4L2_MBUS_PCLK_SAMPLE_FALLING)
+		cfg |= CIGCTRL_INVPOLPCLK;
+
+	if (flags & V4L2_MBUS_VSYNC_ACTIVE_LOW)
+		cfg |= CIGCTRL_INVPOLVSYNC;
+	/*
+	 * HREF is normally high during frame active data
+	 * transmission and low during horizontal synchronization
+	 * period. Thus HREF active high means HSYNC active low.
+	 */
+	if (flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH)
+		cfg |= CIGCTRL_INVPOLHREF; /* HREF active low */
+
+	if (camif->variant->ip_revision == S3C6410_CAMIF_IP_REV) {
+		if (flags & V4L2_MBUS_FIELD_EVEN_LOW)
+			cfg |= CIGCTRL_INVPOLFIELD;
+		cfg |= CIGCTRL_FIELDMODE;
+	}
+
+	pr_debug("Setting CIGCTRL to: %#x\n", cfg);
+
+	camif_write(camif, S3C_CAMIF_REG_CIGCTRL, cfg);
+}
+
+void camif_hw_set_output_addr(struct camif_vp *vp,
+			      struct camif_addr *paddr, int i)
+{
+	struct camif_dev *camif = vp->camif;
+
+	camif_write(camif, S3C_CAMIF_REG_CIYSA(vp->id, i), paddr->y);
+	if (camif->variant->ip_revision == S3C6410_CAMIF_IP_REV
+		|| vp->id == VP_CODEC) {
+		camif_write(camif, S3C_CAMIF_REG_CICBSA(vp->id, i),
+								paddr->cb);
+		camif_write(camif, S3C_CAMIF_REG_CICRSA(vp->id, i),
+								paddr->cr);
+	}
+
+	pr_debug("dst_buf[%d]: %#X, cb: %#X, cr: %#X\n",
+		 i, paddr->y, paddr->cb, paddr->cr);
+}
+
+static void camif_hw_set_out_dma_size(struct camif_vp *vp)
+{
+	struct camif_frame *frame = &vp->out_frame;
+	u32 cfg;
+
+	cfg = camif_read(vp->camif, S3C_CAMIF_REG_CITRGFMT(vp->id, vp->offset));
+	cfg &= ~CITRGFMT_TARGETSIZE_MASK;
+	cfg |= (frame->f_width << 16) | frame->f_height;
+	camif_write(vp->camif, S3C_CAMIF_REG_CITRGFMT(vp->id, vp->offset), cfg);
+}
+
+static void camif_get_dma_burst(u32 width, u32 ybpp, u32 *mburst, u32 *rburst)
+{
+	unsigned int nwords = width * ybpp / 4;
+	unsigned int div, rem;
+
+	if (WARN_ON(width < 8 || (width * ybpp) & 7))
+		return;
+
+	for (div = 16; div >= 2; div /= 2) {
+		if (nwords < div)
+			continue;
+
+		rem = nwords & (div - 1);
+		if (rem == 0) {
+			*mburst = div;
+			*rburst = div;
+			break;
+		}
+		if (rem == div / 2 || rem == div / 4) {
+			*mburst = div;
+			*rburst = rem;
+			break;
+		}
+	}
+}
+
+void camif_hw_set_output_dma(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	struct camif_frame *frame = &vp->out_frame;
+	const struct camif_fmt *fmt = vp->out_fmt;
+	unsigned int ymburst = 0, yrburst = 0;
+	u32 cfg;
+
+	camif_hw_set_out_dma_size(vp);
+
+	if (camif->variant->ip_revision == S3C6410_CAMIF_IP_REV) {
+		struct camif_dma_offset *offset = &frame->dma_offset;
+		/* Set the input dma offsets. */
+		cfg = S3C_CISS_OFFS_INITIAL(offset->initial);
+		cfg |= S3C_CISS_OFFS_LINE(offset->line);
+		camif_write(camif, S3C_CAMIF_REG_CISSY(vp->id), cfg);
+		camif_write(camif, S3C_CAMIF_REG_CISSCB(vp->id), cfg);
+		camif_write(camif, S3C_CAMIF_REG_CISSCR(vp->id), cfg);
+	}
+
+	/* Configure DMA burst values */
+	camif_get_dma_burst(frame->rect.width, fmt->ybpp, &ymburst, &yrburst);
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CICTRL(vp->id, vp->offset));
+	cfg &= ~CICTRL_BURST_MASK;
+
+	cfg |= CICTRL_YBURST1(ymburst) | CICTRL_YBURST2(yrburst);
+	cfg |= CICTRL_CBURST1(ymburst / 2) | CICTRL_CBURST2(yrburst / 2);
+
+	camif_write(camif, S3C_CAMIF_REG_CICTRL(vp->id, vp->offset), cfg);
+
+	pr_debug("ymburst: %u, yrburst: %u\n", ymburst, yrburst);
+}
+
+void camif_hw_set_input_path(struct camif_vp *vp)
+{
+	u32 cfg = camif_read(vp->camif, S3C_CAMIF_REG_MSCTRL(vp->id));
+	cfg &= ~MSCTRL_SEL_DMA_CAM;
+	camif_write(vp->camif, S3C_CAMIF_REG_MSCTRL(vp->id), cfg);
+}
+
+void camif_hw_set_target_format(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	struct camif_frame *frame = &vp->out_frame;
+	u32 cfg;
+
+	pr_debug("fw: %d, fh: %d color: %d\n", frame->f_width,
+		 frame->f_height, vp->out_fmt->color);
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CITRGFMT(vp->id, vp->offset));
+	cfg &= ~CITRGFMT_TARGETSIZE_MASK;
+
+	if (camif->variant->ip_revision == S3C244X_CAMIF_IP_REV) {
+		/* We currently support only YCbCr 4:2:2 at the camera input */
+		cfg |= CITRGFMT_IN422;
+		cfg &= ~CITRGFMT_OUT422;
+		if (vp->out_fmt->color == IMG_FMT_YCBCR422P)
+			cfg |= CITRGFMT_OUT422;
+	} else {
+		cfg &= ~CITRGFMT_OUTFORMAT_MASK;
+		switch (vp->out_fmt->color) {
+		case IMG_FMT_RGB565...IMG_FMT_XRGB8888:
+			cfg |= CITRGFMT_OUTFORMAT_RGB;
+			break;
+		case IMG_FMT_YCBCR420...IMG_FMT_YCRCB420:
+			cfg |= CITRGFMT_OUTFORMAT_YCBCR420;
+			break;
+		case IMG_FMT_YCBCR422P:
+			cfg |= CITRGFMT_OUTFORMAT_YCBCR422;
+			break;
+		case IMG_FMT_YCBYCR422...IMG_FMT_CRYCBY422:
+			cfg |= CITRGFMT_OUTFORMAT_YCBCR422I;
+			break;
+		}
+	}
+
+	/* Rotation is only supported by s3c64xx */
+	if (vp->rotation == 90 || vp->rotation == 270)
+		cfg |= (frame->f_height << 16) | frame->f_width;
+	else
+		cfg |= (frame->f_width << 16) | frame->f_height;
+	camif_write(camif, S3C_CAMIF_REG_CITRGFMT(vp->id, vp->offset), cfg);
+
+	/* Target area, output pixel width * height */
+	cfg = camif_read(camif, S3C_CAMIF_REG_CITAREA(vp->id, vp->offset));
+	cfg &= ~CITAREA_MASK;
+	cfg |= (frame->f_width * frame->f_height);
+	camif_write(camif, S3C_CAMIF_REG_CITAREA(vp->id, vp->offset), cfg);
+}
+
+void camif_hw_set_flip(struct camif_vp *vp)
+{
+	u32 cfg = camif_read(vp->camif,
+				S3C_CAMIF_REG_CITRGFMT(vp->id, vp->offset));
+
+	cfg &= ~CITRGFMT_FLIP_MASK;
+
+	if (vp->hflip)
+		cfg |= CITRGFMT_FLIP_Y_MIRROR;
+	if (vp->vflip)
+		cfg |= CITRGFMT_FLIP_X_MIRROR;
+
+	camif_write(vp->camif, S3C_CAMIF_REG_CITRGFMT(vp->id, vp->offset), cfg);
+}
+
+static void camif_hw_set_prescaler(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	struct camif_scaler *sc = &vp->scaler;
+	u32 cfg, shfactor, addr;
+
+	addr = S3C_CAMIF_REG_CISCPRERATIO(vp->id, vp->offset);
+
+	shfactor = 10 - (sc->h_shift + sc->v_shift);
+	cfg = shfactor << 28;
+
+	cfg |= (sc->pre_h_ratio << 16) | sc->pre_v_ratio;
+	camif_write(camif, addr, cfg);
+
+	cfg = (sc->pre_dst_width << 16) | sc->pre_dst_height;
+	camif_write(camif, S3C_CAMIF_REG_CISCPREDST(vp->id, vp->offset), cfg);
+}
+
+void camif_s3c244x_hw_set_scaler(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	struct camif_scaler *scaler = &vp->scaler;
+	unsigned int color = vp->out_fmt->color;
+	u32 cfg;
+
+	camif_hw_set_prescaler(vp);
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CISCCTRL(vp->id, vp->offset));
+
+	cfg &= ~(CISCCTRL_SCALEUP_MASK | CISCCTRL_SCALERBYPASS |
+		 CISCCTRL_MAIN_RATIO_MASK | CIPRSCCTRL_RGB_FORMAT_24BIT);
+
+	if (scaler->enable) {
+		if (scaler->scaleup_h) {
+			if (vp->id == VP_CODEC)
+				cfg |= CISCCTRL_SCALEUP_H;
+			else
+				cfg |= CIPRSCCTRL_SCALEUP_H;
+		}
+		if (scaler->scaleup_v) {
+			if (vp->id == VP_CODEC)
+				cfg |= CISCCTRL_SCALEUP_V;
+			else
+				cfg |= CIPRSCCTRL_SCALEUP_V;
+		}
+	} else {
+		if (vp->id == VP_CODEC)
+			cfg |= CISCCTRL_SCALERBYPASS;
+	}
+
+	cfg |= ((scaler->main_h_ratio & 0x1ff) << 16);
+	cfg |= scaler->main_v_ratio & 0x1ff;
+
+	if (vp->id == VP_PREVIEW) {
+		if (color == IMG_FMT_XRGB8888)
+			cfg |= CIPRSCCTRL_RGB_FORMAT_24BIT;
+		cfg |= CIPRSCCTRL_SAMPLE;
+	}
+
+	camif_write(camif, S3C_CAMIF_REG_CISCCTRL(vp->id, vp->offset), cfg);
+
+	pr_debug("main: h_ratio: %#x, v_ratio: %#x",
+		 scaler->main_h_ratio, scaler->main_v_ratio);
+}
+
+void camif_s3c64xx_hw_set_scaler(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	struct camif_scaler *scaler = &vp->scaler;
+	unsigned int color = vp->out_fmt->color;
+	u32 cfg;
+
+	camif_hw_set_prescaler(vp);
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CISCCTRL(vp->id, vp->offset));
+
+	cfg &= ~(CISCCTRL_CSCR2Y_WIDE | CISCCTRL_CSCY2R_WIDE
+		| CISCCTRL_SCALEUP_H | CISCCTRL_SCALEUP_V
+		| CISCCTRL_SCALERBYPASS | CISCCTRL_ONE2ONE
+		| CISCCTRL_INRGB_FMT_MASK | CISCCTRL_OUTRGB_FMT_MASK
+		| CISCCTRL_INTERLACE | CISCCTRL_EXTRGB_EXTENSION
+		| CISCCTRL_MAIN_RATIO_MASK);
+
+	cfg |= (CISCCTRL_CSCR2Y_WIDE | CISCCTRL_CSCY2R_WIDE);
+
+	if (!scaler->enable) {
+		cfg |= CISCCTRL_SCALERBYPASS;
+	} else {
+		if (scaler->scaleup_h)
+			cfg |= CISCCTRL_SCALEUP_H;
+		if (scaler->scaleup_v)
+			cfg |= CISCCTRL_SCALEUP_V;
+		if (scaler->copy)
+			cfg |= CISCCTRL_ONE2ONE;
+	}
+
+	switch (color) {
+	case IMG_FMT_RGB666:
+		cfg |= CISCCTRL_OUTRGB_FMT_RGB666;
+		break;
+	case IMG_FMT_XRGB8888:
+		cfg |= CISCCTRL_OUTRGB_FMT_RGB888;
+		break;
+	}
+
+	cfg |= (scaler->main_h_ratio & 0x1ff) << 16;
+	cfg |= scaler->main_v_ratio & 0x1ff;
+
+	camif_write(camif, S3C_CAMIF_REG_CISCCTRL(vp->id, vp->offset), cfg);
+
+	pr_debug("main: h_ratio: %#x, v_ratio: %#x",
+		 scaler->main_h_ratio, scaler->main_v_ratio);
+}
+
+void camif_hw_set_scaler(struct camif_vp *vp)
+{
+	unsigned int ip_rev = vp->camif->variant->ip_revision;
+
+	if (ip_rev == S3C244X_CAMIF_IP_REV)
+		camif_s3c244x_hw_set_scaler(vp);
+	else
+		camif_s3c64xx_hw_set_scaler(vp);
+}
+
+void camif_hw_enable_scaler(struct camif_vp *vp, bool on)
+{
+	u32 addr = S3C_CAMIF_REG_CISCCTRL(vp->id, vp->offset);
+	u32 cfg;
+
+	cfg = camif_read(vp->camif, addr);
+	if (on)
+		cfg |= CISCCTRL_SCALERSTART;
+	else
+		cfg &= ~CISCCTRL_SCALERSTART;
+	camif_write(vp->camif, addr, cfg);
+}
+
+void camif_hw_set_lastirq(struct camif_vp *vp, int enable)
+{
+	u32 addr = S3C_CAMIF_REG_CICTRL(vp->id, vp->offset);
+	u32 cfg;
+
+	cfg = camif_read(vp->camif, addr);
+	if (enable)
+		cfg |= CICTRL_LASTIRQ_ENABLE;
+	else
+		cfg &= ~CICTRL_LASTIRQ_ENABLE;
+	camif_write(vp->camif, addr, cfg);
+}
+
+void camif_hw_enable_capture(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	u32 cfg;
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CIIMGCPT(vp->offset));
+	camif->stream_count++;
+
+	if (camif->variant->ip_revision == S3C6410_CAMIF_IP_REV)
+		cfg |= CIIMGCPT_CPT_FREN_ENABLE(vp->id);
+
+	if (vp->scaler.enable)
+		cfg |= CIIMGCPT_IMGCPTEN_SC(vp->id);
+
+	if (camif->stream_count == 1)
+		cfg |= CIIMGCPT_IMGCPTEN;
+
+	camif_write(camif, S3C_CAMIF_REG_CIIMGCPT(vp->offset), cfg);
+
+	pr_debug("CIIMGCPT: %#x, camif->stream_count: %d\n",
+		 cfg, camif->stream_count);
+}
+
+void camif_hw_disable_capture(struct camif_vp *vp)
+{
+	struct camif_dev *camif = vp->camif;
+	u32 cfg;
+
+	cfg = camif_read(camif, S3C_CAMIF_REG_CIIMGCPT(vp->offset));
+	cfg &= ~CIIMGCPT_IMGCPTEN_SC(vp->id);
+
+	if (WARN_ON(--(camif->stream_count) < 0))
+		camif->stream_count = 0;
+
+	if (camif->stream_count == 0)
+		cfg &= ~CIIMGCPT_IMGCPTEN;
+
+	pr_debug("CIIMGCPT: %#x, camif->stream_count: %d\n",
+		 cfg, camif->stream_count);
+
+	camif_write(camif, S3C_CAMIF_REG_CIIMGCPT(vp->offset), cfg);
+}
+
+void camif_hw_dump_regs(struct camif_dev *camif, const char *label)
+{
+	struct {
+		u32 offset;
+		const char * const name;
+	} registers[] = {
+		{ S3C_CAMIF_REG_CISRCFMT,		"CISRCFMT" },
+		{ S3C_CAMIF_REG_CIWDOFST,		"CIWDOFST" },
+		{ S3C_CAMIF_REG_CIGCTRL,		"CIGCTRL" },
+		{ S3C_CAMIF_REG_CIWDOFST2,		"CIWDOFST2" },
+		{ S3C_CAMIF_REG_CIYSA(0, 0),		"CICOYSA0" },
+		{ S3C_CAMIF_REG_CICBSA(0, 0),		"CICOCBSA0" },
+		{ S3C_CAMIF_REG_CICRSA(0, 0),		"CICOCRSA0" },
+		{ S3C_CAMIF_REG_CIYSA(0, 1),		"CICOYSA1" },
+		{ S3C_CAMIF_REG_CICBSA(0, 1),		"CICOCBSA1" },
+		{ S3C_CAMIF_REG_CICRSA(0, 1),		"CICOCRSA1" },
+		{ S3C_CAMIF_REG_CIYSA(0, 2),		"CICOYSA2" },
+		{ S3C_CAMIF_REG_CICBSA(0, 2),		"CICOCBSA2" },
+		{ S3C_CAMIF_REG_CICRSA(0, 2),		"CICOCRSA2" },
+		{ S3C_CAMIF_REG_CIYSA(0, 3),		"CICOYSA3" },
+		{ S3C_CAMIF_REG_CICBSA(0, 3),		"CICOCBSA3" },
+		{ S3C_CAMIF_REG_CICRSA(0, 3),		"CICOCRSA3" },
+		{ S3C_CAMIF_REG_CIYSA(1, 0),		"CIPRYSA0" },
+		{ S3C_CAMIF_REG_CIYSA(1, 1),		"CIPRYSA1" },
+		{ S3C_CAMIF_REG_CIYSA(1, 2),		"CIPRYSA2" },
+		{ S3C_CAMIF_REG_CIYSA(1, 3),		"CIPRYSA3" },
+		{ S3C_CAMIF_REG_CITRGFMT(0, 0),		"CICOTRGFMT" },
+		{ S3C_CAMIF_REG_CITRGFMT(1, 0),		"CIPRTRGFMT" },
+		{ S3C_CAMIF_REG_CICTRL(0, 0),		"CICOCTRL" },
+		{ S3C_CAMIF_REG_CICTRL(1, 0),		"CIPRCTRL" },
+		{ S3C_CAMIF_REG_CISCPREDST(0, 0),	"CICOSCPREDST" },
+		{ S3C_CAMIF_REG_CISCPREDST(1, 0),	"CIPRSCPREDST" },
+		{ S3C_CAMIF_REG_CISCPRERATIO(0, 0),	"CICOSCPRERATIO" },
+		{ S3C_CAMIF_REG_CISCPRERATIO(1, 0),	"CIPRSCPRERATIO" },
+		{ S3C_CAMIF_REG_CISCCTRL(0, 0),		"CICOSCCTRL" },
+		{ S3C_CAMIF_REG_CISCCTRL(1, 0),		"CIPRSCCTRL" },
+		{ S3C_CAMIF_REG_CITAREA(0, 0),		"CICOTAREA" },
+		{ S3C_CAMIF_REG_CITAREA(1, 0),		"CIPRTAREA" },
+		{ S3C_CAMIF_REG_CISTATUS(0, 0),		"CICOSTATUS" },
+		{ S3C_CAMIF_REG_CISTATUS(1, 0),		"CIPRSTATUS" },
+		{ S3C_CAMIF_REG_CIIMGCPT(0),		"CIIMGCPT" },
+	};
+	u32 i;
+
+	pr_info("--- %s ---\n", label);
+	for (i = 0; i < ARRAY_SIZE(registers); i++) {
+		u32 cfg = readl(camif->io_base + registers[i].offset);
+		printk(KERN_INFO "%s:\t0x%08x\n", registers[i].name, cfg);
+	}
+}
diff --git a/drivers/media/platform/s3c-camif/camif-regs.h b/drivers/media/platform/s3c-camif/camif-regs.h
new file mode 100644
index 000000000000..af2d472ea1dd
--- /dev/null
+++ b/drivers/media/platform/s3c-camif/camif-regs.h
@@ -0,0 +1,269 @@
+/*
+ * Register definition file for s3c24xx/s3c64xx SoC CAMIF driver
+ *
+ * Copyright (C) 2012 Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
+ * Copyright (C) 2012 Tomasz Figa <tomasz.figa@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef CAMIF_REGS_H_
+#define CAMIF_REGS_H_
+
+#include "camif-core.h"
+#include <media/s3c_camif.h>
+
+/*
+ * The id argument indicates the processing path:
+ * id = 0 - codec (FIMC C), 1 - preview (FIMC P).
+ */
+
+/* Camera input format */
+#define S3C_CAMIF_REG_CISRCFMT			0x00
+#define  CISRCFMT_ITU601_8BIT			(1 << 31)
+#define  CISRCFMT_ITU656_8BIT			(0 << 31)
+#define  CISRCFMT_ORDER422_YCBYCR		(0 << 14)
+#define  CISRCFMT_ORDER422_YCRYCB		(1 << 14)
+#define  CISRCFMT_ORDER422_CBYCRY		(2 << 14)
+#define  CISRCFMT_ORDER422_CRYCBY		(3 << 14)
+#define  CISRCFMT_ORDER422_MASK			(3 << 14)
+#define  CISRCFMT_SIZE_CAM_MASK			(0x1fff << 16 | 0x1fff)
+
+/* Window offset */
+#define S3C_CAMIF_REG_CIWDOFST			0x04
+#define  CIWDOFST_WINOFSEN			(1 << 31)
+#define  CIWDOFST_CLROVCOFIY			(1 << 30)
+#define  CIWDOFST_CLROVRLB_PR			(1 << 28)
+/* #define  CIWDOFST_CLROVPRFIY			(1 << 27) */
+#define  CIWDOFST_CLROVCOFICB			(1 << 15)
+#define  CIWDOFST_CLROVCOFICR			(1 << 14)
+#define  CIWDOFST_CLROVPRFICB			(1 << 13)
+#define  CIWDOFST_CLROVPRFICR			(1 << 12)
+#define  CIWDOFST_OFST_MASK			(0x7ff << 16 | 0x7ff)
+
+/* Window offset 2 */
+#define S3C_CAMIF_REG_CIWDOFST2			0x14
+#define  CIWDOFST2_OFST2_MASK			(0xfff << 16 | 0xfff)
+
+/* Global control */
+#define S3C_CAMIF_REG_CIGCTRL			0x08
+#define  CIGCTRL_SWRST				(1 << 31)
+#define  CIGCTRL_CAMRST				(1 << 30)
+#define  CIGCTRL_TESTPATTERN_NORMAL		(0 << 27)
+#define  CIGCTRL_TESTPATTERN_COLOR_BAR		(1 << 27)
+#define  CIGCTRL_TESTPATTERN_HOR_INC		(2 << 27)
+#define  CIGCTRL_TESTPATTERN_VER_INC		(3 << 27)
+#define  CIGCTRL_TESTPATTERN_MASK		(3 << 27)
+#define  CIGCTRL_INVPOLPCLK			(1 << 26)
+#define  CIGCTRL_INVPOLVSYNC			(1 << 25)
+#define  CIGCTRL_INVPOLHREF			(1 << 24)
+#define  CIGCTRL_IRQ_OVFEN			(1 << 22)
+#define  CIGCTRL_HREF_MASK			(1 << 21)
+#define  CIGCTRL_IRQ_LEVEL			(1 << 20)
+/* IRQ_CLR_C, IRQ_CLR_P */
+#define  CIGCTRL_IRQ_CLR(id)			(1 << (19 - (id)))
+#define  CIGCTRL_FIELDMODE			(1 << 2)
+#define  CIGCTRL_INVPOLFIELD			(1 << 1)
+#define  CIGCTRL_CAM_INTERLACE			(1 << 0)
+
+/* Y DMA output frame start address. n = 0..3. */
+#define S3C_CAMIF_REG_CIYSA(id, n)		(0x18 + (id) * 0x54 + (n) * 4)
+/* Cb plane output DMA start address. n = 0..3. Only codec path. */
+#define S3C_CAMIF_REG_CICBSA(id, n)		(0x28 + (id) * 0x54 + (n) * 4)
+/* Cr plane output DMA start address. n = 0..3. Only codec path. */
+#define S3C_CAMIF_REG_CICRSA(id, n)		(0x38 + (id) * 0x54 + (n) * 4)
+
+/* CICOTRGFMT, CIPRTRGFMT - Target format */
+#define S3C_CAMIF_REG_CITRGFMT(id, _offs)	(0x48 + (id) * (0x34 + (_offs)))
+#define  CITRGFMT_IN422				(1 << 31) /* only for s3c24xx */
+#define  CITRGFMT_OUT422			(1 << 30) /* only for s3c24xx */
+#define  CITRGFMT_OUTFORMAT_YCBCR420		(0 << 29) /* only for s3c6410 */
+#define  CITRGFMT_OUTFORMAT_YCBCR422		(1 << 29) /* only for s3c6410 */
+#define  CITRGFMT_OUTFORMAT_YCBCR422I		(2 << 29) /* only for s3c6410 */
+#define  CITRGFMT_OUTFORMAT_RGB			(3 << 29) /* only for s3c6410 */
+#define  CITRGFMT_OUTFORMAT_MASK		(3 << 29) /* only for s3c6410 */
+#define  CITRGFMT_TARGETHSIZE(x)		((x) << 16)
+#define  CITRGFMT_FLIP_NORMAL			(0 << 14)
+#define  CITRGFMT_FLIP_X_MIRROR			(1 << 14)
+#define  CITRGFMT_FLIP_Y_MIRROR			(2 << 14)
+#define  CITRGFMT_FLIP_180			(3 << 14)
+#define  CITRGFMT_FLIP_MASK			(3 << 14)
+/* Preview path only */
+#define  CITRGFMT_ROT90_PR			(1 << 13)
+#define  CITRGFMT_TARGETVSIZE(x)		((x) << 0)
+#define  CITRGFMT_TARGETSIZE_MASK		((0x1fff << 16) | 0x1fff)
+
+/* CICOCTRL, CIPRCTRL. Output DMA control. */
+#define S3C_CAMIF_REG_CICTRL(id, _offs)		(0x4c + (id) * (0x34 + (_offs)))
+#define  CICTRL_BURST_MASK			(0xfffff << 4)
+/* xBURSTn - 5-bits width */
+#define  CICTRL_YBURST1(x)			((x) << 19)
+#define  CICTRL_YBURST2(x)			((x) << 14)
+#define  CICTRL_RGBBURST1(x)			((x) << 19)
+#define  CICTRL_RGBBURST2(x)			((x) << 14)
+#define  CICTRL_CBURST1(x)			((x) << 9)
+#define  CICTRL_CBURST2(x)			((x) << 4)
+#define  CICTRL_LASTIRQ_ENABLE			(1 << 2)
+#define  CICTRL_ORDER422_MASK			(3 << 0)
+
+/* CICOSCPRERATIO, CIPRSCPRERATIO. Pre-scaler control 1. */
+#define S3C_CAMIF_REG_CISCPRERATIO(id, _offs)	(0x50 + (id) * (0x34 + (_offs)))
+
+/* CICOSCPREDST, CIPRSCPREDST. Pre-scaler control 2. */
+#define S3C_CAMIF_REG_CISCPREDST(id, _offs)	(0x54 + (id) * (0x34 + (_offs)))
+
+/* CICOSCCTRL, CIPRSCCTRL. Main scaler control. */
+#define S3C_CAMIF_REG_CISCCTRL(id, _offs)	(0x58 + (id) * (0x34 + (_offs)))
+#define  CISCCTRL_SCALERBYPASS			(1 << 31)
+/* s3c244x preview path only, s3c64xx both */
+#define  CIPRSCCTRL_SAMPLE			(1 << 31)
+/* 0 - 16-bit RGB, 1 - 24-bit RGB */
+#define  CIPRSCCTRL_RGB_FORMAT_24BIT		(1 << 30) /* only for s3c244x */
+#define  CIPRSCCTRL_SCALEUP_H			(1 << 29) /* only for s3c244x */
+#define  CIPRSCCTRL_SCALEUP_V			(1 << 28) /* only for s3c244x */
+/* s3c64xx */
+#define  CISCCTRL_SCALEUP_H			(1 << 30)
+#define  CISCCTRL_SCALEUP_V			(1 << 29)
+#define  CISCCTRL_SCALEUP_MASK			(0x3 << 29)
+#define  CISCCTRL_CSCR2Y_WIDE			(1 << 28)
+#define  CISCCTRL_CSCY2R_WIDE			(1 << 27)
+#define  CISCCTRL_LCDPATHEN_FIFO		(1 << 26)
+#define  CISCCTRL_INTERLACE			(1 << 25)
+#define  CISCCTRL_SCALERSTART			(1 << 15)
+#define  CISCCTRL_INRGB_FMT_RGB565		(0 << 13)
+#define  CISCCTRL_INRGB_FMT_RGB666		(1 << 13)
+#define  CISCCTRL_INRGB_FMT_RGB888		(2 << 13)
+#define  CISCCTRL_INRGB_FMT_MASK		(3 << 13)
+#define  CISCCTRL_OUTRGB_FMT_RGB565		(0 << 11)
+#define  CISCCTRL_OUTRGB_FMT_RGB666		(1 << 11)
+#define  CISCCTRL_OUTRGB_FMT_RGB888		(2 << 11)
+#define  CISCCTRL_OUTRGB_FMT_MASK		(3 << 11)
+#define  CISCCTRL_EXTRGB_EXTENSION		(1 << 10)
+#define  CISCCTRL_ONE2ONE			(1 << 9)
+#define  CISCCTRL_MAIN_RATIO_MASK		(0x1ff << 16 | 0x1ff)
+
+/* CICOTAREA, CIPRTAREA. Target area for DMA (Hsize x Vsize). */
+#define S3C_CAMIF_REG_CITAREA(id, _offs)	(0x5c + (id) * (0x34 + (_offs)))
+#define CITAREA_MASK				0xfffffff
+
+/* Codec (id = 0) or preview (id = 1) path status. */
+#define S3C_CAMIF_REG_CISTATUS(id, _offs)	(0x64 + (id) * (0x34 + (_offs)))
+#define  CISTATUS_OVFIY_STATUS			(1 << 31)
+#define  CISTATUS_OVFICB_STATUS			(1 << 30)
+#define  CISTATUS_OVFICR_STATUS			(1 << 29)
+#define  CISTATUS_OVF_MASK			(0x7 << 29)
+#define  CIPRSTATUS_OVF_MASK			(0x3 << 30)
+#define  CISTATUS_VSYNC_STATUS			(1 << 28)
+#define  CISTATUS_FRAMECNT_MASK			(3 << 26)
+#define  CISTATUS_FRAMECNT(__reg)		(((__reg) >> 26) & 0x3)
+#define  CISTATUS_WINOFSTEN_STATUS		(1 << 25)
+#define  CISTATUS_IMGCPTEN_STATUS		(1 << 22)
+#define  CISTATUS_IMGCPTENSC_STATUS		(1 << 21)
+#define  CISTATUS_VSYNC_A_STATUS		(1 << 20)
+#define  CISTATUS_FRAMEEND_STATUS		(1 << 19) /* 17 on s3c64xx */
+
+/* Image capture enable */
+#define S3C_CAMIF_REG_CIIMGCPT(_offs)		(0xa0 + (_offs))
+#define  CIIMGCPT_IMGCPTEN			(1 << 31)
+#define  CIIMGCPT_IMGCPTEN_SC(id)		(1 << (30 - (id)))
+/* Frame control: 1 - one-shot, 0 - free run */
+#define  CIIMGCPT_CPT_FREN_ENABLE(id)		(1 << (25 - (id)))
+#define  CIIMGCPT_CPT_FRMOD_ENABLE		(0 << 18)
+#define  CIIMGCPT_CPT_FRMOD_CNT			(1 << 18)
+
+/* Capture sequence */
+#define S3C_CAMIF_REG_CICPTSEQ			0xc4
+
+/* Image effects */
+#define S3C_CAMIF_REG_CIIMGEFF(_offs)		(0xb0 + (_offs))
+#define  CIIMGEFF_IE_ENABLE(id)			(1 << (30 + (id)))
+#define  CIIMGEFF_IE_ENABLE_MASK		(3 << 30)
+/* Image effect: 1 - after scaler, 0 - before scaler */
+#define  CIIMGEFF_IE_AFTER_SC			(1 << 29)
+#define  CIIMGEFF_FIN_MASK			(7 << 26)
+#define  CIIMGEFF_FIN_BYPASS			(0 << 26)
+#define  CIIMGEFF_FIN_ARBITRARY			(1 << 26)
+#define  CIIMGEFF_FIN_NEGATIVE			(2 << 26)
+#define  CIIMGEFF_FIN_ARTFREEZE			(3 << 26)
+#define  CIIMGEFF_FIN_EMBOSSING			(4 << 26)
+#define  CIIMGEFF_FIN_SILHOUETTE		(5 << 26)
+#define  CIIMGEFF_PAT_CBCR_MASK			((0xff << 13) | 0xff)
+#define  CIIMGEFF_PAT_CB(x)			((x) << 13)
+#define  CIIMGEFF_PAT_CR(x)			(x)
+
+/* MSCOY0SA, MSPRY0SA. Y/Cb/Cr frame start address for input DMA. */
+#define S3C_CAMIF_REG_MSY0SA(id)		(0xd4 + ((id) * 0x2c))
+#define S3C_CAMIF_REG_MSCB0SA(id)		(0xd8 + ((id) * 0x2c))
+#define S3C_CAMIF_REG_MSCR0SA(id)		(0xdc + ((id) * 0x2c))
+
+/* MSCOY0END, MSCOY0END. Y/Cb/Cr frame end address for input DMA. */
+#define S3C_CAMIF_REG_MSY0END(id)		(0xe0 + ((id) * 0x2c))
+#define S3C_CAMIF_REG_MSCB0END(id)		(0xe4 + ((id) * 0x2c))
+#define S3C_CAMIF_REG_MSCR0END(id)		(0xe8 + ((id) * 0x2c))
+
+/* MSPRYOFF, MSPRYOFF. Y/Cb/Cr offset. n: 0 - codec, 1 - preview. */
+#define S3C_CAMIF_REG_MSYOFF(id)		(0x118 + ((id) * 0x2c))
+#define S3C_CAMIF_REG_MSCBOFF(id)		(0x11c + ((id) * 0x2c))
+#define S3C_CAMIF_REG_MSCROFF(id)		(0x120 + ((id) * 0x2c))
+
+/* Real input DMA data size. n = 0 - codec, 1 - preview. */
+#define S3C_CAMIF_REG_MSWIDTH(id)		(0xf8 + (id) * 0x2c)
+#define  AUTOLOAD_ENABLE			(1 << 31)
+#define  ADDR_CH_DIS				(1 << 30)
+#define  MSHEIGHT(x)				(((x) & 0x3ff) << 16)
+#define  MSWIDTH(x)				((x) & 0x3ff)
+
+/* Input DMA control. n = 0 - codec, 1 - preview */
+#define S3C_CAMIF_REG_MSCTRL(id)		(0xfc + (id) * 0x2c)
+#define  MSCTRL_ORDER422_M_YCBYCR		(0 << 4)
+#define  MSCTRL_ORDER422_M_YCRYCB		(1 << 4)
+#define  MSCTRL_ORDER422_M_CBYCRY		(2 << 4)
+#define  MSCTRL_ORDER422_M_CRYCBY		(3 << 4)
+/* 0 - camera, 1 - DMA */
+#define  MSCTRL_SEL_DMA_CAM			(1 << 3)
+#define  MSCTRL_INFORMAT_M_YCBCR420		(0 << 1)
+#define  MSCTRL_INFORMAT_M_YCBCR422		(1 << 1)
+#define  MSCTRL_INFORMAT_M_YCBCR422I		(2 << 1)
+#define  MSCTRL_INFORMAT_M_RGB			(3 << 1)
+#define  MSCTRL_ENVID_M				(1 << 0)
+
+/* CICOSCOSY, CIPRSCOSY. Scan line Y/Cb/Cr offset. */
+#define S3C_CAMIF_REG_CISSY(id)			(0x12c + (id) * 0x0c)
+#define S3C_CAMIF_REG_CISSCB(id)		(0x130 + (id) * 0x0c)
+#define S3C_CAMIF_REG_CISSCR(id)		(0x134 + (id) * 0x0c)
+#define S3C_CISS_OFFS_INITIAL(x)		((x) << 16)
+#define S3C_CISS_OFFS_LINE(x)			((x) << 0)
+
+/* ------------------------------------------------------------------ */
+
+void camif_hw_reset(struct camif_dev *camif);
+void camif_hw_clear_pending_irq(struct camif_vp *vp);
+void camif_hw_clear_fifo_overflow(struct camif_vp *vp);
+void camif_hw_set_lastirq(struct camif_vp *vp, int enable);
+void camif_hw_set_input_path(struct camif_vp *vp);
+void camif_hw_enable_scaler(struct camif_vp *vp, bool on);
+void camif_hw_enable_capture(struct camif_vp *vp);
+void camif_hw_disable_capture(struct camif_vp *vp);
+void camif_hw_set_camera_bus(struct camif_dev *camif);
+void camif_hw_set_source_format(struct camif_dev *camif);
+void camif_hw_set_camera_crop(struct camif_dev *camif);
+void camif_hw_set_scaler(struct camif_vp *vp);
+void camif_hw_set_flip(struct camif_vp *vp);
+void camif_hw_set_output_dma(struct camif_vp *vp);
+void camif_hw_set_target_format(struct camif_vp *vp);
+void camif_hw_set_test_pattern(struct camif_dev *camif, unsigned int pattern);
+void camif_hw_set_effect(struct camif_dev *camif, unsigned int effect,
+			unsigned int cr, unsigned int cb);
+void camif_hw_set_output_addr(struct camif_vp *vp, struct camif_addr *paddr,
+			      int index);
+void camif_hw_dump_regs(struct camif_dev *camif, const char *label);
+
+static inline u32 camif_hw_get_status(struct camif_vp *vp)
+{
+	return readl(vp->camif->io_base + S3C_CAMIF_REG_CISTATUS(vp->id,
+								vp->offset));
+}
+
+#endif /* CAMIF_REGS_H_ */
diff --git a/include/media/s3c_camif.h b/include/media/s3c_camif.h
new file mode 100644
index 000000000000..df96c2c789b4
--- /dev/null
+++ b/include/media/s3c_camif.h
@@ -0,0 +1,45 @@
+/*
+ * s3c24xx/s3c64xx SoC series Camera Interface (CAMIF) driver
+ *
+ * Copyright (C) 2012 Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef MEDIA_S3C_CAMIF_
+#define MEDIA_S3C_CAMIF_
+
+#include <linux/i2c.h>
+#include <media/v4l2-mediabus.h>
+
+/**
+ * struct s3c_camif_sensor_info - an image sensor description
+ * @i2c_board_info: pointer to an I2C sensor subdevice board info
+ * @clock_frequency: frequency of the clock the host provides to a sensor
+ * @mbus_type: media bus type
+ * @i2c_bus_num: i2c control bus id the sensor is attached to
+ * @flags: the parallel bus flags defining signals polarity (V4L2_MBUS_*)
+ * @use_field: 1 if parallel bus FIELD signal is used (only s3c64xx)
+ */
+struct s3c_camif_sensor_info {
+	struct i2c_board_info i2c_board_info;
+	unsigned long clock_frequency;
+	enum v4l2_mbus_type mbus_type;
+	u16 i2c_bus_num;
+	u16 flags;
+	u8 use_field;
+};
+
+struct s3c_camif_plat_data {
+	struct s3c_camif_sensor_info sensor;
+	int (*gpio_get)(void);
+	int (*gpio_put)(void);
+};
+
+/* Platform default helper functions */
+int s3c_camif_gpio_get(void);
+int s3c_camif_gpio_put(void);
+
+#endif /* MEDIA_S3C_CAMIF_ */
-- 
cgit v1.2.3-55-g7522


From b951b523ea45d5717377ce2216afe98440001660 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Mon, 26 Nov 2012 21:11:10 +0000
Subject: mfd: arizona: Allow the CODEC DAPM context to be accessed elsewhere

Some other device functions need to integrate with signal sources in the
audio portion (primarily for haptics) so allow CODEC to export the DAPM
context by pointing to it from the core driver.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/linux/mfd/arizona/core.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/mfd/arizona/core.h b/include/linux/mfd/arizona/core.h
index dd231ac0bb1f..a580363a7d29 100644
--- a/include/linux/mfd/arizona/core.h
+++ b/include/linux/mfd/arizona/core.h
@@ -78,6 +78,8 @@ enum arizona_type {
 
 #define ARIZONA_NUM_IRQ                   50
 
+struct snd_soc_dapm_context;
+
 struct arizona {
 	struct regmap *regmap;
 	struct device *dev;
@@ -98,6 +100,8 @@ struct arizona {
 
 	struct mutex clk_lock;
 	int clk32k_ref;
+
+	struct snd_soc_dapm_context *dapm;
 };
 
 int arizona_clk32k_enable(struct arizona *arizona);
-- 
cgit v1.2.3-55-g7522


From 9dd555e2f4de1af1bb0f75cc84ed0708fcdb5987 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Mon, 26 Nov 2012 21:17:21 +0000
Subject: Input - arizona-haptics: Add driver haptics module on Arizona CODECs

The Arizona CODECs contain a haptics module providing vibration feedback
support. Implement basic support for this, providing simple start/stop and
signal magnitude control.

Since the output path for haptics is routed through the CODEC audio routing
it is modelled as a signal generator within ASoC, the haptics driver calls
DAPM to start and stop the output drivers. An appropriate output path must
be configured via ALSA to connect the haptics source to the correct output.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/input/misc/Kconfig           |  10 ++
 drivers/input/misc/Makefile          |   1 +
 drivers/input/misc/arizona-haptics.c | 255 +++++++++++++++++++++++++++++++++++
 include/linux/mfd/arizona/pdata.h    |   6 +
 4 files changed, 272 insertions(+)
 create mode 100644 drivers/input/misc/arizona-haptics.c

(limited to 'include')

diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 7c0f1ecfdd7a..104a7c3153c0 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -72,6 +72,16 @@ config INPUT_AD714X_SPI
 	  To compile this driver as a module, choose M here: the
 	  module will be called ad714x-spi.
 
+config INPUT_ARIZONA_HAPTICS
+	tristate "Arizona haptics support"
+	depends on MFD_ARIZONA && SND_SOC
+	select INPUT_FF_MEMLESS
+	help
+	  Say Y to enable support for the haptics module in Arizona CODECs.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called arizona-haptics.
+
 config INPUT_BMA150
 	tristate "BMA150/SMB380 acceleration sensor support"
 	depends on I2C
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index 83fe6f5b77d1..5ea769eda999 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_INPUT_ADXL34X)		+= adxl34x.o
 obj-$(CONFIG_INPUT_ADXL34X_I2C)		+= adxl34x-i2c.o
 obj-$(CONFIG_INPUT_ADXL34X_SPI)		+= adxl34x-spi.o
 obj-$(CONFIG_INPUT_APANEL)		+= apanel.o
+obj-$(CONFIG_INPUT_ARIZONA_HAPTICS)	+= arizona-haptics.o
 obj-$(CONFIG_INPUT_ATI_REMOTE2)		+= ati_remote2.o
 obj-$(CONFIG_INPUT_ATLAS_BTNS)		+= atlas_btns.o
 obj-$(CONFIG_INPUT_BFIN_ROTARY)		+= bfin_rotary.o
diff --git a/drivers/input/misc/arizona-haptics.c b/drivers/input/misc/arizona-haptics.c
new file mode 100644
index 000000000000..7a04f54ef961
--- /dev/null
+++ b/drivers/input/misc/arizona-haptics.c
@@ -0,0 +1,255 @@
+/*
+ * Arizona haptics driver
+ *
+ * Copyright 2012 Wolfson Microelectronics plc
+ *
+ * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/input.h>
+#include <linux/slab.h>
+
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+
+#include <linux/mfd/arizona/core.h>
+#include <linux/mfd/arizona/pdata.h>
+#include <linux/mfd/arizona/registers.h>
+
+struct arizona_haptics {
+	struct arizona *arizona;
+	struct input_dev *input_dev;
+	struct work_struct work;
+
+	struct mutex mutex;
+	u8 intensity;
+};
+
+static void arizona_haptics_work(struct work_struct *work)
+{
+	struct arizona_haptics *haptics = container_of(work,
+						       struct arizona_haptics,
+						       work);
+	struct arizona *arizona = haptics->arizona;
+	struct mutex *dapm_mutex = &arizona->dapm->card->dapm_mutex;
+	int ret;
+
+	if (!haptics->arizona->dapm) {
+		dev_err(arizona->dev, "No DAPM context\n");
+		return;
+	}
+
+	if (haptics->intensity) {
+		ret = regmap_update_bits(arizona->regmap,
+					 ARIZONA_HAPTICS_PHASE_2_INTENSITY,
+					 ARIZONA_PHASE2_INTENSITY_MASK,
+					 haptics->intensity);
+		if (ret != 0) {
+			dev_err(arizona->dev, "Failed to set intensity: %d\n",
+				ret);
+			return;
+		}
+
+		/* This enable sequence will be a noop if already enabled */
+		ret = regmap_update_bits(arizona->regmap,
+					 ARIZONA_HAPTICS_CONTROL_1,
+					 ARIZONA_HAP_CTRL_MASK,
+					 1 << ARIZONA_HAP_CTRL_SHIFT);
+		if (ret != 0) {
+			dev_err(arizona->dev, "Failed to start haptics: %d\n",
+				ret);
+			return;
+		}
+
+		mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+		ret = snd_soc_dapm_enable_pin(arizona->dapm, "HAPTICS");
+		if (ret != 0) {
+			dev_err(arizona->dev, "Failed to start HAPTICS: %d\n",
+				ret);
+			mutex_unlock(dapm_mutex);
+			return;
+		}
+
+		ret = snd_soc_dapm_sync(arizona->dapm);
+		if (ret != 0) {
+			dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
+				ret);
+			mutex_unlock(dapm_mutex);
+			return;
+		}
+
+		mutex_unlock(dapm_mutex);
+
+	} else {
+		/* This disable sequence will be a noop if already enabled */
+		mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+		ret = snd_soc_dapm_disable_pin(arizona->dapm, "HAPTICS");
+		if (ret != 0) {
+			dev_err(arizona->dev, "Failed to disable HAPTICS: %d\n",
+				ret);
+			mutex_unlock(dapm_mutex);
+			return;
+		}
+
+		ret = snd_soc_dapm_sync(arizona->dapm);
+		if (ret != 0) {
+			dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
+				ret);
+			mutex_unlock(dapm_mutex);
+			return;
+		}
+
+		mutex_unlock(dapm_mutex);
+
+		ret = regmap_update_bits(arizona->regmap,
+					 ARIZONA_HAPTICS_CONTROL_1,
+					 ARIZONA_HAP_CTRL_MASK,
+					 1 << ARIZONA_HAP_CTRL_SHIFT);
+		if (ret != 0) {
+			dev_err(arizona->dev, "Failed to stop haptics: %d\n",
+				ret);
+			return;
+		}
+	}
+}
+
+static int arizona_haptics_play(struct input_dev *input, void *data,
+				struct ff_effect *effect)
+{
+	struct arizona_haptics *haptics = input_get_drvdata(input);
+	struct arizona *arizona = haptics->arizona;
+
+	if (!arizona->dapm) {
+		dev_err(arizona->dev, "No DAPM context\n");
+		return -EBUSY;
+	}
+
+	if (effect->u.rumble.strong_magnitude) {
+		/* Scale the magnitude into the range the device supports */
+		if (arizona->pdata.hap_act) {
+			haptics->intensity =
+				effect->u.rumble.strong_magnitude >> 9;
+			if (effect->direction < 0x8000)
+				haptics->intensity += 0x7f;
+		} else {
+			haptics->intensity =
+				effect->u.rumble.strong_magnitude >> 8;
+		}
+	} else {
+		haptics->intensity = 0;
+	}
+
+	schedule_work(&haptics->work);
+
+	return 0;
+}
+
+static void arizona_haptics_close(struct input_dev *input)
+{
+	struct arizona_haptics *haptics = input_get_drvdata(input);
+	struct mutex *dapm_mutex = &haptics->arizona->dapm->card->dapm_mutex;
+
+	cancel_work_sync(&haptics->work);
+
+	mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+	if (haptics->arizona->dapm)
+		snd_soc_dapm_disable_pin(haptics->arizona->dapm, "HAPTICS");
+
+	mutex_unlock(dapm_mutex);
+}
+
+static int arizona_haptics_probe(struct platform_device *pdev)
+{
+	struct arizona *arizona = dev_get_drvdata(pdev->dev.parent);
+	struct arizona_haptics *haptics;
+	int ret;
+
+	haptics = devm_kzalloc(&pdev->dev, sizeof(*haptics), GFP_KERNEL);
+	if (!haptics)
+		return -ENOMEM;
+
+	haptics->arizona = arizona;
+
+	ret = regmap_update_bits(arizona->regmap, ARIZONA_HAPTICS_CONTROL_1,
+				 ARIZONA_HAP_ACT, arizona->pdata.hap_act);
+	if (ret != 0) {
+		dev_err(arizona->dev, "Failed to set haptics actuator: %d\n",
+			ret);
+		return ret;
+	}
+
+	INIT_WORK(&haptics->work, arizona_haptics_work);
+
+	haptics->input_dev = input_allocate_device();
+	if (haptics->input_dev == NULL) {
+		dev_err(arizona->dev, "Failed to allocate input device\n");
+		return -ENOMEM;
+	}
+
+	input_set_drvdata(haptics->input_dev, haptics);
+
+	haptics->input_dev->name = "arizona:haptics";
+	haptics->input_dev->dev.parent = pdev->dev.parent;
+	haptics->input_dev->close = arizona_haptics_close;
+	__set_bit(FF_RUMBLE, haptics->input_dev->ffbit);
+
+	ret = input_ff_create_memless(haptics->input_dev, NULL,
+				      arizona_haptics_play);
+	if (ret < 0) {
+		dev_err(arizona->dev, "input_ff_create_memless() failed: %d\n",
+			ret);
+		goto err_ialloc;
+	}
+
+	ret = input_register_device(haptics->input_dev);
+	if (ret < 0) {
+		dev_err(arizona->dev, "couldn't register input device: %d\n",
+			ret);
+		goto err_iff;
+	}
+
+	platform_set_drvdata(pdev, haptics);
+
+	return 0;
+
+err_iff:
+	if (haptics->input_dev)
+		input_ff_destroy(haptics->input_dev);
+err_ialloc:
+	input_free_device(haptics->input_dev);
+
+	return ret;
+}
+
+static int arizona_haptics_remove(struct platform_device *pdev)
+{
+	struct arizona_haptics *haptics = platform_get_drvdata(pdev);
+
+	input_unregister_device(haptics->input_dev);
+
+	return 0;
+}
+
+static struct platform_driver arizona_haptics_driver = {
+	.probe		= arizona_haptics_probe,
+	.remove		= arizona_haptics_remove,
+	.driver		= {
+		.name	= "arizona-haptics",
+		.owner	= THIS_MODULE,
+	},
+};
+module_platform_driver(arizona_haptics_driver);
+
+MODULE_ALIAS("platform:arizona-haptics");
+MODULE_DESCRIPTION("Arizona haptics driver");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>");
diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h
index 7ab442905a57..8b1d1daaae16 100644
--- a/include/linux/mfd/arizona/pdata.h
+++ b/include/linux/mfd/arizona/pdata.h
@@ -62,6 +62,9 @@
 
 #define ARIZONA_MAX_OUTPUT 6
 
+#define ARIZONA_HAP_ACT_ERM 0
+#define ARIZONA_HAP_ACT_LRA 2
+
 #define ARIZONA_MAX_PDM_SPK 2
 
 struct regulator_init_data;
@@ -114,6 +117,9 @@ struct arizona_pdata {
 
 	/** PDM speaker format */
 	unsigned int spk_fmt[ARIZONA_MAX_PDM_SPK];
+
+	/** Haptic actuator type */
+	unsigned int hap_act;
 };
 
 #endif
-- 
cgit v1.2.3-55-g7522


From e80d0a1ae8bb8fee0edd37427836f108b30f596b Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Wed, 21 Nov 2012 16:26:44 +0100
Subject: cputime: Rename thread_group_times to thread_group_cputime_adjusted

We have thread_group_cputime() and thread_group_times(). The naming
doesn't provide enough information about the difference between
these two APIs.

To lower the confusion, rename thread_group_times() to
thread_group_cputime_adjusted(). This name better suggests that
it's a version of thread_group_cputime() that does some stabilization
on the raw cputime values. ie here: scale on top of CFS runtime
stats and bound lower value for monotonicity.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 fs/proc/array.c        | 4 ++--
 include/linux/sched.h  | 4 ++--
 kernel/exit.c          | 4 ++--
 kernel/sched/cputime.c | 8 ++++----
 kernel/sys.c           | 6 +++---
 5 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/proc/array.c b/fs/proc/array.c
index c1c207c36cae..d3696708fc1a 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -438,7 +438,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 			min_flt += sig->min_flt;
 			maj_flt += sig->maj_flt;
-			thread_group_times(task, &utime, &stime);
+			thread_group_cputime_adjusted(task, &utime, &stime);
 			gtime += sig->gtime;
 		}
 
@@ -454,7 +454,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	if (!whole) {
 		min_flt = task->min_flt;
 		maj_flt = task->maj_flt;
-		task_times(task, &utime, &stime);
+		task_cputime_adjusted(task, &utime, &stime);
 		gtime = task->gtime;
 	}
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e1581a029e3d..e75cab5820ab 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1751,8 +1751,8 @@ static inline void put_task_struct(struct task_struct *t)
 		__put_task_struct(t);
 }
 
-extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
-extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
 /*
  * Per process flags
diff --git a/kernel/exit.c b/kernel/exit.c
index 346616c0092c..618f7ee56003 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1186,11 +1186,11 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * as other threads in the parent group can be right
 		 * here reaping other children at the same time.
 		 *
-		 * We use thread_group_times() to get times for the thread
+		 * We use thread_group_cputime_adjusted() to get times for the thread
 		 * group, which consolidates times for all threads in the
 		 * group including the group leader.
 		 */
-		thread_group_times(p, &tgutime, &tgstime);
+		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
 		spin_lock_irq(&p->real_parent->sighand->siglock);
 		psig = p->real_parent->signal;
 		sig = p->signal;
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index e56f138a23c7..7dc155371b95 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -445,13 +445,13 @@ void account_idle_ticks(unsigned long ticks)
  * Use precise platform statistics if available:
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	*ut = p->utime;
 	*st = p->stime;
 }
 
-void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	struct task_cputime cputime;
 
@@ -516,7 +516,7 @@ static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
 	return (__force cputime_t) temp;
 }
 
-void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	cputime_t rtime, utime = p->utime, total = utime + p->stime;
 
@@ -543,7 +543,7 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 /*
  * Must be called with siglock held.
  */
-void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	struct signal_struct *sig = p->signal;
 	struct task_cputime cputime;
diff --git a/kernel/sys.c b/kernel/sys.c
index e6e0ece5f6a0..265b37690421 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1046,7 +1046,7 @@ void do_sys_times(struct tms *tms)
 	cputime_t tgutime, tgstime, cutime, cstime;
 
 	spin_lock_irq(&current->sighand->siglock);
-	thread_group_times(current, &tgutime, &tgstime);
+	thread_group_cputime_adjusted(current, &tgutime, &tgstime);
 	cutime = current->signal->cutime;
 	cstime = current->signal->cstime;
 	spin_unlock_irq(&current->sighand->siglock);
@@ -1704,7 +1704,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	utime = stime = 0;
 
 	if (who == RUSAGE_THREAD) {
-		task_times(current, &utime, &stime);
+		task_cputime_adjusted(current, &utime, &stime);
 		accumulate_thread_rusage(p, r);
 		maxrss = p->signal->maxrss;
 		goto out;
@@ -1730,7 +1730,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 				break;
 
 		case RUSAGE_SELF:
-			thread_group_times(p, &tgutime, &tgstime);
+			thread_group_cputime_adjusted(p, &tgutime, &tgstime);
 			utime += tgutime;
 			stime += tgstime;
 			r->ru_nvcsw += p->signal->nvcsw;
-- 
cgit v1.2.3-55-g7522


From d37f761dbd276790f70dcf73a287fde2c3464482 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Thu, 22 Nov 2012 00:58:35 +0100
Subject: cputime: Consolidate cputime adjustment code

task_cputime_adjusted() and thread_group_cputime_adjusted()
essentially share the same code. They just don't use the same
source:

* The first function uses the cputime in the task struct and the
previous adjusted snapshot that ensures monotonicity.

* The second adds the cputime of all tasks in the group and the
previous adjusted snapshot of the whole group from the signal
structure.

Just consolidate the common code that does the adjustment. These
functions just need to fetch the values from the appropriate
source.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 include/linux/sched.h  | 23 +++++++++++++++++++----
 kernel/fork.c          |  2 +-
 kernel/sched/cputime.c | 46 +++++++++++++++++++++++-----------------------
 3 files changed, 43 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e75cab5820ab..5dafac366811 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -433,14 +433,29 @@ struct cpu_itimer {
 	u32 incr_error;
 };
 
+/**
+ * struct cputime - snaphsot of system and user cputime
+ * @utime: time spent in user mode
+ * @stime: time spent in system mode
+ *
+ * Gathers a generic snapshot of user and system time.
+ */
+struct cputime {
+	cputime_t utime;
+	cputime_t stime;
+};
+
 /**
  * struct task_cputime - collected CPU time counts
  * @utime:		time spent in user mode, in &cputime_t units
  * @stime:		time spent in kernel mode, in &cputime_t units
  * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
  *
- * This structure groups together three kinds of CPU time that are
- * tracked for threads and thread groups.  Most things considering
+ * This is an extension of struct cputime that includes the total runtime
+ * spent by the task from the scheduler point of view.
+ *
+ * As a result, this structure groups together three kinds of CPU time
+ * that are tracked for threads and thread groups.  Most things considering
  * CPU time want to group these counts together and treat all three
  * of them in parallel.
  */
@@ -581,7 +596,7 @@ struct signal_struct {
 	cputime_t gtime;
 	cputime_t cgtime;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	cputime_t prev_utime, prev_stime;
+	struct cputime prev_cputime;
 #endif
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
 	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
@@ -1340,7 +1355,7 @@ struct task_struct {
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	cputime_t prev_utime, prev_stime;
+	struct cputime prev_cputime;
 #endif
 	unsigned long nvcsw, nivcsw; /* context switch counts */
 	struct timespec start_time; 		/* monotonic time */
diff --git a/kernel/fork.c b/kernel/fork.c
index 8b20ab7d3aa2..0e7cdb90476f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1222,7 +1222,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->utime = p->stime = p->gtime = 0;
 	p->utimescaled = p->stimescaled = 0;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	p->prev_utime = p->prev_stime = 0;
+	p->prev_cputime.utime = p->prev_cputime.stime = 0;
 #endif
 #if defined(SPLIT_RSS_COUNTING)
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 7dc155371b95..220fdc4db770 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -516,14 +516,18 @@ static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
 	return (__force cputime_t) temp;
 }
 
-void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+static void cputime_adjust(struct task_cputime *curr,
+			   struct cputime *prev,
+			   cputime_t *ut, cputime_t *st)
 {
-	cputime_t rtime, utime = p->utime, total = utime + p->stime;
+	cputime_t rtime, utime, total;
 
+	utime = curr->utime;
+	total = utime + curr->stime;
 	/*
 	 * Use CFS's precise accounting:
 	 */
-	rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
+	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
 
 	if (total)
 		utime = scale_utime(utime, rtime, total);
@@ -533,11 +537,22 @@ void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	/*
 	 * Compare with previous values, to keep monotonicity:
 	 */
-	p->prev_utime = max(p->prev_utime, utime);
-	p->prev_stime = max(p->prev_stime, rtime - p->prev_utime);
+	prev->utime = max(prev->utime, utime);
+	prev->stime = max(prev->stime, rtime - prev->utime);
+
+	*ut = prev->utime;
+	*st = prev->stime;
+}
 
-	*ut = p->prev_utime;
-	*st = p->prev_stime;
+void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	struct task_cputime cputime = {
+		.utime = p->utime,
+		.stime = p->stime,
+		.sum_exec_runtime = p->se.sum_exec_runtime,
+	};
+
+	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 
 /*
@@ -545,24 +560,9 @@ void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
  */
 void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
-	struct signal_struct *sig = p->signal;
 	struct task_cputime cputime;
-	cputime_t rtime, utime, total;
 
 	thread_group_cputime(p, &cputime);
-
-	total = cputime.utime + cputime.stime;
-	rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
-
-	if (total)
-		utime = scale_utime(cputime.utime, rtime, total);
-	else
-		utime = rtime;
-
-	sig->prev_utime = max(sig->prev_utime, utime);
-	sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime);
-
-	*ut = sig->prev_utime;
-	*st = sig->prev_stime;
+	cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st);
 }
 #endif
-- 
cgit v1.2.3-55-g7522


From 73ee29460e5d0adbb46e4962df69ae2465746612 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 27 Nov 2012 18:48:33 +0000
Subject: regulator: arizona-ldo1: Support 1.8V mode

Some Arizona device support a 1.8V output mode. Enable this in the driver.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/mfd/wm5102-tables.c           |   3 +
 drivers/regulator/arizona-ldo1.c      | 107 +++++++++++++++++++++++++++++++++-
 include/linux/mfd/arizona/registers.h |  16 +++++
 3 files changed, 125 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mfd/wm5102-tables.c b/drivers/mfd/wm5102-tables.c
index 01b9255ed631..b829a5710ddc 100644
--- a/drivers/mfd/wm5102-tables.c
+++ b/drivers/mfd/wm5102-tables.c
@@ -775,6 +775,7 @@ static const struct reg_default wm5102_reg_default[] = {
 	{ 0x00000154, 0x0000 },   /* R340   - Rate Estimator 3 */ 
 	{ 0x00000155, 0x0000 },   /* R341   - Rate Estimator 4 */ 
 	{ 0x00000156, 0x0000 },   /* R342   - Rate Estimator 5 */ 
+	{ 0x00000161, 0x0000 },   /* R353   - Dynamic Frequency Scaling 1 */ 
 	{ 0x00000171, 0x0000 },   /* R369   - FLL1 Control 1 */ 
 	{ 0x00000172, 0x0008 },   /* R370   - FLL1 Control 2 */ 
 	{ 0x00000173, 0x0018 },   /* R371   - FLL1 Control 3 */ 
@@ -1564,6 +1565,7 @@ static bool wm5102_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_RATE_ESTIMATOR_3:
 	case ARIZONA_RATE_ESTIMATOR_4:
 	case ARIZONA_RATE_ESTIMATOR_5:
+	case ARIZONA_DYNAMIC_FREQUENCY_SCALING_1:
 	case ARIZONA_FLL1_CONTROL_1:
 	case ARIZONA_FLL1_CONTROL_2:
 	case ARIZONA_FLL1_CONTROL_3:
@@ -1596,6 +1598,7 @@ static bool wm5102_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_FLL2_GPIO_CLOCK:
 	case ARIZONA_MIC_CHARGE_PUMP_1:
 	case ARIZONA_LDO1_CONTROL_1:
+	case ARIZONA_LDO1_CONTROL_2:
 	case ARIZONA_LDO2_CONTROL_1:
 	case ARIZONA_MIC_BIAS_CTRL_1:
 	case ARIZONA_MIC_BIAS_CTRL_2:
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index 800c8ad3db91..739faf99b9e2 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -34,6 +34,108 @@ struct arizona_ldo1 {
 	struct regulator_init_data init_data;
 };
 
+static int arizona_ldo1_hc_list_voltage(struct regulator_dev *rdev,
+					unsigned int selector)
+{
+	if (selector >= rdev->desc->n_voltages)
+		return -EINVAL;
+
+	if (selector == rdev->desc->n_voltages - 1)
+		return 1800000;
+	else
+		return rdev->desc->min_uV + (rdev->desc->uV_step * selector);
+}
+
+static int arizona_ldo1_hc_map_voltage(struct regulator_dev *rdev,
+				       int min_uV, int max_uV)
+{
+	int sel;
+
+	sel = DIV_ROUND_UP(min_uV - rdev->desc->min_uV, rdev->desc->uV_step);
+	if (sel >= rdev->desc->n_voltages)
+		sel = rdev->desc->n_voltages - 1;
+
+	return sel;
+}
+
+static int arizona_ldo1_hc_set_voltage_sel(struct regulator_dev *rdev,
+					   unsigned sel)
+{
+	struct arizona_ldo1 *ldo = rdev_get_drvdata(rdev);
+	struct regmap *regmap = ldo->arizona->regmap;
+	unsigned int val;
+	int ret;
+
+	if (sel == rdev->desc->n_voltages - 1)
+		val = ARIZONA_LDO1_HI_PWR;
+	else
+		val = 0;
+
+	ret = regmap_update_bits(regmap, ARIZONA_LDO1_CONTROL_2,
+				 ARIZONA_LDO1_HI_PWR, val);
+	if (ret != 0)
+		return ret;
+
+	ret = regmap_update_bits(regmap, ARIZONA_DYNAMIC_FREQUENCY_SCALING_1,
+				 ARIZONA_SUBSYS_MAX_FREQ, val);
+	if (ret != 0)
+		return ret;
+
+	if (val)
+		return 0;
+
+	val = sel << ARIZONA_LDO1_VSEL_SHIFT;
+
+	return regmap_update_bits(regmap, ARIZONA_LDO1_CONTROL_1,
+				  ARIZONA_LDO1_VSEL_MASK, val);
+}
+
+static int arizona_ldo1_hc_get_voltage_sel(struct regulator_dev *rdev)
+{
+	struct arizona_ldo1 *ldo = rdev_get_drvdata(rdev);
+	struct regmap *regmap = ldo->arizona->regmap;
+	unsigned int val;
+	int ret;
+
+	ret = regmap_read(regmap, ARIZONA_LDO1_CONTROL_2, &val);
+	if (ret != 0)
+		return ret;
+
+	if (val & ARIZONA_LDO1_HI_PWR)
+		return rdev->desc->n_voltages - 1;
+
+	ret = regmap_read(regmap, ARIZONA_LDO1_CONTROL_1, &val);
+	if (ret != 0)
+		return ret;
+
+	return (val & ARIZONA_LDO1_VSEL_MASK) >> ARIZONA_LDO1_VSEL_SHIFT;
+}
+
+static struct regulator_ops arizona_ldo1_hc_ops = {
+	.list_voltage = arizona_ldo1_hc_list_voltage,
+	.map_voltage = arizona_ldo1_hc_map_voltage,
+	.get_voltage_sel = arizona_ldo1_hc_get_voltage_sel,
+	.set_voltage_sel = arizona_ldo1_hc_set_voltage_sel,
+	.get_bypass = regulator_get_bypass_regmap,
+	.set_bypass = regulator_set_bypass_regmap,
+};
+
+static const struct regulator_desc arizona_ldo1_hc = {
+	.name = "LDO1",
+	.supply_name = "LDOVDD",
+	.type = REGULATOR_VOLTAGE,
+	.ops = &arizona_ldo1_hc_ops,
+
+	.bypass_reg = ARIZONA_LDO1_CONTROL_1,
+	.bypass_mask = ARIZONA_LDO1_BYPASS,
+	.min_uV = 900000,
+	.uV_step = 50000,
+	.n_voltages = 8,
+	.enable_time = 500,
+
+	.owner = THIS_MODULE,
+};
+
 static struct regulator_ops arizona_ldo1_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 	.map_voltage = regulator_map_voltage_linear,
@@ -81,6 +183,7 @@ static const struct regulator_init_data arizona_ldo1_default = {
 static __devinit int arizona_ldo1_probe(struct platform_device *pdev)
 {
 	struct arizona *arizona = dev_get_drvdata(pdev->dev.parent);
+	const struct regulator_desc *desc;
 	struct regulator_config config = { };
 	struct arizona_ldo1 *ldo1;
 	int ret;
@@ -100,9 +203,11 @@ static __devinit int arizona_ldo1_probe(struct platform_device *pdev)
 	 */
 	switch (arizona->type) {
 	case WM5102:
+		desc = &arizona_ldo1_hc;
 		ldo1->init_data = arizona_ldo1_dvfs;
 		break;
 	default:
+		desc = &arizona_ldo1;
 		ldo1->init_data = arizona_ldo1_default;
 		break;
 	}
@@ -121,7 +226,7 @@ static __devinit int arizona_ldo1_probe(struct platform_device *pdev)
 	else
 		config.init_data = &ldo1->init_data;
 
-	ldo1->regulator = regulator_register(&arizona_ldo1, &config);
+	ldo1->regulator = regulator_register(desc, &config);
 	if (IS_ERR(ldo1->regulator)) {
 		ret = PTR_ERR(ldo1->regulator);
 		dev_err(arizona->dev, "Failed to register LDO1 supply: %d\n",
diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index 7671a287dfee..ba26e99c388d 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -76,6 +76,7 @@
 #define ARIZONA_RATE_ESTIMATOR_3                 0x154
 #define ARIZONA_RATE_ESTIMATOR_4                 0x155
 #define ARIZONA_RATE_ESTIMATOR_5                 0x156
+#define ARIZONA_DYNAMIC_FREQUENCY_SCALING_1      0x161
 #define ARIZONA_FLL1_CONTROL_1                   0x171
 #define ARIZONA_FLL1_CONTROL_2                   0x172
 #define ARIZONA_FLL1_CONTROL_3                   0x173
@@ -110,6 +111,7 @@
 #define ARIZONA_FLL2_GPIO_CLOCK                  0x1AA
 #define ARIZONA_MIC_CHARGE_PUMP_1                0x200
 #define ARIZONA_LDO1_CONTROL_1                   0x210
+#define ARIZONA_LDO1_CONTROL_2                   0x212
 #define ARIZONA_LDO2_CONTROL_1                   0x213
 #define ARIZONA_MIC_BIAS_CTRL_1                  0x218
 #define ARIZONA_MIC_BIAS_CTRL_2                  0x219
@@ -1573,6 +1575,13 @@
 #define ARIZONA_SAMPLE_RATE_DETECT_D_SHIFT            0  /* SAMPLE_RATE_DETECT_D - [4:0] */
 #define ARIZONA_SAMPLE_RATE_DETECT_D_WIDTH            5  /* SAMPLE_RATE_DETECT_D - [4:0] */
 
+/*
+ * R353 (0x161) - Dynamic Frequency Scaling 1
+ */
+#define ARIZONA_SUBSYS_MAX_FREQ                  0x0001  /* SUBSYS_MAX_FREQ */
+#define ARIZONA_SUBSYS_MAX_FREQ_SHIFT                 0  /* SUBSYS_MAX_FREQ */
+#define ARIZONA_SUBSYS_MAX_FREQ_WIDTH                 1  /* SUBSYS_MAX_FREQ */
+
 /*
  * R369 (0x171) - FLL1 Control 1
  */
@@ -1888,6 +1897,13 @@
 #define ARIZONA_LDO1_ENA_SHIFT                        0  /* LDO1_ENA */
 #define ARIZONA_LDO1_ENA_WIDTH                        1  /* LDO1_ENA */
 
+/*
+ * R530 (0x212) - LDO1 Control 2
+ */
+#define ARIZONA_LDO1_HI_PWR                      0x0001  /* LDO1_HI_PWR */
+#define ARIZONA_LDO1_HI_PWR_SHIFT                     0  /* LDO1_HI_PWR */
+#define ARIZONA_LDO1_HI_PWR_WIDTH                     1  /* LDO1_HI_PWR */
+
 /*
  * R531 (0x213) - LDO2 Control 1
  */
-- 
cgit v1.2.3-55-g7522


From 1c9a9f59149e247e264db1fbf9f8ea3d5066eb64 Mon Sep 17 00:00:00 2001
From: Bill Pemberton
Date: Mon, 19 Nov 2012 13:19:21 -0500
Subject: kobject: remove CONFIG_HOTPLUG ifdefs

Remove conditional code based on CONFIG_HOTPLUG being false.  It's
always on now in preparation of it going away as an option.

Signed-off-by: Bill Pemberton <wfp5p@virginia.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/kobject.h | 18 ------------------
 1 file changed, 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index 1e57449395b1..939b11268c86 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -203,7 +203,6 @@ extern struct kobject *power_kobj;
 /* The global /sys/firmware/ kobject for people to chain off of */
 extern struct kobject *firmware_kobj;
 
-#if defined(CONFIG_HOTPLUG)
 int kobject_uevent(struct kobject *kobj, enum kobject_action action);
 int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 			char *envp[]);
@@ -213,22 +212,5 @@ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...);
 
 int kobject_action_type(const char *buf, size_t count,
 			enum kobject_action *type);
-#else
-static inline int kobject_uevent(struct kobject *kobj,
-				 enum kobject_action action)
-{ return 0; }
-static inline int kobject_uevent_env(struct kobject *kobj,
-				      enum kobject_action action,
-				      char *envp[])
-{ return 0; }
-
-static inline __printf(2, 3)
-int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...)
-{ return -ENOMEM; }
-
-static inline int kobject_action_type(const char *buf, size_t count,
-				      enum kobject_action *type)
-{ return -EINVAL; }
-#endif
 
 #endif /* _KOBJECT_H_ */
-- 
cgit v1.2.3-55-g7522


From 1974a042dd15f1f007a3a1a2dd7a23ca0e42c01d Mon Sep 17 00:00:00 2001
From: Padmavathi Venna
Date: Wed, 28 Nov 2012 16:17:48 +0530
Subject: ASoC: Samsung: Get I2S src_clk from clock alias id.

As the I2S src clks are registered with clkdev using generic
connection id, driver can get the clk name using generic id.
So the variable representing the array of rclk src clks is
deleted.

Signed-off-by: Padmavathi Venna <padma.v@samsung.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/linux/platform_data/asoc-s3c.h |  6 ------
 sound/soc/samsung/i2s.c                | 12 ++++++------
 2 files changed, 6 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/platform_data/asoc-s3c.h b/include/linux/platform_data/asoc-s3c.h
index aa9875f77c40..88272591a895 100644
--- a/include/linux/platform_data/asoc-s3c.h
+++ b/include/linux/platform_data/asoc-s3c.h
@@ -38,12 +38,6 @@ struct samsung_i2s {
 #define QUIRK_NEED_RSTCLR	(1 << 3)
 	/* Quirks of the I2S controller */
 	u32 quirks;
-
-	/*
-	 * Array of clock names that can be used to generate I2S signals.
-	 * Also corresponds to clocks of I2SMOD[10]
-	 */
-	const char **src_clk;
 	dma_addr_t idma_addr;
 };
 
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 547b9190c88f..aaf57b7caebb 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -49,8 +49,6 @@ struct i2s_dai {
 	struct clk *clk;
 	/* Clock for generating I2S signals */
 	struct clk *op_clk;
-	/* Array of clock names for op_clk */
-	const char **src_clk;
 	/* Pointer to the Primary_Fifo if this is Sec_Fifo, NULL otherwise */
 	struct i2s_dai *pri_dai;
 	/* Pointer to the Secondary_Fifo if it has one, NULL otherwise */
@@ -432,8 +430,12 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai,
 				}
 			}
 
-			i2s->op_clk = clk_get(&i2s->pdev->dev,
-						i2s->src_clk[clk_id]);
+			if (clk_id)
+				i2s->op_clk = clk_get(&i2s->pdev->dev,
+						"i2s_opclk1");
+			else
+				i2s->op_clk = clk_get(&i2s->pdev->dev,
+						"i2s_opclk0");
 			clk_prepare_enable(i2s->op_clk);
 			i2s->rclk_srcrate = clk_get_rate(i2s->op_clk);
 
@@ -1067,7 +1069,6 @@ static __devinit int samsung_i2s_probe(struct platform_device *pdev)
 		(struct s3c2410_dma_client *)&pri_dai->dma_capture;
 	pri_dai->dma_playback.channel = dma_pl_chan;
 	pri_dai->dma_capture.channel = dma_cp_chan;
-	pri_dai->src_clk = i2s_cfg->src_clk;
 	pri_dai->dma_playback.dma_size = 4;
 	pri_dai->dma_capture.dma_size = 4;
 	pri_dai->base = regs_base;
@@ -1088,7 +1089,6 @@ static __devinit int samsung_i2s_probe(struct platform_device *pdev)
 			(struct s3c2410_dma_client *)&sec_dai->dma_playback;
 		/* Use iDMA always if SysDMA not provided */
 		sec_dai->dma_playback.channel = dma_pl_sec_chan ? : -1;
-		sec_dai->src_clk = i2s_cfg->src_clk;
 		sec_dai->dma_playback.dma_size = 4;
 		sec_dai->base = regs_base;
 		sec_dai->quirks = quirks;
-- 
cgit v1.2.3-55-g7522


From 394b40f62d7ae18a1c48c13fc483b8193f8c3a98 Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk
Date: Tue, 27 Nov 2012 11:39:40 -0500
Subject: xen/acpi: Move the xen_running_on_version_or_later function.

As on ia64 builds we get:
include/xen/interface/version.h: In function 'xen_running_on_version_or_later':
include/xen/interface/version.h:76: error: implicit declaration of function 'HYPERVISOR_xen_version'

We can later on make this function exportable if there are
modules using part of it. For right now the only two users are
built-in.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/xen/enlighten.c        | 15 +++++++++++++++
 drivers/xen/xen-acpi-pad.c      |  1 +
 include/xen/interface/version.h | 18 ------------------
 include/xen/xen-ops.h           |  1 +
 4 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index eb0edff5499b..3325cd9f7790 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -223,6 +223,21 @@ static void __init xen_banner(void)
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
+/* Check if running on Xen version (major, minor) or later */
+bool
+xen_running_on_version_or_later(unsigned int major, unsigned int minor)
+{
+	unsigned int version;
+
+	if (!xen_domain())
+		return false;
+
+	version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
+		((version >> 16) > major))
+		return true;
+	return false;
+}
 
 #define CPUID_THERM_POWER_LEAF 6
 #define APERFMPERF_PRESENT 0
diff --git a/drivers/xen/xen-acpi-pad.c b/drivers/xen/xen-acpi-pad.c
index f23ecf380088..da39191e7278 100644
--- a/drivers/xen/xen-acpi-pad.c
+++ b/drivers/xen/xen-acpi-pad.c
@@ -20,6 +20,7 @@
 #include <acpi/acpi_drivers.h>
 #include <asm/xen/hypercall.h>
 #include <xen/interface/version.h>
+#include <xen/xen-ops.h>
 
 #define ACPI_PROCESSOR_AGGREGATOR_CLASS	"acpi_pad"
 #define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator"
diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h
index 53553f046497..7ff6498679a3 100644
--- a/include/xen/interface/version.h
+++ b/include/xen/interface/version.h
@@ -63,22 +63,4 @@ struct xen_feature_info {
 /* arg == xen_domain_handle_t. */
 #define XENVER_guest_handle 8
 
-/* Declares the xen_domain() macros. */
-#include <xen/xen.h>
-
-/* Check if running on Xen version (major, minor) or later */
-static inline bool
-xen_running_on_version_or_later(unsigned int major, unsigned int minor)
-{
-	unsigned int version;
-
-	if (!xen_domain())
-		return false;
-
-	version = HYPERVISOR_xen_version(XENVER_version, NULL);
-	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
-		((version >> 16) > major))
-		return true;
-	return false;
-}
 #endif /* __XEN_PUBLIC_VERSION_H__ */
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 6a198e46ab6e..6170abd53d0b 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -29,4 +29,5 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 			       unsigned long mfn, int nr,
 			       pgprot_t prot, unsigned domid);
 
+bool xen_running_on_version_or_later(unsigned int major, unsigned int minor);
 #endif /* INCLUDE_XEN_OPS_H */
-- 
cgit v1.2.3-55-g7522


From f791be492f76dea7b0641ed227a60eeb2fa7e255 Mon Sep 17 00:00:00 2001
From: Bill Pemberton
Date: Mon, 19 Nov 2012 13:23:04 -0500
Subject: mfd: remove use of __devinit

CONFIG_HOTPLUG is going away as an option so __devinit is no longer
needed.

Signed-off-by: Bill Pemberton <wfp5p@virginia.edu>
Cc: Srinidhi Kasagar <srinidhi.kasagar@stericsson.com>
Cc: Peter Tyser <ptyser@xes-inc.com>
Cc: Daniel Walker <dwalker@fifo99.com>
Cc: Bryan Huntsman <bryanh@codeaurora.org>
Acked-by: David Brown <davidb@codeaurora.org>
Acked-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/mfd/88pm800.c             |  8 ++++----
 drivers/mfd/88pm805.c             |  6 +++---
 drivers/mfd/88pm80x.c             |  2 +-
 drivers/mfd/88pm860x-core.c       | 30 +++++++++++++++---------------
 drivers/mfd/ab3100-core.c         |  4 ++--
 drivers/mfd/ab8500-core.c         |  2 +-
 drivers/mfd/ab8500-debugfs.c      |  2 +-
 drivers/mfd/ab8500-gpadc.c        |  2 +-
 drivers/mfd/ab8500-sysctrl.c      |  2 +-
 drivers/mfd/adp5520.c             |  2 +-
 drivers/mfd/arizona-core.c        |  2 +-
 drivers/mfd/arizona-i2c.c         |  2 +-
 drivers/mfd/arizona-spi.c         |  2 +-
 drivers/mfd/cs5535-mfd.c          |  4 ++--
 drivers/mfd/da903x.c              |  6 +++---
 drivers/mfd/da9052-core.c         |  2 +-
 drivers/mfd/da9052-i2c.c          |  2 +-
 drivers/mfd/da9052-spi.c          |  2 +-
 drivers/mfd/da9055-core.c         |  2 +-
 drivers/mfd/da9055-i2c.c          |  2 +-
 drivers/mfd/db8500-prcmu.c        |  2 +-
 drivers/mfd/ezx-pcap.c            |  4 ++--
 drivers/mfd/htc-i2cpld.c          | 12 ++++++------
 drivers/mfd/intel_msic.c          |  4 ++--
 drivers/mfd/janz-cmodio.c         |  6 +++---
 drivers/mfd/jz4740-adc.c          |  2 +-
 drivers/mfd/lm3533-core.c         | 12 ++++++------
 drivers/mfd/lpc_ich.c             | 14 +++++++-------
 drivers/mfd/lpc_sch.c             |  2 +-
 drivers/mfd/max8907.c             |  2 +-
 drivers/mfd/max8925-core.c        |  4 ++--
 drivers/mfd/max8925-i2c.c         |  2 +-
 drivers/mfd/omap-usb-host.c       |  2 +-
 drivers/mfd/omap-usb-tll.c        |  2 +-
 drivers/mfd/palmas.c              |  4 ++--
 drivers/mfd/pcf50633-adc.c        |  2 +-
 drivers/mfd/pcf50633-core.c       |  2 +-
 drivers/mfd/pm8921-core.c         |  4 ++--
 drivers/mfd/pm8xxx-irq.c          |  2 +-
 drivers/mfd/rc5t583.c             |  2 +-
 drivers/mfd/rdc321x-southbridge.c |  2 +-
 drivers/mfd/sm501.c               | 10 +++++-----
 drivers/mfd/sta2x11-mfd.c         |  4 ++--
 drivers/mfd/stmpe-i2c.c           |  2 +-
 drivers/mfd/stmpe-spi.c           |  2 +-
 drivers/mfd/syscon.c              |  2 +-
 drivers/mfd/tc3589x.c             |  4 ++--
 drivers/mfd/tc6387xb.c            |  2 +-
 drivers/mfd/tc6393xb.c            |  2 +-
 drivers/mfd/ti-ssp.c              |  2 +-
 drivers/mfd/timberdale.c          |  2 +-
 drivers/mfd/tps6105x.c            |  4 ++--
 drivers/mfd/tps65090.c            |  4 ++--
 drivers/mfd/tps65217.c            |  2 +-
 drivers/mfd/tps6586x.c            |  6 +++---
 drivers/mfd/tps65910.c            |  6 +++---
 drivers/mfd/tps65911-comparator.c |  2 +-
 drivers/mfd/tps65912-spi.c        |  2 +-
 drivers/mfd/twl-core.c            |  2 +-
 drivers/mfd/twl4030-audio.c       |  2 +-
 drivers/mfd/twl4030-madc.c        |  2 +-
 drivers/mfd/twl4030-power.c       | 20 ++++++++++----------
 drivers/mfd/vx855.c               |  2 +-
 drivers/mfd/wl1273-core.c         |  2 +-
 drivers/mfd/wm831x-spi.c          |  2 +-
 drivers/mfd/wm8994-core.c         |  4 ++--
 include/linux/mfd/88pm80x.h       |  2 +-
 include/linux/mfd/abx500/ab8500.h |  2 +-
 include/linux/mfd/pm8xxx/irq.h    |  4 ++--
 69 files changed, 138 insertions(+), 138 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/88pm800.c b/drivers/mfd/88pm800.c
index 321a50cdebf9..6746ecd260ad 100644
--- a/drivers/mfd/88pm800.c
+++ b/drivers/mfd/88pm800.c
@@ -248,7 +248,7 @@ static const struct regmap_irq pm800_irqs[] = {
 	},
 };
 
-static int __devinit device_gpadc_init(struct pm80x_chip *chip,
+static int device_gpadc_init(struct pm80x_chip *chip,
 				       struct pm80x_platform_data *pdata)
 {
 	struct pm80x_subchip *subchip = chip->subchip;
@@ -315,7 +315,7 @@ out:
 	return ret;
 }
 
-static int __devinit device_irq_init_800(struct pm80x_chip *chip)
+static int device_irq_init_800(struct pm80x_chip *chip)
 {
 	struct regmap *map = chip->regmap;
 	unsigned long flags = IRQF_TRIGGER_FALLING | IRQF_ONESHOT;
@@ -415,7 +415,7 @@ static void pm800_pages_exit(struct pm80x_chip *chip)
 	}
 }
 
-static int __devinit device_800_init(struct pm80x_chip *chip,
+static int device_800_init(struct pm80x_chip *chip,
 				     struct pm80x_platform_data *pdata)
 {
 	int ret, pmic_id;
@@ -499,7 +499,7 @@ out:
 	return ret;
 }
 
-static int __devinit pm800_probe(struct i2c_client *client,
+static int pm800_probe(struct i2c_client *client,
 				 const struct i2c_device_id *id)
 {
 	int ret = 0;
diff --git a/drivers/mfd/88pm805.c b/drivers/mfd/88pm805.c
index 41e0488b4e3b..13c09941dc2c 100644
--- a/drivers/mfd/88pm805.c
+++ b/drivers/mfd/88pm805.c
@@ -135,7 +135,7 @@ static struct regmap_irq pm805_irqs[] = {
 	},
 };
 
-static int __devinit device_irq_init_805(struct pm80x_chip *chip)
+static int device_irq_init_805(struct pm80x_chip *chip)
 {
 	struct regmap *map = chip->regmap;
 	unsigned long flags = IRQF_TRIGGER_FALLING | IRQF_ONESHOT;
@@ -189,7 +189,7 @@ static struct regmap_irq_chip pm805_irq_chip = {
 	.ack_base = PM805_INT_STATUS1,
 };
 
-static int __devinit device_805_init(struct pm80x_chip *chip)
+static int device_805_init(struct pm80x_chip *chip)
 {
 	int ret = 0;
 	unsigned int val;
@@ -232,7 +232,7 @@ out_irq_init:
 	return ret;
 }
 
-static int __devinit pm805_probe(struct i2c_client *client,
+static int pm805_probe(struct i2c_client *client,
 				 const struct i2c_device_id *id)
 {
 	int ret = 0;
diff --git a/drivers/mfd/88pm80x.c b/drivers/mfd/88pm80x.c
index cd0bf527d764..1adb355d86d1 100644
--- a/drivers/mfd/88pm80x.c
+++ b/drivers/mfd/88pm80x.c
@@ -31,7 +31,7 @@ const struct regmap_config pm80x_regmap_config = {
 };
 EXPORT_SYMBOL_GPL(pm80x_regmap_config);
 
-int __devinit pm80x_init(struct i2c_client *client,
+int pm80x_init(struct i2c_client *client,
 				 const struct i2c_device_id *id)
 {
 	struct pm80x_chip *chip;
diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c
index c2d5595e49d0..ad36ad70a0c2 100644
--- a/drivers/mfd/88pm860x-core.c
+++ b/drivers/mfd/88pm860x-core.c
@@ -565,7 +565,7 @@ static struct irq_domain_ops pm860x_irq_domain_ops = {
 	.xlate	= irq_domain_xlate_onetwocell,
 };
 
-static int __devinit device_irq_init(struct pm860x_chip *chip,
+static int device_irq_init(struct pm860x_chip *chip,
 				     struct pm860x_platform_data *pdata)
 {
 	struct i2c_client *i2c = (chip->id == CHIP_PM8607) ? chip->client \
@@ -730,7 +730,7 @@ out:
 }
 EXPORT_SYMBOL(pm8606_osc_disable);
 
-static void __devinit device_osc_init(struct i2c_client *i2c)
+static void device_osc_init(struct i2c_client *i2c)
 {
 	struct pm860x_chip *chip = i2c_get_clientdata(i2c);
 
@@ -745,7 +745,7 @@ static void __devinit device_osc_init(struct i2c_client *i2c)
 	chip->osc_status = PM8606_REF_GP_OSC_OFF;
 }
 
-static void __devinit device_bk_init(struct pm860x_chip *chip,
+static void device_bk_init(struct pm860x_chip *chip,
 				     struct pm860x_platform_data *pdata)
 {
 	int ret, i;
@@ -765,7 +765,7 @@ static void __devinit device_bk_init(struct pm860x_chip *chip,
 		dev_err(chip->dev, "Failed to add backlight subdev\n");
 }
 
-static void __devinit device_led_init(struct pm860x_chip *chip,
+static void device_led_init(struct pm860x_chip *chip,
 				      struct pm860x_platform_data *pdata)
 {
 	int ret, i;
@@ -787,7 +787,7 @@ static void __devinit device_led_init(struct pm860x_chip *chip,
 	}
 }
 
-static void __devinit device_regulator_init(struct pm860x_chip *chip,
+static void device_regulator_init(struct pm860x_chip *chip,
 					    struct pm860x_platform_data *pdata)
 {
 	int ret;
@@ -866,7 +866,7 @@ static void __devinit device_regulator_init(struct pm860x_chip *chip,
 	}
 }
 
-static void __devinit device_rtc_init(struct pm860x_chip *chip,
+static void device_rtc_init(struct pm860x_chip *chip,
 				      struct pm860x_platform_data *pdata)
 {
 	int ret;
@@ -885,7 +885,7 @@ static void __devinit device_rtc_init(struct pm860x_chip *chip,
 		dev_err(chip->dev, "Failed to add rtc subdev\n");
 }
 
-static void __devinit device_touch_init(struct pm860x_chip *chip,
+static void device_touch_init(struct pm860x_chip *chip,
 					struct pm860x_platform_data *pdata)
 {
 	int ret;
@@ -904,7 +904,7 @@ static void __devinit device_touch_init(struct pm860x_chip *chip,
 		dev_err(chip->dev, "Failed to add touch subdev\n");
 }
 
-static void __devinit device_power_init(struct pm860x_chip *chip,
+static void device_power_init(struct pm860x_chip *chip,
 					struct pm860x_platform_data *pdata)
 {
 	int ret;
@@ -951,7 +951,7 @@ static void __devinit device_power_init(struct pm860x_chip *chip,
 	}
 }
 
-static void __devinit device_onkey_init(struct pm860x_chip *chip,
+static void device_onkey_init(struct pm860x_chip *chip,
 					struct pm860x_platform_data *pdata)
 {
 	int ret;
@@ -965,7 +965,7 @@ static void __devinit device_onkey_init(struct pm860x_chip *chip,
 		dev_err(chip->dev, "Failed to add onkey subdev\n");
 }
 
-static void __devinit device_codec_init(struct pm860x_chip *chip,
+static void device_codec_init(struct pm860x_chip *chip,
 					struct pm860x_platform_data *pdata)
 {
 	int ret;
@@ -979,7 +979,7 @@ static void __devinit device_codec_init(struct pm860x_chip *chip,
 		dev_err(chip->dev, "Failed to add codec subdev\n");
 }
 
-static void __devinit device_8607_init(struct pm860x_chip *chip,
+static void device_8607_init(struct pm860x_chip *chip,
 				       struct i2c_client *i2c,
 				       struct pm860x_platform_data *pdata)
 {
@@ -1040,7 +1040,7 @@ out:
 	return;
 }
 
-static void __devinit device_8606_init(struct pm860x_chip *chip,
+static void device_8606_init(struct pm860x_chip *chip,
 				       struct i2c_client *i2c,
 				       struct pm860x_platform_data *pdata)
 {
@@ -1049,7 +1049,7 @@ static void __devinit device_8606_init(struct pm860x_chip *chip,
 	device_led_init(chip, pdata);
 }
 
-static int __devinit pm860x_device_init(struct pm860x_chip *chip,
+static int pm860x_device_init(struct pm860x_chip *chip,
 					struct pm860x_platform_data *pdata)
 {
 	chip->core_irq = 0;
@@ -1109,7 +1109,7 @@ static struct regmap_config pm860x_regmap_config = {
 	.val_bits = 8,
 };
 
-static int __devinit pm860x_dt_init(struct device_node *np,
+static int pm860x_dt_init(struct device_node *np,
 				    struct device *dev,
 				    struct pm860x_platform_data *pdata)
 {
@@ -1127,7 +1127,7 @@ static int __devinit pm860x_dt_init(struct device_node *np,
 	return 0;
 }
 
-static int __devinit pm860x_probe(struct i2c_client *client,
+static int pm860x_probe(struct i2c_client *client,
 				  const struct i2c_device_id *id)
 {
 	struct pm860x_platform_data *pdata = client->dev.platform_data;
diff --git a/drivers/mfd/ab3100-core.c b/drivers/mfd/ab3100-core.c
index 8355d4ee6edd..84b2303bc770 100644
--- a/drivers/mfd/ab3100-core.c
+++ b/drivers/mfd/ab3100-core.c
@@ -708,7 +708,7 @@ ab3100_init_settings[] = {
 	},
 };
 
-static int __devinit ab3100_setup(struct ab3100 *ab3100)
+static int ab3100_setup(struct ab3100 *ab3100)
 {
 	int err = 0;
 	int i;
@@ -857,7 +857,7 @@ static const struct ab_family_id ids[] __devinitconst = {
 	},
 };
 
-static int __devinit ab3100_probe(struct i2c_client *client,
+static int ab3100_probe(struct i2c_client *client,
 				  const struct i2c_device_id *id)
 {
 	struct ab3100 *ab3100;
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index 01a0e01f6a6c..43245f2ce758 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -1248,7 +1248,7 @@ static struct attribute_group ab9540_attr_group = {
 	.attrs	= ab9540_sysfs_entries,
 };
 
-static int __devinit ab8500_probe(struct platform_device *pdev)
+static int ab8500_probe(struct platform_device *pdev)
 {
 	static char *switch_off_status[] = {
 		"Swoff bit programming",
diff --git a/drivers/mfd/ab8500-debugfs.c b/drivers/mfd/ab8500-debugfs.c
index efdbc7bebd01..44843680d982 100644
--- a/drivers/mfd/ab8500-debugfs.c
+++ b/drivers/mfd/ab8500-debugfs.c
@@ -552,7 +552,7 @@ static struct dentry *ab8500_bank_file;
 static struct dentry *ab8500_address_file;
 static struct dentry *ab8500_val_file;
 
-static int __devinit ab8500_debug_probe(struct platform_device *plf)
+static int ab8500_debug_probe(struct platform_device *plf)
 {
 	debug_bank = AB8500_MISC;
 	debug_address = AB8500_REV_REG & 0x00FF;
diff --git a/drivers/mfd/ab8500-gpadc.c b/drivers/mfd/ab8500-gpadc.c
index 97daf61f068c..c5e168e3ef11 100644
--- a/drivers/mfd/ab8500-gpadc.c
+++ b/drivers/mfd/ab8500-gpadc.c
@@ -571,7 +571,7 @@ static void ab8500_gpadc_read_calibration_data(struct ab8500_gpadc *gpadc)
 		gpadc->cal_data[ADC_INPUT_VBAT].offset);
 }
 
-static int __devinit ab8500_gpadc_probe(struct platform_device *pdev)
+static int ab8500_gpadc_probe(struct platform_device *pdev)
 {
 	int ret = 0;
 	struct ab8500_gpadc *gpadc;
diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c
index d8cc157af3e8..499263c3110a 100644
--- a/drivers/mfd/ab8500-sysctrl.c
+++ b/drivers/mfd/ab8500-sysctrl.c
@@ -49,7 +49,7 @@ int ab8500_sysctrl_write(u16 reg, u8 mask, u8 value)
 		(u8)(reg & 0xFF), mask, value);
 }
 
-static int __devinit ab8500_sysctrl_probe(struct platform_device *pdev)
+static int ab8500_sysctrl_probe(struct platform_device *pdev)
 {
 	sysctrl_dev = &pdev->dev;
 	return 0;
diff --git a/drivers/mfd/adp5520.c b/drivers/mfd/adp5520.c
index f664a52687d5..f2f9d8ff6416 100644
--- a/drivers/mfd/adp5520.c
+++ b/drivers/mfd/adp5520.c
@@ -203,7 +203,7 @@ static int adp5520_remove_subdevs(struct adp5520_chip *chip)
 	return device_for_each_child(chip->dev, NULL, __remove_subdev);
 }
 
-static int __devinit adp5520_probe(struct i2c_client *client,
+static int adp5520_probe(struct i2c_client *client,
 					const struct i2c_device_id *id)
 {
 	struct adp5520_platform_data *pdata = client->dev.platform_data;
diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c
index 1b48f2094806..47e711674739 100644
--- a/drivers/mfd/arizona-core.c
+++ b/drivers/mfd/arizona-core.c
@@ -285,7 +285,7 @@ static struct mfd_cell wm5110_devs[] = {
 	{ .name = "wm5110-codec" },
 };
 
-int __devinit arizona_dev_init(struct arizona *arizona)
+int arizona_dev_init(struct arizona *arizona)
 {
 	struct device *dev = arizona->dev;
 	const char *type_name;
diff --git a/drivers/mfd/arizona-i2c.c b/drivers/mfd/arizona-i2c.c
index 43d164736fcb..aaf1a69134df 100644
--- a/drivers/mfd/arizona-i2c.c
+++ b/drivers/mfd/arizona-i2c.c
@@ -22,7 +22,7 @@
 
 #include "arizona.h"
 
-static __devinit int arizona_i2c_probe(struct i2c_client *i2c,
+static int arizona_i2c_probe(struct i2c_client *i2c,
 					  const struct i2c_device_id *id)
 {
 	struct arizona *arizona;
diff --git a/drivers/mfd/arizona-spi.c b/drivers/mfd/arizona-spi.c
index cc79b824f706..9663cafdb7ff 100644
--- a/drivers/mfd/arizona-spi.c
+++ b/drivers/mfd/arizona-spi.c
@@ -22,7 +22,7 @@
 
 #include "arizona.h"
 
-static int __devinit arizona_spi_probe(struct spi_device *spi)
+static int arizona_spi_probe(struct spi_device *spi)
 {
 	const struct spi_device_id *id = spi_get_device_id(spi);
 	struct arizona *arizona;
diff --git a/drivers/mfd/cs5535-mfd.c b/drivers/mfd/cs5535-mfd.c
index 5d3878ad39a6..0779b13a7dd1 100644
--- a/drivers/mfd/cs5535-mfd.c
+++ b/drivers/mfd/cs5535-mfd.c
@@ -113,7 +113,7 @@ static __devinitdata struct mfd_cell cs5535_mfd_cells[] = {
 };
 
 #ifdef CONFIG_OLPC
-static void __devinit cs5535_clone_olpc_cells(void)
+static void cs5535_clone_olpc_cells(void)
 {
 	const char *acpi_clones[] = { "olpc-xo1-pm-acpi", "olpc-xo1-sci-acpi" };
 
@@ -126,7 +126,7 @@ static void __devinit cs5535_clone_olpc_cells(void)
 static void cs5535_clone_olpc_cells(void) { }
 #endif
 
-static int __devinit cs5535_mfd_probe(struct pci_dev *pdev,
+static int cs5535_mfd_probe(struct pci_dev *pdev,
 		const struct pci_device_id *id)
 {
 	int err, i;
diff --git a/drivers/mfd/da903x.c b/drivers/mfd/da903x.c
index c715475df377..5fa1e91a9532 100644
--- a/drivers/mfd/da903x.c
+++ b/drivers/mfd/da903x.c
@@ -246,7 +246,7 @@ int da903x_query_status(struct device *dev, unsigned int sbits)
 }
 EXPORT_SYMBOL(da903x_query_status);
 
-static int __devinit da9030_init_chip(struct da903x_chip *chip)
+static int da9030_init_chip(struct da903x_chip *chip)
 {
 	uint8_t chip_id;
 	int err;
@@ -459,7 +459,7 @@ static int da903x_remove_subdevs(struct da903x_chip *chip)
 	return device_for_each_child(chip->dev, NULL, __remove_subdev);
 }
 
-static int __devinit da903x_add_subdevs(struct da903x_chip *chip,
+static int da903x_add_subdevs(struct da903x_chip *chip,
 					struct da903x_platform_data *pdata)
 {
 	struct da903x_subdev_info *subdev;
@@ -491,7 +491,7 @@ failed:
 	return ret;
 }
 
-static int __devinit da903x_probe(struct i2c_client *client,
+static int da903x_probe(struct i2c_client *client,
 				  const struct i2c_device_id *id)
 {
 	struct da903x_platform_data *pdata = client->dev.platform_data;
diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c
index a0a62b24621b..c71c4a247186 100644
--- a/drivers/mfd/da9052-core.c
+++ b/drivers/mfd/da9052-core.c
@@ -769,7 +769,7 @@ struct regmap_config da9052_regmap_config = {
 };
 EXPORT_SYMBOL_GPL(da9052_regmap_config);
 
-int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id)
+int da9052_device_init(struct da9052 *da9052, u8 chip_id)
 {
 	struct da9052_pdata *pdata = da9052->dev->platform_data;
 	int ret;
diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c
index 8af0f0c5cefe..96f66ed8dbfc 100644
--- a/drivers/mfd/da9052-i2c.c
+++ b/drivers/mfd/da9052-i2c.c
@@ -64,7 +64,7 @@ static const struct of_device_id dialog_dt_ids[] = {
 };
 #endif
 
-static int __devinit da9052_i2c_probe(struct i2c_client *client,
+static int da9052_i2c_probe(struct i2c_client *client,
 				       const struct i2c_device_id *id)
 {
 	struct da9052 *da9052;
diff --git a/drivers/mfd/da9052-spi.c b/drivers/mfd/da9052-spi.c
index cbcc9bebbbe1..1ad324373c97 100644
--- a/drivers/mfd/da9052-spi.c
+++ b/drivers/mfd/da9052-spi.c
@@ -21,7 +21,7 @@
 
 #include <linux/mfd/da9052/da9052.h>
 
-static int __devinit da9052_spi_probe(struct spi_device *spi)
+static int da9052_spi_probe(struct spi_device *spi)
 {
 	int ret;
 	const struct spi_device_id *id = spi_get_device_id(spi);
diff --git a/drivers/mfd/da9055-core.c b/drivers/mfd/da9055-core.c
index ff6c77f392bd..6f5a4984f0aa 100644
--- a/drivers/mfd/da9055-core.c
+++ b/drivers/mfd/da9055-core.c
@@ -377,7 +377,7 @@ static struct regmap_irq_chip da9055_regmap_irq_chip = {
 	.num_irqs = ARRAY_SIZE(da9055_irqs),
 };
 
-int __devinit da9055_device_init(struct da9055 *da9055)
+int da9055_device_init(struct da9055 *da9055)
 {
 	struct da9055_pdata *pdata = da9055->dev->platform_data;
 	int ret;
diff --git a/drivers/mfd/da9055-i2c.c b/drivers/mfd/da9055-i2c.c
index dbaca7bc36da..7778d042fb5d 100644
--- a/drivers/mfd/da9055-i2c.c
+++ b/drivers/mfd/da9055-i2c.c
@@ -18,7 +18,7 @@
 
 #include <linux/mfd/da9055/core.h>
 
-static int __devinit da9055_i2c_probe(struct i2c_client *i2c,
+static int da9055_i2c_probe(struct i2c_client *i2c,
 				      const struct i2c_device_id *id)
 {
 	struct da9055 *da9055;
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index 00b8b0f3dfb6..084a58776837 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -3034,7 +3034,7 @@ static struct mfd_cell db8500_prcmu_devs[] = {
  * prcmu_fw_init - arch init call for the Linux PRCMU fw init logic
  *
  */
-static int __devinit db8500_prcmu_probe(struct platform_device *pdev)
+static int db8500_prcmu_probe(struct platform_device *pdev)
 {
 	struct ab8500_platform_data *ab8500_platdata = pdev->dev.platform_data;
 	struct device_node *np = pdev->dev.of_node;
diff --git a/drivers/mfd/ezx-pcap.c b/drivers/mfd/ezx-pcap.c
index d7e4de041526..d81505e50d12 100644
--- a/drivers/mfd/ezx-pcap.c
+++ b/drivers/mfd/ezx-pcap.c
@@ -371,7 +371,7 @@ static int pcap_remove_subdev(struct device *dev, void *unused)
 	return 0;
 }
 
-static int __devinit pcap_add_subdev(struct pcap_chip *pcap,
+static int pcap_add_subdev(struct pcap_chip *pcap,
 						struct pcap_subdev *subdev)
 {
 	struct platform_device *pdev;
@@ -420,7 +420,7 @@ static int __devexit ezx_pcap_remove(struct spi_device *spi)
 	return 0;
 }
 
-static int __devinit ezx_pcap_probe(struct spi_device *spi)
+static int ezx_pcap_probe(struct spi_device *spi)
 {
 	struct pcap_platform_data *pdata = spi->dev.platform_data;
 	struct pcap_chip *pcap;
diff --git a/drivers/mfd/htc-i2cpld.c b/drivers/mfd/htc-i2cpld.c
index d55065cc324c..324187c0c124 100644
--- a/drivers/mfd/htc-i2cpld.c
+++ b/drivers/mfd/htc-i2cpld.c
@@ -327,7 +327,7 @@ static void htcpld_chip_reset(struct i2c_client *client)
 		client, (chip_data->cache_out = chip_data->reset));
 }
 
-static int __devinit htcpld_setup_chip_irq(
+static int htcpld_setup_chip_irq(
 		struct platform_device *pdev,
 		int chip_index)
 {
@@ -361,7 +361,7 @@ static int __devinit htcpld_setup_chip_irq(
 	return ret;
 }
 
-static int __devinit htcpld_register_chip_i2c(
+static int htcpld_register_chip_i2c(
 		struct platform_device *pdev,
 		int chip_index)
 {
@@ -419,7 +419,7 @@ static int __devinit htcpld_register_chip_i2c(
 	return 0;
 }
 
-static void __devinit htcpld_unregister_chip_i2c(
+static void htcpld_unregister_chip_i2c(
 		struct platform_device *pdev,
 		int chip_index)
 {
@@ -434,7 +434,7 @@ static void __devinit htcpld_unregister_chip_i2c(
 		i2c_unregister_device(chip->client);
 }
 
-static int __devinit htcpld_register_chip_gpio(
+static int htcpld_register_chip_gpio(
 		struct platform_device *pdev,
 		int chip_index)
 {
@@ -501,7 +501,7 @@ static int __devinit htcpld_register_chip_gpio(
 	return 0;
 }
 
-static int __devinit htcpld_setup_chips(struct platform_device *pdev)
+static int htcpld_setup_chips(struct platform_device *pdev)
 {
 	struct htcpld_data *htcpld;
 	struct device *dev = &pdev->dev;
@@ -563,7 +563,7 @@ static int __devinit htcpld_setup_chips(struct platform_device *pdev)
 	return 0;
 }
 
-static int __devinit htcpld_core_probe(struct platform_device *pdev)
+static int htcpld_core_probe(struct platform_device *pdev)
 {
 	struct htcpld_data *htcpld;
 	struct device *dev = &pdev->dev;
diff --git a/drivers/mfd/intel_msic.c b/drivers/mfd/intel_msic.c
index c5f478eb4e18..438ac3df166b 100644
--- a/drivers/mfd/intel_msic.c
+++ b/drivers/mfd/intel_msic.c
@@ -306,7 +306,7 @@ int intel_msic_irq_read(struct intel_msic *msic, unsigned short reg, u8 *val)
 }
 EXPORT_SYMBOL_GPL(intel_msic_irq_read);
 
-static int __devinit intel_msic_init_devices(struct intel_msic *msic)
+static int intel_msic_init_devices(struct intel_msic *msic)
 {
 	struct platform_device *pdev = msic->pdev;
 	struct intel_msic_platform_data *pdata = pdev->dev.platform_data;
@@ -375,7 +375,7 @@ static void __devexit intel_msic_remove_devices(struct intel_msic *msic)
 		gpio_free(pdata->ocd->gpio);
 }
 
-static int __devinit intel_msic_probe(struct platform_device *pdev)
+static int intel_msic_probe(struct platform_device *pdev)
 {
 	struct intel_msic_platform_data *pdata = pdev->dev.platform_data;
 	struct intel_msic *msic;
diff --git a/drivers/mfd/janz-cmodio.c b/drivers/mfd/janz-cmodio.c
index 1a3627784246..55c479e57aad 100644
--- a/drivers/mfd/janz-cmodio.c
+++ b/drivers/mfd/janz-cmodio.c
@@ -63,7 +63,7 @@ struct cmodio_device {
  * Subdevices using the mfd-core API
  */
 
-static int __devinit cmodio_setup_subdevice(struct cmodio_device *priv,
+static int cmodio_setup_subdevice(struct cmodio_device *priv,
 					    char *name, unsigned int devno,
 					    unsigned int modno)
 {
@@ -120,7 +120,7 @@ static int __devinit cmodio_setup_subdevice(struct cmodio_device *priv,
 }
 
 /* Probe each submodule using kernel parameters */
-static int __devinit cmodio_probe_submodules(struct cmodio_device *priv)
+static int cmodio_probe_submodules(struct cmodio_device *priv)
 {
 	struct pci_dev *pdev = priv->pdev;
 	unsigned int num_probed = 0;
@@ -177,7 +177,7 @@ static const struct attribute_group cmodio_sysfs_attr_group = {
  * PCI Driver
  */
 
-static int __devinit cmodio_pci_probe(struct pci_dev *dev,
+static int cmodio_pci_probe(struct pci_dev *dev,
 				      const struct pci_device_id *id)
 {
 	struct cmodio_device *priv;
diff --git a/drivers/mfd/jz4740-adc.c b/drivers/mfd/jz4740-adc.c
index 9aed2a66180e..c0d38c597f0c 100644
--- a/drivers/mfd/jz4740-adc.c
+++ b/drivers/mfd/jz4740-adc.c
@@ -202,7 +202,7 @@ static struct mfd_cell jz4740_adc_cells[] = {
 	},
 };
 
-static int __devinit jz4740_adc_probe(struct platform_device *pdev)
+static int jz4740_adc_probe(struct platform_device *pdev)
 {
 	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c
index e7aa2a5a826b..2b74508655d4 100644
--- a/drivers/mfd/lm3533-core.c
+++ b/drivers/mfd/lm3533-core.c
@@ -382,7 +382,7 @@ static struct attribute_group lm3533_attribute_group = {
 	.attrs		= lm3533_attributes
 };
 
-static int __devinit lm3533_device_als_init(struct lm3533 *lm3533)
+static int lm3533_device_als_init(struct lm3533 *lm3533)
 {
 	struct lm3533_platform_data *pdata = lm3533->dev->platform_data;
 	int ret;
@@ -405,7 +405,7 @@ static int __devinit lm3533_device_als_init(struct lm3533 *lm3533)
 	return 0;
 }
 
-static int __devinit lm3533_device_bl_init(struct lm3533 *lm3533)
+static int lm3533_device_bl_init(struct lm3533 *lm3533)
 {
 	struct lm3533_platform_data *pdata = lm3533->dev->platform_data;
 	int i;
@@ -434,7 +434,7 @@ static int __devinit lm3533_device_bl_init(struct lm3533 *lm3533)
 	return 0;
 }
 
-static int __devinit lm3533_device_led_init(struct lm3533 *lm3533)
+static int lm3533_device_led_init(struct lm3533 *lm3533)
 {
 	struct lm3533_platform_data *pdata = lm3533->dev->platform_data;
 	int i;
@@ -463,7 +463,7 @@ static int __devinit lm3533_device_led_init(struct lm3533 *lm3533)
 	return 0;
 }
 
-static int __devinit lm3533_device_setup(struct lm3533 *lm3533,
+static int lm3533_device_setup(struct lm3533 *lm3533,
 					struct lm3533_platform_data *pdata)
 {
 	int ret;
@@ -479,7 +479,7 @@ static int __devinit lm3533_device_setup(struct lm3533 *lm3533,
 	return 0;
 }
 
-static int __devinit lm3533_device_init(struct lm3533 *lm3533)
+static int lm3533_device_init(struct lm3533 *lm3533)
 {
 	struct lm3533_platform_data *pdata = lm3533->dev->platform_data;
 	int ret;
@@ -596,7 +596,7 @@ static struct regmap_config regmap_config = {
 	.precious_reg	= lm3533_precious_register,
 };
 
-static int __devinit lm3533_i2c_probe(struct i2c_client *i2c,
+static int lm3533_i2c_probe(struct i2c_client *i2c,
 					const struct i2c_device_id *id)
 {
 	struct lm3533 *lm3533;
diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index a43c73ac25b0..99891752c338 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -672,7 +672,7 @@ static void lpc_ich_restore_config_space(struct pci_dev *dev)
 	}
 }
 
-static void __devinit lpc_ich_enable_acpi_space(struct pci_dev *dev)
+static void lpc_ich_enable_acpi_space(struct pci_dev *dev)
 {
 	u8 reg_save;
 
@@ -681,7 +681,7 @@ static void __devinit lpc_ich_enable_acpi_space(struct pci_dev *dev)
 	lpc_ich_acpi_save = reg_save;
 }
 
-static void __devinit lpc_ich_enable_gpio_space(struct pci_dev *dev)
+static void lpc_ich_enable_gpio_space(struct pci_dev *dev)
 {
 	u8 reg_save;
 
@@ -690,7 +690,7 @@ static void __devinit lpc_ich_enable_gpio_space(struct pci_dev *dev)
 	lpc_ich_gpio_save = reg_save;
 }
 
-static void __devinit lpc_ich_finalize_cell(struct mfd_cell *cell,
+static void lpc_ich_finalize_cell(struct mfd_cell *cell,
 					const struct pci_device_id *id)
 {
 	cell->platform_data = &lpc_chipset_info[id->driver_data];
@@ -702,7 +702,7 @@ static void __devinit lpc_ich_finalize_cell(struct mfd_cell *cell,
  * GPIO groups and it's enough to have access to one of these to instantiate
  * the device.
  */
-static int __devinit lpc_ich_check_conflict_gpio(struct resource *res)
+static int lpc_ich_check_conflict_gpio(struct resource *res)
 {
 	int ret;
 	u8 use_gpio = 0;
@@ -721,7 +721,7 @@ static int __devinit lpc_ich_check_conflict_gpio(struct resource *res)
 	return use_gpio ? use_gpio : ret;
 }
 
-static int __devinit lpc_ich_init_gpio(struct pci_dev *dev,
+static int lpc_ich_init_gpio(struct pci_dev *dev,
 				const struct pci_device_id *id)
 {
 	u32 base_addr_cfg;
@@ -798,7 +798,7 @@ gpio_done:
 	return ret;
 }
 
-static int __devinit lpc_ich_init_wdt(struct pci_dev *dev,
+static int lpc_ich_init_wdt(struct pci_dev *dev,
 				const struct pci_device_id *id)
 {
 	u32 base_addr_cfg;
@@ -852,7 +852,7 @@ wdt_done:
 	return ret;
 }
 
-static int __devinit lpc_ich_probe(struct pci_dev *dev,
+static int lpc_ich_probe(struct pci_dev *dev,
 				const struct pci_device_id *id)
 {
 	int ret;
diff --git a/drivers/mfd/lpc_sch.c b/drivers/mfd/lpc_sch.c
index 27477f4533ea..5756a6af08dc 100644
--- a/drivers/mfd/lpc_sch.c
+++ b/drivers/mfd/lpc_sch.c
@@ -83,7 +83,7 @@ static DEFINE_PCI_DEVICE_TABLE(lpc_sch_ids) = {
 };
 MODULE_DEVICE_TABLE(pci, lpc_sch_ids);
 
-static int __devinit lpc_sch_probe(struct pci_dev *dev,
+static int lpc_sch_probe(struct pci_dev *dev,
 				const struct pci_device_id *id)
 {
 	unsigned int base_addr_cfg;
diff --git a/drivers/mfd/max8907.c b/drivers/mfd/max8907.c
index 17f2593d82b8..81ded7a4ca8c 100644
--- a/drivers/mfd/max8907.c
+++ b/drivers/mfd/max8907.c
@@ -183,7 +183,7 @@ static void max8907_power_off(void)
 			MAX8907_MASK_POWER_OFF, MAX8907_MASK_POWER_OFF);
 }
 
-static __devinit int max8907_i2c_probe(struct i2c_client *i2c,
+static int max8907_i2c_probe(struct i2c_client *i2c,
 				       const struct i2c_device_id *id)
 {
 	struct max8907 *max8907;
diff --git a/drivers/mfd/max8925-core.c b/drivers/mfd/max8925-core.c
index 9f54c04912f2..20daa16b83c9 100644
--- a/drivers/mfd/max8925-core.c
+++ b/drivers/mfd/max8925-core.c
@@ -714,7 +714,7 @@ tsc_irq:
 	return 0;
 }
 
-static void __devinit init_regulator(struct max8925_chip *chip,
+static void init_regulator(struct max8925_chip *chip,
 				     struct max8925_platform_data *pdata)
 {
 	int ret;
@@ -821,7 +821,7 @@ static void __devinit init_regulator(struct max8925_chip *chip,
 	}
 }
 
-int __devinit max8925_device_init(struct max8925_chip *chip,
+int max8925_device_init(struct max8925_chip *chip,
 				  struct max8925_platform_data *pdata)
 {
 	int ret;
diff --git a/drivers/mfd/max8925-i2c.c b/drivers/mfd/max8925-i2c.c
index 375e0475f6d2..6e3d30aa00df 100644
--- a/drivers/mfd/max8925-i2c.c
+++ b/drivers/mfd/max8925-i2c.c
@@ -135,7 +135,7 @@ static const struct i2c_device_id max8925_id_table[] = {
 };
 MODULE_DEVICE_TABLE(i2c, max8925_id_table);
 
-static int __devinit max8925_probe(struct i2c_client *client,
+static int max8925_probe(struct i2c_client *client,
 				   const struct i2c_device_id *id)
 {
 	struct max8925_platform_data *pdata = client->dev.platform_data;
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 23cec57c02ba..fc23dfbb6910 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -464,7 +464,7 @@ static void omap_usbhs_deinit(struct device *dev)
  *
  * Allocates basic resources for this USB host controller.
  */
-static int __devinit usbhs_omap_probe(struct platform_device *pdev)
+static int usbhs_omap_probe(struct platform_device *pdev)
 {
 	struct device			*dev =  &pdev->dev;
 	struct usbhs_omap_platform_data	*pdata = dev->platform_data;
diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c
index 2d8edfd85e1c..0b586885446b 100644
--- a/drivers/mfd/omap-usb-tll.c
+++ b/drivers/mfd/omap-usb-tll.c
@@ -200,7 +200,7 @@ static unsigned ohci_omap3_fslsmode(enum usbhs_omap_port_mode mode)
  *
  * Allocates basic resources for this USB host controller.
  */
-static int __devinit usbtll_omap_probe(struct platform_device *pdev)
+static int usbtll_omap_probe(struct platform_device *pdev)
 {
 	struct device				*dev =  &pdev->dev;
 	struct usbtll_omap_platform_data	*pdata = dev->platform_data;
diff --git a/drivers/mfd/palmas.c b/drivers/mfd/palmas.c
index 4f8d6e6b19aa..cb52783390c1 100644
--- a/drivers/mfd/palmas.c
+++ b/drivers/mfd/palmas.c
@@ -247,7 +247,7 @@ static struct regmap_irq_chip palmas_irq_chip = {
 			PALMAS_INT1_MASK),
 };
 
-static void __devinit palmas_dt_to_pdata(struct device_node *node,
+static void palmas_dt_to_pdata(struct device_node *node,
 		struct palmas_platform_data *pdata)
 {
 	int ret;
@@ -275,7 +275,7 @@ static void __devinit palmas_dt_to_pdata(struct device_node *node,
 					PALMAS_POWER_CTRL_ENABLE2_MASK;
 }
 
-static int __devinit palmas_i2c_probe(struct i2c_client *i2c,
+static int palmas_i2c_probe(struct i2c_client *i2c,
 			    const struct i2c_device_id *id)
 {
 	struct palmas *palmas;
diff --git a/drivers/mfd/pcf50633-adc.c b/drivers/mfd/pcf50633-adc.c
index a285b5111edb..dbd2f0d0078e 100644
--- a/drivers/mfd/pcf50633-adc.c
+++ b/drivers/mfd/pcf50633-adc.c
@@ -199,7 +199,7 @@ static void pcf50633_adc_irq(int irq, void *data)
 	kfree(req);
 }
 
-static int __devinit pcf50633_adc_probe(struct platform_device *pdev)
+static int pcf50633_adc_probe(struct platform_device *pdev)
 {
 	struct pcf50633_adc *adc;
 
diff --git a/drivers/mfd/pcf50633-core.c b/drivers/mfd/pcf50633-core.c
index ad438e85cbf7..fc477353081e 100644
--- a/drivers/mfd/pcf50633-core.c
+++ b/drivers/mfd/pcf50633-core.c
@@ -191,7 +191,7 @@ static struct regmap_config pcf50633_regmap_config = {
 	.val_bits = 8,
 };
 
-static int __devinit pcf50633_probe(struct i2c_client *client,
+static int pcf50633_probe(struct i2c_client *client,
 				const struct i2c_device_id *ids)
 {
 	struct pcf50633 *pcf;
diff --git a/drivers/mfd/pm8921-core.c b/drivers/mfd/pm8921-core.c
index 24d57bcc98b6..43491346e7d0 100644
--- a/drivers/mfd/pm8921-core.c
+++ b/drivers/mfd/pm8921-core.c
@@ -80,7 +80,7 @@ static struct pm8xxx_drvdata pm8921_drvdata = {
 	.pmic_read_irq_stat	= pm8921_read_irq_stat,
 };
 
-static int __devinit pm8921_add_subdevices(const struct pm8921_platform_data
+static int pm8921_add_subdevices(const struct pm8921_platform_data
 					   *pdata,
 					   struct pm8921 *pmic,
 					   u32 rev)
@@ -104,7 +104,7 @@ static int __devinit pm8921_add_subdevices(const struct pm8921_platform_data
 	return ret;
 }
 
-static int __devinit pm8921_probe(struct platform_device *pdev)
+static int pm8921_probe(struct platform_device *pdev)
 {
 	const struct pm8921_platform_data *pdata = pdev->dev.platform_data;
 	struct pm8921 *pmic;
diff --git a/drivers/mfd/pm8xxx-irq.c b/drivers/mfd/pm8xxx-irq.c
index d452dd013081..59c20ea329de 100644
--- a/drivers/mfd/pm8xxx-irq.c
+++ b/drivers/mfd/pm8xxx-irq.c
@@ -309,7 +309,7 @@ bail_out:
 }
 EXPORT_SYMBOL_GPL(pm8xxx_get_irq_stat);
 
-struct pm_irq_chip *  __devinit pm8xxx_irq_init(struct device *dev,
+struct pm_irq_chip *  pm8xxx_irq_init(struct device *dev,
 				const struct pm8xxx_irq_platform_data *pdata)
 {
 	struct pm_irq_chip  *chip;
diff --git a/drivers/mfd/rc5t583.c b/drivers/mfd/rc5t583.c
index d38ee24302ca..f721b13e986c 100644
--- a/drivers/mfd/rc5t583.c
+++ b/drivers/mfd/rc5t583.c
@@ -246,7 +246,7 @@ static const struct regmap_config rc5t583_regmap_config = {
 	.cache_type = REGCACHE_RBTREE,
 };
 
-static int __devinit rc5t583_i2c_probe(struct i2c_client *i2c,
+static int rc5t583_i2c_probe(struct i2c_client *i2c,
 			      const struct i2c_device_id *id)
 {
 	struct rc5t583 *rc5t583;
diff --git a/drivers/mfd/rdc321x-southbridge.c b/drivers/mfd/rdc321x-southbridge.c
index 330396306d62..be46539c3080 100644
--- a/drivers/mfd/rdc321x-southbridge.c
+++ b/drivers/mfd/rdc321x-southbridge.c
@@ -72,7 +72,7 @@ static struct mfd_cell rdc321x_sb_cells[] = {
 	},
 };
 
-static int __devinit rdc321x_sb_probe(struct pci_dev *pdev,
+static int rdc321x_sb_probe(struct pci_dev *pdev,
 					const struct pci_device_id *ent)
 {
 	int err;
diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index 777af5ec25d4..c9c102c49028 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -1014,7 +1014,7 @@ static struct gpio_chip gpio_chip_template = {
 	.get			= sm501_gpio_get,
 };
 
-static int __devinit sm501_gpio_register_chip(struct sm501_devdata *sm,
+static int sm501_gpio_register_chip(struct sm501_devdata *sm,
 					      struct sm501_gpio *gpio,
 					      struct sm501_gpio_chip *chip)
 {
@@ -1042,7 +1042,7 @@ static int __devinit sm501_gpio_register_chip(struct sm501_devdata *sm,
 	return gpiochip_add(gchip);
 }
 
-static int __devinit sm501_register_gpio(struct sm501_devdata *sm)
+static int sm501_register_gpio(struct sm501_devdata *sm)
 {
 	struct sm501_gpio *gpio = &sm->gpio;
 	resource_size_t iobase = sm->io_res->start + SM501_GPIO;
@@ -1313,7 +1313,7 @@ static unsigned int sm501_mem_local[] = {
  * Common init code for an SM501
 */
 
-static int __devinit sm501_init_dev(struct sm501_devdata *sm)
+static int sm501_init_dev(struct sm501_devdata *sm)
 {
 	struct sm501_initdata *idata;
 	struct sm501_platdata *pdata;
@@ -1389,7 +1389,7 @@ static int __devinit sm501_init_dev(struct sm501_devdata *sm)
 	return 0;
 }
 
-static int __devinit sm501_plat_probe(struct platform_device *dev)
+static int sm501_plat_probe(struct platform_device *dev)
 {
 	struct sm501_devdata *sm;
 	int ret;
@@ -1578,7 +1578,7 @@ static struct sm501_platdata sm501_pci_platdata = {
 	.gpio_base	= -1,
 };
 
-static int __devinit sm501_pci_probe(struct pci_dev *dev,
+static int sm501_pci_probe(struct pci_dev *dev,
 				     const struct pci_device_id *id)
 {
 	struct sm501_devdata *sm;
diff --git a/drivers/mfd/sta2x11-mfd.c b/drivers/mfd/sta2x11-mfd.c
index d35da6820bea..2cfd55f343c2 100644
--- a/drivers/mfd/sta2x11-mfd.c
+++ b/drivers/mfd/sta2x11-mfd.c
@@ -69,7 +69,7 @@ static struct sta2x11_mfd *sta2x11_mfd_find(struct pci_dev *pdev)
 	return NULL;
 }
 
-static int __devinit sta2x11_mfd_add(struct pci_dev *pdev, gfp_t flags)
+static int sta2x11_mfd_add(struct pci_dev *pdev, gfp_t flags)
 {
 	struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev);
 	struct sta2x11_instance *instance;
@@ -363,7 +363,7 @@ static int sta2x11_mfd_resume(struct pci_dev *pdev)
 	return 0;
 }
 
-static int __devinit sta2x11_mfd_probe(struct pci_dev *pdev,
+static int sta2x11_mfd_probe(struct pci_dev *pdev,
 				       const struct pci_device_id *pci_id)
 {
 	int err, i;
diff --git a/drivers/mfd/stmpe-i2c.c b/drivers/mfd/stmpe-i2c.c
index 6a6aed74b946..8195ca2ac74b 100644
--- a/drivers/mfd/stmpe-i2c.c
+++ b/drivers/mfd/stmpe-i2c.c
@@ -52,7 +52,7 @@ static struct stmpe_client_info i2c_ci = {
 	.write_block = i2c_block_write,
 };
 
-static int __devinit
+static int
 stmpe_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 {
 	i2c_ci.data = (void *)id;
diff --git a/drivers/mfd/stmpe-spi.c b/drivers/mfd/stmpe-spi.c
index 29590ad6a6e4..52774338998f 100644
--- a/drivers/mfd/stmpe-spi.c
+++ b/drivers/mfd/stmpe-spi.c
@@ -82,7 +82,7 @@ static struct stmpe_client_info spi_ci = {
 	.init = spi_init,
 };
 
-static int __devinit
+static int
 stmpe_spi_probe(struct spi_device *spi)
 {
 	const struct spi_device_id *id = spi_get_device_id(spi);
diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c
index d258b595d0b7..3dbfe9ab889c 100644
--- a/drivers/mfd/syscon.c
+++ b/drivers/mfd/syscon.c
@@ -97,7 +97,7 @@ static struct regmap_config syscon_regmap_config = {
 	.reg_stride = 4,
 };
 
-static int __devinit syscon_probe(struct platform_device *pdev)
+static int syscon_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c
index 553ce956da6d..7e197f788b0a 100644
--- a/drivers/mfd/tc3589x.c
+++ b/drivers/mfd/tc3589x.c
@@ -282,7 +282,7 @@ static int tc3589x_chip_init(struct tc3589x *tc3589x)
 	return tc3589x_reg_write(tc3589x, TC3589x_RSTINTCLR, 0x1);
 }
 
-static int __devinit tc3589x_device_init(struct tc3589x *tc3589x)
+static int tc3589x_device_init(struct tc3589x *tc3589x)
 {
 	int ret = 0;
 	unsigned int blocks = tc3589x->pdata->block;
@@ -329,7 +329,7 @@ static int tc3589x_of_probe(struct device_node *np,
 	return 0;
 }
 
-static int __devinit tc3589x_probe(struct i2c_client *i2c,
+static int tc3589x_probe(struct i2c_client *i2c,
 				   const struct i2c_device_id *id)
 {
 	struct tc3589x_platform_data *pdata = i2c->dev.platform_data;
diff --git a/drivers/mfd/tc6387xb.c b/drivers/mfd/tc6387xb.c
index 186f053e36ef..ca18f262c34a 100644
--- a/drivers/mfd/tc6387xb.c
+++ b/drivers/mfd/tc6387xb.c
@@ -138,7 +138,7 @@ static struct mfd_cell tc6387xb_cells[] = {
 	},
 };
 
-static int __devinit tc6387xb_probe(struct platform_device *dev)
+static int tc6387xb_probe(struct platform_device *dev)
 {
 	struct tc6387xb_platform_data *pdata = dev->dev.platform_data;
 	struct resource *iomem, *rscr;
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 9411a88770b8..256723231a4e 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -602,7 +602,7 @@ static void tc6393xb_detach_irq(struct platform_device *dev)
 
 /*--------------------------------------------------------------------------*/
 
-static int __devinit tc6393xb_probe(struct platform_device *dev)
+static int tc6393xb_probe(struct platform_device *dev)
 {
 	struct tc6393xb_platform_data *tcpd = dev->dev.platform_data;
 	struct tc6393xb *tc6393xb;
diff --git a/drivers/mfd/ti-ssp.c b/drivers/mfd/ti-ssp.c
index 1c31f877c6bb..b177f96da864 100644
--- a/drivers/mfd/ti-ssp.c
+++ b/drivers/mfd/ti-ssp.c
@@ -315,7 +315,7 @@ static irqreturn_t ti_ssp_interrupt(int irq, void *dev_data)
 	return IRQ_HANDLED;
 }
 
-static int __devinit ti_ssp_probe(struct platform_device *pdev)
+static int ti_ssp_probe(struct platform_device *pdev)
 {
 	static struct ti_ssp *ssp;
 	const struct ti_ssp_data *pdata = pdev->dev.platform_data;
diff --git a/drivers/mfd/timberdale.c b/drivers/mfd/timberdale.c
index 61badece0b9a..dddf1df57838 100644
--- a/drivers/mfd/timberdale.c
+++ b/drivers/mfd/timberdale.c
@@ -650,7 +650,7 @@ static DEVICE_ATTR(fw_ver, S_IRUGO, show_fw_ver, NULL);
 
 /*--------------------------------------------------------------------------*/
 
-static int __devinit timb_probe(struct pci_dev *dev,
+static int timb_probe(struct pci_dev *dev,
 	const struct pci_device_id *id)
 {
 	struct timberdale_device *priv;
diff --git a/drivers/mfd/tps6105x.c b/drivers/mfd/tps6105x.c
index 45389600f86e..75a84ac4672e 100644
--- a/drivers/mfd/tps6105x.c
+++ b/drivers/mfd/tps6105x.c
@@ -86,7 +86,7 @@ fail:
 }
 EXPORT_SYMBOL(tps6105x_mask_and_set);
 
-static int __devinit tps6105x_startup(struct tps6105x *tps6105x)
+static int tps6105x_startup(struct tps6105x *tps6105x)
 {
 	int ret;
 	u8 regval;
@@ -133,7 +133,7 @@ static struct mfd_cell tps6105x_cells[] = {
 	},
 };
 
-static int __devinit tps6105x_probe(struct i2c_client *client,
+static int tps6105x_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
 	struct tps6105x			*tps6105x;
diff --git a/drivers/mfd/tps65090.c b/drivers/mfd/tps65090.c
index d43ff16d8c4c..0c446eb86bdb 100644
--- a/drivers/mfd/tps65090.c
+++ b/drivers/mfd/tps65090.c
@@ -188,7 +188,7 @@ static irqreturn_t tps65090_irq(int irq, void *data)
 	return acks ? IRQ_HANDLED : IRQ_NONE;
 }
 
-static int __devinit tps65090_irq_init(struct tps65090 *tps65090, int irq,
+static int tps65090_irq_init(struct tps65090 *tps65090, int irq,
 	int irq_base)
 {
 	int i, ret;
@@ -251,7 +251,7 @@ static const struct regmap_config tps65090_regmap_config = {
 	.volatile_reg = is_volatile_reg,
 };
 
-static int __devinit tps65090_i2c_probe(struct i2c_client *client,
+static int tps65090_i2c_probe(struct i2c_client *client,
 					const struct i2c_device_id *id)
 {
 	struct tps65090_platform_data *pdata = client->dev.platform_data;
diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c
index 76360c10246e..8cba75750e91 100644
--- a/drivers/mfd/tps65217.c
+++ b/drivers/mfd/tps65217.c
@@ -153,7 +153,7 @@ static const struct of_device_id tps65217_of_match[] = {
 	{ /* sentinel */ },
 };
 
-static int __devinit tps65217_probe(struct i2c_client *client,
+static int tps65217_probe(struct i2c_client *client,
 				const struct i2c_device_id *ids)
 {
 	struct tps65217 *tps;
diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c
index a2e226f0f185..975fbb5f36aa 100644
--- a/drivers/mfd/tps6586x.c
+++ b/drivers/mfd/tps6586x.c
@@ -267,7 +267,7 @@ static irqreturn_t tps6586x_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int __devinit tps6586x_irq_init(struct tps6586x *tps6586x, int irq,
+static int tps6586x_irq_init(struct tps6586x *tps6586x, int irq,
 				       int irq_base)
 {
 	int i, ret;
@@ -316,7 +316,7 @@ static int __devinit tps6586x_irq_init(struct tps6586x *tps6586x, int irq,
 	return ret;
 }
 
-static int __devinit tps6586x_add_subdevs(struct tps6586x *tps6586x,
+static int tps6586x_add_subdevs(struct tps6586x *tps6586x,
 					  struct tps6586x_platform_data *pdata)
 {
 	struct tps6586x_subdev_info *subdev;
@@ -468,7 +468,7 @@ static void tps6586x_power_off(void)
 	tps6586x_set_bits(tps6586x_dev, TPS6586X_SUPPLYENE, SLEEP_MODE_BIT);
 }
 
-static int __devinit tps6586x_i2c_probe(struct i2c_client *client,
+static int tps6586x_i2c_probe(struct i2c_client *client,
 					const struct i2c_device_id *id)
 {
 	struct tps6586x_platform_data *pdata = client->dev.platform_data;
diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index a3d732bcb519..3a3402290a74 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -78,7 +78,7 @@ static const struct regmap_config tps65910_regmap_config = {
 	.cache_type = REGCACHE_RBTREE,
 };
 
-static int __devinit tps65910_ck32k_init(struct tps65910 *tps65910,
+static int tps65910_ck32k_init(struct tps65910 *tps65910,
 					struct tps65910_board *pmic_pdata)
 {
 	int ret;
@@ -96,7 +96,7 @@ static int __devinit tps65910_ck32k_init(struct tps65910 *tps65910,
 	return 0;
 }
 
-static int __devinit tps65910_sleepinit(struct tps65910 *tps65910,
+static int tps65910_sleepinit(struct tps65910 *tps65910,
 		struct tps65910_board *pmic_pdata)
 {
 	struct device *dev = NULL;
@@ -237,7 +237,7 @@ static void tps65910_power_off(void)
 			DEVCTRL_DEV_ON_MASK);
 }
 
-static __devinit int tps65910_i2c_probe(struct i2c_client *i2c,
+static int tps65910_i2c_probe(struct i2c_client *i2c,
 					const struct i2c_device_id *id)
 {
 	struct tps65910 *tps65910;
diff --git a/drivers/mfd/tps65911-comparator.c b/drivers/mfd/tps65911-comparator.c
index a0255874fb1d..b3d268f95a77 100644
--- a/drivers/mfd/tps65911-comparator.c
+++ b/drivers/mfd/tps65911-comparator.c
@@ -122,7 +122,7 @@ static ssize_t comp_threshold_show(struct device *dev,
 static DEVICE_ATTR(comp1_threshold, S_IRUGO, comp_threshold_show, NULL);
 static DEVICE_ATTR(comp2_threshold, S_IRUGO, comp_threshold_show, NULL);
 
-static __devinit int tps65911_comparator_probe(struct platform_device *pdev)
+static int tps65911_comparator_probe(struct platform_device *pdev)
 {
 	struct tps65910 *tps65910 = dev_get_drvdata(pdev->dev.parent);
 	struct tps65910_board *pdata = dev_get_platdata(tps65910->dev);
diff --git a/drivers/mfd/tps65912-spi.c b/drivers/mfd/tps65912-spi.c
index 054315da9d5f..6366576a3056 100644
--- a/drivers/mfd/tps65912-spi.c
+++ b/drivers/mfd/tps65912-spi.c
@@ -81,7 +81,7 @@ static int tps65912_spi_read(struct tps65912 *tps65912, u8 addr,
 	return ret;
 }
 
-static int __devinit tps65912_spi_probe(struct spi_device *spi)
+static int tps65912_spi_probe(struct spi_device *spi)
 {
 	struct tps65912 *tps65912;
 
diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c
index 4ae642320205..271d98a83caf 100644
--- a/drivers/mfd/twl-core.c
+++ b/drivers/mfd/twl-core.c
@@ -1170,7 +1170,7 @@ static int twl_remove(struct i2c_client *client)
 }
 
 /* NOTE: This driver only handles a single twl4030/tps659x0 chip */
-static int __devinit
+static int
 twl_probe(struct i2c_client *client, const struct i2c_device_id *id)
 {
 	struct twl4030_platform_data	*pdata = client->dev.platform_data;
diff --git a/drivers/mfd/twl4030-audio.c b/drivers/mfd/twl4030-audio.c
index 08f99055b0fa..aacccdcf997c 100644
--- a/drivers/mfd/twl4030-audio.c
+++ b/drivers/mfd/twl4030-audio.c
@@ -184,7 +184,7 @@ static bool twl4030_audio_has_vibra(struct twl4030_audio_data *pdata,
 	return false;
 }
 
-static int __devinit twl4030_audio_probe(struct platform_device *pdev)
+static int twl4030_audio_probe(struct platform_device *pdev)
 {
 	struct twl4030_audio *audio;
 	struct twl4030_audio_data *pdata = pdev->dev.platform_data;
diff --git a/drivers/mfd/twl4030-madc.c b/drivers/mfd/twl4030-madc.c
index 456ecb5ac4fe..228d5aacd332 100644
--- a/drivers/mfd/twl4030-madc.c
+++ b/drivers/mfd/twl4030-madc.c
@@ -692,7 +692,7 @@ static int twl4030_madc_set_power(struct twl4030_madc_data *madc, int on)
 /*
  * Initialize MADC and request for threaded irq
  */
-static int __devinit twl4030_madc_probe(struct platform_device *pdev)
+static int twl4030_madc_probe(struct platform_device *pdev)
 {
 	struct twl4030_madc_data *madc;
 	struct twl4030_madc_platform_data *pdata = pdev->dev.platform_data;
diff --git a/drivers/mfd/twl4030-power.c b/drivers/mfd/twl4030-power.c
index 79ca33dfacca..a5332063183a 100644
--- a/drivers/mfd/twl4030-power.c
+++ b/drivers/mfd/twl4030-power.c
@@ -124,7 +124,7 @@ static u8 res_config_addrs[] = {
 	[RES_MAIN_REF]	= 0x94,
 };
 
-static int __devinit twl4030_write_script_byte(u8 address, u8 byte)
+static int twl4030_write_script_byte(u8 address, u8 byte)
 {
 	int err;
 
@@ -138,7 +138,7 @@ out:
 	return err;
 }
 
-static int __devinit twl4030_write_script_ins(u8 address, u16 pmb_message,
+static int twl4030_write_script_ins(u8 address, u16 pmb_message,
 					   u8 delay, u8 next)
 {
 	int err;
@@ -158,7 +158,7 @@ out:
 	return err;
 }
 
-static int __devinit twl4030_write_script(u8 address, struct twl4030_ins *script,
+static int twl4030_write_script(u8 address, struct twl4030_ins *script,
 				       int len)
 {
 	int err;
@@ -183,7 +183,7 @@ static int __devinit twl4030_write_script(u8 address, struct twl4030_ins *script
 	return err;
 }
 
-static int __devinit twl4030_config_wakeup3_sequence(u8 address)
+static int twl4030_config_wakeup3_sequence(u8 address)
 {
 	int err;
 	u8 data;
@@ -208,7 +208,7 @@ out:
 	return err;
 }
 
-static int __devinit twl4030_config_wakeup12_sequence(u8 address)
+static int twl4030_config_wakeup12_sequence(u8 address)
 {
 	int err = 0;
 	u8 data;
@@ -262,7 +262,7 @@ out:
 	return err;
 }
 
-static int __devinit twl4030_config_sleep_sequence(u8 address)
+static int twl4030_config_sleep_sequence(u8 address)
 {
 	int err;
 
@@ -276,7 +276,7 @@ static int __devinit twl4030_config_sleep_sequence(u8 address)
 	return err;
 }
 
-static int __devinit twl4030_config_warmreset_sequence(u8 address)
+static int twl4030_config_warmreset_sequence(u8 address)
 {
 	int err;
 	u8 rd_data;
@@ -324,7 +324,7 @@ out:
 	return err;
 }
 
-static int __devinit twl4030_configure_resource(struct twl4030_resconfig *rconfig)
+static int twl4030_configure_resource(struct twl4030_resconfig *rconfig)
 {
 	int rconfig_addr;
 	int err;
@@ -416,7 +416,7 @@ static int __devinit twl4030_configure_resource(struct twl4030_resconfig *rconfi
 	return 0;
 }
 
-static int __devinit load_twl4030_script(struct twl4030_script *tscript,
+static int load_twl4030_script(struct twl4030_script *tscript,
 	       u8 address)
 {
 	int err;
@@ -527,7 +527,7 @@ void twl4030_power_off(void)
 		pr_err("TWL4030 Unable to power off\n");
 }
 
-void __devinit twl4030_power_init(struct twl4030_power_data *twl4030_scripts)
+void twl4030_power_init(struct twl4030_power_data *twl4030_scripts)
 {
 	int err = 0;
 	int i;
diff --git a/drivers/mfd/vx855.c b/drivers/mfd/vx855.c
index c5a7df84e6da..66ef03b02569 100644
--- a/drivers/mfd/vx855.c
+++ b/drivers/mfd/vx855.c
@@ -72,7 +72,7 @@ static struct mfd_cell vx855_cells[] = {
 	},
 };
 
-static __devinit int vx855_probe(struct pci_dev *pdev,
+static int vx855_probe(struct pci_dev *pdev,
 				 const struct pci_device_id *id)
 {
 	int ret;
diff --git a/drivers/mfd/wl1273-core.c b/drivers/mfd/wl1273-core.c
index 7f3f3896662d..edbe6c1b755a 100644
--- a/drivers/mfd/wl1273-core.c
+++ b/drivers/mfd/wl1273-core.c
@@ -182,7 +182,7 @@ static int wl1273_core_remove(struct i2c_client *client)
 	return 0;
 }
 
-static int __devinit wl1273_core_probe(struct i2c_client *client,
+static int wl1273_core_probe(struct i2c_client *client,
 				       const struct i2c_device_id *id)
 {
 	struct wl1273_fm_platform_data *pdata = client->dev.platform_data;
diff --git a/drivers/mfd/wm831x-spi.c b/drivers/mfd/wm831x-spi.c
index 4329a3a9726f..4c7225a53ba2 100644
--- a/drivers/mfd/wm831x-spi.c
+++ b/drivers/mfd/wm831x-spi.c
@@ -21,7 +21,7 @@
 
 #include <linux/mfd/wm831x/core.h>
 
-static int __devinit wm831x_spi_probe(struct spi_device *spi)
+static int wm831x_spi_probe(struct spi_device *spi)
 {
 	const struct spi_device_id *id = spi_get_device_id(spi);
 	struct wm831x *wm831x;
diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index bb9cf5216115..46429495836d 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -399,7 +399,7 @@ static const __devinitconst struct reg_default wm1811_reva_patch[] = {
 /*
  * Instantiate the generic non-control parts of the device.
  */
-static __devinit int wm8994_device_init(struct wm8994 *wm8994, int irq)
+static int wm8994_device_init(struct wm8994 *wm8994, int irq)
 {
 	struct wm8994_pdata *pdata = wm8994->dev->platform_data;
 	struct regmap_config *regmap_config;
@@ -689,7 +689,7 @@ static const struct of_device_id wm8994_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, wm8994_of_match);
 
-static __devinit int wm8994_i2c_probe(struct i2c_client *i2c,
+static int wm8994_i2c_probe(struct i2c_client *i2c,
 				      const struct i2c_device_id *id)
 {
 	struct wm8994 *wm8994;
diff --git a/include/linux/mfd/88pm80x.h b/include/linux/mfd/88pm80x.h
index a0ca0dca1244..478672ed0c3d 100644
--- a/include/linux/mfd/88pm80x.h
+++ b/include/linux/mfd/88pm80x.h
@@ -364,6 +364,6 @@ static inline int pm80x_dev_resume(struct device *dev)
 #endif
 
 extern int pm80x_init(struct i2c_client *client,
-			     const struct i2c_device_id *id) __devinit;
+		      const struct i2c_device_id *id);
 extern int pm80x_deinit(struct i2c_client *client);
 #endif /* __LINUX_MFD_88PM80X_H */
diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h
index 1491044efa10..83f0bdc530b7 100644
--- a/include/linux/mfd/abx500/ab8500.h
+++ b/include/linux/mfd/abx500/ab8500.h
@@ -291,7 +291,7 @@ struct ab8500_platform_data {
 	struct ab8500_codec_platform_data *codec;
 };
 
-extern int __devinit ab8500_init(struct ab8500 *ab8500,
+extern int ab8500_init(struct ab8500 *ab8500,
 				 enum ab8500_version version);
 extern int __devexit ab8500_exit(struct ab8500 *ab8500);
 
diff --git a/include/linux/mfd/pm8xxx/irq.h b/include/linux/mfd/pm8xxx/irq.h
index 4b21769f4483..ddaa7f5e9ed9 100644
--- a/include/linux/mfd/pm8xxx/irq.h
+++ b/include/linux/mfd/pm8xxx/irq.h
@@ -37,7 +37,7 @@ struct pm_irq_chip;
 
 #ifdef CONFIG_MFD_PM8XXX_IRQ
 int pm8xxx_get_irq_stat(struct pm_irq_chip *chip, int irq);
-struct pm_irq_chip * __devinit pm8xxx_irq_init(struct device *dev,
+struct pm_irq_chip *pm8xxx_irq_init(struct device *dev,
 				const struct pm8xxx_irq_platform_data *pdata);
 int __devexit pm8xxx_irq_exit(struct pm_irq_chip *chip);
 #else
@@ -45,7 +45,7 @@ static inline int pm8xxx_get_irq_stat(struct pm_irq_chip *chip, int irq)
 {
 	return -ENXIO;
 }
-static inline struct pm_irq_chip * __devinit pm8xxx_irq_init(
+static inline struct pm_irq_chip *pm8xxx_irq_init(
 				const struct device *dev,
 				const struct pm8xxx_irq_platform_data *pdata)
 {
-- 
cgit v1.2.3-55-g7522


From 4740f73fe5388ab5d22d552d2a0dacc62418a70c Mon Sep 17 00:00:00 2001
From: Bill Pemberton
Date: Mon, 19 Nov 2012 13:26:01 -0500
Subject: mfd: remove use of __devexit

CONFIG_HOTPLUG is going away as an option so __devexit is no
longer needed.

Signed-off-by: Bill Pemberton <wfp5p@virginia.edu>
Cc: Srinidhi Kasagar <srinidhi.kasagar@stericsson.com>
Cc: Peter Tyser <ptyser@xes-inc.com>
Cc: Daniel Walker <dwalker@fifo99.com>
Cc: Bryan Huntsman <bryanh@codeaurora.org>
Acked-by: David Brown <davidb@codeaurora.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/mfd/88pm800.c             | 2 +-
 drivers/mfd/88pm805.c             | 2 +-
 drivers/mfd/88pm860x-core.c       | 4 ++--
 drivers/mfd/ab3100-core.c         | 2 +-
 drivers/mfd/ab8500-core.c         | 2 +-
 drivers/mfd/ab8500-debugfs.c      | 2 +-
 drivers/mfd/ab8500-gpadc.c        | 2 +-
 drivers/mfd/ab8500-sysctrl.c      | 2 +-
 drivers/mfd/adp5520.c             | 2 +-
 drivers/mfd/arizona-core.c        | 2 +-
 drivers/mfd/arizona-i2c.c         | 2 +-
 drivers/mfd/arizona-spi.c         | 2 +-
 drivers/mfd/asic3.c               | 2 +-
 drivers/mfd/cs5535-mfd.c          | 2 +-
 drivers/mfd/da903x.c              | 2 +-
 drivers/mfd/da9052-i2c.c          | 2 +-
 drivers/mfd/da9052-spi.c          | 2 +-
 drivers/mfd/da9055-core.c         | 2 +-
 drivers/mfd/da9055-i2c.c          | 2 +-
 drivers/mfd/davinci_voicecodec.c  | 2 +-
 drivers/mfd/ezx-pcap.c            | 2 +-
 drivers/mfd/intel_msic.c          | 4 ++--
 drivers/mfd/janz-cmodio.c         | 2 +-
 drivers/mfd/jz4740-adc.c          | 2 +-
 drivers/mfd/lm3533-core.c         | 4 ++--
 drivers/mfd/lp8788.c              | 2 +-
 drivers/mfd/lpc_ich.c             | 2 +-
 drivers/mfd/lpc_sch.c             | 2 +-
 drivers/mfd/max8907.c             | 2 +-
 drivers/mfd/max8925-core.c        | 2 +-
 drivers/mfd/max8925-i2c.c         | 2 +-
 drivers/mfd/mc13xxx-i2c.c         | 2 +-
 drivers/mfd/mc13xxx-spi.c         | 2 +-
 drivers/mfd/omap-usb-host.c       | 2 +-
 drivers/mfd/omap-usb-tll.c        | 2 +-
 drivers/mfd/pcf50633-adc.c        | 2 +-
 drivers/mfd/pcf50633-core.c       | 2 +-
 drivers/mfd/pm8921-core.c         | 2 +-
 drivers/mfd/pm8xxx-irq.c          | 2 +-
 drivers/mfd/rc5t583.c             | 2 +-
 drivers/mfd/rdc321x-southbridge.c | 2 +-
 drivers/mfd/sm501.c               | 2 +-
 drivers/mfd/sta2x11-mfd.c         | 2 +-
 drivers/mfd/stmpe-i2c.c           | 2 +-
 drivers/mfd/stmpe-spi.c           | 2 +-
 drivers/mfd/syscon.c              | 2 +-
 drivers/mfd/tc3589x.c             | 2 +-
 drivers/mfd/tc6387xb.c            | 2 +-
 drivers/mfd/tc6393xb.c            | 2 +-
 drivers/mfd/ti-ssp.c              | 2 +-
 drivers/mfd/timberdale.c          | 2 +-
 drivers/mfd/tps6105x.c            | 2 +-
 drivers/mfd/tps65090.c            | 2 +-
 drivers/mfd/tps65217.c            | 2 +-
 drivers/mfd/tps6586x.c            | 2 +-
 drivers/mfd/tps65910.c            | 2 +-
 drivers/mfd/tps65911-comparator.c | 2 +-
 drivers/mfd/tps65912-spi.c        | 2 +-
 drivers/mfd/twl4030-audio.c       | 2 +-
 drivers/mfd/twl4030-madc.c        | 2 +-
 drivers/mfd/vx855.c               | 2 +-
 drivers/mfd/wm831x-spi.c          | 2 +-
 drivers/mfd/wm8994-core.c         | 4 ++--
 include/linux/mfd/abx500/ab8500.h | 2 +-
 include/linux/mfd/pm8xxx/irq.h    | 4 ++--
 65 files changed, 70 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/88pm800.c b/drivers/mfd/88pm800.c
index 6746ecd260ad..391e23e6a647 100644
--- a/drivers/mfd/88pm800.c
+++ b/drivers/mfd/88pm800.c
@@ -554,7 +554,7 @@ out_init:
 	return ret;
 }
 
-static int __devexit pm800_remove(struct i2c_client *client)
+static int pm800_remove(struct i2c_client *client)
 {
 	struct pm80x_chip *chip = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/88pm805.c b/drivers/mfd/88pm805.c
index 13c09941dc2c..e671230be2b1 100644
--- a/drivers/mfd/88pm805.c
+++ b/drivers/mfd/88pm805.c
@@ -262,7 +262,7 @@ out_init:
 	return ret;
 }
 
-static int __devexit pm805_remove(struct i2c_client *client)
+static int pm805_remove(struct i2c_client *client)
 {
 	struct pm80x_chip *chip = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c
index 20dd0d41aee4..893fc1ba6ead 100644
--- a/drivers/mfd/88pm860x-core.c
+++ b/drivers/mfd/88pm860x-core.c
@@ -1077,7 +1077,7 @@ static int pm860x_device_init(struct pm860x_chip *chip,
 	return 0;
 }
 
-static void __devexit pm860x_device_exit(struct pm860x_chip *chip)
+static void pm860x_device_exit(struct pm860x_chip *chip)
 {
 	device_irq_exit(chip);
 	mfd_remove_devices(chip->dev);
@@ -1200,7 +1200,7 @@ err:
 	return ret;
 }
 
-static int __devexit pm860x_remove(struct i2c_client *client)
+static int pm860x_remove(struct i2c_client *client)
 {
 	struct pm860x_chip *chip = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/ab3100-core.c b/drivers/mfd/ab3100-core.c
index bf188bc98986..2ec7725f4a08 100644
--- a/drivers/mfd/ab3100-core.c
+++ b/drivers/mfd/ab3100-core.c
@@ -961,7 +961,7 @@ static int ab3100_probe(struct i2c_client *client,
 	return err;
 }
 
-static int __devexit ab3100_remove(struct i2c_client *client)
+static int ab3100_remove(struct i2c_client *client)
 {
 	struct ab3100 *ab3100 = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index 7335a9c8ffae..127b00aadae3 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -1473,7 +1473,7 @@ out_free_ab8500:
 	return ret;
 }
 
-static int __devexit ab8500_remove(struct platform_device *pdev)
+static int ab8500_remove(struct platform_device *pdev)
 {
 	struct ab8500 *ab8500 = platform_get_drvdata(pdev);
 
diff --git a/drivers/mfd/ab8500-debugfs.c b/drivers/mfd/ab8500-debugfs.c
index 44843680d982..5a8e707bc038 100644
--- a/drivers/mfd/ab8500-debugfs.c
+++ b/drivers/mfd/ab8500-debugfs.c
@@ -597,7 +597,7 @@ exit_no_debugfs:
 	return -ENOMEM;
 }
 
-static int __devexit ab8500_debug_remove(struct platform_device *plf)
+static int ab8500_debug_remove(struct platform_device *plf)
 {
 	debugfs_remove(ab8500_val_file);
 	debugfs_remove(ab8500_address_file);
diff --git a/drivers/mfd/ab8500-gpadc.c b/drivers/mfd/ab8500-gpadc.c
index c5e168e3ef11..3fb1f40d6389 100644
--- a/drivers/mfd/ab8500-gpadc.c
+++ b/drivers/mfd/ab8500-gpadc.c
@@ -634,7 +634,7 @@ fail:
 	return ret;
 }
 
-static int __devexit ab8500_gpadc_remove(struct platform_device *pdev)
+static int ab8500_gpadc_remove(struct platform_device *pdev)
 {
 	struct ab8500_gpadc *gpadc = platform_get_drvdata(pdev);
 
diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c
index 499263c3110a..8a33b2c7eead 100644
--- a/drivers/mfd/ab8500-sysctrl.c
+++ b/drivers/mfd/ab8500-sysctrl.c
@@ -55,7 +55,7 @@ static int ab8500_sysctrl_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __devexit ab8500_sysctrl_remove(struct platform_device *pdev)
+static int ab8500_sysctrl_remove(struct platform_device *pdev)
 {
 	sysctrl_dev = NULL;
 	return 0;
diff --git a/drivers/mfd/adp5520.c b/drivers/mfd/adp5520.c
index f2f9d8ff6416..210dd038bb5a 100644
--- a/drivers/mfd/adp5520.c
+++ b/drivers/mfd/adp5520.c
@@ -307,7 +307,7 @@ out_free_chip:
 	return ret;
 }
 
-static int __devexit adp5520_remove(struct i2c_client *client)
+static int adp5520_remove(struct i2c_client *client)
 {
 	struct adp5520_chip *chip = dev_get_drvdata(&client->dev);
 
diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c
index 47e711674739..12fdabfb569e 100644
--- a/drivers/mfd/arizona-core.c
+++ b/drivers/mfd/arizona-core.c
@@ -553,7 +553,7 @@ err_early:
 }
 EXPORT_SYMBOL_GPL(arizona_dev_init);
 
-int __devexit arizona_dev_exit(struct arizona *arizona)
+int arizona_dev_exit(struct arizona *arizona)
 {
 	mfd_remove_devices(arizona->dev);
 	arizona_free_irq(arizona, ARIZONA_IRQ_UNDERCLOCKED, arizona);
diff --git a/drivers/mfd/arizona-i2c.c b/drivers/mfd/arizona-i2c.c
index aaf1a69134df..44a1bb969841 100644
--- a/drivers/mfd/arizona-i2c.c
+++ b/drivers/mfd/arizona-i2c.c
@@ -65,7 +65,7 @@ static int arizona_i2c_probe(struct i2c_client *i2c,
 	return arizona_dev_init(arizona);
 }
 
-static int __devexit arizona_i2c_remove(struct i2c_client *i2c)
+static int arizona_i2c_remove(struct i2c_client *i2c)
 {
 	struct arizona *arizona = dev_get_drvdata(&i2c->dev);
 	arizona_dev_exit(arizona);
diff --git a/drivers/mfd/arizona-spi.c b/drivers/mfd/arizona-spi.c
index 9663cafdb7ff..1b9fdd698b03 100644
--- a/drivers/mfd/arizona-spi.c
+++ b/drivers/mfd/arizona-spi.c
@@ -65,7 +65,7 @@ static int arizona_spi_probe(struct spi_device *spi)
 	return arizona_dev_init(arizona);
 }
 
-static int __devexit arizona_spi_remove(struct spi_device *spi)
+static int arizona_spi_remove(struct spi_device *spi)
 {
 	struct arizona *arizona = dev_get_drvdata(&spi->dev);
 	arizona_dev_exit(arizona);
diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c
index b0720d7c1b71..1b15986c01e1 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -1039,7 +1039,7 @@ static int __init asic3_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int __devexit asic3_remove(struct platform_device *pdev)
+static int asic3_remove(struct platform_device *pdev)
 {
 	int ret;
 	struct asic3 *asic = platform_get_drvdata(pdev);
diff --git a/drivers/mfd/cs5535-mfd.c b/drivers/mfd/cs5535-mfd.c
index d9dc87f067d8..2e4752a9220a 100644
--- a/drivers/mfd/cs5535-mfd.c
+++ b/drivers/mfd/cs5535-mfd.c
@@ -166,7 +166,7 @@ err_disable:
 	return err;
 }
 
-static void __devexit cs5535_mfd_remove(struct pci_dev *pdev)
+static void cs5535_mfd_remove(struct pci_dev *pdev)
 {
 	mfd_remove_devices(&pdev->dev);
 	pci_disable_device(pdev);
diff --git a/drivers/mfd/da903x.c b/drivers/mfd/da903x.c
index 5fa1e91a9532..05176cd2862b 100644
--- a/drivers/mfd/da903x.c
+++ b/drivers/mfd/da903x.c
@@ -544,7 +544,7 @@ out_free_chip:
 	return ret;
 }
 
-static int __devexit da903x_remove(struct i2c_client *client)
+static int da903x_remove(struct i2c_client *client)
 {
 	struct da903x_chip *chip = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c
index 96f66ed8dbfc..ac74a4d1daea 100644
--- a/drivers/mfd/da9052-i2c.c
+++ b/drivers/mfd/da9052-i2c.c
@@ -121,7 +121,7 @@ static int da9052_i2c_probe(struct i2c_client *client,
 	return 0;
 }
 
-static int __devexit da9052_i2c_remove(struct i2c_client *client)
+static int da9052_i2c_remove(struct i2c_client *client)
 {
 	struct da9052 *da9052 = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/da9052-spi.c b/drivers/mfd/da9052-spi.c
index 1ad324373c97..61d63b93576c 100644
--- a/drivers/mfd/da9052-spi.c
+++ b/drivers/mfd/da9052-spi.c
@@ -58,7 +58,7 @@ static int da9052_spi_probe(struct spi_device *spi)
 	return 0;
 }
 
-static int __devexit da9052_spi_remove(struct spi_device *spi)
+static int da9052_spi_remove(struct spi_device *spi)
 {
 	struct da9052 *da9052 = dev_get_drvdata(&spi->dev);
 
diff --git a/drivers/mfd/da9055-core.c b/drivers/mfd/da9055-core.c
index 6f5a4984f0aa..f56a1a9f7777 100644
--- a/drivers/mfd/da9055-core.c
+++ b/drivers/mfd/da9055-core.c
@@ -412,7 +412,7 @@ err:
 	return ret;
 }
 
-void __devexit da9055_device_exit(struct da9055 *da9055)
+void da9055_device_exit(struct da9055 *da9055)
 {
 	regmap_del_irq_chip(da9055->chip_irq, da9055->irq_data);
 	mfd_remove_devices(da9055->dev);
diff --git a/drivers/mfd/da9055-i2c.c b/drivers/mfd/da9055-i2c.c
index 7778d042fb5d..607387ffe8ca 100644
--- a/drivers/mfd/da9055-i2c.c
+++ b/drivers/mfd/da9055-i2c.c
@@ -44,7 +44,7 @@ static int da9055_i2c_probe(struct i2c_client *i2c,
 	return da9055_device_init(da9055);
 }
 
-static int __devexit da9055_i2c_remove(struct i2c_client *i2c)
+static int da9055_i2c_remove(struct i2c_client *i2c)
 {
 	struct da9055 *da9055 = i2c_get_clientdata(i2c);
 
diff --git a/drivers/mfd/davinci_voicecodec.c b/drivers/mfd/davinci_voicecodec.c
index b2b0397059d8..c0bcc872af4e 100644
--- a/drivers/mfd/davinci_voicecodec.c
+++ b/drivers/mfd/davinci_voicecodec.c
@@ -151,7 +151,7 @@ fail1:
 	return ret;
 }
 
-static int __devexit davinci_vc_remove(struct platform_device *pdev)
+static int davinci_vc_remove(struct platform_device *pdev)
 {
 	struct davinci_vc *davinci_vc = platform_get_drvdata(pdev);
 
diff --git a/drivers/mfd/ezx-pcap.c b/drivers/mfd/ezx-pcap.c
index d81505e50d12..b7a61f0f27a4 100644
--- a/drivers/mfd/ezx-pcap.c
+++ b/drivers/mfd/ezx-pcap.c
@@ -391,7 +391,7 @@ static int pcap_add_subdev(struct pcap_chip *pcap,
 	return ret;
 }
 
-static int __devexit ezx_pcap_remove(struct spi_device *spi)
+static int ezx_pcap_remove(struct spi_device *spi)
 {
 	struct pcap_chip *pcap = dev_get_drvdata(&spi->dev);
 	struct pcap_platform_data *pdata = spi->dev.platform_data;
diff --git a/drivers/mfd/intel_msic.c b/drivers/mfd/intel_msic.c
index 438ac3df166b..ab8d0b2739b2 100644
--- a/drivers/mfd/intel_msic.c
+++ b/drivers/mfd/intel_msic.c
@@ -364,7 +364,7 @@ fail:
 	return ret;
 }
 
-static void __devexit intel_msic_remove_devices(struct intel_msic *msic)
+static void intel_msic_remove_devices(struct intel_msic *msic)
 {
 	struct platform_device *pdev = msic->pdev;
 	struct intel_msic_platform_data *pdata = pdev->dev.platform_data;
@@ -445,7 +445,7 @@ static int intel_msic_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __devexit intel_msic_remove(struct platform_device *pdev)
+static int intel_msic_remove(struct platform_device *pdev)
 {
 	struct intel_msic *msic = platform_get_drvdata(pdev);
 
diff --git a/drivers/mfd/janz-cmodio.c b/drivers/mfd/janz-cmodio.c
index 55c479e57aad..45ece11cc27c 100644
--- a/drivers/mfd/janz-cmodio.c
+++ b/drivers/mfd/janz-cmodio.c
@@ -254,7 +254,7 @@ out_return:
 	return ret;
 }
 
-static void __devexit cmodio_pci_remove(struct pci_dev *dev)
+static void cmodio_pci_remove(struct pci_dev *dev)
 {
 	struct cmodio_device *priv = pci_get_drvdata(dev);
 
diff --git a/drivers/mfd/jz4740-adc.c b/drivers/mfd/jz4740-adc.c
index c0d38c597f0c..0b8b55bb9b11 100644
--- a/drivers/mfd/jz4740-adc.c
+++ b/drivers/mfd/jz4740-adc.c
@@ -307,7 +307,7 @@ err_free:
 	return ret;
 }
 
-static int __devexit jz4740_adc_remove(struct platform_device *pdev)
+static int jz4740_adc_remove(struct platform_device *pdev)
 {
 	struct jz4740_adc *adc = platform_get_drvdata(pdev);
 
diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c
index 2b74508655d4..ceebf2c1ea97 100644
--- a/drivers/mfd/lm3533-core.c
+++ b/drivers/mfd/lm3533-core.c
@@ -534,7 +534,7 @@ err_disable:
 	return ret;
 }
 
-static void __devexit lm3533_device_exit(struct lm3533 *lm3533)
+static void lm3533_device_exit(struct lm3533 *lm3533)
 {
 	dev_dbg(lm3533->dev, "%s\n", __func__);
 
@@ -624,7 +624,7 @@ static int lm3533_i2c_probe(struct i2c_client *i2c,
 	return 0;
 }
 
-static int __devexit lm3533_i2c_remove(struct i2c_client *i2c)
+static int lm3533_i2c_remove(struct i2c_client *i2c)
 {
 	struct lm3533 *lm3533 = i2c_get_clientdata(i2c);
 
diff --git a/drivers/mfd/lp8788.c b/drivers/mfd/lp8788.c
index e1d7c9f18cc5..c3d3c9b4d3ad 100644
--- a/drivers/mfd/lp8788.c
+++ b/drivers/mfd/lp8788.c
@@ -203,7 +203,7 @@ static int lp8788_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 			       ARRAY_SIZE(lp8788_devs), NULL, 0, NULL);
 }
 
-static int __devexit lp8788_remove(struct i2c_client *cl)
+static int lp8788_remove(struct i2c_client *cl)
 {
 	struct lp8788 *lp = i2c_get_clientdata(cl);
 
diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index 7c83e1b56588..2ad24caa07db 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -878,7 +878,7 @@ static int lpc_ich_probe(struct pci_dev *dev,
 	return 0;
 }
 
-static void __devexit lpc_ich_remove(struct pci_dev *dev)
+static void lpc_ich_remove(struct pci_dev *dev)
 {
 	mfd_remove_devices(&dev->dev);
 	lpc_ich_restore_config_space(dev);
diff --git a/drivers/mfd/lpc_sch.c b/drivers/mfd/lpc_sch.c
index 5756a6af08dc..5624fcbba69b 100644
--- a/drivers/mfd/lpc_sch.c
+++ b/drivers/mfd/lpc_sch.c
@@ -164,7 +164,7 @@ out_dev:
 	return ret;
 }
 
-static void __devexit lpc_sch_remove(struct pci_dev *dev)
+static void lpc_sch_remove(struct pci_dev *dev)
 {
 	mfd_remove_devices(&dev->dev);
 }
diff --git a/drivers/mfd/max8907.c b/drivers/mfd/max8907.c
index 81ded7a4ca8c..e9b1c93a3ade 100644
--- a/drivers/mfd/max8907.c
+++ b/drivers/mfd/max8907.c
@@ -288,7 +288,7 @@ err_alloc_drvdata:
 	return ret;
 }
 
-static __devexit int max8907_i2c_remove(struct i2c_client *i2c)
+static int max8907_i2c_remove(struct i2c_client *i2c)
 {
 	struct max8907 *max8907 = i2c_get_clientdata(i2c);
 
diff --git a/drivers/mfd/max8925-core.c b/drivers/mfd/max8925-core.c
index 60325c49afda..e32466e865b9 100644
--- a/drivers/mfd/max8925-core.c
+++ b/drivers/mfd/max8925-core.c
@@ -901,7 +901,7 @@ out:
 	return ret;
 }
 
-void __devexit max8925_device_exit(struct max8925_chip *chip)
+void max8925_device_exit(struct max8925_chip *chip)
 {
 	if (chip->core_irq)
 		free_irq(chip->core_irq, chip);
diff --git a/drivers/mfd/max8925-i2c.c b/drivers/mfd/max8925-i2c.c
index 6e3d30aa00df..00b5b456063d 100644
--- a/drivers/mfd/max8925-i2c.c
+++ b/drivers/mfd/max8925-i2c.c
@@ -168,7 +168,7 @@ static int max8925_probe(struct i2c_client *client,
 	return 0;
 }
 
-static int __devexit max8925_remove(struct i2c_client *client)
+static int max8925_remove(struct i2c_client *client)
 {
 	struct max8925_chip *chip = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/mc13xxx-i2c.c b/drivers/mfd/mc13xxx-i2c.c
index 4a605fb63cbc..7957999f30bb 100644
--- a/drivers/mfd/mc13xxx-i2c.c
+++ b/drivers/mfd/mc13xxx-i2c.c
@@ -85,7 +85,7 @@ static int mc13xxx_i2c_probe(struct i2c_client *client,
 	return ret;
 }
 
-static int __devexit mc13xxx_i2c_remove(struct i2c_client *client)
+static int mc13xxx_i2c_remove(struct i2c_client *client)
 {
 	struct mc13xxx *mc13xxx = dev_get_drvdata(&client->dev);
 
diff --git a/drivers/mfd/mc13xxx-spi.c b/drivers/mfd/mc13xxx-spi.c
index e7acd0511156..cb32f69d80ba 100644
--- a/drivers/mfd/mc13xxx-spi.c
+++ b/drivers/mfd/mc13xxx-spi.c
@@ -159,7 +159,7 @@ static int mc13xxx_spi_probe(struct spi_device *spi)
 	return ret;
 }
 
-static int __devexit mc13xxx_spi_remove(struct spi_device *spi)
+static int mc13xxx_spi_remove(struct spi_device *spi)
 {
 	struct mc13xxx *mc13xxx = dev_get_drvdata(&spi->dev);
 
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index fc23dfbb6910..29b8ed21213e 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -652,7 +652,7 @@ end_probe:
  *
  * Reverses the effect of usbhs_omap_probe().
  */
-static int __devexit usbhs_omap_remove(struct platform_device *pdev)
+static int usbhs_omap_remove(struct platform_device *pdev)
 {
 	struct usbhs_hcd_omap *omap = platform_get_drvdata(pdev);
 
diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c
index 0b586885446b..401b976e3aff 100644
--- a/drivers/mfd/omap-usb-tll.c
+++ b/drivers/mfd/omap-usb-tll.c
@@ -348,7 +348,7 @@ end:
  *
  * Reverses the effect of usbtll_omap_probe().
  */
-static int __devexit usbtll_omap_remove(struct platform_device *pdev)
+static int usbtll_omap_remove(struct platform_device *pdev)
 {
 	struct usbtll_omap *tll = platform_get_drvdata(pdev);
 
diff --git a/drivers/mfd/pcf50633-adc.c b/drivers/mfd/pcf50633-adc.c
index dbd2f0d0078e..18b53cb72fea 100644
--- a/drivers/mfd/pcf50633-adc.c
+++ b/drivers/mfd/pcf50633-adc.c
@@ -218,7 +218,7 @@ static int pcf50633_adc_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __devexit pcf50633_adc_remove(struct platform_device *pdev)
+static int pcf50633_adc_remove(struct platform_device *pdev)
 {
 	struct pcf50633_adc *adc = platform_get_drvdata(pdev);
 	int i, head;
diff --git a/drivers/mfd/pcf50633-core.c b/drivers/mfd/pcf50633-core.c
index fc477353081e..64803f13bcec 100644
--- a/drivers/mfd/pcf50633-core.c
+++ b/drivers/mfd/pcf50633-core.c
@@ -275,7 +275,7 @@ static int pcf50633_probe(struct i2c_client *client,
 	return 0;
 }
 
-static int __devexit pcf50633_remove(struct i2c_client *client)
+static int pcf50633_remove(struct i2c_client *client)
 {
 	struct pcf50633 *pcf = i2c_get_clientdata(client);
 	int i;
diff --git a/drivers/mfd/pm8921-core.c b/drivers/mfd/pm8921-core.c
index 43491346e7d0..d4b297cbd801 100644
--- a/drivers/mfd/pm8921-core.c
+++ b/drivers/mfd/pm8921-core.c
@@ -165,7 +165,7 @@ err_read_rev:
 	return rc;
 }
 
-static int __devexit pm8921_remove(struct platform_device *pdev)
+static int pm8921_remove(struct platform_device *pdev)
 {
 	struct pm8xxx_drvdata *drvdata;
 	struct pm8921 *pmic = NULL;
diff --git a/drivers/mfd/pm8xxx-irq.c b/drivers/mfd/pm8xxx-irq.c
index 59c20ea329de..1360e20adf11 100644
--- a/drivers/mfd/pm8xxx-irq.c
+++ b/drivers/mfd/pm8xxx-irq.c
@@ -363,7 +363,7 @@ struct pm_irq_chip *  pm8xxx_irq_init(struct device *dev,
 	return chip;
 }
 
-int __devexit pm8xxx_irq_exit(struct pm_irq_chip *chip)
+int pm8xxx_irq_exit(struct pm_irq_chip *chip)
 {
 	irq_set_chained_handler(chip->devirq, NULL);
 	kfree(chip);
diff --git a/drivers/mfd/rc5t583.c b/drivers/mfd/rc5t583.c
index f721b13e986c..14bdaccefbec 100644
--- a/drivers/mfd/rc5t583.c
+++ b/drivers/mfd/rc5t583.c
@@ -303,7 +303,7 @@ err_add_devs:
 	return ret;
 }
 
-static int  __devexit rc5t583_i2c_remove(struct i2c_client *i2c)
+static int  rc5t583_i2c_remove(struct i2c_client *i2c)
 {
 	struct rc5t583 *rc5t583 = i2c_get_clientdata(i2c);
 
diff --git a/drivers/mfd/rdc321x-southbridge.c b/drivers/mfd/rdc321x-southbridge.c
index be46539c3080..21b7bef73507 100644
--- a/drivers/mfd/rdc321x-southbridge.c
+++ b/drivers/mfd/rdc321x-southbridge.c
@@ -91,7 +91,7 @@ static int rdc321x_sb_probe(struct pci_dev *pdev,
 			       NULL, 0, NULL);
 }
 
-static void __devexit rdc321x_sb_remove(struct pci_dev *pdev)
+static void rdc321x_sb_remove(struct pci_dev *pdev)
 {
 	mfd_remove_devices(&pdev->dev);
 }
diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index 9b53733cb297..9816c232e583 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -1685,7 +1685,7 @@ static void sm501_dev_remove(struct sm501_devdata *sm)
 	sm501_gpio_remove(sm);
 }
 
-static void __devexit sm501_pci_remove(struct pci_dev *dev)
+static void sm501_pci_remove(struct pci_dev *dev)
 {
 	struct sm501_devdata *sm = pci_get_drvdata(dev);
 
diff --git a/drivers/mfd/sta2x11-mfd.c b/drivers/mfd/sta2x11-mfd.c
index 57f3361d0cb0..d6284cacd27a 100644
--- a/drivers/mfd/sta2x11-mfd.c
+++ b/drivers/mfd/sta2x11-mfd.c
@@ -89,7 +89,7 @@ static int sta2x11_mfd_add(struct pci_dev *pdev, gfp_t flags)
 	return 0;
 }
 
-static int __devexit mfd_remove(struct pci_dev *pdev)
+static int mfd_remove(struct pci_dev *pdev)
 {
 	struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev);
 
diff --git a/drivers/mfd/stmpe-i2c.c b/drivers/mfd/stmpe-i2c.c
index 8195ca2ac74b..36df18778029 100644
--- a/drivers/mfd/stmpe-i2c.c
+++ b/drivers/mfd/stmpe-i2c.c
@@ -63,7 +63,7 @@ stmpe_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 	return stmpe_probe(&i2c_ci, id->driver_data);
 }
 
-static int __devexit stmpe_i2c_remove(struct i2c_client *i2c)
+static int stmpe_i2c_remove(struct i2c_client *i2c)
 {
 	struct stmpe *stmpe = dev_get_drvdata(&i2c->dev);
 
diff --git a/drivers/mfd/stmpe-spi.c b/drivers/mfd/stmpe-spi.c
index 52774338998f..973659f8abd9 100644
--- a/drivers/mfd/stmpe-spi.c
+++ b/drivers/mfd/stmpe-spi.c
@@ -101,7 +101,7 @@ stmpe_spi_probe(struct spi_device *spi)
 	return stmpe_probe(&spi_ci, id->driver_data);
 }
 
-static int __devexit stmpe_spi_remove(struct spi_device *spi)
+static int stmpe_spi_remove(struct spi_device *spi)
 {
 	struct stmpe *stmpe = dev_get_drvdata(&spi->dev);
 
diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c
index 3dbfe9ab889c..3f10591ea94e 100644
--- a/drivers/mfd/syscon.c
+++ b/drivers/mfd/syscon.c
@@ -138,7 +138,7 @@ static int syscon_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __devexit syscon_remove(struct platform_device *pdev)
+static int syscon_remove(struct platform_device *pdev)
 {
 	struct syscon *syscon;
 
diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c
index 7e197f788b0a..a06d66b929b1 100644
--- a/drivers/mfd/tc3589x.c
+++ b/drivers/mfd/tc3589x.c
@@ -402,7 +402,7 @@ out_free:
 	return ret;
 }
 
-static int __devexit tc3589x_remove(struct i2c_client *client)
+static int tc3589x_remove(struct i2c_client *client)
 {
 	struct tc3589x *tc3589x = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/tc6387xb.c b/drivers/mfd/tc6387xb.c
index ca18f262c34a..366f7b906278 100644
--- a/drivers/mfd/tc6387xb.c
+++ b/drivers/mfd/tc6387xb.c
@@ -208,7 +208,7 @@ err_no_irq:
 	return ret;
 }
 
-static int __devexit tc6387xb_remove(struct platform_device *dev)
+static int tc6387xb_remove(struct platform_device *dev)
 {
 	struct tc6387xb *tc6387xb = platform_get_drvdata(dev);
 
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 1ff8ed6390d1..15e1463e5e13 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -731,7 +731,7 @@ err_kzalloc:
 	return ret;
 }
 
-static int __devexit tc6393xb_remove(struct platform_device *dev)
+static int tc6393xb_remove(struct platform_device *dev)
 {
 	struct tc6393xb_platform_data *tcpd = dev->dev.platform_data;
 	struct tc6393xb *tc6393xb = platform_get_drvdata(dev);
diff --git a/drivers/mfd/ti-ssp.c b/drivers/mfd/ti-ssp.c
index b177f96da864..09a14cec351b 100644
--- a/drivers/mfd/ti-ssp.c
+++ b/drivers/mfd/ti-ssp.c
@@ -433,7 +433,7 @@ error_res:
 	return error;
 }
 
-static int __devexit ti_ssp_remove(struct platform_device *pdev)
+static int ti_ssp_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct ti_ssp *ssp = dev_get_drvdata(dev);
diff --git a/drivers/mfd/timberdale.c b/drivers/mfd/timberdale.c
index a305ac109496..59e0ee247e86 100644
--- a/drivers/mfd/timberdale.c
+++ b/drivers/mfd/timberdale.c
@@ -840,7 +840,7 @@ err_enable:
 	return -ENODEV;
 }
 
-static void __devexit timb_remove(struct pci_dev *dev)
+static void timb_remove(struct pci_dev *dev)
 {
 	struct timberdale_device *priv = pci_get_drvdata(dev);
 
diff --git a/drivers/mfd/tps6105x.c b/drivers/mfd/tps6105x.c
index 75a84ac4672e..1d302f583adf 100644
--- a/drivers/mfd/tps6105x.c
+++ b/drivers/mfd/tps6105x.c
@@ -199,7 +199,7 @@ fail:
 	return ret;
 }
 
-static int __devexit tps6105x_remove(struct i2c_client *client)
+static int tps6105x_remove(struct i2c_client *client)
 {
 	struct tps6105x *tps6105x = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/tps65090.c b/drivers/mfd/tps65090.c
index 0c446eb86bdb..382a857b0dde 100644
--- a/drivers/mfd/tps65090.c
+++ b/drivers/mfd/tps65090.c
@@ -308,7 +308,7 @@ err_exit:
 	return ret;
 }
 
-static int __devexit tps65090_i2c_remove(struct i2c_client *client)
+static int tps65090_i2c_remove(struct i2c_client *client)
 {
 	struct tps65090 *tps65090 = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c
index 8cba75750e91..e14e252e3473 100644
--- a/drivers/mfd/tps65217.c
+++ b/drivers/mfd/tps65217.c
@@ -214,7 +214,7 @@ static int tps65217_probe(struct i2c_client *client,
 	return 0;
 }
 
-static int __devexit tps65217_remove(struct i2c_client *client)
+static int tps65217_remove(struct i2c_client *client)
 {
 	struct tps65217 *tps = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c
index 975fbb5f36aa..9f92c3b22093 100644
--- a/drivers/mfd/tps6586x.c
+++ b/drivers/mfd/tps6586x.c
@@ -548,7 +548,7 @@ err_mfd_add:
 	return ret;
 }
 
-static int __devexit tps6586x_i2c_remove(struct i2c_client *client)
+static int tps6586x_i2c_remove(struct i2c_client *client)
 {
 	struct tps6586x *tps6586x = i2c_get_clientdata(client);
 
diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index 3a3402290a74..ce054654f5bb 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -302,7 +302,7 @@ static int tps65910_i2c_probe(struct i2c_client *i2c,
 	return ret;
 }
 
-static __devexit int tps65910_i2c_remove(struct i2c_client *i2c)
+static int tps65910_i2c_remove(struct i2c_client *i2c)
 {
 	struct tps65910 *tps65910 = i2c_get_clientdata(i2c);
 
diff --git a/drivers/mfd/tps65911-comparator.c b/drivers/mfd/tps65911-comparator.c
index b3d268f95a77..c0816ebd9d7e 100644
--- a/drivers/mfd/tps65911-comparator.c
+++ b/drivers/mfd/tps65911-comparator.c
@@ -152,7 +152,7 @@ static int tps65911_comparator_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static __devexit int tps65911_comparator_remove(struct platform_device *pdev)
+static int tps65911_comparator_remove(struct platform_device *pdev)
 {
 	struct tps65910 *tps65910;
 
diff --git a/drivers/mfd/tps65912-spi.c b/drivers/mfd/tps65912-spi.c
index 6366576a3056..b45f460d299f 100644
--- a/drivers/mfd/tps65912-spi.c
+++ b/drivers/mfd/tps65912-spi.c
@@ -99,7 +99,7 @@ static int tps65912_spi_probe(struct spi_device *spi)
 	return tps65912_device_init(tps65912);
 }
 
-static int __devexit tps65912_spi_remove(struct spi_device *spi)
+static int tps65912_spi_remove(struct spi_device *spi)
 {
 	struct tps65912 *tps65912 = spi_get_drvdata(spi);
 
diff --git a/drivers/mfd/twl4030-audio.c b/drivers/mfd/twl4030-audio.c
index aacccdcf997c..e16edca92670 100644
--- a/drivers/mfd/twl4030-audio.c
+++ b/drivers/mfd/twl4030-audio.c
@@ -269,7 +269,7 @@ static int twl4030_audio_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int __devexit twl4030_audio_remove(struct platform_device *pdev)
+static int twl4030_audio_remove(struct platform_device *pdev)
 {
 	mfd_remove_devices(&pdev->dev);
 	platform_set_drvdata(pdev, NULL);
diff --git a/drivers/mfd/twl4030-madc.c b/drivers/mfd/twl4030-madc.c
index 228d5aacd332..a39dcf3e2133 100644
--- a/drivers/mfd/twl4030-madc.c
+++ b/drivers/mfd/twl4030-madc.c
@@ -785,7 +785,7 @@ err_power:
 	return ret;
 }
 
-static int __devexit twl4030_madc_remove(struct platform_device *pdev)
+static int twl4030_madc_remove(struct platform_device *pdev)
 {
 	struct twl4030_madc_data *madc = platform_get_drvdata(pdev);
 
diff --git a/drivers/mfd/vx855.c b/drivers/mfd/vx855.c
index 66ef03b02569..757ecc63338c 100644
--- a/drivers/mfd/vx855.c
+++ b/drivers/mfd/vx855.c
@@ -112,7 +112,7 @@ out:
 	return ret;
 }
 
-static void __devexit vx855_remove(struct pci_dev *pdev)
+static void vx855_remove(struct pci_dev *pdev)
 {
 	mfd_remove_devices(&pdev->dev);
 	pci_disable_device(pdev);
diff --git a/drivers/mfd/wm831x-spi.c b/drivers/mfd/wm831x-spi.c
index 4c7225a53ba2..4e70e157a909 100644
--- a/drivers/mfd/wm831x-spi.c
+++ b/drivers/mfd/wm831x-spi.c
@@ -51,7 +51,7 @@ static int wm831x_spi_probe(struct spi_device *spi)
 	return wm831x_device_init(wm831x, type, spi->irq);
 }
 
-static int __devexit wm831x_spi_remove(struct spi_device *spi)
+static int wm831x_spi_remove(struct spi_device *spi)
 {
 	struct wm831x *wm831x = dev_get_drvdata(&spi->dev);
 
diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index 4e2432dc49f9..c7f62ac544ad 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -671,7 +671,7 @@ err:
 	return ret;
 }
 
-static __devexit void wm8994_device_exit(struct wm8994 *wm8994)
+static void wm8994_device_exit(struct wm8994 *wm8994)
 {
 	pm_runtime_disable(wm8994->dev);
 	mfd_remove_devices(wm8994->dev);
@@ -715,7 +715,7 @@ static int wm8994_i2c_probe(struct i2c_client *i2c,
 	return wm8994_device_init(wm8994, i2c->irq);
 }
 
-static __devexit int wm8994_i2c_remove(struct i2c_client *i2c)
+static int wm8994_i2c_remove(struct i2c_client *i2c)
 {
 	struct wm8994 *wm8994 = i2c_get_clientdata(i2c);
 
diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h
index 83f0bdc530b7..1cb5698b4d76 100644
--- a/include/linux/mfd/abx500/ab8500.h
+++ b/include/linux/mfd/abx500/ab8500.h
@@ -293,7 +293,7 @@ struct ab8500_platform_data {
 
 extern int ab8500_init(struct ab8500 *ab8500,
 				 enum ab8500_version version);
-extern int __devexit ab8500_exit(struct ab8500 *ab8500);
+extern int ab8500_exit(struct ab8500 *ab8500);
 
 extern int ab8500_suspend(struct ab8500 *ab8500);
 
diff --git a/include/linux/mfd/pm8xxx/irq.h b/include/linux/mfd/pm8xxx/irq.h
index ddaa7f5e9ed9..f83d6b43ecbb 100644
--- a/include/linux/mfd/pm8xxx/irq.h
+++ b/include/linux/mfd/pm8xxx/irq.h
@@ -39,7 +39,7 @@ struct pm_irq_chip;
 int pm8xxx_get_irq_stat(struct pm_irq_chip *chip, int irq);
 struct pm_irq_chip *pm8xxx_irq_init(struct device *dev,
 				const struct pm8xxx_irq_platform_data *pdata);
-int __devexit pm8xxx_irq_exit(struct pm_irq_chip *chip);
+int pm8xxx_irq_exit(struct pm_irq_chip *chip);
 #else
 static inline int pm8xxx_get_irq_stat(struct pm_irq_chip *chip, int irq)
 {
@@ -51,7 +51,7 @@ static inline struct pm_irq_chip *pm8xxx_irq_init(
 {
 	return ERR_PTR(-ENXIO);
 }
-static inline int __devexit pm8xxx_irq_exit(struct pm_irq_chip *chip)
+static inline int pm8xxx_irq_exit(struct pm_irq_chip *chip)
 {
 	return -ENXIO;
 }
-- 
cgit v1.2.3-55-g7522


From b40b97ae736cad3084b13d2969b10c474572de89 Mon Sep 17 00:00:00 2001
From: Bill Pemberton
Date: Wed, 21 Nov 2012 15:34:57 -0500
Subject: PCI: Remove CONFIG_HOTPLUG ifdefs

Remove conditional code based on CONFIG_HOTPLUG being false.  It's
always on now in preparation of it going away as an option.

Signed-off-by: Bill Pemberton <wfp5p@virginia.edu>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/pci-driver.c | 15 ---------------
 drivers/pci/pci-sysfs.c  |  7 -------
 drivers/pci/pci.h        |  4 ----
 drivers/pci/probe.c      |  2 --
 include/linux/pci.h      |  2 --
 5 files changed, 30 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 6c94fc9489e7..8919801cb27e 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -89,10 +89,6 @@ static void pci_free_dynids(struct pci_driver *drv)
 	spin_unlock(&drv->dynids.lock);
 }
 
-/*
- * Dynamic device ID manipulation via sysfs is disabled for !CONFIG_HOTPLUG
- */
-#ifdef CONFIG_HOTPLUG
 /**
  * store_new_id - sysfs frontend to pci_add_dynid()
  * @driver: target device driver
@@ -191,10 +187,6 @@ static struct driver_attribute pci_drv_attrs[] = {
 	__ATTR_NULL,
 };
 
-#else
-#define pci_drv_attrs	NULL
-#endif /* CONFIG_HOTPLUG */
-
 /**
  * pci_match_id - See if a pci device matches a given pci_id table
  * @ids: array of PCI device id structures to search in
@@ -1223,13 +1215,6 @@ void pci_dev_put(struct pci_dev *dev)
 		put_device(&dev->dev);
 }
 
-#ifndef CONFIG_HOTPLUG
-int pci_uevent(struct device *dev, struct kobj_uevent_env *env)
-{
-	return -ENODEV;
-}
-#endif
-
 struct bus_type pci_bus_type = {
 	.name		= "pci",
 	.match		= pci_bus_match,
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index f39378d9da15..68d56f02e721 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -284,7 +284,6 @@ msi_bus_store(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#ifdef CONFIG_HOTPLUG
 static DEFINE_MUTEX(pci_remove_rescan_mutex);
 static ssize_t bus_rescan_store(struct bus_type *bus, const char *buf,
 				size_t count)
@@ -377,8 +376,6 @@ dev_bus_rescan_store(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#endif
-
 #if defined(CONFIG_PM_RUNTIME) && defined(CONFIG_ACPI)
 static ssize_t d3cold_allowed_store(struct device *dev,
 				    struct device_attribute *attr,
@@ -424,10 +421,8 @@ struct device_attribute pci_dev_attrs[] = {
 	__ATTR(broken_parity_status,(S_IRUGO|S_IWUSR),
 		broken_parity_status_show,broken_parity_status_store),
 	__ATTR(msi_bus, 0644, msi_bus_show, msi_bus_store),
-#ifdef CONFIG_HOTPLUG
 	__ATTR(remove, (S_IWUSR|S_IWGRP), NULL, remove_store),
 	__ATTR(rescan, (S_IWUSR|S_IWGRP), NULL, dev_rescan_store),
-#endif
 #if defined(CONFIG_PM_RUNTIME) && defined(CONFIG_ACPI)
 	__ATTR(d3cold_allowed, 0644, d3cold_allowed_show, d3cold_allowed_store),
 #endif
@@ -435,9 +430,7 @@ struct device_attribute pci_dev_attrs[] = {
 };
 
 struct device_attribute pcibus_dev_attrs[] = {
-#ifdef CONFIG_HOTPLUG
 	__ATTR(rescan, (S_IWUSR|S_IWGRP), NULL, dev_bus_rescan_store),
-#endif
 	__ATTR(cpuaffinity, S_IRUGO, pci_bus_show_cpumaskaffinity, NULL),
 	__ATTR(cpulistaffinity, S_IRUGO, pci_bus_show_cpulistaffinity, NULL),
 	__ATTR_NULL,
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index fd92aab9904b..6e993af4d30b 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -159,11 +159,7 @@ static inline int pci_no_d1d2(struct pci_dev *dev)
 }
 extern struct device_attribute pci_dev_attrs[];
 extern struct device_attribute pcibus_dev_attrs[];
-#ifdef CONFIG_HOTPLUG
 extern struct bus_attribute pci_bus_attrs[];
-#else
-#define pci_bus_attrs	NULL
-#endif
 
 
 /**
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ec909afa90b6..034cb1c73092 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1864,7 +1864,6 @@ struct pci_bus * __devinit pci_scan_bus(int bus, struct pci_ops *ops,
 }
 EXPORT_SYMBOL(pci_scan_bus);
 
-#ifdef CONFIG_HOTPLUG
 /**
  * pci_rescan_bus_bridge_resize - scan a PCI bus for devices.
  * @bridge: PCI bridge for the bus to scan
@@ -1894,7 +1893,6 @@ EXPORT_SYMBOL(pci_add_new_bus);
 EXPORT_SYMBOL(pci_scan_slot);
 EXPORT_SYMBOL(pci_scan_bridge);
 EXPORT_SYMBOL_GPL(pci_scan_child_bus);
-#endif
 
 static int __init pci_sort_bf_cmp(const struct device *d_a, const struct device *d_b)
 {
diff --git a/include/linux/pci.h b/include/linux/pci.h
index ee2179546c63..699e9a920eca 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -941,10 +941,8 @@ void set_pcie_hotplug_bridge(struct pci_dev *pdev);
 
 /* Functions for PCI Hotplug drivers to use */
 int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap);
-#ifdef CONFIG_HOTPLUG
 unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge);
 unsigned int pci_rescan_bus(struct pci_bus *bus);
-#endif
 
 /* Vital product data routines */
 ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
-- 
cgit v1.2.3-55-g7522


From 15856ad50bf5ea02a5ee22399c036d49e7e1124d Mon Sep 17 00:00:00 2001
From: Bill Pemberton
Date: Wed, 21 Nov 2012 15:35:00 -0500
Subject: PCI: Remove __dev* markings

CONFIG_HOTPLUG is going away as an option so __devexit_p, __devint,
__devinitdata, __devinitconst, and _devexit are no longer needed.

Signed-off-by: Bill Pemberton <wfp5p@virginia.edu>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/hotplug/cpcihp_zt5550.c |   4 +-
 drivers/pci/ioapic.c                |   6 +-
 drivers/pci/pci.c                   |   4 +-
 drivers/pci/pcie/aer/aerdrv.c       |   4 +-
 drivers/pci/pcie/portdrv_pci.c      |   2 +-
 drivers/pci/probe.c                 |  18 ++---
 drivers/pci/quirks.c                | 132 ++++++++++++++++++------------------
 drivers/pci/xen-pcifront.c          |  10 +--
 include/linux/pci.h                 |   6 +-
 9 files changed, 93 insertions(+), 93 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/hotplug/cpcihp_zt5550.c b/drivers/pci/hotplug/cpcihp_zt5550.c
index 6bf8d2ab164f..449b4bbc8301 100644
--- a/drivers/pci/hotplug/cpcihp_zt5550.c
+++ b/drivers/pci/hotplug/cpcihp_zt5550.c
@@ -271,7 +271,7 @@ init_hc_error:
 
 }
 
-static void __devexit zt5550_hc_remove_one(struct pci_dev *pdev)
+static void zt5550_hc_remove_one(struct pci_dev *pdev)
 {
 	cpci_hp_stop();
 	cpci_hp_unregister_bus(bus0);
@@ -290,7 +290,7 @@ static struct pci_driver zt5550_hc_driver = {
 	.name		= "zt5550_hc",
 	.id_table	= zt5550_hc_pci_tbl,
 	.probe		= zt5550_hc_init_one,
-	.remove		= __devexit_p(zt5550_hc_remove_one),
+	.remove		= zt5550_hc_remove_one,
 };
 
 static int __init zt5550_init(void)
diff --git a/drivers/pci/ioapic.c b/drivers/pci/ioapic.c
index 205af8dc83c2..2eca902a4283 100644
--- a/drivers/pci/ioapic.c
+++ b/drivers/pci/ioapic.c
@@ -27,7 +27,7 @@ struct ioapic {
 	u32		gsi_base;
 };
 
-static int __devinit ioapic_probe(struct pci_dev *dev, const struct pci_device_id *ent)
+static int ioapic_probe(struct pci_dev *dev, const struct pci_device_id *ent)
 {
 	acpi_handle handle;
 	acpi_status status;
@@ -88,7 +88,7 @@ exit_free:
 	return -ENODEV;
 }
 
-static void __devexit ioapic_remove(struct pci_dev *dev)
+static void ioapic_remove(struct pci_dev *dev)
 {
 	struct ioapic *ioapic = pci_get_drvdata(dev);
 
@@ -110,7 +110,7 @@ static struct pci_driver ioapic_driver = {
 	.name		= "ioapic",
 	.id_table	= ioapic_devices,
 	.probe		= ioapic_probe,
-	.remove		= __devexit_p(ioapic_remove),
+	.remove		= ioapic_remove,
 };
 
 static int __init ioapic_init(void)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index aabf64798bda..bdf66b500f22 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -86,7 +86,7 @@ enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_TUNE_OFF;
  * the dfl or actual value as it sees fit.  Don't forget this is
  * measured in 32-bit words, not bytes.
  */
-u8 pci_dfl_cache_line_size __devinitdata = L1_CACHE_BYTES >> 2;
+u8 pci_dfl_cache_line_size = L1_CACHE_BYTES >> 2;
 u8 pci_cache_line_size;
 
 /*
@@ -3857,7 +3857,7 @@ static int __init pci_resource_alignment_sysfs_init(void)
 
 late_initcall(pci_resource_alignment_sysfs_init);
 
-static void __devinit pci_no_domains(void)
+static void pci_no_domains(void)
 {
 #ifdef CONFIG_PCI_DOMAINS
 	pci_domains_supported = 0;
diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
index 030cf12d5468..76ef634caf6f 100644
--- a/drivers/pci/pcie/aer/aerdrv.c
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -41,7 +41,7 @@ MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 
-static int __devinit aer_probe(struct pcie_device *dev);
+static int aer_probe(struct pcie_device *dev);
 static void aer_remove(struct pcie_device *dev);
 static pci_ers_result_t aer_error_detected(struct pci_dev *dev,
 	enum pci_channel_state error);
@@ -300,7 +300,7 @@ static void aer_remove(struct pcie_device *dev)
  *
  * Invoked when PCI Express bus loads AER service driver.
  */
-static int __devinit aer_probe(struct pcie_device *dev)
+static int aer_probe(struct pcie_device *dev)
 {
 	int status;
 	struct aer_rpc *rpc;
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 0761d90ca279..d4824cb78b49 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -182,7 +182,7 @@ static const struct pci_device_id port_runtime_pm_black_list[] = {
  * this port device.
  *
  */
-static int __devinit pcie_portdrv_probe(struct pci_dev *dev,
+static int pcie_portdrv_probe(struct pci_dev *dev,
 					const struct pci_device_id *id)
 {
 	int status;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 034cb1c73092..3683f6094e3f 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -305,7 +305,7 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 	}
 }
 
-static void __devinit pci_read_bridge_io(struct pci_bus *child)
+static void pci_read_bridge_io(struct pci_bus *child)
 {
 	struct pci_dev *dev = child->self;
 	u8 io_base_lo, io_limit_lo;
@@ -345,7 +345,7 @@ static void __devinit pci_read_bridge_io(struct pci_bus *child)
 	}
 }
 
-static void __devinit pci_read_bridge_mmio(struct pci_bus *child)
+static void pci_read_bridge_mmio(struct pci_bus *child)
 {
 	struct pci_dev *dev = child->self;
 	u16 mem_base_lo, mem_limit_lo;
@@ -367,7 +367,7 @@ static void __devinit pci_read_bridge_mmio(struct pci_bus *child)
 	}
 }
 
-static void __devinit pci_read_bridge_mmio_pref(struct pci_bus *child)
+static void pci_read_bridge_mmio_pref(struct pci_bus *child)
 {
 	struct pci_dev *dev = child->self;
 	u16 mem_base_lo, mem_limit_lo;
@@ -417,7 +417,7 @@ static void __devinit pci_read_bridge_mmio_pref(struct pci_bus *child)
 	}
 }
 
-void __devinit pci_read_bridge_bases(struct pci_bus *child)
+void pci_read_bridge_bases(struct pci_bus *child)
 {
 	struct pci_dev *dev = child->self;
 	struct resource *res;
@@ -705,7 +705,7 @@ static void pci_fixup_parent_subordinate_busnr(struct pci_bus *child, int max)
  * them, we proceed to assigning numbers to the remaining buses in
  * order to avoid overlaps between old and new bus numbers.
  */
-int __devinit pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
+int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 {
 	struct pci_bus *child;
 	int is_cardbus = (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS);
@@ -1586,7 +1586,7 @@ void pcie_bus_configure_settings(struct pci_bus *bus, u8 mpss)
 }
 EXPORT_SYMBOL_GPL(pcie_bus_configure_settings);
 
-unsigned int __devinit pci_scan_child_bus(struct pci_bus *bus)
+unsigned int pci_scan_child_bus(struct pci_bus *bus)
 {
 	unsigned int devfn, pass, max = bus->busn_res.start;
 	struct pci_dev *dev;
@@ -1790,7 +1790,7 @@ void pci_bus_release_busn_res(struct pci_bus *b)
 			res, ret ? "can not be" : "is");
 }
 
-struct pci_bus * __devinit pci_scan_root_bus(struct device *parent, int bus,
+struct pci_bus *pci_scan_root_bus(struct device *parent, int bus,
 		struct pci_ops *ops, void *sysdata, struct list_head *resources)
 {
 	struct pci_host_bridge_window *window;
@@ -1826,7 +1826,7 @@ struct pci_bus * __devinit pci_scan_root_bus(struct device *parent, int bus,
 EXPORT_SYMBOL(pci_scan_root_bus);
 
 /* Deprecated; use pci_scan_root_bus() instead */
-struct pci_bus * __devinit pci_scan_bus_parented(struct device *parent,
+struct pci_bus *pci_scan_bus_parented(struct device *parent,
 		int bus, struct pci_ops *ops, void *sysdata)
 {
 	LIST_HEAD(resources);
@@ -1844,7 +1844,7 @@ struct pci_bus * __devinit pci_scan_bus_parented(struct device *parent,
 }
 EXPORT_SYMBOL(pci_scan_bus_parented);
 
-struct pci_bus * __devinit pci_scan_bus(int bus, struct pci_ops *ops,
+struct pci_bus *pci_scan_bus(int bus, struct pci_ops *ops,
 					void *sysdata)
 {
 	LIST_HEAD(resources);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 7a451ff56ecc..22ad3ee0cf0b 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -37,7 +37,7 @@
  * key system devices. For devices that need to have mmio decoding always-on,
  * we need to set the dev->mmio_always_on bit.
  */
-static void __devinit quirk_mmio_always_on(struct pci_dev *dev)
+static void quirk_mmio_always_on(struct pci_dev *dev)
 {
 	dev->mmio_always_on = 1;
 }
@@ -48,7 +48,7 @@ DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_ANY_ID, PCI_ANY_ID,
  * Mark this device with a broken_parity_status, to allow
  * PCI scanning code to "skip" this now blacklisted device.
  */
-static void __devinit quirk_mellanox_tavor(struct pci_dev *dev)
+static void quirk_mellanox_tavor(struct pci_dev *dev)
 {
 	dev->broken_parity_status = 1;	/* This device gives false positives */
 }
@@ -83,7 +83,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82441,	quirk_p
     This appears to be BIOS not version dependent. So presumably there is a 
     chipset level fix */
     
-static void __devinit quirk_isa_dma_hangs(struct pci_dev *dev)
+static void quirk_isa_dma_hangs(struct pci_dev *dev)
 {
 	if (!isa_dma_bridge_buggy) {
 		isa_dma_bridge_buggy=1;
@@ -106,7 +106,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_3,	quirk_isa_d
  * Intel NM10 "TigerPoint" LPC PM1a_STS.BM_STS must be clear
  * for some HT machines to use C4 w/o hanging.
  */
-static void __devinit quirk_tigerpoint_bm_sts(struct pci_dev *dev)
+static void quirk_tigerpoint_bm_sts(struct pci_dev *dev)
 {
 	u32 pmbase;
 	u16 pm1a;
@@ -125,7 +125,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGP_LPC, quirk
 /*
  *	Chipsets where PCI->PCI transfers vanish or hang
  */
-static void __devinit quirk_nopcipci(struct pci_dev *dev)
+static void quirk_nopcipci(struct pci_dev *dev)
 {
 	if ((pci_pci_problems & PCIPCI_FAIL)==0) {
 		dev_info(&dev->dev, "Disabling direct PCI/PCI transfers\n");
@@ -135,7 +135,7 @@ static void __devinit quirk_nopcipci(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_5597,		quirk_nopcipci);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_496,		quirk_nopcipci);
 
-static void __devinit quirk_nopciamd(struct pci_dev *dev)
+static void quirk_nopciamd(struct pci_dev *dev)
 {
 	u8 rev;
 	pci_read_config_byte(dev, 0x08, &rev);
@@ -150,7 +150,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_8151_0,	quirk_nopci
 /*
  *	Triton requires workarounds to be used by the drivers
  */
-static void __devinit quirk_triton(struct pci_dev *dev)
+static void quirk_triton(struct pci_dev *dev)
 {
 	if ((pci_pci_problems&PCIPCI_TRITON)==0) {
 		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
@@ -229,7 +229,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8361,		quirk_viala
 /*
  *	VIA Apollo VP3 needs ETBF on BT848/878
  */
-static void __devinit quirk_viaetbf(struct pci_dev *dev)
+static void quirk_viaetbf(struct pci_dev *dev)
 {
 	if ((pci_pci_problems&PCIPCI_VIAETBF)==0) {
 		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
@@ -238,7 +238,7 @@ static void __devinit quirk_viaetbf(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C597_0,	quirk_viaetbf);
 
-static void __devinit quirk_vsfx(struct pci_dev *dev)
+static void quirk_vsfx(struct pci_dev *dev)
 {
 	if ((pci_pci_problems&PCIPCI_VSFX)==0) {
 		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
@@ -253,7 +253,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C576,	quirk_vsfx)
  *	workaround applied too
  *	[Info kindly provided by ALi]
  */	
-static void __devinit quirk_alimagik(struct pci_dev *dev)
+static void quirk_alimagik(struct pci_dev *dev)
 {
 	if ((pci_pci_problems&PCIPCI_ALIMAGIK)==0) {
 		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
@@ -267,7 +267,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, 	PCI_DEVICE_ID_AL_M1651, 	quirk_alimag
  *	Natoma has some interesting boundary conditions with Zoran stuff
  *	at least
  */
-static void __devinit quirk_natoma(struct pci_dev *dev)
+static void quirk_natoma(struct pci_dev *dev)
 {
 	if ((pci_pci_problems&PCIPCI_NATOMA)==0) {
 		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
@@ -285,7 +285,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443BX_2, 	qu
  *  This chip can cause PCI parity errors if config register 0xA0 is read
  *  while DMAs are occurring.
  */
-static void __devinit quirk_citrine(struct pci_dev *dev)
+static void quirk_citrine(struct pci_dev *dev)
 {
 	dev->cfg_size = 0xA0;
 }
@@ -295,7 +295,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM,	PCI_DEVICE_ID_IBM_CITRINE,	quirk_cit
  *  S3 868 and 968 chips report region size equal to 32M, but they decode 64M.
  *  If it's needed, re-allocate the region.
  */
-static void __devinit quirk_s3_64M(struct pci_dev *dev)
+static void quirk_s3_64M(struct pci_dev *dev)
 {
 	struct resource *r = &dev->resource[0];
 
@@ -313,7 +313,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3,	PCI_DEVICE_ID_S3_968,		quirk_s3_64M);
  * BAR0 should be 8 bytes; instead, it may be set to something like 8k
  * (which conflicts w/ BAR1's memory range).
  */
-static void __devinit quirk_cs5536_vsa(struct pci_dev *dev)
+static void quirk_cs5536_vsa(struct pci_dev *dev)
 {
 	if (pci_resource_len(dev, 0) != 8) {
 		struct resource *res = &dev->resource[0];
@@ -324,7 +324,7 @@ static void __devinit quirk_cs5536_vsa(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, quirk_cs5536_vsa);
 
-static void __devinit quirk_io_region(struct pci_dev *dev, unsigned region,
+static void quirk_io_region(struct pci_dev *dev, unsigned region,
 	unsigned size, int nr, const char *name)
 {
 	region &= ~(size-1);
@@ -352,7 +352,7 @@ static void __devinit quirk_io_region(struct pci_dev *dev, unsigned region,
  *	ATI Northbridge setups MCE the processor if you even
  *	read somewhere between 0x3b0->0x3bb or read 0x3d3
  */
-static void __devinit quirk_ati_exploding_mce(struct pci_dev *dev)
+static void quirk_ati_exploding_mce(struct pci_dev *dev)
 {
 	dev_info(&dev->dev, "ATI Northbridge, reserving I/O ports 0x3b0 to 0x3bb\n");
 	/* Mae rhaid i ni beidio ag edrych ar y lleoliadiau I/O hyn */
@@ -372,7 +372,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI,	PCI_DEVICE_ID_ATI_RS100,   quirk_ati_
  *	0xE0 (64 bytes of ACPI registers)
  *	0xE2 (32 bytes of SMB registers)
  */
-static void __devinit quirk_ali7101_acpi(struct pci_dev *dev)
+static void quirk_ali7101_acpi(struct pci_dev *dev)
 {
 	u16 region;
 
@@ -440,7 +440,7 @@ static void piix4_mem_quirk(struct pci_dev *dev, const char *name, unsigned int
  *	0x90 (16 bytes of SMB registers)
  * and a few strange programmable PIIX4 device resources.
  */
-static void __devinit quirk_piix4_acpi(struct pci_dev *dev)
+static void quirk_piix4_acpi(struct pci_dev *dev)
 {
 	u32 region, res_a;
 
@@ -489,7 +489,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82443MX_3,	qui
  *	0x40 (128 bytes of ACPI, GPIO & TCO registers)
  *	0x58 (64 bytes of GPIO I/O space)
  */
-static void __devinit quirk_ich4_lpc_acpi(struct pci_dev *dev)
+static void quirk_ich4_lpc_acpi(struct pci_dev *dev)
 {
 	u32 region;
 	u8 enable;
@@ -531,7 +531,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801DB_12,
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801EB_0,		quirk_ich4_lpc_acpi);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_ESB_1,		quirk_ich4_lpc_acpi);
 
-static void __devinit ich6_lpc_acpi_gpio(struct pci_dev *dev)
+static void ich6_lpc_acpi_gpio(struct pci_dev *dev)
 {
 	u32 region;
 	u8 enable;
@@ -555,7 +555,7 @@ static void __devinit ich6_lpc_acpi_gpio(struct pci_dev *dev)
 	}
 }
 
-static void __devinit ich6_lpc_generic_decode(struct pci_dev *dev, unsigned reg, const char *name, int dynsize)
+static void ich6_lpc_generic_decode(struct pci_dev *dev, unsigned reg, const char *name, int dynsize)
 {
 	u32 val;
 	u32 size, base;
@@ -583,7 +583,7 @@ static void __devinit ich6_lpc_generic_decode(struct pci_dev *dev, unsigned reg,
 	dev_info(&dev->dev, "%s PIO at %04x-%04x\n", name, base, base+size-1);
 }
 
-static void __devinit quirk_ich6_lpc(struct pci_dev *dev)
+static void quirk_ich6_lpc(struct pci_dev *dev)
 {
 	/* Shared ACPI/GPIO decode with all ICH6+ */
 	ich6_lpc_acpi_gpio(dev);
@@ -595,7 +595,7 @@ static void __devinit quirk_ich6_lpc(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_0, quirk_ich6_lpc);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_1, quirk_ich6_lpc);
 
-static void __devinit ich7_lpc_generic_decode(struct pci_dev *dev, unsigned reg, const char *name)
+static void ich7_lpc_generic_decode(struct pci_dev *dev, unsigned reg, const char *name)
 {
 	u32 val;
 	u32 mask, base;
@@ -619,7 +619,7 @@ static void __devinit ich7_lpc_generic_decode(struct pci_dev *dev, unsigned reg,
 }
 
 /* ICH7-10 has the same common LPC generic IO decode registers */
-static void __devinit quirk_ich7_lpc(struct pci_dev *dev)
+static void quirk_ich7_lpc(struct pci_dev *dev)
 {
 	/* We share the common ACPI/GPIO decode with ICH6 */
 	ich6_lpc_acpi_gpio(dev);
@@ -648,7 +648,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ICH10_1, qui
  * VIA ACPI: One IO region pointed to by longword at
  *	0x48 or 0x20 (256 bytes of ACPI registers)
  */
-static void __devinit quirk_vt82c586_acpi(struct pci_dev *dev)
+static void quirk_vt82c586_acpi(struct pci_dev *dev)
 {
 	u32 region;
 
@@ -666,7 +666,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C586_3,	quirk_vt
  *	0x70 (128 bytes of hardware monitoring register)
  *	0x90 (16 bytes of SMB registers)
  */
-static void __devinit quirk_vt82c686_acpi(struct pci_dev *dev)
+static void quirk_vt82c686_acpi(struct pci_dev *dev)
 {
 	u16 hm;
 	u32 smb;
@@ -688,7 +688,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C686_4,	quirk_vt
  *	0x88 (128 bytes of power management registers)
  *	0xd0 (16 bytes of SMB registers)
  */
-static void __devinit quirk_vt8235_acpi(struct pci_dev *dev)
+static void quirk_vt8235_acpi(struct pci_dev *dev)
 {
 	u16 pm, smb;
 
@@ -706,7 +706,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8235,	quirk_vt8235
  * TI XIO2000a PCIe-PCI Bridge erroneously reports it supports fast back-to-back:
  *	Disable fast back-to-back on the secondary bus segment
  */
-static void __devinit quirk_xio2000a(struct pci_dev *dev)
+static void quirk_xio2000a(struct pci_dev *dev)
 {
 	struct pci_dev *pdev;
 	u16 command;
@@ -780,7 +780,7 @@ DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8237,		quirk
  * noapic specified. For the moment we assume it's the erratum. We may be wrong
  * of course. However the advice is demonstrably good even if so..
  */
-static void __devinit quirk_amd_ioapic(struct pci_dev *dev)
+static void quirk_amd_ioapic(struct pci_dev *dev)
 {
 	if (dev->revision >= 0x02) {
 		dev_warn(&dev->dev, "I/O APIC: AMD Erratum #22 may be present. In the event of instability try\n");
@@ -789,7 +789,7 @@ static void __devinit quirk_amd_ioapic(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_VIPER_7410,	quirk_amd_ioapic);
 
-static void __devinit quirk_ioapic_rmw(struct pci_dev *dev)
+static void quirk_ioapic_rmw(struct pci_dev *dev)
 {
 	if (dev->devfn == 0 && dev->bus->number == 0)
 		sis_apic_bug = 1;
@@ -801,7 +801,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI,	PCI_ANY_ID,			quirk_ioapic_rmw);
  * Some settings of MMRBC can lead to data corruption so block changes.
  * See AMD 8131 HyperTransport PCI-X Tunnel Revision Guide
  */
-static void __devinit quirk_amd_8131_mmrbc(struct pci_dev *dev)
+static void quirk_amd_8131_mmrbc(struct pci_dev *dev)
 {
 	if (dev->subordinate && dev->revision <= 0x12) {
 		dev_info(&dev->dev, "AMD8131 rev %x detected; "
@@ -819,7 +819,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_
  * value of the ACPI SCI interrupt is only done for convenience.
  *	-jgarzik
  */
-static void __devinit quirk_via_acpi(struct pci_dev *d)
+static void quirk_via_acpi(struct pci_dev *d)
 {
 	/*
 	 * VIA ACPI device: SCI IRQ line in PCI config byte 0x42
@@ -926,7 +926,7 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_VIA, PCI_ANY_ID, quirk_via_vlink);
  * We need to switch it off to be able to recognize the real
  * type of the chip.
  */
-static void __devinit quirk_vt82c598_id(struct pci_dev *dev)
+static void quirk_vt82c598_id(struct pci_dev *dev)
 {
 	pci_write_config_byte(dev, 0xfc, 0);
 	pci_read_config_word(dev, PCI_DEVICE_ID, &dev->device);
@@ -978,7 +978,7 @@ DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_FE_GATE_700C
  *	assigned to it. We force a larger allocation to ensure that
  *	nothing gets put too close to it.
  */
-static void __devinit quirk_dunord ( struct pci_dev * dev )
+static void quirk_dunord(struct pci_dev *dev)
 {
 	struct resource *r = &dev->resource [1];
 	r->start = 0;
@@ -992,7 +992,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_DUNORD,	PCI_DEVICE_ID_DUNORD_I3000,	quirk
  * in the ProgIf. Unfortunately, the ProgIf value is wrong - 0x80
  * instead of 0x01.
  */
-static void __devinit quirk_transparent_bridge(struct pci_dev *dev)
+static void quirk_transparent_bridge(struct pci_dev *dev)
 {
 	dev->transparent = 1;
 }
@@ -1066,7 +1066,7 @@ DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SATA
 /*
  *	Serverworks CSB5 IDE does not fully support native mode
  */
-static void __devinit quirk_svwks_csb5ide(struct pci_dev *pdev)
+static void quirk_svwks_csb5ide(struct pci_dev *pdev)
 {
 	u8 prog;
 	pci_read_config_byte(pdev, PCI_CLASS_PROG, &prog);
@@ -1082,7 +1082,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_CSB
 /*
  *	Intel 82801CAM ICH3-M datasheet says IDE modes must be the same
  */
-static void __devinit quirk_ide_samemode(struct pci_dev *pdev)
+static void quirk_ide_samemode(struct pci_dev *pdev)
 {
 	u8 prog;
 
@@ -1101,7 +1101,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_10, qui
  * Some ATA devices break if put into D3
  */
 
-static void __devinit quirk_no_ata_d3(struct pci_dev *pdev)
+static void quirk_no_ata_d3(struct pci_dev *pdev)
 {
 	pdev->dev_flags |= PCI_DEV_FLAGS_NO_D3;
 }
@@ -1121,7 +1121,7 @@ DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_VIA, PCI_ANY_ID,
 /* This was originally an Alpha specific thing, but it really fits here.
  * The i82375 PCI/EISA bridge appears as non-classified. Fix that.
  */
-static void __devinit quirk_eisa_bridge(struct pci_dev *dev)
+static void quirk_eisa_bridge(struct pci_dev *dev)
 {
 	dev->class = PCI_CLASS_BRIDGE_EISA << 8;
 }
@@ -1155,7 +1155,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82375,	quirk_e
  */
 static int asus_hides_smbus;
 
-static void __devinit asus_hides_smbus_hostbridge(struct pci_dev *dev)
+static void asus_hides_smbus_hostbridge(struct pci_dev *dev)
 {
 	if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_ASUSTEK)) {
 		if (dev->device == PCI_DEVICE_ID_INTEL_82845_HB)
@@ -1538,7 +1538,7 @@ DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB3
 #endif
 
 #ifdef CONFIG_X86_IO_APIC
-static void __devinit quirk_alder_ioapic(struct pci_dev *pdev)
+static void quirk_alder_ioapic(struct pci_dev *pdev)
 {
 	int i;
 
@@ -1561,7 +1561,7 @@ static void __devinit quirk_alder_ioapic(struct pci_dev *pdev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_EESSC,	quirk_alder_ioapic);
 #endif
 
-static void __devinit quirk_pcie_mch(struct pci_dev *pdev)
+static void quirk_pcie_mch(struct pci_dev *pdev)
 {
 	pci_msi_off(pdev);
 	pdev->no_msi = 1;
@@ -1575,7 +1575,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7525_MCH,	quir
  * It's possible for the MSI to get corrupted if shpc and acpi
  * are used together on certain PXH-based systems.
  */
-static void __devinit quirk_pcie_pxh(struct pci_dev *dev)
+static void quirk_pcie_pxh(struct pci_dev *dev)
 {
 	pci_msi_off(dev);
 	dev->no_msi = 1;
@@ -1777,7 +1777,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8111_SMBUS, 	qui
  * but the PIO transfers won't work if BAR0 falls at the odd 8 bytes.
  * Re-allocate the region if needed...
  */
-static void __devinit quirk_tc86c001_ide(struct pci_dev *dev)
+static void quirk_tc86c001_ide(struct pci_dev *dev)
 {
 	struct resource *r = &dev->resource[0];
 
@@ -1790,7 +1790,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TOSHIBA_2,
 			 PCI_DEVICE_ID_TOSHIBA_TC86C001_IDE,
 			 quirk_tc86c001_ide);
 
-static void __devinit quirk_netmos(struct pci_dev *dev)
+static void quirk_netmos(struct pci_dev *dev)
 {
 	unsigned int num_parallel = (dev->subsystem_device & 0xf0) >> 4;
 	unsigned int num_serial = dev->subsystem_device & 0xf;
@@ -1828,7 +1828,7 @@ static void __devinit quirk_netmos(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_NETMOS, PCI_ANY_ID,
 			 PCI_CLASS_COMMUNICATION_SERIAL, 8, quirk_netmos);
 
-static void __devinit quirk_e100_interrupt(struct pci_dev *dev)
+static void quirk_e100_interrupt(struct pci_dev *dev)
 {
 	u16 command, pmcsr;
 	u8 __iomem *csr;
@@ -1901,7 +1901,7 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
  * The 82575 and 82598 may experience data corruption issues when transitioning
  * out of L0S.  To prevent this we need to disable L0S on the pci-e link
  */
-static void __devinit quirk_disable_aspm_l0s(struct pci_dev *dev)
+static void quirk_disable_aspm_l0s(struct pci_dev *dev)
 {
 	dev_info(&dev->dev, "Disabling L0s\n");
 	pci_disable_link_state(dev, PCIE_LINK_STATE_L0S);
@@ -1921,7 +1921,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s);
 
-static void __devinit fixup_rev1_53c810(struct pci_dev* dev)
+static void fixup_rev1_53c810(struct pci_dev *dev)
 {
 	/* rev 1 ncr53c810 chips don't set the class at all which means
 	 * they don't get their resources remapped. Fix that here.
@@ -1935,7 +1935,7 @@ static void __devinit fixup_rev1_53c810(struct pci_dev* dev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NCR, PCI_DEVICE_ID_NCR_53C810, fixup_rev1_53c810);
 
 /* Enable 1k I/O space granularity on the Intel P64H2 */
-static void __devinit quirk_p64h2_1k_io(struct pci_dev *dev)
+static void quirk_p64h2_1k_io(struct pci_dev *dev)
 {
 	u16 en1k;
 
@@ -1968,7 +1968,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA,  PCI_DEVICE_ID_NVIDIA_CK804_PCIE,
 DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_NVIDIA,  PCI_DEVICE_ID_NVIDIA_CK804_PCIE,
 			quirk_nvidia_ck804_pcie_aer_ext_cap);
 
-static void __devinit quirk_via_cx700_pci_parking_caching(struct pci_dev *dev)
+static void quirk_via_cx700_pci_parking_caching(struct pci_dev *dev)
 {
 	/*
 	 * Disable PCI Bus Parking and PCI Master read caching on CX700
@@ -2031,7 +2031,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, 0x324e, quirk_via_cx700_pci_parking_c
  * We believe that it is legal to read beyond the end tag and
  * therefore the solution is to limit the read/write length.
  */
-static void __devinit quirk_brcm_570x_limit_vpd(struct pci_dev *dev)
+static void quirk_brcm_570x_limit_vpd(struct pci_dev *dev)
 {
 	/*
 	 * Only disable the VPD capability for 5706, 5706S, 5708,
@@ -2091,7 +2091,7 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_BROADCOM,
  * the DRBs - this is where we expose device 6.
  * http://www.x86-secret.com/articles/tweak/pat/patsecrets-2.htm
  */
-static void __devinit quirk_unhide_mch_dev6(struct pci_dev *dev)
+static void quirk_unhide_mch_dev6(struct pci_dev *dev)
 {
 	u8 reg;
 
@@ -2115,7 +2115,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82875_HB,
  * supports link speed auto negotiation, but falsely sets
  * the link speed to 5GT/s.
  */
-static void __devinit quirk_tile_plx_gen1(struct pci_dev *dev)
+static void quirk_tile_plx_gen1(struct pci_dev *dev)
 {
 	if (tile_plx_gen1) {
 		pci_write_config_dword(dev, 0x98, 0x1);
@@ -2132,7 +2132,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_PLX, 0x8624, quirk_tile_plx_gen1);
  * aware of it.  Instead of setting the flag on all busses in the
  * machine, simply disable MSI globally.
  */
-static void __devinit quirk_disable_all_msi(struct pci_dev *dev)
+static void quirk_disable_all_msi(struct pci_dev *dev)
 {
 	pci_no_msi();
 	dev_warn(&dev->dev, "MSI quirk detected; MSI disabled\n");
@@ -2146,7 +2146,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT3364, quirk_disab
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8380_0, quirk_disable_all_msi);
 
 /* Disable MSI on chipsets that are known to not support it */
-static void __devinit quirk_disable_msi(struct pci_dev *dev)
+static void quirk_disable_msi(struct pci_dev *dev)
 {
 	if (dev->subordinate) {
 		dev_warn(&dev->dev, "MSI quirk detected; "
@@ -2164,7 +2164,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x5a3f, quirk_disable_msi);
  * we use the possible vendor/device IDs of the host bridge for the
  * declared quirk, and search for the APC bridge by slot number.
  */
-static void __devinit quirk_amd_780_apc_msi(struct pci_dev *host_bridge)
+static void quirk_amd_780_apc_msi(struct pci_dev *host_bridge)
 {
 	struct pci_dev *apc_bridge;
 
@@ -2272,7 +2272,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8132_BRIDGE,
  * for the MCP55 NIC. It is not yet determined whether the msi problem
  * also affects other devices. As for now, turn off msi for this device.
  */
-static void __devinit nvenet_msi_disable(struct pci_dev *dev)
+static void nvenet_msi_disable(struct pci_dev *dev)
 {
 	const char *board_name = dmi_get_system_info(DMI_BOARD_NAME);
 
@@ -2298,7 +2298,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
  * we have it set correctly.
  * Note this is an undocumented register.
  */
-static void __devinit nvbridge_check_legacy_irq_routing(struct pci_dev *dev)
+static void nvbridge_check_legacy_irq_routing(struct pci_dev *dev)
 {
 	u32 cfg;
 
@@ -2534,11 +2534,11 @@ DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, nv_msi_ht_cap_q
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk_all);
 DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk_all);
 
-static void __devinit quirk_msi_intx_disable_bug(struct pci_dev *dev)
+static void quirk_msi_intx_disable_bug(struct pci_dev *dev)
 {
 	dev->dev_flags |= PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG;
 }
-static void __devinit quirk_msi_intx_disable_ati_bug(struct pci_dev *dev)
+static void quirk_msi_intx_disable_ati_bug(struct pci_dev *dev)
 {
 	struct pci_dev *p;
 
@@ -2612,7 +2612,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, 0x1083,
  * kernel fails to allocate resources when hotplug device is 
  * inserted and PCI bus is rescanned.
  */
-static void __devinit quirk_hotplug_bridge(struct pci_dev *dev)
+static void quirk_hotplug_bridge(struct pci_dev *dev)
 {
 	dev->is_hotplug_bridge = 1;
 }
@@ -2752,7 +2752,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x342e, vtd_mask_spec_errors);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x3c28, vtd_mask_spec_errors);
 #endif
 
-static void __devinit fixup_ti816x_class(struct pci_dev* dev)
+static void fixup_ti816x_class(struct pci_dev *dev)
 {
 	/* TI 816x devices do not have class code set when in PCIe boot mode */
 	dev_info(&dev->dev, "Setting PCI class for 816x PCIe device\n");
@@ -2764,7 +2764,7 @@ DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_TI, 0xb800,
 /* Some PCIe devices do not work reliably with the claimed maximum
  * payload size supported.
  */
-static void __devinit fixup_mpss_256(struct pci_dev *dev)
+static void fixup_mpss_256(struct pci_dev *dev)
 {
 	dev->pcie_mpss = 1; /* 256 bytes */
 }
@@ -2782,7 +2782,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SOLARFLARE,
  * coalescing must be disabled.  Unfortunately, it cannot be re-enabled because
  * it is possible to hotplug a device with MPS of 256B.
  */
-static void __devinit quirk_intel_mc_errata(struct pci_dev *dev)
+static void quirk_intel_mc_errata(struct pci_dev *dev)
 {
 	int err;
 	u16 rcc;
@@ -2888,7 +2888,7 @@ static void fixup_debug_report(struct pci_dev *dev, ktime_t calltime,
  * This resolves crashes often seen on monitor unplug.
  */
 #define I915_DEIER_REG 0x4400c
-static void __devinit disable_igfx_irq(struct pci_dev *dev)
+static void disable_igfx_irq(struct pci_dev *dev)
 {
 	void __iomem *regs = pci_iomap(dev, 0, 0);
 	if (regs == NULL) {
@@ -2914,7 +2914,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq);
  * PCI_COMMAND_INTX_DISABLE works though they actually do not properly
  * support this feature.
  */
-static void __devinit quirk_broken_intx_masking(struct pci_dev *dev)
+static void quirk_broken_intx_masking(struct pci_dev *dev)
 {
 	dev->broken_intx_masking = 1;
 }
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 0aab85a51559..db542f4196a4 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -412,7 +412,7 @@ static int pcifront_claim_resource(struct pci_dev *dev, void *data)
 	return 0;
 }
 
-static int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
+static int pcifront_scan_bus(struct pcifront_device *pdev,
 				unsigned int domain, unsigned int bus,
 				struct pci_bus *b)
 {
@@ -441,7 +441,7 @@ static int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
 	return 0;
 }
 
-static int __devinit pcifront_scan_root(struct pcifront_device *pdev,
+static int pcifront_scan_root(struct pcifront_device *pdev,
 				 unsigned int domain, unsigned int bus)
 {
 	struct pci_bus *b;
@@ -503,7 +503,7 @@ err_out:
 	return err;
 }
 
-static int __devinit pcifront_rescan_root(struct pcifront_device *pdev,
+static int pcifront_rescan_root(struct pcifront_device *pdev,
 				   unsigned int domain, unsigned int bus)
 {
 	int err;
@@ -834,7 +834,7 @@ out:
 	return err;
 }
 
-static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
+static int pcifront_try_connect(struct pcifront_device *pdev)
 {
 	int err = -EFAULT;
 	int i, num_roots, len;
@@ -924,7 +924,7 @@ out:
 	return err;
 }
 
-static int __devinit pcifront_attach_devices(struct pcifront_device *pdev)
+static int pcifront_attach_devices(struct pcifront_device *pdev)
 {
 	int err = -EFAULT;
 	int i, num_roots, len;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 699e9a920eca..d03d2463efac 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -588,7 +588,7 @@ struct pci_driver {
  * in a generic manner.
  */
 #define DEFINE_PCI_DEVICE_TABLE(_table) \
-	const struct pci_device_id _table[] __devinitconst
+	const struct pci_device_id _table[]
 
 /**
  * PCI_DEVICE - macro used to describe a specific pci device
@@ -686,7 +686,7 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 int pci_bus_insert_busn_res(struct pci_bus *b, int bus, int busmax);
 int pci_bus_update_busn_res_end(struct pci_bus *b, int busmax);
 void pci_bus_release_busn_res(struct pci_bus *b);
-struct pci_bus * __devinit pci_scan_root_bus(struct device *parent, int bus,
+struct pci_bus *pci_scan_root_bus(struct device *parent, int bus,
 					     struct pci_ops *ops, void *sysdata,
 					     struct list_head *resources);
 struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev,
@@ -1578,7 +1578,7 @@ extern int pci_pci_problems;
 
 extern unsigned long pci_cardbus_io_size;
 extern unsigned long pci_cardbus_mem_size;
-extern u8 __devinitdata pci_dfl_cache_line_size;
+extern u8 pci_dfl_cache_line_size;
 extern u8 pci_cache_line_size;
 
 extern unsigned long pci_hotplug_io_size;
-- 
cgit v1.2.3-55-g7522


From c4144670fd9b34d6eae22c9f83751745898e8243 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Tue, 2 Oct 2012 16:34:38 -0400
Subject: kill daemonize()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/staging/gdm72xx/gdm_usb.c |  4 +-
 fs/file.c                         |  6 ---
 fs/fs_struct.c                    | 24 ----------
 include/linux/fdtable.h           |  1 -
 include/linux/fs_struct.h         |  1 -
 include/linux/sched.h             |  1 -
 kernel/exit.c                     | 92 ---------------------------------------
 7 files changed, 1 insertion(+), 128 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/gdm72xx/gdm_usb.c b/drivers/staging/gdm72xx/gdm_usb.c
index 0c9e8958009b..39db582ab1a6 100644
--- a/drivers/staging/gdm72xx/gdm_usb.c
+++ b/drivers/staging/gdm72xx/gdm_usb.c
@@ -701,8 +701,6 @@ static int k_mode_thread(void *arg)
 	unsigned long flags, flags2, expire;
 	int ret;
 
-	daemonize("k_mode_wimax");
-
 	while (!k_mode_stop) {
 
 		spin_lock_irqsave(&k_lock, flags2);
@@ -764,7 +762,7 @@ static struct usb_driver gdm_usb_driver = {
 static int __init usb_gdm_wimax_init(void)
 {
 #ifdef CONFIG_WIMAX_GDM72XX_K_MODE
-	kthread_run(k_mode_thread, NULL, "WiMax_thread");
+	kthread_run(k_mode_thread, NULL, "k_mode_wimax");
 #endif /* CONFIG_WIMAX_GDM72XX_K_MODE */
 	return usb_register(&gdm_usb_driver);
 }
diff --git a/fs/file.c b/fs/file.c
index 7cb71b992603..7272a1c5831d 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -519,12 +519,6 @@ struct files_struct init_files = {
 	.file_lock	= __SPIN_LOCK_UNLOCKED(init_task.file_lock),
 };
 
-void daemonize_descriptors(void)
-{
-	atomic_inc(&init_files.count);
-	reset_files_struct(&init_files);
-}
-
 /*
  * allocate a file descriptor, mark it busy.
  */
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 5df4775fea03..fe6ca583bbc0 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -164,27 +164,3 @@ struct fs_struct init_fs = {
 	.seq		= SEQCNT_ZERO,
 	.umask		= 0022,
 };
-
-void daemonize_fs_struct(void)
-{
-	struct fs_struct *fs = current->fs;
-
-	if (fs) {
-		int kill;
-
-		task_lock(current);
-
-		spin_lock(&init_fs.lock);
-		init_fs.users++;
-		spin_unlock(&init_fs.lock);
-
-		spin_lock(&fs->lock);
-		current->fs = &init_fs;
-		kill = !--fs->users;
-		spin_unlock(&fs->lock);
-
-		task_unlock(current);
-		if (kill)
-			free_fs_struct(fs);
-	}
-}
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 45052aa814c8..fb7dacae0522 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -95,7 +95,6 @@ struct task_struct;
 struct files_struct *get_files_struct(struct task_struct *);
 void put_files_struct(struct files_struct *fs);
 void reset_files_struct(struct files_struct *);
-void daemonize_descriptors(void);
 int unshare_files(struct files_struct **);
 struct files_struct *dup_fd(struct files_struct *, int *);
 void do_close_on_exec(struct files_struct *);
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 003dc0fd7347..d0ae3a84bcfb 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -21,7 +21,6 @@ extern void set_fs_root(struct fs_struct *, struct path *);
 extern void set_fs_pwd(struct fs_struct *, struct path *);
 extern struct fs_struct *copy_fs_struct(struct fs_struct *);
 extern void free_fs_struct(struct fs_struct *);
-extern void daemonize_fs_struct(void);
 extern int unshare_fs_struct(void);
 
 static inline void get_fs_root(struct fs_struct *fs, struct path *root)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a02df2e..a0166481eb20 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2283,7 +2283,6 @@ extern void flush_itimer_signals(void);
 
 extern void do_group_exit(int);
 
-extern void daemonize(const char *, ...);
 extern int allow_signal(int);
 extern int disallow_signal(int);
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 346616c0092c..f9275e2c7c2c 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -322,43 +322,6 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
 	}
 }
 
-/**
- * reparent_to_kthreadd - Reparent the calling kernel thread to kthreadd
- *
- * If a kernel thread is launched as a result of a system call, or if
- * it ever exits, it should generally reparent itself to kthreadd so it
- * isn't in the way of other processes and is correctly cleaned up on exit.
- *
- * The various task state such as scheduling policy and priority may have
- * been inherited from a user process, so we reset them to sane values here.
- *
- * NOTE that reparent_to_kthreadd() gives the caller full capabilities.
- */
-static void reparent_to_kthreadd(void)
-{
-	write_lock_irq(&tasklist_lock);
-
-	ptrace_unlink(current);
-	/* Reparent to init */
-	current->real_parent = current->parent = kthreadd_task;
-	list_move_tail(&current->sibling, &current->real_parent->children);
-
-	/* Set the exit signal to SIGCHLD so we signal init on exit */
-	current->exit_signal = SIGCHLD;
-
-	if (task_nice(current) < 0)
-		set_user_nice(current, 0);
-	/* cpus_allowed? */
-	/* rt_priority? */
-	/* signals? */
-	memcpy(current->signal->rlim, init_task.signal->rlim,
-	       sizeof(current->signal->rlim));
-
-	atomic_inc(&init_cred.usage);
-	commit_creds(&init_cred);
-	write_unlock_irq(&tasklist_lock);
-}
-
 void __set_special_pids(struct pid *pid)
 {
 	struct task_struct *curr = current->group_leader;
@@ -370,13 +333,6 @@ void __set_special_pids(struct pid *pid)
 		change_pid(curr, PIDTYPE_PGID, pid);
 }
 
-static void set_special_pids(struct pid *pid)
-{
-	write_lock_irq(&tasklist_lock);
-	__set_special_pids(pid);
-	write_unlock_irq(&tasklist_lock);
-}
-
 /*
  * Let kernel threads use this to say that they allow a certain signal.
  * Must not be used if kthread was cloned with CLONE_SIGHAND.
@@ -416,54 +372,6 @@ int disallow_signal(int sig)
 
 EXPORT_SYMBOL(disallow_signal);
 
-/*
- *	Put all the gunge required to become a kernel thread without
- *	attached user resources in one place where it belongs.
- */
-
-void daemonize(const char *name, ...)
-{
-	va_list args;
-	sigset_t blocked;
-
-	va_start(args, name);
-	vsnprintf(current->comm, sizeof(current->comm), name, args);
-	va_end(args);
-
-	/*
-	 * If we were started as result of loading a module, close all of the
-	 * user space pages.  We don't need them, and if we didn't close them
-	 * they would be locked into memory.
-	 */
-	exit_mm(current);
-	/*
-	 * We don't want to get frozen, in case system-wide hibernation
-	 * or suspend transition begins right now.
-	 */
-	current->flags |= (PF_NOFREEZE | PF_KTHREAD);
-
-	if (current->nsproxy != &init_nsproxy) {
-		get_nsproxy(&init_nsproxy);
-		switch_task_namespaces(current, &init_nsproxy);
-	}
-	set_special_pids(&init_struct_pid);
-	proc_clear_tty(current);
-
-	/* Block and flush all signals */
-	sigfillset(&blocked);
-	sigprocmask(SIG_BLOCK, &blocked, NULL);
-	flush_signals(current);
-
-	/* Become as one with the init task */
-
-	daemonize_fs_struct();
-	daemonize_descriptors();
-
-	reparent_to_kthreadd();
-}
-
-EXPORT_SYMBOL(daemonize);
-
 #ifdef CONFIG_MM_OWNER
 /*
  * A task is exiting.   If it owned this mm, find a new owner for the mm.
-- 
cgit v1.2.3-55-g7522


From d2125043aebf7f53cd1c72115c17b01d0bc06ce1 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Tue, 23 Oct 2012 13:17:59 -0400
Subject: generic sys_fork / sys_vfork / sys_clone

... and get rid of idiotic struct pt_regs * in asm-generic/syscalls.h
prototypes of the same, while we are at it.  Eventually we want those
in linux/syscalls.h, of course, but that'll have to wait a bit.

Note that there are *three* variants of sys_clone() order of arguments.
Braindamage galore...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/Kconfig                   | 14 ++++++++++++++
 include/asm-generic/syscalls.h |  7 +++----
 kernel/fork.c                  | 43 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 60 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index 366ec06a5185..8d698fb5ccc9 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -341,4 +341,18 @@ config MODULES_USE_ELF_REL
 	  Modules only use ELF REL relocations.  Modules with ELF RELA
 	  relocations will give an error.
 
+#
+# ABI hall of shame
+#
+config CLONE_BACKWARDS
+	bool
+	help
+	  Architecture has tls passed as the 4th argument of clone(2),
+	  not the 5th one.
+
+config CLONE_BACKWARDS2
+	bool
+	help
+	  Architecture has the first two arguments of clone(2) swapped.
+
 source "kernel/gcov/Kconfig"
diff --git a/include/asm-generic/syscalls.h b/include/asm-generic/syscalls.h
index d89dec864d42..7e4fdb649951 100644
--- a/include/asm-generic/syscalls.h
+++ b/include/asm-generic/syscalls.h
@@ -10,16 +10,15 @@
  */
 #ifndef sys_clone
 asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp,
-			void __user *parent_tid, void __user *child_tid,
-			struct pt_regs *regs);
+			void __user *parent_tid, void __user *child_tid);
 #endif
 
 #ifndef sys_fork
-asmlinkage long sys_fork(struct pt_regs *regs);
+asmlinkage long sys_fork(void);
 #endif
 
 #ifndef sys_vfork
-asmlinkage long sys_vfork(struct pt_regs *regs);
+asmlinkage long sys_vfork(void);
 #endif
 
 #ifndef sys_execve
diff --git a/kernel/fork.c b/kernel/fork.c
index 8b20ab7d3aa2..27a337549dab 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1645,6 +1645,49 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 }
 #endif
 
+#ifdef __ARCH_WANT_SYS_FORK
+SYSCALL_DEFINE0(fork)
+{
+#ifdef CONFIG_MMU
+	return do_fork(SIGCHLD, 0, current_pt_regs(), 0, NULL, NULL);
+#else
+	/* can not support in nommu mode */
+	return(-EINVAL);
+#endif
+}
+#endif
+
+#ifdef __ARCH_WANT_SYS_VFORK
+SYSCALL_DEFINE0(vfork)
+{
+	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, current_pt_regs(),
+			0, NULL, NULL);
+}
+#endif
+
+#ifdef __ARCH_WANT_SYS_CLONE
+#ifdef CONFIG_CLONE_BACKWARDS
+SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
+		 int __user *, parent_tidptr,
+		 int, tls_val,
+		 int __user *, child_tidptr)
+#elif defined(CONFIG_CLONE_BACKWARDS2)
+SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
+		 int __user *, parent_tidptr,
+		 int __user *, child_tidptr,
+		 int, tls_val)
+#else
+SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
+		 int __user *, parent_tidptr,
+		 int __user *, child_tidptr,
+		 int, tls_val)
+#endif
+{
+	return do_fork(clone_flags, newsp, current_pt_regs(), 0,
+		parent_tidptr, child_tidptr);
+}
+#endif
+
 #ifndef ARCH_MIN_MMSTRUCT_ALIGN
 #define ARCH_MIN_MMSTRUCT_ALIGN 0
 #endif
-- 
cgit v1.2.3-55-g7522


From 6b94631f9e8c45a46056cbc6a7a50ecebea4f8da Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Sat, 20 Oct 2012 13:32:30 -0400
Subject: consolidate sys_execve() prototype

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/hexagon/include/asm/syscall.h | 3 ---
 arch/tile/include/asm/syscalls.h   | 4 ----
 arch/x86/include/asm/syscalls.h    | 3 ---
 arch/xtensa/include/asm/syscall.h  | 1 -
 include/asm-generic/syscalls.h     | 7 -------
 include/linux/syscalls.h           | 3 +++
 6 files changed, 3 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h
index fb0e9d48faa6..ec2ce6792cd6 100644
--- a/arch/hexagon/include/asm/syscall.h
+++ b/arch/hexagon/include/asm/syscall.h
@@ -25,12 +25,9 @@ typedef long (*syscall_fn)(unsigned long, unsigned long,
 	unsigned long, unsigned long,
 	unsigned long, unsigned long);
 
-asmlinkage int sys_execve(char __user *ufilename, char __user * __user *argv,
-			  char __user * __user *envp);
 asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp,
 			 unsigned long parent_tidp, unsigned long child_tidp);
 
-#define sys_execve	sys_execve
 #define sys_clone	sys_clone
 
 #include <asm-generic/syscalls.h>
diff --git a/arch/tile/include/asm/syscalls.h b/arch/tile/include/asm/syscalls.h
index 369696d63e7b..394c76f2dc76 100644
--- a/arch/tile/include/asm/syscalls.h
+++ b/arch/tile/include/asm/syscalls.h
@@ -65,13 +65,9 @@ long sys_ftruncate64(unsigned int fd, loff_t length);
 /* Provide versions of standard syscalls that use current_pt_regs(). */
 long sys_clone(unsigned long clone_flags, unsigned long newsp,
 		void __user *parent_tid, void __user *child_tid);
-long sys_execve(const char __user *filename,
-		 const char __user *const __user *argv,
-		 const char __user *const __user *envp);
 long sys_rt_sigreturn(void);
 long sys_sigaltstack(const stack_t __user *, stack_t __user *);
 #define sys_clone sys_clone
-#define sys_execve sys_execve
 #define sys_rt_sigreturn sys_rt_sigreturn
 #define sys_sigaltstack sys_sigaltstack
 
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 2be0b880417e..9e5aef3a2598 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -23,9 +23,6 @@ long sys_iopl(unsigned int, struct pt_regs *);
 /* kernel/process.c */
 int sys_fork(struct pt_regs *);
 int sys_vfork(struct pt_regs *);
-long sys_execve(const char __user *,
-		const char __user *const __user *,
-		const char __user *const __user *);
 long sys_clone(unsigned long, unsigned long, void __user *,
 	       void __user *, struct pt_regs *);
 
diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h
index 124aeee0d381..4e27d76c9612 100644
--- a/arch/xtensa/include/asm/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
@@ -10,7 +10,6 @@
 
 struct pt_regs;
 struct sigaction;
-asmlinkage long sys_execve(char*, char**, char**, struct pt_regs*);
 asmlinkage long xtensa_clone(unsigned long, unsigned long, struct pt_regs*);
 asmlinkage long xtensa_ptrace(long, long, long, long);
 asmlinkage long xtensa_sigreturn(struct pt_regs*);
diff --git a/include/asm-generic/syscalls.h b/include/asm-generic/syscalls.h
index 7e4fdb649951..77960333b1a1 100644
--- a/include/asm-generic/syscalls.h
+++ b/include/asm-generic/syscalls.h
@@ -21,13 +21,6 @@ asmlinkage long sys_fork(void);
 asmlinkage long sys_vfork(void);
 #endif
 
-#ifndef sys_execve
-asmlinkage long sys_execve(const char __user *filename,
-			   const char __user *const __user *argv,
-			   const char __user *const __user *envp,
-			   struct pt_regs *regs);
-#endif
-
 #ifndef sys_mmap2
 asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
 			unsigned long prot, unsigned long flags,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 727f0cd73921..2779009ceaa3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -837,6 +837,9 @@ int kernel_execve(const char *filename, const char *const argv[], const char *co
 		current_pt_regs())
 #endif
 
+asmlinkage long sys_execve(const char __user *filename,
+		const char __user *const __user *argv,
+		const char __user *const __user *envp);
 
 asmlinkage long sys_perf_event_open(
 		struct perf_event_attr __user *attr_uptr,
-- 
cgit v1.2.3-55-g7522


From d03d26e58fde2ec99478e26aab47b55755189b08 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Sat, 20 Oct 2012 21:46:25 -0400
Subject: make compat_do_execve() static, lose pt_regs argument

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/exec.c              | 10 ++++------
 include/linux/compat.h |  2 --
 2 files changed, 4 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/exec.c b/fs/exec.c
index 0039055b1fc6..f86b6cc2d6cc 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1575,10 +1575,9 @@ int do_execve(const char *filename,
 }
 
 #ifdef CONFIG_COMPAT
-int compat_do_execve(const char *filename,
+static int compat_do_execve(const char *filename,
 	const compat_uptr_t __user *__argv,
-	const compat_uptr_t __user *__envp,
-	struct pt_regs *regs)
+	const compat_uptr_t __user *__envp)
 {
 	struct user_arg_ptr argv = {
 		.is_compat = true,
@@ -1588,7 +1587,7 @@ int compat_do_execve(const char *filename,
 		.is_compat = true,
 		.ptr.compat = __envp,
 	};
-	return do_execve_common(filename, argv, envp, regs);
+	return do_execve_common(filename, argv, envp, current_pt_regs());
 }
 #endif
 
@@ -1682,8 +1681,7 @@ asmlinkage long compat_sys_execve(const char __user * filename,
 	struct filename *path = getname(filename);
 	int error = PTR_ERR(path);
 	if (!IS_ERR(path)) {
-		error = compat_do_execve(path->name, argv, envp,
-							current_pt_regs());
+		error = compat_do_execve(path->name, argv, envp);
 		putname(path);
 	}
 	return error;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index d2db71077d93..784ebfe63c48 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -284,8 +284,6 @@ asmlinkage ssize_t compat_sys_pwritev(unsigned long fd,
 		const struct compat_iovec __user *vec,
 		unsigned long vlen, u32 pos_low, u32 pos_high);
 
-int compat_do_execve(const char *filename, const compat_uptr_t __user *argv,
-		     const compat_uptr_t __user *envp, struct pt_regs *regs);
 asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp);
 
-- 
cgit v1.2.3-55-g7522


From da3d4c5fa56236dd924d77ffc4f982356816b93b Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Sat, 20 Oct 2012 21:49:33 -0400
Subject: get rid of pt_regs argument of do_execve()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/exec.c                | 16 ++++++----------
 include/linux/sched.h    |  2 +-
 include/linux/syscalls.h |  3 +--
 3 files changed, 8 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/exec.c b/fs/exec.c
index f86b6cc2d6cc..5797ed07efd3 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1566,12 +1566,11 @@ out_ret:
 
 int do_execve(const char *filename,
 	const char __user *const __user *__argv,
-	const char __user *const __user *__envp,
-	struct pt_regs *regs)
+	const char __user *const __user *__envp)
 {
 	struct user_arg_ptr argv = { .ptr.native = __argv };
 	struct user_arg_ptr envp = { .ptr.native = __envp };
-	return do_execve_common(filename, argv, envp, regs);
+	return do_execve_common(filename, argv, envp, current_pt_regs());
 }
 
 #ifdef CONFIG_COMPAT
@@ -1668,7 +1667,7 @@ SYSCALL_DEFINE3(execve,
 	struct filename *path = getname(filename);
 	int error = PTR_ERR(path);
 	if (!IS_ERR(path)) {
-		error = do_execve(path->name, argv, envp, current_pt_regs());
+		error = do_execve(path->name, argv, envp);
 		putname(path);
 	}
 	return error;
@@ -1694,12 +1693,9 @@ int kernel_execve(const char *filename,
 		  const char *const argv[],
 		  const char *const envp[])
 {
-	struct pt_regs *p = current_pt_regs();
-	int ret;
-
-	ret = do_execve(filename,
+	int ret = do_execve(filename,
 			(const char __user *const __user *)argv,
-			(const char __user *const __user *)envp, p);
+			(const char __user *const __user *)envp);
 	if (ret < 0)
 		return ret;
 
@@ -1707,6 +1703,6 @@ int kernel_execve(const char *filename,
 	 * We were successful.  We won't be returning to our caller, but
 	 * instead to user space by manipulating the kernel stack.
 	 */
-	ret_from_kernel_execve(p);
+	ret_from_kernel_execve(current_pt_regs());
 }
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a0166481eb20..c57249782e48 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2288,7 +2288,7 @@ extern int disallow_signal(int);
 
 extern int do_execve(const char *,
 		     const char __user * const __user *,
-		     const char __user * const __user *, struct pt_regs *);
+		     const char __user * const __user *);
 extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 #ifdef CONFIG_GENERIC_KERNEL_THREAD
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2779009ceaa3..526deb333b91 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -833,8 +833,7 @@ int kernel_execve(const char *filename, const char *const argv[], const char *co
 #define kernel_execve(filename, argv, envp) \
 	do_execve(filename, \
 		(const char __user *const __user *)argv, \
-		(const char __user *const __user *)envp, \
-		current_pt_regs())
+		(const char __user *const __user *)envp)
 #endif
 
 asmlinkage long sys_execve(const char __user *filename,
-- 
cgit v1.2.3-55-g7522


From 3c456bfc4ba66e9cda210da7bc4fb0ba9fcc6972 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Sat, 20 Oct 2012 21:53:31 -0400
Subject: get rid of pt_regs argument of search_binary_handler()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/kernel/binfmt_loader.c | 2 +-
 fs/binfmt_em86.c                  | 2 +-
 fs/binfmt_misc.c                  | 2 +-
 fs/binfmt_script.c                | 2 +-
 fs/exec.c                         | 7 +++----
 include/linux/binfmts.h           | 2 +-
 6 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/binfmt_loader.c b/arch/alpha/kernel/binfmt_loader.c
index d1f474d1d44d..54abbef5d077 100644
--- a/arch/alpha/kernel/binfmt_loader.c
+++ b/arch/alpha/kernel/binfmt_loader.c
@@ -37,7 +37,7 @@ static int load_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	retval = prepare_binprm(bprm);
 	if (retval < 0)
 		return retval;
-	return search_binary_handler(bprm,regs);
+	return search_binary_handler(bprm);
 }
 
 static struct linux_binfmt loader_format = {
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index 2790c7e1912e..7e125718a75e 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -90,7 +90,7 @@ static int load_em86(struct linux_binprm *bprm,struct pt_regs *regs)
 	if (retval < 0)
 		return retval;
 
-	return search_binary_handler(bprm, regs);
+	return search_binary_handler(bprm);
 }
 
 static struct linux_binfmt em86_format = {
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 790b3cddca67..226aeac22ac9 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -199,7 +199,7 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 
 	bprm->recursion_depth++;
 
-	retval = search_binary_handler (bprm, regs);
+	retval = search_binary_handler(bprm);
 	if (retval < 0)
 		goto _error;
 
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index d3b8c1f63155..798b729f01d5 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -95,7 +95,7 @@ static int load_script(struct linux_binprm *bprm,struct pt_regs *regs)
 	retval = prepare_binprm(bprm);
 	if (retval < 0)
 		return retval;
-	return search_binary_handler(bprm,regs);
+	return search_binary_handler(bprm);
 }
 
 static struct linux_binfmt script_format = {
diff --git a/fs/exec.c b/fs/exec.c
index dc5e2830d353..2aee7ef10663 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1349,7 +1349,7 @@ EXPORT_SYMBOL(remove_arg_zero);
 /*
  * cycle the list of binary formats handler, until one recognizes the image
  */
-int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
+int search_binary_handler(struct linux_binprm *bprm)
 {
 	unsigned int depth = bprm->recursion_depth;
 	int try,retval;
@@ -1380,7 +1380,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 			if (!try_module_get(fmt->module))
 				continue;
 			read_unlock(&binfmt_lock);
-			retval = fn(bprm, regs);
+			retval = fn(bprm, current_pt_regs());
 			/*
 			 * Restore the depth counter to its starting value
 			 * in this call, so we don't have to rely on every
@@ -1447,7 +1447,6 @@ static int do_execve_common(const char *filename,
 	bool clear_in_exec;
 	int retval;
 	const struct cred *cred = current_cred();
-	struct pt_regs *regs = current_pt_regs();
 
 	/*
 	 * We move the actual failure in case of RLIMIT_NPROC excess from
@@ -1524,7 +1523,7 @@ static int do_execve_common(const char *filename,
 	if (retval < 0)
 		goto out;
 
-	retval = search_binary_handler(bprm,regs);
+	retval = search_binary_handler(bprm);
 	if (retval < 0)
 		goto out;
 
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index cfcc6bfcaec0..1f6ce133b4c1 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -95,7 +95,7 @@ extern void unregister_binfmt(struct linux_binfmt *);
 
 extern int prepare_binprm(struct linux_binprm *);
 extern int __must_check remove_arg_zero(struct linux_binprm *);
-extern int search_binary_handler(struct linux_binprm *, struct pt_regs *);
+extern int search_binary_handler(struct linux_binprm *);
 extern int flush_old_exec(struct linux_binprm * bprm);
 extern void setup_new_exec(struct linux_binprm * bprm);
 extern void would_dump(struct linux_binprm *, struct file *);
-- 
cgit v1.2.3-55-g7522


From 71613c3b871c5a9f27cc48f124251bcd3aa23be1 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Sat, 20 Oct 2012 22:00:48 -0400
Subject: get rid of pt_regs argument of ->load_binary()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/kernel/binfmt_loader.c | 2 +-
 arch/x86/ia32/ia32_aout.c         | 5 +++--
 fs/binfmt_aout.c                  | 5 +++--
 fs/binfmt_elf.c                   | 5 +++--
 fs/binfmt_elf_fdpic.c             | 6 +++---
 fs/binfmt_em86.c                  | 2 +-
 fs/binfmt_flat.c                  | 5 +++--
 fs/binfmt_misc.c                  | 2 +-
 fs/binfmt_script.c                | 2 +-
 fs/binfmt_som.c                   | 5 +++--
 fs/exec.c                         | 4 ++--
 include/linux/binfmts.h           | 2 +-
 12 files changed, 25 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/binfmt_loader.c b/arch/alpha/kernel/binfmt_loader.c
index 54abbef5d077..9525660c93c0 100644
--- a/arch/alpha/kernel/binfmt_loader.c
+++ b/arch/alpha/kernel/binfmt_loader.c
@@ -5,7 +5,7 @@
 #include <linux/binfmts.h>
 #include <linux/a.out.h>
 
-static int load_binary(struct linux_binprm *bprm, struct pt_regs *regs)
+static int load_binary(struct linux_binprm *bprm)
 {
 	struct exec *eh = (struct exec *)bprm->buf;
 	unsigned long loader;
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 07b3a68d2d29..a703af19c281 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -35,7 +35,7 @@
 #undef WARN_OLD
 #undef CORE_DUMP /* definitely broken */
 
-static int load_aout_binary(struct linux_binprm *, struct pt_regs *regs);
+static int load_aout_binary(struct linux_binprm *);
 static int load_aout_library(struct file *);
 
 #ifdef CORE_DUMP
@@ -260,9 +260,10 @@ static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm)
  * These are the functions used to load a.out style executables and shared
  * libraries.  There is no binary dependent code anywhere else.
  */
-static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
+static int load_aout_binary(struct linux_binprm *bprm)
 {
 	unsigned long error, fd_offset, rlim;
+	struct pt_regs *regs = current_pt_regs();
 	struct exec ex;
 	int retval;
 
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 0e7a6f81ae36..6043567b95c2 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -30,7 +30,7 @@
 #include <asm/cacheflush.h>
 #include <asm/a.out-core.h>
 
-static int load_aout_binary(struct linux_binprm *, struct pt_regs * regs);
+static int load_aout_binary(struct linux_binprm *);
 static int load_aout_library(struct file*);
 
 #ifdef CONFIG_COREDUMP
@@ -201,8 +201,9 @@ static unsigned long __user *create_aout_tables(char __user *p, struct linux_bin
  * libraries.  There is no binary dependent code anywhere else.
  */
 
-static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
+static int load_aout_binary(struct linux_binprm * bprm)
 {
+	struct pt_regs *regs = current_pt_regs();
 	struct exec ex;
 	unsigned long error;
 	unsigned long fd_offset;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index fbd9f60bd763..6d7d1647a68c 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -44,7 +44,7 @@
 #define user_siginfo_t siginfo_t
 #endif
 
-static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs);
+static int load_elf_binary(struct linux_binprm *bprm);
 static int load_elf_library(struct file *);
 static unsigned long elf_map(struct file *, unsigned long, struct elf_phdr *,
 				int, int, unsigned long);
@@ -558,7 +558,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top)
 #endif
 }
 
-static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
+static int load_elf_binary(struct linux_binprm *bprm)
 {
 	struct file *interpreter = NULL; /* to shut gcc up */
  	unsigned long load_addr = 0, load_bias = 0;
@@ -575,6 +575,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	unsigned long reloc_func_desc __maybe_unused = 0;
 	int executable_stack = EXSTACK_DEFAULT;
 	unsigned long def_flags = 0;
+	struct pt_regs *regs = current_pt_regs();
 	struct {
 		struct elfhdr elf_ex;
 		struct elfhdr interp_elf_ex;
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index a46049154107..dc84732e554f 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -56,7 +56,7 @@ typedef char *elf_caddr_t;
 
 MODULE_LICENSE("GPL");
 
-static int load_elf_fdpic_binary(struct linux_binprm *, struct pt_regs *);
+static int load_elf_fdpic_binary(struct linux_binprm *);
 static int elf_fdpic_fetch_phdrs(struct elf_fdpic_params *, struct file *);
 static int elf_fdpic_map_file(struct elf_fdpic_params *, struct file *,
 			      struct mm_struct *, const char *);
@@ -164,10 +164,10 @@ static int elf_fdpic_fetch_phdrs(struct elf_fdpic_params *params,
 /*
  * load an fdpic binary into various bits of memory
  */
-static int load_elf_fdpic_binary(struct linux_binprm *bprm,
-				 struct pt_regs *regs)
+static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 {
 	struct elf_fdpic_params exec_params, interp_params;
+	struct pt_regs *regs = current_pt_regs();
 	struct elf_phdr *phdr;
 	unsigned long stack_size, entryaddr;
 #ifdef ELF_FDPIC_PLAT_INIT
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index 7e125718a75e..4e6cce57d113 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -22,7 +22,7 @@
 #define EM86_INTERP	"/usr/bin/em86"
 #define EM86_I_NAME	"em86"
 
-static int load_em86(struct linux_binprm *bprm,struct pt_regs *regs)
+static int load_em86(struct linux_binprm *bprm)
 {
 	char *interp, *i_name, *i_arg;
 	struct file * file;
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index e280352b28f9..b56371981d16 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -88,7 +88,7 @@ struct lib_info {
 static int load_flat_shared_library(int id, struct lib_info *p);
 #endif
 
-static int load_flat_binary(struct linux_binprm *, struct pt_regs * regs);
+static int load_flat_binary(struct linux_binprm *);
 static int flat_core_dump(struct coredump_params *cprm);
 
 static struct linux_binfmt flat_format = {
@@ -858,9 +858,10 @@ out:
  * libraries.  There is no binary dependent code anywhere else.
  */
 
-static int load_flat_binary(struct linux_binprm * bprm, struct pt_regs * regs)
+static int load_flat_binary(struct linux_binprm * bprm)
 {
 	struct lib_info libinfo;
+	struct pt_regs *regs = current_pt_regs();
 	unsigned long p = bprm->p;
 	unsigned long stack_len;
 	unsigned long start_addr;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 226aeac22ac9..b0b70fbea06c 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -104,7 +104,7 @@ static Node *check_file(struct linux_binprm *bprm)
 /*
  * the loader itself
  */
-static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
+static int load_misc_binary(struct linux_binprm *bprm)
 {
 	Node *fmt;
 	struct file * interp_file = NULL;
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 798b729f01d5..8c954997e7f7 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -14,7 +14,7 @@
 #include <linux/err.h>
 #include <linux/fs.h>
 
-static int load_script(struct linux_binprm *bprm,struct pt_regs *regs)
+static int load_script(struct linux_binprm *bprm)
 {
 	const char *i_arg, *i_name;
 	char *cp;
diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c
index 4517aaff61b4..4e00ed68d4a6 100644
--- a/fs/binfmt_som.c
+++ b/fs/binfmt_som.c
@@ -35,7 +35,7 @@
 
 #include <linux/elf.h>
 
-static int load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs);
+static int load_som_binary(struct linux_binprm * bprm);
 static int load_som_library(struct file *);
 
 /*
@@ -180,13 +180,14 @@ out:
  */
 
 static int
-load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs)
+load_som_binary(struct linux_binprm * bprm)
 {
 	int retval;
 	unsigned int size;
 	unsigned long som_entry;
 	struct som_hdr *som_ex;
 	struct som_exec_auxhdr *hpuxhdr;
+	struct pt_regs *regs = current_pt_regs();
 
 	/* Get the exec-header */
 	som_ex = (struct som_hdr *) bprm->buf;
diff --git a/fs/exec.c b/fs/exec.c
index 2aee7ef10663..721a29929511 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1374,13 +1374,13 @@ int search_binary_handler(struct linux_binprm *bprm)
 	for (try=0; try<2; try++) {
 		read_lock(&binfmt_lock);
 		list_for_each_entry(fmt, &formats, lh) {
-			int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary;
+			int (*fn)(struct linux_binprm *) = fmt->load_binary;
 			if (!fn)
 				continue;
 			if (!try_module_get(fmt->module))
 				continue;
 			read_unlock(&binfmt_lock);
-			retval = fn(bprm, current_pt_regs());
+			retval = fn(bprm);
 			/*
 			 * Restore the depth counter to its starting value
 			 * in this call, so we don't have to rely on every
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 1f6ce133b4c1..2630c9b41a86 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -72,7 +72,7 @@ struct coredump_params {
 struct linux_binfmt {
 	struct list_head lh;
 	struct module *module;
-	int (*load_binary)(struct linux_binprm *, struct  pt_regs * regs);
+	int (*load_binary)(struct linux_binprm *);
 	int (*load_shlib)(struct file *);
 	int (*core_dump)(struct coredump_params *cprm);
 	unsigned long min_coredump;	/* minimal dump size */
-- 
cgit v1.2.3-55-g7522


From 24465a40ba452bd81fdc9eecb2d75bb903aafdf6 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Wed, 28 Nov 2012 23:04:26 -0500
Subject: take sys_fork/sys_vfork/sys_clone prototypes to linux/syscalls.h

now it can be done...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/syscalls.h      |  8 --------
 arch/hexagon/include/asm/syscall.h     |  5 -----
 arch/microblaze/include/asm/Kbuild     |  1 +
 arch/microblaze/include/asm/syscalls.h | 16 ----------------
 arch/s390/kernel/entry.h               |  4 ----
 arch/tile/include/asm/syscalls.h       |  3 ---
 arch/tile/kernel/compat.c              |  1 -
 arch/tile/kernel/sys.c                 |  1 -
 arch/x86/include/asm/syscalls.h        | 11 -----------
 arch/x86/um/shared/sysdep/syscalls.h   |  2 --
 include/asm-generic/syscalls.h         | 12 ------------
 include/linux/syscalls.h               | 10 ++++++++++
 12 files changed, 11 insertions(+), 63 deletions(-)
 delete mode 100644 arch/microblaze/include/asm/syscalls.h

(limited to 'include')

diff --git a/arch/arm64/include/asm/syscalls.h b/arch/arm64/include/asm/syscalls.h
index 010ec127dc5b..20d63b290665 100644
--- a/arch/arm64/include/asm/syscalls.h
+++ b/arch/arm64/include/asm/syscalls.h
@@ -27,14 +27,6 @@ asmlinkage long sys_rt_sigreturn_wrapper(void);
 asmlinkage long sys_sigaltstack_wrapper(const stack_t __user *uss,
 					stack_t __user *uoss);
 
-/*
- * AArch64 sys_clone implementation has a different prototype than the generic
- * one (additional TLS value argument).
- */
-asmlinkage long sys_clone(unsigned long, unsigned long, void __user *, int,
-	       void __user *);
-#define sys_clone	sys_clone
-
 #include <asm-generic/syscalls.h>
 
 #endif	/* __ASM_SYSCALLS_H */
diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h
index ec2ce6792cd6..4af9c7b6f13a 100644
--- a/arch/hexagon/include/asm/syscall.h
+++ b/arch/hexagon/include/asm/syscall.h
@@ -25,11 +25,6 @@ typedef long (*syscall_fn)(unsigned long, unsigned long,
 	unsigned long, unsigned long,
 	unsigned long, unsigned long);
 
-asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp,
-			 unsigned long parent_tidp, unsigned long child_tidp);
-
-#define sys_clone	sys_clone
-
 #include <asm-generic/syscalls.h>
 
 extern void *sys_call_table[];
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 8653072d7e9f..88a758a67922 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm
 header-y  += elf.h
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += syscalls.h
diff --git a/arch/microblaze/include/asm/syscalls.h b/arch/microblaze/include/asm/syscalls.h
deleted file mode 100644
index 27f2f4c0f39f..000000000000
--- a/arch/microblaze/include/asm/syscalls.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __ASM_MICROBLAZE_SYSCALLS_H
-
-asmlinkage long microblaze_vfork(struct pt_regs *regs);
-asmlinkage long microblaze_clone(int flags, unsigned long stack,
-							struct pt_regs *regs);
-asmlinkage long microblaze_execve(const char __user *filenamei,
-				  const char __user *const __user *argv,
-				  const char __user *const __user *envp,
-				  struct pt_regs *regs);
-
-asmlinkage long sys_clone(int flags, unsigned long stack, struct pt_regs *regs);
-#define sys_clone sys_clone
-
-#include <asm-generic/syscalls.h>
-
-#endif /* __ASM_MICROBLAZE_SYSCALLS_H */
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index d0d3f69a7346..d8251b98f17a 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -54,10 +54,6 @@ long sys_s390_fadvise64(int fd, u32 offset_high, u32 offset_low,
 long sys_s390_fadvise64_64(struct fadvise64_64_args __user *args);
 long sys_s390_fallocate(int fd, int mode, loff_t offset, u32 len_high,
 			u32 len_low);
-long sys_fork(void);
-long sys_clone(unsigned long newsp, unsigned long clone_flags,
-	       int __user *parent_tidptr, int __user *child_tidptr);
-long sys_vfork(void);
 long sys_sigsuspend(int history0, int history1, old_sigset_t mask);
 long sys_sigaction(int sig, const struct old_sigaction __user *act,
 		   struct old_sigaction __user *oact);
diff --git a/arch/tile/include/asm/syscalls.h b/arch/tile/include/asm/syscalls.h
index 394c76f2dc76..4c8462a62cb6 100644
--- a/arch/tile/include/asm/syscalls.h
+++ b/arch/tile/include/asm/syscalls.h
@@ -63,11 +63,8 @@ long sys_ftruncate64(unsigned int fd, loff_t length);
 #endif
 
 /* Provide versions of standard syscalls that use current_pt_regs(). */
-long sys_clone(unsigned long clone_flags, unsigned long newsp,
-		void __user *parent_tid, void __user *child_tid);
 long sys_rt_sigreturn(void);
 long sys_sigaltstack(const stack_t __user *, stack_t __user *);
-#define sys_clone sys_clone
 #define sys_rt_sigreturn sys_rt_sigreturn
 #define sys_sigaltstack sys_sigaltstack
 
diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c
index a2e805569d5d..9cd7cb6041c0 100644
--- a/arch/tile/kernel/compat.c
+++ b/arch/tile/kernel/compat.c
@@ -104,7 +104,6 @@ long compat_sys_sched_rr_get_interval(compat_pid_t pid,
 
 /* Call the assembly trampolines where necessary. */
 #define compat_sys_rt_sigreturn _compat_sys_rt_sigreturn
-#undef sys_clone
 #define sys_clone _sys_clone
 
 /*
diff --git a/arch/tile/kernel/sys.c b/arch/tile/kernel/sys.c
index 02ff5c0ef775..b881a7be24bd 100644
--- a/arch/tile/kernel/sys.c
+++ b/arch/tile/kernel/sys.c
@@ -109,7 +109,6 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 /* Call the assembly trampolines where necessary. */
 #undef sys_rt_sigreturn
 #define sys_rt_sigreturn _sys_rt_sigreturn
-#undef sys_clone
 #define sys_clone _sys_clone
 
 /*
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index f7252d11416b..2f8374718aa3 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -20,17 +20,6 @@
 asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
 long sys_iopl(unsigned int, struct pt_regs *);
 
-/* kernel/process.c */
-asmlinkage long sys_fork(void);
-asmlinkage long sys_vfork(void);
-#ifdef CONFIG_CLONE_BACKWARDS
-asmlinkage long sys_clone(unsigned long, unsigned long, void __user *, int,
-	       void __user *);
-#else
-asmlinkage long sys_clone(unsigned long, unsigned long, void __user *,
-	       void __user *, int);
-#endif
-
 /* kernel/ldt.c */
 asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
 
diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h
index ca255a805ed9..bd9a89b67e41 100644
--- a/arch/x86/um/shared/sysdep/syscalls.h
+++ b/arch/x86/um/shared/sysdep/syscalls.h
@@ -1,5 +1,3 @@
-extern long sys_clone(unsigned long clone_flags, unsigned long newsp,
-	       void __user *parent_tid, void __user *child_tid);
 #ifdef __i386__
 #include "syscalls_32.h"
 #else
diff --git a/include/asm-generic/syscalls.h b/include/asm-generic/syscalls.h
index 77960333b1a1..58f466ff00d3 100644
--- a/include/asm-generic/syscalls.h
+++ b/include/asm-generic/syscalls.h
@@ -8,18 +8,6 @@
  * Calling conventions for these system calls can differ, so
  * it's possible to override them.
  */
-#ifndef sys_clone
-asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp,
-			void __user *parent_tid, void __user *child_tid);
-#endif
-
-#ifndef sys_fork
-asmlinkage long sys_fork(void);
-#endif
-
-#ifndef sys_vfork
-asmlinkage long sys_vfork(void);
-#endif
 
 #ifndef sys_mmap2
 asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 526deb333b91..91835e7f364d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -836,6 +836,16 @@ int kernel_execve(const char *filename, const char *const argv[], const char *co
 		(const char __user *const __user *)envp)
 #endif
 
+asmlinkage long sys_fork(void);
+asmlinkage long sys_vfork(void);
+#ifdef CONFIG_CLONE_BACKWARDS
+asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int,
+	       int __user *);
+#else
+asmlinkage long sys_clone(unsigned long, unsigned long, int __user *,
+	       int __user *, int);
+#endif
+
 asmlinkage long sys_execve(const char __user *filename,
 		const char __user *const __user *argv,
 		const char __user *const __user *envp);
-- 
cgit v1.2.3-55-g7522


From afa86fc426ff7e7f5477f15da9c405d08d5cf790 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Mon, 22 Oct 2012 22:51:14 -0400
Subject: flagday: don't pass regs to copy_thread()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/kernel/process.c         | 2 +-
 arch/arm/kernel/process.c           | 2 +-
 arch/arm64/kernel/process.c         | 3 +--
 arch/avr32/kernel/process.c         | 2 +-
 arch/blackfin/kernel/process.c      | 6 +++---
 arch/c6x/kernel/process.c           | 2 +-
 arch/cris/arch-v10/kernel/process.c | 3 +--
 arch/cris/arch-v32/kernel/process.c | 3 +--
 arch/frv/kernel/process.c           | 2 +-
 arch/h8300/kernel/process.c         | 2 +-
 arch/hexagon/kernel/process.c       | 3 +--
 arch/ia64/kernel/process.c          | 3 ++-
 arch/m32r/kernel/process.c          | 2 +-
 arch/m68k/kernel/process.c          | 3 +--
 arch/microblaze/kernel/process.c    | 3 +--
 arch/mips/kernel/process.c          | 4 ++--
 arch/mn10300/kernel/process.c       | 2 +-
 arch/openrisc/kernel/process.c      | 2 +-
 arch/parisc/kernel/process.c        | 5 ++---
 arch/powerpc/kernel/process.c       | 4 ++--
 arch/s390/kernel/process.c          | 3 +--
 arch/score/kernel/process.c         | 4 ++--
 arch/sh/kernel/process_32.c         | 3 +--
 arch/sh/kernel/process_64.c         | 5 ++---
 arch/sparc/kernel/process_32.c      | 5 ++---
 arch/sparc/kernel/process_64.c      | 4 ++--
 arch/tile/kernel/process.c          | 5 ++---
 arch/um/kernel/process.c            | 3 +--
 arch/unicore32/kernel/process.c     | 2 +-
 arch/x86/kernel/process_32.c        | 3 +--
 arch/x86/kernel/process_64.c        | 3 +--
 arch/xtensa/kernel/process.c        | 3 +--
 include/linux/sched.h               | 2 +-
 kernel/fork.c                       | 2 +-
 34 files changed, 45 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index e9705bcc96f9..b5d0d0923699 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -241,7 +241,7 @@ release_thread(struct task_struct *dead_task)
 int
 copy_thread(unsigned long clone_flags, unsigned long usp,
 	    unsigned long arg,
-	    struct task_struct *p, struct pt_regs *wontuse)
+	    struct task_struct *p)
 {
 	extern void ret_from_fork(void);
 	extern void ret_from_kernel_thread(void);
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 4ab80bbb6d95..9800338c5d1b 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -376,7 +376,7 @@ asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
 int
 copy_thread(unsigned long clone_flags, unsigned long stack_start,
-	    unsigned long stk_sz, struct task_struct *p, struct pt_regs *unused)
+	    unsigned long stk_sz, struct task_struct *p)
 {
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 5a1335caf6f1..cb0956bc96ed 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -234,8 +234,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 asmlinkage void ret_from_fork(void) asm("ret_from_fork");
 
 int copy_thread(unsigned long clone_flags, unsigned long stack_start,
-		unsigned long stk_sz, struct task_struct *p,
-		struct pt_regs *unused)
+		unsigned long stk_sz, struct task_struct *p)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 	unsigned long tls = p->thread.tp_value;
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index 03d7aa4a4bc9..fd78f58ea79a 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -299,7 +299,7 @@ asmlinkage void syscall_return(void);
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
 		unsigned long arg,
-		struct task_struct *p, struct pt_regs *unused)
+		struct task_struct *p)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index e5ae8fcab438..582276efaaa4 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -141,14 +141,14 @@ asmlinkage int bfin_clone(unsigned long clone_flags, unsigned long newsp)
 int
 copy_thread(unsigned long clone_flags,
 	    unsigned long usp, unsigned long topstk,
-	    struct task_struct *p, struct pt_regs *regs)
+	    struct task_struct *p)
 {
 	struct pt_regs *childregs;
 	unsigned long *v;
 
 	childregs = (struct pt_regs *) (task_stack_page(p) + THREAD_SIZE) - 1;
 	v = ((unsigned long *)childregs) - 2;
-	if (unlikely(!regs)) {
+	if (unlikely(p->flags & PF_KTHREAD)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		v[0] = usp;
 		v[1] = topstk;
@@ -157,7 +157,7 @@ copy_thread(unsigned long clone_flags,
 		__asm__ __volatile__("%0 = syscfg;":"=da"(childregs->syscfg):);
 		p->thread.usp = 0;
 	} else {
-		*childregs = *regs;
+		*childregs = *current_pt_regs();
 		childregs->r0 = 0;
 		p->thread.usp = usp ? : rdusp();
 		v[0] = v[1] = 0;
diff --git a/arch/c6x/kernel/process.c b/arch/c6x/kernel/process.c
index a3f91895e8b4..6434df476f77 100644
--- a/arch/c6x/kernel/process.c
+++ b/arch/c6x/kernel/process.c
@@ -139,7 +139,7 @@ void start_thread(struct pt_regs *regs, unsigned int pc, unsigned long usp)
  */
 int copy_thread(unsigned long clone_flags, unsigned long usp,
 		unsigned long ustk_size,
-		struct task_struct *p, struct pt_regs *unused)
+		struct task_struct *p)
 {
 	struct pt_regs *childregs;
 
diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c
index 520547c8b196..b1018750cffb 100644
--- a/arch/cris/arch-v10/kernel/process.c
+++ b/arch/cris/arch-v10/kernel/process.c
@@ -94,8 +94,7 @@ asmlinkage void ret_from_fork(void);
 asmlinkage void ret_from_kernel_thread(void);
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg,
-		struct task_struct *p, struct pt_regs *unused)
+		unsigned long arg, struct task_struct *p)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct switch_stack *swstack = ((struct switch_stack *)childregs) - 1;
diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c
index 331e70252df0..2b23ef0e4452 100644
--- a/arch/cris/arch-v32/kernel/process.c
+++ b/arch/cris/arch-v32/kernel/process.c
@@ -109,8 +109,7 @@ extern asmlinkage void ret_from_kernel_thread(void);
 
 int
 copy_thread(unsigned long clone_flags, unsigned long usp,
-	unsigned long arg,
-	struct task_struct *p, struct pt_regs *unused)
+	unsigned long arg, struct task_struct *p)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct switch_stack *swstack = ((struct switch_stack *) childregs) - 1;
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index 0039bf77b192..23916b2a12a2 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -144,7 +144,7 @@ inline unsigned long user_stack(const struct pt_regs *regs)
  */
 int copy_thread(unsigned long clone_flags,
 		unsigned long usp, unsigned long arg,
-		struct task_struct *p, struct pt_regs *unused)
+		struct task_struct *p)
 {
 	struct pt_regs *childregs;
 
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index b0fb4054aee5..b609f63f1590 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -129,7 +129,7 @@ void flush_thread(void)
 
 int copy_thread(unsigned long clone_flags,
                 unsigned long usp, unsigned long topstk,
-		 struct task_struct * p, struct pt_regs *unused)
+		 struct task_struct * p)
 {
 	struct pt_regs * childregs;
 
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index 36dce17ed25c..06ae9ffcabd5 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -87,8 +87,7 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
  * Copy architecture-specific thread state
  */
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg, struct task_struct *p,
-		struct pt_regs *unused)
+		unsigned long arg, struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
 	struct hexagon_switch_stack *ss;
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 25543a295ad9..31360cbbd5f8 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -393,12 +393,13 @@ ia64_load_extra (struct task_struct *task)
 int
 copy_thread(unsigned long clone_flags,
 	     unsigned long user_stack_base, unsigned long user_stack_size,
-	     struct task_struct *p, struct pt_regs *regs)
+	     struct task_struct *p)
 {
 	extern char ia64_ret_from_clone;
 	struct switch_stack *child_stack, *stack;
 	unsigned long rbs, child_rbs, rbs_size;
 	struct pt_regs *child_ptregs;
+	struct pt_regs *regs = current_pt_regs();
 	int retval = 0;
 
 	child_ptregs = (struct pt_regs *) ((unsigned long) p + IA64_STK_OFFSET) - 1;
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index c37e9a9a8f27..765d0f57c787 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -192,7 +192,7 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long spu,
-	unsigned long arg, struct task_struct *tsk, struct pt_regs *unused)
+	unsigned long arg, struct task_struct *tsk)
 {
 	struct pt_regs *childregs = task_pt_regs(tsk);
 	extern void ret_from_fork(void);
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index aa9b11000273..9a3df4df73cc 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -154,8 +154,7 @@ asmlinkage int m68k_clone(struct pt_regs *regs)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		 unsigned long arg,
-		 struct task_struct * p, struct pt_regs * unused)
+		 unsigned long arg, struct task_struct *p)
 {
 	struct fork_frame {
 		struct switch_stack sw;
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index a5fed8db7263..40823fd1db0b 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -120,8 +120,7 @@ void flush_thread(void)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg,
-		struct task_struct *p, struct pt_regs *unused)
+		unsigned long arg, struct task_struct *p)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct thread_info *ti = task_thread_info(p);
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index d13720ac656f..38097652d62d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -114,10 +114,10 @@ void flush_thread(void)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-	unsigned long arg, struct task_struct *p, struct pt_regs *regs)
+	unsigned long arg, struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
-	struct pt_regs *childregs;
+	struct pt_regs *childregs, *regs = current_pt_regs();
 	unsigned long childksp;
 	p->set_child_tid = p->clear_child_tid = NULL;
 
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index 5e0ef396458d..eb09f5a552ff 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -206,7 +206,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
  */
 int copy_thread(unsigned long clone_flags,
 		unsigned long c_usp, unsigned long ustk_size,
-		struct task_struct *p, struct pt_regs *unused)
+		struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *c_regs;
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 6b853668369b..00c233bf0d06 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -142,7 +142,7 @@ extern asmlinkage void ret_from_fork(void);
 
 int
 copy_thread(unsigned long clone_flags, unsigned long usp,
-	    unsigned long arg, struct task_struct *p, struct pt_regs *regs)
+	    unsigned long arg, struct task_struct *p)
 {
 	struct pt_regs *userregs;
 	struct pt_regs *kregs;
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 9753ecf49a06..d13507246c5d 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -204,10 +204,9 @@ int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r)
 
 int
 copy_thread(unsigned long clone_flags, unsigned long usp,
-	    unsigned long arg,
-	    struct task_struct *p, struct pt_regs *unused)
+	    unsigned long arg, struct task_struct *p)
 {
-	struct pt_regs * cregs = &(p->thread.regs);
+	struct pt_regs *cregs = &(p->thread.regs);
 	void *stack = task_stack_page(p);
 	
 	/* We have to use void * instead of a function pointer, because
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index a31437567631..81430674e71c 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -733,8 +733,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg, struct task_struct *p,
-		struct pt_regs *regs)
+		unsigned long arg, struct task_struct *p)
 {
 	struct pt_regs *childregs, *kregs;
 	extern void ret_from_fork(void);
@@ -759,6 +758,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 		ti->flags |= _TIF_RESTOREALL;
 		f = ret_from_kernel_thread;
 	} else {
+		struct pt_regs *regs = current_pt_regs();
 		CHECK_FULL_REGS(regs);
 		*childregs = *regs;
 		if (usp)
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index e37677796a09..536d64579d9a 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -117,8 +117,7 @@ void release_thread(struct task_struct *dead_task)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
-		unsigned long arg,
-		struct task_struct *p, struct pt_regs *unused)
+		unsigned long arg, struct task_struct *p)
 {
 	struct thread_info *ti;
 	struct fake_frame
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index f96379a5aee0..79568466b578 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -87,11 +87,11 @@ void flush_thread(void) {}
  * set up the kernel stack and exception frames for a new process
  */
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg,
-		struct task_struct *p, struct pt_regs *regs)
+		unsigned long arg, struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
+	struct pt_regs *regs = current_pt_regs();
 
 	p->thread.reg0 = (unsigned long) childregs;
 	if (unlikely(p->flags & PF_KTHREAD)) {
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 1786d16b6c64..73eb66fc6253 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -128,8 +128,7 @@ asmlinkage void ret_from_fork(void);
 asmlinkage void ret_from_kernel_thread(void);
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg,
-		struct task_struct *p, struct pt_regs *unused)
+		unsigned long arg, struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs;
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index d5c86a8a3849..e611c85144b1 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -371,10 +371,9 @@ asmlinkage void ret_from_fork(void);
 asmlinkage void ret_from_kernel_thread(void);
 
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg,
-		struct task_struct *p, struct pt_regs *regs)
+		unsigned long arg, struct task_struct *p)
 {
-	struct pt_regs *childregs;
+	struct pt_regs *childregs, *regs = current_pt_regs();
 
 #ifdef CONFIG_SH_FPU
 	/* can't happen for a kernel thread */
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index bf4c6addce7b..ecde946ef834 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -319,11 +319,10 @@ extern void ret_from_fork(void);
 extern void ret_from_kernel_thread(void);
 
 int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long arg,
-		struct task_struct *p, struct pt_regs *regs)
+		unsigned long arg, struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
-	struct pt_regs *childregs;
+	struct pt_regs *childregs, *regs = current_pt_regs();
 	char *new_stack;
 
 #ifndef CONFIG_SMP
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index dff54f46728d..58ef19e7e82f 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -622,10 +622,10 @@ asmlinkage long sparc_do_fork(unsigned long clone_flags,
  * Child  -->  %o0 == parents pid, %o1 == 1
  */
 int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long arg,
-		struct task_struct *p, struct pt_regs *regs)
+		unsigned long arg, struct task_struct *p)
 {
 	struct thread_info *t = task_thread_info(p);
+	struct pt_regs *regs = current_pt_regs();
 	struct sparc_stackf *parent_sf;
 	unsigned long child_stack_sz;
 	char *child_trap_frame;
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 267936b51b59..0e5661e7d00d 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -157,10 +157,9 @@ void arch_release_thread_info(struct thread_info *info)
 static void save_arch_state(struct thread_struct *t);
 
 int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long arg,
-		struct task_struct *p, struct pt_regs *unused)
+		unsigned long arg, struct task_struct *p)
 {
-	struct pt_regs *childregs = task_pt_regs(p);
+	struct pt_regs *childregs = task_pt_regs(p), *regs = current_pt_regs();
 	unsigned long ksp;
 	unsigned long *callee_regs;
 
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index c502c804e8bb..b462b13c5bae 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -161,8 +161,7 @@ void fork_handler(void)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long arg, struct task_struct * p,
-		struct pt_regs *regs)
+		unsigned long arg, struct task_struct * p)
 {
 	void (*handler)(void);
 	int kthread = current->flags & PF_KTHREAD;
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index 79e44e8ae31c..62bad9fed03e 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -262,7 +262,7 @@ asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
 
 int
 copy_thread(unsigned long clone_flags, unsigned long stack_start,
-	    unsigned long stk_sz, struct task_struct *p, struct pt_regs *unused)
+	    unsigned long stk_sz, struct task_struct *p)
 {
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 16efa974532b..b5a8905785e6 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -128,8 +128,7 @@ void release_thread(struct task_struct *dead_task)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long sp,
-	unsigned long arg,
-	struct task_struct *p, struct pt_regs *unused)
+	unsigned long arg, struct task_struct *p)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct task_struct *tsk;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 74aac76c6e34..6e68a6194965 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -146,8 +146,7 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long arg,
-	struct task_struct *p, struct pt_regs *regs)
+		unsigned long arg, struct task_struct *p)
 {
 	int err;
 	struct pt_regs *childregs;
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 0036c14739f8..1accf28da5f5 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -199,8 +199,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
  */
 
 int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn,
-		unsigned long thread_fn_arg,
-		struct task_struct *p, struct pt_regs *unused)
+		unsigned long thread_fn_arg, struct task_struct *p)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c57249782e48..78a2ae3470df 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2271,7 +2271,7 @@ extern void mm_release(struct task_struct *, struct mm_struct *);
 extern struct mm_struct *dup_mm(struct task_struct *tsk);
 
 extern int copy_thread(unsigned long, unsigned long, unsigned long,
-			struct task_struct *, struct pt_regs *);
+			struct task_struct *);
 extern void flush_thread(void);
 extern void exit_thread(void);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 27a337549dab..d96a562b1311 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1320,7 +1320,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	retval = copy_io(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_namespaces;
-	retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
+	retval = copy_thread(clone_flags, stack_start, stack_size, p);
 	if (retval)
 		goto bad_fork_cleanup_io;
 
-- 
cgit v1.2.3-55-g7522


From e80d6661c3a5caa0cebec0853c6cb0db090fb506 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Mon, 22 Oct 2012 23:10:08 -0400
Subject: flagday: kill pt_regs argument of do_fork()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/blackfin/kernel/process.c |  2 +-
 arch/ia64/kernel/entry.S       | 14 ++++++--------
 arch/m68k/kernel/process.c     |  2 +-
 arch/mips/kernel/linux32.c     |  2 +-
 arch/mips/kernel/syscall.c     |  4 ++--
 arch/sparc/kernel/process_32.c |  3 +--
 arch/sparc/kernel/process_64.c |  3 +--
 include/linux/sched.h          |  2 +-
 kernel/fork.c                  | 13 +++++--------
 9 files changed, 19 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 582276efaaa4..3e16ad9b0a99 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -135,7 +135,7 @@ asmlinkage int bfin_clone(unsigned long clone_flags, unsigned long newsp)
 #endif
 	if (newsp)
 		newsp -= 12;
-	return do_fork(clone_flags, newsp, regs, 0, NULL, NULL);
+	return do_fork(clone_flags, newsp, 0, NULL, NULL);
 }
 
 int
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 940a67263629..e25b784a2b72 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -116,13 +116,12 @@ GLOBAL_ENTRY(sys_clone2)
 	mov loc1=r16				// save ar.pfs across do_fork
 	.body
 	mov out1=in1
-	mov out3=in2
+	mov out2=in2
 	tbit.nz p6,p0=in0,CLONE_SETTLS_BIT
-	mov out4=in3	// parent_tidptr: valid only w/CLONE_PARENT_SETTID
+	mov out3=in3	// parent_tidptr: valid only w/CLONE_PARENT_SETTID
 	;;
 (p6)	st8 [r2]=in5				// store TLS in r16 for copy_thread()
-	mov out5=in4	// child_tidptr:  valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID
-	adds out2=IA64_SWITCH_STACK_SIZE+16,sp	// out2 = &regs
+	mov out4=in4	// child_tidptr:  valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID
 	mov out0=in0				// out0 = clone_flags
 	br.call.sptk.many rp=do_fork
 .ret1:	.restore sp
@@ -148,13 +147,12 @@ GLOBAL_ENTRY(sys_clone)
 	mov loc1=r16				// save ar.pfs across do_fork
 	.body
 	mov out1=in1
-	mov out3=16				// stacksize (compensates for 16-byte scratch area)
+	mov out2=16				// stacksize (compensates for 16-byte scratch area)
 	tbit.nz p6,p0=in0,CLONE_SETTLS_BIT
-	mov out4=in2	// parent_tidptr: valid only w/CLONE_PARENT_SETTID
+	mov out3=in2	// parent_tidptr: valid only w/CLONE_PARENT_SETTID
 	;;
 (p6)	st8 [r2]=in4				// store TLS in r13 (tp)
-	mov out5=in3	// child_tidptr:  valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID
-	adds out2=IA64_SWITCH_STACK_SIZE+16,sp	// out2 = &regs
+	mov out4=in3	// child_tidptr:  valid only w/CLONE_CHILD_SETTID or CLONE_CHILD_CLEARTID
 	mov out0=in0				// out0 = clone_flags
 	br.call.sptk.many rp=do_fork
 .ret2:	.restore sp
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 9a3df4df73cc..d538694ad208 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -149,7 +149,7 @@ void flush_thread(void)
 asmlinkage int m68k_clone(struct pt_regs *regs)
 {
 	/* regs will be equal to current_pt_regs() */
-	return do_fork(regs->d1, regs->d2, regs, 0,
+	return do_fork(regs->d1, regs->d2, 0,
 		       (int __user *)regs->d3, (int __user *)regs->d4);
 }
 
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 8796dbc7e358..7adab86c632c 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -312,7 +312,7 @@ _sys32_clone(nabi_no_regargs struct pt_regs regs)
 	/* Use __dummy4 instead of getting it off the stack, so that
 	   syscall() works.  */
 	child_tidptr = (int __user *) __dummy4;
-	return do_fork(clone_flags, newsp, &regs, 0,
+	return do_fork(clone_flags, newsp, 0,
 	               parent_tidptr, child_tidptr);
 }
 
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index c611e2df7767..201cb76b4df9 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -92,7 +92,7 @@ save_static_function(sys_fork);
 static int __used noinline
 _sys_fork(nabi_no_regargs struct pt_regs regs)
 {
-	return do_fork(SIGCHLD, regs.regs[29], &regs, 0, NULL, NULL);
+	return do_fork(SIGCHLD, regs.regs[29], 0, NULL, NULL);
 }
 
 save_static_function(sys_clone);
@@ -123,7 +123,7 @@ _sys_clone(nabi_no_regargs struct pt_regs regs)
 #else
 	child_tidptr = (int __user *) regs.regs[8];
 #endif
-	return do_fork(clone_flags, newsp, &regs, 0,
+	return do_fork(clone_flags, newsp, 0,
 	               parent_tidptr, child_tidptr);
 }
 
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index ecde946ef834..be8e862badaf 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -286,8 +286,7 @@ asmlinkage int sparc_do_fork(unsigned long clone_flags,
 	parent_tid_ptr = regs->u_regs[UREG_I2];
 	child_tid_ptr = regs->u_regs[UREG_I4];
 
-	ret = do_fork(clone_flags, stack_start,
-		      regs, stack_size,
+	ret = do_fork(clone_flags, stack_start, stack_size,
 		      (int __user *) parent_tid_ptr,
 		      (int __user *) child_tid_ptr);
 
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 58ef19e7e82f..cdb80b2adbe0 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -601,8 +601,7 @@ asmlinkage long sparc_do_fork(unsigned long clone_flags,
 		child_tid_ptr = (int __user *) regs->u_regs[UREG_I4];
 	}
 
-	ret = do_fork(clone_flags, stack_start,
-		      regs, stack_size,
+	ret = do_fork(clone_flags, stack_start, stack_size,
 		      parent_tid_ptr, child_tid_ptr);
 
 	/* If we get an error and potentially restart the system
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 78a2ae3470df..1162258bcaf0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2289,7 +2289,7 @@ extern int disallow_signal(int);
 extern int do_execve(const char *,
 		     const char __user * const __user *,
 		     const char __user * const __user *);
-extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
+extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 #ifdef CONFIG_GENERIC_KERNEL_THREAD
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/kernel/fork.c b/kernel/fork.c
index 0e68b6686acb..540730783433 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1527,8 +1527,6 @@ static inline void init_idle_pids(struct pid_link *links)
 struct task_struct * __cpuinit fork_idle(int cpu)
 {
 	struct task_struct *task;
-	struct pt_regs regs;
-
 	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0);
 	if (!IS_ERR(task)) {
 		init_idle_pids(task->pids);
@@ -1546,7 +1544,6 @@ struct task_struct * __cpuinit fork_idle(int cpu)
  */
 long do_fork(unsigned long clone_flags,
 	      unsigned long stack_start,
-	      struct pt_regs *regs,
 	      unsigned long stack_size,
 	      int __user *parent_tidptr,
 	      int __user *child_tidptr)
@@ -1576,7 +1573,7 @@ long do_fork(unsigned long clone_flags,
 	 * requested, no event is reported; otherwise, report if the event
 	 * for the type of forking is enabled.
 	 */
-	if (!(clone_flags & CLONE_UNTRACED) && likely(user_mode(regs))) {
+	if (!(clone_flags & CLONE_UNTRACED)) {
 		if (clone_flags & CLONE_VFORK)
 			trace = PTRACE_EVENT_VFORK;
 		else if ((clone_flags & CSIGNAL) != SIGCHLD)
@@ -1632,7 +1629,7 @@ long do_fork(unsigned long clone_flags,
  */
 pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 {
-	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn, NULL,
+	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn,
 		(unsigned long)arg, NULL, NULL);
 }
 #endif
@@ -1641,7 +1638,7 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 SYSCALL_DEFINE0(fork)
 {
 #ifdef CONFIG_MMU
-	return do_fork(SIGCHLD, 0, current_pt_regs(), 0, NULL, NULL);
+	return do_fork(SIGCHLD, 0, 0, NULL, NULL);
 #else
 	/* can not support in nommu mode */
 	return(-EINVAL);
@@ -1652,7 +1649,7 @@ SYSCALL_DEFINE0(fork)
 #ifdef __ARCH_WANT_SYS_VFORK
 SYSCALL_DEFINE0(vfork)
 {
-	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, current_pt_regs(),
+	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, 
 			0, NULL, NULL);
 }
 #endif
@@ -1675,7 +1672,7 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		 int, tls_val)
 #endif
 {
-	return do_fork(clone_flags, newsp, current_pt_regs(), 0,
+	return do_fork(clone_flags, newsp, 0,
 		parent_tidptr, child_tidptr);
 }
 #endif
-- 
cgit v1.2.3-55-g7522


From 4f4202fe5ae9a43e59303f20d700571f695d7b1b Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Mon, 5 Nov 2012 12:59:15 -0500
Subject: unify default ptrace_signal_deliver

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/include/asm/signal.h   | 3 ---
 arch/arm/include/asm/signal.h     | 1 -
 arch/avr32/include/asm/signal.h   | 2 --
 arch/cris/include/asm/signal.h    | 6 ------
 arch/h8300/include/asm/signal.h   | 2 --
 arch/ia64/include/asm/signal.h    | 2 --
 arch/m32r/include/asm/signal.h    | 4 ----
 arch/m68k/include/asm/signal.h    | 5 ++---
 arch/mips/include/asm/signal.h    | 2 --
 arch/mn10300/include/asm/signal.h | 4 ----
 arch/parisc/include/asm/signal.h  | 2 --
 arch/powerpc/include/asm/signal.h | 2 --
 arch/s390/include/asm/signal.h    | 2 --
 arch/sparc/include/asm/signal.h   | 2 --
 arch/x86/include/asm/signal.h     | 2 --
 arch/xtensa/include/asm/signal.h  | 1 -
 include/asm-generic/signal.h      | 2 --
 include/linux/ptrace.h            | 4 ++++
 18 files changed, 6 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/signal.h b/arch/alpha/include/asm/signal.h
index a9388300abb1..45552862cc10 100644
--- a/arch/alpha/include/asm/signal.h
+++ b/arch/alpha/include/asm/signal.h
@@ -164,9 +164,6 @@ struct sigstack {
 
 #ifdef __KERNEL__
 #include <asm/sigcontext.h>
-
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/signal.h b/arch/arm/include/asm/signal.h
index 5a7963dbd3fb..9a0ea6ab988f 100644
--- a/arch/arm/include/asm/signal.h
+++ b/arch/arm/include/asm/signal.h
@@ -35,5 +35,4 @@ struct k_sigaction {
 };
 
 #include <asm/sigcontext.h>
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
 #endif
diff --git a/arch/avr32/include/asm/signal.h b/arch/avr32/include/asm/signal.h
index 4d502fd6bad3..9326d182e9e5 100644
--- a/arch/avr32/include/asm/signal.h
+++ b/arch/avr32/include/asm/signal.h
@@ -37,6 +37,4 @@ struct k_sigaction {
 #include <asm/sigcontext.h>
 #undef __HAVE_ARCH_SIG_BITOPS
 
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif
diff --git a/arch/cris/include/asm/signal.h b/arch/cris/include/asm/signal.h
index ea6af9aad76c..72dbbf59dfae 100644
--- a/arch/cris/include/asm/signal.h
+++ b/arch/cris/include/asm/signal.h
@@ -152,12 +152,6 @@ typedef struct sigaltstack {
 
 #ifdef __KERNEL__
 #include <asm/sigcontext.h>
-
-/* here we could define asm-optimized sigaddset, sigdelset etc. operations. 
- * if we don't, generic ones are used from linux/signal.h
- */
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/arch/h8300/include/asm/signal.h b/arch/h8300/include/asm/signal.h
index fd8b66e40dca..c43c0a7d2c2e 100644
--- a/arch/h8300/include/asm/signal.h
+++ b/arch/h8300/include/asm/signal.h
@@ -154,8 +154,6 @@ typedef struct sigaltstack {
 #include <asm/sigcontext.h>
 #undef __HAVE_ARCH_SIG_BITOPS
 
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif /* __KERNEL__ */
 
 #endif /* _H8300_SIGNAL_H */
diff --git a/arch/ia64/include/asm/signal.h b/arch/ia64/include/asm/signal.h
index aecda5b9eb4e..3a1b20e74c5c 100644
--- a/arch/ia64/include/asm/signal.h
+++ b/arch/ia64/include/asm/signal.h
@@ -38,7 +38,5 @@ struct k_sigaction {
 
 #  include <asm/sigcontext.h>
 
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 # endif /* !__ASSEMBLY__ */
 #endif /* _ASM_IA64_SIGNAL_H */
diff --git a/arch/m32r/include/asm/signal.h b/arch/m32r/include/asm/signal.h
index ea5f95e4079e..e4d2e2ad5f1e 100644
--- a/arch/m32r/include/asm/signal.h
+++ b/arch/m32r/include/asm/signal.h
@@ -149,10 +149,6 @@ typedef struct sigaltstack {
 
 #undef __HAVE_ARCH_SIG_BITOPS
 
-struct pt_regs;
-
-#define ptrace_signal_deliver(regs, cookie)	do { } while (0)
-
 #endif /* __KERNEL__ */
 
 #endif  /* _ASM_M32R_SIGNAL_H */
diff --git a/arch/m68k/include/asm/signal.h b/arch/m68k/include/asm/signal.h
index 2df26b57c26a..eb51a5241187 100644
--- a/arch/m68k/include/asm/signal.h
+++ b/arch/m68k/include/asm/signal.h
@@ -86,11 +86,10 @@ static inline int sigfindinword(unsigned long word)
 
 #endif /* !CONFIG_CPU_HAS_NO_BITFIELDS */
 
-#ifdef __uClinux__
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-#else
+#ifndef __uClinux__
 struct pt_regs;
 extern void ptrace_signal_deliver(struct pt_regs *regs, void *cookie);
+#define ptrace_signal_deliver ptrace_signal_deliver
 #endif /* __uClinux__ */
 
 #endif /* _M68K_SIGNAL_H */
diff --git a/arch/mips/include/asm/signal.h b/arch/mips/include/asm/signal.h
index 880240dff8b7..cf4a08062d1d 100644
--- a/arch/mips/include/asm/signal.h
+++ b/arch/mips/include/asm/signal.h
@@ -21,6 +21,4 @@
 #include <asm/sigcontext.h>
 #include <asm/siginfo.h>
 
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif /* _ASM_SIGNAL_H */
diff --git a/arch/mn10300/include/asm/signal.h b/arch/mn10300/include/asm/signal.h
index f9668ec3040c..d280e9780793 100644
--- a/arch/mn10300/include/asm/signal.h
+++ b/arch/mn10300/include/asm/signal.h
@@ -45,8 +45,4 @@ struct k_sigaction {
 };
 #include <asm/sigcontext.h>
 
-
-struct pt_regs;
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif /* _ASM_SIGNAL_H */
diff --git a/arch/parisc/include/asm/signal.h b/arch/parisc/include/asm/signal.h
index 21abf4fc169a..0fdb3c835952 100644
--- a/arch/parisc/include/asm/signal.h
+++ b/arch/parisc/include/asm/signal.h
@@ -34,8 +34,6 @@ struct k_sigaction {
 	struct sigaction sa;
 };
 
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #include <asm/sigcontext.h>
 
 #endif /* !__ASSEMBLY */
diff --git a/arch/powerpc/include/asm/signal.h b/arch/powerpc/include/asm/signal.h
index 189998bb61c4..a101637725a2 100644
--- a/arch/powerpc/include/asm/signal.h
+++ b/arch/powerpc/include/asm/signal.h
@@ -3,6 +3,4 @@
 
 #include <uapi/asm/signal.h>
 
-struct pt_regs;
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
 #endif /* _ASM_POWERPC_SIGNAL_H */
diff --git a/arch/s390/include/asm/signal.h b/arch/s390/include/asm/signal.h
index bffdbdd5b3d7..db7ddfaf5b79 100644
--- a/arch/s390/include/asm/signal.h
+++ b/arch/s390/include/asm/signal.h
@@ -39,6 +39,4 @@ struct k_sigaction {
         struct sigaction sa;
 };
 
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif
diff --git a/arch/sparc/include/asm/signal.h b/arch/sparc/include/asm/signal.h
index d243c2ae02d2..77b85850d543 100644
--- a/arch/sparc/include/asm/signal.h
+++ b/arch/sparc/include/asm/signal.h
@@ -26,7 +26,5 @@ struct k_sigaction {
 	void			__user *ka_restorer;
 };
 
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif /* !(__ASSEMBLY__) */
 #endif /* !(__SPARC_SIGNAL_H) */
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 323973f4abf1..0dba8b7a6ac7 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -260,8 +260,6 @@ struct pt_regs;
 
 #endif /* !__i386__ */
 
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/xtensa/include/asm/signal.h b/arch/xtensa/include/asm/signal.h
index 72fd44c85b70..6f586bd90e18 100644
--- a/arch/xtensa/include/asm/signal.h
+++ b/arch/xtensa/include/asm/signal.h
@@ -27,7 +27,6 @@ struct k_sigaction {
 };
 
 #include <asm/sigcontext.h>
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
 
 #endif	/* __ASSEMBLY__ */
 #endif	/* _XTENSA_SIGNAL_H */
diff --git a/include/asm-generic/signal.h b/include/asm-generic/signal.h
index 98caa306122a..d840c90a157a 100644
--- a/include/asm-generic/signal.h
+++ b/include/asm-generic/signal.h
@@ -10,7 +10,5 @@
 #include <asm/sigcontext.h>
 #undef __HAVE_ARCH_SIG_BITOPS
 
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_GENERIC_SIGNAL_H */
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index e0ff4689d35a..7aefbae2452e 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -329,6 +329,10 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
 #define current_pt_regs() task_pt_regs(current)
 #endif
 
+#ifndef ptrace_signal_deliver
+#define ptrace_signal_deliver(regs, cookie) do { } while (0)
+#endif
+
 extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);
-- 
cgit v1.2.3-55-g7522


From 22062a96300dabfef93368a28c34bdf35c9b8308 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Mon, 5 Nov 2012 13:00:27 -0500
Subject: new helper: signal_pt_regs()

Always equal to task_pt_regs(current); defined only when we are in
signal delivery.  It may be different from current_pt_regs() - e.g.
architectures like m68k may have pt_regs location on exception
different from that on a syscall and signals (just as ptrace handling)
may happen on exceptions as well as on syscalls.

When they are equal, it's often better to have signal_pt_regs
defined (in asm/ptrace.h) as current_pt_regs - that tends to be
optimized better than default would be.  However, optimisation is
the only reason why we might want an arch-specific definition;
if current_pt_regs() and task_pt_regs(current) have different
values, the latter one is right.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/include/asm/ptrace.h | 1 +
 arch/h8300/include/asm/ptrace.h | 1 +
 include/linux/ptrace.h          | 9 +++++++++
 3 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/arch/alpha/include/asm/ptrace.h b/arch/alpha/include/asm/ptrace.h
index b87755a19554..b4c5b2fbb647 100644
--- a/arch/alpha/include/asm/ptrace.h
+++ b/arch/alpha/include/asm/ptrace.h
@@ -78,6 +78,7 @@ struct switch_stack {
 
 #define current_pt_regs() \
   ((struct pt_regs *) ((char *)current_thread_info() + 2*PAGE_SIZE) - 1)
+#define signal_pt_regs current_pt_regs
 
 #define force_successful_syscall_return() (current_pt_regs()->r0 = 0)
 
diff --git a/arch/h8300/include/asm/ptrace.h b/arch/h8300/include/asm/ptrace.h
index 00502a61bf0a..7468589a128b 100644
--- a/arch/h8300/include/asm/ptrace.h
+++ b/arch/h8300/include/asm/ptrace.h
@@ -62,6 +62,7 @@ struct pt_regs {
 #define profile_pc(regs) instruction_pointer(regs)
 #define current_pt_regs() ((struct pt_regs *) \
 	(THREAD_SIZE + (unsigned long)current_thread_info()) - 1)
+#define signal_pt_regs() ((struct pt_regs *)current->thread.esp0)
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 #endif /* _H8300_PTRACE_H */
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 7aefbae2452e..b8e6dcec78ae 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -333,6 +333,15 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
 #define ptrace_signal_deliver(regs, cookie) do { } while (0)
 #endif
 
+/*
+ * unlike current_pt_regs(), this one is equal to task_pt_regs(current)
+ * on *all* architectures; the only reason to have a per-arch definition
+ * is optimisation.
+ */
+#ifndef signal_pt_regs
+#define signal_pt_regs() task_pt_regs(current)
+#endif
+
 extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);
-- 
cgit v1.2.3-55-g7522


From b7f9591c44505ee16ed4561cfeb3642798bdd132 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Mon, 5 Nov 2012 13:06:22 -0500
Subject: get rid of ptrace_signal_deliver() arguments

the first one is equal to signal_pt_regs(), the second is never used
(and always NULL, while we are at it).

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/m68k/include/asm/signal.h | 3 +--
 arch/m68k/kernel/signal.c      | 3 ++-
 include/linux/ptrace.h         | 2 +-
 kernel/signal.c                | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/m68k/include/asm/signal.h b/arch/m68k/include/asm/signal.h
index eb51a5241187..9c8c46b06b0c 100644
--- a/arch/m68k/include/asm/signal.h
+++ b/arch/m68k/include/asm/signal.h
@@ -87,8 +87,7 @@ static inline int sigfindinword(unsigned long word)
 #endif /* !CONFIG_CPU_HAS_NO_BITFIELDS */
 
 #ifndef __uClinux__
-struct pt_regs;
-extern void ptrace_signal_deliver(struct pt_regs *regs, void *cookie);
+extern void ptrace_signal_deliver(void);
 #define ptrace_signal_deliver ptrace_signal_deliver
 #endif /* __uClinux__ */
 
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 710a528b928b..9a396cda3147 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -108,8 +108,9 @@ int handle_kernel_fault(struct pt_regs *regs)
 	return 1;
 }
 
-void ptrace_signal_deliver(struct pt_regs *regs, void *cookie)
+void ptrace_signal_deliver(void)
 {
+	struct pt_regs *regs = signal_pt_regs();
 	if (regs->orig_d0 < 0)
 		return;
 	switch (regs->d0) {
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index b8e6dcec78ae..a89ff04bddd9 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -330,7 +330,7 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
 #endif
 
 #ifndef ptrace_signal_deliver
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
+#define ptrace_signal_deliver() ((void)0)
 #endif
 
 /*
diff --git a/kernel/signal.c b/kernel/signal.c
index 0af8868525d6..17d4e17fd614 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2141,7 +2141,7 @@ static void do_jobctl_trap(void)
 static int ptrace_signal(int signr, siginfo_t *info,
 			 struct pt_regs *regs, void *cookie)
 {
-	ptrace_signal_deliver(regs, cookie);
+	ptrace_signal_deliver();
 	/*
 	 * We do not check sig_kernel_stop(signr) but set this marker
 	 * unconditionally because we do not know whether debugger will
-- 
cgit v1.2.3-55-g7522


From 541880d9a2c7871f6370071d55aa6662d329c51e Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Mon, 5 Nov 2012 13:11:26 -0500
Subject: do_coredump(): get rid of pt_regs argument

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/coredump.c            | 4 ++--
 include/linux/coredump.h | 4 ++--
 kernel/signal.c          | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/coredump.c b/fs/coredump.c
index ce47379bfa61..177493272a61 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -458,7 +458,7 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
 	return err;
 }
 
-void do_coredump(siginfo_t *siginfo, struct pt_regs *regs)
+void do_coredump(siginfo_t *siginfo)
 {
 	struct core_state core_state;
 	struct core_name cn;
@@ -474,7 +474,7 @@ void do_coredump(siginfo_t *siginfo, struct pt_regs *regs)
 	static atomic_t core_dump_count = ATOMIC_INIT(0);
 	struct coredump_params cprm = {
 		.siginfo = siginfo,
-		.regs = regs,
+		.regs = signal_pt_regs(),
 		.limit = rlimit(RLIMIT_CORE),
 		/*
 		 * We must use the same mm->flags while dumping core to avoid
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index 1d7399314a89..a98f1ca60407 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -13,9 +13,9 @@
 extern int dump_write(struct file *file, const void *addr, int nr);
 extern int dump_seek(struct file *file, loff_t off);
 #ifdef CONFIG_COREDUMP
-extern void do_coredump(siginfo_t *siginfo, struct pt_regs *regs);
+extern void do_coredump(siginfo_t *siginfo);
 #else
-static inline void do_coredump(siginfo_t *siginfo, struct pt_regs *regs) {}
+static inline void do_coredump(siginfo_t *siginfo) {}
 #endif
 
 #endif /* _LINUX_COREDUMP_H */
diff --git a/kernel/signal.c b/kernel/signal.c
index 2e3b5d572808..e75e4bd2839b 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2359,7 +2359,7 @@ relock:
 			 * first and our do_group_exit call below will use
 			 * that value and ignore the one we pass it.
 			 */
-			do_coredump(info, regs);
+			do_coredump(info);
 		}
 
 		/*
-- 
cgit v1.2.3-55-g7522


From 374a868a726eb8a1cb28ba88805e51ce34222f8d Mon Sep 17 00:00:00 2001
From: Paulo Zanoni
Date: Fri, 23 Nov 2012 12:09:26 -0200
Subject: drm: add drm_mode_cea_vic

This function returns the VIC of the mode. This value can be used when
creating AVI InfoFrames.

Cc: Thierry Reding <thierry.reding@avionic-design.de>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=50371
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Thierry Reding <thierry.reding@avionic-design.de>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_edid.c | 19 +++++++++++++++++++
 include/drm/drm_crtc.h     |  1 +
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 164820003546..011bd4f4635e 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -2079,3 +2079,22 @@ int drm_add_modes_noedid(struct drm_connector *connector,
 	return num_modes;
 }
 EXPORT_SYMBOL(drm_add_modes_noedid);
+
+/**
+ * drm_mode_cea_vic - return the CEA-861 VIC of a given mode
+ * @mode: mode
+ *
+ * RETURNS:
+ * The VIC number, 0 in case it's not a CEA-861 mode.
+ */
+uint8_t drm_mode_cea_vic(const struct drm_display_mode *mode)
+{
+	uint8_t i;
+
+	for (i = 0; i < drm_num_cea_modes; i++)
+		if (drm_mode_equal(mode, &edid_cea_modes[i]))
+			return i + 1;
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_mode_cea_vic);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index c0635b7f8696..3538eda94ef5 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -1055,6 +1055,7 @@ extern struct drm_display_mode *drm_gtf_mode_complex(struct drm_device *dev,
 				int GTF_2C, int GTF_K, int GTF_2J);
 extern int drm_add_modes_noedid(struct drm_connector *connector,
 				int hdisplay, int vdisplay);
+extern uint8_t drm_mode_cea_vic(const struct drm_display_mode *mode);
 
 extern int drm_edid_header_is_valid(const u8 *raw_edid);
 extern bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid);
-- 
cgit v1.2.3-55-g7522


From 4b9347dcbe3b426d19bda99b2061a2d1fe5a2dce Mon Sep 17 00:00:00 2001
From: Marek Szyprowski
Date: Mon, 15 Oct 2012 16:03:51 +0200
Subject: common: DMA-mapping: add DMA_ATTR_FORCE_CONTIGUOUS attribute

This patch adds DMA_ATTR_FORCE_CONTIGUOUS attribute to the DMA-mapping
subsystem.

By default DMA-mapping subsystem is allowed to assemble the buffer
allocated by dma_alloc_attrs() function from individual pages if it can
be mapped as contiguous chunk into device dma address space. By
specifing this attribute the allocated buffer is forced to be contiguous
also in physical memory.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 Documentation/DMA-attributes.txt | 9 +++++++++
 include/linux/dma-attrs.h        | 1 +
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt
index f50309081ac7..e59480db9ee0 100644
--- a/Documentation/DMA-attributes.txt
+++ b/Documentation/DMA-attributes.txt
@@ -91,3 +91,12 @@ transferred to 'device' domain. This attribute can be also used for
 dma_unmap_{single,page,sg} functions family to force buffer to stay in
 device domain after releasing a mapping for it. Use this attribute with
 care!
+
+DMA_ATTR_FORCE_CONTIGUOUS
+-------------------------
+
+By default DMA-mapping subsystem is allowed to assemble the buffer
+allocated by dma_alloc_attrs() function from individual pages if it can
+be mapped as contiguous chunk into device dma address space. By
+specifing this attribute the allocated buffer is forced to be contiguous
+also in physical memory.
diff --git a/include/linux/dma-attrs.h b/include/linux/dma-attrs.h
index f83f793223ff..c8e1831d7572 100644
--- a/include/linux/dma-attrs.h
+++ b/include/linux/dma-attrs.h
@@ -17,6 +17,7 @@ enum dma_attr {
 	DMA_ATTR_NON_CONSISTENT,
 	DMA_ATTR_NO_KERNEL_MAPPING,
 	DMA_ATTR_SKIP_CPU_SYNC,
+	DMA_ATTR_FORCE_CONTIGUOUS,
 	DMA_ATTR_MAX,
 };
 
-- 
cgit v1.2.3-55-g7522


From 9a032e393a8bc888a9b0c898cbdb9db2cee7b536 Mon Sep 17 00:00:00 2001
From: Ian Campbell
Date: Wed, 17 Oct 2012 13:37:49 -0700
Subject: xen: add pages parameter to xen_remap_domain_mfn_range

Also introduce xen_unmap_domain_mfn_range. These are the parts of
Mukesh's "xen/pvh: Implement MMU changes for PVH" which are also
needed as a baseline for ARM privcmd support.

The original patch was:

Signed-off-by: Mukesh Rathor <mukesh.rathor@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

This derivative is also:

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
---
 arch/x86/xen/mmu.c    | 15 ++++++++++++++-
 drivers/xen/privcmd.c |  5 +++--
 include/xen/xen-ops.h |  5 ++++-
 3 files changed, 21 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 6226c99729b9..0f6386a5b437 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2479,7 +2479,9 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token,
 int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 			       unsigned long addr,
 			       unsigned long mfn, int nr,
-			       pgprot_t prot, unsigned domid)
+			       pgprot_t prot, unsigned domid,
+			       struct page **pages)
+
 {
 	struct remap_data rmd;
 	struct mmu_update mmu_update[REMAP_BATCH_SIZE];
@@ -2523,3 +2525,14 @@ out:
 	return err;
 }
 EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
+
+/* Returns: 0 success */
+int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
+			       int numpgs, struct page **pages)
+{
+	if (!pages || !xen_feature(XENFEAT_auto_translated_physmap))
+		return 0;
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 8adb9cc267f9..b612267a8cb6 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -178,7 +178,7 @@ static int mmap_mfn_range(void *data, void *state)
 					msg->va & PAGE_MASK,
 					msg->mfn, msg->npages,
 					vma->vm_page_prot,
-					st->domain);
+					st->domain, NULL);
 	if (rc < 0)
 		return rc;
 
@@ -267,7 +267,8 @@ static int mmap_batch_fn(void *data, void *state)
 	int ret;
 
 	ret = xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1,
-					 st->vma->vm_page_prot, st->domain);
+					 st->vma->vm_page_prot, st->domain,
+					 NULL);
 
 	/* Store error code for second pass. */
 	*(st->err++) = ret;
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 6a198e46ab6e..990b43e441e6 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -27,6 +27,9 @@ struct vm_area_struct;
 int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 			       unsigned long addr,
 			       unsigned long mfn, int nr,
-			       pgprot_t prot, unsigned domid);
+			       pgprot_t prot, unsigned domid,
+			       struct page **pages);
+int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
+			       int numpgs, struct page **pages);
 
 #endif /* INCLUDE_XEN_OPS_H */
-- 
cgit v1.2.3-55-g7522


From 7892f6928d0cd9ef9200a193183c2033b3143dab Mon Sep 17 00:00:00 2001
From: Ian Campbell
Date: Tue, 16 Oct 2012 17:19:15 +0100
Subject: xen: correctly use xen_pfn_t in remap_domain_mfn_range.

For Xen on ARM a PFN is 64 bits so we need to use the appropriate
type here.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
[v2: include the necessary header,
     Reported-by: Fengguang Wu <fengguang.wu@intel.com> ]
---
 arch/x86/xen/mmu.c    | 2 +-
 include/xen/xen-ops.h | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 0f6386a5b437..fd8393f55069 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2478,7 +2478,7 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token,
 
 int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 			       unsigned long addr,
-			       unsigned long mfn, int nr,
+			       xen_pfn_t mfn, int nr,
 			       pgprot_t prot, unsigned domid,
 			       struct page **pages)
 
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 990b43e441e6..a50e7bee8912 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -2,6 +2,7 @@
 #define INCLUDE_XEN_OPS_H
 
 #include <linux/percpu.h>
+#include <asm/xen/interface.h>
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 
@@ -26,7 +27,7 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order);
 struct vm_area_struct;
 int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 			       unsigned long addr,
-			       unsigned long mfn, int nr,
+			       xen_pfn_t mfn, int nr,
 			       pgprot_t prot, unsigned domid,
 			       struct page **pages);
 int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
-- 
cgit v1.2.3-55-g7522


From f832da068b0aadb15f747f6427b6bf945f525ba4 Mon Sep 17 00:00:00 2001
From: Ian Campbell
Date: Wed, 3 Oct 2012 16:37:09 +0100
Subject: xen: arm: implement remap interfaces needed for privcmd mappings.

We use XENMEM_add_to_physmap_range which is the preferred interface
for foreign mappings.

Acked-by: Mukesh Rathor <mukesh.rathor@oracle.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/arm/include/asm/xen/interface.h |   1 +
 arch/arm/xen/enlighten.c             | 100 +++++++++++++++++++++++++++++++++--
 arch/x86/include/asm/xen/interface.h |   1 +
 include/xen/interface/memory.h       |  44 ++++++++++++++-
 4 files changed, 141 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/xen/interface.h b/arch/arm/include/asm/xen/interface.h
index 5000397134b4..1151188bcd83 100644
--- a/arch/arm/include/asm/xen/interface.h
+++ b/arch/arm/include/asm/xen/interface.h
@@ -49,6 +49,7 @@ DEFINE_GUEST_HANDLE(void);
 DEFINE_GUEST_HANDLE(uint64_t);
 DEFINE_GUEST_HANDLE(uint32_t);
 DEFINE_GUEST_HANDLE(xen_pfn_t);
+DEFINE_GUEST_HANDLE(xen_ulong_t);
 
 /* Maximum number of virtual CPUs in multi-processor guests. */
 #define MAX_VIRT_CPUS 1
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index ba5cc134a7d3..f28fc1ac8760 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -9,6 +9,7 @@
 #include <xen/platform_pci.h>
 #include <xen/xenbus.h>
 #include <xen/page.h>
+#include <xen/xen-ops.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 #include <linux/interrupt.h>
@@ -18,6 +19,8 @@
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 
+#include <linux/mm.h>
+
 struct start_info _xen_start_info;
 struct start_info *xen_start_info = &_xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
@@ -43,15 +46,106 @@ EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
 
 static __read_mostly int xen_events_irq = -1;
 
+/* map fgmfn of domid to lpfn in the current domain */
+static int map_foreign_page(unsigned long lpfn, unsigned long fgmfn,
+			    unsigned int domid)
+{
+	int rc;
+	struct xen_add_to_physmap_range xatp = {
+		.domid = DOMID_SELF,
+		.foreign_domid = domid,
+		.size = 1,
+		.space = XENMAPSPACE_gmfn_foreign,
+	};
+	xen_ulong_t idx = fgmfn;
+	xen_pfn_t gpfn = lpfn;
+
+	set_xen_guest_handle(xatp.idxs, &idx);
+	set_xen_guest_handle(xatp.gpfns, &gpfn);
+
+	rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp);
+	if (rc) {
+		pr_warn("Failed to map pfn to mfn rc:%d pfn:%lx mfn:%lx\n",
+			rc, lpfn, fgmfn);
+		return 1;
+	}
+	return 0;
+}
+
+struct remap_data {
+	xen_pfn_t fgmfn; /* foreign domain's gmfn */
+	pgprot_t prot;
+	domid_t  domid;
+	struct vm_area_struct *vma;
+	int index;
+	struct page **pages;
+	struct xen_remap_mfn_info *info;
+};
+
+static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr,
+			void *data)
+{
+	struct remap_data *info = data;
+	struct page *page = info->pages[info->index++];
+	unsigned long pfn = page_to_pfn(page);
+	pte_t pte = pfn_pte(pfn, info->prot);
+
+	if (map_foreign_page(pfn, info->fgmfn, info->domid))
+		return -EFAULT;
+	set_pte_at(info->vma->vm_mm, addr, ptep, pte);
+
+	return 0;
+}
+
 int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 			       unsigned long addr,
-			       unsigned long mfn, int nr,
-			       pgprot_t prot, unsigned domid)
+			       xen_pfn_t mfn, int nr,
+			       pgprot_t prot, unsigned domid,
+			       struct page **pages)
 {
-	return -ENOSYS;
+	int err;
+	struct remap_data data;
+
+	/* TBD: Batching, current sole caller only does page at a time */
+	if (nr > 1)
+		return -EINVAL;
+
+	data.fgmfn = mfn;
+	data.prot = prot;
+	data.domid = domid;
+	data.vma = vma;
+	data.index = 0;
+	data.pages = pages;
+	err = apply_to_page_range(vma->vm_mm, addr, nr << PAGE_SHIFT,
+				  remap_pte_fn, &data);
+	return err;
 }
 EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
 
+int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
+			       int nr, struct page **pages)
+{
+	int i;
+
+	for (i = 0; i < nr; i++) {
+		struct xen_remove_from_physmap xrp;
+		unsigned long rc, pfn;
+
+		pfn = page_to_pfn(pages[i]);
+
+		xrp.domid = DOMID_SELF;
+		xrp.gpfn = pfn;
+		rc = HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp);
+		if (rc) {
+			pr_warn("Failed to unmap pfn:%lx rc:%ld\n",
+				pfn, rc);
+			return rc;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);
+
 /*
  * see Documentation/devicetree/bindings/arm/xen.txt for the
  * documentation of the Xen Device Tree format.
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index 54d52ff1304a..fd9cb7695b5f 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -63,6 +63,7 @@ DEFINE_GUEST_HANDLE(void);
 DEFINE_GUEST_HANDLE(uint64_t);
 DEFINE_GUEST_HANDLE(uint32_t);
 DEFINE_GUEST_HANDLE(xen_pfn_t);
+DEFINE_GUEST_HANDLE(xen_ulong_t);
 #endif
 
 #ifndef HYPERVISOR_VIRT_START
diff --git a/include/xen/interface/memory.h b/include/xen/interface/memory.h
index 90712e2072d5..b40a4315cb8b 100644
--- a/include/xen/interface/memory.h
+++ b/include/xen/interface/memory.h
@@ -153,6 +153,14 @@ struct xen_machphys_mapping {
 };
 DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mapping_t);
 
+#define XENMAPSPACE_shared_info  0 /* shared info page */
+#define XENMAPSPACE_grant_table  1 /* grant table page */
+#define XENMAPSPACE_gmfn         2 /* GMFN */
+#define XENMAPSPACE_gmfn_range   3 /* GMFN range, XENMEM_add_to_physmap only. */
+#define XENMAPSPACE_gmfn_foreign 4 /* GMFN from another dom,
+				    * XENMEM_add_to_physmap_range only.
+				    */
+
 /*
  * Sets the GPFN at which a particular page appears in the specified guest's
  * pseudophysical address space.
@@ -167,8 +175,6 @@ struct xen_add_to_physmap {
     uint16_t    size;
 
     /* Source mapping space. */
-#define XENMAPSPACE_shared_info 0 /* shared info page */
-#define XENMAPSPACE_grant_table 1 /* grant table page */
     unsigned int space;
 
     /* Index into source mapping space. */
@@ -182,6 +188,24 @@ DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap);
 /*** REMOVED ***/
 /*#define XENMEM_translate_gpfn_list  8*/
 
+#define XENMEM_add_to_physmap_range 23
+struct xen_add_to_physmap_range {
+    /* Which domain to change the mapping for. */
+    domid_t domid;
+    uint16_t space; /* => enum phys_map_space */
+
+    /* Number of pages to go through */
+    uint16_t size;
+    domid_t foreign_domid; /* IFF gmfn_foreign */
+
+    /* Indexes into space being mapped. */
+    GUEST_HANDLE(xen_ulong_t) idxs;
+
+    /* GPFN in domid where the source mapping page should appear. */
+    GUEST_HANDLE(xen_pfn_t) gpfns;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_add_to_physmap_range);
+
 /*
  * Returns the pseudo-physical memory map as it was when the domain
  * was started (specified by XENMEM_set_memory_map).
@@ -217,4 +241,20 @@ DEFINE_GUEST_HANDLE_STRUCT(xen_memory_map);
  * during a driver critical region.
  */
 extern spinlock_t xen_reservation_lock;
+
+/*
+ * Unmaps the page appearing at a particular GPFN from the specified guest's
+ * pseudophysical address space.
+ * arg == addr of xen_remove_from_physmap_t.
+ */
+#define XENMEM_remove_from_physmap      15
+struct xen_remove_from_physmap {
+    /* Which domain to change the mapping for. */
+    domid_t domid;
+
+    /* GPFN of the current mapping of the page. */
+    xen_pfn_t gpfn;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_remove_from_physmap);
+
 #endif /* __XEN_PUBLIC_MEMORY_H__ */
-- 
cgit v1.2.3-55-g7522


From b8fbdc42c5c5df8ab1f358fe90e3a8a1bdc9ae48 Mon Sep 17 00:00:00 2001
From: Steffen Trumtrar
Date: Thu, 22 Nov 2012 12:16:43 +0100
Subject: of: add 'const' for of_parse_phandle parameter *np

The existing function does not change the passed device_node pointer. It is
only handed to of_get_property which itself takes a const struct device_node.

of_parse_phandle() can therefore take a const pointer as well.

Signed-off-by: Steffen Trumtrar <s.trumtrar@pengutronix.de>
[grant.likely: drop extraneous whitespace change]
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 drivers/of/base.c  | 4 ++--
 include/linux/of.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index 0ceb26a16050..c3724110a288 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -978,8 +978,8 @@ EXPORT_SYMBOL_GPL(of_property_count_strings);
  * Returns the device_node pointer with refcount incremented.  Use
  * of_node_put() on it when done.
  */
-struct device_node *
-of_parse_phandle(struct device_node *np, const char *phandle_name, int index)
+struct device_node *of_parse_phandle(const struct device_node *np,
+				     const char *phandle_name, int index)
 {
 	const __be32 *phandle;
 	int size;
diff --git a/include/linux/of.h b/include/linux/of.h
index 13e0aacb4d9f..7337dc109c89 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -270,7 +270,7 @@ extern int of_n_size_cells(struct device_node *np);
 extern const struct of_device_id *of_match_node(
 	const struct of_device_id *matches, const struct device_node *node);
 extern int of_modalias_node(struct device_node *node, char *modalias, int len);
-extern struct device_node *of_parse_phandle(struct device_node *np,
+extern struct device_node *of_parse_phandle(const struct device_node *np,
 					    const char *phandle_name,
 					    int index);
 extern int of_parse_phandle_with_args(struct device_node *np,
@@ -438,7 +438,7 @@ static inline int of_property_match_string(struct device_node *np,
 	return -ENOSYS;
 }
 
-static inline struct device_node *of_parse_phandle(struct device_node *np,
+static inline struct device_node *of_parse_phandle(const struct device_node *np,
 						   const char *phandle_name,
 						   int index)
 {
-- 
cgit v1.2.3-55-g7522


From bb728820fe7c42fdb838ab2745fb5fe6b18b5ffa Mon Sep 17 00:00:00 2001
From: Rami Rosen
Date: Wed, 28 Nov 2012 21:55:25 +0000
Subject: core: make GRO methods static.

This patch changes three methods to be static and removes their
EXPORT_SYMBOLs in core/dev.c and their external declaration in
netdevice.h. The methods, dev_gro_receive(), napi_frags_finish() and
napi_skb_finish(), which are in the GRO rx path, are not used
outside core/dev.c.

Signed-off-by: Rami Rosen <ramirose@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 6 ------
 net/core/dev.c            | 9 +++------
 2 files changed, 3 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e9929abeb932..18c5dc98f6dc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2153,16 +2153,10 @@ extern void dev_kfree_skb_any(struct sk_buff *skb);
 extern int		netif_rx(struct sk_buff *skb);
 extern int		netif_rx_ni(struct sk_buff *skb);
 extern int		netif_receive_skb(struct sk_buff *skb);
-extern gro_result_t	dev_gro_receive(struct napi_struct *napi,
-					struct sk_buff *skb);
-extern gro_result_t	napi_skb_finish(gro_result_t ret, struct sk_buff *skb);
 extern gro_result_t	napi_gro_receive(struct napi_struct *napi,
 					 struct sk_buff *skb);
 extern void		napi_gro_flush(struct napi_struct *napi, bool flush_old);
 extern struct sk_buff *	napi_get_frags(struct napi_struct *napi);
-extern gro_result_t	napi_frags_finish(struct napi_struct *napi,
-					  struct sk_buff *skb,
-					  gro_result_t ret);
 extern gro_result_t	napi_gro_frags(struct napi_struct *napi);
 
 static inline void napi_free_frags(struct napi_struct *napi)
diff --git a/net/core/dev.c b/net/core/dev.c
index 2a5f55866429..2f94df257e5a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3592,7 +3592,7 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 }
 EXPORT_SYMBOL(napi_gro_flush);
 
-enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct sk_buff **pp = NULL;
 	struct packet_offload *ptype;
@@ -3683,7 +3683,6 @@ normal:
 	ret = GRO_NORMAL;
 	goto pull;
 }
-EXPORT_SYMBOL(dev_gro_receive);
 
 static inline gro_result_t
 __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
@@ -3710,7 +3709,7 @@ __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 	return dev_gro_receive(napi, skb);
 }
 
-gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
+static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 {
 	switch (ret) {
 	case GRO_NORMAL:
@@ -3736,7 +3735,6 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 
 	return ret;
 }
-EXPORT_SYMBOL(napi_skb_finish);
 
 static void skb_gro_reset_offset(struct sk_buff *skb)
 {
@@ -3788,7 +3786,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(napi_get_frags);
 
-gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
+static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
 			       gro_result_t ret)
 {
 	switch (ret) {
@@ -3813,7 +3811,6 @@ gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
 
 	return ret;
 }
-EXPORT_SYMBOL(napi_frags_finish);
 
 static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 {
-- 
cgit v1.2.3-55-g7522


From 465aac6d496aa3e99caaa6868865fb3830f73d80 Mon Sep 17 00:00:00 2001
From: Randy Dunlap
Date: Fri, 30 Nov 2012 10:01:51 +0000
Subject: Fix build when CONFIG_W1_MASTER_GPIO=m b exporting "allnodes"

ERROR: "allnodes" [drivers/w1/masters/w1-gpio.ko] undefined!

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
[grant.likely: allnodes is too generic; rename to of_allnodes]
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Ville Syrjala <syrjala@sci.fi>
---
 arch/arm/mach-vexpress/v2m.c |  2 +-
 drivers/of/base.c            | 29 +++++++++++++++--------------
 drivers/of/fdt.c             |  2 +-
 drivers/of/pdt.c             | 12 ++++++------
 include/linux/of.h           |  4 ++--
 5 files changed, 25 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 560e0df728f8..359f782c747d 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -589,7 +589,7 @@ void __init v2m_dt_init_early(void)
 		return;
 
 	/* Confirm board type against DT property, if available */
-	if (of_property_read_u32(allnodes, "arm,hbi", &dt_hbi) == 0) {
+	if (of_property_read_u32(of_allnodes, "arm,hbi", &dt_hbi) == 0) {
 		int site = v2m_get_master_site();
 		u32 id = readl(v2m_sysreg_base + (site == SYS_CFG_SITE_DB2 ?
 				V2M_SYS_PROCID1 : V2M_SYS_PROCID0));
diff --git a/drivers/of/base.c b/drivers/of/base.c
index c3724110a288..538e3cfad23e 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -45,7 +45,8 @@ struct alias_prop {
 
 static LIST_HEAD(aliases_lookup);
 
-struct device_node *allnodes;
+struct device_node *of_allnodes;
+EXPORT_SYMBOL(of_allnodes);
 struct device_node *of_chosen;
 struct device_node *of_aliases;
 
@@ -199,7 +200,7 @@ struct device_node *of_find_all_nodes(struct device_node *prev)
 	struct device_node *np;
 
 	read_lock(&devtree_lock);
-	np = prev ? prev->allnext : allnodes;
+	np = prev ? prev->allnext : of_allnodes;
 	for (; np != NULL; np = np->allnext)
 		if (of_node_get(np))
 			break;
@@ -422,7 +423,7 @@ EXPORT_SYMBOL(of_get_child_by_name);
  */
 struct device_node *of_find_node_by_path(const char *path)
 {
-	struct device_node *np = allnodes;
+	struct device_node *np = of_allnodes;
 
 	read_lock(&devtree_lock);
 	for (; np; np = np->allnext) {
@@ -452,7 +453,7 @@ struct device_node *of_find_node_by_name(struct device_node *from,
 	struct device_node *np;
 
 	read_lock(&devtree_lock);
-	np = from ? from->allnext : allnodes;
+	np = from ? from->allnext : of_allnodes;
 	for (; np; np = np->allnext)
 		if (np->name && (of_node_cmp(np->name, name) == 0)
 		    && of_node_get(np))
@@ -481,7 +482,7 @@ struct device_node *of_find_node_by_type(struct device_node *from,
 	struct device_node *np;
 
 	read_lock(&devtree_lock);
-	np = from ? from->allnext : allnodes;
+	np = from ? from->allnext : of_allnodes;
 	for (; np; np = np->allnext)
 		if (np->type && (of_node_cmp(np->type, type) == 0)
 		    && of_node_get(np))
@@ -512,7 +513,7 @@ struct device_node *of_find_compatible_node(struct device_node *from,
 	struct device_node *np;
 
 	read_lock(&devtree_lock);
-	np = from ? from->allnext : allnodes;
+	np = from ? from->allnext : of_allnodes;
 	for (; np; np = np->allnext) {
 		if (type
 		    && !(np->type && (of_node_cmp(np->type, type) == 0)))
@@ -545,7 +546,7 @@ struct device_node *of_find_node_with_property(struct device_node *from,
 	struct property *pp;
 
 	read_lock(&devtree_lock);
-	np = from ? from->allnext : allnodes;
+	np = from ? from->allnext : of_allnodes;
 	for (; np; np = np->allnext) {
 		for (pp = np->properties; pp; pp = pp->next) {
 			if (of_prop_cmp(pp->name, prop_name) == 0) {
@@ -616,7 +617,7 @@ struct device_node *of_find_matching_node_and_match(struct device_node *from,
 		*match = NULL;
 
 	read_lock(&devtree_lock);
-	np = from ? from->allnext : allnodes;
+	np = from ? from->allnext : of_allnodes;
 	for (; np; np = np->allnext) {
 		if (of_match_node(matches, np) && of_node_get(np)) {
 			if (match)
@@ -669,7 +670,7 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 	struct device_node *np;
 
 	read_lock(&devtree_lock);
-	for (np = allnodes; np; np = np->allnext)
+	for (np = of_allnodes; np; np = np->allnext)
 		if (np->phandle == handle)
 			break;
 	of_node_get(np);
@@ -1254,9 +1255,9 @@ void of_attach_node(struct device_node *np)
 
 	write_lock_irqsave(&devtree_lock, flags);
 	np->sibling = np->parent->child;
-	np->allnext = allnodes;
+	np->allnext = of_allnodes;
 	np->parent->child = np;
-	allnodes = np;
+	of_allnodes = np;
 	write_unlock_irqrestore(&devtree_lock, flags);
 }
 
@@ -1277,11 +1278,11 @@ void of_detach_node(struct device_node *np)
 	if (!parent)
 		goto out_unlock;
 
-	if (allnodes == np)
-		allnodes = np->allnext;
+	if (of_allnodes == np)
+		of_allnodes = np->allnext;
 	else {
 		struct device_node *prev;
-		for (prev = allnodes;
+		for (prev = of_allnodes;
 		     prev->allnext != np;
 		     prev = prev->allnext)
 			;
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index e36ff40011f4..a65c39c473bf 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -712,7 +712,7 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
  */
 void __init unflatten_device_tree(void)
 {
-	__unflatten_device_tree(initial_boot_params, &allnodes,
+	__unflatten_device_tree(initial_boot_params, &of_allnodes,
 				early_init_dt_alloc_memory_arch);
 
 	/* Get pointer to "/chosen" and "/aliasas" nodes for use everywhere */
diff --git a/drivers/of/pdt.c b/drivers/of/pdt.c
index 07cc1d678e4d..37b56fd716e6 100644
--- a/drivers/of/pdt.c
+++ b/drivers/of/pdt.c
@@ -241,15 +241,15 @@ void __init of_pdt_build_devicetree(phandle root_node, struct of_pdt_ops *ops)
 	BUG_ON(!ops);
 	of_pdt_prom_ops = ops;
 
-	allnodes = of_pdt_create_node(root_node, NULL);
+	of_allnodes = of_pdt_create_node(root_node, NULL);
 #if defined(CONFIG_SPARC)
-	allnodes->path_component_name = "";
+	of_allnodes->path_component_name = "";
 #endif
-	allnodes->full_name = "/";
+	of_allnodes->full_name = "/";
 
-	nextp = &allnodes->allnext;
-	allnodes->child = of_pdt_build_tree(allnodes,
-			of_pdt_prom_ops->getchild(allnodes->phandle), &nextp);
+	nextp = &of_allnodes->allnext;
+	of_allnodes->child = of_pdt_build_tree(of_allnodes,
+			of_pdt_prom_ops->getchild(of_allnodes->phandle), &nextp);
 
 	/* Get pointer to "/chosen" and "/aliasas" nodes for use everywhere */
 	of_alias_scan(kernel_tree_alloc);
diff --git a/include/linux/of.h b/include/linux/of.h
index 7337dc109c89..60053bd7e79a 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -88,14 +88,14 @@ static inline void of_node_put(struct device_node *node) { }
 #ifdef CONFIG_OF
 
 /* Pointer for first entry in chain of all nodes. */
-extern struct device_node *allnodes;
+extern struct device_node *of_allnodes;
 extern struct device_node *of_chosen;
 extern struct device_node *of_aliases;
 extern rwlock_t devtree_lock;
 
 static inline bool of_have_populated_dt(void)
 {
-	return allnodes != NULL;
+	return of_allnodes != NULL;
 }
 
 static inline bool of_node_is_root(const struct device_node *node)
-- 
cgit v1.2.3-55-g7522


From eed8c02e680c04cd737e0a9cef74e68d8eb0cefa Mon Sep 17 00:00:00 2001
From: Lukas Czerner
Date: Fri, 30 Nov 2012 11:42:40 +0100
Subject: wait: add wait_event_lock_irq() interface

New wait_event{_interruptible}_lock_irq{_cmd} macros added. This commit
moves the private wait_event_lock_irq() macro from MD to regular wait
includes, introduces new macro wait_event_lock_irq_cmd() instead of using
the old method with omitting cmd parameter which is ugly and makes a use
of new macros in the MD. It also introduces the _interruptible_ variant.

The use of new interface is when one have a special lock to protect data
structures used in the condition, or one also needs to invoke "cmd"
before putting it to sleep.

All new macros are expected to be called with the lock taken. The lock
is released before sleep and is reacquired afterwards. We will leave the
macro with the lock held.

Note to DM: IMO this should also fix theoretical race on waitqueue while
using simultaneously wait_event_lock_irq() and wait_event() because of
lack of locking around current state setting and wait queue removal.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Cc: Neil Brown <neilb@suse.de>
Cc: David Howells <dhowells@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/md.c      |   2 +-
 drivers/md/md.h      |  26 --------
 drivers/md/raid1.c   |  15 +++--
 drivers/md/raid10.c  |  15 +++--
 drivers/md/raid5.c   |  12 ++--
 include/linux/wait.h | 164 +++++++++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 184 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9ab768acfb62..7e513a38cec7 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -452,7 +452,7 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
 	spin_lock_irq(&mddev->write_lock);
 	wait_event_lock_irq(mddev->sb_wait,
 			    !mddev->flush_bio,
-			    mddev->write_lock, /*nothing*/);
+			    mddev->write_lock);
 	mddev->flush_bio = bio;
 	spin_unlock_irq(&mddev->write_lock);
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index af443ab868db..1e2fc3d9c74c 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -551,32 +551,6 @@ struct md_thread {
 
 #define THREAD_WAKEUP  0
 
-#define __wait_event_lock_irq(wq, condition, lock, cmd) 		\
-do {									\
-	wait_queue_t __wait;						\
-	init_waitqueue_entry(&__wait, current);				\
-									\
-	add_wait_queue(&wq, &__wait);					\
-	for (;;) {							\
-		set_current_state(TASK_UNINTERRUPTIBLE);		\
-		if (condition)						\
-			break;						\
-		spin_unlock_irq(&lock);					\
-		cmd;							\
-		schedule();						\
-		spin_lock_irq(&lock);					\
-	}								\
-	current->state = TASK_RUNNING;					\
-	remove_wait_queue(&wq, &__wait);				\
-} while (0)
-
-#define wait_event_lock_irq(wq, condition, lock, cmd) 			\
-do {									\
-	if (condition)	 						\
-		break;							\
-	__wait_event_lock_irq(wq, condition, lock, cmd);		\
-} while (0)
-
 static inline void safe_put_page(struct page *p)
 {
 	if (p) put_page(p);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 8034fbd6190c..534dd74a2da0 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -822,7 +822,7 @@ static void raise_barrier(struct r1conf *conf)
 
 	/* Wait until no block IO is waiting */
 	wait_event_lock_irq(conf->wait_barrier, !conf->nr_waiting,
-			    conf->resync_lock, );
+			    conf->resync_lock);
 
 	/* block any new IO from starting */
 	conf->barrier++;
@@ -830,7 +830,7 @@ static void raise_barrier(struct r1conf *conf)
 	/* Now wait for all pending IO to complete */
 	wait_event_lock_irq(conf->wait_barrier,
 			    !conf->nr_pending && conf->barrier < RESYNC_DEPTH,
-			    conf->resync_lock, );
+			    conf->resync_lock);
 
 	spin_unlock_irq(&conf->resync_lock);
 }
@@ -864,8 +864,7 @@ static void wait_barrier(struct r1conf *conf)
 				    (conf->nr_pending &&
 				     current->bio_list &&
 				     !bio_list_empty(current->bio_list)),
-				    conf->resync_lock,
-			);
+				    conf->resync_lock);
 		conf->nr_waiting--;
 	}
 	conf->nr_pending++;
@@ -898,10 +897,10 @@ static void freeze_array(struct r1conf *conf)
 	spin_lock_irq(&conf->resync_lock);
 	conf->barrier++;
 	conf->nr_waiting++;
-	wait_event_lock_irq(conf->wait_barrier,
-			    conf->nr_pending == conf->nr_queued+1,
-			    conf->resync_lock,
-			    flush_pending_writes(conf));
+	wait_event_lock_irq_cmd(conf->wait_barrier,
+				conf->nr_pending == conf->nr_queued+1,
+				conf->resync_lock,
+				flush_pending_writes(conf));
 	spin_unlock_irq(&conf->resync_lock);
 }
 static void unfreeze_array(struct r1conf *conf)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 906ccbd0f7dc..9a08f621b27d 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -952,7 +952,7 @@ static void raise_barrier(struct r10conf *conf, int force)
 
 	/* Wait until no block IO is waiting (unless 'force') */
 	wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
-			    conf->resync_lock, );
+			    conf->resync_lock);
 
 	/* block any new IO from starting */
 	conf->barrier++;
@@ -960,7 +960,7 @@ static void raise_barrier(struct r10conf *conf, int force)
 	/* Now wait for all pending IO to complete */
 	wait_event_lock_irq(conf->wait_barrier,
 			    !conf->nr_pending && conf->barrier < RESYNC_DEPTH,
-			    conf->resync_lock, );
+			    conf->resync_lock);
 
 	spin_unlock_irq(&conf->resync_lock);
 }
@@ -993,8 +993,7 @@ static void wait_barrier(struct r10conf *conf)
 				    (conf->nr_pending &&
 				     current->bio_list &&
 				     !bio_list_empty(current->bio_list)),
-				    conf->resync_lock,
-			);
+				    conf->resync_lock);
 		conf->nr_waiting--;
 	}
 	conf->nr_pending++;
@@ -1027,10 +1026,10 @@ static void freeze_array(struct r10conf *conf)
 	spin_lock_irq(&conf->resync_lock);
 	conf->barrier++;
 	conf->nr_waiting++;
-	wait_event_lock_irq(conf->wait_barrier,
-			    conf->nr_pending == conf->nr_queued+1,
-			    conf->resync_lock,
-			    flush_pending_writes(conf));
+	wait_event_lock_irq_cmd(conf->wait_barrier,
+				conf->nr_pending == conf->nr_queued+1,
+				conf->resync_lock,
+				flush_pending_writes(conf));
 
 	spin_unlock_irq(&conf->resync_lock);
 }
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c5439dce0295..2bf617d6f4fd 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -466,7 +466,7 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 	do {
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    conf->quiesce == 0 || noquiesce,
-				    conf->device_lock, /* nothing */);
+				    conf->device_lock);
 		sh = __find_stripe(conf, sector, conf->generation - previous);
 		if (!sh) {
 			if (!conf->inactive_blocked)
@@ -480,8 +480,7 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 						    (atomic_read(&conf->active_stripes)
 						     < (conf->max_nr_stripes *3/4)
 						     || !conf->inactive_blocked),
-						    conf->device_lock,
-						    );
+						    conf->device_lock);
 				conf->inactive_blocked = 0;
 			} else
 				init_stripe(sh, sector, previous);
@@ -1646,8 +1645,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		spin_lock_irq(&conf->device_lock);
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    !list_empty(&conf->inactive_list),
-				    conf->device_lock,
-				    );
+				    conf->device_lock);
 		osh = get_free_stripe(conf);
 		spin_unlock_irq(&conf->device_lock);
 		atomic_set(&nsh->count, 1);
@@ -4000,7 +3998,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		spin_lock_irq(&conf->device_lock);
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    conf->quiesce == 0,
-				    conf->device_lock, /* nothing */);
+				    conf->device_lock);
 		atomic_inc(&conf->active_aligned_reads);
 		spin_unlock_irq(&conf->device_lock);
 
@@ -6088,7 +6086,7 @@ static void raid5_quiesce(struct mddev *mddev, int state)
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    atomic_read(&conf->active_stripes) == 0 &&
 				    atomic_read(&conf->active_aligned_reads) == 0,
-				    conf->device_lock, /* nothing */);
+				    conf->device_lock);
 		conf->quiesce = 1;
 		spin_unlock_irq(&conf->device_lock);
 		/* allow reshape to continue */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 168dfe122dd3..7cb64d4b499d 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -550,6 +550,170 @@ do {									\
 	__ret;								\
 })
 
+
+#define __wait_event_lock_irq(wq, condition, lock, cmd)			\
+do {									\
+	DEFINE_WAIT(__wait);						\
+									\
+	for (;;) {							\
+		prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE);	\
+		if (condition)						\
+			break;						\
+		spin_unlock_irq(&lock);					\
+		cmd;							\
+		schedule();						\
+		spin_lock_irq(&lock);					\
+	}								\
+	finish_wait(&wq, &__wait);					\
+} while (0)
+
+/**
+ * wait_event_lock_irq_cmd - sleep until a condition gets true. The
+ *			     condition is checked under the lock. This
+ *			     is expected to be called with the lock
+ *			     taken.
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @lock: a locked spinlock_t, which will be released before cmd
+ *	  and schedule() and reacquired afterwards.
+ * @cmd: a command which is invoked outside the critical section before
+ *	 sleep
+ *
+ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
+ * @condition evaluates to true. The @condition is checked each time
+ * the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * This is supposed to be called while holding the lock. The lock is
+ * dropped before invoking the cmd and going to sleep and is reacquired
+ * afterwards.
+ */
+#define wait_event_lock_irq_cmd(wq, condition, lock, cmd)		\
+do {									\
+	if (condition)							\
+		break;							\
+	__wait_event_lock_irq(wq, condition, lock, cmd);		\
+} while (0)
+
+/**
+ * wait_event_lock_irq - sleep until a condition gets true. The
+ *			 condition is checked under the lock. This
+ *			 is expected to be called with the lock
+ *			 taken.
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @lock: a locked spinlock_t, which will be released before schedule()
+ *	  and reacquired afterwards.
+ *
+ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
+ * @condition evaluates to true. The @condition is checked each time
+ * the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * This is supposed to be called while holding the lock. The lock is
+ * dropped before going to sleep and is reacquired afterwards.
+ */
+#define wait_event_lock_irq(wq, condition, lock)			\
+do {									\
+	if (condition)							\
+		break;							\
+	__wait_event_lock_irq(wq, condition, lock, );			\
+} while (0)
+
+
+#define __wait_event_interruptible_lock_irq(wq, condition,		\
+					    lock, ret, cmd)		\
+do {									\
+	DEFINE_WAIT(__wait);						\
+									\
+	for (;;) {							\
+		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
+		if (condition)						\
+			break;						\
+		if (signal_pending(current)) {				\
+			ret = -ERESTARTSYS;				\
+			break;						\
+		}							\
+		spin_unlock_irq(&lock);					\
+		cmd;							\
+		schedule();						\
+		spin_lock_irq(&lock);					\
+	}								\
+	finish_wait(&wq, &__wait);					\
+} while (0)
+
+/**
+ * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true.
+ *		The condition is checked under the lock. This is expected to
+ *		be called with the lock taken.
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @lock: a locked spinlock_t, which will be released before cmd and
+ *	  schedule() and reacquired afterwards.
+ * @cmd: a command which is invoked outside the critical section before
+ *	 sleep
+ *
+ * The process is put to sleep (TASK_INTERRUPTIBLE) until the
+ * @condition evaluates to true or a signal is received. The @condition is
+ * checked each time the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * This is supposed to be called while holding the lock. The lock is
+ * dropped before invoking the cmd and going to sleep and is reacquired
+ * afterwards.
+ *
+ * The macro will return -ERESTARTSYS if it was interrupted by a signal
+ * and 0 if @condition evaluated to true.
+ */
+#define wait_event_interruptible_lock_irq_cmd(wq, condition, lock, cmd)	\
+({									\
+	int __ret = 0;							\
+									\
+	if (!(condition))						\
+		__wait_event_interruptible_lock_irq(wq, condition,	\
+						    lock, __ret, cmd);	\
+	__ret;								\
+})
+
+/**
+ * wait_event_interruptible_lock_irq - sleep until a condition gets true.
+ *		The condition is checked under the lock. This is expected
+ *		to be called with the lock taken.
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @lock: a locked spinlock_t, which will be released before schedule()
+ *	  and reacquired afterwards.
+ *
+ * The process is put to sleep (TASK_INTERRUPTIBLE) until the
+ * @condition evaluates to true or signal is received. The @condition is
+ * checked each time the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * This is supposed to be called while holding the lock. The lock is
+ * dropped before going to sleep and is reacquired afterwards.
+ *
+ * The macro will return -ERESTARTSYS if it was interrupted by a signal
+ * and 0 if @condition evaluated to true.
+ */
+#define wait_event_interruptible_lock_irq(wq, condition, lock)		\
+({									\
+	int __ret = 0;							\
+									\
+	if (!(condition))						\
+		__wait_event_interruptible_lock_irq(wq, condition,	\
+						    lock, __ret, );	\
+	__ret;								\
+})
+
+
 /*
  * These are the old interfaces to sleep waiting for an event.
  * They are racy.  DO NOT use them, use the wait_event* interfaces above.
-- 
cgit v1.2.3-55-g7522


From 7b5a35225b0d4fd779cf79d7624e63d1957f6c4d Mon Sep 17 00:00:00 2001
From: Lukas Czerner
Date: Fri, 30 Nov 2012 11:42:41 +0100
Subject: loop: Limit the number of requests in the bio list

Currently there is not limitation of number of requests in the loop bio
list. This can lead into some nasty situations when the caller spawns
tons of bio requests taking huge amount of memory. This is even more
obvious with discard where blkdev_issue_discard() will submit all bios
for the range and wait for them to finish afterwards. On really big loop
devices and slow backing file system this can lead to OOM situation as
reported by Dave Chinner.

With this patch we will wait in loop_make_request() if the number of
bios in the loop bio list would exceed 'nr_congestion_on'.
We'll wake up the process as we process the bios form the list. Some
threshold hysteresis is in place to avoid high frequency oscillation.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Reported-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 10 ++++++++++
 include/linux/loop.h |  3 +++
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index e9d594fd12cb..800aec7927de 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -463,6 +463,7 @@ out:
  */
 static void loop_add_bio(struct loop_device *lo, struct bio *bio)
 {
+	lo->lo_bio_count++;
 	bio_list_add(&lo->lo_bio_list, bio);
 }
 
@@ -471,6 +472,7 @@ static void loop_add_bio(struct loop_device *lo, struct bio *bio)
  */
 static struct bio *loop_get_bio(struct loop_device *lo)
 {
+	lo->lo_bio_count--;
 	return bio_list_pop(&lo->lo_bio_list);
 }
 
@@ -489,6 +491,10 @@ static void loop_make_request(struct request_queue *q, struct bio *old_bio)
 		goto out;
 	if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
 		goto out;
+	if (lo->lo_bio_count >= q->nr_congestion_on)
+		wait_event_lock_irq(lo->lo_req_wait,
+				    lo->lo_bio_count < q->nr_congestion_off,
+				    lo->lo_lock);
 	loop_add_bio(lo, old_bio);
 	wake_up(&lo->lo_event);
 	spin_unlock_irq(&lo->lo_lock);
@@ -546,6 +552,8 @@ static int loop_thread(void *data)
 			continue;
 		spin_lock_irq(&lo->lo_lock);
 		bio = loop_get_bio(lo);
+		if (lo->lo_bio_count < lo->lo_queue->nr_congestion_off)
+			wake_up(&lo->lo_req_wait);
 		spin_unlock_irq(&lo->lo_lock);
 
 		BUG_ON(!bio);
@@ -873,6 +881,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->transfer = transfer_none;
 	lo->ioctl = NULL;
 	lo->lo_sizelimit = 0;
+	lo->lo_bio_count = 0;
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
@@ -1660,6 +1669,7 @@ static int loop_add(struct loop_device **l, int i)
 	lo->lo_number		= i;
 	lo->lo_thread		= NULL;
 	init_waitqueue_head(&lo->lo_event);
+	init_waitqueue_head(&lo->lo_req_wait);
 	spin_lock_init(&lo->lo_lock);
 	disk->major		= LOOP_MAJOR;
 	disk->first_minor	= i << part_shift;
diff --git a/include/linux/loop.h b/include/linux/loop.h
index 6492181bcb1d..460b60fa7adf 100644
--- a/include/linux/loop.h
+++ b/include/linux/loop.h
@@ -53,10 +53,13 @@ struct loop_device {
 
 	spinlock_t		lo_lock;
 	struct bio_list		lo_bio_list;
+	unsigned int		lo_bio_count;
 	int			lo_state;
 	struct mutex		lo_ctl_mutex;
 	struct task_struct	*lo_thread;
 	wait_queue_head_t	lo_event;
+	/* wait queue for incoming requests */
+	wait_queue_head_t	lo_req_wait;
 
 	struct request_queue	*lo_queue;
 	struct gendisk		*lo_disk;
-- 
cgit v1.2.3-55-g7522


From 12a5105e04143569b3e9e5ef03cf9cad8862473a Mon Sep 17 00:00:00 2001
From: Viresh Kumar
Date: Thu, 29 Nov 2012 00:17:15 +0530
Subject: mfd: stmpe: Get rid of irq_invert_polarity

Since the very first patch, stmpe core driver is using irq_invert_polarity as
part of platform data. But, nobody is actually using it in kernel till now.

Also, this is not something part of hardware specs, but is included to cater
some board mistakes or quirks.

So, better get rid of it. This is earlier discussed here:

https://lkml.org/lkml/2012/11/27/636

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/stmpe.c       | 7 -------
 include/linux/mfd/stmpe.h | 2 --
 2 files changed, 9 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c
index f9f7de796029..90c6151bc52e 100644
--- a/drivers/mfd/stmpe.c
+++ b/drivers/mfd/stmpe.c
@@ -953,13 +953,6 @@ static int __devinit stmpe_chip_init(struct stmpe *stmpe)
 			else
 				icr |= STMPE_ICR_LSB_HIGH;
 		}
-
-		if (stmpe->pdata->irq_invert_polarity) {
-			if (id == STMPE801_ID)
-				icr ^= STMPE801_REG_SYS_CTRL_INT_HI;
-			else
-				icr ^= STMPE_ICR_LSB_HIGH;
-		}
 	}
 
 	if (stmpe->pdata->autosleep) {
diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h
index 15dac790365f..383ac1512a39 100644
--- a/include/linux/mfd/stmpe.h
+++ b/include/linux/mfd/stmpe.h
@@ -190,7 +190,6 @@ struct stmpe_ts_platform_data {
  * @id: device id to distinguish between multiple STMPEs on the same board
  * @blocks: bitmask of blocks to enable (use STMPE_BLOCK_*)
  * @irq_trigger: IRQ trigger to use for the interrupt to the host
- * @irq_invert_polarity: IRQ line is connected with reversed polarity
  * @autosleep: bool to enable/disable stmpe autosleep
  * @autosleep_timeout: inactivity timeout in milliseconds for autosleep
  * @irq_base: base IRQ number.  %STMPE_NR_IRQS irqs will be used, or
@@ -207,7 +206,6 @@ struct stmpe_platform_data {
 	unsigned int blocks;
 	int irq_base;
 	unsigned int irq_trigger;
-	bool irq_invert_polarity;
 	bool autosleep;
 	bool irq_over_gpio;
 	int irq_gpio;
-- 
cgit v1.2.3-55-g7522


From 0e5fca8106199f5c680bb93e75c16381c4c256ce Mon Sep 17 00:00:00 2001
From: Kim, Milo
Date: Thu, 29 Nov 2012 08:48:26 +0000
Subject: mfd: tps65910: Remove unused data

The 'io_mutex' is not used anywhere.
The regmap API supports the mutex internally, so no additional mutex
is required.

And 'domain' private data is unnecessary because the irq domain is
already registered by using regmap_add_irq_chip().

Signed-off-by: Milo(Woogyom) Kim <milo.kim@ti.com>
Acked-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/tps65910.c       | 1 -
 include/linux/mfd/tps65910.h | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index ca3783350ccf..c160c2d76f79 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -486,7 +486,6 @@ static __devinit int tps65910_i2c_probe(struct i2c_client *i2c,
 	tps65910->dev = &i2c->dev;
 	tps65910->i2c_client = i2c;
 	tps65910->id = chip_id;
-	mutex_init(&tps65910->io_mutex);
 
 	tps65910->regmap = devm_regmap_init_i2c(i2c, &tps65910_regmap_config);
 	if (IS_ERR(tps65910->regmap)) {
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index 0b16903f7e88..20e433e551e3 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -893,7 +893,6 @@ struct tps65910 {
 	struct device *dev;
 	struct i2c_client *i2c_client;
 	struct regmap *regmap;
-	struct mutex io_mutex;
 	unsigned int id;
 
 	/* Client devices */
@@ -907,7 +906,6 @@ struct tps65910 {
 	/* IRQ Handling */
 	int chip_irq;
 	struct regmap_irq_chip_data *irq_data;
-	struct irq_domain *domain;
 };
 
 struct tps65910_platform_data {
-- 
cgit v1.2.3-55-g7522


From e29482e8487954c87dc7b4fdbc53574bf1d4cce2 Mon Sep 17 00:00:00 2001
From: Mathias Nyman
Date: Fri, 30 Nov 2012 12:37:36 +0100
Subject: gpio / ACPI: add ACPI support

Add support for translating ACPI GPIO pin numbers to Linux GPIO API pins.
Needs a gpio controller driver with the acpi handler hook set.

Drivers can use acpi_get_gpio() to translate ACPI5 GpioIO and GpioInt
resources to Linux GPIO's.

Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/gpio/Kconfig        |  4 ++++
 drivers/gpio/Makefile       |  1 +
 drivers/gpio/gpiolib-acpi.c | 54 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/acpi_gpio.h   | 19 ++++++++++++++++
 4 files changed, 78 insertions(+)
 create mode 100644 drivers/gpio/gpiolib-acpi.c
 create mode 100644 include/linux/acpi_gpio.h

(limited to 'include')

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index f11d8e3b4041..5c9b384119b8 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -49,6 +49,10 @@ config OF_GPIO
 	def_bool y
 	depends on OF
 
+config GPIO_ACPI
+	def_bool y
+	depends on ACPI
+
 config DEBUG_GPIO
 	bool "Debug GPIO calls"
 	depends on DEBUG_KERNEL
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 9aeed6707326..420dbaca05f1 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -4,6 +4,7 @@ ccflags-$(CONFIG_DEBUG_GPIO)	+= -DDEBUG
 
 obj-$(CONFIG_GPIOLIB)		+= gpiolib.o devres.o
 obj-$(CONFIG_OF_GPIO)		+= gpiolib-of.o
+obj-$(CONFIG_GPIO_ACPI)		+= gpiolib-acpi.o
 
 # Device drivers. Generally keep list sorted alphabetically
 obj-$(CONFIG_GPIO_GENERIC)	+= gpio-generic.o
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
new file mode 100644
index 000000000000..cbad6e908d30
--- /dev/null
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -0,0 +1,54 @@
+/*
+ * ACPI helpers for GPIO API
+ *
+ * Copyright (C) 2012, Intel Corporation
+ * Authors: Mathias Nyman <mathias.nyman@linux.intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/errno.h>
+#include <linux/gpio.h>
+#include <linux/export.h>
+#include <linux/acpi_gpio.h>
+#include <linux/acpi.h>
+
+static int acpi_gpiochip_find(struct gpio_chip *gc, void *data)
+{
+	if (!gc->dev)
+		return false;
+
+	return ACPI_HANDLE(gc->dev) == data;
+}
+
+/**
+ * acpi_get_gpio() - Translate ACPI GPIO pin to GPIO number usable with GPIO API
+ * @path:	ACPI GPIO controller full path name, (e.g. "\\_SB.GPO1")
+ * @pin:	ACPI GPIO pin number (0-based, controller-relative)
+ *
+ * Returns GPIO number to use with Linux generic GPIO API, or errno error value
+ */
+
+int acpi_get_gpio(char *path, int pin)
+{
+	struct gpio_chip *chip;
+	acpi_handle handle;
+	acpi_status status;
+
+	status = acpi_get_handle(NULL, path, &handle);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	chip = gpiochip_find(handle, acpi_gpiochip_find);
+	if (!chip)
+		return -ENODEV;
+
+	if (!gpio_is_valid(chip->base + pin))
+		return -EINVAL;
+
+	return chip->base + pin;
+}
+EXPORT_SYMBOL_GPL(acpi_get_gpio);
diff --git a/include/linux/acpi_gpio.h b/include/linux/acpi_gpio.h
new file mode 100644
index 000000000000..91615a389b65
--- /dev/null
+++ b/include/linux/acpi_gpio.h
@@ -0,0 +1,19 @@
+#ifndef _LINUX_ACPI_GPIO_H_
+#define _LINUX_ACPI_GPIO_H_
+
+#include <linux/errno.h>
+
+#ifdef CONFIG_GPIO_ACPI
+
+int acpi_get_gpio(char *path, int pin);
+
+#else /* CONFIG_GPIO_ACPI */
+
+static inline int acpi_get_gpio(char *path, int pin)
+{
+	return -ENODEV;
+}
+
+#endif /* CONFIG_GPIO_ACPI */
+
+#endif /* _LINUX_ACPI_GPIO_H_ */
-- 
cgit v1.2.3-55-g7522


From b9a9ada14aab17f08c1d9735601f1097cdcfc6de Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Thu, 29 Nov 2012 13:00:10 +0100
Subject: mac80211: remove probe response temporary buffer allocation

Instead of allocating a temporary buffer to build IEs
build them right into the SKB.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c |  7 ++++++-
 drivers/net/wireless/ti/wl1251/main.c |  4 +++-
 drivers/net/wireless/ti/wlcore/cmd.c  |  4 +++-
 include/net/mac80211.h                |  5 ++---
 net/mac80211/tx.c                     |  9 ++-------
 net/mac80211/util.c                   | 26 +++++++++-----------------
 6 files changed, 25 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 2aa8a1aa1184..8a61dbd320e6 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1347,9 +1347,14 @@ static void hw_scan_work(struct work_struct *work)
 						       hwsim->hw_scan_vif,
 						       req->ssids[i].ssid,
 						       req->ssids[i].ssid_len,
-						       req->ie, req->ie_len);
+						       req->ie_len);
 			if (!probe)
 				continue;
+
+			if (req->ie_len)
+				memcpy(skb_put(probe, req->ie_len), req->ie,
+				       req->ie_len);
+
 			local_bh_disable();
 			mac80211_hwsim_tx_frame(hwsim->hw, probe,
 						hwsim->tmp_chan);
diff --git a/drivers/net/wireless/ti/wl1251/main.c b/drivers/net/wireless/ti/wl1251/main.c
index 441cbccbd381..f47e8b0482ad 100644
--- a/drivers/net/wireless/ti/wl1251/main.c
+++ b/drivers/net/wireless/ti/wl1251/main.c
@@ -896,11 +896,13 @@ static int wl1251_op_hw_scan(struct ieee80211_hw *hw,
 		goto out;
 
 	skb = ieee80211_probereq_get(wl->hw, wl->vif, ssid, ssid_len,
-				     req->ie, req->ie_len);
+				     req->ie_len);
 	if (!skb) {
 		ret = -ENOMEM;
 		goto out;
 	}
+	if (req->ie_len)
+		memcpy(skb_put(skb, req->ie_len), req->ie, req->ie_len);
 
 	ret = wl1251_cmd_template_set(wl, CMD_PROBE_REQ, skb->data,
 				      skb->len);
diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index eaef3f41b252..27f83f72a93b 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -1038,11 +1038,13 @@ int wl12xx_cmd_build_probe_req(struct wl1271 *wl, struct wl12xx_vif *wlvif,
 	u16 template_id_5 = CMD_TEMPL_CFG_PROBE_REQ_5;
 
 	skb = ieee80211_probereq_get(wl->hw, vif, ssid, ssid_len,
-				     ie, ie_len);
+				     ie_len);
 	if (!skb) {
 		ret = -ENOMEM;
 		goto out;
 	}
+	if (ie_len)
+		memcpy(skb_put(skb, ie_len), ie, ie_len);
 
 	wl1271_dump(DEBUG_SCAN, "PROBE REQ: ", skb->data, skb->len);
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index e806f1d81f66..0472d806fb41 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3144,8 +3144,7 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
  * @vif: &struct ieee80211_vif pointer from the add_interface callback.
  * @ssid: SSID buffer
  * @ssid_len: length of SSID
- * @ie: buffer containing all IEs except SSID for the template
- * @ie_len: length of the IE buffer
+ * @tailroom: tailroom to reserve at end of SKB for IEs
  *
  * Creates a Probe Request template which can, for example, be uploaded to
  * hardware.
@@ -3153,7 +3152,7 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw,
 struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw,
 				       struct ieee80211_vif *vif,
 				       const u8 *ssid, size_t ssid_len,
-				       const u8 *ie, size_t ie_len);
+				       size_t tailroom);
 
 /**
  * ieee80211_rts_get - RTS frame generation function
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index d8ef3417bf2b..ba1ac9d62b08 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2620,7 +2620,7 @@ EXPORT_SYMBOL(ieee80211_nullfunc_get);
 struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw,
 				       struct ieee80211_vif *vif,
 				       const u8 *ssid, size_t ssid_len,
-				       const u8 *ie, size_t ie_len)
+				       size_t tailroom)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct ieee80211_local *local;
@@ -2634,7 +2634,7 @@ struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw,
 	ie_ssid_len = 2 + ssid_len;
 
 	skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*hdr) +
-			    ie_ssid_len + ie_len);
+			    ie_ssid_len + tailroom);
 	if (!skb)
 		return NULL;
 
@@ -2655,11 +2655,6 @@ struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw,
 		memcpy(pos, ssid, ssid_len);
 	pos += ssid_len;
 
-	if (ie) {
-		pos = skb_put(skb, ie_len);
-		memcpy(pos, ie, ie_len);
-	}
-
 	return skb;
 }
 EXPORT_SYMBOL(ieee80211_probereq_get);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index f119b1b6c1a7..41c9841614b8 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1239,14 +1239,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_local *local = sdata->local;
 	struct sk_buff *skb;
 	struct ieee80211_mgmt *mgmt;
-	size_t buf_len;
-	u8 *buf;
 	u8 chan_no;
-
-	/* FIXME: come up with a proper value */
-	buf = kmalloc(200 + ie_len, GFP_KERNEL);
-	if (!buf)
-		return NULL;
+	int ies_len;
 
 	/*
 	 * Do not send DS Channel parameter for directed probe requests
@@ -1258,15 +1252,16 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	else
 		chan_no = ieee80211_frequency_to_channel(chan->center_freq);
 
-	buf_len = ieee80211_build_preq_ies(local, buf, 200 + ie_len,
-					   ie, ie_len, chan->band,
-					   ratemask, chan_no);
-
 	skb = ieee80211_probereq_get(&local->hw, &sdata->vif,
-				     ssid, ssid_len,
-				     buf, buf_len);
+				     ssid, ssid_len, 100 + ie_len);
 	if (!skb)
-		goto out;
+		return NULL;
+
+	ies_len = ieee80211_build_preq_ies(local, skb_tail_pointer(skb),
+					   skb_tailroom(skb),
+					   ie, ie_len, chan->band,
+					   ratemask, chan_no);
+	skb_put(skb, ies_len);
 
 	if (dst) {
 		mgmt = (struct ieee80211_mgmt *) skb->data;
@@ -1276,9 +1271,6 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 
 	IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;
 
- out:
-	kfree(buf);
-
 	return skb;
 }
 
-- 
cgit v1.2.3-55-g7522


From 9caf03640279e64d0ba36539b42daa1b43a49486 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Thu, 29 Nov 2012 01:25:20 +0100
Subject: cfg80211: fix BSS struct IE access races

When a BSS struct is updated, the IEs are currently
overwritten or freed. This can lead to races if some
other CPU is accessing the BSS struct and using the
IEs concurrently.

Fix this by always allocating the IEs in a new struct
that holds the data and length and protecting access
to this new struct with RCU.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/libertas/cfg.c      |   9 +-
 drivers/net/wireless/mwifiex/sta_ioctl.c |  35 ++-
 include/net/cfg80211.h                   |  41 ++--
 net/mac80211/mlme.c                      |  80 +++---
 net/wireless/core.h                      |   2 -
 net/wireless/nl80211.c                   |  27 +-
 net/wireless/reg.c                       |   2 +-
 net/wireless/reg.h                       |   2 +-
 net/wireless/scan.c                      | 409 +++++++++++++++----------------
 net/wireless/sme.c                       |  13 +-
 net/wireless/util.c                      |   9 +-
 net/wireless/wext-sme.c                  |   8 +-
 12 files changed, 353 insertions(+), 284 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c
index ec36868f6fc5..ec6d5d6b452e 100644
--- a/drivers/net/wireless/libertas/cfg.c
+++ b/drivers/net/wireless/libertas/cfg.c
@@ -298,6 +298,7 @@ static int lbs_add_common_rates_tlv(u8 *tlv, struct cfg80211_bss *bss)
 	const u8 *rates_eid, *ext_rates_eid;
 	int n = 0;
 
+	rcu_read_lock();
 	rates_eid = ieee80211_bss_get_ie(bss, WLAN_EID_SUPP_RATES);
 	ext_rates_eid = ieee80211_bss_get_ie(bss, WLAN_EID_EXT_SUPP_RATES);
 
@@ -325,6 +326,7 @@ static int lbs_add_common_rates_tlv(u8 *tlv, struct cfg80211_bss *bss)
 		*tlv++ = 0x96;
 		n = 4;
 	}
+	rcu_read_unlock();
 
 	rate_tlv->header.len = cpu_to_le16(n);
 	return sizeof(rate_tlv->header) + n;
@@ -1140,11 +1142,13 @@ static int lbs_associate(struct lbs_private *priv,
 	cmd->capability = cpu_to_le16(bss->capability);
 
 	/* add SSID TLV */
+	rcu_read_lock();
 	ssid_eid = ieee80211_bss_get_ie(bss, WLAN_EID_SSID);
 	if (ssid_eid)
 		pos += lbs_add_ssid_tlv(pos, ssid_eid + 2, ssid_eid[1]);
 	else
 		lbs_deb_assoc("no SSID\n");
+	rcu_read_unlock();
 
 	/* add DS param TLV */
 	if (bss->channel)
@@ -1782,7 +1786,7 @@ static int lbs_ibss_join_existing(struct lbs_private *priv,
 	struct cfg80211_ibss_params *params,
 	struct cfg80211_bss *bss)
 {
-	const u8 *rates_eid = ieee80211_bss_get_ie(bss, WLAN_EID_SUPP_RATES);
+	const u8 *rates_eid;
 	struct cmd_ds_802_11_ad_hoc_join cmd;
 	u8 preamble = RADIO_PREAMBLE_SHORT;
 	int ret = 0;
@@ -1841,6 +1845,8 @@ static int lbs_ibss_join_existing(struct lbs_private *priv,
 
 	/* set rates to the intersection of our rates and the rates in the
 	   bss */
+	rcu_read_lock();
+	rates_eid = ieee80211_bss_get_ie(bss, WLAN_EID_SUPP_RATES);
 	if (!rates_eid) {
 		lbs_add_rates(cmd.bss.rates);
 	} else {
@@ -1860,6 +1866,7 @@ static int lbs_ibss_join_existing(struct lbs_private *priv,
 			}
 		}
 	}
+	rcu_read_unlock();
 
 	/* Only v8 and below support setting this */
 	if (MRVL_FW_MAJOR_REV(priv->fwrelease) <= 8) {
diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c
index 24af6ba7d8a1..5d7b83e2dc4d 100644
--- a/drivers/net/wireless/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/mwifiex/sta_ioctl.c
@@ -158,12 +158,22 @@ int mwifiex_fill_new_bss_desc(struct mwifiex_private *priv,
 			      struct cfg80211_bss *bss,
 			      struct mwifiex_bssdescriptor *bss_desc)
 {
-	int ret;
+	int ret, beacon_ie_len;
 	u8 *beacon_ie;
 	struct mwifiex_bss_priv *bss_priv = (void *)bss->priv;
+	const struct cfg80211_bss_ies *ies;
+
+	rcu_read_lock();
+	ies = rcu_dereference(bss->ies);
+	if (WARN_ON(!ies)) {
+		/* should never happen */
+		rcu_read_unlock();
+		return -EINVAL;
+	}
+	beacon_ie = kmemdup(ies->data, ies->len, GFP_ATOMIC);
+	beacon_ie_len = ies->len;
+	rcu_read_unlock();
 
-	beacon_ie = kmemdup(bss->information_elements, bss->len_beacon_ies,
-			    GFP_KERNEL);
 	if (!beacon_ie) {
 		dev_err(priv->adapter->dev, " failed to alloc beacon_ie\n");
 		return -ENOMEM;
@@ -172,7 +182,7 @@ int mwifiex_fill_new_bss_desc(struct mwifiex_private *priv,
 	memcpy(bss_desc->mac_address, bss->bssid, ETH_ALEN);
 	bss_desc->rssi = bss->signal;
 	bss_desc->beacon_buf = beacon_ie;
-	bss_desc->beacon_buf_size = bss->len_beacon_ies;
+	bss_desc->beacon_buf_size = beacon_ie_len;
 	bss_desc->beacon_period = bss->beacon_interval;
 	bss_desc->cap_info_bitmap = bss->capability;
 	bss_desc->bss_band = bss_priv->band;
@@ -198,18 +208,23 @@ int mwifiex_fill_new_bss_desc(struct mwifiex_private *priv,
 static int mwifiex_process_country_ie(struct mwifiex_private *priv,
 				      struct cfg80211_bss *bss)
 {
-	u8 *country_ie, country_ie_len;
+	const u8 *country_ie;
+	u8 country_ie_len;
 	struct mwifiex_802_11d_domain_reg *domain_info =
 					&priv->adapter->domain_reg;
 
-	country_ie = (u8 *)ieee80211_bss_get_ie(bss, WLAN_EID_COUNTRY);
-
-	if (!country_ie)
+	rcu_read_lock();
+	country_ie = ieee80211_bss_get_ie(bss, WLAN_EID_COUNTRY);
+	if (!country_ie) {
+		rcu_read_unlock();
 		return 0;
+	}
 
 	country_ie_len = country_ie[1];
-	if (country_ie_len < IEEE80211_COUNTRY_IE_MIN_LEN)
+	if (country_ie_len < IEEE80211_COUNTRY_IE_MIN_LEN) {
+		rcu_read_unlock();
 		return 0;
+	}
 
 	domain_info->country_code[0] = country_ie[2];
 	domain_info->country_code[1] = country_ie[3];
@@ -223,6 +238,8 @@ static int mwifiex_process_country_ie(struct mwifiex_private *priv,
 	memcpy((u8 *)domain_info->triplet,
 	       &country_ie[2] + IEEE80211_COUNTRY_STRING_LEN, country_ie_len);
 
+	rcu_read_unlock();
+
 	if (mwifiex_send_cmd_async(priv, HostCmd_CMD_802_11D_DOMAIN_INFO,
 				   HostCmd_ACT_GEN_SET, 0, NULL)) {
 		wiphy_err(priv->adapter->wiphy,
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 731b48fa238b..8e6a6b73b9c9 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1205,6 +1205,18 @@ enum cfg80211_signal_type {
 	CFG80211_SIGNAL_TYPE_UNSPEC,
 };
 
+/**
+ * struct cfg80211_bss_ie_data - BSS entry IE data
+ * @rcu_head: internal use, for freeing
+ * @len: length of the IEs
+ * @data: IE data
+ */
+struct cfg80211_bss_ies {
+	struct rcu_head rcu_head;
+	int len;
+	u8 data[];
+};
+
 /**
  * struct cfg80211_bss - BSS description
  *
@@ -1216,36 +1228,34 @@ enum cfg80211_signal_type {
  * @tsf: timestamp of last received update
  * @beacon_interval: the beacon interval as from the frame
  * @capability: the capability field in host byte order
- * @information_elements: the information elements (Note that there
+ * @ies: the information elements (Note that there
  *	is no guarantee that these are well-formed!); this is a pointer to
  *	either the beacon_ies or proberesp_ies depending on whether Probe
  *	Response frame has been received
- * @len_information_elements: total length of the information elements
  * @beacon_ies: the information elements from the last Beacon frame
- * @len_beacon_ies: total length of the beacon_ies
  * @proberesp_ies: the information elements from the last Probe Response frame
- * @len_proberesp_ies: total length of the proberesp_ies
  * @signal: signal strength value (type depends on the wiphy's signal_type)
  * @free_priv: function pointer to free private data
  * @priv: private area for driver use, has at least wiphy->bss_priv_size bytes
  */
 struct cfg80211_bss {
+	u64 tsf;
+
 	struct ieee80211_channel *channel;
 
-	u8 bssid[ETH_ALEN];
-	u64 tsf;
+	const struct cfg80211_bss_ies __rcu *ies;
+	const struct cfg80211_bss_ies __rcu *beacon_ies;
+	const struct cfg80211_bss_ies __rcu *proberesp_ies;
+
+	void (*free_priv)(struct cfg80211_bss *bss);
+
+	s32 signal;
+
 	u16 beacon_interval;
 	u16 capability;
-	u8 *information_elements;
-	size_t len_information_elements;
-	u8 *beacon_ies;
-	size_t len_beacon_ies;
-	u8 *proberesp_ies;
-	size_t len_proberesp_ies;
 
-	s32 signal;
+	u8 bssid[ETH_ALEN];
 
-	void (*free_priv)(struct cfg80211_bss *bss);
 	u8 priv[0] __attribute__((__aligned__(sizeof(void *))));
 };
 
@@ -1253,6 +1263,9 @@ struct cfg80211_bss {
  * ieee80211_bss_get_ie - find IE with given ID
  * @bss: the bss to search
  * @ie: the IE ID
+ *
+ * Note that the return value is an RCU-protected pointer, so
+ * rcu_read_lock() must be held when calling this function.
  * Returns %NULL if not found.
  */
 const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 ie);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 35d8cffc973a..481d5035b397 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1382,19 +1382,26 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata,
 	sdata->u.mgd.flags |= IEEE80211_STA_RESET_SIGNAL_AVE;
 
 	if (sdata->vif.p2p) {
-		u8 noa[2];
-		int ret;
+		const struct cfg80211_bss_ies *ies;
 
-		ret = cfg80211_get_p2p_attr(cbss->information_elements,
-					    cbss->len_information_elements,
-					    IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
-					    noa, sizeof(noa));
-		if (ret >= 2) {
-			bss_conf->p2p_oppps = noa[1] & 0x80;
-			bss_conf->p2p_ctwindow = noa[1] & 0x7f;
-			bss_info_changed |= BSS_CHANGED_P2P_PS;
-			sdata->u.mgd.p2p_noa_index = noa[0];
+		rcu_read_lock();
+		ies = rcu_dereference(cbss->ies);
+		if (ies) {
+			u8 noa[2];
+			int ret;
+
+			ret = cfg80211_get_p2p_attr(
+					ies->data, ies->len,
+					IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
+					noa, sizeof(noa));
+			if (ret >= 2) {
+				bss_conf->p2p_oppps = noa[1] & 0x80;
+				bss_conf->p2p_ctwindow = noa[1] & 0x7f;
+				bss_info_changed |= BSS_CHANGED_P2P_PS;
+				sdata->u.mgd.p2p_noa_index = noa[0];
+			}
 		}
+		rcu_read_unlock();
 	}
 
 	/* just to be sure */
@@ -1659,6 +1666,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
 	} else {
 		int ssid_len;
 
+		rcu_read_lock();
 		ssid = ieee80211_bss_get_ie(ifmgd->associated, WLAN_EID_SSID);
 		if (WARN_ON_ONCE(ssid == NULL))
 			ssid_len = 0;
@@ -1668,6 +1676,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
 		ieee80211_send_probe_req(sdata, dst, ssid + 2, ssid_len, NULL,
 					 0, (u32) -1, true, false,
 					 ifmgd->associated->channel, false);
+		rcu_read_unlock();
 	}
 
 	ifmgd->probe_timeout = jiffies + msecs_to_jiffies(probe_wait_ms);
@@ -1763,6 +1772,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
 	else
 		return NULL;
 
+	rcu_read_lock();
 	ssid = ieee80211_bss_get_ie(cbss, WLAN_EID_SSID);
 	if (WARN_ON_ONCE(ssid == NULL))
 		ssid_len = 0;
@@ -1773,6 +1783,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
 					(u32) -1, cbss->channel,
 					ssid + 2, ssid_len,
 					NULL, 0, true);
+	rcu_read_unlock();
 
 	return skb;
 }
@@ -2858,9 +2869,12 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata)
 			   auth_data->bss->bssid, auth_data->tries,
 			   IEEE80211_AUTH_MAX_TRIES);
 
+		rcu_read_lock();
 		ssidie = ieee80211_bss_get_ie(auth_data->bss, WLAN_EID_SSID);
-		if (!ssidie)
+		if (!ssidie) {
+			rcu_read_unlock();
 			return -EINVAL;
+		}
 		/*
 		 * Direct probe is sent to broadcast address as some APs
 		 * will not answer to direct packet in unassociated state.
@@ -2868,6 +2882,7 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata)
 		ieee80211_send_probe_req(sdata, NULL, ssidie + 2, ssidie[1],
 					 NULL, 0, (u32) -1, true, false,
 					 auth_data->bss->channel, false);
+		rcu_read_unlock();
 	}
 
 	auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT;
@@ -3404,9 +3419,7 @@ static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata,
 	if (ifmgd->flags & IEEE80211_STA_DISABLE_HT)
 		return chains;
 
-	ht_cap_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY,
-				     cbss->information_elements,
-				     cbss->len_information_elements);
+	ht_cap_ie = ieee80211_bss_get_ie(cbss, WLAN_EID_HT_CAPABILITY);
 	if (ht_cap_ie && ht_cap_ie[1] >= sizeof(*ht_cap)) {
 		ht_cap = (void *)(ht_cap_ie + 2);
 		chains = ieee80211_mcs_to_chains(&ht_cap->mcs);
@@ -3419,9 +3432,7 @@ static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata,
 	if (ifmgd->flags & IEEE80211_STA_DISABLE_VHT)
 		return chains;
 
-	vht_cap_ie = cfg80211_find_ie(WLAN_EID_VHT_CAPABILITY,
-				      cbss->information_elements,
-				      cbss->len_information_elements);
+	vht_cap_ie = ieee80211_bss_get_ie(cbss, WLAN_EID_VHT_CAPABILITY);
 	if (vht_cap_ie && vht_cap_ie[1] >= sizeof(*vht_cap)) {
 		u8 nss;
 		u16 tx_mcs_map;
@@ -3457,13 +3468,13 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 			  IEEE80211_STA_DISABLE_80P80MHZ |
 			  IEEE80211_STA_DISABLE_160MHZ);
 
+	rcu_read_lock();
+
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT) &&
 	    sband->ht_cap.ht_supported) {
 		const u8 *ht_oper_ie;
 
-		ht_oper_ie = cfg80211_find_ie(WLAN_EID_HT_OPERATION,
-					      cbss->information_elements,
-					      cbss->len_information_elements);
+		ht_oper_ie = ieee80211_bss_get_ie(cbss, WLAN_EID_HT_OPERATION);
 		if (ht_oper_ie && ht_oper_ie[1] >= sizeof(*ht_oper))
 			ht_oper = (void *)(ht_oper_ie + 2);
 	}
@@ -3472,9 +3483,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	    sband->vht_cap.vht_supported) {
 		const u8 *vht_oper_ie;
 
-		vht_oper_ie = cfg80211_find_ie(WLAN_EID_VHT_OPERATION,
-					       cbss->information_elements,
-					       cbss->len_information_elements);
+		vht_oper_ie = ieee80211_bss_get_ie(cbss,
+						   WLAN_EID_VHT_OPERATION);
 		if (vht_oper_ie && vht_oper_ie[1] >= sizeof(*vht_oper))
 			vht_oper = (void *)(vht_oper_ie + 2);
 		if (vht_oper && !ht_oper) {
@@ -3494,6 +3504,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
 				      local->rx_chains);
 
+	rcu_read_unlock();
+
 	/* will change later if needed */
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 
@@ -3734,14 +3746,21 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	const u8 *ssidie, *ht_ie;
 	int i, err;
 
-	ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID);
-	if (!ssidie)
-		return -EINVAL;
-
 	assoc_data = kzalloc(sizeof(*assoc_data) + req->ie_len, GFP_KERNEL);
 	if (!assoc_data)
 		return -ENOMEM;
 
+	rcu_read_lock();
+	ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID);
+	if (!ssidie) {
+		rcu_read_unlock();
+		kfree(assoc_data);
+		return -EINVAL;
+	}
+	memcpy(assoc_data->ssid, ssidie + 2, ssidie[1]);
+	assoc_data->ssid_len = ssidie[1];
+	rcu_read_unlock();
+
 	mutex_lock(&ifmgd->mtx);
 
 	if (ifmgd->associated)
@@ -3836,12 +3855,14 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	assoc_data->supp_rates = bss->supp_rates;
 	assoc_data->supp_rates_len = bss->supp_rates_len;
 
+	rcu_read_lock();
 	ht_ie = ieee80211_bss_get_ie(req->bss, WLAN_EID_HT_OPERATION);
 	if (ht_ie && ht_ie[1] >= sizeof(struct ieee80211_ht_operation))
 		assoc_data->ap_ht_param =
 			((struct ieee80211_ht_operation *)(ht_ie + 2))->ht_param;
 	else
 		ifmgd->flags |= IEEE80211_STA_DISABLE_HT;
+	rcu_read_unlock();
 
 	if (bss->wmm_used && bss->uapsd_supported &&
 	    (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) {
@@ -3852,9 +3873,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 		ifmgd->flags &= ~IEEE80211_STA_UAPSD_ENABLED;
 	}
 
-	memcpy(assoc_data->ssid, ssidie + 2, ssidie[1]);
-	assoc_data->ssid_len = ssidie[1];
-
 	if (req->prev_bssid)
 		memcpy(assoc_data->prev_bssid, req->prev_bssid, ETH_ALEN);
 
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 6183a0d25b8b..3563097169cb 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -138,8 +138,6 @@ struct cfg80211_internal_bss {
 	unsigned long ts;
 	struct kref ref;
 	atomic_t hold;
-	bool beacon_ies_allocated;
-	bool proberesp_ies_allocated;
 
 	/* must be last because of priv member */
 	struct cfg80211_bss pub;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 4a719770eaaf..f45706adaf34 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4808,6 +4808,7 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 			    struct cfg80211_internal_bss *intbss)
 {
 	struct cfg80211_bss *res = &intbss->pub;
+	const struct cfg80211_bss_ies *ies;
 	void *hdr;
 	struct nlattr *bss;
 
@@ -4828,16 +4829,24 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 	if (!bss)
 		goto nla_put_failure;
 	if ((!is_zero_ether_addr(res->bssid) &&
-	     nla_put(msg, NL80211_BSS_BSSID, ETH_ALEN, res->bssid)) ||
-	    (res->information_elements && res->len_information_elements &&
-	     nla_put(msg, NL80211_BSS_INFORMATION_ELEMENTS,
-		     res->len_information_elements,
-		     res->information_elements)) ||
-	    (res->beacon_ies && res->len_beacon_ies &&
-	     res->beacon_ies != res->information_elements &&
-	     nla_put(msg, NL80211_BSS_BEACON_IES,
-		     res->len_beacon_ies, res->beacon_ies)))
+	     nla_put(msg, NL80211_BSS_BSSID, ETH_ALEN, res->bssid)))
 		goto nla_put_failure;
+
+	rcu_read_lock();
+	ies = rcu_dereference(res->ies);
+	if (ies && ies->len && nla_put(msg, NL80211_BSS_INFORMATION_ELEMENTS,
+				       ies->len, ies->data)) {
+		rcu_read_unlock();
+		goto nla_put_failure;
+	}
+	ies = rcu_dereference(res->beacon_ies);
+	if (ies && ies->len && nla_put(msg, NL80211_BSS_BEACON_IES,
+				       ies->len, ies->data)) {
+		rcu_read_unlock();
+		goto nla_put_failure;
+	}
+	rcu_read_unlock();
+
 	if (res->tsf &&
 	    nla_put_u64(msg, NL80211_BSS_TSF, res->tsf))
 		goto nla_put_failure;
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index bcc7d7ee5a51..b6c7ea6d98f8 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1797,7 +1797,7 @@ EXPORT_SYMBOL(regulatory_hint);
  */
 void regulatory_hint_11d(struct wiphy *wiphy,
 			 enum ieee80211_band band,
-			 u8 *country_ie,
+			 const u8 *country_ie,
 			 u8 country_ie_len)
 {
 	char alpha2[2];
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index f023c8a31c60..4c0a32ffd530 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -81,7 +81,7 @@ int regulatory_hint_found_beacon(struct wiphy *wiphy,
  */
 void regulatory_hint_11d(struct wiphy *wiphy,
 			 enum ieee80211_band band,
-			 u8 *country_ie,
+			 const u8 *country_ie,
 			 u8 country_ie_len);
 
 /**
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 834e0d153fbe..01592d7d4789 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -23,6 +23,7 @@
 
 static void bss_release(struct kref *ref)
 {
+	struct cfg80211_bss_ies *ies;
 	struct cfg80211_internal_bss *bss;
 
 	bss = container_of(ref, struct cfg80211_internal_bss, ref);
@@ -33,10 +34,12 @@ static void bss_release(struct kref *ref)
 	if (bss->pub.free_priv)
 		bss->pub.free_priv(&bss->pub);
 
-	if (bss->beacon_ies_allocated)
-		kfree(bss->pub.beacon_ies);
-	if (bss->proberesp_ies_allocated)
-		kfree(bss->pub.proberesp_ies);
+	ies = (void *)rcu_access_pointer(bss->pub.beacon_ies);
+	if (ies)
+		kfree_rcu(ies, rcu_head);
+	ies = (void *)rcu_access_pointer(bss->pub.proberesp_ies);
+	if (ies)
+		kfree_rcu(ies, rcu_head);
 
 	kfree(bss);
 }
@@ -288,7 +291,7 @@ const u8 *cfg80211_find_vendor_ie(unsigned int oui, u8 oui_type,
 }
 EXPORT_SYMBOL(cfg80211_find_vendor_ie);
 
-static int cmp_ies(u8 num, u8 *ies1, size_t len1, u8 *ies2, size_t len2)
+static int cmp_ies(u8 num, const u8 *ies1, int len1, const u8 *ies2, int len2)
 {
 	const u8 *ie1 = cfg80211_find_ie(num, ies1, len1);
 	const u8 *ie2 = cfg80211_find_ie(num, ies2, len2);
@@ -311,6 +314,7 @@ static int cmp_ies(u8 num, u8 *ies1, size_t len1, u8 *ies2, size_t len2)
 static bool is_bss(struct cfg80211_bss *a, const u8 *bssid,
 		   const u8 *ssid, size_t ssid_len)
 {
+	const struct cfg80211_bss_ies *ies;
 	const u8 *ssidie;
 
 	if (bssid && !ether_addr_equal(a->bssid, bssid))
@@ -319,9 +323,10 @@ static bool is_bss(struct cfg80211_bss *a, const u8 *bssid,
 	if (!ssid)
 		return true;
 
-	ssidie = cfg80211_find_ie(WLAN_EID_SSID,
-				  a->information_elements,
-				  a->len_information_elements);
+	ies = rcu_access_pointer(a->ies);
+	if (!ies)
+		return false;
+	ssidie = cfg80211_find_ie(WLAN_EID_SSID, ies->data, ies->len);
 	if (!ssidie)
 		return false;
 	if (ssidie[1] != ssid_len)
@@ -331,20 +336,21 @@ static bool is_bss(struct cfg80211_bss *a, const u8 *bssid,
 
 static bool is_mesh_bss(struct cfg80211_bss *a)
 {
+	const struct cfg80211_bss_ies *ies;
 	const u8 *ie;
 
 	if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability))
 		return false;
 
-	ie = cfg80211_find_ie(WLAN_EID_MESH_ID,
-			      a->information_elements,
-			      a->len_information_elements);
+	ies = rcu_access_pointer(a->ies);
+	if (!ies)
+		return false;
+
+	ie = cfg80211_find_ie(WLAN_EID_MESH_ID, ies->data, ies->len);
 	if (!ie)
 		return false;
 
-	ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG,
-			      a->information_elements,
-			      a->len_information_elements);
+	ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG, ies->data, ies->len);
 	if (!ie)
 		return false;
 
@@ -355,14 +361,17 @@ static bool is_mesh(struct cfg80211_bss *a,
 		    const u8 *meshid, size_t meshidlen,
 		    const u8 *meshcfg)
 {
+	const struct cfg80211_bss_ies *ies;
 	const u8 *ie;
 
 	if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability))
 		return false;
 
-	ie = cfg80211_find_ie(WLAN_EID_MESH_ID,
-			      a->information_elements,
-			      a->len_information_elements);
+	ies = rcu_access_pointer(a->ies);
+	if (!ies)
+		return false;
+
+	ie = cfg80211_find_ie(WLAN_EID_MESH_ID, ies->data, ies->len);
 	if (!ie)
 		return false;
 	if (ie[1] != meshidlen)
@@ -370,9 +379,7 @@ static bool is_mesh(struct cfg80211_bss *a,
 	if (memcmp(ie + 2, meshid, meshidlen))
 		return false;
 
-	ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG,
-			      a->information_elements,
-			      a->len_information_elements);
+	ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG, ies->data, ies->len);
 	if (!ie)
 		return false;
 	if (ie[1] != sizeof(struct ieee80211_meshconf_ie))
@@ -389,24 +396,28 @@ static bool is_mesh(struct cfg80211_bss *a,
 
 static int cmp_bss_core(struct cfg80211_bss *a, struct cfg80211_bss *b)
 {
+	const struct cfg80211_bss_ies *a_ies, *b_ies;
 	int r;
 
 	if (a->channel != b->channel)
 		return b->channel->center_freq - a->channel->center_freq;
 
 	if (is_mesh_bss(a) && is_mesh_bss(b)) {
+		a_ies = rcu_access_pointer(a->ies);
+		if (!a_ies)
+			return -1;
+		b_ies = rcu_access_pointer(b->ies);
+		if (!b_ies)
+			return 1;
+
 		r = cmp_ies(WLAN_EID_MESH_ID,
-			    a->information_elements,
-			    a->len_information_elements,
-			    b->information_elements,
-			    b->len_information_elements);
+			    a_ies->data, a_ies->len,
+			    b_ies->data, b_ies->len);
 		if (r)
 			return r;
 		return cmp_ies(WLAN_EID_MESH_CONFIG,
-			       a->information_elements,
-			       a->len_information_elements,
-			       b->information_elements,
-			       b->len_information_elements);
+			       a_ies->data, a_ies->len,
+			       b_ies->data, b_ies->len);
 	}
 
 	/*
@@ -419,21 +430,28 @@ static int cmp_bss_core(struct cfg80211_bss *a, struct cfg80211_bss *b)
 static int cmp_bss(struct cfg80211_bss *a,
 		   struct cfg80211_bss *b)
 {
+	const struct cfg80211_bss_ies *a_ies, *b_ies;
 	int r;
 
 	r = cmp_bss_core(a, b);
 	if (r)
 		return r;
 
+	a_ies = rcu_access_pointer(a->ies);
+	if (!a_ies)
+		return -1;
+	b_ies = rcu_access_pointer(b->ies);
+	if (!b_ies)
+		return 1;
+
 	return cmp_ies(WLAN_EID_SSID,
-		       a->information_elements,
-		       a->len_information_elements,
-		       b->information_elements,
-		       b->len_information_elements);
+		       a_ies->data, a_ies->len,
+		       b_ies->data, b_ies->len);
 }
 
 static int cmp_hidden_bss(struct cfg80211_bss *a, struct cfg80211_bss *b)
 {
+	const struct cfg80211_bss_ies *a_ies, *b_ies;
 	const u8 *ie1;
 	const u8 *ie2;
 	int i;
@@ -443,12 +461,15 @@ static int cmp_hidden_bss(struct cfg80211_bss *a, struct cfg80211_bss *b)
 	if (r)
 		return r;
 
-	ie1 = cfg80211_find_ie(WLAN_EID_SSID,
-			       a->information_elements,
-			       a->len_information_elements);
-	ie2 = cfg80211_find_ie(WLAN_EID_SSID,
-			       b->information_elements,
-			       b->len_information_elements);
+	a_ies = rcu_access_pointer(a->ies);
+	if (!a_ies)
+		return -1;
+	b_ies = rcu_access_pointer(b->ies);
+	if (!b_ies)
+		return 1;
+
+	ie1 = cfg80211_find_ie(WLAN_EID_SSID, a_ies->data, a_ies->len);
+	ie2 = cfg80211_find_ie(WLAN_EID_SSID, b_ies->data, b_ies->len);
 
 	/*
 	 * Key comparator must use same algorithm in any rb-tree
@@ -633,126 +654,84 @@ static void
 copy_hidden_ies(struct cfg80211_internal_bss *res,
 		struct cfg80211_internal_bss *hidden)
 {
-	if (unlikely(res->pub.beacon_ies))
-		return;
-	if (WARN_ON(!hidden->pub.beacon_ies))
+	const struct cfg80211_bss_ies *ies;
+
+	if (rcu_access_pointer(res->pub.beacon_ies))
 		return;
 
-	res->pub.beacon_ies = kmalloc(hidden->pub.len_beacon_ies, GFP_ATOMIC);
-	if (unlikely(!res->pub.beacon_ies))
+	ies = rcu_access_pointer(hidden->pub.beacon_ies);
+	if (WARN_ON(!ies))
 		return;
 
-	res->beacon_ies_allocated = true;
-	res->pub.len_beacon_ies = hidden->pub.len_beacon_ies;
-	memcpy(res->pub.beacon_ies, hidden->pub.beacon_ies,
-	       res->pub.len_beacon_ies);
+	ies = kmemdup(ies, sizeof(*ies) + ies->len, GFP_ATOMIC);
+	if (unlikely(!ies))
+		return;
+	rcu_assign_pointer(res->pub.beacon_ies, ies);
 }
 
 static struct cfg80211_internal_bss *
 cfg80211_bss_update(struct cfg80211_registered_device *dev,
-		    struct cfg80211_internal_bss *res)
+		    struct cfg80211_internal_bss *tmp)
 {
 	struct cfg80211_internal_bss *found = NULL;
 
-	/*
-	 * The reference to "res" is donated to this function.
-	 */
-
-	if (WARN_ON(!res->pub.channel)) {
-		kref_put(&res->ref, bss_release);
+	if (WARN_ON(!tmp->pub.channel))
 		return NULL;
-	}
 
-	res->ts = jiffies;
+	tmp->ts = jiffies;
 
 	spin_lock_bh(&dev->bss_lock);
 
-	found = rb_find_bss(dev, res);
+	if (WARN_ON(!rcu_access_pointer(tmp->pub.ies))) {
+		spin_unlock_bh(&dev->bss_lock);
+		return NULL;
+	}
+
+	found = rb_find_bss(dev, tmp);
 
 	if (found) {
-		found->pub.beacon_interval = res->pub.beacon_interval;
-		found->pub.tsf = res->pub.tsf;
-		found->pub.signal = res->pub.signal;
-		found->pub.capability = res->pub.capability;
-		found->ts = res->ts;
+		found->pub.beacon_interval = tmp->pub.beacon_interval;
+		found->pub.tsf = tmp->pub.tsf;
+		found->pub.signal = tmp->pub.signal;
+		found->pub.capability = tmp->pub.capability;
+		found->ts = tmp->ts;
 
 		/* Update IEs */
-		if (res->pub.proberesp_ies) {
-			size_t used = dev->wiphy.bss_priv_size + sizeof(*res);
-			size_t ielen = res->pub.len_proberesp_ies;
-
-			if (found->pub.proberesp_ies &&
-			    !found->proberesp_ies_allocated &&
-			    ksize(found) >= used + ielen) {
-				memcpy(found->pub.proberesp_ies,
-				       res->pub.proberesp_ies, ielen);
-				found->pub.len_proberesp_ies = ielen;
-			} else {
-				u8 *ies = found->pub.proberesp_ies;
-
-				if (found->proberesp_ies_allocated)
-					ies = krealloc(ies, ielen, GFP_ATOMIC);
-				else
-					ies = kmalloc(ielen, GFP_ATOMIC);
-
-				if (ies) {
-					memcpy(ies, res->pub.proberesp_ies,
-					       ielen);
-					found->proberesp_ies_allocated = true;
-					found->pub.proberesp_ies = ies;
-					found->pub.len_proberesp_ies = ielen;
-				}
-			}
+		if (rcu_access_pointer(tmp->pub.proberesp_ies)) {
+			const struct cfg80211_bss_ies *old;
+
+			old = rcu_access_pointer(found->pub.proberesp_ies);
 
+			rcu_assign_pointer(found->pub.proberesp_ies,
+					   tmp->pub.proberesp_ies);
 			/* Override possible earlier Beacon frame IEs */
-			found->pub.information_elements =
-				found->pub.proberesp_ies;
-			found->pub.len_information_elements =
-				found->pub.len_proberesp_ies;
-		}
+			rcu_assign_pointer(found->pub.ies,
+					   tmp->pub.proberesp_ies);
+			if (old)
+				kfree_rcu((struct cfg80211_bss_ies *)old,
+					  rcu_head);
+		} else if (rcu_access_pointer(tmp->pub.beacon_ies)) {
+			const struct cfg80211_bss_ies *old, *ies;
 
-		if (res->pub.beacon_ies) {
-			size_t used = dev->wiphy.bss_priv_size + sizeof(*res);
-			size_t ielen = res->pub.len_beacon_ies;
-			bool information_elements_is_beacon_ies =
-				(found->pub.information_elements ==
-				 found->pub.beacon_ies);
-
-			if (found->pub.beacon_ies &&
-			    !found->beacon_ies_allocated &&
-			    ksize(found) >= used + ielen) {
-				memcpy(found->pub.beacon_ies,
-				       res->pub.beacon_ies, ielen);
-				found->pub.len_beacon_ies = ielen;
-			} else {
-				u8 *ies = found->pub.beacon_ies;
-
-				if (found->beacon_ies_allocated)
-					ies = krealloc(ies, ielen, GFP_ATOMIC);
-				else
-					ies = kmalloc(ielen, GFP_ATOMIC);
-
-				if (ies) {
-					memcpy(ies, res->pub.beacon_ies,
-					       ielen);
-					found->beacon_ies_allocated = true;
-					found->pub.beacon_ies = ies;
-					found->pub.len_beacon_ies = ielen;
-				}
-			}
+			old = rcu_access_pointer(found->pub.beacon_ies);
+			ies = rcu_access_pointer(found->pub.ies);
+
+			rcu_assign_pointer(found->pub.beacon_ies,
+					   tmp->pub.beacon_ies);
 
 			/* Override IEs if they were from a beacon before */
-			if (information_elements_is_beacon_ies) {
-				found->pub.information_elements =
-					found->pub.beacon_ies;
-				found->pub.len_information_elements =
-					found->pub.len_beacon_ies;
-			}
-		}
+			if (old == ies)
+				rcu_assign_pointer(found->pub.ies,
+						   tmp->pub.beacon_ies);
 
-		kref_put(&res->ref, bss_release);
+			if (old)
+				kfree_rcu((struct cfg80211_bss_ies *)old,
+					  rcu_head);
+		}
 	} else {
+		struct cfg80211_internal_bss *new;
 		struct cfg80211_internal_bss *hidden;
+		struct cfg80211_bss_ies *ies;
 
 		/* First check if the beacon is a probe response from
 		 * a hidden bss. If so, copy beacon ies (with nullified
@@ -763,14 +742,32 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 		/* TODO: The code is not trying to update existing probe
 		 * response bss entries when beacon ies are
 		 * getting changed. */
-		hidden = rb_find_hidden_bss(dev, res);
+		hidden = rb_find_hidden_bss(dev, tmp);
 		if (hidden)
-			copy_hidden_ies(res, hidden);
-
-		/* this "consumes" the reference */
-		list_add_tail(&res->list, &dev->bss_list);
-		rb_insert_bss(dev, res);
-		found = res;
+			copy_hidden_ies(tmp, hidden);
+
+		/*
+		 * create a copy -- the "res" variable that is passed in
+		 * is allocated on the stack since it's not needed in the
+		 * more common case of an update
+		 */
+		new = kzalloc(sizeof(*new) + dev->wiphy.bss_priv_size,
+			      GFP_ATOMIC);
+		if (!new) {
+			ies = (void *)rcu_dereference(tmp->pub.beacon_ies);
+			if (ies)
+				kfree_rcu(ies, rcu_head);
+			ies = (void *)rcu_dereference(tmp->pub.proberesp_ies);
+			if (ies)
+				kfree_rcu(ies, rcu_head);
+			spin_unlock_bh(&dev->bss_lock);
+			return NULL;
+		}
+		memcpy(new, tmp, sizeof(*new));
+		kref_init(&new->ref);
+		list_add_tail(&new->list, &dev->bss_list);
+		rb_insert_bss(dev, new);
+		found = new;
 	}
 
 	dev->bss_generation++;
@@ -819,14 +816,12 @@ cfg80211_inform_bss(struct wiphy *wiphy,
 		    u16 beacon_interval, const u8 *ie, size_t ielen,
 		    s32 signal, gfp_t gfp)
 {
-	struct cfg80211_internal_bss *res;
-	size_t privsz;
+	struct cfg80211_bss_ies *ies;
+	struct cfg80211_internal_bss tmp = {}, *res;
 
 	if (WARN_ON(!wiphy))
 		return NULL;
 
-	privsz = wiphy->bss_priv_size;
-
 	if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC &&
 			(signal < 0 || signal > 100)))
 		return NULL;
@@ -835,36 +830,33 @@ cfg80211_inform_bss(struct wiphy *wiphy,
 	if (!channel)
 		return NULL;
 
-	res = kzalloc(sizeof(*res) + privsz + ielen, gfp);
-	if (!res)
-		return NULL;
-
-	memcpy(res->pub.bssid, bssid, ETH_ALEN);
-	res->pub.channel = channel;
-	res->pub.signal = signal;
-	res->pub.tsf = tsf;
-	res->pub.beacon_interval = beacon_interval;
-	res->pub.capability = capability;
+	memcpy(tmp.pub.bssid, bssid, ETH_ALEN);
+	tmp.pub.channel = channel;
+	tmp.pub.signal = signal;
+	tmp.pub.tsf = tsf;
+	tmp.pub.beacon_interval = beacon_interval;
+	tmp.pub.capability = capability;
 	/*
 	 * Since we do not know here whether the IEs are from a Beacon or Probe
 	 * Response frame, we need to pick one of the options and only use it
 	 * with the driver that does not provide the full Beacon/Probe Response
 	 * frame. Use Beacon frame pointer to avoid indicating that this should
-	 * override the information_elements pointer should we have received an
-	 * earlier indication of Probe Response data.
+	 * override the iies pointer should we have received an earlier
+	 * indication of Probe Response data.
 	 *
 	 * The initial buffer for the IEs is allocated with the BSS entry and
 	 * is located after the private area.
 	 */
-	res->pub.beacon_ies = (u8 *)res + sizeof(*res) + privsz;
-	memcpy(res->pub.beacon_ies, ie, ielen);
-	res->pub.len_beacon_ies = ielen;
-	res->pub.information_elements = res->pub.beacon_ies;
-	res->pub.len_information_elements = res->pub.len_beacon_ies;
+	ies = kmalloc(sizeof(*ies) + ielen, gfp);
+	if (!ies)
+		return NULL;
+	ies->len = ielen;
+	memcpy(ies->data, ie, ielen);
 
-	kref_init(&res->ref);
+	rcu_assign_pointer(tmp.pub.beacon_ies, ies);
+	rcu_assign_pointer(tmp.pub.ies, ies);
 
-	res = cfg80211_bss_update(wiphy_to_dev(wiphy), res);
+	res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp);
 	if (!res)
 		return NULL;
 
@@ -883,10 +875,10 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy,
 			  struct ieee80211_mgmt *mgmt, size_t len,
 			  s32 signal, gfp_t gfp)
 {
-	struct cfg80211_internal_bss *res;
+	struct cfg80211_internal_bss tmp = {}, *res;
+	struct cfg80211_bss_ies *ies;
 	size_t ielen = len - offsetof(struct ieee80211_mgmt,
 				      u.probe_resp.variable);
-	size_t privsz;
 
 	BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) !=
 			offsetof(struct ieee80211_mgmt, u.beacon.variable));
@@ -906,45 +898,31 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy,
 	if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable)))
 		return NULL;
 
-	privsz = wiphy->bss_priv_size;
-
 	channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable,
 					   ielen, channel);
 	if (!channel)
 		return NULL;
 
-	res = kzalloc(sizeof(*res) + privsz + ielen, gfp);
-	if (!res)
+	ies = kmalloc(sizeof(*ies) + ielen, gfp);
+	if (!ies)
 		return NULL;
+	ies->len = ielen;
+	memcpy(ies->data, mgmt->u.probe_resp.variable, ielen);
 
-	memcpy(res->pub.bssid, mgmt->bssid, ETH_ALEN);
-	res->pub.channel = channel;
-	res->pub.signal = signal;
-	res->pub.tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp);
-	res->pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
-	res->pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
-	/*
-	 * The initial buffer for the IEs is allocated with the BSS entry and
-	 * is located after the private area.
-	 */
-	if (ieee80211_is_probe_resp(mgmt->frame_control)) {
-		res->pub.proberesp_ies = (u8 *) res + sizeof(*res) + privsz;
-		memcpy(res->pub.proberesp_ies, mgmt->u.probe_resp.variable,
-		       ielen);
-		res->pub.len_proberesp_ies = ielen;
-		res->pub.information_elements = res->pub.proberesp_ies;
-		res->pub.len_information_elements = res->pub.len_proberesp_ies;
-	} else {
-		res->pub.beacon_ies = (u8 *) res + sizeof(*res) + privsz;
-		memcpy(res->pub.beacon_ies, mgmt->u.beacon.variable, ielen);
-		res->pub.len_beacon_ies = ielen;
-		res->pub.information_elements = res->pub.beacon_ies;
-		res->pub.len_information_elements = res->pub.len_beacon_ies;
-	}
-
-	kref_init(&res->ref);
-
-	res = cfg80211_bss_update(wiphy_to_dev(wiphy), res);
+	if (ieee80211_is_probe_resp(mgmt->frame_control))
+		rcu_assign_pointer(tmp.pub.proberesp_ies, ies);
+	else
+		rcu_assign_pointer(tmp.pub.beacon_ies, ies);
+	rcu_assign_pointer(tmp.pub.ies, ies);
+	
+	memcpy(tmp.pub.bssid, mgmt->bssid, ETH_ALEN);
+	tmp.pub.channel = channel;
+	tmp.pub.signal = signal;
+	tmp.pub.tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp);
+	tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
+	tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
+
+	res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp);
 	if (!res)
 		return NULL;
 
@@ -1136,22 +1114,21 @@ int cfg80211_wext_siwscan(struct net_device *dev,
 EXPORT_SYMBOL_GPL(cfg80211_wext_siwscan);
 
 static void ieee80211_scan_add_ies(struct iw_request_info *info,
-				   struct cfg80211_bss *bss,
+				   const struct cfg80211_bss_ies *ies,
 				   char **current_ev, char *end_buf)
 {
-	u8 *pos, *end, *next;
+	const u8 *pos, *end, *next;
 	struct iw_event iwe;
 
-	if (!bss->information_elements ||
-	    !bss->len_information_elements)
+	if (!ies)
 		return;
 
 	/*
 	 * If needed, fragment the IEs buffer (at IE boundaries) into short
 	 * enough fragments to fit into IW_GENERIC_IE_MAX octet messages.
 	 */
-	pos = bss->information_elements;
-	end = pos + bss->len_information_elements;
+	pos = ies->data;
+	end = pos + ies->len;
 
 	while (end - pos > IW_GENERIC_IE_MAX) {
 		next = pos + 2 + pos[1];
@@ -1162,7 +1139,8 @@ static void ieee80211_scan_add_ies(struct iw_request_info *info,
 		iwe.cmd = IWEVGENIE;
 		iwe.u.data.length = next - pos;
 		*current_ev = iwe_stream_add_point(info, *current_ev,
-						   end_buf, &iwe, pos);
+						   end_buf, &iwe,
+						   (void *)pos);
 
 		pos = next;
 	}
@@ -1172,7 +1150,8 @@ static void ieee80211_scan_add_ies(struct iw_request_info *info,
 		iwe.cmd = IWEVGENIE;
 		iwe.u.data.length = end - pos;
 		*current_ev = iwe_stream_add_point(info, *current_ev,
-						   end_buf, &iwe, pos);
+						   end_buf, &iwe,
+						   (void *)pos);
 	}
 }
 
@@ -1191,10 +1170,11 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 	      struct cfg80211_internal_bss *bss, char *current_ev,
 	      char *end_buf)
 {
+	const struct cfg80211_bss_ies *ies;
 	struct iw_event iwe;
+	const u8 *ie;
 	u8 *buf, *cfg, *p;
-	u8 *ie = bss->pub.information_elements;
-	int rem = bss->pub.len_information_elements, i, sig;
+	int rem, i, sig;
 	bool ismesh = false;
 
 	memset(&iwe, 0, sizeof(iwe));
@@ -1259,7 +1239,17 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 	current_ev = iwe_stream_add_point(info, current_ev, end_buf,
 					  &iwe, "");
 
-	while (rem >= 2) {
+	rcu_read_lock();
+	ies = rcu_dereference(bss->pub.ies);
+	if (ies) {
+		rem = ies->len;
+		ie = ies->data;
+	} else {
+		rem = 0;
+		ie = NULL;
+	}
+
+	while (ies && rem >= 2) {
 		/* invalid data */
 		if (ie[1] > rem - 2)
 			break;
@@ -1271,7 +1261,7 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 			iwe.u.data.length = ie[1];
 			iwe.u.data.flags = 1;
 			current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-							  &iwe, ie + 2);
+							  &iwe, (u8 *)ie + 2);
 			break;
 		case WLAN_EID_MESH_ID:
 			memset(&iwe, 0, sizeof(iwe));
@@ -1279,7 +1269,7 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 			iwe.u.data.length = ie[1];
 			iwe.u.data.flags = 1;
 			current_ev = iwe_stream_add_point(info, current_ev, end_buf,
-							  &iwe, ie + 2);
+							  &iwe, (u8 *)ie + 2);
 			break;
 		case WLAN_EID_MESH_CONFIG:
 			ismesh = true;
@@ -1288,7 +1278,7 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 			buf = kmalloc(50, GFP_ATOMIC);
 			if (!buf)
 				break;
-			cfg = ie + 2;
+			cfg = (u8 *)ie + 2;
 			memset(&iwe, 0, sizeof(iwe));
 			iwe.cmd = IWEVCUSTOM;
 			sprintf(buf, "Mesh Network Path Selection Protocol ID: "
@@ -1386,7 +1376,8 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 		kfree(buf);
 	}
 
-	ieee80211_scan_add_ies(info, &bss->pub, &current_ev, end_buf);
+	ieee80211_scan_add_ies(info, ies, &current_ev, end_buf);
+	rcu_read_unlock();
 
 	return current_ev;
 }
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index c7490027237d..f2431e41a373 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -417,7 +417,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			       struct cfg80211_bss *bss)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	u8 *country_ie;
+	const u8 *country_ie;
 #ifdef CONFIG_CFG80211_WEXT
 	union iwreq_data wrqu;
 #endif
@@ -501,7 +501,15 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 	wdev->sme_state = CFG80211_SME_CONNECTED;
 	cfg80211_upload_connect_keys(wdev);
 
-	country_ie = (u8 *) ieee80211_bss_get_ie(bss, WLAN_EID_COUNTRY);
+	rcu_read_lock();
+	country_ie = ieee80211_bss_get_ie(bss, WLAN_EID_COUNTRY);
+	if (!country_ie) {
+		rcu_read_unlock();
+		return;
+	}
+
+	country_ie = kmemdup(country_ie, 2 + country_ie[1], GFP_ATOMIC);
+	rcu_read_unlock();
 
 	if (!country_ie)
 		return;
@@ -515,6 +523,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			    bss->channel->band,
 			    country_ie + 2,
 			    country_ie[1]);
+	kfree(country_ie);
 }
 
 void cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 3cce6e486219..16d76a807c2f 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -688,10 +688,13 @@ EXPORT_SYMBOL(cfg80211_classify8021d);
 
 const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 ie)
 {
-	if (bss->information_elements == NULL)
+	const struct cfg80211_bss_ies *ies;
+
+	ies = rcu_dereference(bss->ies);
+	if (!ies)
 		return NULL;
-	return cfg80211_find_ie(ie, bss->information_elements,
-				 bss->len_information_elements);
+
+	return cfg80211_find_ie(ie, ies->data, ies->len);
 }
 EXPORT_SYMBOL(ieee80211_bss_get_ie);
 
diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c
index 873af63187c0..fb9622f6d99c 100644
--- a/net/wireless/wext-sme.c
+++ b/net/wireless/wext-sme.c
@@ -242,13 +242,17 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev,
 
 	wdev_lock(wdev);
 	if (wdev->current_bss) {
-		const u8 *ie = ieee80211_bss_get_ie(&wdev->current_bss->pub,
-						    WLAN_EID_SSID);
+		const u8 *ie;
+
+		rcu_read_lock();
+		ie = ieee80211_bss_get_ie(&wdev->current_bss->pub,
+					  WLAN_EID_SSID);
 		if (ie) {
 			data->flags = 1;
 			data->length = ie[1];
 			memcpy(ssid, ie + 2, data->length);
 		}
+		rcu_read_unlock();
 	} else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) {
 		data->flags = 1;
 		data->length = wdev->wext.connect.ssid_len;
-- 
cgit v1.2.3-55-g7522


From f87f1a2375a51ef8c5048bfce42587dbea1ca627 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Wed, 21 Nov 2012 16:27:00 +0000
Subject: staging:iio: Move ad7793 driver out of staging

The driver does not expose any custom API to userspace and none of the standard
static code checker tools report any issues, so move it out of staging.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/adc/Kconfig              |  12 +
 drivers/iio/adc/Makefile             |   1 +
 drivers/iio/adc/ad7793.c             | 691 ++++++++++++++++++++++++++++++++++
 drivers/staging/iio/adc/Kconfig      |  12 -
 drivers/staging/iio/adc/Makefile     |   1 -
 drivers/staging/iio/adc/ad7793.c     | 692 -----------------------------------
 drivers/staging/iio/adc/ad7793.h     | 116 ------
 include/linux/platform_data/ad7793.h | 112 ++++++
 8 files changed, 816 insertions(+), 821 deletions(-)
 create mode 100644 drivers/iio/adc/ad7793.c
 delete mode 100644 drivers/staging/iio/adc/ad7793.c
 delete mode 100644 drivers/staging/iio/adc/ad7793.h
 create mode 100644 include/linux/platform_data/ad7793.h

(limited to 'include')

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index cd5eed60be28..408557b02441 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -42,6 +42,18 @@ config AD7791
 	  To compile this driver as a module, choose M here: the module will be
 	  called ad7791.
 
+config AD7793
+	tristate "Analog Devices AD7793 and similar ADCs driver"
+	depends on SPI
+	select AD_SIGMA_DELTA
+	help
+	  Say yes here to build support for Analog Devices AD7785, AD7792, AD7793,
+	  AD7794 and AD7795 SPI analog to digital converters (ADC).
+	  If unsure, say N (but it's safe to say "Y").
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called AD7793.
+
 config AD7476
 	tristate "Analog Devices AD7476 and similar 1-channel ADCs driver"
 	depends on SPI
diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile
index 3256dc64a466..78202d9eb961 100644
--- a/drivers/iio/adc/Makefile
+++ b/drivers/iio/adc/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_AD7266) += ad7266.o
 obj-$(CONFIG_AD7298) += ad7298.o
 obj-$(CONFIG_AD7476) += ad7476.o
 obj-$(CONFIG_AD7791) += ad7791.o
+obj-$(CONFIG_AD7793) += ad7793.o
 obj-$(CONFIG_AD7887) += ad7887.o
 obj-$(CONFIG_AT91_ADC) += at91_adc.o
 obj-$(CONFIG_LP8788_ADC) += lp8788_adc.o
diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c
new file mode 100644
index 000000000000..a109e686b9f7
--- /dev/null
+++ b/drivers/iio/adc/ad7793.c
@@ -0,0 +1,691 @@
+/*
+ * AD7785/AD7792/AD7793/AD7794/AD7795 SPI ADC driver
+ *
+ * Copyright 2011-2012 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/spi/spi.h>
+#include <linux/regulator/consumer.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
+#include <linux/iio/adc/ad_sigma_delta.h>
+#include <linux/platform_data/ad7793.h>
+
+/* Registers */
+#define AD7793_REG_COMM		0 /* Communications Register (WO, 8-bit) */
+#define AD7793_REG_STAT		0 /* Status Register	     (RO, 8-bit) */
+#define AD7793_REG_MODE		1 /* Mode Register	     (RW, 16-bit */
+#define AD7793_REG_CONF		2 /* Configuration Register  (RW, 16-bit) */
+#define AD7793_REG_DATA		3 /* Data Register	     (RO, 16-/24-bit) */
+#define AD7793_REG_ID		4 /* ID Register	     (RO, 8-bit) */
+#define AD7793_REG_IO		5 /* IO Register	     (RO, 8-bit) */
+#define AD7793_REG_OFFSET	6 /* Offset Register	     (RW, 16-bit
+				   * (AD7792)/24-bit (AD7793)) */
+#define AD7793_REG_FULLSALE	7 /* Full-Scale Register
+				   * (RW, 16-bit (AD7792)/24-bit (AD7793)) */
+
+/* Communications Register Bit Designations (AD7793_REG_COMM) */
+#define AD7793_COMM_WEN		(1 << 7) /* Write Enable */
+#define AD7793_COMM_WRITE	(0 << 6) /* Write Operation */
+#define AD7793_COMM_READ	(1 << 6) /* Read Operation */
+#define AD7793_COMM_ADDR(x)	(((x) & 0x7) << 3) /* Register Address */
+#define AD7793_COMM_CREAD	(1 << 2) /* Continuous Read of Data Register */
+
+/* Status Register Bit Designations (AD7793_REG_STAT) */
+#define AD7793_STAT_RDY		(1 << 7) /* Ready */
+#define AD7793_STAT_ERR		(1 << 6) /* Error (Overrange, Underrange) */
+#define AD7793_STAT_CH3		(1 << 2) /* Channel 3 */
+#define AD7793_STAT_CH2		(1 << 1) /* Channel 2 */
+#define AD7793_STAT_CH1		(1 << 0) /* Channel 1 */
+
+/* Mode Register Bit Designations (AD7793_REG_MODE) */
+#define AD7793_MODE_SEL(x)	(((x) & 0x7) << 13) /* Operation Mode Select */
+#define AD7793_MODE_SEL_MASK	(0x7 << 13) /* Operation Mode Select mask */
+#define AD7793_MODE_CLKSRC(x)	(((x) & 0x3) << 6) /* ADC Clock Source Select */
+#define AD7793_MODE_RATE(x)	((x) & 0xF) /* Filter Update Rate Select */
+
+#define AD7793_MODE_CONT		0 /* Continuous Conversion Mode */
+#define AD7793_MODE_SINGLE		1 /* Single Conversion Mode */
+#define AD7793_MODE_IDLE		2 /* Idle Mode */
+#define AD7793_MODE_PWRDN		3 /* Power-Down Mode */
+#define AD7793_MODE_CAL_INT_ZERO	4 /* Internal Zero-Scale Calibration */
+#define AD7793_MODE_CAL_INT_FULL	5 /* Internal Full-Scale Calibration */
+#define AD7793_MODE_CAL_SYS_ZERO	6 /* System Zero-Scale Calibration */
+#define AD7793_MODE_CAL_SYS_FULL	7 /* System Full-Scale Calibration */
+
+#define AD7793_CLK_INT		0 /* Internal 64 kHz Clock not
+				   * available at the CLK pin */
+#define AD7793_CLK_INT_CO	1 /* Internal 64 kHz Clock available
+				   * at the CLK pin */
+#define AD7793_CLK_EXT		2 /* External 64 kHz Clock */
+#define AD7793_CLK_EXT_DIV2	3 /* External Clock divided by 2 */
+
+/* Configuration Register Bit Designations (AD7793_REG_CONF) */
+#define AD7793_CONF_VBIAS(x)	(((x) & 0x3) << 14) /* Bias Voltage
+						     * Generator Enable */
+#define AD7793_CONF_BO_EN	(1 << 13) /* Burnout Current Enable */
+#define AD7793_CONF_UNIPOLAR	(1 << 12) /* Unipolar/Bipolar Enable */
+#define AD7793_CONF_BOOST	(1 << 11) /* Boost Enable */
+#define AD7793_CONF_GAIN(x)	(((x) & 0x7) << 8) /* Gain Select */
+#define AD7793_CONF_REFSEL(x)	((x) << 6) /* INT/EXT Reference Select */
+#define AD7793_CONF_BUF		(1 << 4) /* Buffered Mode Enable */
+#define AD7793_CONF_CHAN(x)	((x) & 0xf) /* Channel select */
+#define AD7793_CONF_CHAN_MASK	0xf /* Channel select mask */
+
+#define AD7793_CH_AIN1P_AIN1M	0 /* AIN1(+) - AIN1(-) */
+#define AD7793_CH_AIN2P_AIN2M	1 /* AIN2(+) - AIN2(-) */
+#define AD7793_CH_AIN3P_AIN3M	2 /* AIN3(+) - AIN3(-) */
+#define AD7793_CH_AIN1M_AIN1M	3 /* AIN1(-) - AIN1(-) */
+#define AD7793_CH_TEMP		6 /* Temp Sensor */
+#define AD7793_CH_AVDD_MONITOR	7 /* AVDD Monitor */
+
+#define AD7795_CH_AIN4P_AIN4M	4 /* AIN4(+) - AIN4(-) */
+#define AD7795_CH_AIN5P_AIN5M	5 /* AIN5(+) - AIN5(-) */
+#define AD7795_CH_AIN6P_AIN6M	6 /* AIN6(+) - AIN6(-) */
+#define AD7795_CH_AIN1M_AIN1M	8 /* AIN1(-) - AIN1(-) */
+
+/* ID Register Bit Designations (AD7793_REG_ID) */
+#define AD7785_ID		0xB
+#define AD7792_ID		0xA
+#define AD7793_ID		0xB
+#define AD7794_ID		0xF
+#define AD7795_ID		0xF
+#define AD7793_ID_MASK		0xF
+
+/* IO (Excitation Current Sources) Register Bit Designations (AD7793_REG_IO) */
+#define AD7793_IO_IEXC1_IOUT1_IEXC2_IOUT2	0 /* IEXC1 connect to IOUT1,
+						   * IEXC2 connect to IOUT2 */
+#define AD7793_IO_IEXC1_IOUT2_IEXC2_IOUT1	1 /* IEXC1 connect to IOUT2,
+						   * IEXC2 connect to IOUT1 */
+#define AD7793_IO_IEXC1_IEXC2_IOUT1		2 /* Both current sources
+						   * IEXC1,2 connect to IOUT1 */
+#define AD7793_IO_IEXC1_IEXC2_IOUT2		3 /* Both current sources
+						   * IEXC1,2 connect to IOUT2 */
+
+#define AD7793_IO_IXCEN_10uA	(1 << 0) /* Excitation Current 10uA */
+#define AD7793_IO_IXCEN_210uA	(2 << 0) /* Excitation Current 210uA */
+#define AD7793_IO_IXCEN_1mA	(3 << 0) /* Excitation Current 1mA */
+
+/* NOTE:
+ * The AD7792/AD7793 features a dual use data out ready DOUT/RDY output.
+ * In order to avoid contentions on the SPI bus, it's therefore necessary
+ * to use spi bus locking.
+ *
+ * The DOUT/RDY output must also be wired to an interrupt capable GPIO.
+ */
+
+struct ad7793_chip_info {
+	unsigned int id;
+	const struct iio_chan_spec *channels;
+	unsigned int num_channels;
+};
+
+struct ad7793_state {
+	const struct ad7793_chip_info	*chip_info;
+	struct regulator		*reg;
+	u16				int_vref_mv;
+	u16				mode;
+	u16				conf;
+	u32				scale_avail[8][2];
+
+	struct ad_sigma_delta		sd;
+
+};
+
+enum ad7793_supported_device_ids {
+	ID_AD7785,
+	ID_AD7792,
+	ID_AD7793,
+	ID_AD7794,
+	ID_AD7795,
+};
+
+static struct ad7793_state *ad_sigma_delta_to_ad7793(struct ad_sigma_delta *sd)
+{
+	return container_of(sd, struct ad7793_state, sd);
+}
+
+static int ad7793_set_channel(struct ad_sigma_delta *sd, unsigned int channel)
+{
+	struct ad7793_state *st = ad_sigma_delta_to_ad7793(sd);
+
+	st->conf &= ~AD7793_CONF_CHAN_MASK;
+	st->conf |= AD7793_CONF_CHAN(channel);
+
+	return ad_sd_write_reg(&st->sd, AD7793_REG_CONF, 2, st->conf);
+}
+
+static int ad7793_set_mode(struct ad_sigma_delta *sd,
+			   enum ad_sigma_delta_mode mode)
+{
+	struct ad7793_state *st = ad_sigma_delta_to_ad7793(sd);
+
+	st->mode &= ~AD7793_MODE_SEL_MASK;
+	st->mode |= AD7793_MODE_SEL(mode);
+
+	return ad_sd_write_reg(&st->sd, AD7793_REG_MODE, 2, st->mode);
+}
+
+static const struct ad_sigma_delta_info ad7793_sigma_delta_info = {
+	.set_channel = ad7793_set_channel,
+	.set_mode = ad7793_set_mode,
+	.has_registers = true,
+	.addr_shift = 3,
+	.read_mask = BIT(6),
+};
+
+static const struct ad_sd_calib_data ad7793_calib_arr[6] = {
+	{AD7793_MODE_CAL_INT_ZERO, AD7793_CH_AIN1P_AIN1M},
+	{AD7793_MODE_CAL_INT_FULL, AD7793_CH_AIN1P_AIN1M},
+	{AD7793_MODE_CAL_INT_ZERO, AD7793_CH_AIN2P_AIN2M},
+	{AD7793_MODE_CAL_INT_FULL, AD7793_CH_AIN2P_AIN2M},
+	{AD7793_MODE_CAL_INT_ZERO, AD7793_CH_AIN3P_AIN3M},
+	{AD7793_MODE_CAL_INT_FULL, AD7793_CH_AIN3P_AIN3M}
+};
+
+static int ad7793_calibrate_all(struct ad7793_state *st)
+{
+	return ad_sd_calibrate_all(&st->sd, ad7793_calib_arr,
+				   ARRAY_SIZE(ad7793_calib_arr));
+}
+
+static int ad7793_setup(struct iio_dev *indio_dev,
+	const struct ad7793_platform_data *pdata,
+	unsigned int vref_mv)
+{
+	struct ad7793_state *st = iio_priv(indio_dev);
+	int i, ret = -1;
+	unsigned long long scale_uv;
+	u32 id;
+
+	if ((pdata->current_source_direction == AD7793_IEXEC1_IEXEC2_IOUT1 ||
+		pdata->current_source_direction == AD7793_IEXEC1_IEXEC2_IOUT2) &&
+		((pdata->exitation_current != AD7793_IX_10uA) &&
+		(pdata->exitation_current != AD7793_IX_210uA)))
+		return -EINVAL;
+
+	/* reset the serial interface */
+	ret = spi_write(st->sd.spi, (u8 *)&ret, sizeof(ret));
+	if (ret < 0)
+		goto out;
+	usleep_range(500, 2000); /* Wait for at least 500us */
+
+	/* write/read test for device presence */
+	ret = ad_sd_read_reg(&st->sd, AD7793_REG_ID, 1, &id);
+	if (ret)
+		goto out;
+
+	id &= AD7793_ID_MASK;
+
+	if (id != st->chip_info->id) {
+		dev_err(&st->sd.spi->dev, "device ID query failed\n");
+		goto out;
+	}
+
+	st->mode = AD7793_MODE_RATE(1);
+	st->mode |= AD7793_MODE_CLKSRC(pdata->clock_src);
+	st->conf = AD7793_CONF_REFSEL(pdata->refsel);
+	st->conf |= AD7793_CONF_VBIAS(pdata->bias_voltage);
+	if (pdata->buffered)
+		st->conf |= AD7793_CONF_BUF;
+	if (pdata->boost_enable)
+		st->conf |= AD7793_CONF_BOOST;
+	if (pdata->burnout_current)
+		st->conf |= AD7793_CONF_BO_EN;
+	if (pdata->unipolar)
+		st->conf |= AD7793_CONF_UNIPOLAR;
+
+	ret = ad7793_set_mode(&st->sd, AD_SD_MODE_IDLE);
+	if (ret)
+		goto out;
+
+	ret = ad7793_set_channel(&st->sd, 0);
+	if (ret)
+		goto out;
+
+	ret = ad_sd_write_reg(&st->sd, AD7793_REG_IO, 1,
+				   pdata->exitation_current |
+			       (pdata->current_source_direction << 2));
+	if (ret)
+		goto out;
+
+	ret = ad7793_calibrate_all(st);
+	if (ret)
+		goto out;
+
+	/* Populate available ADC input ranges */
+	for (i = 0; i < ARRAY_SIZE(st->scale_avail); i++) {
+		scale_uv = ((u64)vref_mv * 100000000)
+			>> (st->chip_info->channels[0].scan_type.realbits -
+			(!!(st->conf & AD7793_CONF_UNIPOLAR) ? 0 : 1));
+		scale_uv >>= i;
+
+		st->scale_avail[i][1] = do_div(scale_uv, 100000000) * 10;
+		st->scale_avail[i][0] = scale_uv;
+	}
+
+	return 0;
+out:
+	dev_err(&st->sd.spi->dev, "setup failed\n");
+	return ret;
+}
+
+static const u16 sample_freq_avail[16] = {0, 470, 242, 123, 62, 50, 39, 33, 19,
+					  17, 16, 12, 10, 8, 6, 4};
+
+static ssize_t ad7793_read_frequency(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct ad7793_state *st = iio_priv(indio_dev);
+
+	return sprintf(buf, "%d\n",
+		       sample_freq_avail[AD7793_MODE_RATE(st->mode)]);
+}
+
+static ssize_t ad7793_write_frequency(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t len)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct ad7793_state *st = iio_priv(indio_dev);
+	long lval;
+	int i, ret;
+
+	mutex_lock(&indio_dev->mlock);
+	if (iio_buffer_enabled(indio_dev)) {
+		mutex_unlock(&indio_dev->mlock);
+		return -EBUSY;
+	}
+	mutex_unlock(&indio_dev->mlock);
+
+	ret = kstrtol(buf, 10, &lval);
+	if (ret)
+		return ret;
+
+	ret = -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(sample_freq_avail); i++)
+		if (lval == sample_freq_avail[i]) {
+			mutex_lock(&indio_dev->mlock);
+			st->mode &= ~AD7793_MODE_RATE(-1);
+			st->mode |= AD7793_MODE_RATE(i);
+			ad_sd_write_reg(&st->sd, AD7793_REG_MODE,
+					 sizeof(st->mode), st->mode);
+			mutex_unlock(&indio_dev->mlock);
+			ret = 0;
+		}
+
+	return ret ? ret : len;
+}
+
+static IIO_DEV_ATTR_SAMP_FREQ(S_IWUSR | S_IRUGO,
+		ad7793_read_frequency,
+		ad7793_write_frequency);
+
+static IIO_CONST_ATTR_SAMP_FREQ_AVAIL(
+	"470 242 123 62 50 39 33 19 17 16 12 10 8 6 4");
+
+static ssize_t ad7793_show_scale_available(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct ad7793_state *st = iio_priv(indio_dev);
+	int i, len = 0;
+
+	for (i = 0; i < ARRAY_SIZE(st->scale_avail); i++)
+		len += sprintf(buf + len, "%d.%09u ", st->scale_avail[i][0],
+			       st->scale_avail[i][1]);
+
+	len += sprintf(buf + len, "\n");
+
+	return len;
+}
+
+static IIO_DEVICE_ATTR_NAMED(in_m_in_scale_available,
+		in_voltage-voltage_scale_available, S_IRUGO,
+		ad7793_show_scale_available, NULL, 0);
+
+static struct attribute *ad7793_attributes[] = {
+	&iio_dev_attr_sampling_frequency.dev_attr.attr,
+	&iio_const_attr_sampling_frequency_available.dev_attr.attr,
+	&iio_dev_attr_in_m_in_scale_available.dev_attr.attr,
+	NULL
+};
+
+static const struct attribute_group ad7793_attribute_group = {
+	.attrs = ad7793_attributes,
+};
+
+static int ad7793_read_raw(struct iio_dev *indio_dev,
+			   struct iio_chan_spec const *chan,
+			   int *val,
+			   int *val2,
+			   long m)
+{
+	struct ad7793_state *st = iio_priv(indio_dev);
+	int ret;
+	unsigned long long scale_uv;
+	bool unipolar = !!(st->conf & AD7793_CONF_UNIPOLAR);
+
+	switch (m) {
+	case IIO_CHAN_INFO_RAW:
+		ret = ad_sigma_delta_single_conversion(indio_dev, chan, val);
+		if (ret < 0)
+			return ret;
+
+		return IIO_VAL_INT;
+
+	case IIO_CHAN_INFO_SCALE:
+		switch (chan->type) {
+		case IIO_VOLTAGE:
+			if (chan->differential) {
+				*val = st->
+					scale_avail[(st->conf >> 8) & 0x7][0];
+				*val2 = st->
+					scale_avail[(st->conf >> 8) & 0x7][1];
+				return IIO_VAL_INT_PLUS_NANO;
+			} else {
+				/* 1170mV / 2^23 * 6 */
+				scale_uv = (1170ULL * 1000000000ULL * 6ULL);
+			}
+			break;
+		case IIO_TEMP:
+				/* 1170mV / 0.81 mV/C / 2^23 */
+				scale_uv = 1444444444444444ULL;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		scale_uv >>= (chan->scan_type.realbits - (unipolar ? 0 : 1));
+		*val = 0;
+		*val2 = scale_uv;
+		return IIO_VAL_INT_PLUS_NANO;
+	case IIO_CHAN_INFO_OFFSET:
+		if (!unipolar)
+			*val = -(1 << (chan->scan_type.realbits - 1));
+		else
+			*val = 0;
+
+		/* Kelvin to Celsius */
+		if (chan->type == IIO_TEMP) {
+			unsigned long long offset;
+			unsigned int shift;
+
+			shift = chan->scan_type.realbits - (unipolar ? 0 : 1);
+			offset = 273ULL << shift;
+			do_div(offset, 1444);
+			*val -= offset;
+		}
+		return IIO_VAL_INT;
+	}
+	return -EINVAL;
+}
+
+static int ad7793_write_raw(struct iio_dev *indio_dev,
+			       struct iio_chan_spec const *chan,
+			       int val,
+			       int val2,
+			       long mask)
+{
+	struct ad7793_state *st = iio_priv(indio_dev);
+	int ret, i;
+	unsigned int tmp;
+
+	mutex_lock(&indio_dev->mlock);
+	if (iio_buffer_enabled(indio_dev)) {
+		mutex_unlock(&indio_dev->mlock);
+		return -EBUSY;
+	}
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		ret = -EINVAL;
+		for (i = 0; i < ARRAY_SIZE(st->scale_avail); i++)
+			if (val2 == st->scale_avail[i][1]) {
+				ret = 0;
+				tmp = st->conf;
+				st->conf &= ~AD7793_CONF_GAIN(-1);
+				st->conf |= AD7793_CONF_GAIN(i);
+
+				if (tmp == st->conf)
+					break;
+
+				ad_sd_write_reg(&st->sd, AD7793_REG_CONF,
+						sizeof(st->conf), st->conf);
+				ad7793_calibrate_all(st);
+				break;
+			}
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	mutex_unlock(&indio_dev->mlock);
+	return ret;
+}
+
+static int ad7793_write_raw_get_fmt(struct iio_dev *indio_dev,
+			       struct iio_chan_spec const *chan,
+			       long mask)
+{
+	return IIO_VAL_INT_PLUS_NANO;
+}
+
+static const struct iio_info ad7793_info = {
+	.read_raw = &ad7793_read_raw,
+	.write_raw = &ad7793_write_raw,
+	.write_raw_get_fmt = &ad7793_write_raw_get_fmt,
+	.attrs = &ad7793_attribute_group,
+	.validate_trigger = ad_sd_validate_trigger,
+	.driver_module = THIS_MODULE,
+};
+
+#define DECLARE_AD7793_CHANNELS(_name, _b, _sb, _s) \
+const struct iio_chan_spec _name##_channels[] = { \
+	AD_SD_DIFF_CHANNEL(0, 0, 0, AD7793_CH_AIN1P_AIN1M, (_b), (_sb), (_s)), \
+	AD_SD_DIFF_CHANNEL(1, 1, 1, AD7793_CH_AIN2P_AIN2M, (_b), (_sb), (_s)), \
+	AD_SD_DIFF_CHANNEL(2, 2, 2, AD7793_CH_AIN3P_AIN3M, (_b), (_sb), (_s)), \
+	AD_SD_SHORTED_CHANNEL(3, 0, AD7793_CH_AIN1M_AIN1M, (_b), (_sb), (_s)), \
+	AD_SD_TEMP_CHANNEL(4, AD7793_CH_TEMP, (_b), (_sb), (_s)), \
+	AD_SD_SUPPLY_CHANNEL(5, 3, AD7793_CH_AVDD_MONITOR, (_b), (_sb), (_s)), \
+	IIO_CHAN_SOFT_TIMESTAMP(6), \
+}
+
+#define DECLARE_AD7795_CHANNELS(_name, _b, _sb) \
+const struct iio_chan_spec _name##_channels[] = { \
+	AD_SD_DIFF_CHANNEL(0, 0, 0, AD7793_CH_AIN1P_AIN1M, (_b), (_sb), 0), \
+	AD_SD_DIFF_CHANNEL(1, 1, 1, AD7793_CH_AIN2P_AIN2M, (_b), (_sb), 0), \
+	AD_SD_DIFF_CHANNEL(2, 2, 2, AD7793_CH_AIN3P_AIN3M, (_b), (_sb), 0), \
+	AD_SD_DIFF_CHANNEL(3, 3, 3, AD7795_CH_AIN4P_AIN4M, (_b), (_sb), 0), \
+	AD_SD_DIFF_CHANNEL(4, 4, 4, AD7795_CH_AIN5P_AIN5M, (_b), (_sb), 0), \
+	AD_SD_DIFF_CHANNEL(5, 5, 5, AD7795_CH_AIN6P_AIN6M, (_b), (_sb), 0), \
+	AD_SD_SHORTED_CHANNEL(6, 0, AD7795_CH_AIN1M_AIN1M, (_b), (_sb), 0), \
+	AD_SD_TEMP_CHANNEL(7, AD7793_CH_TEMP, (_b), (_sb), 0), \
+	AD_SD_SUPPLY_CHANNEL(8, 3, AD7793_CH_AVDD_MONITOR, (_b), (_sb), 0), \
+	IIO_CHAN_SOFT_TIMESTAMP(9), \
+}
+
+static DECLARE_AD7793_CHANNELS(ad7785, 20, 32, 4);
+static DECLARE_AD7793_CHANNELS(ad7792, 16, 32, 0);
+static DECLARE_AD7793_CHANNELS(ad7793, 24, 32, 0);
+static DECLARE_AD7795_CHANNELS(ad7794, 16, 32);
+static DECLARE_AD7795_CHANNELS(ad7795, 24, 32);
+
+static const struct ad7793_chip_info ad7793_chip_info_tbl[] = {
+	[ID_AD7785] = {
+		.id = AD7785_ID,
+		.channels = ad7785_channels,
+		.num_channels = ARRAY_SIZE(ad7785_channels),
+	},
+	[ID_AD7792] = {
+		.id = AD7792_ID,
+		.channels = ad7792_channels,
+		.num_channels = ARRAY_SIZE(ad7792_channels),
+	},
+	[ID_AD7793] = {
+		.id = AD7793_ID,
+		.channels = ad7793_channels,
+		.num_channels = ARRAY_SIZE(ad7793_channels),
+	},
+	[ID_AD7794] = {
+		.id = AD7794_ID,
+		.channels = ad7794_channels,
+		.num_channels = ARRAY_SIZE(ad7794_channels),
+	},
+	[ID_AD7795] = {
+		.id = AD7795_ID,
+		.channels = ad7795_channels,
+		.num_channels = ARRAY_SIZE(ad7795_channels),
+	},
+};
+
+static int ad7793_probe(struct spi_device *spi)
+{
+	const struct ad7793_platform_data *pdata = spi->dev.platform_data;
+	struct ad7793_state *st;
+	struct iio_dev *indio_dev;
+	int ret, vref_mv = 0;
+
+	if (!pdata) {
+		dev_err(&spi->dev, "no platform data?\n");
+		return -ENODEV;
+	}
+
+	if (!spi->irq) {
+		dev_err(&spi->dev, "no IRQ?\n");
+		return -ENODEV;
+	}
+
+	indio_dev = iio_device_alloc(sizeof(*st));
+	if (indio_dev == NULL)
+		return -ENOMEM;
+
+	st = iio_priv(indio_dev);
+
+	ad_sd_init(&st->sd, indio_dev, spi, &ad7793_sigma_delta_info);
+
+	if (pdata->refsel != AD7793_REFSEL_INTERNAL) {
+		st->reg = regulator_get(&spi->dev, "refin");
+		if (IS_ERR(st->reg)) {
+			ret = PTR_ERR(st->reg);
+			goto error_device_free;
+		}
+
+		ret = regulator_enable(st->reg);
+		if (ret)
+			goto error_put_reg;
+
+		vref_mv = regulator_get_voltage(st->reg);
+		if (vref_mv < 0) {
+			ret = vref_mv;
+			goto error_disable_reg;
+		}
+
+		vref_mv /= 1000;
+	} else {
+		vref_mv = 1170; /* Build-in ref */
+	}
+
+	st->chip_info =
+		&ad7793_chip_info_tbl[spi_get_device_id(spi)->driver_data];
+
+	spi_set_drvdata(spi, indio_dev);
+
+	indio_dev->dev.parent = &spi->dev;
+	indio_dev->name = spi_get_device_id(spi)->name;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = st->chip_info->channels;
+	indio_dev->num_channels = st->chip_info->num_channels;
+	indio_dev->info = &ad7793_info;
+
+	ret = ad_sd_setup_buffer_and_trigger(indio_dev);
+	if (ret)
+		goto error_disable_reg;
+
+	ret = ad7793_setup(indio_dev, pdata, vref_mv);
+	if (ret)
+		goto error_remove_trigger;
+
+	ret = iio_device_register(indio_dev);
+	if (ret)
+		goto error_remove_trigger;
+
+	return 0;
+
+error_remove_trigger:
+	ad_sd_cleanup_buffer_and_trigger(indio_dev);
+error_disable_reg:
+	if (pdata->refsel != AD7793_REFSEL_INTERNAL)
+		regulator_disable(st->reg);
+error_put_reg:
+	if (pdata->refsel != AD7793_REFSEL_INTERNAL)
+		regulator_put(st->reg);
+error_device_free:
+	iio_device_free(indio_dev);
+
+	return ret;
+}
+
+static int ad7793_remove(struct spi_device *spi)
+{
+	const struct ad7793_platform_data *pdata = spi->dev.platform_data;
+	struct iio_dev *indio_dev = spi_get_drvdata(spi);
+	struct ad7793_state *st = iio_priv(indio_dev);
+
+	iio_device_unregister(indio_dev);
+	ad_sd_cleanup_buffer_and_trigger(indio_dev);
+
+	if (pdata->refsel != AD7793_REFSEL_INTERNAL) {
+		regulator_disable(st->reg);
+		regulator_put(st->reg);
+	}
+
+	iio_device_free(indio_dev);
+
+	return 0;
+}
+
+static const struct spi_device_id ad7793_id[] = {
+	{"ad7785", ID_AD7785},
+	{"ad7792", ID_AD7792},
+	{"ad7793", ID_AD7793},
+	{"ad7794", ID_AD7794},
+	{"ad7795", ID_AD7795},
+	{}
+};
+MODULE_DEVICE_TABLE(spi, ad7793_id);
+
+static struct spi_driver ad7793_driver = {
+	.driver = {
+		.name	= "ad7793",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= ad7793_probe,
+	.remove		= ad7793_remove,
+	.id_table	= ad7793_id,
+};
+module_spi_driver(ad7793_driver);
+
+MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>");
+MODULE_DESCRIPTION("Analog Devices AD7793 and simialr ADCs");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/staging/iio/adc/Kconfig b/drivers/staging/iio/adc/Kconfig
index dc8582b95b61..fb8c239b0c88 100644
--- a/drivers/staging/iio/adc/Kconfig
+++ b/drivers/staging/iio/adc/Kconfig
@@ -70,18 +70,6 @@ config AD7780
 	  To compile this driver as a module, choose M here: the
 	  module will be called ad7780.
 
-config AD7793
-	tristate "Analog Devices AD7793 and similar ADCs driver"
-	depends on SPI
-	select AD_SIGMA_DELTA
-	help
-	  Say yes here to build support for Analog Devices AD7785, AD7792, AD7793,
-	  AD7794 and AD7795 SPI analog to digital converters (ADC).
-	  If unsure, say N (but it's safe to say "Y").
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called AD7793.
-
 config AD7816
 	tristate "Analog Devices AD7816/7/8 temperature sensor and ADC driver"
 	depends on SPI
diff --git a/drivers/staging/iio/adc/Makefile b/drivers/staging/iio/adc/Makefile
index 7281451a613a..d285596272a0 100644
--- a/drivers/staging/iio/adc/Makefile
+++ b/drivers/staging/iio/adc/Makefile
@@ -14,7 +14,6 @@ obj-$(CONFIG_AD799X) += ad799x.o
 
 obj-$(CONFIG_AD7291) += ad7291.o
 obj-$(CONFIG_AD7780) += ad7780.o
-obj-$(CONFIG_AD7793) += ad7793.o
 obj-$(CONFIG_AD7816) += ad7816.o
 obj-$(CONFIG_AD7192) += ad7192.o
 obj-$(CONFIG_ADT7410) += adt7410.o
diff --git a/drivers/staging/iio/adc/ad7793.c b/drivers/staging/iio/adc/ad7793.c
deleted file mode 100644
index 8928609a1828..000000000000
--- a/drivers/staging/iio/adc/ad7793.c
+++ /dev/null
@@ -1,692 +0,0 @@
-/*
- * AD7785/AD7792/AD7793/AD7794/AD7795 SPI ADC driver
- *
- * Copyright 2011-2012 Analog Devices Inc.
- *
- * Licensed under the GPL-2.
- */
-
-#include <linux/interrupt.h>
-#include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/sysfs.h>
-#include <linux/spi/spi.h>
-#include <linux/regulator/consumer.h>
-#include <linux/err.h>
-#include <linux/sched.h>
-#include <linux/delay.h>
-#include <linux/module.h>
-
-#include <linux/iio/iio.h>
-#include <linux/iio/sysfs.h>
-#include <linux/iio/buffer.h>
-#include <linux/iio/trigger.h>
-#include <linux/iio/trigger_consumer.h>
-#include <linux/iio/triggered_buffer.h>
-#include <linux/iio/adc/ad_sigma_delta.h>
-
-#include "ad7793.h"
-
-/* Registers */
-#define AD7793_REG_COMM		0 /* Communications Register (WO, 8-bit) */
-#define AD7793_REG_STAT		0 /* Status Register	     (RO, 8-bit) */
-#define AD7793_REG_MODE		1 /* Mode Register	     (RW, 16-bit */
-#define AD7793_REG_CONF		2 /* Configuration Register  (RW, 16-bit) */
-#define AD7793_REG_DATA		3 /* Data Register	     (RO, 16-/24-bit) */
-#define AD7793_REG_ID		4 /* ID Register	     (RO, 8-bit) */
-#define AD7793_REG_IO		5 /* IO Register	     (RO, 8-bit) */
-#define AD7793_REG_OFFSET	6 /* Offset Register	     (RW, 16-bit
-				   * (AD7792)/24-bit (AD7793)) */
-#define AD7793_REG_FULLSALE	7 /* Full-Scale Register
-				   * (RW, 16-bit (AD7792)/24-bit (AD7793)) */
-
-/* Communications Register Bit Designations (AD7793_REG_COMM) */
-#define AD7793_COMM_WEN		(1 << 7) /* Write Enable */
-#define AD7793_COMM_WRITE	(0 << 6) /* Write Operation */
-#define AD7793_COMM_READ	(1 << 6) /* Read Operation */
-#define AD7793_COMM_ADDR(x)	(((x) & 0x7) << 3) /* Register Address */
-#define AD7793_COMM_CREAD	(1 << 2) /* Continuous Read of Data Register */
-
-/* Status Register Bit Designations (AD7793_REG_STAT) */
-#define AD7793_STAT_RDY		(1 << 7) /* Ready */
-#define AD7793_STAT_ERR		(1 << 6) /* Error (Overrange, Underrange) */
-#define AD7793_STAT_CH3		(1 << 2) /* Channel 3 */
-#define AD7793_STAT_CH2		(1 << 1) /* Channel 2 */
-#define AD7793_STAT_CH1		(1 << 0) /* Channel 1 */
-
-/* Mode Register Bit Designations (AD7793_REG_MODE) */
-#define AD7793_MODE_SEL(x)	(((x) & 0x7) << 13) /* Operation Mode Select */
-#define AD7793_MODE_SEL_MASK	(0x7 << 13) /* Operation Mode Select mask */
-#define AD7793_MODE_CLKSRC(x)	(((x) & 0x3) << 6) /* ADC Clock Source Select */
-#define AD7793_MODE_RATE(x)	((x) & 0xF) /* Filter Update Rate Select */
-
-#define AD7793_MODE_CONT		0 /* Continuous Conversion Mode */
-#define AD7793_MODE_SINGLE		1 /* Single Conversion Mode */
-#define AD7793_MODE_IDLE		2 /* Idle Mode */
-#define AD7793_MODE_PWRDN		3 /* Power-Down Mode */
-#define AD7793_MODE_CAL_INT_ZERO	4 /* Internal Zero-Scale Calibration */
-#define AD7793_MODE_CAL_INT_FULL	5 /* Internal Full-Scale Calibration */
-#define AD7793_MODE_CAL_SYS_ZERO	6 /* System Zero-Scale Calibration */
-#define AD7793_MODE_CAL_SYS_FULL	7 /* System Full-Scale Calibration */
-
-#define AD7793_CLK_INT		0 /* Internal 64 kHz Clock not
-				   * available at the CLK pin */
-#define AD7793_CLK_INT_CO	1 /* Internal 64 kHz Clock available
-				   * at the CLK pin */
-#define AD7793_CLK_EXT		2 /* External 64 kHz Clock */
-#define AD7793_CLK_EXT_DIV2	3 /* External Clock divided by 2 */
-
-/* Configuration Register Bit Designations (AD7793_REG_CONF) */
-#define AD7793_CONF_VBIAS(x)	(((x) & 0x3) << 14) /* Bias Voltage
-						     * Generator Enable */
-#define AD7793_CONF_BO_EN	(1 << 13) /* Burnout Current Enable */
-#define AD7793_CONF_UNIPOLAR	(1 << 12) /* Unipolar/Bipolar Enable */
-#define AD7793_CONF_BOOST	(1 << 11) /* Boost Enable */
-#define AD7793_CONF_GAIN(x)	(((x) & 0x7) << 8) /* Gain Select */
-#define AD7793_CONF_REFSEL(x)	((x) << 6) /* INT/EXT Reference Select */
-#define AD7793_CONF_BUF		(1 << 4) /* Buffered Mode Enable */
-#define AD7793_CONF_CHAN(x)	((x) & 0xf) /* Channel select */
-#define AD7793_CONF_CHAN_MASK	0xf /* Channel select mask */
-
-#define AD7793_CH_AIN1P_AIN1M	0 /* AIN1(+) - AIN1(-) */
-#define AD7793_CH_AIN2P_AIN2M	1 /* AIN2(+) - AIN2(-) */
-#define AD7793_CH_AIN3P_AIN3M	2 /* AIN3(+) - AIN3(-) */
-#define AD7793_CH_AIN1M_AIN1M	3 /* AIN1(-) - AIN1(-) */
-#define AD7793_CH_TEMP		6 /* Temp Sensor */
-#define AD7793_CH_AVDD_MONITOR	7 /* AVDD Monitor */
-
-#define AD7795_CH_AIN4P_AIN4M	4 /* AIN4(+) - AIN4(-) */
-#define AD7795_CH_AIN5P_AIN5M	5 /* AIN5(+) - AIN5(-) */
-#define AD7795_CH_AIN6P_AIN6M	6 /* AIN6(+) - AIN6(-) */
-#define AD7795_CH_AIN1M_AIN1M	8 /* AIN1(-) - AIN1(-) */
-
-/* ID Register Bit Designations (AD7793_REG_ID) */
-#define AD7785_ID		0xB
-#define AD7792_ID		0xA
-#define AD7793_ID		0xB
-#define AD7794_ID		0xF
-#define AD7795_ID		0xF
-#define AD7793_ID_MASK		0xF
-
-/* IO (Excitation Current Sources) Register Bit Designations (AD7793_REG_IO) */
-#define AD7793_IO_IEXC1_IOUT1_IEXC2_IOUT2	0 /* IEXC1 connect to IOUT1,
-						   * IEXC2 connect to IOUT2 */
-#define AD7793_IO_IEXC1_IOUT2_IEXC2_IOUT1	1 /* IEXC1 connect to IOUT2,
-						   * IEXC2 connect to IOUT1 */
-#define AD7793_IO_IEXC1_IEXC2_IOUT1		2 /* Both current sources
-						   * IEXC1,2 connect to IOUT1 */
-#define AD7793_IO_IEXC1_IEXC2_IOUT2		3 /* Both current sources
-						   * IEXC1,2 connect to IOUT2 */
-
-#define AD7793_IO_IXCEN_10uA	(1 << 0) /* Excitation Current 10uA */
-#define AD7793_IO_IXCEN_210uA	(2 << 0) /* Excitation Current 210uA */
-#define AD7793_IO_IXCEN_1mA	(3 << 0) /* Excitation Current 1mA */
-
-/* NOTE:
- * The AD7792/AD7793 features a dual use data out ready DOUT/RDY output.
- * In order to avoid contentions on the SPI bus, it's therefore necessary
- * to use spi bus locking.
- *
- * The DOUT/RDY output must also be wired to an interrupt capable GPIO.
- */
-
-struct ad7793_chip_info {
-	unsigned int id;
-	const struct iio_chan_spec *channels;
-	unsigned int num_channels;
-};
-
-struct ad7793_state {
-	const struct ad7793_chip_info	*chip_info;
-	struct regulator		*reg;
-	u16				int_vref_mv;
-	u16				mode;
-	u16				conf;
-	u32				scale_avail[8][2];
-
-	struct ad_sigma_delta		sd;
-
-};
-
-enum ad7793_supported_device_ids {
-	ID_AD7785,
-	ID_AD7792,
-	ID_AD7793,
-	ID_AD7794,
-	ID_AD7795,
-};
-
-static struct ad7793_state *ad_sigma_delta_to_ad7793(struct ad_sigma_delta *sd)
-{
-	return container_of(sd, struct ad7793_state, sd);
-}
-
-static int ad7793_set_channel(struct ad_sigma_delta *sd, unsigned int channel)
-{
-	struct ad7793_state *st = ad_sigma_delta_to_ad7793(sd);
-
-	st->conf &= ~AD7793_CONF_CHAN_MASK;
-	st->conf |= AD7793_CONF_CHAN(channel);
-
-	return ad_sd_write_reg(&st->sd, AD7793_REG_CONF, 2, st->conf);
-}
-
-static int ad7793_set_mode(struct ad_sigma_delta *sd,
-			   enum ad_sigma_delta_mode mode)
-{
-	struct ad7793_state *st = ad_sigma_delta_to_ad7793(sd);
-
-	st->mode &= ~AD7793_MODE_SEL_MASK;
-	st->mode |= AD7793_MODE_SEL(mode);
-
-	return ad_sd_write_reg(&st->sd, AD7793_REG_MODE, 2, st->mode);
-}
-
-static const struct ad_sigma_delta_info ad7793_sigma_delta_info = {
-	.set_channel = ad7793_set_channel,
-	.set_mode = ad7793_set_mode,
-	.has_registers = true,
-	.addr_shift = 3,
-	.read_mask = BIT(6),
-};
-
-static const struct ad_sd_calib_data ad7793_calib_arr[6] = {
-	{AD7793_MODE_CAL_INT_ZERO, AD7793_CH_AIN1P_AIN1M},
-	{AD7793_MODE_CAL_INT_FULL, AD7793_CH_AIN1P_AIN1M},
-	{AD7793_MODE_CAL_INT_ZERO, AD7793_CH_AIN2P_AIN2M},
-	{AD7793_MODE_CAL_INT_FULL, AD7793_CH_AIN2P_AIN2M},
-	{AD7793_MODE_CAL_INT_ZERO, AD7793_CH_AIN3P_AIN3M},
-	{AD7793_MODE_CAL_INT_FULL, AD7793_CH_AIN3P_AIN3M}
-};
-
-static int ad7793_calibrate_all(struct ad7793_state *st)
-{
-	return ad_sd_calibrate_all(&st->sd, ad7793_calib_arr,
-				   ARRAY_SIZE(ad7793_calib_arr));
-}
-
-static int ad7793_setup(struct iio_dev *indio_dev,
-	const struct ad7793_platform_data *pdata,
-	unsigned int vref_mv)
-{
-	struct ad7793_state *st = iio_priv(indio_dev);
-	int i, ret = -1;
-	unsigned long long scale_uv;
-	u32 id;
-
-	if ((pdata->current_source_direction == AD7793_IEXEC1_IEXEC2_IOUT1 ||
-		pdata->current_source_direction == AD7793_IEXEC1_IEXEC2_IOUT2) &&
-		((pdata->exitation_current != AD7793_IX_10uA) &&
-		(pdata->exitation_current != AD7793_IX_210uA)))
-		return -EINVAL;
-
-	/* reset the serial interface */
-	ret = spi_write(st->sd.spi, (u8 *)&ret, sizeof(ret));
-	if (ret < 0)
-		goto out;
-	usleep_range(500, 2000); /* Wait for at least 500us */
-
-	/* write/read test for device presence */
-	ret = ad_sd_read_reg(&st->sd, AD7793_REG_ID, 1, &id);
-	if (ret)
-		goto out;
-
-	id &= AD7793_ID_MASK;
-
-	if (id != st->chip_info->id) {
-		dev_err(&st->sd.spi->dev, "device ID query failed\n");
-		goto out;
-	}
-
-	st->mode = AD7793_MODE_RATE(1);
-	st->mode |= AD7793_MODE_CLKSRC(pdata->clock_src);
-	st->conf = AD7793_CONF_REFSEL(pdata->refsel);
-	st->conf |= AD7793_CONF_VBIAS(pdata->bias_voltage);
-	if (pdata->buffered)
-		st->conf |= AD7793_CONF_BUF;
-	if (pdata->boost_enable)
-		st->conf |= AD7793_CONF_BOOST;
-	if (pdata->burnout_current)
-		st->conf |= AD7793_CONF_BO_EN;
-	if (pdata->unipolar)
-		st->conf |= AD7793_CONF_UNIPOLAR;
-
-	ret = ad7793_set_mode(&st->sd, AD_SD_MODE_IDLE);
-	if (ret)
-		goto out;
-
-	ret = ad7793_set_channel(&st->sd, 0);
-	if (ret)
-		goto out;
-
-	ret = ad_sd_write_reg(&st->sd, AD7793_REG_IO, 1,
-				   pdata->exitation_current |
-			       (pdata->current_source_direction << 2));
-	if (ret)
-		goto out;
-
-	ret = ad7793_calibrate_all(st);
-	if (ret)
-		goto out;
-
-	/* Populate available ADC input ranges */
-	for (i = 0; i < ARRAY_SIZE(st->scale_avail); i++) {
-		scale_uv = ((u64)vref_mv * 100000000)
-			>> (st->chip_info->channels[0].scan_type.realbits -
-			(!!(st->conf & AD7793_CONF_UNIPOLAR) ? 0 : 1));
-		scale_uv >>= i;
-
-		st->scale_avail[i][1] = do_div(scale_uv, 100000000) * 10;
-		st->scale_avail[i][0] = scale_uv;
-	}
-
-	return 0;
-out:
-	dev_err(&st->sd.spi->dev, "setup failed\n");
-	return ret;
-}
-
-static const u16 sample_freq_avail[16] = {0, 470, 242, 123, 62, 50, 39, 33, 19,
-					  17, 16, 12, 10, 8, 6, 4};
-
-static ssize_t ad7793_read_frequency(struct device *dev,
-		struct device_attribute *attr,
-		char *buf)
-{
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct ad7793_state *st = iio_priv(indio_dev);
-
-	return sprintf(buf, "%d\n",
-		       sample_freq_avail[AD7793_MODE_RATE(st->mode)]);
-}
-
-static ssize_t ad7793_write_frequency(struct device *dev,
-		struct device_attribute *attr,
-		const char *buf,
-		size_t len)
-{
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct ad7793_state *st = iio_priv(indio_dev);
-	long lval;
-	int i, ret;
-
-	mutex_lock(&indio_dev->mlock);
-	if (iio_buffer_enabled(indio_dev)) {
-		mutex_unlock(&indio_dev->mlock);
-		return -EBUSY;
-	}
-	mutex_unlock(&indio_dev->mlock);
-
-	ret = kstrtol(buf, 10, &lval);
-	if (ret)
-		return ret;
-
-	ret = -EINVAL;
-
-	for (i = 0; i < ARRAY_SIZE(sample_freq_avail); i++)
-		if (lval == sample_freq_avail[i]) {
-			mutex_lock(&indio_dev->mlock);
-			st->mode &= ~AD7793_MODE_RATE(-1);
-			st->mode |= AD7793_MODE_RATE(i);
-			ad_sd_write_reg(&st->sd, AD7793_REG_MODE,
-					 sizeof(st->mode), st->mode);
-			mutex_unlock(&indio_dev->mlock);
-			ret = 0;
-		}
-
-	return ret ? ret : len;
-}
-
-static IIO_DEV_ATTR_SAMP_FREQ(S_IWUSR | S_IRUGO,
-		ad7793_read_frequency,
-		ad7793_write_frequency);
-
-static IIO_CONST_ATTR_SAMP_FREQ_AVAIL(
-	"470 242 123 62 50 39 33 19 17 16 12 10 8 6 4");
-
-static ssize_t ad7793_show_scale_available(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct ad7793_state *st = iio_priv(indio_dev);
-	int i, len = 0;
-
-	for (i = 0; i < ARRAY_SIZE(st->scale_avail); i++)
-		len += sprintf(buf + len, "%d.%09u ", st->scale_avail[i][0],
-			       st->scale_avail[i][1]);
-
-	len += sprintf(buf + len, "\n");
-
-	return len;
-}
-
-static IIO_DEVICE_ATTR_NAMED(in_m_in_scale_available,
-		in_voltage-voltage_scale_available, S_IRUGO,
-		ad7793_show_scale_available, NULL, 0);
-
-static struct attribute *ad7793_attributes[] = {
-	&iio_dev_attr_sampling_frequency.dev_attr.attr,
-	&iio_const_attr_sampling_frequency_available.dev_attr.attr,
-	&iio_dev_attr_in_m_in_scale_available.dev_attr.attr,
-	NULL
-};
-
-static const struct attribute_group ad7793_attribute_group = {
-	.attrs = ad7793_attributes,
-};
-
-static int ad7793_read_raw(struct iio_dev *indio_dev,
-			   struct iio_chan_spec const *chan,
-			   int *val,
-			   int *val2,
-			   long m)
-{
-	struct ad7793_state *st = iio_priv(indio_dev);
-	int ret;
-	unsigned long long scale_uv;
-	bool unipolar = !!(st->conf & AD7793_CONF_UNIPOLAR);
-
-	switch (m) {
-	case IIO_CHAN_INFO_RAW:
-		ret = ad_sigma_delta_single_conversion(indio_dev, chan, val);
-		if (ret < 0)
-			return ret;
-
-		return IIO_VAL_INT;
-
-	case IIO_CHAN_INFO_SCALE:
-		switch (chan->type) {
-		case IIO_VOLTAGE:
-			if (chan->differential) {
-				*val = st->
-					scale_avail[(st->conf >> 8) & 0x7][0];
-				*val2 = st->
-					scale_avail[(st->conf >> 8) & 0x7][1];
-				return IIO_VAL_INT_PLUS_NANO;
-			} else {
-				/* 1170mV / 2^23 * 6 */
-				scale_uv = (1170ULL * 1000000000ULL * 6ULL);
-			}
-			break;
-		case IIO_TEMP:
-				/* 1170mV / 0.81 mV/C / 2^23 */
-				scale_uv = 1444444444444444ULL;
-			break;
-		default:
-			return -EINVAL;
-		}
-
-		scale_uv >>= (chan->scan_type.realbits - (unipolar ? 0 : 1));
-		*val = 0;
-		*val2 = scale_uv;
-		return IIO_VAL_INT_PLUS_NANO;
-	case IIO_CHAN_INFO_OFFSET:
-		if (!unipolar)
-			*val = -(1 << (chan->scan_type.realbits - 1));
-		else
-			*val = 0;
-
-		/* Kelvin to Celsius */
-		if (chan->type == IIO_TEMP) {
-			unsigned long long offset;
-			unsigned int shift;
-
-			shift = chan->scan_type.realbits - (unipolar ? 0 : 1);
-			offset = 273ULL << shift;
-			do_div(offset, 1444);
-			*val -= offset;
-		}
-		return IIO_VAL_INT;
-	}
-	return -EINVAL;
-}
-
-static int ad7793_write_raw(struct iio_dev *indio_dev,
-			       struct iio_chan_spec const *chan,
-			       int val,
-			       int val2,
-			       long mask)
-{
-	struct ad7793_state *st = iio_priv(indio_dev);
-	int ret, i;
-	unsigned int tmp;
-
-	mutex_lock(&indio_dev->mlock);
-	if (iio_buffer_enabled(indio_dev)) {
-		mutex_unlock(&indio_dev->mlock);
-		return -EBUSY;
-	}
-
-	switch (mask) {
-	case IIO_CHAN_INFO_SCALE:
-		ret = -EINVAL;
-		for (i = 0; i < ARRAY_SIZE(st->scale_avail); i++)
-			if (val2 == st->scale_avail[i][1]) {
-				ret = 0;
-				tmp = st->conf;
-				st->conf &= ~AD7793_CONF_GAIN(-1);
-				st->conf |= AD7793_CONF_GAIN(i);
-
-				if (tmp == st->conf)
-					break;
-
-				ad_sd_write_reg(&st->sd, AD7793_REG_CONF,
-						sizeof(st->conf), st->conf);
-				ad7793_calibrate_all(st);
-				break;
-			}
-		break;
-	default:
-		ret = -EINVAL;
-	}
-
-	mutex_unlock(&indio_dev->mlock);
-	return ret;
-}
-
-static int ad7793_write_raw_get_fmt(struct iio_dev *indio_dev,
-			       struct iio_chan_spec const *chan,
-			       long mask)
-{
-	return IIO_VAL_INT_PLUS_NANO;
-}
-
-static const struct iio_info ad7793_info = {
-	.read_raw = &ad7793_read_raw,
-	.write_raw = &ad7793_write_raw,
-	.write_raw_get_fmt = &ad7793_write_raw_get_fmt,
-	.attrs = &ad7793_attribute_group,
-	.validate_trigger = ad_sd_validate_trigger,
-	.driver_module = THIS_MODULE,
-};
-
-#define DECLARE_AD7793_CHANNELS(_name, _b, _sb, _s) \
-const struct iio_chan_spec _name##_channels[] = { \
-	AD_SD_DIFF_CHANNEL(0, 0, 0, AD7793_CH_AIN1P_AIN1M, (_b), (_sb), (_s)), \
-	AD_SD_DIFF_CHANNEL(1, 1, 1, AD7793_CH_AIN2P_AIN2M, (_b), (_sb), (_s)), \
-	AD_SD_DIFF_CHANNEL(2, 2, 2, AD7793_CH_AIN3P_AIN3M, (_b), (_sb), (_s)), \
-	AD_SD_SHORTED_CHANNEL(3, 0, AD7793_CH_AIN1M_AIN1M, (_b), (_sb), (_s)), \
-	AD_SD_TEMP_CHANNEL(4, AD7793_CH_TEMP, (_b), (_sb), (_s)), \
-	AD_SD_SUPPLY_CHANNEL(5, 3, AD7793_CH_AVDD_MONITOR, (_b), (_sb), (_s)), \
-	IIO_CHAN_SOFT_TIMESTAMP(6), \
-}
-
-#define DECLARE_AD7795_CHANNELS(_name, _b, _sb) \
-const struct iio_chan_spec _name##_channels[] = { \
-	AD_SD_DIFF_CHANNEL(0, 0, 0, AD7793_CH_AIN1P_AIN1M, (_b), (_sb), 0), \
-	AD_SD_DIFF_CHANNEL(1, 1, 1, AD7793_CH_AIN2P_AIN2M, (_b), (_sb), 0), \
-	AD_SD_DIFF_CHANNEL(2, 2, 2, AD7793_CH_AIN3P_AIN3M, (_b), (_sb), 0), \
-	AD_SD_DIFF_CHANNEL(3, 3, 3, AD7795_CH_AIN4P_AIN4M, (_b), (_sb), 0), \
-	AD_SD_DIFF_CHANNEL(4, 4, 4, AD7795_CH_AIN5P_AIN5M, (_b), (_sb), 0), \
-	AD_SD_DIFF_CHANNEL(5, 5, 5, AD7795_CH_AIN6P_AIN6M, (_b), (_sb), 0), \
-	AD_SD_SHORTED_CHANNEL(6, 0, AD7795_CH_AIN1M_AIN1M, (_b), (_sb), 0), \
-	AD_SD_TEMP_CHANNEL(7, AD7793_CH_TEMP, (_b), (_sb), 0), \
-	AD_SD_SUPPLY_CHANNEL(8, 3, AD7793_CH_AVDD_MONITOR, (_b), (_sb), 0), \
-	IIO_CHAN_SOFT_TIMESTAMP(9), \
-}
-
-static DECLARE_AD7793_CHANNELS(ad7785, 20, 32, 4);
-static DECLARE_AD7793_CHANNELS(ad7792, 16, 32, 0);
-static DECLARE_AD7793_CHANNELS(ad7793, 24, 32, 0);
-static DECLARE_AD7795_CHANNELS(ad7794, 16, 32);
-static DECLARE_AD7795_CHANNELS(ad7795, 24, 32);
-
-static const struct ad7793_chip_info ad7793_chip_info_tbl[] = {
-	[ID_AD7785] = {
-		.id = AD7785_ID,
-		.channels = ad7785_channels,
-		.num_channels = ARRAY_SIZE(ad7785_channels),
-	},
-	[ID_AD7792] = {
-		.id = AD7792_ID,
-		.channels = ad7792_channels,
-		.num_channels = ARRAY_SIZE(ad7792_channels),
-	},
-	[ID_AD7793] = {
-		.id = AD7793_ID,
-		.channels = ad7793_channels,
-		.num_channels = ARRAY_SIZE(ad7793_channels),
-	},
-	[ID_AD7794] = {
-		.id = AD7794_ID,
-		.channels = ad7794_channels,
-		.num_channels = ARRAY_SIZE(ad7794_channels),
-	},
-	[ID_AD7795] = {
-		.id = AD7795_ID,
-		.channels = ad7795_channels,
-		.num_channels = ARRAY_SIZE(ad7795_channels),
-	},
-};
-
-static int ad7793_probe(struct spi_device *spi)
-{
-	const struct ad7793_platform_data *pdata = spi->dev.platform_data;
-	struct ad7793_state *st;
-	struct iio_dev *indio_dev;
-	int ret, vref_mv = 0;
-
-	if (!pdata) {
-		dev_err(&spi->dev, "no platform data?\n");
-		return -ENODEV;
-	}
-
-	if (!spi->irq) {
-		dev_err(&spi->dev, "no IRQ?\n");
-		return -ENODEV;
-	}
-
-	indio_dev = iio_device_alloc(sizeof(*st));
-	if (indio_dev == NULL)
-		return -ENOMEM;
-
-	st = iio_priv(indio_dev);
-
-	ad_sd_init(&st->sd, indio_dev, spi, &ad7793_sigma_delta_info);
-
-	if (pdata->refsel != AD7793_REFSEL_INTERNAL) {
-		st->reg = regulator_get(&spi->dev, "refin");
-		if (IS_ERR(st->reg)) {
-			ret = PTR_ERR(st->reg);
-			goto error_device_free;
-		}
-
-		ret = regulator_enable(st->reg);
-		if (ret)
-			goto error_put_reg;
-
-		vref_mv = regulator_get_voltage(st->reg);
-		if (vref_mv < 0) {
-			ret = vref_mv;
-			goto error_disable_reg;
-		}
-
-		vref_mv /= 1000;
-	} else {
-		vref_mv = 1170; /* Build-in ref */
-	}
-
-	st->chip_info =
-		&ad7793_chip_info_tbl[spi_get_device_id(spi)->driver_data];
-
-	spi_set_drvdata(spi, indio_dev);
-
-	indio_dev->dev.parent = &spi->dev;
-	indio_dev->name = spi_get_device_id(spi)->name;
-	indio_dev->modes = INDIO_DIRECT_MODE;
-	indio_dev->channels = st->chip_info->channels;
-	indio_dev->num_channels = st->chip_info->num_channels;
-	indio_dev->info = &ad7793_info;
-
-	ret = ad_sd_setup_buffer_and_trigger(indio_dev);
-	if (ret)
-		goto error_disable_reg;
-
-	ret = ad7793_setup(indio_dev, pdata, vref_mv);
-	if (ret)
-		goto error_remove_trigger;
-
-	ret = iio_device_register(indio_dev);
-	if (ret)
-		goto error_remove_trigger;
-
-	return 0;
-
-error_remove_trigger:
-	ad_sd_cleanup_buffer_and_trigger(indio_dev);
-error_disable_reg:
-	if (pdata->refsel != AD7793_REFSEL_INTERNAL)
-		regulator_disable(st->reg);
-error_put_reg:
-	if (pdata->refsel != AD7793_REFSEL_INTERNAL)
-		regulator_put(st->reg);
-error_device_free:
-	iio_device_free(indio_dev);
-
-	return ret;
-}
-
-static int ad7793_remove(struct spi_device *spi)
-{
-	const struct ad7793_platform_data *pdata = spi->dev.platform_data;
-	struct iio_dev *indio_dev = spi_get_drvdata(spi);
-	struct ad7793_state *st = iio_priv(indio_dev);
-
-	iio_device_unregister(indio_dev);
-	ad_sd_cleanup_buffer_and_trigger(indio_dev);
-
-	if (pdata->refsel != AD7793_REFSEL_INTERNAL) {
-		regulator_disable(st->reg);
-		regulator_put(st->reg);
-	}
-
-	iio_device_free(indio_dev);
-
-	return 0;
-}
-
-static const struct spi_device_id ad7793_id[] = {
-	{"ad7785", ID_AD7785},
-	{"ad7792", ID_AD7792},
-	{"ad7793", ID_AD7793},
-	{"ad7794", ID_AD7794},
-	{"ad7795", ID_AD7795},
-	{}
-};
-MODULE_DEVICE_TABLE(spi, ad7793_id);
-
-static struct spi_driver ad7793_driver = {
-	.driver = {
-		.name	= "ad7793",
-		.owner	= THIS_MODULE,
-	},
-	.probe		= ad7793_probe,
-	.remove		= ad7793_remove,
-	.id_table	= ad7793_id,
-};
-module_spi_driver(ad7793_driver);
-
-MODULE_AUTHOR("Michael Hennerich <hennerich@blackfin.uclinux.org>");
-MODULE_DESCRIPTION("Analog Devices AD7793 and simialr ADCs");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/staging/iio/adc/ad7793.h b/drivers/staging/iio/adc/ad7793.h
deleted file mode 100644
index 0e455de215e4..000000000000
--- a/drivers/staging/iio/adc/ad7793.h
+++ /dev/null
@@ -1,116 +0,0 @@
-/*
- * AD7792/AD7793 SPI ADC driver
- *
- * Copyright 2011 Analog Devices Inc.
- *
- * Licensed under the GPL-2.
- */
-#ifndef IIO_ADC_AD7793_H_
-#define IIO_ADC_AD7793_H_
-
-/*
- * TODO: struct ad7793_platform_data needs to go into include/linux/iio
- */
-
-/**
- * enum ad7793_clock_source - AD7793 clock source selection
- * @AD7793_CLK_SRC_INT: Internal 64 kHz clock, not available at the CLK pin.
- * @AD7793_CLK_SRC_INT_CO: Internal 64 kHz clock, available at the CLK pin.
- * @AD7793_CLK_SRC_EXT: Use external clock.
- * @AD7793_CLK_SRC_EXT_DIV2: Use external clock divided by 2.
- */
-enum ad7793_clock_source {
-	AD7793_CLK_SRC_INT,
-	AD7793_CLK_SRC_INT_CO,
-	AD7793_CLK_SRC_EXT,
-	AD7793_CLK_SRC_EXT_DIV2,
-};
-
-/**
- * enum ad7793_bias_voltage - AD7793 bias voltage selection
- * @AD7793_BIAS_VOLTAGE_DISABLED: Bias voltage generator disabled
- * @AD7793_BIAS_VOLTAGE_AIN1: Bias voltage connected to AIN1(-).
- * @AD7793_BIAS_VOLTAGE_AIN2: Bias voltage connected to AIN2(-).
- * @AD7793_BIAS_VOLTAGE_AIN3: Bias voltage connected to AIN3(-).
- *	Only valid for AD7795/AD7796.
- */
-enum ad7793_bias_voltage {
-	AD7793_BIAS_VOLTAGE_DISABLED,
-	AD7793_BIAS_VOLTAGE_AIN1,
-	AD7793_BIAS_VOLTAGE_AIN2,
-	AD7793_BIAS_VOLTAGE_AIN3,
-};
-
-/**
- * enum ad7793_refsel - AD7793 reference voltage selection
- * @AD7793_REFSEL_REFIN1: External reference applied between REFIN1(+)
- *	and REFIN1(-).
- * @AD7793_REFSEL_REFIN2: External reference applied between REFIN2(+) and
- *	and REFIN1(-). Only valid for AD7795/AD7796.
- * @AD7793_REFSEL_INTERNAL: Internal 1.17 V reference.
- */
-enum ad7793_refsel {
-	AD7793_REFSEL_REFIN1 = 0,
-	AD7793_REFSEL_REFIN2 = 1,
-	AD7793_REFSEL_INTERNAL = 2,
-};
-
-/**
- * enum ad7793_current_source_direction - AD7793 excitation current direction
- * @AD7793_IEXEC1_IOUT1_IEXEC2_IOUT2: Current source IEXC1 connected to pin
- *	IOUT1, current source IEXC2 connected to pin IOUT2.
- * @AD7793_IEXEC1_IOUT2_IEXEC2_IOUT1: Current source IEXC2 connected to pin
- *	IOUT1, current source IEXC1 connected to pin IOUT2.
- * @AD7793_IEXEC1_IEXEC2_IOUT1: Both current sources connected to pin IOUT1.
- *	Only valid when the current sources are set to 10 uA or 210 uA.
- * @AD7793_IEXEC1_IEXEC2_IOUT2: Both current sources connected to Pin IOUT2.
- *	Only valid when the current ources are set to 10 uA or 210 uA.
- */
-enum ad7793_current_source_direction {
-	AD7793_IEXEC1_IOUT1_IEXEC2_IOUT2 = 0,
-	AD7793_IEXEC1_IOUT2_IEXEC2_IOUT1 = 1,
-	AD7793_IEXEC1_IEXEC2_IOUT1 = 2,
-	AD7793_IEXEC1_IEXEC2_IOUT2 = 3,
-};
-
-/**
- * enum ad7793_excitation_current - AD7793 excitation current selection
- * @AD7793_IX_DISABLED: Excitation current Disabled.
- * @AD7793_IX_10uA: Enable 10 micro-ampere excitation current.
- * @AD7793_IX_210uA: Enable 210 micro-ampere excitation current.
- * @AD7793_IX_1mA: Enable 1 milli-Ampere excitation current.
- */
-enum ad7793_excitation_current {
-	AD7793_IX_DISABLED = 0,
-	AD7793_IX_10uA = 1,
-	AD7793_IX_210uA = 2,
-	AD7793_IX_1mA = 3,
-};
-
-/**
- * struct ad7793_platform_data - AD7793 platform data
- * @clock_src: Clock source selection
- * @burnout_current: If set to true the 100nA burnout current is enabled.
- * @boost_enable: Enable boost for the bias voltage generator.
- * @buffered: If set to true configure the device for buffered input mode.
- * @unipolar: If set to true sample in unipolar mode, if set to false sample in
- *		bipolar mode.
- * @refsel: Reference voltage selection
- * @bias_voltage: Bias voltage selection
- * @exitation_current: Excitation current selection
- * @current_source_direction: Excitation current direction selection
- */
-struct ad7793_platform_data {
-	enum ad7793_clock_source clock_src;
-	bool burnout_current;
-	bool boost_enable;
-	bool buffered;
-	bool unipolar;
-
-	enum ad7793_refsel refsel;
-	enum ad7793_bias_voltage bias_voltage;
-	enum ad7793_excitation_current exitation_current;
-	enum ad7793_current_source_direction current_source_direction;
-};
-
-#endif /* IIO_ADC_AD7793_H_ */
diff --git a/include/linux/platform_data/ad7793.h b/include/linux/platform_data/ad7793.h
new file mode 100644
index 000000000000..7ea6751aae6d
--- /dev/null
+++ b/include/linux/platform_data/ad7793.h
@@ -0,0 +1,112 @@
+/*
+ * AD7792/AD7793 SPI ADC driver
+ *
+ * Copyright 2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2.
+ */
+#ifndef __LINUX_PLATFORM_DATA_AD7793_H__
+#define __LINUX_PLATFORM_DATA_AD7793_H__
+
+/**
+ * enum ad7793_clock_source - AD7793 clock source selection
+ * @AD7793_CLK_SRC_INT: Internal 64 kHz clock, not available at the CLK pin.
+ * @AD7793_CLK_SRC_INT_CO: Internal 64 kHz clock, available at the CLK pin.
+ * @AD7793_CLK_SRC_EXT: Use external clock.
+ * @AD7793_CLK_SRC_EXT_DIV2: Use external clock divided by 2.
+ */
+enum ad7793_clock_source {
+	AD7793_CLK_SRC_INT,
+	AD7793_CLK_SRC_INT_CO,
+	AD7793_CLK_SRC_EXT,
+	AD7793_CLK_SRC_EXT_DIV2,
+};
+
+/**
+ * enum ad7793_bias_voltage - AD7793 bias voltage selection
+ * @AD7793_BIAS_VOLTAGE_DISABLED: Bias voltage generator disabled
+ * @AD7793_BIAS_VOLTAGE_AIN1: Bias voltage connected to AIN1(-).
+ * @AD7793_BIAS_VOLTAGE_AIN2: Bias voltage connected to AIN2(-).
+ * @AD7793_BIAS_VOLTAGE_AIN3: Bias voltage connected to AIN3(-).
+ *	Only valid for AD7795/AD7796.
+ */
+enum ad7793_bias_voltage {
+	AD7793_BIAS_VOLTAGE_DISABLED,
+	AD7793_BIAS_VOLTAGE_AIN1,
+	AD7793_BIAS_VOLTAGE_AIN2,
+	AD7793_BIAS_VOLTAGE_AIN3,
+};
+
+/**
+ * enum ad7793_refsel - AD7793 reference voltage selection
+ * @AD7793_REFSEL_REFIN1: External reference applied between REFIN1(+)
+ *	and REFIN1(-).
+ * @AD7793_REFSEL_REFIN2: External reference applied between REFIN2(+) and
+ *	and REFIN1(-). Only valid for AD7795/AD7796.
+ * @AD7793_REFSEL_INTERNAL: Internal 1.17 V reference.
+ */
+enum ad7793_refsel {
+	AD7793_REFSEL_REFIN1 = 0,
+	AD7793_REFSEL_REFIN2 = 1,
+	AD7793_REFSEL_INTERNAL = 2,
+};
+
+/**
+ * enum ad7793_current_source_direction - AD7793 excitation current direction
+ * @AD7793_IEXEC1_IOUT1_IEXEC2_IOUT2: Current source IEXC1 connected to pin
+ *	IOUT1, current source IEXC2 connected to pin IOUT2.
+ * @AD7793_IEXEC1_IOUT2_IEXEC2_IOUT1: Current source IEXC2 connected to pin
+ *	IOUT1, current source IEXC1 connected to pin IOUT2.
+ * @AD7793_IEXEC1_IEXEC2_IOUT1: Both current sources connected to pin IOUT1.
+ *	Only valid when the current sources are set to 10 uA or 210 uA.
+ * @AD7793_IEXEC1_IEXEC2_IOUT2: Both current sources connected to Pin IOUT2.
+ *	Only valid when the current ources are set to 10 uA or 210 uA.
+ */
+enum ad7793_current_source_direction {
+	AD7793_IEXEC1_IOUT1_IEXEC2_IOUT2 = 0,
+	AD7793_IEXEC1_IOUT2_IEXEC2_IOUT1 = 1,
+	AD7793_IEXEC1_IEXEC2_IOUT1 = 2,
+	AD7793_IEXEC1_IEXEC2_IOUT2 = 3,
+};
+
+/**
+ * enum ad7793_excitation_current - AD7793 excitation current selection
+ * @AD7793_IX_DISABLED: Excitation current Disabled.
+ * @AD7793_IX_10uA: Enable 10 micro-ampere excitation current.
+ * @AD7793_IX_210uA: Enable 210 micro-ampere excitation current.
+ * @AD7793_IX_1mA: Enable 1 milli-Ampere excitation current.
+ */
+enum ad7793_excitation_current {
+	AD7793_IX_DISABLED = 0,
+	AD7793_IX_10uA = 1,
+	AD7793_IX_210uA = 2,
+	AD7793_IX_1mA = 3,
+};
+
+/**
+ * struct ad7793_platform_data - AD7793 platform data
+ * @clock_src: Clock source selection
+ * @burnout_current: If set to true the 100nA burnout current is enabled.
+ * @boost_enable: Enable boost for the bias voltage generator.
+ * @buffered: If set to true configure the device for buffered input mode.
+ * @unipolar: If set to true sample in unipolar mode, if set to false sample in
+ *		bipolar mode.
+ * @refsel: Reference voltage selection
+ * @bias_voltage: Bias voltage selection
+ * @exitation_current: Excitation current selection
+ * @current_source_direction: Excitation current direction selection
+ */
+struct ad7793_platform_data {
+	enum ad7793_clock_source clock_src;
+	bool burnout_current;
+	bool boost_enable;
+	bool buffered;
+	bool unipolar;
+
+	enum ad7793_refsel refsel;
+	enum ad7793_bias_voltage bias_voltage;
+	enum ad7793_excitation_current exitation_current;
+	enum ad7793_current_source_direction current_source_direction;
+};
+
+#endif /* IIO_ADC_AD7793_H_ */
-- 
cgit v1.2.3-55-g7522


From cd24834130ac655d15accee6757e0eaeab4ad4ef Mon Sep 17 00:00:00 2001
From: Jan Glauber
Date: Thu, 29 Nov 2012 12:50:30 +0100
Subject: s390/pci: base support

Add PCI support for s390, (only 64 bit mode is supported by hardware):
- PCI facility tests
- PCI instructions: pcilg, pcistg, pcistb, stpcifc, mpcifc, rpcit
- map readb/w/l/q and writeb/w/l/q to pcilg and pcistg instructions
- pci_iomap implementation
- memcpy_fromio/toio
- pci_root_ops using special pcilg/pcistg
- device, bus and domain allocation

Signed-off-by: Jan Glauber <jang@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kbuild                 |   1 +
 arch/s390/include/asm/io.h       |  55 +++-
 arch/s390/include/asm/pci.h      |  82 +++++-
 arch/s390/include/asm/pci_insn.h | 280 ++++++++++++++++++++
 arch/s390/include/asm/pci_io.h   | 194 ++++++++++++++
 arch/s390/kernel/dis.c           |  15 ++
 arch/s390/pci/Makefile           |   5 +
 arch/s390/pci/pci.c              | 557 +++++++++++++++++++++++++++++++++++++++
 include/asm-generic/io.h         |  21 +-
 9 files changed, 1201 insertions(+), 9 deletions(-)
 create mode 100644 arch/s390/include/asm/pci_insn.h
 create mode 100644 arch/s390/include/asm/pci_io.h
 create mode 100644 arch/s390/pci/Makefile
 create mode 100644 arch/s390/pci/pci.c

(limited to 'include')

diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild
index cc45d25487b0..647c3eccc3d0 100644
--- a/arch/s390/Kbuild
+++ b/arch/s390/Kbuild
@@ -6,3 +6,4 @@ obj-$(CONFIG_S390_HYPFS_FS)	+= hypfs/
 obj-$(CONFIG_APPLDATA_BASE)	+= appldata/
 obj-$(CONFIG_MATHEMU)		+= math-emu/
 obj-y				+= net/
+obj-$(CONFIG_PCI)		+= pci/
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index 559e921a6bba..16c3eb164f4f 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -9,9 +9,9 @@
 #ifndef _S390_IO_H
 #define _S390_IO_H
 
+#include <linux/kernel.h>
 #include <asm/page.h>
-
-#define IO_SPACE_LIMIT 0xffffffff
+#include <asm/pci_io.h>
 
 /*
  * Change virtual addresses to physical addresses and vv.
@@ -24,10 +24,11 @@ static inline unsigned long virt_to_phys(volatile void * address)
 		 "	lra	%0,0(%1)\n"
 		 "	jz	0f\n"
 		 "	la	%0,0\n"
-                 "0:"
+		 "0:"
 		 : "=a" (real_address) : "a" (address) : "cc");
-        return real_address;
+	return real_address;
 }
+#define virt_to_phys virt_to_phys
 
 static inline void * phys_to_virt(unsigned long address)
 {
@@ -42,4 +43,50 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
  */
 #define xlate_dev_kmem_ptr(p)	p
 
+#define IO_SPACE_LIMIT 0
+
+#ifdef CONFIG_PCI
+
+#define ioremap_nocache(addr, size)	ioremap(addr, size)
+#define ioremap_wc			ioremap_nocache
+
+/* TODO: s390 cannot support io_remap_pfn_range... */
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) 	       \
+	remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
+{
+	return (void __iomem *) offset;
+}
+
+static inline void iounmap(volatile void __iomem *addr)
+{
+}
+
+/*
+ * s390 needs a private implementation of pci_iomap since ioremap with its
+ * offset parameter isn't sufficient. That's because BAR spaces are not
+ * disjunctive on s390 so we need the bar parameter of pci_iomap to find
+ * the corresponding device and create the mapping cookie.
+ */
+#define pci_iomap pci_iomap
+#define pci_iounmap pci_iounmap
+
+#define memcpy_fromio(dst, src, count)	zpci_memcpy_fromio(dst, src, count)
+#define memcpy_toio(dst, src, count)	zpci_memcpy_toio(dst, src, count)
+#define memset_io(dst, val, count)	zpci_memset_io(dst, val, count)
+
+#define __raw_readb	zpci_read_u8
+#define __raw_readw	zpci_read_u16
+#define __raw_readl	zpci_read_u32
+#define __raw_readq	zpci_read_u64
+#define __raw_writeb	zpci_write_u8
+#define __raw_writew	zpci_write_u16
+#define __raw_writel	zpci_write_u32
+#define __raw_writeq	zpci_write_u64
+
+#endif /* CONFIG_PCI */
+
+#include <asm-generic/io.h>
+
 #endif
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 42a145c9ddd6..ff7b3596f47c 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -1,10 +1,84 @@
 #ifndef __ASM_S390_PCI_H
 #define __ASM_S390_PCI_H
 
-/* S/390 systems don't have a PCI bus. This file is just here because some stupid .c code
- * includes it even if CONFIG_PCI is not set.
- */
+/* must be set before including asm-generic/pci.h */
 #define PCI_DMA_BUS_IS_PHYS (0)
+/* must be set before including pci_clp.h */
+#define PCI_BAR_COUNT	6
 
-#endif /* __ASM_S390_PCI_H */
+#include <asm-generic/pci.h>
+#include <asm-generic/pci-dma-compat.h>
 
+#define PCIBIOS_MIN_IO		0x1000
+#define PCIBIOS_MIN_MEM		0x10000000
+
+#define pcibios_assign_all_busses()	(0)
+
+void __iomem *pci_iomap(struct pci_dev *, int, unsigned long);
+void pci_iounmap(struct pci_dev *, void __iomem *);
+int pci_domain_nr(struct pci_bus *);
+int pci_proc_domain(struct pci_bus *);
+
+#define ZPCI_BUS_NR			0	/* default bus number */
+#define ZPCI_DEVFN			0	/* default device number */
+
+/* PCI Function Controls */
+#define ZPCI_FC_FN_ENABLED		0x80
+#define ZPCI_FC_ERROR			0x40
+#define ZPCI_FC_BLOCKED			0x20
+#define ZPCI_FC_DMA_ENABLED		0x10
+
+enum zpci_state {
+	ZPCI_FN_STATE_RESERVED,
+	ZPCI_FN_STATE_STANDBY,
+	ZPCI_FN_STATE_CONFIGURED,
+	ZPCI_FN_STATE_ONLINE,
+	NR_ZPCI_FN_STATES,
+};
+
+struct zpci_bar_struct {
+	u32		val;		/* bar start & 3 flag bits */
+	u8		size;		/* order 2 exponent */
+	u16		map_idx;	/* index into bar mapping array */
+};
+
+/* Private data per function */
+struct zpci_dev {
+	struct pci_dev	*pdev;
+	struct pci_bus	*bus;
+	struct list_head entry;		/* list of all zpci_devices, needed for hotplug, etc. */
+
+	enum zpci_state state;
+	u32		fid;		/* function ID, used by sclp */
+	u32		fh;		/* function handle, used by insn's */
+	u16		pchid;		/* physical channel ID */
+	u8		pfgid;		/* function group ID */
+	u16		domain;
+
+	struct zpci_bar_struct bars[PCI_BAR_COUNT];
+
+	enum pci_bus_speed max_bus_speed;
+};
+
+static inline bool zdev_enabled(struct zpci_dev *zdev)
+{
+	return (zdev->fh & (1UL << 31)) ? true : false;
+}
+
+/* -----------------------------------------------------------------------------
+  Prototypes
+----------------------------------------------------------------------------- */
+/* Base stuff */
+struct zpci_dev *zpci_alloc_device(void);
+int zpci_create_device(struct zpci_dev *);
+int zpci_enable_device(struct zpci_dev *);
+void zpci_stop_device(struct zpci_dev *);
+void zpci_free_device(struct zpci_dev *);
+int zpci_scan_device(struct zpci_dev *);
+
+/* Helpers */
+struct zpci_dev *get_zdev(struct pci_dev *);
+struct zpci_dev *get_zdev_by_fid(u32);
+bool zpci_fid_present(u32);
+
+#endif
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
new file mode 100644
index 000000000000..15b88b908e8c
--- /dev/null
+++ b/arch/s390/include/asm/pci_insn.h
@@ -0,0 +1,280 @@
+#ifndef _ASM_S390_PCI_INSN_H
+#define _ASM_S390_PCI_INSN_H
+
+#include <linux/delay.h>
+
+#define ZPCI_INSN_BUSY_DELAY	1	/* 1 millisecond */
+
+/* Load/Store status codes */
+#define ZPCI_PCI_ST_FUNC_NOT_ENABLED		4
+#define ZPCI_PCI_ST_FUNC_IN_ERR			8
+#define ZPCI_PCI_ST_BLOCKED			12
+#define ZPCI_PCI_ST_INSUF_RES			16
+#define ZPCI_PCI_ST_INVAL_AS			20
+#define ZPCI_PCI_ST_FUNC_ALREADY_ENABLED	24
+#define ZPCI_PCI_ST_DMA_AS_NOT_ENABLED		28
+#define ZPCI_PCI_ST_2ND_OP_IN_INV_AS		36
+#define ZPCI_PCI_ST_FUNC_NOT_AVAIL		40
+#define ZPCI_PCI_ST_ALREADY_IN_RQ_STATE		44
+
+/* Load/Store return codes */
+#define ZPCI_PCI_LS_OK				0
+#define ZPCI_PCI_LS_ERR				1
+#define ZPCI_PCI_LS_BUSY			2
+#define ZPCI_PCI_LS_INVAL_HANDLE		3
+
+/* Load/Store address space identifiers */
+#define ZPCI_PCIAS_MEMIO_0			0
+#define ZPCI_PCIAS_MEMIO_1			1
+#define ZPCI_PCIAS_MEMIO_2			2
+#define ZPCI_PCIAS_MEMIO_3			3
+#define ZPCI_PCIAS_MEMIO_4			4
+#define ZPCI_PCIAS_MEMIO_5			5
+#define ZPCI_PCIAS_CFGSPC			15
+
+/* Modify PCI Function Controls */
+#define ZPCI_MOD_FC_REG_INT	2
+#define ZPCI_MOD_FC_DEREG_INT	3
+#define ZPCI_MOD_FC_REG_IOAT	4
+#define ZPCI_MOD_FC_DEREG_IOAT	5
+#define ZPCI_MOD_FC_REREG_IOAT	6
+#define ZPCI_MOD_FC_RESET_ERROR	7
+#define ZPCI_MOD_FC_RESET_BLOCK	9
+#define ZPCI_MOD_FC_SET_MEASURE	10
+
+/* FIB function controls */
+#define ZPCI_FIB_FC_ENABLED	0x80
+#define ZPCI_FIB_FC_ERROR	0x40
+#define ZPCI_FIB_FC_LS_BLOCKED	0x20
+#define ZPCI_FIB_FC_DMAAS_REG	0x10
+
+/* FIB function controls */
+#define ZPCI_FIB_FC_ENABLED	0x80
+#define ZPCI_FIB_FC_ERROR	0x40
+#define ZPCI_FIB_FC_LS_BLOCKED	0x20
+#define ZPCI_FIB_FC_DMAAS_REG	0x10
+
+/* Function Information Block */
+struct zpci_fib {
+	u32 fmt		:  8;	/* format */
+	u32		: 24;
+	u32 reserved1;
+	u8 fc;			/* function controls */
+	u8 reserved2;
+	u16 reserved3;
+	u32 reserved4;
+	u64 pba;		/* PCI base address */
+	u64 pal;		/* PCI address limit */
+	u64 iota;		/* I/O Translation Anchor */
+	u32		:  1;
+	u32 isc		:  3;	/* Interrupt subclass */
+	u32 noi		: 12;	/* Number of interrupts */
+	u32		:  2;
+	u32 aibvo	:  6;	/* Adapter interrupt bit vector offset */
+	u32 sum		:  1;	/* Adapter int summary bit enabled */
+	u32		:  1;
+	u32 aisbo	:  6;	/* Adapter int summary bit offset */
+	u32 reserved5;
+	u64 aibv;		/* Adapter int bit vector address */
+	u64 aisb;		/* Adapter int summary bit address */
+	u64 fmb_addr;		/* Function measurement block address and key */
+	u64 reserved6;
+	u64 reserved7;
+} __packed;
+
+/* Modify PCI Function Controls */
+static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status)
+{
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rxy,0xe300000000d0,%[req],%[fib]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib)
+		: : "cc");
+	*status = req >> 24 & 0xff;
+	return cc;
+}
+
+static inline int mpcifc_instr(u64 req, struct zpci_fib *fib)
+{
+	u8 cc, status;
+
+	do {
+		cc = __mpcifc(req, fib, &status);
+		if (cc == 2)
+			msleep(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d\n",
+			     __func__, cc, status);
+	return (cc) ? -EIO : 0;
+}
+
+/* Refresh PCI Translations */
+static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status)
+{
+	register u64 __addr asm("2") = addr;
+	register u64 __range asm("3") = range;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rre,0xb9d30000,%[fn],%[addr]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [fn] "+d" (fn)
+		: [addr] "d" (__addr), "d" (__range)
+		: "cc");
+	*status = fn >> 24 & 0xff;
+	return cc;
+}
+
+static inline int rpcit_instr(u64 fn, u64 addr, u64 range)
+{
+	u8 cc, status;
+
+	do {
+		cc = __rpcit(fn, addr, range, &status);
+		if (cc == 2)
+			msleep(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  dma_addr: %Lx  size: %Lx\n",
+			    __func__, cc, status, addr, range);
+	return (cc) ? -EIO : 0;
+}
+
+/* Store PCI function controls */
+static inline u8 __stpcifc(u32 handle, u8 space, struct zpci_fib *fib, u8 *status)
+{
+	u64 fn = (u64) handle << 32 | space << 16;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rxy,0xe300000000d4,%[fn],%[fib]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [fn] "+d" (fn), [fib] "=m" (*fib)
+		: : "cc");
+	*status = fn >> 24 & 0xff;
+	return cc;
+}
+
+/* Set Interruption Controls */
+static inline void sic_instr(u16 ctl, char *unused, u8 isc)
+{
+	asm volatile (
+		"	.insn	rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n"
+		: : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused));
+}
+
+/* PCI Load */
+static inline u8 __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
+{
+	register u64 __req asm("2") = req;
+	register u64 __offset asm("3") = offset;
+	u64 __data;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rre,0xb9d20000,%[data],%[req]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [data] "=d" (__data), [req] "+d" (__req)
+		:  "d" (__offset)
+		: "cc");
+	*status = __req >> 24 & 0xff;
+	*data = __data;
+	return cc;
+}
+
+static inline int pcilg_instr(u64 *data, u64 req, u64 offset)
+{
+	u8 cc, status;
+
+	do {
+		cc = __pcilg(data, req, offset, &status);
+		if (cc == 2)
+			msleep(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc) {
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+			    __func__, cc, status, req, offset);
+		/* TODO: on IO errors set data to 0xff...
+		 * here or in users of pcilg (le conversion)?
+		 */
+	}
+	return (cc) ? -EIO : 0;
+}
+
+/* PCI Store */
+static inline u8 __pcistg(u64 data, u64 req, u64 offset, u8 *status)
+{
+	register u64 __req asm("2") = req;
+	register u64 __offset asm("3") = offset;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rre,0xb9d00000,%[data],%[req]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [req] "+d" (__req)
+		: "d" (__offset), [data] "d" (data)
+		: "cc");
+	*status = __req >> 24 & 0xff;
+	return cc;
+}
+
+static inline int pcistg_instr(u64 data, u64 req, u64 offset)
+{
+	u8 cc, status;
+
+	do {
+		cc = __pcistg(data, req, offset, &status);
+		if (cc == 2)
+			msleep(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+			__func__, cc, status, req, offset);
+	return (cc) ? -EIO : 0;
+}
+
+/* PCI Store Block */
+static inline u8 __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
+{
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rsy,0xeb00000000d0,%[req],%[offset],%[data]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [req] "+d" (req)
+		: [offset] "d" (offset), [data] "Q" (*data)
+		: "cc");
+	*status = req >> 24 & 0xff;
+	return cc;
+}
+
+static inline int pcistb_instr(const u64 *data, u64 req, u64 offset)
+{
+	u8 cc, status;
+
+	do {
+		cc = __pcistb(data, req, offset, &status);
+		if (cc == 2)
+			msleep(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+			    __func__, cc, status, req, offset);
+	return (cc) ? -EIO : 0;
+}
+
+#endif
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
new file mode 100644
index 000000000000..5fd81f31d6c7
--- /dev/null
+++ b/arch/s390/include/asm/pci_io.h
@@ -0,0 +1,194 @@
+#ifndef _ASM_S390_PCI_IO_H
+#define _ASM_S390_PCI_IO_H
+
+#ifdef CONFIG_PCI
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <asm/pci_insn.h>
+
+/* I/O Map */
+#define ZPCI_IOMAP_MAX_ENTRIES		0x7fff
+#define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000ULL
+#define ZPCI_IOMAP_ADDR_IDX_MASK	0x7fff000000000000ULL
+#define ZPCI_IOMAP_ADDR_OFF_MASK	0x0000ffffffffffffULL
+
+struct zpci_iomap_entry {
+	u32 fh;
+	u8 bar;
+};
+
+extern struct zpci_iomap_entry *zpci_iomap_start;
+
+#define ZPCI_IDX(addr)								\
+	(((__force u64) addr & ZPCI_IOMAP_ADDR_IDX_MASK) >> 48)
+#define ZPCI_OFFSET(addr)							\
+	((__force u64) addr & ZPCI_IOMAP_ADDR_OFF_MASK)
+
+#define ZPCI_CREATE_REQ(handle, space, len)					\
+	((u64) handle << 32 | space << 16 | len)
+
+#define zpci_read(LENGTH, RETTYPE)						\
+static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr)	\
+{										\
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];	\
+	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);		\
+	u64 data;								\
+	int rc;									\
+										\
+	rc = pcilg_instr(&data, req, ZPCI_OFFSET(addr));			\
+	if (rc)									\
+		data = -1ULL;							\
+	return (RETTYPE) data;							\
+}
+
+#define zpci_write(LENGTH, VALTYPE)						\
+static inline void zpci_write_##VALTYPE(VALTYPE val,				\
+					const volatile void __iomem *addr)	\
+{										\
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];	\
+	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);		\
+	u64 data = (VALTYPE) val;						\
+										\
+	pcistg_instr(data, req, ZPCI_OFFSET(addr));				\
+}
+
+zpci_read(8, u64)
+zpci_read(4, u32)
+zpci_read(2, u16)
+zpci_read(1, u8)
+zpci_write(8, u64)
+zpci_write(4, u32)
+zpci_write(2, u16)
+zpci_write(1, u8)
+
+static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len)
+{
+	u64 val;
+
+	switch (len) {
+	case 1:
+		val = (u64) *((u8 *) data);
+		break;
+	case 2:
+		val = (u64) *((u16 *) data);
+		break;
+	case 4:
+		val = (u64) *((u32 *) data);
+		break;
+	case 8:
+		val = (u64) *((u64 *) data);
+		break;
+	default:
+		val = 0;		/* let FW report error */
+		break;
+	}
+	return pcistg_instr(val, req, offset);
+}
+
+static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
+{
+	u64 data;
+	u8 cc;
+
+	cc = pcilg_instr(&data,	 req, offset);
+	switch (len) {
+	case 1:
+		*((u8 *) dst) = (u8) data;
+		break;
+	case 2:
+		*((u16 *) dst) = (u16) data;
+		break;
+	case 4:
+		*((u32 *) dst) = (u32) data;
+		break;
+	case 8:
+		*((u64 *) dst) = (u64) data;
+		break;
+	}
+	return cc;
+}
+
+static inline int zpci_write_block(u64 req, const u64 *data, u64 offset)
+{
+	return pcistb_instr(data, req, offset);
+}
+
+static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
+{
+	int count = len > max ? max : len, size = 1;
+
+	while (!(src & 0x1) && !(dst & 0x1) && ((size << 1) <= count)) {
+		dst = dst >> 1;
+		src = src >> 1;
+		size = size << 1;
+	}
+	return size;
+}
+
+static inline int zpci_memcpy_fromio(void *dst,
+				     const volatile void __iomem *src,
+				     unsigned long n)
+{
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(src)];
+	u64 req, offset = ZPCI_OFFSET(src);
+	int size, rc = 0;
+
+	while (n > 0) {
+		size = zpci_get_max_write_size((u64) src, (u64) dst, n, 8);
+		req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size);
+		rc = zpci_read_single(req, dst, offset, size);
+		if (rc)
+			break;
+		offset += size;
+		dst += size;
+		n -= size;
+	}
+	return rc;
+}
+
+static inline int zpci_memcpy_toio(volatile void __iomem *dst,
+				   const void *src, unsigned long n)
+{
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(dst)];
+	u64 req, offset = ZPCI_OFFSET(dst);
+	int size, rc = 0;
+
+	if (!src)
+		return -EINVAL;
+
+	while (n > 0) {
+		size = zpci_get_max_write_size((u64) dst, (u64) src, n, 128);
+		req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size);
+
+		if (size > 8) /* main path */
+			rc = zpci_write_block(req, src, offset);
+		else
+			rc = zpci_write_single(req, src, offset, size);
+		if (rc)
+			break;
+		offset += size;
+		src += size;
+		n -= size;
+	}
+	return rc;
+}
+
+static inline int zpci_memset_io(volatile void __iomem *dst,
+				 unsigned char val, size_t count)
+{
+	u8 *src = kmalloc(count, GFP_KERNEL);
+	int rc;
+
+	if (src == NULL)
+		return -ENOMEM;
+	memset(src, val, count);
+
+	rc = zpci_memcpy_toio(dst, src, count);
+	kfree(src);
+	return rc;
+}
+
+#endif /* CONFIG_PCI */
+
+#endif /* _ASM_S390_PCI_IO_H */
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index afdb9729cf9b..a7f9abd98cf2 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -399,6 +399,10 @@ enum {
 	LONG_INSN_TABORT,
 	LONG_INSN_TBEGIN,
 	LONG_INSN_TBEGINC,
+	LONG_INSN_PCISTG,
+	LONG_INSN_MPCIFC,
+	LONG_INSN_STPCIFC,
+	LONG_INSN_PCISTB,
 };
 
 static char *long_insn_name[] = {
@@ -469,6 +473,10 @@ static char *long_insn_name[] = {
 	[LONG_INSN_TABORT] = "tabort",
 	[LONG_INSN_TBEGIN] = "tbegin",
 	[LONG_INSN_TBEGINC] = "tbeginc",
+	[LONG_INSN_PCISTG] = "pcistg",
+	[LONG_INSN_MPCIFC] = "mpcifc",
+	[LONG_INSN_STPCIFC] = "stpcifc",
+	[LONG_INSN_PCISTB] = "pcistb",
 };
 
 static struct insn opcode[] = {
@@ -1115,6 +1123,9 @@ static struct insn opcode_b9[] = {
 	{ { 0, LONG_INSN_SLHHHR }, 0xcb, INSTR_RRF_R0RR2 },
 	{ "chhr", 0xcd, INSTR_RRE_RR },
 	{ "clhhr", 0xcf, INSTR_RRE_RR },
+	{ { 0, LONG_INSN_PCISTG }, 0xd0, INSTR_RRE_RR },
+	{ "pcilg", 0xd2, INSTR_RRE_RR },
+	{ "rpcit", 0xd3, INSTR_RRE_RR },
 	{ "ahhlr", 0xd8, INSTR_RRF_R0RR2 },
 	{ "shhlr", 0xd9, INSTR_RRF_R0RR2 },
 	{ { 0, LONG_INSN_ALHHLR }, 0xda, INSTR_RRF_R0RR2 },
@@ -1346,6 +1357,8 @@ static struct insn opcode_e3[] = {
 	{ "stfh", 0xcb, INSTR_RXY_RRRD },
 	{ "chf", 0xcd, INSTR_RXY_RRRD },
 	{ "clhf", 0xcf, INSTR_RXY_RRRD },
+	{ { 0, LONG_INSN_MPCIFC }, 0xd0, INSTR_RXY_RRRD },
+	{ { 0, LONG_INSN_STPCIFC }, 0xd4, INSTR_RXY_RRRD },
 #endif
 	{ "lrv", 0x1e, INSTR_RXY_RRRD },
 	{ "lrvh", 0x1f, INSTR_RXY_RRRD },
@@ -1423,6 +1436,8 @@ static struct insn opcode_eb[] = {
 	{ "lmy", 0x98, INSTR_RSY_RRRD },
 	{ "lamy", 0x9a, INSTR_RSY_AARD },
 	{ "stamy", 0x9b, INSTR_RSY_AARD },
+	{ { 0, LONG_INSN_PCISTB }, 0xd0, INSTR_RSY_RRRD },
+	{ "sic", 0xd1, INSTR_RSY_RRRD },
 	{ "srak", 0xdc, INSTR_RSY_RRRD },
 	{ "slak", 0xdd, INSTR_RSY_RRRD },
 	{ "srlk", 0xde, INSTR_RSY_RRRD },
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
new file mode 100644
index 000000000000..78a1344ff7b1
--- /dev/null
+++ b/arch/s390/pci/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the s390 PCI subsystem.
+#
+
+obj-$(CONFIG_PCI)	+= pci.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
new file mode 100644
index 000000000000..0b80ac7e158f
--- /dev/null
+++ b/arch/s390/pci/pci.c
@@ -0,0 +1,557 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ *
+ * The System z PCI code is a rewrite from a prototype by
+ * the following people (Kudoz!):
+ *   Alexander Schmidt <alexschm@de.ibm.com>
+ *   Christoph Raisch <raisch@de.ibm.com>
+ *   Hannes Hering <hering2@de.ibm.com>
+ *   Hoang-Nam Nguyen <hnguyen@de.ibm.com>
+ *   Jan-Bernd Themann <themann@de.ibm.com>
+ *   Stefan Roscher <stefan.roscher@de.ibm.com>
+ *   Thomas Klein <tklein@de.ibm.com>
+ */
+
+#define COMPONENT "zPCI"
+#define pr_fmt(fmt) COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/delay.h>
+#include <linux/seq_file.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+
+#include <asm/facility.h>
+#include <asm/pci_insn.h>
+
+#define DEBUG				/* enable pr_debug */
+
+#define ZPCI_NR_DMA_SPACES		1
+#define ZPCI_NR_DEVICES			CONFIG_PCI_NR_FUNCTIONS
+
+/* list of all detected zpci devices */
+LIST_HEAD(zpci_list);
+DEFINE_MUTEX(zpci_list_lock);
+
+static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
+static DEFINE_SPINLOCK(zpci_domain_lock);
+
+/* I/O Map */
+static DEFINE_SPINLOCK(zpci_iomap_lock);
+static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
+struct zpci_iomap_entry *zpci_iomap_start;
+EXPORT_SYMBOL_GPL(zpci_iomap_start);
+
+struct zpci_dev *get_zdev(struct pci_dev *pdev)
+{
+	return (struct zpci_dev *) pdev->sysdata;
+}
+
+struct zpci_dev *get_zdev_by_fid(u32 fid)
+{
+	struct zpci_dev *tmp, *zdev = NULL;
+
+	mutex_lock(&zpci_list_lock);
+	list_for_each_entry(tmp, &zpci_list, entry) {
+		if (tmp->fid == fid) {
+			zdev = tmp;
+			break;
+		}
+	}
+	mutex_unlock(&zpci_list_lock);
+	return zdev;
+}
+
+bool zpci_fid_present(u32 fid)
+{
+	return (get_zdev_by_fid(fid) != NULL) ? true : false;
+}
+
+static struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus)
+{
+	return (bus && bus->sysdata) ? (struct zpci_dev *) bus->sysdata : NULL;
+}
+
+int pci_domain_nr(struct pci_bus *bus)
+{
+	return ((struct zpci_dev *) bus->sysdata)->domain;
+}
+EXPORT_SYMBOL_GPL(pci_domain_nr);
+
+int pci_proc_domain(struct pci_bus *bus)
+{
+	return pci_domain_nr(bus);
+}
+EXPORT_SYMBOL_GPL(pci_proc_domain);
+
+/* Store PCI function information block */
+static int zpci_store_fib(struct zpci_dev *zdev, u8 *fc)
+{
+	struct zpci_fib *fib;
+	u8 status, cc;
+
+	fib = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!fib)
+		return -ENOMEM;
+
+	do {
+		cc = __stpcifc(zdev->fh, 0, fib, &status);
+		if (cc == 2) {
+			msleep(ZPCI_INSN_BUSY_DELAY);
+			memset(fib, 0, PAGE_SIZE);
+		}
+	} while (cc == 2);
+
+	if (cc)
+		pr_err_once("%s: cc: %u  status: %u\n",
+			    __func__, cc, status);
+
+	/* Return PCI function controls */
+	*fc = fib->fc;
+
+	free_page((unsigned long) fib);
+	return (cc) ? -EIO : 0;
+}
+
+#define ZPCI_PCIAS_CFGSPC	15
+
+static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, ZPCI_PCIAS_CFGSPC, len);
+	u64 data;
+	int rc;
+
+	rc = pcilg_instr(&data, req, offset);
+	data = data << ((8 - len) * 8);
+	data = le64_to_cpu(data);
+	if (!rc)
+		*val = (u32) data;
+	else
+		*val = 0xffffffff;
+	return rc;
+}
+
+static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, ZPCI_PCIAS_CFGSPC, len);
+	u64 data = val;
+	int rc;
+
+	data = cpu_to_le64(data);
+	data = data >> ((8 - len) * 8);
+	rc = pcistg_instr(data, req, offset);
+	return rc;
+}
+
+void __devinit pcibios_fixup_bus(struct pci_bus *bus)
+{
+}
+
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
+				       resource_size_t size,
+				       resource_size_t align)
+{
+	return 0;
+}
+
+/* Create a virtual mapping cookie for a PCI BAR */
+void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max)
+{
+	struct zpci_dev *zdev =	get_zdev(pdev);
+	u64 addr;
+	int idx;
+
+	if ((bar & 7) != bar)
+		return NULL;
+
+	idx = zdev->bars[bar].map_idx;
+	spin_lock(&zpci_iomap_lock);
+	zpci_iomap_start[idx].fh = zdev->fh;
+	zpci_iomap_start[idx].bar = bar;
+	spin_unlock(&zpci_iomap_lock);
+
+	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
+	return (void __iomem *) addr;
+}
+EXPORT_SYMBOL_GPL(pci_iomap);
+
+void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
+{
+	unsigned int idx;
+
+	idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48;
+	spin_lock(&zpci_iomap_lock);
+	zpci_iomap_start[idx].fh = 0;
+	zpci_iomap_start[idx].bar = 0;
+	spin_unlock(&zpci_iomap_lock);
+}
+EXPORT_SYMBOL_GPL(pci_iounmap);
+
+static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
+		    int size, u32 *val)
+{
+	struct zpci_dev *zdev = get_zdev_by_bus(bus);
+
+	if (!zdev || devfn != ZPCI_DEVFN)
+		return 0;
+	return zpci_cfg_load(zdev, where, val, size);
+}
+
+static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
+		     int size, u32 val)
+{
+	struct zpci_dev *zdev = get_zdev_by_bus(bus);
+
+	if (!zdev || devfn != ZPCI_DEVFN)
+		return 0;
+	return zpci_cfg_store(zdev, where, val, size);
+}
+
+static struct pci_ops pci_root_ops = {
+	.read = pci_read,
+	.write = pci_write,
+};
+
+static void zpci_map_resources(struct zpci_dev *zdev)
+{
+	struct pci_dev *pdev = zdev->pdev;
+	resource_size_t len;
+	int i;
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		len = pci_resource_len(pdev, i);
+		if (!len)
+			continue;
+		pdev->resource[i].start = (resource_size_t) pci_iomap(pdev, i, 0);
+		pdev->resource[i].end = pdev->resource[i].start + len - 1;
+		pr_debug("BAR%i: -> start: %Lx  end: %Lx\n",
+			i, pdev->resource[i].start, pdev->resource[i].end);
+	}
+};
+
+static void zpci_unmap_resources(struct pci_dev *pdev)
+{
+	resource_size_t len;
+	int i;
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		len = pci_resource_len(pdev, i);
+		if (!len)
+			continue;
+		pci_iounmap(pdev, (void *) pdev->resource[i].start);
+	}
+};
+
+struct zpci_dev *zpci_alloc_device(void)
+{
+	struct zpci_dev *zdev;
+
+	/* Alloc memory for our private pci device data */
+	zdev = kzalloc(sizeof(*zdev), GFP_KERNEL);
+	if (!zdev)
+		return ERR_PTR(-ENOMEM);
+	return zdev;
+}
+
+void zpci_free_device(struct zpci_dev *zdev)
+{
+	kfree(zdev);
+}
+
+/* Called on removal of pci_dev, leaves zpci and bus device */
+static void zpci_remove_device(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+
+	dev_info(&pdev->dev, "Removing device %u\n", zdev->domain);
+	zdev->state = ZPCI_FN_STATE_CONFIGURED;
+	zpci_unmap_resources(pdev);
+	list_del(&zdev->entry);		/* can be called from init */
+	zdev->pdev = NULL;
+}
+
+static void zpci_scan_devices(void)
+{
+	struct zpci_dev *zdev;
+
+	mutex_lock(&zpci_list_lock);
+	list_for_each_entry(zdev, &zpci_list, entry)
+		if (zdev->state == ZPCI_FN_STATE_CONFIGURED)
+			zpci_scan_device(zdev);
+	mutex_unlock(&zpci_list_lock);
+}
+
+/*
+ * Too late for any s390 specific setup, since interrupts must be set up
+ * already which requires DMA setup too and the pci scan will access the
+ * config space, which only works if the function handle is enabled.
+ */
+int pcibios_enable_device(struct pci_dev *pdev, int mask)
+{
+	struct resource *res;
+	u16 cmd;
+	int i;
+
+	pci_read_config_word(pdev, PCI_COMMAND, &cmd);
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		res = &pdev->resource[i];
+
+		if (res->flags & IORESOURCE_IO)
+			return -EINVAL;
+
+		if (res->flags & IORESOURCE_MEM)
+			cmd |= PCI_COMMAND_MEMORY;
+	}
+	pci_write_config_word(pdev, PCI_COMMAND, cmd);
+	return 0;
+}
+
+void pcibios_disable_device(struct pci_dev *pdev)
+{
+	zpci_remove_device(pdev);
+	pdev->sysdata = NULL;
+}
+
+static struct resource *zpci_alloc_bus_resource(unsigned long start, unsigned long size,
+						unsigned long flags, int domain)
+{
+	struct resource *r;
+	char *name;
+	int rc;
+
+	r = kzalloc(sizeof(*r), GFP_KERNEL);
+	if (!r)
+		return ERR_PTR(-ENOMEM);
+	r->start = start;
+	r->end = r->start + size - 1;
+	r->flags = flags;
+	r->parent = &iomem_resource;
+	name = kmalloc(18, GFP_KERNEL);
+	if (!name) {
+		kfree(r);
+		return ERR_PTR(-ENOMEM);
+	}
+	sprintf(name, "PCI Bus: %04x:%02x", domain, ZPCI_BUS_NR);
+	r->name = name;
+
+	rc = request_resource(&iomem_resource, r);
+	if (rc)
+		pr_debug("request resource %pR failed\n", r);
+	return r;
+}
+
+static int zpci_alloc_iomap(struct zpci_dev *zdev)
+{
+	int entry;
+
+	spin_lock(&zpci_iomap_lock);
+	entry = find_first_zero_bit(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
+	if (entry == ZPCI_IOMAP_MAX_ENTRIES) {
+		spin_unlock(&zpci_iomap_lock);
+		return -ENOSPC;
+	}
+	set_bit(entry, zpci_iomap);
+	spin_unlock(&zpci_iomap_lock);
+	return entry;
+}
+
+static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
+{
+	spin_lock(&zpci_iomap_lock);
+	memset(&zpci_iomap_start[entry], 0, sizeof(struct zpci_iomap_entry));
+	clear_bit(entry, zpci_iomap);
+	spin_unlock(&zpci_iomap_lock);
+}
+
+static int zpci_create_device_bus(struct zpci_dev *zdev)
+{
+	struct resource *res;
+	LIST_HEAD(resources);
+	int i;
+
+	/* allocate mapping entry for each used bar */
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		unsigned long addr, size, flags;
+		int entry;
+
+		if (!zdev->bars[i].size)
+			continue;
+		entry = zpci_alloc_iomap(zdev);
+		if (entry < 0)
+			return entry;
+		zdev->bars[i].map_idx = entry;
+
+		/* only MMIO is supported */
+		flags = IORESOURCE_MEM;
+		if (zdev->bars[i].val & 8)
+			flags |= IORESOURCE_PREFETCH;
+		if (zdev->bars[i].val & 4)
+			flags |= IORESOURCE_MEM_64;
+
+		addr = ZPCI_IOMAP_ADDR_BASE + ((u64) entry << 48);
+
+		size = 1UL << zdev->bars[i].size;
+
+		res = zpci_alloc_bus_resource(addr, size, flags, zdev->domain);
+		if (IS_ERR(res)) {
+			zpci_free_iomap(zdev, entry);
+			return PTR_ERR(res);
+		}
+		pci_add_resource(&resources, res);
+	}
+
+	zdev->bus = pci_create_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops,
+					zdev, &resources);
+	if (!zdev->bus)
+		return -EIO;
+
+	zdev->bus->max_bus_speed = zdev->max_bus_speed;
+	return 0;
+}
+
+static int zpci_alloc_domain(struct zpci_dev *zdev)
+{
+	spin_lock(&zpci_domain_lock);
+	zdev->domain = find_first_zero_bit(zpci_domain, ZPCI_NR_DEVICES);
+	if (zdev->domain == ZPCI_NR_DEVICES) {
+		spin_unlock(&zpci_domain_lock);
+		return -ENOSPC;
+	}
+	set_bit(zdev->domain, zpci_domain);
+	spin_unlock(&zpci_domain_lock);
+	return 0;
+}
+
+static void zpci_free_domain(struct zpci_dev *zdev)
+{
+	spin_lock(&zpci_domain_lock);
+	clear_bit(zdev->domain, zpci_domain);
+	spin_unlock(&zpci_domain_lock);
+}
+
+int zpci_create_device(struct zpci_dev *zdev)
+{
+	int rc;
+
+	rc = zpci_alloc_domain(zdev);
+	if (rc)
+		goto out;
+
+	rc = zpci_create_device_bus(zdev);
+	if (rc)
+		goto out_bus;
+
+	mutex_lock(&zpci_list_lock);
+	list_add_tail(&zdev->entry, &zpci_list);
+	mutex_unlock(&zpci_list_lock);
+
+	if (zdev->state == ZPCI_FN_STATE_STANDBY)
+		return 0;
+
+	return 0;
+
+out_bus:
+	zpci_free_domain(zdev);
+out:
+	return rc;
+}
+
+void zpci_stop_device(struct zpci_dev *zdev)
+{
+	/*
+	 * Note: SCLP disables fh via set-pci-fn so don't
+	 * do that here.
+	 */
+}
+EXPORT_SYMBOL_GPL(zpci_stop_device);
+
+int zpci_scan_device(struct zpci_dev *zdev)
+{
+	zdev->pdev = pci_scan_single_device(zdev->bus, ZPCI_DEVFN);
+	if (!zdev->pdev) {
+		pr_err("pci_scan_single_device failed for fid: 0x%x\n",
+			zdev->fid);
+		goto out;
+	}
+
+	zpci_map_resources(zdev);
+	pci_bus_add_devices(zdev->bus);
+
+	/* now that pdev was added to the bus mark it as used */
+	zdev->state = ZPCI_FN_STATE_ONLINE;
+	return 0;
+
+out:
+	return -EIO;
+}
+EXPORT_SYMBOL_GPL(zpci_scan_device);
+
+static inline int barsize(u8 size)
+{
+	return (size) ? (1 << size) >> 10 : 0;
+}
+
+static int zpci_mem_init(void)
+{
+	/* TODO: use realloc */
+	zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start),
+				   GFP_KERNEL);
+	if (!zpci_iomap_start)
+		goto error_zdev;
+	return 0;
+
+error_zdev:
+	return -ENOMEM;
+}
+
+static void zpci_mem_exit(void)
+{
+	kfree(zpci_iomap_start);
+}
+
+unsigned int pci_probe = 1;
+EXPORT_SYMBOL_GPL(pci_probe);
+
+char * __init pcibios_setup(char *str)
+{
+	if (!strcmp(str, "off")) {
+		pci_probe = 0;
+		return NULL;
+	}
+	return str;
+}
+
+static int __init pci_base_init(void)
+{
+	int rc;
+
+	if (!pci_probe)
+		return 0;
+
+	if (!test_facility(2) || !test_facility(69)
+	    || !test_facility(71) || !test_facility(72))
+		return 0;
+
+	pr_info("Probing PCI hardware: PCI:%d  SID:%d  AEN:%d\n",
+		test_facility(69), test_facility(70),
+		test_facility(71));
+
+	rc = zpci_mem_init();
+	if (rc)
+		goto out_mem;
+
+	zpci_scan_devices();
+	return 0;
+
+	zpci_mem_exit();
+out_mem:
+	return rc;
+}
+subsys_initcall(pci_base_init);
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 448303bdb85f..9e0ebe051243 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -83,19 +83,25 @@ static inline void __raw_writel(u32 b, volatile void __iomem *addr)
 #define writel(b,addr) __raw_writel(__cpu_to_le32(b),addr)
 
 #ifdef CONFIG_64BIT
+#ifndef __raw_readq
 static inline u64 __raw_readq(const volatile void __iomem *addr)
 {
 	return *(const volatile u64 __force *) addr;
 }
+#endif
+
 #define readq(addr) __le64_to_cpu(__raw_readq(addr))
 
+#ifndef __raw_writeq
 static inline void __raw_writeq(u64 b, volatile void __iomem *addr)
 {
 	*(volatile u64 __force *) addr = b;
 }
-#define writeq(b,addr) __raw_writeq(__cpu_to_le64(b),addr)
 #endif
 
+#define writeq(b, addr) __raw_writeq(__cpu_to_le64(b), addr)
+#endif /* CONFIG_64BIT */
+
 #ifndef PCI_IOBASE
 #define PCI_IOBASE ((void __iomem *) 0)
 #endif
@@ -286,15 +292,20 @@ static inline void writesb(const void __iomem *addr, const void *buf, int len)
 
 #ifndef CONFIG_GENERIC_IOMAP
 struct pci_dev;
+extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+
+#ifndef pci_iounmap
 static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
 {
 }
+#endif
 #endif /* CONFIG_GENERIC_IOMAP */
 
 /*
  * Change virtual addresses to physical addresses and vv.
  * These are pretty trivial
  */
+#ifndef virt_to_phys
 static inline unsigned long virt_to_phys(volatile void *address)
 {
 	return __pa((unsigned long)address);
@@ -304,6 +315,7 @@ static inline void *phys_to_virt(unsigned long address)
 {
 	return __va(address);
 }
+#endif
 
 /*
  * Change "struct page" to physical address.
@@ -363,9 +375,16 @@ static inline void *bus_to_virt(unsigned long address)
 }
 #endif
 
+#ifndef memset_io
 #define memset_io(a, b, c)	memset(__io_virt(a), (b), (c))
+#endif
+
+#ifndef memcpy_fromio
 #define memcpy_fromio(a, b, c)	memcpy((a), __io_virt(b), (c))
+#endif
+#ifndef memcpy_toio
 #define memcpy_toio(a, b, c)	memcpy(__io_virt(a), (b), (c))
+#endif
 
 #endif /* __KERNEL__ */
 
-- 
cgit v1.2.3-55-g7522


From 584955632841c069678833f3320b4f6d21a8215e Mon Sep 17 00:00:00 2001
From: Rob Clark
Date: Thu, 11 Oct 2012 20:50:56 -0500
Subject: drm: remove legacy drm_connector_property fxns

Replace references to and remove the connector property fxns, which
have been superseded with the more general object property fxns:

  + drm_connector_attach_property -> drm_object_attach_property
  + drm_connector_property_set_value -> drm_object_property_set_value
  + drm_connector_property_get_value -> drm_object_property_get_value

Signed-off-by: Rob Clark <rob@ti.com>
---
 drivers/gpu/drm/drm_crtc.c      | 31 +++++--------------------------
 drivers/gpu/drm/drm_fb_helper.c |  2 +-
 drivers/gpu/drm/drm_sysfs.c     |  6 +++---
 include/drm/drm_crtc.h          |  8 --------
 4 files changed, 9 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index d6d007275947..f2d667b8bee2 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -559,11 +559,11 @@ int drm_connector_init(struct drm_device *dev,
 	dev->mode_config.num_connector++;
 
 	if (connector_type != DRM_MODE_CONNECTOR_VIRTUAL)
-		drm_connector_attach_property(connector,
+		drm_object_attach_property(&connector->base,
 					      dev->mode_config.edid_property,
 					      0);
 
-	drm_connector_attach_property(connector,
+	drm_object_attach_property(&connector->base,
 				      dev->mode_config.dpms_property, 0);
 
  out:
@@ -2928,27 +2928,6 @@ void drm_property_destroy(struct drm_device *dev, struct drm_property *property)
 }
 EXPORT_SYMBOL(drm_property_destroy);
 
-void drm_connector_attach_property(struct drm_connector *connector,
-			       struct drm_property *property, uint64_t init_val)
-{
-	drm_object_attach_property(&connector->base, property, init_val);
-}
-EXPORT_SYMBOL(drm_connector_attach_property);
-
-int drm_connector_property_set_value(struct drm_connector *connector,
-				  struct drm_property *property, uint64_t value)
-{
-	return drm_object_property_set_value(&connector->base, property, value);
-}
-EXPORT_SYMBOL(drm_connector_property_set_value);
-
-int drm_connector_property_get_value(struct drm_connector *connector,
-				  struct drm_property *property, uint64_t *val)
-{
-	return drm_object_property_get_value(&connector->base, property, val);
-}
-EXPORT_SYMBOL(drm_connector_property_get_value);
-
 void drm_object_attach_property(struct drm_mode_object *obj,
 				struct drm_property *property,
 				uint64_t init_val)
@@ -3185,7 +3164,7 @@ int drm_mode_connector_update_edid_property(struct drm_connector *connector,
 	/* Delete edid, when there is none. */
 	if (!edid) {
 		connector->edid_blob_ptr = NULL;
-		ret = drm_connector_property_set_value(connector, dev->mode_config.edid_property, 0);
+		ret = drm_object_property_set_value(&connector->base, dev->mode_config.edid_property, 0);
 		return ret;
 	}
 
@@ -3195,7 +3174,7 @@ int drm_mode_connector_update_edid_property(struct drm_connector *connector,
 	if (!connector->edid_blob_ptr)
 		return -EINVAL;
 
-	ret = drm_connector_property_set_value(connector,
+	ret = drm_object_property_set_value(&connector->base,
 					       dev->mode_config.edid_property,
 					       connector->edid_blob_ptr->base.id);
 
@@ -3262,7 +3241,7 @@ static int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj,
 
 	/* store the property value if successful */
 	if (!ret)
-		drm_connector_property_set_value(connector, property, value);
+		drm_object_property_set_value(&connector->base, property, value);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 05e623a5d095..954d175bd7fa 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -348,7 +348,7 @@ static void drm_fb_helper_dpms(struct fb_info *info, int dpms_mode)
 		for (j = 0; j < fb_helper->connector_count; j++) {
 			connector = fb_helper->connector_info[j]->connector;
 			connector->funcs->dpms(connector, dpms_mode);
-			drm_connector_property_set_value(connector,
+			drm_object_property_set_value(&connector->base,
 				dev->mode_config.dpms_property, dpms_mode);
 		}
 	}
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index 05cd8fe062af..02296653a058 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -182,7 +182,7 @@ static ssize_t dpms_show(struct device *device,
 	uint64_t dpms_status;
 	int ret;
 
-	ret = drm_connector_property_get_value(connector,
+	ret = drm_object_property_get_value(&connector->base,
 					    dev->mode_config.dpms_property,
 					    &dpms_status);
 	if (ret)
@@ -277,7 +277,7 @@ static ssize_t subconnector_show(struct device *device,
 		return 0;
 	}
 
-	ret = drm_connector_property_get_value(connector, prop, &subconnector);
+	ret = drm_object_property_get_value(&connector->base, prop, &subconnector);
 	if (ret)
 		return 0;
 
@@ -318,7 +318,7 @@ static ssize_t select_subconnector_show(struct device *device,
 		return 0;
 	}
 
-	ret = drm_connector_property_get_value(connector, prop, &subconnector);
+	ret = drm_object_property_get_value(&connector->base, prop, &subconnector);
 	if (ret)
 		return 0;
 
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index c0635b7f8696..ee9b0b59237f 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -920,12 +920,6 @@ extern void drm_mode_set_crtcinfo(struct drm_display_mode *p,
 extern void drm_mode_connector_list_update(struct drm_connector *connector);
 extern int drm_mode_connector_update_edid_property(struct drm_connector *connector,
 						struct edid *edid);
-extern int drm_connector_property_set_value(struct drm_connector *connector,
-					 struct drm_property *property,
-					 uint64_t value);
-extern int drm_connector_property_get_value(struct drm_connector *connector,
-					 struct drm_property *property,
-					 uint64_t *value);
 extern int drm_object_property_set_value(struct drm_mode_object *obj,
 					 struct drm_property *property,
 					 uint64_t val);
@@ -947,8 +941,6 @@ extern int drmfb_remove(struct drm_device *dev, struct drm_framebuffer *fb);
 extern void drm_crtc_probe_connector_modes(struct drm_device *dev, int maxX, int maxY);
 extern bool drm_crtc_in_use(struct drm_crtc *crtc);
 
-extern void drm_connector_attach_property(struct drm_connector *connector,
-					  struct drm_property *property, uint64_t init_val);
 extern void drm_object_attach_property(struct drm_mode_object *obj,
 				       struct drm_property *property,
 				       uint64_t init_val);
-- 
cgit v1.2.3-55-g7522


From 45c3eb7d3a07eb08d1b5b0f5983a996d41610b84 Mon Sep 17 00:00:00 2001
From: Tony Lindgren
Date: Fri, 30 Nov 2012 08:41:50 -0800
Subject: ARM: OMAP: Move plat-omap/dma-omap.h to include/linux/omap-dma.h

Based on earlier discussions[1] we attempted to find a suitable
location for the omap DMA header in commit 2b6c4e73 (ARM: OMAP:
DMA: Move plat/dma.h to plat-omap/dma-omap.h) until the conversion
to dmaengine is complete.

Unfortunately that was before I was able to try to test compile
of the ARM multiplatform builds for omap2+, and the end result
was not very good.

So I'm creating yet another all over the place patch to cut the
last dependency for building omap2+ for ARM multiplatform. After
this, we have finally removed the driver dependencies to the
arch/arm code, except for few drivers that are being worked on.

The other option was to make the <plat-omap/dma-omap.h> path
to work, but we'd have to add some new header directory to for
multiplatform builds.

Or we would have to manually include arch/arm/plat-omap/include
again from arch/arm/Makefile for omap2+.

Neither of these alternatives sound appealing as they will
likely lead addition of various other headers exposed to the
drivers, which we want to avoid for the multiplatform kernels.

Since we already have a minimal include/linux/omap-dma.h,
let's just use that instead and add a note to it to not
use the custom omap DMA functions any longer where possible.

Note that converting omap DMA to dmaengine depends on
dmaengine supporting automatically incrementing the FIFO
address at the device end, and converting all the remaining
legacy drivers. So it's going to be few more merge windows.

[1] https://patchwork.kernel.org/patch/1519591/#

cc: Russell King <linux@arm.linux.org.uk>
cc: Kevin Hilman <khilman@ti.com>
cc: "Benoît Cousson" <b-cousson@ti.com>
cc: Herbert Xu <herbert@gondor.apana.org.au>
cc: "David S. Miller" <davem@davemloft.net>
cc: Vinod Koul <vinod.koul@intel.com>
cc: Dan Williams <djbw@fb.com>
cc: Mauro Carvalho Chehab <mchehab@infradead.org>
cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
cc: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
cc: David Woodhouse <dwmw2@infradead.org>
cc: Kyungmin Park <kyungmin.park@samsung.com>
cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
cc: Florian Tobias Schandinat <FlorianSchandinat@gmx.de>
cc: Hans Verkuil <hans.verkuil@cisco.com>
cc: Vaibhav Hiremath <hvaibhav@ti.com>
cc: Lokesh Vutla <lokeshvutla@ti.com>
cc: Rusty Russell <rusty@rustcorp.com.au>
cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
cc: Afzal Mohammed <afzal@ti.com>
cc: linux-crypto@vger.kernel.org
cc: linux-media@vger.kernel.org
cc: linux-mtd@lists.infradead.org
cc: linux-usb@vger.kernel.org
cc: linux-fbdev@vger.kernel.org
Acked-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap1/board-h2.c                     |   2 +-
 arch/arm/mach-omap1/board-h3.c                     |   2 +-
 arch/arm/mach-omap1/board-palmte.c                 |   2 +-
 arch/arm/mach-omap1/board-palmtt.c                 |   2 +-
 arch/arm/mach-omap1/board-palmz71.c                |   2 +-
 arch/arm/mach-omap1/board-sx1.c                    |   2 +-
 arch/arm/mach-omap1/dma.c                          |   2 +-
 arch/arm/mach-omap1/io.c                           |   2 +-
 arch/arm/mach-omap1/lcd_dma.c                      |   2 +-
 arch/arm/mach-omap1/mcbsp.c                        |   2 +-
 arch/arm/mach-omap1/pm.c                           |   2 +-
 arch/arm/mach-omap2/board-3430sdp.c                |   2 +-
 arch/arm/mach-omap2/board-h4.c                     |   2 +-
 arch/arm/mach-omap2/board-rx51-peripherals.c       |   2 +-
 arch/arm/mach-omap2/board-rx51.c                   |   2 +-
 arch/arm/mach-omap2/devices.c                      |   2 +-
 arch/arm/mach-omap2/dma.c                          |   2 +-
 arch/arm/mach-omap2/io.c                           |   2 +-
 arch/arm/mach-omap2/mcbsp.c                        |   2 +-
 arch/arm/mach-omap2/omap_hwmod_2420_data.c         |   2 +-
 arch/arm/mach-omap2/omap_hwmod_2430_data.c         |   2 +-
 .../mach-omap2/omap_hwmod_2xxx_3xxx_ipblock_data.c |   3 +-
 arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c |   2 +-
 arch/arm/mach-omap2/omap_hwmod_3xxx_data.c         |   2 +-
 arch/arm/mach-omap2/omap_hwmod_44xx_data.c         |   2 +-
 arch/arm/mach-omap2/pm24xx.c                       |   2 +-
 arch/arm/mach-omap2/pm34xx.c                       |   3 +-
 arch/arm/mach-omap2/serial.c                       |   2 +-
 arch/arm/plat-omap/dma.c                           |   2 +-
 arch/arm/plat-omap/include/plat-omap/dma-omap.h    | 377 ---------------------
 drivers/crypto/omap-aes.c                          |   2 +-
 drivers/crypto/omap-sham.c                         |   2 +-
 drivers/dma/omap-dma.c                             |   2 -
 drivers/media/platform/omap/omap_vout.c            |   2 +-
 drivers/media/platform/omap/omap_vout_vrfb.c       |   2 +-
 drivers/media/platform/omap3isp/ispstat.h          |   2 +-
 drivers/media/platform/soc_camera/omap1_camera.c   |   2 +-
 drivers/mtd/nand/omap2.c                           |   1 -
 drivers/mtd/onenand/omap2.c                        |   2 +-
 drivers/usb/gadget/omap_udc.c                      |   2 +-
 drivers/usb/musb/tusb6010_omap.c                   |   2 +-
 drivers/video/omap/lcdc.c                          |   2 +-
 drivers/video/omap/omapfb_main.c                   |   2 +-
 drivers/video/omap/sossi.c                         |   2 +-
 include/linux/omap-dma.h                           | 366 ++++++++++++++++++++
 45 files changed, 408 insertions(+), 422 deletions(-)
 delete mode 100644 arch/arm/plat-omap/include/plat-omap/dma-omap.h

(limited to 'include')

diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c
index 9134b646f01b..dcf364d1a8b1 100644
--- a/arch/arm/mach-omap1/board-h2.c
+++ b/arch/arm/mach-omap1/board-h2.c
@@ -39,7 +39,7 @@
 #include <asm/mach/map.h>
 
 #include <mach/mux.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <mach/tc.h>
 #include <mach/irda.h>
 #include <linux/platform_data/keypad-omap.h>
diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c
index bf213d1d8075..b3fcdedb44ca 100644
--- a/arch/arm/mach-omap1/board-h3.c
+++ b/arch/arm/mach-omap1/board-h3.c
@@ -43,7 +43,7 @@
 #include <mach/mux.h>
 #include <mach/tc.h>
 #include <linux/platform_data/keypad-omap.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <mach/flash.h>
 
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-omap1/board-palmte.c b/arch/arm/mach-omap1/board-palmte.c
index 584b6fab894b..c33dceb46607 100644
--- a/arch/arm/mach-omap1/board-palmte.c
+++ b/arch/arm/mach-omap1/board-palmte.c
@@ -37,7 +37,7 @@
 #include <mach/flash.h>
 #include <mach/mux.h>
 #include <mach/tc.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <mach/irda.h>
 #include <linux/platform_data/keypad-omap.h>
 
diff --git a/arch/arm/mach-omap1/board-palmtt.c b/arch/arm/mach-omap1/board-palmtt.c
index fbc986bfe69e..2948b0ee4be8 100644
--- a/arch/arm/mach-omap1/board-palmtt.c
+++ b/arch/arm/mach-omap1/board-palmtt.c
@@ -36,7 +36,7 @@
 
 #include <mach/flash.h>
 #include <mach/mux.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <mach/tc.h>
 #include <mach/irda.h>
 #include <linux/platform_data/keypad-omap.h>
diff --git a/arch/arm/mach-omap1/board-palmz71.c b/arch/arm/mach-omap1/board-palmz71.c
index 60d917a93763..7a05895c0be3 100644
--- a/arch/arm/mach-omap1/board-palmz71.c
+++ b/arch/arm/mach-omap1/board-palmz71.c
@@ -38,7 +38,7 @@
 
 #include <mach/flash.h>
 #include <mach/mux.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <mach/tc.h>
 #include <mach/irda.h>
 #include <linux/platform_data/keypad-omap.h>
diff --git a/arch/arm/mach-omap1/board-sx1.c b/arch/arm/mach-omap1/board-sx1.c
index 1ebc7e08d6e5..20ed52ae1714 100644
--- a/arch/arm/mach-omap1/board-sx1.c
+++ b/arch/arm/mach-omap1/board-sx1.c
@@ -36,7 +36,7 @@
 
 #include <mach/flash.h>
 #include <mach/mux.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <mach/irda.h>
 #include <mach/tc.h>
 #include <mach/board-sx1.h>
diff --git a/arch/arm/mach-omap1/dma.c b/arch/arm/mach-omap1/dma.c
index 978aed85d328..e190611e4b46 100644
--- a/arch/arm/mach-omap1/dma.c
+++ b/arch/arm/mach-omap1/dma.c
@@ -25,7 +25,7 @@
 #include <linux/device.h>
 #include <linux/io.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <mach/tc.h>
 
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-omap1/io.c b/arch/arm/mach-omap1/io.c
index 5a3b80617a11..499b8accb83d 100644
--- a/arch/arm/mach-omap1/io.c
+++ b/arch/arm/mach-omap1/io.c
@@ -18,7 +18,7 @@
 
 #include <mach/mux.h>
 #include <mach/tc.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include "iomap.h"
 #include "common.h"
diff --git a/arch/arm/mach-omap1/lcd_dma.c b/arch/arm/mach-omap1/lcd_dma.c
index 7ed8c1857d56..77924be37d41 100644
--- a/arch/arm/mach-omap1/lcd_dma.c
+++ b/arch/arm/mach-omap1/lcd_dma.c
@@ -27,7 +27,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include <mach/hardware.h>
 #include <mach/lcdc.h>
diff --git a/arch/arm/mach-omap1/mcbsp.c b/arch/arm/mach-omap1/mcbsp.c
index c6d8fdf92e9c..b0d4723c9a90 100644
--- a/arch/arm/mach-omap1/mcbsp.c
+++ b/arch/arm/mach-omap1/mcbsp.c
@@ -19,7 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <mach/mux.h>
 #include "soc.h"
 #include <linux/platform_data/asoc-ti-mcbsp.h>
diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c
index 66d663a6ef3a..7a7690ab6cb8 100644
--- a/arch/arm/mach-omap1/pm.c
+++ b/arch/arm/mach-omap1/pm.c
@@ -52,7 +52,7 @@
 
 #include <mach/tc.h>
 #include <mach/mux.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <plat/dmtimer.h>
 
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-omap2/board-3430sdp.c b/arch/arm/mach-omap2/board-3430sdp.c
index 6601754f9512..7b201546834d 100644
--- a/arch/arm/mach-omap2/board-3430sdp.c
+++ b/arch/arm/mach-omap2/board-3430sdp.c
@@ -31,7 +31,7 @@
 #include <asm/mach/map.h>
 
 #include "common.h"
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <video/omapdss.h>
 #include <video/omap-panel-tfp410.h>
 
diff --git a/arch/arm/mach-omap2/board-h4.c b/arch/arm/mach-omap2/board-h4.c
index b626dbe6f7bc..9a3878ec2256 100644
--- a/arch/arm/mach-omap2/board-h4.c
+++ b/arch/arm/mach-omap2/board-h4.c
@@ -32,7 +32,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <plat/debug-devices.h>
 
 #include <video/omapdss.h>
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 07005fe40a2a..60529e0b3d67 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -31,7 +31,7 @@
 #include <asm/system_info.h>
 
 #include "common.h"
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include "gpmc-smc91x.h"
 
 #include "board-rx51.h"
diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c
index bf8f74b0ce3e..ee1045c0ad67 100644
--- a/arch/arm/mach-omap2/board-rx51.c
+++ b/arch/arm/mach-omap2/board-rx51.c
@@ -24,7 +24,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include "common.h"
 #include "mux.h"
diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index cf365c387c06..cfef4547f2fd 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -23,7 +23,7 @@
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include "iomap.h"
 #include "omap_hwmod.h"
diff --git a/arch/arm/mach-omap2/dma.c b/arch/arm/mach-omap2/dma.c
index e5aba58da5d2..612b98249873 100644
--- a/arch/arm/mach-omap2/dma.c
+++ b/arch/arm/mach-omap2/dma.c
@@ -28,7 +28,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include "soc.h"
 #include "omap_hwmod.h"
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 7c39238322e0..2c3fdd65387b 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -25,7 +25,7 @@
 #include <asm/tlb.h>
 #include <asm/mach/map.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include "omap_hwmod.h"
 #include "soc.h"
diff --git a/arch/arm/mach-omap2/mcbsp.c b/arch/arm/mach-omap2/mcbsp.c
index bf496510eb5e..df49f2a49461 100644
--- a/arch/arm/mach-omap2/mcbsp.c
+++ b/arch/arm/mach-omap2/mcbsp.c
@@ -21,7 +21,7 @@
 #include <linux/platform_data/asoc-ti-mcbsp.h>
 #include <linux/pm_runtime.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include "omap_device.h"
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_2420_data.c b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
index a8b3368dca3d..10af996aa479 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2420_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
@@ -16,7 +16,7 @@
 #include <linux/i2c-omap.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <plat/dmtimer.h>
 
 #include "omap_hwmod.h"
diff --git a/arch/arm/mach-omap2/omap_hwmod_2430_data.c b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
index dc768c50e523..f14b894ce761 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2430_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
@@ -17,7 +17,7 @@
 #include <linux/platform_data/asoc-ti-mcbsp.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <plat/dmtimer.h>
 
 #include "omap_hwmod.h"
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_3xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_3xxx_ipblock_data.c
index 40d6c93d9853..534974e08add 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_3xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_3xxx_ipblock_data.c
@@ -10,7 +10,8 @@
  * published by the Free Software Foundation.
  */
 
-#include <plat-omap/dma-omap.h>
+#include <linux/dmaengine.h>
+#include <linux/omap-dma.h>
 
 #include "omap_hwmod.h"
 #include "hdq1w.h"
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index a0116d08cf45..63d805521b4b 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/platform_data/gpio-omap.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <plat/dmtimer.h>
 #include <linux/platform_data/spi-omap2-mcspi.h>
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index abe66ced903f..d87e24834dc9 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -19,7 +19,7 @@
 #include <linux/power/smartreflex.h>
 #include <linux/platform_data/gpio-omap.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include "l3_3xxx.h"
 #include "l4_3xxx.h"
 #include <linux/platform_data/asoc-ti-mcbsp.h>
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 7a6132848f5d..61e807f2a798 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -23,7 +23,7 @@
 #include <linux/power/smartreflex.h>
 #include <linux/i2c-omap.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include <linux/platform_data/spi-omap2-mcspi.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
diff --git a/arch/arm/mach-omap2/pm24xx.c b/arch/arm/mach-omap2/pm24xx.c
index c289b3333c99..c333fa6dffa8 100644
--- a/arch/arm/mach-omap2/pm24xx.c
+++ b/arch/arm/mach-omap2/pm24xx.c
@@ -38,7 +38,7 @@
 #include <asm/mach-types.h>
 #include <asm/system_misc.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include "soc.h"
 #include "common.h"
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 770320061422..7be3622cfc85 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -28,6 +28,7 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/omap-dma.h>
 #include <linux/platform_data/gpio-omap.h>
 
 #include <trace/events/power.h>
@@ -38,8 +39,6 @@
 
 #include "clockdomain.h"
 #include "powerdomain.h"
-#include <plat-omap/dma-omap.h>
-
 #include "soc.h"
 #include "common.h"
 #include "cm3xxx.h"
diff --git a/arch/arm/mach-omap2/serial.c b/arch/arm/mach-omap2/serial.c
index aa30a3c20883..93d102535c85 100644
--- a/arch/arm/mach-omap2/serial.c
+++ b/arch/arm/mach-omap2/serial.c
@@ -26,9 +26,9 @@
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
 #include <linux/console.h>
+#include <linux/omap-dma.h>
 
 #include <plat/omap-serial.h>
-#include <plat-omap/dma-omap.h>
 
 #include "common.h"
 #include "omap_hwmod.h"
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index c288b76f8e6c..37a488aaa2ba 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -36,7 +36,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 /*
  * MAX_LOGICAL_DMA_CH_COUNT: the maximum number of logical DMA
diff --git a/arch/arm/plat-omap/include/plat-omap/dma-omap.h b/arch/arm/plat-omap/include/plat-omap/dma-omap.h
deleted file mode 100644
index 6f506ba9e453..000000000000
--- a/arch/arm/plat-omap/include/plat-omap/dma-omap.h
+++ /dev/null
@@ -1,377 +0,0 @@
-/*
- *  OMAP DMA handling defines and function
- *
- *  Copyright (C) 2003 Nokia Corporation
- *  Author: Juha Yrjölä <juha.yrjola@nokia.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-#ifndef __ASM_ARCH_DMA_H
-#define __ASM_ARCH_DMA_H
-
-#include <linux/platform_device.h>
-
-#define INT_DMA_LCD			25
-
-#define OMAP1_DMA_TOUT_IRQ		(1 << 0)
-#define OMAP_DMA_DROP_IRQ		(1 << 1)
-#define OMAP_DMA_HALF_IRQ		(1 << 2)
-#define OMAP_DMA_FRAME_IRQ		(1 << 3)
-#define OMAP_DMA_LAST_IRQ		(1 << 4)
-#define OMAP_DMA_BLOCK_IRQ		(1 << 5)
-#define OMAP1_DMA_SYNC_IRQ		(1 << 6)
-#define OMAP2_DMA_PKT_IRQ		(1 << 7)
-#define OMAP2_DMA_TRANS_ERR_IRQ		(1 << 8)
-#define OMAP2_DMA_SECURE_ERR_IRQ	(1 << 9)
-#define OMAP2_DMA_SUPERVISOR_ERR_IRQ	(1 << 10)
-#define OMAP2_DMA_MISALIGNED_ERR_IRQ	(1 << 11)
-
-#define OMAP_DMA_CCR_EN			(1 << 7)
-#define OMAP_DMA_CCR_RD_ACTIVE		(1 << 9)
-#define OMAP_DMA_CCR_WR_ACTIVE		(1 << 10)
-#define OMAP_DMA_CCR_SEL_SRC_DST_SYNC	(1 << 24)
-#define OMAP_DMA_CCR_BUFFERING_DISABLE	(1 << 25)
-
-#define OMAP_DMA_DATA_TYPE_S8		0x00
-#define OMAP_DMA_DATA_TYPE_S16		0x01
-#define OMAP_DMA_DATA_TYPE_S32		0x02
-
-#define OMAP_DMA_SYNC_ELEMENT		0x00
-#define OMAP_DMA_SYNC_FRAME		0x01
-#define OMAP_DMA_SYNC_BLOCK		0x02
-#define OMAP_DMA_SYNC_PACKET		0x03
-
-#define OMAP_DMA_DST_SYNC_PREFETCH	0x02
-#define OMAP_DMA_SRC_SYNC		0x01
-#define OMAP_DMA_DST_SYNC		0x00
-
-#define OMAP_DMA_PORT_EMIFF		0x00
-#define OMAP_DMA_PORT_EMIFS		0x01
-#define OMAP_DMA_PORT_OCP_T1		0x02
-#define OMAP_DMA_PORT_TIPB		0x03
-#define OMAP_DMA_PORT_OCP_T2		0x04
-#define OMAP_DMA_PORT_MPUI		0x05
-
-#define OMAP_DMA_AMODE_CONSTANT		0x00
-#define OMAP_DMA_AMODE_POST_INC		0x01
-#define OMAP_DMA_AMODE_SINGLE_IDX	0x02
-#define OMAP_DMA_AMODE_DOUBLE_IDX	0x03
-
-#define DMA_DEFAULT_FIFO_DEPTH		0x10
-#define DMA_DEFAULT_ARB_RATE		0x01
-/* Pass THREAD_RESERVE ORed with THREAD_FIFO for tparams */
-#define DMA_THREAD_RESERVE_NORM		(0x00 << 12) /* Def */
-#define DMA_THREAD_RESERVE_ONET		(0x01 << 12)
-#define DMA_THREAD_RESERVE_TWOT		(0x02 << 12)
-#define DMA_THREAD_RESERVE_THREET	(0x03 << 12)
-#define DMA_THREAD_FIFO_NONE		(0x00 << 14) /* Def */
-#define DMA_THREAD_FIFO_75		(0x01 << 14)
-#define DMA_THREAD_FIFO_25		(0x02 << 14)
-#define DMA_THREAD_FIFO_50		(0x03 << 14)
-
-/* DMA4_OCP_SYSCONFIG bits */
-#define DMA_SYSCONFIG_MIDLEMODE_MASK		(3 << 12)
-#define DMA_SYSCONFIG_CLOCKACTIVITY_MASK	(3 << 8)
-#define DMA_SYSCONFIG_EMUFREE			(1 << 5)
-#define DMA_SYSCONFIG_SIDLEMODE_MASK		(3 << 3)
-#define DMA_SYSCONFIG_SOFTRESET			(1 << 2)
-#define DMA_SYSCONFIG_AUTOIDLE			(1 << 0)
-
-#define DMA_SYSCONFIG_MIDLEMODE(n)		((n) << 12)
-#define DMA_SYSCONFIG_SIDLEMODE(n)		((n) << 3)
-
-#define DMA_IDLEMODE_SMARTIDLE			0x2
-#define DMA_IDLEMODE_NO_IDLE			0x1
-#define DMA_IDLEMODE_FORCE_IDLE			0x0
-
-/* Chaining modes*/
-#ifndef CONFIG_ARCH_OMAP1
-#define OMAP_DMA_STATIC_CHAIN		0x1
-#define OMAP_DMA_DYNAMIC_CHAIN		0x2
-#define OMAP_DMA_CHAIN_ACTIVE		0x1
-#define OMAP_DMA_CHAIN_INACTIVE		0x0
-#endif
-
-#define DMA_CH_PRIO_HIGH		0x1
-#define DMA_CH_PRIO_LOW			0x0 /* Def */
-
-/* Errata handling */
-#define IS_DMA_ERRATA(id)		(errata & (id))
-#define SET_DMA_ERRATA(id)		(errata |= (id))
-
-#define DMA_ERRATA_IFRAME_BUFFERING	BIT(0x0)
-#define DMA_ERRATA_PARALLEL_CHANNELS	BIT(0x1)
-#define DMA_ERRATA_i378			BIT(0x2)
-#define DMA_ERRATA_i541			BIT(0x3)
-#define DMA_ERRATA_i88			BIT(0x4)
-#define DMA_ERRATA_3_3			BIT(0x5)
-#define DMA_ROMCODE_BUG			BIT(0x6)
-
-/* Attributes for OMAP DMA Contrller */
-#define DMA_LINKED_LCH			BIT(0x0)
-#define GLOBAL_PRIORITY			BIT(0x1)
-#define RESERVE_CHANNEL			BIT(0x2)
-#define IS_CSSA_32			BIT(0x3)
-#define IS_CDSA_32			BIT(0x4)
-#define IS_RW_PRIORITY			BIT(0x5)
-#define ENABLE_1510_MODE		BIT(0x6)
-#define SRC_PORT			BIT(0x7)
-#define DST_PORT			BIT(0x8)
-#define SRC_INDEX			BIT(0x9)
-#define DST_INDEX			BIT(0xa)
-#define IS_BURST_ONLY4			BIT(0xb)
-#define CLEAR_CSR_ON_READ		BIT(0xc)
-#define IS_WORD_16			BIT(0xd)
-#define ENABLE_16XX_MODE		BIT(0xe)
-#define HS_CHANNELS_RESERVED		BIT(0xf)
-
-/* Defines for DMA Capabilities */
-#define DMA_HAS_TRANSPARENT_CAPS	(0x1 << 18)
-#define DMA_HAS_CONSTANT_FILL_CAPS	(0x1 << 19)
-#define DMA_HAS_DESCRIPTOR_CAPS		(0x3 << 20)
-
-enum omap_reg_offsets {
-
-GCR,		GSCR,		GRST1,		HW_ID,
-PCH2_ID,	PCH0_ID,	PCH1_ID,	PCHG_ID,
-PCHD_ID,	CAPS_0,		CAPS_1,		CAPS_2,
-CAPS_3,		CAPS_4,		PCH2_SR,	PCH0_SR,
-PCH1_SR,	PCHD_SR,	REVISION,	IRQSTATUS_L0,
-IRQSTATUS_L1,	IRQSTATUS_L2,	IRQSTATUS_L3,	IRQENABLE_L0,
-IRQENABLE_L1,	IRQENABLE_L2,	IRQENABLE_L3,	SYSSTATUS,
-OCP_SYSCONFIG,
-
-/* omap1+ specific */
-CPC, CCR2, LCH_CTRL,
-
-/* Common registers for all omap's */
-CSDP,		CCR,		CICR,		CSR,
-CEN,		CFN,		CSFI,		CSEI,
-CSAC,		CDAC,		CDEI,
-CDFI,		CLNK_CTRL,
-
-/* Channel specific registers */
-CSSA,		CDSA,		COLOR,
-CCEN,		CCFN,
-
-/* omap3630 and omap4 specific */
-CDP,		CNDP,		CCDN,
-
-};
-
-enum omap_dma_burst_mode {
-	OMAP_DMA_DATA_BURST_DIS = 0,
-	OMAP_DMA_DATA_BURST_4,
-	OMAP_DMA_DATA_BURST_8,
-	OMAP_DMA_DATA_BURST_16,
-};
-
-enum end_type {
-	OMAP_DMA_LITTLE_ENDIAN = 0,
-	OMAP_DMA_BIG_ENDIAN
-};
-
-enum omap_dma_color_mode {
-	OMAP_DMA_COLOR_DIS = 0,
-	OMAP_DMA_CONSTANT_FILL,
-	OMAP_DMA_TRANSPARENT_COPY
-};
-
-enum omap_dma_write_mode {
-	OMAP_DMA_WRITE_NON_POSTED = 0,
-	OMAP_DMA_WRITE_POSTED,
-	OMAP_DMA_WRITE_LAST_NON_POSTED
-};
-
-enum omap_dma_channel_mode {
-	OMAP_DMA_LCH_2D = 0,
-	OMAP_DMA_LCH_G,
-	OMAP_DMA_LCH_P,
-	OMAP_DMA_LCH_PD
-};
-
-struct omap_dma_channel_params {
-	int data_type;		/* data type 8,16,32 */
-	int elem_count;		/* number of elements in a frame */
-	int frame_count;	/* number of frames in a element */
-
-	int src_port;		/* Only on OMAP1 REVISIT: Is this needed? */
-	int src_amode;		/* constant, post increment, indexed,
-					double indexed */
-	unsigned long src_start;	/* source address : physical */
-	int src_ei;		/* source element index */
-	int src_fi;		/* source frame index */
-
-	int dst_port;		/* Only on OMAP1 REVISIT: Is this needed? */
-	int dst_amode;		/* constant, post increment, indexed,
-					double indexed */
-	unsigned long dst_start;	/* source address : physical */
-	int dst_ei;		/* source element index */
-	int dst_fi;		/* source frame index */
-
-	int trigger;		/* trigger attached if the channel is
-					synchronized */
-	int sync_mode;		/* sycn on element, frame , block or packet */
-	int src_or_dst_synch;	/* source synch(1) or destination synch(0) */
-
-	int ie;			/* interrupt enabled */
-
-	unsigned char read_prio;/* read priority */
-	unsigned char write_prio;/* write priority */
-
-#ifndef CONFIG_ARCH_OMAP1
-	enum omap_dma_burst_mode burst_mode; /* Burst mode 4/8/16 words */
-#endif
-};
-
-struct omap_dma_lch {
-	int next_lch;
-	int dev_id;
-	u16 saved_csr;
-	u16 enabled_irqs;
-	const char *dev_name;
-	void (*callback)(int lch, u16 ch_status, void *data);
-	void *data;
-	long flags;
-	/* required for Dynamic chaining */
-	int prev_linked_ch;
-	int next_linked_ch;
-	int state;
-	int chain_id;
-	int status;
-};
-
-struct omap_dma_dev_attr {
-	u32 dev_caps;
-	u16 lch_count;
-	u16 chan_count;
-	struct omap_dma_lch *chan;
-};
-
-/* System DMA platform data structure */
-struct omap_system_dma_plat_info {
-	struct omap_dma_dev_attr *dma_attr;
-	u32 errata;
-	void (*disable_irq_lch)(int lch);
-	void (*show_dma_caps)(void);
-	void (*clear_lch_regs)(int lch);
-	void (*clear_dma)(int lch);
-	void (*dma_write)(u32 val, int reg, int lch);
-	u32 (*dma_read)(int reg, int lch);
-};
-
-#ifdef CONFIG_ARCH_OMAP2PLUS
-#define dma_omap2plus()	1
-#else
-#define dma_omap2plus()	0
-#endif
-#define dma_omap1()	(!dma_omap2plus())
-#define dma_omap15xx()	((dma_omap1() && (d->dev_caps & ENABLE_1510_MODE)))
-#define dma_omap16xx()	((dma_omap1() && (d->dev_caps & ENABLE_16XX_MODE)))
-
-extern void omap_set_dma_priority(int lch, int dst_port, int priority);
-extern int omap_request_dma(int dev_id, const char *dev_name,
-			void (*callback)(int lch, u16 ch_status, void *data),
-			void *data, int *dma_ch);
-extern void omap_enable_dma_irq(int ch, u16 irq_bits);
-extern void omap_disable_dma_irq(int ch, u16 irq_bits);
-extern void omap_free_dma(int ch);
-extern void omap_start_dma(int lch);
-extern void omap_stop_dma(int lch);
-extern void omap_set_dma_transfer_params(int lch, int data_type,
-					 int elem_count, int frame_count,
-					 int sync_mode,
-					 int dma_trigger, int src_or_dst_synch);
-extern void omap_set_dma_color_mode(int lch, enum omap_dma_color_mode mode,
-				    u32 color);
-extern void omap_set_dma_write_mode(int lch, enum omap_dma_write_mode mode);
-extern void omap_set_dma_channel_mode(int lch, enum omap_dma_channel_mode mode);
-
-extern void omap_set_dma_src_params(int lch, int src_port, int src_amode,
-				    unsigned long src_start,
-				    int src_ei, int src_fi);
-extern void omap_set_dma_src_index(int lch, int eidx, int fidx);
-extern void omap_set_dma_src_data_pack(int lch, int enable);
-extern void omap_set_dma_src_burst_mode(int lch,
-					enum omap_dma_burst_mode burst_mode);
-
-extern void omap_set_dma_dest_params(int lch, int dest_port, int dest_amode,
-				     unsigned long dest_start,
-				     int dst_ei, int dst_fi);
-extern void omap_set_dma_dest_index(int lch, int eidx, int fidx);
-extern void omap_set_dma_dest_data_pack(int lch, int enable);
-extern void omap_set_dma_dest_burst_mode(int lch,
-					 enum omap_dma_burst_mode burst_mode);
-
-extern void omap_set_dma_params(int lch,
-				struct omap_dma_channel_params *params);
-
-extern void omap_dma_link_lch(int lch_head, int lch_queue);
-extern void omap_dma_unlink_lch(int lch_head, int lch_queue);
-
-extern int omap_set_dma_callback(int lch,
-			void (*callback)(int lch, u16 ch_status, void *data),
-			void *data);
-extern dma_addr_t omap_get_dma_src_pos(int lch);
-extern dma_addr_t omap_get_dma_dst_pos(int lch);
-extern void omap_clear_dma(int lch);
-extern int omap_get_dma_active_status(int lch);
-extern int omap_dma_running(void);
-extern void omap_dma_set_global_params(int arb_rate, int max_fifo_depth,
-				       int tparams);
-extern int omap_dma_set_prio_lch(int lch, unsigned char read_prio,
-				 unsigned char write_prio);
-extern void omap_set_dma_dst_endian_type(int lch, enum end_type etype);
-extern void omap_set_dma_src_endian_type(int lch, enum end_type etype);
-extern int omap_get_dma_index(int lch, int *ei, int *fi);
-
-void omap_dma_global_context_save(void);
-void omap_dma_global_context_restore(void);
-
-extern void omap_dma_disable_irq(int lch);
-
-/* Chaining APIs */
-#ifndef CONFIG_ARCH_OMAP1
-extern int omap_request_dma_chain(int dev_id, const char *dev_name,
-				  void (*callback) (int lch, u16 ch_status,
-						    void *data),
-				  int *chain_id, int no_of_chans,
-				  int chain_mode,
-				  struct omap_dma_channel_params params);
-extern int omap_free_dma_chain(int chain_id);
-extern int omap_dma_chain_a_transfer(int chain_id, int src_start,
-				     int dest_start, int elem_count,
-				     int frame_count, void *callbk_data);
-extern int omap_start_dma_chain_transfers(int chain_id);
-extern int omap_stop_dma_chain_transfers(int chain_id);
-extern int omap_get_dma_chain_index(int chain_id, int *ei, int *fi);
-extern int omap_get_dma_chain_dst_pos(int chain_id);
-extern int omap_get_dma_chain_src_pos(int chain_id);
-
-extern int omap_modify_dma_chain_params(int chain_id,
-					struct omap_dma_channel_params params);
-extern int omap_dma_chain_status(int chain_id);
-#endif
-
-#if defined(CONFIG_ARCH_OMAP1) && defined(CONFIG_FB_OMAP)
-#include <mach/lcd_dma.h>
-#else
-static inline int omap_lcd_dma_running(void)
-{
-	return 0;
-}
-#endif
-
-#endif /* __ASM_ARCH_DMA_H */
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index 649a146e1382..e66e8ee5a9af 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -29,7 +29,7 @@
 #include <crypto/scatterwalk.h>
 #include <crypto/aes.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 /* OMAP TRM gives bitfields as start:end, where start is the higher bit
    number. For example 7:0 */
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index d76fe06b9417..1d75e6f95a58 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -37,7 +37,7 @@
 #include <crypto/hash.h>
 #include <crypto/internal/hash.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <mach/irqs.h>
 
 #define SHA_REG_DIGEST(x)		(0x00 + ((x) * 0x04))
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index 7d35c237fbf1..5a31264f2bd1 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -19,8 +19,6 @@
 
 #include "virt-dma.h"
 
-#include <plat-omap/dma-omap.h>
-
 struct omap_dmadev {
 	struct dma_device ddev;
 	spinlock_t lock;
diff --git a/drivers/media/platform/omap/omap_vout.c b/drivers/media/platform/omap/omap_vout.c
index 4b1becc86e54..993504015963 100644
--- a/drivers/media/platform/omap/omap_vout.c
+++ b/drivers/media/platform/omap/omap_vout.c
@@ -45,7 +45,7 @@
 #include <media/v4l2-ioctl.h>
 
 #include <plat/cpu.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <video/omapvrfb.h>
 #include <video/omapdss.h>
 
diff --git a/drivers/media/platform/omap/omap_vout_vrfb.c b/drivers/media/platform/omap/omap_vout_vrfb.c
index 8340445a0ee5..cf1c437a8687 100644
--- a/drivers/media/platform/omap/omap_vout_vrfb.c
+++ b/drivers/media/platform/omap/omap_vout_vrfb.c
@@ -16,7 +16,7 @@
 #include <media/videobuf-dma-contig.h>
 #include <media/v4l2-device.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <video/omapvrfb.h>
 
 #include "omap_voutdef.h"
diff --git a/drivers/media/platform/omap3isp/ispstat.h b/drivers/media/platform/omap3isp/ispstat.h
index 40f87cdd7994..bb363742bd1c 100644
--- a/drivers/media/platform/omap3isp/ispstat.h
+++ b/drivers/media/platform/omap3isp/ispstat.h
@@ -30,7 +30,7 @@
 
 #include <linux/types.h>
 #include <linux/omap3isp.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 #include <media/v4l2-event.h>
 
 #include "isp.h"
diff --git a/drivers/media/platform/soc_camera/omap1_camera.c b/drivers/media/platform/soc_camera/omap1_camera.c
index cae9ce6275e9..611595f1a75e 100644
--- a/drivers/media/platform/soc_camera/omap1_camera.c
+++ b/drivers/media/platform/soc_camera/omap1_camera.c
@@ -34,7 +34,7 @@
 #include <media/videobuf-dma-contig.h>
 #include <media/videobuf-dma-sg.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 
 #define DRIVER_NAME		"omap1-camera"
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 5c8978e90240..1f34ba104ef4 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -27,7 +27,6 @@
 #include <linux/bch.h>
 #endif
 
-#include <plat-omap/dma-omap.h>
 #include <linux/platform_data/mtd-nand-omap2.h>
 
 #define	DRIVER_NAME	"omap2-nand"
diff --git a/drivers/mtd/onenand/omap2.c b/drivers/mtd/onenand/omap2.c
index 99f96e19ebea..00cd3da29435 100644
--- a/drivers/mtd/onenand/omap2.c
+++ b/drivers/mtd/onenand/omap2.c
@@ -41,7 +41,7 @@
 #include <linux/platform_data/mtd-onenand-omap2.h>
 #include <asm/gpio.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #define DRIVER_NAME "omap2-onenand"
 
diff --git a/drivers/usb/gadget/omap_udc.c b/drivers/usb/gadget/omap_udc.c
index 23afa06b65a4..1b8ddc3ddc50 100644
--- a/drivers/usb/gadget/omap_udc.c
+++ b/drivers/usb/gadget/omap_udc.c
@@ -44,7 +44,7 @@
 #include <asm/unaligned.h>
 #include <asm/mach-types.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include <mach/usb.h>
 
diff --git a/drivers/usb/musb/tusb6010_omap.c b/drivers/usb/musb/tusb6010_omap.c
index bfca114f7c56..82310b6bc97b 100644
--- a/drivers/usb/musb/tusb6010_omap.c
+++ b/drivers/usb/musb/tusb6010_omap.c
@@ -16,7 +16,7 @@
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include "musb_core.h"
 #include "tusb6010.h"
diff --git a/drivers/video/omap/lcdc.c b/drivers/video/omap/lcdc.c
index c39d6e46f8c5..b52f62595f65 100644
--- a/drivers/video/omap/lcdc.c
+++ b/drivers/video/omap/lcdc.c
@@ -31,7 +31,7 @@
 #include <linux/gfp.h>
 
 #include <mach/lcdc.h>
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include <asm/mach-types.h>
 
diff --git a/drivers/video/omap/omapfb_main.c b/drivers/video/omap/omapfb_main.c
index 1b5ee8ec192a..e31f5b33b501 100644
--- a/drivers/video/omap/omapfb_main.c
+++ b/drivers/video/omap/omapfb_main.c
@@ -30,7 +30,7 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include "omapfb.h"
 #include "lcdc.h"
diff --git a/drivers/video/omap/sossi.c b/drivers/video/omap/sossi.c
index c510a4457398..d4e7684e7045 100644
--- a/drivers/video/omap/sossi.c
+++ b/drivers/video/omap/sossi.c
@@ -25,7 +25,7 @@
 #include <linux/io.h>
 #include <linux/interrupt.h>
 
-#include <plat-omap/dma-omap.h>
+#include <linux/omap-dma.h>
 
 #include "omapfb.h"
 #include "lcdc.h"
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index eb475a8ea25b..7af25a9c9c51 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -19,4 +19,370 @@ static inline bool omap_dma_filter_fn(struct dma_chan *c, void *d)
 }
 #endif
 
+/*
+ *  Legacy OMAP DMA handling defines and functions
+ *
+ *  NOTE: Do not use these any longer.
+ *
+ *  Use the generic dmaengine functions as defined in
+ *  include/linux/dmaengine.h.
+ *
+ *  Copyright (C) 2003 Nokia Corporation
+ *  Author: Juha Yrjölä <juha.yrjola@nokia.com>
+ *
+ */
+
+#include <linux/platform_device.h>
+
+#define INT_DMA_LCD			25
+
+#define OMAP1_DMA_TOUT_IRQ		(1 << 0)
+#define OMAP_DMA_DROP_IRQ		(1 << 1)
+#define OMAP_DMA_HALF_IRQ		(1 << 2)
+#define OMAP_DMA_FRAME_IRQ		(1 << 3)
+#define OMAP_DMA_LAST_IRQ		(1 << 4)
+#define OMAP_DMA_BLOCK_IRQ		(1 << 5)
+#define OMAP1_DMA_SYNC_IRQ		(1 << 6)
+#define OMAP2_DMA_PKT_IRQ		(1 << 7)
+#define OMAP2_DMA_TRANS_ERR_IRQ		(1 << 8)
+#define OMAP2_DMA_SECURE_ERR_IRQ	(1 << 9)
+#define OMAP2_DMA_SUPERVISOR_ERR_IRQ	(1 << 10)
+#define OMAP2_DMA_MISALIGNED_ERR_IRQ	(1 << 11)
+
+#define OMAP_DMA_CCR_EN			(1 << 7)
+#define OMAP_DMA_CCR_RD_ACTIVE		(1 << 9)
+#define OMAP_DMA_CCR_WR_ACTIVE		(1 << 10)
+#define OMAP_DMA_CCR_SEL_SRC_DST_SYNC	(1 << 24)
+#define OMAP_DMA_CCR_BUFFERING_DISABLE	(1 << 25)
+
+#define OMAP_DMA_DATA_TYPE_S8		0x00
+#define OMAP_DMA_DATA_TYPE_S16		0x01
+#define OMAP_DMA_DATA_TYPE_S32		0x02
+
+#define OMAP_DMA_SYNC_ELEMENT		0x00
+#define OMAP_DMA_SYNC_FRAME		0x01
+#define OMAP_DMA_SYNC_BLOCK		0x02
+#define OMAP_DMA_SYNC_PACKET		0x03
+
+#define OMAP_DMA_DST_SYNC_PREFETCH	0x02
+#define OMAP_DMA_SRC_SYNC		0x01
+#define OMAP_DMA_DST_SYNC		0x00
+
+#define OMAP_DMA_PORT_EMIFF		0x00
+#define OMAP_DMA_PORT_EMIFS		0x01
+#define OMAP_DMA_PORT_OCP_T1		0x02
+#define OMAP_DMA_PORT_TIPB		0x03
+#define OMAP_DMA_PORT_OCP_T2		0x04
+#define OMAP_DMA_PORT_MPUI		0x05
+
+#define OMAP_DMA_AMODE_CONSTANT		0x00
+#define OMAP_DMA_AMODE_POST_INC		0x01
+#define OMAP_DMA_AMODE_SINGLE_IDX	0x02
+#define OMAP_DMA_AMODE_DOUBLE_IDX	0x03
+
+#define DMA_DEFAULT_FIFO_DEPTH		0x10
+#define DMA_DEFAULT_ARB_RATE		0x01
+/* Pass THREAD_RESERVE ORed with THREAD_FIFO for tparams */
+#define DMA_THREAD_RESERVE_NORM		(0x00 << 12) /* Def */
+#define DMA_THREAD_RESERVE_ONET		(0x01 << 12)
+#define DMA_THREAD_RESERVE_TWOT		(0x02 << 12)
+#define DMA_THREAD_RESERVE_THREET	(0x03 << 12)
+#define DMA_THREAD_FIFO_NONE		(0x00 << 14) /* Def */
+#define DMA_THREAD_FIFO_75		(0x01 << 14)
+#define DMA_THREAD_FIFO_25		(0x02 << 14)
+#define DMA_THREAD_FIFO_50		(0x03 << 14)
+
+/* DMA4_OCP_SYSCONFIG bits */
+#define DMA_SYSCONFIG_MIDLEMODE_MASK		(3 << 12)
+#define DMA_SYSCONFIG_CLOCKACTIVITY_MASK	(3 << 8)
+#define DMA_SYSCONFIG_EMUFREE			(1 << 5)
+#define DMA_SYSCONFIG_SIDLEMODE_MASK		(3 << 3)
+#define DMA_SYSCONFIG_SOFTRESET			(1 << 2)
+#define DMA_SYSCONFIG_AUTOIDLE			(1 << 0)
+
+#define DMA_SYSCONFIG_MIDLEMODE(n)		((n) << 12)
+#define DMA_SYSCONFIG_SIDLEMODE(n)		((n) << 3)
+
+#define DMA_IDLEMODE_SMARTIDLE			0x2
+#define DMA_IDLEMODE_NO_IDLE			0x1
+#define DMA_IDLEMODE_FORCE_IDLE			0x0
+
+/* Chaining modes*/
+#ifndef CONFIG_ARCH_OMAP1
+#define OMAP_DMA_STATIC_CHAIN		0x1
+#define OMAP_DMA_DYNAMIC_CHAIN		0x2
+#define OMAP_DMA_CHAIN_ACTIVE		0x1
+#define OMAP_DMA_CHAIN_INACTIVE		0x0
+#endif
+
+#define DMA_CH_PRIO_HIGH		0x1
+#define DMA_CH_PRIO_LOW			0x0 /* Def */
+
+/* Errata handling */
+#define IS_DMA_ERRATA(id)		(errata & (id))
+#define SET_DMA_ERRATA(id)		(errata |= (id))
+
+#define DMA_ERRATA_IFRAME_BUFFERING	BIT(0x0)
+#define DMA_ERRATA_PARALLEL_CHANNELS	BIT(0x1)
+#define DMA_ERRATA_i378			BIT(0x2)
+#define DMA_ERRATA_i541			BIT(0x3)
+#define DMA_ERRATA_i88			BIT(0x4)
+#define DMA_ERRATA_3_3			BIT(0x5)
+#define DMA_ROMCODE_BUG			BIT(0x6)
+
+/* Attributes for OMAP DMA Contrller */
+#define DMA_LINKED_LCH			BIT(0x0)
+#define GLOBAL_PRIORITY			BIT(0x1)
+#define RESERVE_CHANNEL			BIT(0x2)
+#define IS_CSSA_32			BIT(0x3)
+#define IS_CDSA_32			BIT(0x4)
+#define IS_RW_PRIORITY			BIT(0x5)
+#define ENABLE_1510_MODE		BIT(0x6)
+#define SRC_PORT			BIT(0x7)
+#define DST_PORT			BIT(0x8)
+#define SRC_INDEX			BIT(0x9)
+#define DST_INDEX			BIT(0xa)
+#define IS_BURST_ONLY4			BIT(0xb)
+#define CLEAR_CSR_ON_READ		BIT(0xc)
+#define IS_WORD_16			BIT(0xd)
+#define ENABLE_16XX_MODE		BIT(0xe)
+#define HS_CHANNELS_RESERVED		BIT(0xf)
+
+/* Defines for DMA Capabilities */
+#define DMA_HAS_TRANSPARENT_CAPS	(0x1 << 18)
+#define DMA_HAS_CONSTANT_FILL_CAPS	(0x1 << 19)
+#define DMA_HAS_DESCRIPTOR_CAPS		(0x3 << 20)
+
+enum omap_reg_offsets {
+
+GCR,		GSCR,		GRST1,		HW_ID,
+PCH2_ID,	PCH0_ID,	PCH1_ID,	PCHG_ID,
+PCHD_ID,	CAPS_0,		CAPS_1,		CAPS_2,
+CAPS_3,		CAPS_4,		PCH2_SR,	PCH0_SR,
+PCH1_SR,	PCHD_SR,	REVISION,	IRQSTATUS_L0,
+IRQSTATUS_L1,	IRQSTATUS_L2,	IRQSTATUS_L3,	IRQENABLE_L0,
+IRQENABLE_L1,	IRQENABLE_L2,	IRQENABLE_L3,	SYSSTATUS,
+OCP_SYSCONFIG,
+
+/* omap1+ specific */
+CPC, CCR2, LCH_CTRL,
+
+/* Common registers for all omap's */
+CSDP,		CCR,		CICR,		CSR,
+CEN,		CFN,		CSFI,		CSEI,
+CSAC,		CDAC,		CDEI,
+CDFI,		CLNK_CTRL,
+
+/* Channel specific registers */
+CSSA,		CDSA,		COLOR,
+CCEN,		CCFN,
+
+/* omap3630 and omap4 specific */
+CDP,		CNDP,		CCDN,
+
+};
+
+enum omap_dma_burst_mode {
+	OMAP_DMA_DATA_BURST_DIS = 0,
+	OMAP_DMA_DATA_BURST_4,
+	OMAP_DMA_DATA_BURST_8,
+	OMAP_DMA_DATA_BURST_16,
+};
+
+enum end_type {
+	OMAP_DMA_LITTLE_ENDIAN = 0,
+	OMAP_DMA_BIG_ENDIAN
+};
+
+enum omap_dma_color_mode {
+	OMAP_DMA_COLOR_DIS = 0,
+	OMAP_DMA_CONSTANT_FILL,
+	OMAP_DMA_TRANSPARENT_COPY
+};
+
+enum omap_dma_write_mode {
+	OMAP_DMA_WRITE_NON_POSTED = 0,
+	OMAP_DMA_WRITE_POSTED,
+	OMAP_DMA_WRITE_LAST_NON_POSTED
+};
+
+enum omap_dma_channel_mode {
+	OMAP_DMA_LCH_2D = 0,
+	OMAP_DMA_LCH_G,
+	OMAP_DMA_LCH_P,
+	OMAP_DMA_LCH_PD
+};
+
+struct omap_dma_channel_params {
+	int data_type;		/* data type 8,16,32 */
+	int elem_count;		/* number of elements in a frame */
+	int frame_count;	/* number of frames in a element */
+
+	int src_port;		/* Only on OMAP1 REVISIT: Is this needed? */
+	int src_amode;		/* constant, post increment, indexed,
+					double indexed */
+	unsigned long src_start;	/* source address : physical */
+	int src_ei;		/* source element index */
+	int src_fi;		/* source frame index */
+
+	int dst_port;		/* Only on OMAP1 REVISIT: Is this needed? */
+	int dst_amode;		/* constant, post increment, indexed,
+					double indexed */
+	unsigned long dst_start;	/* source address : physical */
+	int dst_ei;		/* source element index */
+	int dst_fi;		/* source frame index */
+
+	int trigger;		/* trigger attached if the channel is
+					synchronized */
+	int sync_mode;		/* sycn on element, frame , block or packet */
+	int src_or_dst_synch;	/* source synch(1) or destination synch(0) */
+
+	int ie;			/* interrupt enabled */
+
+	unsigned char read_prio;/* read priority */
+	unsigned char write_prio;/* write priority */
+
+#ifndef CONFIG_ARCH_OMAP1
+	enum omap_dma_burst_mode burst_mode; /* Burst mode 4/8/16 words */
+#endif
+};
+
+struct omap_dma_lch {
+	int next_lch;
+	int dev_id;
+	u16 saved_csr;
+	u16 enabled_irqs;
+	const char *dev_name;
+	void (*callback)(int lch, u16 ch_status, void *data);
+	void *data;
+	long flags;
+	/* required for Dynamic chaining */
+	int prev_linked_ch;
+	int next_linked_ch;
+	int state;
+	int chain_id;
+	int status;
+};
+
+struct omap_dma_dev_attr {
+	u32 dev_caps;
+	u16 lch_count;
+	u16 chan_count;
+	struct omap_dma_lch *chan;
+};
+
+/* System DMA platform data structure */
+struct omap_system_dma_plat_info {
+	struct omap_dma_dev_attr *dma_attr;
+	u32 errata;
+	void (*disable_irq_lch)(int lch);
+	void (*show_dma_caps)(void);
+	void (*clear_lch_regs)(int lch);
+	void (*clear_dma)(int lch);
+	void (*dma_write)(u32 val, int reg, int lch);
+	u32 (*dma_read)(int reg, int lch);
+};
+
+#ifdef CONFIG_ARCH_OMAP2PLUS
+#define dma_omap2plus()	1
+#else
+#define dma_omap2plus()	0
 #endif
+#define dma_omap1()	(!dma_omap2plus())
+#define dma_omap15xx()	((dma_omap1() && (d->dev_caps & ENABLE_1510_MODE)))
+#define dma_omap16xx()	((dma_omap1() && (d->dev_caps & ENABLE_16XX_MODE)))
+
+extern void omap_set_dma_priority(int lch, int dst_port, int priority);
+extern int omap_request_dma(int dev_id, const char *dev_name,
+			void (*callback)(int lch, u16 ch_status, void *data),
+			void *data, int *dma_ch);
+extern void omap_enable_dma_irq(int ch, u16 irq_bits);
+extern void omap_disable_dma_irq(int ch, u16 irq_bits);
+extern void omap_free_dma(int ch);
+extern void omap_start_dma(int lch);
+extern void omap_stop_dma(int lch);
+extern void omap_set_dma_transfer_params(int lch, int data_type,
+					 int elem_count, int frame_count,
+					 int sync_mode,
+					 int dma_trigger, int src_or_dst_synch);
+extern void omap_set_dma_color_mode(int lch, enum omap_dma_color_mode mode,
+				    u32 color);
+extern void omap_set_dma_write_mode(int lch, enum omap_dma_write_mode mode);
+extern void omap_set_dma_channel_mode(int lch, enum omap_dma_channel_mode mode);
+
+extern void omap_set_dma_src_params(int lch, int src_port, int src_amode,
+				    unsigned long src_start,
+				    int src_ei, int src_fi);
+extern void omap_set_dma_src_index(int lch, int eidx, int fidx);
+extern void omap_set_dma_src_data_pack(int lch, int enable);
+extern void omap_set_dma_src_burst_mode(int lch,
+					enum omap_dma_burst_mode burst_mode);
+
+extern void omap_set_dma_dest_params(int lch, int dest_port, int dest_amode,
+				     unsigned long dest_start,
+				     int dst_ei, int dst_fi);
+extern void omap_set_dma_dest_index(int lch, int eidx, int fidx);
+extern void omap_set_dma_dest_data_pack(int lch, int enable);
+extern void omap_set_dma_dest_burst_mode(int lch,
+					 enum omap_dma_burst_mode burst_mode);
+
+extern void omap_set_dma_params(int lch,
+				struct omap_dma_channel_params *params);
+
+extern void omap_dma_link_lch(int lch_head, int lch_queue);
+extern void omap_dma_unlink_lch(int lch_head, int lch_queue);
+
+extern int omap_set_dma_callback(int lch,
+			void (*callback)(int lch, u16 ch_status, void *data),
+			void *data);
+extern dma_addr_t omap_get_dma_src_pos(int lch);
+extern dma_addr_t omap_get_dma_dst_pos(int lch);
+extern void omap_clear_dma(int lch);
+extern int omap_get_dma_active_status(int lch);
+extern int omap_dma_running(void);
+extern void omap_dma_set_global_params(int arb_rate, int max_fifo_depth,
+				       int tparams);
+extern int omap_dma_set_prio_lch(int lch, unsigned char read_prio,
+				 unsigned char write_prio);
+extern void omap_set_dma_dst_endian_type(int lch, enum end_type etype);
+extern void omap_set_dma_src_endian_type(int lch, enum end_type etype);
+extern int omap_get_dma_index(int lch, int *ei, int *fi);
+
+void omap_dma_global_context_save(void);
+void omap_dma_global_context_restore(void);
+
+extern void omap_dma_disable_irq(int lch);
+
+/* Chaining APIs */
+#ifndef CONFIG_ARCH_OMAP1
+extern int omap_request_dma_chain(int dev_id, const char *dev_name,
+				  void (*callback) (int lch, u16 ch_status,
+						    void *data),
+				  int *chain_id, int no_of_chans,
+				  int chain_mode,
+				  struct omap_dma_channel_params params);
+extern int omap_free_dma_chain(int chain_id);
+extern int omap_dma_chain_a_transfer(int chain_id, int src_start,
+				     int dest_start, int elem_count,
+				     int frame_count, void *callbk_data);
+extern int omap_start_dma_chain_transfers(int chain_id);
+extern int omap_stop_dma_chain_transfers(int chain_id);
+extern int omap_get_dma_chain_index(int chain_id, int *ei, int *fi);
+extern int omap_get_dma_chain_dst_pos(int chain_id);
+extern int omap_get_dma_chain_src_pos(int chain_id);
+
+extern int omap_modify_dma_chain_params(int chain_id,
+					struct omap_dma_channel_params params);
+extern int omap_dma_chain_status(int chain_id);
+#endif
+
+#if defined(CONFIG_ARCH_OMAP1) && defined(CONFIG_FB_OMAP)
+#include <mach/lcd_dma.h>
+#else
+static inline int omap_lcd_dma_running(void)
+{
+	return 0;
+}
+#endif
+
+#endif /* __LINUX_OMAP_DMA_H */
-- 
cgit v1.2.3-55-g7522


From 9a4da8a5b109906a64bed5aaeb83bf4edb1f5888 Mon Sep 17 00:00:00 2001
From: Jan Glauber
Date: Thu, 29 Nov 2012 13:05:05 +0100
Subject: s390/pci: PCI adapter interrupts for MSI/MSI-X

Support PCI adapter interrupts using the Single-IRQ-mode. Single-IRQ-mode
disables an adapter IRQ automatically after delivering it until the SIC
instruction enables it again. This is used to reduce the number of IRQs
for streaming workloads.

Up to 64 MSI handlers can be registered per PCI function.
A hash table is used to map interrupt numbers to MSI descriptors.
The interrupt vector is scanned using the flogr instruction.
Only MSI/MSI-X interrupts are supported, no legacy INTs.

Signed-off-by: Jan Glauber <jang@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/hw_irq.h |  22 ++
 arch/s390/include/asm/irq.h    |  12 ++
 arch/s390/include/asm/isc.h    |   1 +
 arch/s390/include/asm/pci.h    |  27 +++
 arch/s390/kernel/irq.c         |   2 +
 arch/s390/pci/Makefile         |   2 +-
 arch/s390/pci/pci.c            | 464 ++++++++++++++++++++++++++++++++++++++++-
 arch/s390/pci/pci_clp.c        |   3 +
 arch/s390/pci/pci_msi.c        | 141 +++++++++++++
 drivers/pci/msi.c              |   6 +
 include/linux/irq.h            |  10 +-
 11 files changed, 683 insertions(+), 7 deletions(-)
 create mode 100644 arch/s390/include/asm/hw_irq.h
 create mode 100644 arch/s390/pci/pci_msi.c

(limited to 'include')

diff --git a/arch/s390/include/asm/hw_irq.h b/arch/s390/include/asm/hw_irq.h
new file mode 100644
index 000000000000..7e3d2586c1ff
--- /dev/null
+++ b/arch/s390/include/asm/hw_irq.h
@@ -0,0 +1,22 @@
+#ifndef _HW_IRQ_H
+#define _HW_IRQ_H
+
+#include <linux/msi.h>
+#include <linux/pci.h>
+
+static inline struct msi_desc *irq_get_msi_desc(unsigned int irq)
+{
+	return __irq_get_msi_desc(irq);
+}
+
+/* Must be called with msi map lock held */
+static inline int irq_set_msi_desc(unsigned int irq, struct msi_desc *msi)
+{
+	if (!msi)
+		return -EINVAL;
+
+	msi->irq = irq;
+	return 0;
+}
+
+#endif
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index 6703dd986fd4..e6972f85d2b0 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -33,6 +33,8 @@ enum interruption_class {
 	IOINT_APB,
 	IOINT_ADM,
 	IOINT_CSC,
+	IOINT_PCI,
+	IOINT_MSI,
 	NMI_NMI,
 	NR_IRQS,
 };
@@ -51,4 +53,14 @@ void service_subclass_irq_unregister(void);
 void measurement_alert_subclass_register(void);
 void measurement_alert_subclass_unregister(void);
 
+#ifdef CONFIG_LOCKDEP
+#  define disable_irq_nosync_lockdep(irq)	disable_irq_nosync(irq)
+#  define disable_irq_nosync_lockdep_irqsave(irq, flags) \
+						disable_irq_nosync(irq)
+#  define disable_irq_lockdep(irq)		disable_irq(irq)
+#  define enable_irq_lockdep(irq)		enable_irq(irq)
+#  define enable_irq_lockdep_irqrestore(irq, flags) \
+						enable_irq(irq)
+#endif
+
 #endif /* _ASM_IRQ_H */
diff --git a/arch/s390/include/asm/isc.h b/arch/s390/include/asm/isc.h
index 5ae606456b0a..68d7d68300f2 100644
--- a/arch/s390/include/asm/isc.h
+++ b/arch/s390/include/asm/isc.h
@@ -18,6 +18,7 @@
 #define CHSC_SCH_ISC 7			/* CHSC subchannels */
 /* Adapter interrupts. */
 #define QDIO_AIRQ_ISC IO_SCH_ISC	/* I/O subchannel in qdio mode */
+#define PCI_ISC 2			/* PCI I/O subchannels */
 #define AP_ISC 6			/* adjunct processor (crypto) devices */
 
 /* Functions for registration of I/O interruption subclasses */
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 6f98a54950ea..2a6084fa4b1a 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -20,6 +20,10 @@ void pci_iounmap(struct pci_dev *, void __iomem *);
 int pci_domain_nr(struct pci_bus *);
 int pci_proc_domain(struct pci_bus *);
 
+/* MSI arch hooks */
+#define arch_setup_msi_irqs	arch_setup_msi_irqs
+#define arch_teardown_msi_irqs	arch_teardown_msi_irqs
+
 #define ZPCI_BUS_NR			0	/* default bus number */
 #define ZPCI_DEVFN			0	/* default device number */
 
@@ -29,6 +33,15 @@ int pci_proc_domain(struct pci_bus *);
 #define ZPCI_FC_BLOCKED			0x20
 #define ZPCI_FC_DMA_ENABLED		0x10
 
+struct msi_map {
+	unsigned long irq;
+	struct msi_desc *msi;
+	struct hlist_node msi_chain;
+};
+
+#define ZPCI_NR_MSI_VECS	64
+#define ZPCI_MSI_MASK		(ZPCI_NR_MSI_VECS - 1)
+
 enum zpci_state {
 	ZPCI_FN_STATE_RESERVED,
 	ZPCI_FN_STATE_STANDBY,
@@ -56,6 +69,12 @@ struct zpci_dev {
 	u8		pfgid;		/* function group ID */
 	u16		domain;
 
+	/* IRQ stuff */
+	u64		msi_addr;	/* MSI address */
+	struct zdev_irq_map *irq_map;
+	struct msi_map *msi_map[ZPCI_NR_MSI_VECS];
+	unsigned int	aisb;		/* number of the summary bit */
+
 	struct zpci_bar_struct bars[PCI_BAR_COUNT];
 
 	enum pci_bus_speed max_bus_speed;
@@ -83,6 +102,14 @@ int clp_add_pci_device(u32, u32, int);
 int clp_enable_fh(struct zpci_dev *, u8);
 int clp_disable_fh(struct zpci_dev *);
 
+/* MSI */
+struct msi_desc *__irq_get_msi_desc(unsigned int);
+int zpci_msi_set_mask_bits(struct msi_desc *, u32, u32);
+int zpci_setup_msi_irq(struct zpci_dev *, struct msi_desc *, unsigned int, int);
+void zpci_teardown_msi_irq(struct zpci_dev *, struct msi_desc *);
+int zpci_msihash_init(void);
+void zpci_msihash_exit(void);
+
 /* Helpers */
 struct zpci_dev *get_zdev(struct pci_dev *);
 struct zpci_dev *get_zdev_by_fid(u32);
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 6cdc55b26d68..bf24293970ce 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -58,6 +58,8 @@ static const struct irq_class intrclass_names[] = {
 	[IOINT_APB]  = {.name = "APB", .desc = "[I/O] AP Bus"},
 	[IOINT_ADM]  = {.name = "ADM", .desc = "[I/O] EADM Subchannel"},
 	[IOINT_CSC]  = {.name = "CSC", .desc = "[I/O] CHSC Subchannel"},
+	[IOINT_PCI]  = {.name = "PCI", .desc = "[I/O] PCI Interrupt" },
+	[IOINT_MSI] =  {.name = "MSI", .desc = "[I/O] MSI Interrupt" },
 	[NMI_NMI]    = {.name = "NMI", .desc = "[NMI] Machine Check"},
 };
 
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index 1afd68c4c984..628be7bc006c 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -2,4 +2,4 @@
 # Makefile for the s390 PCI subsystem.
 #
 
-obj-$(CONFIG_PCI)	+= pci.o pci_clp.o
+obj-$(CONFIG_PCI)	+= pci.o pci_clp.o pci_msi.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 70f6c56c8d0f..d11dc8a25f34 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -23,17 +23,25 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/kernel_stat.h>
 #include <linux/seq_file.h>
 #include <linux/pci.h>
 #include <linux/msi.h>
 
+#include <asm/isc.h>
+#include <asm/airq.h>
 #include <asm/facility.h>
 #include <asm/pci_insn.h>
 #include <asm/pci_clp.h>
 
 #define DEBUG				/* enable pr_debug */
 
+#define	SIC_IRQ_MODE_ALL		0
+#define	SIC_IRQ_MODE_SINGLE		1
+
 #define ZPCI_NR_DMA_SPACES		1
+#define ZPCI_MSI_VEC_BITS		6
 #define ZPCI_NR_DEVICES			CONFIG_PCI_NR_FUNCTIONS
 
 /* list of all detected zpci devices */
@@ -43,12 +51,63 @@ DEFINE_MUTEX(zpci_list_lock);
 static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
 static DEFINE_SPINLOCK(zpci_domain_lock);
 
+struct callback {
+	irq_handler_t	handler;
+	void		*data;
+};
+
+struct zdev_irq_map {
+	unsigned long	aibv;		/* AI bit vector */
+	int		msi_vecs;	/* consecutive MSI-vectors used */
+	int		__unused;
+	struct callback	cb[ZPCI_NR_MSI_VECS]; /* callback handler array */
+	spinlock_t	lock;		/* protect callbacks against de-reg */
+};
+
+struct intr_bucket {
+	/* amap of adapters, one bit per dev, corresponds to one irq nr */
+	unsigned long	*alloc;
+	/* AI summary bit, global page for all devices */
+	unsigned long	*aisb;
+	/* pointer to aibv and callback data in zdev */
+	struct zdev_irq_map *imap[ZPCI_NR_DEVICES];
+	/* protects the whole bucket struct */
+	spinlock_t	lock;
+};
+
+static struct intr_bucket *bucket;
+
+/* Adapter local summary indicator */
+static u8 *zpci_irq_si;
+
+static atomic_t irq_retries = ATOMIC_INIT(0);
+
 /* I/O Map */
 static DEFINE_SPINLOCK(zpci_iomap_lock);
 static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
 struct zpci_iomap_entry *zpci_iomap_start;
 EXPORT_SYMBOL_GPL(zpci_iomap_start);
 
+/* highest irq summary bit */
+static int __read_mostly aisb_max;
+
+static struct kmem_cache *zdev_irq_cache;
+
+static inline int irq_to_msi_nr(unsigned int irq)
+{
+	return irq & ZPCI_MSI_MASK;
+}
+
+static inline int irq_to_dev_nr(unsigned int irq)
+{
+	return irq >> ZPCI_MSI_VEC_BITS;
+}
+
+static inline struct zdev_irq_map *get_imap(unsigned int irq)
+{
+	return bucket->imap[irq_to_dev_nr(irq)];
+}
+
 struct zpci_dev *get_zdev(struct pci_dev *pdev)
 {
 	return (struct zpci_dev *) pdev->sysdata;
@@ -120,6 +179,67 @@ static int zpci_store_fib(struct zpci_dev *zdev, u8 *fc)
 	return (cc) ? -EIO : 0;
 }
 
+/* Modify PCI: Register adapter interruptions */
+static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb,
+			      u64 aibv)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
+	struct zpci_fib *fib;
+	int rc;
+
+	fib = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!fib)
+		return -ENOMEM;
+
+	fib->isc = PCI_ISC;
+	fib->noi = zdev->irq_map->msi_vecs;
+	fib->sum = 1;		/* enable summary notifications */
+	fib->aibv = aibv;
+	fib->aibvo = 0;		/* every function has its own page */
+	fib->aisb = (u64) bucket->aisb + aisb / 8;
+	fib->aisbo = aisb & ZPCI_MSI_MASK;
+
+	rc = mpcifc_instr(req, fib);
+	pr_debug("%s mpcifc returned noi: %d\n", __func__, fib->noi);
+
+	free_page((unsigned long) fib);
+	return rc;
+}
+
+struct mod_pci_args {
+	u64 base;
+	u64 limit;
+	u64 iota;
+};
+
+static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args *args)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, fn);
+	struct zpci_fib *fib;
+	int rc;
+
+	/* The FIB must be available even if it's not used */
+	fib = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!fib)
+		return -ENOMEM;
+
+	fib->pba = args->base;
+	fib->pal = args->limit;
+	fib->iota = args->iota;
+
+	rc = mpcifc_instr(req, fib);
+	free_page((unsigned long) fib);
+	return rc;
+}
+
+/* Modify PCI: Unregister adapter interruptions */
+static int zpci_unregister_airq(struct zpci_dev *zdev)
+{
+	struct mod_pci_args args = { 0, 0, 0 };
+
+	return mod_pci(zdev, ZPCI_MOD_FC_DEREG_INT, 0, &args);
+}
+
 #define ZPCI_PCIAS_CFGSPC	15
 
 static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
@@ -150,6 +270,55 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 	return rc;
 }
 
+void synchronize_irq(unsigned int irq)
+{
+	/*
+	 * Not needed, the handler is protected by a lock and IRQs that occur
+	 * after the handler is deleted are just NOPs.
+	 */
+}
+EXPORT_SYMBOL_GPL(synchronize_irq);
+
+void enable_irq(unsigned int irq)
+{
+	struct msi_desc *msi = irq_get_msi_desc(irq);
+
+	zpci_msi_set_mask_bits(msi, 1, 0);
+}
+EXPORT_SYMBOL_GPL(enable_irq);
+
+void disable_irq(unsigned int irq)
+{
+	struct msi_desc *msi = irq_get_msi_desc(irq);
+
+	zpci_msi_set_mask_bits(msi, 1, 1);
+}
+EXPORT_SYMBOL_GPL(disable_irq);
+
+void disable_irq_nosync(unsigned int irq)
+{
+	disable_irq(irq);
+}
+EXPORT_SYMBOL_GPL(disable_irq_nosync);
+
+unsigned long probe_irq_on(void)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(probe_irq_on);
+
+int probe_irq_off(unsigned long val)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(probe_irq_off);
+
+unsigned int probe_irq_mask(unsigned long val)
+{
+	return val;
+}
+EXPORT_SYMBOL_GPL(probe_irq_mask);
+
 void __devinit pcibios_fixup_bus(struct pci_bus *bus)
 {
 }
@@ -219,6 +388,155 @@ static struct pci_ops pci_root_ops = {
 	.write = pci_write,
 };
 
+/* store the last handled bit to implement fair scheduling of devices */
+static DEFINE_PER_CPU(unsigned long, next_sbit);
+
+static void zpci_irq_handler(void *dont, void *need)
+{
+	unsigned long sbit, mbit, last = 0, start = __get_cpu_var(next_sbit);
+	int rescan = 0, max = aisb_max;
+	struct zdev_irq_map *imap;
+
+	kstat_cpu(smp_processor_id()).irqs[IOINT_PCI]++;
+	sbit = start;
+
+scan:
+	/* find summary_bit */
+	for_each_set_bit_left_cont(sbit, bucket->aisb, max) {
+		clear_bit(63 - (sbit & 63), bucket->aisb + (sbit >> 6));
+		last = sbit;
+
+		/* find vector bit */
+		imap = bucket->imap[sbit];
+		for_each_set_bit_left(mbit, &imap->aibv, imap->msi_vecs) {
+			kstat_cpu(smp_processor_id()).irqs[IOINT_MSI]++;
+			clear_bit(63 - mbit, &imap->aibv);
+
+			spin_lock(&imap->lock);
+			if (imap->cb[mbit].handler)
+				imap->cb[mbit].handler(mbit,
+					imap->cb[mbit].data);
+			spin_unlock(&imap->lock);
+		}
+	}
+
+	if (rescan)
+		goto out;
+
+	/* scan the skipped bits */
+	if (start > 0) {
+		sbit = 0;
+		max = start;
+		start = 0;
+		goto scan;
+	}
+
+	/* enable interrupts again */
+	sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+
+	/* check again to not lose initiative */
+	rmb();
+	max = aisb_max;
+	sbit = find_first_bit_left(bucket->aisb, max);
+	if (sbit != max) {
+		atomic_inc(&irq_retries);
+		rescan++;
+		goto scan;
+	}
+out:
+	/* store next device bit to scan */
+	__get_cpu_var(next_sbit) = (++last >= aisb_max) ? 0 : last;
+}
+
+/* msi_vecs - number of requested interrupts, 0 place function to error state */
+static int zpci_setup_msi(struct pci_dev *pdev, int msi_vecs)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+	unsigned int aisb, msi_nr;
+	struct msi_desc *msi;
+	int rc;
+
+	/* store the number of used MSI vectors */
+	zdev->irq_map->msi_vecs = min(msi_vecs, ZPCI_NR_MSI_VECS);
+
+	spin_lock(&bucket->lock);
+	aisb = find_first_zero_bit(bucket->alloc, PAGE_SIZE);
+	/* alloc map exhausted? */
+	if (aisb == PAGE_SIZE) {
+		spin_unlock(&bucket->lock);
+		return -EIO;
+	}
+	set_bit(aisb, bucket->alloc);
+	spin_unlock(&bucket->lock);
+
+	zdev->aisb = aisb;
+	if (aisb + 1 > aisb_max)
+		aisb_max = aisb + 1;
+
+	/* wire up IRQ shortcut pointer */
+	bucket->imap[zdev->aisb] = zdev->irq_map;
+	pr_debug("%s: imap[%u] linked to %p\n", __func__, zdev->aisb, zdev->irq_map);
+
+	/* TODO: irq number 0 wont be found if we return less than requested MSIs.
+	 * ignore it for now and fix in common code.
+	 */
+	msi_nr = aisb << ZPCI_MSI_VEC_BITS;
+
+	list_for_each_entry(msi, &pdev->msi_list, list) {
+		rc = zpci_setup_msi_irq(zdev, msi, msi_nr,
+					  aisb << ZPCI_MSI_VEC_BITS);
+		if (rc)
+			return rc;
+		msi_nr++;
+	}
+
+	rc = zpci_register_airq(zdev, aisb, (u64) &zdev->irq_map->aibv);
+	if (rc) {
+		clear_bit(aisb, bucket->alloc);
+		dev_err(&pdev->dev, "register MSI failed with: %d\n", rc);
+		return rc;
+	}
+	return (zdev->irq_map->msi_vecs == msi_vecs) ?
+		0 : zdev->irq_map->msi_vecs;
+}
+
+static void zpci_teardown_msi(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+	struct msi_desc *msi;
+	int aisb, rc;
+
+	rc = zpci_unregister_airq(zdev);
+	if (rc) {
+		dev_err(&pdev->dev, "deregister MSI failed with: %d\n", rc);
+		return;
+	}
+
+	msi = list_first_entry(&pdev->msi_list, struct msi_desc, list);
+	aisb = irq_to_dev_nr(msi->irq);
+
+	list_for_each_entry(msi, &pdev->msi_list, list)
+		zpci_teardown_msi_irq(zdev, msi);
+
+	clear_bit(aisb, bucket->alloc);
+	if (aisb + 1 == aisb_max)
+		aisb_max--;
+}
+
+int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	pr_debug("%s: requesting %d MSI-X interrupts...", __func__, nvec);
+	if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI)
+		return -EINVAL;
+	return zpci_setup_msi(pdev, nvec);
+}
+
+void arch_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	pr_info("%s: on pdev: %p\n", __func__, pdev);
+	zpci_teardown_msi(pdev);
+}
+
 static void zpci_map_resources(struct zpci_dev *zdev)
 {
 	struct pci_dev *pdev = zdev->pdev;
@@ -257,11 +575,23 @@ struct zpci_dev *zpci_alloc_device(void)
 	zdev = kzalloc(sizeof(*zdev), GFP_KERNEL);
 	if (!zdev)
 		return ERR_PTR(-ENOMEM);
+
+	/* Alloc aibv & callback space */
+	zdev->irq_map = kmem_cache_alloc(zdev_irq_cache, GFP_KERNEL);
+	if (!zdev->irq_map)
+		goto error;
+	memset(zdev->irq_map, 0, sizeof(*zdev->irq_map));
+	WARN_ON((u64) zdev->irq_map & 0xff);
 	return zdev;
+
+error:
+	kfree(zdev);
+	return ERR_PTR(-ENOMEM);
 }
 
 void zpci_free_device(struct zpci_dev *zdev)
 {
+	kmem_cache_free(zdev_irq_cache, zdev->irq_map);
 	kfree(zdev);
 }
 
@@ -320,6 +650,118 @@ void pcibios_disable_device(struct pci_dev *pdev)
 	pdev->sysdata = NULL;
 }
 
+int zpci_request_irq(unsigned int irq, irq_handler_t handler, void *data)
+{
+	int msi_nr = irq_to_msi_nr(irq);
+	struct zdev_irq_map *imap;
+	struct msi_desc *msi;
+
+	msi = irq_get_msi_desc(irq);
+	if (!msi)
+		return -EIO;
+
+	imap = get_imap(irq);
+	spin_lock_init(&imap->lock);
+
+	pr_debug("%s: register handler for IRQ:MSI %d:%d\n", __func__, irq >> 6, msi_nr);
+	imap->cb[msi_nr].handler = handler;
+	imap->cb[msi_nr].data = data;
+
+	/*
+	 * The generic MSI code returns with the interrupt disabled on the
+	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
+	 * at that level, so we do it here by hand.
+	 */
+	zpci_msi_set_mask_bits(msi, 1, 0);
+	return 0;
+}
+
+void zpci_free_irq(unsigned int irq)
+{
+	struct zdev_irq_map *imap = get_imap(irq);
+	int msi_nr = irq_to_msi_nr(irq);
+	unsigned long flags;
+
+	pr_debug("%s: for irq: %d\n", __func__, irq);
+
+	spin_lock_irqsave(&imap->lock, flags);
+	imap->cb[msi_nr].handler = NULL;
+	imap->cb[msi_nr].data = NULL;
+	spin_unlock_irqrestore(&imap->lock, flags);
+}
+
+int request_irq(unsigned int irq, irq_handler_t handler,
+		unsigned long irqflags, const char *devname, void *dev_id)
+{
+	pr_debug("%s: irq: %d  handler: %p  flags: %lx  dev: %s\n",
+		__func__, irq, handler, irqflags, devname);
+
+	return zpci_request_irq(irq, handler, dev_id);
+}
+EXPORT_SYMBOL_GPL(request_irq);
+
+void free_irq(unsigned int irq, void *dev_id)
+{
+	zpci_free_irq(irq);
+}
+EXPORT_SYMBOL_GPL(free_irq);
+
+static int __init zpci_irq_init(void)
+{
+	int cpu, rc;
+
+	bucket = kzalloc(sizeof(*bucket), GFP_KERNEL);
+	if (!bucket)
+		return -ENOMEM;
+
+	bucket->aisb = (unsigned long *) get_zeroed_page(GFP_KERNEL);
+	if (!bucket->aisb) {
+		rc = -ENOMEM;
+		goto out_aisb;
+	}
+
+	bucket->alloc = (unsigned long *) get_zeroed_page(GFP_KERNEL);
+	if (!bucket->alloc) {
+		rc = -ENOMEM;
+		goto out_alloc;
+	}
+
+	isc_register(PCI_ISC);
+	zpci_irq_si = s390_register_adapter_interrupt(&zpci_irq_handler, NULL, PCI_ISC);
+	if (IS_ERR(zpci_irq_si)) {
+		rc = PTR_ERR(zpci_irq_si);
+		zpci_irq_si = NULL;
+		goto out_ai;
+	}
+
+	for_each_online_cpu(cpu)
+		per_cpu(next_sbit, cpu) = 0;
+
+	spin_lock_init(&bucket->lock);
+	/* set summary to 1 to be called every time for the ISC */
+	*zpci_irq_si = 1;
+	sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+	return 0;
+
+out_ai:
+	isc_unregister(PCI_ISC);
+	free_page((unsigned long) bucket->alloc);
+out_alloc:
+	free_page((unsigned long) bucket->aisb);
+out_aisb:
+	kfree(bucket);
+	return rc;
+}
+
+static void zpci_irq_exit(void)
+{
+	free_page((unsigned long) bucket->alloc);
+	free_page((unsigned long) bucket->aisb);
+	s390_unregister_adapter_interrupt(zpci_irq_si, PCI_ISC);
+	isc_unregister(PCI_ISC);
+	kfree(bucket);
+}
+
 static struct resource *zpci_alloc_bus_resource(unsigned long start, unsigned long size,
 						unsigned long flags, int domain)
 {
@@ -523,13 +965,20 @@ static inline int barsize(u8 size)
 
 static int zpci_mem_init(void)
 {
+	zdev_irq_cache = kmem_cache_create("PCI_IRQ_cache", sizeof(struct zdev_irq_map),
+				L1_CACHE_BYTES, SLAB_HWCACHE_ALIGN, NULL);
+	if (!zdev_irq_cache)
+		goto error_zdev;
+
 	/* TODO: use realloc */
 	zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start),
 				   GFP_KERNEL);
 	if (!zpci_iomap_start)
-		goto error_zdev;
+		goto error_iomap;
 	return 0;
 
+error_iomap:
+	kmem_cache_destroy(zdev_irq_cache);
 error_zdev:
 	return -ENOMEM;
 }
@@ -537,6 +986,7 @@ error_zdev:
 static void zpci_mem_exit(void)
 {
 	kfree(zpci_iomap_start);
+	kmem_cache_destroy(zdev_irq_cache);
 }
 
 unsigned int pci_probe = 1;
@@ -570,6 +1020,14 @@ static int __init pci_base_init(void)
 	if (rc)
 		goto out_mem;
 
+	rc = zpci_msihash_init();
+	if (rc)
+		goto out_hash;
+
+	rc = zpci_irq_init();
+	if (rc)
+		goto out_irq;
+
 	rc = clp_find_pci_devices();
 	if (rc)
 		goto out_find;
@@ -578,6 +1036,10 @@ static int __init pci_base_init(void)
 	return 0;
 
 out_find:
+	zpci_irq_exit();
+out_irq:
+	zpci_msihash_exit();
+out_hash:
 	zpci_mem_exit();
 out_mem:
 	return rc;
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 291da1a96560..72694fb6d525 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -48,6 +48,9 @@ static void clp_free_block(void *ptr)
 static void clp_store_query_pci_fngrp(struct zpci_dev *zdev,
 				      struct clp_rsp_query_pci_grp *response)
 {
+	zdev->msi_addr = response->msia;
+
+	pr_debug("Supported number of MSI vectors: %u\n", response->noi);
 	switch (response->version) {
 	case 1:
 		zdev->max_bus_speed = PCIE_SPEED_5_0GT;
diff --git a/arch/s390/pci/pci_msi.c b/arch/s390/pci/pci_msi.c
new file mode 100644
index 000000000000..90fd3482b9e2
--- /dev/null
+++ b/arch/s390/pci/pci_msi.c
@@ -0,0 +1,141 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define COMPONENT "zPCI"
+#define pr_fmt(fmt) COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/rculist.h>
+#include <linux/hash.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <asm/hw_irq.h>
+
+/* mapping of irq numbers to msi_desc */
+static struct hlist_head *msi_hash;
+static unsigned int msihash_shift = 6;
+#define msi_hashfn(nr)	hash_long(nr, msihash_shift)
+
+static DEFINE_SPINLOCK(msi_map_lock);
+
+struct msi_desc *__irq_get_msi_desc(unsigned int irq)
+{
+	struct hlist_node *entry;
+	struct msi_map *map;
+
+	hlist_for_each_entry_rcu(map, entry,
+			&msi_hash[msi_hashfn(irq)], msi_chain)
+		if (map->irq == irq)
+			return map->msi;
+	return NULL;
+}
+
+int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag)
+{
+	if (msi->msi_attrib.is_msix) {
+		int offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+			PCI_MSIX_ENTRY_VECTOR_CTRL;
+		msi->masked = readl(msi->mask_base + offset);
+		writel(flag, msi->mask_base + offset);
+	} else {
+		if (msi->msi_attrib.maskbit) {
+			int pos;
+			u32 mask_bits;
+
+			pos = (long) msi->mask_base;
+			pci_read_config_dword(msi->dev, pos, &mask_bits);
+			mask_bits &= ~(mask);
+			mask_bits |= flag & mask;
+			pci_write_config_dword(msi->dev, pos, mask_bits);
+		} else {
+			return 0;
+		}
+	}
+
+	msi->msi_attrib.maskbit = !!flag;
+	return 1;
+}
+
+int zpci_setup_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi,
+			unsigned int nr, int offset)
+{
+	struct msi_map *map;
+	struct msi_msg msg;
+	int rc;
+
+	map = kmalloc(sizeof(*map), GFP_KERNEL);
+	if (map == NULL)
+		return -ENOMEM;
+
+	map->irq = nr;
+	map->msi = msi;
+	zdev->msi_map[nr & ZPCI_MSI_MASK] = map;
+
+	pr_debug("%s hashing irq: %u  to bucket nr: %llu\n",
+		__func__, nr, msi_hashfn(nr));
+	hlist_add_head_rcu(&map->msi_chain, &msi_hash[msi_hashfn(nr)]);
+
+	spin_lock(&msi_map_lock);
+	rc = irq_set_msi_desc(nr, msi);
+	if (rc) {
+		spin_unlock(&msi_map_lock);
+		hlist_del_rcu(&map->msi_chain);
+		kfree(map);
+		zdev->msi_map[nr & ZPCI_MSI_MASK] = NULL;
+		return rc;
+	}
+	spin_unlock(&msi_map_lock);
+
+	msg.data = nr - offset;
+	msg.address_lo = zdev->msi_addr & 0xffffffff;
+	msg.address_hi = zdev->msi_addr >> 32;
+	write_msi_msg(nr, &msg);
+	return 0;
+}
+
+void zpci_teardown_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi)
+{
+	int irq = msi->irq & ZPCI_MSI_MASK;
+	struct msi_map *map;
+
+	msi->msg.address_lo = 0;
+	msi->msg.address_hi = 0;
+	msi->msg.data = 0;
+	msi->irq = 0;
+	zpci_msi_set_mask_bits(msi, 1, 1);
+
+	spin_lock(&msi_map_lock);
+	map = zdev->msi_map[irq];
+	hlist_del_rcu(&map->msi_chain);
+	kfree(map);
+	zdev->msi_map[irq] = NULL;
+	spin_unlock(&msi_map_lock);
+}
+
+/*
+ * The msi hash table has 256 entries which is good for 4..20
+ * devices (a typical device allocates 10 + CPUs MSI's). Maybe make
+ * the hash table size adjustable later.
+ */
+int __init zpci_msihash_init(void)
+{
+	unsigned int i;
+
+	msi_hash = kmalloc(256 * sizeof(*msi_hash), GFP_KERNEL);
+	if (!msi_hash)
+		return -ENOMEM;
+
+	for (i = 0; i < (1U << msihash_shift); i++)
+		INIT_HLIST_HEAD(&msi_hash[i]);
+	return 0;
+}
+
+void __init zpci_msihash_exit(void)
+{
+	kfree(msi_hash);
+}
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index a825d78fd0aa..5099636a6e5f 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -207,6 +207,8 @@ static void msix_mask_irq(struct msi_desc *desc, u32 flag)
 	desc->masked = __msix_mask_irq(desc, flag);
 }
 
+#ifdef CONFIG_GENERIC_HARDIRQS
+
 static void msi_set_mask_bit(struct irq_data *data, u32 flag)
 {
 	struct msi_desc *desc = irq_data_get_msi(data);
@@ -230,6 +232,8 @@ void unmask_msi_irq(struct irq_data *data)
 	msi_set_mask_bit(data, 0);
 }
 
+#endif /* CONFIG_GENERIC_HARDIRQS */
+
 void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
 	BUG_ON(entry->dev->current_state != PCI_D0);
@@ -337,8 +341,10 @@ static void free_msi_irqs(struct pci_dev *dev)
 		if (!entry->irq)
 			continue;
 		nvec = 1 << entry->msi_attrib.multiple;
+#ifdef CONFIG_GENERIC_HARDIRQS
 		for (i = 0; i < nvec; i++)
 			BUG_ON(irq_has_action(entry->irq + i));
+#endif
 	}
 
 	arch_teardown_msi_irqs(dev);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 216b0ba109d7..e21ed837c673 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -10,9 +10,6 @@
  */
 
 #include <linux/smp.h>
-
-#ifndef CONFIG_S390
-
 #include <linux/linkage.h>
 #include <linux/cache.h>
 #include <linux/spinlock.h>
@@ -737,8 +734,11 @@ static inline void irq_gc_lock(struct irq_chip_generic *gc) { }
 static inline void irq_gc_unlock(struct irq_chip_generic *gc) { }
 #endif
 
-#endif /* CONFIG_GENERIC_HARDIRQS */
+#else /* !CONFIG_GENERIC_HARDIRQS */
 
-#endif /* !CONFIG_S390 */
+extern struct msi_desc *irq_get_msi_desc(unsigned int irq);
+extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry);
+
+#endif /* CONFIG_GENERIC_HARDIRQS */
 
 #endif /* _LINUX_IRQ_H */
-- 
cgit v1.2.3-55-g7522


From c07135633bee3f01a6454d15b6411f32cfbeb2fd Mon Sep 17 00:00:00 2001
From: Rami Rosen
Date: Fri, 30 Nov 2012 01:08:47 +0000
Subject: rtnelink: remove unused parameter from rtnl_create_link().

This patch removes an unused parameter (src_net) from rtnl_create_link()
method and from the method single invocation, in veth.
This parameter was used in the past when calling
ops->get_tx_queues(src_net, tb) in rtnl_create_link().
The get_tx_queues() member of rtnl_link_ops was replaced by two methods,
get_num_tx_queues() and get_num_rx_queues(), which do not get any
parameter. This was done in commit d40156aa5ecbd51fed932ed4813df82b56e5ff4d by
Jiri Pirko ("rtnl: allow to specify different num for rx and tx queue count").

Signed-off-by: Rami Rosen <ramirose@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/veth.c      | 2 +-
 include/net/rtnetlink.h | 2 +-
 net/core/rtnetlink.c    | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 24f6b27e169f..95814d9747ef 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -340,7 +340,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	if (IS_ERR(net))
 		return PTR_ERR(net);
 
-	peer = rtnl_create_link(src_net, net, ifname, &veth_link_ops, tbp);
+	peer = rtnl_create_link(net, ifname, &veth_link_ops, tbp);
 	if (IS_ERR(peer)) {
 		put_net(net);
 		return PTR_ERR(peer);
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 6b00c4fc4291..5a15fabd6a75 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -125,7 +125,7 @@ extern void	rtnl_af_unregister(struct rtnl_af_ops *ops);
 
 
 extern struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]);
-extern struct net_device *rtnl_create_link(struct net *src_net, struct net *net,
+extern struct net_device *rtnl_create_link(struct net *net,
 	char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]);
 extern int rtnl_configure_link(struct net_device *dev,
 			       const struct ifinfomsg *ifm);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 575a6ee89944..1868625af25e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1642,7 +1642,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 }
 EXPORT_SYMBOL(rtnl_configure_link);
 
-struct net_device *rtnl_create_link(struct net *src_net, struct net *net,
+struct net_device *rtnl_create_link(struct net *net,
 	char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[])
 {
 	int err;
@@ -1840,7 +1840,7 @@ replay:
 		if (IS_ERR(dest_net))
 			return PTR_ERR(dest_net);
 
-		dev = rtnl_create_link(net, dest_net, ifname, ops, tb);
+		dev = rtnl_create_link(dest_net, ifname, ops, tb);
 		if (IS_ERR(dev)) {
 			err = PTR_ERR(dev);
 			goto out;
-- 
cgit v1.2.3-55-g7522


From 0362063b7be97f6f8e2c644b970f5726489aacdf Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Tue, 27 Nov 2012 00:31:55 +0100
Subject: ssb: extif: fix compile errors

If CONFIG_SSB_EMBEDDED or CONFIG_SSB_DRIVER_MIPS is set and
CONFIG_SSB_DRIVER_EXTIF is not set, it will cause compile problems
because of missing functions. This patch fixes these problems.

The mips driver now also uses ssb_chipco_available() instead of
checking bus->chipco.dev manually.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/ssb/driver_mipscore.c        | 14 ++++++------
 include/linux/ssb/ssb_driver_extif.h | 42 ++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/ssb/driver_mipscore.c b/drivers/ssb/driver_mipscore.c
index b918ba922306..5bd05b136d22 100644
--- a/drivers/ssb/driver_mipscore.c
+++ b/drivers/ssb/driver_mipscore.c
@@ -178,9 +178,9 @@ static void ssb_mips_serial_init(struct ssb_mipscore *mcore)
 {
 	struct ssb_bus *bus = mcore->dev->bus;
 
-	if (bus->extif.dev)
+	if (ssb_extif_available(&bus->extif))
 		mcore->nr_serial_ports = ssb_extif_serial_init(&bus->extif, mcore->serial_ports);
-	else if (bus->chipco.dev)
+	else if (ssb_chipco_available(&bus->chipco))
 		mcore->nr_serial_ports = ssb_chipco_serial_init(&bus->chipco, mcore->serial_ports);
 	else
 		mcore->nr_serial_ports = 0;
@@ -191,7 +191,7 @@ static void ssb_mips_flash_detect(struct ssb_mipscore *mcore)
 	struct ssb_bus *bus = mcore->dev->bus;
 
 	/* When there is no chipcommon on the bus there is 4MB flash */
-	if (!bus->chipco.dev) {
+	if (!ssb_chipco_available(&bus->chipco)) {
 		mcore->pflash.present = true;
 		mcore->pflash.buswidth = 2;
 		mcore->pflash.window = SSB_FLASH1;
@@ -227,9 +227,9 @@ u32 ssb_cpu_clock(struct ssb_mipscore *mcore)
 	if (bus->chipco.capabilities & SSB_CHIPCO_CAP_PMU)
 		return ssb_pmu_get_cpu_clock(&bus->chipco);
 
-	if (bus->extif.dev) {
+	if (ssb_extif_available(&bus->extif)) {
 		ssb_extif_get_clockcontrol(&bus->extif, &pll_type, &n, &m);
-	} else if (bus->chipco.dev) {
+	} else if (ssb_chipco_available(&bus->chipco)) {
 		ssb_chipco_get_clockcpu(&bus->chipco, &pll_type, &n, &m);
 	} else
 		return 0;
@@ -265,9 +265,9 @@ void ssb_mipscore_init(struct ssb_mipscore *mcore)
 		hz = 100000000;
 	ns = 1000000000 / hz;
 
-	if (bus->extif.dev)
+	if (ssb_extif_available(&bus->extif))
 		ssb_extif_timing_init(&bus->extif, ns);
-	else if (bus->chipco.dev)
+	else if (ssb_chipco_available(&bus->chipco))
 		ssb_chipco_timing_init(&bus->chipco, ns);
 
 	/* Assign IRQs to all cores on the bus, start with irq line 2, because serial usually takes 1 */
diff --git a/include/linux/ssb/ssb_driver_extif.h b/include/linux/ssb/ssb_driver_extif.h
index 91161f0aa22b..2604efa7dc4d 100644
--- a/include/linux/ssb/ssb_driver_extif.h
+++ b/include/linux/ssb/ssb_driver_extif.h
@@ -204,11 +204,53 @@ void ssb_extif_get_clockcontrol(struct ssb_extif *extif,
 {
 }
 
+static inline
+void ssb_extif_timing_init(struct ssb_extif *extif, unsigned long ns)
+{
+}
+
 static inline
 void ssb_extif_watchdog_timer_set(struct ssb_extif *extif,
 				  u32 ticks)
 {
 }
 
+static inline u32 ssb_extif_gpio_in(struct ssb_extif *extif, u32 mask)
+{
+	return 0;
+}
+
+static inline u32 ssb_extif_gpio_out(struct ssb_extif *extif, u32 mask,
+				     u32 value)
+{
+	return 0;
+}
+
+static inline u32 ssb_extif_gpio_outen(struct ssb_extif *extif, u32 mask,
+				       u32 value)
+{
+	return 0;
+}
+
+static inline u32 ssb_extif_gpio_polarity(struct ssb_extif *extif, u32 mask,
+					  u32 value)
+{
+	return 0;
+}
+
+static inline u32 ssb_extif_gpio_intmask(struct ssb_extif *extif, u32 mask,
+					 u32 value)
+{
+	return 0;
+}
+
+#ifdef CONFIG_SSB_SERIAL
+static inline int ssb_extif_serial_init(struct ssb_extif *extif,
+					struct ssb_serial_port *ports)
+{
+	return 0;
+}
+#endif /* CONFIG_SSB_SERIAL */
+
 #endif /* CONFIG_SSB_DRIVER_EXTIF */
 #endif /* LINUX_SSB_EXTIFCORE_H_ */
-- 
cgit v1.2.3-55-g7522


From 91d1aa43d30505b0b825db8898ffc80a8eca96c7 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker
Date: Tue, 27 Nov 2012 19:33:25 +0100
Subject: context_tracking: New context tracking susbsystem

Create a new subsystem that probes on kernel boundaries
to keep track of the transitions between level contexts
with two basic initial contexts: user or kernel.

This is an abstraction of some RCU code that use such tracking
to implement its userspace extended quiescent state.

We need to pull this up from RCU into this new level of indirection
because this tracking is also going to be used to implement an "on
demand" generic virtual cputime accounting. A necessary step to
shutdown the tick while still accounting the cputime.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Gilad Ben-Yossef <gilad@benyossef.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
[ paulmck: fix whitespace error and email address. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 arch/Kconfig                            | 15 +++---
 arch/x86/Kconfig                        |  2 +-
 arch/x86/include/asm/context_tracking.h | 31 ++++++++++++
 arch/x86/include/asm/rcu.h              | 32 -------------
 arch/x86/kernel/entry_64.S              |  2 +-
 arch/x86/kernel/ptrace.c                |  8 ++--
 arch/x86/kernel/signal.c                |  5 +-
 arch/x86/kernel/traps.c                 |  2 +-
 arch/x86/mm/fault.c                     |  2 +-
 include/linux/context_tracking.h        | 18 +++++++
 include/linux/rcupdate.h                |  2 -
 init/Kconfig                            | 28 +++++------
 kernel/Makefile                         |  1 +
 kernel/context_tracking.c               | 83 +++++++++++++++++++++++++++++++++
 kernel/rcutree.c                        | 64 +------------------------
 kernel/sched/core.c                     | 11 +++--
 16 files changed, 174 insertions(+), 132 deletions(-)
 create mode 100644 arch/x86/include/asm/context_tracking.h
 delete mode 100644 arch/x86/include/asm/rcu.h
 create mode 100644 include/linux/context_tracking.h
 create mode 100644 kernel/context_tracking.c

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index 366ec06a5185..cc74aaea116c 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -300,15 +300,16 @@ config SECCOMP_FILTER
 
 	  See Documentation/prctl/seccomp_filter.txt for details.
 
-config HAVE_RCU_USER_QS
+config HAVE_CONTEXT_TRACKING
 	bool
 	help
-	  Provide kernel entry/exit hooks necessary for userspace
-	  RCU extended quiescent state. Syscalls need to be wrapped inside
-	  rcu_user_exit()-rcu_user_enter() through the slow path using
-	  TIF_NOHZ flag. Exceptions handlers must be wrapped as well. Irqs
-	  are already protected inside rcu_irq_enter/rcu_irq_exit() but
-	  preemption or signal handling on irq exit still need to be protected.
+	  Provide kernel/user boundaries probes necessary for subsystems
+	  that need it, such as userspace RCU extended quiescent state.
+	  Syscalls need to be wrapped inside user_exit()-user_enter() through
+	  the slow path using TIF_NOHZ flag. Exceptions handlers must be
+	  wrapped as well. Irqs are already protected inside
+	  rcu_irq_enter/rcu_irq_exit() but preemption or signal handling on
+	  irq exit still need to be protected.
 
 config HAVE_VIRT_CPU_ACCOUNTING
 	bool
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 46c3bff3ced2..110cfad24f26 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -106,7 +106,7 @@ config X86
 	select KTIME_SCALAR if X86_32
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
-	select HAVE_RCU_USER_QS if X86_64
+	select HAVE_CONTEXT_TRACKING if X86_64
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select GENERIC_KERNEL_THREAD
 	select GENERIC_KERNEL_EXECVE
diff --git a/arch/x86/include/asm/context_tracking.h b/arch/x86/include/asm/context_tracking.h
new file mode 100644
index 000000000000..1616562683e9
--- /dev/null
+++ b/arch/x86/include/asm/context_tracking.h
@@ -0,0 +1,31 @@
+#ifndef _ASM_X86_CONTEXT_TRACKING_H
+#define _ASM_X86_CONTEXT_TRACKING_H
+
+#ifndef __ASSEMBLY__
+#include <linux/context_tracking.h>
+#include <asm/ptrace.h>
+
+static inline void exception_enter(struct pt_regs *regs)
+{
+	user_exit();
+}
+
+static inline void exception_exit(struct pt_regs *regs)
+{
+#ifdef CONFIG_CONTEXT_TRACKING
+	if (user_mode(regs))
+		user_enter();
+#endif
+}
+
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_CONTEXT_TRACKING
+# define SCHEDULE_USER call schedule_user
+#else
+# define SCHEDULE_USER call schedule
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/rcu.h
deleted file mode 100644
index d1ac07a23979..000000000000
--- a/arch/x86/include/asm/rcu.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef _ASM_X86_RCU_H
-#define _ASM_X86_RCU_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/rcupdate.h>
-#include <asm/ptrace.h>
-
-static inline void exception_enter(struct pt_regs *regs)
-{
-	rcu_user_exit();
-}
-
-static inline void exception_exit(struct pt_regs *regs)
-{
-#ifdef CONFIG_RCU_USER_QS
-	if (user_mode(regs))
-		rcu_user_enter();
-#endif
-}
-
-#else /* __ASSEMBLY__ */
-
-#ifdef CONFIG_RCU_USER_QS
-# define SCHEDULE_USER call schedule_user
-#else
-# define SCHEDULE_USER call schedule
-#endif
-
-#endif /* !__ASSEMBLY__ */
-
-#endif
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 0c58952d64e8..98faeb30139d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -56,7 +56,7 @@
 #include <asm/ftrace.h>
 #include <asm/percpu.h>
 #include <asm/asm.h>
-#include <asm/rcu.h>
+#include <asm/context_tracking.h>
 #include <asm/smap.h>
 #include <linux/err.h>
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index eff5b8c68652..65b88a5dc1a8 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,7 +21,7 @@
 #include <linux/signal.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
-#include <linux/rcupdate.h>
+#include <linux/context_tracking.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -1461,7 +1461,7 @@ long syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
-	rcu_user_exit();
+	user_exit();
 
 	/*
 	 * If we stepped into a sysenter/syscall insn, it trapped in
@@ -1516,7 +1516,7 @@ void syscall_trace_leave(struct pt_regs *regs)
 	 * or do_notify_resume(), in which case we can be in RCU
 	 * user mode.
 	 */
-	rcu_user_exit();
+	user_exit();
 
 	audit_syscall_exit(regs);
 
@@ -1534,5 +1534,5 @@ void syscall_trace_leave(struct pt_regs *regs)
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);
 
-	rcu_user_enter();
+	user_enter();
 }
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 29ad351804e9..20ecac112e74 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -22,6 +22,7 @@
 #include <linux/uaccess.h>
 #include <linux/user-return-notifier.h>
 #include <linux/uprobes.h>
+#include <linux/context_tracking.h>
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
@@ -816,7 +817,7 @@ static void do_signal(struct pt_regs *regs)
 void
 do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 {
-	rcu_user_exit();
+	user_exit();
 
 #ifdef CONFIG_X86_MCE
 	/* notify userspace of pending MCEs */
@@ -840,7 +841,7 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 	if (thread_info_flags & _TIF_USER_RETURN_NOTIFY)
 		fire_user_return_notifiers();
 
-	rcu_user_enter();
+	user_enter();
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8276dc6794cc..eb8586693e0b 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -55,7 +55,7 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/mce.h>
-#include <asm/rcu.h>
+#include <asm/context_tracking.h>
 
 #include <asm/mach_traps.h>
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 8e13ecb41bee..7a529cbab7ad 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -18,7 +18,7 @@
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_START		*/
-#include <asm/rcu.h>			/* exception_enter(), ...	*/
+#include <asm/context_tracking.h>	/* exception_enter(), ...	*/
 
 /*
  * Page fault error code bits:
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
new file mode 100644
index 000000000000..e24339ccb7f0
--- /dev/null
+++ b/include/linux/context_tracking.h
@@ -0,0 +1,18 @@
+#ifndef _LINUX_CONTEXT_TRACKING_H
+#define _LINUX_CONTEXT_TRACKING_H
+
+#ifdef CONFIG_CONTEXT_TRACKING
+#include <linux/sched.h>
+
+extern void user_enter(void);
+extern void user_exit(void);
+extern void context_tracking_task_switch(struct task_struct *prev,
+					 struct task_struct *next);
+#else
+static inline void user_enter(void) { }
+static inline void user_exit(void) { }
+static inline void context_tracking_task_switch(struct task_struct *prev,
+						struct task_struct *next) { }
+#endif /* !CONFIG_CONTEXT_TRACKING */
+
+#endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 8fe7c1840d30..275aa3f1062d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -222,8 +222,6 @@ extern void rcu_user_enter(void);
 extern void rcu_user_exit(void);
 extern void rcu_user_enter_after_irq(void);
 extern void rcu_user_exit_after_irq(void);
-extern void rcu_user_hooks_switch(struct task_struct *prev,
-				  struct task_struct *next);
 #else
 static inline void rcu_user_enter(void) { }
 static inline void rcu_user_exit(void) { }
diff --git a/init/Kconfig b/init/Kconfig
index 5ac6ee094225..2054e048bb98 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -486,9 +486,13 @@ config PREEMPT_RCU
 	  This option enables preemptible-RCU code that is common between
 	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
 
+config CONTEXT_TRACKING
+       bool
+
 config RCU_USER_QS
 	bool "Consider userspace as in RCU extended quiescent state"
-	depends on HAVE_RCU_USER_QS && SMP
+	depends on HAVE_CONTEXT_TRACKING && SMP
+	select CONTEXT_TRACKING
 	help
 	  This option sets hooks on kernel / userspace boundaries and
 	  puts RCU in extended quiescent state when the CPU runs in
@@ -497,24 +501,20 @@ config RCU_USER_QS
 	  try to keep the timer tick on for RCU.
 
 	  Unless you want to hack and help the development of the full
-	  tickless feature, you shouldn't enable this option.  It also
+	  dynticks mode, you shouldn't enable this option.  It also
 	  adds unnecessary overhead.
 
 	  If unsure say N
 
-config RCU_USER_QS_FORCE
-	bool "Force userspace extended QS by default"
-	depends on RCU_USER_QS
+config CONTEXT_TRACKING_FORCE
+	bool "Force context tracking"
+	depends on CONTEXT_TRACKING
 	help
-	  Set the hooks in user/kernel boundaries by default in order to
-	  test this feature that treats userspace as an extended quiescent
-	  state until we have a real user like a full adaptive nohz option.
-
-	  Unless you want to hack and help the development of the full
-	  tickless feature, you shouldn't enable this option. It adds
-	  unnecessary overhead.
-
-	  If unsure say N
+	  Probe on user/kernel boundaries by default in order to
+	  test the features that rely on it such as userspace RCU extended
+	  quiescent states.
+	  This test is there for debugging until we have a real user like the
+	  full dynticks mode.
 
 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
diff --git a/kernel/Makefile b/kernel/Makefile
index 0dfeca4324ee..f90bbfc9727f 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -110,6 +110,7 @@ obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
 obj-$(CONFIG_PADATA) += padata.o
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
+obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
 
 $(obj)/configs.o: $(obj)/config_data.h
 
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
new file mode 100644
index 000000000000..e0e07fd55508
--- /dev/null
+++ b/kernel/context_tracking.c
@@ -0,0 +1,83 @@
+#include <linux/context_tracking.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+
+struct context_tracking {
+	/*
+	 * When active is false, hooks are not set to
+	 * minimize overhead: TIF flags are cleared
+	 * and calls to user_enter/exit are ignored. This
+	 * may be further optimized using static keys.
+	 */
+	bool active;
+	enum {
+		IN_KERNEL = 0,
+		IN_USER,
+	} state;
+};
+
+static DEFINE_PER_CPU(struct context_tracking, context_tracking) = {
+#ifdef CONFIG_CONTEXT_TRACKING_FORCE
+	.active = true,
+#endif
+};
+
+void user_enter(void)
+{
+	unsigned long flags;
+
+	/*
+	 * Some contexts may involve an exception occuring in an irq,
+	 * leading to that nesting:
+	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
+	 * This would mess up the dyntick_nesting count though. And rcu_irq_*()
+	 * helpers are enough to protect RCU uses inside the exception. So
+	 * just return immediately if we detect we are in an IRQ.
+	 */
+	if (in_interrupt())
+		return;
+
+	WARN_ON_ONCE(!current->mm);
+
+	local_irq_save(flags);
+	if (__this_cpu_read(context_tracking.active) &&
+	    __this_cpu_read(context_tracking.state) != IN_USER) {
+		__this_cpu_write(context_tracking.state, IN_USER);
+		rcu_user_enter();
+	}
+	local_irq_restore(flags);
+}
+
+void user_exit(void)
+{
+	unsigned long flags;
+
+	/*
+	 * Some contexts may involve an exception occuring in an irq,
+	 * leading to that nesting:
+	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
+	 * This would mess up the dyntick_nesting count though. And rcu_irq_*()
+	 * helpers are enough to protect RCU uses inside the exception. So
+	 * just return immediately if we detect we are in an IRQ.
+	 */
+	if (in_interrupt())
+		return;
+
+	local_irq_save(flags);
+	if (__this_cpu_read(context_tracking.state) == IN_USER) {
+		__this_cpu_write(context_tracking.state, IN_KERNEL);
+		rcu_user_exit();
+	}
+	local_irq_restore(flags);
+}
+
+void context_tracking_task_switch(struct task_struct *prev,
+			     struct task_struct *next)
+{
+	if (__this_cpu_read(context_tracking.active)) {
+		clear_tsk_thread_flag(prev, TIF_NOHZ);
+		set_tsk_thread_flag(next, TIF_NOHZ);
+	}
+}
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 7733eb56e156..e441b77b614e 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -207,9 +207,6 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
 	.dynticks = ATOMIC_INIT(1),
-#if defined(CONFIG_RCU_USER_QS) && !defined(CONFIG_RCU_USER_QS_FORCE)
-	.ignore_user_qs = true,
-#endif
 };
 
 static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
@@ -420,29 +417,7 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter);
  */
 void rcu_user_enter(void)
 {
-	unsigned long flags;
-	struct rcu_dynticks *rdtp;
-
-	/*
-	 * Some contexts may involve an exception occuring in an irq,
-	 * leading to that nesting:
-	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
-	 * This would mess up the dyntick_nesting count though. And rcu_irq_*()
-	 * helpers are enough to protect RCU uses inside the exception. So
-	 * just return immediately if we detect we are in an IRQ.
-	 */
-	if (in_interrupt())
-		return;
-
-	WARN_ON_ONCE(!current->mm);
-
-	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
-	if (!rdtp->ignore_user_qs && !rdtp->in_user) {
-		rdtp->in_user = true;
-		rcu_eqs_enter(true);
-	}
-	local_irq_restore(flags);
+	rcu_eqs_enter(1);
 }
 
 /**
@@ -579,27 +554,7 @@ EXPORT_SYMBOL_GPL(rcu_idle_exit);
  */
 void rcu_user_exit(void)
 {
-	unsigned long flags;
-	struct rcu_dynticks *rdtp;
-
-	/*
-	 * Some contexts may involve an exception occuring in an irq,
-	 * leading to that nesting:
-	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
-	 * This would mess up the dyntick_nesting count though. And rcu_irq_*()
-	 * helpers are enough to protect RCU uses inside the exception. So
-	 * just return immediately if we detect we are in an IRQ.
-	 */
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
-	if (rdtp->in_user) {
-		rdtp->in_user = false;
-		rcu_eqs_exit(true);
-	}
-	local_irq_restore(flags);
+	rcu_eqs_exit(1);
 }
 
 /**
@@ -722,21 +677,6 @@ int rcu_is_cpu_idle(void)
 }
 EXPORT_SYMBOL(rcu_is_cpu_idle);
 
-#ifdef CONFIG_RCU_USER_QS
-void rcu_user_hooks_switch(struct task_struct *prev,
-			   struct task_struct *next)
-{
-	struct rcu_dynticks *rdtp;
-
-	/* Interrupts are disabled in context switch */
-	rdtp = &__get_cpu_var(rcu_dynticks);
-	if (!rdtp->ignore_user_qs) {
-		clear_tsk_thread_flag(prev, TIF_NOHZ);
-		set_tsk_thread_flag(next, TIF_NOHZ);
-	}
-}
-#endif /* #ifdef CONFIG_RCU_USER_QS */
-
 #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 36f260864f65..80f80dfca70e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -72,6 +72,7 @@
 #include <linux/slab.h>
 #include <linux/init_task.h>
 #include <linux/binfmts.h>
+#include <linux/context_tracking.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -1886,8 +1887,8 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 #endif
 
+	context_tracking_task_switch(prev, next);
 	/* Here we just switch the register state and the stack. */
-	rcu_user_hooks_switch(prev, next);
 	switch_to(prev, next, prev);
 
 	barrier();
@@ -2911,7 +2912,7 @@ asmlinkage void __sched schedule(void)
 }
 EXPORT_SYMBOL(schedule);
 
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_CONTEXT_TRACKING
 asmlinkage void __sched schedule_user(void)
 {
 	/*
@@ -2920,9 +2921,9 @@ asmlinkage void __sched schedule_user(void)
 	 * we haven't yet exited the RCU idle mode. Do it here manually until
 	 * we find a better solution.
 	 */
-	rcu_user_exit();
+	user_exit();
 	schedule();
-	rcu_user_enter();
+	user_enter();
 }
 #endif
 
@@ -3027,7 +3028,7 @@ asmlinkage void __sched preempt_schedule_irq(void)
 	/* Catch callers which need to be fixed */
 	BUG_ON(ti->preempt_count || !irqs_disabled());
 
-	rcu_user_exit();
+	user_exit();
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		local_irq_enable();
-- 
cgit v1.2.3-55-g7522


From ce43b03e8889475817d427b1f3724c7e294b76eb Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Fri, 30 Nov 2012 09:49:27 +0000
Subject: net: move inet_dport/inet_num in sock_common

commit 68835aba4d9b (net: optimize INET input path further)
moved some fields used for tcp/udp sockets lookup in the first cache
line of struct sock_common.

This patch moves inet_dport/inet_num as well, filling a 32bit hole
on 64 bit arches and reducing number of cache line misses in lookups.

Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match
before addresses match, as this check is more discriminant.

Remove the hash check from MATCH() macros because we dont need to
re validate the hash value after taking a refcount on socket, and
use likely/unlikely compiler hints, as the sk_hash/hash check
makes the following conditional tests 100% predicted by cpu.

Introduce skc_addrpair/skc_portpair pair values to better
document the alignment requirements of the port/addr pairs
used in the various MATCH() macros, and remove some casts.

The namespace check can also be done at last.

This slightly improves TCP/UDP lookup times.

IP/TCP early demux needs inet->rx_dst_ifindex and
TCP needs inet->min_ttl, lets group them together in same cache line.

With help from Ben Hutchings & Joe Perches.

Idea of this patch came after Ling Ma proposal to move skc_hash
to the beginning of struct sock_common, and should allow him
to submit a final version of his patch. My tests show an improvement
doing so.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Joe Perches <joe@perches.com>
Cc: Ling Ma <ling.ma.program@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h             | 32 ++++++++++++++-------------
 include/net/inet_hashtables.h    | 48 ++++++++++++++++++++++------------------
 include/net/inet_sock.h          |  8 ++++---
 include/net/inet_timewait_sock.h |  7 ++++--
 include/net/sock.h               | 25 ++++++++++++++++-----
 net/ipv4/inet_hashtables.c       | 36 +++++++++++++++++++-----------
 net/ipv6/inet6_hashtables.c      | 27 +++++++++++++++-------
 7 files changed, 115 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 5e11905a4f01..12729e966dc9 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -364,20 +364,22 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 #define inet_v6_ipv6only(__sk)		0
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 
-#define INET6_MATCH(__sk, __net, __hash, __saddr, __daddr, __ports, __dif)\
-	(((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net)	&& \
-	 ((*((__portpair *)&(inet_sk(__sk)->inet_dport))) == (__ports)) && \
-	 ((__sk)->sk_family		== AF_INET6)		&& \
-	 ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr))	&& \
-	 ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr))	&& \
-	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-
-#define INET6_TW_MATCH(__sk, __net, __hash, __saddr, __daddr, __ports, __dif) \
-	(((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net)	&& \
-	 (*((__portpair *)&(inet_twsk(__sk)->tw_dport)) == (__ports))	&& \
-	 ((__sk)->sk_family	       == PF_INET6)			&& \
-	 (ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_daddr, (__saddr)))	&& \
-	 (ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_rcv_saddr, (__daddr))) && \
-	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)	\
+	((inet_sk(__sk)->inet_portpair == (__ports))		&&	\
+	 ((__sk)->sk_family == AF_INET6)			&&	\
+	 ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr))	&&	\
+	 ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr))	&&	\
+	 (!(__sk)->sk_bound_dev_if	||				\
+	   ((__sk)->sk_bound_dev_if == (__dif))) 		&&	\
+	 net_eq(sock_net(__sk), (__net)))
+
+#define INET6_TW_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)	   \
+	((inet_twsk(__sk)->tw_portpair == (__ports))			&& \
+	 ((__sk)->sk_family == AF_INET6)				&& \
+	 ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_daddr, (__saddr))	&& \
+	 ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_rcv_saddr, (__daddr)) && \
+	 (!(__sk)->sk_bound_dev_if	||				   \
+	  ((__sk)->sk_bound_dev_if == (__dif)))				&& \
+	 net_eq(sock_net(__sk), (__net)))
 
 #endif /* _IPV6_H */
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 54be0287eb98..d1de4fbd45c2 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -299,30 +299,34 @@ typedef __u64 __bitwise __addrpair;
 				   (((__force __u64)(__be32)(__daddr)) << 32) | \
 				   ((__force __u64)(__be32)(__saddr)));
 #endif /* __BIG_ENDIAN */
-#define INET_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
-	(((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net)) &&	\
-	 ((*((__addrpair *)&(inet_sk(__sk)->inet_daddr))) == (__cookie))  &&	\
-	 ((*((__portpair *)&(inet_sk(__sk)->inet_dport))) == (__ports))   &&	\
-	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-#define INET_TW_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
-	(((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net)) &&	\
-	 ((*((__addrpair *)&(inet_twsk(__sk)->tw_daddr))) == (__cookie)) &&	\
-	 ((*((__portpair *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) &&	\
-	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)	\
+	((inet_sk(__sk)->inet_portpair == (__ports))		&&	\
+	 (inet_sk(__sk)->inet_addrpair == (__cookie))		&&	\
+	 (!(__sk)->sk_bound_dev_if	||				\
+	   ((__sk)->sk_bound_dev_if == (__dif))) 		&& 	\
+	 net_eq(sock_net(__sk), (__net)))
+#define INET_TW_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)\
+	((inet_twsk(__sk)->tw_portpair == (__ports))	&&		\
+	 (inet_twsk(__sk)->tw_addrpair == (__cookie))	&&		\
+	 (!(__sk)->sk_bound_dev_if	||				\
+	   ((__sk)->sk_bound_dev_if == (__dif)))	&&		\
+	 net_eq(sock_net(__sk), (__net)))
 #else /* 32-bit arch */
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr)
-#define INET_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)	\
-	(((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net))	&&	\
-	 (inet_sk(__sk)->inet_daddr	== (__saddr))		&&	\
-	 (inet_sk(__sk)->inet_rcv_saddr	== (__daddr))		&&	\
-	 ((*((__portpair *)&(inet_sk(__sk)->inet_dport))) == (__ports))	&&	\
-	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-#define INET_TW_MATCH(__sk, __net, __hash,__cookie, __saddr, __daddr, __ports, __dif)	\
-	(((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net))	&&	\
-	 (inet_twsk(__sk)->tw_daddr	== (__saddr))		&&	\
-	 (inet_twsk(__sk)->tw_rcv_saddr	== (__daddr))		&&	\
-	 ((*((__portpair *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) &&	\
-	 (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
+	((inet_sk(__sk)->inet_portpair == (__ports))	&&		\
+	 (inet_sk(__sk)->inet_daddr	== (__saddr))	&&		\
+	 (inet_sk(__sk)->inet_rcv_saddr	== (__daddr))	&&		\
+	 (!(__sk)->sk_bound_dev_if	||				\
+	   ((__sk)->sk_bound_dev_if == (__dif))) 	&&		\
+	 net_eq(sock_net(__sk), (__net)))
+#define INET_TW_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
+	((inet_twsk(__sk)->tw_portpair == (__ports))	&&		\
+	 (inet_twsk(__sk)->tw_daddr	== (__saddr))	&&		\
+	 (inet_twsk(__sk)->tw_rcv_saddr	== (__daddr))	&&		\
+	 (!(__sk)->sk_bound_dev_if	||				\
+	   ((__sk)->sk_bound_dev_if == (__dif))) 	&&		\
+	 net_eq(sock_net(__sk), (__net)))
 #endif /* 64-bit arch */
 
 /*
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 256c1ed2d69a..a4196cbc84ec 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -144,9 +144,11 @@ struct inet_sock {
 	/* Socket demultiplex comparisons on incoming packets. */
 #define inet_daddr		sk.__sk_common.skc_daddr
 #define inet_rcv_saddr		sk.__sk_common.skc_rcv_saddr
+#define inet_addrpair		sk.__sk_common.skc_addrpair
+#define inet_dport		sk.__sk_common.skc_dport
+#define inet_num		sk.__sk_common.skc_num
+#define inet_portpair		sk.__sk_common.skc_portpair
 
-	__be16			inet_dport;
-	__u16			inet_num;
 	__be32			inet_saddr;
 	__s16			uc_ttl;
 	__u16			cmsg_flags;
@@ -154,6 +156,7 @@ struct inet_sock {
 	__u16			inet_id;
 
 	struct ip_options_rcu __rcu	*inet_opt;
+	int			rx_dst_ifindex;
 	__u8			tos;
 	__u8			min_ttl;
 	__u8			mc_ttl;
@@ -170,7 +173,6 @@ struct inet_sock {
 	int			uc_index;
 	int			mc_index;
 	__be32			mc_addr;
-	int			rx_dst_ifindex;
 	struct ip_mc_socklist __rcu	*mc_list;
 	struct inet_cork_full	cork;
 };
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index ba52c830a7a5..7d658d577368 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -112,6 +112,11 @@ struct inet_timewait_sock {
 #define tw_net			__tw_common.skc_net
 #define tw_daddr        	__tw_common.skc_daddr
 #define tw_rcv_saddr    	__tw_common.skc_rcv_saddr
+#define tw_addrpair		__tw_common.skc_addrpair
+#define tw_dport		__tw_common.skc_dport
+#define tw_num			__tw_common.skc_num
+#define tw_portpair		__tw_common.skc_portpair
+
 	int			tw_timeout;
 	volatile unsigned char	tw_substate;
 	unsigned char		tw_rcv_wscale;
@@ -119,8 +124,6 @@ struct inet_timewait_sock {
 	/* Socket demultiplex comparisons on incoming packets. */
 	/* these three are in inet_sock */
 	__be16			tw_sport;
-	__be16			tw_dport;
-	__u16			tw_num;
 	kmemcheck_bitfield_begin(flags);
 	/* And these are ours. */
 	unsigned int		tw_ipv6only     : 1,
diff --git a/include/net/sock.h b/include/net/sock.h
index c945fba4f543..c4132c1b63a8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -132,6 +132,8 @@ struct net;
  *	@skc_rcv_saddr: Bound local IPv4 addr
  *	@skc_hash: hash value used with various protocol lookup tables
  *	@skc_u16hashes: two u16 hash values used by UDP lookup tables
+ *	@skc_dport: placeholder for inet_dport/tw_dport
+ *	@skc_num: placeholder for inet_num/tw_num
  *	@skc_family: network address family
  *	@skc_state: Connection state
  *	@skc_reuse: %SO_REUSEADDR setting
@@ -149,16 +151,29 @@ struct net;
  *	for struct sock and struct inet_timewait_sock.
  */
 struct sock_common {
-	/* skc_daddr and skc_rcv_saddr must be grouped :
-	 * cf INET_MATCH() and INET_TW_MATCH()
+	/* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned
+	 * address on 64bit arches : cf INET_MATCH() and INET_TW_MATCH()
 	 */
-	__be32			skc_daddr;
-	__be32			skc_rcv_saddr;
-
+	union {
+		unsigned long	skc_addrpair;
+		struct {
+			__be32	skc_daddr;
+			__be32	skc_rcv_saddr;
+		};
+	};
 	union  {
 		unsigned int	skc_hash;
 		__u16		skc_u16hashes[2];
 	};
+	/* skc_dport && skc_num must be grouped as well */
+	union {
+		u32		skc_portpair;
+		struct {
+			__be16	skc_dport;
+			__u16	skc_num;
+		};
+	};
+
 	unsigned short		skc_family;
 	volatile unsigned char	skc_state;
 	unsigned char		skc_reuse;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 7880af970208..fa3ae8148710 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -237,12 +237,14 @@ struct sock *__inet_lookup_established(struct net *net,
 	rcu_read_lock();
 begin:
 	sk_nulls_for_each_rcu(sk, node, &head->chain) {
-		if (INET_MATCH(sk, net, hash, acookie,
-					saddr, daddr, ports, dif)) {
+		if (sk->sk_hash != hash)
+			continue;
+		if (likely(INET_MATCH(sk, net, acookie,
+				      saddr, daddr, ports, dif))) {
 			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
 				goto begintw;
-			if (unlikely(!INET_MATCH(sk, net, hash, acookie,
-				saddr, daddr, ports, dif))) {
+			if (unlikely(!INET_MATCH(sk, net, acookie,
+						 saddr, daddr, ports, dif))) {
 				sock_put(sk);
 				goto begin;
 			}
@@ -260,14 +262,18 @@ begin:
 begintw:
 	/* Must check for a TIME_WAIT'er before going to listener hash. */
 	sk_nulls_for_each_rcu(sk, node, &head->twchain) {
-		if (INET_TW_MATCH(sk, net, hash, acookie,
-					saddr, daddr, ports, dif)) {
+		if (sk->sk_hash != hash)
+			continue;
+		if (likely(INET_TW_MATCH(sk, net, acookie,
+					 saddr, daddr, ports,
+					 dif))) {
 			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
 				sk = NULL;
 				goto out;
 			}
-			if (unlikely(!INET_TW_MATCH(sk, net, hash, acookie,
-				 saddr, daddr, ports, dif))) {
+			if (unlikely(!INET_TW_MATCH(sk, net, acookie,
+						    saddr, daddr, ports,
+						    dif))) {
 				sock_put(sk);
 				goto begintw;
 			}
@@ -314,10 +320,12 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 
 	/* Check TIME-WAIT sockets first. */
 	sk_nulls_for_each(sk2, node, &head->twchain) {
-		tw = inet_twsk(sk2);
+		if (sk2->sk_hash != hash)
+			continue;
 
-		if (INET_TW_MATCH(sk2, net, hash, acookie,
-					saddr, daddr, ports, dif)) {
+		if (likely(INET_TW_MATCH(sk2, net, acookie,
+					 saddr, daddr, ports, dif))) {
+			tw = inet_twsk(sk2);
 			if (twsk_unique(sk, sk2, twp))
 				goto unique;
 			else
@@ -328,8 +336,10 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 
 	/* And established part... */
 	sk_nulls_for_each(sk2, node, &head->chain) {
-		if (INET_MATCH(sk2, net, hash, acookie,
-					saddr, daddr, ports, dif))
+		if (sk2->sk_hash != hash)
+			continue;
+		if (likely(INET_MATCH(sk2, net, acookie,
+				      saddr, daddr, ports, dif)))
 			goto not_unique;
 	}
 
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 73f1a00a96af..dea17fd28e50 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -87,11 +87,13 @@ struct sock *__inet6_lookup_established(struct net *net,
 	rcu_read_lock();
 begin:
 	sk_nulls_for_each_rcu(sk, node, &head->chain) {
-		/* For IPV6 do the cheaper port and family tests first. */
-		if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
+		if (sk->sk_hash != hash)
+			continue;
+		if (likely(INET6_MATCH(sk, net, saddr, daddr, ports, dif))) {
 			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
 				goto begintw;
-			if (!INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
+			if (unlikely(!INET6_MATCH(sk, net, saddr, daddr,
+						  ports, dif))) {
 				sock_put(sk);
 				goto begin;
 			}
@@ -104,12 +106,16 @@ begin:
 begintw:
 	/* Must check for a TIME_WAIT'er before going to listener hash. */
 	sk_nulls_for_each_rcu(sk, node, &head->twchain) {
-		if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
+		if (sk->sk_hash != hash)
+			continue;
+		if (likely(INET6_TW_MATCH(sk, net, saddr, daddr,
+					  ports, dif))) {
 			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
 				sk = NULL;
 				goto out;
 			}
-			if (!INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
+			if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
+						     ports, dif))) {
 				sock_put(sk);
 				goto begintw;
 			}
@@ -236,9 +242,12 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 
 	/* Check TIME-WAIT sockets first. */
 	sk_nulls_for_each(sk2, node, &head->twchain) {
-		tw = inet_twsk(sk2);
+		if (sk2->sk_hash != hash)
+			continue;
 
-		if (INET6_TW_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) {
+		if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr,
+					  ports, dif))) {
+			tw = inet_twsk(sk2);
 			if (twsk_unique(sk, sk2, twp))
 				goto unique;
 			else
@@ -249,7 +258,9 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 
 	/* And established part... */
 	sk_nulls_for_each(sk2, node, &head->chain) {
-		if (INET6_MATCH(sk2, net, hash, saddr, daddr, ports, dif))
+		if (sk2->sk_hash != hash)
+			continue;
+		if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif)))
 			goto not_unique;
 	}
 
-- 
cgit v1.2.3-55-g7522


From 78d86c213f28193082b5d8a1a424044b7ba406f1 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman
Date: Thu, 29 Nov 2012 10:43:28 -0800
Subject: init.h: Remove __dev* sections from the kernel

With the recent work to remove CONFIG_HOTPLUG, we are starting to get a
bunch of __devinit section warnings, despite CONFIG_HOTPLUG always being
enabled.  So, stop marking the sections entirely, by defining them away
the section markings in init.h

Acked-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/init.h | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/init.h b/include/linux/init.h
index e59041e21df3..f63692d6902e 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -93,13 +93,13 @@
 
 #define __exit          __section(.exit.text) __exitused __cold notrace
 
-/* Used for HOTPLUG */
-#define __devinit        __section(.devinit.text) __cold notrace
-#define __devinitdata    __section(.devinit.data)
-#define __devinitconst   __constsection(.devinit.rodata)
-#define __devexit        __section(.devexit.text) __exitused __cold notrace
-#define __devexitdata    __section(.devexit.data)
-#define __devexitconst   __constsection(.devexit.rodata)
+/* Used for HOTPLUG, but that is always enabled now, so just make them noops */
+#define __devinit
+#define __devinitdata
+#define __devinitconst
+#define __devexit
+#define __devexitdata
+#define __devexitconst
 
 /* Used for HOTPLUG_CPU */
 #define __cpuinit        __section(.cpuinit.text) __cold notrace
@@ -126,10 +126,6 @@
 #define __INITRODATA	.section	".init.rodata","a",%progbits
 #define __FINITDATA	.previous
 
-#define __DEVINIT        .section	".devinit.text", "ax"
-#define __DEVINITDATA    .section	".devinit.data", "aw"
-#define __DEVINITRODATA  .section	".devinit.rodata", "a"
-
 #define __CPUINIT        .section	".cpuinit.text", "ax"
 #define __CPUINITDATA    .section	".cpuinit.data", "aw"
 #define __CPUINITRODATA  .section	".cpuinit.rodata", "a"
-- 
cgit v1.2.3-55-g7522


From dc1bdbd9b8a077018d82230bc378f1bcfd8adba8 Mon Sep 17 00:00:00 2001
From: Bart Van Assche
Date: Fri, 16 Sep 2011 20:41:13 +0200
Subject: IB/srp: Allow SRP disconnect through sysfs

Make it possible to disconnect the IB RC connection used by the SRP
protocol to communicate with a target.

Have the SRP transport layer create a sysfs "delete" attribute for
initiator drivers that support this functionality.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: David Dillow <dillowda@ornl.gov>
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Robert Jennings <rcj@linux.vnet.ibm.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 Documentation/ABI/stable/sysfs-transport-srp |  7 +++++++
 drivers/infiniband/ulp/srp/ib_srp.c          | 10 ++++++++++
 drivers/scsi/scsi_transport_srp.c            | 22 +++++++++++++++++++++-
 include/scsi/scsi_transport_srp.h            |  8 ++++++++
 4 files changed, 46 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/ABI/stable/sysfs-transport-srp b/Documentation/ABI/stable/sysfs-transport-srp
index 7b0d4a5350f1..b36fb0dc13c8 100644
--- a/Documentation/ABI/stable/sysfs-transport-srp
+++ b/Documentation/ABI/stable/sysfs-transport-srp
@@ -1,3 +1,10 @@
+What:		/sys/class/srp_remote_ports/port-<h>:<n>/delete
+Date:		June 1, 2012
+KernelVersion:	3.7
+Contact:	linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org
+Description:	Instructs an SRP initiator to disconnect from a target and to
+		remove all LUNs imported from that target.
+
 What:		/sys/class/srp_remote_ports/port-<h>:<n>/port_id
 Date:		June 27, 2007
 KernelVersion:	2.6.24
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 84d9298ed989..d5088ce78290 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -549,6 +549,13 @@ static void srp_remove_work(struct work_struct *work)
 	srp_remove_target(target);
 }
 
+static void srp_rport_delete(struct srp_rport *rport)
+{
+	struct srp_target_port *target = rport->lld_data;
+
+	srp_queue_remove_work(target);
+}
+
 static int srp_connect_target(struct srp_target_port *target)
 {
 	int retries = 3;
@@ -1958,6 +1965,8 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target)
 		return PTR_ERR(rport);
 	}
 
+	rport->lld_data = target;
+
 	spin_lock(&host->target_lock);
 	list_add_tail(&target->list, &host->target_list);
 	spin_unlock(&host->target_lock);
@@ -2524,6 +2533,7 @@ static void srp_remove_one(struct ib_device *device)
 }
 
 static struct srp_function_template ib_srp_transport_functions = {
+	.rport_delete		 = srp_rport_delete,
 };
 
 static int __init srp_init_module(void)
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index 0d85f797141f..f379c7f3034c 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -38,7 +38,7 @@ struct srp_host_attrs {
 #define to_srp_host_attrs(host)	((struct srp_host_attrs *)(host)->shost_data)
 
 #define SRP_HOST_ATTRS 0
-#define SRP_RPORT_ATTRS 2
+#define SRP_RPORT_ATTRS 3
 
 struct srp_internal {
 	struct scsi_transport_template t;
@@ -116,6 +116,24 @@ show_srp_rport_roles(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR(roles, S_IRUGO, show_srp_rport_roles, NULL);
 
+static ssize_t store_srp_rport_delete(struct device *dev,
+				      struct device_attribute *attr,
+				      const char *buf, size_t count)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+	struct Scsi_Host *shost = dev_to_shost(dev);
+	struct srp_internal *i = to_srp_internal(shost->transportt);
+
+	if (i->f->rport_delete) {
+		i->f->rport_delete(rport);
+		return count;
+	} else {
+		return -ENOSYS;
+	}
+}
+
+static DEVICE_ATTR(delete, S_IWUSR, NULL, store_srp_rport_delete);
+
 static void srp_rport_release(struct device *dev)
 {
 	struct srp_rport *rport = dev_to_rport(dev);
@@ -309,6 +327,8 @@ srp_attach_transport(struct srp_function_template *ft)
 	count = 0;
 	i->rport_attrs[count++] = &dev_attr_port_id;
 	i->rport_attrs[count++] = &dev_attr_roles;
+	if (ft->rport_delete)
+		i->rport_attrs[count++] = &dev_attr_delete;
 	i->rport_attrs[count++] = NULL;
 	BUG_ON(count > ARRAY_SIZE(i->rport_attrs));
 
diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h
index 9c60ca1c08c5..ff0f04ac91aa 100644
--- a/include/scsi/scsi_transport_srp.h
+++ b/include/scsi/scsi_transport_srp.h
@@ -14,13 +14,21 @@ struct srp_rport_identifiers {
 };
 
 struct srp_rport {
+	/* for initiator and target drivers */
+
 	struct device dev;
 
 	u8 port_id[16];
 	u8 roles;
+
+	/* for initiator drivers */
+
+	void *lld_data;	/* LLD private data */
 };
 
 struct srp_function_template {
+	/* for initiator drivers */
+	void (*rport_delete)(struct srp_rport *rport);
 	/* for target drivers */
 	int (* tsk_mgmt_response)(struct Scsi_Host *, u64, u64, int);
 	int (* it_nexus_response)(struct Scsi_Host *, u64, int);
-- 
cgit v1.2.3-55-g7522


From 78ad724ade23c66650dcaba04f4d2307c2884c69 Mon Sep 17 00:00:00 2001
From: Sreekanth Reddy
Date: Fri, 30 Nov 2012 07:58:10 +0530
Subject: [SCSI] miscdevice: Adding support for MPT3SAS_MINOR(222)

Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@lsi.com>
Reviewed-by: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
---
 include/linux/miscdevice.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index e0deeb2cc939..09c2300ddb37 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -34,6 +34,7 @@
 #define MWAVE_MINOR		219	/* ACP/Mwave Modem */
 #define MPT_MINOR		220
 #define MPT2SAS_MINOR		221
+#define MPT3SAS_MINOR		222
 #define UINPUT_MINOR		223
 #define MISC_MCELOG_MINOR	227
 #define HPET_MINOR		228
-- 
cgit v1.2.3-55-g7522


From d84fd392bd61524c4d81367969424e6c17086c8c Mon Sep 17 00:00:00 2001
From: Sreekanth Reddy
Date: Fri, 30 Nov 2012 07:43:11 +0530
Subject: [SCSI] scsi_transport_sas: add 12GB definitions for mpt3sas

[jejb: split this core change into a separate patch]
Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@lsi.com>
Reviewed-by: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
---
 drivers/scsi/scsi_transport_sas.c | 1 +
 include/scsi/scsi_transport_sas.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index f7565fc4f0e3..1b681427dde0 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -151,6 +151,7 @@ static struct {
 	{ SAS_LINK_RATE_1_5_GBPS,	"1.5 Gbit" },
 	{ SAS_LINK_RATE_3_0_GBPS,	"3.0 Gbit" },
 	{ SAS_LINK_RATE_6_0_GBPS,	"6.0 Gbit" },
+	{ SAS_LINK_RATE_12_0_GBPS,	"12.0 Gbit" },
 };
 sas_bitfield_name_search(linkspeed, sas_linkspeed_names)
 sas_bitfield_name_set(linkspeed, sas_linkspeed_names)
diff --git a/include/scsi/scsi_transport_sas.h b/include/scsi/scsi_transport_sas.h
index 98b3a20a0102..9b8e08879cfc 100644
--- a/include/scsi/scsi_transport_sas.h
+++ b/include/scsi/scsi_transport_sas.h
@@ -36,6 +36,7 @@ enum sas_linkrate {
 	SAS_LINK_RATE_3_0_GBPS = 9,
 	SAS_LINK_RATE_G2 = SAS_LINK_RATE_3_0_GBPS,
 	SAS_LINK_RATE_6_0_GBPS = 10,
+	SAS_LINK_RATE_12_0_GBPS = 11,
 	/* These are virtual to the transport class and may never
 	 * be signalled normally since the standard defined field
 	 * is only 4 bits */
-- 
cgit v1.2.3-55-g7522


From aeaf6e9d2f49d793d3eb8c1af4095cf25e061b94 Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani
Date: Fri, 30 Nov 2012 10:25:59 +0000
Subject: ipv6: unify logic evaluating inet6_dev's accept_ra property

As of 026359b [ipv6: Send ICMPv6 RSes only when RAs are accepted], the
logic determining whether to send Router Solicitations is identical
to the logic determining whether kernel accepts Router Advertisements.

However the condition itself is repeated in several code locations.

Unify it by introducing 'ipv6_accept_ra()' accessor.

Also, simplify the condition expression, making it more readable.
No semantic change.

Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h  |  9 +++++++++
 net/ipv6/addrconf.c |  3 +--
 net/ipv6/ndisc.c    | 16 ++--------------
 3 files changed, 12 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index acbd8e034310..5af66b26ebdd 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -271,6 +271,15 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
 
 extern bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb);
 
+static inline bool ipv6_accept_ra(struct inet6_dev *idev)
+{
+	/* If forwarding is enabled, RA are not accepted unless the special
+	 * hybrid mode (accept_ra=2) is enabled.
+	 */
+	return idev->cnf.forwarding ? idev->cnf.accept_ra == 2 :
+	    idev->cnf.accept_ra;
+}
+
 #if IS_ENABLED(CONFIG_IPV6)
 static inline int ip6_frag_nqueues(struct net *net)
 {
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index fc0e13ad6337..4b644f656c41 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3150,8 +3150,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 	   router advertisements, start sending router solicitations.
 	 */
 
-	if (((ifp->idev->cnf.accept_ra == 1 && !ifp->idev->cnf.forwarding) ||
-	     ifp->idev->cnf.accept_ra == 2) &&
+	if (ipv6_accept_ra(ifp->idev) &&
 	    ifp->idev->cnf.rtr_solicits > 0 &&
 	    (dev->flags&IFF_LOOPBACK) == 0 &&
 	    (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) {
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index f41853bca428..cf43b6550f5b 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1032,18 +1032,6 @@ errout:
 	rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err);
 }
 
-static inline int accept_ra(struct inet6_dev *in6_dev)
-{
-	/*
-	 * If forwarding is enabled, RA are not accepted unless the special
-	 * hybrid mode (accept_ra=2) is enabled.
-	 */
-	if (in6_dev->cnf.forwarding && in6_dev->cnf.accept_ra < 2)
-		return 0;
-
-	return in6_dev->cnf.accept_ra;
-}
-
 static void ndisc_router_discovery(struct sk_buff *skb)
 {
 	struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb);
@@ -1091,7 +1079,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 		return;
 	}
 
-	if (!accept_ra(in6_dev))
+	if (!ipv6_accept_ra(in6_dev))
 		goto skip_linkparms;
 
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
@@ -1247,7 +1235,7 @@ skip_linkparms:
 			     NEIGH_UPDATE_F_ISROUTER);
 	}
 
-	if (!accept_ra(in6_dev))
+	if (!ipv6_accept_ra(in6_dev))
 		goto out;
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
-- 
cgit v1.2.3-55-g7522


From c971f08cba56ed17fe22040ca5ff97fe5c3f0bd7 Mon Sep 17 00:00:00 2001
From: David Woodhouse
Date: Wed, 28 Nov 2012 00:03:11 +0000
Subject: atm: add release_cb() callback to vcc

The immediate use case for this is that it will allow us to ensure that a
pppoatm queue is woken after it has to drop a packet due to the sock being
locked.

Note that 'release_cb' is called when the socket is *unlocked*. This is
not to be confused with vcc_release() — which probably ought to be called
vcc_close().

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Acked-by: Krzysztof Mazur <krzysiek@podlesie.net>
---
 include/linux/atmdev.h |  1 +
 net/atm/common.c       | 10 ++++++++++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 72db2af902a8..c1da539f5e28 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -99,6 +99,7 @@ struct atm_vcc {
 	struct atm_dev	*dev;		/* device back pointer */
 	struct atm_qos	qos;		/* QOS */
 	struct atm_sap	sap;		/* SAP */
+	void (*release_cb)(struct atm_vcc *vcc); /* release_sock callback */
 	void (*push)(struct atm_vcc *vcc,struct sk_buff *skb);
 	void (*pop)(struct atm_vcc *vcc,struct sk_buff *skb); /* optional */
 	int (*push_oam)(struct atm_vcc *vcc,void *cell);
diff --git a/net/atm/common.c b/net/atm/common.c
index 24216642d696..806fc0a40051 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -126,10 +126,19 @@ static void vcc_write_space(struct sock *sk)
 	rcu_read_unlock();
 }
 
+static void vcc_release_cb(struct sock *sk)
+{
+	struct atm_vcc *vcc = atm_sk(sk);
+
+	if (vcc->release_cb)
+		vcc->release_cb(vcc);
+}
+
 static struct proto vcc_proto = {
 	.name	  = "VCC",
 	.owner	  = THIS_MODULE,
 	.obj_size = sizeof(struct atm_vcc),
+	.release_cb = vcc_release_cb,
 };
 
 int vcc_create(struct net *net, struct socket *sock, int protocol, int family)
@@ -158,6 +167,7 @@ int vcc_create(struct net *net, struct socket *sock, int protocol, int family)
 	vcc->pop = NULL;
 	vcc->owner = NULL;
 	vcc->push_oam = NULL;
+	vcc->release_cb = NULL;
 	vcc->vpi = vcc->vci = 0; /* no VCI/VPI yet */
 	vcc->atm_options = vcc->aal_options = 0;
 	sk->sk_destruct = vcc_sock_destruct;
-- 
cgit v1.2.3-55-g7522


From 26047e2d6bde5b2e1b791e0ec1c3234894fdf3fa Mon Sep 17 00:00:00 2001
From: Daniel Mack
Date: Fri, 30 Nov 2012 11:28:55 +0100
Subject: ASoC: cs4271: fix sparse warning

Make the flag in the pdata of type bool to fix a sparse warning.

Signed-off-by: Daniel Mack <zonque@gmail.com>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/sound/cs4271.h    | 2 +-
 sound/soc/codecs/cs4271.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/sound/cs4271.h b/include/sound/cs4271.h
index 6d9e15ed1dcf..dd8c48d14ed9 100644
--- a/include/sound/cs4271.h
+++ b/include/sound/cs4271.h
@@ -19,7 +19,7 @@
 
 struct cs4271_platform_data {
 	int gpio_nreset;	/* GPIO driving Reset pin, if any */
-	int amutec_eq_bmutec:1;	/* flag to enable AMUTEC=BMUTEC */
+	bool amutec_eq_bmutec;	/* flag to enable AMUTEC=BMUTEC */
 };
 
 #endif /* __CS4271_H */
diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c
index 2ac5fe61a96c..f07d1b7d6c69 100644
--- a/sound/soc/codecs/cs4271.c
+++ b/sound/soc/codecs/cs4271.c
@@ -474,7 +474,7 @@ static int cs4271_probe(struct snd_soc_codec *codec)
 	struct cs4271_platform_data *cs4271plat = codec->dev->platform_data;
 	int ret;
 	int gpio_nreset = -EINVAL;
-	int amutec_eq_bmutec = 0;
+	bool amutec_eq_bmutec = false;
 
 #ifdef CONFIG_OF
 	if (of_match_device(cs4271_dt_ids, codec->dev)) {
@@ -483,7 +483,7 @@ static int cs4271_probe(struct snd_soc_codec *codec)
 
 		if (!of_get_property(codec->dev->of_node,
 				     "cirrus,amutec-eq-bmutec", NULL))
-			amutec_eq_bmutec = 1;
+			amutec_eq_bmutec = true;
 	}
 #endif
 
-- 
cgit v1.2.3-55-g7522


From 077b393d05915f04e2629bfc47c6fce95cae7d3f Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Sun, 2 Dec 2012 07:33:10 +0000
Subject: net: fix sparse endianness warnings on sock_common

# make C=2 CF=-D__CHECK_ENDIAN__ net/ipv4/inet_hashtables.o
...
net/ipv4/inet_hashtables.c:242:7: warning: restricted __portpair degrades to integer
net/ipv4/inet_hashtables.c:242:7: warning: restricted __addrpair degrades to integer
...

Move __portpair/__addrpair from include/net/inet_hashtables.h
to include/net/sock.h where we need them in struct sock_common

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ling Ma <ling.ma.program@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h | 2 --
 include/net/sock.h            | 7 +++++--
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index d1de4fbd45c2..67a8fa098e3a 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -277,7 +277,6 @@ static inline struct sock *inet_lookup_listener(struct net *net,
    On 64bit targets we combine comparisons with pair of adjacent __be32
    fields in the same way.
 */
-typedef __u32 __bitwise __portpair;
 #ifdef __BIG_ENDIAN
 #define INET_COMBINED_PORTS(__sport, __dport) \
 	((__force __portpair)(((__force __u32)(__be16)(__sport) << 16) | (__u32)(__dport)))
@@ -287,7 +286,6 @@ typedef __u32 __bitwise __portpair;
 #endif
 
 #if (BITS_PER_LONG == 64)
-typedef __u64 __bitwise __addrpair;
 #ifdef __BIG_ENDIAN
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
 	const __addrpair __name = (__force __addrpair) ( \
diff --git a/include/net/sock.h b/include/net/sock.h
index c4132c1b63a8..0a9a01a5b0d7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -126,6 +126,9 @@ struct sock;
 struct proto;
 struct net;
 
+typedef __u32 __bitwise __portpair;
+typedef __u64 __bitwise __addrpair;
+
 /**
  *	struct sock_common - minimal network layer representation of sockets
  *	@skc_daddr: Foreign IPv4 addr
@@ -155,7 +158,7 @@ struct sock_common {
 	 * address on 64bit arches : cf INET_MATCH() and INET_TW_MATCH()
 	 */
 	union {
-		unsigned long	skc_addrpair;
+		__addrpair	skc_addrpair;
 		struct {
 			__be32	skc_daddr;
 			__be32	skc_rcv_saddr;
@@ -167,7 +170,7 @@ struct sock_common {
 	};
 	/* skc_dport && skc_num must be grouped as well */
 	union {
-		u32		skc_portpair;
+		__portpair	skc_portpair;
 		struct {
 			__be16	skc_dport;
 			__u16	skc_num;
-- 
cgit v1.2.3-55-g7522


From 0d0cdb028f9d9771e2b346038707734121f906e3 Mon Sep 17 00:00:00 2001
From: Aaron Lu
Date: Mon, 26 Nov 2012 13:55:25 +0800
Subject: libata: restore acpi disable functionality

Commit 66fa7f215 "libata-acpi: improve ACPI disabling" introdcued the
behaviour of disabling ATA ACPI if ata_acpi_on_devcfg failed the 2nd
time, but commit 30dcf76ac dropped this behaviour and this caused
problem for Dimitris Damigos, where his laptop can not resume correctly.

The bugzilla page for it is:
https://bugzilla.kernel.org/show_bug.cgi?id=49331

The problem is, ata_dev_push_id will fail the 2nd time it is invoked,
and due to disabling ACPI code is dropped, ata_acpi_on_devcfg which
calls ata_dev_push_id will keep failing and eventually made the device
disabled.

This patch restores the original behaviour, if acpi failed the 2nd time,
disable acpi functionality for the device(and we do not event need to
add a debug message for this as it is still there ;-).

Reported-by: Dimitris Damigos <damigos@freemail.gr>
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/libata-acpi.c | 4 ++++
 include/linux/libata.h    | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index 5b0ba3f20edc..ef01ac07502e 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -76,6 +76,9 @@ acpi_handle ata_dev_acpi_handle(struct ata_device *dev)
 	acpi_integer adr;
 	struct ata_port *ap = dev->link->ap;
 
+	if (dev->flags & ATA_DFLAG_ACPI_DISABLED)
+		return NULL;
+
 	if (ap->flags & ATA_FLAG_ACPI_SATA) {
 		if (!sata_pmp_attached(ap))
 			adr = SATA_ADR(ap->port_no, NO_PORT_MULT);
@@ -945,6 +948,7 @@ int ata_acpi_on_devcfg(struct ata_device *dev)
 		return rc;
 	}
 
+	dev->flags |= ATA_DFLAG_ACPI_DISABLED;
 	ata_dev_warn(dev, "ACPI: failed the second time, disabled\n");
 
 	/* We can safely continue if no _GTF command has been executed
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 77eeeda2b6e2..e931c9ad1078 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -163,6 +163,7 @@ enum {
 
 	ATA_DFLAG_DA		= (1 << 26), /* device supports Device Attention */
 	ATA_DFLAG_DEVSLP	= (1 << 27), /* device supports Device Sleep */
+	ATA_DFLAG_ACPI_DISABLED = (1 << 28), /* ACPI for the device is disabled */
 
 	ATA_DEV_UNKNOWN		= 0,	/* unknown device */
 	ATA_DEV_ATA		= 1,	/* ATA device */
-- 
cgit v1.2.3-55-g7522


From de90cd71f68e947d3bd6c3f2ef5731ead010a768 Mon Sep 17 00:00:00 2001
From: Shane Huang
Date: Sun, 18 Nov 2012 04:44:41 +0800
Subject: libata: check SATA_SETTINGS log with HW Feature Ctrl

NCQ capability was used to check availability of SATA Settings page
from Identify Device Data Log, which contains DevSlp timing variables.
It does not work on some HDDs and leads to error messages.
IDENTIFY word 78 bit 5(Hardware Feature Control) should be used.

Quoting SATA spec 3.1:
If Hardware Feature Control is supported, then:
a) IDENTIFY DEVICE data word 78 bit 5 (see 13.2.1.18) shall be
set to one;
b) the SET FEATURES Select Hardware Feature Control subcommand
shall be supported (see 13.3.8);
c) page 08h of the Identify Device Data log (see 13.7.7) shall
be supported;

This patch is not tested on SATA HDD with DevSlp supported.

Reported-by: Borislav Petkov <bp@amd64.org>
Signed-off-by: Shane Huang <shane.huang@amd.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/libata-core.c | 3 +--
 include/linux/ata.h       | 1 +
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index f46fbd3bd3fb..caffe73c1e4a 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2330,9 +2330,8 @@ int ata_dev_configure(struct ata_device *dev)
 
 		/* Obtain SATA Settings page from Identify Device Data Log,
 		 * which contains DevSlp timing variables etc.
-		 * Exclude old devices with ata_id_has_ncq()
 		 */
-		if (ata_id_has_ncq(dev->id)) {
+		if (ata_id_has_hw_feature_ctrl(dev->id)) {
 			err_mask = ata_read_log_page(dev,
 						     ATA_LOG_SATA_ID_DEV_DATA,
 						     ATA_LOG_SATA_SETTINGS,
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 408da9502177..18cbb93fdbca 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -593,6 +593,7 @@ static inline int ata_is_data(u8 prot)
 #define ata_id_cdb_intr(id)	(((id)[ATA_ID_CONFIG] & 0x60) == 0x20)
 #define ata_id_has_da(id)	((id)[ATA_ID_SATA_CAPABILITY_2] & (1 << 4))
 #define ata_id_has_devslp(id)	((id)[ATA_ID_FEATURE_SUPP] & (1 << 8))
+#define ata_id_has_hw_feature_ctrl(id)	((id)[ATA_ID_FEATURE_SUPP] & (1 << 5))
 
 static inline bool ata_id_has_hipm(const u16 *id)
 {
-- 
cgit v1.2.3-55-g7522


From b7db04d9264fca4b00e949da7b3180c50e243fca Mon Sep 17 00:00:00 2001
From: Brian Norris
Date: Fri, 2 Nov 2012 12:29:32 -0700
Subject: libata: implement ata_platform_remove_one()

This relatively simple boiler-plate code is repeated in several platform
drivers. We should implement a common version in libata.

Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/libata-core.c | 23 +++++++++++++++++++++++
 include/linux/libata.h    |  4 ++++
 2 files changed, 27 insertions(+)

(limited to 'include')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 583f26d6d455..8e3f4a90c088 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -67,6 +67,7 @@
 #include <linux/cdrom.h>
 #include <linux/ratelimit.h>
 #include <linux/pm_runtime.h>
+#include <linux/platform_device.h>
 
 #include "libata.h"
 #include "libata-transport.h"
@@ -6382,6 +6383,26 @@ int ata_pci_device_resume(struct pci_dev *pdev)
 
 #endif /* CONFIG_PCI */
 
+/**
+ *	ata_platform_remove_one - Platform layer callback for device removal
+ *	@pdev: Platform device that was removed
+ *
+ *	Platform layer indicates to libata via this hook that hot-unplug or
+ *	module unload event has occurred.  Detach all ports.  Resource
+ *	release is handled via devres.
+ *
+ *	LOCKING:
+ *	Inherited from platform layer (may sleep).
+ */
+int ata_platform_remove_one(struct platform_device *pdev)
+{
+	struct ata_host *host = platform_get_drvdata(pdev);
+
+	ata_host_detach(host);
+
+	return 0;
+}
+
 static int __init ata_parse_force_one(char **cur,
 				      struct ata_force_ent *force_ent,
 				      const char **reason)
@@ -6877,6 +6898,8 @@ EXPORT_SYMBOL_GPL(ata_pci_device_resume);
 #endif /* CONFIG_PM */
 #endif /* CONFIG_PCI */
 
+EXPORT_SYMBOL_GPL(ata_platform_remove_one);
+
 EXPORT_SYMBOL_GPL(__ata_ehi_push_desc);
 EXPORT_SYMBOL_GPL(ata_ehi_push_desc);
 EXPORT_SYMBOL_GPL(ata_ehi_clear_desc);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index e931c9ad1078..83ba0ab2c915 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1115,6 +1115,10 @@ extern int ata_pci_device_resume(struct pci_dev *pdev);
 #endif /* CONFIG_PM */
 #endif /* CONFIG_PCI */
 
+struct platform_device;
+
+extern int ata_platform_remove_one(struct platform_device *pdev);
+
 /*
  * ACPI - drivers/ata/libata-acpi.c
  */
-- 
cgit v1.2.3-55-g7522


From 156f34d26a74c6ea060fb43d898f17509ed8e18a Mon Sep 17 00:00:00 2001
From: Brian Norris
Date: Fri, 2 Nov 2012 00:46:24 -0700
Subject: pata_platform: remove unused remove function

All users of __pata_platform_remove() have been converted to utilize the
common ata_platform_remove_one().

Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/pata_platform.c  | 17 -----------------
 include/linux/ata_platform.h |  2 --
 2 files changed, 19 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c
index 449aa29931bc..f4372d0c7ce6 100644
--- a/drivers/ata/pata_platform.c
+++ b/drivers/ata/pata_platform.c
@@ -178,23 +178,6 @@ int __devinit __pata_platform_probe(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(__pata_platform_probe);
 
-/**
- *	__pata_platform_remove		-	unplug a platform interface
- *	@dev: device
- *
- *	A platform bus ATA device has been unplugged. Perform the needed
- *	cleanup. Also called on module unload for any active devices.
- */
-int __pata_platform_remove(struct device *dev)
-{
-	struct ata_host *host = dev_get_drvdata(dev);
-
-	ata_host_detach(host);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(__pata_platform_remove);
-
 static int __devinit pata_platform_probe(struct platform_device *pdev)
 {
 	struct resource *io_res;
diff --git a/include/linux/ata_platform.h b/include/linux/ata_platform.h
index b856a2a590d9..fe9989636b62 100644
--- a/include/linux/ata_platform.h
+++ b/include/linux/ata_platform.h
@@ -22,8 +22,6 @@ extern int __devinit __pata_platform_probe(struct device *dev,
 					   unsigned int ioport_shift,
 					   int __pio_mask);
 
-extern int __devexit __pata_platform_remove(struct device *dev);
-
 /*
  * Marvell SATA private data
  */
-- 
cgit v1.2.3-55-g7522


From 5d7fad48ca763f6b20c2d4daf7df9fd7aa2cb242 Mon Sep 17 00:00:00 2001
From: Simon Wunderlich
Date: Fri, 30 Nov 2012 19:17:28 +0100
Subject: mac80211: Fix typo in mac80211.h

Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 0472d806fb41..1c02fb3b3817 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -164,7 +164,7 @@ enum ieee80211_chanctx_change {
  *	active on the channel to receive MIMO transmissions
  * @rx_chains_dynamic: The number of RX chains that must be enabled
  *	after RTS/CTS handshake to receive SMPS MIMO transmissions;
- *	this will always be >= @rx_chains_always.
+ *	this will always be >= @rx_chains_static.
  * @drv_priv: data area for driver use, will always be aligned to
  *	sizeof(void *), size is determined in hw information.
  */
-- 
cgit v1.2.3-55-g7522


From 3ad909bc8f2ea32fd7d24266c61cd4605feecec8 Mon Sep 17 00:00:00 2001
From: Linus Walleij
Date: Fri, 30 Nov 2012 16:30:43 +0100
Subject: ARM: 7588/1: amba: create a resource parent registrator

This creates amba_apb_device_add_res() and
amba_ahb_device_add_res() respectively, to add devices with
another parent than iomem_resource. This is needed to specify
that a device is contained in a specific IO range.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 drivers/amba/bus.c       | 32 ++++++++++++++++++++++++++++----
 include/linux/amba/bus.h | 10 ++++++++++
 2 files changed, 38 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index e8eb91bd0d28..a2fc56d2e681 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -546,7 +546,8 @@ EXPORT_SYMBOL_GPL(amba_device_add);
 static struct amba_device *
 amba_aphb_device_add(struct device *parent, const char *name,
 		     resource_size_t base, size_t size, int irq1, int irq2,
-		     void *pdata, unsigned int periphid, u64 dma_mask)
+		     void *pdata, unsigned int periphid, u64 dma_mask,
+		     struct resource *resbase)
 {
 	struct amba_device *dev;
 	int ret;
@@ -563,7 +564,7 @@ amba_aphb_device_add(struct device *parent, const char *name,
 	dev->dev.platform_data = pdata;
 	dev->dev.parent = parent;
 
-	ret = amba_device_add(dev, &iomem_resource);
+	ret = amba_device_add(dev, resbase);
 	if (ret) {
 		amba_device_put(dev);
 		return ERR_PTR(ret);
@@ -578,7 +579,7 @@ amba_apb_device_add(struct device *parent, const char *name,
 		    void *pdata, unsigned int periphid)
 {
 	return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata,
-				    periphid, 0);
+				    periphid, 0, &iomem_resource);
 }
 EXPORT_SYMBOL_GPL(amba_apb_device_add);
 
@@ -588,10 +589,33 @@ amba_ahb_device_add(struct device *parent, const char *name,
 		    void *pdata, unsigned int periphid)
 {
 	return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata,
-				    periphid, ~0ULL);
+				    periphid, ~0ULL, &iomem_resource);
 }
 EXPORT_SYMBOL_GPL(amba_ahb_device_add);
 
+struct amba_device *
+amba_apb_device_add_res(struct device *parent, const char *name,
+			resource_size_t base, size_t size, int irq1,
+			int irq2, void *pdata, unsigned int periphid,
+			struct resource *resbase)
+{
+	return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata,
+				    periphid, 0, resbase);
+}
+EXPORT_SYMBOL_GPL(amba_apb_device_add_res);
+
+struct amba_device *
+amba_ahb_device_add_res(struct device *parent, const char *name,
+			resource_size_t base, size_t size, int irq1,
+			int irq2, void *pdata, unsigned int periphid,
+			struct resource *resbase)
+{
+	return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata,
+				    periphid, ~0ULL, resbase);
+}
+EXPORT_SYMBOL_GPL(amba_ahb_device_add_res);
+
+
 static void amba_device_initialize(struct amba_device *dev, const char *name)
 {
 	device_initialize(&dev->dev);
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index d36417158d8f..43ec7e247a80 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -71,6 +71,16 @@ struct amba_device *amba_ahb_device_add(struct device *parent, const char *name,
 					resource_size_t base, size_t size,
 					int irq1, int irq2, void *pdata,
 					unsigned int periphid);
+struct amba_device *
+amba_apb_device_add_res(struct device *parent, const char *name,
+			resource_size_t base, size_t size, int irq1,
+			int irq2, void *pdata, unsigned int periphid,
+			struct resource *resbase);
+struct amba_device *
+amba_ahb_device_add_res(struct device *parent, const char *name,
+			resource_size_t base, size_t size, int irq1,
+			int irq2, void *pdata, unsigned int periphid,
+			struct resource *resbase);
 void amba_device_unregister(struct amba_device *);
 struct amba_device *amba_find_device(const char *, struct device *, unsigned int, unsigned int);
 int amba_request_regions(struct amba_device *, const char *);
-- 
cgit v1.2.3-55-g7522


From 04dac0111da7e1d284952cd415162451ffaa094d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Tue, 27 Nov 2012 21:30:52 +0100
Subject: netfilter: nf_conntrack: improve nf_conn object traceability

This patch modifies the conntrack subsystem so that all existing
allocated conntrack objects can be found in any of the following
places:

* the hash table, this is the typical place for alive conntrack objects.
* the unconfirmed list, this is the place for newly created conntrack objects
  that are still traversing the stack.
* the dying list, this is where you can find conntrack objects that are dying
  or that should die anytime soon (eg. once the destroy event is delivered to
  the conntrackd daemon).

Thus, we make sure that we follow the track for all existing conntrack
objects. This patch, together with some extension of the ctnetlink interface
to dump the content of the dying and unconfirmed lists, will help in case
to debug suspected nf_conn object leaks.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack.h |  2 +-
 net/netfilter/nf_conntrack_core.c    | 25 +++++++++----------------
 net/netfilter/nf_conntrack_netlink.c |  2 +-
 3 files changed, 11 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index f1494feba79f..caca0c4d6b4b 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -182,7 +182,7 @@ __nf_conntrack_find(struct net *net, u16 zone,
 
 extern int nf_conntrack_hash_check_insert(struct nf_conn *ct);
 extern void nf_ct_delete_from_lists(struct nf_conn *ct);
-extern void nf_ct_insert_dying_list(struct nf_conn *ct);
+extern void nf_ct_dying_timeout(struct nf_conn *ct);
 
 extern void nf_conntrack_flush_report(struct net *net, u32 pid, int report);
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 0f241be28f9e..af175166fffa 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -221,11 +221,9 @@ destroy_conntrack(struct nf_conntrack *nfct)
 	 * too. */
 	nf_ct_remove_expectations(ct);
 
-	/* We overload first tuple to link into unconfirmed list. */
-	if (!nf_ct_is_confirmed(ct)) {
-		BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
-		hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
-	}
+	/* We overload first tuple to link into unconfirmed or dying list.*/
+	BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
+	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
 
 	NF_CT_STAT_INC(net, delete);
 	spin_unlock_bh(&nf_conntrack_lock);
@@ -247,6 +245,9 @@ void nf_ct_delete_from_lists(struct nf_conn *ct)
 	 * Otherwise we can get spurious warnings. */
 	NF_CT_STAT_INC(net, delete_list);
 	clean_from_lists(ct);
+	/* add this conntrack to the dying list */
+	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+			     &net->ct.dying);
 	spin_unlock_bh(&nf_conntrack_lock);
 }
 EXPORT_SYMBOL_GPL(nf_ct_delete_from_lists);
@@ -268,31 +269,23 @@ static void death_by_event(unsigned long ul_conntrack)
 	}
 	/* we've got the event delivered, now it's dying */
 	set_bit(IPS_DYING_BIT, &ct->status);
-	spin_lock(&nf_conntrack_lock);
-	hlist_nulls_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
-	spin_unlock(&nf_conntrack_lock);
 	nf_ct_put(ct);
 }
 
-void nf_ct_insert_dying_list(struct nf_conn *ct)
+void nf_ct_dying_timeout(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
 	struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct);
 
 	BUG_ON(ecache == NULL);
 
-	/* add this conntrack to the dying list */
-	spin_lock_bh(&nf_conntrack_lock);
-	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
-			     &net->ct.dying);
-	spin_unlock_bh(&nf_conntrack_lock);
 	/* set a new timer to retry event delivery */
 	setup_timer(&ecache->timeout, death_by_event, (unsigned long)ct);
 	ecache->timeout.expires = jiffies +
 		(random32() % net->ct.sysctl_events_retry_timeout);
 	add_timer(&ecache->timeout);
 }
-EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list);
+EXPORT_SYMBOL_GPL(nf_ct_dying_timeout);
 
 static void death_by_timeout(unsigned long ul_conntrack)
 {
@@ -307,7 +300,7 @@ static void death_by_timeout(unsigned long ul_conntrack)
 	    unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) {
 		/* destroy event was not delivered */
 		nf_ct_delete_from_lists(ct);
-		nf_ct_insert_dying_list(ct);
+		nf_ct_dying_timeout(ct);
 		return;
 	}
 	set_bit(IPS_DYING_BIT, &ct->status);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 7bbfb3deea30..34370a928360 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -989,7 +989,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 					      nlmsg_report(nlh)) < 0) {
 			nf_ct_delete_from_lists(ct);
 			/* we failed to report the event, try later */
-			nf_ct_insert_dying_list(ct);
+			nf_ct_dying_timeout(ct);
 			nf_ct_put(ct);
 			return 0;
 		}
-- 
cgit v1.2.3-55-g7522


From d871befe357ccc262edbb0a4f9aeea650012edf5 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Tue, 27 Nov 2012 14:49:42 +0100
Subject: netfilter: ctnetlink: dump entries from the dying and unconfirmed
 lists

This patch adds a new operation to dump the content of the dying and
unconfirmed lists.

Under some situations, the global conntrack counter can be inconsistent
with the number of entries that we can dump from the conntrack table.
The way to resolve this is to allow dumping the content of the unconfirmed
and dying lists, so far it was not possible to look at its content.

This provides some extra instrumentation to resolve problematic situations
in which anyone suspects memory leaks.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nfnetlink_conntrack.h |   2 +
 net/netfilter/nf_conntrack_netlink.c               | 108 +++++++++++++++++++++
 2 files changed, 110 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
index 43bfe3e1685b..86e930cf3dfb 100644
--- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
@@ -9,6 +9,8 @@ enum cntl_msg_types {
 	IPCTNL_MSG_CT_GET_CTRZERO,
 	IPCTNL_MSG_CT_GET_STATS_CPU,
 	IPCTNL_MSG_CT_GET_STATS,
+	IPCTNL_MSG_CT_GET_DYING,
+	IPCTNL_MSG_CT_GET_UNCONFIRMED,
 
 	IPCTNL_MSG_MAX
 };
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 34370a928360..c24a00a73c7b 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1089,6 +1089,112 @@ out:
 	return err == -EAGAIN ? -ENOBUFS : err;
 }
 
+static int ctnetlink_done_list(struct netlink_callback *cb)
+{
+	if (cb->args[1])
+		nf_ct_put((struct nf_conn *)cb->args[1]);
+	return 0;
+}
+
+static int
+ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb,
+		    struct hlist_nulls_head *list)
+{
+	struct nf_conn *ct, *last;
+	struct nf_conntrack_tuple_hash *h;
+	struct hlist_nulls_node *n;
+	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	u_int8_t l3proto = nfmsg->nfgen_family;
+	int res;
+
+	if (cb->args[2])
+		return 0;
+
+	spin_lock_bh(&nf_conntrack_lock);
+	last = (struct nf_conn *)cb->args[1];
+restart:
+	hlist_nulls_for_each_entry(h, n, list, hnnode) {
+		ct = nf_ct_tuplehash_to_ctrack(h);
+		if (l3proto && nf_ct_l3num(ct) != l3proto)
+			continue;
+		if (cb->args[1]) {
+			if (ct != last)
+				continue;
+			cb->args[1] = 0;
+		}
+		rcu_read_lock();
+		res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
+					  cb->nlh->nlmsg_seq,
+					  NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
+					  ct);
+		rcu_read_unlock();
+		if (res < 0) {
+			nf_conntrack_get(&ct->ct_general);
+			cb->args[1] = (unsigned long)ct;
+			goto out;
+		}
+	}
+	if (cb->args[1]) {
+		cb->args[1] = 0;
+		goto restart;
+	} else
+		cb->args[2] = 1;
+out:
+	spin_unlock_bh(&nf_conntrack_lock);
+	if (last)
+		nf_ct_put(last);
+
+	return skb->len;
+}
+
+static int
+ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+
+	return ctnetlink_dump_list(skb, cb, &net->ct.dying);
+}
+
+static int
+ctnetlink_get_ct_dying(struct sock *ctnl, struct sk_buff *skb,
+		       const struct nlmsghdr *nlh,
+		       const struct nlattr * const cda[])
+{
+	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = ctnetlink_dump_dying,
+			.done = ctnetlink_done_list,
+		};
+		return netlink_dump_start(ctnl, skb, nlh, &c);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int
+ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+
+	return ctnetlink_dump_list(skb, cb, &net->ct.unconfirmed);
+}
+
+static int
+ctnetlink_get_ct_unconfirmed(struct sock *ctnl, struct sk_buff *skb,
+			     const struct nlmsghdr *nlh,
+			     const struct nlattr * const cda[])
+{
+	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = ctnetlink_dump_unconfirmed,
+			.done = ctnetlink_done_list,
+		};
+		return netlink_dump_start(ctnl, skb, nlh, &c);
+	}
+
+	return -EOPNOTSUPP;
+}
+
 #ifdef CONFIG_NF_NAT_NEEDED
 static int
 ctnetlink_parse_nat_setup(struct nf_conn *ct,
@@ -2712,6 +2818,8 @@ static const struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = {
 					    .policy = ct_nla_policy },
 	[IPCTNL_MSG_CT_GET_STATS_CPU]	= { .call = ctnetlink_stat_ct_cpu },
 	[IPCTNL_MSG_CT_GET_STATS]	= { .call = ctnetlink_stat_ct },
+	[IPCTNL_MSG_CT_GET_DYING]	= { .call = ctnetlink_get_ct_dying },
+	[IPCTNL_MSG_CT_GET_UNCONFIRMED]	= { .call = ctnetlink_get_ct_unconfirmed },
 };
 
 static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = {
-- 
cgit v1.2.3-55-g7522


From 0360ae412d09bc6f4864c801effcb20bfd84520e Mon Sep 17 00:00:00 2001
From: Florian Westphal
Date: Fri, 23 Nov 2012 06:22:21 +0000
Subject: netfilter: kill support for per-af queue backends

We used to have several queueing backends, but nowadays only
nfnetlink_queue remains.

In light of this there doesn't seem to be a good reason to
support per-af registering -- just hook up nfnetlink_queue on module
load and remove it on unload.

This means that the userspace BIND/UNBIND_PF commands are now obsolete;
the kernel will ignore them.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_queue.h     |   8 +-
 net/netfilter/core.c                 |   2 -
 net/netfilter/nf_queue.c             | 152 +++--------------------------------
 net/netfilter/nfnetlink_queue_core.c |  14 ++--
 4 files changed, 20 insertions(+), 156 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index 252fd1010b77..fb1c0be38b6d 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -21,14 +21,10 @@ struct nf_queue_entry {
 struct nf_queue_handler {
 	int			(*outfn)(struct nf_queue_entry *entry,
 					 unsigned int queuenum);
-	char			*name;
 };
 
-extern int nf_register_queue_handler(u_int8_t pf,
-				     const struct nf_queue_handler *qh);
-extern int nf_unregister_queue_handler(u_int8_t pf,
-				       const struct nf_queue_handler *qh);
-extern void nf_unregister_queue_handlers(const struct nf_queue_handler *qh);
+void nf_register_queue_handler(const struct nf_queue_handler *qh);
+void nf_unregister_queue_handler(void);
 extern void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict);
 
 #endif /* _NF_QUEUE_H */
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 68912dadf13d..a9c488b6c50d 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -295,8 +295,6 @@ void __init netfilter_init(void)
 		panic("cannot create netfilter proc entry");
 #endif
 
-	if (netfilter_queue_init() < 0)
-		panic("cannot initialize nf_queue");
 	if (netfilter_log_init() < 0)
 		panic("cannot initialize nf_log");
 }
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 8d2cf9ec37a8..d812c1235b30 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -14,84 +14,32 @@
 #include "nf_internals.h"
 
 /*
- * A queue handler may be registered for each protocol.  Each is protected by
- * long term mutex.  The handler must provide an an outfn() to accept packets
- * for queueing and must reinject all packets it receives, no matter what.
+ * Hook for nfnetlink_queue to register its queue handler.
+ * We do this so that most of the NFQUEUE code can be modular.
+ *
+ * Once the queue is registered it must reinject all packets it
+ * receives, no matter what.
  */
-static const struct nf_queue_handler __rcu *queue_handler[NFPROTO_NUMPROTO] __read_mostly;
-
-static DEFINE_MUTEX(queue_handler_mutex);
+static const struct nf_queue_handler __rcu *queue_handler __read_mostly;
 
 /* return EBUSY when somebody else is registered, return EEXIST if the
  * same handler is registered, return 0 in case of success. */
-int nf_register_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh)
+void nf_register_queue_handler(const struct nf_queue_handler *qh)
 {
-	int ret;
-	const struct nf_queue_handler *old;
-
-	if (pf >= ARRAY_SIZE(queue_handler))
-		return -EINVAL;
-
-	mutex_lock(&queue_handler_mutex);
-	old = rcu_dereference_protected(queue_handler[pf],
-					lockdep_is_held(&queue_handler_mutex));
-	if (old == qh)
-		ret = -EEXIST;
-	else if (old)
-		ret = -EBUSY;
-	else {
-		rcu_assign_pointer(queue_handler[pf], qh);
-		ret = 0;
-	}
-	mutex_unlock(&queue_handler_mutex);
-
-	return ret;
+	/* should never happen, we only have one queueing backend in kernel */
+	WARN_ON(rcu_access_pointer(queue_handler));
+	rcu_assign_pointer(queue_handler, qh);
 }
 EXPORT_SYMBOL(nf_register_queue_handler);
 
 /* The caller must flush their queue before this */
-int nf_unregister_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh)
+void nf_unregister_queue_handler(void)
 {
-	const struct nf_queue_handler *old;
-
-	if (pf >= ARRAY_SIZE(queue_handler))
-		return -EINVAL;
-
-	mutex_lock(&queue_handler_mutex);
-	old = rcu_dereference_protected(queue_handler[pf],
-					lockdep_is_held(&queue_handler_mutex));
-	if (old && old != qh) {
-		mutex_unlock(&queue_handler_mutex);
-		return -EINVAL;
-	}
-
-	RCU_INIT_POINTER(queue_handler[pf], NULL);
-	mutex_unlock(&queue_handler_mutex);
-
+	RCU_INIT_POINTER(queue_handler, NULL);
 	synchronize_rcu();
-
-	return 0;
 }
 EXPORT_SYMBOL(nf_unregister_queue_handler);
 
-void nf_unregister_queue_handlers(const struct nf_queue_handler *qh)
-{
-	u_int8_t pf;
-
-	mutex_lock(&queue_handler_mutex);
-	for (pf = 0; pf < ARRAY_SIZE(queue_handler); pf++)  {
-		if (rcu_dereference_protected(
-				queue_handler[pf],
-				lockdep_is_held(&queue_handler_mutex)
-				) == qh)
-			RCU_INIT_POINTER(queue_handler[pf], NULL);
-	}
-	mutex_unlock(&queue_handler_mutex);
-
-	synchronize_rcu();
-}
-EXPORT_SYMBOL_GPL(nf_unregister_queue_handlers);
-
 static void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
 {
 	/* Release those devices we held, or Alexey will kill me. */
@@ -137,7 +85,7 @@ static int __nf_queue(struct sk_buff *skb,
 	/* QUEUE == DROP if no one is waiting, to be safe. */
 	rcu_read_lock();
 
-	qh = rcu_dereference(queue_handler[pf]);
+	qh = rcu_dereference(queue_handler);
 	if (!qh) {
 		status = -ESRCH;
 		goto err_unlock;
@@ -344,77 +292,3 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	kfree(entry);
 }
 EXPORT_SYMBOL(nf_reinject);
-
-#ifdef CONFIG_PROC_FS
-static void *seq_start(struct seq_file *seq, loff_t *pos)
-{
-	if (*pos >= ARRAY_SIZE(queue_handler))
-		return NULL;
-
-	return pos;
-}
-
-static void *seq_next(struct seq_file *s, void *v, loff_t *pos)
-{
-	(*pos)++;
-
-	if (*pos >= ARRAY_SIZE(queue_handler))
-		return NULL;
-
-	return pos;
-}
-
-static void seq_stop(struct seq_file *s, void *v)
-{
-
-}
-
-static int seq_show(struct seq_file *s, void *v)
-{
-	int ret;
-	loff_t *pos = v;
-	const struct nf_queue_handler *qh;
-
-	rcu_read_lock();
-	qh = rcu_dereference(queue_handler[*pos]);
-	if (!qh)
-		ret = seq_printf(s, "%2lld NONE\n", *pos);
-	else
-		ret = seq_printf(s, "%2lld %s\n", *pos, qh->name);
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static const struct seq_operations nfqueue_seq_ops = {
-	.start	= seq_start,
-	.next	= seq_next,
-	.stop	= seq_stop,
-	.show	= seq_show,
-};
-
-static int nfqueue_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &nfqueue_seq_ops);
-}
-
-static const struct file_operations nfqueue_file_ops = {
-	.owner	 = THIS_MODULE,
-	.open	 = nfqueue_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-#endif /* PROC_FS */
-
-
-int __init netfilter_queue_init(void)
-{
-#ifdef CONFIG_PROC_FS
-	if (!proc_create("nf_queue", S_IRUGO,
-			 proc_net_netfilter, &nfqueue_file_ops))
-		return -1;
-#endif
-	return 0;
-}
-
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index e12d44e75b21..3158d87b56a8 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -809,7 +809,6 @@ static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
 };
 
 static const struct nf_queue_handler nfqh = {
-	.name 	= "nf_queue",
 	.outfn	= &nfqnl_enqueue_packet,
 };
 
@@ -827,14 +826,10 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb,
 	if (nfqa[NFQA_CFG_CMD]) {
 		cmd = nla_data(nfqa[NFQA_CFG_CMD]);
 
-		/* Commands without queue context - might sleep */
+		/* Obsolete commands without queue context */
 		switch (cmd->command) {
-		case NFQNL_CFG_CMD_PF_BIND:
-			return nf_register_queue_handler(ntohs(cmd->pf),
-							 &nfqh);
-		case NFQNL_CFG_CMD_PF_UNBIND:
-			return nf_unregister_queue_handler(ntohs(cmd->pf),
-							   &nfqh);
+		case NFQNL_CFG_CMD_PF_BIND: return 0;
+		case NFQNL_CFG_CMD_PF_UNBIND: return 0;
 		}
 	}
 
@@ -1074,6 +1069,7 @@ static int __init nfnetlink_queue_init(void)
 #endif
 
 	register_netdevice_notifier(&nfqnl_dev_notifier);
+	nf_register_queue_handler(&nfqh);
 	return status;
 
 #ifdef CONFIG_PROC_FS
@@ -1087,7 +1083,7 @@ cleanup_netlink_notifier:
 
 static void __exit nfnetlink_queue_fini(void)
 {
-	nf_unregister_queue_handlers(&nfqh);
+	nf_unregister_queue_handler();
 	unregister_netdevice_notifier(&nfqnl_dev_notifier);
 #ifdef CONFIG_PROC_FS
 	remove_proc_entry("nfnetlink_queue", proc_net_netfilter);
-- 
cgit v1.2.3-55-g7522


From a0ecb85a2c3af73c63b6d44ce82aea52347ccf55 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik
Date: Fri, 30 Nov 2012 12:37:26 +0000
Subject: netfilter: nf_nat: Handle routing changes in MASQUERADE target

When the route changes (backup default route, VPNs) which affect a
masqueraded target, the packets were sent out with the outdated source
address. The patch addresses the issue by comparing the outgoing interface
directly with the masqueraded interface in the nat table.

Events are inefficient in this case, because it'd require adding route
events to the network core and then scanning the whole conntrack table
and re-checking the route for all entry.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat.h    | 15 +++++++++++++++
 net/ipv4/netfilter/iptable_nat.c  |  4 ++++
 net/ipv6/netfilter/ip6table_nat.c |  4 ++++
 3 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index bd8eea720f2e..ad14a799fd2e 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -68,4 +68,19 @@ static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct)
 #endif
 }
 
+static inline bool nf_nat_oif_changed(unsigned int hooknum,
+				      enum ip_conntrack_info ctinfo,
+				      struct nf_conn_nat *nat,
+				      const struct net_device *out)
+{
+#if IS_ENABLED(CONFIG_IP_NF_TARGET_MASQUERADE) || \
+    IS_ENABLED(CONFIG_IP6_NF_TARGET_MASQUERADE)
+	return nat->masq_index && hooknum == NF_INET_POST_ROUTING &&
+	       CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL &&
+	       nat->masq_index != out->ifindex;
+#else
+	return false;
+#endif
+}
+
 #endif
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index ac635a7b4416..da2c8a368f68 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -134,6 +134,10 @@ nf_nat_ipv4_fn(unsigned int hooknum,
 		/* ESTABLISHED */
 		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
 			     ctinfo == IP_CT_ESTABLISHED_REPLY);
+		if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) {
+			nf_ct_kill_acct(ct, ctinfo, skb);
+			return NF_DROP;
+		}
 	}
 
 	return nf_nat_packet(ct, ctinfo, hooknum, skb);
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index fa84cf8ec6bc..6c8ae24b85eb 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -137,6 +137,10 @@ nf_nat_ipv6_fn(unsigned int hooknum,
 		/* ESTABLISHED */
 		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
 			     ctinfo == IP_CT_ESTABLISHED_REPLY);
+		if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) {
+			nf_ct_kill_acct(ct, ctinfo, skb);
+			return NF_DROP;
+		}
 	}
 
 	return nf_nat_packet(ct, ctinfo, hooknum, skb);
-- 
cgit v1.2.3-55-g7522


From 64b37b2a63eb2f80b65c7185f0013f8ffc637ae3 Mon Sep 17 00:00:00 2001
From: Matthieu CASTET
Date: Tue, 6 Nov 2012 11:51:44 +0100
Subject: mtd: nand: add NAND_BUSWIDTH_AUTO to autodetect bus width

The driver call nand_scan_ident in 8 bit mode, then
readid or onfi detection are done (and detect bus width).
The driver should update its bus width before calling nand_scan_tail.

This work because readid and onfi are read work 8 byte mode.

Note that nand_scan_ident send command (NAND_CMD_RESET, NAND_CMD_READID, NAND_CMD_PARAM), address and read data
The ONFI specificication is not very clear for x16 device if high byte of address should be driven to 0,
but according to [1] it should be ok to not drive it during autodetection.

[1]
3.3.2. Target Initialization

[...]
The Read ID and Read Parameter Page commands only use the lower 8-bits of the data bus.
The host shall not issue commands that use a word data width on x16 devices until the host
determines the device supports a 16-bit data bus width in the parameter page.

Signed-off-by: Matthieu CASTET <matthieu.castet@parrot.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 drivers/mtd/nand/nand_base.c | 14 +++++++++-----
 include/linux/mtd/nand.h     |  7 +++++++
 2 files changed, 16 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 6f58e1633e2f..5851c51ac2df 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3250,11 +3250,15 @@ ident_done:
 			break;
 	}
 
-	/*
-	 * Check, if buswidth is correct. Hardware drivers should set
-	 * chip correct!
-	 */
-	if (busw != (chip->options & NAND_BUSWIDTH_16)) {
+	if (chip->options & NAND_BUSWIDTH_AUTO) {
+		WARN_ON(chip->options & NAND_BUSWIDTH_16);
+		chip->options |= busw;
+		nand_set_defaults(chip, busw);
+	} else if (busw != (chip->options & NAND_BUSWIDTH_16)) {
+		/*
+		 * Check, if buswidth is correct. Hardware drivers should set
+		 * chip correct!
+		 */
 		pr_info("NAND device: Manufacturer ID:"
 			" 0x%02x, Chip ID: 0x%02x (%s %s)\n", *maf_id,
 			*dev_id, nand_manuf_ids[maf_idx].name, mtd->name);
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 9d8a6048aacd..7ccb3c59ed60 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -219,6 +219,13 @@ typedef enum {
 #define NAND_OWN_BUFFERS	0x00020000
 /* Chip may not exist, so silence any errors in scan */
 #define NAND_SCAN_SILENT_NODEV	0x00040000
+/*
+ * Autodetect nand buswidth with readid/onfi.
+ * This suppose the driver will configure the hardware in 8 bits mode
+ * when calling nand_scan_ident, and update its configuration
+ * before calling nand_scan_tail.
+ */
+#define NAND_BUSWIDTH_AUTO      0x00080000
 
 /* Options set by nand scan */
 /* Nand scan has allocated controller struct */
-- 
cgit v1.2.3-55-g7522


From 72b15b6ae97796c5fac687addde5dbfab872cf94 Mon Sep 17 00:00:00 2001
From: Omar Ramirez Luna
Date: Mon, 19 Nov 2012 19:05:50 -0600
Subject: iommu/omap: Migrate to hwmod framework

Use hwmod data and device attributes to build and register an
omap device for iommu driver.

 - Update the naming convention in isp module.
 - Remove unneeded check for number of resources, as this is now
   handled by omap_device and prevents driver from loading.
 - Now unused, remove platform device and resource data, handling
   of sysconfig register for softreset purposes, use default
   latency structure.
 - Use hwmod API for reset handling.

Signed-off-by: Omar Ramirez Luna <omar.luna@linaro.org>
Tested-by: Ohad Ben-Cohen <ohad@wizery.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 arch/arm/mach-omap2/devices.c            |   2 +-
 arch/arm/mach-omap2/omap-iommu.c         | 168 +++++++------------------------
 drivers/iommu/omap-iommu.c               |  23 ++++-
 drivers/iommu/omap-iommu2.c              |  19 ----
 include/linux/platform_data/iommu-omap.h |   8 +-
 5 files changed, 64 insertions(+), 156 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index c15f5a97b51c..787a996ec4eb 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -214,7 +214,7 @@ static struct platform_device omap3isp_device = {
 };
 
 static struct omap_iommu_arch_data omap3_isp_iommu = {
-	.name = "isp",
+	.name = "mmu_isp",
 };
 
 int omap3_init_camera(struct isp_platform_data *pdata)
diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c
index a6a4ff8744b7..02726a647b1d 100644
--- a/arch/arm/mach-omap2/omap-iommu.c
+++ b/arch/arm/mach-omap2/omap-iommu.c
@@ -12,153 +12,61 @@
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/err.h>
+#include <linux/slab.h>
 
 #include <linux/platform_data/iommu-omap.h>
+#include <plat/omap_hwmod.h>
+#include <plat/omap_device.h>
 
-#include "soc.h"
-#include "common.h"
-
-struct iommu_device {
-	resource_size_t base;
-	int irq;
-	struct iommu_platform_data pdata;
-	struct resource res[2];
-};
-static struct iommu_device *devices;
-static int num_iommu_devices;
-
-#ifdef CONFIG_ARCH_OMAP3
-static struct iommu_device omap3_devices[] = {
-	{
-		.base = 0x480bd400,
-		.irq = 24 + OMAP_INTC_START,
-		.pdata = {
-			.name = "isp",
-			.nr_tlb_entries = 8,
-			.clk_name = "cam_ick",
-			.da_start = 0x0,
-			.da_end = 0xFFFFF000,
-		},
-	},
-#if defined(CONFIG_OMAP_IOMMU_IVA2)
-	{
-		.base = 0x5d000000,
-		.irq = 28 + OMAP_INTC_START,
-		.pdata = {
-			.name = "iva2",
-			.nr_tlb_entries = 32,
-			.clk_name = "iva2_ck",
-			.da_start = 0x11000000,
-			.da_end = 0xFFFFF000,
-		},
-	},
-#endif
-};
-#define NR_OMAP3_IOMMU_DEVICES ARRAY_SIZE(omap3_devices)
-static struct platform_device *omap3_iommu_pdev[NR_OMAP3_IOMMU_DEVICES];
-#else
-#define omap3_devices		NULL
-#define NR_OMAP3_IOMMU_DEVICES	0
-#define omap3_iommu_pdev	NULL
-#endif
-
-#ifdef CONFIG_ARCH_OMAP4
-static struct iommu_device omap4_devices[] = {
-	{
-		.base = OMAP4_MMU1_BASE,
-		.irq = 100 + OMAP44XX_IRQ_GIC_START,
-		.pdata = {
-			.name = "ducati",
-			.nr_tlb_entries = 32,
-			.clk_name = "ipu_fck",
-			.da_start = 0x0,
-			.da_end = 0xFFFFF000,
-		},
-	},
-	{
-		.base = OMAP4_MMU2_BASE,
-		.irq = 28 + OMAP44XX_IRQ_GIC_START,
-		.pdata = {
-			.name = "tesla",
-			.nr_tlb_entries = 32,
-			.clk_name = "dsp_fck",
-			.da_start = 0x0,
-			.da_end = 0xFFFFF000,
-		},
-	},
-};
-#define NR_OMAP4_IOMMU_DEVICES ARRAY_SIZE(omap4_devices)
-static struct platform_device *omap4_iommu_pdev[NR_OMAP4_IOMMU_DEVICES];
-#else
-#define omap4_devices		NULL
-#define NR_OMAP4_IOMMU_DEVICES	0
-#define omap4_iommu_pdev	NULL
-#endif
-
-static struct platform_device **omap_iommu_pdev;
-
-static int __init omap_iommu_init(void)
+static int __init omap_iommu_dev_init(struct omap_hwmod *oh, void *unused)
 {
-	int i, err;
-	struct resource res[] = {
-		{ .flags = IORESOURCE_MEM },
-		{ .flags = IORESOURCE_IRQ },
-	};
+	struct platform_device *pdev;
+	struct iommu_platform_data *pdata;
+	struct omap_mmu_dev_attr *a = (struct omap_mmu_dev_attr *)oh->dev_attr;
+	static int i;
+
+	pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
+
+	pdata->name = oh->name;
+	pdata->clk_name = oh->main_clk;
+	pdata->nr_tlb_entries = a->nr_tlb_entries;
+	pdata->da_start = a->da_start;
+	pdata->da_end = a->da_end;
+
+	if (oh->rst_lines_cnt == 1) {
+		pdata->reset_name = oh->rst_lines->name;
+		pdata->assert_reset = omap_device_assert_hardreset;
+		pdata->deassert_reset = omap_device_deassert_hardreset;
+	}
 
-	if (cpu_is_omap34xx()) {
-		devices = omap3_devices;
-		omap_iommu_pdev = omap3_iommu_pdev;
-		num_iommu_devices = NR_OMAP3_IOMMU_DEVICES;
-	} else if (cpu_is_omap44xx()) {
-		devices = omap4_devices;
-		omap_iommu_pdev = omap4_iommu_pdev;
-		num_iommu_devices = NR_OMAP4_IOMMU_DEVICES;
-	} else
-		return -ENODEV;
+	pdev = omap_device_build("omap-iommu", i, oh, pdata, sizeof(*pdata),
+				NULL, 0, 0);
 
-	for (i = 0; i < num_iommu_devices; i++) {
-		struct platform_device *pdev;
-		const struct iommu_device *d = &devices[i];
+	kfree(pdata);
 
-		pdev = platform_device_alloc("omap-iommu", i);
-		if (!pdev) {
-			err = -ENOMEM;
-			goto err_out;
-		}
+	if (IS_ERR(pdev)) {
+		pr_err("%s: device build err: %ld\n", __func__, PTR_ERR(pdev));
+		return PTR_ERR(pdev);
+	}
 
-		res[0].start = d->base;
-		res[0].end = d->base + MMU_REG_SIZE - 1;
-		res[1].start = res[1].end = d->irq;
+	i++;
 
-		err = platform_device_add_resources(pdev, res,
-						    ARRAY_SIZE(res));
-		if (err)
-			goto err_out;
-		err = platform_device_add_data(pdev, &d->pdata,
-					       sizeof(d->pdata));
-		if (err)
-			goto err_out;
-		err = platform_device_add(pdev);
-		if (err)
-			goto err_out;
-		omap_iommu_pdev[i] = pdev;
-	}
 	return 0;
+}
 
-err_out:
-	while (i--)
-		platform_device_put(omap_iommu_pdev[i]);
-	return err;
+static int __init omap_iommu_init(void)
+{
+	return omap_hwmod_for_each_by_class("mmu", omap_iommu_dev_init, NULL);
 }
 /* must be ready before omap3isp is probed */
 subsys_initcall(omap_iommu_init);
 
 static void __exit omap_iommu_exit(void)
 {
-	int i;
-
-	for (i = 0; i < num_iommu_devices; i++)
-		platform_device_unregister(omap_iommu_pdev[i]);
+	/* Do nothing */
 }
 module_exit(omap_iommu_exit);
 
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index f8082da6179b..af9b4f31f594 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -143,13 +143,23 @@ EXPORT_SYMBOL_GPL(omap_iommu_arch_version);
 static int iommu_enable(struct omap_iommu *obj)
 {
 	int err;
+	struct platform_device *pdev = to_platform_device(obj->dev);
+	struct iommu_platform_data *pdata = pdev->dev.platform_data;
 
-	if (!obj)
+	if (!obj || !pdata)
 		return -EINVAL;
 
 	if (!arch_iommu)
 		return -ENODEV;
 
+	if (pdata->deassert_reset) {
+		err = pdata->deassert_reset(pdev, pdata->reset_name);
+		if (err) {
+			dev_err(obj->dev, "deassert_reset failed: %d\n", err);
+			return err;
+		}
+	}
+
 	clk_enable(obj->clk);
 
 	err = arch_iommu->enable(obj);
@@ -159,12 +169,18 @@ static int iommu_enable(struct omap_iommu *obj)
 
 static void iommu_disable(struct omap_iommu *obj)
 {
-	if (!obj)
+	struct platform_device *pdev = to_platform_device(obj->dev);
+	struct iommu_platform_data *pdata = pdev->dev.platform_data;
+
+	if (!obj || !pdata)
 		return;
 
 	arch_iommu->disable(obj);
 
 	clk_disable(obj->clk);
+
+	if (pdata->assert_reset)
+		pdata->assert_reset(pdev, pdata->reset_name);
 }
 
 /*
@@ -926,9 +942,6 @@ static int __devinit omap_iommu_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct iommu_platform_data *pdata = pdev->dev.platform_data;
 
-	if (pdev->num_resources != 2)
-		return -EINVAL;
-
 	obj = kzalloc(sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL);
 	if (!obj)
 		return -ENOMEM;
diff --git a/drivers/iommu/omap-iommu2.c b/drivers/iommu/omap-iommu2.c
index c02020292377..4a3a1c7a38c1 100644
--- a/drivers/iommu/omap-iommu2.c
+++ b/drivers/iommu/omap-iommu2.c
@@ -35,12 +35,8 @@
 #define MMU_SYS_IDLE_SMART	(2 << MMU_SYS_IDLE_SHIFT)
 #define MMU_SYS_IDLE_MASK	(3 << MMU_SYS_IDLE_SHIFT)
 
-#define MMU_SYS_SOFTRESET	(1 << 1)
 #define MMU_SYS_AUTOIDLE	1
 
-/* SYSSTATUS */
-#define MMU_SYS_RESETDONE	1
-
 /* IRQSTATUS & IRQENABLE */
 #define MMU_IRQ_MULTIHITFAULT	(1 << 4)
 #define MMU_IRQ_TABLEWALKFAULT	(1 << 3)
@@ -97,7 +93,6 @@ static void __iommu_set_twl(struct omap_iommu *obj, bool on)
 static int omap2_iommu_enable(struct omap_iommu *obj)
 {
 	u32 l, pa;
-	unsigned long timeout;
 
 	if (!obj->iopgd || !IS_ALIGNED((u32)obj->iopgd,  SZ_16K))
 		return -EINVAL;
@@ -106,20 +101,6 @@ static int omap2_iommu_enable(struct omap_iommu *obj)
 	if (!IS_ALIGNED(pa, SZ_16K))
 		return -EINVAL;
 
-	iommu_write_reg(obj, MMU_SYS_SOFTRESET, MMU_SYSCONFIG);
-
-	timeout = jiffies + msecs_to_jiffies(20);
-	do {
-		l = iommu_read_reg(obj, MMU_SYSSTATUS);
-		if (l & MMU_SYS_RESETDONE)
-			break;
-	} while (!time_after(jiffies, timeout));
-
-	if (!(l & MMU_SYS_RESETDONE)) {
-		dev_err(obj->dev, "can't take mmu out of reset\n");
-		return -ENODEV;
-	}
-
 	l = iommu_read_reg(obj, MMU_REVISION);
 	dev_info(obj->dev, "%s: version %d.%d\n", obj->name,
 		 (l >> 4) & 0xf, l & 0xf);
diff --git a/include/linux/platform_data/iommu-omap.h b/include/linux/platform_data/iommu-omap.h
index c677b9f2fefa..ef2060d7eeb8 100644
--- a/include/linux/platform_data/iommu-omap.h
+++ b/include/linux/platform_data/iommu-omap.h
@@ -10,6 +10,8 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/platform_device.h>
+
 #define MMU_REG_SIZE		256
 
 /**
@@ -43,7 +45,11 @@ struct omap_mmu_dev_attr {
 struct iommu_platform_data {
 	const char *name;
 	const char *clk_name;
-	const int nr_tlb_entries;
+	const char *reset_name;
+	int nr_tlb_entries;
 	u32 da_start;
 	u32 da_end;
+
+	int (*assert_reset)(struct platform_device *pdev, const char *name);
+	int (*deassert_reset)(struct platform_device *pdev, const char *name);
 };
-- 
cgit v1.2.3-55-g7522


From ebf7cda0f92effd8169b831fae81e9437dce1fef Mon Sep 17 00:00:00 2001
From: Omar Ramirez Luna
Date: Mon, 19 Nov 2012 19:05:51 -0600
Subject: iommu/omap: Adapt to runtime pm

Use runtime PM functionality interfaced with hwmod enable/idle
functions, to replace direct clock operations and sysconfig
handling.

Due to reset sequence, pm_runtime_[get|put]_sync must be used, to
avoid possible operations with the module under reset. Because of
this and given that the driver uses spin_locks to protect their
critical sections, we must use pm_runtime_irq_safe in order for the
runtime ops to be happy, otherwise might_sleep_if checks in runtime
framework will complain.

The remaining pm_runtime out of iommu_enable and iommu_disable
corresponds to paths that can be accessed through debugfs, some of
them doesn't work if the module is not enabled first, but in future
if the mmu is idled withouth freeing, these are needed to debug.

Signed-off-by: Omar Ramirez Luna <omar.luna@linaro.org>
Tested-by: Ohad Ben-Cohen <ohad@wizery.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 arch/arm/mach-omap2/omap-iommu.c         |  1 -
 drivers/iommu/omap-iommu.c               | 40 +++++++++++++++-----------------
 drivers/iommu/omap-iommu.h               |  3 ---
 drivers/iommu/omap-iommu2.c              | 17 --------------
 include/linux/platform_data/iommu-omap.h |  1 -
 5 files changed, 19 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c
index 02726a647b1d..7642fc4672c1 100644
--- a/arch/arm/mach-omap2/omap-iommu.c
+++ b/arch/arm/mach-omap2/omap-iommu.c
@@ -31,7 +31,6 @@ static int __init omap_iommu_dev_init(struct omap_hwmod *oh, void *unused)
 		return -ENOMEM;
 
 	pdata->name = oh->name;
-	pdata->clk_name = oh->main_clk;
 	pdata->nr_tlb_entries = a->nr_tlb_entries;
 	pdata->da_start = a->da_start;
 	pdata->da_end = a->da_end;
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index af9b4f31f594..18108c1405e2 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -16,13 +16,13 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
-#include <linux/clk.h>
 #include <linux/platform_device.h>
 #include <linux/iommu.h>
 #include <linux/omap-iommu.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/io.h>
+#include <linux/pm_runtime.h>
 
 #include <asm/cacheflush.h>
 
@@ -160,7 +160,7 @@ static int iommu_enable(struct omap_iommu *obj)
 		}
 	}
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 
 	err = arch_iommu->enable(obj);
 
@@ -177,7 +177,7 @@ static void iommu_disable(struct omap_iommu *obj)
 
 	arch_iommu->disable(obj);
 
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 
 	if (pdata->assert_reset)
 		pdata->assert_reset(pdev, pdata->reset_name);
@@ -303,7 +303,7 @@ static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
 	if (!obj || !obj->nr_tlb_entries || !e)
 		return -EINVAL;
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 
 	iotlb_lock_get(obj, &l);
 	if (l.base == obj->nr_tlb_entries) {
@@ -333,7 +333,7 @@ static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
 
 	cr = iotlb_alloc_cr(obj, e);
 	if (IS_ERR(cr)) {
-		clk_disable(obj->clk);
+		pm_runtime_put_sync(obj->dev);
 		return PTR_ERR(cr);
 	}
 
@@ -347,7 +347,7 @@ static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
 		l.vict = l.base;
 	iotlb_lock_set(obj, &l);
 out:
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 	return err;
 }
 
@@ -377,7 +377,7 @@ static void flush_iotlb_page(struct omap_iommu *obj, u32 da)
 	int i;
 	struct cr_regs cr;
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 
 	for_each_iotlb_cr(obj, obj->nr_tlb_entries, i, cr) {
 		u32 start;
@@ -396,7 +396,7 @@ static void flush_iotlb_page(struct omap_iommu *obj, u32 da)
 			iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY);
 		}
 	}
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 
 	if (i == obj->nr_tlb_entries)
 		dev_dbg(obj->dev, "%s: no page for %08x\n", __func__, da);
@@ -410,7 +410,7 @@ static void flush_iotlb_all(struct omap_iommu *obj)
 {
 	struct iotlb_lock l;
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 
 	l.base = 0;
 	l.vict = 0;
@@ -418,7 +418,7 @@ static void flush_iotlb_all(struct omap_iommu *obj)
 
 	iommu_write_reg(obj, 1, MMU_GFLUSH);
 
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 }
 
 #if defined(CONFIG_OMAP_IOMMU_DEBUG) || defined(CONFIG_OMAP_IOMMU_DEBUG_MODULE)
@@ -428,11 +428,11 @@ ssize_t omap_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t bytes)
 	if (!obj || !buf)
 		return -EINVAL;
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 
 	bytes = arch_iommu->dump_ctx(obj, buf, bytes);
 
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 
 	return bytes;
 }
@@ -446,7 +446,7 @@ __dump_tlb_entries(struct omap_iommu *obj, struct cr_regs *crs, int num)
 	struct cr_regs tmp;
 	struct cr_regs *p = crs;
 
-	clk_enable(obj->clk);
+	pm_runtime_get_sync(obj->dev);
 	iotlb_lock_get(obj, &saved);
 
 	for_each_iotlb_cr(obj, num, i, tmp) {
@@ -456,7 +456,7 @@ __dump_tlb_entries(struct omap_iommu *obj, struct cr_regs *crs, int num)
 	}
 
 	iotlb_lock_set(obj, &saved);
-	clk_disable(obj->clk);
+	pm_runtime_put_sync(obj->dev);
 
 	return  p - crs;
 }
@@ -946,10 +946,6 @@ static int __devinit omap_iommu_probe(struct platform_device *pdev)
 	if (!obj)
 		return -ENOMEM;
 
-	obj->clk = clk_get(&pdev->dev, pdata->clk_name);
-	if (IS_ERR(obj->clk))
-		goto err_clk;
-
 	obj->nr_tlb_entries = pdata->nr_tlb_entries;
 	obj->name = pdata->name;
 	obj->dev = &pdev->dev;
@@ -992,6 +988,9 @@ static int __devinit omap_iommu_probe(struct platform_device *pdev)
 		goto err_irq;
 	platform_set_drvdata(pdev, obj);
 
+	pm_runtime_irq_safe(obj->dev);
+	pm_runtime_enable(obj->dev);
+
 	dev_info(&pdev->dev, "%s registered\n", obj->name);
 	return 0;
 
@@ -1000,8 +999,6 @@ err_irq:
 err_ioremap:
 	release_mem_region(res->start, resource_size(res));
 err_mem:
-	clk_put(obj->clk);
-err_clk:
 	kfree(obj);
 	return err;
 }
@@ -1022,7 +1019,8 @@ static int __devexit omap_iommu_remove(struct platform_device *pdev)
 	release_mem_region(res->start, resource_size(res));
 	iounmap(obj->regbase);
 
-	clk_put(obj->clk);
+	pm_runtime_disable(obj->dev);
+
 	dev_info(&pdev->dev, "%s removed\n", obj->name);
 	kfree(obj);
 	return 0;
diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h
index 2b5f3c04d167..120084206602 100644
--- a/drivers/iommu/omap-iommu.h
+++ b/drivers/iommu/omap-iommu.h
@@ -29,7 +29,6 @@ struct iotlb_entry {
 struct omap_iommu {
 	const char	*name;
 	struct module	*owner;
-	struct clk	*clk;
 	void __iomem	*regbase;
 	struct device	*dev;
 	void		*isr_priv;
@@ -116,8 +115,6 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev)
  * MMU Register offsets
  */
 #define MMU_REVISION		0x00
-#define MMU_SYSCONFIG		0x10
-#define MMU_SYSSTATUS		0x14
 #define MMU_IRQSTATUS		0x18
 #define MMU_IRQENABLE		0x1c
 #define MMU_WALKING_ST		0x40
diff --git a/drivers/iommu/omap-iommu2.c b/drivers/iommu/omap-iommu2.c
index 4a3a1c7a38c1..d745094a69dd 100644
--- a/drivers/iommu/omap-iommu2.c
+++ b/drivers/iommu/omap-iommu2.c
@@ -28,15 +28,6 @@
  */
 #define IOMMU_ARCH_VERSION	0x00000011
 
-/* SYSCONF */
-#define MMU_SYS_IDLE_SHIFT	3
-#define MMU_SYS_IDLE_FORCE	(0 << MMU_SYS_IDLE_SHIFT)
-#define MMU_SYS_IDLE_NONE	(1 << MMU_SYS_IDLE_SHIFT)
-#define MMU_SYS_IDLE_SMART	(2 << MMU_SYS_IDLE_SHIFT)
-#define MMU_SYS_IDLE_MASK	(3 << MMU_SYS_IDLE_SHIFT)
-
-#define MMU_SYS_AUTOIDLE	1
-
 /* IRQSTATUS & IRQENABLE */
 #define MMU_IRQ_MULTIHITFAULT	(1 << 4)
 #define MMU_IRQ_TABLEWALKFAULT	(1 << 3)
@@ -105,11 +96,6 @@ static int omap2_iommu_enable(struct omap_iommu *obj)
 	dev_info(obj->dev, "%s: version %d.%d\n", obj->name,
 		 (l >> 4) & 0xf, l & 0xf);
 
-	l = iommu_read_reg(obj, MMU_SYSCONFIG);
-	l &= ~MMU_SYS_IDLE_MASK;
-	l |= (MMU_SYS_IDLE_SMART | MMU_SYS_AUTOIDLE);
-	iommu_write_reg(obj, l, MMU_SYSCONFIG);
-
 	iommu_write_reg(obj, pa, MMU_TTB);
 
 	__iommu_set_twl(obj, true);
@@ -123,7 +109,6 @@ static void omap2_iommu_disable(struct omap_iommu *obj)
 
 	l &= ~MMU_CNTL_MASK;
 	iommu_write_reg(obj, l, MMU_CNTL);
-	iommu_write_reg(obj, MMU_SYS_IDLE_FORCE, MMU_SYSCONFIG);
 
 	dev_dbg(obj->dev, "%s is shutting down\n", obj->name);
 }
@@ -252,8 +237,6 @@ omap2_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t len)
 	char *p = buf;
 
 	pr_reg(REVISION);
-	pr_reg(SYSCONFIG);
-	pr_reg(SYSSTATUS);
 	pr_reg(IRQSTATUS);
 	pr_reg(IRQENABLE);
 	pr_reg(WALKING_ST);
diff --git a/include/linux/platform_data/iommu-omap.h b/include/linux/platform_data/iommu-omap.h
index ef2060d7eeb8..5b429c43a297 100644
--- a/include/linux/platform_data/iommu-omap.h
+++ b/include/linux/platform_data/iommu-omap.h
@@ -44,7 +44,6 @@ struct omap_mmu_dev_attr {
 
 struct iommu_platform_data {
 	const char *name;
-	const char *clk_name;
 	const char *reset_name;
 	int nr_tlb_entries;
 	u32 da_start;
-- 
cgit v1.2.3-55-g7522


From 20714bfef84d3e690c9c6f8e9cd46543b5ae1eed Mon Sep 17 00:00:00 2001
From: Frédéric Dalleau
Date: Wed, 21 Nov 2012 10:51:12 +0100
Subject: Bluetooth: Implement deferred sco socket setup

In order to authenticate and configure an incoming SCO connection, the
BT_DEFER_SETUP option was added. This option is intended to defer reply
to Connect Request on SCO sockets.
When a connection is requested, the listening socket is unblocked but
the effective connection setup happens only on first recv. Any send
between accept and recv fails with -ENOTCONN.

Signed-off-by: Frédéric Dalleau <frederic.dalleau@linux.intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  9 ++++---
 net/bluetooth/hci_event.c        | 52 ++++++++++++++++++++++++++++++++++++----
 net/bluetooth/sco.c              | 35 ++++++++++++++++++++++++---
 3 files changed, 86 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ef5b85dac3f7..76891a914e75 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -376,7 +376,7 @@ extern int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt);
 extern int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb,
 			      u16 flags);
 
-extern int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr);
+extern int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags);
 extern void sco_connect_cfm(struct hci_conn *hcon, __u8 status);
 extern void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason);
 extern int sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb);
@@ -577,6 +577,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst);
 int hci_conn_del(struct hci_conn *conn);
 void hci_conn_hash_flush(struct hci_dev *hdev);
 void hci_conn_check_pending(struct hci_dev *hdev);
+void hci_conn_accept(struct hci_conn *conn, int mask);
 
 struct hci_chan *hci_chan_create(struct hci_conn *conn);
 void hci_chan_del(struct hci_chan *chan);
@@ -779,8 +780,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define lmp_host_le_br_capable(dev) ((dev)->host_features[0] & LMP_HOST_LE_BREDR)
 
 /* ----- HCI protocols ----- */
+#define HCI_PROTO_DEFER             0x01
+
 static inline int hci_proto_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr,
-								__u8 type)
+					__u8 type, __u8 *flags)
 {
 	switch (type) {
 	case ACL_LINK:
@@ -788,7 +791,7 @@ static inline int hci_proto_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr,
 
 	case SCO_LINK:
 	case ESCO_LINK:
-		return sco_connect_ind(hdev, bdaddr);
+		return sco_connect_ind(hdev, bdaddr, flags);
 
 	default:
 		BT_ERR("unknown link type %d", type);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 9f5c5f244502..3843f1897c86 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2047,15 +2047,53 @@ unlock:
 	hci_conn_check_pending(hdev);
 }
 
+void hci_conn_accept(struct hci_conn *conn, int mask)
+{
+	struct hci_dev *hdev = conn->hdev;
+
+	BT_DBG("conn %p", conn);
+
+	conn->state = BT_CONFIG;
+
+	if (!lmp_esco_capable(hdev)) {
+		struct hci_cp_accept_conn_req cp;
+
+		bacpy(&cp.bdaddr, &conn->dst);
+
+		if (lmp_rswitch_capable(hdev) && (mask & HCI_LM_MASTER))
+			cp.role = 0x00; /* Become master */
+		else
+			cp.role = 0x01; /* Remain slave */
+
+		hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp);
+	} else /* lmp_esco_capable(hdev)) */ {
+		struct hci_cp_accept_sync_conn_req cp;
+
+		bacpy(&cp.bdaddr, &conn->dst);
+		cp.pkt_type = cpu_to_le16(conn->pkt_type);
+
+		cp.tx_bandwidth   = __constant_cpu_to_le32(0x00001f40);
+		cp.rx_bandwidth   = __constant_cpu_to_le32(0x00001f40);
+		cp.max_latency    = __constant_cpu_to_le16(0xffff);
+		cp.content_format = cpu_to_le16(hdev->voice_setting);
+		cp.retrans_effort = 0xff;
+
+		hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ,
+			     sizeof(cp), &cp);
+	}
+}
+
 static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_conn_request *ev = (void *) skb->data;
 	int mask = hdev->link_mode;
+	__u8 flags = 0;
 
 	BT_DBG("%s bdaddr %pMR type 0x%x", hdev->name, &ev->bdaddr,
 	       ev->link_type);
 
-	mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type);
+	mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type,
+				      &flags);
 
 	if ((mask & HCI_LM_ACCEPT) &&
 	    !hci_blacklist_lookup(hdev, &ev->bdaddr)) {
@@ -2081,12 +2119,13 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		}
 
 		memcpy(conn->dev_class, ev->dev_class, 3);
-		conn->state = BT_CONNECT;
 
 		hci_dev_unlock(hdev);
 
-		if (ev->link_type == ACL_LINK || !lmp_esco_capable(hdev)) {
+		if (ev->link_type == ACL_LINK ||
+		    (!(flags & HCI_PROTO_DEFER) && !lmp_esco_capable(hdev))) {
 			struct hci_cp_accept_conn_req cp;
+			conn->state = BT_CONNECT;
 
 			bacpy(&cp.bdaddr, &ev->bdaddr);
 
@@ -2097,8 +2136,9 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 			hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp),
 				     &cp);
-		} else {
+		} else if (!(flags & HCI_PROTO_DEFER)) {
 			struct hci_cp_accept_sync_conn_req cp;
+			conn->state = BT_CONNECT;
 
 			bacpy(&cp.bdaddr, &ev->bdaddr);
 			cp.pkt_type = cpu_to_le16(conn->pkt_type);
@@ -2111,6 +2151,10 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 			hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ,
 				     sizeof(cp), &cp);
+		} else {
+			conn->state = BT_CONNECT2;
+			hci_proto_connect_cfm(conn, 0);
+			hci_conn_put(conn);
 		}
 	} else {
 		/* Connection rejected */
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index c6678f2bffc9..eea17cdcaf7f 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -397,6 +397,7 @@ static void sco_sock_init(struct sock *sk, struct sock *parent)
 
 	if (parent) {
 		sk->sk_type = parent->sk_type;
+		bt_sk(sk)->flags = bt_sk(parent)->flags;
 		security_sk_clone(parent, sk);
 	}
 }
@@ -662,6 +663,28 @@ static int sco_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	return err;
 }
 
+static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
+			    struct msghdr *msg, size_t len, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sco_pinfo *pi = sco_pi(sk);
+
+	lock_sock(sk);
+
+	if (sk->sk_state == BT_CONNECT2 &&
+	    test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
+		hci_conn_accept(pi->conn->hcon, 0);
+		sk->sk_state = BT_CONFIG;
+
+		release_sock(sk);
+		return 0;
+	}
+
+	release_sock(sk);
+
+	return bt_sock_recvmsg(iocb, sock, msg, len, flags);
+}
+
 static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
@@ -906,7 +929,10 @@ static void sco_conn_ready(struct sco_conn *conn)
 		hci_conn_hold(conn->hcon);
 		__sco_chan_add(conn, sk, parent);
 
-		sk->sk_state = BT_CONNECTED;
+		if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags))
+			sk->sk_state = BT_CONNECT2;
+		else
+			sk->sk_state = BT_CONNECTED;
 
 		/* Wake up parent */
 		parent->sk_data_ready(parent, 1);
@@ -919,7 +945,7 @@ done:
 }
 
 /* ----- SCO interface with lower layer (HCI) ----- */
-int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr)
+int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 {
 	struct sock *sk;
 	struct hlist_node *node;
@@ -936,6 +962,9 @@ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr)
 		if (!bacmp(&bt_sk(sk)->src, &hdev->bdaddr) ||
 		    !bacmp(&bt_sk(sk)->src, BDADDR_ANY)) {
 			lm |= HCI_LM_ACCEPT;
+
+			if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))
+				*flags |= HCI_PROTO_DEFER;
 			break;
 		}
 	}
@@ -1024,7 +1053,7 @@ static const struct proto_ops sco_sock_ops = {
 	.accept		= sco_sock_accept,
 	.getname	= sco_sock_getname,
 	.sendmsg	= sco_sock_sendmsg,
-	.recvmsg	= bt_sock_recvmsg,
+	.recvmsg	= sco_sock_recvmsg,
 	.poll		= bt_sock_poll,
 	.ioctl		= bt_sock_ioctl,
 	.mmap		= sock_no_mmap,
-- 
cgit v1.2.3-55-g7522


From ffa88e02bc67a1496fae762ad899e8f49136e7a1 Mon Sep 17 00:00:00 2001
From: Gustavo Padovan
Date: Fri, 23 Nov 2012 16:50:51 -0200
Subject: Bluetooth: Move double negation to macros

Some comparisons needs to double negation(!!) in order to make the value
of the field boolean. Add it to the macro makes the code more readable.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  6 +++---
 net/bluetooth/hci_event.c        |  4 ++--
 net/bluetooth/mgmt.c             | 10 +++++-----
 3 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 76891a914e75..2f2b743f5b10 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -767,7 +767,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define lmp_sniffsubr_capable(dev) ((dev)->features[5] & LMP_SNIFF_SUBR)
 #define lmp_pause_enc_capable(dev) ((dev)->features[5] & LMP_PAUSE_ENC)
 #define lmp_ext_inq_capable(dev)   ((dev)->features[6] & LMP_EXT_INQ)
-#define lmp_le_br_capable(dev)     ((dev)->features[6] & LMP_SIMUL_LE_BR)
+#define lmp_le_br_capable(dev)     !!((dev)->features[6] & LMP_SIMUL_LE_BR)
 #define lmp_ssp_capable(dev)       ((dev)->features[6] & LMP_SIMPLE_PAIR)
 #define lmp_no_flush_capable(dev)  ((dev)->features[6] & LMP_NO_FLUSH)
 #define lmp_lsto_capable(dev)      ((dev)->features[7] & LMP_LSTO)
@@ -776,8 +776,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 
 /* ----- Extended LMP capabilities ----- */
 #define lmp_host_ssp_capable(dev)  ((dev)->host_features[0] & LMP_HOST_SSP)
-#define lmp_host_le_capable(dev)   ((dev)->host_features[0] & LMP_HOST_LE)
-#define lmp_host_le_br_capable(dev) ((dev)->host_features[0] & LMP_HOST_LE_BREDR)
+#define lmp_host_le_capable(dev)   !!((dev)->host_features[0] & LMP_HOST_LE)
+#define lmp_host_le_br_capable(dev) !!((dev)->host_features[0] & LMP_HOST_LE_BREDR)
 
 /* ----- HCI protocols ----- */
 #define HCI_PROTO_DEFER             0x01
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 3843f1897c86..705078a0cc39 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -794,10 +794,10 @@ static void hci_set_le_support(struct hci_dev *hdev)
 
 	if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) {
 		cp.le = 1;
-		cp.simul = !!lmp_le_br_capable(hdev);
+		cp.simul = lmp_le_br_capable(hdev);
 	}
 
-	if (cp.le != !!lmp_host_le_capable(hdev))
+	if (cp.le != lmp_host_le_capable(hdev))
 		hci_send_cmd(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(cp),
 			     &cp);
 }
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index dedbb1d8b2d2..5d0ef759ef49 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1225,7 +1225,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	}
 
 	val = !!cp->val;
-	enabled = !!lmp_host_le_capable(hdev);
+	enabled = lmp_host_le_capable(hdev);
 
 	if (!hdev_is_powered(hdev) || val == enabled) {
 		bool changed = false;
@@ -1261,7 +1261,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	if (val) {
 		hci_cp.le = val;
-		hci_cp.simul = !!lmp_le_br_capable(hdev);
+		hci_cp.simul = lmp_le_br_capable(hdev);
 	}
 
 	err = hci_send_cmd(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp),
@@ -2924,13 +2924,13 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered)
 			struct hci_cp_write_le_host_supported cp;
 
 			cp.le = 1;
-			cp.simul = !!lmp_le_br_capable(hdev);
+			cp.simul = lmp_le_br_capable(hdev);
 
 			/* Check first if we already have the right
 			 * host state (host features set)
 			 */
-			if (cp.le != !!lmp_host_le_capable(hdev) ||
-			    cp.simul != !!lmp_host_le_br_capable(hdev))
+			if (cp.le != lmp_host_le_capable(hdev) ||
+			    cp.simul != lmp_host_le_br_capable(hdev))
 				hci_send_cmd(hdev,
 					     HCI_OP_WRITE_LE_HOST_SUPPORTED,
 					     sizeof(cp), &cp);
-- 
cgit v1.2.3-55-g7522


From 5d05416e0907b0dd30b62b002bed3b85e6efbd61 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 29 Nov 2012 17:46:05 +0200
Subject: Bluetooth: AMP: Check that AMP is present and active

Before starting quering remote AMP controllers make sure
that there is local active AMP controller.

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 16 ++++++++++++++++
 net/bluetooth/l2cap_core.c       |  1 +
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2f2b743f5b10..014a2eaa5389 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -779,6 +779,22 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define lmp_host_le_capable(dev)   !!((dev)->host_features[0] & LMP_HOST_LE)
 #define lmp_host_le_br_capable(dev) !!((dev)->host_features[0] & LMP_HOST_LE_BREDR)
 
+/* returns true if at least one AMP active */
+static inline bool hci_amp_capable(void)
+{
+	struct hci_dev *hdev;
+	bool ret = false;
+
+	read_lock(&hci_dev_list_lock);
+	list_for_each_entry(hdev, &hci_dev_list, list)
+		if (hdev->amp_type == HCI_AMP &&
+		    test_bit(HCI_UP, &hdev->flags))
+			ret = true;
+	read_unlock(&hci_dev_list_lock);
+
+	return ret;
+}
+
 /* ----- HCI protocols ----- */
 #define HCI_PROTO_DEFER             0x01
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index f7ee037c7934..d8cffdbf0d37 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1013,6 +1013,7 @@ static bool __amp_capable(struct l2cap_chan *chan)
 	struct l2cap_conn *conn = chan->conn;
 
 	if (enable_hs &&
+	    hci_amp_capable() &&
 	    chan->chan_policy == BT_CHANNEL_POLICY_AMP_PREFERRED &&
 	    conn->fixed_chan_mask & L2CAP_FC_A2MP)
 		return true;
-- 
cgit v1.2.3-55-g7522


From f2592d3ee3c5817981f343b90bfb9c5612f38d23 Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko
Date: Thu, 29 Nov 2012 17:46:08 +0200
Subject: Bluetooth: trivial: Change NO_FCS_RECV to RECV_NO_FCS

Make code more readable by changing CONF_NO_FCS_RECV which is read
as "No L2CAP FCS option received" to CONF_RECV_NO_FCS which means
"Received L2CAP option NO_FCS". This flag really means that we have
received L2CAP FRAME CHECK SEQUENCE (FCS) OPTION with value "No FCS".

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h |  2 +-
 net/bluetooth/l2cap_core.c    | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index f57fab04e7c5..7588ef44ebaf 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -611,7 +611,7 @@ enum {
 	CONF_MTU_DONE,
 	CONF_MODE_DONE,
 	CONF_CONNECT_PEND,
-	CONF_NO_FCS_RECV,
+	CONF_RECV_NO_FCS,
 	CONF_STATE2_DEVICE,
 	CONF_EWS_RECV,
 	CONF_LOC_CONF_PEND,
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 8c432771d6f9..2c78208d793e 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -3112,7 +3112,7 @@ done:
 
 		if (chan->conn->feat_mask & L2CAP_FEAT_FCS)
 			if (chan->fcs == L2CAP_FCS_NONE ||
-			    test_bit(CONF_NO_FCS_RECV, &chan->conf_state)) {
+			    test_bit(CONF_RECV_NO_FCS, &chan->conf_state)) {
 				chan->fcs = L2CAP_FCS_NONE;
 				l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1,
 						   chan->fcs);
@@ -3140,7 +3140,7 @@ done:
 
 		if (chan->conn->feat_mask & L2CAP_FEAT_FCS)
 			if (chan->fcs == L2CAP_FCS_NONE ||
-			    test_bit(CONF_NO_FCS_RECV, &chan->conf_state)) {
+			    test_bit(CONF_RECV_NO_FCS, &chan->conf_state)) {
 				chan->fcs = L2CAP_FCS_NONE;
 				l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1,
 						   chan->fcs);
@@ -3196,7 +3196,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data)
 
 		case L2CAP_CONF_FCS:
 			if (val == L2CAP_FCS_NONE)
-				set_bit(CONF_NO_FCS_RECV, &chan->conf_state);
+				set_bit(CONF_RECV_NO_FCS, &chan->conf_state);
 			break;
 
 		case L2CAP_CONF_EFS:
@@ -3435,7 +3435,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len,
 		case L2CAP_CONF_FCS:
 			if (*result == L2CAP_CONF_PENDING)
 				if (val == L2CAP_FCS_NONE)
-					set_bit(CONF_NO_FCS_RECV,
+					set_bit(CONF_RECV_NO_FCS,
 						&chan->conf_state);
 			break;
 		}
@@ -3807,7 +3807,7 @@ static inline void set_default_fcs(struct l2cap_chan *chan)
 	 */
 	if (chan->mode != L2CAP_MODE_ERTM && chan->mode != L2CAP_MODE_STREAMING)
 		chan->fcs = L2CAP_FCS_NONE;
-	else if (!test_bit(CONF_NO_FCS_RECV, &chan->conf_state))
+	else if (!test_bit(CONF_RECV_NO_FCS, &chan->conf_state))
 		chan->fcs = L2CAP_FCS_CRC16;
 }
 
-- 
cgit v1.2.3-55-g7522


From 196d67593439b03088913227093e374235596e33 Mon Sep 17 00:00:00 2001
From: Michele Baldessari
Date: Sat, 1 Dec 2012 04:49:42 +0000
Subject: sctp: Add support to per-association statistics via a new
 SCTP_GET_ASSOC_STATS call

The current SCTP stack is lacking a mechanism to have per association
statistics. This is an implementation modeled after OpenSolaris'
SCTP_GET_ASSOC_STATS.

Userspace part will follow on lksctp if/when there is a general ACK on
this.
V4:
- Move ipackets++ before q->immediate.func() for consistency reasons
- Move sctp_max_rto() at the end of sctp_transport_update_rto() to avoid
  returning bogus RTO values
- return asoc->rto_min when max_obs_rto value has not changed

V3:
- Increase ictrlchunks in sctp_assoc_bh_rcv() as well
- Move ipackets++ to sctp_inq_push()
- return 0 when no rto updates took place since the last call

V2:
- Implement partial retrieval of stat struct to cope for future expansion
- Kill the rtxpackets counter as it cannot be precise anyway
- Rename outseqtsns to outofseqtsns to make it clearer that these are out
  of sequence unexpected TSNs
- Move asoc->ipackets++ under a lock to avoid potential miscounts
- Fold asoc->opackets++ into the already existing asoc check
- Kill unneeded (q->asoc) test when increasing rtxchunks
- Do not count octrlchunks if sending failed (SCTP_XMIT_OK != 0)
- Don't count SHUTDOWNs as SACKs
- Move SCTP_GET_ASSOC_STATS to the private space API
- Adjust the len check in sctp_getsockopt_assoc_stats() to allow for
  future struct growth
- Move association statistics in their own struct
- Update idupchunks when we send a SACK with dup TSNs
- return min_rto in max_rto when RTO has not changed. Also return the
  transport when max_rto last changed.

Signed-off: Michele Baldessari <michele@acksyn.org>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h    | 12 ++++++++
 include/net/sctp/structs.h | 36 ++++++++++++++++++++++++
 include/net/sctp/user.h    | 27 ++++++++++++++++++
 net/sctp/associola.c       | 10 ++++++-
 net/sctp/endpointola.c     |  5 +++-
 net/sctp/inqueue.c         |  2 ++
 net/sctp/output.c          | 14 ++++++----
 net/sctp/outqueue.c        | 12 ++++++--
 net/sctp/sm_make_chunk.c   |  5 ++--
 net/sctp/sm_sideeffect.c   |  1 +
 net/sctp/sm_statefuns.c    | 10 +++++--
 net/sctp/socket.c          | 69 ++++++++++++++++++++++++++++++++++++++++++++++
 net/sctp/transport.c       |  2 ++
 13 files changed, 192 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 9c6414f553f9..7fdf298a47ef 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -272,6 +272,18 @@ struct sctp_mib {
         unsigned long   mibs[SCTP_MIB_MAX];
 };
 
+/* helper function to track stats about max rto and related transport */
+static inline void sctp_max_rto(struct sctp_association *asoc,
+				struct sctp_transport *trans)
+{
+	if (asoc->stats.max_obs_rto < (__u64)trans->rto) {
+		asoc->stats.max_obs_rto = trans->rto;
+		memset(&asoc->stats.obs_rto_ipaddr, 0,
+			sizeof(struct sockaddr_storage));
+		memcpy(&asoc->stats.obs_rto_ipaddr, &trans->ipaddr,
+			trans->af_specific->sockaddr_len);
+	}
+}
 
 /* Print debugging messages.  */
 #if SCTP_DEBUG
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 2b2f61dd4036..c2521016d646 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1312,6 +1312,40 @@ struct sctp_inithdr_host {
 	__u32 initial_tsn;
 };
 
+/* SCTP_GET_ASSOC_STATS counters */
+struct sctp_priv_assoc_stats {
+	/* Maximum observed rto in the association during subsequent
+	 * observations. Value is set to 0 if no RTO measurement took place
+	 * The transport where the max_rto was observed is returned in
+	 * obs_rto_ipaddr
+	 */
+	struct sockaddr_storage obs_rto_ipaddr;
+	__u64 max_obs_rto;
+	/* Total In and Out SACKs received and sent */
+	__u64 isacks;
+	__u64 osacks;
+	/* Total In and Out packets received and sent */
+	__u64 opackets;
+	__u64 ipackets;
+	/* Total retransmitted chunks */
+	__u64 rtxchunks;
+	/* TSN received > next expected */
+	__u64 outofseqtsns;
+	/* Duplicate Chunks received */
+	__u64 idupchunks;
+	/* Gap Ack Blocks received */
+	__u64 gapcnt;
+	/* Unordered data chunks sent and received */
+	__u64 ouodchunks;
+	__u64 iuodchunks;
+	/* Ordered data chunks sent and received */
+	__u64 oodchunks;
+	__u64 iodchunks;
+	/* Control chunks sent and received */
+	__u64 octrlchunks;
+	__u64 ictrlchunks;
+};
+
 /* RFC2960
  *
  * 12. Recommended Transmission Control Block (TCB) Parameters
@@ -1830,6 +1864,8 @@ struct sctp_association {
 
 	__u8 need_ecne:1,	/* Need to send an ECNE Chunk? */
 	     temp:1;		/* Is it a temporary association? */
+
+	struct sctp_priv_assoc_stats stats;
 };
 
 
diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h
index 1b02d7ad453b..9a0ae091366d 100644
--- a/include/net/sctp/user.h
+++ b/include/net/sctp/user.h
@@ -107,6 +107,7 @@ typedef __s32 sctp_assoc_t;
 #define SCTP_GET_LOCAL_ADDRS	109		/* Get all local address. */
 #define SCTP_SOCKOPT_CONNECTX	110		/* CONNECTX requests. */
 #define SCTP_SOCKOPT_CONNECTX3	111	/* CONNECTX requests (updated) */
+#define SCTP_GET_ASSOC_STATS	112	/* Read only */
 
 /*
  * 5.2.1 SCTP Initiation Structure (SCTP_INIT)
@@ -719,6 +720,32 @@ struct sctp_getaddrs {
 	__u8			addrs[0]; /*output, variable size*/
 };
 
+/* A socket user request obtained via SCTP_GET_ASSOC_STATS that retrieves
+ * association stats. All stats are counts except sas_maxrto and
+ * sas_obs_rto_ipaddr. maxrto is the max observed rto + transport since
+ * the last call. Will return 0 when RTO was not update since last call
+ */
+struct sctp_assoc_stats {
+	sctp_assoc_t	sas_assoc_id;    /* Input */
+					 /* Transport of observed max RTO */
+	struct sockaddr_storage sas_obs_rto_ipaddr;
+	__u64		sas_maxrto;      /* Maximum Observed RTO for period */
+	__u64		sas_isacks;	 /* SACKs received */
+	__u64		sas_osacks;	 /* SACKs sent */
+	__u64		sas_opackets;	 /* Packets sent */
+	__u64		sas_ipackets;	 /* Packets received */
+	__u64		sas_rtxchunks;   /* Retransmitted Chunks */
+	__u64		sas_outofseqtsns;/* TSN received > next expected */
+	__u64		sas_idupchunks;  /* Dups received (ordered+unordered) */
+	__u64		sas_gapcnt;      /* Gap Acknowledgements Received */
+	__u64		sas_ouodchunks;  /* Unordered data chunks sent */
+	__u64		sas_iuodchunks;  /* Unordered data chunks received */
+	__u64		sas_oodchunks;	 /* Ordered data chunks sent */
+	__u64		sas_iodchunks;	 /* Ordered data chunks received */
+	__u64		sas_octrlchunks; /* Control chunks sent */
+	__u64		sas_ictrlchunks; /* Control chunks received */
+};
+
 /* These are bit fields for msghdr->msg_flags.  See section 5.1.  */
 /* On user space Linux, these live in <bits/socket.h> as an enum.  */
 enum sctp_msg_flags {
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index b1ef3bc301a5..ba3f9cc4c047 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -321,6 +321,9 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 	asoc->default_timetolive = sp->default_timetolive;
 	asoc->default_rcv_context = sp->default_rcv_context;
 
+	/* SCTP_GET_ASSOC_STATS COUNTERS */
+	memset(&asoc->stats, 0, sizeof(struct sctp_priv_assoc_stats));
+
 	/* AUTH related initializations */
 	INIT_LIST_HEAD(&asoc->endpoint_shared_keys);
 	err = sctp_auth_asoc_copy_shkeys(ep, asoc, gfp);
@@ -760,6 +763,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 
 	/* Set the transport's RTO.initial value */
 	peer->rto = asoc->rto_initial;
+	sctp_max_rto(asoc, peer);
 
 	/* Set the peer's active state. */
 	peer->state = peer_state;
@@ -1152,8 +1156,12 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 		 */
 		if (sctp_chunk_is_data(chunk))
 			asoc->peer.last_data_from = chunk->transport;
-		else
+		else {
 			SCTP_INC_STATS(net, SCTP_MIB_INCTRLCHUNKS);
+			asoc->stats.ictrlchunks++;
+			if (chunk->chunk_hdr->type == SCTP_CID_SACK)
+				asoc->stats.isacks++;
+		}
 
 		if (chunk->transport)
 			chunk->transport->last_time_heard = jiffies;
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 1859e2bc83d1..32ab55b18281 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -480,8 +480,11 @@ normal:
 		 */
 		if (asoc && sctp_chunk_is_data(chunk))
 			asoc->peer.last_data_from = chunk->transport;
-		else
+		else {
 			SCTP_INC_STATS(sock_net(ep->base.sk), SCTP_MIB_INCTRLCHUNKS);
+			if (asoc)
+				asoc->stats.ictrlchunks++;
+		}
 
 		if (chunk->transport)
 			chunk->transport->last_time_heard = jiffies;
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 397296fb156f..2d5ad280de38 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -104,6 +104,8 @@ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk)
 	 * on the BH related data structures.
 	 */
 	list_add_tail(&chunk->list, &q->in_chunk_list);
+	if (chunk->asoc)
+		chunk->asoc->stats.ipackets++;
 	q->immediate.func(&q->immediate);
 }
 
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 4e90188bf489..f5200a2ad852 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -311,6 +311,8 @@ static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet,
 
 	    case SCTP_CID_SACK:
 		packet->has_sack = 1;
+		if (chunk->asoc)
+			chunk->asoc->stats.osacks++;
 		break;
 
 	    case SCTP_CID_AUTH:
@@ -584,11 +586,13 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	 */
 
 	/* Dump that on IP!  */
-	if (asoc && asoc->peer.last_sent_to != tp) {
-		/* Considering the multiple CPU scenario, this is a
-		 * "correcter" place for last_sent_to.  --xguo
-		 */
-		asoc->peer.last_sent_to = tp;
+	if (asoc) {
+		asoc->stats.opackets++;
+		if (asoc->peer.last_sent_to != tp)
+			/* Considering the multiple CPU scenario, this is a
+			 * "correcter" place for last_sent_to.  --xguo
+			 */
+			asoc->peer.last_sent_to = tp;
 	}
 
 	if (has_data) {
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 1b4a7f8ec3fd..379c81dee9d1 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -667,6 +667,7 @@ redo:
 				chunk->fast_retransmit = SCTP_DONT_FRTX;
 
 			q->empty = 0;
+			q->asoc->stats.rtxchunks++;
 			break;
 		}
 
@@ -876,12 +877,14 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
 			if (status  != SCTP_XMIT_OK) {
 				/* put the chunk back */
 				list_add(&chunk->list, &q->control_chunk_list);
-			} else if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN) {
+			} else {
+				asoc->stats.octrlchunks++;
 				/* PR-SCTP C5) If a FORWARD TSN is sent, the
 				 * sender MUST assure that at least one T3-rtx
 				 * timer is running.
 				 */
-				sctp_transport_reset_timers(transport);
+				if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN)
+					sctp_transport_reset_timers(transport);
 			}
 			break;
 
@@ -1055,6 +1058,10 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
 				 */
 				if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING)
 					chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM;
+				if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
+					asoc->stats.ouodchunks++;
+				else
+					asoc->stats.oodchunks++;
 
 				break;
 
@@ -1162,6 +1169,7 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk)
 
 	sack_ctsn = ntohl(sack->cum_tsn_ack);
 	gap_ack_blocks = ntohs(sack->num_gap_ack_blocks);
+	asoc->stats.gapcnt += gap_ack_blocks;
 	/*
 	 * SFR-CACC algorithm:
 	 * On receipt of a SACK the sender SHOULD execute the
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index e0f01a4e8cd6..e1c5fc2be6b8 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -804,10 +804,11 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc)
 				 gabs);
 
 	/* Add the duplicate TSN information.  */
-	if (num_dup_tsns)
+	if (num_dup_tsns) {
+		aptr->stats.idupchunks += num_dup_tsns;
 		sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns,
 				 sctp_tsnmap_get_dups(map));
-
+	}
 	/* Once we have a sack generated, check to see what our sack
 	 * generation is, if its 0, reset the transports to 0, and reset
 	 * the association generation to 1
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index c0769569b05d..c9577754a708 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -542,6 +542,7 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands,
 	 */
 	if (!is_hb || transport->hb_sent) {
 		transport->rto = min((transport->rto * 2), transport->asoc->rto_max);
+		sctp_max_rto(asoc, transport);
 	}
 }
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index e92079d27eae..ebcd1eedb115 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -6133,6 +6133,8 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 		/* The TSN is too high--silently discard the chunk and
 		 * count on it getting retransmitted later.
 		 */
+		if (chunk->asoc)
+			chunk->asoc->stats.outofseqtsns++;
 		return SCTP_IERROR_HIGH_TSN;
 	} else if (tmp > 0) {
 		/* This is a duplicate.  Record it.  */
@@ -6232,10 +6234,14 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	/* Note: Some chunks may get overcounted (if we drop) or overcounted
 	 * if we renege and the chunk arrives again.
 	 */
-	if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
+	if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) {
 		SCTP_INC_STATS(net, SCTP_MIB_INUNORDERCHUNKS);
-	else {
+		if (chunk->asoc)
+			chunk->asoc->stats.iuodchunks++;
+	} else {
 		SCTP_INC_STATS(net, SCTP_MIB_INORDERCHUNKS);
+		if (chunk->asoc)
+			chunk->asoc->stats.iodchunks++;
 		ordered = 1;
 	}
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index bc1624913c42..9e65758cb038 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -611,6 +611,7 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
 				    2*asoc->pathmtu, 4380));
 				trans->ssthresh = asoc->peer.i.a_rwnd;
 				trans->rto = asoc->rto_initial;
+				sctp_max_rto(asoc, trans);
 				trans->rtt = trans->srtt = trans->rttvar = 0;
 				sctp_transport_route(trans, NULL,
 				    sctp_sk(asoc->base.sk));
@@ -5635,6 +5636,71 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk,
 	return 0;
 }
 
+/*
+ * SCTP_GET_ASSOC_STATS
+ *
+ * This option retrieves local per endpoint statistics. It is modeled
+ * after OpenSolaris' implementation
+ */
+static int sctp_getsockopt_assoc_stats(struct sock *sk, int len,
+				       char __user *optval,
+				       int __user *optlen)
+{
+	struct sctp_assoc_stats sas;
+	struct sctp_association *asoc = NULL;
+
+	/* User must provide at least the assoc id */
+	if (len < sizeof(sctp_assoc_t))
+		return -EINVAL;
+
+	if (copy_from_user(&sas, optval, len))
+		return -EFAULT;
+
+	asoc = sctp_id2assoc(sk, sas.sas_assoc_id);
+	if (!asoc)
+		return -EINVAL;
+
+	sas.sas_rtxchunks = asoc->stats.rtxchunks;
+	sas.sas_gapcnt = asoc->stats.gapcnt;
+	sas.sas_outofseqtsns = asoc->stats.outofseqtsns;
+	sas.sas_osacks = asoc->stats.osacks;
+	sas.sas_isacks = asoc->stats.isacks;
+	sas.sas_octrlchunks = asoc->stats.octrlchunks;
+	sas.sas_ictrlchunks = asoc->stats.ictrlchunks;
+	sas.sas_oodchunks = asoc->stats.oodchunks;
+	sas.sas_iodchunks = asoc->stats.iodchunks;
+	sas.sas_ouodchunks = asoc->stats.ouodchunks;
+	sas.sas_iuodchunks = asoc->stats.iuodchunks;
+	sas.sas_idupchunks = asoc->stats.idupchunks;
+	sas.sas_opackets = asoc->stats.opackets;
+	sas.sas_ipackets = asoc->stats.ipackets;
+
+	/* New high max rto observed, will return 0 if not a single
+	 * RTO update took place. obs_rto_ipaddr will be bogus
+	 * in such a case
+	 */
+	sas.sas_maxrto = asoc->stats.max_obs_rto;
+	memcpy(&sas.sas_obs_rto_ipaddr, &asoc->stats.obs_rto_ipaddr,
+		sizeof(struct sockaddr_storage));
+
+	/* Mark beginning of a new observation period */
+	asoc->stats.max_obs_rto = asoc->rto_min;
+
+	/* Allow the struct to grow and fill in as much as possible */
+	len = min_t(size_t, len, sizeof(sas));
+
+	if (put_user(len, optlen))
+		return -EFAULT;
+
+	SCTP_DEBUG_PRINTK("sctp_getsockopt_assoc_stat(%d): %d\n",
+			  len, sas.sas_assoc_id);
+
+	if (copy_to_user(optval, &sas, len))
+		return -EFAULT;
+
+	return 0;
+}
+
 SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
 				char __user *optval, int __user *optlen)
 {
@@ -5776,6 +5842,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
 	case SCTP_PEER_ADDR_THLDS:
 		retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen);
 		break;
+	case SCTP_GET_ASSOC_STATS:
+		retval = sctp_getsockopt_assoc_stats(sk, len, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 206cf5238fd3..310f11eb2206 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -363,6 +363,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt)
 	if (tp->rto > tp->asoc->rto_max)
 		tp->rto = tp->asoc->rto_max;
 
+	sctp_max_rto(tp->asoc, tp);
 	tp->rtt = rtt;
 
 	/* Reset rto_pending so that a new RTT measurement is started when a
@@ -620,6 +621,7 @@ void sctp_transport_reset(struct sctp_transport *t)
 	t->burst_limited = 0;
 	t->ssthresh = asoc->peer.i.a_rwnd;
 	t->rto = asoc->rto_initial;
+	sctp_max_rto(asoc, t);
 	t->rtt = 0;
 	t->srtt = 0;
 	t->rttvar = 0;
-- 
cgit v1.2.3-55-g7522


From 5d097109257c03a71845729f8db6b5770c4bbedc Mon Sep 17 00:00:00 2001
From: Michael S. Tsirkin
Date: Mon, 3 Dec 2012 10:07:14 +0000
Subject: tun: only queue packets on device

Historically tun supported two modes of operation:
- in default mode, a small number of packets would get queued
  at the device, the rest would be queued in qdisc
- in one queue mode, all packets would get queued at the device

This might have made sense up to a point where we made the
queue depth for both modes the same and set it to
a huge value (500) so unless the consumer
is stuck the chance of losing packets is small.

Thus in practice both modes behave the same, but the
default mode has some problems:
- if packets are never consumed, fragments are never orphaned
  which cases a DOS for sender using zero copy transmit
- overrun errors are hard to diagnose: fifo error is incremented
  only once so you can not distinguish between
  userspace that is stuck and a transient failure,
  tcpdump on the device does not show any traffic

Userspace solves this simply by enabling IFF_ONE_QUEUE
but there seems to be little point in not doing the
right thing for everyone, by default.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c           | 24 ++++++++----------------
 include/uapi/linux/if_tun.h |  2 ++
 2 files changed, 10 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 71f6874d8048..a1b2389e6d7f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -690,21 +690,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * number of queues.
 	 */
 	if (skb_queue_len(&tfile->socket.sk->sk_receive_queue)
-			  >= dev->tx_queue_len / tun->numqueues){
-		if (!(tun->flags & TUN_ONE_QUEUE)) {
-			/* Normal queueing mode. */
-			/* Packet scheduler handles dropping of further packets. */
-			netif_stop_subqueue(dev, txq);
-
-			/* We won't see all dropped packets individually, so overrun
-			 * error is more appropriate. */
-			dev->stats.tx_fifo_errors++;
-		} else {
-			/* Single queue mode.
-			 * Driver handles dropping of all packets itself. */
-			goto drop;
-		}
-	}
+			  >= dev->tx_queue_len / tun->numqueues)
+		goto drop;
 
 	/* Orphan the skb - required as we might hang on to it
 	 * for indefinite time. */
@@ -1319,7 +1306,6 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 			schedule();
 			continue;
 		}
-		netif_wake_subqueue(tun->dev, tfile->queue_index);
 
 		ret = tun_put_user(tun, tfile, skb, iv, len);
 		kfree_skb(skb);
@@ -1482,6 +1468,9 @@ static int tun_flags(struct tun_struct *tun)
 	if (tun->flags & TUN_NO_PI)
 		flags |= IFF_NO_PI;
 
+	/* This flag has no real effect.  We track the value for backwards
+	 * compatibility.
+	 */
 	if (tun->flags & TUN_ONE_QUEUE)
 		flags |= IFF_ONE_QUEUE;
 
@@ -1632,6 +1621,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 	else
 		tun->flags &= ~TUN_NO_PI;
 
+	/* This flag has no real effect.  We track the value for backwards
+	 * compatibility.
+	 */
 	if (ifr->ifr_flags & IFF_ONE_QUEUE)
 		tun->flags |= TUN_ONE_QUEUE;
 	else
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 958497ad5bb5..2835b85fd46d 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -31,6 +31,7 @@
 #define TUN_FASYNC	0x0010
 #define TUN_NOCHECKSUM	0x0020
 #define TUN_NO_PI	0x0040
+/* This flag has no real effect */
 #define TUN_ONE_QUEUE	0x0080
 #define TUN_PERSIST 	0x0100	
 #define TUN_VNET_HDR 	0x0200
@@ -60,6 +61,7 @@
 #define IFF_TUN		0x0001
 #define IFF_TAP		0x0002
 #define IFF_NO_PI	0x1000
+/* This flag has no real effect */
 #define IFF_ONE_QUEUE	0x2000
 #define IFF_VNET_HDR	0x4000
 #define IFF_TUN_EXCL	0x8000
-- 
cgit v1.2.3-55-g7522


From 2a3098ff6c2109557868f9f230f4725312dcb882 Mon Sep 17 00:00:00 2001
From: Inki Dae
Date: Sun, 4 Nov 2012 05:48:52 -0800
Subject: drm/exynos: add userptr feature for g2d module

This patch adds userptr feautre for G2D module.

The userptr means user space address allocated by malloc().
And the purpose of this feature is to make G2D's dma able
to access the user space region.

To user this feature, user should flag G2D_BUF_USRPTR to
offset variable of struct drm_exynos_g2d_cmd and fill
struct drm_exynos_g2d_userptr with user space address
and size for it and then should set a pointer to
drm_exynos_g2d_userptr object to data variable of struct
drm_exynos_g2d_cmd. The last bit of offset variable is used
to check if the cmdlist's buffer type is userptr or not.
If userptr, the g2d driver gets user space address and size
and then gets pages through get_user_pages().
(another case is counted as gem handle)

Below is sample codes:

static void set_cmd(struct drm_exynos_g2d_cmd *cmd,
		unsigned long offset, unsigned long data)
{
	cmd->offset = offset;
	cmd->data = data;
}

static int solid_fill_test(int x, int y, unsigned long userptr)
{
	struct drm_exynos_g2d_cmd cmd_gem[5];
	struct drm_exynos_g2d_userptr g2d_userptr;
	unsigned int gem_nr = 0;
	...

	g2d_userptr.userptr = userptr;
	g2d_userptr.size = x * y * 4;

	set_cmd(&cmd_gem[gem_nr++], DST_BASE_ADDR_REG |
					G2D_BUF_USERPTR,
			(unsigned long)&g2d_userptr);
	...
}

int main(int argc, char **argv)
{
	unsigned long addr;
	...

	addr = malloc(x * y * 4);
	...

	solid_fill_test(x, y, addr);
	...
}

And next, the pages are mapped with iommu table and the device
address is set to cmdlist so that G2D's dma can access it.
As you may know, the pages from get_user_pages() are pinned.
In other words, they CAN NOT be migrated and also swapped out.
So the dma access would be safe.

But the use of userptr feature has performance overhead so
this patch also has memory pool to the userptr feature.
Please, assume that user sends cmdlist filled with userptr
and size every time to g2d driver, and the get_user_pages
funcion will be called every time.

The memory pool has maximum 64MB size and the userptr that
user had ever sent, is holded in the memory pool.
This meaning is that if the userptr from user is same as one
in the memory pool, device address to the userptr in the memory
pool is set to cmdlist.

And last, the pages from get_user_pages() will be freed once
user calls free() and the dma access is completed. Actually,
get_user_pages() takes 2 reference counts if the user process
has never accessed user region allocated by malloc(). Then, if
the user calls free(), the page reference count becomes 1 and
becomes 0 with put_page() call. And the reverse holds as well.
This means how the pages backed are used by dma and freed.

This patch is based on "drm/exynos: add iommu support for g2d",
	https://patchwork.kernel.org/patch/1629481/

Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_drv.h |   3 +-
 drivers/gpu/drm/exynos/exynos_drm_g2d.c | 342 +++++++++++++++++++++++++++++---
 drivers/gpu/drm/exynos/exynos_drm_gem.c | 123 ++++++++++++
 drivers/gpu/drm/exynos/exynos_drm_gem.h |  45 +++++
 include/uapi/drm/exynos_drm.h           |  13 +-
 5 files changed, 499 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index 8c9f4b05fc17..9c9c2dc75828 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -231,8 +231,7 @@ struct exynos_drm_g2d_private {
 	struct device		*dev;
 	struct list_head	inuse_cmdlist;
 	struct list_head	event_list;
-	struct list_head	gem_list;
-	unsigned int		gem_nr;
+	struct list_head	userptr_list;
 };
 
 struct drm_exynos_file_private {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index bac2399857d1..a9002adc4694 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -97,11 +97,19 @@
 
 #define MAX_BUF_ADDR_NR			6
 
+/* maximum buffer pool size of userptr is 64MB as default */
+#define MAX_POOL		(64 * 1024 * 1024)
+
+enum {
+	BUF_TYPE_GEM = 1,
+	BUF_TYPE_USERPTR,
+};
+
 /* cmdlist data structure */
 struct g2d_cmdlist {
-	u32	head;
-	u32	data[G2D_CMDLIST_DATA_NUM];
-	u32	last;	/* last data offset */
+	u32		head;
+	unsigned long	data[G2D_CMDLIST_DATA_NUM];
+	u32		last;	/* last data offset */
 };
 
 struct drm_exynos_pending_g2d_event {
@@ -109,11 +117,26 @@ struct drm_exynos_pending_g2d_event {
 	struct drm_exynos_g2d_event	event;
 };
 
+struct g2d_cmdlist_userptr {
+	struct list_head	list;
+	dma_addr_t		dma_addr;
+	unsigned long		userptr;
+	unsigned long		size;
+	struct page		**pages;
+	unsigned int		npages;
+	struct sg_table		*sgt;
+	struct vm_area_struct	*vma;
+	atomic_t		refcount;
+	bool			in_pool;
+	bool			out_of_list;
+};
+
 struct g2d_cmdlist_node {
 	struct list_head	list;
 	struct g2d_cmdlist	*cmdlist;
 	unsigned int		map_nr;
-	unsigned int		handles[MAX_BUF_ADDR_NR];
+	unsigned long		handles[MAX_BUF_ADDR_NR];
+	unsigned int		obj_type[MAX_BUF_ADDR_NR];
 	dma_addr_t		dma_addr;
 
 	struct drm_exynos_pending_g2d_event	*event;
@@ -152,6 +175,9 @@ struct g2d_data {
 	struct list_head		runqueue;
 	struct mutex			runqueue_mutex;
 	struct kmem_cache		*runqueue_slab;
+
+	unsigned long			current_pool;
+	unsigned long			max_pool;
 };
 
 static int g2d_init_cmdlist(struct g2d_data *g2d)
@@ -256,6 +282,229 @@ add_to_list:
 		list_add_tail(&node->event->base.link, &g2d_priv->event_list);
 }
 
+static void g2d_userptr_put_dma_addr(struct drm_device *drm_dev,
+					unsigned long obj,
+					bool force)
+{
+	struct g2d_cmdlist_userptr *g2d_userptr =
+					(struct g2d_cmdlist_userptr *)obj;
+
+	if (!obj)
+		return;
+
+	if (force)
+		goto out;
+
+	atomic_dec(&g2d_userptr->refcount);
+
+	if (atomic_read(&g2d_userptr->refcount) > 0)
+		return;
+
+	if (g2d_userptr->in_pool)
+		return;
+
+out:
+	exynos_gem_unmap_sgt_from_dma(drm_dev, g2d_userptr->sgt,
+					DMA_BIDIRECTIONAL);
+
+	exynos_gem_put_pages_to_userptr(g2d_userptr->pages,
+					g2d_userptr->npages,
+					g2d_userptr->vma);
+
+	if (!g2d_userptr->out_of_list)
+		list_del_init(&g2d_userptr->list);
+
+	sg_free_table(g2d_userptr->sgt);
+	kfree(g2d_userptr->sgt);
+	g2d_userptr->sgt = NULL;
+
+	kfree(g2d_userptr->pages);
+	kfree(g2d_userptr);
+	g2d_userptr->pages = NULL;
+	g2d_userptr = NULL;
+}
+
+dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
+					unsigned long userptr,
+					unsigned long size,
+					struct drm_file *filp,
+					unsigned long *obj)
+{
+	struct drm_exynos_file_private *file_priv = filp->driver_priv;
+	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
+	struct g2d_cmdlist_userptr *g2d_userptr;
+	struct g2d_data *g2d;
+	struct page **pages;
+	struct sg_table	*sgt;
+	struct vm_area_struct *vma;
+	unsigned long start, end;
+	unsigned int npages, offset;
+	int ret;
+
+	if (!size) {
+		DRM_ERROR("invalid userptr size.\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	g2d = dev_get_drvdata(g2d_priv->dev);
+
+	/* check if userptr already exists in userptr_list. */
+	list_for_each_entry(g2d_userptr, &g2d_priv->userptr_list, list) {
+		if (g2d_userptr->userptr == userptr) {
+			/*
+			 * also check size because there could be same address
+			 * and different size.
+			 */
+			if (g2d_userptr->size == size) {
+				atomic_inc(&g2d_userptr->refcount);
+				*obj = (unsigned long)g2d_userptr;
+
+				return &g2d_userptr->dma_addr;
+			}
+
+			/*
+			 * at this moment, maybe g2d dma is accessing this
+			 * g2d_userptr memory region so just remove this
+			 * g2d_userptr object from userptr_list not to be
+			 * referred again and also except it the userptr
+			 * pool to be released after the dma access completion.
+			 */
+			g2d_userptr->out_of_list = true;
+			g2d_userptr->in_pool = false;
+			list_del_init(&g2d_userptr->list);
+
+			break;
+		}
+	}
+
+	g2d_userptr = kzalloc(sizeof(*g2d_userptr), GFP_KERNEL);
+	if (!g2d_userptr) {
+		DRM_ERROR("failed to allocate g2d_userptr.\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	atomic_set(&g2d_userptr->refcount, 1);
+
+	start = userptr & PAGE_MASK;
+	offset = userptr & ~PAGE_MASK;
+	end = PAGE_ALIGN(userptr + size);
+	npages = (end - start) >> PAGE_SHIFT;
+	g2d_userptr->npages = npages;
+
+	pages = kzalloc(npages * sizeof(struct page *), GFP_KERNEL);
+	if (!pages) {
+		DRM_ERROR("failed to allocate pages.\n");
+		kfree(g2d_userptr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	vma = find_vma(current->mm, userptr);
+	if (!vma) {
+		DRM_ERROR("failed to get vm region.\n");
+		ret = -EFAULT;
+		goto err_free_pages;
+	}
+
+	if (vma->vm_end < userptr + size) {
+		DRM_ERROR("vma is too small.\n");
+		ret = -EFAULT;
+		goto err_free_pages;
+	}
+
+	g2d_userptr->vma = exynos_gem_get_vma(vma);
+	if (!g2d_userptr->vma) {
+		DRM_ERROR("failed to copy vma.\n");
+		ret = -ENOMEM;
+		goto err_free_pages;
+	}
+
+	g2d_userptr->size = size;
+
+	ret = exynos_gem_get_pages_from_userptr(start & PAGE_MASK,
+						npages, pages, vma);
+	if (ret < 0) {
+		DRM_ERROR("failed to get user pages from userptr.\n");
+		goto err_put_vma;
+	}
+
+	g2d_userptr->pages = pages;
+
+	sgt = kzalloc(sizeof *sgt, GFP_KERNEL);
+	if (!sgt) {
+		DRM_ERROR("failed to allocate sg table.\n");
+		ret = -ENOMEM;
+		goto err_free_userptr;
+	}
+
+	ret = sg_alloc_table_from_pages(sgt, pages, npages, offset,
+					size, GFP_KERNEL);
+	if (ret < 0) {
+		DRM_ERROR("failed to get sgt from pages.\n");
+		goto err_free_sgt;
+	}
+
+	g2d_userptr->sgt = sgt;
+
+	ret = exynos_gem_map_sgt_with_dma(drm_dev, g2d_userptr->sgt,
+						DMA_BIDIRECTIONAL);
+	if (ret < 0) {
+		DRM_ERROR("failed to map sgt with dma region.\n");
+		goto err_free_sgt;
+	}
+
+	g2d_userptr->dma_addr = sgt->sgl[0].dma_address;
+	g2d_userptr->userptr = userptr;
+
+	list_add_tail(&g2d_userptr->list, &g2d_priv->userptr_list);
+
+	if (g2d->current_pool + (npages << PAGE_SHIFT) < g2d->max_pool) {
+		g2d->current_pool += npages << PAGE_SHIFT;
+		g2d_userptr->in_pool = true;
+	}
+
+	*obj = (unsigned long)g2d_userptr;
+
+	return &g2d_userptr->dma_addr;
+
+err_free_sgt:
+	sg_free_table(sgt);
+	kfree(sgt);
+	sgt = NULL;
+
+err_free_userptr:
+	exynos_gem_put_pages_to_userptr(g2d_userptr->pages,
+					g2d_userptr->npages,
+					g2d_userptr->vma);
+
+err_put_vma:
+	exynos_gem_put_vma(g2d_userptr->vma);
+
+err_free_pages:
+	kfree(pages);
+	kfree(g2d_userptr);
+	pages = NULL;
+	g2d_userptr = NULL;
+
+	return ERR_PTR(ret);
+}
+
+static void g2d_userptr_free_all(struct drm_device *drm_dev,
+					struct g2d_data *g2d,
+					struct drm_file *filp)
+{
+	struct drm_exynos_file_private *file_priv = filp->driver_priv;
+	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
+	struct g2d_cmdlist_userptr *g2d_userptr, *n;
+
+	list_for_each_entry_safe(g2d_userptr, n, &g2d_priv->userptr_list, list)
+		if (g2d_userptr->in_pool)
+			g2d_userptr_put_dma_addr(drm_dev,
+						(unsigned long)g2d_userptr,
+						true);
+
+	g2d->current_pool = 0;
+}
+
 static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 				struct g2d_cmdlist_node *node,
 				struct drm_device *drm_dev,
@@ -272,10 +521,31 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 		offset = cmdlist->last - (i * 2 + 1);
 		handle = cmdlist->data[offset];
 
-		addr = exynos_drm_gem_get_dma_addr(drm_dev, handle, file);
-		if (IS_ERR(addr)) {
-			node->map_nr = i;
-			return -EFAULT;
+		if (node->obj_type[i] == BUF_TYPE_GEM) {
+			addr = exynos_drm_gem_get_dma_addr(drm_dev, handle,
+								file);
+			if (IS_ERR(addr)) {
+				node->map_nr = i;
+				return -EFAULT;
+			}
+		} else {
+			struct drm_exynos_g2d_userptr g2d_userptr;
+
+			if (copy_from_user(&g2d_userptr, (void __user *)handle,
+				sizeof(struct drm_exynos_g2d_userptr))) {
+				node->map_nr = i;
+				return -EFAULT;
+			}
+
+			addr = g2d_userptr_get_dma_addr(drm_dev,
+							g2d_userptr.userptr,
+							g2d_userptr.size,
+							file,
+							&handle);
+			if (IS_ERR(addr)) {
+				node->map_nr = i;
+				return -EFAULT;
+			}
 		}
 
 		cmdlist->data[offset] = *addr;
@@ -293,9 +563,14 @@ static void g2d_unmap_cmdlist_gem(struct g2d_data *g2d,
 	int i;
 
 	for (i = 0; i < node->map_nr; i++) {
-		unsigned int handle = node->handles[i];
+		unsigned long handle = node->handles[i];
 
-		exynos_drm_gem_put_dma_addr(subdrv->drm_dev, handle, filp);
+		if (node->obj_type[i] == BUF_TYPE_GEM)
+			exynos_drm_gem_put_dma_addr(subdrv->drm_dev, handle,
+							filp);
+		else
+			g2d_userptr_put_dma_addr(subdrv->drm_dev, handle,
+							false);
 
 		node->handles[i] = 0;
 	}
@@ -438,15 +713,28 @@ static irqreturn_t g2d_irq_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int g2d_check_reg_offset(struct device *dev, struct g2d_cmdlist *cmdlist,
+static int g2d_check_reg_offset(struct device *dev,
+				struct g2d_cmdlist_node *node,
 				int nr, bool for_addr)
 {
+	struct g2d_cmdlist *cmdlist = node->cmdlist;
 	int reg_offset;
 	int index;
 	int i;
 
 	for (i = 0; i < nr; i++) {
 		index = cmdlist->last - 2 * (i + 1);
+
+		if (for_addr) {
+			/* check userptr buffer type. */
+			reg_offset = (cmdlist->data[index] &
+					~0x7fffffff) >> 31;
+			if (reg_offset) {
+				node->obj_type[i] = BUF_TYPE_USERPTR;
+				cmdlist->data[index] &= ~G2D_BUF_USERPTR;
+			}
+		}
+
 		reg_offset = cmdlist->data[index] & ~0xfffff000;
 
 		if (reg_offset < G2D_VALID_START || reg_offset > G2D_VALID_END)
@@ -463,6 +751,9 @@ static int g2d_check_reg_offset(struct device *dev, struct g2d_cmdlist *cmdlist,
 		case G2D_MSK_BASE_ADDR:
 			if (!for_addr)
 				goto err;
+
+			if (node->obj_type[i] != BUF_TYPE_USERPTR)
+				node->obj_type[i] = BUF_TYPE_GEM;
 			break;
 		default:
 			if (for_addr)
@@ -474,7 +765,7 @@ static int g2d_check_reg_offset(struct device *dev, struct g2d_cmdlist *cmdlist,
 	return 0;
 
 err:
-	dev_err(dev, "Bad register offset: 0x%x\n", cmdlist->data[index]);
+	dev_err(dev, "Bad register offset: 0x%lx\n", cmdlist->data[index]);
 	return -EINVAL;
 }
 
@@ -574,7 +865,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	}
 
 	/* Check size of cmdlist: last 2 is about G2D_BITBLT_START */
-	size = cmdlist->last + req->cmd_nr * 2 + req->cmd_gem_nr * 2 + 2;
+	size = cmdlist->last + req->cmd_nr * 2 + req->cmd_buf_nr * 2 + 2;
 	if (size > G2D_CMDLIST_DATA_NUM) {
 		dev_err(dev, "cmdlist size is too big\n");
 		ret = -EINVAL;
@@ -591,25 +882,25 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	}
 	cmdlist->last += req->cmd_nr * 2;
 
-	ret = g2d_check_reg_offset(dev, cmdlist, req->cmd_nr, false);
+	ret = g2d_check_reg_offset(dev, node, req->cmd_nr, false);
 	if (ret < 0)
 		goto err_free_event;
 
-	node->map_nr = req->cmd_gem_nr;
-	if (req->cmd_gem_nr) {
-		struct drm_exynos_g2d_cmd *cmd_gem;
+	node->map_nr = req->cmd_buf_nr;
+	if (req->cmd_buf_nr) {
+		struct drm_exynos_g2d_cmd *cmd_buf;
 
-		cmd_gem = (struct drm_exynos_g2d_cmd *)(uint32_t)req->cmd_gem;
+		cmd_buf = (struct drm_exynos_g2d_cmd *)(uint32_t)req->cmd_buf;
 
 		if (copy_from_user(cmdlist->data + cmdlist->last,
-					(void __user *)cmd_gem,
-					sizeof(*cmd_gem) * req->cmd_gem_nr)) {
+					(void __user *)cmd_buf,
+					sizeof(*cmd_buf) * req->cmd_buf_nr)) {
 			ret = -EFAULT;
 			goto err_free_event;
 		}
-		cmdlist->last += req->cmd_gem_nr * 2;
+		cmdlist->last += req->cmd_buf_nr * 2;
 
-		ret = g2d_check_reg_offset(dev, cmdlist, req->cmd_gem_nr, true);
+		ret = g2d_check_reg_offset(dev, node, req->cmd_buf_nr, true);
 		if (ret < 0)
 			goto err_free_event;
 
@@ -759,7 +1050,7 @@ static int g2d_open(struct drm_device *drm_dev, struct device *dev,
 
 	INIT_LIST_HEAD(&g2d_priv->inuse_cmdlist);
 	INIT_LIST_HEAD(&g2d_priv->event_list);
-	INIT_LIST_HEAD(&g2d_priv->gem_list);
+	INIT_LIST_HEAD(&g2d_priv->userptr_list);
 
 	return 0;
 }
@@ -793,6 +1084,9 @@ static void g2d_close(struct drm_device *drm_dev, struct device *dev,
 	}
 	mutex_unlock(&g2d->cmdlist_mutex);
 
+	/* release all g2d_userptr in pool. */
+	g2d_userptr_free_all(drm_dev, g2d, file);
+
 	kfree(file_priv->g2d_priv);
 }
 
@@ -863,6 +1157,8 @@ static int __devinit g2d_probe(struct platform_device *pdev)
 		goto err_put_clk;
 	}
 
+	g2d->max_pool = MAX_POOL;
+
 	platform_set_drvdata(pdev, g2d);
 
 	subdrv = &g2d->subdrv;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 5fdfb8f51a41..2cc6b3ae4e07 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -448,6 +448,129 @@ int exynos_drm_gem_get_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
+struct vm_area_struct *exynos_gem_get_vma(struct vm_area_struct *vma)
+{
+	struct vm_area_struct *vma_copy;
+
+	vma_copy = kmalloc(sizeof(*vma_copy), GFP_KERNEL);
+	if (!vma_copy)
+		return NULL;
+
+	if (vma->vm_ops && vma->vm_ops->open)
+		vma->vm_ops->open(vma);
+
+	if (vma->vm_file)
+		get_file(vma->vm_file);
+
+	memcpy(vma_copy, vma, sizeof(*vma));
+
+	vma_copy->vm_mm = NULL;
+	vma_copy->vm_next = NULL;
+	vma_copy->vm_prev = NULL;
+
+	return vma_copy;
+}
+
+void exynos_gem_put_vma(struct vm_area_struct *vma)
+{
+	if (!vma)
+		return;
+
+	if (vma->vm_ops && vma->vm_ops->close)
+		vma->vm_ops->close(vma);
+
+	if (vma->vm_file)
+		fput(vma->vm_file);
+
+	kfree(vma);
+}
+
+int exynos_gem_get_pages_from_userptr(unsigned long start,
+						unsigned int npages,
+						struct page **pages,
+						struct vm_area_struct *vma)
+{
+	int get_npages;
+
+	/* the memory region mmaped with VM_PFNMAP. */
+	if (vma_is_io(vma)) {
+		unsigned int i;
+
+		for (i = 0; i < npages; ++i, start += PAGE_SIZE) {
+			unsigned long pfn;
+			int ret = follow_pfn(vma, start, &pfn);
+			if (ret)
+				return ret;
+
+			pages[i] = pfn_to_page(pfn);
+		}
+
+		if (i != npages) {
+			DRM_ERROR("failed to get user_pages.\n");
+			return -EINVAL;
+		}
+
+		return 0;
+	}
+
+	get_npages = get_user_pages(current, current->mm, start,
+					npages, 1, 1, pages, NULL);
+	get_npages = max(get_npages, 0);
+	if (get_npages != npages) {
+		DRM_ERROR("failed to get user_pages.\n");
+		while (get_npages)
+			put_page(pages[--get_npages]);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+void exynos_gem_put_pages_to_userptr(struct page **pages,
+					unsigned int npages,
+					struct vm_area_struct *vma)
+{
+	if (!vma_is_io(vma)) {
+		unsigned int i;
+
+		for (i = 0; i < npages; i++) {
+			set_page_dirty_lock(pages[i]);
+
+			/*
+			 * undo the reference we took when populating
+			 * the table.
+			 */
+			put_page(pages[i]);
+		}
+	}
+}
+
+int exynos_gem_map_sgt_with_dma(struct drm_device *drm_dev,
+				struct sg_table *sgt,
+				enum dma_data_direction dir)
+{
+	int nents;
+
+	mutex_lock(&drm_dev->struct_mutex);
+
+	nents = dma_map_sg(drm_dev->dev, sgt->sgl, sgt->nents, dir);
+	if (!nents) {
+		DRM_ERROR("failed to map sgl with dma.\n");
+		mutex_unlock(&drm_dev->struct_mutex);
+		return nents;
+	}
+
+	mutex_unlock(&drm_dev->struct_mutex);
+	return 0;
+}
+
+void exynos_gem_unmap_sgt_from_dma(struct drm_device *drm_dev,
+				struct sg_table *sgt,
+				enum dma_data_direction dir)
+{
+	dma_unmap_sg(drm_dev->dev, sgt->sgl, sgt->nents, dir);
+}
+
 int exynos_drm_gem_init_object(struct drm_gem_object *obj)
 {
 	DRM_DEBUG_KMS("%s\n", __FILE__);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 83d21ef1d1e9..4248d7fb698f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -35,22 +35,29 @@
  * exynos drm gem buffer structure.
  *
  * @kvaddr: kernel virtual address to allocated memory region.
+ * *userptr: user space address.
  * @dma_addr: bus address(accessed by dma) to allocated memory region.
  *	- this address could be physical address without IOMMU and
  *	device address with IOMMU.
+ * @write: whether pages will be written to by the caller.
  * @sgt: sg table to transfer page data.
  * @pages: contain all pages to allocated memory region.
  * @page_size: could be 4K, 64K or 1MB.
  * @size: size of allocated memory region.
+ * @pfnmap: indicate whether memory region from userptr is mmaped with
+ *	VM_PFNMAP or not.
  */
 struct exynos_drm_gem_buf {
 	void __iomem		*kvaddr;
+	unsigned long		userptr;
 	dma_addr_t		dma_addr;
 	struct dma_attrs	dma_attrs;
+	unsigned int		write;
 	struct sg_table		*sgt;
 	struct page		**pages;
 	unsigned long		page_size;
 	unsigned long		size;
+	bool			pfnmap;
 };
 
 /*
@@ -66,6 +73,7 @@ struct exynos_drm_gem_buf {
  *	or at framebuffer creation.
  * @size: size requested from user, in bytes and this size is aligned
  *	in page unit.
+ * @vma: a pointer to vm_area.
  * @flags: indicate memory type to allocated buffer and cache attruibute.
  *
  * P.S. this object would be transfered to user as kms_bo.handle so
@@ -75,6 +83,7 @@ struct exynos_drm_gem_obj {
 	struct drm_gem_object		base;
 	struct exynos_drm_gem_buf	*buffer;
 	unsigned long			size;
+	struct vm_area_struct		*vma;
 	unsigned int			flags;
 };
 
@@ -129,6 +138,10 @@ int exynos_drm_gem_map_offset_ioctl(struct drm_device *dev, void *data,
 int exynos_drm_gem_mmap_ioctl(struct drm_device *dev, void *data,
 			      struct drm_file *file_priv);
 
+/* map user space allocated by malloc to pages. */
+int exynos_drm_gem_userptr_ioctl(struct drm_device *dev, void *data,
+				      struct drm_file *file_priv);
+
 /* get buffer information to memory region allocated by gem. */
 int exynos_drm_gem_get_ioctl(struct drm_device *dev, void *data,
 				      struct drm_file *file_priv);
@@ -164,4 +177,36 @@ int exynos_drm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 /* set vm_flags and we can change the vm attribute to other one at here. */
 int exynos_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
 
+static inline int vma_is_io(struct vm_area_struct *vma)
+{
+	return !!(vma->vm_flags & (VM_IO | VM_PFNMAP));
+}
+
+/* get a copy of a virtual memory region. */
+struct vm_area_struct *exynos_gem_get_vma(struct vm_area_struct *vma);
+
+/* release a userspace virtual memory area. */
+void exynos_gem_put_vma(struct vm_area_struct *vma);
+
+/* get pages from user space. */
+int exynos_gem_get_pages_from_userptr(unsigned long start,
+						unsigned int npages,
+						struct page **pages,
+						struct vm_area_struct *vma);
+
+/* drop the reference to pages. */
+void exynos_gem_put_pages_to_userptr(struct page **pages,
+					unsigned int npages,
+					struct vm_area_struct *vma);
+
+/* map sgt with dma region. */
+int exynos_gem_map_sgt_with_dma(struct drm_device *drm_dev,
+				struct sg_table *sgt,
+				enum dma_data_direction dir);
+
+/* unmap sgt from dma region. */
+void exynos_gem_unmap_sgt_from_dma(struct drm_device *drm_dev,
+				struct sg_table *sgt,
+				enum dma_data_direction dir);
+
 #endif
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
index c0494d586e23..49f010f2b27f 100644
--- a/include/uapi/drm/exynos_drm.h
+++ b/include/uapi/drm/exynos_drm.h
@@ -133,17 +133,26 @@ struct drm_exynos_g2d_cmd {
 	__u32	data;
 };
 
+enum drm_exynos_g2d_buf_type {
+	G2D_BUF_USERPTR = 1 << 31,
+};
+
 enum drm_exynos_g2d_event_type {
 	G2D_EVENT_NOT,
 	G2D_EVENT_NONSTOP,
 	G2D_EVENT_STOP,		/* not yet */
 };
 
+struct drm_exynos_g2d_userptr {
+	unsigned long userptr;
+	unsigned long size;
+};
+
 struct drm_exynos_g2d_set_cmdlist {
 	__u64					cmd;
-	__u64					cmd_gem;
+	__u64					cmd_buf;
 	__u32					cmd_nr;
-	__u32					cmd_gem_nr;
+	__u32					cmd_buf_nr;
 
 	/* for g2d event */
 	__u64					event_type;
-- 
cgit v1.2.3-55-g7522


From cc248d4b1ddf05fefc1373d9d7a4dd1df71b6190 Mon Sep 17 00:00:00 2001
From: J. Bruce Fields
Date: Mon, 3 Dec 2012 16:11:13 -0500
Subject: svcrpc: don't byte-swap sk_reclen in place

Byte-swapping in place is always a little dubious.

Let's instead define this field to always be big-endian, and do the
swapping on demand where we need it.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svcsock.h | 12 +++++++++++-
 net/sunrpc/svcsock.c           | 26 +++++++++++---------------
 2 files changed, 22 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 92ad02f0dcc0..613cf42227aa 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -26,11 +26,21 @@ struct svc_sock {
 	void			(*sk_owspace)(struct sock *);
 
 	/* private TCP part */
-	u32			sk_reclen;	/* length of record */
+	__be32			sk_reclen;	/* length of record */
 	u32			sk_tcplen;	/* current read length */
 	struct page *		sk_pages[RPCSVC_MAXPAGES];	/* received data */
 };
 
+static inline u32 svc_sock_reclen(struct svc_sock *svsk)
+{
+	return ntohl(svsk->sk_reclen) & RPC_FRAGMENT_SIZE_MASK;
+}
+
+static inline u32 svc_sock_final_rec(struct svc_sock *svsk)
+{
+	return ntohl(svsk->sk_reclen) & RPC_LAST_STREAM_FRAGMENT;
+}
+
 /*
  * Function prototypes.
  */
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 03827cef1fa7..d50de2b95036 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -950,8 +950,7 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 			return -EAGAIN;
 		}
 
-		svsk->sk_reclen = ntohl(svsk->sk_reclen);
-		if (!(svsk->sk_reclen & RPC_LAST_STREAM_FRAGMENT)) {
+		if (!(svc_sock_final_rec(svsk))) {
 			/* FIXME: technically, a record can be fragmented,
 			 *  and non-terminal fragments will not have the top
 			 *  bit set in the fragment length header.
@@ -961,21 +960,18 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 			goto err_delete;
 		}
 
-		svsk->sk_reclen &= RPC_FRAGMENT_SIZE_MASK;
-		dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen);
-		if (svsk->sk_reclen > serv->sv_max_mesg) {
+		dprintk("svc: TCP record, %d bytes\n", svc_sock_reclen(svsk));
+		if (svc_sock_reclen(svsk) > serv->sv_max_mesg) {
 			net_notice_ratelimited("RPC: fragment too large: 0x%08lx\n",
-					       (unsigned long)svsk->sk_reclen);
+					(unsigned long)svc_sock_reclen(svsk));
 			goto err_delete;
 		}
 	}
 
-	if (svsk->sk_reclen < 8)
+	if (svc_sock_reclen(svsk) < 8)
 		goto err_delete; /* client is nuts. */
 
-	len = svsk->sk_reclen;
-
-	return len;
+	return svc_sock_reclen(svsk);
 error:
 	dprintk("RPC: TCP recv_record got %d\n", len);
 	return len;
@@ -1019,7 +1015,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 	if (dst->iov_len < src->iov_len)
 		return -EAGAIN; /* whatever; just giving up. */
 	memcpy(dst->iov_base, src->iov_base, src->iov_len);
-	xprt_complete_rqst(req->rq_task, svsk->sk_reclen);
+	xprt_complete_rqst(req->rq_task, rqstp->rq_arg.len);
 	rqstp->rq_arg.len = 0;
 	return 0;
 }
@@ -1064,12 +1060,12 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 		goto error;
 
 	base = svc_tcp_restore_pages(svsk, rqstp);
-	want = svsk->sk_reclen - base;
+	want = svc_sock_reclen(svsk) - base;
 
 	vec = rqstp->rq_vec;
 
 	pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0],
-						svsk->sk_reclen);
+						svc_sock_reclen(svsk));
 
 	rqstp->rq_respages = &rqstp->rq_pages[pnum];
 
@@ -1082,11 +1078,11 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 		if (len < 0 && len != -EAGAIN)
 			goto err_other;
 		dprintk("svc: incomplete TCP record (%d of %d)\n",
-			svsk->sk_tcplen, svsk->sk_reclen);
+			svsk->sk_tcplen, svc_sock_reclen(svsk));
 		goto err_noclose;
 	}
 
-	rqstp->rq_arg.len = svsk->sk_reclen;
+	rqstp->rq_arg.len = svc_sock_reclen(svsk);
 	rqstp->rq_arg.page_base = 0;
 	if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) {
 		rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len;
-- 
cgit v1.2.3-55-g7522


From 8af345f58ac9b350bb23c1457c613381d9f00472 Mon Sep 17 00:00:00 2001
From: J. Bruce Fields
Date: Mon, 3 Dec 2012 16:45:35 -0500
Subject: svcrpc: track rpc data length separately from sk_tcplen

Keep a separate field, sk_datalen, that tracks only the data contained
in a fragment, not including the fragment header.

For now, this is always just max(0, sk_tcplen - 4), but after we allow
multiple fragments sk_datalen will accumulate the total rpc data size
while sk_tcplen only tracks progress receiving the current fragment.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svcsock.h | 11 +++++++++--
 net/sunrpc/svcsock.c           | 19 ++++++++++++-------
 2 files changed, 21 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 613cf42227aa..62fd1b756e99 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -26,8 +26,15 @@ struct svc_sock {
 	void			(*sk_owspace)(struct sock *);
 
 	/* private TCP part */
-	__be32			sk_reclen;	/* length of record */
-	u32			sk_tcplen;	/* current read length */
+	/* On-the-wire fragment header: */
+	__be32			sk_reclen;
+	/* As we receive a record, this includes the length received so
+	 * far (including the fragment header): */
+	u32			sk_tcplen;
+	/* Total length of the data (not including fragment headers)
+	 * received so far in the fragments making up this rpc: */
+	u32			sk_datalen;
+
 	struct page *		sk_pages[RPCSVC_MAXPAGES];	/* received data */
 };
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 1db42b1ffe28..2b09e2306bfa 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -874,9 +874,9 @@ static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst
 {
 	unsigned int i, len, npages;
 
-	if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
+	if (svsk->sk_datalen == 0)
 		return 0;
-	len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
+	len = svsk->sk_datalen;
 	npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	for (i = 0; i < npages; i++) {
 		if (rqstp->rq_pages[i] != NULL)
@@ -893,9 +893,9 @@ static void svc_tcp_save_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
 {
 	unsigned int i, len, npages;
 
-	if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
+	if (svsk->sk_datalen == 0)
 		return;
-	len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
+	len = svsk->sk_datalen;
 	npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	for (i = 0; i < npages; i++) {
 		svsk->sk_pages[i] = rqstp->rq_pages[i];
@@ -907,9 +907,9 @@ static void svc_tcp_clear_pages(struct svc_sock *svsk)
 {
 	unsigned int i, len, npages;
 
-	if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
+	if (svsk->sk_datalen == 0)
 		goto out;
-	len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
+	len = svsk->sk_datalen;
 	npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	for (i = 0; i < npages; i++) {
 		BUG_ON(svsk->sk_pages[i] == NULL);
@@ -918,6 +918,7 @@ static void svc_tcp_clear_pages(struct svc_sock *svsk)
 	}
 out:
 	svsk->sk_tcplen = 0;
+	svsk->sk_datalen = 0;
 }
 
 /*
@@ -1066,8 +1067,10 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 
 	/* Now receive data */
 	len = svc_partial_recvfrom(rqstp, vec, pnum, want, base);
-	if (len >= 0)
+	if (len >= 0) {
 		svsk->sk_tcplen += len;
+		svsk->sk_datalen += len;
+	}
 	if (len != want) {
 		svc_tcp_save_pages(svsk, rqstp);
 		if (len < 0 && len != -EAGAIN)
@@ -1100,6 +1103,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 	/* Reset TCP read info */
 	svsk->sk_reclen = 0;
 	svsk->sk_tcplen = 0;
+	svsk->sk_datalen = 0;
 	/* If we have more data, signal svc_xprt_enqueue() to try again */
 	if (svc_recv_available(svsk) > sizeof(rpc_fraghdr))
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
@@ -1296,6 +1300,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 
 		svsk->sk_reclen = 0;
 		svsk->sk_tcplen = 0;
+		svsk->sk_datalen = 0;
 		memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages));
 
 		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
-- 
cgit v1.2.3-55-g7522


From d67b8c616b48df30e2836d797795f2420d109bc9 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Tue, 4 Dec 2012 01:13:35 +0000
Subject: netconf: advertise mc_forwarding status

This patch advertise the MC_FORWARDING status for IPv4 and IPv6.
This field is readonly, only multicast engine in the kernel updates it.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/inetdevice.h   |  3 +++
 include/net/addrconf.h       |  3 +++
 include/uapi/linux/netconf.h |  1 +
 net/ipv4/devinet.c           | 10 ++++++++--
 net/ipv4/ipmr.c              | 12 ++++++++++++
 net/ipv6/addrconf.c          | 10 ++++++++--
 net/ipv6/ip6mr.c             | 20 ++++++++++++++++++--
 7 files changed, 53 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index d032780d0ce5..a9d828976a77 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -171,6 +171,9 @@ struct in_ifaddr {
 extern int register_inetaddr_notifier(struct notifier_block *nb);
 extern int unregister_inetaddr_notifier(struct notifier_block *nb);
 
+extern void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
+					struct ipv4_devconf *devconf);
+
 extern struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref);
 static inline struct net_device *ip_dev_find(struct net *net, __be32 addr)
 {
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 9e63e76b20e7..df4ef9453384 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -172,6 +172,9 @@ extern bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
 extern int register_inet6addr_notifier(struct notifier_block *nb);
 extern int unregister_inet6addr_notifier(struct notifier_block *nb);
 
+extern void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
+					 struct ipv6_devconf *devconf);
+
 /**
  * __in6_dev_get - get inet6_dev pointer from netdevice
  * @dev: network device
diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
index 75dcbc587fb5..64804a798b0c 100644
--- a/include/uapi/linux/netconf.h
+++ b/include/uapi/linux/netconf.h
@@ -13,6 +13,7 @@ enum {
 	NETCONFA_IFINDEX,
 	NETCONFA_FORWARDING,
 	NETCONFA_RP_FILTER,
+	NETCONFA_MC_FORWARDING,
 	__NETCONFA_MAX
 };
 #define NETCONFA_MAX	(__NETCONFA_MAX - 1)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e13183abd7f6..cc06a47f1216 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1453,6 +1453,8 @@ static int inet_netconf_msgsize_devconf(int type)
 		size += nla_total_size(4);
 	if (type == -1 || type == NETCONFA_RP_FILTER)
 		size += nla_total_size(4);
+	if (type == -1 || type == NETCONFA_MC_FORWARDING)
+		size += nla_total_size(4);
 
 	return size;
 }
@@ -1485,6 +1487,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	    nla_put_s32(skb, NETCONFA_RP_FILTER,
 			IPV4_DEVCONF(*devconf, RP_FILTER)) < 0)
 		goto nla_put_failure;
+	if ((type == -1 || type == NETCONFA_MC_FORWARDING) &&
+	    nla_put_s32(skb, NETCONFA_MC_FORWARDING,
+			IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0)
+		goto nla_put_failure;
 
 	return nlmsg_end(skb, nlh);
 
@@ -1493,8 +1499,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
-					struct ipv4_devconf *devconf)
+void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
+				 struct ipv4_devconf *devconf)
 {
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 58e4160fdcee..0c452e3fdc1b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -65,6 +65,7 @@
 #include <net/checksum.h>
 #include <net/netlink.h>
 #include <net/fib_rules.h>
+#include <linux/netconf.h>
 
 #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
 #define CONFIG_IP_PIMSM	1
@@ -582,6 +583,9 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 	in_dev = __in_dev_get_rtnl(dev);
 	if (in_dev) {
 		IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--;
+		inet_netconf_notify_devconf(dev_net(dev),
+					    NETCONFA_MC_FORWARDING,
+					    dev->ifindex, &in_dev->cnf);
 		ip_rt_multicast_event(in_dev);
 	}
 
@@ -772,6 +776,8 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 		return -EADDRNOTAVAIL;
 	}
 	IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++;
+	inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, dev->ifindex,
+				    &in_dev->cnf);
 	ip_rt_multicast_event(in_dev);
 
 	/* Fill in the VIF structures */
@@ -1185,6 +1191,9 @@ static void mrtsock_destruct(struct sock *sk)
 	ipmr_for_each_table(mrt, net) {
 		if (sk == rtnl_dereference(mrt->mroute_sk)) {
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
+			inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+						    NETCONFA_IFINDEX_ALL,
+						    net->ipv4.devconf_all);
 			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
 			mroute_clean_tables(mrt);
 		}
@@ -1236,6 +1245,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		if (ret == 0) {
 			rcu_assign_pointer(mrt->mroute_sk, sk);
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)++;
+			inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+						    NETCONFA_IFINDEX_ALL,
+						    net->ipv4.devconf_all);
 		}
 		rtnl_unlock();
 		return ret;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 22ae75d54017..28e0e627229c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -469,6 +469,8 @@ static int inet6_netconf_msgsize_devconf(int type)
 	/* type -1 is used for ALL */
 	if (type == -1 || type == NETCONFA_FORWARDING)
 		size += nla_total_size(4);
+	if (type == -1 || type == NETCONFA_MC_FORWARDING)
+		size += nla_total_size(4);
 
 	return size;
 }
@@ -496,6 +498,10 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	if ((type == -1 || type == NETCONFA_FORWARDING) &&
 	    nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0)
 		goto nla_put_failure;
+	if ((type == -1 || type == NETCONFA_MC_FORWARDING) &&
+	    nla_put_s32(skb, NETCONFA_MC_FORWARDING,
+			devconf->mc_forwarding) < 0)
+		goto nla_put_failure;
 
 	return nlmsg_end(skb, nlh);
 
@@ -504,8 +510,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
-					 struct ipv6_devconf *devconf)
+void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
+				  struct ipv6_devconf *devconf)
 {
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 926ea544f499..1c05fe604d37 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -52,6 +52,7 @@
 #include <linux/netfilter_ipv6.h>
 #include <linux/export.h>
 #include <net/ip6_checksum.h>
+#include <linux/netconf.h>
 
 struct mr6_table {
 	struct list_head	list;
@@ -805,8 +806,12 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
 	dev_set_allmulti(dev, -1);
 
 	in6_dev = __in6_dev_get(dev);
-	if (in6_dev)
+	if (in6_dev) {
 		in6_dev->cnf.mc_forwarding--;
+		inet6_netconf_notify_devconf(dev_net(dev),
+					     NETCONFA_MC_FORWARDING,
+					     dev->ifindex, &in6_dev->cnf);
+	}
 
 	if (v->flags & MIFF_REGISTER)
 		unregister_netdevice_queue(dev, head);
@@ -958,8 +963,12 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
 	}
 
 	in6_dev = __in6_dev_get(dev);
-	if (in6_dev)
+	if (in6_dev) {
 		in6_dev->cnf.mc_forwarding++;
+		inet6_netconf_notify_devconf(dev_net(dev),
+					     NETCONFA_MC_FORWARDING,
+					     dev->ifindex, &in6_dev->cnf);
+	}
 
 	/*
 	 *	Fill in the VIF structures
@@ -1513,6 +1522,9 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
 	if (likely(mrt->mroute6_sk == NULL)) {
 		mrt->mroute6_sk = sk;
 		net->ipv6.devconf_all->mc_forwarding++;
+		inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+					     NETCONFA_IFINDEX_ALL,
+					     net->ipv6.devconf_all);
 	}
 	else
 		err = -EADDRINUSE;
@@ -1535,6 +1547,10 @@ int ip6mr_sk_done(struct sock *sk)
 			write_lock_bh(&mrt_lock);
 			mrt->mroute6_sk = NULL;
 			net->ipv6.devconf_all->mc_forwarding--;
+			inet6_netconf_notify_devconf(net,
+						     NETCONFA_MC_FORWARDING,
+						     NETCONFA_IFINDEX_ALL,
+						     net->ipv6.devconf_all);
 			write_unlock_bh(&mrt_lock);
 
 			mroute_clean_tables(mrt);
-- 
cgit v1.2.3-55-g7522


From adfa85e45dac616ff4f8bfceff1621ccafc0b1ff Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Tue, 4 Dec 2012 01:13:37 +0000
Subject: ipmr/ip6mr: advertise mfc stats via rtnetlink

These statistics can be checked only via /proc/net/ip_mr_cache or
SIOCGETSGCNT[_IN6] and thus only for the table RT_TABLE_DEFAULT.
Advertising them via rtnetlink allows to get statistics for all cache entries,
whatever the table is.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/rtnetlink.h | 7 +++++++
 net/ipv4/ipmr.c                | 7 +++++++
 net/ipv6/ip6mr.c               | 7 +++++++
 3 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 3dee071770d5..80abe27dc2a7 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -288,6 +288,7 @@ enum rtattr_type_t {
 	RTA_MP_ALGO, /* no longer used */
 	RTA_TABLE,
 	RTA_MARK,
+	RTA_MFC_STATS,
 	__RTA_MAX
 };
 
@@ -408,6 +409,12 @@ struct rta_session {
 	} u;
 };
 
+struct rta_mfc_stats {
+	__u64	mfcs_packets;
+	__u64	mfcs_bytes;
+	__u64	mfcs_wrong_if;
+};
+
 /****
  *		General form of address family dependent message.
  ****/
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 0c452e3fdc1b..c5617d646b93 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2046,6 +2046,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 	int ct;
 	struct rtnexthop *nhp;
 	struct nlattr *mp_attr;
+	struct rta_mfc_stats mfcs;
 
 	/* If cache is unresolved, don't try to parse IIF and OIF */
 	if (c->mfc_parent >= MAXVIFS)
@@ -2074,6 +2075,12 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 
 	nla_nest_end(skb, mp_attr);
 
+	mfcs.mfcs_packets = c->mfc_un.res.pkt;
+	mfcs.mfcs_bytes = c->mfc_un.res.bytes;
+	mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
+	if (nla_put(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0)
+		return -EMSGSIZE;
+
 	rtm->rtm_type = RTN_MULTICAST;
 	return 1;
 }
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 23f364a9efb5..4220a7b93386 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2120,6 +2120,7 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 	int ct;
 	struct rtnexthop *nhp;
 	struct nlattr *mp_attr;
+	struct rta_mfc_stats mfcs;
 
 	/* If cache is unresolved, don't try to parse IIF and OIF */
 	if (c->mf6c_parent >= MAXMIFS)
@@ -2149,6 +2150,12 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 
 	nla_nest_end(skb, mp_attr);
 
+	mfcs.mfcs_packets = c->mfc_un.res.pkt;
+	mfcs.mfcs_bytes = c->mfc_un.res.bytes;
+	mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
+	if (nla_put(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0)
+		return -EMSGSIZE;
+
 	rtm->rtm_type = RTN_MULTICAST;
 	return 1;
 }
-- 
cgit v1.2.3-55-g7522


From 9a68ac72a44ecb6d4dc4a7cadf45e1a2cd183885 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Tue, 4 Dec 2012 01:13:38 +0000
Subject: ipmr/ip6mr: report origin of mfc entry into rtnl msg

A mfc entry can be static or not (added via the mroute_sk socket). The patch
reports MFC_STATIC flag into rtm_protocol by setting rtm_protocol to
RTPROT_STATIC or RTPROT_MROUTED.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/rtnetlink.h | 1 +
 net/ipv4/ipmr.c                | 5 ++++-
 net/ipv6/ip6mr.c               | 5 ++++-
 3 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 80abe27dc2a7..33d29cea37ea 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -227,6 +227,7 @@ enum {
 #define RTPROT_XORP	14	/* XORP */
 #define RTPROT_NTK	15	/* Netsukuku */
 #define RTPROT_DHCP	16      /* DHCP client */
+#define RTPROT_MROUTED	17      /* Multicast daemon */
 
 /* rtm_scope
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c5617d646b93..91782a7634c2 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2169,7 +2169,10 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 		goto nla_put_failure;
 	rtm->rtm_type     = RTN_MULTICAST;
 	rtm->rtm_scope    = RT_SCOPE_UNIVERSE;
-	rtm->rtm_protocol = RTPROT_UNSPEC;
+	if (c->mfc_flags & MFC_STATIC)
+		rtm->rtm_protocol = RTPROT_STATIC;
+	else
+		rtm->rtm_protocol = RTPROT_MROUTED;
 	rtm->rtm_flags    = 0;
 
 	if (nla_put_be32(skb, RTA_SRC, c->mfc_origin) ||
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 4220a7b93386..d51b91122866 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2249,7 +2249,10 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 	if (nla_put_u32(skb, RTA_TABLE, mrt->id))
 		goto nla_put_failure;
 	rtm->rtm_scope    = RT_SCOPE_UNIVERSE;
-	rtm->rtm_protocol = RTPROT_UNSPEC;
+	if (c->mfc_flags & MFC_STATIC)
+		rtm->rtm_protocol = RTPROT_STATIC;
+	else
+		rtm->rtm_protocol = RTPROT_MROUTED;
 	rtm->rtm_flags    = 0;
 
 	if (nla_put(skb, RTA_SRC, 16, &c->mf6c_origin) ||
-- 
cgit v1.2.3-55-g7522


From 0ff8754981261a80f4b77db2536dfea92c2d4539 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger
Date: Tue, 4 Dec 2012 23:43:57 -0800
Subject: target: Add link_magic for fabric allow_link destination target_items

This patch adds [dev,lun]_link_magic value assignment + checks within generic
target_fabric_port_link() and target_fabric_mappedlun_link() code to ensure
destination config_item *target_item sent from configfs_symlink() ->
config_item_operations->allow_link() is the underlying se_device->dev_group
and se_lun->lun_group that we expect to symlink.

Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: stable@vger.kernel.org
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c          |  1 +
 drivers/target/target_core_fabric_configfs.c | 12 ++++++++++++
 drivers/target/target_core_tpg.c             |  1 +
 include/target/target_core_base.h            |  4 ++++
 4 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 3f604393d89c..e2695101bb99 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1352,6 +1352,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	if (!dev)
 		return NULL;
 
+	dev->dev_link_magic = SE_DEV_LINK_MAGIC;
 	dev->se_hba = hba;
 	dev->transport = hba->transport;
 
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index 9c6791734ee8..810263dfa4a1 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -70,6 +70,12 @@ static int target_fabric_mappedlun_link(
 	struct se_portal_group *se_tpg;
 	struct config_item *nacl_ci, *tpg_ci, *tpg_ci_s, *wwn_ci, *wwn_ci_s;
 	int ret = 0, lun_access;
+
+	if (lun->lun_link_magic != SE_LUN_LINK_MAGIC) {
+		pr_err("Bad lun->lun_link_magic, not a valid lun_ci pointer:"
+			" %p to struct lun: %p\n", lun_ci, lun);
+		return -EFAULT;
+	}
 	/*
 	 * Ensure that the source port exists
 	 */
@@ -742,6 +748,12 @@ static int target_fabric_port_link(
 	struct target_fabric_configfs *tf;
 	int ret;
 
+	if (dev->dev_link_magic != SE_DEV_LINK_MAGIC) {
+		pr_err("Bad dev->dev_link_magic, not a valid se_dev_ci pointer:"
+			" %p to struct se_device: %p\n", se_dev_ci, dev);
+		return -EFAULT;
+	}
+
 	tpg_ci = &lun_ci->ci_parent->ci_group->cg_item;
 	se_tpg = container_of(to_config_group(tpg_ci),
 				struct se_portal_group, tpg_group);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index d84cc0a8739e..0163309e2aba 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -669,6 +669,7 @@ int core_tpg_register(
 	for (i = 0; i < TRANSPORT_MAX_LUNS_PER_TPG; i++) {
 		lun = se_tpg->tpg_lun_list[i];
 		lun->unpacked_lun = i;
+		lun->lun_link_magic = SE_LUN_LINK_MAGIC;
 		lun->lun_status = TRANSPORT_LUN_STATUS_FREE;
 		atomic_set(&lun->lun_acl_count, 0);
 		init_completion(&lun->lun_shutdown_comp);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 645d90ac6097..1346ee04db5e 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -624,6 +624,8 @@ struct se_dev_stat_grps {
 };
 
 struct se_device {
+#define SE_DEV_LINK_MAGIC			0xfeeddeef
+	u32			dev_link_magic;
 	/* RELATIVE TARGET PORT IDENTIFER Counter */
 	u16			dev_rpti_counter;
 	/* Used for SAM Task Attribute ordering */
@@ -722,6 +724,8 @@ struct se_port_stat_grps {
 };
 
 struct se_lun {
+#define SE_LUN_LINK_MAGIC			0xffff7771
+	u32			lun_link_magic;
 	/* See transport_lun_status_table */
 	enum transport_lun_status_table lun_status;
 	u32			lun_access;
-- 
cgit v1.2.3-55-g7522


From 5b632fe85ec82e5c43740b52e74c66df50a37db3 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka
Date: Mon, 3 Dec 2012 12:56:33 +0100
Subject: mac80211: introduce IEEE80211_HW_TEARDOWN_AGGR_ON_BAR_FAIL

Commit f0425beda4d404a6e751439b562100b902ba9c98 "mac80211: retry sending
failed BAR frames later instead of tearing down aggr" caused regression
on rt2x00 hardware (connection hangs). This regression was fixed by
commit be03d4a45c09ee5100d3aaaedd087f19bc20d01 "rt2x00: Don't let
mac80211 send a BAR when an AMPDU subframe fails". But the latter
commit caused yet another problem reported in
https://bugzilla.kernel.org/show_bug.cgi?id=42828#c22

After long discussion in this thread:
http://mid.gmane.org/20121018075615.GA18212@redhat.com
and testing various alternative solutions, which failed on one or other
setup, we have no other good fix for the issues like just revert both
mentioned earlier commits.

To do not affect other hardware which benefit from commit
f0425beda4d404a6e751439b562100b902ba9c98, instead of reverting it,
introduce flag that when used will restore mac80211 behaviour before
the commit.

Cc: stable@vger.kernel.org
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
[replaced link with mid.gmane.org that has message-id]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 5 +++++
 net/mac80211/status.c  | 6 +++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 1c02fb3b3817..ee50c5eba50c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1369,6 +1369,10 @@ struct ieee80211_tx_control {
  * @IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF: Use the P2P Device address for any
  *	P2P Interface. This will be honoured even if more than one interface
  *	is supported.
+ *
+ * @IEEE80211_HW_TEARDOWN_AGGR_ON_BAR_FAIL: On this hardware TX BA session
+ *	should be tear down once BAR frame will not be acked.
+ *
  */
 enum ieee80211_hw_flags {
 	IEEE80211_HW_HAS_RATE_CONTROL			= 1<<0,
@@ -1397,6 +1401,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_TX_AMPDU_SETUP_IN_HW		= 1<<23,
 	IEEE80211_HW_SCAN_WHILE_IDLE			= 1<<24,
 	IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF		= 1<<25,
+	IEEE80211_HW_TEARDOWN_AGGR_ON_BAR_FAIL		= 1<<26,
 };
 
 /**
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 6400037dd8ec..04f6bf292a57 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -502,7 +502,11 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 				       IEEE80211_BAR_CTRL_TID_INFO_MASK) >>
 				      IEEE80211_BAR_CTRL_TID_INFO_SHIFT;
 
-				ieee80211_set_bar_pending(sta, tid, ssn);
+				if (local->hw.flags &
+				    IEEE80211_HW_TEARDOWN_AGGR_ON_BAR_FAIL)
+					ieee80211_stop_tx_ba_session(&sta->sta, tid);
+				else
+					ieee80211_set_bar_pending(sta, tid, ssn);
 			}
 		}
 
-- 
cgit v1.2.3-55-g7522


From d71f2f88825b31553881944959962b1871099e1f Mon Sep 17 00:00:00 2001
From: Rafael J. Wysocki
Date: Wed, 5 Dec 2012 11:59:22 +0100
Subject: ACPI / PM: Fix header of acpi_dev_pm_detach() in acpi.h

The header of acpi_dev_pm_detach() in include/linux/acpi.h has an
incorrect return type, which should be void.  Fix that.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 28ba643c92c1..79345cd5ac20 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -459,7 +459,7 @@ static inline int acpi_subsys_resume_early(struct device *dev) { return 0; }
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_PM)
 int acpi_dev_pm_attach(struct device *dev, bool power_on);
-int acpi_dev_pm_detach(struct device *dev, bool power_off);
+void acpi_dev_pm_detach(struct device *dev, bool power_off);
 #else
 static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
 {
-- 
cgit v1.2.3-55-g7522


From 01f218803757c9ec1152ac2fd39d03c27c452634 Mon Sep 17 00:00:00 2001
From: Michael S. Tsirkin
Date: Wed, 17 Oct 2012 18:06:02 +0200
Subject: kvm: add kvm_set_irq_inatomic

Add an API to inject IRQ from atomic context.
Return EWOULDBLOCK if impossible (e.g. for multicast).
Only MSI is supported ATM.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 include/linux/kvm_host.h |  1 +
 virt/kvm/irq_comm.c      | 83 +++++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 72 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8e5c7b651655..36c3704bfa7c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -693,6 +693,7 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic,
 				   unsigned long *deliver_bitmask);
 #endif
 int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level);
+int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level);
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
 		int irq_source_id, int level);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 2eb58af7ee99..656fa455e154 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -102,6 +102,23 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	return r;
 }
 
+static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+				   struct kvm_lapic_irq *irq)
+{
+	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+
+	irq->dest_id = (e->msi.address_lo &
+			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+	irq->vector = (e->msi.data &
+			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
+	irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
+	irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
+	irq->delivery_mode = e->msi.data & 0x700;
+	irq->level = 1;
+	irq->shorthand = 0;
+	/* TODO Deal with RH bit of MSI message address */
+}
+
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 		struct kvm *kvm, int irq_source_id, int level)
 {
@@ -110,22 +127,26 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	if (!level)
 		return -1;
 
-	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+	kvm_set_msi_irq(e, &irq);
 
-	irq.dest_id = (e->msi.address_lo &
-			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
-	irq.vector = (e->msi.data &
-			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
-	irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
-	irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
-	irq.delivery_mode = e->msi.data & 0x700;
-	irq.level = 1;
-	irq.shorthand = 0;
-
-	/* TODO Deal with RH bit of MSI message address */
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
+
+static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
+			 struct kvm *kvm)
+{
+	struct kvm_lapic_irq irq;
+	int r;
+
+	kvm_set_msi_irq(e, &irq);
+
+	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r))
+		return r;
+	else
+		return -EWOULDBLOCK;
+}
+
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
 {
 	struct kvm_kernel_irq_routing_entry route;
@@ -178,6 +199,44 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 	return ret;
 }
 
+/*
+ * Deliver an IRQ in an atomic context if we can, or return a failure,
+ * user can retry in a process context.
+ * Return value:
+ *  -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
+ *  Other values - No need to retry.
+ */
+int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
+{
+	struct kvm_kernel_irq_routing_entry *e;
+	int ret = -EINVAL;
+	struct kvm_irq_routing_table *irq_rt;
+	struct hlist_node *n;
+
+	trace_kvm_set_irq(irq, level, irq_source_id);
+
+	/*
+	 * Injection into either PIC or IOAPIC might need to scan all CPUs,
+	 * which would need to be retried from thread context;  when same GSI
+	 * is connected to both PIC and IOAPIC, we'd have to report a
+	 * partial failure here.
+	 * Since there's no easy way to do this, we only support injecting MSI
+	 * which is limited to 1:1 GSI mapping.
+	 */
+	rcu_read_lock();
+	irq_rt = rcu_dereference(kvm->irq_routing);
+	if (irq < irq_rt->nr_rt_entries)
+		hlist_for_each_entry(e, n, &irq_rt->map[irq], link) {
+			if (likely(e->type == KVM_IRQ_ROUTING_MSI))
+				ret = kvm_set_msi_inatomic(e, kvm);
+			else
+				ret = -EWOULDBLOCK;
+			break;
+		}
+	rcu_read_unlock();
+	return ret;
+}
+
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
 	struct kvm_irq_ack_notifier *kian;
-- 
cgit v1.2.3-55-g7522


From 8fa72d234da9b6b473bbb1f74d533663e4996e6b Mon Sep 17 00:00:00 2001
From: Jeff Moyer
Date: Wed, 5 Dec 2012 20:17:21 +0100
Subject: bdi: add a user-tunable cpu_list for the bdi flusher threads

In realtime environments, it may be desirable to keep the per-bdi
flusher threads from running on certain cpus.  This patch adds a
cpu_list file to /sys/class/bdi/* to enable this.  The default is to tie
the flusher threads to the same numa node as the backing device (though
I could be convinced to make it a mask of all cpus to avoid a change in
behaviour).

Thanks to Jeremy Eder for the original idea.

Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/backing-dev.h |  4 +++
 mm/backing-dev.c            | 84 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 88 insertions(+)

(limited to 'include')

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 2a9a9abc9126..238521a19849 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -18,6 +18,7 @@
 #include <linux/writeback.h>
 #include <linux/atomic.h>
 #include <linux/sysctl.h>
+#include <linux/mutex.h>
 
 struct page;
 struct device;
@@ -105,6 +106,9 @@ struct backing_dev_info {
 
 	struct timer_list laptop_mode_wb_timer;
 
+	cpumask_t *flusher_cpumask; /* used for writeback thread scheduling */
+	struct mutex flusher_cpumask_lock;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debug_dir;
 	struct dentry *debug_stats;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index d3ca2b3ee176..bd6a6cabef71 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/device.h>
+#include <linux/slab.h>
 #include <trace/events/writeback.h>
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
@@ -221,12 +222,63 @@ static ssize_t max_ratio_store(struct device *dev,
 }
 BDI_SHOW(max_ratio, bdi->max_ratio)
 
+static ssize_t cpu_list_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	struct bdi_writeback *wb = &bdi->wb;
+	cpumask_var_t newmask;
+	ssize_t ret;
+	struct task_struct *task;
+
+	if (!alloc_cpumask_var(&newmask, GFP_KERNEL))
+		return -ENOMEM;
+
+	ret = cpulist_parse(buf, newmask);
+	if (!ret) {
+		spin_lock_bh(&bdi->wb_lock);
+		task = wb->task;
+		if (task)
+			get_task_struct(task);
+		spin_unlock_bh(&bdi->wb_lock);
+
+		mutex_lock(&bdi->flusher_cpumask_lock);
+		if (task) {
+			ret = set_cpus_allowed_ptr(task, newmask);
+			put_task_struct(task);
+		}
+		if (ret == 0) {
+			cpumask_copy(bdi->flusher_cpumask, newmask);
+			ret = count;
+		}
+		mutex_unlock(&bdi->flusher_cpumask_lock);
+
+	}
+	free_cpumask_var(newmask);
+
+	return ret;
+}
+
+static ssize_t cpu_list_show(struct device *dev,
+		struct device_attribute *attr, char *page)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	ssize_t ret;
+
+	mutex_lock(&bdi->flusher_cpumask_lock);
+	ret = cpulist_scnprintf(page, PAGE_SIZE-1, bdi->flusher_cpumask);
+	mutex_unlock(&bdi->flusher_cpumask_lock);
+
+	return ret;
+}
+
 #define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
 
 static struct device_attribute bdi_dev_attrs[] = {
 	__ATTR_RW(read_ahead_kb),
 	__ATTR_RW(min_ratio),
 	__ATTR_RW(max_ratio),
+	__ATTR_RW(cpu_list),
 	__ATTR_NULL,
 };
 
@@ -428,6 +480,7 @@ static int bdi_forker_thread(void *ptr)
 				writeback_inodes_wb(&bdi->wb, 1024,
 						    WB_REASON_FORKER_THREAD);
 			} else {
+				int ret;
 				/*
 				 * The spinlock makes sure we do not lose
 				 * wake-ups when racing with 'bdi_queue_work()'.
@@ -437,6 +490,14 @@ static int bdi_forker_thread(void *ptr)
 				spin_lock_bh(&bdi->wb_lock);
 				bdi->wb.task = task;
 				spin_unlock_bh(&bdi->wb_lock);
+				mutex_lock(&bdi->flusher_cpumask_lock);
+				ret = set_cpus_allowed_ptr(task,
+							bdi->flusher_cpumask);
+				mutex_unlock(&bdi->flusher_cpumask_lock);
+				if (ret)
+					printk_once("%s: failed to bind flusher"
+						    " thread %s, error %d\n",
+						    __func__, task->comm, ret);
 				wake_up_process(task);
 			}
 			bdi_clear_pending(bdi);
@@ -509,6 +570,17 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 						dev_name(dev));
 		if (IS_ERR(wb->task))
 			return PTR_ERR(wb->task);
+	} else {
+		int node;
+		/*
+		 * Set up a default cpumask for the flusher threads that
+		 * includes all cpus on the same numa node as the device.
+		 * The mask may be overridden via sysfs.
+		 */
+		node = dev_to_node(bdi->dev);
+		if (node != NUMA_NO_NODE)
+			cpumask_copy(bdi->flusher_cpumask,
+				     cpumask_of_node(node));
 	}
 
 	bdi_debug_register(bdi, dev_name(dev));
@@ -634,6 +706,15 @@ int bdi_init(struct backing_dev_info *bdi)
 
 	bdi_wb_init(&bdi->wb, bdi);
 
+	if (!bdi_cap_flush_forker(bdi)) {
+		bdi->flusher_cpumask = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+		if (!bdi->flusher_cpumask)
+			return -ENOMEM;
+		cpumask_setall(bdi->flusher_cpumask);
+		mutex_init(&bdi->flusher_cpumask_lock);
+	} else
+		bdi->flusher_cpumask = NULL;
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
 		err = percpu_counter_init(&bdi->bdi_stat[i], 0);
 		if (err)
@@ -656,6 +737,7 @@ int bdi_init(struct backing_dev_info *bdi)
 err:
 		while (i--)
 			percpu_counter_destroy(&bdi->bdi_stat[i]);
+		kfree(bdi->flusher_cpumask);
 	}
 
 	return err;
@@ -683,6 +765,8 @@ void bdi_destroy(struct backing_dev_info *bdi)
 
 	bdi_unregister(bdi);
 
+	kfree(bdi->flusher_cpumask);
+
 	/*
 	 * If bdi_unregister() had already been called earlier, the
 	 * wakeup_timer could still be armed because bdi_prune_sb()
-- 
cgit v1.2.3-55-g7522


From 7793eeabc89fd342b96fdadce5a50c46ab77f3f9 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas
Date: Wed, 5 Dec 2012 13:51:17 -0700
Subject: PCI: Add and use standard PCI-X Capability register names

Add and use #defines for PCI-X Capability registers and fields.
Note that the PCI-X Capability has a different layout for
type 0 (endpoint) and type 1 (bridge) devices.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>---
 drivers/pci/probe.c           | 15 +++++++++------
 include/uapi/linux/pci_regs.h | 15 ++++++++++++++-
 2 files changed, 23 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ec909afa90b6..81d06676ce34 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -579,14 +579,16 @@ static void pci_set_bus_speed(struct pci_bus *bus)
 	if (pos) {
 		u16 status;
 		enum pci_bus_speed max;
-		pci_read_config_word(bridge, pos + 2, &status);
 
-		if (status & 0x8000) {
+		pci_read_config_word(bridge, pos + PCI_X_BRIDGE_SSTATUS,
+				     &status);
+
+		if (status & PCI_X_SSTATUS_533MHZ) {
 			max = PCI_SPEED_133MHz_PCIX_533;
-		} else if (status & 0x4000) {
+		} else if (status & PCI_X_SSTATUS_266MHZ) {
 			max = PCI_SPEED_133MHz_PCIX_266;
-		} else if (status & 0x0002) {
-			if (((status >> 12) & 0x3) == 2) {
+		} else if (status & PCI_X_SSTATUS_133MHZ) {
+			if ((status & PCI_X_SSTATUS_VERS) == PCI_X_SSTATUS_V2) {
 				max = PCI_SPEED_133MHz_PCIX_ECC;
 			} else {
 				max = PCI_SPEED_133MHz_PCIX;
@@ -596,7 +598,8 @@ static void pci_set_bus_speed(struct pci_bus *bus)
 		}
 
 		bus->max_bus_speed = max;
-		bus->cur_bus_speed = pcix_bus_speed[(status >> 6) & 0xf];
+		bus->cur_bus_speed = pcix_bus_speed[
+			(status & PCI_X_SSTATUS_FREQ) >> 6];
 
 		return;
 	}
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 20ae747ddf34..4cca834f9abd 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -349,7 +349,7 @@
 #define  PCI_AF_STATUS_TP	0x01
 #define PCI_CAP_AF_SIZEOF	6	/* size of AF registers */
 
-/* PCI-X registers */
+/* PCI-X registers (Type 0 (non-bridge) devices) */
 
 #define PCI_X_CMD		2	/* Modes & Features */
 #define  PCI_X_CMD_DPERR_E	0x0001	/* Data Parity Error Recovery Enable */
@@ -389,6 +389,19 @@
 #define PCI_CAP_PCIX_SIZEOF_V1	24	/* size for Version 1 */
 #define PCI_CAP_PCIX_SIZEOF_V2	PCI_CAP_PCIX_SIZEOF_V1	/* Same for v2 */
 
+/* PCI-X registers (Type 1 (bridge) devices) */
+
+#define PCI_X_BRIDGE_SSTATUS	2	/* Secondary Status */
+#define  PCI_X_SSTATUS_64BIT	0x0001	/* Secondary AD interface is 64 bits */
+#define  PCI_X_SSTATUS_133MHZ	0x0002	/* 133 MHz capable */
+#define  PCI_X_SSTATUS_FREQ	0x03c0	/* Secondary Bus Mode and Frequency */
+#define  PCI_X_SSTATUS_VERS	0x3000	/* PCI-X Capability Version */
+#define  PCI_X_SSTATUS_V1	0x1000	/* Mode 2, not Mode 1 */
+#define  PCI_X_SSTATUS_V2	0x2000	/* Mode 1 or Modes 1 and 2 */
+#define  PCI_X_SSTATUS_266MHZ	0x4000	/* 266 MHz capable */
+#define  PCI_X_SSTATUS_533MHZ	0x8000	/* 533 MHz capable */
+#define PCI_X_BRIDGE_STATUS	4	/* Bridge Status */
+
 /* PCI Bridge Subsystem ID registers */
 
 #define PCI_SSVID_VENDOR_ID     4	/* PCI-Bridge subsystem vendor id register */
-- 
cgit v1.2.3-55-g7522


From c2d3babfafbb9f6629cfb47139758e59a5eb0d80 Mon Sep 17 00:00:00 2001
From: David S. Miller
Date: Wed, 5 Dec 2012 16:24:45 -0500
Subject: bridge: implement multicast fast leave

V3: make it a flag
V2: make the toggle per-port

Fast leave allows bridge to immediately stops the multicast
traffic on the port receives IGMP Leave when IGMP snooping is enabled,
no timeouts are observed.

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
 include/uapi/linux/if_link.h |  1 +
 net/bridge/br_multicast.c    |  2 +-
 net/bridge/br_netlink.c      |  4 +++-
 net/bridge/br_private.h      |  2 +-
 net/bridge/br_sysfs_if.c     | 19 +------------------
 5 files changed, 7 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index bb58aeb7f34d..60f3b6b90602 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -218,6 +218,7 @@ enum {
 	IFLA_BRPORT_MODE,	/* mode (hairpin)          */
 	IFLA_BRPORT_GUARD,	/* bpdu guard              */
 	IFLA_BRPORT_PROTECT,	/* root port protection    */
+	IFLA_BRPORT_FAST_LEAVE,	/* multicast fast leave    */
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 2391bae4f733..a2a7a1a79081 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1225,7 +1225,7 @@ static void br_multicast_leave_group(struct net_bridge *br,
 	if (!mp)
 		goto out;
 
-	if (port && port->multicast_fast_leave) {
+	if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) {
 		struct net_bridge_port_group __rcu **pp;
 
 		for (pp = &mp->ports;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 65429b99a2a3..850b7d1f3a41 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -53,7 +53,8 @@ static int br_port_fill_attrs(struct sk_buff *skb,
 	    nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) ||
 	    nla_put_u8(skb, IFLA_BRPORT_MODE, mode) ||
 	    nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) ||
-	    nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)))
+	    nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) ||
+	    nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)))
 		return -EMSGSIZE;
 
 	return 0;
@@ -210,6 +211,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 
 	br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
 	br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
+	br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE);
 
 	if (tb[IFLA_BRPORT_COST]) {
 		err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index cdbf9047a659..cd86222cf5e3 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -137,11 +137,11 @@ struct net_bridge_port
 #define BR_HAIRPIN_MODE		0x00000001
 #define BR_BPDU_GUARD           0x00000002
 #define BR_ROOT_BLOCK		0x00000004
+#define BR_MULTICAST_FAST_LEAVE	0x00000008
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	u32				multicast_startup_queries_sent;
 	unsigned char			multicast_router;
-	unsigned char			multicast_fast_leave;
 	struct timer_list		multicast_router_timer;
 	struct timer_list		multicast_query_timer;
 	struct hlist_head		mglist;
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index dc484ace0be3..a1ef1b6e14dc 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -173,24 +173,7 @@ static int store_multicast_router(struct net_bridge_port *p,
 static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router,
 		   store_multicast_router);
 
-static ssize_t show_multicast_fast_leave(struct net_bridge_port *p,
-					 char *buf)
-{
-	return sprintf(buf, "%d\n", p->multicast_fast_leave);
-}
-
-static int store_multicast_fast_leave(struct net_bridge_port *p,
-				      unsigned long v)
-{
-	if (p->br->multicast_disabled)
-		return -EINVAL;
-
-	p->multicast_fast_leave = !!v;
-	return 0;
-}
-
-static BRPORT_ATTR(multicast_fast_leave, S_IRUGO | S_IWUSR,
-		   show_multicast_fast_leave, store_multicast_fast_leave);
+BRPORT_ATTR_FLAG(multicast_fast_leave, BR_MULTICAST_FAST_LEAVE);
 #endif
 
 static const struct brport_attribute *brport_attrs[] = {
-- 
cgit v1.2.3-55-g7522


From dd5fc854de5fd37adfcef8a366cd21a55aa01d3d Mon Sep 17 00:00:00 2001
From: Matthew Garrett
Date: Wed, 5 Dec 2012 14:33:26 -0700
Subject: EFI: Stash ROMs if they're not in the PCI BAR

EFI provides support for providing PCI ROMs via means other than the ROM
BAR. This support vanishes after we've exited boot services, so add support
for stashing copies of the ROMs in setup_data if they're not otherwise
available.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Seth Forshee <seth.forshee@canonical.com>---
 arch/x86/boot/compressed/eboot.c | 118 +++++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/bootparam.h |   1 +
 arch/x86/include/asm/pci.h       |  12 ++++
 include/linux/efi.h              |  71 +++++++++++++++++++++++
 4 files changed, 202 insertions(+)

(limited to 'include')

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c760e073963e..8a54313bc7dc 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -8,6 +8,7 @@
  * ----------------------------------------------------------------------- */
 
 #include <linux/efi.h>
+#include <linux/pci.h>
 #include <asm/efi.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
@@ -243,6 +244,121 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size)
 	*size = len;
 }
 
+static efi_status_t setup_efi_pci(struct boot_params *params)
+{
+	efi_pci_io_protocol *pci;
+	efi_status_t status;
+	void **pci_handle;
+	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+	unsigned long nr_pci, size = 0;
+	int i;
+	struct setup_data *data;
+
+	data = (struct setup_data *)params->hdr.setup_data;
+
+	while (data && data->next)
+		data = (struct setup_data *)data->next;
+
+	status = efi_call_phys5(sys_table->boottime->locate_handle,
+				EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+				NULL, &size, pci_handle);
+
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		status = efi_call_phys3(sys_table->boottime->allocate_pool,
+					EFI_LOADER_DATA, size, &pci_handle);
+
+		if (status != EFI_SUCCESS)
+			return status;
+
+		status = efi_call_phys5(sys_table->boottime->locate_handle,
+					EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+					NULL, &size, pci_handle);
+	}
+
+	if (status != EFI_SUCCESS)
+		goto free_handle;
+
+	nr_pci = size / sizeof(void *);
+	for (i = 0; i < nr_pci; i++) {
+		void *h = pci_handle[i];
+		uint64_t attributes;
+		struct pci_setup_rom *rom;
+
+		status = efi_call_phys3(sys_table->boottime->handle_protocol,
+					h, &pci_proto, &pci);
+
+		if (status != EFI_SUCCESS)
+			continue;
+
+		if (!pci)
+			continue;
+
+		status = efi_call_phys4(pci->attributes, pci,
+					EfiPciIoAttributeOperationGet, 0,
+					&attributes);
+
+		if (status != EFI_SUCCESS)
+			continue;
+
+		if (!attributes & EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM)
+			continue;
+
+		if (!pci->romimage || !pci->romsize)
+			continue;
+
+		size = pci->romsize + sizeof(*rom);
+
+		status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA, size, &rom);
+
+		if (status != EFI_SUCCESS)
+			continue;
+
+		rom->data.type = SETUP_PCI;
+		rom->data.len = size - sizeof(struct setup_data);
+		rom->data.next = 0;
+		rom->pcilen = pci->romsize;
+
+		status = efi_call_phys5(pci->pci.read, pci,
+					EfiPciIoWidthUint16, PCI_VENDOR_ID,
+					1, &(rom->vendor));
+
+		if (status != EFI_SUCCESS)
+			goto free_struct;
+
+		status = efi_call_phys5(pci->pci.read, pci,
+					EfiPciIoWidthUint16, PCI_DEVICE_ID,
+					1, &(rom->devid));
+
+		if (status != EFI_SUCCESS)
+			goto free_struct;
+
+		status = efi_call_phys5(pci->get_location, pci,
+					&(rom->segment), &(rom->bus),
+					&(rom->device), &(rom->function));
+
+		if (status != EFI_SUCCESS)
+			goto free_struct;
+
+		memcpy(rom->romdata, pci->romimage, pci->romsize);
+
+		if (data)
+			data->next = (uint64_t)rom;
+		else
+			params->hdr.setup_data = (uint64_t)rom;
+
+		data = (struct setup_data *)rom;
+
+		continue;
+	free_struct:
+		efi_call_phys1(sys_table->boottime->free_pool, rom);
+	}
+
+free_handle:
+	efi_call_phys1(sys_table->boottime->free_pool, pci_handle);
+	return status;
+}
+
 /*
  * See if we have Graphics Output Protocol
  */
@@ -1026,6 +1142,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 
 	setup_graphics(boot_params);
 
+	setup_efi_pci(boot_params);
+
 	status = efi_call_phys3(sys_table->boottime->allocate_pool,
 				EFI_LOADER_DATA, sizeof(*gdt),
 				(void **)&gdt);
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 2ad874cb661c..92862cd90201 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -13,6 +13,7 @@
 #define SETUP_NONE			0
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
+#define SETUP_PCI			3
 
 /* extensible setup data list node */
 struct setup_data {
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 6e41b9343928..dba7805176bf 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -171,4 +171,16 @@ cpumask_of_pcibus(const struct pci_bus *bus)
 }
 #endif
 
+struct pci_setup_rom {
+	struct setup_data data;
+	uint16_t vendor;
+	uint16_t devid;
+	uint64_t pcilen;
+	unsigned long segment;
+	unsigned long bus;
+	unsigned long device;
+	unsigned long function;
+	uint8_t romdata[0];
+};
+
 #endif /* _ASM_X86_PCI_H */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 8670eb1eb8cd..8eb1be17c801 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -196,6 +196,77 @@ typedef struct {
 	void *create_event_ex;
 } efi_boot_services_t;
 
+typedef enum {
+	EfiPciIoWidthUint8,
+	EfiPciIoWidthUint16,
+	EfiPciIoWidthUint32,
+	EfiPciIoWidthUint64,
+	EfiPciIoWidthFifoUint8,
+	EfiPciIoWidthFifoUint16,
+	EfiPciIoWidthFifoUint32,
+	EfiPciIoWidthFifoUint64,
+	EfiPciIoWidthFillUint8,
+	EfiPciIoWidthFillUint16,
+	EfiPciIoWidthFillUint32,
+	EfiPciIoWidthFillUint64,
+	EfiPciIoWidthMaximum
+} EFI_PCI_IO_PROTOCOL_WIDTH;
+
+typedef enum {
+	EfiPciIoAttributeOperationGet,
+	EfiPciIoAttributeOperationSet,
+	EfiPciIoAttributeOperationEnable,
+	EfiPciIoAttributeOperationDisable,
+	EfiPciIoAttributeOperationSupported,
+    EfiPciIoAttributeOperationMaximum
+} EFI_PCI_IO_PROTOCOL_ATTRIBUTE_OPERATION;
+
+
+typedef struct {
+	void *read;
+	void *write;
+} efi_pci_io_protocol_access_t;
+
+typedef struct {
+	void *poll_mem;
+	void *poll_io;
+	efi_pci_io_protocol_access_t mem;
+	efi_pci_io_protocol_access_t io;
+	efi_pci_io_protocol_access_t pci;
+	void *copy_mem;
+	void *map;
+	void *unmap;
+	void *allocate_buffer;
+	void *free_buffer;
+	void *flush;
+	void *get_location;
+	void *attributes;
+	void *get_bar_attributes;
+	void *set_bar_attributes;
+	uint64_t romsize;
+	void *romimage;
+} efi_pci_io_protocol;
+
+#define EFI_PCI_IO_ATTRIBUTE_ISA_MOTHERBOARD_IO 0x0001
+#define EFI_PCI_IO_ATTRIBUTE_ISA_IO 0x0002
+#define EFI_PCI_IO_ATTRIBUTE_VGA_PALETTE_IO 0x0004
+#define EFI_PCI_IO_ATTRIBUTE_VGA_MEMORY 0x0008
+#define EFI_PCI_IO_ATTRIBUTE_VGA_IO 0x0010
+#define EFI_PCI_IO_ATTRIBUTE_IDE_PRIMARY_IO 0x0020
+#define EFI_PCI_IO_ATTRIBUTE_IDE_SECONDARY_IO 0x0040
+#define EFI_PCI_IO_ATTRIBUTE_MEMORY_WRITE_COMBINE 0x0080
+#define EFI_PCI_IO_ATTRIBUTE_IO 0x0100
+#define EFI_PCI_IO_ATTRIBUTE_MEMORY 0x0200
+#define EFI_PCI_IO_ATTRIBUTE_BUS_MASTER 0x0400
+#define EFI_PCI_IO_ATTRIBUTE_MEMORY_CACHED 0x0800
+#define EFI_PCI_IO_ATTRIBUTE_MEMORY_DISABLE 0x1000
+#define EFI_PCI_IO_ATTRIBUTE_EMBEDDED_DEVICE 0x2000
+#define EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM 0x4000
+#define EFI_PCI_IO_ATTRIBUTE_DUAL_ADDRESS_CYCLE 0x8000
+#define EFI_PCI_IO_ATTRIBUTE_ISA_IO_16 0x10000
+#define EFI_PCI_IO_ATTRIBUTE_VGA_PALETTE_IO_16 0x20000
+#define EFI_PCI_IO_ATTRIBUTE_VGA_IO_16 0x40000
+
 /*
  * Types and defines for EFI ResetSystem
  */
-- 
cgit v1.2.3-55-g7522


From eca0d4676d8e29c209ddce0c0c1755472ffc70a6 Mon Sep 17 00:00:00 2001
From: Matthew Garrett
Date: Wed, 5 Dec 2012 14:33:27 -0700
Subject: PCI: Add pcibios_add_device

Platforms may want to provide architecture-specific functionality during
PCI enumeration. Add a pcibios_add_device() call that architectures can
override to do so.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Seth Forshee <seth.forshee@canonical.com>---
 drivers/pci/bus.c   |  5 +++++
 drivers/pci/pci.c   | 13 +++++++++++++
 include/linux/pci.h |  1 +
 3 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 6241fd05bd41..4f22fa16a3ba 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -170,6 +170,11 @@ int pci_bus_add_device(struct pci_dev *dev)
 	int retval;
 
 	pci_fixup_device(pci_fixup_final, dev);
+
+	retval = pcibios_add_device(dev);
+	if (retval)
+		return retval;
+
 	retval = device_add(&dev->dev);
 	if (retval)
 		return retval;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 54858838f098..fa0ddd51a216 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1333,6 +1333,19 @@ void pcim_pin_device(struct pci_dev *pdev)
 		dr->pinned = 1;
 }
 
+/*
+ * pcibios_add_device - provide arch specific hooks when adding device dev
+ * @dev: the PCI device being added
+ *
+ * Permits the platform to provide architecture specific functionality when
+ * devices are added. This is the default implementation. Architecture
+ * implementations can override this.
+ */
+int __weak pcibios_add_device (struct pci_dev *dev)
+{
+	return 0;
+}
+
 /**
  * pcibios_disable_device - disable arch specific PCI resources for device dev
  * @dev: the PCI device to disable
diff --git a/include/linux/pci.h b/include/linux/pci.h
index ee2179546c63..195c2593bd31 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1592,6 +1592,7 @@ void pcibios_disable_device(struct pci_dev *dev);
 void pcibios_set_master(struct pci_dev *dev);
 int pcibios_set_pcie_reset_state(struct pci_dev *dev,
 				 enum pcie_reset_state state);
+int pcibios_add_device(struct pci_dev *dev);
 
 #ifdef CONFIG_PCI_MMCONFIG
 extern void __init pci_mmcfg_early_init(void);
-- 
cgit v1.2.3-55-g7522


From 84c1b80e32638f881c17390dfe88143e5cd3f583 Mon Sep 17 00:00:00 2001
From: Matthew Garrett
Date: Wed, 5 Dec 2012 14:33:27 -0700
Subject: PCI: Add support for non-BAR ROMs

Platforms may provide their own mechanisms for obtaining ROMs. Add support
for using data provided by the platform in that case.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Seth Forshee <seth.forshee@canonical.com>---
 drivers/pci/rom.c   | 11 +++++++++--
 include/linux/pci.h |  2 ++
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index 0b3037ab8b93..3a3828fbc879 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -117,12 +117,18 @@ void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size)
 	loff_t start;
 	void __iomem *rom;
 
+	/*
+	 * Some devices may provide ROMs via a source other than the BAR
+	 */
+	if (pdev->rom && pdev->romlen) {
+		*size = pdev->romlen;
+		return phys_to_virt((phys_addr_t)pdev->rom);
 	/*
 	 * IORESOURCE_ROM_SHADOW set on x86, x86_64 and IA64 supports legacy
 	 * memory map if the VGA enable bit of the Bridge Control register is
 	 * set for embedded VGA.
 	 */
-	if (res->flags & IORESOURCE_ROM_SHADOW) {
+	} else if (res->flags & IORESOURCE_ROM_SHADOW) {
 		/* primary video rom always starts here */
 		start = (loff_t)0xC0000;
 		*size = 0x20000; /* cover C000:0 through E000:0 */
@@ -181,7 +187,8 @@ void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom)
 	if (res->flags & (IORESOURCE_ROM_COPY | IORESOURCE_ROM_BIOS_COPY))
 		return;
 
-	iounmap(rom);
+	if (!pdev->rom || !pdev->romlen)
+		iounmap(rom);
 
 	/* Disable again before continuing, leave enabled if pci=rom */
 	if (!(res->flags & (IORESOURCE_ROM_ENABLE | IORESOURCE_ROM_SHADOW)))
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 195c2593bd31..f116b2d859dc 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -333,6 +333,8 @@ struct pci_dev {
 	};
 	struct pci_ats	*ats;	/* Address Translation Service */
 #endif
+	void *rom; /* Physical pointer to ROM if it's not from the BAR */
+	size_t romlen; /* Length of ROM if it's not from the BAR */
 };
 
 static inline struct pci_dev *pci_physfn(struct pci_dev *dev)
-- 
cgit v1.2.3-55-g7522


From 161b96c383c442f4d7dabbb8500a5fbd551b344d Mon Sep 17 00:00:00 2001
From: Alexander Shiyan
Date: Wed, 7 Nov 2012 21:30:29 +0400
Subject: spi/clps711x: New SPI master driver

This patch add new driver for CLPS711X SPI master controller.
Due to platform limitations driver supports only 8 bit transfer mode.
Chip select control is handled via GPIO.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 drivers/spi/Kconfig                        |   7 +
 drivers/spi/Makefile                       |   1 +
 drivers/spi/spi-clps711x.c                 | 296 +++++++++++++++++++++++++++++
 include/linux/platform_data/spi-clps711x.h |  21 ++
 4 files changed, 325 insertions(+)
 create mode 100644 drivers/spi/spi-clps711x.c
 create mode 100644 include/linux/platform_data/spi-clps711x.h

(limited to 'include')

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 1acae359cabe..2a13e637e46b 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -123,6 +123,13 @@ config SPI_BUTTERFLY
 	  inexpensive battery powered microcontroller evaluation board.
 	  This same cable can be used to flash new firmware.
 
+config SPI_CLPS711X
+	tristate "CLPS711X host SPI controller"
+	depends on ARCH_CLPS711X
+	help
+	  This enables dedicated general purpose SPI/Microwire1-compatible
+	  master mode interface (SSI1) for CLPS711X-based CPUs.
+
 config SPI_COLDFIRE_QSPI
 	tristate "Freescale Coldfire QSPI controller"
 	depends on (M520x || M523x || M5249 || M525x || M527x || M528x || M532x)
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index c48df47e4b0f..25ab4a1cd014 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_SPI_BFIN5XX)		+= spi-bfin5xx.o
 obj-$(CONFIG_SPI_BFIN_SPORT)		+= spi-bfin-sport.o
 obj-$(CONFIG_SPI_BITBANG)		+= spi-bitbang.o
 obj-$(CONFIG_SPI_BUTTERFLY)		+= spi-butterfly.o
+obj-$(CONFIG_SPI_CLPS711X)		+= spi-clps711x.o
 obj-$(CONFIG_SPI_COLDFIRE_QSPI)		+= spi-coldfire-qspi.o
 obj-$(CONFIG_SPI_DAVINCI)		+= spi-davinci.o
 obj-$(CONFIG_SPI_DESIGNWARE)		+= spi-dw.o
diff --git a/drivers/spi/spi-clps711x.c b/drivers/spi/spi-clps711x.c
new file mode 100644
index 000000000000..59677eb30f94
--- /dev/null
+++ b/drivers/spi/spi-clps711x.c
@@ -0,0 +1,296 @@
+/*
+ *  CLPS711X SPI bus driver
+ *
+ *  Copyright (C) 2012 Alexander Shiyan <shc_work@mail.ru>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/platform_data/spi-clps711x.h>
+
+#include <mach/hardware.h>
+
+#define DRIVER_NAME	"spi-clps711x"
+
+struct spi_clps711x_data {
+	struct completion	done;
+
+	struct clk		*spi_clk;
+	u32			max_speed_hz;
+
+	u8			*tx_buf;
+	u8			*rx_buf;
+	int			count;
+	int			len;
+
+	int			chipselect[0];
+};
+
+static int spi_clps711x_setup(struct spi_device *spi)
+{
+	struct spi_clps711x_data *hw = spi_master_get_devdata(spi->master);
+
+	if (spi->bits_per_word != 8) {
+		dev_err(&spi->dev, "Unsupported master bus width %i\n",
+			spi->bits_per_word);
+		return -EINVAL;
+	}
+
+	/* We are expect that SPI-device is not selected */
+	gpio_direction_output(hw->chipselect[spi->chip_select],
+			      !(spi->mode & SPI_CS_HIGH));
+
+	return 0;
+}
+
+static void spi_clps711x_setup_mode(struct spi_device *spi)
+{
+	/* Setup edge for transfer */
+	if (spi->mode & SPI_CPHA)
+		clps_writew(clps_readw(SYSCON3) | SYSCON3_ADCCKNSEN, SYSCON3);
+	else
+		clps_writew(clps_readw(SYSCON3) & ~SYSCON3_ADCCKNSEN, SYSCON3);
+}
+
+static int spi_clps711x_setup_xfer(struct spi_device *spi,
+				   struct spi_transfer *xfer)
+{
+	u32 speed = xfer->speed_hz ? : spi->max_speed_hz;
+	u8 bpw = xfer->bits_per_word ? : spi->bits_per_word;
+	struct spi_clps711x_data *hw = spi_master_get_devdata(spi->master);
+
+	if (bpw != 8) {
+		dev_err(&spi->dev, "Unsupported master bus width %i\n", bpw);
+		return -EINVAL;
+	}
+
+	/* Setup SPI frequency divider */
+	if (!speed || (speed >= hw->max_speed_hz))
+		clps_writel((clps_readl(SYSCON1) & ~SYSCON1_ADCKSEL_MASK) |
+			    SYSCON1_ADCKSEL(3), SYSCON1);
+	else if (speed >= (hw->max_speed_hz / 2))
+		clps_writel((clps_readl(SYSCON1) & ~SYSCON1_ADCKSEL_MASK) |
+			    SYSCON1_ADCKSEL(2), SYSCON1);
+	else if (speed >= (hw->max_speed_hz / 8))
+		clps_writel((clps_readl(SYSCON1) & ~SYSCON1_ADCKSEL_MASK) |
+			    SYSCON1_ADCKSEL(1), SYSCON1);
+	else
+		clps_writel((clps_readl(SYSCON1) & ~SYSCON1_ADCKSEL_MASK) |
+			    SYSCON1_ADCKSEL(0), SYSCON1);
+
+	return 0;
+}
+
+static int spi_clps711x_transfer_one_message(struct spi_master *master,
+					     struct spi_message *msg)
+{
+	struct spi_clps711x_data *hw = spi_master_get_devdata(master);
+	struct spi_transfer *xfer;
+	int status = 0, cs = hw->chipselect[msg->spi->chip_select];
+	u32 data;
+
+	spi_clps711x_setup_mode(msg->spi);
+
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		if (spi_clps711x_setup_xfer(msg->spi, xfer)) {
+			status = -EINVAL;
+			goto out_xfr;
+		}
+
+		gpio_set_value(cs, !!(msg->spi->mode & SPI_CS_HIGH));
+
+		INIT_COMPLETION(hw->done);
+
+		hw->count = 0;
+		hw->len = xfer->len;
+		hw->tx_buf = (u8 *)xfer->tx_buf;
+		hw->rx_buf = (u8 *)xfer->rx_buf;
+
+		/* Initiate transfer */
+		data = hw->tx_buf ? hw->tx_buf[hw->count] : 0;
+		clps_writel(data | SYNCIO_FRMLEN(8) | SYNCIO_TXFRMEN, SYNCIO);
+
+		wait_for_completion(&hw->done);
+
+		if (xfer->delay_usecs)
+			udelay(xfer->delay_usecs);
+
+		if (xfer->cs_change ||
+		    list_is_last(&xfer->transfer_list, &msg->transfers))
+			gpio_set_value(cs, !(msg->spi->mode & SPI_CS_HIGH));
+
+		msg->actual_length += xfer->len;
+	}
+
+out_xfr:
+	msg->status = status;
+	spi_finalize_current_message(master);
+
+	return 0;
+}
+
+static irqreturn_t spi_clps711x_isr(int irq, void *dev_id)
+{
+	struct spi_clps711x_data *hw = (struct spi_clps711x_data *)dev_id;
+	u32 data;
+
+	/* Handle RX */
+	data = clps_readb(SYNCIO);
+	if (hw->rx_buf)
+		hw->rx_buf[hw->count] = (u8)data;
+
+	hw->count++;
+
+	/* Handle TX */
+	if (hw->count < hw->len) {
+		data = hw->tx_buf ? hw->tx_buf[hw->count] : 0;
+		clps_writel(data | SYNCIO_FRMLEN(8) | SYNCIO_TXFRMEN, SYNCIO);
+	} else
+		complete(&hw->done);
+
+	return IRQ_HANDLED;
+}
+
+static int __devinit spi_clps711x_probe(struct platform_device *pdev)
+{
+	int i, ret;
+	struct spi_master *master;
+	struct spi_clps711x_data *hw;
+	struct spi_clps711x_pdata *pdata = dev_get_platdata(&pdev->dev);
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "No platform data supplied\n");
+		return -EINVAL;
+	}
+
+	if (pdata->num_chipselect < 1) {
+		dev_err(&pdev->dev, "At least one CS must be defined\n");
+		return -EINVAL;
+	}
+
+	master = spi_alloc_master(&pdev->dev,
+				  sizeof(struct spi_clps711x_data) +
+				  sizeof(int) * pdata->num_chipselect);
+	if (!master) {
+		dev_err(&pdev->dev, "SPI allocating memory error\n");
+		return -ENOMEM;
+	}
+
+	master->bus_num = pdev->id;
+	master->mode_bits = SPI_CPHA | SPI_CS_HIGH;
+	master->num_chipselect = pdata->num_chipselect;
+	master->setup = spi_clps711x_setup;
+	master->transfer_one_message = spi_clps711x_transfer_one_message;
+
+	hw = spi_master_get_devdata(master);
+
+	for (i = 0; i < master->num_chipselect; i++) {
+		hw->chipselect[i] = pdata->chipselect[i];
+		if (!gpio_is_valid(hw->chipselect[i])) {
+			dev_err(&pdev->dev, "Invalid CS GPIO %i\n", i);
+			ret = -EINVAL;
+			goto err_out;
+		}
+		if (gpio_request(hw->chipselect[i], DRIVER_NAME)) {
+			dev_err(&pdev->dev, "Can't get CS GPIO %i\n", i);
+			ret = -EINVAL;
+			goto err_out;
+		}
+	}
+
+	hw->spi_clk = devm_clk_get(&pdev->dev, "spi");
+	if (IS_ERR(hw->spi_clk)) {
+		dev_err(&pdev->dev, "Can't get clocks\n");
+		ret = PTR_ERR(hw->spi_clk);
+		goto err_out;
+	}
+	hw->max_speed_hz = clk_get_rate(hw->spi_clk);
+
+	init_completion(&hw->done);
+	platform_set_drvdata(pdev, master);
+
+	/* Disable extended mode due hardware problems */
+	clps_writew(clps_readw(SYSCON3) & ~SYSCON3_ADCCON, SYSCON3);
+
+	/* Clear possible pending interrupt */
+	clps_readl(SYNCIO);
+
+	ret = devm_request_irq(&pdev->dev, IRQ_SSEOTI, spi_clps711x_isr, 0,
+			       dev_name(&pdev->dev), hw);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't request IRQ\n");
+		clk_put(hw->spi_clk);
+		goto clk_out;
+	}
+
+	ret = spi_register_master(master);
+	if (!ret) {
+		dev_info(&pdev->dev,
+			 "SPI bus driver initialized. Master clock %u Hz\n",
+			 hw->max_speed_hz);
+		return 0;
+	}
+
+	dev_err(&pdev->dev, "Failed to register master\n");
+	devm_free_irq(&pdev->dev, IRQ_SSEOTI, hw);
+
+clk_out:
+	devm_clk_put(&pdev->dev, hw->spi_clk);
+
+err_out:
+	while (--i >= 0)
+		if (gpio_is_valid(hw->chipselect[i]))
+			gpio_free(hw->chipselect[i]);
+
+	platform_set_drvdata(pdev, NULL);
+	spi_master_put(master);
+	kfree(master);
+
+	return ret;
+}
+
+static int __devexit spi_clps711x_remove(struct platform_device *pdev)
+{
+	int i;
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_clps711x_data *hw = spi_master_get_devdata(master);
+
+	devm_free_irq(&pdev->dev, IRQ_SSEOTI, hw);
+
+	for (i = 0; i < master->num_chipselect; i++)
+		if (gpio_is_valid(hw->chipselect[i]))
+			gpio_free(hw->chipselect[i]);
+
+	devm_clk_put(&pdev->dev, hw->spi_clk);
+	platform_set_drvdata(pdev, NULL);
+	spi_unregister_master(master);
+	kfree(master);
+
+	return 0;
+}
+
+static struct platform_driver clps711x_spi_driver = {
+	.driver	= {
+		.name	= DRIVER_NAME,
+		.owner	= THIS_MODULE,
+	},
+	.probe	= spi_clps711x_probe,
+	.remove	= __devexit_p(spi_clps711x_remove),
+};
+module_platform_driver(clps711x_spi_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Alexander Shiyan <shc_work@mail.ru>");
+MODULE_DESCRIPTION("CLPS711X SPI bus driver");
diff --git a/include/linux/platform_data/spi-clps711x.h b/include/linux/platform_data/spi-clps711x.h
new file mode 100644
index 000000000000..301956e63143
--- /dev/null
+++ b/include/linux/platform_data/spi-clps711x.h
@@ -0,0 +1,21 @@
+/*
+ *  CLPS711X SPI bus driver definitions
+ *
+ *  Copyright (C) 2012 Alexander Shiyan <shc_work@mail.ru>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef ____LINUX_PLATFORM_DATA_SPI_CLPS711X_H
+#define ____LINUX_PLATFORM_DATA_SPI_CLPS711X_H
+
+/* Board specific platform_data */
+struct spi_clps711x_pdata {
+	int *chipselect;	/* Array of GPIO-numbers */
+	int num_chipselect;	/* Total count of GPIOs */
+};
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 464ee9f966404786ba4c6be35dc8362ee8e6ba4e Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Tue, 20 Nov 2012 12:49:27 -0500
Subject: NFSv4.1: Ensure that the client tracks the server
 target_highest_slotid

Dynamic slot allocation in NFSv4.1 depends on the client being able to
track the server's target value for the highest slotid in the
slot table.  See the reference in Section 2.10.6.1 of RFC5661.

To avoid ordering problems in the case where 2 SEQUENCE replies contain
conflicting updates to this target value, we also introduce a generation
counter, to track whether or not an RPC containing a SEQUENCE operation
was launched before or after the last update.

Also rename the nfs4_slot_table target_max_slots field to
'target_highest_slotid' to avoid confusion with a slot
table size or number of slots.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/callback_proc.c    |  2 +-
 fs/nfs/nfs4proc.c         | 25 +++++++++++++++++++++++++
 fs/nfs/nfs4state.c        |  7 +++----
 fs/nfs/nfs4xdr.c          |  4 ++--
 include/linux/nfs_fs_sb.h |  5 +++--
 include/linux/nfs_xdr.h   |  2 ++
 6 files changed, 36 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 0be08b964f38..0ef047b7d28d 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -576,7 +576,7 @@ __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy,
 	if (args->crsa_target_max_slots == fc_tbl->max_slots)
 		goto out;
 
-	fc_tbl->target_max_slots = args->crsa_target_max_slots;
+	fc_tbl->target_highest_slotid = args->crsa_target_max_slots;
 	nfs41_handle_recall_slot(cps->clp);
 out:
 	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 197ef3e4e1f7..d91abaa522e8 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -488,6 +488,28 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 	res->sr_slot = NULL;
 }
 
+/* Update the client's idea of target_highest_slotid */
+static void nfs41_set_target_slotid_locked(struct nfs4_slot_table *tbl,
+		u32 target_highest_slotid)
+{
+	if (tbl->target_highest_slotid == target_highest_slotid)
+		return;
+	tbl->target_highest_slotid = target_highest_slotid;
+	tbl->generation++;
+}
+
+static void nfs41_update_target_slotid(struct nfs4_slot_table *tbl,
+		struct nfs4_slot *slot,
+		struct nfs4_sequence_res *res)
+{
+	spin_lock(&tbl->slot_tbl_lock);
+	if (tbl->generation != slot->generation)
+		goto out;
+	nfs41_set_target_slotid_locked(tbl, res->sr_target_highest_slotid);
+out:
+	spin_unlock(&tbl->slot_tbl_lock);
+}
+
 static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
 	struct nfs4_session *session;
@@ -522,6 +544,7 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 		/* Check sequence flags */
 		if (res->sr_status_flags != 0)
 			nfs4_schedule_lease_recovery(clp);
+		nfs41_update_target_slotid(slot->table, slot, res);
 		break;
 	case -NFS4ERR_DELAY:
 		/* The server detected a resend of the RPC call and
@@ -583,6 +606,7 @@ static struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl)
 		tbl->highest_used_slotid = slotid;
 	ret = &tbl->slots[slotid];
 	ret->renewal_time = jiffies;
+	ret->generation = tbl->generation;
 
 out:
 	dprintk("<-- %s used_slots=%04lx highest_used=%d slotid=%d \n",
@@ -5693,6 +5717,7 @@ static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl,
 		tbl->max_slots = max_slots;
 	}
 	tbl->highest_used_slotid = NFS4_NO_SLOT;
+	tbl->target_highest_slotid = max_slots - 1;
 	for (i = 0; i < tbl->max_slots; i++)
 		tbl->slots[i].seq_nr = ivalue;
 	spin_unlock(&tbl->slot_tbl_lock);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9495789c425b..842cb8c2f65d 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2033,17 +2033,16 @@ static int nfs4_recall_slot(struct nfs_client *clp)
 		return 0;
 	nfs4_begin_drain_session(clp);
 	fc_tbl = &clp->cl_session->fc_slot_table;
-	new = nfs4_alloc_slots(fc_tbl, fc_tbl->target_max_slots, GFP_NOFS);
+	new = nfs4_alloc_slots(fc_tbl, fc_tbl->target_highest_slotid + 1, GFP_NOFS);
         if (!new)
 		return -ENOMEM;
 
 	spin_lock(&fc_tbl->slot_tbl_lock);
-	for (i = 0; i < fc_tbl->target_max_slots; i++)
+	for (i = 0; i <= fc_tbl->target_highest_slotid; i++)
 		new[i].seq_nr = fc_tbl->slots[i].seq_nr;
 	old = fc_tbl->slots;
 	fc_tbl->slots = new;
-	fc_tbl->max_slots = fc_tbl->target_max_slots;
-	fc_tbl->target_max_slots = 0;
+	fc_tbl->max_slots = fc_tbl->target_highest_slotid + 1;
 	clp->cl_session->fc_attrs.max_reqs = fc_tbl->max_slots;
 	spin_unlock(&fc_tbl->slot_tbl_lock);
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 27b0fec1a6b0..05d34f1fcc19 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -5552,8 +5552,8 @@ static int decode_sequence(struct xdr_stream *xdr,
 	}
 	/* highest slot id - currently not processed */
 	dummy = be32_to_cpup(p++);
-	/* target highest slot id - currently not processed */
-	dummy = be32_to_cpup(p++);
+	/* target highest slot id */
+	res->sr_target_highest_slotid = be32_to_cpup(p++);
 	/* result flags */
 	res->sr_status_flags = be32_to_cpup(p);
 	status = 0;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index b0412873d29c..57d406997def 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -217,8 +217,9 @@ struct nfs4_slot_table {
 	u32		max_slots;		/* # slots in table */
 	u32		highest_used_slotid;	/* sent to server on each SEQ.
 						 * op for dynamic resizing */
-	u32		target_max_slots;	/* Set by CB_RECALL_SLOT as
-						 * the new max_slots */
+	u32		target_highest_slotid;	/* Server max_slot target */
+	unsigned long	generation;		/* Generation counter for
+						   target_highest_slotid */
 	struct completion complete;
 };
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index deb31bbbb857..08c47db7417f 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -188,6 +188,7 @@ struct nfs4_channel_attrs {
 /* nfs41 sessions slot seqid */
 struct nfs4_slot {
 	struct nfs4_slot_table	*table;
+	unsigned long		generation;
 	unsigned long		renewal_time;
 	u32			slot_nr;
 	u32		 	seq_nr;
@@ -202,6 +203,7 @@ struct nfs4_sequence_res {
 	struct nfs4_slot	*sr_slot;	/* slot used to send request */
 	int			sr_status;	/* sequence operation status */
 	u32			sr_status_flags;
+	u32			sr_target_highest_slotid;
 };
 
 struct nfs4_get_lease_time_args {
-- 
cgit v1.2.3-55-g7522


From da0507b7c95ccd4d9c86394eef42fe076032af30 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Tue, 20 Nov 2012 18:10:30 -0500
Subject: NFSv4.1: Reset the sequence number for slots that have been
 deallocated

When the server tells us that it is dynamically resizing the session
replay cache, we should reset the sequence number for those slots
that have been deallocated.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c         | 18 ++++++++++++++++++
 fs/nfs/nfs4xdr.c          |  4 ++--
 include/linux/nfs_fs_sb.h |  1 +
 include/linux/nfs_xdr.h   |  1 +
 4 files changed, 22 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d91abaa522e8..52435ec44193 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -498,6 +498,22 @@ static void nfs41_set_target_slotid_locked(struct nfs4_slot_table *tbl,
 	tbl->generation++;
 }
 
+static void nfs41_set_server_slotid_locked(struct nfs4_slot_table *tbl,
+		u32 highest_slotid)
+{
+	unsigned int max_slotid, i;
+
+	if (tbl->server_highest_slotid == highest_slotid)
+		return;
+	if (tbl->highest_used_slotid > highest_slotid)
+		return;
+	max_slotid = min(tbl->max_slots - 1, highest_slotid);
+	/* Reset the seq_nr for deallocated slots */
+	for (i = tbl->server_highest_slotid + 1; i <= max_slotid; i++)
+		tbl->slots[i].seq_nr = 1;
+	tbl->server_highest_slotid = highest_slotid;
+}
+
 static void nfs41_update_target_slotid(struct nfs4_slot_table *tbl,
 		struct nfs4_slot *slot,
 		struct nfs4_sequence_res *res)
@@ -505,6 +521,7 @@ static void nfs41_update_target_slotid(struct nfs4_slot_table *tbl,
 	spin_lock(&tbl->slot_tbl_lock);
 	if (tbl->generation != slot->generation)
 		goto out;
+	nfs41_set_server_slotid_locked(tbl, res->sr_highest_slotid);
 	nfs41_set_target_slotid_locked(tbl, res->sr_target_highest_slotid);
 out:
 	spin_unlock(&tbl->slot_tbl_lock);
@@ -5718,6 +5735,7 @@ static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl,
 	}
 	tbl->highest_used_slotid = NFS4_NO_SLOT;
 	tbl->target_highest_slotid = max_slots - 1;
+	tbl->server_highest_slotid = max_slots - 1;
 	for (i = 0; i < tbl->max_slots; i++)
 		tbl->slots[i].seq_nr = ivalue;
 	spin_unlock(&tbl->slot_tbl_lock);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 05d34f1fcc19..a67040f51597 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -5550,8 +5550,8 @@ static int decode_sequence(struct xdr_stream *xdr,
 		dprintk("%s Invalid slot id\n", __func__);
 		goto out_err;
 	}
-	/* highest slot id - currently not processed */
-	dummy = be32_to_cpup(p++);
+	/* highest slot id */
+	res->sr_highest_slotid = be32_to_cpup(p++);
 	/* target highest slot id */
 	res->sr_target_highest_slotid = be32_to_cpup(p++);
 	/* result flags */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 57d406997def..646e64bbff4c 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -218,6 +218,7 @@ struct nfs4_slot_table {
 	u32		highest_used_slotid;	/* sent to server on each SEQ.
 						 * op for dynamic resizing */
 	u32		target_highest_slotid;	/* Server max_slot target */
+	u32		server_highest_slotid;	/* Server highest slotid */
 	unsigned long	generation;		/* Generation counter for
 						   target_highest_slotid */
 	struct completion complete;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 08c47db7417f..3ddb08fba935 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -203,6 +203,7 @@ struct nfs4_sequence_res {
 	struct nfs4_slot	*sr_slot;	/* slot used to send request */
 	int			sr_status;	/* sequence operation status */
 	u32			sr_status_flags;
+	u32			sr_highest_slotid;
 	u32			sr_target_highest_slotid;
 };
 
-- 
cgit v1.2.3-55-g7522


From 97e548a93de213b149eea025a97d88e28143b445 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Tue, 20 Nov 2012 14:45:48 -0500
Subject: NFSv4.1: Support dynamic resizing of the session slot table

Allow the server to control the size of the session slot table
by adjusting the value of sr_target_max_slots in the reply to the
SEQUENCE operation.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c         | 12 ++++++++++--
 fs/nfs/nfs4state.c        |  6 +++---
 include/linux/nfs_fs_sb.h |  1 +
 3 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 62212231ce62..1792ece8b53c 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -492,10 +492,17 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 static void nfs41_set_target_slotid_locked(struct nfs4_slot_table *tbl,
 		u32 target_highest_slotid)
 {
+	unsigned int max_slotid, i;
+
 	if (tbl->target_highest_slotid == target_highest_slotid)
 		return;
 	tbl->target_highest_slotid = target_highest_slotid;
 	tbl->generation++;
+
+	max_slotid = min(tbl->max_slots - 1, tbl->target_highest_slotid);
+	for (i = tbl->max_slotid + 1; i <= max_slotid; i++)
+		rpc_wake_up_next(&tbl->slot_tbl_waitq);
+	tbl->max_slotid = max_slotid;
 }
 
 void nfs41_set_target_slotid(struct nfs4_slot_table *tbl,
@@ -622,8 +629,8 @@ static struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl)
 	dprintk("--> %s used_slots=%04lx highest_used=%u max_slots=%u\n",
 		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
 		tbl->max_slots);
-	slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slots);
-	if (slotid >= tbl->max_slots)
+	slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slotid + 1);
+	if (slotid > tbl->max_slotid)
 		goto out;
 	__set_bit(slotid, tbl->used_slots);
 	if (slotid > tbl->highest_used_slotid ||
@@ -5744,6 +5751,7 @@ static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl,
 	tbl->highest_used_slotid = NFS4_NO_SLOT;
 	tbl->target_highest_slotid = max_slots - 1;
 	tbl->server_highest_slotid = max_slots - 1;
+	tbl->max_slotid = max_slots - 1;
 	for (i = 0; i < tbl->max_slots; i++)
 		tbl->slots[i].seq_nr = ivalue;
 	spin_unlock(&tbl->slot_tbl_lock);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 842cb8c2f65d..1b7fa73c9436 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -254,15 +254,14 @@ static void nfs4_end_drain_session(struct nfs_client *clp)
 {
 	struct nfs4_session *ses = clp->cl_session;
 	struct nfs4_slot_table *tbl;
-	int max_slots;
+	unsigned int i;
 
 	if (ses == NULL)
 		return;
 	tbl = &ses->fc_slot_table;
 	if (test_and_clear_bit(NFS4_SESSION_DRAINING, &ses->session_state)) {
 		spin_lock(&tbl->slot_tbl_lock);
-		max_slots = tbl->max_slots;
-		while (max_slots--) {
+		for (i = 0; i <= tbl->max_slotid; i++) {
 			if (rpc_wake_up_first(&tbl->slot_tbl_waitq,
 						nfs4_set_task_privileged,
 						NULL) == NULL)
@@ -2043,6 +2042,7 @@ static int nfs4_recall_slot(struct nfs_client *clp)
 	old = fc_tbl->slots;
 	fc_tbl->slots = new;
 	fc_tbl->max_slots = fc_tbl->target_highest_slotid + 1;
+	fc_tbl->max_slotid = fc_tbl->target_highest_slotid;
 	clp->cl_session->fc_attrs.max_reqs = fc_tbl->max_slots;
 	spin_unlock(&fc_tbl->slot_tbl_lock);
 
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 646e64bbff4c..30715508fade 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -215,6 +215,7 @@ struct nfs4_slot_table {
 	spinlock_t	slot_tbl_lock;
 	struct rpc_wait_queue	slot_tbl_waitq;	/* allocators may wait here */
 	u32		max_slots;		/* # slots in table */
+	u32		max_slotid;		/* Max allowed slotid value */
 	u32		highest_used_slotid;	/* sent to server on each SEQ.
 						 * op for dynamic resizing */
 	u32		target_highest_slotid;	/* Server max_slot target */
-- 
cgit v1.2.3-55-g7522


From 87dda67e7386ba7d2164391ea58b34e028d8157b Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Tue, 20 Nov 2012 19:49:20 -0500
Subject: NFSv4.1: Allow SEQUENCE to resize the slot table on the fly

Instead of an array of slots, use a singly linked list of slots that
can be dynamically appended to or shrunk.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4_fs.h        |   4 +-
 fs/nfs/nfs4proc.c       | 174 +++++++++++++++++++++++++++++++-----------------
 fs/nfs/nfs4state.c      |  22 ++----
 include/linux/nfs_xdr.h |   1 +
 4 files changed, 121 insertions(+), 80 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 5d4e82b10c3c..856bc496a210 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -258,10 +258,10 @@ extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
 extern int nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data,
 				  bool sync);
 
-extern struct nfs4_slot *nfs4_alloc_slots(struct nfs4_slot_table *table,
-		u32 max_slots, gfp_t gfp_flags);
 extern void nfs41_set_target_slotid(struct nfs4_slot_table *tbl,
 		u32 target_highest_slotid);
+extern int nfs4_resize_slot_table(struct nfs4_slot_table *tbl,
+		u32 max_reqs, u32 ivalue);
 
 static inline bool
 is_ds_only_client(struct nfs_client *clp)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1792ece8b53c..fc65300172e1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -396,6 +396,27 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp
 
 #if defined(CONFIG_NFS_V4_1)
 
+/*
+ * nfs4_shrink_slot_table - free retired slots from the slot table
+ */
+static void nfs4_shrink_slot_table(struct nfs4_slot_table  *tbl, u32 newsize)
+{
+	struct nfs4_slot **p;
+	if (newsize >= tbl->max_slots)
+		return;
+
+	p = &tbl->slots;
+	while (newsize--)
+		p = &(*p)->next;
+	while (*p) {
+		struct nfs4_slot *slot = *p;
+
+		*p = slot->next;
+		kfree(slot);
+		tbl->max_slots--;
+	}
+}
+
 /*
  * nfs4_free_slot - free a slot and efficiently update slot table.
  *
@@ -499,7 +520,7 @@ static void nfs41_set_target_slotid_locked(struct nfs4_slot_table *tbl,
 	tbl->target_highest_slotid = target_highest_slotid;
 	tbl->generation++;
 
-	max_slotid = min(tbl->max_slots - 1, tbl->target_highest_slotid);
+	max_slotid = min(NFS4_MAX_SLOT_TABLE - 1, tbl->target_highest_slotid);
 	for (i = tbl->max_slotid + 1; i <= max_slotid; i++)
 		rpc_wake_up_next(&tbl->slot_tbl_waitq);
 	tbl->max_slotid = max_slotid;
@@ -516,16 +537,12 @@ void nfs41_set_target_slotid(struct nfs4_slot_table *tbl,
 static void nfs41_set_server_slotid_locked(struct nfs4_slot_table *tbl,
 		u32 highest_slotid)
 {
-	unsigned int max_slotid, i;
-
 	if (tbl->server_highest_slotid == highest_slotid)
 		return;
 	if (tbl->highest_used_slotid > highest_slotid)
 		return;
-	max_slotid = min(tbl->max_slots - 1, highest_slotid);
-	/* Reset the seq_nr for deallocated slots */
-	for (i = tbl->server_highest_slotid + 1; i <= max_slotid; i++)
-		tbl->slots[i].seq_nr = 1;
+	/* Deallocate slots */
+	nfs4_shrink_slot_table(tbl, highest_slotid + 1);
 	tbl->server_highest_slotid = highest_slotid;
 }
 
@@ -612,6 +629,42 @@ static int nfs4_sequence_done(struct rpc_task *task,
 	return nfs41_sequence_done(task, res);
 }
 
+static struct nfs4_slot *nfs4_new_slot(struct nfs4_slot_table  *tbl,
+		u32 slotid, u32 seq_init, gfp_t gfp_mask)
+{
+	struct nfs4_slot *slot;
+
+	slot = kzalloc(sizeof(*slot), gfp_mask);
+	if (slot) {
+		slot->table = tbl;
+		slot->slot_nr = slotid;
+		slot->seq_nr = seq_init;
+	}
+	return slot;
+}
+
+static struct nfs4_slot *nfs4_find_or_create_slot(struct nfs4_slot_table  *tbl,
+		u32 slotid, u32 seq_init, gfp_t gfp_mask)
+{
+	struct nfs4_slot **p, *slot;
+
+	p = &tbl->slots;
+	for (;;) {
+		if (*p == NULL) {
+			*p = nfs4_new_slot(tbl, tbl->max_slots,
+					seq_init, gfp_mask);
+			if (*p == NULL)
+				break;
+			tbl->max_slots++;
+		}
+		slot = *p;
+		if (slot->slot_nr == slotid)
+			return slot;
+		p = &slot->next;
+	}
+	return NULL;
+}
+
 /*
  * nfs4_alloc_slot - efficiently look for a free slot
  *
@@ -628,15 +681,17 @@ static struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl)
 
 	dprintk("--> %s used_slots=%04lx highest_used=%u max_slots=%u\n",
 		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
-		tbl->max_slots);
+		tbl->max_slotid + 1);
 	slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slotid + 1);
 	if (slotid > tbl->max_slotid)
 		goto out;
+	ret = nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
+	if (ret == NULL)
+		goto out;
 	__set_bit(slotid, tbl->used_slots);
 	if (slotid > tbl->highest_used_slotid ||
 			tbl->highest_used_slotid == NFS4_NO_SLOT)
 		tbl->highest_used_slotid = slotid;
-	ret = &tbl->slots[slotid];
 	ret->renewal_time = jiffies;
 	ret->generation = tbl->generation;
 
@@ -5718,67 +5773,56 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
 	return status;
 }
 
-struct nfs4_slot *nfs4_alloc_slots(struct nfs4_slot_table *table,
-		u32 max_slots, gfp_t gfp_flags)
+static int nfs4_grow_slot_table(struct nfs4_slot_table *tbl,
+		 u32 max_reqs, u32 ivalue)
 {
-	struct nfs4_slot *tbl;
-	u32 i;
-
-	tbl = kmalloc_array(max_slots, sizeof(*tbl), gfp_flags);
-	if (tbl != NULL) {
-		for (i = 0; i < max_slots; i++) {
-			tbl[i].table = table;
-			tbl[i].slot_nr = i;
-		}
-	}
-	return tbl;
+	if (max_reqs <= tbl->max_slots)
+		return 0;
+	if (nfs4_find_or_create_slot(tbl, max_reqs - 1, ivalue, GFP_NOFS))
+		return 0;
+	return -ENOMEM;
 }
 
-static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl,
-		struct nfs4_slot *new,
-		u32 max_slots,
+static void nfs4_reset_slot_table(struct nfs4_slot_table *tbl,
+		u32 server_highest_slotid,
 		u32 ivalue)
 {
-	struct nfs4_slot *old = NULL;
-	u32 i;
+	struct nfs4_slot **p;
 
-	spin_lock(&tbl->slot_tbl_lock);
-	if (new) {
-		old = tbl->slots;
-		tbl->slots = new;
-		tbl->max_slots = max_slots;
+	nfs4_shrink_slot_table(tbl, server_highest_slotid + 1);
+	p = &tbl->slots;
+	while (*p) {
+		(*p)->seq_nr = ivalue;
+		p = &(*p)->next;
 	}
 	tbl->highest_used_slotid = NFS4_NO_SLOT;
-	tbl->target_highest_slotid = max_slots - 1;
-	tbl->server_highest_slotid = max_slots - 1;
-	tbl->max_slotid = max_slots - 1;
-	for (i = 0; i < tbl->max_slots; i++)
-		tbl->slots[i].seq_nr = ivalue;
-	spin_unlock(&tbl->slot_tbl_lock);
-	kfree(old);
+	tbl->target_highest_slotid = server_highest_slotid;
+	tbl->server_highest_slotid = server_highest_slotid;
+	tbl->max_slotid = server_highest_slotid;
 }
 
 /*
  * (re)Initialise a slot table
  */
-static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl, u32 max_reqs,
-				 u32 ivalue)
+static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl,
+		u32 max_reqs, u32 ivalue)
 {
-	struct nfs4_slot *new = NULL;
-	int ret = -ENOMEM;
+	int ret;
 
 	dprintk("--> %s: max_reqs=%u, tbl->max_slots %d\n", __func__,
 		max_reqs, tbl->max_slots);
 
-	/* Does the newly negotiated max_reqs match the existing slot table? */
-	if (max_reqs != tbl->max_slots) {
-		new = nfs4_alloc_slots(tbl, max_reqs, GFP_NOFS);
-		if (!new)
-			goto out;
-	}
-	ret = 0;
+	if (max_reqs > NFS4_MAX_SLOT_TABLE)
+		max_reqs = NFS4_MAX_SLOT_TABLE;
+
+	ret = nfs4_grow_slot_table(tbl, max_reqs, ivalue);
+	if (ret)
+		goto out;
+
+	spin_lock(&tbl->slot_tbl_lock);
+	nfs4_reset_slot_table(tbl, max_reqs - 1, ivalue);
+	spin_unlock(&tbl->slot_tbl_lock);
 
-	nfs4_add_and_init_slots(tbl, new, max_reqs, ivalue);
 	dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__,
 		tbl, tbl->slots, tbl->max_slots);
 out:
@@ -5786,18 +5830,28 @@ out:
 	return ret;
 }
 
+int nfs4_resize_slot_table(struct nfs4_slot_table *tbl,
+		 u32 max_reqs, u32 ivalue)
+{
+	int ret;
+
+	if (max_reqs > NFS4_MAX_SLOT_TABLE)
+		max_reqs = NFS4_MAX_SLOT_TABLE;
+	ret = nfs4_grow_slot_table(tbl, max_reqs, ivalue);
+	if (ret)
+		return ret;
+	spin_lock(&tbl->slot_tbl_lock);
+	nfs4_shrink_slot_table(tbl, max_reqs);
+	tbl->max_slotid = max_reqs - 1;
+	spin_unlock(&tbl->slot_tbl_lock);
+	return 0;
+}
+
 /* Destroy the slot table */
 static void nfs4_destroy_slot_tables(struct nfs4_session *session)
 {
-	if (session->fc_slot_table.slots != NULL) {
-		kfree(session->fc_slot_table.slots);
-		session->fc_slot_table.slots = NULL;
-	}
-	if (session->bc_slot_table.slots != NULL) {
-		kfree(session->bc_slot_table.slots);
-		session->bc_slot_table.slots = NULL;
-	}
-	return;
+	nfs4_shrink_slot_table(&session->fc_slot_table, 0);
+	nfs4_shrink_slot_table(&session->bc_slot_table, 0);
 }
 
 /*
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 1b7fa73c9436..c14b2c7ac8a7 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2025,29 +2025,15 @@ out:
 static int nfs4_recall_slot(struct nfs_client *clp)
 {
 	struct nfs4_slot_table *fc_tbl;
-	struct nfs4_slot *new, *old;
-	int i;
+	u32 new_size;
 
 	if (!nfs4_has_session(clp))
 		return 0;
 	nfs4_begin_drain_session(clp);
-	fc_tbl = &clp->cl_session->fc_slot_table;
-	new = nfs4_alloc_slots(fc_tbl, fc_tbl->target_highest_slotid + 1, GFP_NOFS);
-        if (!new)
-		return -ENOMEM;
 
-	spin_lock(&fc_tbl->slot_tbl_lock);
-	for (i = 0; i <= fc_tbl->target_highest_slotid; i++)
-		new[i].seq_nr = fc_tbl->slots[i].seq_nr;
-	old = fc_tbl->slots;
-	fc_tbl->slots = new;
-	fc_tbl->max_slots = fc_tbl->target_highest_slotid + 1;
-	fc_tbl->max_slotid = fc_tbl->target_highest_slotid;
-	clp->cl_session->fc_attrs.max_reqs = fc_tbl->max_slots;
-	spin_unlock(&fc_tbl->slot_tbl_lock);
-
-	kfree(old);
-	return 0;
+	fc_tbl = &clp->cl_session->fc_slot_table;
+	new_size = fc_tbl->server_highest_slotid + 1;
+	return nfs4_resize_slot_table(fc_tbl, new_size, 1);
 }
 
 static int nfs4_bind_conn_to_session(struct nfs_client *clp)
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 3ddb08fba935..44d256f6021c 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -188,6 +188,7 @@ struct nfs4_channel_attrs {
 /* nfs41 sessions slot seqid */
 struct nfs4_slot {
 	struct nfs4_slot_table	*table;
+	struct nfs4_slot	*next;
 	unsigned long		generation;
 	unsigned long		renewal_time;
 	u32			slot_nr;
-- 
cgit v1.2.3-55-g7522


From c34309a45ea491e5f0c0d0af49ccfa018ff35fc1 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Mon, 26 Nov 2012 14:33:03 -0500
Subject: NFS: Remove unused function slot_idx

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 include/linux/nfs_fs_sb.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 30715508fade..e707c1b69796 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -225,11 +225,6 @@ struct nfs4_slot_table {
 	struct completion complete;
 };
 
-static inline int slot_idx(struct nfs4_slot_table *tbl, struct nfs4_slot *sp)
-{
-	return sp - tbl->slots;
-}
-
 /*
  * Session related parameters
  */
-- 
cgit v1.2.3-55-g7522


From 76e697ba7e8d187f50e385d21a2b2f1709a62c14 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Mon, 26 Nov 2012 14:20:49 -0500
Subject: NFSv4.1: Move slot table and session struct definitions to
 nfs4session.h

Clean up. Gather NFSv4.1 slot definitions in fs/nfs/nfs4session.h.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/blocklayout/blocklayout.c |   1 +
 fs/nfs/callback_xdr.c            |   1 +
 fs/nfs/internal.h                |  21 --------
 fs/nfs/nfs4_fs.h                 |  12 -----
 fs/nfs/nfs4filelayout.c          |   1 +
 fs/nfs/nfs4session.h             | 101 +++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4state.c               |   1 +
 fs/nfs/nfs4xdr.c                 |   1 +
 fs/nfs/super.c                   |   1 +
 include/linux/nfs_fs_sb.h        |  49 -------------------
 include/linux/nfs_xdr.h          |  11 +----
 11 files changed, 108 insertions(+), 92 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index f1027b06a1a9..4fa788c93f46 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -40,6 +40,7 @@
 #include <linux/pagevec.h>
 
 #include "../pnfs.h"
+#include "../nfs4session.h"
 #include "../internal.h"
 #include "blocklayout.h"
 
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index ea6a7b190e6b..59461c957d9d 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -16,6 +16,7 @@
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "internal.h"
+#include "nfs4session.h"
 
 #define CB_OP_TAGLEN_MAXSZ	(512)
 #define CB_OP_HDR_RES_MAXSZ	(2 + CB_OP_TAGLEN_MAXSZ)
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 8965a998b306..9bdbfc3884a9 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -18,27 +18,6 @@ struct nfs_string;
  */
 #define NFS_MAX_READAHEAD	(RPC_DEF_SLOT_TABLE - 1)
 
-/*
- * Determine if sessions are in use.
- */
-static inline int nfs4_has_session(const struct nfs_client *clp)
-{
-#ifdef CONFIG_NFS_V4_1
-	if (clp->cl_session)
-		return 1;
-#endif /* CONFIG_NFS_V4_1 */
-	return 0;
-}
-
-static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
-{
-#ifdef CONFIG_NFS_V4_1
-	if (nfs4_has_session(clp))
-		return (clp->cl_session->flags & SESSION4_PERSIST);
-#endif /* CONFIG_NFS_V4_1 */
-	return 0;
-}
-
 static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr)
 {
 	if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid))
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index cd3e3096b60a..322bd0168ebf 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -29,11 +29,6 @@ enum nfs4_client_state {
 	NFS4CLNT_BIND_CONN_TO_SESSION,
 };
 
-enum nfs4_session_state {
-	NFS4_SESSION_INITING,
-	NFS4_SESSION_DRAINING,
-};
-
 #define NFS4_RENEW_TIMEOUT		0x01
 #define NFS4_RENEW_DELEGATION_CB	0x02
 
@@ -327,13 +322,6 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
 extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
 extern void nfs41_server_notify_target_slotid_update(struct nfs_client *clp);
 
-extern void nfs4_session_drain_complete(struct nfs4_session *session,
-		struct nfs4_slot_table *tbl);
-
-static inline bool nfs4_session_draining(struct nfs4_session *session)
-{
-	return !!test_bit(NFS4_SESSION_DRAINING, &session->session_state);
-}
 #else
 static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
 {
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index bfb28fa38e74..591a1a7f8f94 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -35,6 +35,7 @@
 
 #include <linux/sunrpc/metrics.h>
 
+#include "nfs4session.h"
 #include "internal.h"
 #include "delegation.h"
 #include "nfs4filelayout.h"
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index cb47b1eb0886..e96323ff1d95 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -7,6 +7,68 @@
 #ifndef __LINUX_FS_NFS_NFS4SESSION_H
 #define __LINUX_FS_NFS_NFS4SESSION_H
 
+/* maximum number of slots to use */
+#define NFS4_DEF_SLOT_TABLE_SIZE (16U)
+#define NFS4_MAX_SLOT_TABLE (256U)
+#define NFS4_NO_SLOT ((u32)-1)
+
+#if IS_ENABLED(CONFIG_NFS_V4)
+
+/* Sessions slot seqid */
+struct nfs4_slot {
+	struct nfs4_slot_table	*table;
+	struct nfs4_slot	*next;
+	unsigned long		generation;
+	unsigned long		renewal_time;
+	u32			slot_nr;
+	u32		 	seq_nr;
+};
+
+/* Sessions */
+#define SLOT_TABLE_SZ DIV_ROUND_UP(NFS4_MAX_SLOT_TABLE, 8*sizeof(long))
+struct nfs4_slot_table {
+	struct nfs4_session *session;		/* Parent session */
+	struct nfs4_slot *slots;		/* seqid per slot */
+	unsigned long   used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */
+	spinlock_t	slot_tbl_lock;
+	struct rpc_wait_queue	slot_tbl_waitq;	/* allocators may wait here */
+	u32		max_slots;		/* # slots in table */
+	u32		max_slotid;		/* Max allowed slotid value */
+	u32		highest_used_slotid;	/* sent to server on each SEQ.
+						 * op for dynamic resizing */
+	u32		target_highest_slotid;	/* Server max_slot target */
+	u32		server_highest_slotid;	/* Server highest slotid */
+	unsigned long	generation;		/* Generation counter for
+						   target_highest_slotid */
+	struct completion complete;
+};
+
+/*
+ * Session related parameters
+ */
+struct nfs4_session {
+	struct nfs4_sessionid		sess_id;
+	u32				flags;
+	unsigned long			session_state;
+	u32				hash_alg;
+	u32				ssv_len;
+
+	/* The fore and back channel */
+	struct nfs4_channel_attrs	fc_attrs;
+	struct nfs4_slot_table		fc_slot_table;
+	struct nfs4_channel_attrs	bc_attrs;
+	struct nfs4_slot_table		bc_slot_table;
+	struct nfs_client		*clp;
+	/* Create session arguments */
+	unsigned int			fc_target_max_rqst_sz;
+	unsigned int			fc_target_max_resp_sz;
+};
+
+enum nfs4_session_state {
+	NFS4_SESSION_INITING,
+	NFS4_SESSION_DRAINING,
+};
+
 #if defined(CONFIG_NFS_V4_1)
 extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
 extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
@@ -24,6 +86,31 @@ extern void nfs4_destroy_session(struct nfs4_session *session);
 extern int nfs4_init_session(struct nfs_server *server);
 extern int nfs4_init_ds_session(struct nfs_client *, unsigned long);
 
+extern void nfs4_session_drain_complete(struct nfs4_session *session,
+		struct nfs4_slot_table *tbl);
+
+static inline bool nfs4_session_draining(struct nfs4_session *session)
+{
+	return !!test_bit(NFS4_SESSION_DRAINING, &session->session_state);
+}
+
+/*
+ * Determine if sessions are in use.
+ */
+static inline int nfs4_has_session(const struct nfs_client *clp)
+{
+	if (clp->cl_session)
+		return 1;
+	return 0;
+}
+
+static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
+{
+	if (nfs4_has_session(clp))
+		return (clp->cl_session->flags & SESSION4_PERSIST);
+	return 0;
+}
+
 #else /* defined(CONFIG_NFS_V4_1) */
 
 static inline int nfs4_init_session(struct nfs_server *server)
@@ -31,5 +118,19 @@ static inline int nfs4_init_session(struct nfs_server *server)
 	return 0;
 }
 
+/*
+ * Determine if sessions are in use.
+ */
+static inline int nfs4_has_session(const struct nfs_client *clp)
+{
+	return 0;
+}
+
+static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
+{
+	return 0;
+}
+
 #endif /* defined(CONFIG_NFS_V4_1) */
+#endif /* IS_ENABLED(CONFIG_NFS_V4) */
 #endif /* __LINUX_FS_NFS_NFS4SESSION_H */
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 1077b9698381..1402283d152d 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -57,6 +57,7 @@
 #include "callback.h"
 #include "delegation.h"
 #include "internal.h"
+#include "nfs4session.h"
 #include "pnfs.h"
 #include "netns.h"
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index a67040f51597..e786dc7582b1 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -56,6 +56,7 @@
 
 #include "nfs4_fs.h"
 #include "internal.h"
+#include "nfs4session.h"
 #include "pnfs.h"
 #include "netns.h"
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 652d3f7176a9..e12cea4b36a5 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -64,6 +64,7 @@
 #include "iostat.h"
 #include "internal.h"
 #include "fscache.h"
+#include "nfs4session.h"
 #include "pnfs.h"
 #include "nfs.h"
 
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index e707c1b69796..6c6ed153a9b4 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -198,53 +198,4 @@ struct nfs_server {
 #define NFS_CAP_POSIX_LOCK	(1U << 14)
 #define NFS_CAP_UIDGID_NOMAP	(1U << 15)
 
-
-/* maximum number of slots to use */
-#define NFS4_DEF_SLOT_TABLE_SIZE (16U)
-#define NFS4_MAX_SLOT_TABLE (256U)
-#define NFS4_NO_SLOT ((u32)-1)
-
-#if IS_ENABLED(CONFIG_NFS_V4)
-
-/* Sessions */
-#define SLOT_TABLE_SZ DIV_ROUND_UP(NFS4_MAX_SLOT_TABLE, 8*sizeof(long))
-struct nfs4_slot_table {
-	struct nfs4_session *session;		/* Parent session */
-	struct nfs4_slot *slots;		/* seqid per slot */
-	unsigned long   used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */
-	spinlock_t	slot_tbl_lock;
-	struct rpc_wait_queue	slot_tbl_waitq;	/* allocators may wait here */
-	u32		max_slots;		/* # slots in table */
-	u32		max_slotid;		/* Max allowed slotid value */
-	u32		highest_used_slotid;	/* sent to server on each SEQ.
-						 * op for dynamic resizing */
-	u32		target_highest_slotid;	/* Server max_slot target */
-	u32		server_highest_slotid;	/* Server highest slotid */
-	unsigned long	generation;		/* Generation counter for
-						   target_highest_slotid */
-	struct completion complete;
-};
-
-/*
- * Session related parameters
- */
-struct nfs4_session {
-	struct nfs4_sessionid		sess_id;
-	u32				flags;
-	unsigned long			session_state;
-	u32				hash_alg;
-	u32				ssv_len;
-
-	/* The fore and back channel */
-	struct nfs4_channel_attrs	fc_attrs;
-	struct nfs4_slot_table		fc_slot_table;
-	struct nfs4_channel_attrs	bc_attrs;
-	struct nfs4_slot_table		bc_slot_table;
-	struct nfs_client		*clp;
-	/* Create session arguments */
-	unsigned int			fc_target_max_rqst_sz;
-	unsigned int			fc_target_max_resp_sz;
-};
-
-#endif /* CONFIG_NFS_V4 */
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 44d256f6021c..2076149db1a4 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -185,16 +185,7 @@ struct nfs4_channel_attrs {
 	u32			max_reqs;
 };
 
-/* nfs41 sessions slot seqid */
-struct nfs4_slot {
-	struct nfs4_slot_table	*table;
-	struct nfs4_slot	*next;
-	unsigned long		generation;
-	unsigned long		renewal_time;
-	u32			slot_nr;
-	u32		 	seq_nr;
-};
-
+struct nfs4_slot;
 struct nfs4_sequence_args {
 	struct nfs4_slot	*sa_slot;
 	u8			sa_cache_this;
-- 
cgit v1.2.3-55-g7522


From 8fe72bac8de784c4059b41a7dd6bb0151a3ae898 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Mon, 29 Oct 2012 19:02:20 -0400
Subject: NFSv4: Clean up handling of privileged operations

Privileged rpc calls are those that are run by the state recovery thread,
in cases where we're trying to recover the system after a server reboot
or a network partition. In those cases, we want to fence off all other
rpc calls (see nfs4_begin_drain_session()) so that they don't end up
using stateids or clientids that are in the process of being recovered.

Prior to this patch, we had to set up special callback functions in
order to declare an rpc call as being privileged.
By adding a new field to the sequence arguments, this patch simplifies
things considerably, and allows us to declare the rpc call as privileged
before it is run.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       | 114 ++++++++++++++++++------------------------------
 include/linux/nfs_xdr.h |   3 +-
 2 files changed, 44 insertions(+), 73 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4b1635ce658d..38a709d78594 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -490,11 +490,17 @@ static void nfs41_init_sequence(struct nfs4_sequence_args *args,
 {
 	args->sa_slot = NULL;
 	args->sa_cache_this = 0;
+	args->sa_privileged = 0;
 	if (cache_reply)
 		args->sa_cache_this = 1;
 	res->sr_slot = NULL;
 }
 
+static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args)
+{
+	args->sa_privileged = 1;
+}
+
 int nfs41_setup_sequence(struct nfs4_session *session,
 				struct nfs4_sequence_args *args,
 				struct nfs4_sequence_res *res,
@@ -514,7 +520,7 @@ int nfs41_setup_sequence(struct nfs4_session *session,
 
 	spin_lock(&tbl->slot_tbl_lock);
 	if (test_bit(NFS4_SESSION_DRAINING, &session->session_state) &&
-	    !rpc_task_has_priority(task, RPC_PRIORITY_PRIVILEGED)) {
+	    !args->sa_privileged) {
 		/* The state manager will wait until the slot table is empty */
 		dprintk("%s session is draining\n", __func__);
 		goto out_sleep;
@@ -548,6 +554,9 @@ out_success:
 	rpc_call_start(task);
 	return 0;
 out_sleep:
+	/* Privileged tasks are queued with top priority */
+	if (args->sa_privileged)
+		rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
 	rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
 	spin_unlock(&tbl->slot_tbl_lock);
 	return -EAGAIN;
@@ -593,12 +602,6 @@ static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata)
 	nfs41_setup_sequence(session, data->seq_args, data->seq_res, task);
 }
 
-static void nfs41_call_priv_sync_prepare(struct rpc_task *task, void *calldata)
-{
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
-	nfs41_call_sync_prepare(task, calldata);
-}
-
 static void nfs41_call_sync_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs41_call_sync_data *data = calldata;
@@ -611,17 +614,11 @@ static const struct rpc_call_ops nfs41_call_sync_ops = {
 	.rpc_call_done = nfs41_call_sync_done,
 };
 
-static const struct rpc_call_ops nfs41_call_priv_sync_ops = {
-	.rpc_call_prepare = nfs41_call_priv_sync_prepare,
-	.rpc_call_done = nfs41_call_sync_done,
-};
-
 static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
 				   struct nfs_server *server,
 				   struct rpc_message *msg,
 				   struct nfs4_sequence_args *args,
-				   struct nfs4_sequence_res *res,
-				   int privileged)
+				   struct nfs4_sequence_res *res)
 {
 	int ret;
 	struct rpc_task *task;
@@ -637,8 +634,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
 		.callback_data = &data
 	};
 
-	if (privileged)
-		task_setup.callback_ops = &nfs41_call_priv_sync_ops;
 	task = rpc_run_task(&task_setup);
 	if (IS_ERR(task))
 		ret = PTR_ERR(task);
@@ -656,16 +651,21 @@ int _nfs4_call_sync_session(struct rpc_clnt *clnt,
 			    struct nfs4_sequence_args *args,
 			    struct nfs4_sequence_res *res)
 {
-	return nfs4_call_sync_sequence(clnt, server, msg, args, res, 0);
+	return nfs4_call_sync_sequence(clnt, server, msg, args, res);
 }
 
 #else
-static inline
+static
 void nfs41_init_sequence(struct nfs4_sequence_args *args,
 		struct nfs4_sequence_res *res, int cache_reply)
 {
 }
 
+static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args)
+{
+}
+
+
 static int nfs4_sequence_done(struct rpc_task *task,
 			       struct nfs4_sequence_res *res)
 {
@@ -1475,13 +1475,6 @@ unlock_no_action:
 	rcu_read_unlock();
 out_no_action:
 	task->tk_action = NULL;
-
-}
-
-static void nfs4_recover_open_prepare(struct rpc_task *task, void *calldata)
-{
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
-	nfs4_open_prepare(task, calldata);
 }
 
 static void nfs4_open_done(struct rpc_task *task, void *calldata)
@@ -1542,12 +1535,6 @@ static const struct rpc_call_ops nfs4_open_ops = {
 	.rpc_release = nfs4_open_release,
 };
 
-static const struct rpc_call_ops nfs4_recover_open_ops = {
-	.rpc_call_prepare = nfs4_recover_open_prepare,
-	.rpc_call_done = nfs4_open_done,
-	.rpc_release = nfs4_open_release,
-};
-
 static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
 {
 	struct inode *dir = data->dir->d_inode;
@@ -1577,7 +1564,7 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
 	data->rpc_status = 0;
 	data->cancelled = 0;
 	if (isrecover)
-		task_setup_data.callback_ops = &nfs4_recover_open_ops;
+		nfs4_set_sequence_privileged(&o_arg->seq_args);
 	task = rpc_run_task(&task_setup_data);
         if (IS_ERR(task))
                 return PTR_ERR(task);
@@ -4558,8 +4545,9 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
 		return;
 	/* Do we need to do an open_to_lock_owner? */
 	if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) {
-		if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0)
+		if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) {
 			goto out_release_lock_seqid;
+		}
 		data->arg.open_stateid = &state->stateid;
 		data->arg.new_lock_owner = 1;
 		data->res.open_seqid = data->arg.open_seqid;
@@ -4574,13 +4562,7 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
 	nfs_release_seqid(data->arg.open_seqid);
 out_release_lock_seqid:
 	nfs_release_seqid(data->arg.lock_seqid);
-	dprintk("%s: done!, ret = %d\n", __func__, task->tk_status);
-}
-
-static void nfs4_recover_lock_prepare(struct rpc_task *task, void *calldata)
-{
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
-	nfs4_lock_prepare(task, calldata);
+	dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status);
 }
 
 static void nfs4_lock_done(struct rpc_task *task, void *calldata)
@@ -4635,12 +4617,6 @@ static const struct rpc_call_ops nfs4_lock_ops = {
 	.rpc_release = nfs4_lock_release,
 };
 
-static const struct rpc_call_ops nfs4_recover_lock_ops = {
-	.rpc_call_prepare = nfs4_recover_lock_prepare,
-	.rpc_call_done = nfs4_lock_done,
-	.rpc_release = nfs4_lock_release,
-};
-
 static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_state *lsp, int new_lock_owner, int error)
 {
 	switch (error) {
@@ -4683,15 +4659,15 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 		return -ENOMEM;
 	if (IS_SETLKW(cmd))
 		data->arg.block = 1;
-	if (recovery_type > NFS_LOCK_NEW) {
-		if (recovery_type == NFS_LOCK_RECLAIM)
-			data->arg.reclaim = NFS_LOCK_RECLAIM;
-		task_setup_data.callback_ops = &nfs4_recover_lock_ops;
-	}
 	nfs41_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1);
 	msg.rpc_argp = &data->arg;
 	msg.rpc_resp = &data->res;
 	task_setup_data.callback_data = data;
+	if (recovery_type > NFS_LOCK_NEW) {
+		if (recovery_type == NFS_LOCK_RECLAIM)
+			data->arg.reclaim = NFS_LOCK_RECLAIM;
+		nfs4_set_sequence_privileged(&data->arg.seq_args);
+	}
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
@@ -5432,7 +5408,6 @@ static void nfs4_get_lease_time_prepare(struct rpc_task *task,
 			(struct nfs4_get_lease_time_data *)calldata;
 
 	dprintk("--> %s\n", __func__);
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
 	/* just setup sequence, do not trigger session recovery
 	   since we're invoked within one */
 	nfs41_setup_sequence(data->clp->cl_session,
@@ -5500,6 +5475,7 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
 	int status;
 
 	nfs41_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0);
+	nfs4_set_sequence_privileged(&args.la_seq_args);
 	dprintk("--> %s\n", __func__);
 	task = rpc_run_task(&task_setup);
 
@@ -5775,26 +5751,15 @@ static void nfs41_sequence_prepare(struct rpc_task *task, void *data)
 	nfs41_setup_sequence(clp->cl_session, args, res, task);
 }
 
-static void nfs41_sequence_prepare_privileged(struct rpc_task *task, void *data)
-{
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
-	nfs41_sequence_prepare(task, data);
-}
-
 static const struct rpc_call_ops nfs41_sequence_ops = {
 	.rpc_call_done = nfs41_sequence_call_done,
 	.rpc_call_prepare = nfs41_sequence_prepare,
 	.rpc_release = nfs41_sequence_release,
 };
 
-static const struct rpc_call_ops nfs41_sequence_privileged_ops = {
-	.rpc_call_done = nfs41_sequence_call_done,
-	.rpc_call_prepare = nfs41_sequence_prepare_privileged,
-	.rpc_release = nfs41_sequence_release,
-};
-
-static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred,
-					     const struct rpc_call_ops *seq_ops)
+static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp,
+		struct rpc_cred *cred,
+		bool is_privileged)
 {
 	struct nfs4_sequence_data *calldata;
 	struct rpc_message msg = {
@@ -5804,7 +5769,7 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_
 	struct rpc_task_setup task_setup_data = {
 		.rpc_client = clp->cl_rpcclient,
 		.rpc_message = &msg,
-		.callback_ops = seq_ops,
+		.callback_ops = &nfs41_sequence_ops,
 		.flags = RPC_TASK_ASYNC | RPC_TASK_SOFT,
 	};
 
@@ -5816,6 +5781,8 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_
 		return ERR_PTR(-ENOMEM);
 	}
 	nfs41_init_sequence(&calldata->args, &calldata->res, 0);
+	if (is_privileged)
+		nfs4_set_sequence_privileged(&calldata->args);
 	msg.rpc_argp = &calldata->args;
 	msg.rpc_resp = &calldata->res;
 	calldata->clp = clp;
@@ -5831,7 +5798,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr
 
 	if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0)
 		return 0;
-	task = _nfs41_proc_sequence(clp, cred, &nfs41_sequence_ops);
+	task = _nfs41_proc_sequence(clp, cred, false);
 	if (IS_ERR(task))
 		ret = PTR_ERR(task);
 	else
@@ -5845,7 +5812,7 @@ static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
 	struct rpc_task *task;
 	int ret;
 
-	task = _nfs41_proc_sequence(clp, cred, &nfs41_sequence_privileged_ops);
+	task = _nfs41_proc_sequence(clp, cred, true);
 	if (IS_ERR(task)) {
 		ret = PTR_ERR(task);
 		goto out;
@@ -5874,7 +5841,6 @@ static void nfs4_reclaim_complete_prepare(struct rpc_task *task, void *data)
 {
 	struct nfs4_reclaim_complete_data *calldata = data;
 
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
 	nfs41_setup_sequence(calldata->clp->cl_session,
 			&calldata->arg.seq_args,
 			&calldata->res.seq_res,
@@ -5955,6 +5921,7 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp)
 	calldata->arg.one_fs = 0;
 
 	nfs41_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 0);
+	nfs4_set_sequence_privileged(&calldata->arg.seq_args);
 	msg.rpc_argp = &calldata->arg;
 	msg.rpc_resp = &calldata->res;
 	task_setup_data.callback_data = calldata;
@@ -6521,7 +6488,9 @@ static int _nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 
 	dprintk("NFS call  test_stateid %p\n", stateid);
 	nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
-	status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
+	nfs4_set_sequence_privileged(&args.seq_args);
+	status = nfs4_call_sync_sequence(server->client, server, &msg,
+			&args.seq_args, &res.seq_res);
 	if (status != NFS_OK) {
 		dprintk("NFS reply test_stateid: failed, %d\n", status);
 		return status;
@@ -6568,8 +6537,9 @@ static int _nfs4_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 
 	dprintk("NFS call  free_stateid %p\n", stateid);
 	nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
+	nfs4_set_sequence_privileged(&args.seq_args);
 	status = nfs4_call_sync_sequence(server->client, server, &msg,
-					 &args.seq_args, &res.seq_res, 1);
+			&args.seq_args, &res.seq_res);
 	dprintk("NFS reply free_stateid: %d\n", status);
 	return status;
 }
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 2076149db1a4..baa673edb597 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -188,7 +188,8 @@ struct nfs4_channel_attrs {
 struct nfs4_slot;
 struct nfs4_sequence_args {
 	struct nfs4_slot	*sa_slot;
-	u8			sa_cache_this;
+	u8			sa_cache_this : 1,
+				sa_privileged : 1;
 };
 
 struct nfs4_sequence_res {
-- 
cgit v1.2.3-55-g7522


From 62ae082d883d167cdaa7895cf2972d85e178228a Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Thu, 29 Nov 2012 17:10:01 -0500
Subject: NFSv4: Reorder the XDR structures to put sequence at the top, not
 bottom

Pre-condition for optimising the slot allocation and reintroducing FIFO
behaviour.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 include/linux/nfs_xdr.h | 138 ++++++++++++++++++++++++------------------------
 1 file changed, 69 insertions(+), 69 deletions(-)

(limited to 'include')

diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index baa673edb597..a55abd499c21 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -205,8 +205,8 @@ struct nfs4_get_lease_time_args {
 };
 
 struct nfs4_get_lease_time_res {
-	struct nfs_fsinfo	       *lr_fsinfo;
 	struct nfs4_sequence_res	lr_seq_res;
+	struct nfs_fsinfo	       *lr_fsinfo;
 };
 
 #define PNFS_LAYOUT_MAXSIZE 4096
@@ -224,23 +224,23 @@ struct pnfs_layout_range {
 };
 
 struct nfs4_layoutget_args {
+	struct nfs4_sequence_args seq_args;
 	__u32 type;
 	struct pnfs_layout_range range;
 	__u64 minlength;
 	__u32 maxcount;
 	struct inode *inode;
 	struct nfs_open_context *ctx;
-	struct nfs4_sequence_args seq_args;
 	nfs4_stateid stateid;
 	struct nfs4_layoutdriver_data layout;
 };
 
 struct nfs4_layoutget_res {
+	struct nfs4_sequence_res seq_res;
 	__u32 return_on_close;
 	struct pnfs_layout_range range;
 	__u32 type;
 	nfs4_stateid stateid;
-	struct nfs4_sequence_res seq_res;
 	struct nfs4_layoutdriver_data *layoutp;
 };
 
@@ -251,38 +251,38 @@ struct nfs4_layoutget {
 };
 
 struct nfs4_getdevicelist_args {
+	struct nfs4_sequence_args seq_args;
 	const struct nfs_fh *fh;
 	u32 layoutclass;
-	struct nfs4_sequence_args seq_args;
 };
 
 struct nfs4_getdevicelist_res {
-	struct pnfs_devicelist *devlist;
 	struct nfs4_sequence_res seq_res;
+	struct pnfs_devicelist *devlist;
 };
 
 struct nfs4_getdeviceinfo_args {
-	struct pnfs_device *pdev;
 	struct nfs4_sequence_args seq_args;
+	struct pnfs_device *pdev;
 };
 
 struct nfs4_getdeviceinfo_res {
-	struct pnfs_device *pdev;
 	struct nfs4_sequence_res seq_res;
+	struct pnfs_device *pdev;
 };
 
 struct nfs4_layoutcommit_args {
+	struct nfs4_sequence_args seq_args;
 	nfs4_stateid stateid;
 	__u64 lastbytewritten;
 	struct inode *inode;
 	const u32 *bitmask;
-	struct nfs4_sequence_args seq_args;
 };
 
 struct nfs4_layoutcommit_res {
+	struct nfs4_sequence_res seq_res;
 	struct nfs_fattr *fattr;
 	const struct nfs_server *server;
-	struct nfs4_sequence_res seq_res;
 	int status;
 };
 
@@ -296,11 +296,11 @@ struct nfs4_layoutcommit_data {
 };
 
 struct nfs4_layoutreturn_args {
+	struct nfs4_sequence_args seq_args;
 	struct pnfs_layout_hdr *layout;
 	struct inode *inode;
 	nfs4_stateid stateid;
 	__u32   layout_type;
-	struct nfs4_sequence_args seq_args;
 };
 
 struct nfs4_layoutreturn_res {
@@ -326,6 +326,7 @@ struct stateowner_id {
  * Arguments to the open call.
  */
 struct nfs_openargs {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *	fh;
 	struct nfs_seqid *	seqid;
 	int			open_flags;
@@ -346,10 +347,10 @@ struct nfs_openargs {
 	const u32 *		bitmask;
 	const u32 *		open_bitmap;
 	__u32			claim;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_openres {
+	struct nfs4_sequence_res	seq_res;
 	nfs4_stateid            stateid;
 	struct nfs_fh           fh;
 	struct nfs4_change_info	cinfo;
@@ -364,7 +365,6 @@ struct nfs_openres {
 	__u32			attrset[NFS4_BITMAP_SIZE];
 	struct nfs4_string	*owner;
 	struct nfs4_string	*group_owner;
-	struct nfs4_sequence_res	seq_res;
 	__u32			access_request;
 	__u32			access_supported;
 	__u32			access_result;
@@ -388,20 +388,20 @@ struct nfs_open_confirmres {
  * Arguments to the close call.
  */
 struct nfs_closeargs {
+	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *         fh;
 	nfs4_stateid *		stateid;
 	struct nfs_seqid *	seqid;
 	fmode_t			fmode;
 	const u32 *		bitmask;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_closeres {
+	struct nfs4_sequence_res	seq_res;
 	nfs4_stateid            stateid;
 	struct nfs_fattr *	fattr;
 	struct nfs_seqid *	seqid;
 	const struct nfs_server *server;
-	struct nfs4_sequence_res	seq_res;
 };
 /*
  *  * Arguments to the lock,lockt, and locku call.
@@ -413,6 +413,7 @@ struct nfs_lowner {
 };
 
 struct nfs_lock_args {
+	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *		fh;
 	struct file_lock *	fl;
 	struct nfs_seqid *	lock_seqid;
@@ -423,40 +424,39 @@ struct nfs_lock_args {
 	unsigned char		block : 1;
 	unsigned char		reclaim : 1;
 	unsigned char		new_lock_owner : 1;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_lock_res {
+	struct nfs4_sequence_res	seq_res;
 	nfs4_stateid		stateid;
 	struct nfs_seqid *	lock_seqid;
 	struct nfs_seqid *	open_seqid;
-	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs_locku_args {
+	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *		fh;
 	struct file_lock *	fl;
 	struct nfs_seqid *	seqid;
 	nfs4_stateid *		stateid;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_locku_res {
+	struct nfs4_sequence_res	seq_res;
 	nfs4_stateid		stateid;
 	struct nfs_seqid *	seqid;
-	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs_lockt_args {
+	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *		fh;
 	struct file_lock *	fl;
 	struct nfs_lowner	lock_owner;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_lockt_res {
-	struct file_lock *	denied; /* LOCK, LOCKT failed */
 	struct nfs4_sequence_res	seq_res;
+	struct file_lock *	denied; /* LOCK, LOCKT failed */
 };
 
 struct nfs_release_lockowner_args {
@@ -464,22 +464,23 @@ struct nfs_release_lockowner_args {
 };
 
 struct nfs4_delegreturnargs {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *fhandle;
 	const nfs4_stateid *stateid;
 	const u32 * bitmask;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_delegreturnres {
+	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr * fattr;
 	const struct nfs_server *server;
-	struct nfs4_sequence_res	seq_res;
 };
 
 /*
  * Arguments to the read call.
  */
 struct nfs_readargs {
+	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *		fh;
 	struct nfs_open_context *context;
 	struct nfs_lock_context *lock_context;
@@ -487,20 +488,20 @@ struct nfs_readargs {
 	__u32			count;
 	unsigned int		pgbase;
 	struct page **		pages;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_readres {
+	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr *	fattr;
 	__u32			count;
 	int                     eof;
-	struct nfs4_sequence_res	seq_res;
 };
 
 /*
  * Arguments to the write call.
  */
 struct nfs_writeargs {
+	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *		fh;
 	struct nfs_open_context *context;
 	struct nfs_lock_context *lock_context;
@@ -510,7 +511,6 @@ struct nfs_writeargs {
 	unsigned int		pgbase;
 	struct page **		pages;
 	const u32 *		bitmask;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_write_verifier {
@@ -523,65 +523,65 @@ struct nfs_writeverf {
 };
 
 struct nfs_writeres {
+	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr *	fattr;
 	struct nfs_writeverf *	verf;
 	__u32			count;
 	const struct nfs_server *server;
-	struct nfs4_sequence_res	seq_res;
 };
 
 /*
  * Arguments to the commit call.
  */
 struct nfs_commitargs {
+	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh		*fh;
 	__u64			offset;
 	__u32			count;
 	const u32		*bitmask;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_commitres {
+	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr	*fattr;
 	struct nfs_writeverf	*verf;
 	const struct nfs_server *server;
-	struct nfs4_sequence_res	seq_res;
 };
 
 /*
  * Common arguments to the unlink call
  */
 struct nfs_removeargs {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh	*fh;
 	struct qstr		name;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_removeres {
+	struct nfs4_sequence_res 	seq_res;
 	const struct nfs_server *server;
 	struct nfs_fattr	*dir_attr;
 	struct nfs4_change_info	cinfo;
-	struct nfs4_sequence_res 	seq_res;
 };
 
 /*
  * Common arguments to the rename call
  */
 struct nfs_renameargs {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh		*old_dir;
 	const struct nfs_fh		*new_dir;
 	const struct qstr		*old_name;
 	const struct qstr		*new_name;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_renameres {
+	struct nfs4_sequence_res	seq_res;
 	const struct nfs_server		*server;
 	struct nfs4_change_info		old_cinfo;
 	struct nfs_fattr		*old_fattr;
 	struct nfs4_change_info		new_cinfo;
 	struct nfs_fattr		*new_fattr;
-	struct nfs4_sequence_res	seq_res;
 };
 
 /*
@@ -622,20 +622,20 @@ struct nfs_createargs {
 };
 
 struct nfs_setattrargs {
+	struct nfs4_sequence_args 	seq_args;
 	struct nfs_fh *                 fh;
 	nfs4_stateid                    stateid;
 	struct iattr *                  iap;
 	const struct nfs_server *	server; /* Needed for name mapping */
 	const u32 *			bitmask;
-	struct nfs4_sequence_args 	seq_args;
 };
 
 struct nfs_setaclargs {
+	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *			fh;
 	size_t				acl_len;
 	unsigned int			acl_pgbase;
 	struct page **			acl_pages;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_setaclres {
@@ -643,27 +643,27 @@ struct nfs_setaclres {
 };
 
 struct nfs_getaclargs {
+	struct nfs4_sequence_args 	seq_args;
 	struct nfs_fh *			fh;
 	size_t				acl_len;
 	unsigned int			acl_pgbase;
 	struct page **			acl_pages;
-	struct nfs4_sequence_args 	seq_args;
 };
 
 /* getxattr ACL interface flags */
 #define NFS4_ACL_TRUNC		0x0001	/* ACL was truncated */
 struct nfs_getaclres {
+	struct nfs4_sequence_res	seq_res;
 	size_t				acl_len;
 	size_t				acl_data_offset;
 	int				acl_flags;
 	struct page *			acl_scratch;
-	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs_setattrres {
+	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr *              fattr;
 	const struct nfs_server *	server;
-	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs_linkargs {
@@ -828,21 +828,22 @@ struct nfs3_getaclres {
 typedef u64 clientid4;
 
 struct nfs4_accessargs {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *		fh;
 	const u32 *			bitmask;
 	u32				access;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_accessres {
+	struct nfs4_sequence_res	seq_res;
 	const struct nfs_server *	server;
 	struct nfs_fattr *		fattr;
 	u32				supported;
 	u32				access;
-	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_create_arg {
+	struct nfs4_sequence_args 	seq_args;
 	u32				ftype;
 	union {
 		struct {
@@ -859,88 +860,88 @@ struct nfs4_create_arg {
 	const struct iattr *		attrs;
 	const struct nfs_fh *		dir_fh;
 	const u32 *			bitmask;
-	struct nfs4_sequence_args 	seq_args;
 };
 
 struct nfs4_create_res {
+	struct nfs4_sequence_res	seq_res;
 	const struct nfs_server *	server;
 	struct nfs_fh *			fh;
 	struct nfs_fattr *		fattr;
 	struct nfs4_change_info		dir_cinfo;
-	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_fsinfo_arg {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *		fh;
 	const u32 *			bitmask;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_fsinfo_res {
-	struct nfs_fsinfo	       *fsinfo;
 	struct nfs4_sequence_res	seq_res;
+	struct nfs_fsinfo	       *fsinfo;
 };
 
 struct nfs4_getattr_arg {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *		fh;
 	const u32 *			bitmask;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_getattr_res {
+	struct nfs4_sequence_res	seq_res;
 	const struct nfs_server *	server;
 	struct nfs_fattr *		fattr;
-	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_link_arg {
+	struct nfs4_sequence_args 	seq_args;
 	const struct nfs_fh *		fh;
 	const struct nfs_fh *		dir_fh;
 	const struct qstr *		name;
 	const u32 *			bitmask;
-	struct nfs4_sequence_args 	seq_args;
 };
 
 struct nfs4_link_res {
+	struct nfs4_sequence_res	seq_res;
 	const struct nfs_server *	server;
 	struct nfs_fattr *		fattr;
 	struct nfs4_change_info		cinfo;
 	struct nfs_fattr *		dir_attr;
-	struct nfs4_sequence_res	seq_res;
 };
 
 
 struct nfs4_lookup_arg {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *		dir_fh;
 	const struct qstr *		name;
 	const u32 *			bitmask;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_lookup_res {
+	struct nfs4_sequence_res	seq_res;
 	const struct nfs_server *	server;
 	struct nfs_fattr *		fattr;
 	struct nfs_fh *			fh;
-	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_lookup_root_arg {
-	const u32 *			bitmask;
 	struct nfs4_sequence_args	seq_args;
+	const u32 *			bitmask;
 };
 
 struct nfs4_pathconf_arg {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *		fh;
 	const u32 *			bitmask;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_pathconf_res {
-	struct nfs_pathconf	       *pathconf;
 	struct nfs4_sequence_res	seq_res;
+	struct nfs_pathconf	       *pathconf;
 };
 
 struct nfs4_readdir_arg {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *		fh;
 	u64				cookie;
 	nfs4_verifier			verifier;
@@ -949,21 +950,20 @@ struct nfs4_readdir_arg {
 	unsigned int			pgbase;	/* zero-copy data */
 	const u32 *			bitmask;
 	int				plus;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_readdir_res {
+	struct nfs4_sequence_res	seq_res;
 	nfs4_verifier			verifier;
 	unsigned int			pgbase;
-	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_readlink {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *		fh;
 	unsigned int			pgbase;
 	unsigned int			pglen;   /* zero-copy data */
 	struct page **			pages;   /* zero-copy data */
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_readlink_res {
@@ -989,28 +989,28 @@ struct nfs4_setclientid_res {
 };
 
 struct nfs4_statfs_arg {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *		fh;
 	const u32 *			bitmask;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_statfs_res {
-	struct nfs_fsstat	       *fsstat;
 	struct nfs4_sequence_res	seq_res;
+	struct nfs_fsstat	       *fsstat;
 };
 
 struct nfs4_server_caps_arg {
-	struct nfs_fh		       *fhandle;
 	struct nfs4_sequence_args	seq_args;
+	struct nfs_fh		       *fhandle;
 };
 
 struct nfs4_server_caps_res {
+	struct nfs4_sequence_res	seq_res;
 	u32				attr_bitmask[3];
 	u32				acl_bitmask;
 	u32				has_links;
 	u32				has_symlinks;
 	u32				fh_expire_type;
-	struct nfs4_sequence_res	seq_res;
 };
 
 #define NFS4_PATHNAME_MAXCOMPONENTS 512
@@ -1036,16 +1036,16 @@ struct nfs4_fs_locations {
 };
 
 struct nfs4_fs_locations_arg {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *dir_fh;
 	const struct qstr *name;
 	struct page *page;
 	const u32 *bitmask;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_fs_locations_res {
-	struct nfs4_fs_locations       *fs_locations;
 	struct nfs4_sequence_res	seq_res;
+	struct nfs4_fs_locations       *fs_locations;
 };
 
 struct nfs4_secinfo_oid {
@@ -1070,14 +1070,14 @@ struct nfs4_secinfo_flavors {
 };
 
 struct nfs4_secinfo_arg {
+	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh		*dir_fh;
 	const struct qstr		*name;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_secinfo_res {
-	struct nfs4_secinfo_flavors	*flavors;
 	struct nfs4_sequence_res	seq_res;
+	struct nfs4_secinfo_flavors	*flavors;
 };
 
 #endif /* CONFIG_NFS_V4 */
@@ -1157,9 +1157,9 @@ struct nfs41_create_session_res {
 };
 
 struct nfs41_reclaim_complete_args {
+	struct nfs4_sequence_args	seq_args;
 	/* In the future extend to include curr_fh for use with migration */
 	unsigned char			one_fs:1;
-	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs41_reclaim_complete_res {
@@ -1169,28 +1169,28 @@ struct nfs41_reclaim_complete_res {
 #define SECINFO_STYLE_CURRENT_FH 0
 #define SECINFO_STYLE_PARENT 1
 struct nfs41_secinfo_no_name_args {
-	int				style;
 	struct nfs4_sequence_args	seq_args;
+	int				style;
 };
 
 struct nfs41_test_stateid_args {
-	nfs4_stateid			*stateid;
 	struct nfs4_sequence_args	seq_args;
+	nfs4_stateid			*stateid;
 };
 
 struct nfs41_test_stateid_res {
-	unsigned int			status;
 	struct nfs4_sequence_res	seq_res;
+	unsigned int			status;
 };
 
 struct nfs41_free_stateid_args {
-	nfs4_stateid			*stateid;
 	struct nfs4_sequence_args	seq_args;
+	nfs4_stateid			*stateid;
 };
 
 struct nfs41_free_stateid_res {
-	unsigned int			status;
 	struct nfs4_sequence_res	seq_res;
+	unsigned int			status;
 };
 
 #else
-- 
cgit v1.2.3-55-g7522


From c05eecf636101dd4347b2d8fa457626bf0088e0a Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Fri, 30 Nov 2012 23:59:29 -0500
Subject: SUNRPC: Don't allow low priority tasks to pre-empt higher priority
 ones

Currently, the priority queues attempt to be 'fair' to lower priority
tasks by scheduling them after a certain number of higher priority tasks
have run. The problem is that both the transport send queue and
the NFSv4.1 session slot queue have strong ordering requirements.

This patch therefore removes the fairness code in favour of strong
ordering of task priorities.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 include/linux/sunrpc/sched.h |  1 -
 net/sunrpc/sched.c           | 44 ++++++++++++++++++++++----------------------
 2 files changed, 22 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index dc0c3cc3ada3..b64f8eb0b973 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -192,7 +192,6 @@ struct rpc_wait_queue {
 	pid_t			owner;			/* process id of last task serviced */
 	unsigned char		maxpriority;		/* maximum priority (0 if queue is not a priority queue) */
 	unsigned char		priority;		/* current priority */
-	unsigned char		count;			/* # task groups remaining serviced so far */
 	unsigned char		nr;			/* # tasks remaining for cookie */
 	unsigned short		qlen;			/* total # tasks waiting in queue */
 	struct rpc_timer	timer_list;
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 1aefc9fef866..d17a704aaf5f 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -98,6 +98,23 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task)
 	list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list);
 }
 
+static void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority)
+{
+	queue->priority = priority;
+}
+
+static void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid)
+{
+	queue->owner = pid;
+	queue->nr = RPC_BATCH_COUNT;
+}
+
+static void rpc_reset_waitqueue_priority(struct rpc_wait_queue *queue)
+{
+	rpc_set_waitqueue_priority(queue, queue->maxpriority);
+	rpc_set_waitqueue_owner(queue, 0);
+}
+
 /*
  * Add new request to a priority queue.
  */
@@ -109,9 +126,11 @@ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue,
 	struct rpc_task *t;
 
 	INIT_LIST_HEAD(&task->u.tk_wait.links);
-	q = &queue->tasks[queue_priority];
 	if (unlikely(queue_priority > queue->maxpriority))
-		q = &queue->tasks[queue->maxpriority];
+		queue_priority = queue->maxpriority;
+	if (queue_priority > queue->priority)
+		rpc_set_waitqueue_priority(queue, queue_priority);
+	q = &queue->tasks[queue_priority];
 	list_for_each_entry(t, q, u.tk_wait.list) {
 		if (t->tk_owner == task->tk_owner) {
 			list_add_tail(&task->u.tk_wait.list, &t->u.tk_wait.links);
@@ -180,24 +199,6 @@ static void __rpc_remove_wait_queue(struct rpc_wait_queue *queue, struct rpc_tas
 			task->tk_pid, queue, rpc_qname(queue));
 }
 
-static inline void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority)
-{
-	queue->priority = priority;
-	queue->count = 1 << (priority * 2);
-}
-
-static inline void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid)
-{
-	queue->owner = pid;
-	queue->nr = RPC_BATCH_COUNT;
-}
-
-static inline void rpc_reset_waitqueue_priority(struct rpc_wait_queue *queue)
-{
-	rpc_set_waitqueue_priority(queue, queue->maxpriority);
-	rpc_set_waitqueue_owner(queue, 0);
-}
-
 static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const char *qname, unsigned char nr_queues)
 {
 	int i;
@@ -464,8 +465,7 @@ static struct rpc_task *__rpc_find_next_queued_priority(struct rpc_wait_queue *q
 		/*
 		 * Check if we need to switch queues.
 		 */
-		if (--queue->count)
-			goto new_owner;
+		goto new_owner;
 	}
 
 	/*
-- 
cgit v1.2.3-55-g7522


From 914daba865cb5c38cd5fdee024ca38029315b38f Mon Sep 17 00:00:00 2001
From: Alexander Graf
Date: Tue, 9 Oct 2012 00:22:59 +0200
Subject: KVM: Distangle eventfd code from irqchip

The current eventfd code assumes that when we have eventfd, we also have
irqfd for in-kernel interrupt delivery. This is not necessarily true. On
PPC we don't have an in-kernel irqchip yet, but we can still support easily
support eventfd.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 include/linux/kvm_host.h | 12 +++++++++++-
 virt/kvm/eventfd.c       |  6 ++++++
 2 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8e5c7b651655..c823e47c3641 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -900,10 +900,20 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 #ifdef CONFIG_HAVE_KVM_EVENTFD
 
 void kvm_eventfd_init(struct kvm *kvm);
+int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
+
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_irqfd_release(struct kvm *kvm);
 void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *);
-int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
+#else
+static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
+{
+	return -EINVAL;
+}
+
+static inline void kvm_irqfd_release(struct kvm *kvm) {}
+#endif
 
 #else
 
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 9718e98d6d2a..d7424c8c138a 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -35,6 +35,7 @@
 
 #include "iodev.h"
 
+#ifdef __KVM_HAVE_IOAPIC
 /*
  * --------------------------------------------------------------------
  * irqfd: Allows an fd to be used to inject an interrupt to the guest
@@ -425,17 +426,21 @@ fail:
 	kfree(irqfd);
 	return ret;
 }
+#endif
 
 void
 kvm_eventfd_init(struct kvm *kvm)
 {
+#ifdef __KVM_HAVE_IOAPIC
 	spin_lock_init(&kvm->irqfds.lock);
 	INIT_LIST_HEAD(&kvm->irqfds.items);
 	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
 	mutex_init(&kvm->irqfds.resampler_lock);
+#endif
 	INIT_LIST_HEAD(&kvm->ioeventfds);
 }
 
+#ifdef __KVM_HAVE_IOAPIC
 /*
  * shutdown any irqfd's that match fd+gsi
  */
@@ -555,6 +560,7 @@ static void __exit irqfd_module_exit(void)
 
 module_init(irqfd_module_init);
 module_exit(irqfd_module_exit);
+#endif
 
 /*
  * --------------------------------------------------------------------
-- 
cgit v1.2.3-55-g7522


From a2932923ccf63c419c77aaa18ac09be98f2c94d8 Mon Sep 17 00:00:00 2001
From: Paul Mackerras
Date: Mon, 19 Nov 2012 22:57:20 +0000
Subject: KVM: PPC: Book3S HV: Provide a method for userspace to read and write
 the HPT

A new ioctl, KVM_PPC_GET_HTAB_FD, returns a file descriptor.  Reads on
this fd return the contents of the HPT (hashed page table), writes
create and/or remove entries in the HPT.  There is a new capability,
KVM_CAP_PPC_HTAB_FD, to indicate the presence of the ioctl.  The ioctl
takes an argument structure with the index of the first HPT entry to
read out and a set of flags.  The flags indicate whether the user is
intending to read or write the HPT, and whether to return all entries
or only the "bolted" entries (those with the bolted bit, 0x10, set in
the first doubleword).

This is intended for use in implementing qemu's savevm/loadvm and for
live migration.  Therefore, on reads, the first pass returns information
about all HPTEs (or all bolted HPTEs).  When the first pass reaches the
end of the HPT, it returns from the read.  Subsequent reads only return
information about HPTEs that have changed since they were last read.
A read that finds no changed HPTEs in the HPT following where the last
read finished will return 0 bytes.

The format of the data provides a simple run-length compression of the
invalid entries.  Each block of data starts with a header that indicates
the index (position in the HPT, which is just an array), the number of
valid entries starting at that index (may be zero), and the number of
invalid entries following those valid entries.  The valid entries, 16
bytes each, follow the header.  The invalid entries are not explicitly
represented.

Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix documentation]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt        |  54 +++++
 arch/powerpc/include/asm/kvm_book3s_64.h |  22 ++
 arch/powerpc/include/asm/kvm_ppc.h       |   2 +
 arch/powerpc/include/uapi/asm/kvm.h      |  25 +++
 arch/powerpc/kvm/book3s_64_mmu_hv.c      | 344 +++++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv.c             |  12 --
 arch/powerpc/kvm/powerpc.c               |  17 ++
 include/uapi/linux/kvm.h                 |   3 +
 8 files changed, 467 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 6671fdc0afb1..a5607c571cb3 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2071,6 +2071,60 @@ KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
 
 Note that the vcpu ioctl is asynchronous to vcpu execution.
 
+4.78 KVM_PPC_GET_HTAB_FD
+
+Capability: KVM_CAP_PPC_HTAB_FD
+Architectures: powerpc
+Type: vm ioctl
+Parameters: Pointer to struct kvm_get_htab_fd (in)
+Returns: file descriptor number (>= 0) on success, -1 on error
+
+This returns a file descriptor that can be used either to read out the
+entries in the guest's hashed page table (HPT), or to write entries to
+initialize the HPT.  The returned fd can only be written to if the
+KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
+can only be read if that bit is clear.  The argument struct looks like
+this:
+
+/* For KVM_PPC_GET_HTAB_FD */
+struct kvm_get_htab_fd {
+	__u64	flags;
+	__u64	start_index;
+	__u64	reserved[2];
+};
+
+/* Values for kvm_get_htab_fd.flags */
+#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
+#define KVM_GET_HTAB_WRITE		((__u64)0x2)
+
+The `start_index' field gives the index in the HPT of the entry at
+which to start reading.  It is ignored when writing.
+
+Reads on the fd will initially supply information about all
+"interesting" HPT entries.  Interesting entries are those with the
+bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise
+all entries.  When the end of the HPT is reached, the read() will
+return.  If read() is called again on the fd, it will start again from
+the beginning of the HPT, but will only return HPT entries that have
+changed since they were last read.
+
+Data read or written is structured as a header (8 bytes) followed by a
+series of valid HPT entries (16 bytes) each.  The header indicates how
+many valid HPT entries there are and how many invalid entries follow
+the valid entries.  The invalid entries are not represented explicitly
+in the stream.  The header format is:
+
+struct kvm_get_htab_header {
+	__u32	index;
+	__u16	n_valid;
+	__u16	n_invalid;
+};
+
+Writes to the fd create HPT entries starting at the index given in the
+header; first `n_valid' valid entries with contents from the data
+written, then `n_invalid' invalid entries, invalidating any previously
+valid entries found.
+
 
 5. The kvm_run structure
 ------------------------
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index b322e5bd6964..38bec1dc9928 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -246,4 +246,26 @@ static inline bool slot_is_aligned(struct kvm_memory_slot *memslot,
 	return !(memslot->base_gfn & mask) && !(memslot->npages & mask);
 }
 
+/*
+ * This works for 4k, 64k and 16M pages on POWER7,
+ * and 4k and 16M pages on PPC970.
+ */
+static inline unsigned long slb_pgsize_encoding(unsigned long psize)
+{
+	unsigned long senc = 0;
+
+	if (psize > 0x1000) {
+		senc = SLB_VSID_L;
+		if (psize == 0x10000)
+			senc |= SLB_VSID_LP_01;
+	}
+	return senc;
+}
+
+static inline int is_vrma_hpte(unsigned long hpte_v)
+{
+	return (hpte_v & ~0xffffffUL) ==
+		(HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)));
+}
+
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 609cca3e9426..1ca31e92ee75 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -164,6 +164,8 @@ extern void kvmppc_bookehv_exit(void);
 
 extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu);
 
+extern int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *);
+
 /*
  * Cuts out inst bits with ordering according to spec.
  * That means the leftmost bit is zero. All given bits are included.
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index b89ae4db45ce..514883dd311e 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -331,6 +331,31 @@ struct kvm_book3e_206_tlb_params {
 	__u32 reserved[8];
 };
 
+/* For KVM_PPC_GET_HTAB_FD */
+struct kvm_get_htab_fd {
+	__u64	flags;
+	__u64	start_index;
+	__u64	reserved[2];
+};
+
+/* Values for kvm_get_htab_fd.flags */
+#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
+#define KVM_GET_HTAB_WRITE		((__u64)0x2)
+
+/*
+ * Data read on the file descriptor is formatted as a series of
+ * records, each consisting of a header followed by a series of
+ * `n_valid' HPTEs (16 bytes each), which are all valid.  Following
+ * those valid HPTEs there are `n_invalid' invalid HPTEs, which
+ * are not represented explicitly in the stream.  The same format
+ * is used for writing.
+ */
+struct kvm_get_htab_header {
+	__u32	index;
+	__u16	n_valid;
+	__u16	n_invalid;
+};
+
 #define KVM_REG_PPC_HIOR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x1)
 #define KVM_REG_PPC_IAC1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x2)
 #define KVM_REG_PPC_IAC2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 6ee6516a0bee..0aa40734c8f6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -25,6 +25,8 @@
 #include <linux/hugetlb.h>
 #include <linux/vmalloc.h>
 #include <linux/srcu.h>
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -1145,6 +1147,348 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
 	put_page(page);
 }
 
+/*
+ * Functions for reading and writing the hash table via reads and
+ * writes on a file descriptor.
+ *
+ * Reads return the guest view of the hash table, which has to be
+ * pieced together from the real hash table and the guest_rpte
+ * values in the revmap array.
+ *
+ * On writes, each HPTE written is considered in turn, and if it
+ * is valid, it is written to the HPT as if an H_ENTER with the
+ * exact flag set was done.  When the invalid count is non-zero
+ * in the header written to the stream, the kernel will make
+ * sure that that many HPTEs are invalid, and invalidate them
+ * if not.
+ */
+
+struct kvm_htab_ctx {
+	unsigned long	index;
+	unsigned long	flags;
+	struct kvm	*kvm;
+	int		first_pass;
+};
+
+#define HPTE_SIZE	(2 * sizeof(unsigned long))
+
+static long record_hpte(unsigned long flags, unsigned long *hptp,
+			unsigned long *hpte, struct revmap_entry *revp,
+			int want_valid, int first_pass)
+{
+	unsigned long v, r;
+	int ok = 1;
+	int valid, dirty;
+
+	/* Unmodified entries are uninteresting except on the first pass */
+	dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED);
+	if (!first_pass && !dirty)
+		return 0;
+
+	valid = 0;
+	if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT)) {
+		valid = 1;
+		if ((flags & KVM_GET_HTAB_BOLTED_ONLY) &&
+		    !(hptp[0] & HPTE_V_BOLTED))
+			valid = 0;
+	}
+	if (valid != want_valid)
+		return 0;
+
+	v = r = 0;
+	if (valid || dirty) {
+		/* lock the HPTE so it's stable and read it */
+		preempt_disable();
+		while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
+			cpu_relax();
+		v = hptp[0];
+		if (v & HPTE_V_ABSENT) {
+			v &= ~HPTE_V_ABSENT;
+			v |= HPTE_V_VALID;
+		}
+		/* re-evaluate valid and dirty from synchronized HPTE value */
+		valid = !!(v & HPTE_V_VALID);
+		if ((flags & KVM_GET_HTAB_BOLTED_ONLY) && !(v & HPTE_V_BOLTED))
+			valid = 0;
+		r = revp->guest_rpte | (hptp[1] & (HPTE_R_R | HPTE_R_C));
+		dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED);
+		/* only clear modified if this is the right sort of entry */
+		if (valid == want_valid && dirty) {
+			r &= ~HPTE_GR_MODIFIED;
+			revp->guest_rpte = r;
+		}
+		asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
+		hptp[0] &= ~HPTE_V_HVLOCK;
+		preempt_enable();
+		if (!(valid == want_valid && (first_pass || dirty)))
+			ok = 0;
+	}
+	hpte[0] = v;
+	hpte[1] = r;
+	return ok;
+}
+
+static ssize_t kvm_htab_read(struct file *file, char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct kvm_htab_ctx *ctx = file->private_data;
+	struct kvm *kvm = ctx->kvm;
+	struct kvm_get_htab_header hdr;
+	unsigned long *hptp;
+	struct revmap_entry *revp;
+	unsigned long i, nb, nw;
+	unsigned long __user *lbuf;
+	struct kvm_get_htab_header __user *hptr;
+	unsigned long flags;
+	int first_pass;
+	unsigned long hpte[2];
+
+	if (!access_ok(VERIFY_WRITE, buf, count))
+		return -EFAULT;
+
+	first_pass = ctx->first_pass;
+	flags = ctx->flags;
+
+	i = ctx->index;
+	hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+	revp = kvm->arch.revmap + i;
+	lbuf = (unsigned long __user *)buf;
+
+	nb = 0;
+	while (nb + sizeof(hdr) + HPTE_SIZE < count) {
+		/* Initialize header */
+		hptr = (struct kvm_get_htab_header __user *)buf;
+		hdr.index = i;
+		hdr.n_valid = 0;
+		hdr.n_invalid = 0;
+		nw = nb;
+		nb += sizeof(hdr);
+		lbuf = (unsigned long __user *)(buf + sizeof(hdr));
+
+		/* Skip uninteresting entries, i.e. clean on not-first pass */
+		if (!first_pass) {
+			while (i < kvm->arch.hpt_npte &&
+			       !(revp->guest_rpte & HPTE_GR_MODIFIED)) {
+				++i;
+				hptp += 2;
+				++revp;
+			}
+		}
+
+		/* Grab a series of valid entries */
+		while (i < kvm->arch.hpt_npte &&
+		       hdr.n_valid < 0xffff &&
+		       nb + HPTE_SIZE < count &&
+		       record_hpte(flags, hptp, hpte, revp, 1, first_pass)) {
+			/* valid entry, write it out */
+			++hdr.n_valid;
+			if (__put_user(hpte[0], lbuf) ||
+			    __put_user(hpte[1], lbuf + 1))
+				return -EFAULT;
+			nb += HPTE_SIZE;
+			lbuf += 2;
+			++i;
+			hptp += 2;
+			++revp;
+		}
+		/* Now skip invalid entries while we can */
+		while (i < kvm->arch.hpt_npte &&
+		       hdr.n_invalid < 0xffff &&
+		       record_hpte(flags, hptp, hpte, revp, 0, first_pass)) {
+			/* found an invalid entry */
+			++hdr.n_invalid;
+			++i;
+			hptp += 2;
+			++revp;
+		}
+
+		if (hdr.n_valid || hdr.n_invalid) {
+			/* write back the header */
+			if (__copy_to_user(hptr, &hdr, sizeof(hdr)))
+				return -EFAULT;
+			nw = nb;
+			buf = (char __user *)lbuf;
+		} else {
+			nb = nw;
+		}
+
+		/* Check if we've wrapped around the hash table */
+		if (i >= kvm->arch.hpt_npte) {
+			i = 0;
+			ctx->first_pass = 0;
+			break;
+		}
+	}
+
+	ctx->index = i;
+
+	return nb;
+}
+
+static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	struct kvm_htab_ctx *ctx = file->private_data;
+	struct kvm *kvm = ctx->kvm;
+	struct kvm_get_htab_header hdr;
+	unsigned long i, j;
+	unsigned long v, r;
+	unsigned long __user *lbuf;
+	unsigned long *hptp;
+	unsigned long tmp[2];
+	ssize_t nb;
+	long int err, ret;
+	int rma_setup;
+
+	if (!access_ok(VERIFY_READ, buf, count))
+		return -EFAULT;
+
+	/* lock out vcpus from running while we're doing this */
+	mutex_lock(&kvm->lock);
+	rma_setup = kvm->arch.rma_setup_done;
+	if (rma_setup) {
+		kvm->arch.rma_setup_done = 0;	/* temporarily */
+		/* order rma_setup_done vs. vcpus_running */
+		smp_mb();
+		if (atomic_read(&kvm->arch.vcpus_running)) {
+			kvm->arch.rma_setup_done = 1;
+			mutex_unlock(&kvm->lock);
+			return -EBUSY;
+		}
+	}
+
+	err = 0;
+	for (nb = 0; nb + sizeof(hdr) <= count; ) {
+		err = -EFAULT;
+		if (__copy_from_user(&hdr, buf, sizeof(hdr)))
+			break;
+
+		err = 0;
+		if (nb + hdr.n_valid * HPTE_SIZE > count)
+			break;
+
+		nb += sizeof(hdr);
+		buf += sizeof(hdr);
+
+		err = -EINVAL;
+		i = hdr.index;
+		if (i >= kvm->arch.hpt_npte ||
+		    i + hdr.n_valid + hdr.n_invalid > kvm->arch.hpt_npte)
+			break;
+
+		hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+		lbuf = (unsigned long __user *)buf;
+		for (j = 0; j < hdr.n_valid; ++j) {
+			err = -EFAULT;
+			if (__get_user(v, lbuf) || __get_user(r, lbuf + 1))
+				goto out;
+			err = -EINVAL;
+			if (!(v & HPTE_V_VALID))
+				goto out;
+			lbuf += 2;
+			nb += HPTE_SIZE;
+
+			if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT))
+				kvmppc_do_h_remove(kvm, 0, i, 0, tmp);
+			err = -EIO;
+			ret = kvmppc_virtmode_do_h_enter(kvm, H_EXACT, i, v, r,
+							 tmp);
+			if (ret != H_SUCCESS) {
+				pr_err("kvm_htab_write ret %ld i=%ld v=%lx "
+				       "r=%lx\n", ret, i, v, r);
+				goto out;
+			}
+			if (!rma_setup && is_vrma_hpte(v)) {
+				unsigned long psize = hpte_page_size(v, r);
+				unsigned long senc = slb_pgsize_encoding(psize);
+				unsigned long lpcr;
+
+				kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
+					(VRMA_VSID << SLB_VSID_SHIFT_1T);
+				lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
+				lpcr |= senc << (LPCR_VRMASD_SH - 4);
+				kvm->arch.lpcr = lpcr;
+				rma_setup = 1;
+			}
+			++i;
+			hptp += 2;
+		}
+
+		for (j = 0; j < hdr.n_invalid; ++j) {
+			if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT))
+				kvmppc_do_h_remove(kvm, 0, i, 0, tmp);
+			++i;
+			hptp += 2;
+		}
+		err = 0;
+	}
+
+ out:
+	/* Order HPTE updates vs. rma_setup_done */
+	smp_wmb();
+	kvm->arch.rma_setup_done = rma_setup;
+	mutex_unlock(&kvm->lock);
+
+	if (err)
+		return err;
+	return nb;
+}
+
+static int kvm_htab_release(struct inode *inode, struct file *filp)
+{
+	struct kvm_htab_ctx *ctx = filp->private_data;
+
+	filp->private_data = NULL;
+	if (!(ctx->flags & KVM_GET_HTAB_WRITE))
+		atomic_dec(&ctx->kvm->arch.hpte_mod_interest);
+	kvm_put_kvm(ctx->kvm);
+	kfree(ctx);
+	return 0;
+}
+
+static struct file_operations kvm_htab_fops = {
+	.read		= kvm_htab_read,
+	.write		= kvm_htab_write,
+	.llseek		= default_llseek,
+	.release	= kvm_htab_release,
+};
+
+int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
+{
+	int ret;
+	struct kvm_htab_ctx *ctx;
+	int rwflag;
+
+	/* reject flags we don't recognize */
+	if (ghf->flags & ~(KVM_GET_HTAB_BOLTED_ONLY | KVM_GET_HTAB_WRITE))
+		return -EINVAL;
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	kvm_get_kvm(kvm);
+	ctx->kvm = kvm;
+	ctx->index = ghf->start_index;
+	ctx->flags = ghf->flags;
+	ctx->first_pass = 1;
+
+	rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY;
+	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag);
+	if (ret < 0) {
+		kvm_put_kvm(kvm);
+		return ret;
+	}
+
+	if (rwflag == O_RDONLY) {
+		mutex_lock(&kvm->slots_lock);
+		atomic_inc(&kvm->arch.hpte_mod_interest);
+		/* make sure kvmppc_do_h_enter etc. see the increment */
+		synchronize_srcu_expedited(&kvm->srcu);
+		mutex_unlock(&kvm->slots_lock);
+	}
+
+	return ret;
+}
+
 void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_mmu *mmu = &vcpu->arch.mmu;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 843eb754a1d5..a4f59dbcd800 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1563,18 +1563,6 @@ out:
 	return r;
 }
 
-static unsigned long slb_pgsize_encoding(unsigned long psize)
-{
-	unsigned long senc = 0;
-
-	if (psize > 0x1000) {
-		senc = SLB_VSID_L;
-		if (psize == 0x10000)
-			senc |= SLB_VSID_LP_01;
-	}
-	return senc;
-}
-
 static void unpin_slot(struct kvm_memory_slot *memslot)
 {
 	unsigned long *physp;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index d583ea15e151..70739a089560 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -354,6 +354,12 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = 1;
 #else
 		r = 0;
+		break;
+#endif
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	case KVM_CAP_PPC_HTAB_FD:
+		r = 1;
+		break;
 #endif
 		break;
 	case KVM_CAP_NR_VCPUS:
@@ -954,6 +960,17 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+
+	case KVM_PPC_GET_HTAB_FD: {
+		struct kvm *kvm = filp->private_data;
+		struct kvm_get_htab_fd ghf;
+
+		r = -EFAULT;
+		if (copy_from_user(&ghf, argp, sizeof(ghf)))
+			break;
+		r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
+		break;
+	}
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 494a84c37c3e..e6e5d4b13708 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -634,6 +634,7 @@ struct kvm_ppc_smmu_info {
 #endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
+#define KVM_CAP_PPC_HTAB_FD 84
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -859,6 +860,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
 /* Available with KVM_CAP_RMA */
 #define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
+/* Available with KVM_CAP_PPC_HTAB_FD */
+#define KVM_PPC_GET_HTAB_FD	  _IOW(KVMIO,  0xaa, struct kvm_get_htab_fd)
 
 /*
  * ioctls for vcpu fds
-- 
cgit v1.2.3-55-g7522


From cf66bb93e0f75e0a4ba1ec070692618fa028e994 Mon Sep 17 00:00:00 2001
From: David Woodhouse
Date: Mon, 3 Dec 2012 16:25:40 +0000
Subject: byteorder: allow arch to opt to use GCC intrinsics for byteswapping

Since GCC 4.4, there have been __builtin_bswap32() and __builtin_bswap16()
intrinsics. A __builtin_bswap16() came a little later (4.6 for PowerPC,
48 for other platforms).

By using these instead of the inline assembler that most architectures
have in their __arch_swabXX() macros, we let the compiler see what's
actually happening. The resulting code should be at least as good, and
much *better* in the cases where it can be combined with a nearby load
or store, using a load-and-byteswap or store-and-byteswap instruction
(e.g. lwbrx/stwbrx on PowerPC, movbe on Atom).

When GCC is sufficiently recent *and* the architecture opts in to using
the intrinsics by setting CONFIG_ARCH_USE_BUILTIN_BSWAP, they will be
used in preference to the __arch_swabXX() macros. An architecture which
does not set ARCH_USE_BUILTIN_BSWAP will continue to use its own
hand-crafted macros.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/Kconfig                   | 19 +++++++++++++++++++
 include/linux/compiler-gcc4.h  | 10 ++++++++++
 include/linux/compiler-intel.h |  7 +++++++
 include/uapi/linux/swab.h      | 12 +++++++++---
 4 files changed, 45 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index 366ec06a5185..c31416b10586 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -112,6 +112,25 @@ config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	  See Documentation/unaligned-memory-access.txt for more
 	  information on the topic of unaligned memory accesses.
 
+config ARCH_USE_BUILTIN_BSWAP
+       bool
+       help
+	 Modern versions of GCC (since 4.4) have builtin functions
+	 for handling byte-swapping. Using these, instead of the old
+	 inline assembler that the architecture code provides in the
+	 __arch_bswapXX() macros, allows the compiler to see what's
+	 happening and offers more opportunity for optimisation. In
+	 particular, the compiler will be able to combine the byteswap
+	 with a nearby load or store and use load-and-swap or
+	 store-and-swap instructions if the architecture has them. It
+	 should almost *never* result in code which is worse than the
+	 hand-coded assembler in <asm/swab.h>.  But just in case it
+	 does, the use of the builtins is optional.
+
+	 Any architecture with load-and-swap or store-and-swap
+	 instructions should set this. And it shouldn't hurt to set it
+	 on architectures that don't have such instructions.
+
 config HAVE_SYSCALL_WRAPPERS
 	bool
 
diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index 412bc6c2b023..dc16a858e77c 100644
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -63,3 +63,13 @@
 #define __compiletime_warning(message) __attribute__((warning(message)))
 #define __compiletime_error(message) __attribute__((error(message)))
 #endif
+
+#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+#if __GNUC_MINOR__ >= 4
+#define __HAVE_BUILTIN_BSWAP32__
+#define __HAVE_BUILTIN_BSWAP64__
+#endif
+#if __GNUC_MINOR__ >= 8 || (defined(__powerpc__) && __GNUC_MINOR__ >= 6)
+#define __HAVE_BUILTIN_BSWAP16__
+#endif
+#endif
diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h
index d8e636e5607d..973ce10c40b6 100644
--- a/include/linux/compiler-intel.h
+++ b/include/linux/compiler-intel.h
@@ -29,3 +29,10 @@
 #endif
 
 #define uninitialized_var(x) x
+
+#ifndef __HAVE_BUILTIN_BSWAP16__
+/* icc has this, but it's called _bswap16 */
+#define __HAVE_BUILTIN_BSWAP16__
+#define __builtin_bswap16 _bswap16
+#endif
+
diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h
index e811474724c2..0e011eb91b5d 100644
--- a/include/uapi/linux/swab.h
+++ b/include/uapi/linux/swab.h
@@ -45,7 +45,9 @@
 
 static inline __attribute_const__ __u16 __fswab16(__u16 val)
 {
-#ifdef __arch_swab16
+#ifdef __HAVE_BUILTIN_BSWAP16__
+	return __builtin_bswap16(val);
+#elif defined (__arch_swab16)
 	return __arch_swab16(val);
 #else
 	return ___constant_swab16(val);
@@ -54,7 +56,9 @@ static inline __attribute_const__ __u16 __fswab16(__u16 val)
 
 static inline __attribute_const__ __u32 __fswab32(__u32 val)
 {
-#ifdef __arch_swab32
+#ifdef __HAVE_BUILTIN_BSWAP32__
+	return __builtin_bswap32(val);
+#elif defined(__arch_swab32)
 	return __arch_swab32(val);
 #else
 	return ___constant_swab32(val);
@@ -63,7 +67,9 @@ static inline __attribute_const__ __u32 __fswab32(__u32 val)
 
 static inline __attribute_const__ __u64 __fswab64(__u64 val)
 {
-#ifdef __arch_swab64
+#ifdef __HAVE_BUILTIN_BSWAP64__
+	return __builtin_bswap64(val);
+#elif defined (__arch_swab64)
 	return __arch_swab64(val);
 #elif defined(__SWAB_64_THRU_32__)
 	__u32 h = val >> 32;
-- 
cgit v1.2.3-55-g7522


From d1e7de3007c6e34c5e6d5e1b707b5aba4a1cd57f Mon Sep 17 00:00:00 2001
From: Marek Szyprowski
Date: Tue, 4 Dec 2012 15:01:01 +0100
Subject: regulators: add regulator_can_change_voltage() function

Introduce a regulator_can_change_voltage() function for the subsytems or
drivers which might check if applying voltage change is possible and use
special workaround code when the driver is used with fixed regulators or
regulators with disabled ability to change the voltage.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 drivers/regulator/core.c           | 22 ++++++++++++++++++++++
 include/linux/regulator/consumer.h |  1 +
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index e872c8be080e..59e08633372a 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1866,6 +1866,28 @@ int regulator_is_enabled(struct regulator *regulator)
 }
 EXPORT_SYMBOL_GPL(regulator_is_enabled);
 
+/**
+ * regulator_can_change_voltage - check if regulator can change voltage
+ * @regulator: regulator source
+ *
+ * Returns positive if the regulator driver backing the source/client
+ * can change its voltage, false otherwise. Usefull for detecting fixed
+ * or dummy regulators and disabling voltage change logic in the client
+ * driver.
+ */
+int regulator_can_change_voltage(struct regulator *regulator)
+{
+	struct regulator_dev	*rdev = regulator->rdev;
+
+	if (rdev->constraints &&
+	    rdev->constraints->valid_ops_mask & REGULATOR_CHANGE_VOLTAGE &&
+	    rdev->desc->n_voltages > 1)
+		return 1;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(regulator_can_change_voltage);
+
 /**
  * regulator_count_voltages - count regulator_list_voltage() selectors
  * @regulator: regulator source
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index c43cd3556b1f..5d0f7c10bef1 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -160,6 +160,7 @@ int regulator_bulk_force_disable(int num_consumers,
 void regulator_bulk_free(int num_consumers,
 			 struct regulator_bulk_data *consumers);
 
+int regulator_can_change_voltage(struct regulator *regulator);
 int regulator_count_voltages(struct regulator *regulator);
 int regulator_list_voltage(struct regulator *regulator, unsigned selector);
 int regulator_is_supported_voltage(struct regulator *regulator,
-- 
cgit v1.2.3-55-g7522


From 044ab5257806310a0150146df3b74b8adaa4ebcf Mon Sep 17 00:00:00 2001
From: Jussi Kivilinna
Date: Tue, 13 Nov 2012 11:43:14 +0200
Subject: crypto: cast5/cast6 - move lookup tables to shared module

CAST5 and CAST6 both use same lookup tables, which can be moved shared module
'cast_common'.

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/x86/crypto/cast5-avx-x86_64-asm_64.S |  16 +-
 arch/x86/crypto/cast6-avx-x86_64-asm_64.S |  16 +-
 crypto/Kconfig                            |  10 ++
 crypto/Makefile                           |   1 +
 crypto/cast5_generic.c                    | 277 +---------------------------
 crypto/cast6_generic.c                    | 280 +----------------------------
 crypto/cast_common.c                      | 290 ++++++++++++++++++++++++++++++
 include/crypto/cast5.h                    |   6 +-
 include/crypto/cast6.h                    |   6 +-
 include/crypto/cast_common.h              |   9 +
 10 files changed, 336 insertions(+), 575 deletions(-)
 create mode 100644 crypto/cast_common.c
 create mode 100644 include/crypto/cast_common.h

(limited to 'include')

diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
index 12478e472368..15b00ac7cbd3 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -25,10 +25,10 @@
 
 .file "cast5-avx-x86_64-asm_64.S"
 
-.extern cast5_s1
-.extern cast5_s2
-.extern cast5_s3
-.extern cast5_s4
+.extern cast_s1
+.extern cast_s2
+.extern cast_s3
+.extern cast_s4
 
 /* structure of crypto context */
 #define km	0
@@ -36,10 +36,10 @@
 #define rr	((16*4)+16)
 
 /* s-boxes */
-#define s1	cast5_s1
-#define s2	cast5_s2
-#define s3	cast5_s3
-#define s4	cast5_s4
+#define s1	cast_s1
+#define s2	cast_s2
+#define s3	cast_s3
+#define s4	cast_s4
 
 /**********************************************************************
   16-way AVX cast5
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index 83a53818f0a5..2569d0da841f 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -27,20 +27,20 @@
 
 .file "cast6-avx-x86_64-asm_64.S"
 
-.extern cast6_s1
-.extern cast6_s2
-.extern cast6_s3
-.extern cast6_s4
+.extern cast_s1
+.extern cast_s2
+.extern cast_s3
+.extern cast_s4
 
 /* structure of crypto context */
 #define km	0
 #define kr	(12*4*4)
 
 /* s-boxes */
-#define s1	cast6_s1
-#define s2	cast6_s2
-#define s3	cast6_s3
-#define s4	cast6_s4
+#define s1	cast_s1
+#define s2	cast_s2
+#define s3	cast_s3
+#define s4	cast_s4
 
 /**********************************************************************
   8-way AVX cast6
diff --git a/crypto/Kconfig b/crypto/Kconfig
index c226b2c7e47c..4641d95651d3 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -841,9 +841,16 @@ config CRYPTO_CAMELLIA_SPARC64
 	  See also:
 	  <https://info.isl.ntt.co.jp/crypt/eng/camellia/index_s.html>
 
+config CRYPTO_CAST_COMMON
+	tristate
+	help
+	  Common parts of the CAST cipher algorithms shared by the
+	  generic c and the assembler implementations.
+
 config CRYPTO_CAST5
 	tristate "CAST5 (CAST-128) cipher algorithm"
 	select CRYPTO_ALGAPI
+	select CRYPTO_CAST_COMMON
 	help
 	  The CAST5 encryption algorithm (synonymous with CAST-128) is
 	  described in RFC2144.
@@ -854,6 +861,7 @@ config CRYPTO_CAST5_AVX_X86_64
 	select CRYPTO_ALGAPI
 	select CRYPTO_CRYPTD
 	select CRYPTO_ABLK_HELPER_X86
+	select CRYPTO_CAST_COMMON
 	select CRYPTO_CAST5
 	help
 	  The CAST5 encryption algorithm (synonymous with CAST-128) is
@@ -865,6 +873,7 @@ config CRYPTO_CAST5_AVX_X86_64
 config CRYPTO_CAST6
 	tristate "CAST6 (CAST-256) cipher algorithm"
 	select CRYPTO_ALGAPI
+	select CRYPTO_CAST_COMMON
 	help
 	  The CAST6 encryption algorithm (synonymous with CAST-256) is
 	  described in RFC2612.
@@ -876,6 +885,7 @@ config CRYPTO_CAST6_AVX_X86_64
 	select CRYPTO_CRYPTD
 	select CRYPTO_ABLK_HELPER_X86
 	select CRYPTO_GLUE_HELPER_X86
+	select CRYPTO_CAST_COMMON
 	select CRYPTO_CAST6
 	select CRYPTO_LRW
 	select CRYPTO_XTS
diff --git a/crypto/Makefile b/crypto/Makefile
index 8cf61ffe3513..d59dec749804 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -68,6 +68,7 @@ obj-$(CONFIG_CRYPTO_TWOFISH_COMMON) += twofish_common.o
 obj-$(CONFIG_CRYPTO_SERPENT) += serpent_generic.o
 obj-$(CONFIG_CRYPTO_AES) += aes_generic.o
 obj-$(CONFIG_CRYPTO_CAMELLIA) += camellia_generic.o
+obj-$(CONFIG_CRYPTO_CAST_COMMON) += cast_common.o
 obj-$(CONFIG_CRYPTO_CAST5) += cast5_generic.o
 obj-$(CONFIG_CRYPTO_CAST6) += cast6_generic.o
 obj-$(CONFIG_CRYPTO_ARC4) += arc4.o
diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c
index bc525dbd8a4b..5558f630a0eb 100644
--- a/crypto/cast5_generic.c
+++ b/crypto/cast5_generic.c
@@ -30,275 +30,6 @@
 #include <linux/types.h>
 #include <crypto/cast5.h>
 
-
-const u32 cast5_s1[256] = {
-	0x30fb40d4, 0x9fa0ff0b, 0x6beccd2f, 0x3f258c7a, 0x1e213f2f,
-	0x9c004dd3, 0x6003e540, 0xcf9fc949,
-	0xbfd4af27, 0x88bbbdb5, 0xe2034090, 0x98d09675, 0x6e63a0e0,
-	0x15c361d2, 0xc2e7661d, 0x22d4ff8e,
-	0x28683b6f, 0xc07fd059, 0xff2379c8, 0x775f50e2, 0x43c340d3,
-	0xdf2f8656, 0x887ca41a, 0xa2d2bd2d,
-	0xa1c9e0d6, 0x346c4819, 0x61b76d87, 0x22540f2f, 0x2abe32e1,
-	0xaa54166b, 0x22568e3a, 0xa2d341d0,
-	0x66db40c8, 0xa784392f, 0x004dff2f, 0x2db9d2de, 0x97943fac,
-	0x4a97c1d8, 0x527644b7, 0xb5f437a7,
-	0xb82cbaef, 0xd751d159, 0x6ff7f0ed, 0x5a097a1f, 0x827b68d0,
-	0x90ecf52e, 0x22b0c054, 0xbc8e5935,
-	0x4b6d2f7f, 0x50bb64a2, 0xd2664910, 0xbee5812d, 0xb7332290,
-	0xe93b159f, 0xb48ee411, 0x4bff345d,
-	0xfd45c240, 0xad31973f, 0xc4f6d02e, 0x55fc8165, 0xd5b1caad,
-	0xa1ac2dae, 0xa2d4b76d, 0xc19b0c50,
-	0x882240f2, 0x0c6e4f38, 0xa4e4bfd7, 0x4f5ba272, 0x564c1d2f,
-	0xc59c5319, 0xb949e354, 0xb04669fe,
-	0xb1b6ab8a, 0xc71358dd, 0x6385c545, 0x110f935d, 0x57538ad5,
-	0x6a390493, 0xe63d37e0, 0x2a54f6b3,
-	0x3a787d5f, 0x6276a0b5, 0x19a6fcdf, 0x7a42206a, 0x29f9d4d5,
-	0xf61b1891, 0xbb72275e, 0xaa508167,
-	0x38901091, 0xc6b505eb, 0x84c7cb8c, 0x2ad75a0f, 0x874a1427,
-	0xa2d1936b, 0x2ad286af, 0xaa56d291,
-	0xd7894360, 0x425c750d, 0x93b39e26, 0x187184c9, 0x6c00b32d,
-	0x73e2bb14, 0xa0bebc3c, 0x54623779,
-	0x64459eab, 0x3f328b82, 0x7718cf82, 0x59a2cea6, 0x04ee002e,
-	0x89fe78e6, 0x3fab0950, 0x325ff6c2,
-	0x81383f05, 0x6963c5c8, 0x76cb5ad6, 0xd49974c9, 0xca180dcf,
-	0x380782d5, 0xc7fa5cf6, 0x8ac31511,
-	0x35e79e13, 0x47da91d0, 0xf40f9086, 0xa7e2419e, 0x31366241,
-	0x051ef495, 0xaa573b04, 0x4a805d8d,
-	0x548300d0, 0x00322a3c, 0xbf64cddf, 0xba57a68e, 0x75c6372b,
-	0x50afd341, 0xa7c13275, 0x915a0bf5,
-	0x6b54bfab, 0x2b0b1426, 0xab4cc9d7, 0x449ccd82, 0xf7fbf265,
-	0xab85c5f3, 0x1b55db94, 0xaad4e324,
-	0xcfa4bd3f, 0x2deaa3e2, 0x9e204d02, 0xc8bd25ac, 0xeadf55b3,
-	0xd5bd9e98, 0xe31231b2, 0x2ad5ad6c,
-	0x954329de, 0xadbe4528, 0xd8710f69, 0xaa51c90f, 0xaa786bf6,
-	0x22513f1e, 0xaa51a79b, 0x2ad344cc,
-	0x7b5a41f0, 0xd37cfbad, 0x1b069505, 0x41ece491, 0xb4c332e6,
-	0x032268d4, 0xc9600acc, 0xce387e6d,
-	0xbf6bb16c, 0x6a70fb78, 0x0d03d9c9, 0xd4df39de, 0xe01063da,
-	0x4736f464, 0x5ad328d8, 0xb347cc96,
-	0x75bb0fc3, 0x98511bfb, 0x4ffbcc35, 0xb58bcf6a, 0xe11f0abc,
-	0xbfc5fe4a, 0xa70aec10, 0xac39570a,
-	0x3f04442f, 0x6188b153, 0xe0397a2e, 0x5727cb79, 0x9ceb418f,
-	0x1cacd68d, 0x2ad37c96, 0x0175cb9d,
-	0xc69dff09, 0xc75b65f0, 0xd9db40d8, 0xec0e7779, 0x4744ead4,
-	0xb11c3274, 0xdd24cb9e, 0x7e1c54bd,
-	0xf01144f9, 0xd2240eb1, 0x9675b3fd, 0xa3ac3755, 0xd47c27af,
-	0x51c85f4d, 0x56907596, 0xa5bb15e6,
-	0x580304f0, 0xca042cf1, 0x011a37ea, 0x8dbfaadb, 0x35ba3e4a,
-	0x3526ffa0, 0xc37b4d09, 0xbc306ed9,
-	0x98a52666, 0x5648f725, 0xff5e569d, 0x0ced63d0, 0x7c63b2cf,
-	0x700b45e1, 0xd5ea50f1, 0x85a92872,
-	0xaf1fbda7, 0xd4234870, 0xa7870bf3, 0x2d3b4d79, 0x42e04198,
-	0x0cd0ede7, 0x26470db8, 0xf881814c,
-	0x474d6ad7, 0x7c0c5e5c, 0xd1231959, 0x381b7298, 0xf5d2f4db,
-	0xab838653, 0x6e2f1e23, 0x83719c9e,
-	0xbd91e046, 0x9a56456e, 0xdc39200c, 0x20c8c571, 0x962bda1c,
-	0xe1e696ff, 0xb141ab08, 0x7cca89b9,
-	0x1a69e783, 0x02cc4843, 0xa2f7c579, 0x429ef47d, 0x427b169c,
-	0x5ac9f049, 0xdd8f0f00, 0x5c8165bf
-};
-EXPORT_SYMBOL_GPL(cast5_s1);
-const u32 cast5_s2[256] = {
-	0x1f201094, 0xef0ba75b, 0x69e3cf7e, 0x393f4380, 0xfe61cf7a,
-	0xeec5207a, 0x55889c94, 0x72fc0651,
-	0xada7ef79, 0x4e1d7235, 0xd55a63ce, 0xde0436ba, 0x99c430ef,
-	0x5f0c0794, 0x18dcdb7d, 0xa1d6eff3,
-	0xa0b52f7b, 0x59e83605, 0xee15b094, 0xe9ffd909, 0xdc440086,
-	0xef944459, 0xba83ccb3, 0xe0c3cdfb,
-	0xd1da4181, 0x3b092ab1, 0xf997f1c1, 0xa5e6cf7b, 0x01420ddb,
-	0xe4e7ef5b, 0x25a1ff41, 0xe180f806,
-	0x1fc41080, 0x179bee7a, 0xd37ac6a9, 0xfe5830a4, 0x98de8b7f,
-	0x77e83f4e, 0x79929269, 0x24fa9f7b,
-	0xe113c85b, 0xacc40083, 0xd7503525, 0xf7ea615f, 0x62143154,
-	0x0d554b63, 0x5d681121, 0xc866c359,
-	0x3d63cf73, 0xcee234c0, 0xd4d87e87, 0x5c672b21, 0x071f6181,
-	0x39f7627f, 0x361e3084, 0xe4eb573b,
-	0x602f64a4, 0xd63acd9c, 0x1bbc4635, 0x9e81032d, 0x2701f50c,
-	0x99847ab4, 0xa0e3df79, 0xba6cf38c,
-	0x10843094, 0x2537a95e, 0xf46f6ffe, 0xa1ff3b1f, 0x208cfb6a,
-	0x8f458c74, 0xd9e0a227, 0x4ec73a34,
-	0xfc884f69, 0x3e4de8df, 0xef0e0088, 0x3559648d, 0x8a45388c,
-	0x1d804366, 0x721d9bfd, 0xa58684bb,
-	0xe8256333, 0x844e8212, 0x128d8098, 0xfed33fb4, 0xce280ae1,
-	0x27e19ba5, 0xd5a6c252, 0xe49754bd,
-	0xc5d655dd, 0xeb667064, 0x77840b4d, 0xa1b6a801, 0x84db26a9,
-	0xe0b56714, 0x21f043b7, 0xe5d05860,
-	0x54f03084, 0x066ff472, 0xa31aa153, 0xdadc4755, 0xb5625dbf,
-	0x68561be6, 0x83ca6b94, 0x2d6ed23b,
-	0xeccf01db, 0xa6d3d0ba, 0xb6803d5c, 0xaf77a709, 0x33b4a34c,
-	0x397bc8d6, 0x5ee22b95, 0x5f0e5304,
-	0x81ed6f61, 0x20e74364, 0xb45e1378, 0xde18639b, 0x881ca122,
-	0xb96726d1, 0x8049a7e8, 0x22b7da7b,
-	0x5e552d25, 0x5272d237, 0x79d2951c, 0xc60d894c, 0x488cb402,
-	0x1ba4fe5b, 0xa4b09f6b, 0x1ca815cf,
-	0xa20c3005, 0x8871df63, 0xb9de2fcb, 0x0cc6c9e9, 0x0beeff53,
-	0xe3214517, 0xb4542835, 0x9f63293c,
-	0xee41e729, 0x6e1d2d7c, 0x50045286, 0x1e6685f3, 0xf33401c6,
-	0x30a22c95, 0x31a70850, 0x60930f13,
-	0x73f98417, 0xa1269859, 0xec645c44, 0x52c877a9, 0xcdff33a6,
-	0xa02b1741, 0x7cbad9a2, 0x2180036f,
-	0x50d99c08, 0xcb3f4861, 0xc26bd765, 0x64a3f6ab, 0x80342676,
-	0x25a75e7b, 0xe4e6d1fc, 0x20c710e6,
-	0xcdf0b680, 0x17844d3b, 0x31eef84d, 0x7e0824e4, 0x2ccb49eb,
-	0x846a3bae, 0x8ff77888, 0xee5d60f6,
-	0x7af75673, 0x2fdd5cdb, 0xa11631c1, 0x30f66f43, 0xb3faec54,
-	0x157fd7fa, 0xef8579cc, 0xd152de58,
-	0xdb2ffd5e, 0x8f32ce19, 0x306af97a, 0x02f03ef8, 0x99319ad5,
-	0xc242fa0f, 0xa7e3ebb0, 0xc68e4906,
-	0xb8da230c, 0x80823028, 0xdcdef3c8, 0xd35fb171, 0x088a1bc8,
-	0xbec0c560, 0x61a3c9e8, 0xbca8f54d,
-	0xc72feffa, 0x22822e99, 0x82c570b4, 0xd8d94e89, 0x8b1c34bc,
-	0x301e16e6, 0x273be979, 0xb0ffeaa6,
-	0x61d9b8c6, 0x00b24869, 0xb7ffce3f, 0x08dc283b, 0x43daf65a,
-	0xf7e19798, 0x7619b72f, 0x8f1c9ba4,
-	0xdc8637a0, 0x16a7d3b1, 0x9fc393b7, 0xa7136eeb, 0xc6bcc63e,
-	0x1a513742, 0xef6828bc, 0x520365d6,
-	0x2d6a77ab, 0x3527ed4b, 0x821fd216, 0x095c6e2e, 0xdb92f2fb,
-	0x5eea29cb, 0x145892f5, 0x91584f7f,
-	0x5483697b, 0x2667a8cc, 0x85196048, 0x8c4bacea, 0x833860d4,
-	0x0d23e0f9, 0x6c387e8a, 0x0ae6d249,
-	0xb284600c, 0xd835731d, 0xdcb1c647, 0xac4c56ea, 0x3ebd81b3,
-	0x230eabb0, 0x6438bc87, 0xf0b5b1fa,
-	0x8f5ea2b3, 0xfc184642, 0x0a036b7a, 0x4fb089bd, 0x649da589,
-	0xa345415e, 0x5c038323, 0x3e5d3bb9,
-	0x43d79572, 0x7e6dd07c, 0x06dfdf1e, 0x6c6cc4ef, 0x7160a539,
-	0x73bfbe70, 0x83877605, 0x4523ecf1
-};
-EXPORT_SYMBOL_GPL(cast5_s2);
-const u32 cast5_s3[256] = {
-	0x8defc240, 0x25fa5d9f, 0xeb903dbf, 0xe810c907, 0x47607fff,
-	0x369fe44b, 0x8c1fc644, 0xaececa90,
-	0xbeb1f9bf, 0xeefbcaea, 0xe8cf1950, 0x51df07ae, 0x920e8806,
-	0xf0ad0548, 0xe13c8d83, 0x927010d5,
-	0x11107d9f, 0x07647db9, 0xb2e3e4d4, 0x3d4f285e, 0xb9afa820,
-	0xfade82e0, 0xa067268b, 0x8272792e,
-	0x553fb2c0, 0x489ae22b, 0xd4ef9794, 0x125e3fbc, 0x21fffcee,
-	0x825b1bfd, 0x9255c5ed, 0x1257a240,
-	0x4e1a8302, 0xbae07fff, 0x528246e7, 0x8e57140e, 0x3373f7bf,
-	0x8c9f8188, 0xa6fc4ee8, 0xc982b5a5,
-	0xa8c01db7, 0x579fc264, 0x67094f31, 0xf2bd3f5f, 0x40fff7c1,
-	0x1fb78dfc, 0x8e6bd2c1, 0x437be59b,
-	0x99b03dbf, 0xb5dbc64b, 0x638dc0e6, 0x55819d99, 0xa197c81c,
-	0x4a012d6e, 0xc5884a28, 0xccc36f71,
-	0xb843c213, 0x6c0743f1, 0x8309893c, 0x0feddd5f, 0x2f7fe850,
-	0xd7c07f7e, 0x02507fbf, 0x5afb9a04,
-	0xa747d2d0, 0x1651192e, 0xaf70bf3e, 0x58c31380, 0x5f98302e,
-	0x727cc3c4, 0x0a0fb402, 0x0f7fef82,
-	0x8c96fdad, 0x5d2c2aae, 0x8ee99a49, 0x50da88b8, 0x8427f4a0,
-	0x1eac5790, 0x796fb449, 0x8252dc15,
-	0xefbd7d9b, 0xa672597d, 0xada840d8, 0x45f54504, 0xfa5d7403,
-	0xe83ec305, 0x4f91751a, 0x925669c2,
-	0x23efe941, 0xa903f12e, 0x60270df2, 0x0276e4b6, 0x94fd6574,
-	0x927985b2, 0x8276dbcb, 0x02778176,
-	0xf8af918d, 0x4e48f79e, 0x8f616ddf, 0xe29d840e, 0x842f7d83,
-	0x340ce5c8, 0x96bbb682, 0x93b4b148,
-	0xef303cab, 0x984faf28, 0x779faf9b, 0x92dc560d, 0x224d1e20,
-	0x8437aa88, 0x7d29dc96, 0x2756d3dc,
-	0x8b907cee, 0xb51fd240, 0xe7c07ce3, 0xe566b4a1, 0xc3e9615e,
-	0x3cf8209d, 0x6094d1e3, 0xcd9ca341,
-	0x5c76460e, 0x00ea983b, 0xd4d67881, 0xfd47572c, 0xf76cedd9,
-	0xbda8229c, 0x127dadaa, 0x438a074e,
-	0x1f97c090, 0x081bdb8a, 0x93a07ebe, 0xb938ca15, 0x97b03cff,
-	0x3dc2c0f8, 0x8d1ab2ec, 0x64380e51,
-	0x68cc7bfb, 0xd90f2788, 0x12490181, 0x5de5ffd4, 0xdd7ef86a,
-	0x76a2e214, 0xb9a40368, 0x925d958f,
-	0x4b39fffa, 0xba39aee9, 0xa4ffd30b, 0xfaf7933b, 0x6d498623,
-	0x193cbcfa, 0x27627545, 0x825cf47a,
-	0x61bd8ba0, 0xd11e42d1, 0xcead04f4, 0x127ea392, 0x10428db7,
-	0x8272a972, 0x9270c4a8, 0x127de50b,
-	0x285ba1c8, 0x3c62f44f, 0x35c0eaa5, 0xe805d231, 0x428929fb,
-	0xb4fcdf82, 0x4fb66a53, 0x0e7dc15b,
-	0x1f081fab, 0x108618ae, 0xfcfd086d, 0xf9ff2889, 0x694bcc11,
-	0x236a5cae, 0x12deca4d, 0x2c3f8cc5,
-	0xd2d02dfe, 0xf8ef5896, 0xe4cf52da, 0x95155b67, 0x494a488c,
-	0xb9b6a80c, 0x5c8f82bc, 0x89d36b45,
-	0x3a609437, 0xec00c9a9, 0x44715253, 0x0a874b49, 0xd773bc40,
-	0x7c34671c, 0x02717ef6, 0x4feb5536,
-	0xa2d02fff, 0xd2bf60c4, 0xd43f03c0, 0x50b4ef6d, 0x07478cd1,
-	0x006e1888, 0xa2e53f55, 0xb9e6d4bc,
-	0xa2048016, 0x97573833, 0xd7207d67, 0xde0f8f3d, 0x72f87b33,
-	0xabcc4f33, 0x7688c55d, 0x7b00a6b0,
-	0x947b0001, 0x570075d2, 0xf9bb88f8, 0x8942019e, 0x4264a5ff,
-	0x856302e0, 0x72dbd92b, 0xee971b69,
-	0x6ea22fde, 0x5f08ae2b, 0xaf7a616d, 0xe5c98767, 0xcf1febd2,
-	0x61efc8c2, 0xf1ac2571, 0xcc8239c2,
-	0x67214cb8, 0xb1e583d1, 0xb7dc3e62, 0x7f10bdce, 0xf90a5c38,
-	0x0ff0443d, 0x606e6dc6, 0x60543a49,
-	0x5727c148, 0x2be98a1d, 0x8ab41738, 0x20e1be24, 0xaf96da0f,
-	0x68458425, 0x99833be5, 0x600d457d,
-	0x282f9350, 0x8334b362, 0xd91d1120, 0x2b6d8da0, 0x642b1e31,
-	0x9c305a00, 0x52bce688, 0x1b03588a,
-	0xf7baefd5, 0x4142ed9c, 0xa4315c11, 0x83323ec5, 0xdfef4636,
-	0xa133c501, 0xe9d3531c, 0xee353783
-};
-EXPORT_SYMBOL_GPL(cast5_s3);
-const u32 cast5_s4[256] = {
-	0x9db30420, 0x1fb6e9de, 0xa7be7bef, 0xd273a298, 0x4a4f7bdb,
-	0x64ad8c57, 0x85510443, 0xfa020ed1,
-	0x7e287aff, 0xe60fb663, 0x095f35a1, 0x79ebf120, 0xfd059d43,
-	0x6497b7b1, 0xf3641f63, 0x241e4adf,
-	0x28147f5f, 0x4fa2b8cd, 0xc9430040, 0x0cc32220, 0xfdd30b30,
-	0xc0a5374f, 0x1d2d00d9, 0x24147b15,
-	0xee4d111a, 0x0fca5167, 0x71ff904c, 0x2d195ffe, 0x1a05645f,
-	0x0c13fefe, 0x081b08ca, 0x05170121,
-	0x80530100, 0xe83e5efe, 0xac9af4f8, 0x7fe72701, 0xd2b8ee5f,
-	0x06df4261, 0xbb9e9b8a, 0x7293ea25,
-	0xce84ffdf, 0xf5718801, 0x3dd64b04, 0xa26f263b, 0x7ed48400,
-	0x547eebe6, 0x446d4ca0, 0x6cf3d6f5,
-	0x2649abdf, 0xaea0c7f5, 0x36338cc1, 0x503f7e93, 0xd3772061,
-	0x11b638e1, 0x72500e03, 0xf80eb2bb,
-	0xabe0502e, 0xec8d77de, 0x57971e81, 0xe14f6746, 0xc9335400,
-	0x6920318f, 0x081dbb99, 0xffc304a5,
-	0x4d351805, 0x7f3d5ce3, 0xa6c866c6, 0x5d5bcca9, 0xdaec6fea,
-	0x9f926f91, 0x9f46222f, 0x3991467d,
-	0xa5bf6d8e, 0x1143c44f, 0x43958302, 0xd0214eeb, 0x022083b8,
-	0x3fb6180c, 0x18f8931e, 0x281658e6,
-	0x26486e3e, 0x8bd78a70, 0x7477e4c1, 0xb506e07c, 0xf32d0a25,
-	0x79098b02, 0xe4eabb81, 0x28123b23,
-	0x69dead38, 0x1574ca16, 0xdf871b62, 0x211c40b7, 0xa51a9ef9,
-	0x0014377b, 0x041e8ac8, 0x09114003,
-	0xbd59e4d2, 0xe3d156d5, 0x4fe876d5, 0x2f91a340, 0x557be8de,
-	0x00eae4a7, 0x0ce5c2ec, 0x4db4bba6,
-	0xe756bdff, 0xdd3369ac, 0xec17b035, 0x06572327, 0x99afc8b0,
-	0x56c8c391, 0x6b65811c, 0x5e146119,
-	0x6e85cb75, 0xbe07c002, 0xc2325577, 0x893ff4ec, 0x5bbfc92d,
-	0xd0ec3b25, 0xb7801ab7, 0x8d6d3b24,
-	0x20c763ef, 0xc366a5fc, 0x9c382880, 0x0ace3205, 0xaac9548a,
-	0xeca1d7c7, 0x041afa32, 0x1d16625a,
-	0x6701902c, 0x9b757a54, 0x31d477f7, 0x9126b031, 0x36cc6fdb,
-	0xc70b8b46, 0xd9e66a48, 0x56e55a79,
-	0x026a4ceb, 0x52437eff, 0x2f8f76b4, 0x0df980a5, 0x8674cde3,
-	0xedda04eb, 0x17a9be04, 0x2c18f4df,
-	0xb7747f9d, 0xab2af7b4, 0xefc34d20, 0x2e096b7c, 0x1741a254,
-	0xe5b6a035, 0x213d42f6, 0x2c1c7c26,
-	0x61c2f50f, 0x6552daf9, 0xd2c231f8, 0x25130f69, 0xd8167fa2,
-	0x0418f2c8, 0x001a96a6, 0x0d1526ab,
-	0x63315c21, 0x5e0a72ec, 0x49bafefd, 0x187908d9, 0x8d0dbd86,
-	0x311170a7, 0x3e9b640c, 0xcc3e10d7,
-	0xd5cad3b6, 0x0caec388, 0xf73001e1, 0x6c728aff, 0x71eae2a1,
-	0x1f9af36e, 0xcfcbd12f, 0xc1de8417,
-	0xac07be6b, 0xcb44a1d8, 0x8b9b0f56, 0x013988c3, 0xb1c52fca,
-	0xb4be31cd, 0xd8782806, 0x12a3a4e2,
-	0x6f7de532, 0x58fd7eb6, 0xd01ee900, 0x24adffc2, 0xf4990fc5,
-	0x9711aac5, 0x001d7b95, 0x82e5e7d2,
-	0x109873f6, 0x00613096, 0xc32d9521, 0xada121ff, 0x29908415,
-	0x7fbb977f, 0xaf9eb3db, 0x29c9ed2a,
-	0x5ce2a465, 0xa730f32c, 0xd0aa3fe8, 0x8a5cc091, 0xd49e2ce7,
-	0x0ce454a9, 0xd60acd86, 0x015f1919,
-	0x77079103, 0xdea03af6, 0x78a8565e, 0xdee356df, 0x21f05cbe,
-	0x8b75e387, 0xb3c50651, 0xb8a5c3ef,
-	0xd8eeb6d2, 0xe523be77, 0xc2154529, 0x2f69efdf, 0xafe67afb,
-	0xf470c4b2, 0xf3e0eb5b, 0xd6cc9876,
-	0x39e4460c, 0x1fda8538, 0x1987832f, 0xca007367, 0xa99144f8,
-	0x296b299e, 0x492fc295, 0x9266beab,
-	0xb5676e69, 0x9bd3ddda, 0xdf7e052f, 0xdb25701c, 0x1b5e51ee,
-	0xf65324e6, 0x6afce36c, 0x0316cc04,
-	0x8644213e, 0xb7dc59d0, 0x7965291f, 0xccd6fd43, 0x41823979,
-	0x932bcdf6, 0xb657c34d, 0x4edfd282,
-	0x7ae5290c, 0x3cb9536b, 0x851e20fe, 0x9833557e, 0x13ecf0b0,
-	0xd3ffb372, 0x3f85c5c1, 0x0aef7ed2
-};
-EXPORT_SYMBOL_GPL(cast5_s4);
 static const u32 s5[256] = {
 	0x7ec90c04, 0x2c6e74b9, 0x9b0e66df, 0xa6337911, 0xb86a7fff,
 	0x1dd358f5, 0x44dd9d44, 0x1731167f,
@@ -564,10 +295,10 @@ static const u32 sb8[256] = {
 	0xeaee6801, 0x8db2a283, 0xea8bf59e
 };
 
-#define s1 cast5_s1
-#define s2 cast5_s2
-#define s3 cast5_s3
-#define s4 cast5_s4
+#define s1 cast_s1
+#define s2 cast_s2
+#define s3 cast_s3
+#define s4 cast_s4
 
 #define F1(D, m, r)  ((I = ((m) + (D))), (I = rol32(I, (r))),   \
 	(((s1[I >> 24] ^ s2[(I>>16)&0xff]) - s3[(I>>8)&0xff]) + s4[I&0xff]))
diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c
index 1acd2f1c48fc..de732528a430 100644
--- a/crypto/cast6_generic.c
+++ b/crypto/cast6_generic.c
@@ -27,10 +27,10 @@
 #include <linux/types.h>
 #include <crypto/cast6.h>
 
-#define s1 cast6_s1
-#define s2 cast6_s2
-#define s3 cast6_s3
-#define s4 cast6_s4
+#define s1 cast_s1
+#define s2 cast_s2
+#define s3 cast_s3
+#define s4 cast_s4
 
 #define F1(D, r, m)  ((I = ((m) + (D))), (I = rol32(I, (r))),   \
 	(((s1[I >> 24] ^ s2[(I>>16)&0xff]) - s3[(I>>8)&0xff]) + s4[I&0xff]))
@@ -39,278 +39,6 @@
 #define F3(D, r, m)  ((I = ((m) - (D))), (I = rol32(I, (r))),   \
 	(((s1[I >> 24] + s2[(I>>16)&0xff]) ^ s3[(I>>8)&0xff]) - s4[I&0xff]))
 
-const u32 cast6_s1[256] = {
-	0x30fb40d4, 0x9fa0ff0b, 0x6beccd2f, 0x3f258c7a, 0x1e213f2f,
-	0x9c004dd3, 0x6003e540, 0xcf9fc949,
-	0xbfd4af27, 0x88bbbdb5, 0xe2034090, 0x98d09675, 0x6e63a0e0,
-	0x15c361d2, 0xc2e7661d, 0x22d4ff8e,
-	0x28683b6f, 0xc07fd059, 0xff2379c8, 0x775f50e2, 0x43c340d3,
-	0xdf2f8656, 0x887ca41a, 0xa2d2bd2d,
-	0xa1c9e0d6, 0x346c4819, 0x61b76d87, 0x22540f2f, 0x2abe32e1,
-	0xaa54166b, 0x22568e3a, 0xa2d341d0,
-	0x66db40c8, 0xa784392f, 0x004dff2f, 0x2db9d2de, 0x97943fac,
-	0x4a97c1d8, 0x527644b7, 0xb5f437a7,
-	0xb82cbaef, 0xd751d159, 0x6ff7f0ed, 0x5a097a1f, 0x827b68d0,
-	0x90ecf52e, 0x22b0c054, 0xbc8e5935,
-	0x4b6d2f7f, 0x50bb64a2, 0xd2664910, 0xbee5812d, 0xb7332290,
-	0xe93b159f, 0xb48ee411, 0x4bff345d,
-	0xfd45c240, 0xad31973f, 0xc4f6d02e, 0x55fc8165, 0xd5b1caad,
-	0xa1ac2dae, 0xa2d4b76d, 0xc19b0c50,
-	0x882240f2, 0x0c6e4f38, 0xa4e4bfd7, 0x4f5ba272, 0x564c1d2f,
-	0xc59c5319, 0xb949e354, 0xb04669fe,
-	0xb1b6ab8a, 0xc71358dd, 0x6385c545, 0x110f935d, 0x57538ad5,
-	0x6a390493, 0xe63d37e0, 0x2a54f6b3,
-	0x3a787d5f, 0x6276a0b5, 0x19a6fcdf, 0x7a42206a, 0x29f9d4d5,
-	0xf61b1891, 0xbb72275e, 0xaa508167,
-	0x38901091, 0xc6b505eb, 0x84c7cb8c, 0x2ad75a0f, 0x874a1427,
-	0xa2d1936b, 0x2ad286af, 0xaa56d291,
-	0xd7894360, 0x425c750d, 0x93b39e26, 0x187184c9, 0x6c00b32d,
-	0x73e2bb14, 0xa0bebc3c, 0x54623779,
-	0x64459eab, 0x3f328b82, 0x7718cf82, 0x59a2cea6, 0x04ee002e,
-	0x89fe78e6, 0x3fab0950, 0x325ff6c2,
-	0x81383f05, 0x6963c5c8, 0x76cb5ad6, 0xd49974c9, 0xca180dcf,
-	0x380782d5, 0xc7fa5cf6, 0x8ac31511,
-	0x35e79e13, 0x47da91d0, 0xf40f9086, 0xa7e2419e, 0x31366241,
-	0x051ef495, 0xaa573b04, 0x4a805d8d,
-	0x548300d0, 0x00322a3c, 0xbf64cddf, 0xba57a68e, 0x75c6372b,
-	0x50afd341, 0xa7c13275, 0x915a0bf5,
-	0x6b54bfab, 0x2b0b1426, 0xab4cc9d7, 0x449ccd82, 0xf7fbf265,
-	0xab85c5f3, 0x1b55db94, 0xaad4e324,
-	0xcfa4bd3f, 0x2deaa3e2, 0x9e204d02, 0xc8bd25ac, 0xeadf55b3,
-	0xd5bd9e98, 0xe31231b2, 0x2ad5ad6c,
-	0x954329de, 0xadbe4528, 0xd8710f69, 0xaa51c90f, 0xaa786bf6,
-	0x22513f1e, 0xaa51a79b, 0x2ad344cc,
-	0x7b5a41f0, 0xd37cfbad, 0x1b069505, 0x41ece491, 0xb4c332e6,
-	0x032268d4, 0xc9600acc, 0xce387e6d,
-	0xbf6bb16c, 0x6a70fb78, 0x0d03d9c9, 0xd4df39de, 0xe01063da,
-	0x4736f464, 0x5ad328d8, 0xb347cc96,
-	0x75bb0fc3, 0x98511bfb, 0x4ffbcc35, 0xb58bcf6a, 0xe11f0abc,
-	0xbfc5fe4a, 0xa70aec10, 0xac39570a,
-	0x3f04442f, 0x6188b153, 0xe0397a2e, 0x5727cb79, 0x9ceb418f,
-	0x1cacd68d, 0x2ad37c96, 0x0175cb9d,
-	0xc69dff09, 0xc75b65f0, 0xd9db40d8, 0xec0e7779, 0x4744ead4,
-	0xb11c3274, 0xdd24cb9e, 0x7e1c54bd,
-	0xf01144f9, 0xd2240eb1, 0x9675b3fd, 0xa3ac3755, 0xd47c27af,
-	0x51c85f4d, 0x56907596, 0xa5bb15e6,
-	0x580304f0, 0xca042cf1, 0x011a37ea, 0x8dbfaadb, 0x35ba3e4a,
-	0x3526ffa0, 0xc37b4d09, 0xbc306ed9,
-	0x98a52666, 0x5648f725, 0xff5e569d, 0x0ced63d0, 0x7c63b2cf,
-	0x700b45e1, 0xd5ea50f1, 0x85a92872,
-	0xaf1fbda7, 0xd4234870, 0xa7870bf3, 0x2d3b4d79, 0x42e04198,
-	0x0cd0ede7, 0x26470db8, 0xf881814c,
-	0x474d6ad7, 0x7c0c5e5c, 0xd1231959, 0x381b7298, 0xf5d2f4db,
-	0xab838653, 0x6e2f1e23, 0x83719c9e,
-	0xbd91e046, 0x9a56456e, 0xdc39200c, 0x20c8c571, 0x962bda1c,
-	0xe1e696ff, 0xb141ab08, 0x7cca89b9,
-	0x1a69e783, 0x02cc4843, 0xa2f7c579, 0x429ef47d, 0x427b169c,
-	0x5ac9f049, 0xdd8f0f00, 0x5c8165bf
-};
-EXPORT_SYMBOL_GPL(cast6_s1);
-
-const u32 cast6_s2[256] = {
-	0x1f201094, 0xef0ba75b, 0x69e3cf7e, 0x393f4380, 0xfe61cf7a,
-	0xeec5207a, 0x55889c94, 0x72fc0651,
-	0xada7ef79, 0x4e1d7235, 0xd55a63ce, 0xde0436ba, 0x99c430ef,
-	0x5f0c0794, 0x18dcdb7d, 0xa1d6eff3,
-	0xa0b52f7b, 0x59e83605, 0xee15b094, 0xe9ffd909, 0xdc440086,
-	0xef944459, 0xba83ccb3, 0xe0c3cdfb,
-	0xd1da4181, 0x3b092ab1, 0xf997f1c1, 0xa5e6cf7b, 0x01420ddb,
-	0xe4e7ef5b, 0x25a1ff41, 0xe180f806,
-	0x1fc41080, 0x179bee7a, 0xd37ac6a9, 0xfe5830a4, 0x98de8b7f,
-	0x77e83f4e, 0x79929269, 0x24fa9f7b,
-	0xe113c85b, 0xacc40083, 0xd7503525, 0xf7ea615f, 0x62143154,
-	0x0d554b63, 0x5d681121, 0xc866c359,
-	0x3d63cf73, 0xcee234c0, 0xd4d87e87, 0x5c672b21, 0x071f6181,
-	0x39f7627f, 0x361e3084, 0xe4eb573b,
-	0x602f64a4, 0xd63acd9c, 0x1bbc4635, 0x9e81032d, 0x2701f50c,
-	0x99847ab4, 0xa0e3df79, 0xba6cf38c,
-	0x10843094, 0x2537a95e, 0xf46f6ffe, 0xa1ff3b1f, 0x208cfb6a,
-	0x8f458c74, 0xd9e0a227, 0x4ec73a34,
-	0xfc884f69, 0x3e4de8df, 0xef0e0088, 0x3559648d, 0x8a45388c,
-	0x1d804366, 0x721d9bfd, 0xa58684bb,
-	0xe8256333, 0x844e8212, 0x128d8098, 0xfed33fb4, 0xce280ae1,
-	0x27e19ba5, 0xd5a6c252, 0xe49754bd,
-	0xc5d655dd, 0xeb667064, 0x77840b4d, 0xa1b6a801, 0x84db26a9,
-	0xe0b56714, 0x21f043b7, 0xe5d05860,
-	0x54f03084, 0x066ff472, 0xa31aa153, 0xdadc4755, 0xb5625dbf,
-	0x68561be6, 0x83ca6b94, 0x2d6ed23b,
-	0xeccf01db, 0xa6d3d0ba, 0xb6803d5c, 0xaf77a709, 0x33b4a34c,
-	0x397bc8d6, 0x5ee22b95, 0x5f0e5304,
-	0x81ed6f61, 0x20e74364, 0xb45e1378, 0xde18639b, 0x881ca122,
-	0xb96726d1, 0x8049a7e8, 0x22b7da7b,
-	0x5e552d25, 0x5272d237, 0x79d2951c, 0xc60d894c, 0x488cb402,
-	0x1ba4fe5b, 0xa4b09f6b, 0x1ca815cf,
-	0xa20c3005, 0x8871df63, 0xb9de2fcb, 0x0cc6c9e9, 0x0beeff53,
-	0xe3214517, 0xb4542835, 0x9f63293c,
-	0xee41e729, 0x6e1d2d7c, 0x50045286, 0x1e6685f3, 0xf33401c6,
-	0x30a22c95, 0x31a70850, 0x60930f13,
-	0x73f98417, 0xa1269859, 0xec645c44, 0x52c877a9, 0xcdff33a6,
-	0xa02b1741, 0x7cbad9a2, 0x2180036f,
-	0x50d99c08, 0xcb3f4861, 0xc26bd765, 0x64a3f6ab, 0x80342676,
-	0x25a75e7b, 0xe4e6d1fc, 0x20c710e6,
-	0xcdf0b680, 0x17844d3b, 0x31eef84d, 0x7e0824e4, 0x2ccb49eb,
-	0x846a3bae, 0x8ff77888, 0xee5d60f6,
-	0x7af75673, 0x2fdd5cdb, 0xa11631c1, 0x30f66f43, 0xb3faec54,
-	0x157fd7fa, 0xef8579cc, 0xd152de58,
-	0xdb2ffd5e, 0x8f32ce19, 0x306af97a, 0x02f03ef8, 0x99319ad5,
-	0xc242fa0f, 0xa7e3ebb0, 0xc68e4906,
-	0xb8da230c, 0x80823028, 0xdcdef3c8, 0xd35fb171, 0x088a1bc8,
-	0xbec0c560, 0x61a3c9e8, 0xbca8f54d,
-	0xc72feffa, 0x22822e99, 0x82c570b4, 0xd8d94e89, 0x8b1c34bc,
-	0x301e16e6, 0x273be979, 0xb0ffeaa6,
-	0x61d9b8c6, 0x00b24869, 0xb7ffce3f, 0x08dc283b, 0x43daf65a,
-	0xf7e19798, 0x7619b72f, 0x8f1c9ba4,
-	0xdc8637a0, 0x16a7d3b1, 0x9fc393b7, 0xa7136eeb, 0xc6bcc63e,
-	0x1a513742, 0xef6828bc, 0x520365d6,
-	0x2d6a77ab, 0x3527ed4b, 0x821fd216, 0x095c6e2e, 0xdb92f2fb,
-	0x5eea29cb, 0x145892f5, 0x91584f7f,
-	0x5483697b, 0x2667a8cc, 0x85196048, 0x8c4bacea, 0x833860d4,
-	0x0d23e0f9, 0x6c387e8a, 0x0ae6d249,
-	0xb284600c, 0xd835731d, 0xdcb1c647, 0xac4c56ea, 0x3ebd81b3,
-	0x230eabb0, 0x6438bc87, 0xf0b5b1fa,
-	0x8f5ea2b3, 0xfc184642, 0x0a036b7a, 0x4fb089bd, 0x649da589,
-	0xa345415e, 0x5c038323, 0x3e5d3bb9,
-	0x43d79572, 0x7e6dd07c, 0x06dfdf1e, 0x6c6cc4ef, 0x7160a539,
-	0x73bfbe70, 0x83877605, 0x4523ecf1
-};
-EXPORT_SYMBOL_GPL(cast6_s2);
-
-const u32 cast6_s3[256] = {
-	0x8defc240, 0x25fa5d9f, 0xeb903dbf, 0xe810c907, 0x47607fff,
-	0x369fe44b, 0x8c1fc644, 0xaececa90,
-	0xbeb1f9bf, 0xeefbcaea, 0xe8cf1950, 0x51df07ae, 0x920e8806,
-	0xf0ad0548, 0xe13c8d83, 0x927010d5,
-	0x11107d9f, 0x07647db9, 0xb2e3e4d4, 0x3d4f285e, 0xb9afa820,
-	0xfade82e0, 0xa067268b, 0x8272792e,
-	0x553fb2c0, 0x489ae22b, 0xd4ef9794, 0x125e3fbc, 0x21fffcee,
-	0x825b1bfd, 0x9255c5ed, 0x1257a240,
-	0x4e1a8302, 0xbae07fff, 0x528246e7, 0x8e57140e, 0x3373f7bf,
-	0x8c9f8188, 0xa6fc4ee8, 0xc982b5a5,
-	0xa8c01db7, 0x579fc264, 0x67094f31, 0xf2bd3f5f, 0x40fff7c1,
-	0x1fb78dfc, 0x8e6bd2c1, 0x437be59b,
-	0x99b03dbf, 0xb5dbc64b, 0x638dc0e6, 0x55819d99, 0xa197c81c,
-	0x4a012d6e, 0xc5884a28, 0xccc36f71,
-	0xb843c213, 0x6c0743f1, 0x8309893c, 0x0feddd5f, 0x2f7fe850,
-	0xd7c07f7e, 0x02507fbf, 0x5afb9a04,
-	0xa747d2d0, 0x1651192e, 0xaf70bf3e, 0x58c31380, 0x5f98302e,
-	0x727cc3c4, 0x0a0fb402, 0x0f7fef82,
-	0x8c96fdad, 0x5d2c2aae, 0x8ee99a49, 0x50da88b8, 0x8427f4a0,
-	0x1eac5790, 0x796fb449, 0x8252dc15,
-	0xefbd7d9b, 0xa672597d, 0xada840d8, 0x45f54504, 0xfa5d7403,
-	0xe83ec305, 0x4f91751a, 0x925669c2,
-	0x23efe941, 0xa903f12e, 0x60270df2, 0x0276e4b6, 0x94fd6574,
-	0x927985b2, 0x8276dbcb, 0x02778176,
-	0xf8af918d, 0x4e48f79e, 0x8f616ddf, 0xe29d840e, 0x842f7d83,
-	0x340ce5c8, 0x96bbb682, 0x93b4b148,
-	0xef303cab, 0x984faf28, 0x779faf9b, 0x92dc560d, 0x224d1e20,
-	0x8437aa88, 0x7d29dc96, 0x2756d3dc,
-	0x8b907cee, 0xb51fd240, 0xe7c07ce3, 0xe566b4a1, 0xc3e9615e,
-	0x3cf8209d, 0x6094d1e3, 0xcd9ca341,
-	0x5c76460e, 0x00ea983b, 0xd4d67881, 0xfd47572c, 0xf76cedd9,
-	0xbda8229c, 0x127dadaa, 0x438a074e,
-	0x1f97c090, 0x081bdb8a, 0x93a07ebe, 0xb938ca15, 0x97b03cff,
-	0x3dc2c0f8, 0x8d1ab2ec, 0x64380e51,
-	0x68cc7bfb, 0xd90f2788, 0x12490181, 0x5de5ffd4, 0xdd7ef86a,
-	0x76a2e214, 0xb9a40368, 0x925d958f,
-	0x4b39fffa, 0xba39aee9, 0xa4ffd30b, 0xfaf7933b, 0x6d498623,
-	0x193cbcfa, 0x27627545, 0x825cf47a,
-	0x61bd8ba0, 0xd11e42d1, 0xcead04f4, 0x127ea392, 0x10428db7,
-	0x8272a972, 0x9270c4a8, 0x127de50b,
-	0x285ba1c8, 0x3c62f44f, 0x35c0eaa5, 0xe805d231, 0x428929fb,
-	0xb4fcdf82, 0x4fb66a53, 0x0e7dc15b,
-	0x1f081fab, 0x108618ae, 0xfcfd086d, 0xf9ff2889, 0x694bcc11,
-	0x236a5cae, 0x12deca4d, 0x2c3f8cc5,
-	0xd2d02dfe, 0xf8ef5896, 0xe4cf52da, 0x95155b67, 0x494a488c,
-	0xb9b6a80c, 0x5c8f82bc, 0x89d36b45,
-	0x3a609437, 0xec00c9a9, 0x44715253, 0x0a874b49, 0xd773bc40,
-	0x7c34671c, 0x02717ef6, 0x4feb5536,
-	0xa2d02fff, 0xd2bf60c4, 0xd43f03c0, 0x50b4ef6d, 0x07478cd1,
-	0x006e1888, 0xa2e53f55, 0xb9e6d4bc,
-	0xa2048016, 0x97573833, 0xd7207d67, 0xde0f8f3d, 0x72f87b33,
-	0xabcc4f33, 0x7688c55d, 0x7b00a6b0,
-	0x947b0001, 0x570075d2, 0xf9bb88f8, 0x8942019e, 0x4264a5ff,
-	0x856302e0, 0x72dbd92b, 0xee971b69,
-	0x6ea22fde, 0x5f08ae2b, 0xaf7a616d, 0xe5c98767, 0xcf1febd2,
-	0x61efc8c2, 0xf1ac2571, 0xcc8239c2,
-	0x67214cb8, 0xb1e583d1, 0xb7dc3e62, 0x7f10bdce, 0xf90a5c38,
-	0x0ff0443d, 0x606e6dc6, 0x60543a49,
-	0x5727c148, 0x2be98a1d, 0x8ab41738, 0x20e1be24, 0xaf96da0f,
-	0x68458425, 0x99833be5, 0x600d457d,
-	0x282f9350, 0x8334b362, 0xd91d1120, 0x2b6d8da0, 0x642b1e31,
-	0x9c305a00, 0x52bce688, 0x1b03588a,
-	0xf7baefd5, 0x4142ed9c, 0xa4315c11, 0x83323ec5, 0xdfef4636,
-	0xa133c501, 0xe9d3531c, 0xee353783
-};
-EXPORT_SYMBOL_GPL(cast6_s3);
-
-const u32 cast6_s4[256] = {
-	0x9db30420, 0x1fb6e9de, 0xa7be7bef, 0xd273a298, 0x4a4f7bdb,
-	0x64ad8c57, 0x85510443, 0xfa020ed1,
-	0x7e287aff, 0xe60fb663, 0x095f35a1, 0x79ebf120, 0xfd059d43,
-	0x6497b7b1, 0xf3641f63, 0x241e4adf,
-	0x28147f5f, 0x4fa2b8cd, 0xc9430040, 0x0cc32220, 0xfdd30b30,
-	0xc0a5374f, 0x1d2d00d9, 0x24147b15,
-	0xee4d111a, 0x0fca5167, 0x71ff904c, 0x2d195ffe, 0x1a05645f,
-	0x0c13fefe, 0x081b08ca, 0x05170121,
-	0x80530100, 0xe83e5efe, 0xac9af4f8, 0x7fe72701, 0xd2b8ee5f,
-	0x06df4261, 0xbb9e9b8a, 0x7293ea25,
-	0xce84ffdf, 0xf5718801, 0x3dd64b04, 0xa26f263b, 0x7ed48400,
-	0x547eebe6, 0x446d4ca0, 0x6cf3d6f5,
-	0x2649abdf, 0xaea0c7f5, 0x36338cc1, 0x503f7e93, 0xd3772061,
-	0x11b638e1, 0x72500e03, 0xf80eb2bb,
-	0xabe0502e, 0xec8d77de, 0x57971e81, 0xe14f6746, 0xc9335400,
-	0x6920318f, 0x081dbb99, 0xffc304a5,
-	0x4d351805, 0x7f3d5ce3, 0xa6c866c6, 0x5d5bcca9, 0xdaec6fea,
-	0x9f926f91, 0x9f46222f, 0x3991467d,
-	0xa5bf6d8e, 0x1143c44f, 0x43958302, 0xd0214eeb, 0x022083b8,
-	0x3fb6180c, 0x18f8931e, 0x281658e6,
-	0x26486e3e, 0x8bd78a70, 0x7477e4c1, 0xb506e07c, 0xf32d0a25,
-	0x79098b02, 0xe4eabb81, 0x28123b23,
-	0x69dead38, 0x1574ca16, 0xdf871b62, 0x211c40b7, 0xa51a9ef9,
-	0x0014377b, 0x041e8ac8, 0x09114003,
-	0xbd59e4d2, 0xe3d156d5, 0x4fe876d5, 0x2f91a340, 0x557be8de,
-	0x00eae4a7, 0x0ce5c2ec, 0x4db4bba6,
-	0xe756bdff, 0xdd3369ac, 0xec17b035, 0x06572327, 0x99afc8b0,
-	0x56c8c391, 0x6b65811c, 0x5e146119,
-	0x6e85cb75, 0xbe07c002, 0xc2325577, 0x893ff4ec, 0x5bbfc92d,
-	0xd0ec3b25, 0xb7801ab7, 0x8d6d3b24,
-	0x20c763ef, 0xc366a5fc, 0x9c382880, 0x0ace3205, 0xaac9548a,
-	0xeca1d7c7, 0x041afa32, 0x1d16625a,
-	0x6701902c, 0x9b757a54, 0x31d477f7, 0x9126b031, 0x36cc6fdb,
-	0xc70b8b46, 0xd9e66a48, 0x56e55a79,
-	0x026a4ceb, 0x52437eff, 0x2f8f76b4, 0x0df980a5, 0x8674cde3,
-	0xedda04eb, 0x17a9be04, 0x2c18f4df,
-	0xb7747f9d, 0xab2af7b4, 0xefc34d20, 0x2e096b7c, 0x1741a254,
-	0xe5b6a035, 0x213d42f6, 0x2c1c7c26,
-	0x61c2f50f, 0x6552daf9, 0xd2c231f8, 0x25130f69, 0xd8167fa2,
-	0x0418f2c8, 0x001a96a6, 0x0d1526ab,
-	0x63315c21, 0x5e0a72ec, 0x49bafefd, 0x187908d9, 0x8d0dbd86,
-	0x311170a7, 0x3e9b640c, 0xcc3e10d7,
-	0xd5cad3b6, 0x0caec388, 0xf73001e1, 0x6c728aff, 0x71eae2a1,
-	0x1f9af36e, 0xcfcbd12f, 0xc1de8417,
-	0xac07be6b, 0xcb44a1d8, 0x8b9b0f56, 0x013988c3, 0xb1c52fca,
-	0xb4be31cd, 0xd8782806, 0x12a3a4e2,
-	0x6f7de532, 0x58fd7eb6, 0xd01ee900, 0x24adffc2, 0xf4990fc5,
-	0x9711aac5, 0x001d7b95, 0x82e5e7d2,
-	0x109873f6, 0x00613096, 0xc32d9521, 0xada121ff, 0x29908415,
-	0x7fbb977f, 0xaf9eb3db, 0x29c9ed2a,
-	0x5ce2a465, 0xa730f32c, 0xd0aa3fe8, 0x8a5cc091, 0xd49e2ce7,
-	0x0ce454a9, 0xd60acd86, 0x015f1919,
-	0x77079103, 0xdea03af6, 0x78a8565e, 0xdee356df, 0x21f05cbe,
-	0x8b75e387, 0xb3c50651, 0xb8a5c3ef,
-	0xd8eeb6d2, 0xe523be77, 0xc2154529, 0x2f69efdf, 0xafe67afb,
-	0xf470c4b2, 0xf3e0eb5b, 0xd6cc9876,
-	0x39e4460c, 0x1fda8538, 0x1987832f, 0xca007367, 0xa99144f8,
-	0x296b299e, 0x492fc295, 0x9266beab,
-	0xb5676e69, 0x9bd3ddda, 0xdf7e052f, 0xdb25701c, 0x1b5e51ee,
-	0xf65324e6, 0x6afce36c, 0x0316cc04,
-	0x8644213e, 0xb7dc59d0, 0x7965291f, 0xccd6fd43, 0x41823979,
-	0x932bcdf6, 0xb657c34d, 0x4edfd282,
-	0x7ae5290c, 0x3cb9536b, 0x851e20fe, 0x9833557e, 0x13ecf0b0,
-	0xd3ffb372, 0x3f85c5c1, 0x0aef7ed2
-};
-EXPORT_SYMBOL_GPL(cast6_s4);
-
 static const u32 Tm[24][8] = {
 	{ 0x5a827999, 0xc95c653a, 0x383650db, 0xa7103c7c, 0x15ea281d,
 		0x84c413be, 0xf39dff5f, 0x6277eb00 } ,
diff --git a/crypto/cast_common.c b/crypto/cast_common.c
new file mode 100644
index 000000000000..a15f523d5f56
--- /dev/null
+++ b/crypto/cast_common.c
@@ -0,0 +1,290 @@
+/*
+ * Common lookup tables for CAST-128 (cast5) and CAST-256 (cast6)
+ *
+ * Copyright © 1998, 1999, 2000, 2001 Free Software Foundation, Inc.
+ * Copyright © 2003 Kartikey Mahendra Bhatt <kartik_me@hotmail.com>
+ * Copyright © 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <linux/module.h>
+#include <crypto/cast_common.h>
+
+const u32 cast_s1[256] = {
+	0x30fb40d4, 0x9fa0ff0b, 0x6beccd2f, 0x3f258c7a, 0x1e213f2f,
+	0x9c004dd3, 0x6003e540, 0xcf9fc949,
+	0xbfd4af27, 0x88bbbdb5, 0xe2034090, 0x98d09675, 0x6e63a0e0,
+	0x15c361d2, 0xc2e7661d, 0x22d4ff8e,
+	0x28683b6f, 0xc07fd059, 0xff2379c8, 0x775f50e2, 0x43c340d3,
+	0xdf2f8656, 0x887ca41a, 0xa2d2bd2d,
+	0xa1c9e0d6, 0x346c4819, 0x61b76d87, 0x22540f2f, 0x2abe32e1,
+	0xaa54166b, 0x22568e3a, 0xa2d341d0,
+	0x66db40c8, 0xa784392f, 0x004dff2f, 0x2db9d2de, 0x97943fac,
+	0x4a97c1d8, 0x527644b7, 0xb5f437a7,
+	0xb82cbaef, 0xd751d159, 0x6ff7f0ed, 0x5a097a1f, 0x827b68d0,
+	0x90ecf52e, 0x22b0c054, 0xbc8e5935,
+	0x4b6d2f7f, 0x50bb64a2, 0xd2664910, 0xbee5812d, 0xb7332290,
+	0xe93b159f, 0xb48ee411, 0x4bff345d,
+	0xfd45c240, 0xad31973f, 0xc4f6d02e, 0x55fc8165, 0xd5b1caad,
+	0xa1ac2dae, 0xa2d4b76d, 0xc19b0c50,
+	0x882240f2, 0x0c6e4f38, 0xa4e4bfd7, 0x4f5ba272, 0x564c1d2f,
+	0xc59c5319, 0xb949e354, 0xb04669fe,
+	0xb1b6ab8a, 0xc71358dd, 0x6385c545, 0x110f935d, 0x57538ad5,
+	0x6a390493, 0xe63d37e0, 0x2a54f6b3,
+	0x3a787d5f, 0x6276a0b5, 0x19a6fcdf, 0x7a42206a, 0x29f9d4d5,
+	0xf61b1891, 0xbb72275e, 0xaa508167,
+	0x38901091, 0xc6b505eb, 0x84c7cb8c, 0x2ad75a0f, 0x874a1427,
+	0xa2d1936b, 0x2ad286af, 0xaa56d291,
+	0xd7894360, 0x425c750d, 0x93b39e26, 0x187184c9, 0x6c00b32d,
+	0x73e2bb14, 0xa0bebc3c, 0x54623779,
+	0x64459eab, 0x3f328b82, 0x7718cf82, 0x59a2cea6, 0x04ee002e,
+	0x89fe78e6, 0x3fab0950, 0x325ff6c2,
+	0x81383f05, 0x6963c5c8, 0x76cb5ad6, 0xd49974c9, 0xca180dcf,
+	0x380782d5, 0xc7fa5cf6, 0x8ac31511,
+	0x35e79e13, 0x47da91d0, 0xf40f9086, 0xa7e2419e, 0x31366241,
+	0x051ef495, 0xaa573b04, 0x4a805d8d,
+	0x548300d0, 0x00322a3c, 0xbf64cddf, 0xba57a68e, 0x75c6372b,
+	0x50afd341, 0xa7c13275, 0x915a0bf5,
+	0x6b54bfab, 0x2b0b1426, 0xab4cc9d7, 0x449ccd82, 0xf7fbf265,
+	0xab85c5f3, 0x1b55db94, 0xaad4e324,
+	0xcfa4bd3f, 0x2deaa3e2, 0x9e204d02, 0xc8bd25ac, 0xeadf55b3,
+	0xd5bd9e98, 0xe31231b2, 0x2ad5ad6c,
+	0x954329de, 0xadbe4528, 0xd8710f69, 0xaa51c90f, 0xaa786bf6,
+	0x22513f1e, 0xaa51a79b, 0x2ad344cc,
+	0x7b5a41f0, 0xd37cfbad, 0x1b069505, 0x41ece491, 0xb4c332e6,
+	0x032268d4, 0xc9600acc, 0xce387e6d,
+	0xbf6bb16c, 0x6a70fb78, 0x0d03d9c9, 0xd4df39de, 0xe01063da,
+	0x4736f464, 0x5ad328d8, 0xb347cc96,
+	0x75bb0fc3, 0x98511bfb, 0x4ffbcc35, 0xb58bcf6a, 0xe11f0abc,
+	0xbfc5fe4a, 0xa70aec10, 0xac39570a,
+	0x3f04442f, 0x6188b153, 0xe0397a2e, 0x5727cb79, 0x9ceb418f,
+	0x1cacd68d, 0x2ad37c96, 0x0175cb9d,
+	0xc69dff09, 0xc75b65f0, 0xd9db40d8, 0xec0e7779, 0x4744ead4,
+	0xb11c3274, 0xdd24cb9e, 0x7e1c54bd,
+	0xf01144f9, 0xd2240eb1, 0x9675b3fd, 0xa3ac3755, 0xd47c27af,
+	0x51c85f4d, 0x56907596, 0xa5bb15e6,
+	0x580304f0, 0xca042cf1, 0x011a37ea, 0x8dbfaadb, 0x35ba3e4a,
+	0x3526ffa0, 0xc37b4d09, 0xbc306ed9,
+	0x98a52666, 0x5648f725, 0xff5e569d, 0x0ced63d0, 0x7c63b2cf,
+	0x700b45e1, 0xd5ea50f1, 0x85a92872,
+	0xaf1fbda7, 0xd4234870, 0xa7870bf3, 0x2d3b4d79, 0x42e04198,
+	0x0cd0ede7, 0x26470db8, 0xf881814c,
+	0x474d6ad7, 0x7c0c5e5c, 0xd1231959, 0x381b7298, 0xf5d2f4db,
+	0xab838653, 0x6e2f1e23, 0x83719c9e,
+	0xbd91e046, 0x9a56456e, 0xdc39200c, 0x20c8c571, 0x962bda1c,
+	0xe1e696ff, 0xb141ab08, 0x7cca89b9,
+	0x1a69e783, 0x02cc4843, 0xa2f7c579, 0x429ef47d, 0x427b169c,
+	0x5ac9f049, 0xdd8f0f00, 0x5c8165bf
+};
+EXPORT_SYMBOL_GPL(cast_s1);
+
+const u32 cast_s2[256] = {
+	0x1f201094, 0xef0ba75b, 0x69e3cf7e, 0x393f4380, 0xfe61cf7a,
+	0xeec5207a, 0x55889c94, 0x72fc0651,
+	0xada7ef79, 0x4e1d7235, 0xd55a63ce, 0xde0436ba, 0x99c430ef,
+	0x5f0c0794, 0x18dcdb7d, 0xa1d6eff3,
+	0xa0b52f7b, 0x59e83605, 0xee15b094, 0xe9ffd909, 0xdc440086,
+	0xef944459, 0xba83ccb3, 0xe0c3cdfb,
+	0xd1da4181, 0x3b092ab1, 0xf997f1c1, 0xa5e6cf7b, 0x01420ddb,
+	0xe4e7ef5b, 0x25a1ff41, 0xe180f806,
+	0x1fc41080, 0x179bee7a, 0xd37ac6a9, 0xfe5830a4, 0x98de8b7f,
+	0x77e83f4e, 0x79929269, 0x24fa9f7b,
+	0xe113c85b, 0xacc40083, 0xd7503525, 0xf7ea615f, 0x62143154,
+	0x0d554b63, 0x5d681121, 0xc866c359,
+	0x3d63cf73, 0xcee234c0, 0xd4d87e87, 0x5c672b21, 0x071f6181,
+	0x39f7627f, 0x361e3084, 0xe4eb573b,
+	0x602f64a4, 0xd63acd9c, 0x1bbc4635, 0x9e81032d, 0x2701f50c,
+	0x99847ab4, 0xa0e3df79, 0xba6cf38c,
+	0x10843094, 0x2537a95e, 0xf46f6ffe, 0xa1ff3b1f, 0x208cfb6a,
+	0x8f458c74, 0xd9e0a227, 0x4ec73a34,
+	0xfc884f69, 0x3e4de8df, 0xef0e0088, 0x3559648d, 0x8a45388c,
+	0x1d804366, 0x721d9bfd, 0xa58684bb,
+	0xe8256333, 0x844e8212, 0x128d8098, 0xfed33fb4, 0xce280ae1,
+	0x27e19ba5, 0xd5a6c252, 0xe49754bd,
+	0xc5d655dd, 0xeb667064, 0x77840b4d, 0xa1b6a801, 0x84db26a9,
+	0xe0b56714, 0x21f043b7, 0xe5d05860,
+	0x54f03084, 0x066ff472, 0xa31aa153, 0xdadc4755, 0xb5625dbf,
+	0x68561be6, 0x83ca6b94, 0x2d6ed23b,
+	0xeccf01db, 0xa6d3d0ba, 0xb6803d5c, 0xaf77a709, 0x33b4a34c,
+	0x397bc8d6, 0x5ee22b95, 0x5f0e5304,
+	0x81ed6f61, 0x20e74364, 0xb45e1378, 0xde18639b, 0x881ca122,
+	0xb96726d1, 0x8049a7e8, 0x22b7da7b,
+	0x5e552d25, 0x5272d237, 0x79d2951c, 0xc60d894c, 0x488cb402,
+	0x1ba4fe5b, 0xa4b09f6b, 0x1ca815cf,
+	0xa20c3005, 0x8871df63, 0xb9de2fcb, 0x0cc6c9e9, 0x0beeff53,
+	0xe3214517, 0xb4542835, 0x9f63293c,
+	0xee41e729, 0x6e1d2d7c, 0x50045286, 0x1e6685f3, 0xf33401c6,
+	0x30a22c95, 0x31a70850, 0x60930f13,
+	0x73f98417, 0xa1269859, 0xec645c44, 0x52c877a9, 0xcdff33a6,
+	0xa02b1741, 0x7cbad9a2, 0x2180036f,
+	0x50d99c08, 0xcb3f4861, 0xc26bd765, 0x64a3f6ab, 0x80342676,
+	0x25a75e7b, 0xe4e6d1fc, 0x20c710e6,
+	0xcdf0b680, 0x17844d3b, 0x31eef84d, 0x7e0824e4, 0x2ccb49eb,
+	0x846a3bae, 0x8ff77888, 0xee5d60f6,
+	0x7af75673, 0x2fdd5cdb, 0xa11631c1, 0x30f66f43, 0xb3faec54,
+	0x157fd7fa, 0xef8579cc, 0xd152de58,
+	0xdb2ffd5e, 0x8f32ce19, 0x306af97a, 0x02f03ef8, 0x99319ad5,
+	0xc242fa0f, 0xa7e3ebb0, 0xc68e4906,
+	0xb8da230c, 0x80823028, 0xdcdef3c8, 0xd35fb171, 0x088a1bc8,
+	0xbec0c560, 0x61a3c9e8, 0xbca8f54d,
+	0xc72feffa, 0x22822e99, 0x82c570b4, 0xd8d94e89, 0x8b1c34bc,
+	0x301e16e6, 0x273be979, 0xb0ffeaa6,
+	0x61d9b8c6, 0x00b24869, 0xb7ffce3f, 0x08dc283b, 0x43daf65a,
+	0xf7e19798, 0x7619b72f, 0x8f1c9ba4,
+	0xdc8637a0, 0x16a7d3b1, 0x9fc393b7, 0xa7136eeb, 0xc6bcc63e,
+	0x1a513742, 0xef6828bc, 0x520365d6,
+	0x2d6a77ab, 0x3527ed4b, 0x821fd216, 0x095c6e2e, 0xdb92f2fb,
+	0x5eea29cb, 0x145892f5, 0x91584f7f,
+	0x5483697b, 0x2667a8cc, 0x85196048, 0x8c4bacea, 0x833860d4,
+	0x0d23e0f9, 0x6c387e8a, 0x0ae6d249,
+	0xb284600c, 0xd835731d, 0xdcb1c647, 0xac4c56ea, 0x3ebd81b3,
+	0x230eabb0, 0x6438bc87, 0xf0b5b1fa,
+	0x8f5ea2b3, 0xfc184642, 0x0a036b7a, 0x4fb089bd, 0x649da589,
+	0xa345415e, 0x5c038323, 0x3e5d3bb9,
+	0x43d79572, 0x7e6dd07c, 0x06dfdf1e, 0x6c6cc4ef, 0x7160a539,
+	0x73bfbe70, 0x83877605, 0x4523ecf1
+};
+EXPORT_SYMBOL_GPL(cast_s2);
+
+const u32 cast_s3[256] = {
+	0x8defc240, 0x25fa5d9f, 0xeb903dbf, 0xe810c907, 0x47607fff,
+	0x369fe44b, 0x8c1fc644, 0xaececa90,
+	0xbeb1f9bf, 0xeefbcaea, 0xe8cf1950, 0x51df07ae, 0x920e8806,
+	0xf0ad0548, 0xe13c8d83, 0x927010d5,
+	0x11107d9f, 0x07647db9, 0xb2e3e4d4, 0x3d4f285e, 0xb9afa820,
+	0xfade82e0, 0xa067268b, 0x8272792e,
+	0x553fb2c0, 0x489ae22b, 0xd4ef9794, 0x125e3fbc, 0x21fffcee,
+	0x825b1bfd, 0x9255c5ed, 0x1257a240,
+	0x4e1a8302, 0xbae07fff, 0x528246e7, 0x8e57140e, 0x3373f7bf,
+	0x8c9f8188, 0xa6fc4ee8, 0xc982b5a5,
+	0xa8c01db7, 0x579fc264, 0x67094f31, 0xf2bd3f5f, 0x40fff7c1,
+	0x1fb78dfc, 0x8e6bd2c1, 0x437be59b,
+	0x99b03dbf, 0xb5dbc64b, 0x638dc0e6, 0x55819d99, 0xa197c81c,
+	0x4a012d6e, 0xc5884a28, 0xccc36f71,
+	0xb843c213, 0x6c0743f1, 0x8309893c, 0x0feddd5f, 0x2f7fe850,
+	0xd7c07f7e, 0x02507fbf, 0x5afb9a04,
+	0xa747d2d0, 0x1651192e, 0xaf70bf3e, 0x58c31380, 0x5f98302e,
+	0x727cc3c4, 0x0a0fb402, 0x0f7fef82,
+	0x8c96fdad, 0x5d2c2aae, 0x8ee99a49, 0x50da88b8, 0x8427f4a0,
+	0x1eac5790, 0x796fb449, 0x8252dc15,
+	0xefbd7d9b, 0xa672597d, 0xada840d8, 0x45f54504, 0xfa5d7403,
+	0xe83ec305, 0x4f91751a, 0x925669c2,
+	0x23efe941, 0xa903f12e, 0x60270df2, 0x0276e4b6, 0x94fd6574,
+	0x927985b2, 0x8276dbcb, 0x02778176,
+	0xf8af918d, 0x4e48f79e, 0x8f616ddf, 0xe29d840e, 0x842f7d83,
+	0x340ce5c8, 0x96bbb682, 0x93b4b148,
+	0xef303cab, 0x984faf28, 0x779faf9b, 0x92dc560d, 0x224d1e20,
+	0x8437aa88, 0x7d29dc96, 0x2756d3dc,
+	0x8b907cee, 0xb51fd240, 0xe7c07ce3, 0xe566b4a1, 0xc3e9615e,
+	0x3cf8209d, 0x6094d1e3, 0xcd9ca341,
+	0x5c76460e, 0x00ea983b, 0xd4d67881, 0xfd47572c, 0xf76cedd9,
+	0xbda8229c, 0x127dadaa, 0x438a074e,
+	0x1f97c090, 0x081bdb8a, 0x93a07ebe, 0xb938ca15, 0x97b03cff,
+	0x3dc2c0f8, 0x8d1ab2ec, 0x64380e51,
+	0x68cc7bfb, 0xd90f2788, 0x12490181, 0x5de5ffd4, 0xdd7ef86a,
+	0x76a2e214, 0xb9a40368, 0x925d958f,
+	0x4b39fffa, 0xba39aee9, 0xa4ffd30b, 0xfaf7933b, 0x6d498623,
+	0x193cbcfa, 0x27627545, 0x825cf47a,
+	0x61bd8ba0, 0xd11e42d1, 0xcead04f4, 0x127ea392, 0x10428db7,
+	0x8272a972, 0x9270c4a8, 0x127de50b,
+	0x285ba1c8, 0x3c62f44f, 0x35c0eaa5, 0xe805d231, 0x428929fb,
+	0xb4fcdf82, 0x4fb66a53, 0x0e7dc15b,
+	0x1f081fab, 0x108618ae, 0xfcfd086d, 0xf9ff2889, 0x694bcc11,
+	0x236a5cae, 0x12deca4d, 0x2c3f8cc5,
+	0xd2d02dfe, 0xf8ef5896, 0xe4cf52da, 0x95155b67, 0x494a488c,
+	0xb9b6a80c, 0x5c8f82bc, 0x89d36b45,
+	0x3a609437, 0xec00c9a9, 0x44715253, 0x0a874b49, 0xd773bc40,
+	0x7c34671c, 0x02717ef6, 0x4feb5536,
+	0xa2d02fff, 0xd2bf60c4, 0xd43f03c0, 0x50b4ef6d, 0x07478cd1,
+	0x006e1888, 0xa2e53f55, 0xb9e6d4bc,
+	0xa2048016, 0x97573833, 0xd7207d67, 0xde0f8f3d, 0x72f87b33,
+	0xabcc4f33, 0x7688c55d, 0x7b00a6b0,
+	0x947b0001, 0x570075d2, 0xf9bb88f8, 0x8942019e, 0x4264a5ff,
+	0x856302e0, 0x72dbd92b, 0xee971b69,
+	0x6ea22fde, 0x5f08ae2b, 0xaf7a616d, 0xe5c98767, 0xcf1febd2,
+	0x61efc8c2, 0xf1ac2571, 0xcc8239c2,
+	0x67214cb8, 0xb1e583d1, 0xb7dc3e62, 0x7f10bdce, 0xf90a5c38,
+	0x0ff0443d, 0x606e6dc6, 0x60543a49,
+	0x5727c148, 0x2be98a1d, 0x8ab41738, 0x20e1be24, 0xaf96da0f,
+	0x68458425, 0x99833be5, 0x600d457d,
+	0x282f9350, 0x8334b362, 0xd91d1120, 0x2b6d8da0, 0x642b1e31,
+	0x9c305a00, 0x52bce688, 0x1b03588a,
+	0xf7baefd5, 0x4142ed9c, 0xa4315c11, 0x83323ec5, 0xdfef4636,
+	0xa133c501, 0xe9d3531c, 0xee353783
+};
+EXPORT_SYMBOL_GPL(cast_s3);
+
+const u32 cast_s4[256] = {
+	0x9db30420, 0x1fb6e9de, 0xa7be7bef, 0xd273a298, 0x4a4f7bdb,
+	0x64ad8c57, 0x85510443, 0xfa020ed1,
+	0x7e287aff, 0xe60fb663, 0x095f35a1, 0x79ebf120, 0xfd059d43,
+	0x6497b7b1, 0xf3641f63, 0x241e4adf,
+	0x28147f5f, 0x4fa2b8cd, 0xc9430040, 0x0cc32220, 0xfdd30b30,
+	0xc0a5374f, 0x1d2d00d9, 0x24147b15,
+	0xee4d111a, 0x0fca5167, 0x71ff904c, 0x2d195ffe, 0x1a05645f,
+	0x0c13fefe, 0x081b08ca, 0x05170121,
+	0x80530100, 0xe83e5efe, 0xac9af4f8, 0x7fe72701, 0xd2b8ee5f,
+	0x06df4261, 0xbb9e9b8a, 0x7293ea25,
+	0xce84ffdf, 0xf5718801, 0x3dd64b04, 0xa26f263b, 0x7ed48400,
+	0x547eebe6, 0x446d4ca0, 0x6cf3d6f5,
+	0x2649abdf, 0xaea0c7f5, 0x36338cc1, 0x503f7e93, 0xd3772061,
+	0x11b638e1, 0x72500e03, 0xf80eb2bb,
+	0xabe0502e, 0xec8d77de, 0x57971e81, 0xe14f6746, 0xc9335400,
+	0x6920318f, 0x081dbb99, 0xffc304a5,
+	0x4d351805, 0x7f3d5ce3, 0xa6c866c6, 0x5d5bcca9, 0xdaec6fea,
+	0x9f926f91, 0x9f46222f, 0x3991467d,
+	0xa5bf6d8e, 0x1143c44f, 0x43958302, 0xd0214eeb, 0x022083b8,
+	0x3fb6180c, 0x18f8931e, 0x281658e6,
+	0x26486e3e, 0x8bd78a70, 0x7477e4c1, 0xb506e07c, 0xf32d0a25,
+	0x79098b02, 0xe4eabb81, 0x28123b23,
+	0x69dead38, 0x1574ca16, 0xdf871b62, 0x211c40b7, 0xa51a9ef9,
+	0x0014377b, 0x041e8ac8, 0x09114003,
+	0xbd59e4d2, 0xe3d156d5, 0x4fe876d5, 0x2f91a340, 0x557be8de,
+	0x00eae4a7, 0x0ce5c2ec, 0x4db4bba6,
+	0xe756bdff, 0xdd3369ac, 0xec17b035, 0x06572327, 0x99afc8b0,
+	0x56c8c391, 0x6b65811c, 0x5e146119,
+	0x6e85cb75, 0xbe07c002, 0xc2325577, 0x893ff4ec, 0x5bbfc92d,
+	0xd0ec3b25, 0xb7801ab7, 0x8d6d3b24,
+	0x20c763ef, 0xc366a5fc, 0x9c382880, 0x0ace3205, 0xaac9548a,
+	0xeca1d7c7, 0x041afa32, 0x1d16625a,
+	0x6701902c, 0x9b757a54, 0x31d477f7, 0x9126b031, 0x36cc6fdb,
+	0xc70b8b46, 0xd9e66a48, 0x56e55a79,
+	0x026a4ceb, 0x52437eff, 0x2f8f76b4, 0x0df980a5, 0x8674cde3,
+	0xedda04eb, 0x17a9be04, 0x2c18f4df,
+	0xb7747f9d, 0xab2af7b4, 0xefc34d20, 0x2e096b7c, 0x1741a254,
+	0xe5b6a035, 0x213d42f6, 0x2c1c7c26,
+	0x61c2f50f, 0x6552daf9, 0xd2c231f8, 0x25130f69, 0xd8167fa2,
+	0x0418f2c8, 0x001a96a6, 0x0d1526ab,
+	0x63315c21, 0x5e0a72ec, 0x49bafefd, 0x187908d9, 0x8d0dbd86,
+	0x311170a7, 0x3e9b640c, 0xcc3e10d7,
+	0xd5cad3b6, 0x0caec388, 0xf73001e1, 0x6c728aff, 0x71eae2a1,
+	0x1f9af36e, 0xcfcbd12f, 0xc1de8417,
+	0xac07be6b, 0xcb44a1d8, 0x8b9b0f56, 0x013988c3, 0xb1c52fca,
+	0xb4be31cd, 0xd8782806, 0x12a3a4e2,
+	0x6f7de532, 0x58fd7eb6, 0xd01ee900, 0x24adffc2, 0xf4990fc5,
+	0x9711aac5, 0x001d7b95, 0x82e5e7d2,
+	0x109873f6, 0x00613096, 0xc32d9521, 0xada121ff, 0x29908415,
+	0x7fbb977f, 0xaf9eb3db, 0x29c9ed2a,
+	0x5ce2a465, 0xa730f32c, 0xd0aa3fe8, 0x8a5cc091, 0xd49e2ce7,
+	0x0ce454a9, 0xd60acd86, 0x015f1919,
+	0x77079103, 0xdea03af6, 0x78a8565e, 0xdee356df, 0x21f05cbe,
+	0x8b75e387, 0xb3c50651, 0xb8a5c3ef,
+	0xd8eeb6d2, 0xe523be77, 0xc2154529, 0x2f69efdf, 0xafe67afb,
+	0xf470c4b2, 0xf3e0eb5b, 0xd6cc9876,
+	0x39e4460c, 0x1fda8538, 0x1987832f, 0xca007367, 0xa99144f8,
+	0x296b299e, 0x492fc295, 0x9266beab,
+	0xb5676e69, 0x9bd3ddda, 0xdf7e052f, 0xdb25701c, 0x1b5e51ee,
+	0xf65324e6, 0x6afce36c, 0x0316cc04,
+	0x8644213e, 0xb7dc59d0, 0x7965291f, 0xccd6fd43, 0x41823979,
+	0x932bcdf6, 0xb657c34d, 0x4edfd282,
+	0x7ae5290c, 0x3cb9536b, 0x851e20fe, 0x9833557e, 0x13ecf0b0,
+	0xd3ffb372, 0x3f85c5c1, 0x0aef7ed2
+};
+EXPORT_SYMBOL_GPL(cast_s4);
+
+MODULE_LICENSE("GPL");
diff --git a/include/crypto/cast5.h b/include/crypto/cast5.h
index 586183a0406e..14fbf39d6380 100644
--- a/include/crypto/cast5.h
+++ b/include/crypto/cast5.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/crypto.h>
+#include <crypto/cast_common.h>
 
 #define CAST5_BLOCK_SIZE 8
 #define CAST5_MIN_KEY_SIZE 5
@@ -19,9 +20,4 @@ int cast5_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen);
 void __cast5_encrypt(struct cast5_ctx *ctx, u8 *dst, const u8 *src);
 void __cast5_decrypt(struct cast5_ctx *ctx, u8 *dst, const u8 *src);
 
-extern const u32 cast5_s1[256];
-extern const u32 cast5_s2[256];
-extern const u32 cast5_s3[256];
-extern const u32 cast5_s4[256];
-
 #endif
diff --git a/include/crypto/cast6.h b/include/crypto/cast6.h
index 157af6f342c8..32b60eb8bd24 100644
--- a/include/crypto/cast6.h
+++ b/include/crypto/cast6.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/crypto.h>
+#include <crypto/cast_common.h>
 
 #define CAST6_BLOCK_SIZE 16
 #define CAST6_MIN_KEY_SIZE 16
@@ -20,9 +21,4 @@ int cast6_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen);
 void __cast6_encrypt(struct cast6_ctx *ctx, u8 *dst, const u8 *src);
 void __cast6_decrypt(struct cast6_ctx *ctx, u8 *dst, const u8 *src);
 
-extern const u32 cast6_s1[256];
-extern const u32 cast6_s2[256];
-extern const u32 cast6_s3[256];
-extern const u32 cast6_s4[256];
-
 #endif
diff --git a/include/crypto/cast_common.h b/include/crypto/cast_common.h
new file mode 100644
index 000000000000..b7df35cd9f0a
--- /dev/null
+++ b/include/crypto/cast_common.h
@@ -0,0 +1,9 @@
+#ifndef _CRYPTO_CAST_COMMON_H
+#define _CRYPTO_CAST_COMMON_H
+
+extern const u32 cast_s1[256];
+extern const u32 cast_s2[256];
+extern const u32 cast_s3[256];
+extern const u32 cast_s4[256];
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 6d49e352ae9aed3f599041b0c0389aa924815f14 Mon Sep 17 00:00:00 2001
From: Nadia Yvette Chambers
Date: Thu, 6 Dec 2012 10:39:54 +0100
Subject: propagate name change to comments in kernel source

I've legally changed my name with New York State, the US Social Security
Administration, et al. This patch propagates the name change and change
in initials and login to comments in the kernel source as well.

Signed-off-by: Nadia Yvette Chambers <nyc@holomorphy.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 MAINTAINERS                       | 2 +-
 arch/alpha/include/asm/mmzone.h   | 2 +-
 arch/frv/mm/pgalloc.c             | 2 +-
 arch/mn10300/mm/pgtable.c         | 2 +-
 arch/x86/mm/pgtable.c             | 2 +-
 fs/hugetlbfs/inode.c              | 2 +-
 fs/ncpfs/mmap.c                   | 2 +-
 include/linux/hash.h              | 2 +-
 kernel/pid.c                      | 4 ++--
 kernel/profile.c                  | 7 ++++---
 kernel/trace/ftrace.c             | 2 +-
 kernel/trace/trace.c              | 2 +-
 kernel/trace/trace_functions.c    | 2 +-
 kernel/trace/trace_irqsoff.c      | 2 +-
 kernel/trace/trace_sched_wakeup.c | 2 +-
 kernel/wait.c                     | 2 +-
 lib/bitmap.c                      | 2 +-
 mm/hugetlb.c                      | 2 +-
 mm/page_alloc.c                   | 4 ++--
 19 files changed, 24 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 322db3ae83cf..e16a3f5a1b79 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3576,7 +3576,7 @@ S:	Maintained
 F:	drivers/input/touchscreen/htcpen.c
 
 HUGETLB FILESYSTEM
-M:	William Irwin <wli@holomorphy.com>
+M:	Nadia Yvette Chambers <nyc@holomorphy.com>
 S:	Maintained
 F:	fs/hugetlbfs/
 
diff --git a/arch/alpha/include/asm/mmzone.h b/arch/alpha/include/asm/mmzone.h
index 445dc42e0334..c5b5d6bac9ed 100644
--- a/arch/alpha/include/asm/mmzone.h
+++ b/arch/alpha/include/asm/mmzone.h
@@ -66,7 +66,7 @@ PLAT_NODE_DATA_LOCALNR(unsigned long p, int n)
     ((unsigned long)__va(NODE_DATA(kvaddr_to_nid(kaddr))->node_start_pfn  \
 			 << PAGE_SHIFT))
 
-/* XXX: FIXME -- wli */
+/* XXX: FIXME -- nyc */
 #define kern_addr_valid(kaddr)	(0)
 
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c
index 4fb63a36bd52..f6084bc524e8 100644
--- a/arch/frv/mm/pgalloc.c
+++ b/arch/frv/mm/pgalloc.c
@@ -77,7 +77,7 @@ void __set_pmd(pmd_t *pmdptr, unsigned long pmd)
  * checks at dup_mmap(), exec(), and other mmlist addition points
  * could be used. The locking scheme was chosen on the basis of
  * manfred's recommendations and having no core impact whatsoever.
- * -- wli
+ * -- nyc
  */
 DEFINE_SPINLOCK(pgd_lock);
 struct page *pgd_list;
diff --git a/arch/mn10300/mm/pgtable.c b/arch/mn10300/mm/pgtable.c
index 4ebf117c3285..bd9ada693f95 100644
--- a/arch/mn10300/mm/pgtable.c
+++ b/arch/mn10300/mm/pgtable.c
@@ -95,7 +95,7 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
  * checks at dup_mmap(), exec(), and other mmlist addition points
  * could be used. The locking scheme was chosen on the basis of
  * manfred's recommendations and having no core impact whatsoever.
- * -- wli
+ * -- nyc
  */
 DEFINE_SPINLOCK(pgd_lock);
 struct page *pgd_list;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 8573b83a63d0..217eb705fac0 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -137,7 +137,7 @@ static void pgd_dtor(pgd_t *pgd)
  * against pageattr.c; it is the unique case in which a valid change
  * of kernel pagetables can't be lazily synchronized by vmalloc faults.
  * vmalloc faults work because attached pagetables are never freed.
- * -- wli
+ * -- nyc
  */
 
 #ifdef CONFIG_X86_PAE
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index c5bc355d8243..c98d0665fa5c 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1,7 +1,7 @@
 /*
  * hugetlbpage-backed filesystem.  Based on ramfs.
  *
- * William Irwin, 2002
+ * Nadia Yvette Chambers, 2002
  *
  * Copyright (C) 2002 Linus Torvalds.
  */
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index be20a7e171a0..63d14a99483d 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -89,7 +89,7 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area,
 	/*
 	 * If I understand ncp_read_kernel() properly, the above always
 	 * fetches from the network, here the analogue of disk.
-	 * -- wli
+	 * -- nyc
 	 */
 	count_vm_event(PGMAJFAULT);
 	mem_cgroup_count_vm_event(area->vm_mm, PGMAJFAULT);
diff --git a/include/linux/hash.h b/include/linux/hash.h
index 24df9e70406f..61c97ae22e01 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -1,7 +1,7 @@
 #ifndef _LINUX_HASH_H
 #define _LINUX_HASH_H
 /* Fast hashing routine for ints,  longs and pointers.
-   (C) 2002 William Lee Irwin III, IBM */
+   (C) 2002 Nadia Yvette Chambers, IBM */
 
 /*
  * Knuth recommends primes in approximately golden ratio to the maximum
diff --git a/kernel/pid.c b/kernel/pid.c
index aebd4f5aaf41..fd996c1ed9f8 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -1,8 +1,8 @@
 /*
  * Generic pidhash and scalable, time-bounded PID allocator
  *
- * (C) 2002-2003 William Irwin, IBM
- * (C) 2004 William Irwin, Oracle
+ * (C) 2002-2003 Nadia Yvette Chambers, IBM
+ * (C) 2004 Nadia Yvette Chambers, Oracle
  * (C) 2002-2004 Ingo Molnar, Red Hat
  *
  * pid-structures are backing objects for tasks sharing a given ID to chain
diff --git a/kernel/profile.c b/kernel/profile.c
index 76b8e77773ee..1f391819c42f 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -8,9 +8,10 @@
  *  Scheduler profiling support, Arjan van de Ven and Ingo Molnar,
  *	Red Hat, July 2004
  *  Consolidation of architecture support code for profiling,
- *	William Irwin, Oracle, July 2004
+ *	Nadia Yvette Chambers, Oracle, July 2004
  *  Amortized hit count accounting via per-cpu open-addressed hashtables
- *	to resolve timer interrupt livelocks, William Irwin, Oracle, 2004
+ *	to resolve timer interrupt livelocks, Nadia Yvette Chambers,
+ *	Oracle, 2004
  */
 
 #include <linux/export.h>
@@ -256,7 +257,7 @@ EXPORT_SYMBOL_GPL(unregister_timer_hook);
  * pagetable hash functions, but uses a full hashtable full of finite
  * collision chains, not just pairs of them.
  *
- * -- wli
+ * -- nyc
  */
 static void __profile_flip_buffers(void *unused)
 {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 9dcf15d38380..b1a817c14ed5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -10,7 +10,7 @@
  * Based on code in the latency_tracer, that is:
  *
  *  Copyright (C) 2004-2006 Ingo Molnar
- *  Copyright (C) 2004 William Lee Irwin III
+ *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 
 #include <linux/stop_machine.h>
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 31e4f55773f1..3cff052715fe 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9,7 +9,7 @@
  *
  * Based on code from the latency_tracer, that is:
  *  Copyright (C) 2004-2006 Ingo Molnar
- *  Copyright (C) 2004 William Lee Irwin III
+ *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 #include <linux/ring_buffer.h>
 #include <generated/utsrelease.h>
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 507a7a9630bf..c7b83d03ff68 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -7,7 +7,7 @@
  * Based on code from the latency_tracer, that is:
  *
  *  Copyright (C) 2004-2006 Ingo Molnar
- *  Copyright (C) 2004 William Lee Irwin III
+ *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 #include <linux/ring_buffer.h>
 #include <linux/debugfs.h>
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index d98ee8283b29..cddb3b40bf7b 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -7,7 +7,7 @@
  * From code in the latency_tracer, that is:
  *
  *  Copyright (C) 2004-2006 Ingo Molnar
- *  Copyright (C) 2004 William Lee Irwin III
+ *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 #include <linux/kallsyms.h>
 #include <linux/debugfs.h>
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 02170c00c413..45464947a5ff 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -7,7 +7,7 @@
  * Based on code from the latency_tracer, that is:
  *
  *  Copyright (C) 2004-2006 Ingo Molnar
- *  Copyright (C) 2004 William Lee Irwin III
+ *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 #include <linux/module.h>
 #include <linux/fs.h>
diff --git a/kernel/wait.c b/kernel/wait.c
index 7fdd9eaca2c3..6698e0c04ead 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -1,7 +1,7 @@
 /*
  * Generic waiting primitives.
  *
- * (C) 2004 William Irwin, Oracle
+ * (C) 2004 Nadia Yvette Chambers, Oracle
  */
 #include <linux/init.h>
 #include <linux/export.h>
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 06fdfa1aeba7..06f7e4fe8d2d 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -353,7 +353,7 @@ again:
 EXPORT_SYMBOL(bitmap_find_next_zero_area);
 
 /*
- * Bitmap printing & parsing functions: first version by Bill Irwin,
+ * Bitmap printing & parsing functions: first version by Nadia Yvette Chambers,
  * second version by Paul Jackson, third by Joe Korty.
  */
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 59a0059b39e2..3b7a20ea3808 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1,6 +1,6 @@
 /*
  * Generic hugetlb support.
- * (C) William Irwin, April 2004
+ * (C) Nadia Yvette Chambers, April 2004
  */
 #include <linux/list.h>
 #include <linux/init.h>
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5b74de6702e0..57806b7e118b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -523,7 +523,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
  * If a block is freed, and its buddy is also free, then this
  * triggers coalescing into a block of larger size.
  *
- * -- wli
+ * -- nyc
  */
 
 static inline void __free_one_page(struct page *page,
@@ -780,7 +780,7 @@ void __init init_cma_reserved_pageblock(struct page *page)
  * large block of memory acted on by a series of small allocations.
  * This behavior is a critical factor in sglist merging's success.
  *
- * -- wli
+ * -- nyc
  */
 static inline void expand(struct zone *zone, struct page *page,
 	int low, int high, struct free_area *area,
-- 
cgit v1.2.3-55-g7522


From 01331040e6442ad09181bfaacd8bb9687dce2389 Mon Sep 17 00:00:00 2001
From: Johannes Berg
Date: Wed, 5 Dec 2012 16:45:31 +0100
Subject: wireless: fix VHT max AMPDU exponent definition

This is really a 3-bit field, not a single bit,
so declare a mask and shift. Also fix hwsim, it
advertises the maximum possible.

While at it reindent all the defines using tabs
instead of spaces.

Change-Id: I7cd81c0d72f76deb5010aba5bfa3dd312006e898
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c |  2 +-
 include/linux/ieee80211.h             | 54 ++++++++++++++++++-----------------
 2 files changed, 29 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 8a61dbd320e6..ff9085502bea 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2223,7 +2223,7 @@ static int __init init_mac80211_hwsim(void)
 				IEEE80211_VHT_CAP_RXSTBC_2 |
 				IEEE80211_VHT_CAP_RXSTBC_3 |
 				IEEE80211_VHT_CAP_RXSTBC_4 |
-				IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT;
+				IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK;
 			sband->vht_cap.vht_mcs.rx_mcs_map =
 				cpu_to_le16(IEEE80211_VHT_MCS_SUPPORT_0_8 << 0 |
 					    IEEE80211_VHT_MCS_SUPPORT_0_8 << 2 |
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 8f690e53dd89..f0859cc73861 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1251,32 +1251,34 @@ struct ieee80211_vht_operation {
 #define IEEE80211_VHT_MCS_NOT_SUPPORTED 3
 
 /* 802.11ac VHT Capabilities */
-#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895                0x00000000
-#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991                0x00000001
-#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454               0x00000002
-#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ              0x00000004
-#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ     0x00000008
-#define IEEE80211_VHT_CAP_RXLDPC                              0x00000010
-#define IEEE80211_VHT_CAP_SHORT_GI_80                         0x00000020
-#define IEEE80211_VHT_CAP_SHORT_GI_160                        0x00000040
-#define IEEE80211_VHT_CAP_TXSTBC                              0x00000080
-#define IEEE80211_VHT_CAP_RXSTBC_1                            0x00000100
-#define IEEE80211_VHT_CAP_RXSTBC_2                            0x00000200
-#define IEEE80211_VHT_CAP_RXSTBC_3                            0x00000300
-#define IEEE80211_VHT_CAP_RXSTBC_4                            0x00000400
-#define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE               0x00000800
-#define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE               0x00001000
-#define IEEE80211_VHT_CAP_BEAMFORMER_ANTENNAS_MAX             0x00006000
-#define IEEE80211_VHT_CAP_SOUNDING_DIMENTION_MAX              0x00030000
-#define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE               0x00080000
-#define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE               0x00100000
-#define IEEE80211_VHT_CAP_VHT_TXOP_PS                         0x00200000
-#define IEEE80211_VHT_CAP_HTC_VHT                             0x00400000
-#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT          0x00800000
-#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB   0x08000000
-#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB     0x0c000000
-#define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN                  0x10000000
-#define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN                  0x20000000
+#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895			0x00000000
+#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991			0x00000001
+#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454			0x00000002
+#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ		0x00000004
+#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ	0x00000008
+#define IEEE80211_VHT_CAP_RXLDPC				0x00000010
+#define IEEE80211_VHT_CAP_SHORT_GI_80				0x00000020
+#define IEEE80211_VHT_CAP_SHORT_GI_160				0x00000040
+#define IEEE80211_VHT_CAP_TXSTBC				0x00000080
+#define IEEE80211_VHT_CAP_RXSTBC_1				0x00000100
+#define IEEE80211_VHT_CAP_RXSTBC_2				0x00000200
+#define IEEE80211_VHT_CAP_RXSTBC_3				0x00000300
+#define IEEE80211_VHT_CAP_RXSTBC_4				0x00000400
+#define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE			0x00000800
+#define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE			0x00001000
+#define IEEE80211_VHT_CAP_BEAMFORMER_ANTENNAS_MAX		0x00006000
+#define IEEE80211_VHT_CAP_SOUNDING_DIMENTION_MAX		0x00030000
+#define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE			0x00080000
+#define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE			0x00100000
+#define IEEE80211_VHT_CAP_VHT_TXOP_PS				0x00200000
+#define IEEE80211_VHT_CAP_HTC_VHT				0x00400000
+#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT	23
+#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK	\
+		(7 << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT)
+#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB	0x08000000
+#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB	0x0c000000
+#define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN			0x10000000
+#define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN			0x20000000
 
 /* Authentication algorithms */
 #define WLAN_AUTH_OPEN 0
-- 
cgit v1.2.3-55-g7522


From 3f3299d5c0268d6cc3f47b446e8aca436e4a5651 Mon Sep 17 00:00:00 2001
From: Bart Van Assche
Date: Wed, 28 Nov 2012 13:42:38 +0100
Subject: block: Rename queue dead flag

QUEUE_FLAG_DEAD is used to indicate that queuing new requests must
stop. After this flag has been set queue draining starts. However,
during the queue draining phase it is still safe to invoke the
queue's request_fn, so QUEUE_FLAG_DYING is a better name for this
flag.

This patch has been generated by running the following command
over the kernel source tree:

git grep -lEw 'blk_queue_dead|QUEUE_FLAG_DEAD' |
    xargs sed -i.tmp -e 's/blk_queue_dead/blk_queue_dying/g'      \
        -e 's/QUEUE_FLAG_DEAD/QUEUE_FLAG_DYING/g';                \
sed -i.tmp -e "s/QUEUE_FLAG_DYING$(printf \\t)*5/QUEUE_FLAG_DYING$(printf \\t)5/g" \
    include/linux/blkdev.h;                                       \
sed -i.tmp -e 's/ DEAD/ DYING/g' -e 's/dead queue/a dying queue/' \
    -e 's/Dead queue/A dying queue/' block/blk-core.c

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: James Bottomley <JBottomley@Parallels.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Chanho Min <chanho.min@lge.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c      |  2 +-
 block/blk-core.c        | 26 +++++++++++++-------------
 block/blk-exec.c        |  2 +-
 block/blk-sysfs.c       |  4 ++--
 block/blk-throttle.c    |  2 +-
 block/blk.h             |  2 +-
 drivers/scsi/scsi_lib.c |  2 +-
 include/linux/blkdev.h  |  4 ++--
 8 files changed, 22 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index d0b770391ad4..5dea4e8dbc55 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -231,7 +231,7 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 	 * we shouldn't allow anything to go through for a bypassing queue.
 	 */
 	if (unlikely(blk_queue_bypass(q)))
-		return ERR_PTR(blk_queue_dead(q) ? -EINVAL : -EBUSY);
+		return ERR_PTR(blk_queue_dying(q) ? -EINVAL : -EBUSY);
 	return __blkg_lookup_create(blkcg, q, NULL);
 }
 EXPORT_SYMBOL_GPL(blkg_lookup_create);
diff --git a/block/blk-core.c b/block/blk-core.c
index ee0e5cafa859..1a95272cca50 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -473,20 +473,20 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end);
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
  *
- * Mark @q DEAD, drain all pending requests, destroy and put it.  All
+ * Mark @q DYING, drain all pending requests, destroy and put it.  All
  * future requests will be failed immediately with -ENODEV.
  */
 void blk_cleanup_queue(struct request_queue *q)
 {
 	spinlock_t *lock = q->queue_lock;
 
-	/* mark @q DEAD, no new request or merges will be allowed afterwards */
+	/* mark @q DYING, no new request or merges will be allowed afterwards */
 	mutex_lock(&q->sysfs_lock);
-	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
+	queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
 	spin_lock_irq(lock);
 
 	/*
-	 * Dead queue is permanently in bypass mode till released.  Note
+	 * A dying queue is permanently in bypass mode till released.  Note
 	 * that, unlike blk_queue_bypass_start(), we aren't performing
 	 * synchronize_rcu() after entering bypass mode to avoid the delay
 	 * as some drivers create and destroy a lot of queues while
@@ -499,11 +499,11 @@ void blk_cleanup_queue(struct request_queue *q)
 
 	queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
-	queue_flag_set(QUEUE_FLAG_DEAD, q);
+	queue_flag_set(QUEUE_FLAG_DYING, q);
 	spin_unlock_irq(lock);
 	mutex_unlock(&q->sysfs_lock);
 
-	/* drain all requests queued before DEAD marking */
+	/* drain all requests queued before DYING marking */
 	blk_drain_queue(q, true);
 
 	/* @q won't process any more request, flush async actions */
@@ -716,7 +716,7 @@ EXPORT_SYMBOL(blk_init_allocated_queue);
 
 bool blk_get_queue(struct request_queue *q)
 {
-	if (likely(!blk_queue_dead(q))) {
+	if (likely(!blk_queue_dying(q))) {
 		__blk_get_queue(q);
 		return true;
 	}
@@ -870,7 +870,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 	const bool is_sync = rw_is_sync(rw_flags) != 0;
 	int may_queue;
 
-	if (unlikely(blk_queue_dead(q)))
+	if (unlikely(blk_queue_dying(q)))
 		return NULL;
 
 	may_queue = elv_may_queue(q, rw_flags);
@@ -1050,7 +1050,7 @@ retry:
 	if (rq)
 		return rq;
 
-	if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dead(q))) {
+	if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) {
 		blk_put_rl(rl);
 		return NULL;
 	}
@@ -1910,7 +1910,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 		return -EIO;
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	if (unlikely(blk_queue_dead(q))) {
+	if (unlikely(blk_queue_dying(q))) {
 		spin_unlock_irqrestore(q->queue_lock, flags);
 		return -ENODEV;
 	}
@@ -2885,9 +2885,9 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
 	trace_block_unplug(q, depth, !from_schedule);
 
 	/*
-	 * Don't mess with dead queue.
+	 * Don't mess with a dying queue.
 	 */
-	if (unlikely(blk_queue_dead(q))) {
+	if (unlikely(blk_queue_dying(q))) {
 		spin_unlock(q->queue_lock);
 		return;
 	}
@@ -2996,7 +2996,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		/*
 		 * Short-circuit if @q is dead
 		 */
-		if (unlikely(blk_queue_dead(q))) {
+		if (unlikely(blk_queue_dying(q))) {
 			__blk_end_request_all(rq, -ENODEV);
 			continue;
 		}
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 8b6dc5bd4dd0..4aec98df7ba5 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -60,7 +60,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	spin_lock_irq(q->queue_lock);
 
-	if (unlikely(blk_queue_dead(q))) {
+	if (unlikely(blk_queue_dying(q))) {
 		rq->errors = -ENXIO;
 		if (rq->end_io)
 			rq->end_io(rq, rq->errors);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index ce6204608822..788147797a79 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -466,7 +466,7 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 	if (!entry->show)
 		return -EIO;
 	mutex_lock(&q->sysfs_lock);
-	if (blk_queue_dead(q)) {
+	if (blk_queue_dying(q)) {
 		mutex_unlock(&q->sysfs_lock);
 		return -ENOENT;
 	}
@@ -488,7 +488,7 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 
 	q = container_of(kobj, struct request_queue, kobj);
 	mutex_lock(&q->sysfs_lock);
-	if (blk_queue_dead(q)) {
+	if (blk_queue_dying(q)) {
 		mutex_unlock(&q->sysfs_lock);
 		return -ENOENT;
 	}
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index a9664fa0b609..31146225f3d0 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -302,7 +302,7 @@ static struct throtl_grp *throtl_lookup_create_tg(struct throtl_data *td,
 		/* if %NULL and @q is alive, fall back to root_tg */
 		if (!IS_ERR(blkg))
 			tg = blkg_to_tg(blkg);
-		else if (!blk_queue_dead(q))
+		else if (!blk_queue_dying(q))
 			tg = td_root_tg(td);
 	}
 
diff --git a/block/blk.h b/block/blk.h
index ca51543b248c..2218a8a78292 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -96,7 +96,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			q->flush_queue_delayed = 1;
 			return NULL;
 		}
-		if (unlikely(blk_queue_dead(q)) ||
+		if (unlikely(blk_queue_dying(q)) ||
 		    !q->elevator->type->ops.elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index da36a3a81a9e..f29a1a9b54d2 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1406,7 +1406,7 @@ static int scsi_lld_busy(struct request_queue *q)
 	struct scsi_device *sdev = q->queuedata;
 	struct Scsi_Host *shost;
 
-	if (blk_queue_dead(q))
+	if (blk_queue_dying(q))
 		return 0;
 
 	shost = sdev->host;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1756001210d2..aba8246afe72 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -437,7 +437,7 @@ struct request_queue {
 #define QUEUE_FLAG_STOPPED	2	/* queue is stopped */
 #define	QUEUE_FLAG_SYNCFULL	3	/* read queue has been filled */
 #define QUEUE_FLAG_ASYNCFULL	4	/* write queue has been filled */
-#define QUEUE_FLAG_DEAD		5	/* queue being torn down */
+#define QUEUE_FLAG_DYING	5	/* queue being torn down */
 #define QUEUE_FLAG_BYPASS	6	/* act as dumb FIFO queue */
 #define QUEUE_FLAG_BIDI		7	/* queue supports bidi requests */
 #define QUEUE_FLAG_NOMERGES     8	/* disable merge attempts */
@@ -521,7 +521,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
-#define blk_queue_dead(q)	test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
+#define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
 #define blk_queue_bypass(q)	test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_noxmerges(q)	\
-- 
cgit v1.2.3-55-g7522


From c246e80d86736312933646896c4157daf511dadc Mon Sep 17 00:00:00 2001
From: Bart Van Assche
Date: Thu, 6 Dec 2012 14:32:01 +0100
Subject: block: Avoid that request_fn is invoked on a dead queue

A block driver may start cleaning up resources needed by its
request_fn as soon as blk_cleanup_queue() finished, so request_fn
must not be invoked after draining finished. This is important
when blk_run_queue() is invoked without any requests in progress.
As an example, if blk_drain_queue() and scsi_run_queue() run in
parallel, blk_drain_queue() may have finished all requests after
scsi_run_queue() has taken a SCSI device off the starved list but
before that last function has had a chance to run the queue.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Cc: James Bottomley <JBottomley@Parallels.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Chanho Min <chanho.min@lge.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 31 +++++++++++++++++++++++++++----
 block/blk-exec.c       |  2 +-
 block/blk.h            |  2 ++
 include/linux/blkdev.h |  2 ++
 4 files changed, 32 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index a182b586b06a..f52d05ff5d24 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -292,6 +292,25 @@ void blk_sync_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
+/**
+ * __blk_run_queue_uncond - run a queue whether or not it has been stopped
+ * @q:	The queue to run
+ *
+ * Description:
+ *    Invoke request handling on a queue if there are any pending requests.
+ *    May be used to restart request handling after a request has completed.
+ *    This variant runs the queue whether or not the queue has been
+ *    stopped. Must be called with the queue lock held and interrupts
+ *    disabled. See also @blk_run_queue.
+ */
+inline void __blk_run_queue_uncond(struct request_queue *q)
+{
+	if (unlikely(blk_queue_dead(q)))
+		return;
+
+	q->request_fn(q);
+}
+
 /**
  * __blk_run_queue - run a single device queue
  * @q:	The queue to run
@@ -305,7 +324,7 @@ void __blk_run_queue(struct request_queue *q)
 	if (unlikely(blk_queue_stopped(q)))
 		return;
 
-	q->request_fn(q);
+	__blk_run_queue_uncond(q);
 }
 EXPORT_SYMBOL(__blk_run_queue);
 
@@ -477,8 +496,8 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end);
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
  *
- * Mark @q DYING, drain all pending requests, destroy and put it.  All
- * future requests will be failed immediately with -ENODEV.
+ * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and
+ * put it.  All future requests will be failed immediately with -ENODEV.
  */
 void blk_cleanup_queue(struct request_queue *q)
 {
@@ -507,9 +526,13 @@ void blk_cleanup_queue(struct request_queue *q)
 	spin_unlock_irq(lock);
 	mutex_unlock(&q->sysfs_lock);
 
-	/* drain all requests queued before DYING marking */
+	/*
+	 * Drain all requests queued before DYING marking. Set DEAD flag to
+	 * prevent that q->request_fn() gets invoked after draining finished.
+	 */
 	spin_lock_irq(lock);
 	__blk_drain_queue(q, true);
+	queue_flag_set(QUEUE_FLAG_DEAD, q);
 	spin_unlock_irq(lock);
 
 	/* @q won't process any more request, flush async actions */
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 4aec98df7ba5..1320e74d79b8 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -72,7 +72,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	__blk_run_queue(q);
 	/* the queue is stopped so it won't be run */
 	if (rq->cmd_type == REQ_TYPE_PM_RESUME)
-		q->request_fn(q);
+		__blk_run_queue_uncond(q);
 	spin_unlock_irq(q->queue_lock);
 }
 EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
diff --git a/block/blk.h b/block/blk.h
index 2218a8a78292..47fdfdd41520 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -145,6 +145,8 @@ int blk_try_merge(struct request *rq, struct bio *bio);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
+void __blk_run_queue_uncond(struct request_queue *q);
+
 int blk_dev_init(void);
 
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index aba8246afe72..8bc46c250ca4 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -452,6 +452,7 @@ struct request_queue {
 #define QUEUE_FLAG_ADD_RANDOM  16	/* Contributes to random pool */
 #define QUEUE_FLAG_SECDISCARD  17	/* supports SECDISCARD */
 #define QUEUE_FLAG_SAME_FORCE  18	/* force complete on same CPU */
+#define QUEUE_FLAG_DEAD        19	/* queue tear-down finished */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -522,6 +523,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
+#define blk_queue_dead(q)	test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
 #define blk_queue_bypass(q)	test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_noxmerges(q)	\
-- 
cgit v1.2.3-55-g7522


From 24faf6f604efe18236bded4303009fc252913bf0 Mon Sep 17 00:00:00 2001
From: Bart Van Assche
Date: Wed, 28 Nov 2012 13:46:45 +0100
Subject: block: Make blk_cleanup_queue() wait until request_fn finished

Some request_fn implementations, e.g. scsi_request_fn(), unlock
the queue lock internally. This may result in multiple threads
executing request_fn for the same queue simultaneously. Keep
track of the number of active request_fn calls and make sure that
blk_cleanup_queue() waits until all active request_fn invocations
have finished. A block driver may start cleaning up resources
needed by its request_fn as soon as blk_cleanup_queue() finished,
so blk_cleanup_queue() must wait for all outstanding request_fn
invocations to finish.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reported-by: Chanho Min <chanho.min@lge.com>
Cc: James Bottomley <JBottomley@Parallels.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 10 ++++++++++
 include/linux/blkdev.h |  6 ++++++
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 9fb23537c7ad..473015ee28a2 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -309,7 +309,16 @@ inline void __blk_run_queue_uncond(struct request_queue *q)
 	if (unlikely(blk_queue_dead(q)))
 		return;
 
+	/*
+	 * Some request_fn implementations, e.g. scsi_request_fn(), unlock
+	 * the queue lock internally. As a result multiple threads may be
+	 * running such a request function concurrently. Keep track of the
+	 * number of active request_fn invocations such that blk_drain_queue()
+	 * can wait until all these request_fn calls have finished.
+	 */
+	q->request_fn_active++;
 	q->request_fn(q);
+	q->request_fn_active--;
 }
 
 /**
@@ -408,6 +417,7 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
 			__blk_run_queue(q);
 
 		drain |= q->nr_rqs_elvpriv;
+		drain |= q->request_fn_active;
 
 		/*
 		 * Unfortunately, requests are queued at and tracked from
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8bc46c250ca4..c9d233e727f2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -378,6 +378,12 @@ struct request_queue {
 
 	unsigned int		nr_sorted;
 	unsigned int		in_flight[2];
+	/*
+	 * Number of active block driver functions for which blk_drain_queue()
+	 * must wait. Must be incremented around functions that unlock the
+	 * queue_lock internally, e.g. scsi_request_fn().
+	 */
+	unsigned int		request_fn_active;
 
 	unsigned int		rq_timeout;
 	struct timer_list	timeout;
-- 
cgit v1.2.3-55-g7522


From 80729beb3326fd682543f4f4ea534df47ab48967 Mon Sep 17 00:00:00 2001
From: Bart Van Assche
Date: Wed, 28 Nov 2012 13:47:36 +0100
Subject: bsg: Remove unused function bsg_goose_queue()

The function bsg_goose_queue() does not have any in-tree callers,
so let's remove it.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bsg-lib.c         | 13 -------------
 include/linux/bsg-lib.h |  1 -
 2 files changed, 14 deletions(-)

(limited to 'include')

diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index deee61fbb741..650f427d915b 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -151,19 +151,6 @@ failjob_rls_job:
 	return -ENOMEM;
 }
 
-/*
- * bsg_goose_queue - restart queue in case it was stopped
- * @q: request q to be restarted
- */
-void bsg_goose_queue(struct request_queue *q)
-{
-	if (!q)
-		return;
-
-	blk_run_queue_async(q);
-}
-EXPORT_SYMBOL_GPL(bsg_goose_queue);
-
 /**
  * bsg_request_fn - generic handler for bsg requests
  * @q: request queue to manage
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index 4d0fb3df2f4a..a226652a5a6c 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -67,6 +67,5 @@ void bsg_job_done(struct bsg_job *job, int result,
 int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name,
 		    bsg_job_fn *job_fn, int dd_job_size);
 void bsg_request_fn(struct request_queue *q);
-void bsg_goose_queue(struct request_queue *q);
 
 #endif
-- 
cgit v1.2.3-55-g7522


From bc245cc36c5687dd3fbf6d4a1b3c13d41f9cb189 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Wed, 5 Dec 2012 18:45:58 +0100
Subject: ssb/bcma: add common header for watchdog

This adds a common header for watchdog functions, so a watchdog driver
just needs to use this and could provide watchdog functionality for ssb
and bcma based SoCs. Patches for a watchdog driver using this interface
will be send later.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/linux/bcm47xx_wdt.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
 create mode 100644 include/linux/bcm47xx_wdt.h

(limited to 'include')

diff --git a/include/linux/bcm47xx_wdt.h b/include/linux/bcm47xx_wdt.h
new file mode 100644
index 000000000000..e5dfc256485b
--- /dev/null
+++ b/include/linux/bcm47xx_wdt.h
@@ -0,0 +1,19 @@
+#ifndef LINUX_BCM47XX_WDT_H_
+#define LINUX_BCM47XX_WDT_H_
+
+#include <linux/types.h>
+
+
+struct bcm47xx_wdt {
+	u32 (*timer_set)(struct bcm47xx_wdt *, u32);
+	u32 (*timer_set_ms)(struct bcm47xx_wdt *, u32);
+	u32 max_timer_ms;
+
+	void *driver_data;
+};
+
+static inline void *bcm47xx_wdt_get_drvdata(struct bcm47xx_wdt *wdt)
+{
+	return wdt->driver_data;
+}
+#endif /* LINUX_BCM47XX_WDT_H_ */
-- 
cgit v1.2.3-55-g7522


From a22a3114a820ca3eadee6af53d90736e5ca68fa1 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Wed, 5 Dec 2012 18:46:01 +0100
Subject: bcma: add methods for watchdog driver

The watchdog driver wants to set the watchdog timeout in ms and not in
ticks, which is depending on the SoC type and the clock.
Calculate the number of ticks per millisecond and provide two functions
for the watchdog driver. Also return the ticks or millisecond the timer
was set to in case the provided value was bigger than the max allowed
value.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/driver_chipcommon.c            | 38 ++++++++++++++++++++++++++++-
 include/linux/bcma/bcma_driver_chipcommon.h |  4 +--
 2 files changed, 39 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c
index 7c132e5eceb0..117222697e1f 100644
--- a/drivers/bcma/driver_chipcommon.c
+++ b/drivers/bcma/driver_chipcommon.c
@@ -10,6 +10,7 @@
  */
 
 #include "bcma_private.h"
+#include <linux/bcm47xx_wdt.h>
 #include <linux/export.h>
 #include <linux/bcma/bcma.h>
 
@@ -52,6 +53,39 @@ static u32 bcma_chipco_watchdog_get_max_timer(struct bcma_drv_cc *cc)
 		return (1 << nb) - 1;
 }
 
+static u32 bcma_chipco_watchdog_timer_set_wdt(struct bcm47xx_wdt *wdt,
+					      u32 ticks)
+{
+	struct bcma_drv_cc *cc = bcm47xx_wdt_get_drvdata(wdt);
+
+	return bcma_chipco_watchdog_timer_set(cc, ticks);
+}
+
+static u32 bcma_chipco_watchdog_timer_set_ms_wdt(struct bcm47xx_wdt *wdt,
+						 u32 ms)
+{
+	struct bcma_drv_cc *cc = bcm47xx_wdt_get_drvdata(wdt);
+	u32 ticks;
+
+	ticks = bcma_chipco_watchdog_timer_set(cc, cc->ticks_per_ms * ms);
+	return ticks / cc->ticks_per_ms;
+}
+
+static int bcma_chipco_watchdog_ticks_per_ms(struct bcma_drv_cc *cc)
+{
+	struct bcma_bus *bus = cc->core->bus;
+
+	if (cc->capabilities & BCMA_CC_CAP_PMU) {
+		if (bus->chipinfo.id == BCMA_CHIP_ID_BCM4706)
+			/* 4706 CC and PMU watchdogs are clocked at 1/4 of ALP clock */
+			return bcma_chipco_alp_clock(cc) / 4000;
+		else
+			/* based on 32KHz ILP clock */
+			return 32;
+	} else {
+		return bcma_chipco_alp_clock(cc) / 1000;
+	}
+}
 
 void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc)
 {
@@ -100,12 +134,13 @@ void bcma_core_chipcommon_init(struct bcma_drv_cc *cc)
 			((leddc_on << BCMA_CC_GPIOTIMER_ONTIME_SHIFT) |
 			 (leddc_off << BCMA_CC_GPIOTIMER_OFFTIME_SHIFT)));
 	}
+	cc->ticks_per_ms = bcma_chipco_watchdog_ticks_per_ms(cc);
 
 	cc->setup_done = true;
 }
 
 /* Set chip watchdog reset timer to fire in 'ticks' backplane cycles */
-void bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks)
+u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks)
 {
 	u32 maxt;
 	enum bcma_clkmode clkmode;
@@ -125,6 +160,7 @@ void bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks)
 		/* instant NMI */
 		bcma_cc_write32(cc, BCMA_CC_WATCHDOG, ticks);
 	}
+	return ticks;
 }
 
 void bcma_chipco_irq_mask(struct bcma_drv_cc *cc, u32 mask, u32 value)
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index 145f3c56227f..2f9b01493a90 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -570,6 +570,7 @@ struct bcma_drv_cc {
 	int nr_serial_ports;
 	struct bcma_serial_port serial_ports[4];
 #endif /* CONFIG_BCMA_DRIVER_MIPS */
+	u32 ticks_per_ms;
 };
 
 /* Register access */
@@ -593,8 +594,7 @@ extern void bcma_chipco_resume(struct bcma_drv_cc *cc);
 
 void bcma_chipco_bcm4331_ext_pa_lines_ctl(struct bcma_drv_cc *cc, bool enable);
 
-extern void bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc,
-					  u32 ticks);
+extern u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks);
 
 void bcma_chipco_irq_mask(struct bcma_drv_cc *cc, u32 mask, u32 value);
 
-- 
cgit v1.2.3-55-g7522


From a4855f39d4eb3f550ca5f4aac79bd999da42dc54 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Wed, 5 Dec 2012 18:46:02 +0100
Subject: bcma: register watchdog driver

Register the watchdog driver to the system if this is a SoC. Using the
watchdog on a non SoC device, like a PCIe card, will make the PCIe
card die when the timeout expired, but starting it again is not
supported by bcma.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/bcma_private.h                 |  2 ++
 drivers/bcma/driver_chipcommon.c            | 22 ++++++++++++++++++++++
 drivers/bcma/main.c                         |  8 ++++++++
 include/linux/bcma/bcma_driver_chipcommon.h |  3 +++
 4 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index 169fc58427d3..bcb830ec4bb4 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -84,6 +84,8 @@ extern void __exit bcma_host_pci_exit(void);
 /* driver_pci.c */
 u32 bcma_pcie_read(struct bcma_drv_pci *pc, u32 address);
 
+extern int bcma_chipco_watchdog_register(struct bcma_drv_cc *cc);
+
 #ifdef CONFIG_BCMA_DRIVER_PCI_HOSTMODE
 bool __devinit bcma_core_pci_is_in_hostmode(struct bcma_drv_pci *pc);
 void __devinit bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc);
diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c
index 117222697e1f..d017f2512275 100644
--- a/drivers/bcma/driver_chipcommon.c
+++ b/drivers/bcma/driver_chipcommon.c
@@ -12,6 +12,7 @@
 #include "bcma_private.h"
 #include <linux/bcm47xx_wdt.h>
 #include <linux/export.h>
+#include <linux/platform_device.h>
 #include <linux/bcma/bcma.h>
 
 static inline u32 bcma_cc_write32_masked(struct bcma_drv_cc *cc, u16 offset,
@@ -87,6 +88,27 @@ static int bcma_chipco_watchdog_ticks_per_ms(struct bcma_drv_cc *cc)
 	}
 }
 
+int bcma_chipco_watchdog_register(struct bcma_drv_cc *cc)
+{
+	struct bcm47xx_wdt wdt = {};
+	struct platform_device *pdev;
+
+	wdt.driver_data = cc;
+	wdt.timer_set = bcma_chipco_watchdog_timer_set_wdt;
+	wdt.timer_set_ms = bcma_chipco_watchdog_timer_set_ms_wdt;
+	wdt.max_timer_ms = bcma_chipco_watchdog_get_max_timer(cc) / cc->ticks_per_ms;
+
+	pdev = platform_device_register_data(NULL, "bcm47xx-wdt",
+					     cc->core->bus->num, &wdt,
+					     sizeof(wdt));
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	cc->watchdog = pdev;
+
+	return 0;
+}
+
 void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc)
 {
 	if (cc->early_setup_done)
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index a9718893000b..debd4f142f93 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -165,6 +165,12 @@ static int bcma_register_cores(struct bcma_bus *bus)
 	}
 #endif
 
+	if (bus->hosttype == BCMA_HOSTTYPE_SOC) {
+		err = bcma_chipco_watchdog_register(&bus->drv_cc);
+		if (err)
+			bcma_err(bus, "Error registering watchdog driver\n");
+	}
+
 	return 0;
 }
 
@@ -177,6 +183,8 @@ static void bcma_unregister_cores(struct bcma_bus *bus)
 		if (core->dev_registered)
 			device_unregister(&core->dev);
 	}
+	if (bus->hosttype == BCMA_HOSTTYPE_SOC)
+		platform_device_unregister(bus->drv_cc.watchdog);
 }
 
 int __devinit bcma_bus_register(struct bcma_bus *bus)
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index 2f9b01493a90..e51359180b6f 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -1,6 +1,8 @@
 #ifndef LINUX_BCMA_DRIVER_CC_H_
 #define LINUX_BCMA_DRIVER_CC_H_
 
+#include <linux/platform_device.h>
+
 /** ChipCommon core registers. **/
 #define BCMA_CC_ID			0x0000
 #define  BCMA_CC_ID_ID			0x0000FFFF
@@ -571,6 +573,7 @@ struct bcma_drv_cc {
 	struct bcma_serial_port serial_ports[4];
 #endif /* CONFIG_BCMA_DRIVER_MIPS */
 	u32 ticks_per_ms;
+	struct platform_device *watchdog;
 };
 
 /* Register access */
-- 
cgit v1.2.3-55-g7522


From 7ffbffe37de3979d43c1105e38eb2918bf5d35fe Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Wed, 5 Dec 2012 18:46:05 +0100
Subject: ssb: add methods for watchdog driver

The watchdog driver wants to set the watchdog timeout in ms and not in
ticks, which is depending on the SoC type and the clock.
Calculate the number of ticks per millisecond and provide two functions
for the watchdog driver. Also return the ticks or millisecond the timer
was set to in case the provided value was bigger than the max allowed
value.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/ssb/driver_chipcommon.c           | 47 ++++++++++++++++++++++++++++++-
 drivers/ssb/ssb_private.h                 |  5 ++++
 include/linux/ssb/ssb_driver_chipcommon.h |  5 ++--
 3 files changed, 54 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/ssb/driver_chipcommon.c b/drivers/ssb/driver_chipcommon.c
index 6e080f6a07a5..95c33a05f434 100644
--- a/drivers/ssb/driver_chipcommon.c
+++ b/drivers/ssb/driver_chipcommon.c
@@ -4,6 +4,7 @@
  *
  * Copyright 2005, Broadcom Corporation
  * Copyright 2006, 2007, Michael Buesch <m@bues.ch>
+ * Copyright 2012, Hauke Mehrtens <hauke@hauke-m.de>
  *
  * Licensed under the GNU/GPL. See COPYING for details.
  */
@@ -12,6 +13,7 @@
 #include <linux/ssb/ssb_regs.h>
 #include <linux/export.h>
 #include <linux/pci.h>
+#include <linux/bcm47xx_wdt.h>
 
 #include "ssb_private.h"
 
@@ -306,6 +308,43 @@ static u32 ssb_chipco_watchdog_get_max_timer(struct ssb_chipcommon *cc)
 		return (1 << nb) - 1;
 }
 
+u32 ssb_chipco_watchdog_timer_set_wdt(struct bcm47xx_wdt *wdt, u32 ticks)
+{
+	struct ssb_chipcommon *cc = bcm47xx_wdt_get_drvdata(wdt);
+
+	if (cc->dev->bus->bustype != SSB_BUSTYPE_SSB)
+		return 0;
+
+	return ssb_chipco_watchdog_timer_set(cc, ticks);
+}
+
+u32 ssb_chipco_watchdog_timer_set_ms(struct bcm47xx_wdt *wdt, u32 ms)
+{
+	struct ssb_chipcommon *cc = bcm47xx_wdt_get_drvdata(wdt);
+	u32 ticks;
+
+	if (cc->dev->bus->bustype != SSB_BUSTYPE_SSB)
+		return 0;
+
+	ticks = ssb_chipco_watchdog_timer_set(cc, cc->ticks_per_ms * ms);
+	return ticks / cc->ticks_per_ms;
+}
+
+static int ssb_chipco_watchdog_ticks_per_ms(struct ssb_chipcommon *cc)
+{
+	struct ssb_bus *bus = cc->dev->bus;
+
+	if (cc->capabilities & SSB_CHIPCO_CAP_PMU) {
+			/* based on 32KHz ILP clock */
+			return 32;
+	} else {
+		if (cc->dev->id.revision < 18)
+			return ssb_clockspeed(bus) / 1000;
+		else
+			return ssb_chipco_alp_clock(cc) / 1000;
+	}
+}
+
 void ssb_chipcommon_init(struct ssb_chipcommon *cc)
 {
 	if (!cc->dev)
@@ -323,6 +362,11 @@ void ssb_chipcommon_init(struct ssb_chipcommon *cc)
 	chipco_powercontrol_init(cc);
 	ssb_chipco_set_clockmode(cc, SSB_CLKMODE_FAST);
 	calc_fast_powerup_delay(cc);
+
+	if (cc->dev->bus->bustype == SSB_BUSTYPE_SSB) {
+		cc->ticks_per_ms = ssb_chipco_watchdog_ticks_per_ms(cc);
+		cc->max_timer_ms = ssb_chipco_watchdog_get_max_timer(cc) / cc->ticks_per_ms;
+	}
 }
 
 void ssb_chipco_suspend(struct ssb_chipcommon *cc)
@@ -421,7 +465,7 @@ void ssb_chipco_timing_init(struct ssb_chipcommon *cc,
 }
 
 /* Set chip watchdog reset timer to fire in 'ticks' backplane cycles */
-void ssb_chipco_watchdog_timer_set(struct ssb_chipcommon *cc, u32 ticks)
+u32 ssb_chipco_watchdog_timer_set(struct ssb_chipcommon *cc, u32 ticks)
 {
 	u32 maxt;
 	enum ssb_clkmode clkmode;
@@ -441,6 +485,7 @@ void ssb_chipco_watchdog_timer_set(struct ssb_chipcommon *cc, u32 ticks)
 		/* instant NMI */
 		chipco_write32(cc, SSB_CHIPCO_WATCHDOG, ticks);
 	}
+	return ticks;
 }
 
 void ssb_chipco_irq_mask(struct ssb_chipcommon *cc, u32 mask, u32 value)
diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h
index 98b2915cd30b..03cc40a71510 100644
--- a/drivers/ssb/ssb_private.h
+++ b/drivers/ssb/ssb_private.h
@@ -3,6 +3,7 @@
 
 #include <linux/ssb/ssb.h>
 #include <linux/types.h>
+#include <linux/bcm47xx_wdt.h>
 
 
 #define PFX	"ssb: "
@@ -212,4 +213,8 @@ extern u32 ssb_pmu_get_cpu_clock(struct ssb_chipcommon *cc);
 extern u32 ssb_pmu_get_controlclock(struct ssb_chipcommon *cc);
 extern u32 ssb_pmu_get_alp_clock(struct ssb_chipcommon *cc);
 
+extern u32 ssb_chipco_watchdog_timer_set_wdt(struct bcm47xx_wdt *wdt,
+					     u32 ticks);
+extern u32 ssb_chipco_watchdog_timer_set_ms(struct bcm47xx_wdt *wdt, u32 ms);
+
 #endif /* LINUX_SSB_PRIVATE_H_ */
diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h
index c2b02a5c86ae..38339fd68a5f 100644
--- a/include/linux/ssb/ssb_driver_chipcommon.h
+++ b/include/linux/ssb/ssb_driver_chipcommon.h
@@ -591,6 +591,8 @@ struct ssb_chipcommon {
 	/* Fast Powerup Delay constant */
 	u16 fast_pwrup_delay;
 	struct ssb_chipcommon_pmu pmu;
+	u32 ticks_per_ms;
+	u32 max_timer_ms;
 };
 
 static inline bool ssb_chipco_available(struct ssb_chipcommon *cc)
@@ -630,8 +632,7 @@ enum ssb_clkmode {
 extern void ssb_chipco_set_clockmode(struct ssb_chipcommon *cc,
 				     enum ssb_clkmode mode);
 
-extern void ssb_chipco_watchdog_timer_set(struct ssb_chipcommon *cc,
-					  u32 ticks);
+extern u32 ssb_chipco_watchdog_timer_set(struct ssb_chipcommon *cc, u32 ticks);
 
 void ssb_chipco_irq_mask(struct ssb_chipcommon *cc, u32 mask, u32 value);
 
-- 
cgit v1.2.3-55-g7522


From 7280b51a29f8e6cc7d449d565182d1e1b6183907 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Wed, 5 Dec 2012 18:46:06 +0100
Subject: ssb: extif: add check for max value before setting watchdog register

Prevent the watchdog register on the extif core to be set to a too
high value.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/ssb/driver_extif.c           | 5 +++--
 include/linux/ssb/ssb_driver_extif.h | 1 +
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/ssb/driver_extif.c b/drivers/ssb/driver_extif.c
index dc47f30e9cf7..0aa4c2a85774 100644
--- a/drivers/ssb/driver_extif.c
+++ b/drivers/ssb/driver_extif.c
@@ -112,9 +112,10 @@ void ssb_extif_get_clockcontrol(struct ssb_extif *extif,
 	*m = extif_read32(extif, SSB_EXTIF_CLOCK_SB);
 }
 
-void ssb_extif_watchdog_timer_set(struct ssb_extif *extif,
-				  u32 ticks)
+void ssb_extif_watchdog_timer_set(struct ssb_extif *extif, u32 ticks)
 {
+	if (ticks > SSB_EXTIF_WATCHDOG_MAX_TIMER)
+		ticks = SSB_EXTIF_WATCHDOG_MAX_TIMER;
 	extif_write32(extif, SSB_EXTIF_WATCHDOG, ticks);
 }
 
diff --git a/include/linux/ssb/ssb_driver_extif.h b/include/linux/ssb/ssb_driver_extif.h
index 2604efa7dc4d..b618188939d2 100644
--- a/include/linux/ssb/ssb_driver_extif.h
+++ b/include/linux/ssb/ssb_driver_extif.h
@@ -152,6 +152,7 @@
 /* watchdog */
 #define SSB_EXTIF_WATCHDOG_CLK		48000000	/* Hz */
 
+#define SSB_EXTIF_WATCHDOG_MAX_TIMER	((1 << 28) - 1)
 
 
 #ifdef CONFIG_SSB_DRIVER_EXTIF
-- 
cgit v1.2.3-55-g7522


From 9f640a6376e54fa9ae834c32cbe92cefeec970dc Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Wed, 5 Dec 2012 18:46:07 +0100
Subject: ssb: extif: add methods for watchdog driver

The watchdog driver wants to set the watchdog timeout in ms and not in
ticks, add a method converting ms to ticks before setting the watchdog
register. Return the ticks or millisecond the timer was set to in case
the provided value was bigger than the max allowed value.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/ssb/driver_extif.c           | 21 ++++++++++++++++++++-
 drivers/ssb/ssb_private.h            | 15 +++++++++++++++
 include/linux/ssb/ssb_driver_extif.h |  9 +++++----
 3 files changed, 40 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/ssb/driver_extif.c b/drivers/ssb/driver_extif.c
index 0aa4c2a85774..553227a3062d 100644
--- a/drivers/ssb/driver_extif.c
+++ b/drivers/ssb/driver_extif.c
@@ -112,11 +112,30 @@ void ssb_extif_get_clockcontrol(struct ssb_extif *extif,
 	*m = extif_read32(extif, SSB_EXTIF_CLOCK_SB);
 }
 
-void ssb_extif_watchdog_timer_set(struct ssb_extif *extif, u32 ticks)
+u32 ssb_extif_watchdog_timer_set_wdt(struct bcm47xx_wdt *wdt, u32 ticks)
+{
+	struct ssb_extif *extif = bcm47xx_wdt_get_drvdata(wdt);
+
+	return ssb_extif_watchdog_timer_set(extif, ticks);
+}
+
+u32 ssb_extif_watchdog_timer_set_ms(struct bcm47xx_wdt *wdt, u32 ms)
+{
+	struct ssb_extif *extif = bcm47xx_wdt_get_drvdata(wdt);
+	u32 ticks = (SSB_EXTIF_WATCHDOG_CLK / 1000) * ms;
+
+	ticks = ssb_extif_watchdog_timer_set(extif, ticks);
+
+	return (ticks * 1000) / SSB_EXTIF_WATCHDOG_CLK;
+}
+
+u32 ssb_extif_watchdog_timer_set(struct ssb_extif *extif, u32 ticks)
 {
 	if (ticks > SSB_EXTIF_WATCHDOG_MAX_TIMER)
 		ticks = SSB_EXTIF_WATCHDOG_MAX_TIMER;
 	extif_write32(extif, SSB_EXTIF_WATCHDOG, ticks);
+
+	return ticks;
 }
 
 u32 ssb_extif_gpio_in(struct ssb_extif *extif, u32 mask)
diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h
index 03cc40a71510..50ea02877777 100644
--- a/drivers/ssb/ssb_private.h
+++ b/drivers/ssb/ssb_private.h
@@ -217,4 +217,19 @@ extern u32 ssb_chipco_watchdog_timer_set_wdt(struct bcm47xx_wdt *wdt,
 					     u32 ticks);
 extern u32 ssb_chipco_watchdog_timer_set_ms(struct bcm47xx_wdt *wdt, u32 ms);
 
+#ifdef CONFIG_SSB_DRIVER_EXTIF
+extern u32 ssb_extif_watchdog_timer_set_wdt(struct bcm47xx_wdt *wdt, u32 ticks);
+extern u32 ssb_extif_watchdog_timer_set_ms(struct bcm47xx_wdt *wdt, u32 ms);
+#else
+static inline u32 ssb_extif_watchdog_timer_set_wdt(struct bcm47xx_wdt *wdt,
+						   u32 ticks)
+{
+	return 0;
+}
+static inline u32 ssb_extif_watchdog_timer_set_ms(struct bcm47xx_wdt *wdt,
+						  u32 ms)
+{
+	return 0;
+}
+#endif
 #endif /* LINUX_SSB_PRIVATE_H_ */
diff --git a/include/linux/ssb/ssb_driver_extif.h b/include/linux/ssb/ssb_driver_extif.h
index b618188939d2..99511d0e931d 100644
--- a/include/linux/ssb/ssb_driver_extif.h
+++ b/include/linux/ssb/ssb_driver_extif.h
@@ -153,6 +153,8 @@
 #define SSB_EXTIF_WATCHDOG_CLK		48000000	/* Hz */
 
 #define SSB_EXTIF_WATCHDOG_MAX_TIMER	((1 << 28) - 1)
+#define SSB_EXTIF_WATCHDOG_MAX_TIMER_MS	(SSB_EXTIF_WATCHDOG_MAX_TIMER \
+					 / (SSB_EXTIF_WATCHDOG_CLK / 1000))
 
 
 #ifdef CONFIG_SSB_DRIVER_EXTIF
@@ -172,8 +174,7 @@ extern void ssb_extif_get_clockcontrol(struct ssb_extif *extif,
 extern void ssb_extif_timing_init(struct ssb_extif *extif,
 				  unsigned long ns);
 
-extern void ssb_extif_watchdog_timer_set(struct ssb_extif *extif,
-					 u32 ticks);
+extern u32 ssb_extif_watchdog_timer_set(struct ssb_extif *extif, u32 ticks);
 
 /* Extif GPIO pin access */
 u32 ssb_extif_gpio_in(struct ssb_extif *extif, u32 mask);
@@ -211,9 +212,9 @@ void ssb_extif_timing_init(struct ssb_extif *extif, unsigned long ns)
 }
 
 static inline
-void ssb_extif_watchdog_timer_set(struct ssb_extif *extif,
-				  u32 ticks)
+u32 ssb_extif_watchdog_timer_set(struct ssb_extif *extif, u32 ticks)
 {
+	return 0;
 }
 
 static inline u32 ssb_extif_gpio_in(struct ssb_extif *extif, u32 mask)
-- 
cgit v1.2.3-55-g7522


From bde327eff8a722df1198df9b14464f84f1adfb65 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens
Date: Wed, 5 Dec 2012 18:46:08 +0100
Subject: ssb: register watchdog driver

Register the watchdog driver to the system if it is a SoC. Using the
watchdog on a non SoC device, like a PCI card, will make the PCI
card die when the timeout expired, but starting it again is not
supported by ssb.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/ssb/embedded.c    | 35 +++++++++++++++++++++++++++++++++++
 drivers/ssb/main.c        |  8 ++++++++
 drivers/ssb/ssb_private.h | 10 ++++++++++
 include/linux/ssb/ssb.h   |  2 ++
 4 files changed, 55 insertions(+)

(limited to 'include')

diff --git a/drivers/ssb/embedded.c b/drivers/ssb/embedded.c
index 9ef124f9ee2d..bb18d76f9f2c 100644
--- a/drivers/ssb/embedded.c
+++ b/drivers/ssb/embedded.c
@@ -4,11 +4,13 @@
  *
  * Copyright 2005-2008, Broadcom Corporation
  * Copyright 2006-2008, Michael Buesch <m@bues.ch>
+ * Copyright 2012, Hauke Mehrtens <hauke@hauke-m.de>
  *
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
 #include <linux/export.h>
+#include <linux/platform_device.h>
 #include <linux/ssb/ssb.h>
 #include <linux/ssb/ssb_embedded.h>
 #include <linux/ssb/ssb_driver_pci.h>
@@ -32,6 +34,39 @@ int ssb_watchdog_timer_set(struct ssb_bus *bus, u32 ticks)
 }
 EXPORT_SYMBOL(ssb_watchdog_timer_set);
 
+int ssb_watchdog_register(struct ssb_bus *bus)
+{
+	struct bcm47xx_wdt wdt = {};
+	struct platform_device *pdev;
+
+	if (ssb_chipco_available(&bus->chipco)) {
+		wdt.driver_data = &bus->chipco;
+		wdt.timer_set = ssb_chipco_watchdog_timer_set_wdt;
+		wdt.timer_set_ms = ssb_chipco_watchdog_timer_set_ms;
+		wdt.max_timer_ms = bus->chipco.max_timer_ms;
+	} else if (ssb_extif_available(&bus->extif)) {
+		wdt.driver_data = &bus->extif;
+		wdt.timer_set = ssb_extif_watchdog_timer_set_wdt;
+		wdt.timer_set_ms = ssb_extif_watchdog_timer_set_ms;
+		wdt.max_timer_ms = SSB_EXTIF_WATCHDOG_MAX_TIMER_MS;
+	} else {
+		return -ENODEV;
+	}
+
+	pdev = platform_device_register_data(NULL, "bcm47xx-wdt",
+					     bus->busnumber, &wdt,
+					     sizeof(wdt));
+	if (IS_ERR(pdev)) {
+		ssb_dprintk(KERN_INFO PFX
+			    "can not register watchdog device, err: %li\n",
+			    PTR_ERR(pdev));
+		return PTR_ERR(pdev);
+	}
+
+	bus->watchdog = pdev;
+	return 0;
+}
+
 u32 ssb_gpio_in(struct ssb_bus *bus, u32 mask)
 {
 	unsigned long flags;
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index df0f145c22fc..58c7da29a37c 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -13,6 +13,7 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/platform_device.h>
 #include <linux/ssb/ssb.h>
 #include <linux/ssb/ssb_regs.h>
 #include <linux/ssb/ssb_driver_gige.h>
@@ -433,6 +434,11 @@ static void ssb_devices_unregister(struct ssb_bus *bus)
 		if (sdev->dev)
 			device_unregister(sdev->dev);
 	}
+
+#ifdef CONFIG_SSB_EMBEDDED
+	if (bus->bustype == SSB_BUSTYPE_SSB)
+		platform_device_unregister(bus->watchdog);
+#endif
 }
 
 void ssb_bus_unregister(struct ssb_bus *bus)
@@ -561,6 +567,8 @@ static int __devinit ssb_attach_queued_buses(void)
 		if (err)
 			goto error;
 		ssb_pcicore_init(&bus->pcicore);
+		if (bus->bustype == SSB_BUSTYPE_SSB)
+			ssb_watchdog_register(bus);
 		ssb_bus_may_powerdown(bus);
 
 		err = ssb_devices_register(bus);
diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h
index 50ea02877777..8942db1d855a 100644
--- a/drivers/ssb/ssb_private.h
+++ b/drivers/ssb/ssb_private.h
@@ -232,4 +232,14 @@ static inline u32 ssb_extif_watchdog_timer_set_ms(struct bcm47xx_wdt *wdt,
 	return 0;
 }
 #endif
+
+#ifdef CONFIG_SSB_EMBEDDED
+extern int ssb_watchdog_register(struct ssb_bus *bus);
+#else /* CONFIG_SSB_EMBEDDED */
+static inline int ssb_watchdog_register(struct ssb_bus *bus)
+{
+	return 0;
+}
+#endif /* CONFIG_SSB_EMBEDDED */
+
 #endif /* LINUX_SSB_PRIVATE_H_ */
diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h
index bb674c02f306..1f64e3f1f22b 100644
--- a/include/linux/ssb/ssb.h
+++ b/include/linux/ssb/ssb.h
@@ -8,6 +8,7 @@
 #include <linux/pci.h>
 #include <linux/mod_devicetable.h>
 #include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
 
 #include <linux/ssb/ssb_regs.h>
 
@@ -432,6 +433,7 @@ struct ssb_bus {
 #ifdef CONFIG_SSB_EMBEDDED
 	/* Lock for GPIO register access. */
 	spinlock_t gpio_lock;
+	struct platform_device *watchdog;
 #endif /* EMBEDDED */
 
 	/* Internal-only stuff follows. Do not touch. */
-- 
cgit v1.2.3-55-g7522


From eb044c48446f676ae5c38b30a2e2165742a52f4a Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi
Date: Thu, 6 Dec 2012 15:35:25 +0100
Subject: ASoC: omap-twl4030: Update the header file to support more boards

The common machine driver will be able to support new boards where the voice
port is also in use.
At the same time add possibility to fine tune the connections from twl4030
on the board: jack detection GPIO, input/output selection

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/linux/platform_data/omap-twl4030.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/linux/platform_data/omap-twl4030.h b/include/linux/platform_data/omap-twl4030.h
index c7bef788daab..ee60ef79d792 100644
--- a/include/linux/platform_data/omap-twl4030.h
+++ b/include/linux/platform_data/omap-twl4030.h
@@ -25,8 +25,34 @@
 #ifndef _OMAP_TWL4030_H_
 #define _OMAP_TWL4030_H_
 
+/* To select if only one channel is connected in a stereo port */
+#define OMAP_TWL4030_LEFT	(1 << 0)
+#define OMAP_TWL4030_RIGHT	(1 << 1)
+
 struct omap_tw4030_pdata {
 	const char *card_name;
+	/* Voice port is connected to McBSP3 */
+	bool voice_connected;
+
+	/* The driver will parse the connection flags if this flag is set */
+	bool	custom_routing;
+	/* Flags to indicate connected audio ports. */
+	u8	has_hs;
+	u8	has_hf;
+	u8	has_predriv;
+	u8	has_carkit;
+	bool	has_ear;
+
+	bool	has_mainmic;
+	bool	has_submic;
+	bool	has_hsmic;
+	bool	has_carkitmic;
+	bool	has_digimic0;
+	bool	has_digimic1;
+	u8	has_linein;
+
+	/* Jack detect GPIO or  <= 0 if it is not implemented */
+	int jack_detect;
 };
 
 #endif /* _OMAP_TWL4030_H_ */
-- 
cgit v1.2.3-55-g7522


From d0c6c482f6d8c2145717ab0266c87e3e792527ef Mon Sep 17 00:00:00 2001
From: Daniel Mack
Date: Wed, 5 Dec 2012 18:20:36 +0100
Subject: ASoC: McASP: remove unused variables

codec_fmt and sample_rate variables are unused in both snd_platform_data
and davinci_audio_dev, so drop them.

Signed-off-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/linux/platform_data/davinci_asp.h | 1 -
 sound/soc/davinci/davinci-mcasp.c         | 1 -
 sound/soc/davinci/davinci-mcasp.h         | 2 --
 3 files changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h
index f3d6e4f20962..8db5ae03b6e3 100644
--- a/include/linux/platform_data/davinci_asp.h
+++ b/include/linux/platform_data/davinci_asp.h
@@ -23,7 +23,6 @@ struct snd_platform_data {
 	u32 rx_dma_offset;
 	int asp_chan_q;	/* event queue number for ASP channel */
 	int ram_chan_q;	/* event queue number for RAM channel */
-	unsigned int codec_fmt;
 	/*
 	 * Allowing this is more efficient and eliminates left and right swaps
 	 * caused by underruns, but will swap the left and right channels
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 571559501b0b..7c248371f7ec 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -1158,7 +1158,6 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 	dev->tdm_slots = pdata->tdm_slots;
 	dev->num_serializer = pdata->num_serializer;
 	dev->serial_dir = pdata->serial_dir;
-	dev->codec_fmt = pdata->codec_fmt;
 	dev->version = pdata->version;
 	dev->txnumevt = pdata->txnumevt;
 	dev->rxnumevt = pdata->rxnumevt;
diff --git a/sound/soc/davinci/davinci-mcasp.h b/sound/soc/davinci/davinci-mcasp.h
index 156f15f55744..a42b5d96739f 100644
--- a/sound/soc/davinci/davinci-mcasp.h
+++ b/sound/soc/davinci/davinci-mcasp.h
@@ -40,9 +40,7 @@ enum {
 struct davinci_audio_dev {
 	struct davinci_pcm_dma_params dma_params[2];
 	void __iomem *base;
-	int sample_rate;
 	struct device *dev;
-	unsigned int codec_fmt;
 
 	/* McASP specific data */
 	int	tdm_slots;
-- 
cgit v1.2.3-55-g7522


From 805f864ebefc39065b6b0cf2548f13c2fbf888d9 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto
Date: Thu, 6 Dec 2012 01:10:28 -0800
Subject: gpio: pcf857x: use client->irq for gpio_to_irq()

6e20a0a429bd4dc07d6de16d9c247270e04e4aa0
(gpio: pcf857x: enable gpio_to_irq() support)
added gpio_to_irq() support on pcf857x driver,
but it used pdata->irq.
This patch modifies driver to use client->irq instead of it.
It modifies kzm9g board platform settings,
and device probe information too.
This patch is tested on kzm9g board

Reported-by: Christian Engelmayer <christian.engelmayer@frequentis.com>
Acked-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/arm/mach-shmobile/board-kzm9g.c |  2 +-
 drivers/gpio/gpio-pcf857x.c          | 29 +++++++++++------------------
 include/linux/i2c/pcf857x.h          |  3 ---
 3 files changed, 12 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c
index 0a43f3189c21..7a05de794a8c 100644
--- a/arch/arm/mach-shmobile/board-kzm9g.c
+++ b/arch/arm/mach-shmobile/board-kzm9g.c
@@ -548,7 +548,6 @@ static struct platform_device fsi_ak4648_device = {
 /* I2C */
 static struct pcf857x_platform_data pcf8575_pdata = {
 	.gpio_base	= GPIO_PCF8575_BASE,
-	.irq		= intcs_evt2irq(0x3260), /* IRQ19 */
 };
 
 static struct i2c_board_info i2c0_devices[] = {
@@ -570,6 +569,7 @@ static struct i2c_board_info i2c1_devices[] = {
 static struct i2c_board_info i2c3_devices[] = {
 	{
 		I2C_BOARD_INFO("pcf8575", 0x20),
+		.irq		= intcs_evt2irq(0x3260), /* IRQ19 */
 		.platform_data = &pcf8575_pdata,
 	},
 };
diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c
index 16af35cd2b10..a19b7457a726 100644
--- a/drivers/gpio/gpio-pcf857x.c
+++ b/drivers/gpio/gpio-pcf857x.c
@@ -223,11 +223,11 @@ static void pcf857x_irq_domain_cleanup(struct pcf857x *gpio)
 
 static int pcf857x_irq_domain_init(struct pcf857x *gpio,
 				   struct pcf857x_platform_data *pdata,
-				   struct device *dev)
+				   struct i2c_client *client)
 {
 	int status;
 
-	gpio->irq_domain = irq_domain_add_linear(dev->of_node,
+	gpio->irq_domain = irq_domain_add_linear(client->dev.of_node,
 						 gpio->chip.ngpio,
 						 &pcf857x_irq_domain_ops,
 						 NULL);
@@ -235,15 +235,15 @@ static int pcf857x_irq_domain_init(struct pcf857x *gpio,
 		goto fail;
 
 	/* enable real irq */
-	status = request_irq(pdata->irq, pcf857x_irq_demux, 0,
-			     dev_name(dev), gpio);
+	status = request_irq(client->irq, pcf857x_irq_demux, 0,
+			     dev_name(&client->dev), gpio);
 	if (status)
 		goto fail;
 
 	/* enable gpio_to_irq() */
 	INIT_WORK(&gpio->work, pcf857x_irq_demux_work);
 	gpio->chip.to_irq	= pcf857x_to_irq;
-	gpio->irq		= pdata->irq;
+	gpio->irq		= client->irq;
 
 	return 0;
 
@@ -285,8 +285,8 @@ static int pcf857x_probe(struct i2c_client *client,
 	gpio->chip.ngpio		= id->driver_data;
 
 	/* enable gpio_to_irq() if platform has settings */
-	if (pdata && pdata->irq) {
-		status = pcf857x_irq_domain_init(gpio, pdata, &client->dev);
+	if (pdata && client->irq) {
+		status = pcf857x_irq_domain_init(gpio, pdata, client);
 		if (status < 0) {
 			dev_err(&client->dev, "irq_domain init failed\n");
 			goto fail;
@@ -368,15 +368,6 @@ static int pcf857x_probe(struct i2c_client *client,
 	if (status < 0)
 		goto fail;
 
-	/* NOTE: these chips can issue "some pin-changed" IRQs, which we
-	 * don't yet even try to use.  Among other issues, the relevant
-	 * genirq state isn't available to modular drivers; and most irq
-	 * methods can't be called from sleeping contexts.
-	 */
-
-	dev_info(&client->dev, "%s\n",
-			client->irq ? " (irq ignored)" : "");
-
 	/* Let platform code set up the GPIOs and their users.
 	 * Now is the first time anyone could use them.
 	 */
@@ -388,13 +379,15 @@ static int pcf857x_probe(struct i2c_client *client,
 			dev_warn(&client->dev, "setup --> %d\n", status);
 	}
 
+	dev_info(&client->dev, "probed\n");
+
 	return 0;
 
 fail:
 	dev_dbg(&client->dev, "probe error %d for '%s'\n",
 			status, client->name);
 
-	if (pdata && pdata->irq)
+	if (pdata && client->irq)
 		pcf857x_irq_domain_cleanup(gpio);
 
 	kfree(gpio);
@@ -418,7 +411,7 @@ static int pcf857x_remove(struct i2c_client *client)
 		}
 	}
 
-	if (pdata && pdata->irq)
+	if (pdata && client->irq)
 		pcf857x_irq_domain_cleanup(gpio);
 
 	status = gpiochip_remove(&gpio->chip);
diff --git a/include/linux/i2c/pcf857x.h b/include/linux/i2c/pcf857x.h
index 781e6bd06c34..0767a2a6b2f1 100644
--- a/include/linux/i2c/pcf857x.h
+++ b/include/linux/i2c/pcf857x.h
@@ -10,7 +10,6 @@
  * @setup: optional callback issued once the GPIOs are valid
  * @teardown: optional callback issued before the GPIOs are invalidated
  * @context: optional parameter passed to setup() and teardown()
- * @irq: optional interrupt number
  *
  * In addition to the I2C_BOARD_INFO() state appropriate to each chip,
  * the i2c_board_info used with the pcf875x driver must provide its
@@ -40,8 +39,6 @@ struct pcf857x_platform_data {
 					int gpio, unsigned ngpio,
 					void *context);
 	void		*context;
-
-	int		irq;
 };
 
 #endif /* __LINUX_PCF857X_H */
-- 
cgit v1.2.3-55-g7522


From 4529eefad087f97b33c0f31984d924b1f15d7bae Mon Sep 17 00:00:00 2001
From: Lamarque V. Souza
Date: Thu, 6 Dec 2012 12:39:55 -0200
Subject: HID: hidp: fallback to input session properly if hid is blacklisted

This patch against kernel 3.7.0-rc8 fixes a kernel oops when turning on the
bluetooth mouse with id 0458:0058 [1].

The mouse in question supports both input and hid sessions, however it is
blacklisted in drivers/hid/hid-core.c so the input session is one that should
be used. Long ago (around kernel 3.0.0) some changes in the bluetooth
subsystem made the kernel do not fallback to input session when hid session is
not supported or blacklisted. This patch restore that behaviour by making the
kernel try the input session if hid_add_device returns ENODEV.

The patch exports hid_ignore() from hid-core.c so that it can be used in the
bluetooth subsystem.

[1] https://bugzilla.kernel.org/show_bug.cgi?id=39882

Signed-off-by: Lamarque V. Souza <lamarque@gmail.com>
Acked-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-core.c    | 11 ++++++++---
 include/linux/hid.h       |  1 +
 net/bluetooth/hidp/core.c |  9 ++++++++-
 3 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index a7550bb30836..2629d5240d63 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2145,8 +2145,13 @@ static const struct hid_device_id hid_mouse_ignore_list[] = {
 	{ }
 };
 
-static bool hid_ignore(struct hid_device *hdev)
+bool hid_ignore(struct hid_device *hdev)
 {
+	if (hdev->quirks & HID_QUIRK_NO_IGNORE)
+		return false;
+	if (hdev->quirks & HID_QUIRK_IGNORE)
+		return true;
+
 	switch (hdev->vendor) {
 	case USB_VENDOR_ID_CODEMERCS:
 		/* ignore all Code Mercenaries IOWarrior devices */
@@ -2201,6 +2206,7 @@ static bool hid_ignore(struct hid_device *hdev)
 
 	return !!hid_match_id(hdev, hid_ignore_list);
 }
+EXPORT_SYMBOL_GPL(hid_ignore);
 
 int hid_add_device(struct hid_device *hdev)
 {
@@ -2212,8 +2218,7 @@ int hid_add_device(struct hid_device *hdev)
 
 	/* we need to kill them here, otherwise they will stay allocated to
 	 * wait for coming driver */
-	if (!(hdev->quirks & HID_QUIRK_NO_IGNORE)
-            && (hid_ignore(hdev) || (hdev->quirks & HID_QUIRK_IGNORE)))
+	if (hid_ignore(hdev))
 		return -ENODEV;
 
 	/*
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 7e1f37db7582..abce7eb4f258 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -721,6 +721,7 @@ struct hid_ll_driver {
 
 extern int hid_debug;
 
+extern bool hid_ignore(struct hid_device *);
 extern int hid_add_device(struct hid_device *);
 extern void hid_destroy_device(struct hid_device *);
 
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index ccd985da6518..1f4a32bb2971 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -941,6 +941,13 @@ static int hidp_setup_hid(struct hidp_session *session,
 	hid->hid_get_raw_report = hidp_get_raw_report;
 	hid->hid_output_raw_report = hidp_output_raw_report;
 
+	/* True if device is blacklisted in drivers/hid/hid-core.c */
+	if (hid_ignore(hid)) {
+		hid_destroy_device(session->hid);
+		session->hid = NULL;
+		return -ENODEV;
+	}
+
 	return 0;
 
 fault:
@@ -1013,7 +1020,7 @@ int hidp_add_connection(struct hidp_connadd_req *req, struct socket *ctrl_sock,
 
 	if (req->rd_size > 0) {
 		err = hidp_setup_hid(session, req);
-		if (err)
+		if (err && err != -ENODEV)
 			goto purge;
 	}
 
-- 
cgit v1.2.3-55-g7522


From 8dd2491a4216778a81668581041ba1c06453ed6c Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Wed, 10 Oct 2012 10:26:45 +0300
Subject: OMAPDSS: add omapdss_compat_init()

Add two new exported functions, omapdss_compat_init and
omapdss_compat_uninit, which are to be used by omapfb, omap_vout to
enable compatibility mode for omapdss. The functions are called by
omapdss internally for now, and moved to other drivers later.

The compatibility mode is implemented fully in the following patches.
For now, enabling compat mode only sets up the private data in apply.c.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/omap2/dss/apply.c | 33 ++++++++++++++++++++++++++++++++-
 drivers/video/omap2/dss/core.c  |  4 +++-
 drivers/video/omap2/dss/dss.h   |  1 -
 include/video/omapdss.h         |  3 +++
 4 files changed, 38 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/video/omap2/dss/apply.c b/drivers/video/omap2/dss/apply.c
index 4a5cc5c64d4b..ba1343274bb7 100644
--- a/drivers/video/omap2/dss/apply.c
+++ b/drivers/video/omap2/dss/apply.c
@@ -18,6 +18,7 @@
 #define DSS_SUBSYS_NAME "APPLY"
 
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/jiffies.h>
@@ -131,7 +132,7 @@ static struct mgr_priv_data *get_mgr_priv(struct omap_overlay_manager *mgr)
 	return &dss_data.mgr_priv_data_array[mgr->id];
 }
 
-void dss_apply_init(void)
+static void apply_init_priv(void)
 {
 	const int num_ovls = dss_feat_get_num_ovls();
 	struct mgr_priv_data *mp;
@@ -1463,3 +1464,33 @@ err:
 	return r;
 }
 
+static int compat_refcnt;
+static DEFINE_MUTEX(compat_init_lock);
+
+int omapdss_compat_init(void)
+{
+	mutex_lock(&compat_init_lock);
+
+	if (compat_refcnt++ > 0)
+		goto out;
+
+	apply_init_priv();
+
+out:
+	mutex_unlock(&compat_init_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(omapdss_compat_init);
+
+void omapdss_compat_uninit(void)
+{
+	mutex_lock(&compat_init_lock);
+
+	if (--compat_refcnt > 0)
+		goto out;
+
+out:
+	mutex_unlock(&compat_init_lock);
+}
+EXPORT_SYMBOL(omapdss_compat_uninit);
diff --git a/drivers/video/omap2/dss/core.c b/drivers/video/omap2/dss/core.c
index 5c5e59190586..86c743f5ed2e 100644
--- a/drivers/video/omap2/dss/core.c
+++ b/drivers/video/omap2/dss/core.c
@@ -232,7 +232,7 @@ static int __init omap_dss_probe(struct platform_device *pdev)
 
 	dss_features_init(omapdss_get_version());
 
-	dss_apply_init();
+	omapdss_compat_init();
 
 	dss_init_overlay_managers(pdev);
 	dss_init_overlays(pdev);
@@ -264,6 +264,8 @@ static int omap_dss_remove(struct platform_device *pdev)
 	dss_uninit_overlays(pdev);
 	dss_uninit_overlay_managers(pdev);
 
+	omapdss_compat_uninit();
+
 	return 0;
 }
 
diff --git a/drivers/video/omap2/dss/dss.h b/drivers/video/omap2/dss/dss.h
index bdf843135661..9da3d61b8a56 100644
--- a/drivers/video/omap2/dss/dss.h
+++ b/drivers/video/omap2/dss/dss.h
@@ -178,7 +178,6 @@ void dss_copy_device_pdata(struct omap_dss_device *dst,
 		const struct omap_dss_device *src);
 
 /* apply */
-void dss_apply_init(void);
 int dss_mgr_wait_for_go(struct omap_overlay_manager *mgr);
 int dss_mgr_wait_for_go_ovl(struct omap_overlay *ovl);
 void dss_mgr_start_update(struct omap_overlay_manager *mgr);
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index b1248c2d36e1..a9402362d817 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -836,4 +836,7 @@ void omapdss_rfbi_set_data_lines(struct omap_dss_device *dssdev,
 void omapdss_rfbi_set_interface_timings(struct omap_dss_device *dssdev,
 		struct rfbi_timings *timings);
 
+int omapdss_compat_init(void);
+void omapdss_compat_uninit(void);
+
 #endif
-- 
cgit v1.2.3-55-g7522


From 549acbe7a3380dd3bd2ac71698549148ecc0d17e Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Wed, 10 Oct 2012 14:03:11 +0300
Subject: OMAPDSS: move omap_dispc_wait_for_irq_interruptible_timeout to
 dispc-compat.c

We have two functions to wait for a dispc interrupt:

int omap_dispc_wait_for_irq_timeout(u32 irqmask, unsigned long timeout);
int omap_dispc_wait_for_irq_interruptible_timeout(u32 irqmask,

Of these, the former is not used at all, and can be removed. The latter
is only used by the compat layer, and can be moved to the compat layer
code.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/omap2/dss/dispc-compat.c | 30 ++++++++++++++++++
 drivers/video/omap2/dss/dispc-compat.h |  3 ++
 drivers/video/omap2/dss/dispc.c        | 57 ----------------------------------
 include/video/omapdss.h                |  4 ---
 4 files changed, 33 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/drivers/video/omap2/dss/dispc-compat.c b/drivers/video/omap2/dss/dispc-compat.c
index cca38488ab27..24e1d5e974eb 100644
--- a/drivers/video/omap2/dss/dispc-compat.c
+++ b/drivers/video/omap2/dss/dispc-compat.c
@@ -205,3 +205,33 @@ void dispc_mgr_disable_sync(enum omap_channel channel)
 		WARN_ON(1);
 }
 
+int omap_dispc_wait_for_irq_interruptible_timeout(u32 irqmask,
+		unsigned long timeout)
+{
+	void dispc_irq_wait_handler(void *data, u32 mask)
+	{
+		complete((struct completion *)data);
+	}
+
+	int r;
+	DECLARE_COMPLETION_ONSTACK(completion);
+
+	r = omap_dispc_register_isr(dispc_irq_wait_handler, &completion,
+			irqmask);
+
+	if (r)
+		return r;
+
+	timeout = wait_for_completion_interruptible_timeout(&completion,
+			timeout);
+
+	omap_dispc_unregister_isr(dispc_irq_wait_handler, &completion, irqmask);
+
+	if (timeout == 0)
+		return -ETIMEDOUT;
+
+	if (timeout == -ERESTARTSYS)
+		return -ERESTARTSYS;
+
+	return 0;
+}
diff --git a/drivers/video/omap2/dss/dispc-compat.h b/drivers/video/omap2/dss/dispc-compat.h
index 2d4f5e77a7bf..8322d43d28c3 100644
--- a/drivers/video/omap2/dss/dispc-compat.h
+++ b/drivers/video/omap2/dss/dispc-compat.h
@@ -21,4 +21,7 @@
 void dispc_mgr_enable_sync(enum omap_channel channel);
 void dispc_mgr_disable_sync(enum omap_channel channel);
 
+int omap_dispc_wait_for_irq_interruptible_timeout(u32 irqmask,
+		unsigned long timeout);
+
 #endif
diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c
index 73972e99ec63..f7c734214022 100644
--- a/drivers/video/omap2/dss/dispc.c
+++ b/drivers/video/omap2/dss/dispc.c
@@ -3750,63 +3750,6 @@ static void dispc_error_worker(struct work_struct *work)
 	dispc_runtime_put();
 }
 
-int omap_dispc_wait_for_irq_timeout(u32 irqmask, unsigned long timeout)
-{
-	void dispc_irq_wait_handler(void *data, u32 mask)
-	{
-		complete((struct completion *)data);
-	}
-
-	int r;
-	DECLARE_COMPLETION_ONSTACK(completion);
-
-	r = omap_dispc_register_isr(dispc_irq_wait_handler, &completion,
-			irqmask);
-
-	if (r)
-		return r;
-
-	timeout = wait_for_completion_timeout(&completion, timeout);
-
-	omap_dispc_unregister_isr(dispc_irq_wait_handler, &completion, irqmask);
-
-	if (timeout == 0)
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-int omap_dispc_wait_for_irq_interruptible_timeout(u32 irqmask,
-		unsigned long timeout)
-{
-	void dispc_irq_wait_handler(void *data, u32 mask)
-	{
-		complete((struct completion *)data);
-	}
-
-	int r;
-	DECLARE_COMPLETION_ONSTACK(completion);
-
-	r = omap_dispc_register_isr(dispc_irq_wait_handler, &completion,
-			irqmask);
-
-	if (r)
-		return r;
-
-	timeout = wait_for_completion_interruptible_timeout(&completion,
-			timeout);
-
-	omap_dispc_unregister_isr(dispc_irq_wait_handler, &completion, irqmask);
-
-	if (timeout == 0)
-		return -ETIMEDOUT;
-
-	if (timeout == -ERESTARTSYS)
-		return -ERESTARTSYS;
-
-	return 0;
-}
-
 static void _omap_dispc_initialize_irq(void)
 {
 	unsigned long flags;
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index a9402362d817..823a07b00fe5 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -775,10 +775,6 @@ typedef void (*omap_dispc_isr_t) (void *arg, u32 mask);
 int omap_dispc_register_isr(omap_dispc_isr_t isr, void *arg, u32 mask);
 int omap_dispc_unregister_isr(omap_dispc_isr_t isr, void *arg, u32 mask);
 
-int omap_dispc_wait_for_irq_timeout(u32 irqmask, unsigned long timeout);
-int omap_dispc_wait_for_irq_interruptible_timeout(u32 irqmask,
-		unsigned long timeout);
-
 #define to_dss_driver(x) container_of((x), struct omap_dss_driver, driver)
 #define to_dss_device(x) container_of((x), struct omap_dss_device, dev)
 
-- 
cgit v1.2.3-55-g7522


From a97a96347598201ae39b5aee67638dae2cebe454 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Wed, 24 Oct 2012 13:52:40 +0300
Subject: OMAPDSS: export dss_mgr_ops functions

Export dss_mgr_ops related functions.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/omap2/dss/dss.h    | 30 ------------------------------
 drivers/video/omap2/dss/output.c |  9 +++++++++
 include/video/omapdss.h          | 29 +++++++++++++++++++++++++++++
 3 files changed, 38 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/video/omap2/dss/dss.h b/drivers/video/omap2/dss/dss.h
index 8c89cdda96dd..1d8483cbe395 100644
--- a/drivers/video/omap2/dss/dss.h
+++ b/drivers/video/omap2/dss/dss.h
@@ -179,19 +179,6 @@ void dss_put_device(struct omap_dss_device *dssdev);
 void dss_copy_device_pdata(struct omap_dss_device *dst,
 		const struct omap_dss_device *src);
 
-/* apply */
-void dss_mgr_start_update(struct omap_overlay_manager *mgr);
-int dss_mgr_enable(struct omap_overlay_manager *mgr);
-void dss_mgr_disable(struct omap_overlay_manager *mgr);
-void dss_mgr_set_timings(struct omap_overlay_manager *mgr,
-		const struct omap_video_timings *timings);
-void dss_mgr_set_lcd_config(struct omap_overlay_manager *mgr,
-		const struct dss_lcd_mgr_config *config);
-int dss_mgr_register_framedone_handler(struct omap_overlay_manager *mgr,
-		void (*handler)(void *), void *data);
-void dss_mgr_unregister_framedone_handler(struct omap_overlay_manager *mgr,
-		void (*handler)(void *), void *data);
-
 /* output */
 void dss_register_output(struct omap_dss_output *out);
 void dss_unregister_output(struct omap_dss_output *out);
@@ -529,21 +516,4 @@ static inline void dss_collect_irq_stats(u32 irqstatus, unsigned *irq_arr)
 }
 #endif
 
-struct dss_mgr_ops {
-	void (*start_update)(struct omap_overlay_manager *mgr);
-	int (*enable)(struct omap_overlay_manager *mgr);
-	void (*disable)(struct omap_overlay_manager *mgr);
-	void (*set_timings)(struct omap_overlay_manager *mgr,
-			const struct omap_video_timings *timings);
-	void (*set_lcd_config)(struct omap_overlay_manager *mgr,
-			const struct dss_lcd_mgr_config *config);
-	int (*register_framedone_handler)(struct omap_overlay_manager *mgr,
-			void (*handler)(void *), void *data);
-	void (*unregister_framedone_handler)(struct omap_overlay_manager *mgr,
-			void (*handler)(void *), void *data);
-};
-
-int dss_install_mgr_ops(const struct dss_mgr_ops *mgr_ops);
-void dss_uninstall_mgr_ops(void);
-
 #endif
diff --git a/drivers/video/omap2/dss/output.c b/drivers/video/omap2/dss/output.c
index 6def0d7bbd05..79dea1a1a732 100644
--- a/drivers/video/omap2/dss/output.c
+++ b/drivers/video/omap2/dss/output.c
@@ -125,47 +125,56 @@ int dss_install_mgr_ops(const struct dss_mgr_ops *mgr_ops)
 
 	return 0;
 }
+EXPORT_SYMBOL(dss_install_mgr_ops);
 
 void dss_uninstall_mgr_ops(void)
 {
 	dss_mgr_ops = NULL;
 }
+EXPORT_SYMBOL(dss_uninstall_mgr_ops);
 
 void dss_mgr_set_timings(struct omap_overlay_manager *mgr,
 		const struct omap_video_timings *timings)
 {
 	dss_mgr_ops->set_timings(mgr, timings);
 }
+EXPORT_SYMBOL(dss_mgr_set_timings);
 
 void dss_mgr_set_lcd_config(struct omap_overlay_manager *mgr,
 		const struct dss_lcd_mgr_config *config)
 {
 	dss_mgr_ops->set_lcd_config(mgr, config);
 }
+EXPORT_SYMBOL(dss_mgr_set_lcd_config);
 
 int dss_mgr_enable(struct omap_overlay_manager *mgr)
 {
 	return dss_mgr_ops->enable(mgr);
 }
+EXPORT_SYMBOL(dss_mgr_enable);
 
 void dss_mgr_disable(struct omap_overlay_manager *mgr)
 {
 	dss_mgr_ops->disable(mgr);
 }
+EXPORT_SYMBOL(dss_mgr_disable);
 
 void dss_mgr_start_update(struct omap_overlay_manager *mgr)
 {
 	dss_mgr_ops->start_update(mgr);
 }
+EXPORT_SYMBOL(dss_mgr_start_update);
 
 int dss_mgr_register_framedone_handler(struct omap_overlay_manager *mgr,
 		void (*handler)(void *), void *data)
 {
 	return dss_mgr_ops->register_framedone_handler(mgr, handler, data);
 }
+EXPORT_SYMBOL(dss_mgr_register_framedone_handler);
 
 void dss_mgr_unregister_framedone_handler(struct omap_overlay_manager *mgr,
 		void (*handler)(void *), void *data)
 {
 	dss_mgr_ops->unregister_framedone_handler(mgr, handler, data);
 }
+EXPORT_SYMBOL(dss_mgr_unregister_framedone_handler);
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index 823a07b00fe5..d1bf3bc54db6 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -55,6 +55,7 @@
 
 struct omap_dss_device;
 struct omap_overlay_manager;
+struct dss_lcd_mgr_config;
 struct snd_aes_iec958;
 struct snd_cea_861_aud_if;
 
@@ -835,4 +836,32 @@ void omapdss_rfbi_set_interface_timings(struct omap_dss_device *dssdev,
 int omapdss_compat_init(void);
 void omapdss_compat_uninit(void);
 
+struct dss_mgr_ops {
+	void (*start_update)(struct omap_overlay_manager *mgr);
+	int (*enable)(struct omap_overlay_manager *mgr);
+	void (*disable)(struct omap_overlay_manager *mgr);
+	void (*set_timings)(struct omap_overlay_manager *mgr,
+			const struct omap_video_timings *timings);
+	void (*set_lcd_config)(struct omap_overlay_manager *mgr,
+			const struct dss_lcd_mgr_config *config);
+	int (*register_framedone_handler)(struct omap_overlay_manager *mgr,
+			void (*handler)(void *), void *data);
+	void (*unregister_framedone_handler)(struct omap_overlay_manager *mgr,
+			void (*handler)(void *), void *data);
+};
+
+int dss_install_mgr_ops(const struct dss_mgr_ops *mgr_ops);
+void dss_uninstall_mgr_ops(void);
+
+void dss_mgr_set_timings(struct omap_overlay_manager *mgr,
+		const struct omap_video_timings *timings);
+void dss_mgr_set_lcd_config(struct omap_overlay_manager *mgr,
+		const struct dss_lcd_mgr_config *config);
+int dss_mgr_enable(struct omap_overlay_manager *mgr);
+void dss_mgr_disable(struct omap_overlay_manager *mgr);
+void dss_mgr_start_update(struct omap_overlay_manager *mgr);
+int dss_mgr_register_framedone_handler(struct omap_overlay_manager *mgr,
+		void (*handler)(void *), void *data);
+void dss_mgr_unregister_framedone_handler(struct omap_overlay_manager *mgr,
+		void (*handler)(void *), void *data);
 #endif
-- 
cgit v1.2.3-55-g7522


From eda34273631a9c4bae65eb49394549f6007f2fb8 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Wed, 7 Nov 2012 16:26:11 +0200
Subject: OMAPDSS: export dss_feat functions

Export dss_features related functions.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/omap2/dss/dss_features.c | 6 ++++++
 drivers/video/omap2/dss/dss_features.h | 5 -----
 include/video/omapdss.h                | 8 ++++++++
 3 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/video/omap2/dss/dss_features.c b/drivers/video/omap2/dss/dss_features.c
index 1d125c6bfd19..18688c12e30d 100644
--- a/drivers/video/omap2/dss/dss_features.c
+++ b/drivers/video/omap2/dss/dss_features.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/err.h>
 #include <linux/slab.h>
@@ -839,11 +840,13 @@ int dss_feat_get_num_mgrs(void)
 {
 	return omap_current_dss_features->num_mgrs;
 }
+EXPORT_SYMBOL(dss_feat_get_num_mgrs);
 
 int dss_feat_get_num_ovls(void)
 {
 	return omap_current_dss_features->num_ovls;
 }
+EXPORT_SYMBOL(dss_feat_get_num_ovls);
 
 int dss_feat_get_num_wbs(void)
 {
@@ -864,16 +867,19 @@ enum omap_display_type dss_feat_get_supported_displays(enum omap_channel channel
 {
 	return omap_current_dss_features->supported_displays[channel];
 }
+EXPORT_SYMBOL(dss_feat_get_supported_displays);
 
 enum omap_dss_output_id dss_feat_get_supported_outputs(enum omap_channel channel)
 {
 	return omap_current_dss_features->supported_outputs[channel];
 }
+EXPORT_SYMBOL(dss_feat_get_supported_outputs);
 
 enum omap_color_mode dss_feat_get_supported_color_modes(enum omap_plane plane)
 {
 	return omap_current_dss_features->supported_color_modes[plane];
 }
+EXPORT_SYMBOL(dss_feat_get_supported_color_modes);
 
 enum omap_overlay_caps dss_feat_get_overlay_caps(enum omap_plane plane)
 {
diff --git a/drivers/video/omap2/dss/dss_features.h b/drivers/video/omap2/dss/dss_features.h
index 385b0afe63c2..489b9bec4a6d 100644
--- a/drivers/video/omap2/dss/dss_features.h
+++ b/drivers/video/omap2/dss/dss_features.h
@@ -101,14 +101,9 @@ enum dss_range_param {
 };
 
 /* DSS Feature Functions */
-int dss_feat_get_num_mgrs(void);
-int dss_feat_get_num_ovls(void);
 int dss_feat_get_num_wbs(void);
 unsigned long dss_feat_get_param_min(enum dss_range_param param);
 unsigned long dss_feat_get_param_max(enum dss_range_param param);
-enum omap_display_type dss_feat_get_supported_displays(enum omap_channel channel);
-enum omap_dss_output_id dss_feat_get_supported_outputs(enum omap_channel channel);
-enum omap_color_mode dss_feat_get_supported_color_modes(enum omap_plane plane);
 enum omap_overlay_caps dss_feat_get_overlay_caps(enum omap_plane plane);
 bool dss_feat_color_mode_supported(enum omap_plane plane,
 		enum omap_color_mode color_mode);
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index d1bf3bc54db6..8c9df4867273 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -755,6 +755,14 @@ const char *omapdss_get_default_display_name(void);
 int omap_dss_start_device(struct omap_dss_device *dssdev);
 void omap_dss_stop_device(struct omap_dss_device *dssdev);
 
+int dss_feat_get_num_mgrs(void);
+int dss_feat_get_num_ovls(void);
+enum omap_display_type dss_feat_get_supported_displays(enum omap_channel channel);
+enum omap_dss_output_id dss_feat_get_supported_outputs(enum omap_channel channel);
+enum omap_color_mode dss_feat_get_supported_color_modes(enum omap_plane plane);
+
+
+
 int omap_dss_get_num_overlay_managers(void);
 struct omap_overlay_manager *omap_dss_get_overlay_manager(int num);
 
-- 
cgit v1.2.3-55-g7522


From 348be69d306260c9bcb62662c4cf04196a2b9f53 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Wed, 7 Nov 2012 18:17:35 +0200
Subject: OMAPDSS: export dispc functions

Export DISPC functions.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/omap2/dss/dispc.c | 23 +++++++++++++++++++++++
 drivers/video/omap2/dss/dss.h   | 36 +-----------------------------------
 include/video/omapdss.h         | 39 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 63 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c
index 67548839ff51..fedbd2c8e97a 100644
--- a/drivers/video/omap2/dss/dispc.c
+++ b/drivers/video/omap2/dss/dispc.c
@@ -494,6 +494,7 @@ int dispc_runtime_get(void)
 	WARN_ON(r < 0);
 	return r < 0 ? r : 0;
 }
+EXPORT_SYMBOL(dispc_runtime_get);
 
 void dispc_runtime_put(void)
 {
@@ -504,11 +505,13 @@ void dispc_runtime_put(void)
 	r = pm_runtime_put_sync(&dispc.pdev->dev);
 	WARN_ON(r < 0 && r != -ENOSYS);
 }
+EXPORT_SYMBOL(dispc_runtime_put);
 
 u32 dispc_mgr_get_vsync_irq(enum omap_channel channel)
 {
 	return mgr_desc[channel].vsync_irq;
 }
+EXPORT_SYMBOL(dispc_mgr_get_vsync_irq);
 
 u32 dispc_mgr_get_framedone_irq(enum omap_channel channel)
 {
@@ -517,11 +520,13 @@ u32 dispc_mgr_get_framedone_irq(enum omap_channel channel)
 
 	return mgr_desc[channel].framedone_irq;
 }
+EXPORT_SYMBOL(dispc_mgr_get_framedone_irq);
 
 u32 dispc_mgr_get_sync_lost_irq(enum omap_channel channel)
 {
 	return mgr_desc[channel].sync_lost_irq;
 }
+EXPORT_SYMBOL(dispc_mgr_get_sync_lost_irq);
 
 u32 dispc_wb_get_framedone_irq(void)
 {
@@ -532,6 +537,7 @@ bool dispc_mgr_go_busy(enum omap_channel channel)
 {
 	return mgr_fld_read(channel, DISPC_MGR_FLD_GO) == 1;
 }
+EXPORT_SYMBOL(dispc_mgr_go_busy);
 
 void dispc_mgr_go(enum omap_channel channel)
 {
@@ -542,6 +548,7 @@ void dispc_mgr_go(enum omap_channel channel)
 
 	mgr_fld_write(channel, DISPC_MGR_FLD_GO, 1);
 }
+EXPORT_SYMBOL(dispc_mgr_go);
 
 bool dispc_wb_go_busy(void)
 {
@@ -945,6 +952,7 @@ void dispc_ovl_set_channel_out(enum omap_plane plane, enum omap_channel channel)
 	}
 	dispc_write_reg(DISPC_OVL_ATTRIBUTES(plane), val);
 }
+EXPORT_SYMBOL(dispc_ovl_set_channel_out);
 
 static enum omap_channel dispc_ovl_get_channel_out(enum omap_plane plane)
 {
@@ -2359,6 +2367,7 @@ int dispc_ovl_check(enum omap_plane plane, enum omap_channel channel,
 			&five_taps, x_predecim, y_predecim, pos_x,
 			oi->rotation_type, false);
 }
+EXPORT_SYMBOL(dispc_ovl_check);
 
 static int dispc_ovl_setup_common(enum omap_plane plane,
 		enum omap_overlay_caps caps, u32 paddr, u32 p_uv_addr,
@@ -2539,6 +2548,7 @@ int dispc_ovl_setup(enum omap_plane plane, const struct omap_overlay_info *oi,
 
 	return r;
 }
+EXPORT_SYMBOL(dispc_ovl_setup);
 
 int dispc_wb_setup(const struct omap_dss_writeback_info *wi,
 		bool mem_to_mem, const struct omap_video_timings *mgr_timings)
@@ -2599,11 +2609,13 @@ int dispc_ovl_enable(enum omap_plane plane, bool enable)
 
 	return 0;
 }
+EXPORT_SYMBOL(dispc_ovl_enable);
 
 bool dispc_ovl_enabled(enum omap_plane plane)
 {
 	return REG_GET(DISPC_OVL_ATTRIBUTES(plane), 0, 0);
 }
+EXPORT_SYMBOL(dispc_ovl_enabled);
 
 void dispc_mgr_enable(enum omap_channel channel, bool enable)
 {
@@ -2611,11 +2623,13 @@ void dispc_mgr_enable(enum omap_channel channel, bool enable)
 	/* flush posted write */
 	mgr_fld_read(channel, DISPC_MGR_FLD_ENABLE);
 }
+EXPORT_SYMBOL(dispc_mgr_enable);
 
 bool dispc_mgr_is_enabled(enum omap_channel channel)
 {
 	return !!mgr_fld_read(channel, DISPC_MGR_FLD_ENABLE);
 }
+EXPORT_SYMBOL(dispc_mgr_is_enabled);
 
 void dispc_wb_enable(bool enable)
 {
@@ -2712,6 +2726,7 @@ void dispc_mgr_setup(enum omap_channel channel,
 		dispc_mgr_set_cpr_coef(channel, &info->cpr_coefs);
 	}
 }
+EXPORT_SYMBOL(dispc_mgr_setup);
 
 static void dispc_mgr_set_tft_data_lines(enum omap_channel channel, u8 data_lines)
 {
@@ -2788,6 +2803,7 @@ void dispc_mgr_set_lcd_config(enum omap_channel channel,
 
 	dispc_mgr_set_lcd_type_tft(channel);
 }
+EXPORT_SYMBOL(dispc_mgr_set_lcd_config);
 
 static bool _dispc_mgr_size_ok(u16 width, u16 height)
 {
@@ -2926,6 +2942,7 @@ void dispc_mgr_set_timings(enum omap_channel channel,
 
 	dispc_mgr_set_size(channel, t.x_res, t.y_res);
 }
+EXPORT_SYMBOL(dispc_mgr_set_timings);
 
 static void dispc_mgr_set_lcd_divisor(enum omap_channel channel, u16 lck_div,
 		u16 pck_div)
@@ -3389,16 +3406,19 @@ u32 dispc_read_irqstatus(void)
 {
 	return dispc_read_reg(DISPC_IRQSTATUS);
 }
+EXPORT_SYMBOL(dispc_read_irqstatus);
 
 void dispc_clear_irqstatus(u32 mask)
 {
 	dispc_write_reg(DISPC_IRQSTATUS, mask);
 }
+EXPORT_SYMBOL(dispc_clear_irqstatus);
 
 u32 dispc_read_irqenable(void)
 {
 	return dispc_read_reg(DISPC_IRQENABLE);
 }
+EXPORT_SYMBOL(dispc_read_irqenable);
 
 void dispc_write_irqenable(u32 mask)
 {
@@ -3409,6 +3429,7 @@ void dispc_write_irqenable(u32 mask)
 
 	dispc_write_reg(DISPC_IRQENABLE, mask);
 }
+EXPORT_SYMBOL(dispc_write_irqenable);
 
 void dispc_enable_sidle(void)
 {
@@ -3584,11 +3605,13 @@ int dispc_request_irq(irq_handler_t handler, void *dev_id)
 	return devm_request_irq(&dispc.pdev->dev, dispc.irq, handler,
 			     IRQF_SHARED, "OMAP DISPC", dev_id);
 }
+EXPORT_SYMBOL(dispc_request_irq);
 
 void dispc_free_irq(void *dev_id)
 {
 	devm_free_irq(&dispc.pdev->dev, dispc.irq, dev_id);
 }
+EXPORT_SYMBOL(dispc_free_irq);
 
 /* DISPC HW IP initialisation */
 static int __init omap_dispchw_probe(struct platform_device *pdev)
diff --git a/drivers/video/omap2/dss/dss.h b/drivers/video/omap2/dss/dss.h
index 1d8483cbe395..ebe9e08b2a91 100644
--- a/drivers/video/omap2/dss/dss.h
+++ b/drivers/video/omap2/dss/dss.h
@@ -365,16 +365,6 @@ void dpi_uninit_platform_driver(void) __exit;
 int dispc_init_platform_driver(void) __init;
 void dispc_uninit_platform_driver(void) __exit;
 void dispc_dump_clocks(struct seq_file *s);
-u32 dispc_read_irqstatus(void);
-void dispc_clear_irqstatus(u32 mask);
-u32 dispc_read_irqenable(void);
-void dispc_write_irqenable(u32 mask);
-
-int dispc_request_irq(irq_handler_t handler, void *dev_id);
-void dispc_free_irq(void *dev_id);
-
-int dispc_runtime_get(void);
-void dispc_runtime_put(void);
 
 void dispc_enable_sidle(void);
 void dispc_disable_sidle(void);
@@ -398,29 +388,7 @@ void dispc_ovl_set_fifo_threshold(enum omap_plane plane, u32 low, u32 high);
 void dispc_ovl_compute_fifo_thresholds(enum omap_plane plane,
 		u32 *fifo_low, u32 *fifo_high, bool use_fifomerge,
 		bool manual_update);
-int dispc_ovl_setup(enum omap_plane plane, const struct omap_overlay_info *oi,
-		bool replication, const struct omap_video_timings *mgr_timings,
-		bool mem_to_mem);
-int dispc_ovl_enable(enum omap_plane plane, bool enable);
-bool dispc_ovl_enabled(enum omap_plane plane);
-void dispc_ovl_set_channel_out(enum omap_plane plane,
-		enum omap_channel channel);
-int dispc_ovl_check(enum omap_plane plane, enum omap_channel channel,
-		const struct omap_overlay_info *oi,
-		const struct omap_video_timings *timings,
-		int *x_predecim, int *y_predecim);
-
-u32 dispc_mgr_get_vsync_irq(enum omap_channel channel);
-u32 dispc_mgr_get_framedone_irq(enum omap_channel channel);
-u32 dispc_mgr_get_sync_lost_irq(enum omap_channel channel);
-bool dispc_mgr_go_busy(enum omap_channel channel);
-void dispc_mgr_go(enum omap_channel channel);
-void dispc_mgr_enable(enum omap_channel channel, bool enable);
-bool dispc_mgr_is_enabled(enum omap_channel channel);
-void dispc_mgr_set_lcd_config(enum omap_channel channel,
-		const struct dss_lcd_mgr_config *config);
-void dispc_mgr_set_timings(enum omap_channel channel,
-		const struct omap_video_timings *timings);
+
 unsigned long dispc_mgr_lclk_rate(enum omap_channel channel);
 unsigned long dispc_mgr_pclk_rate(enum omap_channel channel);
 unsigned long dispc_core_clk_rate(void);
@@ -428,8 +396,6 @@ void dispc_mgr_set_clock_div(enum omap_channel channel,
 		const struct dispc_clock_info *cinfo);
 int dispc_mgr_get_clock_div(enum omap_channel channel,
 		struct dispc_clock_info *cinfo);
-void dispc_mgr_setup(enum omap_channel channel,
-		const struct omap_overlay_manager_info *info);
 
 u32 dispc_wb_get_framedone_irq(void);
 bool dispc_wb_go_busy(void);
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index 8c9df4867273..caefa093337d 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -21,6 +21,7 @@
 #include <linux/list.h>
 #include <linux/kobject.h>
 #include <linux/device.h>
+#include <linux/interrupt.h>
 
 #define DISPC_IRQ_FRAMEDONE		(1 << 0)
 #define DISPC_IRQ_VSYNC			(1 << 1)
@@ -784,6 +785,44 @@ typedef void (*omap_dispc_isr_t) (void *arg, u32 mask);
 int omap_dispc_register_isr(omap_dispc_isr_t isr, void *arg, u32 mask);
 int omap_dispc_unregister_isr(omap_dispc_isr_t isr, void *arg, u32 mask);
 
+u32 dispc_read_irqstatus(void);
+void dispc_clear_irqstatus(u32 mask);
+u32 dispc_read_irqenable(void);
+void dispc_write_irqenable(u32 mask);
+
+int dispc_request_irq(irq_handler_t handler, void *dev_id);
+void dispc_free_irq(void *dev_id);
+
+int dispc_runtime_get(void);
+void dispc_runtime_put(void);
+
+void dispc_mgr_enable(enum omap_channel channel, bool enable);
+bool dispc_mgr_is_enabled(enum omap_channel channel);
+u32 dispc_mgr_get_vsync_irq(enum omap_channel channel);
+u32 dispc_mgr_get_framedone_irq(enum omap_channel channel);
+u32 dispc_mgr_get_sync_lost_irq(enum omap_channel channel);
+bool dispc_mgr_go_busy(enum omap_channel channel);
+void dispc_mgr_go(enum omap_channel channel);
+void dispc_mgr_set_lcd_config(enum omap_channel channel,
+		const struct dss_lcd_mgr_config *config);
+void dispc_mgr_set_timings(enum omap_channel channel,
+		const struct omap_video_timings *timings);
+void dispc_mgr_setup(enum omap_channel channel,
+		const struct omap_overlay_manager_info *info);
+
+int dispc_ovl_check(enum omap_plane plane, enum omap_channel channel,
+		const struct omap_overlay_info *oi,
+		const struct omap_video_timings *timings,
+		int *x_predecim, int *y_predecim);
+
+int dispc_ovl_enable(enum omap_plane plane, bool enable);
+bool dispc_ovl_enabled(enum omap_plane plane);
+void dispc_ovl_set_channel_out(enum omap_plane plane,
+		enum omap_channel channel);
+int dispc_ovl_setup(enum omap_plane plane, const struct omap_overlay_info *oi,
+		bool replication, const struct omap_video_timings *mgr_timings,
+		bool mem_to_mem);
+
 #define to_dss_driver(x) container_of((x), struct omap_dss_driver, driver)
 #define to_dss_device(x) container_of((x), struct omap_dss_device, dev)
 
-- 
cgit v1.2.3-55-g7522


From 6ded7cd605502eff7341bbd912ebc90c3674c764 Mon Sep 17 00:00:00 2001
From: trem
Date: Tue, 4 Dec 2012 08:52:10 +0000
Subject: net: phy: smsc: force all capable mode if the phy is started in
 powerdown mode

A SMSC PHY in power down mode can't be used.
If a SMSC PHY is in this mode in the config_init
stage, the mode "all capable" is set. So the PHY
could then be used.

Signed-off-by: Philippe Reynes <tremyfr@yahoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/smsc.c  | 26 +++++++++++++++++++++++++-
 include/linux/smscphy.h |  5 +++++
 2 files changed, 30 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 16dceed29d8c..ef883e3048c0 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -43,7 +43,31 @@ static int smsc_phy_ack_interrupt(struct phy_device *phydev)
 
 static int smsc_phy_config_init(struct phy_device *phydev)
 {
-	int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS);
+	int rc = phy_read(phydev, MII_LAN83C185_SPECIAL_MODES);
+	if (rc < 0)
+		return rc;
+
+	/* If the SMSC PHY is in power down mode, then set it
+	 * in all capable mode before using it.
+	 */
+	if ((rc & MII_LAN83C185_MODE_MASK) == MII_LAN83C185_MODE_POWERDOWN) {
+		int timeout = 50000;
+
+		/* set "all capable" mode and reset the phy */
+		rc |= MII_LAN83C185_MODE_ALL;
+		phy_write(phydev, MII_LAN83C185_SPECIAL_MODES, rc);
+		phy_write(phydev, MII_BMCR, BMCR_RESET);
+
+		/* wait end of reset (max 500 ms) */
+		do {
+			udelay(10);
+			if (timeout-- == 0)
+				return -1;
+			rc = phy_read(phydev, MII_BMCR);
+		} while (rc & BMCR_RESET);
+	}
+
+	rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS);
 	if (rc < 0)
 		return rc;
 
diff --git a/include/linux/smscphy.h b/include/linux/smscphy.h
index ce718cbce435..f4bf16e16e16 100644
--- a/include/linux/smscphy.h
+++ b/include/linux/smscphy.h
@@ -4,6 +4,7 @@
 #define MII_LAN83C185_ISF 29 /* Interrupt Source Flags */
 #define MII_LAN83C185_IM  30 /* Interrupt Mask */
 #define MII_LAN83C185_CTRL_STATUS 17 /* Mode/Status Register */
+#define MII_LAN83C185_SPECIAL_MODES 18 /* Special Modes Register */
 
 #define MII_LAN83C185_ISF_INT1 (1<<1) /* Auto-Negotiation Page Received */
 #define MII_LAN83C185_ISF_INT2 (1<<2) /* Parallel Detection Fault */
@@ -22,4 +23,8 @@
 #define MII_LAN83C185_EDPWRDOWN (1 << 13) /* EDPWRDOWN */
 #define MII_LAN83C185_ENERGYON  (1 << 1)  /* ENERGYON */
 
+#define MII_LAN83C185_MODE_MASK      0xE0
+#define MII_LAN83C185_MODE_POWERDOWN 0xC0 /* Power Down mode */
+#define MII_LAN83C185_MODE_ALL       0xE0 /* All capable mode */
+
 #endif /* __LINUX_SMSCPHY_H__ */
-- 
cgit v1.2.3-55-g7522


From 7508320678b7819ac6aeb89580b8622a424ce586 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas
Date: Wed, 5 Dec 2012 13:51:19 -0700
Subject: PCI: Add standard PCIe Capability Link ASPM field names

Add standard #defines for ASPM fields in PCI Express Link Capability and
Link Control registers.

Previously we used PCIE_LINK_STATE_L0S and PCIE_LINK_STATE_L1 directly, but
these are defined for the Linux ASPM interfaces, e.g.,
pci_disable_link_state(), and only coincidentally match the actual register
bits.  PCIE_LINK_STATE_CLKPM, also part of that interface, does not match
the register bit.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>---
 drivers/pci/pcie/aspm.c       | 11 ++++++-----
 include/uapi/linux/pci_regs.h |  2 ++
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 213753b283a6..c2faf9d0ffde 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -427,7 +427,8 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 
 static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val)
 {
-	pcie_capability_clear_and_set_word(pdev, PCI_EXP_LNKCTL, 0x3, val);
+	pcie_capability_clear_and_set_word(pdev, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC, val);
 }
 
 static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state)
@@ -442,12 +443,12 @@ static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state)
 		return;
 	/* Convert ASPM state to upstream/downstream ASPM register state */
 	if (state & ASPM_STATE_L0S_UP)
-		dwstream |= PCIE_LINK_STATE_L0S;
+		dwstream |= PCI_EXP_LNKCTL_ASPM_L0S;
 	if (state & ASPM_STATE_L0S_DW)
-		upstream |= PCIE_LINK_STATE_L0S;
+		upstream |= PCI_EXP_LNKCTL_ASPM_L0S;
 	if (state & ASPM_STATE_L1) {
-		upstream |= PCIE_LINK_STATE_L1;
-		dwstream |= PCIE_LINK_STATE_L1;
+		upstream |= PCI_EXP_LNKCTL_ASPM_L1;
+		dwstream |= PCI_EXP_LNKCTL_ASPM_L1;
 	}
 	/*
 	 * Spec 2.0 suggests all functions should be configured the
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 4cca834f9abd..0b6dbe49dc1e 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -469,6 +469,8 @@
 #define  PCI_EXP_LNKCAP_PN	0xff000000 /* Port Number */
 #define PCI_EXP_LNKCTL		16	/* Link Control */
 #define  PCI_EXP_LNKCTL_ASPMC	0x0003	/* ASPM Control */
+#define  PCI_EXP_LNKCTL_ASPM_L0S  0x01	/* L0s Enable */
+#define  PCI_EXP_LNKCTL_ASPM_L1   0x02	/* L1 Enable */
 #define  PCI_EXP_LNKCTL_RCB	0x0008	/* Read Completion Boundary */
 #define  PCI_EXP_LNKCTL_LD	0x0010	/* Link Disable */
 #define  PCI_EXP_LNKCTL_RL	0x0020	/* Retrain Link */
-- 
cgit v1.2.3-55-g7522


From 45122ca26ced7fae41049326a3797a73f961db2e Mon Sep 17 00:00:00 2001
From: Thomas Graf
Date: Thu, 6 Dec 2012 09:25:05 +0000
Subject: sctp: Add RCU protection to assoc->transport_addr_list

peer.transport_addr_list is currently only protected by sk_sock
which is inpractical to acquire for procfs dumping purposes.

This patch adds RCU protection allowing for the procfs readers to
enter RCU read-side critical sections.

Modification of the list continues to be serialized via sk_lock.

V2: Use list_del_rcu() in sctp_association_free() to be safe
    Skip transports marked dead when dumping for procfs

Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h |  2 ++
 net/sctp/associola.c       |  6 +++---
 net/sctp/proc.c            | 14 ++++++++++++--
 net/sctp/transport.c       | 18 +++++++++++++-----
 4 files changed, 30 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index c2521016d646..fdeb85a970fc 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -949,6 +949,8 @@ struct sctp_transport {
 
 	/* 64-bit random number sent with heartbeat. */
 	__u64 hb_nonce;
+
+	struct rcu_head rcu;
 };
 
 struct sctp_transport *sctp_transport_new(struct net *, const union sctp_addr *,
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index ba3f9cc4c047..b45ed1f96921 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -448,7 +448,7 @@ void sctp_association_free(struct sctp_association *asoc)
 	/* Release the transport structures. */
 	list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) {
 		transport = list_entry(pos, struct sctp_transport, transports);
-		list_del(pos);
+		list_del_rcu(pos);
 		sctp_transport_free(transport);
 	}
 
@@ -568,7 +568,7 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
 		sctp_assoc_update_retran_path(asoc);
 
 	/* Remove this peer from the list. */
-	list_del(&peer->transports);
+	list_del_rcu(&peer->transports);
 
 	/* Get the first transport of asoc. */
 	pos = asoc->peer.transport_addr_list.next;
@@ -769,7 +769,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 	peer->state = peer_state;
 
 	/* Attach the remote transport to our asoc.  */
-	list_add_tail(&peer->transports, &asoc->peer.transport_addr_list);
+	list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list);
 	asoc->peer.transport_count++;
 
 	/* If we do not yet have a primary path, set one.  */
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 06b05ee17d8d..8c19e97262ca 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -162,15 +162,20 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa
 	struct sctp_af *af;
 
 	primary = &assoc->peer.primary_addr;
-	list_for_each_entry(transport, &assoc->peer.transport_addr_list,
+	rcu_read_lock();
+	list_for_each_entry_rcu(transport, &assoc->peer.transport_addr_list,
 			transports) {
 		addr = &transport->ipaddr;
+		if (transport->dead)
+			continue;
+
 		af = sctp_get_af_specific(addr->sa.sa_family);
 		if (af->cmp_addr(addr, primary)) {
 			seq_printf(seq, "*");
 		}
 		af->seq_dump_addr(seq, addr);
 	}
+	rcu_read_unlock();
 }
 
 static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos)
@@ -441,12 +446,16 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 	head = &sctp_assoc_hashtable[hash];
 	sctp_local_bh_disable();
 	read_lock(&head->lock);
+	rcu_read_lock();
 	sctp_for_each_hentry(epb, node, &head->chain) {
 		if (!net_eq(sock_net(epb->sk), seq_file_net(seq)))
 			continue;
 		assoc = sctp_assoc(epb);
-		list_for_each_entry(tsp, &assoc->peer.transport_addr_list,
+		list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list,
 					transports) {
+			if (tsp->dead)
+				continue;
+
 			/*
 			 * The remote address (ADDR)
 			 */
@@ -492,6 +501,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 		}
 	}
 
+	rcu_read_unlock();
 	read_unlock(&head->lock);
 	sctp_local_bh_enable();
 
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 310f11eb2206..4e45bb68aef0 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -163,13 +163,11 @@ void sctp_transport_free(struct sctp_transport *transport)
 	sctp_transport_put(transport);
 }
 
-/* Destroy the transport data structure.
- * Assumes there are no more users of this structure.
- */
-static void sctp_transport_destroy(struct sctp_transport *transport)
+static void sctp_transport_destroy_rcu(struct rcu_head *head)
 {
-	SCTP_ASSERT(transport->dead, "Transport is not dead", return);
+	struct sctp_transport *transport;
 
+	transport = container_of(head, struct sctp_transport, rcu);
 	if (transport->asoc)
 		sctp_association_put(transport->asoc);
 
@@ -180,6 +178,16 @@ static void sctp_transport_destroy(struct sctp_transport *transport)
 	SCTP_DBG_OBJCNT_DEC(transport);
 }
 
+/* Destroy the transport data structure.
+ * Assumes there are no more users of this structure.
+ */
+static void sctp_transport_destroy(struct sctp_transport *transport)
+{
+	SCTP_ASSERT(transport->dead, "Transport is not dead", return);
+
+	call_rcu(&transport->rcu, sctp_transport_destroy_rcu);
+}
+
 /* Start T3_rtx timer if it is not already running and update the heartbeat
  * timer.  This routine is called every time a DATA chunk is sent.
  */
-- 
cgit v1.2.3-55-g7522


From ee07c6e7a6f8a25c18f0a6b18152fbd7499245f6 Mon Sep 17 00:00:00 2001
From: Cong Wang
Date: Fri, 7 Dec 2012 00:04:48 +0000
Subject: bridge: export multicast database via netlink

V5: fix two bugs pointed out by Thomas
    remove seq check for now, mark it as TODO

V4: remove some useless #include
    some coding style fix

V3: drop debugging printk's
    update selinux perm table as well

V2: drop patch 1/2, export ifindex directly
    Redesign netlink attributes
    Improve netlink seq check
    Handle IPv6 addr as well

This patch exports bridge multicast database via netlink
message type RTM_GETMDB. Similar to fdb, but currently bridge-specific.
We may need to support modify multicast database too (RTM_{ADD,DEL}MDB).

(Thanks to Thomas for patient reviews)

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Cong Wang <amwang@redhat.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h |  55 ++++++++++++++
 include/uapi/linux/rtnetlink.h |   3 +
 net/bridge/Makefile            |   2 +-
 net/bridge/br_mdb.c            | 163 +++++++++++++++++++++++++++++++++++++++++
 net/bridge/br_multicast.c      |   1 +
 net/bridge/br_private.h        |   1 +
 security/selinux/nlmsgtab.c    |   1 +
 7 files changed, 225 insertions(+), 1 deletion(-)
 create mode 100644 net/bridge/br_mdb.c

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index b3885791e11e..9a0f6ff0d7e7 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -116,4 +116,59 @@ enum {
 	__IFLA_BRIDGE_MAX,
 };
 #define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1)
+
+/* Bridge multicast database attributes
+ * [MDBA_MDB] = {
+ *     [MDBA_MDB_ENTRY] = {
+ *         [MDBA_MDB_ENTRY_INFO]
+ *     }
+ * }
+ * [MDBA_ROUTER] = {
+ *    [MDBA_ROUTER_PORT]
+ * }
+ */
+enum {
+	MDBA_UNSPEC,
+	MDBA_MDB,
+	MDBA_ROUTER,
+	__MDBA_MAX,
+};
+#define MDBA_MAX (__MDBA_MAX - 1)
+
+enum {
+	MDBA_MDB_UNSPEC,
+	MDBA_MDB_ENTRY,
+	__MDBA_MDB_MAX,
+};
+#define MDBA_MDB_MAX (__MDBA_MDB_MAX - 1)
+
+enum {
+	MDBA_MDB_ENTRY_UNSPEC,
+	MDBA_MDB_ENTRY_INFO,
+	__MDBA_MDB_ENTRY_MAX,
+};
+#define MDBA_MDB_ENTRY_MAX (__MDBA_MDB_ENTRY_MAX - 1)
+
+enum {
+	MDBA_ROUTER_UNSPEC,
+	MDBA_ROUTER_PORT,
+	__MDBA_ROUTER_MAX,
+};
+#define MDBA_ROUTER_MAX (__MDBA_ROUTER_MAX - 1)
+
+struct br_port_msg {
+	__u32 ifindex;
+};
+
+struct br_mdb_entry {
+	__u32 ifindex;
+	struct {
+		union {
+			__be32	ip4;
+			struct in6_addr ip6;
+		} u;
+		__be16		proto;
+	} addr;
+};
+
 #endif /* _UAPI_LINUX_IF_BRIDGE_H */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 33d29cea37ea..354a1e7d32a3 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -125,6 +125,9 @@ enum {
 	RTM_GETNETCONF = 82,
 #define RTM_GETNETCONF RTM_GETNETCONF
 
+	RTM_GETMDB = 86,
+#define RTM_GETMDB RTM_GETMDB
+
 	__RTM_MAX,
 #define RTM_MAX		(((__RTM_MAX + 3) & ~3) - 1)
 };
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index d0359ea8ee79..e859098f5ee9 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -12,6 +12,6 @@ bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o
 
 bridge-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o
 
-bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o
+bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o
 
 obj-$(CONFIG_BRIDGE_NF_EBTABLES) += netfilter/
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
new file mode 100644
index 000000000000..edc0d731f6b2
--- /dev/null
+++ b/net/bridge/br_mdb.c
@@ -0,0 +1,163 @@
+#include <linux/err.h>
+#include <linux/igmp.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/rculist.h>
+#include <linux/skbuff.h>
+#include <net/ip.h>
+#include <net/netlink.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6.h>
+#endif
+
+#include "br_private.h"
+
+static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
+			       struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct net_bridge_port *p;
+	struct hlist_node *n;
+	struct nlattr *nest;
+
+	if (!br->multicast_router || hlist_empty(&br->router_list))
+		return 0;
+
+	nest = nla_nest_start(skb, MDBA_ROUTER);
+	if (nest == NULL)
+		return -EMSGSIZE;
+
+	hlist_for_each_entry_rcu(p, n, &br->router_list, rlist) {
+		if (p && nla_put_u32(skb, MDBA_ROUTER_PORT, p->dev->ifindex))
+			goto fail;
+	}
+
+	nla_nest_end(skb, nest);
+	return 0;
+fail:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
+			    struct net_device *dev)
+{
+	struct net_bridge *br = netdev_priv(dev);
+	struct net_bridge_mdb_htable *mdb;
+	struct nlattr *nest, *nest2;
+	int i, err = 0;
+	int idx = 0, s_idx = cb->args[1];
+
+	if (br->multicast_disabled)
+		return 0;
+
+	mdb = rcu_dereference(br->mdb);
+	if (!mdb)
+		return 0;
+
+	nest = nla_nest_start(skb, MDBA_MDB);
+	if (nest == NULL)
+		return -EMSGSIZE;
+
+	for (i = 0; i < mdb->max; i++) {
+		struct hlist_node *h;
+		struct net_bridge_mdb_entry *mp;
+		struct net_bridge_port_group *p, **pp;
+		struct net_bridge_port *port;
+
+		hlist_for_each_entry_rcu(mp, h, &mdb->mhash[i], hlist[mdb->ver]) {
+			if (idx < s_idx)
+				goto skip;
+
+			nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
+			if (nest2 == NULL) {
+				err = -EMSGSIZE;
+				goto out;
+			}
+
+			for (pp = &mp->ports;
+			     (p = rcu_dereference(*pp)) != NULL;
+			      pp = &p->next) {
+				port = p->port;
+				if (port) {
+					struct br_mdb_entry e;
+					e.ifindex = port->dev->ifindex;
+					e.addr.u.ip4 = p->addr.u.ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+					e.addr.u.ip6 = p->addr.u.ip6;
+#endif
+					e.addr.proto = p->addr.proto;
+					if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(e), &e)) {
+						nla_nest_cancel(skb, nest2);
+						err = -EMSGSIZE;
+						goto out;
+					}
+				}
+			}
+			nla_nest_end(skb, nest2);
+		skip:
+			idx++;
+		}
+	}
+
+out:
+	cb->args[1] = idx;
+	nla_nest_end(skb, nest);
+	return err;
+}
+
+static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net_device *dev;
+	struct net *net = sock_net(skb->sk);
+	struct nlmsghdr *nlh = NULL;
+	int idx = 0, s_idx;
+
+	s_idx = cb->args[0];
+
+	rcu_read_lock();
+
+	/* TODO: in case of rehashing, we need to check
+	 * consistency for dumping.
+	 */
+	cb->seq = net->dev_base_seq;
+
+	for_each_netdev_rcu(net, dev) {
+		if (dev->priv_flags & IFF_EBRIDGE) {
+			struct br_port_msg *bpm;
+
+			if (idx < s_idx)
+				goto skip;
+
+			nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+					cb->nlh->nlmsg_seq, RTM_GETMDB,
+					sizeof(*bpm), NLM_F_MULTI);
+			if (nlh == NULL)
+				break;
+
+			bpm = nlmsg_data(nlh);
+			bpm->ifindex = dev->ifindex;
+			if (br_mdb_fill_info(skb, cb, dev) < 0)
+				goto out;
+			if (br_rports_fill_info(skb, cb, dev) < 0)
+				goto out;
+
+			cb->args[1] = 0;
+			nlmsg_end(skb, nlh);
+		skip:
+			idx++;
+		}
+	}
+
+out:
+	if (nlh)
+		nlmsg_end(skb, nlh);
+	rcu_read_unlock();
+	cb->args[0] = idx;
+	return skb->len;
+}
+
+void br_mdb_init(void)
+{
+	rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, NULL);
+}
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index a2a7a1a79081..68e375ac93bd 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1605,6 +1605,7 @@ void br_multicast_init(struct net_bridge *br)
 		    br_multicast_querier_expired, (unsigned long)br);
 	setup_timer(&br->multicast_query_timer, br_multicast_query_expired,
 		    (unsigned long)br);
+	br_mdb_init();
 }
 
 void br_multicast_open(struct net_bridge *br)
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index cd86222cf5e3..ae0a6ec0a702 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -433,6 +433,7 @@ extern int br_multicast_set_port_router(struct net_bridge_port *p,
 extern int br_multicast_toggle(struct net_bridge *br, unsigned long val);
 extern int br_multicast_set_querier(struct net_bridge *br, unsigned long val);
 extern int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val);
+extern void br_mdb_init(void);
 
 static inline bool br_multicast_is_router(struct net_bridge *br)
 {
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index d309e7f472d8..163aaa77d5aa 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -67,6 +67,7 @@ static struct nlmsg_perm nlmsg_route_perms[] =
 	{ RTM_GETADDRLABEL,	NETLINK_ROUTE_SOCKET__NLMSG_READ  },
 	{ RTM_GETDCB,		NETLINK_ROUTE_SOCKET__NLMSG_READ  },
 	{ RTM_SETDCB,		NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETMDB,		NETLINK_ROUTE_SOCKET__NLMSG_READ  },
 };
 
 static struct nlmsg_perm nlmsg_tcpdiag_perms[] =
-- 
cgit v1.2.3-55-g7522


From 57f570838341507682b7705f1d950608ef2182bd Mon Sep 17 00:00:00 2001
From: Marek Olšák
Date: Sun, 2 Dec 2012 21:03:33 +0100
Subject: drm/radeon: add a CS flag END_OF_FRAME

No version bump is required because setting the flag on older DRM has
no effect.

This only reserves the bit and doesn't use it. I assume we will use it
for buffer eviction heuristics.

Signed-off-by: Marek Olšák <maraeo@gmail.com>
---
 include/uapi/drm/radeon_drm.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 4766c0f6a838..0c8a62c543f7 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -913,6 +913,7 @@ struct drm_radeon_gem_va {
 /* The first dword of RADEON_CHUNK_ID_FLAGS is a uint32 of these flags: */
 #define RADEON_CS_KEEP_TILING_FLAGS 0x01
 #define RADEON_CS_USE_VM            0x02
+#define RADEON_CS_END_OF_FRAME      0x04 /* a hint from userspace which CS is the last one */
 /* The second dword of RADEON_CHUNK_ID_FLAGS is a uint32 that sets the ring type */
 #define RADEON_CS_RING_GFX          0
 #define RADEON_CS_RING_COMPUTE      1
-- 
cgit v1.2.3-55-g7522


From 2e1a7674f65eb2c9118ab59d9c8aa9c731da6b85 Mon Sep 17 00:00:00 2001
From: Alex Deucher
Date: Tue, 4 Dec 2012 12:55:37 -0500
Subject: drm/radeon: add new INFO ioctl requests

Add requests to get the number of shader engines (SE) and
the number of SH per SE.  These are needed for geometry
and tesselation shaders in the 3D driver as well as setting
up PA_SC_RASTER_CONFIG on SI asics.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_kms.c | 16 ++++++++++++++++
 include/uapi/drm/radeon_drm.h       |  4 ++++
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index dc781c49b96b..9c312f9afb68 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -361,6 +361,22 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			return -EINVAL;
 		}
 		break;
+	case RADEON_INFO_MAX_SE:
+		if (rdev->family >= CHIP_TAHITI)
+			value = rdev->config.si.max_shader_engines;
+		else if (rdev->family >= CHIP_CAYMAN)
+			value = rdev->config.cayman.max_shader_engines;
+		else if (rdev->family >= CHIP_CEDAR)
+			value = rdev->config.evergreen.num_ses;
+		else
+			value = 1;
+		break;
+	case RADEON_INFO_MAX_SH_PER_SE:
+		if (rdev->family >= CHIP_TAHITI)
+			value = rdev->config.si.max_sh_per_se;
+		else
+			return -EINVAL;
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 0c8a62c543f7..5645a878faec 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -967,6 +967,10 @@ struct drm_radeon_cs {
 #define RADEON_INFO_MAX_PIPES		0x10
 /* timestamp for GL_ARB_timer_query (OpenGL), returns the current GPU clock */
 #define RADEON_INFO_TIMESTAMP		0x11
+/* max shader engines (SE) - needed for geometry shaders, etc. */
+#define RADEON_INFO_MAX_SE		0x12
+/* max SH per SE */
+#define RADEON_INFO_MAX_SH_PER_SE	0x13
 
 struct drm_radeon_info {
 	uint32_t		request;
-- 
cgit v1.2.3-55-g7522


From 6a674e9c75b17e7a88ff15b3c2e269eed54f7cfb Mon Sep 17 00:00:00 2001
From: Joseph Gasparakis
Date: Fri, 7 Dec 2012 14:14:14 +0000
Subject: net: Add support for hardware-offloaded encapsulation

This patch adds support in the kernel for offloading in the NIC Tx and Rx
checksumming for encapsulated packets (such as VXLAN and IP GRE).

For Tx encapsulation offload, the driver will need to set the right bits
in netdev->hw_enc_features. The protocol driver will have to set the
skb->encapsulation bit and populate the inner headers, so the NIC driver will
use those inner headers to calculate the csum in hardware.

For Rx encapsulation offload, the driver will need to set again the
skb->encapsulation flag and the skb->ip_csum to CHECKSUM_UNNECESSARY.
In that case the protocol driver should push the decapsulated packet up
to the stack, again with CHECKSUM_UNNECESSARY. In ether case, the protocol
driver should set the skb->encapsulation flag back to zero. Finally the
protocol driver should have NETIF_F_RXCSUM flag set in its features.

Signed-off-by: Joseph Gasparakis <joseph.gasparakis@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ip.h        |  5 +++
 include/linux/ipv6.h      |  5 +++
 include/linux/netdevice.h |  6 +++
 include/linux/skbuff.h    | 95 ++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/tcp.h       | 10 +++++
 include/linux/udp.h       |  5 +++
 net/core/skbuff.c         |  9 +++++
 7 files changed, 134 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ip.h b/include/linux/ip.h
index 58b82a22a52b..492bc6513533 100644
--- a/include/linux/ip.h
+++ b/include/linux/ip.h
@@ -25,6 +25,11 @@ static inline struct iphdr *ip_hdr(const struct sk_buff *skb)
 	return (struct iphdr *)skb_network_header(skb);
 }
 
+static inline struct iphdr *inner_ip_hdr(const struct sk_buff *skb)
+{
+	return (struct iphdr *)skb_inner_network_header(skb);
+}
+
 static inline struct iphdr *ipip_hdr(const struct sk_buff *skb)
 {
 	return (struct iphdr *)skb_transport_header(skb);
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 12729e966dc9..faed1e357dd6 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -67,6 +67,11 @@ static inline struct ipv6hdr *ipv6_hdr(const struct sk_buff *skb)
 	return (struct ipv6hdr *)skb_network_header(skb);
 }
 
+static inline struct ipv6hdr *inner_ipv6_hdr(const struct sk_buff *skb)
+{
+	return (struct ipv6hdr *)skb_inner_network_header(skb);
+}
+
 static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb)
 {
 	return (struct ipv6hdr *)skb_transport_header(skb);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 18c5dc98f6dc..c6a14d4d1396 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1063,6 +1063,12 @@ struct net_device {
 	netdev_features_t	wanted_features;
 	/* mask of features inheritable by VLAN devices */
 	netdev_features_t	vlan_features;
+	/* mask of features inherited by encapsulating devices
+	 * This field indicates what encapsulation offloads
+	 * the hardware is capable of doing, and drivers will
+	 * need to set them appropriately.
+	 */
+	netdev_features_t	hw_enc_features;
 
 	/* Interface index. Unique device identifier	*/
 	int			ifindex;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f2af494330ab..320e976d5ab8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -376,6 +376,8 @@ typedef unsigned char *sk_buff_data_t;
  *	@mark: Generic packet mark
  *	@dropcount: total number of sk_receive_queue overflows
  *	@vlan_tci: vlan tag control information
+ *	@inner_transport_header: Inner transport layer header (encapsulation)
+ *	@inner_network_header: Network layer header (encapsulation)
  *	@transport_header: Transport layer header
  *	@network_header: Network layer header
  *	@mac_header: Link layer header
@@ -471,7 +473,13 @@ struct sk_buff {
 	__u8			wifi_acked:1;
 	__u8			no_fcs:1;
 	__u8			head_frag:1;
-	/* 8/10 bit hole (depending on ndisc_nodetype presence) */
+	/* Encapsulation protocol and NIC drivers should use
+	 * this flag to indicate to each other if the skb contains
+	 * encapsulated packet or not and maybe use the inner packet
+	 * headers if needed
+	 */
+	__u8			encapsulation:1;
+	/* 7/9 bit hole (depending on ndisc_nodetype presence) */
 	kmemcheck_bitfield_end(flags2);
 
 #ifdef CONFIG_NET_DMA
@@ -486,6 +494,8 @@ struct sk_buff {
 		__u32		avail_size;
 	};
 
+	sk_buff_data_t		inner_transport_header;
+	sk_buff_data_t		inner_network_header;
 	sk_buff_data_t		transport_header;
 	sk_buff_data_t		network_header;
 	sk_buff_data_t		mac_header;
@@ -1435,12 +1445,53 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+static inline void skb_reset_inner_headers(struct sk_buff *skb)
+{
+	skb->inner_network_header = skb->network_header;
+	skb->inner_transport_header = skb->transport_header;
+}
+
 static inline void skb_reset_mac_len(struct sk_buff *skb)
 {
 	skb->mac_len = skb->network_header - skb->mac_header;
 }
 
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
+static inline unsigned char *skb_inner_transport_header(const struct sk_buff
+							*skb)
+{
+	return skb->head + skb->inner_transport_header;
+}
+
+static inline void skb_reset_inner_transport_header(struct sk_buff *skb)
+{
+	skb->inner_transport_header = skb->data - skb->head;
+}
+
+static inline void skb_set_inner_transport_header(struct sk_buff *skb,
+						   const int offset)
+{
+	skb_reset_inner_transport_header(skb);
+	skb->inner_transport_header += offset;
+}
+
+static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb)
+{
+	return skb->head + skb->inner_network_header;
+}
+
+static inline void skb_reset_inner_network_header(struct sk_buff *skb)
+{
+	skb->inner_network_header = skb->data - skb->head;
+}
+
+static inline void skb_set_inner_network_header(struct sk_buff *skb,
+						const int offset)
+{
+	skb_reset_inner_network_header(skb);
+	skb->inner_network_header += offset;
+}
+
 static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
 {
 	return skb->head + skb->transport_header;
@@ -1496,6 +1547,38 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
 }
 
 #else /* NET_SKBUFF_DATA_USES_OFFSET */
+static inline unsigned char *skb_inner_transport_header(const struct sk_buff
+							*skb)
+{
+	return skb->inner_transport_header;
+}
+
+static inline void skb_reset_inner_transport_header(struct sk_buff *skb)
+{
+	skb->inner_transport_header = skb->data;
+}
+
+static inline void skb_set_inner_transport_header(struct sk_buff *skb,
+						   const int offset)
+{
+	skb->inner_transport_header = skb->data + offset;
+}
+
+static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb)
+{
+	return skb->inner_network_header;
+}
+
+static inline void skb_reset_inner_network_header(struct sk_buff *skb)
+{
+	skb->inner_network_header = skb->data;
+}
+
+static inline void skb_set_inner_network_header(struct sk_buff *skb,
+						const int offset)
+{
+	skb->inner_network_header = skb->data + offset;
+}
 
 static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
 {
@@ -1574,11 +1657,21 @@ static inline u32 skb_network_header_len(const struct sk_buff *skb)
 	return skb->transport_header - skb->network_header;
 }
 
+static inline u32 skb_inner_network_header_len(const struct sk_buff *skb)
+{
+	return skb->inner_transport_header - skb->inner_network_header;
+}
+
 static inline int skb_network_offset(const struct sk_buff *skb)
 {
 	return skb_network_header(skb) - skb->data;
 }
 
+static inline int skb_inner_network_offset(const struct sk_buff *skb)
+{
+	return skb_inner_network_header(skb) - skb->data;
+}
+
 static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
 {
 	return pskb_may_pull(skb, skb_network_offset(skb) + len);
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 60b7aac15e0e..4e1d2283e3cc 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -35,6 +35,16 @@ static inline unsigned int tcp_hdrlen(const struct sk_buff *skb)
 	return tcp_hdr(skb)->doff * 4;
 }
 
+static inline struct tcphdr *inner_tcp_hdr(const struct sk_buff *skb)
+{
+	return (struct tcphdr *)skb_inner_transport_header(skb);
+}
+
+static inline unsigned int inner_tcp_hdrlen(const struct sk_buff *skb)
+{
+	return inner_tcp_hdr(skb)->doff * 4;
+}
+
 static inline unsigned int tcp_optlen(const struct sk_buff *skb)
 {
 	return (tcp_hdr(skb)->doff - 5) * 4;
diff --git a/include/linux/udp.h b/include/linux/udp.h
index 0b67d7793520..9d81de123c90 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -27,6 +27,11 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb)
 	return (struct udphdr *)skb_transport_header(skb);
 }
 
+static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb)
+{
+	return (struct udphdr *)skb_inner_transport_header(skb);
+}
+
 #define UDP_HTABLE_SIZE_MIN		(CONFIG_BASE_SMALL ? 128 : 256)
 
 static inline int udp_hashfn(struct net *net, unsigned num, unsigned mask)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 880722e22cc5..ccbabf565732 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -682,11 +682,14 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->transport_header	= old->transport_header;
 	new->network_header	= old->network_header;
 	new->mac_header		= old->mac_header;
+	new->inner_transport_header = old->inner_transport_header;
+	new->inner_network_header = old->inner_transport_header;
 	skb_dst_copy(new, old);
 	new->rxhash		= old->rxhash;
 	new->ooo_okay		= old->ooo_okay;
 	new->l4_rxhash		= old->l4_rxhash;
 	new->no_fcs		= old->no_fcs;
+	new->encapsulation	= old->encapsulation;
 #ifdef CONFIG_XFRM
 	new->sp			= secpath_get(old->sp);
 #endif
@@ -892,6 +895,8 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->network_header   += offset;
 	if (skb_mac_header_was_set(new))
 		new->mac_header	      += offset;
+	new->inner_transport_header += offset;
+	new->inner_network_header   += offset;
 #endif
 	skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
 	skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
@@ -1089,6 +1094,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 	skb->network_header   += off;
 	if (skb_mac_header_was_set(skb))
 		skb->mac_header += off;
+	skb->inner_transport_header += off;
+	skb->inner_network_header += off;
 	/* Only adjust this if it actually is csum_start rather than csum */
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		skb->csum_start += nhead;
@@ -1188,6 +1195,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 	n->network_header   += off;
 	if (skb_mac_header_was_set(skb))
 		n->mac_header += off;
+	n->inner_transport_header += off;
+	n->inner_network_header	   += off;
 #endif
 
 	return n;
-- 
cgit v1.2.3-55-g7522


From 986a4f4d452dec004697f667439d27c3fda9c928 Mon Sep 17 00:00:00 2001
From: Jason Wang
Date: Fri, 7 Dec 2012 07:04:56 +0000
Subject: virtio_net: multiqueue support

This patch adds the multiqueue (VIRTIO_NET_F_MQ) support to virtio_net
driver. VIRTIO_NET_F_MQ capable device could allow the driver to do packet
transmission and reception through multiple queue pairs and does the packet
steering to get better performance. By default, one one queue pair is used, user
could change the number of queue pairs by ethtool in the next patch.

When multiple queue pairs is used and the number of queue pairs is equal to the
number of vcpus. Driver does the following optimizations to implement per-cpu
virt queue pairs:

- select the txq based on the smp processor id.
- smp affinity hint to the cpu that owns the queue pairs.

This could be used with the flow steering support of the device to guarantee the
packets of a single flow is handled by the same cpu.

Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c        | 473 +++++++++++++++++++++++++++++++---------
 include/uapi/linux/virtio_net.h |  27 +++
 2 files changed, 402 insertions(+), 98 deletions(-)

(limited to 'include')

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 02a71021565e..c0830488a390 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -58,6 +58,9 @@ struct send_queue {
 
 	/* TX: fragments + linear part + virtio header */
 	struct scatterlist sg[MAX_SKB_FRAGS + 2];
+
+	/* Name of the send queue: output.$index */
+	char name[40];
 };
 
 /* Internal representation of a receive virtqueue */
@@ -75,22 +78,34 @@ struct receive_queue {
 
 	/* RX: fragments + linear part + virtio header */
 	struct scatterlist sg[MAX_SKB_FRAGS + 2];
+
+	/* Name of this receive queue: input.$index */
+	char name[40];
 };
 
 struct virtnet_info {
 	struct virtio_device *vdev;
 	struct virtqueue *cvq;
 	struct net_device *dev;
-	struct send_queue sq;
-	struct receive_queue rq;
+	struct send_queue *sq;
+	struct receive_queue *rq;
 	unsigned int status;
 
+	/* Max # of queue pairs supported by the device */
+	u16 max_queue_pairs;
+
+	/* # of queue pairs currently used by the driver */
+	u16 curr_queue_pairs;
+
 	/* I like... big packets and I cannot lie! */
 	bool big_packets;
 
 	/* Host will merge rx buffers for big packets (shake it! shake it!) */
 	bool mergeable_rx_bufs;
 
+	/* Has control virtqueue */
+	bool has_cvq;
+
 	/* enable config space updates */
 	bool config_enable;
 
@@ -105,6 +120,9 @@ struct virtnet_info {
 
 	/* Lock for config space updates */
 	struct mutex config_lock;
+
+	/* Does the affinity hint is set for virtqueues? */
+	bool affinity_hint_set;
 };
 
 struct skb_vnet_hdr {
@@ -125,6 +143,29 @@ struct padded_vnet_hdr {
 	char padding[6];
 };
 
+/* Converting between virtqueue no. and kernel tx/rx queue no.
+ * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
+ */
+static int vq2txq(struct virtqueue *vq)
+{
+	return (virtqueue_get_queue_index(vq) - 1) / 2;
+}
+
+static int txq2vq(int txq)
+{
+	return txq * 2 + 1;
+}
+
+static int vq2rxq(struct virtqueue *vq)
+{
+	return virtqueue_get_queue_index(vq) / 2;
+}
+
+static int rxq2vq(int rxq)
+{
+	return rxq * 2;
+}
+
 static inline struct skb_vnet_hdr *skb_vnet_hdr(struct sk_buff *skb)
 {
 	return (struct skb_vnet_hdr *)skb->cb;
@@ -165,7 +206,7 @@ static void skb_xmit_done(struct virtqueue *vq)
 	virtqueue_disable_cb(vq);
 
 	/* We were probably waiting for more output buffers. */
-	netif_wake_queue(vi->dev);
+	netif_wake_subqueue(vi->dev, vq2txq(vq));
 }
 
 static void set_skb_frag(struct sk_buff *skb, struct page *page,
@@ -502,7 +543,7 @@ static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
 static void skb_recv_done(struct virtqueue *rvq)
 {
 	struct virtnet_info *vi = rvq->vdev->priv;
-	struct receive_queue *rq = &vi->rq;
+	struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];
 
 	/* Schedule NAPI, Suppress further interrupts if successful. */
 	if (napi_schedule_prep(&rq->napi)) {
@@ -532,15 +573,21 @@ static void refill_work(struct work_struct *work)
 	struct virtnet_info *vi =
 		container_of(work, struct virtnet_info, refill.work);
 	bool still_empty;
+	int i;
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		struct receive_queue *rq = &vi->rq[i];
 
-	napi_disable(&vi->rq.napi);
-	still_empty = !try_fill_recv(&vi->rq, GFP_KERNEL);
-	virtnet_napi_enable(&vi->rq);
+		napi_disable(&rq->napi);
+		still_empty = !try_fill_recv(rq, GFP_KERNEL);
+		virtnet_napi_enable(rq);
 
-	/* In theory, this can happen: if we don't get any buffers in
-	 * we will *never* try to fill again. */
-	if (still_empty)
-		schedule_delayed_work(&vi->refill, HZ/2);
+		/* In theory, this can happen: if we don't get any buffers in
+		 * we will *never* try to fill again.
+		 */
+		if (still_empty)
+			schedule_delayed_work(&vi->refill, HZ/2);
+	}
 }
 
 static int virtnet_poll(struct napi_struct *napi, int budget)
@@ -578,6 +625,21 @@ again:
 	return received;
 }
 
+static int virtnet_open(struct net_device *dev)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		/* Make sure we have some buffers: if oom use wq. */
+		if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+			schedule_delayed_work(&vi->refill, 0);
+		virtnet_napi_enable(&vi->rq[i]);
+	}
+
+	return 0;
+}
+
 static unsigned int free_old_xmit_skbs(struct send_queue *sq)
 {
 	struct sk_buff *skb;
@@ -650,7 +712,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
-	struct send_queue *sq = &vi->sq;
+	int qnum = skb_get_queue_mapping(skb);
+	struct send_queue *sq = &vi->sq[qnum];
 	int capacity;
 
 	/* Free up any pending old buffers before queueing new ones. */
@@ -664,13 +727,14 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (likely(capacity == -ENOMEM)) {
 			if (net_ratelimit())
 				dev_warn(&dev->dev,
-					 "TX queue failure: out of memory\n");
+					 "TXQ (%d) failure: out of memory\n",
+					 qnum);
 		} else {
 			dev->stats.tx_fifo_errors++;
 			if (net_ratelimit())
 				dev_warn(&dev->dev,
-					 "Unexpected TX queue failure: %d\n",
-					 capacity);
+					 "Unexpected TXQ (%d) failure: %d\n",
+					 qnum, capacity);
 		}
 		dev->stats.tx_dropped++;
 		kfree_skb(skb);
@@ -685,12 +749,12 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Apparently nice girls don't return TX_BUSY; stop the queue
 	 * before it gets out of hand.  Naturally, this wastes entries. */
 	if (capacity < 2+MAX_SKB_FRAGS) {
-		netif_stop_queue(dev);
+		netif_stop_subqueue(dev, qnum);
 		if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
 			/* More just got used, free them then recheck. */
 			capacity += free_old_xmit_skbs(sq);
 			if (capacity >= 2+MAX_SKB_FRAGS) {
-				netif_start_queue(dev);
+				netif_start_subqueue(dev, qnum);
 				virtqueue_disable_cb(sq->vq);
 			}
 		}
@@ -758,23 +822,13 @@ static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev,
 static void virtnet_netpoll(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
+	int i;
 
-	napi_schedule(&vi->rq.napi);
+	for (i = 0; i < vi->curr_queue_pairs; i++)
+		napi_schedule(&vi->rq[i].napi);
 }
 #endif
 
-static int virtnet_open(struct net_device *dev)
-{
-	struct virtnet_info *vi = netdev_priv(dev);
-
-	/* Make sure we have some buffers: if oom use wq. */
-	if (!try_fill_recv(&vi->rq, GFP_KERNEL))
-		schedule_delayed_work(&vi->refill, 0);
-
-	virtnet_napi_enable(&vi->rq);
-	return 0;
-}
-
 /*
  * Send command via the control virtqueue and check status.  Commands
  * supported by the hypervisor, as indicated by feature bits, should
@@ -830,13 +884,39 @@ static void virtnet_ack_link_announce(struct virtnet_info *vi)
 	rtnl_unlock();
 }
 
+static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
+{
+	struct scatterlist sg;
+	struct virtio_net_ctrl_mq s;
+	struct net_device *dev = vi->dev;
+
+	if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
+		return 0;
+
+	s.virtqueue_pairs = queue_pairs;
+	sg_init_one(&sg, &s, sizeof(s));
+
+	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
+				  VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg, 1, 0)){
+		dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n",
+			 queue_pairs);
+		return -EINVAL;
+	} else
+		vi->curr_queue_pairs = queue_pairs;
+
+	return 0;
+}
+
 static int virtnet_close(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
+	int i;
 
 	/* Make sure refill_work doesn't re-enable napi! */
 	cancel_delayed_work_sync(&vi->refill);
-	napi_disable(&vi->rq.napi);
+
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		napi_disable(&vi->rq[i].napi);
 
 	return 0;
 }
@@ -943,13 +1023,41 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev, u16 vid)
 	return 0;
 }
 
+static void virtnet_set_affinity(struct virtnet_info *vi, bool set)
+{
+	int i;
+
+	/* In multiqueue mode, when the number of cpu is equal to the number of
+	 * queue pairs, we let the queue pairs to be private to one cpu by
+	 * setting the affinity hint to eliminate the contention.
+	 */
+	if ((vi->curr_queue_pairs == 1 ||
+	     vi->max_queue_pairs != num_online_cpus()) && set) {
+		if (vi->affinity_hint_set)
+			set = false;
+		else
+			return;
+	}
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		int cpu = set ? i : -1;
+		virtqueue_set_affinity(vi->rq[i].vq, cpu);
+		virtqueue_set_affinity(vi->sq[i].vq, cpu);
+	}
+
+	if (set)
+		vi->affinity_hint_set = true;
+	else
+		vi->affinity_hint_set = false;
+}
+
 static void virtnet_get_ringparam(struct net_device *dev,
 				struct ethtool_ringparam *ring)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 
-	ring->rx_max_pending = virtqueue_get_vring_size(vi->rq.vq);
-	ring->tx_max_pending = virtqueue_get_vring_size(vi->sq.vq);
+	ring->rx_max_pending = virtqueue_get_vring_size(vi->rq[0].vq);
+	ring->tx_max_pending = virtqueue_get_vring_size(vi->sq[0].vq);
 	ring->rx_pending = ring->rx_max_pending;
 	ring->tx_pending = ring->tx_max_pending;
 }
@@ -984,6 +1092,21 @@ static int virtnet_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
+/* To avoid contending a lock hold by a vcpu who would exit to host, select the
+ * txq based on the processor id.
+ * TODO: handle cpu hotplug.
+ */
+static u16 virtnet_select_queue(struct net_device *dev, struct sk_buff *skb)
+{
+	int txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) :
+		  smp_processor_id();
+
+	while (unlikely(txq >= dev->real_num_tx_queues))
+		txq -= dev->real_num_tx_queues;
+
+	return txq;
+}
+
 static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
@@ -995,6 +1118,7 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_get_stats64     = virtnet_stats,
 	.ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid,
+	.ndo_select_queue     = virtnet_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = virtnet_netpoll,
 #endif
@@ -1030,10 +1154,10 @@ static void virtnet_config_changed_work(struct work_struct *work)
 
 	if (vi->status & VIRTIO_NET_S_LINK_UP) {
 		netif_carrier_on(vi->dev);
-		netif_wake_queue(vi->dev);
+		netif_tx_wake_all_queues(vi->dev);
 	} else {
 		netif_carrier_off(vi->dev);
-		netif_stop_queue(vi->dev);
+		netif_tx_stop_all_queues(vi->dev);
 	}
 done:
 	mutex_unlock(&vi->config_lock);
@@ -1046,48 +1170,203 @@ static void virtnet_config_changed(struct virtio_device *vdev)
 	schedule_work(&vi->config_work);
 }
 
+static void virtnet_free_queues(struct virtnet_info *vi)
+{
+	kfree(vi->rq);
+	kfree(vi->sq);
+}
+
+static void free_receive_bufs(struct virtnet_info *vi)
+{
+	int i;
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		while (vi->rq[i].pages)
+			__free_pages(get_a_page(&vi->rq[i], GFP_KERNEL), 0);
+	}
+}
+
+static void free_unused_bufs(struct virtnet_info *vi)
+{
+	void *buf;
+	int i;
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		struct virtqueue *vq = vi->sq[i].vq;
+		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
+			dev_kfree_skb(buf);
+	}
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		struct virtqueue *vq = vi->rq[i].vq;
+
+		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
+			if (vi->mergeable_rx_bufs || vi->big_packets)
+				give_pages(&vi->rq[i], buf);
+			else
+				dev_kfree_skb(buf);
+			--vi->rq[i].num;
+		}
+		BUG_ON(vi->rq[i].num != 0);
+	}
+}
+
 static void virtnet_del_vqs(struct virtnet_info *vi)
 {
 	struct virtio_device *vdev = vi->vdev;
 
+	virtnet_set_affinity(vi, false);
+
 	vdev->config->del_vqs(vdev);
+
+	virtnet_free_queues(vi);
 }
 
-static int init_vqs(struct virtnet_info *vi)
+static int virtnet_find_vqs(struct virtnet_info *vi)
 {
-	struct virtqueue *vqs[3];
-	vq_callback_t *callbacks[] = { skb_recv_done, skb_xmit_done, NULL};
-	const char *names[] = { "input", "output", "control" };
-	int nvqs, err;
-
-	/* We expect two virtqueues, receive then send,
-	 * and optionally control. */
-	nvqs = virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ? 3 : 2;
-
-	err = vi->vdev->config->find_vqs(vi->vdev, nvqs, vqs, callbacks, names);
-	if (err)
-		return err;
+	vq_callback_t **callbacks;
+	struct virtqueue **vqs;
+	int ret = -ENOMEM;
+	int i, total_vqs;
+	const char **names;
+
+	/* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
+	 * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by
+	 * possible control vq.
+	 */
+	total_vqs = vi->max_queue_pairs * 2 +
+		    virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ);
+
+	/* Allocate space for find_vqs parameters */
+	vqs = kzalloc(total_vqs * sizeof(*vqs), GFP_KERNEL);
+	if (!vqs)
+		goto err_vq;
+	callbacks = kmalloc(total_vqs * sizeof(*callbacks), GFP_KERNEL);
+	if (!callbacks)
+		goto err_callback;
+	names = kmalloc(total_vqs * sizeof(*names), GFP_KERNEL);
+	if (!names)
+		goto err_names;
+
+	/* Parameters for control virtqueue, if any */
+	if (vi->has_cvq) {
+		callbacks[total_vqs - 1] = NULL;
+		names[total_vqs - 1] = "control";
+	}
 
-	vi->rq.vq = vqs[0];
-	vi->sq.vq = vqs[1];
+	/* Allocate/initialize parameters for send/receive virtqueues */
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		callbacks[rxq2vq(i)] = skb_recv_done;
+		callbacks[txq2vq(i)] = skb_xmit_done;
+		sprintf(vi->rq[i].name, "input.%d", i);
+		sprintf(vi->sq[i].name, "output.%d", i);
+		names[rxq2vq(i)] = vi->rq[i].name;
+		names[txq2vq(i)] = vi->sq[i].name;
+	}
 
-	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
-		vi->cvq = vqs[2];
+	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
+					 names);
+	if (ret)
+		goto err_find;
 
+	if (vi->has_cvq) {
+		vi->cvq = vqs[total_vqs - 1];
 		if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
 			vi->dev->features |= NETIF_F_HW_VLAN_FILTER;
 	}
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		vi->rq[i].vq = vqs[rxq2vq(i)];
+		vi->sq[i].vq = vqs[txq2vq(i)];
+	}
+
+	kfree(names);
+	kfree(callbacks);
+	kfree(vqs);
+
 	return 0;
+
+err_find:
+	kfree(names);
+err_names:
+	kfree(callbacks);
+err_callback:
+	kfree(vqs);
+err_vq:
+	return ret;
+}
+
+static int virtnet_alloc_queues(struct virtnet_info *vi)
+{
+	int i;
+
+	vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL);
+	if (!vi->sq)
+		goto err_sq;
+	vi->rq = kzalloc(sizeof(*vi->rq) * vi->max_queue_pairs, GFP_KERNEL);
+	if (!vi->sq)
+		goto err_rq;
+
+	INIT_DELAYED_WORK(&vi->refill, refill_work);
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		vi->rq[i].pages = NULL;
+		netif_napi_add(vi->dev, &vi->rq[i].napi, virtnet_poll,
+			       napi_weight);
+
+		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
+		sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
+	}
+
+	return 0;
+
+err_rq:
+	kfree(vi->sq);
+err_sq:
+	return -ENOMEM;
+}
+
+static int init_vqs(struct virtnet_info *vi)
+{
+	int ret;
+
+	/* Allocate send & receive queues */
+	ret = virtnet_alloc_queues(vi);
+	if (ret)
+		goto err;
+
+	ret = virtnet_find_vqs(vi);
+	if (ret)
+		goto err_free;
+
+	virtnet_set_affinity(vi, true);
+	return 0;
+
+err_free:
+	virtnet_free_queues(vi);
+err:
+	return ret;
 }
 
 static int virtnet_probe(struct virtio_device *vdev)
 {
-	int err;
+	int i, err;
 	struct net_device *dev;
 	struct virtnet_info *vi;
+	u16 max_queue_pairs;
+
+	/* Find if host supports multiqueue virtio_net device */
+	err = virtio_config_val(vdev, VIRTIO_NET_F_MQ,
+				offsetof(struct virtio_net_config,
+				max_virtqueue_pairs), &max_queue_pairs);
+
+	/* We need at least 2 queue's */
+	if (err || max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||
+	    max_queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX ||
+	    !virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
+		max_queue_pairs = 1;
 
 	/* Allocate ourselves a network device with room for our info */
-	dev = alloc_etherdev(sizeof(struct virtnet_info));
+	dev = alloc_etherdev_mq(sizeof(struct virtnet_info), max_queue_pairs);
 	if (!dev)
 		return -ENOMEM;
 
@@ -1133,22 +1412,17 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 	/* Set up our device-specific information */
 	vi = netdev_priv(dev);
-	netif_napi_add(dev, &vi->rq.napi, virtnet_poll, napi_weight);
 	vi->dev = dev;
 	vi->vdev = vdev;
 	vdev->priv = vi;
-	vi->rq.pages = NULL;
 	vi->stats = alloc_percpu(struct virtnet_stats);
 	err = -ENOMEM;
 	if (vi->stats == NULL)
 		goto free;
 
-	INIT_DELAYED_WORK(&vi->refill, refill_work);
 	mutex_init(&vi->config_lock);
 	vi->config_enable = true;
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
-	sg_init_table(vi->rq.sg, ARRAY_SIZE(vi->rq.sg));
-	sg_init_table(vi->sq.sg, ARRAY_SIZE(vi->sq.sg));
 
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
@@ -1159,10 +1433,21 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
 		vi->mergeable_rx_bufs = true;
 
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
+		vi->has_cvq = true;
+
+	/* Use single tx/rx queue pair as default */
+	vi->curr_queue_pairs = 1;
+	vi->max_queue_pairs = max_queue_pairs;
+
+	/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
 	err = init_vqs(vi);
 	if (err)
 		goto free_stats;
 
+	netif_set_real_num_tx_queues(dev, 1);
+	netif_set_real_num_rx_queues(dev, 1);
+
 	err = register_netdev(dev);
 	if (err) {
 		pr_debug("virtio_net: registering device failed\n");
@@ -1170,12 +1455,15 @@ static int virtnet_probe(struct virtio_device *vdev)
 	}
 
 	/* Last of all, set up some receive buffers. */
-	try_fill_recv(&vi->rq, GFP_KERNEL);
-
-	/* If we didn't even get one input buffer, we're useless. */
-	if (vi->rq.num == 0) {
-		err = -ENOMEM;
-		goto unregister;
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		try_fill_recv(&vi->rq[i], GFP_KERNEL);
+
+		/* If we didn't even get one input buffer, we're useless. */
+		if (vi->rq[i].num == 0) {
+			free_unused_bufs(vi);
+			err = -ENOMEM;
+			goto free_recv_bufs;
+		}
 	}
 
 	/* Assume link up if device can't report link status,
@@ -1188,12 +1476,16 @@ static int virtnet_probe(struct virtio_device *vdev)
 		netif_carrier_on(dev);
 	}
 
-	pr_debug("virtnet: registered device %s\n", dev->name);
+	pr_debug("virtnet: registered device %s with %d RX and TX vq's\n",
+		 dev->name, max_queue_pairs);
+
 	return 0;
 
-unregister:
+free_recv_bufs:
+	free_receive_bufs(vi);
 	unregister_netdev(dev);
 free_vqs:
+	cancel_delayed_work_sync(&vi->refill);
 	virtnet_del_vqs(vi);
 free_stats:
 	free_percpu(vi->stats);
@@ -1202,28 +1494,6 @@ free:
 	return err;
 }
 
-static void free_unused_bufs(struct virtnet_info *vi)
-{
-	void *buf;
-	while (1) {
-		buf = virtqueue_detach_unused_buf(vi->sq.vq);
-		if (!buf)
-			break;
-		dev_kfree_skb(buf);
-	}
-	while (1) {
-		buf = virtqueue_detach_unused_buf(vi->rq.vq);
-		if (!buf)
-			break;
-		if (vi->mergeable_rx_bufs || vi->big_packets)
-			give_pages(&vi->rq, buf);
-		else
-			dev_kfree_skb(buf);
-		--vi->rq.num;
-	}
-	BUG_ON(vi->rq.num != 0);
-}
-
 static void remove_vq_common(struct virtnet_info *vi)
 {
 	vi->vdev->config->reset(vi->vdev);
@@ -1231,10 +1501,9 @@ static void remove_vq_common(struct virtnet_info *vi)
 	/* Free unused buffers in both send and recv, if any. */
 	free_unused_bufs(vi);
 
-	virtnet_del_vqs(vi);
+	free_receive_bufs(vi);
 
-	while (vi->rq.pages)
-		__free_pages(get_a_page(&vi->rq, GFP_KERNEL), 0);
+	virtnet_del_vqs(vi);
 }
 
 static void virtnet_remove(struct virtio_device *vdev)
@@ -1260,6 +1529,7 @@ static void virtnet_remove(struct virtio_device *vdev)
 static int virtnet_freeze(struct virtio_device *vdev)
 {
 	struct virtnet_info *vi = vdev->priv;
+	int i;
 
 	/* Prevent config work handler from accessing the device */
 	mutex_lock(&vi->config_lock);
@@ -1270,7 +1540,10 @@ static int virtnet_freeze(struct virtio_device *vdev)
 	cancel_delayed_work_sync(&vi->refill);
 
 	if (netif_running(vi->dev))
-		napi_disable(&vi->rq.napi);
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			napi_disable(&vi->rq[i].napi);
+			netif_napi_del(&vi->rq[i].napi);
+		}
 
 	remove_vq_common(vi);
 
@@ -1282,24 +1555,28 @@ static int virtnet_freeze(struct virtio_device *vdev)
 static int virtnet_restore(struct virtio_device *vdev)
 {
 	struct virtnet_info *vi = vdev->priv;
-	int err;
+	int err, i;
 
 	err = init_vqs(vi);
 	if (err)
 		return err;
 
 	if (netif_running(vi->dev))
-		virtnet_napi_enable(&vi->rq);
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			virtnet_napi_enable(&vi->rq[i]);
 
 	netif_device_attach(vi->dev);
 
-	if (!try_fill_recv(&vi->rq, GFP_KERNEL))
-		schedule_delayed_work(&vi->refill, 0);
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+			schedule_delayed_work(&vi->refill, 0);
 
 	mutex_lock(&vi->config_lock);
 	vi->config_enable = true;
 	mutex_unlock(&vi->config_lock);
 
+	virtnet_set_queues(vi, vi->curr_queue_pairs);
+
 	return 0;
 }
 #endif
@@ -1317,7 +1594,7 @@ static unsigned int features[] = {
 	VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO,
 	VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
 	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
-	VIRTIO_NET_F_GUEST_ANNOUNCE,
+	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,
 };
 
 static struct virtio_driver virtio_net_driver = {
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 2470f541af50..848e3584d7c8 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -51,6 +51,8 @@
 #define VIRTIO_NET_F_CTRL_RX_EXTRA 20	/* Extra RX mode control support */
 #define VIRTIO_NET_F_GUEST_ANNOUNCE 21	/* Guest can announce device on the
 					 * network */
+#define VIRTIO_NET_F_MQ	22	/* Device supports Receive Flow
+					 * Steering */
 
 #define VIRTIO_NET_S_LINK_UP	1	/* Link is up */
 #define VIRTIO_NET_S_ANNOUNCE	2	/* Announcement is needed */
@@ -60,6 +62,11 @@ struct virtio_net_config {
 	__u8 mac[6];
 	/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
 	__u16 status;
+	/* Maximum number of each of transmit and receive queues;
+	 * see VIRTIO_NET_F_MQ and VIRTIO_NET_CTRL_MQ.
+	 * Legal values are between 1 and 0x8000
+	 */
+	__u16 max_virtqueue_pairs;
 } __attribute__((packed));
 
 /* This is the first element of the scatter-gather list.  If you don't
@@ -166,4 +173,24 @@ struct virtio_net_ctrl_mac {
 #define VIRTIO_NET_CTRL_ANNOUNCE       3
  #define VIRTIO_NET_CTRL_ANNOUNCE_ACK         0
 
+/*
+ * Control Receive Flow Steering
+ *
+ * The command VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET
+ * enables Receive Flow Steering, specifying the number of the transmit and
+ * receive queues that will be used. After the command is consumed and acked by
+ * the device, the device will not steer new packets on receive virtqueues
+ * other than specified nor read from transmit virtqueues other than specified.
+ * Accordingly, driver should not transmit new packets  on virtqueues other than
+ * specified.
+ */
+struct virtio_net_ctrl_mq {
+	u16 virtqueue_pairs;
+};
+
+#define VIRTIO_NET_CTRL_MQ   4
+ #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET        0
+ #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN        1
+ #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX        0x8000
+
 #endif /* _LINUX_VIRTIO_NET_H */
-- 
cgit v1.2.3-55-g7522


From be2f6f5a7833b99bdee97c4b877dcd2afc6cdd00 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Sun, 9 Dec 2012 15:40:30 +0100
Subject: mfd: wm5102: Add readback of DSP status 3 register

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/wm5102-tables.c           | 2 ++
 include/linux/mfd/arizona/registers.h | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/wm5102-tables.c b/drivers/mfd/wm5102-tables.c
index 005de63d01d6..8844b2f9de87 100644
--- a/drivers/mfd/wm5102-tables.c
+++ b/drivers/mfd/wm5102-tables.c
@@ -2336,6 +2336,7 @@ static bool wm5102_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP1_CLOCKING_1:
 	case ARIZONA_DSP1_STATUS_1:
 	case ARIZONA_DSP1_STATUS_2:
+	case ARIZONA_DSP1_STATUS_3:
 		return true;
 	default:
 		return false;
@@ -2386,6 +2387,7 @@ static bool wm5102_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_AOD_IRQ_RAW_STATUS:
 	case ARIZONA_DSP1_STATUS_1:
 	case ARIZONA_DSP1_STATUS_2:
+	case ARIZONA_DSP1_STATUS_3:
 	case ARIZONA_HEADPHONE_DETECT_2:
 	case ARIZONA_MIC_DETECT_3:
 		return true;
diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index 7671a287dfee..81bca23c9a92 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -979,6 +979,7 @@
 #define ARIZONA_DSP1_CLOCKING_1                  0x1101
 #define ARIZONA_DSP1_STATUS_1                    0x1104
 #define ARIZONA_DSP1_STATUS_2                    0x1105
+#define ARIZONA_DSP1_STATUS_3                    0x1106
 #define ARIZONA_DSP2_CONTROL_1                   0x1200
 #define ARIZONA_DSP2_CLOCKING_1                  0x1201
 #define ARIZONA_DSP2_STATUS_1                    0x1204
-- 
cgit v1.2.3-55-g7522


From 20154fd3706d603216f462854862203d231c6086 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Sat, 1 Dec 2012 14:24:40 +0100
Subject: asm-generic/mmu.h: Remove unused vmlist field from mm_context_t

Nothing is using the vmlist field in mm_context_t anymore. It has been removed
from the non-generic versions over 3 years ago 8feae1311 ("NOMMU: Make VMAs per
MM as for MMU-mode linux").

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 include/asm-generic/mmu.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/mmu.h b/include/asm-generic/mmu.h
index 4f4aa56d6b52..a67ae0a91599 100644
--- a/include/asm-generic/mmu.h
+++ b/include/asm-generic/mmu.h
@@ -7,7 +7,6 @@
  */
 #ifndef __ASSEMBLY__
 typedef struct {
-	struct vm_list_struct	*vmlist;
 	unsigned long		end_brk;
 } mm_context_t;
 #endif
-- 
cgit v1.2.3-55-g7522


From 9d2951bcd96ff2d5a88022ad3b4aebd6357d65d7 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen
Date: Sat, 1 Dec 2012 14:24:41 +0100
Subject: asm-generic/mmu.h: Add support for FDPIC

No-MMU architectures often have support for FDPIC binaries. FDPIC support
requires two additional fields in the mm_context_t struct. This patch adds these
fields to the generic mm_context_t definition if support for FDPIC binaries is
enabled. This allows to use the generic mmu.h for a few more architectures.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 include/asm-generic/mmu.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/mmu.h b/include/asm-generic/mmu.h
index a67ae0a91599..0ed3f1cfb854 100644
--- a/include/asm-generic/mmu.h
+++ b/include/asm-generic/mmu.h
@@ -8,6 +8,11 @@
 #ifndef __ASSEMBLY__
 typedef struct {
 	unsigned long		end_brk;
+
+#ifdef CONFIG_BINFMT_ELF_FDPIC
+	unsigned long		exec_fdpic_loadmap;
+	unsigned long		interp_fdpic_loadmap;
+#endif
 } mm_context_t;
 #endif
 
-- 
cgit v1.2.3-55-g7522


From 97a875cbdf89a4638eea57c2b456c7cc4e3e8b21 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst
Date: Wed, 28 Nov 2012 11:25:44 +0000
Subject: drm/ttm: remove no_wait_reserve, v3

All items on the lru list are always reservable, so this is a stupid
thing to keep. Not only that, it is used in a way which would
guarantee deadlocks if it were ever to be set to block on reserve.

This is a lot of churn, but mostly because of the removal of the
argument which can be nested arbitrarily deeply in many places.

No change of code in this patch except removal of the no_wait_reserve
argument, the previous patch removed the use of no_wait_reserve.

v2:
 - Warn if -EBUSY is returned on reservation, all objects on the list
   should be reservable. Adjusted patch slightly due to conflicts.
v3:
 - Focus on no_wait_reserve removal only.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/ast/ast_ttm.c            | 10 +++---
 drivers/gpu/drm/cirrus/cirrus_ttm.c      | 10 +++---
 drivers/gpu/drm/mgag200/mgag200_ttm.c    | 10 +++---
 drivers/gpu/drm/nouveau/nouveau_bo.c     | 55 +++++++++++++++-----------------
 drivers/gpu/drm/nouveau/nouveau_bo.h     |  2 +-
 drivers/gpu/drm/nouveau/nouveau_gem.c    |  2 +-
 drivers/gpu/drm/radeon/radeon_object.c   |  8 ++---
 drivers/gpu/drm/radeon/radeon_ttm.c      | 31 +++++++++---------
 drivers/gpu/drm/ttm/ttm_bo.c             | 46 +++++++++++++-------------
 drivers/gpu/drm/ttm/ttm_bo_util.c        |  6 ++--
 drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c   | 13 ++++----
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c  |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c |  2 +-
 include/drm/ttm/ttm_bo_api.h             |  3 +-
 include/drm/ttm/ttm_bo_driver.h          | 19 ++++-------
 15 files changed, 107 insertions(+), 114 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 0a54f65a8ebb..3602731a6112 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -186,11 +186,11 @@ static void ast_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *
 
 static int ast_bo_move(struct ttm_buffer_object *bo,
 		       bool evict, bool interruptible,
-		       bool no_wait_reserve, bool no_wait_gpu,
+		       bool no_wait_gpu,
 		       struct ttm_mem_reg *new_mem)
 {
 	int r;
-	r = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
+	r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
 	return r;
 }
 
@@ -383,7 +383,7 @@ int ast_bo_pin(struct ast_bo *bo, u32 pl_flag, u64 *gpu_addr)
 	ast_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
 		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
-	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false, false);
+	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
 
@@ -406,7 +406,7 @@ int ast_bo_unpin(struct ast_bo *bo)
 
 	for (i = 0; i < bo->placement.num_placement ; i++)
 		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
-	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false, false);
+	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
 
@@ -431,7 +431,7 @@ int ast_bo_push_sysram(struct ast_bo *bo)
 	for (i = 0; i < bo->placement.num_placement ; i++)
 		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
 
-	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false, false);
+	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret) {
 		DRM_ERROR("pushing to VRAM failed\n");
 		return ret;
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 90d770143cc2..1413a26e4905 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -186,11 +186,11 @@ static void cirrus_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_re
 
 static int cirrus_bo_move(struct ttm_buffer_object *bo,
 		       bool evict, bool interruptible,
-		       bool no_wait_reserve, bool no_wait_gpu,
+		       bool no_wait_gpu,
 		       struct ttm_mem_reg *new_mem)
 {
 	int r;
-	r = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
+	r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
 	return r;
 }
 
@@ -388,7 +388,7 @@ int cirrus_bo_pin(struct cirrus_bo *bo, u32 pl_flag, u64 *gpu_addr)
 	cirrus_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
 		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
-	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false, false);
+	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
 
@@ -411,7 +411,7 @@ int cirrus_bo_unpin(struct cirrus_bo *bo)
 
 	for (i = 0; i < bo->placement.num_placement ; i++)
 		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
-	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false, false);
+	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
 
@@ -436,7 +436,7 @@ int cirrus_bo_push_sysram(struct cirrus_bo *bo)
 	for (i = 0; i < bo->placement.num_placement ; i++)
 		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
 
-	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false, false);
+	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret) {
 		DRM_ERROR("pushing to VRAM failed\n");
 		return ret;
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 49d60a620122..8fc9d9201945 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -186,11 +186,11 @@ static void mgag200_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_r
 
 static int mgag200_bo_move(struct ttm_buffer_object *bo,
 		       bool evict, bool interruptible,
-		       bool no_wait_reserve, bool no_wait_gpu,
+		       bool no_wait_gpu,
 		       struct ttm_mem_reg *new_mem)
 {
 	int r;
-	r = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
+	r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
 	return r;
 }
 
@@ -382,7 +382,7 @@ int mgag200_bo_pin(struct mgag200_bo *bo, u32 pl_flag, u64 *gpu_addr)
 	mgag200_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
 		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
-	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false, false);
+	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
 
@@ -405,7 +405,7 @@ int mgag200_bo_unpin(struct mgag200_bo *bo)
 
 	for (i = 0; i < bo->placement.num_placement ; i++)
 		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
-	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false, false);
+	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
 
@@ -430,7 +430,7 @@ int mgag200_bo_push_sysram(struct mgag200_bo *bo)
 	for (i = 0; i < bo->placement.num_placement ; i++)
 		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
 
-	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false, false);
+	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret) {
 		DRM_ERROR("pushing to VRAM failed\n");
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 4c950b4cf416..5614c89148cb 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -315,7 +315,7 @@ nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t memtype)
 
 	nouveau_bo_placement_set(nvbo, memtype, 0);
 
-	ret = nouveau_bo_validate(nvbo, false, false, false);
+	ret = nouveau_bo_validate(nvbo, false, false);
 	if (ret == 0) {
 		switch (bo->mem.mem_type) {
 		case TTM_PL_VRAM:
@@ -351,7 +351,7 @@ nouveau_bo_unpin(struct nouveau_bo *nvbo)
 
 	nouveau_bo_placement_set(nvbo, bo->mem.placement, 0);
 
-	ret = nouveau_bo_validate(nvbo, false, false, false);
+	ret = nouveau_bo_validate(nvbo, false, false);
 	if (ret == 0) {
 		switch (bo->mem.mem_type) {
 		case TTM_PL_VRAM:
@@ -392,12 +392,12 @@ nouveau_bo_unmap(struct nouveau_bo *nvbo)
 
 int
 nouveau_bo_validate(struct nouveau_bo *nvbo, bool interruptible,
-		    bool no_wait_reserve, bool no_wait_gpu)
+		    bool no_wait_gpu)
 {
 	int ret;
 
-	ret = ttm_bo_validate(&nvbo->bo, &nvbo->placement, interruptible,
-			      no_wait_reserve, no_wait_gpu);
+	ret = ttm_bo_validate(&nvbo->bo, &nvbo->placement,
+			      interruptible, no_wait_gpu);
 	if (ret)
 		return ret;
 
@@ -556,8 +556,7 @@ nouveau_bo_evict_flags(struct ttm_buffer_object *bo, struct ttm_placement *pl)
 static int
 nouveau_bo_move_accel_cleanup(struct nouveau_channel *chan,
 			      struct nouveau_bo *nvbo, bool evict,
-			      bool no_wait_reserve, bool no_wait_gpu,
-			      struct ttm_mem_reg *new_mem)
+			      bool no_wait_gpu, struct ttm_mem_reg *new_mem)
 {
 	struct nouveau_fence *fence = NULL;
 	int ret;
@@ -567,7 +566,7 @@ nouveau_bo_move_accel_cleanup(struct nouveau_channel *chan,
 		return ret;
 
 	ret = ttm_bo_move_accel_cleanup(&nvbo->bo, fence, evict,
-					no_wait_reserve, no_wait_gpu, new_mem);
+					no_wait_gpu, new_mem);
 	nouveau_fence_unref(&fence);
 	return ret;
 }
@@ -965,8 +964,7 @@ nouveau_vma_getmap(struct nouveau_channel *chan, struct nouveau_bo *nvbo,
 
 static int
 nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
-		     bool no_wait_reserve, bool no_wait_gpu,
-		     struct ttm_mem_reg *new_mem)
+		     bool no_wait_gpu, struct ttm_mem_reg *new_mem)
 {
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 	struct nouveau_channel *chan = chan = drm->channel;
@@ -995,7 +993,6 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
 	ret = drm->ttm.move(chan, bo, &bo->mem, new_mem);
 	if (ret == 0) {
 		ret = nouveau_bo_move_accel_cleanup(chan, nvbo, evict,
-						    no_wait_reserve,
 						    no_wait_gpu, new_mem);
 	}
 
@@ -1064,8 +1061,7 @@ nouveau_bo_move_init(struct nouveau_drm *drm)
 
 static int
 nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
-		      bool no_wait_reserve, bool no_wait_gpu,
-		      struct ttm_mem_reg *new_mem)
+		      bool no_wait_gpu, struct ttm_mem_reg *new_mem)
 {
 	u32 placement_memtype = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING;
 	struct ttm_placement placement;
@@ -1078,7 +1074,7 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
-	ret = ttm_bo_mem_space(bo, &placement, &tmp_mem, intr, no_wait_reserve, no_wait_gpu);
+	ret = ttm_bo_mem_space(bo, &placement, &tmp_mem, intr, no_wait_gpu);
 	if (ret)
 		return ret;
 
@@ -1086,11 +1082,11 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 	if (ret)
 		goto out;
 
-	ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait_reserve, no_wait_gpu, &tmp_mem);
+	ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait_gpu, &tmp_mem);
 	if (ret)
 		goto out;
 
-	ret = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, new_mem);
+	ret = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem);
 out:
 	ttm_bo_mem_put(bo, &tmp_mem);
 	return ret;
@@ -1098,8 +1094,7 @@ out:
 
 static int
 nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
-		      bool no_wait_reserve, bool no_wait_gpu,
-		      struct ttm_mem_reg *new_mem)
+		      bool no_wait_gpu, struct ttm_mem_reg *new_mem)
 {
 	u32 placement_memtype = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING;
 	struct ttm_placement placement;
@@ -1112,15 +1107,15 @@ nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
 
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
-	ret = ttm_bo_mem_space(bo, &placement, &tmp_mem, intr, no_wait_reserve, no_wait_gpu);
+	ret = ttm_bo_mem_space(bo, &placement, &tmp_mem, intr, no_wait_gpu);
 	if (ret)
 		return ret;
 
-	ret = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, &tmp_mem);
+	ret = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem);
 	if (ret)
 		goto out;
 
-	ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait_reserve, no_wait_gpu, new_mem);
+	ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait_gpu, new_mem);
 	if (ret)
 		goto out;
 
@@ -1195,8 +1190,7 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo,
 
 static int
 nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, bool intr,
-		bool no_wait_reserve, bool no_wait_gpu,
-		struct ttm_mem_reg *new_mem)
+		bool no_wait_gpu, struct ttm_mem_reg *new_mem)
 {
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
@@ -1220,23 +1214,26 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, bool intr,
 
 	/* CPU copy if we have no accelerated method available */
 	if (!drm->ttm.move) {
-		ret = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
+		ret = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
 		goto out;
 	}
 
 	/* Hardware assisted copy. */
 	if (new_mem->mem_type == TTM_PL_SYSTEM)
-		ret = nouveau_bo_move_flipd(bo, evict, intr, no_wait_reserve, no_wait_gpu, new_mem);
+		ret = nouveau_bo_move_flipd(bo, evict, intr,
+					    no_wait_gpu, new_mem);
 	else if (old_mem->mem_type == TTM_PL_SYSTEM)
-		ret = nouveau_bo_move_flips(bo, evict, intr, no_wait_reserve, no_wait_gpu, new_mem);
+		ret = nouveau_bo_move_flips(bo, evict, intr,
+					    no_wait_gpu, new_mem);
 	else
-		ret = nouveau_bo_move_m2mf(bo, evict, intr, no_wait_reserve, no_wait_gpu, new_mem);
+		ret = nouveau_bo_move_m2mf(bo, evict, intr,
+					   no_wait_gpu, new_mem);
 
 	if (!ret)
 		goto out;
 
 	/* Fallback to software copy. */
-	ret = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
+	ret = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
 
 out:
 	if (nv_device(drm->device)->card_type < NV_50) {
@@ -1343,7 +1340,7 @@ nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
 	nvbo->placement.fpfn = 0;
 	nvbo->placement.lpfn = mappable;
 	nouveau_bo_placement_set(nvbo, TTM_PL_FLAG_VRAM, 0);
-	return nouveau_bo_validate(nvbo, false, true, false);
+	return nouveau_bo_validate(nvbo, false, false);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h
index dec51b1098fe..25ca37989d2c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.h
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.h
@@ -76,7 +76,7 @@ u32  nouveau_bo_rd32(struct nouveau_bo *, unsigned index);
 void nouveau_bo_wr32(struct nouveau_bo *, unsigned index, u32 val);
 void nouveau_bo_fence(struct nouveau_bo *, struct nouveau_fence *);
 int  nouveau_bo_validate(struct nouveau_bo *, bool interruptible,
-			 bool no_wait_reserve, bool no_wait_gpu);
+			 bool no_wait_gpu);
 
 struct nouveau_vma *
 nouveau_bo_vma_find(struct nouveau_bo *, struct nouveau_vm *);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 5e2f52158f19..8bf695c52f95 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -433,7 +433,7 @@ validate_list(struct nouveau_channel *chan, struct list_head *list,
 			return ret;
 		}
 
-		ret = nouveau_bo_validate(nvbo, true, false, false);
+		ret = nouveau_bo_validate(nvbo, true, false);
 		if (unlikely(ret)) {
 			if (ret != -ERESTARTSYS)
 				NV_ERROR(drm, "fail ttm_validate\n");
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index e6ee65cdfb5c..bfb332e616dc 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -250,7 +250,7 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 	}
 	for (i = 0; i < bo->placement.num_placement; i++)
 		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
 	if (likely(r == 0)) {
 		bo->pin_count = 1;
 		if (gpu_addr != NULL)
@@ -279,7 +279,7 @@ int radeon_bo_unpin(struct radeon_bo *bo)
 		return 0;
 	for (i = 0; i < bo->placement.num_placement; i++)
 		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false, false);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
 	if (unlikely(r != 0))
 		dev_err(bo->rdev->dev, "%p validate failed for unpin\n", bo);
 	return r;
@@ -365,7 +365,7 @@ int radeon_bo_list_validate(struct list_head *head)
 		retry:
 			radeon_ttm_placement_from_domain(bo, domain);
 			r = ttm_bo_validate(&bo->tbo, &bo->placement,
-						true, false, false);
+						true, false);
 			if (unlikely(r)) {
 				if (r != -ERESTARTSYS && domain == RADEON_GEM_DOMAIN_VRAM) {
 					domain |= RADEON_GEM_DOMAIN_GTT;
@@ -585,7 +585,7 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 			/* hurrah the memory is not visible ! */
 			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
 			rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
-			r = ttm_bo_validate(bo, &rbo->placement, false, true, false);
+			r = ttm_bo_validate(bo, &rbo->placement, false, false);
 			if (unlikely(r != 0))
 				return r;
 			offset = bo->mem.start << PAGE_SHIFT;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 563c8edcb03b..1d8ff2f850ba 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -216,7 +216,7 @@ static void radeon_move_null(struct ttm_buffer_object *bo,
 }
 
 static int radeon_move_blit(struct ttm_buffer_object *bo,
-			bool evict, int no_wait_reserve, bool no_wait_gpu,
+			bool evict, bool no_wait_gpu,
 			struct ttm_mem_reg *new_mem,
 			struct ttm_mem_reg *old_mem)
 {
@@ -266,14 +266,14 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 			&fence);
 	/* FIXME: handle copy error */
 	r = ttm_bo_move_accel_cleanup(bo, (void *)fence,
-				      evict, no_wait_reserve, no_wait_gpu, new_mem);
+				      evict, no_wait_gpu, new_mem);
 	radeon_fence_unref(&fence);
 	return r;
 }
 
 static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 				bool evict, bool interruptible,
-				bool no_wait_reserve, bool no_wait_gpu,
+				bool no_wait_gpu,
 				struct ttm_mem_reg *new_mem)
 {
 	struct radeon_device *rdev;
@@ -294,7 +294,7 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 	placement.busy_placement = &placements;
 	placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
 	r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
-			     interruptible, no_wait_reserve, no_wait_gpu);
+			     interruptible, no_wait_gpu);
 	if (unlikely(r)) {
 		return r;
 	}
@@ -308,11 +308,11 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-	r = radeon_move_blit(bo, true, no_wait_reserve, no_wait_gpu, &tmp_mem, old_mem);
+	r = radeon_move_blit(bo, true, no_wait_gpu, &tmp_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-	r = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, new_mem);
+	r = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem);
 out_cleanup:
 	ttm_bo_mem_put(bo, &tmp_mem);
 	return r;
@@ -320,7 +320,7 @@ out_cleanup:
 
 static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
 				bool evict, bool interruptible,
-				bool no_wait_reserve, bool no_wait_gpu,
+				bool no_wait_gpu,
 				struct ttm_mem_reg *new_mem)
 {
 	struct radeon_device *rdev;
@@ -340,15 +340,16 @@ static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
 	placement.num_busy_placement = 1;
 	placement.busy_placement = &placements;
 	placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
-	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, interruptible, no_wait_reserve, no_wait_gpu);
+	r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
+			     interruptible, no_wait_gpu);
 	if (unlikely(r)) {
 		return r;
 	}
-	r = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, &tmp_mem);
+	r = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-	r = radeon_move_blit(bo, true, no_wait_reserve, no_wait_gpu, new_mem, old_mem);
+	r = radeon_move_blit(bo, true, no_wait_gpu, new_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
@@ -359,7 +360,7 @@ out_cleanup:
 
 static int radeon_bo_move(struct ttm_buffer_object *bo,
 			bool evict, bool interruptible,
-			bool no_wait_reserve, bool no_wait_gpu,
+			bool no_wait_gpu,
 			struct ttm_mem_reg *new_mem)
 {
 	struct radeon_device *rdev;
@@ -388,18 +389,18 @@ static int radeon_bo_move(struct ttm_buffer_object *bo,
 	if (old_mem->mem_type == TTM_PL_VRAM &&
 	    new_mem->mem_type == TTM_PL_SYSTEM) {
 		r = radeon_move_vram_ram(bo, evict, interruptible,
-					no_wait_reserve, no_wait_gpu, new_mem);
+					no_wait_gpu, new_mem);
 	} else if (old_mem->mem_type == TTM_PL_SYSTEM &&
 		   new_mem->mem_type == TTM_PL_VRAM) {
 		r = radeon_move_ram_vram(bo, evict, interruptible,
-					    no_wait_reserve, no_wait_gpu, new_mem);
+					    no_wait_gpu, new_mem);
 	} else {
-		r = radeon_move_blit(bo, evict, no_wait_reserve, no_wait_gpu, new_mem, old_mem);
+		r = radeon_move_blit(bo, evict, no_wait_gpu, new_mem, old_mem);
 	}
 
 	if (r) {
 memcpy:
-		r = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem);
+		r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
 	}
 	return r;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 6059771d506e..a9151337d5b9 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -366,7 +366,7 @@ static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc)
 static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 				  struct ttm_mem_reg *mem,
 				  bool evict, bool interruptible,
-				  bool no_wait_reserve, bool no_wait_gpu)
+				  bool no_wait_gpu)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	bool old_is_pci = ttm_mem_reg_is_pci(bdev, &bo->mem);
@@ -420,12 +420,12 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 
 	if (!(old_man->flags & TTM_MEMTYPE_FLAG_FIXED) &&
 	    !(new_man->flags & TTM_MEMTYPE_FLAG_FIXED))
-		ret = ttm_bo_move_ttm(bo, evict, no_wait_reserve, no_wait_gpu, mem);
+		ret = ttm_bo_move_ttm(bo, evict, no_wait_gpu, mem);
 	else if (bdev->driver->move)
 		ret = bdev->driver->move(bo, evict, interruptible,
-					 no_wait_reserve, no_wait_gpu, mem);
+					 no_wait_gpu, mem);
 	else
-		ret = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, mem);
+		ret = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, mem);
 
 	if (ret) {
 		if (bdev->driver->move_notify) {
@@ -749,7 +749,7 @@ void ttm_bo_unlock_delayed_workqueue(struct ttm_bo_device *bdev, int resched)
 EXPORT_SYMBOL(ttm_bo_unlock_delayed_workqueue);
 
 static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
-			bool no_wait_reserve, bool no_wait_gpu)
+			bool no_wait_gpu)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_mem_reg evict_mem;
@@ -780,7 +780,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	placement.num_busy_placement = 0;
 	bdev->driver->evict_flags(bo, &placement);
 	ret = ttm_bo_mem_space(bo, &placement, &evict_mem, interruptible,
-				no_wait_reserve, no_wait_gpu);
+				no_wait_gpu);
 	if (ret) {
 		if (ret != -ERESTARTSYS) {
 			pr_err("Failed to find memory space for buffer 0x%p eviction\n",
@@ -791,7 +791,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	}
 
 	ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, interruptible,
-				     no_wait_reserve, no_wait_gpu);
+				     no_wait_gpu);
 	if (ret) {
 		if (ret != -ERESTARTSYS)
 			pr_err("Buffer eviction failed\n");
@@ -805,7 +805,7 @@ out:
 
 static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 				uint32_t mem_type,
-				bool interruptible, bool no_wait_reserve,
+				bool interruptible,
 				bool no_wait_gpu)
 {
 	struct ttm_bo_global *glob = bdev->glob;
@@ -841,7 +841,7 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 
 	ttm_bo_list_ref_sub(bo, put_count, true);
 
-	ret = ttm_bo_evict(bo, interruptible, no_wait_reserve, no_wait_gpu);
+	ret = ttm_bo_evict(bo, interruptible, no_wait_gpu);
 	ttm_bo_unreserve(bo);
 
 	kref_put(&bo->list_kref, ttm_bo_release_list);
@@ -866,7 +866,6 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 					struct ttm_placement *placement,
 					struct ttm_mem_reg *mem,
 					bool interruptible,
-					bool no_wait_reserve,
 					bool no_wait_gpu)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
@@ -879,8 +878,8 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 			return ret;
 		if (mem->mm_node)
 			break;
-		ret = ttm_mem_evict_first(bdev, mem_type, interruptible,
-						no_wait_reserve, no_wait_gpu);
+		ret = ttm_mem_evict_first(bdev, mem_type,
+					  interruptible, no_wait_gpu);
 		if (unlikely(ret != 0))
 			return ret;
 	} while (1);
@@ -945,7 +944,7 @@ static bool ttm_bo_mt_compatible(struct ttm_mem_type_manager *man,
 int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 			struct ttm_placement *placement,
 			struct ttm_mem_reg *mem,
-			bool interruptible, bool no_wait_reserve,
+			bool interruptible,
 			bool no_wait_gpu)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
@@ -1036,7 +1035,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		}
 
 		ret = ttm_bo_mem_force_space(bo, mem_type, placement, mem,
-						interruptible, no_wait_reserve, no_wait_gpu);
+						interruptible, no_wait_gpu);
 		if (ret == 0 && mem->mm_node) {
 			mem->placement = cur_flags;
 			return 0;
@@ -1051,7 +1050,7 @@ EXPORT_SYMBOL(ttm_bo_mem_space);
 
 int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 			struct ttm_placement *placement,
-			bool interruptible, bool no_wait_reserve,
+			bool interruptible,
 			bool no_wait_gpu)
 {
 	int ret = 0;
@@ -1078,10 +1077,12 @@ int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 	/*
 	 * Determine where to move the buffer.
 	 */
-	ret = ttm_bo_mem_space(bo, placement, &mem, interruptible, no_wait_reserve, no_wait_gpu);
+	ret = ttm_bo_mem_space(bo, placement, &mem,
+			       interruptible, no_wait_gpu);
 	if (ret)
 		goto out_unlock;
-	ret = ttm_bo_handle_move_mem(bo, &mem, false, interruptible, no_wait_reserve, no_wait_gpu);
+	ret = ttm_bo_handle_move_mem(bo, &mem, false,
+				     interruptible, no_wait_gpu);
 out_unlock:
 	if (ret && mem.mm_node)
 		ttm_bo_mem_put(bo, &mem);
@@ -1110,7 +1111,7 @@ static int ttm_bo_mem_compat(struct ttm_placement *placement,
 
 int ttm_bo_validate(struct ttm_buffer_object *bo,
 			struct ttm_placement *placement,
-			bool interruptible, bool no_wait_reserve,
+			bool interruptible,
 			bool no_wait_gpu)
 {
 	int ret;
@@ -1126,7 +1127,8 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	 */
 	ret = ttm_bo_mem_compat(placement, &bo->mem);
 	if (ret < 0) {
-		ret = ttm_bo_move_buffer(bo, placement, interruptible, no_wait_reserve, no_wait_gpu);
+		ret = ttm_bo_move_buffer(bo, placement, interruptible,
+					 no_wait_gpu);
 		if (ret)
 			return ret;
 	} else {
@@ -1239,7 +1241,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 			goto out_err;
 	}
 
-	ret = ttm_bo_validate(bo, placement, interruptible, false, false);
+	ret = ttm_bo_validate(bo, placement, interruptible, false);
 	if (ret)
 		goto out_err;
 
@@ -1325,7 +1327,7 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
 	spin_lock(&glob->lru_lock);
 	while (!list_empty(&man->lru)) {
 		spin_unlock(&glob->lru_lock);
-		ret = ttm_mem_evict_first(bdev, mem_type, false, false, false);
+		ret = ttm_mem_evict_first(bdev, mem_type, false, false);
 		if (ret) {
 			if (allow_errors) {
 				return ret;
@@ -1837,7 +1839,7 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 		evict_mem.mem_type = TTM_PL_SYSTEM;
 
 		ret = ttm_bo_handle_move_mem(bo, &evict_mem, true,
-					     false, false, false);
+					     false, false);
 		if (unlikely(ret != 0))
 			goto out;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index b9c4e515b1d8..9e9c5d2a5c74 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -43,7 +43,7 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo)
 }
 
 int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
-		    bool evict, bool no_wait_reserve,
+		    bool evict,
 		    bool no_wait_gpu, struct ttm_mem_reg *new_mem)
 {
 	struct ttm_tt *ttm = bo->ttm;
@@ -314,7 +314,7 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst,
 }
 
 int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
-		       bool evict, bool no_wait_reserve, bool no_wait_gpu,
+		       bool evict, bool no_wait_gpu,
 		       struct ttm_mem_reg *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
@@ -611,7 +611,7 @@ EXPORT_SYMBOL(ttm_bo_kunmap);
 
 int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			      void *sync_obj,
-			      bool evict, bool no_wait_reserve,
+			      bool evict,
 			      bool no_wait_gpu,
 			      struct ttm_mem_reg *new_mem)
 {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
index e88b0eb1a179..5fae06ad7e25 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
@@ -66,7 +66,7 @@ int vmw_dmabuf_to_placement(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		goto err;
 
-	ret = ttm_bo_validate(bo, placement, interruptible, false, false);
+	ret = ttm_bo_validate(bo, placement, interruptible, false);
 
 	ttm_bo_unreserve(bo);
 
@@ -123,7 +123,7 @@ int vmw_dmabuf_to_vram_or_gmr(struct vmw_private *dev_priv,
 	else
 		placement = &vmw_vram_gmr_placement;
 
-	ret = ttm_bo_validate(bo, placement, interruptible, false, false);
+	ret = ttm_bo_validate(bo, placement, interruptible, false);
 	if (likely(ret == 0) || ret == -ERESTARTSYS)
 		goto err_unreserve;
 
@@ -138,7 +138,7 @@ int vmw_dmabuf_to_vram_or_gmr(struct vmw_private *dev_priv,
 	else
 		placement = &vmw_vram_placement;
 
-	ret = ttm_bo_validate(bo, placement, interruptible, false, false);
+	ret = ttm_bo_validate(bo, placement, interruptible, false);
 
 err_unreserve:
 	ttm_bo_unreserve(bo);
@@ -223,10 +223,9 @@ int vmw_dmabuf_to_start_of_vram(struct vmw_private *dev_priv,
 	if (bo->mem.mem_type == TTM_PL_VRAM &&
 	    bo->mem.start < bo->num_pages &&
 	    bo->mem.start > 0)
-		(void) ttm_bo_validate(bo, &vmw_sys_placement, false,
-				       false, false);
+		(void) ttm_bo_validate(bo, &vmw_sys_placement, false, false);
 
-	ret = ttm_bo_validate(bo, &placement, interruptible, false, false);
+	ret = ttm_bo_validate(bo, &placement, interruptible, false);
 
 	/* For some reason we didn't up at the start of vram */
 	WARN_ON(ret == 0 && bo->offset != 0);
@@ -315,7 +314,7 @@ void vmw_bo_pin(struct ttm_buffer_object *bo, bool pin)
 	placement.num_placement = 1;
 	placement.placement = &pl_flags;
 
-	ret = ttm_bo_validate(bo, &placement, false, true, true);
+	ret = ttm_bo_validate(bo, &placement, false, true);
 
 	BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type);
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 534c96703c3f..394e6476105b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1245,7 +1245,7 @@ static int vmw_validate_single_buffer(struct vmw_private *dev_priv,
 	 * used as a GMR, this will return -ENOMEM.
 	 */
 
-	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, true, false, false);
+	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, true, false);
 	if (likely(ret == 0 || ret == -ERESTARTSYS))
 		return ret;
 
@@ -1255,7 +1255,7 @@ static int vmw_validate_single_buffer(struct vmw_private *dev_priv,
 	 */
 
 	DRM_INFO("Falling through to VRAM.\n");
-	ret = ttm_bo_validate(bo, &vmw_vram_placement, true, false, false);
+	ret = ttm_bo_validate(bo, &vmw_vram_placement, true, false);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 0def4ff5b621..e01a17b407b2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -1018,7 +1018,7 @@ int vmw_resource_check_buffer(struct vmw_resource *res,
 	backup_dirty = res->backup_dirty;
 	ret = ttm_bo_validate(&res->backup->base,
 			      res->func->backup_placement,
-			      true, false, false);
+			      true, false);
 
 	if (unlikely(ret != 0))
 		goto out_no_validate;
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index c6cae733ddef..3cb5d848fb66 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -337,7 +337,6 @@ extern int ttm_bo_wait(struct ttm_buffer_object *bo, bool lazy,
  * @bo: The buffer object.
  * @placement: Proposed placement for the buffer object.
  * @interruptible: Sleep interruptible if sleeping.
- * @no_wait_reserve: Return immediately if other buffers are busy.
  * @no_wait_gpu: Return immediately if the GPU is busy.
  *
  * Changes placement and caching policy of the buffer object
@@ -350,7 +349,7 @@ extern int ttm_bo_wait(struct ttm_buffer_object *bo, bool lazy,
  */
 extern int ttm_bo_validate(struct ttm_buffer_object *bo,
 				struct ttm_placement *placement,
-				bool interruptible, bool no_wait_reserve,
+				bool interruptible,
 				bool no_wait_gpu);
 
 /**
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index dd96442cdc2a..e3a43a47d78c 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -394,7 +394,7 @@ struct ttm_bo_driver {
 	 */
 	int (*move) (struct ttm_buffer_object *bo,
 		     bool evict, bool interruptible,
-		     bool no_wait_reserve, bool no_wait_gpu,
+		     bool no_wait_gpu,
 		     struct ttm_mem_reg *new_mem);
 
 	/**
@@ -703,7 +703,6 @@ extern bool ttm_mem_reg_is_pci(struct ttm_bo_device *bdev,
  * @proposed_placement: Proposed new placement for the buffer object.
  * @mem: A struct ttm_mem_reg.
  * @interruptible: Sleep interruptible when sliping.
- * @no_wait_reserve: Return immediately if other buffers are busy.
  * @no_wait_gpu: Return immediately if the GPU is busy.
  *
  * Allocate memory space for the buffer object pointed to by @bo, using
@@ -719,7 +718,7 @@ extern int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 				struct ttm_placement *placement,
 				struct ttm_mem_reg *mem,
 				bool interruptible,
-				bool no_wait_reserve, bool no_wait_gpu);
+				bool no_wait_gpu);
 
 extern void ttm_bo_mem_put(struct ttm_buffer_object *bo,
 			   struct ttm_mem_reg *mem);
@@ -901,7 +900,6 @@ extern int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo,
  *
  * @bo: A pointer to a struct ttm_buffer_object.
  * @evict: 1: This is an eviction. Don't try to pipeline.
- * @no_wait_reserve: Return immediately if other buffers are busy.
  * @no_wait_gpu: Return immediately if the GPU is busy.
  * @new_mem: struct ttm_mem_reg indicating where to move.
  *
@@ -916,15 +914,14 @@ extern int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo,
  */
 
 extern int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
-			   bool evict, bool no_wait_reserve,
-			   bool no_wait_gpu, struct ttm_mem_reg *new_mem);
+			   bool evict, bool no_wait_gpu,
+			   struct ttm_mem_reg *new_mem);
 
 /**
  * ttm_bo_move_memcpy
  *
  * @bo: A pointer to a struct ttm_buffer_object.
  * @evict: 1: This is an eviction. Don't try to pipeline.
- * @no_wait_reserve: Return immediately if other buffers are busy.
  * @no_wait_gpu: Return immediately if the GPU is busy.
  * @new_mem: struct ttm_mem_reg indicating where to move.
  *
@@ -939,8 +936,8 @@ extern int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
  */
 
 extern int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
-			      bool evict, bool no_wait_reserve,
-			      bool no_wait_gpu, struct ttm_mem_reg *new_mem);
+			      bool evict, bool no_wait_gpu,
+			      struct ttm_mem_reg *new_mem);
 
 /**
  * ttm_bo_free_old_node
@@ -957,7 +954,6 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  * @bo: A pointer to a struct ttm_buffer_object.
  * @sync_obj: A sync object that signals when moving is complete.
  * @evict: This is an evict move. Don't return until the buffer is idle.
- * @no_wait_reserve: Return immediately if other buffers are busy.
  * @no_wait_gpu: Return immediately if the GPU is busy.
  * @new_mem: struct ttm_mem_reg indicating where to move.
  *
@@ -971,8 +967,7 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
 
 extern int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 				     void *sync_obj,
-				     bool evict, bool no_wait_reserve,
-				     bool no_wait_gpu,
+				     bool evict, bool no_wait_gpu,
 				     struct ttm_mem_reg *new_mem);
 /**
  * ttm_io_prot
-- 
cgit v1.2.3-55-g7522


From 759f5f3752e03f15727688b5288e360ef90c1306 Mon Sep 17 00:00:00 2001
From: Vivien Didelot
Date: Fri, 7 Dec 2012 21:36:34 -0500
Subject: gpio: add TS-5500 DIO blocks support

Technologic Systems TS-5500 provides digital I/O lines exposed through
pin blocks. On this platform, there are three of them, named DIO1, DIO2
and LCD port, that may be used as a DIO block.

The TS-5500 pin blocks are described in the product's wiki:
http://wiki.embeddedarm.com/wiki/TS-5500#Digital_I.2FO

This driver is not limited to the TS-5500 blocks. It can be extended to
support similar boards pin blocks, such as on the TS-5600.

This patch is the V2 of the previous https://lkml.org/lkml/2012/9/25/671
with corrections suggested by Linus Walleij.

Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: Jerome Oufella <jerome.oufella@savoirfairelinux.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/Kconfig                      |   8 +
 drivers/gpio/Makefile                     |   1 +
 drivers/gpio/gpio-ts5500.c                | 466 ++++++++++++++++++++++++++++++
 include/linux/platform_data/gpio-ts5500.h |  27 ++
 4 files changed, 502 insertions(+)
 create mode 100644 drivers/gpio/gpio-ts5500.c
 create mode 100644 include/linux/platform_data/gpio-ts5500.h

(limited to 'include')

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 46e96f3fc3f8..39d9323abbda 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -211,6 +211,14 @@ config GPIO_STA2X11
 	  Say yes here to support the STA2x11/ConneXt GPIO device.
 	  The GPIO module has 128 GPIO pins with alternate functions.
 
+config GPIO_TS5500
+	tristate "TS-5500 DIO blocks and compatibles"
+	help
+	  This driver supports Digital I/O exposed by pin blocks found on some
+	  Technologic Systems platforms. It includes, but is not limited to, 3
+	  blocks of the TS-5500: DIO1, DIO2 and the LCD port, and the TS-5600
+	  LCD port.
+
 config GPIO_VT8500
 	bool "VIA/Wondermedia SoC GPIO Support"
 	depends on ARCH_VT8500
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index a268d99f4e43..a41c2503bd40 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -71,6 +71,7 @@ obj-$(CONFIG_ARCH_DAVINCI_TNETV107X) += gpio-tnetv107x.o
 obj-$(CONFIG_GPIO_TPS6586X)	+= gpio-tps6586x.o
 obj-$(CONFIG_GPIO_TPS65910)	+= gpio-tps65910.o
 obj-$(CONFIG_GPIO_TPS65912)	+= gpio-tps65912.o
+obj-$(CONFIG_GPIO_TS5500)	+= gpio-ts5500.o
 obj-$(CONFIG_GPIO_TWL4030)	+= gpio-twl4030.o
 obj-$(CONFIG_GPIO_TWL6040)	+= gpio-twl6040.o
 obj-$(CONFIG_GPIO_UCB1400)	+= gpio-ucb1400.o
diff --git a/drivers/gpio/gpio-ts5500.c b/drivers/gpio/gpio-ts5500.c
new file mode 100644
index 000000000000..0634ceea3c24
--- /dev/null
+++ b/drivers/gpio/gpio-ts5500.c
@@ -0,0 +1,466 @@
+/*
+ * Digital I/O driver for Technologic Systems TS-5500
+ *
+ * Copyright (c) 2012 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ *
+ * Technologic Systems platforms have pin blocks, exposing several Digital
+ * Input/Output lines (DIO). This driver aims to support single pin blocks.
+ * In that sense, the support is not limited to the TS-5500 blocks.
+ * Actually, the following platforms have DIO support:
+ *
+ * TS-5500:
+ *   Documentation: http://wiki.embeddedarm.com/wiki/TS-5500
+ *   Blocks: DIO1, DIO2 and LCD port.
+ *
+ * TS-5600:
+ *   Documentation: http://wiki.embeddedarm.com/wiki/TS-5600
+ *   Blocks: LCD port (identical to TS-5500 LCD).
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/gpio.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_data/gpio-ts5500.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+/* List of supported Technologic Systems platforms DIO blocks */
+enum ts5500_blocks { TS5500_DIO1, TS5500_DIO2, TS5500_LCD, TS5600_LCD };
+
+struct ts5500_priv {
+	const struct ts5500_dio *pinout;
+	struct gpio_chip gpio_chip;
+	spinlock_t lock;
+	bool strap;
+	u8 hwirq;
+};
+
+/*
+ * Hex 7D is used to control several blocks (e.g. DIO2 and LCD port).
+ * This flag ensures that the region has been requested by this driver.
+ */
+static bool hex7d_reserved;
+
+/*
+ * This structure is used to describe capabilities of DIO lines,
+ * such as available directions and connected interrupt (if any).
+ */
+struct ts5500_dio {
+	const u8 value_addr;
+	const u8 value_mask;
+	const u8 control_addr;
+	const u8 control_mask;
+	const bool no_input;
+	const bool no_output;
+	const u8 irq;
+};
+
+#define TS5500_DIO_IN_OUT(vaddr, vbit, caddr, cbit)	\
+	{						\
+		.value_addr = vaddr,			\
+		.value_mask = BIT(vbit),		\
+		.control_addr = caddr,			\
+		.control_mask = BIT(cbit),		\
+	}
+
+#define TS5500_DIO_IN(addr, bit)		\
+	{					\
+		.value_addr = addr,		\
+		.value_mask = BIT(bit),		\
+		.no_output = true,		\
+	}
+
+#define TS5500_DIO_IN_IRQ(addr, bit, _irq)	\
+	{					\
+		.value_addr = addr,		\
+		.value_mask = BIT(bit),		\
+		.no_output = true,		\
+		.irq = _irq,			\
+	}
+
+#define TS5500_DIO_OUT(addr, bit)		\
+	{					\
+		.value_addr = addr,		\
+		.value_mask = BIT(bit),		\
+		.no_input = true,		\
+	}
+
+/*
+ * Input/Output DIO lines are programmed in groups of 4. Their values are
+ * available through 4 consecutive bits in a value port, whereas the direction
+ * of these 4 lines is driven by only 1 bit in a control port.
+ */
+#define TS5500_DIO_GROUP(vaddr, vbitfrom, caddr, cbit)		\
+	TS5500_DIO_IN_OUT(vaddr, vbitfrom + 0, caddr, cbit),	\
+	TS5500_DIO_IN_OUT(vaddr, vbitfrom + 1, caddr, cbit),	\
+	TS5500_DIO_IN_OUT(vaddr, vbitfrom + 2, caddr, cbit),	\
+	TS5500_DIO_IN_OUT(vaddr, vbitfrom + 3, caddr, cbit)
+
+/*
+ * TS-5500 DIO1 block
+ *
+ *  value    control  dir    hw
+ *  addr bit addr bit in out irq name     pin offset
+ *
+ *  0x7b  0  0x7a  0  x   x      DIO1_0   1   0
+ *  0x7b  1  0x7a  0  x   x      DIO1_1   3   1
+ *  0x7b  2  0x7a  0  x   x      DIO1_2   5   2
+ *  0x7b  3  0x7a  0  x   x      DIO1_3   7   3
+ *  0x7b  4  0x7a  1  x   x      DIO1_4   9   4
+ *  0x7b  5  0x7a  1  x   x      DIO1_5   11  5
+ *  0x7b  6  0x7a  1  x   x      DIO1_6   13  6
+ *  0x7b  7  0x7a  1  x   x      DIO1_7   15  7
+ *  0x7c  0  0x7a  5  x   x      DIO1_8   4   8
+ *  0x7c  1  0x7a  5  x   x      DIO1_9   6   9
+ *  0x7c  2  0x7a  5  x   x      DIO1_10  8   10
+ *  0x7c  3  0x7a  5  x   x      DIO1_11  10  11
+ *  0x7c  4           x          DIO1_12  12  12
+ *  0x7c  5           x      7   DIO1_13  14  13
+ */
+static const struct ts5500_dio ts5500_dio1[] = {
+	TS5500_DIO_GROUP(0x7b, 0, 0x7a, 0),
+	TS5500_DIO_GROUP(0x7b, 4, 0x7a, 1),
+	TS5500_DIO_GROUP(0x7c, 0, 0x7a, 5),
+	TS5500_DIO_IN(0x7c, 4),
+	TS5500_DIO_IN_IRQ(0x7c, 5, 7),
+};
+
+/*
+ * TS-5500 DIO2 block
+ *
+ *  value    control  dir    hw
+ *  addr bit addr bit in out irq name     pin offset
+ *
+ *  0x7e  0  0x7d  0  x   x      DIO2_0   1   0
+ *  0x7e  1  0x7d  0  x   x      DIO2_1   3   1
+ *  0x7e  2  0x7d  0  x   x      DIO2_2   5   2
+ *  0x7e  3  0x7d  0  x   x      DIO2_3   7   3
+ *  0x7e  4  0x7d  1  x   x      DIO2_4   9   4
+ *  0x7e  5  0x7d  1  x   x      DIO2_5   11  5
+ *  0x7e  6  0x7d  1  x   x      DIO2_6   13  6
+ *  0x7e  7  0x7d  1  x   x      DIO2_7   15  7
+ *  0x7f  0  0x7d  5  x   x      DIO2_8   4   8
+ *  0x7f  1  0x7d  5  x   x      DIO2_9   6   9
+ *  0x7f  2  0x7d  5  x   x      DIO2_10  8   10
+ *  0x7f  3  0x7d  5  x   x      DIO2_11  10  11
+ *  0x7f  4           x      6   DIO2_13  14  12
+ */
+static const struct ts5500_dio ts5500_dio2[] = {
+	TS5500_DIO_GROUP(0x7e, 0, 0x7d, 0),
+	TS5500_DIO_GROUP(0x7e, 4, 0x7d, 1),
+	TS5500_DIO_GROUP(0x7f, 0, 0x7d, 5),
+	TS5500_DIO_IN_IRQ(0x7f, 4, 6),
+};
+
+/*
+ * TS-5500 LCD port used as DIO block
+ * TS-5600 LCD port is identical
+ *
+ *  value    control  dir    hw
+ *  addr bit addr bit in out irq name    pin offset
+ *
+ *  0x72  0  0x7d  2  x   x      LCD_0   8   0
+ *  0x72  1  0x7d  2  x   x      LCD_1   7   1
+ *  0x72  2  0x7d  2  x   x      LCD_2   10  2
+ *  0x72  3  0x7d  2  x   x      LCD_3   9   3
+ *  0x72  4  0x7d  3  x   x      LCD_4   12  4
+ *  0x72  5  0x7d  3  x   x      LCD_5   11  5
+ *  0x72  6  0x7d  3  x   x      LCD_6   14  6
+ *  0x72  7  0x7d  3  x   x      LCD_7   13  7
+ *  0x73  0               x      LCD_EN  5   8
+ *  0x73  6           x          LCD_WR  6   9
+ *  0x73  7           x      1   LCD_RS  3   10
+ */
+static const struct ts5500_dio ts5500_lcd[] = {
+	TS5500_DIO_GROUP(0x72, 0, 0x7d, 2),
+	TS5500_DIO_GROUP(0x72, 4, 0x7d, 3),
+	TS5500_DIO_OUT(0x73, 0),
+	TS5500_DIO_IN(0x73, 6),
+	TS5500_DIO_IN_IRQ(0x73, 7, 1),
+};
+
+static inline struct ts5500_priv *ts5500_gc_to_priv(struct gpio_chip *chip)
+{
+	return container_of(chip, struct ts5500_priv, gpio_chip);
+}
+
+static inline void ts5500_set_mask(u8 mask, u8 addr)
+{
+	u8 val = inb(addr);
+	val |= mask;
+	outb(val, addr);
+}
+
+static inline void ts5500_clear_mask(u8 mask, u8 addr)
+{
+	u8 val = inb(addr);
+	val &= ~mask;
+	outb(val, addr);
+}
+
+static int ts5500_gpio_input(struct gpio_chip *chip, unsigned offset)
+{
+	struct ts5500_priv *priv = ts5500_gc_to_priv(chip);
+	const struct ts5500_dio line = priv->pinout[offset];
+	unsigned long flags;
+
+	if (line.no_input)
+		return -ENXIO;
+
+	if (line.no_output)
+		return 0;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	ts5500_clear_mask(line.control_mask, line.control_addr);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
+static int ts5500_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	struct ts5500_priv *priv = ts5500_gc_to_priv(chip);
+	const struct ts5500_dio line = priv->pinout[offset];
+
+	return !!(inb(line.value_addr) & line.value_mask);
+}
+
+static int ts5500_gpio_output(struct gpio_chip *chip, unsigned offset, int val)
+{
+	struct ts5500_priv *priv = ts5500_gc_to_priv(chip);
+	const struct ts5500_dio line = priv->pinout[offset];
+	unsigned long flags;
+
+	if (line.no_output)
+		return -ENXIO;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (!line.no_input)
+		ts5500_set_mask(line.control_mask, line.control_addr);
+
+	if (val)
+		ts5500_set_mask(line.value_mask, line.value_addr);
+	else
+		ts5500_clear_mask(line.value_mask, line.value_addr);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
+static void ts5500_gpio_set(struct gpio_chip *chip, unsigned offset, int val)
+{
+	struct ts5500_priv *priv = ts5500_gc_to_priv(chip);
+	const struct ts5500_dio line = priv->pinout[offset];
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (val)
+		ts5500_set_mask(line.value_mask, line.value_addr);
+	else
+		ts5500_clear_mask(line.value_mask, line.value_addr);
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static int ts5500_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
+{
+	struct ts5500_priv *priv = ts5500_gc_to_priv(chip);
+	const struct ts5500_dio *block = priv->pinout;
+	const struct ts5500_dio line = block[offset];
+
+	/* Only one pin is connected to an interrupt */
+	if (line.irq)
+		return line.irq;
+
+	/* As this pin is input-only, we may strap it to another in/out pin */
+	if (priv->strap)
+		return priv->hwirq;
+
+	return -ENXIO;
+}
+
+static int ts5500_enable_irq(struct ts5500_priv *priv)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (priv->hwirq == 7)
+		ts5500_set_mask(BIT(7), 0x7a); /* DIO1_13 on IRQ7 */
+	else if (priv->hwirq == 6)
+		ts5500_set_mask(BIT(7), 0x7d); /* DIO2_13 on IRQ6 */
+	else if (priv->hwirq == 1)
+		ts5500_set_mask(BIT(6), 0x7d); /* LCD_RS on IRQ1 */
+	else
+		ret = -EINVAL;
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return ret;
+}
+
+static void ts5500_disable_irq(struct ts5500_priv *priv)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (priv->hwirq == 7)
+		ts5500_clear_mask(BIT(7), 0x7a); /* DIO1_13 on IRQ7 */
+	else if (priv->hwirq == 6)
+		ts5500_clear_mask(BIT(7), 0x7d); /* DIO2_13 on IRQ6 */
+	else if (priv->hwirq == 1)
+		ts5500_clear_mask(BIT(6), 0x7d); /* LCD_RS on IRQ1 */
+	else
+		dev_err(priv->gpio_chip.dev, "invalid hwirq %d\n", priv->hwirq);
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static int __devinit ts5500_dio_probe(struct platform_device *pdev)
+{
+	enum ts5500_blocks block = platform_get_device_id(pdev)->driver_data;
+	struct ts5500_dio_platform_data *pdata = pdev->dev.platform_data;
+	struct device *dev = &pdev->dev;
+	const char *name = dev_name(dev);
+	struct ts5500_priv *priv;
+	struct resource *res;
+	unsigned long flags;
+	int ret;
+
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!res) {
+		dev_err(dev, "missing IRQ resource\n");
+		return -EINVAL;
+	}
+
+	priv = devm_kzalloc(dev, sizeof(struct ts5500_priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, priv);
+	priv->hwirq = res->start;
+	spin_lock_init(&priv->lock);
+
+	priv->gpio_chip.owner = THIS_MODULE;
+	priv->gpio_chip.label = name;
+	priv->gpio_chip.dev = dev;
+	priv->gpio_chip.direction_input = ts5500_gpio_input;
+	priv->gpio_chip.direction_output = ts5500_gpio_output;
+	priv->gpio_chip.get = ts5500_gpio_get;
+	priv->gpio_chip.set = ts5500_gpio_set;
+	priv->gpio_chip.to_irq = ts5500_gpio_to_irq;
+	priv->gpio_chip.base = -1;
+	if (pdata) {
+		priv->gpio_chip.base = pdata->base;
+		priv->strap = pdata->strap;
+	}
+
+	switch (block) {
+	case TS5500_DIO1:
+		priv->pinout = ts5500_dio1;
+		priv->gpio_chip.ngpio = ARRAY_SIZE(ts5500_dio1);
+
+		if (!devm_request_region(dev, 0x7a, 3, name)) {
+			dev_err(dev, "failed to request %s ports\n", name);
+			return -EBUSY;
+		}
+		break;
+	case TS5500_DIO2:
+		priv->pinout = ts5500_dio2;
+		priv->gpio_chip.ngpio = ARRAY_SIZE(ts5500_dio2);
+
+		if (!devm_request_region(dev, 0x7e, 2, name)) {
+			dev_err(dev, "failed to request %s ports\n", name);
+			return -EBUSY;
+		}
+
+		if (hex7d_reserved)
+			break;
+
+		if (!devm_request_region(dev, 0x7d, 1, name)) {
+			dev_err(dev, "failed to request %s 7D\n", name);
+			return -EBUSY;
+		}
+
+		hex7d_reserved = true;
+		break;
+	case TS5500_LCD:
+	case TS5600_LCD:
+		priv->pinout = ts5500_lcd;
+		priv->gpio_chip.ngpio = ARRAY_SIZE(ts5500_lcd);
+
+		if (!devm_request_region(dev, 0x72, 2, name)) {
+			dev_err(dev, "failed to request %s ports\n", name);
+			return -EBUSY;
+		}
+
+		if (!hex7d_reserved) {
+			if (!devm_request_region(dev, 0x7d, 1, name)) {
+				dev_err(dev, "failed to request %s 7D\n", name);
+				return -EBUSY;
+			}
+
+			hex7d_reserved = true;
+		}
+
+		/* Ensure usage of LCD port as DIO */
+		spin_lock_irqsave(&priv->lock, flags);
+		ts5500_clear_mask(BIT(4), 0x7d);
+		spin_unlock_irqrestore(&priv->lock, flags);
+		break;
+	}
+
+	ret = gpiochip_add(&priv->gpio_chip);
+	if (ret) {
+		dev_err(dev, "failed to register the gpio chip\n");
+		return ret;
+	}
+
+	ret = ts5500_enable_irq(priv);
+	if (ret) {
+		dev_err(dev, "invalid interrupt %d\n", priv->hwirq);
+		goto cleanup;
+	}
+
+	return 0;
+cleanup:
+	if (gpiochip_remove(&priv->gpio_chip))
+		dev_err(dev, "failed to remove gpio chip\n");
+	return ret;
+}
+
+static int __devexit ts5500_dio_remove(struct platform_device *pdev)
+{
+	struct ts5500_priv *priv = platform_get_drvdata(pdev);
+
+	ts5500_disable_irq(priv);
+	return gpiochip_remove(&priv->gpio_chip);
+}
+
+static struct platform_device_id ts5500_dio_ids[] = {
+	{ "ts5500-dio1", TS5500_DIO1 },
+	{ "ts5500-dio2", TS5500_DIO2 },
+	{ "ts5500-dio-lcd", TS5500_LCD },
+	{ "ts5600-dio-lcd", TS5600_LCD },
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, ts5500_dio_ids);
+
+static struct platform_driver ts5500_dio_driver = {
+	.driver = {
+		.name = "ts5500-dio",
+		.owner = THIS_MODULE,
+	},
+	.probe = ts5500_dio_probe,
+	.remove = __devexit_p(ts5500_dio_remove),
+	.id_table = ts5500_dio_ids,
+};
+
+module_platform_driver(ts5500_dio_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Savoir-faire Linux Inc. <kernel@savoirfairelinux.com>");
+MODULE_DESCRIPTION("Technologic Systems TS-5500 Digital I/O driver");
diff --git a/include/linux/platform_data/gpio-ts5500.h b/include/linux/platform_data/gpio-ts5500.h
new file mode 100644
index 000000000000..b10d11c9bb49
--- /dev/null
+++ b/include/linux/platform_data/gpio-ts5500.h
@@ -0,0 +1,27 @@
+/*
+ * GPIO (DIO) header for Technologic Systems TS-5500
+ *
+ * Copyright (c) 2012 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _PDATA_GPIO_TS5500_H
+#define _PDATA_GPIO_TS5500_H
+
+/**
+ * struct ts5500_dio_platform_data - TS-5500 pin block configuration
+ * @base:	The GPIO base number to use.
+ * @strap:	The only pin connected to an interrupt in a block is input-only.
+ *		If you need a bidirectional line which can trigger an IRQ, you
+ *		may strap it with an in/out pin. This flag indicates this case.
+ */
+struct ts5500_dio_platform_data {
+	int base;
+	bool strap;
+};
+
+#endif /* _PDATA_GPIO_TS5500_H */
-- 
cgit v1.2.3-55-g7522


From dbd3fc3345390a989a033427aa915a0dfb62149f Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas
Date: Mon, 10 Dec 2012 11:24:42 -0700
Subject: PCI: Use phys_addr_t for physical ROM address

Use phys_addr_t rather than "void *" for physical memory address.
This removes casts and fixes a "cast from pointer to integer of different
size" warning on ppc44x_defconfig.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>---
 arch/x86/pci/common.c | 4 ++--
 drivers/pci/rom.c     | 2 +-
 include/linux/pci.h   | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index fddb9f66cc47..d07f3bbca5a1 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -628,8 +628,8 @@ int pcibios_add_device(struct pci_dev *dev)
 			    (PCI_FUNC(dev->devfn) == rom->function) &&
 			    (dev->vendor == rom->vendor) &&
 			    (dev->device == rom->devid)) {
-				dev->rom = (void *)(unsigned long)(pa_data +
-				      offsetof(struct pci_setup_rom, romdata));
+				dev->rom = pa_data +
+				      offsetof(struct pci_setup_rom, romdata);
 				dev->romlen = rom->pcilen;
 			}
 		}
diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index 3a3828fbc879..ab886b7ee327 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -122,7 +122,7 @@ void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size)
 	 */
 	if (pdev->rom && pdev->romlen) {
 		*size = pdev->romlen;
-		return phys_to_virt((phys_addr_t)pdev->rom);
+		return phys_to_virt(pdev->rom);
 	/*
 	 * IORESOURCE_ROM_SHADOW set on x86, x86_64 and IA64 supports legacy
 	 * memory map if the VGA enable bit of the Bridge Control register is
diff --git a/include/linux/pci.h b/include/linux/pci.h
index f116b2d859dc..957563b7a5e3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -333,7 +333,7 @@ struct pci_dev {
 	};
 	struct pci_ats	*ats;	/* Address Translation Service */
 #endif
-	void *rom; /* Physical pointer to ROM if it's not from the BAR */
+	phys_addr_t rom; /* Physical address of ROM if it's not from the BAR */
 	size_t romlen; /* Length of ROM if it's not from the BAR */
 };
 
-- 
cgit v1.2.3-55-g7522


From ab5c4f71d8c7add173a2d32e5beefdaaf1b7cbbc Mon Sep 17 00:00:00 2001
From: Gabor Juhos
Date: Mon, 10 Dec 2012 15:30:28 +0100
Subject: ath9k: allow to load EEPROM content via firmware API

The calibration data for devices w/o a separate
EEPROM chip can be specified via the 'eeprom_data'
field of 'ath9k_platform_data'. The 'eeprom_data'
is usually filled from board specific setup
functions. It is easy if the EEPROM data is mapped
to the memory, but it can be complicated if it is
stored elsewhere.

The patch adds support for loading of the EEPROM
data via the firmware API to avoid this limitation.

Signed-off-by: Gabor Juhos <juhosg@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/net/wireless/ath/ath9k/eeprom.c | 19 ++++++++++-
 drivers/net/wireless/ath/ath9k/hw.h     |  3 ++
 drivers/net/wireless/ath/ath9k/init.c   | 60 ++++++++++++++++++++++++++++++++-
 include/linux/ath9k_platform.h          |  2 ++
 4 files changed, 82 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c
index eb9ac5ea6180..971d770722cf 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom.c
@@ -113,12 +113,29 @@ void ath9k_hw_usb_gen_fill_eeprom(struct ath_hw *ah, u16 *eep_data,
 	}
 }
 
+static bool ath9k_hw_nvram_read_blob(struct ath_hw *ah, u32 off,
+				     u16 *data)
+{
+	u16 *blob_data;
+
+	if (off * sizeof(u16) > ah->eeprom_blob->size)
+		return false;
+
+	blob_data = (u16 *)ah->eeprom_blob->data;
+	*data =  blob_data[off];
+	return true;
+}
+
 bool ath9k_hw_nvram_read(struct ath_hw *ah, u32 off, u16 *data)
 {
 	struct ath_common *common = ath9k_hw_common(ah);
 	bool ret;
 
-	ret = common->bus_ops->eeprom_read(common, off, data);
+	if (ah->eeprom_blob)
+		ret = ath9k_hw_nvram_read_blob(ah, off, data);
+	else
+		ret = common->bus_ops->eeprom_read(common, off, data);
+
 	if (!ret)
 		ath_dbg(common, EEPROM,
 			"unable to read eeprom region at offset %u\n", off);
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index eff67592db18..7f1a8e91c908 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -20,6 +20,7 @@
 #include <linux/if_ether.h>
 #include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/firmware.h>
 
 #include "mac.h"
 #include "ani.h"
@@ -921,6 +922,8 @@ struct ath_hw {
 	bool is_clk_25mhz;
 	int (*get_mac_revision)(void);
 	int (*external_reset)(void);
+
+	const struct firmware *eeprom_blob;
 };
 
 struct ath_bus_ops {
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 80cae53a33e5..27703a5e48d6 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -23,6 +23,11 @@
 
 #include "ath9k.h"
 
+struct ath9k_eeprom_ctx {
+	struct completion complete;
+	struct ath_hw *ah;
+};
+
 static char *dev_info = "ath9k";
 
 MODULE_AUTHOR("Atheros Communications");
@@ -506,6 +511,51 @@ static void ath9k_init_misc(struct ath_softc *sc)
 		sc->ant_comb.count = ATH_ANT_DIV_COMB_INIT_COUNT;
 }
 
+static void ath9k_eeprom_request_cb(const struct firmware *eeprom_blob,
+				    void *ctx)
+{
+	struct ath9k_eeprom_ctx *ec = ctx;
+
+	if (eeprom_blob)
+		ec->ah->eeprom_blob = eeprom_blob;
+
+	complete(&ec->complete);
+}
+
+static int ath9k_eeprom_request(struct ath_softc *sc, const char *name)
+{
+	struct ath9k_eeprom_ctx ec;
+	struct ath_hw *ah = ah = sc->sc_ah;
+	int err;
+
+	/* try to load the EEPROM content asynchronously */
+	init_completion(&ec.complete);
+	ec.ah = sc->sc_ah;
+
+	err = request_firmware_nowait(THIS_MODULE, 1, name, sc->dev, GFP_KERNEL,
+				      &ec, ath9k_eeprom_request_cb);
+	if (err < 0) {
+		ath_err(ath9k_hw_common(ah),
+			"EEPROM request failed\n");
+		return err;
+	}
+
+	wait_for_completion(&ec.complete);
+
+	if (!ah->eeprom_blob) {
+		ath_err(ath9k_hw_common(ah),
+			"Unable to load EEPROM file %s\n", name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void ath9k_eeprom_release(struct ath_softc *sc)
+{
+	release_firmware(sc->sc_ah->eeprom_blob);
+}
+
 static int ath9k_init_softc(u16 devid, struct ath_softc *sc,
 			    const struct ath_bus_ops *bus_ops)
 {
@@ -583,6 +633,12 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc,
 	ath_read_cachesize(common, &csz);
 	common->cachelsz = csz << 2; /* convert to bytes */
 
+	if (pdata->eeprom_name) {
+		ret = ath9k_eeprom_request(sc, pdata->eeprom_name);
+		if (ret)
+			goto err_eeprom;
+	}
+
 	/* Initializes the hardware for all supported chipsets */
 	ret = ath9k_hw_init(ah);
 	if (ret)
@@ -619,7 +675,8 @@ err_btcoex:
 err_queues:
 	ath9k_hw_deinit(ah);
 err_hw:
-
+	ath9k_eeprom_release(sc);
+err_eeprom:
 	kfree(ah);
 	sc->sc_ah = NULL;
 
@@ -882,6 +939,7 @@ static void ath9k_deinit_softc(struct ath_softc *sc)
 	if (sc->dfs_detector != NULL)
 		sc->dfs_detector->exit(sc->dfs_detector);
 
+	ath9k_eeprom_release(sc);
 	kfree(sc->sc_ah);
 	sc->sc_ah = NULL;
 }
diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h
index 6e3f54f37844..fcdd81bd5314 100644
--- a/include/linux/ath9k_platform.h
+++ b/include/linux/ath9k_platform.h
@@ -22,6 +22,8 @@
 #define ATH9K_PLAT_EEP_MAX_WORDS	2048
 
 struct ath9k_platform_data {
+	const char *eeprom_name;
+
 	u16 eeprom_data[ATH9K_PLAT_EEP_MAX_WORDS];
 	u8 *macaddr;
 
-- 
cgit v1.2.3-55-g7522


From dd31866b0d55c9b70722ebad6ccd643223d9269e Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim
Date: Fri, 2 Nov 2012 17:06:26 +0900
Subject: f2fs: add on-disk layout

This adds a header file describing the on-disk layout of f2fs.

Signed-off-by: Changman Lee <cm224.lee@samsung.com>
Signed-off-by: Chul Lee <chur.lee@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
---
 include/linux/f2fs_fs.h | 410 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 410 insertions(+)
 create mode 100644 include/linux/f2fs_fs.h

(limited to 'include')

diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
new file mode 100644
index 000000000000..1429ece7caab
--- /dev/null
+++ b/include/linux/f2fs_fs.h
@@ -0,0 +1,410 @@
+/**
+ * include/linux/f2fs_fs.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _LINUX_F2FS_FS_H
+#define _LINUX_F2FS_FS_H
+
+#include <linux/pagemap.h>
+#include <linux/types.h>
+
+#define F2FS_SUPER_OFFSET		1024	/* byte-size offset */
+#define F2FS_LOG_SECTOR_SIZE		9	/* 9 bits for 512 byte */
+#define F2FS_LOG_SECTORS_PER_BLOCK	3	/* 4KB: F2FS_BLKSIZE */
+#define F2FS_BLKSIZE			4096	/* support only 4KB block */
+#define F2FS_MAX_EXTENSION		64	/* # of extension entries */
+
+#define NULL_ADDR		0x0U
+#define NEW_ADDR		-1U
+
+#define F2FS_ROOT_INO(sbi)	(sbi->root_ino_num)
+#define F2FS_NODE_INO(sbi)	(sbi->node_ino_num)
+#define F2FS_META_INO(sbi)	(sbi->meta_ino_num)
+
+/* This flag is used by node and meta inodes, and by recovery */
+#define GFP_F2FS_ZERO	(GFP_NOFS | __GFP_ZERO)
+
+/*
+ * For further optimization on multi-head logs, on-disk layout supports maximum
+ * 16 logs by default. The number, 16, is expected to cover all the cases
+ * enoughly. The implementaion currently uses no more than 6 logs.
+ * Half the logs are used for nodes, and the other half are used for data.
+ */
+#define MAX_ACTIVE_LOGS	16
+#define MAX_ACTIVE_NODE_LOGS	8
+#define MAX_ACTIVE_DATA_LOGS	8
+
+/*
+ * For superblock
+ */
+struct f2fs_super_block {
+	__le32 magic;			/* Magic Number */
+	__le16 major_ver;		/* Major Version */
+	__le16 minor_ver;		/* Minor Version */
+	__le32 log_sectorsize;		/* log2 sector size in bytes */
+	__le32 log_sectors_per_block;	/* log2 # of sectors per block */
+	__le32 log_blocksize;		/* log2 block size in bytes */
+	__le32 log_blocks_per_seg;	/* log2 # of blocks per segment */
+	__le32 segs_per_sec;		/* # of segments per section */
+	__le32 secs_per_zone;		/* # of sections per zone */
+	__le32 checksum_offset;		/* checksum offset inside super block */
+	__le64 block_count;		/* total # of user blocks */
+	__le32 section_count;		/* total # of sections */
+	__le32 segment_count;		/* total # of segments */
+	__le32 segment_count_ckpt;	/* # of segments for checkpoint */
+	__le32 segment_count_sit;	/* # of segments for SIT */
+	__le32 segment_count_nat;	/* # of segments for NAT */
+	__le32 segment_count_ssa;	/* # of segments for SSA */
+	__le32 segment_count_main;	/* # of segments for main area */
+	__le32 segment0_blkaddr;	/* start block address of segment 0 */
+	__le32 cp_blkaddr;		/* start block address of checkpoint */
+	__le32 sit_blkaddr;		/* start block address of SIT */
+	__le32 nat_blkaddr;		/* start block address of NAT */
+	__le32 ssa_blkaddr;		/* start block address of SSA */
+	__le32 main_blkaddr;		/* start block address of main area */
+	__le32 root_ino;		/* root inode number */
+	__le32 node_ino;		/* node inode number */
+	__le32 meta_ino;		/* meta inode number */
+	__u8 uuid[16];			/* 128-bit uuid for volume */
+	__le16 volume_name[512];	/* volume name */
+	__le32 extension_count;		/* # of extensions below */
+	__u8 extension_list[F2FS_MAX_EXTENSION][8];	/* extension array */
+} __packed;
+
+/*
+ * For checkpoint
+ */
+#define CP_ERROR_FLAG		0x00000008
+#define CP_COMPACT_SUM_FLAG	0x00000004
+#define CP_ORPHAN_PRESENT_FLAG	0x00000002
+#define CP_UMOUNT_FLAG		0x00000001
+
+struct f2fs_checkpoint {
+	__le64 checkpoint_ver;		/* checkpoint block version number */
+	__le64 user_block_count;	/* # of user blocks */
+	__le64 valid_block_count;	/* # of valid blocks in main area */
+	__le32 rsvd_segment_count;	/* # of reserved segments for gc */
+	__le32 overprov_segment_count;	/* # of overprovision segments */
+	__le32 free_segment_count;	/* # of free segments in main area */
+
+	/* information of current node segments */
+	__le32 cur_node_segno[MAX_ACTIVE_NODE_LOGS];
+	__le16 cur_node_blkoff[MAX_ACTIVE_NODE_LOGS];
+	/* information of current data segments */
+	__le32 cur_data_segno[MAX_ACTIVE_DATA_LOGS];
+	__le16 cur_data_blkoff[MAX_ACTIVE_DATA_LOGS];
+	__le32 ckpt_flags;		/* Flags : umount and journal_present */
+	__le32 cp_pack_total_block_count;	/* total # of one cp pack */
+	__le32 cp_pack_start_sum;	/* start block number of data summary */
+	__le32 valid_node_count;	/* Total number of valid nodes */
+	__le32 valid_inode_count;	/* Total number of valid inodes */
+	__le32 next_free_nid;		/* Next free node number */
+	__le32 sit_ver_bitmap_bytesize;	/* Default value 64 */
+	__le32 nat_ver_bitmap_bytesize; /* Default value 256 */
+	__le32 checksum_offset;		/* checksum offset inside cp block */
+	__le64 elapsed_time;		/* mounted time */
+	/* allocation type of current segment */
+	unsigned char alloc_type[MAX_ACTIVE_LOGS];
+
+	/* SIT and NAT version bitmap */
+	unsigned char sit_nat_version_bitmap[1];
+} __packed;
+
+/*
+ * For orphan inode management
+ */
+#define F2FS_ORPHANS_PER_BLOCK	1020
+
+struct f2fs_orphan_block {
+	__le32 ino[F2FS_ORPHANS_PER_BLOCK];	/* inode numbers */
+	__le32 reserved;	/* reserved */
+	__le16 blk_addr;	/* block index in current CP */
+	__le16 blk_count;	/* Number of orphan inode blocks in CP */
+	__le32 entry_count;	/* Total number of orphan nodes in current CP */
+	__le32 check_sum;	/* CRC32 for orphan inode block */
+} __packed;
+
+/*
+ * For NODE structure
+ */
+struct f2fs_extent {
+	__le32 fofs;		/* start file offset of the extent */
+	__le32 blk_addr;	/* start block address of the extent */
+	__le32 len;		/* lengh of the extent */
+} __packed;
+
+#define F2FS_MAX_NAME_LEN	256
+#define ADDRS_PER_INODE         923	/* Address Pointers in an Inode */
+#define ADDRS_PER_BLOCK         1018	/* Address Pointers in a Direct Block */
+#define NIDS_PER_BLOCK          1018	/* Node IDs in an Indirect Block */
+
+struct f2fs_inode {
+	__le16 i_mode;			/* file mode */
+	__u8 i_advise;			/* file hints */
+	__u8 i_reserved;		/* reserved */
+	__le32 i_uid;			/* user ID */
+	__le32 i_gid;			/* group ID */
+	__le32 i_links;			/* links count */
+	__le64 i_size;			/* file size in bytes */
+	__le64 i_blocks;		/* file size in blocks */
+	__le64 i_atime;			/* access time */
+	__le64 i_ctime;			/* change time */
+	__le64 i_mtime;			/* modification time */
+	__le32 i_atime_nsec;		/* access time in nano scale */
+	__le32 i_ctime_nsec;		/* change time in nano scale */
+	__le32 i_mtime_nsec;		/* modification time in nano scale */
+	__le32 i_generation;		/* file version (for NFS) */
+	__le32 i_current_depth;		/* only for directory depth */
+	__le32 i_xattr_nid;		/* nid to save xattr */
+	__le32 i_flags;			/* file attributes */
+	__le32 i_pino;			/* parent inode number */
+	__le32 i_namelen;		/* file name length */
+	__u8 i_name[F2FS_MAX_NAME_LEN];	/* file name for SPOR */
+
+	struct f2fs_extent i_ext;	/* caching a largest extent */
+
+	__le32 i_addr[ADDRS_PER_INODE];	/* Pointers to data blocks */
+
+	__le32 i_nid[5];		/* direct(2), indirect(2),
+						double_indirect(1) node id */
+} __packed;
+
+struct direct_node {
+	__le32 addr[ADDRS_PER_BLOCK];	/* array of data block address */
+} __packed;
+
+struct indirect_node {
+	__le32 nid[NIDS_PER_BLOCK];	/* array of data block address */
+} __packed;
+
+enum {
+	COLD_BIT_SHIFT = 0,
+	FSYNC_BIT_SHIFT,
+	DENT_BIT_SHIFT,
+	OFFSET_BIT_SHIFT
+};
+
+struct node_footer {
+	__le32 nid;		/* node id */
+	__le32 ino;		/* inode nunmber */
+	__le32 flag;		/* include cold/fsync/dentry marks and offset */
+	__le64 cp_ver;		/* checkpoint version */
+	__le32 next_blkaddr;	/* next node page block address */
+} __packed;
+
+struct f2fs_node {
+	/* can be one of three types: inode, direct, and indirect types */
+	union {
+		struct f2fs_inode i;
+		struct direct_node dn;
+		struct indirect_node in;
+	};
+	struct node_footer footer;
+} __packed;
+
+/*
+ * For NAT entries
+ */
+#define NAT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_nat_entry))
+
+struct f2fs_nat_entry {
+	__u8 version;		/* latest version of cached nat entry */
+	__le32 ino;		/* inode number */
+	__le32 block_addr;	/* block address */
+} __packed;
+
+struct f2fs_nat_block {
+	struct f2fs_nat_entry entries[NAT_ENTRY_PER_BLOCK];
+} __packed;
+
+/*
+ * For SIT entries
+ *
+ * Each segment is 2MB in size by default so that a bitmap for validity of
+ * there-in blocks should occupy 64 bytes, 512 bits.
+ * Not allow to change this.
+ */
+#define SIT_VBLOCK_MAP_SIZE 64
+#define SIT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_sit_entry))
+
+/*
+ * Note that f2fs_sit_entry->vblocks has the following bit-field information.
+ * [15:10] : allocation type such as CURSEG_XXXX_TYPE
+ * [9:0] : valid block count
+ */
+#define SIT_VBLOCKS_SHIFT	10
+#define SIT_VBLOCKS_MASK	((1 << SIT_VBLOCKS_SHIFT) - 1)
+#define GET_SIT_VBLOCKS(raw_sit)				\
+	(le16_to_cpu((raw_sit)->vblocks) & SIT_VBLOCKS_MASK)
+#define GET_SIT_TYPE(raw_sit)					\
+	((le16_to_cpu((raw_sit)->vblocks) & ~SIT_VBLOCKS_MASK)	\
+	 >> SIT_VBLOCKS_SHIFT)
+
+struct f2fs_sit_entry {
+	__le16 vblocks;				/* reference above */
+	__u8 valid_map[SIT_VBLOCK_MAP_SIZE];	/* bitmap for valid blocks */
+	__le64 mtime;				/* segment age for cleaning */
+} __packed;
+
+struct f2fs_sit_block {
+	struct f2fs_sit_entry entries[SIT_ENTRY_PER_BLOCK];
+} __packed;
+
+/*
+ * For segment summary
+ *
+ * One summary block contains exactly 512 summary entries, which represents
+ * exactly 2MB segment by default. Not allow to change the basic units.
+ *
+ * NOTE: For initializing fields, you must use set_summary
+ *
+ * - If data page, nid represents dnode's nid
+ * - If node page, nid represents the node page's nid.
+ *
+ * The ofs_in_node is used by only data page. It represents offset
+ * from node's page's beginning to get a data block address.
+ * ex) data_blkaddr = (block_t)(nodepage_start_address + ofs_in_node)
+ */
+#define ENTRIES_IN_SUM		512
+#define	SUMMARY_SIZE		(sizeof(struct f2fs_summary))
+#define	SUM_FOOTER_SIZE		(sizeof(struct summary_footer))
+#define SUM_ENTRY_SIZE		(SUMMARY_SIZE * ENTRIES_IN_SUM)
+
+/* a summary entry for a 4KB-sized block in a segment */
+struct f2fs_summary {
+	__le32 nid;		/* parent node id */
+	union {
+		__u8 reserved[3];
+		struct {
+			__u8 version;		/* node version number */
+			__le16 ofs_in_node;	/* block index in parent node */
+		} __packed;
+	};
+} __packed;
+
+/* summary block type, node or data, is stored to the summary_footer */
+#define SUM_TYPE_NODE		(1)
+#define SUM_TYPE_DATA		(0)
+
+struct summary_footer {
+	unsigned char entry_type;	/* SUM_TYPE_XXX */
+	__u32 check_sum;		/* summary checksum */
+} __packed;
+
+#define SUM_JOURNAL_SIZE	(PAGE_CACHE_SIZE - SUM_FOOTER_SIZE -\
+				SUM_ENTRY_SIZE)
+#define NAT_JOURNAL_ENTRIES	((SUM_JOURNAL_SIZE - 2) /\
+				sizeof(struct nat_journal_entry))
+#define NAT_JOURNAL_RESERVED	((SUM_JOURNAL_SIZE - 2) %\
+				sizeof(struct nat_journal_entry))
+#define SIT_JOURNAL_ENTRIES	((SUM_JOURNAL_SIZE - 2) /\
+				sizeof(struct sit_journal_entry))
+#define SIT_JOURNAL_RESERVED	((SUM_JOURNAL_SIZE - 2) %\
+				sizeof(struct sit_journal_entry))
+/*
+ * frequently updated NAT/SIT entries can be stored in the spare area in
+ * summary blocks
+ */
+enum {
+	NAT_JOURNAL = 0,
+	SIT_JOURNAL
+};
+
+struct nat_journal_entry {
+	__le32 nid;
+	struct f2fs_nat_entry ne;
+} __packed;
+
+struct nat_journal {
+	struct nat_journal_entry entries[NAT_JOURNAL_ENTRIES];
+	__u8 reserved[NAT_JOURNAL_RESERVED];
+} __packed;
+
+struct sit_journal_entry {
+	__le32 segno;
+	struct f2fs_sit_entry se;
+} __packed;
+
+struct sit_journal {
+	struct sit_journal_entry entries[SIT_JOURNAL_ENTRIES];
+	__u8 reserved[SIT_JOURNAL_RESERVED];
+} __packed;
+
+/* 4KB-sized summary block structure */
+struct f2fs_summary_block {
+	struct f2fs_summary entries[ENTRIES_IN_SUM];
+	union {
+		__le16 n_nats;
+		__le16 n_sits;
+	};
+	/* spare area is used by NAT or SIT journals */
+	union {
+		struct nat_journal nat_j;
+		struct sit_journal sit_j;
+	};
+	struct summary_footer footer;
+} __packed;
+
+/*
+ * For directory operations
+ */
+#define F2FS_DOT_HASH		0
+#define F2FS_DDOT_HASH		F2FS_DOT_HASH
+#define F2FS_MAX_HASH		(~((0x3ULL) << 62))
+#define F2FS_HASH_COL_BIT	((0x1ULL) << 63)
+
+typedef __le32	f2fs_hash_t;
+
+/* One directory entry slot covers 8bytes-long file name */
+#define F2FS_NAME_LEN		8
+
+/* the number of dentry in a block */
+#define NR_DENTRY_IN_BLOCK	214
+
+/* MAX level for dir lookup */
+#define MAX_DIR_HASH_DEPTH	63
+
+#define SIZE_OF_DIR_ENTRY	11	/* by byte */
+#define SIZE_OF_DENTRY_BITMAP	((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \
+					BITS_PER_BYTE)
+#define SIZE_OF_RESERVED	(PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \
+				F2FS_NAME_LEN) * \
+				NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP))
+
+/* One directory entry slot representing F2FS_NAME_LEN-sized file name */
+struct f2fs_dir_entry {
+	__le32 hash_code;	/* hash code of file name */
+	__le32 ino;		/* inode number */
+	__le16 name_len;	/* lengh of file name */
+	__u8 file_type;		/* file type */
+} __packed;
+
+/* 4KB-sized directory entry block */
+struct f2fs_dentry_block {
+	/* validity bitmap for directory entries in each block */
+	__u8 dentry_bitmap[SIZE_OF_DENTRY_BITMAP];
+	__u8 reserved[SIZE_OF_RESERVED];
+	struct f2fs_dir_entry dentry[NR_DENTRY_IN_BLOCK];
+	__u8 filename[NR_DENTRY_IN_BLOCK][F2FS_NAME_LEN];
+} __packed;
+
+/* file types used in inode_info->flags */
+enum {
+	F2FS_FT_UNKNOWN,
+	F2FS_FT_REG_FILE,
+	F2FS_FT_DIR,
+	F2FS_FT_CHRDEV,
+	F2FS_FT_BLKDEV,
+	F2FS_FT_FIFO,
+	F2FS_FT_SOCK,
+	F2FS_FT_SYMLINK,
+	F2FS_FT_MAX
+};
+
+#endif  /* _LINUX_F2FS_FS_H */
-- 
cgit v1.2.3-55-g7522


From 39a53e0ce0df01b3cf4bb898c7ae2fd2189647d5 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim
Date: Wed, 28 Nov 2012 13:37:31 +0900
Subject: f2fs: add superblock and major in-memory structure

This adds the following major in-memory structures in f2fs.

- f2fs_sb_info:
  contains f2fs-specific information, two special inode pointers for node and
  meta address spaces, and orphan inode management.

- f2fs_inode_info:
  contains vfs_inode and other fs-specific information.

- f2fs_nm_info:
  contains node manager information such as NAT entry cache, free nid list,
  and NAT page management.

- f2fs_node_info:
  represents a node as node id, inode number, block address, and its version.

- f2fs_sm_info:
  contains segment manager information such as SIT entry cache, free segment
  map, current active logs, dirty segment management, and segment utilization.
  The specific structures are sit_info, free_segmap_info, dirty_seglist_info,
  curseg_info.

In addition, add F2FS_SUPER_MAGIC in magic.h.

Signed-off-by: Chul Lee <chur.lee@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
---
 fs/f2fs/f2fs.h             | 1062 ++++++++++++++++++++++++++++++++++++++++++++
 fs/f2fs/node.h             |  353 +++++++++++++++
 fs/f2fs/segment.h          |  615 +++++++++++++++++++++++++
 include/uapi/linux/magic.h |    1 +
 4 files changed, 2031 insertions(+)
 create mode 100644 fs/f2fs/f2fs.h
 create mode 100644 fs/f2fs/node.h
 create mode 100644 fs/f2fs/segment.h

(limited to 'include')

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
new file mode 100644
index 000000000000..7aa70b54172d
--- /dev/null
+++ b/fs/f2fs/f2fs.h
@@ -0,0 +1,1062 @@
+/**
+ * fs/f2fs/f2fs.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _LINUX_F2FS_H
+#define _LINUX_F2FS_H
+
+#include <linux/types.h>
+#include <linux/page-flags.h>
+#include <linux/buffer_head.h>
+#include <linux/version.h>
+#include <linux/slab.h>
+#include <linux/crc32.h>
+#include <linux/magic.h>
+
+/*
+ * For mount options
+ */
+#define F2FS_MOUNT_BG_GC		0x00000001
+#define F2FS_MOUNT_DISABLE_ROLL_FORWARD	0x00000002
+#define F2FS_MOUNT_DISCARD		0x00000004
+#define F2FS_MOUNT_NOHEAP		0x00000008
+#define F2FS_MOUNT_XATTR_USER		0x00000010
+#define F2FS_MOUNT_POSIX_ACL		0x00000020
+#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY	0x00000040
+
+#define clear_opt(sbi, option)	(sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
+#define set_opt(sbi, option)	(sbi->mount_opt.opt |= F2FS_MOUNT_##option)
+#define test_opt(sbi, option)	(sbi->mount_opt.opt & F2FS_MOUNT_##option)
+
+#define ver_after(a, b)	(typecheck(unsigned long long, a) &&		\
+		typecheck(unsigned long long, b) &&			\
+		((long long)((a) - (b)) > 0))
+
+typedef u64 block_t;
+typedef u32 nid_t;
+
+struct f2fs_mount_info {
+	unsigned int	opt;
+};
+
+static inline __u32 f2fs_crc32(void *buff, size_t len)
+{
+	return crc32_le(F2FS_SUPER_MAGIC, buff, len);
+}
+
+static inline bool f2fs_crc_valid(__u32 blk_crc, void *buff, size_t buff_size)
+{
+	return f2fs_crc32(buff, buff_size) == blk_crc;
+}
+
+/*
+ * For checkpoint manager
+ */
+enum {
+	NAT_BITMAP,
+	SIT_BITMAP
+};
+
+/* for the list of orphan inodes */
+struct orphan_inode_entry {
+	struct list_head list;	/* list head */
+	nid_t ino;		/* inode number */
+};
+
+/* for the list of directory inodes */
+struct dir_inode_entry {
+	struct list_head list;	/* list head */
+	struct inode *inode;	/* vfs inode pointer */
+};
+
+/* for the list of fsync inodes, used only during recovery */
+struct fsync_inode_entry {
+	struct list_head list;	/* list head */
+	struct inode *inode;	/* vfs inode pointer */
+	block_t blkaddr;	/* block address locating the last inode */
+};
+
+#define nats_in_cursum(sum)		(le16_to_cpu(sum->n_nats))
+#define sits_in_cursum(sum)		(le16_to_cpu(sum->n_sits))
+
+#define nat_in_journal(sum, i)		(sum->nat_j.entries[i].ne)
+#define nid_in_journal(sum, i)		(sum->nat_j.entries[i].nid)
+#define sit_in_journal(sum, i)		(sum->sit_j.entries[i].se)
+#define segno_in_journal(sum, i)	(sum->sit_j.entries[i].segno)
+
+static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i)
+{
+	int before = nats_in_cursum(rs);
+	rs->n_nats = cpu_to_le16(before + i);
+	return before;
+}
+
+static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
+{
+	int before = sits_in_cursum(rs);
+	rs->n_sits = cpu_to_le16(before + i);
+	return before;
+}
+
+/*
+ * For INODE and NODE manager
+ */
+#define XATTR_NODE_OFFSET	(-1)	/*
+					 * store xattrs to one node block per
+					 * file keeping -1 as its node offset to
+					 * distinguish from index node blocks.
+					 */
+#define RDONLY_NODE		1	/*
+					 * specify a read-only mode when getting
+					 * a node block. 0 is read-write mode.
+					 * used by get_dnode_of_data().
+					 */
+#define F2FS_LINK_MAX		32000	/* maximum link count per file */
+
+/* for in-memory extent cache entry */
+struct extent_info {
+	rwlock_t ext_lock;	/* rwlock for consistency */
+	unsigned int fofs;	/* start offset in a file */
+	u32 blk_addr;		/* start block address of the extent */
+	unsigned int len;	/* lenth of the extent */
+};
+
+/*
+ * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
+ */
+#define FADVISE_COLD_BIT	0x01
+
+struct f2fs_inode_info {
+	struct inode vfs_inode;		/* serve a vfs inode */
+	unsigned long i_flags;		/* keep an inode flags for ioctl */
+	unsigned char i_advise;		/* use to give file attribute hints */
+	unsigned int i_current_depth;	/* use only in directory structure */
+	umode_t i_acl_mode;		/* keep file acl mode temporarily */
+
+	/* Use below internally in f2fs*/
+	unsigned long flags;		/* use to pass per-file flags */
+	unsigned long long data_version;/* lastes version of data for fsync */
+	atomic_t dirty_dents;		/* # of dirty dentry pages */
+	f2fs_hash_t chash;		/* hash value of given file name */
+	unsigned int clevel;		/* maximum level of given file name */
+	nid_t i_xattr_nid;		/* node id that contains xattrs */
+	struct extent_info ext;		/* in-memory extent cache entry */
+};
+
+static inline void get_extent_info(struct extent_info *ext,
+					struct f2fs_extent i_ext)
+{
+	write_lock(&ext->ext_lock);
+	ext->fofs = le32_to_cpu(i_ext.fofs);
+	ext->blk_addr = le32_to_cpu(i_ext.blk_addr);
+	ext->len = le32_to_cpu(i_ext.len);
+	write_unlock(&ext->ext_lock);
+}
+
+static inline void set_raw_extent(struct extent_info *ext,
+					struct f2fs_extent *i_ext)
+{
+	read_lock(&ext->ext_lock);
+	i_ext->fofs = cpu_to_le32(ext->fofs);
+	i_ext->blk_addr = cpu_to_le32(ext->blk_addr);
+	i_ext->len = cpu_to_le32(ext->len);
+	read_unlock(&ext->ext_lock);
+}
+
+struct f2fs_nm_info {
+	block_t nat_blkaddr;		/* base disk address of NAT */
+	nid_t max_nid;			/* maximum possible node ids */
+	nid_t init_scan_nid;		/* the first nid to be scanned */
+	nid_t next_scan_nid;		/* the next nid to be scanned */
+
+	/* NAT cache management */
+	struct radix_tree_root nat_root;/* root of the nat entry cache */
+	rwlock_t nat_tree_lock;		/* protect nat_tree_lock */
+	unsigned int nat_cnt;		/* the # of cached nat entries */
+	struct list_head nat_entries;	/* cached nat entry list (clean) */
+	struct list_head dirty_nat_entries; /* cached nat entry list (dirty) */
+
+	/* free node ids management */
+	struct list_head free_nid_list;	/* a list for free nids */
+	spinlock_t free_nid_list_lock;	/* protect free nid list */
+	unsigned int fcnt;		/* the number of free node id */
+	struct mutex build_lock;	/* lock for build free nids */
+
+	/* for checkpoint */
+	char *nat_bitmap;		/* NAT bitmap pointer */
+	int bitmap_size;		/* bitmap size */
+};
+
+/*
+ * this structure is used as one of function parameters.
+ * all the information are dedicated to a given direct node block determined
+ * by the data offset in a file.
+ */
+struct dnode_of_data {
+	struct inode *inode;		/* vfs inode pointer */
+	struct page *inode_page;	/* its inode page, NULL is possible */
+	struct page *node_page;		/* cached direct node page */
+	nid_t nid;			/* node id of the direct node block */
+	unsigned int ofs_in_node;	/* data offset in the node page */
+	bool inode_page_locked;		/* inode page is locked or not */
+	block_t	data_blkaddr;		/* block address of the node block */
+};
+
+static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
+		struct page *ipage, struct page *npage, nid_t nid)
+{
+	dn->inode = inode;
+	dn->inode_page = ipage;
+	dn->node_page = npage;
+	dn->nid = nid;
+	dn->inode_page_locked = 0;
+}
+
+/*
+ * For SIT manager
+ *
+ * By default, there are 6 active log areas across the whole main area.
+ * When considering hot and cold data separation to reduce cleaning overhead,
+ * we split 3 for data logs and 3 for node logs as hot, warm, and cold types,
+ * respectively.
+ * In the current design, you should not change the numbers intentionally.
+ * Instead, as a mount option such as active_logs=x, you can use 2, 4, and 6
+ * logs individually according to the underlying devices. (default: 6)
+ * Just in case, on-disk layout covers maximum 16 logs that consist of 8 for
+ * data and 8 for node logs.
+ */
+#define	NR_CURSEG_DATA_TYPE	(3)
+#define NR_CURSEG_NODE_TYPE	(3)
+#define NR_CURSEG_TYPE	(NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
+
+enum {
+	CURSEG_HOT_DATA	= 0,	/* directory entry blocks */
+	CURSEG_WARM_DATA,	/* data blocks */
+	CURSEG_COLD_DATA,	/* multimedia or GCed data blocks */
+	CURSEG_HOT_NODE,	/* direct node blocks of directory files */
+	CURSEG_WARM_NODE,	/* direct node blocks of normal files */
+	CURSEG_COLD_NODE,	/* indirect node blocks */
+	NO_CHECK_TYPE
+};
+
+struct f2fs_sm_info {
+	struct sit_info *sit_info;		/* whole segment information */
+	struct free_segmap_info *free_info;	/* free segment information */
+	struct dirty_seglist_info *dirty_info;	/* dirty segment information */
+	struct curseg_info *curseg_array;	/* active segment information */
+
+	struct list_head wblist_head;	/* list of under-writeback pages */
+	spinlock_t wblist_lock;		/* lock for checkpoint */
+
+	block_t seg0_blkaddr;		/* block address of 0'th segment */
+	block_t main_blkaddr;		/* start block address of main area */
+	block_t ssa_blkaddr;		/* start block address of SSA area */
+
+	unsigned int segment_count;	/* total # of segments */
+	unsigned int main_segments;	/* # of segments in main area */
+	unsigned int reserved_segments;	/* # of reserved segments */
+	unsigned int ovp_segments;	/* # of overprovision segments */
+};
+
+/*
+ * For directory operation
+ */
+#define	NODE_DIR1_BLOCK		(ADDRS_PER_INODE + 1)
+#define	NODE_DIR2_BLOCK		(ADDRS_PER_INODE + 2)
+#define	NODE_IND1_BLOCK		(ADDRS_PER_INODE + 3)
+#define	NODE_IND2_BLOCK		(ADDRS_PER_INODE + 4)
+#define	NODE_DIND_BLOCK		(ADDRS_PER_INODE + 5)
+
+/*
+ * For superblock
+ */
+/*
+ * COUNT_TYPE for monitoring
+ *
+ * f2fs monitors the number of several block types such as on-writeback,
+ * dirty dentry blocks, dirty node blocks, and dirty meta blocks.
+ */
+enum count_type {
+	F2FS_WRITEBACK,
+	F2FS_DIRTY_DENTS,
+	F2FS_DIRTY_NODES,
+	F2FS_DIRTY_META,
+	NR_COUNT_TYPE,
+};
+
+/*
+ * FS_LOCK nesting subclasses for the lock validator:
+ *
+ * The locking order between these classes is
+ * RENAME -> DENTRY_OPS -> DATA_WRITE -> DATA_NEW
+ *    -> DATA_TRUNC -> NODE_WRITE -> NODE_NEW -> NODE_TRUNC
+ */
+enum lock_type {
+	RENAME,		/* for renaming operations */
+	DENTRY_OPS,	/* for directory operations */
+	DATA_WRITE,	/* for data write */
+	DATA_NEW,	/* for data allocation */
+	DATA_TRUNC,	/* for data truncate */
+	NODE_NEW,	/* for node allocation */
+	NODE_TRUNC,	/* for node truncate */
+	NODE_WRITE,	/* for node write */
+	NR_LOCK_TYPE,
+};
+
+/*
+ * The below are the page types of bios used in submti_bio().
+ * The available types are:
+ * DATA			User data pages. It operates as async mode.
+ * NODE			Node pages. It operates as async mode.
+ * META			FS metadata pages such as SIT, NAT, CP.
+ * NR_PAGE_TYPE		The number of page types.
+ * META_FLUSH		Make sure the previous pages are written
+ *			with waiting the bio's completion
+ * ...			Only can be used with META.
+ */
+enum page_type {
+	DATA,
+	NODE,
+	META,
+	NR_PAGE_TYPE,
+	META_FLUSH,
+};
+
+struct f2fs_sb_info {
+	struct super_block *sb;			/* pointer to VFS super block */
+	struct buffer_head *raw_super_buf;	/* buffer head of raw sb */
+	struct f2fs_super_block *raw_super;	/* raw super block pointer */
+	int s_dirty;				/* dirty flag for checkpoint */
+
+	/* for node-related operations */
+	struct f2fs_nm_info *nm_info;		/* node manager */
+	struct inode *node_inode;		/* cache node blocks */
+
+	/* for segment-related operations */
+	struct f2fs_sm_info *sm_info;		/* segment manager */
+	struct bio *bio[NR_PAGE_TYPE];		/* bios to merge */
+	sector_t last_block_in_bio[NR_PAGE_TYPE];	/* last block number */
+	struct rw_semaphore bio_sem;		/* IO semaphore */
+
+	/* for checkpoint */
+	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
+	struct inode *meta_inode;		/* cache meta blocks */
+	struct mutex cp_mutex;			/* for checkpoint procedure */
+	struct mutex fs_lock[NR_LOCK_TYPE];	/* for blocking FS operations */
+	struct mutex write_inode;		/* mutex for write inode */
+	struct mutex writepages;		/* mutex for writepages() */
+	int por_doing;				/* recovery is doing or not */
+
+	/* for orphan inode management */
+	struct list_head orphan_inode_list;	/* orphan inode list */
+	struct mutex orphan_inode_mutex;	/* for orphan inode list */
+	unsigned int n_orphans;			/* # of orphan inodes */
+
+	/* for directory inode management */
+	struct list_head dir_inode_list;	/* dir inode list */
+	spinlock_t dir_inode_lock;		/* for dir inode list lock */
+	unsigned int n_dirty_dirs;		/* # of dir inodes */
+
+	/* basic file system units */
+	unsigned int log_sectors_per_block;	/* log2 sectors per block */
+	unsigned int log_blocksize;		/* log2 block size */
+	unsigned int blocksize;			/* block size */
+	unsigned int root_ino_num;		/* root inode number*/
+	unsigned int node_ino_num;		/* node inode number*/
+	unsigned int meta_ino_num;		/* meta inode number*/
+	unsigned int log_blocks_per_seg;	/* log2 blocks per segment */
+	unsigned int blocks_per_seg;		/* blocks per segment */
+	unsigned int segs_per_sec;		/* segments per section */
+	unsigned int secs_per_zone;		/* sections per zone */
+	unsigned int total_sections;		/* total section count */
+	unsigned int total_node_count;		/* total node block count */
+	unsigned int total_valid_node_count;	/* valid node block count */
+	unsigned int total_valid_inode_count;	/* valid inode count */
+	int active_logs;			/* # of active logs */
+
+	block_t user_block_count;		/* # of user blocks */
+	block_t total_valid_block_count;	/* # of valid blocks */
+	block_t alloc_valid_block_count;	/* # of allocated blocks */
+	block_t last_valid_block_count;		/* for recovery */
+	u32 s_next_generation;			/* for NFS support */
+	atomic_t nr_pages[NR_COUNT_TYPE];	/* # of pages, see count_type */
+
+	struct f2fs_mount_info mount_opt;	/* mount options */
+
+	/* for cleaning operations */
+	struct mutex gc_mutex;			/* mutex for GC */
+	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
+
+	/*
+	 * for stat information.
+	 * one is for the LFS mode, and the other is for the SSR mode.
+	 */
+	struct f2fs_stat_info *stat_info;	/* FS status information */
+	unsigned int segment_count[2];		/* # of allocated segments */
+	unsigned int block_count[2];		/* # of allocated blocks */
+	unsigned int last_victim[2];		/* last victim segment # */
+	int total_hit_ext, read_hit_ext;	/* extent cache hit ratio */
+	int bg_gc;				/* background gc calls */
+	spinlock_t stat_lock;			/* lock for stat operations */
+};
+
+/*
+ * Inline functions
+ */
+static inline struct f2fs_inode_info *F2FS_I(struct inode *inode)
+{
+	return container_of(inode, struct f2fs_inode_info, vfs_inode);
+}
+
+static inline struct f2fs_sb_info *F2FS_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi)
+{
+	return (struct f2fs_super_block *)(sbi->raw_super);
+}
+
+static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi)
+{
+	return (struct f2fs_checkpoint *)(sbi->ckpt);
+}
+
+static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi)
+{
+	return (struct f2fs_nm_info *)(sbi->nm_info);
+}
+
+static inline struct f2fs_sm_info *SM_I(struct f2fs_sb_info *sbi)
+{
+	return (struct f2fs_sm_info *)(sbi->sm_info);
+}
+
+static inline struct sit_info *SIT_I(struct f2fs_sb_info *sbi)
+{
+	return (struct sit_info *)(SM_I(sbi)->sit_info);
+}
+
+static inline struct free_segmap_info *FREE_I(struct f2fs_sb_info *sbi)
+{
+	return (struct free_segmap_info *)(SM_I(sbi)->free_info);
+}
+
+static inline struct dirty_seglist_info *DIRTY_I(struct f2fs_sb_info *sbi)
+{
+	return (struct dirty_seglist_info *)(SM_I(sbi)->dirty_info);
+}
+
+static inline void F2FS_SET_SB_DIRT(struct f2fs_sb_info *sbi)
+{
+	sbi->s_dirty = 1;
+}
+
+static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi)
+{
+	sbi->s_dirty = 0;
+}
+
+static inline void mutex_lock_op(struct f2fs_sb_info *sbi, enum lock_type t)
+{
+	mutex_lock_nested(&sbi->fs_lock[t], t);
+}
+
+static inline void mutex_unlock_op(struct f2fs_sb_info *sbi, enum lock_type t)
+{
+	mutex_unlock(&sbi->fs_lock[t]);
+}
+
+/*
+ * Check whether the given nid is within node id range.
+ */
+static inline void check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
+{
+	BUG_ON((nid >= NM_I(sbi)->max_nid));
+}
+
+#define F2FS_DEFAULT_ALLOCATED_BLOCKS	1
+
+/*
+ * Check whether the inode has blocks or not
+ */
+static inline int F2FS_HAS_BLOCKS(struct inode *inode)
+{
+	if (F2FS_I(inode)->i_xattr_nid)
+		return (inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS + 1);
+	else
+		return (inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS);
+}
+
+static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
+				 struct inode *inode, blkcnt_t count)
+{
+	block_t	valid_block_count;
+
+	spin_lock(&sbi->stat_lock);
+	valid_block_count =
+		sbi->total_valid_block_count + (block_t)count;
+	if (valid_block_count > sbi->user_block_count) {
+		spin_unlock(&sbi->stat_lock);
+		return false;
+	}
+	inode->i_blocks += count;
+	sbi->total_valid_block_count = valid_block_count;
+	sbi->alloc_valid_block_count += (block_t)count;
+	spin_unlock(&sbi->stat_lock);
+	return true;
+}
+
+static inline int dec_valid_block_count(struct f2fs_sb_info *sbi,
+						struct inode *inode,
+						blkcnt_t count)
+{
+	spin_lock(&sbi->stat_lock);
+	BUG_ON(sbi->total_valid_block_count < (block_t) count);
+	BUG_ON(inode->i_blocks < count);
+	inode->i_blocks -= count;
+	sbi->total_valid_block_count -= (block_t)count;
+	spin_unlock(&sbi->stat_lock);
+	return 0;
+}
+
+static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
+{
+	atomic_inc(&sbi->nr_pages[count_type]);
+	F2FS_SET_SB_DIRT(sbi);
+}
+
+static inline void inode_inc_dirty_dents(struct inode *inode)
+{
+	atomic_inc(&F2FS_I(inode)->dirty_dents);
+}
+
+static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
+{
+	atomic_dec(&sbi->nr_pages[count_type]);
+}
+
+static inline void inode_dec_dirty_dents(struct inode *inode)
+{
+	atomic_dec(&F2FS_I(inode)->dirty_dents);
+}
+
+static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
+{
+	return atomic_read(&sbi->nr_pages[count_type]);
+}
+
+static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
+{
+	block_t ret;
+	spin_lock(&sbi->stat_lock);
+	ret = sbi->total_valid_block_count;
+	spin_unlock(&sbi->stat_lock);
+	return ret;
+}
+
+static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+
+	/* return NAT or SIT bitmap */
+	if (flag == NAT_BITMAP)
+		return le32_to_cpu(ckpt->nat_ver_bitmap_bytesize);
+	else if (flag == SIT_BITMAP)
+		return le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);
+
+	return 0;
+}
+
+static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	int offset = (flag == NAT_BITMAP) ? ckpt->sit_ver_bitmap_bytesize : 0;
+	return &ckpt->sit_nat_version_bitmap + offset;
+}
+
+static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
+{
+	block_t start_addr;
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	unsigned long long ckpt_version = le64_to_cpu(ckpt->checkpoint_ver);
+
+	start_addr = le64_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
+
+	/*
+	 * odd numbered checkpoint should at cp segment 0
+	 * and even segent must be at cp segment 1
+	 */
+	if (!(ckpt_version & 1))
+		start_addr += sbi->blocks_per_seg;
+
+	return start_addr;
+}
+
+static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
+{
+	return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
+}
+
+static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
+						struct inode *inode,
+						unsigned int count)
+{
+	block_t	valid_block_count;
+	unsigned int valid_node_count;
+
+	spin_lock(&sbi->stat_lock);
+
+	valid_block_count = sbi->total_valid_block_count + (block_t)count;
+	sbi->alloc_valid_block_count += (block_t)count;
+	valid_node_count = sbi->total_valid_node_count + count;
+
+	if (valid_block_count > sbi->user_block_count) {
+		spin_unlock(&sbi->stat_lock);
+		return false;
+	}
+
+	if (valid_node_count > sbi->total_node_count) {
+		spin_unlock(&sbi->stat_lock);
+		return false;
+	}
+
+	if (inode)
+		inode->i_blocks += count;
+	sbi->total_valid_node_count = valid_node_count;
+	sbi->total_valid_block_count = valid_block_count;
+	spin_unlock(&sbi->stat_lock);
+
+	return true;
+}
+
+static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
+						struct inode *inode,
+						unsigned int count)
+{
+	spin_lock(&sbi->stat_lock);
+
+	BUG_ON(sbi->total_valid_block_count < count);
+	BUG_ON(sbi->total_valid_node_count < count);
+	BUG_ON(inode->i_blocks < count);
+
+	inode->i_blocks -= count;
+	sbi->total_valid_node_count -= count;
+	sbi->total_valid_block_count -= (block_t)count;
+
+	spin_unlock(&sbi->stat_lock);
+}
+
+static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
+{
+	unsigned int ret;
+	spin_lock(&sbi->stat_lock);
+	ret = sbi->total_valid_node_count;
+	spin_unlock(&sbi->stat_lock);
+	return ret;
+}
+
+static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
+{
+	spin_lock(&sbi->stat_lock);
+	BUG_ON(sbi->total_valid_inode_count == sbi->total_node_count);
+	sbi->total_valid_inode_count++;
+	spin_unlock(&sbi->stat_lock);
+}
+
+static inline int dec_valid_inode_count(struct f2fs_sb_info *sbi)
+{
+	spin_lock(&sbi->stat_lock);
+	BUG_ON(!sbi->total_valid_inode_count);
+	sbi->total_valid_inode_count--;
+	spin_unlock(&sbi->stat_lock);
+	return 0;
+}
+
+static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi)
+{
+	unsigned int ret;
+	spin_lock(&sbi->stat_lock);
+	ret = sbi->total_valid_inode_count;
+	spin_unlock(&sbi->stat_lock);
+	return ret;
+}
+
+static inline void f2fs_put_page(struct page *page, int unlock)
+{
+	if (!page || IS_ERR(page))
+		return;
+
+	if (unlock) {
+		BUG_ON(!PageLocked(page));
+		unlock_page(page);
+	}
+	page_cache_release(page);
+}
+
+static inline void f2fs_put_dnode(struct dnode_of_data *dn)
+{
+	if (dn->node_page)
+		f2fs_put_page(dn->node_page, 1);
+	if (dn->inode_page && dn->node_page != dn->inode_page)
+		f2fs_put_page(dn->inode_page, 0);
+	dn->node_page = NULL;
+	dn->inode_page = NULL;
+}
+
+static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name,
+					size_t size, void (*ctor)(void *))
+{
+	return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, ctor);
+}
+
+#define RAW_IS_INODE(p)	((p)->footer.nid == (p)->footer.ino)
+
+static inline bool IS_INODE(struct page *page)
+{
+	struct f2fs_node *p = (struct f2fs_node *)page_address(page);
+	return RAW_IS_INODE(p);
+}
+
+static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
+{
+	return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr;
+}
+
+static inline block_t datablock_addr(struct page *node_page,
+		unsigned int offset)
+{
+	struct f2fs_node *raw_node;
+	__le32 *addr_array;
+	raw_node = (struct f2fs_node *)page_address(node_page);
+	addr_array = blkaddr_in_node(raw_node);
+	return le32_to_cpu(addr_array[offset]);
+}
+
+static inline int f2fs_test_bit(unsigned int nr, char *addr)
+{
+	int mask;
+
+	addr += (nr >> 3);
+	mask = 1 << (7 - (nr & 0x07));
+	return mask & *addr;
+}
+
+static inline int f2fs_set_bit(unsigned int nr, char *addr)
+{
+	int mask;
+	int ret;
+
+	addr += (nr >> 3);
+	mask = 1 << (7 - (nr & 0x07));
+	ret = mask & *addr;
+	*addr |= mask;
+	return ret;
+}
+
+static inline int f2fs_clear_bit(unsigned int nr, char *addr)
+{
+	int mask;
+	int ret;
+
+	addr += (nr >> 3);
+	mask = 1 << (7 - (nr & 0x07));
+	ret = mask & *addr;
+	*addr &= ~mask;
+	return ret;
+}
+
+/* used for f2fs_inode_info->flags */
+enum {
+	FI_NEW_INODE,		/* indicate newly allocated inode */
+	FI_NEED_CP,		/* need to do checkpoint during fsync */
+	FI_INC_LINK,		/* need to increment i_nlink */
+	FI_ACL_MODE,		/* indicate acl mode */
+	FI_NO_ALLOC,		/* should not allocate any blocks */
+};
+
+static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
+{
+	set_bit(flag, &fi->flags);
+}
+
+static inline int is_inode_flag_set(struct f2fs_inode_info *fi, int flag)
+{
+	return test_bit(flag, &fi->flags);
+}
+
+static inline void clear_inode_flag(struct f2fs_inode_info *fi, int flag)
+{
+	clear_bit(flag, &fi->flags);
+}
+
+static inline void set_acl_inode(struct f2fs_inode_info *fi, umode_t mode)
+{
+	fi->i_acl_mode = mode;
+	set_inode_flag(fi, FI_ACL_MODE);
+}
+
+static inline int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag)
+{
+	if (is_inode_flag_set(fi, FI_ACL_MODE)) {
+		clear_inode_flag(fi, FI_ACL_MODE);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * file.c
+ */
+int f2fs_sync_file(struct file *, loff_t, loff_t, int);
+void truncate_data_blocks(struct dnode_of_data *);
+void f2fs_truncate(struct inode *);
+int f2fs_setattr(struct dentry *, struct iattr *);
+int truncate_hole(struct inode *, pgoff_t, pgoff_t);
+long f2fs_ioctl(struct file *, unsigned int, unsigned long);
+
+/*
+ * inode.c
+ */
+void f2fs_set_inode_flags(struct inode *);
+struct inode *f2fs_iget_nowait(struct super_block *, unsigned long);
+struct inode *f2fs_iget(struct super_block *, unsigned long);
+void update_inode(struct inode *, struct page *);
+int f2fs_write_inode(struct inode *, struct writeback_control *);
+void f2fs_evict_inode(struct inode *);
+
+/*
+ * namei.c
+ */
+struct dentry *f2fs_get_parent(struct dentry *child);
+
+/*
+ * dir.c
+ */
+struct f2fs_dir_entry *f2fs_find_entry(struct inode *, struct qstr *,
+							struct page **);
+struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
+ino_t f2fs_inode_by_name(struct inode *, struct qstr *);
+void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
+				struct page *, struct inode *);
+void init_dent_inode(struct dentry *, struct page *);
+int f2fs_add_link(struct dentry *, struct inode *);
+void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *);
+int f2fs_make_empty(struct inode *, struct inode *);
+bool f2fs_empty_dir(struct inode *);
+
+/*
+ * super.c
+ */
+int f2fs_sync_fs(struct super_block *, int);
+
+/*
+ * hash.c
+ */
+f2fs_hash_t f2fs_dentry_hash(const char *, int);
+
+/*
+ * node.c
+ */
+struct dnode_of_data;
+struct node_info;
+
+int is_checkpointed_node(struct f2fs_sb_info *, nid_t);
+void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
+int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
+int truncate_inode_blocks(struct inode *, pgoff_t);
+int remove_inode_page(struct inode *);
+int new_inode_page(struct inode *, struct dentry *);
+struct page *new_node_page(struct dnode_of_data *, unsigned int);
+void ra_node_page(struct f2fs_sb_info *, nid_t);
+struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
+struct page *get_node_page_ra(struct page *, int);
+void sync_inode_page(struct dnode_of_data *);
+int sync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *);
+bool alloc_nid(struct f2fs_sb_info *, nid_t *);
+void alloc_nid_done(struct f2fs_sb_info *, nid_t);
+void alloc_nid_failed(struct f2fs_sb_info *, nid_t);
+void recover_node_page(struct f2fs_sb_info *, struct page *,
+		struct f2fs_summary *, struct node_info *, block_t);
+int recover_inode_page(struct f2fs_sb_info *, struct page *);
+int restore_node_summary(struct f2fs_sb_info *, unsigned int,
+				struct f2fs_summary_block *);
+void flush_nat_entries(struct f2fs_sb_info *);
+int build_node_manager(struct f2fs_sb_info *);
+void destroy_node_manager(struct f2fs_sb_info *);
+int create_node_manager_caches(void);
+void destroy_node_manager_caches(void);
+
+/*
+ * segment.c
+ */
+void f2fs_balance_fs(struct f2fs_sb_info *);
+void invalidate_blocks(struct f2fs_sb_info *, block_t);
+void locate_dirty_segment(struct f2fs_sb_info *, unsigned int);
+void clear_prefree_segments(struct f2fs_sb_info *);
+int npages_for_summary_flush(struct f2fs_sb_info *);
+void allocate_new_segments(struct f2fs_sb_info *);
+struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
+struct bio *f2fs_bio_alloc(struct block_device *, sector_t, int, gfp_t);
+void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool sync);
+int write_meta_page(struct f2fs_sb_info *, struct page *,
+					struct writeback_control *);
+void write_node_page(struct f2fs_sb_info *, struct page *, unsigned int,
+					block_t, block_t *);
+void write_data_page(struct inode *, struct page *, struct dnode_of_data*,
+					block_t, block_t *);
+void rewrite_data_page(struct f2fs_sb_info *, struct page *, block_t);
+void recover_data_page(struct f2fs_sb_info *, struct page *,
+				struct f2fs_summary *, block_t, block_t);
+void rewrite_node_page(struct f2fs_sb_info *, struct page *,
+				struct f2fs_summary *, block_t, block_t);
+void write_data_summaries(struct f2fs_sb_info *, block_t);
+void write_node_summaries(struct f2fs_sb_info *, block_t);
+int lookup_journal_in_cursum(struct f2fs_summary_block *,
+					int, unsigned int, int);
+void flush_sit_entries(struct f2fs_sb_info *);
+int build_segment_manager(struct f2fs_sb_info *);
+void reset_victim_segmap(struct f2fs_sb_info *);
+void destroy_segment_manager(struct f2fs_sb_info *);
+
+/*
+ * checkpoint.c
+ */
+struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
+struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
+long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
+int check_orphan_space(struct f2fs_sb_info *);
+void add_orphan_inode(struct f2fs_sb_info *, nid_t);
+void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
+int recover_orphan_inodes(struct f2fs_sb_info *);
+int get_valid_checkpoint(struct f2fs_sb_info *);
+void set_dirty_dir_page(struct inode *, struct page *);
+void remove_dirty_dir_inode(struct inode *);
+void sync_dirty_dir_inodes(struct f2fs_sb_info *);
+void block_operations(struct f2fs_sb_info *);
+void write_checkpoint(struct f2fs_sb_info *, bool, bool);
+void init_orphan_info(struct f2fs_sb_info *);
+int create_checkpoint_caches(void);
+void destroy_checkpoint_caches(void);
+
+/*
+ * data.c
+ */
+int reserve_new_block(struct dnode_of_data *);
+void update_extent_cache(block_t, struct dnode_of_data *);
+struct page *find_data_page(struct inode *, pgoff_t);
+struct page *get_lock_data_page(struct inode *, pgoff_t);
+struct page *get_new_data_page(struct inode *, pgoff_t, bool);
+int f2fs_readpage(struct f2fs_sb_info *, struct page *, block_t, int);
+int do_write_data_page(struct page *);
+
+/*
+ * gc.c
+ */
+int start_gc_thread(struct f2fs_sb_info *);
+void stop_gc_thread(struct f2fs_sb_info *);
+block_t start_bidx_of_node(unsigned int);
+int f2fs_gc(struct f2fs_sb_info *, int);
+void build_gc_manager(struct f2fs_sb_info *);
+int create_gc_caches(void);
+void destroy_gc_caches(void);
+
+/*
+ * recovery.c
+ */
+void recover_fsync_data(struct f2fs_sb_info *);
+bool space_for_roll_forward(struct f2fs_sb_info *);
+
+/*
+ * debug.c
+ */
+#ifdef CONFIG_F2FS_STAT_FS
+struct f2fs_stat_info {
+	struct list_head stat_list;
+	struct f2fs_sb_info *sbi;
+	struct mutex stat_lock;
+	int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs;
+	int main_area_segs, main_area_sections, main_area_zones;
+	int hit_ext, total_ext;
+	int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta;
+	int nats, sits, fnids;
+	int total_count, utilization;
+	int bg_gc;
+	unsigned int valid_count, valid_node_count, valid_inode_count;
+	unsigned int bimodal, avg_vblocks;
+	int util_free, util_valid, util_invalid;
+	int rsvd_segs, overp_segs;
+	int dirty_count, node_pages, meta_pages;
+	int prefree_count, call_count;
+	int tot_segs, node_segs, data_segs, free_segs, free_secs;
+	int tot_blks, data_blks, node_blks;
+	int curseg[NR_CURSEG_TYPE];
+	int cursec[NR_CURSEG_TYPE];
+	int curzone[NR_CURSEG_TYPE];
+
+	unsigned int segment_count[2];
+	unsigned int block_count[2];
+	unsigned base_mem, cache_mem;
+};
+
+#define stat_inc_call_count(si)	((si)->call_count++)
+
+#define stat_inc_seg_count(sbi, type)					\
+	do {								\
+		struct f2fs_stat_info *si = sbi->stat_info;		\
+		(si)->tot_segs++;					\
+		if (type == SUM_TYPE_DATA)				\
+			si->data_segs++;				\
+		else							\
+			si->node_segs++;				\
+	} while (0)
+
+#define stat_inc_tot_blk_count(si, blks)				\
+	(si->tot_blks += (blks))
+
+#define stat_inc_data_blk_count(sbi, blks)				\
+	do {								\
+		struct f2fs_stat_info *si = sbi->stat_info;		\
+		stat_inc_tot_blk_count(si, blks);			\
+		si->data_blks += (blks);				\
+	} while (0)
+
+#define stat_inc_node_blk_count(sbi, blks)				\
+	do {								\
+		struct f2fs_stat_info *si = sbi->stat_info;		\
+		stat_inc_tot_blk_count(si, blks);			\
+		si->node_blks += (blks);				\
+	} while (0)
+
+int f2fs_build_stats(struct f2fs_sb_info *);
+void f2fs_destroy_stats(struct f2fs_sb_info *);
+void destroy_root_stats(void);
+#else
+#define stat_inc_call_count(si)
+#define stat_inc_seg_count(si, type)
+#define stat_inc_tot_blk_count(si, blks)
+#define stat_inc_data_blk_count(si, blks)
+#define stat_inc_node_blk_count(sbi, blks)
+
+static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
+static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
+static inline void destroy_root_stats(void) { }
+#endif
+
+extern const struct file_operations f2fs_dir_operations;
+extern const struct file_operations f2fs_file_operations;
+extern const struct inode_operations f2fs_file_inode_operations;
+extern const struct address_space_operations f2fs_dblock_aops;
+extern const struct address_space_operations f2fs_node_aops;
+extern const struct address_space_operations f2fs_meta_aops;
+extern const struct inode_operations f2fs_dir_inode_operations;
+extern const struct inode_operations f2fs_symlink_inode_operations;
+extern const struct inode_operations f2fs_special_inode_operations;
+#endif
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
new file mode 100644
index 000000000000..5d525ed312ba
--- /dev/null
+++ b/fs/f2fs/node.h
@@ -0,0 +1,353 @@
+/**
+ * fs/f2fs/node.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/* start node id of a node block dedicated to the given node id */
+#define	START_NID(nid) ((nid / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)
+
+/* node block offset on the NAT area dedicated to the given start node id */
+#define	NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
+
+/* # of pages to perform readahead before building free nids */
+#define FREE_NID_PAGES 4
+
+/* maximum # of free node ids to produce during build_free_nids */
+#define MAX_FREE_NIDS (NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES)
+
+/* maximum readahead size for node during getting data blocks */
+#define MAX_RA_NODE		128
+
+/* maximum cached nat entries to manage memory footprint */
+#define NM_WOUT_THRESHOLD	(64 * NAT_ENTRY_PER_BLOCK)
+
+/* vector size for gang look-up from nat cache that consists of radix tree */
+#define NATVEC_SIZE	64
+
+/*
+ * For node information
+ */
+struct node_info {
+	nid_t nid;		/* node id */
+	nid_t ino;		/* inode number of the node's owner */
+	block_t	blk_addr;	/* block address of the node */
+	unsigned char version;	/* version of the node */
+};
+
+struct nat_entry {
+	struct list_head list;	/* for clean or dirty nat list */
+	bool checkpointed;	/* whether it is checkpointed or not */
+	struct node_info ni;	/* in-memory node information */
+};
+
+#define nat_get_nid(nat)		(nat->ni.nid)
+#define nat_set_nid(nat, n)		(nat->ni.nid = n)
+#define nat_get_blkaddr(nat)		(nat->ni.blk_addr)
+#define nat_set_blkaddr(nat, b)		(nat->ni.blk_addr = b)
+#define nat_get_ino(nat)		(nat->ni.ino)
+#define nat_set_ino(nat, i)		(nat->ni.ino = i)
+#define nat_get_version(nat)		(nat->ni.version)
+#define nat_set_version(nat, v)		(nat->ni.version = v)
+
+#define __set_nat_cache_dirty(nm_i, ne)					\
+	list_move_tail(&ne->list, &nm_i->dirty_nat_entries);
+#define __clear_nat_cache_dirty(nm_i, ne)				\
+	list_move_tail(&ne->list, &nm_i->nat_entries);
+#define inc_node_version(version)	(++version)
+
+static inline void node_info_from_raw_nat(struct node_info *ni,
+						struct f2fs_nat_entry *raw_ne)
+{
+	ni->ino = le32_to_cpu(raw_ne->ino);
+	ni->blk_addr = le32_to_cpu(raw_ne->block_addr);
+	ni->version = raw_ne->version;
+}
+
+/*
+ * For free nid mangement
+ */
+enum nid_state {
+	NID_NEW,	/* newly added to free nid list */
+	NID_ALLOC	/* it is allocated */
+};
+
+struct free_nid {
+	struct list_head list;	/* for free node id list */
+	nid_t nid;		/* node id */
+	int state;		/* in use or not: NID_NEW or NID_ALLOC */
+};
+
+static inline int next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	struct free_nid *fnid;
+
+	if (nm_i->fcnt <= 0)
+		return -1;
+	spin_lock(&nm_i->free_nid_list_lock);
+	fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list);
+	*nid = fnid->nid;
+	spin_unlock(&nm_i->free_nid_list_lock);
+	return 0;
+}
+
+/*
+ * inline functions
+ */
+static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size);
+}
+
+static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	pgoff_t block_off;
+	pgoff_t block_addr;
+	int seg_off;
+
+	block_off = NAT_BLOCK_OFFSET(start);
+	seg_off = block_off >> sbi->log_blocks_per_seg;
+
+	block_addr = (pgoff_t)(nm_i->nat_blkaddr +
+		(seg_off << sbi->log_blocks_per_seg << 1) +
+		(block_off & ((1 << sbi->log_blocks_per_seg) - 1)));
+
+	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
+		block_addr += sbi->blocks_per_seg;
+
+	return block_addr;
+}
+
+static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi,
+						pgoff_t block_addr)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+	block_addr -= nm_i->nat_blkaddr;
+	if ((block_addr >> sbi->log_blocks_per_seg) % 2)
+		block_addr -= sbi->blocks_per_seg;
+	else
+		block_addr += sbi->blocks_per_seg;
+
+	return block_addr + nm_i->nat_blkaddr;
+}
+
+static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
+{
+	unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);
+
+	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
+		f2fs_clear_bit(block_off, nm_i->nat_bitmap);
+	else
+		f2fs_set_bit(block_off, nm_i->nat_bitmap);
+}
+
+static inline void fill_node_footer(struct page *page, nid_t nid,
+				nid_t ino, unsigned int ofs, bool reset)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	if (reset)
+		memset(rn, 0, sizeof(*rn));
+	rn->footer.nid = cpu_to_le32(nid);
+	rn->footer.ino = cpu_to_le32(ino);
+	rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
+}
+
+static inline void copy_node_footer(struct page *dst, struct page *src)
+{
+	void *src_addr = page_address(src);
+	void *dst_addr = page_address(dst);
+	struct f2fs_node *src_rn = (struct f2fs_node *)src_addr;
+	struct f2fs_node *dst_rn = (struct f2fs_node *)dst_addr;
+	memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer));
+}
+
+static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	rn->footer.cp_ver = ckpt->checkpoint_ver;
+	rn->footer.next_blkaddr = blkaddr;
+}
+
+static inline nid_t ino_of_node(struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	return le32_to_cpu(rn->footer.ino);
+}
+
+static inline nid_t nid_of_node(struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	return le32_to_cpu(rn->footer.nid);
+}
+
+static inline unsigned int ofs_of_node(struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned flag = le32_to_cpu(rn->footer.flag);
+	return flag >> OFFSET_BIT_SHIFT;
+}
+
+static inline unsigned long long cpver_of_node(struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	return le64_to_cpu(rn->footer.cp_ver);
+}
+
+static inline block_t next_blkaddr_of_node(struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	return le32_to_cpu(rn->footer.next_blkaddr);
+}
+
+/*
+ * f2fs assigns the following node offsets described as (num).
+ * N = NIDS_PER_BLOCK
+ *
+ *  Inode block (0)
+ *    |- direct node (1)
+ *    |- direct node (2)
+ *    |- indirect node (3)
+ *    |            `- direct node (4 => 4 + N - 1)
+ *    |- indirect node (4 + N)
+ *    |            `- direct node (5 + N => 5 + 2N - 1)
+ *    `- double indirect node (5 + 2N)
+ *                 `- indirect node (6 + 2N)
+ *                       `- direct node (x(N + 1))
+ */
+static inline bool IS_DNODE(struct page *node_page)
+{
+	unsigned int ofs = ofs_of_node(node_page);
+	if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
+			ofs == 5 + 2 * NIDS_PER_BLOCK)
+		return false;
+	if (ofs >= 6 + 2 * NIDS_PER_BLOCK) {
+		ofs -= 6 + 2 * NIDS_PER_BLOCK;
+		if ((long int)ofs % (NIDS_PER_BLOCK + 1))
+			return false;
+	}
+	return true;
+}
+
+static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
+{
+	struct f2fs_node *rn = (struct f2fs_node *)page_address(p);
+
+	wait_on_page_writeback(p);
+
+	if (i)
+		rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
+	else
+		rn->in.nid[off] = cpu_to_le32(nid);
+	set_page_dirty(p);
+}
+
+static inline nid_t get_nid(struct page *p, int off, bool i)
+{
+	struct f2fs_node *rn = (struct f2fs_node *)page_address(p);
+	if (i)
+		return le32_to_cpu(rn->i.i_nid[off - NODE_DIR1_BLOCK]);
+	return le32_to_cpu(rn->in.nid[off]);
+}
+
+/*
+ * Coldness identification:
+ *  - Mark cold files in f2fs_inode_info
+ *  - Mark cold node blocks in their node footer
+ *  - Mark cold data pages in page cache
+ */
+static inline int is_cold_file(struct inode *inode)
+{
+	return F2FS_I(inode)->i_advise & FADVISE_COLD_BIT;
+}
+
+static inline int is_cold_data(struct page *page)
+{
+	return PageChecked(page);
+}
+
+static inline void set_cold_data(struct page *page)
+{
+	SetPageChecked(page);
+}
+
+static inline void clear_cold_data(struct page *page)
+{
+	ClearPageChecked(page);
+}
+
+static inline int is_cold_node(struct page *page)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+	return flag & (0x1 << COLD_BIT_SHIFT);
+}
+
+static inline unsigned char is_fsync_dnode(struct page *page)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+	return flag & (0x1 << FSYNC_BIT_SHIFT);
+}
+
+static inline unsigned char is_dent_dnode(struct page *page)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+	return flag & (0x1 << DENT_BIT_SHIFT);
+}
+
+static inline void set_cold_node(struct inode *inode, struct page *page)
+{
+	struct f2fs_node *rn = (struct f2fs_node *)page_address(page);
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+
+	if (S_ISDIR(inode->i_mode))
+		flag &= ~(0x1 << COLD_BIT_SHIFT);
+	else
+		flag |= (0x1 << COLD_BIT_SHIFT);
+	rn->footer.flag = cpu_to_le32(flag);
+}
+
+static inline void set_fsync_mark(struct page *page, int mark)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+	if (mark)
+		flag |= (0x1 << FSYNC_BIT_SHIFT);
+	else
+		flag &= ~(0x1 << FSYNC_BIT_SHIFT);
+	rn->footer.flag = cpu_to_le32(flag);
+}
+
+static inline void set_dentry_mark(struct page *page, int mark)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+	if (mark)
+		flag |= (0x1 << DENT_BIT_SHIFT);
+	else
+		flag &= ~(0x1 << DENT_BIT_SHIFT);
+	rn->footer.flag = cpu_to_le32(flag);
+}
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
new file mode 100644
index 000000000000..e380a8ef13f5
--- /dev/null
+++ b/fs/f2fs/segment.h
@@ -0,0 +1,615 @@
+/**
+ * fs/f2fs/segment.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/* constant macro */
+#define NULL_SEGNO			((unsigned int)(~0))
+
+/* V: Logical segment # in volume, R: Relative segment # in main area */
+#define GET_L2R_SEGNO(free_i, segno)	(segno - free_i->start_segno)
+#define GET_R2L_SEGNO(free_i, segno)	(segno + free_i->start_segno)
+
+#define IS_DATASEG(t)							\
+	((t == CURSEG_HOT_DATA) || (t == CURSEG_COLD_DATA) ||		\
+	(t == CURSEG_WARM_DATA))
+
+#define IS_NODESEG(t)							\
+	((t == CURSEG_HOT_NODE) || (t == CURSEG_COLD_NODE) ||		\
+	(t == CURSEG_WARM_NODE))
+
+#define IS_CURSEG(sbi, segno)						\
+	((segno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
+	 (segno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\
+	 (segno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) ||	\
+	 (segno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) ||	\
+	 (segno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) ||	\
+	 (segno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
+
+#define IS_CURSEC(sbi, secno)						\
+	((secno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
+	  sbi->segs_per_sec))	\
+
+#define START_BLOCK(sbi, segno)						\
+	(SM_I(sbi)->seg0_blkaddr +					\
+	 (GET_R2L_SEGNO(FREE_I(sbi), segno) << sbi->log_blocks_per_seg))
+#define NEXT_FREE_BLKADDR(sbi, curseg)					\
+	(START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff)
+
+#define MAIN_BASE_BLOCK(sbi)	(SM_I(sbi)->main_blkaddr)
+
+#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr)				\
+	((blk_addr) - SM_I(sbi)->seg0_blkaddr)
+#define GET_SEGNO_FROM_SEG0(sbi, blk_addr)				\
+	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg)
+#define GET_SEGNO(sbi, blk_addr)					\
+	(((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ?		\
+	NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi),			\
+		GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
+#define GET_SECNO(sbi, segno)					\
+	((segno) / sbi->segs_per_sec)
+#define GET_ZONENO_FROM_SEGNO(sbi, segno)				\
+	((segno / sbi->segs_per_sec) / sbi->secs_per_zone)
+
+#define GET_SUM_BLOCK(sbi, segno)				\
+	((sbi->sm_info->ssa_blkaddr) + segno)
+
+#define GET_SUM_TYPE(footer) ((footer)->entry_type)
+#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = type)
+
+#define SIT_ENTRY_OFFSET(sit_i, segno)					\
+	(segno % sit_i->sents_per_block)
+#define SIT_BLOCK_OFFSET(sit_i, segno)					\
+	(segno / SIT_ENTRY_PER_BLOCK)
+#define	START_SEGNO(sit_i, segno)		\
+	(SIT_BLOCK_OFFSET(sit_i, segno) * SIT_ENTRY_PER_BLOCK)
+#define f2fs_bitmap_size(nr)			\
+	(BITS_TO_LONGS(nr) * sizeof(unsigned long))
+#define TOTAL_SEGS(sbi)	(SM_I(sbi)->main_segments)
+
+/* during checkpoint, bio_private is used to synchronize the last bio */
+struct bio_private {
+	struct f2fs_sb_info *sbi;
+	bool is_sync;
+	void *wait;
+};
+
+/*
+ * indicate a block allocation direction: RIGHT and LEFT.
+ * RIGHT means allocating new sections towards the end of volume.
+ * LEFT means the opposite direction.
+ */
+enum {
+	ALLOC_RIGHT = 0,
+	ALLOC_LEFT
+};
+
+/*
+ * In the victim_sel_policy->alloc_mode, there are two block allocation modes.
+ * LFS writes data sequentially with cleaning operations.
+ * SSR (Slack Space Recycle) reuses obsolete space without cleaning operations.
+ */
+enum {
+	LFS = 0,
+	SSR
+};
+
+/*
+ * In the victim_sel_policy->gc_mode, there are two gc, aka cleaning, modes.
+ * GC_CB is based on cost-benefit algorithm.
+ * GC_GREEDY is based on greedy algorithm.
+ */
+enum {
+	GC_CB = 0,
+	GC_GREEDY
+};
+
+/*
+ * BG_GC means the background cleaning job.
+ * FG_GC means the on-demand cleaning job.
+ */
+enum {
+	BG_GC = 0,
+	FG_GC
+};
+
+/* for a function parameter to select a victim segment */
+struct victim_sel_policy {
+	int alloc_mode;			/* LFS or SSR */
+	int gc_mode;			/* GC_CB or GC_GREEDY */
+	unsigned long *dirty_segmap;	/* dirty segment bitmap */
+	unsigned int offset;		/* last scanned bitmap offset */
+	unsigned int ofs_unit;		/* bitmap search unit */
+	unsigned int min_cost;		/* minimum cost */
+	unsigned int min_segno;		/* segment # having min. cost */
+};
+
+struct seg_entry {
+	unsigned short valid_blocks;	/* # of valid blocks */
+	unsigned char *cur_valid_map;	/* validity bitmap of blocks */
+	/*
+	 * # of valid blocks and the validity bitmap stored in the the last
+	 * checkpoint pack. This information is used by the SSR mode.
+	 */
+	unsigned short ckpt_valid_blocks;
+	unsigned char *ckpt_valid_map;
+	unsigned char type;		/* segment type like CURSEG_XXX_TYPE */
+	unsigned long long mtime;	/* modification time of the segment */
+};
+
+struct sec_entry {
+	unsigned int valid_blocks;	/* # of valid blocks in a section */
+};
+
+struct segment_allocation {
+	void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
+};
+
+struct sit_info {
+	const struct segment_allocation *s_ops;
+
+	block_t sit_base_addr;		/* start block address of SIT area */
+	block_t sit_blocks;		/* # of blocks used by SIT area */
+	block_t written_valid_blocks;	/* # of valid blocks in main area */
+	char *sit_bitmap;		/* SIT bitmap pointer */
+	unsigned int bitmap_size;	/* SIT bitmap size */
+
+	unsigned long *dirty_sentries_bitmap;	/* bitmap for dirty sentries */
+	unsigned int dirty_sentries;		/* # of dirty sentries */
+	unsigned int sents_per_block;		/* # of SIT entries per block */
+	struct mutex sentry_lock;		/* to protect SIT cache */
+	struct seg_entry *sentries;		/* SIT segment-level cache */
+	struct sec_entry *sec_entries;		/* SIT section-level cache */
+
+	/* for cost-benefit algorithm in cleaning procedure */
+	unsigned long long elapsed_time;	/* elapsed time after mount */
+	unsigned long long mounted_time;	/* mount time */
+	unsigned long long min_mtime;		/* min. modification time */
+	unsigned long long max_mtime;		/* max. modification time */
+};
+
+struct free_segmap_info {
+	unsigned int start_segno;	/* start segment number logically */
+	unsigned int free_segments;	/* # of free segments */
+	unsigned int free_sections;	/* # of free sections */
+	rwlock_t segmap_lock;		/* free segmap lock */
+	unsigned long *free_segmap;	/* free segment bitmap */
+	unsigned long *free_secmap;	/* free section bitmap */
+};
+
+/* Notice: The order of dirty type is same with CURSEG_XXX in f2fs.h */
+enum dirty_type {
+	DIRTY_HOT_DATA,		/* dirty segments assigned as hot data logs */
+	DIRTY_WARM_DATA,	/* dirty segments assigned as warm data logs */
+	DIRTY_COLD_DATA,	/* dirty segments assigned as cold data logs */
+	DIRTY_HOT_NODE,		/* dirty segments assigned as hot node logs */
+	DIRTY_WARM_NODE,	/* dirty segments assigned as warm node logs */
+	DIRTY_COLD_NODE,	/* dirty segments assigned as cold node logs */
+	DIRTY,			/* to count # of dirty segments */
+	PRE,			/* to count # of entirely obsolete segments */
+	NR_DIRTY_TYPE
+};
+
+struct dirty_seglist_info {
+	const struct victim_selection *v_ops;	/* victim selction operation */
+	unsigned long *dirty_segmap[NR_DIRTY_TYPE];
+	struct mutex seglist_lock;		/* lock for segment bitmaps */
+	int nr_dirty[NR_DIRTY_TYPE];		/* # of dirty segments */
+	unsigned long *victim_segmap[2];	/* BG_GC, FG_GC */
+};
+
+/* victim selection function for cleaning and SSR */
+struct victim_selection {
+	int (*get_victim)(struct f2fs_sb_info *, unsigned int *,
+							int, int, char);
+};
+
+/* for active log information */
+struct curseg_info {
+	struct mutex curseg_mutex;		/* lock for consistency */
+	struct f2fs_summary_block *sum_blk;	/* cached summary block */
+	unsigned char alloc_type;		/* current allocation type */
+	unsigned int segno;			/* current segment number */
+	unsigned short next_blkoff;		/* next block offset to write */
+	unsigned int zone;			/* current zone number */
+	unsigned int next_segno;		/* preallocated segment */
+};
+
+/*
+ * inline functions
+ */
+static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type)
+{
+	return (struct curseg_info *)(SM_I(sbi)->curseg_array + type);
+}
+
+static inline struct seg_entry *get_seg_entry(struct f2fs_sb_info *sbi,
+						unsigned int segno)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	return &sit_i->sentries[segno];
+}
+
+static inline struct sec_entry *get_sec_entry(struct f2fs_sb_info *sbi,
+						unsigned int segno)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	return &sit_i->sec_entries[GET_SECNO(sbi, segno)];
+}
+
+static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
+				unsigned int segno, int section)
+{
+	/*
+	 * In order to get # of valid blocks in a section instantly from many
+	 * segments, f2fs manages two counting structures separately.
+	 */
+	if (section > 1)
+		return get_sec_entry(sbi, segno)->valid_blocks;
+	else
+		return get_seg_entry(sbi, segno)->valid_blocks;
+}
+
+static inline void seg_info_from_raw_sit(struct seg_entry *se,
+					struct f2fs_sit_entry *rs)
+{
+	se->valid_blocks = GET_SIT_VBLOCKS(rs);
+	se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
+	memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+	se->type = GET_SIT_TYPE(rs);
+	se->mtime = le64_to_cpu(rs->mtime);
+}
+
+static inline void seg_info_to_raw_sit(struct seg_entry *se,
+					struct f2fs_sit_entry *rs)
+{
+	unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) |
+					se->valid_blocks;
+	rs->vblocks = cpu_to_le16(raw_vblocks);
+	memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
+	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+	se->ckpt_valid_blocks = se->valid_blocks;
+	rs->mtime = cpu_to_le64(se->mtime);
+}
+
+static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
+		unsigned int max, unsigned int segno)
+{
+	unsigned int ret;
+	read_lock(&free_i->segmap_lock);
+	ret = find_next_bit(free_i->free_segmap, max, segno);
+	read_unlock(&free_i->segmap_lock);
+	return ret;
+}
+
+static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int secno = segno / sbi->segs_per_sec;
+	unsigned int start_segno = secno * sbi->segs_per_sec;
+	unsigned int next;
+
+	write_lock(&free_i->segmap_lock);
+	clear_bit(segno, free_i->free_segmap);
+	free_i->free_segments++;
+
+	next = find_next_bit(free_i->free_segmap, TOTAL_SEGS(sbi), start_segno);
+	if (next >= start_segno + sbi->segs_per_sec) {
+		clear_bit(secno, free_i->free_secmap);
+		free_i->free_sections++;
+	}
+	write_unlock(&free_i->segmap_lock);
+}
+
+static inline void __set_inuse(struct f2fs_sb_info *sbi,
+		unsigned int segno)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int secno = segno / sbi->segs_per_sec;
+	set_bit(segno, free_i->free_segmap);
+	free_i->free_segments--;
+	if (!test_and_set_bit(secno, free_i->free_secmap))
+		free_i->free_sections--;
+}
+
+static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
+		unsigned int segno)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int secno = segno / sbi->segs_per_sec;
+	unsigned int start_segno = secno * sbi->segs_per_sec;
+	unsigned int next;
+
+	write_lock(&free_i->segmap_lock);
+	if (test_and_clear_bit(segno, free_i->free_segmap)) {
+		free_i->free_segments++;
+
+		next = find_next_bit(free_i->free_segmap, TOTAL_SEGS(sbi),
+								start_segno);
+		if (next >= start_segno + sbi->segs_per_sec) {
+			if (test_and_clear_bit(secno, free_i->free_secmap))
+				free_i->free_sections++;
+		}
+	}
+	write_unlock(&free_i->segmap_lock);
+}
+
+static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
+		unsigned int segno)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int secno = segno / sbi->segs_per_sec;
+	write_lock(&free_i->segmap_lock);
+	if (!test_and_set_bit(segno, free_i->free_segmap)) {
+		free_i->free_segments--;
+		if (!test_and_set_bit(secno, free_i->free_secmap))
+			free_i->free_sections--;
+	}
+	write_unlock(&free_i->segmap_lock);
+}
+
+static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
+		void *dst_addr)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size);
+}
+
+static inline block_t written_block_count(struct f2fs_sb_info *sbi)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	block_t vblocks;
+
+	mutex_lock(&sit_i->sentry_lock);
+	vblocks = sit_i->written_valid_blocks;
+	mutex_unlock(&sit_i->sentry_lock);
+
+	return vblocks;
+}
+
+static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int free_segs;
+
+	read_lock(&free_i->segmap_lock);
+	free_segs = free_i->free_segments;
+	read_unlock(&free_i->segmap_lock);
+
+	return free_segs;
+}
+
+static inline int reserved_segments(struct f2fs_sb_info *sbi)
+{
+	return SM_I(sbi)->reserved_segments;
+}
+
+static inline unsigned int free_sections(struct f2fs_sb_info *sbi)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int free_secs;
+
+	read_lock(&free_i->segmap_lock);
+	free_secs = free_i->free_sections;
+	read_unlock(&free_i->segmap_lock);
+
+	return free_secs;
+}
+
+static inline unsigned int prefree_segments(struct f2fs_sb_info *sbi)
+{
+	return DIRTY_I(sbi)->nr_dirty[PRE];
+}
+
+static inline unsigned int dirty_segments(struct f2fs_sb_info *sbi)
+{
+	return DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_DATA] +
+		DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_DATA] +
+		DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_DATA] +
+		DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_NODE] +
+		DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_NODE] +
+		DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_NODE];
+}
+
+static inline int overprovision_segments(struct f2fs_sb_info *sbi)
+{
+	return SM_I(sbi)->ovp_segments;
+}
+
+static inline int overprovision_sections(struct f2fs_sb_info *sbi)
+{
+	return ((unsigned int) overprovision_segments(sbi)) / sbi->segs_per_sec;
+}
+
+static inline int reserved_sections(struct f2fs_sb_info *sbi)
+{
+	return ((unsigned int) reserved_segments(sbi)) / sbi->segs_per_sec;
+}
+
+static inline bool need_SSR(struct f2fs_sb_info *sbi)
+{
+	return (free_sections(sbi) < overprovision_sections(sbi));
+}
+
+static inline int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	return DIRTY_I(sbi)->v_ops->get_victim(sbi,
+				&(curseg)->next_segno, BG_GC, type, SSR);
+}
+
+static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi)
+{
+	return free_sections(sbi) <= reserved_sections(sbi);
+}
+
+static inline int utilization(struct f2fs_sb_info *sbi)
+{
+	return (long int)valid_user_blocks(sbi) * 100 /
+			(long int)sbi->user_block_count;
+}
+
+/*
+ * Sometimes f2fs may be better to drop out-of-place update policy.
+ * So, if fs utilization is over MIN_IPU_UTIL, then f2fs tries to write
+ * data in the original place likewise other traditional file systems.
+ * But, currently set 100 in percentage, which means it is disabled.
+ * See below need_inplace_update().
+ */
+#define MIN_IPU_UTIL		100
+static inline bool need_inplace_update(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	if (S_ISDIR(inode->i_mode))
+		return false;
+	if (need_SSR(sbi) && utilization(sbi) > MIN_IPU_UTIL)
+		return true;
+	return false;
+}
+
+static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi,
+		int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	return curseg->segno;
+}
+
+static inline unsigned char curseg_alloc_type(struct f2fs_sb_info *sbi,
+		int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	return curseg->alloc_type;
+}
+
+static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	return curseg->next_blkoff;
+}
+
+static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	unsigned int end_segno = SM_I(sbi)->segment_count - 1;
+	BUG_ON(segno > end_segno);
+}
+
+/*
+ * This function is used for only debugging.
+ * NOTE: In future, we have to remove this function.
+ */
+static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
+{
+	struct f2fs_sm_info *sm_info = SM_I(sbi);
+	block_t total_blks = sm_info->segment_count << sbi->log_blocks_per_seg;
+	block_t start_addr = sm_info->seg0_blkaddr;
+	block_t end_addr = start_addr + total_blks - 1;
+	BUG_ON(blk_addr < start_addr);
+	BUG_ON(blk_addr > end_addr);
+}
+
+/*
+ * Summary block is always treated as invalid block
+ */
+static inline void check_block_count(struct f2fs_sb_info *sbi,
+		int segno, struct f2fs_sit_entry *raw_sit)
+{
+	struct f2fs_sm_info *sm_info = SM_I(sbi);
+	unsigned int end_segno = sm_info->segment_count - 1;
+	int valid_blocks = 0;
+	int i;
+
+	/* check segment usage */
+	BUG_ON(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg);
+
+	/* check boundary of a given segment number */
+	BUG_ON(segno > end_segno);
+
+	/* check bitmap with valid block count */
+	for (i = 0; i < sbi->blocks_per_seg; i++)
+		if (f2fs_test_bit(i, raw_sit->valid_map))
+			valid_blocks++;
+	BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
+}
+
+static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
+						unsigned int start)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	unsigned int offset = SIT_BLOCK_OFFSET(sit_i, start);
+	block_t blk_addr = sit_i->sit_base_addr + offset;
+
+	check_seg_range(sbi, start);
+
+	/* calculate sit block address */
+	if (f2fs_test_bit(offset, sit_i->sit_bitmap))
+		blk_addr += sit_i->sit_blocks;
+
+	return blk_addr;
+}
+
+static inline pgoff_t next_sit_addr(struct f2fs_sb_info *sbi,
+						pgoff_t block_addr)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	block_addr -= sit_i->sit_base_addr;
+	if (block_addr < sit_i->sit_blocks)
+		block_addr += sit_i->sit_blocks;
+	else
+		block_addr -= sit_i->sit_blocks;
+
+	return block_addr + sit_i->sit_base_addr;
+}
+
+static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
+{
+	unsigned int block_off = SIT_BLOCK_OFFSET(sit_i, start);
+
+	if (f2fs_test_bit(block_off, sit_i->sit_bitmap))
+		f2fs_clear_bit(block_off, sit_i->sit_bitmap);
+	else
+		f2fs_set_bit(block_off, sit_i->sit_bitmap);
+}
+
+static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	return sit_i->elapsed_time + CURRENT_TIME_SEC.tv_sec -
+						sit_i->mounted_time;
+}
+
+static inline void set_summary(struct f2fs_summary *sum, nid_t nid,
+			unsigned int ofs_in_node, unsigned char version)
+{
+	sum->nid = cpu_to_le32(nid);
+	sum->ofs_in_node = cpu_to_le16(ofs_in_node);
+	sum->version = version;
+}
+
+static inline block_t start_sum_block(struct f2fs_sb_info *sbi)
+{
+	return __start_cp_addr(sbi) +
+		le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
+}
+
+static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
+{
+	return __start_cp_addr(sbi) +
+		le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_total_block_count)
+				- (base + 1) + type;
+}
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index e15192cb9cf4..66353ffd06a7 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -23,6 +23,7 @@
 #define EXT4_SUPER_MAGIC	0xEF53
 #define BTRFS_SUPER_MAGIC	0x9123683E
 #define NILFS_SUPER_MAGIC	0x3434
+#define F2FS_SUPER_MAGIC	0xF2F52010
 #define HPFS_SUPER_MAGIC	0xf995e849
 #define ISOFS_SUPER_MAGIC	0x9660
 #define JFFS2_SUPER_MAGIC	0x72b6
-- 
cgit v1.2.3-55-g7522


From 25ca923b2a766b9c93b63777ead351137533a623 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim
Date: Wed, 28 Nov 2012 16:12:41 +0900
Subject: f2fs: fix endian conversion bugs reported by sparse

This patch should resolve the bugs reported by the sparse tool.
Initial reports were written by "kbuild test robot" managed by fengguang.wu.

In my local machines, I've tested also by running:
> make C=2 CF="-D__CHECK_ENDIAN__"

Accordingly, I've found lots of warnings and bugs related to the endian
conversion. And I've fixed all at this moment.

Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
---
 fs/f2fs/checkpoint.c    | 32 +++++++++++++++++---------------
 fs/f2fs/data.c          |  2 +-
 fs/f2fs/debug.c         |  2 +-
 fs/f2fs/dir.c           |  8 ++++----
 fs/f2fs/f2fs.h          | 25 +++++++++++++++++++++++--
 fs/f2fs/hash.c          |  3 +--
 fs/f2fs/node.c          |  4 ++--
 fs/f2fs/node.h          |  2 +-
 fs/f2fs/recovery.c      |  2 +-
 fs/f2fs/segment.c       | 14 +++++++-------
 fs/f2fs/super.c         |  8 ++++----
 include/linux/f2fs_fs.h |  6 +++---
 12 files changed, 65 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index ab743f92ee06..7c18f8efaadc 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -268,7 +268,7 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 {
 	block_t start_blk, orphan_blkaddr, i, j;
 
-	if (!(F2FS_CKPT(sbi)->ckpt_flags & CP_ORPHAN_PRESENT_FLAG))
+	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
 		return 0;
 
 	sbi->por_doing = 1;
@@ -287,7 +287,7 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 		f2fs_put_page(page, 1);
 	}
 	/* clear Orphan Flag */
-	F2FS_CKPT(sbi)->ckpt_flags &= (~CP_ORPHAN_PRESENT_FLAG);
+	clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
 	sbi->por_doing = 0;
 	return 0;
 }
@@ -376,7 +376,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	pre_version = le64_to_cpu(cp_block->checkpoint_ver);
 
 	/* Read the 2nd cp block in this CP pack */
-	cp_addr += le64_to_cpu(cp_block->cp_pack_total_block_count) - 1;
+	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
 	cp_page_2 = get_meta_page(sbi, cp_addr);
 
 	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2);
@@ -605,8 +605,8 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	block_t start_blk;
 	struct page *cp_page;
 	unsigned int data_sum_blocks, orphan_blocks;
+	unsigned int crc32 = 0;
 	void *kaddr;
-	__u32 crc32 = 0;
 	int i;
 
 	/* Flush all the NAT/SIT pages */
@@ -646,33 +646,35 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	/* 2 cp  + n data seg summary + orphan inode blocks */
 	data_sum_blocks = npages_for_summary_flush(sbi);
 	if (data_sum_blocks < 3)
-		ckpt->ckpt_flags |= CP_COMPACT_SUM_FLAG;
+		set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
 	else
-		ckpt->ckpt_flags &= (~CP_COMPACT_SUM_FLAG);
+		clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
 
 	orphan_blocks = (sbi->n_orphans + F2FS_ORPHANS_PER_BLOCK - 1)
 					/ F2FS_ORPHANS_PER_BLOCK;
-	ckpt->cp_pack_start_sum = 1 + orphan_blocks;
-	ckpt->cp_pack_total_block_count = 2 + data_sum_blocks + orphan_blocks;
+	ckpt->cp_pack_start_sum = cpu_to_le32(1 + orphan_blocks);
 
 	if (is_umount) {
-		ckpt->ckpt_flags |= CP_UMOUNT_FLAG;
-		ckpt->cp_pack_total_block_count += NR_CURSEG_NODE_TYPE;
+		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
+			data_sum_blocks + orphan_blocks + NR_CURSEG_NODE_TYPE);
 	} else {
-		ckpt->ckpt_flags &= (~CP_UMOUNT_FLAG);
+		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
+			data_sum_blocks + orphan_blocks);
 	}
 
 	if (sbi->n_orphans)
-		ckpt->ckpt_flags |= CP_ORPHAN_PRESENT_FLAG;
+		set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 	else
-		ckpt->ckpt_flags &= (~CP_ORPHAN_PRESENT_FLAG);
+		clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 
 	/* update SIT/NAT bitmap */
 	get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
 	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
 
 	crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset));
-	*(__u32 *)((unsigned char *)ckpt +
+	*(__le32 *)((unsigned char *)ckpt +
 				le32_to_cpu(ckpt->checksum_offset))
 				= cpu_to_le32(crc32);
 
@@ -716,7 +718,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	sbi->alloc_valid_block_count = 0;
 
 	/* Here, we only have one bio having CP pack */
-	if (sbi->ckpt->ckpt_flags & CP_ERROR_FLAG)
+	if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG))
 		sbi->sb->s_flags |= MS_RDONLY;
 	else
 		sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index c2fd0a80db16..5635cc5a9d4d 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -545,7 +545,7 @@ redirty_out:
 
 #define MAX_DESIRED_PAGES_WP	4096
 
-int f2fs_write_data_pages(struct address_space *mapping,
+static int f2fs_write_data_pages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index a56181c1b28b..fb62960a1dc1 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -27,7 +27,7 @@
 static LIST_HEAD(f2fs_stat_list);
 static struct dentry *debugfs_root;
 
-void update_general_status(struct f2fs_sb_info *sbi)
+static void update_general_status(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_stat_info *si = sbi->stat_info;
 	int i;
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 5975568d03df..5ec7a06120e1 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -80,7 +80,7 @@ static bool early_match_name(const char *name, int namelen,
 	if (le16_to_cpu(de->name_len) != namelen)
 		return false;
 
-	if (le32_to_cpu(de->hash_code) != namehash)
+	if (de->hash_code != namehash)
 		return false;
 
 	return true;
@@ -143,7 +143,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 	nbucket = dir_buckets(level);
 	nblock = bucket_blocks(level);
 
-	bidx = dir_block_index(level, namehash % nbucket);
+	bidx = dir_block_index(level, le32_to_cpu(namehash) % nbucket);
 	end_block = bidx + nblock;
 
 	for (; bidx < end_block; bidx++) {
@@ -406,7 +406,7 @@ start:
 	nbucket = dir_buckets(level);
 	nblock = bucket_blocks(level);
 
-	bidx = dir_block_index(level, (dentry_hash % nbucket));
+	bidx = dir_block_index(level, (le32_to_cpu(dentry_hash) % nbucket));
 
 	for (block = bidx; block <= (bidx + nblock - 1); block++) {
 		mutex_lock_op(sbi, DENTRY_OPS);
@@ -437,7 +437,7 @@ add_dentry:
 	wait_on_page_writeback(dentry_page);
 
 	de = &dentry_blk->dentry[bit_pos];
-	de->hash_code = cpu_to_le32(dentry_hash);
+	de->hash_code = dentry_hash;
 	de->name_len = cpu_to_le16(namelen);
 	memcpy(dentry_blk->filename[bit_pos], name, namelen);
 	de->ino = cpu_to_le32(inode->i_ino);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d3f5a70e2a49..8d7fde1bda1e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -463,6 +463,26 @@ static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi)
 	sbi->s_dirty = 0;
 }
 
+static inline bool is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
+{
+	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
+	return ckpt_flags & f;
+}
+
+static inline void set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
+{
+	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
+	ckpt_flags |= f;
+	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
+}
+
+static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
+{
+	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
+	ckpt_flags &= (~f);
+	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
+}
+
 static inline void mutex_lock_op(struct f2fs_sb_info *sbi, enum lock_type t)
 {
 	mutex_lock_nested(&sbi->fs_lock[t], t);
@@ -577,7 +597,8 @@ static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag)
 static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	int offset = (flag == NAT_BITMAP) ? ckpt->sit_ver_bitmap_bytesize : 0;
+	int offset = (flag == NAT_BITMAP) ?
+			le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
 	return &ckpt->sit_nat_version_bitmap + offset;
 }
 
@@ -587,7 +608,7 @@ static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	unsigned long long ckpt_version = le64_to_cpu(ckpt->checkpoint_ver);
 
-	start_addr = le64_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
+	start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
 
 	/*
 	 * odd numbered checkpoint should at cp segment 0
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index 098a1963d7c7..beb155e8d06d 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -92,7 +92,6 @@ f2fs_hash_t f2fs_dentry_hash(const char *name, int len)
 	hash = buf[0];
 	minor_hash = buf[1];
 
-	f2fs_hash = hash;
-	f2fs_hash &= ~F2FS_HASH_COL_BIT;
+	f2fs_hash = cpu_to_le32(hash & ~F2FS_HASH_COL_BIT);
 	return f2fs_hash;
 }
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 216f04dc1177..5d421fe22575 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1445,8 +1445,8 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 
 	memcpy(dst, src, (unsigned long)&src->i.i_ext - (unsigned long)&src->i);
 	dst->i.i_size = 0;
-	dst->i.i_blocks = 1;
-	dst->i.i_links = 1;
+	dst->i.i_blocks = cpu_to_le64(1);
+	dst->i.i_links = cpu_to_le32(1);
 	dst->i.i_xattr_nid = 0;
 
 	new_ni = old_ni;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 5d525ed312ba..0ab92d643052 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -177,7 +177,7 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
 	void *kaddr = page_address(page);
 	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
 	rn->footer.cp_ver = ckpt->checkpoint_ver;
-	rn->footer.next_blkaddr = blkaddr;
+	rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
 }
 
 static inline nid_t ino_of_node(struct page *node_page)
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 7a43df0b72c1..222a7bb92214 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -81,7 +81,7 @@ static int recover_inode(struct inode *inode, struct page *node_page)
 	struct f2fs_node *raw_node = (struct f2fs_node *)kaddr;
 	struct f2fs_inode *raw_inode = &(raw_node->i);
 
-	inode->i_mode = le32_to_cpu(raw_inode->i_mode);
+	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
 	i_size_write(inode, le64_to_cpu(raw_inode->i_size));
 	inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
 	inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index ed7c079cfc7f..d973c56e8bd6 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -630,7 +630,7 @@ static void f2fs_end_io_write(struct bio *bio, int err)
 			SetPageError(page);
 			if (page->mapping)
 				set_bit(AS_EIO, &page->mapping->flags);
-			p->sbi->ckpt->ckpt_flags |= CP_ERROR_FLAG;
+			set_ckpt_flags(p->sbi->ckpt, CP_ERROR_FLAG);
 			set_page_dirty(page);
 		}
 		end_page_writeback(page);
@@ -1067,7 +1067,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 		segno = le32_to_cpu(ckpt->cur_data_segno[type]);
 		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type -
 							CURSEG_HOT_DATA]);
-		if (ckpt->ckpt_flags & CP_UMOUNT_FLAG)
+		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type);
 		else
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
@@ -1076,7 +1076,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 							CURSEG_HOT_NODE]);
 		blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type -
 							CURSEG_HOT_NODE]);
-		if (ckpt->ckpt_flags & CP_UMOUNT_FLAG)
+		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE,
 							type - CURSEG_HOT_NODE);
 		else
@@ -1087,7 +1087,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	sum = (struct f2fs_summary_block *)page_address(new);
 
 	if (IS_NODESEG(type)) {
-		if (ckpt->ckpt_flags & CP_UMOUNT_FLAG) {
+		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) {
 			struct f2fs_summary *ns = &sum->entries[0];
 			int i;
 			for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
@@ -1119,7 +1119,7 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 {
 	int type = CURSEG_HOT_DATA;
 
-	if (sbi->ckpt->ckpt_flags & CP_COMPACT_SUM_FLAG) {
+	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) {
 		/* restore for compacted data summary */
 		if (read_compacted_summaries(sbi))
 			return -EINVAL;
@@ -1208,7 +1208,7 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi,
 
 void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 {
-	if (sbi->ckpt->ckpt_flags & CP_COMPACT_SUM_FLAG)
+	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG))
 		write_compacted_summaries(sbi, start_blk);
 	else
 		write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA);
@@ -1216,7 +1216,7 @@ void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 
 void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 {
-	if (sbi->ckpt->ckpt_flags & CP_UMOUNT_FLAG)
+	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG))
 		write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
 	return;
 }
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 8661c93538af..878bf382f848 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -89,7 +89,7 @@ static void f2fs_i_callback(struct rcu_head *head)
 	kmem_cache_free(f2fs_inode_cachep, F2FS_I(inode));
 }
 
-void f2fs_destroy_inode(struct inode *inode)
+static void f2fs_destroy_inode(struct inode *inode)
 {
 	call_rcu(&inode->i_rcu, f2fs_i_callback);
 }
@@ -445,7 +445,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (sanity_check_raw_super(raw_super))
 		goto free_sb_buf;
 
-	sb->s_maxbytes = max_file_size(raw_super->log_blocksize);
+	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
 	sb->s_max_links = F2FS_LINK_MAX;
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 
@@ -527,7 +527,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 
 	/* if there are nt orphan nodes free them */
 	err = -EINVAL;
-	if (!(sbi->ckpt->ckpt_flags & CP_UMOUNT_FLAG) &&
+	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) &&
 				recover_orphan_inodes(sbi))
 		goto free_node_inode;
 
@@ -547,7 +547,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	/* recover fsynced data */
-	if (!(sbi->ckpt->ckpt_flags & CP_UMOUNT_FLAG) &&
+	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) &&
 				!test_opt(sbi, DISABLE_ROLL_FORWARD))
 		recover_fsync_data(sbi);
 
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 1429ece7caab..c2fbbc35c1e6 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -272,8 +272,8 @@ struct f2fs_sit_block {
  * ex) data_blkaddr = (block_t)(nodepage_start_address + ofs_in_node)
  */
 #define ENTRIES_IN_SUM		512
-#define	SUMMARY_SIZE		(sizeof(struct f2fs_summary))
-#define	SUM_FOOTER_SIZE		(sizeof(struct summary_footer))
+#define	SUMMARY_SIZE		(7)	/* sizeof(struct summary) */
+#define	SUM_FOOTER_SIZE		(5)	/* sizeof(struct summary_footer) */
 #define SUM_ENTRY_SIZE		(SUMMARY_SIZE * ENTRIES_IN_SUM)
 
 /* a summary entry for a 4KB-sized block in a segment */
@@ -297,7 +297,7 @@ struct summary_footer {
 	__u32 check_sum;		/* summary checksum */
 } __packed;
 
-#define SUM_JOURNAL_SIZE	(PAGE_CACHE_SIZE - SUM_FOOTER_SIZE -\
+#define SUM_JOURNAL_SIZE	(F2FS_BLKSIZE - SUM_FOOTER_SIZE -\
 				SUM_ENTRY_SIZE)
 #define NAT_JOURNAL_ENTRIES	((SUM_JOURNAL_SIZE - 2) /\
 				sizeof(struct nat_journal_entry))
-- 
cgit v1.2.3-55-g7522


From 457d08ee4fd91c8df17917ff2d32565e6adacbfc Mon Sep 17 00:00:00 2001
From: Namjae Jeon
Date: Sat, 8 Dec 2012 14:54:50 +0900
Subject: f2fs: introduce accessor to retrieve number of dentry slots

Simplify code by providing the accessor macro to retrieve the
number of dentry slots for a given filename length.

Signed-off-by: Namjae Jeon <namjae.jeon@samsung.com>
Signed-off-by: Amit Sahrawat <a.sahrawat@samsung.com>
---
 fs/f2fs/dir.c           | 13 +++++--------
 include/linux/f2fs_fs.h |  3 +++
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index fc02d8b43aea..d900c088c7c6 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -99,8 +99,7 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
 					NR_DENTRY_IN_BLOCK, 0);
 	while (bit_pos < NR_DENTRY_IN_BLOCK) {
 		de = &dentry_blk->dentry[bit_pos];
-		slots = (le16_to_cpu(de->name_len) + F2FS_NAME_LEN - 1) /
-							F2FS_NAME_LEN;
+		slots = GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
 
 		if (early_match_name(name, namelen, namehash, de)) {
 			if (!memcmp(dentry_blk->filename[bit_pos],
@@ -130,7 +129,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 		unsigned int level, const char *name, int namelen,
 			f2fs_hash_t namehash, struct page **res_page)
 {
-	int s = (namelen + F2FS_NAME_LEN - 1) / F2FS_NAME_LEN;
+	int s = GET_DENTRY_SLOTS(namelen);
 	unsigned int nbucket, nblock;
 	unsigned int bidx, end_block;
 	struct page *dentry_page;
@@ -383,7 +382,7 @@ int f2fs_add_link(struct dentry *dentry, struct inode *inode)
 	int namelen = dentry->d_name.len;
 	struct page *dentry_page = NULL;
 	struct f2fs_dentry_block *dentry_blk = NULL;
-	int slots = (namelen + F2FS_NAME_LEN - 1) / F2FS_NAME_LEN;
+	int slots = GET_DENTRY_SLOTS(namelen);
 	int err = 0;
 	int i;
 
@@ -465,8 +464,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	struct address_space *mapping = page->mapping;
 	struct inode *dir = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
-	int slots = (le16_to_cpu(dentry->name_len) + F2FS_NAME_LEN - 1) /
-							F2FS_NAME_LEN;
+	int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
 	void *kaddr = page_address(page);
 	int i;
 
@@ -641,8 +639,7 @@ static int f2fs_readdir(struct file *file, void *dirent, filldir_t filldir)
 				file->f_pos += bit_pos - start_bit_pos;
 				goto success;
 			}
-			slots = (le16_to_cpu(de->name_len) + F2FS_NAME_LEN - 1)
-								/ F2FS_NAME_LEN;
+			slots = GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
 			bit_pos += slots;
 		}
 		bit_pos = 0;
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index c2fbbc35c1e6..f9a12f6243a5 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -363,6 +363,9 @@ typedef __le32	f2fs_hash_t;
 
 /* One directory entry slot covers 8bytes-long file name */
 #define F2FS_NAME_LEN		8
+#define F2FS_NAME_LEN_BITS	3
+
+#define GET_DENTRY_SLOTS(x)	((x + F2FS_NAME_LEN - 1) >> F2FS_NAME_LEN_BITS)
 
 /* the number of dentry in a block */
 #define NR_DENTRY_IN_BLOCK	214
-- 
cgit v1.2.3-55-g7522


From 3c58346525d82625e68e24f071804c2dc057b6f4 Mon Sep 17 00:00:00 2001
From: Christoph Lameter
Date: Wed, 28 Nov 2012 16:23:01 +0000
Subject: slab: Simplify bootstrap

The nodelists field in kmem_cache is pointing to the first unused
object in the array field when bootstrap is complete.

A problem with the current approach is that the statically sized
kmem_cache structure use on boot can only contain NR_CPUS entries.
If the number of nodes plus the number of cpus is greater then we
would overwrite memory following the kmem_cache_boot definition.

Increase the size of the array field to ensure that also the node
pointers fit into the array field.

Once we do that we no longer need the kmem_cache_nodelists
array and we can then also use that structure elsewhere.

Acked-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
---
 include/linux/slab_def.h |  6 +++++-
 mm/slab.c                | 21 +++++++++++++--------
 2 files changed, 18 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index cc290f0bdb34..45c0356fdc8c 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -89,9 +89,13 @@ struct kmem_cache {
 	 * (see kmem_cache_init())
 	 * We still use [NR_CPUS] and not [1] or [0] because cache_cache
 	 * is statically defined, so we reserve the max number of cpus.
+	 *
+	 * We also need to guarantee that the list is able to accomodate a
+	 * pointer for each node since "nodelists" uses the remainder of
+	 * available pointers.
 	 */
 	struct kmem_list3 **nodelists;
-	struct array_cache *array[NR_CPUS];
+	struct array_cache *array[NR_CPUS + MAX_NUMNODES];
 	/*
 	 * Do not add fields after array[]
 	 */
diff --git a/mm/slab.c b/mm/slab.c
index e26bff5ed1a6..c7ea5234c4e9 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -553,9 +553,7 @@ static struct arraycache_init initarray_generic =
     { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
 
 /* internal cache of cache description objs */
-static struct kmem_list3 *kmem_cache_nodelists[MAX_NUMNODES];
 static struct kmem_cache kmem_cache_boot = {
-	.nodelists = kmem_cache_nodelists,
 	.batchcount = 1,
 	.limit = BOOT_CPUCACHE_ENTRIES,
 	.shared = 1,
@@ -1559,6 +1557,15 @@ static void __init set_up_list3s(struct kmem_cache *cachep, int index)
 	}
 }
 
+/*
+ * The memory after the last cpu cache pointer is used for the
+ * the nodelists pointer.
+ */
+static void setup_nodelists_pointer(struct kmem_cache *cachep)
+{
+	cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids];
+}
+
 /*
  * Initialisation.  Called after the page allocator have been initialised and
  * before smp_init().
@@ -1573,15 +1580,14 @@ void __init kmem_cache_init(void)
 	int node;
 
 	kmem_cache = &kmem_cache_boot;
+	setup_nodelists_pointer(kmem_cache);
 
 	if (num_possible_nodes() == 1)
 		use_alien_caches = 0;
 
-	for (i = 0; i < NUM_INIT_LISTS; i++) {
+	for (i = 0; i < NUM_INIT_LISTS; i++)
 		kmem_list3_init(&initkmem_list3[i]);
-		if (i < MAX_NUMNODES)
-			kmem_cache->nodelists[i] = NULL;
-	}
+
 	set_up_list3s(kmem_cache, CACHE_CACHE);
 
 	/*
@@ -1619,7 +1625,6 @@ void __init kmem_cache_init(void)
 	list_add(&kmem_cache->list, &slab_caches);
 	kmem_cache->colour_off = cache_line_size();
 	kmem_cache->array[smp_processor_id()] = &initarray_cache.cache;
-	kmem_cache->nodelists[node] = &initkmem_list3[CACHE_CACHE + node];
 
 	/*
 	 * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
@@ -2422,7 +2427,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	else
 		gfp = GFP_NOWAIT;
 
-	cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids];
+	setup_nodelists_pointer(cachep);
 #if DEBUG
 
 	/*
-- 
cgit v1.2.3-55-g7522


From 2c3cf556b2f7ab5823195766eddec6f1a43134f5 Mon Sep 17 00:00:00 2001
From: Rik van Riel
Date: Tue, 9 Oct 2012 15:31:12 +0200
Subject: x86/mm: Introduce pte_accessible()

We need pte_present to return true for _PAGE_PROTNONE pages, to indicate that
the pte is associated with a page.

However, for TLB flushing purposes, we would like to know whether the pte
points to an actually accessible page.  This allows us to skip remote TLB
flushes for pages that are not actually accessible.

Fill in this method for x86 and provide a safe (but slower) method
on other architectures.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Fixed-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-66p11te4uj23gevgh4j987ip@git.kernel.org
[ Added Linus's review fixes. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/pgtable.h | 6 ++++++
 include/asm-generic/pgtable.h  | 4 ++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index a1f780d45f76..5fe03aaca92e 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -407,6 +407,12 @@ static inline int pte_present(pte_t a)
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
 }
 
+#define pte_accessible pte_accessible
+static inline int pte_accessible(pte_t a)
+{
+	return pte_flags(a) & _PAGE_PRESENT;
+}
+
 static inline int pte_hidden(pte_t pte)
 {
 	return pte_flags(pte) & _PAGE_HIDDEN;
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index b36ce40bd1c6..48fc1dc1c74b 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -219,6 +219,10 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #define move_pte(pte, prot, old_addr, new_addr)	(pte)
 #endif
 
+#ifndef pte_accessible
+# define pte_accessible(pte)		((void)(pte),1)
+#endif
+
 #ifndef flush_tlb_fix_spurious_fault
 #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
 #endif
-- 
cgit v1.2.3-55-g7522


From 7da4d641c58d201c3cc1835c05ca1a7fa26f0856 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra
Date: Mon, 19 Nov 2012 03:14:23 +0100
Subject: mm: Count the number of pages affected in change_protection()

This will be used for three kinds of purposes:

 - to optimize mprotect()

 - to speed up working set scanning for working set areas that
   have not been touched

 - to more accurately scan per real working set

No change in functionality from this patch.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/hugetlb.h |  8 +++++--
 include/linux/mm.h      |  3 +++
 mm/hugetlb.c            | 10 +++++++--
 mm/mprotect.c           | 58 +++++++++++++++++++++++++++++++++++++------------
 4 files changed, 61 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 225164842ab6..06e691baab86 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -87,7 +87,7 @@ struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 				pud_t *pud, int write);
 int pmd_huge(pmd_t pmd);
 int pud_huge(pud_t pmd);
-void hugetlb_change_protection(struct vm_area_struct *vma,
+unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 
 #else /* !CONFIG_HUGETLB_PAGE */
@@ -132,7 +132,11 @@ static inline void copy_huge_page(struct page *dst, struct page *src)
 {
 }
 
-#define hugetlb_change_protection(vma, address, end, newprot)
+static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
+		unsigned long address, unsigned long end, pgprot_t newprot)
+{
+	return 0;
+}
 
 static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 			struct vm_area_struct *vma, unsigned long start,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bcaab4e6fe91..1856c62d82cd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1078,6 +1078,9 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 extern unsigned long do_mremap(unsigned long addr,
 			       unsigned long old_len, unsigned long new_len,
 			       unsigned long flags, unsigned long new_addr);
+extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+			      unsigned long end, pgprot_t newprot,
+			      int dirty_accountable);
 extern int mprotect_fixup(struct vm_area_struct *vma,
 			  struct vm_area_struct **pprev, unsigned long start,
 			  unsigned long end, unsigned long newflags);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 59a0059b39e2..712895eda0d0 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3014,7 +3014,7 @@ same_page:
 	return i ? i : -EFAULT;
 }
 
-void hugetlb_change_protection(struct vm_area_struct *vma,
+unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot)
 {
 	struct mm_struct *mm = vma->vm_mm;
@@ -3022,6 +3022,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 	pte_t *ptep;
 	pte_t pte;
 	struct hstate *h = hstate_vma(vma);
+	unsigned long pages = 0;
 
 	BUG_ON(address >= end);
 	flush_cache_range(vma, address, end);
@@ -3032,12 +3033,15 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
-		if (huge_pmd_unshare(mm, &address, ptep))
+		if (huge_pmd_unshare(mm, &address, ptep)) {
+			pages++;
 			continue;
+		}
 		if (!huge_pte_none(huge_ptep_get(ptep))) {
 			pte = huge_ptep_get_and_clear(mm, address, ptep);
 			pte = pte_mkhuge(pte_modify(pte, newprot));
 			set_huge_pte_at(mm, address, ptep, pte);
+			pages++;
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
@@ -3049,6 +3053,8 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 	 */
 	flush_tlb_range(vma, start, end);
 	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+
+	return pages << h->order;
 }
 
 int hugetlb_reserve_pages(struct inode *inode,
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a40992610ab6..1e265be25f85 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -35,12 +35,13 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 }
 #endif
 
-static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
+static unsigned long change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable)
 {
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
+	unsigned long pages = 0;
 
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	arch_enter_lazy_mmu_mode();
@@ -60,6 +61,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				ptent = pte_mkwrite(ptent);
 
 			ptep_modify_prot_commit(mm, addr, pte, ptent);
+			pages++;
 		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
@@ -72,18 +74,22 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				set_pte_at(mm, addr, pte,
 					swp_entry_to_pte(entry));
 			}
+			pages++;
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
+
+	return pages;
 }
 
-static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
+static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable)
 {
 	pmd_t *pmd;
 	unsigned long next;
+	unsigned long pages = 0;
 
 	pmd = pmd_offset(pud, addr);
 	do {
@@ -91,35 +97,42 @@ static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
 				split_huge_page_pmd(vma->vm_mm, pmd);
-			else if (change_huge_pmd(vma, pmd, addr, newprot))
+			else if (change_huge_pmd(vma, pmd, addr, newprot)) {
+				pages += HPAGE_PMD_NR;
 				continue;
+			}
 			/* fall through */
 		}
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		change_pte_range(vma->vm_mm, pmd, addr, next, newprot,
+		pages += change_pte_range(vma->vm_mm, pmd, addr, next, newprot,
 				 dirty_accountable);
 	} while (pmd++, addr = next, addr != end);
+
+	return pages;
 }
 
-static inline void change_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+static inline unsigned long change_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable)
 {
 	pud_t *pud;
 	unsigned long next;
+	unsigned long pages = 0;
 
 	pud = pud_offset(pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		change_pmd_range(vma, pud, addr, next, newprot,
+		pages += change_pmd_range(vma, pud, addr, next, newprot,
 				 dirty_accountable);
 	} while (pud++, addr = next, addr != end);
+
+	return pages;
 }
 
-static void change_protection(struct vm_area_struct *vma,
+static unsigned long change_protection_range(struct vm_area_struct *vma,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable)
 {
@@ -127,6 +140,7 @@ static void change_protection(struct vm_area_struct *vma,
 	pgd_t *pgd;
 	unsigned long next;
 	unsigned long start = addr;
+	unsigned long pages = 0;
 
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
@@ -135,10 +149,30 @@ static void change_protection(struct vm_area_struct *vma,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		change_pud_range(vma, pgd, addr, next, newprot,
+		pages += change_pud_range(vma, pgd, addr, next, newprot,
 				 dirty_accountable);
 	} while (pgd++, addr = next, addr != end);
+
 	flush_tlb_range(vma, start, end);
+
+	return pages;
+}
+
+unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+		       unsigned long end, pgprot_t newprot,
+		       int dirty_accountable)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long pages;
+
+	mmu_notifier_invalidate_range_start(mm, start, end);
+	if (is_vm_hugetlb_page(vma))
+		pages = hugetlb_change_protection(vma, start, end, newprot);
+	else
+		pages = change_protection_range(vma, start, end, newprot, dirty_accountable);
+	mmu_notifier_invalidate_range_end(mm, start, end);
+
+	return pages;
 }
 
 int
@@ -213,12 +247,8 @@ success:
 		dirty_accountable = 1;
 	}
 
-	mmu_notifier_invalidate_range_start(mm, start, end);
-	if (is_vm_hugetlb_page(vma))
-		hugetlb_change_protection(vma, start, end, vma->vm_page_prot);
-	else
-		change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
-	mmu_notifier_invalidate_range_end(mm, start, end);
+	change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
+
 	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
 	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
 	perf_event_mmap(vma);
-- 
cgit v1.2.3-55-g7522


From 5647bc293ab15f66a7b1cda850c5e9d162a6c7c2 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Fri, 19 Oct 2012 10:46:20 +0100
Subject: mm: compaction: Move migration fail/success stats to migrate.c

The compact_pages_moved and compact_pagemigrate_failed events are
convenient for determining if compaction is active and to what
degree migration is succeeding but it's at the wrong level. Other
users of migration may also want to know if migration is working
properly and this will be particularly true for any automated
NUMA migration. This patch moves the counters down to migration
with the new events called pgmigrate_success and pgmigrate_fail.
The compact_blocks_moved counter is removed because while it was
useful for debugging initially, it's worthless now as no meaningful
conclusions can be drawn from its value.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
 include/linux/vm_event_item.h | 4 +++-
 mm/compaction.c               | 4 ----
 mm/migrate.c                  | 6 ++++++
 mm/vmstat.c                   | 7 ++++---
 4 files changed, 13 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 3d3114594370..8aa7cb94b5fb 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -38,8 +38,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
 		KSWAPD_SKIP_CONGESTION_WAIT,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+#ifdef CONFIG_MIGRATION
+		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
+#endif
 #ifdef CONFIG_COMPACTION
-		COMPACTBLOCKS, COMPACTPAGES, COMPACTPAGEFAILED,
 		COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS,
 #endif
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/mm/compaction.c b/mm/compaction.c
index 9eef55838fca..00ad88395216 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -994,10 +994,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		update_nr_listpages(cc);
 		nr_remaining = cc->nr_migratepages;
 
-		count_vm_event(COMPACTBLOCKS);
-		count_vm_events(COMPACTPAGES, nr_migrate - nr_remaining);
-		if (nr_remaining)
-			count_vm_events(COMPACTPAGEFAILED, nr_remaining);
 		trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
 						nr_remaining);
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 77ed2d773705..04687f69cc17 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -962,6 +962,7 @@ int migrate_pages(struct list_head *from,
 {
 	int retry = 1;
 	int nr_failed = 0;
+	int nr_succeeded = 0;
 	int pass = 0;
 	struct page *page;
 	struct page *page2;
@@ -988,6 +989,7 @@ int migrate_pages(struct list_head *from,
 				retry++;
 				break;
 			case 0:
+				nr_succeeded++;
 				break;
 			default:
 				/* Permanent failure */
@@ -998,6 +1000,10 @@ int migrate_pages(struct list_head *from,
 	}
 	rc = 0;
 out:
+	if (nr_succeeded)
+		count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
+	if (nr_failed)
+		count_vm_events(PGMIGRATE_FAIL, nr_failed);
 	if (!swapwrite)
 		current->flags &= ~PF_SWAPWRITE;
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c7370579111b..89a7fd665b32 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -774,10 +774,11 @@ const char * const vmstat_text[] = {
 
 	"pgrotated",
 
+#ifdef CONFIG_MIGRATION
+	"pgmigrate_success",
+	"pgmigrate_fail",
+#endif
 #ifdef CONFIG_COMPACTION
-	"compact_blocks_moved",
-	"compact_pages_moved",
-	"compact_pagemigrate_failed",
 	"compact_stall",
 	"compact_fail",
 	"compact_success",
-- 
cgit v1.2.3-55-g7522


From 7b2a2d4a18fffac3c4872021529b0657896db788 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Fri, 19 Oct 2012 14:07:31 +0100
Subject: mm: migrate: Add a tracepoint for migrate_pages

The pgmigrate_success and pgmigrate_fail vmstat counters tells the user
about migration activity but not the type or the reason. This patch adds
a tracepoint to identify the type of page migration and why the page is
being migrated.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
 include/linux/migrate.h        | 13 +++++++++--
 include/trace/events/migrate.h | 51 ++++++++++++++++++++++++++++++++++++++++++
 mm/compaction.c                |  3 ++-
 mm/memory-failure.c            |  3 ++-
 mm/memory_hotplug.c            |  3 ++-
 mm/mempolicy.c                 |  6 +++--
 mm/migrate.c                   | 10 +++++++--
 mm/page_alloc.c                |  3 ++-
 8 files changed, 82 insertions(+), 10 deletions(-)
 create mode 100644 include/trace/events/migrate.h

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index ce7e6671968b..9d1c159e2427 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -7,6 +7,15 @@
 
 typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 
+enum migrate_reason {
+	MR_COMPACTION,
+	MR_MEMORY_FAILURE,
+	MR_MEMORY_HOTPLUG,
+	MR_SYSCALL,		/* also applies to cpusets */
+	MR_MEMPOLICY_MBIND,
+	MR_CMA
+};
+
 #ifdef CONFIG_MIGRATION
 
 extern void putback_lru_pages(struct list_head *l);
@@ -14,7 +23,7 @@ extern int migrate_page(struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
 extern int migrate_pages(struct list_head *l, new_page_t x,
 			unsigned long private, bool offlining,
-			enum migrate_mode mode);
+			enum migrate_mode mode, int reason);
 extern int migrate_huge_page(struct page *, new_page_t x,
 			unsigned long private, bool offlining,
 			enum migrate_mode mode);
@@ -35,7 +44,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 static inline void putback_lru_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private, bool offlining,
-		enum migrate_mode mode) { return -ENOSYS; }
+		enum migrate_mode mode, int reason) { return -ENOSYS; }
 static inline int migrate_huge_page(struct page *page, new_page_t x,
 		unsigned long private, bool offlining,
 		enum migrate_mode mode) { return -ENOSYS; }
diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
new file mode 100644
index 000000000000..ec2a6ccfd7e5
--- /dev/null
+++ b/include/trace/events/migrate.h
@@ -0,0 +1,51 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM migrate
+
+#if !defined(_TRACE_MIGRATE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MIGRATE_H
+
+#define MIGRATE_MODE						\
+	{MIGRATE_ASYNC,		"MIGRATE_ASYNC"},		\
+	{MIGRATE_SYNC_LIGHT,	"MIGRATE_SYNC_LIGHT"},		\
+	{MIGRATE_SYNC,		"MIGRATE_SYNC"}		
+
+#define MIGRATE_REASON						\
+	{MR_COMPACTION,		"compaction"},			\
+	{MR_MEMORY_FAILURE,	"memory_failure"},		\
+	{MR_MEMORY_HOTPLUG,	"memory_hotplug"},		\
+	{MR_SYSCALL,		"syscall_or_cpuset"},		\
+	{MR_MEMPOLICY_MBIND,	"mempolicy_mbind"},		\
+	{MR_CMA,		"cma"}
+
+TRACE_EVENT(mm_migrate_pages,
+
+	TP_PROTO(unsigned long succeeded, unsigned long failed,
+		 enum migrate_mode mode, int reason),
+
+	TP_ARGS(succeeded, failed, mode, reason),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,		succeeded)
+		__field(	unsigned long,		failed)
+		__field(	enum migrate_mode,	mode)
+		__field(	int,			reason)
+	),
+
+	TP_fast_assign(
+		__entry->succeeded	= succeeded;
+		__entry->failed		= failed;
+		__entry->mode		= mode;
+		__entry->reason		= reason;
+	),
+
+	TP_printk("nr_succeeded=%lu nr_failed=%lu mode=%s reason=%s",
+		__entry->succeeded,
+		__entry->failed,
+		__print_symbolic(__entry->mode, MIGRATE_MODE),
+		__print_symbolic(__entry->reason, MIGRATE_REASON))
+);
+
+#endif /* _TRACE_MIGRATE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/mm/compaction.c b/mm/compaction.c
index 00ad88395216..2c077a78487c 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -990,7 +990,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		nr_migrate = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
 				(unsigned long)cc, false,
-				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC);
+				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
+				MR_COMPACTION);
 		update_nr_listpages(cc);
 		nr_remaining = cc->nr_migratepages;
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6c5899b9034a..ddb68a169e45 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1558,7 +1558,8 @@ int soft_offline_page(struct page *page, int flags)
 					    page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
-							false, MIGRATE_SYNC);
+							false, MIGRATE_SYNC,
+							MR_MEMORY_FAILURE);
 		if (ret) {
 			putback_lru_pages(&pagelist);
 			pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e4eeacae2b91..e598bd15c041 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -812,7 +812,8 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		 * migrate_pages returns # of failed pages.
 		 */
 		ret = migrate_pages(&source, alloc_migrate_target, 0,
-							true, MIGRATE_SYNC);
+							true, MIGRATE_SYNC,
+							MR_MEMORY_HOTPLUG);
 		if (ret)
 			putback_lru_pages(&source);
 	}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d04a8a54c294..66e90ecc2350 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -961,7 +961,8 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, new_node_page, dest,
-							false, MIGRATE_SYNC);
+							false, MIGRATE_SYNC,
+							MR_SYSCALL);
 		if (err)
 			putback_lru_pages(&pagelist);
 	}
@@ -1202,7 +1203,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 		if (!list_empty(&pagelist)) {
 			nr_failed = migrate_pages(&pagelist, new_vma_page,
 						(unsigned long)vma,
-						false, MIGRATE_SYNC);
+						false, MIGRATE_SYNC,
+						MR_MEMPOLICY_MBIND);
 			if (nr_failed)
 				putback_lru_pages(&pagelist);
 		}
diff --git a/mm/migrate.c b/mm/migrate.c
index 04687f69cc17..27be9c923dc1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -38,6 +38,9 @@
 
 #include <asm/tlbflush.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/migrate.h>
+
 #include "internal.h"
 
 /*
@@ -958,7 +961,7 @@ out:
  */
 int migrate_pages(struct list_head *from,
 		new_page_t get_new_page, unsigned long private, bool offlining,
-		enum migrate_mode mode)
+		enum migrate_mode mode, int reason)
 {
 	int retry = 1;
 	int nr_failed = 0;
@@ -1004,6 +1007,8 @@ out:
 		count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
 	if (nr_failed)
 		count_vm_events(PGMIGRATE_FAIL, nr_failed);
+	trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason);
+
 	if (!swapwrite)
 		current->flags &= ~PF_SWAPWRITE;
 
@@ -1145,7 +1150,8 @@ set_status:
 	err = 0;
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, new_page_node,
-				(unsigned long)pm, 0, MIGRATE_SYNC);
+				(unsigned long)pm, 0, MIGRATE_SYNC,
+				MR_SYSCALL);
 		if (err)
 			putback_lru_pages(&pagelist);
 	}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7bb35ac0964a..5953dc2d196f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5707,7 +5707,8 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 
 		ret = migrate_pages(&cc->migratepages,
 				    alloc_migrate_target,
-				    0, false, MIGRATE_SYNC);
+				    0, false, MIGRATE_SYNC,
+				    MR_CMA);
 	}
 
 	putback_lru_pages(&cc->migratepages);
-- 
cgit v1.2.3-55-g7522


From 397487db696cae0b026a474a5cd66f4e372995e6 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Fri, 19 Oct 2012 12:00:10 +0100
Subject: mm: compaction: Add scanned and isolated counters for compaction

Compaction already has tracepoints to count scanned and isolated pages
but it requires that ftrace be enabled and if that information has to be
written to disk then it can be disruptive. This patch adds vmstat counters
for compaction called compact_migrate_scanned, compact_free_scanned and
compact_isolated.

With these counters, it is possible to define a basic cost model for
compaction. This approximates of how much work compaction is doing and can
be compared that with an oprofile showing TLB misses and see if the cost of
compaction is being offset by THP for example. Minimally a compaction patch
can be evaluated in terms of whether it increases or decreases cost. The
basic cost model looks like this

Fundamental unit u:	a word	sizeof(void *)

Ca  = cost of struct page access = sizeof(struct page) / u

Cmc = Cost migrate page copy = (Ca + PAGE_SIZE/u) * 2
Cmf = Cost migrate failure   = Ca * 2
Ci  = Cost page isolation    = (Ca + Wi)
	where Wi is a constant that should reflect the approximate
	cost of the locking operation.

Csm = Cost migrate scanning = Ca
Csf = Cost free    scanning = Ca

Overall cost =	(Csm * compact_migrate_scanned) +
	      	(Csf * compact_free_scanned)    +
	      	(Ci  * compact_isolated)	+
		(Cmc * pgmigrate_success)	+
		(Cmf * pgmigrate_failed)

Where the values are read from /proc/vmstat.

This is very basic and ignores certain costs such as the allocation cost
to do a migrate page copy but any improvement to the model would still
use the same vmstat counters.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
 include/linux/vm_event_item.h | 2 ++
 mm/compaction.c               | 8 ++++++++
 mm/vmstat.c                   | 3 +++
 3 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 8aa7cb94b5fb..a1f750b8e72a 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -42,6 +42,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
 #endif
 #ifdef CONFIG_COMPACTION
+		COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED,
+		COMPACTISOLATED,
 		COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS,
 #endif
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/mm/compaction.c b/mm/compaction.c
index 2c077a78487c..aee7443a4d5a 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -356,6 +356,10 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	if (blockpfn == end_pfn)
 		update_pageblock_skip(cc, valid_page, total_isolated, false);
 
+	count_vm_events(COMPACTFREE_SCANNED, nr_scanned);
+	if (total_isolated)
+		count_vm_events(COMPACTISOLATED, total_isolated);
+
 	return total_isolated;
 }
 
@@ -646,6 +650,10 @@ next_pageblock:
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
+	count_vm_events(COMPACTMIGRATE_SCANNED, nr_scanned);
+	if (nr_isolated)
+		count_vm_events(COMPACTISOLATED, nr_isolated);
+
 	return low_pfn;
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 89a7fd665b32..3a067fabe190 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -779,6 +779,9 @@ const char * const vmstat_text[] = {
 	"pgmigrate_fail",
 #endif
 #ifdef CONFIG_COMPACTION
+	"compact_migrate_scanned",
+	"compact_free_scanned",
+	"compact_isolated",
 	"compact_stall",
 	"compact_fail",
 	"compact_success",
-- 
cgit v1.2.3-55-g7522


From be3a728427a605990a7a0b6dbf9e29b68e266146 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli
Date: Thu, 4 Oct 2012 01:50:47 +0200
Subject: mm: numa: pte_numa() and pmd_numa()

Implement pte_numa and pmd_numa.

We must atomically set the numa bit and clear the present bit to
define a pte_numa or pmd_numa.

Once a pte or pmd has been set as pte_numa or pmd_numa, the next time
a thread touches a virtual address in the corresponding virtual range,
a NUMA hinting page fault will trigger. The NUMA hinting page fault
will clear the NUMA bit and set the present bit again to resolve the
page fault.

The expectation is that a NUMA hinting page fault is used as part
of a placement policy that decides if a page should remain on the
current node or migrated to a different node.

Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 arch/x86/include/asm/pgtable.h |  11 ++++-
 include/asm-generic/pgtable.h  | 106 +++++++++++++++++++++++++++++++++++++++++
 init/Kconfig                   |  37 ++++++++++++++
 3 files changed, 152 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5fe03aaca92e..5199db2923d3 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -404,7 +404,8 @@ static inline int pte_same(pte_t a, pte_t b)
 
 static inline int pte_present(pte_t a)
 {
-	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
+	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE |
+			       _PAGE_NUMA);
 }
 
 #define pte_accessible pte_accessible
@@ -426,7 +427,8 @@ static inline int pmd_present(pmd_t pmd)
 	 * the _PAGE_PSE flag will remain set at all times while the
 	 * _PAGE_PRESENT bit is clear).
 	 */
-	return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE);
+	return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE |
+				 _PAGE_NUMA);
 }
 
 static inline int pmd_none(pmd_t pmd)
@@ -485,6 +487,11 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
 
 static inline int pmd_bad(pmd_t pmd)
 {
+#ifdef CONFIG_NUMA_BALANCING
+	/* pmd_numa check */
+	if ((pmd_flags(pmd) & (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA)
+		return 0;
+#endif
 	return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
 }
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 48fc1dc1c74b..f27c83668d10 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -558,6 +558,112 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 #endif
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
+/*
+ * _PAGE_NUMA works identical to _PAGE_PROTNONE (it's actually the
+ * same bit too). It's set only when _PAGE_PRESET is not set and it's
+ * never set if _PAGE_PRESENT is set.
+ *
+ * pte/pmd_present() returns true if pte/pmd_numa returns true. Page
+ * fault triggers on those regions if pte/pmd_numa returns true
+ * (because _PAGE_PRESENT is not set).
+ */
+#ifndef pte_numa
+static inline int pte_numa(pte_t pte)
+{
+	return (pte_flags(pte) &
+		(_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+}
+#endif
+
+#ifndef pmd_numa
+static inline int pmd_numa(pmd_t pmd)
+{
+	return (pmd_flags(pmd) &
+		(_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+}
+#endif
+
+/*
+ * pte/pmd_mknuma sets the _PAGE_ACCESSED bitflag automatically
+ * because they're called by the NUMA hinting minor page fault. If we
+ * wouldn't set the _PAGE_ACCESSED bitflag here, the TLB miss handler
+ * would be forced to set it later while filling the TLB after we
+ * return to userland. That would trigger a second write to memory
+ * that we optimize away by setting _PAGE_ACCESSED here.
+ */
+#ifndef pte_mknonnuma
+static inline pte_t pte_mknonnuma(pte_t pte)
+{
+	pte = pte_clear_flags(pte, _PAGE_NUMA);
+	return pte_set_flags(pte, _PAGE_PRESENT|_PAGE_ACCESSED);
+}
+#endif
+
+#ifndef pmd_mknonnuma
+static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+{
+	pmd = pmd_clear_flags(pmd, _PAGE_NUMA);
+	return pmd_set_flags(pmd, _PAGE_PRESENT|_PAGE_ACCESSED);
+}
+#endif
+
+#ifndef pte_mknuma
+static inline pte_t pte_mknuma(pte_t pte)
+{
+	pte = pte_set_flags(pte, _PAGE_NUMA);
+	return pte_clear_flags(pte, _PAGE_PRESENT);
+}
+#endif
+
+#ifndef pmd_mknuma
+static inline pmd_t pmd_mknuma(pmd_t pmd)
+{
+	pmd = pmd_set_flags(pmd, _PAGE_NUMA);
+	return pmd_clear_flags(pmd, _PAGE_PRESENT);
+}
+#endif
+#else
+extern int pte_numa(pte_t pte);
+extern int pmd_numa(pmd_t pmd);
+extern pte_t pte_mknonnuma(pte_t pte);
+extern pmd_t pmd_mknonnuma(pmd_t pmd);
+extern pte_t pte_mknuma(pte_t pte);
+extern pmd_t pmd_mknuma(pmd_t pmd);
+#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
+#else
+static inline int pmd_numa(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline int pte_numa(pte_t pte)
+{
+	return 0;
+}
+
+static inline pte_t pte_mknonnuma(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+{
+	return pmd;
+}
+
+static inline pte_t pte_mknuma(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_mknuma(pmd_t pmd)
+{
+	return pmd;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #endif /* CONFIG_MMU */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/init/Kconfig b/init/Kconfig
index 6fdd6e339326..9f00f004796a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -696,6 +696,43 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
 	bool
 
+#
+# For architectures that want to enable the support for NUMA-affine scheduler
+# balancing logic:
+#
+config ARCH_SUPPORTS_NUMA_BALANCING
+	bool
+
+# For architectures that (ab)use NUMA to represent different memory regions
+# all cpu-local but of different latencies, such as SuperH.
+#
+config ARCH_WANT_NUMA_VARIABLE_LOCALITY
+	bool
+
+#
+# For architectures that are willing to define _PAGE_NUMA as _PAGE_PROTNONE
+config ARCH_WANTS_PROT_NUMA_PROT_NONE
+	bool
+
+config ARCH_USES_NUMA_PROT_NONE
+	bool
+	default y
+	depends on ARCH_WANTS_PROT_NUMA_PROT_NONE
+	depends on NUMA_BALANCING
+
+config NUMA_BALANCING
+	bool "Memory placement aware NUMA scheduler"
+	default y
+	depends on ARCH_SUPPORTS_NUMA_BALANCING
+	depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
+	depends on SMP && NUMA && MIGRATION
+	help
+	  This option adds support for automatic NUMA aware memory/task placement.
+	  The mechanism is quite primitive and is based on migrating memory when
+	  it is references to the node the task is running on.
+
+	  This system will be inactive on UMA systems.
+
 menuconfig CGROUPS
 	boolean "Control Group support"
 	depends on EVENTFD
-- 
cgit v1.2.3-55-g7522


From 0b9d705297b273657923518dbea2377cd03532ed Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli
Date: Fri, 5 Oct 2012 21:36:27 +0200
Subject: mm: numa: Support NUMA hinting page faults from gup/gup_fast

Introduce FOLL_NUMA to tell follow_page to check
pte/pmd_numa. get_user_pages must use FOLL_NUMA, and it's safe to do
so because it always invokes handle_mm_fault and retries the
follow_page later.

KVM secondary MMU page faults will trigger the NUMA hinting page
faults through gup_fast -> get_user_pages -> follow_page ->
handle_mm_fault.

Other follow_page callers like KSM should not use FOLL_NUMA, or they
would fail to get the pages if they use follow_page instead of
get_user_pages.

[ This patch was picked up from the AutoNUMA tree. ]

Originally-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
[ ported to this tree. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
 include/linux/mm.h |  1 +
 mm/memory.c        | 17 +++++++++++++++++
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1856c62d82cd..fa1615211159 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1572,6 +1572,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address,
 #define FOLL_MLOCK	0x40	/* mark page as mlocked */
 #define FOLL_SPLIT	0x80	/* don't return transhuge pages, split them */
 #define FOLL_HWPOISON	0x100	/* check page is hwpoisoned */
+#define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
diff --git a/mm/memory.c b/mm/memory.c
index 7cf762857baa..cd8e0daf1912 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1517,6 +1517,8 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
 		goto out;
 	}
+	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+		goto no_page_table;
 	if (pmd_trans_huge(*pmd)) {
 		if (flags & FOLL_SPLIT) {
 			split_huge_page_pmd(mm, pmd);
@@ -1546,6 +1548,8 @@ split_fallthrough:
 	pte = *ptep;
 	if (!pte_present(pte))
 		goto no_page;
+	if ((flags & FOLL_NUMA) && pte_numa(pte))
+		goto no_page;
 	if ((flags & FOLL_WRITE) && !pte_write(pte))
 		goto unlock;
 
@@ -1697,6 +1701,19 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			(VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
 	vm_flags &= (gup_flags & FOLL_FORCE) ?
 			(VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+
+	/*
+	 * If FOLL_FORCE and FOLL_NUMA are both set, handle_mm_fault
+	 * would be called on PROT_NONE ranges. We must never invoke
+	 * handle_mm_fault on PROT_NONE ranges or the NUMA hinting
+	 * page faults would unprotect the PROT_NONE ranges if
+	 * _PAGE_NUMA and _PAGE_PROTNONE are sharing the same pte/pmd
+	 * bitflag. So to avoid that, don't set FOLL_NUMA if
+	 * FOLL_FORCE is set.
+	 */
+	if (!(gup_flags & FOLL_FORCE))
+		gup_flags |= FOLL_NUMA;
+
 	i = 0;
 
 	do {
-- 
cgit v1.2.3-55-g7522


From d10e63f29488b0f312a443f9507ea9b6fd3c9090 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Thu, 25 Oct 2012 14:16:31 +0200
Subject: mm: numa: Create basic numa page hinting infrastructure

Note: This patch started as "mm/mpol: Create special PROT_NONE
	infrastructure" and preserves the basic idea but steals *very*
	heavily from "autonuma: numa hinting page faults entry points" for
	the actual fault handlers without the migration parts.	The end
	result is barely recognisable as either patch so all Signed-off
	and Reviewed-bys are dropped. If Peter, Ingo and Andrea are ok with
	this version, I will re-add the signed-offs-by to reflect the history.

In order to facilitate a lazy -- fault driven -- migration of pages, create
a special transient PAGE_NUMA variant, we can then use the 'spurious'
protection faults to drive our migrations from.

The meaning of PAGE_NUMA depends on the architecture but on x86 it is
effectively PROT_NONE. Actual PROT_NONE mappings will not generate these
NUMA faults for the reason that the page fault code checks the permission on
the VMA (and will throw a segmentation fault on actual PROT_NONE mappings),
before it ever calls handle_mm_fault.

[dhillf@gmail.com: Fix typo]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
 include/linux/huge_mm.h |  10 +++++
 mm/huge_memory.c        |  22 ++++++++++
 mm/memory.c             | 112 ++++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 141 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b31cb7da0346..a1d26a98c655 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -159,6 +159,10 @@ static inline struct page *compound_trans_head(struct page *page)
 	}
 	return page;
 }
+
+extern int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
+				  pmd_t pmd, pmd_t *pmdp);
+
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
@@ -195,6 +199,12 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd,
 {
 	return 0;
 }
+
+static inline int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
+					pmd_t pmd, pmd_t *pmdp)
+{
+}
+
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cd24aa562144..f5f37630c54d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1018,6 +1018,28 @@ out:
 	return page;
 }
 
+/* NUMA hinting page fault entry point for trans huge pmds */
+int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
+				pmd_t pmd, pmd_t *pmdp)
+{
+	struct page *page;
+	unsigned long haddr = addr & HPAGE_PMD_MASK;
+
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(pmd, *pmdp)))
+		goto out_unlock;
+
+	page = pmd_page(pmd);
+	pmd = pmd_mknonnuma(pmd);
+	set_pmd_at(mm, haddr, pmdp, pmd);
+	VM_BUG_ON(pmd_numa(*pmdp));
+	update_mmu_cache_pmd(vma, addr, pmdp);
+
+out_unlock:
+	spin_unlock(&mm->page_table_lock);
+	return 0;
+}
+
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
diff --git a/mm/memory.c b/mm/memory.c
index cd8e0daf1912..e30616f2cc3d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3448,6 +3448,103 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
 }
 
+int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+		   unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd)
+{
+	struct page *page;
+	spinlock_t *ptl;
+
+	/*
+	* The "pte" at this point cannot be used safely without
+	* validation through pte_unmap_same(). It's of NUMA type but
+	* the pfn may be screwed if the read is non atomic.
+	*
+	* ptep_modify_prot_start is not called as this is clearing
+	* the _PAGE_NUMA bit and it is not really expected that there
+	* would be concurrent hardware modifications to the PTE.
+	*/
+	ptl = pte_lockptr(mm, pmd);
+	spin_lock(ptl);
+	if (unlikely(!pte_same(*ptep, pte)))
+		goto out_unlock;
+	pte = pte_mknonnuma(pte);
+	set_pte_at(mm, addr, ptep, pte);
+	update_mmu_cache(vma, addr, ptep);
+
+	page = vm_normal_page(vma, addr, pte);
+	if (!page) {
+		pte_unmap_unlock(ptep, ptl);
+		return 0;
+	}
+
+out_unlock:
+	pte_unmap_unlock(ptep, ptl);
+	return 0;
+}
+
+/* NUMA hinting page fault entry point for regular pmds */
+#ifdef CONFIG_NUMA_BALANCING
+static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+		     unsigned long addr, pmd_t *pmdp)
+{
+	pmd_t pmd;
+	pte_t *pte, *orig_pte;
+	unsigned long _addr = addr & PMD_MASK;
+	unsigned long offset;
+	spinlock_t *ptl;
+	bool numa = false;
+
+	spin_lock(&mm->page_table_lock);
+	pmd = *pmdp;
+	if (pmd_numa(pmd)) {
+		set_pmd_at(mm, _addr, pmdp, pmd_mknonnuma(pmd));
+		numa = true;
+	}
+	spin_unlock(&mm->page_table_lock);
+
+	if (!numa)
+		return 0;
+
+	/* we're in a page fault so some vma must be in the range */
+	BUG_ON(!vma);
+	BUG_ON(vma->vm_start >= _addr + PMD_SIZE);
+	offset = max(_addr, vma->vm_start) & ~PMD_MASK;
+	VM_BUG_ON(offset >= PMD_SIZE);
+	orig_pte = pte = pte_offset_map_lock(mm, pmdp, _addr, &ptl);
+	pte += offset >> PAGE_SHIFT;
+	for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
+		pte_t pteval = *pte;
+		struct page *page;
+		if (!pte_present(pteval))
+			continue;
+		if (!pte_numa(pteval))
+			continue;
+		if (addr >= vma->vm_end) {
+			vma = find_vma(mm, addr);
+			/* there's a pte present so there must be a vma */
+			BUG_ON(!vma);
+			BUG_ON(addr < vma->vm_start);
+		}
+		if (pte_numa(pteval)) {
+			pteval = pte_mknonnuma(pteval);
+			set_pte_at(mm, addr, pte, pteval);
+		}
+		page = vm_normal_page(vma, addr, pteval);
+		if (unlikely(!page))
+			continue;
+	}
+	pte_unmap_unlock(orig_pte, ptl);
+
+	return 0;
+}
+#else
+static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+		     unsigned long addr, pmd_t *pmdp)
+{
+	BUG();
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /*
  * These routines also need to handle stuff like marking pages dirty
  * and/or accessed for architectures that don't do it in hardware (most
@@ -3486,6 +3583,9 @@ int handle_pte_fault(struct mm_struct *mm,
 					pte, pmd, flags, entry);
 	}
 
+	if (pte_numa(entry))
+		return do_numa_page(mm, vma, address, entry, pte, pmd);
+
 	ptl = pte_lockptr(mm, pmd);
 	spin_lock(ptl);
 	if (unlikely(!pte_same(*pte, entry)))
@@ -3554,9 +3654,11 @@ retry:
 
 		barrier();
 		if (pmd_trans_huge(orig_pmd)) {
-			if (flags & FAULT_FLAG_WRITE &&
-			    !pmd_write(orig_pmd) &&
-			    !pmd_trans_splitting(orig_pmd)) {
+			if (pmd_numa(*pmd))
+				return do_huge_pmd_numa_page(mm, address,
+							     orig_pmd, pmd);
+
+			if ((flags & FAULT_FLAG_WRITE) && !pmd_write(orig_pmd)) {
 				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
 							  orig_pmd);
 				/*
@@ -3568,10 +3670,14 @@ retry:
 					goto retry;
 				return ret;
 			}
+
 			return 0;
 		}
 	}
 
+	if (pmd_numa(*pmd))
+		return do_pmd_numa_page(mm, vma, address, pmd);
+
 	/*
 	 * Use __pte_alloc instead of pte_alloc_map, because we can't
 	 * run pte_offset_map on the pmd, if an huge pmd could
-- 
cgit v1.2.3-55-g7522


From 479e2802d09f1e18a97262c4c6f8f17ae5884bd8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra
Date: Thu, 25 Oct 2012 14:16:28 +0200
Subject: mm: mempolicy: Make MPOL_LOCAL a real policy

Make MPOL_LOCAL a real and exposed policy such that applications that
relied on the previous default behaviour can explicitly request it.

Requested-by: Christoph Lameter <cl@linux.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/uapi/linux/mempolicy.h | 1 +
 mm/mempolicy.c                 | 9 ++++++---
 2 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 23e62e0537e2..3e835c9d847b 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -20,6 +20,7 @@ enum {
 	MPOL_PREFERRED,
 	MPOL_BIND,
 	MPOL_INTERLEAVE,
+	MPOL_LOCAL,
 	MPOL_MAX,	/* always last member of enum */
 };
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 66e90ecc2350..54bd3e5ed776 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -269,6 +269,10 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 			     (flags & MPOL_F_RELATIVE_NODES)))
 				return ERR_PTR(-EINVAL);
 		}
+	} else if (mode == MPOL_LOCAL) {
+		if (!nodes_empty(*nodes))
+			return ERR_PTR(-EINVAL);
+		mode = MPOL_PREFERRED;
 	} else if (nodes_empty(*nodes))
 		return ERR_PTR(-EINVAL);
 	policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
@@ -2399,7 +2403,6 @@ void numa_default_policy(void)
  * "local" is pseudo-policy:  MPOL_PREFERRED with MPOL_F_LOCAL flag
  * Used only for mpol_parse_str() and mpol_to_str()
  */
-#define MPOL_LOCAL MPOL_MAX
 static const char * const policy_modes[] =
 {
 	[MPOL_DEFAULT]    = "default",
@@ -2452,12 +2455,12 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
 	if (flags)
 		*flags++ = '\0';	/* terminate mode string */
 
-	for (mode = 0; mode <= MPOL_LOCAL; mode++) {
+	for (mode = 0; mode < MPOL_MAX; mode++) {
 		if (!strcmp(str, policy_modes[mode])) {
 			break;
 		}
 	}
-	if (mode > MPOL_LOCAL)
+	if (mode >= MPOL_MAX)
 		goto out;
 
 	switch (mode) {
-- 
cgit v1.2.3-55-g7522


From d3a710337b0590f43fd236d5e6518439afc7410a Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn
Date: Thu, 25 Oct 2012 14:16:29 +0200
Subject: mm: mempolicy: Add MPOL_NOOP

This patch augments the MPOL_MF_LAZY feature by adding a "NOOP" policy
to mbind().  When the NOOP policy is used with the 'MOVE and 'LAZY
flags, mbind() will map the pages PROT_NONE so that they will be
migrated on the next touch.

This allows an application to prepare for a new phase of operation
where different regions of shared storage will be assigned to
worker threads, w/o changing policy.  Note that we could just use
"default" policy in this case.  However, this also allows an
application to request that pages be migrated, only if necessary,
to follow any arbitrary policy that might currently apply to a
range of pages, without knowing the policy, or without specifying
multiple mbind()s for ranges with different policies.

[ Bug in early version of mpol_parse_str() reported by Fengguang Wu. ]

Bug-Reported-by: Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/uapi/linux/mempolicy.h |  1 +
 mm/mempolicy.c                 | 11 ++++++-----
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 3e835c9d847b..d23dca8367cc 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -21,6 +21,7 @@ enum {
 	MPOL_BIND,
 	MPOL_INTERLEAVE,
 	MPOL_LOCAL,
+	MPOL_NOOP,		/* retain existing policy for range */
 	MPOL_MAX,	/* always last member of enum */
 };
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 54bd3e5ed776..c21e91477c4f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -251,10 +251,10 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 	pr_debug("setting mode %d flags %d nodes[0] %lx\n",
 		 mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
 
-	if (mode == MPOL_DEFAULT) {
+	if (mode == MPOL_DEFAULT || mode == MPOL_NOOP) {
 		if (nodes && !nodes_empty(*nodes))
 			return ERR_PTR(-EINVAL);
-		return NULL;	/* simply delete any existing policy */
+		return NULL;
 	}
 	VM_BUG_ON(!nodes);
 
@@ -1147,7 +1147,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (start & ~PAGE_MASK)
 		return -EINVAL;
 
-	if (mode == MPOL_DEFAULT)
+	if (mode == MPOL_DEFAULT || mode == MPOL_NOOP)
 		flags &= ~MPOL_MF_STRICT;
 
 	len = (len + PAGE_SIZE - 1) & PAGE_MASK;
@@ -2409,7 +2409,8 @@ static const char * const policy_modes[] =
 	[MPOL_PREFERRED]  = "prefer",
 	[MPOL_BIND]       = "bind",
 	[MPOL_INTERLEAVE] = "interleave",
-	[MPOL_LOCAL]      = "local"
+	[MPOL_LOCAL]      = "local",
+	[MPOL_NOOP]	  = "noop",	/* should not actually be used */
 };
 
 
@@ -2460,7 +2461,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
 			break;
 		}
 	}
-	if (mode >= MPOL_MAX)
+	if (mode >= MPOL_MAX || mode == MPOL_NOOP)
 		goto out;
 
 	switch (mode) {
-- 
cgit v1.2.3-55-g7522


From 771fb4d806a92bf6c988fcfbd286ae40a9374332 Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn
Date: Thu, 25 Oct 2012 14:16:30 +0200
Subject: mm: mempolicy: Check for misplaced page

This patch provides a new function to test whether a page resides
on a node that is appropriate for the mempolicy for the vma and
address where the page is supposed to be mapped.  This involves
looking up the node where the page belongs.  So, the function
returns that node so that it may be used to allocated the page
without consulting the policy again.

A subsequent patch will call this function from the fault path.
Because of this, I don't want to go ahead and allocate the page, e.g.,
via alloc_page_vma() only to have to free it if it has the correct
policy.  So, I just mimic the alloc_page_vma() node computation
logic--sort of.

Note:  we could use this function to implement a MPOL_MF_STRICT
behavior when migrating pages to match mbind() mempolicy--e.g.,
to ensure that pages in an interleaved range are reinterleaved
rather than left where they are when they reside on any page in
the interleave nodemask.

Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
[ Added MPOL_F_LAZY to trigger migrate-on-fault;
  simplified code now that we don't have to bother
  with special crap for interleaved ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mempolicy.h      |  8 +++++
 include/uapi/linux/mempolicy.h |  1 +
 mm/mempolicy.c                 | 76 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 85 insertions(+)

(limited to 'include')

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index e5ccb9ddd90e..c511e2523560 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -198,6 +198,8 @@ static inline int vma_migratable(struct vm_area_struct *vma)
 	return 1;
 }
 
+extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
+
 #else
 
 struct mempolicy {};
@@ -323,5 +325,11 @@ static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
 	return 0;
 }
 
+static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
+				 unsigned long address)
+{
+	return -1; /* no node preference */
+}
+
 #endif /* CONFIG_NUMA */
 #endif
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index d23dca8367cc..472de8a5d37e 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -61,6 +61,7 @@ enum mpol_rebind_step {
 #define MPOL_F_SHARED  (1 << 0)	/* identify shared policies */
 #define MPOL_F_LOCAL   (1 << 1)	/* preferred local allocation */
 #define MPOL_F_REBINDING (1 << 2)	/* identify policies in rebinding */
+#define MPOL_F_MOF	(1 << 3) /* this policy wants migrate on fault */
 
 
 #endif /* _UAPI_LINUX_MEMPOLICY_H */
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index c21e91477c4f..df1466d3d2d8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2181,6 +2181,82 @@ static void sp_free(struct sp_node *n)
 	kmem_cache_free(sn_cache, n);
 }
 
+/**
+ * mpol_misplaced - check whether current page node is valid in policy
+ *
+ * @page   - page to be checked
+ * @vma    - vm area where page mapped
+ * @addr   - virtual address where page mapped
+ *
+ * Lookup current policy node id for vma,addr and "compare to" page's
+ * node id.
+ *
+ * Returns:
+ *	-1	- not misplaced, page is in the right node
+ *	node	- node id where the page should be
+ *
+ * Policy determination "mimics" alloc_page_vma().
+ * Called from fault path where we know the vma and faulting address.
+ */
+int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr)
+{
+	struct mempolicy *pol;
+	struct zone *zone;
+	int curnid = page_to_nid(page);
+	unsigned long pgoff;
+	int polnid = -1;
+	int ret = -1;
+
+	BUG_ON(!vma);
+
+	pol = get_vma_policy(current, vma, addr);
+	if (!(pol->flags & MPOL_F_MOF))
+		goto out;
+
+	switch (pol->mode) {
+	case MPOL_INTERLEAVE:
+		BUG_ON(addr >= vma->vm_end);
+		BUG_ON(addr < vma->vm_start);
+
+		pgoff = vma->vm_pgoff;
+		pgoff += (addr - vma->vm_start) >> PAGE_SHIFT;
+		polnid = offset_il_node(pol, vma, pgoff);
+		break;
+
+	case MPOL_PREFERRED:
+		if (pol->flags & MPOL_F_LOCAL)
+			polnid = numa_node_id();
+		else
+			polnid = pol->v.preferred_node;
+		break;
+
+	case MPOL_BIND:
+		/*
+		 * allows binding to multiple nodes.
+		 * use current page if in policy nodemask,
+		 * else select nearest allowed node, if any.
+		 * If no allowed nodes, use current [!misplaced].
+		 */
+		if (node_isset(curnid, pol->v.nodes))
+			goto out;
+		(void)first_zones_zonelist(
+				node_zonelist(numa_node_id(), GFP_HIGHUSER),
+				gfp_zone(GFP_HIGHUSER),
+				&pol->v.nodes, &zone);
+		polnid = zone->node;
+		break;
+
+	default:
+		BUG();
+	}
+	if (curnid != polnid)
+		ret = polnid;
+out:
+	mpol_cond_put(pol);
+
+	return ret;
+}
+
 static void sp_delete(struct shared_policy *sp, struct sp_node *n)
 {
 	pr_debug("deleting %lx-l%lx\n", n->start, n->end);
-- 
cgit v1.2.3-55-g7522


From 7039e1dbec6eeaa8ecab43a82d6589eeced995c3 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra
Date: Thu, 25 Oct 2012 14:16:34 +0200
Subject: mm: migrate: Introduce migrate_misplaced_page()

Note: This was originally based on Peter's patch "mm/migrate: Introduce
	migrate_misplaced_page()" but borrows extremely heavily from Andrea's
	"autonuma: memory follows CPU algorithm and task/mm_autonuma stats
	collection". The end result is barely recognisable so signed-offs
	had to be dropped. If original authors are ok with it, I'll
	re-add the signed-off-bys.

Add migrate_misplaced_page() which deals with migrating pages from
faults.

Based-on-work-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Based-on-work-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Based-on-work-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
 include/linux/migrate.h |  11 +++++
 mm/migrate.c            | 108 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 117 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 9d1c159e2427..f0d0313eea6f 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -13,6 +13,7 @@ enum migrate_reason {
 	MR_MEMORY_HOTPLUG,
 	MR_SYSCALL,		/* also applies to cpusets */
 	MR_MEMPOLICY_MBIND,
+	MR_NUMA_MISPLACED,
 	MR_CMA
 };
 
@@ -73,4 +74,14 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 #define fail_migrate_page NULL
 
 #endif /* CONFIG_MIGRATION */
+
+#ifdef CONFIG_NUMA_BALANCING
+extern int migrate_misplaced_page(struct page *page, int node);
+#else
+static inline int migrate_misplaced_page(struct page *page, int node)
+{
+	return -EAGAIN; /* can't migrate now */
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #endif /* _LINUX_MIGRATE_H */
diff --git a/mm/migrate.c b/mm/migrate.c
index 27be9c923dc1..d168aec98427 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -282,7 +282,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page,
 		struct buffer_head *head, enum migrate_mode mode)
 {
-	int expected_count;
+	int expected_count = 0;
 	void **pslot;
 
 	if (!mapping) {
@@ -1415,4 +1415,108 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
  	}
  	return err;
 }
-#endif
+
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * Returns true if this is a safe migration target node for misplaced NUMA
+ * pages. Currently it only checks the watermarks which crude
+ */
+static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
+				   int nr_migrate_pages)
+{
+	int z;
+	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
+		struct zone *zone = pgdat->node_zones + z;
+
+		if (!populated_zone(zone))
+			continue;
+
+		if (zone->all_unreclaimable)
+			continue;
+
+		/* Avoid waking kswapd by allocating pages_to_migrate pages. */
+		if (!zone_watermark_ok(zone, 0,
+				       high_wmark_pages(zone) +
+				       nr_migrate_pages,
+				       0, 0))
+			continue;
+		return true;
+	}
+	return false;
+}
+
+static struct page *alloc_misplaced_dst_page(struct page *page,
+					   unsigned long data,
+					   int **result)
+{
+	int nid = (int) data;
+	struct page *newpage;
+
+	newpage = alloc_pages_exact_node(nid,
+					 (GFP_HIGHUSER_MOVABLE | GFP_THISNODE |
+					  __GFP_NOMEMALLOC | __GFP_NORETRY |
+					  __GFP_NOWARN) &
+					 ~GFP_IOFS, 0);
+	return newpage;
+}
+
+/*
+ * Attempt to migrate a misplaced page to the specified destination
+ * node. Caller is expected to have an elevated reference count on
+ * the page that will be dropped by this function before returning.
+ */
+int migrate_misplaced_page(struct page *page, int node)
+{
+	int isolated = 0;
+	LIST_HEAD(migratepages);
+
+	/*
+	 * Don't migrate pages that are mapped in multiple processes.
+	 * TODO: Handle false sharing detection instead of this hammer
+	 */
+	if (page_mapcount(page) != 1) {
+		put_page(page);
+		goto out;
+	}
+
+	/* Avoid migrating to a node that is nearly full */
+	if (migrate_balanced_pgdat(NODE_DATA(node), 1)) {
+		int page_lru;
+
+		if (isolate_lru_page(page)) {
+			put_page(page);
+			goto out;
+		}
+		isolated = 1;
+
+		/*
+		 * Page is isolated which takes a reference count so now the
+		 * callers reference can be safely dropped without the page
+		 * disappearing underneath us during migration
+		 */
+		put_page(page);
+
+		page_lru = page_is_file_cache(page);
+		inc_zone_page_state(page, NR_ISOLATED_ANON + page_lru);
+		list_add(&page->lru, &migratepages);
+	}
+
+	if (isolated) {
+		int nr_remaining;
+
+		nr_remaining = migrate_pages(&migratepages,
+				alloc_misplaced_dst_page,
+				node, false, MIGRATE_ASYNC,
+				MR_NUMA_MISPLACED);
+		if (nr_remaining) {
+			putback_lru_pages(&migratepages);
+			isolated = 0;
+		}
+	}
+	BUG_ON(!list_empty(&migratepages));
+out:
+	return isolated;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+#endif /* CONFIG_NUMA */
-- 
cgit v1.2.3-55-g7522


From 4daae3b4b9e49b7e0935499a352f1c59d90287d2 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Fri, 2 Nov 2012 11:33:45 +0000
Subject: mm: mempolicy: Use _PAGE_NUMA to migrate pages

Note: Based on "mm/mpol: Use special PROT_NONE to migrate pages" but
	sufficiently different that the signed-off-bys were dropped

Combine our previous _PAGE_NUMA, mpol_misplaced and migrate_misplaced_page()
pieces into an effective migrate on fault scheme.

Note that (on x86) we rely on PROT_NONE pages being !present and avoid
the TLB flush from try_to_unmap(TTU_MIGRATION). This greatly improves the
page-migration performance.

Based-on-work-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/huge_mm.h |  9 +++++----
 mm/huge_memory.c        | 31 ++++++++++++++++++++++++++++---
 mm/memory.c             | 32 +++++++++++++++++++++++++++-----
 3 files changed, 60 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index a1d26a98c655..dabb5108d6c0 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -160,8 +160,8 @@ static inline struct page *compound_trans_head(struct page *page)
 	return page;
 }
 
-extern int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
-				  pmd_t pmd, pmd_t *pmdp);
+extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+				unsigned long addr, pmd_t pmd, pmd_t *pmdp);
 
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
@@ -200,9 +200,10 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd,
 	return 0;
 }
 
-static inline int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
-					pmd_t pmd, pmd_t *pmdp)
+static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+					unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
+	return 0;
 }
 
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f5f37630c54d..5723b551c023 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -18,6 +18,7 @@
 #include <linux/freezer.h>
 #include <linux/mman.h>
 #include <linux/pagemap.h>
+#include <linux/migrate.h>
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
 #include "internal.h"
@@ -1019,17 +1020,39 @@ out:
 }
 
 /* NUMA hinting page fault entry point for trans huge pmds */
-int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
-				pmd_t pmd, pmd_t *pmdp)
+int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
-	struct page *page;
+	struct page *page = NULL;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
+	int target_nid;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
 	page = pmd_page(pmd);
+	get_page(page);
+	spin_unlock(&mm->page_table_lock);
+
+	target_nid = mpol_misplaced(page, vma, haddr);
+	if (target_nid == -1)
+		goto clear_pmdnuma;
+
+	/*
+	 * Due to lacking code to migrate thp pages, we'll split
+	 * (which preserves the special PROT_NONE) and re-take the
+	 * fault on the normal pages.
+	 */
+	split_huge_page(page);
+	put_page(page);
+	return 0;
+
+clear_pmdnuma:
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(pmd, *pmdp)))
+		goto out_unlock;
+
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
@@ -1037,6 +1060,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
 
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
+	if (page)
+		put_page(page);
 	return 0;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index e30616f2cc3d..d52542680e10 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -57,6 +57,7 @@
 #include <linux/swapops.h>
 #include <linux/elf.h>
 #include <linux/gfp.h>
+#include <linux/migrate.h>
 
 #include <asm/io.h>
 #include <asm/pgalloc.h>
@@ -3451,8 +3452,9 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		   unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd)
 {
-	struct page *page;
+	struct page *page = NULL;
 	spinlock_t *ptl;
+	int current_nid, target_nid;
 
 	/*
 	* The "pte" at this point cannot be used safely without
@@ -3465,8 +3467,11 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	*/
 	ptl = pte_lockptr(mm, pmd);
 	spin_lock(ptl);
-	if (unlikely(!pte_same(*ptep, pte)))
-		goto out_unlock;
+	if (unlikely(!pte_same(*ptep, pte))) {
+		pte_unmap_unlock(ptep, ptl);
+		goto out;
+	}
+
 	pte = pte_mknonnuma(pte);
 	set_pte_at(mm, addr, ptep, pte);
 	update_mmu_cache(vma, addr, ptep);
@@ -3477,8 +3482,25 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return 0;
 	}
 
-out_unlock:
+	get_page(page);
+	current_nid = page_to_nid(page);
+	target_nid = mpol_misplaced(page, vma, addr);
 	pte_unmap_unlock(ptep, ptl);
+	if (target_nid == -1) {
+		/*
+		 * Account for the fault against the current node if it not
+		 * being replaced regardless of where the page is located.
+		 */
+		current_nid = numa_node_id();
+		put_page(page);
+		goto out;
+	}
+
+	/* Migrate to the requested node */
+	if (migrate_misplaced_page(page, target_nid))
+		current_nid = target_nid;
+
+out:
 	return 0;
 }
 
@@ -3655,7 +3677,7 @@ retry:
 		barrier();
 		if (pmd_trans_huge(orig_pmd)) {
 			if (pmd_numa(*pmd))
-				return do_huge_pmd_numa_page(mm, address,
+				return do_huge_pmd_numa_page(mm, vma, address,
 							     orig_pmd, pmd);
 
 			if ((flags & FAULT_FLAG_WRITE) && !pmd_write(orig_pmd)) {
-- 
cgit v1.2.3-55-g7522


From b24f53a0bea38b266d219ee651b22dba727c44ae Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn
Date: Thu, 25 Oct 2012 14:16:32 +0200
Subject: mm: mempolicy: Add MPOL_MF_LAZY

NOTE: Once again there is a lot of patch stealing and the end result
	is sufficiently different that I had to drop the signed-offs.
	Will re-add if the original authors are ok with that.

This patch adds another mbind() flag to request "lazy migration".  The
flag, MPOL_MF_LAZY, modifies MPOL_MF_MOVE* such that the selected
pages are marked PROT_NONE. The pages will be migrated in the fault
path on "first touch", if the policy dictates at that time.

"Lazy Migration" will allow testing of migrate-on-fault via mbind().
Also allows applications to specify that only subsequently touched
pages be migrated to obey new policy, instead of all pages in range.
This can be useful for multi-threaded applications working on a
large shared data area that is initialized by an initial thread
resulting in all pages on one [or a few, if overflowed] nodes.
After PROT_NONE, the pages in regions assigned to the worker threads
will be automatically migrated local to the threads on 1st touch.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
 include/linux/mm.h             |   5 ++
 include/uapi/linux/mempolicy.h |  13 ++-
 mm/mempolicy.c                 | 185 +++++++++++++++++++++++++++++++++++++----
 3 files changed, 185 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index fa1615211159..471185e29bab 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1551,6 +1551,11 @@ static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
 }
 #endif
 
+#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
+void change_prot_numa(struct vm_area_struct *vma,
+			unsigned long start, unsigned long end);
+#endif
+
 struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr);
 int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 			unsigned long pfn, unsigned long size, pgprot_t);
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 472de8a5d37e..6a1baae3775d 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -49,9 +49,16 @@ enum mpol_rebind_step {
 
 /* Flags for mbind */
 #define MPOL_MF_STRICT	(1<<0)	/* Verify existing pages in the mapping */
-#define MPOL_MF_MOVE	(1<<1)	/* Move pages owned by this process to conform to mapping */
-#define MPOL_MF_MOVE_ALL (1<<2)	/* Move every page to conform to mapping */
-#define MPOL_MF_INTERNAL (1<<3)	/* Internal flags start here */
+#define MPOL_MF_MOVE	 (1<<1)	/* Move pages owned by this process to conform
+				   to policy */
+#define MPOL_MF_MOVE_ALL (1<<2)	/* Move every page to conform to policy */
+#define MPOL_MF_LAZY	 (1<<3)	/* Modifies '_MOVE:  lazy migrate on fault */
+#define MPOL_MF_INTERNAL (1<<4)	/* Internal flags start here */
+
+#define MPOL_MF_VALID	(MPOL_MF_STRICT   | 	\
+			 MPOL_MF_MOVE     | 	\
+			 MPOL_MF_MOVE_ALL |	\
+			 MPOL_MF_LAZY)
 
 /*
  * Internal flags that share the struct mempolicy flags word with
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index df1466d3d2d8..51d3ebd8561e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -90,6 +90,7 @@
 #include <linux/syscalls.h>
 #include <linux/ctype.h>
 #include <linux/mm_inline.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
@@ -565,6 +566,145 @@ static inline int check_pgd_range(struct vm_area_struct *vma,
 	return 0;
 }
 
+#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
+/*
+ * Here we search for not shared page mappings (mapcount == 1) and we
+ * set up the pmd/pte_numa on those mappings so the very next access
+ * will fire a NUMA hinting page fault.
+ */
+static int
+change_prot_numa_range(struct mm_struct *mm, struct vm_area_struct *vma,
+			unsigned long address)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte, *_pte;
+	struct page *page;
+	unsigned long _address, end;
+	spinlock_t *ptl;
+	int ret = 0;
+
+	VM_BUG_ON(address & ~PAGE_MASK);
+
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
+		goto out;
+
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		goto out;
+
+	pmd = pmd_offset(pud, address);
+	if (pmd_none(*pmd))
+		goto out;
+
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		int page_nid;
+		ret = HPAGE_PMD_NR;
+
+		VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+
+		if (pmd_numa(*pmd)) {
+			spin_unlock(&mm->page_table_lock);
+			goto out;
+		}
+
+		page = pmd_page(*pmd);
+
+		/* only check non-shared pages */
+		if (page_mapcount(page) != 1) {
+			spin_unlock(&mm->page_table_lock);
+			goto out;
+		}
+
+		page_nid = page_to_nid(page);
+
+		if (pmd_numa(*pmd)) {
+			spin_unlock(&mm->page_table_lock);
+			goto out;
+		}
+
+		set_pmd_at(mm, address, pmd, pmd_mknuma(*pmd));
+		ret += HPAGE_PMD_NR;
+		/* defer TLB flush to lower the overhead */
+		spin_unlock(&mm->page_table_lock);
+		goto out;
+	}
+
+	if (pmd_trans_unstable(pmd))
+		goto out;
+	VM_BUG_ON(!pmd_present(*pmd));
+
+	end = min(vma->vm_end, (address + PMD_SIZE) & PMD_MASK);
+	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
+	for (_address = address, _pte = pte; _address < end;
+	     _pte++, _address += PAGE_SIZE) {
+		pte_t pteval = *_pte;
+		if (!pte_present(pteval))
+			continue;
+		if (pte_numa(pteval))
+			continue;
+		page = vm_normal_page(vma, _address, pteval);
+		if (unlikely(!page))
+			continue;
+		/* only check non-shared pages */
+		if (page_mapcount(page) != 1)
+			continue;
+
+		set_pte_at(mm, _address, _pte, pte_mknuma(pteval));
+
+		/* defer TLB flush to lower the overhead */
+		ret++;
+	}
+	pte_unmap_unlock(pte, ptl);
+
+	if (ret && !pmd_numa(*pmd)) {
+		spin_lock(&mm->page_table_lock);
+		set_pmd_at(mm, address, pmd, pmd_mknuma(*pmd));
+		spin_unlock(&mm->page_table_lock);
+		/* defer TLB flush to lower the overhead */
+	}
+
+out:
+	return ret;
+}
+
+/* Assumes mmap_sem is held */
+void
+change_prot_numa(struct vm_area_struct *vma,
+			unsigned long address, unsigned long end)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	int progress = 0;
+
+	while (address < end) {
+		VM_BUG_ON(address < vma->vm_start ||
+			  address + PAGE_SIZE > vma->vm_end);
+
+		progress += change_prot_numa_range(mm, vma, address);
+		address = (address + PMD_SIZE) & PMD_MASK;
+	}
+
+	/*
+	 * Flush the TLB for the mm to start the NUMA hinting
+	 * page faults after we finish scanning this vma part
+	 * if there were any PTE updates
+	 */
+	if (progress) {
+		mmu_notifier_invalidate_range_start(vma->vm_mm, address, end);
+		flush_tlb_range(vma, address, end);
+		mmu_notifier_invalidate_range_end(vma->vm_mm, address, end);
+	}
+}
+#else
+static unsigned long change_prot_numa(struct vm_area_struct *vma,
+			unsigned long addr, unsigned long end)
+{
+	return 0;
+}
+#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
+
 /*
  * Check if all pages in a range are on a set of nodes.
  * If pagelist != NULL then isolate pages from the LRU and
@@ -583,22 +723,32 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 		return ERR_PTR(-EFAULT);
 	prev = NULL;
 	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
+		unsigned long endvma = vma->vm_end;
+
+		if (endvma > end)
+			endvma = end;
+		if (vma->vm_start > start)
+			start = vma->vm_start;
+
 		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
 			if (!vma->vm_next && vma->vm_end < end)
 				return ERR_PTR(-EFAULT);
 			if (prev && prev->vm_end < vma->vm_start)
 				return ERR_PTR(-EFAULT);
 		}
-		if (!is_vm_hugetlb_page(vma) &&
-		    ((flags & MPOL_MF_STRICT) ||
+
+		if (is_vm_hugetlb_page(vma))
+			goto next;
+
+		if (flags & MPOL_MF_LAZY) {
+			change_prot_numa(vma, start, endvma);
+			goto next;
+		}
+
+		if ((flags & MPOL_MF_STRICT) ||
 		     ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
-				vma_migratable(vma)))) {
-			unsigned long endvma = vma->vm_end;
+		      vma_migratable(vma))) {
 
-			if (endvma > end)
-				endvma = end;
-			if (vma->vm_start > start)
-				start = vma->vm_start;
 			err = check_pgd_range(vma, start, endvma, nodes,
 						flags, private);
 			if (err) {
@@ -606,6 +756,7 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 				break;
 			}
 		}
+next:
 		prev = vma;
 	}
 	return first;
@@ -1138,8 +1289,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 	int err;
 	LIST_HEAD(pagelist);
 
-	if (flags & ~(unsigned long)(MPOL_MF_STRICT |
-				     MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+	if (flags & ~(unsigned long)MPOL_MF_VALID)
 		return -EINVAL;
 	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
 		return -EPERM;
@@ -1162,6 +1312,9 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 
+	if (flags & MPOL_MF_LAZY)
+		new->flags |= MPOL_F_MOF;
+
 	/*
 	 * If we are using the default policy then operation
 	 * on discontinuous address spaces is okay after all
@@ -1198,13 +1351,15 @@ static long do_mbind(unsigned long start, unsigned long len,
 	vma = check_range(mm, start, end, nmask,
 			  flags | MPOL_MF_INVERT, &pagelist);
 
-	err = PTR_ERR(vma);
-	if (!IS_ERR(vma)) {
-		int nr_failed = 0;
-
+	err = PTR_ERR(vma);	/* maybe ... */
+	if (!IS_ERR(vma) && mode != MPOL_NOOP)
 		err = mbind_range(mm, start, end, new);
 
+	if (!err) {
+		int nr_failed = 0;
+
 		if (!list_empty(&pagelist)) {
+			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
 			nr_failed = migrate_pages(&pagelist, new_vma_page,
 						(unsigned long)vma,
 						false, MIGRATE_SYNC,
@@ -1213,7 +1368,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 				putback_lru_pages(&pagelist);
 		}
 
-		if (!err && nr_failed && (flags & MPOL_MF_STRICT))
+		if (nr_failed && (flags & MPOL_MF_STRICT))
 			err = -EIO;
 	} else
 		putback_lru_pages(&pagelist);
-- 
cgit v1.2.3-55-g7522


From 4b10e7d562c90d0a72f324832c26653947a07381 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Thu, 25 Oct 2012 14:16:32 +0200
Subject: mm: mempolicy: Implement change_prot_numa() in terms of
 change_protection()

This patch converts change_prot_numa() to use change_protection(). As
pte_numa and friends check the PTE bits directly it is necessary for
change_protection() to use pmd_mknuma(). Hence the required
modifications to change_protection() are a little clumsy but the
end result is that most of the numa page table helpers are just one or
two instructions.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/huge_mm.h |   3 +-
 include/linux/mm.h      |   4 +-
 mm/huge_memory.c        |  14 ++++-
 mm/mempolicy.c          | 137 +++++-------------------------------------------
 mm/mprotect.c           |  72 +++++++++++++++++++------
 5 files changed, 85 insertions(+), 145 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index dabb5108d6c0..027ad04ef3a8 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -27,7 +27,8 @@ extern int move_huge_pmd(struct vm_area_struct *vma,
 			 unsigned long new_addr, unsigned long old_end,
 			 pmd_t *old_pmd, pmd_t *new_pmd);
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-			unsigned long addr, pgprot_t newprot);
+			unsigned long addr, pgprot_t newprot,
+			int prot_numa);
 
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 471185e29bab..d04c2f0aab36 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1080,7 +1080,7 @@ extern unsigned long do_mremap(unsigned long addr,
 			       unsigned long flags, unsigned long new_addr);
 extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 			      unsigned long end, pgprot_t newprot,
-			      int dirty_accountable);
+			      int dirty_accountable, int prot_numa);
 extern int mprotect_fixup(struct vm_area_struct *vma,
 			  struct vm_area_struct **pprev, unsigned long start,
 			  unsigned long end, unsigned long newflags);
@@ -1552,7 +1552,7 @@ static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
 #endif
 
 #ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
-void change_prot_numa(struct vm_area_struct *vma,
+unsigned long change_prot_numa(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end);
 #endif
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5723b551c023..d79f7a55bf6f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1147,7 +1147,7 @@ out:
 }
 
 int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, pgprot_t newprot)
+		unsigned long addr, pgprot_t newprot, int prot_numa)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	int ret = 0;
@@ -1155,7 +1155,17 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
 		pmd_t entry;
 		entry = pmdp_get_and_clear(mm, addr, pmd);
-		entry = pmd_modify(entry, newprot);
+		if (!prot_numa)
+			entry = pmd_modify(entry, newprot);
+		else {
+			struct page *page = pmd_page(*pmd);
+
+			/* only check non-shared pages */
+			if (page_mapcount(page) == 1 &&
+			    !pmd_numa(*pmd)) {
+				entry = pmd_mknuma(entry);
+			}
+		}
 		set_pmd_at(mm, addr, pmd, entry);
 		spin_unlock(&vma->vm_mm->page_table_lock);
 		ret = 1;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 51d3ebd8561e..75d4600a5e92 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -568,134 +568,23 @@ static inline int check_pgd_range(struct vm_area_struct *vma,
 
 #ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
 /*
- * Here we search for not shared page mappings (mapcount == 1) and we
- * set up the pmd/pte_numa on those mappings so the very next access
- * will fire a NUMA hinting page fault.
+ * This is used to mark a range of virtual addresses to be inaccessible.
+ * These are later cleared by a NUMA hinting fault. Depending on these
+ * faults, pages may be migrated for better NUMA placement.
+ *
+ * This is assuming that NUMA faults are handled using PROT_NONE. If
+ * an architecture makes a different choice, it will need further
+ * changes to the core.
  */
-static int
-change_prot_numa_range(struct mm_struct *mm, struct vm_area_struct *vma,
-			unsigned long address)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte, *_pte;
-	struct page *page;
-	unsigned long _address, end;
-	spinlock_t *ptl;
-	int ret = 0;
-
-	VM_BUG_ON(address & ~PAGE_MASK);
-
-	pgd = pgd_offset(mm, address);
-	if (!pgd_present(*pgd))
-		goto out;
-
-	pud = pud_offset(pgd, address);
-	if (!pud_present(*pud))
-		goto out;
-
-	pmd = pmd_offset(pud, address);
-	if (pmd_none(*pmd))
-		goto out;
-
-	if (pmd_trans_huge_lock(pmd, vma) == 1) {
-		int page_nid;
-		ret = HPAGE_PMD_NR;
-
-		VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-
-		if (pmd_numa(*pmd)) {
-			spin_unlock(&mm->page_table_lock);
-			goto out;
-		}
-
-		page = pmd_page(*pmd);
-
-		/* only check non-shared pages */
-		if (page_mapcount(page) != 1) {
-			spin_unlock(&mm->page_table_lock);
-			goto out;
-		}
-
-		page_nid = page_to_nid(page);
-
-		if (pmd_numa(*pmd)) {
-			spin_unlock(&mm->page_table_lock);
-			goto out;
-		}
-
-		set_pmd_at(mm, address, pmd, pmd_mknuma(*pmd));
-		ret += HPAGE_PMD_NR;
-		/* defer TLB flush to lower the overhead */
-		spin_unlock(&mm->page_table_lock);
-		goto out;
-	}
-
-	if (pmd_trans_unstable(pmd))
-		goto out;
-	VM_BUG_ON(!pmd_present(*pmd));
-
-	end = min(vma->vm_end, (address + PMD_SIZE) & PMD_MASK);
-	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
-	for (_address = address, _pte = pte; _address < end;
-	     _pte++, _address += PAGE_SIZE) {
-		pte_t pteval = *_pte;
-		if (!pte_present(pteval))
-			continue;
-		if (pte_numa(pteval))
-			continue;
-		page = vm_normal_page(vma, _address, pteval);
-		if (unlikely(!page))
-			continue;
-		/* only check non-shared pages */
-		if (page_mapcount(page) != 1)
-			continue;
-
-		set_pte_at(mm, _address, _pte, pte_mknuma(pteval));
-
-		/* defer TLB flush to lower the overhead */
-		ret++;
-	}
-	pte_unmap_unlock(pte, ptl);
-
-	if (ret && !pmd_numa(*pmd)) {
-		spin_lock(&mm->page_table_lock);
-		set_pmd_at(mm, address, pmd, pmd_mknuma(*pmd));
-		spin_unlock(&mm->page_table_lock);
-		/* defer TLB flush to lower the overhead */
-	}
-
-out:
-	return ret;
-}
-
-/* Assumes mmap_sem is held */
-void
-change_prot_numa(struct vm_area_struct *vma,
-			unsigned long address, unsigned long end)
+unsigned long change_prot_numa(struct vm_area_struct *vma,
+			unsigned long addr, unsigned long end)
 {
-	struct mm_struct *mm = vma->vm_mm;
-	int progress = 0;
-
-	while (address < end) {
-		VM_BUG_ON(address < vma->vm_start ||
-			  address + PAGE_SIZE > vma->vm_end);
+	int nr_updated;
+	BUILD_BUG_ON(_PAGE_NUMA != _PAGE_PROTNONE);
 
-		progress += change_prot_numa_range(mm, vma, address);
-		address = (address + PMD_SIZE) & PMD_MASK;
-	}
+	nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1);
 
-	/*
-	 * Flush the TLB for the mm to start the NUMA hinting
-	 * page faults after we finish scanning this vma part
-	 * if there were any PTE updates
-	 */
-	if (progress) {
-		mmu_notifier_invalidate_range_start(vma->vm_mm, address, end);
-		flush_tlb_range(vma, address, end);
-		mmu_notifier_invalidate_range_end(vma->vm_mm, address, end);
-	}
+	return nr_updated;
 }
 #else
 static unsigned long change_prot_numa(struct vm_area_struct *vma,
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 7c3628a8b486..7ef6ae964e8f 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -35,10 +35,11 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 }
 #endif
 
-static unsigned long change_pte_range(struct mm_struct *mm, pmd_t *pmd,
+static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable)
+		int dirty_accountable, int prot_numa)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
 	unsigned long pages = 0;
@@ -49,19 +50,39 @@ static unsigned long change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 		oldpte = *pte;
 		if (pte_present(oldpte)) {
 			pte_t ptent;
+			bool updated = false;
 
 			ptent = ptep_modify_prot_start(mm, addr, pte);
-			ptent = pte_modify(ptent, newprot);
+			if (!prot_numa) {
+				ptent = pte_modify(ptent, newprot);
+				updated = true;
+			} else {
+				struct page *page;
+
+				page = vm_normal_page(vma, addr, oldpte);
+				if (page) {
+					/* only check non-shared pages */
+					if (!pte_numa(oldpte) &&
+					    page_mapcount(page) == 1) {
+						ptent = pte_mknuma(ptent);
+						updated = true;
+					}
+				}
+			}
 
 			/*
 			 * Avoid taking write faults for pages we know to be
 			 * dirty.
 			 */
-			if (dirty_accountable && pte_dirty(ptent))
+			if (dirty_accountable && pte_dirty(ptent)) {
 				ptent = pte_mkwrite(ptent);
+				updated = true;
+			}
+
+			if (updated)
+				pages++;
 
 			ptep_modify_prot_commit(mm, addr, pte, ptent);
-			pages++;
 		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
@@ -83,9 +104,25 @@ static unsigned long change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	return pages;
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
+		pmd_t *pmd)
+{
+	spin_lock(&mm->page_table_lock);
+	set_pmd_at(mm, addr & PMD_MASK, pmd, pmd_mknuma(*pmd));
+	spin_unlock(&mm->page_table_lock);
+}
+#else
+static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
+		pmd_t *pmd)
+{
+	BUG();
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable)
+		int dirty_accountable, int prot_numa)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -97,7 +134,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
 				split_huge_page_pmd(vma->vm_mm, pmd);
-			else if (change_huge_pmd(vma, pmd, addr, newprot)) {
+			else if (change_huge_pmd(vma, pmd, addr, newprot, prot_numa)) {
 				pages += HPAGE_PMD_NR;
 				continue;
 			}
@@ -105,8 +142,11 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *
 		}
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		pages += change_pte_range(vma->vm_mm, pmd, addr, next, newprot,
-				 dirty_accountable);
+		pages += change_pte_range(vma, pmd, addr, next, newprot,
+				 dirty_accountable, prot_numa);
+
+		if (prot_numa)
+			change_pmd_protnuma(vma->vm_mm, addr, pmd);
 	} while (pmd++, addr = next, addr != end);
 
 	return pages;
@@ -114,7 +154,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *
 
 static inline unsigned long change_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable)
+		int dirty_accountable, int prot_numa)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -126,7 +166,7 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma, pgd_t *
 		if (pud_none_or_clear_bad(pud))
 			continue;
 		pages += change_pmd_range(vma, pud, addr, next, newprot,
-				 dirty_accountable);
+				 dirty_accountable, prot_numa);
 	} while (pud++, addr = next, addr != end);
 
 	return pages;
@@ -134,7 +174,7 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma, pgd_t *
 
 static unsigned long change_protection_range(struct vm_area_struct *vma,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable)
+		int dirty_accountable, int prot_numa)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
@@ -150,7 +190,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
 		pages += change_pud_range(vma, pgd, addr, next, newprot,
-				 dirty_accountable);
+				 dirty_accountable, prot_numa);
 	} while (pgd++, addr = next, addr != end);
 
 	/* Only flush the TLB if we actually modified any entries: */
@@ -162,7 +202,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 
 unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 		       unsigned long end, pgprot_t newprot,
-		       int dirty_accountable)
+		       int dirty_accountable, int prot_numa)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long pages;
@@ -171,7 +211,7 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 	if (is_vm_hugetlb_page(vma))
 		pages = hugetlb_change_protection(vma, start, end, newprot);
 	else
-		pages = change_protection_range(vma, start, end, newprot, dirty_accountable);
+		pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
 	mmu_notifier_invalidate_range_end(mm, start, end);
 
 	return pages;
@@ -249,7 +289,7 @@ success:
 		dirty_accountable = 1;
 	}
 
-	change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
+	change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable, 0);
 
 	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
 	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
-- 
cgit v1.2.3-55-g7522


From a720094ded8cbb303111035be91858011d2eac71 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Fri, 16 Nov 2012 09:37:58 +0000
Subject: mm: mempolicy: Hide MPOL_NOOP and MPOL_MF_LAZY from userspace for now

The use of MPOL_NOOP and MPOL_MF_LAZY to allow an application to
explicitly request lazy migration is a good idea but the actual
API has not been well reviewed and once released we have to support it.
For now this patch prevents an application using the services. This
will need to be revisited.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/uapi/linux/mempolicy.h | 4 +---
 mm/mempolicy.c                 | 9 ++++-----
 2 files changed, 5 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 6a1baae3775d..16fb4e6efbc4 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -21,7 +21,6 @@ enum {
 	MPOL_BIND,
 	MPOL_INTERLEAVE,
 	MPOL_LOCAL,
-	MPOL_NOOP,		/* retain existing policy for range */
 	MPOL_MAX,	/* always last member of enum */
 };
 
@@ -57,8 +56,7 @@ enum mpol_rebind_step {
 
 #define MPOL_MF_VALID	(MPOL_MF_STRICT   | 	\
 			 MPOL_MF_MOVE     | 	\
-			 MPOL_MF_MOVE_ALL |	\
-			 MPOL_MF_LAZY)
+			 MPOL_MF_MOVE_ALL)
 
 /*
  * Internal flags that share the struct mempolicy flags word with
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 75d4600a5e92..a7a62fe7c280 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -252,7 +252,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 	pr_debug("setting mode %d flags %d nodes[0] %lx\n",
 		 mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
 
-	if (mode == MPOL_DEFAULT || mode == MPOL_NOOP) {
+	if (mode == MPOL_DEFAULT) {
 		if (nodes && !nodes_empty(*nodes))
 			return ERR_PTR(-EINVAL);
 		return NULL;
@@ -1186,7 +1186,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (start & ~PAGE_MASK)
 		return -EINVAL;
 
-	if (mode == MPOL_DEFAULT || mode == MPOL_NOOP)
+	if (mode == MPOL_DEFAULT)
 		flags &= ~MPOL_MF_STRICT;
 
 	len = (len + PAGE_SIZE - 1) & PAGE_MASK;
@@ -1241,7 +1241,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 			  flags | MPOL_MF_INVERT, &pagelist);
 
 	err = PTR_ERR(vma);	/* maybe ... */
-	if (!IS_ERR(vma) && mode != MPOL_NOOP)
+	if (!IS_ERR(vma))
 		err = mbind_range(mm, start, end, new);
 
 	if (!err) {
@@ -2530,7 +2530,6 @@ static const char * const policy_modes[] =
 	[MPOL_BIND]       = "bind",
 	[MPOL_INTERLEAVE] = "interleave",
 	[MPOL_LOCAL]      = "local",
-	[MPOL_NOOP]	  = "noop",	/* should not actually be used */
 };
 
 
@@ -2581,7 +2580,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
 			break;
 		}
 	}
-	if (mode >= MPOL_MAX || mode == MPOL_NOOP)
+	if (mode >= MPOL_MAX)
 		goto out;
 
 	switch (mode) {
-- 
cgit v1.2.3-55-g7522


From cbee9f88ec1b8dd6b58f25f54e4f52c82ed77690 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra
Date: Thu, 25 Oct 2012 14:16:43 +0200
Subject: mm: numa: Add fault driven placement and migration

NOTE: This patch is based on "sched, numa, mm: Add fault driven
	placement and migration policy" but as it throws away all the policy
	to just leave a basic foundation I had to drop the signed-offs-by.

This patch creates a bare-bones method for setting PTEs pte_numa in the
context of the scheduler that when faulted later will be faulted onto the
node the CPU is running on.  In itself this does nothing useful but any
placement policy will fundamentally depend on receiving hints on placement
from fault context and doing something intelligent about it.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
---
 arch/sh/mm/Kconfig       |   1 +
 arch/x86/Kconfig         |   2 +
 include/linux/mm_types.h |  11 +++++
 include/linux/sched.h    |  20 ++++++++
 kernel/sched/core.c      |  13 +++++
 kernel/sched/fair.c      | 125 +++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/features.h  |   7 +++
 kernel/sched/sched.h     |   6 +++
 kernel/sysctl.c          |  24 ++++++++-
 mm/huge_memory.c         |   5 +-
 mm/memory.c              |  14 +++++-
 11 files changed, 224 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig
index cb8f9920f4dd..0f7c852f355c 100644
--- a/arch/sh/mm/Kconfig
+++ b/arch/sh/mm/Kconfig
@@ -111,6 +111,7 @@ config VSYSCALL
 config NUMA
 	bool "Non Uniform Memory Access (NUMA) Support"
 	depends on MMU && SYS_SUPPORTS_NUMA && EXPERIMENTAL
+	select ARCH_WANT_NUMA_VARIABLE_LOCALITY
 	default n
 	help
 	  Some SH systems have many various memories scattered around
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 46c3bff3ced2..1137028fc6d9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -22,6 +22,8 @@ config X86
 	def_bool y
 	select HAVE_AOUT if X86_32
 	select HAVE_UNSTABLE_SCHED_CLOCK
+	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_PCSPKR_PLATFORM
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 31f8a3af7d94..ed8638c29b3e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -397,6 +397,17 @@ struct mm_struct {
 #endif
 #ifdef CONFIG_CPUMASK_OFFSTACK
 	struct cpumask cpumask_allocation;
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+	/*
+	 * numa_next_scan is the next time when the PTEs will me marked
+	 * pte_numa to gather statistics and migrate pages to new nodes
+	 * if necessary
+	 */
+	unsigned long numa_next_scan;
+
+	/* numa_scan_seq prevents two threads setting pte_numa */
+	int numa_scan_seq;
 #endif
 	struct uprobes_state uprobes_state;
 };
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a02df2e..844af5b12cb2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1479,6 +1479,14 @@ struct task_struct {
 	short il_next;
 	short pref_node_fork;
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	int numa_scan_seq;
+	int numa_migrate_seq;
+	unsigned int numa_scan_period;
+	u64 node_stamp;			/* migration stamp  */
+	struct callback_head numa_work;
+#endif /* CONFIG_NUMA_BALANCING */
+
 	struct rcu_head rcu;
 
 	/*
@@ -1553,6 +1561,14 @@ struct task_struct {
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
+#ifdef CONFIG_NUMA_BALANCING
+extern void task_numa_fault(int node, int pages);
+#else
+static inline void task_numa_fault(int node, int pages)
+{
+}
+#endif
+
 /*
  * Priority of a process goes from 0..MAX_PRIO-1, valid RT
  * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
@@ -1990,6 +2006,10 @@ enum sched_tunable_scaling {
 };
 extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 
+extern unsigned int sysctl_numa_balancing_scan_period_min;
+extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_settle_count;
+
 #ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d8927fda712..cad0d092ce3b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1533,6 +1533,19 @@ static void __sched_fork(struct task_struct *p)
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
+
+#ifdef CONFIG_NUMA_BALANCING
+	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
+		p->mm->numa_next_scan = jiffies;
+		p->mm->numa_scan_seq = 0;
+	}
+
+	p->node_stamp = 0ULL;
+	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
+	p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
+	p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+	p->numa_work.next = &p->numa_work;
+#endif /* CONFIG_NUMA_BALANCING */
 }
 
 /*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6b800a14b990..6831abb5dbef 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -26,6 +26,8 @@
 #include <linux/slab.h>
 #include <linux/profile.h>
 #include <linux/interrupt.h>
+#include <linux/mempolicy.h>
+#include <linux/task_work.h>
 
 #include <trace/events/sched.h>
 
@@ -776,6 +778,126 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * numa task sample period in ms: 5s
+ */
+unsigned int sysctl_numa_balancing_scan_period_min = 5000;
+unsigned int sysctl_numa_balancing_scan_period_max = 5000*16;
+
+static void task_numa_placement(struct task_struct *p)
+{
+	int seq = ACCESS_ONCE(p->mm->numa_scan_seq);
+
+	if (p->numa_scan_seq == seq)
+		return;
+	p->numa_scan_seq = seq;
+
+	/* FIXME: Scheduling placement policy hints go here */
+}
+
+/*
+ * Got a PROT_NONE fault for a page on @node.
+ */
+void task_numa_fault(int node, int pages)
+{
+	struct task_struct *p = current;
+
+	/* FIXME: Allocate task-specific structure for placement policy here */
+
+	task_numa_placement(p);
+}
+
+/*
+ * The expensive part of numa migration is done from task_work context.
+ * Triggered from task_tick_numa().
+ */
+void task_numa_work(struct callback_head *work)
+{
+	unsigned long migrate, next_scan, now = jiffies;
+	struct task_struct *p = current;
+	struct mm_struct *mm = p->mm;
+
+	WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
+
+	work->next = work; /* protect against double add */
+	/*
+	 * Who cares about NUMA placement when they're dying.
+	 *
+	 * NOTE: make sure not to dereference p->mm before this check,
+	 * exit_task_work() happens _after_ exit_mm() so we could be called
+	 * without p->mm even though we still had it when we enqueued this
+	 * work.
+	 */
+	if (p->flags & PF_EXITING)
+		return;
+
+	/*
+	 * Enforce maximal scan/migration frequency..
+	 */
+	migrate = mm->numa_next_scan;
+	if (time_before(now, migrate))
+		return;
+
+	if (p->numa_scan_period == 0)
+		p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+
+	next_scan = now + 2*msecs_to_jiffies(p->numa_scan_period);
+	if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
+		return;
+
+	ACCESS_ONCE(mm->numa_scan_seq)++;
+	{
+		struct vm_area_struct *vma;
+
+		down_read(&mm->mmap_sem);
+		for (vma = mm->mmap; vma; vma = vma->vm_next) {
+			if (!vma_migratable(vma))
+				continue;
+			change_prot_numa(vma, vma->vm_start, vma->vm_end);
+		}
+		up_read(&mm->mmap_sem);
+	}
+}
+
+/*
+ * Drive the periodic memory faults..
+ */
+void task_tick_numa(struct rq *rq, struct task_struct *curr)
+{
+	struct callback_head *work = &curr->numa_work;
+	u64 period, now;
+
+	/*
+	 * We don't care about NUMA placement if we don't have memory.
+	 */
+	if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
+		return;
+
+	/*
+	 * Using runtime rather than walltime has the dual advantage that
+	 * we (mostly) drive the selection from busy threads and that the
+	 * task needs to have done some actual work before we bother with
+	 * NUMA placement.
+	 */
+	now = curr->se.sum_exec_runtime;
+	period = (u64)curr->numa_scan_period * NSEC_PER_MSEC;
+
+	if (now - curr->node_stamp > period) {
+		curr->node_stamp = now;
+
+		if (!time_before(jiffies, curr->mm->numa_next_scan)) {
+			init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */
+			task_work_add(curr, work, true);
+		}
+	}
+}
+#else
+static void task_tick_numa(struct rq *rq, struct task_struct *curr)
+{
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 static void
 account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -4954,6 +5076,9 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 		cfs_rq = cfs_rq_of(se);
 		entity_tick(cfs_rq, se, queued);
 	}
+
+	if (sched_feat_numa(NUMA))
+		task_tick_numa(rq, curr);
 }
 
 /*
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index eebefcad7027..5fb7aefbec80 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -61,3 +61,10 @@ SCHED_FEAT(TTWU_QUEUE, true)
 SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
+
+/*
+ * Apply the automatic NUMA scheduling policy
+ */
+#ifdef CONFIG_NUMA_BALANCING
+SCHED_FEAT(NUMA,	true)
+#endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7a7db09cfabc..ae31c051ff2f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -648,6 +648,12 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
 #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
 #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
 
+#ifdef CONFIG_NUMA_BALANCING
+#define sched_feat_numa(x) sched_feat(x)
+#else
+#define sched_feat_numa(x) (0)
+#endif
+
 static inline u64 global_rt_period(void)
 {
 	return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 26f65eaa01f9..025e1ae50ef1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -256,9 +256,11 @@ static int min_sched_granularity_ns = 100000;		/* 100 usecs */
 static int max_sched_granularity_ns = NSEC_PER_SEC;	/* 1 second */
 static int min_wakeup_granularity_ns;			/* 0 usecs */
 static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
+#ifdef CONFIG_SMP
 static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
 static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
-#endif
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_SCHED_DEBUG */
 
 #ifdef CONFIG_COMPACTION
 static int min_extfrag_threshold;
@@ -301,6 +303,7 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &min_wakeup_granularity_ns,
 		.extra2		= &max_wakeup_granularity_ns,
 	},
+#ifdef CONFIG_SMP
 	{
 		.procname	= "sched_tunable_scaling",
 		.data		= &sysctl_sched_tunable_scaling,
@@ -347,7 +350,24 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
-#endif
+#endif /* CONFIG_SMP */
+#ifdef CONFIG_NUMA_BALANCING
+	{
+		.procname	= "numa_balancing_scan_period_min_ms",
+		.data		= &sysctl_numa_balancing_scan_period_min,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "numa_balancing_scan_period_max_ms",
+		.data		= &sysctl_numa_balancing_scan_period_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#endif /* CONFIG_NUMA_BALANCING */
+#endif /* CONFIG_SCHED_DEBUG */
 	{
 		.procname	= "sched_rt_period_us",
 		.data		= &sysctl_sched_rt_period,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d79f7a55bf6f..ee8133794a56 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1046,6 +1046,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	split_huge_page(page);
 	put_page(page);
+
 	return 0;
 
 clear_pmdnuma:
@@ -1060,8 +1061,10 @@ clear_pmdnuma:
 
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
-	if (page)
+	if (page) {
 		put_page(page);
+		task_numa_fault(numa_node_id(), HPAGE_PMD_NR);
+	}
 	return 0;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index d52542680e10..8012c1907895 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3454,7 +3454,8 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
-	int current_nid, target_nid;
+	int current_nid = -1;
+	int target_nid;
 
 	/*
 	* The "pte" at this point cannot be used safely without
@@ -3501,6 +3502,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		current_nid = target_nid;
 
 out:
+	task_numa_fault(current_nid, 1);
 	return 0;
 }
 
@@ -3537,6 +3539,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
 		pte_t pteval = *pte;
 		struct page *page;
+		int curr_nid;
 		if (!pte_present(pteval))
 			continue;
 		if (!pte_numa(pteval))
@@ -3554,6 +3557,15 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		page = vm_normal_page(vma, addr, pteval);
 		if (unlikely(!page))
 			continue;
+		/* only check non-shared pages */
+		if (unlikely(page_mapcount(page) != 1))
+			continue;
+		pte_unmap_unlock(pte, ptl);
+
+		curr_nid = page_to_nid(page);
+		task_numa_fault(curr_nid, 1);
+
+		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
 	pte_unmap_unlock(orig_pte, ptl);
 
-- 
cgit v1.2.3-55-g7522


From 6e5fb223e89dbe5cb5c563f8d4a4a0a7d62455a8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra
Date: Thu, 25 Oct 2012 14:16:45 +0200
Subject: mm: sched: numa: Implement constant, per task Working Set Sampling
 (WSS) rate

Previously, to probe the working set of a task, we'd use
a very simple and crude method: mark all of its address
space PROT_NONE.

That method has various (obvious) disadvantages:

 - it samples the working set at dissimilar rates,
   giving some tasks a sampling quality advantage
   over others.

 - creates performance problems for tasks with very
   large working sets

 - over-samples processes with large address spaces but
   which only very rarely execute

Improve that method by keeping a rotating offset into the
address space that marks the current position of the scan,
and advance it by a constant rate (in a CPU cycles execution
proportional manner). If the offset reaches the last mapped
address of the mm then it then it starts over at the first
address.

The per-task nature of the working set sampling functionality in this tree
allows such constant rate, per task, execution-weight proportional sampling
of the working set, with an adaptive sampling interval/frequency that
goes from once per 100ms up to just once per 8 seconds.  The current
sampling volume is 256 MB per interval.

As tasks mature and converge their working set, so does the
sampling rate slow down to just a trickle, 256 MB per 8
seconds of CPU time executed.

This, beyond being adaptive, also rate-limits rarely
executing systems and does not over-sample on overloaded
systems.

[ In AutoNUMA speak, this patch deals with the effective sampling
  rate of the 'hinting page fault'. AutoNUMA's scanning is
  currently rate-limited, but it is also fundamentally
  single-threaded, executing in the knuma_scand kernel thread,
  so the limit in AutoNUMA is global and does not scale up with
  the number of CPUs, nor does it scan tasks in an execution
  proportional manner.

  So the idea of rate-limiting the scanning was first implemented
  in the AutoNUMA tree via a global rate limit. This patch goes
  beyond that by implementing an execution rate proportional
  working set sampling rate that is not implemented via a single
  global scanning daemon. ]

[ Dan Carpenter pointed out a possible NULL pointer dereference in the
  first version of this patch. ]

Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com>
Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
[ Wrote changelog and fixed bug. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
 include/linux/mm_types.h |  3 +++
 include/linux/sched.h    |  1 +
 kernel/sched/fair.c      | 65 ++++++++++++++++++++++++++++++++++++++----------
 kernel/sysctl.c          |  7 ++++++
 4 files changed, 63 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ed8638c29b3e..d1e246c5e50c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -406,6 +406,9 @@ struct mm_struct {
 	 */
 	unsigned long numa_next_scan;
 
+	/* Restart point for scanning and setting pte_numa */
+	unsigned long numa_scan_offset;
+
 	/* numa_scan_seq prevents two threads setting pte_numa */
 	int numa_scan_seq;
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 844af5b12cb2..37841958d234 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2008,6 +2008,7 @@ extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 
 extern unsigned int sysctl_numa_balancing_scan_period_min;
 extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_scan_size;
 extern unsigned int sysctl_numa_balancing_settle_count;
 
 #ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6831abb5dbef..0a349dd1fa60 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -780,10 +780,13 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 #ifdef CONFIG_NUMA_BALANCING
 /*
- * numa task sample period in ms: 5s
+ * numa task sample period in ms
  */
-unsigned int sysctl_numa_balancing_scan_period_min = 5000;
-unsigned int sysctl_numa_balancing_scan_period_max = 5000*16;
+unsigned int sysctl_numa_balancing_scan_period_min = 100;
+unsigned int sysctl_numa_balancing_scan_period_max = 100*16;
+
+/* Portion of address space to scan in MB */
+unsigned int sysctl_numa_balancing_scan_size = 256;
 
 static void task_numa_placement(struct task_struct *p)
 {
@@ -808,6 +811,12 @@ void task_numa_fault(int node, int pages)
 	task_numa_placement(p);
 }
 
+static void reset_ptenuma_scan(struct task_struct *p)
+{
+	ACCESS_ONCE(p->mm->numa_scan_seq)++;
+	p->mm->numa_scan_offset = 0;
+}
+
 /*
  * The expensive part of numa migration is done from task_work context.
  * Triggered from task_tick_numa().
@@ -817,6 +826,9 @@ void task_numa_work(struct callback_head *work)
 	unsigned long migrate, next_scan, now = jiffies;
 	struct task_struct *p = current;
 	struct mm_struct *mm = p->mm;
+	struct vm_area_struct *vma;
+	unsigned long offset, end;
+	long length;
 
 	WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
 
@@ -846,18 +858,45 @@ void task_numa_work(struct callback_head *work)
 	if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
 		return;
 
-	ACCESS_ONCE(mm->numa_scan_seq)++;
-	{
-		struct vm_area_struct *vma;
+	offset = mm->numa_scan_offset;
+	length = sysctl_numa_balancing_scan_size;
+	length <<= 20;
 
-		down_read(&mm->mmap_sem);
-		for (vma = mm->mmap; vma; vma = vma->vm_next) {
-			if (!vma_migratable(vma))
-				continue;
-			change_prot_numa(vma, vma->vm_start, vma->vm_end);
-		}
-		up_read(&mm->mmap_sem);
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, offset);
+	if (!vma) {
+		reset_ptenuma_scan(p);
+		offset = 0;
+		vma = mm->mmap;
+	}
+	for (; vma && length > 0; vma = vma->vm_next) {
+		if (!vma_migratable(vma))
+			continue;
+
+		/* Skip small VMAs. They are not likely to be of relevance */
+		if (((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) < HPAGE_PMD_NR)
+			continue;
+
+		offset = max(offset, vma->vm_start);
+		end = min(ALIGN(offset + length, HPAGE_SIZE), vma->vm_end);
+		length -= end - offset;
+
+		change_prot_numa(vma, offset, end);
+
+		offset = end;
 	}
+
+	/*
+	 * It is possible to reach the end of the VMA list but the last few VMAs are
+	 * not guaranteed to the vma_migratable. If they are not, we would find the
+	 * !migratable VMA on the next scan but not reset the scanner to the start
+	 * so check it now.
+	 */
+	if (vma)
+		mm->numa_scan_offset = offset;
+	else
+		reset_ptenuma_scan(p);
+	up_read(&mm->mmap_sem);
 }
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 025e1ae50ef1..7d3a2e0475e5 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -366,6 +366,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "numa_balancing_scan_size_mb",
+		.data		= &sysctl_numa_balancing_scan_size,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_SCHED_DEBUG */
 	{
-- 
cgit v1.2.3-55-g7522


From 4b96a29ba891dd59734cb7be80a900fe93aa2d9f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra
Date: Thu, 25 Oct 2012 14:16:47 +0200
Subject: mm: sched: numa: Implement slow start for working set sampling

Add a 1 second delay before starting to scan the working set of
a task and starting to balance it amongst nodes.

[ note that before the constant per task WSS sampling rate patch
  the initial scan would happen much later still, in effect that
  patch caused this regression. ]

The theory is that short-run tasks benefit very little from NUMA
placement: they come and go, and they better stick to the node
they were started on. As tasks mature and rebalance to other CPUs
and nodes, so does their NUMA placement have to change and so
does it start to matter more and more.

In practice this change fixes an observable kbuild regression:

   # [ a perf stat --null --repeat 10 test of ten bzImage builds to /dev/shm ]

   !NUMA:
   45.291088843 seconds time elapsed                                          ( +-  0.40% )
   45.154231752 seconds time elapsed                                          ( +-  0.36% )

   +NUMA, no slow start:
   46.172308123 seconds time elapsed                                          ( +-  0.30% )
   46.343168745 seconds time elapsed                                          ( +-  0.25% )

   +NUMA, 1 sec slow start:
   45.224189155 seconds time elapsed                                          ( +-  0.25% )
   45.160866532 seconds time elapsed                                          ( +-  0.17% )

and it also fixes an observable perf bench (hackbench) regression:

   # perf stat --null --repeat 10 perf bench sched messaging

   -NUMA:

   -NUMA:                  0.246225691 seconds time elapsed                   ( +-  1.31% )
   +NUMA no slow start:    0.252620063 seconds time elapsed                   ( +-  1.13% )

   +NUMA 1sec delay:       0.248076230 seconds time elapsed                   ( +-  1.35% )

The implementation is simple and straightforward, most of the patch
deals with adding the /proc/sys/kernel/numa_balancing_scan_delay_ms tunable
knob.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
[ Wrote the changelog, ran measurements, tuned the default. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
---
 include/linux/sched.h | 1 +
 kernel/sched/core.c   | 2 +-
 kernel/sched/fair.c   | 5 +++++
 kernel/sysctl.c       | 7 +++++++
 4 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 37841958d234..7d95a232b5b9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2006,6 +2006,7 @@ enum sched_tunable_scaling {
 };
 extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 
+extern unsigned int sysctl_numa_balancing_scan_delay;
 extern unsigned int sysctl_numa_balancing_scan_period_min;
 extern unsigned int sysctl_numa_balancing_scan_period_max;
 extern unsigned int sysctl_numa_balancing_scan_size;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cad0d092ce3b..fbfc4843063f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1543,7 +1543,7 @@ static void __sched_fork(struct task_struct *p)
 	p->node_stamp = 0ULL;
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
 	p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
-	p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
 #endif /* CONFIG_NUMA_BALANCING */
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f6e1f25ed2bd..7727b0161579 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -788,6 +788,9 @@ unsigned int sysctl_numa_balancing_scan_period_max = 100*16;
 /* Portion of address space to scan in MB */
 unsigned int sysctl_numa_balancing_scan_size = 256;
 
+/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
+unsigned int sysctl_numa_balancing_scan_delay = 1000;
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq = ACCESS_ONCE(p->mm->numa_scan_seq);
@@ -929,6 +932,8 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
 	period = (u64)curr->numa_scan_period * NSEC_PER_MSEC;
 
 	if (now - curr->node_stamp > period) {
+		if (!curr->node_stamp)
+			curr->numa_scan_period = sysctl_numa_balancing_scan_period_min;
 		curr->node_stamp = now;
 
 		if (!time_before(jiffies, curr->mm->numa_next_scan)) {
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7d3a2e0475e5..48a68cc258c1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -352,6 +352,13 @@ static struct ctl_table kern_table[] = {
 	},
 #endif /* CONFIG_SMP */
 #ifdef CONFIG_NUMA_BALANCING
+	{
+		.procname	= "numa_balancing_scan_delay_ms",
+		.data		= &sysctl_numa_balancing_scan_delay,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "numa_balancing_scan_period_min_ms",
 		.data		= &sysctl_numa_balancing_scan_period_min,
-- 
cgit v1.2.3-55-g7522


From 03c5a6e16322c997bf8f264851bfa3f532ad515f Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Fri, 2 Nov 2012 14:52:48 +0000
Subject: mm: numa: Add pte updates, hinting and migration stats

It is tricky to quantify the basic cost of automatic NUMA placement in a
meaningful manner. This patch adds some vmstats that can be used as part
of a basic costing model.

u    = basic unit = sizeof(void *)
Ca   = cost of struct page access = sizeof(struct page) / u
Cpte = Cost PTE access = Ca
Cupdate = Cost PTE update = (2 * Cpte) + (2 * Wlock)
	where Cpte is incurred twice for a read and a write and Wlock
	is a constant representing the cost of taking or releasing a
	lock
Cnumahint = Cost of a minor page fault = some high constant e.g. 1000
Cpagerw = Cost to read or write a full page = Ca + PAGE_SIZE/u
Ci = Cost of page isolation = Ca + Wi
	where Wi is a constant that should reflect the approximate cost
	of the locking operation
Cpagecopy = Cpagerw + (Cpagerw * Wnuma) + Ci + (Ci * Wnuma)
	where Wnuma is the approximate NUMA factor. 1 is local. 1.2
	would imply that remote accesses are 20% more expensive

Balancing cost = Cpte * numa_pte_updates +
		Cnumahint * numa_hint_faults +
		Ci * numa_pages_migrated +
		Cpagecopy * numa_pages_migrated

Note that numa_pages_migrated is used as a measure of how many pages
were isolated even though it would miss pages that failed to migrate. A
vmstat counter could have been added for it but the isolation cost is
pretty marginal in comparison to the overall cost so it seemed overkill.

The ideal way to measure automatic placement benefit would be to count
the number of remote accesses versus local accesses and do something like

	benefit = (remote_accesses_before - remove_access_after) * Wnuma

but the information is not readily available. As a workload converges, the
expection would be that the number of remote numa hints would reduce to 0.

	convergence = numa_hint_faults_local / numa_hint_faults
		where this is measured for the last N number of
		numa hints recorded. When the workload is fully
		converged the value is 1.

This can measure if the placement policy is converging and how fast it is
doing it.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
---
 include/linux/vm_event_item.h |  6 ++++++
 include/linux/vmstat.h        |  8 ++++++++
 mm/huge_memory.c              |  5 +++++
 mm/memory.c                   | 12 ++++++++++++
 mm/mempolicy.c                |  2 ++
 mm/migrate.c                  |  3 ++-
 mm/vmstat.c                   |  6 ++++++
 7 files changed, 41 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index a1f750b8e72a..55600049e794 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -38,6 +38,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
 		KSWAPD_SKIP_CONGESTION_WAIT,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+#ifdef CONFIG_NUMA_BALANCING
+		NUMA_PTE_UPDATES,
+		NUMA_HINT_FAULTS,
+		NUMA_HINT_FAULTS_LOCAL,
+		NUMA_PAGE_MIGRATE,
+#endif
 #ifdef CONFIG_MIGRATION
 		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
 #endif
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 92a86b2cce33..a13291f7da88 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -80,6 +80,14 @@ static inline void vm_events_fold_cpu(int cpu)
 
 #endif /* CONFIG_VM_EVENT_COUNTERS */
 
+#ifdef CONFIG_NUMA_BALANCING
+#define count_vm_numa_event(x)     count_vm_event(x)
+#define count_vm_numa_events(x, y) count_vm_events(x, y)
+#else
+#define count_vm_numa_event(x) do {} while (0)
+#define count_vm_numa_events(x, y) do {} while (0)
+#endif /* CONFIG_NUMA_BALANCING */
+
 #define __count_zone_vm_events(item, zone, delta) \
 		__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
 		zone_idx(zone), delta)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ee8133794a56..f3a477fffd09 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1026,6 +1026,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page = NULL;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
 	int target_nid;
+	int current_nid = -1;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
@@ -1034,6 +1035,10 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	page = pmd_page(pmd);
 	get_page(page);
 	spin_unlock(&mm->page_table_lock);
+	current_nid = page_to_nid(page);
+	count_vm_numa_event(NUMA_HINT_FAULTS);
+	if (current_nid == numa_node_id())
+		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
 	target_nid = mpol_misplaced(page, vma, haddr);
 	if (target_nid == -1)
diff --git a/mm/memory.c b/mm/memory.c
index 8012c1907895..8a7b4ccbe136 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3477,6 +3477,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	set_pte_at(mm, addr, ptep, pte);
 	update_mmu_cache(vma, addr, ptep);
 
+	count_vm_numa_event(NUMA_HINT_FAULTS);
 	page = vm_normal_page(vma, addr, pte);
 	if (!page) {
 		pte_unmap_unlock(ptep, ptl);
@@ -3485,6 +3486,8 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	get_page(page);
 	current_nid = page_to_nid(page);
+	if (current_nid == numa_node_id())
+		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 	target_nid = mpol_misplaced(page, vma, addr);
 	pte_unmap_unlock(ptep, ptl);
 	if (target_nid == -1) {
@@ -3517,6 +3520,9 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long offset;
 	spinlock_t *ptl;
 	bool numa = false;
+	int local_nid = numa_node_id();
+	unsigned long nr_faults = 0;
+	unsigned long nr_faults_local = 0;
 
 	spin_lock(&mm->page_table_lock);
 	pmd = *pmdp;
@@ -3565,10 +3571,16 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		curr_nid = page_to_nid(page);
 		task_numa_fault(curr_nid, 1);
 
+		nr_faults++;
+		if (curr_nid == local_nid)
+			nr_faults_local++;
+
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
 	pte_unmap_unlock(orig_pte, ptl);
 
+	count_vm_numa_events(NUMA_HINT_FAULTS, nr_faults);
+	count_vm_numa_events(NUMA_HINT_FAULTS_LOCAL, nr_faults_local);
 	return 0;
 }
 #else
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index a7a62fe7c280..516491fbfaa8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -583,6 +583,8 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
 	BUILD_BUG_ON(_PAGE_NUMA != _PAGE_PROTNONE);
 
 	nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1);
+	if (nr_updated)
+		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
 
 	return nr_updated;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index c7d550011a64..23bba5d6edff 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1514,7 +1514,8 @@ int migrate_misplaced_page(struct page *page, int node)
 		if (nr_remaining) {
 			putback_lru_pages(&migratepages);
 			isolated = 0;
-		}
+		} else
+			count_vm_numa_event(NUMA_PAGE_MIGRATE);
 	}
 	BUG_ON(!list_empty(&migratepages));
 out:
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 3a067fabe190..c0f1f6db5182 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -774,6 +774,12 @@ const char * const vmstat_text[] = {
 
 	"pgrotated",
 
+#ifdef CONFIG_NUMA_BALANCING
+	"numa_pte_updates",
+	"numa_hint_faults",
+	"numa_hint_faults_local",
+	"numa_pages_migrated",
+#endif
 #ifdef CONFIG_MIGRATION
 	"pgmigrate_success",
 	"pgmigrate_fail",
-- 
cgit v1.2.3-55-g7522


From 5606e3877ad8baea42f3a71ebde0a03622bbb551 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Fri, 2 Nov 2012 18:19:13 +0000
Subject: mm: numa: Migrate on reference policy

This is the simplest possible policy that still does something of note.
When a pte_numa is faulted, it is moved immediately. Any replacement
policy must at least do better than this and in all likelihood this
policy regresses normal workloads.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
---
 include/uapi/linux/mempolicy.h |  1 +
 mm/mempolicy.c                 | 38 ++++++++++++++++++++++++++++++++++++--
 2 files changed, 37 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 16fb4e6efbc4..0d11c3dcd3a1 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -67,6 +67,7 @@ enum mpol_rebind_step {
 #define MPOL_F_LOCAL   (1 << 1)	/* preferred local allocation */
 #define MPOL_F_REBINDING (1 << 2)	/* identify policies in rebinding */
 #define MPOL_F_MOF	(1 << 3) /* this policy wants migrate on fault */
+#define MPOL_F_MORON	(1 << 4) /* Migrate On pte_numa Reference On Node */
 
 
 #endif /* _UAPI_LINUX_MEMPOLICY_H */
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 516491fbfaa8..4c1c8d83ac6a 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -118,6 +118,26 @@ static struct mempolicy default_policy = {
 	.flags = MPOL_F_LOCAL,
 };
 
+static struct mempolicy preferred_node_policy[MAX_NUMNODES];
+
+static struct mempolicy *get_task_policy(struct task_struct *p)
+{
+	struct mempolicy *pol = p->mempolicy;
+	int node;
+
+	if (!pol) {
+		node = numa_node_id();
+		if (node != -1)
+			pol = &preferred_node_policy[node];
+
+		/* preferred_node_policy is not initialised early in boot */
+		if (!pol->mode)
+			pol = NULL;
+	}
+
+	return pol;
+}
+
 static const struct mempolicy_operations {
 	int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
 	/*
@@ -1598,7 +1618,7 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
 struct mempolicy *get_vma_policy(struct task_struct *task,
 		struct vm_area_struct *vma, unsigned long addr)
 {
-	struct mempolicy *pol = task->mempolicy;
+	struct mempolicy *pol = get_task_policy(task);
 
 	if (vma) {
 		if (vma->vm_ops && vma->vm_ops->get_policy) {
@@ -2021,7 +2041,7 @@ retry_cpuset:
  */
 struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
-	struct mempolicy *pol = current->mempolicy;
+	struct mempolicy *pol = get_task_policy(current);
 	struct page *page;
 	unsigned int cpuset_mems_cookie;
 
@@ -2295,6 +2315,11 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 	default:
 		BUG();
 	}
+
+	/* Migrate the page towards the node whose CPU is referencing it */
+	if (pol->flags & MPOL_F_MORON)
+		polnid = numa_node_id();
+
 	if (curnid != polnid)
 		ret = polnid;
 out:
@@ -2483,6 +2508,15 @@ void __init numa_policy_init(void)
 				     sizeof(struct sp_node),
 				     0, SLAB_PANIC, NULL);
 
+	for_each_node(nid) {
+		preferred_node_policy[nid] = (struct mempolicy) {
+			.refcnt = ATOMIC_INIT(1),
+			.mode = MPOL_PREFERRED,
+			.flags = MPOL_F_MOF | MPOL_F_MORON,
+			.v = { .preferred_node = nid, },
+		};
+	}
+
 	/*
 	 * Set interleaving policy for system init. Interleaving is only
 	 * enabled across suitably sized nodes (default is >= 16MB), or
-- 
cgit v1.2.3-55-g7522


From 8177a420ed7c16c171ed3c3aec5b0676db38c247 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli
Date: Fri, 23 Mar 2012 20:56:34 +0100
Subject: mm: numa: Structures for Migrate On Fault per NUMA migration rate
 limiting

This defines the per-node data used by Migrate On Fault in order to
rate limit the migration. The rate limiting is applied independently
to each destination node.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mmzone.h | 13 +++++++++++++
 mm/page_alloc.c        |  5 +++++
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a23923ba8263..28601fdfcdb2 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -717,6 +717,19 @@ typedef struct pglist_data {
 	struct task_struct *kswapd;	/* Protected by lock_memory_hotplug() */
 	int kswapd_max_order;
 	enum zone_type classzone_idx;
+#ifdef CONFIG_NUMA_BALANCING
+	/*
+	 * Lock serializing the per destination node AutoNUMA memory
+	 * migration rate limiting data.
+	 */
+	spinlock_t numabalancing_migrate_lock;
+
+	/* Rate limiting time interval */
+	unsigned long numabalancing_migrate_next_window;
+
+	/* Number of pages migrated during the rate limiting time interval */
+	unsigned long numabalancing_migrate_nr_pages;
+#endif
 } pg_data_t;
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5953dc2d196f..ef025e20dbee 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4449,6 +4449,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 	int ret;
 
 	pgdat_resize_init(pgdat);
+#ifdef CONFIG_NUMA_BALANCING
+	spin_lock_init(&pgdat->numabalancing_migrate_lock);
+	pgdat->numabalancing_migrate_nr_pages = 0;
+	pgdat->numabalancing_migrate_next_window = jiffies;
+#endif
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	init_waitqueue_head(&pgdat->pfmemalloc_wait);
 	pgdat_page_cgroup_init(pgdat);
-- 
cgit v1.2.3-55-g7522


From e14808b49f55e0e1135da5e4a154a540dd9f3662 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Mon, 19 Nov 2012 10:59:15 +0000
Subject: mm: numa: Rate limit setting of pte_numa if node is saturated

If there are a large number of NUMA hinting faults and all of them
are resulting in migrations it may indicate that memory is just
bouncing uselessly around. NUMA balancing cost is likely exceeding
any benefit from locality. Rate limit the PTE updates if the node
is migration rate-limited. As noted in the comments, this distorts
the NUMA faulting statistics.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/migrate.h |  6 ++++++
 kernel/sched/fair.c     |  9 +++++++++
 mm/migrate.c            | 20 ++++++++++++++++++++
 3 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index f0d0313eea6f..91556889adac 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -77,11 +77,17 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 
 #ifdef CONFIG_NUMA_BALANCING
 extern int migrate_misplaced_page(struct page *page, int node);
+extern int migrate_misplaced_page(struct page *page, int node);
+extern bool migrate_ratelimited(int node);
 #else
 static inline int migrate_misplaced_page(struct page *page, int node)
 {
 	return -EAGAIN; /* can't migrate now */
 }
+static inline bool migrate_ratelimited(int node)
+{
+	return false;
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #endif /* _LINUX_MIGRATE_H */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7727b0161579..37e895a941ab 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -27,6 +27,7 @@
 #include <linux/profile.h>
 #include <linux/interrupt.h>
 #include <linux/mempolicy.h>
+#include <linux/migrate.h>
 #include <linux/task_work.h>
 
 #include <trace/events/sched.h>
@@ -861,6 +862,14 @@ void task_numa_work(struct callback_head *work)
 	if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
 		return;
 
+	/*
+	 * Do not set pte_numa if the current running node is rate-limited.
+	 * This loses statistics on the fault but if we are unwilling to
+	 * migrate to this node, it is less likely we can do useful work
+	 */
+	if (migrate_ratelimited(numa_node_id()))
+		return;
+
 	start = mm->numa_scan_offset;
 	pages = sysctl_numa_balancing_scan_size;
 	pages <<= 20 - PAGE_SHIFT; /* MB in pages */
diff --git a/mm/migrate.c b/mm/migrate.c
index 4b8267f1842f..32a1afca6009 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1464,10 +1464,30 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
  * page migration rate limiting control.
  * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs
  * window of time. Default here says do not migrate more than 1280M per second.
+ * If a node is rate-limited then PTE NUMA updates are also rate-limited. However
+ * as it is faults that reset the window, pte updates will happen unconditionally
+ * if there has not been a fault since @pteupdate_interval_millisecs after the
+ * throttle window closed.
  */
 static unsigned int migrate_interval_millisecs __read_mostly = 100;
+static unsigned int pteupdate_interval_millisecs __read_mostly = 1000;
 static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT);
 
+/* Returns true if NUMA migration is currently rate limited */
+bool migrate_ratelimited(int node)
+{
+	pg_data_t *pgdat = NODE_DATA(node);
+
+	if (time_after(jiffies, pgdat->numabalancing_migrate_next_window +
+				msecs_to_jiffies(pteupdate_interval_millisecs)))
+		return false;
+
+	if (pgdat->numabalancing_migrate_nr_pages < ratelimit_pages)
+		return false;
+
+	return true;
+}
+
 /*
  * Attempt to migrate a misplaced page to the specified destination
  * node. Caller is expected to have an elevated reference count on
-- 
cgit v1.2.3-55-g7522


From 57e0a0309160b1b4ebde9f3c6a867cd96ac368bf Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Mon, 12 Nov 2012 09:06:20 +0000
Subject: mm: numa: Introduce last_nid to the page frame

This patch introduces a last_nid field to the page struct. This is used
to build a two-stage filter in the next patch that is aimed at
mitigating a problem whereby pages migrate to the wrong node when
referenced by a process that was running off its home node.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mm.h       | 30 ++++++++++++++++++++++++++++++
 include/linux/mm_types.h |  4 ++++
 mm/page_alloc.c          |  2 ++
 3 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index d04c2f0aab36..d87f9ec4a145 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -693,6 +693,36 @@ static inline int page_to_nid(const struct page *page)
 }
 #endif
 
+#ifdef CONFIG_NUMA_BALANCING
+static inline int page_xchg_last_nid(struct page *page, int nid)
+{
+	return xchg(&page->_last_nid, nid);
+}
+
+static inline int page_last_nid(struct page *page)
+{
+	return page->_last_nid;
+}
+static inline void reset_page_last_nid(struct page *page)
+{
+	page->_last_nid = -1;
+}
+#else
+static inline int page_xchg_last_nid(struct page *page, int nid)
+{
+	return page_to_nid(page);
+}
+
+static inline int page_last_nid(struct page *page)
+{
+	return page_to_nid(page);
+}
+
+static inline void reset_page_last_nid(struct page *page)
+{
+}
+#endif
+
 static inline struct zone *page_zone(const struct page *page)
 {
 	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d1e246c5e50c..c5fffa239861 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -175,6 +175,10 @@ struct page {
 	 */
 	void *shadow;
 #endif
+
+#ifdef CONFIG_NUMA_BALANCING
+	int _last_nid;
+#endif
 }
 /*
  * The struct page can be forced to be double word aligned so that atomic ops
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ef025e20dbee..73f226a1206e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -608,6 +608,7 @@ static inline int free_pages_check(struct page *page)
 		bad_page(page);
 		return 1;
 	}
+	reset_page_last_nid(page);
 	if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
 		page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	return 0;
@@ -3826,6 +3827,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		mminit_verify_page_links(page, zone, nid, pfn);
 		init_page_count(page);
 		reset_page_mapcount(page);
+		reset_page_last_nid(page);
 		SetPageReserved(page);
 		/*
 		 * Mark the block movable so that blocks are reserved for
-- 
cgit v1.2.3-55-g7522


From b8593bfda1652755136333cdd362de125b283a9c Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Wed, 21 Nov 2012 01:18:23 +0000
Subject: mm: sched: Adapt the scanning rate if a NUMA hinting fault does not
 migrate

The PTE scanning rate and fault rates are two of the biggest sources of
system CPU overhead with automatic NUMA placement.  Ideally a proper policy
would detect if a workload was properly placed, schedule and adjust the
PTE scanning rate accordingly. We do not track the necessary information
to do that but we at least know if we migrated or not.

This patch scans slower if a page was not migrated as the result of a
NUMA hinting fault up to sysctl_numa_balancing_scan_period_max which is
now higher than the previous default. Once every minute it will reset
the scanner in case of phase changes.

This is hilariously crude and the numbers are arbitrary. Workloads will
converge quite slowly in comparison to what a proper policy should be able
to do. On the plus side, we will chew up less CPU for workloads that have
no need for automatic balancing.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mm_types.h |  3 +++
 include/linux/sched.h    |  5 +++--
 kernel/sched/core.c      |  1 +
 kernel/sched/fair.c      | 29 +++++++++++++++++++++--------
 kernel/sysctl.c          |  7 +++++++
 mm/huge_memory.c         |  2 +-
 mm/memory.c              | 12 ++++++++----
 7 files changed, 44 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index c5fffa239861..e850a23dd6ec 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -410,6 +410,9 @@ struct mm_struct {
 	 */
 	unsigned long numa_next_scan;
 
+	/* numa_next_reset is when the PTE scanner period will be reset */
+	unsigned long numa_next_reset;
+
 	/* Restart point for scanning and setting pte_numa */
 	unsigned long numa_scan_offset;
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7d95a232b5b9..0f4ff2bd03f6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1562,9 +1562,9 @@ struct task_struct {
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
 #ifdef CONFIG_NUMA_BALANCING
-extern void task_numa_fault(int node, int pages);
+extern void task_numa_fault(int node, int pages, bool migrated);
 #else
-static inline void task_numa_fault(int node, int pages)
+static inline void task_numa_fault(int node, int pages, bool migrated)
 {
 }
 #endif
@@ -2009,6 +2009,7 @@ extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 extern unsigned int sysctl_numa_balancing_scan_delay;
 extern unsigned int sysctl_numa_balancing_scan_period_min;
 extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_scan_period_reset;
 extern unsigned int sysctl_numa_balancing_scan_size;
 extern unsigned int sysctl_numa_balancing_settle_count;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fbfc4843063f..9d255bc0e278 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1537,6 +1537,7 @@ static void __sched_fork(struct task_struct *p)
 #ifdef CONFIG_NUMA_BALANCING
 	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
 		p->mm->numa_next_scan = jiffies;
+		p->mm->numa_next_reset = jiffies;
 		p->mm->numa_scan_seq = 0;
 	}
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index dd18087fd369..4b577863933f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -784,7 +784,8 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * numa task sample period in ms
  */
 unsigned int sysctl_numa_balancing_scan_period_min = 100;
-unsigned int sysctl_numa_balancing_scan_period_max = 100*16;
+unsigned int sysctl_numa_balancing_scan_period_max = 100*50;
+unsigned int sysctl_numa_balancing_scan_period_reset = 100*600;
 
 /* Portion of address space to scan in MB */
 unsigned int sysctl_numa_balancing_scan_size = 256;
@@ -806,20 +807,19 @@ static void task_numa_placement(struct task_struct *p)
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
-void task_numa_fault(int node, int pages)
+void task_numa_fault(int node, int pages, bool migrated)
 {
 	struct task_struct *p = current;
 
 	/* FIXME: Allocate task-specific structure for placement policy here */
 
 	/*
-	 * Assume that as faults occur that pages are getting properly placed
-	 * and fewer NUMA hints are required. Note that this is a big
-	 * assumption, it assumes processes reach a steady steady with no
-	 * further phase changes.
+	 * If pages are properly placed (did not migrate) then scan slower.
+	 * This is reset periodically in case of phase changes
 	 */
-	p->numa_scan_period = min(sysctl_numa_balancing_scan_period_max,
-				p->numa_scan_period + jiffies_to_msecs(2));
+        if (!migrated)
+		p->numa_scan_period = min(sysctl_numa_balancing_scan_period_max,
+			p->numa_scan_period + jiffies_to_msecs(10));
 
 	task_numa_placement(p);
 }
@@ -857,6 +857,19 @@ void task_numa_work(struct callback_head *work)
 	if (p->flags & PF_EXITING)
 		return;
 
+	/*
+	 * Reset the scan period if enough time has gone by. Objective is that
+	 * scanning will be reduced if pages are properly placed. As tasks
+	 * can enter different phases this needs to be re-examined. Lacking
+	 * proper tracking of reference behaviour, this blunt hammer is used.
+	 */
+	migrate = mm->numa_next_reset;
+	if (time_after(now, migrate)) {
+		p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+		next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);
+		xchg(&mm->numa_next_reset, next_scan);
+	}
+
 	/*
 	 * Enforce maximal scan/migration frequency..
 	 */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 48a68cc258c1..8906f90d6fa2 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -366,6 +366,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "numa_balancing_scan_period_reset",
+		.data		= &sysctl_numa_balancing_scan_period_reset,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "numa_balancing_scan_period_max_ms",
 		.data		= &sysctl_numa_balancing_scan_period_max,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 79b96064f8fc..199b261a257e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1068,7 +1068,7 @@ out_unlock:
 	spin_unlock(&mm->page_table_lock);
 	if (page) {
 		put_page(page);
-		task_numa_fault(numa_node_id(), HPAGE_PMD_NR);
+		task_numa_fault(numa_node_id(), HPAGE_PMD_NR, false);
 	}
 	return 0;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 84c6d9eab182..39edb11b63dc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3468,6 +3468,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	int current_nid = -1;
 	int target_nid;
+	bool migrated = false;
 
 	/*
 	* The "pte" at this point cannot be used safely without
@@ -3509,12 +3510,13 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	/* Migrate to the requested node */
-	if (migrate_misplaced_page(page, target_nid))
+	migrated = migrate_misplaced_page(page, target_nid);
+	if (migrated)
 		current_nid = target_nid;
 
 out:
 	if (current_nid != -1)
-		task_numa_fault(current_nid, 1);
+		task_numa_fault(current_nid, 1, migrated);
 	return 0;
 }
 
@@ -3554,6 +3556,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct page *page;
 		int curr_nid = local_nid;
 		int target_nid;
+		bool migrated;
 		if (!pte_present(pteval))
 			continue;
 		if (!pte_numa(pteval))
@@ -3590,9 +3593,10 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 		/* Migrate to the requested node */
 		pte_unmap_unlock(pte, ptl);
-		if (migrate_misplaced_page(page, target_nid))
+		migrated = migrate_misplaced_page(page, target_nid);
+		if (migrated)
 			curr_nid = target_nid;
-		task_numa_fault(curr_nid, 1);
+		task_numa_fault(curr_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
-- 
cgit v1.2.3-55-g7522


From 1a687c2e9a99335c9e77392f050fe607fa18a652 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Thu, 22 Nov 2012 11:16:36 +0000
Subject: mm: sched: numa: Control enabling and disabling of NUMA balancing

This patch adds Kconfig options and kernel parameters to allow the
enabling and disabling of automatic NUMA balancing. The existance
of such a switch was and is very important when debugging problems
related to transparent hugepages and we should have the same for
automatic NUMA placement.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 Documentation/kernel-parameters.txt |  3 +++
 include/linux/sched.h               |  4 ++++
 init/Kconfig                        |  8 +++++++
 kernel/sched/core.c                 | 48 +++++++++++++++++++++++++------------
 kernel/sched/fair.c                 |  3 +++
 kernel/sched/features.h             |  6 +++--
 mm/mempolicy.c                      | 46 +++++++++++++++++++++++++++++++++++
 7 files changed, 101 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 9776f068306b..2e8d2625b814 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1996,6 +1996,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nr_uarts=	[SERIAL] maximum number of UARTs to be registered.
 
+	numa_balancing=	[KNL,X86] Enable or disable automatic NUMA balancing.
+			Allowed values are enable and disable
+
 	numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
 			one of ['zone', 'node', 'default'] can be specified
 			This can be set from sysctl after boot.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0f4ff2bd03f6..b1e619f9ff1a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1563,10 +1563,14 @@ struct task_struct {
 
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int node, int pages, bool migrated);
+extern void set_numabalancing_state(bool enabled);
 #else
 static inline void task_numa_fault(int node, int pages, bool migrated)
 {
 }
+static inline void set_numabalancing_state(bool enabled)
+{
+}
 #endif
 
 /*
diff --git a/init/Kconfig b/init/Kconfig
index 9f00f004796a..18e2a5920a34 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -720,6 +720,14 @@ config ARCH_USES_NUMA_PROT_NONE
 	depends on ARCH_WANTS_PROT_NUMA_PROT_NONE
 	depends on NUMA_BALANCING
 
+config NUMA_BALANCING_DEFAULT_ENABLED
+	bool "Automatically enable NUMA aware memory/task placement"
+	default y
+	depends on NUMA_BALANCING
+	help
+	  If set, autonumic NUMA balancing will be enabled if running on a NUMA
+	  machine.
+
 config NUMA_BALANCING
 	bool "Memory placement aware NUMA scheduler"
 	default y
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9d255bc0e278..7a45015274ab 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -192,23 +192,10 @@ static void sched_feat_disable(int i) { };
 static void sched_feat_enable(int i) { };
 #endif /* HAVE_JUMP_LABEL */
 
-static ssize_t
-sched_feat_write(struct file *filp, const char __user *ubuf,
-		size_t cnt, loff_t *ppos)
+static int sched_feat_set(char *cmp)
 {
-	char buf[64];
-	char *cmp;
-	int neg = 0;
 	int i;
-
-	if (cnt > 63)
-		cnt = 63;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-	cmp = strstrip(buf);
+	int neg = 0;
 
 	if (strncmp(cmp, "NO_", 3) == 0) {
 		neg = 1;
@@ -228,6 +215,27 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 		}
 	}
 
+	return i;
+}
+
+static ssize_t
+sched_feat_write(struct file *filp, const char __user *ubuf,
+		size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	char *cmp;
+	int i;
+
+	if (cnt > 63)
+		cnt = 63;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+	cmp = strstrip(buf);
+
+	i = sched_feat_set(cmp);
 	if (i == __SCHED_FEAT_NR)
 		return -EINVAL;
 
@@ -1549,6 +1557,16 @@ static void __sched_fork(struct task_struct *p)
 #endif /* CONFIG_NUMA_BALANCING */
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+void set_numabalancing_state(bool enabled)
+{
+	if (enabled)
+		sched_feat_set("NUMA");
+	else
+		sched_feat_set("NO_NUMA");
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /*
  * fork()/clone()-time setup:
  */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4b577863933f..7a02a2082e95 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -811,6 +811,9 @@ void task_numa_fault(int node, int pages, bool migrated)
 {
 	struct task_struct *p = current;
 
+	if (!sched_feat_numa(NUMA))
+		return;
+
 	/* FIXME: Allocate task-specific structure for placement policy here */
 
 	/*
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 5fb7aefbec80..d2373a3e3252 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -63,8 +63,10 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
 
 /*
- * Apply the automatic NUMA scheduling policy
+ * Apply the automatic NUMA scheduling policy. Enabled automatically
+ * at runtime if running on a NUMA machine. Can be controlled via
+ * numa_balancing=
  */
 #ifdef CONFIG_NUMA_BALANCING
-SCHED_FEAT(NUMA,	true)
+SCHED_FEAT(NUMA,	false)
 #endif
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index fd20e28fd2ad..046308e9b999 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2521,6 +2521,50 @@ void mpol_free_shared_policy(struct shared_policy *p)
 	mutex_unlock(&p->mutex);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static bool __initdata numabalancing_override;
+
+static void __init check_numabalancing_enable(void)
+{
+	bool numabalancing_default = false;
+
+	if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED))
+		numabalancing_default = true;
+
+	if (nr_node_ids > 1 && !numabalancing_override) {
+		printk(KERN_INFO "Enabling automatic NUMA balancing. "
+			"Configure with numa_balancing= or sysctl");
+		set_numabalancing_state(numabalancing_default);
+	}
+}
+
+static int __init setup_numabalancing(char *str)
+{
+	int ret = 0;
+	if (!str)
+		goto out;
+	numabalancing_override = true;
+
+	if (!strcmp(str, "enable")) {
+		set_numabalancing_state(true);
+		ret = 1;
+	} else if (!strcmp(str, "disable")) {
+		set_numabalancing_state(false);
+		ret = 1;
+	}
+out:
+	if (!ret)
+		printk(KERN_WARNING "Unable to parse numa_balancing=\n");
+
+	return ret;
+}
+__setup("numa_balancing=", setup_numabalancing);
+#else
+static inline void __init check_numabalancing_enable(void)
+{
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /* assumes fs == KERNEL_DS */
 void __init numa_policy_init(void)
 {
@@ -2571,6 +2615,8 @@ void __init numa_policy_init(void)
 
 	if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
 		printk("numa_policy_init: interleaving failed\n");
+
+	check_numabalancing_enable();
 }
 
 /* Reset policy of current process to default */
-- 
cgit v1.2.3-55-g7522


From 5bca23035391928c4c7301835accca3551b96cc2 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Thu, 22 Nov 2012 14:40:03 +0000
Subject: mm: sched: numa: Delay PTE scanning until a task is scheduled on a
 new node

Due to the fact that migrations are driven by the CPU a task is running
on there is no point tracking NUMA faults until one task runs on a new
node. This patch tracks the first node used by an address space. Until
it changes, PTE scanning is disabled and no NUMA hinting faults are
trapped. This should help workloads that are short-lived, do not care
about NUMA placement or have bound themselves to a single node.

This takes advantage of the logic in "mm: sched: numa: Implement slow
start for working set sampling" to delay when the checks are made. This
will take advantage of processes that set their CPU and node bindings
early in their lifetime. It will also potentially allow any initial load
balancing to take place.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mm_types.h | 10 ++++++++++
 kernel/fork.c            |  3 +++
 kernel/sched/fair.c      | 18 ++++++++++++++++++
 kernel/sched/features.h  |  4 +++-
 4 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index e850a23dd6ec..197422a1598c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -418,10 +418,20 @@ struct mm_struct {
 
 	/* numa_scan_seq prevents two threads setting pte_numa */
 	int numa_scan_seq;
+
+	/*
+	 * The first node a task was scheduled on. If a task runs on
+	 * a different node than Make PTE Scan Go Now.
+	 */
+	int first_nid;
 #endif
 	struct uprobes_state uprobes_state;
 };
 
+/* first nid will either be a valid NID or one of these values */
+#define NUMA_PTE_SCAN_INIT	-1
+#define NUMA_PTE_SCAN_ACTIVE	-2
+
 static inline void mm_init_cpumask(struct mm_struct *mm)
 {
 #ifdef CONFIG_CPUMASK_OFFSTACK
diff --git a/kernel/fork.c b/kernel/fork.c
index 8b20ab7d3aa2..296ea308096d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -820,6 +820,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	mm->pmd_huge_pte = NULL;
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+	mm->first_nid = NUMA_PTE_SCAN_INIT;
 #endif
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7a02a2082e95..3e18f611a5aa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -860,6 +860,24 @@ void task_numa_work(struct callback_head *work)
 	if (p->flags & PF_EXITING)
 		return;
 
+	/*
+	 * We do not care about task placement until a task runs on a node
+	 * other than the first one used by the address space. This is
+	 * largely because migrations are driven by what CPU the task
+	 * is running on. If it's never scheduled on another node, it'll
+	 * not migrate so why bother trapping the fault.
+	 */
+	if (mm->first_nid == NUMA_PTE_SCAN_INIT)
+		mm->first_nid = numa_node_id();
+	if (mm->first_nid != NUMA_PTE_SCAN_ACTIVE) {
+		/* Are we running on a new node yet? */
+		if (numa_node_id() == mm->first_nid &&
+		    !sched_feat_numa(NUMA_FORCE))
+			return;
+
+		mm->first_nid = NUMA_PTE_SCAN_ACTIVE;
+	}
+
 	/*
 	 * Reset the scan period if enough time has gone by. Objective is that
 	 * scanning will be reduced if pages are properly placed. As tasks
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index d2373a3e3252..e7c25fff1e94 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -65,8 +65,10 @@ SCHED_FEAT(LB_MIN, false)
 /*
  * Apply the automatic NUMA scheduling policy. Enabled automatically
  * at runtime if running on a NUMA machine. Can be controlled via
- * numa_balancing=
+ * numa_balancing=. Allow PTE scanning to be forced on UMA machines
+ * for debugging the core machinery.
  */
 #ifdef CONFIG_NUMA_BALANCING
 SCHED_FEAT(NUMA,	false)
+SCHED_FEAT(NUMA_FORCE,	false)
 #endif
-- 
cgit v1.2.3-55-g7522


From b32967ff101a7508f70be8de59b278d4df92fa00 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Mon, 19 Nov 2012 12:35:47 +0000
Subject: mm: numa: Add THP migration for the NUMA working set scanning fault
 case.

Note: This is very heavily based on a patch from Peter Zijlstra with
	fixes from Ingo Molnar, Hugh Dickins and Johannes Weiner.  That patch
	put a lot of migration logic into mm/huge_memory.c where it does
	not belong. This version puts tries to share some of the migration
	logic with migrate_misplaced_page.  However, it should be noted
	that now migrate.c is doing more with the pagetable manipulation
	than is preferred. The end result is barely recognisable so as
	before, the signed-offs had to be removed but will be re-added if
	the original authors are ok with it.

Add THP migration for the NUMA working set scanning fault case.

It uses the page lock to serialize. No migration pte dance is
necessary because the pte is already unmapped when we decide
to migrate.

[dhillf@gmail.com: Fix memory leak on isolation failure]
[dhillf@gmail.com: Fix transfer of last_nid information]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/migrate.h |  15 ++++
 mm/huge_memory.c        |  59 +++++++++----
 mm/internal.h           |   7 +-
 mm/memcontrol.c         |   7 +-
 mm/migrate.c            | 231 +++++++++++++++++++++++++++++++++++++++---------
 5 files changed, 255 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 91556889adac..51eac4bdc606 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -79,6 +79,12 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 extern int migrate_misplaced_page(struct page *page, int node);
 extern int migrate_misplaced_page(struct page *page, int node);
 extern bool migrate_ratelimited(int node);
+extern int migrate_misplaced_transhuge_page(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			pmd_t *pmd, pmd_t entry,
+			unsigned long address,
+			struct page *page, int node);
+
 #else
 static inline int migrate_misplaced_page(struct page *page, int node)
 {
@@ -88,6 +94,15 @@ static inline bool migrate_ratelimited(int node)
 {
 	return false;
 }
+
+static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			pmd_t *pmd, pmd_t entry,
+			unsigned long address,
+			struct page *page, int node)
+{
+	return -EAGAIN;
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #endif /* _LINUX_MIGRATE_H */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 199b261a257e..711baf84b153 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -600,7 +600,7 @@ out:
 }
 __setup("transparent_hugepage=", setup_transparent_hugepage);
 
-static inline pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
+pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 {
 	if (likely(vma->vm_flags & VM_WRITE))
 		pmd = pmd_mkwrite(pmd);
@@ -1023,10 +1023,12 @@ out:
 int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
-	struct page *page = NULL;
+	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
 	int target_nid;
 	int current_nid = -1;
+	bool migrated;
+	bool page_locked = false;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
@@ -1034,42 +1036,61 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	page = pmd_page(pmd);
 	get_page(page);
-	spin_unlock(&mm->page_table_lock);
 	current_nid = page_to_nid(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
 	if (current_nid == numa_node_id())
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
 	target_nid = mpol_misplaced(page, vma, haddr);
-	if (target_nid == -1)
+	if (target_nid == -1) {
+		put_page(page);
 		goto clear_pmdnuma;
+	}
 
-	/*
-	 * Due to lacking code to migrate thp pages, we'll split
-	 * (which preserves the special PROT_NONE) and re-take the
-	 * fault on the normal pages.
-	 */
-	split_huge_page(page);
-	put_page(page);
-
-	return 0;
+	/* Acquire the page lock to serialise THP migrations */
+	spin_unlock(&mm->page_table_lock);
+	lock_page(page);
+	page_locked = true;
 
-clear_pmdnuma:
+	/* Confirm the PTE did not while locked */
 	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(pmd, *pmdp)))
+	if (unlikely(!pmd_same(pmd, *pmdp))) {
+		unlock_page(page);
+		put_page(page);
 		goto out_unlock;
+	}
+	spin_unlock(&mm->page_table_lock);
+
+	/* Migrate the THP to the requested node */
+	migrated = migrate_misplaced_transhuge_page(mm, vma,
+				pmdp, pmd, addr,
+				page, target_nid);
+	if (migrated)
+		current_nid = target_nid;
+	else {
+		spin_lock(&mm->page_table_lock);
+		if (unlikely(!pmd_same(pmd, *pmdp))) {
+			unlock_page(page);
+			goto out_unlock;
+		}
+		goto clear_pmdnuma;
+	}
+
+	task_numa_fault(current_nid, HPAGE_PMD_NR, migrated);
+	return 0;
 
+clear_pmdnuma:
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
+	if (page_locked)
+		unlock_page(page);
 
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
-	if (page) {
-		put_page(page);
-		task_numa_fault(numa_node_id(), HPAGE_PMD_NR, false);
-	}
+	if (current_nid != -1)
+		task_numa_fault(current_nid, HPAGE_PMD_NR, migrated);
 	return 0;
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index a4fa284f6bc2..7e60ac826f2b 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -212,15 +212,18 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page)
 {
 	if (TestClearPageMlocked(page)) {
 		unsigned long flags;
+		int nr_pages = hpage_nr_pages(page);
 
 		local_irq_save(flags);
-		__dec_zone_page_state(page, NR_MLOCK);
+		__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
 		SetPageMlocked(newpage);
-		__inc_zone_page_state(newpage, NR_MLOCK);
+		__mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages);
 		local_irq_restore(flags);
 	}
 }
 
+extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern unsigned long vma_address(struct page *page,
 				 struct vm_area_struct *vma);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index dd39ba000b31..d97af9636ab2 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3288,15 +3288,18 @@ void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 				  struct mem_cgroup **memcgp)
 {
 	struct mem_cgroup *memcg = NULL;
+	unsigned int nr_pages = 1;
 	struct page_cgroup *pc;
 	enum charge_type ctype;
 
 	*memcgp = NULL;
 
-	VM_BUG_ON(PageTransHuge(page));
 	if (mem_cgroup_disabled())
 		return;
 
+	if (PageTransHuge(page))
+		nr_pages <<= compound_order(page);
+
 	pc = lookup_page_cgroup(page);
 	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc)) {
@@ -3358,7 +3361,7 @@ void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 	 * charged to the res_counter since we plan on replacing the
 	 * old one and only one page is going to be left afterwards.
 	 */
-	__mem_cgroup_commit_charge(memcg, newpage, 1, ctype, false);
+	__mem_cgroup_commit_charge(memcg, newpage, nr_pages, ctype, false);
 }
 
 /* remove redundant charge if migration failed*/
diff --git a/mm/migrate.c b/mm/migrate.c
index 2a5ce135eef0..c9400960fd52 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -410,7 +410,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
  */
 void migrate_page_copy(struct page *newpage, struct page *page)
 {
-	if (PageHuge(page))
+	if (PageHuge(page) || PageTransHuge(page))
 		copy_huge_page(newpage, page);
 	else
 		copy_highpage(newpage, page);
@@ -1491,25 +1491,10 @@ bool migrate_ratelimited(int node)
 	return true;
 }
 
-/*
- * Attempt to migrate a misplaced page to the specified destination
- * node. Caller is expected to have an elevated reference count on
- * the page that will be dropped by this function before returning.
- */
-int migrate_misplaced_page(struct page *page, int node)
+/* Returns true if the node is migrate rate-limited after the update */
+bool numamigrate_update_ratelimit(pg_data_t *pgdat)
 {
-	pg_data_t *pgdat = NODE_DATA(node);
-	int isolated = 0;
-	LIST_HEAD(migratepages);
-
-	/*
-	 * Don't migrate pages that are mapped in multiple processes.
-	 * TODO: Handle false sharing detection instead of this hammer
-	 */
-	if (page_mapcount(page) != 1) {
-		put_page(page);
-		goto out;
-	}
+	bool rate_limited = false;
 
 	/*
 	 * Rate-limit the amount of data that is being migrated to a node.
@@ -1522,13 +1507,18 @@ int migrate_misplaced_page(struct page *page, int node)
 		pgdat->numabalancing_migrate_next_window = jiffies +
 			msecs_to_jiffies(migrate_interval_millisecs);
 	}
-	if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) {
-		spin_unlock(&pgdat->numabalancing_migrate_lock);
-		put_page(page);
-		goto out;
-	}
-	pgdat->numabalancing_migrate_nr_pages++;
+	if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages)
+		rate_limited = true;
+	else
+		pgdat->numabalancing_migrate_nr_pages++;
 	spin_unlock(&pgdat->numabalancing_migrate_lock);
+	
+	return rate_limited;
+}
+
+int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
+{
+	int ret = 0;
 
 	/* Avoid migrating to a node that is nearly full */
 	if (migrate_balanced_pgdat(pgdat, 1)) {
@@ -1536,13 +1526,18 @@ int migrate_misplaced_page(struct page *page, int node)
 
 		if (isolate_lru_page(page)) {
 			put_page(page);
-			goto out;
+			return 0;
 		}
-		isolated = 1;
 
+		/* Page is isolated */
+		ret = 1;
 		page_lru = page_is_file_cache(page);
-		inc_zone_page_state(page, NR_ISOLATED_ANON + page_lru);
-		list_add(&page->lru, &migratepages);
+		if (!PageTransHuge(page))
+			inc_zone_page_state(page, NR_ISOLATED_ANON + page_lru);
+		else
+			mod_zone_page_state(page_zone(page),
+					NR_ISOLATED_ANON + page_lru,
+					HPAGE_PMD_NR);
 	}
 
 	/*
@@ -1555,23 +1550,177 @@ int migrate_misplaced_page(struct page *page, int node)
 	 */
 	put_page(page);
 
-	if (isolated) {
-		int nr_remaining;
-
-		nr_remaining = migrate_pages(&migratepages,
-				alloc_misplaced_dst_page,
-				node, false, MIGRATE_ASYNC,
-				MR_NUMA_MISPLACED);
-		if (nr_remaining) {
-			putback_lru_pages(&migratepages);
-			isolated = 0;
-		} else
-			count_vm_numa_event(NUMA_PAGE_MIGRATE);
+	return ret;
+}
+
+/*
+ * Attempt to migrate a misplaced page to the specified destination
+ * node. Caller is expected to have an elevated reference count on
+ * the page that will be dropped by this function before returning.
+ */
+int migrate_misplaced_page(struct page *page, int node)
+{
+	pg_data_t *pgdat = NODE_DATA(node);
+	int isolated = 0;
+	int nr_remaining;
+	LIST_HEAD(migratepages);
+
+	/*
+	 * Don't migrate pages that are mapped in multiple processes.
+	 * TODO: Handle false sharing detection instead of this hammer
+	 */
+	if (page_mapcount(page) != 1) {
+		put_page(page);
+		goto out;
 	}
+
+	/*
+	 * Rate-limit the amount of data that is being migrated to a node.
+	 * Optimal placement is no good if the memory bus is saturated and
+	 * all the time is being spent migrating!
+	 */
+	if (numamigrate_update_ratelimit(pgdat)) {
+		put_page(page);
+		goto out;
+	}
+
+	isolated = numamigrate_isolate_page(pgdat, page);
+	if (!isolated)
+		goto out;
+
+	list_add(&page->lru, &migratepages);
+	nr_remaining = migrate_pages(&migratepages,
+			alloc_misplaced_dst_page,
+			node, false, MIGRATE_ASYNC,
+			MR_NUMA_MISPLACED);
+	if (nr_remaining) {
+		putback_lru_pages(&migratepages);
+		isolated = 0;
+	} else
+		count_vm_numa_event(NUMA_PAGE_MIGRATE);
 	BUG_ON(!list_empty(&migratepages));
 out:
 	return isolated;
 }
+
+int migrate_misplaced_transhuge_page(struct mm_struct *mm,
+				struct vm_area_struct *vma,
+				pmd_t *pmd, pmd_t entry,
+				unsigned long address,
+				struct page *page, int node)
+{
+	unsigned long haddr = address & HPAGE_PMD_MASK;
+	pg_data_t *pgdat = NODE_DATA(node);
+	int isolated = 0;
+	struct page *new_page = NULL;
+	struct mem_cgroup *memcg = NULL;
+	int page_lru = page_is_file_cache(page);
+
+	/*
+	 * Don't migrate pages that are mapped in multiple processes.
+	 * TODO: Handle false sharing detection instead of this hammer
+	 */
+	if (page_mapcount(page) != 1)
+		goto out_dropref;
+
+	/*
+	 * Rate-limit the amount of data that is being migrated to a node.
+	 * Optimal placement is no good if the memory bus is saturated and
+	 * all the time is being spent migrating!
+	 */
+	if (numamigrate_update_ratelimit(pgdat))
+		goto out_dropref;
+
+	new_page = alloc_pages_node(node,
+		(GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
+	if (!new_page)
+		goto out_dropref;
+	page_xchg_last_nid(new_page, page_last_nid(page));
+
+	isolated = numamigrate_isolate_page(pgdat, page);
+	if (!isolated) {
+		put_page(new_page);
+		goto out_keep_locked;
+	}
+
+	/* Prepare a page as a migration target */
+	__set_page_locked(new_page);
+	SetPageSwapBacked(new_page);
+
+	/* anon mapping, we can simply copy page->mapping to the new page: */
+	new_page->mapping = page->mapping;
+	new_page->index = page->index;
+	migrate_page_copy(new_page, page);
+	WARN_ON(PageLRU(new_page));
+
+	/* Recheck the target PMD */
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(*pmd, entry))) {
+		spin_unlock(&mm->page_table_lock);
+
+		/* Reverse changes made by migrate_page_copy() */
+		if (TestClearPageActive(new_page))
+			SetPageActive(page);
+		if (TestClearPageUnevictable(new_page))
+			SetPageUnevictable(page);
+		mlock_migrate_page(page, new_page);
+
+		unlock_page(new_page);
+		put_page(new_page);		/* Free it */
+
+		unlock_page(page);
+		putback_lru_page(page);
+
+		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
+		goto out;
+	}
+
+	/*
+	 * Traditional migration needs to prepare the memcg charge
+	 * transaction early to prevent the old page from being
+	 * uncharged when installing migration entries.  Here we can
+	 * save the potential rollback and start the charge transfer
+	 * only when migration is already known to end successfully.
+	 */
+	mem_cgroup_prepare_migration(page, new_page, &memcg);
+
+	entry = mk_pmd(new_page, vma->vm_page_prot);
+	entry = pmd_mknonnuma(entry);
+	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+	entry = pmd_mkhuge(entry);
+
+	page_add_new_anon_rmap(new_page, vma, haddr);
+
+	set_pmd_at(mm, haddr, pmd, entry);
+	update_mmu_cache_pmd(vma, address, entry);
+	page_remove_rmap(page);
+	/*
+	 * Finish the charge transaction under the page table lock to
+	 * prevent split_huge_page() from dividing up the charge
+	 * before it's fully transferred to the new page.
+	 */
+	mem_cgroup_end_migration(memcg, page, new_page, true);
+	spin_unlock(&mm->page_table_lock);
+
+	unlock_page(new_page);
+	unlock_page(page);
+	put_page(page);			/* Drop the rmap reference */
+	put_page(page);			/* Drop the LRU isolation reference */
+
+	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
+	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
+
+out:
+	mod_zone_page_state(page_zone(page),
+			NR_ISOLATED_ANON + page_lru,
+			-HPAGE_PMD_NR);
+	return isolated;
+
+out_dropref:
+	put_page(page);
+out_keep_locked:
+	return 0;
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #endif /* CONFIG_NUMA */
-- 
cgit v1.2.3-55-g7522


From 220018d388b8ab1fca1c5f0c6474bab47ad2c9c0 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Wed, 5 Dec 2012 09:32:56 +0000
Subject: mm: numa: Add THP migration for the NUMA working set scanning fault
 case build fix

Commit "Add THP migration for the NUMA working set scanning fault case"
breaks the build because HPAGE_PMD_SHIFT and HPAGE_PMD_MASK defined to
explode without CONFIG_TRANSPARENT_HUGEPAGE:

mm/migrate.c: In function 'migrate_misplaced_transhuge_page_put':
mm/migrate.c:1549: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed
mm/migrate.c:1564: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed
mm/migrate.c:1566: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed
mm/migrate.c:1573: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed
mm/migrate.c:1606: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed
mm/migrate.c:1648: error: call to '__build_bug_failed' declared with attribute error: BUILD_BUG failed

CONFIG_NUMA_BALANCING allows compilation without enabling transparent
hugepages, so define the dummy function for such a configuration and only
define migrate_misplaced_transhuge_page_put() when transparent hugepages
are enabled.

Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/migrate.h | 16 +++++++++-------
 mm/migrate.c            |  2 ++
 2 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 51eac4bdc606..d52afb9a790c 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -79,12 +79,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 extern int migrate_misplaced_page(struct page *page, int node);
 extern int migrate_misplaced_page(struct page *page, int node);
 extern bool migrate_ratelimited(int node);
-extern int migrate_misplaced_transhuge_page(struct mm_struct *mm,
-			struct vm_area_struct *vma,
-			pmd_t *pmd, pmd_t entry,
-			unsigned long address,
-			struct page *page, int node);
-
 #else
 static inline int migrate_misplaced_page(struct page *page, int node)
 {
@@ -94,7 +88,15 @@ static inline bool migrate_ratelimited(int node)
 {
 	return false;
 }
+#endif /* CONFIG_NUMA_BALANCING */
 
+#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+extern int migrate_misplaced_transhuge_page(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			pmd_t *pmd, pmd_t entry,
+			unsigned long address,
+			struct page *page, int node);
+#else
 static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 			struct vm_area_struct *vma,
 			pmd_t *pmd, pmd_t entry,
@@ -103,6 +105,6 @@ static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 {
 	return -EAGAIN;
 }
-#endif /* CONFIG_NUMA_BALANCING */
+#endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/
 
 #endif /* _LINUX_MIGRATE_H */
diff --git a/mm/migrate.c b/mm/migrate.c
index c9400960fd52..9341a501d168 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1602,7 +1602,9 @@ int migrate_misplaced_page(struct page *page, int node)
 out:
 	return isolated;
 }
+#endif /* CONFIG_NUMA_BALANCING */
 
+#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
 int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 				struct vm_area_struct *vma,
 				pmd_t *pmd, pmd_t entry,
-- 
cgit v1.2.3-55-g7522


From 5a505085f043e8380f83610f79642853c051e2f1 Mon Sep 17 00:00:00 2001
From: Ingo Molnar
Date: Sun, 2 Dec 2012 19:56:46 +0000
Subject: mm/rmap: Convert the struct anon_vma::mutex to an rwsem

Convert the struct anon_vma::mutex to an rwsem, which will help
in solving a page-migration scalability problem. (Addressed in
a separate patch.)

The conversion is simple and straightforward: in every case
where we mutex_lock()ed we'll now down_write().

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Turner <pjt@google.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/rmap.h | 16 ++++++++--------
 mm/huge_memory.c     |  4 ++--
 mm/mmap.c            |  8 ++++----
 mm/rmap.c            | 22 +++++++++++-----------
 4 files changed, 25 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index bfe1f4780644..f3f41d242e25 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -7,7 +7,7 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
-#include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/memcontrol.h>
 
 /*
@@ -25,8 +25,8 @@
  * pointing to this anon_vma once its vma list is empty.
  */
 struct anon_vma {
-	struct anon_vma *root;	/* Root of this anon_vma tree */
-	struct mutex mutex;	/* Serialize access to vma list */
+	struct anon_vma *root;		/* Root of this anon_vma tree */
+	struct rw_semaphore rwsem;	/* W: modification, R: walking the list */
 	/*
 	 * The refcount is taken on an anon_vma when there is no
 	 * guarantee that the vma of page tables will exist for
@@ -64,7 +64,7 @@ struct anon_vma_chain {
 	struct vm_area_struct *vma;
 	struct anon_vma *anon_vma;
 	struct list_head same_vma;   /* locked by mmap_sem & page_table_lock */
-	struct rb_node rb;			/* locked by anon_vma->mutex */
+	struct rb_node rb;			/* locked by anon_vma->rwsem */
 	unsigned long rb_subtree_last;
 #ifdef CONFIG_DEBUG_VM_RB
 	unsigned long cached_vma_start, cached_vma_last;
@@ -108,24 +108,24 @@ static inline void vma_lock_anon_vma(struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	if (anon_vma)
-		mutex_lock(&anon_vma->root->mutex);
+		down_write(&anon_vma->root->rwsem);
 }
 
 static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	if (anon_vma)
-		mutex_unlock(&anon_vma->root->mutex);
+		up_write(&anon_vma->root->rwsem);
 }
 
 static inline void anon_vma_lock(struct anon_vma *anon_vma)
 {
-	mutex_lock(&anon_vma->root->mutex);
+	down_write(&anon_vma->root->rwsem);
 }
 
 static inline void anon_vma_unlock(struct anon_vma *anon_vma)
 {
-	mutex_unlock(&anon_vma->root->mutex);
+	up_write(&anon_vma->root->rwsem);
 }
 
 /*
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 711baf84b153..acd37fe55eb7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1292,7 +1292,7 @@ static int __split_huge_page_splitting(struct page *page,
 		 * We can't temporarily set the pmd to null in order
 		 * to split it, the pmd must remain marked huge at all
 		 * times or the VM won't take the pmd_trans_huge paths
-		 * and it won't wait on the anon_vma->root->mutex to
+		 * and it won't wait on the anon_vma->root->rwsem to
 		 * serialize against split_huge_page*.
 		 */
 		pmdp_splitting_flush(vma, address, pmd);
@@ -1495,7 +1495,7 @@ static int __split_huge_page_map(struct page *page,
 	return ret;
 }
 
-/* must be called with anon_vma->root->mutex hold */
+/* must be called with anon_vma->root->rwsem held */
 static void __split_huge_page(struct page *page,
 			      struct anon_vma *anon_vma)
 {
diff --git a/mm/mmap.c b/mm/mmap.c
index 9a796c41e7d9..88408632da66 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2561,15 +2561,15 @@ static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
 		 * The LSB of head.next can't change from under us
 		 * because we hold the mm_all_locks_mutex.
 		 */
-		mutex_lock_nest_lock(&anon_vma->root->mutex, &mm->mmap_sem);
+		down_write(&anon_vma->root->rwsem);
 		/*
 		 * We can safely modify head.next after taking the
-		 * anon_vma->root->mutex. If some other vma in this mm shares
+		 * anon_vma->root->rwsem. If some other vma in this mm shares
 		 * the same anon_vma we won't take it again.
 		 *
 		 * No need of atomic instructions here, head.next
 		 * can't change from under us thanks to the
-		 * anon_vma->root->mutex.
+		 * anon_vma->root->rwsem.
 		 */
 		if (__test_and_set_bit(0, (unsigned long *)
 				       &anon_vma->root->rb_root.rb_node))
@@ -2671,7 +2671,7 @@ static void vm_unlock_anon_vma(struct anon_vma *anon_vma)
 		 *
 		 * No need of atomic instructions here, head.next
 		 * can't change from under us until we release the
-		 * anon_vma->root->mutex.
+		 * anon_vma->root->rwsem.
 		 */
 		if (!__test_and_clear_bit(0, (unsigned long *)
 					  &anon_vma->root->rb_root.rb_node))
diff --git a/mm/rmap.c b/mm/rmap.c
index 2ee1ef0f317b..6e3ee3b82798 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -24,7 +24,7 @@
  *   mm->mmap_sem
  *     page->flags PG_locked (lock_page)
  *       mapping->i_mmap_mutex
- *         anon_vma->mutex
+ *         anon_vma->rwsem
  *           mm->page_table_lock or pte_lock
  *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
  *             swap_lock (in swap_duplicate, swap_info_get)
@@ -37,7 +37,7 @@
  *                           in arch-dependent flush_dcache_mmap_lock,
  *                           within bdi.wb->list_lock in __sync_single_inode)
  *
- * anon_vma->mutex,mapping->i_mutex      (memory_failure, collect_procs_anon)
+ * anon_vma->rwsem,mapping->i_mutex      (memory_failure, collect_procs_anon)
  *   ->tasklist_lock
  *     pte map lock
  */
@@ -103,7 +103,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma)
 	 * LOCK should suffice since the actual taking of the lock must
 	 * happen _before_ what follows.
 	 */
-	if (mutex_is_locked(&anon_vma->root->mutex)) {
+	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
 		anon_vma_lock(anon_vma);
 		anon_vma_unlock(anon_vma);
 	}
@@ -219,9 +219,9 @@ static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct
 	struct anon_vma *new_root = anon_vma->root;
 	if (new_root != root) {
 		if (WARN_ON_ONCE(root))
-			mutex_unlock(&root->mutex);
+			up_write(&root->rwsem);
 		root = new_root;
-		mutex_lock(&root->mutex);
+		down_write(&root->rwsem);
 	}
 	return root;
 }
@@ -229,7 +229,7 @@ static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct
 static inline void unlock_anon_vma_root(struct anon_vma *root)
 {
 	if (root)
-		mutex_unlock(&root->mutex);
+		up_write(&root->rwsem);
 }
 
 /*
@@ -349,7 +349,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 	/*
 	 * Iterate the list once more, it now only contains empty and unlinked
 	 * anon_vmas, destroy them. Could not do before due to __put_anon_vma()
-	 * needing to acquire the anon_vma->root->mutex.
+	 * needing to write-acquire the anon_vma->root->rwsem.
 	 */
 	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
 		struct anon_vma *anon_vma = avc->anon_vma;
@@ -365,7 +365,7 @@ static void anon_vma_ctor(void *data)
 {
 	struct anon_vma *anon_vma = data;
 
-	mutex_init(&anon_vma->mutex);
+	init_rwsem(&anon_vma->rwsem);
 	atomic_set(&anon_vma->refcount, 0);
 	anon_vma->rb_root = RB_ROOT;
 }
@@ -457,14 +457,14 @@ struct anon_vma *page_lock_anon_vma(struct page *page)
 
 	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
 	root_anon_vma = ACCESS_ONCE(anon_vma->root);
-	if (mutex_trylock(&root_anon_vma->mutex)) {
+	if (down_write_trylock(&root_anon_vma->rwsem)) {
 		/*
 		 * If the page is still mapped, then this anon_vma is still
 		 * its anon_vma, and holding the mutex ensures that it will
 		 * not go away, see anon_vma_free().
 		 */
 		if (!page_mapped(page)) {
-			mutex_unlock(&root_anon_vma->mutex);
+			up_write(&root_anon_vma->rwsem);
 			anon_vma = NULL;
 		}
 		goto out;
@@ -1299,7 +1299,7 @@ out_mlock:
 	/*
 	 * We need mmap_sem locking, Otherwise VM_LOCKED check makes
 	 * unstable result and race. Plus, We can't wait here because
-	 * we now hold anon_vma->mutex or mapping->i_mmap_mutex.
+	 * we now hold anon_vma->rwsem or mapping->i_mmap_mutex.
 	 * if trylock failed, the page remain in evictable lru and later
 	 * vmscan could retry to move the page to unevictable lru if the
 	 * page is actually mlocked.
-- 
cgit v1.2.3-55-g7522


From 4fc3f1d66b1ef0d7b8dc11f4ff1cc510f78b37d6 Mon Sep 17 00:00:00 2001
From: Ingo Molnar
Date: Sun, 2 Dec 2012 19:56:50 +0000
Subject: mm/rmap, migration: Make rmap_walk_anon() and try_to_unmap_anon()
 more scalable

rmap_walk_anon() and try_to_unmap_anon() appears to be too
careful about locking the anon vma: while it needs protection
against anon vma list modifications, it does not need exclusive
access to the list itself.

Transforming this exclusive lock to a read-locked rwsem removes
a global lock from the hot path of page-migration intense
threaded workloads which can cause pathological performance like
this:

    96.43%        process 0  [kernel.kallsyms]  [k] perf_trace_sched_switch
                  |
                  --- perf_trace_sched_switch
                      __schedule
                      schedule
                      schedule_preempt_disabled
                      __mutex_lock_common.isra.6
                      __mutex_lock_slowpath
                      mutex_lock
                     |
                     |--50.61%-- rmap_walk
                     |          move_to_new_page
                     |          migrate_pages
                     |          migrate_misplaced_page
                     |          __do_numa_page.isra.69
                     |          handle_pte_fault
                     |          handle_mm_fault
                     |          __do_page_fault
                     |          do_page_fault
                     |          page_fault
                     |          __memset_sse2
                     |          |
                     |           --100.00%-- worker_thread
                     |                     |
                     |                      --100.00%-- start_thread
                     |
                      --49.39%-- page_lock_anon_vma
                                try_to_unmap_anon
                                try_to_unmap
                                migrate_pages
                                migrate_misplaced_page
                                __do_numa_page.isra.69
                                handle_pte_fault
                                handle_mm_fault
                                __do_page_fault
                                do_page_fault
                                page_fault
                                __memset_sse2
                                |
                                 --100.00%-- worker_thread
                                           start_thread

With this change applied the profile is now nicely flat
and there's no anon-vma related scheduling/blocking.

Rename anon_vma_[un]lock() => anon_vma_[un]lock_write(),
to make it clearer that it's an exclusive write-lock in
that case - suggested by Rik van Riel.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Turner <pjt@google.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/huge_mm.h |  2 +-
 include/linux/rmap.h    | 17 ++++++++++++++---
 mm/huge_memory.c        |  6 +++---
 mm/ksm.c                |  6 +++---
 mm/memory-failure.c     |  4 ++--
 mm/migrate.c            |  2 +-
 mm/mmap.c               |  2 +-
 mm/mremap.c             |  2 +-
 mm/rmap.c               | 48 ++++++++++++++++++++++++------------------------
 9 files changed, 50 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 027ad04ef3a8..0d1208c0bdc4 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -102,7 +102,7 @@ extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd);
 #define wait_split_huge_page(__anon_vma, __pmd)				\
 	do {								\
 		pmd_t *____pmd = (__pmd);				\
-		anon_vma_lock(__anon_vma);				\
+		anon_vma_lock_write(__anon_vma);			\
 		anon_vma_unlock(__anon_vma);				\
 		BUG_ON(pmd_trans_splitting(*____pmd) ||			\
 		       pmd_trans_huge(*____pmd));			\
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index f3f41d242e25..c20635c527a9 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -118,7 +118,7 @@ static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
 		up_write(&anon_vma->root->rwsem);
 }
 
-static inline void anon_vma_lock(struct anon_vma *anon_vma)
+static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
 {
 	down_write(&anon_vma->root->rwsem);
 }
@@ -128,6 +128,17 @@ static inline void anon_vma_unlock(struct anon_vma *anon_vma)
 	up_write(&anon_vma->root->rwsem);
 }
 
+static inline void anon_vma_lock_read(struct anon_vma *anon_vma)
+{
+	down_read(&anon_vma->root->rwsem);
+}
+
+static inline void anon_vma_unlock_read(struct anon_vma *anon_vma)
+{
+	up_read(&anon_vma->root->rwsem);
+}
+
+
 /*
  * anon_vma helper functions.
  */
@@ -220,8 +231,8 @@ int try_to_munlock(struct page *);
 /*
  * Called by memory-failure.c to kill processes.
  */
-struct anon_vma *page_lock_anon_vma(struct page *page);
-void page_unlock_anon_vma(struct anon_vma *anon_vma);
+struct anon_vma *page_lock_anon_vma_read(struct page *page);
+void page_unlock_anon_vma_read(struct anon_vma *anon_vma);
 int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
 
 /*
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index acd37fe55eb7..a24c9cb9c83e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1549,7 +1549,7 @@ int split_huge_page(struct page *page)
 	int ret = 1;
 
 	BUG_ON(!PageAnon(page));
-	anon_vma = page_lock_anon_vma(page);
+	anon_vma = page_lock_anon_vma_read(page);
 	if (!anon_vma)
 		goto out;
 	ret = 0;
@@ -1562,7 +1562,7 @@ int split_huge_page(struct page *page)
 
 	BUG_ON(PageCompound(page));
 out_unlock:
-	page_unlock_anon_vma(anon_vma);
+	page_unlock_anon_vma_read(anon_vma);
 out:
 	return ret;
 }
@@ -2074,7 +2074,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	if (!pmd_present(*pmd) || pmd_trans_huge(*pmd))
 		goto out;
 
-	anon_vma_lock(vma->anon_vma);
+	anon_vma_lock_write(vma->anon_vma);
 
 	pte = pte_offset_map(pmd, address);
 	ptl = pte_lockptr(mm, pmd);
diff --git a/mm/ksm.c b/mm/ksm.c
index ae539f0b8aa1..7fa37de1ee0c 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1634,7 +1634,7 @@ again:
 		struct anon_vma_chain *vmac;
 		struct vm_area_struct *vma;
 
-		anon_vma_lock(anon_vma);
+		anon_vma_lock_write(anon_vma);
 		anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
 					       0, ULONG_MAX) {
 			vma = vmac->vma;
@@ -1688,7 +1688,7 @@ again:
 		struct anon_vma_chain *vmac;
 		struct vm_area_struct *vma;
 
-		anon_vma_lock(anon_vma);
+		anon_vma_lock_write(anon_vma);
 		anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
 					       0, ULONG_MAX) {
 			vma = vmac->vma;
@@ -1741,7 +1741,7 @@ again:
 		struct anon_vma_chain *vmac;
 		struct vm_area_struct *vma;
 
-		anon_vma_lock(anon_vma);
+		anon_vma_lock_write(anon_vma);
 		anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
 					       0, ULONG_MAX) {
 			vma = vmac->vma;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ddb68a169e45..f2cd830f66c0 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -402,7 +402,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	struct anon_vma *av;
 	pgoff_t pgoff;
 
-	av = page_lock_anon_vma(page);
+	av = page_lock_anon_vma_read(page);
 	if (av == NULL)	/* Not actually mapped anymore */
 		return;
 
@@ -423,7 +423,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 		}
 	}
 	read_unlock(&tasklist_lock);
-	page_unlock_anon_vma(av);
+	page_unlock_anon_vma_read(av);
 }
 
 /*
diff --git a/mm/migrate.c b/mm/migrate.c
index f24e9cc49cc4..6e46485f014c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -754,7 +754,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 	 */
 	if (PageAnon(page)) {
 		/*
-		 * Only page_lock_anon_vma() understands the subtleties of
+		 * Only page_lock_anon_vma_read() understands the subtleties of
 		 * getting a hold on an anon_vma from outside one of its mms.
 		 */
 		anon_vma = page_get_anon_vma(page);
diff --git a/mm/mmap.c b/mm/mmap.c
index 88408632da66..68a16b40c209 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -602,7 +602,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 	if (anon_vma) {
 		VM_BUG_ON(adjust_next && next->anon_vma &&
 			  anon_vma != next->anon_vma);
-		anon_vma_lock(anon_vma);
+		anon_vma_lock_write(anon_vma);
 		anon_vma_interval_tree_pre_update_vma(vma);
 		if (adjust_next)
 			anon_vma_interval_tree_pre_update_vma(next);
diff --git a/mm/mremap.c b/mm/mremap.c
index 1b61c2d3307a..3dabd170753a 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -104,7 +104,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		}
 		if (vma->anon_vma) {
 			anon_vma = vma->anon_vma;
-			anon_vma_lock(anon_vma);
+			anon_vma_lock_write(anon_vma);
 		}
 	}
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 6e3ee3b82798..b0f612df7b9d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -87,24 +87,24 @@ static inline void anon_vma_free(struct anon_vma *anon_vma)
 	VM_BUG_ON(atomic_read(&anon_vma->refcount));
 
 	/*
-	 * Synchronize against page_lock_anon_vma() such that
+	 * Synchronize against page_lock_anon_vma_read() such that
 	 * we can safely hold the lock without the anon_vma getting
 	 * freed.
 	 *
 	 * Relies on the full mb implied by the atomic_dec_and_test() from
 	 * put_anon_vma() against the acquire barrier implied by
-	 * mutex_trylock() from page_lock_anon_vma(). This orders:
+	 * down_read_trylock() from page_lock_anon_vma_read(). This orders:
 	 *
-	 * page_lock_anon_vma()		VS	put_anon_vma()
-	 *   mutex_trylock()			  atomic_dec_and_test()
+	 * page_lock_anon_vma_read()	VS	put_anon_vma()
+	 *   down_read_trylock()		  atomic_dec_and_test()
 	 *   LOCK				  MB
-	 *   atomic_read()			  mutex_is_locked()
+	 *   atomic_read()			  rwsem_is_locked()
 	 *
 	 * LOCK should suffice since the actual taking of the lock must
 	 * happen _before_ what follows.
 	 */
 	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
-		anon_vma_lock(anon_vma);
+		anon_vma_lock_write(anon_vma);
 		anon_vma_unlock(anon_vma);
 	}
 
@@ -146,7 +146,7 @@ static void anon_vma_chain_link(struct vm_area_struct *vma,
  * allocate a new one.
  *
  * Anon-vma allocations are very subtle, because we may have
- * optimistically looked up an anon_vma in page_lock_anon_vma()
+ * optimistically looked up an anon_vma in page_lock_anon_vma_read()
  * and that may actually touch the spinlock even in the newly
  * allocated vma (it depends on RCU to make sure that the
  * anon_vma isn't actually destroyed).
@@ -181,7 +181,7 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 			allocated = anon_vma;
 		}
 
-		anon_vma_lock(anon_vma);
+		anon_vma_lock_write(anon_vma);
 		/* page_table_lock to protect against threads */
 		spin_lock(&mm->page_table_lock);
 		if (likely(!vma->anon_vma)) {
@@ -306,7 +306,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	get_anon_vma(anon_vma->root);
 	/* Mark this anon_vma as the one where our new (COWed) pages go. */
 	vma->anon_vma = anon_vma;
-	anon_vma_lock(anon_vma);
+	anon_vma_lock_write(anon_vma);
 	anon_vma_chain_link(vma, avc, anon_vma);
 	anon_vma_unlock(anon_vma);
 
@@ -442,7 +442,7 @@ out:
  * atomic op -- the trylock. If we fail the trylock, we fall back to getting a
  * reference like with page_get_anon_vma() and then block on the mutex.
  */
-struct anon_vma *page_lock_anon_vma(struct page *page)
+struct anon_vma *page_lock_anon_vma_read(struct page *page)
 {
 	struct anon_vma *anon_vma = NULL;
 	struct anon_vma *root_anon_vma;
@@ -457,14 +457,14 @@ struct anon_vma *page_lock_anon_vma(struct page *page)
 
 	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
 	root_anon_vma = ACCESS_ONCE(anon_vma->root);
-	if (down_write_trylock(&root_anon_vma->rwsem)) {
+	if (down_read_trylock(&root_anon_vma->rwsem)) {
 		/*
 		 * If the page is still mapped, then this anon_vma is still
 		 * its anon_vma, and holding the mutex ensures that it will
 		 * not go away, see anon_vma_free().
 		 */
 		if (!page_mapped(page)) {
-			up_write(&root_anon_vma->rwsem);
+			up_read(&root_anon_vma->rwsem);
 			anon_vma = NULL;
 		}
 		goto out;
@@ -484,15 +484,15 @@ struct anon_vma *page_lock_anon_vma(struct page *page)
 
 	/* we pinned the anon_vma, its safe to sleep */
 	rcu_read_unlock();
-	anon_vma_lock(anon_vma);
+	anon_vma_lock_read(anon_vma);
 
 	if (atomic_dec_and_test(&anon_vma->refcount)) {
 		/*
 		 * Oops, we held the last refcount, release the lock
 		 * and bail -- can't simply use put_anon_vma() because
-		 * we'll deadlock on the anon_vma_lock() recursion.
+		 * we'll deadlock on the anon_vma_lock_write() recursion.
 		 */
-		anon_vma_unlock(anon_vma);
+		anon_vma_unlock_read(anon_vma);
 		__put_anon_vma(anon_vma);
 		anon_vma = NULL;
 	}
@@ -504,9 +504,9 @@ out:
 	return anon_vma;
 }
 
-void page_unlock_anon_vma(struct anon_vma *anon_vma)
+void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
 {
-	anon_vma_unlock(anon_vma);
+	anon_vma_unlock_read(anon_vma);
 }
 
 /*
@@ -732,7 +732,7 @@ static int page_referenced_anon(struct page *page,
 	struct anon_vma_chain *avc;
 	int referenced = 0;
 
-	anon_vma = page_lock_anon_vma(page);
+	anon_vma = page_lock_anon_vma_read(page);
 	if (!anon_vma)
 		return referenced;
 
@@ -754,7 +754,7 @@ static int page_referenced_anon(struct page *page,
 			break;
 	}
 
-	page_unlock_anon_vma(anon_vma);
+	page_unlock_anon_vma_read(anon_vma);
 	return referenced;
 }
 
@@ -1474,7 +1474,7 @@ static int try_to_unmap_anon(struct page *page, enum ttu_flags flags)
 	struct anon_vma_chain *avc;
 	int ret = SWAP_AGAIN;
 
-	anon_vma = page_lock_anon_vma(page);
+	anon_vma = page_lock_anon_vma_read(page);
 	if (!anon_vma)
 		return ret;
 
@@ -1501,7 +1501,7 @@ static int try_to_unmap_anon(struct page *page, enum ttu_flags flags)
 			break;
 	}
 
-	page_unlock_anon_vma(anon_vma);
+	page_unlock_anon_vma_read(anon_vma);
 	return ret;
 }
 
@@ -1696,7 +1696,7 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
 	int ret = SWAP_AGAIN;
 
 	/*
-	 * Note: remove_migration_ptes() cannot use page_lock_anon_vma()
+	 * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read()
 	 * because that depends on page_mapped(); but not all its usages
 	 * are holding mmap_sem. Users without mmap_sem are required to
 	 * take a reference count to prevent the anon_vma disappearing
@@ -1704,7 +1704,7 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
 	anon_vma = page_anon_vma(page);
 	if (!anon_vma)
 		return ret;
-	anon_vma_lock(anon_vma);
+	anon_vma_lock_read(anon_vma);
 	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
 		struct vm_area_struct *vma = avc->vma;
 		unsigned long address = vma_address(page, vma);
@@ -1712,7 +1712,7 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
 		if (ret != SWAP_AGAIN)
 			break;
 	}
-	anon_vma_unlock(anon_vma);
+	anon_vma_unlock_read(anon_vma);
 	return ret;
 }
 
-- 
cgit v1.2.3-55-g7522


From 1daa8a0b2000974e07eacbabecd61bccadc933b9 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski
Date: Mon, 10 Dec 2012 20:41:27 +0100
Subject: of/i2c: add dummy inline functions for when CONFIG_OF_I2C(_MODULE)
 isn't defined

If CONFIG_OF_I2C and CONFIG_OF_I2C_MODULE are undefined no declaration of
of_find_i2c_device_by_node and of_find_i2c_adapter_by_node will be
available. Add dummy inline functions to avoid compilation breakage.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 include/linux/of_i2c.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/linux/of_i2c.h b/include/linux/of_i2c.h
index 1cb775f8e663..cfb545cd86b5 100644
--- a/include/linux/of_i2c.h
+++ b/include/linux/of_i2c.h
@@ -29,6 +29,18 @@ static inline void of_i2c_register_devices(struct i2c_adapter *adap)
 {
 	return;
 }
+
+static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node)
+{
+	return NULL;
+}
+
+/* must call put_device() when done with returned i2c_adapter device */
+static inline struct i2c_adapter *of_find_i2c_adapter_by_node(
+						struct device_node *node)
+{
+	return NULL;
+}
 #endif /* CONFIG_OF_I2C */
 
 #endif /* __LINUX_OF_I2C_H */
-- 
cgit v1.2.3-55-g7522


From 93c667ca2598bd84f1bd3f2fa176af69707699fe Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski
Date: Mon, 10 Dec 2012 20:41:30 +0100
Subject: of: *node argument to of_parse_phandle_with_args should be const

The "struct device_node *" argument of of_parse_phandle_with_args() can
be const. Making this change makes it explicit that the function will
not modify a node.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
[grant.likely: Resolved conflict with previous patch modifying of_parse_phandle()]
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 drivers/of/base.c  | 2 +-
 include/linux/of.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index 538e3cfad23e..be846408dbc1 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1025,7 +1025,7 @@ EXPORT_SYMBOL(of_parse_phandle);
  * To get a device_node of the `node2' node you may call this:
  * of_parse_phandle_with_args(node3, "list", "#list-cells", 1, &args);
  */
-int of_parse_phandle_with_args(struct device_node *np, const char *list_name,
+int of_parse_phandle_with_args(const struct device_node *np, const char *list_name,
 				const char *cells_name, int index,
 				struct of_phandle_args *out_args)
 {
diff --git a/include/linux/of.h b/include/linux/of.h
index 60053bd7e79a..6cfea9aa401f 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -273,7 +273,7 @@ extern int of_modalias_node(struct device_node *node, char *modalias, int len);
 extern struct device_node *of_parse_phandle(const struct device_node *np,
 					    const char *phandle_name,
 					    int index);
-extern int of_parse_phandle_with_args(struct device_node *np,
+extern int of_parse_phandle_with_args(const struct device_node *np,
 	const char *list_name, const char *cells_name, int index,
 	struct of_phandle_args *out_args);
 
-- 
cgit v1.2.3-55-g7522


From f8e8f97c11d5ff3cc47d85b97c7c35e443dcf490 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Mon, 10 Dec 2012 12:32:03 +0000
Subject: net: fix a race in gro_cell_poll()

Dmitry Kravkov reported packet drops for GRE packets since GRO support
was added.

There is a race in gro_cell_poll() because we call napi_complete()
without any synchronization with a concurrent gro_cells_receive()

Once bug was triggered, we queued packets but did not schedule NAPI
poll.

We can fix this issue using the spinlock protected the napi_skbs queue,
as we have to hold it to perform skb dequeue anyway.

As we open-code skb_dequeue(), we no longer need to mask IRQS, as both
producer and consumer run under BH context.

Bug added in commit c9e6bc644e (net: add gro_cells infrastructure)

Reported-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gro_cells.h | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h
index 4fd8a4b4b7ee..e5062c955ea6 100644
--- a/include/net/gro_cells.h
+++ b/include/net/gro_cells.h
@@ -17,7 +17,6 @@ struct gro_cells {
 
 static inline void gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 {
-	unsigned long flags;
 	struct gro_cell *cell = gcells->cells;
 	struct net_device *dev = skb->dev;
 
@@ -35,32 +34,37 @@ static inline void gro_cells_receive(struct gro_cells *gcells, struct sk_buff *s
 		return;
 	}
 
-	spin_lock_irqsave(&cell->napi_skbs.lock, flags);
+	/* We run in BH context */
+	spin_lock(&cell->napi_skbs.lock);
 
 	__skb_queue_tail(&cell->napi_skbs, skb);
 	if (skb_queue_len(&cell->napi_skbs) == 1)
 		napi_schedule(&cell->napi);
 
-	spin_unlock_irqrestore(&cell->napi_skbs.lock, flags);
+	spin_unlock(&cell->napi_skbs.lock);
 }
 
+/* called unser BH context */
 static inline int gro_cell_poll(struct napi_struct *napi, int budget)
 {
 	struct gro_cell *cell = container_of(napi, struct gro_cell, napi);
 	struct sk_buff *skb;
 	int work_done = 0;
 
+	spin_lock(&cell->napi_skbs.lock);
 	while (work_done < budget) {
-		skb = skb_dequeue(&cell->napi_skbs);
+		skb = __skb_dequeue(&cell->napi_skbs);
 		if (!skb)
 			break;
-
+		spin_unlock(&cell->napi_skbs.lock);
 		napi_gro_receive(napi, skb);
 		work_done++;
+		spin_lock(&cell->napi_skbs.lock);
 	}
 
 	if (work_done < budget)
 		napi_complete(napi);
+	spin_unlock(&cell->napi_skbs.lock);
 	return work_done;
 }
 
-- 
cgit v1.2.3-55-g7522


From d8153d4d8b7b6141770e1416c4a338161205ed1b Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo
Date: Tue, 14 Jun 2011 17:29:45 +0200
Subject: inotify, fanotify: replace fsnotify_put_group() with
 fsnotify_destroy_group()

Currently in fsnotify_put_group() the ref count of a group is decremented and if
it becomes 0 fsnotify_destroy_group() is called. Since a groups ref count is only
at group creation set to 1 and never increased after that a call to fsnotify_put_group()
always results in a call to fsnotify_destroy_group().
With this patch fsnotify_destroy_group() is called directly.

Signed-off-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 fs/notify/fanotify/fanotify_user.c | 14 +++++++-------
 fs/notify/group.c                  |  2 +-
 fs/notify/inotify/inotify_user.c   |  8 +++-----
 include/linux/fsnotify_backend.h   |  3 ++-
 4 files changed, 13 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index d43803669739..82ae6d783c14 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -415,7 +415,7 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
 	/* matches the fanotify_init->fsnotify_alloc_group */
-	fsnotify_put_group(group);
+	fsnotify_destroy_group(group);
 
 	return 0;
 }
@@ -728,13 +728,13 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 		break;
 	default:
 		fd = -EINVAL;
-		goto out_put_group;
+		goto out_destroy_group;
 	}
 
 	if (flags & FAN_UNLIMITED_QUEUE) {
 		fd = -EPERM;
 		if (!capable(CAP_SYS_ADMIN))
-			goto out_put_group;
+			goto out_destroy_group;
 		group->max_events = UINT_MAX;
 	} else {
 		group->max_events = FANOTIFY_DEFAULT_MAX_EVENTS;
@@ -743,7 +743,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	if (flags & FAN_UNLIMITED_MARKS) {
 		fd = -EPERM;
 		if (!capable(CAP_SYS_ADMIN))
-			goto out_put_group;
+			goto out_destroy_group;
 		group->fanotify_data.max_marks = UINT_MAX;
 	} else {
 		group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS;
@@ -751,12 +751,12 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 
 	fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
 	if (fd < 0)
-		goto out_put_group;
+		goto out_destroy_group;
 
 	return fd;
 
-out_put_group:
-	fsnotify_put_group(group);
+out_destroy_group:
+	fsnotify_destroy_group(group);
 	return fd;
 }
 
diff --git a/fs/notify/group.c b/fs/notify/group.c
index 63fc294a4692..cfda328c3d11 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -50,7 +50,7 @@ void fsnotify_final_destroy_group(struct fsnotify_group *group)
  * situtation, the fsnotify_final_destroy_group will get called when that final
  * mark is freed.
  */
-static void fsnotify_destroy_group(struct fsnotify_group *group)
+void fsnotify_destroy_group(struct fsnotify_group *group)
 {
 	/* clear all inode marks for this group */
 	fsnotify_clear_marks_by_group(group);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 8445fbc8985c..dbafbfc8ceca 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -293,10 +293,8 @@ static int inotify_release(struct inode *ignored, struct file *file)
 
 	pr_debug("%s: group=%p\n", __func__, group);
 
-	fsnotify_clear_marks_by_group(group);
-
 	/* free this group, matching get was inotify_init->fsnotify_obtain_group */
-	fsnotify_put_group(group);
+	fsnotify_destroy_group(group);
 
 	return 0;
 }
@@ -712,7 +710,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 
 	if (atomic_inc_return(&group->inotify_data.user->inotify_devs) >
 	    inotify_max_user_instances) {
-		fsnotify_put_group(group);
+		fsnotify_destroy_group(group);
 		return ERR_PTR(-EMFILE);
 	}
 
@@ -741,7 +739,7 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
 	ret = anon_inode_getfd("inotify", &inotify_fops, group,
 				  O_RDONLY | flags);
 	if (ret < 0)
-		fsnotify_put_group(group);
+		fsnotify_destroy_group(group);
 
 	return ret;
 }
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 63d966d5c2ea..d2ad345bdeec 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -364,7 +364,8 @@ static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode
 extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops);
 /* drop reference on a group from fsnotify_alloc_group */
 extern void fsnotify_put_group(struct fsnotify_group *group);
-
+/* destroy group */
+extern void fsnotify_destroy_group(struct fsnotify_group *group);
 /* take a reference to an event */
 extern void fsnotify_get_event(struct fsnotify_event *event);
 extern void fsnotify_put_event(struct fsnotify_event *event);
-- 
cgit v1.2.3-55-g7522


From 986129520479d689962a42c31acdeaf854ac91f5 Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo
Date: Tue, 14 Jun 2011 17:29:46 +0200
Subject: fsnotify: introduce fsnotify_get_group()

Introduce fsnotify_get_group() which increments the reference counter of a group.

Signed-off-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 fs/notify/group.c                | 8 ++++++++
 include/linux/fsnotify_backend.h | 4 +++-
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/notify/group.c b/fs/notify/group.c
index cfda328c3d11..1d57c35f1043 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -62,6 +62,14 @@ void fsnotify_destroy_group(struct fsnotify_group *group)
 		fsnotify_final_destroy_group(group);
 }
 
+/*
+ * Get reference to a group.
+ */
+void fsnotify_get_group(struct fsnotify_group *group)
+{
+	atomic_inc(&group->refcnt);
+}
+
 /*
  * Drop a reference to a group.  Free it if it's through.
  */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index d2ad345bdeec..e76cef75295d 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -360,8 +360,10 @@ static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode
 
 /* called from fsnotify listeners, such as fanotify or dnotify */
 
-/* get a reference to an existing or create a new group */
+/* create a new group */
 extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops);
+/* get reference to a group */
+extern void fsnotify_get_group(struct fsnotify_group *group);
 /* drop reference on a group from fsnotify_alloc_group */
 extern void fsnotify_put_group(struct fsnotify_group *group);
 /* destroy group */
-- 
cgit v1.2.3-55-g7522


From 986ab09807ca9454c3f54aae4db7e1bb00daeed3 Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo
Date: Tue, 14 Jun 2011 17:29:50 +0200
Subject: fsnotify: use a mutex instead of a spinlock to protect a groups mark
 list

Replaces the groups mark_lock spinlock with a mutex. Using a mutex instead
of a spinlock results in more flexibility (i.e it allows to sleep while the
lock is held).

Signed-off-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 fs/notify/group.c                |  2 +-
 fs/notify/inode_mark.c           |  4 ++--
 fs/notify/mark.c                 | 18 +++++++++---------
 fs/notify/vfsmount_mark.c        |  4 ++--
 include/linux/fsnotify_backend.h |  2 +-
 5 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/notify/group.c b/fs/notify/group.c
index 354044c47e23..1f7305711fc9 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -95,7 +95,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
 	init_waitqueue_head(&group->notification_waitq);
 	group->max_events = UINT_MAX;
 
-	spin_lock_init(&group->mark_lock);
+	mutex_init(&group->mark_mutex);
 	INIT_LIST_HEAD(&group->marks_list);
 
 	group->ops = ops;
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index b13c00ac48eb..4e9071e37d5d 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -63,8 +63,8 @@ void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
 {
 	struct inode *inode = mark->i.inode;
 
+	BUG_ON(!mutex_is_locked(&mark->group->mark_mutex));
 	assert_spin_locked(&mark->lock);
-	assert_spin_locked(&mark->group->mark_lock);
 
 	spin_lock(&inode->i_lock);
 
@@ -191,8 +191,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 
 	mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
 
+	BUG_ON(!mutex_is_locked(&group->mark_mutex));
 	assert_spin_locked(&mark->lock);
-	assert_spin_locked(&group->mark_lock);
 
 	spin_lock(&inode->i_lock);
 
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 32447dc06c07..ab25b810b146 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -136,13 +136,13 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark)
 	group = mark->group;
 	spin_unlock(&mark->lock);
 
-	spin_lock(&group->mark_lock);
+	mutex_lock(&group->mark_mutex);
 	spin_lock(&mark->lock);
 
 	/* something else already called this function on this mark */
 	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
 		spin_unlock(&mark->lock);
-		spin_unlock(&group->mark_lock);
+		mutex_unlock(&group->mark_mutex);
 		goto put_group;
 	}
 
@@ -159,7 +159,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark)
 	list_del_init(&mark->g_list);
 
 	spin_unlock(&mark->lock);
-	spin_unlock(&group->mark_lock);
+	mutex_unlock(&group->mark_mutex);
 
 	spin_lock(&destroy_lock);
 	list_add(&mark->destroy_list, &destroy_list);
@@ -232,11 +232,11 @@ int fsnotify_add_mark(struct fsnotify_mark *mark,
 
 	/*
 	 * LOCKING ORDER!!!!
-	 * group->mark_lock
+	 * group->mark_mutex
 	 * mark->lock
 	 * inode->i_lock
 	 */
-	spin_lock(&group->mark_lock);
+	mutex_lock(&group->mark_mutex);
 
 	spin_lock(&mark->lock);
 	mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE;
@@ -263,7 +263,7 @@ int fsnotify_add_mark(struct fsnotify_mark *mark,
 	fsnotify_set_mark_mask_locked(mark, mark->mask);
 	spin_unlock(&mark->lock);
 
-	spin_unlock(&group->mark_lock);
+	mutex_unlock(&group->mark_mutex);
 
 	if (inode)
 		__fsnotify_update_child_dentry_flags(inode);
@@ -277,7 +277,7 @@ err:
 	atomic_dec(&group->num_marks);
 
 	spin_unlock(&mark->lock);
-	spin_unlock(&group->mark_lock);
+	mutex_unlock(&group->mark_mutex);
 
 	spin_lock(&destroy_lock);
 	list_add(&mark->destroy_list, &destroy_list);
@@ -296,7 +296,7 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 	struct fsnotify_mark *lmark, *mark;
 	LIST_HEAD(free_list);
 
-	spin_lock(&group->mark_lock);
+	mutex_lock(&group->mark_mutex);
 	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
 		if (mark->flags & flags) {
 			list_add(&mark->free_g_list, &free_list);
@@ -304,7 +304,7 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 			fsnotify_get_mark(mark);
 		}
 	}
-	spin_unlock(&group->mark_lock);
+	mutex_unlock(&group->mark_mutex);
 
 	list_for_each_entry_safe(mark, lmark, &free_list, free_g_list) {
 		fsnotify_destroy_mark(mark);
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index b7b4b0e8554f..f26a348827f8 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -88,8 +88,8 @@ void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark)
 {
 	struct vfsmount *mnt = mark->m.mnt;
 
+	BUG_ON(!mutex_is_locked(&mark->group->mark_mutex));
 	assert_spin_locked(&mark->lock);
-	assert_spin_locked(&mark->group->mark_lock);
 
 	spin_lock(&mnt->mnt_root->d_lock);
 
@@ -151,8 +151,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 
 	mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
 
+	BUG_ON(!mutex_is_locked(&group->mark_mutex));
 	assert_spin_locked(&mark->lock);
-	assert_spin_locked(&group->mark_lock);
 
 	spin_lock(&mnt->mnt_root->d_lock);
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index e76cef75295d..c5848346840d 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -141,7 +141,7 @@ struct fsnotify_group {
 	unsigned int priority;
 
 	/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
-	spinlock_t mark_lock;		/* protect marks_list */
+	struct mutex mark_mutex;	/* protect marks_list */
 	atomic_t num_marks;		/* 1 for each mark and 1 for not being
 					 * past the point of no return when freeing
 					 * a group */
-- 
cgit v1.2.3-55-g7522


From e2a29943e9a2ee2aa737a77f550f46ba72269db4 Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo
Date: Tue, 14 Jun 2011 17:29:51 +0200
Subject: fsnotify: pass group to fsnotify_destroy_mark()

In fsnotify_destroy_mark() dont get the group from the passed mark anymore,
but pass the group itself as an additional parameter to the function.

Signed-off-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 fs/notify/dnotify/dnotify.c          |  4 ++--
 fs/notify/fanotify/fanotify_user.c   |  4 ++--
 fs/notify/inode_mark.c               | 10 +++++++++-
 fs/notify/inotify/inotify_fsnotify.c |  2 +-
 fs/notify/inotify/inotify_user.c     |  2 +-
 fs/notify/mark.c                     | 21 ++++-----------------
 fs/notify/vfsmount_mark.c            | 10 +++++++++-
 include/linux/fsnotify_backend.h     |  5 +++--
 kernel/audit_tree.c                  | 10 +++++-----
 kernel/audit_watch.c                 |  4 ++--
 10 files changed, 38 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 3344bdd5506e..08b886f119ce 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -201,7 +201,7 @@ void dnotify_flush(struct file *filp, fl_owner_t id)
 
 	/* nothing else could have found us thanks to the dnotify_mark_mutex */
 	if (dn_mark->dn == NULL)
-		fsnotify_destroy_mark(fsn_mark);
+		fsnotify_destroy_mark(fsn_mark, dnotify_group);
 
 	mutex_unlock(&dnotify_mark_mutex);
 
@@ -385,7 +385,7 @@ out:
 	spin_unlock(&fsn_mark->lock);
 
 	if (destroy)
-		fsnotify_destroy_mark(fsn_mark);
+		fsnotify_destroy_mark(fsn_mark, dnotify_group);
 
 	mutex_unlock(&dnotify_mark_mutex);
 	fsnotify_put_mark(fsn_mark);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 599a01952c74..1218d10424d0 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -546,7 +546,7 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
 	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
 						 &destroy_mark);
 	if (destroy_mark)
-		fsnotify_destroy_mark(fsn_mark);
+		fsnotify_destroy_mark(fsn_mark, group);
 
 	fsnotify_put_mark(fsn_mark);
 	if (removed & real_mount(mnt)->mnt_fsnotify_mask)
@@ -570,7 +570,7 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
 	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
 						 &destroy_mark);
 	if (destroy_mark)
-		fsnotify_destroy_mark(fsn_mark);
+		fsnotify_destroy_mark(fsn_mark, group);
 	/* matches the fsnotify_find_inode_mark() */
 	fsnotify_put_mark(fsn_mark);
 	if (removed & inode->i_fsnotify_mask)
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index 4e9071e37d5d..21230209c957 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -99,8 +99,16 @@ void fsnotify_clear_marks_by_inode(struct inode *inode)
 	spin_unlock(&inode->i_lock);
 
 	list_for_each_entry_safe(mark, lmark, &free_list, i.free_i_list) {
-		fsnotify_destroy_mark(mark);
+		struct fsnotify_group *group;
+
+		spin_lock(&mark->lock);
+		fsnotify_get_group(mark->group);
+		group = mark->group;
+		spin_unlock(&mark->lock);
+
+		fsnotify_destroy_mark(mark, group);
 		fsnotify_put_mark(mark);
+		fsnotify_put_group(group);
 	}
 }
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 74977fbf5aae..871569c7d609 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -132,7 +132,7 @@ static int inotify_handle_event(struct fsnotify_group *group,
 	}
 
 	if (inode_mark->mask & IN_ONESHOT)
-		fsnotify_destroy_mark(inode_mark);
+		fsnotify_destroy_mark(inode_mark, group);
 
 	return ret;
 }
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 246250f1db7a..00ff82ff7c9f 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -816,7 +816,7 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
 
 	ret = 0;
 
-	fsnotify_destroy_mark(&i_mark->fsn_mark);
+	fsnotify_destroy_mark(&i_mark->fsn_mark, group);
 
 	/* match ref taken by inotify_idr_find */
 	fsnotify_put_mark(&i_mark->fsn_mark);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index ab25b810b146..b77c833c8d0a 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -121,21 +121,11 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
  * The caller had better be holding a reference to this mark so we don't actually
  * do the final put under the mark->lock
  */
-void fsnotify_destroy_mark(struct fsnotify_mark *mark)
+void fsnotify_destroy_mark(struct fsnotify_mark *mark,
+			   struct fsnotify_group *group)
 {
-	struct fsnotify_group *group;
 	struct inode *inode = NULL;
 
-	spin_lock(&mark->lock);
-	/* dont get the group from a mark that is not alive yet */
-	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
-		spin_unlock(&mark->lock);
-		return;
-	}
-	fsnotify_get_group(mark->group);
-	group = mark->group;
-	spin_unlock(&mark->lock);
-
 	mutex_lock(&group->mark_mutex);
 	spin_lock(&mark->lock);
 
@@ -143,7 +133,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark)
 	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
 		spin_unlock(&mark->lock);
 		mutex_unlock(&group->mark_mutex);
-		goto put_group;
+		return;
 	}
 
 	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
@@ -194,9 +184,6 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark)
 	 */
 
 	atomic_dec(&group->num_marks);
-
-put_group:
-	fsnotify_put_group(group);
 }
 
 void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
@@ -307,7 +294,7 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 	mutex_unlock(&group->mark_mutex);
 
 	list_for_each_entry_safe(mark, lmark, &free_list, free_g_list) {
-		fsnotify_destroy_mark(mark);
+		fsnotify_destroy_mark(mark, group);
 		fsnotify_put_mark(mark);
 	}
 }
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index f26a348827f8..4df58b8ea64a 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -46,8 +46,16 @@ void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
 	spin_unlock(&mnt->mnt_root->d_lock);
 
 	list_for_each_entry_safe(mark, lmark, &free_list, m.free_m_list) {
-		fsnotify_destroy_mark(mark);
+		struct fsnotify_group *group;
+
+		spin_lock(&mark->lock);
+		fsnotify_get_group(mark->group);
+		group = mark->group;
+		spin_unlock(&mark->lock);
+
+		fsnotify_destroy_mark(mark, group);
 		fsnotify_put_mark(mark);
+		fsnotify_put_group(group);
 	}
 }
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index c5848346840d..140b4b8a100b 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -408,8 +408,9 @@ extern void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask
 /* attach the mark to both the group and the inode */
 extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
 			     struct inode *inode, struct vfsmount *mnt, int allow_dups);
-/* given a mark, flag it to be freed when all references are dropped */
-extern void fsnotify_destroy_mark(struct fsnotify_mark *mark);
+/* given a group and a mark, flag mark to be freed when all references are dropped */
+extern void fsnotify_destroy_mark(struct fsnotify_mark *mark,
+				  struct fsnotify_group *group);
 /* run all the marks in a group, and clear all of the vfsmount marks */
 extern void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group);
 /* run all the marks in a group, and clear all of the inode marks */
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index ed206fd88cca..e81175ef25f8 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -249,7 +249,7 @@ static void untag_chunk(struct node *p)
 		list_del_rcu(&chunk->hash);
 		spin_unlock(&hash_lock);
 		spin_unlock(&entry->lock);
-		fsnotify_destroy_mark(entry);
+		fsnotify_destroy_mark(entry, audit_tree_group);
 		goto out;
 	}
 
@@ -291,7 +291,7 @@ static void untag_chunk(struct node *p)
 		owner->root = new;
 	spin_unlock(&hash_lock);
 	spin_unlock(&entry->lock);
-	fsnotify_destroy_mark(entry);
+	fsnotify_destroy_mark(entry, audit_tree_group);
 	fsnotify_put_mark(&new->mark);	/* drop initial reference */
 	goto out;
 
@@ -331,7 +331,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree)
 		spin_unlock(&hash_lock);
 		chunk->dead = 1;
 		spin_unlock(&entry->lock);
-		fsnotify_destroy_mark(entry);
+		fsnotify_destroy_mark(entry, audit_tree_group);
 		fsnotify_put_mark(entry);
 		return 0;
 	}
@@ -412,7 +412,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 		spin_unlock(&chunk_entry->lock);
 		spin_unlock(&old_entry->lock);
 
-		fsnotify_destroy_mark(chunk_entry);
+		fsnotify_destroy_mark(chunk_entry, audit_tree_group);
 
 		fsnotify_put_mark(chunk_entry);
 		fsnotify_put_mark(old_entry);
@@ -443,7 +443,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	spin_unlock(&hash_lock);
 	spin_unlock(&chunk_entry->lock);
 	spin_unlock(&old_entry->lock);
-	fsnotify_destroy_mark(old_entry);
+	fsnotify_destroy_mark(old_entry, audit_tree_group);
 	fsnotify_put_mark(chunk_entry);	/* drop initial reference */
 	fsnotify_put_mark(old_entry); /* pair to fsnotify_find mark_entry */
 	return 0;
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 3823281401b5..a66affc1c12c 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -349,7 +349,7 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 	}
 	mutex_unlock(&audit_filter_mutex);
 
-	fsnotify_destroy_mark(&parent->mark);
+	fsnotify_destroy_mark(&parent->mark, audit_watch_group);
 }
 
 /* Get path information necessary for adding watches. */
@@ -456,7 +456,7 @@ void audit_remove_watch_rule(struct audit_krule *krule)
 
 		if (list_empty(&parent->watches)) {
 			audit_get_parent(parent);
-			fsnotify_destroy_mark(&parent->mark);
+			fsnotify_destroy_mark(&parent->mark, audit_watch_group);
 			audit_put_parent(parent);
 		}
 	}
-- 
cgit v1.2.3-55-g7522


From d5a335b845792d2a69ed1e244c0b233117b7db3c Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo
Date: Tue, 14 Jun 2011 17:29:52 +0200
Subject: fsnotify: introduce locked versions of fsnotify_add_mark() and
 fsnotify_remove_mark()

This patch introduces fsnotify_add_mark_locked() and fsnotify_remove_mark_locked()
which are essentially the same as fsnotify_add_mark() and fsnotify_remove_mark() but
assume that the caller has already taken the groups mark mutex.

Signed-off-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 fs/notify/mark.c                 | 42 ++++++++++++++++++++++++++++------------
 include/linux/fsnotify_backend.h |  4 ++++
 2 files changed, 34 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index b77c833c8d0a..f9dda0304a10 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -121,18 +121,18 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
  * The caller had better be holding a reference to this mark so we don't actually
  * do the final put under the mark->lock
  */
-void fsnotify_destroy_mark(struct fsnotify_mark *mark,
-			   struct fsnotify_group *group)
+void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
+				  struct fsnotify_group *group)
 {
 	struct inode *inode = NULL;
 
-	mutex_lock(&group->mark_mutex);
+	BUG_ON(!mutex_is_locked(&group->mark_mutex));
+
 	spin_lock(&mark->lock);
 
 	/* something else already called this function on this mark */
 	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
 		spin_unlock(&mark->lock);
-		mutex_unlock(&group->mark_mutex);
 		return;
 	}
 
@@ -149,6 +149,8 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 	list_del_init(&mark->g_list);
 
 	spin_unlock(&mark->lock);
+
+	/* release lock temporarily */
 	mutex_unlock(&group->mark_mutex);
 
 	spin_lock(&destroy_lock);
@@ -184,6 +186,16 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 	 */
 
 	atomic_dec(&group->num_marks);
+
+	mutex_lock(&group->mark_mutex);
+}
+
+void fsnotify_destroy_mark(struct fsnotify_mark *mark,
+			   struct fsnotify_group *group)
+{
+	mutex_lock(&group->mark_mutex);
+	fsnotify_destroy_mark_locked(mark, group);
+	mutex_unlock(&group->mark_mutex);
 }
 
 void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
@@ -208,14 +220,15 @@ void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mas
  * These marks may be used for the fsnotify backend to determine which
  * event types should be delivered to which group.
  */
-int fsnotify_add_mark(struct fsnotify_mark *mark,
-		      struct fsnotify_group *group, struct inode *inode,
-		      struct vfsmount *mnt, int allow_dups)
+int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
+			     struct fsnotify_group *group, struct inode *inode,
+			     struct vfsmount *mnt, int allow_dups)
 {
 	int ret = 0;
 
 	BUG_ON(inode && mnt);
 	BUG_ON(!inode && !mnt);
+	BUG_ON(!mutex_is_locked(&group->mark_mutex));
 
 	/*
 	 * LOCKING ORDER!!!!
@@ -223,8 +236,6 @@ int fsnotify_add_mark(struct fsnotify_mark *mark,
 	 * mark->lock
 	 * inode->i_lock
 	 */
-	mutex_lock(&group->mark_mutex);
-
 	spin_lock(&mark->lock);
 	mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE;
 
@@ -250,8 +261,6 @@ int fsnotify_add_mark(struct fsnotify_mark *mark,
 	fsnotify_set_mark_mask_locked(mark, mark->mask);
 	spin_unlock(&mark->lock);
 
-	mutex_unlock(&group->mark_mutex);
-
 	if (inode)
 		__fsnotify_update_child_dentry_flags(inode);
 
@@ -264,7 +273,6 @@ err:
 	atomic_dec(&group->num_marks);
 
 	spin_unlock(&mark->lock);
-	mutex_unlock(&group->mark_mutex);
 
 	spin_lock(&destroy_lock);
 	list_add(&mark->destroy_list, &destroy_list);
@@ -274,6 +282,16 @@ err:
 	return ret;
 }
 
+int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
+		      struct inode *inode, struct vfsmount *mnt, int allow_dups)
+{
+	int ret;
+	mutex_lock(&group->mark_mutex);
+	ret = fsnotify_add_mark_locked(mark, group, inode, mnt, allow_dups);
+	mutex_unlock(&group->mark_mutex);
+	return ret;
+}
+
 /*
  * clear any marks in a group in which mark->flags & flags is true
  */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 140b4b8a100b..26c06afa264e 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -408,9 +408,13 @@ extern void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask
 /* attach the mark to both the group and the inode */
 extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
 			     struct inode *inode, struct vfsmount *mnt, int allow_dups);
+extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, struct fsnotify_group *group,
+				    struct inode *inode, struct vfsmount *mnt, int allow_dups);
 /* given a group and a mark, flag mark to be freed when all references are dropped */
 extern void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 				  struct fsnotify_group *group);
+extern void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
+					 struct fsnotify_group *group);
 /* run all the marks in a group, and clear all of the vfsmount marks */
 extern void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group);
 /* run all the marks in a group, and clear all of the inode marks */
-- 
cgit v1.2.3-55-g7522


From 64c20d2a20fce295c260ea6cb3b468edfa2fb07b Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo
Date: Tue, 14 Jun 2011 17:29:53 +0200
Subject: fsnotify: dont put marks on temporary list when clearing marks by
 group

In clear_marks_by_group_flags() the mark list of a group is iterated and the
marks are put on a temporary list.
Since we introduced fsnotify_destroy_mark_locked() we dont need the temp list
any more and are able to remove the marks while the mark list is iterated and
the mark list mutex is held.

Signed-off-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 fs/notify/mark.c                 | 10 ++--------
 include/linux/fsnotify_backend.h |  1 -
 2 files changed, 2 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index f9dda0304a10..0e93d90bb753 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -299,22 +299,16 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 					 unsigned int flags)
 {
 	struct fsnotify_mark *lmark, *mark;
-	LIST_HEAD(free_list);
 
 	mutex_lock(&group->mark_mutex);
 	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
 		if (mark->flags & flags) {
-			list_add(&mark->free_g_list, &free_list);
-			list_del_init(&mark->g_list);
 			fsnotify_get_mark(mark);
+			fsnotify_destroy_mark_locked(mark, group);
+			fsnotify_put_mark(mark);
 		}
 	}
 	mutex_unlock(&group->mark_mutex);
-
-	list_for_each_entry_safe(mark, lmark, &free_list, free_g_list) {
-		fsnotify_destroy_mark(mark, group);
-		fsnotify_put_mark(mark);
-	}
 }
 
 /*
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 26c06afa264e..5a8899350456 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -287,7 +287,6 @@ struct fsnotify_mark {
 		struct fsnotify_inode_mark i;
 		struct fsnotify_vfsmount_mark m;
 	};
-	struct list_head free_g_list;	/* tmp list used when freeing this mark */
 	__u32 ignored_mask;		/* events types to ignore */
 #define FSNOTIFY_MARK_FLAG_INODE		0x01
 #define FSNOTIFY_MARK_FLAG_VFSMOUNT		0x02
-- 
cgit v1.2.3-55-g7522


From 6960b0d909cde5bdff49e4e5c1250edd10be7ebd Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo
Date: Fri, 12 Aug 2011 01:13:31 +0200
Subject: fsnotify: change locking order

On Mon, Aug 01, 2011 at 04:38:22PM -0400, Eric Paris wrote:
>
> I finally built and tested a v3.0 kernel with these patches (I know I'm
> SOOOOOO far behind).  Not what I hoped for:
>
> > [  150.937798] VFS: Busy inodes after unmount of tmpfs. Self-destruct in 5 seconds.  Have a nice day...
> > [  150.945290] BUG: unable to handle kernel NULL pointer dereference at 0000000000000070
> > [  150.946012] IP: [<ffffffff810ffd58>] shmem_free_inode+0x18/0x50
> > [  150.946012] PGD 2bf9e067 PUD 2bf9f067 PMD 0
> > [  150.946012] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
> > [  150.946012] CPU 0
> > [  150.946012] Modules linked in: nfs lockd fscache auth_rpcgss nfs_acl sunrpc ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_filter ip6_tables ext4 jbd2 crc16 joydev ata_piix i2c_piix4 pcspkr uinput ipv6 autofs4 usbhid [last unloaded: scsi_wait_scan]
> > [  150.946012]
> > [  150.946012] Pid: 2764, comm: syscall_thrash Not tainted 3.0.0+ #1 Red Hat KVM
> > [  150.946012] RIP: 0010:[<ffffffff810ffd58>]  [<ffffffff810ffd58>] shmem_free_inode+0x18/0x50
> > [  150.946012] RSP: 0018:ffff88002c2e5df8  EFLAGS: 00010282
> > [  150.946012] RAX: 000000004e370d9f RBX: 0000000000000000 RCX: ffff88003a029438
> > [  150.946012] RDX: 0000000033630a5f RSI: 0000000000000000 RDI: ffff88003491c240
> > [  150.946012] RBP: ffff88002c2e5e08 R08: 0000000000000000 R09: 0000000000000000
> > [  150.946012] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88003a029428
> > [  150.946012] R13: ffff88003a029428 R14: ffff88003a029428 R15: ffff88003499a610
> > [  150.946012] FS:  00007f5a05420700(0000) GS:ffff88003f600000(0000) knlGS:0000000000000000
> > [  150.946012] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> > [  150.946012] CR2: 0000000000000070 CR3: 000000002a662000 CR4: 00000000000006f0
> > [  150.946012] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> > [  150.946012] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
> > [  150.946012] Process syscall_thrash (pid: 2764, threadinfo ffff88002c2e4000, task ffff88002bfbc760)
> > [  150.946012] Stack:
> > [  150.946012]  ffff88003a029438 ffff88003a029428 ffff88002c2e5e38 ffffffff81102f76
> > [  150.946012]  ffff88003a029438 ffff88003a029598 ffffffff8160f9c0 ffff88002c221250
> > [  150.946012]  ffff88002c2e5e68 ffffffff8115e9be ffff88002c2e5e68 ffff88003a029438
> > [  150.946012] Call Trace:
> > [  150.946012]  [<ffffffff81102f76>] shmem_evict_inode+0x76/0x130
> > [  150.946012]  [<ffffffff8115e9be>] evict+0x7e/0x170
> > [  150.946012]  [<ffffffff8115ee40>] iput_final+0xd0/0x190
> > [  150.946012]  [<ffffffff8115ef33>] iput+0x33/0x40
> > [  150.946012]  [<ffffffff81180205>] fsnotify_destroy_mark_locked+0x145/0x160
> > [  150.946012]  [<ffffffff81180316>] fsnotify_destroy_mark+0x36/0x50
> > [  150.946012]  [<ffffffff81181937>] sys_inotify_rm_watch+0x77/0xd0
> > [  150.946012]  [<ffffffff815aca52>] system_call_fastpath+0x16/0x1b
> > [  150.946012] Code: 67 4a 00 b8 e4 ff ff ff eb aa 66 0f 1f 84 00 00 00 00 00 55 48 89 e5 48 83 ec 10 48 89 1c 24 4c 89 64 24 08 48 8b 9f 40 05 00 00
> > [  150.946012]  83 7b 70 00 74 1c 4c 8d a3 80 00 00 00 4c 89 e7 e8 d2 5d 4a
> > [  150.946012] RIP  [<ffffffff810ffd58>] shmem_free_inode+0x18/0x50
> > [  150.946012]  RSP <ffff88002c2e5df8>
> > [  150.946012] CR2: 0000000000000070
>
> Looks at aweful lot like the problem from:
> http://www.spinics.net/lists/linux-fsdevel/msg46101.html
>

I tried to reproduce this bug with your test program, but without success.
However, if I understand correctly, this occurs since we dont hold any locks when
we call iput() in mark_destroy(), right?
With the patches you tested, iput() is also not called within any lock, since the
groups mark_mutex is released temporarily before iput() is called.  This is, since
the original codes behaviour is similar.
However since we now have a mutex as the biggest lock, we can do what you
suggested (http://www.spinics.net/lists/linux-fsdevel/msg46107.html) and
call iput() with the mutex held to avoid the race.
The patch below implements this. It uses nested locking to avoid deadlock in case
we do the final iput() on an inode which still holds marks and thus would take
the mutex again when calling fsnotify_inode_delete() in destroy_inode().

Signed-off-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 fs/notify/mark.c                 | 20 ++++++++++----------
 include/linux/fsnotify_backend.h |  7 ++++---
 2 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 0e93d90bb753..fc6b49bf7360 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -150,6 +150,8 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
 
 	spin_unlock(&mark->lock);
 
+	if (inode && (mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED))
+		iput(inode);
 	/* release lock temporarily */
 	mutex_unlock(&group->mark_mutex);
 
@@ -157,6 +159,11 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
 	list_add(&mark->destroy_list, &destroy_list);
 	spin_unlock(&destroy_lock);
 	wake_up(&destroy_waitq);
+	/*
+	 * We don't necessarily have a ref on mark from caller so the above destroy
+	 * may have actually freed it, unless this group provides a 'freeing_mark'
+	 * function which must be holding a reference.
+	 */
 
 	/*
 	 * Some groups like to know that marks are being freed.  This is a
@@ -178,22 +185,15 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
 	 * is just a lazy update (and could be a perf win...)
 	 */
 
-	if (inode && (mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED))
-		iput(inode);
-	/*
-	 * We don't necessarily have a ref on mark from caller so the above iput
-	 * may have already destroyed it.  Don't touch from now on.
-	 */
-
 	atomic_dec(&group->num_marks);
 
-	mutex_lock(&group->mark_mutex);
+	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
 }
 
 void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 			   struct fsnotify_group *group)
 {
-	mutex_lock(&group->mark_mutex);
+	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
 	fsnotify_destroy_mark_locked(mark, group);
 	mutex_unlock(&group->mark_mutex);
 }
@@ -300,7 +300,7 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 {
 	struct fsnotify_mark *lmark, *mark;
 
-	mutex_lock(&group->mark_mutex);
+	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
 	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
 		if (mark->flags & flags) {
 			fsnotify_get_mark(mark);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 5a8899350456..1af2f6a722c0 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -88,9 +88,10 @@ struct fsnotify_event_private_data;
  *		if the group is interested in this event.
  * handle_event - main call for a group to handle an fs event
  * free_group_priv - called when a group refcnt hits 0 to clean up the private union
- * freeing-mark - this means that a mark has been flagged to die when everything
- *		finishes using it.  The function is supplied with what must be a
- *		valid group and inode to use to clean up.
+ * freeing_mark - called when a mark is being destroyed for some reason.  The group
+ * 		MUST be holding a reference on each mark and that reference must be
+ * 		dropped in this function.  inotify uses this function to send
+ * 		userspace messages that marks have been removed.
  */
 struct fsnotify_ops {
 	bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode,
-- 
cgit v1.2.3-55-g7522


From 0a6b6bd5919a65030b557ec8fe81f6fb3e93744a Mon Sep 17 00:00:00 2001
From: Eric Paris
Date: Fri, 14 Oct 2011 17:43:39 -0400
Subject: fsnotify: make fasync generic for both inotify and fanotify

inotify is supposed to support async signal notification when information
is available on the inotify fd.  This patch moves that support to generic
fsnotify functions so it can be used by all notification mechanisms.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 fs/notify/fanotify/fanotify_user.c |  4 ++++
 fs/notify/group.c                  |  7 +++++++
 fs/notify/inotify/inotify_user.c   | 13 ++++---------
 fs/notify/notification.c           |  1 +
 include/linux/fsnotify_backend.h   |  5 ++++-
 5 files changed, 20 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 1218d10424d0..f0e7a57bc899 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -414,6 +414,10 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
+
+	if (file->f_flags & FASYNC)
+		fsnotify_fasync(-1, file, 0);
+
 	/* matches the fanotify_init->fsnotify_alloc_group */
 	fsnotify_destroy_group(group);
 
diff --git a/fs/notify/group.c b/fs/notify/group.c
index 1f7305711fc9..bd2625bd88b4 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -102,3 +102,10 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
 
 	return group;
 }
+
+int fsnotify_fasync(int fd, struct file *file, int on)
+{
+	struct fsnotify_group *group = file->private_data;
+
+	return fasync_helper(fd, file, on, &group->fsn_fa) >= 0 ? 0 : -EIO;
+}
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 00ff82ff7c9f..68f7bec1e664 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -280,19 +280,15 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 	return ret;
 }
 
-static int inotify_fasync(int fd, struct file *file, int on)
-{
-	struct fsnotify_group *group = file->private_data;
-
-	return fasync_helper(fd, file, on, &group->inotify_data.fa) >= 0 ? 0 : -EIO;
-}
-
 static int inotify_release(struct inode *ignored, struct file *file)
 {
 	struct fsnotify_group *group = file->private_data;
 
 	pr_debug("%s: group=%p\n", __func__, group);
 
+	if (file->f_flags & FASYNC)
+		fsnotify_fasync(-1, file, 0);
+
 	/* free this group, matching get was inotify_init->fsnotify_obtain_group */
 	fsnotify_destroy_group(group);
 
@@ -335,7 +331,7 @@ static long inotify_ioctl(struct file *file, unsigned int cmd,
 static const struct file_operations inotify_fops = {
 	.poll		= inotify_poll,
 	.read		= inotify_read,
-	.fasync		= inotify_fasync,
+	.fasync		= fsnotify_fasync,
 	.release	= inotify_release,
 	.unlocked_ioctl	= inotify_ioctl,
 	.compat_ioctl	= inotify_ioctl,
@@ -706,7 +702,6 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 	spin_lock_init(&group->inotify_data.idr_lock);
 	idr_init(&group->inotify_data.idr);
 	group->inotify_data.last_wd = 0;
-	group->inotify_data.fa = NULL;
 	group->inotify_data.user = get_current_user();
 
 	if (atomic_inc_return(&group->inotify_data.user->inotify_devs) >
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index c887b1378f7e..b3963d8c9988 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -225,6 +225,7 @@ alloc_holder:
 	mutex_unlock(&group->notification_mutex);
 
 	wake_up(&group->notification_waitq);
+	kill_fasync(&group->fsn_fa, SIGIO, POLL_IN);
 	return return_event;
 }
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 1af2f6a722c0..d5b0910d4961 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -148,6 +148,8 @@ struct fsnotify_group {
 					 * a group */
 	struct list_head marks_list;	/* all inode marks for this group */
 
+	struct fasync_struct    *fsn_fa;    /* async notification */
+
 	/* groups can define private fields here or use the void *private */
 	union {
 		void *private;
@@ -156,7 +158,6 @@ struct fsnotify_group {
 			spinlock_t	idr_lock;
 			struct idr      idr;
 			u32             last_wd;
-			struct fasync_struct    *fa;    /* async notification */
 			struct user_struct      *user;
 		} inotify_data;
 #endif
@@ -368,6 +369,8 @@ extern void fsnotify_get_group(struct fsnotify_group *group);
 extern void fsnotify_put_group(struct fsnotify_group *group);
 /* destroy group */
 extern void fsnotify_destroy_group(struct fsnotify_group *group);
+/* fasync handler function */
+extern int fsnotify_fasync(int fd, struct file *file, int on);
 /* take a reference to an event */
 extern void fsnotify_get_event(struct fsnotify_event *event);
 extern void fsnotify_put_event(struct fsnotify_event *event);
-- 
cgit v1.2.3-55-g7522


From d0e1d66b5aa1ec9f556f951aa9a114cc192cd01c Mon Sep 17 00:00:00 2001
From: Namjae Jeon
Date: Tue, 11 Dec 2012 16:00:21 -0800
Subject: writeback: remove nr_pages_dirtied arg from
 balance_dirty_pages_ratelimited_nr()

There is no reason to pass the nr_pages_dirtied argument, because
nr_pages_dirtied value from the caller is unused in
balance_dirty_pages_ratelimited_nr().

Signed-off-by: Namjae Jeon <linkinjeon@gmail.com>
Signed-off-by: Vivek Trivedi <vtrivedi018@gmail.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/btrfs/disk-io.c        |  8 ++++----
 fs/btrfs/file.c           |  3 +--
 fs/btrfs/ioctl.c          |  2 +-
 fs/ocfs2/file.c           |  5 +----
 fs/splice.c               |  5 +----
 include/linux/writeback.h |  9 +--------
 mm/page-writeback.c       | 11 +++++------
 7 files changed, 14 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7cda51995c1e..22a0439e5a86 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3416,8 +3416,8 @@ void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr)
 	num_dirty = root->fs_info->dirty_metadata_bytes;
 
 	if (num_dirty > thresh) {
-		balance_dirty_pages_ratelimited_nr(
-				   root->fs_info->btree_inode->i_mapping, 1);
+		balance_dirty_pages_ratelimited(
+				   root->fs_info->btree_inode->i_mapping);
 	}
 	return;
 }
@@ -3437,8 +3437,8 @@ void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr)
 	num_dirty = root->fs_info->dirty_metadata_bytes;
 
 	if (num_dirty > thresh) {
-		balance_dirty_pages_ratelimited_nr(
-				   root->fs_info->btree_inode->i_mapping, 1);
+		balance_dirty_pages_ratelimited(
+				   root->fs_info->btree_inode->i_mapping);
 	}
 	return;
 }
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 9ab1bed88116..a8ee75cb96ee 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1346,8 +1346,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 
 		cond_resched();
 
-		balance_dirty_pages_ratelimited_nr(inode->i_mapping,
-						   dirty_pages);
+		balance_dirty_pages_ratelimited(inode->i_mapping);
 		if (dirty_pages < (root->leafsize >> PAGE_CACHE_SHIFT) + 1)
 			btrfs_btree_balance_dirty(root, 1);
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 8fcf9a59c28d..5b3429ab8ec1 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1225,7 +1225,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 		}
 
 		defrag_count += ret;
-		balance_dirty_pages_ratelimited_nr(inode->i_mapping, ret);
+		balance_dirty_pages_ratelimited(inode->i_mapping);
 		mutex_unlock(&inode->i_mutex);
 
 		if (newer_than) {
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 5a4ee77cec51..dda089804942 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2513,18 +2513,15 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
 		ret = sd.num_spliced;
 
 	if (ret > 0) {
-		unsigned long nr_pages;
 		int err;
 
-		nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-
 		err = generic_write_sync(out, *ppos, ret);
 		if (err)
 			ret = err;
 		else
 			*ppos += ret;
 
-		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
+		balance_dirty_pages_ratelimited(mapping);
 	}
 
 	return ret;
diff --git a/fs/splice.c b/fs/splice.c
index 13e5b4776e7a..8890604e3fcd 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1024,17 +1024,14 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 		ret = sd.num_spliced;
 
 	if (ret > 0) {
-		unsigned long nr_pages;
 		int err;
 
-		nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-
 		err = generic_write_sync(out, *ppos, ret);
 		if (err)
 			ret = err;
 		else
 			*ppos += ret;
-		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
+		balance_dirty_pages_ratelimited(mapping);
 	}
 	sb_end_write(inode->i_sb);
 
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 50c3e8fa06a8..b82a83aba311 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -161,14 +161,7 @@ void __bdi_update_bandwidth(struct backing_dev_info *bdi,
 			    unsigned long start_time);
 
 void page_writeback_init(void);
-void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
-					unsigned long nr_pages_dirtied);
-
-static inline void
-balance_dirty_pages_ratelimited(struct address_space *mapping)
-{
-	balance_dirty_pages_ratelimited_nr(mapping, 1);
-}
+void balance_dirty_pages_ratelimited(struct address_space *mapping);
 
 typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
 				void *data);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 830893b2b3c7..6f4271224493 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1069,7 +1069,7 @@ static void bdi_update_bandwidth(struct backing_dev_info *bdi,
 }
 
 /*
- * After a task dirtied this many pages, balance_dirty_pages_ratelimited_nr()
+ * After a task dirtied this many pages, balance_dirty_pages_ratelimited()
  * will look to see if it needs to start dirty throttling.
  *
  * If dirty_poll_interval is too low, big NUMA machines will call the expensive
@@ -1436,9 +1436,8 @@ static DEFINE_PER_CPU(int, bdp_ratelimits);
 DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
 
 /**
- * balance_dirty_pages_ratelimited_nr - balance dirty memory state
+ * balance_dirty_pages_ratelimited - balance dirty memory state
  * @mapping: address_space which was dirtied
- * @nr_pages_dirtied: number of pages which the caller has just dirtied
  *
  * Processes which are dirtying memory should call in here once for each page
  * which was newly dirtied.  The function will periodically check the system's
@@ -1449,8 +1448,7 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
  * limit we decrease the ratelimiting by a lot, to prevent individual processes
  * from overshooting the limit by (ratelimit_pages) each.
  */
-void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
-					unsigned long nr_pages_dirtied)
+void balance_dirty_pages_ratelimited(struct address_space *mapping)
 {
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 	int ratelimit;
@@ -1484,6 +1482,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 	 */
 	p = &__get_cpu_var(dirty_throttle_leaks);
 	if (*p > 0 && current->nr_dirtied < ratelimit) {
+		unsigned long nr_pages_dirtied;
 		nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied);
 		*p -= nr_pages_dirtied;
 		current->nr_dirtied += nr_pages_dirtied;
@@ -1493,7 +1492,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 	if (unlikely(current->nr_dirtied >= ratelimit))
 		balance_dirty_pages(mapping, current->nr_dirtied);
 }
-EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
+EXPORT_SYMBOL(balance_dirty_pages_ratelimited);
 
 void throttle_vm_writeout(gfp_t gfp_mask)
 {
-- 
cgit v1.2.3-55-g7522


From 19965460e31c73a934d2c19c152f876a75bdff3e Mon Sep 17 00:00:00 2001
From: David Rientjes
Date: Tue, 11 Dec 2012 16:00:26 -0800
Subject: mm, memcg: make mem_cgroup_out_of_memory() static

mem_cgroup_out_of_memory() is only referenced from within file scope, so
it can be marked static.

Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/oom.h | 2 --
 mm/memcontrol.c     | 4 ++--
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/oom.h b/include/linux/oom.h
index fb9826847b89..4a4188da4570 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -49,8 +49,6 @@ extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 		unsigned long totalpages, const nodemask_t *nodemask,
 		bool force_kill);
-extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
-				     int order);
 
 extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *mask, bool force_kill);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index dd39ba000b31..cf6d0df4849c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1498,8 +1498,8 @@ static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 	return limit;
 }
 
-void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
-			      int order)
+static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+				     int order)
 {
 	struct mem_cgroup *iter;
 	unsigned long chosen_points = 0;
-- 
cgit v1.2.3-55-g7522


From e5adfffc857788c8b7eca0e98cf1e26f1964b292 Mon Sep 17 00:00:00 2001
From: Kirill A. Shutemov
Date: Tue, 11 Dec 2012 16:00:29 -0800
Subject: mm: use IS_ENABLED(CONFIG_NUMA) instead of NUMA_BUILD

We don't need custom NUMA_BUILD anymore, since we have handy
IS_ENABLED().

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h    |  2 +-
 include/linux/kernel.h |  7 -------
 mm/page_alloc.c        | 18 ++++++++++--------
 mm/vmalloc.c           |  4 ++--
 4 files changed, 13 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index d0a79678f169..31e8041274f6 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -266,7 +266,7 @@ static inline enum zone_type gfp_zone(gfp_t flags)
 
 static inline int gfp_zonelist(gfp_t flags)
 {
-	if (NUMA_BUILD && unlikely(flags & __GFP_THISNODE))
+	if (IS_ENABLED(CONFIG_NUMA) && unlikely(flags & __GFP_THISNODE))
 		return 1;
 
 	return 0;
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 7d8dfc7392f1..815e5845d954 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -687,13 +687,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 /* Trap pasters of __FUNCTION__ at compile-time */
 #define __FUNCTION__ (__func__)
 
-/* This helps us to avoid #ifdef CONFIG_NUMA */
-#ifdef CONFIG_NUMA
-#define NUMA_BUILD 1
-#else
-#define NUMA_BUILD 0
-#endif
-
 /* This helps us avoid #ifdef CONFIG_COMPACTION */
 #ifdef CONFIG_COMPACTION
 #define COMPACTION_BUILD 1
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index dc018b486b74..a49b0ea3cc2f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1871,7 +1871,7 @@ zonelist_scan:
 	 */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 						high_zoneidx, nodemask) {
-		if (NUMA_BUILD && zlc_active &&
+		if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
 			!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;
 		if ((alloc_flags & ALLOC_CPUSET) &&
@@ -1917,7 +1917,8 @@ zonelist_scan:
 				    classzone_idx, alloc_flags))
 				goto try_this_zone;
 
-			if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
+			if (IS_ENABLED(CONFIG_NUMA) &&
+					!did_zlc_setup && nr_online_nodes > 1) {
 				/*
 				 * we do zlc_setup if there are multiple nodes
 				 * and before considering the first zone allowed
@@ -1936,7 +1937,7 @@ zonelist_scan:
 			 * As we may have just activated ZLC, check if the first
 			 * eligible zone has failed zone_reclaim recently.
 			 */
-			if (NUMA_BUILD && zlc_active &&
+			if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
 				!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;
 
@@ -1962,11 +1963,11 @@ try_this_zone:
 		if (page)
 			break;
 this_zone_full:
-		if (NUMA_BUILD)
+		if (IS_ENABLED(CONFIG_NUMA))
 			zlc_mark_zone_full(zonelist, z);
 	}
 
-	if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
+	if (unlikely(IS_ENABLED(CONFIG_NUMA) && page == NULL && zlc_active)) {
 		/* Disable zlc cache for second zonelist scan */
 		zlc_active = 0;
 		goto zonelist_scan;
@@ -2266,7 +2267,7 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 	/* After successful reclaim, reconsider all zones for allocation */
-	if (NUMA_BUILD)
+	if (IS_ENABLED(CONFIG_NUMA))
 		zlc_clear_zones_full(zonelist);
 
 retry:
@@ -2412,7 +2413,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 * allowed per node queues are empty and that nodes are
 	 * over allocated.
 	 */
-	if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+	if (IS_ENABLED(CONFIG_NUMA) &&
+			(gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
 restart:
@@ -2819,7 +2821,7 @@ unsigned int nr_free_pagecache_pages(void)
 
 static inline void show_node(struct zone *zone)
 {
-	if (NUMA_BUILD)
+	if (IS_ENABLED(CONFIG_NUMA))
 		printk("Node %d ", zone_to_nid(zone));
 }
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 78e08300db21..5123a169ab7b 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2550,7 +2550,7 @@ static void s_stop(struct seq_file *m, void *p)
 
 static void show_numa_info(struct seq_file *m, struct vm_struct *v)
 {
-	if (NUMA_BUILD) {
+	if (IS_ENABLED(CONFIG_NUMA)) {
 		unsigned int nr, *counters = m->private;
 
 		if (!counters)
@@ -2615,7 +2615,7 @@ static int vmalloc_open(struct inode *inode, struct file *file)
 	unsigned int *ptr = NULL;
 	int ret;
 
-	if (NUMA_BUILD) {
+	if (IS_ENABLED(CONFIG_NUMA)) {
 		ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
 		if (ptr == NULL)
 			return -ENOMEM;
-- 
cgit v1.2.3-55-g7522


From d84da3f9e4f18809821562bd960e00a10673b341 Mon Sep 17 00:00:00 2001
From: Kirill A. Shutemov
Date: Tue, 11 Dec 2012 16:00:31 -0800
Subject: mm: use IS_ENABLED(CONFIG_COMPACTION) instead of COMPACTION_BUILD

We don't need custom COMPACTION_BUILD anymore, since we have handy
IS_ENABLED().

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 7 -------
 mm/vmscan.c            | 9 +++++----
 2 files changed, 5 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 815e5845d954..dd9900cabf89 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -687,13 +687,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 /* Trap pasters of __FUNCTION__ at compile-time */
 #define __FUNCTION__ (__func__)
 
-/* This helps us avoid #ifdef CONFIG_COMPACTION */
-#ifdef CONFIG_COMPACTION
-#define COMPACTION_BUILD 1
-#else
-#define COMPACTION_BUILD 0
-#endif
-
 /* This helps us to avoid #ifdef CONFIG_SYMBOL_PREFIX */
 #ifdef CONFIG_SYMBOL_PREFIX
 #define SYMBOL_PREFIX CONFIG_SYMBOL_PREFIX
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b7ed37675644..a1ce17f44be0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1752,7 +1752,7 @@ out:
 /* Use reclaim/compaction for costly allocs or under memory pressure */
 static bool in_reclaim_compaction(struct scan_control *sc)
 {
-	if (COMPACTION_BUILD && sc->order &&
+	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
 			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
 			 sc->priority < DEF_PRIORITY - 2))
 		return true;
@@ -2005,7 +2005,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			if (zone->all_unreclaimable &&
 					sc->priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
-			if (COMPACTION_BUILD) {
+			if (IS_ENABLED(CONFIG_COMPACTION)) {
 				/*
 				 * If we already have plenty of memory free for
 				 * compaction in this zone, don't free any more.
@@ -2421,7 +2421,8 @@ static bool zone_balanced(struct zone *zone, int order,
 				    balance_gap, classzone_idx, 0))
 		return false;
 
-	if (COMPACTION_BUILD && order && !compaction_suitable(zone, order))
+	if (IS_ENABLED(CONFIG_COMPACTION) && order &&
+	    !compaction_suitable(zone, order))
 		return false;
 
 	return true;
@@ -2684,7 +2685,7 @@ loop_again:
 			 * Do not reclaim more than needed for compaction.
 			 */
 			testorder = order;
-			if (COMPACTION_BUILD && order &&
+			if (IS_ENABLED(CONFIG_COMPACTION) && order &&
 					compaction_suitable(zone, order) !=
 						COMPACT_SKIPPED)
 				testorder = 0;
-- 
cgit v1.2.3-55-g7522


From b023f46813cde6e3b8a8c24f432ff9c1fd8e9a64 Mon Sep 17 00:00:00 2001
From: Wen Congyang
Date: Tue, 11 Dec 2012 16:00:45 -0800
Subject: memory-hotplug: skip HWPoisoned page when offlining pages

hwpoisoned may be set when we offline a page by the sysfs interface
/sys/devices/system/memory/soft_offline_page or
/sys/devices/system/memory/hard_offline_page. If we don't clear
this flag when onlining pages, this page can't be freed, and will
not in free list. So we can't offline these pages again. So we
should skip such page when offlining pages.

Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-isolation.h | 10 ++++++----
 mm/memory-failure.c            |  2 +-
 mm/memory_hotplug.c            |  5 +++--
 mm/page_alloc.c                | 27 +++++++++++++++++++++++----
 mm/page_isolation.c            | 27 ++++++++++++++++++++-------
 5 files changed, 53 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 76a9539cfd3f..a92061e08d48 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -2,7 +2,8 @@
 #define __LINUX_PAGEISOLATION_H
 
 
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count);
+bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
+			 bool skip_hwpoisoned_pages);
 void set_pageblock_migratetype(struct page *page, int migratetype);
 int move_freepages_block(struct zone *zone, struct page *page,
 				int migratetype);
@@ -21,7 +22,7 @@ int move_freepages(struct zone *zone,
  */
 int
 start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			 unsigned migratetype);
+			 unsigned migratetype, bool skip_hwpoisoned_pages);
 
 /*
  * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE.
@@ -34,12 +35,13 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 /*
  * Test all pages in [start_pfn, end_pfn) are isolated or not.
  */
-int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn);
+int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
+			bool skip_hwpoisoned_pages);
 
 /*
  * Internal functions. Changes pageblock's migrate type.
  */
-int set_migratetype_isolate(struct page *page);
+int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages);
 void unset_migratetype_isolate(struct page *page, unsigned migratetype);
 struct page *alloc_migrate_target(struct page *page, unsigned long private,
 				int **resultp);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 8b20278be6a6..2c9fc7340b12 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1385,7 +1385,7 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags)
 	 * Isolate the page, so that it doesn't get reallocated if it
 	 * was free.
 	 */
-	set_migratetype_isolate(p);
+	set_migratetype_isolate(p, true);
 	/*
 	 * When the target page is a free hugepage, just remove it
 	 * from free hugepage list.
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e4eeacae2b91..0095d156324a 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -847,7 +847,7 @@ check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages,
 {
 	int ret;
 	long offlined = *(long *)data;
-	ret = test_pages_isolated(start_pfn, start_pfn + nr_pages);
+	ret = test_pages_isolated(start_pfn, start_pfn + nr_pages, true);
 	offlined = nr_pages;
 	if (!ret)
 		*(long *)data += offlined;
@@ -894,7 +894,8 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	nr_pages = end_pfn - start_pfn;
 
 	/* set above range as isolated */
-	ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
+	ret = start_isolate_page_range(start_pfn, end_pfn,
+				       MIGRATE_MOVABLE, true);
 	if (ret)
 		goto out;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a49b0ea3cc2f..6f50cfe98a7b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5616,7 +5616,8 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
  * MIGRATE_MOVABLE block might include unmovable pages. It means you can't
  * expect this function should be exact.
  */
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count)
+bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
+			 bool skip_hwpoisoned_pages)
 {
 	unsigned long pfn, iter, found;
 	int mt;
@@ -5651,6 +5652,13 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count)
 			continue;
 		}
 
+		/*
+		 * The HWPoisoned page may be not in buddy system, and
+		 * page_count() is not 0.
+		 */
+		if (skip_hwpoisoned_pages && PageHWPoison(page))
+			continue;
+
 		if (!PageLRU(page))
 			found++;
 		/*
@@ -5693,7 +5701,7 @@ bool is_pageblock_removable_nolock(struct page *page)
 			zone->zone_start_pfn + zone->spanned_pages <= pfn)
 		return false;
 
-	return !has_unmovable_pages(zone, page, 0);
+	return !has_unmovable_pages(zone, page, 0, true);
 }
 
 #ifdef CONFIG_CMA
@@ -5864,7 +5872,8 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 */
 
 	ret = start_isolate_page_range(pfn_max_align_down(start),
-				       pfn_max_align_up(end), migratetype);
+				       pfn_max_align_up(end), migratetype,
+				       false);
 	if (ret)
 		return ret;
 
@@ -5903,7 +5912,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	}
 
 	/* Make sure the range is really isolated. */
-	if (test_pages_isolated(outer_start, end)) {
+	if (test_pages_isolated(outer_start, end, false)) {
 		pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n",
 		       outer_start, end);
 		ret = -EBUSY;
@@ -6018,6 +6027,16 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 			continue;
 		}
 		page = pfn_to_page(pfn);
+		/*
+		 * The HWPoisoned page may be not in buddy system, and
+		 * page_count() is not 0.
+		 */
+		if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {
+			pfn++;
+			SetPageReserved(page);
+			continue;
+		}
+
 		BUG_ON(page_count(page));
 		BUG_ON(!PageBuddy(page));
 		order = page_order(page);
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index f2f5b4818e94..9d2264ea4606 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -30,7 +30,7 @@ static void restore_pageblock_isolate(struct page *page, int migratetype)
 	zone->nr_pageblock_isolate--;
 }
 
-int set_migratetype_isolate(struct page *page)
+int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages)
 {
 	struct zone *zone;
 	unsigned long flags, pfn;
@@ -66,7 +66,8 @@ int set_migratetype_isolate(struct page *page)
 	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
 	 * We just check MOVABLE pages.
 	 */
-	if (!has_unmovable_pages(zone, page, arg.pages_found))
+	if (!has_unmovable_pages(zone, page, arg.pages_found,
+				 skip_hwpoisoned_pages))
 		ret = 0;
 
 	/*
@@ -134,7 +135,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * Returns 0 on success and -EBUSY if any part of range cannot be isolated.
  */
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     unsigned migratetype)
+			     unsigned migratetype, bool skip_hwpoisoned_pages)
 {
 	unsigned long pfn;
 	unsigned long undo_pfn;
@@ -147,7 +148,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	     pfn < end_pfn;
 	     pfn += pageblock_nr_pages) {
 		page = __first_valid_page(pfn, pageblock_nr_pages);
-		if (page && set_migratetype_isolate(page)) {
+		if (page &&
+		    set_migratetype_isolate(page, skip_hwpoisoned_pages)) {
 			undo_pfn = pfn;
 			goto undo;
 		}
@@ -190,7 +192,8 @@ int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  * Returns 1 if all pages in the range are isolated.
  */
 static int
-__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
+__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
+				  bool skip_hwpoisoned_pages)
 {
 	struct page *page;
 
@@ -220,6 +223,14 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
 		else if (page_count(page) == 0 &&
 			get_freepage_migratetype(page) == MIGRATE_ISOLATE)
 			pfn += 1;
+		else if (skip_hwpoisoned_pages && PageHWPoison(page)) {
+			/*
+			 * The HWPoisoned page may be not in buddy
+			 * system, and page_count() is not 0.
+			 */
+			pfn++;
+			continue;
+		}
 		else
 			break;
 	}
@@ -228,7 +239,8 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
 	return 1;
 }
 
-int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
+int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
+			bool skip_hwpoisoned_pages)
 {
 	unsigned long pfn, flags;
 	struct page *page;
@@ -251,7 +263,8 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	/* Check all pages are free or Marked as ISOLATED */
 	zone = page_zone(page);
 	spin_lock_irqsave(&zone->lock, flags);
-	ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn);
+	ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn,
+						skip_hwpoisoned_pages);
 	spin_unlock_irqrestore(&zone->lock, flags);
 	return ret ? 0 : -EBUSY;
 }
-- 
cgit v1.2.3-55-g7522


From 8732794b166196cc501c2ddd9e7c97cf45ab64c5 Mon Sep 17 00:00:00 2001
From: Wen Congyang
Date: Tue, 11 Dec 2012 16:00:56 -0800
Subject: numa: convert static memory to dynamically allocated memory for per
 node device

We use a static array to store struct node.  In many cases, we don't have
too many nodes, and some memory will be unused.  Convert it to per-device
dynamically allocated memory.

Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/kernel/sysfs.c |  4 ++--
 drivers/base/node.c         | 38 ++++++++++++++++++++++----------------
 include/linux/node.h        |  2 +-
 mm/hugetlb.c                |  4 ++--
 4 files changed, 27 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index cf357a059ddb..3ce1f864c2d3 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -607,7 +607,7 @@ static void register_nodes(void)
 
 int sysfs_add_device_to_node(struct device *dev, int nid)
 {
-	struct node *node = &node_devices[nid];
+	struct node *node = node_devices[nid];
 	return sysfs_create_link(&node->dev.kobj, &dev->kobj,
 			kobject_name(&dev->kobj));
 }
@@ -615,7 +615,7 @@ EXPORT_SYMBOL_GPL(sysfs_add_device_to_node);
 
 void sysfs_remove_device_from_node(struct device *dev, int nid)
 {
-	struct node *node = &node_devices[nid];
+	struct node *node = node_devices[nid];
 	sysfs_remove_link(&node->dev.kobj, kobject_name(&dev->kobj));
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node);
diff --git a/drivers/base/node.c b/drivers/base/node.c
index af1a177216f1..28216ce74b3d 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -306,7 +306,7 @@ void unregister_node(struct node *node)
 	device_unregister(&node->dev);
 }
 
-struct node node_devices[MAX_NUMNODES];
+struct node *node_devices[MAX_NUMNODES];
 
 /*
  * register cpu under node
@@ -323,15 +323,15 @@ int register_cpu_under_node(unsigned int cpu, unsigned int nid)
 	if (!obj)
 		return 0;
 
-	ret = sysfs_create_link(&node_devices[nid].dev.kobj,
+	ret = sysfs_create_link(&node_devices[nid]->dev.kobj,
 				&obj->kobj,
 				kobject_name(&obj->kobj));
 	if (ret)
 		return ret;
 
 	return sysfs_create_link(&obj->kobj,
-				 &node_devices[nid].dev.kobj,
-				 kobject_name(&node_devices[nid].dev.kobj));
+				 &node_devices[nid]->dev.kobj,
+				 kobject_name(&node_devices[nid]->dev.kobj));
 }
 
 int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
@@ -345,10 +345,10 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 	if (!obj)
 		return 0;
 
-	sysfs_remove_link(&node_devices[nid].dev.kobj,
+	sysfs_remove_link(&node_devices[nid]->dev.kobj,
 			  kobject_name(&obj->kobj));
 	sysfs_remove_link(&obj->kobj,
-			  kobject_name(&node_devices[nid].dev.kobj));
+			  kobject_name(&node_devices[nid]->dev.kobj));
 
 	return 0;
 }
@@ -390,15 +390,15 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 			continue;
 		if (page_nid != nid)
 			continue;
-		ret = sysfs_create_link_nowarn(&node_devices[nid].dev.kobj,
+		ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
 					&mem_blk->dev.kobj,
 					kobject_name(&mem_blk->dev.kobj));
 		if (ret)
 			return ret;
 
 		return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
-				&node_devices[nid].dev.kobj,
-				kobject_name(&node_devices[nid].dev.kobj));
+				&node_devices[nid]->dev.kobj,
+				kobject_name(&node_devices[nid]->dev.kobj));
 	}
 	/* mem section does not span the specified node */
 	return 0;
@@ -431,10 +431,10 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
 			continue;
 		if (node_test_and_set(nid, *unlinked_nodes))
 			continue;
-		sysfs_remove_link(&node_devices[nid].dev.kobj,
+		sysfs_remove_link(&node_devices[nid]->dev.kobj,
 			 kobject_name(&mem_blk->dev.kobj));
 		sysfs_remove_link(&mem_blk->dev.kobj,
-			 kobject_name(&node_devices[nid].dev.kobj));
+			 kobject_name(&node_devices[nid]->dev.kobj));
 	}
 	NODEMASK_FREE(unlinked_nodes);
 	return 0;
@@ -500,7 +500,7 @@ static void node_hugetlb_work(struct work_struct *work)
 
 static void init_node_hugetlb_work(int nid)
 {
-	INIT_WORK(&node_devices[nid].node_work, node_hugetlb_work);
+	INIT_WORK(&node_devices[nid]->node_work, node_hugetlb_work);
 }
 
 static int node_memory_callback(struct notifier_block *self,
@@ -517,7 +517,7 @@ static int node_memory_callback(struct notifier_block *self,
 		 * when transitioning to/from memoryless state.
 		 */
 		if (nid != NUMA_NO_NODE)
-			schedule_work(&node_devices[nid].node_work);
+			schedule_work(&node_devices[nid]->node_work);
 		break;
 
 	case MEM_GOING_ONLINE:
@@ -558,9 +558,13 @@ int register_one_node(int nid)
 		struct node *parent = NULL;
 
 		if (p_node != nid)
-			parent = &node_devices[p_node];
+			parent = node_devices[p_node];
 
-		error = register_node(&node_devices[nid], nid, parent);
+		node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
+		if (!node_devices[nid])
+			return -ENOMEM;
+
+		error = register_node(node_devices[nid], nid, parent);
 
 		/* link cpu under this node */
 		for_each_present_cpu(cpu) {
@@ -581,7 +585,9 @@ int register_one_node(int nid)
 
 void unregister_one_node(int nid)
 {
-	unregister_node(&node_devices[nid]);
+	unregister_node(node_devices[nid]);
+	kfree(node_devices[nid]);
+	node_devices[nid] = NULL;
 }
 
 /*
diff --git a/include/linux/node.h b/include/linux/node.h
index 624e53cecc02..10316f1c68a9 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -27,7 +27,7 @@ struct node {
 };
 
 struct memory_block;
-extern struct node node_devices[];
+extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
 extern int register_node(struct node *, int, struct node *);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 59a0059b39e2..1ef2cd4ae3c9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1800,7 +1800,7 @@ static void hugetlb_unregister_all_nodes(void)
 	 * remove hstate attributes from any nodes that have them.
 	 */
 	for (nid = 0; nid < nr_node_ids; nid++)
-		hugetlb_unregister_node(&node_devices[nid]);
+		hugetlb_unregister_node(node_devices[nid]);
 }
 
 /*
@@ -1845,7 +1845,7 @@ static void hugetlb_register_all_nodes(void)
 	int nid;
 
 	for_each_node_state(nid, N_HIGH_MEMORY) {
-		struct node *node = &node_devices[nid];
+		struct node *node = node_devices[nid];
 		if (node->dev.id == nid)
 			hugetlb_register_node(node);
 	}
-- 
cgit v1.2.3-55-g7522


From d9713679dbd2a6ecb840cd5b65a3ec555c1ec3d4 Mon Sep 17 00:00:00 2001
From: Lai Jiangshan
Date: Tue, 11 Dec 2012 16:01:03 -0800
Subject: memory_hotplug: fix possible incorrect node_states[N_NORMAL_MEMORY]

Currently memory_hotplug only manages the node_states[N_HIGH_MEMORY], it
forgets to manage node_states[N_NORMAL_MEMORY].  This may cause
node_states[N_NORMAL_MEMORY] to become incorrect.

Example, if a node is empty before online, and we online a memory which is
in ZONE_NORMAL.  And after online, node_states[N_HIGH_MEMORY] is correct,
but node_states[N_NORMAL_MEMORY] is incorrect, the online code doesn't set
the new online node to node_states[N_NORMAL_MEMORY].

The same thing will happen when offlining (the offline code doesn't clear
the node from node_states[N_NORMAL_MEMORY] when needed).  Some memory
managment code depends node_states[N_NORMAL_MEMORY], so we have to fix up
the node_states[N_NORMAL_MEMORY].

We add node_states_check_changes_online() and
node_states_check_changes_offline() to detect whether
node_states[N_HIGH_MEMORY] and node_states[N_NORMAL_MEMORY] are changed
while hotpluging.

Also add @status_change_nid_normal to struct memory_notify, thus the
memory hotplug callbacks know whether the node_states[N_NORMAL_MEMORY] are
changed.  (We can add a @flags and reuse @status_change_nid instead of
introducing @status_change_nid_normal, but it will add much more
complexity in memory hotplug callback in every subsystem.  So introducing
@status_change_nid_normal is better and it doesn't change the sematics of
@status_change_nid)

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Rob Landley <rob@landley.net>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Greg Kroah-Hartman <gregkh@suse.de>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/memory-hotplug.txt |   5 +-
 include/linux/memory.h           |   1 +
 mm/memory_hotplug.c              | 136 ++++++++++++++++++++++++++++++++++-----
 3 files changed, 125 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index 6d0c2519cf47..6e6cbc78f329 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -377,15 +377,18 @@ The third argument is passed by pointer of struct memory_notify.
 struct memory_notify {
        unsigned long start_pfn;
        unsigned long nr_pages;
+       int status_change_nid_normal;
        int status_change_nid;
 }
 
 start_pfn is start_pfn of online/offline memory.
 nr_pages is # of pages of online/offline memory.
+status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask
+is (will be) set/clear, if this is -1, then nodemask status is not changed.
 status_change_nid is set node id when N_HIGH_MEMORY of nodemask is (will be)
 set/clear. It means a new(memoryless) node gets new memory by online and a
 node loses all memory. If this is -1, then nodemask status is not changed.
-If status_changed_nid >= 0, callback should create/discard structures for the
+If status_changed_nid* >= 0, callback should create/discard structures for the
 node if necessary.
 
 --------------
diff --git a/include/linux/memory.h b/include/linux/memory.h
index ff9a9f8e0ed9..a09216d0dcc7 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -53,6 +53,7 @@ int arch_get_memory_phys_device(unsigned long start_pfn);
 struct memory_notify {
 	unsigned long start_pfn;
 	unsigned long nr_pages;
+	int status_change_nid_normal;
 	int status_change_nid;
 };
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ec2f199cc5f7..72195602ded5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -460,6 +460,53 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 	return 0;
 }
 
+/* check which state of node_states will be changed when online memory */
+static void node_states_check_changes_online(unsigned long nr_pages,
+	struct zone *zone, struct memory_notify *arg)
+{
+	int nid = zone_to_nid(zone);
+	enum zone_type zone_last = ZONE_NORMAL;
+
+	/*
+	 * If we have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
+	 * which have 0...ZONE_NORMAL, set zone_last to ZONE_NORMAL.
+	 *
+	 * If we don't have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
+	 * which have 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
+	 */
+	if (N_HIGH_MEMORY == N_NORMAL_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	/*
+	 * if the memory to be online is in a zone of 0...zone_last, and
+	 * the zones of 0...zone_last don't have memory before online, we will
+	 * need to set the node to node_states[N_NORMAL_MEMORY] after
+	 * the memory is online.
+	 */
+	if (zone_idx(zone) <= zone_last && !node_state(nid, N_NORMAL_MEMORY))
+		arg->status_change_nid_normal = nid;
+	else
+		arg->status_change_nid_normal = -1;
+
+	/*
+	 * if the node don't have memory befor online, we will need to
+	 * set the node to node_states[N_HIGH_MEMORY] after the memory
+	 * is online.
+	 */
+	if (!node_state(nid, N_HIGH_MEMORY))
+		arg->status_change_nid = nid;
+	else
+		arg->status_change_nid = -1;
+}
+
+static void node_states_set_node(int node, struct memory_notify *arg)
+{
+	if (arg->status_change_nid_normal >= 0)
+		node_set_state(node, N_NORMAL_MEMORY);
+
+	node_set_state(node, N_HIGH_MEMORY);
+}
+
 
 int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 {
@@ -471,13 +518,18 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 	struct memory_notify arg;
 
 	lock_memory_hotplug();
+	/*
+	 * This doesn't need a lock to do pfn_to_page().
+	 * The section can't be removed here because of the
+	 * memory_block->state_mutex.
+	 */
+	zone = page_zone(pfn_to_page(pfn));
+
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
-	arg.status_change_nid = -1;
+	node_states_check_changes_online(nr_pages, zone, &arg);
 
 	nid = page_to_nid(pfn_to_page(pfn));
-	if (node_present_pages(nid) == 0)
-		arg.status_change_nid = nid;
 
 	ret = memory_notify(MEM_GOING_ONLINE, &arg);
 	ret = notifier_to_errno(ret);
@@ -486,12 +538,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 		unlock_memory_hotplug();
 		return ret;
 	}
-	/*
-	 * This doesn't need a lock to do pfn_to_page().
-	 * The section can't be removed here because of the
-	 * memory_block->state_mutex.
-	 */
-	zone = page_zone(pfn_to_page(pfn));
 	/*
 	 * If this zone is not populated, then it is not in zonelist.
 	 * This means the page allocator ignores this zone.
@@ -521,7 +567,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 	zone->present_pages += onlined_pages;
 	zone->zone_pgdat->node_present_pages += onlined_pages;
 	if (onlined_pages) {
-		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
+		node_states_set_node(zone_to_nid(zone), &arg);
 		if (need_zonelists_rebuild)
 			build_all_zonelists(NULL, NULL);
 		else
@@ -871,6 +917,67 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	return offlined;
 }
 
+/* check which state of node_states will be changed when offline memory */
+static void node_states_check_changes_offline(unsigned long nr_pages,
+		struct zone *zone, struct memory_notify *arg)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	unsigned long present_pages = 0;
+	enum zone_type zt, zone_last = ZONE_NORMAL;
+
+	/*
+	 * If we have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
+	 * which have 0...ZONE_NORMAL, set zone_last to ZONE_NORMAL.
+	 *
+	 * If we don't have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
+	 * which have 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
+	 */
+	if (N_HIGH_MEMORY == N_NORMAL_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	/*
+	 * check whether node_states[N_NORMAL_MEMORY] will be changed.
+	 * If the memory to be offline is in a zone of 0...zone_last,
+	 * and it is the last present memory, 0...zone_last will
+	 * become empty after offline , thus we can determind we will
+	 * need to clear the node from node_states[N_NORMAL_MEMORY].
+	 */
+	for (zt = 0; zt <= zone_last; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
+		arg->status_change_nid_normal = zone_to_nid(zone);
+	else
+		arg->status_change_nid_normal = -1;
+
+	/*
+	 * node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE
+	 */
+	zone_last = ZONE_MOVABLE;
+
+	/*
+	 * check whether node_states[N_HIGH_MEMORY] will be changed
+	 * If we try to offline the last present @nr_pages from the node,
+	 * we can determind we will need to clear the node from
+	 * node_states[N_HIGH_MEMORY].
+	 */
+	for (; zt <= zone_last; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+	if (nr_pages >= present_pages)
+		arg->status_change_nid = zone_to_nid(zone);
+	else
+		arg->status_change_nid = -1;
+}
+
+static void node_states_clear_node(int node, struct memory_notify *arg)
+{
+	if (arg->status_change_nid_normal >= 0)
+		node_clear_state(node, N_NORMAL_MEMORY);
+
+	if ((N_HIGH_MEMORY != N_NORMAL_MEMORY) &&
+	    (arg->status_change_nid >= 0))
+		node_clear_state(node, N_HIGH_MEMORY);
+}
+
 static int __ref __offline_pages(unsigned long start_pfn,
 		  unsigned long end_pfn, unsigned long timeout)
 {
@@ -905,9 +1012,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
 
 	arg.start_pfn = start_pfn;
 	arg.nr_pages = nr_pages;
-	arg.status_change_nid = -1;
-	if (nr_pages >= node_present_pages(node))
-		arg.status_change_nid = node;
+	node_states_check_changes_offline(nr_pages, zone, &arg);
 
 	ret = memory_notify(MEM_GOING_OFFLINE, &arg);
 	ret = notifier_to_errno(ret);
@@ -980,10 +1085,9 @@ repeat:
 	} else
 		zone_pcp_update(zone);
 
-	if (!node_present_pages(node)) {
-		node_clear_state(node, N_HIGH_MEMORY);
+	node_states_clear_node(node, &arg);
+	if (arg.status_change_nid >= 0)
 		kswapd_stop(node);
-	}
 
 	vm_total_pages = nr_free_pagecache_pages();
 	writeback_set_ratelimit();
-- 
cgit v1.2.3-55-g7522


From a1dd450bcb1a05e8218b9aac0ee36f8755d8a140 Mon Sep 17 00:00:00 2001
From: Will Deacon
Date: Tue, 11 Dec 2012 16:01:27 -0800
Subject: mm: thp: set the accessed flag for old pages on access fault

On x86 memory accesses to pages without the ACCESSED flag set result in
the ACCESSED flag being set automatically.  With the ARM architecture a
page access fault is raised instead (and it will continue to be raised
until the ACCESSED flag is set for the appropriate PTE/PMD).

For normal memory pages, handle_pte_fault will call pte_mkyoung
(effectively setting the ACCESSED flag).  For transparent huge pages,
pmd_mkyoung will only be called for a write fault.

This patch ensures that faults on transparent hugepages which do not
result in a CoW update the access flags for the faulting pmd.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Ni zhan Chen <nizhan.chen@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h |  4 ++++
 mm/huge_memory.c        | 22 ++++++++++++++++++++++
 mm/memory.c             |  8 ++++++--
 3 files changed, 32 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b31cb7da0346..1af477552459 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -8,6 +8,10 @@ extern int do_huge_pmd_anonymous_page(struct mm_struct *mm,
 extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			 pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 			 struct vm_area_struct *vma);
+extern void huge_pmd_set_accessed(struct mm_struct *mm,
+				  struct vm_area_struct *vma,
+				  unsigned long address, pmd_t *pmd,
+				  pmd_t orig_pmd, int dirty);
 extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			       unsigned long address, pmd_t *pmd,
 			       pmd_t orig_pmd);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ea5fb93a53a9..5f902e20e8c0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -784,6 +784,28 @@ out:
 	return ret;
 }
 
+void huge_pmd_set_accessed(struct mm_struct *mm,
+			   struct vm_area_struct *vma,
+			   unsigned long address,
+			   pmd_t *pmd, pmd_t orig_pmd,
+			   int dirty)
+{
+	pmd_t entry;
+	unsigned long haddr;
+
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(*pmd, orig_pmd)))
+		goto unlock;
+
+	entry = pmd_mkyoung(orig_pmd);
+	haddr = address & HPAGE_PMD_MASK;
+	if (pmdp_set_access_flags(vma, haddr, pmd, entry, dirty))
+		update_mmu_cache_pmd(vma, address, pmd);
+
+unlock:
+	spin_unlock(&mm->page_table_lock);
+}
+
 static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long address,
diff --git a/mm/memory.c b/mm/memory.c
index 221fc9ffcab1..765377385632 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3537,8 +3537,9 @@ retry:
 
 		barrier();
 		if (pmd_trans_huge(orig_pmd)) {
-			if (flags & FAULT_FLAG_WRITE &&
-			    !pmd_write(orig_pmd) &&
+			unsigned int dirty = flags & FAULT_FLAG_WRITE;
+
+			if (dirty && !pmd_write(orig_pmd) &&
 			    !pmd_trans_splitting(orig_pmd)) {
 				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
 							  orig_pmd);
@@ -3550,6 +3551,9 @@ retry:
 				if (unlikely(ret & VM_FAULT_OOM))
 					goto retry;
 				return ret;
+			} else {
+				huge_pmd_set_accessed(mm, vma, address, pmd,
+						      orig_pmd, dirty);
 			}
 			return 0;
 		}
-- 
cgit v1.2.3-55-g7522


From 42d7395feb56f0655cd8b68e06fc6063823449f8 Mon Sep 17 00:00:00 2001
From: Andi Kleen
Date: Tue, 11 Dec 2012 16:01:34 -0800
Subject: mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB

There was some desire in large applications using MAP_HUGETLB or
SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on
others.  This is useful together with NUMA policy: use 2MB interleaving
on some mappings, but 1GB on local mappings.

This patch extends the IPC/SHM syscall interfaces slightly to allow
specifying the page size.

It borrows some upper bits in the existing flag arguments and allows
encoding the log of the desired page size in addition to the *_HUGETLB
flag.  When 0 is specified the default size is used, this makes the
change fully compatible.

Extending the internal hugetlb code to handle this is straight forward.
Instead of a single mount it just keeps an array of them and selects the
right mount based on the specified page size.  When no page size is
specified it uses the mount of the default page size.

The change is not visible in /proc/mounts because internal mounts don't
appear there.  It also has very little overhead: the additional mounts
just consume a super block, but not more memory when not used.

I also exported the new flags to the user headers (they were previously
under __KERNEL__).  Right now only symbols for x86 and some other
architecture for 1GB and 2MB are defined.  The interface should already
work for all other architectures though.  Only architectures that define
multiple hugetlb sizes actually need it (that is currently x86, tile,
powerpc).  However tile and powerpc have user configurable hugetlb
sizes, so it's not easy to add defines.  A program on those
architectures would need to query sysfs and use the appropiate log2.

[akpm@linux-foundation.org: cleanups]
[rientjes@google.com: fix build]
[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hillf Danton <dhillf@gmail.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/include/asm/mman.h          | 11 ++++++
 arch/mips/include/uapi/asm/mman.h      | 11 ++++++
 arch/parisc/include/uapi/asm/mman.h    | 11 ++++++
 arch/x86/include/asm/mman.h            |  3 ++
 arch/xtensa/include/uapi/asm/mman.h    | 11 ++++++
 fs/hugetlbfs/inode.c                   | 63 +++++++++++++++++++++++++++-------
 include/linux/hugetlb.h                |  7 ++--
 include/linux/shm.h                    | 15 ++++++++
 include/uapi/asm-generic/mman-common.h | 11 ++++++
 include/uapi/asm-generic/mman.h        |  2 ++
 ipc/shm.c                              |  3 +-
 mm/mmap.c                              |  5 +--
 12 files changed, 135 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/mman.h b/arch/alpha/include/asm/mman.h
index cbeb3616a28e..0086b472bc2b 100644
--- a/arch/alpha/include/asm/mman.h
+++ b/arch/alpha/include/asm/mman.h
@@ -63,4 +63,15 @@
 /* compatibility flags */
 #define MAP_FILE	0
 
+/*
+ * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define MAP_HUGE_SHIFT	26
+#define MAP_HUGE_MASK	0x3f
+
 #endif /* __ALPHA_MMAN_H__ */
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index 46d3da0d4b92..9a936ac9a942 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -87,4 +87,15 @@
 /* compatibility flags */
 #define MAP_FILE	0
 
+/*
+ * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define MAP_HUGE_SHIFT	26
+#define MAP_HUGE_MASK	0x3f
+
 #endif /* _ASM_MMAN_H */
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index 12219ebce869..294d251ca7b2 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -70,4 +70,15 @@
 #define MAP_FILE	0
 #define MAP_VARIABLE	0
 
+/*
+ * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define MAP_HUGE_SHIFT	26
+#define MAP_HUGE_MASK	0x3f
+
 #endif /* __PARISC_MMAN_H__ */
diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
index 593e51d4643f..513b05f15bb4 100644
--- a/arch/x86/include/asm/mman.h
+++ b/arch/x86/include/asm/mman.h
@@ -3,6 +3,9 @@
 
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 
+#define MAP_HUGE_2MB    (21 << MAP_HUGE_SHIFT)
+#define MAP_HUGE_1GB    (30 << MAP_HUGE_SHIFT)
+
 #include <asm-generic/mman.h>
 
 #endif /* _ASM_X86_MMAN_H */
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index 25bc6c1309c3..00eed6786d7e 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -93,4 +93,15 @@
 /* compatibility flags */
 #define MAP_FILE	0
 
+/*
+ * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define MAP_HUGE_SHIFT	26
+#define MAP_HUGE_MASK	0x3f
+
 #endif /* _XTENSA_MMAN_H */
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index c5bc355d8243..21b8a4875237 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -923,7 +923,7 @@ static struct file_system_type hugetlbfs_fs_type = {
 	.kill_sb	= kill_litter_super,
 };
 
-static struct vfsmount *hugetlbfs_vfsmount;
+static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
 
 static int can_do_hugetlb_shm(void)
 {
@@ -932,9 +932,22 @@ static int can_do_hugetlb_shm(void)
 	return capable(CAP_IPC_LOCK) || in_group_p(shm_group);
 }
 
+static int get_hstate_idx(int page_size_log)
+{
+	struct hstate *h;
+
+	if (!page_size_log)
+		return default_hstate_idx;
+	h = size_to_hstate(1 << page_size_log);
+	if (!h)
+		return -1;
+	return h - hstates;
+}
+
 struct file *hugetlb_file_setup(const char *name, unsigned long addr,
 				size_t size, vm_flags_t acctflag,
-				struct user_struct **user, int creat_flags)
+				struct user_struct **user,
+				int creat_flags, int page_size_log)
 {
 	int error = -ENOMEM;
 	struct file *file;
@@ -944,9 +957,14 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
 	struct qstr quick_string;
 	struct hstate *hstate;
 	unsigned long num_pages;
+	int hstate_idx;
+
+	hstate_idx = get_hstate_idx(page_size_log);
+	if (hstate_idx < 0)
+		return ERR_PTR(-ENODEV);
 
 	*user = NULL;
-	if (!hugetlbfs_vfsmount)
+	if (!hugetlbfs_vfsmount[hstate_idx])
 		return ERR_PTR(-ENOENT);
 
 	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
@@ -963,7 +981,7 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
 		}
 	}
 
-	root = hugetlbfs_vfsmount->mnt_root;
+	root = hugetlbfs_vfsmount[hstate_idx]->mnt_root;
 	quick_string.name = name;
 	quick_string.len = strlen(quick_string.name);
 	quick_string.hash = 0;
@@ -971,7 +989,7 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
 	if (!path.dentry)
 		goto out_shm_unlock;
 
-	path.mnt = mntget(hugetlbfs_vfsmount);
+	path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
 	error = -ENOSPC;
 	inode = hugetlbfs_get_inode(root->d_sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
@@ -1011,8 +1029,9 @@ out_shm_unlock:
 
 static int __init init_hugetlbfs_fs(void)
 {
+	struct hstate *h;
 	int error;
-	struct vfsmount *vfsmount;
+	int i;
 
 	error = bdi_init(&hugetlbfs_backing_dev_info);
 	if (error)
@@ -1029,14 +1048,26 @@ static int __init init_hugetlbfs_fs(void)
 	if (error)
 		goto out;
 
-	vfsmount = kern_mount(&hugetlbfs_fs_type);
+	i = 0;
+	for_each_hstate(h) {
+		char buf[50];
+		unsigned ps_kb = 1U << (h->order + PAGE_SHIFT - 10);
 
-	if (!IS_ERR(vfsmount)) {
-		hugetlbfs_vfsmount = vfsmount;
-		return 0;
-	}
+		snprintf(buf, sizeof(buf), "pagesize=%uK", ps_kb);
+		hugetlbfs_vfsmount[i] = kern_mount_data(&hugetlbfs_fs_type,
+							buf);
 
-	error = PTR_ERR(vfsmount);
+		if (IS_ERR(hugetlbfs_vfsmount[i])) {
+			pr_err("hugetlb: Cannot mount internal hugetlbfs for "
+				"page size %uK", ps_kb);
+			error = PTR_ERR(hugetlbfs_vfsmount[i]);
+			hugetlbfs_vfsmount[i] = NULL;
+		}
+		i++;
+	}
+	/* Non default hstates are optional */
+	if (!IS_ERR_OR_NULL(hugetlbfs_vfsmount[default_hstate_idx]))
+		return 0;
 
  out:
 	kmem_cache_destroy(hugetlbfs_inode_cachep);
@@ -1047,13 +1078,19 @@ static int __init init_hugetlbfs_fs(void)
 
 static void __exit exit_hugetlbfs_fs(void)
 {
+	struct hstate *h;
+	int i;
+
+
 	/*
 	 * Make sure all delayed rcu free inodes are flushed before we
 	 * destroy cache.
 	 */
 	rcu_barrier();
 	kmem_cache_destroy(hugetlbfs_inode_cachep);
-	kern_unmount(hugetlbfs_vfsmount);
+	i = 0;
+	for_each_hstate(h)
+		kern_unmount(hugetlbfs_vfsmount[i++]);
 	unregister_filesystem(&hugetlbfs_fs_type);
 	bdi_destroy(&hugetlbfs_backing_dev_info);
 }
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 225164842ab6..3e7fa1acf09c 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -183,7 +183,8 @@ extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
 struct file *hugetlb_file_setup(const char *name, unsigned long addr,
 				size_t size, vm_flags_t acct,
-				struct user_struct **user, int creat_flags);
+				struct user_struct **user, int creat_flags,
+				int page_size_log);
 
 static inline int is_file_hugepages(struct file *file)
 {
@@ -195,12 +196,14 @@ static inline int is_file_hugepages(struct file *file)
 	return 0;
 }
 
+
 #else /* !CONFIG_HUGETLBFS */
 
 #define is_file_hugepages(file)			0
 static inline struct file *
 hugetlb_file_setup(const char *name, unsigned long addr, size_t size,
-		vm_flags_t acctflag, struct user_struct **user, int creat_flags)
+		vm_flags_t acctflag, struct user_struct **user, int creat_flags,
+		int page_size_log)
 {
 	return ERR_PTR(-ENOSYS);
 }
diff --git a/include/linux/shm.h b/include/linux/shm.h
index bcf8a6a3ec00..429c1995d756 100644
--- a/include/linux/shm.h
+++ b/include/linux/shm.h
@@ -29,6 +29,21 @@ struct shmid_kernel /* private to the kernel */
 #define SHM_HUGETLB     04000   /* segment will use huge TLB pages */
 #define SHM_NORESERVE   010000  /* don't check for reservations */
 
+/* Bits [26:31] are reserved */
+
+/*
+ * When SHM_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define SHM_HUGE_SHIFT  26
+#define SHM_HUGE_MASK   0x3f
+#define SHM_HUGE_2MB    (21 << SHM_HUGE_SHIFT)
+#define SHM_HUGE_1GB    (30 << SHM_HUGE_SHIFT)
+
 #ifdef CONFIG_SYSVIPC
 long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr,
 	      unsigned long shmlba);
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index d030d2c2647a..4164529a94f9 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -55,4 +55,15 @@
 /* compatibility flags */
 #define MAP_FILE	0
 
+/*
+ * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define MAP_HUGE_SHIFT	26
+#define MAP_HUGE_MASK	0x3f
+
 #endif /* __ASM_GENERIC_MMAN_COMMON_H */
diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h
index 32c8bd6a196d..e9fe6fd2a074 100644
--- a/include/uapi/asm-generic/mman.h
+++ b/include/uapi/asm-generic/mman.h
@@ -13,6 +13,8 @@
 #define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x40000		/* create a huge page mapping */
 
+/* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */
+
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
 
diff --git a/ipc/shm.c b/ipc/shm.c
index dff40c9f73c9..4fa6d8fee730 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -495,7 +495,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 		if (shmflg & SHM_NORESERVE)
 			acctflag = VM_NORESERVE;
 		file = hugetlb_file_setup(name, 0, size, acctflag,
-					&shp->mlock_user, HUGETLB_SHMFS_INODE);
+				  &shp->mlock_user, HUGETLB_SHMFS_INODE,
+				(shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
 	} else {
 		/*
 		 * Do not allow no accounting for OVERCOMMIT_NEVER, even
diff --git a/mm/mmap.c b/mm/mmap.c
index 9a796c41e7d9..ebf19031c5e4 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1153,8 +1153,9 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		 * memory so no accounting is necessary
 		 */
 		file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len,
-						VM_NORESERVE, &user,
-						HUGETLB_ANONHUGE_INODE);
+				VM_NORESERVE,
+				&user, HUGETLB_ANONHUGE_INODE,
+				(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
 		if (IS_ERR(file))
 			return PTR_ERR(file);
 	}
-- 
cgit v1.2.3-55-g7522


From d37371870ceb1d2165397dc36114725b6dca946c Mon Sep 17 00:00:00 2001
From: Michel Lespinasse
Date: Tue, 11 Dec 2012 16:01:38 -0800
Subject: mm: augment vma rbtree with rb_subtree_gap

Define vma->rb_subtree_gap as the largest gap between any vma in the
subtree rooted at that vma, and their predecessor.  Or, for a recursive
definition, vma->rb_subtree_gap is the max of:

 - vma->vm_start - vma->vm_prev->vm_end
 - rb_subtree_gap fields of the vmas pointed by vma->rb.rb_left and
   vma->rb.rb_right

This will allow get_unmapped_area_* to find a free area of the right
size in O(log(N)) time, instead of potentially having to do a linear
walk across all the VMAs.

Also define mm->highest_vm_end as the vm_end field of the highest vma,
so that we can easily check if the following gap is suitable.

This does have the potential to make unmapping VMAs more expensive,
especially for processes with very large numbers of VMAs, where the VMA
rbtree can grow quite deep.

Signed-off-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_types.h |   9 +++
 mm/mmap.c                | 143 +++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 141 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 31f8a3af7d94..94fa52b28ee8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -237,6 +237,14 @@ struct vm_area_struct {
 
 	struct rb_node vm_rb;
 
+	/*
+	 * Largest free memory gap in bytes to the left of this VMA.
+	 * Either between this VMA and vma->vm_prev, or between one of the
+	 * VMAs below us in the VMA rbtree and its ->vm_prev. This helps
+	 * get_unmapped_area find a free area of the right size.
+	 */
+	unsigned long rb_subtree_gap;
+
 	/*
 	 * For areas with an address space and backing store,
 	 * linkage into the address_space->i_mmap interval tree, or
@@ -322,6 +330,7 @@ struct mm_struct {
 	unsigned long task_size;		/* size of task vm space */
 	unsigned long cached_hole_size; 	/* if non-zero, the largest hole below free_area_cache */
 	unsigned long free_area_cache;		/* first hole of size cached_hole_size or larger */
+	unsigned long highest_vm_end;		/* highest vma end address */
 	pgd_t * pgd;
 	atomic_t mm_users;			/* How many users with user space? */
 	atomic_t mm_count;			/* How many references to "struct mm_struct" (users count as 1) */
diff --git a/mm/mmap.c b/mm/mmap.c
index ebf19031c5e4..bdcea6310fff 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -31,6 +31,7 @@
 #include <linux/audit.h>
 #include <linux/khugepaged.h>
 #include <linux/uprobes.h>
+#include <linux/rbtree_augmented.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -297,6 +298,27 @@ out:
 	return retval;
 }
 
+static long vma_compute_subtree_gap(struct vm_area_struct *vma)
+{
+	unsigned long max, subtree_gap;
+	max = vma->vm_start;
+	if (vma->vm_prev)
+		max -= vma->vm_prev->vm_end;
+	if (vma->vm_rb.rb_left) {
+		subtree_gap = rb_entry(vma->vm_rb.rb_left,
+				struct vm_area_struct, vm_rb)->rb_subtree_gap;
+		if (subtree_gap > max)
+			max = subtree_gap;
+	}
+	if (vma->vm_rb.rb_right) {
+		subtree_gap = rb_entry(vma->vm_rb.rb_right,
+				struct vm_area_struct, vm_rb)->rb_subtree_gap;
+		if (subtree_gap > max)
+			max = subtree_gap;
+	}
+	return max;
+}
+
 #ifdef CONFIG_DEBUG_VM_RB
 static int browse_rb(struct rb_root *root)
 {
@@ -327,6 +349,18 @@ static int browse_rb(struct rb_root *root)
 	return i;
 }
 
+static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		struct vm_area_struct *vma;
+		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
+		BUG_ON(vma != ignore &&
+		       vma->rb_subtree_gap != vma_compute_subtree_gap(vma));
+	}
+}
+
 void validate_mm(struct mm_struct *mm)
 {
 	int bug = 0;
@@ -349,9 +383,52 @@ void validate_mm(struct mm_struct *mm)
 	BUG_ON(bug);
 }
 #else
+#define validate_mm_rb(root, ignore) do { } while (0)
 #define validate_mm(mm) do { } while (0)
 #endif
 
+RB_DECLARE_CALLBACKS(static, vma_gap_callbacks, struct vm_area_struct, vm_rb,
+		     unsigned long, rb_subtree_gap, vma_compute_subtree_gap)
+
+/*
+ * Update augmented rbtree rb_subtree_gap values after vma->vm_start or
+ * vma->vm_prev->vm_end values changed, without modifying the vma's position
+ * in the rbtree.
+ */
+static void vma_gap_update(struct vm_area_struct *vma)
+{
+	/*
+	 * As it turns out, RB_DECLARE_CALLBACKS() already created a callback
+	 * function that does exacltly what we want.
+	 */
+	vma_gap_callbacks_propagate(&vma->vm_rb, NULL);
+}
+
+static inline void vma_rb_insert(struct vm_area_struct *vma,
+				 struct rb_root *root)
+{
+	/* All rb_subtree_gap values must be consistent prior to insertion */
+	validate_mm_rb(root, NULL);
+
+	rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
+}
+
+static void vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root)
+{
+	/*
+	 * All rb_subtree_gap values must be consistent prior to erase,
+	 * with the possible exception of the vma being erased.
+	 */
+	validate_mm_rb(root, vma);
+
+	/*
+	 * Note rb_erase_augmented is a fairly large inline function,
+	 * so make sure we instantiate it only once with our desired
+	 * augmented rbtree callbacks.
+	 */
+	rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
+}
+
 /*
  * vma has some anon_vma assigned, and is already inserted on that
  * anon_vma's interval trees.
@@ -421,8 +498,25 @@ static int find_vma_links(struct mm_struct *mm, unsigned long addr,
 void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct rb_node **rb_link, struct rb_node *rb_parent)
 {
+	/* Update tracking information for the gap following the new vma. */
+	if (vma->vm_next)
+		vma_gap_update(vma->vm_next);
+	else
+		mm->highest_vm_end = vma->vm_end;
+
+	/*
+	 * vma->vm_prev wasn't known when we followed the rbtree to find the
+	 * correct insertion point for that vma. As a result, we could not
+	 * update the vma vm_rb parents rb_subtree_gap values on the way down.
+	 * So, we first insert the vma with a zero rb_subtree_gap value
+	 * (to be consistent with what we did on the way down), and then
+	 * immediately update the gap to the correct value. Finally we
+	 * rebalance the rbtree after all augmented values have been set.
+	 */
 	rb_link_node(&vma->vm_rb, rb_parent, rb_link);
-	rb_insert_color(&vma->vm_rb, &mm->mm_rb);
+	vma->rb_subtree_gap = 0;
+	vma_gap_update(vma);
+	vma_rb_insert(vma, &mm->mm_rb);
 }
 
 static void __vma_link_file(struct vm_area_struct *vma)
@@ -498,12 +592,12 @@ static inline void
 __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev)
 {
-	struct vm_area_struct *next = vma->vm_next;
+	struct vm_area_struct *next;
 
-	prev->vm_next = next;
+	vma_rb_erase(vma, &mm->mm_rb);
+	prev->vm_next = next = vma->vm_next;
 	if (next)
 		next->vm_prev = prev;
-	rb_erase(&vma->vm_rb, &mm->mm_rb);
 	if (mm->mmap_cache == vma)
 		mm->mmap_cache = prev;
 }
@@ -525,6 +619,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	struct rb_root *root = NULL;
 	struct anon_vma *anon_vma = NULL;
 	struct file *file = vma->vm_file;
+	bool start_changed = false, end_changed = false;
 	long adjust_next = 0;
 	int remove_next = 0;
 
@@ -615,8 +710,14 @@ again:			remove_next = 1 + (end > next->vm_end);
 			vma_interval_tree_remove(next, root);
 	}
 
-	vma->vm_start = start;
-	vma->vm_end = end;
+	if (start != vma->vm_start) {
+		vma->vm_start = start;
+		start_changed = true;
+	}
+	if (end != vma->vm_end) {
+		vma->vm_end = end;
+		end_changed = true;
+	}
 	vma->vm_pgoff = pgoff;
 	if (adjust_next) {
 		next->vm_start += adjust_next << PAGE_SHIFT;
@@ -645,6 +746,15 @@ again:			remove_next = 1 + (end > next->vm_end);
 		 * (it may either follow vma or precede it).
 		 */
 		__insert_vm_struct(mm, insert);
+	} else {
+		if (start_changed)
+			vma_gap_update(vma);
+		if (end_changed) {
+			if (!next)
+				mm->highest_vm_end = end;
+			else if (!adjust_next)
+				vma_gap_update(next);
+		}
 	}
 
 	if (anon_vma) {
@@ -678,10 +788,13 @@ again:			remove_next = 1 + (end > next->vm_end);
 		 * we must remove another next too. It would clutter
 		 * up the code too much to do both in one go.
 		 */
-		if (remove_next == 2) {
-			next = vma->vm_next;
+		next = vma->vm_next;
+		if (remove_next == 2)
 			goto again;
-		}
+		else if (next)
+			vma_gap_update(next);
+		else
+			mm->highest_vm_end = end;
 	}
 	if (insert && file)
 		uprobe_mmap(insert);
@@ -1784,6 +1897,10 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 				anon_vma_interval_tree_pre_update_vma(vma);
 				vma->vm_end = address;
 				anon_vma_interval_tree_post_update_vma(vma);
+				if (vma->vm_next)
+					vma_gap_update(vma->vm_next);
+				else
+					vma->vm_mm->highest_vm_end = address;
 				perf_event_mmap(vma);
 			}
 		}
@@ -1838,6 +1955,7 @@ int expand_downwards(struct vm_area_struct *vma,
 				vma->vm_start = address;
 				vma->vm_pgoff -= grow;
 				anon_vma_interval_tree_post_update_vma(vma);
+				vma_gap_update(vma);
 				perf_event_mmap(vma);
 			}
 		}
@@ -1960,14 +2078,17 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	insertion_point = (prev ? &prev->vm_next : &mm->mmap);
 	vma->vm_prev = NULL;
 	do {
-		rb_erase(&vma->vm_rb, &mm->mm_rb);
+		vma_rb_erase(vma, &mm->mm_rb);
 		mm->map_count--;
 		tail_vma = vma;
 		vma = vma->vm_next;
 	} while (vma && vma->vm_start < end);
 	*insertion_point = vma;
-	if (vma)
+	if (vma) {
 		vma->vm_prev = prev;
+		vma_gap_update(vma);
+	} else
+		mm->highest_vm_end = prev ? prev->vm_end : 0;
 	tail_vma->vm_next = NULL;
 	if (mm->unmap_area == arch_unmap_area)
 		addr = prev ? prev->vm_end : mm->mmap_base;
-- 
cgit v1.2.3-55-g7522


From e4c6bfd2d79d063017ab19a18915f0bc759f32d9 Mon Sep 17 00:00:00 2001
From: Rik van Riel
Date: Tue, 11 Dec 2012 16:01:44 -0800
Subject: mm: rearrange vm_area_struct for fewer cache misses

The kernel walks the VMA rbtree in various places, including the page
fault path.  However, the vm_rb node spanned two cache lines, on 64 bit
systems with 64 byte cache lines (most x86 systems).

Rearrange vm_area_struct a little, so all the information we need to do a
VMA tree walk is in the first cache line.

[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Michel Lespinasse <walken@google.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_types.h | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 94fa52b28ee8..7ade2731b5d6 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -224,7 +224,8 @@ struct vm_region {
  * library, the executable area etc).
  */
 struct vm_area_struct {
-	struct mm_struct * vm_mm;	/* The address space we belong to. */
+	/* The first cache line has the info for VMA tree walking. */
+
 	unsigned long vm_start;		/* Our start address within vm_mm. */
 	unsigned long vm_end;		/* The first byte after our end address
 					   within vm_mm. */
@@ -232,9 +233,6 @@ struct vm_area_struct {
 	/* linked list of VM areas per task, sorted by address */
 	struct vm_area_struct *vm_next, *vm_prev;
 
-	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
-	unsigned long vm_flags;		/* Flags, see mm.h. */
-
 	struct rb_node vm_rb;
 
 	/*
@@ -245,6 +243,12 @@ struct vm_area_struct {
 	 */
 	unsigned long rb_subtree_gap;
 
+	/* Second cache line starts here. */
+
+	struct mm_struct *vm_mm;	/* The address space we belong to. */
+	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
+	unsigned long vm_flags;		/* Flags, see mm.h. */
+
 	/*
 	 * For areas with an address space and backing store,
 	 * linkage into the address_space->i_mmap interval tree, or
-- 
cgit v1.2.3-55-g7522


From db4fbfb9523c93583c339e66023506f651c1d54b Mon Sep 17 00:00:00 2001
From: Michel Lespinasse
Date: Tue, 11 Dec 2012 16:01:49 -0800
Subject: mm: vm_unmapped_area() lookup function

Implement vm_unmapped_area() using the rb_subtree_gap and highest_vm_end
information to look up for suitable virtual address space gaps.

struct vm_unmapped_area_info is used to define the desired allocation
request:
 - lowest or highest possible address matching the remaining constraints
 - desired gap length
 - low/high address limits that the gap must fit into
 - alignment mask and offset

Also update the generic arch_get_unmapped_area[_topdown] functions to make
use of vm_unmapped_area() instead of implementing a brute force search.

[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  31 ++++++
 mm/mmap.c          | 312 +++++++++++++++++++++++++++++++++++++----------------
 2 files changed, 253 insertions(+), 90 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index bcaab4e6fe91..4af4f0b1be4c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1456,6 +1456,37 @@ extern unsigned long vm_mmap(struct file *, unsigned long,
         unsigned long, unsigned long,
         unsigned long, unsigned long);
 
+struct vm_unmapped_area_info {
+#define VM_UNMAPPED_AREA_TOPDOWN 1
+	unsigned long flags;
+	unsigned long length;
+	unsigned long low_limit;
+	unsigned long high_limit;
+	unsigned long align_mask;
+	unsigned long align_offset;
+};
+
+extern unsigned long unmapped_area(struct vm_unmapped_area_info *info);
+extern unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info);
+
+/*
+ * Search for an unmapped address range.
+ *
+ * We are looking for a range that:
+ * - does not intersect with any VMA;
+ * - is contained within the [low_limit, high_limit) interval;
+ * - is at least the desired size.
+ * - satisfies (begin_addr & align_mask) == (align_offset & align_mask)
+ */
+static inline unsigned long
+vm_unmapped_area(struct vm_unmapped_area_info *info)
+{
+	if (!(info->flags & VM_UNMAPPED_AREA_TOPDOWN))
+		return unmapped_area(info);
+	else
+		return unmapped_area_topdown(info);
+}
+
 /* truncate.c */
 extern void truncate_inode_pages(struct address_space *, loff_t);
 extern void truncate_inode_pages_range(struct address_space *,
diff --git a/mm/mmap.c b/mm/mmap.c
index ff93f6c8436c..5646677a96d5 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1539,6 +1539,206 @@ unacct_error:
 	return error;
 }
 
+unsigned long unmapped_area(struct vm_unmapped_area_info *info)
+{
+	/*
+	 * We implement the search by looking for an rbtree node that
+	 * immediately follows a suitable gap. That is,
+	 * - gap_start = vma->vm_prev->vm_end <= info->high_limit - length;
+	 * - gap_end   = vma->vm_start        >= info->low_limit  + length;
+	 * - gap_end - gap_start >= length
+	 */
+
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long length, low_limit, high_limit, gap_start, gap_end;
+
+	/* Adjust search length to account for worst case alignment overhead */
+	length = info->length + info->align_mask;
+	if (length < info->length)
+		return -ENOMEM;
+
+	/* Adjust search limits by the desired length */
+	if (info->high_limit < length)
+		return -ENOMEM;
+	high_limit = info->high_limit - length;
+
+	if (info->low_limit > high_limit)
+		return -ENOMEM;
+	low_limit = info->low_limit + length;
+
+	/* Check if rbtree root looks promising */
+	if (RB_EMPTY_ROOT(&mm->mm_rb))
+		goto check_highest;
+	vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb);
+	if (vma->rb_subtree_gap < length)
+		goto check_highest;
+
+	while (true) {
+		/* Visit left subtree if it looks promising */
+		gap_end = vma->vm_start;
+		if (gap_end >= low_limit && vma->vm_rb.rb_left) {
+			struct vm_area_struct *left =
+				rb_entry(vma->vm_rb.rb_left,
+					 struct vm_area_struct, vm_rb);
+			if (left->rb_subtree_gap >= length) {
+				vma = left;
+				continue;
+			}
+		}
+
+		gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
+check_current:
+		/* Check if current node has a suitable gap */
+		if (gap_start > high_limit)
+			return -ENOMEM;
+		if (gap_end >= low_limit && gap_end - gap_start >= length)
+			goto found;
+
+		/* Visit right subtree if it looks promising */
+		if (vma->vm_rb.rb_right) {
+			struct vm_area_struct *right =
+				rb_entry(vma->vm_rb.rb_right,
+					 struct vm_area_struct, vm_rb);
+			if (right->rb_subtree_gap >= length) {
+				vma = right;
+				continue;
+			}
+		}
+
+		/* Go back up the rbtree to find next candidate node */
+		while (true) {
+			struct rb_node *prev = &vma->vm_rb;
+			if (!rb_parent(prev))
+				goto check_highest;
+			vma = rb_entry(rb_parent(prev),
+				       struct vm_area_struct, vm_rb);
+			if (prev == vma->vm_rb.rb_left) {
+				gap_start = vma->vm_prev->vm_end;
+				gap_end = vma->vm_start;
+				goto check_current;
+			}
+		}
+	}
+
+check_highest:
+	/* Check highest gap, which does not precede any rbtree node */
+	gap_start = mm->highest_vm_end;
+	gap_end = ULONG_MAX;  /* Only for VM_BUG_ON below */
+	if (gap_start > high_limit)
+		return -ENOMEM;
+
+found:
+	/* We found a suitable gap. Clip it with the original low_limit. */
+	if (gap_start < info->low_limit)
+		gap_start = info->low_limit;
+
+	/* Adjust gap address to the desired alignment */
+	gap_start += (info->align_offset - gap_start) & info->align_mask;
+
+	VM_BUG_ON(gap_start + info->length > info->high_limit);
+	VM_BUG_ON(gap_start + info->length > gap_end);
+	return gap_start;
+}
+
+unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long length, low_limit, high_limit, gap_start, gap_end;
+
+	/* Adjust search length to account for worst case alignment overhead */
+	length = info->length + info->align_mask;
+	if (length < info->length)
+		return -ENOMEM;
+
+	/*
+	 * Adjust search limits by the desired length.
+	 * See implementation comment at top of unmapped_area().
+	 */
+	gap_end = info->high_limit;
+	if (gap_end < length)
+		return -ENOMEM;
+	high_limit = gap_end - length;
+
+	if (info->low_limit > high_limit)
+		return -ENOMEM;
+	low_limit = info->low_limit + length;
+
+	/* Check highest gap, which does not precede any rbtree node */
+	gap_start = mm->highest_vm_end;
+	if (gap_start <= high_limit)
+		goto found_highest;
+
+	/* Check if rbtree root looks promising */
+	if (RB_EMPTY_ROOT(&mm->mm_rb))
+		return -ENOMEM;
+	vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb);
+	if (vma->rb_subtree_gap < length)
+		return -ENOMEM;
+
+	while (true) {
+		/* Visit right subtree if it looks promising */
+		gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
+		if (gap_start <= high_limit && vma->vm_rb.rb_right) {
+			struct vm_area_struct *right =
+				rb_entry(vma->vm_rb.rb_right,
+					 struct vm_area_struct, vm_rb);
+			if (right->rb_subtree_gap >= length) {
+				vma = right;
+				continue;
+			}
+		}
+
+check_current:
+		/* Check if current node has a suitable gap */
+		gap_end = vma->vm_start;
+		if (gap_end < low_limit)
+			return -ENOMEM;
+		if (gap_start <= high_limit && gap_end - gap_start >= length)
+			goto found;
+
+		/* Visit left subtree if it looks promising */
+		if (vma->vm_rb.rb_left) {
+			struct vm_area_struct *left =
+				rb_entry(vma->vm_rb.rb_left,
+					 struct vm_area_struct, vm_rb);
+			if (left->rb_subtree_gap >= length) {
+				vma = left;
+				continue;
+			}
+		}
+
+		/* Go back up the rbtree to find next candidate node */
+		while (true) {
+			struct rb_node *prev = &vma->vm_rb;
+			if (!rb_parent(prev))
+				return -ENOMEM;
+			vma = rb_entry(rb_parent(prev),
+				       struct vm_area_struct, vm_rb);
+			if (prev == vma->vm_rb.rb_right) {
+				gap_start = vma->vm_prev ?
+					vma->vm_prev->vm_end : 0;
+				goto check_current;
+			}
+		}
+	}
+
+found:
+	/* We found a suitable gap. Clip it with the original high_limit. */
+	if (gap_end > info->high_limit)
+		gap_end = info->high_limit;
+
+found_highest:
+	/* Compute highest gap address at the desired alignment */
+	gap_end -= info->length;
+	gap_end -= (gap_end - info->align_offset) & info->align_mask;
+
+	VM_BUG_ON(gap_end < info->low_limit);
+	VM_BUG_ON(gap_end < gap_start);
+	return gap_end;
+}
+
 /* Get an address range which is currently unmapped.
  * For shmat() with addr=0.
  *
@@ -1557,7 +1757,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long start_addr;
+	struct vm_unmapped_area_info info;
 
 	if (len > TASK_SIZE)
 		return -ENOMEM;
@@ -1572,40 +1772,13 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		    (!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
-	if (len > mm->cached_hole_size) {
-	        start_addr = addr = mm->free_area_cache;
-	} else {
-	        start_addr = addr = TASK_UNMAPPED_BASE;
-	        mm->cached_hole_size = 0;
-	}
 
-full_search:
-	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
-		/* At this point:  (!vma || addr < vma->vm_end). */
-		if (TASK_SIZE - len < addr) {
-			/*
-			 * Start a new search - just in case we missed
-			 * some holes.
-			 */
-			if (start_addr != TASK_UNMAPPED_BASE) {
-				addr = TASK_UNMAPPED_BASE;
-			        start_addr = addr;
-				mm->cached_hole_size = 0;
-				goto full_search;
-			}
-			return -ENOMEM;
-		}
-		if (!vma || addr + len <= vma->vm_start) {
-			/*
-			 * Remember the place where we stopped the search:
-			 */
-			mm->free_area_cache = addr + len;
-			return addr;
-		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
-		addr = vma->vm_end;
-	}
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = TASK_UNMAPPED_BASE;
+	info.high_limit = TASK_SIZE;
+	info.align_mask = 0;
+	return vm_unmapped_area(&info);
 }
 #endif	
 
@@ -1630,7 +1803,8 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
-	unsigned long addr = addr0, start_addr;
+	unsigned long addr = addr0;
+	struct vm_unmapped_area_info info;
 
 	/* requested length too big for entire address space */
 	if (len > TASK_SIZE)
@@ -1648,53 +1822,12 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			return addr;
 	}
 
-	/* check if free_area_cache is useful for us */
-	if (len <= mm->cached_hole_size) {
- 	        mm->cached_hole_size = 0;
- 		mm->free_area_cache = mm->mmap_base;
- 	}
-
-try_again:
-	/* either no address requested or can't fit in requested address hole */
-	start_addr = addr = mm->free_area_cache;
-
-	if (addr < len)
-		goto fail;
-
-	addr -= len;
-	do {
-		/*
-		 * Lookup failure means no vma is above this address,
-		 * else if new region fits below vma->vm_start,
-		 * return with success:
-		 */
-		vma = find_vma(mm, addr);
-		if (!vma || addr+len <= vma->vm_start)
-			/* remember the address as a hint for next time */
-			return (mm->free_area_cache = addr);
-
- 		/* remember the largest hole we saw so far */
- 		if (addr + mm->cached_hole_size < vma->vm_start)
- 		        mm->cached_hole_size = vma->vm_start - addr;
-
-		/* try just below the current vma->vm_start */
-		addr = vma->vm_start-len;
-	} while (len < vma->vm_start);
-
-fail:
-	/*
-	 * if hint left us with no space for the requested
-	 * mapping then try again:
-	 *
-	 * Note: this is different with the case of bottomup
-	 * which does the fully line-search, but we use find_vma
-	 * here that causes some holes skipped.
-	 */
-	if (start_addr != mm->mmap_base) {
-		mm->free_area_cache = mm->mmap_base;
-		mm->cached_hole_size = 0;
-		goto try_again;
-	}
+	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+	info.length = len;
+	info.low_limit = PAGE_SIZE;
+	info.high_limit = mm->mmap_base;
+	info.align_mask = 0;
+	addr = vm_unmapped_area(&info);
 
 	/*
 	 * A failed mmap() very likely causes application failure,
@@ -1702,14 +1835,13 @@ fail:
 	 * can happen with large stack limits and large mmap()
 	 * allocations.
 	 */
-	mm->cached_hole_size = ~0UL;
-  	mm->free_area_cache = TASK_UNMAPPED_BASE;
-	addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
-	/*
-	 * Restore the topdown base:
-	 */
-	mm->free_area_cache = mm->mmap_base;
-	mm->cached_hole_size = ~0UL;
+	if (addr & ~PAGE_MASK) {
+		VM_BUG_ON(addr != -ENOMEM);
+		info.flags = 0;
+		info.low_limit = TASK_UNMAPPED_BASE;
+		info.high_limit = TASK_SIZE;
+		addr = vm_unmapped_area(&info);
+	}
 
 	return addr;
 }
-- 
cgit v1.2.3-55-g7522


From 78bd52097d04205a33a8014a1b8ac01cf1ae9d06 Mon Sep 17 00:00:00 2001
From: Rafael Aquini
Date: Tue, 11 Dec 2012 16:02:31 -0800
Subject: mm: adjust address_space_operations.migratepage() return code

Memory fragmentation introduced by ballooning might reduce significantly
the number of 2MB contiguous memory blocks that can be used within a
guest, thus imposing performance penalties associated with the reduced
number of transparent huge pages that could be used by the guest workload.

This patch-set follows the main idea discussed at 2012 LSFMMS session:
"Ballooning for transparent huge pages" -- http://lwn.net/Articles/490114/
to introduce the required changes to the virtio_balloon driver, as well as
the changes to the core compaction & migration bits, in order to make
those subsystems aware of ballooned pages and allow memory balloon pages
become movable within a guest, thus avoiding the aforementioned
fragmentation issue

Following are numbers that prove this patch benefits on allowing
compaction to be more effective at memory ballooned guests.

Results for STRESS-HIGHALLOC benchmark, from Mel Gorman's mmtests suite,
running on a 4gB RAM KVM guest which was ballooning 512mB RAM in 64mB
chunks, at every minute (inflating/deflating), while test was running:

===BEGIN stress-highalloc

STRESS-HIGHALLOC
                 highalloc-3.7     highalloc-3.7
                     rc4-clean         rc4-patch
Pass 1          55.00 ( 0.00%)    62.00 ( 7.00%)
Pass 2          54.00 ( 0.00%)    62.00 ( 8.00%)
while Rested    75.00 ( 0.00%)    80.00 ( 5.00%)

MMTests Statistics: duration
                 3.7         3.7
           rc4-clean   rc4-patch
User         1207.59     1207.46
System       1300.55     1299.61
Elapsed      2273.72     2157.06

MMTests Statistics: vmstat
                                3.7         3.7
                          rc4-clean   rc4-patch
Page Ins                    3581516     2374368
Page Outs                  11148692    10410332
Swap Ins                         80          47
Swap Outs                      3641         476
Direct pages scanned          37978       33826
Kswapd pages scanned        1828245     1342869
Kswapd pages reclaimed      1710236     1304099
Direct pages reclaimed        32207       31005
Kswapd efficiency               93%         97%
Kswapd velocity             804.077     622.546
Direct efficiency               84%         91%
Direct velocity              16.703      15.682
Percentage direct scans          2%          2%
Page writes by reclaim        79252        9704
Page writes file              75611        9228
Page writes anon               3641         476
Page reclaim immediate        16764       11014
Page rescued immediate            0           0
Slabs scanned               2171904     2152448
Direct inode steals             385        2261
Kswapd inode steals          659137      609670
Kswapd skipped wait               1          69
THP fault alloc                 546         631
THP collapse alloc              361         339
THP splits                      259         263
THP fault fallback               98          50
THP collapse fail                20          17
Compaction stalls               747         499
Compaction success              244         145
Compaction failures             503         354
Compaction pages moved       370888      474837
Compaction move failure       77378       65259

===END stress-highalloc

This patch:

Introduce MIGRATEPAGE_SUCCESS as the default return code for
address_space_operations.migratepage() method and documents the expected
return code for the same method in failure cases.

Signed-off-by: Rafael Aquini <aquini@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/hugetlbfs/inode.c    |  4 ++--
 include/linux/migrate.h |  7 +++++++
 mm/migrate.c            | 33 +++++++++++++++------------------
 3 files changed, 24 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 47e6e2f21e21..4a55f35a6ced 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -582,11 +582,11 @@ static int hugetlbfs_migrate_page(struct address_space *mapping,
 	int rc;
 
 	rc = migrate_huge_page_move_mapping(mapping, newpage, page);
-	if (rc)
+	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
 	migrate_page_copy(newpage, page);
 
-	return 0;
+	return MIGRATEPAGE_SUCCESS;
 }
 
 static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index ce7e6671968b..a4e886d17f87 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -7,6 +7,13 @@
 
 typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 
+/*
+ * Return values from addresss_space_operations.migratepage():
+ * - negative errno on page migration failure;
+ * - zero on page migration success;
+ */
+#define MIGRATEPAGE_SUCCESS		0
+
 #ifdef CONFIG_MIGRATION
 
 extern void putback_lru_pages(struct list_head *l);
diff --git a/mm/migrate.c b/mm/migrate.c
index 1dc4598d2513..33f5f82a6006 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -276,7 +276,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 		/* Anonymous page without mapping */
 		if (page_count(page) != 1)
 			return -EAGAIN;
-		return 0;
+		return MIGRATEPAGE_SUCCESS;
 	}
 
 	spin_lock_irq(&mapping->tree_lock);
@@ -346,7 +346,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	}
 	spin_unlock_irq(&mapping->tree_lock);
 
-	return 0;
+	return MIGRATEPAGE_SUCCESS;
 }
 
 /*
@@ -362,7 +362,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 	if (!mapping) {
 		if (page_count(page) != 1)
 			return -EAGAIN;
-		return 0;
+		return MIGRATEPAGE_SUCCESS;
 	}
 
 	spin_lock_irq(&mapping->tree_lock);
@@ -389,7 +389,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 	page_unfreeze_refs(page, expected_count - 1);
 
 	spin_unlock_irq(&mapping->tree_lock);
-	return 0;
+	return MIGRATEPAGE_SUCCESS;
 }
 
 /*
@@ -476,11 +476,11 @@ int migrate_page(struct address_space *mapping,
 
 	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode);
 
-	if (rc)
+	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
 
 	migrate_page_copy(newpage, page);
-	return 0;
+	return MIGRATEPAGE_SUCCESS;
 }
 EXPORT_SYMBOL(migrate_page);
 
@@ -503,7 +503,7 @@ int buffer_migrate_page(struct address_space *mapping,
 
 	rc = migrate_page_move_mapping(mapping, newpage, page, head, mode);
 
-	if (rc)
+	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
 
 	/*
@@ -539,7 +539,7 @@ int buffer_migrate_page(struct address_space *mapping,
 
 	} while (bh != head);
 
-	return 0;
+	return MIGRATEPAGE_SUCCESS;
 }
 EXPORT_SYMBOL(buffer_migrate_page);
 #endif
@@ -618,7 +618,7 @@ static int fallback_migrate_page(struct address_space *mapping,
  *
  * Return value:
  *   < 0 - error code
- *  == 0 - success
+ *  MIGRATEPAGE_SUCCESS - success
  */
 static int move_to_new_page(struct page *newpage, struct page *page,
 				int remap_swapcache, enum migrate_mode mode)
@@ -655,7 +655,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 	else
 		rc = fallback_migrate_page(mapping, newpage, page, mode);
 
-	if (rc) {
+	if (rc != MIGRATEPAGE_SUCCESS) {
 		newpage->mapping = NULL;
 	} else {
 		if (remap_swapcache)
@@ -804,7 +804,7 @@ skip_unmap:
 		put_anon_vma(anon_vma);
 
 uncharge:
-	mem_cgroup_end_migration(mem, page, newpage, rc == 0);
+	mem_cgroup_end_migration(mem, page, newpage, rc == MIGRATEPAGE_SUCCESS);
 unlock:
 	unlock_page(page);
 out:
@@ -977,7 +977,7 @@ int migrate_pages(struct list_head *from,
 			case -EAGAIN:
 				retry++;
 				break;
-			case 0:
+			case MIGRATEPAGE_SUCCESS:
 				break;
 			default:
 				/* Permanent failure */
@@ -986,15 +986,12 @@ int migrate_pages(struct list_head *from,
 			}
 		}
 	}
-	rc = 0;
+	rc = nr_failed + retry;
 out:
 	if (!swapwrite)
 		current->flags &= ~PF_SWAPWRITE;
 
-	if (rc)
-		return rc;
-
-	return nr_failed + retry;
+	return rc;
 }
 
 int migrate_huge_page(struct page *hpage, new_page_t get_new_page,
@@ -1014,7 +1011,7 @@ int migrate_huge_page(struct page *hpage, new_page_t get_new_page,
 			/* try again */
 			cond_resched();
 			break;
-		case 0:
+		case MIGRATEPAGE_SUCCESS:
 			goto out;
 		default:
 			rc = -EIO;
-- 
cgit v1.2.3-55-g7522


From 252aa6f5be64c90c67b9f066ccff880f6b487d32 Mon Sep 17 00:00:00 2001
From: Rafael Aquini
Date: Tue, 11 Dec 2012 16:02:35 -0800
Subject: mm: redefine address_space.assoc_mapping

Overhaul struct address_space.assoc_mapping renaming it to
address_space.private_data and its type is redefined to void*.  By this
approach we consistently name the .private_* elements from struct
address_space as well as allow extended usage for address_space
association with other data structures through ->private_data.

Also, all users of old ->assoc_mapping element are converted to reflect
its new name and type change (->private_data).

Signed-off-by: Rafael Aquini <aquini@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/buffer.c        | 12 ++++++------
 fs/gfs2/glock.c    |  2 +-
 fs/inode.c         |  2 +-
 fs/nilfs2/page.c   |  2 +-
 include/linux/fs.h |  2 +-
 5 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/buffer.c b/fs/buffer.c
index ec0aca8ba6bf..6e9ed48064fc 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -555,7 +555,7 @@ void emergency_thaw_all(void)
  */
 int sync_mapping_buffers(struct address_space *mapping)
 {
-	struct address_space *buffer_mapping = mapping->assoc_mapping;
+	struct address_space *buffer_mapping = mapping->private_data;
 
 	if (buffer_mapping == NULL || list_empty(&mapping->private_list))
 		return 0;
@@ -588,10 +588,10 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
 	struct address_space *buffer_mapping = bh->b_page->mapping;
 
 	mark_buffer_dirty(bh);
-	if (!mapping->assoc_mapping) {
-		mapping->assoc_mapping = buffer_mapping;
+	if (!mapping->private_data) {
+		mapping->private_data = buffer_mapping;
 	} else {
-		BUG_ON(mapping->assoc_mapping != buffer_mapping);
+		BUG_ON(mapping->private_data != buffer_mapping);
 	}
 	if (!bh->b_assoc_map) {
 		spin_lock(&buffer_mapping->private_lock);
@@ -788,7 +788,7 @@ void invalidate_inode_buffers(struct inode *inode)
 	if (inode_has_buffers(inode)) {
 		struct address_space *mapping = &inode->i_data;
 		struct list_head *list = &mapping->private_list;
-		struct address_space *buffer_mapping = mapping->assoc_mapping;
+		struct address_space *buffer_mapping = mapping->private_data;
 
 		spin_lock(&buffer_mapping->private_lock);
 		while (!list_empty(list))
@@ -811,7 +811,7 @@ int remove_inode_buffers(struct inode *inode)
 	if (inode_has_buffers(inode)) {
 		struct address_space *mapping = &inode->i_data;
 		struct list_head *list = &mapping->private_list;
-		struct address_space *buffer_mapping = mapping->assoc_mapping;
+		struct address_space *buffer_mapping = mapping->private_data;
 
 		spin_lock(&buffer_mapping->private_lock);
 		while (!list_empty(list)) {
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index e6c2fd53cab2..0f22d09f358d 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -768,7 +768,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		mapping->host = s->s_bdev->bd_inode;
 		mapping->flags = 0;
 		mapping_set_gfp_mask(mapping, GFP_NOFS);
-		mapping->assoc_mapping = NULL;
+		mapping->private_data = NULL;
 		mapping->backing_dev_info = s->s_bdi;
 		mapping->writeback_index = 0;
 	}
diff --git a/fs/inode.c b/fs/inode.c
index 64999f144153..14084b72b259 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -165,7 +165,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	mapping->host = inode;
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
-	mapping->assoc_mapping = NULL;
+	mapping->private_data = NULL;
 	mapping->backing_dev_info = &default_backing_dev_info;
 	mapping->writeback_index = 0;
 
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 3e7b2a0dc0c8..07f76db04ec7 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -431,7 +431,7 @@ void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
 	mapping->host = inode;
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
-	mapping->assoc_mapping = NULL;
+	mapping->private_data = NULL;
 	mapping->backing_dev_info = bdi;
 	mapping->a_ops = &empty_aops;
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 75fe9a134803..408fb1e77a0a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -418,7 +418,7 @@ struct address_space {
 	struct backing_dev_info *backing_dev_info; /* device readahead, etc */
 	spinlock_t		private_lock;	/* for use by the address_space */
 	struct list_head	private_list;	/* ditto */
-	struct address_space	*assoc_mapping;	/* ditto */
+	void			*private_data;	/* ditto */
 } __attribute__((aligned(sizeof(long))));
 	/*
 	 * On most architectures that alignment is already the case; but
-- 
cgit v1.2.3-55-g7522


From 18468d93e53b037e1a04ec58398eab763d054064 Mon Sep 17 00:00:00 2001
From: Rafael Aquini
Date: Tue, 11 Dec 2012 16:02:38 -0800
Subject: mm: introduce a common interface for balloon pages mobility

Memory fragmentation introduced by ballooning might reduce significantly
the number of 2MB contiguous memory blocks that can be used within a guest,
thus imposing performance penalties associated with the reduced number of
transparent huge pages that could be used by the guest workload.

This patch introduces a common interface to help a balloon driver on
making its page set movable to compaction, and thus allowing the system
to better leverage the compation efforts on memory defragmentation.

[akpm@linux-foundation.org: use PAGE_FLAGS_CHECK_AT_PREP, s/__balloon_page_flags/page_flags_cleared/, small cleanups]
[rientjes@google.com: allow balloon compaction for any system with memory compaction enabled, which is the defconfig]
Signed-off-by: Rafael Aquini <aquini@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/balloon_compaction.h | 272 +++++++++++++++++++++++++++++++++
 include/linux/migrate.h            |  10 ++
 include/linux/pagemap.h            |  16 ++
 mm/Kconfig                         |  15 ++
 mm/Makefile                        |   3 +-
 mm/balloon_compaction.c            | 302 +++++++++++++++++++++++++++++++++++++
 6 files changed, 617 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/balloon_compaction.h
 create mode 100644 mm/balloon_compaction.c

(limited to 'include')

diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
new file mode 100644
index 000000000000..f7f1d7169b11
--- /dev/null
+++ b/include/linux/balloon_compaction.h
@@ -0,0 +1,272 @@
+/*
+ * include/linux/balloon_compaction.h
+ *
+ * Common interface definitions for making balloon pages movable by compaction.
+ *
+ * Despite being perfectly possible to perform ballooned pages migration, they
+ * make a special corner case to compaction scans because balloon pages are not
+ * enlisted at any LRU list like the other pages we do compact / migrate.
+ *
+ * As the page isolation scanning step a compaction thread does is a lockless
+ * procedure (from a page standpoint), it might bring some racy situations while
+ * performing balloon page compaction. In order to sort out these racy scenarios
+ * and safely perform balloon's page compaction and migration we must, always,
+ * ensure following these three simple rules:
+ *
+ *   i. when updating a balloon's page ->mapping element, strictly do it under
+ *      the following lock order, independently of the far superior
+ *      locking scheme (lru_lock, balloon_lock):
+ *	    +-page_lock(page);
+ *	      +--spin_lock_irq(&b_dev_info->pages_lock);
+ *	            ... page->mapping updates here ...
+ *
+ *  ii. before isolating or dequeueing a balloon page from the balloon device
+ *      pages list, the page reference counter must be raised by one and the
+ *      extra refcount must be dropped when the page is enqueued back into
+ *      the balloon device page list, thus a balloon page keeps its reference
+ *      counter raised only while it is under our special handling;
+ *
+ * iii. after the lockless scan step have selected a potential balloon page for
+ *      isolation, re-test the page->mapping flags and the page ref counter
+ *      under the proper page lock, to ensure isolating a valid balloon page
+ *      (not yet isolated, nor under release procedure)
+ *
+ * The functions provided by this interface are placed to help on coping with
+ * the aforementioned balloon page corner case, as well as to ensure the simple
+ * set of exposed rules are satisfied while we are dealing with balloon pages
+ * compaction / migration.
+ *
+ * Copyright (C) 2012, Red Hat, Inc.  Rafael Aquini <aquini@redhat.com>
+ */
+#ifndef _LINUX_BALLOON_COMPACTION_H
+#define _LINUX_BALLOON_COMPACTION_H
+#include <linux/pagemap.h>
+#include <linux/page-flags.h>
+#include <linux/migrate.h>
+#include <linux/gfp.h>
+#include <linux/err.h>
+
+/*
+ * Balloon device information descriptor.
+ * This struct is used to allow the common balloon compaction interface
+ * procedures to find the proper balloon device holding memory pages they'll
+ * have to cope for page compaction / migration, as well as it serves the
+ * balloon driver as a page book-keeper for its registered balloon devices.
+ */
+struct balloon_dev_info {
+	void *balloon_device;		/* balloon device descriptor */
+	struct address_space *mapping;	/* balloon special page->mapping */
+	unsigned long isolated_pages;	/* # of isolated pages for migration */
+	spinlock_t pages_lock;		/* Protection to pages list */
+	struct list_head pages;		/* Pages enqueued & handled to Host */
+};
+
+extern struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info);
+extern struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info);
+extern struct balloon_dev_info *balloon_devinfo_alloc(
+						void *balloon_dev_descriptor);
+
+static inline void balloon_devinfo_free(struct balloon_dev_info *b_dev_info)
+{
+	kfree(b_dev_info);
+}
+
+/*
+ * balloon_page_free - release a balloon page back to the page free lists
+ * @page: ballooned page to be set free
+ *
+ * This function must be used to properly set free an isolated/dequeued balloon
+ * page at the end of a sucessful page migration, or at the balloon driver's
+ * page release procedure.
+ */
+static inline void balloon_page_free(struct page *page)
+{
+	/*
+	 * Balloon pages always get an extra refcount before being isolated
+	 * and before being dequeued to help on sorting out fortuite colisions
+	 * between a thread attempting to isolate and another thread attempting
+	 * to release the very same balloon page.
+	 *
+	 * Before we handle the page back to Buddy, lets drop its extra refcnt.
+	 */
+	put_page(page);
+	__free_page(page);
+}
+
+#ifdef CONFIG_BALLOON_COMPACTION
+extern bool balloon_page_isolate(struct page *page);
+extern void balloon_page_putback(struct page *page);
+extern int balloon_page_migrate(struct page *newpage,
+				struct page *page, enum migrate_mode mode);
+extern struct address_space
+*balloon_mapping_alloc(struct balloon_dev_info *b_dev_info,
+			const struct address_space_operations *a_ops);
+
+static inline void balloon_mapping_free(struct address_space *balloon_mapping)
+{
+	kfree(balloon_mapping);
+}
+
+/*
+ * page_flags_cleared - helper to perform balloon @page ->flags tests.
+ *
+ * As balloon pages are obtained from buddy and we do not play with page->flags
+ * at driver level (exception made when we get the page lock for compaction),
+ * we can safely identify a ballooned page by checking if the
+ * PAGE_FLAGS_CHECK_AT_PREP page->flags are all cleared.  This approach also
+ * helps us skip ballooned pages that are locked for compaction or release, thus
+ * mitigating their racy check at balloon_page_movable()
+ */
+static inline bool page_flags_cleared(struct page *page)
+{
+	return !(page->flags & PAGE_FLAGS_CHECK_AT_PREP);
+}
+
+/*
+ * __is_movable_balloon_page - helper to perform @page mapping->flags tests
+ */
+static inline bool __is_movable_balloon_page(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	return mapping_balloon(mapping);
+}
+
+/*
+ * balloon_page_movable - test page->mapping->flags to identify balloon pages
+ *			  that can be moved by compaction/migration.
+ *
+ * This function is used at core compaction's page isolation scheme, therefore
+ * most pages exposed to it are not enlisted as balloon pages and so, to avoid
+ * undesired side effects like racing against __free_pages(), we cannot afford
+ * holding the page locked while testing page->mapping->flags here.
+ *
+ * As we might return false positives in the case of a balloon page being just
+ * released under us, the page->mapping->flags need to be re-tested later,
+ * under the proper page lock, at the functions that will be coping with the
+ * balloon page case.
+ */
+static inline bool balloon_page_movable(struct page *page)
+{
+	/*
+	 * Before dereferencing and testing mapping->flags, let's make sure
+	 * this is not a page that uses ->mapping in a different way
+	 */
+	if (page_flags_cleared(page) && !page_mapped(page) &&
+	    page_count(page) == 1)
+		return __is_movable_balloon_page(page);
+
+	return false;
+}
+
+/*
+ * balloon_page_insert - insert a page into the balloon's page list and make
+ *		         the page->mapping assignment accordingly.
+ * @page    : page to be assigned as a 'balloon page'
+ * @mapping : allocated special 'balloon_mapping'
+ * @head    : balloon's device page list head
+ *
+ * Caller must ensure the page is locked and the spin_lock protecting balloon
+ * pages list is held before inserting a page into the balloon device.
+ */
+static inline void balloon_page_insert(struct page *page,
+				       struct address_space *mapping,
+				       struct list_head *head)
+{
+	page->mapping = mapping;
+	list_add(&page->lru, head);
+}
+
+/*
+ * balloon_page_delete - delete a page from balloon's page list and clear
+ *			 the page->mapping assignement accordingly.
+ * @page    : page to be released from balloon's page list
+ *
+ * Caller must ensure the page is locked and the spin_lock protecting balloon
+ * pages list is held before deleting a page from the balloon device.
+ */
+static inline void balloon_page_delete(struct page *page)
+{
+	page->mapping = NULL;
+	list_del(&page->lru);
+}
+
+/*
+ * balloon_page_device - get the b_dev_info descriptor for the balloon device
+ *			 that enqueues the given page.
+ */
+static inline struct balloon_dev_info *balloon_page_device(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	if (likely(mapping))
+		return mapping->private_data;
+
+	return NULL;
+}
+
+static inline gfp_t balloon_mapping_gfp_mask(void)
+{
+	return GFP_HIGHUSER_MOVABLE;
+}
+
+static inline bool balloon_compaction_check(void)
+{
+	return true;
+}
+
+#else /* !CONFIG_BALLOON_COMPACTION */
+
+static inline void *balloon_mapping_alloc(void *balloon_device,
+				const struct address_space_operations *a_ops)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void balloon_mapping_free(struct address_space *balloon_mapping)
+{
+	return;
+}
+
+static inline void balloon_page_insert(struct page *page,
+				       struct address_space *mapping,
+				       struct list_head *head)
+{
+	list_add(&page->lru, head);
+}
+
+static inline void balloon_page_delete(struct page *page)
+{
+	list_del(&page->lru);
+}
+
+static inline bool balloon_page_movable(struct page *page)
+{
+	return false;
+}
+
+static inline bool balloon_page_isolate(struct page *page)
+{
+	return false;
+}
+
+static inline void balloon_page_putback(struct page *page)
+{
+	return;
+}
+
+static inline int balloon_page_migrate(struct page *newpage,
+				struct page *page, enum migrate_mode mode)
+{
+	return 0;
+}
+
+static inline gfp_t balloon_mapping_gfp_mask(void)
+{
+	return GFP_HIGHUSER;
+}
+
+static inline bool balloon_compaction_check(void)
+{
+	return false;
+}
+#endif /* CONFIG_BALLOON_COMPACTION */
+#endif /* _LINUX_BALLOON_COMPACTION_H */
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index a4e886d17f87..ce42847ed35f 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -11,8 +11,18 @@ typedef struct page *new_page_t(struct page *, unsigned long private, int **);
  * Return values from addresss_space_operations.migratepage():
  * - negative errno on page migration failure;
  * - zero on page migration success;
+ *
+ * The balloon page migration introduces this special case where a 'distinct'
+ * return code is used to flag a successful page migration to unmap_and_move().
+ * This approach is necessary because page migration can race against balloon
+ * deflation procedure, and for such case we could introduce a nasty page leak
+ * if a successfully migrated balloon page gets released concurrently with
+ * migration's unmap_and_move() wrap-up steps.
  */
 #define MIGRATEPAGE_SUCCESS		0
+#define MIGRATEPAGE_BALLOON_SUCCESS	1 /* special ret code for balloon page
+					   * sucessful migration case.
+					   */
 
 #ifdef CONFIG_MIGRATION
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e42c762f0dc7..6da609d14c15 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -24,6 +24,7 @@ enum mapping_flags {
 	AS_ENOSPC	= __GFP_BITS_SHIFT + 1,	/* ENOSPC on async write */
 	AS_MM_ALL_LOCKS	= __GFP_BITS_SHIFT + 2,	/* under mm_take_all_locks() */
 	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
+	AS_BALLOON_MAP  = __GFP_BITS_SHIFT + 4, /* balloon page special map */
 };
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
@@ -53,6 +54,21 @@ static inline int mapping_unevictable(struct address_space *mapping)
 	return !!mapping;
 }
 
+static inline void mapping_set_balloon(struct address_space *mapping)
+{
+	set_bit(AS_BALLOON_MAP, &mapping->flags);
+}
+
+static inline void mapping_clear_balloon(struct address_space *mapping)
+{
+	clear_bit(AS_BALLOON_MAP, &mapping->flags);
+}
+
+static inline int mapping_balloon(struct address_space *mapping)
+{
+	return mapping && test_bit(AS_BALLOON_MAP, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
diff --git a/mm/Kconfig b/mm/Kconfig
index a3f8dddaaab3..e6651c5de14f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -187,6 +187,21 @@ config SPLIT_PTLOCK_CPUS
 	default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC
 	default "4"
 
+#
+# support for memory balloon compaction
+config BALLOON_COMPACTION
+	bool "Allow for balloon memory compaction/migration"
+	def_bool y
+	depends on COMPACTION && VIRTIO_BALLOON
+	help
+	  Memory fragmentation introduced by ballooning might reduce
+	  significantly the number of 2MB contiguous memory blocks that can be
+	  used within a guest, thus imposing performance penalties associated
+	  with the reduced number of transparent huge pages that could be used
+	  by the guest workload. Allowing the compaction & migration for memory
+	  pages enlisted as being part of memory balloon devices avoids the
+	  scenario aforementioned and helps improving memory defragmentation.
+
 #
 # support for memory compaction
 config COMPACTION
diff --git a/mm/Makefile b/mm/Makefile
index 6b025f80af34..3a4628751f89 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -16,7 +16,8 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
-			   compaction.o interval_tree.o $(mmu-y)
+			   compaction.o balloon_compaction.o \
+			   interval_tree.o $(mmu-y)
 
 obj-y += init-mm.o
 
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
new file mode 100644
index 000000000000..07dbc8ec46cf
--- /dev/null
+++ b/mm/balloon_compaction.c
@@ -0,0 +1,302 @@
+/*
+ * mm/balloon_compaction.c
+ *
+ * Common interface for making balloon pages movable by compaction.
+ *
+ * Copyright (C) 2012, Red Hat, Inc.  Rafael Aquini <aquini@redhat.com>
+ */
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/balloon_compaction.h>
+
+/*
+ * balloon_devinfo_alloc - allocates a balloon device information descriptor.
+ * @balloon_dev_descriptor: pointer to reference the balloon device which
+ *                          this struct balloon_dev_info will be servicing.
+ *
+ * Driver must call it to properly allocate and initialize an instance of
+ * struct balloon_dev_info which will be used to reference a balloon device
+ * as well as to keep track of the balloon device page list.
+ */
+struct balloon_dev_info *balloon_devinfo_alloc(void *balloon_dev_descriptor)
+{
+	struct balloon_dev_info *b_dev_info;
+	b_dev_info = kmalloc(sizeof(*b_dev_info), GFP_KERNEL);
+	if (!b_dev_info)
+		return ERR_PTR(-ENOMEM);
+
+	b_dev_info->balloon_device = balloon_dev_descriptor;
+	b_dev_info->mapping = NULL;
+	b_dev_info->isolated_pages = 0;
+	spin_lock_init(&b_dev_info->pages_lock);
+	INIT_LIST_HEAD(&b_dev_info->pages);
+
+	return b_dev_info;
+}
+EXPORT_SYMBOL_GPL(balloon_devinfo_alloc);
+
+/*
+ * balloon_page_enqueue - allocates a new page and inserts it into the balloon
+ *			  page list.
+ * @b_dev_info: balloon device decriptor where we will insert a new page to
+ *
+ * Driver must call it to properly allocate a new enlisted balloon page
+ * before definetively removing it from the guest system.
+ * This function returns the page address for the recently enqueued page or
+ * NULL in the case we fail to allocate a new page this turn.
+ */
+struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
+{
+	unsigned long flags;
+	struct page *page = alloc_page(balloon_mapping_gfp_mask() |
+					__GFP_NOMEMALLOC | __GFP_NORETRY);
+	if (!page)
+		return NULL;
+
+	/*
+	 * Block others from accessing the 'page' when we get around to
+	 * establishing additional references. We should be the only one
+	 * holding a reference to the 'page' at this point.
+	 */
+	BUG_ON(!trylock_page(page));
+	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	balloon_page_insert(page, b_dev_info->mapping, &b_dev_info->pages);
+	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+	unlock_page(page);
+	return page;
+}
+EXPORT_SYMBOL_GPL(balloon_page_enqueue);
+
+/*
+ * balloon_page_dequeue - removes a page from balloon's page list and returns
+ *			  the its address to allow the driver release the page.
+ * @b_dev_info: balloon device decriptor where we will grab a page from.
+ *
+ * Driver must call it to properly de-allocate a previous enlisted balloon page
+ * before definetively releasing it back to the guest system.
+ * This function returns the page address for the recently dequeued page or
+ * NULL in the case we find balloon's page list temporarily empty due to
+ * compaction isolated pages.
+ */
+struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
+{
+	struct page *page, *tmp;
+	unsigned long flags;
+	bool dequeued_page;
+
+	dequeued_page = false;
+	list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) {
+		/*
+		 * Block others from accessing the 'page' while we get around
+		 * establishing additional references and preparing the 'page'
+		 * to be released by the balloon driver.
+		 */
+		if (trylock_page(page)) {
+			spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+			/*
+			 * Raise the page refcount here to prevent any wrong
+			 * attempt to isolate this page, in case of coliding
+			 * with balloon_page_isolate() just after we release
+			 * the page lock.
+			 *
+			 * balloon_page_free() will take care of dropping
+			 * this extra refcount later.
+			 */
+			get_page(page);
+			balloon_page_delete(page);
+			spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+			unlock_page(page);
+			dequeued_page = true;
+			break;
+		}
+	}
+
+	if (!dequeued_page) {
+		/*
+		 * If we are unable to dequeue a balloon page because the page
+		 * list is empty and there is no isolated pages, then something
+		 * went out of track and some balloon pages are lost.
+		 * BUG() here, otherwise the balloon driver may get stuck into
+		 * an infinite loop while attempting to release all its pages.
+		 */
+		spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+		if (unlikely(list_empty(&b_dev_info->pages) &&
+			     !b_dev_info->isolated_pages))
+			BUG();
+		spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+		page = NULL;
+	}
+	return page;
+}
+EXPORT_SYMBOL_GPL(balloon_page_dequeue);
+
+#ifdef CONFIG_BALLOON_COMPACTION
+/*
+ * balloon_mapping_alloc - allocates a special ->mapping for ballooned pages.
+ * @b_dev_info: holds the balloon device information descriptor.
+ * @a_ops: balloon_mapping address_space_operations descriptor.
+ *
+ * Driver must call it to properly allocate and initialize an instance of
+ * struct address_space which will be used as the special page->mapping for
+ * balloon device enlisted page instances.
+ */
+struct address_space *balloon_mapping_alloc(struct balloon_dev_info *b_dev_info,
+				const struct address_space_operations *a_ops)
+{
+	struct address_space *mapping;
+
+	mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
+	if (!mapping)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * Give a clean 'zeroed' status to all elements of this special
+	 * balloon page->mapping struct address_space instance.
+	 */
+	address_space_init_once(mapping);
+
+	/*
+	 * Set mapping->flags appropriately, to allow balloon pages
+	 * ->mapping identification.
+	 */
+	mapping_set_balloon(mapping);
+	mapping_set_gfp_mask(mapping, balloon_mapping_gfp_mask());
+
+	/* balloon's page->mapping->a_ops callback descriptor */
+	mapping->a_ops = a_ops;
+
+	/*
+	 * Establish a pointer reference back to the balloon device descriptor
+	 * this particular page->mapping will be servicing.
+	 * This is used by compaction / migration procedures to identify and
+	 * access the balloon device pageset while isolating / migrating pages.
+	 *
+	 * As some balloon drivers can register multiple balloon devices
+	 * for a single guest, this also helps compaction / migration to
+	 * properly deal with multiple balloon pagesets, when required.
+	 */
+	mapping->private_data = b_dev_info;
+	b_dev_info->mapping = mapping;
+
+	return mapping;
+}
+EXPORT_SYMBOL_GPL(balloon_mapping_alloc);
+
+static inline void __isolate_balloon_page(struct page *page)
+{
+	struct balloon_dev_info *b_dev_info = page->mapping->private_data;
+	unsigned long flags;
+	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	list_del(&page->lru);
+	b_dev_info->isolated_pages++;
+	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+}
+
+static inline void __putback_balloon_page(struct page *page)
+{
+	struct balloon_dev_info *b_dev_info = page->mapping->private_data;
+	unsigned long flags;
+	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	list_add(&page->lru, &b_dev_info->pages);
+	b_dev_info->isolated_pages--;
+	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+}
+
+static inline int __migrate_balloon_page(struct address_space *mapping,
+		struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+	return page->mapping->a_ops->migratepage(mapping, newpage, page, mode);
+}
+
+/* __isolate_lru_page() counterpart for a ballooned page */
+bool balloon_page_isolate(struct page *page)
+{
+	/*
+	 * Avoid burning cycles with pages that are yet under __free_pages(),
+	 * or just got freed under us.
+	 *
+	 * In case we 'win' a race for a balloon page being freed under us and
+	 * raise its refcount preventing __free_pages() from doing its job
+	 * the put_page() at the end of this block will take care of
+	 * release this page, thus avoiding a nasty leakage.
+	 */
+	if (likely(get_page_unless_zero(page))) {
+		/*
+		 * As balloon pages are not isolated from LRU lists, concurrent
+		 * compaction threads can race against page migration functions
+		 * as well as race against the balloon driver releasing a page.
+		 *
+		 * In order to avoid having an already isolated balloon page
+		 * being (wrongly) re-isolated while it is under migration,
+		 * or to avoid attempting to isolate pages being released by
+		 * the balloon driver, lets be sure we have the page lock
+		 * before proceeding with the balloon page isolation steps.
+		 */
+		if (likely(trylock_page(page))) {
+			/*
+			 * A ballooned page, by default, has just one refcount.
+			 * Prevent concurrent compaction threads from isolating
+			 * an already isolated balloon page by refcount check.
+			 */
+			if (__is_movable_balloon_page(page) &&
+			    page_count(page) == 2) {
+				__isolate_balloon_page(page);
+				unlock_page(page);
+				return true;
+			}
+			unlock_page(page);
+		}
+		put_page(page);
+	}
+	return false;
+}
+
+/* putback_lru_page() counterpart for a ballooned page */
+void balloon_page_putback(struct page *page)
+{
+	/*
+	 * 'lock_page()' stabilizes the page and prevents races against
+	 * concurrent isolation threads attempting to re-isolate it.
+	 */
+	lock_page(page);
+
+	if (__is_movable_balloon_page(page)) {
+		__putback_balloon_page(page);
+		/* drop the extra ref count taken for page isolation */
+		put_page(page);
+	} else {
+		WARN_ON(1);
+		dump_page(page);
+	}
+	unlock_page(page);
+}
+
+/* move_to_new_page() counterpart for a ballooned page */
+int balloon_page_migrate(struct page *newpage,
+			 struct page *page, enum migrate_mode mode)
+{
+	struct address_space *mapping;
+	int rc = -EAGAIN;
+
+	/*
+	 * Block others from accessing the 'newpage' when we get around to
+	 * establishing additional references. We should be the only one
+	 * holding a reference to the 'newpage' at this point.
+	 */
+	BUG_ON(!trylock_page(newpage));
+
+	if (WARN_ON(!__is_movable_balloon_page(page))) {
+		dump_page(page);
+		unlock_page(newpage);
+		return rc;
+	}
+
+	mapping = page->mapping;
+	if (mapping)
+		rc = __migrate_balloon_page(mapping, newpage, page, mode);
+
+	unlock_page(newpage);
+	return rc;
+}
+#endif /* CONFIG_BALLOON_COMPACTION */
-- 
cgit v1.2.3-55-g7522


From 5733c7d11dff44e98d2ca16617886a78086b354f Mon Sep 17 00:00:00 2001
From: Rafael Aquini
Date: Tue, 11 Dec 2012 16:02:47 -0800
Subject: mm: introduce putback_movable_pages()

The PATCH "mm: introduce compaction and migration for virtio ballooned pages"
hacks around putback_lru_pages() in order to allow ballooned pages to be
re-inserted on balloon page list as if a ballooned page was like a LRU page.

As ballooned pages are not legitimate LRU pages, this patch introduces
putback_movable_pages() to properly cope with cases where the isolated
pageset contains ballooned pages and LRU pages, thus fixing the mentioned
inelegant hack around putback_lru_pages().

Signed-off-by: Rafael Aquini <aquini@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/migrate.h |  2 ++
 mm/compaction.c         |  6 +++---
 mm/migrate.c            | 20 ++++++++++++++++++++
 mm/page_alloc.c         |  2 +-
 4 files changed, 26 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index ce42847ed35f..0b5865c61efd 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -27,6 +27,7 @@ typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 #ifdef CONFIG_MIGRATION
 
 extern void putback_lru_pages(struct list_head *l);
+extern void putback_movable_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
 extern int migrate_pages(struct list_head *l, new_page_t x,
@@ -50,6 +51,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 #else
 
 static inline void putback_lru_pages(struct list_head *l) {}
+static inline void putback_movable_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private, bool offlining,
 		enum migrate_mode mode) { return -ENOSYS; }
diff --git a/mm/compaction.c b/mm/compaction.c
index 470474c03b61..d24dd2d7bad4 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1003,7 +1003,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		switch (isolate_migratepages(zone, cc)) {
 		case ISOLATE_ABORT:
 			ret = COMPACT_PARTIAL;
-			putback_lru_pages(&cc->migratepages);
+			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
 			goto out;
 		case ISOLATE_NONE:
@@ -1026,9 +1026,9 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
 						nr_remaining);
 
-		/* Release LRU pages not migrated */
+		/* Release isolated pages not migrated */
 		if (err) {
-			putback_lru_pages(&cc->migratepages);
+			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
 			if (err == -ENOMEM) {
 				ret = COMPACT_PARTIAL;
diff --git a/mm/migrate.c b/mm/migrate.c
index 427343c0c296..3f675ca08279 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -76,6 +76,26 @@ void putback_lru_pages(struct list_head *l)
 	struct page *page;
 	struct page *page2;
 
+	list_for_each_entry_safe(page, page2, l, lru) {
+		list_del(&page->lru);
+		dec_zone_page_state(page, NR_ISOLATED_ANON +
+				page_is_file_cache(page));
+			putback_lru_page(page);
+	}
+}
+
+/*
+ * Put previously isolated pages back onto the appropriate lists
+ * from where they were once taken off for compaction/migration.
+ *
+ * This function shall be used instead of putback_lru_pages(),
+ * whenever the isolated pageset has been built by isolate_migratepages_range()
+ */
+void putback_movable_pages(struct list_head *l)
+{
+	struct page *page;
+	struct page *page2;
+
 	list_for_each_entry_safe(page, page2, l, lru) {
 		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5a7b7611d4e4..d9fbac1b5030 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5761,7 +5761,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 				    0, false, MIGRATE_SYNC);
 	}
 
-	putback_lru_pages(&cc->migratepages);
+	putback_movable_pages(&cc->migratepages);
 	return ret > 0 ? 0 : ret;
 }
 
-- 
cgit v1.2.3-55-g7522


From fa264375175a382621c5344a6508e02ec4d1c3c0 Mon Sep 17 00:00:00 2001
From: Yasuaki Ishimatsu
Date: Tue, 11 Dec 2012 16:02:52 -0800
Subject: mm: cleanup register_node()

register_node() is defined as extern in include/linux/node.h.  But the
function is only called from register_one_node() in driver/base/node.c.

So the patch defines register_node() as static.

Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/node.c  | 2 +-
 include/linux/node.h | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 4282e82d9f26..fffed4c96bb3 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -277,7 +277,7 @@ static void node_device_release(struct device *dev)
  *
  * Initialize and register the node device.
  */
-int register_node(struct node *node, int num, struct node *parent)
+static int register_node(struct node *node, int num, struct node *parent)
 {
 	int error;
 
diff --git a/include/linux/node.h b/include/linux/node.h
index 10316f1c68a9..2115ad5d6f19 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -30,7 +30,6 @@ struct memory_block;
 extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
-extern int register_node(struct node *, int, struct node *);
 extern void unregister_node(struct node *node);
 #ifdef CONFIG_NUMA
 extern int register_one_node(int nid);
-- 
cgit v1.2.3-55-g7522


From a9c58b907dbc6821533dfc295b63caf111ff1f16 Mon Sep 17 00:00:00 2001
From: David Rientjes
Date: Tue, 11 Dec 2012 16:02:54 -0800
Subject: mm, oom: change type of oom_score_adj to short

The maximum oom_score_adj is 1000 and the minimum oom_score_adj is -1000,
so this range can be represented by the signed short type with no
functional change.  The extra space this frees up in struct signal_struct
will be used for per-thread oom kill flags in the next patch.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Cc: Anton Vorontsov <anton.vorontsov@linaro.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/staging/android/lowmemorykiller.c | 16 ++++++++--------
 fs/proc/base.c                            | 10 +++++-----
 include/linux/oom.h                       |  4 ++--
 include/linux/sched.h                     |  6 +++---
 include/trace/events/oom.h                |  4 ++--
 include/trace/events/task.h               |  8 ++++----
 mm/ksm.c                                  |  2 +-
 mm/oom_kill.c                             | 10 +++++-----
 mm/swapfile.c                             |  2 +-
 9 files changed, 31 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index b91e4bc332a7..3b91b0fd4de3 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -40,7 +40,7 @@
 #include <linux/notifier.h>
 
 static uint32_t lowmem_debug_level = 2;
-static int lowmem_adj[6] = {
+static short lowmem_adj[6] = {
 	0,
 	1,
 	6,
@@ -70,9 +70,9 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
 	int rem = 0;
 	int tasksize;
 	int i;
-	int min_score_adj = OOM_SCORE_ADJ_MAX + 1;
+	short min_score_adj = OOM_SCORE_ADJ_MAX + 1;
 	int selected_tasksize = 0;
-	int selected_oom_score_adj;
+	short selected_oom_score_adj;
 	int array_size = ARRAY_SIZE(lowmem_adj);
 	int other_free = global_page_state(NR_FREE_PAGES);
 	int other_file = global_page_state(NR_FILE_PAGES) -
@@ -90,7 +90,7 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
 		}
 	}
 	if (sc->nr_to_scan > 0)
-		lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d, ma %d\n",
+		lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d, ma %hd\n",
 				sc->nr_to_scan, sc->gfp_mask, other_free,
 				other_file, min_score_adj);
 	rem = global_page_state(NR_ACTIVE_ANON) +
@@ -107,7 +107,7 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
 	rcu_read_lock();
 	for_each_process(tsk) {
 		struct task_struct *p;
-		int oom_score_adj;
+		short oom_score_adj;
 
 		if (tsk->flags & PF_KTHREAD)
 			continue;
@@ -141,11 +141,11 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
 		selected = p;
 		selected_tasksize = tasksize;
 		selected_oom_score_adj = oom_score_adj;
-		lowmem_print(2, "select %d (%s), adj %d, size %d, to kill\n",
+		lowmem_print(2, "select %d (%s), adj %hd, size %d, to kill\n",
 			     p->pid, p->comm, oom_score_adj, tasksize);
 	}
 	if (selected) {
-		lowmem_print(1, "send sigkill to %d (%s), adj %d, size %d\n",
+		lowmem_print(1, "send sigkill to %d (%s), adj %hd, size %d\n",
 			     selected->pid, selected->comm,
 			     selected_oom_score_adj, selected_tasksize);
 		lowmem_deathpending_timeout = jiffies + HZ;
@@ -176,7 +176,7 @@ static void __exit lowmem_exit(void)
 }
 
 module_param_named(cost, lowmem_shrinker.seeks, int, S_IRUGO | S_IWUSR);
-module_param_array_named(adj, lowmem_adj, int, &lowmem_adj_size,
+module_param_array_named(adj, lowmem_adj, short, &lowmem_adj_size,
 			 S_IRUGO | S_IWUSR);
 module_param_array_named(minfree, lowmem_minfree, uint, &lowmem_minfree_size,
 			 S_IRUGO | S_IWUSR);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9e28356a959a..aa63d25157b8 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -985,7 +985,7 @@ static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
 {
 	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
 	char buffer[PROC_NUMBUF];
-	int oom_score_adj = OOM_SCORE_ADJ_MIN;
+	short oom_score_adj = OOM_SCORE_ADJ_MIN;
 	unsigned long flags;
 	size_t len;
 
@@ -996,7 +996,7 @@ static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
 		unlock_task_sighand(task, &flags);
 	}
 	put_task_struct(task);
-	len = snprintf(buffer, sizeof(buffer), "%d\n", oom_score_adj);
+	len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj);
 	return simple_read_from_buffer(buf, count, ppos, buffer, len);
 }
 
@@ -1043,15 +1043,15 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 		goto err_task_lock;
 	}
 
-	if (oom_score_adj < task->signal->oom_score_adj_min &&
+	if ((short)oom_score_adj < task->signal->oom_score_adj_min &&
 			!capable(CAP_SYS_RESOURCE)) {
 		err = -EACCES;
 		goto err_sighand;
 	}
 
-	task->signal->oom_score_adj = oom_score_adj;
+	task->signal->oom_score_adj = (short)oom_score_adj;
 	if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
-		task->signal->oom_score_adj_min = oom_score_adj;
+		task->signal->oom_score_adj_min = (short)oom_score_adj;
 	trace_oom_score_adj_update(task);
 
 err_sighand:
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 4a4188da4570..922dab164eb0 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -29,8 +29,8 @@ enum oom_scan_t {
 	OOM_SCAN_SELECT,	/* always select this thread first */
 };
 
-extern void compare_swap_oom_score_adj(int old_val, int new_val);
-extern int test_set_oom_score_adj(int new_val);
+extern void compare_swap_oom_score_adj(short old_val, short new_val);
+extern short test_set_oom_score_adj(short new_val);
 
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a02df2e..ed30456152da 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -631,9 +631,9 @@ struct signal_struct {
 	struct rw_semaphore group_rwsem;
 #endif
 
-	int oom_score_adj;	/* OOM kill score adjustment */
-	int oom_score_adj_min;	/* OOM kill score adjustment minimum value.
-				 * Only settable by CAP_SYS_RESOURCE. */
+	short oom_score_adj;		/* OOM kill score adjustment */
+	short oom_score_adj_min;	/* OOM kill score adjustment min value.
+					 * Only settable by CAP_SYS_RESOURCE. */
 
 	struct mutex cred_guard_mutex;	/* guard against foreign influences on
 					 * credential calculations
diff --git a/include/trace/events/oom.h b/include/trace/events/oom.h
index dd4ba3b92002..1e974983757e 100644
--- a/include/trace/events/oom.h
+++ b/include/trace/events/oom.h
@@ -14,7 +14,7 @@ TRACE_EVENT(oom_score_adj_update,
 	TP_STRUCT__entry(
 		__field(	pid_t,	pid)
 		__array(	char,	comm,	TASK_COMM_LEN )
-		__field(	 int,	oom_score_adj)
+		__field(	short,	oom_score_adj)
 	),
 
 	TP_fast_assign(
@@ -23,7 +23,7 @@ TRACE_EVENT(oom_score_adj_update,
 		__entry->oom_score_adj = task->signal->oom_score_adj;
 	),
 
-	TP_printk("pid=%d comm=%s oom_score_adj=%d",
+	TP_printk("pid=%d comm=%s oom_score_adj=%hd",
 		__entry->pid, __entry->comm, __entry->oom_score_adj)
 );
 
diff --git a/include/trace/events/task.h b/include/trace/events/task.h
index b53add02e929..102a646e1996 100644
--- a/include/trace/events/task.h
+++ b/include/trace/events/task.h
@@ -15,7 +15,7 @@ TRACE_EVENT(task_newtask,
 		__field(	pid_t,	pid)
 		__array(	char,	comm, TASK_COMM_LEN)
 		__field( unsigned long, clone_flags)
-		__field(	int,    oom_score_adj)
+		__field(	short,	oom_score_adj)
 	),
 
 	TP_fast_assign(
@@ -25,7 +25,7 @@ TRACE_EVENT(task_newtask,
 		__entry->oom_score_adj = task->signal->oom_score_adj;
 	),
 
-	TP_printk("pid=%d comm=%s clone_flags=%lx oom_score_adj=%d",
+	TP_printk("pid=%d comm=%s clone_flags=%lx oom_score_adj=%hd",
 		__entry->pid, __entry->comm,
 		__entry->clone_flags, __entry->oom_score_adj)
 );
@@ -40,7 +40,7 @@ TRACE_EVENT(task_rename,
 		__field(	pid_t,	pid)
 		__array(	char, oldcomm,  TASK_COMM_LEN)
 		__array(	char, newcomm,  TASK_COMM_LEN)
-		__field(	int, oom_score_adj)
+		__field(	short,	oom_score_adj)
 	),
 
 	TP_fast_assign(
@@ -50,7 +50,7 @@ TRACE_EVENT(task_rename,
 		__entry->oom_score_adj = task->signal->oom_score_adj;
 	),
 
-	TP_printk("pid=%d oldcomm=%s newcomm=%s oom_score_adj=%d",
+	TP_printk("pid=%d oldcomm=%s newcomm=%s oom_score_adj=%hd",
 		__entry->pid, __entry->oldcomm,
 		__entry->newcomm, __entry->oom_score_adj)
 );
diff --git a/mm/ksm.c b/mm/ksm.c
index 31ae5ea1eac0..b4d5a9deb17f 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1919,7 +1919,7 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (ksm_run != flags) {
 		ksm_run = flags;
 		if (flags & KSM_RUN_UNMERGE) {
-			int oom_score_adj;
+			short oom_score_adj;
 
 			oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
 			err = unmerge_and_remove_all_rmap_items();
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 7e9e9113bd05..37ab4c5ab6e8 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -53,7 +53,7 @@ static DEFINE_SPINLOCK(zone_scan_lock);
  * @old_val.  Usually used to reinstate a previous value to prevent racing with
  * userspacing tuning the value in the interim.
  */
-void compare_swap_oom_score_adj(int old_val, int new_val)
+void compare_swap_oom_score_adj(short old_val, short new_val)
 {
 	struct sighand_struct *sighand = current->sighand;
 
@@ -72,7 +72,7 @@ void compare_swap_oom_score_adj(int old_val, int new_val)
  * synchronization and returns the old value.  Usually used to temporarily
  * set a value, save the old value in the caller, and then reinstate it later.
  */
-int test_set_oom_score_adj(int new_val)
+short test_set_oom_score_adj(short new_val)
 {
 	struct sighand_struct *sighand = current->sighand;
 	int old_val;
@@ -193,7 +193,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	if (!p)
 		return 0;
 
-	adj = p->signal->oom_score_adj;
+	adj = (long)p->signal->oom_score_adj;
 	if (adj == OOM_SCORE_ADJ_MIN) {
 		task_unlock(p);
 		return 0;
@@ -399,7 +399,7 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu         %5d %s\n",
+		pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu         %5hd %s\n",
 			task->pid, from_kuid(&init_user_ns, task_uid(task)),
 			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
 			task->mm->nr_ptes,
@@ -415,7 +415,7 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 {
 	task_lock(current);
 	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
-		"oom_score_adj=%d\n",
+		"oom_score_adj=%hd\n",
 		current->comm, gfp_mask, order,
 		current->signal->oom_score_adj);
 	cpuset_print_task_mems_allowed(current);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 0fbb45283c66..bb6f6a04e92d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1498,7 +1498,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	struct address_space *mapping;
 	struct inode *inode;
 	struct filename *pathname;
-	int oom_score_adj;
+	short oom_score_adj;
 	int i, type, prev;
 	int err;
 
-- 
cgit v1.2.3-55-g7522


From e1e12d2f3104be886073ac6c5c4678f30b1b9e51 Mon Sep 17 00:00:00 2001
From: David Rientjes
Date: Tue, 11 Dec 2012 16:02:56 -0800
Subject: mm, oom: fix race when specifying a thread as the oom origin

test_set_oom_score_adj() and compare_swap_oom_score_adj() are used to
specify that current should be killed first if an oom condition occurs in
between the two calls.

The usage is

	short oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
	...
	compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);

to store the thread's oom_score_adj, temporarily change it to the maximum
score possible, and then restore the old value if it is still the same.

This happens to still be racy, however, if the user writes
OOM_SCORE_ADJ_MAX to /proc/pid/oom_score_adj in between the two calls.
The compare_swap_oom_score_adj() will then incorrectly reset the old value
prior to the write of OOM_SCORE_ADJ_MAX.

To fix this, introduce a new oom_flags_t member in struct signal_struct
that will be used for per-thread oom killer flags.  KSM and swapoff can
now use a bit in this member to specify that threads should be killed
first in oom conditions without playing around with oom_score_adj.

This also allows the correct oom_score_adj to always be shown when reading
/proc/pid/oom_score.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Cc: Anton Vorontsov <anton.vorontsov@linaro.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/oom.h   | 19 +++++++++++++++++--
 include/linux/sched.h |  1 +
 include/linux/types.h |  1 +
 mm/ksm.c              |  7 ++-----
 mm/oom_kill.c         | 49 +++++++------------------------------------------
 mm/swapfile.c         |  5 ++---
 6 files changed, 30 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/linux/oom.h b/include/linux/oom.h
index 922dab164eb0..da60007075b5 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -29,8 +29,23 @@ enum oom_scan_t {
 	OOM_SCAN_SELECT,	/* always select this thread first */
 };
 
-extern void compare_swap_oom_score_adj(short old_val, short new_val);
-extern short test_set_oom_score_adj(short new_val);
+/* Thread is the potential origin of an oom condition; kill first on oom */
+#define OOM_FLAG_ORIGIN		((__force oom_flags_t)0x1)
+
+static inline void set_current_oom_origin(void)
+{
+	current->signal->oom_flags |= OOM_FLAG_ORIGIN;
+}
+
+static inline void clear_current_oom_origin(void)
+{
+	current->signal->oom_flags &= ~OOM_FLAG_ORIGIN;
+}
+
+static inline bool oom_task_origin(const struct task_struct *p)
+{
+	return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN);
+}
 
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ed30456152da..3e387df065fc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -631,6 +631,7 @@ struct signal_struct {
 	struct rw_semaphore group_rwsem;
 #endif
 
+	oom_flags_t oom_flags;
 	short oom_score_adj;		/* OOM kill score adjustment */
 	short oom_score_adj_min;	/* OOM kill score adjustment min value.
 					 * Only settable by CAP_SYS_RESOURCE. */
diff --git a/include/linux/types.h b/include/linux/types.h
index 1cc0e4b9a048..4d118ba11349 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -156,6 +156,7 @@ typedef u32 dma_addr_t;
 #endif
 typedef unsigned __bitwise__ gfp_t;
 typedef unsigned __bitwise__ fmode_t;
+typedef unsigned __bitwise__ oom_flags_t;
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
 typedef u64 phys_addr_t;
diff --git a/mm/ksm.c b/mm/ksm.c
index b4d5a9deb17f..382d930a0bf1 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1919,12 +1919,9 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (ksm_run != flags) {
 		ksm_run = flags;
 		if (flags & KSM_RUN_UNMERGE) {
-			short oom_score_adj;
-
-			oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
+			set_current_oom_origin();
 			err = unmerge_and_remove_all_rmap_items();
-			compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX,
-								oom_score_adj);
+			clear_current_oom_origin();
 			if (err) {
 				ksm_run = KSM_RUN_STOP;
 				count = err;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 37ab4c5ab6e8..18f1ae2b45de 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -44,48 +44,6 @@ int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks = 1;
 static DEFINE_SPINLOCK(zone_scan_lock);
 
-/*
- * compare_swap_oom_score_adj() - compare and swap current's oom_score_adj
- * @old_val: old oom_score_adj for compare
- * @new_val: new oom_score_adj for swap
- *
- * Sets the oom_score_adj value for current to @new_val iff its present value is
- * @old_val.  Usually used to reinstate a previous value to prevent racing with
- * userspacing tuning the value in the interim.
- */
-void compare_swap_oom_score_adj(short old_val, short new_val)
-{
-	struct sighand_struct *sighand = current->sighand;
-
-	spin_lock_irq(&sighand->siglock);
-	if (current->signal->oom_score_adj == old_val)
-		current->signal->oom_score_adj = new_val;
-	trace_oom_score_adj_update(current);
-	spin_unlock_irq(&sighand->siglock);
-}
-
-/**
- * test_set_oom_score_adj() - set current's oom_score_adj and return old value
- * @new_val: new oom_score_adj value
- *
- * Sets the oom_score_adj value for current to @new_val with proper
- * synchronization and returns the old value.  Usually used to temporarily
- * set a value, save the old value in the caller, and then reinstate it later.
- */
-short test_set_oom_score_adj(short new_val)
-{
-	struct sighand_struct *sighand = current->sighand;
-	int old_val;
-
-	spin_lock_irq(&sighand->siglock);
-	old_val = current->signal->oom_score_adj;
-	current->signal->oom_score_adj = new_val;
-	trace_oom_score_adj_update(current);
-	spin_unlock_irq(&sighand->siglock);
-
-	return old_val;
-}
-
 #ifdef CONFIG_NUMA
 /**
  * has_intersects_mems_allowed() - check task eligiblity for kill
@@ -310,6 +268,13 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 	if (!task->mm)
 		return OOM_SCAN_CONTINUE;
 
+	/*
+	 * If task is allocating a lot of memory and has been marked to be
+	 * killed first if it triggers an oom, then select it.
+	 */
+	if (oom_task_origin(task))
+		return OOM_SCAN_SELECT;
+
 	if (task->flags & PF_EXITING && !force_kill) {
 		/*
 		 * If this task is not being ptraced on exit, then wait for it
diff --git a/mm/swapfile.c b/mm/swapfile.c
index bb6f6a04e92d..e97a0e5aea91 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1498,7 +1498,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	struct address_space *mapping;
 	struct inode *inode;
 	struct filename *pathname;
-	short oom_score_adj;
 	int i, type, prev;
 	int err;
 
@@ -1557,9 +1556,9 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	p->flags &= ~SWP_WRITEOK;
 	spin_unlock(&swap_lock);
 
-	oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
+	set_current_oom_origin();
 	err = try_to_unuse(type, false, 0); /* force all pages to be unused */
-	compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);
+	clear_current_oom_origin();
 
 	if (err) {
 		/* re-insert swap space back into swap_list */
-- 
cgit v1.2.3-55-g7522


From bc357f431c836c6631751e3ef7dfe7882394ad67 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski
Date: Tue, 11 Dec 2012 16:02:59 -0800
Subject: mm: cma: remove watermark hacks

Commits 2139cbe627b8 ("cma: fix counting of isolated pages") and
d95ea5d18e69 ("cma: fix watermark checking") introduced a reliable
method of free page accounting when memory is being allocated from CMA
regions, so the workaround introduced earlier by commit 49f223a9cd96
("mm: trigger page reclaim in alloc_contig_range() to stabilise
watermarks") can be finally removed.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Mel Gorman <mel@csn.ul.ie>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h |  9 --------
 mm/page_alloc.c        | 58 --------------------------------------------------
 2 files changed, 67 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a23923ba8263..0c0b1d608a69 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -63,10 +63,8 @@ enum {
 
 #ifdef CONFIG_CMA
 #  define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
-#  define cma_wmark_pages(zone)	zone->min_cma_pages
 #else
 #  define is_migrate_cma(migratetype) false
-#  define cma_wmark_pages(zone) 0
 #endif
 
 #define for_each_migratetype_order(order, type) \
@@ -382,13 +380,6 @@ struct zone {
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/* see spanned/present_pages for more description */
 	seqlock_t		span_seqlock;
-#endif
-#ifdef CONFIG_CMA
-	/*
-	 * CMA needs to increase watermark levels during the allocation
-	 * process to make sure that the system is not starved.
-	 */
-	unsigned long		min_cma_pages;
 #endif
 	struct free_area	free_area[MAX_ORDER];
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 265fea4fbc81..5a8d339d282a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5218,10 +5218,6 @@ static void __setup_per_zone_wmarks(void)
 		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
 		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
 
-		zone->watermark[WMARK_MIN] += cma_wmark_pages(zone);
-		zone->watermark[WMARK_LOW] += cma_wmark_pages(zone);
-		zone->watermark[WMARK_HIGH] += cma_wmark_pages(zone);
-
 		setup_zone_migrate_reserve(zone);
 		spin_unlock_irqrestore(&zone->lock, flags);
 	}
@@ -5766,54 +5762,6 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 	return ret > 0 ? 0 : ret;
 }
 
-/*
- * Update zone's cma pages counter used for watermark level calculation.
- */
-static inline void __update_cma_watermarks(struct zone *zone, int count)
-{
-	unsigned long flags;
-	spin_lock_irqsave(&zone->lock, flags);
-	zone->min_cma_pages += count;
-	spin_unlock_irqrestore(&zone->lock, flags);
-	setup_per_zone_wmarks();
-}
-
-/*
- * Trigger memory pressure bump to reclaim some pages in order to be able to
- * allocate 'count' pages in single page units. Does similar work as
- *__alloc_pages_slowpath() function.
- */
-static int __reclaim_pages(struct zone *zone, gfp_t gfp_mask, int count)
-{
-	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
-	struct zonelist *zonelist = node_zonelist(0, gfp_mask);
-	int did_some_progress = 0;
-	int order = 1;
-
-	/*
-	 * Increase level of watermarks to force kswapd do his job
-	 * to stabilise at new watermark level.
-	 */
-	__update_cma_watermarks(zone, count);
-
-	/* Obey watermarks as if the page was being allocated */
-	while (!zone_watermark_ok(zone, 0, low_wmark_pages(zone), 0, 0)) {
-		wake_all_kswapd(order, zonelist, high_zoneidx, zone_idx(zone));
-
-		did_some_progress = __perform_reclaim(gfp_mask, order, zonelist,
-						      NULL);
-		if (!did_some_progress) {
-			/* Exhausted what can be done so it's blamo time */
-			out_of_memory(zonelist, gfp_mask, order, NULL, false);
-		}
-	}
-
-	/* Restore original watermark levels. */
-	__update_cma_watermarks(zone, -count);
-
-	return count;
-}
-
 /**
  * alloc_contig_range() -- tries to allocate given range of pages
  * @start:	start PFN to allocate
@@ -5837,7 +5785,6 @@ static int __reclaim_pages(struct zone *zone, gfp_t gfp_mask, int count)
 int alloc_contig_range(unsigned long start, unsigned long end,
 		       unsigned migratetype)
 {
-	struct zone *zone = page_zone(pfn_to_page(start));
 	unsigned long outer_start, outer_end;
 	int ret = 0, order;
 
@@ -5922,11 +5869,6 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		goto done;
 	}
 
-	/*
-	 * Reclaim enough pages to make sure that contiguous allocation
-	 * will not starve the system.
-	 */
-	__reclaim_pages(zone, GFP_HIGHUSER_MOVABLE, end-start);
 
 	/* Grab isolated pages from freelists. */
 	outer_end = isolate_freepages_range(&cc, outer_start, end);
-- 
cgit v1.2.3-55-g7522


From 81df9bff2609f07cef4690ac2ebda1611b55b05a Mon Sep 17 00:00:00 2001
From: Joonsoo Kim
Date: Tue, 11 Dec 2012 16:03:10 -0800
Subject: bootmem: fix wrong call parameter for free_bootmem()

It is strange that alloc_bootmem() returns a virtual address and
free_bootmem() requires a physical address.  Anyway, free_bootmem()'s
first parameter should be physical address.

There are some call sites for free_bootmem() with virtual address.  So fix
them.

[akpm@linux-foundation.org: improve free_bootmem() and free_bootmem_pate() documentation]
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Cc: Haavard Skinnemoen <hskinnemoen@gmail.com>
Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/platforms/cell/celleb_pci.c |  4 ++--
 drivers/macintosh/smu.c                  |  2 +-
 include/linux/bootmem.h                  |  4 ++--
 lib/cpumask.c                            |  2 +-
 mm/bootmem.c                             | 20 ++++++++++----------
 5 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c
index abc8af43ea7c..173568140a32 100644
--- a/arch/powerpc/platforms/cell/celleb_pci.c
+++ b/arch/powerpc/platforms/cell/celleb_pci.c
@@ -401,11 +401,11 @@ error:
 	} else {
 		if (config && *config) {
 			size = 256;
-			free_bootmem((unsigned long)(*config), size);
+			free_bootmem(__pa(*config), size);
 		}
 		if (res && *res) {
 			size = sizeof(struct celleb_pci_resource);
-			free_bootmem((unsigned long)(*res), size);
+			free_bootmem(__pa(*res), size);
 		}
 	}
 
diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index 7d5a6b40b31c..196368009001 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -565,7 +565,7 @@ fail_msg_node:
 fail_db_node:
 	of_node_put(smu->db_node);
 fail_bootmem:
-	free_bootmem((unsigned long)smu, sizeof(struct smu_device));
+	free_bootmem(__pa(smu), sizeof(struct smu_device));
 	smu = NULL;
 fail_np:
 	of_node_put(np);
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 6d6795d46a75..7b74452c5317 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -51,8 +51,8 @@ extern unsigned long free_all_bootmem(void);
 extern void free_bootmem_node(pg_data_t *pgdat,
 			      unsigned long addr,
 			      unsigned long size);
-extern void free_bootmem(unsigned long addr, unsigned long size);
-extern void free_bootmem_late(unsigned long addr, unsigned long size);
+extern void free_bootmem(unsigned long physaddr, unsigned long size);
+extern void free_bootmem_late(unsigned long physaddr, unsigned long size);
 
 /*
  * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE,
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 402a54ac35cb..d327b87c99b7 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -161,6 +161,6 @@ EXPORT_SYMBOL(free_cpumask_var);
  */
 void __init free_bootmem_cpumask_var(cpumask_var_t mask)
 {
-	free_bootmem((unsigned long)mask, cpumask_size());
+	free_bootmem(__pa(mask), cpumask_size());
 }
 #endif
diff --git a/mm/bootmem.c b/mm/bootmem.c
index f468185b3b28..ecc45958ac0c 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -147,21 +147,21 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 
 /*
  * free_bootmem_late - free bootmem pages directly to page allocator
- * @addr: starting address of the range
+ * @addr: starting physical address of the range
  * @size: size of the range in bytes
  *
  * This is only useful when the bootmem allocator has already been torn
  * down, but we are still initializing the system.  Pages are given directly
  * to the page allocator, no bootmem metadata is updated because it is gone.
  */
-void __init free_bootmem_late(unsigned long addr, unsigned long size)
+void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
 {
 	unsigned long cursor, end;
 
-	kmemleak_free_part(__va(addr), size);
+	kmemleak_free_part(__va(physaddr), size);
 
-	cursor = PFN_UP(addr);
-	end = PFN_DOWN(addr + size);
+	cursor = PFN_UP(physaddr);
+	end = PFN_DOWN(physaddr + size);
 
 	for (; cursor < end; cursor++) {
 		__free_pages_bootmem(pfn_to_page(cursor), 0);
@@ -377,21 +377,21 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 
 /**
  * free_bootmem - mark a page range as usable
- * @addr: starting address of the range
+ * @addr: starting physical address of the range
  * @size: size of the range in bytes
  *
  * Partial pages will be considered reserved and left as they are.
  *
  * The range must be contiguous but may span node boundaries.
  */
-void __init free_bootmem(unsigned long addr, unsigned long size)
+void __init free_bootmem(unsigned long physaddr, unsigned long size)
 {
 	unsigned long start, end;
 
-	kmemleak_free_part(__va(addr), size);
+	kmemleak_free_part(__va(physaddr), size);
 
-	start = PFN_UP(addr);
-	end = PFN_DOWN(addr + size);
+	start = PFN_UP(physaddr);
+	end = PFN_DOWN(physaddr + size);
 
 	mark_bootmem(start, end, 0, 0);
 }
-- 
cgit v1.2.3-55-g7522


From 511c2aba8f07fc45bdcba548cb63f7b8a450c6dc Mon Sep 17 00:00:00 2001
From: Lai Jiangshan
Date: Tue, 11 Dec 2012 16:03:16 -0800
Subject: mm, memory-hotplug: dynamic configure movable memory and portion
 memory

Add online_movable and online_kernel for logic memory hotplug.  This is
the dynamic version of "movablecore" & "kernelcore".

We have the same reason to introduce it as to introduce "movablecore" &
"kernelcore".  It has the same motive as "movablecore" & "kernelcore", but
it is dynamic/running-time:

o We can configure memory as kernelcore or movablecore after boot.

  Userspace workload is increased, we need more hugepage, we can't use
  "online_movable" to add memory and allow the system use more
  THP(transparent-huge-page), vice-verse when kernel workload is increase.

  Also help for virtualization to dynamic configure host/guest's memory,
  to save/(reduce waste) memory.

  Memory capacity on Demand

o When a new node is physically online after boot, we need to use
  "online_movable" or "online_kernel" to configure/portion it as we
  expected when we logic-online it.

  This configuration also helps for physically-memory-migrate.

o all benefit as the same as existed "movablecore" & "kernelcore".

o Preparing for movable-node, which is very important for power-saving,
  hardware partitioning and high-available-system(hardware fault
  management).

(Note, we don't introduce movable-node here.)

Action behavior:
When a memoryblock/memorysection is onlined by "online_movable", the kernel
will not have directly reference to the page of the memoryblock,
thus we can remove that memory any time when needed.

When it is online by "online_kernel", the kernel can use it.
When it is online by "online", the zone type doesn't changed.

Current constraints:
Only the memoryblock which is adjacent to the ZONE_MOVABLE
can be online from ZONE_NORMAL to ZONE_MOVABLE.

[akpm@linux-foundation.org: use min_t, cleanups]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/memory-hotplug.txt |  14 +++++-
 drivers/base/memory.c            |  33 ++++++++-----
 include/linux/memory_hotplug.h   |  13 ++++-
 mm/memory_hotplug.c              | 100 ++++++++++++++++++++++++++++++++++++++-
 4 files changed, 146 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index 6e6cbc78f329..c6f993d491b5 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -161,7 +161,8 @@ a recent addition and not present on older kernels.
 		    in the memory block.
 'state'           : read-write
                     at read:  contains online/offline state of memory.
-                    at write: user can specify "online", "offline" command
+                    at write: user can specify "online_kernel",
+                    "online_movable", "online", "offline" command
                     which will be performed on al sections in the block.
 'phys_device'     : read-only: designed to show the name of physical memory
                     device.  This is not well implemented now.
@@ -255,6 +256,17 @@ For onlining, you have to write "online" to the section's state file as:
 
 % echo online > /sys/devices/system/memory/memoryXXX/state
 
+This onlining will not change the ZONE type of the target memory section,
+If the memory section is in ZONE_NORMAL, you can change it to ZONE_MOVABLE:
+
+% echo online_movable > /sys/devices/system/memory/memoryXXX/state
+(NOTE: current limit: this memory section must be adjacent to ZONE_MOVABLE)
+
+And if the memory section is in ZONE_MOVABLE, you can change it to ZONE_NORMAL:
+
+% echo online_kernel > /sys/devices/system/memory/memoryXXX/state
+(NOTE: current limit: this memory section must be adjacent to ZONE_NORMAL)
+
 After this, section memoryXXX's state will be 'online' and the amount of
 available memory will be increased.
 
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 7eb1211ab688..987604d56c83 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -254,7 +254,7 @@ static bool pages_correctly_reserved(unsigned long start_pfn,
  * OK to have direct references to sparsemem variables in here.
  */
 static int
-memory_block_action(unsigned long phys_index, unsigned long action)
+memory_block_action(unsigned long phys_index, unsigned long action, int online_type)
 {
 	unsigned long start_pfn;
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
@@ -269,7 +269,7 @@ memory_block_action(unsigned long phys_index, unsigned long action)
 			if (!pages_correctly_reserved(start_pfn, nr_pages))
 				return -EBUSY;
 
-			ret = online_pages(start_pfn, nr_pages);
+			ret = online_pages(start_pfn, nr_pages, online_type);
 			break;
 		case MEM_OFFLINE:
 			ret = offline_pages(start_pfn, nr_pages);
@@ -284,7 +284,8 @@ memory_block_action(unsigned long phys_index, unsigned long action)
 }
 
 static int __memory_block_change_state(struct memory_block *mem,
-		unsigned long to_state, unsigned long from_state_req)
+		unsigned long to_state, unsigned long from_state_req,
+		int online_type)
 {
 	int ret = 0;
 
@@ -296,7 +297,7 @@ static int __memory_block_change_state(struct memory_block *mem,
 	if (to_state == MEM_OFFLINE)
 		mem->state = MEM_GOING_OFFLINE;
 
-	ret = memory_block_action(mem->start_section_nr, to_state);
+	ret = memory_block_action(mem->start_section_nr, to_state, online_type);
 
 	if (ret) {
 		mem->state = from_state_req;
@@ -319,12 +320,14 @@ out:
 }
 
 static int memory_block_change_state(struct memory_block *mem,
-		unsigned long to_state, unsigned long from_state_req)
+		unsigned long to_state, unsigned long from_state_req,
+		int online_type)
 {
 	int ret;
 
 	mutex_lock(&mem->state_mutex);
-	ret = __memory_block_change_state(mem, to_state, from_state_req);
+	ret = __memory_block_change_state(mem, to_state, from_state_req,
+					  online_type);
 	mutex_unlock(&mem->state_mutex);
 
 	return ret;
@@ -338,10 +341,18 @@ store_mem_state(struct device *dev,
 
 	mem = container_of(dev, struct memory_block, dev);
 
-	if (!strncmp(buf, "online", min((int)count, 6)))
-		ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
-	else if(!strncmp(buf, "offline", min((int)count, 7)))
-		ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
+	if (!strncmp(buf, "online_kernel", min_t(int, count, 13)))
+		ret = memory_block_change_state(mem, MEM_ONLINE,
+						MEM_OFFLINE, ONLINE_KERNEL);
+	else if (!strncmp(buf, "online_movable", min_t(int, count, 14)))
+		ret = memory_block_change_state(mem, MEM_ONLINE,
+						MEM_OFFLINE, ONLINE_MOVABLE);
+	else if (!strncmp(buf, "online", min_t(int, count, 6)))
+		ret = memory_block_change_state(mem, MEM_ONLINE,
+						MEM_OFFLINE, ONLINE_KEEP);
+	else if(!strncmp(buf, "offline", min_t(int, count, 7)))
+		ret = memory_block_change_state(mem, MEM_OFFLINE,
+						MEM_ONLINE, -1);
 
 	if (ret)
 		return ret;
@@ -676,7 +687,7 @@ int offline_memory_block(struct memory_block *mem)
 
 	mutex_lock(&mem->state_mutex);
 	if (mem->state != MEM_OFFLINE)
-		ret = __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
+		ret = __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1);
 	mutex_unlock(&mem->state_mutex);
 
 	return ret;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 95573ec4ee6c..4a45c4e50025 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -26,6 +26,13 @@ enum {
 	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
 };
 
+/* Types for control the zone type of onlined memory */
+enum {
+	ONLINE_KEEP,
+	ONLINE_KERNEL,
+	ONLINE_MOVABLE,
+};
+
 /*
  * pgdat resizing functions
  */
@@ -46,6 +53,10 @@ void pgdat_resize_init(struct pglist_data *pgdat)
 }
 /*
  * Zone resizing functions
+ *
+ * Note: any attempt to resize a zone should has pgdat_resize_lock()
+ * zone_span_writelock() both held. This ensure the size of a zone
+ * can't be changed while pgdat_resize_lock() held.
  */
 static inline unsigned zone_span_seqbegin(struct zone *zone)
 {
@@ -71,7 +82,7 @@ extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
 extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
 /* VM interface that may be used by firmware interface */
-extern int online_pages(unsigned long, unsigned long);
+extern int online_pages(unsigned long, unsigned long, int);
 extern void __offline_isolated_pages(unsigned long, unsigned long);
 
 typedef void (*online_page_callback_t)(struct page *page);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 571130ee66d7..5c1f4959e6b4 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -214,6 +214,88 @@ static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
 	zone_span_writeunlock(zone);
 }
 
+static void resize_zone(struct zone *zone, unsigned long start_pfn,
+		unsigned long end_pfn)
+{
+	zone_span_writelock(zone);
+
+	zone->zone_start_pfn = start_pfn;
+	zone->spanned_pages = end_pfn - start_pfn;
+
+	zone_span_writeunlock(zone);
+}
+
+static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
+		unsigned long end_pfn)
+{
+	enum zone_type zid = zone_idx(zone);
+	int nid = zone->zone_pgdat->node_id;
+	unsigned long pfn;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn++)
+		set_page_links(pfn_to_page(pfn), zid, nid, pfn);
+}
+
+static int move_pfn_range_left(struct zone *z1, struct zone *z2,
+		unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long flags;
+
+	pgdat_resize_lock(z1->zone_pgdat, &flags);
+
+	/* can't move pfns which are higher than @z2 */
+	if (end_pfn > z2->zone_start_pfn + z2->spanned_pages)
+		goto out_fail;
+	/* the move out part mast at the left most of @z2 */
+	if (start_pfn > z2->zone_start_pfn)
+		goto out_fail;
+	/* must included/overlap */
+	if (end_pfn <= z2->zone_start_pfn)
+		goto out_fail;
+
+	resize_zone(z1, z1->zone_start_pfn, end_pfn);
+	resize_zone(z2, end_pfn, z2->zone_start_pfn + z2->spanned_pages);
+
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+
+	fix_zone_id(z1, start_pfn, end_pfn);
+
+	return 0;
+out_fail:
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+	return -1;
+}
+
+static int move_pfn_range_right(struct zone *z1, struct zone *z2,
+		unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long flags;
+
+	pgdat_resize_lock(z1->zone_pgdat, &flags);
+
+	/* can't move pfns which are lower than @z1 */
+	if (z1->zone_start_pfn > start_pfn)
+		goto out_fail;
+	/* the move out part mast at the right most of @z1 */
+	if (z1->zone_start_pfn + z1->spanned_pages >  end_pfn)
+		goto out_fail;
+	/* must included/overlap */
+	if (start_pfn >= z1->zone_start_pfn + z1->spanned_pages)
+		goto out_fail;
+
+	resize_zone(z1, z1->zone_start_pfn, start_pfn);
+	resize_zone(z2, start_pfn, z2->zone_start_pfn + z2->spanned_pages);
+
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+
+	fix_zone_id(z2, start_pfn, end_pfn);
+
+	return 0;
+out_fail:
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+	return -1;
+}
+
 static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
 			    unsigned long end_pfn)
 {
@@ -508,7 +590,7 @@ static void node_states_set_node(int node, struct memory_notify *arg)
 }
 
 
-int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
 {
 	unsigned long onlined_pages = 0;
 	struct zone *zone;
@@ -525,6 +607,22 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 	 */
 	zone = page_zone(pfn_to_page(pfn));
 
+	if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) {
+		if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) {
+			unlock_memory_hotplug();
+			return -1;
+		}
+	}
+	if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) {
+		if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) {
+			unlock_memory_hotplug();
+			return -1;
+		}
+	}
+
+	/* Previous code may changed the zone of the pfn range */
+	zone = page_zone(pfn_to_page(pfn));
+
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
 	node_states_check_changes_online(nr_pages, zone, &arg);
-- 
cgit v1.2.3-55-g7522


From 1abbe1394a84c10919e32242318e715b04d7e33b Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Tue, 11 Dec 2012 15:54:33 +0000
Subject: pkt_sched: avoid requeues if possible

With BQL being deployed, we can more likely have following behavior :

We dequeue a packet from qdisc in dequeue_skb(), then we realize target
tx queue is in XOFF state in sch_direct_xmit(), and we have to hold the
skb into gso_skb for later.

This shows in stats (tc -s qdisc dev eth0) as requeues.

Problem of these requeues is that high priority packets can not be
dequeued as long as this (possibly low prio and big TSO packet) is not
removed from gso_skb.

At 1Gbps speed, a full size TSO packet is 500 us of extra latency.

In some cases, we know that all packets dequeued from a qdisc are
for a particular and known txq :

- If device is non multi queue
- For all MQ/MQPRIO slave qdiscs

This patch introduces a new qdisc flag, TCQ_F_ONETXQUEUE to mark
this capability, so that dequeue_skb() is allowed to dequeue a packet
only if the associated txq is not stopped.

This indeed reduce latencies for high prio packets (or improve fairness
with sfq/fq_codel), and almost remove qdisc 'requeues'.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  7 +++++++
 net/sched/sch_api.c       |  2 ++
 net/sched/sch_generic.c   | 11 ++++++-----
 net/sched/sch_mq.c        |  4 +++-
 net/sched/sch_mqprio.c    |  4 ++++
 5 files changed, 22 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 4616f468d599..1540f9c2fcf4 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -50,6 +50,13 @@ struct Qdisc {
 #define TCQ_F_INGRESS		2
 #define TCQ_F_CAN_BYPASS	4
 #define TCQ_F_MQROOT		8
+#define TCQ_F_ONETXQUEUE	0x10 /* dequeue_skb() can assume all skbs are for
+				      * q->dev_queue : It can test
+				      * netif_xmit_frozen_or_stopped() before
+				      * dequeueing next packet.
+				      * Its true for MQ/MQPRIO slaves, or non
+				      * multiqueue device.
+				      */
 #define TCQ_F_WARN_NONWC	(1 << 16)
 	int			padded;
 	const struct Qdisc_ops	*ops;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 4799c4840c1a..d84f7e734cd7 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -833,6 +833,8 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 				goto err_out3;
 		}
 		lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
+		if (!netif_is_multiqueue(dev))
+			sch->flags |= TCQ_F_ONETXQUEUE;
 	}
 
 	sch->handle = handle;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index aefc1504dc88..5d81a4478514 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -53,20 +53,19 @@ static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 {
 	struct sk_buff *skb = q->gso_skb;
+	const struct netdev_queue *txq = q->dev_queue;
 
 	if (unlikely(skb)) {
-		struct net_device *dev = qdisc_dev(q);
-		struct netdev_queue *txq;
-
 		/* check the reason of requeuing without tx lock first */
-		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+		txq = netdev_get_tx_queue(txq->dev, skb_get_queue_mapping(skb));
 		if (!netif_xmit_frozen_or_stopped(txq)) {
 			q->gso_skb = NULL;
 			q->q.qlen--;
 		} else
 			skb = NULL;
 	} else {
-		skb = q->dequeue(q);
+		if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq))
+			skb = q->dequeue(q);
 	}
 
 	return skb;
@@ -686,6 +685,8 @@ static void attach_one_default_qdisc(struct net_device *dev,
 			netdev_info(dev, "activation failed\n");
 			return;
 		}
+		if (!netif_is_multiqueue(dev))
+			qdisc->flags |= TCQ_F_ONETXQUEUE;
 	}
 	dev_queue->qdisc_sleeping = qdisc;
 }
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 0a4b2f9a0094..5da78a19ac9a 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -63,6 +63,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt)
 		if (qdisc == NULL)
 			goto err;
 		priv->qdiscs[ntx] = qdisc;
+		qdisc->flags |= TCQ_F_ONETXQUEUE;
 	}
 
 	sch->flags |= TCQ_F_MQROOT;
@@ -150,7 +151,8 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 		dev_deactivate(dev);
 
 	*old = dev_graft_qdisc(dev_queue, new);
-
+	if (new)
+		new->flags |= TCQ_F_ONETXQUEUE;
 	if (dev->flags & IFF_UP)
 		dev_activate(dev);
 	return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index d1831ca966d4..accec33c454c 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -132,6 +132,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 			goto err;
 		}
 		priv->qdiscs[i] = qdisc;
+		qdisc->flags |= TCQ_F_ONETXQUEUE;
 	}
 
 	/* If the mqprio options indicate that hardware should own
@@ -205,6 +206,9 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 
 	*old = dev_graft_qdisc(dev_queue, new);
 
+	if (new)
+		new->flags |= TCQ_F_ONETXQUEUE;
+
 	if (dev->flags & IFF_UP)
 		dev_activate(dev);
 
-- 
cgit v1.2.3-55-g7522


From 1f53ef17d3ed6c34868cc8e7aa7c1d351c2fdc95 Mon Sep 17 00:00:00 2001
From: Zhang Rui
Date: Wed, 12 Dec 2012 15:31:37 +0800
Subject: Thermal: Fix DEFAULT_THERMAL_GOVERNOR

Fix DEFAULT_THERMAL_GOVERNOR to be consistant with the
default governor selected in kernel config file.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/thermal/step_wise.c |  2 +-
 include/linux/thermal.h     | 10 ++++++++--
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c
index 1242cffed8b0..0cd5e9fbab1c 100644
--- a/drivers/thermal/step_wise.c
+++ b/drivers/thermal/step_wise.c
@@ -170,7 +170,7 @@ static int step_wise_throttle(struct thermal_zone_device *tz, int trip)
 }
 
 static struct thermal_governor thermal_gov_step_wise = {
-	.name		= DEFAULT_THERMAL_GOVERNOR,
+	.name		= "step_wise",
 	.throttle	= step_wise_throttle,
 	.owner		= THIS_MODULE,
 };
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 807f2146fe35..fe82022478e7 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -46,8 +46,14 @@
 #define THERMAL_GENL_VERSION                    0x01
 #define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_group"
 
-/* Default Thermal Governor: Does Linear Throttling */
-#define DEFAULT_THERMAL_GOVERNOR	"step_wise"
+/* Default Thermal Governor */
+#if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
+#define DEFAULT_THERMAL_GOVERNOR       "step_wise"
+#elif defined(CONFIG_THERMAL_DEFAULT_GOV_FAIR_SHARE)
+#define DEFAULT_THERMAL_GOVERNOR       "fair_share"
+#elif defined(CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE)
+#define DEFAULT_THERMAL_GOVERNOR       "user_space"
+#endif
 
 struct thermal_zone_device;
 struct thermal_cooling_device;
-- 
cgit v1.2.3-55-g7522


From 83499b52c61f50292f0aae36499de8a8fc3e37c3 Mon Sep 17 00:00:00 2001
From: Alexander Holler
Date: Sun, 9 Dec 2012 12:44:30 +0100
Subject: HID: sensors: autodetect USB HID sensor hubs

It should not be necessary to add IDs for HID sensor hubs to lists in
hid-core.c and hid-sensor-hub.c. So instead of a whitelist, autodetect such USB
HID sensor hubs, based on a collection of type physical inside a useage page of
type sensor. If some sensor hubs stil must be usable as raw devices, a
blacklist might be created.

Signed-off-by: Alexander Holler <holler@ahsoftware.de>
Acked-by: "Pandruvada, Srinivas" <srinivas.pandruvada@intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-core.c         | 11 ++++++++++-
 drivers/hid/hid-sensor-hub.c   | 32 +-------------------------------
 include/linux/hid-sensor-ids.h |  1 -
 include/linux/hid.h            |  2 ++
 4 files changed, 13 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index f4109fd657ff..7df5399a9386 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -713,7 +713,12 @@ static int hid_scan_report(struct hid_device *hid)
 					hid_scan_usage(hid, u);
 				break;
 			}
-		}
+		} else if (page == HID_UP_SENSOR &&
+			item.type == HID_ITEM_TYPE_MAIN &&
+			item.tag == HID_MAIN_ITEM_TAG_BEGIN_COLLECTION &&
+			(item_udata(&item) & 0xff) == HID_COLLECTION_PHYSICAL &&
+			hid->bus == BUS_USB)
+			hid->group = HID_GROUP_SENSOR_HUB;
 	}
 
 	return 0;
@@ -1465,6 +1470,10 @@ EXPORT_SYMBOL_GPL(hid_disconnect);
  * there is a proper autodetection and autoloading in place (based on presence
  * of HID_DG_CONTACTID), so those devices don't need to be added to this list,
  * as we are doing the right thing in hid_scan_usage().
+ *
+ * Autodetection for (USB) HID sensor hubs exists too. If a collection of type
+ * physical is found inside a usage page of type sensor, hid-sensor-hub will be
+ * used as a driver. See hid_scan_report().
  */
 static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_WCP32PU) },
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index d9d73e9163eb..ca88ddc2d78f 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -82,23 +82,6 @@ struct hid_sensor_hub_callbacks_list {
 	void *priv;
 };
 
-static int sensor_hub_check_for_sensor_page(struct hid_device *hdev)
-{
-	int i;
-	int ret = -EINVAL;
-
-	for (i = 0; i < hdev->maxcollection; i++) {
-		struct hid_collection *col = &hdev->collection[i];
-		if (col->type == HID_COLLECTION_PHYSICAL &&
-		   (col->usage & HID_USAGE_PAGE) == HID_UP_SENSOR) {
-			ret = 0;
-			break;
-		}
-	}
-
-	return ret;
-}
-
 static struct hid_report *sensor_hub_report(int id, struct hid_device *hdev,
 						int dir)
 {
@@ -524,10 +507,6 @@ static int sensor_hub_probe(struct hid_device *hdev,
 		hid_err(hdev, "parse failed\n");
 		goto err_free;
 	}
-	if (sensor_hub_check_for_sensor_page(hdev) < 0) {
-		hid_err(hdev, "sensor page not found\n");
-		goto err_free;
-	}
 	INIT_LIST_HEAD(&hdev->inputs);
 
 	ret = hid_hw_start(hdev, 0);
@@ -630,16 +609,7 @@ static void sensor_hub_remove(struct hid_device *hdev)
 }
 
 static const struct hid_device_id sensor_hub_devices[] = {
-	{ HID_USB_DEVICE(USB_VENDOR_ID_INTEL_8086,
-			USB_DEVICE_ID_SENSOR_HUB_1020) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_INTEL_8087,
-			USB_DEVICE_ID_SENSOR_HUB_1020) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_INTEL_8086,
-			USB_DEVICE_ID_SENSOR_HUB_09FA) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_INTEL_8087,
-			USB_DEVICE_ID_SENSOR_HUB_09FA) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_STANTUM_STM,
-			USB_DEVICE_ID_SENSOR_HUB_7014) },
+	{ HID_DEVICE(BUS_USB, HID_GROUP_SENSOR_HUB, HID_ANY_ID, HID_ANY_ID) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, sensor_hub_devices);
diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h
index ca8d7e94eb3c..55f277372fed 100644
--- a/include/linux/hid-sensor-ids.h
+++ b/include/linux/hid-sensor-ids.h
@@ -19,7 +19,6 @@
 #ifndef _HID_SENSORS_IDS_H
 #define _HID_SENSORS_IDS_H
 
-#define HID_UP_SENSOR						0x00200000
 #define HID_MAX_PHY_DEVICES					0xFF
 
 /* Accel 3D (200073) */
diff --git a/include/linux/hid.h b/include/linux/hid.h
index c076041a069e..c5f6ec2b15c2 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -167,6 +167,7 @@ struct hid_item {
 #define HID_UP_MSVENDOR		0xff000000
 #define HID_UP_CUSTOM		0x00ff0000
 #define HID_UP_LOGIVENDOR	0xffbc0000
+#define HID_UP_SENSOR		0x00200000
 
 #define HID_USAGE		0x0000ffff
 
@@ -292,6 +293,7 @@ struct hid_item {
  */
 #define HID_GROUP_GENERIC			0x0001
 #define HID_GROUP_MULTITOUCH			0x0002
+#define HID_GROUP_SENSOR_HUB			0x0003
 
 /*
  * This is the global environment of the parser. This information is
-- 
cgit v1.2.3-55-g7522


From 895464fa4b52f0e5a2ceffc173bad012be02b465 Mon Sep 17 00:00:00 2001
From: stephen hemminger
Date: Wed, 12 Dec 2012 06:58:52 +0000
Subject: uapi: add missing netconf.h to export list

Add netconf.h for use by iproute2.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/Kbuild | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index e194387ef784..2564a968ca48 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -258,6 +258,7 @@ header-y += neighbour.h
 header-y += net.h
 header-y += net_dropmon.h
 header-y += net_tstamp.h
+header-y += netconf.h
 header-y += netdevice.h
 header-y += netfilter.h
 header-y += netfilter_arp.h
-- 
cgit v1.2.3-55-g7522


From fd0ea7dbfae16015e72c4bbc6b1b43fffc3b914f Mon Sep 17 00:00:00 2001
From: YOSHIFUJI Hideaki
Date: Thu, 13 Dec 2012 02:40:26 +0900
Subject: ndisc: Unexport ndisc_{build,send}_skb().

These symbols were exported for bonding device by commit 305d552a
("bonding: send IPv6 neighbor advertisement on failover").

It bacame obsolete by commit 7c899432 ("bonding, ipv4, ipv6, vlan: Handle
NETDEV_BONDING_FAILOVER like NETDEV_NOTIFY_PEERS") and removed by
commit 4f5762ec ("bonding: Remove obsolete source file 'bond_ipv6.c'").

Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ndisc.h | 15 ---------------
 net/ipv6/ndisc.c    | 27 +++++++++++----------------
 2 files changed, 11 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 980d263765cf..7af1ea893038 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -190,21 +190,6 @@ extern void			ndisc_send_redirect(struct sk_buff *skb,
 extern int			ndisc_mc_map(const struct in6_addr *addr, char *buf,
 					     struct net_device *dev, int dir);
 
-extern struct sk_buff		*ndisc_build_skb(struct net_device *dev,
-						 const struct in6_addr *daddr,
-						 const struct in6_addr *saddr,
-						 struct icmp6hdr *icmp6h,
-						 const struct in6_addr *target,
-						 int llinfo);
-
-extern void			ndisc_send_skb(struct sk_buff *skb,
-					       struct net_device *dev,
-					       struct neighbour *neigh,
-					       const struct in6_addr *daddr,
-					       const struct in6_addr *saddr,
-					       struct icmp6hdr *icmp6h);
-
-
 
 /*
  *	IGMP
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index cf43b6550f5b..4c02e6ab96e7 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -370,12 +370,12 @@ static void pndisc_destructor(struct pneigh_entry *n)
 	ipv6_dev_mc_dec(dev, &maddr);
 }
 
-struct sk_buff *ndisc_build_skb(struct net_device *dev,
-				const struct in6_addr *daddr,
-				const struct in6_addr *saddr,
-				struct icmp6hdr *icmp6h,
-				const struct in6_addr *target,
-				int llinfo)
+static struct sk_buff *ndisc_build_skb(struct net_device *dev,
+				       const struct in6_addr *daddr,
+				       const struct in6_addr *saddr,
+				       struct icmp6hdr *icmp6h,
+				       const struct in6_addr *target,
+				       int llinfo)
 {
 	struct net *net = dev_net(dev);
 	struct sock *sk = net->ipv6.ndisc_sk;
@@ -431,14 +431,11 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev,
 	return skb;
 }
 
-EXPORT_SYMBOL(ndisc_build_skb);
-
-void ndisc_send_skb(struct sk_buff *skb,
-		    struct net_device *dev,
-		    struct neighbour *neigh,
-		    const struct in6_addr *daddr,
-		    const struct in6_addr *saddr,
-		    struct icmp6hdr *icmp6h)
+static void ndisc_send_skb(struct sk_buff *skb, struct net_device *dev,
+			   struct neighbour *neigh,
+			   const struct in6_addr *daddr,
+			   const struct in6_addr *saddr,
+			   struct icmp6hdr *icmp6h)
 {
 	struct flowi6 fl6;
 	struct dst_entry *dst;
@@ -473,8 +470,6 @@ void ndisc_send_skb(struct sk_buff *skb,
 	rcu_read_unlock();
 }
 
-EXPORT_SYMBOL(ndisc_send_skb);
-
 /*
  *	Send a Neighbour Discover packet
  */
-- 
cgit v1.2.3-55-g7522


From 37a393bc4932d7bac360f40064aaafc01ab44901 Mon Sep 17 00:00:00 2001
From: Cong Wang
Date: Tue, 11 Dec 2012 22:23:07 +0000
Subject: bridge: notify mdb changes via netlink

As Stephen mentioned, we need to monitor the mdb
changes in user-space, so add notifications via netlink too.

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Cong Wang <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/rtnetlink.h |  6 ++++
 net/bridge/br_mdb.c            | 80 ++++++++++++++++++++++++++++++++++++++++++
 net/bridge/br_multicast.c      |  2 ++
 net/bridge/br_private.h        |  2 ++
 4 files changed, 90 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 354a1e7d32a3..7a5eb196ade9 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -125,6 +125,10 @@ enum {
 	RTM_GETNETCONF = 82,
 #define RTM_GETNETCONF RTM_GETNETCONF
 
+	RTM_NEWMDB = 84,
+#define RTM_NEWMDB RTM_NEWMDB
+	RTM_DELMDB = 85,
+#define RTM_DELMDB RTM_DELMDB
 	RTM_GETMDB = 86,
 #define RTM_GETMDB RTM_GETMDB
 
@@ -607,6 +611,8 @@ enum rtnetlink_groups {
 #define RTNLGRP_IPV4_NETCONF	RTNLGRP_IPV4_NETCONF
 	RTNLGRP_IPV6_NETCONF,
 #define RTNLGRP_IPV6_NETCONF	RTNLGRP_IPV6_NETCONF
+	RTNLGRP_MDB,
+#define RTNLGRP_MDB		RTNLGRP_MDB
 	__RTNLGRP_MAX
 };
 #define RTNLGRP_MAX	(__RTNLGRP_MAX - 1)
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index ccc43a9bff80..a8cfbf5f3c68 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -155,6 +155,86 @@ out:
 	return skb->len;
 }
 
+static int nlmsg_populate_mdb_fill(struct sk_buff *skb,
+				   struct net_device *dev,
+				   struct br_mdb_entry *entry, u32 pid,
+				   u32 seq, int type, unsigned int flags)
+{
+	struct nlmsghdr *nlh;
+	struct br_port_msg *bpm;
+	struct nlattr *nest, *nest2;
+
+	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	bpm = nlmsg_data(nlh);
+	bpm->family  = AF_BRIDGE;
+	bpm->ifindex = dev->ifindex;
+	nest = nla_nest_start(skb, MDBA_MDB);
+	if (nest == NULL)
+		goto cancel;
+	nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
+	if (nest2 == NULL)
+		goto end;
+
+	if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(*entry), entry))
+		goto end;
+
+	nla_nest_end(skb, nest2);
+	nla_nest_end(skb, nest);
+	return nlmsg_end(skb, nlh);
+
+end:
+	nla_nest_end(skb, nest);
+cancel:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static inline size_t rtnl_mdb_nlmsg_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct br_port_msg))
+		+ nla_total_size(sizeof(struct br_mdb_entry));
+}
+
+static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry,
+			    int type)
+{
+	struct net *net = dev_net(dev);
+	struct sk_buff *skb;
+	int err = -ENOBUFS;
+
+	skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC);
+	if (!skb)
+		goto errout;
+
+	err = nlmsg_populate_mdb_fill(skb, dev, entry, 0, 0, type, NTF_SELF);
+	if (err < 0) {
+		kfree_skb(skb);
+		goto errout;
+	}
+
+	rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC);
+	return;
+errout:
+	rtnl_set_sk_err(net, RTNLGRP_MDB, err);
+}
+
+void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
+		   struct br_ip *group, int type)
+{
+	struct br_mdb_entry entry;
+
+	entry.ifindex = port->dev->ifindex;
+	entry.addr.proto = group->proto;
+	entry.addr.u.ip4 = group->u.ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+	entry.addr.u.ip6 = group->u.ip6;
+#endif
+	__br_mdb_notify(dev, &entry, type);
+}
+
 void br_mdb_init(void)
 {
 	rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, NULL);
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 847b98a1d5e0..d929586ce39e 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -681,6 +681,7 @@ static int br_multicast_add_group(struct net_bridge *br,
 		    (unsigned long)p);
 
 	rcu_assign_pointer(*pp, p);
+	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
 
 found:
 	mod_timer(&p->timer, now + br->multicast_membership_interval);
@@ -1240,6 +1241,7 @@ static void br_multicast_leave_group(struct net_bridge *br,
 			hlist_del_init(&p->mglist);
 			del_timer(&p->timer);
 			call_rcu_bh(&p->rcu, br_multicast_free_pg);
+			br_mdb_notify(br->dev, port, group, RTM_DELMDB);
 
 			if (!mp->ports && !mp->mglist &&
 			    netif_running(br->dev))
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index f95b766c7a98..2807c7680c38 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -435,6 +435,8 @@ extern int br_multicast_toggle(struct net_bridge *br, unsigned long val);
 extern int br_multicast_set_querier(struct net_bridge *br, unsigned long val);
 extern int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val);
 extern void br_mdb_init(void);
+extern void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
+			  struct br_ip *group, int type);
 
 static inline bool br_multicast_is_router(struct net_bridge *br)
 {
-- 
cgit v1.2.3-55-g7522


From cfd567543590f71ca0af397437e2554f9756d750 Mon Sep 17 00:00:00 2001
From: Cong Wang
Date: Tue, 11 Dec 2012 22:23:08 +0000
Subject: bridge: add support of adding and deleting mdb entries

This patch implents adding/deleting mdb entries via netlink.
Currently all entries are temp, we probably need a flag to distinguish
permanent entries too.

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Cong Wang <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h |   8 ++
 net/bridge/br_mdb.c            | 240 +++++++++++++++++++++++++++++++++++++++++
 net/bridge/br_multicast.c      |  55 +++++-----
 net/bridge/br_private.h        |  23 ++++
 4 files changed, 297 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 9a0f6ff0d7e7..afbb18a0227c 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -157,6 +157,7 @@ enum {
 #define MDBA_ROUTER_MAX (__MDBA_ROUTER_MAX - 1)
 
 struct br_port_msg {
+	__u8  family;
 	__u32 ifindex;
 };
 
@@ -171,4 +172,11 @@ struct br_mdb_entry {
 	} addr;
 };
 
+enum {
+	MDBA_SET_ENTRY_UNSPEC,
+	MDBA_SET_ENTRY,
+	__MDBA_SET_ENTRY_MAX,
+};
+#define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_BRIDGE_H */
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index a8cfbf5f3c68..6f0a2eebcb27 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -4,6 +4,7 @@
 #include <linux/netdevice.h>
 #include <linux/rculist.h>
 #include <linux/skbuff.h>
+#include <linux/if_ether.h>
 #include <net/ip.h>
 #include <net/netlink.h>
 #if IS_ENABLED(CONFIG_IPV6)
@@ -235,7 +236,246 @@ void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
 	__br_mdb_notify(dev, &entry, type);
 }
 
+static bool is_valid_mdb_entry(struct br_mdb_entry *entry)
+{
+	if (entry->ifindex == 0)
+		return false;
+
+	if (entry->addr.proto == htons(ETH_P_IP)) {
+		if (!ipv4_is_multicast(entry->addr.u.ip4))
+			return false;
+		if (ipv4_is_local_multicast(entry->addr.u.ip4))
+			return false;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (entry->addr.proto == htons(ETH_P_IPV6)) {
+		if (!ipv6_is_transient_multicast(&entry->addr.u.ip6))
+			return false;
+#endif
+	} else
+		return false;
+
+	return true;
+}
+
+static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
+			struct net_device **pdev, struct br_mdb_entry **pentry)
+{
+	struct net *net = sock_net(skb->sk);
+	struct br_mdb_entry *entry;
+	struct br_port_msg *bpm;
+	struct nlattr *tb[MDBA_SET_ENTRY_MAX+1];
+	struct net_device *dev;
+	int err;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY, NULL);
+	if (err < 0)
+		return err;
+
+	bpm = nlmsg_data(nlh);
+	if (bpm->ifindex == 0) {
+		pr_info("PF_BRIDGE: br_mdb_parse() with invalid ifindex\n");
+		return -EINVAL;
+	}
+
+	dev = __dev_get_by_index(net, bpm->ifindex);
+	if (dev == NULL) {
+		pr_info("PF_BRIDGE: br_mdb_parse() with unknown ifindex\n");
+		return -ENODEV;
+	}
+
+	if (!(dev->priv_flags & IFF_EBRIDGE)) {
+		pr_info("PF_BRIDGE: br_mdb_parse() with non-bridge\n");
+		return -EOPNOTSUPP;
+	}
+
+	*pdev = dev;
+
+	if (!tb[MDBA_SET_ENTRY] ||
+	    nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) {
+		pr_info("PF_BRIDGE: br_mdb_parse() with invalid attr\n");
+		return -EINVAL;
+	}
+
+	entry = nla_data(tb[MDBA_SET_ENTRY]);
+	if (!is_valid_mdb_entry(entry)) {
+		pr_info("PF_BRIDGE: br_mdb_parse() with invalid entry\n");
+		return -EINVAL;
+	}
+
+	*pentry = entry;
+	return 0;
+}
+
+static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
+			    struct br_ip *group)
+{
+	struct net_bridge_mdb_entry *mp;
+	struct net_bridge_port_group *p;
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_mdb_htable *mdb;
+	int err;
+
+	mdb = mlock_dereference(br->mdb, br);
+	mp = br_mdb_ip_get(mdb, group);
+	if (!mp) {
+		mp = br_multicast_new_group(br, port, group);
+		err = PTR_ERR(mp);
+		if (IS_ERR(mp))
+			return err;
+	}
+
+	for (pp = &mp->ports;
+	     (p = mlock_dereference(*pp, br)) != NULL;
+	     pp = &p->next) {
+		if (p->port == port)
+			return -EEXIST;
+		if ((unsigned long)p->port < (unsigned long)port)
+			break;
+	}
+
+	p = br_multicast_new_port_group(port, group, *pp);
+	if (unlikely(!p))
+		return -ENOMEM;
+	rcu_assign_pointer(*pp, p);
+
+	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
+	return 0;
+}
+
+static int __br_mdb_add(struct net *net, struct net_bridge *br,
+			struct br_mdb_entry *entry)
+{
+	struct br_ip ip;
+	struct net_device *dev;
+	struct net_bridge_port *p;
+	int ret;
+
+	if (!netif_running(br->dev) || br->multicast_disabled)
+		return -EINVAL;
+
+	dev = __dev_get_by_index(net, entry->ifindex);
+	if (!dev)
+		return -ENODEV;
+
+	p = br_port_get_rtnl(dev);
+	if (!p || p->br != br || p->state == BR_STATE_DISABLED)
+		return -EINVAL;
+
+	ip.proto = entry->addr.proto;
+	if (ip.proto == htons(ETH_P_IP))
+		ip.u.ip4 = entry->addr.u.ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+	else
+		ip.u.ip6 = entry->addr.u.ip6;
+#endif
+
+	spin_lock_bh(&br->multicast_lock);
+	ret = br_mdb_add_group(br, p, &ip);
+	spin_unlock_bh(&br->multicast_lock);
+	return ret;
+}
+
+static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+{
+	struct net *net = sock_net(skb->sk);
+	struct br_mdb_entry *entry;
+	struct net_device *dev;
+	struct net_bridge *br;
+	int err;
+
+	err = br_mdb_parse(skb, nlh, &dev, &entry);
+	if (err < 0)
+		return err;
+
+	br = netdev_priv(dev);
+
+	err = __br_mdb_add(net, br, entry);
+	if (!err)
+		__br_mdb_notify(dev, entry, RTM_NEWMDB);
+	return err;
+}
+
+static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
+{
+	struct net_bridge_mdb_htable *mdb;
+	struct net_bridge_mdb_entry *mp;
+	struct net_bridge_port_group *p;
+	struct net_bridge_port_group __rcu **pp;
+	struct br_ip ip;
+	int err = -EINVAL;
+
+	if (!netif_running(br->dev) || br->multicast_disabled)
+		return -EINVAL;
+
+	if (timer_pending(&br->multicast_querier_timer))
+		return -EBUSY;
+
+	ip.proto = entry->addr.proto;
+	if (ip.proto == htons(ETH_P_IP))
+		ip.u.ip4 = entry->addr.u.ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+	else
+		ip.u.ip6 = entry->addr.u.ip6;
+#endif
+
+	spin_lock_bh(&br->multicast_lock);
+	mdb = mlock_dereference(br->mdb, br);
+
+	mp = br_mdb_ip_get(mdb, &ip);
+	if (!mp)
+		goto unlock;
+
+	for (pp = &mp->ports;
+	     (p = mlock_dereference(*pp, br)) != NULL;
+	     pp = &p->next) {
+		if (!p->port || p->port->dev->ifindex != entry->ifindex)
+			continue;
+
+		if (p->port->state == BR_STATE_DISABLED)
+			goto unlock;
+
+		rcu_assign_pointer(*pp, p->next);
+		hlist_del_init(&p->mglist);
+		del_timer(&p->timer);
+		call_rcu_bh(&p->rcu, br_multicast_free_pg);
+		err = 0;
+
+		if (!mp->ports && !mp->mglist &&
+		    netif_running(br->dev))
+			mod_timer(&mp->timer, jiffies);
+		break;
+	}
+
+unlock:
+	spin_unlock_bh(&br->multicast_lock);
+	return err;
+}
+
+static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+{
+	struct net_device *dev;
+	struct br_mdb_entry *entry;
+	struct net_bridge *br;
+	int err;
+
+	err = br_mdb_parse(skb, nlh, &dev, &entry);
+	if (err < 0)
+		return err;
+
+	br = netdev_priv(dev);
+
+	err = __br_mdb_del(br, entry);
+	if (!err)
+		__br_mdb_notify(dev, entry, RTM_DELMDB);
+	return err;
+}
+
 void br_mdb_init(void)
 {
 	rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, NULL);
+	rtnl_register(PF_BRIDGE, RTM_NEWMDB, br_mdb_add, NULL, NULL);
+	rtnl_register(PF_BRIDGE, RTM_DELMDB, br_mdb_del, NULL, NULL);
 }
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index d929586ce39e..977c3ee02e65 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -27,27 +27,14 @@
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
 #include <net/mld.h>
-#include <net/addrconf.h>
 #include <net/ip6_checksum.h>
 #endif
 
 #include "br_private.h"
 
-#define mlock_dereference(X, br) \
-	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
-
 static void br_multicast_start_querier(struct net_bridge *br);
 unsigned int br_mdb_rehash_seq;
 
-#if IS_ENABLED(CONFIG_IPV6)
-static inline int ipv6_is_transient_multicast(const struct in6_addr *addr)
-{
-	if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr))
-		return 1;
-	return 0;
-}
-#endif
-
 static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
 {
 	if (a->proto != b->proto)
@@ -104,8 +91,8 @@ static struct net_bridge_mdb_entry *__br_mdb_ip_get(
 	return NULL;
 }
 
-static struct net_bridge_mdb_entry *br_mdb_ip_get(
-	struct net_bridge_mdb_htable *mdb, struct br_ip *dst)
+struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge_mdb_htable *mdb,
+					   struct br_ip *dst)
 {
 	if (!mdb)
 		return NULL;
@@ -208,7 +195,7 @@ static int br_mdb_copy(struct net_bridge_mdb_htable *new,
 	return maxlen > elasticity ? -EINVAL : 0;
 }
 
-static void br_multicast_free_pg(struct rcu_head *head)
+void br_multicast_free_pg(struct rcu_head *head)
 {
 	struct net_bridge_port_group *p =
 		container_of(head, struct net_bridge_port_group, rcu);
@@ -584,9 +571,8 @@ err:
 	return mp;
 }
 
-static struct net_bridge_mdb_entry *br_multicast_new_group(
-	struct net_bridge *br, struct net_bridge_port *port,
-	struct br_ip *group)
+struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
+	struct net_bridge_port *port, struct br_ip *group)
 {
 	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_mdb_entry *mp;
@@ -633,6 +619,26 @@ out:
 	return mp;
 }
 
+struct net_bridge_port_group *br_multicast_new_port_group(
+			struct net_bridge_port *port,
+			struct br_ip *group,
+			struct net_bridge_port_group *next)
+{
+	struct net_bridge_port_group *p;
+
+	p = kzalloc(sizeof(*p), GFP_ATOMIC);
+	if (unlikely(!p))
+		return NULL;
+
+	p->addr = *group;
+	p->port = port;
+	p->next = next;
+	hlist_add_head(&p->mglist, &port->mglist);
+	setup_timer(&p->timer, br_multicast_port_group_expired,
+		    (unsigned long)p);
+	return p;
+}
+
 static int br_multicast_add_group(struct net_bridge *br,
 				  struct net_bridge_port *port,
 				  struct br_ip *group)
@@ -668,18 +674,9 @@ static int br_multicast_add_group(struct net_bridge *br,
 			break;
 	}
 
-	p = kzalloc(sizeof(*p), GFP_ATOMIC);
-	err = -ENOMEM;
+	p = br_multicast_new_port_group(port, group, *pp);
 	if (unlikely(!p))
 		goto err;
-
-	p->addr = *group;
-	p->port = port;
-	p->next = *pp;
-	hlist_add_head(&p->mglist, &port->mglist);
-	setup_timer(&p->timer, br_multicast_port_group_expired,
-		    (unsigned long)p);
-
 	rcu_assign_pointer(*pp, p);
 	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 2807c7680c38..f21a739a6186 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -434,10 +434,33 @@ extern int br_multicast_set_port_router(struct net_bridge_port *p,
 extern int br_multicast_toggle(struct net_bridge *br, unsigned long val);
 extern int br_multicast_set_querier(struct net_bridge *br, unsigned long val);
 extern int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val);
+extern struct net_bridge_mdb_entry *br_mdb_ip_get(
+				struct net_bridge_mdb_htable *mdb,
+				struct br_ip *dst);
+extern struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
+				struct net_bridge_port *port, struct br_ip *group);
+extern void br_multicast_free_pg(struct rcu_head *head);
+extern struct net_bridge_port_group *br_multicast_new_port_group(
+				struct net_bridge_port *port,
+				struct br_ip *group,
+				struct net_bridge_port_group *next);
 extern void br_mdb_init(void);
 extern void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
 			  struct br_ip *group, int type);
 
+#define mlock_dereference(X, br) \
+	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
+
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/addrconf.h>
+static inline int ipv6_is_transient_multicast(const struct in6_addr *addr)
+{
+	if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr))
+		return 1;
+	return 0;
+}
+#endif
+
 static inline bool br_multicast_is_router(struct net_bridge *br)
 {
 	return br->multicast_router == 2 ||
-- 
cgit v1.2.3-55-g7522


From d4676eac0de2e6d88eb3e2c02b4e9813d7d7f205 Mon Sep 17 00:00:00 2001
From: Yan Burman
Date: Wed, 12 Dec 2012 02:13:17 +0000
Subject: net: ethtool: Add destination MAC address to flow steering API

Add ability to specify destination MAC address for L3/L4 flow spec
in order to be able to specify action for different VM's under vSwitch
configuration. This change is transparent to older userspace.

Signed-off-by: Yan Burman <yanb@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ethtool.h | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index d3eaaaf1009e..be8c41e2dc15 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -500,13 +500,15 @@ union ethtool_flow_union {
 	struct ethtool_ah_espip4_spec		esp_ip4_spec;
 	struct ethtool_usrip4_spec		usr_ip4_spec;
 	struct ethhdr				ether_spec;
-	__u8					hdata[60];
+	__u8					hdata[52];
 };
 
 struct ethtool_flow_ext {
-	__be16	vlan_etype;
-	__be16	vlan_tci;
-	__be32	data[2];
+	__u8		padding[2];
+	unsigned char	h_dest[ETH_ALEN];	/* destination eth addr	*/
+	__be16		vlan_etype;
+	__be16		vlan_tci;
+	__be32		data[2];
 };
 
 /**
@@ -1027,6 +1029,7 @@ enum ethtool_sfeatures_retval_bits {
 #define	ETHER_FLOW	0x12	/* spec only (ether_spec) */
 /* Flag to enable additional fields in struct ethtool_rx_flow_spec */
 #define	FLOW_EXT	0x80000000
+#define	FLOW_MAC_EXT	0x40000000
 
 /* L3-L4 network traffic flow hash options */
 #define	RXH_L2DA	(1 << 1)
-- 
cgit v1.2.3-55-g7522


From 93b4796dede916de74b21fbd637588da6a99a7ec Mon Sep 17 00:00:00 2001
From: Kirill A. Shutemov
Date: Wed, 12 Dec 2012 13:50:54 -0800
Subject: thp: do_huge_pmd_wp_page(): handle huge zero page

On write access to huge zero page we alloc a new huge page and clear it.

If ENOMEM, graceful fallback: we create a new pmd table and set pte around
fault address to newly allocated normal (4k) page.  All other ptes in the
pmd set to normal zero page.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@linux.intel.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |   8 ++++
 mm/huge_memory.c   | 111 +++++++++++++++++++++++++++++++++++++++++++++--------
 mm/memory.c        |   7 ----
 3 files changed, 104 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4af4f0b1be4c..4b80bad4a367 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -516,6 +516,14 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 }
 #endif
 
+#ifndef my_zero_pfn
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+	extern unsigned long zero_pfn;
+	return zero_pfn;
+}
+#endif
+
 /*
  * Multiple processes may "see" the same page. E.g. for untouched
  * mappings of /dev/null, all processes see the same page full of
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 650625390f61..a959b3a4ddd5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -858,6 +858,70 @@ unlock:
 	spin_unlock(&mm->page_table_lock);
 }
 
+static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
+		struct vm_area_struct *vma, unsigned long address,
+		pmd_t *pmd, unsigned long haddr)
+{
+	pgtable_t pgtable;
+	pmd_t _pmd;
+	struct page *page;
+	int i, ret = 0;
+	unsigned long mmun_start;	/* For mmu_notifiers */
+	unsigned long mmun_end;		/* For mmu_notifiers */
+
+	page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+	if (!page) {
+		ret |= VM_FAULT_OOM;
+		goto out;
+	}
+
+	if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) {
+		put_page(page);
+		ret |= VM_FAULT_OOM;
+		goto out;
+	}
+
+	clear_user_highpage(page, address);
+	__SetPageUptodate(page);
+
+	mmun_start = haddr;
+	mmun_end   = haddr + HPAGE_PMD_SIZE;
+	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+
+	spin_lock(&mm->page_table_lock);
+	pmdp_clear_flush(vma, haddr, pmd);
+	/* leave pmd empty until pte is filled */
+
+	pgtable = pgtable_trans_huge_withdraw(mm);
+	pmd_populate(mm, &_pmd, pgtable);
+
+	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+		pte_t *pte, entry;
+		if (haddr == (address & PAGE_MASK)) {
+			entry = mk_pte(page, vma->vm_page_prot);
+			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+			page_add_new_anon_rmap(page, vma, haddr);
+		} else {
+			entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
+			entry = pte_mkspecial(entry);
+		}
+		pte = pte_offset_map(&_pmd, haddr);
+		VM_BUG_ON(!pte_none(*pte));
+		set_pte_at(mm, haddr, pte, entry);
+		pte_unmap(pte);
+	}
+	smp_wmb(); /* make pte visible before pmd */
+	pmd_populate(mm, pmd, pgtable);
+	spin_unlock(&mm->page_table_lock);
+	inc_mm_counter(mm, MM_ANONPAGES);
+
+	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+
+	ret |= VM_FAULT_WRITE;
+out:
+	return ret;
+}
+
 static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long address,
@@ -964,19 +1028,21 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pmd_t *pmd, pmd_t orig_pmd)
 {
 	int ret = 0;
-	struct page *page, *new_page;
+	struct page *page = NULL, *new_page;
 	unsigned long haddr;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
 	VM_BUG_ON(!vma->anon_vma);
+	haddr = address & HPAGE_PMD_MASK;
+	if (is_huge_zero_pmd(orig_pmd))
+		goto alloc;
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(*pmd, orig_pmd)))
 		goto out_unlock;
 
 	page = pmd_page(orig_pmd);
 	VM_BUG_ON(!PageCompound(page) || !PageHead(page));
-	haddr = address & HPAGE_PMD_MASK;
 	if (page_mapcount(page) == 1) {
 		pmd_t entry;
 		entry = pmd_mkyoung(orig_pmd);
@@ -988,7 +1054,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	get_page(page);
 	spin_unlock(&mm->page_table_lock);
-
+alloc:
 	if (transparent_hugepage_enabled(vma) &&
 	    !transparent_hugepage_debug_cow())
 		new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
@@ -998,24 +1064,34 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (unlikely(!new_page)) {
 		count_vm_event(THP_FAULT_FALLBACK);
-		ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
-						   pmd, orig_pmd, page, haddr);
-		if (ret & VM_FAULT_OOM)
-			split_huge_page(page);
-		put_page(page);
+		if (is_huge_zero_pmd(orig_pmd)) {
+			ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
+					address, pmd, haddr);
+		} else {
+			ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
+					pmd, orig_pmd, page, haddr);
+			if (ret & VM_FAULT_OOM)
+				split_huge_page(page);
+			put_page(page);
+		}
 		goto out;
 	}
 	count_vm_event(THP_FAULT_ALLOC);
 
 	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
 		put_page(new_page);
-		split_huge_page(page);
-		put_page(page);
+		if (page) {
+			split_huge_page(page);
+			put_page(page);
+		}
 		ret |= VM_FAULT_OOM;
 		goto out;
 	}
 
-	copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
+	if (is_huge_zero_pmd(orig_pmd))
+		clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
+	else
+		copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
 	__SetPageUptodate(new_page);
 
 	mmun_start = haddr;
@@ -1023,7 +1099,8 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 
 	spin_lock(&mm->page_table_lock);
-	put_page(page);
+	if (page)
+		put_page(page);
 	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
 		spin_unlock(&mm->page_table_lock);
 		mem_cgroup_uncharge_page(new_page);
@@ -1031,14 +1108,18 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_mn;
 	} else {
 		pmd_t entry;
-		VM_BUG_ON(!PageHead(page));
 		entry = mk_huge_pmd(new_page, vma);
 		pmdp_clear_flush(vma, haddr, pmd);
 		page_add_new_anon_rmap(new_page, vma, haddr);
 		set_pmd_at(mm, haddr, pmd, entry);
 		update_mmu_cache_pmd(vma, address, pmd);
-		page_remove_rmap(page);
-		put_page(page);
+		if (is_huge_zero_pmd(orig_pmd))
+			add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
+		else {
+			VM_BUG_ON(!PageHead(page));
+			page_remove_rmap(page);
+			put_page(page);
+		}
 		ret |= VM_FAULT_WRITE;
 	}
 	spin_unlock(&mm->page_table_lock);
diff --git a/mm/memory.c b/mm/memory.c
index 765377385632..259b34fe1347 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -724,13 +724,6 @@ static inline int is_zero_pfn(unsigned long pfn)
 }
 #endif
 
-#ifndef my_zero_pfn
-static inline unsigned long my_zero_pfn(unsigned long addr)
-{
-	return zero_pfn;
-}
-#endif
-
 /*
  * vm_normal_page -- This function gets the "struct page" associated with a pte.
  *
-- 
cgit v1.2.3-55-g7522


From e180377f1ae48b3cbc559c9875d9b038f7f000c6 Mon Sep 17 00:00:00 2001
From: Kirill A. Shutemov
Date: Wed, 12 Dec 2012 13:50:59 -0800
Subject: thp: change split_huge_page_pmd() interface

Pass vma instead of mm and add address parameter.

In most cases we already have vma on the stack. We provides
split_huge_page_pmd_mm() for few cases when we have mm, but not vma.

This change is preparation to huge zero pmd splitting implementation.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@linux.intel.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/transhuge.txt |  4 ++--
 arch/x86/kernel/vm86_32.c      |  2 +-
 fs/proc/task_mmu.c             |  2 +-
 include/linux/huge_mm.h        | 14 ++++++++++----
 mm/huge_memory.c               | 19 +++++++++++++++++--
 mm/memory.c                    |  4 ++--
 mm/mempolicy.c                 |  2 +-
 mm/mprotect.c                  |  2 +-
 mm/mremap.c                    |  2 +-
 mm/pagewalk.c                  |  2 +-
 10 files changed, 37 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
index f734bb2a78dc..8f5b41db314c 100644
--- a/Documentation/vm/transhuge.txt
+++ b/Documentation/vm/transhuge.txt
@@ -276,7 +276,7 @@ unaffected. libhugetlbfs will also work fine as usual.
 == Graceful fallback ==
 
 Code walking pagetables but unware about huge pmds can simply call
-split_huge_page_pmd(mm, pmd) where the pmd is the one returned by
+split_huge_page_pmd(vma, addr, pmd) where the pmd is the one returned by
 pmd_offset. It's trivial to make the code transparent hugepage aware
 by just grepping for "pmd_offset" and adding split_huge_page_pmd where
 missing after pmd_offset returns the pmd. Thanks to the graceful
@@ -299,7 +299,7 @@ diff --git a/mm/mremap.c b/mm/mremap.c
 		return NULL;
 
 	pmd = pmd_offset(pud, addr);
-+	split_huge_page_pmd(mm, pmd);
++	split_huge_page_pmd(vma, addr, pmd);
 	if (pmd_none_or_clear_bad(pmd))
 		return NULL;
 
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 5c9687b1bde6..1dfe69cc78a8 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -182,7 +182,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	if (pud_none_or_clear_bad(pud))
 		goto out;
 	pmd = pmd_offset(pud, 0xA0000);
-	split_huge_page_pmd(mm, pmd);
+	split_huge_page_pmd_mm(mm, 0xA0000, pmd);
 	if (pmd_none_or_clear_bad(pmd))
 		goto out;
 	pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 90c63f9392a5..291a0d15a0be 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -643,7 +643,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	spinlock_t *ptl;
 	struct page *page;
 
-	split_huge_page_pmd(walk->mm, pmd);
+	split_huge_page_pmd(vma, addr, pmd);
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 1af477552459..3132ea788581 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -95,12 +95,14 @@ extern int handle_pte_fault(struct mm_struct *mm,
 			    struct vm_area_struct *vma, unsigned long address,
 			    pte_t *pte, pmd_t *pmd, unsigned int flags);
 extern int split_huge_page(struct page *page);
-extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd);
-#define split_huge_page_pmd(__mm, __pmd)				\
+extern void __split_huge_page_pmd(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmd);
+#define split_huge_page_pmd(__vma, __address, __pmd)			\
 	do {								\
 		pmd_t *____pmd = (__pmd);				\
 		if (unlikely(pmd_trans_huge(*____pmd)))			\
-			__split_huge_page_pmd(__mm, ____pmd);		\
+			__split_huge_page_pmd(__vma, __address,		\
+					____pmd);			\
 	}  while (0)
 #define wait_split_huge_page(__anon_vma, __pmd)				\
 	do {								\
@@ -110,6 +112,8 @@ extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd);
 		BUG_ON(pmd_trans_splitting(*____pmd) ||			\
 		       pmd_trans_huge(*____pmd));			\
 	} while (0)
+extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
+		pmd_t *pmd);
 #if HPAGE_PMD_ORDER > MAX_ORDER
 #error "hugepages can't be allocated by the buddy allocator"
 #endif
@@ -177,10 +181,12 @@ static inline int split_huge_page(struct page *page)
 {
 	return 0;
 }
-#define split_huge_page_pmd(__mm, __pmd)	\
+#define split_huge_page_pmd(__vma, __address, __pmd)	\
 	do { } while (0)
 #define wait_split_huge_page(__anon_vma, __pmd)	\
 	do { } while (0)
+#define split_huge_page_pmd_mm(__mm, __address, __pmd)	\
+	do { } while (0)
 #define compound_trans_head(page) compound_head(page)
 static inline int hugepage_madvise(struct vm_area_struct *vma,
 				   unsigned long *vm_flags, int advice)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7742fb36eb4d..de6aa5f3fdd2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2475,9 +2475,14 @@ static int khugepaged(void *none)
 	return 0;
 }
 
-void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd)
+void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
+		pmd_t *pmd)
 {
 	struct page *page;
+	unsigned long haddr = address & HPAGE_PMD_MASK;
+	struct mm_struct *mm = vma->vm_mm;
+
+	BUG_ON(vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE);
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_trans_huge(*pmd))) {
@@ -2495,6 +2500,16 @@ void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd)
 	BUG_ON(pmd_trans_huge(*pmd));
 }
 
+void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
+		pmd_t *pmd)
+{
+	struct vm_area_struct *vma;
+
+	vma = find_vma(mm, address);
+	BUG_ON(vma == NULL);
+	split_huge_page_pmd(vma, address, pmd);
+}
+
 static void split_huge_page_address(struct mm_struct *mm,
 				    unsigned long address)
 {
@@ -2509,7 +2524,7 @@ static void split_huge_page_address(struct mm_struct *mm,
 	 * Caller holds the mmap_sem write mode, so a huge pmd cannot
 	 * materialize from under us.
 	 */
-	split_huge_page_pmd(mm, pmd);
+	split_huge_page_pmd_mm(mm, address, pmd);
 }
 
 void __vma_adjust_trans_huge(struct vm_area_struct *vma,
diff --git a/mm/memory.c b/mm/memory.c
index 259b34fe1347..f9a4b0cb8623 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1243,7 +1243,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 					BUG();
 				}
 #endif
-				split_huge_page_pmd(vma->vm_mm, pmd);
+				split_huge_page_pmd(vma, addr, pmd);
 			} else if (zap_huge_pmd(tlb, vma, pmd, addr))
 				goto next;
 			/* fall through */
@@ -1512,7 +1512,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	}
 	if (pmd_trans_huge(*pmd)) {
 		if (flags & FOLL_SPLIT) {
-			split_huge_page_pmd(mm, pmd);
+			split_huge_page_pmd(vma, address, pmd);
 			goto split_fallthrough;
 		}
 		spin_lock(&mm->page_table_lock);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 05b28361a39b..0719e8dd4945 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -511,7 +511,7 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		split_huge_page_pmd(vma->vm_mm, pmd);
+		split_huge_page_pmd(vma, addr, pmd);
 		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
 			continue;
 		if (check_pte_range(vma, pmd, addr, next, nodes,
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a40992610ab6..e8c3938db6fa 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -90,7 +90,7 @@ static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
-				split_huge_page_pmd(vma->vm_mm, pmd);
+				split_huge_page_pmd(vma, addr, pmd);
 			else if (change_huge_pmd(vma, pmd, addr, newprot))
 				continue;
 			/* fall through */
diff --git a/mm/mremap.c b/mm/mremap.c
index 1b61c2d3307a..eabb24da6c9e 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -182,7 +182,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				need_flush = true;
 				continue;
 			} else if (!err) {
-				split_huge_page_pmd(vma->vm_mm, old_pmd);
+				split_huge_page_pmd(vma, old_addr, old_pmd);
 			}
 			VM_BUG_ON(pmd_trans_huge(*old_pmd));
 		}
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 6c118d012bb5..35aa294656cd 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -58,7 +58,7 @@ again:
 		if (!walk->pte_entry)
 			continue;
 
-		split_huge_page_pmd(walk->mm, pmd);
+		split_huge_page_pmd_mm(walk->mm, addr, pmd);
 		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
 			goto again;
 		err = walk_pte_range(pmd, addr, next, walk);
-- 
cgit v1.2.3-55-g7522


From d8a8e1f0da3d29d7268b3300c96a059d63901b76 Mon Sep 17 00:00:00 2001
From: Kirill A. Shutemov
Date: Wed, 12 Dec 2012 13:51:09 -0800
Subject: thp, vmstat: implement HZP_ALLOC and HZP_ALLOC_FAILED events

hzp_alloc is incremented every time a huge zero page is successfully
	allocated. It includes allocations which where dropped due
	race with other allocation. Note, it doesn't count every map
	of the huge zero page, only its allocation.

hzp_alloc_failed is incremented if kernel fails to allocate huge zero
	page and falls back to using small pages.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@linux.intel.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/transhuge.txt | 8 ++++++++
 include/linux/vm_event_item.h  | 2 ++
 mm/huge_memory.c               | 5 ++++-
 mm/vmstat.c                    | 2 ++
 4 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
index 8f5b41db314c..60aeedd54615 100644
--- a/Documentation/vm/transhuge.txt
+++ b/Documentation/vm/transhuge.txt
@@ -197,6 +197,14 @@ thp_split is incremented every time a huge page is split into base
 	pages. This can happen for a variety of reasons but a common
 	reason is that a huge page is old and is being reclaimed.
 
+thp_zero_page_alloc is incremented every time a huge zero page is
+	successfully allocated. It includes allocations which where
+	dropped due race with other allocation. Note, it doesn't count
+	every map of the huge zero page, only its allocation.
+
+thp_zero_page_alloc_failed is incremented if kernel fails to allocate
+	huge zero page and falls back to using small pages.
+
 As the system ages, allocating huge pages may be expensive as the
 system uses memory compaction to copy data around memory to free a
 huge page for use. There are some counters in /proc/vmstat to help
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 3d3114594370..fe786f07d2bd 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -58,6 +58,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		THP_COLLAPSE_ALLOC,
 		THP_COLLAPSE_ALLOC_FAILED,
 		THP_SPLIT,
+		THP_ZERO_PAGE_ALLOC,
+		THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
 		NR_VM_EVENT_ITEMS
 };
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d89220cb1d9f..9a5d45dfad44 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -184,8 +184,11 @@ retry:
 
 	zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE,
 			HPAGE_PMD_ORDER);
-	if (!zero_page)
+	if (!zero_page) {
+		count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
 		return 0;
+	}
+	count_vm_event(THP_ZERO_PAGE_ALLOC);
 	preempt_disable();
 	if (cmpxchg(&huge_zero_pfn, 0, page_to_pfn(zero_page))) {
 		preempt_enable();
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c7370579111b..5da4b19023c3 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -801,6 +801,8 @@ const char * const vmstat_text[] = {
 	"thp_collapse_alloc",
 	"thp_collapse_alloc_failed",
 	"thp_split",
+	"thp_zero_page_alloc",
+	"thp_zero_page_alloc_failed",
 #endif
 
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
-- 
cgit v1.2.3-55-g7522


From 79da5407eeadc740fbf4b45d6df7d7f8e6adaf2c Mon Sep 17 00:00:00 2001
From: Kirill A. Shutemov
Date: Wed, 12 Dec 2012 13:51:12 -0800
Subject: thp: introduce sysfs knob to disable huge zero page

By default kernel tries to use huge zero page on read page fault.  It's
possible to disable huge zero page by writing 0 or enable it back by
writing 1:

echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page
echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@linux.intel.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/transhuge.txt |  7 +++++++
 include/linux/huge_mm.h        |  4 ++++
 mm/huge_memory.c               | 21 +++++++++++++++++++--
 3 files changed, 30 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
index 60aeedd54615..8785fb87d9c7 100644
--- a/Documentation/vm/transhuge.txt
+++ b/Documentation/vm/transhuge.txt
@@ -116,6 +116,13 @@ echo always >/sys/kernel/mm/transparent_hugepage/defrag
 echo madvise >/sys/kernel/mm/transparent_hugepage/defrag
 echo never >/sys/kernel/mm/transparent_hugepage/defrag
 
+By default kernel tries to use huge zero page on read page fault.
+It's possible to disable huge zero page by writing 0 or enable it
+back by writing 1:
+
+echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page
+echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page
+
 khugepaged will be automatically started when
 transparent_hugepage/enabled is set to "always" or "madvise, and it'll
 be automatically shutdown if it's set to "never".
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 3132ea788581..092dc5305a32 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -39,6 +39,7 @@ enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,
+	TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG,
 #ifdef CONFIG_DEBUG_VM
 	TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG,
 #endif
@@ -78,6 +79,9 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 	 (transparent_hugepage_flags &					\
 	  (1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG) &&		\
 	  (__vma)->vm_flags & VM_HUGEPAGE))
+#define transparent_hugepage_use_zero_page()				\
+	(transparent_hugepage_flags &					\
+	 (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
 #ifdef CONFIG_DEBUG_VM
 #define transparent_hugepage_debug_cow()				\
 	(transparent_hugepage_flags &					\
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9a5d45dfad44..72835cea0b0f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -39,7 +39,8 @@ unsigned long transparent_hugepage_flags __read_mostly =
 	(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
 #endif
 	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)|
-	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
+	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
+	(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
 
 /* default scan 8*512 pte (or vmas) every 30 second */
 static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8;
@@ -357,6 +358,20 @@ static ssize_t defrag_store(struct kobject *kobj,
 static struct kobj_attribute defrag_attr =
 	__ATTR(defrag, 0644, defrag_show, defrag_store);
 
+static ssize_t use_zero_page_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	return single_flag_show(kobj, attr, buf,
+				TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
+}
+static ssize_t use_zero_page_store(struct kobject *kobj,
+		struct kobj_attribute *attr, const char *buf, size_t count)
+{
+	return single_flag_store(kobj, attr, buf, count,
+				 TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
+}
+static struct kobj_attribute use_zero_page_attr =
+	__ATTR(use_zero_page, 0644, use_zero_page_show, use_zero_page_store);
 #ifdef CONFIG_DEBUG_VM
 static ssize_t debug_cow_show(struct kobject *kobj,
 				struct kobj_attribute *attr, char *buf)
@@ -378,6 +393,7 @@ static struct kobj_attribute debug_cow_attr =
 static struct attribute *hugepage_attr[] = {
 	&enabled_attr.attr,
 	&defrag_attr.attr,
+	&use_zero_page_attr.attr,
 #ifdef CONFIG_DEBUG_VM
 	&debug_cow_attr.attr,
 #endif
@@ -779,7 +795,8 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			return VM_FAULT_OOM;
 		if (unlikely(khugepaged_enter(vma)))
 			return VM_FAULT_OOM;
-		if (!(flags & FAULT_FLAG_WRITE)) {
+		if (!(flags & FAULT_FLAG_WRITE) &&
+				transparent_hugepage_use_zero_page()) {
 			pgtable_t pgtable;
 			unsigned long zero_pfn;
 			pgtable = pte_alloc_one(mm, haddr);
-- 
cgit v1.2.3-55-g7522


From 8219fc48adb3b09eabf502c560bf13f273ea69a3 Mon Sep 17 00:00:00 2001
From: Lai Jiangshan
Date: Wed, 12 Dec 2012 13:51:21 -0800
Subject: mm: node_states: introduce N_MEMORY

We have N_NORMAL_MEMORY for standing for the nodes that have normal memory
with zone_type <= ZONE_NORMAL.

And we have N_HIGH_MEMORY for standing for the nodes that have normal or
high memory.

But we don't have any word to stand for the nodes that have *any* memory.

And we have N_CPU but without N_MEMORY.

Current code reuse the N_HIGH_MEMORY for this purpose because any node
which has memory must have high memory or normal memory currently.

A)	But this reusing is bad for *readability*. Because the name
	N_HIGH_MEMORY just stands for high or normal:

A.example 1)
	mem_cgroup_nr_lru_pages():
		for_each_node_state(nid, N_HIGH_MEMORY)

	The user will be confused(why this function just counts for high or
	normal memory node? does it counts for ZONE_MOVABLE's lru pages?)
	until someone else tell them N_HIGH_MEMORY is reused to stand for
	nodes that have any memory.

A.cont) If we introduce N_MEMORY, we can reduce this confusing
	AND make the code more clearly:

A.example 2) mm/page_cgroup.c use N_HIGH_MEMORY twice:

	One is in page_cgroup_init(void):
		for_each_node_state(nid, N_HIGH_MEMORY) {

	It means if the node have memory, we will allocate page_cgroup map for
	the node. We should use N_MEMORY instead here to gaim more clearly.

	The second using is in alloc_page_cgroup():
		if (node_state(nid, N_HIGH_MEMORY))
			addr = vzalloc_node(size, nid);

	It means if the node has high or normal memory that can be allocated
	from kernel. We should keep N_HIGH_MEMORY here, and it will be better
	if the "any memory" semantic of N_HIGH_MEMORY is removed.

B)	This reusing is out-dated if we introduce MOVABLE-dedicated node.
	The MOVABLE-dedicated node should not appear in
	node_stats[N_HIGH_MEMORY] nor node_stats[N_NORMAL_MEMORY],
	because MOVABLE-dedicated node has no high or normal memory.

	In x86_64, N_HIGH_MEMORY=N_NORMAL_MEMORY, if a MOVABLE-dedicated node
	is in node_stats[N_HIGH_MEMORY], it is also means it is in
	node_stats[N_NORMAL_MEMORY], it causes SLUB wrong.

	The slub uses
		for_each_node_state(nid, N_NORMAL_MEMORY)
	and creates kmem_cache_node for MOVABLE-dedicated node and cause problem.

In one word, we need a N_MEMORY.  We just intrude it as an alias to
N_HIGH_MEMORY and fix all im-proper usages of N_HIGH_MEMORY in late
patches.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: Hillf Danton <dhillf@gmail.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: Lin Feng <linfeng@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/nodemask.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 7afc36334d52..c6ebdc97a428 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -380,6 +380,7 @@ enum node_states {
 #else
 	N_HIGH_MEMORY = N_NORMAL_MEMORY,
 #endif
+	N_MEMORY = N_HIGH_MEMORY,
 	N_CPU,		/* The node has one or more cpus */
 	NR_NODE_STATES
 };
-- 
cgit v1.2.3-55-g7522


From 38d7bee9d24adf4c95676a3dc902827c72930ebb Mon Sep 17 00:00:00 2001
From: Lai Jiangshan
Date: Wed, 12 Dec 2012 13:51:24 -0800
Subject: cpuset: use N_MEMORY instead N_HIGH_MEMORY

N_HIGH_MEMORY stands for the nodes that has normal or high memory.
N_MEMORY stands for the nodes that has any memory.

The code here need to handle with the nodes which have memory, we should
use N_MEMORY instead.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Hillf Danton <dhillf@gmail.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Lin Feng <linfeng@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cgroups/cpusets.txt |  2 +-
 include/linux/cpuset.h            |  2 +-
 kernel/cpuset.c                   | 32 ++++++++++++++++----------------
 3 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index cefd3d8bbd11..12e01d432bfe 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
@@ -218,7 +218,7 @@ and name space for cpusets, with a minimum of additional kernel code.
 The cpus and mems files in the root (top_cpuset) cpuset are
 read-only.  The cpus file automatically tracks the value of
 cpu_online_mask using a CPU hotplug notifier, and the mems file
-automatically tracks the value of node_states[N_HIGH_MEMORY]--i.e.,
+automatically tracks the value of node_states[N_MEMORY]--i.e.,
 nodes with memory--using the cpuset_track_online_nodes() hook.
 
 
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 838320fc3d1d..8c8a60d29407 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -144,7 +144,7 @@ static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
 	return node_possible_map;
 }
 
-#define cpuset_current_mems_allowed (node_states[N_HIGH_MEMORY])
+#define cpuset_current_mems_allowed (node_states[N_MEMORY])
 static inline void cpuset_init_current_mems_allowed(void) {}
 
 static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b017887d632f..7bb63eea6eb8 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -302,10 +302,10 @@ static void guarantee_online_cpus(const struct cpuset *cs,
  * are online, with memory.  If none are online with memory, walk
  * up the cpuset hierarchy until we find one that does have some
  * online mems.  If we get all the way to the top and still haven't
- * found any online mems, return node_states[N_HIGH_MEMORY].
+ * found any online mems, return node_states[N_MEMORY].
  *
  * One way or another, we guarantee to return some non-empty subset
- * of node_states[N_HIGH_MEMORY].
+ * of node_states[N_MEMORY].
  *
  * Call with callback_mutex held.
  */
@@ -313,14 +313,14 @@ static void guarantee_online_cpus(const struct cpuset *cs,
 static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
 {
 	while (cs && !nodes_intersects(cs->mems_allowed,
-					node_states[N_HIGH_MEMORY]))
+					node_states[N_MEMORY]))
 		cs = cs->parent;
 	if (cs)
 		nodes_and(*pmask, cs->mems_allowed,
-					node_states[N_HIGH_MEMORY]);
+					node_states[N_MEMORY]);
 	else
-		*pmask = node_states[N_HIGH_MEMORY];
-	BUG_ON(!nodes_intersects(*pmask, node_states[N_HIGH_MEMORY]));
+		*pmask = node_states[N_MEMORY];
+	BUG_ON(!nodes_intersects(*pmask, node_states[N_MEMORY]));
 }
 
 /*
@@ -1100,7 +1100,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 		return -ENOMEM;
 
 	/*
-	 * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
+	 * top_cpuset.mems_allowed tracks node_stats[N_MEMORY];
 	 * it's read-only
 	 */
 	if (cs == &top_cpuset) {
@@ -1122,7 +1122,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 			goto done;
 
 		if (!nodes_subset(trialcs->mems_allowed,
-				node_states[N_HIGH_MEMORY])) {
+				node_states[N_MEMORY])) {
 			retval =  -EINVAL;
 			goto done;
 		}
@@ -2026,7 +2026,7 @@ static struct cpuset *cpuset_next(struct list_head *queue)
  * before dropping down to the next.  It always processes a node before
  * any of its children.
  *
- * In the case of memory hot-unplug, it will remove nodes from N_HIGH_MEMORY
+ * In the case of memory hot-unplug, it will remove nodes from N_MEMORY
  * if all present pages from a node are offlined.
  */
 static void
@@ -2065,7 +2065,7 @@ scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event)
 
 			/* Continue past cpusets with all mems online */
 			if (nodes_subset(cp->mems_allowed,
-					node_states[N_HIGH_MEMORY]))
+					node_states[N_MEMORY]))
 				continue;
 
 			oldmems = cp->mems_allowed;
@@ -2073,7 +2073,7 @@ scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event)
 			/* Remove offline mems from this cpuset. */
 			mutex_lock(&callback_mutex);
 			nodes_and(cp->mems_allowed, cp->mems_allowed,
-						node_states[N_HIGH_MEMORY]);
+						node_states[N_MEMORY]);
 			mutex_unlock(&callback_mutex);
 
 			/* Move tasks from the empty cpuset to a parent */
@@ -2126,8 +2126,8 @@ void cpuset_update_active_cpus(bool cpu_online)
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
- * Keep top_cpuset.mems_allowed tracking node_states[N_HIGH_MEMORY].
- * Call this routine anytime after node_states[N_HIGH_MEMORY] changes.
+ * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY].
+ * Call this routine anytime after node_states[N_MEMORY] changes.
  * See cpuset_update_active_cpus() for CPU hotplug handling.
  */
 static int cpuset_track_online_nodes(struct notifier_block *self,
@@ -2140,7 +2140,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 	case MEM_ONLINE:
 		oldmems = top_cpuset.mems_allowed;
 		mutex_lock(&callback_mutex);
-		top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+		top_cpuset.mems_allowed = node_states[N_MEMORY];
 		mutex_unlock(&callback_mutex);
 		update_tasks_nodemask(&top_cpuset, &oldmems, NULL);
 		break;
@@ -2169,7 +2169,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 void __init cpuset_init_smp(void)
 {
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
-	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+	top_cpuset.mems_allowed = node_states[N_MEMORY];
 
 	hotplug_memory_notifier(cpuset_track_online_nodes, 10);
 
@@ -2237,7 +2237,7 @@ void cpuset_init_current_mems_allowed(void)
  *
  * Description: Returns the nodemask_t mems_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
- * subset of node_states[N_HIGH_MEMORY], even if this means going outside the
+ * subset of node_states[N_MEMORY], even if this means going outside the
  * tasks cpuset.
  **/
 
-- 
cgit v1.2.3-55-g7522


From 6715ddf94576ff39f5d1cda8d4c568d3b79e82ec Mon Sep 17 00:00:00 2001
From: Lai Jiangshan
Date: Wed, 12 Dec 2012 13:51:49 -0800
Subject: hotplug: update nodemasks management

Update nodemasks management for N_MEMORY.

[lliubbo@gmail.com: fix build]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Lin Feng <linfeng@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Bob Liu <lliubbo@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/memory-hotplug.txt |  5 ++-
 include/linux/memory.h           |  1 +
 mm/memory_hotplug.c              | 87 +++++++++++++++++++++++++++++++++-------
 3 files changed, 77 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index c6f993d491b5..8e5eacbdcfa3 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -390,6 +390,7 @@ struct memory_notify {
        unsigned long start_pfn;
        unsigned long nr_pages;
        int status_change_nid_normal;
+       int status_change_nid_high;
        int status_change_nid;
 }
 
@@ -397,7 +398,9 @@ start_pfn is start_pfn of online/offline memory.
 nr_pages is # of pages of online/offline memory.
 status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask
 is (will be) set/clear, if this is -1, then nodemask status is not changed.
-status_change_nid is set node id when N_HIGH_MEMORY of nodemask is (will be)
+status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask
+is (will be) set/clear, if this is -1, then nodemask status is not changed.
+status_change_nid is set node id when N_MEMORY of nodemask is (will be)
 set/clear. It means a new(memoryless) node gets new memory by online and a
 node loses all memory. If this is -1, then nodemask status is not changed.
 If status_changed_nid* >= 0, callback should create/discard structures for the
diff --git a/include/linux/memory.h b/include/linux/memory.h
index a09216d0dcc7..45e93b468878 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -54,6 +54,7 @@ struct memory_notify {
 	unsigned long start_pfn;
 	unsigned long nr_pages;
 	int status_change_nid_normal;
+	int status_change_nid_high;
 	int status_change_nid;
 };
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index de9cb14ae753..eca4aac1a83b 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -595,13 +595,15 @@ static void node_states_check_changes_online(unsigned long nr_pages,
 	enum zone_type zone_last = ZONE_NORMAL;
 
 	/*
-	 * If we have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
-	 * which have 0...ZONE_NORMAL, set zone_last to ZONE_NORMAL.
+	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_NORMAL,
+	 * set zone_last to ZONE_NORMAL.
 	 *
-	 * If we don't have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
-	 * which have 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
+	 * If we don't have HIGHMEM nor movable node,
+	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
+	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
 	 */
-	if (N_HIGH_MEMORY == N_NORMAL_MEMORY)
+	if (N_MEMORY == N_NORMAL_MEMORY)
 		zone_last = ZONE_MOVABLE;
 
 	/*
@@ -615,12 +617,34 @@ static void node_states_check_changes_online(unsigned long nr_pages,
 	else
 		arg->status_change_nid_normal = -1;
 
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * If we have movable node, node_states[N_HIGH_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
+	 * set zone_last to ZONE_HIGHMEM.
+	 *
+	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_MOVABLE,
+	 * set zone_last to ZONE_MOVABLE.
+	 */
+	zone_last = ZONE_HIGHMEM;
+	if (N_MEMORY == N_HIGH_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	if (zone_idx(zone) <= zone_last && !node_state(nid, N_HIGH_MEMORY))
+		arg->status_change_nid_high = nid;
+	else
+		arg->status_change_nid_high = -1;
+#else
+	arg->status_change_nid_high = arg->status_change_nid_normal;
+#endif
+
 	/*
 	 * if the node don't have memory befor online, we will need to
-	 * set the node to node_states[N_HIGH_MEMORY] after the memory
+	 * set the node to node_states[N_MEMORY] after the memory
 	 * is online.
 	 */
-	if (!node_state(nid, N_HIGH_MEMORY))
+	if (!node_state(nid, N_MEMORY))
 		arg->status_change_nid = nid;
 	else
 		arg->status_change_nid = -1;
@@ -631,7 +655,10 @@ static void node_states_set_node(int node, struct memory_notify *arg)
 	if (arg->status_change_nid_normal >= 0)
 		node_set_state(node, N_NORMAL_MEMORY);
 
-	node_set_state(node, N_HIGH_MEMORY);
+	if (arg->status_change_nid_high >= 0)
+		node_set_state(node, N_HIGH_MEMORY);
+
+	node_set_state(node, N_MEMORY);
 }
 
 
@@ -1099,13 +1126,15 @@ static void node_states_check_changes_offline(unsigned long nr_pages,
 	enum zone_type zt, zone_last = ZONE_NORMAL;
 
 	/*
-	 * If we have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
-	 * which have 0...ZONE_NORMAL, set zone_last to ZONE_NORMAL.
+	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_NORMAL,
+	 * set zone_last to ZONE_NORMAL.
 	 *
-	 * If we don't have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
-	 * which have 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
+	 * If we don't have HIGHMEM nor movable node,
+	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
+	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
 	 */
-	if (N_HIGH_MEMORY == N_NORMAL_MEMORY)
+	if (N_MEMORY == N_NORMAL_MEMORY)
 		zone_last = ZONE_MOVABLE;
 
 	/*
@@ -1122,6 +1151,30 @@ static void node_states_check_changes_offline(unsigned long nr_pages,
 	else
 		arg->status_change_nid_normal = -1;
 
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * If we have movable node, node_states[N_HIGH_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
+	 * set zone_last to ZONE_HIGHMEM.
+	 *
+	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
+	 * contains nodes which have zones of 0...ZONE_MOVABLE,
+	 * set zone_last to ZONE_MOVABLE.
+	 */
+	zone_last = ZONE_HIGHMEM;
+	if (N_MEMORY == N_HIGH_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	for (; zt <= zone_last; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
+		arg->status_change_nid_high = zone_to_nid(zone);
+	else
+		arg->status_change_nid_high = -1;
+#else
+	arg->status_change_nid_high = arg->status_change_nid_normal;
+#endif
+
 	/*
 	 * node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE
 	 */
@@ -1146,9 +1199,13 @@ static void node_states_clear_node(int node, struct memory_notify *arg)
 	if (arg->status_change_nid_normal >= 0)
 		node_clear_state(node, N_NORMAL_MEMORY);
 
-	if ((N_HIGH_MEMORY != N_NORMAL_MEMORY) &&
-	    (arg->status_change_nid >= 0))
+	if ((N_MEMORY != N_NORMAL_MEMORY) &&
+	    (arg->status_change_nid_high >= 0))
 		node_clear_state(node, N_HIGH_MEMORY);
+
+	if ((N_MEMORY != N_HIGH_MEMORY) &&
+	    (arg->status_change_nid >= 0))
+		node_clear_state(node, N_MEMORY);
 }
 
 static int __ref __offline_pages(unsigned long start_pfn,
-- 
cgit v1.2.3-55-g7522


From 44e33e8f95171b93968c3ac3cf8516998b1db65d Mon Sep 17 00:00:00 2001
From: Greg Thelen
Date: Wed, 12 Dec 2012 13:51:52 -0800
Subject: res_counter: delete res_counter_write()

Since commit 628f42355389 ("memcg: limit change shrink usage") both
res_counter_write() and write_strategy_fn have been unused.  This patch
deletes them both.

Signed-off-by: Greg Thelen <gthelen@google.com>
Cc: Glauber Costa <glommer@parallels.com>
Cc: Tejun Heo <tj@kernel.org>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/res_counter.h |  5 -----
 kernel/res_counter.c        | 22 ----------------------
 2 files changed, 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 7d7fbe2ef782..6f54e40fa218 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -74,14 +74,9 @@ ssize_t res_counter_read(struct res_counter *counter, int member,
 		const char __user *buf, size_t nbytes, loff_t *pos,
 		int (*read_strategy)(unsigned long long val, char *s));
 
-typedef int (*write_strategy_fn)(const char *buf, unsigned long long *val);
-
 int res_counter_memparse_write_strategy(const char *buf,
 					unsigned long long *res);
 
-int res_counter_write(struct res_counter *counter, int member,
-		      const char *buffer, write_strategy_fn write_strategy);
-
 /*
  * the field descriptors. one for each member of res_counter
  */
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index ad581aa2369a..3920d593e63c 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -192,25 +192,3 @@ int res_counter_memparse_write_strategy(const char *buf,
 	*res = PAGE_ALIGN(*res);
 	return 0;
 }
-
-int res_counter_write(struct res_counter *counter, int member,
-		      const char *buf, write_strategy_fn write_strategy)
-{
-	char *end;
-	unsigned long flags;
-	unsigned long long tmp, *val;
-
-	if (write_strategy) {
-		if (write_strategy(buf, &tmp))
-			return -EINVAL;
-	} else {
-		tmp = simple_strtoull(buf, &end, 10);
-		if (*end != '\0')
-			return -EINVAL;
-	}
-	spin_lock_irqsave(&counter->lock, flags);
-	val = res_counter_member(counter, member);
-	*val = tmp;
-	spin_unlock_irqrestore(&counter->lock, flags);
-	return 0;
-}
-- 
cgit v1.2.3-55-g7522


From 05b0afd73d04109d87f00ccd39f099e217c37263 Mon Sep 17 00:00:00 2001
From: Andrew Morton
Date: Wed, 12 Dec 2012 13:51:56 -0800
Subject: mm: add a reminder comment for __GFP_BITS_SHIFT

Cc: Glauber Costa <glommer@parallels.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 31e8041274f6..f74856e17e48 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -34,6 +34,7 @@ struct vm_area_struct;
 #define ___GFP_NO_KSWAPD	0x400000u
 #define ___GFP_OTHER_NODE	0x800000u
 #define ___GFP_WRITE		0x1000000u
+/* If the above are modified, __GFP_BITS_SHIFT may need updating */
 
 /*
  * GFP bitmasks..
-- 
cgit v1.2.3-55-g7522


From 68ae564bbac8eb9ed54ddd2529b0e29ee190b355 Mon Sep 17 00:00:00 2001
From: David Rientjes
Date: Wed, 12 Dec 2012 13:51:57 -0800
Subject: mm, memcg: avoid unnecessary function call when memcg is disabled

While profiling numa/core v16 with cgroup_disable=memory on the command
line, I noticed mem_cgroup_count_vm_event() still showed up as high as
0.60% in perftop.

This occurs because the function is called extremely often even when memcg
is disabled.

To fix this, inline the check for mem_cgroup_disabled() so we avoid the
unnecessary function call if memcg is disabled.

Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Glauber Costa <glommer@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 9 ++++++++-
 mm/memcontrol.c            | 6 ++++--
 2 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 11ddc7ffeba8..e98a74c0c9c0 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -181,7 +181,14 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
-void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
+void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
+static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
+					     enum vm_event_item idx)
+{
+	if (mem_cgroup_disabled())
+		return;
+	__mem_cgroup_count_vm_event(mm, idx);
+}
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 49d86d06e1dd..7f0e3571df7e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -59,6 +59,8 @@
 #include <trace/events/vmscan.h>
 
 struct cgroup_subsys mem_cgroup_subsys __read_mostly;
+EXPORT_SYMBOL(mem_cgroup_subsys);
+
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 static struct mem_cgroup *root_mem_cgroup __read_mostly;
 
@@ -1015,7 +1017,7 @@ void mem_cgroup_iter_break(struct mem_cgroup *root,
 	     iter != NULL;				\
 	     iter = mem_cgroup_iter(NULL, iter, NULL))
 
-void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
+void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 {
 	struct mem_cgroup *memcg;
 
@@ -1040,7 +1042,7 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 out:
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(mem_cgroup_count_vm_event);
+EXPORT_SYMBOL(__mem_cgroup_count_vm_event);
 
 /**
  * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
-- 
cgit v1.2.3-55-g7522


From 20b2f52b73febce476fc9376f0296c1aa0e4f5a7 Mon Sep 17 00:00:00 2001
From: Lai Jiangshan
Date: Wed, 12 Dec 2012 13:52:00 -0800
Subject: numa: add CONFIG_MOVABLE_NODE for movable-dedicated node

We need a node which only contains movable memory.  This feature is very
important for node hotplug.  If a node has normal/highmem, the memory may
be used by the kernel and can't be offlined.  If the node only contains
movable memory, we can offline the memory and the node.

All are prepared, we can actually introduce N_MEMORY.
add CONFIG_MOVABLE_NODE make we can use it for movable-dedicated node

[akpm@linux-foundation.org: fix Kconfig text]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Tested-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/node.c      | 6 ++++++
 include/linux/nodemask.h | 4 ++++
 mm/Kconfig               | 8 ++++++++
 mm/page_alloc.c          | 3 +++
 4 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 49dbe7dc9ada..fac124a7e1c5 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -643,6 +643,9 @@ static struct node_attr node_state_attr[] = {
 	[N_NORMAL_MEMORY] = _NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY),
 #ifdef CONFIG_HIGHMEM
 	[N_HIGH_MEMORY] = _NODE_ATTR(has_high_memory, N_HIGH_MEMORY),
+#endif
+#ifdef CONFIG_MOVABLE_NODE
+	[N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY),
 #endif
 	[N_CPU] = _NODE_ATTR(has_cpu, N_CPU),
 };
@@ -653,6 +656,9 @@ static struct attribute *node_state_attrs[] = {
 	&node_state_attr[N_NORMAL_MEMORY].attr.attr,
 #ifdef CONFIG_HIGHMEM
 	&node_state_attr[N_HIGH_MEMORY].attr.attr,
+#endif
+#ifdef CONFIG_MOVABLE_NODE
+	&node_state_attr[N_MEMORY].attr.attr,
 #endif
 	&node_state_attr[N_CPU].attr.attr,
 	NULL
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index c6ebdc97a428..4e2cbfa640b7 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -380,7 +380,11 @@ enum node_states {
 #else
 	N_HIGH_MEMORY = N_NORMAL_MEMORY,
 #endif
+#ifdef CONFIG_MOVABLE_NODE
+	N_MEMORY,		/* The node has memory(regular, high, movable) */
+#else
 	N_MEMORY = N_HIGH_MEMORY,
+#endif
 	N_CPU,		/* The node has one or more cpus */
 	NR_NODE_STATES
 };
diff --git a/mm/Kconfig b/mm/Kconfig
index e6651c5de14f..1680a0123a13 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -143,6 +143,14 @@ config NO_BOOTMEM
 config MEMORY_ISOLATION
 	boolean
 
+config MOVABLE_NODE
+	boolean "Enable to assign a node which has only movable memory"
+	depends on HAVE_MEMBLOCK
+	depends on NO_BOOTMEM
+	depends on X86_64
+	depends on NUMA
+	default y
+
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 35727168896b..2bf0d43d646b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -89,6 +89,9 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
 	[N_NORMAL_MEMORY] = { { [0] = 1UL } },
 #ifdef CONFIG_HIGHMEM
 	[N_HIGH_MEMORY] = { { [0] = 1UL } },
+#endif
+#ifdef CONFIG_MOVABLE_NODE
+	[N_MEMORY] = { { [0] = 1UL } },
 #endif
 	[N_CPU] = { { [0] = 1UL } },
 #endif	/* NUMA */
-- 
cgit v1.2.3-55-g7522


From 9feedc9d831e18ae6d0d15aa562e5e46ba53647b Mon Sep 17 00:00:00 2001
From: Jiang Liu
Date: Wed, 12 Dec 2012 13:52:12 -0800
Subject: mm: introduce new field "managed_pages" to struct zone

Currently a zone's present_pages is calcuated as below, which is
inaccurate and may cause trouble to memory hotplug.

	spanned_pages - absent_pages - memmap_pages - dma_reserve.

During fixing bugs caused by inaccurate zone->present_pages, we found
zone->present_pages has been abused.  The field zone->present_pages may
have different meanings in different contexts:

1) pages existing in a zone.
2) pages managed by the buddy system.

For more discussions about the issue, please refer to:
  http://lkml.org/lkml/2012/11/5/866
  https://patchwork.kernel.org/patch/1346751/

This patchset tries to introduce a new field named "managed_pages" to
struct zone, which counts "pages managed by the buddy system".  And revert
zone->present_pages to count "physical pages existing in a zone", which
also keep in consistence with pgdat->node_present_pages.

We will set an initial value for zone->managed_pages in function
free_area_init_core() and will adjust it later if the initial value is
inaccurate.

For DMA/normal zones, the initial value is set to:

	(spanned_pages - absent_pages - memmap_pages - dma_reserve)

Later zone->managed_pages will be adjusted to the accurate value when the
bootmem allocator frees all free pages to the buddy system in function
free_all_bootmem_node() and free_all_bootmem().

The bootmem allocator doesn't touch highmem pages, so highmem zones'
managed_pages is set to the accurate value "spanned_pages - absent_pages"
in function free_area_init_core() and won't be updated anymore.

This patch also adds a new field "managed_pages" to /proc/zoneinfo
and sysrq showmem.

[akpm@linux-foundation.org: small comment tweaks]
Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Maciej Rutecki <maciej.rutecki@gmail.com>
Tested-by: Chris Clayton <chris2553@googlemail.com>
Cc: "Rafael J . Wysocki" <rjw@sisk.pl>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 41 ++++++++++++++++++++++++++++++++++-------
 mm/bootmem.c           | 21 +++++++++++++++++++++
 mm/memory_hotplug.c    | 10 ++++++++++
 mm/nobootmem.c         | 22 ++++++++++++++++++++++
 mm/page_alloc.c        | 44 ++++++++++++++++++++++++++++++--------------
 mm/vmstat.c            |  6 ++++--
 6 files changed, 121 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 0c0b1d608a69..cd55dad56aac 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -460,17 +460,44 @@ struct zone {
 	unsigned long		zone_start_pfn;
 
 	/*
-	 * zone_start_pfn, spanned_pages and present_pages are all
-	 * protected by span_seqlock.  It is a seqlock because it has
-	 * to be read outside of zone->lock, and it is done in the main
-	 * allocator path.  But, it is written quite infrequently.
+	 * spanned_pages is the total pages spanned by the zone, including
+	 * holes, which is calculated as:
+	 * 	spanned_pages = zone_end_pfn - zone_start_pfn;
 	 *
-	 * The lock is declared along with zone->lock because it is
+	 * present_pages is physical pages existing within the zone, which
+	 * is calculated as:
+	 *	present_pages = spanned_pages - absent_pages(pags in holes);
+	 *
+	 * managed_pages is present pages managed by the buddy system, which
+	 * is calculated as (reserved_pages includes pages allocated by the
+	 * bootmem allocator):
+	 *	managed_pages = present_pages - reserved_pages;
+	 *
+	 * So present_pages may be used by memory hotplug or memory power
+	 * management logic to figure out unmanaged pages by checking
+	 * (present_pages - managed_pages). And managed_pages should be used
+	 * by page allocator and vm scanner to calculate all kinds of watermarks
+	 * and thresholds.
+	 *
+	 * Locking rules:
+	 *
+	 * zone_start_pfn and spanned_pages are protected by span_seqlock.
+	 * It is a seqlock because it has to be read outside of zone->lock,
+	 * and it is done in the main allocator path.  But, it is written
+	 * quite infrequently.
+	 *
+	 * The span_seq lock is declared along with zone->lock because it is
 	 * frequently read in proximity to zone->lock.  It's good to
 	 * give them a chance of being in the same cacheline.
+	 *
+	 * Write access to present_pages and managed_pages at runtime should
+	 * be protected by lock_memory_hotplug()/unlock_memory_hotplug().
+	 * Any reader who can't tolerant drift of present_pages and
+	 * managed_pages should hold memory hotplug lock to get a stable value.
 	 */
-	unsigned long		spanned_pages;	/* total size, including holes */
-	unsigned long		present_pages;	/* amount of memory (excluding holes) */
+	unsigned long		spanned_pages;
+	unsigned long		present_pages;
+	unsigned long		managed_pages;
 
 	/*
 	 * rarely used fields:
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 26d057a8b552..19262ac05dd2 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -229,6 +229,22 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 	return count;
 }
 
+static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
+{
+	struct zone *z;
+
+	/*
+	 * In free_area_init_core(), highmem zone's managed_pages is set to
+	 * present_pages, and bootmem allocator doesn't allocate from highmem
+	 * zones. So there's no need to recalculate managed_pages because all
+	 * highmem pages will be managed by the buddy system. Here highmem
+	 * zone also includes highmem movable zone.
+	 */
+	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
+		if (!is_highmem(z))
+			z->managed_pages = 0;
+}
+
 /**
  * free_all_bootmem_node - release a node's free pages to the buddy allocator
  * @pgdat: node to be released
@@ -238,6 +254,7 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
 {
 	register_page_bootmem_info_node(pgdat);
+	reset_node_lowmem_managed_pages(pgdat);
 	return free_all_bootmem_core(pgdat->bdata);
 }
 
@@ -250,6 +267,10 @@ unsigned long __init free_all_bootmem(void)
 {
 	unsigned long total_pages = 0;
 	bootmem_data_t *bdata;
+	struct pglist_data *pgdat;
+
+	for_each_online_pgdat(pgdat)
+		reset_node_lowmem_managed_pages(pgdat);
 
 	list_for_each_entry(bdata, &bdata_list, list)
 		total_pages += free_all_bootmem_core(bdata);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c6cd8b515424..b7c93ca896d6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -106,6 +106,7 @@ static void get_page_bootmem(unsigned long info,  struct page *page,
 void __ref put_page_bootmem(struct page *page)
 {
 	unsigned long type;
+	static DEFINE_MUTEX(ppb_lock);
 
 	type = (unsigned long) page->lru.next;
 	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
@@ -115,7 +116,14 @@ void __ref put_page_bootmem(struct page *page)
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
 		INIT_LIST_HEAD(&page->lru);
+
+		/*
+		 * Please refer to comment for __free_pages_bootmem()
+		 * for why we serialize here.
+		 */
+		mutex_lock(&ppb_lock);
 		__free_pages_bootmem(page, 0);
+		mutex_unlock(&ppb_lock);
 	}
 
 }
@@ -748,6 +756,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 		return ret;
 	}
 
+	zone->managed_pages += onlined_pages;
 	zone->present_pages += onlined_pages;
 	zone->zone_pgdat->node_present_pages += onlined_pages;
 	if (onlined_pages) {
@@ -1321,6 +1330,7 @@ repeat:
 	/* reset pagetype flags and makes migrate type to be MOVABLE */
 	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
 	/* removal success */
+	zone->managed_pages -= offlined_pages;
 	zone->present_pages -= offlined_pages;
 	zone->zone_pgdat->node_present_pages -= offlined_pages;
 	totalram_pages -= offlined_pages;
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index bd82f6b31411..b8294fc03df8 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -137,6 +137,22 @@ unsigned long __init free_low_memory_core_early(int nodeid)
 	return count;
 }
 
+static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
+{
+	struct zone *z;
+
+	/*
+	 * In free_area_init_core(), highmem zone's managed_pages is set to
+	 * present_pages, and bootmem allocator doesn't allocate from highmem
+	 * zones. So there's no need to recalculate managed_pages because all
+	 * highmem pages will be managed by the buddy system. Here highmem
+	 * zone also includes highmem movable zone.
+	 */
+	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
+		if (!is_highmem(z))
+			z->managed_pages = 0;
+}
+
 /**
  * free_all_bootmem_node - release a node's free pages to the buddy allocator
  * @pgdat: node to be released
@@ -146,6 +162,7 @@ unsigned long __init free_low_memory_core_early(int nodeid)
 unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
 {
 	register_page_bootmem_info_node(pgdat);
+	reset_node_lowmem_managed_pages(pgdat);
 
 	/* free_low_memory_core_early(MAX_NUMNODES) will be called later */
 	return 0;
@@ -158,6 +175,11 @@ unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
  */
 unsigned long __init free_all_bootmem(void)
 {
+	struct pglist_data *pgdat;
+
+	for_each_online_pgdat(pgdat)
+		reset_node_lowmem_managed_pages(pgdat);
+
 	/*
 	 * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id
 	 *  because in some case like Node0 doesn't have RAM installed
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2bf0d43d646b..0b6a6d04300a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -735,6 +735,13 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	local_irq_restore(flags);
 }
 
+/*
+ * Read access to zone->managed_pages is safe because it's unsigned long,
+ * but we still need to serialize writers. Currently all callers of
+ * __free_pages_bootmem() except put_page_bootmem() should only be used
+ * at boot time. So for shorter boot time, we shift the burden to
+ * put_page_bootmem() to serialize writers.
+ */
 void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
 {
 	unsigned int nr_pages = 1 << order;
@@ -750,6 +757,7 @@ void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
 		set_page_count(p, 0);
 	}
 
+	page_zone(page)->managed_pages += 1 << order;
 	set_page_refcounted(page);
 	__free_pages(page, order);
 }
@@ -2984,6 +2992,7 @@ void show_free_areas(unsigned int filter)
 			" isolated(anon):%lukB"
 			" isolated(file):%lukB"
 			" present:%lukB"
+			" managed:%lukB"
 			" mlocked:%lukB"
 			" dirty:%lukB"
 			" writeback:%lukB"
@@ -3013,6 +3022,7 @@ void show_free_areas(unsigned int filter)
 			K(zone_page_state(zone, NR_ISOLATED_ANON)),
 			K(zone_page_state(zone, NR_ISOLATED_FILE)),
 			K(zone->present_pages),
+			K(zone->managed_pages),
 			K(zone_page_state(zone, NR_MLOCK)),
 			K(zone_page_state(zone, NR_FILE_DIRTY)),
 			K(zone_page_state(zone, NR_WRITEBACK)),
@@ -4502,48 +4512,54 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
-		unsigned long size, realsize, memmap_pages;
+		unsigned long size, realsize, freesize, memmap_pages;
 
 		size = zone_spanned_pages_in_node(nid, j, zones_size);
-		realsize = size - zone_absent_pages_in_node(nid, j,
+		realsize = freesize = size - zone_absent_pages_in_node(nid, j,
 								zholes_size);
 
 		/*
-		 * Adjust realsize so that it accounts for how much memory
+		 * Adjust freesize so that it accounts for how much memory
 		 * is used by this zone for memmap. This affects the watermark
 		 * and per-cpu initialisations
 		 */
 		memmap_pages =
 			PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT;
-		if (realsize >= memmap_pages) {
-			realsize -= memmap_pages;
+		if (freesize >= memmap_pages) {
+			freesize -= memmap_pages;
 			if (memmap_pages)
 				printk(KERN_DEBUG
 				       "  %s zone: %lu pages used for memmap\n",
 				       zone_names[j], memmap_pages);
 		} else
 			printk(KERN_WARNING
-				"  %s zone: %lu pages exceeds realsize %lu\n",
-				zone_names[j], memmap_pages, realsize);
+				"  %s zone: %lu pages exceeds freesize %lu\n",
+				zone_names[j], memmap_pages, freesize);
 
 		/* Account for reserved pages */
-		if (j == 0 && realsize > dma_reserve) {
-			realsize -= dma_reserve;
+		if (j == 0 && freesize > dma_reserve) {
+			freesize -= dma_reserve;
 			printk(KERN_DEBUG "  %s zone: %lu pages reserved\n",
 					zone_names[0], dma_reserve);
 		}
 
 		if (!is_highmem_idx(j))
-			nr_kernel_pages += realsize;
-		nr_all_pages += realsize;
+			nr_kernel_pages += freesize;
+		nr_all_pages += freesize;
 
 		zone->spanned_pages = size;
-		zone->present_pages = realsize;
+		zone->present_pages = freesize;
+		/*
+		 * Set an approximate value for lowmem here, it will be adjusted
+		 * when the bootmem allocator frees pages into the buddy system.
+		 * And all highmem pages will be managed by the buddy system.
+		 */
+		zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
 #ifdef CONFIG_NUMA
 		zone->node = nid;
-		zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio)
+		zone->min_unmapped_pages = (freesize*sysctl_min_unmapped_ratio)
 						/ 100;
-		zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100;
+		zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100;
 #endif
 		zone->name = zone_names[j];
 		spin_lock_init(&zone->lock);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 9a4a522c0b0f..df14808f0a36 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -994,14 +994,16 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n        high     %lu"
 		   "\n        scanned  %lu"
 		   "\n        spanned  %lu"
-		   "\n        present  %lu",
+		   "\n        present  %lu"
+		   "\n        managed  %lu",
 		   zone_page_state(zone, NR_FREE_PAGES),
 		   min_wmark_pages(zone),
 		   low_wmark_pages(zone),
 		   high_wmark_pages(zone),
 		   zone->pages_scanned,
 		   zone->spanned_pages,
-		   zone->present_pages);
+		   zone->present_pages,
+		   zone->managed_pages);
 
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
 		seq_printf(m, "\n    %-12s %lu", vmstat_text[i],
-- 
cgit v1.2.3-55-g7522


From 816422ad76474fed8052b6f7b905a054d082e59a Mon Sep 17 00:00:00 2001
From: Kirill A. Shutemov
Date: Wed, 12 Dec 2012 13:52:36 -0800
Subject: asm-generic, mm: pgtable: consolidate zero page helpers

We have two different implementation of is_zero_pfn() and my_zero_pfn()
helpers: for architectures with and without zero page coloring.

Let's consolidate them in <asm-generic/pgtable.h>.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/mips/include/asm/pgtable.h | 11 +----------
 arch/s390/include/asm/pgtable.h | 11 +----------
 include/asm-generic/pgtable.h   | 26 ++++++++++++++++++++++++++
 include/linux/mm.h              |  8 --------
 mm/memory.c                     |  7 -------
 5 files changed, 28 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index c02158be836c..14490e9443af 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -76,16 +76,7 @@ extern unsigned long zero_page_mask;
 
 #define ZERO_PAGE(vaddr) \
 	(virt_to_page((void *)(empty_zero_page + (((unsigned long)(vaddr)) & zero_page_mask))))
-
-#define is_zero_pfn is_zero_pfn
-static inline int is_zero_pfn(unsigned long pfn)
-{
-	extern unsigned long zero_pfn;
-	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
-	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
-}
-
-#define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
+#define __HAVE_COLOR_ZERO_PAGE
 
 extern void paging_init(void);
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 2d3b7cb26005..c814e6f5b57d 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -55,16 +55,7 @@ extern unsigned long zero_page_mask;
 #define ZERO_PAGE(vaddr) \
 	(virt_to_page((void *)(empty_zero_page + \
 	 (((unsigned long)(vaddr)) &zero_page_mask))))
-
-#define is_zero_pfn is_zero_pfn
-static inline int is_zero_pfn(unsigned long pfn)
-{
-	extern unsigned long zero_pfn;
-	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
-	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
-}
-
-#define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
+#define __HAVE_COLOR_ZERO_PAGE
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index b36ce40bd1c6..284e80831d2c 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -449,6 +449,32 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size);
 #endif
 
+#ifdef __HAVE_COLOR_ZERO_PAGE
+static inline int is_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long zero_pfn;
+	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
+	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
+}
+
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+	return page_to_pfn(ZERO_PAGE(addr));
+}
+#else
+static inline int is_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long zero_pfn;
+	return pfn == zero_pfn;
+}
+
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+	extern unsigned long zero_pfn;
+	return zero_pfn;
+}
+#endif
+
 #ifdef CONFIG_MMU
 
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4b80bad4a367..4af4f0b1be4c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -516,14 +516,6 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 }
 #endif
 
-#ifndef my_zero_pfn
-static inline unsigned long my_zero_pfn(unsigned long addr)
-{
-	extern unsigned long zero_pfn;
-	return zero_pfn;
-}
-#endif
-
 /*
  * Multiple processes may "see" the same page. E.g. for untouched
  * mappings of /dev/null, all processes see the same page full of
diff --git a/mm/memory.c b/mm/memory.c
index f9a4b0cb8623..3f680e7c7645 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -717,13 +717,6 @@ static inline bool is_cow_mapping(vm_flags_t flags)
 	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 }
 
-#ifndef is_zero_pfn
-static inline int is_zero_pfn(unsigned long pfn)
-{
-	return pfn == zero_pfn;
-}
-#endif
-
 /*
  * vm_normal_page -- This function gets the "struct page" associated with a pte.
  *
-- 
cgit v1.2.3-55-g7522


From 98870901cce098bbe94d90d2c41d8d1fa8d94392 Mon Sep 17 00:00:00 2001
From: Lin Feng
Date: Wed, 12 Dec 2012 13:52:39 -0800
Subject: mm/bootmem.c: remove unused wrapper function
 reserve_bootmem_generic()

reserve_bootmem_generic() has no caller,

Signed-off-by: Lin Feng <linfeng@cn.fujitsu.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bootmem.h | 3 ---
 mm/bootmem.c            | 6 ------
 2 files changed, 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 7b74452c5317..3f778c27f825 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -137,9 +137,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
 #define alloc_bootmem_low_pages_node(pgdat, x) \
 	__alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0)
 
-extern int reserve_bootmem_generic(unsigned long addr, unsigned long size,
-				   int flags);
-
 #ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP
 extern void *alloc_remap(int nid, unsigned long size);
 #else
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 19262ac05dd2..1324cd74faec 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -460,12 +460,6 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size,
 	return mark_bootmem(start, end, 1, flags);
 }
 
-int __weak __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
-				   int flags)
-{
-	return reserve_bootmem(phys, len, flags);
-}
-
 static unsigned long __init align_idx(struct bootmem_data *bdata,
 				      unsigned long idx, unsigned long step)
 {
-- 
cgit v1.2.3-55-g7522


From 7056741fd9fc14a65608549a4657cf5178f05f63 Mon Sep 17 00:00:00 2001
From: Jim Kukunas
Date: Thu, 8 Nov 2012 13:47:44 -0800
Subject: lib/raid6: Add AVX2 optimized recovery functions

Optimize RAID6 recovery functions to take advantage of
the 256-bit YMM integer instructions introduced in AVX2.

The patch was tested and benchmarked before submission.
However hardware is not yet released so benchmark numbers
cannot be reported.

Acked-by: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Jim Kukunas <james.t.kukunas@linux.intel.com>
Signed-off-by: NeilBrown <neilb@suse.de>
---
 arch/x86/Makefile       |   5 +-
 include/linux/raid/pq.h |   1 +
 lib/raid6/Makefile      |   2 +-
 lib/raid6/algos.c       |   3 +
 lib/raid6/recov_avx2.c  | 327 ++++++++++++++++++++++++++++++++++++++++++++++++
 lib/raid6/test/Makefile |   2 +-
 lib/raid6/x86.h         |  14 ++-
 7 files changed, 345 insertions(+), 9 deletions(-)
 create mode 100644 lib/raid6/recov_avx2.c

(limited to 'include')

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 58790bd85c1d..95477aae9ff7 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -123,9 +123,10 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI
 # does binutils support specific instructions?
 asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
+avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
 
-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr)
-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr)
+KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
 
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index 640c69ceec96..3156347452b9 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -109,6 +109,7 @@ struct raid6_recov_calls {
 
 extern const struct raid6_recov_calls raid6_recov_intx1;
 extern const struct raid6_recov_calls raid6_recov_ssse3;
+extern const struct raid6_recov_calls raid6_recov_avx2;
 
 /* Algorithm list */
 extern const struct raid6_calls * const raid6_algos[];
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index de06dfe165b8..8c2e22bef661 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -1,6 +1,6 @@
 obj-$(CONFIG_RAID6_PQ)	+= raid6_pq.o
 
-raid6_pq-y	+= algos.o recov.o recov_ssse3.o tables.o int1.o int2.o int4.o \
+raid6_pq-y	+= algos.o recov.o recov_ssse3.o recov_avx2.o tables.o int1.o int2.o int4.o \
 		   int8.o int16.o int32.o altivec1.o altivec2.o altivec4.o \
 		   altivec8.o mmx.o sse1.o sse2.o
 hostprogs-y	+= mktables
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 589f5f50ad2e..8b7f55cadb45 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -72,6 +72,9 @@ EXPORT_SYMBOL_GPL(raid6_datap_recov);
 
 const struct raid6_recov_calls *const raid6_recov_algos[] = {
 #if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__)
+#ifdef CONFIG_AS_AVX2
+	&raid6_recov_avx2,
+#endif
 	&raid6_recov_ssse3,
 #endif
 	&raid6_recov_intx1,
diff --git a/lib/raid6/recov_avx2.c b/lib/raid6/recov_avx2.c
new file mode 100644
index 000000000000..43a9bab91879
--- /dev/null
+++ b/lib/raid6/recov_avx2.c
@@ -0,0 +1,327 @@
+/*
+ * Copyright (C) 2012 Intel Corporation
+ * Author: Jim Kukunas <james.t.kukunas@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__)
+
+#if CONFIG_AS_AVX2
+
+#include <linux/raid/pq.h>
+#include "x86.h"
+
+static int raid6_has_avx2(void)
+{
+	return boot_cpu_has(X86_FEATURE_AVX2) &&
+		boot_cpu_has(X86_FEATURE_AVX);
+}
+
+static void raid6_2data_recov_avx2(int disks, size_t bytes, int faila,
+		int failb, void **ptrs)
+{
+	u8 *p, *q, *dp, *dq;
+	const u8 *pbmul;	/* P multiplier table for B data */
+	const u8 *qmul;		/* Q multiplier table (for both) */
+	const u8 x0f = 0x0f;
+
+	p = (u8 *)ptrs[disks-2];
+	q = (u8 *)ptrs[disks-1];
+
+	/* Compute syndrome with zero for the missing data pages
+	   Use the dead data pages as temporary storage for
+	   delta p and delta q */
+	dp = (u8 *)ptrs[faila];
+	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[disks-2] = dp;
+	dq = (u8 *)ptrs[failb];
+	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[disks-1] = dq;
+
+	raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila]   = dp;
+	ptrs[failb]   = dq;
+	ptrs[disks-2] = p;
+	ptrs[disks-1] = q;
+
+	/* Now, pick the proper data tables */
+	pbmul = raid6_vgfmul[raid6_gfexi[failb-faila]];
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
+		raid6_gfexp[failb]]];
+
+	kernel_fpu_begin();
+
+	/* ymm0 = x0f[16] */
+	asm volatile("vpbroadcastb %0, %%ymm7" : : "m" (x0f));
+
+	while (bytes) {
+#ifdef CONFIG_X86_64
+		asm volatile("vmovdqa %0, %%ymm1" : : "m" (q[0]));
+		asm volatile("vmovdqa %0, %%ymm9" : : "m" (q[32]));
+		asm volatile("vmovdqa %0, %%ymm0" : : "m" (p[0]));
+		asm volatile("vmovdqa %0, %%ymm8" : : "m" (p[32]));
+		asm volatile("vpxor %0, %%ymm1, %%ymm1" : : "m" (dq[0]));
+		asm volatile("vpxor %0, %%ymm9, %%ymm9" : : "m" (dq[32]));
+		asm volatile("vpxor %0, %%ymm0, %%ymm0" : : "m" (dp[0]));
+		asm volatile("vpxor %0, %%ymm8, %%ymm8" : : "m" (dp[32]));
+
+		/*
+		 * 1 = dq[0]  ^ q[0]
+		 * 9 = dq[32] ^ q[32]
+		 * 0 = dp[0]  ^ p[0]
+		 * 8 = dp[32] ^ p[32]
+		 */
+
+		asm volatile("vbroadcasti128 %0, %%ymm4" : : "m" (qmul[0]));
+		asm volatile("vbroadcasti128 %0, %%ymm5" : : "m" (qmul[16]));
+
+		asm volatile("vpsraw $4, %ymm1, %ymm3");
+		asm volatile("vpsraw $4, %ymm9, %ymm12");
+		asm volatile("vpand %ymm7, %ymm1, %ymm1");
+		asm volatile("vpand %ymm7, %ymm9, %ymm9");
+		asm volatile("vpand %ymm7, %ymm3, %ymm3");
+		asm volatile("vpand %ymm7, %ymm12, %ymm12");
+		asm volatile("vpshufb %ymm9, %ymm4, %ymm14");
+		asm volatile("vpshufb %ymm1, %ymm4, %ymm4");
+		asm volatile("vpshufb %ymm12, %ymm5, %ymm15");
+		asm volatile("vpshufb %ymm3, %ymm5, %ymm5");
+		asm volatile("vpxor %ymm14, %ymm15, %ymm15");
+		asm volatile("vpxor %ymm4, %ymm5, %ymm5");
+
+		/*
+		 * 5 = qx[0]
+		 * 15 = qx[32]
+		 */
+
+		asm volatile("vbroadcasti128 %0, %%ymm4" : : "m" (pbmul[0]));
+		asm volatile("vbroadcasti128 %0, %%ymm1" : : "m" (pbmul[16]));
+		asm volatile("vpsraw $4, %ymm0, %ymm2");
+		asm volatile("vpsraw $4, %ymm8, %ymm6");
+		asm volatile("vpand %ymm7, %ymm0, %ymm3");
+		asm volatile("vpand %ymm7, %ymm8, %ymm14");
+		asm volatile("vpand %ymm7, %ymm2, %ymm2");
+		asm volatile("vpand %ymm7, %ymm6, %ymm6");
+		asm volatile("vpshufb %ymm14, %ymm4, %ymm12");
+		asm volatile("vpshufb %ymm3, %ymm4, %ymm4");
+		asm volatile("vpshufb %ymm6, %ymm1, %ymm13");
+		asm volatile("vpshufb %ymm2, %ymm1, %ymm1");
+		asm volatile("vpxor %ymm4, %ymm1, %ymm1");
+		asm volatile("vpxor %ymm12, %ymm13, %ymm13");
+
+		/*
+		 * 1  = pbmul[px[0]]
+		 * 13 = pbmul[px[32]]
+		 */
+		asm volatile("vpxor %ymm5, %ymm1, %ymm1");
+		asm volatile("vpxor %ymm15, %ymm13, %ymm13");
+
+		/*
+		 * 1 = db = DQ
+		 * 13 = db[32] = DQ[32]
+		 */
+		asm volatile("vmovdqa %%ymm1, %0" : "=m" (dq[0]));
+		asm volatile("vmovdqa %%ymm13,%0" : "=m" (dq[32]));
+		asm volatile("vpxor %ymm1, %ymm0, %ymm0");
+		asm volatile("vpxor %ymm13, %ymm8, %ymm8");
+
+		asm volatile("vmovdqa %%ymm0, %0" : "=m" (dp[0]));
+		asm volatile("vmovdqa %%ymm8, %0" : "=m" (dp[32]));
+
+		bytes -= 64;
+		p += 64;
+		q += 64;
+		dp += 64;
+		dq += 64;
+#else
+		asm volatile("vmovdqa %0, %%ymm1" : : "m" (*q));
+		asm volatile("vmovdqa %0, %%ymm0" : : "m" (*p));
+		asm volatile("vpxor %0, %%ymm1, %%ymm1" : : "m" (*dq));
+		asm volatile("vpxor %0, %%ymm0, %%ymm0" : : "m" (*dp));
+
+		/* 1 = dq ^ q;  0 = dp ^ p */
+
+		asm volatile("vbroadcasti128 %0, %%ymm4" : : "m" (qmul[0]));
+		asm volatile("vbroadcasti128 %0, %%ymm5" : : "m" (qmul[16]));
+
+		/*
+		 * 1 = dq ^ q
+		 * 3 = dq ^ p >> 4
+		 */
+		asm volatile("vpsraw $4, %ymm1, %ymm3");
+		asm volatile("vpand %ymm7, %ymm1, %ymm1");
+		asm volatile("vpand %ymm7, %ymm3, %ymm3");
+		asm volatile("vpshufb %ymm1, %ymm4, %ymm4");
+		asm volatile("vpshufb %ymm3, %ymm5, %ymm5");
+		asm volatile("vpxor %ymm4, %ymm5, %ymm5");
+
+		/* 5 = qx */
+
+		asm volatile("vbroadcasti128 %0, %%ymm4" : : "m" (pbmul[0]));
+		asm volatile("vbroadcasti128 %0, %%ymm1" : : "m" (pbmul[16]));
+
+		asm volatile("vpsraw $4, %ymm0, %ymm2");
+		asm volatile("vpand %ymm7, %ymm0, %ymm3");
+		asm volatile("vpand %ymm7, %ymm2, %ymm2");
+		asm volatile("vpshufb %ymm3, %ymm4, %ymm4");
+		asm volatile("vpshufb %ymm2, %ymm1, %ymm1");
+		asm volatile("vpxor %ymm4, %ymm1, %ymm1");
+
+		/* 1 = pbmul[px] */
+		asm volatile("vpxor %ymm5, %ymm1, %ymm1");
+		/* 1 = db = DQ */
+		asm volatile("vmovdqa %%ymm1, %0" : "=m" (dq[0]));
+
+		asm volatile("vpxor %ymm1, %ymm0, %ymm0");
+		asm volatile("vmovdqa %%ymm0, %0" : "=m" (dp[0]));
+
+		bytes -= 32;
+		p += 32;
+		q += 32;
+		dp += 32;
+		dq += 32;
+#endif
+	}
+
+	kernel_fpu_end();
+}
+
+static void raid6_datap_recov_avx2(int disks, size_t bytes, int faila,
+		void **ptrs)
+{
+	u8 *p, *q, *dq;
+	const u8 *qmul;		/* Q multiplier table */
+	const u8 x0f = 0x0f;
+
+	p = (u8 *)ptrs[disks-2];
+	q = (u8 *)ptrs[disks-1];
+
+	/* Compute syndrome with zero for the missing data page
+	   Use the dead data page as temporary storage for delta q */
+	dq = (u8 *)ptrs[faila];
+	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[disks-1] = dq;
+
+	raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila]   = dq;
+	ptrs[disks-1] = q;
+
+	/* Now, pick the proper data tables */
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
+
+	kernel_fpu_begin();
+
+	asm volatile("vpbroadcastb %0, %%ymm7" : : "m" (x0f));
+
+	while (bytes) {
+#ifdef CONFIG_X86_64
+		asm volatile("vmovdqa %0, %%ymm3" : : "m" (dq[0]));
+		asm volatile("vmovdqa %0, %%ymm8" : : "m" (dq[32]));
+		asm volatile("vpxor %0, %%ymm3, %%ymm3" : : "m" (q[0]));
+		asm volatile("vpxor %0, %%ymm8, %%ymm8" : : "m" (q[32]));
+
+		/*
+		 * 3 = q[0] ^ dq[0]
+		 * 8 = q[32] ^ dq[32]
+		 */
+		asm volatile("vbroadcasti128 %0, %%ymm0" : : "m" (qmul[0]));
+		asm volatile("vmovapd %ymm0, %ymm13");
+		asm volatile("vbroadcasti128 %0, %%ymm1" : : "m" (qmul[16]));
+		asm volatile("vmovapd %ymm1, %ymm14");
+
+		asm volatile("vpsraw $4, %ymm3, %ymm6");
+		asm volatile("vpsraw $4, %ymm8, %ymm12");
+		asm volatile("vpand %ymm7, %ymm3, %ymm3");
+		asm volatile("vpand %ymm7, %ymm8, %ymm8");
+		asm volatile("vpand %ymm7, %ymm6, %ymm6");
+		asm volatile("vpand %ymm7, %ymm12, %ymm12");
+		asm volatile("vpshufb %ymm3, %ymm0, %ymm0");
+		asm volatile("vpshufb %ymm8, %ymm13, %ymm13");
+		asm volatile("vpshufb %ymm6, %ymm1, %ymm1");
+		asm volatile("vpshufb %ymm12, %ymm14, %ymm14");
+		asm volatile("vpxor %ymm0, %ymm1, %ymm1");
+		asm volatile("vpxor %ymm13, %ymm14, %ymm14");
+
+		/*
+		 * 1  = qmul[q[0]  ^ dq[0]]
+		 * 14 = qmul[q[32] ^ dq[32]]
+		 */
+		asm volatile("vmovdqa %0, %%ymm2" : : "m" (p[0]));
+		asm volatile("vmovdqa %0, %%ymm12" : : "m" (p[32]));
+		asm volatile("vpxor %ymm1, %ymm2, %ymm2");
+		asm volatile("vpxor %ymm14, %ymm12, %ymm12");
+
+		/*
+		 * 2  = p[0]  ^ qmul[q[0]  ^ dq[0]]
+		 * 12 = p[32] ^ qmul[q[32] ^ dq[32]]
+		 */
+
+		asm volatile("vmovdqa %%ymm1, %0" : "=m" (dq[0]));
+		asm volatile("vmovdqa %%ymm14, %0" : "=m" (dq[32]));
+		asm volatile("vmovdqa %%ymm2, %0" : "=m" (p[0]));
+		asm volatile("vmovdqa %%ymm12,%0" : "=m" (p[32]));
+
+		bytes -= 64;
+		p += 64;
+		q += 64;
+		dq += 64;
+#else
+		asm volatile("vmovdqa %0, %%ymm3" : : "m" (dq[0]));
+		asm volatile("vpxor %0, %%ymm3, %%ymm3" : : "m" (q[0]));
+
+		/* 3 = q ^ dq */
+
+		asm volatile("vbroadcasti128 %0, %%ymm0" : : "m" (qmul[0]));
+		asm volatile("vbroadcasti128 %0, %%ymm1" : : "m" (qmul[16]));
+
+		asm volatile("vpsraw $4, %ymm3, %ymm6");
+		asm volatile("vpand %ymm7, %ymm3, %ymm3");
+		asm volatile("vpand %ymm7, %ymm6, %ymm6");
+		asm volatile("vpshufb %ymm3, %ymm0, %ymm0");
+		asm volatile("vpshufb %ymm6, %ymm1, %ymm1");
+		asm volatile("vpxor %ymm0, %ymm1, %ymm1");
+
+		/* 1 = qmul[q ^ dq] */
+
+		asm volatile("vmovdqa %0, %%ymm2" : : "m" (p[0]));
+		asm volatile("vpxor %ymm1, %ymm2, %ymm2");
+
+		/* 2 = p ^ qmul[q ^ dq] */
+
+		asm volatile("vmovdqa %%ymm1, %0" : "=m" (dq[0]));
+		asm volatile("vmovdqa %%ymm2, %0" : "=m" (p[0]));
+
+		bytes -= 32;
+		p += 32;
+		q += 32;
+		dq += 32;
+#endif
+	}
+
+	kernel_fpu_end();
+}
+
+const struct raid6_recov_calls raid6_recov_avx2 = {
+	.data2 = raid6_2data_recov_avx2,
+	.datap = raid6_datap_recov_avx2,
+	.valid = raid6_has_avx2,
+#ifdef CONFIG_X86_64
+	.name = "avx2x2",
+#else
+	.name = "avx2x1",
+#endif
+	.priority = 2,
+};
+
+#else
+#warning "your version of binutils lacks AVX2 support"
+#endif
+
+#endif
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index c76151d94764..d919c98ce266 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -23,7 +23,7 @@ RANLIB	 = ranlib
 all:	raid6.a raid6test
 
 raid6.a: int1.o int2.o int4.o int8.o int16.o int32.o mmx.o sse1.o sse2.o \
-	 altivec1.o altivec2.o altivec4.o altivec8.o recov.o recov_ssse3.o algos.o \
+	 altivec1.o altivec2.o altivec4.o altivec8.o recov.o recov_ssse3.o recov_avx2.o algos.o \
 	 tables.o
 	 rm -f $@
 	 $(AR) cq $@ $^
diff --git a/lib/raid6/x86.h b/lib/raid6/x86.h
index d55d63232c55..b7595484a815 100644
--- a/lib/raid6/x86.h
+++ b/lib/raid6/x86.h
@@ -45,19 +45,23 @@ static inline void kernel_fpu_end(void)
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
 #define X86_FEATURE_SSSE3	(4*32+ 9) /* Supplemental SSE-3 */
 #define X86_FEATURE_AVX	(4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_AVX2        (9*32+ 5) /* AVX2 instructions */
 #define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
 
 /* Should work well enough on modern CPUs for testing */
 static inline int boot_cpu_has(int flag)
 {
-	u32 eax = (flag & 0x20) ? 0x80000001 : 1;
-	u32 ecx, edx;
+	u32 eax, ebx, ecx, edx;
+
+	eax = (flag & 0x100) ? 7 :
+		(flag & 0x20) ? 0x80000001 : 1;
+	ecx = 0;
 
 	asm volatile("cpuid"
-		     : "+a" (eax), "=d" (edx), "=c" (ecx)
-		     : : "ebx");
+		     : "+a" (eax), "=b" (ebx), "=d" (edx), "+c" (ecx));
 
-	return ((flag & 0x80 ? ecx : edx) >> (flag & 31)) & 1;
+	return ((flag & 0x100 ? ebx :
+		(flag & 0x80) ? ecx : edx) >> (flag & 31)) & 1;
 }
 
 #endif /* ndef __KERNEL__ */
-- 
cgit v1.2.3-55-g7522


From 2c935842bdb46f5f557426feb4d2bdfdad1aa5f9 Mon Sep 17 00:00:00 2001
From: Yuanhan Liu
Date: Fri, 30 Nov 2012 13:10:39 -0800
Subject: lib/raid6: Add AVX2 optimized gen_syndrome functions

Add AVX2 optimized gen_syndrom functions, which is simply based on
sse2.c written by hpa.

Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Jim Kukunas <james.t.kukunas@linux.intel.com>
Signed-off-by: NeilBrown <neilb@suse.de>
---
 include/linux/raid/pq.h |   3 +
 lib/raid6/Makefile      |   2 +-
 lib/raid6/algos.c       |   9 ++
 lib/raid6/avx2.c        | 251 ++++++++++++++++++++++++++++++++++++++++++++++++
 lib/raid6/test/Makefile |  12 ++-
 5 files changed, 275 insertions(+), 2 deletions(-)
 create mode 100644 lib/raid6/avx2.c

(limited to 'include')

diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index 3156347452b9..8dfaa2ce2e95 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -98,6 +98,9 @@ extern const struct raid6_calls raid6_altivec1;
 extern const struct raid6_calls raid6_altivec2;
 extern const struct raid6_calls raid6_altivec4;
 extern const struct raid6_calls raid6_altivec8;
+extern const struct raid6_calls raid6_avx2x1;
+extern const struct raid6_calls raid6_avx2x2;
+extern const struct raid6_calls raid6_avx2x4;
 
 struct raid6_recov_calls {
 	void (*data2)(int, size_t, int, int, void **);
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 8c2e22bef661..3430711b9bdf 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -2,7 +2,7 @@ obj-$(CONFIG_RAID6_PQ)	+= raid6_pq.o
 
 raid6_pq-y	+= algos.o recov.o recov_ssse3.o recov_avx2.o tables.o int1.o int2.o int4.o \
 		   int8.o int16.o int32.o altivec1.o altivec2.o altivec4.o \
-		   altivec8.o mmx.o sse1.o sse2.o
+		   altivec8.o mmx.o sse1.o sse2.o avx2.o
 hostprogs-y	+= mktables
 
 quiet_cmd_unroll = UNROLL  $@
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 8b7f55cadb45..6d7316fe9f30 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -45,11 +45,20 @@ const struct raid6_calls * const raid6_algos[] = {
 	&raid6_sse1x2,
 	&raid6_sse2x1,
 	&raid6_sse2x2,
+#ifdef CONFIG_AS_AVX2
+	&raid6_avx2x1,
+	&raid6_avx2x2,
+#endif
 #endif
 #if defined(__x86_64__) && !defined(__arch_um__)
 	&raid6_sse2x1,
 	&raid6_sse2x2,
 	&raid6_sse2x4,
+#ifdef CONFIG_AS_AVX2
+	&raid6_avx2x1,
+	&raid6_avx2x2,
+	&raid6_avx2x4,
+#endif
 #endif
 #ifdef CONFIG_ALTIVEC
 	&raid6_altivec1,
diff --git a/lib/raid6/avx2.c b/lib/raid6/avx2.c
new file mode 100644
index 000000000000..bc3b1dd436eb
--- /dev/null
+++ b/lib/raid6/avx2.c
@@ -0,0 +1,251 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 2012 Intel Corporation
+ *   Author: Yuanhan Liu <yuanhan.liu@linux.intel.com>
+ *
+ *   Based on sse2.c: Copyright 2002 H. Peter Anvin - All Rights Reserved
+ *
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
+ *   (at your option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * AVX2 implementation of RAID-6 syndrome functions
+ *
+ */
+
+#ifdef CONFIG_AS_AVX2
+
+#include <linux/raid/pq.h>
+#include "x86.h"
+
+static const struct raid6_avx2_constants {
+	u64 x1d[4];
+} raid6_avx2_constants __aligned(32) = {
+	{ 0x1d1d1d1d1d1d1d1dULL, 0x1d1d1d1d1d1d1d1dULL,
+	  0x1d1d1d1d1d1d1d1dULL, 0x1d1d1d1d1d1d1d1dULL,},
+};
+
+static int raid6_have_avx2(void)
+{
+	return boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX);
+}
+
+/*
+ * Plain AVX2 implementation
+ */
+static void raid6_avx21_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = disks - 3;		/* Highest data disk */
+	p = dptr[z0+1];		/* XOR parity */
+	q = dptr[z0+2];		/* RS syndrome */
+
+	kernel_fpu_begin();
+
+	asm volatile("vmovdqa %0,%%ymm0" : : "m" (raid6_avx2_constants.x1d[0]));
+	asm volatile("vpxor %ymm3,%ymm3,%ymm3");	/* Zero temp */
+
+	for (d = 0; d < bytes; d += 32) {
+		asm volatile("prefetchnta %0" : : "m" (dptr[z0][d]));
+		asm volatile("vmovdqa %0,%%ymm2" : : "m" (dptr[z0][d]));/* P[0] */
+		asm volatile("prefetchnta %0" : : "m" (dptr[z0-1][d]));
+		asm volatile("vmovdqa %ymm2,%ymm4");/* Q[0] */
+		asm volatile("vmovdqa %0,%%ymm6" : : "m" (dptr[z0-1][d]));
+		for (z = z0-2; z >= 0; z--) {
+			asm volatile("prefetchnta %0" : : "m" (dptr[z][d]));
+			asm volatile("vpcmpgtb %ymm4,%ymm3,%ymm5");
+			asm volatile("vpaddb %ymm4,%ymm4,%ymm4");
+			asm volatile("vpand %ymm0,%ymm5,%ymm5");
+			asm volatile("vpxor %ymm5,%ymm4,%ymm4");
+			asm volatile("vpxor %ymm6,%ymm2,%ymm2");
+			asm volatile("vpxor %ymm6,%ymm4,%ymm4");
+			asm volatile("vmovdqa %0,%%ymm6" : : "m" (dptr[z][d]));
+		}
+		asm volatile("vpcmpgtb %ymm4,%ymm3,%ymm5");
+		asm volatile("vpaddb %ymm4,%ymm4,%ymm4");
+		asm volatile("vpand %ymm0,%ymm5,%ymm5");
+		asm volatile("vpxor %ymm5,%ymm4,%ymm4");
+		asm volatile("vpxor %ymm6,%ymm2,%ymm2");
+		asm volatile("vpxor %ymm6,%ymm4,%ymm4");
+
+		asm volatile("vmovntdq %%ymm2,%0" : "=m" (p[d]));
+		asm volatile("vpxor %ymm2,%ymm2,%ymm2");
+		asm volatile("vmovntdq %%ymm4,%0" : "=m" (q[d]));
+		asm volatile("vpxor %ymm4,%ymm4,%ymm4");
+	}
+
+	asm volatile("sfence" : : : "memory");
+	kernel_fpu_end();
+}
+
+const struct raid6_calls raid6_avx2x1 = {
+	raid6_avx21_gen_syndrome,
+	raid6_have_avx2,
+	"avx2x1",
+	1			/* Has cache hints */
+};
+
+/*
+ * Unrolled-by-2 AVX2 implementation
+ */
+static void raid6_avx22_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = disks - 3;		/* Highest data disk */
+	p = dptr[z0+1];		/* XOR parity */
+	q = dptr[z0+2];		/* RS syndrome */
+
+	kernel_fpu_begin();
+
+	asm volatile("vmovdqa %0,%%ymm0" : : "m" (raid6_avx2_constants.x1d[0]));
+	asm volatile("vpxor %ymm1,%ymm1,%ymm1"); /* Zero temp */
+
+	/* We uniformly assume a single prefetch covers at least 32 bytes */
+	for (d = 0; d < bytes; d += 64) {
+		asm volatile("prefetchnta %0" : : "m" (dptr[z0][d]));
+		asm volatile("prefetchnta %0" : : "m" (dptr[z0][d+32]));
+		asm volatile("vmovdqa %0,%%ymm2" : : "m" (dptr[z0][d]));/* P[0] */
+		asm volatile("vmovdqa %0,%%ymm3" : : "m" (dptr[z0][d+32]));/* P[1] */
+		asm volatile("vmovdqa %ymm2,%ymm4"); /* Q[0] */
+		asm volatile("vmovdqa %ymm3,%ymm6"); /* Q[1] */
+		for (z = z0-1; z >= 0; z--) {
+			asm volatile("prefetchnta %0" : : "m" (dptr[z][d]));
+			asm volatile("prefetchnta %0" : : "m" (dptr[z][d+32]));
+			asm volatile("vpcmpgtb %ymm4,%ymm1,%ymm5");
+			asm volatile("vpcmpgtb %ymm6,%ymm1,%ymm7");
+			asm volatile("vpaddb %ymm4,%ymm4,%ymm4");
+			asm volatile("vpaddb %ymm6,%ymm6,%ymm6");
+			asm volatile("vpand %ymm0,%ymm5,%ymm5");
+			asm volatile("vpand %ymm0,%ymm7,%ymm7");
+			asm volatile("vpxor %ymm5,%ymm4,%ymm4");
+			asm volatile("vpxor %ymm7,%ymm6,%ymm6");
+			asm volatile("vmovdqa %0,%%ymm5" : : "m" (dptr[z][d]));
+			asm volatile("vmovdqa %0,%%ymm7" : : "m" (dptr[z][d+32]));
+			asm volatile("vpxor %ymm5,%ymm2,%ymm2");
+			asm volatile("vpxor %ymm7,%ymm3,%ymm3");
+			asm volatile("vpxor %ymm5,%ymm4,%ymm4");
+			asm volatile("vpxor %ymm7,%ymm6,%ymm6");
+		}
+		asm volatile("vmovntdq %%ymm2,%0" : "=m" (p[d]));
+		asm volatile("vmovntdq %%ymm3,%0" : "=m" (p[d+32]));
+		asm volatile("vmovntdq %%ymm4,%0" : "=m" (q[d]));
+		asm volatile("vmovntdq %%ymm6,%0" : "=m" (q[d+32]));
+	}
+
+	asm volatile("sfence" : : : "memory");
+	kernel_fpu_end();
+}
+
+const struct raid6_calls raid6_avx2x2 = {
+	raid6_avx22_gen_syndrome,
+	raid6_have_avx2,
+	"avx2x2",
+	1			/* Has cache hints */
+};
+
+#ifdef CONFIG_X86_64
+
+/*
+ * Unrolled-by-4 AVX2 implementation
+ */
+static void raid6_avx24_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = disks - 3;		/* Highest data disk */
+	p = dptr[z0+1];		/* XOR parity */
+	q = dptr[z0+2];		/* RS syndrome */
+
+	kernel_fpu_begin();
+
+	asm volatile("vmovdqa %0,%%ymm0" : : "m" (raid6_avx2_constants.x1d[0]));
+	asm volatile("vpxor %ymm1,%ymm1,%ymm1");	/* Zero temp */
+	asm volatile("vpxor %ymm2,%ymm2,%ymm2");	/* P[0] */
+	asm volatile("vpxor %ymm3,%ymm3,%ymm3");	/* P[1] */
+	asm volatile("vpxor %ymm4,%ymm4,%ymm4");	/* Q[0] */
+	asm volatile("vpxor %ymm6,%ymm6,%ymm6");	/* Q[1] */
+	asm volatile("vpxor %ymm10,%ymm10,%ymm10");	/* P[2] */
+	asm volatile("vpxor %ymm11,%ymm11,%ymm11");	/* P[3] */
+	asm volatile("vpxor %ymm12,%ymm12,%ymm12");	/* Q[2] */
+	asm volatile("vpxor %ymm14,%ymm14,%ymm14");	/* Q[3] */
+
+	for (d = 0; d < bytes; d += 128) {
+		for (z = z0; z >= 0; z--) {
+			asm volatile("prefetchnta %0" : : "m" (dptr[z][d]));
+			asm volatile("prefetchnta %0" : : "m" (dptr[z][d+32]));
+			asm volatile("prefetchnta %0" : : "m" (dptr[z][d+64]));
+			asm volatile("prefetchnta %0" : : "m" (dptr[z][d+96]));
+			asm volatile("vpcmpgtb %ymm4,%ymm1,%ymm5");
+			asm volatile("vpcmpgtb %ymm6,%ymm1,%ymm7");
+			asm volatile("vpcmpgtb %ymm12,%ymm1,%ymm13");
+			asm volatile("vpcmpgtb %ymm14,%ymm1,%ymm15");
+			asm volatile("vpaddb %ymm4,%ymm4,%ymm4");
+			asm volatile("vpaddb %ymm6,%ymm6,%ymm6");
+			asm volatile("vpaddb %ymm12,%ymm12,%ymm12");
+			asm volatile("vpaddb %ymm14,%ymm14,%ymm14");
+			asm volatile("vpand %ymm0,%ymm5,%ymm5");
+			asm volatile("vpand %ymm0,%ymm7,%ymm7");
+			asm volatile("vpand %ymm0,%ymm13,%ymm13");
+			asm volatile("vpand %ymm0,%ymm15,%ymm15");
+			asm volatile("vpxor %ymm5,%ymm4,%ymm4");
+			asm volatile("vpxor %ymm7,%ymm6,%ymm6");
+			asm volatile("vpxor %ymm13,%ymm12,%ymm12");
+			asm volatile("vpxor %ymm15,%ymm14,%ymm14");
+			asm volatile("vmovdqa %0,%%ymm5" : : "m" (dptr[z][d]));
+			asm volatile("vmovdqa %0,%%ymm7" : : "m" (dptr[z][d+32]));
+			asm volatile("vmovdqa %0,%%ymm13" : : "m" (dptr[z][d+64]));
+			asm volatile("vmovdqa %0,%%ymm15" : : "m" (dptr[z][d+96]));
+			asm volatile("vpxor %ymm5,%ymm2,%ymm2");
+			asm volatile("vpxor %ymm7,%ymm3,%ymm3");
+			asm volatile("vpxor %ymm13,%ymm10,%ymm10");
+			asm volatile("vpxor %ymm15,%ymm11,%ymm11");
+			asm volatile("vpxor %ymm5,%ymm4,%ymm4");
+			asm volatile("vpxor %ymm7,%ymm6,%ymm6");
+			asm volatile("vpxor %ymm13,%ymm12,%ymm12");
+			asm volatile("vpxor %ymm15,%ymm14,%ymm14");
+		}
+		asm volatile("vmovntdq %%ymm2,%0" : "=m" (p[d]));
+		asm volatile("vpxor %ymm2,%ymm2,%ymm2");
+		asm volatile("vmovntdq %%ymm3,%0" : "=m" (p[d+32]));
+		asm volatile("vpxor %ymm3,%ymm3,%ymm3");
+		asm volatile("vmovntdq %%ymm10,%0" : "=m" (p[d+64]));
+		asm volatile("vpxor %ymm10,%ymm10,%ymm10");
+		asm volatile("vmovntdq %%ymm11,%0" : "=m" (p[d+96]));
+		asm volatile("vpxor %ymm11,%ymm11,%ymm11");
+		asm volatile("vmovntdq %%ymm4,%0" : "=m" (q[d]));
+		asm volatile("vpxor %ymm4,%ymm4,%ymm4");
+		asm volatile("vmovntdq %%ymm6,%0" : "=m" (q[d+32]));
+		asm volatile("vpxor %ymm6,%ymm6,%ymm6");
+		asm volatile("vmovntdq %%ymm12,%0" : "=m" (q[d+64]));
+		asm volatile("vpxor %ymm12,%ymm12,%ymm12");
+		asm volatile("vmovntdq %%ymm14,%0" : "=m" (q[d+96]));
+		asm volatile("vpxor %ymm14,%ymm14,%ymm14");
+	}
+
+	asm volatile("sfence" : : : "memory");
+	kernel_fpu_end();
+}
+
+const struct raid6_calls raid6_avx2x4 = {
+	raid6_avx24_gen_syndrome,
+	raid6_have_avx2,
+	"avx2x4",
+	1			/* Has cache hints */
+};
+#endif
+
+#endif /* CONFIG_AS_AVX2 */
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index d919c98ce266..754cbac0f9f8 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -11,6 +11,16 @@ AWK	 = awk -f
 AR	 = ar
 RANLIB	 = ranlib
 
+ARCH := $(shell uname -m 2>/dev/null | sed -e /s/i.86/i386/)
+ifeq ($(ARCH),i386)
+        CFLAGS += -DCONFIG_X86_32
+endif
+ifeq ($(ARCH),x86_64)
+        CFLAGS += -DCONFIG_X86_64
+endif
+CFLAGS += $(shell echo "vpbroadcastb %xmm0, %ymm1"| gcc -c -x assembler - &&\
+	     rm ./-.o && echo -DCONFIG_AS_AVX2=1)
+
 .c.o:
 	$(CC) $(CFLAGS) -c -o $@ $<
 
@@ -22,7 +32,7 @@ RANLIB	 = ranlib
 
 all:	raid6.a raid6test
 
-raid6.a: int1.o int2.o int4.o int8.o int16.o int32.o mmx.o sse1.o sse2.o \
+raid6.a: int1.o int2.o int4.o int8.o int16.o int32.o mmx.o sse1.o sse2.o avx2.o \
 	 altivec1.o altivec2.o altivec4.o altivec8.o recov.o recov_ssse3.o recov_avx2.o algos.o \
 	 tables.o
 	 rm -f $@
-- 
cgit v1.2.3-55-g7522


From 83aff95eb9d60aff5497e9f44a2ae906b86d8e88 Mon Sep 17 00:00:00 2001
From: Sage Weil
Date: Wed, 28 Nov 2012 12:28:24 -0800
Subject: libceph: remove 'osdtimeout' option

This would reset a connection with any OSD that had an outstanding
request that was taking more than N seconds.  The idea was that if the
OSD was buggy, the client could compensate by resending the request.

In reality, this only served to hide server bugs, and we haven't
actually seen such a bug in quite a while.  Moreover, the userspace
client code never did this.

More importantly, often the request is taking a long time because the
OSD is trying to recover, or overloaded, and killing the connection
and retrying would only make the situation worse by giving the OSD
more work to do.

Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>
---
 fs/ceph/super.c              |  2 --
 include/linux/ceph/libceph.h |  2 --
 net/ceph/ceph_common.c       |  3 +--
 net/ceph/osd_client.c        | 47 ++++----------------------------------------
 4 files changed, 5 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 2f586b0e5e0f..fcda1c73a1e5 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -403,8 +403,6 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 		seq_printf(m, ",mount_timeout=%d", opt->mount_timeout);
 	if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
 		seq_printf(m, ",osd_idle_ttl=%d", opt->osd_idle_ttl);
-	if (opt->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT)
-		seq_printf(m, ",osdtimeout=%d", opt->osd_timeout);
 	if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
 		seq_printf(m, ",osdkeepalivetimeout=%d",
 			   opt->osd_keepalive_timeout);
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 42624789b06f..317aff8feb0a 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -43,7 +43,6 @@ struct ceph_options {
 	struct ceph_entity_addr my_addr;
 	int mount_timeout;
 	int osd_idle_ttl;
-	int osd_timeout;
 	int osd_keepalive_timeout;
 
 	/*
@@ -63,7 +62,6 @@ struct ceph_options {
  * defaults
  */
 #define CEPH_MOUNT_TIMEOUT_DEFAULT  60
-#define CEPH_OSD_TIMEOUT_DEFAULT    60  /* seconds */
 #define CEPH_OSD_KEEPALIVE_DEFAULT  5
 #define CEPH_OSD_IDLE_TTL_DEFAULT    60
 
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index a8020293f342..ee71ea26777a 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -305,7 +305,6 @@ ceph_parse_options(char *options, const char *dev_name,
 
 	/* start with defaults */
 	opt->flags = CEPH_OPT_DEFAULT;
-	opt->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT;
 	opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
 	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */
 	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;   /* seconds */
@@ -391,7 +390,7 @@ ceph_parse_options(char *options, const char *dev_name,
 
 			/* misc */
 		case Opt_osdtimeout:
-			opt->osd_timeout = intval;
+			pr_warning("ignoring deprecated osdtimeout option\n");
 			break;
 		case Opt_osdkeepalivetimeout:
 			opt->osd_keepalive_timeout = intval;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index ccbdfbba9e53..7ebfe13267e6 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -608,14 +608,6 @@ static void __kick_osd_requests(struct ceph_osd_client *osdc,
 	}
 }
 
-static void kick_osd_requests(struct ceph_osd_client *osdc,
-			      struct ceph_osd *kickosd)
-{
-	mutex_lock(&osdc->request_mutex);
-	__kick_osd_requests(osdc, kickosd);
-	mutex_unlock(&osdc->request_mutex);
-}
-
 /*
  * If the osd connection drops, we need to resubmit all requests.
  */
@@ -629,7 +621,9 @@ static void osd_reset(struct ceph_connection *con)
 	dout("osd_reset osd%d\n", osd->o_osd);
 	osdc = osd->o_osdc;
 	down_read(&osdc->map_sem);
-	kick_osd_requests(osdc, osd);
+	mutex_lock(&osdc->request_mutex);
+	__kick_osd_requests(osdc, osd);
+	mutex_unlock(&osdc->request_mutex);
 	send_queued(osdc);
 	up_read(&osdc->map_sem);
 }
@@ -1091,12 +1085,10 @@ static void handle_timeout(struct work_struct *work)
 {
 	struct ceph_osd_client *osdc =
 		container_of(work, struct ceph_osd_client, timeout_work.work);
-	struct ceph_osd_request *req, *last_req = NULL;
+	struct ceph_osd_request *req;
 	struct ceph_osd *osd;
-	unsigned long timeout = osdc->client->options->osd_timeout * HZ;
 	unsigned long keepalive =
 		osdc->client->options->osd_keepalive_timeout * HZ;
-	unsigned long last_stamp = 0;
 	struct list_head slow_osds;
 	dout("timeout\n");
 	down_read(&osdc->map_sem);
@@ -1105,37 +1097,6 @@ static void handle_timeout(struct work_struct *work)
 
 	mutex_lock(&osdc->request_mutex);
 
-	/*
-	 * reset osds that appear to be _really_ unresponsive.  this
-	 * is a failsafe measure.. we really shouldn't be getting to
-	 * this point if the system is working properly.  the monitors
-	 * should mark the osd as failed and we should find out about
-	 * it from an updated osd map.
-	 */
-	while (timeout && !list_empty(&osdc->req_lru)) {
-		req = list_entry(osdc->req_lru.next, struct ceph_osd_request,
-				 r_req_lru_item);
-
-		/* hasn't been long enough since we sent it? */
-		if (time_before(jiffies, req->r_stamp + timeout))
-			break;
-
-		/* hasn't been long enough since it was acked? */
-		if (req->r_request->ack_stamp == 0 ||
-		    time_before(jiffies, req->r_request->ack_stamp + timeout))
-			break;
-
-		BUG_ON(req == last_req && req->r_stamp == last_stamp);
-		last_req = req;
-		last_stamp = req->r_stamp;
-
-		osd = req->r_osd;
-		BUG_ON(!osd);
-		pr_warning(" tid %llu timed out on osd%d, will reset osd\n",
-			   req->r_tid, osd->o_osd);
-		__kick_osd_requests(osdc, osd);
-	}
-
 	/*
 	 * ping osds that are a bit slow.  this ensures that if there
 	 * is a break in the TCP connection we will notice, and reopen
-- 
cgit v1.2.3-55-g7522


From d2cc4dde9206aa2c7fb237aa689d3277cc070547 Mon Sep 17 00:00:00 2001
From: Joe Perches
Date: Thu, 29 Nov 2012 08:37:03 -0600
Subject: bdi_register: add __printf verification, fix arg mismatch

__printf is useful to verify format and arguments.

Signed-off-by: Joe Perches <joe@perches.com>
Reviewed-by: Alex Elder <elder@inktank.com>
---
 fs/ceph/super.c             | 2 +-
 include/linux/backing-dev.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index fcda1c73a1e5..1a144001b2e1 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -842,7 +842,7 @@ static int ceph_register_bdi(struct super_block *sb,
 		fsc->backing_dev_info.ra_pages =
 			default_backing_dev_info.ra_pages;
 
-	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%d",
+	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
 			   atomic_long_inc_return(&bdi_seq));
 	if (!err)
 		sb->s_bdi = &fsc->backing_dev_info;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 2a9a9abc9126..12731a19ef06 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -114,6 +114,7 @@ struct backing_dev_info {
 int bdi_init(struct backing_dev_info *bdi);
 void bdi_destroy(struct backing_dev_info *bdi);
 
+__printf(3, 4)
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...);
 int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
-- 
cgit v1.2.3-55-g7522


From dc2e57340deb8be1133b1eae2c7d4303133c133c Mon Sep 17 00:00:00 2001
From: Yan Burman
Date: Thu, 13 Dec 2012 05:20:59 +0000
Subject: net: ethool: Document struct ethtool_flow_ext

Add documentation for struct ethtool_flow_ext especially in regard
to what flags are needed for which fields.

Signed-off-by: Yan Burman <yanb@mellanox.com>
Reviewed-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ethtool.h | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index be8c41e2dc15..0c9b44871df0 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -503,9 +503,20 @@ union ethtool_flow_union {
 	__u8					hdata[52];
 };
 
+/**
+ * struct ethtool_flow_ext - additional RX flow fields
+ * @h_dest: destination MAC address
+ * @vlan_etype: VLAN EtherType
+ * @vlan_tci: VLAN tag control information
+ * @data: user defined data
+ *
+ * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT
+ * is set in &struct ethtool_rx_flow_spec @flow_type.
+ * @h_dest is valid if %FLOW_MAC_EXT is set.
+ */
 struct ethtool_flow_ext {
 	__u8		padding[2];
-	unsigned char	h_dest[ETH_ALEN];	/* destination eth addr	*/
+	unsigned char	h_dest[ETH_ALEN];
 	__be16		vlan_etype;
 	__be16		vlan_tci;
 	__be32		data[2];
@@ -519,7 +530,8 @@ struct ethtool_flow_ext {
  * @m_u: Masks for flow field bits to be matched
  * @m_ext: Masks for additional field bits to be matched
  *	Note, all additional fields must be ignored unless @flow_type
- *	includes the %FLOW_EXT flag.
+ *	includes the %FLOW_EXT or %FLOW_MAC_EXT flag
+ *	(see &struct ethtool_flow_ext description).
  * @ring_cookie: RX ring/queue index to deliver to, or %RX_CLS_FLOW_DISC
  *	if packets should be discarded
  * @location: Location of rule in the table.  Locations must be
-- 
cgit v1.2.3-55-g7522


From 79e62fc3827bd437c304c1810f36896fc1e717b1 Mon Sep 17 00:00:00 2001
From: Andy Grover
Date: Tue, 11 Dec 2012 16:30:53 -0800
Subject: target/iscsi_target: Add NodeACL tags for initiator group support

Thanks for reviews, looking a lot better.

---- 8< ----

Initiator access config could be easier. The way other storage vendors
have addressed this is to support initiator groups: the admin adds
initiator WWNs to the group, and then LUN permissions can be granted for
the entire group at once.

Instead of changing ktarget's configfs interface, this patch keeps
the configfs interface per-initiator-wwn and just adds a 'tag' field
for each. This should be enough for user tools like targetcli to group
initiator ACLs and sync their configurations.

acl_tag is not used internally, but needs to be kept in configfs so that
all user tools can avoid dependencies on each other.

Code tested to work, although userspace pieces still to be implemented.

Signed-off-by: Andy Grover <agrover@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/iscsi/iscsi_target_configfs.c | 24 ++++++++++++++++++++++++
 drivers/target/target_core_tpg.c             | 23 +++++++++++++++++++++++
 include/target/target_core_base.h            |  2 ++
 include/target/target_core_fabric.h          |  2 ++
 4 files changed, 51 insertions(+)

(limited to 'include')

diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 542641c504a6..5201d5ef9700 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -754,9 +754,33 @@ static ssize_t lio_target_nacl_store_cmdsn_depth(
 
 TF_NACL_BASE_ATTR(lio_target, cmdsn_depth, S_IRUGO | S_IWUSR);
 
+static ssize_t lio_target_nacl_show_tag(
+	struct se_node_acl *se_nacl,
+	char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%s", se_nacl->acl_tag);
+}
+
+static ssize_t lio_target_nacl_store_tag(
+	struct se_node_acl *se_nacl,
+	const char *page,
+	size_t count)
+{
+	int ret;
+
+	ret = core_tpg_set_initiator_node_tag(se_nacl->se_tpg, se_nacl, page);
+
+	if (ret < 0)
+		return ret;
+	return count;
+}
+
+TF_NACL_BASE_ATTR(lio_target, tag, S_IRUGO | S_IWUSR);
+
 static struct configfs_attribute *lio_target_initiator_attrs[] = {
 	&lio_target_nacl_info.attr,
 	&lio_target_nacl_cmdsn_depth.attr,
+	&lio_target_nacl_tag.attr,
 	NULL,
 };
 
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index 0163309e2aba..5192ac0337f7 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -616,6 +616,29 @@ int core_tpg_set_initiator_node_queue_depth(
 }
 EXPORT_SYMBOL(core_tpg_set_initiator_node_queue_depth);
 
+/*	core_tpg_set_initiator_node_tag():
+ *
+ *	Initiator nodeacl tags are not used internally, but may be used by
+ *	userspace to emulate aliases or groups.
+ *	Returns length of newly-set tag or -EINVAL.
+ */
+int core_tpg_set_initiator_node_tag(
+	struct se_portal_group *tpg,
+	struct se_node_acl *acl,
+	const char *new_tag)
+{
+	if (strlen(new_tag) >= MAX_ACL_TAG_SIZE)
+		return -EINVAL;
+
+	if (!strncmp("NULL", new_tag, 4)) {
+		acl->acl_tag[0] = '\0';
+		return 0;
+	}
+
+	return snprintf(acl->acl_tag, MAX_ACL_TAG_SIZE, "%s", new_tag);
+}
+EXPORT_SYMBOL(core_tpg_set_initiator_node_tag);
+
 static int core_tpg_setup_virtual_lun0(struct se_portal_group *se_tpg)
 {
 	/* Set in core_dev_setup_virtual_lun0() */
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 1346ee04db5e..7cae2360221e 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -507,6 +507,8 @@ struct se_node_acl {
 	bool			acl_stop:1;
 	u32			queue_depth;
 	u32			acl_index;
+#define MAX_ACL_TAG_SIZE 64
+	char			acl_tag[MAX_ACL_TAG_SIZE];
 	u64			num_cmds;
 	u64			read_bytes;
 	u64			write_bytes;
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 9087b200e552..aaa1ee6ab391 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -142,6 +142,8 @@ int	core_tpg_del_initiator_node_acl(struct se_portal_group *,
 		struct se_node_acl *, int);
 int	core_tpg_set_initiator_node_queue_depth(struct se_portal_group *,
 		unsigned char *, u32, int);
+int	core_tpg_set_initiator_node_tag(struct se_portal_group *,
+		struct se_node_acl *, const char *);
 int	core_tpg_register(struct target_core_fabric_ops *, struct se_wwn *,
 		struct se_portal_group *, void *, int);
 int	core_tpg_deregister(struct se_portal_group *);
-- 
cgit v1.2.3-55-g7522


From 34e1169d996ab148490c01b65b4ee371cf8ffba2 Mon Sep 17 00:00:00 2001
From: Kees Cook
Date: Tue, 16 Oct 2012 07:31:07 +1030
Subject: module: add syscall to load module from fd

As part of the effort to create a stronger boundary between root and
kernel, Chrome OS wants to be able to enforce that kernel modules are
being loaded only from our read-only crypto-hash verified (dm_verity)
root filesystem. Since the init_module syscall hands the kernel a module
as a memory blob, no reasoning about the origin of the blob can be made.

Earlier proposals for appending signatures to kernel modules would not be
useful in Chrome OS, since it would involve adding an additional set of
keys to our kernel and builds for no good reason: we already trust the
contents of our root filesystem. We don't need to verify those kernel
modules a second time. Having to do signature checking on module loading
would slow us down and be redundant. All we need to know is where a
module is coming from so we can say yes/no to loading it.

If a file descriptor is used as the source of a kernel module, many more
things can be reasoned about. In Chrome OS's case, we could enforce that
the module lives on the filesystem we expect it to live on.  In the case
of IMA (or other LSMs), it would be possible, for example, to examine
extended attributes that may contain signatures over the contents of
the module.

This introduces a new syscall (on x86), similar to init_module, that has
only two arguments. The first argument is used as a file descriptor to
the module and the second argument is a pointer to the NULL terminated
string of module arguments.

Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (merge fixes)
---
 arch/x86/syscalls/syscall_32.tbl |   1 +
 arch/x86/syscalls/syscall_64.tbl |   1 +
 include/linux/syscalls.h         |   1 +
 kernel/module.c                  | 367 +++++++++++++++++++++++----------------
 kernel/sys_ni.c                  |   1 +
 5 files changed, 223 insertions(+), 148 deletions(-)

(limited to 'include')

diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index a47103fbc692..83b3838417ed 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -356,3 +356,4 @@
 347	i386	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
 348	i386	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
 349	i386	kcmp			sys_kcmp
+350	i386	finit_module		sys_finit_module
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index a582bfed95bb..7c58c84b7bc8 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -319,6 +319,7 @@
 310	64	process_vm_readv	sys_process_vm_readv
 311	64	process_vm_writev	sys_process_vm_writev
 312	common	kcmp			sys_kcmp
+313	common	finit_module		sys_finit_module
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 727f0cd73921..32bc035bcd68 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -868,4 +868,5 @@ asmlinkage long sys_process_vm_writev(pid_t pid,
 
 asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type,
 			 unsigned long idx1, unsigned long idx2);
+asmlinkage long sys_finit_module(int fd, const char __user *uargs);
 #endif
diff --git a/kernel/module.c b/kernel/module.c
index 6e48c3a43599..6d2c4e4ca1f5 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -21,6 +21,7 @@
 #include <linux/ftrace_event.h>
 #include <linux/init.h>
 #include <linux/kallsyms.h>
+#include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kernel.h>
@@ -2425,18 +2426,17 @@ static inline void kmemleak_load_module(const struct module *mod,
 #endif
 
 #ifdef CONFIG_MODULE_SIG
-static int module_sig_check(struct load_info *info,
-			    const void *mod, unsigned long *_len)
+static int module_sig_check(struct load_info *info)
 {
 	int err = -ENOKEY;
-	unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1;
-	unsigned long len = *_len;
+	const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1;
+	const void *mod = info->hdr;
 
-	if (len > markerlen &&
-	    memcmp(mod + len - markerlen, MODULE_SIG_STRING, markerlen) == 0) {
+	if (info->len > markerlen &&
+	    memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) {
 		/* We truncate the module to discard the signature */
-		*_len -= markerlen;
-		err = mod_verify_sig(mod, _len);
+		info->len -= markerlen;
+		err = mod_verify_sig(mod, &info->len);
 	}
 
 	if (!err) {
@@ -2454,59 +2454,97 @@ static int module_sig_check(struct load_info *info,
 	return err;
 }
 #else /* !CONFIG_MODULE_SIG */
-static int module_sig_check(struct load_info *info,
-			    void *mod, unsigned long *len)
+static int module_sig_check(struct load_info *info)
 {
 	return 0;
 }
 #endif /* !CONFIG_MODULE_SIG */
 
-/* Sets info->hdr, info->len and info->sig_ok. */
-static int copy_and_check(struct load_info *info,
-			  const void __user *umod, unsigned long len,
-			  const char __user *uargs)
+/* Sanity checks against invalid binaries, wrong arch, weird elf version. */
+static int elf_header_check(struct load_info *info)
 {
-	int err;
-	Elf_Ehdr *hdr;
+	if (info->len < sizeof(*(info->hdr)))
+		return -ENOEXEC;
+
+	if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0
+	    || info->hdr->e_type != ET_REL
+	    || !elf_check_arch(info->hdr)
+	    || info->hdr->e_shentsize != sizeof(Elf_Shdr))
+		return -ENOEXEC;
+
+	if (info->hdr->e_shoff >= info->len
+	    || (info->hdr->e_shnum * sizeof(Elf_Shdr) >
+		info->len - info->hdr->e_shoff))
+		return -ENOEXEC;
 
-	if (len < sizeof(*hdr))
+	return 0;
+}
+
+/* Sets info->hdr and info->len. */
+static int copy_module_from_user(const void __user *umod, unsigned long len,
+				  struct load_info *info)
+{
+	info->len = len;
+	if (info->len < sizeof(*(info->hdr)))
 		return -ENOEXEC;
 
 	/* Suck in entire file: we'll want most of it. */
-	if ((hdr = vmalloc(len)) == NULL)
+	info->hdr = vmalloc(info->len);
+	if (!info->hdr)
 		return -ENOMEM;
 
-	if (copy_from_user(hdr, umod, len) != 0) {
-		err = -EFAULT;
-		goto free_hdr;
+	if (copy_from_user(info->hdr, umod, info->len) != 0) {
+		vfree(info->hdr);
+		return -EFAULT;
 	}
 
-	err = module_sig_check(info, hdr, &len);
+	return 0;
+}
+
+/* Sets info->hdr and info->len. */
+static int copy_module_from_fd(int fd, struct load_info *info)
+{
+	struct file *file;
+	int err;
+	struct kstat stat;
+	loff_t pos;
+	ssize_t bytes = 0;
+
+	file = fget(fd);
+	if (!file)
+		return -ENOEXEC;
+
+	err = vfs_getattr(file->f_vfsmnt, file->f_dentry, &stat);
 	if (err)
-		goto free_hdr;
+		goto out;
 
-	/* Sanity checks against insmoding binaries or wrong arch,
-	   weird elf version */
-	if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0
-	    || hdr->e_type != ET_REL
-	    || !elf_check_arch(hdr)
-	    || hdr->e_shentsize != sizeof(Elf_Shdr)) {
-		err = -ENOEXEC;
-		goto free_hdr;
+	if (stat.size > INT_MAX) {
+		err = -EFBIG;
+		goto out;
 	}
-
-	if (hdr->e_shoff >= len ||
-	    hdr->e_shnum * sizeof(Elf_Shdr) > len - hdr->e_shoff) {
-		err = -ENOEXEC;
-		goto free_hdr;
+	info->hdr = vmalloc(stat.size);
+	if (!info->hdr) {
+		err = -ENOMEM;
+		goto out;
 	}
 
-	info->hdr = hdr;
-	info->len = len;
-	return 0;
+	pos = 0;
+	while (pos < stat.size) {
+		bytes = kernel_read(file, pos, (char *)(info->hdr) + pos,
+				    stat.size - pos);
+		if (bytes < 0) {
+			vfree(info->hdr);
+			err = bytes;
+			goto out;
+		}
+		if (bytes == 0)
+			break;
+		pos += bytes;
+	}
+	info->len = pos;
 
-free_hdr:
-	vfree(hdr);
+out:
+	fput(file);
 	return err;
 }
 
@@ -2945,33 +2983,123 @@ static bool finished_loading(const char *name)
 	return ret;
 }
 
+/* Call module constructors. */
+static void do_mod_ctors(struct module *mod)
+{
+#ifdef CONFIG_CONSTRUCTORS
+	unsigned long i;
+
+	for (i = 0; i < mod->num_ctors; i++)
+		mod->ctors[i]();
+#endif
+}
+
+/* This is where the real work happens */
+static int do_init_module(struct module *mod)
+{
+	int ret = 0;
+
+	blocking_notifier_call_chain(&module_notify_list,
+			MODULE_STATE_COMING, mod);
+
+	/* Set RO and NX regions for core */
+	set_section_ro_nx(mod->module_core,
+				mod->core_text_size,
+				mod->core_ro_size,
+				mod->core_size);
+
+	/* Set RO and NX regions for init */
+	set_section_ro_nx(mod->module_init,
+				mod->init_text_size,
+				mod->init_ro_size,
+				mod->init_size);
+
+	do_mod_ctors(mod);
+	/* Start the module */
+	if (mod->init != NULL)
+		ret = do_one_initcall(mod->init);
+	if (ret < 0) {
+		/* Init routine failed: abort.  Try to protect us from
+                   buggy refcounters. */
+		mod->state = MODULE_STATE_GOING;
+		synchronize_sched();
+		module_put(mod);
+		blocking_notifier_call_chain(&module_notify_list,
+					     MODULE_STATE_GOING, mod);
+		free_module(mod);
+		wake_up_all(&module_wq);
+		return ret;
+	}
+	if (ret > 0) {
+		printk(KERN_WARNING
+"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n"
+"%s: loading module anyway...\n",
+		       __func__, mod->name, ret,
+		       __func__);
+		dump_stack();
+	}
+
+	/* Now it's a first class citizen! */
+	mod->state = MODULE_STATE_LIVE;
+	blocking_notifier_call_chain(&module_notify_list,
+				     MODULE_STATE_LIVE, mod);
+
+	/* We need to finish all async code before the module init sequence is done */
+	async_synchronize_full();
+
+	mutex_lock(&module_mutex);
+	/* Drop initial reference. */
+	module_put(mod);
+	trim_init_extable(mod);
+#ifdef CONFIG_KALLSYMS
+	mod->num_symtab = mod->core_num_syms;
+	mod->symtab = mod->core_symtab;
+	mod->strtab = mod->core_strtab;
+#endif
+	unset_module_init_ro_nx(mod);
+	module_free(mod, mod->module_init);
+	mod->module_init = NULL;
+	mod->init_size = 0;
+	mod->init_ro_size = 0;
+	mod->init_text_size = 0;
+	mutex_unlock(&module_mutex);
+	wake_up_all(&module_wq);
+
+	return 0;
+}
+
+static int may_init_module(void)
+{
+	if (!capable(CAP_SYS_MODULE) || modules_disabled)
+		return -EPERM;
+
+	return 0;
+}
+
 /* Allocate and load the module: note that size of section 0 is always
    zero, and we rely on this for optional sections. */
-static struct module *load_module(void __user *umod,
-				  unsigned long len,
-				  const char __user *uargs)
+static int load_module(struct load_info *info, const char __user *uargs)
 {
-	struct load_info info = { NULL, };
 	struct module *mod, *old;
 	long err;
 
-	pr_debug("load_module: umod=%p, len=%lu, uargs=%p\n",
-	       umod, len, uargs);
+	err = module_sig_check(info);
+	if (err)
+		goto free_copy;
 
-	/* Copy in the blobs from userspace, check they are vaguely sane. */
-	err = copy_and_check(&info, umod, len, uargs);
+	err = elf_header_check(info);
 	if (err)
-		return ERR_PTR(err);
+		goto free_copy;
 
 	/* Figure out module layout, and allocate all the memory. */
-	mod = layout_and_allocate(&info);
+	mod = layout_and_allocate(info);
 	if (IS_ERR(mod)) {
 		err = PTR_ERR(mod);
 		goto free_copy;
 	}
 
 #ifdef CONFIG_MODULE_SIG
-	mod->sig_ok = info.sig_ok;
+	mod->sig_ok = info->sig_ok;
 	if (!mod->sig_ok)
 		add_taint_module(mod, TAINT_FORCED_MODULE);
 #endif
@@ -2983,25 +3111,25 @@ static struct module *load_module(void __user *umod,
 
 	/* Now we've got everything in the final locations, we can
 	 * find optional sections. */
-	find_module_sections(mod, &info);
+	find_module_sections(mod, info);
 
 	err = check_module_license_and_versions(mod);
 	if (err)
 		goto free_unload;
 
 	/* Set up MODINFO_ATTR fields */
-	setup_modinfo(mod, &info);
+	setup_modinfo(mod, info);
 
 	/* Fix up syms, so that st_value is a pointer to location. */
-	err = simplify_symbols(mod, &info);
+	err = simplify_symbols(mod, info);
 	if (err < 0)
 		goto free_modinfo;
 
-	err = apply_relocations(mod, &info);
+	err = apply_relocations(mod, info);
 	if (err < 0)
 		goto free_modinfo;
 
-	err = post_relocation(mod, &info);
+	err = post_relocation(mod, info);
 	if (err < 0)
 		goto free_modinfo;
 
@@ -3041,14 +3169,14 @@ again:
 	}
 
 	/* This has to be done once we're sure module name is unique. */
-	dynamic_debug_setup(info.debug, info.num_debug);
+	dynamic_debug_setup(info->debug, info->num_debug);
 
 	/* Find duplicate symbols */
 	err = verify_export_symbols(mod);
 	if (err < 0)
 		goto ddebug;
 
-	module_bug_finalize(info.hdr, info.sechdrs, mod);
+	module_bug_finalize(info->hdr, info->sechdrs, mod);
 	list_add_rcu(&mod->list, &modules);
 	mutex_unlock(&module_mutex);
 
@@ -3059,16 +3187,17 @@ again:
 		goto unlink;
 
 	/* Link in to syfs. */
-	err = mod_sysfs_setup(mod, &info, mod->kp, mod->num_kp);
+	err = mod_sysfs_setup(mod, info, mod->kp, mod->num_kp);
 	if (err < 0)
 		goto unlink;
 
 	/* Get rid of temporary copy. */
-	free_copy(&info);
+	free_copy(info);
 
 	/* Done! */
 	trace_module_load(mod);
-	return mod;
+
+	return do_init_module(mod);
 
  unlink:
 	mutex_lock(&module_mutex);
@@ -3077,7 +3206,7 @@ again:
 	module_bug_cleanup(mod);
 	wake_up_all(&module_wq);
  ddebug:
-	dynamic_debug_remove(info.debug);
+	dynamic_debug_remove(info->debug);
  unlock:
 	mutex_unlock(&module_mutex);
 	synchronize_sched();
@@ -3089,106 +3218,48 @@ again:
  free_unload:
 	module_unload_free(mod);
  free_module:
-	module_deallocate(mod, &info);
+	module_deallocate(mod, info);
  free_copy:
-	free_copy(&info);
-	return ERR_PTR(err);
-}
-
-/* Call module constructors. */
-static void do_mod_ctors(struct module *mod)
-{
-#ifdef CONFIG_CONSTRUCTORS
-	unsigned long i;
-
-	for (i = 0; i < mod->num_ctors; i++)
-		mod->ctors[i]();
-#endif
+	free_copy(info);
+	return err;
 }
 
-/* This is where the real work happens */
 SYSCALL_DEFINE3(init_module, void __user *, umod,
 		unsigned long, len, const char __user *, uargs)
 {
-	struct module *mod;
-	int ret = 0;
-
-	/* Must have permission */
-	if (!capable(CAP_SYS_MODULE) || modules_disabled)
-		return -EPERM;
+	int err;
+	struct load_info info = { };
 
-	/* Do all the hard work */
-	mod = load_module(umod, len, uargs);
-	if (IS_ERR(mod))
-		return PTR_ERR(mod);
+	err = may_init_module();
+	if (err)
+		return err;
 
-	blocking_notifier_call_chain(&module_notify_list,
-			MODULE_STATE_COMING, mod);
+	pr_debug("init_module: umod=%p, len=%lu, uargs=%p\n",
+	       umod, len, uargs);
 
-	/* Set RO and NX regions for core */
-	set_section_ro_nx(mod->module_core,
-				mod->core_text_size,
-				mod->core_ro_size,
-				mod->core_size);
+	err = copy_module_from_user(umod, len, &info);
+	if (err)
+		return err;
 
-	/* Set RO and NX regions for init */
-	set_section_ro_nx(mod->module_init,
-				mod->init_text_size,
-				mod->init_ro_size,
-				mod->init_size);
+	return load_module(&info, uargs);
+}
 
-	do_mod_ctors(mod);
-	/* Start the module */
-	if (mod->init != NULL)
-		ret = do_one_initcall(mod->init);
-	if (ret < 0) {
-		/* Init routine failed: abort.  Try to protect us from
-                   buggy refcounters. */
-		mod->state = MODULE_STATE_GOING;
-		synchronize_sched();
-		module_put(mod);
-		blocking_notifier_call_chain(&module_notify_list,
-					     MODULE_STATE_GOING, mod);
-		free_module(mod);
-		wake_up_all(&module_wq);
-		return ret;
-	}
-	if (ret > 0) {
-		printk(KERN_WARNING
-"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n"
-"%s: loading module anyway...\n",
-		       __func__, mod->name, ret,
-		       __func__);
-		dump_stack();
-	}
+SYSCALL_DEFINE2(finit_module, int, fd, const char __user *, uargs)
+{
+	int err;
+	struct load_info info = { };
 
-	/* Now it's a first class citizen! */
-	mod->state = MODULE_STATE_LIVE;
-	blocking_notifier_call_chain(&module_notify_list,
-				     MODULE_STATE_LIVE, mod);
+	err = may_init_module();
+	if (err)
+		return err;
 
-	/* We need to finish all async code before the module init sequence is done */
-	async_synchronize_full();
+	pr_debug("finit_module: fd=%d, uargs=%p\n", fd, uargs);
 
-	mutex_lock(&module_mutex);
-	/* Drop initial reference. */
-	module_put(mod);
-	trim_init_extable(mod);
-#ifdef CONFIG_KALLSYMS
-	mod->num_symtab = mod->core_num_syms;
-	mod->symtab = mod->core_symtab;
-	mod->strtab = mod->core_strtab;
-#endif
-	unset_module_init_ro_nx(mod);
-	module_free(mod, mod->module_init);
-	mod->module_init = NULL;
-	mod->init_size = 0;
-	mod->init_ro_size = 0;
-	mod->init_text_size = 0;
-	mutex_unlock(&module_mutex);
-	wake_up_all(&module_wq);
+	err = copy_module_from_fd(fd, &info);
+	if (err)
+		return err;
 
-	return 0;
+	return load_module(&info, uargs);
 }
 
 static inline int within(unsigned long addr, void *start, unsigned long size)
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index dbff751e4086..395084d4ce16 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -25,6 +25,7 @@ cond_syscall(sys_swapoff);
 cond_syscall(sys_kexec_load);
 cond_syscall(compat_sys_kexec_load);
 cond_syscall(sys_init_module);
+cond_syscall(sys_finit_module);
 cond_syscall(sys_delete_module);
 cond_syscall(sys_socketpair);
 cond_syscall(sys_bind);
-- 
cgit v1.2.3-55-g7522


From 2f3238aebedb243804f58d62d57244edec4149b2 Mon Sep 17 00:00:00 2001
From: Rusty Russell
Date: Mon, 22 Oct 2012 18:09:41 +1030
Subject: module: add flags arg to sys_finit_module()

Thanks to Michael Kerrisk for keeping us honest.  These flags are actually
useful for eliminating the only case where kmod has to mangle a module's
internals: for overriding module versioning.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Lucas De Marchi <lucas.demarchi@profusion.mobi>
Acked-by: Kees Cook <keescook@chromium.org>
---
 include/linux/syscalls.h    |  2 +-
 include/uapi/linux/module.h |  8 ++++++++
 kernel/module.c             | 40 ++++++++++++++++++++++++++--------------
 3 files changed, 35 insertions(+), 15 deletions(-)
 create mode 100644 include/uapi/linux/module.h

(limited to 'include')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 32bc035bcd68..8cf7b508cb50 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -868,5 +868,5 @@ asmlinkage long sys_process_vm_writev(pid_t pid,
 
 asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type,
 			 unsigned long idx1, unsigned long idx2);
-asmlinkage long sys_finit_module(int fd, const char __user *uargs);
+asmlinkage long sys_finit_module(int fd, const char __user *uargs, int flags);
 #endif
diff --git a/include/uapi/linux/module.h b/include/uapi/linux/module.h
new file mode 100644
index 000000000000..38da4258b12f
--- /dev/null
+++ b/include/uapi/linux/module.h
@@ -0,0 +1,8 @@
+#ifndef _UAPI_LINUX_MODULE_H
+#define _UAPI_LINUX_MODULE_H
+
+/* Flags for sys_finit_module: */
+#define MODULE_INIT_IGNORE_MODVERSIONS	1
+#define MODULE_INIT_IGNORE_VERMAGIC	2
+
+#endif /* _UAPI_LINUX_MODULE_H */
diff --git a/kernel/module.c b/kernel/module.c
index 6d2c4e4ca1f5..1395ca382fb5 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -60,6 +60,7 @@
 #include <linux/pfn.h>
 #include <linux/bsearch.h>
 #include <linux/fips.h>
+#include <uapi/linux/module.h>
 #include "module-internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -2553,7 +2554,7 @@ static void free_copy(struct load_info *info)
 	vfree(info->hdr);
 }
 
-static int rewrite_section_headers(struct load_info *info)
+static int rewrite_section_headers(struct load_info *info, int flags)
 {
 	unsigned int i;
 
@@ -2581,7 +2582,10 @@ static int rewrite_section_headers(struct load_info *info)
 	}
 
 	/* Track but don't keep modinfo and version sections. */
-	info->index.vers = find_sec(info, "__versions");
+	if (flags & MODULE_INIT_IGNORE_MODVERSIONS)
+		info->index.vers = 0; /* Pretend no __versions section! */
+	else
+		info->index.vers = find_sec(info, "__versions");
 	info->index.info = find_sec(info, ".modinfo");
 	info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC;
 	info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC;
@@ -2596,7 +2600,7 @@ static int rewrite_section_headers(struct load_info *info)
  * Return the temporary module pointer (we'll replace it with the final
  * one when we move the module sections around).
  */
-static struct module *setup_load_info(struct load_info *info)
+static struct module *setup_load_info(struct load_info *info, int flags)
 {
 	unsigned int i;
 	int err;
@@ -2607,7 +2611,7 @@ static struct module *setup_load_info(struct load_info *info)
 	info->secstrings = (void *)info->hdr
 		+ info->sechdrs[info->hdr->e_shstrndx].sh_offset;
 
-	err = rewrite_section_headers(info);
+	err = rewrite_section_headers(info, flags);
 	if (err)
 		return ERR_PTR(err);
 
@@ -2645,11 +2649,14 @@ static struct module *setup_load_info(struct load_info *info)
 	return mod;
 }
 
-static int check_modinfo(struct module *mod, struct load_info *info)
+static int check_modinfo(struct module *mod, struct load_info *info, int flags)
 {
 	const char *modmagic = get_modinfo(info, "vermagic");
 	int err;
 
+	if (flags & MODULE_INIT_IGNORE_VERMAGIC)
+		modmagic = NULL;
+
 	/* This is allowed: modprobe --force will invalidate it. */
 	if (!modmagic) {
 		err = try_to_force_load(mod, "bad vermagic");
@@ -2885,18 +2892,18 @@ int __weak module_frob_arch_sections(Elf_Ehdr *hdr,
 	return 0;
 }
 
-static struct module *layout_and_allocate(struct load_info *info)
+static struct module *layout_and_allocate(struct load_info *info, int flags)
 {
 	/* Module within temporary copy. */
 	struct module *mod;
 	Elf_Shdr *pcpusec;
 	int err;
 
-	mod = setup_load_info(info);
+	mod = setup_load_info(info, flags);
 	if (IS_ERR(mod))
 		return mod;
 
-	err = check_modinfo(mod, info);
+	err = check_modinfo(mod, info, flags);
 	if (err)
 		return ERR_PTR(err);
 
@@ -3078,7 +3085,8 @@ static int may_init_module(void)
 
 /* Allocate and load the module: note that size of section 0 is always
    zero, and we rely on this for optional sections. */
-static int load_module(struct load_info *info, const char __user *uargs)
+static int load_module(struct load_info *info, const char __user *uargs,
+		       int flags)
 {
 	struct module *mod, *old;
 	long err;
@@ -3092,7 +3100,7 @@ static int load_module(struct load_info *info, const char __user *uargs)
 		goto free_copy;
 
 	/* Figure out module layout, and allocate all the memory. */
-	mod = layout_and_allocate(info);
+	mod = layout_and_allocate(info, flags);
 	if (IS_ERR(mod)) {
 		err = PTR_ERR(mod);
 		goto free_copy;
@@ -3241,10 +3249,10 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 	if (err)
 		return err;
 
-	return load_module(&info, uargs);
+	return load_module(&info, uargs, 0);
 }
 
-SYSCALL_DEFINE2(finit_module, int, fd, const char __user *, uargs)
+SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 {
 	int err;
 	struct load_info info = { };
@@ -3253,13 +3261,17 @@ SYSCALL_DEFINE2(finit_module, int, fd, const char __user *, uargs)
 	if (err)
 		return err;
 
-	pr_debug("finit_module: fd=%d, uargs=%p\n", fd, uargs);
+	pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags);
+
+	if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS
+		      |MODULE_INIT_IGNORE_VERMAGIC))
+		return -EINVAL;
 
 	err = copy_module_from_fd(fd, &info);
 	if (err)
 		return err;
 
-	return load_module(&info, uargs);
+	return load_module(&info, uargs, flags);
 }
 
 static inline int within(unsigned long addr, void *start, unsigned long size)
-- 
cgit v1.2.3-55-g7522


From 2e72d51b4ac32989496870cd8171b3682fea1839 Mon Sep 17 00:00:00 2001
From: Kees Cook
Date: Tue, 16 Oct 2012 07:32:07 +1030
Subject: security: introduce kernel_module_from_file hook

Now that kernel module origins can be reasoned about, provide a hook to
the LSMs to make policy decisions about the module file. This will let
Chrome OS enforce that loadable kernel modules can only come from its
read-only hash-verified root filesystem. Other LSMs can, for example,
read extended attributes for signatures, etc.

Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: Eric Paris <eparis@redhat.com>
Acked-by: Mimi Zohar <zohar@us.ibm.com>
Acked-by: James Morris <james.l.morris@oracle.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/security.h | 13 +++++++++++++
 kernel/module.c          | 11 +++++++++++
 security/capability.c    |  6 ++++++
 security/security.c      |  5 +++++
 4 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/include/linux/security.h b/include/linux/security.h
index 05e88bdcf7d9..0f6afc657f77 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -694,6 +694,12 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	userspace to load a kernel module with the given name.
  *	@kmod_name name of the module requested by the kernel
  *	Return 0 if successful.
+ * @kernel_module_from_file:
+ *	Load a kernel module from userspace.
+ *	@file contains the file structure pointing to the file containing
+ *	the kernel module to load. If the module is being loaded from a blob,
+ *	this argument will be NULL.
+ *	Return 0 if permission is granted.
  * @task_fix_setuid:
  *	Update the module's state after setting one or more of the user
  *	identity attributes of the current process.  The @flags parameter
@@ -1508,6 +1514,7 @@ struct security_operations {
 	int (*kernel_act_as)(struct cred *new, u32 secid);
 	int (*kernel_create_files_as)(struct cred *new, struct inode *inode);
 	int (*kernel_module_request)(char *kmod_name);
+	int (*kernel_module_from_file)(struct file *file);
 	int (*task_fix_setuid) (struct cred *new, const struct cred *old,
 				int flags);
 	int (*task_setpgid) (struct task_struct *p, pid_t pgid);
@@ -1765,6 +1772,7 @@ void security_transfer_creds(struct cred *new, const struct cred *old);
 int security_kernel_act_as(struct cred *new, u32 secid);
 int security_kernel_create_files_as(struct cred *new, struct inode *inode);
 int security_kernel_module_request(char *kmod_name);
+int security_kernel_module_from_file(struct file *file);
 int security_task_fix_setuid(struct cred *new, const struct cred *old,
 			     int flags);
 int security_task_setpgid(struct task_struct *p, pid_t pgid);
@@ -2278,6 +2286,11 @@ static inline int security_kernel_module_request(char *kmod_name)
 	return 0;
 }
 
+static inline int security_kernel_module_from_file(struct file *file)
+{
+	return 0;
+}
+
 static inline int security_task_fix_setuid(struct cred *new,
 					   const struct cred *old,
 					   int flags)
diff --git a/kernel/module.c b/kernel/module.c
index 1395ca382fb5..a1d2ed8bab93 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -29,6 +29,7 @@
 #include <linux/vmalloc.h>
 #include <linux/elf.h>
 #include <linux/proc_fs.h>
+#include <linux/security.h>
 #include <linux/seq_file.h>
 #include <linux/syscalls.h>
 #include <linux/fcntl.h>
@@ -2485,10 +2486,16 @@ static int elf_header_check(struct load_info *info)
 static int copy_module_from_user(const void __user *umod, unsigned long len,
 				  struct load_info *info)
 {
+	int err;
+
 	info->len = len;
 	if (info->len < sizeof(*(info->hdr)))
 		return -ENOEXEC;
 
+	err = security_kernel_module_from_file(NULL);
+	if (err)
+		return err;
+
 	/* Suck in entire file: we'll want most of it. */
 	info->hdr = vmalloc(info->len);
 	if (!info->hdr)
@@ -2515,6 +2522,10 @@ static int copy_module_from_fd(int fd, struct load_info *info)
 	if (!file)
 		return -ENOEXEC;
 
+	err = security_kernel_module_from_file(file);
+	if (err)
+		goto out;
+
 	err = vfs_getattr(file->f_vfsmnt, file->f_dentry, &stat);
 	if (err)
 		goto out;
diff --git a/security/capability.c b/security/capability.c
index b14a30c234b8..0fe5a026aef8 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -395,6 +395,11 @@ static int cap_kernel_module_request(char *kmod_name)
 	return 0;
 }
 
+static int cap_kernel_module_from_file(struct file *file)
+{
+	return 0;
+}
+
 static int cap_task_setpgid(struct task_struct *p, pid_t pgid)
 {
 	return 0;
@@ -967,6 +972,7 @@ void __init security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, kernel_act_as);
 	set_to_cap_if_null(ops, kernel_create_files_as);
 	set_to_cap_if_null(ops, kernel_module_request);
+	set_to_cap_if_null(ops, kernel_module_from_file);
 	set_to_cap_if_null(ops, task_fix_setuid);
 	set_to_cap_if_null(ops, task_setpgid);
 	set_to_cap_if_null(ops, task_getpgid);
diff --git a/security/security.c b/security/security.c
index 8dcd4ae10a5f..ce88630de15d 100644
--- a/security/security.c
+++ b/security/security.c
@@ -820,6 +820,11 @@ int security_kernel_module_request(char *kmod_name)
 	return security_ops->kernel_module_request(kmod_name);
 }
 
+int security_kernel_module_from_file(struct file *file)
+{
+	return security_ops->kernel_module_from_file(file);
+}
+
 int security_task_fix_setuid(struct cred *new, const struct cred *old,
 			     int flags)
 {
-- 
cgit v1.2.3-55-g7522


From 1625cee56f8e6193b5a0809a414dfa395bd9cf1e Mon Sep 17 00:00:00 2001
From: Kees Cook
Date: Tue, 16 Oct 2012 12:40:03 +1030
Subject: add finit_module syscall to asm-generic

This adds the finit_module syscall to the generic syscall list.

Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/uapi/asm-generic/unistd.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 6e595ba545f4..2c531f478410 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -690,9 +690,11 @@ __SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
           compat_sys_process_vm_writev)
 #define __NR_kcmp 272
 __SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 273
+__SYSCALL(__NR_finit_module, sys_finit_module)
 
 #undef __NR_syscalls
-#define __NR_syscalls 273
+#define __NR_syscalls 274
 
 /*
  * All syscalls below here should go away really,
-- 
cgit v1.2.3-55-g7522


From fdf90729e57812cb12d7938e2dee7c71e875fb08 Mon Sep 17 00:00:00 2001
From: Mimi Zohar
Date: Tue, 16 Oct 2012 12:40:08 +1030
Subject: ima: support new kernel module syscall

With the addition of the new kernel module syscall, which defines two
arguments - a file descriptor to the kernel module and a pointer to a NULL
terminated string of module arguments - it is now possible to measure and
appraise kernel modules like any other file on the file system.

This patch adds support to measure and appraise kernel modules in an
extensible and consistent manner.

To support filesystems without extended attribute support, additional
patches could pass the signature as the first parameter.

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 Documentation/ABI/testing/ima_policy |  3 ++-
 include/linux/ima.h                  |  6 ++++++
 security/integrity/ima/ima.h         |  2 +-
 security/integrity/ima/ima_api.c     |  4 ++--
 security/integrity/ima/ima_main.c    | 21 +++++++++++++++++++++
 security/integrity/ima/ima_policy.c  |  3 +++
 security/security.c                  |  7 ++++++-
 7 files changed, 41 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy
index 986946613542..ec0a38ef3145 100644
--- a/Documentation/ABI/testing/ima_policy
+++ b/Documentation/ABI/testing/ima_policy
@@ -23,7 +23,7 @@ Description:
 			lsm:	[[subj_user=] [subj_role=] [subj_type=]
 				 [obj_user=] [obj_role=] [obj_type=]]
 
-		base: 	func:= [BPRM_CHECK][FILE_MMAP][FILE_CHECK]
+		base: 	func:= [BPRM_CHECK][FILE_MMAP][FILE_CHECK][MODULE_CHECK]
 			mask:= [MAY_READ] [MAY_WRITE] [MAY_APPEND] [MAY_EXEC]
 			fsmagic:= hex value
 			uid:= decimal value
@@ -53,6 +53,7 @@ Description:
 			measure func=BPRM_CHECK
 			measure func=FILE_MMAP mask=MAY_EXEC
 			measure func=FILE_CHECK mask=MAY_READ uid=0
+			measure func=MODULE_CHECK uid=0
 			appraise fowner=0
 
 		The default policy measures all executables in bprm_check,
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 2c7223d7e73b..86c361e947b9 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -18,6 +18,7 @@ extern int ima_bprm_check(struct linux_binprm *bprm);
 extern int ima_file_check(struct file *file, int mask);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
+extern int ima_module_check(struct file *file);
 
 #else
 static inline int ima_bprm_check(struct linux_binprm *bprm)
@@ -40,6 +41,11 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot)
 	return 0;
 }
 
+static inline int ima_module_check(struct file *file)
+{
+	return 0;
+}
+
 #endif /* CONFIG_IMA_H */
 
 #ifdef CONFIG_IMA_APPRAISE
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 6ee8826662cc..3b2adb794f15 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -127,7 +127,7 @@ struct integrity_iint_cache *integrity_iint_insert(struct inode *inode);
 struct integrity_iint_cache *integrity_iint_find(struct inode *inode);
 
 /* IMA policy related functions */
-enum ima_hooks { FILE_CHECK = 1, FILE_MMAP, BPRM_CHECK, POST_SETATTR };
+enum ima_hooks { FILE_CHECK = 1, FILE_MMAP, BPRM_CHECK, MODULE_CHECK, POST_SETATTR };
 
 int ima_match_policy(struct inode *inode, enum ima_hooks func, int mask,
 		     int flags);
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index b356884fb3ef..0cea3db21657 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -100,12 +100,12 @@ err_out:
  * ima_get_action - appraise & measure decision based on policy.
  * @inode: pointer to inode to measure
  * @mask: contains the permission mask (MAY_READ, MAY_WRITE, MAY_EXECUTE)
- * @function: calling function (FILE_CHECK, BPRM_CHECK, FILE_MMAP)
+ * @function: calling function (FILE_CHECK, BPRM_CHECK, FILE_MMAP, MODULE_CHECK)
  *
  * The policy is defined in terms of keypairs:
  * 		subj=, obj=, type=, func=, mask=, fsmagic=
  *	subj,obj, and type: are LSM specific.
- * 	func: FILE_CHECK | BPRM_CHECK | FILE_MMAP
+ * 	func: FILE_CHECK | BPRM_CHECK | FILE_MMAP | MODULE_CHECK
  * 	mask: contains the permission mask
  *	fsmagic: hex value
  *
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 73c9a268253e..45de18e9a6f2 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -280,6 +280,27 @@ int ima_file_check(struct file *file, int mask)
 }
 EXPORT_SYMBOL_GPL(ima_file_check);
 
+/**
+ * ima_module_check - based on policy, collect/store/appraise measurement.
+ * @file: pointer to the file to be measured/appraised
+ *
+ * Measure/appraise kernel modules based on policy.
+ *
+ * Always return 0 and audit dentry_open failures.
+ * Return code is based upon measurement appraisal.
+ */
+int ima_module_check(struct file *file)
+{
+	int rc;
+
+	if (!file)
+		rc = INTEGRITY_UNKNOWN;
+	else
+		rc = process_measurement(file, file->f_dentry->d_name.name,
+					 MAY_EXEC, MODULE_CHECK);
+	return (ima_appraise & IMA_APPRAISE_ENFORCE) ? rc : 0;
+}
+
 static int __init init_ima(void)
 {
 	int error;
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index c7dacd2eab7a..af7d182d5a46 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -80,6 +80,7 @@ static struct ima_rule_entry default_rules[] = {
 	 .flags = IMA_FUNC | IMA_MASK},
 	{.action = MEASURE,.func = FILE_CHECK,.mask = MAY_READ,.uid = GLOBAL_ROOT_UID,
 	 .flags = IMA_FUNC | IMA_MASK | IMA_UID},
+	{.action = MEASURE,.func = MODULE_CHECK, .flags = IMA_FUNC},
 };
 
 static struct ima_rule_entry default_appraise_rules[] = {
@@ -401,6 +402,8 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 			/* PATH_CHECK is for backwards compat */
 			else if (strcmp(args[0].from, "PATH_CHECK") == 0)
 				entry->func = FILE_CHECK;
+			else if (strcmp(args[0].from, "MODULE_CHECK") == 0)
+				entry->func = MODULE_CHECK;
 			else if (strcmp(args[0].from, "FILE_MMAP") == 0)
 				entry->func = FILE_MMAP;
 			else if (strcmp(args[0].from, "BPRM_CHECK") == 0)
diff --git a/security/security.c b/security/security.c
index ce88630de15d..daa97f4ac9d1 100644
--- a/security/security.c
+++ b/security/security.c
@@ -822,7 +822,12 @@ int security_kernel_module_request(char *kmod_name)
 
 int security_kernel_module_from_file(struct file *file)
 {
-	return security_ops->kernel_module_from_file(file);
+	int ret;
+
+	ret = security_ops->kernel_module_from_file(file);
+	if (ret)
+		return ret;
+	return ima_module_check(file);
 }
 
 int security_task_fix_setuid(struct cred *new, const struct cred *old,
-- 
cgit v1.2.3-55-g7522


From 6f33d58794ef4cef4b2c706029810f9688bd3026 Mon Sep 17 00:00:00 2001
From: Rusty Russell
Date: Thu, 22 Nov 2012 12:30:25 +1030
Subject: __UNIQUE_ID()

Jan Beulich points out __COUNTER__ (gcc 4.3 and above), so let's use
that to create unique ids.  This is better than __LINE__ which we use
today, so provide a wrapper.

Stanislaw Gruszka <sgruszka@redhat.com> reported that some module parameters
start with a digit, so we need to prepend when we for the unique id.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Jan Beulich <jbeulich@suse.com>
---
 include/linux/compiler-gcc4.h | 2 ++
 include/linux/compiler.h      | 9 +++++++++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index 412bc6c2b023..56c802cba7f6 100644
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -31,6 +31,8 @@
 
 #define __linktime_error(message) __attribute__((__error__(message)))
 
+#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
 #if __GNUC_MINOR__ >= 5
 /*
  * Mark a position in code as unreachable.  This can be used to
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index f430e4162f41..5f45335e1ac7 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -42,6 +42,10 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # define __rcu
 #endif
 
+/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
+#define ___PASTE(a,b) a##b
+#define __PASTE(a,b) ___PASTE(a,b)
+
 #ifdef __KERNEL__
 
 #ifdef __GNUC__
@@ -164,6 +168,11 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
     (typeof(ptr)) (__ptr + (off)); })
 #endif
 
+/* Not-quite-unique ID. */
+#ifndef __UNIQUE_ID
+# define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
+#endif
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
-- 
cgit v1.2.3-55-g7522


From 34182eea36fc1d70d748b0947c873314980ba806 Mon Sep 17 00:00:00 2001
From: Rusty Russell
Date: Thu, 22 Nov 2012 12:30:25 +1030
Subject: moduleparam: use __UNIQUE_ID()

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/moduleparam.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index d6a58065c09c..137b4198fc03 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -16,17 +16,15 @@
 /* Chosen so that structs with an unsigned long line up. */
 #define MAX_PARAM_PREFIX_LEN (64 - sizeof(unsigned long))
 
-#define ___module_cat(a,b) __mod_ ## a ## b
-#define __module_cat(a,b) ___module_cat(a,b)
 #ifdef MODULE
 #define __MODULE_INFO(tag, name, info)					  \
-static const char __module_cat(name,__LINE__)[]				  \
+static const char __UNIQUE_ID(name)[]					  \
   __used __attribute__((section(".modinfo"), unused, aligned(1)))	  \
   = __stringify(tag) "=" info
 #else  /* !MODULE */
 /* This struct is here for syntactic coherency, it is not used */
 #define __MODULE_INFO(tag, name, info)					  \
-  struct __module_cat(name,__LINE__) {}
+  struct __UNIQUE_ID(name) {}
 #endif
 #define __MODULE_PARM_TYPE(name, _type)					  \
   __MODULE_INFO(parmtype, name##type, #name ":" _type)
-- 
cgit v1.2.3-55-g7522


From facc0a6bd494ce21e31b34fc355ecf702518272b Mon Sep 17 00:00:00 2001
From: David Howells
Date: Wed, 5 Dec 2012 11:55:28 +1030
Subject: ASN.1: Define indefinite length marker constant

Define a constant to hold the marker value seen in an indefinite-length
element.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/asn1.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/asn1.h b/include/linux/asn1.h
index 5c3f4e4b9a23..eed6982860ba 100644
--- a/include/linux/asn1.h
+++ b/include/linux/asn1.h
@@ -64,4 +64,6 @@ enum asn1_tag {
 	ASN1_LONG_TAG	= 31	/* Long form tag */
 };
 
+#define ASN1_INDEFINITE_LENGTH 0x80
+
 #endif /* _LINUX_ASN1_H */
-- 
cgit v1.2.3-55-g7522


From 8349e5aeaadd160b7cce554a62a05be4b2d894aa Mon Sep 17 00:00:00 2001
From: Jeff Garzik
Date: Fri, 14 Dec 2012 09:34:01 -0500
Subject: Revert "libata: check SATA_SETTINGS log with HW Feature Ctrl"

This reverts commit de90cd71f68e947d3bd6c3f2ef5731ead010a768.

Shane Huang writes:

  Please suspend this patch because I just received two new
  DevSlp drives but found word 78 bit 5 is _not_ set.

  I'm checking with the drive vendor whether he gave me
  the wrong information. If bit 5 is not the necessary and
  sufficient condition, I will implement another patch to
  replace ata_device->sata_settings into ->devslp_timing.

Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/libata-core.c | 3 ++-
 include/linux/ata.h       | 1 -
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 47d59616fe3d..9e8b99af400d 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2331,8 +2331,9 @@ int ata_dev_configure(struct ata_device *dev)
 
 		/* Obtain SATA Settings page from Identify Device Data Log,
 		 * which contains DevSlp timing variables etc.
+		 * Exclude old devices with ata_id_has_ncq()
 		 */
-		if (ata_id_has_hw_feature_ctrl(dev->id)) {
+		if (ata_id_has_ncq(dev->id)) {
 			err_mask = ata_read_log_page(dev,
 						     ATA_LOG_SATA_ID_DEV_DATA,
 						     ATA_LOG_SATA_SETTINGS,
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 18cbb93fdbca..408da9502177 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -593,7 +593,6 @@ static inline int ata_is_data(u8 prot)
 #define ata_id_cdb_intr(id)	(((id)[ATA_ID_CONFIG] & 0x60) == 0x20)
 #define ata_id_has_da(id)	((id)[ATA_ID_SATA_CAPABILITY_2] & (1 << 4))
 #define ata_id_has_devslp(id)	((id)[ATA_ID_FEATURE_SUPP] & (1 << 8))
-#define ata_id_has_hw_feature_ctrl(id)	((id)[ATA_ID_FEATURE_SUPP] & (1 << 5))
 
 static inline bool ata_id_has_hipm(const u16 *id)
 {
-- 
cgit v1.2.3-55-g7522


From 278a334cbc96d3da66d56235b8ce84081e9a1892 Mon Sep 17 00:00:00 2001
From: Alex Deucher
Date: Thu, 13 Dec 2012 12:27:28 -0500
Subject: drm/radeon: enable the async DMA rings in the CS ioctl

This enables the functionality added in the previous
patches.  Userspace acceleration drivers can use the
CS ioctl to submit command buffers to the async DMA
rings.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_cs.c | 12 ++++++++++++
 include/uapi/drm/radeon_drm.h      |  1 +
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 1b32a5ab972d..396baba0141a 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -112,6 +112,18 @@ static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority
 		} else
 			p->ring = RADEON_RING_TYPE_GFX_INDEX;
 		break;
+	case RADEON_CS_RING_DMA:
+		if (p->rdev->family >= CHIP_CAYMAN) {
+			if (p->priority > 0)
+				p->ring = R600_RING_TYPE_DMA_INDEX;
+			else
+				p->ring = CAYMAN_RING_TYPE_DMA1_INDEX;
+		} else if (p->rdev->family >= CHIP_R600) {
+			p->ring = R600_RING_TYPE_DMA_INDEX;
+		} else {
+			return -EINVAL;
+		}
+		break;
 	}
 	return 0;
 }
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 5645a878faec..eeda91774c8a 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -917,6 +917,7 @@ struct drm_radeon_gem_va {
 /* The second dword of RADEON_CHUNK_ID_FLAGS is a uint32 that sets the ring type */
 #define RADEON_CS_RING_GFX          0
 #define RADEON_CS_RING_COMPUTE      1
+#define RADEON_CS_RING_DMA          2
 /* The third dword of RADEON_CHUNK_ID_FLAGS is a sint32 that sets the priority */
 /* 0 = normal, + = higher priority, - = lower priority */
 
-- 
cgit v1.2.3-55-g7522


From cb471f14b5eebfed22bb9f2d0f06601f171c574a Mon Sep 17 00:00:00 2001
From: Eunchul Kim
Date: Fri, 14 Dec 2012 18:10:31 +0900
Subject: drm/exynos: add ipp subsystem

This patch adds Image Post Processing(IPP) support for exynos drm driver.

IPP supports image scaler/rotator and input/output DMA operations
using IPP subsystem framework to control FIMC, Rotator and GSC hardware
and supports some user interfaces for user side.

And each IPP-based drivers support Memory to Memory operations
with various converting. And in case of FIMC hardware, it also supports
Writeback and Display output operations through local path.

Features:
- Memory to Memory operation support.
- Various pixel formats support.
- Image scaling support.
- Color Space Conversion support.
- Image crop operation support.
- Rotate operation support to 90, 180 or 270 degree.
- Flip operation support to vertical, horizontal or both.
- Writeback operation support to display blended image of FIMD fifo on screen

A summary to IPP Subsystem operations:
First of all, user should get property capabilities from IPP subsystem
and set these properties to hardware registers for desired operations.
The properties could be pixel format, position, rotation degree and
flip operation.

And next, user should set source and destination buffer data using
DRM_EXYNOS_IPP_QUEUE_BUF ioctl command with gem handles to source and
destinition buffers.

And next, user can control user-desired hardware with desired operations
such as play, stop, pause and resume controls.

And finally, user can aware of dma operation completion and also get
destination buffer that it contains user-desried result through dequeue
command.

IOCTL commands:
- DRM_EXYNOS_IPP_GET_PROPERTY
  . get ipp driver capabilitis and id.
- DRM_EXYNOS_IPP_SET_PROPERTY
  . set format, position, rotation, flip to source and destination buffers
- DRM_EXYNOS_IPP_QUEUE_BUF
  . enqueue/dequeue buffer and make event list.
- DRM_EXYNOS_IPP_CMD_CTRL
  . play/stop/pause/resume control.

Event:
- DRM_EXYNOS_IPP_EVENT
  . a event to notify dma operation completion to user side.

Basic control flow:
Open -> Get properties -> User choose desired IPP sub driver(FIMC, Rotator
or GSCALER) -> Set Property -> Create gem handle -> Enqueue to source and
destination buffers -> Command control(Play) -> Event is notified to User
-> User gets destinition buffer complated -> (Enqueue to source and
destination buffers -> Event is notified to User) * N -> Queue/Dequeue to
source and destination buffers -> Command control(Stop) -> Free gem handle
-> Close

Changelog v1 ~ v5:
- added comments, code fixups and cleanups.

Signed-off-by: Eunchul Kim <chulspro.kim@samsung.com>
Signed-off-by: Jinyoung Jeon <jy0.jeon@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
---
 drivers/gpu/drm/exynos/Kconfig          |    6 +
 drivers/gpu/drm/exynos/Makefile         |    1 +
 drivers/gpu/drm/exynos/exynos_drm_drv.c |   24 +
 drivers/gpu/drm/exynos/exynos_drm_drv.h |    7 +
 drivers/gpu/drm/exynos/exynos_drm_ipp.c | 2042 +++++++++++++++++++++++++++++++
 drivers/gpu/drm/exynos/exynos_drm_ipp.h |  266 ++++
 include/uapi/drm/exynos_drm.h           |  190 +++
 7 files changed, 2536 insertions(+)
 create mode 100644 drivers/gpu/drm/exynos/exynos_drm_ipp.c
 create mode 100644 drivers/gpu/drm/exynos/exynos_drm_ipp.h

(limited to 'include')

diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 86fb75d3fcad..80ab242e2739 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -45,3 +45,9 @@ config DRM_EXYNOS_G2D
 	depends on DRM_EXYNOS && !VIDEO_SAMSUNG_S5P_G2D
 	help
 	  Choose this option if you want to use Exynos G2D for DRM.
+
+config DRM_EXYNOS_IPP
+	bool "Exynos DRM IPP"
+	depends on DRM_EXYNOS
+	help
+	  Choose this option if you want to use IPP feature for DRM.
diff --git a/drivers/gpu/drm/exynos/Makefile b/drivers/gpu/drm/exynos/Makefile
index 26813b8a5056..6c536ce4d95b 100644
--- a/drivers/gpu/drm/exynos/Makefile
+++ b/drivers/gpu/drm/exynos/Makefile
@@ -16,5 +16,6 @@ exynosdrm-$(CONFIG_DRM_EXYNOS_HDMI)	+= exynos_hdmi.o exynos_mixer.o \
 					   exynos_drm_hdmi.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_VIDI)	+= exynos_drm_vidi.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_G2D)	+= exynos_drm_g2d.o
+exynosdrm-$(CONFIG_DRM_EXYNOS_IPP)	+= exynos_drm_ipp.o
 
 obj-$(CONFIG_DRM_EXYNOS)		+= exynosdrm.o
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 4a1168d3e907..0eb8a972e21c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -40,6 +40,7 @@
 #include "exynos_drm_vidi.h"
 #include "exynos_drm_dmabuf.h"
 #include "exynos_drm_g2d.h"
+#include "exynos_drm_ipp.h"
 #include "exynos_drm_iommu.h"
 
 #define DRIVER_NAME	"exynos"
@@ -249,6 +250,14 @@ static struct drm_ioctl_desc exynos_ioctls[] = {
 			exynos_g2d_set_cmdlist_ioctl, DRM_UNLOCKED | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(EXYNOS_G2D_EXEC,
 			exynos_g2d_exec_ioctl, DRM_UNLOCKED | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(EXYNOS_IPP_GET_PROPERTY,
+			exynos_drm_ipp_get_property, DRM_UNLOCKED | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(EXYNOS_IPP_SET_PROPERTY,
+			exynos_drm_ipp_set_property, DRM_UNLOCKED | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(EXYNOS_IPP_QUEUE_BUF,
+			exynos_drm_ipp_queue_buf, DRM_UNLOCKED | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(EXYNOS_IPP_CMD_CTRL,
+			exynos_drm_ipp_cmd_ctrl, DRM_UNLOCKED | DRM_AUTH),
 };
 
 static const struct file_operations exynos_drm_driver_fops = {
@@ -363,6 +372,12 @@ static int __init exynos_drm_init(void)
 		goto out_g2d;
 #endif
 
+#ifdef CONFIG_DRM_EXYNOS_IPP
+	ret = platform_driver_register(&ipp_driver);
+	if (ret < 0)
+		goto out_ipp;
+#endif
+
 	ret = platform_driver_register(&exynos_drm_platform_driver);
 	if (ret < 0)
 		goto out_drm;
@@ -380,6 +395,11 @@ out:
 	platform_driver_unregister(&exynos_drm_platform_driver);
 
 out_drm:
+#ifdef CONFIG_DRM_EXYNOS_IPP
+	platform_driver_unregister(&ipp_driver);
+out_ipp:
+#endif
+
 #ifdef CONFIG_DRM_EXYNOS_G2D
 	platform_driver_unregister(&g2d_driver);
 out_g2d:
@@ -416,6 +436,10 @@ static void __exit exynos_drm_exit(void)
 
 	platform_driver_unregister(&exynos_drm_platform_driver);
 
+#ifdef CONFIG_DRM_EXYNOS_IPP
+	platform_driver_unregister(&ipp_driver);
+#endif
+
 #ifdef CONFIG_DRM_EXYNOS_G2D
 	platform_driver_unregister(&g2d_driver);
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index e4ea74df4fc2..44ab3c7b6a90 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -232,8 +232,14 @@ struct exynos_drm_g2d_private {
 	struct list_head	userptr_list;
 };
 
+struct exynos_drm_ipp_private {
+	struct device	*dev;
+	struct list_head	event_list;
+};
+
 struct drm_exynos_file_private {
 	struct exynos_drm_g2d_private	*g2d_priv;
+	struct exynos_drm_ipp_private	*ipp_priv;
 };
 
 /*
@@ -343,4 +349,5 @@ extern struct platform_driver mixer_driver;
 extern struct platform_driver exynos_drm_common_hdmi_driver;
 extern struct platform_driver vidi_driver;
 extern struct platform_driver g2d_driver;
+extern struct platform_driver ipp_driver;
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
new file mode 100644
index 000000000000..c640935ab7d7
--- /dev/null
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -0,0 +1,2042 @@
+/*
+ * Copyright (C) 2012 Samsung Electronics Co.Ltd
+ * Authors:
+ *	Eunchul Kim <chulspro.kim@samsung.com>
+ *	Jinyoung Jeon <jy0.jeon@samsung.com>
+ *	Sangmin Lee <lsmin.lee@samsung.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+#include <linux/clk.h>
+#include <linux/pm_runtime.h>
+#include <plat/map-base.h>
+
+#include <drm/drmP.h>
+#include <drm/exynos_drm.h>
+#include "exynos_drm_drv.h"
+#include "exynos_drm_gem.h"
+#include "exynos_drm_ipp.h"
+
+/*
+ * IPP is stand for Image Post Processing and
+ * supports image scaler/rotator and input/output DMA operations.
+ * using FIMC, GSC, Rotator, so on.
+ * IPP is integration device driver of same attribute h/w
+ */
+
+/*
+ * TODO
+ * 1. expand command control id.
+ * 2. integrate	property and config.
+ * 3. removed send_event id check routine.
+ * 4. compare send_event id if needed.
+ * 5. free subdrv_remove notifier callback list if needed.
+ * 6. need to check subdrv_open about multi-open.
+ * 7. need to power_on implement power and sysmmu ctrl.
+ */
+
+#define get_ipp_context(dev)	platform_get_drvdata(to_platform_device(dev))
+#define ipp_is_m2m_cmd(c)	(c == IPP_CMD_M2M)
+
+/*
+ * A structure of event.
+ *
+ * @base: base of event.
+ * @event: ipp event.
+ */
+struct drm_exynos_ipp_send_event {
+	struct drm_pending_event	base;
+	struct drm_exynos_ipp_event	event;
+};
+
+/*
+ * A structure of memory node.
+ *
+ * @list: list head to memory queue information.
+ * @ops_id: id of operations.
+ * @prop_id: id of property.
+ * @buf_id: id of buffer.
+ * @buf_info: gem objects and dma address, size.
+ * @filp: a pointer to drm_file.
+ */
+struct drm_exynos_ipp_mem_node {
+	struct list_head	list;
+	enum drm_exynos_ops_id	ops_id;
+	u32	prop_id;
+	u32	buf_id;
+	struct drm_exynos_ipp_buf_info	buf_info;
+	struct drm_file		*filp;
+};
+
+/*
+ * A structure of ipp context.
+ *
+ * @subdrv: prepare initialization using subdrv.
+ * @ipp_lock: lock for synchronization of access to ipp_idr.
+ * @prop_lock: lock for synchronization of access to prop_idr.
+ * @ipp_idr: ipp driver idr.
+ * @prop_idr: property idr.
+ * @event_workq: event work queue.
+ * @cmd_workq: command work queue.
+ */
+struct ipp_context {
+	struct exynos_drm_subdrv	subdrv;
+	struct mutex	ipp_lock;
+	struct mutex	prop_lock;
+	struct idr	ipp_idr;
+	struct idr	prop_idr;
+	struct workqueue_struct	*event_workq;
+	struct workqueue_struct	*cmd_workq;
+};
+
+static LIST_HEAD(exynos_drm_ippdrv_list);
+static DEFINE_MUTEX(exynos_drm_ippdrv_lock);
+static BLOCKING_NOTIFIER_HEAD(exynos_drm_ippnb_list);
+
+int exynos_drm_ippdrv_register(struct exynos_drm_ippdrv *ippdrv)
+{
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (!ippdrv)
+		return -EINVAL;
+
+	mutex_lock(&exynos_drm_ippdrv_lock);
+	list_add_tail(&ippdrv->drv_list, &exynos_drm_ippdrv_list);
+	mutex_unlock(&exynos_drm_ippdrv_lock);
+
+	return 0;
+}
+
+int exynos_drm_ippdrv_unregister(struct exynos_drm_ippdrv *ippdrv)
+{
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (!ippdrv)
+		return -EINVAL;
+
+	mutex_lock(&exynos_drm_ippdrv_lock);
+	list_del(&ippdrv->drv_list);
+	mutex_unlock(&exynos_drm_ippdrv_lock);
+
+	return 0;
+}
+
+static int ipp_create_id(struct idr *id_idr, struct mutex *lock, void *obj,
+		u32 *idp)
+{
+	int ret;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+again:
+	/* ensure there is space available to allocate a handle */
+	if (idr_pre_get(id_idr, GFP_KERNEL) == 0) {
+		DRM_ERROR("failed to get idr.\n");
+		return -ENOMEM;
+	}
+
+	/* do the allocation under our mutexlock */
+	mutex_lock(lock);
+	ret = idr_get_new_above(id_idr, obj, 1, (int *)idp);
+	mutex_unlock(lock);
+	if (ret == -EAGAIN)
+		goto again;
+
+	return ret;
+}
+
+static void *ipp_find_obj(struct idr *id_idr, struct mutex *lock, u32 id)
+{
+	void *obj;
+
+	DRM_DEBUG_KMS("%s:id[%d]\n", __func__, id);
+
+	mutex_lock(lock);
+
+	/* find object using handle */
+	obj = idr_find(id_idr, id);
+	if (!obj) {
+		DRM_ERROR("failed to find object.\n");
+		mutex_unlock(lock);
+		return ERR_PTR(-ENODEV);
+	}
+
+	mutex_unlock(lock);
+
+	return obj;
+}
+
+static inline bool ipp_check_dedicated(struct exynos_drm_ippdrv *ippdrv,
+		enum drm_exynos_ipp_cmd	cmd)
+{
+	/*
+	 * check dedicated flag and WB, OUTPUT operation with
+	 * power on state.
+	 */
+	if (ippdrv->dedicated || (!ipp_is_m2m_cmd(cmd) &&
+	    !pm_runtime_suspended(ippdrv->dev)))
+		return true;
+
+	return false;
+}
+
+static struct exynos_drm_ippdrv *ipp_find_driver(struct ipp_context *ctx,
+		struct drm_exynos_ipp_property *property)
+{
+	struct exynos_drm_ippdrv *ippdrv;
+	u32 ipp_id = property->ipp_id;
+
+	DRM_DEBUG_KMS("%s:ipp_id[%d]\n", __func__, ipp_id);
+
+	if (ipp_id) {
+		/* find ipp driver using idr */
+		ippdrv = ipp_find_obj(&ctx->ipp_idr, &ctx->ipp_lock,
+			ipp_id);
+		if (IS_ERR_OR_NULL(ippdrv)) {
+			DRM_ERROR("not found ipp%d driver.\n", ipp_id);
+			return ippdrv;
+		}
+
+		/*
+		 * WB, OUTPUT opertion not supported multi-operation.
+		 * so, make dedicated state at set property ioctl.
+		 * when ipp driver finished operations, clear dedicated flags.
+		 */
+		if (ipp_check_dedicated(ippdrv, property->cmd)) {
+			DRM_ERROR("already used choose device.\n");
+			return ERR_PTR(-EBUSY);
+		}
+
+		/*
+		 * This is necessary to find correct device in ipp drivers.
+		 * ipp drivers have different abilities,
+		 * so need to check property.
+		 */
+		if (ippdrv->check_property &&
+		    ippdrv->check_property(ippdrv->dev, property)) {
+			DRM_ERROR("not support property.\n");
+			return ERR_PTR(-EINVAL);
+		}
+
+		return ippdrv;
+	} else {
+		/*
+		 * This case is search all ipp driver for finding.
+		 * user application don't set ipp_id in this case,
+		 * so ipp subsystem search correct driver in driver list.
+		 */
+		list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
+			if (ipp_check_dedicated(ippdrv, property->cmd)) {
+				DRM_DEBUG_KMS("%s:used device.\n", __func__);
+				continue;
+			}
+
+			if (ippdrv->check_property &&
+			    ippdrv->check_property(ippdrv->dev, property)) {
+				DRM_DEBUG_KMS("%s:not support property.\n",
+					__func__);
+				continue;
+			}
+
+			return ippdrv;
+		}
+
+		DRM_ERROR("not support ipp driver operations.\n");
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
+static struct exynos_drm_ippdrv *ipp_find_drv_by_handle(u32 prop_id)
+{
+	struct exynos_drm_ippdrv *ippdrv;
+	struct drm_exynos_ipp_cmd_node *c_node;
+	int count = 0;
+
+	DRM_DEBUG_KMS("%s:prop_id[%d]\n", __func__, prop_id);
+
+	if (list_empty(&exynos_drm_ippdrv_list)) {
+		DRM_DEBUG_KMS("%s:ippdrv_list is empty.\n", __func__);
+		return ERR_PTR(-ENODEV);
+	}
+
+	/*
+	 * This case is search ipp driver by prop_id handle.
+	 * sometimes, ipp subsystem find driver by prop_id.
+	 * e.g PAUSE state, queue buf, command contro.
+	 */
+	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
+		DRM_DEBUG_KMS("%s:count[%d]ippdrv[0x%x]\n", __func__,
+			count++, (int)ippdrv);
+
+		if (!list_empty(&ippdrv->cmd_list)) {
+			list_for_each_entry(c_node, &ippdrv->cmd_list, list)
+				if (c_node->property.prop_id == prop_id)
+					return ippdrv;
+		}
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
+int exynos_drm_ipp_get_property(struct drm_device *drm_dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_exynos_file_private *file_priv = file->driver_priv;
+	struct exynos_drm_ipp_private *priv = file_priv->ipp_priv;
+	struct device *dev = priv->dev;
+	struct ipp_context *ctx = get_ipp_context(dev);
+	struct drm_exynos_ipp_prop_list *prop_list = data;
+	struct exynos_drm_ippdrv *ippdrv;
+	int count = 0;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (!ctx) {
+		DRM_ERROR("invalid context.\n");
+		return -EINVAL;
+	}
+
+	if (!prop_list) {
+		DRM_ERROR("invalid property parameter.\n");
+		return -EINVAL;
+	}
+
+	DRM_DEBUG_KMS("%s:ipp_id[%d]\n", __func__, prop_list->ipp_id);
+
+	if (!prop_list->ipp_id) {
+		list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list)
+			count++;
+		/*
+		 * Supports ippdrv list count for user application.
+		 * First step user application getting ippdrv count.
+		 * and second step getting ippdrv capability using ipp_id.
+		 */
+		prop_list->count = count;
+	} else {
+		/*
+		 * Getting ippdrv capability by ipp_id.
+		 * some deivce not supported wb, output interface.
+		 * so, user application detect correct ipp driver
+		 * using this ioctl.
+		 */
+		ippdrv = ipp_find_obj(&ctx->ipp_idr, &ctx->ipp_lock,
+						prop_list->ipp_id);
+		if (!ippdrv) {
+			DRM_ERROR("not found ipp%d driver.\n",
+					prop_list->ipp_id);
+			return -EINVAL;
+		}
+
+		prop_list = ippdrv->prop_list;
+	}
+
+	return 0;
+}
+
+static void ipp_print_property(struct drm_exynos_ipp_property *property,
+		int idx)
+{
+	struct drm_exynos_ipp_config *config = &property->config[idx];
+	struct drm_exynos_pos *pos = &config->pos;
+	struct drm_exynos_sz *sz = &config->sz;
+
+	DRM_DEBUG_KMS("%s:prop_id[%d]ops[%s]fmt[0x%x]\n",
+		__func__, property->prop_id, idx ? "dst" : "src", config->fmt);
+
+	DRM_DEBUG_KMS("%s:pos[%d %d %d %d]sz[%d %d]f[%d]r[%d]\n",
+		__func__, pos->x, pos->y, pos->w, pos->h,
+		sz->hsize, sz->vsize, config->flip, config->degree);
+}
+
+static int ipp_find_and_set_property(struct drm_exynos_ipp_property *property)
+{
+	struct exynos_drm_ippdrv *ippdrv;
+	struct drm_exynos_ipp_cmd_node *c_node;
+	u32 prop_id = property->prop_id;
+
+	DRM_DEBUG_KMS("%s:prop_id[%d]\n", __func__, prop_id);
+
+	ippdrv = ipp_find_drv_by_handle(prop_id);
+	if (IS_ERR_OR_NULL(ippdrv)) {
+		DRM_ERROR("failed to get ipp driver.\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Find command node using command list in ippdrv.
+	 * when we find this command no using prop_id.
+	 * return property information set in this command node.
+	 */
+	list_for_each_entry(c_node, &ippdrv->cmd_list, list) {
+		if ((c_node->property.prop_id == prop_id) &&
+		    (c_node->state == IPP_STATE_STOP)) {
+			DRM_DEBUG_KMS("%s:found cmd[%d]ippdrv[0x%x]\n",
+				__func__, property->cmd, (int)ippdrv);
+
+			c_node->property = *property;
+			return 0;
+		}
+	}
+
+	DRM_ERROR("failed to search property.\n");
+
+	return -EINVAL;
+}
+
+static struct drm_exynos_ipp_cmd_work *ipp_create_cmd_work(void)
+{
+	struct drm_exynos_ipp_cmd_work *cmd_work;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	cmd_work = kzalloc(sizeof(*cmd_work), GFP_KERNEL);
+	if (!cmd_work) {
+		DRM_ERROR("failed to alloc cmd_work.\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	INIT_WORK((struct work_struct *)cmd_work, ipp_sched_cmd);
+
+	return cmd_work;
+}
+
+static struct drm_exynos_ipp_event_work *ipp_create_event_work(void)
+{
+	struct drm_exynos_ipp_event_work *event_work;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	event_work = kzalloc(sizeof(*event_work), GFP_KERNEL);
+	if (!event_work) {
+		DRM_ERROR("failed to alloc event_work.\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	INIT_WORK((struct work_struct *)event_work, ipp_sched_event);
+
+	return event_work;
+}
+
+int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_exynos_file_private *file_priv = file->driver_priv;
+	struct exynos_drm_ipp_private *priv = file_priv->ipp_priv;
+	struct device *dev = priv->dev;
+	struct ipp_context *ctx = get_ipp_context(dev);
+	struct drm_exynos_ipp_property *property = data;
+	struct exynos_drm_ippdrv *ippdrv;
+	struct drm_exynos_ipp_cmd_node *c_node;
+	int ret, i;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (!ctx) {
+		DRM_ERROR("invalid context.\n");
+		return -EINVAL;
+	}
+
+	if (!property) {
+		DRM_ERROR("invalid property parameter.\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * This is log print for user application property.
+	 * user application set various property.
+	 */
+	for_each_ipp_ops(i)
+		ipp_print_property(property, i);
+
+	/*
+	 * set property ioctl generated new prop_id.
+	 * but in this case already asigned prop_id using old set property.
+	 * e.g PAUSE state. this case supports find current prop_id and use it
+	 * instead of allocation.
+	 */
+	if (property->prop_id) {
+		DRM_DEBUG_KMS("%s:prop_id[%d]\n", __func__, property->prop_id);
+		return ipp_find_and_set_property(property);
+	}
+
+	/* find ipp driver using ipp id */
+	ippdrv = ipp_find_driver(ctx, property);
+	if (IS_ERR_OR_NULL(ippdrv)) {
+		DRM_ERROR("failed to get ipp driver.\n");
+		return -EINVAL;
+	}
+
+	/* allocate command node */
+	c_node = kzalloc(sizeof(*c_node), GFP_KERNEL);
+	if (!c_node) {
+		DRM_ERROR("failed to allocate map node.\n");
+		return -ENOMEM;
+	}
+
+	/* create property id */
+	ret = ipp_create_id(&ctx->prop_idr, &ctx->prop_lock, c_node,
+		&property->prop_id);
+	if (ret) {
+		DRM_ERROR("failed to create id.\n");
+		goto err_clear;
+	}
+
+	DRM_DEBUG_KMS("%s:created prop_id[%d]cmd[%d]ippdrv[0x%x]\n",
+		__func__, property->prop_id, property->cmd, (int)ippdrv);
+
+	/* stored property information and ippdrv in private data */
+	c_node->priv = priv;
+	c_node->property = *property;
+	c_node->state = IPP_STATE_IDLE;
+
+	c_node->start_work = ipp_create_cmd_work();
+	if (IS_ERR_OR_NULL(c_node->start_work)) {
+		DRM_ERROR("failed to create start work.\n");
+		goto err_clear;
+	}
+
+	c_node->stop_work = ipp_create_cmd_work();
+	if (IS_ERR_OR_NULL(c_node->stop_work)) {
+		DRM_ERROR("failed to create stop work.\n");
+		goto err_free_start;
+	}
+
+	c_node->event_work = ipp_create_event_work();
+	if (IS_ERR_OR_NULL(c_node->event_work)) {
+		DRM_ERROR("failed to create event work.\n");
+		goto err_free_stop;
+	}
+
+	mutex_init(&c_node->cmd_lock);
+	mutex_init(&c_node->mem_lock);
+	mutex_init(&c_node->event_lock);
+
+	init_completion(&c_node->start_complete);
+	init_completion(&c_node->stop_complete);
+
+	for_each_ipp_ops(i)
+		INIT_LIST_HEAD(&c_node->mem_list[i]);
+
+	INIT_LIST_HEAD(&c_node->event_list);
+	list_splice_init(&priv->event_list, &c_node->event_list);
+	list_add_tail(&c_node->list, &ippdrv->cmd_list);
+
+	/* make dedicated state without m2m */
+	if (!ipp_is_m2m_cmd(property->cmd))
+		ippdrv->dedicated = true;
+
+	return 0;
+
+err_free_stop:
+	kfree(c_node->stop_work);
+err_free_start:
+	kfree(c_node->start_work);
+err_clear:
+	kfree(c_node);
+	return ret;
+}
+
+static void ipp_clean_cmd_node(struct drm_exynos_ipp_cmd_node *c_node)
+{
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	/* delete list */
+	list_del(&c_node->list);
+
+	/* destroy mutex */
+	mutex_destroy(&c_node->cmd_lock);
+	mutex_destroy(&c_node->mem_lock);
+	mutex_destroy(&c_node->event_lock);
+
+	/* free command node */
+	kfree(c_node->start_work);
+	kfree(c_node->stop_work);
+	kfree(c_node->event_work);
+	kfree(c_node);
+}
+
+static int ipp_check_mem_list(struct drm_exynos_ipp_cmd_node *c_node)
+{
+	struct drm_exynos_ipp_property *property = &c_node->property;
+	struct drm_exynos_ipp_mem_node *m_node;
+	struct list_head *head;
+	int ret, i, count[EXYNOS_DRM_OPS_MAX] = { 0, };
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	mutex_lock(&c_node->mem_lock);
+
+	for_each_ipp_ops(i) {
+		/* source/destination memory list */
+		head = &c_node->mem_list[i];
+
+		if (list_empty(head)) {
+			DRM_DEBUG_KMS("%s:%s memory empty.\n", __func__,
+				i ? "dst" : "src");
+			continue;
+		}
+
+		/* find memory node entry */
+		list_for_each_entry(m_node, head, list) {
+			DRM_DEBUG_KMS("%s:%s,count[%d]m_node[0x%x]\n", __func__,
+				i ? "dst" : "src", count[i], (int)m_node);
+			count[i]++;
+		}
+	}
+
+	DRM_DEBUG_KMS("%s:min[%d]max[%d]\n", __func__,
+		min(count[EXYNOS_DRM_OPS_SRC], count[EXYNOS_DRM_OPS_DST]),
+		max(count[EXYNOS_DRM_OPS_SRC], count[EXYNOS_DRM_OPS_DST]));
+
+	/*
+	 * M2M operations should be need paired memory address.
+	 * so, need to check minimum count about src, dst.
+	 * other case not use paired memory, so use maximum count
+	 */
+	if (ipp_is_m2m_cmd(property->cmd))
+		ret = min(count[EXYNOS_DRM_OPS_SRC],
+			count[EXYNOS_DRM_OPS_DST]);
+	else
+		ret = max(count[EXYNOS_DRM_OPS_SRC],
+			count[EXYNOS_DRM_OPS_DST]);
+
+	mutex_unlock(&c_node->mem_lock);
+
+	return ret;
+}
+
+static struct drm_exynos_ipp_mem_node
+		*ipp_find_mem_node(struct drm_exynos_ipp_cmd_node *c_node,
+		struct drm_exynos_ipp_queue_buf *qbuf)
+{
+	struct drm_exynos_ipp_mem_node *m_node;
+	struct list_head *head;
+	int count = 0;
+
+	DRM_DEBUG_KMS("%s:buf_id[%d]\n", __func__, qbuf->buf_id);
+
+	/* source/destination memory list */
+	head = &c_node->mem_list[qbuf->ops_id];
+
+	/* find memory node from memory list */
+	list_for_each_entry(m_node, head, list) {
+		DRM_DEBUG_KMS("%s:count[%d]m_node[0x%x]\n",
+			__func__, count++, (int)m_node);
+
+		/* compare buffer id */
+		if (m_node->buf_id == qbuf->buf_id)
+			return m_node;
+	}
+
+	return NULL;
+}
+
+static int ipp_set_mem_node(struct exynos_drm_ippdrv *ippdrv,
+		struct drm_exynos_ipp_cmd_node *c_node,
+		struct drm_exynos_ipp_mem_node *m_node)
+{
+	struct exynos_drm_ipp_ops *ops = NULL;
+	int ret = 0;
+
+	DRM_DEBUG_KMS("%s:node[0x%x]\n", __func__, (int)m_node);
+
+	if (!m_node) {
+		DRM_ERROR("invalid queue node.\n");
+		return -EFAULT;
+	}
+
+	mutex_lock(&c_node->mem_lock);
+
+	DRM_DEBUG_KMS("%s:ops_id[%d]\n", __func__, m_node->ops_id);
+
+	/* get operations callback */
+	ops = ippdrv->ops[m_node->ops_id];
+	if (!ops) {
+		DRM_ERROR("not support ops.\n");
+		ret = -EFAULT;
+		goto err_unlock;
+	}
+
+	/* set address and enable irq */
+	if (ops->set_addr) {
+		ret = ops->set_addr(ippdrv->dev, &m_node->buf_info,
+			m_node->buf_id, IPP_BUF_ENQUEUE);
+		if (ret) {
+			DRM_ERROR("failed to set addr.\n");
+			goto err_unlock;
+		}
+	}
+
+err_unlock:
+	mutex_unlock(&c_node->mem_lock);
+	return ret;
+}
+
+static struct drm_exynos_ipp_mem_node
+		*ipp_get_mem_node(struct drm_device *drm_dev,
+		struct drm_file *file,
+		struct drm_exynos_ipp_cmd_node *c_node,
+		struct drm_exynos_ipp_queue_buf *qbuf)
+{
+	struct drm_exynos_ipp_mem_node *m_node;
+	struct drm_exynos_ipp_buf_info buf_info;
+	void *addr;
+	int i;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	mutex_lock(&c_node->mem_lock);
+
+	m_node = kzalloc(sizeof(*m_node), GFP_KERNEL);
+	if (!m_node) {
+		DRM_ERROR("failed to allocate queue node.\n");
+		goto err_unlock;
+	}
+
+	/* clear base address for error handling */
+	memset(&buf_info, 0x0, sizeof(buf_info));
+
+	/* operations, buffer id */
+	m_node->ops_id = qbuf->ops_id;
+	m_node->prop_id = qbuf->prop_id;
+	m_node->buf_id = qbuf->buf_id;
+
+	DRM_DEBUG_KMS("%s:m_node[0x%x]ops_id[%d]\n", __func__,
+		(int)m_node, qbuf->ops_id);
+	DRM_DEBUG_KMS("%s:prop_id[%d]buf_id[%d]\n", __func__,
+		qbuf->prop_id, m_node->buf_id);
+
+	for_each_ipp_planar(i) {
+		DRM_DEBUG_KMS("%s:i[%d]handle[0x%x]\n", __func__,
+			i, qbuf->handle[i]);
+
+		/* get dma address by handle */
+		if (qbuf->handle[i]) {
+			addr = exynos_drm_gem_get_dma_addr(drm_dev,
+					qbuf->handle[i], file);
+			if (IS_ERR(addr)) {
+				DRM_ERROR("failed to get addr.\n");
+				goto err_clear;
+			}
+
+			buf_info.handles[i] = qbuf->handle[i];
+			buf_info.base[i] = *(dma_addr_t *) addr;
+			DRM_DEBUG_KMS("%s:i[%d]base[0x%x]hd[0x%x]\n",
+				__func__, i, buf_info.base[i],
+				(int)buf_info.handles[i]);
+		}
+	}
+
+	m_node->filp = file;
+	m_node->buf_info = buf_info;
+	list_add_tail(&m_node->list, &c_node->mem_list[qbuf->ops_id]);
+
+	mutex_unlock(&c_node->mem_lock);
+	return m_node;
+
+err_clear:
+	kfree(m_node);
+err_unlock:
+	mutex_unlock(&c_node->mem_lock);
+	return ERR_PTR(-EFAULT);
+}
+
+static int ipp_put_mem_node(struct drm_device *drm_dev,
+		struct drm_exynos_ipp_cmd_node *c_node,
+		struct drm_exynos_ipp_mem_node *m_node)
+{
+	int i;
+
+	DRM_DEBUG_KMS("%s:node[0x%x]\n", __func__, (int)m_node);
+
+	if (!m_node) {
+		DRM_ERROR("invalid dequeue node.\n");
+		return -EFAULT;
+	}
+
+	if (list_empty(&m_node->list)) {
+		DRM_ERROR("empty memory node.\n");
+		return -ENOMEM;
+	}
+
+	mutex_lock(&c_node->mem_lock);
+
+	DRM_DEBUG_KMS("%s:ops_id[%d]\n", __func__, m_node->ops_id);
+
+	/* put gem buffer */
+	for_each_ipp_planar(i) {
+		unsigned long handle = m_node->buf_info.handles[i];
+		if (handle)
+			exynos_drm_gem_put_dma_addr(drm_dev, handle,
+							m_node->filp);
+	}
+
+	/* delete list in queue */
+	list_del(&m_node->list);
+	kfree(m_node);
+
+	mutex_unlock(&c_node->mem_lock);
+
+	return 0;
+}
+
+static void ipp_free_event(struct drm_pending_event *event)
+{
+	kfree(event);
+}
+
+static int ipp_get_event(struct drm_device *drm_dev,
+		struct drm_file *file,
+		struct drm_exynos_ipp_cmd_node *c_node,
+		struct drm_exynos_ipp_queue_buf *qbuf)
+{
+	struct drm_exynos_ipp_send_event *e;
+	unsigned long flags;
+
+	DRM_DEBUG_KMS("%s:ops_id[%d]buf_id[%d]\n", __func__,
+		qbuf->ops_id, qbuf->buf_id);
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+
+	if (!e) {
+		DRM_ERROR("failed to allocate event.\n");
+		spin_lock_irqsave(&drm_dev->event_lock, flags);
+		file->event_space += sizeof(e->event);
+		spin_unlock_irqrestore(&drm_dev->event_lock, flags);
+		return -ENOMEM;
+	}
+
+	/* make event */
+	e->event.base.type = DRM_EXYNOS_IPP_EVENT;
+	e->event.base.length = sizeof(e->event);
+	e->event.user_data = qbuf->user_data;
+	e->event.prop_id = qbuf->prop_id;
+	e->event.buf_id[EXYNOS_DRM_OPS_DST] = qbuf->buf_id;
+	e->base.event = &e->event.base;
+	e->base.file_priv = file;
+	e->base.destroy = ipp_free_event;
+	list_add_tail(&e->base.link, &c_node->event_list);
+
+	return 0;
+}
+
+static void ipp_put_event(struct drm_exynos_ipp_cmd_node *c_node,
+		struct drm_exynos_ipp_queue_buf *qbuf)
+{
+	struct drm_exynos_ipp_send_event *e, *te;
+	int count = 0;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (list_empty(&c_node->event_list)) {
+		DRM_DEBUG_KMS("%s:event_list is empty.\n", __func__);
+		return;
+	}
+
+	list_for_each_entry_safe(e, te, &c_node->event_list, base.link) {
+		DRM_DEBUG_KMS("%s:count[%d]e[0x%x]\n",
+			__func__, count++, (int)e);
+
+		/*
+		 * quf == NULL condition means all event deletion.
+		 * stop operations want to delete all event list.
+		 * another case delete only same buf id.
+		 */
+		if (!qbuf) {
+			/* delete list */
+			list_del(&e->base.link);
+			kfree(e);
+		}
+
+		/* compare buffer id */
+		if (qbuf && (qbuf->buf_id ==
+		    e->event.buf_id[EXYNOS_DRM_OPS_DST])) {
+			/* delete list */
+			list_del(&e->base.link);
+			kfree(e);
+			return;
+		}
+	}
+}
+
+void ipp_handle_cmd_work(struct device *dev,
+		struct exynos_drm_ippdrv *ippdrv,
+		struct drm_exynos_ipp_cmd_work *cmd_work,
+		struct drm_exynos_ipp_cmd_node *c_node)
+{
+	struct ipp_context *ctx = get_ipp_context(dev);
+
+	cmd_work->ippdrv = ippdrv;
+	cmd_work->c_node = c_node;
+	queue_work(ctx->cmd_workq, (struct work_struct *)cmd_work);
+}
+
+static int ipp_queue_buf_with_run(struct device *dev,
+		struct drm_exynos_ipp_cmd_node *c_node,
+		struct drm_exynos_ipp_mem_node *m_node,
+		struct drm_exynos_ipp_queue_buf *qbuf)
+{
+	struct exynos_drm_ippdrv *ippdrv;
+	struct drm_exynos_ipp_property *property;
+	struct exynos_drm_ipp_ops *ops;
+	int ret;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	ippdrv = ipp_find_drv_by_handle(qbuf->prop_id);
+	if (IS_ERR_OR_NULL(ippdrv)) {
+		DRM_ERROR("failed to get ipp driver.\n");
+		return -EFAULT;
+	}
+
+	ops = ippdrv->ops[qbuf->ops_id];
+	if (!ops) {
+		DRM_ERROR("failed to get ops.\n");
+		return -EFAULT;
+	}
+
+	property = &c_node->property;
+
+	if (c_node->state != IPP_STATE_START) {
+		DRM_DEBUG_KMS("%s:bypass for invalid state.\n" , __func__);
+		return 0;
+	}
+
+	if (!ipp_check_mem_list(c_node)) {
+		DRM_DEBUG_KMS("%s:empty memory.\n", __func__);
+		return 0;
+	}
+
+	/*
+	 * If set destination buffer and enabled clock,
+	 * then m2m operations need start operations at queue_buf
+	 */
+	if (ipp_is_m2m_cmd(property->cmd)) {
+		struct drm_exynos_ipp_cmd_work *cmd_work = c_node->start_work;
+
+		cmd_work->ctrl = IPP_CTRL_PLAY;
+		ipp_handle_cmd_work(dev, ippdrv, cmd_work, c_node);
+	} else {
+		ret = ipp_set_mem_node(ippdrv, c_node, m_node);
+		if (ret) {
+			DRM_ERROR("failed to set m node.\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void ipp_clean_queue_buf(struct drm_device *drm_dev,
+		struct drm_exynos_ipp_cmd_node *c_node,
+		struct drm_exynos_ipp_queue_buf *qbuf)
+{
+	struct drm_exynos_ipp_mem_node *m_node, *tm_node;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (!list_empty(&c_node->mem_list[qbuf->ops_id])) {
+		/* delete list */
+		list_for_each_entry_safe(m_node, tm_node,
+			&c_node->mem_list[qbuf->ops_id], list) {
+			if (m_node->buf_id == qbuf->buf_id &&
+			    m_node->ops_id == qbuf->ops_id)
+				ipp_put_mem_node(drm_dev, c_node, m_node);
+		}
+	}
+}
+
+int exynos_drm_ipp_queue_buf(struct drm_device *drm_dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_exynos_file_private *file_priv = file->driver_priv;
+	struct exynos_drm_ipp_private *priv = file_priv->ipp_priv;
+	struct device *dev = priv->dev;
+	struct ipp_context *ctx = get_ipp_context(dev);
+	struct drm_exynos_ipp_queue_buf *qbuf = data;
+	struct drm_exynos_ipp_cmd_node *c_node;
+	struct drm_exynos_ipp_mem_node *m_node;
+	int ret;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (!qbuf) {
+		DRM_ERROR("invalid buf parameter.\n");
+		return -EINVAL;
+	}
+
+	if (qbuf->ops_id >= EXYNOS_DRM_OPS_MAX) {
+		DRM_ERROR("invalid ops parameter.\n");
+		return -EINVAL;
+	}
+
+	DRM_DEBUG_KMS("%s:prop_id[%d]ops_id[%s]buf_id[%d]buf_type[%d]\n",
+		__func__, qbuf->prop_id, qbuf->ops_id ? "dst" : "src",
+		qbuf->buf_id, qbuf->buf_type);
+
+	/* find command node */
+	c_node = ipp_find_obj(&ctx->prop_idr, &ctx->prop_lock,
+		qbuf->prop_id);
+	if (!c_node) {
+		DRM_ERROR("failed to get command node.\n");
+		return -EFAULT;
+	}
+
+	/* buffer control */
+	switch (qbuf->buf_type) {
+	case IPP_BUF_ENQUEUE:
+		/* get memory node */
+		m_node = ipp_get_mem_node(drm_dev, file, c_node, qbuf);
+		if (IS_ERR(m_node)) {
+			DRM_ERROR("failed to get m_node.\n");
+			return PTR_ERR(m_node);
+		}
+
+		/*
+		 * first step get event for destination buffer.
+		 * and second step when M2M case run with destination buffer
+		 * if needed.
+		 */
+		if (qbuf->ops_id == EXYNOS_DRM_OPS_DST) {
+			/* get event for destination buffer */
+			ret = ipp_get_event(drm_dev, file, c_node, qbuf);
+			if (ret) {
+				DRM_ERROR("failed to get event.\n");
+				goto err_clean_node;
+			}
+
+			/*
+			 * M2M case run play control for streaming feature.
+			 * other case set address and waiting.
+			 */
+			ret = ipp_queue_buf_with_run(dev, c_node, m_node, qbuf);
+			if (ret) {
+				DRM_ERROR("failed to run command.\n");
+				goto err_clean_node;
+			}
+		}
+		break;
+	case IPP_BUF_DEQUEUE:
+		mutex_lock(&c_node->cmd_lock);
+
+		/* put event for destination buffer */
+		if (qbuf->ops_id == EXYNOS_DRM_OPS_DST)
+			ipp_put_event(c_node, qbuf);
+
+		ipp_clean_queue_buf(drm_dev, c_node, qbuf);
+
+		mutex_unlock(&c_node->cmd_lock);
+		break;
+	default:
+		DRM_ERROR("invalid buffer control.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+
+err_clean_node:
+	DRM_ERROR("clean memory nodes.\n");
+
+	ipp_clean_queue_buf(drm_dev, c_node, qbuf);
+	return ret;
+}
+
+static bool exynos_drm_ipp_check_valid(struct device *dev,
+		enum drm_exynos_ipp_ctrl ctrl, enum drm_exynos_ipp_state state)
+{
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (ctrl != IPP_CTRL_PLAY) {
+		if (pm_runtime_suspended(dev)) {
+			DRM_ERROR("pm:runtime_suspended.\n");
+			goto err_status;
+		}
+	}
+
+	switch (ctrl) {
+	case IPP_CTRL_PLAY:
+		if (state != IPP_STATE_IDLE)
+			goto err_status;
+		break;
+	case IPP_CTRL_STOP:
+		if (state == IPP_STATE_STOP)
+			goto err_status;
+		break;
+	case IPP_CTRL_PAUSE:
+		if (state != IPP_STATE_START)
+			goto err_status;
+		break;
+	case IPP_CTRL_RESUME:
+		if (state != IPP_STATE_STOP)
+			goto err_status;
+		break;
+	default:
+		DRM_ERROR("invalid state.\n");
+		goto err_status;
+		break;
+	}
+
+	return true;
+
+err_status:
+	DRM_ERROR("invalid status:ctrl[%d]state[%d]\n", ctrl, state);
+	return false;
+}
+
+int exynos_drm_ipp_cmd_ctrl(struct drm_device *drm_dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_exynos_file_private *file_priv = file->driver_priv;
+	struct exynos_drm_ipp_private *priv = file_priv->ipp_priv;
+	struct exynos_drm_ippdrv *ippdrv = NULL;
+	struct device *dev = priv->dev;
+	struct ipp_context *ctx = get_ipp_context(dev);
+	struct drm_exynos_ipp_cmd_ctrl *cmd_ctrl = data;
+	struct drm_exynos_ipp_cmd_work *cmd_work;
+	struct drm_exynos_ipp_cmd_node *c_node;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (!ctx) {
+		DRM_ERROR("invalid context.\n");
+		return -EINVAL;
+	}
+
+	if (!cmd_ctrl) {
+		DRM_ERROR("invalid control parameter.\n");
+		return -EINVAL;
+	}
+
+	DRM_DEBUG_KMS("%s:ctrl[%d]prop_id[%d]\n", __func__,
+		cmd_ctrl->ctrl, cmd_ctrl->prop_id);
+
+	ippdrv = ipp_find_drv_by_handle(cmd_ctrl->prop_id);
+	if (IS_ERR(ippdrv)) {
+		DRM_ERROR("failed to get ipp driver.\n");
+		return PTR_ERR(ippdrv);
+	}
+
+	c_node = ipp_find_obj(&ctx->prop_idr, &ctx->prop_lock,
+		cmd_ctrl->prop_id);
+	if (!c_node) {
+		DRM_ERROR("invalid command node list.\n");
+		return -EINVAL;
+	}
+
+	if (!exynos_drm_ipp_check_valid(ippdrv->dev, cmd_ctrl->ctrl,
+	    c_node->state)) {
+		DRM_ERROR("invalid state.\n");
+		return -EINVAL;
+	}
+
+	switch (cmd_ctrl->ctrl) {
+	case IPP_CTRL_PLAY:
+		if (pm_runtime_suspended(ippdrv->dev))
+			pm_runtime_get_sync(ippdrv->dev);
+		c_node->state = IPP_STATE_START;
+
+		cmd_work = c_node->start_work;
+		cmd_work->ctrl = cmd_ctrl->ctrl;
+		ipp_handle_cmd_work(dev, ippdrv, cmd_work, c_node);
+		c_node->state = IPP_STATE_START;
+		break;
+	case IPP_CTRL_STOP:
+		cmd_work = c_node->stop_work;
+		cmd_work->ctrl = cmd_ctrl->ctrl;
+		ipp_handle_cmd_work(dev, ippdrv, cmd_work, c_node);
+
+		if (!wait_for_completion_timeout(&c_node->stop_complete,
+		    msecs_to_jiffies(300))) {
+			DRM_ERROR("timeout stop:prop_id[%d]\n",
+				c_node->property.prop_id);
+		}
+
+		c_node->state = IPP_STATE_STOP;
+		ippdrv->dedicated = false;
+		ipp_clean_cmd_node(c_node);
+
+		if (list_empty(&ippdrv->cmd_list))
+			pm_runtime_put_sync(ippdrv->dev);
+		break;
+	case IPP_CTRL_PAUSE:
+		cmd_work = c_node->stop_work;
+		cmd_work->ctrl = cmd_ctrl->ctrl;
+		ipp_handle_cmd_work(dev, ippdrv, cmd_work, c_node);
+
+		if (!wait_for_completion_timeout(&c_node->stop_complete,
+		    msecs_to_jiffies(200))) {
+			DRM_ERROR("timeout stop:prop_id[%d]\n",
+				c_node->property.prop_id);
+		}
+
+		c_node->state = IPP_STATE_STOP;
+		break;
+	case IPP_CTRL_RESUME:
+		c_node->state = IPP_STATE_START;
+		cmd_work = c_node->start_work;
+		cmd_work->ctrl = cmd_ctrl->ctrl;
+		ipp_handle_cmd_work(dev, ippdrv, cmd_work, c_node);
+		break;
+	default:
+		DRM_ERROR("could not support this state currently.\n");
+		return -EINVAL;
+	}
+
+	DRM_DEBUG_KMS("%s:done ctrl[%d]prop_id[%d]\n", __func__,
+		cmd_ctrl->ctrl, cmd_ctrl->prop_id);
+
+	return 0;
+}
+
+int exynos_drm_ippnb_register(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(
+		&exynos_drm_ippnb_list, nb);
+}
+
+int exynos_drm_ippnb_unregister(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(
+		&exynos_drm_ippnb_list, nb);
+}
+
+int exynos_drm_ippnb_send_event(unsigned long val, void *v)
+{
+	return blocking_notifier_call_chain(
+		&exynos_drm_ippnb_list, val, v);
+}
+
+static int ipp_set_property(struct exynos_drm_ippdrv *ippdrv,
+		struct drm_exynos_ipp_property *property)
+{
+	struct exynos_drm_ipp_ops *ops = NULL;
+	bool swap = false;
+	int ret, i;
+
+	if (!property) {
+		DRM_ERROR("invalid property parameter.\n");
+		return -EINVAL;
+	}
+
+	DRM_DEBUG_KMS("%s:prop_id[%d]\n", __func__, property->prop_id);
+
+	/* reset h/w block */
+	if (ippdrv->reset &&
+	    ippdrv->reset(ippdrv->dev)) {
+		DRM_ERROR("failed to reset.\n");
+		return -EINVAL;
+	}
+
+	/* set source,destination operations */
+	for_each_ipp_ops(i) {
+		struct drm_exynos_ipp_config *config =
+			&property->config[i];
+
+		ops = ippdrv->ops[i];
+		if (!ops || !config) {
+			DRM_ERROR("not support ops and config.\n");
+			return -EINVAL;
+		}
+
+		/* set format */
+		if (ops->set_fmt) {
+			ret = ops->set_fmt(ippdrv->dev, config->fmt);
+			if (ret) {
+				DRM_ERROR("not support format.\n");
+				return ret;
+			}
+		}
+
+		/* set transform for rotation, flip */
+		if (ops->set_transf) {
+			ret = ops->set_transf(ippdrv->dev, config->degree,
+				config->flip, &swap);
+			if (ret) {
+				DRM_ERROR("not support tranf.\n");
+				return -EINVAL;
+			}
+		}
+
+		/* set size */
+		if (ops->set_size) {
+			ret = ops->set_size(ippdrv->dev, swap, &config->pos,
+				&config->sz);
+			if (ret) {
+				DRM_ERROR("not support size.\n");
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
+		struct drm_exynos_ipp_cmd_node *c_node)
+{
+	struct drm_exynos_ipp_mem_node *m_node;
+	struct drm_exynos_ipp_property *property = &c_node->property;
+	struct list_head *head;
+	int ret, i;
+
+	DRM_DEBUG_KMS("%s:prop_id[%d]\n", __func__, property->prop_id);
+
+	/* store command info in ippdrv */
+	ippdrv->cmd = c_node;
+
+	if (!ipp_check_mem_list(c_node)) {
+		DRM_DEBUG_KMS("%s:empty memory.\n", __func__);
+		return -ENOMEM;
+	}
+
+	/* set current property in ippdrv */
+	ret = ipp_set_property(ippdrv, property);
+	if (ret) {
+		DRM_ERROR("failed to set property.\n");
+		ippdrv->cmd = NULL;
+		return ret;
+	}
+
+	/* check command */
+	switch (property->cmd) {
+	case IPP_CMD_M2M:
+		for_each_ipp_ops(i) {
+			/* source/destination memory list */
+			head = &c_node->mem_list[i];
+
+			m_node = list_first_entry(head,
+				struct drm_exynos_ipp_mem_node, list);
+			if (!m_node) {
+				DRM_ERROR("failed to get node.\n");
+				ret = -EFAULT;
+				return ret;
+			}
+
+			DRM_DEBUG_KMS("%s:m_node[0x%x]\n",
+				__func__, (int)m_node);
+
+			ret = ipp_set_mem_node(ippdrv, c_node, m_node);
+			if (ret) {
+				DRM_ERROR("failed to set m node.\n");
+				return ret;
+			}
+		}
+		break;
+	case IPP_CMD_WB:
+		/* destination memory list */
+		head = &c_node->mem_list[EXYNOS_DRM_OPS_DST];
+
+		list_for_each_entry(m_node, head, list) {
+			ret = ipp_set_mem_node(ippdrv, c_node, m_node);
+			if (ret) {
+				DRM_ERROR("failed to set m node.\n");
+				return ret;
+			}
+		}
+		break;
+	case IPP_CMD_OUTPUT:
+		/* source memory list */
+		head = &c_node->mem_list[EXYNOS_DRM_OPS_SRC];
+
+		list_for_each_entry(m_node, head, list) {
+			ret = ipp_set_mem_node(ippdrv, c_node, m_node);
+			if (ret) {
+				DRM_ERROR("failed to set m node.\n");
+				return ret;
+			}
+		}
+		break;
+	default:
+		DRM_ERROR("invalid operations.\n");
+		return -EINVAL;
+	}
+
+	DRM_DEBUG_KMS("%s:cmd[%d]\n", __func__, property->cmd);
+
+	/* start operations */
+	if (ippdrv->start) {
+		ret = ippdrv->start(ippdrv->dev, property->cmd);
+		if (ret) {
+			DRM_ERROR("failed to start ops.\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int ipp_stop_property(struct drm_device *drm_dev,
+		struct exynos_drm_ippdrv *ippdrv,
+		struct drm_exynos_ipp_cmd_node *c_node)
+{
+	struct drm_exynos_ipp_mem_node *m_node, *tm_node;
+	struct drm_exynos_ipp_property *property = &c_node->property;
+	struct list_head *head;
+	int ret = 0, i;
+
+	DRM_DEBUG_KMS("%s:prop_id[%d]\n", __func__, property->prop_id);
+
+	/* put event */
+	ipp_put_event(c_node, NULL);
+
+	/* check command */
+	switch (property->cmd) {
+	case IPP_CMD_M2M:
+		for_each_ipp_ops(i) {
+			/* source/destination memory list */
+			head = &c_node->mem_list[i];
+
+			if (list_empty(head)) {
+				DRM_DEBUG_KMS("%s:mem_list is empty.\n",
+					__func__);
+				break;
+			}
+
+			list_for_each_entry_safe(m_node, tm_node,
+				head, list) {
+				ret = ipp_put_mem_node(drm_dev, c_node,
+					m_node);
+				if (ret) {
+					DRM_ERROR("failed to put m_node.\n");
+					goto err_clear;
+				}
+			}
+		}
+		break;
+	case IPP_CMD_WB:
+		/* destination memory list */
+		head = &c_node->mem_list[EXYNOS_DRM_OPS_DST];
+
+		if (list_empty(head)) {
+			DRM_DEBUG_KMS("%s:mem_list is empty.\n", __func__);
+			break;
+		}
+
+		list_for_each_entry_safe(m_node, tm_node, head, list) {
+			ret = ipp_put_mem_node(drm_dev, c_node, m_node);
+			if (ret) {
+				DRM_ERROR("failed to put m_node.\n");
+				goto err_clear;
+			}
+		}
+		break;
+	case IPP_CMD_OUTPUT:
+		/* source memory list */
+		head = &c_node->mem_list[EXYNOS_DRM_OPS_SRC];
+
+		if (list_empty(head)) {
+			DRM_DEBUG_KMS("%s:mem_list is empty.\n", __func__);
+			break;
+		}
+
+		list_for_each_entry_safe(m_node, tm_node, head, list) {
+			ret = ipp_put_mem_node(drm_dev, c_node, m_node);
+			if (ret) {
+				DRM_ERROR("failed to put m_node.\n");
+				goto err_clear;
+			}
+		}
+		break;
+	default:
+		DRM_ERROR("invalid operations.\n");
+		ret = -EINVAL;
+		goto err_clear;
+	}
+
+err_clear:
+	/* stop operations */
+	if (ippdrv->stop)
+		ippdrv->stop(ippdrv->dev, property->cmd);
+
+	return ret;
+}
+
+void ipp_sched_cmd(struct work_struct *work)
+{
+	struct drm_exynos_ipp_cmd_work *cmd_work =
+		(struct drm_exynos_ipp_cmd_work *)work;
+	struct exynos_drm_ippdrv *ippdrv;
+	struct drm_exynos_ipp_cmd_node *c_node;
+	struct drm_exynos_ipp_property *property;
+	int ret;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	ippdrv = cmd_work->ippdrv;
+	if (!ippdrv) {
+		DRM_ERROR("invalid ippdrv list.\n");
+		return;
+	}
+
+	c_node = cmd_work->c_node;
+	if (!c_node) {
+		DRM_ERROR("invalid command node list.\n");
+		return;
+	}
+
+	mutex_lock(&c_node->cmd_lock);
+
+	property = &c_node->property;
+	if (!property) {
+		DRM_ERROR("failed to get property:prop_id[%d]\n",
+			c_node->property.prop_id);
+		goto err_unlock;
+	}
+
+	switch (cmd_work->ctrl) {
+	case IPP_CTRL_PLAY:
+	case IPP_CTRL_RESUME:
+		ret = ipp_start_property(ippdrv, c_node);
+		if (ret) {
+			DRM_ERROR("failed to start property:prop_id[%d]\n",
+				c_node->property.prop_id);
+			goto err_unlock;
+		}
+
+		/*
+		 * M2M case supports wait_completion of transfer.
+		 * because M2M case supports single unit operation
+		 * with multiple queue.
+		 * M2M need to wait completion of data transfer.
+		 */
+		if (ipp_is_m2m_cmd(property->cmd)) {
+			if (!wait_for_completion_timeout
+			    (&c_node->start_complete, msecs_to_jiffies(200))) {
+				DRM_ERROR("timeout event:prop_id[%d]\n",
+					c_node->property.prop_id);
+				goto err_unlock;
+			}
+		}
+		break;
+	case IPP_CTRL_STOP:
+	case IPP_CTRL_PAUSE:
+		ret = ipp_stop_property(ippdrv->drm_dev, ippdrv,
+			c_node);
+		if (ret) {
+			DRM_ERROR("failed to stop property.\n");
+			goto err_unlock;
+		}
+
+		complete(&c_node->stop_complete);
+		break;
+	default:
+		DRM_ERROR("unknown control type\n");
+		break;
+	}
+
+	DRM_DEBUG_KMS("%s:ctrl[%d] done.\n", __func__, cmd_work->ctrl);
+
+err_unlock:
+	mutex_unlock(&c_node->cmd_lock);
+}
+
+static int ipp_send_event(struct exynos_drm_ippdrv *ippdrv,
+		struct drm_exynos_ipp_cmd_node *c_node, int *buf_id)
+{
+	struct drm_device *drm_dev = ippdrv->drm_dev;
+	struct drm_exynos_ipp_property *property = &c_node->property;
+	struct drm_exynos_ipp_mem_node *m_node;
+	struct drm_exynos_ipp_queue_buf qbuf;
+	struct drm_exynos_ipp_send_event *e;
+	struct list_head *head;
+	struct timeval now;
+	unsigned long flags;
+	u32 tbuf_id[EXYNOS_DRM_OPS_MAX] = {0, };
+	int ret, i;
+
+	for_each_ipp_ops(i)
+		DRM_DEBUG_KMS("%s:%s buf_id[%d]\n", __func__,
+			i ? "dst" : "src", buf_id[i]);
+
+	if (!drm_dev) {
+		DRM_ERROR("failed to get drm_dev.\n");
+		return -EINVAL;
+	}
+
+	if (!property) {
+		DRM_ERROR("failed to get property.\n");
+		return -EINVAL;
+	}
+
+	if (list_empty(&c_node->event_list)) {
+		DRM_DEBUG_KMS("%s:event list is empty.\n", __func__);
+		return 0;
+	}
+
+	if (!ipp_check_mem_list(c_node)) {
+		DRM_DEBUG_KMS("%s:empty memory.\n", __func__);
+		return 0;
+	}
+
+	/* check command */
+	switch (property->cmd) {
+	case IPP_CMD_M2M:
+		for_each_ipp_ops(i) {
+			/* source/destination memory list */
+			head = &c_node->mem_list[i];
+
+			m_node = list_first_entry(head,
+				struct drm_exynos_ipp_mem_node, list);
+			if (!m_node) {
+				DRM_ERROR("empty memory node.\n");
+				return -ENOMEM;
+			}
+
+			tbuf_id[i] = m_node->buf_id;
+			DRM_DEBUG_KMS("%s:%s buf_id[%d]\n", __func__,
+				i ? "dst" : "src", tbuf_id[i]);
+
+			ret = ipp_put_mem_node(drm_dev, c_node, m_node);
+			if (ret)
+				DRM_ERROR("failed to put m_node.\n");
+		}
+		break;
+	case IPP_CMD_WB:
+		/* clear buf for finding */
+		memset(&qbuf, 0x0, sizeof(qbuf));
+		qbuf.ops_id = EXYNOS_DRM_OPS_DST;
+		qbuf.buf_id = buf_id[EXYNOS_DRM_OPS_DST];
+
+		/* get memory node entry */
+		m_node = ipp_find_mem_node(c_node, &qbuf);
+		if (!m_node) {
+			DRM_ERROR("empty memory node.\n");
+			return -ENOMEM;
+		}
+
+		tbuf_id[EXYNOS_DRM_OPS_DST] = m_node->buf_id;
+
+		ret = ipp_put_mem_node(drm_dev, c_node, m_node);
+		if (ret)
+			DRM_ERROR("failed to put m_node.\n");
+		break;
+	case IPP_CMD_OUTPUT:
+		/* source memory list */
+		head = &c_node->mem_list[EXYNOS_DRM_OPS_SRC];
+
+		m_node = list_first_entry(head,
+			struct drm_exynos_ipp_mem_node, list);
+		if (!m_node) {
+			DRM_ERROR("empty memory node.\n");
+			return -ENOMEM;
+		}
+
+		tbuf_id[EXYNOS_DRM_OPS_SRC] = m_node->buf_id;
+
+		ret = ipp_put_mem_node(drm_dev, c_node, m_node);
+		if (ret)
+			DRM_ERROR("failed to put m_node.\n");
+		break;
+	default:
+		DRM_ERROR("invalid operations.\n");
+		return -EINVAL;
+	}
+
+	if (tbuf_id[EXYNOS_DRM_OPS_DST] != buf_id[EXYNOS_DRM_OPS_DST])
+		DRM_ERROR("failed to match buf_id[%d %d]prop_id[%d]\n",
+			tbuf_id[1], buf_id[1], property->prop_id);
+
+	/*
+	 * command node have event list of destination buffer
+	 * If destination buffer enqueue to mem list,
+	 * then we make event and link to event list tail.
+	 * so, we get first event for first enqueued buffer.
+	 */
+	e = list_first_entry(&c_node->event_list,
+		struct drm_exynos_ipp_send_event, base.link);
+
+	if (!e) {
+		DRM_ERROR("empty event.\n");
+		return -EINVAL;
+	}
+
+	do_gettimeofday(&now);
+	DRM_DEBUG_KMS("%s:tv_sec[%ld]tv_usec[%ld]\n"
+		, __func__, now.tv_sec, now.tv_usec);
+	e->event.tv_sec = now.tv_sec;
+	e->event.tv_usec = now.tv_usec;
+	e->event.prop_id = property->prop_id;
+
+	/* set buffer id about source destination */
+	for_each_ipp_ops(i)
+		e->event.buf_id[i] = tbuf_id[i];
+
+	spin_lock_irqsave(&drm_dev->event_lock, flags);
+	list_move_tail(&e->base.link, &e->base.file_priv->event_list);
+	wake_up_interruptible(&e->base.file_priv->event_wait);
+	spin_unlock_irqrestore(&drm_dev->event_lock, flags);
+
+	DRM_DEBUG_KMS("%s:done cmd[%d]prop_id[%d]buf_id[%d]\n", __func__,
+		property->cmd, property->prop_id, tbuf_id[EXYNOS_DRM_OPS_DST]);
+
+	return 0;
+}
+
+void ipp_sched_event(struct work_struct *work)
+{
+	struct drm_exynos_ipp_event_work *event_work =
+		(struct drm_exynos_ipp_event_work *)work;
+	struct exynos_drm_ippdrv *ippdrv;
+	struct drm_exynos_ipp_cmd_node *c_node;
+	int ret;
+
+	if (!event_work) {
+		DRM_ERROR("failed to get event_work.\n");
+		return;
+	}
+
+	DRM_DEBUG_KMS("%s:buf_id[%d]\n", __func__,
+		event_work->buf_id[EXYNOS_DRM_OPS_DST]);
+
+	ippdrv = event_work->ippdrv;
+	if (!ippdrv) {
+		DRM_ERROR("failed to get ipp driver.\n");
+		return;
+	}
+
+	c_node = ippdrv->cmd;
+	if (!c_node) {
+		DRM_ERROR("failed to get command node.\n");
+		return;
+	}
+
+	/*
+	 * IPP supports command thread, event thread synchronization.
+	 * If IPP close immediately from user land, then IPP make
+	 * synchronization with command thread, so make complete event.
+	 * or going out operations.
+	 */
+	if (c_node->state != IPP_STATE_START) {
+		DRM_DEBUG_KMS("%s:bypass state[%d]prop_id[%d]\n",
+			__func__, c_node->state, c_node->property.prop_id);
+		goto err_completion;
+	}
+
+	mutex_lock(&c_node->event_lock);
+
+	ret = ipp_send_event(ippdrv, c_node, event_work->buf_id);
+	if (ret) {
+		DRM_ERROR("failed to send event.\n");
+		goto err_completion;
+	}
+
+err_completion:
+	if (ipp_is_m2m_cmd(c_node->property.cmd))
+		complete(&c_node->start_complete);
+
+	mutex_unlock(&c_node->event_lock);
+}
+
+static int ipp_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
+{
+	struct ipp_context *ctx = get_ipp_context(dev);
+	struct exynos_drm_ippdrv *ippdrv;
+	int ret, count = 0;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	/* get ipp driver entry */
+	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
+		ippdrv->drm_dev = drm_dev;
+
+		ret = ipp_create_id(&ctx->ipp_idr, &ctx->ipp_lock, ippdrv,
+			&ippdrv->ipp_id);
+		if (ret) {
+			DRM_ERROR("failed to create id.\n");
+			goto err_idr;
+		}
+
+		DRM_DEBUG_KMS("%s:count[%d]ippdrv[0x%x]ipp_id[%d]\n", __func__,
+			count++, (int)ippdrv, ippdrv->ipp_id);
+
+		if (ippdrv->ipp_id == 0) {
+			DRM_ERROR("failed to get ipp_id[%d]\n",
+				ippdrv->ipp_id);
+			goto err_idr;
+		}
+
+		/* store parent device for node */
+		ippdrv->parent_dev = dev;
+
+		/* store event work queue and handler */
+		ippdrv->event_workq = ctx->event_workq;
+		ippdrv->sched_event = ipp_sched_event;
+		INIT_LIST_HEAD(&ippdrv->cmd_list);
+	}
+
+	return 0;
+
+err_idr:
+	idr_remove_all(&ctx->ipp_idr);
+	idr_remove_all(&ctx->prop_idr);
+	idr_destroy(&ctx->ipp_idr);
+	idr_destroy(&ctx->prop_idr);
+	return ret;
+}
+
+static void ipp_subdrv_remove(struct drm_device *drm_dev, struct device *dev)
+{
+	struct exynos_drm_ippdrv *ippdrv;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	/* get ipp driver entry */
+	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
+		ippdrv->drm_dev = NULL;
+		exynos_drm_ippdrv_unregister(ippdrv);
+	}
+}
+
+static int ipp_subdrv_open(struct drm_device *drm_dev, struct device *dev,
+		struct drm_file *file)
+{
+	struct drm_exynos_file_private *file_priv = file->driver_priv;
+	struct exynos_drm_ipp_private *priv;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		DRM_ERROR("failed to allocate priv.\n");
+		return -ENOMEM;
+	}
+	priv->dev = dev;
+	file_priv->ipp_priv = priv;
+
+	INIT_LIST_HEAD(&priv->event_list);
+
+	DRM_DEBUG_KMS("%s:done priv[0x%x]\n", __func__, (int)priv);
+
+	return 0;
+}
+
+static void ipp_subdrv_close(struct drm_device *drm_dev, struct device *dev,
+		struct drm_file *file)
+{
+	struct drm_exynos_file_private *file_priv = file->driver_priv;
+	struct exynos_drm_ipp_private *priv = file_priv->ipp_priv;
+	struct exynos_drm_ippdrv *ippdrv = NULL;
+	struct drm_exynos_ipp_cmd_node *c_node, *tc_node;
+	int count = 0;
+
+	DRM_DEBUG_KMS("%s:for priv[0x%x]\n", __func__, (int)priv);
+
+	if (list_empty(&exynos_drm_ippdrv_list)) {
+		DRM_DEBUG_KMS("%s:ippdrv_list is empty.\n", __func__);
+		goto err_clear;
+	}
+
+	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
+		if (list_empty(&ippdrv->cmd_list))
+			continue;
+
+		list_for_each_entry_safe(c_node, tc_node,
+			&ippdrv->cmd_list, list) {
+			DRM_DEBUG_KMS("%s:count[%d]ippdrv[0x%x]\n",
+				__func__, count++, (int)ippdrv);
+
+			if (c_node->priv == priv) {
+				/*
+				 * userland goto unnormal state. process killed.
+				 * and close the file.
+				 * so, IPP didn't called stop cmd ctrl.
+				 * so, we are make stop operation in this state.
+				 */
+				if (c_node->state == IPP_STATE_START) {
+					ipp_stop_property(drm_dev, ippdrv,
+						c_node);
+					c_node->state = IPP_STATE_STOP;
+				}
+
+				ippdrv->dedicated = false;
+				ipp_clean_cmd_node(c_node);
+				if (list_empty(&ippdrv->cmd_list))
+					pm_runtime_put_sync(ippdrv->dev);
+			}
+		}
+	}
+
+err_clear:
+	kfree(priv);
+	return;
+}
+
+static int __devinit ipp_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ipp_context *ctx;
+	struct exynos_drm_subdrv *subdrv;
+	int ret;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	mutex_init(&ctx->ipp_lock);
+	mutex_init(&ctx->prop_lock);
+
+	idr_init(&ctx->ipp_idr);
+	idr_init(&ctx->prop_idr);
+
+	/*
+	 * create single thread for ipp event
+	 * IPP supports event thread for IPP drivers.
+	 * IPP driver send event_work to this thread.
+	 * and IPP event thread send event to user process.
+	 */
+	ctx->event_workq = create_singlethread_workqueue("ipp_event");
+	if (!ctx->event_workq) {
+		dev_err(dev, "failed to create event workqueue\n");
+		ret = -EINVAL;
+		goto err_clear;
+	}
+
+	/*
+	 * create single thread for ipp command
+	 * IPP supports command thread for user process.
+	 * user process make command node using set property ioctl.
+	 * and make start_work and send this work to command thread.
+	 * and then this command thread start property.
+	 */
+	ctx->cmd_workq = create_singlethread_workqueue("ipp_cmd");
+	if (!ctx->cmd_workq) {
+		dev_err(dev, "failed to create cmd workqueue\n");
+		ret = -EINVAL;
+		goto err_event_workq;
+	}
+
+	/* set sub driver informations */
+	subdrv = &ctx->subdrv;
+	subdrv->dev = dev;
+	subdrv->probe = ipp_subdrv_probe;
+	subdrv->remove = ipp_subdrv_remove;
+	subdrv->open = ipp_subdrv_open;
+	subdrv->close = ipp_subdrv_close;
+
+	platform_set_drvdata(pdev, ctx);
+
+	ret = exynos_drm_subdrv_register(subdrv);
+	if (ret < 0) {
+		DRM_ERROR("failed to register drm ipp device.\n");
+		goto err_cmd_workq;
+	}
+
+	dev_info(&pdev->dev, "drm ipp registered successfully.\n");
+
+	return 0;
+
+err_cmd_workq:
+	destroy_workqueue(ctx->cmd_workq);
+err_event_workq:
+	destroy_workqueue(ctx->event_workq);
+err_clear:
+	kfree(ctx);
+	return ret;
+}
+
+static int __devexit ipp_remove(struct platform_device *pdev)
+{
+	struct ipp_context *ctx = platform_get_drvdata(pdev);
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	/* unregister sub driver */
+	exynos_drm_subdrv_unregister(&ctx->subdrv);
+
+	/* remove,destroy ipp idr */
+	idr_remove_all(&ctx->ipp_idr);
+	idr_remove_all(&ctx->prop_idr);
+	idr_destroy(&ctx->ipp_idr);
+	idr_destroy(&ctx->prop_idr);
+
+	mutex_destroy(&ctx->ipp_lock);
+	mutex_destroy(&ctx->prop_lock);
+
+	/* destroy command, event work queue */
+	destroy_workqueue(ctx->cmd_workq);
+	destroy_workqueue(ctx->event_workq);
+
+	kfree(ctx);
+
+	return 0;
+}
+
+static int ipp_power_ctrl(struct ipp_context *ctx, bool enable)
+{
+	DRM_DEBUG_KMS("%s:enable[%d]\n", __func__, enable);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int ipp_suspend(struct device *dev)
+{
+	struct ipp_context *ctx = get_ipp_context(dev);
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (pm_runtime_suspended(dev))
+		return 0;
+
+	return ipp_power_ctrl(ctx, false);
+}
+
+static int ipp_resume(struct device *dev)
+{
+	struct ipp_context *ctx = get_ipp_context(dev);
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (!pm_runtime_suspended(dev))
+		return ipp_power_ctrl(ctx, true);
+
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_PM_RUNTIME
+static int ipp_runtime_suspend(struct device *dev)
+{
+	struct ipp_context *ctx = get_ipp_context(dev);
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	return ipp_power_ctrl(ctx, false);
+}
+
+static int ipp_runtime_resume(struct device *dev)
+{
+	struct ipp_context *ctx = get_ipp_context(dev);
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	return ipp_power_ctrl(ctx, true);
+}
+#endif
+
+static const struct dev_pm_ops ipp_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(ipp_suspend, ipp_resume)
+	SET_RUNTIME_PM_OPS(ipp_runtime_suspend, ipp_runtime_resume, NULL)
+};
+
+struct platform_driver ipp_driver = {
+	.probe		= ipp_probe,
+	.remove		= __devexit_p(ipp_remove),
+	.driver		= {
+		.name	= "exynos-drm-ipp",
+		.owner	= THIS_MODULE,
+		.pm	= &ipp_pm_ops,
+	},
+};
+
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.h b/drivers/gpu/drm/exynos/exynos_drm_ipp.h
new file mode 100644
index 000000000000..28ffac95386c
--- /dev/null
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.h
@@ -0,0 +1,266 @@
+/*
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *
+ * Authors:
+ *	Eunchul Kim <chulspro.kim@samsung.com>
+ *	Jinyoung Jeon <jy0.jeon@samsung.com>
+ *	Sangmin Lee <lsmin.lee@samsung.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _EXYNOS_DRM_IPP_H_
+#define _EXYNOS_DRM_IPP_H_
+
+#define for_each_ipp_ops(pos)	\
+	for (pos = 0; pos < EXYNOS_DRM_OPS_MAX; pos++)
+#define for_each_ipp_planar(pos)	\
+	for (pos = 0; pos < EXYNOS_DRM_PLANAR_MAX; pos++)
+
+#define IPP_GET_LCD_WIDTH	_IOR('F', 302, int)
+#define IPP_GET_LCD_HEIGHT	_IOR('F', 303, int)
+#define IPP_SET_WRITEBACK	_IOW('F', 304, u32)
+
+/* definition of state */
+enum drm_exynos_ipp_state {
+	IPP_STATE_IDLE,
+	IPP_STATE_START,
+	IPP_STATE_STOP,
+};
+
+/*
+ * A structure of command work information.
+ * @work: work structure.
+ * @ippdrv: current work ippdrv.
+ * @c_node: command node information.
+ * @ctrl: command control.
+ */
+struct drm_exynos_ipp_cmd_work {
+	struct work_struct	work;
+	struct exynos_drm_ippdrv	*ippdrv;
+	struct drm_exynos_ipp_cmd_node *c_node;
+	enum drm_exynos_ipp_ctrl	ctrl;
+};
+
+/*
+ * A structure of command node.
+ *
+ * @priv: IPP private infomation.
+ * @list: list head to command queue information.
+ * @event_list: list head of event.
+ * @mem_list: list head to source,destination memory queue information.
+ * @cmd_lock: lock for synchronization of access to ioctl.
+ * @mem_lock: lock for synchronization of access to memory nodes.
+ * @event_lock: lock for synchronization of access to scheduled event.
+ * @start_complete: completion of start of command.
+ * @stop_complete: completion of stop of command.
+ * @property: property information.
+ * @start_work: start command work structure.
+ * @stop_work: stop command work structure.
+ * @event_work: event work structure.
+ * @state: state of command node.
+ */
+struct drm_exynos_ipp_cmd_node {
+	struct exynos_drm_ipp_private *priv;
+	struct list_head	list;
+	struct list_head	event_list;
+	struct list_head	mem_list[EXYNOS_DRM_OPS_MAX];
+	struct mutex	cmd_lock;
+	struct mutex	mem_lock;
+	struct mutex	event_lock;
+	struct completion	start_complete;
+	struct completion	stop_complete;
+	struct drm_exynos_ipp_property	property;
+	struct drm_exynos_ipp_cmd_work *start_work;
+	struct drm_exynos_ipp_cmd_work *stop_work;
+	struct drm_exynos_ipp_event_work *event_work;
+	enum drm_exynos_ipp_state	state;
+};
+
+/*
+ * A structure of buffer information.
+ *
+ * @gem_objs: Y, Cb, Cr each gem object.
+ * @base: Y, Cb, Cr each planar address.
+ */
+struct drm_exynos_ipp_buf_info {
+	unsigned long	handles[EXYNOS_DRM_PLANAR_MAX];
+	dma_addr_t	base[EXYNOS_DRM_PLANAR_MAX];
+};
+
+/*
+ * A structure of wb setting infomation.
+ *
+ * @enable: enable flag for wb.
+ * @refresh: HZ of the refresh rate.
+ */
+struct drm_exynos_ipp_set_wb {
+	__u32	enable;
+	__u32	refresh;
+};
+
+/*
+ * A structure of event work information.
+ *
+ * @work: work structure.
+ * @ippdrv: current work ippdrv.
+ * @buf_id: id of src, dst buffer.
+ */
+struct drm_exynos_ipp_event_work {
+	struct work_struct	work;
+	struct exynos_drm_ippdrv *ippdrv;
+	u32	buf_id[EXYNOS_DRM_OPS_MAX];
+};
+
+/*
+ * A structure of source,destination operations.
+ *
+ * @set_fmt: set format of image.
+ * @set_transf: set transform(rotations, flip).
+ * @set_size: set size of region.
+ * @set_addr: set address for dma.
+ */
+struct exynos_drm_ipp_ops {
+	int (*set_fmt)(struct device *dev, u32 fmt);
+	int (*set_transf)(struct device *dev,
+		enum drm_exynos_degree degree,
+		enum drm_exynos_flip flip, bool *swap);
+	int (*set_size)(struct device *dev, int swap,
+		struct drm_exynos_pos *pos, struct drm_exynos_sz *sz);
+	int (*set_addr)(struct device *dev,
+		 struct drm_exynos_ipp_buf_info *buf_info, u32 buf_id,
+		enum drm_exynos_ipp_buf_type buf_type);
+};
+
+/*
+ * A structure of ipp driver.
+ *
+ * @drv_list: list head for registed sub driver information.
+ * @parent_dev: parent device information.
+ * @dev: platform device.
+ * @drm_dev: drm device.
+ * @ipp_id: id of ipp driver.
+ * @dedicated: dedicated ipp device.
+ * @ops: source, destination operations.
+ * @event_workq: event work queue.
+ * @cmd: current command information.
+ * @cmd_list: list head for command information.
+ * @prop_list: property informations of current ipp driver.
+ * @check_property: check property about format, size, buffer.
+ * @reset: reset ipp block.
+ * @start: ipp each device start.
+ * @stop: ipp each device stop.
+ * @sched_event: work schedule handler.
+ */
+struct exynos_drm_ippdrv {
+	struct list_head	drv_list;
+	struct device	*parent_dev;
+	struct device	*dev;
+	struct drm_device	*drm_dev;
+	u32	ipp_id;
+	bool	dedicated;
+	struct exynos_drm_ipp_ops	*ops[EXYNOS_DRM_OPS_MAX];
+	struct workqueue_struct	*event_workq;
+	struct drm_exynos_ipp_cmd_node *cmd;
+	struct list_head	cmd_list;
+	struct drm_exynos_ipp_prop_list *prop_list;
+
+	int (*check_property)(struct device *dev,
+		struct drm_exynos_ipp_property *property);
+	int (*reset)(struct device *dev);
+	int (*start)(struct device *dev, enum drm_exynos_ipp_cmd cmd);
+	void (*stop)(struct device *dev, enum drm_exynos_ipp_cmd cmd);
+	void (*sched_event)(struct work_struct *work);
+};
+
+#ifdef CONFIG_DRM_EXYNOS_IPP
+extern int exynos_drm_ippdrv_register(struct exynos_drm_ippdrv *ippdrv);
+extern int exynos_drm_ippdrv_unregister(struct exynos_drm_ippdrv *ippdrv);
+extern int exynos_drm_ipp_get_property(struct drm_device *drm_dev, void *data,
+					 struct drm_file *file);
+extern int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
+					 struct drm_file *file);
+extern int exynos_drm_ipp_queue_buf(struct drm_device *drm_dev, void *data,
+					 struct drm_file *file);
+extern int exynos_drm_ipp_cmd_ctrl(struct drm_device *drm_dev, void *data,
+					 struct drm_file *file);
+extern int exynos_drm_ippnb_register(struct notifier_block *nb);
+extern int exynos_drm_ippnb_unregister(struct notifier_block *nb);
+extern int exynos_drm_ippnb_send_event(unsigned long val, void *v);
+extern void ipp_sched_cmd(struct work_struct *work);
+extern void ipp_sched_event(struct work_struct *work);
+
+#else
+static inline int exynos_drm_ippdrv_register(struct exynos_drm_ippdrv *ippdrv)
+{
+	return -ENODEV;
+}
+
+static inline int exynos_drm_ippdrv_unregister(struct exynos_drm_ippdrv *ippdrv)
+{
+	return -ENODEV;
+}
+
+static inline int exynos_drm_ipp_get_property(struct drm_device *drm_dev,
+						void *data,
+						struct drm_file *file_priv)
+{
+	return -ENOTTY;
+}
+
+static inline int exynos_drm_ipp_set_property(struct drm_device *drm_dev,
+						void *data,
+						struct drm_file *file_priv)
+{
+	return -ENOTTY;
+}
+
+static inline int exynos_drm_ipp_queue_buf(struct drm_device *drm_dev,
+						void *data,
+						struct drm_file *file)
+{
+	return -ENOTTY;
+}
+
+static inline int exynos_drm_ipp_cmd_ctrl(struct drm_device *drm_dev,
+						void *data,
+						struct drm_file *file)
+{
+	return -ENOTTY;
+}
+
+static inline int exynos_drm_ippnb_register(struct notifier_block *nb)
+{
+	return -ENODEV;
+}
+
+static inline int exynos_drm_ippnb_unregister(struct notifier_block *nb)
+{
+	return -ENODEV;
+}
+
+static inline int exynos_drm_ippnb_send_event(unsigned long val, void *v)
+{
+	return -ENOTTY;
+}
+#endif
+
+#endif /* _EXYNOS_DRM_IPP_H_ */
+
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
index 49f010f2b27f..e7f52c334005 100644
--- a/include/uapi/drm/exynos_drm.h
+++ b/include/uapi/drm/exynos_drm.h
@@ -163,6 +163,170 @@ struct drm_exynos_g2d_exec {
 	__u64					async;
 };
 
+enum drm_exynos_ops_id {
+	EXYNOS_DRM_OPS_SRC,
+	EXYNOS_DRM_OPS_DST,
+	EXYNOS_DRM_OPS_MAX,
+};
+
+struct drm_exynos_sz {
+	__u32	hsize;
+	__u32	vsize;
+};
+
+struct drm_exynos_pos {
+	__u32	x;
+	__u32	y;
+	__u32	w;
+	__u32	h;
+};
+
+enum drm_exynos_flip {
+	EXYNOS_DRM_FLIP_NONE = (0 << 0),
+	EXYNOS_DRM_FLIP_VERTICAL = (1 << 0),
+	EXYNOS_DRM_FLIP_HORIZONTAL = (1 << 1),
+};
+
+enum drm_exynos_degree {
+	EXYNOS_DRM_DEGREE_0,
+	EXYNOS_DRM_DEGREE_90,
+	EXYNOS_DRM_DEGREE_180,
+	EXYNOS_DRM_DEGREE_270,
+};
+
+enum drm_exynos_planer {
+	EXYNOS_DRM_PLANAR_Y,
+	EXYNOS_DRM_PLANAR_CB,
+	EXYNOS_DRM_PLANAR_CR,
+	EXYNOS_DRM_PLANAR_MAX,
+};
+
+/**
+ * A structure for ipp supported property list.
+ *
+ * @version: version of this structure.
+ * @ipp_id: id of ipp driver.
+ * @count: count of ipp driver.
+ * @writeback: flag of writeback supporting.
+ * @flip: flag of flip supporting.
+ * @degree: flag of degree information.
+ * @csc: flag of csc supporting.
+ * @crop: flag of crop supporting.
+ * @scale: flag of scale supporting.
+ * @refresh_min: min hz of refresh.
+ * @refresh_max: max hz of refresh.
+ * @crop_min: crop min resolution.
+ * @crop_max: crop max resolution.
+ * @scale_min: scale min resolution.
+ * @scale_max: scale max resolution.
+ */
+struct drm_exynos_ipp_prop_list {
+	__u32	version;
+	__u32	ipp_id;
+	__u32	count;
+	__u32	writeback;
+	__u32	flip;
+	__u32	degree;
+	__u32	csc;
+	__u32	crop;
+	__u32	scale;
+	__u32	refresh_min;
+	__u32	refresh_max;
+	__u32	reserved;
+	struct drm_exynos_sz	crop_min;
+	struct drm_exynos_sz	crop_max;
+	struct drm_exynos_sz	scale_min;
+	struct drm_exynos_sz	scale_max;
+};
+
+/**
+ * A structure for ipp config.
+ *
+ * @ops_id: property of operation directions.
+ * @flip: property of mirror, flip.
+ * @degree: property of rotation degree.
+ * @fmt: property of image format.
+ * @sz: property of image size.
+ * @pos: property of image position(src-cropped,dst-scaler).
+ */
+struct drm_exynos_ipp_config {
+	enum drm_exynos_ops_id ops_id;
+	enum drm_exynos_flip	flip;
+	enum drm_exynos_degree	degree;
+	__u32	fmt;
+	struct drm_exynos_sz	sz;
+	struct drm_exynos_pos	pos;
+};
+
+enum drm_exynos_ipp_cmd {
+	IPP_CMD_NONE,
+	IPP_CMD_M2M,
+	IPP_CMD_WB,
+	IPP_CMD_OUTPUT,
+	IPP_CMD_MAX,
+};
+
+/**
+ * A structure for ipp property.
+ *
+ * @config: source, destination config.
+ * @cmd: definition of command.
+ * @ipp_id: id of ipp driver.
+ * @prop_id: id of property.
+ * @refresh_rate: refresh rate.
+ */
+struct drm_exynos_ipp_property {
+	struct drm_exynos_ipp_config config[EXYNOS_DRM_OPS_MAX];
+	enum drm_exynos_ipp_cmd	cmd;
+	__u32	ipp_id;
+	__u32	prop_id;
+	__u32	refresh_rate;
+};
+
+enum drm_exynos_ipp_buf_type {
+	IPP_BUF_ENQUEUE,
+	IPP_BUF_DEQUEUE,
+};
+
+/**
+ * A structure for ipp buffer operations.
+ *
+ * @ops_id: operation directions.
+ * @buf_type: definition of buffer.
+ * @prop_id: id of property.
+ * @buf_id: id of buffer.
+ * @handle: Y, Cb, Cr each planar handle.
+ * @user_data: user data.
+ */
+struct drm_exynos_ipp_queue_buf {
+	enum drm_exynos_ops_id	ops_id;
+	enum drm_exynos_ipp_buf_type	buf_type;
+	__u32	prop_id;
+	__u32	buf_id;
+	__u32	handle[EXYNOS_DRM_PLANAR_MAX];
+	__u32	reserved;
+	__u64	user_data;
+};
+
+enum drm_exynos_ipp_ctrl {
+	IPP_CTRL_PLAY,
+	IPP_CTRL_STOP,
+	IPP_CTRL_PAUSE,
+	IPP_CTRL_RESUME,
+	IPP_CTRL_MAX,
+};
+
+/**
+ * A structure for ipp start/stop operations.
+ *
+ * @prop_id: id of property.
+ * @ctrl: definition of control.
+ */
+struct drm_exynos_ipp_cmd_ctrl {
+	__u32	prop_id;
+	enum drm_exynos_ipp_ctrl	ctrl;
+};
+
 #define DRM_EXYNOS_GEM_CREATE		0x00
 #define DRM_EXYNOS_GEM_MAP_OFFSET	0x01
 #define DRM_EXYNOS_GEM_MMAP		0x02
@@ -175,6 +339,12 @@ struct drm_exynos_g2d_exec {
 #define DRM_EXYNOS_G2D_SET_CMDLIST	0x21
 #define DRM_EXYNOS_G2D_EXEC		0x22
 
+/* IPP - Image Post Processing */
+#define DRM_EXYNOS_IPP_GET_PROPERTY	0x30
+#define DRM_EXYNOS_IPP_SET_PROPERTY	0x31
+#define DRM_EXYNOS_IPP_QUEUE_BUF	0x32
+#define DRM_EXYNOS_IPP_CMD_CTRL	0x33
+
 #define DRM_IOCTL_EXYNOS_GEM_CREATE		DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_GEM_CREATE, struct drm_exynos_gem_create)
 
@@ -197,8 +367,18 @@ struct drm_exynos_g2d_exec {
 #define DRM_IOCTL_EXYNOS_G2D_EXEC		DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_G2D_EXEC, struct drm_exynos_g2d_exec)
 
+#define DRM_IOCTL_EXYNOS_IPP_GET_PROPERTY	DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_GET_PROPERTY, struct drm_exynos_ipp_prop_list)
+#define DRM_IOCTL_EXYNOS_IPP_SET_PROPERTY	DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_SET_PROPERTY, struct drm_exynos_ipp_property)
+#define DRM_IOCTL_EXYNOS_IPP_QUEUE_BUF	DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_QUEUE_BUF, struct drm_exynos_ipp_queue_buf)
+#define DRM_IOCTL_EXYNOS_IPP_CMD_CTRL		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_CMD_CTRL, struct drm_exynos_ipp_cmd_ctrl)
+
 /* EXYNOS specific events */
 #define DRM_EXYNOS_G2D_EVENT		0x80000000
+#define DRM_EXYNOS_IPP_EVENT		0x80000001
 
 struct drm_exynos_g2d_event {
 	struct drm_event	base;
@@ -209,4 +389,14 @@ struct drm_exynos_g2d_event {
 	__u32			reserved;
 };
 
+struct drm_exynos_ipp_event {
+	struct drm_event	base;
+	__u64			user_data;
+	__u32			tv_sec;
+	__u32			tv_usec;
+	__u32			prop_id;
+	__u32			reserved;
+	__u32			buf_id[EXYNOS_DRM_OPS_MAX];
+};
+
 #endif /* _UAPI_EXYNOS_DRM_H_ */
-- 
cgit v1.2.3-55-g7522


From 16102edb49b6cc7fbb68b10c04a42b78fbceb3ed Mon Sep 17 00:00:00 2001
From: Eunchul Kim
Date: Fri, 14 Dec 2012 17:58:55 +0900
Subject: drm/exynos: add fimc ipp driver

FIMC is stand for Fully Interfactive Mobile Camera and
supports image scaler/rotator/crop/flip/csc and input/output DMA operations
and also supports writeback and display output operations.

This driver is registered to IPP subsystem framework to be used by user side
and user can control the FIMC hardware through some interfaces of IPP subsystem
framework.

Changelog v6:
- fix build warning.

Changelog v1 ~ v5:
- add comments, code fixups and cleanups.

Signed-off-by: Eunchul Kim <chulspro.kim@samsung.com>
Signed-off-by: Jinyoung Jeon <jy0.jeon@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
---
 drivers/gpu/drm/exynos/Kconfig           |    6 +
 drivers/gpu/drm/exynos/Makefile          |    1 +
 drivers/gpu/drm/exynos/exynos_drm_drv.c  |   15 +
 drivers/gpu/drm/exynos/exynos_drm_drv.h  |    1 +
 drivers/gpu/drm/exynos/exynos_drm_fimc.c | 2001 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/exynos/exynos_drm_fimc.h |   37 +
 drivers/gpu/drm/exynos/regs-fimc.h       |  669 ++++++++++
 include/drm/exynos_drm.h                 |   26 +
 8 files changed, 2756 insertions(+)
 create mode 100644 drivers/gpu/drm/exynos/exynos_drm_fimc.c
 create mode 100644 drivers/gpu/drm/exynos/exynos_drm_fimc.h
 create mode 100644 drivers/gpu/drm/exynos/regs-fimc.h

(limited to 'include')

diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 80ab242e2739..66c02df360e7 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -51,3 +51,9 @@ config DRM_EXYNOS_IPP
 	depends on DRM_EXYNOS
 	help
 	  Choose this option if you want to use IPP feature for DRM.
+
+config DRM_EXYNOS_FIMC
+	bool "Exynos DRM FIMC"
+	depends on DRM_EXYNOS_IPP
+	help
+	  Choose this option if you want to use Exynos FIMC for DRM.
diff --git a/drivers/gpu/drm/exynos/Makefile b/drivers/gpu/drm/exynos/Makefile
index 6c536ce4d95b..9710024ed000 100644
--- a/drivers/gpu/drm/exynos/Makefile
+++ b/drivers/gpu/drm/exynos/Makefile
@@ -17,5 +17,6 @@ exynosdrm-$(CONFIG_DRM_EXYNOS_HDMI)	+= exynos_hdmi.o exynos_mixer.o \
 exynosdrm-$(CONFIG_DRM_EXYNOS_VIDI)	+= exynos_drm_vidi.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_G2D)	+= exynos_drm_g2d.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_IPP)	+= exynos_drm_ipp.o
+exynosdrm-$(CONFIG_DRM_EXYNOS_FIMC)	+= exynos_drm_fimc.o
 
 obj-$(CONFIG_DRM_EXYNOS)		+= exynosdrm.o
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 0eb8a972e21c..73f02ac53bad 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -372,6 +372,12 @@ static int __init exynos_drm_init(void)
 		goto out_g2d;
 #endif
 
+#ifdef CONFIG_DRM_EXYNOS_FIMC
+	ret = platform_driver_register(&fimc_driver);
+	if (ret < 0)
+		goto out_fimc;
+#endif
+
 #ifdef CONFIG_DRM_EXYNOS_IPP
 	ret = platform_driver_register(&ipp_driver);
 	if (ret < 0)
@@ -400,6 +406,11 @@ out_drm:
 out_ipp:
 #endif
 
+#ifdef CONFIG_DRM_EXYNOS_FIMC
+	platform_driver_unregister(&fimc_driver);
+out_fimc:
+#endif
+
 #ifdef CONFIG_DRM_EXYNOS_G2D
 	platform_driver_unregister(&g2d_driver);
 out_g2d:
@@ -440,6 +451,10 @@ static void __exit exynos_drm_exit(void)
 	platform_driver_unregister(&ipp_driver);
 #endif
 
+#ifdef CONFIG_DRM_EXYNOS_FIMC
+	platform_driver_unregister(&fimc_driver);
+#endif
+
 #ifdef CONFIG_DRM_EXYNOS_G2D
 	platform_driver_unregister(&g2d_driver);
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index 44ab3c7b6a90..63803508e4df 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -349,5 +349,6 @@ extern struct platform_driver mixer_driver;
 extern struct platform_driver exynos_drm_common_hdmi_driver;
 extern struct platform_driver vidi_driver;
 extern struct platform_driver g2d_driver;
+extern struct platform_driver fimc_driver;
 extern struct platform_driver ipp_driver;
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
new file mode 100644
index 000000000000..61ea24296b52
--- /dev/null
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -0,0 +1,2001 @@
+/*
+ * Copyright (C) 2012 Samsung Electronics Co.Ltd
+ * Authors:
+ *	Eunchul Kim <chulspro.kim@samsung.com>
+ *	Jinyoung Jeon <jy0.jeon@samsung.com>
+ *	Sangmin Lee <lsmin.lee@samsung.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/pm_runtime.h>
+#include <plat/map-base.h>
+
+#include <drm/drmP.h>
+#include <drm/exynos_drm.h>
+#include "regs-fimc.h"
+#include "exynos_drm_ipp.h"
+#include "exynos_drm_fimc.h"
+
+/*
+ * FIMC is stand for Fully Interactive Mobile Camera and
+ * supports image scaler/rotator and input/output DMA operations.
+ * input DMA reads image data from the memory.
+ * output DMA writes image data to memory.
+ * FIMC supports image rotation and image effect functions.
+ *
+ * M2M operation : supports crop/scale/rotation/csc so on.
+ * Memory ----> FIMC H/W ----> Memory.
+ * Writeback operation : supports cloned screen with FIMD.
+ * FIMD ----> FIMC H/W ----> Memory.
+ * Output operation : supports direct display using local path.
+ * Memory ----> FIMC H/W ----> FIMD.
+ */
+
+/*
+ * TODO
+ * 1. check suspend/resume api if needed.
+ * 2. need to check use case platform_device_id.
+ * 3. check src/dst size with, height.
+ * 4. added check_prepare api for right register.
+ * 5. need to add supported list in prop_list.
+ * 6. check prescaler/scaler optimization.
+ */
+
+#define FIMC_MAX_DEVS	4
+#define FIMC_MAX_SRC	2
+#define FIMC_MAX_DST	32
+#define FIMC_SHFACTOR	10
+#define FIMC_BUF_STOP	1
+#define FIMC_BUF_START	2
+#define FIMC_REG_SZ		32
+#define FIMC_WIDTH_ITU_709	1280
+#define FIMC_REFRESH_MAX	60
+#define FIMC_REFRESH_MIN	12
+#define FIMC_CROP_MAX	8192
+#define FIMC_CROP_MIN	32
+#define FIMC_SCALE_MAX	4224
+#define FIMC_SCALE_MIN	32
+
+#define get_fimc_context(dev)	platform_get_drvdata(to_platform_device(dev))
+#define get_ctx_from_ippdrv(ippdrv)	container_of(ippdrv,\
+					struct fimc_context, ippdrv);
+#define fimc_read(offset)		readl(ctx->regs + (offset))
+#define fimc_write(cfg, offset)	writel(cfg, ctx->regs + (offset))
+
+enum fimc_wb {
+	FIMC_WB_NONE,
+	FIMC_WB_A,
+	FIMC_WB_B,
+};
+
+/*
+ * A structure of scaler.
+ *
+ * @range: narrow, wide.
+ * @bypass: unused scaler path.
+ * @up_h: horizontal scale up.
+ * @up_v: vertical scale up.
+ * @hratio: horizontal ratio.
+ * @vratio: vertical ratio.
+ */
+struct fimc_scaler {
+	bool	range;
+	bool bypass;
+	bool up_h;
+	bool up_v;
+	u32 hratio;
+	u32 vratio;
+};
+
+/*
+ * A structure of scaler capability.
+ *
+ * find user manual table 43-1.
+ * @in_hori: scaler input horizontal size.
+ * @bypass: scaler bypass mode.
+ * @dst_h_wo_rot: target horizontal size without output rotation.
+ * @dst_h_rot: target horizontal size with output rotation.
+ * @rl_w_wo_rot: real width without input rotation.
+ * @rl_h_rot: real height without output rotation.
+ */
+struct fimc_capability {
+	/* scaler */
+	u32	in_hori;
+	u32	bypass;
+	/* output rotator */
+	u32	dst_h_wo_rot;
+	u32	dst_h_rot;
+	/* input rotator */
+	u32	rl_w_wo_rot;
+	u32	rl_h_rot;
+};
+
+/*
+ * A structure of fimc driver data.
+ *
+ * @parent_clk: name of parent clock.
+ */
+struct fimc_driverdata {
+	char	*parent_clk;
+};
+
+/*
+ * A structure of fimc context.
+ *
+ * @ippdrv: prepare initialization using ippdrv.
+ * @regs_res: register resources.
+ * @regs: memory mapped io registers.
+ * @lock: locking of operations.
+ * @sclk_fimc_clk: fimc source clock.
+ * @fimc_clk: fimc clock.
+ * @wb_clk: writeback a clock.
+ * @wb_b_clk: writeback b clock.
+ * @sc: scaler infomations.
+ * @odr: ordering of YUV.
+ * @ver: fimc version.
+ * @pol: porarity of writeback.
+ * @id: fimc id.
+ * @irq: irq number.
+ * @suspended: qos operations.
+ */
+struct fimc_context {
+	struct exynos_drm_ippdrv	ippdrv;
+	struct resource	*regs_res;
+	void __iomem	*regs;
+	struct mutex	lock;
+	struct clk	*sclk_fimc_clk;
+	struct clk	*fimc_clk;
+	struct clk	*wb_clk;
+	struct clk	*wb_b_clk;
+	struct fimc_scaler	sc;
+	struct fimc_driverdata	*ddata;
+	struct exynos_drm_ipp_pol	pol;
+	int	id;
+	int	irq;
+	bool	suspended;
+};
+
+static void fimc_sw_reset(struct fimc_context *ctx, bool pattern)
+{
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:pattern[%d]\n", __func__, pattern);
+
+	cfg = fimc_read(EXYNOS_CISRCFMT);
+	cfg |= EXYNOS_CISRCFMT_ITU601_8BIT;
+	if (pattern)
+		cfg |= EXYNOS_CIGCTRL_TESTPATTERN_COLOR_BAR;
+
+	fimc_write(cfg, EXYNOS_CISRCFMT);
+
+	/* s/w reset */
+	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg |= (EXYNOS_CIGCTRL_SWRST);
+	fimc_write(cfg, EXYNOS_CIGCTRL);
+
+	/* s/w reset complete */
+	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg &= ~EXYNOS_CIGCTRL_SWRST;
+	fimc_write(cfg, EXYNOS_CIGCTRL);
+
+	/* reset sequence */
+	fimc_write(0x0, EXYNOS_CIFCNTSEQ);
+}
+
+static void fimc_set_camblk_fimd0_wb(struct fimc_context *ctx)
+{
+	u32 camblk_cfg;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	camblk_cfg = readl(SYSREG_CAMERA_BLK);
+	camblk_cfg &= ~(SYSREG_FIMD0WB_DEST_MASK);
+	camblk_cfg |= ctx->id << (SYSREG_FIMD0WB_DEST_SHIFT);
+
+	writel(camblk_cfg, SYSREG_CAMERA_BLK);
+}
+
+static void fimc_set_type_ctrl(struct fimc_context *ctx, enum fimc_wb wb)
+{
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:wb[%d]\n", __func__, wb);
+
+	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg &= ~(EXYNOS_CIGCTRL_TESTPATTERN_MASK |
+		EXYNOS_CIGCTRL_SELCAM_ITU_MASK |
+		EXYNOS_CIGCTRL_SELCAM_MIPI_MASK |
+		EXYNOS_CIGCTRL_SELCAM_FIMC_MASK |
+		EXYNOS_CIGCTRL_SELWB_CAMIF_MASK |
+		EXYNOS_CIGCTRL_SELWRITEBACK_MASK);
+
+	switch (wb) {
+	case FIMC_WB_A:
+		cfg |= (EXYNOS_CIGCTRL_SELWRITEBACK_A |
+			EXYNOS_CIGCTRL_SELWB_CAMIF_WRITEBACK);
+		break;
+	case FIMC_WB_B:
+		cfg |= (EXYNOS_CIGCTRL_SELWRITEBACK_B |
+			EXYNOS_CIGCTRL_SELWB_CAMIF_WRITEBACK);
+		break;
+	case FIMC_WB_NONE:
+	default:
+		cfg |= (EXYNOS_CIGCTRL_SELCAM_ITU_A |
+			EXYNOS_CIGCTRL_SELWRITEBACK_A |
+			EXYNOS_CIGCTRL_SELCAM_MIPI_A |
+			EXYNOS_CIGCTRL_SELCAM_FIMC_ITU);
+		break;
+	}
+
+	fimc_write(cfg, EXYNOS_CIGCTRL);
+}
+
+static void fimc_set_polarity(struct fimc_context *ctx,
+		struct exynos_drm_ipp_pol *pol)
+{
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:inv_pclk[%d]inv_vsync[%d]\n",
+		__func__, pol->inv_pclk, pol->inv_vsync);
+	DRM_DEBUG_KMS("%s:inv_href[%d]inv_hsync[%d]\n",
+		__func__, pol->inv_href, pol->inv_hsync);
+
+	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg &= ~(EXYNOS_CIGCTRL_INVPOLPCLK | EXYNOS_CIGCTRL_INVPOLVSYNC |
+		 EXYNOS_CIGCTRL_INVPOLHREF | EXYNOS_CIGCTRL_INVPOLHSYNC);
+
+	if (pol->inv_pclk)
+		cfg |= EXYNOS_CIGCTRL_INVPOLPCLK;
+	if (pol->inv_vsync)
+		cfg |= EXYNOS_CIGCTRL_INVPOLVSYNC;
+	if (pol->inv_href)
+		cfg |= EXYNOS_CIGCTRL_INVPOLHREF;
+	if (pol->inv_hsync)
+		cfg |= EXYNOS_CIGCTRL_INVPOLHSYNC;
+
+	fimc_write(cfg, EXYNOS_CIGCTRL);
+}
+
+static void fimc_handle_jpeg(struct fimc_context *ctx, bool enable)
+{
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:enable[%d]\n", __func__, enable);
+
+	cfg = fimc_read(EXYNOS_CIGCTRL);
+	if (enable)
+		cfg |= EXYNOS_CIGCTRL_CAM_JPEG;
+	else
+		cfg &= ~EXYNOS_CIGCTRL_CAM_JPEG;
+
+	fimc_write(cfg, EXYNOS_CIGCTRL);
+}
+
+static void fimc_handle_irq(struct fimc_context *ctx, bool enable,
+		bool overflow, bool level)
+{
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:enable[%d]overflow[%d]level[%d]\n", __func__,
+			enable, overflow, level);
+
+	cfg = fimc_read(EXYNOS_CIGCTRL);
+	if (enable) {
+		cfg &= ~(EXYNOS_CIGCTRL_IRQ_OVFEN | EXYNOS_CIGCTRL_IRQ_LEVEL);
+		cfg |= EXYNOS_CIGCTRL_IRQ_ENABLE;
+		if (overflow)
+			cfg |= EXYNOS_CIGCTRL_IRQ_OVFEN;
+		if (level)
+			cfg |= EXYNOS_CIGCTRL_IRQ_LEVEL;
+	} else
+		cfg &= ~(EXYNOS_CIGCTRL_IRQ_OVFEN | EXYNOS_CIGCTRL_IRQ_ENABLE);
+
+	fimc_write(cfg, EXYNOS_CIGCTRL);
+}
+
+static void fimc_clear_irq(struct fimc_context *ctx)
+{
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg |= EXYNOS_CIGCTRL_IRQ_CLR;
+	fimc_write(cfg, EXYNOS_CIGCTRL);
+}
+
+static bool fimc_check_ovf(struct fimc_context *ctx)
+{
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	u32 cfg, status, flag;
+
+	status = fimc_read(EXYNOS_CISTATUS);
+	flag = EXYNOS_CISTATUS_OVFIY | EXYNOS_CISTATUS_OVFICB |
+		EXYNOS_CISTATUS_OVFICR;
+
+	DRM_DEBUG_KMS("%s:flag[0x%x]\n", __func__, flag);
+
+	if (status & flag) {
+		cfg = fimc_read(EXYNOS_CIWDOFST);
+		cfg |= (EXYNOS_CIWDOFST_CLROVFIY | EXYNOS_CIWDOFST_CLROVFICB |
+			EXYNOS_CIWDOFST_CLROVFICR);
+
+		fimc_write(cfg, EXYNOS_CIWDOFST);
+
+		cfg = fimc_read(EXYNOS_CIWDOFST);
+		cfg &= ~(EXYNOS_CIWDOFST_CLROVFIY | EXYNOS_CIWDOFST_CLROVFICB |
+			EXYNOS_CIWDOFST_CLROVFICR);
+
+		fimc_write(cfg, EXYNOS_CIWDOFST);
+
+		dev_err(ippdrv->dev, "occured overflow at %d, status 0x%x.\n",
+			ctx->id, status);
+		return true;
+	}
+
+	return false;
+}
+
+static bool fimc_check_frame_end(struct fimc_context *ctx)
+{
+	u32 cfg;
+
+	cfg = fimc_read(EXYNOS_CISTATUS);
+
+	DRM_DEBUG_KMS("%s:cfg[0x%x]\n", __func__, cfg);
+
+	if (!(cfg & EXYNOS_CISTATUS_FRAMEEND))
+		return false;
+
+	cfg &= ~(EXYNOS_CISTATUS_FRAMEEND);
+	fimc_write(cfg, EXYNOS_CISTATUS);
+
+	return true;
+}
+
+static int fimc_get_buf_id(struct fimc_context *ctx)
+{
+	u32 cfg;
+	int frame_cnt, buf_id;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	cfg = fimc_read(EXYNOS_CISTATUS2);
+	frame_cnt = EXYNOS_CISTATUS2_GET_FRAMECOUNT_BEFORE(cfg);
+
+	if (frame_cnt == 0)
+		frame_cnt = EXYNOS_CISTATUS2_GET_FRAMECOUNT_PRESENT(cfg);
+
+	DRM_DEBUG_KMS("%s:present[%d]before[%d]\n", __func__,
+		EXYNOS_CISTATUS2_GET_FRAMECOUNT_PRESENT(cfg),
+		EXYNOS_CISTATUS2_GET_FRAMECOUNT_BEFORE(cfg));
+
+	if (frame_cnt == 0) {
+		DRM_ERROR("failed to get frame count.\n");
+		return -EIO;
+	}
+
+	buf_id = frame_cnt - 1;
+	DRM_DEBUG_KMS("%s:buf_id[%d]\n", __func__, buf_id);
+
+	return buf_id;
+}
+
+static void fimc_handle_lastend(struct fimc_context *ctx, bool enable)
+{
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:enable[%d]\n", __func__, enable);
+
+	cfg = fimc_read(EXYNOS_CIOCTRL);
+	if (enable)
+		cfg |= EXYNOS_CIOCTRL_LASTENDEN;
+	else
+		cfg &= ~EXYNOS_CIOCTRL_LASTENDEN;
+
+	fimc_write(cfg, EXYNOS_CIOCTRL);
+}
+
+
+static int fimc_src_set_fmt_order(struct fimc_context *ctx, u32 fmt)
+{
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:fmt[0x%x]\n", __func__, fmt);
+
+	/* RGB */
+	cfg = fimc_read(EXYNOS_CISCCTRL);
+	cfg &= ~EXYNOS_CISCCTRL_INRGB_FMT_RGB_MASK;
+
+	switch (fmt) {
+	case DRM_FORMAT_RGB565:
+		cfg |= EXYNOS_CISCCTRL_INRGB_FMT_RGB565;
+		fimc_write(cfg, EXYNOS_CISCCTRL);
+		return 0;
+	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_XRGB8888:
+		cfg |= EXYNOS_CISCCTRL_INRGB_FMT_RGB888;
+		fimc_write(cfg, EXYNOS_CISCCTRL);
+		return 0;
+	default:
+		/* bypass */
+		break;
+	}
+
+	/* YUV */
+	cfg = fimc_read(EXYNOS_MSCTRL);
+	cfg &= ~(EXYNOS_MSCTRL_ORDER2P_SHIFT_MASK |
+		EXYNOS_MSCTRL_C_INT_IN_2PLANE |
+		EXYNOS_MSCTRL_ORDER422_YCBYCR);
+
+	switch (fmt) {
+	case DRM_FORMAT_YUYV:
+		cfg |= EXYNOS_MSCTRL_ORDER422_YCBYCR;
+		break;
+	case DRM_FORMAT_YVYU:
+		cfg |= EXYNOS_MSCTRL_ORDER422_YCRYCB;
+		break;
+	case DRM_FORMAT_UYVY:
+		cfg |= EXYNOS_MSCTRL_ORDER422_CBYCRY;
+		break;
+	case DRM_FORMAT_VYUY:
+	case DRM_FORMAT_YUV444:
+		cfg |= EXYNOS_MSCTRL_ORDER422_CRYCBY;
+		break;
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV61:
+		cfg |= (EXYNOS_MSCTRL_ORDER2P_LSB_CRCB |
+			EXYNOS_MSCTRL_C_INT_IN_2PLANE);
+		break;
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+		cfg |= EXYNOS_MSCTRL_C_INT_IN_3PLANE;
+		break;
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV12MT:
+	case DRM_FORMAT_NV16:
+		cfg |= (EXYNOS_MSCTRL_ORDER2P_LSB_CBCR |
+			EXYNOS_MSCTRL_C_INT_IN_2PLANE);
+		break;
+	default:
+		dev_err(ippdrv->dev, "inavlid source yuv order 0x%x.\n", fmt);
+		return -EINVAL;
+	}
+
+	fimc_write(cfg, EXYNOS_MSCTRL);
+
+	return 0;
+}
+
+static int fimc_src_set_fmt(struct device *dev, u32 fmt)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:fmt[0x%x]\n", __func__, fmt);
+
+	cfg = fimc_read(EXYNOS_MSCTRL);
+	cfg &= ~EXYNOS_MSCTRL_INFORMAT_RGB;
+
+	switch (fmt) {
+	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_XRGB8888:
+		cfg |= EXYNOS_MSCTRL_INFORMAT_RGB;
+		break;
+	case DRM_FORMAT_YUV444:
+		cfg |= EXYNOS_MSCTRL_INFORMAT_YCBCR420;
+		break;
+	case DRM_FORMAT_YUYV:
+	case DRM_FORMAT_YVYU:
+	case DRM_FORMAT_UYVY:
+	case DRM_FORMAT_VYUY:
+		cfg |= EXYNOS_MSCTRL_INFORMAT_YCBCR422_1PLANE;
+		break;
+	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
+	case DRM_FORMAT_YUV422:
+		cfg |= EXYNOS_MSCTRL_INFORMAT_YCBCR422;
+		break;
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV12MT:
+		cfg |= EXYNOS_MSCTRL_INFORMAT_YCBCR420;
+		break;
+	default:
+		dev_err(ippdrv->dev, "inavlid source format 0x%x.\n", fmt);
+		return -EINVAL;
+	}
+
+	fimc_write(cfg, EXYNOS_MSCTRL);
+
+	cfg = fimc_read(EXYNOS_CIDMAPARAM);
+	cfg &= ~EXYNOS_CIDMAPARAM_R_MODE_MASK;
+
+	if (fmt == DRM_FORMAT_NV12MT)
+		cfg |= EXYNOS_CIDMAPARAM_R_MODE_64X32;
+	else
+		cfg |= EXYNOS_CIDMAPARAM_R_MODE_LINEAR;
+
+	fimc_write(cfg, EXYNOS_CIDMAPARAM);
+
+	return fimc_src_set_fmt_order(ctx, fmt);
+}
+
+static int fimc_src_set_transf(struct device *dev,
+		enum drm_exynos_degree degree,
+		enum drm_exynos_flip flip, bool *swap)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	u32 cfg1, cfg2;
+
+	DRM_DEBUG_KMS("%s:degree[%d]flip[0x%x]\n", __func__,
+		degree, flip);
+
+	cfg1 = fimc_read(EXYNOS_MSCTRL);
+	cfg1 &= ~(EXYNOS_MSCTRL_FLIP_X_MIRROR |
+		EXYNOS_MSCTRL_FLIP_Y_MIRROR);
+
+	cfg2 = fimc_read(EXYNOS_CITRGFMT);
+	cfg2 &= ~EXYNOS_CITRGFMT_INROT90_CLOCKWISE;
+
+	switch (degree) {
+	case EXYNOS_DRM_DEGREE_0:
+		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+			cfg1 |= EXYNOS_MSCTRL_FLIP_X_MIRROR;
+		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+			cfg1 |= EXYNOS_MSCTRL_FLIP_Y_MIRROR;
+		break;
+	case EXYNOS_DRM_DEGREE_90:
+		cfg2 |= EXYNOS_CITRGFMT_INROT90_CLOCKWISE;
+		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+			cfg1 |= EXYNOS_MSCTRL_FLIP_X_MIRROR;
+		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+			cfg1 |= EXYNOS_MSCTRL_FLIP_Y_MIRROR;
+		break;
+	case EXYNOS_DRM_DEGREE_180:
+		cfg1 |= (EXYNOS_MSCTRL_FLIP_X_MIRROR |
+			EXYNOS_MSCTRL_FLIP_Y_MIRROR);
+		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+			cfg1 &= ~EXYNOS_MSCTRL_FLIP_X_MIRROR;
+		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+			cfg1 &= ~EXYNOS_MSCTRL_FLIP_Y_MIRROR;
+		break;
+	case EXYNOS_DRM_DEGREE_270:
+		cfg1 |= (EXYNOS_MSCTRL_FLIP_X_MIRROR |
+			EXYNOS_MSCTRL_FLIP_Y_MIRROR);
+		cfg2 |= EXYNOS_CITRGFMT_INROT90_CLOCKWISE;
+		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+			cfg1 &= ~EXYNOS_MSCTRL_FLIP_X_MIRROR;
+		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+			cfg1 &= ~EXYNOS_MSCTRL_FLIP_Y_MIRROR;
+		break;
+	default:
+		dev_err(ippdrv->dev, "inavlid degree value %d.\n", degree);
+		return -EINVAL;
+	}
+
+	fimc_write(cfg1, EXYNOS_MSCTRL);
+	fimc_write(cfg2, EXYNOS_CITRGFMT);
+	*swap = (cfg2 & EXYNOS_CITRGFMT_INROT90_CLOCKWISE) ? 1 : 0;
+
+	return 0;
+}
+
+static int fimc_set_window(struct fimc_context *ctx,
+		struct drm_exynos_pos *pos, struct drm_exynos_sz *sz)
+{
+	u32 cfg, h1, h2, v1, v2;
+
+	/* cropped image */
+	h1 = pos->x;
+	h2 = sz->hsize - pos->w - pos->x;
+	v1 = pos->y;
+	v2 = sz->vsize - pos->h - pos->y;
+
+	DRM_DEBUG_KMS("%s:x[%d]y[%d]w[%d]h[%d]hsize[%d]vsize[%d]\n",
+	__func__, pos->x, pos->y, pos->w, pos->h, sz->hsize, sz->vsize);
+	DRM_DEBUG_KMS("%s:h1[%d]h2[%d]v1[%d]v2[%d]\n", __func__,
+		h1, h2, v1, v2);
+
+	/*
+	 * set window offset 1, 2 size
+	 * check figure 43-21 in user manual
+	 */
+	cfg = fimc_read(EXYNOS_CIWDOFST);
+	cfg &= ~(EXYNOS_CIWDOFST_WINHOROFST_MASK |
+		EXYNOS_CIWDOFST_WINVEROFST_MASK);
+	cfg |= (EXYNOS_CIWDOFST_WINHOROFST(h1) |
+		EXYNOS_CIWDOFST_WINVEROFST(v1));
+	cfg |= EXYNOS_CIWDOFST_WINOFSEN;
+	fimc_write(cfg, EXYNOS_CIWDOFST);
+
+	cfg = (EXYNOS_CIWDOFST2_WINHOROFST2(h2) |
+		EXYNOS_CIWDOFST2_WINVEROFST2(v2));
+	fimc_write(cfg, EXYNOS_CIWDOFST2);
+
+	return 0;
+}
+
+static int fimc_src_set_size(struct device *dev, int swap,
+		struct drm_exynos_pos *pos, struct drm_exynos_sz *sz)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct drm_exynos_pos img_pos = *pos;
+	struct drm_exynos_sz img_sz = *sz;
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:swap[%d]hsize[%d]vsize[%d]\n",
+		__func__, swap, sz->hsize, sz->vsize);
+
+	/* original size */
+	cfg = (EXYNOS_ORGISIZE_HORIZONTAL(img_sz.hsize) |
+		EXYNOS_ORGISIZE_VERTICAL(img_sz.vsize));
+
+	fimc_write(cfg, EXYNOS_ORGISIZE);
+
+	DRM_DEBUG_KMS("%s:x[%d]y[%d]w[%d]h[%d]\n", __func__,
+		pos->x, pos->y, pos->w, pos->h);
+
+	if (swap) {
+		img_pos.w = pos->h;
+		img_pos.h = pos->w;
+		img_sz.hsize = sz->vsize;
+		img_sz.vsize = sz->hsize;
+	}
+
+	/* set input DMA image size */
+	cfg = fimc_read(EXYNOS_CIREAL_ISIZE);
+	cfg &= ~(EXYNOS_CIREAL_ISIZE_HEIGHT_MASK |
+		EXYNOS_CIREAL_ISIZE_WIDTH_MASK);
+	cfg |= (EXYNOS_CIREAL_ISIZE_WIDTH(img_pos.w) |
+		EXYNOS_CIREAL_ISIZE_HEIGHT(img_pos.h));
+	fimc_write(cfg, EXYNOS_CIREAL_ISIZE);
+
+	/*
+	 * set input FIFO image size
+	 * for now, we support only ITU601 8 bit mode
+	 */
+	cfg = (EXYNOS_CISRCFMT_ITU601_8BIT |
+		EXYNOS_CISRCFMT_SOURCEHSIZE(img_sz.hsize) |
+		EXYNOS_CISRCFMT_SOURCEVSIZE(img_sz.vsize));
+	fimc_write(cfg, EXYNOS_CISRCFMT);
+
+	/* offset Y(RGB), Cb, Cr */
+	cfg = (EXYNOS_CIIYOFF_HORIZONTAL(img_pos.x) |
+		EXYNOS_CIIYOFF_VERTICAL(img_pos.y));
+	fimc_write(cfg, EXYNOS_CIIYOFF);
+	cfg = (EXYNOS_CIICBOFF_HORIZONTAL(img_pos.x) |
+		EXYNOS_CIICBOFF_VERTICAL(img_pos.y));
+	fimc_write(cfg, EXYNOS_CIICBOFF);
+	cfg = (EXYNOS_CIICROFF_HORIZONTAL(img_pos.x) |
+		EXYNOS_CIICROFF_VERTICAL(img_pos.y));
+	fimc_write(cfg, EXYNOS_CIICROFF);
+
+	return fimc_set_window(ctx, &img_pos, &img_sz);
+}
+
+static int fimc_src_set_addr(struct device *dev,
+		struct drm_exynos_ipp_buf_info *buf_info, u32 buf_id,
+		enum drm_exynos_ipp_buf_type buf_type)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->cmd;
+	struct drm_exynos_ipp_property *property;
+	struct drm_exynos_ipp_config *config;
+
+	if (!c_node) {
+		DRM_ERROR("failed to get c_node.\n");
+		return -EINVAL;
+	}
+
+	property = &c_node->property;
+	if (!property) {
+		DRM_ERROR("failed to get property.\n");
+		return -EINVAL;
+	}
+
+	DRM_DEBUG_KMS("%s:prop_id[%d]buf_id[%d]buf_type[%d]\n", __func__,
+		property->prop_id, buf_id, buf_type);
+
+	if (buf_id > FIMC_MAX_SRC) {
+		dev_info(ippdrv->dev, "inavlid buf_id %d.\n", buf_id);
+		return -ENOMEM;
+	}
+
+	/* address register set */
+	switch (buf_type) {
+	case IPP_BUF_ENQUEUE:
+		config = &property->config[EXYNOS_DRM_OPS_SRC];
+		fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_Y],
+			EXYNOS_CIIYSA(buf_id));
+
+		if (config->fmt == DRM_FORMAT_YVU420) {
+			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CR],
+				EXYNOS_CIICBSA(buf_id));
+			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CB],
+				EXYNOS_CIICRSA(buf_id));
+		} else {
+			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CB],
+				EXYNOS_CIICBSA(buf_id));
+			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CR],
+				EXYNOS_CIICRSA(buf_id));
+		}
+		break;
+	case IPP_BUF_DEQUEUE:
+		fimc_write(0x0, EXYNOS_CIIYSA(buf_id));
+		fimc_write(0x0, EXYNOS_CIICBSA(buf_id));
+		fimc_write(0x0, EXYNOS_CIICRSA(buf_id));
+		break;
+	default:
+		/* bypass */
+		break;
+	}
+
+	return 0;
+}
+
+static struct exynos_drm_ipp_ops fimc_src_ops = {
+	.set_fmt = fimc_src_set_fmt,
+	.set_transf = fimc_src_set_transf,
+	.set_size = fimc_src_set_size,
+	.set_addr = fimc_src_set_addr,
+};
+
+static int fimc_dst_set_fmt_order(struct fimc_context *ctx, u32 fmt)
+{
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:fmt[0x%x]\n", __func__, fmt);
+
+	/* RGB */
+	cfg = fimc_read(EXYNOS_CISCCTRL);
+	cfg &= ~EXYNOS_CISCCTRL_OUTRGB_FMT_RGB_MASK;
+
+	switch (fmt) {
+	case DRM_FORMAT_RGB565:
+		cfg |= EXYNOS_CISCCTRL_OUTRGB_FMT_RGB565;
+		fimc_write(cfg, EXYNOS_CISCCTRL);
+		return 0;
+	case DRM_FORMAT_RGB888:
+		cfg |= EXYNOS_CISCCTRL_OUTRGB_FMT_RGB888;
+		fimc_write(cfg, EXYNOS_CISCCTRL);
+		return 0;
+	case DRM_FORMAT_XRGB8888:
+		cfg |= (EXYNOS_CISCCTRL_OUTRGB_FMT_RGB888 |
+			EXYNOS_CISCCTRL_EXTRGB_EXTENSION);
+		fimc_write(cfg, EXYNOS_CISCCTRL);
+		break;
+	default:
+		/* bypass */
+		break;
+	}
+
+	/* YUV */
+	cfg = fimc_read(EXYNOS_CIOCTRL);
+	cfg &= ~(EXYNOS_CIOCTRL_ORDER2P_MASK |
+		EXYNOS_CIOCTRL_ORDER422_MASK |
+		EXYNOS_CIOCTRL_YCBCR_PLANE_MASK);
+
+	switch (fmt) {
+	case DRM_FORMAT_XRGB8888:
+		cfg |= EXYNOS_CIOCTRL_ALPHA_OUT;
+		break;
+	case DRM_FORMAT_YUYV:
+		cfg |= EXYNOS_CIOCTRL_ORDER422_YCBYCR;
+		break;
+	case DRM_FORMAT_YVYU:
+		cfg |= EXYNOS_CIOCTRL_ORDER422_YCRYCB;
+		break;
+	case DRM_FORMAT_UYVY:
+		cfg |= EXYNOS_CIOCTRL_ORDER422_CBYCRY;
+		break;
+	case DRM_FORMAT_VYUY:
+		cfg |= EXYNOS_CIOCTRL_ORDER422_CRYCBY;
+		break;
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV61:
+		cfg |= EXYNOS_CIOCTRL_ORDER2P_LSB_CRCB;
+		cfg |= EXYNOS_CIOCTRL_YCBCR_2PLANE;
+		break;
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+		cfg |= EXYNOS_CIOCTRL_YCBCR_3PLANE;
+		break;
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV12MT:
+	case DRM_FORMAT_NV16:
+		cfg |= EXYNOS_CIOCTRL_ORDER2P_LSB_CBCR;
+		cfg |= EXYNOS_CIOCTRL_YCBCR_2PLANE;
+		break;
+	default:
+		dev_err(ippdrv->dev, "inavlid target yuv order 0x%x.\n", fmt);
+		return -EINVAL;
+	}
+
+	fimc_write(cfg, EXYNOS_CIOCTRL);
+
+	return 0;
+}
+
+static int fimc_dst_set_fmt(struct device *dev, u32 fmt)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:fmt[0x%x]\n", __func__, fmt);
+
+	cfg = fimc_read(EXYNOS_CIEXTEN);
+
+	if (fmt == DRM_FORMAT_AYUV) {
+		cfg |= EXYNOS_CIEXTEN_YUV444_OUT;
+		fimc_write(cfg, EXYNOS_CIEXTEN);
+	} else {
+		cfg &= ~EXYNOS_CIEXTEN_YUV444_OUT;
+		fimc_write(cfg, EXYNOS_CIEXTEN);
+
+		cfg = fimc_read(EXYNOS_CITRGFMT);
+		cfg &= ~EXYNOS_CITRGFMT_OUTFORMAT_MASK;
+
+		switch (fmt) {
+		case DRM_FORMAT_RGB565:
+		case DRM_FORMAT_RGB888:
+		case DRM_FORMAT_XRGB8888:
+			cfg |= EXYNOS_CITRGFMT_OUTFORMAT_RGB;
+			break;
+		case DRM_FORMAT_YUYV:
+		case DRM_FORMAT_YVYU:
+		case DRM_FORMAT_UYVY:
+		case DRM_FORMAT_VYUY:
+			cfg |= EXYNOS_CITRGFMT_OUTFORMAT_YCBCR422_1PLANE;
+			break;
+		case DRM_FORMAT_NV16:
+		case DRM_FORMAT_NV61:
+		case DRM_FORMAT_YUV422:
+			cfg |= EXYNOS_CITRGFMT_OUTFORMAT_YCBCR422;
+			break;
+		case DRM_FORMAT_YUV420:
+		case DRM_FORMAT_YVU420:
+		case DRM_FORMAT_NV12:
+		case DRM_FORMAT_NV12MT:
+		case DRM_FORMAT_NV21:
+			cfg |= EXYNOS_CITRGFMT_OUTFORMAT_YCBCR420;
+			break;
+		default:
+			dev_err(ippdrv->dev, "inavlid target format 0x%x.\n",
+				fmt);
+			return -EINVAL;
+		}
+
+		fimc_write(cfg, EXYNOS_CITRGFMT);
+	}
+
+	cfg = fimc_read(EXYNOS_CIDMAPARAM);
+	cfg &= ~EXYNOS_CIDMAPARAM_W_MODE_MASK;
+
+	if (fmt == DRM_FORMAT_NV12MT)
+		cfg |= EXYNOS_CIDMAPARAM_W_MODE_64X32;
+	else
+		cfg |= EXYNOS_CIDMAPARAM_W_MODE_LINEAR;
+
+	fimc_write(cfg, EXYNOS_CIDMAPARAM);
+
+	return fimc_dst_set_fmt_order(ctx, fmt);
+}
+
+static int fimc_dst_set_transf(struct device *dev,
+		enum drm_exynos_degree degree,
+		enum drm_exynos_flip flip, bool *swap)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:degree[%d]flip[0x%x]\n", __func__,
+		degree, flip);
+
+	cfg = fimc_read(EXYNOS_CITRGFMT);
+	cfg &= ~EXYNOS_CITRGFMT_FLIP_MASK;
+	cfg &= ~EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE;
+
+	switch (degree) {
+	case EXYNOS_DRM_DEGREE_0:
+		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+			cfg |= EXYNOS_CITRGFMT_FLIP_X_MIRROR;
+		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+			cfg |= EXYNOS_CITRGFMT_FLIP_Y_MIRROR;
+		break;
+	case EXYNOS_DRM_DEGREE_90:
+		cfg |= EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE;
+		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+			cfg |= EXYNOS_CITRGFMT_FLIP_X_MIRROR;
+		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+			cfg |= EXYNOS_CITRGFMT_FLIP_Y_MIRROR;
+		break;
+	case EXYNOS_DRM_DEGREE_180:
+		cfg |= (EXYNOS_CITRGFMT_FLIP_X_MIRROR |
+			EXYNOS_CITRGFMT_FLIP_Y_MIRROR);
+		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+			cfg &= ~EXYNOS_CITRGFMT_FLIP_X_MIRROR;
+		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+			cfg &= ~EXYNOS_CITRGFMT_FLIP_Y_MIRROR;
+		break;
+	case EXYNOS_DRM_DEGREE_270:
+		cfg |= (EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE |
+			EXYNOS_CITRGFMT_FLIP_X_MIRROR |
+			EXYNOS_CITRGFMT_FLIP_Y_MIRROR);
+		if (flip & EXYNOS_DRM_FLIP_VERTICAL)
+			cfg &= ~EXYNOS_CITRGFMT_FLIP_X_MIRROR;
+		if (flip & EXYNOS_DRM_FLIP_HORIZONTAL)
+			cfg &= ~EXYNOS_CITRGFMT_FLIP_Y_MIRROR;
+		break;
+	default:
+		dev_err(ippdrv->dev, "inavlid degree value %d.\n", degree);
+		return -EINVAL;
+	}
+
+	fimc_write(cfg, EXYNOS_CITRGFMT);
+	*swap = (cfg & EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE) ? 1 : 0;
+
+	return 0;
+}
+
+static int fimc_get_ratio_shift(u32 src, u32 dst, u32 *ratio, u32 *shift)
+{
+	DRM_DEBUG_KMS("%s:src[%d]dst[%d]\n", __func__, src, dst);
+
+	if (src >= dst * 64) {
+		DRM_ERROR("failed to make ratio and shift.\n");
+		return -EINVAL;
+	} else if (src >= dst * 32) {
+		*ratio = 32;
+		*shift = 5;
+	} else if (src >= dst * 16) {
+		*ratio = 16;
+		*shift = 4;
+	} else if (src >= dst * 8) {
+		*ratio = 8;
+		*shift = 3;
+	} else if (src >= dst * 4) {
+		*ratio = 4;
+		*shift = 2;
+	} else if (src >= dst * 2) {
+		*ratio = 2;
+		*shift = 1;
+	} else {
+		*ratio = 1;
+		*shift = 0;
+	}
+
+	return 0;
+}
+
+static int fimc_set_prescaler(struct fimc_context *ctx, struct fimc_scaler *sc,
+		struct drm_exynos_pos *src, struct drm_exynos_pos *dst)
+{
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	u32 cfg, cfg_ext, shfactor;
+	u32 pre_dst_width, pre_dst_height;
+	u32 pre_hratio, hfactor, pre_vratio, vfactor;
+	int ret = 0;
+	u32 src_w, src_h, dst_w, dst_h;
+
+	cfg_ext = fimc_read(EXYNOS_CITRGFMT);
+	if (cfg_ext & EXYNOS_CITRGFMT_INROT90_CLOCKWISE) {
+		src_w = src->h;
+		src_h = src->w;
+	} else {
+		src_w = src->w;
+		src_h = src->h;
+	}
+
+	if (cfg_ext & EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE) {
+		dst_w = dst->h;
+		dst_h = dst->w;
+	} else {
+		dst_w = dst->w;
+		dst_h = dst->h;
+	}
+
+	ret = fimc_get_ratio_shift(src_w, dst_w, &pre_hratio, &hfactor);
+	if (ret) {
+		dev_err(ippdrv->dev, "failed to get ratio horizontal.\n");
+		return ret;
+	}
+
+	ret = fimc_get_ratio_shift(src_h, dst_h, &pre_vratio, &vfactor);
+	if (ret) {
+		dev_err(ippdrv->dev, "failed to get ratio vertical.\n");
+		return ret;
+	}
+
+	pre_dst_width = src_w / pre_hratio;
+	pre_dst_height = src_h / pre_vratio;
+	DRM_DEBUG_KMS("%s:pre_dst_width[%d]pre_dst_height[%d]\n", __func__,
+		pre_dst_width, pre_dst_height);
+	DRM_DEBUG_KMS("%s:pre_hratio[%d]hfactor[%d]pre_vratio[%d]vfactor[%d]\n",
+		__func__, pre_hratio, hfactor, pre_vratio, vfactor);
+
+	sc->hratio = (src_w << 14) / (dst_w << hfactor);
+	sc->vratio = (src_h << 14) / (dst_h << vfactor);
+	sc->up_h = (dst_w >= src_w) ? true : false;
+	sc->up_v = (dst_h >= src_h) ? true : false;
+	DRM_DEBUG_KMS("%s:hratio[%d]vratio[%d]up_h[%d]up_v[%d]\n",
+	__func__, sc->hratio, sc->vratio, sc->up_h, sc->up_v);
+
+	shfactor = FIMC_SHFACTOR - (hfactor + vfactor);
+	DRM_DEBUG_KMS("%s:shfactor[%d]\n", __func__, shfactor);
+
+	cfg = (EXYNOS_CISCPRERATIO_SHFACTOR(shfactor) |
+		EXYNOS_CISCPRERATIO_PREHORRATIO(pre_hratio) |
+		EXYNOS_CISCPRERATIO_PREVERRATIO(pre_vratio));
+	fimc_write(cfg, EXYNOS_CISCPRERATIO);
+
+	cfg = (EXYNOS_CISCPREDST_PREDSTWIDTH(pre_dst_width) |
+		EXYNOS_CISCPREDST_PREDSTHEIGHT(pre_dst_height));
+	fimc_write(cfg, EXYNOS_CISCPREDST);
+
+	return ret;
+}
+
+static void fimc_set_scaler(struct fimc_context *ctx, struct fimc_scaler *sc)
+{
+	u32 cfg, cfg_ext;
+
+	DRM_DEBUG_KMS("%s:range[%d]bypass[%d]up_h[%d]up_v[%d]\n",
+		__func__, sc->range, sc->bypass, sc->up_h, sc->up_v);
+	DRM_DEBUG_KMS("%s:hratio[%d]vratio[%d]\n",
+		__func__, sc->hratio, sc->vratio);
+
+	cfg = fimc_read(EXYNOS_CISCCTRL);
+	cfg &= ~(EXYNOS_CISCCTRL_SCALERBYPASS |
+		EXYNOS_CISCCTRL_SCALEUP_H | EXYNOS_CISCCTRL_SCALEUP_V |
+		EXYNOS_CISCCTRL_MAIN_V_RATIO_MASK |
+		EXYNOS_CISCCTRL_MAIN_H_RATIO_MASK |
+		EXYNOS_CISCCTRL_CSCR2Y_WIDE |
+		EXYNOS_CISCCTRL_CSCY2R_WIDE);
+
+	if (sc->range)
+		cfg |= (EXYNOS_CISCCTRL_CSCR2Y_WIDE |
+			EXYNOS_CISCCTRL_CSCY2R_WIDE);
+	if (sc->bypass)
+		cfg |= EXYNOS_CISCCTRL_SCALERBYPASS;
+	if (sc->up_h)
+		cfg |= EXYNOS_CISCCTRL_SCALEUP_H;
+	if (sc->up_v)
+		cfg |= EXYNOS_CISCCTRL_SCALEUP_V;
+
+	cfg |= (EXYNOS_CISCCTRL_MAINHORRATIO((sc->hratio >> 6)) |
+		EXYNOS_CISCCTRL_MAINVERRATIO((sc->vratio >> 6)));
+	fimc_write(cfg, EXYNOS_CISCCTRL);
+
+	cfg_ext = fimc_read(EXYNOS_CIEXTEN);
+	cfg_ext &= ~EXYNOS_CIEXTEN_MAINHORRATIO_EXT_MASK;
+	cfg_ext &= ~EXYNOS_CIEXTEN_MAINVERRATIO_EXT_MASK;
+	cfg_ext |= (EXYNOS_CIEXTEN_MAINHORRATIO_EXT(sc->hratio) |
+		EXYNOS_CIEXTEN_MAINVERRATIO_EXT(sc->vratio));
+	fimc_write(cfg_ext, EXYNOS_CIEXTEN);
+}
+
+static int fimc_dst_set_size(struct device *dev, int swap,
+		struct drm_exynos_pos *pos, struct drm_exynos_sz *sz)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct drm_exynos_pos img_pos = *pos;
+	struct drm_exynos_sz img_sz = *sz;
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:swap[%d]hsize[%d]vsize[%d]\n",
+		__func__, swap, sz->hsize, sz->vsize);
+
+	/* original size */
+	cfg = (EXYNOS_ORGOSIZE_HORIZONTAL(img_sz.hsize) |
+		EXYNOS_ORGOSIZE_VERTICAL(img_sz.vsize));
+
+	fimc_write(cfg, EXYNOS_ORGOSIZE);
+
+	DRM_DEBUG_KMS("%s:x[%d]y[%d]w[%d]h[%d]\n",
+		__func__, pos->x, pos->y, pos->w, pos->h);
+
+	/* CSC ITU */
+	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg &= ~EXYNOS_CIGCTRL_CSC_MASK;
+
+	if (sz->hsize >= FIMC_WIDTH_ITU_709)
+		cfg |= EXYNOS_CIGCTRL_CSC_ITU709;
+	else
+		cfg |= EXYNOS_CIGCTRL_CSC_ITU601;
+
+	fimc_write(cfg, EXYNOS_CIGCTRL);
+
+	if (swap) {
+		img_pos.w = pos->h;
+		img_pos.h = pos->w;
+		img_sz.hsize = sz->vsize;
+		img_sz.vsize = sz->hsize;
+	}
+
+	/* target image size */
+	cfg = fimc_read(EXYNOS_CITRGFMT);
+	cfg &= ~(EXYNOS_CITRGFMT_TARGETH_MASK |
+		EXYNOS_CITRGFMT_TARGETV_MASK);
+	cfg |= (EXYNOS_CITRGFMT_TARGETHSIZE(img_pos.w) |
+		EXYNOS_CITRGFMT_TARGETVSIZE(img_pos.h));
+	fimc_write(cfg, EXYNOS_CITRGFMT);
+
+	/* target area */
+	cfg = EXYNOS_CITAREA_TARGET_AREA(img_pos.w * img_pos.h);
+	fimc_write(cfg, EXYNOS_CITAREA);
+
+	/* offset Y(RGB), Cb, Cr */
+	cfg = (EXYNOS_CIOYOFF_HORIZONTAL(img_pos.x) |
+		EXYNOS_CIOYOFF_VERTICAL(img_pos.y));
+	fimc_write(cfg, EXYNOS_CIOYOFF);
+	cfg = (EXYNOS_CIOCBOFF_HORIZONTAL(img_pos.x) |
+		EXYNOS_CIOCBOFF_VERTICAL(img_pos.y));
+	fimc_write(cfg, EXYNOS_CIOCBOFF);
+	cfg = (EXYNOS_CIOCROFF_HORIZONTAL(img_pos.x) |
+		EXYNOS_CIOCROFF_VERTICAL(img_pos.y));
+	fimc_write(cfg, EXYNOS_CIOCROFF);
+
+	return 0;
+}
+
+static int fimc_dst_get_buf_seq(struct fimc_context *ctx)
+{
+	u32 cfg, i, buf_num = 0;
+	u32 mask = 0x00000001;
+
+	cfg = fimc_read(EXYNOS_CIFCNTSEQ);
+
+	for (i = 0; i < FIMC_REG_SZ; i++)
+		if (cfg & (mask << i))
+			buf_num++;
+
+	DRM_DEBUG_KMS("%s:buf_num[%d]\n", __func__, buf_num);
+
+	return buf_num;
+}
+
+static int fimc_dst_set_buf_seq(struct fimc_context *ctx, u32 buf_id,
+		enum drm_exynos_ipp_buf_type buf_type)
+{
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	bool enable;
+	u32 cfg;
+	u32 mask = 0x00000001 << buf_id;
+	int ret = 0;
+
+	DRM_DEBUG_KMS("%s:buf_id[%d]buf_type[%d]\n", __func__,
+		buf_id, buf_type);
+
+	mutex_lock(&ctx->lock);
+
+	/* mask register set */
+	cfg = fimc_read(EXYNOS_CIFCNTSEQ);
+
+	switch (buf_type) {
+	case IPP_BUF_ENQUEUE:
+		enable = true;
+		break;
+	case IPP_BUF_DEQUEUE:
+		enable = false;
+		break;
+	default:
+		dev_err(ippdrv->dev, "invalid buf ctrl parameter.\n");
+		ret =  -EINVAL;
+		goto err_unlock;
+	}
+
+	/* sequence id */
+	cfg &= (~mask);
+	cfg |= (enable << buf_id);
+	fimc_write(cfg, EXYNOS_CIFCNTSEQ);
+
+	/* interrupt enable */
+	if (buf_type == IPP_BUF_ENQUEUE &&
+	    fimc_dst_get_buf_seq(ctx) >= FIMC_BUF_START)
+		fimc_handle_irq(ctx, true, false, true);
+
+	/* interrupt disable */
+	if (buf_type == IPP_BUF_DEQUEUE &&
+	    fimc_dst_get_buf_seq(ctx) <= FIMC_BUF_STOP)
+		fimc_handle_irq(ctx, false, false, true);
+
+err_unlock:
+	mutex_unlock(&ctx->lock);
+	return ret;
+}
+
+static int fimc_dst_set_addr(struct device *dev,
+		struct drm_exynos_ipp_buf_info *buf_info, u32 buf_id,
+		enum drm_exynos_ipp_buf_type buf_type)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->cmd;
+	struct drm_exynos_ipp_property *property;
+	struct drm_exynos_ipp_config *config;
+
+	if (!c_node) {
+		DRM_ERROR("failed to get c_node.\n");
+		return -EINVAL;
+	}
+
+	property = &c_node->property;
+	if (!property) {
+		DRM_ERROR("failed to get property.\n");
+		return -EINVAL;
+	}
+
+	DRM_DEBUG_KMS("%s:prop_id[%d]buf_id[%d]buf_type[%d]\n", __func__,
+		property->prop_id, buf_id, buf_type);
+
+	if (buf_id > FIMC_MAX_DST) {
+		dev_info(ippdrv->dev, "inavlid buf_id %d.\n", buf_id);
+		return -ENOMEM;
+	}
+
+	/* address register set */
+	switch (buf_type) {
+	case IPP_BUF_ENQUEUE:
+		config = &property->config[EXYNOS_DRM_OPS_DST];
+
+		fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_Y],
+			EXYNOS_CIOYSA(buf_id));
+
+		if (config->fmt == DRM_FORMAT_YVU420) {
+			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CR],
+				EXYNOS_CIOCBSA(buf_id));
+			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CB],
+				EXYNOS_CIOCRSA(buf_id));
+		} else {
+			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CB],
+				EXYNOS_CIOCBSA(buf_id));
+			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CR],
+				EXYNOS_CIOCRSA(buf_id));
+		}
+		break;
+	case IPP_BUF_DEQUEUE:
+		fimc_write(0x0, EXYNOS_CIOYSA(buf_id));
+		fimc_write(0x0, EXYNOS_CIOCBSA(buf_id));
+		fimc_write(0x0, EXYNOS_CIOCRSA(buf_id));
+		break;
+	default:
+		/* bypass */
+		break;
+	}
+
+	return fimc_dst_set_buf_seq(ctx, buf_id, buf_type);
+}
+
+static struct exynos_drm_ipp_ops fimc_dst_ops = {
+	.set_fmt = fimc_dst_set_fmt,
+	.set_transf = fimc_dst_set_transf,
+	.set_size = fimc_dst_set_size,
+	.set_addr = fimc_dst_set_addr,
+};
+
+static int fimc_clk_ctrl(struct fimc_context *ctx, bool enable)
+{
+	DRM_DEBUG_KMS("%s:enable[%d]\n", __func__, enable);
+
+	if (enable) {
+		clk_enable(ctx->sclk_fimc_clk);
+		clk_enable(ctx->fimc_clk);
+		clk_enable(ctx->wb_clk);
+		ctx->suspended = false;
+	} else {
+		clk_disable(ctx->sclk_fimc_clk);
+		clk_disable(ctx->fimc_clk);
+		clk_disable(ctx->wb_clk);
+		ctx->suspended = true;
+	}
+
+	return 0;
+}
+
+static irqreturn_t fimc_irq_handler(int irq, void *dev_id)
+{
+	struct fimc_context *ctx = dev_id;
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->cmd;
+	struct drm_exynos_ipp_event_work *event_work =
+		c_node->event_work;
+	int buf_id;
+
+	DRM_DEBUG_KMS("%s:fimc id[%d]\n", __func__, ctx->id);
+
+	fimc_clear_irq(ctx);
+	if (fimc_check_ovf(ctx))
+		return IRQ_NONE;
+
+	if (!fimc_check_frame_end(ctx))
+		return IRQ_NONE;
+
+	buf_id = fimc_get_buf_id(ctx);
+	if (buf_id < 0)
+		return IRQ_HANDLED;
+
+	DRM_DEBUG_KMS("%s:buf_id[%d]\n", __func__, buf_id);
+
+	if (fimc_dst_set_buf_seq(ctx, buf_id, IPP_BUF_DEQUEUE) < 0) {
+		DRM_ERROR("failed to dequeue.\n");
+		return IRQ_HANDLED;
+	}
+
+	event_work->ippdrv = ippdrv;
+	event_work->buf_id[EXYNOS_DRM_OPS_DST] = buf_id;
+	queue_work(ippdrv->event_workq, (struct work_struct *)event_work);
+
+	return IRQ_HANDLED;
+}
+
+static int fimc_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
+{
+	struct drm_exynos_ipp_prop_list *prop_list;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	prop_list = devm_kzalloc(ippdrv->dev, sizeof(*prop_list), GFP_KERNEL);
+	if (!prop_list) {
+		DRM_ERROR("failed to alloc property list.\n");
+		return -ENOMEM;
+	}
+
+	prop_list->version = 1;
+	prop_list->writeback = 1;
+	prop_list->refresh_min = FIMC_REFRESH_MIN;
+	prop_list->refresh_max = FIMC_REFRESH_MAX;
+	prop_list->flip = (1 << EXYNOS_DRM_FLIP_NONE) |
+				(1 << EXYNOS_DRM_FLIP_VERTICAL) |
+				(1 << EXYNOS_DRM_FLIP_HORIZONTAL);
+	prop_list->degree = (1 << EXYNOS_DRM_DEGREE_0) |
+				(1 << EXYNOS_DRM_DEGREE_90) |
+				(1 << EXYNOS_DRM_DEGREE_180) |
+				(1 << EXYNOS_DRM_DEGREE_270);
+	prop_list->csc = 1;
+	prop_list->crop = 1;
+	prop_list->crop_max.hsize = FIMC_CROP_MAX;
+	prop_list->crop_max.vsize = FIMC_CROP_MAX;
+	prop_list->crop_min.hsize = FIMC_CROP_MIN;
+	prop_list->crop_min.vsize = FIMC_CROP_MIN;
+	prop_list->scale = 1;
+	prop_list->scale_max.hsize = FIMC_SCALE_MAX;
+	prop_list->scale_max.vsize = FIMC_SCALE_MAX;
+	prop_list->scale_min.hsize = FIMC_SCALE_MIN;
+	prop_list->scale_min.vsize = FIMC_SCALE_MIN;
+
+	ippdrv->prop_list = prop_list;
+
+	return 0;
+}
+
+static inline bool fimc_check_drm_flip(enum drm_exynos_flip flip)
+{
+	switch (flip) {
+	case EXYNOS_DRM_FLIP_NONE:
+	case EXYNOS_DRM_FLIP_VERTICAL:
+	case EXYNOS_DRM_FLIP_HORIZONTAL:
+		return true;
+	default:
+		DRM_DEBUG_KMS("%s:invalid flip\n", __func__);
+		return false;
+	}
+}
+
+static int fimc_ippdrv_check_property(struct device *dev,
+		struct drm_exynos_ipp_property *property)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	struct drm_exynos_ipp_prop_list *pp = ippdrv->prop_list;
+	struct drm_exynos_ipp_config *config;
+	struct drm_exynos_pos *pos;
+	struct drm_exynos_sz *sz;
+	bool swap;
+	int i;
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	for_each_ipp_ops(i) {
+		if ((i == EXYNOS_DRM_OPS_SRC) &&
+			(property->cmd == IPP_CMD_WB))
+			continue;
+
+		config = &property->config[i];
+		pos = &config->pos;
+		sz = &config->sz;
+
+		/* check for flip */
+		if (!fimc_check_drm_flip(config->flip)) {
+			DRM_ERROR("invalid flip.\n");
+			goto err_property;
+		}
+
+		/* check for degree */
+		switch (config->degree) {
+		case EXYNOS_DRM_DEGREE_90:
+		case EXYNOS_DRM_DEGREE_270:
+			swap = true;
+			break;
+		case EXYNOS_DRM_DEGREE_0:
+		case EXYNOS_DRM_DEGREE_180:
+			swap = false;
+			break;
+		default:
+			DRM_ERROR("invalid degree.\n");
+			goto err_property;
+		}
+
+		/* check for buffer bound */
+		if ((pos->x + pos->w > sz->hsize) ||
+			(pos->y + pos->h > sz->vsize)) {
+			DRM_ERROR("out of buf bound.\n");
+			goto err_property;
+		}
+
+		/* check for crop */
+		if ((i == EXYNOS_DRM_OPS_SRC) && (pp->crop)) {
+			if (swap) {
+				if ((pos->h < pp->crop_min.hsize) ||
+					(sz->vsize > pp->crop_max.hsize) ||
+					(pos->w < pp->crop_min.vsize) ||
+					(sz->hsize > pp->crop_max.vsize)) {
+					DRM_ERROR("out of crop size.\n");
+					goto err_property;
+				}
+			} else {
+				if ((pos->w < pp->crop_min.hsize) ||
+					(sz->hsize > pp->crop_max.hsize) ||
+					(pos->h < pp->crop_min.vsize) ||
+					(sz->vsize > pp->crop_max.vsize)) {
+					DRM_ERROR("out of crop size.\n");
+					goto err_property;
+				}
+			}
+		}
+
+		/* check for scale */
+		if ((i == EXYNOS_DRM_OPS_DST) && (pp->scale)) {
+			if (swap) {
+				if ((pos->h < pp->scale_min.hsize) ||
+					(sz->vsize > pp->scale_max.hsize) ||
+					(pos->w < pp->scale_min.vsize) ||
+					(sz->hsize > pp->scale_max.vsize)) {
+					DRM_ERROR("out of scale size.\n");
+					goto err_property;
+				}
+			} else {
+				if ((pos->w < pp->scale_min.hsize) ||
+					(sz->hsize > pp->scale_max.hsize) ||
+					(pos->h < pp->scale_min.vsize) ||
+					(sz->vsize > pp->scale_max.vsize)) {
+					DRM_ERROR("out of scale size.\n");
+					goto err_property;
+				}
+			}
+		}
+	}
+
+	return 0;
+
+err_property:
+	for_each_ipp_ops(i) {
+		if ((i == EXYNOS_DRM_OPS_SRC) &&
+			(property->cmd == IPP_CMD_WB))
+			continue;
+
+		config = &property->config[i];
+		pos = &config->pos;
+		sz = &config->sz;
+
+		DRM_ERROR("[%s]f[%d]r[%d]pos[%d %d %d %d]sz[%d %d]\n",
+			i ? "dst" : "src", config->flip, config->degree,
+			pos->x, pos->y, pos->w, pos->h,
+			sz->hsize, sz->vsize);
+	}
+
+	return -EINVAL;
+}
+
+static void fimc_clear_addr(struct fimc_context *ctx)
+{
+	int i;
+
+	DRM_DEBUG_KMS("%s:\n", __func__);
+
+	for (i = 0; i < FIMC_MAX_SRC; i++) {
+		fimc_write(0, EXYNOS_CIIYSA(i));
+		fimc_write(0, EXYNOS_CIICBSA(i));
+		fimc_write(0, EXYNOS_CIICRSA(i));
+	}
+
+	for (i = 0; i < FIMC_MAX_DST; i++) {
+		fimc_write(0, EXYNOS_CIOYSA(i));
+		fimc_write(0, EXYNOS_CIOCBSA(i));
+		fimc_write(0, EXYNOS_CIOCRSA(i));
+	}
+}
+
+static int fimc_ippdrv_reset(struct device *dev)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	/* reset h/w block */
+	fimc_sw_reset(ctx, false);
+
+	/* reset scaler capability */
+	memset(&ctx->sc, 0x0, sizeof(ctx->sc));
+
+	fimc_clear_addr(ctx);
+
+	return 0;
+}
+
+static int fimc_ippdrv_start(struct device *dev, enum drm_exynos_ipp_cmd cmd)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+	struct drm_exynos_ipp_cmd_node *c_node = ippdrv->cmd;
+	struct drm_exynos_ipp_property *property;
+	struct drm_exynos_ipp_config *config;
+	struct drm_exynos_pos	img_pos[EXYNOS_DRM_OPS_MAX];
+	struct drm_exynos_ipp_set_wb set_wb;
+	int ret, i;
+	u32 cfg0, cfg1;
+
+	DRM_DEBUG_KMS("%s:cmd[%d]\n", __func__, cmd);
+
+	if (!c_node) {
+		DRM_ERROR("failed to get c_node.\n");
+		return -EINVAL;
+	}
+
+	property = &c_node->property;
+	if (!property) {
+		DRM_ERROR("failed to get property.\n");
+		return -EINVAL;
+	}
+
+	fimc_handle_irq(ctx, true, false, true);
+
+	for_each_ipp_ops(i) {
+		config = &property->config[i];
+		img_pos[i] = config->pos;
+	}
+
+	ret = fimc_set_prescaler(ctx, &ctx->sc,
+		&img_pos[EXYNOS_DRM_OPS_SRC],
+		&img_pos[EXYNOS_DRM_OPS_DST]);
+	if (ret) {
+		dev_err(dev, "failed to set precalser.\n");
+		return ret;
+	}
+
+	/* If set ture, we can save jpeg about screen */
+	fimc_handle_jpeg(ctx, false);
+	fimc_set_scaler(ctx, &ctx->sc);
+	fimc_set_polarity(ctx, &ctx->pol);
+
+	switch (cmd) {
+	case IPP_CMD_M2M:
+		fimc_set_type_ctrl(ctx, FIMC_WB_NONE);
+		fimc_handle_lastend(ctx, false);
+
+		/* setup dma */
+		cfg0 = fimc_read(EXYNOS_MSCTRL);
+		cfg0 &= ~EXYNOS_MSCTRL_INPUT_MASK;
+		cfg0 |= EXYNOS_MSCTRL_INPUT_MEMORY;
+		fimc_write(cfg0, EXYNOS_MSCTRL);
+		break;
+	case IPP_CMD_WB:
+		fimc_set_type_ctrl(ctx, FIMC_WB_A);
+		fimc_handle_lastend(ctx, true);
+
+		/* setup FIMD */
+		fimc_set_camblk_fimd0_wb(ctx);
+
+		set_wb.enable = 1;
+		set_wb.refresh = property->refresh_rate;
+		exynos_drm_ippnb_send_event(IPP_SET_WRITEBACK, (void *)&set_wb);
+		break;
+	case IPP_CMD_OUTPUT:
+	default:
+		ret = -EINVAL;
+		dev_err(dev, "invalid operations.\n");
+		return ret;
+	}
+
+	/* Reset status */
+	fimc_write(0x0, EXYNOS_CISTATUS);
+
+	cfg0 = fimc_read(EXYNOS_CIIMGCPT);
+	cfg0 &= ~EXYNOS_CIIMGCPT_IMGCPTEN_SC;
+	cfg0 |= EXYNOS_CIIMGCPT_IMGCPTEN_SC;
+
+	/* Scaler */
+	cfg1 = fimc_read(EXYNOS_CISCCTRL);
+	cfg1 &= ~EXYNOS_CISCCTRL_SCAN_MASK;
+	cfg1 |= (EXYNOS_CISCCTRL_PROGRESSIVE |
+		EXYNOS_CISCCTRL_SCALERSTART);
+
+	fimc_write(cfg1, EXYNOS_CISCCTRL);
+
+	/* Enable image capture*/
+	cfg0 |= EXYNOS_CIIMGCPT_IMGCPTEN;
+	fimc_write(cfg0, EXYNOS_CIIMGCPT);
+
+	/* Disable frame end irq */
+	cfg0 = fimc_read(EXYNOS_CIGCTRL);
+	cfg0 &= ~EXYNOS_CIGCTRL_IRQ_END_DISABLE;
+	fimc_write(cfg0, EXYNOS_CIGCTRL);
+
+	cfg0 = fimc_read(EXYNOS_CIOCTRL);
+	cfg0 &= ~EXYNOS_CIOCTRL_WEAVE_MASK;
+	fimc_write(cfg0, EXYNOS_CIOCTRL);
+
+	if (cmd == IPP_CMD_M2M) {
+		cfg0 = fimc_read(EXYNOS_MSCTRL);
+		cfg0 |= EXYNOS_MSCTRL_ENVID;
+		fimc_write(cfg0, EXYNOS_MSCTRL);
+
+		cfg0 = fimc_read(EXYNOS_MSCTRL);
+		cfg0 |= EXYNOS_MSCTRL_ENVID;
+		fimc_write(cfg0, EXYNOS_MSCTRL);
+	}
+
+	return 0;
+}
+
+static void fimc_ippdrv_stop(struct device *dev, enum drm_exynos_ipp_cmd cmd)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct drm_exynos_ipp_set_wb set_wb = {0, 0};
+	u32 cfg;
+
+	DRM_DEBUG_KMS("%s:cmd[%d]\n", __func__, cmd);
+
+	switch (cmd) {
+	case IPP_CMD_M2M:
+		/* Source clear */
+		cfg = fimc_read(EXYNOS_MSCTRL);
+		cfg &= ~EXYNOS_MSCTRL_INPUT_MASK;
+		cfg &= ~EXYNOS_MSCTRL_ENVID;
+		fimc_write(cfg, EXYNOS_MSCTRL);
+		break;
+	case IPP_CMD_WB:
+		exynos_drm_ippnb_send_event(IPP_SET_WRITEBACK, (void *)&set_wb);
+		break;
+	case IPP_CMD_OUTPUT:
+	default:
+		dev_err(dev, "invalid operations.\n");
+		break;
+	}
+
+	fimc_handle_irq(ctx, false, false, true);
+
+	/* reset sequence */
+	fimc_write(0x0, EXYNOS_CIFCNTSEQ);
+
+	/* Scaler disable */
+	cfg = fimc_read(EXYNOS_CISCCTRL);
+	cfg &= ~EXYNOS_CISCCTRL_SCALERSTART;
+	fimc_write(cfg, EXYNOS_CISCCTRL);
+
+	/* Disable image capture */
+	cfg = fimc_read(EXYNOS_CIIMGCPT);
+	cfg &= ~(EXYNOS_CIIMGCPT_IMGCPTEN_SC | EXYNOS_CIIMGCPT_IMGCPTEN);
+	fimc_write(cfg, EXYNOS_CIIMGCPT);
+
+	/* Enable frame end irq */
+	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg |= EXYNOS_CIGCTRL_IRQ_END_DISABLE;
+	fimc_write(cfg, EXYNOS_CIGCTRL);
+}
+
+static int __devinit fimc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct fimc_context *ctx;
+	struct clk	*parent_clk;
+	struct resource *res;
+	struct exynos_drm_ippdrv *ippdrv;
+	struct exynos_drm_fimc_pdata *pdata;
+	struct fimc_driverdata *ddata;
+	int ret;
+
+	pdata = pdev->dev.platform_data;
+	if (!pdata) {
+		dev_err(dev, "no platform data specified.\n");
+		return -EINVAL;
+	}
+
+	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ddata = (struct fimc_driverdata *)
+		platform_get_device_id(pdev)->driver_data;
+
+	/* clock control */
+	ctx->sclk_fimc_clk = clk_get(dev, "sclk_fimc");
+	if (IS_ERR(ctx->sclk_fimc_clk)) {
+		dev_err(dev, "failed to get src fimc clock.\n");
+		ret = PTR_ERR(ctx->sclk_fimc_clk);
+		goto err_ctx;
+	}
+	clk_enable(ctx->sclk_fimc_clk);
+
+	ctx->fimc_clk = clk_get(dev, "fimc");
+	if (IS_ERR(ctx->fimc_clk)) {
+		dev_err(dev, "failed to get fimc clock.\n");
+		ret = PTR_ERR(ctx->fimc_clk);
+		clk_disable(ctx->sclk_fimc_clk);
+		clk_put(ctx->sclk_fimc_clk);
+		goto err_ctx;
+	}
+
+	ctx->wb_clk = clk_get(dev, "pxl_async0");
+	if (IS_ERR(ctx->wb_clk)) {
+		dev_err(dev, "failed to get writeback a clock.\n");
+		ret = PTR_ERR(ctx->wb_clk);
+		clk_disable(ctx->sclk_fimc_clk);
+		clk_put(ctx->sclk_fimc_clk);
+		clk_put(ctx->fimc_clk);
+		goto err_ctx;
+	}
+
+	ctx->wb_b_clk = clk_get(dev, "pxl_async1");
+	if (IS_ERR(ctx->wb_b_clk)) {
+		dev_err(dev, "failed to get writeback b clock.\n");
+		ret = PTR_ERR(ctx->wb_b_clk);
+		clk_disable(ctx->sclk_fimc_clk);
+		clk_put(ctx->sclk_fimc_clk);
+		clk_put(ctx->fimc_clk);
+		clk_put(ctx->wb_clk);
+		goto err_ctx;
+	}
+
+	parent_clk = clk_get(dev, ddata->parent_clk);
+
+	if (IS_ERR(parent_clk)) {
+		dev_err(dev, "failed to get parent clock.\n");
+		ret = PTR_ERR(parent_clk);
+		clk_disable(ctx->sclk_fimc_clk);
+		clk_put(ctx->sclk_fimc_clk);
+		clk_put(ctx->fimc_clk);
+		clk_put(ctx->wb_clk);
+		clk_put(ctx->wb_b_clk);
+		goto err_ctx;
+	}
+
+	if (clk_set_parent(ctx->sclk_fimc_clk, parent_clk)) {
+		dev_err(dev, "failed to set parent.\n");
+		ret = -EINVAL;
+		clk_put(parent_clk);
+		clk_disable(ctx->sclk_fimc_clk);
+		clk_put(ctx->sclk_fimc_clk);
+		clk_put(ctx->fimc_clk);
+		clk_put(ctx->wb_clk);
+		clk_put(ctx->wb_b_clk);
+		goto err_ctx;
+	}
+
+	clk_put(parent_clk);
+	clk_set_rate(ctx->sclk_fimc_clk, pdata->clk_rate);
+
+	/* resource memory */
+	ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!ctx->regs_res) {
+		dev_err(dev, "failed to find registers.\n");
+		ret = -ENOENT;
+		goto err_clk;
+	}
+
+	ctx->regs = devm_request_and_ioremap(dev, ctx->regs_res);
+	if (!ctx->regs) {
+		dev_err(dev, "failed to map registers.\n");
+		ret = -ENXIO;
+		goto err_clk;
+	}
+
+	/* resource irq */
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!res) {
+		dev_err(dev, "failed to request irq resource.\n");
+		ret = -ENOENT;
+		goto err_get_regs;
+	}
+
+	ctx->irq = res->start;
+	ret = request_threaded_irq(ctx->irq, NULL, fimc_irq_handler,
+		IRQF_ONESHOT, "drm_fimc", ctx);
+	if (ret < 0) {
+		dev_err(dev, "failed to request irq.\n");
+		goto err_get_regs;
+	}
+
+	/* context initailization */
+	ctx->id = pdev->id;
+	ctx->pol = pdata->pol;
+	ctx->ddata = ddata;
+
+	ippdrv = &ctx->ippdrv;
+	ippdrv->dev = dev;
+	ippdrv->ops[EXYNOS_DRM_OPS_SRC] = &fimc_src_ops;
+	ippdrv->ops[EXYNOS_DRM_OPS_DST] = &fimc_dst_ops;
+	ippdrv->check_property = fimc_ippdrv_check_property;
+	ippdrv->reset = fimc_ippdrv_reset;
+	ippdrv->start = fimc_ippdrv_start;
+	ippdrv->stop = fimc_ippdrv_stop;
+	ret = fimc_init_prop_list(ippdrv);
+	if (ret < 0) {
+		dev_err(dev, "failed to init property list.\n");
+		goto err_get_irq;
+	}
+
+	DRM_DEBUG_KMS("%s:id[%d]ippdrv[0x%x]\n", __func__, ctx->id,
+		(int)ippdrv);
+
+	mutex_init(&ctx->lock);
+	platform_set_drvdata(pdev, ctx);
+
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
+	ret = exynos_drm_ippdrv_register(ippdrv);
+	if (ret < 0) {
+		dev_err(dev, "failed to register drm fimc device.\n");
+		goto err_ippdrv_register;
+	}
+
+	dev_info(&pdev->dev, "drm fimc registered successfully.\n");
+
+	return 0;
+
+err_ippdrv_register:
+	devm_kfree(dev, ippdrv->prop_list);
+	pm_runtime_disable(dev);
+err_get_irq:
+	free_irq(ctx->irq, ctx);
+err_get_regs:
+	devm_iounmap(dev, ctx->regs);
+err_clk:
+	clk_put(ctx->sclk_fimc_clk);
+	clk_put(ctx->fimc_clk);
+	clk_put(ctx->wb_clk);
+	clk_put(ctx->wb_b_clk);
+err_ctx:
+	devm_kfree(dev, ctx);
+	return ret;
+}
+
+static int __devexit fimc_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct fimc_context *ctx = get_fimc_context(dev);
+	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
+
+	devm_kfree(dev, ippdrv->prop_list);
+	exynos_drm_ippdrv_unregister(ippdrv);
+	mutex_destroy(&ctx->lock);
+
+	pm_runtime_set_suspended(dev);
+	pm_runtime_disable(dev);
+
+	free_irq(ctx->irq, ctx);
+	devm_iounmap(dev, ctx->regs);
+
+	clk_put(ctx->sclk_fimc_clk);
+	clk_put(ctx->fimc_clk);
+	clk_put(ctx->wb_clk);
+	clk_put(ctx->wb_b_clk);
+
+	devm_kfree(dev, ctx);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int fimc_suspend(struct device *dev)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+
+	DRM_DEBUG_KMS("%s:id[%d]\n", __func__, ctx->id);
+
+	if (pm_runtime_suspended(dev))
+		return 0;
+
+	return fimc_clk_ctrl(ctx, false);
+}
+
+static int fimc_resume(struct device *dev)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+
+	DRM_DEBUG_KMS("%s:id[%d]\n", __func__, ctx->id);
+
+	if (!pm_runtime_suspended(dev))
+		return fimc_clk_ctrl(ctx, true);
+
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_PM_RUNTIME
+static int fimc_runtime_suspend(struct device *dev)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+
+	DRM_DEBUG_KMS("%s:id[%d]\n", __func__, ctx->id);
+
+	return  fimc_clk_ctrl(ctx, false);
+}
+
+static int fimc_runtime_resume(struct device *dev)
+{
+	struct fimc_context *ctx = get_fimc_context(dev);
+
+	DRM_DEBUG_KMS("%s:id[%d]\n", __func__, ctx->id);
+
+	return  fimc_clk_ctrl(ctx, true);
+}
+#endif
+
+static struct fimc_driverdata exynos4210_fimc_data = {
+	.parent_clk = "mout_mpll",
+};
+
+static struct fimc_driverdata exynos4410_fimc_data = {
+	.parent_clk = "mout_mpll_user",
+};
+
+static struct platform_device_id fimc_driver_ids[] = {
+	{
+		.name		= "exynos4210-fimc",
+		.driver_data	= (unsigned long)&exynos4210_fimc_data,
+	}, {
+		.name		= "exynos4412-fimc",
+		.driver_data	= (unsigned long)&exynos4410_fimc_data,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(platform, fimc_driver_ids);
+
+static const struct dev_pm_ops fimc_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(fimc_suspend, fimc_resume)
+	SET_RUNTIME_PM_OPS(fimc_runtime_suspend, fimc_runtime_resume, NULL)
+};
+
+struct platform_driver fimc_driver = {
+	.probe		= fimc_probe,
+	.remove		= __devexit_p(fimc_remove),
+	.id_table	= fimc_driver_ids,
+	.driver		= {
+		.name	= "exynos-drm-fimc",
+		.owner	= THIS_MODULE,
+		.pm	= &fimc_pm_ops,
+	},
+};
+
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.h b/drivers/gpu/drm/exynos/exynos_drm_fimc.h
new file mode 100644
index 000000000000..dc970fa0d888
--- /dev/null
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *
+ * Authors:
+ *	Eunchul Kim <chulspro.kim@samsung.com>
+ *	Jinyoung Jeon <jy0.jeon@samsung.com>
+ *	Sangmin Lee <lsmin.lee@samsung.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _EXYNOS_DRM_FIMC_H_
+#define _EXYNOS_DRM_FIMC_H_
+
+/*
+ * TODO
+ * FIMD output interface notifier callback.
+ */
+
+#endif /* _EXYNOS_DRM_FIMC_H_ */
diff --git a/drivers/gpu/drm/exynos/regs-fimc.h b/drivers/gpu/drm/exynos/regs-fimc.h
new file mode 100644
index 000000000000..b4f9ca1fd851
--- /dev/null
+++ b/drivers/gpu/drm/exynos/regs-fimc.h
@@ -0,0 +1,669 @@
+/* drivers/gpu/drm/exynos/regs-fimc.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com/
+ *
+ * Register definition file for Samsung Camera Interface (FIMC) driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef EXYNOS_REGS_FIMC_H
+#define EXYNOS_REGS_FIMC_H
+
+/*
+ * Register part
+*/
+/* Input source format */
+#define EXYNOS_CISRCFMT		(0x00)
+/* Window offset */
+#define EXYNOS_CIWDOFST		(0x04)
+/* Global control */
+#define EXYNOS_CIGCTRL		(0x08)
+/* Window offset 2 */
+#define EXYNOS_CIWDOFST2	(0x14)
+/* Y 1st frame start address for output DMA */
+#define EXYNOS_CIOYSA1		(0x18)
+/* Y 2nd frame start address for output DMA */
+#define EXYNOS_CIOYSA2		(0x1c)
+/* Y 3rd frame start address for output DMA */
+#define EXYNOS_CIOYSA3		(0x20)
+/* Y 4th frame start address for output DMA */
+#define EXYNOS_CIOYSA4		(0x24)
+/* Cb 1st frame start address for output DMA */
+#define EXYNOS_CIOCBSA1		(0x28)
+/* Cb 2nd frame start address for output DMA */
+#define EXYNOS_CIOCBSA2		(0x2c)
+/* Cb 3rd frame start address for output DMA */
+#define EXYNOS_CIOCBSA3		(0x30)
+/* Cb 4th frame start address for output DMA */
+#define EXYNOS_CIOCBSA4		(0x34)
+/* Cr 1st frame start address for output DMA */
+#define EXYNOS_CIOCRSA1		(0x38)
+/* Cr 2nd frame start address for output DMA */
+#define EXYNOS_CIOCRSA2		(0x3c)
+/* Cr 3rd frame start address for output DMA */
+#define EXYNOS_CIOCRSA3		(0x40)
+/* Cr 4th frame start address for output DMA */
+#define EXYNOS_CIOCRSA4		(0x44)
+/* Target image format */
+#define EXYNOS_CITRGFMT		(0x48)
+/* Output DMA control */
+#define EXYNOS_CIOCTRL		(0x4c)
+/* Pre-scaler control 1 */
+#define EXYNOS_CISCPRERATIO	(0x50)
+/* Pre-scaler control 2 */
+#define EXYNOS_CISCPREDST		(0x54)
+/* Main scaler control */
+#define EXYNOS_CISCCTRL		(0x58)
+/* Target area */
+#define EXYNOS_CITAREA		(0x5c)
+/* Status */
+#define EXYNOS_CISTATUS		(0x64)
+/* Status2 */
+#define EXYNOS_CISTATUS2		(0x68)
+/* Image capture enable command */
+#define EXYNOS_CIIMGCPT		(0xc0)
+/* Capture sequence */
+#define EXYNOS_CICPTSEQ		(0xc4)
+/* Image effects */
+#define EXYNOS_CIIMGEFF		(0xd0)
+/* Y frame start address for input DMA */
+#define EXYNOS_CIIYSA0		(0xd4)
+/* Cb frame start address for input DMA */
+#define EXYNOS_CIICBSA0		(0xd8)
+/* Cr frame start address for input DMA */
+#define EXYNOS_CIICRSA0		(0xdc)
+/* Input DMA Y Line Skip */
+#define EXYNOS_CIILINESKIP_Y	(0xec)
+/* Input DMA Cb Line Skip */
+#define EXYNOS_CIILINESKIP_CB	(0xf0)
+/* Input DMA Cr Line Skip */
+#define EXYNOS_CIILINESKIP_CR	(0xf4)
+/* Real input DMA image size */
+#define EXYNOS_CIREAL_ISIZE	(0xf8)
+/* Input DMA control */
+#define EXYNOS_MSCTRL		(0xfc)
+/* Y frame start address for input DMA */
+#define EXYNOS_CIIYSA1		(0x144)
+/* Cb frame start address for input DMA */
+#define EXYNOS_CIICBSA1		(0x148)
+/* Cr frame start address for input DMA */
+#define EXYNOS_CIICRSA1		(0x14c)
+/* Output DMA Y offset */
+#define EXYNOS_CIOYOFF		(0x168)
+/* Output DMA CB offset */
+#define EXYNOS_CIOCBOFF		(0x16c)
+/* Output DMA CR offset */
+#define EXYNOS_CIOCROFF		(0x170)
+/* Input DMA Y offset */
+#define EXYNOS_CIIYOFF		(0x174)
+/* Input DMA CB offset */
+#define EXYNOS_CIICBOFF		(0x178)
+/* Input DMA CR offset */
+#define EXYNOS_CIICROFF		(0x17c)
+/* Input DMA original image size */
+#define EXYNOS_ORGISIZE		(0x180)
+/* Output DMA original image size */
+#define EXYNOS_ORGOSIZE		(0x184)
+/* Real output DMA image size */
+#define EXYNOS_CIEXTEN		(0x188)
+/* DMA parameter */
+#define EXYNOS_CIDMAPARAM		(0x18c)
+/* MIPI CSI image format */
+#define EXYNOS_CSIIMGFMT		(0x194)
+/* FIMC Clock Source Select */
+#define EXYNOS_MISC_FIMC		(0x198)
+
+/* Add for FIMC v5.1 */
+/* Output Frame Buffer Sequence */
+#define EXYNOS_CIFCNTSEQ		(0x1fc)
+/* Y 5th frame start address for output DMA */
+#define EXYNOS_CIOYSA5		(0x200)
+/* Y 6th frame start address for output DMA */
+#define EXYNOS_CIOYSA6		(0x204)
+/* Y 7th frame start address for output DMA */
+#define EXYNOS_CIOYSA7		(0x208)
+/* Y 8th frame start address for output DMA */
+#define EXYNOS_CIOYSA8		(0x20c)
+/* Y 9th frame start address for output DMA */
+#define EXYNOS_CIOYSA9		(0x210)
+/* Y 10th frame start address for output DMA */
+#define EXYNOS_CIOYSA10		(0x214)
+/* Y 11th frame start address for output DMA */
+#define EXYNOS_CIOYSA11		(0x218)
+/* Y 12th frame start address for output DMA */
+#define EXYNOS_CIOYSA12		(0x21c)
+/* Y 13th frame start address for output DMA */
+#define EXYNOS_CIOYSA13		(0x220)
+/* Y 14th frame start address for output DMA */
+#define EXYNOS_CIOYSA14		(0x224)
+/* Y 15th frame start address for output DMA */
+#define EXYNOS_CIOYSA15		(0x228)
+/* Y 16th frame start address for output DMA */
+#define EXYNOS_CIOYSA16		(0x22c)
+/* Y 17th frame start address for output DMA */
+#define EXYNOS_CIOYSA17		(0x230)
+/* Y 18th frame start address for output DMA */
+#define EXYNOS_CIOYSA18		(0x234)
+/* Y 19th frame start address for output DMA */
+#define EXYNOS_CIOYSA19		(0x238)
+/* Y 20th frame start address for output DMA */
+#define EXYNOS_CIOYSA20		(0x23c)
+/* Y 21th frame start address for output DMA */
+#define EXYNOS_CIOYSA21		(0x240)
+/* Y 22th frame start address for output DMA */
+#define EXYNOS_CIOYSA22		(0x244)
+/* Y 23th frame start address for output DMA */
+#define EXYNOS_CIOYSA23		(0x248)
+/* Y 24th frame start address for output DMA */
+#define EXYNOS_CIOYSA24		(0x24c)
+/* Y 25th frame start address for output DMA */
+#define EXYNOS_CIOYSA25		(0x250)
+/* Y 26th frame start address for output DMA */
+#define EXYNOS_CIOYSA26		(0x254)
+/* Y 27th frame start address for output DMA */
+#define EXYNOS_CIOYSA27		(0x258)
+/* Y 28th frame start address for output DMA */
+#define EXYNOS_CIOYSA28		(0x25c)
+/* Y 29th frame start address for output DMA */
+#define EXYNOS_CIOYSA29		(0x260)
+/* Y 30th frame start address for output DMA */
+#define EXYNOS_CIOYSA30		(0x264)
+/* Y 31th frame start address for output DMA */
+#define EXYNOS_CIOYSA31		(0x268)
+/* Y 32th frame start address for output DMA */
+#define EXYNOS_CIOYSA32		(0x26c)
+
+/* CB 5th frame start address for output DMA */
+#define EXYNOS_CIOCBSA5		(0x270)
+/* CB 6th frame start address for output DMA */
+#define EXYNOS_CIOCBSA6		(0x274)
+/* CB 7th frame start address for output DMA */
+#define EXYNOS_CIOCBSA7		(0x278)
+/* CB 8th frame start address for output DMA */
+#define EXYNOS_CIOCBSA8		(0x27c)
+/* CB 9th frame start address for output DMA */
+#define EXYNOS_CIOCBSA9		(0x280)
+/* CB 10th frame start address for output DMA */
+#define EXYNOS_CIOCBSA10		(0x284)
+/* CB 11th frame start address for output DMA */
+#define EXYNOS_CIOCBSA11		(0x288)
+/* CB 12th frame start address for output DMA */
+#define EXYNOS_CIOCBSA12		(0x28c)
+/* CB 13th frame start address for output DMA */
+#define EXYNOS_CIOCBSA13		(0x290)
+/* CB 14th frame start address for output DMA */
+#define EXYNOS_CIOCBSA14		(0x294)
+/* CB 15th frame start address for output DMA */
+#define EXYNOS_CIOCBSA15		(0x298)
+/* CB 16th frame start address for output DMA */
+#define EXYNOS_CIOCBSA16		(0x29c)
+/* CB 17th frame start address for output DMA */
+#define EXYNOS_CIOCBSA17		(0x2a0)
+/* CB 18th frame start address for output DMA */
+#define EXYNOS_CIOCBSA18		(0x2a4)
+/* CB 19th frame start address for output DMA */
+#define EXYNOS_CIOCBSA19		(0x2a8)
+/* CB 20th frame start address for output DMA */
+#define EXYNOS_CIOCBSA20		(0x2ac)
+/* CB 21th frame start address for output DMA */
+#define EXYNOS_CIOCBSA21		(0x2b0)
+/* CB 22th frame start address for output DMA */
+#define EXYNOS_CIOCBSA22		(0x2b4)
+/* CB 23th frame start address for output DMA */
+#define EXYNOS_CIOCBSA23		(0x2b8)
+/* CB 24th frame start address for output DMA */
+#define EXYNOS_CIOCBSA24		(0x2bc)
+/* CB 25th frame start address for output DMA */
+#define EXYNOS_CIOCBSA25		(0x2c0)
+/* CB 26th frame start address for output DMA */
+#define EXYNOS_CIOCBSA26		(0x2c4)
+/* CB 27th frame start address for output DMA */
+#define EXYNOS_CIOCBSA27		(0x2c8)
+/* CB 28th frame start address for output DMA */
+#define EXYNOS_CIOCBSA28		(0x2cc)
+/* CB 29th frame start address for output DMA */
+#define EXYNOS_CIOCBSA29		(0x2d0)
+/* CB 30th frame start address for output DMA */
+#define EXYNOS_CIOCBSA30		(0x2d4)
+/* CB 31th frame start address for output DMA */
+#define EXYNOS_CIOCBSA31		(0x2d8)
+/* CB 32th frame start address for output DMA */
+#define EXYNOS_CIOCBSA32		(0x2dc)
+
+/* CR 5th frame start address for output DMA */
+#define EXYNOS_CIOCRSA5		(0x2e0)
+/* CR 6th frame start address for output DMA */
+#define EXYNOS_CIOCRSA6		(0x2e4)
+/* CR 7th frame start address for output DMA */
+#define EXYNOS_CIOCRSA7		(0x2e8)
+/* CR 8th frame start address for output DMA */
+#define EXYNOS_CIOCRSA8		(0x2ec)
+/* CR 9th frame start address for output DMA */
+#define EXYNOS_CIOCRSA9		(0x2f0)
+/* CR 10th frame start address for output DMA */
+#define EXYNOS_CIOCRSA10		(0x2f4)
+/* CR 11th frame start address for output DMA */
+#define EXYNOS_CIOCRSA11		(0x2f8)
+/* CR 12th frame start address for output DMA */
+#define EXYNOS_CIOCRSA12		(0x2fc)
+/* CR 13th frame start address for output DMA */
+#define EXYNOS_CIOCRSA13		(0x300)
+/* CR 14th frame start address for output DMA */
+#define EXYNOS_CIOCRSA14		(0x304)
+/* CR 15th frame start address for output DMA */
+#define EXYNOS_CIOCRSA15		(0x308)
+/* CR 16th frame start address for output DMA */
+#define EXYNOS_CIOCRSA16		(0x30c)
+/* CR 17th frame start address for output DMA */
+#define EXYNOS_CIOCRSA17		(0x310)
+/* CR 18th frame start address for output DMA */
+#define EXYNOS_CIOCRSA18		(0x314)
+/* CR 19th frame start address for output DMA */
+#define EXYNOS_CIOCRSA19		(0x318)
+/* CR 20th frame start address for output DMA */
+#define EXYNOS_CIOCRSA20		(0x31c)
+/* CR 21th frame start address for output DMA */
+#define EXYNOS_CIOCRSA21		(0x320)
+/* CR 22th frame start address for output DMA */
+#define EXYNOS_CIOCRSA22		(0x324)
+/* CR 23th frame start address for output DMA */
+#define EXYNOS_CIOCRSA23		(0x328)
+/* CR 24th frame start address for output DMA */
+#define EXYNOS_CIOCRSA24		(0x32c)
+/* CR 25th frame start address for output DMA */
+#define EXYNOS_CIOCRSA25		(0x330)
+/* CR 26th frame start address for output DMA */
+#define EXYNOS_CIOCRSA26		(0x334)
+/* CR 27th frame start address for output DMA */
+#define EXYNOS_CIOCRSA27		(0x338)
+/* CR 28th frame start address for output DMA */
+#define EXYNOS_CIOCRSA28		(0x33c)
+/* CR 29th frame start address for output DMA */
+#define EXYNOS_CIOCRSA29		(0x340)
+/* CR 30th frame start address for output DMA */
+#define EXYNOS_CIOCRSA30		(0x344)
+/* CR 31th frame start address for output DMA */
+#define EXYNOS_CIOCRSA31		(0x348)
+/* CR 32th frame start address for output DMA */
+#define EXYNOS_CIOCRSA32		(0x34c)
+
+/*
+ * Macro part
+*/
+/* frame start address 1 ~ 4, 5 ~ 32 */
+/* Number of Default PingPong Memory */
+#define DEF_PP		4
+#define EXYNOS_CIOYSA(__x)		\
+	(((__x) < DEF_PP) ?	\
+	 (EXYNOS_CIOYSA1  + (__x) * 4) : \
+	(EXYNOS_CIOYSA5  + ((__x) - DEF_PP) * 4))
+#define EXYNOS_CIOCBSA(__x)	\
+	(((__x) < DEF_PP) ?	\
+	 (EXYNOS_CIOCBSA1 + (__x) * 4) : \
+	(EXYNOS_CIOCBSA5 + ((__x) - DEF_PP) * 4))
+#define EXYNOS_CIOCRSA(__x)	\
+	(((__x) < DEF_PP) ?	\
+	 (EXYNOS_CIOCRSA1 + (__x) * 4) : \
+	(EXYNOS_CIOCRSA5 + ((__x) - DEF_PP) * 4))
+/* Number of Default PingPong Memory */
+#define DEF_IPP		1
+#define EXYNOS_CIIYSA(__x)		\
+	(((__x) < DEF_IPP) ?	\
+	 (EXYNOS_CIIYSA0) : (EXYNOS_CIIYSA1))
+#define EXYNOS_CIICBSA(__x)	\
+	(((__x) < DEF_IPP) ?	\
+	 (EXYNOS_CIICBSA0) : (EXYNOS_CIICBSA1))
+#define EXYNOS_CIICRSA(__x)	\
+	(((__x) < DEF_IPP) ?	\
+	 (EXYNOS_CIICRSA0) : (EXYNOS_CIICRSA1))
+
+#define EXYNOS_CISRCFMT_SOURCEHSIZE(x)		((x) << 16)
+#define EXYNOS_CISRCFMT_SOURCEVSIZE(x)		((x) << 0)
+
+#define EXYNOS_CIWDOFST_WINHOROFST(x)		((x) << 16)
+#define EXYNOS_CIWDOFST_WINVEROFST(x)		((x) << 0)
+
+#define EXYNOS_CIWDOFST2_WINHOROFST2(x)		((x) << 16)
+#define EXYNOS_CIWDOFST2_WINVEROFST2(x)		((x) << 0)
+
+#define EXYNOS_CITRGFMT_TARGETHSIZE(x)		(((x) & 0x1fff) << 16)
+#define EXYNOS_CITRGFMT_TARGETVSIZE(x)		(((x) & 0x1fff) << 0)
+
+#define EXYNOS_CISCPRERATIO_SHFACTOR(x)		((x) << 28)
+#define EXYNOS_CISCPRERATIO_PREHORRATIO(x)		((x) << 16)
+#define EXYNOS_CISCPRERATIO_PREVERRATIO(x)		((x) << 0)
+
+#define EXYNOS_CISCPREDST_PREDSTWIDTH(x)		((x) << 16)
+#define EXYNOS_CISCPREDST_PREDSTHEIGHT(x)		((x) << 0)
+
+#define EXYNOS_CISCCTRL_MAINHORRATIO(x)		((x) << 16)
+#define EXYNOS_CISCCTRL_MAINVERRATIO(x)		((x) << 0)
+
+#define EXYNOS_CITAREA_TARGET_AREA(x)		((x) << 0)
+
+#define EXYNOS_CISTATUS_GET_FRAME_COUNT(x)		(((x) >> 26) & 0x3)
+#define EXYNOS_CISTATUS_GET_FRAME_END(x)		(((x) >> 17) & 0x1)
+#define EXYNOS_CISTATUS_GET_LAST_CAPTURE_END(x)	(((x) >> 16) & 0x1)
+#define EXYNOS_CISTATUS_GET_LCD_STATUS(x)		(((x) >> 9) & 0x1)
+#define EXYNOS_CISTATUS_GET_ENVID_STATUS(x)	(((x) >> 8) & 0x1)
+
+#define EXYNOS_CISTATUS2_GET_FRAMECOUNT_BEFORE(x)	(((x) >> 7) & 0x3f)
+#define EXYNOS_CISTATUS2_GET_FRAMECOUNT_PRESENT(x)	((x) & 0x3f)
+
+#define EXYNOS_CIIMGEFF_FIN(x)			((x & 0x7) << 26)
+#define EXYNOS_CIIMGEFF_PAT_CB(x)			((x) << 13)
+#define EXYNOS_CIIMGEFF_PAT_CR(x)			((x) << 0)
+
+#define EXYNOS_CIILINESKIP(x)			(((x) & 0xf) << 24)
+
+#define EXYNOS_CIREAL_ISIZE_HEIGHT(x)		((x) << 16)
+#define EXYNOS_CIREAL_ISIZE_WIDTH(x)		((x) << 0)
+
+#define EXYNOS_MSCTRL_SUCCESSIVE_COUNT(x)		((x) << 24)
+#define EXYNOS_MSCTRL_GET_INDMA_STATUS(x)		((x) & 0x1)
+
+#define EXYNOS_CIOYOFF_VERTICAL(x)			((x) << 16)
+#define EXYNOS_CIOYOFF_HORIZONTAL(x)		((x) << 0)
+
+#define EXYNOS_CIOCBOFF_VERTICAL(x)		((x) << 16)
+#define EXYNOS_CIOCBOFF_HORIZONTAL(x)		((x) << 0)
+
+#define EXYNOS_CIOCROFF_VERTICAL(x)		((x) << 16)
+#define EXYNOS_CIOCROFF_HORIZONTAL(x)		((x) << 0)
+
+#define EXYNOS_CIIYOFF_VERTICAL(x)			((x) << 16)
+#define EXYNOS_CIIYOFF_HORIZONTAL(x)		((x) << 0)
+
+#define EXYNOS_CIICBOFF_VERTICAL(x)		((x) << 16)
+#define EXYNOS_CIICBOFF_HORIZONTAL(x)		((x) << 0)
+
+#define EXYNOS_CIICROFF_VERTICAL(x)		((x) << 16)
+#define EXYNOS_CIICROFF_HORIZONTAL(x)		((x) << 0)
+
+#define EXYNOS_ORGISIZE_VERTICAL(x)		((x) << 16)
+#define EXYNOS_ORGISIZE_HORIZONTAL(x)		((x) << 0)
+
+#define EXYNOS_ORGOSIZE_VERTICAL(x)		((x) << 16)
+#define EXYNOS_ORGOSIZE_HORIZONTAL(x)		((x) << 0)
+
+#define EXYNOS_CIEXTEN_TARGETH_EXT(x)		((((x) & 0x2000) >> 13) << 26)
+#define EXYNOS_CIEXTEN_TARGETV_EXT(x)		((((x) & 0x2000) >> 13) << 24)
+#define EXYNOS_CIEXTEN_MAINHORRATIO_EXT(x)		(((x) & 0x3F) << 10)
+#define EXYNOS_CIEXTEN_MAINVERRATIO_EXT(x)		((x) & 0x3F)
+
+/*
+ * Bit definition part
+*/
+/* Source format register */
+#define EXYNOS_CISRCFMT_ITU601_8BIT		(1 << 31)
+#define EXYNOS_CISRCFMT_ITU656_8BIT		(0 << 31)
+#define EXYNOS_CISRCFMT_ITU601_16BIT		(1 << 29)
+#define EXYNOS_CISRCFMT_ORDER422_YCBYCR		(0 << 14)
+#define EXYNOS_CISRCFMT_ORDER422_YCRYCB		(1 << 14)
+#define EXYNOS_CISRCFMT_ORDER422_CBYCRY		(2 << 14)
+#define EXYNOS_CISRCFMT_ORDER422_CRYCBY		(3 << 14)
+/* ITU601 16bit only */
+#define EXYNOS_CISRCFMT_ORDER422_Y4CBCRCBCR	(0 << 14)
+/* ITU601 16bit only */
+#define EXYNOS_CISRCFMT_ORDER422_Y4CRCBCRCB	(1 << 14)
+
+/* Window offset register */
+#define EXYNOS_CIWDOFST_WINOFSEN			(1 << 31)
+#define EXYNOS_CIWDOFST_CLROVFIY			(1 << 30)
+#define EXYNOS_CIWDOFST_CLROVRLB			(1 << 29)
+#define EXYNOS_CIWDOFST_WINHOROFST_MASK		(0x7ff << 16)
+#define EXYNOS_CIWDOFST_CLROVFICB			(1 << 15)
+#define EXYNOS_CIWDOFST_CLROVFICR			(1 << 14)
+#define EXYNOS_CIWDOFST_WINVEROFST_MASK		(0xfff << 0)
+
+/* Global control register */
+#define EXYNOS_CIGCTRL_SWRST			(1 << 31)
+#define EXYNOS_CIGCTRL_CAMRST_A			(1 << 30)
+#define EXYNOS_CIGCTRL_SELCAM_ITU_B		(0 << 29)
+#define EXYNOS_CIGCTRL_SELCAM_ITU_A		(1 << 29)
+#define EXYNOS_CIGCTRL_SELCAM_ITU_MASK		(1 << 29)
+#define EXYNOS_CIGCTRL_TESTPATTERN_NORMAL		(0 << 27)
+#define EXYNOS_CIGCTRL_TESTPATTERN_COLOR_BAR	(1 << 27)
+#define EXYNOS_CIGCTRL_TESTPATTERN_HOR_INC		(2 << 27)
+#define EXYNOS_CIGCTRL_TESTPATTERN_VER_INC		(3 << 27)
+#define EXYNOS_CIGCTRL_TESTPATTERN_MASK		(3 << 27)
+#define EXYNOS_CIGCTRL_TESTPATTERN_SHIFT		(27)
+#define EXYNOS_CIGCTRL_INVPOLPCLK			(1 << 26)
+#define EXYNOS_CIGCTRL_INVPOLVSYNC			(1 << 25)
+#define EXYNOS_CIGCTRL_INVPOLHREF			(1 << 24)
+#define EXYNOS_CIGCTRL_IRQ_OVFEN			(1 << 22)
+#define EXYNOS_CIGCTRL_HREF_MASK			(1 << 21)
+#define EXYNOS_CIGCTRL_IRQ_EDGE			(0 << 20)
+#define EXYNOS_CIGCTRL_IRQ_LEVEL			(1 << 20)
+#define EXYNOS_CIGCTRL_IRQ_CLR			(1 << 19)
+#define EXYNOS_CIGCTRL_IRQ_END_DISABLE		(1 << 18)
+#define EXYNOS_CIGCTRL_IRQ_DISABLE			(0 << 16)
+#define EXYNOS_CIGCTRL_IRQ_ENABLE			(1 << 16)
+#define EXYNOS_CIGCTRL_SHADOW_DISABLE		(1 << 12)
+#define EXYNOS_CIGCTRL_CAM_JPEG			(1 << 8)
+#define EXYNOS_CIGCTRL_SELCAM_MIPI_B		(0 << 7)
+#define EXYNOS_CIGCTRL_SELCAM_MIPI_A		(1 << 7)
+#define EXYNOS_CIGCTRL_SELCAM_MIPI_MASK		(1 << 7)
+#define EXYNOS_CIGCTRL_SELWB_CAMIF_CAMERA	(0 << 6)
+#define EXYNOS_CIGCTRL_SELWB_CAMIF_WRITEBACK	(1 << 6)
+#define EXYNOS_CIGCTRL_SELWRITEBACK_MASK		(1 << 10)
+#define EXYNOS_CIGCTRL_SELWRITEBACK_A		(1 << 10)
+#define EXYNOS_CIGCTRL_SELWRITEBACK_B		(0 << 10)
+#define EXYNOS_CIGCTRL_SELWB_CAMIF_MASK		(1 << 6)
+#define EXYNOS_CIGCTRL_CSC_ITU601			(0 << 5)
+#define EXYNOS_CIGCTRL_CSC_ITU709			(1 << 5)
+#define EXYNOS_CIGCTRL_CSC_MASK			(1 << 5)
+#define EXYNOS_CIGCTRL_INVPOLHSYNC			(1 << 4)
+#define EXYNOS_CIGCTRL_SELCAM_FIMC_ITU		(0 << 3)
+#define EXYNOS_CIGCTRL_SELCAM_FIMC_MIPI		(1 << 3)
+#define EXYNOS_CIGCTRL_SELCAM_FIMC_MASK		(1 << 3)
+#define EXYNOS_CIGCTRL_PROGRESSIVE			(0 << 0)
+#define EXYNOS_CIGCTRL_INTERLACE			(1 << 0)
+
+/* Window offset2 register */
+#define EXYNOS_CIWDOFST_WINHOROFST2_MASK		(0xfff << 16)
+#define EXYNOS_CIWDOFST_WINVEROFST2_MASK		(0xfff << 16)
+
+/* Target format register */
+#define EXYNOS_CITRGFMT_INROT90_CLOCKWISE		(1 << 31)
+#define EXYNOS_CITRGFMT_OUTFORMAT_YCBCR420		(0 << 29)
+#define EXYNOS_CITRGFMT_OUTFORMAT_YCBCR422		(1 << 29)
+#define EXYNOS_CITRGFMT_OUTFORMAT_YCBCR422_1PLANE	(2 << 29)
+#define EXYNOS_CITRGFMT_OUTFORMAT_RGB		(3 << 29)
+#define EXYNOS_CITRGFMT_OUTFORMAT_MASK		(3 << 29)
+#define EXYNOS_CITRGFMT_FLIP_SHIFT			(14)
+#define EXYNOS_CITRGFMT_FLIP_NORMAL		(0 << 14)
+#define EXYNOS_CITRGFMT_FLIP_X_MIRROR		(1 << 14)
+#define EXYNOS_CITRGFMT_FLIP_Y_MIRROR		(2 << 14)
+#define EXYNOS_CITRGFMT_FLIP_180			(3 << 14)
+#define EXYNOS_CITRGFMT_FLIP_MASK			(3 << 14)
+#define EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE		(1 << 13)
+#define EXYNOS_CITRGFMT_TARGETV_MASK		(0x1fff << 0)
+#define EXYNOS_CITRGFMT_TARGETH_MASK		(0x1fff << 16)
+
+/* Output DMA control register */
+#define EXYNOS_CIOCTRL_WEAVE_OUT			(1 << 31)
+#define EXYNOS_CIOCTRL_WEAVE_MASK			(1 << 31)
+#define EXYNOS_CIOCTRL_LASTENDEN			(1 << 30)
+#define EXYNOS_CIOCTRL_ORDER2P_LSB_CBCR		(0 << 24)
+#define EXYNOS_CIOCTRL_ORDER2P_LSB_CRCB		(1 << 24)
+#define EXYNOS_CIOCTRL_ORDER2P_MSB_CRCB		(2 << 24)
+#define EXYNOS_CIOCTRL_ORDER2P_MSB_CBCR		(3 << 24)
+#define EXYNOS_CIOCTRL_ORDER2P_SHIFT		(24)
+#define EXYNOS_CIOCTRL_ORDER2P_MASK		(3 << 24)
+#define EXYNOS_CIOCTRL_YCBCR_3PLANE		(0 << 3)
+#define EXYNOS_CIOCTRL_YCBCR_2PLANE		(1 << 3)
+#define EXYNOS_CIOCTRL_YCBCR_PLANE_MASK		(1 << 3)
+#define EXYNOS_CIOCTRL_LASTIRQ_ENABLE		(1 << 2)
+#define EXYNOS_CIOCTRL_ALPHA_OUT			(0xff << 4)
+#define EXYNOS_CIOCTRL_ORDER422_YCBYCR		(0 << 0)
+#define EXYNOS_CIOCTRL_ORDER422_YCRYCB		(1 << 0)
+#define EXYNOS_CIOCTRL_ORDER422_CBYCRY		(2 << 0)
+#define EXYNOS_CIOCTRL_ORDER422_CRYCBY		(3 << 0)
+#define EXYNOS_CIOCTRL_ORDER422_MASK		(3 << 0)
+
+/* Main scaler control register */
+#define EXYNOS_CISCCTRL_SCALERBYPASS		(1 << 31)
+#define EXYNOS_CISCCTRL_SCALEUP_H			(1 << 30)
+#define EXYNOS_CISCCTRL_SCALEUP_V			(1 << 29)
+#define EXYNOS_CISCCTRL_CSCR2Y_NARROW		(0 << 28)
+#define EXYNOS_CISCCTRL_CSCR2Y_WIDE		(1 << 28)
+#define EXYNOS_CISCCTRL_CSCY2R_NARROW		(0 << 27)
+#define EXYNOS_CISCCTRL_CSCY2R_WIDE		(1 << 27)
+#define EXYNOS_CISCCTRL_LCDPATHEN_FIFO		(1 << 26)
+#define EXYNOS_CISCCTRL_PROGRESSIVE		(0 << 25)
+#define EXYNOS_CISCCTRL_INTERLACE			(1 << 25)
+#define EXYNOS_CISCCTRL_SCAN_MASK			(1 << 25)
+#define EXYNOS_CISCCTRL_SCALERSTART		(1 << 15)
+#define EXYNOS_CISCCTRL_INRGB_FMT_RGB565		(0 << 13)
+#define EXYNOS_CISCCTRL_INRGB_FMT_RGB666		(1 << 13)
+#define EXYNOS_CISCCTRL_INRGB_FMT_RGB888		(2 << 13)
+#define EXYNOS_CISCCTRL_INRGB_FMT_RGB_MASK		(3 << 13)
+#define EXYNOS_CISCCTRL_OUTRGB_FMT_RGB565		(0 << 11)
+#define EXYNOS_CISCCTRL_OUTRGB_FMT_RGB666		(1 << 11)
+#define EXYNOS_CISCCTRL_OUTRGB_FMT_RGB888		(2 << 11)
+#define EXYNOS_CISCCTRL_OUTRGB_FMT_RGB_MASK	(3 << 11)
+#define EXYNOS_CISCCTRL_EXTRGB_NORMAL		(0 << 10)
+#define EXYNOS_CISCCTRL_EXTRGB_EXTENSION		(1 << 10)
+#define EXYNOS_CISCCTRL_ONE2ONE			(1 << 9)
+#define EXYNOS_CISCCTRL_MAIN_V_RATIO_MASK		(0x1ff << 0)
+#define EXYNOS_CISCCTRL_MAIN_H_RATIO_MASK		(0x1ff << 16)
+
+/* Status register */
+#define EXYNOS_CISTATUS_OVFIY			(1 << 31)
+#define EXYNOS_CISTATUS_OVFICB			(1 << 30)
+#define EXYNOS_CISTATUS_OVFICR			(1 << 29)
+#define EXYNOS_CISTATUS_VSYNC			(1 << 28)
+#define EXYNOS_CISTATUS_SCALERSTART		(1 << 26)
+#define EXYNOS_CISTATUS_WINOFSTEN			(1 << 25)
+#define EXYNOS_CISTATUS_IMGCPTEN			(1 << 22)
+#define EXYNOS_CISTATUS_IMGCPTENSC			(1 << 21)
+#define EXYNOS_CISTATUS_VSYNC_A			(1 << 20)
+#define EXYNOS_CISTATUS_VSYNC_B			(1 << 19)
+#define EXYNOS_CISTATUS_OVRLB			(1 << 18)
+#define EXYNOS_CISTATUS_FRAMEEND			(1 << 17)
+#define EXYNOS_CISTATUS_LASTCAPTUREEND		(1 << 16)
+#define EXYNOS_CISTATUS_VVALID_A			(1 << 15)
+#define EXYNOS_CISTATUS_VVALID_B			(1 << 14)
+
+/* Image capture enable register */
+#define EXYNOS_CIIMGCPT_IMGCPTEN			(1 << 31)
+#define EXYNOS_CIIMGCPT_IMGCPTEN_SC		(1 << 30)
+#define EXYNOS_CIIMGCPT_CPT_FREN_ENABLE		(1 << 25)
+#define EXYNOS_CIIMGCPT_CPT_FRMOD_EN		(0 << 18)
+#define EXYNOS_CIIMGCPT_CPT_FRMOD_CNT		(1 << 18)
+
+/* Image effects register */
+#define EXYNOS_CIIMGEFF_IE_DISABLE			(0 << 30)
+#define EXYNOS_CIIMGEFF_IE_ENABLE			(1 << 30)
+#define EXYNOS_CIIMGEFF_IE_SC_BEFORE		(0 << 29)
+#define EXYNOS_CIIMGEFF_IE_SC_AFTER		(1 << 29)
+#define EXYNOS_CIIMGEFF_FIN_BYPASS			(0 << 26)
+#define EXYNOS_CIIMGEFF_FIN_ARBITRARY		(1 << 26)
+#define EXYNOS_CIIMGEFF_FIN_NEGATIVE		(2 << 26)
+#define EXYNOS_CIIMGEFF_FIN_ARTFREEZE		(3 << 26)
+#define EXYNOS_CIIMGEFF_FIN_EMBOSSING		(4 << 26)
+#define EXYNOS_CIIMGEFF_FIN_SILHOUETTE		(5 << 26)
+#define EXYNOS_CIIMGEFF_FIN_MASK			(7 << 26)
+#define EXYNOS_CIIMGEFF_PAT_CBCR_MASK		((0xff < 13) | (0xff < 0))
+
+/* Real input DMA size register */
+#define EXYNOS_CIREAL_ISIZE_AUTOLOAD_ENABLE	(1 << 31)
+#define EXYNOS_CIREAL_ISIZE_ADDR_CH_DISABLE	(1 << 30)
+#define EXYNOS_CIREAL_ISIZE_HEIGHT_MASK		(0x3FFF << 16)
+#define EXYNOS_CIREAL_ISIZE_WIDTH_MASK		(0x3FFF << 0)
+
+/* Input DMA control register */
+#define EXYNOS_MSCTRL_FIELD_MASK			(1 << 31)
+#define EXYNOS_MSCTRL_FIELD_WEAVE			(1 << 31)
+#define EXYNOS_MSCTRL_FIELD_NORMAL			(0 << 31)
+#define EXYNOS_MSCTRL_BURST_CNT			(24)
+#define EXYNOS_MSCTRL_BURST_CNT_MASK		(0xf << 24)
+#define EXYNOS_MSCTRL_ORDER2P_LSB_CBCR		(0 << 16)
+#define EXYNOS_MSCTRL_ORDER2P_LSB_CRCB		(1 << 16)
+#define EXYNOS_MSCTRL_ORDER2P_MSB_CRCB		(2 << 16)
+#define EXYNOS_MSCTRL_ORDER2P_MSB_CBCR		(3 << 16)
+#define EXYNOS_MSCTRL_ORDER2P_SHIFT		(16)
+#define EXYNOS_MSCTRL_ORDER2P_SHIFT_MASK		(0x3 << 16)
+#define EXYNOS_MSCTRL_C_INT_IN_3PLANE		(0 << 15)
+#define EXYNOS_MSCTRL_C_INT_IN_2PLANE		(1 << 15)
+#define EXYNOS_MSCTRL_FLIP_SHIFT			(13)
+#define EXYNOS_MSCTRL_FLIP_NORMAL			(0 << 13)
+#define EXYNOS_MSCTRL_FLIP_X_MIRROR		(1 << 13)
+#define EXYNOS_MSCTRL_FLIP_Y_MIRROR		(2 << 13)
+#define EXYNOS_MSCTRL_FLIP_180			(3 << 13)
+#define EXYNOS_MSCTRL_FLIP_MASK			(3 << 13)
+#define EXYNOS_MSCTRL_ORDER422_CRYCBY		(0 << 4)
+#define EXYNOS_MSCTRL_ORDER422_YCRYCB		(1 << 4)
+#define EXYNOS_MSCTRL_ORDER422_CBYCRY		(2 << 4)
+#define EXYNOS_MSCTRL_ORDER422_YCBYCR		(3 << 4)
+#define EXYNOS_MSCTRL_INPUT_EXTCAM			(0 << 3)
+#define EXYNOS_MSCTRL_INPUT_MEMORY			(1 << 3)
+#define EXYNOS_MSCTRL_INPUT_MASK			(1 << 3)
+#define EXYNOS_MSCTRL_INFORMAT_YCBCR420		(0 << 1)
+#define EXYNOS_MSCTRL_INFORMAT_YCBCR422		(1 << 1)
+#define EXYNOS_MSCTRL_INFORMAT_YCBCR422_1PLANE	(2 << 1)
+#define EXYNOS_MSCTRL_INFORMAT_RGB			(3 << 1)
+#define EXYNOS_MSCTRL_ENVID			(1 << 0)
+
+/* DMA parameter register */
+#define EXYNOS_CIDMAPARAM_R_MODE_LINEAR		(0 << 29)
+#define EXYNOS_CIDMAPARAM_R_MODE_CONFTILE		(1 << 29)
+#define EXYNOS_CIDMAPARAM_R_MODE_16X16		(2 << 29)
+#define EXYNOS_CIDMAPARAM_R_MODE_64X32		(3 << 29)
+#define EXYNOS_CIDMAPARAM_R_MODE_MASK		(3 << 29)
+#define EXYNOS_CIDMAPARAM_R_TILE_HSIZE_64		(0 << 24)
+#define EXYNOS_CIDMAPARAM_R_TILE_HSIZE_128		(1 << 24)
+#define EXYNOS_CIDMAPARAM_R_TILE_HSIZE_256		(2 << 24)
+#define EXYNOS_CIDMAPARAM_R_TILE_HSIZE_512		(3 << 24)
+#define EXYNOS_CIDMAPARAM_R_TILE_HSIZE_1024	(4 << 24)
+#define EXYNOS_CIDMAPARAM_R_TILE_HSIZE_2048	(5 << 24)
+#define EXYNOS_CIDMAPARAM_R_TILE_HSIZE_4096	(6 << 24)
+#define EXYNOS_CIDMAPARAM_R_TILE_VSIZE_1		(0 << 20)
+#define EXYNOS_CIDMAPARAM_R_TILE_VSIZE_2		(1 << 20)
+#define EXYNOS_CIDMAPARAM_R_TILE_VSIZE_4		(2 << 20)
+#define EXYNOS_CIDMAPARAM_R_TILE_VSIZE_8		(3 << 20)
+#define EXYNOS_CIDMAPARAM_R_TILE_VSIZE_16		(4 << 20)
+#define EXYNOS_CIDMAPARAM_R_TILE_VSIZE_32		(5 << 20)
+#define EXYNOS_CIDMAPARAM_W_MODE_LINEAR		(0 << 13)
+#define EXYNOS_CIDMAPARAM_W_MODE_CONFTILE		(1 << 13)
+#define EXYNOS_CIDMAPARAM_W_MODE_16X16		(2 << 13)
+#define EXYNOS_CIDMAPARAM_W_MODE_64X32		(3 << 13)
+#define EXYNOS_CIDMAPARAM_W_MODE_MASK		(3 << 13)
+#define EXYNOS_CIDMAPARAM_W_TILE_HSIZE_64		(0 << 8)
+#define EXYNOS_CIDMAPARAM_W_TILE_HSIZE_128		(1 << 8)
+#define EXYNOS_CIDMAPARAM_W_TILE_HSIZE_256		(2 << 8)
+#define EXYNOS_CIDMAPARAM_W_TILE_HSIZE_512		(3 << 8)
+#define EXYNOS_CIDMAPARAM_W_TILE_HSIZE_1024	(4 << 8)
+#define EXYNOS_CIDMAPARAM_W_TILE_HSIZE_2048	(5 << 8)
+#define EXYNOS_CIDMAPARAM_W_TILE_HSIZE_4096	(6 << 8)
+#define EXYNOS_CIDMAPARAM_W_TILE_VSIZE_1		(0 << 4)
+#define EXYNOS_CIDMAPARAM_W_TILE_VSIZE_2		(1 << 4)
+#define EXYNOS_CIDMAPARAM_W_TILE_VSIZE_4		(2 << 4)
+#define EXYNOS_CIDMAPARAM_W_TILE_VSIZE_8		(3 << 4)
+#define EXYNOS_CIDMAPARAM_W_TILE_VSIZE_16		(4 << 4)
+#define EXYNOS_CIDMAPARAM_W_TILE_VSIZE_32		(5 << 4)
+
+/* Gathering Extension register */
+#define EXYNOS_CIEXTEN_TARGETH_EXT_MASK		(1 << 26)
+#define EXYNOS_CIEXTEN_TARGETV_EXT_MASK		(1 << 24)
+#define EXYNOS_CIEXTEN_MAINHORRATIO_EXT_MASK	(0x3F << 10)
+#define EXYNOS_CIEXTEN_MAINVERRATIO_EXT_MASK	(0x3F)
+#define EXYNOS_CIEXTEN_YUV444_OUT			(1 << 22)
+
+/* FIMC Clock Source Select register */
+#define EXYNOS_CLKSRC_HCLK				(0 << 1)
+#define EXYNOS_CLKSRC_HCLK_MASK			(1 << 1)
+#define EXYNOS_CLKSRC_SCLK				(1 << 1)
+
+/* SYSREG for FIMC writeback */
+#define SYSREG_CAMERA_BLK			(S3C_VA_SYS + 0x0218)
+#define SYSREG_ISP_BLK				(S3C_VA_SYS + 0x020c)
+#define SYSREG_FIMD0WB_DEST_MASK	(0x3 << 23)
+#define SYSREG_FIMD0WB_DEST_SHIFT	23
+
+#endif /* EXYNOS_REGS_FIMC_H */
diff --git a/include/drm/exynos_drm.h b/include/drm/exynos_drm.h
index 3c13a3a4b158..808dad29607a 100644
--- a/include/drm/exynos_drm.h
+++ b/include/drm/exynos_drm.h
@@ -85,4 +85,30 @@ struct exynos_drm_hdmi_pdata {
 	int (*get_hpd)(void);
 };
 
+/**
+ * Platform Specific Structure for DRM based IPP.
+ *
+ * @inv_pclk: if set 1. invert pixel clock
+ * @inv_vsync: if set 1. invert vsync signal for wb
+ * @inv_href: if set 1. invert href signal
+ * @inv_hsync: if set 1. invert hsync signal for wb
+ */
+struct exynos_drm_ipp_pol {
+	unsigned int inv_pclk;
+	unsigned int inv_vsync;
+	unsigned int inv_href;
+	unsigned int inv_hsync;
+};
+
+/**
+ * Platform Specific Structure for DRM based FIMC.
+ *
+ * @pol: current hardware block polarity settings.
+ * @clk_rate: current hardware clock rate.
+ */
+struct exynos_drm_fimc_pdata {
+	struct exynos_drm_ipp_pol pol;
+	int clk_rate;
+};
+
 #endif	/* _EXYNOS_DRM_H_ */
-- 
cgit v1.2.3-55-g7522


From 093d04d42fa094f6740bb188f0ad0c215ff61e2c Mon Sep 17 00:00:00 2001
From: Duan Jiong
Date: Fri, 14 Dec 2012 02:59:59 +0000
Subject: ipv6: Change skb->data before using icmpv6_notify() to propagate
 redirect

In function ndisc_redirect_rcv(), the skb->data points to the transport
header, but function icmpv6_notify() need the skb->data points to the
inner IP packet. So before using icmpv6_notify() to propagate redirect,
change skb->data to point the inner IP packet that triggered the sending
of the Redirect, and introduce struct rd_msg to make it easy.

Signed-off-by: Duan Jiong <djduanjiong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ndisc.h |  7 +++++++
 net/ipv6/ndisc.c    | 17 +++++++++++++++++
 2 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 7af1ea893038..23b3a7c58783 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -78,6 +78,13 @@ struct ra_msg {
 	__be32			retrans_timer;
 };
 
+struct rd_msg {
+	struct icmp6hdr icmph;
+	struct in6_addr	target;
+	struct in6_addr	dest;
+	__u8		opt[0];
+};
+
 struct nd_opt_hdr {
 	__u8		nd_opt_type;
 	__u8		nd_opt_len;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index f2a007b7bde3..6574175795df 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1314,6 +1314,12 @@ out:
 
 static void ndisc_redirect_rcv(struct sk_buff *skb)
 {
+	u8 *hdr;
+	struct ndisc_options ndopts;
+	struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb);
+	u32 ndoptlen = skb->tail - (skb->transport_header +
+				    offsetof(struct rd_msg, opt));
+
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	switch (skb->ndisc_nodetype) {
 	case NDISC_NODETYPE_HOST:
@@ -1330,6 +1336,17 @@ static void ndisc_redirect_rcv(struct sk_buff *skb)
 		return;
 	}
 
+	if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts))
+		return;
+
+	if (!ndopts.nd_opts_rh)
+		return;
+
+	hdr = (u8 *)ndopts.nd_opts_rh;
+	hdr += 8;
+	if (!pskb_pull(skb, hdr - skb_transport_header(skb)))
+		return;
+
 	icmpv6_notify(skb, NDISC_REDIRECT, 0, 0);
 }
 
-- 
cgit v1.2.3-55-g7522


From e337e24d6624e74a558aa69071e112a65f7b5758 Mon Sep 17 00:00:00 2001
From: Christoph Paasch
Date: Fri, 14 Dec 2012 04:07:58 +0000
Subject: inet: Fix kmemleak in tcp_v4/6_syn_recv_sock and
 dccp_v4/6_request_recv_sock

If in either of the above functions inet_csk_route_child_sock() or
__inet_inherit_port() fails, the newsk will not be freed:

unreferenced object 0xffff88022e8a92c0 (size 1592):
  comm "softirq", pid 0, jiffies 4294946244 (age 726.160s)
  hex dump (first 32 bytes):
    0a 01 01 01 0a 01 01 02 00 00 00 00 a7 cc 16 00  ................
    02 00 03 01 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff8153d190>] kmemleak_alloc+0x21/0x3e
    [<ffffffff810ab3e7>] kmem_cache_alloc+0xb5/0xc5
    [<ffffffff8149b65b>] sk_prot_alloc.isra.53+0x2b/0xcd
    [<ffffffff8149b784>] sk_clone_lock+0x16/0x21e
    [<ffffffff814d711a>] inet_csk_clone_lock+0x10/0x7b
    [<ffffffff814ebbc3>] tcp_create_openreq_child+0x21/0x481
    [<ffffffff814e8fa5>] tcp_v4_syn_recv_sock+0x3a/0x23b
    [<ffffffff814ec5ba>] tcp_check_req+0x29f/0x416
    [<ffffffff814e8e10>] tcp_v4_do_rcv+0x161/0x2bc
    [<ffffffff814eb917>] tcp_v4_rcv+0x6c9/0x701
    [<ffffffff814cea9f>] ip_local_deliver_finish+0x70/0xc4
    [<ffffffff814cec20>] ip_local_deliver+0x4e/0x7f
    [<ffffffff814ce9f8>] ip_rcv_finish+0x1fc/0x233
    [<ffffffff814cee68>] ip_rcv+0x217/0x267
    [<ffffffff814a7bbe>] __netif_receive_skb+0x49e/0x553
    [<ffffffff814a7cc3>] netif_receive_skb+0x50/0x82

This happens, because sk_clone_lock initializes sk_refcnt to 2, and thus
a single sock_put() is not enough to free the memory. Additionally, things
like xfrm, memcg, cookie_values,... may have been initialized.
We have to free them properly.

This is fixed by forcing a call to tcp_done(), ending up in
inet_csk_destroy_sock, doing the final sock_put(). tcp_done() is necessary,
because it ends up doing all the cleanup on xfrm, memcg, cookie_values,
xfrm,...

Before calling tcp_done, we have to set the socket to SOCK_DEAD, to
force it entering inet_csk_destroy_sock. To avoid the warning in
inet_csk_destroy_sock, inet_num has to be set to 0.
As inet_csk_destroy_sock does a dec on orphan_count, we first have to
increase it.

Calling tcp_done() allows us to remove the calls to
tcp_clear_xmit_timer() and tcp_cleanup_congestion_control().

A similar approach is taken for dccp by calling dccp_done().

This is in the kernel since 093d282321 (tproxy: fix hash locking issue
when using port redirection in __inet_inherit_port()), thus since
version >= 2.6.37.

Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h |  1 +
 net/dccp/ipv4.c                    |  4 ++--
 net/dccp/ipv6.c                    |  3 ++-
 net/ipv4/inet_connection_sock.c    | 16 ++++++++++++++++
 net/ipv4/tcp_ipv4.c                |  6 ++----
 net/ipv6/tcp_ipv6.c                |  3 ++-
 6 files changed, 25 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index ba1d3615acbb..183292722f6e 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -318,6 +318,7 @@ extern void inet_csk_reqsk_queue_prune(struct sock *parent,
 				       const unsigned long max_rto);
 
 extern void inet_csk_destroy_sock(struct sock *sk);
+extern void inet_csk_prepare_forced_close(struct sock *sk);
 
 /*
  * LISTEN is a special case for poll..
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 176ecdba4a22..4f9f5eb478f1 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -439,8 +439,8 @@ exit:
 	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return NULL;
 put_and_exit:
-	bh_unlock_sock(newsk);
-	sock_put(newsk);
+	inet_csk_prepare_forced_close(newsk);
+	dccp_done(newsk);
 	goto exit;
 }
 
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 56840b249f3b..6e05981f271e 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -585,7 +585,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 	newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
 
 	if (__inet_inherit_port(sk, newsk) < 0) {
-		sock_put(newsk);
+		inet_csk_prepare_forced_close(newsk);
+		dccp_done(newsk);
 		goto out;
 	}
 	__inet6_hash(newsk, NULL);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 2026542d6836..d0670f00d524 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -710,6 +710,22 @@ void inet_csk_destroy_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_csk_destroy_sock);
 
+/* This function allows to force a closure of a socket after the call to
+ * tcp/dccp_create_openreq_child().
+ */
+void inet_csk_prepare_forced_close(struct sock *sk)
+{
+	/* sk_clone_lock locked the socket and set refcnt to 2 */
+	bh_unlock_sock(sk);
+	sock_put(sk);
+
+	/* The below has to be done to allow calling inet_csk_destroy_sock */
+	sock_set_flag(sk, SOCK_DEAD);
+	percpu_counter_inc(sk->sk_prot->orphan_count);
+	inet_sk(sk)->inet_num = 0;
+}
+EXPORT_SYMBOL(inet_csk_prepare_forced_close);
+
 int inet_csk_listen_start(struct sock *sk, const int nr_table_entries)
 {
 	struct inet_sock *inet = inet_sk(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1ed230716d51..54139fa514e6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1767,10 +1767,8 @@ exit:
 	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return NULL;
 put_and_exit:
-	tcp_clear_xmit_timers(newsk);
-	tcp_cleanup_congestion_control(newsk);
-	bh_unlock_sock(newsk);
-	sock_put(newsk);
+	inet_csk_prepare_forced_close(newsk);
+	tcp_done(newsk);
 	goto exit;
 }
 EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6565cf55eb1e..93825dd3a7c0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1288,7 +1288,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 #endif
 
 	if (__inet_inherit_port(sk, newsk) < 0) {
-		sock_put(newsk);
+		inet_csk_prepare_forced_close(newsk);
+		tcp_done(newsk);
 		goto out;
 	}
 	__inet6_hash(newsk, NULL);
-- 
cgit v1.2.3-55-g7522


From ca2e16faa7378878c1522a7c1b6c38211de3331d Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen
Date: Thu, 22 Nov 2012 10:39:56 +0200
Subject: OMAP: board-files: fix i2c_bus for tfp410

The i2c handling in tfp410 driver, which handles converting parallel RGB
to DVI, was changed in 958f2717b84e88bf833d996997fda8f73276f2af
(OMAPDSS: TFP410: pdata rewrite). The patch changed what value the
driver considers as invalid/undefined.  Before the patch, 0 was the
invalid value, but as 0 is a valid bus number, the patch changed this to
-1.

However, the fact was missed that many board files do not define the bus
number at all, thus it's left to 0. This causes the driver to fail to
get the i2c bus, exiting from the driver's probe with an error, meaning
that the DVI output does not work for those boards.

This patch fixes the issue by changing the i2c_bus number field in the
driver's platform data from u16 to int, and setting the bus number to -1
in the board files for the boards that did not define the bus. The
exception is devkit8000, for which the bus is set to 1, which is the
correct bus for that board.

The bug exists in v3.5+ kernels.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Reported-by: Thomas Weber <thomas@tomweber.eu>
Cc: Thomas Weber <thomas@tomweber.eu>
Cc: <stable@vger.kernel.org> # v3.5+
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/board-3430sdp.c      | 1 +
 arch/arm/mach-omap2/board-am3517evm.c    | 1 +
 arch/arm/mach-omap2/board-cm-t35.c       | 1 +
 arch/arm/mach-omap2/board-devkit8000.c   | 1 +
 arch/arm/mach-omap2/board-omap3evm.c     | 1 +
 arch/arm/mach-omap2/board-omap3stalker.c | 1 +
 include/video/omap-panel-tfp410.h        | 2 +-
 7 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/board-3430sdp.c b/arch/arm/mach-omap2/board-3430sdp.c
index 7b201546834d..bb73afc9ac17 100644
--- a/arch/arm/mach-omap2/board-3430sdp.c
+++ b/arch/arm/mach-omap2/board-3430sdp.c
@@ -157,6 +157,7 @@ static struct omap_dss_device sdp3430_lcd_device = {
 
 static struct tfp410_platform_data dvi_panel = {
 	.power_down_gpio	= -1,
+	.i2c_bus_num		= -1,
 };
 
 static struct omap_dss_device sdp3430_dvi_device = {
diff --git a/arch/arm/mach-omap2/board-am3517evm.c b/arch/arm/mach-omap2/board-am3517evm.c
index 4be58fd071f6..f81a303b87ff 100644
--- a/arch/arm/mach-omap2/board-am3517evm.c
+++ b/arch/arm/mach-omap2/board-am3517evm.c
@@ -208,6 +208,7 @@ static struct omap_dss_device am3517_evm_tv_device = {
 
 static struct tfp410_platform_data dvi_panel = {
 	.power_down_gpio	= -1,
+	.i2c_bus_num		= -1,
 };
 
 static struct omap_dss_device am3517_evm_dvi_device = {
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index c8e37dc00892..b3102c2f4a3c 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -241,6 +241,7 @@ static struct omap_dss_device cm_t35_lcd_device = {
 
 static struct tfp410_platform_data dvi_panel = {
 	.power_down_gpio	= CM_T35_DVI_EN_GPIO,
+	.i2c_bus_num		= -1,
 };
 
 static struct omap_dss_device cm_t35_dvi_device = {
diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c
index 7667eb749522..12865af25d3a 100644
--- a/arch/arm/mach-omap2/board-devkit8000.c
+++ b/arch/arm/mach-omap2/board-devkit8000.c
@@ -141,6 +141,7 @@ static struct omap_dss_device devkit8000_lcd_device = {
 
 static struct tfp410_platform_data dvi_panel = {
 	.power_down_gpio	= -1,
+	.i2c_bus_num		= 1,
 };
 
 static struct omap_dss_device devkit8000_dvi_device = {
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index 54647d6286b4..3985f35aee06 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -240,6 +240,7 @@ static struct omap_dss_device omap3_evm_tv_device = {
 
 static struct tfp410_platform_data dvi_panel = {
 	.power_down_gpio	= OMAP3EVM_DVI_PANEL_EN_GPIO,
+	.i2c_bus_num		= -1,
 };
 
 static struct omap_dss_device omap3_evm_dvi_device = {
diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c
index d8638b3b4f94..53a6cbcf9747 100644
--- a/arch/arm/mach-omap2/board-omap3stalker.c
+++ b/arch/arm/mach-omap2/board-omap3stalker.c
@@ -118,6 +118,7 @@ static struct omap_dss_device omap3_stalker_tv_device = {
 
 static struct tfp410_platform_data dvi_panel = {
 	.power_down_gpio	= DSS_ENABLE_GPIO,
+	.i2c_bus_num		= -1,
 };
 
 static struct omap_dss_device omap3_stalker_dvi_device = {
diff --git a/include/video/omap-panel-tfp410.h b/include/video/omap-panel-tfp410.h
index 68c31d79c571..aef35e48bc7e 100644
--- a/include/video/omap-panel-tfp410.h
+++ b/include/video/omap-panel-tfp410.h
@@ -28,7 +28,7 @@ struct omap_dss_device;
  * @power_down_gpio: gpio number for PD pin (or -1 if not available)
  */
 struct tfp410_platform_data {
-	u16 i2c_bus_num;
+	int i2c_bus_num;
 	int power_down_gpio;
 };
 
-- 
cgit v1.2.3-55-g7522


From 8dd2cb7e880d2f77fba53b523c99133ad5054cfd Mon Sep 17 00:00:00 2001
From: Shaohua Li
Date: Fri, 14 Dec 2012 11:15:36 +0800
Subject: block: discard granularity might not be power of 2

In MD raid case, discard granularity might not be power of 2, for example, a
4-disk raid5 has 3*chunk_size discard granularity. Correct the calculation for
such cases.

Reported-by: Neil Brown <neilb@suse.de>
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-lib.c        | 23 +++++++++++++----------
 block/blk-settings.c   |  6 +++---
 include/linux/blkdev.h |  7 ++++---
 3 files changed, 20 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 9373b58dfab1..5677fd33d7d2 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -43,8 +43,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	DECLARE_COMPLETION_ONSTACK(wait);
 	struct request_queue *q = bdev_get_queue(bdev);
 	int type = REQ_WRITE | REQ_DISCARD;
-	unsigned int max_discard_sectors;
-	unsigned int granularity, alignment, mask;
+	sector_t max_discard_sectors;
+	sector_t granularity, alignment;
 	struct bio_batch bb;
 	struct bio *bio;
 	int ret = 0;
@@ -57,15 +57,16 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
 	granularity = max(q->limits.discard_granularity >> 9, 1U);
-	mask = granularity - 1;
-	alignment = (bdev_discard_alignment(bdev) >> 9) & mask;
+	alignment = bdev_discard_alignment(bdev) >> 9;
+	alignment = sector_div(alignment, granularity);
 
 	/*
 	 * Ensure that max_discard_sectors is of the proper
 	 * granularity, so that requests stay aligned after a split.
 	 */
 	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
-	max_discard_sectors = round_down(max_discard_sectors, granularity);
+	sector_div(max_discard_sectors, granularity);
+	max_discard_sectors *= granularity;
 	if (unlikely(!max_discard_sectors)) {
 		/* Avoid infinite loop below. Being cautious never hurts. */
 		return -EOPNOTSUPP;
@@ -83,7 +84,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 	while (nr_sects) {
 		unsigned int req_sects;
-		sector_t end_sect;
+		sector_t end_sect, tmp;
 
 		bio = bio_alloc(gfp_mask, 1);
 		if (!bio) {
@@ -98,10 +99,12 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		 * misaligned, stop the discard at the previous aligned sector.
 		 */
 		end_sect = sector + req_sects;
-		if (req_sects < nr_sects && (end_sect & mask) != alignment) {
-			end_sect =
-				round_down(end_sect - alignment, granularity)
-				+ alignment;
+		tmp = end_sect;
+		if (req_sects < nr_sects &&
+		    sector_div(tmp, granularity) != alignment) {
+			end_sect = end_sect - alignment;
+			sector_div(end_sect, granularity);
+			end_sect = end_sect * granularity + alignment;
 			req_sects = end_sect - sector;
 		}
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 779bb7646bcd..c50ecf0ea3b1 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -611,7 +611,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			bottom = b->discard_granularity + alignment;
 
 			/* Verify that top and bottom intervals line up */
-			if (max(top, bottom) & (min(top, bottom) - 1))
+			if ((max(top, bottom) % min(top, bottom)) != 0)
 				t->discard_misaligned = 1;
 		}
 
@@ -619,8 +619,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 						      b->max_discard_sectors);
 		t->discard_granularity = max(t->discard_granularity,
 					     b->discard_granularity);
-		t->discard_alignment = lcm(t->discard_alignment, alignment) &
-			(t->discard_granularity - 1);
+		t->discard_alignment = lcm(t->discard_alignment, alignment) %
+			t->discard_granularity;
 	}
 
 	return ret;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c9d233e727f2..acb4f7bbbd32 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1188,13 +1188,14 @@ static inline int queue_discard_alignment(struct request_queue *q)
 
 static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector)
 {
-	unsigned int alignment = (sector << 9) & (lim->discard_granularity - 1);
+	sector_t alignment = sector << 9;
+	alignment = sector_div(alignment, lim->discard_granularity);
 
 	if (!lim->max_discard_sectors)
 		return 0;
 
-	return (lim->discard_granularity + lim->discard_alignment - alignment)
-		& (lim->discard_granularity - 1);
+	alignment = lim->discard_granularity + lim->discard_alignment - alignment;
+	return sector_div(alignment, lim->discard_granularity);
 }
 
 static inline int bdev_discard_alignment(struct block_device *bdev)
-- 
cgit v1.2.3-55-g7522


From 63b68901dfd590cc13d4fe5c08dec2ca75b3c4aa Mon Sep 17 00:00:00 2001
From: Roger Quadros
Date: Fri, 14 Dec 2012 09:09:11 -0800
Subject: mfd: omap-usb-host: get rid of cpu_is_omap..() macros

Instead of using cpu_is_omap..() macros in the device driver we
rely on information provided in the platform data.

The only information we need is whether the USB Host module has
a single ULPI bypass control bit for all ports or individual bypass
control bits for each port. OMAP3 REV2.1 and earlier have the former.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Acked-by: Samuel Ortiz <sameo@linux.intel.com>
[tony@atomide.com: updated to remove plat/cpu.h]
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/usb-host.c         | 4 ++++
 drivers/mfd/omap-usb-host.c            | 3 +--
 include/linux/platform_data/usb-omap.h | 3 +++
 3 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/usb-host.c b/arch/arm/mach-omap2/usb-host.c
index d1dbe125b34f..2e44e8a22884 100644
--- a/arch/arm/mach-omap2/usb-host.c
+++ b/arch/arm/mach-omap2/usb-host.c
@@ -508,6 +508,10 @@ void __init usbhs_init(const struct usbhs_omap_board_data *pdata)
 	if (cpu_is_omap34xx()) {
 		setup_ehci_io_mux(pdata->port_mode);
 		setup_ohci_io_mux(pdata->port_mode);
+
+		if (omap_rev() <= OMAP3430_REV_ES2_1)
+			usbhs_data.single_ulpi_bypass = true;
+
 	} else if (cpu_is_omap44xx()) {
 		setup_4430ehci_io_mux(pdata->port_mode);
 		setup_4430ohci_io_mux(pdata->port_mode);
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 770a0d01e0b9..05164d7f054b 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -25,7 +25,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/spinlock.h>
 #include <linux/gpio.h>
-#include <plat/cpu.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/usb-omap.h>
 #include <linux/pm_runtime.h>
@@ -384,7 +383,7 @@ static void omap_usbhs_init(struct device *dev)
 			reg &= ~OMAP_UHH_HOSTCONFIG_P3_CONNECT_STATUS;
 
 		/* Bypass the TLL module for PHY mode operation */
-		if (cpu_is_omap3430() && (omap_rev() <= OMAP3430_REV_ES2_1)) {
+		if (pdata->single_ulpi_bypass) {
 			dev_dbg(dev, "OMAP3 ES version <= ES2.1\n");
 			if (is_ehci_phy_mode(pdata->port_mode[0]) ||
 				is_ehci_phy_mode(pdata->port_mode[1]) ||
diff --git a/include/linux/platform_data/usb-omap.h b/include/linux/platform_data/usb-omap.h
index 8570bcfe6311..ef65b67c56c3 100644
--- a/include/linux/platform_data/usb-omap.h
+++ b/include/linux/platform_data/usb-omap.h
@@ -59,6 +59,9 @@ struct usbhs_omap_platform_data {
 
 	struct ehci_hcd_omap_platform_data	*ehci_data;
 	struct ohci_hcd_omap_platform_data	*ohci_data;
+
+	/* OMAP3 <= ES2.1 have a single ulpi bypass control bit */
+	unsigned				single_ulpi_bypass:1;
 };
 
 /*-------------------------------------------------------------------------*/
-- 
cgit v1.2.3-55-g7522


From d9ba573718666df2e7e30d671f81bba39d07f91c Mon Sep 17 00:00:00 2001
From: Tony Lindgren
Date: Fri, 14 Dec 2012 09:09:11 -0800
Subject: ARM: OMAP: Move plat/omap-serial.h to
 include/linux/platform_data/serial-omap.h

We need to move this file to allow ARM multiplatform configurations
to build for omap2+. This can now be done as this file now only
contains platform_data.

cc: Russell King <linux@arm.linux.org.uk>
cc: Alan Cox <alan@linux.intel.com>
cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cc: Govindraj.R <govindraj.raja@ti.com>
cc: Kevin Hilman <khilman@ti.com>
cc: linux-serial@vger.kernel.org
Reviewed-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/serial.c                  |  3 +-
 arch/arm/plat-omap/include/plat/omap-serial.h | 51 ---------------------------
 drivers/tty/serial/omap-serial.c              |  3 +-
 include/linux/platform_data/serial-omap.h     | 51 +++++++++++++++++++++++++++
 4 files changed, 53 insertions(+), 55 deletions(-)
 delete mode 100644 arch/arm/plat-omap/include/plat/omap-serial.h
 create mode 100644 include/linux/platform_data/serial-omap.h

(limited to 'include')

diff --git a/arch/arm/mach-omap2/serial.c b/arch/arm/mach-omap2/serial.c
index 93d102535c85..04fdbc4c499b 100644
--- a/arch/arm/mach-omap2/serial.c
+++ b/arch/arm/mach-omap2/serial.c
@@ -27,8 +27,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/console.h>
 #include <linux/omap-dma.h>
-
-#include <plat/omap-serial.h>
+#include <linux/platform_data/serial-omap.h>
 
 #include "common.h"
 #include "omap_hwmod.h"
diff --git a/arch/arm/plat-omap/include/plat/omap-serial.h b/arch/arm/plat-omap/include/plat/omap-serial.h
deleted file mode 100644
index ff9b0aab5281..000000000000
--- a/arch/arm/plat-omap/include/plat/omap-serial.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- * Driver for OMAP-UART controller.
- * Based on drivers/serial/8250.c
- *
- * Copyright (C) 2010 Texas Instruments.
- *
- * Authors:
- *	Govindraj R	<govindraj.raja@ti.com>
- *	Thara Gopinath	<thara@ti.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef __OMAP_SERIAL_H__
-#define __OMAP_SERIAL_H__
-
-#include <linux/serial_core.h>
-#include <linux/device.h>
-#include <linux/pm_qos.h>
-
-#define DRIVER_NAME	"omap_uart"
-
-/*
- * Use tty device name as ttyO, [O -> OMAP]
- * in bootargs we specify as console=ttyO0 if uart1
- * is used as console uart.
- */
-#define OMAP_SERIAL_NAME	"ttyO"
-
-struct omap_uart_port_info {
-	bool			dma_enabled;	/* To specify DMA Mode */
-	unsigned int		uartclk;	/* UART clock rate */
-	upf_t			flags;		/* UPF_* flags */
-	unsigned int		dma_rx_buf_size;
-	unsigned int		dma_rx_timeout;
-	unsigned int		autosuspend_timeout;
-	unsigned int		dma_rx_poll_rate;
-	int			DTR_gpio;
-	int			DTR_inverted;
-	int			DTR_present;
-
-	int (*get_context_loss_count)(struct device *);
-	void (*set_forceidle)(struct device *);
-	void (*set_noidle)(struct device *);
-	void (*enable_wakeup)(struct device *, bool);
-};
-
-#endif /* __OMAP_SERIAL_H__ */
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 23f797eb7a28..57d6b29c039c 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -41,8 +41,7 @@
 #include <linux/of.h>
 #include <linux/gpio.h>
 #include <linux/pinctrl/consumer.h>
-
-#include <plat/omap-serial.h>
+#include <linux/platform_data/serial-omap.h>
 
 #define OMAP_MAX_HSUART_PORTS	6
 
diff --git a/include/linux/platform_data/serial-omap.h b/include/linux/platform_data/serial-omap.h
new file mode 100644
index 000000000000..ff9b0aab5281
--- /dev/null
+++ b/include/linux/platform_data/serial-omap.h
@@ -0,0 +1,51 @@
+/*
+ * Driver for OMAP-UART controller.
+ * Based on drivers/serial/8250.c
+ *
+ * Copyright (C) 2010 Texas Instruments.
+ *
+ * Authors:
+ *	Govindraj R	<govindraj.raja@ti.com>
+ *	Thara Gopinath	<thara@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __OMAP_SERIAL_H__
+#define __OMAP_SERIAL_H__
+
+#include <linux/serial_core.h>
+#include <linux/device.h>
+#include <linux/pm_qos.h>
+
+#define DRIVER_NAME	"omap_uart"
+
+/*
+ * Use tty device name as ttyO, [O -> OMAP]
+ * in bootargs we specify as console=ttyO0 if uart1
+ * is used as console uart.
+ */
+#define OMAP_SERIAL_NAME	"ttyO"
+
+struct omap_uart_port_info {
+	bool			dma_enabled;	/* To specify DMA Mode */
+	unsigned int		uartclk;	/* UART clock rate */
+	upf_t			flags;		/* UPF_* flags */
+	unsigned int		dma_rx_buf_size;
+	unsigned int		dma_rx_timeout;
+	unsigned int		autosuspend_timeout;
+	unsigned int		dma_rx_poll_rate;
+	int			DTR_gpio;
+	int			DTR_inverted;
+	int			DTR_present;
+
+	int (*get_context_loss_count)(struct device *);
+	void (*set_forceidle)(struct device *);
+	void (*set_noidle)(struct device *);
+	void (*enable_wakeup)(struct device *, bool);
+};
+
+#endif /* __OMAP_SERIAL_H__ */
-- 
cgit v1.2.3-55-g7522


From 9bffb1fb7c22c96d51d4ba06e2e023dd568a5872 Mon Sep 17 00:00:00 2001
From: Misael Lopez Cruz
Date: Thu, 13 Dec 2012 12:23:05 -0600
Subject: ASoC: Prevent pop_wait overwrite

pop_wait is used to determine if a deferred playback close
needs to be cancelled when the a PCM is open or if after
the power-down delay expires it needs to run. pop_wait is
associated with the CODEC DAI, so the CODEC DAI must be
unique. This holds true for most CODECs, except for the
dummy CODEC and its DAI.

In DAI links with non-unique dummy CODECs (e.g. front-ends),
pop_wait can be overwritten by another DAI link using also a
dummy CODEC. Failure to cancel a deferred close can cause
mute due to the DAPM STOP event sent in the deferred work.

One scenario where pop_wait is overwritten and causing mute
is below (where hw:0,0 and hw:0,1 are two front-ends with
default pmdown_time = 5 secs):

aplay /dev/urandom -D hw:0,0 -c 2 -r 48000 -f S16_LE -d 1
sleep 1
aplay /dev/urandom -D hw:0,1 -c 2 -r 48000 -f S16_LE -d 3 &
aplay /dev/urandom -D hw:0,0 -c 2 -r 48000 -f S16_LE

Since CODECs may not be unique, pop_wait is moved to the PCM
runtime structure. Creating separate dummy CODECs for each
DAI link can also solve the problem, but at this point it's
only pop_wait variable in the CODEC DAI that has negative
effects by not being unique.

Signed-off-by: Misael Lopez Cruz <misael.lopez@ti.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/sound/soc-dai.h  |  1 -
 include/sound/soc.h      |  1 +
 sound/soc/soc-compress.c |  2 +-
 sound/soc/soc-pcm.c      | 12 ++++++------
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index 628db7bca4fd..3953cea0ecfb 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -242,7 +242,6 @@ struct snd_soc_dai {
 	unsigned int symmetric_rates:1;
 	struct snd_pcm_runtime *runtime;
 	unsigned int active;
-	unsigned char pop_wait:1;
 	unsigned char probed:1;
 
 	struct snd_soc_dapm_widget *playback_widget;
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 91244a096c19..769e27c774a3 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1039,6 +1039,7 @@ struct snd_soc_pcm_runtime {
 	struct snd_soc_dpcm_runtime dpcm[2];
 
 	long pmdown_time;
+	unsigned char pop_wait:1;
 
 	/* runtime devices */
 	struct snd_pcm *pcm;
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index 967d0e173e1b..5fbfb06e8083 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -113,7 +113,7 @@ static int soc_compr_free(struct snd_compr_stream *cstream)
 					SNDRV_PCM_STREAM_PLAYBACK,
 					SND_SOC_DAPM_STREAM_STOP);
 		} else
-			codec_dai->pop_wait = 1;
+			rtd->pop_wait = 1;
 			schedule_delayed_work(&rtd->delayed_work,
 				msecs_to_jiffies(rtd->pmdown_time));
 	} else {
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index ef22d0bd9e9e..3a2423bd84b2 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -333,11 +333,11 @@ static void close_delayed_work(struct work_struct *work)
 	pr_debug("pop wq checking: %s status: %s waiting: %s\n",
 		 codec_dai->driver->playback.stream_name,
 		 codec_dai->playback_active ? "active" : "inactive",
-		 codec_dai->pop_wait ? "yes" : "no");
+		 rtd->pop_wait ? "yes" : "no");
 
 	/* are we waiting on this codec DAI stream */
-	if (codec_dai->pop_wait == 1) {
-		codec_dai->pop_wait = 0;
+	if (rtd->pop_wait == 1) {
+		rtd->pop_wait = 0;
 		snd_soc_dapm_stream_event(rtd, SNDRV_PCM_STREAM_PLAYBACK,
 					  SND_SOC_DAPM_STREAM_STOP);
 	}
@@ -407,7 +407,7 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 						  SND_SOC_DAPM_STREAM_STOP);
 		} else {
 			/* start delayed pop wq here for playback streams */
-			codec_dai->pop_wait = 1;
+			rtd->pop_wait = 1;
 			schedule_delayed_work(&rtd->delayed_work,
 				msecs_to_jiffies(rtd->pmdown_time));
 		}
@@ -478,8 +478,8 @@ static int soc_pcm_prepare(struct snd_pcm_substream *substream)
 
 	/* cancel any delayed stream shutdown that is pending */
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK &&
-	    codec_dai->pop_wait) {
-		codec_dai->pop_wait = 0;
+	    rtd->pop_wait) {
+		rtd->pop_wait = 0;
 		cancel_delayed_work(&rtd->delayed_work);
 	}
 
-- 
cgit v1.2.3-55-g7522


From 8e63b6a8adabb0551124c3b78f7f5f36912c3728 Mon Sep 17 00:00:00 2001
From: Trond Myklebust
Date: Sat, 15 Dec 2012 15:21:52 -0500
Subject: NFSv4.1: Move the RPC timestamp out of the slot.

Shave a few bytes off the slot table size by moving the RPC timestamp
into the sequence results.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c       | 14 +++++++-------
 fs/nfs/nfs4session.c    |  3 +--
 fs/nfs/nfs4session.h    |  1 -
 include/linux/nfs_xdr.h |  1 +
 4 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 9003b8f6b77f..afb428e63b52 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -419,7 +419,6 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 {
 	struct nfs4_session *session;
 	struct nfs4_slot *slot;
-	unsigned long timestamp;
 	struct nfs_client *clp;
 	int ret = 1;
 
@@ -444,9 +443,8 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 	case 0:
 		/* Update the slot's sequence and clientid lease timer */
 		++slot->seq_nr;
-		timestamp = slot->renewal_time;
 		clp = session->clp;
-		do_renew_lease(clp, timestamp);
+		do_renew_lease(clp, res->sr_timestamp);
 		/* Check sequence flags */
 		if (res->sr_status_flags != 0)
 			nfs4_schedule_lease_recovery(clp);
@@ -473,10 +471,11 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
 		 * Could this slot have been previously retired?
 		 * If so, then the server may be expecting seq_nr = 1!
 		 */
-		if (slot->seq_nr == 1)
-			break;
-		slot->seq_nr = 1;
-		goto retry_nowait;
+		if (slot->seq_nr != 1) {
+			slot->seq_nr = 1;
+			goto retry_nowait;
+		}
+		break;
 	case -NFS4ERR_SEQ_FALSE_RETRY:
 		++slot->seq_nr;
 		goto retry_nowait;
@@ -567,6 +566,7 @@ int nfs41_setup_sequence(struct nfs4_session *session,
 			slot->slot_nr, slot->seq_nr);
 
 	res->sr_slot = slot;
+	res->sr_timestamp = jiffies;
 	res->sr_status_flags = 0;
 	/*
 	 * sr_status is only set in decode_sequence, and so will remain
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index 1e6c87c443a7..0e1cc1f4e51a 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -143,7 +143,6 @@ struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl)
 	if (slotid > tbl->highest_used_slotid ||
 			tbl->highest_used_slotid == NFS4_NO_SLOT)
 		tbl->highest_used_slotid = slotid;
-	ret->renewal_time = jiffies;
 	ret->generation = tbl->generation;
 
 out:
@@ -228,9 +227,9 @@ static bool nfs41_assign_slot(struct rpc_task *task, void *pslot)
 
 	if (nfs4_session_draining(tbl->session) && !args->sa_privileged)
 		return false;
-	slot->renewal_time = jiffies;
 	slot->generation = tbl->generation;
 	args->sa_slot = slot;
+	res->sr_timestamp = jiffies;
 	res->sr_slot = slot;
 	res->sr_status_flags = 0;
 	res->sr_status = 1;
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 04f834cab16c..d17b08091d4b 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -19,7 +19,6 @@ struct nfs4_slot {
 	struct nfs4_slot_table	*table;
 	struct nfs4_slot	*next;
 	unsigned long		generation;
-	unsigned long		renewal_time;
 	u32			slot_nr;
 	u32		 	seq_nr;
 };
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index a55abd499c21..29adb12c7ecf 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -194,6 +194,7 @@ struct nfs4_sequence_args {
 
 struct nfs4_sequence_res {
 	struct nfs4_slot	*sr_slot;	/* slot used to send request */
+	unsigned long		sr_timestamp;
 	int			sr_status;	/* sequence operation status */
 	u32			sr_status_flags;
 	u32			sr_highest_slotid;
-- 
cgit v1.2.3-55-g7522


From 11520e5e7c1855fc3bf202bb3be35a39d9efa034 Mon Sep 17 00:00:00 2001
From: Linus Torvalds
Date: Sat, 15 Dec 2012 15:15:24 -0800
Subject: Revert "x86-64/efi: Use EFI to deal with platform wall clock (again)"

This reverts commit bd52276fa1d4 ("x86-64/efi: Use EFI to deal with
platform wall clock (again)"), and the two supporting commits:

  da5a108d05b4: "x86/kernel: remove tboot 1:1 page table creation code"

  185034e72d59: "x86, efi: 1:1 pagetable mapping for virtual EFI calls")

as they all depend semantically on commit 53b87cf088e2 ("x86, mm:
Include the entire kernel memory map in trampoline_pgd") that got
reverted earlier due to the problems it caused.

This was pointed out by Yinghai Lu, and verified by me on my Macbook Air
that uses EFI.

Pointed-out-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/efi.h     | 28 ++++-----------
 arch/x86/kernel/tboot.c        | 78 +++++++++++++++++++++++++++++++++++++++---
 arch/x86/mm/pageattr.c         | 10 +++---
 arch/x86/platform/efi/efi.c    | 30 +++++++++++++---
 arch/x86/platform/efi/efi_64.c | 15 --------
 include/linux/efi.h            |  2 ++
 init/main.c                    |  8 ++---
 7 files changed, 116 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index fd13815fe85c..6e8fdf5ad113 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -69,37 +69,23 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 	efi_call6((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
 		  (u64)(a4), (u64)(a5), (u64)(a6))
 
-extern unsigned long efi_call_virt_prelog(void);
-extern void efi_call_virt_epilog(unsigned long);
-
-#define efi_callx(x, func, ...)					\
-	({							\
-		efi_status_t __status;				\
-		unsigned long __pgd;				\
-								\
-		__pgd = efi_call_virt_prelog();			\
-		__status = efi_call##x(func, __VA_ARGS__);	\
-		efi_call_virt_epilog(__pgd);			\
-		__status;					\
-	})
-
 #define efi_call_virt0(f)				\
-	efi_callx(0, (void *)(efi.systab->runtime->f))
+	efi_call0((void *)(efi.systab->runtime->f))
 #define efi_call_virt1(f, a1)					\
-	efi_callx(1, (void *)(efi.systab->runtime->f), (u64)(a1))
+	efi_call1((void *)(efi.systab->runtime->f), (u64)(a1))
 #define efi_call_virt2(f, a1, a2)					\
-	efi_callx(2, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2))
+	efi_call2((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2))
 #define efi_call_virt3(f, a1, a2, a3)					\
-	efi_callx(3, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+	efi_call3((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3))
 #define efi_call_virt4(f, a1, a2, a3, a4)				\
-	efi_callx(4, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+	efi_call4((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4))
 #define efi_call_virt5(f, a1, a2, a3, a4, a5)				\
-	efi_callx(5, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+	efi_call5((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4), (u64)(a5))
 #define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)			\
-	efi_callx(6, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+	efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
 extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index d4f460f962ee..f84fe00fad48 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -103,13 +103,71 @@ void __init tboot_probe(void)
 	pr_debug("tboot_size: 0x%x\n", tboot->tboot_size);
 }
 
+static pgd_t *tboot_pg_dir;
+static struct mm_struct tboot_mm = {
+	.mm_rb          = RB_ROOT,
+	.pgd            = swapper_pg_dir,
+	.mm_users       = ATOMIC_INIT(2),
+	.mm_count       = ATOMIC_INIT(1),
+	.mmap_sem       = __RWSEM_INITIALIZER(init_mm.mmap_sem),
+	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
+	.mmlist         = LIST_HEAD_INIT(init_mm.mmlist),
+};
+
 static inline void switch_to_tboot_pt(void)
 {
-#ifdef CONFIG_X86_32
-	load_cr3(initial_page_table);
-#else
-	write_cr3(real_mode_header->trampoline_pgd);
-#endif
+	write_cr3(virt_to_phys(tboot_pg_dir));
+}
+
+static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
+			  pgprot_t prot)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_offset(&tboot_mm, vaddr);
+	pud = pud_alloc(&tboot_mm, pgd, vaddr);
+	if (!pud)
+		return -1;
+	pmd = pmd_alloc(&tboot_mm, pud, vaddr);
+	if (!pmd)
+		return -1;
+	pte = pte_alloc_map(&tboot_mm, NULL, pmd, vaddr);
+	if (!pte)
+		return -1;
+	set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot));
+	pte_unmap(pte);
+	return 0;
+}
+
+static int map_tboot_pages(unsigned long vaddr, unsigned long start_pfn,
+			   unsigned long nr)
+{
+	/* Reuse the original kernel mapping */
+	tboot_pg_dir = pgd_alloc(&tboot_mm);
+	if (!tboot_pg_dir)
+		return -1;
+
+	for (; nr > 0; nr--, vaddr += PAGE_SIZE, start_pfn++) {
+		if (map_tboot_page(vaddr, start_pfn, PAGE_KERNEL_EXEC))
+			return -1;
+	}
+
+	return 0;
+}
+
+static void tboot_create_trampoline(void)
+{
+	u32 map_base, map_size;
+
+	/* Create identity map for tboot shutdown code. */
+	map_base = PFN_DOWN(tboot->tboot_base);
+	map_size = PFN_UP(tboot->tboot_size);
+	if (map_tboot_pages(map_base << PAGE_SHIFT, map_base, map_size))
+		panic("tboot: Error mapping tboot pages (mfns) @ 0x%x, 0x%x\n",
+		      map_base, map_size);
 }
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -167,6 +225,14 @@ void tboot_shutdown(u32 shutdown_type)
 	if (!tboot_enabled())
 		return;
 
+	/*
+	 * if we're being called before the 1:1 mapping is set up then just
+	 * return and let the normal shutdown happen; this should only be
+	 * due to very early panic()
+	 */
+	if (!tboot_pg_dir)
+		return;
+
 	/* if this is S3 then set regions to MAC */
 	if (shutdown_type == TB_SHUTDOWN_S3)
 		if (tboot_setup_sleep())
@@ -277,6 +343,8 @@ static __init int tboot_late_init(void)
 	if (!tboot_enabled())
 		return 0;
 
+	tboot_create_trampoline();
+
 	atomic_set(&ap_wfs_count, 0);
 	register_hotcpu_notifier(&tboot_cpu_notifier);
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 931930a96160..a718e0d23503 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -919,13 +919,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	/*
 	 * On success we use clflush, when the CPU supports it to
-	 * avoid the wbindv. If the CPU does not support it, in the
-	 * error case, and during early boot (for EFI) we fall back
-	 * to cpa_flush_all (which uses wbinvd):
+	 * avoid the wbindv. If the CPU does not support it and in the
+	 * error case we fall back to cpa_flush_all (which uses
+	 * wbindv):
 	 */
-	if (early_boot_irqs_disabled)
-		__cpa_flush_all((void *)(long)cache);
-	else if (!ret && cpu_has_clflush) {
+	if (!ret && cpu_has_clflush) {
 		if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
 			cpa_flush_array(addr, numpages, cache,
 					cpa.flags, pages);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 0a34d9e9c263..ad4439145f85 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -239,7 +239,22 @@ static efi_status_t __init phys_efi_set_virtual_address_map(
 	return status;
 }
 
-static int efi_set_rtc_mmss(unsigned long nowtime)
+static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
+					     efi_time_cap_t *tc)
+{
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	efi_call_phys_prelog();
+	status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm),
+				virt_to_phys(tc));
+	efi_call_phys_epilog();
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
+}
+
+int efi_set_rtc_mmss(unsigned long nowtime)
 {
 	int real_seconds, real_minutes;
 	efi_status_t 	status;
@@ -268,7 +283,7 @@ static int efi_set_rtc_mmss(unsigned long nowtime)
 	return 0;
 }
 
-static unsigned long efi_get_time(void)
+unsigned long efi_get_time(void)
 {
 	efi_status_t status;
 	efi_time_t eft;
@@ -624,13 +639,18 @@ static int __init efi_runtime_init(void)
 	}
 	/*
 	 * We will only need *early* access to the following
-	 * EFI runtime service before set_virtual_address_map
+	 * two EFI runtime services before set_virtual_address_map
 	 * is invoked.
 	 */
+	efi_phys.get_time = (efi_get_time_t *)runtime->get_time;
 	efi_phys.set_virtual_address_map =
 		(efi_set_virtual_address_map_t *)
 		runtime->set_virtual_address_map;
-
+	/*
+	 * Make efi_get_time can be called before entering
+	 * virtual mode.
+	 */
+	efi.get_time = phys_efi_get_time;
 	early_iounmap(runtime, sizeof(efi_runtime_services_t));
 
 	return 0;
@@ -716,10 +736,12 @@ void __init efi_init(void)
 		efi_enabled = 0;
 		return;
 	}
+#ifdef CONFIG_X86_32
 	if (efi_is_native()) {
 		x86_platform.get_wallclock = efi_get_time;
 		x86_platform.set_wallclock = efi_set_rtc_mmss;
 	}
+#endif
 
 #if EFI_DEBUG
 	print_efi_memmap();
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 06c8b2e662ab..95fd505dfeb6 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -58,21 +58,6 @@ static void __init early_code_mapping_set_exec(int executable)
 	}
 }
 
-unsigned long efi_call_virt_prelog(void)
-{
-	unsigned long saved;
-
-	saved = read_cr3();
-	write_cr3(real_mode_header->trampoline_pgd);
-
-	return saved;
-}
-
-void efi_call_virt_epilog(unsigned long saved)
-{
-	write_cr3(saved);
-}
-
 void __init efi_call_phys_prelog(void)
 {
 	unsigned long vaddress;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 02a69418be18..8b84916dc671 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -587,6 +587,8 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size);
 extern int __init efi_uart_console_only (void);
 extern void efi_initialize_iomem_resources(struct resource *code_resource,
 		struct resource *data_resource, struct resource *bss_resource);
+extern unsigned long efi_get_time(void);
+extern int efi_set_rtc_mmss(unsigned long nowtime);
 extern void efi_reserve_boot_services(void);
 extern struct efi_memory_map memmap;
 
diff --git a/init/main.c b/init/main.c
index 6af5470b8067..63ae904a99a8 100644
--- a/init/main.c
+++ b/init/main.c
@@ -463,10 +463,6 @@ static void __init mm_init(void)
 	percpu_init_late();
 	pgtable_cache_init();
 	vmalloc_init();
-#ifdef CONFIG_X86
-	if (efi_enabled)
-		efi_enter_virtual_mode();
-#endif
 }
 
 asmlinkage void __init start_kernel(void)
@@ -607,6 +603,10 @@ asmlinkage void __init start_kernel(void)
 	calibrate_delay();
 	pidmap_init();
 	anon_vma_init();
+#ifdef CONFIG_X86
+	if (efi_enabled)
+		efi_enter_virtual_mode();
+#endif
 	thread_info_cache_init();
 	cred_init();
 	fork_init(totalram_pages);
-- 
cgit v1.2.3-55-g7522


From ccb1c31a7a8744cd153a7d92b726a56b56ad61d3 Mon Sep 17 00:00:00 2001
From: Amerigo Wang
Date: Fri, 14 Dec 2012 22:09:51 +0000
Subject: bridge: add flags to distinguish permanent mdb entires

This patch adds a flag to each mdb entry, so that we can distinguish
permanent entries with temporary entries.

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h | 3 +++
 net/bridge/br_mdb.c            | 9 ++++++---
 net/bridge/br_multicast.c      | 8 +++++---
 net/bridge/br_private.h        | 4 +++-
 4 files changed, 17 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index afbb18a0227c..5db297514aec 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -163,6 +163,9 @@ struct br_port_msg {
 
 struct br_mdb_entry {
 	__u32 ifindex;
+#define MDB_TEMPORARY 0
+#define MDB_PERMANENT 1
+	__u8 state;
 	struct {
 		union {
 			__be32	ip4;
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 6f0a2eebcb27..9cf5d2b28c76 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -83,6 +83,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 				if (port) {
 					struct br_mdb_entry e;
 					e.ifindex = port->dev->ifindex;
+					e.state = p->state;
 					e.addr.u.ip4 = p->addr.u.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
 					e.addr.u.ip6 = p->addr.u.ip6;
@@ -253,6 +254,8 @@ static bool is_valid_mdb_entry(struct br_mdb_entry *entry)
 #endif
 	} else
 		return false;
+	if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY)
+		return false;
 
 	return true;
 }
@@ -310,7 +313,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
 }
 
 static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
-			    struct br_ip *group)
+			    struct br_ip *group, unsigned char state)
 {
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
@@ -336,7 +339,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 			break;
 	}
 
-	p = br_multicast_new_port_group(port, group, *pp);
+	p = br_multicast_new_port_group(port, group, *pp, state);
 	if (unlikely(!p))
 		return -ENOMEM;
 	rcu_assign_pointer(*pp, p);
@@ -373,7 +376,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
 #endif
 
 	spin_lock_bh(&br->multicast_lock);
-	ret = br_mdb_add_group(br, p, &ip);
+	ret = br_mdb_add_group(br, p, &ip, entry->state);
 	spin_unlock_bh(&br->multicast_lock);
 	return ret;
 }
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 2561af9d18a2..dce9defae3c6 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -279,7 +279,7 @@ static void br_multicast_port_group_expired(unsigned long data)
 
 	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) || timer_pending(&pg->timer) ||
-	    hlist_unhashed(&pg->mglist))
+	    hlist_unhashed(&pg->mglist) || pg->state & MDB_PERMANENT)
 		goto out;
 
 	br_multicast_del_pg(br, pg);
@@ -622,7 +622,8 @@ out:
 struct net_bridge_port_group *br_multicast_new_port_group(
 			struct net_bridge_port *port,
 			struct br_ip *group,
-			struct net_bridge_port_group __rcu *next)
+			struct net_bridge_port_group __rcu *next,
+			unsigned char state)
 {
 	struct net_bridge_port_group *p;
 
@@ -632,6 +633,7 @@ struct net_bridge_port_group *br_multicast_new_port_group(
 
 	p->addr = *group;
 	p->port = port;
+	p->state = state;
 	rcu_assign_pointer(p->next, next);
 	hlist_add_head(&p->mglist, &port->mglist);
 	setup_timer(&p->timer, br_multicast_port_group_expired,
@@ -674,7 +676,7 @@ static int br_multicast_add_group(struct net_bridge *br,
 			break;
 	}
 
-	p = br_multicast_new_port_group(port, group, *pp);
+	p = br_multicast_new_port_group(port, group, *pp, MDB_TEMPORARY);
 	if (unlikely(!p))
 		goto err;
 	rcu_assign_pointer(*pp, p);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index f21a739a6186..49b85af44016 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -83,6 +83,7 @@ struct net_bridge_port_group {
 	struct rcu_head			rcu;
 	struct timer_list		timer;
 	struct br_ip			addr;
+	unsigned char			state;
 };
 
 struct net_bridge_mdb_entry
@@ -443,7 +444,8 @@ extern void br_multicast_free_pg(struct rcu_head *head);
 extern struct net_bridge_port_group *br_multicast_new_port_group(
 				struct net_bridge_port *port,
 				struct br_ip *group,
-				struct net_bridge_port_group *next);
+				struct net_bridge_port_group *next,
+				unsigned char state);
 extern void br_mdb_init(void);
 extern void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
 			  struct br_ip *group, int type);
-- 
cgit v1.2.3-55-g7522


From 252b3e8c1bc0c2b20348ae87d67efcd0a8209f72 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Tue, 11 Dec 2012 04:07:42 +0000
Subject: netfilter: xt_CT: fix crash while destroy ct templates

In (d871bef netfilter: ctnetlink: dump entries from the dying and
unconfirmed lists), we assume that all conntrack objects are
inserted in any of the existing lists. However, template conntrack
objects were not. This results in hitting BUG_ON in the
destroy_conntrack path while removing a rule that uses the CT target.

This patch fixes the situation by adding the template lists, which
is where template conntrack objects reside now.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netns/conntrack.h     | 1 +
 net/netfilter/nf_conntrack_core.c | 2 ++
 net/netfilter/xt_CT.c             | 8 ++++++++
 3 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index a1d83cc8bf85..923cb20051ed 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -71,6 +71,7 @@ struct netns_ct {
 	struct hlist_head	*expect_hash;
 	struct hlist_nulls_head	unconfirmed;
 	struct hlist_nulls_head	dying;
+	struct hlist_nulls_head tmpl;
 	struct ip_conntrack_stat __percpu *stat;
 	struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
 	struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 08cdc71d8e87..016d95ead930 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1526,6 +1526,7 @@ err_extend:
  */
 #define UNCONFIRMED_NULLS_VAL	((1<<30)+0)
 #define DYING_NULLS_VAL		((1<<30)+1)
+#define TEMPLATE_NULLS_VAL	((1<<30)+2)
 
 static int nf_conntrack_init_net(struct net *net)
 {
@@ -1534,6 +1535,7 @@ static int nf_conntrack_init_net(struct net *net)
 	atomic_set(&net->ct.count, 0);
 	INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL);
 	INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL);
+	INIT_HLIST_NULLS_HEAD(&net->ct.tmpl, TEMPLATE_NULLS_VAL);
 	net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
 	if (!net->ct.stat) {
 		ret = -ENOMEM;
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index ae7f5daeee43..1668f41acc6e 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -149,6 +149,10 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par)
 
 	__set_bit(IPS_TEMPLATE_BIT, &ct->status);
 	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
+
+	/* Overload tuple linked list to put us in template list. */
+	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+				 &par->net->ct.tmpl);
 out:
 	info->ct = ct;
 	return 0;
@@ -289,6 +293,10 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 
 	__set_bit(IPS_TEMPLATE_BIT, &ct->status);
 	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
+
+	/* Overload tuple linked list to put us in template list. */
+	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+				 &par->net->ct.tmpl);
 out:
 	info->ct = ct;
 	return 0;
-- 
cgit v1.2.3-55-g7522


From fb57dc817c24d46b035320d871b7a3fcc778558d Mon Sep 17 00:00:00 2001
From: Liu Bo
Date: Fri, 30 Nov 2012 11:24:22 +0000
Subject: Btrfs: parse parent 0 into correct value in tracepoint

Value 0 is not a tree id, so besides an upper limit, a lower limit is
necessary as well while parsing root types of tracepoint.

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
---
 include/trace/events/btrfs.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 54fab041b22a..ea546a4e9609 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -45,7 +45,8 @@ struct extent_buffer;
 
 #define show_root_type(obj)						\
 	obj, ((obj >= BTRFS_DATA_RELOC_TREE_OBJECTID) ||		\
-	      (obj <= BTRFS_CSUM_TREE_OBJECTID )) ? __show_root_type(obj) : "-"
+	      (obj >= BTRFS_ROOT_TREE_OBJECTID &&			\
+	       obj <= BTRFS_CSUM_TREE_OBJECTID)) ? __show_root_type(obj) : "-"
 
 #define BTRFS_GROUP_FLAGS	\
 	{ BTRFS_BLOCK_GROUP_DATA,	"DATA"}, \
-- 
cgit v1.2.3-55-g7522


From b45305fce5bb1abec263fcff9d81ebecd6306ede Mon Sep 17 00:00:00 2001
From: Daniel Vetter
Date: Mon, 17 Dec 2012 16:21:27 +0100
Subject: drm/i915: Implement workaround for broken CS tlb on i830/845

Now that Chris Wilson demonstrated that the key for stability on early
gen 2 is to simple _never_ exchange the physical backing storage of
batch buffers I've tried a stab at a kernel solution. Doesn't look too
nefarious imho, now that I don't try to be too clever for my own good
any more.

v2: After discussing the various techniques, we've decided to always blit
batches on the suspect devices, but allow userspace to opt out of the
kernel workaround assume full responsibility for providing coherent
batches. The principal reason is that avoiding the blit does improve
performance in a few key microbenchmarks and also in cairo-trace
replays.

Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet:
- Drop the hunk which uses HAS_BROKEN_CS_TLB to implement the ring
  wrap w/a. Suggested by Chris Wilson.
- Also add the ACTHD check from Chris Wilson for the error state
  dumping, so that we still catch batches when userspace opts out of
  the w/a.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c            |  3 ++
 drivers/gpu/drm/i915/i915_drv.h            |  4 ++
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  2 +
 drivers/gpu/drm/i915/i915_irq.c            | 12 +++++
 drivers/gpu/drm/i915/intel_ringbuffer.c    | 76 ++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/intel_ringbuffer.h    |  1 +
 include/uapi/drm/i915_drm.h                | 10 ++++
 7 files changed, 100 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 8f63cd5de4b4..99daa896105d 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -989,6 +989,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_SECURE_BATCHES:
 		value = capable(CAP_SYS_ADMIN);
 		break;
+	case I915_PARAM_HAS_PINNED_BATCHES:
+		value = 1;
+		break;
 	default:
 		DRM_DEBUG_DRIVER("Unknown parameter %d\n",
 				 param->param);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 062a60b381b7..1a4c3a1c111f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1100,6 +1100,7 @@ struct drm_i915_gem_object {
 	 */
 	atomic_t pending_flip;
 };
+#define to_gem_object(obj) (&((struct drm_i915_gem_object *)(obj))->base)
 
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
@@ -1199,6 +1200,9 @@ struct drm_i915_file_private {
 #define HAS_OVERLAY(dev)		(INTEL_INFO(dev)->has_overlay)
 #define OVERLAY_NEEDS_PHYSICAL(dev)	(INTEL_INFO(dev)->overlay_needs_physical)
 
+/* Early gen2 have a totally busted CS tlb and require pinned batches. */
+#define HAS_BROKEN_CS_TLB(dev)		(IS_I830(dev) || IS_845G(dev))
+
 /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
  * rows, which changed the alignment requirements and fence programming.
  */
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index ee8f97f0539e..d6a994a07393 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -808,6 +808,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 		flags |= I915_DISPATCH_SECURE;
 	}
+	if (args->flags & I915_EXEC_IS_PINNED)
+		flags |= I915_DISPATCH_PINNED;
 
 	switch (args->flags & I915_EXEC_RING_MASK) {
 	case I915_EXEC_DEFAULT:
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index a4dc97f8b9f0..2220dec3e5d9 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1087,6 +1087,18 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 	if (!ring->get_seqno)
 		return NULL;
 
+	if (HAS_BROKEN_CS_TLB(dev_priv->dev)) {
+		u32 acthd = I915_READ(ACTHD);
+
+		if (WARN_ON(ring->id != RCS))
+			return NULL;
+
+		obj = ring->private;
+		if (acthd >= obj->gtt_offset &&
+		    acthd < obj->gtt_offset + obj->base.size)
+			return i915_error_object_create(dev_priv, obj);
+	}
+
 	seqno = ring->get_seqno(ring, false);
 	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
 		if (obj->ring != ring)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 2346b920bd86..ae253e04c391 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -547,9 +547,14 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 
 static void render_ring_cleanup(struct intel_ring_buffer *ring)
 {
+	struct drm_device *dev = ring->dev;
+
 	if (!ring->private)
 		return;
 
+	if (HAS_BROKEN_CS_TLB(dev))
+		drm_gem_object_unreference(to_gem_object(ring->private));
+
 	cleanup_pipe_control(ring);
 }
 
@@ -969,6 +974,8 @@ i965_dispatch_execbuffer(struct intel_ring_buffer *ring,
 	return 0;
 }
 
+/* Just userspace ABI convention to limit the wa batch bo to a resonable size */
+#define I830_BATCH_LIMIT (256*1024)
 static int
 i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 				u32 offset, u32 len,
@@ -976,15 +983,47 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 {
 	int ret;
 
-	ret = intel_ring_begin(ring, 4);
-	if (ret)
-		return ret;
+	if (flags & I915_DISPATCH_PINNED) {
+		ret = intel_ring_begin(ring, 4);
+		if (ret)
+			return ret;
 
-	intel_ring_emit(ring, MI_BATCH_BUFFER);
-	intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
-	intel_ring_emit(ring, offset + len - 8);
-	intel_ring_emit(ring, 0);
-	intel_ring_advance(ring);
+		intel_ring_emit(ring, MI_BATCH_BUFFER);
+		intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
+		intel_ring_emit(ring, offset + len - 8);
+		intel_ring_emit(ring, MI_NOOP);
+		intel_ring_advance(ring);
+	} else {
+		struct drm_i915_gem_object *obj = ring->private;
+		u32 cs_offset = obj->gtt_offset;
+
+		if (len > I830_BATCH_LIMIT)
+			return -ENOSPC;
+
+		ret = intel_ring_begin(ring, 9+3);
+		if (ret)
+			return ret;
+		/* Blit the batch (which has now all relocs applied) to the stable batch
+		 * scratch bo area (so that the CS never stumbles over its tlb
+		 * invalidation bug) ... */
+		intel_ring_emit(ring, XY_SRC_COPY_BLT_CMD |
+				XY_SRC_COPY_BLT_WRITE_ALPHA |
+				XY_SRC_COPY_BLT_WRITE_RGB);
+		intel_ring_emit(ring, BLT_DEPTH_32 | BLT_ROP_GXCOPY | 4096);
+		intel_ring_emit(ring, 0);
+		intel_ring_emit(ring, (DIV_ROUND_UP(len, 4096) << 16) | 1024);
+		intel_ring_emit(ring, cs_offset);
+		intel_ring_emit(ring, 0);
+		intel_ring_emit(ring, 4096);
+		intel_ring_emit(ring, offset);
+		intel_ring_emit(ring, MI_FLUSH);
+
+		/* ... and execute it. */
+		intel_ring_emit(ring, MI_BATCH_BUFFER);
+		intel_ring_emit(ring, cs_offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
+		intel_ring_emit(ring, cs_offset + len - 8);
+		intel_ring_advance(ring);
+	}
 
 	return 0;
 }
@@ -1596,6 +1635,27 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 	ring->init = init_render_ring;
 	ring->cleanup = render_ring_cleanup;
 
+	/* Workaround batchbuffer to combat CS tlb bug. */
+	if (HAS_BROKEN_CS_TLB(dev)) {
+		struct drm_i915_gem_object *obj;
+		int ret;
+
+		obj = i915_gem_alloc_object(dev, I830_BATCH_LIMIT);
+		if (obj == NULL) {
+			DRM_ERROR("Failed to allocate batch bo\n");
+			return -ENOMEM;
+		}
+
+		ret = i915_gem_object_pin(obj, 0, true, false);
+		if (ret != 0) {
+			drm_gem_object_unreference(&obj->base);
+			DRM_ERROR("Failed to ping batch bo\n");
+			return ret;
+		}
+
+		ring->private = obj;
+	}
+
 	return intel_init_ring_buffer(dev, ring);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 526182ed0c6d..6af87cd05725 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -94,6 +94,7 @@ struct  intel_ring_buffer {
 					       u32 offset, u32 length,
 					       unsigned flags);
 #define I915_DISPATCH_SECURE 0x1
+#define I915_DISPATCH_PINNED 0x2
 	void		(*cleanup)(struct intel_ring_buffer *ring);
 	int		(*sync_to)(struct intel_ring_buffer *ring,
 				   struct intel_ring_buffer *to,
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index b746a3cf5fa9..c4d2e9c74002 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -307,6 +307,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_PRIME_VMAP_FLUSH	 21
 #define I915_PARAM_RSVD_FOR_FUTURE_USE	 22
 #define I915_PARAM_HAS_SECURE_BATCHES	 23
+#define I915_PARAM_HAS_PINNED_BATCHES	 24
 
 typedef struct drm_i915_getparam {
 	int param;
@@ -677,6 +678,15 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_SECURE		(1<<9)
 
+/** Inform the kernel that the batch is and will always be pinned. This
+ * negates the requirement for a workaround to be performed to avoid
+ * an incoherent CS (such as can be found on 830/845). If this flag is
+ * not passed, the kernel will endeavour to make sure the batch is
+ * coherent with the CS before execution. If this flag is passed,
+ * userspace assumes the responsibility for ensuring the same.
+ */
+#define I915_EXEC_IS_PINNED		(1<<10)
+
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
 	(eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK
-- 
cgit v1.2.3-55-g7522


From 9360b53661a2c7754517b2925580055bacc8ec38 Mon Sep 17 00:00:00 2001
From: Linus Torvalds
Date: Mon, 17 Dec 2012 11:29:09 -0800
Subject: Revert "bdi: add a user-tunable cpu_list for the bdi flusher threads"

This reverts commit 8fa72d234da9b6b473bbb1f74d533663e4996e6b.

People disagree about how this should be done, so let's revert this for
now so that nobody starts using the new tuning interface.  Tejun is
thinking about a more generic interface for thread pool affinity.

Requested-by: Tejun Heo <tj@kernel.org>
Acked-by: Jeff Moyer <jmoyer@redhat.com>
Acked-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/backing-dev.h |  4 ---
 mm/backing-dev.c            | 84 ---------------------------------------------
 2 files changed, 88 deletions(-)

(limited to 'include')

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 238521a19849..2a9a9abc9126 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -18,7 +18,6 @@
 #include <linux/writeback.h>
 #include <linux/atomic.h>
 #include <linux/sysctl.h>
-#include <linux/mutex.h>
 
 struct page;
 struct device;
@@ -106,9 +105,6 @@ struct backing_dev_info {
 
 	struct timer_list laptop_mode_wb_timer;
 
-	cpumask_t *flusher_cpumask; /* used for writeback thread scheduling */
-	struct mutex flusher_cpumask_lock;
-
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debug_dir;
 	struct dentry *debug_stats;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index bd6a6cabef71..d3ca2b3ee176 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -10,7 +10,6 @@
 #include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/device.h>
-#include <linux/slab.h>
 #include <trace/events/writeback.h>
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
@@ -222,63 +221,12 @@ static ssize_t max_ratio_store(struct device *dev,
 }
 BDI_SHOW(max_ratio, bdi->max_ratio)
 
-static ssize_t cpu_list_store(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
-{
-	struct backing_dev_info *bdi = dev_get_drvdata(dev);
-	struct bdi_writeback *wb = &bdi->wb;
-	cpumask_var_t newmask;
-	ssize_t ret;
-	struct task_struct *task;
-
-	if (!alloc_cpumask_var(&newmask, GFP_KERNEL))
-		return -ENOMEM;
-
-	ret = cpulist_parse(buf, newmask);
-	if (!ret) {
-		spin_lock_bh(&bdi->wb_lock);
-		task = wb->task;
-		if (task)
-			get_task_struct(task);
-		spin_unlock_bh(&bdi->wb_lock);
-
-		mutex_lock(&bdi->flusher_cpumask_lock);
-		if (task) {
-			ret = set_cpus_allowed_ptr(task, newmask);
-			put_task_struct(task);
-		}
-		if (ret == 0) {
-			cpumask_copy(bdi->flusher_cpumask, newmask);
-			ret = count;
-		}
-		mutex_unlock(&bdi->flusher_cpumask_lock);
-
-	}
-	free_cpumask_var(newmask);
-
-	return ret;
-}
-
-static ssize_t cpu_list_show(struct device *dev,
-		struct device_attribute *attr, char *page)
-{
-	struct backing_dev_info *bdi = dev_get_drvdata(dev);
-	ssize_t ret;
-
-	mutex_lock(&bdi->flusher_cpumask_lock);
-	ret = cpulist_scnprintf(page, PAGE_SIZE-1, bdi->flusher_cpumask);
-	mutex_unlock(&bdi->flusher_cpumask_lock);
-
-	return ret;
-}
-
 #define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
 
 static struct device_attribute bdi_dev_attrs[] = {
 	__ATTR_RW(read_ahead_kb),
 	__ATTR_RW(min_ratio),
 	__ATTR_RW(max_ratio),
-	__ATTR_RW(cpu_list),
 	__ATTR_NULL,
 };
 
@@ -480,7 +428,6 @@ static int bdi_forker_thread(void *ptr)
 				writeback_inodes_wb(&bdi->wb, 1024,
 						    WB_REASON_FORKER_THREAD);
 			} else {
-				int ret;
 				/*
 				 * The spinlock makes sure we do not lose
 				 * wake-ups when racing with 'bdi_queue_work()'.
@@ -490,14 +437,6 @@ static int bdi_forker_thread(void *ptr)
 				spin_lock_bh(&bdi->wb_lock);
 				bdi->wb.task = task;
 				spin_unlock_bh(&bdi->wb_lock);
-				mutex_lock(&bdi->flusher_cpumask_lock);
-				ret = set_cpus_allowed_ptr(task,
-							bdi->flusher_cpumask);
-				mutex_unlock(&bdi->flusher_cpumask_lock);
-				if (ret)
-					printk_once("%s: failed to bind flusher"
-						    " thread %s, error %d\n",
-						    __func__, task->comm, ret);
 				wake_up_process(task);
 			}
 			bdi_clear_pending(bdi);
@@ -570,17 +509,6 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 						dev_name(dev));
 		if (IS_ERR(wb->task))
 			return PTR_ERR(wb->task);
-	} else {
-		int node;
-		/*
-		 * Set up a default cpumask for the flusher threads that
-		 * includes all cpus on the same numa node as the device.
-		 * The mask may be overridden via sysfs.
-		 */
-		node = dev_to_node(bdi->dev);
-		if (node != NUMA_NO_NODE)
-			cpumask_copy(bdi->flusher_cpumask,
-				     cpumask_of_node(node));
 	}
 
 	bdi_debug_register(bdi, dev_name(dev));
@@ -706,15 +634,6 @@ int bdi_init(struct backing_dev_info *bdi)
 
 	bdi_wb_init(&bdi->wb, bdi);
 
-	if (!bdi_cap_flush_forker(bdi)) {
-		bdi->flusher_cpumask = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
-		if (!bdi->flusher_cpumask)
-			return -ENOMEM;
-		cpumask_setall(bdi->flusher_cpumask);
-		mutex_init(&bdi->flusher_cpumask_lock);
-	} else
-		bdi->flusher_cpumask = NULL;
-
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
 		err = percpu_counter_init(&bdi->bdi_stat[i], 0);
 		if (err)
@@ -737,7 +656,6 @@ int bdi_init(struct backing_dev_info *bdi)
 err:
 		while (i--)
 			percpu_counter_destroy(&bdi->bdi_stat[i]);
-		kfree(bdi->flusher_cpumask);
 	}
 
 	return err;
@@ -765,8 +683,6 @@ void bdi_destroy(struct backing_dev_info *bdi)
 
 	bdi_unregister(bdi);
 
-	kfree(bdi->flusher_cpumask);
-
 	/*
 	 * If bdi_unregister() had already been called earlier, the
 	 * wakeup_timer could still be armed because bdi_prune_sb()
-- 
cgit v1.2.3-55-g7522


From 7929d407e47fbf843fe1337fd95ed57785ae5e9d Mon Sep 17 00:00:00 2001
From: Matthew Leach
Date: Mon, 17 Dec 2012 15:59:32 -0800
Subject: include/linux/init.h: use the stringify operator for the
 __define_initcall macro

Currently the __define_initcall() macro takes three arguments, fn, id and
level.  The level argument is exactly the same as the id argument but
wrapped in quotes.  To overcome this need to specify three arguments to
the __define_initcall macro, where one argument is the stringification of
another, we can just use the stringification macro instead.

Signed-off-by: Matthew Leach <matthew@mattleach.net>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/include/asm/machdep.h | 36 +++++++++++++++++-----------------
 include/linux/init.h               | 40 +++++++++++++++++++-------------------
 2 files changed, 38 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index c4231973edd3..3c82daf8be99 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -320,28 +320,28 @@ static inline void log_error(char *buf, unsigned int err_type, int fatal)
 		ppc_md.log_error(buf, err_type, fatal);
 }
 
-#define __define_machine_initcall(mach,level,fn,id) \
+#define __define_machine_initcall(mach, fn, id) \
 	static int __init __machine_initcall_##mach##_##fn(void) { \
 		if (machine_is(mach)) return fn(); \
 		return 0; \
 	} \
-	__define_initcall(level,__machine_initcall_##mach##_##fn,id);
-
-#define machine_core_initcall(mach,fn)		__define_machine_initcall(mach,"1",fn,1)
-#define machine_core_initcall_sync(mach,fn)	__define_machine_initcall(mach,"1s",fn,1s)
-#define machine_postcore_initcall(mach,fn)	__define_machine_initcall(mach,"2",fn,2)
-#define machine_postcore_initcall_sync(mach,fn)	__define_machine_initcall(mach,"2s",fn,2s)
-#define machine_arch_initcall(mach,fn)		__define_machine_initcall(mach,"3",fn,3)
-#define machine_arch_initcall_sync(mach,fn)	__define_machine_initcall(mach,"3s",fn,3s)
-#define machine_subsys_initcall(mach,fn)	__define_machine_initcall(mach,"4",fn,4)
-#define machine_subsys_initcall_sync(mach,fn)	__define_machine_initcall(mach,"4s",fn,4s)
-#define machine_fs_initcall(mach,fn)		__define_machine_initcall(mach,"5",fn,5)
-#define machine_fs_initcall_sync(mach,fn)	__define_machine_initcall(mach,"5s",fn,5s)
-#define machine_rootfs_initcall(mach,fn)	__define_machine_initcall(mach,"rootfs",fn,rootfs)
-#define machine_device_initcall(mach,fn)	__define_machine_initcall(mach,"6",fn,6)
-#define machine_device_initcall_sync(mach,fn)	__define_machine_initcall(mach,"6s",fn,6s)
-#define machine_late_initcall(mach,fn)		__define_machine_initcall(mach,"7",fn,7)
-#define machine_late_initcall_sync(mach,fn)	__define_machine_initcall(mach,"7s",fn,7s)
+	__define_initcall(__machine_initcall_##mach##_##fn, id);
+
+#define machine_core_initcall(mach, fn)		__define_machine_initcall(mach, fn, 1)
+#define machine_core_initcall_sync(mach, fn)	__define_machine_initcall(mach, fn, 1s)
+#define machine_postcore_initcall(mach, fn)	__define_machine_initcall(mach, fn, 2)
+#define machine_postcore_initcall_sync(mach, fn)	__define_machine_initcall(mach, fn, 2s)
+#define machine_arch_initcall(mach, fn)		__define_machine_initcall(mach, fn, 3)
+#define machine_arch_initcall_sync(mach, fn)	__define_machine_initcall(mach, fn, 3s)
+#define machine_subsys_initcall(mach, fn)	__define_machine_initcall(mach, fn, 4)
+#define machine_subsys_initcall_sync(mach, fn)	__define_machine_initcall(mach, fn, 4s)
+#define machine_fs_initcall(mach, fn)		__define_machine_initcall(mach, fn, 5)
+#define machine_fs_initcall_sync(mach, fn)	__define_machine_initcall(mach, fn, 5s)
+#define machine_rootfs_initcall(mach, fn)	__define_machine_initcall(mach, fn, rootfs)
+#define machine_device_initcall(mach, fn)	__define_machine_initcall(mach, fn, 6)
+#define machine_device_initcall_sync(mach, fn)	__define_machine_initcall(mach, fn, 6s)
+#define machine_late_initcall(mach, fn)		__define_machine_initcall(mach, fn, 7)
+#define machine_late_initcall_sync(mach, fn)	__define_machine_initcall(mach, fn, 7s)
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_MACHDEP_H */
diff --git a/include/linux/init.h b/include/linux/init.h
index f63692d6902e..a799273714ac 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -182,16 +182,16 @@ extern bool initcall_debug;
  * can point at the same handler without causing duplicate-symbol build errors.
  */
 
-#define __define_initcall(level,fn,id) \
+#define __define_initcall(fn, id) \
 	static initcall_t __initcall_##fn##id __used \
-	__attribute__((__section__(".initcall" level ".init"))) = fn
+	__attribute__((__section__(".initcall" #id ".init"))) = fn
 
 /*
  * Early initcalls run before initializing SMP.
  *
  * Only for built-in code, not modules.
  */
-#define early_initcall(fn)		__define_initcall("early",fn,early)
+#define early_initcall(fn)		__define_initcall(fn, early)
 
 /*
  * A "pure" initcall has no dependencies on anything else, and purely
@@ -200,23 +200,23 @@ extern bool initcall_debug;
  * This only exists for built-in code, not for modules.
  * Keep main.c:initcall_level_names[] in sync.
  */
-#define pure_initcall(fn)		__define_initcall("0",fn,0)
-
-#define core_initcall(fn)		__define_initcall("1",fn,1)
-#define core_initcall_sync(fn)		__define_initcall("1s",fn,1s)
-#define postcore_initcall(fn)		__define_initcall("2",fn,2)
-#define postcore_initcall_sync(fn)	__define_initcall("2s",fn,2s)
-#define arch_initcall(fn)		__define_initcall("3",fn,3)
-#define arch_initcall_sync(fn)		__define_initcall("3s",fn,3s)
-#define subsys_initcall(fn)		__define_initcall("4",fn,4)
-#define subsys_initcall_sync(fn)	__define_initcall("4s",fn,4s)
-#define fs_initcall(fn)			__define_initcall("5",fn,5)
-#define fs_initcall_sync(fn)		__define_initcall("5s",fn,5s)
-#define rootfs_initcall(fn)		__define_initcall("rootfs",fn,rootfs)
-#define device_initcall(fn)		__define_initcall("6",fn,6)
-#define device_initcall_sync(fn)	__define_initcall("6s",fn,6s)
-#define late_initcall(fn)		__define_initcall("7",fn,7)
-#define late_initcall_sync(fn)		__define_initcall("7s",fn,7s)
+#define pure_initcall(fn)		__define_initcall(fn, 0)
+
+#define core_initcall(fn)		__define_initcall(fn, 1)
+#define core_initcall_sync(fn)		__define_initcall(fn, 1s)
+#define postcore_initcall(fn)		__define_initcall(fn, 2)
+#define postcore_initcall_sync(fn)	__define_initcall(fn, 2s)
+#define arch_initcall(fn)		__define_initcall(fn, 3)
+#define arch_initcall_sync(fn)		__define_initcall(fn, 3s)
+#define subsys_initcall(fn)		__define_initcall(fn, 4)
+#define subsys_initcall_sync(fn)	__define_initcall(fn, 4s)
+#define fs_initcall(fn)			__define_initcall(fn, 5)
+#define fs_initcall_sync(fn)		__define_initcall(fn, 5s)
+#define rootfs_initcall(fn)		__define_initcall(fn, rootfs)
+#define device_initcall(fn)		__define_initcall(fn, 6)
+#define device_initcall_sync(fn)	__define_initcall(fn, 6s)
+#define late_initcall(fn)		__define_initcall(fn, 7)
+#define late_initcall_sync(fn)		__define_initcall(fn, 7s)
 
 #define __initcall(fn) device_initcall(fn)
 
-- 
cgit v1.2.3-55-g7522


From 965c8e59cfcf845ecde2265a1d1bfee5f011d302 Mon Sep 17 00:00:00 2001
From: Andrew Morton
Date: Mon, 17 Dec 2012 15:59:39 -0800
Subject: lseek: the "whence" argument is called "whence"

But the kernel decided to call it "origin" instead.  Fix most of the
sites.

Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/bad_inode.c           |  2 +-
 fs/block_dev.c           |  4 ++--
 fs/btrfs/file.c          | 16 ++++++++--------
 fs/ceph/dir.c            |  4 ++--
 fs/ceph/file.c           |  6 +++---
 fs/cifs/cifsfs.c         |  8 ++++----
 fs/configfs/dir.c        |  4 ++--
 fs/ext3/dir.c            |  6 +++---
 fs/ext4/dir.c            |  6 +++---
 fs/ext4/file.c           | 22 +++++++++++-----------
 fs/fuse/file.c           |  8 ++++----
 fs/gfs2/file.c           | 10 +++++-----
 fs/libfs.c               |  4 ++--
 fs/nfs/dir.c             |  6 +++---
 fs/nfs/file.c            | 10 +++++-----
 fs/ocfs2/extent_map.c    | 12 ++++++------
 fs/ocfs2/file.c          |  6 +++---
 fs/pstore/inode.c        |  6 +++---
 fs/read_write.c          | 40 ++++++++++++++++++++--------------------
 fs/seq_file.c            |  4 ++--
 fs/ubifs/dir.c           |  4 ++--
 include/linux/fs.h       | 12 ++++++------
 include/linux/ftrace.h   |  4 ++--
 include/linux/syscalls.h |  4 ++--
 kernel/trace/ftrace.c    |  4 ++--
 mm/shmem.c               | 20 ++++++++++----------
 26 files changed, 116 insertions(+), 116 deletions(-)

(limited to 'include')

diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index b1342ffb3cf6..922ad460bff9 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -16,7 +16,7 @@
 #include <linux/poll.h>
 
 
-static loff_t bad_file_llseek(struct file *file, loff_t offset, int origin)
+static loff_t bad_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	return -EIO;
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index ab3a456f6650..172f8491a2bd 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -321,7 +321,7 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping,
  * for a block special file file->f_path.dentry->d_inode->i_size is zero
  * so we compute the size by hand (just as in block_read/write above)
  */
-static loff_t block_llseek(struct file *file, loff_t offset, int origin)
+static loff_t block_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *bd_inode = file->f_mapping->host;
 	loff_t size;
@@ -331,7 +331,7 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin)
 	size = i_size_read(bd_inode);
 
 	retval = -EINVAL;
-	switch (origin) {
+	switch (whence) {
 		case SEEK_END:
 			offset += size;
 			break;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a8ee75cb96ee..9c6673a9231f 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2120,7 +2120,7 @@ out:
 	return ret;
 }
 
-static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
+static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct extent_map *em;
@@ -2154,7 +2154,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
 	 * before the position we want in case there is outstanding delalloc
 	 * going on here.
 	 */
-	if (origin == SEEK_HOLE && start != 0) {
+	if (whence == SEEK_HOLE && start != 0) {
 		if (start <= root->sectorsize)
 			em = btrfs_get_extent_fiemap(inode, NULL, 0, 0,
 						     root->sectorsize, 0);
@@ -2188,13 +2188,13 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
 				}
 			}
 
-			if (origin == SEEK_HOLE) {
+			if (whence == SEEK_HOLE) {
 				*offset = start;
 				free_extent_map(em);
 				break;
 			}
 		} else {
-			if (origin == SEEK_DATA) {
+			if (whence == SEEK_DATA) {
 				if (em->block_start == EXTENT_MAP_DELALLOC) {
 					if (start >= inode->i_size) {
 						free_extent_map(em);
@@ -2231,16 +2231,16 @@ out:
 	return ret;
 }
 
-static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
+static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	int ret;
 
 	mutex_lock(&inode->i_mutex);
-	switch (origin) {
+	switch (whence) {
 	case SEEK_END:
 	case SEEK_CUR:
-		offset = generic_file_llseek(file, offset, origin);
+		offset = generic_file_llseek(file, offset, whence);
 		goto out;
 	case SEEK_DATA:
 	case SEEK_HOLE:
@@ -2249,7 +2249,7 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
 			return -ENXIO;
 		}
 
-		ret = find_desired_extent(inode, &offset, origin);
+		ret = find_desired_extent(inode, &offset, whence);
 		if (ret) {
 			mutex_unlock(&inode->i_mutex);
 			return ret;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index e5b77319c97b..8c1aabe93b67 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -454,7 +454,7 @@ static void reset_readdir(struct ceph_file_info *fi)
 	fi->flags &= ~CEPH_F_ATEND;
 }
 
-static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int origin)
+static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct ceph_file_info *fi = file->private_data;
 	struct inode *inode = file->f_mapping->host;
@@ -463,7 +463,7 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int origin)
 
 	mutex_lock(&inode->i_mutex);
 	retval = -EINVAL;
-	switch (origin) {
+	switch (whence) {
 	case SEEK_END:
 		offset += inode->i_size + 2;   /* FIXME */
 		break;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 5840d2aaed15..d4dfdcf76d7f 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -797,7 +797,7 @@ out:
 /*
  * llseek.  be sure to verify file size on SEEK_END.
  */
-static loff_t ceph_llseek(struct file *file, loff_t offset, int origin)
+static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	int ret;
@@ -805,7 +805,7 @@ static loff_t ceph_llseek(struct file *file, loff_t offset, int origin)
 	mutex_lock(&inode->i_mutex);
 	__ceph_do_pending_vmtruncate(inode);
 
-	if (origin == SEEK_END || origin == SEEK_DATA || origin == SEEK_HOLE) {
+	if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
 		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
 		if (ret < 0) {
 			offset = ret;
@@ -813,7 +813,7 @@ static loff_t ceph_llseek(struct file *file, loff_t offset, int origin)
 		}
 	}
 
-	switch (origin) {
+	switch (whence) {
 	case SEEK_END:
 		offset += inode->i_size;
 		break;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 210f0af83fc4..ce9f3c5421bf 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -695,13 +695,13 @@ static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	return written;
 }
 
-static loff_t cifs_llseek(struct file *file, loff_t offset, int origin)
+static loff_t cifs_llseek(struct file *file, loff_t offset, int whence)
 {
 	/*
-	 * origin == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate
+	 * whence == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate
 	 * the cached file length
 	 */
-	if (origin != SEEK_SET && origin != SEEK_CUR) {
+	if (whence != SEEK_SET && whence != SEEK_CUR) {
 		int rc;
 		struct inode *inode = file->f_path.dentry->d_inode;
 
@@ -728,7 +728,7 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int origin)
 		if (rc < 0)
 			return (loff_t)rc;
 	}
-	return generic_file_llseek(file, offset, origin);
+	return generic_file_llseek(file, offset, whence);
 }
 
 static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 7414ae24a79b..712b10f64c70 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1613,12 +1613,12 @@ static int configfs_readdir(struct file * filp, void * dirent, filldir_t filldir
 	return 0;
 }
 
-static loff_t configfs_dir_lseek(struct file * file, loff_t offset, int origin)
+static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
 {
 	struct dentry * dentry = file->f_path.dentry;
 
 	mutex_lock(&dentry->d_inode->i_mutex);
-	switch (origin) {
+	switch (whence) {
 		case 1:
 			offset += file->f_pos;
 		case 0:
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index c8fff930790d..dd91264ba94f 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -296,17 +296,17 @@ static inline loff_t ext3_get_htree_eof(struct file *filp)
  * NOTE: offsets obtained *before* ext3_set_inode_flag(dir, EXT3_INODE_INDEX)
  *       will be invalid once the directory was converted into a dx directory
  */
-loff_t ext3_dir_llseek(struct file *file, loff_t offset, int origin)
+loff_t ext3_dir_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	int dx_dir = is_dx_dir(inode);
 	loff_t htree_max = ext3_get_htree_eof(file);
 
 	if (likely(dx_dir))
-		return generic_file_llseek_size(file, offset, origin,
+		return generic_file_llseek_size(file, offset, whence,
 					        htree_max, htree_max);
 	else
-		return generic_file_llseek(file, offset, origin);
+		return generic_file_llseek(file, offset, whence);
 }
 
 /*
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index b8d877f6c1fa..80a28b297279 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -333,17 +333,17 @@ static inline loff_t ext4_get_htree_eof(struct file *filp)
  *
  * For non-htree, ext4_llseek already chooses the proper max offset.
  */
-loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin)
+loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	int dx_dir = is_dx_dir(inode);
 	loff_t htree_max = ext4_get_htree_eof(file);
 
 	if (likely(dx_dir))
-		return generic_file_llseek_size(file, offset, origin,
+		return generic_file_llseek_size(file, offset, whence,
 						    htree_max, htree_max);
 	else
-		return ext4_llseek(file, offset, origin);
+		return ext4_llseek(file, offset, whence);
 }
 
 /*
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index b64a60bf105a..d07c27ca594a 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -303,7 +303,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
  * page cache has data or not.
  */
 static int ext4_find_unwritten_pgoff(struct inode *inode,
-				     int origin,
+				     int whence,
 				     struct ext4_map_blocks *map,
 				     loff_t *offset)
 {
@@ -333,10 +333,10 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  (pgoff_t)num);
 		if (nr_pages == 0) {
-			if (origin == SEEK_DATA)
+			if (whence == SEEK_DATA)
 				break;
 
-			BUG_ON(origin != SEEK_HOLE);
+			BUG_ON(whence != SEEK_HOLE);
 			/*
 			 * If this is the first time to go into the loop and
 			 * offset is not beyond the end offset, it will be a
@@ -352,7 +352,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 		 * offset is smaller than the first page offset, it will be a
 		 * hole at this offset.
 		 */
-		if (lastoff == startoff && origin == SEEK_HOLE &&
+		if (lastoff == startoff && whence == SEEK_HOLE &&
 		    lastoff < page_offset(pvec.pages[0])) {
 			found = 1;
 			break;
@@ -366,7 +366,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 			 * If the current offset is not beyond the end of given
 			 * range, it will be a hole.
 			 */
-			if (lastoff < endoff && origin == SEEK_HOLE &&
+			if (lastoff < endoff && whence == SEEK_HOLE &&
 			    page->index > end) {
 				found = 1;
 				*offset = lastoff;
@@ -391,10 +391,10 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 				do {
 					if (buffer_uptodate(bh) ||
 					    buffer_unwritten(bh)) {
-						if (origin == SEEK_DATA)
+						if (whence == SEEK_DATA)
 							found = 1;
 					} else {
-						if (origin == SEEK_HOLE)
+						if (whence == SEEK_HOLE)
 							found = 1;
 					}
 					if (found) {
@@ -416,7 +416,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 		 * The no. of pages is less than our desired, that would be a
 		 * hole in there.
 		 */
-		if (nr_pages < num && origin == SEEK_HOLE) {
+		if (nr_pages < num && whence == SEEK_HOLE) {
 			found = 1;
 			*offset = lastoff;
 			break;
@@ -609,7 +609,7 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
  * by calling generic_file_llseek_size() with the appropriate maxbytes
  * value for each.
  */
-loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
+loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	loff_t maxbytes;
@@ -619,11 +619,11 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
 	else
 		maxbytes = inode->i_sb->s_maxbytes;
 
-	switch (origin) {
+	switch (whence) {
 	case SEEK_SET:
 	case SEEK_CUR:
 	case SEEK_END:
-		return generic_file_llseek_size(file, offset, origin,
+		return generic_file_llseek_size(file, offset, whence,
 						maxbytes, i_size_read(inode));
 	case SEEK_DATA:
 		return ext4_seek_data(file, offset, maxbytes);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 78d2837bc940..e21d4d8f87e3 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1599,19 +1599,19 @@ static sector_t fuse_bmap(struct address_space *mapping, sector_t block)
 	return err ? 0 : outarg.block;
 }
 
-static loff_t fuse_file_llseek(struct file *file, loff_t offset, int origin)
+static loff_t fuse_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	loff_t retval;
 	struct inode *inode = file->f_path.dentry->d_inode;
 
 	/* No i_mutex protection necessary for SEEK_CUR and SEEK_SET */
-	if (origin == SEEK_CUR || origin == SEEK_SET)
-		return generic_file_llseek(file, offset, origin);
+	if (whence == SEEK_CUR || whence == SEEK_SET)
+		return generic_file_llseek(file, offset, whence);
 
 	mutex_lock(&inode->i_mutex);
 	retval = fuse_update_attributes(inode, NULL, file, NULL);
 	if (!retval)
-		retval = generic_file_llseek(file, offset, origin);
+		retval = generic_file_llseek(file, offset, whence);
 	mutex_unlock(&inode->i_mutex);
 
 	return retval;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index dfe2d8cb9b2c..991ab2d484dd 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -44,7 +44,7 @@
  * gfs2_llseek - seek to a location in a file
  * @file: the file
  * @offset: the offset
- * @origin: Where to seek from (SEEK_SET, SEEK_CUR, or SEEK_END)
+ * @whence: Where to seek from (SEEK_SET, SEEK_CUR, or SEEK_END)
  *
  * SEEK_END requires the glock for the file because it references the
  * file's size.
@@ -52,26 +52,26 @@
  * Returns: The new offset, or errno
  */
 
-static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
+static loff_t gfs2_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
 	struct gfs2_holder i_gh;
 	loff_t error;
 
-	switch (origin) {
+	switch (whence) {
 	case SEEK_END: /* These reference inode->i_size */
 	case SEEK_DATA:
 	case SEEK_HOLE:
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
 					   &i_gh);
 		if (!error) {
-			error = generic_file_llseek(file, offset, origin);
+			error = generic_file_llseek(file, offset, whence);
 			gfs2_glock_dq_uninit(&i_gh);
 		}
 		break;
 	case SEEK_CUR:
 	case SEEK_SET:
-		error = generic_file_llseek(file, offset, origin);
+		error = generic_file_llseek(file, offset, whence);
 		break;
 	default:
 		error = -EINVAL;
diff --git a/fs/libfs.c b/fs/libfs.c
index 7cc37ca19cd8..35fc6e74cd88 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -81,11 +81,11 @@ int dcache_dir_close(struct inode *inode, struct file *file)
 	return 0;
 }
 
-loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin)
+loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	mutex_lock(&dentry->d_inode->i_mutex);
-	switch (origin) {
+	switch (whence) {
 		case 1:
 			offset += file->f_pos;
 		case 0:
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b9e66b7e0c14..1cc71f60b491 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -871,7 +871,7 @@ out:
 	return res;
 }
 
-static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin)
+static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 {
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
@@ -880,10 +880,10 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin)
 	dfprintk(FILE, "NFS: llseek dir(%s/%s, %lld, %d)\n",
 			dentry->d_parent->d_name.name,
 			dentry->d_name.name,
-			offset, origin);
+			offset, whence);
 
 	mutex_lock(&inode->i_mutex);
-	switch (origin) {
+	switch (whence) {
 		case 1:
 			offset += filp->f_pos;
 		case 0:
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 582bb8866131..3c2b893665ba 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -119,18 +119,18 @@ force_reval:
 	return __nfs_revalidate_inode(server, inode);
 }
 
-loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
+loff_t nfs_file_llseek(struct file *filp, loff_t offset, int whence)
 {
 	dprintk("NFS: llseek file(%s/%s, %lld, %d)\n",
 			filp->f_path.dentry->d_parent->d_name.name,
 			filp->f_path.dentry->d_name.name,
-			offset, origin);
+			offset, whence);
 
 	/*
-	 * origin == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate
+	 * whence == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate
 	 * the cached file length
 	 */
-	if (origin != SEEK_SET && origin != SEEK_CUR) {
+	if (whence != SEEK_SET && whence != SEEK_CUR) {
 		struct inode *inode = filp->f_mapping->host;
 
 		int retval = nfs_revalidate_file_size(inode, filp);
@@ -138,7 +138,7 @@ loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 			return (loff_t)retval;
 	}
 
-	return generic_file_llseek(filp, offset, origin);
+	return generic_file_llseek(filp, offset, whence);
 }
 EXPORT_SYMBOL_GPL(nfs_file_llseek);
 
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 70b5863a2d64..f487aa343442 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -832,7 +832,7 @@ out:
 	return ret;
 }
 
-int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin)
+int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	int ret;
@@ -843,7 +843,7 @@ int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin)
 	struct buffer_head *di_bh = NULL;
 	struct ocfs2_extent_rec rec;
 
-	BUG_ON(origin != SEEK_DATA && origin != SEEK_HOLE);
+	BUG_ON(whence != SEEK_DATA && whence != SEEK_HOLE);
 
 	ret = ocfs2_inode_lock(inode, &di_bh, 0);
 	if (ret) {
@@ -859,7 +859,7 @@ int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin)
 	}
 
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
-		if (origin == SEEK_HOLE)
+		if (whence == SEEK_HOLE)
 			*offset = inode->i_size;
 		goto out_unlock;
 	}
@@ -888,8 +888,8 @@ int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin)
 			is_data = (rec.e_flags & OCFS2_EXT_UNWRITTEN) ?  0 : 1;
 		}
 
-		if ((!is_data && origin == SEEK_HOLE) ||
-		    (is_data && origin == SEEK_DATA)) {
+		if ((!is_data && whence == SEEK_HOLE) ||
+		    (is_data && whence == SEEK_DATA)) {
 			if (extoff > *offset)
 				*offset = extoff;
 			goto out_unlock;
@@ -899,7 +899,7 @@ int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin)
 			cpos += clen;
 	}
 
-	if (origin == SEEK_HOLE) {
+	if (whence == SEEK_HOLE) {
 		extoff = cpos;
 		extoff <<= cs_bits;
 		extlen = clen;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index dda089804942..fe492e1a3cfc 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2637,14 +2637,14 @@ bail:
 }
 
 /* Refer generic_file_llseek_unlocked() */
-static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int origin)
+static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	int ret = 0;
 
 	mutex_lock(&inode->i_mutex);
 
-	switch (origin) {
+	switch (whence) {
 	case SEEK_SET:
 		break;
 	case SEEK_END:
@@ -2659,7 +2659,7 @@ static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int origin)
 		break;
 	case SEEK_DATA:
 	case SEEK_HOLE:
-		ret = ocfs2_seek_data_hole_offset(file, &offset, origin);
+		ret = ocfs2_seek_data_hole_offset(file, &offset, whence);
 		if (ret)
 			goto out;
 		break;
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index ed1d8c7212da..67de74ca85f4 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -151,13 +151,13 @@ static int pstore_file_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static loff_t pstore_file_llseek(struct file *file, loff_t off, int origin)
+static loff_t pstore_file_llseek(struct file *file, loff_t off, int whence)
 {
 	struct seq_file *sf = file->private_data;
 
 	if (sf->op)
-		return seq_lseek(file, off, origin);
-	return default_llseek(file, off, origin);
+		return seq_lseek(file, off, whence);
+	return default_llseek(file, off, whence);
 }
 
 static const struct file_operations pstore_file_operations = {
diff --git a/fs/read_write.c b/fs/read_write.c
index d06534857e9e..1edaf099ddd7 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -54,7 +54,7 @@ static loff_t lseek_execute(struct file *file, struct inode *inode,
  * generic_file_llseek_size - generic llseek implementation for regular files
  * @file:	file structure to seek on
  * @offset:	file offset to seek to
- * @origin:	type of seek
+ * @whence:	type of seek
  * @size:	max size of this file in file system
  * @eof:	offset used for SEEK_END position
  *
@@ -67,12 +67,12 @@ static loff_t lseek_execute(struct file *file, struct inode *inode,
  * read/writes behave like SEEK_SET against seeks.
  */
 loff_t
-generic_file_llseek_size(struct file *file, loff_t offset, int origin,
+generic_file_llseek_size(struct file *file, loff_t offset, int whence,
 		loff_t maxsize, loff_t eof)
 {
 	struct inode *inode = file->f_mapping->host;
 
-	switch (origin) {
+	switch (whence) {
 	case SEEK_END:
 		offset += eof;
 		break;
@@ -122,17 +122,17 @@ EXPORT_SYMBOL(generic_file_llseek_size);
  * generic_file_llseek - generic llseek implementation for regular files
  * @file:	file structure to seek on
  * @offset:	file offset to seek to
- * @origin:	type of seek
+ * @whence:	type of seek
  *
  * This is a generic implemenation of ->llseek useable for all normal local
  * filesystems.  It just updates the file offset to the value specified by
- * @offset and @origin under i_mutex.
+ * @offset and @whence under i_mutex.
  */
-loff_t generic_file_llseek(struct file *file, loff_t offset, int origin)
+loff_t generic_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 
-	return generic_file_llseek_size(file, offset, origin,
+	return generic_file_llseek_size(file, offset, whence,
 					inode->i_sb->s_maxbytes,
 					i_size_read(inode));
 }
@@ -142,32 +142,32 @@ EXPORT_SYMBOL(generic_file_llseek);
  * noop_llseek - No Operation Performed llseek implementation
  * @file:	file structure to seek on
  * @offset:	file offset to seek to
- * @origin:	type of seek
+ * @whence:	type of seek
  *
  * This is an implementation of ->llseek useable for the rare special case when
  * userspace expects the seek to succeed but the (device) file is actually not
  * able to perform the seek. In this case you use noop_llseek() instead of
  * falling back to the default implementation of ->llseek.
  */
-loff_t noop_llseek(struct file *file, loff_t offset, int origin)
+loff_t noop_llseek(struct file *file, loff_t offset, int whence)
 {
 	return file->f_pos;
 }
 EXPORT_SYMBOL(noop_llseek);
 
-loff_t no_llseek(struct file *file, loff_t offset, int origin)
+loff_t no_llseek(struct file *file, loff_t offset, int whence)
 {
 	return -ESPIPE;
 }
 EXPORT_SYMBOL(no_llseek);
 
-loff_t default_llseek(struct file *file, loff_t offset, int origin)
+loff_t default_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_path.dentry->d_inode;
 	loff_t retval;
 
 	mutex_lock(&inode->i_mutex);
-	switch (origin) {
+	switch (whence) {
 		case SEEK_END:
 			offset += i_size_read(inode);
 			break;
@@ -216,7 +216,7 @@ out:
 }
 EXPORT_SYMBOL(default_llseek);
 
-loff_t vfs_llseek(struct file *file, loff_t offset, int origin)
+loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
 {
 	loff_t (*fn)(struct file *, loff_t, int);
 
@@ -225,11 +225,11 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int origin)
 		if (file->f_op && file->f_op->llseek)
 			fn = file->f_op->llseek;
 	}
-	return fn(file, offset, origin);
+	return fn(file, offset, whence);
 }
 EXPORT_SYMBOL(vfs_llseek);
 
-SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, origin)
+SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
 {
 	off_t retval;
 	struct fd f = fdget(fd);
@@ -237,8 +237,8 @@ SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, origin)
 		return -EBADF;
 
 	retval = -EINVAL;
-	if (origin <= SEEK_MAX) {
-		loff_t res = vfs_llseek(f.file, offset, origin);
+	if (whence <= SEEK_MAX) {
+		loff_t res = vfs_llseek(f.file, offset, whence);
 		retval = res;
 		if (res != (loff_t)retval)
 			retval = -EOVERFLOW;	/* LFS: should only happen on 32 bit platforms */
@@ -250,7 +250,7 @@ SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, origin)
 #ifdef __ARCH_WANT_SYS_LLSEEK
 SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
 		unsigned long, offset_low, loff_t __user *, result,
-		unsigned int, origin)
+		unsigned int, whence)
 {
 	int retval;
 	struct fd f = fdget(fd);
@@ -260,11 +260,11 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
 		return -EBADF;
 
 	retval = -EINVAL;
-	if (origin > SEEK_MAX)
+	if (whence > SEEK_MAX)
 		goto out_putf;
 
 	offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low,
-			origin);
+			whence);
 
 	retval = (int)offset;
 	if (offset >= 0) {
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 99dffab4c4e4..9d863fb501f9 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -300,14 +300,14 @@ EXPORT_SYMBOL(seq_read);
  *
  *	Ready-made ->f_op->llseek()
  */
-loff_t seq_lseek(struct file *file, loff_t offset, int origin)
+loff_t seq_lseek(struct file *file, loff_t offset, int whence)
 {
 	struct seq_file *m = file->private_data;
 	loff_t retval = -EINVAL;
 
 	mutex_lock(&m->lock);
 	m->version = file->f_version;
-	switch (origin) {
+	switch (whence) {
 		case 1:
 			offset += file->f_pos;
 		case 0:
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index e271fba1651b..8a574776a493 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -453,11 +453,11 @@ out:
 }
 
 /* If a directory is seeked, we have to free saved readdir() state */
-static loff_t ubifs_dir_llseek(struct file *file, loff_t offset, int origin)
+static loff_t ubifs_dir_llseek(struct file *file, loff_t offset, int whence)
 {
 	kfree(file->private_data);
 	file->private_data = NULL;
-	return generic_file_llseek(file, offset, origin);
+	return generic_file_llseek(file, offset, whence);
 }
 
 /* Free saved readdir() state when the directory is closed */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 408fb1e77a0a..029552ff774c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2286,9 +2286,9 @@ extern ino_t find_inode_number(struct dentry *, struct qstr *);
 #include <linux/err.h>
 
 /* needed for stackable file system support */
-extern loff_t default_llseek(struct file *file, loff_t offset, int origin);
+extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
 
-extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
+extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
 
 extern int inode_init_always(struct super_block *, struct inode *);
 extern void inode_init_once(struct inode *);
@@ -2396,11 +2396,11 @@ extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 
 extern void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
-extern loff_t noop_llseek(struct file *file, loff_t offset, int origin);
-extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
-extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
+extern loff_t noop_llseek(struct file *file, loff_t offset, int whence);
+extern loff_t no_llseek(struct file *file, loff_t offset, int whence);
+extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
 extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
-		int origin, loff_t maxsize, loff_t eof);
+		int whence, loff_t maxsize, loff_t eof);
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index a52f2f4fe030..92691d85c320 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -394,7 +394,7 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf,
 			    size_t cnt, loff_t *ppos);
 ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf,
 			     size_t cnt, loff_t *ppos);
-loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int origin);
+loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int whence);
 int ftrace_regex_release(struct inode *inode, struct file *file);
 
 void __init
@@ -559,7 +559,7 @@ static inline ssize_t ftrace_filter_write(struct file *file, const char __user *
 			    size_t cnt, loff_t *ppos) { return -ENODEV; }
 static inline ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf,
 			     size_t cnt, loff_t *ppos) { return -ENODEV; }
-static inline loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
+static inline loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int whence)
 {
 	return -ENODEV;
 }
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 91835e7f364d..36c3b07c5119 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -560,10 +560,10 @@ asmlinkage long sys_utime(char __user *filename,
 asmlinkage long sys_utimes(char __user *filename,
 				struct timeval __user *utimes);
 asmlinkage long sys_lseek(unsigned int fd, off_t offset,
-			  unsigned int origin);
+			  unsigned int whence);
 asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high,
 			unsigned long offset_low, loff_t __user *result,
-			unsigned int origin);
+			unsigned int whence);
 asmlinkage long sys_read(unsigned int fd, char __user *buf, size_t count);
 asmlinkage long sys_readahead(int fd, loff_t offset, size_t count);
 asmlinkage long sys_readv(unsigned long fd,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index afd092de45b7..3ffe4c5ad3f3 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2675,12 +2675,12 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
 }
 
 loff_t
-ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
+ftrace_regex_lseek(struct file *file, loff_t offset, int whence)
 {
 	loff_t ret;
 
 	if (file->f_mode & FMODE_READ)
-		ret = seq_lseek(file, offset, origin);
+		ret = seq_lseek(file, offset, whence);
 	else
 		file->f_pos = ret = 1;
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 03f9ba8fb8e5..5c90d84c2b02 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1719,7 +1719,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
  * llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
  */
 static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
-				    pgoff_t index, pgoff_t end, int origin)
+				    pgoff_t index, pgoff_t end, int whence)
 {
 	struct page *page;
 	struct pagevec pvec;
@@ -1733,13 +1733,13 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
 					pvec.nr, pvec.pages, indices);
 		if (!pvec.nr) {
-			if (origin == SEEK_DATA)
+			if (whence == SEEK_DATA)
 				index = end;
 			break;
 		}
 		for (i = 0; i < pvec.nr; i++, index++) {
 			if (index < indices[i]) {
-				if (origin == SEEK_HOLE) {
+				if (whence == SEEK_HOLE) {
 					done = true;
 					break;
 				}
@@ -1751,8 +1751,8 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 					page = NULL;
 			}
 			if (index >= end ||
-			    (page && origin == SEEK_DATA) ||
-			    (!page && origin == SEEK_HOLE)) {
+			    (page && whence == SEEK_DATA) ||
+			    (!page && whence == SEEK_HOLE)) {
 				done = true;
 				break;
 			}
@@ -1765,15 +1765,15 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 	return index;
 }
 
-static loff_t shmem_file_llseek(struct file *file, loff_t offset, int origin)
+static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
 	pgoff_t start, end;
 	loff_t new_offset;
 
-	if (origin != SEEK_DATA && origin != SEEK_HOLE)
-		return generic_file_llseek_size(file, offset, origin,
+	if (whence != SEEK_DATA && whence != SEEK_HOLE)
+		return generic_file_llseek_size(file, offset, whence,
 					MAX_LFS_FILESIZE, i_size_read(inode));
 	mutex_lock(&inode->i_mutex);
 	/* We're holding i_mutex so we can access i_size directly */
@@ -1785,12 +1785,12 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int origin)
 	else {
 		start = offset >> PAGE_CACHE_SHIFT;
 		end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-		new_offset = shmem_seek_hole_data(mapping, start, end, origin);
+		new_offset = shmem_seek_hole_data(mapping, start, end, whence);
 		new_offset <<= PAGE_CACHE_SHIFT;
 		if (new_offset > offset) {
 			if (new_offset < inode->i_size)
 				offset = new_offset;
-			else if (origin == SEEK_DATA)
+			else if (whence == SEEK_DATA)
 				offset = -ENXIO;
 			else
 				offset = inode->i_size;
-- 
cgit v1.2.3-55-g7522


From 41739ee355abc39d36bde6feed32ad16c63ceea2 Mon Sep 17 00:00:00 2001
From: Will Deacon
Date: Mon, 17 Dec 2012 15:59:42 -0800
Subject: asm-generic: io: don't perform swab during {in,out} string functions

The {in,out}s{b,w,l} functions are designed to operate on a stream of
bytes and therefore should not perform any byte-swapping, regardless of
the CPU byte order.

This patch fixes the generic IO header so that {in,out}s{b,w,l} call the
__raw_{read,write} functions directly rather than going via the
endian-correcting accessors.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Ben Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/io.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 9e0ebe051243..d1e93284d72a 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -154,7 +154,7 @@ static inline void insb(unsigned long addr, void *buffer, int count)
 	if (count) {
 		u8 *buf = buffer;
 		do {
-			u8 x = inb(addr);
+			u8 x = __raw_readb(addr + PCI_IOBASE);
 			*buf++ = x;
 		} while (--count);
 	}
@@ -167,7 +167,7 @@ static inline void insw(unsigned long addr, void *buffer, int count)
 	if (count) {
 		u16 *buf = buffer;
 		do {
-			u16 x = inw(addr);
+			u16 x = __raw_readw(addr + PCI_IOBASE);
 			*buf++ = x;
 		} while (--count);
 	}
@@ -180,7 +180,7 @@ static inline void insl(unsigned long addr, void *buffer, int count)
 	if (count) {
 		u32 *buf = buffer;
 		do {
-			u32 x = inl(addr);
+			u32 x = __raw_readl(addr + PCI_IOBASE);
 			*buf++ = x;
 		} while (--count);
 	}
@@ -193,7 +193,7 @@ static inline void outsb(unsigned long addr, const void *buffer, int count)
 	if (count) {
 		const u8 *buf = buffer;
 		do {
-			outb(*buf++, addr);
+			__raw_writeb(*buf++, addr + PCI_IOBASE);
 		} while (--count);
 	}
 }
@@ -205,7 +205,7 @@ static inline void outsw(unsigned long addr, const void *buffer, int count)
 	if (count) {
 		const u16 *buf = buffer;
 		do {
-			outw(*buf++, addr);
+			__raw_writew(*buf++, addr + PCI_IOBASE);
 		} while (--count);
 	}
 }
@@ -217,7 +217,7 @@ static inline void outsl(unsigned long addr, const void *buffer, int count)
 	if (count) {
 		const u32 *buf = buffer;
 		do {
-			outl(*buf++, addr);
+			__raw_writel(*buf++, addr + PCI_IOBASE);
 		} while (--count);
 	}
 }
-- 
cgit v1.2.3-55-g7522


From 8cc9764c9c7d01a6e2c3ddac8f0ac7716be01868 Mon Sep 17 00:00:00 2001
From: Kim, Milo
Date: Mon, 17 Dec 2012 16:00:43 -0800
Subject: drivers/video/backlight/lp855x_bl.c: use generic PWM functions

The LP855x family devices support the PWM input for the backlight control.
 Period of the PWM is configurable in the platform side.  Platform
specific functions are unnecessary anymore because generic PWM functions
are used inside the driver.

(PWM input mode)
To set the brightness, new lp855x_pwm_ctrl() is used.
If a PWM device is not allocated, devm_pwm_get() is called.
The PWM consumer name is from the chip name such as 'lp8550' and 'lp8556'.
To get the brightness value, no additional handling is required.
Just the value of 'props.brightness' is returned.

If the PWM driver is not ready while initializing the LP855x driver, it's
OK.  The PWM device can be retrieved later, when the brightness value is
changed.

Documentation is updated with an example.

[akpm@linux-foundation.org: coding-style simplification, per Thierry]
Signed-off-by: Milo(Woogyom) Kim <milo.kim@ti.com>
Cc: Thierry Reding <thierry.reding@avionic-design.de>
Cc: Richard Purdie <rpurdie@rpsys.net>
Cc: Bryan Wu <bryan.wu@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/backlight/lp855x-driver.txt | 10 ++-------
 drivers/video/backlight/lp855x_bl.c       | 37 ++++++++++++++++++++++---------
 include/linux/platform_data/lp855x.h      |  9 ++------
 3 files changed, 30 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/Documentation/backlight/lp855x-driver.txt b/Documentation/backlight/lp855x-driver.txt
index f5e4caafab7d..1529394cfe8b 100644
--- a/Documentation/backlight/lp855x-driver.txt
+++ b/Documentation/backlight/lp855x-driver.txt
@@ -35,11 +35,8 @@ For supporting platform specific data, the lp855x platform data can be used.
 * mode : Brightness control mode. PWM or register based.
 * device_control : Value of DEVICE CONTROL register.
 * initial_brightness : Initial value of backlight brightness.
-* pwm_data : Platform specific pwm generation functions.
+* period_ns : Platform specific PWM period value. unit is nano.
 	     Only valid when brightness is pwm input mode.
-	     Functions should be implemented by PWM driver.
-	     - pwm_set_intensity() : set duty of PWM
-	     - pwm_get_intensity() : get current duty of PWM
 * load_new_rom_data :
 	0 : use default configuration data
 	1 : update values of eeprom or eprom registers on loading driver
@@ -71,8 +68,5 @@ static struct lp855x_platform_data lp8556_pdata = {
 	.mode = PWM_BASED,
 	.device_control = PWM_CONFIG(LP8556),
 	.initial_brightness = INITIAL_BRT,
-	.pwm_data = {
-		     .pwm_set_intensity = platform_pwm_set_intensity,
-		     .pwm_get_intensity = platform_pwm_get_intensity,
-		     },
+	.period_ns = 1000000,
 };
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index fd985e0681e9..b437541555ff 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -15,6 +15,7 @@
 #include <linux/backlight.h>
 #include <linux/err.h>
 #include <linux/platform_data/lp855x.h>
+#include <linux/pwm.h>
 
 /* Registers */
 #define BRIGHTNESS_CTRL		0x00
@@ -36,6 +37,7 @@ struct lp855x {
 	struct device *dev;
 	struct mutex xfer_lock;
 	struct lp855x_platform_data *pdata;
+	struct pwm_device *pwm;
 };
 
 static int lp855x_read_byte(struct lp855x *lp, u8 reg, u8 *data)
@@ -121,6 +123,28 @@ static int lp855x_init_registers(struct lp855x *lp)
 	return ret;
 }
 
+static void lp855x_pwm_ctrl(struct lp855x *lp, int br, int max_br)
+{
+	unsigned int period = lp->pdata->period_ns;
+	unsigned int duty = br * period / max_br;
+	struct pwm_device *pwm;
+
+	/* request pwm device with the consumer name */
+	if (!lp->pwm) {
+		pwm = devm_pwm_get(lp->dev, lp->chipname);
+		if (IS_ERR(pwm))
+			return;
+
+		lp->pwm = pwm;
+	}
+
+	pwm_config(lp->pwm, duty, period);
+	if (duty)
+		pwm_enable(lp->pwm);
+	else
+		pwm_disable(lp->pwm);
+}
+
 static int lp855x_bl_update_status(struct backlight_device *bl)
 {
 	struct lp855x *lp = bl_get_data(bl);
@@ -130,12 +154,10 @@ static int lp855x_bl_update_status(struct backlight_device *bl)
 		bl->props.brightness = 0;
 
 	if (mode == PWM_BASED) {
-		struct lp855x_pwm_data *pd = &lp->pdata->pwm_data;
 		int br = bl->props.brightness;
 		int max_br = bl->props.max_brightness;
 
-		if (pd->pwm_set_intensity)
-			pd->pwm_set_intensity(br, max_br);
+		lp855x_pwm_ctrl(lp, br, max_br);
 
 	} else if (mode == REGISTER_BASED) {
 		u8 val = bl->props.brightness;
@@ -150,14 +172,7 @@ static int lp855x_bl_get_brightness(struct backlight_device *bl)
 	struct lp855x *lp = bl_get_data(bl);
 	enum lp855x_brightness_ctrl_mode mode = lp->pdata->mode;
 
-	if (mode == PWM_BASED) {
-		struct lp855x_pwm_data *pd = &lp->pdata->pwm_data;
-		int max_br = bl->props.max_brightness;
-
-		if (pd->pwm_get_intensity)
-			bl->props.brightness = pd->pwm_get_intensity(max_br);
-
-	} else if (mode == REGISTER_BASED) {
+	if (mode == REGISTER_BASED) {
 		u8 val = 0;
 
 		lp855x_read_byte(lp, BRIGHTNESS_CTRL, &val);
diff --git a/include/linux/platform_data/lp855x.h b/include/linux/platform_data/lp855x.h
index 761f31752367..e81f62d24ee2 100644
--- a/include/linux/platform_data/lp855x.h
+++ b/include/linux/platform_data/lp855x.h
@@ -89,11 +89,6 @@ enum lp8556_brightness_source {
 	LP8556_COMBINED2,	/* pwm + i2c after the shaper block */
 };
 
-struct lp855x_pwm_data {
-	void (*pwm_set_intensity) (int brightness, int max_brightness);
-	int (*pwm_get_intensity) (int max_brightness);
-};
-
 struct lp855x_rom_data {
 	u8 addr;
 	u8 val;
@@ -105,7 +100,7 @@ struct lp855x_rom_data {
  * @mode : brightness control by pwm or lp855x register
  * @device_control : value of DEVICE CONTROL register
  * @initial_brightness : initial value of backlight brightness
- * @pwm_data : platform specific pwm generation functions.
+ * @period_ns : platform specific pwm period value. unit is nano.
 		Only valid when mode is PWM_BASED.
  * @load_new_rom_data :
 	0 : use default configuration data
@@ -118,7 +113,7 @@ struct lp855x_platform_data {
 	enum lp855x_brightness_ctrl_mode mode;
 	u8 device_control;
 	int initial_brightness;
-	struct lp855x_pwm_data pwm_data;
+	unsigned int period_ns;
 	u8 load_new_rom_data;
 	int size_program;
 	struct lp855x_rom_data *rom_data;
-- 
cgit v1.2.3-55-g7522


From 762a936fba7bd9225ca9a96e4860f6969b6b5670 Mon Sep 17 00:00:00 2001
From: Thierry Reding
Date: Mon, 17 Dec 2012 16:01:06 -0800
Subject: backlight: add of_find_backlight_by_node()

This function finds the struct backlight_device for a given device tree
node.  A dummy function is provided so that it safely compiles out if OF
support is disabled.

[akpm@linux-foundation.org: Don't use IS_ENABLED(CONFIG_OF)]
Signed-off-by: Thierry Reding <thierry.reding@avionic-design.de>
Acked-by: Jingoo Han <jg1.han@samsung.com>
Reviewed-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Thierry Reding <thierry.reding@avionic-design.de>
Reviewed-by: Grant Likely <grant.likely@secretlab.ca>
Acked-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/video/backlight/backlight.c | 29 +++++++++++++++++++++++++++++
 include/linux/backlight.h           | 10 ++++++++++
 2 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c
index 297db2fa91f5..345f6660d4b3 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -370,6 +370,35 @@ void backlight_device_unregister(struct backlight_device *bd)
 }
 EXPORT_SYMBOL(backlight_device_unregister);
 
+#ifdef CONFIG_OF
+static int of_parent_match(struct device *dev, void *data)
+{
+	return dev->parent && dev->parent->of_node == data;
+}
+
+/**
+ * of_find_backlight_by_node() - find backlight device by device-tree node
+ * @node: device-tree node of the backlight device
+ *
+ * Returns a pointer to the backlight device corresponding to the given DT
+ * node or NULL if no such backlight device exists or if the device hasn't
+ * been probed yet.
+ *
+ * This function obtains a reference on the backlight device and it is the
+ * caller's responsibility to drop the reference by calling put_device() on
+ * the backlight device's .dev field.
+ */
+struct backlight_device *of_find_backlight_by_node(struct device_node *node)
+{
+	struct device *dev;
+
+	dev = class_find_device(backlight_class, NULL, node, of_parent_match);
+
+	return dev ? to_backlight_device(dev) : NULL;
+}
+EXPORT_SYMBOL(of_find_backlight_by_node);
+#endif
+
 static void __exit backlight_class_exit(void)
 {
 	class_destroy(backlight_class);
diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 5ffc6dda4675..da9a0825e007 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -134,4 +134,14 @@ struct generic_bl_info {
 	void (*kick_battery)(void);
 };
 
+#ifdef CONFIG_OF
+struct backlight_device *of_find_backlight_by_node(struct device_node *node);
+#else
+static inline struct backlight_device *
+of_find_backlight_by_node(struct device_node *node)
+{
+	return NULL;
+}
+#endif
+
 #endif
-- 
cgit v1.2.3-55-g7522


From b18888ab256f05626193be955a7a03f01d676f8c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko
Date: Mon, 17 Dec 2012 16:01:18 -0800
Subject: string: introduce helper to get base file name from given path

There are several places in the kernel that use functionality like
basename(3) with the exception: in case of '/foo/bar/' we expect to get an
empty string.  Let's do it common helper for them.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: YAMANE Toshiaki <yamanetoshi@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/string.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/linux/string.h b/include/linux/string.h
index 630125818ca8..ac889c5ea11b 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -143,4 +143,15 @@ static inline bool strstarts(const char *str, const char *prefix)
 
 extern size_t memweight(const void *ptr, size_t bytes);
 
+/**
+ * kbasename - return the last part of a pathname.
+ *
+ * @path: path to extract the filename from.
+ */
+static inline const char *kbasename(const char *path)
+{
+	const char *tail = strrchr(path, '/');
+	return tail ? tail + 1 : path;
+}
+
 #endif /* _LINUX_STRING_H_ */
-- 
cgit v1.2.3-55-g7522


From a1fd3e24d8a484b3265a6d485202afe093c058f3 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov
Date: Mon, 17 Dec 2012 16:01:32 -0800
Subject: percpu_rw_semaphore: reimplement to not block the readers
 unnecessarily

Currently the writer does msleep() plus synchronize_sched() 3 times to
acquire/release the semaphore, and during this time the readers are
blocked completely.  Even if the "write" section was not actually started
or if it was already finished.

With this patch down_write/up_write does synchronize_sched() twice and
down_read/up_read are still possible during this time, just they use the
slow path.

percpu_down_write() first forces the readers to use rw_semaphore and
increment the "slow" counter to take the lock for reading, then it
takes that rw_semaphore for writing and blocks the readers.

Also.  With this patch the code relies on the documented behaviour of
synchronize_sched(), it doesn't try to pair synchronize_sched() with
barrier.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anton Arapov <anton@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/percpu-rwsem.h |  83 ++++-------------------
 lib/Makefile                 |   2 +-
 lib/percpu-rwsem.c           | 154 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 168 insertions(+), 71 deletions(-)
 create mode 100644 lib/percpu-rwsem.c

(limited to 'include')

diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index bd1e86071e57..592f0d610d8e 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -2,82 +2,25 @@
 #define _LINUX_PERCPU_RWSEM_H
 
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/percpu.h>
-#include <linux/rcupdate.h>
-#include <linux/delay.h>
+#include <linux/wait.h>
 
 struct percpu_rw_semaphore {
-	unsigned __percpu *counters;
-	bool locked;
-	struct mutex mtx;
+	unsigned int __percpu	*fast_read_ctr;
+	struct mutex		writer_mutex;
+	struct rw_semaphore	rw_sem;
+	atomic_t		slow_read_ctr;
+	wait_queue_head_t	write_waitq;
 };
 
-#define light_mb()	barrier()
-#define heavy_mb()	synchronize_sched_expedited()
+extern void percpu_down_read(struct percpu_rw_semaphore *);
+extern void percpu_up_read(struct percpu_rw_semaphore *);
 
-static inline void percpu_down_read(struct percpu_rw_semaphore *p)
-{
-	rcu_read_lock_sched();
-	if (unlikely(p->locked)) {
-		rcu_read_unlock_sched();
-		mutex_lock(&p->mtx);
-		this_cpu_inc(*p->counters);
-		mutex_unlock(&p->mtx);
-		return;
-	}
-	this_cpu_inc(*p->counters);
-	rcu_read_unlock_sched();
-	light_mb(); /* A, between read of p->locked and read of data, paired with D */
-}
+extern void percpu_down_write(struct percpu_rw_semaphore *);
+extern void percpu_up_write(struct percpu_rw_semaphore *);
 
-static inline void percpu_up_read(struct percpu_rw_semaphore *p)
-{
-	light_mb(); /* B, between read of the data and write to p->counter, paired with C */
-	this_cpu_dec(*p->counters);
-}
-
-static inline unsigned __percpu_count(unsigned __percpu *counters)
-{
-	unsigned total = 0;
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		total += ACCESS_ONCE(*per_cpu_ptr(counters, cpu));
-
-	return total;
-}
-
-static inline void percpu_down_write(struct percpu_rw_semaphore *p)
-{
-	mutex_lock(&p->mtx);
-	p->locked = true;
-	synchronize_sched_expedited(); /* make sure that all readers exit the rcu_read_lock_sched region */
-	while (__percpu_count(p->counters))
-		msleep(1);
-	heavy_mb(); /* C, between read of p->counter and write to data, paired with B */
-}
-
-static inline void percpu_up_write(struct percpu_rw_semaphore *p)
-{
-	heavy_mb(); /* D, between write to data and write to p->locked, paired with A */
-	p->locked = false;
-	mutex_unlock(&p->mtx);
-}
-
-static inline int percpu_init_rwsem(struct percpu_rw_semaphore *p)
-{
-	p->counters = alloc_percpu(unsigned);
-	if (unlikely(!p->counters))
-		return -ENOMEM;
-	p->locked = false;
-	mutex_init(&p->mtx);
-	return 0;
-}
-
-static inline void percpu_free_rwsem(struct percpu_rw_semaphore *p)
-{
-	free_percpu(p->counters);
-	p->counters = NULL; /* catch use after free bugs */
-}
+extern int percpu_init_rwsem(struct percpu_rw_semaphore *);
+extern void percpu_free_rwsem(struct percpu_rw_semaphore *);
 
 #endif
diff --git a/lib/Makefile b/lib/Makefile
index e2152fa7ff4d..e959c20efb24 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -9,7 +9,7 @@ endif
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o timerqueue.o\
-	 idr.o int_sqrt.o extable.o \
+	 idr.o int_sqrt.o extable.o percpu-rwsem.o \
 	 sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
 	 proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
diff --git a/lib/percpu-rwsem.c b/lib/percpu-rwsem.c
new file mode 100644
index 000000000000..2e03bcfe48f9
--- /dev/null
+++ b/lib/percpu-rwsem.c
@@ -0,0 +1,154 @@
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
+#include <linux/percpu.h>
+#include <linux/wait.h>
+#include <linux/percpu-rwsem.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+
+int percpu_init_rwsem(struct percpu_rw_semaphore *brw)
+{
+	brw->fast_read_ctr = alloc_percpu(int);
+	if (unlikely(!brw->fast_read_ctr))
+		return -ENOMEM;
+
+	mutex_init(&brw->writer_mutex);
+	init_rwsem(&brw->rw_sem);
+	atomic_set(&brw->slow_read_ctr, 0);
+	init_waitqueue_head(&brw->write_waitq);
+	return 0;
+}
+
+void percpu_free_rwsem(struct percpu_rw_semaphore *brw)
+{
+	free_percpu(brw->fast_read_ctr);
+	brw->fast_read_ctr = NULL; /* catch use after free bugs */
+}
+
+/*
+ * This is the fast-path for down_read/up_read, it only needs to ensure
+ * there is no pending writer (!mutex_is_locked() check) and inc/dec the
+ * fast per-cpu counter. The writer uses synchronize_sched_expedited() to
+ * serialize with the preempt-disabled section below.
+ *
+ * The nontrivial part is that we should guarantee acquire/release semantics
+ * in case when
+ *
+ *	R_W: down_write() comes after up_read(), the writer should see all
+ *	     changes done by the reader
+ * or
+ *	W_R: down_read() comes after up_write(), the reader should see all
+ *	     changes done by the writer
+ *
+ * If this helper fails the callers rely on the normal rw_semaphore and
+ * atomic_dec_and_test(), so in this case we have the necessary barriers.
+ *
+ * But if it succeeds we do not have any barriers, mutex_is_locked() or
+ * __this_cpu_add() below can be reordered with any LOAD/STORE done by the
+ * reader inside the critical section. See the comments in down_write and
+ * up_write below.
+ */
+static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val)
+{
+	bool success = false;
+
+	preempt_disable();
+	if (likely(!mutex_is_locked(&brw->writer_mutex))) {
+		__this_cpu_add(*brw->fast_read_ctr, val);
+		success = true;
+	}
+	preempt_enable();
+
+	return success;
+}
+
+/*
+ * Like the normal down_read() this is not recursive, the writer can
+ * come after the first percpu_down_read() and create the deadlock.
+ */
+void percpu_down_read(struct percpu_rw_semaphore *brw)
+{
+	if (likely(update_fast_ctr(brw, +1)))
+		return;
+
+	down_read(&brw->rw_sem);
+	atomic_inc(&brw->slow_read_ctr);
+	up_read(&brw->rw_sem);
+}
+
+void percpu_up_read(struct percpu_rw_semaphore *brw)
+{
+	if (likely(update_fast_ctr(brw, -1)))
+		return;
+
+	/* false-positive is possible but harmless */
+	if (atomic_dec_and_test(&brw->slow_read_ctr))
+		wake_up_all(&brw->write_waitq);
+}
+
+static int clear_fast_ctr(struct percpu_rw_semaphore *brw)
+{
+	unsigned int sum = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		sum += per_cpu(*brw->fast_read_ctr, cpu);
+		per_cpu(*brw->fast_read_ctr, cpu) = 0;
+	}
+
+	return sum;
+}
+
+/*
+ * A writer takes ->writer_mutex to exclude other writers and to force the
+ * readers to switch to the slow mode, note the mutex_is_locked() check in
+ * update_fast_ctr().
+ *
+ * After that the readers can only inc/dec the slow ->slow_read_ctr counter,
+ * ->fast_read_ctr is stable. Once the writer moves its sum into the slow
+ * counter it represents the number of active readers.
+ *
+ * Finally the writer takes ->rw_sem for writing and blocks the new readers,
+ * then waits until the slow counter becomes zero.
+ */
+void percpu_down_write(struct percpu_rw_semaphore *brw)
+{
+	/* also blocks update_fast_ctr() which checks mutex_is_locked() */
+	mutex_lock(&brw->writer_mutex);
+
+	/*
+	 * 1. Ensures mutex_is_locked() is visible to any down_read/up_read
+	 *    so that update_fast_ctr() can't succeed.
+	 *
+	 * 2. Ensures we see the result of every previous this_cpu_add() in
+	 *    update_fast_ctr().
+	 *
+	 * 3. Ensures that if any reader has exited its critical section via
+	 *    fast-path, it executes a full memory barrier before we return.
+	 *    See R_W case in the comment above update_fast_ctr().
+	 */
+	synchronize_sched_expedited();
+
+	/* nobody can use fast_read_ctr, move its sum into slow_read_ctr */
+	atomic_add(clear_fast_ctr(brw), &brw->slow_read_ctr);
+
+	/* block the new readers completely */
+	down_write(&brw->rw_sem);
+
+	/* wait for all readers to complete their percpu_up_read() */
+	wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr));
+}
+
+void percpu_up_write(struct percpu_rw_semaphore *brw)
+{
+	/* allow the new readers, but only the slow-path */
+	up_write(&brw->rw_sem);
+
+	/*
+	 * Insert the barrier before the next fast-path in down_read,
+	 * see W_R case in the comment above update_fast_ctr().
+	 */
+	synchronize_sched_expedited();
+	mutex_unlock(&brw->writer_mutex);
+}
-- 
cgit v1.2.3-55-g7522


From 9390ef0c85fd065f01045fef708b046c98cda04c Mon Sep 17 00:00:00 2001
From: Oleg Nesterov
Date: Mon, 17 Dec 2012 16:01:36 -0800
Subject: percpu_rw_semaphore: kill ->writer_mutex, add ->write_ctr

percpu_rw_semaphore->writer_mutex was only added to simplify the initial
rewrite, the only thing it protects is clear_fast_ctr() which otherwise
could be called by multiple writers.  ->rw_sem is enough to serialize the
writers.

Kill this mutex and add "atomic_t write_ctr" instead.  The writers
increment/decrement this counter, the readers check it is zero instead of
mutex_is_locked().

Move atomic_add(clear_fast_ctr(), slow_read_ctr) under down_write() to
avoid the race with other writers.  This is a bit sub-optimal, only the
first writer needs this and we do not need to exclude the readers at this
stage.  But this is simple, we do not want another internal lock until we
add more features.

And this speeds up the write-contended case.  Before this patch the racing
writers sleep in synchronize_sched_expedited() sequentially, with this
patch multiple synchronize_sched_expedited's can "overlap" with each
other.  Note: we can do more optimizations, this is only the first step.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Anton Arapov <anton@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michal Marek <mmarek@suse.cz>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/percpu-rwsem.h |  4 ++--
 lib/percpu-rwsem.c           | 34 ++++++++++++++++------------------
 2 files changed, 18 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 592f0d610d8e..d2146a4f833e 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -1,14 +1,14 @@
 #ifndef _LINUX_PERCPU_RWSEM_H
 #define _LINUX_PERCPU_RWSEM_H
 
-#include <linux/mutex.h>
+#include <linux/atomic.h>
 #include <linux/rwsem.h>
 #include <linux/percpu.h>
 #include <linux/wait.h>
 
 struct percpu_rw_semaphore {
 	unsigned int __percpu	*fast_read_ctr;
-	struct mutex		writer_mutex;
+	atomic_t		write_ctr;
 	struct rw_semaphore	rw_sem;
 	atomic_t		slow_read_ctr;
 	wait_queue_head_t	write_waitq;
diff --git a/lib/percpu-rwsem.c b/lib/percpu-rwsem.c
index 2e03bcfe48f9..ce92ab563a08 100644
--- a/lib/percpu-rwsem.c
+++ b/lib/percpu-rwsem.c
@@ -1,4 +1,4 @@
-#include <linux/mutex.h>
+#include <linux/atomic.h>
 #include <linux/rwsem.h>
 #include <linux/percpu.h>
 #include <linux/wait.h>
@@ -13,8 +13,8 @@ int percpu_init_rwsem(struct percpu_rw_semaphore *brw)
 	if (unlikely(!brw->fast_read_ctr))
 		return -ENOMEM;
 
-	mutex_init(&brw->writer_mutex);
 	init_rwsem(&brw->rw_sem);
+	atomic_set(&brw->write_ctr, 0);
 	atomic_set(&brw->slow_read_ctr, 0);
 	init_waitqueue_head(&brw->write_waitq);
 	return 0;
@@ -28,7 +28,7 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw)
 
 /*
  * This is the fast-path for down_read/up_read, it only needs to ensure
- * there is no pending writer (!mutex_is_locked() check) and inc/dec the
+ * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the
  * fast per-cpu counter. The writer uses synchronize_sched_expedited() to
  * serialize with the preempt-disabled section below.
  *
@@ -44,7 +44,7 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw)
  * If this helper fails the callers rely on the normal rw_semaphore and
  * atomic_dec_and_test(), so in this case we have the necessary barriers.
  *
- * But if it succeeds we do not have any barriers, mutex_is_locked() or
+ * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or
  * __this_cpu_add() below can be reordered with any LOAD/STORE done by the
  * reader inside the critical section. See the comments in down_write and
  * up_write below.
@@ -54,7 +54,7 @@ static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val)
 	bool success = false;
 
 	preempt_disable();
-	if (likely(!mutex_is_locked(&brw->writer_mutex))) {
+	if (likely(!atomic_read(&brw->write_ctr))) {
 		__this_cpu_add(*brw->fast_read_ctr, val);
 		success = true;
 	}
@@ -101,9 +101,8 @@ static int clear_fast_ctr(struct percpu_rw_semaphore *brw)
 }
 
 /*
- * A writer takes ->writer_mutex to exclude other writers and to force the
- * readers to switch to the slow mode, note the mutex_is_locked() check in
- * update_fast_ctr().
+ * A writer increments ->write_ctr to force the readers to switch to the
+ * slow mode, note the atomic_read() check in update_fast_ctr().
  *
  * After that the readers can only inc/dec the slow ->slow_read_ctr counter,
  * ->fast_read_ctr is stable. Once the writer moves its sum into the slow
@@ -114,11 +113,10 @@ static int clear_fast_ctr(struct percpu_rw_semaphore *brw)
  */
 void percpu_down_write(struct percpu_rw_semaphore *brw)
 {
-	/* also blocks update_fast_ctr() which checks mutex_is_locked() */
-	mutex_lock(&brw->writer_mutex);
-
+	/* tell update_fast_ctr() there is a pending writer */
+	atomic_inc(&brw->write_ctr);
 	/*
-	 * 1. Ensures mutex_is_locked() is visible to any down_read/up_read
+	 * 1. Ensures that write_ctr != 0 is visible to any down_read/up_read
 	 *    so that update_fast_ctr() can't succeed.
 	 *
 	 * 2. Ensures we see the result of every previous this_cpu_add() in
@@ -130,25 +128,25 @@ void percpu_down_write(struct percpu_rw_semaphore *brw)
 	 */
 	synchronize_sched_expedited();
 
+	/* exclude other writers, and block the new readers completely */
+	down_write(&brw->rw_sem);
+
 	/* nobody can use fast_read_ctr, move its sum into slow_read_ctr */
 	atomic_add(clear_fast_ctr(brw), &brw->slow_read_ctr);
 
-	/* block the new readers completely */
-	down_write(&brw->rw_sem);
-
 	/* wait for all readers to complete their percpu_up_read() */
 	wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr));
 }
 
 void percpu_up_write(struct percpu_rw_semaphore *brw)
 {
-	/* allow the new readers, but only the slow-path */
+	/* release the lock, but the readers can't use the fast-path */
 	up_write(&brw->rw_sem);
-
 	/*
 	 * Insert the barrier before the next fast-path in down_read,
 	 * see W_R case in the comment above update_fast_ctr().
 	 */
 	synchronize_sched_expedited();
-	mutex_unlock(&brw->writer_mutex);
+	/* the last writer unblocks update_fast_ctr() */
+	atomic_dec(&brw->write_ctr);
 }
-- 
cgit v1.2.3-55-g7522


From 8ebe34731a0d1a9d89b536430afd98d0fadec99b Mon Sep 17 00:00:00 2001
From: Oleg Nesterov
Date: Mon, 17 Dec 2012 16:01:38 -0800
Subject: percpu_rw_semaphore: add lockdep annotations

Add lockdep annotations.  Not only this can help to find the potential
problems, we do not want the false warnings if, say, the task takes two
different percpu_rw_semaphore's for reading.  IOW, at least ->rw_sem
should not use a single class.

This patch exposes this internal lock to lockdep so that it represents the
whole percpu_rw_semaphore.  This way we do not need to add another "fake"
->lockdep_map and lock_class_key.  More importantly, this also makes the
output from lockdep much more understandable if it finds the problem.

In short, with this patch from lockdep pov percpu_down_read() and
percpu_up_read() acquire/release ->rw_sem for reading, this matches the
actual semantics.  This abuses __up_read() but I hope this is fine and in
fact I'd like to have down_read_no_lockdep() as well,
percpu_down_read_recursive_readers() will need it.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Anton Arapov <anton@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michal Marek <mmarek@suse.cz>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/percpu-rwsem.h | 10 +++++++++-
 lib/percpu-rwsem.c           | 21 +++++++++++++++++----
 2 files changed, 26 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index d2146a4f833e..3e88c9a7d57f 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -5,6 +5,7 @@
 #include <linux/rwsem.h>
 #include <linux/percpu.h>
 #include <linux/wait.h>
+#include <linux/lockdep.h>
 
 struct percpu_rw_semaphore {
 	unsigned int __percpu	*fast_read_ctr;
@@ -20,7 +21,14 @@ extern void percpu_up_read(struct percpu_rw_semaphore *);
 extern void percpu_down_write(struct percpu_rw_semaphore *);
 extern void percpu_up_write(struct percpu_rw_semaphore *);
 
-extern int percpu_init_rwsem(struct percpu_rw_semaphore *);
+extern int __percpu_init_rwsem(struct percpu_rw_semaphore *,
+				const char *, struct lock_class_key *);
 extern void percpu_free_rwsem(struct percpu_rw_semaphore *);
 
+#define percpu_init_rwsem(brw)	\
+({								\
+	static struct lock_class_key rwsem_key;			\
+	__percpu_init_rwsem(brw, #brw, &rwsem_key);		\
+})
+
 #endif
diff --git a/lib/percpu-rwsem.c b/lib/percpu-rwsem.c
index ce92ab563a08..652a8ee8efe9 100644
--- a/lib/percpu-rwsem.c
+++ b/lib/percpu-rwsem.c
@@ -2,18 +2,21 @@
 #include <linux/rwsem.h>
 #include <linux/percpu.h>
 #include <linux/wait.h>
+#include <linux/lockdep.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
 
-int percpu_init_rwsem(struct percpu_rw_semaphore *brw)
+int __percpu_init_rwsem(struct percpu_rw_semaphore *brw,
+			const char *name, struct lock_class_key *rwsem_key)
 {
 	brw->fast_read_ctr = alloc_percpu(int);
 	if (unlikely(!brw->fast_read_ctr))
 		return -ENOMEM;
 
-	init_rwsem(&brw->rw_sem);
+	/* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
+	__init_rwsem(&brw->rw_sem, name, rwsem_key);
 	atomic_set(&brw->write_ctr, 0);
 	atomic_set(&brw->slow_read_ctr, 0);
 	init_waitqueue_head(&brw->write_waitq);
@@ -66,19 +69,29 @@ static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val)
 /*
  * Like the normal down_read() this is not recursive, the writer can
  * come after the first percpu_down_read() and create the deadlock.
+ *
+ * Note: returns with lock_is_held(brw->rw_sem) == T for lockdep,
+ * percpu_up_read() does rwsem_release(). This pairs with the usage
+ * of ->rw_sem in percpu_down/up_write().
  */
 void percpu_down_read(struct percpu_rw_semaphore *brw)
 {
-	if (likely(update_fast_ctr(brw, +1)))
+	might_sleep();
+	if (likely(update_fast_ctr(brw, +1))) {
+		rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_);
 		return;
+	}
 
 	down_read(&brw->rw_sem);
 	atomic_inc(&brw->slow_read_ctr);
-	up_read(&brw->rw_sem);
+	/* avoid up_read()->rwsem_release() */
+	__up_read(&brw->rw_sem);
 }
 
 void percpu_up_read(struct percpu_rw_semaphore *brw)
 {
+	rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_);
+
 	if (likely(update_fast_ctr(brw, -1)))
 		return;
 
-- 
cgit v1.2.3-55-g7522


From 0ad50c3896afbb3c103409a18260e601b87a744c Mon Sep 17 00:00:00 2001
From: Catalin Marinas
Date: Mon, 17 Dec 2012 16:01:45 -0800
Subject: compat: generic compat_sys_sched_rr_get_interval() implementation

This function is used by sparc, powerpc tile and arm64 for compat support.
 The patch adds a generic implementation with a wrapper for PowerPC to do
the u32->int sign extension.

The reason for a single patch covering powerpc, tile, sparc and arm64 is
to keep it bisectable, otherwise kernel building may fail with mismatched
function declarations.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>  [for tile]
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/include/asm/unistd.h   |  1 +
 arch/arm64/kernel/sys_compat.c    | 15 ---------------
 arch/powerpc/include/asm/systbl.h |  2 +-
 arch/powerpc/include/asm/unistd.h |  1 +
 arch/powerpc/kernel/sys_ppc32.c   | 17 ++++-------------
 arch/sparc/include/asm/unistd.h   |  1 +
 arch/sparc/kernel/sys_sparc32.c   | 14 --------------
 arch/tile/include/asm/compat.h    |  2 --
 arch/tile/include/asm/unistd.h    |  1 +
 arch/tile/kernel/compat.c         | 18 ------------------
 include/linux/compat.h            |  3 +++
 kernel/compat.c                   | 17 +++++++++++++++++
 12 files changed, 29 insertions(+), 63 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index d69aeea6da1e..76fb7dd3350a 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -20,6 +20,7 @@
 #define __ARCH_WANT_SYS_GETPGRP
 #define __ARCH_WANT_SYS_LLSEEK
 #define __ARCH_WANT_SYS_NICE
+#define __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL
 #define __ARCH_WANT_SYS_SIGPENDING
 #define __ARCH_WANT_SYS_SIGPROCMASK
 #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index f7b05edf8ce3..26e9c4eeaba8 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -28,21 +28,6 @@
 #include <asm/cacheflush.h>
 #include <asm/unistd32.h>
 
-asmlinkage int compat_sys_sched_rr_get_interval(compat_pid_t pid,
-						struct compat_timespec __user *interval)
-{
-	struct timespec t;
-	int ret;
-	mm_segment_t old_fs = get_fs();
-
-	set_fs(KERNEL_DS);
-	ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t);
-	set_fs(old_fs);
-	if (put_compat_timespec(&t, interval))
-		return -EFAULT;
-	return ret;
-}
-
 static inline void
 do_compat_cache_op(unsigned long start, unsigned long end, int flags)
 {
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 840838769853..cec8aae5cbf8 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -164,7 +164,7 @@ COMPAT_SYS_SPU(sched_getscheduler)
 SYSCALL_SPU(sched_yield)
 COMPAT_SYS_SPU(sched_get_priority_max)
 COMPAT_SYS_SPU(sched_get_priority_min)
-COMPAT_SYS_SPU(sched_rr_get_interval)
+SYSX_SPU(sys_sched_rr_get_interval,compat_sys_sched_rr_get_interval_wrapper,sys_sched_rr_get_interval)
 COMPAT_SYS_SPU(nanosleep)
 SYSCALL_SPU(mremap)
 SYSCALL_SPU(setresuid)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 76fe846ec40e..bcbbe413c606 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -54,6 +54,7 @@
 #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
 #define __ARCH_WANT_SYS_NEWFSTATAT
 #define __ARCH_WANT_COMPAT_SYS_SENDFILE
+#define __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL
 #endif
 #define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index 9c2ed90ece8f..8a93778ed9f5 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -175,19 +175,10 @@ asmlinkage long compat_sys_prctl(u32 option, u32 arg2, u32 arg3, u32 arg4, u32 a
  * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode)
  * and the register representation of a signed int (msr in 64-bit mode) is performed.
  */
-asmlinkage long compat_sys_sched_rr_get_interval(u32 pid, struct compat_timespec __user *interval)
-{
-	struct timespec t;
-	int ret;
-	mm_segment_t old_fs = get_fs ();
-
-	/* The __user pointer cast is valid because of the set_fs() */
-	set_fs (KERNEL_DS);
-	ret = sys_sched_rr_get_interval((int)pid, (struct timespec __user *) &t);
-	set_fs (old_fs);
-	if (put_compat_timespec(&t, interval))
-		return -EFAULT;
-	return ret;
+asmlinkage long compat_sys_sched_rr_get_interval_wrapper(u32 pid,
+							 struct compat_timespec __user *interval)
+{
+	return compat_sys_sched_rr_get_interval((int)pid, interval);
 }
 
 /* Note: it is necessary to treat mode as an unsigned int,
diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h
index c3e5d8b64171..497386a7ed28 100644
--- a/arch/sparc/include/asm/unistd.h
+++ b/arch/sparc/include/asm/unistd.h
@@ -45,6 +45,7 @@
 #define __ARCH_WANT_COMPAT_SYS_TIME
 #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
 #define __ARCH_WANT_COMPAT_SYS_SENDFILE
+#define __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL
 #endif
 #define __ARCH_WANT_SYS_EXECVE
 
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index 03c7e929ec34..4a4cdc633f6b 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -211,20 +211,6 @@ asmlinkage long compat_sys_sysfs(int option, u32 arg1, u32 arg2)
 	return sys_sysfs(option, arg1, arg2);
 }
 
-asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, struct compat_timespec __user *interval)
-{
-	struct timespec t;
-	int ret;
-	mm_segment_t old_fs = get_fs ();
-	
-	set_fs (KERNEL_DS);
-	ret = sys_sched_rr_get_interval(pid, (struct timespec __user *) &t);
-	set_fs (old_fs);
-	if (put_compat_timespec(&t, interval))
-		return -EFAULT;
-	return ret;
-}
-
 asmlinkage long compat_sys_rt_sigprocmask(int how,
 					  compat_sigset_t __user *set,
 					  compat_sigset_t __user *oset,
diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index ca61fb4296b3..88f3c227afd9 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -296,8 +296,6 @@ long compat_sys_sync_file_range2(int fd, unsigned int flags,
 long compat_sys_fallocate(int fd, int mode,
 			  u32 offset_lo, u32 offset_hi,
 			  u32 len_lo, u32 len_hi);
-long compat_sys_sched_rr_get_interval(compat_pid_t pid,
-				      struct compat_timespec __user *interval);
 
 /* Assembly trampoline to avoid clobbering r0. */
 long _compat_sys_rt_sigreturn(void);
diff --git a/arch/tile/include/asm/unistd.h b/arch/tile/include/asm/unistd.h
index b51c6ee3cd6c..fe841e7d4963 100644
--- a/arch/tile/include/asm/unistd.h
+++ b/arch/tile/include/asm/unistd.h
@@ -14,6 +14,7 @@
 /* In compat mode, we use sys_llseek() for compat_sys_llseek(). */
 #ifdef CONFIG_COMPAT
 #define __ARCH_WANT_SYS_LLSEEK
+#define __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL
 #endif
 #define __ARCH_WANT_SYS_NEWFSTATAT
 #define __ARCH_WANT_SYS_EXECVE
diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c
index 9cd7cb6041c0..7f72401b4f45 100644
--- a/arch/tile/kernel/compat.c
+++ b/arch/tile/kernel/compat.c
@@ -76,24 +76,6 @@ long compat_sys_fallocate(int fd, int mode,
 			     ((loff_t)len_hi << 32) | len_lo);
 }
 
-
-
-long compat_sys_sched_rr_get_interval(compat_pid_t pid,
-				      struct compat_timespec __user *interval)
-{
-	struct timespec t;
-	int ret;
-	mm_segment_t old_fs = get_fs();
-
-	set_fs(KERNEL_DS);
-	ret = sys_sched_rr_get_interval(pid,
-					(struct timespec __force __user *)&t);
-	set_fs(old_fs);
-	if (put_compat_timespec(&t, interval))
-		return -EFAULT;
-	return ret;
-}
-
 /* Provide the compat syscall number to call mapping. */
 #undef __SYSCALL
 #define __SYSCALL(nr, call) [nr] = (call),
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 784ebfe63c48..e4920bd58a47 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -588,6 +588,9 @@ asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid,
 asmlinkage long compat_sys_sendfile(int out_fd, int in_fd,
 				    compat_off_t __user *offset, compat_size_t count);
 
+asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid,
+						 struct compat_timespec __user *interval);
+
 #else
 
 #define is_compat_task() (0)
diff --git a/kernel/compat.c b/kernel/compat.c
index c28a306ae05c..f6150e92dfc9 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -1215,6 +1215,23 @@ compat_sys_sysinfo(struct compat_sysinfo __user *info)
 	return 0;
 }
 
+#ifdef __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL
+asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid,
+						 struct compat_timespec __user *interval)
+{
+	struct timespec t;
+	int ret;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(KERNEL_DS);
+	ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t);
+	set_fs(old_fs);
+	if (put_compat_timespec(&t, interval))
+		return -EFAULT;
+	return ret;
+}
+#endif /* __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL */
+
 /*
  * Allocate user-space memory for the duration of a single system call,
  * in order to marshall parameters inside a compat thunk.
-- 
cgit v1.2.3-55-g7522


From 4c925d6031f719fad6ea8b1c94a636f4c0fea39b Mon Sep 17 00:00:00 2001
From: Eldad Zack
Date: Mon, 17 Dec 2012 16:03:04 -0800
Subject: kstrto*: add documentation

As Bruce Fields pointed out, kstrto* is currently lacking kerneldoc
comments.  This patch adds kerneldoc comments to common variants of
kstrto*: kstrto(u)l, kstrto(u)ll and kstrto(u)int.

Signed-off-by: Eldad Zack <eldad@fogrefinery.com>
Cc: J. Bruce Fields <bfields@fieldses.org>
Cc: Joe Perches <joe@perches.com>
Cc: Randy Dunlap <rdunlap@xenotime.net>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Rob Landley <rob@landley.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/DocBook/kernel-api.tmpl |  3 ++
 include/linux/kernel.h                | 33 ++++++++++++++++++
 lib/kstrtox.c                         | 64 +++++++++++++++++++++++++++++++++++
 3 files changed, 100 insertions(+)

(limited to 'include')

diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index 00687ee9d363..f75ab4c1b281 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -58,6 +58,9 @@
 
      <sect1><title>String Conversions</title>
 !Elib/vsprintf.c
+!Finclude/linux/kernel.h kstrtol
+!Finclude/linux/kernel.h kstrtoul
+!Elib/kstrtox.c
      </sect1>
      <sect1><title>String Manipulation</title>
 <!-- All functions are exported at now
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index d97ed5897447..d140e8fb075f 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -220,6 +220,23 @@ int __must_check _kstrtol(const char *s, unsigned int base, long *res);
 
 int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res);
 int __must_check kstrtoll(const char *s, unsigned int base, long long *res);
+
+/**
+ * kstrtoul - convert a string to an unsigned long
+ * @s: The start of the string. The string must be null-terminated, and may also
+ *  include a single newline before its terminating null. The first character
+ *  may also be a plus sign, but not a minus sign.
+ * @base: The number base to use. The maximum supported base is 16. If base is
+ *  given as 0, then the base of the string is automatically detected with the
+ *  conventional semantics - If it begins with 0x the number will be parsed as a
+ *  hexadecimal (case insensitive), if it otherwise begins with 0, it will be
+ *  parsed as an octal number. Otherwise it will be parsed as a decimal.
+ * @res: Where to write the result of the conversion on success.
+ *
+ * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
+ * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * be checked.
+*/
 static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res)
 {
 	/*
@@ -233,6 +250,22 @@ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsign
 		return _kstrtoul(s, base, res);
 }
 
+/**
+ * kstrtol - convert a string to a long
+ * @s: The start of the string. The string must be null-terminated, and may also
+ *  include a single newline before its terminating null. The first character
+ *  may also be a plus sign or a minus sign.
+ * @base: The number base to use. The maximum supported base is 16. If base is
+ *  given as 0, then the base of the string is automatically detected with the
+ *  conventional semantics - If it begins with 0x the number will be parsed as a
+ *  hexadecimal (case insensitive), if it otherwise begins with 0, it will be
+ *  parsed as an octal number. Otherwise it will be parsed as a decimal.
+ * @res: Where to write the result of the conversion on success.
+ *
+ * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
+ * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * be checked.
+ */
 static inline int __must_check kstrtol(const char *s, unsigned int base, long *res)
 {
 	/*
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index c3615eab0cc3..f78ae0c0c4e2 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -104,6 +104,22 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
 	return 0;
 }
 
+/**
+ * kstrtoull - convert a string to an unsigned long long
+ * @s: The start of the string. The string must be null-terminated, and may also
+ *  include a single newline before its terminating null. The first character
+ *  may also be a plus sign, but not a minus sign.
+ * @base: The number base to use. The maximum supported base is 16. If base is
+ *  given as 0, then the base of the string is automatically detected with the
+ *  conventional semantics - If it begins with 0x the number will be parsed as a
+ *  hexadecimal (case insensitive), if it otherwise begins with 0, it will be
+ *  parsed as an octal number. Otherwise it will be parsed as a decimal.
+ * @res: Where to write the result of the conversion on success.
+ *
+ * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
+ * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * be checked.
+ */
 int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
 {
 	if (s[0] == '+')
@@ -112,6 +128,22 @@ int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
 }
 EXPORT_SYMBOL(kstrtoull);
 
+/**
+ * kstrtoll - convert a string to a long long
+ * @s: The start of the string. The string must be null-terminated, and may also
+ *  include a single newline before its terminating null. The first character
+ *  may also be a plus sign or a minus sign.
+ * @base: The number base to use. The maximum supported base is 16. If base is
+ *  given as 0, then the base of the string is automatically detected with the
+ *  conventional semantics - If it begins with 0x the number will be parsed as a
+ *  hexadecimal (case insensitive), if it otherwise begins with 0, it will be
+ *  parsed as an octal number. Otherwise it will be parsed as a decimal.
+ * @res: Where to write the result of the conversion on success.
+ *
+ * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
+ * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * be checked.
+ */
 int kstrtoll(const char *s, unsigned int base, long long *res)
 {
 	unsigned long long tmp;
@@ -168,6 +200,22 @@ int _kstrtol(const char *s, unsigned int base, long *res)
 }
 EXPORT_SYMBOL(_kstrtol);
 
+/**
+ * kstrtouint - convert a string to an unsigned int
+ * @s: The start of the string. The string must be null-terminated, and may also
+ *  include a single newline before its terminating null. The first character
+ *  may also be a plus sign, but not a minus sign.
+ * @base: The number base to use. The maximum supported base is 16. If base is
+ *  given as 0, then the base of the string is automatically detected with the
+ *  conventional semantics - If it begins with 0x the number will be parsed as a
+ *  hexadecimal (case insensitive), if it otherwise begins with 0, it will be
+ *  parsed as an octal number. Otherwise it will be parsed as a decimal.
+ * @res: Where to write the result of the conversion on success.
+ *
+ * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
+ * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * be checked.
+ */
 int kstrtouint(const char *s, unsigned int base, unsigned int *res)
 {
 	unsigned long long tmp;
@@ -183,6 +231,22 @@ int kstrtouint(const char *s, unsigned int base, unsigned int *res)
 }
 EXPORT_SYMBOL(kstrtouint);
 
+/**
+ * kstrtoint - convert a string to an int
+ * @s: The start of the string. The string must be null-terminated, and may also
+ *  include a single newline before its terminating null. The first character
+ *  may also be a plus sign or a minus sign.
+ * @base: The number base to use. The maximum supported base is 16. If base is
+ *  given as 0, then the base of the string is automatically detected with the
+ *  conventional semantics - If it begins with 0x the number will be parsed as a
+ *  hexadecimal (case insensitive), if it otherwise begins with 0, it will be
+ *  parsed as an octal number. Otherwise it will be parsed as a decimal.
+ * @res: Where to write the result of the conversion on success.
+ *
+ * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
+ * Used as a replacement for the obsolete simple_strtoull. Return code must
+ * be checked.
+ */
 int kstrtoint(const char *s, unsigned int base, int *res)
 {
 	long long tmp;
-- 
cgit v1.2.3-55-g7522


From 992fb6e170639b0849bace8e49bf31bd37c4123c Mon Sep 17 00:00:00 2001
From: Oleg Nesterov
Date: Mon, 17 Dec 2012 16:03:07 -0800
Subject: ptrace: introduce PTRACE_O_EXITKILL

Ptrace jailers want to be sure that the tracee can never escape
from the control. However if the tracer dies unexpectedly the
tracee continues to run in potentially unsafe mode.

Add the new ptrace option PTRACE_O_EXITKILL. If the tracer exits
it sends SIGKILL to every tracee which has this bit set.

Note that the new option is not equal to the last-option << 1.  Because
currently all options have an event, and the new one starts the eventless
group.  It uses the random 20 bit, so we have the room for 12 more events,
but we can also add the new eventless options below this one.

Suggested by Amnon Shiloh.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Tested-by: Amnon Shiloh <u3557@miso.sublimeip.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: Chris Evans <scarybeasts@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ptrace.h      | 2 ++
 include/uapi/linux/ptrace.h | 5 ++++-
 kernel/ptrace.c             | 3 +++
 3 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index a89ff04bddd9..addfbe7c180e 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -32,6 +32,8 @@
 #define PT_TRACE_EXIT		PT_EVENT_FLAG(PTRACE_EVENT_EXIT)
 #define PT_TRACE_SECCOMP	PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP)
 
+#define PT_EXITKILL		(PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT)
+
 /* single stepping state bits (used on ARM and PA-RISC) */
 #define PT_SINGLESTEP_BIT	31
 #define PT_SINGLESTEP		(1<<PT_SINGLESTEP_BIT)
diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h
index 1ef6c056a9e4..022ab186a812 100644
--- a/include/uapi/linux/ptrace.h
+++ b/include/uapi/linux/ptrace.h
@@ -73,7 +73,10 @@
 #define PTRACE_O_TRACEEXIT	(1 << PTRACE_EVENT_EXIT)
 #define PTRACE_O_TRACESECCOMP	(1 << PTRACE_EVENT_SECCOMP)
 
-#define PTRACE_O_MASK		0x000000ff
+/* eventless options */
+#define PTRACE_O_EXITKILL	(1 << 20)
+
+#define PTRACE_O_MASK		(0x000000ff | PTRACE_O_EXITKILL)
 
 #include <asm/ptrace.h>
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1f5e55dda955..ec8118ab2a47 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -457,6 +457,9 @@ void exit_ptrace(struct task_struct *tracer)
 		return;
 
 	list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
+		if (unlikely(p->ptrace & PT_EXITKILL))
+			send_sig_info(SIGKILL, SEND_SIG_FORCED, p);
+
 		if (__ptrace_detach(tracer, p))
 			list_add(&p->ptrace_entry, &ptrace_dead);
 	}
-- 
cgit v1.2.3-55-g7522


From d740269867021faf4ce38a449353d2b986c34a67 Mon Sep 17 00:00:00 2001
From: Kees Cook
Date: Mon, 17 Dec 2012 16:03:20 -0800
Subject: exec: use -ELOOP for max recursion depth

To avoid an explosion of request_module calls on a chain of abusive
scripts, fail maximum recursion with -ELOOP instead of -ENOEXEC. As soon
as maximum recursion depth is hit, the error will fail all the way back
up the chain, aborting immediately.

This also has the side-effect of stopping the user's shell from attempting
to reexecute the top-level file as a shell script. As seen in the
dash source:

        if (cmd != path_bshell && errno == ENOEXEC) {
                *argv-- = cmd;
                *argv = cmd = path_bshell;
                goto repeat;
        }

The above logic was designed for running scripts automatically that lacked
the "#!" header, not to re-try failed recursion. On a legitimate -ENOEXEC,
things continue to behave as the shell expects.

Additionally, when tracking recursion, the binfmt handlers should not be
involved. The recursion being tracked is the depth of calls through
search_binary_handler(), so that function should be exclusively responsible
for tracking the depth.

Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: halfdog <me@halfdog.net>
Cc: P J P <ppandit@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_em86.c        |  1 -
 fs/binfmt_misc.c        |  6 ------
 fs/binfmt_script.c      |  4 +---
 fs/exec.c               | 10 +++++-----
 include/linux/binfmts.h |  2 --
 5 files changed, 6 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index 4e6cce57d113..037a3e2b045b 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -42,7 +42,6 @@ static int load_em86(struct linux_binprm *bprm)
 			return -ENOEXEC;
 	}
 
-	bprm->recursion_depth++; /* Well, the bang-shell is implicit... */
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index b0b70fbea06c..9be335fb8a7c 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -117,10 +117,6 @@ static int load_misc_binary(struct linux_binprm *bprm)
 	if (!enabled)
 		goto _ret;
 
-	retval = -ENOEXEC;
-	if (bprm->recursion_depth > BINPRM_MAX_RECURSION)
-		goto _ret;
-
 	/* to keep locking time low, we copy the interpreter string */
 	read_lock(&entries_lock);
 	fmt = check_file(bprm);
@@ -197,8 +193,6 @@ static int load_misc_binary(struct linux_binprm *bprm)
 	if (retval < 0)
 		goto _error;
 
-	bprm->recursion_depth++;
-
 	retval = search_binary_handler(bprm);
 	if (retval < 0)
 		goto _error;
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 8c954997e7f7..1610a91637e5 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -22,15 +22,13 @@ static int load_script(struct linux_binprm *bprm)
 	char interp[BINPRM_BUF_SIZE];
 	int retval;
 
-	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!') ||
-	    (bprm->recursion_depth > BINPRM_MAX_RECURSION))
+	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
 		return -ENOEXEC;
 	/*
 	 * This section does the #! interpretation.
 	 * Sorta complicated, but hopefully it will work.  -TYT
 	 */
 
-	bprm->recursion_depth++;
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
diff --git a/fs/exec.c b/fs/exec.c
index 721a29929511..d5eb9e605ffd 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1356,6 +1356,10 @@ int search_binary_handler(struct linux_binprm *bprm)
 	struct linux_binfmt *fmt;
 	pid_t old_pid, old_vpid;
 
+	/* This allows 4 levels of binfmt rewrites before failing hard. */
+	if (depth > 5)
+		return -ELOOP;
+
 	retval = security_bprm_check(bprm);
 	if (retval)
 		return retval;
@@ -1380,12 +1384,8 @@ int search_binary_handler(struct linux_binprm *bprm)
 			if (!try_module_get(fmt->module))
 				continue;
 			read_unlock(&binfmt_lock);
+			bprm->recursion_depth = depth + 1;
 			retval = fn(bprm);
-			/*
-			 * Restore the depth counter to its starting value
-			 * in this call, so we don't have to rely on every
-			 * load_binary function to restore it on return.
-			 */
 			bprm->recursion_depth = depth;
 			if (retval >= 0) {
 				if (depth == 0) {
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 2630c9b41a86..a4c2b565c835 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -54,8 +54,6 @@ struct linux_binprm {
 #define BINPRM_FLAGS_EXECFD_BIT 1
 #define BINPRM_FLAGS_EXECFD (1 << BINPRM_FLAGS_EXECFD_BIT)
 
-#define BINPRM_MAX_RECURSION 4
-
 /* Function parameter for binfmt->coredump */
 struct coredump_params {
 	siginfo_t *siginfo;
-- 
cgit v1.2.3-55-g7522


From a5ba911ec3792168530d35e16a8ec3b6fc60bcb5 Mon Sep 17 00:00:00 2001
From: Gao feng
Date: Mon, 17 Dec 2012 16:03:22 -0800
Subject: pidns: remove unused is_container_init()

Since commit 1cdcbec1a337 ("CRED: Neuter sys_capset()")
is_container_init() has no callers.

Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Cc: David Howells <dhowells@redhat.com>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Cc: James Morris <jmorris@namei.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h |  6 ------
 kernel/pid.c          | 15 ---------------
 2 files changed, 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b089c92c609b..9914c662ed7b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1778,12 +1778,6 @@ static inline int is_global_init(struct task_struct *tsk)
 	return tsk->pid == 1;
 }
 
-/*
- * is_container_init:
- * check whether in the task is init in its own pid namespace.
- */
-extern int is_container_init(struct task_struct *tsk);
-
 extern struct pid *cad_pid;
 
 extern void free_task(struct task_struct *tsk);
diff --git a/kernel/pid.c b/kernel/pid.c
index fd996c1ed9f8..a54a1123c7cf 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -81,21 +81,6 @@ struct pid_namespace init_pid_ns = {
 };
 EXPORT_SYMBOL_GPL(init_pid_ns);
 
-int is_container_init(struct task_struct *tsk)
-{
-	int ret = 0;
-	struct pid *pid;
-
-	rcu_read_lock();
-	pid = task_pid(tsk);
-	if (pid != NULL && pid->numbers[pid->level].nr == 1)
-		ret = 1;
-	rcu_read_unlock();
-
-	return ret;
-}
-EXPORT_SYMBOL(is_container_init);
-
 /*
  * Note: disable interrupts while the pidmap_lock is held as an
  * interrupt might come in and do read_lock(&tasklist_lock).
-- 
cgit v1.2.3-55-g7522


From 8529091e8e2ae25e0f4003086f619765ff255e4b Mon Sep 17 00:00:00 2001
From: Josh Triplett
Date: Mon, 17 Dec 2012 16:03:24 -0800
Subject: linux/compiler.h: add __must_hold macro for functions called with a
 lock held

linux/compiler.h has macros to denote functions that acquire or release
locks, but not to denote functions called with a lock held that return
with the lock still held.  Add a __must_hold macro to cover that case.

Signed-off-by: Josh Triplett <josh@joshtriplett.org>
Reported-by: Ed Cashin <ecashin@coraid.com>
Tested-by: Ed Cashin <ecashin@coraid.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index f430e4162f41..b121554f1fe2 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -10,6 +10,7 @@
 # define __force	__attribute__((force))
 # define __nocast	__attribute__((nocast))
 # define __iomem	__attribute__((noderef, address_space(2)))
+# define __must_hold(x)	__attribute__((context(x,1,1)))
 # define __acquires(x)	__attribute__((context(x,0,1)))
 # define __releases(x)	__attribute__((context(x,1,0)))
 # define __acquire(x)	__context__(x,1)
@@ -33,6 +34,7 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # define __chk_user_ptr(x) (void)0
 # define __chk_io_ptr(x) (void)0
 # define __builtin_warning(x, y...) (1)
+# define __must_hold(x)
 # define __acquires(x)
 # define __releases(x)
 # define __acquire(x) (void)0
-- 
cgit v1.2.3-55-g7522


From 496f2f93b1cc286f5a4f4f9acdc1e5314978683f Mon Sep 17 00:00:00 2001
From: Akinobu Mita
Date: Mon, 17 Dec 2012 16:04:23 -0800
Subject: random32: rename random32 to prandom

This renames all random32 functions to have 'prandom_' prefix as follows:

  void prandom_seed(u32 seed);	/* rename from srandom32() */
  u32 prandom_u32(void);		/* rename from random32() */
  void prandom_seed_state(struct rnd_state *state, u64 seed);
  				/* rename from prandom32_seed() */
  u32 prandom_u32_state(struct rnd_state *state);
  				/* rename from prandom32() */

The purpose of this renaming is to prevent some kernel developers from
assuming that prandom32() and random32() might imply that only
prandom32() was the one using a pseudo-random number generator by
prandom32's "p", and the result may be a very embarassing security
exposure.  This concern was expressed by Theodore Ts'o.

And furthermore, I'm going to introduce new functions for getting the
requested number of pseudo-random bytes.  If I continue to use both
prandom32 and random32 prefixes for these functions, the confusion
is getting worse.

As a result of this renaming, "prandom_" is the common prefix for
pseudo-random number library.

Currently, srandom32() and random32() are preserved because it is
difficult to rename too many users at once.

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Robert Love <robert.w.love@intel.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Cc: David Laight <david.laight@aculab.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Artem Bityutskiy <dedekind1@gmail.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/scsi/fcoe/fcoe_ctlr.c |  4 ++--
 include/linux/random.h        | 17 ++++++++++-----
 lib/interval_tree_test_main.c |  7 ++++---
 lib/random32.c                | 48 +++++++++++++++++++++----------------------
 lib/rbtree_test.c             |  6 +++---
 5 files changed, 45 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 2ebe03a4b51d..4a909d7cfde1 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -2144,7 +2144,7 @@ static void fcoe_ctlr_vn_restart(struct fcoe_ctlr *fip)
 	 */
 	port_id = fip->port_id;
 	if (fip->probe_tries)
-		port_id = prandom32(&fip->rnd_state) & 0xffff;
+		port_id = prandom_u32_state(&fip->rnd_state) & 0xffff;
 	else if (!port_id)
 		port_id = fip->lp->wwpn & 0xffff;
 	if (!port_id || port_id == 0xffff)
@@ -2169,7 +2169,7 @@ static void fcoe_ctlr_vn_restart(struct fcoe_ctlr *fip)
 static void fcoe_ctlr_vn_start(struct fcoe_ctlr *fip)
 {
 	fip->probe_tries = 0;
-	prandom32_seed(&fip->rnd_state, fip->lp->wwpn);
+	prandom_seed_state(&fip->rnd_state, fip->lp->wwpn);
 	fcoe_ctlr_vn_restart(fip);
 }
 
diff --git a/include/linux/random.h b/include/linux/random.h
index 6330ed47b38b..db6debc6649e 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -25,10 +25,17 @@ extern const struct file_operations random_fops, urandom_fops;
 unsigned int get_random_int(void);
 unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len);
 
-u32 random32(void);
-void srandom32(u32 seed);
+u32 prandom_u32(void);
+void prandom_seed(u32 seed);
 
-u32 prandom32(struct rnd_state *);
+/*
+ * These macros are preserved for backward compatibility and should be
+ * removed as soon as a transition is finished.
+ */
+#define random32() prandom_u32()
+#define srandom32(seed) prandom_seed(seed)
+
+u32 prandom_u32_state(struct rnd_state *);
 
 /*
  * Handle minimum values for seeds
@@ -39,11 +46,11 @@ static inline u32 __seed(u32 x, u32 m)
 }
 
 /**
- * prandom32_seed - set seed for prandom32().
+ * prandom_seed_state - set seed for prandom_u32_state().
  * @state: pointer to state structure to receive the seed.
  * @seed: arbitrary 64-bit value to use as a seed.
  */
-static inline void prandom32_seed(struct rnd_state *state, u64 seed)
+static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
 {
 	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
 
diff --git a/lib/interval_tree_test_main.c b/lib/interval_tree_test_main.c
index b25903987f7a..245900b98c8e 100644
--- a/lib/interval_tree_test_main.c
+++ b/lib/interval_tree_test_main.c
@@ -30,7 +30,8 @@ static void init(void)
 {
 	int i;
 	for (i = 0; i < NODES; i++) {
-		u32 a = prandom32(&rnd), b = prandom32(&rnd);
+		u32 a = prandom_u32_state(&rnd);
+		u32 b = prandom_u32_state(&rnd);
 		if (a <= b) {
 			nodes[i].start = a;
 			nodes[i].last = b;
@@ -40,7 +41,7 @@ static void init(void)
 		}
 	}
 	for (i = 0; i < SEARCHES; i++)
-		queries[i] = prandom32(&rnd);
+		queries[i] = prandom_u32_state(&rnd);
 }
 
 static int interval_tree_test_init(void)
@@ -51,7 +52,7 @@ static int interval_tree_test_init(void)
 
 	printk(KERN_ALERT "interval tree insert/remove");
 
-	prandom32_seed(&rnd, 3141592653589793238ULL);
+	prandom_seed_state(&rnd, 3141592653589793238ULL);
 	init();
 
 	time1 = get_cycles();
diff --git a/lib/random32.c b/lib/random32.c
index 938bde5876ac..d1830fade915 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -42,13 +42,13 @@
 static DEFINE_PER_CPU(struct rnd_state, net_rand_state);
 
 /**
- *	prandom32 - seeded pseudo-random number generator.
+ *	prandom_u32_state - seeded pseudo-random number generator.
  *	@state: pointer to state structure holding seeded state.
  *
  *	This is used for pseudo-randomness with no outside seeding.
- *	For more random results, use random32().
+ *	For more random results, use prandom_u32().
  */
-u32 prandom32(struct rnd_state *state)
+u32 prandom_u32_state(struct rnd_state *state)
 {
 #define TAUSWORTHE(s,a,b,c,d) ((s&c)<<d) ^ (((s <<a) ^ s)>>b)
 
@@ -58,32 +58,32 @@ u32 prandom32(struct rnd_state *state)
 
 	return (state->s1 ^ state->s2 ^ state->s3);
 }
-EXPORT_SYMBOL(prandom32);
+EXPORT_SYMBOL(prandom_u32_state);
 
 /**
- *	random32 - pseudo random number generator
+ *	prandom_u32 - pseudo random number generator
  *
  *	A 32 bit pseudo-random number is generated using a fast
  *	algorithm suitable for simulation. This algorithm is NOT
  *	considered safe for cryptographic use.
  */
-u32 random32(void)
+u32 prandom_u32(void)
 {
 	unsigned long r;
 	struct rnd_state *state = &get_cpu_var(net_rand_state);
-	r = prandom32(state);
+	r = prandom_u32_state(state);
 	put_cpu_var(state);
 	return r;
 }
-EXPORT_SYMBOL(random32);
+EXPORT_SYMBOL(prandom_u32);
 
 /**
- *	srandom32 - add entropy to pseudo random number generator
+ *	prandom_seed - add entropy to pseudo random number generator
  *	@seed: seed value
  *
- *	Add some additional seeding to the random32() pool.
+ *	Add some additional seeding to the prandom pool.
  */
-void srandom32(u32 entropy)
+void prandom_seed(u32 entropy)
 {
 	int i;
 	/*
@@ -95,13 +95,13 @@ void srandom32(u32 entropy)
 		state->s1 = __seed(state->s1 ^ entropy, 1);
 	}
 }
-EXPORT_SYMBOL(srandom32);
+EXPORT_SYMBOL(prandom_seed);
 
 /*
  *	Generate some initially weak seeding values to allow
- *	to start the random32() engine.
+ *	to start the prandom_u32() engine.
  */
-static int __init random32_init(void)
+static int __init prandom_init(void)
 {
 	int i;
 
@@ -114,22 +114,22 @@ static int __init random32_init(void)
 		state->s3 = __seed(LCG(state->s2), 15);
 
 		/* "warm it up" */
-		prandom32(state);
-		prandom32(state);
-		prandom32(state);
-		prandom32(state);
-		prandom32(state);
-		prandom32(state);
+		prandom_u32_state(state);
+		prandom_u32_state(state);
+		prandom_u32_state(state);
+		prandom_u32_state(state);
+		prandom_u32_state(state);
+		prandom_u32_state(state);
 	}
 	return 0;
 }
-core_initcall(random32_init);
+core_initcall(prandom_init);
 
 /*
  *	Generate better values after random number generator
  *	is fully initialized.
  */
-static int __init random32_reseed(void)
+static int __init prandom_reseed(void)
 {
 	int i;
 
@@ -143,8 +143,8 @@ static int __init random32_reseed(void)
 		state->s3 = __seed(seeds[2], 15);
 
 		/* mix it in */
-		prandom32(state);
+		prandom_u32_state(state);
 	}
 	return 0;
 }
-late_initcall(random32_reseed);
+late_initcall(prandom_reseed);
diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c
index d7f491a54579..af38aedbd874 100644
--- a/lib/rbtree_test.c
+++ b/lib/rbtree_test.c
@@ -96,8 +96,8 @@ static void init(void)
 {
 	int i;
 	for (i = 0; i < NODES; i++) {
-		nodes[i].key = prandom32(&rnd);
-		nodes[i].val = prandom32(&rnd);
+		nodes[i].key = prandom_u32_state(&rnd);
+		nodes[i].val = prandom_u32_state(&rnd);
 	}
 }
 
@@ -155,7 +155,7 @@ static int rbtree_test_init(void)
 
 	printk(KERN_ALERT "rbtree testing");
 
-	prandom32_seed(&rnd, 3141592653589793238ULL);
+	prandom_seed_state(&rnd, 3141592653589793238ULL);
 	init();
 
 	time1 = get_cycles();
-- 
cgit v1.2.3-55-g7522


From 6582c665d6b882dad8329e05749fbcf119f1ab88 Mon Sep 17 00:00:00 2001
From: Akinobu Mita
Date: Mon, 17 Dec 2012 16:04:25 -0800
Subject: prandom: introduce prandom_bytes() and prandom_bytes_state()

Add functions to get the requested number of pseudo-random bytes.

The difference from get_random_bytes() is that it generates pseudo-random
numbers by prandom_u32().  It doesn't consume the entropy pool, and the
sequence is reproducible if the same rnd_state is used.  So it is suitable
for generating random bytes for testing.

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Artem Bityutskiy <dedekind1@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Eilon Greenstein <eilong@broadcom.com>
Cc: David Laight <david.laight@aculab.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Robert Love <robert.w.love@intel.com>
Cc: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/random.h |  2 ++
 lib/random32.c         | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+)

(limited to 'include')

diff --git a/include/linux/random.h b/include/linux/random.h
index db6debc6649e..d9846088c2c5 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -26,6 +26,7 @@ unsigned int get_random_int(void);
 unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len);
 
 u32 prandom_u32(void);
+void prandom_bytes(void *buf, int nbytes);
 void prandom_seed(u32 seed);
 
 /*
@@ -36,6 +37,7 @@ void prandom_seed(u32 seed);
 #define srandom32(seed) prandom_seed(seed)
 
 u32 prandom_u32_state(struct rnd_state *);
+void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes);
 
 /*
  * Handle minimum values for seeds
diff --git a/lib/random32.c b/lib/random32.c
index d1830fade915..52280d5526be 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -77,6 +77,55 @@ u32 prandom_u32(void)
 }
 EXPORT_SYMBOL(prandom_u32);
 
+/*
+ *	prandom_bytes_state - get the requested number of pseudo-random bytes
+ *
+ *	@state: pointer to state structure holding seeded state.
+ *	@buf: where to copy the pseudo-random bytes to
+ *	@bytes: the requested number of bytes
+ *
+ *	This is used for pseudo-randomness with no outside seeding.
+ *	For more random results, use prandom_bytes().
+ */
+void prandom_bytes_state(struct rnd_state *state, void *buf, int bytes)
+{
+	unsigned char *p = buf;
+	int i;
+
+	for (i = 0; i < round_down(bytes, sizeof(u32)); i += sizeof(u32)) {
+		u32 random = prandom_u32_state(state);
+		int j;
+
+		for (j = 0; j < sizeof(u32); j++) {
+			p[i + j] = random;
+			random >>= BITS_PER_BYTE;
+		}
+	}
+	if (i < bytes) {
+		u32 random = prandom_u32_state(state);
+
+		for (; i < bytes; i++) {
+			p[i] = random;
+			random >>= BITS_PER_BYTE;
+		}
+	}
+}
+EXPORT_SYMBOL(prandom_bytes_state);
+
+/**
+ *	prandom_bytes - get the requested number of pseudo-random bytes
+ *	@buf: where to copy the pseudo-random bytes to
+ *	@bytes: the requested number of bytes
+ */
+void prandom_bytes(void *buf, int bytes)
+{
+	struct rnd_state *state = &get_cpu_var(net_rand_state);
+
+	prandom_bytes_state(state, buf, bytes);
+	put_cpu_var(state);
+}
+EXPORT_SYMBOL(prandom_bytes);
+
 /**
  *	prandom_seed - add entropy to pseudo random number generator
  *	@seed: seed value
-- 
cgit v1.2.3-55-g7522


From 55985dd72ab27b47530dcc8bdddd28b69f4abe8b Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov
Date: Mon, 17 Dec 2012 16:04:55 -0800
Subject: procfs: add ability to plug in auxiliary fdinfo providers

This patch brings ability to print out auxiliary data associated with
file in procfs interface /proc/pid/fdinfo/fd.

In particular further patches make eventfd, evenpoll, signalfd and
fsnotify to print additional information complete enough to restore
these objects after checkpoint.

To simplify the code we add show_fdinfo callback inside struct
file_operations (as Al and Pavel are proposing).

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrey Vagin <avagin@openvz.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: James Bottomley <jbottomley@parallels.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Matthew Helsley <matt.helsley@gmail.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@onelan.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/fd.c       | 2 ++
 include/linux/fs.h | 4 ++--
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index f28a875f8779..d7a4a28ef630 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -50,6 +50,8 @@ static int seq_show(struct seq_file *m, void *v)
 	if (!ret) {
                 seq_printf(m, "pos:\t%lli\nflags:\t0%o\n",
 			   (long long)file->f_pos, f_flags);
+		if (file->f_op->show_fdinfo)
+			ret = file->f_op->show_fdinfo(m, file);
 		fput(file);
 	}
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 029552ff774c..5abf703d06ba 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -44,6 +44,7 @@ struct vm_area_struct;
 struct vfsmount;
 struct cred;
 struct swap_info_struct;
+struct seq_file;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -1543,6 +1544,7 @@ struct file_operations {
 	int (*setlease)(struct file *, long, struct file_lock **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
+	int (*show_fdinfo)(struct seq_file *m, struct file *f);
 };
 
 struct inode_operations {
@@ -1578,8 +1580,6 @@ struct inode_operations {
 			   umode_t create_mode, int *opened);
 } ____cacheline_aligned;
 
-struct seq_file;
-
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      unsigned long nr_segs, unsigned long fast_segs,
 			      struct iovec *fast_pointer,
-- 
cgit v1.2.3-55-g7522


From 138d22b58696c506799f8de759804083ff9effae Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov
Date: Mon, 17 Dec 2012 16:05:02 -0800
Subject: fs, epoll: add procfs fdinfo helper

This allows us to print out eventpoll target file descriptor, events and
data, the /proc/pid/fdinfo/fd consists of

 | pos:	0
 | flags:	02
 | tfd:        5 events:       1d data: ffffffffffffffff enabled: 1

[avagin@: fix for unitialized ret variable]

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrey Vagin <avagin@openvz.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: James Bottomley <jbottomley@parallels.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Matthew Helsley <matt.helsley@gmail.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@onelan.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/eventpoll.c          | 28 ++++++++++++++++++++++++++++
 fs/proc/array.c         |  2 +-
 fs/signalfd.c           | 18 ++++++++++++++++++
 include/linux/proc_fs.h |  3 +++
 4 files changed, 50 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index cd96649bfe62..be56b21435f8 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -38,6 +38,8 @@
 #include <asm/io.h>
 #include <asm/mman.h>
 #include <linux/atomic.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 
 /*
  * LOCKING:
@@ -783,8 +785,34 @@ static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
 	return pollflags != -1 ? pollflags : 0;
 }
 
+#ifdef CONFIG_PROC_FS
+static int ep_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct eventpoll *ep = f->private_data;
+	struct rb_node *rbp;
+	int ret = 0;
+
+	mutex_lock(&ep->mtx);
+	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+		struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
+
+		ret = seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
+				 epi->ffd.fd, epi->event.events,
+				 (long long)epi->event.data);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&ep->mtx);
+
+	return ret;
+}
+#endif
+
 /* File callbacks that implement the eventpoll file behaviour */
 static const struct file_operations eventpoll_fops = {
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= ep_show_fdinfo,
+#endif
 	.release	= ep_eventpoll_release,
 	.poll		= ep_eventpoll_poll,
 	.llseek		= noop_llseek,
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 439544fec388..060a56a91278 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -220,7 +220,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 	seq_putc(m, '\n');
 }
 
-static void render_sigset_t(struct seq_file *m, const char *header,
+void render_sigset_t(struct seq_file *m, const char *header,
 				sigset_t *set)
 {
 	int i;
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 8bee4e570911..b53486961735 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -29,6 +29,7 @@
 #include <linux/anon_inodes.h>
 #include <linux/signalfd.h>
 #include <linux/syscalls.h>
+#include <linux/proc_fs.h>
 
 void signalfd_cleanup(struct sighand_struct *sighand)
 {
@@ -227,7 +228,24 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count,
 	return total ? total: ret;
 }
 
+#ifdef CONFIG_PROC_FS
+static int signalfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct signalfd_ctx *ctx = f->private_data;
+	sigset_t sigmask;
+
+	sigmask = ctx->sigmask;
+	signotset(&sigmask);
+	render_sigset_t(m, "sigmask:\t", &sigmask);
+
+	return 0;
+}
+#endif
+
 static const struct file_operations signalfd_fops = {
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= signalfd_show_fdinfo,
+#endif
 	.release	= signalfd_release,
 	.poll		= signalfd_poll,
 	.read		= signalfd_read,
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 3fd2e871ff1b..b4f70f0a9a48 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -290,4 +290,7 @@ static inline struct net *PDE_NET(struct proc_dir_entry *pde)
 	return pde->parent->data;
 }
 
+#include <linux/signal.h>
+
+void render_sigset_t(struct seq_file *m, const char *header, sigset_t *set);
 #endif /* _LINUX_PROC_FS_H */
-- 
cgit v1.2.3-55-g7522


From 711c7bf9914060d7aaf3c1a15f38094a5d5e748f Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov
Date: Mon, 17 Dec 2012 16:05:08 -0800
Subject: fs, exportfs: add exportfs_encode_inode_fh() helper

We will need this helper in the next patch to provide a file handle for
inotify marks in /proc/pid/fdinfo output.

The patch is rather providing the way to use inodes directly when dentry
is not available (like in case of inotify system).

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrey Vagin <avagin@openvz.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: James Bottomley <jbottomley@parallels.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Matthew Helsley <matt.helsley@gmail.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@onelan.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/exportfs/expfs.c      | 19 ++++++++++++++-----
 include/linux/exportfs.h |  2 ++
 2 files changed, 16 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 10f137381ac7..606bb074c501 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -341,10 +341,21 @@ static int export_encode_fh(struct inode *inode, struct fid *fid,
 	return type;
 }
 
+int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
+			     int *max_len, struct inode *parent)
+{
+	const struct export_operations *nop = inode->i_sb->s_export_op;
+
+	if (nop && nop->encode_fh)
+		return nop->encode_fh(inode, fid->raw, max_len, parent);
+
+	return export_encode_fh(inode, fid, max_len, parent);
+}
+EXPORT_SYMBOL_GPL(exportfs_encode_inode_fh);
+
 int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len,
 		int connectable)
 {
-	const struct export_operations *nop = dentry->d_sb->s_export_op;
 	int error;
 	struct dentry *p = NULL;
 	struct inode *inode = dentry->d_inode, *parent = NULL;
@@ -357,10 +368,8 @@ int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len,
 		 */
 		parent = p->d_inode;
 	}
-	if (nop && nop->encode_fh)
-		error = nop->encode_fh(inode, fid->raw, max_len, parent);
-	else
-		error = export_encode_fh(inode, fid, max_len, parent);
+
+	error = exportfs_encode_inode_fh(inode, fid, max_len, parent);
 	dput(p);
 
 	return error;
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 12291a7ee275..c7e6b6392ab8 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -177,6 +177,8 @@ struct export_operations {
 	int (*commit_metadata)(struct inode *inode);
 };
 
+extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
+				    int *max_len, struct inode *parent);
 extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid,
 	int *max_len, int connectable);
 extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
-- 
cgit v1.2.3-55-g7522


From ebb351cf78ee6bf3262e6b4b6906f456c05e6d5e Mon Sep 17 00:00:00 2001
From: Roger Pau Monne
Date: Tue, 4 Dec 2012 15:21:53 +0100
Subject: llist/xen-blkfront: implement safe version of llist_for_each_entry

Implement a safe version of llist_for_each_entry, and use it in
blkif_free. Previously grants where freed while iterating the list,
which lead to dereferences when trying to fetch the next item.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Acked-by:  Andrew Morton <akpm@linux-foundation.org>
[v2: Move the llist_for_each_entry_safe in llist.h]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/block/xen-blkfront.c |  3 ++-
 include/linux/llist.h        | 25 +++++++++++++++++++++++++
 2 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 96e9b00db081..cfdb033c7107 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -792,6 +792,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 {
 	struct llist_node *all_gnts;
 	struct grant *persistent_gnt;
+	struct llist_node *n;
 
 	/* Prevent new requests being issued until we fix things up. */
 	spin_lock_irq(&info->io_lock);
@@ -804,7 +805,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 	/* Remove all persistent grants */
 	if (info->persistent_gnts_c) {
 		all_gnts = llist_del_all(&info->persistent_gnts);
-		llist_for_each_entry(persistent_gnt, all_gnts, node) {
+		llist_for_each_entry_safe(persistent_gnt, n, all_gnts, node) {
 			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
 			__free_page(pfn_to_page(persistent_gnt->pfn));
 			kfree(persistent_gnt);
diff --git a/include/linux/llist.h b/include/linux/llist.h
index a5199f6d0e82..d0ab98f73d38 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -124,6 +124,31 @@ static inline void init_llist_head(struct llist_head *list)
 	     &(pos)->member != NULL;					\
 	     (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member))
 
+/**
+ * llist_for_each_entry_safe - iterate safely against remove over some entries
+ * of lock-less list of given type.
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as a temporary storage.
+ * @node:	the fist entry of deleted list entries.
+ * @member:	the name of the llist_node with the struct.
+ *
+ * In general, some entries of the lock-less list can be traversed
+ * safely only after being removed from list, so start with an entry
+ * instead of list head. This variant allows removal of entries
+ * as we iterate.
+ *
+ * If being used on entries deleted from lock-less list directly, the
+ * traverse order is from the newest to the oldest added entry.  If
+ * you want to traverse from the oldest to the newest, you must
+ * reverse the order by yourself before traversing.
+ */
+#define llist_for_each_entry_safe(pos, n, node, member)		\
+	for ((pos) = llist_entry((node), typeof(*(pos)), member),	\
+	     (n) = (pos)->member.next;					\
+	     &(pos)->member != NULL;					\
+	     (pos) = llist_entry(n, typeof(*(pos)), member),		\
+	     (n) = (&(pos)->member != NULL) ? (pos)->member.next : NULL)
+
 /**
  * llist_empty - tests whether a lock-less list is empty
  * @head:	the list to test
-- 
cgit v1.2.3-55-g7522


From cc31fd9c4f8fc466ec8488d617150e751f643903 Mon Sep 17 00:00:00 2001
From: Wei Liu
Date: Thu, 13 Dec 2012 15:31:35 +0000
Subject: xen: Add EVTCHNOP_reset in Xen interface header files.

Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 include/xen/interface/event_channel.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/xen/interface/event_channel.h b/include/xen/interface/event_channel.h
index 2090881c3650..f4942921e202 100644
--- a/include/xen/interface/event_channel.h
+++ b/include/xen/interface/event_channel.h
@@ -177,6 +177,19 @@ struct evtchn_unmask {
 	evtchn_port_t port;
 };
 
+/*
+ * EVTCHNOP_reset: Close all event channels associated with specified domain.
+ * NOTES:
+ *  1. <dom> may be specified as DOMID_SELF.
+ *  2. Only a sufficiently-privileged domain may specify other than DOMID_SELF.
+ */
+#define EVTCHNOP_reset		 10
+struct evtchn_reset {
+	/* IN parameters. */
+	domid_t dom;
+};
+typedef struct evtchn_reset evtchn_reset_t;
+
 struct evtchn_op {
 	uint32_t cmd; /* EVTCHNOP_* */
 	union {
-- 
cgit v1.2.3-55-g7522


From afc59400d6c65bad66d4ad0b2daf879cbff8e23e Mon Sep 17 00:00:00 2001
From: J. Bruce Fields
Date: Mon, 10 Dec 2012 18:01:37 -0500
Subject: nfsd4: cleanup: replace rq_resused count by rq_next_page pointer

It may be a matter of personal taste, but I find this makes the code
clearer.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs2acl.c                       |  2 +-
 fs/nfsd/nfs3acl.c                       |  2 +-
 fs/nfsd/nfs3proc.c                      |  6 +++---
 fs/nfsd/nfs3xdr.c                       | 33 ++++++++++++++++-----------------
 fs/nfsd/nfs4xdr.c                       | 24 ++++++++++++------------
 fs/nfsd/nfsxdr.c                        | 11 ++++++-----
 fs/nfsd/vfs.c                           | 18 ++++++++----------
 include/linux/sunrpc/svc.h              |  6 +++---
 net/sunrpc/svc.c                        |  2 +-
 net/sunrpc/svcsock.c                    |  2 ++
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 10 +++++-----
 net/sunrpc/xprtrdma/svc_rdma_sendto.c   |  4 +++-
 12 files changed, 61 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index b314888825d5..9170861c804a 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -253,7 +253,7 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 		(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,
 		(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
 	while (w > 0) {
-		if (!rqstp->rq_respages[rqstp->rq_resused++])
+		if (!*(rqstp->rq_next_page++))
 			return 0;
 		w -= PAGE_SIZE;
 	}
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index a596e9d987e4..9cbc1a841f87 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -184,7 +184,7 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 			(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,
 			(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
 		while (w > 0) {
-			if (!rqstp->rq_respages[rqstp->rq_resused++])
+			if (!*(rqstp->rq_next_page++))
 				return 0;
 			w -= PAGE_SIZE;
 		}
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 97d90d1c8608..1fc02dfdc5c4 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -460,7 +460,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
 	__be32	nfserr;
 	int	count = 0;
 	loff_t	offset;
-	int	i;
+	struct page **p;
 	caddr_t	page_addr = NULL;
 
 	dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n",
@@ -484,8 +484,8 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
 				     &resp->common,
 				     nfs3svc_encode_entry_plus);
 	memcpy(resp->verf, argp->verf, 8);
-	for (i=1; i<rqstp->rq_resused ; i++) {
-		page_addr = page_address(rqstp->rq_respages[i]);
+	for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
+		page_addr = page_address(*p);
 
 		if (((caddr_t)resp->buffer >= page_addr) &&
 		    ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 2b8618de6c27..324c0baf7cda 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -325,7 +325,7 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_readargs *args)
 {
 	unsigned int len;
-	int v,pn;
+	int v;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
 	if (!(p = decode_fh(p, &args->fh)))
@@ -340,8 +340,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 	/* set up the kvec */
 	v=0;
 	while (len > 0) {
-		pn = rqstp->rq_resused++;
-		rqstp->rq_vec[v].iov_base = page_address(rqstp->rq_respages[pn]);
+		struct page *p = *(rqstp->rq_next_page++);
+
+		rqstp->rq_vec[v].iov_base = page_address(p);
 		rqstp->rq_vec[v].iov_len = len < PAGE_SIZE? len : PAGE_SIZE;
 		len -= rqstp->rq_vec[v].iov_len;
 		v++;
@@ -463,8 +464,7 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 	len = ntohl(*p++);
 	if (len == 0 || len > NFS3_MAXPATHLEN || len >= PAGE_SIZE)
 		return 0;
-	args->tname = new =
-		page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+	args->tname = new = page_address(*(rqstp->rq_next_page++));
 	args->tlen = len;
 	/* first copy and check from the first page */
 	old = (char*)p;
@@ -535,8 +535,7 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
 {
 	if (!(p = decode_fh(p, &args->fh)))
 		return 0;
-	args->buffer =
-		page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+	args->buffer = page_address(*(rqstp->rq_next_page++));
 
 	return xdr_argsize_check(rqstp, p);
 }
@@ -567,8 +566,7 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
 	if (args->count > PAGE_SIZE)
 		args->count = PAGE_SIZE;
 
-	args->buffer =
-		page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+	args->buffer = page_address(*(rqstp->rq_next_page++));
 
 	return xdr_argsize_check(rqstp, p);
 }
@@ -577,7 +575,7 @@ int
 nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_readdirargs *args)
 {
-	int len, pn;
+	int len;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
 	if (!(p = decode_fh(p, &args->fh)))
@@ -592,9 +590,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
 	args->count = len;
 
 	while (len > 0) {
-		pn = rqstp->rq_resused++;
+		struct page *p = *(rqstp->rq_next_page++);
 		if (!args->buffer)
-			args->buffer = page_address(rqstp->rq_respages[pn]);
+			args->buffer = page_address(p);
 		len -= PAGE_SIZE;
 	}
 
@@ -880,7 +878,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 		       					common);
 	__be32		*p = cd->buffer;
 	caddr_t		curr_page_addr = NULL;
-	int		pn;		/* current page number */
+	struct page **	page;
 	int		slen;		/* string (name) length */
 	int		elen;		/* estimated entry length in words */
 	int		num_entry_words = 0;	/* actual number of words */
@@ -917,8 +915,9 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 	}
 
 	/* determine which page in rq_respages[] we are currently filling */
-	for (pn=1; pn < cd->rqstp->rq_resused; pn++) {
-		curr_page_addr = page_address(cd->rqstp->rq_respages[pn]);
+	for (page = cd->rqstp->rq_respages + 1;
+				page < cd->rqstp->rq_next_page; page++) {
+		curr_page_addr = page_address(*page);
 
 		if (((caddr_t)cd->buffer >= curr_page_addr) &&
 		    ((caddr_t)cd->buffer <  curr_page_addr + PAGE_SIZE))
@@ -933,14 +932,14 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 		if (plus)
 			p = encode_entryplus_baggage(cd, p, name, namlen);
 		num_entry_words = p - cd->buffer;
-	} else if (cd->rqstp->rq_respages[pn+1] != NULL) {
+	} else if (*(page+1) != NULL) {
 		/* temporarily encode entry into next page, then move back to
 		 * current and next page in rq_respages[] */
 		__be32 *p1, *tmp;
 		int len1, len2;
 
 		/* grab next page for temporary storage of entry */
-		p1 = tmp = page_address(cd->rqstp->rq_respages[pn+1]);
+		p1 = tmp = page_address(*(page+1));
 
 		p1 = encode_entry_baggage(cd, p1, name, namlen, ino);
 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index d7a3be5ab777..0dc11586682f 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2906,7 +2906,8 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_read *read)
 {
 	u32 eof;
-	int v, pn;
+	int v;
+	struct page *page;
 	unsigned long maxcount; 
 	long len;
 	__be32 *p;
@@ -2925,16 +2926,15 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 	len = maxcount;
 	v = 0;
 	while (len > 0) {
-		pn = resp->rqstp->rq_resused;
-		if (!resp->rqstp->rq_respages[pn]) { /* ran out of pages */
+		page = *(resp->rqstp->rq_next_page);
+		if (!page) { /* ran out of pages */
 			maxcount -= len;
 			break;
 		}
-		resp->rqstp->rq_vec[v].iov_base =
-			page_address(resp->rqstp->rq_respages[pn]);
+		resp->rqstp->rq_vec[v].iov_base = page_address(page);
 		resp->rqstp->rq_vec[v].iov_len =
 			len < PAGE_SIZE ? len : PAGE_SIZE;
-		resp->rqstp->rq_resused++;
+		resp->rqstp->rq_next_page++;
 		v++;
 		len -= PAGE_SIZE;
 	}
@@ -2980,10 +2980,10 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
 		return nfserr;
 	if (resp->xbuf->page_len)
 		return nfserr_resource;
-	if (!resp->rqstp->rq_respages[resp->rqstp->rq_resused])
+	if (!*resp->rqstp->rq_next_page)
 		return nfserr_resource;
 
-	page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]);
+	page = page_address(*(resp->rqstp->rq_next_page++));
 
 	maxcount = PAGE_SIZE;
 	RESERVE_SPACE(4);
@@ -3031,7 +3031,7 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
 		return nfserr;
 	if (resp->xbuf->page_len)
 		return nfserr_resource;
-	if (!resp->rqstp->rq_respages[resp->rqstp->rq_resused])
+	if (!*resp->rqstp->rq_next_page)
 		return nfserr_resource;
 
 	RESERVE_SPACE(NFS4_VERIFIER_SIZE);
@@ -3059,7 +3059,7 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
 		goto err_no_verf;
 	}
 
-	page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]);
+	page = page_address(*(resp->rqstp->rq_next_page++));
 	readdir->common.err = 0;
 	readdir->buflen = maxcount;
 	readdir->buffer = page;
@@ -3082,8 +3082,8 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
 	p = readdir->buffer;
 	*p++ = 0;	/* no more entries */
 	*p++ = htonl(readdir->common.err == nfserr_eof);
-	resp->xbuf->page_len = ((char*)p) - (char*)page_address(
-		resp->rqstp->rq_respages[resp->rqstp->rq_resused-1]);
+	resp->xbuf->page_len = ((char*)p) -
+		(char*)page_address(*(resp->rqstp->rq_next_page-1));
 
 	/* Use rest of head for padding and remaining ops: */
 	resp->xbuf->tail[0].iov_base = tailbase;
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 65ec595e2226..979b42106979 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -246,7 +246,7 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd_readargs *args)
 {
 	unsigned int len;
-	int v,pn;
+	int v;
 	if (!(p = decode_fh(p, &args->fh)))
 		return 0;
 
@@ -262,8 +262,9 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 	 */
 	v=0;
 	while (len > 0) {
-		pn = rqstp->rq_resused++;
-		rqstp->rq_vec[v].iov_base = page_address(rqstp->rq_respages[pn]);
+		struct page *p = *(rqstp->rq_next_page++);
+
+		rqstp->rq_vec[v].iov_base = page_address(p);
 		rqstp->rq_vec[v].iov_len = len < PAGE_SIZE?len:PAGE_SIZE;
 		len -= rqstp->rq_vec[v].iov_len;
 		v++;
@@ -355,7 +356,7 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli
 {
 	if (!(p = decode_fh(p, &args->fh)))
 		return 0;
-	args->buffer = page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+	args->buffer = page_address(*(rqstp->rq_next_page++));
 
 	return xdr_argsize_check(rqstp, p);
 }
@@ -396,7 +397,7 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
 	if (args->count > PAGE_SIZE)
 		args->count = PAGE_SIZE;
 
-	args->buffer = page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+	args->buffer = page_address(*(rqstp->rq_next_page++));
 
 	return xdr_argsize_check(rqstp, p);
 }
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index b31e46eeb026..f0a6d88d7fff 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -886,7 +886,7 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		  struct splice_desc *sd)
 {
 	struct svc_rqst *rqstp = sd->u.data;
-	struct page **pp = rqstp->rq_respages + rqstp->rq_resused;
+	struct page **pp = rqstp->rq_next_page;
 	struct page *page = buf->page;
 	size_t size;
 
@@ -894,17 +894,15 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 
 	if (rqstp->rq_res.page_len == 0) {
 		get_page(page);
-		put_page(*pp);
-		*pp = page;
-		rqstp->rq_resused++;
+		put_page(*rqstp->rq_next_page);
+		*(rqstp->rq_next_page++) = page;
 		rqstp->rq_res.page_base = buf->offset;
 		rqstp->rq_res.page_len = size;
 	} else if (page != pp[-1]) {
 		get_page(page);
-		if (*pp)
-			put_page(*pp);
-		*pp = page;
-		rqstp->rq_resused++;
+		if (*rqstp->rq_next_page)
+			put_page(*rqstp->rq_next_page);
+		*(rqstp->rq_next_page++) = page;
 		rqstp->rq_res.page_len += size;
 	} else
 		rqstp->rq_res.page_len += size;
@@ -936,8 +934,8 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 			.u.data		= rqstp,
 		};
 
-		WARN_ON_ONCE(rqstp->rq_resused != 1);
-		rqstp->rq_resused = 1;
+		WARN_ON_ONCE(rqstp->rq_next_page != rqstp->rq_respages + 1);
+		rqstp->rq_next_page = rqstp->rq_respages + 1;
 		host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
 	} else {
 		oldfs = get_fs();
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index d83db800fe02..676ddf53b3ee 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -243,6 +243,7 @@ struct svc_rqst {
 	struct page *		rq_pages[RPCSVC_MAXPAGES];
 	struct page *		*rq_respages;	/* points into rq_pages */
 	int			rq_resused;	/* number of pages used for result */
+	struct page *		*rq_next_page; /* next reply page to use */
 
 	struct kvec		rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */
 
@@ -338,9 +339,8 @@ xdr_ressize_check(struct svc_rqst *rqstp, __be32 *p)
 
 static inline void svc_free_res_pages(struct svc_rqst *rqstp)
 {
-	while (rqstp->rq_resused) {
-		struct page **pp = (rqstp->rq_respages +
-				    --rqstp->rq_resused);
+	while (rqstp->rq_next_page != rqstp->rq_respages) {
+		struct page **pp = --rqstp->rq_next_page;
 		if (*pp) {
 			put_page(*pp);
 			*pp = NULL;
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 529400d59755..c6abf1a6ba95 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1297,7 +1297,7 @@ svc_process(struct svc_rqst *rqstp)
 	 * Setup response xdr_buf.
 	 * Initially it has just one page
 	 */
-	rqstp->rq_resused = 1;
+	rqstp->rq_next_page = &rqstp->rq_respages[1];
 	resv->iov_base = page_address(rqstp->rq_respages[0]);
 	resv->iov_len = 0;
 	rqstp->rq_res.pages = rqstp->rq_respages + 1;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index d8e5adfeac30..dcd5669c5154 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -601,6 +601,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 		rqstp->rq_respages = rqstp->rq_pages + 1 +
 			DIV_ROUND_UP(rqstp->rq_arg.page_len, PAGE_SIZE);
 	}
+	rqstp->rq_next_page = rqstp->rq_respages+1;
 
 	if (serv->sv_stats)
 		serv->sv_stats->netudpcnt++;
@@ -1066,6 +1067,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 						svsk->sk_datalen + want);
 
 	rqstp->rq_respages = &rqstp->rq_pages[pnum];
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
 	/* Now receive data */
 	len = svc_partial_recvfrom(rqstp, vec, pnum, want, base);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 41cb63b623df..0ce75524ed21 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -521,11 +521,11 @@ next_sge:
 		rqstp->rq_pages[ch_no] = NULL;
 
 	/*
-	 * Detach res pages. svc_release must see a resused count of
-	 * zero or it will attempt to put them.
+	 * Detach res pages. If svc_release sees any it will attempt to
+	 * put them.
 	 */
-	while (rqstp->rq_resused)
-		rqstp->rq_respages[--rqstp->rq_resused] = NULL;
+	while (rqstp->rq_next_page != rqstp->rq_respages)
+		*(--rqstp->rq_next_page) = NULL;
 
 	return err;
 }
@@ -550,7 +550,7 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
 
 	/* rq_respages starts after the last arg page */
 	rqstp->rq_respages = &rqstp->rq_arg.pages[page_no];
-	rqstp->rq_resused = 0;
+	rqstp->rq_next_page = &rqstp->rq_arg.pages[page_no];
 
 	/* Rebuild rq_arg head and tail. */
 	rqstp->rq_arg.head[0] = head->arg.head[0];
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 42eb7ba0b903..c1d124dc772b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -548,6 +548,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	int sge_no;
 	int sge_bytes;
 	int page_no;
+	int pages;
 	int ret;
 
 	/* Post a recv buffer to handle another request. */
@@ -611,7 +612,8 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	 * respages array. They are our pages until the I/O
 	 * completes.
 	 */
-	for (page_no = 0; page_no < rqstp->rq_resused; page_no++) {
+	pages = rqstp->rq_next_page - rqstp->rq_respages;
+	for (page_no = 0; page_no < pages; page_no++) {
 		ctxt->pages[page_no+1] = rqstp->rq_respages[page_no];
 		ctxt->count++;
 		rqstp->rq_respages[page_no] = NULL;
-- 
cgit v1.2.3-55-g7522


From 06ca287dbac9cc19d04ac2901b8c4882c03795ff Mon Sep 17 00:00:00 2001
From: Rusty Russell
Date: Tue, 16 Oct 2012 23:56:14 +1030
Subject: virtio: move queue_index and num_free fields into core struct
 virtqueue.

They're generic concepts, so hoist them.  This also avoids accessor
functions (though kept around for merge with DaveM's net tree).

This goes even further than Jason Wang's 17bb6d4088 patch
("virtio-ring: move queue_index to vring_virtqueue") which moved the
queue_index from the specific transport.

Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/virtio/virtio_mmio.c |  4 ++--
 drivers/virtio/virtio_pci.c  |  6 ++----
 drivers/virtio/virtio_ring.c | 34 +++++++++++-----------------------
 include/linux/virtio.h       | 14 +++++++++++++-
 4 files changed, 28 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 6b1b7e184939..5a0e1d32ce13 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -225,7 +225,7 @@ static void vm_notify(struct virtqueue *vq)
 
 	/* We write the queue's selector into the notification register to
 	 * signal the other end */
-	writel(virtqueue_get_queue_index(vq), vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+	writel(vq->index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
 }
 
 /* Notify all virtqueues on an interrupt. */
@@ -266,7 +266,7 @@ static void vm_del_vq(struct virtqueue *vq)
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
 	struct virtio_mmio_vq_info *info = vq->priv;
 	unsigned long flags, size;
-	unsigned int index = virtqueue_get_queue_index(vq);
+	unsigned int index = vq->index;
 
 	spin_lock_irqsave(&vm_dev->lock, flags);
 	list_del(&info->node);
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index b59237c1d540..e3ecc94591ad 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -203,8 +203,7 @@ static void vp_notify(struct virtqueue *vq)
 
 	/* we write the queue's selector into the notification register to
 	 * signal the other end */
-	iowrite16(virtqueue_get_queue_index(vq),
-		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
+	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
 }
 
 /* Handle a configuration change: Tell driver if it wants to know. */
@@ -479,8 +478,7 @@ static void vp_del_vq(struct virtqueue *vq)
 	list_del(&info->node);
 	spin_unlock_irqrestore(&vp_dev->lock, flags);
 
-	iowrite16(virtqueue_get_queue_index(vq),
-		vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
 
 	if (vp_dev->msix_enabled) {
 		iowrite16(VIRTIO_MSI_NO_VECTOR,
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 286c30cb393d..33a4ce009bcc 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -93,8 +93,6 @@ struct vring_virtqueue
 	/* Host publishes avail event idx */
 	bool event;
 
-	/* Number of free buffers */
-	unsigned int num_free;
 	/* Head of free buffer list. */
 	unsigned int free_head;
 	/* Number we've added since last sync. */
@@ -106,9 +104,6 @@ struct vring_virtqueue
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	void (*notify)(struct virtqueue *vq);
 
-	/* Index of the queue */
-	int queue_index;
-
 #ifdef DEBUG
 	/* They're supposed to lock for us. */
 	unsigned int in_use;
@@ -167,7 +162,7 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	desc[i-1].next = 0;
 
 	/* We're about to use a buffer */
-	vq->num_free--;
+	vq->vq.num_free--;
 
 	/* Use a single buffer which doesn't continue */
 	head = vq->free_head;
@@ -181,13 +176,6 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	return head;
 }
 
-int virtqueue_get_queue_index(struct virtqueue *_vq)
-{
-	struct vring_virtqueue *vq = to_vvq(_vq);
-	return vq->queue_index;
-}
-EXPORT_SYMBOL_GPL(virtqueue_get_queue_index);
-
 /**
  * virtqueue_add_buf - expose buffer to other end
  * @vq: the struct virtqueue we're talking about.
@@ -235,7 +223,7 @@ int virtqueue_add_buf(struct virtqueue *_vq,
 
 	/* If the host supports indirect descriptor tables, and we have multiple
 	 * buffers, then go indirect. FIXME: tune this threshold */
-	if (vq->indirect && (out + in) > 1 && vq->num_free) {
+	if (vq->indirect && (out + in) > 1 && vq->vq.num_free) {
 		head = vring_add_indirect(vq, sg, out, in, gfp);
 		if (likely(head >= 0))
 			goto add_head;
@@ -244,9 +232,9 @@ int virtqueue_add_buf(struct virtqueue *_vq,
 	BUG_ON(out + in > vq->vring.num);
 	BUG_ON(out + in == 0);
 
-	if (vq->num_free < out + in) {
+	if (vq->vq.num_free < out + in) {
 		pr_debug("Can't add buf len %i - avail = %i\n",
-			 out + in, vq->num_free);
+			 out + in, vq->vq.num_free);
 		/* FIXME: for historical reasons, we force a notify here if
 		 * there are outgoing parts to the buffer.  Presumably the
 		 * host should service the ring ASAP. */
@@ -257,7 +245,7 @@ int virtqueue_add_buf(struct virtqueue *_vq,
 	}
 
 	/* We're about to use some buffers from the free list. */
-	vq->num_free -= out + in;
+	vq->vq.num_free -= out + in;
 
 	head = vq->free_head;
 	for (i = vq->free_head; out; i = vq->vring.desc[i].next, out--) {
@@ -303,7 +291,7 @@ add_head:
 	pr_debug("Added buffer head %i to %p\n", head, vq);
 	END_USE(vq);
 
-	return vq->num_free;
+	return vq->vq.num_free;
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_buf);
 
@@ -400,13 +388,13 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
 
 	while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) {
 		i = vq->vring.desc[i].next;
-		vq->num_free++;
+		vq->vq.num_free++;
 	}
 
 	vq->vring.desc[i].next = vq->free_head;
 	vq->free_head = head;
 	/* Plus final descriptor */
-	vq->num_free++;
+	vq->vq.num_free++;
 }
 
 static inline bool more_used(const struct vring_virtqueue *vq)
@@ -606,7 +594,7 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 		return buf;
 	}
 	/* That should have freed everything. */
-	BUG_ON(vq->num_free != vq->vring.num);
+	BUG_ON(vq->vq.num_free != vq->vring.num);
 
 	END_USE(vq);
 	return NULL;
@@ -660,12 +648,13 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 	vq->vq.callback = callback;
 	vq->vq.vdev = vdev;
 	vq->vq.name = name;
+	vq->vq.num_free = num;
+	vq->vq.index = index;
 	vq->notify = notify;
 	vq->weak_barriers = weak_barriers;
 	vq->broken = false;
 	vq->last_used_idx = 0;
 	vq->num_added = 0;
-	vq->queue_index = index;
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;
@@ -680,7 +669,6 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 		vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
 
 	/* Put everything in free lists. */
-	vq->num_free = num;
 	vq->free_head = 0;
 	for (i = 0; i < num-1; i++) {
 		vq->vring.desc[i].next = i+1;
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 533b1157f22e..4b8f17d90458 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -16,12 +16,20 @@
  * @name: the name of this virtqueue (mainly for debugging)
  * @vdev: the virtio device this queue was created for.
  * @priv: a pointer for the virtqueue implementation to use.
+ * @index: the zero-based ordinal number for this queue.
+ * @num_free: number of elements we expect to be able to fit.
+ *
+ * A note on @num_free: with indirect buffers, each buffer needs one
+ * element in the queue, otherwise a buffer will need one element per
+ * sg element.
  */
 struct virtqueue {
 	struct list_head list;
 	void (*callback)(struct virtqueue *vq);
 	const char *name;
 	struct virtio_device *vdev;
+	unsigned int index;
+	unsigned int num_free;
 	void *priv;
 };
 
@@ -50,7 +58,11 @@ void *virtqueue_detach_unused_buf(struct virtqueue *vq);
 
 unsigned int virtqueue_get_vring_size(struct virtqueue *vq);
 
-int virtqueue_get_queue_index(struct virtqueue *vq);
+/* FIXME: Obsolete accessor, but required for virtio_net merge. */
+static inline unsigned int virtqueue_get_queue_index(struct virtqueue *vq)
+{
+	return vq->index;
+}
 
 /**
  * virtio_device - representation of a device using virtio
-- 
cgit v1.2.3-55-g7522


From 9bffdca8c64a72ac54c47a552734ab457bc720d4 Mon Sep 17 00:00:00 2001
From: Wanlong Gao
Date: Tue, 11 Dec 2012 11:04:50 +1030
Subject: virtio: use dev_to_virtio wrapper in virtio

Use dev_to_virtio wrapper in virtio to make code clearly.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Wanlong Gao <gaowanlong@cn.fujitsu.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/virtio/virtio.c | 19 +++++++++----------
 include/linux/virtio.h  |  6 +++++-
 2 files changed, 14 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 1e8659ca27ef..1346ae8e14f3 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -10,33 +10,32 @@ static DEFINE_IDA(virtio_index_ida);
 static ssize_t device_show(struct device *_d,
 			   struct device_attribute *attr, char *buf)
 {
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	return sprintf(buf, "0x%04x\n", dev->id.device);
 }
 static ssize_t vendor_show(struct device *_d,
 			   struct device_attribute *attr, char *buf)
 {
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	return sprintf(buf, "0x%04x\n", dev->id.vendor);
 }
 static ssize_t status_show(struct device *_d,
 			   struct device_attribute *attr, char *buf)
 {
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	return sprintf(buf, "0x%08x\n", dev->config->get_status(dev));
 }
 static ssize_t modalias_show(struct device *_d,
 			     struct device_attribute *attr, char *buf)
 {
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
-
+	struct virtio_device *dev = dev_to_virtio(_d);
 	return sprintf(buf, "virtio:d%08Xv%08X\n",
 		       dev->id.device, dev->id.vendor);
 }
 static ssize_t features_show(struct device *_d,
 			     struct device_attribute *attr, char *buf)
 {
-	struct virtio_device *dev = container_of(_d, struct virtio_device, dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	unsigned int i;
 	ssize_t len = 0;
 
@@ -71,7 +70,7 @@ static inline int virtio_id_match(const struct virtio_device *dev,
 static int virtio_dev_match(struct device *_dv, struct device_driver *_dr)
 {
 	unsigned int i;
-	struct virtio_device *dev = container_of(_dv,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_dv);
 	const struct virtio_device_id *ids;
 
 	ids = container_of(_dr, struct virtio_driver, driver)->id_table;
@@ -83,7 +82,7 @@ static int virtio_dev_match(struct device *_dv, struct device_driver *_dr)
 
 static int virtio_uevent(struct device *_dv, struct kobj_uevent_env *env)
 {
-	struct virtio_device *dev = container_of(_dv,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_dv);
 
 	return add_uevent_var(env, "MODALIAS=virtio:d%08Xv%08X",
 			      dev->id.device, dev->id.vendor);
@@ -111,7 +110,7 @@ EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
 static int virtio_dev_probe(struct device *_d)
 {
 	int err, i;
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	struct virtio_driver *drv = container_of(dev->dev.driver,
 						 struct virtio_driver, driver);
 	u32 device_features;
@@ -152,7 +151,7 @@ static int virtio_dev_probe(struct device *_d)
 
 static int virtio_dev_remove(struct device *_d)
 {
-	struct virtio_device *dev = container_of(_d,struct virtio_device,dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	struct virtio_driver *drv = container_of(dev->dev.driver,
 						 struct virtio_driver, driver);
 
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 4b8f17d90458..5f1f80c76468 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -85,7 +85,11 @@ struct virtio_device {
 	void *priv;
 };
 
-#define dev_to_virtio(dev) container_of(dev, struct virtio_device, dev)
+static inline struct virtio_device *dev_to_virtio(struct device *_dev)
+{
+	return container_of(_dev, struct virtio_device, dev);
+}
+
 int register_virtio_device(struct virtio_device *dev);
 void unregister_virtio_device(struct virtio_device *dev);
 
-- 
cgit v1.2.3-55-g7522


From 9a2bdcc85d28506d4e5d4a9618fb133a3f40945d Mon Sep 17 00:00:00 2001
From: Wanlong Gao
Date: Mon, 10 Dec 2012 16:38:33 +0800
Subject: virtio: add drv_to_virtio to make code clearly

Add drv_to_virtio wrapper to get virtio_driver from device_driver.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Wanlong Gao <gaowanlong@cn.fujitsu.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/virtio/virtio.c | 11 ++++-------
 include/linux/virtio.h  |  5 +++++
 2 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 1346ae8e14f3..1c01ac3fad08 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -73,7 +73,7 @@ static int virtio_dev_match(struct device *_dv, struct device_driver *_dr)
 	struct virtio_device *dev = dev_to_virtio(_dv);
 	const struct virtio_device_id *ids;
 
-	ids = container_of(_dr, struct virtio_driver, driver)->id_table;
+	ids = drv_to_virtio(_dr)->id_table;
 	for (i = 0; ids[i].device; i++)
 		if (virtio_id_match(dev, &ids[i]))
 			return 1;
@@ -97,8 +97,7 @@ void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
 					 unsigned int fbit)
 {
 	unsigned int i;
-	struct virtio_driver *drv = container_of(vdev->dev.driver,
-						 struct virtio_driver, driver);
+	struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver);
 
 	for (i = 0; i < drv->feature_table_size; i++)
 		if (drv->feature_table[i] == fbit)
@@ -111,8 +110,7 @@ static int virtio_dev_probe(struct device *_d)
 {
 	int err, i;
 	struct virtio_device *dev = dev_to_virtio(_d);
-	struct virtio_driver *drv = container_of(dev->dev.driver,
-						 struct virtio_driver, driver);
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 	u32 device_features;
 
 	/* We have a driver! */
@@ -152,8 +150,7 @@ static int virtio_dev_probe(struct device *_d)
 static int virtio_dev_remove(struct device *_d)
 {
 	struct virtio_device *dev = dev_to_virtio(_d);
-	struct virtio_driver *drv = container_of(dev->dev.driver,
-						 struct virtio_driver, driver);
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 
 	drv->remove(dev);
 
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 5f1f80c76468..cf8adb1f5b2c 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -119,6 +119,11 @@ struct virtio_driver {
 #endif
 };
 
+static inline struct virtio_driver *drv_to_virtio(struct device_driver *drv)
+{
+	return container_of(drv, struct virtio_driver, driver);
+}
+
 int register_virtio_driver(struct virtio_driver *drv);
 void unregister_virtio_driver(struct virtio_driver *drv);
 #endif /* _LINUX_VIRTIO_H */
-- 
cgit v1.2.3-55-g7522


From 1b6370463e88b0c1c317de16d7b962acc1dab4f2 Mon Sep 17 00:00:00 2001
From: Sjur Brændeland
Date: Fri, 14 Dec 2012 14:40:51 +1030
Subject: virtio_console: Add support for remoteproc serial

Add a simple serial connection driver called
VIRTIO_ID_RPROC_SERIAL (11) for communicating with a
remote processor in an asymmetric multi-processing
configuration.

This implementation reuses the existing virtio_console
implementation, and adds support for DMA allocation
of data buffers and disables use of tty console and
the virtio control queue.

Signed-off-by: Sjur Brændeland <sjur.brandeland@stericsson.com>
Acked-by: Amit Shah <amit.shah@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/char/virtio_console.c   | 192 +++++++++++++++++++++++++++++++++++-----
 include/uapi/linux/virtio_ids.h |   1 +
 2 files changed, 170 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 548224686963..55a89a4ae42f 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -37,8 +37,12 @@
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 #include <linux/module.h>
+#include <linux/dma-mapping.h>
+#include <linux/kconfig.h>
 #include "../tty/hvc/hvc_console.h"
 
+#define is_rproc_enabled IS_ENABLED(CONFIG_REMOTEPROC)
+
 /*
  * This is a global struct for storing common data for all the devices
  * this driver handles.
@@ -112,6 +116,15 @@ struct port_buffer {
 	/* offset in the buf from which to consume data */
 	size_t offset;
 
+	/* DMA address of buffer */
+	dma_addr_t dma;
+
+	/* Device we got DMA memory from */
+	struct device *dev;
+
+	/* List of pending dma buffers to free */
+	struct list_head list;
+
 	/* If sgpages == 0 then buf is used */
 	unsigned int sgpages;
 
@@ -331,6 +344,11 @@ static bool is_console_port(struct port *port)
 	return false;
 }
 
+static bool is_rproc_serial(const struct virtio_device *vdev)
+{
+	return is_rproc_enabled && vdev->id.device == VIRTIO_ID_RPROC_SERIAL;
+}
+
 static inline bool use_multiport(struct ports_device *portdev)
 {
 	/*
@@ -342,11 +360,13 @@ static inline bool use_multiport(struct ports_device *portdev)
 	return portdev->vdev->features[0] & (1 << VIRTIO_CONSOLE_F_MULTIPORT);
 }
 
-static void free_buf(struct port_buffer *buf)
+static DEFINE_SPINLOCK(dma_bufs_lock);
+static LIST_HEAD(pending_free_dma_bufs);
+
+static void free_buf(struct port_buffer *buf, bool can_sleep)
 {
 	unsigned int i;
 
-	kfree(buf->buf);
 	for (i = 0; i < buf->sgpages; i++) {
 		struct page *page = sg_page(&buf->sg[i]);
 		if (!page)
@@ -354,14 +374,57 @@ static void free_buf(struct port_buffer *buf)
 		put_page(page);
 	}
 
+	if (!buf->dev) {
+		kfree(buf->buf);
+	} else if (is_rproc_enabled) {
+		unsigned long flags;
+
+		/* dma_free_coherent requires interrupts to be enabled. */
+		if (!can_sleep) {
+			/* queue up dma-buffers to be freed later */
+			spin_lock_irqsave(&dma_bufs_lock, flags);
+			list_add_tail(&buf->list, &pending_free_dma_bufs);
+			spin_unlock_irqrestore(&dma_bufs_lock, flags);
+			return;
+		}
+		dma_free_coherent(buf->dev, buf->size, buf->buf, buf->dma);
+
+		/* Release device refcnt and allow it to be freed */
+		put_device(buf->dev);
+	}
+
 	kfree(buf);
 }
 
+static void reclaim_dma_bufs(void)
+{
+	unsigned long flags;
+	struct port_buffer *buf, *tmp;
+	LIST_HEAD(tmp_list);
+
+	if (list_empty(&pending_free_dma_bufs))
+		return;
+
+	/* Create a copy of the pending_free_dma_bufs while holding the lock */
+	spin_lock_irqsave(&dma_bufs_lock, flags);
+	list_cut_position(&tmp_list, &pending_free_dma_bufs,
+			  pending_free_dma_bufs.prev);
+	spin_unlock_irqrestore(&dma_bufs_lock, flags);
+
+	/* Release the dma buffers, without irqs enabled */
+	list_for_each_entry_safe(buf, tmp, &tmp_list, list) {
+		list_del(&buf->list);
+		free_buf(buf, true);
+	}
+}
+
 static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
 				     int pages)
 {
 	struct port_buffer *buf;
 
+	reclaim_dma_bufs();
+
 	/*
 	 * Allocate buffer and the sg list. The sg list array is allocated
 	 * directly after the port_buffer struct.
@@ -373,11 +436,34 @@ static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
 
 	buf->sgpages = pages;
 	if (pages > 0) {
+		buf->dev = NULL;
 		buf->buf = NULL;
 		return buf;
 	}
 
-	buf->buf = kmalloc(buf_size, GFP_KERNEL);
+	if (is_rproc_serial(vq->vdev)) {
+		/*
+		 * Allocate DMA memory from ancestor. When a virtio
+		 * device is created by remoteproc, the DMA memory is
+		 * associated with the grandparent device:
+		 * vdev => rproc => platform-dev.
+		 * The code here would have been less quirky if
+		 * DMA_MEMORY_INCLUDES_CHILDREN had been supported
+		 * in dma-coherent.c
+		 */
+		if (!vq->vdev->dev.parent || !vq->vdev->dev.parent->parent)
+			goto free_buf;
+		buf->dev = vq->vdev->dev.parent->parent;
+
+		/* Increase device refcnt to avoid freeing it */
+		get_device(buf->dev);
+		buf->buf = dma_alloc_coherent(buf->dev, buf_size, &buf->dma,
+					      GFP_KERNEL);
+	} else {
+		buf->dev = NULL;
+		buf->buf = kmalloc(buf_size, GFP_KERNEL);
+	}
+
 	if (!buf->buf)
 		goto free_buf;
 	buf->len = 0;
@@ -446,7 +532,7 @@ static void discard_port_data(struct port *port)
 		port->stats.bytes_discarded += buf->len - buf->offset;
 		if (add_inbuf(port->in_vq, buf) < 0) {
 			err++;
-			free_buf(buf);
+			free_buf(buf, false);
 		}
 		port->inbuf = NULL;
 		buf = get_inbuf(port);
@@ -518,7 +604,7 @@ static void reclaim_consumed_buffers(struct port *port)
 		return;
 	}
 	while ((buf = virtqueue_get_buf(port->out_vq, &len))) {
-		free_buf(buf);
+		free_buf(buf, false);
 		port->outvq_full = false;
 	}
 }
@@ -765,7 +851,7 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
 		goto out;
 
 free_buf:
-	free_buf(buf);
+	free_buf(buf, true);
 out:
 	return ret;
 }
@@ -839,6 +925,15 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 		.u.data = &sgl,
 	};
 
+	/*
+	 * Rproc_serial does not yet support splice. To support splice
+	 * pipe_to_sg() must allocate dma-buffers and copy content from
+	 * regular pages to dma pages. And alloc_buf and free_buf must
+	 * support allocating and freeing such a list of dma-buffers.
+	 */
+	if (is_rproc_serial(port->out_vq->vdev))
+		return -EINVAL;
+
 	ret = wait_port_writable(port, filp->f_flags & O_NONBLOCK);
 	if (ret < 0)
 		return ret;
@@ -857,7 +952,7 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 		ret = __send_to_port(port, buf->sg, sgl.n, sgl.len, buf, true);
 
 	if (unlikely(ret <= 0))
-		kfree(sgl.sg);
+		free_buf(buf, true);
 	return ret;
 }
 
@@ -906,6 +1001,7 @@ static int port_fops_release(struct inode *inode, struct file *filp)
 	reclaim_consumed_buffers(port);
 	spin_unlock_irq(&port->outvq_lock);
 
+	reclaim_dma_bufs();
 	/*
 	 * Locks aren't necessary here as a port can't be opened after
 	 * unplug, and if a port isn't unplugged, a kref would already
@@ -1057,7 +1153,10 @@ static void resize_console(struct port *port)
 		return;
 
 	vdev = port->portdev->vdev;
-	if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_SIZE))
+
+	/* Don't test F_SIZE at all if we're rproc: not a valid feature! */
+	if (!is_rproc_serial(vdev) &&
+	    virtio_has_feature(vdev, VIRTIO_CONSOLE_F_SIZE))
 		hvc_resize(port->cons.hvc, port->cons.ws);
 }
 
@@ -1249,7 +1348,7 @@ static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
 		ret = add_inbuf(vq, buf);
 		if (ret < 0) {
 			spin_unlock_irq(lock);
-			free_buf(buf);
+			free_buf(buf, true);
 			break;
 		}
 		nr_added_bufs++;
@@ -1337,10 +1436,18 @@ static int add_port(struct ports_device *portdev, u32 id)
 		goto free_device;
 	}
 
-	/*
-	 * If we're not using multiport support, this has to be a console port
-	 */
-	if (!use_multiport(port->portdev)) {
+	if (is_rproc_serial(port->portdev->vdev))
+		/*
+		 * For rproc_serial assume remote processor is connected.
+		 * rproc_serial does not want the console port, only
+		 * the generic port implementation.
+		 */
+		port->host_connected = true;
+	else if (!use_multiport(port->portdev)) {
+		/*
+		 * If we're not using multiport support,
+		 * this has to be a console port.
+		 */
 		err = init_port_console(port);
 		if (err)
 			goto free_inbufs;
@@ -1373,7 +1480,7 @@ static int add_port(struct ports_device *portdev, u32 id)
 
 free_inbufs:
 	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
-		free_buf(buf);
+		free_buf(buf, true);
 free_device:
 	device_destroy(pdrvdata.class, port->dev->devt);
 free_cdev:
@@ -1415,11 +1522,11 @@ static void remove_port_data(struct port *port)
 
 	/* Remove buffers we queued up for the Host to send us data in. */
 	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
-		free_buf(buf);
+		free_buf(buf, true);
 
 	/* Free pending buffers from the out-queue. */
 	while ((buf = virtqueue_detach_unused_buf(port->out_vq)))
-		free_buf(buf);
+		free_buf(buf, true);
 }
 
 /*
@@ -1621,7 +1728,7 @@ static void control_work_handler(struct work_struct *work)
 		if (add_inbuf(portdev->c_ivq, buf) < 0) {
 			dev_warn(&portdev->vdev->dev,
 				 "Error adding buffer to queue\n");
-			free_buf(buf);
+			free_buf(buf, false);
 		}
 	}
 	spin_unlock(&portdev->cvq_lock);
@@ -1817,10 +1924,10 @@ static void remove_controlq_data(struct ports_device *portdev)
 		return;
 
 	while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
-		free_buf(buf);
+		free_buf(buf, true);
 
 	while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
-		free_buf(buf);
+		free_buf(buf, true);
 }
 
 /*
@@ -1867,11 +1974,15 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
 
 	multiport = false;
 	portdev->config.max_nr_ports = 1;
-	if (virtio_config_val(vdev, VIRTIO_CONSOLE_F_MULTIPORT,
-			      offsetof(struct virtio_console_config,
-				       max_nr_ports),
-			      &portdev->config.max_nr_ports) == 0)
+
+	/* Don't test MULTIPORT at all if we're rproc: not a valid feature! */
+	if (!is_rproc_serial(vdev) &&
+	    virtio_config_val(vdev, VIRTIO_CONSOLE_F_MULTIPORT,
+				  offsetof(struct virtio_console_config,
+					   max_nr_ports),
+				  &portdev->config.max_nr_ports) == 0) {
 		multiport = true;
+	}
 
 	err = init_vqs(portdev);
 	if (err < 0) {
@@ -1981,6 +2092,16 @@ static unsigned int features[] = {
 	VIRTIO_CONSOLE_F_MULTIPORT,
 };
 
+static struct virtio_device_id rproc_serial_id_table[] = {
+#if IS_ENABLED(CONFIG_REMOTEPROC)
+	{ VIRTIO_ID_RPROC_SERIAL, VIRTIO_DEV_ANY_ID },
+#endif
+	{ 0 },
+};
+
+static unsigned int rproc_serial_features[] = {
+};
+
 #ifdef CONFIG_PM
 static int virtcons_freeze(struct virtio_device *vdev)
 {
@@ -2065,6 +2186,20 @@ static struct virtio_driver virtio_console = {
 #endif
 };
 
+/*
+ * virtio_rproc_serial refers to __devinit function which causes
+ * section mismatch warnings. So use __refdata to silence warnings.
+ */
+static struct virtio_driver __refdata virtio_rproc_serial = {
+	.feature_table = rproc_serial_features,
+	.feature_table_size = ARRAY_SIZE(rproc_serial_features),
+	.driver.name =	"virtio_rproc_serial",
+	.driver.owner =	THIS_MODULE,
+	.id_table =	rproc_serial_id_table,
+	.probe =	virtcons_probe,
+	.remove =	virtcons_remove,
+};
+
 static int __init init(void)
 {
 	int err;
@@ -2089,7 +2224,15 @@ static int __init init(void)
 		pr_err("Error %d registering virtio driver\n", err);
 		goto free;
 	}
+	err = register_virtio_driver(&virtio_rproc_serial);
+	if (err < 0) {
+		pr_err("Error %d registering virtio rproc serial driver\n",
+		       err);
+		goto unregister;
+	}
 	return 0;
+unregister:
+	unregister_virtio_driver(&virtio_console);
 free:
 	if (pdrvdata.debugfs_dir)
 		debugfs_remove_recursive(pdrvdata.debugfs_dir);
@@ -2099,7 +2242,10 @@ free:
 
 static void __exit fini(void)
 {
+	reclaim_dma_bufs();
+
 	unregister_virtio_driver(&virtio_console);
+	unregister_virtio_driver(&virtio_rproc_serial);
 
 	class_destroy(pdrvdata.class);
 	if (pdrvdata.debugfs_dir)
diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
index 270fb22c5811..a7630d04029f 100644
--- a/include/uapi/linux/virtio_ids.h
+++ b/include/uapi/linux/virtio_ids.h
@@ -37,5 +37,6 @@
 #define VIRTIO_ID_RPMSG		7 /* virtio remote processor messaging */
 #define VIRTIO_ID_SCSI		8 /* virtio scsi */
 #define VIRTIO_ID_9P		9 /* 9p virtio console */
+#define VIRTIO_ID_RPROC_SERIAL 11 /* virtio remoteproc serial link */
 
 #endif /* _LINUX_VIRTIO_IDS_H */
-- 
cgit v1.2.3-55-g7522


From b81034506fc9b879cb726feb01342be0cdbe6e25 Mon Sep 17 00:00:00 2001
From: Chris Wilson
Date: Fri, 7 Dec 2012 20:37:06 +0000
Subject: drm: Export routines for inserting preallocated nodes into the mm
 manager

Required by i915 in order to avoid the allocation in the middle of
manipulating the drm_mm lists.

Use a pair of stubs to preserve the existing EXPORT_SYMBOLs for
backporting; to be removed later.

Cc: Dave Airlie <airlied@redhat.com>
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
[danvet: bikeshedded-away the atomic parameter, it's not yet used
anywhere.]
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_mm.c | 41 +++++++++++++++++++++++++++++------------
 include/drm/drm_mm.h     | 25 +++++++++++++++++++++----
 2 files changed, 50 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 0761a03cdbb2..2bf9670ba29b 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -184,19 +184,27 @@ EXPORT_SYMBOL(drm_mm_get_block_generic);
  * -ENOSPC if no suitable free area is available. The preallocated memory node
  * must be cleared.
  */
-int drm_mm_insert_node(struct drm_mm *mm, struct drm_mm_node *node,
-		       unsigned long size, unsigned alignment)
+int drm_mm_insert_node_generic(struct drm_mm *mm, struct drm_mm_node *node,
+			       unsigned long size, unsigned alignment,
+			       unsigned long color)
 {
 	struct drm_mm_node *hole_node;
 
-	hole_node = drm_mm_search_free(mm, size, alignment, false);
+	hole_node = drm_mm_search_free_generic(mm, size, alignment,
+					       color, 0);
 	if (!hole_node)
 		return -ENOSPC;
 
-	drm_mm_insert_helper(hole_node, node, size, alignment, 0);
-
+	drm_mm_insert_helper(hole_node, node, size, alignment, color);
 	return 0;
 }
+EXPORT_SYMBOL(drm_mm_insert_node_generic);
+
+int drm_mm_insert_node(struct drm_mm *mm, struct drm_mm_node *node,
+		       unsigned long size, unsigned alignment)
+{
+	return drm_mm_insert_node_generic(mm, node, size, alignment, 0);
+}
 EXPORT_SYMBOL(drm_mm_insert_node);
 
 static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
@@ -275,22 +283,31 @@ EXPORT_SYMBOL(drm_mm_get_block_range_generic);
  * -ENOSPC if no suitable free area is available. This is for range
  * restricted allocations. The preallocated memory node must be cleared.
  */
-int drm_mm_insert_node_in_range(struct drm_mm *mm, struct drm_mm_node *node,
-				unsigned long size, unsigned alignment,
-				unsigned long start, unsigned long end)
+int drm_mm_insert_node_in_range_generic(struct drm_mm *mm, struct drm_mm_node *node,
+					unsigned long size, unsigned alignment, unsigned long color,
+					unsigned long start, unsigned long end)
 {
 	struct drm_mm_node *hole_node;
 
-	hole_node = drm_mm_search_free_in_range(mm, size, alignment,
-						start, end, false);
+	hole_node = drm_mm_search_free_in_range_generic(mm,
+							size, alignment, color,
+							start, end, 0);
 	if (!hole_node)
 		return -ENOSPC;
 
-	drm_mm_insert_helper_range(hole_node, node, size, alignment, 0,
+	drm_mm_insert_helper_range(hole_node, node,
+				   size, alignment, color,
 				   start, end);
-
 	return 0;
 }
+EXPORT_SYMBOL(drm_mm_insert_node_in_range_generic);
+
+int drm_mm_insert_node_in_range(struct drm_mm *mm, struct drm_mm_node *node,
+				unsigned long size, unsigned alignment,
+				unsigned long start, unsigned long end)
+{
+	return drm_mm_insert_node_in_range_generic(mm, node, size, alignment, 0, start, end);
+}
 EXPORT_SYMBOL(drm_mm_insert_node_in_range);
 
 /**
diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
index 06d7f798a08c..0f4a366f6fa6 100644
--- a/include/drm/drm_mm.h
+++ b/include/drm/drm_mm.h
@@ -158,12 +158,29 @@ static inline struct drm_mm_node *drm_mm_get_block_atomic_range(
 	return drm_mm_get_block_range_generic(parent, size, alignment, 0,
 						start, end, 1);
 }
-extern int drm_mm_insert_node(struct drm_mm *mm, struct drm_mm_node *node,
-			      unsigned long size, unsigned alignment);
+
+extern int drm_mm_insert_node(struct drm_mm *mm,
+			      struct drm_mm_node *node,
+			      unsigned long size,
+			      unsigned alignment);
 extern int drm_mm_insert_node_in_range(struct drm_mm *mm,
 				       struct drm_mm_node *node,
-				       unsigned long size, unsigned alignment,
-				       unsigned long start, unsigned long end);
+				       unsigned long size,
+				       unsigned alignment,
+				       unsigned long start,
+				       unsigned long end);
+extern int drm_mm_insert_node_generic(struct drm_mm *mm,
+				      struct drm_mm_node *node,
+				      unsigned long size,
+				      unsigned alignment,
+				      unsigned long color);
+extern int drm_mm_insert_node_in_range_generic(struct drm_mm *mm,
+				       struct drm_mm_node *node,
+				       unsigned long size,
+				       unsigned alignment,
+				       unsigned long color,
+				       unsigned long start,
+				       unsigned long end);
 extern void drm_mm_put_block(struct drm_mm_node *cur);
 extern void drm_mm_remove_node(struct drm_mm_node *node);
 extern void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new);
-- 
cgit v1.2.3-55-g7522


From 7a64bf05b2a6fe3703062d13d389e3eb904741c6 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:21:51 -0800
Subject: mm: add a __GFP_KMEMCG flag

This flag is used to indicate to the callees that this allocation is a
kernel allocation in process context, and should be accounted to current's
memcg.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: JoonSoo Kim <js1304@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h             | 2 ++
 include/trace/events/gfpflags.h | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index f74856e17e48..643c9a6f7f34 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -30,6 +30,7 @@ struct vm_area_struct;
 #define ___GFP_HARDWALL		0x20000u
 #define ___GFP_THISNODE		0x40000u
 #define ___GFP_RECLAIMABLE	0x80000u
+#define ___GFP_KMEMCG		0x100000u
 #define ___GFP_NOTRACK		0x200000u
 #define ___GFP_NO_KSWAPD	0x400000u
 #define ___GFP_OTHER_NODE	0x800000u
@@ -89,6 +90,7 @@ struct vm_area_struct;
 
 #define __GFP_NO_KSWAPD	((__force gfp_t)___GFP_NO_KSWAPD)
 #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
+#define __GFP_KMEMCG	((__force gfp_t)___GFP_KMEMCG) /* Allocation comes from a memcg-accounted resource */
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)	/* Allocator intends to dirty page */
 
 /*
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
index d6fd8e5b14b7..1eddbf1557f2 100644
--- a/include/trace/events/gfpflags.h
+++ b/include/trace/events/gfpflags.h
@@ -34,6 +34,7 @@
 	{(unsigned long)__GFP_HARDWALL,		"GFP_HARDWALL"},	\
 	{(unsigned long)__GFP_THISNODE,		"GFP_THISNODE"},	\
 	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
+	{(unsigned long)__GFP_KMEMCG,		"GFP_KMEMCG"},		\
 	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"},		\
 	{(unsigned long)__GFP_NOTRACK,		"GFP_NOTRACK"},		\
 	{(unsigned long)__GFP_NO_KSWAPD,	"GFP_NO_KSWAPD"},	\
-- 
cgit v1.2.3-55-g7522


From 7ae1e1d0f8ac2927ed7e3ca6d15e42d485903459 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:21:56 -0800
Subject: memcg: kmem controller infrastructure

Introduce infrastructure for tracking kernel memory pages to a given
memcg.  This will happen whenever the caller includes the flag
__GFP_KMEMCG flag, and the task belong to a memcg other than the root.

In memcontrol.h those functions are wrapped in inline acessors.  The idea
is to later on, patch those with static branches, so we don't incur any
overhead when no mem cgroups with limited kmem are being used.

Users of this functionality shall interact with the memcg core code
through the following functions:

memcg_kmem_newpage_charge: will return true if the group can handle the
                           allocation. At this point, struct page is not
                           yet allocated.

memcg_kmem_commit_charge: will either revert the charge, if struct page
                          allocation failed, or embed memcg information
                          into page_cgroup.

memcg_kmem_uncharge_page: called at free time, will revert the charge.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 110 +++++++++++++++++++++++++++++
 mm/memcontrol.c            | 170 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 280 insertions(+)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e98a74c0c9c0..afa2ad40457e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -21,6 +21,7 @@
 #define _LINUX_MEMCONTROL_H
 #include <linux/cgroup.h>
 #include <linux/vm_event_item.h>
+#include <linux/hardirq.h>
 
 struct mem_cgroup;
 struct page_cgroup;
@@ -414,5 +415,114 @@ static inline void sock_release_memcg(struct sock *sk)
 {
 }
 #endif /* CONFIG_INET && CONFIG_MEMCG_KMEM */
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline bool memcg_kmem_enabled(void)
+{
+	return true;
+}
+
+/*
+ * In general, we'll do everything in our power to not incur in any overhead
+ * for non-memcg users for the kmem functions. Not even a function call, if we
+ * can avoid it.
+ *
+ * Therefore, we'll inline all those functions so that in the best case, we'll
+ * see that kmemcg is off for everybody and proceed quickly.  If it is on,
+ * we'll still do most of the flag checking inline. We check a lot of
+ * conditions, but because they are pretty simple, they are expected to be
+ * fast.
+ */
+bool __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg,
+					int order);
+void __memcg_kmem_commit_charge(struct page *page,
+				       struct mem_cgroup *memcg, int order);
+void __memcg_kmem_uncharge_pages(struct page *page, int order);
+
+/**
+ * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
+ * @gfp: the gfp allocation flags.
+ * @memcg: a pointer to the memcg this was charged against.
+ * @order: allocation order.
+ *
+ * returns true if the memcg where the current task belongs can hold this
+ * allocation.
+ *
+ * We return true automatically if this allocation is not to be accounted to
+ * any memcg.
+ */
+static inline bool
+memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
+{
+	if (!memcg_kmem_enabled())
+		return true;
+
+	/*
+	 * __GFP_NOFAIL allocations will move on even if charging is not
+	 * possible. Therefore we don't even try, and have this allocation
+	 * unaccounted. We could in theory charge it with
+	 * res_counter_charge_nofail, but we hope those allocations are rare,
+	 * and won't be worth the trouble.
+	 */
+	if (!(gfp & __GFP_KMEMCG) || (gfp & __GFP_NOFAIL))
+		return true;
+	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
+		return true;
+
+	/* If the test is dying, just let it go. */
+	if (unlikely(fatal_signal_pending(current)))
+		return true;
+
+	return __memcg_kmem_newpage_charge(gfp, memcg, order);
+}
+
+/**
+ * memcg_kmem_uncharge_pages: uncharge pages from memcg
+ * @page: pointer to struct page being freed
+ * @order: allocation order.
+ *
+ * there is no need to specify memcg here, since it is embedded in page_cgroup
+ */
+static inline void
+memcg_kmem_uncharge_pages(struct page *page, int order)
+{
+	if (memcg_kmem_enabled())
+		__memcg_kmem_uncharge_pages(page, order);
+}
+
+/**
+ * memcg_kmem_commit_charge: embeds correct memcg in a page
+ * @page: pointer to struct page recently allocated
+ * @memcg: the memcg structure we charged against
+ * @order: allocation order.
+ *
+ * Needs to be called after memcg_kmem_newpage_charge, regardless of success or
+ * failure of the allocation. if @page is NULL, this function will revert the
+ * charges. Otherwise, it will commit the memcg given by @memcg to the
+ * corresponding page_cgroup.
+ */
+static inline void
+memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
+{
+	if (memcg_kmem_enabled() && memcg)
+		__memcg_kmem_commit_charge(page, memcg, order);
+}
+
+#else
+static inline bool
+memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
+{
+	return true;
+}
+
+static inline void memcg_kmem_uncharge_pages(struct page *page, int order)
+{
+}
+
+static inline void
+memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index bba1cb4bbb82..b9afa060b8d6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -10,6 +10,10 @@
  * Copyright (C) 2009 Nokia Corporation
  * Author: Kirill A. Shutemov
  *
+ * Kernel Memory Controller
+ * Copyright (C) 2012 Parallels Inc. and Google Inc.
+ * Authors: Glauber Costa and Suleiman Souhlal
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -2661,6 +2665,172 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	memcg_check_events(memcg, page);
 }
 
+#ifdef CONFIG_MEMCG_KMEM
+static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
+{
+	return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg) &&
+		(memcg->kmem_account_flags & KMEM_ACCOUNTED_MASK);
+}
+
+static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
+{
+	struct res_counter *fail_res;
+	struct mem_cgroup *_memcg;
+	int ret = 0;
+	bool may_oom;
+
+	ret = res_counter_charge(&memcg->kmem, size, &fail_res);
+	if (ret)
+		return ret;
+
+	/*
+	 * Conditions under which we can wait for the oom_killer. Those are
+	 * the same conditions tested by the core page allocator
+	 */
+	may_oom = (gfp & __GFP_FS) && !(gfp & __GFP_NORETRY);
+
+	_memcg = memcg;
+	ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT,
+				      &_memcg, may_oom);
+
+	if (ret == -EINTR)  {
+		/*
+		 * __mem_cgroup_try_charge() chosed to bypass to root due to
+		 * OOM kill or fatal signal.  Since our only options are to
+		 * either fail the allocation or charge it to this cgroup, do
+		 * it as a temporary condition. But we can't fail. From a
+		 * kmem/slab perspective, the cache has already been selected,
+		 * by mem_cgroup_kmem_get_cache(), so it is too late to change
+		 * our minds.
+		 *
+		 * This condition will only trigger if the task entered
+		 * memcg_charge_kmem in a sane state, but was OOM-killed during
+		 * __mem_cgroup_try_charge() above. Tasks that were already
+		 * dying when the allocation triggers should have been already
+		 * directed to the root cgroup in memcontrol.h
+		 */
+		res_counter_charge_nofail(&memcg->res, size, &fail_res);
+		if (do_swap_account)
+			res_counter_charge_nofail(&memcg->memsw, size,
+						  &fail_res);
+		ret = 0;
+	} else if (ret)
+		res_counter_uncharge(&memcg->kmem, size);
+
+	return ret;
+}
+
+static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
+{
+	res_counter_uncharge(&memcg->kmem, size);
+	res_counter_uncharge(&memcg->res, size);
+	if (do_swap_account)
+		res_counter_uncharge(&memcg->memsw, size);
+}
+
+/*
+ * We need to verify if the allocation against current->mm->owner's memcg is
+ * possible for the given order. But the page is not allocated yet, so we'll
+ * need a further commit step to do the final arrangements.
+ *
+ * It is possible for the task to switch cgroups in this mean time, so at
+ * commit time, we can't rely on task conversion any longer.  We'll then use
+ * the handle argument to return to the caller which cgroup we should commit
+ * against. We could also return the memcg directly and avoid the pointer
+ * passing, but a boolean return value gives better semantics considering
+ * the compiled-out case as well.
+ *
+ * Returning true means the allocation is possible.
+ */
+bool
+__memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
+{
+	struct mem_cgroup *memcg;
+	int ret;
+
+	*_memcg = NULL;
+	memcg = try_get_mem_cgroup_from_mm(current->mm);
+
+	/*
+	 * very rare case described in mem_cgroup_from_task. Unfortunately there
+	 * isn't much we can do without complicating this too much, and it would
+	 * be gfp-dependent anyway. Just let it go
+	 */
+	if (unlikely(!memcg))
+		return true;
+
+	if (!memcg_can_account_kmem(memcg)) {
+		css_put(&memcg->css);
+		return true;
+	}
+
+	mem_cgroup_get(memcg);
+
+	ret = memcg_charge_kmem(memcg, gfp, PAGE_SIZE << order);
+	if (!ret)
+		*_memcg = memcg;
+	else
+		mem_cgroup_put(memcg);
+
+	css_put(&memcg->css);
+	return (ret == 0);
+}
+
+void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
+			      int order)
+{
+	struct page_cgroup *pc;
+
+	VM_BUG_ON(mem_cgroup_is_root(memcg));
+
+	/* The page allocation failed. Revert */
+	if (!page) {
+		memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+		mem_cgroup_put(memcg);
+		return;
+	}
+
+	pc = lookup_page_cgroup(page);
+	lock_page_cgroup(pc);
+	pc->mem_cgroup = memcg;
+	SetPageCgroupUsed(pc);
+	unlock_page_cgroup(pc);
+}
+
+void __memcg_kmem_uncharge_pages(struct page *page, int order)
+{
+	struct mem_cgroup *memcg = NULL;
+	struct page_cgroup *pc;
+
+
+	pc = lookup_page_cgroup(page);
+	/*
+	 * Fast unlocked return. Theoretically might have changed, have to
+	 * check again after locking.
+	 */
+	if (!PageCgroupUsed(pc))
+		return;
+
+	lock_page_cgroup(pc);
+	if (PageCgroupUsed(pc)) {
+		memcg = pc->mem_cgroup;
+		ClearPageCgroupUsed(pc);
+	}
+	unlock_page_cgroup(pc);
+
+	/*
+	 * We trust that only if there is a memcg associated with the page, it
+	 * is a valid allocation
+	 */
+	if (!memcg)
+		return;
+
+	VM_BUG_ON(mem_cgroup_is_root(memcg));
+	memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+	mem_cgroup_put(memcg);
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
 #define PCGF_NOCOPY_AT_SPLIT (1 << PCG_LOCK | 1 << PCG_MIGRATION)
-- 
cgit v1.2.3-55-g7522


From 6a1a0d3b625a4091e7a0eb249aefc6a644385149 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:00 -0800
Subject: mm: allocate kernel pages to the right memcg

When a process tries to allocate a page with the __GFP_KMEMCG flag, the
page allocator will call the corresponding memcg functions to validate
the allocation.  Tasks in the root memcg can always proceed.

To avoid adding markers to the page - and a kmem flag that would
necessarily follow, as much as doing page_cgroup lookups for no reason,
whoever is marking its allocations with __GFP_KMEMCG flag is responsible
for telling the page allocator that this is such an allocation at
free_pages() time.  This is done by the invocation of
__free_accounted_pages() and free_accounted_pages().

Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h |  3 +++
 mm/page_alloc.c     | 35 +++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 643c9a6f7f34..0f615eb23d05 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -367,6 +367,9 @@ extern void free_pages(unsigned long addr, unsigned int order);
 extern void free_hot_cold_page(struct page *page, int cold);
 extern void free_hot_cold_page_list(struct list_head *list, int cold);
 
+extern void __free_memcg_kmem_pages(struct page *page, unsigned int order);
+extern void free_memcg_kmem_pages(unsigned long addr, unsigned int order);
+
 #define __free_page(page) __free_pages((page), 0)
 #define free_page(addr) free_pages((addr), 0)
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 62496edbd8dd..2ad2ad168efe 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2612,6 +2612,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	int migratetype = allocflags_to_migratetype(gfp_mask);
 	unsigned int cpuset_mems_cookie;
 	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET;
+	struct mem_cgroup *memcg = NULL;
 
 	gfp_mask &= gfp_allowed_mask;
 
@@ -2630,6 +2631,13 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!zonelist->_zonerefs->zone))
 		return NULL;
 
+	/*
+	 * Will only have any effect when __GFP_KMEMCG is set.  This is
+	 * verified in the (always inline) callee
+	 */
+	if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
+		return NULL;
+
 retry_cpuset:
 	cpuset_mems_cookie = get_mems_allowed();
 
@@ -2665,6 +2673,8 @@ out:
 	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
 		goto retry_cpuset;
 
+	memcg_kmem_commit_charge(page, memcg, order);
+
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2717,6 +2727,31 @@ void free_pages(unsigned long addr, unsigned int order)
 
 EXPORT_SYMBOL(free_pages);
 
+/*
+ * __free_memcg_kmem_pages and free_memcg_kmem_pages will free
+ * pages allocated with __GFP_KMEMCG.
+ *
+ * Those pages are accounted to a particular memcg, embedded in the
+ * corresponding page_cgroup. To avoid adding a hit in the allocator to search
+ * for that information only to find out that it is NULL for users who have no
+ * interest in that whatsoever, we provide these functions.
+ *
+ * The caller knows better which flags it relies on.
+ */
+void __free_memcg_kmem_pages(struct page *page, unsigned int order)
+{
+	memcg_kmem_uncharge_pages(page, order);
+	__free_pages(page, order);
+}
+
+void free_memcg_kmem_pages(unsigned long addr, unsigned int order)
+{
+	if (addr != 0) {
+		VM_BUG_ON(!virt_addr_valid((void *)addr));
+		__free_memcg_kmem_pages(virt_to_page((void *)addr), order);
+	}
+}
+
 static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size)
 {
 	if (addr) {
-- 
cgit v1.2.3-55-g7522


From 50bdd430c20566b13d8bc59946184b08f5875de6 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:04 -0800
Subject: res_counter: return amount of charges after res_counter_uncharge()

It is useful to know how many charges are still left after a call to
res_counter_uncharge.  While it is possible to issue a res_counter_read
after uncharge, this can be racy.

If we need, for instance, to take some action when the counters drop down
to 0, only one of the callers should see it.  This is the same semantics
as the atomic variables in the kernel.

Since the current return value is void, we don't need to worry about
anything breaking due to this change: nobody relied on that, and only
users appearing from now on will be checking this value.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cgroups/resource_counter.txt |  7 ++++---
 include/linux/res_counter.h                | 12 +++++++-----
 kernel/res_counter.c                       | 20 +++++++++++++-------
 3 files changed, 24 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
index 0c4a344e78fa..c4d99ed0b418 100644
--- a/Documentation/cgroups/resource_counter.txt
+++ b/Documentation/cgroups/resource_counter.txt
@@ -83,16 +83,17 @@ to work with it.
 	res_counter->lock internally (it must be called with res_counter->lock
 	held). The force parameter indicates whether we can bypass the limit.
 
- e. void res_counter_uncharge[_locked]
+ e. u64 res_counter_uncharge[_locked]
 			(struct res_counter *rc, unsigned long val)
 
 	When a resource is released (freed) it should be de-accounted
 	from the resource counter it was accounted to.  This is called
-	"uncharging".
+	"uncharging". The return value of this function indicate the amount
+	of charges still present in the counter.
 
 	The _locked routines imply that the res_counter->lock is taken.
 
- f. void res_counter_uncharge_until
+ f. u64 res_counter_uncharge_until
 		(struct res_counter *rc, struct res_counter *top,
 		 unsinged long val)
 
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 6f54e40fa218..5ae8456d9670 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -125,14 +125,16 @@ int res_counter_charge_nofail(struct res_counter *counter,
  *
  * these calls check for usage underflow and show a warning on the console
  * _locked call expects the counter->lock to be taken
+ *
+ * returns the total charges still present in @counter.
  */
 
-void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
-void res_counter_uncharge(struct res_counter *counter, unsigned long val);
+u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
+u64 res_counter_uncharge(struct res_counter *counter, unsigned long val);
 
-void res_counter_uncharge_until(struct res_counter *counter,
-				struct res_counter *top,
-				unsigned long val);
+u64 res_counter_uncharge_until(struct res_counter *counter,
+			       struct res_counter *top,
+			       unsigned long val);
 /**
  * res_counter_margin - calculate chargeable space of a counter
  * @cnt: the counter
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index 3920d593e63c..ff55247e7049 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -86,33 +86,39 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
 	return __res_counter_charge(counter, val, limit_fail_at, true);
 }
 
-void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
+u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
 {
 	if (WARN_ON(counter->usage < val))
 		val = counter->usage;
 
 	counter->usage -= val;
+	return counter->usage;
 }
 
-void res_counter_uncharge_until(struct res_counter *counter,
-				struct res_counter *top,
-				unsigned long val)
+u64 res_counter_uncharge_until(struct res_counter *counter,
+			       struct res_counter *top,
+			       unsigned long val)
 {
 	unsigned long flags;
 	struct res_counter *c;
+	u64 ret = 0;
 
 	local_irq_save(flags);
 	for (c = counter; c != top; c = c->parent) {
+		u64 r;
 		spin_lock(&c->lock);
-		res_counter_uncharge_locked(c, val);
+		r = res_counter_uncharge_locked(c, val);
+		if (c == counter)
+			ret = r;
 		spin_unlock(&c->lock);
 	}
 	local_irq_restore(flags);
+	return ret;
 }
 
-void res_counter_uncharge(struct res_counter *counter, unsigned long val)
+u64 res_counter_uncharge(struct res_counter *counter, unsigned long val)
 {
-	res_counter_uncharge_until(counter, NULL, val);
+	return res_counter_uncharge_until(counter, NULL, val);
 }
 
 static inline unsigned long long *
-- 
cgit v1.2.3-55-g7522


From a8964b9b84f99c0b1b5d7c09520f89f0700e742e Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:09 -0800
Subject: memcg: use static branches when code not in use

We can use static branches to patch the code in or out when not used.

Because the _ACTIVE bit on kmem_accounted is only set after the increment
is done, we guarantee that the root memcg will always be selected for kmem
charges until all call sites are patched (see memcg_kmem_enabled).  This
guarantees that no mischarges are applied.

Static branch decrement happens when the last reference count from the
kmem accounting in memcg dies.  This will only happen when the charges
drop down to 0.

When that happens, we need to disable the static branch only on those
memcgs that enabled it.  To achieve this, we would be forced to complicate
the code by keeping track of which memcgs were the ones that actually
enabled limits, and which ones got it from its parents.

It is a lot simpler just to do static_key_slow_inc() on every child
that is accounted.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  4 ++-
 mm/memcontrol.c            | 79 +++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 78 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index afa2ad40457e..87d61e840ddd 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -22,6 +22,7 @@
 #include <linux/cgroup.h>
 #include <linux/vm_event_item.h>
 #include <linux/hardirq.h>
+#include <linux/jump_label.h>
 
 struct mem_cgroup;
 struct page_cgroup;
@@ -417,9 +418,10 @@ static inline void sock_release_memcg(struct sock *sk)
 #endif /* CONFIG_INET && CONFIG_MEMCG_KMEM */
 
 #ifdef CONFIG_MEMCG_KMEM
+extern struct static_key memcg_kmem_enabled_key;
 static inline bool memcg_kmem_enabled(void)
 {
-	return true;
+	return static_key_false(&memcg_kmem_enabled_key);
 }
 
 /*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9a62ac3ea881..bc70254558fa 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -346,10 +346,13 @@ struct mem_cgroup {
 /* internal only representation about the status of kmem accounting. */
 enum {
 	KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */
+	KMEM_ACCOUNTED_ACTIVATED, /* static key enabled. */
 	KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
 };
 
-#define KMEM_ACCOUNTED_MASK (1 << KMEM_ACCOUNTED_ACTIVE)
+/* We account when limit is on, but only after call sites are patched */
+#define KMEM_ACCOUNTED_MASK \
+		((1 << KMEM_ACCOUNTED_ACTIVE) | (1 << KMEM_ACCOUNTED_ACTIVATED))
 
 #ifdef CONFIG_MEMCG_KMEM
 static inline void memcg_kmem_set_active(struct mem_cgroup *memcg)
@@ -362,6 +365,11 @@ static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
 	return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
 }
 
+static void memcg_kmem_set_activated(struct mem_cgroup *memcg)
+{
+	set_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags);
+}
+
 static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
 {
 	if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
@@ -532,6 +540,26 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
 }
 #endif
 
+#ifdef CONFIG_MEMCG_KMEM
+struct static_key memcg_kmem_enabled_key;
+
+static void disarm_kmem_keys(struct mem_cgroup *memcg)
+{
+	if (memcg_kmem_is_active(memcg))
+		static_key_slow_dec(&memcg_kmem_enabled_key);
+}
+#else
+static void disarm_kmem_keys(struct mem_cgroup *memcg)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+static void disarm_static_keys(struct mem_cgroup *memcg)
+{
+	disarm_sock_keys(memcg);
+	disarm_kmem_keys(memcg);
+}
+
 static void drain_all_stock_async(struct mem_cgroup *memcg);
 
 static struct mem_cgroup_per_zone *
@@ -4204,6 +4232,8 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
 {
 	int ret = -EINVAL;
 #ifdef CONFIG_MEMCG_KMEM
+	bool must_inc_static_branch = false;
+
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 	/*
 	 * For simplicity, we won't allow this to be disabled.  It also can't
@@ -4234,7 +4264,15 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
 		ret = res_counter_set_limit(&memcg->kmem, val);
 		VM_BUG_ON(ret);
 
-		memcg_kmem_set_active(memcg);
+		/*
+		 * After this point, kmem_accounted (that we test atomically in
+		 * the beginning of this conditional), is no longer 0. This
+		 * guarantees only one process will set the following boolean
+		 * to true. We don't need test_and_set because we're protected
+		 * by the set_limit_mutex anyway.
+		 */
+		memcg_kmem_set_activated(memcg);
+		must_inc_static_branch = true;
 		/*
 		 * kmem charges can outlive the cgroup. In the case of slab
 		 * pages, for instance, a page contain objects from various
@@ -4247,6 +4285,27 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
 out:
 	mutex_unlock(&set_limit_mutex);
 	cgroup_unlock();
+
+	/*
+	 * We are by now familiar with the fact that we can't inc the static
+	 * branch inside cgroup_lock. See disarm functions for details. A
+	 * worker here is overkill, but also wrong: After the limit is set, we
+	 * must start accounting right away. Since this operation can't fail,
+	 * we can safely defer it to here - no rollback will be needed.
+	 *
+	 * The boolean used to control this is also safe, because
+	 * KMEM_ACCOUNTED_ACTIVATED guarantees that only one process will be
+	 * able to set it to true;
+	 */
+	if (must_inc_static_branch) {
+		static_key_slow_inc(&memcg_kmem_enabled_key);
+		/*
+		 * setting the active bit after the inc will guarantee no one
+		 * starts accounting before all call sites are patched
+		 */
+		memcg_kmem_set_active(memcg);
+	}
+
 #endif
 	return ret;
 }
@@ -4258,8 +4317,20 @@ static void memcg_propagate_kmem(struct mem_cgroup *memcg)
 		return;
 	memcg->kmem_account_flags = parent->kmem_account_flags;
 #ifdef CONFIG_MEMCG_KMEM
-	if (memcg_kmem_is_active(memcg))
+	/*
+	 * When that happen, we need to disable the static branch only on those
+	 * memcgs that enabled it. To achieve this, we would be forced to
+	 * complicate the code by keeping track of which memcgs were the ones
+	 * that actually enabled limits, and which ones got it from its
+	 * parents.
+	 *
+	 * It is a lot simpler just to do static_key_slow_inc() on every child
+	 * that is accounted.
+	 */
+	if (memcg_kmem_is_active(memcg)) {
 		mem_cgroup_get(memcg);
+		static_key_slow_inc(&memcg_kmem_enabled_key);
+	}
 #endif
 }
 
@@ -5184,7 +5255,7 @@ static void free_work(struct work_struct *work)
 	 * to move this code around, and make sure it is outside
 	 * the cgroup_lock.
 	 */
-	disarm_sock_keys(memcg);
+	disarm_static_keys(memcg);
 	if (size < PAGE_SIZE)
 		kfree(memcg);
 	else
-- 
cgit v1.2.3-55-g7522


From 2ad306b17c0ac5a1b1f250d5f772aeb87fdf1eba Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:18 -0800
Subject: fork: protect architectures where THREAD_SIZE >= PAGE_SIZE against
 fork bombs

Because those architectures will draw their stacks directly from the page
allocator, rather than the slab cache, we can directly pass __GFP_KMEMCG
flag, and issue the corresponding free_pages.

This code path is taken when the architecture doesn't define
CONFIG_ARCH_THREAD_INFO_ALLOCATOR (only ia64 seems to), and has
THREAD_SIZE >= PAGE_SIZE.  Luckily, most - if not all - of the remaining
architectures fall in this category.

This will guarantee that every stack page is accounted to the memcg the
process currently lives on, and will have the allocations to fail if they
go over limit.

For the time being, I am defining a new variant of THREADINFO_GFP, not to
mess with the other path.  Once the slab is also tracked by memcg, we can
get rid of that flag.

Tested to successfully protect against :(){ :|:& };:

Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Frederic Weisbecker <fweisbec@redhat.com>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/thread_info.h | 2 ++
 kernel/fork.c               | 4 ++--
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index ccc1899bd62e..e7e04736802f 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -61,6 +61,8 @@ extern long do_no_restart_syscall(struct restart_block *parm);
 # define THREADINFO_GFP		(GFP_KERNEL | __GFP_NOTRACK)
 #endif
 
+#define THREADINFO_GFP_ACCOUNTED (THREADINFO_GFP | __GFP_KMEMCG)
+
 /*
  * flag set/clear/test wrappers
  * - pass TIF_xxxx constants to these functions
diff --git a/kernel/fork.c b/kernel/fork.c
index c36c4e301efe..85f6d536608d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -146,7 +146,7 @@ void __weak arch_release_thread_info(struct thread_info *ti)
 static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
 						  int node)
 {
-	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
+	struct page *page = alloc_pages_node(node, THREADINFO_GFP_ACCOUNTED,
 					     THREAD_SIZE_ORDER);
 
 	return page ? page_address(page) : NULL;
@@ -154,7 +154,7 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
 
 static inline void free_thread_info(struct thread_info *ti)
 {
-	free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
+	free_memcg_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER);
 }
 # else
 static struct kmem_cache *thread_info_cache;
-- 
cgit v1.2.3-55-g7522


From ba6c496ed834a37a26fc6fc87fc9aecb0fa0014d Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:27 -0800
Subject: slab/slub: struct memcg_params

For the kmem slab controller, we need to record some extra information in
the kmem_cache structure.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Suleiman Souhlal <suleiman@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slab.h     | 24 ++++++++++++++++++++++++
 include/linux/slab_def.h |  3 +++
 include/linux/slub_def.h |  3 +++
 mm/slab.h                | 13 +++++++++++++
 4 files changed, 43 insertions(+)

(limited to 'include')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 743a10415122..00efba149222 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -176,6 +176,30 @@ void kmem_cache_free(struct kmem_cache *, void *);
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
 
+/*
+ * This is the main placeholder for memcg-related information in kmem caches.
+ * struct kmem_cache will hold a pointer to it, so the memory cost while
+ * disabled is 1 pointer. The runtime cost while enabled, gets bigger than it
+ * would otherwise be if that would be bundled in kmem_cache: we'll need an
+ * extra pointer chase. But the trade off clearly lays in favor of not
+ * penalizing non-users.
+ *
+ * Both the root cache and the child caches will have it. For the root cache,
+ * this will hold a dynamically allocated array large enough to hold
+ * information about the currently limited memcgs in the system.
+ *
+ * Child caches will hold extra metadata needed for its operation. Fields are:
+ *
+ * @memcg: pointer to the memcg this cache belongs to
+ */
+struct memcg_cache_params {
+	bool is_root_cache;
+	union {
+		struct kmem_cache *memcg_caches[0];
+		struct mem_cgroup *memcg;
+	};
+};
+
 /*
  * Common kmalloc functions provided by all allocators
  */
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 45c0356fdc8c..8bb6e0eaf3c6 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -81,6 +81,9 @@ struct kmem_cache {
 	 */
 	int obj_offset;
 #endif /* CONFIG_DEBUG_SLAB */
+#ifdef CONFIG_MEMCG_KMEM
+	struct memcg_cache_params *memcg_params;
+#endif
 
 /* 6) per-cpu/per-node data, touched during every alloc/free */
 	/*
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index df448adb7283..961e72eab907 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -101,6 +101,9 @@ struct kmem_cache {
 #ifdef CONFIG_SYSFS
 	struct kobject kobj;	/* For sysfs */
 #endif
+#ifdef CONFIG_MEMCG_KMEM
+	struct memcg_cache_params *memcg_params;
+#endif
 
 #ifdef CONFIG_NUMA
 	/*
diff --git a/mm/slab.h b/mm/slab.h
index 1cb9c9ee0e6f..49e7a8b1d27e 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -100,4 +100,17 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
 void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
 ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 		       size_t count, loff_t *ppos);
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline bool is_root_cache(struct kmem_cache *s)
+{
+	return !s->memcg_params || s->memcg_params->is_root_cache;
+}
+#else
+static inline bool is_root_cache(struct kmem_cache *s)
+{
+	return true;
+}
+
+#endif
 #endif
-- 
cgit v1.2.3-55-g7522


From 2633d7a028239a738b793be5ca8fa6ac312f5793 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:34 -0800
Subject: slab/slub: consider a memcg parameter in kmem_create_cache

Allow a memcg parameter to be passed during cache creation.  When the slub
allocator is being used, it will only merge caches that belong to the same
memcg.  We'll do this by scanning the global list, and then translating
the cache to a memcg-specific cache

Default function is created as a wrapper, passing NULL to the memcg
version.  We only merge caches that belong to the same memcg.

A helper is provided, memcg_css_id: because slub needs a unique cache name
for sysfs.  Since this is visible, but not the canonical location for slab
data, the cache name is not used, the css_id should suffice.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 26 +++++++++++++++++++++++
 include/linux/slab.h       | 14 ++++++++++++-
 mm/memcontrol.c            | 51 ++++++++++++++++++++++++++++++++++++++++++++++
 mm/slab.h                  | 23 +++++++++++++++++----
 mm/slab_common.c           | 42 ++++++++++++++++++++++++++++++--------
 mm/slub.c                  | 19 +++++++++++++----
 6 files changed, 157 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 87d61e840ddd..0b69a0470007 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -28,6 +28,7 @@ struct mem_cgroup;
 struct page_cgroup;
 struct page;
 struct mm_struct;
+struct kmem_cache;
 
 /* Stats that can be updated by kernel. */
 enum mem_cgroup_page_stat_item {
@@ -441,6 +442,11 @@ void __memcg_kmem_commit_charge(struct page *page,
 				       struct mem_cgroup *memcg, int order);
 void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
+int memcg_cache_id(struct mem_cgroup *memcg);
+int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s);
+void memcg_release_cache(struct kmem_cache *cachep);
+void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep);
+
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
  * @gfp: the gfp allocation flags.
@@ -525,6 +531,26 @@ static inline void
 memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
 {
 }
+
+static inline int memcg_cache_id(struct mem_cgroup *memcg)
+{
+	return -1;
+}
+
+static inline int memcg_register_cache(struct mem_cgroup *memcg,
+				       struct kmem_cache *s)
+{
+	return 0;
+}
+
+static inline void memcg_release_cache(struct kmem_cache *cachep)
+{
+}
+
+static inline void memcg_cache_list_add(struct mem_cgroup *memcg,
+					struct kmem_cache *s)
+{
+}
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 00efba149222..c0fcf28c15b2 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -116,6 +116,7 @@ struct kmem_cache {
 };
 #endif
 
+struct mem_cgroup;
 /*
  * struct kmem_cache related prototypes
  */
@@ -125,6 +126,9 @@ int slab_is_available(void);
 struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			unsigned long,
 			void (*)(void *));
+struct kmem_cache *
+kmem_cache_create_memcg(struct mem_cgroup *, const char *, size_t, size_t,
+			unsigned long, void (*)(void *));
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
 void kmem_cache_free(struct kmem_cache *, void *);
@@ -191,15 +195,23 @@ void kmem_cache_free(struct kmem_cache *, void *);
  * Child caches will hold extra metadata needed for its operation. Fields are:
  *
  * @memcg: pointer to the memcg this cache belongs to
+ * @list: list_head for the list of all caches in this memcg
+ * @root_cache: pointer to the global, root cache, this cache was derived from
  */
 struct memcg_cache_params {
 	bool is_root_cache;
 	union {
 		struct kmem_cache *memcg_caches[0];
-		struct mem_cgroup *memcg;
+		struct {
+			struct mem_cgroup *memcg;
+			struct list_head list;
+			struct kmem_cache *root_cache;
+		};
 	};
 };
 
+int memcg_update_all_caches(int num_memcgs);
+
 /*
  * Common kmalloc functions provided by all allocators
  */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e16694d5e118..3eafe6cf6ca4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -341,6 +341,14 @@ struct mem_cgroup {
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
 	struct tcp_memcontrol tcp_mem;
 #endif
+#if defined(CONFIG_MEMCG_KMEM)
+	/* analogous to slab_common's slab_caches list. per-memcg */
+	struct list_head memcg_slab_caches;
+	/* Not a spinlock, we can take a lot of time walking the list */
+	struct mutex slab_caches_mutex;
+        /* Index in the kmem_cache->memcg_params->memcg_caches array */
+	int kmemcg_id;
+#endif
 };
 
 /* internal only representation about the status of kmem accounting. */
@@ -2785,6 +2793,47 @@ static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
 		mem_cgroup_put(memcg);
 }
 
+void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep)
+{
+	if (!memcg)
+		return;
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches);
+	mutex_unlock(&memcg->slab_caches_mutex);
+}
+
+/*
+ * helper for acessing a memcg's index. It will be used as an index in the
+ * child cache array in kmem_cache, and also to derive its name. This function
+ * will return -1 when this is not a kmem-limited memcg.
+ */
+int memcg_cache_id(struct mem_cgroup *memcg)
+{
+	return memcg ? memcg->kmemcg_id : -1;
+}
+
+int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s)
+{
+	size_t size = sizeof(struct memcg_cache_params);
+
+	if (!memcg_kmem_enabled())
+		return 0;
+
+	s->memcg_params = kzalloc(size, GFP_KERNEL);
+	if (!s->memcg_params)
+		return -ENOMEM;
+
+	if (memcg)
+		s->memcg_params->memcg = memcg;
+	return 0;
+}
+
+void memcg_release_cache(struct kmem_cache *s)
+{
+	kfree(s->memcg_params);
+}
+
 /*
  * We need to verify if the allocation against current->mm->owner's memcg is
  * possible for the given order. But the page is not allocated yet, so we'll
@@ -5026,7 +5075,9 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
+	memcg->kmemcg_id = -1;
 	memcg_propagate_kmem(memcg);
+
 	return mem_cgroup_sockets_init(memcg, ss);
 };
 
diff --git a/mm/slab.h b/mm/slab.h
index 49e7a8b1d27e..abe582d20c79 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -43,12 +43,15 @@ extern struct kmem_cache *create_kmalloc_cache(const char *name, size_t size,
 extern void create_boot_cache(struct kmem_cache *, const char *name,
 			size_t size, unsigned long flags);
 
+struct mem_cgroup;
 #ifdef CONFIG_SLUB
-struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
-	size_t align, unsigned long flags, void (*ctor)(void *));
+struct kmem_cache *
+__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
+		   size_t align, unsigned long flags, void (*ctor)(void *));
 #else
-static inline struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
-	size_t align, unsigned long flags, void (*ctor)(void *))
+static inline struct kmem_cache *
+__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
+		   size_t align, unsigned long flags, void (*ctor)(void *))
 { return NULL; }
 #endif
 
@@ -106,11 +109,23 @@ static inline bool is_root_cache(struct kmem_cache *s)
 {
 	return !s->memcg_params || s->memcg_params->is_root_cache;
 }
+
+static inline bool cache_match_memcg(struct kmem_cache *cachep,
+				     struct mem_cgroup *memcg)
+{
+	return (is_root_cache(cachep) && !memcg) ||
+				(cachep->memcg_params->memcg == memcg);
+}
 #else
 static inline bool is_root_cache(struct kmem_cache *s)
 {
 	return true;
 }
 
+static inline bool cache_match_memcg(struct kmem_cache *cachep,
+				     struct mem_cgroup *memcg)
+{
+	return true;
+}
 #endif
 #endif
diff --git a/mm/slab_common.c b/mm/slab_common.c
index a8e76d79ee65..3031badcc577 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -18,6 +18,7 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/page.h>
+#include <linux/memcontrol.h>
 
 #include "slab.h"
 
@@ -27,7 +28,8 @@ DEFINE_MUTEX(slab_mutex);
 struct kmem_cache *kmem_cache;
 
 #ifdef CONFIG_DEBUG_VM
-static int kmem_cache_sanity_check(const char *name, size_t size)
+static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
+				   size_t size)
 {
 	struct kmem_cache *s = NULL;
 
@@ -53,7 +55,13 @@ static int kmem_cache_sanity_check(const char *name, size_t size)
 			continue;
 		}
 
-		if (!strcmp(s->name, name)) {
+		/*
+		 * For simplicity, we won't check this in the list of memcg
+		 * caches. We have control over memcg naming, and if there
+		 * aren't duplicates in the global list, there won't be any
+		 * duplicates in the memcg lists as well.
+		 */
+		if (!memcg && !strcmp(s->name, name)) {
 			pr_err("%s (%s): Cache name already exists.\n",
 			       __func__, name);
 			dump_stack();
@@ -66,7 +74,8 @@ static int kmem_cache_sanity_check(const char *name, size_t size)
 	return 0;
 }
 #else
-static inline int kmem_cache_sanity_check(const char *name, size_t size)
+static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
+					  const char *name, size_t size)
 {
 	return 0;
 }
@@ -125,8 +134,9 @@ unsigned long calculate_alignment(unsigned long flags,
  * as davem.
  */
 
-struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align,
-		unsigned long flags, void (*ctor)(void *))
+struct kmem_cache *
+kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
+			size_t align, unsigned long flags, void (*ctor)(void *))
 {
 	struct kmem_cache *s = NULL;
 	int err = 0;
@@ -134,7 +144,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
 	get_online_cpus();
 	mutex_lock(&slab_mutex);
 
-	if (!kmem_cache_sanity_check(name, size) == 0)
+	if (!kmem_cache_sanity_check(memcg, name, size) == 0)
 		goto out_locked;
 
 	/*
@@ -145,7 +155,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
 	 */
 	flags &= CACHE_CREATE_MASK;
 
-	s = __kmem_cache_alias(name, size, align, flags, ctor);
+	s = __kmem_cache_alias(memcg, name, size, align, flags, ctor);
 	if (s)
 		goto out_locked;
 
@@ -154,6 +164,13 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
 		s->object_size = s->size = size;
 		s->align = calculate_alignment(flags, align, size);
 		s->ctor = ctor;
+
+		if (memcg_register_cache(memcg, s)) {
+			kmem_cache_free(kmem_cache, s);
+			err = -ENOMEM;
+			goto out_locked;
+		}
+
 		s->name = kstrdup(name, GFP_KERNEL);
 		if (!s->name) {
 			kmem_cache_free(kmem_cache, s);
@@ -163,10 +180,9 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
 
 		err = __kmem_cache_create(s, flags);
 		if (!err) {
-
 			s->refcount = 1;
 			list_add(&s->list, &slab_caches);
-
+			memcg_cache_list_add(memcg, s);
 		} else {
 			kfree(s->name);
 			kmem_cache_free(kmem_cache, s);
@@ -194,6 +210,13 @@ out_locked:
 
 	return s;
 }
+
+struct kmem_cache *
+kmem_cache_create(const char *name, size_t size, size_t align,
+		  unsigned long flags, void (*ctor)(void *))
+{
+	return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor);
+}
 EXPORT_SYMBOL(kmem_cache_create);
 
 void kmem_cache_destroy(struct kmem_cache *s)
@@ -209,6 +232,7 @@ void kmem_cache_destroy(struct kmem_cache *s)
 			if (s->flags & SLAB_DESTROY_BY_RCU)
 				rcu_barrier();
 
+			memcg_release_cache(s);
 			kfree(s->name);
 			kmem_cache_free(kmem_cache, s);
 		} else {
diff --git a/mm/slub.c b/mm/slub.c
index 87f9f32bf0cd..985332b38852 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -31,6 +31,7 @@
 #include <linux/fault-inject.h>
 #include <linux/stacktrace.h>
 #include <linux/prefetch.h>
+#include <linux/memcontrol.h>
 
 #include <trace/events/kmem.h>
 
@@ -3786,7 +3787,7 @@ static int slab_unmergeable(struct kmem_cache *s)
 	return 0;
 }
 
-static struct kmem_cache *find_mergeable(size_t size,
+static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
 		size_t align, unsigned long flags, const char *name,
 		void (*ctor)(void *))
 {
@@ -3822,17 +3823,21 @@ static struct kmem_cache *find_mergeable(size_t size,
 		if (s->size - size >= sizeof(void *))
 			continue;
 
+		if (!cache_match_memcg(s, memcg))
+			continue;
+
 		return s;
 	}
 	return NULL;
 }
 
-struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
-		size_t align, unsigned long flags, void (*ctor)(void *))
+struct kmem_cache *
+__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
+		   size_t align, unsigned long flags, void (*ctor)(void *))
 {
 	struct kmem_cache *s;
 
-	s = find_mergeable(size, align, flags, name, ctor);
+	s = find_mergeable(memcg, size, align, flags, name, ctor);
 	if (s) {
 		s->refcount++;
 		/*
@@ -5156,6 +5161,12 @@ static char *create_unique_id(struct kmem_cache *s)
 	if (p != name + 1)
 		*p++ = '-';
 	p += sprintf(p, "%07d", s->size);
+
+#ifdef CONFIG_MEMCG_KMEM
+	if (!is_root_cache(s))
+		p += sprintf(p, "-%08d", memcg_cache_id(s->memcg_params->memcg));
+#endif
+
 	BUG_ON(p > name + ID_STR_LENGTH - 1);
 	return name;
 }
-- 
cgit v1.2.3-55-g7522


From 55007d849759252ddd573aeb36143b947202d509 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:38 -0800
Subject: memcg: allocate memory for memcg caches whenever a new memcg appears

Every cache that is considered a root cache (basically the "original"
caches, tied to the root memcg/no-memcg) will have an array that should be
large enough to store a cache pointer per each memcg in the system.

Theoreticaly, this is as high as 1 << sizeof(css_id), which is currently
in the 64k pointers range.  Most of the time, we won't be using that much.

What goes in this patch, is a simple scheme to dynamically allocate such
an array, in order to minimize memory usage for memcg caches.  Because we
would also like to avoid allocations all the time, at least for now, the
array will only grow.  It will tend to be big enough to hold the maximum
number of kmem-limited memcgs ever achieved.

We'll allocate it to be a minimum of 64 kmem-limited memcgs.  When we have
more than that, we'll start doubling the size of this array every time the
limit is reached.

Because we are only considering kmem limited memcgs, a natural point for
this to happen is when we write to the limit.  At that point, we already
have set_limit_mutex held, so that will become our natural synchronization
mechanism.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |   2 +
 mm/memcontrol.c            | 207 +++++++++++++++++++++++++++++++++++++++++----
 mm/slab_common.c           |  28 ++++++
 3 files changed, 221 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 0b69a0470007..45085e14e023 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -447,6 +447,8 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s);
 void memcg_release_cache(struct kmem_cache *cachep);
 void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep);
 
+int memcg_update_cache_size(struct kmem_cache *s, int num_groups);
+void memcg_update_array_size(int num_groups);
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
  * @gfp: the gfp allocation flags.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3eafe6cf6ca4..db38b60e5f87 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -378,6 +378,11 @@ static void memcg_kmem_set_activated(struct mem_cgroup *memcg)
 	set_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags);
 }
 
+static void memcg_kmem_clear_activated(struct mem_cgroup *memcg)
+{
+	clear_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags);
+}
+
 static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
 {
 	if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
@@ -549,12 +554,48 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
 #endif
 
 #ifdef CONFIG_MEMCG_KMEM
+/*
+ * This will be the memcg's index in each cache's ->memcg_params->memcg_caches.
+ * There are two main reasons for not using the css_id for this:
+ *  1) this works better in sparse environments, where we have a lot of memcgs,
+ *     but only a few kmem-limited. Or also, if we have, for instance, 200
+ *     memcgs, and none but the 200th is kmem-limited, we'd have to have a
+ *     200 entry array for that.
+ *
+ *  2) In order not to violate the cgroup API, we would like to do all memory
+ *     allocation in ->create(). At that point, we haven't yet allocated the
+ *     css_id. Having a separate index prevents us from messing with the cgroup
+ *     core for this
+ *
+ * The current size of the caches array is stored in
+ * memcg_limited_groups_array_size.  It will double each time we have to
+ * increase it.
+ */
+static DEFINE_IDA(kmem_limited_groups);
+static int memcg_limited_groups_array_size;
+/*
+ * MIN_SIZE is different than 1, because we would like to avoid going through
+ * the alloc/free process all the time. In a small machine, 4 kmem-limited
+ * cgroups is a reasonable guess. In the future, it could be a parameter or
+ * tunable, but that is strictly not necessary.
+ *
+ * MAX_SIZE should be as large as the number of css_ids. Ideally, we could get
+ * this constant directly from cgroup, but it is understandable that this is
+ * better kept as an internal representation in cgroup.c. In any case, the
+ * css_id space is not getting any smaller, and we don't have to necessarily
+ * increase ours as well if it increases.
+ */
+#define MEMCG_CACHES_MIN_SIZE 4
+#define MEMCG_CACHES_MAX_SIZE 65535
+
 struct static_key memcg_kmem_enabled_key;
 
 static void disarm_kmem_keys(struct mem_cgroup *memcg)
 {
-	if (memcg_kmem_is_active(memcg))
+	if (memcg_kmem_is_active(memcg)) {
 		static_key_slow_dec(&memcg_kmem_enabled_key);
+		ida_simple_remove(&kmem_limited_groups, memcg->kmemcg_id);
+	}
 	/*
 	 * This check can't live in kmem destruction function,
 	 * since the charges will outlive the cgroup
@@ -2813,6 +2854,120 @@ int memcg_cache_id(struct mem_cgroup *memcg)
 	return memcg ? memcg->kmemcg_id : -1;
 }
 
+/*
+ * This ends up being protected by the set_limit mutex, during normal
+ * operation, because that is its main call site.
+ *
+ * But when we create a new cache, we can call this as well if its parent
+ * is kmem-limited. That will have to hold set_limit_mutex as well.
+ */
+int memcg_update_cache_sizes(struct mem_cgroup *memcg)
+{
+	int num, ret;
+
+	num = ida_simple_get(&kmem_limited_groups,
+				0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
+	if (num < 0)
+		return num;
+	/*
+	 * After this point, kmem_accounted (that we test atomically in
+	 * the beginning of this conditional), is no longer 0. This
+	 * guarantees only one process will set the following boolean
+	 * to true. We don't need test_and_set because we're protected
+	 * by the set_limit_mutex anyway.
+	 */
+	memcg_kmem_set_activated(memcg);
+
+	ret = memcg_update_all_caches(num+1);
+	if (ret) {
+		ida_simple_remove(&kmem_limited_groups, num);
+		memcg_kmem_clear_activated(memcg);
+		return ret;
+	}
+
+	memcg->kmemcg_id = num;
+	INIT_LIST_HEAD(&memcg->memcg_slab_caches);
+	mutex_init(&memcg->slab_caches_mutex);
+	return 0;
+}
+
+static size_t memcg_caches_array_size(int num_groups)
+{
+	ssize_t size;
+	if (num_groups <= 0)
+		return 0;
+
+	size = 2 * num_groups;
+	if (size < MEMCG_CACHES_MIN_SIZE)
+		size = MEMCG_CACHES_MIN_SIZE;
+	else if (size > MEMCG_CACHES_MAX_SIZE)
+		size = MEMCG_CACHES_MAX_SIZE;
+
+	return size;
+}
+
+/*
+ * We should update the current array size iff all caches updates succeed. This
+ * can only be done from the slab side. The slab mutex needs to be held when
+ * calling this.
+ */
+void memcg_update_array_size(int num)
+{
+	if (num > memcg_limited_groups_array_size)
+		memcg_limited_groups_array_size = memcg_caches_array_size(num);
+}
+
+int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
+{
+	struct memcg_cache_params *cur_params = s->memcg_params;
+
+	VM_BUG_ON(s->memcg_params && !s->memcg_params->is_root_cache);
+
+	if (num_groups > memcg_limited_groups_array_size) {
+		int i;
+		ssize_t size = memcg_caches_array_size(num_groups);
+
+		size *= sizeof(void *);
+		size += sizeof(struct memcg_cache_params);
+
+		s->memcg_params = kzalloc(size, GFP_KERNEL);
+		if (!s->memcg_params) {
+			s->memcg_params = cur_params;
+			return -ENOMEM;
+		}
+
+		s->memcg_params->is_root_cache = true;
+
+		/*
+		 * There is the chance it will be bigger than
+		 * memcg_limited_groups_array_size, if we failed an allocation
+		 * in a cache, in which case all caches updated before it, will
+		 * have a bigger array.
+		 *
+		 * But if that is the case, the data after
+		 * memcg_limited_groups_array_size is certainly unused
+		 */
+		for (i = 0; i < memcg_limited_groups_array_size; i++) {
+			if (!cur_params->memcg_caches[i])
+				continue;
+			s->memcg_params->memcg_caches[i] =
+						cur_params->memcg_caches[i];
+		}
+
+		/*
+		 * Ideally, we would wait until all caches succeed, and only
+		 * then free the old one. But this is not worth the extra
+		 * pointer per-cache we'd have to have for this.
+		 *
+		 * It is not a big deal if some caches are left with a size
+		 * bigger than the others. And all updates will reset this
+		 * anyway.
+		 */
+		kfree(cur_params);
+	}
+	return 0;
+}
+
 int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s)
 {
 	size_t size = sizeof(struct memcg_cache_params);
@@ -2820,6 +2975,9 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s)
 	if (!memcg_kmem_enabled())
 		return 0;
 
+	if (!memcg)
+		size += memcg_limited_groups_array_size * sizeof(void *);
+
 	s->memcg_params = kzalloc(size, GFP_KERNEL);
 	if (!s->memcg_params)
 		return -ENOMEM;
@@ -4326,14 +4484,11 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
 		ret = res_counter_set_limit(&memcg->kmem, val);
 		VM_BUG_ON(ret);
 
-		/*
-		 * After this point, kmem_accounted (that we test atomically in
-		 * the beginning of this conditional), is no longer 0. This
-		 * guarantees only one process will set the following boolean
-		 * to true. We don't need test_and_set because we're protected
-		 * by the set_limit_mutex anyway.
-		 */
-		memcg_kmem_set_activated(memcg);
+		ret = memcg_update_cache_sizes(memcg);
+		if (ret) {
+			res_counter_set_limit(&memcg->kmem, RESOURCE_MAX);
+			goto out;
+		}
 		must_inc_static_branch = true;
 		/*
 		 * kmem charges can outlive the cgroup. In the case of slab
@@ -4372,11 +4527,13 @@ out:
 	return ret;
 }
 
-static void memcg_propagate_kmem(struct mem_cgroup *memcg)
+static int memcg_propagate_kmem(struct mem_cgroup *memcg)
 {
+	int ret = 0;
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
 	if (!parent)
-		return;
+		goto out;
+
 	memcg->kmem_account_flags = parent->kmem_account_flags;
 #ifdef CONFIG_MEMCG_KMEM
 	/*
@@ -4389,11 +4546,24 @@ static void memcg_propagate_kmem(struct mem_cgroup *memcg)
 	 * It is a lot simpler just to do static_key_slow_inc() on every child
 	 * that is accounted.
 	 */
-	if (memcg_kmem_is_active(memcg)) {
-		mem_cgroup_get(memcg);
-		static_key_slow_inc(&memcg_kmem_enabled_key);
-	}
+	if (!memcg_kmem_is_active(memcg))
+		goto out;
+
+	/*
+	 * destroy(), called if we fail, will issue static_key_slow_inc() and
+	 * mem_cgroup_put() if kmem is enabled. We have to either call them
+	 * unconditionally, or clear the KMEM_ACTIVE flag. I personally find
+	 * this more consistent, since it always leads to the same destroy path
+	 */
+	mem_cgroup_get(memcg);
+	static_key_slow_inc(&memcg_kmem_enabled_key);
+
+	mutex_lock(&set_limit_mutex);
+	ret = memcg_update_cache_sizes(memcg);
+	mutex_unlock(&set_limit_mutex);
 #endif
+out:
+	return ret;
 }
 
 /*
@@ -5075,8 +5245,12 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
+	int ret;
+
 	memcg->kmemcg_id = -1;
-	memcg_propagate_kmem(memcg);
+	ret = memcg_propagate_kmem(memcg);
+	if (ret)
+		return ret;
 
 	return mem_cgroup_sockets_init(memcg, ss);
 };
@@ -5479,6 +5653,7 @@ mem_cgroup_css_alloc(struct cgroup *cont)
 		res_counter_init(&memcg->res, &parent->res);
 		res_counter_init(&memcg->memsw, &parent->memsw);
 		res_counter_init(&memcg->kmem, &parent->kmem);
+
 		/*
 		 * We increment refcnt of the parent to ensure that we can
 		 * safely access it on res_counter_charge/uncharge.
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3031badcc577..1c424b6511bf 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -81,6 +81,34 @@ static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
 }
 #endif
 
+#ifdef CONFIG_MEMCG_KMEM
+int memcg_update_all_caches(int num_memcgs)
+{
+	struct kmem_cache *s;
+	int ret = 0;
+	mutex_lock(&slab_mutex);
+
+	list_for_each_entry(s, &slab_caches, list) {
+		if (!is_root_cache(s))
+			continue;
+
+		ret = memcg_update_cache_size(s, num_memcgs);
+		/*
+		 * See comment in memcontrol.c, memcg_update_cache_size:
+		 * Instead of freeing the memory, we'll just leave the caches
+		 * up to this point in an updated state.
+		 */
+		if (ret)
+			goto out;
+	}
+
+	memcg_update_array_size(num_memcgs);
+out:
+	mutex_unlock(&slab_mutex);
+	return ret;
+}
+#endif
+
 /*
  * Figure out what the alignment of the objects will be given a set of
  * flags, a user specified alignment and the size of the objects.
-- 
cgit v1.2.3-55-g7522


From d7f25f8a2f81252d1ac134470ba1d0a287cf8fcd Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:40 -0800
Subject: memcg: infrastructure to match an allocation to the right cache

The page allocator is able to bind a page to a memcg when it is
allocated.  But for the caches, we'd like to have as many objects as
possible in a page belonging to the same cache.

This is done in this patch by calling memcg_kmem_get_cache in the
beginning of every allocation function.  This function is patched out by
static branches when kernel memory controller is not being used.

It assumes that the task allocating, which determines the memcg in the
page allocator, belongs to the same cgroup throughout the whole process.
Misaccounting can happen if the task calls memcg_kmem_get_cache() while
belonging to a cgroup, and later on changes.  This is considered
acceptable, and should only happen upon task migration.

Before the cache is created by the memcg core, there is also a possible
imbalance: the task belongs to a memcg, but the cache being allocated from
is the global cache, since the child cache is not yet guaranteed to be
ready.  This case is also fine, since in this case the GFP_KMEMCG will not
be passed and the page allocator will not attempt any cgroup accounting.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  41 +++++++++
 init/Kconfig               |   1 -
 mm/memcontrol.c            | 217 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 258 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 45085e14e023..bd9b5d73bc2b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -449,6 +449,10 @@ void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep);
 
 int memcg_update_cache_size(struct kmem_cache *s, int num_groups);
 void memcg_update_array_size(int num_groups);
+
+struct kmem_cache *
+__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
+
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
  * @gfp: the gfp allocation flags.
@@ -518,6 +522,37 @@ memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
 		__memcg_kmem_commit_charge(page, memcg, order);
 }
 
+/**
+ * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation
+ * @cachep: the original global kmem cache
+ * @gfp: allocation flags.
+ *
+ * This function assumes that the task allocating, which determines the memcg
+ * in the page allocator, belongs to the same cgroup throughout the whole
+ * process.  Misacounting can happen if the task calls memcg_kmem_get_cache()
+ * while belonging to a cgroup, and later on changes. This is considered
+ * acceptable, and should only happen upon task migration.
+ *
+ * Before the cache is created by the memcg core, there is also a possible
+ * imbalance: the task belongs to a memcg, but the cache being allocated from
+ * is the global cache, since the child cache is not yet guaranteed to be
+ * ready. This case is also fine, since in this case the GFP_KMEMCG will not be
+ * passed and the page allocator will not attempt any cgroup accounting.
+ */
+static __always_inline struct kmem_cache *
+memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
+{
+	if (!memcg_kmem_enabled())
+		return cachep;
+	if (gfp & __GFP_NOFAIL)
+		return cachep;
+	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
+		return cachep;
+	if (unlikely(fatal_signal_pending(current)))
+		return cachep;
+
+	return __memcg_kmem_get_cache(cachep, gfp);
+}
 #else
 static inline bool
 memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
@@ -553,6 +588,12 @@ static inline void memcg_cache_list_add(struct mem_cgroup *memcg,
 					struct kmem_cache *s)
 {
 }
+
+static inline struct kmem_cache *
+memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
+{
+	return cachep;
+}
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/init/Kconfig b/init/Kconfig
index 19ccb33c99d9..7d30240e5bfe 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -883,7 +883,6 @@ config MEMCG_KMEM
 	bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)"
 	depends on MEMCG && EXPERIMENTAL
 	depends on SLUB || SLAB
-	default n
 	help
 	  The Kernel Memory extension for Memory Resource Controller can limit
 	  the amount of memory used by kernel objects in the system. Those are
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index db38b60e5f87..efd26620a60b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -588,7 +588,14 @@ static int memcg_limited_groups_array_size;
 #define MEMCG_CACHES_MIN_SIZE 4
 #define MEMCG_CACHES_MAX_SIZE 65535
 
+/*
+ * A lot of the calls to the cache allocation functions are expected to be
+ * inlined by the compiler. Since the calls to memcg_kmem_get_cache are
+ * conditional to this static branch, we'll have to allow modules that does
+ * kmem_cache_alloc and the such to see this symbol as well
+ */
 struct static_key memcg_kmem_enabled_key;
+EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
 static void disarm_kmem_keys(struct mem_cgroup *memcg)
 {
@@ -2989,9 +2996,219 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s)
 
 void memcg_release_cache(struct kmem_cache *s)
 {
+	struct kmem_cache *root;
+	struct mem_cgroup *memcg;
+	int id;
+
+	/*
+	 * This happens, for instance, when a root cache goes away before we
+	 * add any memcg.
+	 */
+	if (!s->memcg_params)
+		return;
+
+	if (s->memcg_params->is_root_cache)
+		goto out;
+
+	memcg = s->memcg_params->memcg;
+	id  = memcg_cache_id(memcg);
+
+	root = s->memcg_params->root_cache;
+	root->memcg_params->memcg_caches[id] = NULL;
+	mem_cgroup_put(memcg);
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_del(&s->memcg_params->list);
+	mutex_unlock(&memcg->slab_caches_mutex);
+
+out:
 	kfree(s->memcg_params);
 }
 
+static char *memcg_cache_name(struct mem_cgroup *memcg, struct kmem_cache *s)
+{
+	char *name;
+	struct dentry *dentry;
+
+	rcu_read_lock();
+	dentry = rcu_dereference(memcg->css.cgroup->dentry);
+	rcu_read_unlock();
+
+	BUG_ON(dentry == NULL);
+
+	name = kasprintf(GFP_KERNEL, "%s(%d:%s)", s->name,
+			 memcg_cache_id(memcg), dentry->d_name.name);
+
+	return name;
+}
+
+static struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg,
+					 struct kmem_cache *s)
+{
+	char *name;
+	struct kmem_cache *new;
+
+	name = memcg_cache_name(memcg, s);
+	if (!name)
+		return NULL;
+
+	new = kmem_cache_create_memcg(memcg, name, s->object_size, s->align,
+				      (s->flags & ~SLAB_PANIC), s->ctor);
+
+	kfree(name);
+	return new;
+}
+
+/*
+ * This lock protects updaters, not readers. We want readers to be as fast as
+ * they can, and they will either see NULL or a valid cache value. Our model
+ * allow them to see NULL, in which case the root memcg will be selected.
+ *
+ * We need this lock because multiple allocations to the same cache from a non
+ * will span more than one worker. Only one of them can create the cache.
+ */
+static DEFINE_MUTEX(memcg_cache_mutex);
+static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
+						  struct kmem_cache *cachep)
+{
+	struct kmem_cache *new_cachep;
+	int idx;
+
+	BUG_ON(!memcg_can_account_kmem(memcg));
+
+	idx = memcg_cache_id(memcg);
+
+	mutex_lock(&memcg_cache_mutex);
+	new_cachep = cachep->memcg_params->memcg_caches[idx];
+	if (new_cachep)
+		goto out;
+
+	new_cachep = kmem_cache_dup(memcg, cachep);
+
+	if (new_cachep == NULL) {
+		new_cachep = cachep;
+		goto out;
+	}
+
+	mem_cgroup_get(memcg);
+	new_cachep->memcg_params->root_cache = cachep;
+
+	cachep->memcg_params->memcg_caches[idx] = new_cachep;
+	/*
+	 * the readers won't lock, make sure everybody sees the updated value,
+	 * so they won't put stuff in the queue again for no reason
+	 */
+	wmb();
+out:
+	mutex_unlock(&memcg_cache_mutex);
+	return new_cachep;
+}
+
+struct create_work {
+	struct mem_cgroup *memcg;
+	struct kmem_cache *cachep;
+	struct work_struct work;
+};
+
+static void memcg_create_cache_work_func(struct work_struct *w)
+{
+	struct create_work *cw;
+
+	cw = container_of(w, struct create_work, work);
+	memcg_create_kmem_cache(cw->memcg, cw->cachep);
+	/* Drop the reference gotten when we enqueued. */
+	css_put(&cw->memcg->css);
+	kfree(cw);
+}
+
+/*
+ * Enqueue the creation of a per-memcg kmem_cache.
+ * Called with rcu_read_lock.
+ */
+static void memcg_create_cache_enqueue(struct mem_cgroup *memcg,
+				       struct kmem_cache *cachep)
+{
+	struct create_work *cw;
+
+	cw = kmalloc(sizeof(struct create_work), GFP_NOWAIT);
+	if (cw == NULL)
+		return;
+
+	/* The corresponding put will be done in the workqueue. */
+	if (!css_tryget(&memcg->css)) {
+		kfree(cw);
+		return;
+	}
+
+	cw->memcg = memcg;
+	cw->cachep = cachep;
+
+	INIT_WORK(&cw->work, memcg_create_cache_work_func);
+	schedule_work(&cw->work);
+}
+
+/*
+ * Return the kmem_cache we're supposed to use for a slab allocation.
+ * We try to use the current memcg's version of the cache.
+ *
+ * If the cache does not exist yet, if we are the first user of it,
+ * we either create it immediately, if possible, or create it asynchronously
+ * in a workqueue.
+ * In the latter case, we will let the current allocation go through with
+ * the original cache.
+ *
+ * Can't be called in interrupt context or from kernel threads.
+ * This function needs to be called with rcu_read_lock() held.
+ */
+struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep,
+					  gfp_t gfp)
+{
+	struct mem_cgroup *memcg;
+	int idx;
+
+	VM_BUG_ON(!cachep->memcg_params);
+	VM_BUG_ON(!cachep->memcg_params->is_root_cache);
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(rcu_dereference(current->mm->owner));
+	rcu_read_unlock();
+
+	if (!memcg_can_account_kmem(memcg))
+		return cachep;
+
+	idx = memcg_cache_id(memcg);
+
+	/*
+	 * barrier to mare sure we're always seeing the up to date value.  The
+	 * code updating memcg_caches will issue a write barrier to match this.
+	 */
+	read_barrier_depends();
+	if (unlikely(cachep->memcg_params->memcg_caches[idx] == NULL)) {
+		/*
+		 * If we are in a safe context (can wait, and not in interrupt
+		 * context), we could be be predictable and return right away.
+		 * This would guarantee that the allocation being performed
+		 * already belongs in the new cache.
+		 *
+		 * However, there are some clashes that can arrive from locking.
+		 * For instance, because we acquire the slab_mutex while doing
+		 * kmem_cache_dup, this means no further allocation could happen
+		 * with the slab_mutex held.
+		 *
+		 * Also, because cache creation issue get_online_cpus(), this
+		 * creates a lock chain: memcg_slab_mutex -> cpu_hotplug_mutex,
+		 * that ends up reversed during cpu hotplug. (cpuset allocates
+		 * a bunch of GFP_KERNEL memory during cpuup). Due to all that,
+		 * better to defer everything.
+		 */
+		memcg_create_cache_enqueue(memcg, cachep);
+		return cachep;
+	}
+
+	return cachep->memcg_params->memcg_caches[idx];
+}
+EXPORT_SYMBOL(__memcg_kmem_get_cache);
+
 /*
  * We need to verify if the allocation against current->mm->owner's memcg is
  * possible for the given order. But the page is not allocated yet, so we'll
-- 
cgit v1.2.3-55-g7522


From 0e9d92f2d02d8c8320f0502307c688d07bdac2b3 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:42 -0800
Subject: memcg: skip memcg kmem allocations in specified code regions

Create a mechanism that skip memcg allocations during certain pieces of
our core code.  It basically works in the same way as
preempt_disable()/preempt_enable(): By marking a region under which all
allocations will be accounted to the root memcg.

We need this to prevent races in early cache creation, when we
allocate data using caches that are not necessarily created already.

Signed-off-by: Glauber Costa <glommer@parallels.com>
yCc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h |  1 +
 mm/memcontrol.c       | 57 ++++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 55 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9914c662ed7b..f712465b05c5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1597,6 +1597,7 @@ struct task_struct {
 		unsigned long nr_pages;	/* uncharged usage */
 		unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
 	} memcg_batch;
+	unsigned int memcg_kmem_skip_account;
 #endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	atomic_t ptrace_bp_refcnt;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index efd26620a60b..65302a083d2f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3025,6 +3025,37 @@ out:
 	kfree(s->memcg_params);
 }
 
+/*
+ * During the creation a new cache, we need to disable our accounting mechanism
+ * altogether. This is true even if we are not creating, but rather just
+ * enqueing new caches to be created.
+ *
+ * This is because that process will trigger allocations; some visible, like
+ * explicit kmallocs to auxiliary data structures, name strings and internal
+ * cache structures; some well concealed, like INIT_WORK() that can allocate
+ * objects during debug.
+ *
+ * If any allocation happens during memcg_kmem_get_cache, we will recurse back
+ * to it. This may not be a bounded recursion: since the first cache creation
+ * failed to complete (waiting on the allocation), we'll just try to create the
+ * cache again, failing at the same point.
+ *
+ * memcg_kmem_get_cache is prepared to abort after seeing a positive count of
+ * memcg_kmem_skip_account. So we enclose anything that might allocate memory
+ * inside the following two functions.
+ */
+static inline void memcg_stop_kmem_account(void)
+{
+	VM_BUG_ON(!current->mm);
+	current->memcg_kmem_skip_account++;
+}
+
+static inline void memcg_resume_kmem_account(void)
+{
+	VM_BUG_ON(!current->mm);
+	current->memcg_kmem_skip_account--;
+}
+
 static char *memcg_cache_name(struct mem_cgroup *memcg, struct kmem_cache *s)
 {
 	char *name;
@@ -3084,7 +3115,6 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 		goto out;
 
 	new_cachep = kmem_cache_dup(memcg, cachep);
-
 	if (new_cachep == NULL) {
 		new_cachep = cachep;
 		goto out;
@@ -3125,8 +3155,8 @@ static void memcg_create_cache_work_func(struct work_struct *w)
  * Enqueue the creation of a per-memcg kmem_cache.
  * Called with rcu_read_lock.
  */
-static void memcg_create_cache_enqueue(struct mem_cgroup *memcg,
-				       struct kmem_cache *cachep)
+static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg,
+					 struct kmem_cache *cachep)
 {
 	struct create_work *cw;
 
@@ -3147,6 +3177,24 @@ static void memcg_create_cache_enqueue(struct mem_cgroup *memcg,
 	schedule_work(&cw->work);
 }
 
+static void memcg_create_cache_enqueue(struct mem_cgroup *memcg,
+				       struct kmem_cache *cachep)
+{
+	/*
+	 * We need to stop accounting when we kmalloc, because if the
+	 * corresponding kmalloc cache is not yet created, the first allocation
+	 * in __memcg_create_cache_enqueue will recurse.
+	 *
+	 * However, it is better to enclose the whole function. Depending on
+	 * the debugging options enabled, INIT_WORK(), for instance, can
+	 * trigger an allocation. This too, will make us recurse. Because at
+	 * this point we can't allow ourselves back into memcg_kmem_get_cache,
+	 * the safest choice is to do it like this, wrapping the whole function.
+	 */
+	memcg_stop_kmem_account();
+	__memcg_create_cache_enqueue(memcg, cachep);
+	memcg_resume_kmem_account();
+}
 /*
  * Return the kmem_cache we're supposed to use for a slab allocation.
  * We try to use the current memcg's version of the cache.
@@ -3169,6 +3217,9 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep,
 	VM_BUG_ON(!cachep->memcg_params);
 	VM_BUG_ON(!cachep->memcg_params->is_root_cache);
 
+	if (!current->mm || current->memcg_kmem_skip_account)
+		return cachep;
+
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(current->mm->owner));
 	rcu_read_unlock();
-- 
cgit v1.2.3-55-g7522


From b9ce5ef49f00daf2254c6953c8d31f79aabccd34 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:46 -0800
Subject: sl[au]b: always get the cache from its page in kmem_cache_free()

struct page already has this information.  If we start chaining caches,
this information will always be more trustworthy than whatever is passed
into the function.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  5 +++++
 mm/slab.c                  |  6 +++++-
 mm/slab.h                  | 39 +++++++++++++++++++++++++++++++++++++++
 mm/slob.c                  |  2 +-
 mm/slub.c                  | 15 +++------------
 5 files changed, 53 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index bd9b5d73bc2b..2298122e71ad 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -554,6 +554,11 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 	return __memcg_kmem_get_cache(cachep, gfp);
 }
 #else
+static inline bool memcg_kmem_enabled(void)
+{
+	return false;
+}
+
 static inline bool
 memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
 {
diff --git a/mm/slab.c b/mm/slab.c
index c26ab9fbe1f5..bab6fec765a7 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -87,7 +87,6 @@
  */
 
 #include	<linux/slab.h>
-#include	"slab.h"
 #include	<linux/mm.h>
 #include	<linux/poison.h>
 #include	<linux/swap.h>
@@ -128,6 +127,8 @@
 
 #include	"internal.h"
 
+#include	"slab.h"
+
 /*
  * DEBUG	- 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
  *		  0 for faster, smaller code (especially in the critical paths).
@@ -3883,6 +3884,9 @@ EXPORT_SYMBOL(__kmalloc);
 void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 {
 	unsigned long flags;
+	cachep = cache_from_obj(cachep, objp);
+	if (!cachep)
+		return;
 
 	local_irq_save(flags);
 	debug_check_no_locks_freed(objp, cachep->object_size);
diff --git a/mm/slab.h b/mm/slab.h
index abe582d20c79..c95e922b166d 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -116,6 +116,13 @@ static inline bool cache_match_memcg(struct kmem_cache *cachep,
 	return (is_root_cache(cachep) && !memcg) ||
 				(cachep->memcg_params->memcg == memcg);
 }
+
+static inline bool slab_equal_or_root(struct kmem_cache *s,
+					struct kmem_cache *p)
+{
+	return (p == s) ||
+		(s->memcg_params && (p == s->memcg_params->root_cache));
+}
 #else
 static inline bool is_root_cache(struct kmem_cache *s)
 {
@@ -127,5 +134,37 @@ static inline bool cache_match_memcg(struct kmem_cache *cachep,
 {
 	return true;
 }
+
+static inline bool slab_equal_or_root(struct kmem_cache *s,
+				      struct kmem_cache *p)
+{
+	return true;
+}
 #endif
+
+static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
+{
+	struct kmem_cache *cachep;
+	struct page *page;
+
+	/*
+	 * When kmemcg is not being used, both assignments should return the
+	 * same value. but we don't want to pay the assignment price in that
+	 * case. If it is not compiled in, the compiler should be smart enough
+	 * to not do even the assignment. In that case, slab_equal_or_root
+	 * will also be a constant.
+	 */
+	if (!memcg_kmem_enabled() && !unlikely(s->flags & SLAB_DEBUG_FREE))
+		return s;
+
+	page = virt_to_head_page(x);
+	cachep = page->slab_cache;
+	if (slab_equal_or_root(cachep, s))
+		return cachep;
+
+	pr_err("%s: Wrong slab cache. %s but object is from %s\n",
+		__FUNCTION__, cachep->name, s->name);
+	WARN_ON_ONCE(1);
+	return s;
+}
 #endif
diff --git a/mm/slob.c b/mm/slob.c
index 795bab7d391d..a99fdf7a0907 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -58,7 +58,6 @@
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include "slab.h"
 
 #include <linux/mm.h>
 #include <linux/swap.h> /* struct reclaim_state */
@@ -73,6 +72,7 @@
 
 #include <linux/atomic.h>
 
+#include "slab.h"
 /*
  * slob_block has a field 'units', which indicates size of block if +ve,
  * or offset of next block if -ve (in SLOB_UNITs).
diff --git a/mm/slub.c b/mm/slub.c
index 985332b38852..6d5f2305d7a4 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2611,19 +2611,10 @@ redo:
 
 void kmem_cache_free(struct kmem_cache *s, void *x)
 {
-	struct page *page;
-
-	page = virt_to_head_page(x);
-
-	if (kmem_cache_debug(s) && page->slab_cache != s) {
-		pr_err("kmem_cache_free: Wrong slab cache. %s but object"
-			" is from  %s\n", page->slab_cache->name, s->name);
-		WARN_ON_ONCE(1);
+	s = cache_from_obj(s, x);
+	if (!s)
 		return;
-	}
-
-	slab_free(s, page, x, _RET_IP_);
-
+	slab_free(s, virt_to_head_page(x), x, _RET_IP_);
 	trace_kmem_cache_free(_RET_IP_, x);
 }
 EXPORT_SYMBOL(kmem_cache_free);
-- 
cgit v1.2.3-55-g7522


From d79923fad95b0cdf7770e024677180c734cb7148 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:48 -0800
Subject: sl[au]b: allocate objects from memcg cache

We are able to match a cache allocation to a particular memcg.  If the
task doesn't change groups during the allocation itself - a rare event,
this will give us a good picture about who is the first group to touch a
cache page.

This patch uses the now available infrastructure by calling
memcg_kmem_get_cache() before all the cache allocations.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slub_def.h | 5 ++++-
 mm/memcontrol.c          | 3 +++
 mm/slab.c                | 6 +++++-
 mm/slub.c                | 7 ++++---
 4 files changed, 16 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 961e72eab907..364ba6c9fe21 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -225,7 +225,10 @@ void *__kmalloc(size_t size, gfp_t flags);
 static __always_inline void *
 kmalloc_order(size_t size, gfp_t flags, unsigned int order)
 {
-	void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order);
+	void *ret;
+
+	flags |= (__GFP_COMP | __GFP_KMEMCG);
+	ret = (void *) __get_free_pages(flags, order);
 	kmemleak_alloc(ret, size, 1, flags);
 	return ret;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 65302a083d2f..cc13797d0fbc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3086,6 +3086,9 @@ static struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg,
 	new = kmem_cache_create_memcg(memcg, name, s->object_size, s->align,
 				      (s->flags & ~SLAB_PANIC), s->ctor);
 
+	if (new)
+		new->allocflags |= __GFP_KMEMCG;
+
 	kfree(name);
 	return new;
 }
diff --git a/mm/slab.c b/mm/slab.c
index bab6fec765a7..e265865e8700 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1933,7 +1933,7 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 	}
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += nr_freed;
-	free_pages((unsigned long)addr, cachep->gfporder);
+	free_memcg_kmem_pages((unsigned long)addr, cachep->gfporder);
 }
 
 static void kmem_rcu_free(struct rcu_head *head)
@@ -3486,6 +3486,8 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	if (slab_should_failslab(cachep, flags))
 		return NULL;
 
+	cachep = memcg_kmem_get_cache(cachep, flags);
+
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 
@@ -3571,6 +3573,8 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
 	if (slab_should_failslab(cachep, flags))
 		return NULL;
 
+	cachep = memcg_kmem_get_cache(cachep, flags);
+
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 	objp = __do_cache_alloc(cachep, flags);
diff --git a/mm/slub.c b/mm/slub.c
index 6d5f2305d7a4..ef39e872b8eb 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1405,7 +1405,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 	reset_page_mapcount(page);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += pages;
-	__free_pages(page, order);
+	__free_memcg_kmem_pages(page, order);
 }
 
 #define need_reserve_slab_rcu						\
@@ -2323,6 +2323,7 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
 	if (slab_pre_alloc_hook(s, gfpflags))
 		return NULL;
 
+	s = memcg_kmem_get_cache(s, gfpflags);
 redo:
 
 	/*
@@ -3284,7 +3285,7 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 	struct page *page;
 	void *ptr = NULL;
 
-	flags |= __GFP_COMP | __GFP_NOTRACK;
+	flags |= __GFP_COMP | __GFP_NOTRACK | __GFP_KMEMCG;
 	page = alloc_pages_node(node, flags, get_order(size));
 	if (page)
 		ptr = page_address(page);
@@ -3390,7 +3391,7 @@ void kfree(const void *x)
 	if (unlikely(!PageSlab(page))) {
 		BUG_ON(!PageCompound(page));
 		kmemleak_free(x);
-		__free_pages(page, compound_order(page));
+		__free_memcg_kmem_pages(page, compound_order(page));
 		return;
 	}
 	slab_free(page->slab_cache, page, object, _RET_IP_);
-- 
cgit v1.2.3-55-g7522


From 1f458cbf122288b23620ee822e19bcbb76c8d6ec Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:50 -0800
Subject: memcg: destroy memcg caches

Implement destruction of memcg caches.  Right now, only caches where our
reference counter is the last remaining are deleted.  If there are any
other reference counters around, we just leave the caches lying around
until they go away.

When that happens, a destruction function is called from the cache code.
Caches are only destroyed in process context, so we queue them up for
later processing in the general case.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  2 ++
 include/linux/slab.h       | 10 +++++++-
 mm/memcontrol.c            | 63 ++++++++++++++++++++++++++++++++++++++++++++++
 mm/slab.c                  |  3 +++
 mm/slab.h                  | 23 +++++++++++++++++
 mm/slub.c                  |  7 +++++-
 6 files changed, 106 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 2298122e71ad..79fcf0cd7186 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -453,6 +453,8 @@ void memcg_update_array_size(int num_groups);
 struct kmem_cache *
 __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
 
+void mem_cgroup_destroy_cache(struct kmem_cache *cachep);
+
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
  * @gfp: the gfp allocation flags.
diff --git a/include/linux/slab.h b/include/linux/slab.h
index c0fcf28c15b2..869efb8d2377 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -11,6 +11,8 @@
 
 #include <linux/gfp.h>
 #include <linux/types.h>
+#include <linux/workqueue.h>
+
 
 /*
  * Flags to pass to kmem_cache_create().
@@ -179,7 +181,6 @@ void kmem_cache_free(struct kmem_cache *, void *);
 #ifndef ARCH_SLAB_MINALIGN
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
-
 /*
  * This is the main placeholder for memcg-related information in kmem caches.
  * struct kmem_cache will hold a pointer to it, so the memory cost while
@@ -197,6 +198,10 @@ void kmem_cache_free(struct kmem_cache *, void *);
  * @memcg: pointer to the memcg this cache belongs to
  * @list: list_head for the list of all caches in this memcg
  * @root_cache: pointer to the global, root cache, this cache was derived from
+ * @dead: set to true after the memcg dies; the cache may still be around.
+ * @nr_pages: number of pages that belongs to this cache.
+ * @destroy: worker to be called whenever we are ready, or believe we may be
+ *           ready, to destroy this cache.
  */
 struct memcg_cache_params {
 	bool is_root_cache;
@@ -206,6 +211,9 @@ struct memcg_cache_params {
 			struct mem_cgroup *memcg;
 			struct list_head list;
 			struct kmem_cache *root_cache;
+			bool dead;
+			atomic_t nr_pages;
+			struct work_struct destroy;
 		};
 	};
 };
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index cc13797d0fbc..270a36789859 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2779,6 +2779,19 @@ static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
 		(memcg->kmem_account_flags & KMEM_ACCOUNTED_MASK);
 }
 
+/*
+ * This is a bit cumbersome, but it is rarely used and avoids a backpointer
+ * in the memcg_cache_params struct.
+ */
+static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
+{
+	struct kmem_cache *cachep;
+
+	VM_BUG_ON(p->is_root_cache);
+	cachep = p->root_cache;
+	return cachep->memcg_params->memcg_caches[memcg_cache_id(p->memcg)];
+}
+
 static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 {
 	struct res_counter *fail_res;
@@ -3056,6 +3069,31 @@ static inline void memcg_resume_kmem_account(void)
 	current->memcg_kmem_skip_account--;
 }
 
+static void kmem_cache_destroy_work_func(struct work_struct *w)
+{
+	struct kmem_cache *cachep;
+	struct memcg_cache_params *p;
+
+	p = container_of(w, struct memcg_cache_params, destroy);
+
+	cachep = memcg_params_to_cache(p);
+
+	if (!atomic_read(&cachep->memcg_params->nr_pages))
+		kmem_cache_destroy(cachep);
+}
+
+void mem_cgroup_destroy_cache(struct kmem_cache *cachep)
+{
+	if (!cachep->memcg_params->dead)
+		return;
+
+	/*
+	 * We have to defer the actual destroying to a workqueue, because
+	 * we might currently be in a context that cannot sleep.
+	 */
+	schedule_work(&cachep->memcg_params->destroy);
+}
+
 static char *memcg_cache_name(struct mem_cgroup *memcg, struct kmem_cache *s)
 {
 	char *name;
@@ -3125,6 +3163,7 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 
 	mem_cgroup_get(memcg);
 	new_cachep->memcg_params->root_cache = cachep;
+	atomic_set(&new_cachep->memcg_params->nr_pages , 0);
 
 	cachep->memcg_params->memcg_caches[idx] = new_cachep;
 	/*
@@ -3143,6 +3182,25 @@ struct create_work {
 	struct work_struct work;
 };
 
+static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
+{
+	struct kmem_cache *cachep;
+	struct memcg_cache_params *params;
+
+	if (!memcg_kmem_is_active(memcg))
+		return;
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_for_each_entry(params, &memcg->memcg_slab_caches, list) {
+		cachep = memcg_params_to_cache(params);
+		cachep->memcg_params->dead = true;
+		INIT_WORK(&cachep->memcg_params->destroy,
+			  kmem_cache_destroy_work_func);
+		schedule_work(&cachep->memcg_params->destroy);
+	}
+	mutex_unlock(&memcg->slab_caches_mutex);
+}
+
 static void memcg_create_cache_work_func(struct work_struct *w)
 {
 	struct create_work *cw;
@@ -3358,6 +3416,10 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
 	VM_BUG_ON(mem_cgroup_is_root(memcg));
 	memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
 }
+#else
+static inline void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
+{
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -5975,6 +6037,7 @@ static void mem_cgroup_css_offline(struct cgroup *cont)
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
 	mem_cgroup_reparent_charges(memcg);
+	mem_cgroup_destroy_all_caches(memcg);
 }
 
 static void mem_cgroup_css_free(struct cgroup *cont)
diff --git a/mm/slab.c b/mm/slab.c
index e265865e8700..7467343f9fe7 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1895,6 +1895,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 		if (page->pfmemalloc)
 			SetPageSlabPfmemalloc(page + i);
 	}
+	memcg_bind_pages(cachep, cachep->gfporder);
 
 	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
 		kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid);
@@ -1931,6 +1932,8 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 		__ClearPageSlab(page);
 		page++;
 	}
+
+	memcg_release_pages(cachep, cachep->gfporder);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += nr_freed;
 	free_memcg_kmem_pages((unsigned long)addr, cachep->gfporder);
diff --git a/mm/slab.h b/mm/slab.h
index c95e922b166d..43d8a38b534f 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -117,6 +117,21 @@ static inline bool cache_match_memcg(struct kmem_cache *cachep,
 				(cachep->memcg_params->memcg == memcg);
 }
 
+static inline void memcg_bind_pages(struct kmem_cache *s, int order)
+{
+	if (!is_root_cache(s))
+		atomic_add(1 << order, &s->memcg_params->nr_pages);
+}
+
+static inline void memcg_release_pages(struct kmem_cache *s, int order)
+{
+	if (is_root_cache(s))
+		return;
+
+	if (atomic_sub_and_test((1 << order), &s->memcg_params->nr_pages))
+		mem_cgroup_destroy_cache(s);
+}
+
 static inline bool slab_equal_or_root(struct kmem_cache *s,
 					struct kmem_cache *p)
 {
@@ -135,6 +150,14 @@ static inline bool cache_match_memcg(struct kmem_cache *cachep,
 	return true;
 }
 
+static inline void memcg_bind_pages(struct kmem_cache *s, int order)
+{
+}
+
+static inline void memcg_release_pages(struct kmem_cache *s, int order)
+{
+}
+
 static inline bool slab_equal_or_root(struct kmem_cache *s,
 				      struct kmem_cache *p)
 {
diff --git a/mm/slub.c b/mm/slub.c
index ef39e872b8eb..692177bebdf0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1344,6 +1344,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	void *start;
 	void *last;
 	void *p;
+	int order;
 
 	BUG_ON(flags & GFP_SLAB_BUG_MASK);
 
@@ -1352,7 +1353,9 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if (!page)
 		goto out;
 
+	order = compound_order(page);
 	inc_slabs_node(s, page_to_nid(page), page->objects);
+	memcg_bind_pages(s, order);
 	page->slab_cache = s;
 	__SetPageSlab(page);
 	if (page->pfmemalloc)
@@ -1361,7 +1364,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	start = page_address(page);
 
 	if (unlikely(s->flags & SLAB_POISON))
-		memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));
+		memset(start, POISON_INUSE, PAGE_SIZE << order);
 
 	last = start;
 	for_each_object(p, s, start, page->objects) {
@@ -1402,6 +1405,8 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 
 	__ClearPageSlabPfmemalloc(page);
 	__ClearPageSlab(page);
+
+	memcg_release_pages(s, order);
 	reset_page_mapcount(page);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += pages;
-- 
cgit v1.2.3-55-g7522


From 7cf2798240a2a2230cb16a391beef98d8a7ad362 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:22:55 -0800
Subject: memcg/sl[au]b: track all the memcg children of a kmem_cache

This enables us to remove all the children of a kmem_cache being
destroyed, if for example the kernel module it's being used in gets
unloaded.  Otherwise, the children will still point to the destroyed
parent.

Signed-off-by: Suleiman Souhlal <suleiman@google.com>
Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  5 +++++
 mm/memcontrol.c            | 49 ++++++++++++++++++++++++++++++++++++++++++++--
 mm/slab_common.c           |  3 +++
 3 files changed, 55 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 79fcf0cd7186..e119f3ef793c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -454,6 +454,7 @@ struct kmem_cache *
 __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
 
 void mem_cgroup_destroy_cache(struct kmem_cache *cachep);
+void kmem_cache_destroy_memcg_children(struct kmem_cache *s);
 
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
@@ -601,6 +602,10 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	return cachep;
 }
+
+static inline void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+{
+}
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 270a36789859..4b68ec2c8df6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2772,6 +2772,8 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	memcg_check_events(memcg, page);
 }
 
+static DEFINE_MUTEX(set_limit_mutex);
+
 #ifdef CONFIG_MEMCG_KMEM
 static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
 {
@@ -3176,6 +3178,51 @@ out:
 	return new_cachep;
 }
 
+void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+{
+	struct kmem_cache *c;
+	int i;
+
+	if (!s->memcg_params)
+		return;
+	if (!s->memcg_params->is_root_cache)
+		return;
+
+	/*
+	 * If the cache is being destroyed, we trust that there is no one else
+	 * requesting objects from it. Even if there are, the sanity checks in
+	 * kmem_cache_destroy should caught this ill-case.
+	 *
+	 * Still, we don't want anyone else freeing memcg_caches under our
+	 * noses, which can happen if a new memcg comes to life. As usual,
+	 * we'll take the set_limit_mutex to protect ourselves against this.
+	 */
+	mutex_lock(&set_limit_mutex);
+	for (i = 0; i < memcg_limited_groups_array_size; i++) {
+		c = s->memcg_params->memcg_caches[i];
+		if (!c)
+			continue;
+
+		/*
+		 * We will now manually delete the caches, so to avoid races
+		 * we need to cancel all pending destruction workers and
+		 * proceed with destruction ourselves.
+		 *
+		 * kmem_cache_destroy() will call kmem_cache_shrink internally,
+		 * and that could spawn the workers again: it is likely that
+		 * the cache still have active pages until this very moment.
+		 * This would lead us back to mem_cgroup_destroy_cache.
+		 *
+		 * But that will not execute at all if the "dead" flag is not
+		 * set, so flip it down to guarantee we are in control.
+		 */
+		c->memcg_params->dead = false;
+		cancel_delayed_work_sync(&c->memcg_params->destroy);
+		kmem_cache_destroy(c);
+	}
+	mutex_unlock(&set_limit_mutex);
+}
+
 struct create_work {
 	struct mem_cgroup *memcg;
 	struct kmem_cache *cachep;
@@ -4284,8 +4331,6 @@ void mem_cgroup_print_bad_page(struct page *page)
 }
 #endif
 
-static DEFINE_MUTEX(set_limit_mutex);
-
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 				unsigned long long val)
 {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 1c424b6511bf..080a43804bf1 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -249,6 +249,9 @@ EXPORT_SYMBOL(kmem_cache_create);
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
+	/* Destroy all the children caches if we aren't a memcg cache */
+	kmem_cache_destroy_memcg_children(s);
+
 	get_online_cpus();
 	mutex_lock(&slab_mutex);
 	s->refcount--;
-- 
cgit v1.2.3-55-g7522


From 749c54151a6e5b229e4ae067dbc651e54b161fbc Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:23:01 -0800
Subject: memcg: aggregate memcg cache values in slabinfo

When we create caches in memcgs, we need to display their usage
information somewhere.  We'll adopt a scheme similar to /proc/meminfo,
with aggregate totals shown in the global file, and per-group information
stored in the group itself.

For the time being, only reads are allowed in the per-group cache.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  8 ++++++++
 include/linux/slab.h       |  4 ++++
 mm/memcontrol.c            | 30 +++++++++++++++++++++++++++++-
 mm/slab.h                  | 27 +++++++++++++++++++++++++++
 mm/slab_common.c           | 44 ++++++++++++++++++++++++++++++++++++++++----
 5 files changed, 108 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e119f3ef793c..8dc7c746b44f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -420,6 +420,11 @@ static inline void sock_release_memcg(struct sock *sk)
 
 #ifdef CONFIG_MEMCG_KMEM
 extern struct static_key memcg_kmem_enabled_key;
+
+extern int memcg_limited_groups_array_size;
+#define for_each_memcg_cache_index(_idx)	\
+	for ((_idx) = 0; i < memcg_limited_groups_array_size; (_idx)++)
+
 static inline bool memcg_kmem_enabled(void)
 {
 	return static_key_false(&memcg_kmem_enabled_key);
@@ -557,6 +562,9 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 	return __memcg_kmem_get_cache(cachep, gfp);
 }
 #else
+#define for_each_memcg_cache_index(_idx)	\
+	for (; NULL; )
+
 static inline bool memcg_kmem_enabled(void)
 {
 	return false;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 869efb8d2377..b9278663f22a 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -220,6 +220,10 @@ struct memcg_cache_params {
 
 int memcg_update_all_caches(int num_memcgs);
 
+struct seq_file;
+int cache_show(struct kmem_cache *s, struct seq_file *m);
+void print_slabinfo_header(struct seq_file *m);
+
 /*
  * Common kmalloc functions provided by all allocators
  */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7633e0d429e0..a32d83c2e353 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -572,7 +572,8 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
  * increase it.
  */
 static DEFINE_IDA(kmem_limited_groups);
-static int memcg_limited_groups_array_size;
+int memcg_limited_groups_array_size;
+
 /*
  * MIN_SIZE is different than 1, because we would like to avoid going through
  * the alloc/free process all the time. In a small machine, 4 kmem-limited
@@ -2794,6 +2795,27 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
 	return cachep->memcg_params->memcg_caches[memcg_cache_id(p->memcg)];
 }
 
+#ifdef CONFIG_SLABINFO
+static int mem_cgroup_slabinfo_read(struct cgroup *cont, struct cftype *cft,
+					struct seq_file *m)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	struct memcg_cache_params *params;
+
+	if (!memcg_can_account_kmem(memcg))
+		return -EIO;
+
+	print_slabinfo_header(m);
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_for_each_entry(params, &memcg->memcg_slab_caches, list)
+		cache_show(memcg_params_to_cache(params), m);
+	mutex_unlock(&memcg->slab_caches_mutex);
+
+	return 0;
+}
+#endif
+
 static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 {
 	struct res_counter *fail_res;
@@ -5822,6 +5844,12 @@ static struct cftype mem_cgroup_files[] = {
 		.trigger = mem_cgroup_reset,
 		.read = mem_cgroup_read,
 	},
+#ifdef CONFIG_SLABINFO
+	{
+		.name = "kmem.slabinfo",
+		.read_seq_string = mem_cgroup_slabinfo_read,
+	},
+#endif
 #endif
 	{ },	/* terminate */
 };
diff --git a/mm/slab.h b/mm/slab.h
index 43d8a38b534f..ec5dae1c8e75 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -138,6 +138,23 @@ static inline bool slab_equal_or_root(struct kmem_cache *s,
 	return (p == s) ||
 		(s->memcg_params && (p == s->memcg_params->root_cache));
 }
+
+/*
+ * We use suffixes to the name in memcg because we can't have caches
+ * created in the system with the same name. But when we print them
+ * locally, better refer to them with the base name
+ */
+static inline const char *cache_name(struct kmem_cache *s)
+{
+	if (!is_root_cache(s))
+		return s->memcg_params->root_cache->name;
+	return s->name;
+}
+
+static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
+{
+	return s->memcg_params->memcg_caches[idx];
+}
 #else
 static inline bool is_root_cache(struct kmem_cache *s)
 {
@@ -163,6 +180,16 @@ static inline bool slab_equal_or_root(struct kmem_cache *s,
 {
 	return true;
 }
+
+static inline const char *cache_name(struct kmem_cache *s)
+{
+	return s->name;
+}
+
+static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
+{
+	return NULL;
+}
 #endif
 
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 080a43804bf1..081f1b8d9a7b 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -322,7 +322,7 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
 
 
 #ifdef CONFIG_SLABINFO
-static void print_slabinfo_header(struct seq_file *m)
+void print_slabinfo_header(struct seq_file *m)
 {
 	/*
 	 * Output format version, so at least we can change it
@@ -366,16 +366,43 @@ static void s_stop(struct seq_file *m, void *p)
 	mutex_unlock(&slab_mutex);
 }
 
-static int s_show(struct seq_file *m, void *p)
+static void
+memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
+{
+	struct kmem_cache *c;
+	struct slabinfo sinfo;
+	int i;
+
+	if (!is_root_cache(s))
+		return;
+
+	for_each_memcg_cache_index(i) {
+		c = cache_from_memcg(s, i);
+		if (!c)
+			continue;
+
+		memset(&sinfo, 0, sizeof(sinfo));
+		get_slabinfo(c, &sinfo);
+
+		info->active_slabs += sinfo.active_slabs;
+		info->num_slabs += sinfo.num_slabs;
+		info->shared_avail += sinfo.shared_avail;
+		info->active_objs += sinfo.active_objs;
+		info->num_objs += sinfo.num_objs;
+	}
+}
+
+int cache_show(struct kmem_cache *s, struct seq_file *m)
 {
-	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
 	struct slabinfo sinfo;
 
 	memset(&sinfo, 0, sizeof(sinfo));
 	get_slabinfo(s, &sinfo);
 
+	memcg_accumulate_slabinfo(s, &sinfo);
+
 	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
-		   s->name, sinfo.active_objs, sinfo.num_objs, s->size,
+		   cache_name(s), sinfo.active_objs, sinfo.num_objs, s->size,
 		   sinfo.objects_per_slab, (1 << sinfo.cache_order));
 
 	seq_printf(m, " : tunables %4u %4u %4u",
@@ -387,6 +414,15 @@ static int s_show(struct seq_file *m, void *p)
 	return 0;
 }
 
+static int s_show(struct seq_file *m, void *p)
+{
+	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+
+	if (!is_root_cache(s))
+		return 0;
+	return cache_show(s, m);
+}
+
 /*
  * slabinfo_op - iterator that generates /proc/slabinfo
  *
-- 
cgit v1.2.3-55-g7522


From 943a451a87d229ca564a27274b58eaeae35fde5d Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:23:03 -0800
Subject: slab: propagate tunable values

SLAB allows us to tune a particular cache behavior with tunables.  When
creating a new memcg cache copy, we'd like to preserve any tunables the
parent cache already had.

This could be done by an explicit call to do_tune_cpucache() after the
cache is created.  But this is not very convenient now that the caches are
created from common code, since this function is SLAB-specific.

Another method of doing that is taking advantage of the fact that
do_tune_cpucache() is always called from enable_cpucache(), which is
called at cache initialization.  We can just preset the values, and then
things work as expected.

It can also happen that a root cache has its tunables updated during
normal system operation.  In this case, we will propagate the change to
all caches that are already active.

This change will require us to move the assignment of root_cache in
memcg_params a bit earlier.  We need this to be already set - which
memcg_kmem_register_cache will do - when we reach __kmem_cache_create()

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  8 +++++---
 include/linux/slab.h       |  2 +-
 mm/memcontrol.c            | 10 ++++++----
 mm/slab.c                  | 44 +++++++++++++++++++++++++++++++++++++++++---
 mm/slab.h                  | 12 ++++++++++++
 mm/slab_common.c           |  7 ++++---
 6 files changed, 69 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 8dc7c746b44f..ea02ff970836 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -448,7 +448,8 @@ void __memcg_kmem_commit_charge(struct page *page,
 void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
 int memcg_cache_id(struct mem_cgroup *memcg);
-int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s);
+int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
+			 struct kmem_cache *root_cache);
 void memcg_release_cache(struct kmem_cache *cachep);
 void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep);
 
@@ -590,8 +591,9 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return -1;
 }
 
-static inline int memcg_register_cache(struct mem_cgroup *memcg,
-				       struct kmem_cache *s)
+static inline int
+memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
+		     struct kmem_cache *root_cache)
 {
 	return 0;
 }
diff --git a/include/linux/slab.h b/include/linux/slab.h
index b9278663f22a..5d168d7e0a28 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -130,7 +130,7 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			void (*)(void *));
 struct kmem_cache *
 kmem_cache_create_memcg(struct mem_cgroup *, const char *, size_t, size_t,
-			unsigned long, void (*)(void *));
+			unsigned long, void (*)(void *), struct kmem_cache *);
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
 void kmem_cache_free(struct kmem_cache *, void *);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a32d83c2e353..f3009b4bae51 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3012,7 +3012,8 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
 	return 0;
 }
 
-int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s)
+int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
+			 struct kmem_cache *root_cache)
 {
 	size_t size = sizeof(struct memcg_cache_params);
 
@@ -3026,8 +3027,10 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s)
 	if (!s->memcg_params)
 		return -ENOMEM;
 
-	if (memcg)
+	if (memcg) {
 		s->memcg_params->memcg = memcg;
+		s->memcg_params->root_cache = root_cache;
+	}
 	return 0;
 }
 
@@ -3186,7 +3189,7 @@ static struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg,
 		return NULL;
 
 	new = kmem_cache_create_memcg(memcg, name, s->object_size, s->align,
-				      (s->flags & ~SLAB_PANIC), s->ctor);
+				      (s->flags & ~SLAB_PANIC), s->ctor, s);
 
 	if (new)
 		new->allocflags |= __GFP_KMEMCG;
@@ -3226,7 +3229,6 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	}
 
 	mem_cgroup_get(memcg);
-	new_cachep->memcg_params->root_cache = cachep;
 	atomic_set(&new_cachep->memcg_params->nr_pages , 0);
 
 	cachep->memcg_params->memcg_caches[idx] = new_cachep;
diff --git a/mm/slab.c b/mm/slab.c
index 7467343f9fe7..4dcbf96a77b4 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4041,7 +4041,7 @@ static void do_ccupdate_local(void *info)
 }
 
 /* Always called with the slab_mutex held */
-static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
+static int __do_tune_cpucache(struct kmem_cache *cachep, int limit,
 				int batchcount, int shared, gfp_t gfp)
 {
 	struct ccupdate_struct *new;
@@ -4084,12 +4084,48 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 	return alloc_kmemlist(cachep, gfp);
 }
 
+static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
+				int batchcount, int shared, gfp_t gfp)
+{
+	int ret;
+	struct kmem_cache *c = NULL;
+	int i = 0;
+
+	ret = __do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
+
+	if (slab_state < FULL)
+		return ret;
+
+	if ((ret < 0) || !is_root_cache(cachep))
+		return ret;
+
+	for_each_memcg_cache_index(i) {
+		c = cache_from_memcg(cachep, i);
+		if (c)
+			/* return value determined by the parent cache only */
+			__do_tune_cpucache(c, limit, batchcount, shared, gfp);
+	}
+
+	return ret;
+}
+
 /* Called with slab_mutex held always */
 static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	int err;
-	int limit, shared;
+	int limit = 0;
+	int shared = 0;
+	int batchcount = 0;
+
+	if (!is_root_cache(cachep)) {
+		struct kmem_cache *root = memcg_root_cache(cachep);
+		limit = root->limit;
+		shared = root->shared;
+		batchcount = root->batchcount;
+	}
 
+	if (limit && shared && batchcount)
+		goto skip_setup;
 	/*
 	 * The head array serves three purposes:
 	 * - create a LIFO ordering, i.e. return objects that are cache-warm
@@ -4131,7 +4167,9 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
 	if (limit > 32)
 		limit = 32;
 #endif
-	err = do_tune_cpucache(cachep, limit, (limit + 1) / 2, shared, gfp);
+	batchcount = (limit + 1) / 2;
+skip_setup:
+	err = do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
 	if (err)
 		printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n",
 		       cachep->name, -err);
diff --git a/mm/slab.h b/mm/slab.h
index ec5dae1c8e75..34a98d642196 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -155,6 +155,13 @@ static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
 {
 	return s->memcg_params->memcg_caches[idx];
 }
+
+static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
+{
+	if (is_root_cache(s))
+		return s;
+	return s->memcg_params->root_cache;
+}
 #else
 static inline bool is_root_cache(struct kmem_cache *s)
 {
@@ -190,6 +197,11 @@ static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
 {
 	return NULL;
 }
+
+static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
+{
+	return s;
+}
 #endif
 
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 081f1b8d9a7b..3f3cd97d3fdf 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -164,7 +164,8 @@ unsigned long calculate_alignment(unsigned long flags,
 
 struct kmem_cache *
 kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
-			size_t align, unsigned long flags, void (*ctor)(void *))
+			size_t align, unsigned long flags, void (*ctor)(void *),
+			struct kmem_cache *parent_cache)
 {
 	struct kmem_cache *s = NULL;
 	int err = 0;
@@ -193,7 +194,7 @@ kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
 		s->align = calculate_alignment(flags, align, size);
 		s->ctor = ctor;
 
-		if (memcg_register_cache(memcg, s)) {
+		if (memcg_register_cache(memcg, s, parent_cache)) {
 			kmem_cache_free(kmem_cache, s);
 			err = -ENOMEM;
 			goto out_locked;
@@ -243,7 +244,7 @@ struct kmem_cache *
 kmem_cache_create(const char *name, size_t size, size_t align,
 		  unsigned long flags, void (*ctor)(void *))
 {
-	return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor);
+	return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL);
 }
 EXPORT_SYMBOL(kmem_cache_create);
 
-- 
cgit v1.2.3-55-g7522


From 107dab5c92d5f9c3afe962036e47c207363255c7 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:23:05 -0800
Subject: slub: slub-specific propagation changes

SLUB allows us to tune a particular cache behavior with sysfs-based
tunables.  When creating a new memcg cache copy, we'd like to preserve any
tunables the parent cache already had.

This can be done by tapping into the store attribute function provided by
the allocator.  We of course don't need to mess with read-only fields.
Since the attributes can have multiple types and are stored internally by
sysfs, the best strategy is to issue a ->show() in the root cache, and
then ->store() in the memcg cache.

The drawback of that, is that sysfs can allocate up to a page in buffering
for show(), that we are likely not to need, but also can't guarantee.  To
avoid always allocating a page for that, we can update the caches at store
time with the maximum attribute size ever stored to the root cache.  We
will then get a buffer big enough to hold it.  The corolary to this, is
that if no stores happened, nothing will be propagated.

It can also happen that a root cache has its tunables updated during
normal system operation.  In this case, we will propagate the change to
all caches that are already active.

[akpm@linux-foundation.org: tweak code to avoid __maybe_unused]
Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slub_def.h |  1 +
 mm/slub.c                | 76 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 76 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 364ba6c9fe21..9db4825cd393 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -103,6 +103,7 @@ struct kmem_cache {
 #endif
 #ifdef CONFIG_MEMCG_KMEM
 	struct memcg_cache_params *memcg_params;
+	int max_attr_size; /* for propagation, maximum size of a stored attr */
 #endif
 
 #ifdef CONFIG_NUMA
diff --git a/mm/slub.c b/mm/slub.c
index 692177bebdf0..21c94d9695ec 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -201,13 +201,14 @@ enum track_item { TRACK_ALLOC, TRACK_FREE };
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
 static void sysfs_slab_remove(struct kmem_cache *);
-
+static void memcg_propagate_slab_attrs(struct kmem_cache *s);
 #else
 static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
 static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
 							{ return 0; }
 static inline void sysfs_slab_remove(struct kmem_cache *s) { }
 
+static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
 #endif
 
 static inline void stat(const struct kmem_cache *s, enum stat_item si)
@@ -3865,6 +3866,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
 	if (slab_state <= UP)
 		return 0;
 
+	memcg_propagate_slab_attrs(s);
 	mutex_unlock(&slab_mutex);
 	err = sysfs_slab_add(s);
 	mutex_lock(&slab_mutex);
@@ -5098,10 +5100,82 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		return -EIO;
 
 	err = attribute->store(s, buf, len);
+#ifdef CONFIG_MEMCG_KMEM
+	if (slab_state >= FULL && err >= 0 && is_root_cache(s)) {
+		int i;
+
+		mutex_lock(&slab_mutex);
+		if (s->max_attr_size < len)
+			s->max_attr_size = len;
 
+		for_each_memcg_cache_index(i) {
+			struct kmem_cache *c = cache_from_memcg(s, i);
+			/*
+			 * This function's return value is determined by the
+			 * parent cache only
+			 */
+			if (c)
+				attribute->store(c, buf, len);
+		}
+		mutex_unlock(&slab_mutex);
+	}
+#endif
 	return err;
 }
 
+static void memcg_propagate_slab_attrs(struct kmem_cache *s)
+{
+#ifdef CONFIG_MEMCG_KMEM
+	int i;
+	char *buffer = NULL;
+
+	if (!is_root_cache(s))
+		return;
+
+	/*
+	 * This mean this cache had no attribute written. Therefore, no point
+	 * in copying default values around
+	 */
+	if (!s->max_attr_size)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) {
+		char mbuf[64];
+		char *buf;
+		struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
+
+		if (!attr || !attr->store || !attr->show)
+			continue;
+
+		/*
+		 * It is really bad that we have to allocate here, so we will
+		 * do it only as a fallback. If we actually allocate, though,
+		 * we can just use the allocated buffer until the end.
+		 *
+		 * Most of the slub attributes will tend to be very small in
+		 * size, but sysfs allows buffers up to a page, so they can
+		 * theoretically happen.
+		 */
+		if (buffer)
+			buf = buffer;
+		else if (s->max_attr_size < ARRAY_SIZE(mbuf))
+			buf = mbuf;
+		else {
+			buffer = (char *) get_zeroed_page(GFP_KERNEL);
+			if (WARN_ON(!buffer))
+				continue;
+			buf = buffer;
+		}
+
+		attr->show(s->memcg_params->root_cache, buf);
+		attr->store(s, buf, strlen(buf));
+	}
+
+	if (buffer)
+		free_page((unsigned long)buffer);
+#endif
+}
+
 static const struct sysfs_ops slab_sysfs_ops = {
 	.show = slab_attr_show,
 	.store = slab_attr_store,
-- 
cgit v1.2.3-55-g7522


From ebe945c27628fca03723582eba138acc2e2f3d15 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Tue, 18 Dec 2012 14:23:10 -0800
Subject: memcg: add comments clarifying aspects of cache attribute propagation

This patch clarifies two aspects of cache attribute propagation.

First, the expected context for the for_each_memcg_cache macro in
memcontrol.h.  The usages already in the codebase are safe.  In mm/slub.c,
it is trivially safe because the lock is acquired right before the loop.
In mm/slab.c, it is less so: the lock is acquired by an outer function a
few steps back in the stack, so a VM_BUG_ON() is added to make sure it is
indeed safe.

A comment is also added to detail why we are returning the value of the
parent cache and ignoring the children's when we propagate the attributes.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  6 ++++++
 mm/slab.c                  |  1 +
 mm/slub.c                  | 21 +++++++++++++++++----
 3 files changed, 24 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ea02ff970836..0108a56f814e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -422,6 +422,12 @@ static inline void sock_release_memcg(struct sock *sk)
 extern struct static_key memcg_kmem_enabled_key;
 
 extern int memcg_limited_groups_array_size;
+
+/*
+ * Helper macro to loop through all memcg-specific caches. Callers must still
+ * check if the cache is valid (it is either valid or NULL).
+ * the slab_mutex must be held when looping through those caches
+ */
 #define for_each_memcg_cache_index(_idx)	\
 	for ((_idx) = 0; i < memcg_limited_groups_array_size; (_idx)++)
 
diff --git a/mm/slab.c b/mm/slab.c
index 4dcbf96a77b4..e7667a3584bc 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4099,6 +4099,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 	if ((ret < 0) || !is_root_cache(cachep))
 		return ret;
 
+	VM_BUG_ON(!mutex_is_locked(&slab_mutex));
 	for_each_memcg_cache_index(i) {
 		c = cache_from_memcg(cachep, i);
 		if (c)
diff --git a/mm/slub.c b/mm/slub.c
index 21c94d9695ec..efe2cffc29b0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5108,12 +5108,25 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		if (s->max_attr_size < len)
 			s->max_attr_size = len;
 
+		/*
+		 * This is a best effort propagation, so this function's return
+		 * value will be determined by the parent cache only. This is
+		 * basically because not all attributes will have a well
+		 * defined semantics for rollbacks - most of the actions will
+		 * have permanent effects.
+		 *
+		 * Returning the error value of any of the children that fail
+		 * is not 100 % defined, in the sense that users seeing the
+		 * error code won't be able to know anything about the state of
+		 * the cache.
+		 *
+		 * Only returning the error code for the parent cache at least
+		 * has well defined semantics. The cache being written to
+		 * directly either failed or succeeded, in which case we loop
+		 * through the descendants with best-effort propagation.
+		 */
 		for_each_memcg_cache_index(i) {
 			struct kmem_cache *c = cache_from_memcg(s, i);
-			/*
-			 * This function's return value is determined by the
-			 * parent cache only
-			 */
 			if (c)
 				attribute->store(c, buf, len);
 		}
-- 
cgit v1.2.3-55-g7522


From 7179e7bf4592ac5a7b30257a7df6259ee81e51da Mon Sep 17 00:00:00 2001
From: Jianguo Wu
Date: Tue, 18 Dec 2012 14:23:19 -0800
Subject: mm/hugetlb: create hugetlb cgroup file in hugetlb_init

Build kernel with CONFIG_HUGETLBFS=y,CONFIG_HUGETLB_PAGE=y and
CONFIG_CGROUP_HUGETLB=y, then specify hugepagesz=xx boot option, system
will fail to boot.

This failure is caused by following code path:

  setup_hugepagesz
    hugetlb_add_hstate
      hugetlb_cgroup_file_init
        cgroup_add_cftypes
          kzalloc <--slab is *not available* yet

For this path, slab is not available yet, so memory allocated will be
failed, and cause WARN_ON() in hugetlb_cgroup_file_init().

So I move hugetlb_cgroup_file_init() into hugetlb_init().

[akpm@linux-foundation.org: tweak coding-style, remove pointless __init on inlined function]
[akpm@linux-foundation.org: fix warning]
Signed-off-by: Jianguo Wu <wujianguo@huawei.com>
Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb_cgroup.h |  5 ++---
 mm/hugetlb.c                   | 11 +----------
 mm/hugetlb_cgroup.c            | 19 +++++++++++++++++--
 3 files changed, 20 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index d73878c694b3..ce8217f7b5c2 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -62,7 +62,7 @@ extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 					 struct page *page);
 extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
 					   struct hugetlb_cgroup *h_cg);
-extern int hugetlb_cgroup_file_init(int idx) __init;
+extern void hugetlb_cgroup_file_init(void) __init;
 extern void hugetlb_cgroup_migrate(struct page *oldhpage,
 				   struct page *newhpage);
 
@@ -111,9 +111,8 @@ hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
 	return;
 }
 
-static inline int __init hugetlb_cgroup_file_init(int idx)
+static inline void hugetlb_cgroup_file_init(void)
 {
-	return 0;
 }
 
 static inline void hugetlb_cgroup_migrate(struct page *oldhpage,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e5318c7793ae..4f3ea0b1e57c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1906,14 +1906,12 @@ static int __init hugetlb_init(void)
 		default_hstate.max_huge_pages = default_hstate_max_huge_pages;
 
 	hugetlb_init_hstates();
-
 	gather_bootmem_prealloc();
-
 	report_hugepages();
 
 	hugetlb_sysfs_init();
-
 	hugetlb_register_all_nodes();
+	hugetlb_cgroup_file_init();
 
 	return 0;
 }
@@ -1943,13 +1941,6 @@ void __init hugetlb_add_hstate(unsigned order)
 	h->next_nid_to_free = first_node(node_states[N_MEMORY]);
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
-	/*
-	 * Add cgroup control files only if the huge page consists
-	 * of more than two normal pages. This is because we use
-	 * page[2].lru.next for storing cgoup details.
-	 */
-	if (order >= HUGETLB_CGROUP_MIN_ORDER)
-		hugetlb_cgroup_file_init(hugetlb_max_hstate - 1);
 
 	parsed_hstate = h;
 }
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index b5bde7a5c017..9cea7de22ffb 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -333,7 +333,7 @@ static char *mem_fmt(char *buf, int size, unsigned long hsize)
 	return buf;
 }
 
-int __init hugetlb_cgroup_file_init(int idx)
+static void __init __hugetlb_cgroup_file_init(int idx)
 {
 	char buf[32];
 	struct cftype *cft;
@@ -375,7 +375,22 @@ int __init hugetlb_cgroup_file_init(int idx)
 
 	WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files));
 
-	return 0;
+	return;
+}
+
+void __init hugetlb_cgroup_file_init(void)
+{
+	struct hstate *h;
+
+	for_each_hstate(h) {
+		/*
+		 * Add cgroup control files only if the huge page consists
+		 * of more than two normal pages. This is because we use
+		 * page[2].lru.next for storing cgroup details.
+		 */
+		if (huge_page_order(h) >= HUGETLB_CGROUP_MIN_ORDER)
+			__hugetlb_cgroup_file_init(hstate_index(h));
+	}
 }
 
 /*
-- 
cgit v1.2.3-55-g7522


From 59771079c18c44e39106f0f30054025acafadb41 Mon Sep 17 00:00:00 2001
From: Linus Torvalds
Date: Wed, 19 Dec 2012 07:18:35 -0800
Subject: blk: avoid divide-by-zero with zero discard granularity

Commit 8dd2cb7e880d ("block: discard granularity might not be power of
2") changed a couple of 'binary and' operations into modulus operations.
Which turned the harmless case of a zero discard_granularity into a
possible divide-by-zero.

The code also had a much more subtle bug: it was doing the modulus of a
value in bytes using 'sector_t'.  That was always conceptually wrong,
but didn't actually matter back when the code assumed a power-of-two
granularity: we only looked at the low bits anyway.

But with potentially arbitrary sector numbers, using a 'sector_t' to
express bytes is very very wrong: depending on configuration it limits
the starting offset of the device to just 32 bits, and any overflow
would result in a wrong value if the modulus wasn't a power-of-two.

So re-write the code to not only protect against the divide-by-zero, but
to do the starting sector arithmetic in sectors, and using the proper
types.

[ For any mathematicians out there: it also looks monumentally stupid to
  do the 'modulo granularity' operation *twice*, never mind having a "+
  granularity" in the second modulus op.

  But that's the easiest way to avoid negative values or overflow, and
  it is how the original code was done. ]

Reported-by: Ingo Molnar <mingo@kernel.org>
Reported-by: Doug Anderson <dianders@chromium.org>
Cc: Neil Brown <neilb@suse.de>
Cc: Shaohua Li <shli@fusionio.com>
Acked-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/blkdev.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index acb4f7bbbd32..f94bc83011ed 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1188,14 +1188,25 @@ static inline int queue_discard_alignment(struct request_queue *q)
 
 static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector)
 {
-	sector_t alignment = sector << 9;
-	alignment = sector_div(alignment, lim->discard_granularity);
+	unsigned int alignment, granularity, offset;
 
 	if (!lim->max_discard_sectors)
 		return 0;
 
-	alignment = lim->discard_granularity + lim->discard_alignment - alignment;
-	return sector_div(alignment, lim->discard_granularity);
+	/* Why are these in bytes, not sectors? */
+	alignment = lim->discard_alignment >> 9;
+	granularity = lim->discard_granularity >> 9;
+	if (!granularity)
+		return 0;
+
+	/* Offset of the partition start in 'granularity' sectors */
+	offset = sector_div(sector, granularity);
+
+	/* And why do we do this modulus *again* in blkdev_issue_discard()? */
+	offset = (granularity + alignment - offset) % granularity;
+
+	/* Turn it back into bytes, gaah */
+	return offset << 9;
 }
 
 static inline int bdev_discard_alignment(struct block_device *bdev)
-- 
cgit v1.2.3-55-g7522


From ab28698d33af05abab0bcf8021eafe38f7434f24 Mon Sep 17 00:00:00 2001
From: Jonas Gorski
Date: Wed, 19 Dec 2012 09:10:09 -0600
Subject: of: define struct device in of_platform.h if !OF_DEVICE and
 !OF_ADDRESS

Fixes the following warning:

include/linux/of_platform.h:106:13: warning: 'struct device' declared
inside parameter list [enabled by default]
include/linux/of_platform.h:106:13: warning: its scope is only this
definition or declaration, which is probably not what you want [enabled
by default]

Signed-off-by: Jonas Gorski <jogo@openwrt.org>
Signed-off-by: Rob Herring <robherring2@gmail.com>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 include/linux/of_platform.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index b47d2040c9f2..3863a4dbdf18 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -100,6 +100,7 @@ extern int of_platform_populate(struct device_node *root,
 
 #if !defined(CONFIG_OF_ADDRESS)
 struct of_dev_auxdata;
+struct device;
 static inline int of_platform_populate(struct device_node *root,
 					const struct of_device_id *matches,
 					const struct of_dev_auxdata *lookup,
-- 
cgit v1.2.3-55-g7522


From 3c439b5586e9200f7e6287ee77c175c4d5b0eeed Mon Sep 17 00:00:00 2001
From: Jack Morgenstein
Date: Thu, 6 Dec 2012 17:12:00 +0000
Subject: mlx4_core: Allow choosing flow steering mode

Device managed flow steering will be enabled only under administrator
directive provided through setting the existing module parameter
log_num_mgm_entry_size to -1 (if the device actually supports flow
steering).  If flow steering isn't requested or not available, the
driver will use the value of log_num_mgm_entry_size and B0 steering.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 52 ++++++++++++++++++++++++++-----
 drivers/net/ethernet/mellanox/mlx4/mcg.c  |  7 +----
 drivers/net/ethernet/mellanox/mlx4/mlx4.h |  6 ++--
 include/linux/mlx4/device.h               |  1 +
 4 files changed, 50 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 680d81026cbd..e1bafffbc3b1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -85,15 +85,15 @@ static int probe_vf;
 module_param(probe_vf, int, 0644);
 MODULE_PARM_DESC(probe_vf, "number of vfs to probe by pf driver (num_vfs > 0)");
 
-int mlx4_log_num_mgm_entry_size = 10;
+int mlx4_log_num_mgm_entry_size = MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE;
 module_param_named(log_num_mgm_entry_size,
 			mlx4_log_num_mgm_entry_size, int, 0444);
 MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
 					 " of qp per mcg, for example:"
-					 " 10 gives 248.range: 9<="
+					 " 10 gives 248.range: 7 <="
 					 " log_num_mgm_entry_size <= 12."
-					 " Not in use with device managed"
-					 " flow steering");
+					 " To activate device managed"
+					 " flow steering when available, set to -1");
 
 static bool enable_64b_cqe_eqe;
 module_param(enable_64b_cqe_eqe, bool, 0444);
@@ -1318,12 +1318,30 @@ static void mlx4_parav_master_pf_caps(struct mlx4_dev *dev)
 	}
 }
 
+static int choose_log_fs_mgm_entry_size(int qp_per_entry)
+{
+	int i = MLX4_MIN_MGM_LOG_ENTRY_SIZE;
+
+	for (i = MLX4_MIN_MGM_LOG_ENTRY_SIZE; i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE;
+	      i++) {
+		if (qp_per_entry <= 4 * ((1 << i) / 16 - 2))
+			break;
+	}
+
+	return (i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE) ? i : -1;
+}
+
 static void choose_steering_mode(struct mlx4_dev *dev,
 				 struct mlx4_dev_cap *dev_cap)
 {
-	if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
+	if (mlx4_log_num_mgm_entry_size == -1 &&
+	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
 	    (!mlx4_is_mfunc(dev) ||
-	     (dev_cap->fs_max_num_qp_per_entry >= (num_vfs + 1)))) {
+	     (dev_cap->fs_max_num_qp_per_entry >= (num_vfs + 1))) &&
+	    choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry) >=
+		MLX4_MIN_MGM_LOG_ENTRY_SIZE) {
+		dev->oper_log_mgm_entry_size =
+			choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry);
 		dev->caps.steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED;
 		dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
 		dev->caps.fs_log_max_ucast_qp_range_size =
@@ -1340,10 +1358,17 @@ static void choose_steering_mode(struct mlx4_dev *dev,
 				mlx4_warn(dev, "Must have both UC_STEER and MC_STEER flags "
 					  "set to use B0 steering. Falling back to A0 steering mode.\n");
 		}
+		dev->oper_log_mgm_entry_size =
+			mlx4_log_num_mgm_entry_size > 0 ?
+			mlx4_log_num_mgm_entry_size :
+			MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE;
 		dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
 	}
-	mlx4_dbg(dev, "Steering mode is: %s\n",
-		 mlx4_steering_mode_str(dev->caps.steering_mode));
+	mlx4_dbg(dev, "Steering mode is: %s, oper_log_mgm_entry_size = %d, "
+		 "modparam log_num_mgm_entry_size = %d\n",
+		 mlx4_steering_mode_str(dev->caps.steering_mode),
+		 dev->oper_log_mgm_entry_size,
+		 mlx4_log_num_mgm_entry_size);
 }
 
 static int mlx4_init_hca(struct mlx4_dev *dev)
@@ -2479,6 +2504,17 @@ static int __init mlx4_verify_params(void)
 		port_type_array[0] = true;
 	}
 
+	if (mlx4_log_num_mgm_entry_size != -1 &&
+	    (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
+	     mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE)) {
+		pr_warning("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not "
+			   "in legal range (-1 or %d..%d)\n",
+			   mlx4_log_num_mgm_entry_size,
+			   MLX4_MIN_MGM_LOG_ENTRY_SIZE,
+			   MLX4_MAX_MGM_LOG_ENTRY_SIZE);
+		return -1;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index e151c21baf2b..1ee4db3c6400 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -54,12 +54,7 @@ struct mlx4_mgm {
 
 int mlx4_get_mgm_entry_size(struct mlx4_dev *dev)
 {
-	if (dev->caps.steering_mode ==
-	    MLX4_STEERING_MODE_DEVICE_MANAGED)
-		return 1 << MLX4_FS_MGM_LOG_ENTRY_SIZE;
-	else
-		return min((1 << mlx4_log_num_mgm_entry_size),
-			   MLX4_MAX_MGM_ENTRY_SIZE);
+	return 1 << dev->oper_log_mgm_entry_size;
 }
 
 int mlx4_get_qp_per_mgm(struct mlx4_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 1cf42036d7bb..116c5c29d2d1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -94,8 +94,10 @@ enum {
 };
 
 enum {
-	MLX4_MAX_MGM_ENTRY_SIZE = 0x1000,
-	MLX4_MAX_QP_PER_MGM	= 4 * (MLX4_MAX_MGM_ENTRY_SIZE / 16 - 2),
+	MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE = 10,
+	MLX4_MIN_MGM_LOG_ENTRY_SIZE = 7,
+	MLX4_MAX_MGM_LOG_ENTRY_SIZE = 12,
+	MLX4_MAX_QP_PER_MGM = 4 * ((1 << MLX4_MAX_MGM_LOG_ENTRY_SIZE) / 16 - 2),
 	MLX4_MTT_ENTRY_PER_SEG	= 8,
 };
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 21821da2abfd..20ea939c22a6 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -625,6 +625,7 @@ struct mlx4_dev {
 	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];
 	int			num_vfs;
+	int			oper_log_mgm_entry_size;
 	u64			regid_promisc_array[MLX4_MAX_PORTS + 1];
 	u64			regid_allmulti_array[MLX4_MAX_PORTS + 1];
 };
-- 
cgit v1.2.3-55-g7522


From a1c088e01b71d90852b0df5a77cdae46bd0e0c05 Mon Sep 17 00:00:00 2001
From: Oliver Neukum
Date: Tue, 18 Dec 2012 04:45:29 +0000
Subject: usbnet: handle PM failure gracefully

If a device fails to do remote wakeup, this is no reason
to abort an open totally. This patch just continues without
runtime PM.

Signed-off-by: Oliver Neukum <oneukum@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c   | 15 ++++++++-------
 include/linux/usb/usbnet.h |  1 +
 2 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index c04110ba677f..50ed7ab09c9f 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -719,7 +719,8 @@ int usbnet_stop (struct net_device *net)
 	dev->flags = 0;
 	del_timer_sync (&dev->delay);
 	tasklet_kill (&dev->bh);
-	if (info->manage_power)
+	if (info->manage_power &&
+	    !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags))
 		info->manage_power(dev, 0);
 	else
 		usb_autopm_put_interface(dev->intf);
@@ -794,14 +795,14 @@ int usbnet_open (struct net_device *net)
 	tasklet_schedule (&dev->bh);
 	if (info->manage_power) {
 		retval = info->manage_power(dev, 1);
-		if (retval < 0)
-			goto done_manage_power_error;
-		usb_autopm_put_interface(dev->intf);
+		if (retval < 0) {
+			retval = 0;
+			set_bit(EVENT_NO_RUNTIME_PM, &dev->flags);
+		} else {
+			usb_autopm_put_interface(dev->intf);
+		}
 	}
 	return retval;
-
-done_manage_power_error:
-	clear_bit(EVENT_DEV_OPEN, &dev->flags);
 done:
 	usb_autopm_put_interface(dev->intf);
 done_nopm:
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 9bbeabf66c54..288b32aadab2 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -69,6 +69,7 @@ struct usbnet {
 #		define EVENT_DEV_ASLEEP 6
 #		define EVENT_DEV_OPEN	7
 #		define EVENT_DEVICE_REPORT_IDLE	8
+#		define EVENT_NO_RUNTIME_PM	9
 };
 
 static inline struct usb_driver *driver_of(struct usb_interface *intf)
-- 
cgit v1.2.3-55-g7522


From 2dd7c8cf29769f6b66f26b501db2364640c2c9d0 Mon Sep 17 00:00:00 2001
From: Oliver Neukum
Date: Tue, 18 Dec 2012 04:45:52 +0000
Subject: usbnet: generic manage_power()

Centralise common code for manage_power() in usbnet
by making a generic simple implementation

Signed-off-by: Oliver Neukum <oneukum@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c   | 10 ++++++++++
 include/linux/usb/usbnet.h |  2 ++
 2 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 50ed7ab09c9f..3d4bf01641b4 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1616,6 +1616,16 @@ void usbnet_device_suggests_idle(struct usbnet *dev)
 }
 EXPORT_SYMBOL(usbnet_device_suggests_idle);
 
+/*
+ * For devices that can do without special commands
+ */
+int usbnet_manage_power(struct usbnet *dev, int on)
+{
+	dev->intf->needs_remote_wakeup = on;
+	return 0;
+}
+EXPORT_SYMBOL(usbnet_manage_power);
+
 /*-------------------------------------------------------------------------*/
 static int __usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 			     u16 value, u16 index, void *data, u16 size)
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 288b32aadab2..bd45eb7bedc8 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -241,4 +241,6 @@ extern void usbnet_set_msglevel(struct net_device *, u32);
 extern void usbnet_get_drvinfo(struct net_device *, struct ethtool_drvinfo *);
 extern int usbnet_nway_reset(struct net_device *net);
 
+extern int usbnet_manage_power(struct usbnet *, int);
+
 #endif /* __LINUX_USB_USBNET_H */
-- 
cgit v1.2.3-55-g7522


From cf13a84d174947df4bb809edfb4887393642303e Mon Sep 17 00:00:00 2001
From: Fabio Porcedda
Date: Fri, 5 Oct 2012 12:16:09 +0200
Subject: watchdog: WatchDog Timer Driver Core: fix comment

Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>
---
 include/linux/watchdog.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h
index 87490ac4bd87..3a9df2f43be6 100644
--- a/include/linux/watchdog.h
+++ b/include/linux/watchdog.h
@@ -129,7 +129,7 @@ static inline void *watchdog_get_drvdata(struct watchdog_device *wdd)
 	return wdd->driver_data;
 }
 
-/* drivers/watchdog/core/watchdog_core.c */
+/* drivers/watchdog/watchdog_core.c */
 extern int watchdog_register_device(struct watchdog_device *);
 extern void watchdog_unregister_device(struct watchdog_device *);
 
-- 
cgit v1.2.3-55-g7522


From 468366138850f20543f1d4878028900672b23dae Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Fri, 23 Nov 2012 09:12:59 -0500
Subject: COMPAT_SYSCALL_DEFINE: infrastructure

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/s390/include/asm/compat.h |  3 +++
 include/linux/compat.h         | 42 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

(limited to 'include')

diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 18cd6b592650..f8c6df6cd1f0 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -7,6 +7,9 @@
 #include <linux/sched.h>
 #include <linux/thread_info.h>
 
+#define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p(typeof(0?(t)0:0ULL), u64))
+#define __SC_DELOUSE(t,v) (t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v))
+
 #define PSW32_MASK_PER		0x40000000UL
 #define PSW32_MASK_DAT		0x04000000UL
 #define PSW32_MASK_IO		0x02000000UL
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 784ebfe63c48..a7877fa809fd 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -23,6 +23,48 @@
 #define COMPAT_USE_64BIT_TIME 0
 #endif
 
+#ifndef __SC_DELOUSE
+#define __SC_DELOUSE(t,v) ((t)(unsigned long)(v))
+#endif
+
+#define __SC_CCAST1(t1, a1)      __SC_DELOUSE(t1,a1)
+#define __SC_CCAST2(t2, a2, ...) __SC_DELOUSE(t2,a2), __SC_CCAST1(__VA_ARGS__)
+#define __SC_CCAST3(t3, a3, ...) __SC_DELOUSE(t3,a3), __SC_CCAST2(__VA_ARGS__)
+#define __SC_CCAST4(t4, a4, ...) __SC_DELOUSE(t4,a4), __SC_CCAST3(__VA_ARGS__)
+#define __SC_CCAST5(t5, a5, ...) __SC_DELOUSE(t5,a5), __SC_CCAST4(__VA_ARGS__)
+#define __SC_CCAST6(t6, a6, ...) __SC_DELOUSE(t6,a6), __SC_CCAST5(__VA_ARGS__)
+#define COMPAT_SYSCALL_DEFINE1(name, ...) \
+        COMPAT_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_DEFINE2(name, ...) \
+	COMPAT_SYSCALL_DEFINEx(2, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_DEFINE3(name, ...) \
+	COMPAT_SYSCALL_DEFINEx(3, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_DEFINE4(name, ...) \
+	COMPAT_SYSCALL_DEFINEx(4, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_DEFINE5(name, ...) \
+	COMPAT_SYSCALL_DEFINEx(5, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_DEFINE6(name, ...) \
+	COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__)
+
+#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
+
+#define COMPAT_SYSCALL_DEFINEx(x, name, ...)				\
+	asmlinkage long compat_sys##name(__SC_DECL##x(__VA_ARGS__));	\
+	static inline long C_SYSC##name(__SC_DECL##x(__VA_ARGS__));	\
+	asmlinkage long compat_SyS##name(__SC_LONG##x(__VA_ARGS__))	\
+	{								\
+		return (long) C_SYSC##name(__SC_CCAST##x(__VA_ARGS__));	\
+	}								\
+	SYSCALL_ALIAS(compat_sys##name, compat_SyS##name);		\
+	static inline long C_SYSC##name(__SC_DECL##x(__VA_ARGS__))
+
+#else /* CONFIG_HAVE_SYSCALL_WRAPPERS */
+
+#define COMPAT_SYSCALL_DEFINEx(x, name, ...)				\
+	asmlinkage long compat_sys##name(__SC_DECL##x(__VA_ARGS__))
+
+#endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */
+
 #define compat_jiffies_to_clock_t(x)	\
 		(((unsigned long)(x) * COMPAT_USER_HZ) / HZ)
 
-- 
cgit v1.2.3-55-g7522


From ae903caae267154de7cf8576b130ff474630596b Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Fri, 14 Dec 2012 12:44:11 -0500
Subject: Bury the conditionals from kernel_thread/kernel_execve series

All architectures have
	CONFIG_GENERIC_KERNEL_THREAD
	CONFIG_GENERIC_KERNEL_EXECVE
	__ARCH_WANT_SYS_EXECVE
None of them have __ARCH_WANT_KERNEL_EXECVE and there are only two callers
of kernel_execve() (which is a trivial wrapper for do_execve() now) left.
Kill the conditionals and make both callers use do_execve().

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/Kconfig                             |  6 ------
 arch/alpha/Kconfig                       |  2 --
 arch/alpha/include/asm/unistd.h          |  1 -
 arch/arm/Kconfig                         |  2 --
 arch/arm/include/asm/unistd.h            |  1 -
 arch/arm64/Kconfig                       |  2 --
 arch/arm64/include/asm/unistd.h          |  1 -
 arch/avr32/Kconfig                       |  2 --
 arch/avr32/include/asm/unistd.h          |  1 -
 arch/blackfin/Kconfig                    |  2 --
 arch/blackfin/include/asm/unistd.h       |  1 -
 arch/c6x/Kconfig                         |  2 --
 arch/c6x/include/uapi/asm/unistd.h       |  1 -
 arch/cris/Kconfig                        |  2 --
 arch/cris/include/asm/unistd.h           |  1 -
 arch/frv/Kconfig                         |  2 --
 arch/frv/include/asm/unistd.h            |  1 -
 arch/h8300/Kconfig                       |  2 --
 arch/h8300/include/asm/unistd.h          |  1 -
 arch/hexagon/Kconfig                     |  2 --
 arch/hexagon/include/uapi/asm/unistd.h   |  1 -
 arch/ia64/Kconfig                        |  2 --
 arch/ia64/include/asm/unistd.h           |  1 -
 arch/m32r/Kconfig                        |  2 --
 arch/m32r/include/asm/unistd.h           |  1 -
 arch/m68k/Kconfig                        |  2 --
 arch/m68k/include/asm/unistd.h           |  1 -
 arch/microblaze/Kconfig                  |  2 --
 arch/microblaze/include/asm/unistd.h     |  1 -
 arch/mips/Kconfig                        |  2 --
 arch/mips/include/asm/unistd.h           |  1 -
 arch/mn10300/Kconfig                     |  2 --
 arch/mn10300/include/asm/unistd.h        |  1 -
 arch/openrisc/Kconfig                    |  2 --
 arch/openrisc/include/uapi/asm/unistd.h  |  1 -
 arch/parisc/Kconfig                      |  2 --
 arch/parisc/include/asm/unistd.h         |  1 -
 arch/powerpc/Kconfig                     |  2 --
 arch/powerpc/include/asm/unistd.h        |  1 -
 arch/s390/Kconfig                        |  2 --
 arch/s390/include/asm/unistd.h           |  1 -
 arch/score/Kconfig                       |  2 --
 arch/score/include/asm/unistd.h          |  1 -
 arch/sh/Kconfig                          |  2 --
 arch/sh/include/asm/unistd.h             |  1 -
 arch/sparc/Kconfig                       |  2 --
 arch/sparc/include/asm/unistd.h          |  1 -
 arch/tile/Kconfig                        |  2 --
 arch/tile/include/asm/unistd.h           |  1 -
 arch/unicore32/Kconfig                   |  2 --
 arch/unicore32/include/uapi/asm/unistd.h |  1 -
 arch/x86/Kconfig                         |  2 --
 arch/x86/include/asm/unistd.h            |  1 -
 arch/x86/um/Kconfig                      |  2 --
 arch/xtensa/Kconfig                      |  2 --
 arch/xtensa/include/asm/unistd.h         |  1 -
 fs/exec.c                                | 21 ---------------------
 include/linux/binfmts.h                  |  4 ----
 include/linux/sched.h                    |  2 --
 include/linux/syscalls.h                 |  9 ---------
 init/main.c                              |  4 +++-
 kernel/fork.c                            |  2 --
 kernel/kmod.c                            |  6 +++---
 63 files changed, 6 insertions(+), 131 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index 8d698fb5ccc9..0a8dd0585d0d 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -271,12 +271,6 @@ config ARCH_WANT_OLD_COMPAT_IPC
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	bool
 
-config GENERIC_KERNEL_THREAD
-	bool
-
-config GENERIC_KERNEL_EXECVE
-	bool
-
 config HAVE_ARCH_SECCOMP_FILTER
 	bool
 	help
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 5dd7f5db24d4..7e3710c0cce5 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -20,8 +20,6 @@ config ALPHA
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
 	help
diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h
index eb3a4664ced2..68c75f2fadb9 100644
--- a/arch/alpha/include/asm/unistd.h
+++ b/arch/alpha/include/asm/unistd.h
@@ -481,7 +481,6 @@
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_SIGPENDING
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 8918a2dd89b4..b789654e7e2f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -11,8 +11,6 @@ config ARM
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 7cd13cc62624..21a2700d2957 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -41,7 +41,6 @@
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_SOCKETCALL
 #endif
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 4b03c56ec329..a846029bebcc 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -7,8 +7,6 @@ config ARM64
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
-	select GENERIC_KERNEL_EXECVE
-	select GENERIC_KERNEL_THREAD
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select HARDIRQS_SW_RESEND
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index d69aeea6da1e..738322945d1a 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -27,6 +27,5 @@
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #endif
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
 #include <uapi/asm/unistd.h>
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index 649aeb9acecb..06e73bf665e9 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -17,8 +17,6 @@ config AVR32
 	select GENERIC_CLOCKEVENTS
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	help
 	  AVR32 is a high-performance 32-bit RISC microprocessor core,
 	  designed for cost-sensitive embedded applications, with particular
diff --git a/arch/avr32/include/asm/unistd.h b/arch/avr32/include/asm/unistd.h
index f05a9804e8e2..0bdf6371574e 100644
--- a/arch/avr32/include/asm/unistd.h
+++ b/arch/avr32/include/asm/unistd.h
@@ -39,7 +39,6 @@
 #define __ARCH_WANT_SYS_GETPGRP
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index ab9ff4075f4d..b6f3ad5441c5 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -45,8 +45,6 @@ config BLACKFIN
 	select ARCH_USES_GETTIMEOFFSET if !GENERIC_CLOCKEVENTS
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 config GENERIC_CSUM
 	def_bool y
diff --git a/arch/blackfin/include/asm/unistd.h b/arch/blackfin/include/asm/unistd.h
index 460514a1a4e1..38711e28baac 100644
--- a/arch/blackfin/include/asm/unistd.h
+++ b/arch/blackfin/include/asm/unistd.h
@@ -446,7 +446,6 @@
 #define __ARCH_WANT_SYS_NICE
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_VFORK
 
 /*
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 66eab3703c75..f6a3648f5ec3 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -17,8 +17,6 @@ config C6X
 	select OF
 	select OF_EARLY_FLATTREE
 	select GENERIC_CLOCKEVENTS
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select MODULES_USE_ELF_RELA
 
 config MMU
diff --git a/arch/c6x/include/uapi/asm/unistd.h b/arch/c6x/include/uapi/asm/unistd.h
index f3987a8703d9..e7d09a614d10 100644
--- a/arch/c6x/include/uapi/asm/unistd.h
+++ b/arch/c6x/include/uapi/asm/unistd.h
@@ -14,7 +14,6 @@
  *   more details.
  */
 
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
 
 /* Use the standard ABI for syscalls. */
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index 0cac6a49f230..c59a01dd9c0c 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -49,8 +49,6 @@ config CRIS
 	select GENERIC_SMP_IDLE_THREAD if ETRAX_ARCH_V32
 	select GENERIC_CMOS_UPDATE
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select CLONE_BACKWARDS2
 
 config HZ
diff --git a/arch/cris/include/asm/unistd.h b/arch/cris/include/asm/unistd.h
index f27b542e0ebc..5cda75a9cc1e 100644
--- a/arch/cris/include/asm/unistd.h
+++ b/arch/cris/include/asm/unistd.h
@@ -371,7 +371,6 @@
 #define __ARCH_WANT_SYS_SIGPROCMASK
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index df2eb4bd9fa2..9d262645f667 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -12,8 +12,6 @@ config FRV
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_CPU_DEVICES
 	select ARCH_WANT_IPC_PARSE_VERSION
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 config ZONE_DMA
 	bool
diff --git a/arch/frv/include/asm/unistd.h b/arch/frv/include/asm/unistd.h
index 1807d8ea8cb5..d685da17f5fb 100644
--- a/arch/frv/include/asm/unistd.h
+++ b/arch/frv/include/asm/unistd.h
@@ -29,7 +29,6 @@
 #define __ARCH_WANT_SYS_SIGPROCMASK
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index 04bef4d25b4a..98fabd10e95f 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -8,8 +8,6 @@ config H8300
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 config SYMBOL_PREFIX
 	string
diff --git a/arch/h8300/include/asm/unistd.h b/arch/h8300/include/asm/unistd.h
index c2c2f5c7d6bf..566f94860c45 100644
--- a/arch/h8300/include/asm/unistd.h
+++ b/arch/h8300/include/asm/unistd.h
@@ -356,7 +356,6 @@
 #define __ARCH_WANT_SYS_SIGPROCMASK
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index e418803b6c8e..0744f7d7b1fd 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -31,8 +31,6 @@ config HEXAGON
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	---help---
 	  Qualcomm Hexagon is a processor architecture designed for high
 	  performance and low power across a wide variety of applications.
diff --git a/arch/hexagon/include/uapi/asm/unistd.h b/arch/hexagon/include/uapi/asm/unistd.h
index 2af81533bd0f..4a87cc47075c 100644
--- a/arch/hexagon/include/uapi/asm/unistd.h
+++ b/arch/hexagon/include/uapi/asm/unistd.h
@@ -27,7 +27,6 @@
  */
 
 #define sys_mmap2 sys_mmap_pgoff
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
 
 #include <asm-generic/unistd.h>
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 670600468128..3279646120e3 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -42,8 +42,6 @@ config IA64
 	select GENERIC_TIME_VSYSCALL_OLD
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index 1574bca86138..8b3ff2f5b861 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -29,7 +29,6 @@
 
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 
 #if !defined(__ASSEMBLY__) && !defined(ASSEMBLER)
 
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 5183f43a2cf7..f807721e19a5 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -15,8 +15,6 @@ config M32R
 	select GENERIC_ATOMIC64
 	select ARCH_USES_GETTIMEOFFSET
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 config SBUS
 	bool
diff --git a/arch/m32r/include/asm/unistd.h b/arch/m32r/include/asm/unistd.h
index d9e7351af2a4..cbfa39158fef 100644
--- a/arch/m32r/include/asm/unistd.h
+++ b/arch/m32r/include/asm/unistd.h
@@ -352,7 +352,6 @@
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 953a7ba5d050..6710084e072a 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -15,8 +15,6 @@ config M68K
 	select FPU if MMU
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_REL
 	select MODULES_USE_ELF_RELA
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index a021d67cdd72..847994ce6804 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -31,7 +31,6 @@
 #define __ARCH_WANT_SYS_SIGPROCMASK
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 4bcf89148f3c..ba3b7c8c04b8 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -26,8 +26,6 @@ config MICROBLAZE
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select CLONE_BACKWARDS
 
 config SWAP
diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h
index 94d978986b75..38cabf4db548 100644
--- a/arch/microblaze/include/asm/unistd.h
+++ b/arch/microblaze/include/asm/unistd.h
@@ -422,7 +422,6 @@
 #define __ARCH_WANT_SYS_SIGPROCMASK
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
 #define __ARCH_WANT_SYS_VFORK
 #ifdef CONFIG_MMU
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 4183e62f178c..dba9390d37cf 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -40,8 +40,6 @@ config MIPS
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_REL
 	select MODULES_USE_ELF_RELA if 64BIT
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 menu "Machine selection"
 
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index b306e2081cad..9e47cc11aa26 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -20,7 +20,6 @@
 #define __ARCH_OMIT_COMPAT_SYS_GETDENTS64
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_GETHOSTNAME
 #define __ARCH_WANT_SYS_IPC
 #define __ARCH_WANT_SYS_PAUSE
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 72471744a912..aa03f2e13385 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -8,8 +8,6 @@ config MN10300
 	select HAVE_ARCH_KGDB
 	select HAVE_NMI_WATCHDOG if MN10300_WD_TIMER
 	select GENERIC_CLOCKEVENTS
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select MODULES_USE_ELF_RELA
 
 config AM33_2
diff --git a/arch/mn10300/include/asm/unistd.h b/arch/mn10300/include/asm/unistd.h
index cabf8ba73b27..e6d2ed4ba68f 100644
--- a/arch/mn10300/include/asm/unistd.h
+++ b/arch/mn10300/include/asm/unistd.h
@@ -43,7 +43,6 @@
 #define __ARCH_WANT_SYS_SIGPROCMASK
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index e7f1a2993f78..05f2ba41ff1a 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -22,8 +22,6 @@ config OPENRISC
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 config MMU
 	def_bool y
diff --git a/arch/openrisc/include/uapi/asm/unistd.h b/arch/openrisc/include/uapi/asm/unistd.h
index 5082b8066325..ce40b71df006 100644
--- a/arch/openrisc/include/uapi/asm/unistd.h
+++ b/arch/openrisc/include/uapi/asm/unistd.h
@@ -20,7 +20,6 @@
 
 #define sys_mmap2 sys_mmap_pgoff
 
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_CLONE
 
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index e688a2be30f6..b77feffbadea 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -22,8 +22,6 @@ config PARISC
 	select GENERIC_STRNCPY_FROM_USER
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select CLONE_BACKWARDS
 
 	help
diff --git a/arch/parisc/include/asm/unistd.h b/arch/parisc/include/asm/unistd.h
index 1efef41659c9..3043194547cd 100644
--- a/arch/parisc/include/asm/unistd.h
+++ b/arch/parisc/include/asm/unistd.h
@@ -163,7 +163,6 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5)	\
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
 #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 951a517a1a0f..17903f1f356b 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -141,10 +141,8 @@ config PPC
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
-	select GENERIC_KERNEL_THREAD
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_EXECVE
 	select CLONE_BACKWARDS
 
 config EARLY_PRINTK
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 76fe846ec40e..784872f93711 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -55,7 +55,6 @@
 #define __ARCH_WANT_SYS_NEWFSTATAT
 #define __ARCH_WANT_COMPAT_SYS_SENDFILE
 #endif
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3cbb8757704e..5029ebf7110e 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -137,8 +137,6 @@ config S390
 	select GENERIC_CLOCKEVENTS
 	select KTIME_SCALAR if 32BIT
 	select HAVE_ARCH_SECCOMP_FILTER
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
 	select CLONE_BACKWARDS2
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 086bb8eaf6ab..636530872516 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -53,7 +53,6 @@
 #   define __ARCH_WANT_COMPAT_SYS_TIME
 #   define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
 # endif
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index 45893390c7dd..3b1482e7afac 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -13,8 +13,6 @@ config SCORE
        select GENERIC_CLOCKEVENTS
        select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_REL
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select CLONE_BACKWARDS
 
 choice
diff --git a/arch/score/include/asm/unistd.h b/arch/score/include/asm/unistd.h
index 56001c93095a..9cb4260a5f3e 100644
--- a/arch/score/include/asm/unistd.h
+++ b/arch/score/include/asm/unistd.h
@@ -4,7 +4,6 @@
 #define __ARCH_WANT_SYSCALL_NO_FLAGS
 #define __ARCH_WANT_SYSCALL_OFF_T
 #define __ARCH_WANT_SYSCALL_DEPRECATED
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 8451317eed58..babc2b826c5c 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -40,8 +40,6 @@ config SUPERH
 	select GENERIC_STRNLEN_USER
 	select HAVE_MOD_ARCH_SPECIFIC if DWARF_UNWINDER
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
 	  and consumer electronics; it was also used in the Sega Dreamcast
diff --git a/arch/sh/include/asm/unistd.h b/arch/sh/include/asm/unistd.h
index 43d3f26b2eab..012004ed3330 100644
--- a/arch/sh/include/asm/unistd.h
+++ b/arch/sh/include/asm/unistd.h
@@ -28,7 +28,6 @@
 # define __ARCH_WANT_SYS_SIGPENDING
 # define __ARCH_WANT_SYS_SIGPROCMASK
 # define __ARCH_WANT_SYS_RT_SIGACTION
-# define __ARCH_WANT_SYS_EXECVE
 # define __ARCH_WANT_SYS_FORK
 # define __ARCH_WANT_SYS_VFORK
 # define __ARCH_WANT_SYS_CLONE
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 0c7d365fa402..9f2edb5c5551 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -41,8 +41,6 @@ config SPARC
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 config SPARC32
 	def_bool !64BIT
diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h
index c3e5d8b64171..0ecea6ed943e 100644
--- a/arch/sparc/include/asm/unistd.h
+++ b/arch/sparc/include/asm/unistd.h
@@ -46,7 +46,6 @@
 #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
 #define __ARCH_WANT_COMPAT_SYS_SENDFILE
 #endif
-#define __ARCH_WANT_SYS_EXECVE
 
 /*
  * "Conditional" syscalls
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index ea7f61e8bc9e..875d008828b8 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -21,8 +21,6 @@ config TILE
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 # FIXME: investigate whether we need/want these options.
 #	select HAVE_IOREMAP_PROT
diff --git a/arch/tile/include/asm/unistd.h b/arch/tile/include/asm/unistd.h
index b51c6ee3cd6c..940831fe9e94 100644
--- a/arch/tile/include/asm/unistd.h
+++ b/arch/tile/include/asm/unistd.h
@@ -16,6 +16,5 @@
 #define __ARCH_WANT_SYS_LLSEEK
 #endif
 #define __ARCH_WANT_SYS_NEWFSTATAT
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
 #include <uapi/asm/unistd.h>
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index c4fbb21e802b..60651df5f952 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -16,8 +16,6 @@ config UNICORE32
 	select ARCH_WANT_FRAME_POINTERS
 	select GENERIC_IOMAP
 	select MODULES_USE_ELF_REL
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	help
 	  UniCore-32 is 32-bit Instruction Set Architecture,
 	  including a series of low-power-consumption RISC chip
diff --git a/arch/unicore32/include/uapi/asm/unistd.h b/arch/unicore32/include/uapi/asm/unistd.h
index 00cf5e286fca..d4cc4559d848 100644
--- a/arch/unicore32/include/uapi/asm/unistd.h
+++ b/arch/unicore32/include/uapi/asm/unistd.h
@@ -12,5 +12,4 @@
 
 /* Use the standard ABI for syscalls. */
 #include <asm-generic/unistd.h>
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0df6e7d84539..01ca0ebaff0e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -108,8 +108,6 @@ config X86
 	select GENERIC_STRNLEN_USER
 	select HAVE_RCU_USER_QS if X86_64
 	select HAVE_IRQ_TIME_ACCOUNTING
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select MODULES_USE_ELF_REL if X86_32
 	select MODULES_USE_ELF_RELA if X86_64
 	select CLONE_BACKWARDS if X86_32
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 0e7dea7d3669..9dcfcc1d6f92 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -50,7 +50,6 @@
 # define __ARCH_WANT_SYS_TIME
 # define __ARCH_WANT_SYS_UTIME
 # define __ARCH_WANT_SYS_WAITPID
-# define __ARCH_WANT_SYS_EXECVE
 # define __ARCH_WANT_SYS_FORK
 # define __ARCH_WANT_SYS_VFORK
 # define __ARCH_WANT_SYS_CLONE
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 8f51c39750d1..0fd20f241e40 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -13,8 +13,6 @@ endmenu
 config UML_X86
 	def_bool y
 	select GENERIC_FIND_FIRST_BIT
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 
 config 64BIT
 	bool "64-bit kernel" if SUBARCH = "x86"
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 2481f267be29..03a8c107e07e 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -13,8 +13,6 @@ config XTENSA
 	select GENERIC_CPU_DEVICES
 	select MODULES_USE_ELF_RELA
 	select GENERIC_PCI_IOMAP
-	select GENERIC_KERNEL_THREAD
-	select GENERIC_KERNEL_EXECVE
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select CLONE_BACKWARDS
 	help
diff --git a/arch/xtensa/include/asm/unistd.h b/arch/xtensa/include/asm/unistd.h
index e002dbcc88b6..eb63ea87815c 100644
--- a/arch/xtensa/include/asm/unistd.h
+++ b/arch/xtensa/include/asm/unistd.h
@@ -1,7 +1,6 @@
 #ifndef _XTENSA_UNISTD_H
 #define _XTENSA_UNISTD_H
 
-#define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
 #include <uapi/asm/unistd.h>
 
diff --git a/fs/exec.c b/fs/exec.c
index 721a29929511..090ac91da2e9 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1657,7 +1657,6 @@ int get_dumpable(struct mm_struct *mm)
 	return __get_dumpable(mm->flags);
 }
 
-#ifdef __ARCH_WANT_SYS_EXECVE
 SYSCALL_DEFINE3(execve,
 		const char __user *, filename,
 		const char __user *const __user *, argv,
@@ -1685,23 +1684,3 @@ asmlinkage long compat_sys_execve(const char __user * filename,
 	return error;
 }
 #endif
-#endif
-
-#ifdef __ARCH_WANT_KERNEL_EXECVE
-int kernel_execve(const char *filename,
-		  const char *const argv[],
-		  const char *const envp[])
-{
-	int ret = do_execve(filename,
-			(const char __user *const __user *)argv,
-			(const char __user *const __user *)envp);
-	if (ret < 0)
-		return ret;
-
-	/*
-	 * We were successful.  We won't be returning to our caller, but
-	 * instead to user space by manipulating the kernel stack.
-	 */
-	ret_from_kernel_execve(current_pt_regs());
-}
-#endif
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 2630c9b41a86..8c1388c6ae27 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -121,8 +121,4 @@ extern void install_exec_creds(struct linux_binprm *bprm);
 extern void set_binfmt(struct linux_binfmt *new);
 extern void free_bprm(struct linux_binprm *);
 
-#ifdef __ARCH_WANT_KERNEL_EXECVE
-extern void ret_from_kernel_execve(struct pt_regs *normal) __noreturn;
-#endif
-
 #endif /* _LINUX_BINFMTS_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1162258bcaf0..9e5a54e3d84f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2291,9 +2291,7 @@ extern int do_execve(const char *,
 		     const char __user * const __user *);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
-#ifdef CONFIG_GENERIC_KERNEL_THREAD
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-#endif
 
 extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 91835e7f364d..9fe5f946526e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -827,15 +827,6 @@ asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags,
 				  const char  __user *pathname);
 asmlinkage long sys_syncfs(int fd);
 
-#ifndef CONFIG_GENERIC_KERNEL_EXECVE
-int kernel_execve(const char *filename, const char *const argv[], const char *const envp[]);
-#else
-#define kernel_execve(filename, argv, envp) \
-	do_execve(filename, \
-		(const char __user *const __user *)argv, \
-		(const char __user *const __user *)envp)
-#endif
-
 asmlinkage long sys_fork(void);
 asmlinkage long sys_vfork(void);
 #ifdef CONFIG_CLONE_BACKWARDS
diff --git a/init/main.c b/init/main.c
index e33e09df3cbc..155ac208d581 100644
--- a/init/main.c
+++ b/init/main.c
@@ -797,7 +797,9 @@ static void __init do_pre_smp_initcalls(void)
 static int run_init_process(const char *init_filename)
 {
 	argv_init[0] = init_filename;
-	return kernel_execve(init_filename, argv_init, envp_init);
+	return do_execve(init_filename,
+		(const char __user *const __user *)argv_init,
+		(const char __user *const __user *)envp_init);
 }
 
 static void __init kernel_init_freeable(void);
diff --git a/kernel/fork.c b/kernel/fork.c
index 540730783433..389712ffc0ad 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1623,7 +1623,6 @@ long do_fork(unsigned long clone_flags,
 	return nr;
 }
 
-#ifdef CONFIG_GENERIC_KERNEL_THREAD
 /*
  * Create a kernel thread.
  */
@@ -1632,7 +1631,6 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn,
 		(unsigned long)arg, NULL, NULL);
 }
-#endif
 
 #ifdef __ARCH_WANT_SYS_FORK
 SYSCALL_DEFINE0(fork)
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 1c317e386831..0023a87e8de6 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -219,9 +219,9 @@ static int ____call_usermodehelper(void *data)
 
 	commit_creds(new);
 
-	retval = kernel_execve(sub_info->path,
-			       (const char *const *)sub_info->argv,
-			       (const char *const *)sub_info->envp);
+	retval = do_execve(sub_info->path,
+			   (const char __user *const __user *)sub_info->argv,
+			   (const char __user *const __user *)sub_info->envp);
 	if (!retval)
 		return 0;
 
-- 
cgit v1.2.3-55-g7522


From 1ca97bb541a1f5a735e697a8bba763cde3aab452 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Sun, 18 Nov 2012 12:50:10 -0500
Subject: new helper: current_user_stack_pointer()

	Cross-architecture equivalent of rdusp(); default is
user_stack_pointer(current_pt_regs()) - that works for almost all
platforms that have usp saved in pt_regs.  The only exception from
that is ia64 - we want memory stack, not the backing store for
register one.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/include/asm/ptrace.h    | 1 +
 arch/blackfin/include/asm/ptrace.h | 1 +
 arch/cris/include/asm/ptrace.h     | 1 +
 arch/h8300/include/asm/ptrace.h    | 1 +
 arch/ia64/include/asm/ptrace.h     | 5 +++++
 arch/m68k/include/asm/ptrace.h     | 1 +
 include/linux/ptrace.h             | 4 ++++
 7 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/arch/alpha/include/asm/ptrace.h b/arch/alpha/include/asm/ptrace.h
index b4c5b2fbb647..fd53c74ac943 100644
--- a/arch/alpha/include/asm/ptrace.h
+++ b/arch/alpha/include/asm/ptrace.h
@@ -72,6 +72,7 @@ struct switch_stack {
 #define user_mode(regs) (((regs)->ps & 8) != 0)
 #define instruction_pointer(regs) ((regs)->pc)
 #define profile_pc(regs) instruction_pointer(regs)
+#define current_user_stack_pointer() rdusp()
 
 #define task_pt_regs(task) \
   ((struct pt_regs *) (task_stack_page(task) + 2*PAGE_SIZE) - 1)
diff --git a/arch/blackfin/include/asm/ptrace.h b/arch/blackfin/include/asm/ptrace.h
index 10d8641180f2..c42002506a26 100644
--- a/arch/blackfin/include/asm/ptrace.h
+++ b/arch/blackfin/include/asm/ptrace.h
@@ -106,6 +106,7 @@ struct pt_regs {
 #define arch_has_single_step()	(1)
 /* common code demands this function */
 #define ptrace_disable(child) user_disable_single_step(child)
+#define current_user_stack_pointer() rdusp()
 
 extern int is_user_addr_valid(struct task_struct *child,
 			      unsigned long start, unsigned long len);
diff --git a/arch/cris/include/asm/ptrace.h b/arch/cris/include/asm/ptrace.h
index 6618893bfe8e..551c081ab62b 100644
--- a/arch/cris/include/asm/ptrace.h
+++ b/arch/cris/include/asm/ptrace.h
@@ -10,6 +10,7 @@
 #define PTRACE_SETREGS            13
 
 #define profile_pc(regs) instruction_pointer(regs)
+#define current_user_stack_pointer() rdusp()
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/h8300/include/asm/ptrace.h b/arch/h8300/include/asm/ptrace.h
index 7468589a128b..6183371d0c93 100644
--- a/arch/h8300/include/asm/ptrace.h
+++ b/arch/h8300/include/asm/ptrace.h
@@ -63,6 +63,7 @@ struct pt_regs {
 #define current_pt_regs() ((struct pt_regs *) \
 	(THREAD_SIZE + (unsigned long)current_thread_info()) - 1)
 #define signal_pt_regs() ((struct pt_regs *)current->thread.esp0)
+#define current_user_stack_pointer() rdusp()
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 #endif /* _H8300_PTRACE_H */
diff --git a/arch/ia64/include/asm/ptrace.h b/arch/ia64/include/asm/ptrace.h
index b0e973649cb9..845143990a1d 100644
--- a/arch/ia64/include/asm/ptrace.h
+++ b/arch/ia64/include/asm/ptrace.h
@@ -78,6 +78,11 @@ static inline long regs_return_value(struct pt_regs *regs)
 	unsigned long __ip = instruction_pointer(regs);			\
 	(__ip & ~3UL) + ((__ip & 3UL) << 2);				\
 })
+/*
+ * Why not default?  Because user_stack_pointer() on ia64 gives register
+ * stack backing store instead...
+ */
+#define current_user_stack_pointer() (current_pt_regs()->r12)
 
   /* given a pointer to a task_struct, return the user's pt_regs */
 # define task_pt_regs(t)		(((struct pt_regs *) ((char *) (t) + IA64_STK_OFFSET)) - 1)
diff --git a/arch/m68k/include/asm/ptrace.h b/arch/m68k/include/asm/ptrace.h
index 0f717045bdde..a45cb6894ad3 100644
--- a/arch/m68k/include/asm/ptrace.h
+++ b/arch/m68k/include/asm/ptrace.h
@@ -15,6 +15,7 @@
 #define profile_pc(regs) instruction_pointer(regs)
 #define current_pt_regs() \
 	(struct pt_regs *)((char *)current_thread_info() + THREAD_SIZE) - 1
+#define current_user_stack_pointer() rdusp()
 
 #define arch_has_single_step()	(1)
 
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index a89ff04bddd9..a3a9d085f932 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -342,6 +342,10 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
 #define signal_pt_regs() task_pt_regs(current)
 #endif
 
+#ifndef current_user_stack_pointer
+#define current_user_stack_pointer() user_stack_pointer(current_pt_regs())
+#endif
+
 extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);
-- 
cgit v1.2.3-55-g7522


From 031b6566983ad9c0247087f039af22b3f87596a3 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Sun, 18 Nov 2012 15:13:17 -0500
Subject: unify SS_ONSTACK/SS_DISABLE definitions

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/include/asm/signal.h        | 6 ------
 arch/arm/include/uapi/asm/signal.h     | 7 -------
 arch/avr32/include/uapi/asm/signal.h   | 6 ------
 arch/cris/include/asm/signal.h         | 6 ------
 arch/h8300/include/asm/signal.h        | 6 ------
 arch/ia64/include/uapi/asm/signal.h    | 6 ------
 arch/m32r/include/asm/signal.h         | 6 ------
 arch/m68k/include/uapi/asm/signal.h    | 6 ------
 arch/mips/include/uapi/asm/signal.h    | 6 ------
 arch/mn10300/include/uapi/asm/signal.h | 6 ------
 arch/parisc/include/uapi/asm/signal.h  | 6 ------
 arch/powerpc/include/uapi/asm/signal.h | 6 ------
 arch/s390/include/uapi/asm/signal.h    | 6 ------
 arch/sparc/include/uapi/asm/signal.h   | 6 ------
 arch/x86/include/asm/signal.h          | 6 ------
 arch/xtensa/include/uapi/asm/signal.h  | 6 ------
 include/uapi/asm-generic/signal.h      | 6 ------
 include/uapi/linux/signal.h            | 2 ++
 18 files changed, 2 insertions(+), 103 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/signal.h b/arch/alpha/include/asm/signal.h
index 45552862cc10..a9aa0133f656 100644
--- a/arch/alpha/include/asm/signal.h
+++ b/arch/alpha/include/asm/signal.h
@@ -98,12 +98,6 @@ typedef unsigned long sigset_t;
 #define SA_ONESHOT	SA_RESETHAND
 #define SA_NOMASK	SA_NODEFER
 
-/* 
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	4096
 #define SIGSTKSZ	16384
 
diff --git a/arch/arm/include/uapi/asm/signal.h b/arch/arm/include/uapi/asm/signal.h
index 921c57fdc52e..33073bdcf091 100644
--- a/arch/arm/include/uapi/asm/signal.h
+++ b/arch/arm/include/uapi/asm/signal.h
@@ -87,13 +87,6 @@ typedef unsigned long sigset_t;
 #define SA_NOMASK	SA_NODEFER
 #define SA_ONESHOT	SA_RESETHAND
 
-
-/* 
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/avr32/include/uapi/asm/signal.h b/arch/avr32/include/uapi/asm/signal.h
index eb46f61adb7d..1b77a93eff50 100644
--- a/arch/avr32/include/uapi/asm/signal.h
+++ b/arch/avr32/include/uapi/asm/signal.h
@@ -89,12 +89,6 @@ typedef unsigned long sigset_t;
 #define SA_NOMASK	SA_NODEFER
 #define SA_ONESHOT	SA_RESETHAND
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/cris/include/asm/signal.h b/arch/cris/include/asm/signal.h
index 72dbbf59dfae..fdbffb773d81 100644
--- a/arch/cris/include/asm/signal.h
+++ b/arch/cris/include/asm/signal.h
@@ -97,12 +97,6 @@ typedef unsigned long sigset_t;
 
 #define SA_RESTORER	0x04000000
 
-/* 
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/h8300/include/asm/signal.h b/arch/h8300/include/asm/signal.h
index c43c0a7d2c2e..575c79a008f4 100644
--- a/arch/h8300/include/asm/signal.h
+++ b/arch/h8300/include/asm/signal.h
@@ -96,12 +96,6 @@ typedef unsigned long sigset_t;
 
 #define SA_RESTORER	0x04000000
 
-/* 
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/ia64/include/uapi/asm/signal.h b/arch/ia64/include/uapi/asm/signal.h
index e531c424434c..c0ea2855e96b 100644
--- a/arch/ia64/include/uapi/asm/signal.h
+++ b/arch/ia64/include/uapi/asm/signal.h
@@ -78,12 +78,6 @@
 
 #define SA_RESTORER	0x04000000
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 /*
  * The minimum stack size needs to be fairly large because we want to
  * be sure that an app compiled for today's CPUs will continue to run
diff --git a/arch/m32r/include/asm/signal.h b/arch/m32r/include/asm/signal.h
index e4d2e2ad5f1e..ba714c45259d 100644
--- a/arch/m32r/include/asm/signal.h
+++ b/arch/m32r/include/asm/signal.h
@@ -98,12 +98,6 @@ typedef unsigned long sigset_t;
 
 #define SA_RESTORER	0x04000000
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/m68k/include/uapi/asm/signal.h b/arch/m68k/include/uapi/asm/signal.h
index 2b450f311bd9..cba6f858bb46 100644
--- a/arch/m68k/include/uapi/asm/signal.h
+++ b/arch/m68k/include/uapi/asm/signal.h
@@ -80,12 +80,6 @@ typedef unsigned long sigset_t;
 #define SA_NOMASK	SA_NODEFER
 #define SA_ONESHOT	SA_RESETHAND
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/mips/include/uapi/asm/signal.h b/arch/mips/include/uapi/asm/signal.h
index 3f1237c6c80e..770732cb8d03 100644
--- a/arch/mips/include/uapi/asm/signal.h
+++ b/arch/mips/include/uapi/asm/signal.h
@@ -86,12 +86,6 @@ typedef unsigned long old_sigset_t;		/* at least 32 bits */
 
 #define SA_RESTORER	0x04000000	/* Only for o32 */
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK     1
-#define SS_DISABLE     2
-
 #define MINSIGSTKSZ    2048
 #define SIGSTKSZ       8192
 
diff --git a/arch/mn10300/include/uapi/asm/signal.h b/arch/mn10300/include/uapi/asm/signal.h
index 08dcd6a85618..f423a08d7eeb 100644
--- a/arch/mn10300/include/uapi/asm/signal.h
+++ b/arch/mn10300/include/uapi/asm/signal.h
@@ -92,12 +92,6 @@ typedef unsigned long sigset_t;
 
 #define SA_RESTORER	0x04000000
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h
index b1ddaa243376..a2fa297196bc 100644
--- a/arch/parisc/include/uapi/asm/signal.h
+++ b/arch/parisc/include/uapi/asm/signal.h
@@ -71,12 +71,6 @@
 
 #define SA_RESTORER	0x04000000 /* obsolete -- ignored */
 
-/* 
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/powerpc/include/uapi/asm/signal.h b/arch/powerpc/include/uapi/asm/signal.h
index 48fa8d3f2f9a..e079fb39d5bc 100644
--- a/arch/powerpc/include/uapi/asm/signal.h
+++ b/arch/powerpc/include/uapi/asm/signal.h
@@ -85,12 +85,6 @@ typedef struct {
 
 #define SA_RESTORER	0x04000000U
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/s390/include/uapi/asm/signal.h b/arch/s390/include/uapi/asm/signal.h
index 8c6a49e392ee..2f43cfbf5f1a 100644
--- a/arch/s390/include/uapi/asm/signal.h
+++ b/arch/s390/include/uapi/asm/signal.h
@@ -90,12 +90,6 @@ typedef unsigned long sigset_t;
 
 #define SA_RESTORER     0x04000000
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK      1
-#define SS_DISABLE      2
-
 #define MINSIGSTKSZ     2048
 #define SIGSTKSZ        8192
 
diff --git a/arch/sparc/include/uapi/asm/signal.h b/arch/sparc/include/uapi/asm/signal.h
index 1a041892538f..c4ffd6c97106 100644
--- a/arch/sparc/include/uapi/asm/signal.h
+++ b/arch/sparc/include/uapi/asm/signal.h
@@ -147,12 +147,6 @@ struct sigstack {
 #define SIG_UNBLOCK        0x02	/* for unblocking signals */
 #define SIG_SETMASK        0x04	/* for setting the signal mask */
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	4096
 #define SIGSTKSZ	16384
 
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 0dba8b7a6ac7..7bb5490b3aa2 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -112,12 +112,6 @@ typedef unsigned long sigset_t;
 
 #define SA_RESTORER	0x04000000
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/xtensa/include/uapi/asm/signal.h b/arch/xtensa/include/uapi/asm/signal.h
index b88ce96f2af9..dacf716dd3e0 100644
--- a/arch/xtensa/include/uapi/asm/signal.h
+++ b/arch/xtensa/include/uapi/asm/signal.h
@@ -97,12 +97,6 @@ typedef struct {
 
 #define SA_RESTORER	0x04000000
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/include/uapi/asm-generic/signal.h b/include/uapi/asm-generic/signal.h
index 0a78028984de..6fae30fd16ab 100644
--- a/include/uapi/asm-generic/signal.h
+++ b/include/uapi/asm-generic/signal.h
@@ -80,12 +80,6 @@
  *	SA_RESTORER	0x04000000
  */
 
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/include/uapi/linux/signal.h b/include/uapi/linux/signal.h
index dff452ed6d00..e1bd50c29ded 100644
--- a/include/uapi/linux/signal.h
+++ b/include/uapi/linux/signal.h
@@ -4,5 +4,7 @@
 #include <asm/signal.h>
 #include <asm/siginfo.h>
 
+#define SS_ONSTACK	1
+#define SS_DISABLE	2
 
 #endif /* _UAPI_LINUX_SIGNAL_H */
-- 
cgit v1.2.3-55-g7522


From 5c49574ffd7ac07eae8c3b065d19e6ebc7e4760f Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Sun, 18 Nov 2012 15:29:16 -0500
Subject: new helper: restore_altstack()

to be used by rt_sigreturn instances

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/signal.h | 2 ++
 kernel/signal.c        | 7 +++++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/linux/signal.h b/include/linux/signal.h
index e19a011b43b7..5969522136fe 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -385,4 +385,6 @@ int unhandled_signal(struct task_struct *tsk, int sig);
 
 void signals_init(void);
 
+int restore_altstack(const stack_t __user *);
+
 #endif /* _LINUX_SIGNAL_H */
diff --git a/kernel/signal.c b/kernel/signal.c
index e75e4bd2839b..887f2fefe207 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3103,6 +3103,13 @@ out:
 	return error;
 }
 
+int restore_altstack(const stack_t __user *uss)
+{
+	int err = do_sigaltstack(uss, NULL, current_user_stack_pointer());
+	/* squash all but EFAULT for now */
+	return err == -EFAULT ? err : 0;
+}
+
 #ifdef __ARCH_WANT_SYS_SIGPENDING
 
 /**
-- 
cgit v1.2.3-55-g7522


From 9b064fc3f95a8e44e929fdf4d6037334ea03d15b Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Fri, 14 Dec 2012 13:49:35 -0500
Subject: new helper: compat_user_stack_pointer()

Compat counterpart of current_user_stack_pointer(); for most of the biarch
architectures those two are identical, but e.g. arm64 and arm use different
registers for stack pointer...

Note that amd64 variants of current_user_stack_pointer/compat_user_stack_pointer
do *not* rely on pt_regs having been through FIXUP_TOP_OF_STACK.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/compat.h | 5 +++--
 arch/x86/include/asm/ptrace.h   | 7 +++++++
 include/linux/compat.h          | 3 +++
 3 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 37e610dc084e..d9ec40217a27 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -209,10 +209,11 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 	return (u32)(unsigned long)uptr;
 }
 
+#define compat_user_stack_pointer() (current_pt_regs()->compat_sp)
+
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
-	struct pt_regs *regs = task_pt_regs(current);
-	return (void __user *)regs->compat_sp - len;
+	return (void __user *)compat_user_stack_pointer() - len;
 }
 
 struct compat_ipc64_perm {
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 19f16ebaf4fa..7e560b6daf5d 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -203,6 +203,13 @@ static inline bool user_64bit_mode(struct pt_regs *regs)
 	return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs;
 #endif
 }
+
+#define current_user_stack_pointer()	this_cpu_read(old_rsp)
+/* ia32 vs. x32 difference */
+#define compat_user_stack_pointer()	\
+	(test_thread_flag(TIF_IA32) 	\
+	 ? current_pt_regs()->sp 	\
+	 : this_cpu_read(old_rsp))
 #endif
 
 #ifdef CONFIG_X86_32
diff --git a/include/linux/compat.h b/include/linux/compat.h
index a7877fa809fd..62bb76f91baf 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -65,6 +65,9 @@
 
 #endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */
 
+#ifndef compat_user_stack_pointer
+#define compat_user_stack_pointer() current_user_stack_pointer()
+#endif
 #define compat_jiffies_to_clock_t(x)	\
 		(((unsigned long)(x) * COMPAT_USER_HZ) / HZ)
 
-- 
cgit v1.2.3-55-g7522


From 6bf9adfc90370b695cb111116e15fdc0e1906270 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Fri, 14 Dec 2012 14:09:47 -0500
Subject: introduce generic sys_sigaltstack(), switch x86 and um to it

Conditional on CONFIG_GENERIC_SIGALTSTACK; architectures that do not
select it are completely unaffected

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/Kconfig                     | 3 +++
 arch/um/kernel/signal.c          | 5 -----
 arch/x86/Kconfig                 | 1 +
 arch/x86/include/asm/syscalls.h  | 3 ---
 arch/x86/kernel/entry_32.S       | 1 -
 arch/x86/kernel/entry_64.S       | 1 -
 arch/x86/kernel/signal.c         | 7 -------
 arch/x86/syscalls/syscall_32.tbl | 2 +-
 arch/x86/syscalls/syscall_64.tbl | 2 +-
 arch/x86/um/Kconfig              | 1 +
 arch/x86/um/sys_call_table_32.c  | 1 -
 arch/x86/um/sys_call_table_64.c  | 1 -
 include/linux/syscalls.h         | 6 ++++++
 kernel/signal.c                  | 6 ++++++
 14 files changed, 19 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index 0a8dd0585d0d..330176824594 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -335,6 +335,9 @@ config MODULES_USE_ELF_REL
 	  Modules only use ELF REL relocations.  Modules with ELF RELA
 	  relocations will give an error.
 
+config GENERIC_SIGALTSTACK
+	bool
+
 #
 # ABI hall of shame
 #
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index db18eb6124e1..48ccf718e290 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -132,8 +132,3 @@ long sys_sigsuspend(int history0, int history1, old_sigset_t mask)
 	siginitset(&blocked, mask);
 	return sigsuspend(&blocked);
 }
-
-long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss)
-{
-	return do_sigaltstack(uss, uoss, PT_REGS_SP(&current->thread.regs));
-}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 01ca0ebaff0e..f380614d7d89 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -111,6 +111,7 @@ config X86
 	select MODULES_USE_ELF_REL if X86_32
 	select MODULES_USE_ELF_RELA if X86_64
 	select CLONE_BACKWARDS if X86_32
+	select GENERIC_SIGALTSTACK
 
 config INSTRUCTION_DECODER
 	def_bool y
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 2f8374718aa3..58b7e3eac0ae 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -25,9 +25,6 @@ asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
 
 /* kernel/signal.c */
 long sys_rt_sigreturn(struct pt_regs *);
-long sys_sigaltstack(const stack_t __user *, stack_t __user *,
-		     struct pt_regs *);
-
 
 /* kernel/tls.c */
 asmlinkage int sys_set_thread_area(struct user_desc __user *);
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index c763116c5359..ff84d5469d77 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -739,7 +739,6 @@ ENTRY(ptregs_##name) ; \
 ENDPROC(ptregs_##name)
 
 PTREGSCALL1(iopl)
-PTREGSCALL2(sigaltstack)
 PTREGSCALL0(sigreturn)
 PTREGSCALL0(rt_sigreturn)
 PTREGSCALL2(vm86)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 2363e820ed68..6e462019f195 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -864,7 +864,6 @@ END(stub_\func)
 	FORK_LIKE  clone
 	FORK_LIKE  fork
 	FORK_LIKE  vfork
-	PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx
 	PTREGSCALL stub_iopl, sys_iopl, %rsi
 
 ENTRY(ptregscall_common)
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 70b27ee6118e..16d065c23baf 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -602,13 +602,6 @@ sys_sigaction(int sig, const struct old_sigaction __user *act,
 }
 #endif /* CONFIG_X86_32 */
 
-long
-sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
-		struct pt_regs *regs)
-{
-	return do_sigaltstack(uss, uoss, regs->sp);
-}
-
 /*
  * Do a signal return; undo the signal stack.
  */
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index ee3c220ee500..62c7b222e45c 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -192,7 +192,7 @@
 183	i386	getcwd			sys_getcwd
 184	i386	capget			sys_capget
 185	i386	capset			sys_capset
-186	i386	sigaltstack		ptregs_sigaltstack		stub32_sigaltstack
+186	i386	sigaltstack		sys_sigaltstack			stub32_sigaltstack
 187	i386	sendfile		sys_sendfile			sys32_sendfile
 188	i386	getpmsg
 189	i386	putpmsg
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index a582bfed95bb..6ffa7f9d005e 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -137,7 +137,7 @@
 128	64	rt_sigtimedwait		sys_rt_sigtimedwait
 129	64	rt_sigqueueinfo		sys_rt_sigqueueinfo
 130	common	rt_sigsuspend		sys_rt_sigsuspend
-131	64	sigaltstack		stub_sigaltstack
+131	64	sigaltstack		sys_sigaltstack
 132	common	utime			sys_utime
 133	common	mknod			sys_mknod
 134	64	uselib
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 0fd20f241e40..96b89d874ead 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -13,6 +13,7 @@ endmenu
 config UML_X86
 	def_bool y
 	select GENERIC_FIND_FIRST_BIT
+	select GENERIC_SIGALTSTACK
 
 config 64BIT
 	bool "64-bit kernel" if SUBARCH = "x86"
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 812e98c098e4..a0c3b0d1a122 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -27,7 +27,6 @@
 #define ptregs_iopl sys_iopl
 #define ptregs_vm86old sys_vm86old
 #define ptregs_vm86 sys_vm86
-#define ptregs_sigaltstack sys_sigaltstack
 
 #define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ;
 #include <asm/syscalls_32.h>
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index 170bd926a69c..f2f0723070ca 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -31,7 +31,6 @@
 #define stub_fork sys_fork
 #define stub_vfork sys_vfork
 #define stub_execve sys_execve
-#define stub_sigaltstack sys_sigaltstack
 #define stub_rt_sigreturn sys_rt_sigreturn
 
 #define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 9fe5f946526e..6ca1e08210c6 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -63,6 +63,7 @@ struct getcpu_cache;
 struct old_linux_dirent;
 struct perf_event_attr;
 struct file_handle;
+struct sigaltstack;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -299,6 +300,11 @@ asmlinkage long sys_personality(unsigned int personality);
 asmlinkage long sys_sigpending(old_sigset_t __user *set);
 asmlinkage long sys_sigprocmask(int how, old_sigset_t __user *set,
 				old_sigset_t __user *oset);
+#ifdef CONFIG_GENERIC_SIGALTSTACK
+asmlinkage long sys_sigaltstack(const struct sigaltstack __user *uss,
+				struct sigaltstack __user *uoss);
+#endif
+
 asmlinkage long sys_getitimer(int which, struct itimerval __user *value);
 asmlinkage long sys_setitimer(int which,
 				struct itimerval __user *value,
diff --git a/kernel/signal.c b/kernel/signal.c
index 887f2fefe207..f05f4c4150d9 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3102,6 +3102,12 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s
 out:
 	return error;
 }
+#ifdef CONFIG_GENERIC_SIGALTSTACK
+SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss)
+{
+	return do_sigaltstack(uss, uoss, current_user_stack_pointer());
+}
+#endif
 
 int restore_altstack(const stack_t __user *uss)
 {
-- 
cgit v1.2.3-55-g7522


From 9026843952adac5b123c7b8dc961e5c15828d9e1 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Fri, 14 Dec 2012 14:47:53 -0500
Subject: generic compat_sys_sigaltstack()

Again, conditional on CONFIG_GENERIC_SIGALTSTACK

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/ia32/ia32_signal.c      | 50 +---------------------------------------
 arch/x86/ia32/ia32entry.S        |  1 -
 arch/x86/include/asm/ia32.h      | 10 ++------
 arch/x86/include/asm/sys_ia32.h  |  2 --
 arch/x86/kernel/entry_64.S       |  2 --
 arch/x86/kernel/signal.c         |  4 +---
 arch/x86/syscalls/syscall_32.tbl |  2 +-
 arch/x86/syscalls/syscall_64.tbl |  2 +-
 include/linux/compat.h           | 16 +++++++++++++
 kernel/signal.c                  | 45 ++++++++++++++++++++++++++++++++++++
 10 files changed, 67 insertions(+), 67 deletions(-)

(limited to 'include')

diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index efc6a958b71d..a866411a2fcc 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -136,52 +136,6 @@ asmlinkage long sys32_sigsuspend(int history0, int history1, old_sigset_t mask)
 	return sigsuspend(&blocked);
 }
 
-asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr,
-				  stack_ia32_t __user *uoss_ptr,
-				  struct pt_regs *regs)
-{
-	stack_t uss, uoss;
-	int ret, err = 0;
-	mm_segment_t seg;
-
-	if (uss_ptr) {
-		u32 ptr;
-
-		memset(&uss, 0, sizeof(stack_t));
-		if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t)))
-			return -EFAULT;
-
-		get_user_try {
-			get_user_ex(ptr, &uss_ptr->ss_sp);
-			get_user_ex(uss.ss_flags, &uss_ptr->ss_flags);
-			get_user_ex(uss.ss_size, &uss_ptr->ss_size);
-		} get_user_catch(err);
-
-		if (err)
-			return -EFAULT;
-		uss.ss_sp = compat_ptr(ptr);
-	}
-	seg = get_fs();
-	set_fs(KERNEL_DS);
-	ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL),
-			     (stack_t __force __user *) &uoss, regs->sp);
-	set_fs(seg);
-	if (ret >= 0 && uoss_ptr)  {
-		if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)))
-			return -EFAULT;
-
-		put_user_try {
-			put_user_ex(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp);
-			put_user_ex(uoss.ss_flags, &uoss_ptr->ss_flags);
-			put_user_ex(uoss.ss_size, &uoss_ptr->ss_size);
-		} put_user_catch(err);
-
-		if (err)
-			ret = -EFAULT;
-	}
-	return ret;
-}
-
 /*
  * Do a signal return; undo the signal stack.
  */
@@ -292,7 +246,6 @@ asmlinkage long sys32_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe_ia32 __user *frame;
 	sigset_t set;
 	unsigned int ax;
-	struct pt_regs tregs;
 
 	frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
 
@@ -306,8 +259,7 @@ asmlinkage long sys32_rt_sigreturn(struct pt_regs *regs)
 	if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
 		goto badframe;
 
-	tregs = *regs;
-	if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT)
+	if (compat_restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
 
 	return ax;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 32e6f05ddaaa..102ff7cb3e41 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -464,7 +464,6 @@ GLOBAL(\label)
 
 	PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi
 	PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi
-	PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx
 	PTREGSCALL stub32_execve, compat_sys_execve, %rcx
 	PTREGSCALL stub32_fork, sys_fork, %rdi
 	PTREGSCALL stub32_vfork, sys_vfork, %rdi
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index e6232773ce49..4c6da2e4bb1d 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -29,16 +29,10 @@ struct old_sigaction32 {
 	unsigned int sa_restorer;	/* Another 32 bit pointer */
 };
 
-typedef struct sigaltstack_ia32 {
-	unsigned int	ss_sp;
-	int		ss_flags;
-	unsigned int	ss_size;
-} stack_ia32_t;
-
 struct ucontext_ia32 {
 	unsigned int	  uc_flags;
 	unsigned int 	  uc_link;
-	stack_ia32_t	  uc_stack;
+	compat_stack_t	  uc_stack;
 	struct sigcontext_ia32 uc_mcontext;
 	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
 };
@@ -46,7 +40,7 @@ struct ucontext_ia32 {
 struct ucontext_x32 {
 	unsigned int	  uc_flags;
 	unsigned int 	  uc_link;
-	stack_ia32_t	  uc_stack;
+	compat_stack_t	  uc_stack;
 	unsigned int	  uc__pad0;     /* needed for alignment */
 	struct sigcontext uc_mcontext;  /* the 64-bit sigcontext type */
 	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index c76fae4d90be..31f61f96e0fb 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -69,8 +69,6 @@ asmlinkage long sys32_fallocate(int, int, unsigned,
 
 /* ia32/ia32_signal.c */
 asmlinkage long sys32_sigsuspend(int, int, old_sigset_t);
-asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *,
-				  stack_ia32_t __user *, struct pt_regs *);
 asmlinkage long sys32_sigreturn(struct pt_regs *);
 asmlinkage long sys32_rt_sigreturn(struct pt_regs *);
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 6e462019f195..86d81199bbde 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -912,8 +912,6 @@ ENTRY(stub_rt_sigreturn)
 END(stub_rt_sigreturn)
 
 #ifdef CONFIG_X86_X32_ABI
-	PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx
-
 ENTRY(stub_x32_rt_sigreturn)
 	CFI_STARTPROC
 	addq $8, %rsp
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 16d065c23baf..b17ed37c61a2 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -857,7 +857,6 @@ asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe_x32 __user *frame;
 	sigset_t set;
 	unsigned long ax;
-	struct pt_regs tregs;
 
 	frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
 
@@ -871,8 +870,7 @@ asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
 	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
 		goto badframe;
 
-	tregs = *regs;
-	if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT)
+	if (compat_restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
 
 	return ax;
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index 62c7b222e45c..235226efaa7f 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -192,7 +192,7 @@
 183	i386	getcwd			sys_getcwd
 184	i386	capget			sys_capget
 185	i386	capset			sys_capset
-186	i386	sigaltstack		sys_sigaltstack			stub32_sigaltstack
+186	i386	sigaltstack		sys_sigaltstack			compat_sys_sigaltstack
 187	i386	sendfile		sys_sendfile			sys32_sendfile
 188	i386	getpmsg
 189	i386	putpmsg
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 6ffa7f9d005e..c68cbe7174e7 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -337,7 +337,7 @@
 522	x32	rt_sigpending		sys32_rt_sigpending
 523	x32	rt_sigtimedwait		compat_sys_rt_sigtimedwait
 524	x32	rt_sigqueueinfo		sys32_rt_sigqueueinfo
-525	x32	sigaltstack		stub_x32_sigaltstack
+525	x32	sigaltstack		compat_sys_sigaltstack
 526	x32	timer_create		compat_sys_timer_create
 527	x32	mq_notify		compat_sys_mq_notify
 528	x32	kexec_load		compat_sys_kexec_load
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 62bb76f91baf..cb5637e2ee2c 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -68,6 +68,16 @@
 #ifndef compat_user_stack_pointer
 #define compat_user_stack_pointer() current_user_stack_pointer()
 #endif
+#ifdef CONFIG_GENERIC_SIGALTSTACK
+#ifndef compat_sigaltstack	/* we'll need that for MIPS */
+typedef struct compat_sigaltstack {
+	compat_uptr_t			ss_sp;
+	int				ss_flags;
+	compat_size_t			ss_size;
+} compat_stack_t;
+#endif
+#endif
+
 #define compat_jiffies_to_clock_t(x)	\
 		(((unsigned long)(x) * COMPAT_USER_HZ) / HZ)
 
@@ -632,6 +642,12 @@ asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid,
 
 asmlinkage long compat_sys_sendfile(int out_fd, int in_fd,
 				    compat_off_t __user *offset, compat_size_t count);
+#ifdef CONFIG_GENERIC_SIGALTSTACK
+asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr,
+				       compat_stack_t __user *uoss_ptr);
+
+int compat_restore_altstack(const compat_stack_t __user *uss);
+#endif
 
 #else
 
diff --git a/kernel/signal.c b/kernel/signal.c
index f05f4c4150d9..aee85bd76b8a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -31,6 +31,7 @@
 #include <linux/nsproxy.h>
 #include <linux/user_namespace.h>
 #include <linux/uprobes.h>
+#include <linux/compat.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/signal.h>
 
@@ -3116,6 +3117,50 @@ int restore_altstack(const stack_t __user *uss)
 	return err == -EFAULT ? err : 0;
 }
 
+#ifdef CONFIG_COMPAT
+#ifdef CONFIG_GENERIC_SIGALTSTACK
+asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr,
+				       compat_stack_t __user *uoss_ptr)
+{
+	stack_t uss, uoss;
+	int ret;
+	mm_segment_t seg;
+
+	if (uss_ptr) {
+		compat_stack_t uss32;
+
+		memset(&uss, 0, sizeof(stack_t));
+		if (copy_from_user(&uss32, uss_ptr, sizeof(compat_stack_t)))
+			return -EFAULT;
+		uss.ss_sp = compat_ptr(uss32.ss_sp);
+		uss.ss_flags = uss32.ss_flags;
+		uss.ss_size = uss32.ss_size;
+	}
+	seg = get_fs();
+	set_fs(KERNEL_DS);
+	ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL),
+			     (stack_t __force __user *) &uoss,
+			     compat_user_stack_pointer());
+	set_fs(seg);
+	if (ret >= 0 && uoss_ptr)  {
+		if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(compat_stack_t)) ||
+		    __put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) ||
+		    __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) ||
+		    __put_user(uoss.ss_size, &uoss_ptr->ss_size))
+			ret = -EFAULT;
+	}
+	return ret;
+}
+
+int compat_restore_altstack(const compat_stack_t __user *uss)
+{
+	int err = compat_sys_sigaltstack(uss, NULL);
+	/* squash all but -EFAULT for now */
+	return err == -EFAULT ? err : 0;
+}
+#endif
+#endif
+
 #ifdef __ARCH_WANT_SYS_SIGPENDING
 
 /**
-- 
cgit v1.2.3-55-g7522


From c40702c49faef05ae324f121d8b3e215244ee152 Mon Sep 17 00:00:00 2001
From: Al Viro
Date: Tue, 20 Nov 2012 14:24:26 -0500
Subject: new helpers: __save_altstack/__compat_save_altstack, switch x86 and
 um to those

note that they are relying on access_ok() already checked by caller.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/ia32/ia32_signal.c |  5 +----
 arch/x86/kernel/signal.c    | 18 ++++--------------
 arch/x86/um/signal.c        |  9 ++-------
 include/linux/compat.h      |  1 +
 include/linux/signal.h      |  1 +
 kernel/signal.c             | 16 ++++++++++++++++
 6 files changed, 25 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index a866411a2fcc..a1daf4a65009 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -467,10 +467,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
-		put_user_ex(sas_ss_flags(regs->sp),
-			    &frame->uc.uc_stack.ss_flags);
-		put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+		err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
 
 		if (ka->sa.sa_flags & SA_RESTORER)
 			restorer = ka->sa.sa_restorer;
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b17ed37c61a2..a6c8a347b8c6 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -363,10 +363,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
-		put_user_ex(sas_ss_flags(regs->sp),
-			    &frame->uc.uc_stack.ss_flags);
-		put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+		err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
 
 		/* Set up to return from userspace.  */
 		restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
@@ -413,7 +410,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	struct rt_sigframe __user *frame;
 	void __user *fp = NULL;
 	int err = 0;
-	struct task_struct *me = current;
 
 	frame = get_sigframe(ka, regs, sizeof(struct rt_sigframe), &fp);
 
@@ -432,10 +428,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		put_user_ex(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
-		put_user_ex(sas_ss_flags(regs->sp),
-			    &frame->uc.uc_stack.ss_flags);
-		put_user_ex(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
+		err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
 
 		/* Set up to return from userspace.  If provided, use a stub
 		   already in userspace.  */
@@ -502,10 +495,7 @@ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
-		put_user_ex(sas_ss_flags(regs->sp),
-			    &frame->uc.uc_stack.ss_flags);
-		put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+		err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
 		put_user_ex(0, &frame->uc.uc__pad0);
 
 		if (ka->sa.sa_flags & SA_RESTORER) {
@@ -651,7 +641,7 @@ long sys_rt_sigreturn(struct pt_regs *regs)
 	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
 		goto badframe;
 
-	if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT)
+	if (restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
 
 	return ax;
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index bdaa08cfbcf4..71cef48ea5cd 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -342,9 +342,7 @@ static int copy_ucontext_to_user(struct ucontext __user *uc,
 {
 	int err = 0;
 
-	err |= put_user(current->sas_ss_sp, &uc->uc_stack.ss_sp);
-	err |= put_user(sas_ss_flags(sp), &uc->uc_stack.ss_flags);
-	err |= put_user(current->sas_ss_size, &uc->uc_stack.ss_size);
+	err |= __save_altstack(&uc->uc_stack, sp);
 	err |= copy_sc_to_user(&uc->uc_mcontext, fp, &current->thread.regs, 0);
 	err |= copy_to_user(&uc->uc_sigmask, set, sizeof(*set));
 	return err;
@@ -529,10 +527,7 @@ int setup_signal_stack_si(unsigned long stack_top, int sig,
 	/* Create the ucontext.  */
 	err |= __put_user(0, &frame->uc.uc_flags);
 	err |= __put_user(0, &frame->uc.uc_link);
-	err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
-	err |= __put_user(sas_ss_flags(PT_REGS_SP(regs)),
-			  &frame->uc.uc_stack.ss_flags);
-	err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
+	err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs));
 	err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs,
 			       set->sig[0]);
 	err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate);
diff --git a/include/linux/compat.h b/include/linux/compat.h
index cb5637e2ee2c..334813307ec1 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -647,6 +647,7 @@ asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr,
 				       compat_stack_t __user *uoss_ptr);
 
 int compat_restore_altstack(const compat_stack_t __user *uss);
+int __compat_save_altstack(compat_stack_t __user *, unsigned long);
 #endif
 
 #else
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 5969522136fe..0a89ffc48466 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -386,5 +386,6 @@ int unhandled_signal(struct task_struct *tsk, int sig);
 void signals_init(void);
 
 int restore_altstack(const stack_t __user *);
+int __save_altstack(stack_t __user *, unsigned long);
 
 #endif /* _LINUX_SIGNAL_H */
diff --git a/kernel/signal.c b/kernel/signal.c
index aee85bd76b8a..f072513302c3 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3117,6 +3117,14 @@ int restore_altstack(const stack_t __user *uss)
 	return err == -EFAULT ? err : 0;
 }
 
+int __save_altstack(stack_t __user *uss, unsigned long sp)
+{
+	struct task_struct *t = current;
+	return  __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) |
+		__put_user(sas_ss_flags(sp), &uss->ss_flags) |
+		__put_user(t->sas_ss_size, &uss->ss_size);
+}
+
 #ifdef CONFIG_COMPAT
 #ifdef CONFIG_GENERIC_SIGALTSTACK
 asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr,
@@ -3158,6 +3166,14 @@ int compat_restore_altstack(const compat_stack_t __user *uss)
 	/* squash all but -EFAULT for now */
 	return err == -EFAULT ? err : 0;
 }
+
+int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp)
+{
+	struct task_struct *t = current;
+	return  __put_user(ptr_to_compat((void __user *)t->sas_ss_sp), &uss->ss_sp) |
+		__put_user(sas_ss_flags(sp), &uss->ss_flags) |
+		__put_user(t->sas_ss_size, &uss->ss_size);
+}
 #endif
 #endif
 
-- 
cgit v1.2.3-55-g7522


From ada65c74059f8c104f1b467c126205471634c435 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst
Date: Wed, 12 Dec 2012 10:23:03 +0100
Subject: dma-buf: remove fallback for !CONFIG_DMA_SHARED_BUFFER

Documentation says that code requiring dma-buf should add it to
select, so inline fallbacks are not going to be used. A link error
will make it obvious what went wrong, instead of silently doing
nothing at runtime.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Rob Clark <rob.clark@linaro.org>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
---
 include/linux/dma-buf.h | 99 -------------------------------------------------
 1 file changed, 99 deletions(-)

(limited to 'include')

diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index eb48f3816df9..bd2e52ccc4f2 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -156,7 +156,6 @@ static inline void get_dma_buf(struct dma_buf *dmabuf)
 	get_file(dmabuf->file);
 }
 
-#ifdef CONFIG_DMA_SHARED_BUFFER
 struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 							struct device *dev);
 void dma_buf_detach(struct dma_buf *dmabuf,
@@ -184,103 +183,5 @@ int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *,
 		 unsigned long);
 void *dma_buf_vmap(struct dma_buf *);
 void dma_buf_vunmap(struct dma_buf *, void *vaddr);
-#else
-
-static inline struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
-							struct device *dev)
-{
-	return ERR_PTR(-ENODEV);
-}
-
-static inline void dma_buf_detach(struct dma_buf *dmabuf,
-				  struct dma_buf_attachment *dmabuf_attach)
-{
-	return;
-}
-
-static inline struct dma_buf *dma_buf_export(void *priv,
-					     const struct dma_buf_ops *ops,
-					     size_t size, int flags)
-{
-	return ERR_PTR(-ENODEV);
-}
-
-static inline int dma_buf_fd(struct dma_buf *dmabuf, int flags)
-{
-	return -ENODEV;
-}
-
-static inline struct dma_buf *dma_buf_get(int fd)
-{
-	return ERR_PTR(-ENODEV);
-}
-
-static inline void dma_buf_put(struct dma_buf *dmabuf)
-{
-	return;
-}
-
-static inline struct sg_table *dma_buf_map_attachment(
-	struct dma_buf_attachment *attach, enum dma_data_direction write)
-{
-	return ERR_PTR(-ENODEV);
-}
-
-static inline void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
-			struct sg_table *sg, enum dma_data_direction dir)
-{
-	return;
-}
-
-static inline int dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
-					   size_t start, size_t len,
-					   enum dma_data_direction dir)
-{
-	return -ENODEV;
-}
-
-static inline void dma_buf_end_cpu_access(struct dma_buf *dmabuf,
-					  size_t start, size_t len,
-					  enum dma_data_direction dir)
-{
-}
-
-static inline void *dma_buf_kmap_atomic(struct dma_buf *dmabuf,
-					unsigned long pnum)
-{
-	return NULL;
-}
-
-static inline void dma_buf_kunmap_atomic(struct dma_buf *dmabuf,
-					 unsigned long pnum, void *vaddr)
-{
-}
-
-static inline void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long pnum)
-{
-	return NULL;
-}
-
-static inline void dma_buf_kunmap(struct dma_buf *dmabuf,
-				  unsigned long pnum, void *vaddr)
-{
-}
-
-static inline int dma_buf_mmap(struct dma_buf *dmabuf,
-			       struct vm_area_struct *vma,
-			       unsigned long pgoff)
-{
-	return -ENODEV;
-}
-
-static inline void *dma_buf_vmap(struct dma_buf *dmabuf)
-{
-	return NULL;
-}
-
-static inline void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
-{
-}
-#endif /* CONFIG_DMA_SHARED_BUFFER */
 
 #endif /* __DMA_BUF_H__ */
-- 
cgit v1.2.3-55-g7522


From 9bde4f0b1c83d1129a9fc8ec5b2611ba6dab1215 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Wed, 19 Dec 2012 16:05:00 +0000
Subject: ASoC: core: Fix SOC_DOUBLE_RANGE() macros

Although we've had macros defining double _RANGE controls for a while now
they've not actually been backed up properly by the implementation, it's
treated everything as mono. Fix that by implementing the handling in the
stereo controls, ensuring that the mono controls don't mistakenly get
treated as stereo.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Acked-by: Liam Girdwood <lrg@ti.com>
---
 include/sound/soc.h  | 10 ++++++----
 sound/soc/soc-core.c | 32 ++++++++++++++++++++++++++++++--
 2 files changed, 36 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 769e27c774a3..bc56738cb109 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -58,8 +58,9 @@
 	.info = snd_soc_info_volsw_range, .get = snd_soc_get_volsw_range, \
 	.put = snd_soc_put_volsw_range, \
 	.private_value = (unsigned long)&(struct soc_mixer_control) \
-		{.reg = xreg, .shift = xshift, .min = xmin,\
-		 .max = xmax, .platform_max = xmax, .invert = xinvert} }
+		{.reg = xreg, .rreg = xreg, .shift = xshift, \
+		 .rshift = xshift,  .min = xmin, .max = xmax, \
+		 .platform_max = xmax, .invert = xinvert} }
 #define SOC_SINGLE_TLV(xname, reg, shift, max, invert, tlv_array) \
 {	.iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \
 	.access = SNDRV_CTL_ELEM_ACCESS_TLV_READ |\
@@ -88,8 +89,9 @@
 	.info = snd_soc_info_volsw_range, \
 	.get = snd_soc_get_volsw_range, .put = snd_soc_put_volsw_range, \
 	.private_value = (unsigned long)&(struct soc_mixer_control) \
-		{.reg = xreg, .shift = xshift, .min = xmin,\
-		 .max = xmax, .platform_max = xmax, .invert = xinvert} }
+		{.reg = xreg, .rreg = xreg, .shift = xshift, \
+		 .rshift = xshift, .min = xmin, .max = xmax, \
+		 .platform_max = xmax, .invert = xinvert} }
 #define SOC_DOUBLE(xname, reg, shift_left, shift_right, max, invert) \
 {	.iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = (xname),\
 	.info = snd_soc_info_volsw, .get = snd_soc_get_volsw, \
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 91d592ff67b7..e0d4630bfb4f 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2917,7 +2917,7 @@ int snd_soc_info_volsw_range(struct snd_kcontrol *kcontrol,
 	platform_max = mc->platform_max;
 
 	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
-	uinfo->count = 1;
+	uinfo->count = snd_soc_volsw_is_stereo(mc) ? 2 : 1;
 	uinfo->value.integer.min = 0;
 	uinfo->value.integer.max = platform_max - min;
 
@@ -2941,12 +2941,14 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol,
 		(struct soc_mixer_control *)kcontrol->private_value;
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	unsigned int reg = mc->reg;
+	unsigned int rreg = mc->rreg;
 	unsigned int shift = mc->shift;
 	int min = mc->min;
 	int max = mc->max;
 	unsigned int mask = (1 << fls(max)) - 1;
 	unsigned int invert = mc->invert;
 	unsigned int val, val_mask;
+	int ret;
 
 	val = ((ucontrol->value.integer.value[0] + min) & mask);
 	if (invert)
@@ -2954,7 +2956,21 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol,
 	val_mask = mask << shift;
 	val = val << shift;
 
-	return snd_soc_update_bits_locked(codec, reg, val_mask, val);
+	ret = snd_soc_update_bits_locked(codec, reg, val_mask, val);
+	if (ret != 0)
+		return ret;
+
+	if (snd_soc_volsw_is_stereo(mc)) {
+		val = ((ucontrol->value.integer.value[1] + min) & mask);
+		if (invert)
+			val = max - val;
+		val_mask = mask << shift;
+		val = val << shift;
+
+		ret = snd_soc_update_bits_locked(codec, rreg, val_mask, val);
+	}
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_put_volsw_range);
 
@@ -2974,11 +2990,13 @@ int snd_soc_get_volsw_range(struct snd_kcontrol *kcontrol,
 		(struct soc_mixer_control *)kcontrol->private_value;
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	unsigned int reg = mc->reg;
+	unsigned int rreg = mc->rreg;
 	unsigned int shift = mc->shift;
 	int min = mc->min;
 	int max = mc->max;
 	unsigned int mask = (1 << fls(max)) - 1;
 	unsigned int invert = mc->invert;
+	int ret;
 
 	ucontrol->value.integer.value[0] =
 		(snd_soc_read(codec, reg) >> shift) & mask;
@@ -2988,6 +3006,16 @@ int snd_soc_get_volsw_range(struct snd_kcontrol *kcontrol,
 	ucontrol->value.integer.value[0] =
 		ucontrol->value.integer.value[0] - min;
 
+	if (snd_soc_volsw_is_stereo(mc)) {
+		ucontrol->value.integer.value[1] =
+			(snd_soc_read(codec, rreg) >> shift) & mask;
+		if (invert)
+			ucontrol->value.integer.value[1] =
+				max - ucontrol->value.integer.value[1];
+		ucontrol->value.integer.value[1] =
+			ucontrol->value.integer.value[1] - min;
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_soc_get_volsw_range);
-- 
cgit v1.2.3-55-g7522


From 39e3c9553f34381a1b664c27b0c696a266a5735e Mon Sep 17 00:00:00 2001
From: Jeff Layton
Date: Wed, 28 Nov 2012 11:30:53 -0500
Subject: vfs: remove DCACHE_NEED_LOOKUP

The code that relied on that flag was ripped out of btrfs quite some
time ago, and never added back. Josef indicated that he was going to
take a different approach to the problem in btrfs, and that we
could just eliminate this flag.

Cc: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/btrfs/inode.c       | 16 +---------------
 fs/dcache.c            | 33 +--------------------------------
 fs/namei.c             | 11 +----------
 include/linux/dcache.h |  8 --------
 4 files changed, 3 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 67ed24ae86bb..16d9e8e191e6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4262,16 +4262,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 	if (dentry->d_name.len > BTRFS_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	if (unlikely(d_need_lookup(dentry))) {
-		memcpy(&location, dentry->d_fsdata, sizeof(struct btrfs_key));
-		kfree(dentry->d_fsdata);
-		dentry->d_fsdata = NULL;
-		/* This thing is hashed, drop it for now */
-		d_drop(dentry);
-	} else {
-		ret = btrfs_inode_by_name(dir, dentry, &location);
-	}
-
+	ret = btrfs_inode_by_name(dir, dentry, &location);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
@@ -4341,11 +4332,6 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
 	struct dentry *ret;
 
 	ret = d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry);
-	if (unlikely(d_need_lookup(dentry))) {
-		spin_lock(&dentry->d_lock);
-		dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
-		spin_unlock(&dentry->d_lock);
-	}
 	return ret;
 }
 
diff --git a/fs/dcache.c b/fs/dcache.c
index 3a463d0c4fe8..1782be3fc3ef 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -454,24 +454,6 @@ void d_drop(struct dentry *dentry)
 }
 EXPORT_SYMBOL(d_drop);
 
-/*
- * d_clear_need_lookup - drop a dentry from cache and clear the need lookup flag
- * @dentry: dentry to drop
- *
- * This is called when we do a lookup on a placeholder dentry that needed to be
- * looked up.  The dentry should have been hashed in order for it to be found by
- * the lookup code, but now needs to be unhashed while we do the actual lookup
- * and clear the DCACHE_NEED_LOOKUP flag.
- */
-void d_clear_need_lookup(struct dentry *dentry)
-{
-	spin_lock(&dentry->d_lock);
-	__d_drop(dentry);
-	dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
-	spin_unlock(&dentry->d_lock);
-}
-EXPORT_SYMBOL(d_clear_need_lookup);
-
 /*
  * Finish off a dentry we've decided to kill.
  * dentry->d_lock must be held, returns with it unlocked.
@@ -565,13 +547,7 @@ repeat:
  	if (d_unhashed(dentry))
 		goto kill_it;
 
-	/*
-	 * If this dentry needs lookup, don't set the referenced flag so that it
-	 * is more likely to be cleaned up by the dcache shrinker in case of
-	 * memory pressure.
-	 */
-	if (!d_need_lookup(dentry))
-		dentry->d_flags |= DCACHE_REFERENCED;
+	dentry->d_flags |= DCACHE_REFERENCED;
 	dentry_lru_add(dentry);
 
 	dentry->d_count--;
@@ -1736,13 +1712,6 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
 		return found;
 	}
 
-	/*
-	 * We are going to instantiate this dentry, unhash it and clear the
-	 * lookup flag so we can do that.
-	 */
-	if (unlikely(d_need_lookup(found)))
-		d_clear_need_lookup(found);
-
 	/*
 	 * Negative dentry: instantiate it unless the inode is a directory and
 	 * already has a dentry.
diff --git a/fs/namei.c b/fs/namei.c
index 35195ff9d194..25a41e02984b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1275,9 +1275,7 @@ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
 	*need_lookup = false;
 	dentry = d_lookup(dir, name);
 	if (dentry) {
-		if (d_need_lookup(dentry)) {
-			*need_lookup = true;
-		} else if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
+		if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
 			error = d_revalidate(dentry, flags);
 			if (unlikely(error <= 0)) {
 				if (error < 0) {
@@ -1383,8 +1381,6 @@ static int lookup_fast(struct nameidata *nd, struct qstr *name,
 			return -ECHILD;
 		nd->seq = seq;
 
-		if (unlikely(d_need_lookup(dentry)))
-			goto unlazy;
 		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
 			status = d_revalidate(dentry, nd->flags);
 			if (unlikely(status <= 0)) {
@@ -1410,11 +1406,6 @@ unlazy:
 	if (unlikely(!dentry))
 		goto need_lookup;
 
-	if (unlikely(d_need_lookup(dentry))) {
-		dput(dentry);
-		goto need_lookup;
-	}
-
 	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
 		status = d_revalidate(dentry, nd->flags);
 	if (unlikely(status <= 0)) {
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 59200795482e..c1754b59ddd3 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -202,7 +202,6 @@ struct dentry_operations {
 #define DCACHE_MOUNTED		0x10000	/* is a mountpoint */
 #define DCACHE_NEED_AUTOMOUNT	0x20000	/* handle automount on this dir */
 #define DCACHE_MANAGE_TRANSIT	0x40000	/* manage transit from this dirent */
-#define DCACHE_NEED_LOOKUP	0x80000 /* dentry requires i_op->lookup */
 #define DCACHE_MANAGED_DENTRY \
 	(DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT)
 
@@ -408,13 +407,6 @@ static inline bool d_mountpoint(struct dentry *dentry)
 	return dentry->d_flags & DCACHE_MOUNTED;
 }
 
-static inline bool d_need_lookup(struct dentry *dentry)
-{
-	return dentry->d_flags & DCACHE_NEED_LOOKUP;
-}
-
-extern void d_clear_need_lookup(struct dentry *dentry);
-
 extern int sysctl_vfs_cache_pressure;
 
 #endif	/* __LINUX_DCACHE_H */
-- 
cgit v1.2.3-55-g7522


From c4d6d8dbf335c7fa47341654a37c53a512b519bb Mon Sep 17 00:00:00 2001
From: David Howells
Date: Thu, 20 Dec 2012 21:52:32 +0000
Subject: CacheFiles: Fix the marking of cached pages

Under some circumstances CacheFiles defers the marking of pages with PG_fscache
so that it can take advantage of pagevecs to reduce the number of calls to
fscache_mark_pages_cached() and the netfs's hook to keep track of this.

There are, however, two problems with this:

 (1) It can lead to the PG_fscache mark being applied _after_ the page is set
     PG_uptodate and unlocked (by the call to fscache_end_io()).

 (2) CacheFiles's ref on the page is dropped immediately following
     fscache_end_io() - and so may not still be held when the mark is applied.
     This can lead to the page being passed back to the allocator before the
     mark is applied.

Fix this by, where appropriate, marking the page before calling
fscache_end_io() and releasing the page.  This means that we can't take
advantage of pagevecs and have to make a separate call for each page to the
marking routines.

The symptoms of this are Bad Page state errors cropping up under memory
pressure, for example:

BUG: Bad page state in process tar  pfn:002da
page:ffffea0000009fb0 count:0 mapcount:0 mapping:          (null) index:0x1447
page flags: 0x1000(private_2)
Pid: 4574, comm: tar Tainted: G        W   3.1.0-rc4-fsdevel+ #1064
Call Trace:
 [<ffffffff8109583c>] ? dump_page+0xb9/0xbe
 [<ffffffff81095916>] bad_page+0xd5/0xea
 [<ffffffff81095d82>] get_page_from_freelist+0x35b/0x46a
 [<ffffffff810961f3>] __alloc_pages_nodemask+0x362/0x662
 [<ffffffff810989da>] __do_page_cache_readahead+0x13a/0x267
 [<ffffffff81098942>] ? __do_page_cache_readahead+0xa2/0x267
 [<ffffffff81098d7b>] ra_submit+0x1c/0x20
 [<ffffffff8109900a>] ondemand_readahead+0x28b/0x29a
 [<ffffffff81098ee2>] ? ondemand_readahead+0x163/0x29a
 [<ffffffff810990ce>] page_cache_sync_readahead+0x38/0x3a
 [<ffffffff81091d8a>] generic_file_aio_read+0x2ab/0x67e
 [<ffffffffa008cfbe>] nfs_file_read+0xa4/0xc9 [nfs]
 [<ffffffff810c22c4>] do_sync_read+0xba/0xfa
 [<ffffffff81177a47>] ? security_file_permission+0x7b/0x84
 [<ffffffff810c25dd>] ? rw_verify_area+0xab/0xc8
 [<ffffffff810c29a4>] vfs_read+0xaa/0x13a
 [<ffffffff810c2a79>] sys_read+0x45/0x6c
 [<ffffffff813ac37b>] system_call_fastpath+0x16/0x1b

As can be seen, PG_private_2 (== PG_fscache) is set in the page flags.

Instrumenting fscache_mark_pages_cached() to verify whether page->mapping was
set appropriately showed that sometimes it wasn't.  This led to the discovery
that sometimes the page has apparently been reclaimed by the time the marker
got to see it.

Reported-by: M. Stevens <m@tippett.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
---
 fs/cachefiles/rdwr.c          | 34 ++++++++-----------------
 fs/fscache/page.c             | 59 ++++++++++++++++++++++++++-----------------
 include/linux/fscache-cache.h |  3 +++
 include/linux/fscache.h       | 12 ++++-----
 4 files changed, 56 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index c994691d9445..3367abdcdac4 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -176,9 +176,8 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
 	recheck:
 		if (PageUptodate(monitor->back_page)) {
 			copy_highpage(monitor->netfs_page, monitor->back_page);
-
-			pagevec_add(&pagevec, monitor->netfs_page);
-			fscache_mark_pages_cached(monitor->op, &pagevec);
+			fscache_mark_page_cached(monitor->op,
+						 monitor->netfs_page);
 			error = 0;
 		} else if (!PageError(monitor->back_page)) {
 			/* the page has probably been truncated */
@@ -335,8 +334,7 @@ backing_page_already_present:
 backing_page_already_uptodate:
 	_debug("- uptodate");
 
-	pagevec_add(pagevec, netpage);
-	fscache_mark_pages_cached(op, pagevec);
+	fscache_mark_page_cached(op, netpage);
 
 	copy_highpage(netpage, backpage);
 	fscache_end_io(op, netpage, 0);
@@ -448,8 +446,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 						       &pagevec);
 	} else if (cachefiles_has_space(cache, 0, 1) == 0) {
 		/* there's space in the cache we can use */
-		pagevec_add(&pagevec, page);
-		fscache_mark_pages_cached(op, &pagevec);
+		fscache_mark_page_cached(op, page);
 		ret = -ENODATA;
 	} else {
 		ret = -ENOBUFS;
@@ -465,8 +462,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
  */
 static int cachefiles_read_backing_file(struct cachefiles_object *object,
 					struct fscache_retrieval *op,
-					struct list_head *list,
-					struct pagevec *mark_pvec)
+					struct list_head *list)
 {
 	struct cachefiles_one_read *monitor = NULL;
 	struct address_space *bmapping = object->backer->d_inode->i_mapping;
@@ -626,13 +622,13 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 		page_cache_release(backpage);
 		backpage = NULL;
 
-		if (!pagevec_add(mark_pvec, netpage))
-			fscache_mark_pages_cached(op, mark_pvec);
+		fscache_mark_page_cached(op, netpage);
 
 		page_cache_get(netpage);
 		if (!pagevec_add(&lru_pvec, netpage))
 			__pagevec_lru_add_file(&lru_pvec);
 
+		/* the netpage is unlocked and marked up to date here */
 		fscache_end_io(op, netpage, 0);
 		page_cache_release(netpage);
 		netpage = NULL;
@@ -775,15 +771,11 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 	/* submit the apparently valid pages to the backing fs to be read from
 	 * disk */
 	if (nrbackpages > 0) {
-		ret2 = cachefiles_read_backing_file(object, op, &backpages,
-						    &pagevec);
+		ret2 = cachefiles_read_backing_file(object, op, &backpages);
 		if (ret2 == -ENOMEM || ret2 == -EINTR)
 			ret = ret2;
 	}
 
-	if (pagevec_count(&pagevec) > 0)
-		fscache_mark_pages_cached(op, &pagevec);
-
 	_leave(" = %d [nr=%u%s]",
 	       ret, *nr_pages, list_empty(pages) ? " empty" : "");
 	return ret;
@@ -806,7 +798,6 @@ int cachefiles_allocate_page(struct fscache_retrieval *op,
 {
 	struct cachefiles_object *object;
 	struct cachefiles_cache *cache;
-	struct pagevec pagevec;
 	int ret;
 
 	object = container_of(op->op.object,
@@ -817,13 +808,10 @@ int cachefiles_allocate_page(struct fscache_retrieval *op,
 	_enter("%p,{%lx},", object, page->index);
 
 	ret = cachefiles_has_space(cache, 0, 1);
-	if (ret == 0) {
-		pagevec_init(&pagevec, 0);
-		pagevec_add(&pagevec, page);
-		fscache_mark_pages_cached(op, &pagevec);
-	} else {
+	if (ret == 0)
+		fscache_mark_page_cached(op, page);
+	else
 		ret = -ENOBUFS;
-	}
 
 	_leave(" = %d", ret);
 	return ret;
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 3f7a59bfa7ad..d7c663cfc923 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -914,6 +914,40 @@ done:
 }
 EXPORT_SYMBOL(__fscache_uncache_page);
 
+/**
+ * fscache_mark_page_cached - Mark a page as being cached
+ * @op: The retrieval op pages are being marked for
+ * @page: The page to be marked
+ *
+ * Mark a netfs page as being cached.  After this is called, the netfs
+ * must call fscache_uncache_page() to remove the mark.
+ */
+void fscache_mark_page_cached(struct fscache_retrieval *op, struct page *page)
+{
+	struct fscache_cookie *cookie = op->op.object->cookie;
+
+#ifdef CONFIG_FSCACHE_STATS
+	atomic_inc(&fscache_n_marks);
+#endif
+
+	_debug("- mark %p{%lx}", page, page->index);
+	if (TestSetPageFsCache(page)) {
+		static bool once_only;
+		if (!once_only) {
+			once_only = true;
+			printk(KERN_WARNING "FS-Cache:"
+			       " Cookie type %s marked page %lx"
+			       " multiple times\n",
+			       cookie->def->name, page->index);
+		}
+	}
+
+	if (cookie->def->mark_page_cached)
+		cookie->def->mark_page_cached(cookie->netfs_data,
+					      op->mapping, page);
+}
+EXPORT_SYMBOL(fscache_mark_page_cached);
+
 /**
  * fscache_mark_pages_cached - Mark pages as being cached
  * @op: The retrieval op pages are being marked for
@@ -925,32 +959,11 @@ EXPORT_SYMBOL(__fscache_uncache_page);
 void fscache_mark_pages_cached(struct fscache_retrieval *op,
 			       struct pagevec *pagevec)
 {
-	struct fscache_cookie *cookie = op->op.object->cookie;
 	unsigned long loop;
 
-#ifdef CONFIG_FSCACHE_STATS
-	atomic_add(pagevec->nr, &fscache_n_marks);
-#endif
-
-	for (loop = 0; loop < pagevec->nr; loop++) {
-		struct page *page = pagevec->pages[loop];
-
-		_debug("- mark %p{%lx}", page, page->index);
-		if (TestSetPageFsCache(page)) {
-			static bool once_only;
-			if (!once_only) {
-				once_only = true;
-				printk(KERN_WARNING "FS-Cache:"
-				       " Cookie type %s marked page %lx"
-				       " multiple times\n",
-				       cookie->def->name, page->index);
-			}
-		}
-	}
+	for (loop = 0; loop < pagevec->nr; loop++)
+		fscache_mark_page_cached(op, pagevec->pages[loop]);
 
-	if (cookie->def->mark_pages_cached)
-		cookie->def->mark_pages_cached(cookie->netfs_data,
-					       op->mapping, pagevec);
 	pagevec_reinit(pagevec);
 }
 EXPORT_SYMBOL(fscache_mark_pages_cached);
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index ce31408b1e47..9879183b55d8 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -504,6 +504,9 @@ extern void fscache_withdraw_cache(struct fscache_cache *cache);
 
 extern void fscache_io_error(struct fscache_cache *cache);
 
+extern void fscache_mark_page_cached(struct fscache_retrieval *op,
+				     struct page *page);
+
 extern void fscache_mark_pages_cached(struct fscache_retrieval *op,
 				      struct pagevec *pagevec);
 
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 9ec20dec3353..f4b6353543bf 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -135,14 +135,14 @@ struct fscache_cookie_def {
 	 */
 	void (*put_context)(void *cookie_netfs_data, void *context);
 
-	/* indicate pages that now have cache metadata retained
-	 * - this function should mark the specified pages as now being cached
-	 * - the pages will have been marked with PG_fscache before this is
+	/* indicate page that now have cache metadata retained
+	 * - this function should mark the specified page as now being cached
+	 * - the page will have been marked with PG_fscache before this is
 	 *   called, so this is optional
 	 */
-	void (*mark_pages_cached)(void *cookie_netfs_data,
-				  struct address_space *mapping,
-				  struct pagevec *cached_pvec);
+	void (*mark_page_cached)(void *cookie_netfs_data,
+				 struct address_space *mapping,
+				 struct page *page);
 
 	/* indicate the cookie is no longer cached
 	 * - this function is called when the backing store currently caching
-- 
cgit v1.2.3-55-g7522


From ef46ed888efb1e8da33be5d33c9b54476289a43b Mon Sep 17 00:00:00 2001
From: David Howells
Date: Thu, 20 Dec 2012 21:52:35 +0000
Subject: FS-Cache: Make cookie relinquishment wait for outstanding reads

Make fscache_relinquish_cookie() log a warning and wait if there are any
outstanding reads left on the cookie it was given.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 fs/fscache/cookie.c           | 18 ++++++++++++++----
 fs/fscache/operation.c        | 10 ++++++++--
 include/linux/fscache-cache.h |  1 +
 3 files changed, 23 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 0666996adf80..66be9eccede0 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -442,22 +442,32 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
 
 	event = retire ? FSCACHE_OBJECT_EV_RETIRE : FSCACHE_OBJECT_EV_RELEASE;
 
+try_again:
 	spin_lock(&cookie->lock);
 
 	/* break links with all the active objects */
 	while (!hlist_empty(&cookie->backing_objects)) {
+		int n_reads;
 		object = hlist_entry(cookie->backing_objects.first,
 				     struct fscache_object,
 				     cookie_link);
 
 		_debug("RELEASE OBJ%x", object->debug_id);
 
-		if (atomic_read(&object->n_reads)) {
+		set_bit(FSCACHE_COOKIE_WAITING_ON_READS, &cookie->flags);
+		n_reads = atomic_read(&object->n_reads);
+		if (n_reads) {
+			int n_ops = object->n_ops;
+			int n_in_progress = object->n_in_progress;
 			spin_unlock(&cookie->lock);
 			printk(KERN_ERR "FS-Cache:"
-			       " Cookie '%s' still has %d outstanding reads\n",
-			       cookie->def->name, atomic_read(&object->n_reads));
-			BUG();
+			       " Cookie '%s' still has %d outstanding reads (%d,%d)\n",
+			       cookie->def->name,
+			       n_reads, n_ops, n_in_progress);
+			wait_on_bit(&cookie->flags, FSCACHE_COOKIE_WAITING_ON_READS,
+				    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			printk("Wait finished\n");
+			goto try_again;
 		}
 
 		/* detach each cache object from the object cookie */
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index 30afdfa7aec7..c857ab824d6e 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -340,8 +340,14 @@ void fscache_put_operation(struct fscache_operation *op)
 
 	object = op->object;
 
-	if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags))
-		atomic_dec(&object->n_reads);
+	if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags)) {
+		if (atomic_dec_and_test(&object->n_reads)) {
+			clear_bit(FSCACHE_COOKIE_WAITING_ON_READS,
+				  &object->cookie->flags);
+			wake_up_bit(&object->cookie->flags,
+				    FSCACHE_COOKIE_WAITING_ON_READS);
+		}
+	}
 
 	/* now... we may get called with the object spinlock held, so we
 	 * complete the cleanup here only if we can immediately acquire the
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 9879183b55d8..e3d6d939d959 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -301,6 +301,7 @@ struct fscache_cookie {
 #define FSCACHE_COOKIE_PENDING_FILL	3	/* T if pending initial fill on object */
 #define FSCACHE_COOKIE_FILLING		4	/* T if filling object incrementally */
 #define FSCACHE_COOKIE_UNAVAILABLE	5	/* T if cookie is unavailable (error, etc) */
+#define FSCACHE_COOKIE_WAITING_ON_READS	6	/* T if cookie is waiting on reads */
 };
 
 extern struct fscache_cookie fscache_fsdef_index;
-- 
cgit v1.2.3-55-g7522


From 9f10523f891928330b7529da54c1a3cc65180b1a Mon Sep 17 00:00:00 2001
From: David Howells
Date: Thu, 20 Dec 2012 21:52:35 +0000
Subject: FS-Cache: Fix operation state management and accounting

Fix the state management of internal fscache operations and the accounting of
what operations are in what states.

This is done by:

 (1) Give struct fscache_operation a enum variable that directly represents the
     state it's currently in, rather than spreading this knowledge over a bunch
     of flags, who's processing the operation at the moment and whether it is
     queued or not.

     This makes it easier to write assertions to check the state at various
     points and to prevent invalid state transitions.

 (2) Add an 'operation complete' state and supply a function to indicate the
     completion of an operation (fscache_op_complete()) and make things call
     it.  The final call to fscache_put_operation() can then check that an op
     in the appropriate state (complete or cancelled).

 (3) Adjust the use of object->n_ops, ->n_in_progress, ->n_exclusive to better
     govern the state of an object:

	(a) The ->n_ops is now the number of extant operations on the object
	    and is now decremented by fscache_put_operation() only.

	(b) The ->n_in_progress is simply the number of objects that have been
	    taken off of the object's pending queue for the purposes of being
	    run.  This is decremented by fscache_op_complete() only.

	(c) The ->n_exclusive is the number of exclusive ops that have been
	    submitted and queued or are in progress.  It is decremented by
	    fscache_op_complete() and by fscache_cancel_op().

     fscache_put_operation() and fscache_operation_gc() now no longer try to
     clean up ->n_exclusive and ->n_in_progress.  That was leading to double
     decrements against fscache_cancel_op().

     fscache_cancel_op() now no longer decrements ->n_ops.  That was leading to
     double decrements against fscache_put_operation().

     fscache_submit_exclusive_op() now decides whether it has to queue an op
     based on ->n_in_progress being > 0 rather than ->n_ops > 0 as the latter
     will persist in being true even after all preceding operations have been
     cancelled or completed.  Furthermore, if an object is active and there are
     runnable ops against it, there must be at least one op running.

 (4) Add a remaining-pages counter (n_pages) to struct fscache_retrieval and
     provide a function to record completion of the pages as they complete.

     When n_pages reaches 0, the operation is deemed to be complete and
     fscache_op_complete() is called.

     Add calls to fscache_retrieval_complete() anywhere we've finished with a
     page we've been given to read or allocate for.  This includes places where
     we just return pages to the netfs for reading from the server and where
     accessing the cache fails and we discard the proposed netfs page.

The bugs in the unfixed state management manifest themselves as oopses like the
following where the operation completion gets out of sync with return of the
cookie by the netfs.  This is possible because the cache unlocks and returns
all the netfs pages before recording its completion - which means that there's
nothing to stop the netfs discarding them and returning the cookie.


FS-Cache: Cookie 'NFS.fh' still has outstanding reads
------------[ cut here ]------------
kernel BUG at fs/fscache/cookie.c:519!
invalid opcode: 0000 [#1] SMP
CPU 1
Modules linked in: cachefiles nfs fscache auth_rpcgss nfs_acl lockd sunrpc

Pid: 400, comm: kswapd0 Not tainted 3.1.0-rc7-fsdevel+ #1090                  /DG965RY
RIP: 0010:[<ffffffffa007050a>]  [<ffffffffa007050a>] __fscache_relinquish_cookie+0x170/0x343 [fscache]
RSP: 0018:ffff8800368cfb00  EFLAGS: 00010282
RAX: 000000000000003c RBX: ffff880023cc8790 RCX: 0000000000000000
RDX: 0000000000002f2e RSI: 0000000000000001 RDI: ffffffff813ab86c
RBP: ffff8800368cfb50 R08: 0000000000000002 R09: 0000000000000000
R10: ffff88003a1b7890 R11: ffff88001df6e488 R12: ffff880023d8ed98
R13: ffff880023cc8798 R14: 0000000000000004 R15: ffff88003b8bf370
FS:  0000000000000000(0000) GS:ffff88003bd00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00000000008ba008 CR3: 0000000023d93000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process kswapd0 (pid: 400, threadinfo ffff8800368ce000, task ffff88003b8bf040)
Stack:
 ffff88003b8bf040 ffff88001df6e528 ffff88001df6e528 ffffffffa00b46b0
 ffff88003b8bf040 ffff88001df6e488 ffff88001df6e620 ffffffffa00b46b0
 ffff88001ebd04c8 0000000000000004 ffff8800368cfb70 ffffffffa00b2c91
Call Trace:
 [<ffffffffa00b2c91>] nfs_fscache_release_inode_cookie+0x3b/0x47 [nfs]
 [<ffffffffa008f25f>] nfs_clear_inode+0x3c/0x41 [nfs]
 [<ffffffffa0090df1>] nfs4_evict_inode+0x2f/0x33 [nfs]
 [<ffffffff810d8d47>] evict+0xa1/0x15c
 [<ffffffff810d8e2e>] dispose_list+0x2c/0x38
 [<ffffffff810d9ebd>] prune_icache_sb+0x28c/0x29b
 [<ffffffff810c56b7>] prune_super+0xd5/0x140
 [<ffffffff8109b615>] shrink_slab+0x102/0x1ab
 [<ffffffff8109d690>] balance_pgdat+0x2f2/0x595
 [<ffffffff8103e009>] ? process_timeout+0xb/0xb
 [<ffffffff8109dba3>] kswapd+0x270/0x289
 [<ffffffff8104c5ea>] ? __init_waitqueue_head+0x46/0x46
 [<ffffffff8109d933>] ? balance_pgdat+0x595/0x595
 [<ffffffff8104bf7a>] kthread+0x7f/0x87
 [<ffffffff813ad6b4>] kernel_thread_helper+0x4/0x10
 [<ffffffff81026b98>] ? finish_task_switch+0x45/0xc0
 [<ffffffff813abcdd>] ? retint_restore_args+0xe/0xe
 [<ffffffff8104befb>] ? __init_kthread_worker+0x53/0x53
 [<ffffffff813ad6b0>] ? gs_change+0xb/0xb

Signed-off-by: David Howells <dhowells@redhat.com>
---
 Documentation/filesystems/caching/backend-api.txt | 26 ++++++-
 Documentation/filesystems/caching/operations.txt  |  2 +-
 fs/cachefiles/rdwr.c                              | 31 ++++++--
 fs/fscache/object.c                               |  2 -
 fs/fscache/operation.c                            | 91 +++++++++++++++--------
 fs/fscache/page.c                                 | 25 ++++++-
 include/linux/fscache-cache.h                     | 37 +++++++--
 7 files changed, 164 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/caching/backend-api.txt b/Documentation/filesystems/caching/backend-api.txt
index 382d52cdaf2d..f4769b9399df 100644
--- a/Documentation/filesystems/caching/backend-api.txt
+++ b/Documentation/filesystems/caching/backend-api.txt
@@ -419,7 +419,10 @@ performed on the denizens of the cache.  These are held in a structure of type:
 
      If an I/O error occurs, fscache_io_error() should be called and -ENOBUFS
      returned if possible or fscache_end_io() called with a suitable error
-     code..
+     code.
+
+     fscache_put_retrieval() should be called after a page or pages are dealt
+     with.  This will complete the operation when all pages are dealt with.
 
 
  (*) Request pages be read from cache [mandatory]:
@@ -526,6 +529,27 @@ FS-Cache provides some utilities that a cache backend may make use of:
      error value should be 0 if successful and an error otherwise.
 
 
+ (*) Record that one or more pages being retrieved or allocated have been dealt
+     with:
+
+	void fscache_retrieval_complete(struct fscache_retrieval *op,
+					int n_pages);
+
+     This is called to record the fact that one or more pages have been dealt
+     with and are no longer the concern of this operation.  When the number of
+     pages remaining in the operation reaches 0, the operation will be
+     completed.
+
+
+ (*) Record operation completion:
+
+	void fscache_op_complete(struct fscache_operation *op);
+
+     This is called to record the completion of an operation.  This deducts
+     this operation from the parent object's run state, potentially permitting
+     one or more pending operations to start running.
+
+
  (*) Set highest store limit:
 
 	void fscache_set_store_limit(struct fscache_object *object,
diff --git a/Documentation/filesystems/caching/operations.txt b/Documentation/filesystems/caching/operations.txt
index b6b070c57cbf..bee2a5f93d60 100644
--- a/Documentation/filesystems/caching/operations.txt
+++ b/Documentation/filesystems/caching/operations.txt
@@ -174,7 +174,7 @@ Operations are used through the following procedure:
      necessary (the object might have died whilst the thread was waiting).
 
      When it has finished doing its processing, it should call
-     fscache_put_operation() on it.
+     fscache_op_complete() and fscache_put_operation() on it.
 
  (4) The operation holds an effective lock upon the object, preventing other
      exclusive ops conflicting until it is released.  The operation can be
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index bf123d9c3206..93a0815e0498 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -197,6 +197,7 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
 
 		fscache_end_io(op, monitor->netfs_page, error);
 		page_cache_release(monitor->netfs_page);
+		fscache_retrieval_complete(op, 1);
 		fscache_put_retrieval(op);
 		kfree(monitor);
 
@@ -339,6 +340,7 @@ backing_page_already_uptodate:
 
 	copy_highpage(netpage, backpage);
 	fscache_end_io(op, netpage, 0);
+	fscache_retrieval_complete(op, 1);
 
 success:
 	_debug("success");
@@ -360,6 +362,7 @@ read_error:
 		goto out;
 io_error:
 	cachefiles_io_error_obj(object, "Page read error on backing file");
+	fscache_retrieval_complete(op, 1);
 	ret = -ENOBUFS;
 	goto out;
 
@@ -369,6 +372,7 @@ nomem_monitor:
 	fscache_put_retrieval(monitor->op);
 	kfree(monitor);
 nomem:
+	fscache_retrieval_complete(op, 1);
 	_leave(" = -ENOMEM");
 	return -ENOMEM;
 }
@@ -407,7 +411,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 	_enter("{%p},{%lx},,,", object, page->index);
 
 	if (!object->backer)
-		return -ENOBUFS;
+		goto enobufs;
 
 	inode = object->backer->d_inode;
 	ASSERT(S_ISREG(inode->i_mode));
@@ -416,7 +420,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 
 	/* calculate the shift required to use bmap */
 	if (inode->i_sb->s_blocksize > PAGE_SIZE)
-		return -ENOBUFS;
+		goto enobufs;
 
 	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
 
@@ -448,13 +452,19 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 	} else if (cachefiles_has_space(cache, 0, 1) == 0) {
 		/* there's space in the cache we can use */
 		fscache_mark_page_cached(op, page);
+		fscache_retrieval_complete(op, 1);
 		ret = -ENODATA;
 	} else {
-		ret = -ENOBUFS;
+		goto enobufs;
 	}
 
 	_leave(" = %d", ret);
 	return ret;
+
+enobufs:
+	fscache_retrieval_complete(op, 1);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
 }
 
 /*
@@ -632,6 +642,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 
 		/* the netpage is unlocked and marked up to date here */
 		fscache_end_io(op, netpage, 0);
+		fscache_retrieval_complete(op, 1);
 		page_cache_release(netpage);
 		netpage = NULL;
 		continue;
@@ -659,6 +670,7 @@ out:
 	list_for_each_entry_safe(netpage, _n, list, lru) {
 		list_del(&netpage->lru);
 		page_cache_release(netpage);
+		fscache_retrieval_complete(op, 1);
 	}
 
 	_leave(" = %d", ret);
@@ -707,7 +719,7 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 	       *nr_pages);
 
 	if (!object->backer)
-		return -ENOBUFS;
+		goto all_enobufs;
 
 	space = 1;
 	if (cachefiles_has_space(cache, 0, *nr_pages) < 0)
@@ -720,7 +732,7 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 
 	/* calculate the shift required to use bmap */
 	if (inode->i_sb->s_blocksize > PAGE_SIZE)
-		return -ENOBUFS;
+		goto all_enobufs;
 
 	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
 
@@ -760,7 +772,10 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 			nrbackpages++;
 		} else if (space && pagevec_add(&pagevec, page) == 0) {
 			fscache_mark_pages_cached(op, &pagevec);
+			fscache_retrieval_complete(op, 1);
 			ret = -ENODATA;
+		} else {
+			fscache_retrieval_complete(op, 1);
 		}
 	}
 
@@ -781,6 +796,10 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 	_leave(" = %d [nr=%u%s]",
 	       ret, *nr_pages, list_empty(pages) ? " empty" : "");
 	return ret;
+
+all_enobufs:
+	fscache_retrieval_complete(op, *nr_pages);
+	return -ENOBUFS;
 }
 
 /*
@@ -815,6 +834,7 @@ int cachefiles_allocate_page(struct fscache_retrieval *op,
 	else
 		ret = -ENOBUFS;
 
+	fscache_retrieval_complete(op, 1);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -864,6 +884,7 @@ int cachefiles_allocate_pages(struct fscache_retrieval *op,
 		ret = -ENOBUFS;
 	}
 
+	fscache_retrieval_complete(op, *nr_pages);
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index b6b897c550ac..773bc798a416 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -587,8 +587,6 @@ static void fscache_object_available(struct fscache_object *object)
 	if (object->n_in_progress == 0) {
 		if (object->n_ops > 0) {
 			ASSERTCMP(object->n_ops, >=, object->n_obj_ops);
-			ASSERTIF(object->n_ops > object->n_obj_ops,
-				 !list_empty(&object->pending_ops));
 			fscache_start_operations(object);
 		} else {
 			ASSERT(list_empty(&object->pending_ops));
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index c857ab824d6e..748f9553c2cb 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -37,6 +37,7 @@ void fscache_enqueue_operation(struct fscache_operation *op)
 	ASSERT(op->processor != NULL);
 	ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE);
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
 
 	fscache_stat(&fscache_n_op_enqueue);
 	switch (op->flags & FSCACHE_OP_TYPE) {
@@ -64,6 +65,9 @@ EXPORT_SYMBOL(fscache_enqueue_operation);
 static void fscache_run_op(struct fscache_object *object,
 			   struct fscache_operation *op)
 {
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
+
+	op->state = FSCACHE_OP_ST_IN_PROGRESS;
 	object->n_in_progress++;
 	if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
 		wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
@@ -80,22 +84,23 @@ static void fscache_run_op(struct fscache_object *object,
 int fscache_submit_exclusive_op(struct fscache_object *object,
 				struct fscache_operation *op)
 {
-	int ret;
-
 	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
 
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
 	spin_lock(&object->lock);
 	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
 	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
 	ASSERT(list_empty(&op->pend_link));
 
-	ret = -ENOBUFS;
+	op->state = FSCACHE_OP_ST_PENDING;
 	if (fscache_object_is_active(object)) {
 		op->object = object;
 		object->n_ops++;
 		object->n_exclusive++;	/* reads and writes must wait */
 
-		if (object->n_ops > 1) {
+		if (object->n_in_progress > 0) {
 			atomic_inc(&op->usage);
 			list_add_tail(&op->pend_link, &object->pending_ops);
 			fscache_stat(&fscache_n_op_pend);
@@ -111,7 +116,6 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 
 		/* need to issue a new write op after this */
 		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
-		ret = 0;
 	} else if (object->state == FSCACHE_OBJECT_CREATING) {
 		op->object = object;
 		object->n_ops++;
@@ -119,14 +123,13 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 		atomic_inc(&op->usage);
 		list_add_tail(&op->pend_link, &object->pending_ops);
 		fscache_stat(&fscache_n_op_pend);
-		ret = 0;
 	} else {
 		/* not allowed to submit ops in any other state */
 		BUG();
 	}
 
 	spin_unlock(&object->lock);
-	return ret;
+	return 0;
 }
 
 /*
@@ -186,6 +189,7 @@ int fscache_submit_op(struct fscache_object *object,
 	_enter("{OBJ%x OP%x},{%u}",
 	       object->debug_id, op->debug_id, atomic_read(&op->usage));
 
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
 
 	spin_lock(&object->lock);
@@ -196,6 +200,7 @@ int fscache_submit_op(struct fscache_object *object,
 	ostate = object->state;
 	smp_rmb();
 
+	op->state = FSCACHE_OP_ST_PENDING;
 	if (fscache_object_is_active(object)) {
 		op->object = object;
 		object->n_ops++;
@@ -225,12 +230,15 @@ int fscache_submit_op(struct fscache_object *object,
 		   object->state == FSCACHE_OBJECT_LC_DYING ||
 		   object->state == FSCACHE_OBJECT_WITHDRAWING) {
 		fscache_stat(&fscache_n_op_rejected);
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
 		fscache_report_unexpected_submission(object, op, ostate);
 		ASSERT(!fscache_object_is_active(object));
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	} else {
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	}
 
@@ -290,13 +298,18 @@ int fscache_cancel_op(struct fscache_operation *op)
 
 	_enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id);
 
+	ASSERTCMP(op->state, >=, FSCACHE_OP_ST_PENDING);
+	ASSERTCMP(op->state, !=, FSCACHE_OP_ST_CANCELLED);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
 	spin_lock(&object->lock);
 
 	ret = -EBUSY;
-	if (!list_empty(&op->pend_link)) {
+	if (op->state == FSCACHE_OP_ST_PENDING) {
+		ASSERT(!list_empty(&op->pend_link));
 		fscache_stat(&fscache_n_op_cancelled);
 		list_del_init(&op->pend_link);
-		object->n_ops--;
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
 			object->n_exclusive--;
 		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
@@ -310,6 +323,37 @@ int fscache_cancel_op(struct fscache_operation *op)
 	return ret;
 }
 
+/*
+ * Record the completion of an in-progress operation.
+ */
+void fscache_op_complete(struct fscache_operation *op)
+{
+	struct fscache_object *object = op->object;
+
+	_enter("OBJ%x", object->debug_id);
+
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
+	ASSERTCMP(object->n_in_progress, >, 0);
+	ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags),
+		    object->n_exclusive, >, 0);
+	ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags),
+		    object->n_in_progress, ==, 1);
+
+	spin_lock(&object->lock);
+
+	op->state = FSCACHE_OP_ST_COMPLETE;
+
+	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+		object->n_exclusive--;
+	object->n_in_progress--;
+	if (object->n_in_progress == 0)
+		fscache_start_operations(object);
+
+	spin_unlock(&object->lock);
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_op_complete);
+
 /*
  * release an operation
  * - queues pending ops if this is the last in-progress op
@@ -328,8 +372,9 @@ void fscache_put_operation(struct fscache_operation *op)
 		return;
 
 	_debug("PUT OP");
-	if (test_and_set_bit(FSCACHE_OP_DEAD, &op->flags))
-		BUG();
+	ASSERTIFCMP(op->state != FSCACHE_OP_ST_COMPLETE,
+		    op->state, ==, FSCACHE_OP_ST_CANCELLED);
+	op->state = FSCACHE_OP_ST_DEAD;
 
 	fscache_stat(&fscache_n_op_release);
 
@@ -365,16 +410,6 @@ void fscache_put_operation(struct fscache_operation *op)
 		return;
 	}
 
-	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
-		ASSERTCMP(object->n_exclusive, >, 0);
-		object->n_exclusive--;
-	}
-
-	ASSERTCMP(object->n_in_progress, >, 0);
-	object->n_in_progress--;
-	if (object->n_in_progress == 0)
-		fscache_start_operations(object);
-
 	ASSERTCMP(object->n_ops, >, 0);
 	object->n_ops--;
 	if (object->n_ops == 0)
@@ -413,23 +448,14 @@ void fscache_operation_gc(struct work_struct *work)
 		spin_unlock(&cache->op_gc_list_lock);
 
 		object = op->object;
+		spin_lock(&object->lock);
 
 		_debug("GC DEFERRED REL OBJ%x OP%x",
 		       object->debug_id, op->debug_id);
 		fscache_stat(&fscache_n_op_gc);
 
 		ASSERTCMP(atomic_read(&op->usage), ==, 0);
-
-		spin_lock(&object->lock);
-		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
-			ASSERTCMP(object->n_exclusive, >, 0);
-			object->n_exclusive--;
-		}
-
-		ASSERTCMP(object->n_in_progress, >, 0);
-		object->n_in_progress--;
-		if (object->n_in_progress == 0)
-			fscache_start_operations(object);
+		ASSERTCMP(op->state, ==, FSCACHE_OP_ST_DEAD);
 
 		ASSERTCMP(object->n_ops, >, 0);
 		object->n_ops--;
@@ -437,6 +463,7 @@ void fscache_operation_gc(struct work_struct *work)
 			fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
 
 		spin_unlock(&object->lock);
+		kfree(op);
 
 	} while (count++ < 20);
 
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 248a12e22532..b38b13d2a555 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -162,6 +162,7 @@ static void fscache_attr_changed_op(struct fscache_operation *op)
 			fscache_abort_object(object);
 	}
 
+	fscache_op_complete(op);
 	_leave("");
 }
 
@@ -223,6 +224,8 @@ static void fscache_release_retrieval_op(struct fscache_operation *_op)
 
 	_enter("{OP%x}", op->op.debug_id);
 
+	ASSERTCMP(op->n_pages, ==, 0);
+
 	fscache_hist(fscache_retrieval_histogram, op->start_time);
 	if (op->context)
 		fscache_put_context(op->op.object->cookie, op->context);
@@ -320,6 +323,11 @@ static int fscache_wait_for_retrieval_activation(struct fscache_object *object,
 	_debug("<<< GO");
 
 check_if_dead:
+	if (op->op.state == FSCACHE_OP_ST_CANCELLED) {
+		fscache_stat(stat_object_dead);
+		_leave(" = -ENOBUFS [cancelled]");
+		return -ENOBUFS;
+	}
 	if (unlikely(fscache_object_is_dead(object))) {
 		fscache_stat(stat_object_dead);
 		return -ENOBUFS;
@@ -364,6 +372,7 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 		_leave(" = -ENOMEM");
 		return -ENOMEM;
 	}
+	op->n_pages = 1;
 
 	spin_lock(&cookie->lock);
 
@@ -375,10 +384,10 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 	ASSERTCMP(object->state, >, FSCACHE_OBJECT_LOOKING_UP);
 
 	atomic_inc(&object->n_reads);
-	set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
+	__set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
 
 	if (fscache_submit_op(object, &op->op) < 0)
-		goto nobufs_unlock;
+		goto nobufs_unlock_dec;
 	spin_unlock(&cookie->lock);
 
 	fscache_stat(&fscache_n_retrieval_ops);
@@ -425,6 +434,8 @@ error:
 	_leave(" = %d", ret);
 	return ret;
 
+nobufs_unlock_dec:
+	atomic_dec(&object->n_reads);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
 	kfree(op);
@@ -482,6 +493,7 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 	op = fscache_alloc_retrieval(mapping, end_io_func, context);
 	if (!op)
 		return -ENOMEM;
+	op->n_pages = *nr_pages;
 
 	spin_lock(&cookie->lock);
 
@@ -491,10 +503,10 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 			     struct fscache_object, cookie_link);
 
 	atomic_inc(&object->n_reads);
-	set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
+	__set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
 
 	if (fscache_submit_op(object, &op->op) < 0)
-		goto nobufs_unlock;
+		goto nobufs_unlock_dec;
 	spin_unlock(&cookie->lock);
 
 	fscache_stat(&fscache_n_retrieval_ops);
@@ -541,6 +553,8 @@ error:
 	_leave(" = %d", ret);
 	return ret;
 
+nobufs_unlock_dec:
+	atomic_dec(&object->n_reads);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
 	kfree(op);
@@ -583,6 +597,7 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 	op = fscache_alloc_retrieval(page->mapping, NULL, NULL);
 	if (!op)
 		return -ENOMEM;
+	op->n_pages = 1;
 
 	spin_lock(&cookie->lock);
 
@@ -696,6 +711,7 @@ static void fscache_write_op(struct fscache_operation *_op)
 	fscache_end_page_write(object, page);
 	if (ret < 0) {
 		fscache_abort_object(object);
+		fscache_op_complete(&op->op);
 	} else {
 		fscache_enqueue_operation(&op->op);
 	}
@@ -710,6 +726,7 @@ superseded:
 	spin_unlock(&cookie->stores_lock);
 	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
 	spin_unlock(&object->lock);
+	fscache_op_complete(&op->op);
 	_leave("");
 }
 
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index e3d6d939d959..f5facd1d333f 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -75,6 +75,16 @@ extern wait_queue_head_t fscache_cache_cleared_wq;
 typedef void (*fscache_operation_release_t)(struct fscache_operation *op);
 typedef void (*fscache_operation_processor_t)(struct fscache_operation *op);
 
+enum fscache_operation_state {
+	FSCACHE_OP_ST_BLANK,		/* Op is not yet submitted */
+	FSCACHE_OP_ST_INITIALISED,	/* Op is initialised */
+	FSCACHE_OP_ST_PENDING,		/* Op is blocked from running */
+	FSCACHE_OP_ST_IN_PROGRESS,	/* Op is in progress */
+	FSCACHE_OP_ST_COMPLETE,		/* Op is complete */
+	FSCACHE_OP_ST_CANCELLED,	/* Op has been cancelled */
+	FSCACHE_OP_ST_DEAD		/* Op is now dead */
+};
+
 struct fscache_operation {
 	struct work_struct	work;		/* record for async ops */
 	struct list_head	pend_link;	/* link in object->pending_ops */
@@ -86,10 +96,10 @@ struct fscache_operation {
 #define FSCACHE_OP_MYTHREAD	0x0002	/* - processing is done be issuing thread, not pool */
 #define FSCACHE_OP_WAITING	4	/* cleared when op is woken */
 #define FSCACHE_OP_EXCLUSIVE	5	/* exclusive op, other ops must wait */
-#define FSCACHE_OP_DEAD		6	/* op is now dead */
-#define FSCACHE_OP_DEC_READ_CNT	7	/* decrement object->n_reads on destruction */
-#define FSCACHE_OP_KEEP_FLAGS	0xc0	/* flags to keep when repurposing an op */
+#define FSCACHE_OP_DEC_READ_CNT	6	/* decrement object->n_reads on destruction */
+#define FSCACHE_OP_KEEP_FLAGS	0x0070	/* flags to keep when repurposing an op */
 
+	enum fscache_operation_state state;
 	atomic_t		usage;
 	unsigned		debug_id;	/* debugging ID */
 
@@ -106,6 +116,7 @@ extern atomic_t fscache_op_debug_id;
 extern void fscache_op_work_func(struct work_struct *work);
 
 extern void fscache_enqueue_operation(struct fscache_operation *);
+extern void fscache_op_complete(struct fscache_operation *);
 extern void fscache_put_operation(struct fscache_operation *);
 
 /**
@@ -122,6 +133,7 @@ static inline void fscache_operation_init(struct fscache_operation *op,
 {
 	INIT_WORK(&op->work, fscache_op_work_func);
 	atomic_set(&op->usage, 1);
+	op->state = FSCACHE_OP_ST_INITIALISED;
 	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
 	op->processor = processor;
 	op->release = release;
@@ -138,6 +150,7 @@ struct fscache_retrieval {
 	void			*context;	/* netfs read context (pinned) */
 	struct list_head	to_do;		/* list of things to be done by the backend */
 	unsigned long		start_time;	/* time at which retrieval started */
+	unsigned		n_pages;	/* number of pages to be retrieved */
 };
 
 typedef int (*fscache_page_retrieval_func_t)(struct fscache_retrieval *op,
@@ -173,9 +186,23 @@ static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op)
 	fscache_enqueue_operation(&op->op);
 }
 
+/**
+ * fscache_retrieval_complete - Record (partial) completion of a retrieval
+ * @op: The retrieval operation affected
+ * @n_pages: The number of pages to account for
+ */
+static inline void fscache_retrieval_complete(struct fscache_retrieval *op,
+					      int n_pages)
+{
+	op->n_pages -= n_pages;
+	if (op->n_pages <= 0)
+		fscache_op_complete(&op->op);
+}
+
 /**
  * fscache_put_retrieval - Drop a reference to a retrieval operation
  * @op: The retrieval operation affected
+ * @n_pages: The number of pages to account for
  *
  * Drop a reference to a retrieval operation.
  */
@@ -333,10 +360,10 @@ struct fscache_object {
 
 	int			debug_id;	/* debugging ID */
 	int			n_children;	/* number of child objects */
-	int			n_ops;		/* number of ops outstanding on object */
+	int			n_ops;		/* number of extant ops on object */
 	int			n_obj_ops;	/* number of object ops outstanding on object */
 	int			n_in_progress;	/* number of ops in progress */
-	int			n_exclusive;	/* number of exclusive ops queued */
+	int			n_exclusive;	/* number of exclusive ops queued or in progress */
 	atomic_t		n_reads;	/* number of read ops in progress */
 	spinlock_t		lock;		/* state and operations lock */
 
-- 
cgit v1.2.3-55-g7522


From ef778e7ae67cd426c30cad43378b908f5eb0bad5 Mon Sep 17 00:00:00 2001
From: David Howells
Date: Thu, 20 Dec 2012 21:52:36 +0000
Subject: FS-Cache: Provide proper invalidation

Provide a proper invalidation method rather than relying on the netfs retiring
the cookie it has and getting a new one.  The problem with this is that isn't
easy for the netfs to make sure that it has completed/cancelled all its
outstanding storage and retrieval operations on the cookie it is retiring.

Instead, have the cache provide an invalidation method that will cancel or wait
for all currently outstanding operations before invalidating the cache, and
will cause new operations to queue up behind that.  Whilst invalidation is in
progress, some requests will be rejected until the cache can stack a barrier on
the operation queue to cause new operations to be deferred behind it.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 Documentation/filesystems/caching/backend-api.txt | 12 ++++
 Documentation/filesystems/caching/netfs-api.txt   | 46 ++++++++++++---
 Documentation/filesystems/caching/object.txt      | 23 +++++---
 fs/fscache/cookie.c                               | 60 +++++++++++++++++++
 fs/fscache/internal.h                             | 10 ++++
 fs/fscache/object.c                               | 72 +++++++++++++++++++++++
 fs/fscache/operation.c                            | 32 ++++++++++
 fs/fscache/page.c                                 | 51 ++++++++++++++++
 fs/fscache/stats.c                                | 11 +++-
 include/linux/fscache-cache.h                     |  8 ++-
 include/linux/fscache.h                           | 38 ++++++++++++
 11 files changed, 345 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/caching/backend-api.txt b/Documentation/filesystems/caching/backend-api.txt
index f4769b9399df..d78bab9622c6 100644
--- a/Documentation/filesystems/caching/backend-api.txt
+++ b/Documentation/filesystems/caching/backend-api.txt
@@ -308,6 +308,18 @@ performed on the denizens of the cache.  These are held in a structure of type:
      obtained by calling object->cookie->def->get_aux()/get_attr().
 
 
+ (*) Invalidate data object [mandatory]:
+
+	int (*invalidate_object)(struct fscache_operation *op)
+
+     This is called to invalidate a data object (as pointed to by op->object).
+     All the data stored for this object should be discarded and an
+     attr_changed operation should be performed.  The caller will follow up
+     with an object update operation.
+
+     fscache_op_complete() must be called on op before returning.
+
+
  (*) Discard object [mandatory]:
 
 	void (*drop_object)(struct fscache_object *object)
diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt
index 7cc6bf2871eb..97e6c0ecc5ef 100644
--- a/Documentation/filesystems/caching/netfs-api.txt
+++ b/Documentation/filesystems/caching/netfs-api.txt
@@ -35,8 +35,9 @@ This document contains the following sections:
 	(12) Index and data file update
 	(13) Miscellaneous cookie operations
 	(14) Cookie unregistration
-	(15) Index and data file invalidation
-	(16) FS-Cache specific page flags.
+	(15) Index invalidation
+	(16) Data file invalidation
+	(17) FS-Cache specific page flags.
 
 
 =============================
@@ -767,13 +768,42 @@ the cookies for "child" indices, objects and pages have been relinquished
 first.
 
 
-================================
-INDEX AND DATA FILE INVALIDATION
-================================
+==================
+INDEX INVALIDATION
+==================
+
+There is no direct way to invalidate an index subtree.  To do this, the caller
+should relinquish and retire the cookie they have, and then acquire a new one.
+
+
+======================
+DATA FILE INVALIDATION
+======================
+
+Sometimes it will be necessary to invalidate an object that contains data.
+Typically this will be necessary when the server tells the netfs of a foreign
+change - at which point the netfs has to throw away all the state it had for an
+inode and reload from the server.
+
+To indicate that a cache object should be invalidated, the following function
+can be called:
+
+	void fscache_invalidate(struct fscache_cookie *cookie);
+
+This can be called with spinlocks held as it defers the work to a thread pool.
+All extant storage, retrieval and attribute change ops at this point are
+cancelled and discarded.  Some future operations will be rejected until the
+cache has had a chance to insert a barrier in the operations queue.  After
+that, operations will be queued again behind the invalidation operation.
+
+The invalidation operation will perform an attribute change operation and an
+auxiliary data update operation as it is very likely these will have changed.
+
+Using the following function, the netfs can wait for the invalidation operation
+to have reached a point at which it can start submitting ordinary operations
+once again:
 
-There is no direct way to invalidate an index subtree or a data file.  To do
-this, the caller should relinquish and retire the cookie they have, and then
-acquire a new one.
+	void fscache_wait_on_invalidate(struct fscache_cookie *cookie);
 
 
 ===========================
diff --git a/Documentation/filesystems/caching/object.txt b/Documentation/filesystems/caching/object.txt
index 58313348da87..100ff41127e4 100644
--- a/Documentation/filesystems/caching/object.txt
+++ b/Documentation/filesystems/caching/object.txt
@@ -216,7 +216,14 @@ servicing netfs requests:
      The normal running state.  In this state, requests the netfs makes will be
      passed on to the cache.
 
- (6) State FSCACHE_OBJECT_UPDATING.
+ (6) State FSCACHE_OBJECT_INVALIDATING.
+
+     The object is undergoing invalidation.  When the state comes here, it
+     discards all pending read, write and attribute change operations as it is
+     going to clear out the cache entirely and reinitialise it.  It will then
+     continue to the FSCACHE_OBJECT_UPDATING state.
+
+ (7) State FSCACHE_OBJECT_UPDATING.
 
      The state machine comes here to update the object in the cache from the
      netfs's records.  This involves updating the auxiliary data that is used
@@ -225,13 +232,13 @@ servicing netfs requests:
 And there are terminal states in which an object cleans itself up, deallocates
 memory and potentially deletes stuff from disk:
 
- (7) State FSCACHE_OBJECT_LC_DYING.
+ (8) State FSCACHE_OBJECT_LC_DYING.
 
      The object comes here if it is dying because of a lookup or creation
      error.  This would be due to a disk error or system error of some sort.
      Temporary data is cleaned up, and the parent is released.
 
- (8) State FSCACHE_OBJECT_DYING.
+ (9) State FSCACHE_OBJECT_DYING.
 
      The object comes here if it is dying due to an error, because its parent
      cookie has been relinquished by the netfs or because the cache is being
@@ -241,27 +248,27 @@ memory and potentially deletes stuff from disk:
      can destroy themselves.  This object waits for all its children to go away
      before advancing to the next state.
 
- (9) State FSCACHE_OBJECT_ABORT_INIT.
+(10) State FSCACHE_OBJECT_ABORT_INIT.
 
      The object comes to this state if it was waiting on its parent in
      FSCACHE_OBJECT_INIT, but its parent died.  The object will destroy itself
      so that the parent may proceed from the FSCACHE_OBJECT_DYING state.
 
-(10) State FSCACHE_OBJECT_RELEASING.
-(11) State FSCACHE_OBJECT_RECYCLING.
+(11) State FSCACHE_OBJECT_RELEASING.
+(12) State FSCACHE_OBJECT_RECYCLING.
 
      The object comes to one of these two states when dying once it is rid of
      all its children, if it is dying because the netfs relinquished its
      cookie.  In the first state, the cached data is expected to persist, and
      in the second it will be deleted.
 
-(12) State FSCACHE_OBJECT_WITHDRAWING.
+(13) State FSCACHE_OBJECT_WITHDRAWING.
 
      The object transits to this state if the cache decides it wants to
      withdraw the object from service, perhaps to make space, but also due to
      error or just because the whole cache is being withdrawn.
 
-(13) State FSCACHE_OBJECT_DEAD.
+(14) State FSCACHE_OBJECT_DEAD.
 
      The object transits to this state when the in-memory object record is
      ready to be deleted.  The object processor shouldn't ever see an object in
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 66be9eccede0..8dcb114758e3 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -369,6 +369,66 @@ cant_attach_object:
 	return ret;
 }
 
+/*
+ * Invalidate an object.  Callable with spinlocks held.
+ */
+void __fscache_invalidate(struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+
+	_enter("{%s}", cookie->def->name);
+
+	fscache_stat(&fscache_n_invalidates);
+
+	/* Only permit invalidation of data files.  Invalidating an index will
+	 * require the caller to release all its attachments to the tree rooted
+	 * there, and if it's doing that, it may as well just retire the
+	 * cookie.
+	 */
+	ASSERTCMP(cookie->def->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE);
+
+	/* We will be updating the cookie too. */
+	BUG_ON(!cookie->def->get_aux);
+
+	/* If there's an object, we tell the object state machine to handle the
+	 * invalidation on our behalf, otherwise there's nothing to do.
+	 */
+	if (!hlist_empty(&cookie->backing_objects)) {
+		spin_lock(&cookie->lock);
+
+		if (!hlist_empty(&cookie->backing_objects) &&
+		    !test_and_set_bit(FSCACHE_COOKIE_INVALIDATING,
+				      &cookie->flags)) {
+			object = hlist_entry(cookie->backing_objects.first,
+					     struct fscache_object,
+					     cookie_link);
+			if (object->state < FSCACHE_OBJECT_DYING)
+				fscache_raise_event(
+					object, FSCACHE_OBJECT_EV_INVALIDATE);
+		}
+
+		spin_unlock(&cookie->lock);
+	}
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_invalidate);
+
+/*
+ * Wait for object invalidation to complete.
+ */
+void __fscache_wait_on_invalidate(struct fscache_cookie *cookie)
+{
+	_enter("%p", cookie);
+
+	wait_on_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING,
+		    fscache_wait_bit_interruptible,
+		    TASK_UNINTERRUPTIBLE);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_wait_on_invalidate);
+
 /*
  * update the index entries backing a cookie
  */
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index f6aad48d38a8..c81179303930 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -122,10 +122,16 @@ extern int fscache_submit_exclusive_op(struct fscache_object *,
 extern int fscache_submit_op(struct fscache_object *,
 			     struct fscache_operation *);
 extern int fscache_cancel_op(struct fscache_operation *);
+extern void fscache_cancel_all_ops(struct fscache_object *);
 extern void fscache_abort_object(struct fscache_object *);
 extern void fscache_start_operations(struct fscache_object *);
 extern void fscache_operation_gc(struct work_struct *);
 
+/*
+ * page.c
+ */
+extern void fscache_invalidate_writes(struct fscache_cookie *);
+
 /*
  * proc.c
  */
@@ -205,6 +211,9 @@ extern atomic_t fscache_n_acquires_ok;
 extern atomic_t fscache_n_acquires_nobufs;
 extern atomic_t fscache_n_acquires_oom;
 
+extern atomic_t fscache_n_invalidates;
+extern atomic_t fscache_n_invalidates_run;
+
 extern atomic_t fscache_n_updates;
 extern atomic_t fscache_n_updates_null;
 extern atomic_t fscache_n_updates_run;
@@ -237,6 +246,7 @@ extern atomic_t fscache_n_cop_alloc_object;
 extern atomic_t fscache_n_cop_lookup_object;
 extern atomic_t fscache_n_cop_lookup_complete;
 extern atomic_t fscache_n_cop_grab_object;
+extern atomic_t fscache_n_cop_invalidate_object;
 extern atomic_t fscache_n_cop_update_object;
 extern atomic_t fscache_n_cop_drop_object;
 extern atomic_t fscache_n_cop_put_object;
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 773bc798a416..80b549141ea6 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -14,6 +14,7 @@
 
 #define FSCACHE_DEBUG_LEVEL COOKIE
 #include <linux/module.h>
+#include <linux/slab.h>
 #include "internal.h"
 
 const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = {
@@ -22,6 +23,7 @@ const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = {
 	[FSCACHE_OBJECT_CREATING]	= "OBJECT_CREATING",
 	[FSCACHE_OBJECT_AVAILABLE]	= "OBJECT_AVAILABLE",
 	[FSCACHE_OBJECT_ACTIVE]		= "OBJECT_ACTIVE",
+	[FSCACHE_OBJECT_INVALIDATING]	= "OBJECT_INVALIDATING",
 	[FSCACHE_OBJECT_UPDATING]	= "OBJECT_UPDATING",
 	[FSCACHE_OBJECT_DYING]		= "OBJECT_DYING",
 	[FSCACHE_OBJECT_LC_DYING]	= "OBJECT_LC_DYING",
@@ -39,6 +41,7 @@ const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5] = {
 	[FSCACHE_OBJECT_CREATING]	= "CRTN",
 	[FSCACHE_OBJECT_AVAILABLE]	= "AVBL",
 	[FSCACHE_OBJECT_ACTIVE]		= "ACTV",
+	[FSCACHE_OBJECT_INVALIDATING]	= "INVL",
 	[FSCACHE_OBJECT_UPDATING]	= "UPDT",
 	[FSCACHE_OBJECT_DYING]		= "DYNG",
 	[FSCACHE_OBJECT_LC_DYING]	= "LCDY",
@@ -54,6 +57,7 @@ static void fscache_put_object(struct fscache_object *);
 static void fscache_initialise_object(struct fscache_object *);
 static void fscache_lookup_object(struct fscache_object *);
 static void fscache_object_available(struct fscache_object *);
+static void fscache_invalidate_object(struct fscache_object *);
 static void fscache_release_object(struct fscache_object *);
 static void fscache_withdraw_object(struct fscache_object *);
 static void fscache_enqueue_dependents(struct fscache_object *);
@@ -78,6 +82,15 @@ static inline void fscache_done_parent_op(struct fscache_object *object)
 	spin_unlock(&parent->lock);
 }
 
+/*
+ * Notify netfs of invalidation completion.
+ */
+static inline void fscache_invalidation_complete(struct fscache_cookie *cookie)
+{
+	if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
+}
+
 /*
  * process events that have been sent to an object's state machine
  * - initiates parent lookup
@@ -125,6 +138,16 @@ static void fscache_object_state_machine(struct fscache_object *object)
 	case FSCACHE_OBJECT_ACTIVE:
 		goto active_transit;
 
+		/* Invalidate an object on disk */
+	case FSCACHE_OBJECT_INVALIDATING:
+		clear_bit(FSCACHE_OBJECT_EV_INVALIDATE, &object->events);
+		fscache_stat(&fscache_n_invalidates_run);
+		fscache_stat(&fscache_n_cop_invalidate_object);
+		fscache_invalidate_object(object);
+		fscache_stat_d(&fscache_n_cop_invalidate_object);
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
+		goto active_transit;
+
 		/* update the object metadata on disk */
 	case FSCACHE_OBJECT_UPDATING:
 		clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events);
@@ -275,6 +298,9 @@ active_transit:
 	case FSCACHE_OBJECT_EV_ERROR:
 		new_state = FSCACHE_OBJECT_DYING;
 		goto change_state;
+	case FSCACHE_OBJECT_EV_INVALIDATE:
+		new_state = FSCACHE_OBJECT_INVALIDATING;
+		goto change_state;
 	case FSCACHE_OBJECT_EV_UPDATE:
 		new_state = FSCACHE_OBJECT_UPDATING;
 		goto change_state;
@@ -679,6 +705,7 @@ static void fscache_withdraw_object(struct fscache_object *object)
 		if (object->cookie == cookie) {
 			hlist_del_init(&object->cookie_link);
 			object->cookie = NULL;
+			fscache_invalidation_complete(cookie);
 			detached = true;
 		}
 		spin_unlock(&cookie->lock);
@@ -888,3 +915,48 @@ enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
 	return result;
 }
 EXPORT_SYMBOL(fscache_check_aux);
+
+/*
+ * Asynchronously invalidate an object.
+ */
+static void fscache_invalidate_object(struct fscache_object *object)
+{
+	struct fscache_operation *op;
+	struct fscache_cookie *cookie = object->cookie;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	/* Reject any new read/write ops and abort any that are pending. */
+	fscache_invalidate_writes(cookie);
+	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+	fscache_cancel_all_ops(object);
+
+	/* Now we have to wait for in-progress reads and writes */
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op) {
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR);
+		_leave(" [ENOMEM]");
+		return;
+	}
+
+	fscache_operation_init(op, object->cache->ops->invalidate_object, NULL);
+	op->flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_EXCLUSIVE);
+
+	spin_lock(&cookie->lock);
+	if (fscache_submit_exclusive_op(object, op) < 0)
+		BUG();
+	spin_unlock(&cookie->lock);
+	fscache_put_operation(op);
+
+	/* Once we've completed the invalidation, we know there will be no data
+	 * stored in the cache and thus we can reinstate the data-check-skip
+	 * optimisation.
+	 */
+	set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+	/* We can allow read and write requests to come in once again.  They'll
+	 * queue up behind our exclusive invalidation operation.
+	 */
+	fscache_invalidation_complete(cookie);
+	_leave("");
+}
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index 748f9553c2cb..c58dbe613266 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -323,6 +323,38 @@ int fscache_cancel_op(struct fscache_operation *op)
 	return ret;
 }
 
+/*
+ * Cancel all pending operations on an object
+ */
+void fscache_cancel_all_ops(struct fscache_object *object)
+{
+	struct fscache_operation *op;
+
+	_enter("OBJ%x", object->debug_id);
+
+	spin_lock(&object->lock);
+
+	while (!list_empty(&object->pending_ops)) {
+		op = list_entry(object->pending_ops.next,
+				struct fscache_operation, pend_link);
+		fscache_stat(&fscache_n_op_cancelled);
+		list_del_init(&op->pend_link);
+
+		ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+		fscache_put_operation(op);
+		cond_resched_lock(&object->lock);
+	}
+
+	spin_unlock(&object->lock);
+	_leave("");
+}
+
 /*
  * Record the completion of an in-progress operation.
  */
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index b38b13d2a555..7bf9d2557052 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -361,6 +361,11 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 	if (hlist_empty(&cookie->backing_objects))
 		goto nobufs;
 
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
 	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
 	ASSERTCMP(page, !=, NULL);
 
@@ -483,6 +488,11 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 	if (hlist_empty(&cookie->backing_objects))
 		goto nobufs;
 
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
 	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
 	ASSERTCMP(*nr_pages, >, 0);
 	ASSERT(!list_empty(pages));
@@ -591,6 +601,11 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
 	ASSERTCMP(page, !=, NULL);
 
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
 	if (fscache_wait_for_deferred_lookup(cookie) < 0)
 		return -ERESTARTSYS;
 
@@ -730,6 +745,37 @@ superseded:
 	_leave("");
 }
 
+/*
+ * Clear the pages pending writing for invalidation
+ */
+void fscache_invalidate_writes(struct fscache_cookie *cookie)
+{
+	struct page *page;
+	void *results[16];
+	int n, i;
+
+	_enter("");
+
+	while (spin_lock(&cookie->stores_lock),
+	       n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0,
+					      ARRAY_SIZE(results),
+					      FSCACHE_COOKIE_PENDING_TAG),
+	       n > 0) {
+		for (i = n - 1; i >= 0; i--) {
+			page = results[i];
+			radix_tree_delete(&cookie->stores, page->index);
+		}
+
+		spin_unlock(&cookie->stores_lock);
+
+		for (i = n - 1; i >= 0; i--)
+			page_cache_release(results[i]);
+	}
+
+	spin_unlock(&cookie->stores_lock);
+	_leave("");
+}
+
 /*
  * request a page be stored in the cache
  * - returns:
@@ -776,6 +822,11 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 
 	fscache_stat(&fscache_n_stores);
 
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
 	op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY);
 	if (!op)
 		goto nomem;
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 4765190d537f..51cdaee14109 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -80,6 +80,9 @@ atomic_t fscache_n_acquires_ok;
 atomic_t fscache_n_acquires_nobufs;
 atomic_t fscache_n_acquires_oom;
 
+atomic_t fscache_n_invalidates;
+atomic_t fscache_n_invalidates_run;
+
 atomic_t fscache_n_updates;
 atomic_t fscache_n_updates_null;
 atomic_t fscache_n_updates_run;
@@ -112,6 +115,7 @@ atomic_t fscache_n_cop_alloc_object;
 atomic_t fscache_n_cop_lookup_object;
 atomic_t fscache_n_cop_lookup_complete;
 atomic_t fscache_n_cop_grab_object;
+atomic_t fscache_n_cop_invalidate_object;
 atomic_t fscache_n_cop_update_object;
 atomic_t fscache_n_cop_drop_object;
 atomic_t fscache_n_cop_put_object;
@@ -168,6 +172,10 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_object_created),
 		   atomic_read(&fscache_n_object_lookups_timed_out));
 
+	seq_printf(m, "Invals : n=%u run=%u\n",
+		   atomic_read(&fscache_n_invalidates),
+		   atomic_read(&fscache_n_invalidates_run));
+
 	seq_printf(m, "Updates: n=%u nul=%u run=%u\n",
 		   atomic_read(&fscache_n_updates),
 		   atomic_read(&fscache_n_updates_null),
@@ -246,7 +254,8 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_cop_lookup_object),
 		   atomic_read(&fscache_n_cop_lookup_complete),
 		   atomic_read(&fscache_n_cop_grab_object));
-	seq_printf(m, "CacheOp: upo=%d dro=%d pto=%d atc=%d syn=%d\n",
+	seq_printf(m, "CacheOp: inv=%d upo=%d dro=%d pto=%d atc=%d syn=%d\n",
+		   atomic_read(&fscache_n_cop_invalidate_object),
 		   atomic_read(&fscache_n_cop_update_object),
 		   atomic_read(&fscache_n_cop_drop_object),
 		   atomic_read(&fscache_n_cop_put_object),
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index f5facd1d333f..1e454ad7a832 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -254,6 +254,9 @@ struct fscache_cache_ops {
 	/* store the updated auxiliary data on an object */
 	void (*update_object)(struct fscache_object *object);
 
+	/* Invalidate an object */
+	void (*invalidate_object)(struct fscache_operation *op);
+
 	/* discard the resources pinned by an object and effect retirement if
 	 * necessary */
 	void (*drop_object)(struct fscache_object *object);
@@ -329,6 +332,7 @@ struct fscache_cookie {
 #define FSCACHE_COOKIE_FILLING		4	/* T if filling object incrementally */
 #define FSCACHE_COOKIE_UNAVAILABLE	5	/* T if cookie is unavailable (error, etc) */
 #define FSCACHE_COOKIE_WAITING_ON_READS	6	/* T if cookie is waiting on reads */
+#define FSCACHE_COOKIE_INVALIDATING	7	/* T if cookie is being invalidated */
 };
 
 extern struct fscache_cookie fscache_fsdef_index;
@@ -345,6 +349,7 @@ struct fscache_object {
 		/* active states */
 		FSCACHE_OBJECT_AVAILABLE,	/* cleaning up object after creation */
 		FSCACHE_OBJECT_ACTIVE,		/* object is usable */
+		FSCACHE_OBJECT_INVALIDATING,	/* object is invalidating */
 		FSCACHE_OBJECT_UPDATING,	/* object is updating */
 
 		/* terminal states */
@@ -378,7 +383,8 @@ struct fscache_object {
 #define FSCACHE_OBJECT_EV_RELEASE	4	/* T if netfs requested object release */
 #define FSCACHE_OBJECT_EV_RETIRE	5	/* T if netfs requested object retirement */
 #define FSCACHE_OBJECT_EV_WITHDRAW	6	/* T if cache requested object withdrawal */
-#define FSCACHE_OBJECT_EVENTS_MASK	0x7f	/* mask of all events*/
+#define FSCACHE_OBJECT_EV_INVALIDATE	7	/* T if cache requested object invalidation */
+#define FSCACHE_OBJECT_EVENTS_MASK	0xff	/* mask of all events*/
 
 	unsigned long		flags;
 #define FSCACHE_OBJECT_LOCK		0	/* T if object is busy being processed */
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index f4b6353543bf..7a086235da4b 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -185,6 +185,8 @@ extern struct fscache_cookie *__fscache_acquire_cookie(
 extern void __fscache_relinquish_cookie(struct fscache_cookie *, int);
 extern void __fscache_update_cookie(struct fscache_cookie *);
 extern int __fscache_attr_changed(struct fscache_cookie *);
+extern void __fscache_invalidate(struct fscache_cookie *);
+extern void __fscache_wait_on_invalidate(struct fscache_cookie *);
 extern int __fscache_read_or_alloc_page(struct fscache_cookie *,
 					struct page *,
 					fscache_rw_complete_t,
@@ -389,6 +391,42 @@ int fscache_attr_changed(struct fscache_cookie *cookie)
 		return -ENOBUFS;
 }
 
+/**
+ * fscache_invalidate - Notify cache that an object needs invalidation
+ * @cookie: The cookie representing the cache object
+ *
+ * Notify the cache that an object is needs to be invalidated and that it
+ * should abort any retrievals or stores it is doing on the cache.  The object
+ * is then marked non-caching until such time as the invalidation is complete.
+ *
+ * This can be called with spinlocks held.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_invalidate(struct fscache_cookie *cookie)
+{
+	if (fscache_cookie_valid(cookie))
+		__fscache_invalidate(cookie);
+}
+
+/**
+ * fscache_wait_on_invalidate - Wait for invalidation to complete
+ * @cookie: The cookie representing the cache object
+ *
+ * Wait for the invalidation of an object to complete.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_wait_on_invalidate(struct fscache_cookie *cookie)
+{
+	if (fscache_cookie_valid(cookie))
+		__fscache_wait_on_invalidate(cookie);
+}
+
 /**
  * fscache_reserve_space - Reserve data space for a cached object
  * @cookie: The cookie representing the cache object
-- 
cgit v1.2.3-55-g7522


From a02de9608595c8ef649ef03ae735b0b45e3d4396 Mon Sep 17 00:00:00 2001
From: David Howells
Date: Thu, 20 Dec 2012 21:52:36 +0000
Subject: VFS: Make more complete truncate operation available to CacheFiles

Make a more complete truncate operation available to CacheFiles (including
security checks and suchlike) so that it can use this to clear invalidated
cache files.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/open.c          | 50 +++++++++++++++++++++++++++-----------------------
 include/linux/fs.h |  1 +
 2 files changed, 28 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/fs/open.c b/fs/open.c
index 182d8667b7bd..c819bbdab47f 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -61,33 +61,22 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
 	return ret;
 }
 
-static long do_sys_truncate(const char __user *pathname, loff_t length)
+long vfs_truncate(struct path *path, loff_t length)
 {
-	struct path path;
 	struct inode *inode;
-	int error;
-
-	error = -EINVAL;
-	if (length < 0)	/* sorry, but loff_t says... */
-		goto out;
+	long error;
 
-	error = user_path(pathname, &path);
-	if (error)
-		goto out;
-	inode = path.dentry->d_inode;
+	inode = path->dentry->d_inode;
 
 	/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
-	error = -EISDIR;
 	if (S_ISDIR(inode->i_mode))
-		goto dput_and_out;
-
-	error = -EINVAL;
+		return -EISDIR;
 	if (!S_ISREG(inode->i_mode))
-		goto dput_and_out;
+		return -EINVAL;
 
-	error = mnt_want_write(path.mnt);
+	error = mnt_want_write(path->mnt);
 	if (error)
-		goto dput_and_out;
+		goto out;
 
 	error = inode_permission(inode, MAY_WRITE);
 	if (error)
@@ -111,19 +100,34 @@ static long do_sys_truncate(const char __user *pathname, loff_t length)
 
 	error = locks_verify_truncate(inode, NULL, length);
 	if (!error)
-		error = security_path_truncate(&path);
+		error = security_path_truncate(path);
 	if (!error)
-		error = do_truncate(path.dentry, length, 0, NULL);
+		error = do_truncate(path->dentry, length, 0, NULL);
 
 put_write_and_out:
 	put_write_access(inode);
 mnt_drop_write_and_out:
-	mnt_drop_write(path.mnt);
-dput_and_out:
-	path_put(&path);
+	mnt_drop_write(path->mnt);
 out:
 	return error;
 }
+EXPORT_SYMBOL_GPL(vfs_truncate);
+
+static long do_sys_truncate(const char __user *pathname, loff_t length)
+{
+	struct path path;
+	int error;
+
+	if (length < 0)	/* sorry, but loff_t says... */
+		return -EINVAL;
+
+	error = user_path(pathname, &path);
+	if (!error) {
+		error = vfs_truncate(&path, length);
+		path_put(&path);
+	}
+	return error;
+}
 
 SYSCALL_DEFINE2(truncate, const char __user *, path, long, length)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a823d4be38e7..017a15b707e2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1999,6 +1999,7 @@ struct filename {
 	bool			separate; /* should "name" be freed? */
 };
 
+extern long vfs_truncate(struct path *, loff_t);
 extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
 		       struct file *filp);
 extern int do_fallocate(struct file *file, int mode, loff_t offset,
-- 
cgit v1.2.3-55-g7522


From 36a02de5d7981435931d4608ee3e510b752e072b Mon Sep 17 00:00:00 2001
From: David Howells
Date: Wed, 5 Dec 2012 13:34:46 +0000
Subject: FS-Cache: Convert the object event ID #defines into an enum

Convert the fscache_object event IDs from #defines into an enum.  Also add an
extra label to the enum to carry the event count and redefine the event mask
in terms of that.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/linux/fscache-cache.h | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 1e454ad7a832..73e68c8d5df4 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -337,6 +337,23 @@ struct fscache_cookie {
 
 extern struct fscache_cookie fscache_fsdef_index;
 
+/*
+ * Event list for fscache_object::{event_mask,events}
+ */
+enum {
+	FSCACHE_OBJECT_EV_REQUEUE,	/* T if object should be requeued */
+	FSCACHE_OBJECT_EV_UPDATE,	/* T if object should be updated */
+	FSCACHE_OBJECT_EV_INVALIDATE,	/* T if cache requested object invalidation */
+	FSCACHE_OBJECT_EV_CLEARED,	/* T if accessors all gone */
+	FSCACHE_OBJECT_EV_ERROR,	/* T if fatal error occurred during processing */
+	FSCACHE_OBJECT_EV_RELEASE,	/* T if netfs requested object release */
+	FSCACHE_OBJECT_EV_RETIRE,	/* T if netfs requested object retirement */
+	FSCACHE_OBJECT_EV_WITHDRAW,	/* T if cache requested object withdrawal */
+	NR_FSCACHE_OBJECT_EVENTS
+};
+
+#define FSCACHE_OBJECT_EVENTS_MASK ((1UL << NR_FSCACHE_OBJECT_EVENTS) - 1)
+
 /*
  * on-disk cache file or index handle
  */
@@ -376,15 +393,6 @@ struct fscache_object {
 	unsigned long		event_mask;	/* events this object is interested in */
 	unsigned long		events;		/* events to be processed by this object
 						 * (order is important - using fls) */
-#define FSCACHE_OBJECT_EV_REQUEUE	0	/* T if object should be requeued */
-#define FSCACHE_OBJECT_EV_UPDATE	1	/* T if object should be updated */
-#define FSCACHE_OBJECT_EV_CLEARED	2	/* T if accessors all gone */
-#define FSCACHE_OBJECT_EV_ERROR		3	/* T if fatal error occurred during processing */
-#define FSCACHE_OBJECT_EV_RELEASE	4	/* T if netfs requested object release */
-#define FSCACHE_OBJECT_EV_RETIRE	5	/* T if netfs requested object retirement */
-#define FSCACHE_OBJECT_EV_WITHDRAW	6	/* T if cache requested object withdrawal */
-#define FSCACHE_OBJECT_EV_INVALIDATE	7	/* T if cache requested object invalidation */
-#define FSCACHE_OBJECT_EVENTS_MASK	0xff	/* mask of all events*/
 
 	unsigned long		flags;
 #define FSCACHE_OBJECT_LOCK		0	/* T if object is busy being processed */
-- 
cgit v1.2.3-55-g7522


From 1f372dff1da37e2b36ae9085368fa46896398598 Mon Sep 17 00:00:00 2001
From: David Howells
Date: Thu, 13 Dec 2012 20:03:13 +0000
Subject: FS-Cache: Mark cancellation of in-progress operation

Mark as cancelled an operation that is in progress rather than pending at the
time it is cancelled, and call fscache_complete_op() to cancel an operation so
that blocked ops can be started.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 fs/cachefiles/interface.c     |  2 +-
 fs/fscache/operation.c        |  7 ++++---
 fs/fscache/page.c             | 10 +++++-----
 include/linux/fscache-cache.h |  4 ++--
 4 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 7a9d574b961c..746ce532e130 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -484,7 +484,7 @@ static void cachefiles_invalidate_object(struct fscache_operation *op)
 		}
 	}
 
-	fscache_op_complete(op);
+	fscache_op_complete(op, true);
 	_leave("");
 }
 
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index 9e6b7d232bb1..36c59604130d 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -363,9 +363,9 @@ void fscache_cancel_all_ops(struct fscache_object *object)
 }
 
 /*
- * Record the completion of an in-progress operation.
+ * Record the completion or cancellation of an in-progress operation.
  */
-void fscache_op_complete(struct fscache_operation *op)
+void fscache_op_complete(struct fscache_operation *op, bool cancelled)
 {
 	struct fscache_object *object = op->object;
 
@@ -380,7 +380,8 @@ void fscache_op_complete(struct fscache_operation *op)
 
 	spin_lock(&object->lock);
 
-	op->state = FSCACHE_OP_ST_COMPLETE;
+	op->state = cancelled ?
+		FSCACHE_OP_ST_CANCELLED : FSCACHE_OP_ST_COMPLETE;
 
 	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
 		object->n_exclusive--;
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index ef0218f5080d..8a92b9fabe83 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -171,7 +171,7 @@ static void fscache_attr_changed_op(struct fscache_operation *op)
 			fscache_abort_object(object);
 	}
 
-	fscache_op_complete(op);
+	fscache_op_complete(op, true);
 	_leave("");
 }
 
@@ -704,7 +704,7 @@ static void fscache_write_op(struct fscache_operation *_op)
 		 * exists, so we should just cancel this write operation.
 		 */
 		spin_unlock(&object->lock);
-		op->op.state = FSCACHE_OP_ST_CANCELLED;
+		fscache_op_complete(&op->op, false);
 		_leave(" [inactive]");
 		return;
 	}
@@ -717,7 +717,7 @@ static void fscache_write_op(struct fscache_operation *_op)
 		 * cancel this write operation.
 		 */
 		spin_unlock(&object->lock);
-		op->op.state = FSCACHE_OP_ST_CANCELLED;
+		fscache_op_complete(&op->op, false);
 		_leave(" [cancel] op{f=%lx s=%u} obj{s=%u f=%lx}",
 		       _op->flags, _op->state, object->state, object->flags);
 		return;
@@ -755,7 +755,7 @@ static void fscache_write_op(struct fscache_operation *_op)
 	fscache_end_page_write(object, page);
 	if (ret < 0) {
 		fscache_abort_object(object);
-		fscache_op_complete(&op->op);
+		fscache_op_complete(&op->op, true);
 	} else {
 		fscache_enqueue_operation(&op->op);
 	}
@@ -770,7 +770,7 @@ superseded:
 	spin_unlock(&cookie->stores_lock);
 	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
 	spin_unlock(&object->lock);
-	fscache_op_complete(&op->op);
+	fscache_op_complete(&op->op, true);
 	_leave("");
 }
 
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 73e68c8d5df4..5dfa0aa216b6 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -116,7 +116,7 @@ extern atomic_t fscache_op_debug_id;
 extern void fscache_op_work_func(struct work_struct *work);
 
 extern void fscache_enqueue_operation(struct fscache_operation *);
-extern void fscache_op_complete(struct fscache_operation *);
+extern void fscache_op_complete(struct fscache_operation *, bool);
 extern void fscache_put_operation(struct fscache_operation *);
 
 /**
@@ -196,7 +196,7 @@ static inline void fscache_retrieval_complete(struct fscache_retrieval *op,
 {
 	op->n_pages -= n_pages;
 	if (op->n_pages <= 0)
-		fscache_op_complete(&op->op);
+		fscache_op_complete(&op->op, true);
 }
 
 /**
-- 
cgit v1.2.3-55-g7522


From d30357f2f0ec0bfb67fd39f8f76d22d02d78631e Mon Sep 17 00:00:00 2001
From: Marco Stornelli
Date: Sat, 15 Dec 2012 11:59:20 +0100
Subject: vfs: drop vmtruncate

Removed vmtruncate

Signed-off-by: Marco Stornelli <marco.stornelli@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/libfs.c         | 2 --
 include/linux/fs.h | 1 -
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/fs/libfs.c b/fs/libfs.c
index 35fc6e74cd88..916da8c4158b 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -369,8 +369,6 @@ int simple_setattr(struct dentry *dentry, struct iattr *iattr)
 	struct inode *inode = dentry->d_inode;
 	int error;
 
-	WARN_ON_ONCE(inode->i_op->truncate);
-
 	error = inode_change_ok(inode, iattr);
 	if (error)
 		return error;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a823d4be38e7..a0c5ba57ffc5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1565,7 +1565,6 @@ struct inode_operations {
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
-	void (*truncate) (struct inode *);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
 	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
-- 
cgit v1.2.3-55-g7522


From 7898575fc81bd707ce0844cb06874d48e39bbe09 Mon Sep 17 00:00:00 2001
From: Marco Stornelli
Date: Sat, 15 Dec 2012 12:00:02 +0100
Subject: mm: drop vmtruncate

Removed vmtruncate

Signed-off-by: Marco Stornelli <marco.stornelli@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/mm.h |  1 -
 mm/truncate.c      | 23 -----------------------
 2 files changed, 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7f4f906190bd..63204078f72b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1007,7 +1007,6 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 
 extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
-extern int vmtruncate(struct inode *inode, loff_t offset);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
 int truncate_inode_page(struct address_space *mapping, struct page *page);
 int generic_error_remove_page(struct address_space *mapping, struct page *page);
diff --git a/mm/truncate.c b/mm/truncate.c
index d51ce92d6e83..c75b736e54b7 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -576,29 +576,6 @@ void truncate_setsize(struct inode *inode, loff_t newsize)
 }
 EXPORT_SYMBOL(truncate_setsize);
 
-/**
- * vmtruncate - unmap mappings "freed" by truncate() syscall
- * @inode: inode of the file used
- * @newsize: file offset to start truncating
- *
- * This function is deprecated and truncate_setsize or truncate_pagecache
- * should be used instead, together with filesystem specific block truncation.
- */
-int vmtruncate(struct inode *inode, loff_t newsize)
-{
-	int error;
-
-	error = inode_newsize_ok(inode, newsize);
-	if (error)
-		return error;
-
-	truncate_setsize(inode, newsize);
-	if (inode->i_op->truncate)
-		inode->i_op->truncate(inode);
-	return 0;
-}
-EXPORT_SYMBOL(vmtruncate);
-
 /**
  * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
  * @inode: inode
-- 
cgit v1.2.3-55-g7522


From 471667391a92bf7bf2cd4ff31a3ad88e5dec934b Mon Sep 17 00:00:00 2001
From: Alessio Igor Bogani
Date: Thu, 13 Dec 2012 12:22:39 +0100
Subject: vfs: Remove useless function prototypes

Commit 8e22cc88d68ca1a46d7d582938f979eb640ed30f removes the (un)lock_super
function definitions but forgets to remove their prototypes.

Signed-off-by: Alessio Igor Bogani <abogani@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index a0c5ba57ffc5..05cd238ad941 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1445,10 +1445,6 @@ static inline void sb_start_intwrite(struct super_block *sb)
 
 extern bool inode_owner_or_capable(const struct inode *inode);
 
-/* not quite ready to be deprecated, but... */
-extern void lock_super(struct super_block *);
-extern void unlock_super(struct super_block *);
-
 /*
  * VFS helper functions..
  */
-- 
cgit v1.2.3-55-g7522


From b9d6ba94b875192ef5e2dab92d72beea33b83c3d Mon Sep 17 00:00:00 2001
From: Jeff Layton
Date: Thu, 20 Dec 2012 14:59:40 -0500
Subject: vfs: add a retry_estale helper function to handle retries on ESTALE

This function is expected to be called from path-based syscalls to help
them decide whether to try the lookup and call again in the event that
they got an -ESTALE return back on an earier try.

Currently, we only retry the call once on an ESTALE error, but in the
event that we decide that that's not enough in the future, we should be
able to change the logic in this helper without too much effort.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/namei.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/linux/namei.h b/include/linux/namei.h
index 4bf19d8174ed..66542b644804 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -98,4 +98,20 @@ static inline void nd_terminate_link(void *name, size_t len, size_t maxlen)
 	((char *) name)[min(len, maxlen)] = '\0';
 }
 
+/**
+ * retry_estale - determine whether the caller should retry an operation
+ * @error: the error that would currently be returned
+ * @flags: flags being used for next lookup attempt
+ *
+ * Check to see if the error code was -ESTALE, and then determine whether
+ * to retry the call based on whether "flags" already has LOOKUP_REVAL set.
+ *
+ * Returns true if the caller should try the operation again.
+ */
+static inline bool
+retry_estale(const long error, const unsigned int flags)
+{
+	return error == -ESTALE && !(flags & LOOKUP_REVAL);
+}
+
 #endif /* _LINUX_NAMEI_H */
-- 
cgit v1.2.3-55-g7522


From 1ac12b4b6d707937f9de6d09622823b2fd0c93ef Mon Sep 17 00:00:00 2001
From: Jeff Layton
Date: Tue, 11 Dec 2012 12:10:06 -0500
Subject: vfs: turn is_dir argument to kern_path_create into a lookup_flags arg

Where we can pass in LOOKUP_DIRECTORY or LOOKUP_REVAL. Any other flags
passed in here are currently ignored.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/powerpc/platforms/cell/spufs/syscalls.c |  2 +-
 drivers/base/devtmpfs.c                      |  2 +-
 fs/namei.c                                   | 21 ++++++++++++++++-----
 include/linux/namei.h                        |  4 ++--
 4 files changed, 20 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index 5b7d8ffbf890..baee994fe810 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -66,7 +66,7 @@ static long do_spu_create(const char __user *pathname, unsigned int flags,
 	struct dentry *dentry;
 	int ret;
 
-	dentry = user_path_create(AT_FDCWD, pathname, &path, 1);
+	dentry = user_path_create(AT_FDCWD, pathname, &path, LOOKUP_DIRECTORY);
 	ret = PTR_ERR(dentry);
 	if (!IS_ERR(dentry)) {
 		ret = spufs_create(&path, dentry, flags, mode, neighbor);
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 147d1a4dd269..17cf7cad601e 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -148,7 +148,7 @@ static int dev_mkdir(const char *name, umode_t mode)
 	struct path path;
 	int err;
 
-	dentry = kern_path_create(AT_FDCWD, name, &path, 1);
+	dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_DIRECTORY);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
diff --git a/fs/namei.c b/fs/namei.c
index 25a41e02984b..8f8e41f6eb52 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3030,12 +3030,22 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 	return file;
 }
 
-struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, int is_dir)
+struct dentry *kern_path_create(int dfd, const char *pathname,
+				struct path *path, unsigned int lookup_flags)
 {
 	struct dentry *dentry = ERR_PTR(-EEXIST);
 	struct nameidata nd;
 	int err2;
-	int error = do_path_lookup(dfd, pathname, LOOKUP_PARENT, &nd);
+	int error;
+	bool is_dir = (lookup_flags & LOOKUP_DIRECTORY);
+
+	/*
+	 * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any
+	 * other flags passed in are ignored!
+	 */
+	lookup_flags &= LOOKUP_REVAL;
+
+	error = do_path_lookup(dfd, pathname, LOOKUP_PARENT|lookup_flags, &nd);
 	if (error)
 		return ERR_PTR(error);
 
@@ -3099,13 +3109,14 @@ void done_path_create(struct path *path, struct dentry *dentry)
 }
 EXPORT_SYMBOL(done_path_create);
 
-struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, int is_dir)
+struct dentry *user_path_create(int dfd, const char __user *pathname,
+				struct path *path, unsigned int lookup_flags)
 {
 	struct filename *tmp = getname(pathname);
 	struct dentry *res;
 	if (IS_ERR(tmp))
 		return ERR_CAST(tmp);
-	res = kern_path_create(dfd, tmp->name, path, is_dir);
+	res = kern_path_create(dfd, tmp->name, path, lookup_flags);
 	putname(tmp);
 	return res;
 }
@@ -3228,7 +3239,7 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
 	struct path path;
 	int error;
 
-	dentry = user_path_create(dfd, pathname, &path, 1);
+	dentry = user_path_create(dfd, pathname, &path, LOOKUP_DIRECTORY);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 66542b644804..e998c030061d 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -65,8 +65,8 @@ extern int user_path_at_empty(int, const char __user *, unsigned, struct path *,
 
 extern int kern_path(const char *, unsigned, struct path *);
 
-extern struct dentry *kern_path_create(int, const char *, struct path *, int);
-extern struct dentry *user_path_create(int, const char __user *, struct path *, int);
+extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int);
+extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int);
 extern void done_path_create(struct path *, struct dentry *);
 extern struct dentry *kern_path_locked(const char *, struct path *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
-- 
cgit v1.2.3-55-g7522


From b66c5984017533316fd1951770302649baf1aa33 Mon Sep 17 00:00:00 2001
From: Kees Cook
Date: Thu, 20 Dec 2012 15:05:16 -0800
Subject: exec: do not leave bprm->interp on stack

If a series of scripts are executed, each triggering module loading via
unprintable bytes in the script header, kernel stack contents can leak
into the command line.

Normally execution of binfmt_script and binfmt_misc happens recursively.
However, when modules are enabled, and unprintable bytes exist in the
bprm->buf, execution will restart after attempting to load matching
binfmt modules.  Unfortunately, the logic in binfmt_script and
binfmt_misc does not expect to get restarted.  They leave bprm->interp
pointing to their local stack.  This means on restart bprm->interp is
left pointing into unused stack memory which can then be copied into the
userspace argv areas.

After additional study, it seems that both recursion and restart remains
the desirable way to handle exec with scripts, misc, and modules.  As
such, we need to protect the changes to interp.

This changes the logic to require allocation for any changes to the
bprm->interp.  To avoid adding a new kmalloc to every exec, the default
value is left as-is.  Only when passing through binfmt_script or
binfmt_misc does an allocation take place.

For a proof of concept, see DoTest.sh from:

   http://www.halfdog.net/Security/2012/LinuxKernelBinfmtScriptStackDataDisclosure/

Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: halfdog <me@halfdog.net>
Cc: P J P <ppandit@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_misc.c        |  5 ++++-
 fs/binfmt_script.c      |  4 +++-
 fs/exec.c               | 15 +++++++++++++++
 include/linux/binfmts.h |  1 +
 4 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 9be335fb8a7c..0c8869fdd14e 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -172,7 +172,10 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		goto _error;
 	bprm->argc ++;
 
-	bprm->interp = iname;	/* for binfmt_script */
+	/* Update interp in case binfmt_script needs it. */
+	retval = bprm_change_interp(iname, bprm);
+	if (retval < 0)
+		goto _error;
 
 	interp_file = open_exec (iname);
 	retval = PTR_ERR (interp_file);
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 1610a91637e5..5027a3e14922 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -80,7 +80,9 @@ static int load_script(struct linux_binprm *bprm)
 	retval = copy_strings_kernel(1, &i_name, bprm);
 	if (retval) return retval; 
 	bprm->argc++;
-	bprm->interp = interp;
+	retval = bprm_change_interp(interp, bprm);
+	if (retval < 0)
+		return retval;
 
 	/*
 	 * OK, now restart the process with the interpreter's dentry.
diff --git a/fs/exec.c b/fs/exec.c
index d8e1191cb112..237d5342786c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1175,9 +1175,24 @@ void free_bprm(struct linux_binprm *bprm)
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
+	/* If a binfmt changed the interp, free it. */
+	if (bprm->interp != bprm->filename)
+		kfree(bprm->interp);
 	kfree(bprm);
 }
 
+int bprm_change_interp(char *interp, struct linux_binprm *bprm)
+{
+	/* If a binfmt changed the interp, free it first. */
+	if (bprm->interp != bprm->filename)
+		kfree(bprm->interp);
+	bprm->interp = kstrdup(interp, GFP_KERNEL);
+	if (!bprm->interp)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL(bprm_change_interp);
+
 /*
  * install the new credentials for this executable
  */
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index a4c2b565c835..bdf3965f0a29 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -112,6 +112,7 @@ extern int setup_arg_pages(struct linux_binprm * bprm,
 			   unsigned long stack_top,
 			   int executable_stack);
 extern int bprm_mm_init(struct linux_binprm *bprm);
+extern int bprm_change_interp(char *interp, struct linux_binprm *bprm);
 extern int copy_strings_kernel(int argc, const char *const *argv,
 			       struct linux_binprm *bprm);
 extern int prepare_bprm_creds(struct linux_binprm *bprm);
-- 
cgit v1.2.3-55-g7522


From c4e18497d8fd92eef2c6e7eadcc1a107ccd115ea Mon Sep 17 00:00:00 2001
From: Guenter Roeck
Date: Thu, 20 Dec 2012 15:05:42 -0800
Subject: linux/kernel.h: fix DIV_ROUND_CLOSEST with unsigned divisors

Commit 263a523d18bc ("linux/kernel.h: Fix warning seen with W=1 due to
change in DIV_ROUND_CLOSEST") fixes a warning seen with W=1 due to
change in DIV_ROUND_CLOSEST.

Unfortunately, the C compiler converts divide operations with unsigned
divisors to unsigned, even if the dividend is signed and negative (for
example, -10 / 5U = 858993457).  The C standard says "If one operand has
unsigned int type, the other operand is converted to unsigned int", so
the compiler is not to blame.  As a result, DIV_ROUND_CLOSEST(0, 2U) and
similar operations now return bad values, since the automatic conversion
of expressions such as "0 - 2U/2" to unsigned was not taken into
account.

Fix by checking for the divisor variable type when deciding which
operation to perform.  This fixes DIV_ROUND_CLOSEST(0, 2U), but still
returns bad values for negative dividends divided by unsigned divisors.
Mark the latter case as unsupported.

One observed effect of this problem is that the s2c_hwmon driver reports
a value of 4198403 instead of 0 if the ADC reads 0.

Other impact is unpredictable.  Problem is seen if the divisor is an
unsigned variable or constant and the dividend is less than (divisor/2).

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reported-by: Juergen Beisert <jbe@pengutronix.de>
Tested-by: Juergen Beisert <jbe@pengutronix.de>
Cc: Jean Delvare <khali@linux-fr.org>
Cc: <stable@vger.kernel.org>	[3.7.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index d140e8fb075f..c566927efcbd 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -77,13 +77,15 @@
 
 /*
  * Divide positive or negative dividend by positive divisor and round
- * to closest integer. Result is undefined for negative divisors.
+ * to closest integer. Result is undefined for negative divisors and
+ * for negative dividends if the divisor variable type is unsigned.
  */
 #define DIV_ROUND_CLOSEST(x, divisor)(			\
 {							\
 	typeof(x) __x = x;				\
 	typeof(divisor) __d = divisor;			\
-	(((typeof(x))-1) > 0 || (__x) > 0) ?		\
+	(((typeof(x))-1) > 0 ||				\
+	 ((typeof(divisor))-1) > 0 || (__x) > 0) ?	\
 		(((__x) + ((__d) / 2)) / (__d)) :	\
 		(((__x) - ((__d) / 2)) / (__d));	\
 }							\
-- 
cgit v1.2.3-55-g7522


From 5023e5cf58e1dae904e2e8b5b9779c33512b75a1 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka
Date: Fri, 21 Dec 2012 20:23:36 +0000
Subject: dm ioctl: remove PF_MEMALLOC

When allocating memory for the userspace ioctl data, set some
appropriate GPF flags directly instead of using PF_MEMALLOC.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-ioctl.c         | 13 ++++---------
 include/uapi/linux/dm-ioctl.h |  4 ++--
 2 files changed, 6 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index a651d528f80d..a37aeba7dc1b 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1556,7 +1556,10 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl **param)
 
 	secure_data = tmp.flags & DM_SECURE_DATA_FLAG;
 
-	dmi = vmalloc(tmp.data_size);
+	/*
+	 * Try to avoid low memory issues when a device is suspended.
+	 */
+	dmi = __vmalloc(tmp.data_size, GFP_NOIO | __GFP_REPEAT | __GFP_HIGH, PAGE_KERNEL);
 	if (!dmi) {
 		if (secure_data && clear_user(user, tmp.data_size))
 			return -EFAULT;
@@ -1656,19 +1659,11 @@ static int ctl_ioctl(uint command, struct dm_ioctl __user *user)
 		return -ENOTTY;
 	}
 
-	/*
-	 * Trying to avoid low memory issues when a device is
-	 * suspended.
-	 */
-	current->flags |= PF_MEMALLOC;
-
 	/*
 	 * Copy the parameters into kernel space.
 	 */
 	r = copy_params(user, &param);
 
-	current->flags &= ~PF_MEMALLOC;
-
 	if (r)
 		return r;
 
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index 91e3a360f611..539b179b349c 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -268,8 +268,8 @@ enum {
 
 #define DM_VERSION_MAJOR	4
 #define DM_VERSION_MINOR	23
-#define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2012-07-25)"
+#define DM_VERSION_PATCHLEVEL	1
+#define DM_VERSION_EXTRA	"-ioctl (2012-12-18)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
-- 
cgit v1.2.3-55-g7522


From d54eaa5a0fde0a202e4e91f200f818edcef15bee Mon Sep 17 00:00:00 2001
From: Mike Snitzer
Date: Fri, 21 Dec 2012 20:23:36 +0000
Subject: dm: prepare to support WRITE SAME

Allow targets to opt in to WRITE SAME support by setting
'num_write_same_requests' in the dm_target structure.

A dm device will only advertise WRITE SAME support if all its
targets and all its underlying devices support it.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-table.c         | 30 +++++++++++++++++++++++++++++-
 include/linux/device-mapper.h |  5 +++++
 2 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index fa2955790031..6be58b696377 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1414,6 +1414,33 @@ static bool dm_table_all_devices_attribute(struct dm_table *t,
 	return 1;
 }
 
+static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev,
+					 sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && !q->limits.max_write_same_sectors;
+}
+
+static bool dm_table_supports_write_same(struct dm_table *t)
+{
+	struct dm_target *ti;
+	unsigned i = 0;
+
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
+
+		if (!ti->num_write_same_requests)
+			return false;
+
+		if (!ti->type->iterate_devices ||
+		    !ti->type->iterate_devices(ti, device_not_write_same_capable, NULL))
+			return false;
+	}
+
+	return true;
+}
+
 void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			       struct queue_limits *limits)
 {
@@ -1445,7 +1472,8 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	else
 		queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, q);
 
-	q->limits.max_write_same_sectors = 0;
+	if (!dm_table_supports_write_same(t))
+		q->limits.max_write_same_sectors = 0;
 
 	dm_table_set_integrity(t);
 
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 38d27a10aa5d..d1f6cd8486f2 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -205,6 +205,11 @@ struct dm_target {
 	 */
 	unsigned num_discard_requests;
 
+	/*
+	 * The number of WRITE SAME requests that will be submitted to the target.
+	 */
+	unsigned num_write_same_requests;
+
 	/* target specific data */
 	void *private;
 
-- 
cgit v1.2.3-55-g7522


From c0820cf5ad09522bdd9ff68e84841a09c9f339d8 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka
Date: Fri, 21 Dec 2012 20:23:38 +0000
Subject: dm: introduce per_bio_data

Introduce a field per_bio_data_size in struct dm_target.

Targets can set this field in the constructor. If a target sets this
field to a non-zero value, "per_bio_data_size" bytes of auxiliary data
are allocated for each bio submitted to the target. These data can be
used for any purpose by the target and help us improve performance by
removing some per-target mempools.

Per-bio data is accessed with dm_per_bio_data. The
argument data_size must be the same as the value per_bio_data_size in
dm_target.

If the target has a pointer to per_bio_data, it can get a pointer to
the bio with dm_bio_from_per_bio_data() function (data_size must be the
same as the value passed to dm_per_bio_data).

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-table.c         | 11 ++++++++++-
 drivers/md/dm.c               | 33 +++++++++++++++------------------
 drivers/md/dm.h               |  2 +-
 include/linux/device-mapper.h | 30 ++++++++++++++++++++++++++++++
 4 files changed, 56 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 6be58b696377..daf25d0890b3 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -967,13 +967,22 @@ bool dm_table_request_based(struct dm_table *t)
 int dm_table_alloc_md_mempools(struct dm_table *t)
 {
 	unsigned type = dm_table_get_type(t);
+	unsigned per_bio_data_size = 0;
+	struct dm_target *tgt;
+	unsigned i;
 
 	if (unlikely(type == DM_TYPE_NONE)) {
 		DMWARN("no table type is set, can't allocate mempools");
 		return -EINVAL;
 	}
 
-	t->mempools = dm_alloc_md_mempools(type, t->integrity_supported);
+	if (type == DM_TYPE_BIO_BASED)
+		for (i = 0; i < t->num_targets; i++) {
+			tgt = t->targets + i;
+			per_bio_data_size = max(per_bio_data_size, tgt->per_bio_data_size);
+		}
+
+	t->mempools = dm_alloc_md_mempools(type, t->integrity_supported, per_bio_data_size);
 	if (!t->mempools)
 		return -ENOMEM;
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5401cdce0fc5..2765cf2ba0ff 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -62,18 +62,6 @@ struct dm_io {
 	spinlock_t endio_lock;
 };
 
-/*
- * For bio-based dm.
- * One of these is allocated per target within a bio.  Hopefully
- * this will be simplified out one day.
- */
-struct dm_target_io {
-	struct dm_io *io;
-	struct dm_target *ti;
-	union map_info info;
-	struct bio clone;
-};
-
 /*
  * For request-based dm.
  * One of these is allocated per request.
@@ -1980,13 +1968,20 @@ static void free_dev(struct mapped_device *md)
 
 static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 {
-	struct dm_md_mempools *p;
+	struct dm_md_mempools *p = dm_table_get_md_mempools(t);
 
-	if (md->io_pool && (md->tio_pool || dm_table_get_type(t) == DM_TYPE_BIO_BASED) && md->bs)
-		/* the md already has necessary mempools */
+	if (md->io_pool && (md->tio_pool || dm_table_get_type(t) == DM_TYPE_BIO_BASED) && md->bs) {
+		/*
+		 * The md already has necessary mempools. Reload just the
+		 * bioset because front_pad may have changed because
+		 * a different table was loaded.
+		 */
+		bioset_free(md->bs);
+		md->bs = p->bs;
+		p->bs = NULL;
 		goto out;
+	}
 
-	p = dm_table_get_md_mempools(t);
 	BUG_ON(!p || md->io_pool || md->tio_pool || md->bs);
 
 	md->io_pool = p->io_pool;
@@ -2745,7 +2740,7 @@ int dm_noflush_suspending(struct dm_target *ti)
 }
 EXPORT_SYMBOL_GPL(dm_noflush_suspending);
 
-struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity)
+struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, unsigned per_bio_data_size)
 {
 	struct dm_md_mempools *pools = kmalloc(sizeof(*pools), GFP_KERNEL);
 	unsigned int pool_size = (type == DM_TYPE_BIO_BASED) ? 16 : MIN_IOS;
@@ -2753,6 +2748,8 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity)
 	if (!pools)
 		return NULL;
 
+	per_bio_data_size = roundup(per_bio_data_size, __alignof__(struct dm_target_io));
+
 	pools->io_pool = (type == DM_TYPE_BIO_BASED) ?
 			 mempool_create_slab_pool(MIN_IOS, _io_cache) :
 			 mempool_create_slab_pool(MIN_IOS, _rq_bio_info_cache);
@@ -2768,7 +2765,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity)
 
 	pools->bs = (type == DM_TYPE_BIO_BASED) ?
 		bioset_create(pool_size,
-			      offsetof(struct dm_target_io, clone)) :
+			      per_bio_data_size + offsetof(struct dm_target_io, clone)) :
 		bioset_create(pool_size,
 			      offsetof(struct dm_rq_clone_bio_info, clone));
 	if (!pools->bs)
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 6a99fefaa743..45b97da1bd06 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -159,7 +159,7 @@ void dm_kcopyd_exit(void);
 /*
  * Mempool operations
  */
-struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity);
+struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, unsigned per_bio_data_size);
 void dm_free_md_mempools(struct dm_md_mempools *pools);
 
 #endif
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index d1f6cd8486f2..6f0e73b4a80d 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -210,6 +210,12 @@ struct dm_target {
 	 */
 	unsigned num_write_same_requests;
 
+	/*
+	 * The minimum number of extra bytes allocated in each bio for the
+	 * target to use.  dm_per_bio_data returns the data location.
+	 */
+	unsigned per_bio_data_size;
+
 	/* target specific data */
 	void *private;
 
@@ -246,6 +252,30 @@ struct dm_target_callbacks {
 	int (*congested_fn) (struct dm_target_callbacks *, int);
 };
 
+/*
+ * For bio-based dm.
+ * One of these is allocated for each bio.
+ * This structure shouldn't be touched directly by target drivers.
+ * It is here so that we can inline dm_per_bio_data and
+ * dm_bio_from_per_bio_data
+ */
+struct dm_target_io {
+	struct dm_io *io;
+	struct dm_target *ti;
+	union map_info info;
+	struct bio clone;
+};
+
+static inline void *dm_per_bio_data(struct bio *bio, size_t data_size)
+{
+	return (char *)bio - offsetof(struct dm_target_io, clone) - data_size;
+}
+
+static inline struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size)
+{
+	return (struct bio *)((char *)data + data_size + offsetof(struct dm_target_io, clone));
+}
+
 int dm_register_target(struct target_type *t);
 void dm_unregister_target(struct target_type *t);
 
-- 
cgit v1.2.3-55-g7522


From ddbd658f6446a35e4d6ba84812fd71023320cae2 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka
Date: Fri, 21 Dec 2012 20:23:39 +0000
Subject: dm: move target request nr to dm_target_io

This patch moves target_request_nr from map_info to dm_target_io and
makes it accessible with dm_bio_get_target_request_nr.

This patch is a preparation for the next patch that removes map_info.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-snap.c          |  2 +-
 drivers/md/dm-stripe.c        |  4 ++--
 drivers/md/dm.c               |  3 ++-
 include/linux/device-mapper.h | 14 ++++++++++----
 4 files changed, 15 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 5e88bc437be0..b7e179cdc5af 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1682,7 +1682,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio,
 	chunk_t chunk;
 
 	if (bio->bi_rw & REQ_FLUSH) {
-		if (!map_context->target_request_nr)
+		if (!dm_bio_get_target_request_nr(bio))
 			bio->bi_bdev = s->origin->bdev;
 		else
 			bio->bi_bdev = s->cow->bdev;
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index e2f876539743..4e7ba82146c0 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -279,13 +279,13 @@ static int stripe_map(struct dm_target *ti, struct bio *bio,
 	unsigned target_request_nr;
 
 	if (bio->bi_rw & REQ_FLUSH) {
-		target_request_nr = map_context->target_request_nr;
+		target_request_nr = dm_bio_get_target_request_nr(bio);
 		BUG_ON(target_request_nr >= sc->stripes);
 		bio->bi_bdev = sc->stripe[target_request_nr].dev->bdev;
 		return DM_MAPIO_REMAPPED;
 	}
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
-		target_request_nr = map_context->target_request_nr;
+		target_request_nr = dm_bio_get_target_request_nr(bio);
 		BUG_ON(target_request_nr >= sc->stripes);
 		return stripe_map_discard(sc, bio, target_request_nr);
 	}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 2765cf2ba0ff..5ee580b4f330 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1099,6 +1099,7 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci,
 	tio->io = ci->io;
 	tio->ti = ti;
 	memset(&tio->info, 0, sizeof(tio->info));
+	tio->target_request_nr = 0;
 
 	return tio;
 }
@@ -1109,7 +1110,7 @@ static void __issue_target_request(struct clone_info *ci, struct dm_target *ti,
 	struct dm_target_io *tio = alloc_tio(ci, ti, ci->bio->bi_max_vecs);
 	struct bio *clone = &tio->clone;
 
-	tio->info.target_request_nr = request_nr;
+	tio->target_request_nr = request_nr;
 
 	/*
 	 * Discard requests require the bio's inline iovecs be initialized.
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 6f0e73b4a80d..eb96ef6fd8b7 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -23,7 +23,6 @@ typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t;
 union map_info {
 	void *ptr;
 	unsigned long long ll;
-	unsigned target_request_nr;
 };
 
 /*
@@ -193,20 +192,21 @@ struct dm_target {
 	 * A number of zero-length barrier requests that will be submitted
 	 * to the target for the purpose of flushing cache.
 	 *
-	 * The request number will be placed in union map_info->target_request_nr.
+	 * The request number can be accessed with dm_bio_get_target_request_nr.
 	 * It is a responsibility of the target driver to remap these requests
 	 * to the real underlying devices.
 	 */
 	unsigned num_flush_requests;
 
 	/*
-	 * The number of discard requests that will be submitted to the
-	 * target.  map_info->request_nr is used just like num_flush_requests.
+	 * The number of discard requests that will be submitted to the target.
+	 * The request number can be accessed with dm_bio_get_target_request_nr.
 	 */
 	unsigned num_discard_requests;
 
 	/*
 	 * The number of WRITE SAME requests that will be submitted to the target.
+	 * The request number can be accessed with dm_bio_get_target_request_nr.
 	 */
 	unsigned num_write_same_requests;
 
@@ -263,6 +263,7 @@ struct dm_target_io {
 	struct dm_io *io;
 	struct dm_target *ti;
 	union map_info info;
+	unsigned target_request_nr;
 	struct bio clone;
 };
 
@@ -276,6 +277,11 @@ static inline struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size)
 	return (struct bio *)((char *)data + data_size + offsetof(struct dm_target_io, clone));
 }
 
+static inline unsigned dm_bio_get_target_request_nr(const struct bio *bio)
+{
+	return container_of(bio, struct dm_target_io, clone)->target_request_nr;
+}
+
 int dm_register_target(struct target_type *t);
 void dm_unregister_target(struct target_type *t);
 
-- 
cgit v1.2.3-55-g7522


From 7de3ee57da4b717050e79c9313a9bf66ccc72519 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka
Date: Fri, 21 Dec 2012 20:23:41 +0000
Subject: dm: remove map_info

This patch removes map_info from bio-based device mapper targets.
map_info is still used for request-based targets.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-crypt.c         |  5 ++---
 drivers/md/dm-delay.c         |  5 ++---
 drivers/md/dm-flakey.c        |  6 ++----
 drivers/md/dm-linear.c        |  3 +--
 drivers/md/dm-raid.c          |  4 ++--
 drivers/md/dm-raid1.c         |  6 ++----
 drivers/md/dm-snap.c          | 12 ++++--------
 drivers/md/dm-stripe.c        |  6 ++----
 drivers/md/dm-target.c        |  5 ++---
 drivers/md/dm-thin.c          | 15 +++++----------
 drivers/md/dm-verity.c        |  3 +--
 drivers/md/dm-zero.c          |  5 ++---
 drivers/md/dm.c               |  4 ++--
 include/linux/device-mapper.h |  6 ++----
 14 files changed, 31 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index bbf459bca61d..f7369f9d8595 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1689,8 +1689,7 @@ bad:
 	return ret;
 }
 
-static int crypt_map(struct dm_target *ti, struct bio *bio,
-		     union map_info *map_context)
+static int crypt_map(struct dm_target *ti, struct bio *bio)
 {
 	struct dm_crypt_io *io;
 	struct crypt_config *cc = ti->private;
@@ -1846,7 +1845,7 @@ static int crypt_iterate_devices(struct dm_target *ti,
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 11, 0},
+	.version = {1, 12, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index f53846f9ab50..cc1bd048acb2 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -274,8 +274,7 @@ static void delay_resume(struct dm_target *ti)
 	atomic_set(&dc->may_delay, 1);
 }
 
-static int delay_map(struct dm_target *ti, struct bio *bio,
-		     union map_info *map_context)
+static int delay_map(struct dm_target *ti, struct bio *bio)
 {
 	struct delay_c *dc = ti->private;
 
@@ -338,7 +337,7 @@ out:
 
 static struct target_type delay_target = {
 	.name	     = "delay",
-	.version     = {1, 1, 0},
+	.version     = {1, 2, 0},
 	.module      = THIS_MODULE,
 	.ctr	     = delay_ctr,
 	.dtr	     = delay_dtr,
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 660f98167e7b..9721f2ffb1a2 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -270,8 +270,7 @@ static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
 	}
 }
 
-static int flakey_map(struct dm_target *ti, struct bio *bio,
-		      union map_info *map_context)
+static int flakey_map(struct dm_target *ti, struct bio *bio)
 {
 	struct flakey_c *fc = ti->private;
 	unsigned elapsed;
@@ -321,8 +320,7 @@ map_bio:
 	return DM_MAPIO_REMAPPED;
 }
 
-static int flakey_end_io(struct dm_target *ti, struct bio *bio,
-			 int error, union map_info *map_context)
+static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error)
 {
 	struct flakey_c *fc = ti->private;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 82222a8cf750..328cad5617ab 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -88,8 +88,7 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio)
 		bio->bi_sector = linear_map_sector(ti, bio->bi_sector);
 }
 
-static int linear_map(struct dm_target *ti, struct bio *bio,
-		      union map_info *map_context)
+static int linear_map(struct dm_target *ti, struct bio *bio)
 {
 	linear_map_bio(ti, bio);
 
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 4a20bf8c72da..3d8984edeff7 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1218,7 +1218,7 @@ static void raid_dtr(struct dm_target *ti)
 	context_free(rs);
 }
 
-static int raid_map(struct dm_target *ti, struct bio *bio, union map_info *map_context)
+static int raid_map(struct dm_target *ti, struct bio *bio)
 {
 	struct raid_set *rs = ti->private;
 	struct mddev *mddev = &rs->md;
@@ -1432,7 +1432,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 3, 1},
+	.version = {1, 4, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 57685cf0afa8..fa519185ebba 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1142,8 +1142,7 @@ static void mirror_dtr(struct dm_target *ti)
 /*
  * Mirror mapping function
  */
-static int mirror_map(struct dm_target *ti, struct bio *bio,
-		      union map_info *map_context)
+static int mirror_map(struct dm_target *ti, struct bio *bio)
 {
 	int r, rw = bio_rw(bio);
 	struct mirror *m;
@@ -1192,8 +1191,7 @@ static int mirror_map(struct dm_target *ti, struct bio *bio,
 	return DM_MAPIO_REMAPPED;
 }
 
-static int mirror_end_io(struct dm_target *ti, struct bio *bio,
-			 int error, union map_info *map_context)
+static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 {
 	int rw = bio_rw(bio);
 	struct mirror_set *ms = (struct mirror_set *) ti->private;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index e1ecacf2456f..59fc18ae52c2 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1567,8 +1567,7 @@ static void remap_exception(struct dm_snapshot *s, struct dm_exception *e,
 					  s->store->chunk_mask);
 }
 
-static int snapshot_map(struct dm_target *ti, struct bio *bio,
-			union map_info *map_context)
+static int snapshot_map(struct dm_target *ti, struct bio *bio)
 {
 	struct dm_exception *e;
 	struct dm_snapshot *s = ti->private;
@@ -1683,8 +1682,7 @@ out:
  * If merging is currently taking place on the chunk in question, the
  * I/O is deferred by adding it to s->bios_queued_during_merge.
  */
-static int snapshot_merge_map(struct dm_target *ti, struct bio *bio,
-			      union map_info *map_context)
+static int snapshot_merge_map(struct dm_target *ti, struct bio *bio)
 {
 	struct dm_exception *e;
 	struct dm_snapshot *s = ti->private;
@@ -1744,8 +1742,7 @@ out_unlock:
 	return r;
 }
 
-static int snapshot_end_io(struct dm_target *ti, struct bio *bio,
-			   int error, union map_info *map_context)
+static int snapshot_end_io(struct dm_target *ti, struct bio *bio, int error)
 {
 	struct dm_snapshot *s = ti->private;
 
@@ -2119,8 +2116,7 @@ static void origin_dtr(struct dm_target *ti)
 	dm_put_device(ti, dev);
 }
 
-static int origin_map(struct dm_target *ti, struct bio *bio,
-		      union map_info *map_context)
+static int origin_map(struct dm_target *ti, struct bio *bio)
 {
 	struct dm_dev *dev = ti->private;
 	bio->bi_bdev = dev->bdev;
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 4e7ba82146c0..6b0e5ea38027 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -271,8 +271,7 @@ static int stripe_map_discard(struct stripe_c *sc, struct bio *bio,
 	}
 }
 
-static int stripe_map(struct dm_target *ti, struct bio *bio,
-		      union map_info *map_context)
+static int stripe_map(struct dm_target *ti, struct bio *bio)
 {
 	struct stripe_c *sc = ti->private;
 	uint32_t stripe;
@@ -342,8 +341,7 @@ static int stripe_status(struct dm_target *ti, status_type_t type,
 	return 0;
 }
 
-static int stripe_end_io(struct dm_target *ti, struct bio *bio,
-			 int error, union map_info *map_context)
+static int stripe_end_io(struct dm_target *ti, struct bio *bio, int error)
 {
 	unsigned i;
 	char major_minor[16];
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 8da366cf381c..617d21a77256 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -126,15 +126,14 @@ static void io_err_dtr(struct dm_target *tt)
 	/* empty */
 }
 
-static int io_err_map(struct dm_target *tt, struct bio *bio,
-		      union map_info *map_context)
+static int io_err_map(struct dm_target *tt, struct bio *bio)
 {
 	return -EIO;
 }
 
 static struct target_type error_target = {
 	.name = "error",
-	.version = {1, 0, 1},
+	.version = {1, 1, 0},
 	.ctr  = io_err_ctr,
 	.dtr  = io_err_dtr,
 	.map  = io_err_map,
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index e7743c69a24c..675ae5274016 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -1371,8 +1371,7 @@ static void thin_hook_bio(struct thin_c *tc, struct bio *bio)
 /*
  * Non-blocking function called from the thin target's map function.
  */
-static int thin_bio_map(struct dm_target *ti, struct bio *bio,
-			union map_info *map_context)
+static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 {
 	int r;
 	struct thin_c *tc = ti->private;
@@ -1980,8 +1979,7 @@ out_unlock:
 	return r;
 }
 
-static int pool_map(struct dm_target *ti, struct bio *bio,
-		    union map_info *map_context)
+static int pool_map(struct dm_target *ti, struct bio *bio)
 {
 	int r;
 	struct pool_c *pt = ti->private;
@@ -2626,17 +2624,14 @@ out_unlock:
 	return r;
 }
 
-static int thin_map(struct dm_target *ti, struct bio *bio,
-		    union map_info *map_context)
+static int thin_map(struct dm_target *ti, struct bio *bio)
 {
 	bio->bi_sector = dm_target_offset(ti, bio->bi_sector);
 
-	return thin_bio_map(ti, bio, map_context);
+	return thin_bio_map(ti, bio);
 }
 
-static int thin_endio(struct dm_target *ti,
-		      struct bio *bio, int err,
-		      union map_info *map_context)
+static int thin_endio(struct dm_target *ti, struct bio *bio, int err)
 {
 	unsigned long flags;
 	struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index 78f349894b24..52cde982164a 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -458,8 +458,7 @@ no_prefetch_cluster:
  * Bio map function. It allocates dm_verity_io structure and bio vector and
  * fills them. Then it issues prefetches and the I/O.
  */
-static int verity_map(struct dm_target *ti, struct bio *bio,
-		      union map_info *map_context)
+static int verity_map(struct dm_target *ti, struct bio *bio)
 {
 	struct dm_verity *v = ti->private;
 	struct dm_verity_io *io;
diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c
index cc2b3cb81946..69a5c3b3b340 100644
--- a/drivers/md/dm-zero.c
+++ b/drivers/md/dm-zero.c
@@ -33,8 +33,7 @@ static int zero_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 /*
  * Return zeros only on reads
  */
-static int zero_map(struct dm_target *ti, struct bio *bio,
-		      union map_info *map_context)
+static int zero_map(struct dm_target *ti, struct bio *bio)
 {
 	switch(bio_rw(bio)) {
 	case READ:
@@ -56,7 +55,7 @@ static int zero_map(struct dm_target *ti, struct bio *bio,
 
 static struct target_type zero_target = {
 	.name   = "zero",
-	.version = {1, 0, 0},
+	.version = {1, 1, 0},
 	.module = THIS_MODULE,
 	.ctr    = zero_ctr,
 	.map    = zero_map,
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5ee580b4f330..c72e4d5a9617 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -645,7 +645,7 @@ static void clone_endio(struct bio *bio, int error)
 		error = -EIO;
 
 	if (endio) {
-		r = endio(tio->ti, bio, error, &tio->info);
+		r = endio(tio->ti, bio, error);
 		if (r < 0 || r == DM_ENDIO_REQUEUE)
 			/*
 			 * error and requeue request are handled
@@ -1004,7 +1004,7 @@ static void __map_bio(struct dm_target *ti, struct dm_target_io *tio)
 	 */
 	atomic_inc(&tio->io->io_count);
 	sector = clone->bi_sector;
-	r = ti->type->map(ti, clone, &tio->info);
+	r = ti->type->map(ti, clone);
 	if (r == DM_MAPIO_REMAPPED) {
 		/* the bio has been remapped so dispatch it */
 
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index eb96ef6fd8b7..bf6afa2fc432 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -45,8 +45,7 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti);
  * = 1: simple remap complete
  * = 2: The target wants to push back the io
  */
-typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio,
-			  union map_info *map_context);
+typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio);
 typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone,
 				  union map_info *map_context);
 
@@ -59,8 +58,7 @@ typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone,
  * 2   : The target wants to push back the io
  */
 typedef int (*dm_endio_fn) (struct dm_target *ti,
-			    struct bio *bio, int error,
-			    union map_info *map_context);
+			    struct bio *bio, int error);
 typedef int (*dm_request_endio_fn) (struct dm_target *ti,
 				    struct request *clone, int error,
 				    union map_info *map_context);
-- 
cgit v1.2.3-55-g7522


From 30e6c9fa93cf3dbc7cc6df1d748ad25e4264545a Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Thu, 20 Dec 2012 17:25:08 +0000
Subject: net: devnet_rename_seq should be a seqcount

Using a seqlock for devnet_rename_seq is not a good idea,
as device_rename() can sleep.

As we hold RTNL, we dont need a protection for writers,
and only need a seqcount so that readers can catch a change done
by a writer.

Bug added in commit c91f6df2db4972d3 (sockopt: Change getsockopt() of
SO_BINDTODEVICE to return an interface name)

Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Brian Haley <brian.haley@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 +-
 net/core/dev.c            | 18 +++++++++---------
 net/core/sock.c           |  4 ++--
 3 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 02e0f6b156c3..c599e4782d45 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1576,7 +1576,7 @@ extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
 
 extern rwlock_t				dev_base_lock;		/* Device list lock */
 
-extern seqlock_t	devnet_rename_seq;	/* Device rename lock */
+extern seqcount_t	devnet_rename_seq;	/* Device rename seq */
 
 
 #define for_each_netdev(net, d)		\
diff --git a/net/core/dev.c b/net/core/dev.c
index d0cbc93fcf32..515473ee52cb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -203,7 +203,7 @@ static struct list_head offload_base __read_mostly;
 DEFINE_RWLOCK(dev_base_lock);
 EXPORT_SYMBOL(dev_base_lock);
 
-DEFINE_SEQLOCK(devnet_rename_seq);
+seqcount_t devnet_rename_seq;
 
 static inline void dev_base_seq_inc(struct net *net)
 {
@@ -1093,10 +1093,10 @@ int dev_change_name(struct net_device *dev, const char *newname)
 	if (dev->flags & IFF_UP)
 		return -EBUSY;
 
-	write_seqlock(&devnet_rename_seq);
+	write_seqcount_begin(&devnet_rename_seq);
 
 	if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
-		write_sequnlock(&devnet_rename_seq);
+		write_seqcount_end(&devnet_rename_seq);
 		return 0;
 	}
 
@@ -1104,7 +1104,7 @@ int dev_change_name(struct net_device *dev, const char *newname)
 
 	err = dev_get_valid_name(net, dev, newname);
 	if (err < 0) {
-		write_sequnlock(&devnet_rename_seq);
+		write_seqcount_end(&devnet_rename_seq);
 		return err;
 	}
 
@@ -1112,11 +1112,11 @@ rollback:
 	ret = device_rename(&dev->dev, dev->name);
 	if (ret) {
 		memcpy(dev->name, oldname, IFNAMSIZ);
-		write_sequnlock(&devnet_rename_seq);
+		write_seqcount_end(&devnet_rename_seq);
 		return ret;
 	}
 
-	write_sequnlock(&devnet_rename_seq);
+	write_seqcount_end(&devnet_rename_seq);
 
 	write_lock_bh(&dev_base_lock);
 	hlist_del_rcu(&dev->name_hlist);
@@ -1135,7 +1135,7 @@ rollback:
 		/* err >= 0 after dev_alloc_name() or stores the first errno */
 		if (err >= 0) {
 			err = ret;
-			write_seqlock(&devnet_rename_seq);
+			write_seqcount_begin(&devnet_rename_seq);
 			memcpy(dev->name, oldname, IFNAMSIZ);
 			goto rollback;
 		} else {
@@ -4180,7 +4180,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
 		return -EFAULT;
 
 retry:
-	seq = read_seqbegin(&devnet_rename_seq);
+	seq = read_seqcount_begin(&devnet_rename_seq);
 	rcu_read_lock();
 	dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex);
 	if (!dev) {
@@ -4190,7 +4190,7 @@ retry:
 
 	strcpy(ifr.ifr_name, dev->name);
 	rcu_read_unlock();
-	if (read_seqretry(&devnet_rename_seq, seq))
+	if (read_seqcount_retry(&devnet_rename_seq, seq))
 		goto retry;
 
 	if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
diff --git a/net/core/sock.c b/net/core/sock.c
index a692ef49c9bb..bc131d419683 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -583,7 +583,7 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval,
 		goto out;
 
 retry:
-	seq = read_seqbegin(&devnet_rename_seq);
+	seq = read_seqcount_begin(&devnet_rename_seq);
 	rcu_read_lock();
 	dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
 	ret = -ENODEV;
@@ -594,7 +594,7 @@ retry:
 
 	strcpy(devname, dev->name);
 	rcu_read_unlock();
-	if (read_seqretry(&devnet_rename_seq, seq))
+	if (read_seqcount_retry(&devnet_rename_seq, seq))
 		goto retry;
 
 	len = strlen(devname) + 1;
-- 
cgit v1.2.3-55-g7522


From 10db9069eb5c60195170a4119bdbcbce69a4945f Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Thu, 20 Dec 2012 01:54:51 +0000
Subject: netfilter: xt_CT: recover NOTRACK target support

Florian Westphal reported that the removal of the NOTRACK target
(9655050 netfilter: remove xt_NOTRACK) is breaking some existing
setups.

That removal was scheduled for removal since long time ago as
described in Documentation/feature-removal-schedule.txt

What:  xt_NOTRACK
Files: net/netfilter/xt_NOTRACK.c
When:  April 2011
Why:   Superseded by xt_CT

Still, people may have not notice / may have decided to stick to an
old iptables version. I agree with him in that some more conservative
approach by spotting some printk to warn users for some time is less
agressive.

Current iptables 1.4.16.3 already contains the aliasing support
that makes it point to the CT target, so upgrading would fix it.
Still, the policy so far has been to avoid pushing our users to
upgrade.

As a solution, this patch recovers the NOTRACK target inside the CT
target and it now spots a warning.

Reported-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netns/x_tables.h |  1 +
 net/netfilter/Kconfig        |  4 ++++
 net/netfilter/xt_CT.c        | 50 +++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 54 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/netns/x_tables.h b/include/net/netns/x_tables.h
index 591db7d657a3..c24060ee411e 100644
--- a/include/net/netns/x_tables.h
+++ b/include/net/netns/x_tables.h
@@ -8,6 +8,7 @@ struct ebt_table;
 
 struct netns_xt {
 	struct list_head tables[NFPROTO_NUMPROTO];
+	bool notrack_deprecated_warning;
 #if defined(CONFIG_BRIDGE_NF_EBTABLES) || \
     defined(CONFIG_BRIDGE_NF_EBTABLES_MODULE)
 	struct ebt_table *broute_table;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index fefa514b9917..390f96cc8ed4 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -680,6 +680,10 @@ config NETFILTER_XT_TARGET_NFQUEUE
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NETFILTER_XT_TARGET_NOTRACK
+	tristate  '"NOTRACK" target support (DEPRECATED)'
+	select NETFILTER_XT_TARGET_CT
+
 config NETFILTER_XT_TARGET_RATEEST
 	tristate '"RATEEST" target support'
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 1668f41acc6e..2a0843081840 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -385,14 +385,60 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = {
 	},
 };
 
+static unsigned int
+notrack_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	/* Previously seen (loopback)? Ignore. */
+	if (skb->nfct != NULL)
+		return XT_CONTINUE;
+
+	skb->nfct = &nf_ct_untracked_get()->ct_general;
+	skb->nfctinfo = IP_CT_NEW;
+	nf_conntrack_get(skb->nfct);
+
+	return XT_CONTINUE;
+}
+
+static int notrack_chk(const struct xt_tgchk_param *par)
+{
+	if (!par->net->xt.notrack_deprecated_warning) {
+		pr_info("netfilter: NOTRACK target is deprecated, "
+			"use CT instead or upgrade iptables\n");
+		par->net->xt.notrack_deprecated_warning = true;
+	}
+	return 0;
+}
+
+static struct xt_target notrack_tg_reg __read_mostly = {
+	.name		= "NOTRACK",
+	.revision	= 0,
+	.family		= NFPROTO_UNSPEC,
+	.checkentry	= notrack_chk,
+	.target		= notrack_tg,
+	.table		= "raw",
+	.me		= THIS_MODULE,
+};
+
 static int __init xt_ct_tg_init(void)
 {
-	return xt_register_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg));
+	int ret;
+
+	ret = xt_register_target(&notrack_tg_reg);
+	if (ret < 0)
+		return ret;
+
+	ret = xt_register_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg));
+	if (ret < 0) {
+		xt_unregister_target(&notrack_tg_reg);
+		return ret;
+	}
+	return 0;
 }
 
 static void __exit xt_ct_tg_exit(void)
 {
 	xt_unregister_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg));
+	xt_unregister_target(&notrack_tg_reg);
 }
 
 module_init(xt_ct_tg_init);
@@ -402,3 +448,5 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Xtables: connection tracking target");
 MODULE_ALIAS("ipt_CT");
 MODULE_ALIAS("ip6t_CT");
+MODULE_ALIAS("ipt_NOTRACK");
+MODULE_ALIAS("ip6t_NOTRACK");
-- 
cgit v1.2.3-55-g7522


From 4520fb3c3690f2643006d85f09ecb74554c10e95 Mon Sep 17 00:00:00 2001
From: Jan Kara
Date: Tue, 25 Dec 2012 13:28:54 -0500
Subject: ext4: split off ext4_journalled_invalidatepage()

In data=journal mode we don't need delalloc or DIO handling in invalidatepage
and similarly in other modes we don't need the journal handling. So split
invalidatepage implementations.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c             | 23 ++++++++++++++++-------
 include/trace/events/ext4.h | 14 +++++++++++++-
 2 files changed, 29 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index cb1c1ab2720b..12d3fbcff59f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2880,8 +2880,6 @@ static void ext4_invalidatepage_free_endio(struct page *page, unsigned long offs
 
 static void ext4_invalidatepage(struct page *page, unsigned long offset)
 {
-	journal_t *journal = EXT4_JOURNAL(page->mapping->host);
-
 	trace_ext4_invalidatepage(page, offset);
 
 	/*
@@ -2889,16 +2887,27 @@ static void ext4_invalidatepage(struct page *page, unsigned long offset)
 	 */
 	if (ext4_should_dioread_nolock(page->mapping->host))
 		ext4_invalidatepage_free_endio(page, offset);
+
+	/* No journalling happens on data buffers when this function is used */
+	WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page)));
+
+	block_invalidatepage(page, offset);
+}
+
+static void ext4_journalled_invalidatepage(struct page *page,
+					   unsigned long offset)
+{
+	journal_t *journal = EXT4_JOURNAL(page->mapping->host);
+
+	trace_ext4_journalled_invalidatepage(page, offset);
+
 	/*
 	 * If it's a full truncate we just forget about the pending dirtying
 	 */
 	if (offset == 0)
 		ClearPageChecked(page);
 
-	if (journal)
-		jbd2_journal_invalidatepage(journal, page, offset);
-	else
-		block_invalidatepage(page, offset);
+	jbd2_journal_invalidatepage(journal, page, offset);
 }
 
 static int ext4_releasepage(struct page *page, gfp_t wait)
@@ -3264,7 +3273,7 @@ static const struct address_space_operations ext4_journalled_aops = {
 	.write_end		= ext4_journalled_write_end,
 	.set_page_dirty		= ext4_journalled_set_page_dirty,
 	.bmap			= ext4_bmap,
-	.invalidatepage		= ext4_invalidatepage,
+	.invalidatepage		= ext4_journalled_invalidatepage,
 	.releasepage		= ext4_releasepage,
 	.direct_IO		= ext4_direct_IO,
 	.is_partially_uptodate  = block_is_partially_uptodate,
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index f6372b011366..7e8c36bc7082 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -451,7 +451,7 @@ DEFINE_EVENT(ext4__page_op, ext4_releasepage,
 	TP_ARGS(page)
 );
 
-TRACE_EVENT(ext4_invalidatepage,
+DECLARE_EVENT_CLASS(ext4_invalidatepage_op,
 	TP_PROTO(struct page *page, unsigned long offset),
 
 	TP_ARGS(page, offset),
@@ -477,6 +477,18 @@ TRACE_EVENT(ext4_invalidatepage,
 		  (unsigned long) __entry->index, __entry->offset)
 );
 
+DEFINE_EVENT(ext4_invalidatepage_op, ext4_invalidatepage,
+	TP_PROTO(struct page *page, unsigned long offset),
+
+	TP_ARGS(page, offset)
+);
+
+DEFINE_EVENT(ext4_invalidatepage_op, ext4_journalled_invalidatepage,
+	TP_PROTO(struct page *page, unsigned long offset),
+
+	TP_ARGS(page, offset)
+);
+
 TRACE_EVENT(ext4_discard_blocks,
 	TP_PROTO(struct super_block *sb, unsigned long long blk,
 			unsigned long long count),
-- 
cgit v1.2.3-55-g7522


From 53e872681fed6a43047e71bf927f77d06f467988 Mon Sep 17 00:00:00 2001
From: Jan Kara
Date: Tue, 25 Dec 2012 13:29:52 -0500
Subject: ext4: fix deadlock in journal_unmap_buffer()

We cannot wait for transaction commit in journal_unmap_buffer()
because we hold page lock which ranks below transaction start.  We
solve the issue by bailing out of journal_unmap_buffer() and
jbd2_journal_invalidatepage() with -EBUSY.  Caller is then responsible
for waiting for transaction commit to finish and try invalidation
again. Since the issue can happen only for page stradding i_size, it
is simple enough to manually call jbd2_journal_invalidatepage() for
such page from ext4_setattr(), check the return value and wait if
necessary.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c       | 82 ++++++++++++++++++++++++++++++++++++++++++++-------
 fs/jbd2/transaction.c | 27 +++++++++--------
 include/linux/jbd2.h  |  2 +-
 3 files changed, 86 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 12d3fbcff59f..cbfe13bf5b2a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2894,8 +2894,8 @@ static void ext4_invalidatepage(struct page *page, unsigned long offset)
 	block_invalidatepage(page, offset);
 }
 
-static void ext4_journalled_invalidatepage(struct page *page,
-					   unsigned long offset)
+static int __ext4_journalled_invalidatepage(struct page *page,
+					    unsigned long offset)
 {
 	journal_t *journal = EXT4_JOURNAL(page->mapping->host);
 
@@ -2907,7 +2907,14 @@ static void ext4_journalled_invalidatepage(struct page *page,
 	if (offset == 0)
 		ClearPageChecked(page);
 
-	jbd2_journal_invalidatepage(journal, page, offset);
+	return jbd2_journal_invalidatepage(journal, page, offset);
+}
+
+/* Wrapper for aops... */
+static void ext4_journalled_invalidatepage(struct page *page,
+					   unsigned long offset)
+{
+	WARN_ON(__ext4_journalled_invalidatepage(page, offset) < 0);
 }
 
 static int ext4_releasepage(struct page *page, gfp_t wait)
@@ -4313,6 +4320,47 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
 	return err;
 }
 
+/*
+ * In data=journal mode ext4_journalled_invalidatepage() may fail to invalidate
+ * buffers that are attached to a page stradding i_size and are undergoing
+ * commit. In that case we have to wait for commit to finish and try again.
+ */
+static void ext4_wait_for_tail_page_commit(struct inode *inode)
+{
+	struct page *page;
+	unsigned offset;
+	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+	tid_t commit_tid = 0;
+	int ret;
+
+	offset = inode->i_size & (PAGE_CACHE_SIZE - 1);
+	/*
+	 * All buffers in the last page remain valid? Then there's nothing to
+	 * do. We do the check mainly to optimize the common PAGE_CACHE_SIZE ==
+	 * blocksize case
+	 */
+	if (offset > PAGE_CACHE_SIZE - (1 << inode->i_blkbits))
+		return;
+	while (1) {
+		page = find_lock_page(inode->i_mapping,
+				      inode->i_size >> PAGE_CACHE_SHIFT);
+		if (!page)
+			return;
+		ret = __ext4_journalled_invalidatepage(page, offset);
+		unlock_page(page);
+		page_cache_release(page);
+		if (ret != -EBUSY)
+			return;
+		commit_tid = 0;
+		read_lock(&journal->j_state_lock);
+		if (journal->j_committing_transaction)
+			commit_tid = journal->j_committing_transaction->t_tid;
+		read_unlock(&journal->j_state_lock);
+		if (commit_tid)
+			jbd2_log_wait_commit(journal, commit_tid);
+	}
+}
+
 /*
  * ext4_setattr()
  *
@@ -4426,16 +4474,28 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
-		if (attr->ia_size != i_size_read(inode)) {
-			truncate_setsize(inode, attr->ia_size);
-			/* Inode size will be reduced, wait for dio in flight.
-			 * Temporarily disable dioread_nolock to prevent
-			 * livelock. */
+		if (attr->ia_size != inode->i_size) {
+			loff_t oldsize = inode->i_size;
+
+			i_size_write(inode, attr->ia_size);
+			/*
+			 * Blocks are going to be removed from the inode. Wait
+			 * for dio in flight.  Temporarily disable
+			 * dioread_nolock to prevent livelock.
+			 */
 			if (orphan) {
-				ext4_inode_block_unlocked_dio(inode);
-				inode_dio_wait(inode);
-				ext4_inode_resume_unlocked_dio(inode);
+				if (!ext4_should_journal_data(inode)) {
+					ext4_inode_block_unlocked_dio(inode);
+					inode_dio_wait(inode);
+					ext4_inode_resume_unlocked_dio(inode);
+				} else
+					ext4_wait_for_tail_page_commit(inode);
 			}
+			/*
+			 * Truncate pagecache after we've waited for commit
+			 * in data=journal mode to make pages freeable.
+			 */
+			truncate_pagecache(inode, oldsize, inode->i_size);
 		}
 		ext4_truncate(inode);
 	}
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index cd4485db42b3..ddc51a7f4508 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1840,7 +1840,6 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 
 	BUFFER_TRACE(bh, "entry");
 
-retry:
 	/*
 	 * It is safe to proceed here without the j_list_lock because the
 	 * buffers cannot be stolen by try_to_free_buffers as long as we are
@@ -1935,14 +1934,11 @@ retry:
 		 * for commit and try again.
 		 */
 		if (partial_page) {
-			tid_t tid = journal->j_committing_transaction->t_tid;
-
 			jbd2_journal_put_journal_head(jh);
 			spin_unlock(&journal->j_list_lock);
 			jbd_unlock_bh_state(bh);
 			write_unlock(&journal->j_state_lock);
-			jbd2_log_wait_commit(journal, tid);
-			goto retry;
+			return -EBUSY;
 		}
 		/*
 		 * OK, buffer won't be reachable after truncate. We just set
@@ -2003,21 +1999,23 @@ zap_buffer_unlocked:
  * @page:    page to flush
  * @offset:  length of page to invalidate.
  *
- * Reap page buffers containing data after offset in page.
- *
+ * Reap page buffers containing data after offset in page. Can return -EBUSY
+ * if buffers are part of the committing transaction and the page is straddling
+ * i_size. Caller then has to wait for current commit and try again.
  */
-void jbd2_journal_invalidatepage(journal_t *journal,
-		      struct page *page,
-		      unsigned long offset)
+int jbd2_journal_invalidatepage(journal_t *journal,
+				struct page *page,
+				unsigned long offset)
 {
 	struct buffer_head *head, *bh, *next;
 	unsigned int curr_off = 0;
 	int may_free = 1;
+	int ret = 0;
 
 	if (!PageLocked(page))
 		BUG();
 	if (!page_has_buffers(page))
-		return;
+		return 0;
 
 	/* We will potentially be playing with lists other than just the
 	 * data lists (especially for journaled data mode), so be
@@ -2031,9 +2029,11 @@ void jbd2_journal_invalidatepage(journal_t *journal,
 		if (offset <= curr_off) {
 			/* This block is wholly outside the truncation point */
 			lock_buffer(bh);
-			may_free &= journal_unmap_buffer(journal, bh,
-							 offset > 0);
+			ret = journal_unmap_buffer(journal, bh, offset > 0);
 			unlock_buffer(bh);
+			if (ret < 0)
+				return ret;
+			may_free &= ret;
 		}
 		curr_off = next_off;
 		bh = next;
@@ -2044,6 +2044,7 @@ void jbd2_journal_invalidatepage(journal_t *journal,
 		if (may_free && try_to_free_buffers(page))
 			J_ASSERT(!page_has_buffers(page));
 	}
+	return 0;
 }
 
 /*
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 1be23d9fdacb..e30b66346942 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1098,7 +1098,7 @@ void		 jbd2_journal_set_triggers(struct buffer_head *,
 extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
 extern void	 journal_sync_buffer (struct buffer_head *);
-extern void	 jbd2_journal_invalidatepage(journal_t *,
+extern int	 jbd2_journal_invalidatepage(journal_t *,
 				struct page *, unsigned long);
 extern int	 jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t);
 extern int	 jbd2_journal_stop(handle_t *);
-- 
cgit v1.2.3-55-g7522


From aaf4f97f267aa0dbc42f089b33325e61aac8622e Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven
Date: Sun, 16 Dec 2012 18:27:33 +0100
Subject: asm-generic/dma-mapping-broken.h: Provide
 dma_alloc_attrs()/dma_free_attrs()

Since commit 0049fb2603b7afb1080776ee691dfa5a3d282357 ("OMAPFB: use
dma_alloc_attrs to allocate memory") we have one non-arch user of
dma_{alloc,free}_attrs().

Hence provide these functions, as wrappers around
dma_{alloc,free}_coherent().

Note that most architectures do it the other way around. But as these are
dummy functions, we don't care.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
---
 include/asm-generic/dma-mapping-broken.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/dma-mapping-broken.h b/include/asm-generic/dma-mapping-broken.h
index ccf7b4f34a3c..6c32af918c2f 100644
--- a/include/asm-generic/dma-mapping-broken.h
+++ b/include/asm-generic/dma-mapping-broken.h
@@ -16,6 +16,22 @@ extern void
 dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
 		    dma_addr_t dma_handle);
 
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
+{
+	/* attrs is not supported and ignored */
+	return dma_alloc_coherent(dev, size, dma_handle, flag);
+}
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
+{
+	/* attrs is not supported and ignored */
+	dma_free_coherent(dev, size, cpu_addr, dma_handle);
+}
+
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
-- 
cgit v1.2.3-55-g7522


From 08b60f8438879a84246d7debded31c9cb7aea6e4 Mon Sep 17 00:00:00 2001
From: Stephen Warren
Date: Mon, 24 Dec 2012 11:14:58 -0700
Subject: namei.h: include errno.h

This solves:

In file included from fs/ext3/symlink.c:20:0:
include/linux/namei.h: In function 'retry_estale':
include/linux/namei.h:114:19: error: 'ESTALE' undeclared (first use in this function)

Signed-off-by: Stephen Warren <swarren@wwwdotorg.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/namei.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/namei.h b/include/linux/namei.h
index e998c030061d..5a5ff57ceed4 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -2,6 +2,7 @@
 #define _LINUX_NAMEI_H
 
 #include <linux/dcache.h>
+#include <linux/errno.h>
 #include <linux/linkage.h>
 #include <linux/path.h>
 
-- 
cgit v1.2.3-55-g7522


From c876ad7682155958d0c9c27afe9017925c230d64 Mon Sep 17 00:00:00 2001
From: Eric W. Biederman
Date: Fri, 21 Dec 2012 20:27:12 -0800
Subject: pidns: Stop pid allocation when init dies

Oleg pointed out that in a pid namespace the sequence.
- pid 1 becomes a zombie
- setns(thepidns), fork,...
- reaping pid 1.
- The injected processes exiting.

Can lead to processes attempting access their child reaper and
instead following a stale pointer.

That waitpid for init can return before all of the processes in
the pid namespace have exited is also unfortunate.

Avoid these problems by disabling the allocation of new pids in a pid
namespace when init dies, instead of when the last process in a pid
namespace is reaped.

Pointed-out-by:  Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/pid.h           |  1 +
 include/linux/pid_namespace.h |  4 +++-
 kernel/pid.c                  | 15 ++++++++++++---
 kernel/pid_namespace.c        |  4 ++++
 4 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/pid.h b/include/linux/pid.h
index b152d44fb181..2381c973d897 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -121,6 +121,7 @@ int next_pidmap(struct pid_namespace *pid_ns, unsigned int last);
 
 extern struct pid *alloc_pid(struct pid_namespace *ns);
 extern void free_pid(struct pid *pid);
+extern void disable_pid_allocation(struct pid_namespace *ns);
 
 /*
  * ns_of_pid() returns the pid namespace in which the specified pid was
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index bf285999273a..215e5e3dda10 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -21,7 +21,7 @@ struct pid_namespace {
 	struct kref kref;
 	struct pidmap pidmap[PIDMAP_ENTRIES];
 	int last_pid;
-	int nr_hashed;
+	unsigned int nr_hashed;
 	struct task_struct *child_reaper;
 	struct kmem_cache *pid_cachep;
 	unsigned int level;
@@ -42,6 +42,8 @@ struct pid_namespace {
 
 extern struct pid_namespace init_pid_ns;
 
+#define PIDNS_HASH_ADDING (1U << 31)
+
 #ifdef CONFIG_PID_NS
 static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 {
diff --git a/kernel/pid.c b/kernel/pid.c
index 36aa02ff17d6..de9af600006f 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -270,7 +270,6 @@ void free_pid(struct pid *pid)
 			wake_up_process(ns->child_reaper);
 			break;
 		case 0:
-			ns->nr_hashed = -1;
 			schedule_work(&ns->proc_work);
 			break;
 		}
@@ -319,7 +318,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 
 	upid = pid->numbers + ns->level;
 	spin_lock_irq(&pidmap_lock);
-	if (ns->nr_hashed < 0)
+	if (!(ns->nr_hashed & PIDNS_HASH_ADDING))
 		goto out_unlock;
 	for ( ; upid >= pid->numbers; --upid) {
 		hlist_add_head_rcu(&upid->pid_chain,
@@ -342,6 +341,13 @@ out_free:
 	goto out;
 }
 
+void disable_pid_allocation(struct pid_namespace *ns)
+{
+	spin_lock_irq(&pidmap_lock);
+	ns->nr_hashed &= ~PIDNS_HASH_ADDING;
+	spin_unlock_irq(&pidmap_lock);
+}
+
 struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
 {
 	struct hlist_node *elem;
@@ -573,6 +579,9 @@ void __init pidhash_init(void)
 
 void __init pidmap_init(void)
 {
+	/* Veryify no one has done anything silly */
+	BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING);
+
 	/* bump default and minimum pid_max based on number of cpus */
 	pid_max = min(pid_max_max, max_t(int, pid_max,
 				PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
@@ -584,7 +593,7 @@ void __init pidmap_init(void)
 	/* Reserve PID 0. We never call free_pidmap(0) */
 	set_bit(0, init_pid_ns.pidmap[0].page);
 	atomic_dec(&init_pid_ns.pidmap[0].nr_free);
-	init_pid_ns.nr_hashed = 1;
+	init_pid_ns.nr_hashed = PIDNS_HASH_ADDING;
 
 	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
 			SLAB_HWCACHE_ALIGN | SLAB_PANIC);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index fdbd0cdf271a..c1c3dc1c6023 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -115,6 +115,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	ns->level = level;
 	ns->parent = get_pid_ns(parent_pid_ns);
 	ns->user_ns = get_user_ns(user_ns);
+	ns->nr_hashed = PIDNS_HASH_ADDING;
 	INIT_WORK(&ns->proc_work, proc_cleanup_work);
 
 	set_bit(0, ns->pidmap[0].page);
@@ -181,6 +182,9 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	int rc;
 	struct task_struct *task, *me = current;
 
+	/* Don't allow any more processes into the pid namespace */
+	disable_pid_allocation(pid_ns);
+
 	/* Ignore SIGCHLD causing any terminated children to autoreap */
 	spin_lock_irq(&me->sighand->siglock);
 	me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN;
-- 
cgit v1.2.3-55-g7522


From f13a3664e4d1de8adc1fc82b981ba4699a731fa1 Mon Sep 17 00:00:00 2001
From: Vineet Gupta
Date: Mon, 24 Dec 2012 10:51:36 +0530
Subject: CONFIG_GENERIC_SIGALTSTACK build breakage with asm-generic/syscalls.h

Saner transition plan for GENERIC_SIGALTSTACK conversion - instead of
adding #define sys_sigaltstack sys_sigaltstack in asm/syscalls.h of
architecture if it's pulls asm-generic/syscalls.h, only to have those
defines removed once all architectures are converted, make the
declaration in said asm-generic/syscalls.h conditional on the lack
of GENERIC_SIGALTSTACK.  Less messy in intermediate stages that way...

Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: james.hogan@imgtec.com
Cc: arnd@arndb.de
Cc: torvalds@linux-foundation.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/asm-generic/syscalls.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/syscalls.h b/include/asm-generic/syscalls.h
index 58f466ff00d3..1db51b8524e9 100644
--- a/include/asm-generic/syscalls.h
+++ b/include/asm-generic/syscalls.h
@@ -21,10 +21,12 @@ asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
 			unsigned long fd, off_t pgoff);
 #endif
 
+#ifndef CONFIG_GENERIC_SIGALTSTACK
 #ifndef sys_sigaltstack
 asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
 			struct pt_regs *);
 #endif
+#endif
 
 #ifndef sys_rt_sigreturn
 asmlinkage long sys_rt_sigreturn(struct pt_regs *regs);
-- 
cgit v1.2.3-55-g7522


From 130f1b8f35f14d27c43da755f3c9226318c17f57 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas
Date: Wed, 26 Dec 2012 10:39:23 -0700
Subject: PCI: Add PCIe Link Capability link speed and width names

Add standard #defines for the Supported Link Speeds field in the PCIe
Link Capabilities register.

Note that prior to PCIe spec r3.0, these encodings were defined:

    0001b  2.5GT/s Link speed supported
    0010b  5.0GT/s and 2.5GT/s Link speed supported

Starting with spec r3.0, these encodings refer to bits 0 and 1 in the
Supported Link Speeds Vector in the Link Capabilities 2 register, and bits
0 and 1 there mean 2.5 GT/s and 5.0 GT/s, respectively.  Therefore, code
that followed r2.0 and interpreted 0x1 as 2.5GT/s and 0x2 as 5.0GT/s will
continue to work, and we can identify a device using the new encodings
because it will have a non-zero Link Capabilities 2 register.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/uapi/linux/pci_regs.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 6b7b6f1e2fd6..ebfadc56d1b4 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -458,6 +458,8 @@
 #define  PCI_EXP_DEVSTA_TRPND	0x20	/* Transactions Pending */
 #define PCI_EXP_LNKCAP		12	/* Link Capabilities */
 #define  PCI_EXP_LNKCAP_SLS	0x0000000f /* Supported Link Speeds */
+#define  PCI_EXP_LNKCAP_SLS_2_5GB 0x1	/* LNKCAP2 SLS Vector bit 0 (2.5GT/s) */
+#define  PCI_EXP_LNKCAP_SLS_5_0GB 0x2	/* LNKCAP2 SLS Vector bit 1 (5.0GT/s) */
 #define  PCI_EXP_LNKCAP_MLW	0x000003f0 /* Maximum Link Width */
 #define  PCI_EXP_LNKCAP_ASPMS	0x00000c00 /* ASPM Support */
 #define  PCI_EXP_LNKCAP_L0SEL	0x00007000 /* L0s Exit Latency */
-- 
cgit v1.2.3-55-g7522


From 812089e01b9f65f90fc8fc670d8cce72a0e01fbb Mon Sep 17 00:00:00 2001
From: Andy Lutomirski
Date: Sat, 1 Dec 2012 12:37:20 -0800
Subject: PCI: Reduce Ricoh 0xe822 SD card reader base clock frequency to 50MHz

Otherwise it fails like this on cards like the Transcend 16GB SDHC card:

    mmc0: new SDHC card at address b368
    mmcblk0: mmc0:b368 SDC   15.0 GiB
    mmcblk0: error -110 sending status command, retrying
    mmcblk0: error -84 transferring data, sector 0, nr 8, cmd response 0x900, card status 0xb0

Tested on my Lenovo x200 laptop.

[bhelgaas: changelog]
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Chris Ball <cjb@laptop.org>
CC: Manoj Iyer <manoj.iyer@canonical.com>
CC: stable@vger.kernel.org---
 drivers/pci/quirks.c    | 7 +++++--
 include/linux/pci_ids.h | 1 +
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 8f7a6344e79e..0369fb6fc1da 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2725,7 +2725,7 @@ static void ricoh_mmc_fixup_r5c832(struct pci_dev *dev)
 	if (PCI_FUNC(dev->devfn))
 		return;
 	/*
-	 * RICOH 0xe823 SD/MMC card reader fails to recognize
+	 * RICOH 0xe822 and 0xe823 SD/MMC card readers fail to recognize
 	 * certain types of SD/MMC cards. Lowering the SD base
 	 * clock frequency from 200Mhz to 50Mhz fixes this issue.
 	 *
@@ -2736,7 +2736,8 @@ static void ricoh_mmc_fixup_r5c832(struct pci_dev *dev)
 	 * 0xf9  - Key register for 0x150
 	 * 0xfc  - key register for 0xe1
 	 */
-	if (dev->device == PCI_DEVICE_ID_RICOH_R5CE823) {
+	if (dev->device == PCI_DEVICE_ID_RICOH_R5CE822 ||
+	    dev->device == PCI_DEVICE_ID_RICOH_R5CE823) {
 		pci_write_config_byte(dev, 0xf9, 0xfc);
 		pci_write_config_byte(dev, 0x150, 0x10);
 		pci_write_config_byte(dev, 0xf9, 0x00);
@@ -2763,6 +2764,8 @@ static void ricoh_mmc_fixup_r5c832(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
 DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE822, ricoh_mmc_fixup_r5c832);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE822, ricoh_mmc_fixup_r5c832);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_mmc_fixup_r5c832);
 DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_mmc_fixup_r5c832);
 #endif /*CONFIG_MMC_RICOH_MMC*/
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 0f8447376ddb..0eb65796bcb9 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1568,6 +1568,7 @@
 #define PCI_DEVICE_ID_RICOH_RL5C476	0x0476
 #define PCI_DEVICE_ID_RICOH_RL5C478	0x0478
 #define PCI_DEVICE_ID_RICOH_R5C822	0x0822
+#define PCI_DEVICE_ID_RICOH_R5CE822	0xe822
 #define PCI_DEVICE_ID_RICOH_R5CE823	0xe823
 #define PCI_DEVICE_ID_RICOH_R5C832	0x0832
 #define PCI_DEVICE_ID_RICOH_R5C843	0x0843
-- 
cgit v1.2.3-55-g7522


From 3d0dcfbd8fa2a1e63fabb5f8edac8b8a27860d98 Mon Sep 17 00:00:00 2001
From: Li Zefan
Date: Tue, 25 Dec 2012 20:48:24 +0000
Subject: netprio_cgroup: define sk_cgrp_prioidx only if NETPRIO_CGROUP is
 enabled

sock->sk_cgrp_prioidx won't be used at all if CONFIG_NETPRIO_CGROUP=n.

Signed-off-by: Li Zefan <lizefan@huawei.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 93a6745bfdb2..182ca99405ad 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -367,7 +367,7 @@ struct sock {
 	unsigned short		sk_ack_backlog;
 	unsigned short		sk_max_ack_backlog;
 	__u32			sk_priority;
-#ifdef CONFIG_CGROUPS
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
 	__u32			sk_cgrp_prioidx;
 #endif
 	struct pid		*sk_peer_pid;
-- 
cgit v1.2.3-55-g7522


From ad4b3fb7ff9940bcdb1e4cd62bd189d10fa636ba Mon Sep 17 00:00:00 2001
From: Christoffer Dall
Date: Fri, 21 Dec 2012 13:03:50 -0500
Subject: mm: Fix PageHead when !CONFIG_PAGEFLAGS_EXTENDED

Unfortunately with !CONFIG_PAGEFLAGS_EXTENDED, (!PageHead) is false, and
(PageHead) is true, for tail pages.  If this is indeed the intended
behavior, which I doubt because it breaks cache cleaning on some ARM
systems, then the nomenclature is highly problematic.

This patch makes sure PageHead is only true for head pages and PageTail
is only true for tail pages, and neither is true for non-compound pages.

[ This buglet seems ancient - seems to have been introduced back in Apr
  2008 in commit 6a1e7f777f61: "pageflags: convert to the use of new
  macros".  And the reason nobody noticed is because the PageHead()
  tests are almost all about just sanity-checking, and only used on
  pages that are actual page heads.  The fact that the old code returned
  true for tail pages too was thus not really noticeable.   - Linus ]

Signed-off-by: Christoffer Dall <cdall@cs.columbia.edu>
Acked-by:  Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Will Deacon <Will.Deacon@arm.com>
Cc: Steve Capper <Steve.Capper@arm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: stable@kernel.org  # 2.6.26+
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index b5d13841604e..70473da47b3f 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -362,7 +362,7 @@ static inline void ClearPageCompound(struct page *page)
  * pages on the LRU and/or pagecache.
  */
 TESTPAGEFLAG(Compound, compound)
-__PAGEFLAG(Head, compound)
+__SETPAGEFLAG(Head, compound)  __CLEARPAGEFLAG(Head, compound)
 
 /*
  * PG_reclaim is used in combination with PG_compound to mark the
@@ -374,8 +374,14 @@ __PAGEFLAG(Head, compound)
  * PG_compound & PG_reclaim	=> Tail page
  * PG_compound & ~PG_reclaim	=> Head page
  */
+#define PG_head_mask ((1L << PG_compound))
 #define PG_head_tail_mask ((1L << PG_compound) | (1L << PG_reclaim))
 
+static inline int PageHead(struct page *page)
+{
+	return ((page->flags & PG_head_tail_mask) == PG_head_mask);
+}
+
 static inline int PageTail(struct page *page)
 {
 	return ((page->flags & PG_head_tail_mask) == PG_head_tail_mask);
-- 
cgit v1.2.3-55-g7522


From a7a88b23737095e6c18a20c5d4eef9e25ec5b829 Mon Sep 17 00:00:00 2001
From: Hugh Dickins
Date: Wed, 2 Jan 2013 02:04:23 -0800
Subject: mempolicy: remove arg from mpol_parse_str, mpol_to_str

Remove the unused argument (formerly no_context) from mpol_parse_str()
and from mpol_to_str().

Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/task_mmu.c        |  2 +-
 include/linux/mempolicy.h | 11 ++++-------
 mm/mempolicy.c            |  6 ++----
 mm/shmem.c                |  4 ++--
 4 files changed, 9 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 448455b7fd91..ca5ce7f9f800 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1278,7 +1278,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	walk.mm = mm;
 
 	pol = get_vma_policy(task, vma, vma->vm_start);
-	mpol_to_str(buffer, sizeof(buffer), pol, 0);
+	mpol_to_str(buffer, sizeof(buffer), pol);
 	mpol_cond_put(pol);
 
 	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 9adc270de7ef..92bc9988a180 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -165,11 +165,10 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 
 
 #ifdef CONFIG_TMPFS
-extern int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context);
+extern int mpol_parse_str(char *str, struct mempolicy **mpol);
 #endif
 
-extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
-			int no_context);
+extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol);
 
 /* Check if a vma is migratable */
 static inline int vma_migratable(struct vm_area_struct *vma)
@@ -296,15 +295,13 @@ static inline void check_highest_zone(int k)
 }
 
 #ifdef CONFIG_TMPFS
-static inline int mpol_parse_str(char *str, struct mempolicy **mpol,
-				int no_context)
+static inline int mpol_parse_str(char *str, struct mempolicy **mpol)
 {
 	return 1;	/* error */
 }
 #endif
 
-static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
-				int no_context)
+static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 {
 	return 0;
 }
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 02c914cca53d..1cb200af3828 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2612,14 +2612,13 @@ static const char * const policy_modes[] =
  * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option.
  * @str:  string containing mempolicy to parse
  * @mpol:  pointer to struct mempolicy pointer, returned on success.
- * @unused:  redundant argument, to be removed later.
  *
  * Format of input:
  *	<mode>[=<flags>][:<nodelist>]
  *
  * On success, returns 0, else 1
  */
-int mpol_parse_str(char *str, struct mempolicy **mpol, int unused)
+int mpol_parse_str(char *str, struct mempolicy **mpol)
 {
 	struct mempolicy *new = NULL;
 	unsigned short mode;
@@ -2747,13 +2746,12 @@ out:
  * @buffer:  to contain formatted mempolicy string
  * @maxlen:  length of @buffer
  * @pol:  pointer to mempolicy to be formatted
- * @unused:  redundant argument, to be removed later.
  *
  * Convert a mempolicy into a string.
  * Returns the number of characters in buffer (if positive)
  * or an error (negative)
  */
-int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int unused)
+int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 {
 	char *p = buffer;
 	int l;
diff --git a/mm/shmem.c b/mm/shmem.c
index 5c90d84c2b02..5dd56f6efdbd 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -889,7 +889,7 @@ static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
 	if (!mpol || mpol->mode == MPOL_DEFAULT)
 		return;		/* show nothing */
 
-	mpol_to_str(buffer, sizeof(buffer), mpol, 1);
+	mpol_to_str(buffer, sizeof(buffer), mpol);
 
 	seq_printf(seq, ",mpol=%s", buffer);
 }
@@ -2463,7 +2463,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
 			if (!gid_valid(sbinfo->gid))
 				goto bad_val;
 		} else if (!strcmp(this_char,"mpol")) {
-			if (mpol_parse_str(value, &sbinfo->mpol, 1))
+			if (mpol_parse_str(value, &sbinfo->mpol))
 				goto bad_val;
 		} else {
 			printk(KERN_ERR "tmpfs: Bad mount option %s\n",
-- 
cgit v1.2.3-55-g7522


From 42288fe366c4f1ce7522bc9f27d0bc2a81c55264 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Fri, 21 Dec 2012 23:10:25 +0000
Subject: mm: mempolicy: Convert shared_policy mutex to spinlock

Sasha was fuzzing with trinity and reported the following problem:

  BUG: sleeping function called from invalid context at kernel/mutex.c:269
  in_atomic(): 1, irqs_disabled(): 0, pid: 6361, name: trinity-main
  2 locks held by trinity-main/6361:
   #0:  (&mm->mmap_sem){++++++}, at: [<ffffffff810aa314>] __do_page_fault+0x1e4/0x4f0
   #1:  (&(&mm->page_table_lock)->rlock){+.+...}, at: [<ffffffff8122f017>] handle_pte_fault+0x3f7/0x6a0
  Pid: 6361, comm: trinity-main Tainted: G        W
  3.7.0-rc2-next-20121024-sasha-00001-gd95ef01-dirty #74
  Call Trace:
    __might_sleep+0x1c3/0x1e0
    mutex_lock_nested+0x29/0x50
    mpol_shared_policy_lookup+0x2e/0x90
    shmem_get_policy+0x2e/0x30
    get_vma_policy+0x5a/0xa0
    mpol_misplaced+0x41/0x1d0
    handle_pte_fault+0x465/0x6a0

This was triggered by a different version of automatic NUMA balancing
but in theory the current version is vunerable to the same problem.

do_numa_page
  -> numa_migrate_prep
    -> mpol_misplaced
      -> get_vma_policy
        -> shmem_get_policy

It's very unlikely this will happen as shared pages are not marked
pte_numa -- see the page_mapcount() check in change_pte_range() -- but
it is possible.

To address this, this patch restores sp->lock as originally implemented
by Kosaki Motohiro.  In the path where get_vma_policy() is called, it
should not be calling sp_alloc() so it is not necessary to treat the PTL
specially.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Tested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mempolicy.h |  2 +-
 mm/mempolicy.c            | 68 +++++++++++++++++++++++++++++++++--------------
 2 files changed, 49 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 92bc9988a180..0d7df39a5885 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -123,7 +123,7 @@ struct sp_node {
 
 struct shared_policy {
 	struct rb_root root;
-	struct mutex mutex;
+	spinlock_t lock;
 };
 
 void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 1cb200af3828..e2df1c1fb41f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2132,7 +2132,7 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
  */
 
 /* lookup first element intersecting start-end */
-/* Caller holds sp->mutex */
+/* Caller holds sp->lock */
 static struct sp_node *
 sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
 {
@@ -2196,13 +2196,13 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
 
 	if (!sp->root.rb_node)
 		return NULL;
-	mutex_lock(&sp->mutex);
+	spin_lock(&sp->lock);
 	sn = sp_lookup(sp, idx, idx+1);
 	if (sn) {
 		mpol_get(sn->policy);
 		pol = sn->policy;
 	}
-	mutex_unlock(&sp->mutex);
+	spin_unlock(&sp->lock);
 	return pol;
 }
 
@@ -2328,6 +2328,14 @@ static void sp_delete(struct shared_policy *sp, struct sp_node *n)
 	sp_free(n);
 }
 
+static void sp_node_init(struct sp_node *node, unsigned long start,
+			unsigned long end, struct mempolicy *pol)
+{
+	node->start = start;
+	node->end = end;
+	node->policy = pol;
+}
+
 static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
 				struct mempolicy *pol)
 {
@@ -2344,10 +2352,7 @@ static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
 		return NULL;
 	}
 	newpol->flags |= MPOL_F_SHARED;
-
-	n->start = start;
-	n->end = end;
-	n->policy = newpol;
+	sp_node_init(n, start, end, newpol);
 
 	return n;
 }
@@ -2357,9 +2362,12 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 				 unsigned long end, struct sp_node *new)
 {
 	struct sp_node *n;
+	struct sp_node *n_new = NULL;
+	struct mempolicy *mpol_new = NULL;
 	int ret = 0;
 
-	mutex_lock(&sp->mutex);
+restart:
+	spin_lock(&sp->lock);
 	n = sp_lookup(sp, start, end);
 	/* Take care of old policies in the same range. */
 	while (n && n->start < end) {
@@ -2372,14 +2380,16 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 		} else {
 			/* Old policy spanning whole new range. */
 			if (n->end > end) {
-				struct sp_node *new2;
-				new2 = sp_alloc(end, n->end, n->policy);
-				if (!new2) {
-					ret = -ENOMEM;
-					goto out;
-				}
+				if (!n_new)
+					goto alloc_new;
+
+				*mpol_new = *n->policy;
+				atomic_set(&mpol_new->refcnt, 1);
+				sp_node_init(n_new, n->end, end, mpol_new);
+				sp_insert(sp, n_new);
 				n->end = start;
-				sp_insert(sp, new2);
+				n_new = NULL;
+				mpol_new = NULL;
 				break;
 			} else
 				n->end = start;
@@ -2390,9 +2400,27 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 	}
 	if (new)
 		sp_insert(sp, new);
-out:
-	mutex_unlock(&sp->mutex);
+	spin_unlock(&sp->lock);
+	ret = 0;
+
+err_out:
+	if (mpol_new)
+		mpol_put(mpol_new);
+	if (n_new)
+		kmem_cache_free(sn_cache, n_new);
+
 	return ret;
+
+alloc_new:
+	spin_unlock(&sp->lock);
+	ret = -ENOMEM;
+	n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL);
+	if (!n_new)
+		goto err_out;
+	mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
+	if (!mpol_new)
+		goto err_out;
+	goto restart;
 }
 
 /**
@@ -2410,7 +2438,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 	int ret;
 
 	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
-	mutex_init(&sp->mutex);
+	spin_lock_init(&sp->lock);
 
 	if (mpol) {
 		struct vm_area_struct pvma;
@@ -2476,14 +2504,14 @@ void mpol_free_shared_policy(struct shared_policy *p)
 
 	if (!p->root.rb_node)
 		return;
-	mutex_lock(&p->mutex);
+	spin_lock(&p->lock);
 	next = rb_first(&p->root);
 	while (next) {
 		n = rb_entry(next, struct sp_node, nd);
 		next = rb_next(&n->nd);
 		sp_delete(p, n);
 	}
-	mutex_unlock(&p->mutex);
+	spin_unlock(&p->lock);
 }
 
 #ifdef CONFIG_NUMA_BALANCING
-- 
cgit v1.2.3-55-g7522


From 3d33fcc11bdd11b6949cf5c406726a094395dc4f Mon Sep 17 00:00:00 2001
From: David Howells
Date: Wed, 2 Jan 2013 15:12:55 +0000
Subject: UAPI: Remove empty Kbuild files

Empty files can get deleted by the patch program, so remove empty Kbuild
files and their links from the parent Kbuilds.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/Kbuild            | 3 ---
 include/linux/Kbuild      | 5 -----
 include/linux/hdlc/Kbuild | 0
 include/linux/hsi/Kbuild  | 0
 include/linux/raid/Kbuild | 0
 include/linux/usb/Kbuild  | 0
 include/rdma/Kbuild       | 0
 include/sound/Kbuild      | 0
 8 files changed, 8 deletions(-)
 delete mode 100644 include/linux/Kbuild
 delete mode 100644 include/linux/hdlc/Kbuild
 delete mode 100644 include/linux/hsi/Kbuild
 delete mode 100644 include/linux/raid/Kbuild
 delete mode 100644 include/linux/usb/Kbuild
 delete mode 100644 include/rdma/Kbuild
 delete mode 100644 include/sound/Kbuild

(limited to 'include')

diff --git a/include/Kbuild b/include/Kbuild
index 83256b64166a..1dfd33e8d43b 100644
--- a/include/Kbuild
+++ b/include/Kbuild
@@ -1,8 +1,5 @@
 # Top-level Makefile calls into asm-$(ARCH)
 # List only non-arch directories below
 
-header-y += linux/
-header-y += sound/
-header-y += rdma/
 header-y += video/
 header-y += scsi/
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
deleted file mode 100644
index 7fe2dae251e5..000000000000
--- a/include/linux/Kbuild
+++ /dev/null
@@ -1,5 +0,0 @@
-header-y += dvb/
-header-y += hdlc/
-header-y += hsi/
-header-y += raid/
-header-y += usb/
diff --git a/include/linux/hdlc/Kbuild b/include/linux/hdlc/Kbuild
deleted file mode 100644
index e69de29bb2d1..000000000000
diff --git a/include/linux/hsi/Kbuild b/include/linux/hsi/Kbuild
deleted file mode 100644
index e69de29bb2d1..000000000000
diff --git a/include/linux/raid/Kbuild b/include/linux/raid/Kbuild
deleted file mode 100644
index e69de29bb2d1..000000000000
diff --git a/include/linux/usb/Kbuild b/include/linux/usb/Kbuild
deleted file mode 100644
index e69de29bb2d1..000000000000
diff --git a/include/rdma/Kbuild b/include/rdma/Kbuild
deleted file mode 100644
index e69de29bb2d1..000000000000
diff --git a/include/sound/Kbuild b/include/sound/Kbuild
deleted file mode 100644
index e69de29bb2d1..000000000000
-- 
cgit v1.2.3-55-g7522


From f568f6ca811fe681ecfd11c4ce78b6aa488020c0 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman
Date: Fri, 21 Dec 2012 15:02:05 -0800
Subject: pstore: remove __dev* attributes.

CONFIG_HOTPLUG is going away as an option.  As a result, the __dev*
markings need to be removed.

This change removes the use of __devinit from the pstore filesystem.

Based on patches originally written by Bill Pemberton, but redone by me
in order to handle some of the coding style issues better, by hand.

Cc: Bill Pemberton <wfp5p@virginia.edu>
Cc: Anton Vorontsov <cbouatmailru@gmail.com>
Cc: Colin Cross <ccross@android.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/pstore/ram.c            | 14 ++++++--------
 fs/pstore/ram_core.c       |  9 ++++-----
 include/linux/pstore_ram.h |  5 ++---
 3 files changed, 12 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index f883e7e74305..7003e5266f25 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -291,9 +291,8 @@ static void ramoops_free_przs(struct ramoops_context *cxt)
 	kfree(cxt->przs);
 }
 
-static int __devinit ramoops_init_przs(struct device *dev,
-				       struct ramoops_context *cxt,
-				       phys_addr_t *paddr, size_t dump_mem_sz)
+static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
+			     phys_addr_t *paddr, size_t dump_mem_sz)
 {
 	int err = -ENOMEM;
 	int i;
@@ -336,10 +335,9 @@ fail_prz:
 	return err;
 }
 
-static int __devinit ramoops_init_prz(struct device *dev,
-				      struct ramoops_context *cxt,
-				      struct persistent_ram_zone **prz,
-				      phys_addr_t *paddr, size_t sz, u32 sig)
+static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt,
+			    struct persistent_ram_zone **prz,
+			    phys_addr_t *paddr, size_t sz, u32 sig)
 {
 	if (!sz)
 		return 0;
@@ -367,7 +365,7 @@ static int __devinit ramoops_init_prz(struct device *dev,
 	return 0;
 }
 
-static int __devinit ramoops_probe(struct platform_device *pdev)
+static int ramoops_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct ramoops_platform_data *pdata = pdev->dev.platform_data;
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index eecd2a8a84dd..0306303be372 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -390,8 +390,8 @@ static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size,
 	return 0;
 }
 
-static int __devinit persistent_ram_post_init(struct persistent_ram_zone *prz,
-					      u32 sig, int ecc_size)
+static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig,
+				    int ecc_size)
 {
 	int ret;
 
@@ -443,9 +443,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz)
 	kfree(prz);
 }
 
-struct persistent_ram_zone * __devinit persistent_ram_new(phys_addr_t start,
-							  size_t size, u32 sig,
-							  int ecc_size)
+struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
+					       u32 sig, int ecc_size)
 {
 	struct persistent_ram_zone *prz;
 	int ret = -ENOMEM;
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 098d2a838296..cb6ab5feab67 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -46,9 +46,8 @@ struct persistent_ram_zone {
 	size_t old_log_size;
 };
 
-struct persistent_ram_zone * __devinit persistent_ram_new(phys_addr_t start,
-							  size_t size, u32 sig,
-							  int ecc_size);
+struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
+					       u32 sig, int ecc_size);
 void persistent_ram_free(struct persistent_ram_zone *prz);
 void persistent_ram_zap(struct persistent_ram_zone *prz);
 
-- 
cgit v1.2.3-55-g7522


From 0f58a01ddd5e8177255705ba15e64c3b74d67993 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman
Date: Fri, 21 Dec 2012 15:12:59 -0800
Subject: Drivers: bcma: remove __dev* attributes.

CONFIG_HOTPLUG is going away as an option.  As a result, the __dev*
markings need to be removed.

This change removes the use of __devinit, __devexit_p, and __devexit
from these drivers.

Based on patches originally written by Bill Pemberton, but redone by me
in order to handle some of the coding style issues better, by hand.

Cc: Bill Pemberton <wfp5p@virginia.edu>
Cc: "Rafał Miłecki" <zajec5@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bcma/bcma_private.h               |  6 +++---
 drivers/bcma/driver_gmac_cmn.c            |  2 +-
 drivers/bcma/driver_pci.c                 |  4 ++--
 drivers/bcma/driver_pci_host.c            | 13 ++++++-------
 drivers/bcma/host_pci.c                   |  8 ++++----
 drivers/bcma/main.c                       |  2 +-
 include/linux/bcma/bcma_driver_gmac_cmn.h |  2 +-
 include/linux/bcma/bcma_driver_pci.h      |  2 +-
 8 files changed, 19 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index 4a2d72ec6d43..19e3fbfd5757 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -22,7 +22,7 @@
 struct bcma_bus;
 
 /* main.c */
-int __devinit bcma_bus_register(struct bcma_bus *bus);
+int bcma_bus_register(struct bcma_bus *bus);
 void bcma_bus_unregister(struct bcma_bus *bus);
 int __init bcma_bus_early_register(struct bcma_bus *bus,
 				   struct bcma_device *core_cc,
@@ -87,8 +87,8 @@ u32 bcma_pcie_read(struct bcma_drv_pci *pc, u32 address);
 extern int bcma_chipco_watchdog_register(struct bcma_drv_cc *cc);
 
 #ifdef CONFIG_BCMA_DRIVER_PCI_HOSTMODE
-bool __devinit bcma_core_pci_is_in_hostmode(struct bcma_drv_pci *pc);
-void __devinit bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc);
+bool bcma_core_pci_is_in_hostmode(struct bcma_drv_pci *pc);
+void bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc);
 #endif /* CONFIG_BCMA_DRIVER_PCI_HOSTMODE */
 
 #ifdef CONFIG_BCMA_DRIVER_GPIO
diff --git a/drivers/bcma/driver_gmac_cmn.c b/drivers/bcma/driver_gmac_cmn.c
index 834225f65e8f..dcb137926d31 100644
--- a/drivers/bcma/driver_gmac_cmn.c
+++ b/drivers/bcma/driver_gmac_cmn.c
@@ -8,7 +8,7 @@
 #include "bcma_private.h"
 #include <linux/bcma/bcma.h>
 
-void __devinit bcma_core_gmac_cmn_init(struct bcma_drv_gmac_cmn *gc)
+void bcma_core_gmac_cmn_init(struct bcma_drv_gmac_cmn *gc)
 {
 	mutex_init(&gc->phy_mutex);
 }
diff --git a/drivers/bcma/driver_pci.c b/drivers/bcma/driver_pci.c
index c39ee6d45850..cf7a476a519f 100644
--- a/drivers/bcma/driver_pci.c
+++ b/drivers/bcma/driver_pci.c
@@ -207,14 +207,14 @@ static void bcma_core_pci_config_fixup(struct bcma_drv_pci *pc)
  * Init.
  **************************************************/
 
-static void __devinit bcma_core_pci_clientmode_init(struct bcma_drv_pci *pc)
+static void bcma_core_pci_clientmode_init(struct bcma_drv_pci *pc)
 {
 	bcma_core_pci_fixcfg(pc);
 	bcma_pcicore_serdes_workaround(pc);
 	bcma_core_pci_config_fixup(pc);
 }
 
-void __devinit bcma_core_pci_init(struct bcma_drv_pci *pc)
+void bcma_core_pci_init(struct bcma_drv_pci *pc)
 {
 	if (pc->setup_done)
 		return;
diff --git a/drivers/bcma/driver_pci_host.c b/drivers/bcma/driver_pci_host.c
index e6b5c89469dc..af0c9fabee54 100644
--- a/drivers/bcma/driver_pci_host.c
+++ b/drivers/bcma/driver_pci_host.c
@@ -24,7 +24,7 @@
 #define BCMA_PCI_SLOT_MAX	16
 #define	PCI_CONFIG_SPACE_SIZE	256
 
-bool __devinit bcma_core_pci_is_in_hostmode(struct bcma_drv_pci *pc)
+bool bcma_core_pci_is_in_hostmode(struct bcma_drv_pci *pc)
 {
 	struct bcma_bus *bus = pc->core->bus;
 	u16 chipid_top;
@@ -264,10 +264,9 @@ static int bcma_core_pci_hostmode_write_config(struct pci_bus *bus,
 }
 
 /* return cap_offset if requested capability exists in the PCI config space */
-static u8 __devinit bcma_find_pci_capability(struct bcma_drv_pci *pc,
-					     unsigned int dev,
-					     unsigned int func, u8 req_cap_id,
-					     unsigned char *buf, u32 *buflen)
+static u8 bcma_find_pci_capability(struct bcma_drv_pci *pc, unsigned int dev,
+				   unsigned int func, u8 req_cap_id,
+				   unsigned char *buf, u32 *buflen)
 {
 	u8 cap_id;
 	u8 cap_ptr = 0;
@@ -334,7 +333,7 @@ static u8 __devinit bcma_find_pci_capability(struct bcma_drv_pci *pc,
  * Retry Status (CRS) Completion Status to software then
  * enable the feature.
  */
-static void __devinit bcma_core_pci_enable_crs(struct bcma_drv_pci *pc)
+static void bcma_core_pci_enable_crs(struct bcma_drv_pci *pc)
 {
 	struct bcma_bus *bus = pc->core->bus;
 	u8 cap_ptr, root_ctrl, root_cap, dev;
@@ -381,7 +380,7 @@ static void __devinit bcma_core_pci_enable_crs(struct bcma_drv_pci *pc)
 	}
 }
 
-void __devinit bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc)
+void bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc)
 {
 	struct bcma_bus *bus = pc->core->bus;
 	struct bcma_drv_pci_host *pc_host;
diff --git a/drivers/bcma/host_pci.c b/drivers/bcma/host_pci.c
index 98fdc3e014e7..fbf2759e7e4e 100644
--- a/drivers/bcma/host_pci.c
+++ b/drivers/bcma/host_pci.c
@@ -155,8 +155,8 @@ static const struct bcma_host_ops bcma_host_pci_ops = {
 	.awrite32	= bcma_host_pci_awrite32,
 };
 
-static int __devinit bcma_host_pci_probe(struct pci_dev *dev,
-					 const struct pci_device_id *id)
+static int bcma_host_pci_probe(struct pci_dev *dev,
+			       const struct pci_device_id *id)
 {
 	struct bcma_bus *bus;
 	int err = -ENOMEM;
@@ -226,7 +226,7 @@ err_kfree_bus:
 	return err;
 }
 
-static void __devexit bcma_host_pci_remove(struct pci_dev *dev)
+static void bcma_host_pci_remove(struct pci_dev *dev)
 {
 	struct bcma_bus *bus = pci_get_drvdata(dev);
 
@@ -284,7 +284,7 @@ static struct pci_driver bcma_pci_bridge_driver = {
 	.name = "bcma-pci-bridge",
 	.id_table = bcma_pci_bridge_tbl,
 	.probe = bcma_host_pci_probe,
-	.remove = __devexit_p(bcma_host_pci_remove),
+	.remove = bcma_host_pci_remove,
 	.driver.pm = BCMA_PM_OPS,
 };
 
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 53ba20ca17e0..4a92f647b58b 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -192,7 +192,7 @@ static void bcma_unregister_cores(struct bcma_bus *bus)
 		platform_device_unregister(bus->drv_cc.watchdog);
 }
 
-int __devinit bcma_bus_register(struct bcma_bus *bus)
+int bcma_bus_register(struct bcma_bus *bus)
 {
 	int err;
 	struct bcma_device *core;
diff --git a/include/linux/bcma/bcma_driver_gmac_cmn.h b/include/linux/bcma/bcma_driver_gmac_cmn.h
index def894b83b0d..4dd1f33e36a2 100644
--- a/include/linux/bcma/bcma_driver_gmac_cmn.h
+++ b/include/linux/bcma/bcma_driver_gmac_cmn.h
@@ -92,7 +92,7 @@ struct bcma_drv_gmac_cmn {
 #define gmac_cmn_write32(gc, offset, val)	bcma_write32((gc)->core, offset, val)
 
 #ifdef CONFIG_BCMA_DRIVER_GMAC_CMN
-extern void __devinit bcma_core_gmac_cmn_init(struct bcma_drv_gmac_cmn *gc);
+extern void bcma_core_gmac_cmn_init(struct bcma_drv_gmac_cmn *gc);
 #else
 static inline void bcma_core_gmac_cmn_init(struct bcma_drv_gmac_cmn *gc) { }
 #endif
diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h
index 41da581e1612..c48d98d27b77 100644
--- a/include/linux/bcma/bcma_driver_pci.h
+++ b/include/linux/bcma/bcma_driver_pci.h
@@ -214,7 +214,7 @@ struct bcma_drv_pci {
 #define pcicore_write16(pc, offset, val)	bcma_write16((pc)->core, offset, val)
 #define pcicore_write32(pc, offset, val)	bcma_write32((pc)->core, offset, val)
 
-extern void __devinit bcma_core_pci_init(struct bcma_drv_pci *pc);
+extern void bcma_core_pci_init(struct bcma_drv_pci *pc);
 extern int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc,
 				 struct bcma_device *core, bool enable);
 extern void bcma_core_pci_extend_L1timer(struct bcma_drv_pci *pc, bool extend);
-- 
cgit v1.2.3-55-g7522


From e389623a68622e3c9be440ab522fac1aa1ca3454 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman
Date: Fri, 21 Dec 2012 15:15:49 -0800
Subject: include: remove __dev* attributes.

CONFIG_HOTPLUG is going away as an option.  As a result, the __dev*
markings need to be removed.

This change removes the use of __devinit from some include files that
were previously missed.

Based on patches originally written by Bill Pemberton, but redone by me
in order to handle some of the coding style issues better, by hand.

Cc: Bill Pemberton <wfp5p@virginia.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/asm-generic/parport.h |  4 ++--
 include/linux/ata_platform.h  | 12 ++++++------
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/parport.h b/include/asm-generic/parport.h
index 40528cb977e8..2c9f9d4336ca 100644
--- a/include/asm-generic/parport.h
+++ b/include/asm-generic/parport.h
@@ -10,8 +10,8 @@
  * to devices on the PCI bus.
  */
 
-static int __devinit parport_pc_find_isa_ports(int autoirq, int autodma);
-static int __devinit parport_pc_find_nonpci_ports(int autoirq, int autodma)
+static int parport_pc_find_isa_ports(int autoirq, int autodma);
+static int parport_pc_find_nonpci_ports(int autoirq, int autodma)
 {
 #ifdef CONFIG_ISA
 	return parport_pc_find_isa_ports(autoirq, autodma);
diff --git a/include/linux/ata_platform.h b/include/linux/ata_platform.h
index fe9989636b62..b9fde17f767c 100644
--- a/include/linux/ata_platform.h
+++ b/include/linux/ata_platform.h
@@ -15,12 +15,12 @@ struct pata_platform_info {
 	unsigned int irq_flags;
 };
 
-extern int __devinit __pata_platform_probe(struct device *dev,
-					   struct resource *io_res,
-					   struct resource *ctl_res,
-					   struct resource *irq_res,
-					   unsigned int ioport_shift,
-					   int __pio_mask);
+extern int __pata_platform_probe(struct device *dev,
+				 struct resource *io_res,
+				 struct resource *ctl_res,
+				 struct resource *irq_res,
+				 unsigned int ioport_shift,
+				 int __pio_mask);
 
 /*
  * Marvell SATA private data
-- 
cgit v1.2.3-55-g7522


From d81aecb5e680311e1f3fd71e49e6a4072d2374d2 Mon Sep 17 00:00:00 2001
From: Inki Dae
Date: Tue, 18 Dec 2012 02:30:17 +0900
Subject: drm/exynos: change file license to GPL

This patch changes file license to GPL

Most of exynos files had been copied from some random
file and not updated correctly. So this patch corrects
the file license.

Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_buf.c       | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_buf.h       | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_connector.c | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_connector.h | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_core.c      | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_crtc.c      | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_crtc.h      | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_dmabuf.c    | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_dmabuf.h    | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_drv.c       | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_drv.h       | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_encoder.c   | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_encoder.h   | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_fb.c        | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_fb.h        | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_fbdev.c     | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_fbdev.h     | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_fimc.h      | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_gem.c       | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_gem.h       | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_gsc.h       | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_hdmi.h      | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_iommu.c     | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_iommu.h     | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_ipp.h       | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_rotator.h   | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_drm_vidi.h      | 22 ++++------------------
 drivers/gpu/drm/exynos/exynos_hdmi.h          | 22 ++++------------------
 include/drm/exynos_drm.h                      | 22 ++++------------------
 include/uapi/drm/exynos_drm.h                 | 22 ++++------------------
 30 files changed, 120 insertions(+), 540 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/exynos/exynos_drm_buf.c b/drivers/gpu/drm/exynos/exynos_drm_buf.c
index 9601bad47a2e..13a8489b39ff 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_buf.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_buf.c
@@ -3,24 +3,10 @@
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  * Author: Inki Dae <inki.dae@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_buf.h b/drivers/gpu/drm/exynos/exynos_drm_buf.h
index 25cf16285033..a6412f19673c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_buf.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_buf.h
@@ -3,24 +3,10 @@
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  * Author: Inki Dae <inki.dae@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_BUF_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.c b/drivers/gpu/drm/exynos/exynos_drm_connector.c
index 0f68a2872673..ab37437bad8a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_connector.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_connector.c
@@ -5,24 +5,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.h b/drivers/gpu/drm/exynos/exynos_drm_connector.h
index 22f6cc442c3d..547c6b590357 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_connector.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_connector.h
@@ -5,24 +5,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_CONNECTOR_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
index 94026ad76a77..4667c9f67acd 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_core.c
@@ -6,24 +6,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index 2efa4b031d73..d59a03a6508f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -6,24 +6,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.h b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
index 6bae8d8c250e..8ac3969bb35b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
@@ -6,24 +6,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_CRTC_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
index e98b096aaf39..315037af7fe0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
@@ -3,24 +3,10 @@
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  * Author: Inki Dae <inki.dae@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.h b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.h
index 662a8f98ccdb..49acfafb4fdb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.h
@@ -3,24 +3,10 @@
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  * Author: Inki Dae <inki.dae@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_DMABUF_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index e0a8e8024b01..56e9a412c5c5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -5,24 +5,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index f5a97745bf93..b9e51bc09e81 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -6,24 +6,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_DRV_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_encoder.c b/drivers/gpu/drm/exynos/exynos_drm_encoder.c
index 301485215a70..c63721f64aec 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_encoder.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_encoder.c
@@ -6,24 +6,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_encoder.h b/drivers/gpu/drm/exynos/exynos_drm_encoder.h
index 88bb25a2a917..89e2fb0770af 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_encoder.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_encoder.h
@@ -5,24 +5,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_ENCODER_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 5426cc5a5e8d..294c0513f587 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -6,24 +6,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.h b/drivers/gpu/drm/exynos/exynos_drm_fb.h
index 96262e54f76d..517471b37566 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.h
@@ -5,24 +5,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_FB_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index eae064a3ee30..71f867340a88 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -6,24 +6,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.h b/drivers/gpu/drm/exynos/exynos_drm_fbdev.h
index ccfce8a1a451..e16d7f0ae192 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.h
@@ -6,24 +6,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_FBDEV_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.h b/drivers/gpu/drm/exynos/exynos_drm_fimc.h
index dc970fa0d888..127a424c5fdf 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.h
@@ -6,24 +6,10 @@
  *	Jinyoung Jeon <jy0.jeon@samsung.com>
  *	Sangmin Lee <lsmin.lee@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_FIMC_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index d48183e7e056..473180776528 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -3,24 +3,10 @@
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  * Author: Inki Dae <inki.dae@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index f11f2afd5bfc..35ebac47dc2b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -3,24 +3,10 @@
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  * Authoer: Inki Dae <inki.dae@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_GEM_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.h b/drivers/gpu/drm/exynos/exynos_drm_gsc.h
index b3c3bc618c0f..29ec1c5efcf2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.h
@@ -6,24 +6,10 @@
  *	Jinyoung Jeon <jy0.jeon@samsung.com>
  *	Sangmin Lee <lsmin.lee@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_GSC_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_hdmi.h b/drivers/gpu/drm/exynos/exynos_drm_hdmi.h
index fcc3093ec8fe..784a7e9a766c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_hdmi.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_hdmi.h
@@ -3,24 +3,10 @@
  * Copyright (c) 2011 Samsung Electronics Co., Ltd.
  * Authoer: Inki Dae <inki.dae@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_HDMI_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_iommu.c b/drivers/gpu/drm/exynos/exynos_drm_iommu.c
index 2482b7f96341..3799d5c2b5df 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_iommu.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_iommu.c
@@ -3,24 +3,10 @@
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  * Author: Inki Dae <inki.dae@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #include <drmP.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_iommu.h b/drivers/gpu/drm/exynos/exynos_drm_iommu.h
index 18a0ca190b98..53b7deea8ab7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_iommu.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_iommu.h
@@ -3,24 +3,10 @@
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  * Authoer: Inki Dae <inki.dae@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_IOMMU_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.h b/drivers/gpu/drm/exynos/exynos_drm_ipp.h
index 28ffac95386c..034f8f3cf88c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.h
@@ -6,24 +6,10 @@
  *	Jinyoung Jeon <jy0.jeon@samsung.com>
  *	Sangmin Lee <lsmin.lee@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_IPP_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.h b/drivers/gpu/drm/exynos/exynos_drm_rotator.h
index a2d7a14a52b6..71a0b4c0c1e8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.h
@@ -5,24 +5,10 @@
  *	YoungJun Cho <yj44.cho@samsung.com>
  *	Eunchul Kim <chulspro.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef	_EXYNOS_DRM_ROTATOR_H_
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.h b/drivers/gpu/drm/exynos/exynos_drm_vidi.h
index a4babe4e65d7..1e5fdaa36ccc 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.h
@@ -3,24 +3,10 @@
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  * Author: Inki Dae <inki.dae@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_DRM_VIDI_H_
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.h b/drivers/gpu/drm/exynos/exynos_hdmi.h
index 1c3b6d8f1fe7..0ddf3957de15 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.h
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.h
@@ -5,24 +5,10 @@
  *	Inki Dae <inki.dae@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _EXYNOS_HDMI_H_
diff --git a/include/drm/exynos_drm.h b/include/drm/exynos_drm.h
index 808dad29607a..d6aeaf3c6d6c 100644
--- a/include/drm/exynos_drm.h
+++ b/include/drm/exynos_drm.h
@@ -6,24 +6,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 #ifndef _EXYNOS_DRM_H_
 #define _EXYNOS_DRM_H_
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
index e7f52c334005..81354d0e7fd7 100644
--- a/include/uapi/drm/exynos_drm.h
+++ b/include/uapi/drm/exynos_drm.h
@@ -6,24 +6,10 @@
  *	Joonyoung Shim <jy0922.shim@samsung.com>
  *	Seung-Woo Kim <sw0312.kim@samsung.com>
  *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
  */
 
 #ifndef _UAPI_EXYNOS_DRM_H_
-- 
cgit v1.2.3-55-g7522


From 4f21877cb8b9e9f85a541af43b9ee66d9006bb69 Mon Sep 17 00:00:00 2001
From: Eunchul Kim
Date: Sat, 22 Dec 2012 17:49:24 +0900
Subject: drm/exynos: consider both case of vflip and hflip.

This patch considers both case of vflip and hflip.
If we want that the contents in buffer to be rotated to 180 degree,
then we can use h,vflip or 180 degree.

Changelog v2:
- added EXYNOS_DRM_FLIP_BOTH enum value to avoid build warnning.

Signed-off-by: Eunchul Kim <chulspro.kim@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_fimc.c    | 1 +
 drivers/gpu/drm/exynos/exynos_drm_gsc.c     | 2 +-
 drivers/gpu/drm/exynos/exynos_drm_rotator.c | 1 +
 include/uapi/drm/exynos_drm.h               | 2 ++
 4 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 5dc02517c2fd..abfff9e333c4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -1387,6 +1387,7 @@ static inline bool fimc_check_drm_flip(enum drm_exynos_flip flip)
 	case EXYNOS_DRM_FLIP_NONE:
 	case EXYNOS_DRM_FLIP_VERTICAL:
 	case EXYNOS_DRM_FLIP_HORIZONTAL:
+	case EXYNOS_DRM_FLIP_BOTH:
 		return true;
 	default:
 		DRM_DEBUG_KMS("%s:invalid flip\n", __func__);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index ba5fefdff4b7..3e5b4568d89c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1391,7 +1391,7 @@ static inline bool gsc_check_drm_flip(enum drm_exynos_flip flip)
 	case EXYNOS_DRM_FLIP_NONE:
 	case EXYNOS_DRM_FLIP_VERTICAL:
 	case EXYNOS_DRM_FLIP_HORIZONTAL:
-	case EXYNOS_DRM_FLIP_VERTICAL | EXYNOS_DRM_FLIP_HORIZONTAL:
+	case EXYNOS_DRM_FLIP_BOTH:
 		return true;
 	default:
 		DRM_DEBUG_KMS("%s:invalid flip\n", __func__);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 17e4474ae899..8bf9c5016c01 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -513,6 +513,7 @@ static inline bool rotator_check_drm_flip(enum drm_exynos_flip flip)
 	case EXYNOS_DRM_FLIP_NONE:
 	case EXYNOS_DRM_FLIP_VERTICAL:
 	case EXYNOS_DRM_FLIP_HORIZONTAL:
+	case EXYNOS_DRM_FLIP_BOTH:
 		return true;
 	default:
 		DRM_DEBUG_KMS("%s:invalid flip\n", __func__);
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
index 81354d0e7fd7..d5844122ff32 100644
--- a/include/uapi/drm/exynos_drm.h
+++ b/include/uapi/drm/exynos_drm.h
@@ -171,6 +171,8 @@ enum drm_exynos_flip {
 	EXYNOS_DRM_FLIP_NONE = (0 << 0),
 	EXYNOS_DRM_FLIP_VERTICAL = (1 << 0),
 	EXYNOS_DRM_FLIP_HORIZONTAL = (1 << 1),
+	EXYNOS_DRM_FLIP_BOTH = EXYNOS_DRM_FLIP_VERTICAL |
+			EXYNOS_DRM_FLIP_HORIZONTAL,
 };
 
 enum drm_exynos_degree {
-- 
cgit v1.2.3-55-g7522


From 03f595668017f1a1fb971c02fc37140bc6e7bb1c Mon Sep 17 00:00:00 2001
From: Stanislav Kinsbursky
Date: Fri, 4 Jan 2013 15:34:50 -0800
Subject: ipc: add sysctl to specify desired next object id

Add 3 new variables and sysctls to tune them (by one "next_id" variable
for messages, semaphores and shared memory respectively).  This variable
can be used to set desired id for next allocated IPC object.  By default
it's equal to -1 and old behaviour is preserved.  If this variable is
non-negative, then desired idr will be extracted from it and used as a
start value to search for free IDR slot.

Notes:

1) this patch doesn't guarantee that the new object will have desired
   id.  So it's up to user space how to handle new object with wrong id.

2) After a sucessful id allocation attempt, "next_id" will be set back
   to -1 (if it was non-negative).

[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/sysctl/kernel.txt | 19 +++++++++++++++++++
 include/linux/ipc_namespace.h   |  1 +
 ipc/ipc_sysctl.c                | 32 ++++++++++++++++++++++++++++++++
 ipc/util.c                      | 16 ++++++++++++----
 ipc/util.h                      |  1 +
 5 files changed, 65 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 2907ba6c3607..51b953a1b149 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -38,6 +38,7 @@ show up in /proc/sys/kernel:
 - l2cr                        [ PPC only ]
 - modprobe                    ==> Documentation/debugging-modules.txt
 - modules_disabled
+- msg_next_id		      [ sysv ipc ]
 - msgmax
 - msgmnb
 - msgmni
@@ -62,7 +63,9 @@ show up in /proc/sys/kernel:
 - rtsig-max
 - rtsig-nr
 - sem
+- sem_next_id		      [ sysv ipc ]
 - sg-big-buff                 [ generic SCSI device (sg) ]
+- shm_next_id		      [ sysv ipc ]
 - shm_rmid_forced
 - shmall
 - shmmax                      [ sysv ipc ]
@@ -320,6 +323,22 @@ to false.
 
 ==============================================================
 
+msg_next_id, sem_next_id, and shm_next_id:
+
+These three toggles allows to specify desired id for next allocated IPC
+object: message, semaphore or shared memory respectively.
+
+By default they are equal to -1, which means generic allocation logic.
+Possible values to set are in range {0..INT_MAX}.
+
+Notes:
+1) kernel doesn't guarantee, that new object will have desired id. So,
+it's up to userspace, how to handle an object with "wrong" id.
+2) Toggle with non-default value will be set back to -1 by kernel after
+successful IPC object allocation.
+
+==============================================================
+
 nmi_watchdog:
 
 Enables/Disables the NMI watchdog on x86 systems. When the value is
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index fe771978e877..ae221a7b5092 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -24,6 +24,7 @@ struct ipc_ids {
 	unsigned short seq_max;
 	struct rw_semaphore rw_mutex;
 	struct idr ipcs_idr;
+	int next_id;
 };
 
 struct ipc_namespace {
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 00fba2bab87d..130dfece27ac 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -158,6 +158,9 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
 
 static int zero;
 static int one = 1;
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static int int_max = INT_MAX;
+#endif
 
 static struct ctl_table ipc_kern_table[] = {
 	{
@@ -227,6 +230,35 @@ static struct ctl_table ipc_kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	{
+		.procname	= "sem_next_id",
+		.data		= &init_ipc_ns.ids[IPC_SEM_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "msg_next_id",
+		.data		= &init_ipc_ns.ids[IPC_MSG_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "shm_next_id",
+		.data		= &init_ipc_ns.ids[IPC_SHM_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+#endif
 	{}
 };
 
diff --git a/ipc/util.c b/ipc/util.c
index 72fd0785ac94..74e1d9c7a98a 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -122,6 +122,7 @@ void ipc_init_ids(struct ipc_ids *ids)
 
 	ids->in_use = 0;
 	ids->seq = 0;
+	ids->next_id = -1;
 	{
 		int seq_limit = INT_MAX/SEQ_MULTIPLIER;
 		if (seq_limit > USHRT_MAX)
@@ -252,6 +253,7 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 	kuid_t euid;
 	kgid_t egid;
 	int id, err;
+	int next_id = ids->next_id;
 
 	if (size > IPCMNI)
 		size = IPCMNI;
@@ -264,7 +266,8 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 	rcu_read_lock();
 	spin_lock(&new->lock);
 
-	err = idr_get_new(&ids->ipcs_idr, new, &id);
+	err = idr_get_new_above(&ids->ipcs_idr, new,
+				(next_id < 0) ? 0 : ipcid_to_idx(next_id), &id);
 	if (err) {
 		spin_unlock(&new->lock);
 		rcu_read_unlock();
@@ -277,9 +280,14 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 	new->cuid = new->uid = euid;
 	new->gid = new->cgid = egid;
 
-	new->seq = ids->seq++;
-	if(ids->seq > ids->seq_max)
-		ids->seq = 0;
+	if (next_id < 0) {
+		new->seq = ids->seq++;
+		if (ids->seq > ids->seq_max)
+			ids->seq = 0;
+	} else {
+		new->seq = ipcid_to_seqx(next_id);
+		ids->next_id = -1;
+	}
 
 	new->id = ipc_buildid(id, new->seq);
 	return id;
diff --git a/ipc/util.h b/ipc/util.h
index c8fe2f7631e9..a61e0ca2bffd 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -92,6 +92,7 @@ void __init ipc_init_proc_interface(const char *path, const char *header,
 #define IPC_SHM_IDS	2
 
 #define ipcid_to_idx(id) ((id) % SEQ_MULTIPLIER)
+#define ipcid_to_seqx(id) ((id) / SEQ_MULTIPLIER)
 
 /* must be called with ids->rw_mutex acquired for writing */
 int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);
-- 
cgit v1.2.3-55-g7522


From f9dd87f4738c7555aca2cdf8cb2b2326cafb0cad Mon Sep 17 00:00:00 2001
From: Stanislav Kinsbursky
Date: Fri, 4 Jan 2013 15:34:52 -0800
Subject: ipc: message queue receive cleanup

Move all message related manipulation into one function msg_fill().
Actually, two functions because of the compat one.

[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/msg.h |  5 +++--
 ipc/compat.c        | 45 +++++++++++++++++++--------------------------
 ipc/msg.c           | 44 +++++++++++++++++++++++---------------------
 3 files changed, 45 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/include/linux/msg.h b/include/linux/msg.h
index 7a4b9e97d29a..fc5743a554e6 100644
--- a/include/linux/msg.h
+++ b/include/linux/msg.h
@@ -34,7 +34,8 @@ struct msg_queue {
 /* Helper routines for sys_msgsnd and sys_msgrcv */
 extern long do_msgsnd(int msqid, long mtype, void __user *mtext,
 			size_t msgsz, int msgflg);
-extern long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
-			size_t msgsz, long msgtyp, int msgflg);
+extern long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
+		      int msgflg,
+		      long (*msg_fill)(void __user *, struct msg_msg *, size_t));
 
 #endif /* _LINUX_MSG_H */
diff --git a/ipc/compat.c b/ipc/compat.c
index ad9518eb26e0..eb3ea16d2d1d 100644
--- a/ipc/compat.c
+++ b/ipc/compat.c
@@ -306,6 +306,20 @@ static long do_compat_semctl(int first, int second, int third, u32 pad)
 	return err;
 }
 
+long compat_do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz)
+{
+	struct compat_msgbuf __user *msgp = dest;
+	size_t msgsz;
+
+	if (put_user(msg->m_type, &msgp->mtype))
+		return -EFAULT;
+
+	msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz;
+	if (store_msg(msgp->mtext, msg, msgsz))
+		return -EFAULT;
+	return msgsz;
+}
+
 #ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
 long compat_sys_semctl(int first, int second, int third, void __user *uptr)
 {
@@ -337,10 +351,6 @@ long compat_sys_msgsnd(int first, int second, int third, void __user *uptr)
 long compat_sys_msgrcv(int first, int second, int msgtyp, int third,
 			   int version, void __user *uptr)
 {
-	struct compat_msgbuf __user *up;
-	long type;
-	int err;
-
 	if (first < 0)
 		return -EINVAL;
 	if (second < 0)
@@ -348,23 +358,14 @@ long compat_sys_msgrcv(int first, int second, int msgtyp, int third,
 
 	if (!version) {
 		struct compat_ipc_kludge ipck;
-		err = -EINVAL;
 		if (!uptr)
-			goto out;
-		err = -EFAULT;
+			return -EINVAL;
 		if (copy_from_user (&ipck, uptr, sizeof(ipck)))
-			goto out;
+			return -EFAULT;
 		uptr = compat_ptr(ipck.msgp);
 		msgtyp = ipck.msgtyp;
 	}
-	up = uptr;
-	err = do_msgrcv(first, &type, up->mtext, second, msgtyp, third);
-	if (err < 0)
-		goto out;
-	if (put_user(type, &up->mtype))
-		err = -EFAULT;
-out:
-	return err;
+	return do_msgrcv(first, uptr, second, msgtyp, third, compat_do_msg_fill);
 }
 #else
 long compat_sys_semctl(int semid, int semnum, int cmd, int arg)
@@ -385,16 +386,8 @@ long compat_sys_msgsnd(int msqid, struct compat_msgbuf __user *msgp,
 long compat_sys_msgrcv(int msqid, struct compat_msgbuf __user *msgp,
 		       compat_ssize_t msgsz, long msgtyp, int msgflg)
 {
-	long err, mtype;
-
-	err =  do_msgrcv(msqid, &mtype, msgp->mtext, (ssize_t)msgsz, msgtyp, msgflg);
-	if (err < 0)
-		goto out;
-
-	if (put_user(mtype, &msgp->mtype))
-		err = -EFAULT;
- out:
-	return err;
+	return do_msgrcv(msqid, msgp, (ssize_t)msgsz, msgtyp, msgflg,
+			 compat_do_msg_fill);
 }
 #endif
 
diff --git a/ipc/msg.c b/ipc/msg.c
index 2f272fa76595..cefc24f46e3e 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -755,15 +755,30 @@ static inline int convert_mode(long *msgtyp, int msgflg)
 	return SEARCH_EQUAL;
 }
 
-long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
-		size_t msgsz, long msgtyp, int msgflg)
+static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz)
+{
+	struct msgbuf __user *msgp = dest;
+	size_t msgsz;
+
+	if (put_user(msg->m_type, &msgp->mtype))
+		return -EFAULT;
+
+	msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz;
+	if (store_msg(msgp->mtext, msg, msgsz))
+		return -EFAULT;
+	return msgsz;
+}
+
+long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
+	       int msgflg,
+	       long (*msg_handler)(void __user *, struct msg_msg *, size_t))
 {
 	struct msg_queue *msq;
 	struct msg_msg *msg;
 	int mode;
 	struct ipc_namespace *ns;
 
-	if (msqid < 0 || (long) msgsz < 0)
+	if (msqid < 0 || (long) bufsz < 0)
 		return -EINVAL;
 	mode = convert_mode(&msgtyp, msgflg);
 	ns = current->nsproxy->ipc_ns;
@@ -804,7 +819,7 @@ long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
 			 * Found a suitable message.
 			 * Unlink it from the queue.
 			 */
-			if ((msgsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
+			if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
 				msg = ERR_PTR(-E2BIG);
 				goto out_unlock;
 			}
@@ -831,7 +846,7 @@ long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
 		if (msgflg & MSG_NOERROR)
 			msr_d.r_maxsize = INT_MAX;
 		else
-			msr_d.r_maxsize = msgsz;
+			msr_d.r_maxsize = bufsz;
 		msr_d.r_msg = ERR_PTR(-EAGAIN);
 		current->state = TASK_INTERRUPTIBLE;
 		msg_unlock(msq);
@@ -894,29 +909,16 @@ out_unlock:
 	if (IS_ERR(msg))
 		return PTR_ERR(msg);
 
-	msgsz = (msgsz > msg->m_ts) ? msg->m_ts : msgsz;
-	*pmtype = msg->m_type;
-	if (store_msg(mtext, msg, msgsz))
-		msgsz = -EFAULT;
-
+	bufsz = msg_handler(buf, msg, bufsz);
 	free_msg(msg);
 
-	return msgsz;
+	return bufsz;
 }
 
 SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
 		long, msgtyp, int, msgflg)
 {
-	long err, mtype;
-
-	err =  do_msgrcv(msqid, &mtype, msgp->mtext, msgsz, msgtyp, msgflg);
-	if (err < 0)
-		goto out;
-
-	if (put_user(mtype, &msgp->mtype))
-		err = -EFAULT;
-out:
-	return err;
+	return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill);
 }
 
 #ifdef CONFIG_PROC_FS
-- 
cgit v1.2.3-55-g7522


From 4a674f34ba04a002244edaf891b5da7fc1473ae8 Mon Sep 17 00:00:00 2001
From: Stanislav Kinsbursky
Date: Fri, 4 Jan 2013 15:34:55 -0800
Subject: ipc: introduce message queue copy feature

This patch is required for checkpoint/restore in userspace.

c/r requires some way to get all pending IPC messages without deleting
them from the queue (checkpoint can fail and in this case tasks will be
resumed, so queue have to be valid).

To achive this, new operation flag MSG_COPY for sys_msgrcv() system call
was introduced.  If this flag was specified, then mtype is interpreted as
number of the message to copy.

If MSG_COPY is set, then kernel will allocate dummy message with passed
size, and then use new copy_msg() helper function to copy desired message
(instead of unlinking it from the queue).

Notes:

1) Return -ENOSYS if MSG_COPY is specified, but
   CONFIG_CHECKPOINT_RESTORE is not set.

Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/uapi/linux/msg.h |  1 +
 ipc/msg.c                | 64 ++++++++++++++++++++++++++++++++++++++++++++++--
 ipc/msgutil.c            | 38 ++++++++++++++++++++++++++++
 ipc/util.h               |  1 +
 4 files changed, 102 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/msg.h b/include/uapi/linux/msg.h
index 78dbd2f996a3..22d95c6854e0 100644
--- a/include/uapi/linux/msg.h
+++ b/include/uapi/linux/msg.h
@@ -10,6 +10,7 @@
 /* msgrcv options */
 #define MSG_NOERROR     010000  /* no error if message is too big */
 #define MSG_EXCEPT      020000  /* recv any msg except of specified type.*/
+#define MSG_COPY        040000  /* copy (not remove) all queue messages */
 
 /* Obsolete, used only for backwards compatibility and libc5 compiles */
 struct msqid_ds {
diff --git a/ipc/msg.c b/ipc/msg.c
index cefc24f46e3e..d20ffc7d3f24 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -769,6 +769,45 @@ static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz)
 	return msgsz;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static inline struct msg_msg *fill_copy(unsigned long copy_nr,
+					unsigned long msg_nr,
+					struct msg_msg *msg,
+					struct msg_msg *copy)
+{
+	if (copy_nr == msg_nr)
+		return copy_msg(msg, copy);
+	return NULL;
+}
+
+static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz,
+					   int msgflg, long *msgtyp,
+					   unsigned long *copy_number)
+{
+	struct msg_msg *copy;
+
+	*copy_number = *msgtyp;
+	*msgtyp = 0;
+	/*
+	 * Create dummy message to copy real message to.
+	 */
+	copy = load_msg(buf, bufsz);
+	if (!IS_ERR(copy))
+		copy->m_ts = bufsz;
+	return copy;
+}
+
+static inline void free_copy(int msgflg, struct msg_msg *copy)
+{
+	if (msgflg & MSG_COPY)
+		free_msg(copy);
+}
+#else
+#define free_copy(msgflg, copy)				do {} while (0)
+#define prepare_copy(buf, sz, msgflg, msgtyp, copy_nr)	ERR_PTR(-ENOSYS)
+#define fill_copy(copy_nr, msg_nr, msg, copy)		NULL
+#endif
+
 long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 	       int msgflg,
 	       long (*msg_handler)(void __user *, struct msg_msg *, size_t))
@@ -777,19 +816,29 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 	struct msg_msg *msg;
 	int mode;
 	struct ipc_namespace *ns;
+	struct msg_msg *copy;
+	unsigned long __maybe_unused copy_number;
 
 	if (msqid < 0 || (long) bufsz < 0)
 		return -EINVAL;
+	if (msgflg & MSG_COPY) {
+		copy = prepare_copy(buf, bufsz, msgflg, &msgtyp, &copy_number);
+		if (IS_ERR(copy))
+			return PTR_ERR(copy);
+	}
 	mode = convert_mode(&msgtyp, msgflg);
 	ns = current->nsproxy->ipc_ns;
 
 	msq = msg_lock_check(ns, msqid);
-	if (IS_ERR(msq))
+	if (IS_ERR(msq)) {
+		free_copy(msgflg, copy);
 		return PTR_ERR(msq);
+	}
 
 	for (;;) {
 		struct msg_receiver msr_d;
 		struct list_head *tmp;
+		long msg_counter = 0;
 
 		msg = ERR_PTR(-EACCES);
 		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
@@ -809,8 +858,15 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 				if (mode == SEARCH_LESSEQUAL &&
 						walk_msg->m_type != 1) {
 					msgtyp = walk_msg->m_type - 1;
+				} else if (msgflg & MSG_COPY) {
+					msg = fill_copy(copy_number,
+							msg_counter,
+							walk_msg, copy);
+					if (msg)
+						break;
 				} else
 					break;
+				msg_counter++;
 			}
 			tmp = tmp->next;
 		}
@@ -823,6 +879,8 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 				msg = ERR_PTR(-E2BIG);
 				goto out_unlock;
 			}
+			if (msgflg & MSG_COPY)
+				goto out_unlock;
 			list_del(&msg->m_list);
 			msq->q_qnum--;
 			msq->q_rtime = get_seconds();
@@ -906,8 +964,10 @@ out_unlock:
 			break;
 		}
 	}
-	if (IS_ERR(msg))
+	if (IS_ERR(msg)) {
+		free_copy(msgflg, copy);
 		return PTR_ERR(msg);
+	}
 
 	bufsz = msg_handler(buf, msg, bufsz);
 	free_msg(msg);
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 6471f1bdae96..7eecdad40efc 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -102,7 +102,45 @@ out_err:
 	free_msg(msg);
 	return ERR_PTR(err);
 }
+#ifdef CONFIG_CHECKPOINT_RESTORE
+struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
+{
+	struct msg_msgseg *dst_pseg, *src_pseg;
+	int len = src->m_ts;
+	int alen;
+
+	BUG_ON(dst == NULL);
+	if (src->m_ts > dst->m_ts)
+		return ERR_PTR(-EINVAL);
+
+	alen = len;
+	if (alen > DATALEN_MSG)
+		alen = DATALEN_MSG;
+
+	dst->next = NULL;
+	dst->security = NULL;
 
+	memcpy(dst + 1, src + 1, alen);
+
+	len -= alen;
+	dst_pseg = dst->next;
+	src_pseg = src->next;
+	while (len > 0) {
+		alen = len;
+		if (alen > DATALEN_SEG)
+			alen = DATALEN_SEG;
+		memcpy(dst_pseg + 1, src_pseg + 1, alen);
+		dst_pseg = dst_pseg->next;
+		len -= alen;
+		src_pseg = src_pseg->next;
+	}
+
+	dst->m_type = src->m_type;
+	dst->m_ts = src->m_ts;
+
+	return dst;
+}
+#endif
 int store_msg(void __user *dest, struct msg_msg *msg, int len)
 {
 	int alen;
diff --git a/ipc/util.h b/ipc/util.h
index a61e0ca2bffd..eeb79a1fbd83 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -140,6 +140,7 @@ int ipc_parse_version (int *cmd);
 
 extern void free_msg(struct msg_msg *msg);
 extern struct msg_msg *load_msg(const void __user *src, int len);
+extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst);
 extern int store_msg(void __user *dest, struct msg_msg *msg, int len);
 
 extern void recompute_msgmni(struct ipc_namespace *);
-- 
cgit v1.2.3-55-g7522


From 3a665531a3b7c2ad2c87903b24646be6916340e4 Mon Sep 17 00:00:00 2001
From: Stanislav Kinsbursky
Date: Fri, 4 Jan 2013 15:34:56 -0800
Subject: selftests: IPC message queue copy feature test

This test can be used to check wheither kernel supports IPC message queue
copy and restore features (required by CRIU project).

Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/msg.h                  |   3 +-
 ipc/compat.c                         |   3 +-
 tools/testing/selftests/ipc/Makefile |  25 ++++
 tools/testing/selftests/ipc/msgque.c | 246 +++++++++++++++++++++++++++++++++++
 4 files changed, 275 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/ipc/Makefile
 create mode 100644 tools/testing/selftests/ipc/msgque.c

(limited to 'include')

diff --git a/include/linux/msg.h b/include/linux/msg.h
index fc5743a554e6..391af8d11cce 100644
--- a/include/linux/msg.h
+++ b/include/linux/msg.h
@@ -36,6 +36,7 @@ extern long do_msgsnd(int msqid, long mtype, void __user *mtext,
 			size_t msgsz, int msgflg);
 extern long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 		      int msgflg,
-		      long (*msg_fill)(void __user *, struct msg_msg *, size_t));
+		      long (*msg_fill)(void __user *, struct msg_msg *,
+				       size_t));
 
 #endif /* _LINUX_MSG_H */
diff --git a/ipc/compat.c b/ipc/compat.c
index eb3ea16d2d1d..2547f29dcd1b 100644
--- a/ipc/compat.c
+++ b/ipc/compat.c
@@ -365,7 +365,8 @@ long compat_sys_msgrcv(int first, int second, int msgtyp, int third,
 		uptr = compat_ptr(ipck.msgp);
 		msgtyp = ipck.msgtyp;
 	}
-	return do_msgrcv(first, uptr, second, msgtyp, third, compat_do_msg_fill);
+	return do_msgrcv(first, uptr, second, msgtyp, third,
+			 compat_do_msg_fill);
 }
 #else
 long compat_sys_semctl(int semid, int semnum, int cmd, int arg)
diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile
new file mode 100644
index 000000000000..5386fd7c43ae
--- /dev/null
+++ b/tools/testing/selftests/ipc/Makefile
@@ -0,0 +1,25 @@
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/)
+ifeq ($(ARCH),i386)
+        ARCH := X86
+	CFLAGS := -DCONFIG_X86_32 -D__i386__
+endif
+ifeq ($(ARCH),x86_64)
+	ARCH := X86
+	CFLAGS := -DCONFIG_X86_64 -D__x86_64__
+endif
+
+CFLAGS += -I../../../../usr/include/
+
+all:
+ifeq ($(ARCH),X86)
+	gcc $(CFLAGS) msgque.c -o msgque_test
+else
+	echo "Not an x86 target, can't build msgque selftest"
+endif
+
+run_tests: all
+	./msgque_test
+
+clean:
+	rm -fr ./msgque_test
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
new file mode 100644
index 000000000000..d66418237d21
--- /dev/null
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -0,0 +1,246 @@
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/msg.h>
+#include <fcntl.h>
+
+#define MAX_MSG_SIZE		32
+
+struct msg1 {
+	int msize;
+	long mtype;
+	char mtext[MAX_MSG_SIZE];
+};
+
+#define TEST_STRING "Test sysv5 msg"
+#define MSG_TYPE 1
+
+#define ANOTHER_TEST_STRING "Yet another test sysv5 msg"
+#define ANOTHER_MSG_TYPE 26538
+
+struct msgque_data {
+	key_t key;
+	int msq_id;
+	int qbytes;
+	int qnum;
+	int mode;
+	struct msg1 *messages;
+};
+
+int restore_queue(struct msgque_data *msgque)
+{
+	int fd, ret, id, i;
+	char buf[32];
+
+	fd = open("/proc/sys/kernel/msg_next_id", O_WRONLY);
+	if (fd == -1) {
+		printf("Failed to open /proc/sys/kernel/msg_next_id\n");
+		return -errno;
+	}
+	sprintf(buf, "%d", msgque->msq_id);
+
+	ret = write(fd, buf, strlen(buf));
+	if (ret != strlen(buf)) {
+		printf("Failed to write to /proc/sys/kernel/msg_next_id\n");
+		return -errno;
+	}
+
+	id = msgget(msgque->key, msgque->mode | IPC_CREAT | IPC_EXCL);
+	if (id == -1) {
+		printf("Failed to create queue\n");
+		return -errno;
+	}
+
+	if (id != msgque->msq_id) {
+		printf("Restored queue has wrong id (%d instead of %d)\n",
+							id, msgque->msq_id);
+		ret = -EFAULT;
+		goto destroy;
+	}
+
+	for (i = 0; i < msgque->qnum; i++) {
+		if (msgsnd(msgque->msq_id, &msgque->messages[i].mtype,
+			   msgque->messages[i].msize, IPC_NOWAIT) != 0) {
+			printf("msgsnd failed (%m)\n");
+			ret = -errno;
+			goto destroy;
+		};
+	}
+	return 0;
+
+destroy:
+	if (msgctl(id, IPC_RMID, 0))
+		printf("Failed to destroy queue: %d\n", -errno);
+	return ret;
+}
+
+int check_and_destroy_queue(struct msgque_data *msgque)
+{
+	struct msg1 message;
+	int cnt = 0, ret;
+
+	while (1) {
+		ret = msgrcv(msgque->msq_id, &message.mtype, MAX_MSG_SIZE,
+				0, IPC_NOWAIT);
+		if (ret < 0) {
+			if (errno == ENOMSG)
+				break;
+			printf("Failed to read IPC message: %m\n");
+			ret = -errno;
+			goto err;
+		}
+		if (ret != msgque->messages[cnt].msize) {
+			printf("Wrong message size: %d (expected %d)\n", ret,
+						msgque->messages[cnt].msize);
+			ret = -EINVAL;
+			goto err;
+		}
+		if (message.mtype != msgque->messages[cnt].mtype) {
+			printf("Wrong message type\n");
+			ret = -EINVAL;
+			goto err;
+		}
+		if (memcmp(message.mtext, msgque->messages[cnt].mtext, ret)) {
+			printf("Wrong message content\n");
+			ret = -EINVAL;
+			goto err;
+		}
+		cnt++;
+	}
+
+	if (cnt != msgque->qnum) {
+		printf("Wrong message number\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	ret = 0;
+err:
+	if (msgctl(msgque->msq_id, IPC_RMID, 0)) {
+		printf("Failed to destroy queue: %d\n", -errno);
+		return -errno;
+	}
+	return ret;
+}
+
+int dump_queue(struct msgque_data *msgque)
+{
+	struct msqid64_ds ds;
+	int kern_id;
+	int i, ret;
+
+	for (kern_id = 0; kern_id < 256; kern_id++) {
+		ret = msgctl(kern_id, MSG_STAT, &ds);
+		if (ret < 0) {
+			if (errno == -EINVAL)
+				continue;
+			printf("Failed to get stats for IPC queue with id %d\n",
+					kern_id);
+			return -errno;
+		}
+
+		if (ret == msgque->msq_id)
+			break;
+	}
+
+	msgque->messages = malloc(sizeof(struct msg1) * ds.msg_qnum);
+	if (msgque->messages == NULL) {
+		printf("Failed to get stats for IPC queue\n");
+		return -ENOMEM;
+	}
+
+	msgque->qnum = ds.msg_qnum;
+	msgque->mode = ds.msg_perm.mode;
+	msgque->qbytes = ds.msg_qbytes;
+
+	for (i = 0; i < msgque->qnum; i++) {
+		ret = msgrcv(msgque->msq_id, &msgque->messages[i].mtype,
+				MAX_MSG_SIZE, i, IPC_NOWAIT | MSG_COPY);
+		if (ret < 0) {
+			printf("Failed to copy IPC message: %m (%d)\n", errno);
+			return -errno;
+		}
+		msgque->messages[i].msize = ret;
+	}
+	return 0;
+}
+
+int fill_msgque(struct msgque_data *msgque)
+{
+	struct msg1 msgbuf;
+
+	msgbuf.mtype = MSG_TYPE;
+	memcpy(msgbuf.mtext, TEST_STRING, sizeof(TEST_STRING));
+	if (msgsnd(msgque->msq_id, &msgbuf.mtype, sizeof(TEST_STRING),
+				IPC_NOWAIT) != 0) {
+		printf("First message send failed (%m)\n");
+		return -errno;
+	};
+
+	msgbuf.mtype = ANOTHER_MSG_TYPE;
+	memcpy(msgbuf.mtext, ANOTHER_TEST_STRING, sizeof(ANOTHER_TEST_STRING));
+	if (msgsnd(msgque->msq_id, &msgbuf.mtype, sizeof(ANOTHER_TEST_STRING),
+				IPC_NOWAIT) != 0) {
+		printf("Second message send failed (%m)\n");
+		return -errno;
+	};
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	int msg, pid, err;
+	struct msgque_data msgque;
+
+	msgque.key = ftok(argv[0], 822155650);
+	if (msgque.key == -1) {
+		printf("Can't make key\n");
+		return -errno;
+	}
+
+	msgque.msq_id = msgget(msgque.key, IPC_CREAT | IPC_EXCL | 0666);
+	if (msgque.msq_id == -1) {
+		printf("Can't create queue\n");
+		goto err_out;
+	}
+
+	err = fill_msgque(&msgque);
+	if (err) {
+		printf("Failed to fill queue\n");
+		goto err_destroy;
+	}
+
+	err = dump_queue(&msgque);
+	if (err) {
+		printf("Failed to dump queue\n");
+		goto err_destroy;
+	}
+
+	err = check_and_destroy_queue(&msgque);
+	if (err) {
+		printf("Failed to check and destroy queue\n");
+		goto err_out;
+	}
+
+	err = restore_queue(&msgque);
+	if (err) {
+		printf("Failed to restore queue\n");
+		goto err_destroy;
+	}
+
+	err = check_and_destroy_queue(&msgque);
+	if (err) {
+		printf("Failed to test queue\n");
+		goto err_out;
+	}
+	return 0;
+
+err_destroy:
+	if (msgctl(msgque.msq_id, IPC_RMID, 0)) {
+		printf("Failed to destroy queue: %d\n", -errno);
+		return -errno;
+	}
+err_out:
+	return err;
+}
-- 
cgit v1.2.3-55-g7522


From a458431e176ddb27e8ef8b98c2a681b217337393 Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz
Date: Fri, 4 Jan 2013 15:35:08 -0800
Subject: mm: fix zone_watermark_ok_safe() accounting of isolated pages

Commit 702d1a6e0766 ("memory-hotplug: fix kswapd looping forever
problem") added an isolated pageblocks counter (nr_pageblock_isolate in
struct zone) and used it to adjust free pages counter in
zone_watermark_ok_safe() to prevent kswapd looping forever problem.

Then later, commit 2139cbe627b8 ("cma: fix counting of isolated pages")
fixed accounting of isolated pages in global free pages counter.  It
made the previous zone_watermark_ok_safe() fix unnecessary and
potentially harmful (cause now isolated pages may be accounted twice
making free pages counter incorrect).

This patch removes the special isolated pageblocks counter altogether
which fixes zone_watermark_ok_safe() free pages check.

Reported-by: Tomasz Stanislawski <t.stanislaws@samsung.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Aaditya Kumar <aaditya.kumar.30@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h |  8 --------
 mm/page_alloc.c        | 27 ---------------------------
 mm/page_isolation.c    | 26 ++------------------------
 3 files changed, 2 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4bec5be82cab..73b64a38b984 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -503,14 +503,6 @@ struct zone {
 	 * rarely used fields:
 	 */
 	const char		*name;
-#ifdef CONFIG_MEMORY_ISOLATION
-	/*
-	 * the number of MIGRATE_ISOLATE *pageblock*.
-	 * We need this for free page counting. Look at zone_watermark_ok_safe.
-	 * It's protected by zone->lock
-	 */
-	int		nr_pageblock_isolate;
-#endif
 } ____cacheline_internodealigned_in_smp;
 
 typedef enum {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4ba5e37127fc..bc6cc0e913bd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -221,11 +221,6 @@ EXPORT_SYMBOL(nr_online_nodes);
 
 int page_group_by_mobility_disabled __read_mostly;
 
-/*
- * NOTE:
- * Don't use set_pageblock_migratetype(page, MIGRATE_ISOLATE) directly.
- * Instead, use {un}set_pageblock_isolate.
- */
 void set_pageblock_migratetype(struct page *page, int migratetype)
 {
 
@@ -1655,20 +1650,6 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	return true;
 }
 
-#ifdef CONFIG_MEMORY_ISOLATION
-static inline unsigned long nr_zone_isolate_freepages(struct zone *zone)
-{
-	if (unlikely(zone->nr_pageblock_isolate))
-		return zone->nr_pageblock_isolate * pageblock_nr_pages;
-	return 0;
-}
-#else
-static inline unsigned long nr_zone_isolate_freepages(struct zone *zone)
-{
-	return 0;
-}
-#endif
-
 bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 		      int classzone_idx, int alloc_flags)
 {
@@ -1684,14 +1665,6 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
 	if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
 		free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
 
-	/*
-	 * If the zone has MIGRATE_ISOLATE type free pages, we should consider
-	 * it.  nr_zone_isolate_freepages is never accurate so kswapd might not
-	 * sleep although it could do so.  But this is more desirable for memory
-	 * hotplug than sleeping which can cause a livelock in the direct
-	 * reclaim path.
-	 */
-	free_pages -= nr_zone_isolate_freepages(z);
 	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
 								free_pages);
 }
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 9d2264ea4606..383bdbb98b04 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -8,28 +8,6 @@
 #include <linux/memory.h>
 #include "internal.h"
 
-/* called while holding zone->lock */
-static void set_pageblock_isolate(struct page *page)
-{
-	if (get_pageblock_migratetype(page) == MIGRATE_ISOLATE)
-		return;
-
-	set_pageblock_migratetype(page, MIGRATE_ISOLATE);
-	page_zone(page)->nr_pageblock_isolate++;
-}
-
-/* called while holding zone->lock */
-static void restore_pageblock_isolate(struct page *page, int migratetype)
-{
-	struct zone *zone = page_zone(page);
-	if (WARN_ON(get_pageblock_migratetype(page) != MIGRATE_ISOLATE))
-		return;
-
-	BUG_ON(zone->nr_pageblock_isolate <= 0);
-	set_pageblock_migratetype(page, migratetype);
-	zone->nr_pageblock_isolate--;
-}
-
 int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages)
 {
 	struct zone *zone;
@@ -80,7 +58,7 @@ out:
 		unsigned long nr_pages;
 		int migratetype = get_pageblock_migratetype(page);
 
-		set_pageblock_isolate(page);
+		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
 		nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE);
 
 		__mod_zone_freepage_state(zone, -nr_pages, migratetype);
@@ -103,7 +81,7 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 		goto out;
 	nr_pages = move_freepages_block(zone, page, migratetype);
 	__mod_zone_freepage_state(zone, nr_pages, migratetype);
-	restore_pageblock_isolate(page, migratetype);
+	set_pageblock_migratetype(page, migratetype);
 out:
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
-- 
cgit v1.2.3-55-g7522


From 53a59fc67f97374758e63a9c785891ec62324c81 Mon Sep 17 00:00:00 2001
From: Michal Hocko
Date: Fri, 4 Jan 2013 15:35:12 -0800
Subject: mm: limit mmu_gather batching to fix soft lockups on !CONFIG_PREEMPT

Since commit e303297e6c3a ("mm: extended batches for generic
mmu_gather") we are batching pages to be freed until either
tlb_next_batch cannot allocate a new batch or we are done.

This works just fine most of the time but we can get in troubles with
non-preemptible kernel (CONFIG_PREEMPT_NONE or CONFIG_PREEMPT_VOLUNTARY)
on large machines where too aggressive batching might lead to soft
lockups during process exit path (exit_mmap) because there are no
scheduling points down the free_pages_and_swap_cache path and so the
freeing can take long enough to trigger the soft lockup.

The lockup is harmless except when the system is setup to panic on
softlockup which is not that unusual.

The simplest way to work around this issue is to limit the maximum
number of batches in a single mmu_gather.  10k of collected pages should
be safe to prevent from soft lockups (we would have 2ms for one) even if
they are all freed without an explicit scheduling point.

This patch doesn't add any new explicit scheduling points because it
relies on zap_pmd_range during page tables zapping which calls
cond_resched per PMD.

The following lockup has been reported for 3.0 kernel with a huge
process (in order of hundreds gigs but I do know any more details).

  BUG: soft lockup - CPU#56 stuck for 22s! [kernel:31053]
  Modules linked in: af_packet nfs lockd fscache auth_rpcgss nfs_acl sunrpc mptctl mptbase autofs4 binfmt_misc dm_round_robin dm_multipath bonding cpufreq_conservative cpufreq_userspace cpufreq_powersave pcc_cpufreq mperf microcode fuse loop osst sg sd_mod crc_t10dif st qla2xxx scsi_transport_fc scsi_tgt netxen_nic i7core_edac iTCO_wdt joydev e1000e serio_raw pcspkr edac_core iTCO_vendor_support acpi_power_meter rtc_cmos hpwdt hpilo button container usbhid hid dm_mirror dm_region_hash dm_log linear uhci_hcd ehci_hcd usbcore usb_common scsi_dh_emc scsi_dh_alua scsi_dh_hp_sw scsi_dh_rdac scsi_dh dm_snapshot pcnet32 mii edd dm_mod raid1 ext3 mbcache jbd fan thermal processor thermal_sys hwmon cciss scsi_mod
  Supported: Yes
  CPU 56
  Pid: 31053, comm: kernel Not tainted 3.0.31-0.9-default #1 HP ProLiant DL580 G7
  RIP: 0010:  _raw_spin_unlock_irqrestore+0x8/0x10
  RSP: 0018:ffff883ec1037af0  EFLAGS: 00000206
  RAX: 0000000000000e00 RBX: ffffea01a0817e28 RCX: ffff88803ffd9e80
  RDX: 0000000000000200 RSI: 0000000000000206 RDI: 0000000000000206
  RBP: 0000000000000002 R08: 0000000000000001 R09: ffff887ec724a400
  R10: 0000000000000000 R11: dead000000200200 R12: ffffffff8144c26e
  R13: 0000000000000030 R14: 0000000000000297 R15: 000000000000000e
  FS:  00007ed834282700(0000) GS:ffff88c03f200000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
  CR2: 000000000068b240 CR3: 0000003ec13c5000 CR4: 00000000000006e0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
  Process kernel (pid: 31053, threadinfo ffff883ec1036000, task ffff883ebd5d4100)
  Call Trace:
    release_pages+0xc5/0x260
    free_pages_and_swap_cache+0x9d/0xc0
    tlb_flush_mmu+0x5c/0x80
    tlb_finish_mmu+0xe/0x50
    exit_mmap+0xbd/0x120
    mmput+0x49/0x120
    exit_mm+0x122/0x160
    do_exit+0x17a/0x430
    do_group_exit+0x3d/0xb0
    get_signal_to_deliver+0x247/0x480
    do_signal+0x71/0x1b0
    do_notify_resume+0x98/0xb0
    int_signal+0x12/0x17
  DWARF2 unwinder stuck at int_signal+0x12/0x17

Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: <stable@vger.kernel.org>	[3.0+]
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/tlb.h | 9 +++++++++
 mm/memory.c               | 5 +++++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index ed6642ad03e0..25f01d0bc149 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -78,6 +78,14 @@ struct mmu_gather_batch {
 #define MAX_GATHER_BATCH	\
 	((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *))
 
+/*
+ * Limit the maximum number of mmu_gather batches to reduce a risk of soft
+ * lockups for non-preemptible kernels on huge machines when a lot of memory
+ * is zapped during unmapping.
+ * 10K pages freed at once should be safe even without a preemption point.
+ */
+#define MAX_GATHER_BATCH_COUNT	(10000UL/MAX_GATHER_BATCH)
+
 /* struct mmu_gather is an opaque type used by the mm code for passing around
  * any data needed by arch specific code for tlb_remove_page.
  */
@@ -96,6 +104,7 @@ struct mmu_gather {
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
+	unsigned int		batch_count;
 };
 
 #define HAVE_GENERIC_MMU_GATHER
diff --git a/mm/memory.c b/mm/memory.c
index e0a9b0ce4f10..49fb1cf08611 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -184,10 +184,14 @@ static int tlb_next_batch(struct mmu_gather *tlb)
 		return 1;
 	}
 
+	if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
+		return 0;
+
 	batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
 	if (!batch)
 		return 0;
 
+	tlb->batch_count++;
 	batch->next = NULL;
 	batch->nr   = 0;
 	batch->max  = MAX_GATHER_BATCH;
@@ -216,6 +220,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
 	tlb->local.nr   = 0;
 	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
 	tlb->active     = &tlb->local;
+	tlb->batch_count = 0;
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb->batch = NULL;
-- 
cgit v1.2.3-55-g7522


From e909c682d04e55e77a3c9d158e7dc36027195493 Mon Sep 17 00:00:00 2001
From: Sascha Hauer
Date: Mon, 7 Jan 2013 10:57:14 +0100
Subject: [media] coda: Fix build due to iram.h rename

commit c045e3f13 (ARM: imx: include iram.h rather than mach/iram.h) changed the
location of iram.h, which causes the following build error when building the coda
driver:

drivers/media/platform/coda.c:27:23: error: mach/iram.h: No such file or directory
drivers/media/platform/coda.c: In function 'coda_probe':
drivers/media/platform/coda.c:2000: error: implicit declaration of function 'iram_alloc'
drivers/media/platform/coda.c:2001: warning: assignment makes pointer from integer without a cast
drivers/media/platform/coda.c: In function 'coda_remove':
drivers/media/platform/coda.c:2024: error: implicit declaration of function 'iram_free'

Since the content of iram.h is not imx specific, move it to
include/linux/platform_data/imx-iram.h instead. This is an intermediate solution
until the i.MX iram allocator is converted to the generic SRAM allocator.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Acked-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 arch/arm/mach-imx/iram.h               | 41 ----------------------------------
 arch/arm/mach-imx/iram_alloc.c         |  3 +--
 drivers/media/platform/coda.c          |  2 +-
 include/linux/platform_data/imx-iram.h | 41 ++++++++++++++++++++++++++++++++++
 4 files changed, 43 insertions(+), 44 deletions(-)
 delete mode 100644 arch/arm/mach-imx/iram.h
 create mode 100644 include/linux/platform_data/imx-iram.h

(limited to 'include')

diff --git a/arch/arm/mach-imx/iram.h b/arch/arm/mach-imx/iram.h
deleted file mode 100644
index 022690c33702..000000000000
--- a/arch/arm/mach-imx/iram.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/*
- * Copyright (C) 2010 Freescale Semiconductor, Inc. All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-#include <linux/errno.h>
-
-#ifdef CONFIG_IRAM_ALLOC
-
-int __init iram_init(unsigned long base, unsigned long size);
-void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr);
-void iram_free(unsigned long dma_addr, unsigned int size);
-
-#else
-
-static inline int __init iram_init(unsigned long base, unsigned long size)
-{
-	return -ENOMEM;
-}
-
-static inline void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr)
-{
-	return NULL;
-}
-
-static inline void iram_free(unsigned long base, unsigned long size) {}
-
-#endif
diff --git a/arch/arm/mach-imx/iram_alloc.c b/arch/arm/mach-imx/iram_alloc.c
index 6c80424f678e..e05cf407db65 100644
--- a/arch/arm/mach-imx/iram_alloc.c
+++ b/arch/arm/mach-imx/iram_alloc.c
@@ -22,8 +22,7 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/genalloc.h>
-
-#include "iram.h"
+#include "linux/platform_data/imx-iram.h"
 
 static unsigned long iram_phys_base;
 static void __iomem *iram_virt_base;
diff --git a/drivers/media/platform/coda.c b/drivers/media/platform/coda.c
index 7b8b547f2d51..afadd3aba3e0 100644
--- a/drivers/media/platform/coda.c
+++ b/drivers/media/platform/coda.c
@@ -23,8 +23,8 @@
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 #include <linux/of.h>
+#include <linux/platform_data/imx-iram.h>
 
-#include <mach/iram.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ioctl.h>
diff --git a/include/linux/platform_data/imx-iram.h b/include/linux/platform_data/imx-iram.h
new file mode 100644
index 000000000000..022690c33702
--- /dev/null
+++ b/include/linux/platform_data/imx-iram.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright (C) 2010 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+#include <linux/errno.h>
+
+#ifdef CONFIG_IRAM_ALLOC
+
+int __init iram_init(unsigned long base, unsigned long size);
+void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr);
+void iram_free(unsigned long dma_addr, unsigned int size);
+
+#else
+
+static inline int __init iram_init(unsigned long base, unsigned long size)
+{
+	return -ENOMEM;
+}
+
+static inline void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr)
+{
+	return NULL;
+}
+
+static inline void iram_free(unsigned long base, unsigned long size) {}
+
+#endif
-- 
cgit v1.2.3-55-g7522


From 901593f2bf221659a605bdc1dcb11376ea934163 Mon Sep 17 00:00:00 2001
From: Chris Wilson
Date: Wed, 19 Dec 2012 16:51:06 +0000
Subject: drm: Only evict the blocks required to create the requested hole

Avoid clobbering adjacent blocks if they happen to expire earlier and
amalgamate together to form the requested hole.

In passing this fixes a regression from
commit ea7b1dd44867e9cd6bac67e7c9fc3f128b5b255c
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Fri Feb 18 17:59:12 2011 +0100

    drm: mm: track free areas implicitly

which swaps the end address for size (with a potential overflow) and
effectively causes the eviction code to clobber almost all earlier
buffers above the evictee.

v2: Check the original hole not the adjusted as the coloring may confuse
us when later searching for the overlapping nodes. Also make sure that
we do apply the range restriction and color adjustment in the same
order for both scanning, searching and insertion.

v3: Send the version that was actually tested.

Note that this seems to be ducttape of decent quality ot paper over
some of our unbind related gpu hangs reported since 3.7. It is not
fully effective though, and certainly doesn't fix the underlying bug.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
[danvet: Added note plus bugzilla link and tested-by.]
Cc: stable@vger.kernel.org
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=55984
Tested-by:  Norbert Preining <preining@logic.at>
Acked-by: Dave Airlie <airlied@gmail.com
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_mm.c | 45 +++++++++++++++++----------------------------
 include/drm/drm_mm.h     |  2 +-
 2 files changed, 18 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 2bf9670ba29b..2aa331499f81 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -221,11 +221,13 @@ static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
 
 	BUG_ON(!hole_node->hole_follows || node->allocated);
 
-	if (mm->color_adjust)
-		mm->color_adjust(hole_node, color, &adj_start, &adj_end);
-
 	if (adj_start < start)
 		adj_start = start;
+	if (adj_end > end)
+		adj_end = end;
+
+	if (mm->color_adjust)
+		mm->color_adjust(hole_node, color, &adj_start, &adj_end);
 
 	if (alignment) {
 		unsigned tmp = adj_start % alignment;
@@ -506,7 +508,7 @@ void drm_mm_init_scan(struct drm_mm *mm,
 	mm->scan_size = size;
 	mm->scanned_blocks = 0;
 	mm->scan_hit_start = 0;
-	mm->scan_hit_size = 0;
+	mm->scan_hit_end = 0;
 	mm->scan_check_range = 0;
 	mm->prev_scanned_node = NULL;
 }
@@ -533,7 +535,7 @@ void drm_mm_init_scan_with_range(struct drm_mm *mm,
 	mm->scan_size = size;
 	mm->scanned_blocks = 0;
 	mm->scan_hit_start = 0;
-	mm->scan_hit_size = 0;
+	mm->scan_hit_end = 0;
 	mm->scan_start = start;
 	mm->scan_end = end;
 	mm->scan_check_range = 1;
@@ -552,8 +554,7 @@ int drm_mm_scan_add_block(struct drm_mm_node *node)
 	struct drm_mm *mm = node->mm;
 	struct drm_mm_node *prev_node;
 	unsigned long hole_start, hole_end;
-	unsigned long adj_start;
-	unsigned long adj_end;
+	unsigned long adj_start, adj_end;
 
 	mm->scanned_blocks++;
 
@@ -570,14 +571,8 @@ int drm_mm_scan_add_block(struct drm_mm_node *node)
 	node->node_list.next = &mm->prev_scanned_node->node_list;
 	mm->prev_scanned_node = node;
 
-	hole_start = drm_mm_hole_node_start(prev_node);
-	hole_end = drm_mm_hole_node_end(prev_node);
-
-	adj_start = hole_start;
-	adj_end = hole_end;
-
-	if (mm->color_adjust)
-		mm->color_adjust(prev_node, mm->scan_color, &adj_start, &adj_end);
+	adj_start = hole_start = drm_mm_hole_node_start(prev_node);
+	adj_end = hole_end = drm_mm_hole_node_end(prev_node);
 
 	if (mm->scan_check_range) {
 		if (adj_start < mm->scan_start)
@@ -586,11 +581,14 @@ int drm_mm_scan_add_block(struct drm_mm_node *node)
 			adj_end = mm->scan_end;
 	}
 
+	if (mm->color_adjust)
+		mm->color_adjust(prev_node, mm->scan_color,
+				 &adj_start, &adj_end);
+
 	if (check_free_hole(adj_start, adj_end,
 			    mm->scan_size, mm->scan_alignment)) {
 		mm->scan_hit_start = hole_start;
-		mm->scan_hit_size = hole_end;
-
+		mm->scan_hit_end = hole_end;
 		return 1;
 	}
 
@@ -626,19 +624,10 @@ int drm_mm_scan_remove_block(struct drm_mm_node *node)
 			       node_list);
 
 	prev_node->hole_follows = node->scanned_preceeds_hole;
-	INIT_LIST_HEAD(&node->node_list);
 	list_add(&node->node_list, &prev_node->node_list);
 
-	/* Only need to check for containement because start&size for the
-	 * complete resulting free block (not just the desired part) is
-	 * stored. */
-	if (node->start >= mm->scan_hit_start &&
-	    node->start + node->size
-	    		<= mm->scan_hit_start + mm->scan_hit_size) {
-		return 1;
-	}
-
-	return 0;
+	 return (drm_mm_hole_node_end(node) > mm->scan_hit_start &&
+		 node->start < mm->scan_hit_end);
 }
 EXPORT_SYMBOL(drm_mm_scan_remove_block);
 
diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
index 0f4a366f6fa6..3527fb3f75bb 100644
--- a/include/drm/drm_mm.h
+++ b/include/drm/drm_mm.h
@@ -70,7 +70,7 @@ struct drm_mm {
 	unsigned long scan_color;
 	unsigned long scan_size;
 	unsigned long scan_hit_start;
-	unsigned scan_hit_size;
+	unsigned long scan_hit_end;
 	unsigned scanned_blocks;
 	unsigned long scan_start;
 	unsigned long scan_end;
-- 
cgit v1.2.3-55-g7522


From 08c097fc3bb283299a6915a6a3795edab85979b1 Mon Sep 17 00:00:00 2001
From: Marc Dionne
Date: Wed, 9 Jan 2013 14:16:30 +0000
Subject: cred: Remove tgcred pointer from struct cred

Commit 3a50597de863 ("KEYS: Make the session and process keyrings
per-thread") removed the definition of the thread_group_cred structure,
but left a now unused pointer in struct cred.

Signed-off-by: Marc Dionne <marc.c.dionne@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cred.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/cred.h b/include/linux/cred.h
index abb2cd50f6b2..04421e825365 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -128,7 +128,6 @@ struct cred {
 	struct key	*process_keyring; /* keyring private to this process */
 	struct key	*thread_keyring; /* keyring private to this thread */
 	struct key	*request_key_auth; /* assumed request_key authority */
-	struct thread_group_cred *tgcred; /* thread-group shared credentials */
 #endif
 #ifdef CONFIG_SECURITY
 	void		*security;	/* subjective LSM security */
-- 
cgit v1.2.3-55-g7522


From 54b956b903607f8f8878754dd4352da6a54a1da2 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman
Date: Thu, 10 Jan 2013 10:57:01 -0800
Subject: Remove __dev* markings from init.h

Now that all in-kernel users of __dev* are gone, let's remove them from
init.h to keep them from popping up again and again.

Thanks to Bill Pemberton for doing all of the hard work to make removal
of this possible.

Cc: Bill Pemberton <wfp5p@virginia.edu>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/init.h | 20 --------------------
 1 file changed, 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/init.h b/include/linux/init.h
index a799273714ac..10ed4f436458 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -93,14 +93,6 @@
 
 #define __exit          __section(.exit.text) __exitused __cold notrace
 
-/* Used for HOTPLUG, but that is always enabled now, so just make them noops */
-#define __devinit
-#define __devinitdata
-#define __devinitconst
-#define __devexit
-#define __devexitdata
-#define __devexitconst
-
 /* Used for HOTPLUG_CPU */
 #define __cpuinit        __section(.cpuinit.text) __cold notrace
 #define __cpuinitdata    __section(.cpuinit.data)
@@ -337,18 +329,6 @@ void __init parse_early_options(char *cmdline);
 #define __INITRODATA_OR_MODULE __INITRODATA
 #endif /*CONFIG_MODULES*/
 
-/* Functions marked as __devexit may be discarded at kernel link time, depending
-   on config options.  Newer versions of binutils detect references from
-   retained sections to discarded sections and flag an error.  Pointers to
-   __devexit functions must use __devexit_p(function_name), the wrapper will
-   insert either the function_name or NULL, depending on the config options.
- */
-#if defined(MODULE) || defined(CONFIG_HOTPLUG)
-#define __devexit_p(x) x
-#else
-#define __devexit_p(x) NULL
-#endif
-
 #ifdef MODULE
 #define __exit_p(x) x
 #else
-- 
cgit v1.2.3-55-g7522


From ba829137bfd167623363548aa385be769c6b2664 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke
Date: Mon, 17 Dec 2012 09:53:33 +0100
Subject: target: Introduce TCM_NO_SENSE

Introduce TCM_NO_SENSE, mapping to sense code
'Not ready, no additional sense information'.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Cc: Nicholas Bellinger <nab@risingtidesystems.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_transport.c | 10 ++++++++++
 include/target/target_core_base.h      |  1 +
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 978762dc81bf..104bf3b45a01 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2597,6 +2597,16 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd,
 	 * SENSE KEY values from include/scsi/scsi.h
 	 */
 	switch (reason) {
+	case TCM_NO_SENSE:
+		/* CURRENT ERROR */
+		buffer[0] = 0x70;
+		buffer[SPC_ADD_SENSE_LEN_OFFSET] = 10;
+		/* Not Ready */
+		buffer[SPC_SENSE_KEY_OFFSET] = NOT_READY;
+		/* NO ADDITIONAL SENSE INFORMATION */
+		buffer[SPC_ASC_KEY_OFFSET] = 0;
+		buffer[SPC_ASCQ_KEY_OFFSET] = 0;
+		break;
 	case TCM_NON_EXISTENT_LUN:
 		/* CURRENT ERROR */
 		buffer[0] = 0x70;
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 7cae2360221e..663e34a5383f 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -174,6 +174,7 @@ typedef unsigned __bitwise__ sense_reason_t;
 
 enum tcm_sense_reason_table {
 #define R(x)	(__force sense_reason_t )(x)
+	TCM_NO_SENSE				= R(0x00),
 	TCM_NON_EXISTENT_LUN			= R(0x01),
 	TCM_UNSUPPORTED_SCSI_OPCODE		= R(0x02),
 	TCM_INCORRECT_AMOUNT_OF_DATA		= R(0x03),
-- 
cgit v1.2.3-55-g7522


From 47ecfcb7d01418fcbfbc75183ba5e28e98b667b2 Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Fri, 11 Jan 2013 09:27:01 +0000
Subject: mm: compaction: Partially revert capture of suitable high-order page

Eric Wong reported on 3.7 and 3.8-rc2 that ppoll() got stuck when
waiting for POLLIN on a local TCP socket.  It was easier to trigger if
there was disk IO and dirty pages at the same time and he bisected it to
commit 1fb3f8ca0e92 ("mm: compaction: capture a suitable high-order page
immediately when it is made available").

The intention of that patch was to improve high-order allocations under
memory pressure after changes made to reclaim in 3.6 drastically hurt
THP allocations but the approach was flawed.  For Eric, the problem was
that page->pfmemalloc was not being cleared for captured pages leading
to a poor interaction with swap-over-NFS support causing the packets to
be dropped.  However, I identified a few more problems with the patch
including the fact that it can increase contention on zone->lock in some
cases which could result in async direct compaction being aborted early.

In retrospect the capture patch took the wrong approach.  What it should
have done is mark the pageblock being migrated as MIGRATE_ISOLATE if it
was allocating for THP and avoided races that way.  While the patch was
showing to improve allocation success rates at the time, the benefit is
marginal given the relative complexity and it should be revisited from
scratch in the context of the other reclaim-related changes that have
taken place since the patch was first written and tested.  This patch
partially reverts commit 1fb3f8ca "mm: compaction: capture a suitable
high-order page immediately when it is made available".

Reported-and-tested-by: Eric Wong <normalperson@yhbt.net>
Tested-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h |  4 +-
 include/linux/mm.h         |  1 -
 mm/compaction.c            | 92 +++++++---------------------------------------
 mm/internal.h              |  1 -
 mm/page_alloc.c            | 35 ++++--------------
 5 files changed, 23 insertions(+), 110 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 6ecb6dc2f303..cc7bddeaf553 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
-			bool sync, bool *contended, struct page **page);
+			bool sync, bool *contended);
 extern int compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
@@ -75,7 +75,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync, bool *contended, struct page **page)
+			bool sync, bool *contended)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 63204078f72b..66e2f7c61e5c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -455,7 +455,6 @@ void put_pages_list(struct list_head *pages);
 
 void split_page(struct page *page, unsigned int order);
 int split_free_page(struct page *page);
-int capture_free_page(struct page *page, int alloc_order, int migratetype);
 
 /*
  * Compound pages have a destructor function.  Provide a
diff --git a/mm/compaction.c b/mm/compaction.c
index 6b807e466497..2c570432aa56 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -816,6 +816,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 static int compact_finished(struct zone *zone,
 			    struct compact_control *cc)
 {
+	unsigned int order;
 	unsigned long watermark;
 
 	if (fatal_signal_pending(current))
@@ -850,22 +851,16 @@ static int compact_finished(struct zone *zone,
 		return COMPACT_CONTINUE;
 
 	/* Direct compactor: Is a suitable page free? */
-	if (cc->page) {
-		/* Was a suitable page captured? */
-		if (*cc->page)
+	for (order = cc->order; order < MAX_ORDER; order++) {
+		struct free_area *area = &zone->free_area[order];
+
+		/* Job done if page is free of the right migratetype */
+		if (!list_empty(&area->free_list[cc->migratetype]))
+			return COMPACT_PARTIAL;
+
+		/* Job done if allocation would set block type */
+		if (cc->order >= pageblock_order && area->nr_free)
 			return COMPACT_PARTIAL;
-	} else {
-		unsigned int order;
-		for (order = cc->order; order < MAX_ORDER; order++) {
-			struct free_area *area = &zone->free_area[cc->order];
-			/* Job done if page is free of the right migratetype */
-			if (!list_empty(&area->free_list[cc->migratetype]))
-				return COMPACT_PARTIAL;
-
-			/* Job done if allocation would set block type */
-			if (cc->order >= pageblock_order && area->nr_free)
-				return COMPACT_PARTIAL;
-		}
 	}
 
 	return COMPACT_CONTINUE;
@@ -921,60 +916,6 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	return COMPACT_CONTINUE;
 }
 
-static void compact_capture_page(struct compact_control *cc)
-{
-	unsigned long flags;
-	int mtype, mtype_low, mtype_high;
-
-	if (!cc->page || *cc->page)
-		return;
-
-	/*
-	 * For MIGRATE_MOVABLE allocations we capture a suitable page ASAP
-	 * regardless of the migratetype of the freelist is is captured from.
-	 * This is fine because the order for a high-order MIGRATE_MOVABLE
-	 * allocation is typically at least a pageblock size and overall
-	 * fragmentation is not impaired. Other allocation types must
-	 * capture pages from their own migratelist because otherwise they
-	 * could pollute other pageblocks like MIGRATE_MOVABLE with
-	 * difficult to move pages and making fragmentation worse overall.
-	 */
-	if (cc->migratetype == MIGRATE_MOVABLE) {
-		mtype_low = 0;
-		mtype_high = MIGRATE_PCPTYPES;
-	} else {
-		mtype_low = cc->migratetype;
-		mtype_high = cc->migratetype + 1;
-	}
-
-	/* Speculatively examine the free lists without zone lock */
-	for (mtype = mtype_low; mtype < mtype_high; mtype++) {
-		int order;
-		for (order = cc->order; order < MAX_ORDER; order++) {
-			struct page *page;
-			struct free_area *area;
-			area = &(cc->zone->free_area[order]);
-			if (list_empty(&area->free_list[mtype]))
-				continue;
-
-			/* Take the lock and attempt capture of the page */
-			if (!compact_trylock_irqsave(&cc->zone->lock, &flags, cc))
-				return;
-			if (!list_empty(&area->free_list[mtype])) {
-				page = list_entry(area->free_list[mtype].next,
-							struct page, lru);
-				if (capture_free_page(page, cc->order, mtype)) {
-					spin_unlock_irqrestore(&cc->zone->lock,
-									flags);
-					*cc->page = page;
-					return;
-				}
-			}
-			spin_unlock_irqrestore(&cc->zone->lock, flags);
-		}
-	}
-}
-
 static int compact_zone(struct zone *zone, struct compact_control *cc)
 {
 	int ret;
@@ -1054,9 +995,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 				goto out;
 			}
 		}
-
-		/* Capture a page now if it is a suitable size */
-		compact_capture_page(cc);
 	}
 
 out:
@@ -1069,8 +1007,7 @@ out:
 
 static unsigned long compact_zone_order(struct zone *zone,
 				 int order, gfp_t gfp_mask,
-				 bool sync, bool *contended,
-				 struct page **page)
+				 bool sync, bool *contended)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1080,7 +1017,6 @@ static unsigned long compact_zone_order(struct zone *zone,
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
 		.sync = sync,
-		.page = page,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1110,7 +1046,7 @@ int sysctl_extfrag_threshold = 500;
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync, bool *contended, struct page **page)
+			bool sync, bool *contended)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1136,7 +1072,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		int status;
 
 		status = compact_zone_order(zone, order, gfp_mask, sync,
-						contended, page);
+						contended);
 		rc = max(status, rc);
 
 		/* If a normal allocation would succeed, stop compacting */
@@ -1192,7 +1128,6 @@ int compact_pgdat(pg_data_t *pgdat, int order)
 	struct compact_control cc = {
 		.order = order,
 		.sync = false,
-		.page = NULL,
 	};
 
 	return __compact_pgdat(pgdat, &cc);
@@ -1203,7 +1138,6 @@ static int compact_node(int nid)
 	struct compact_control cc = {
 		.order = -1,
 		.sync = true,
-		.page = NULL,
 	};
 
 	return __compact_pgdat(NODE_DATA(nid), &cc);
diff --git a/mm/internal.h b/mm/internal.h
index d597f94cc205..9ba21100ebf3 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -135,7 +135,6 @@ struct compact_control {
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
 	bool contended;			/* True if a lock was contended */
-	struct page **page;		/* Page captured of requested size */
 };
 
 unsigned long
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bc6cc0e913bd..ece7b8e8a5b6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1384,14 +1384,8 @@ void split_page(struct page *page, unsigned int order)
 		set_page_refcounted(page + i);
 }
 
-/*
- * Similar to the split_page family of functions except that the page
- * required at the given order and being isolated now to prevent races
- * with parallel allocators
- */
-int capture_free_page(struct page *page, int alloc_order, int migratetype)
+static int __isolate_free_page(struct page *page, unsigned int order)
 {
-	unsigned int order;
 	unsigned long watermark;
 	struct zone *zone;
 	int mt;
@@ -1399,7 +1393,6 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 	BUG_ON(!PageBuddy(page));
 
 	zone = page_zone(page);
-	order = page_order(page);
 	mt = get_pageblock_migratetype(page);
 
 	if (mt != MIGRATE_ISOLATE) {
@@ -1408,7 +1401,7 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
 			return 0;
 
-		__mod_zone_freepage_state(zone, -(1UL << alloc_order), mt);
+		__mod_zone_freepage_state(zone, -(1UL << order), mt);
 	}
 
 	/* Remove page from free list */
@@ -1416,11 +1409,7 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 	zone->free_area[order].nr_free--;
 	rmv_page_order(page);
 
-	if (alloc_order != order)
-		expand(zone, page, alloc_order, order,
-			&zone->free_area[order], migratetype);
-
-	/* Set the pageblock if the captured page is at least a pageblock */
+	/* Set the pageblock if the isolated page is at least a pageblock */
 	if (order >= pageblock_order - 1) {
 		struct page *endpage = page + (1 << order) - 1;
 		for (; page < endpage; page += pageblock_nr_pages) {
@@ -1431,7 +1420,7 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 		}
 	}
 
-	return 1UL << alloc_order;
+	return 1UL << order;
 }
 
 /*
@@ -1449,10 +1438,9 @@ int split_free_page(struct page *page)
 	unsigned int order;
 	int nr_pages;
 
-	BUG_ON(!PageBuddy(page));
 	order = page_order(page);
 
-	nr_pages = capture_free_page(page, order, 0);
+	nr_pages = __isolate_free_page(page, order);
 	if (!nr_pages)
 		return 0;
 
@@ -2136,8 +2124,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	bool *contended_compaction, bool *deferred_compaction,
 	unsigned long *did_some_progress)
 {
-	struct page *page = NULL;
-
 	if (!order)
 		return NULL;
 
@@ -2149,16 +2135,12 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, sync_migration,
-						contended_compaction, &page);
+						contended_compaction);
 	current->flags &= ~PF_MEMALLOC;
 
-	/* If compaction captured a page, prep and use it */
-	if (page) {
-		prep_new_page(page, order, gfp_mask);
-		goto got_page;
-	}
-
 	if (*did_some_progress != COMPACT_SKIPPED) {
+		struct page *page;
+
 		/* Page migration frees to the PCP lists but we want merging */
 		drain_pages(get_cpu());
 		put_cpu();
@@ -2168,7 +2150,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 				alloc_flags & ~ALLOC_NO_WATERMARKS,
 				preferred_zone, migratetype);
 		if (page) {
-got_page:
 			preferred_zone->compact_blockskip_flush = false;
 			preferred_zone->compact_considered = 0;
 			preferred_zone->compact_defer_shift = 0;
-- 
cgit v1.2.3-55-g7522


From 896f97ea95c1d29c0520ee0766b66b7f64cb967c Mon Sep 17 00:00:00 2001
From: David Decotigny
Date: Fri, 11 Jan 2013 14:31:36 -0800
Subject: lib: cpu_rmap: avoid flushing all workqueues

In some cases, free_irq_cpu_rmap() is called while holding a lock (eg
rtnl).  This can lead to deadlocks, because it invokes
flush_scheduled_work() which ends up waiting for whole system workqueue
to flush, but some pending works might try to acquire the lock we are
already holding.

This commit uses reference-counting to replace
irq_run_affinity_notifiers().  It also removes
irq_run_affinity_notifiers() altogether.

[akpm@linux-foundation.org: eliminate free_cpu_rmap, rename cpu_rmap_reclaim() to cpu_rmap_release(), propagate kref_put() retval from cpu_rmap_put()]
Signed-off-by: David Decotigny <decot@googlers.com>
Reviewed-by: Ben Hutchings <bhutchings@solarflare.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Acked-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cpu_rmap.h  | 13 ++++--------
 include/linux/interrupt.h |  5 -----
 lib/cpu_rmap.c            | 54 ++++++++++++++++++++++++++++++++++++++++++-----
 3 files changed, 53 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h
index ac3bbb5b9502..1739510d8994 100644
--- a/include/linux/cpu_rmap.h
+++ b/include/linux/cpu_rmap.h
@@ -13,9 +13,11 @@
 #include <linux/cpumask.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/kref.h>
 
 /**
  * struct cpu_rmap - CPU affinity reverse-map
+ * @refcount: kref for object
  * @size: Number of objects to be reverse-mapped
  * @used: Number of objects added
  * @obj: Pointer to array of object pointers
@@ -23,6 +25,7 @@
  *      based on affinity masks
  */
 struct cpu_rmap {
+	struct kref	refcount;
 	u16		size, used;
 	void		**obj;
 	struct {
@@ -33,15 +36,7 @@ struct cpu_rmap {
 #define CPU_RMAP_DIST_INF 0xffff
 
 extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags);
-
-/**
- * free_cpu_rmap - free CPU affinity reverse-map
- * @rmap: Reverse-map allocated with alloc_cpu_rmap(), or %NULL
- */
-static inline void free_cpu_rmap(struct cpu_rmap *rmap)
-{
-	kfree(rmap);
-}
+extern int cpu_rmap_put(struct cpu_rmap *rmap);
 
 extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj);
 extern int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 5e4e6170f43a..5fa5afeeb759 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -268,11 +268,6 @@ struct irq_affinity_notify {
 extern int
 irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
 
-static inline void irq_run_affinity_notifiers(void)
-{
-	flush_scheduled_work();
-}
-
 #else /* CONFIG_SMP */
 
 static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 145dec5267c9..5fbed5caba6e 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -45,6 +45,7 @@ struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
 	if (!rmap)
 		return NULL;
 
+	kref_init(&rmap->refcount);
 	rmap->obj = (void **)((char *)rmap + obj_offset);
 
 	/* Initially assign CPUs to objects on a rota, since we have
@@ -63,6 +64,35 @@ struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
 }
 EXPORT_SYMBOL(alloc_cpu_rmap);
 
+/**
+ * cpu_rmap_release - internal reclaiming helper called from kref_put
+ * @ref: kref to struct cpu_rmap
+ */
+static void cpu_rmap_release(struct kref *ref)
+{
+	struct cpu_rmap *rmap = container_of(ref, struct cpu_rmap, refcount);
+	kfree(rmap);
+}
+
+/**
+ * cpu_rmap_get - internal helper to get new ref on a cpu_rmap
+ * @rmap: reverse-map allocated with alloc_cpu_rmap()
+ */
+static inline void cpu_rmap_get(struct cpu_rmap *rmap)
+{
+	kref_get(&rmap->refcount);
+}
+
+/**
+ * cpu_rmap_put - release ref on a cpu_rmap
+ * @rmap: reverse-map allocated with alloc_cpu_rmap()
+ */
+int cpu_rmap_put(struct cpu_rmap *rmap)
+{
+	return kref_put(&rmap->refcount, cpu_rmap_release);
+}
+EXPORT_SYMBOL(cpu_rmap_put);
+
 /* Reevaluate nearest object for given CPU, comparing with the given
  * neighbours at the given distance.
  */
@@ -197,8 +227,7 @@ struct irq_glue {
  * free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs
  * @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL
  *
- * Must be called in process context, before freeing the IRQs, and
- * without holding any locks required by global workqueue items.
+ * Must be called in process context, before freeing the IRQs.
  */
 void free_irq_cpu_rmap(struct cpu_rmap *rmap)
 {
@@ -212,12 +241,18 @@ void free_irq_cpu_rmap(struct cpu_rmap *rmap)
 		glue = rmap->obj[index];
 		irq_set_affinity_notifier(glue->notify.irq, NULL);
 	}
-	irq_run_affinity_notifiers();
 
-	kfree(rmap);
+	cpu_rmap_put(rmap);
 }
 EXPORT_SYMBOL(free_irq_cpu_rmap);
 
+/**
+ * irq_cpu_rmap_notify - callback for IRQ subsystem when IRQ affinity updated
+ * @notify: struct irq_affinity_notify passed by irq/manage.c
+ * @mask: cpu mask for new SMP affinity
+ *
+ * This is executed in workqueue context.
+ */
 static void
 irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
 {
@@ -230,10 +265,16 @@ irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
 		pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc);
 }
 
+/**
+ * irq_cpu_rmap_release - reclaiming callback for IRQ subsystem
+ * @ref: kref to struct irq_affinity_notify passed by irq/manage.c
+ */
 static void irq_cpu_rmap_release(struct kref *ref)
 {
 	struct irq_glue *glue =
 		container_of(ref, struct irq_glue, notify.kref);
+
+	cpu_rmap_put(glue->rmap);
 	kfree(glue);
 }
 
@@ -258,10 +299,13 @@ int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
 	glue->notify.notify = irq_cpu_rmap_notify;
 	glue->notify.release = irq_cpu_rmap_release;
 	glue->rmap = rmap;
+	cpu_rmap_get(rmap);
 	glue->index = cpu_rmap_add(rmap, glue);
 	rc = irq_set_affinity_notifier(irq, &glue->notify);
-	if (rc)
+	if (rc) {
+		cpu_rmap_put(glue->rmap);
 		kfree(glue);
+	}
 	return rc;
 }
 EXPORT_SYMBOL(irq_cpu_rmap_add);
-- 
cgit v1.2.3-55-g7522


From 1b963c81b14509e330e0fe3218b645ece2738dc5 Mon Sep 17 00:00:00 2001
From: Jiri Kosina
Date: Fri, 11 Jan 2013 14:31:56 -0800
Subject: lockdep, rwsem: provide down_write_nest_lock()

down_write_nest_lock() provides a means to annotate locking scenario
where an outer lock is guaranteed to serialize the order nested locks
are being acquired.

This is analogoue to already existing mutex_lock_nest_lock() and
spin_lock_nest_lock().

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mel Gorman <mel@csn.ul.ie>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/lockdep.h |  3 +++
 include/linux/rwsem.h   |  9 +++++++++
 kernel/rwsem.c          | 10 ++++++++++
 3 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 00e46376e28f..2bca44b0893c 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -524,14 +524,17 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
 #  define rwsem_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 2, NULL, i)
+#  define rwsem_acquire_nest(l, s, t, n, i)	lock_acquire(l, s, t, 0, 2, n, i)
 #  define rwsem_acquire_read(l, s, t, i)	lock_acquire(l, s, t, 1, 2, NULL, i)
 # else
 #  define rwsem_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 1, NULL, i)
+#  define rwsem_acquire_nest(l, s, t, n, i)	lock_acquire(l, s, t, 0, 1, n, i)
 #  define rwsem_acquire_read(l, s, t, i)	lock_acquire(l, s, t, 1, 1, NULL, i)
 # endif
 # define rwsem_release(l, n, i)			lock_release(l, n, i)
 #else
 # define rwsem_acquire(l, s, t, i)		do { } while (0)
+# define rwsem_acquire_nest(l, s, t, n, i)	do { } while (0)
 # define rwsem_acquire_read(l, s, t, i)		do { } while (0)
 # define rwsem_release(l, n, i)			do { } while (0)
 #endif
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 54bd7cd7ecbd..413cc11e414a 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -125,8 +125,17 @@ extern void downgrade_write(struct rw_semaphore *sem);
  */
 extern void down_read_nested(struct rw_semaphore *sem, int subclass);
 extern void down_write_nested(struct rw_semaphore *sem, int subclass);
+extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock);
+
+# define down_write_nest_lock(sem, nest_lock)			\
+do {								\
+	typecheck(struct lockdep_map *, &(nest_lock)->dep_map);	\
+	_down_write_nest_lock(sem, &(nest_lock)->dep_map);	\
+} while (0);
+
 #else
 # define down_read_nested(sem, subclass)		down_read(sem)
+# define down_write_nest_lock(sem, nest_lock)	down_read(sem)
 # define down_write_nested(sem, subclass)	down_write(sem)
 #endif
 
diff --git a/kernel/rwsem.c b/kernel/rwsem.c
index 6850f53e02d8..b3c6c3fcd847 100644
--- a/kernel/rwsem.c
+++ b/kernel/rwsem.c
@@ -116,6 +116,16 @@ void down_read_nested(struct rw_semaphore *sem, int subclass)
 
 EXPORT_SYMBOL(down_read_nested);
 
+void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
+{
+	might_sleep();
+	rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
+
+	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
+}
+
+EXPORT_SYMBOL(_down_write_nest_lock);
+
 void down_write_nested(struct rw_semaphore *sem, int subclass)
 {
 	might_sleep();
-- 
cgit v1.2.3-55-g7522


From 7b9205bd775afc4439ed86d617f9042ee9e76a71 Mon Sep 17 00:00:00 2001
From: Kees Cook
Date: Fri, 11 Jan 2013 14:32:05 -0800
Subject: audit: create explicit AUDIT_SECCOMP event type

The seccomp path was using AUDIT_ANOM_ABEND from when seccomp mode 1
could only kill a process.  While we still want to make sure an audit
record is forced on a kill, this should use a separate record type since
seccomp mode 2 introduces other behaviors.

In the case of "handled" behaviors (process wasn't killed), only emit a
record if the process is under inspection.  This change also fixes
userspace examination of seccomp audit events, since it was considered
malformed due to missing fields of the AUDIT_ANOM_ABEND event type.

Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Eric Paris <eparis@redhat.com>
Cc: Jeff Layton <jlayton@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Julien Tinnes <jln@google.com>
Acked-by: Will Drewry <wad@chromium.org>
Acked-by: Steve Grubb <sgrubb@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/audit.h      |  3 ++-
 include/uapi/linux/audit.h |  1 +
 kernel/auditsc.c           | 14 +++++++++++---
 3 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index bce729afbcf9..9d5104d7aba9 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -157,7 +157,8 @@ void audit_core_dumps(long signr);
 
 static inline void audit_seccomp(unsigned long syscall, long signr, int code)
 {
-	if (unlikely(!audit_dummy_context()))
+	/* Force a record to be reported if a signal was delivered. */
+	if (signr || unlikely(!audit_dummy_context()))
 		__audit_seccomp(syscall, signr, code);
 }
 
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 76352ac45f24..09a2d94ab113 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -106,6 +106,7 @@
 #define AUDIT_MMAP		1323	/* Record showing descriptor and flags in mmap */
 #define AUDIT_NETFILTER_PKT	1324	/* Packets traversing netfilter chains */
 #define AUDIT_NETFILTER_CFG	1325	/* Netfilter chain modifications */
+#define AUDIT_SECCOMP		1326	/* Secure Computing event */
 
 #define AUDIT_AVC		1400	/* SE Linux avc denial or grant */
 #define AUDIT_SELINUX_ERR	1401	/* Internal SE Linux Errors */
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index e37e6a12c5e3..3e46d1dec613 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2675,7 +2675,7 @@ void __audit_mmap_fd(int fd, int flags)
 	context->type = AUDIT_MMAP;
 }
 
-static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
+static void audit_log_task(struct audit_buffer *ab)
 {
 	kuid_t auid, uid;
 	kgid_t gid;
@@ -2693,6 +2693,11 @@ static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
 	audit_log_task_context(ab);
 	audit_log_format(ab, " pid=%d comm=", current->pid);
 	audit_log_untrustedstring(ab, current->comm);
+}
+
+static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
+{
+	audit_log_task(ab);
 	audit_log_format(ab, " reason=");
 	audit_log_string(ab, reason);
 	audit_log_format(ab, " sig=%ld", signr);
@@ -2723,8 +2728,11 @@ void __audit_seccomp(unsigned long syscall, long signr, int code)
 {
 	struct audit_buffer *ab;
 
-	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
-	audit_log_abend(ab, "seccomp", signr);
+	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_SECCOMP);
+	if (unlikely(!ab))
+		return;
+	audit_log_task(ab);
+	audit_log_format(ab, " sig=%ld", signr);
 	audit_log_format(ab, " syscall=%ld", syscall);
 	audit_log_format(ab, " compat=%d", is_compat_task());
 	audit_log_format(ab, " ip=0x%lx", KSTK_EIP(current));
-- 
cgit v1.2.3-55-g7522


From c0a3a20b6c4b5229ef5d26fd9b1c4b1957632aa7 Mon Sep 17 00:00:00 2001
From: Mike Frysinger
Date: Fri, 11 Jan 2013 14:32:13 -0800
Subject: linux/audit.h: move ptrace.h include to kernel header

While the kernel internals want pt_regs (and so it includes
linux/ptrace.h), the user version of audit.h does not need it.  So move
the include out of the uapi version.

This avoids issues where people want the audit defines and userland
ptrace api.  Including both the kernel ptrace and the userland ptrace
headers can easily lead to failure.

Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Cc: Eric Paris <eparis@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/audit.h      | 1 +
 include/uapi/linux/audit.h | 1 -
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 9d5104d7aba9..5a6d718adf34 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -24,6 +24,7 @@
 #define _LINUX_AUDIT_H_
 
 #include <linux/sched.h>
+#include <linux/ptrace.h>
 #include <uapi/linux/audit.h>
 
 struct audit_sig_info {
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 09a2d94ab113..9f096f1c0907 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -26,7 +26,6 @@
 
 #include <linux/types.h>
 #include <linux/elf-em.h>
-#include <linux/ptrace.h>
 
 /* The netlink messages for the audit system is divided into blocks:
  * 1000 - 1099 are for commanding the audit system
-- 
cgit v1.2.3-55-g7522


From 8fb74b9fb2b182d54beee592350d9ea1f325917a Mon Sep 17 00:00:00 2001
From: Mel Gorman
Date: Fri, 11 Jan 2013 14:32:16 -0800
Subject: mm: compaction: partially revert capture of suitable high-order page

Eric Wong reported on 3.7 and 3.8-rc2 that ppoll() got stuck when
waiting for POLLIN on a local TCP socket.  It was easier to trigger if
there was disk IO and dirty pages at the same time and he bisected it to
commit 1fb3f8ca0e92 ("mm: compaction: capture a suitable high-order page
immediately when it is made available").

The intention of that patch was to improve high-order allocations under
memory pressure after changes made to reclaim in 3.6 drastically hurt
THP allocations but the approach was flawed.  For Eric, the problem was
that page->pfmemalloc was not being cleared for captured pages leading
to a poor interaction with swap-over-NFS support causing the packets to
be dropped.  However, I identified a few more problems with the patch
including the fact that it can increase contention on zone->lock in some
cases which could result in async direct compaction being aborted early.

In retrospect the capture patch took the wrong approach.  What it should
have done is mark the pageblock being migrated as MIGRATE_ISOLATE if it
was allocating for THP and avoided races that way.  While the patch was
showing to improve allocation success rates at the time, the benefit is
marginal given the relative complexity and it should be revisited from
scratch in the context of the other reclaim-related changes that have
taken place since the patch was first written and tested.  This patch
partially reverts commit 1fb3f8ca0e92 ("mm: compaction: capture a
suitable high-order page immediately when it is made available").

Reported-and-tested-by: Eric Wong <normalperson@yhbt.net>
Tested-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h |  4 +-
 include/linux/mm.h         |  1 -
 mm/compaction.c            | 92 +++++++---------------------------------------
 mm/internal.h              |  1 -
 mm/page_alloc.c            | 35 ++++--------------
 5 files changed, 23 insertions(+), 110 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 6ecb6dc2f303..cc7bddeaf553 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
-			bool sync, bool *contended, struct page **page);
+			bool sync, bool *contended);
 extern int compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
@@ -75,7 +75,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync, bool *contended, struct page **page)
+			bool sync, bool *contended)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 63204078f72b..66e2f7c61e5c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -455,7 +455,6 @@ void put_pages_list(struct list_head *pages);
 
 void split_page(struct page *page, unsigned int order);
 int split_free_page(struct page *page);
-int capture_free_page(struct page *page, int alloc_order, int migratetype);
 
 /*
  * Compound pages have a destructor function.  Provide a
diff --git a/mm/compaction.c b/mm/compaction.c
index f8f5c111b7d7..c62bd063d766 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -816,6 +816,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 static int compact_finished(struct zone *zone,
 			    struct compact_control *cc)
 {
+	unsigned int order;
 	unsigned long watermark;
 
 	if (fatal_signal_pending(current))
@@ -850,22 +851,16 @@ static int compact_finished(struct zone *zone,
 		return COMPACT_CONTINUE;
 
 	/* Direct compactor: Is a suitable page free? */
-	if (cc->page) {
-		/* Was a suitable page captured? */
-		if (*cc->page)
+	for (order = cc->order; order < MAX_ORDER; order++) {
+		struct free_area *area = &zone->free_area[order];
+
+		/* Job done if page is free of the right migratetype */
+		if (!list_empty(&area->free_list[cc->migratetype]))
+			return COMPACT_PARTIAL;
+
+		/* Job done if allocation would set block type */
+		if (cc->order >= pageblock_order && area->nr_free)
 			return COMPACT_PARTIAL;
-	} else {
-		unsigned int order;
-		for (order = cc->order; order < MAX_ORDER; order++) {
-			struct free_area *area = &zone->free_area[cc->order];
-			/* Job done if page is free of the right migratetype */
-			if (!list_empty(&area->free_list[cc->migratetype]))
-				return COMPACT_PARTIAL;
-
-			/* Job done if allocation would set block type */
-			if (cc->order >= pageblock_order && area->nr_free)
-				return COMPACT_PARTIAL;
-		}
 	}
 
 	return COMPACT_CONTINUE;
@@ -921,60 +916,6 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	return COMPACT_CONTINUE;
 }
 
-static void compact_capture_page(struct compact_control *cc)
-{
-	unsigned long flags;
-	int mtype, mtype_low, mtype_high;
-
-	if (!cc->page || *cc->page)
-		return;
-
-	/*
-	 * For MIGRATE_MOVABLE allocations we capture a suitable page ASAP
-	 * regardless of the migratetype of the freelist is is captured from.
-	 * This is fine because the order for a high-order MIGRATE_MOVABLE
-	 * allocation is typically at least a pageblock size and overall
-	 * fragmentation is not impaired. Other allocation types must
-	 * capture pages from their own migratelist because otherwise they
-	 * could pollute other pageblocks like MIGRATE_MOVABLE with
-	 * difficult to move pages and making fragmentation worse overall.
-	 */
-	if (cc->migratetype == MIGRATE_MOVABLE) {
-		mtype_low = 0;
-		mtype_high = MIGRATE_PCPTYPES;
-	} else {
-		mtype_low = cc->migratetype;
-		mtype_high = cc->migratetype + 1;
-	}
-
-	/* Speculatively examine the free lists without zone lock */
-	for (mtype = mtype_low; mtype < mtype_high; mtype++) {
-		int order;
-		for (order = cc->order; order < MAX_ORDER; order++) {
-			struct page *page;
-			struct free_area *area;
-			area = &(cc->zone->free_area[order]);
-			if (list_empty(&area->free_list[mtype]))
-				continue;
-
-			/* Take the lock and attempt capture of the page */
-			if (!compact_trylock_irqsave(&cc->zone->lock, &flags, cc))
-				return;
-			if (!list_empty(&area->free_list[mtype])) {
-				page = list_entry(area->free_list[mtype].next,
-							struct page, lru);
-				if (capture_free_page(page, cc->order, mtype)) {
-					spin_unlock_irqrestore(&cc->zone->lock,
-									flags);
-					*cc->page = page;
-					return;
-				}
-			}
-			spin_unlock_irqrestore(&cc->zone->lock, flags);
-		}
-	}
-}
-
 static int compact_zone(struct zone *zone, struct compact_control *cc)
 {
 	int ret;
@@ -1054,9 +995,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 				goto out;
 			}
 		}
-
-		/* Capture a page now if it is a suitable size */
-		compact_capture_page(cc);
 	}
 
 out:
@@ -1069,8 +1007,7 @@ out:
 
 static unsigned long compact_zone_order(struct zone *zone,
 				 int order, gfp_t gfp_mask,
-				 bool sync, bool *contended,
-				 struct page **page)
+				 bool sync, bool *contended)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1080,7 +1017,6 @@ static unsigned long compact_zone_order(struct zone *zone,
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
 		.sync = sync,
-		.page = page,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1110,7 +1046,7 @@ int sysctl_extfrag_threshold = 500;
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync, bool *contended, struct page **page)
+			bool sync, bool *contended)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1136,7 +1072,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		int status;
 
 		status = compact_zone_order(zone, order, gfp_mask, sync,
-						contended, page);
+						contended);
 		rc = max(status, rc);
 
 		/* If a normal allocation would succeed, stop compacting */
@@ -1192,7 +1128,6 @@ int compact_pgdat(pg_data_t *pgdat, int order)
 	struct compact_control cc = {
 		.order = order,
 		.sync = false,
-		.page = NULL,
 	};
 
 	return __compact_pgdat(pgdat, &cc);
@@ -1203,7 +1138,6 @@ static int compact_node(int nid)
 	struct compact_control cc = {
 		.order = -1,
 		.sync = true,
-		.page = NULL,
 	};
 
 	return __compact_pgdat(NODE_DATA(nid), &cc);
diff --git a/mm/internal.h b/mm/internal.h
index d597f94cc205..9ba21100ebf3 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -135,7 +135,6 @@ struct compact_control {
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
 	bool contended;			/* True if a lock was contended */
-	struct page **page;		/* Page captured of requested size */
 };
 
 unsigned long
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c957805a7f0e..df2022ff0c8a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1384,14 +1384,8 @@ void split_page(struct page *page, unsigned int order)
 		set_page_refcounted(page + i);
 }
 
-/*
- * Similar to the split_page family of functions except that the page
- * required at the given order and being isolated now to prevent races
- * with parallel allocators
- */
-int capture_free_page(struct page *page, int alloc_order, int migratetype)
+static int __isolate_free_page(struct page *page, unsigned int order)
 {
-	unsigned int order;
 	unsigned long watermark;
 	struct zone *zone;
 	int mt;
@@ -1399,7 +1393,6 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 	BUG_ON(!PageBuddy(page));
 
 	zone = page_zone(page);
-	order = page_order(page);
 	mt = get_pageblock_migratetype(page);
 
 	if (mt != MIGRATE_ISOLATE) {
@@ -1408,7 +1401,7 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
 			return 0;
 
-		__mod_zone_freepage_state(zone, -(1UL << alloc_order), mt);
+		__mod_zone_freepage_state(zone, -(1UL << order), mt);
 	}
 
 	/* Remove page from free list */
@@ -1416,11 +1409,7 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 	zone->free_area[order].nr_free--;
 	rmv_page_order(page);
 
-	if (alloc_order != order)
-		expand(zone, page, alloc_order, order,
-			&zone->free_area[order], migratetype);
-
-	/* Set the pageblock if the captured page is at least a pageblock */
+	/* Set the pageblock if the isolated page is at least a pageblock */
 	if (order >= pageblock_order - 1) {
 		struct page *endpage = page + (1 << order) - 1;
 		for (; page < endpage; page += pageblock_nr_pages) {
@@ -1431,7 +1420,7 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 		}
 	}
 
-	return 1UL << alloc_order;
+	return 1UL << order;
 }
 
 /*
@@ -1449,10 +1438,9 @@ int split_free_page(struct page *page)
 	unsigned int order;
 	int nr_pages;
 
-	BUG_ON(!PageBuddy(page));
 	order = page_order(page);
 
-	nr_pages = capture_free_page(page, order, 0);
+	nr_pages = __isolate_free_page(page, order);
 	if (!nr_pages)
 		return 0;
 
@@ -2136,8 +2124,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	bool *contended_compaction, bool *deferred_compaction,
 	unsigned long *did_some_progress)
 {
-	struct page *page = NULL;
-
 	if (!order)
 		return NULL;
 
@@ -2149,16 +2135,12 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, sync_migration,
-						contended_compaction, &page);
+						contended_compaction);
 	current->flags &= ~PF_MEMALLOC;
 
-	/* If compaction captured a page, prep and use it */
-	if (page) {
-		prep_new_page(page, order, gfp_mask);
-		goto got_page;
-	}
-
 	if (*did_some_progress != COMPACT_SKIPPED) {
+		struct page *page;
+
 		/* Page migration frees to the PCP lists but we want merging */
 		drain_pages(get_cpu());
 		put_cpu();
@@ -2168,7 +2150,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 				alloc_flags & ~ALLOC_NO_WATERMARKS,
 				preferred_zone, migratetype);
 		if (page) {
-got_page:
 			preferred_zone->compact_blockskip_flush = false;
 			preferred_zone->compact_considered = 0;
 			preferred_zone->compact_defer_shift = 0;
-- 
cgit v1.2.3-55-g7522


From 3cb7a56344ca45ee56d71c5f8fe9f922306bff1f Mon Sep 17 00:00:00 2001
From: Michel Lespinasse
Date: Fri, 11 Jan 2013 14:32:20 -0800
Subject: lib/rbtree.c: avoid the use of non-static __always_inline

lib/rbtree.c declared __rb_erase_color() as __always_inline void, and
then exported it with EXPORT_SYMBOL.

This was because __rb_erase_color() must be exported for augmented
rbtree users, but it must also be inlined into rb_erase() so that the
dummy callback can get optimized out of that call site.

(Actually with a modern compiler, none of the dummy callback functions
should even be generated as separate text functions).

The above usage is legal C, but it was unusual enough for some compilers
to warn about it.  This change makes things more explicit, with a static
__always_inline ____rb_erase_color function for use in rb_erase(), and a
separate non-inline __rb_erase_color function for use in
rb_erase_augmented call sites.

Signed-off-by: Michel Lespinasse <walken@google.com>
Reported-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/rbtree_augmented.h | 14 +++++++++++---
 lib/rbtree.c                     | 20 +++++++++++++++++---
 2 files changed, 28 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index 2ac60c9cf644..fea49b5da12a 100644
--- a/include/linux/rbtree_augmented.h
+++ b/include/linux/rbtree_augmented.h
@@ -123,9 +123,9 @@ __rb_change_child(struct rb_node *old, struct rb_node *new,
 extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
 
-static __always_inline void
-rb_erase_augmented(struct rb_node *node, struct rb_root *root,
-		   const struct rb_augment_callbacks *augment)
+static __always_inline struct rb_node *
+__rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		     const struct rb_augment_callbacks *augment)
 {
 	struct rb_node *child = node->rb_right, *tmp = node->rb_left;
 	struct rb_node *parent, *rebalance;
@@ -217,6 +217,14 @@ rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 	}
 
 	augment->propagate(tmp, NULL);
+	return rebalance;
+}
+
+static __always_inline void
+rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		   const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
 	if (rebalance)
 		__rb_erase_color(rebalance, root, augment->rotate);
 }
diff --git a/lib/rbtree.c b/lib/rbtree.c
index 4f56a11d67fa..c0e31fe2fabf 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -194,8 +194,12 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 	}
 }
 
-__always_inline void
-__rb_erase_color(struct rb_node *parent, struct rb_root *root,
+/*
+ * Inline version for rb_erase() use - we want to be able to inline
+ * and eliminate the dummy_rotate callback there
+ */
+static __always_inline void
+____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
 {
 	struct rb_node *node = NULL, *sibling, *tmp1, *tmp2;
@@ -355,6 +359,13 @@ __rb_erase_color(struct rb_node *parent, struct rb_root *root,
 		}
 	}
 }
+
+/* Non-inline version for rb_erase_augmented() use */
+void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	____rb_erase_color(parent, root, augment_rotate);
+}
 EXPORT_SYMBOL(__rb_erase_color);
 
 /*
@@ -380,7 +391,10 @@ EXPORT_SYMBOL(rb_insert_color);
 
 void rb_erase(struct rb_node *node, struct rb_root *root)
 {
-	rb_erase_augmented(node, root, &dummy_callbacks);
+	struct rb_node *rebalance;
+	rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+	if (rebalance)
+		____rb_erase_color(rebalance, root, dummy_rotate);
 }
 EXPORT_SYMBOL(rb_erase);
 
-- 
cgit v1.2.3-55-g7522


From d07d7507bfb4e23735c9b83e397c43e1e8a173e8 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka
Date: Thu, 10 Jan 2013 23:19:10 +0000
Subject: net, wireless: overwrite default_ethtool_ops

Since:

commit 2c60db037034d27f8c636403355d52872da92f81
Author: Eric Dumazet <edumazet@google.com>
Date:   Sun Sep 16 09:17:26 2012 +0000

    net: provide a default dev->ethtool_ops

wireless core does not correctly assign ethtool_ops.

After alloc_netdev*() call, some cfg80211 drivers provide they own
ethtool_ops, but some do not. For them, wireless core provide generic
cfg80211_ethtool_ops, which is assigned in NETDEV_REGISTER notify call:

        if (!dev->ethtool_ops)
                dev->ethtool_ops = &cfg80211_ethtool_ops;

But after Eric's commit, dev->ethtool_ops is no longer NULL (on cfg80211
drivers without custom ethtool_ops), but points to &default_ethtool_ops.

In order to fix the problem, provide function which will overwrite
default_ethtool_ops and use it by wireless core.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Acked-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 3 +++
 net/core/dev.c            | 8 ++++++++
 net/wireless/core.c       | 3 +--
 3 files changed, 12 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c599e4782d45..9ef07d0868b6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -60,6 +60,9 @@ struct wireless_dev;
 #define SET_ETHTOOL_OPS(netdev,ops) \
 	( (netdev)->ethtool_ops = (ops) )
 
+extern void netdev_set_default_ethtool_ops(struct net_device *dev,
+					   const struct ethtool_ops *ops);
+
 /* hardware address assignment types */
 #define NET_ADDR_PERM		0	/* address is permanent (default) */
 #define NET_ADDR_RANDOM		1	/* address is generated randomly */
diff --git a/net/core/dev.c b/net/core/dev.c
index 515473ee52cb..f64e439b4a00 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6121,6 +6121,14 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
 
 static const struct ethtool_ops default_ethtool_ops;
 
+void netdev_set_default_ethtool_ops(struct net_device *dev,
+				    const struct ethtool_ops *ops)
+{
+	if (dev->ethtool_ops == &default_ethtool_ops)
+		dev->ethtool_ops = ops;
+}
+EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops);
+
 /**
  *	alloc_netdev_mqs - allocate network device
  *	@sizeof_priv:	size of private data to allocate space for
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 14d990400354..b677eab55b68 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -866,8 +866,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		/* allow mac80211 to determine the timeout */
 		wdev->ps_timeout = -1;
 
-		if (!dev->ethtool_ops)
-			dev->ethtool_ops = &cfg80211_ethtool_ops;
+		netdev_set_default_ethtool_ops(dev, &cfg80211_ethtool_ops);
 
 		if ((wdev->iftype == NL80211_IFTYPE_STATION ||
 		     wdev->iftype == NL80211_IFTYPE_P2P_CLIENT ||
-- 
cgit v1.2.3-55-g7522


From 0d21b0e3477395e7ff2acc269f15df6e6a8d356d Mon Sep 17 00:00:00 2001
From: Rusty Russell
Date: Sat, 12 Jan 2013 11:38:44 +1030
Subject: module: add new state MODULE_STATE_UNFORMED.

You should never look at such a module, so it's excised from all paths
which traverse the modules list.

We add the state at the end, to avoid gratuitous ABI break (ksplice).

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/module.h      | 10 ++++----
 kernel/debug/kdb/kdb_main.c |  2 ++
 kernel/module.c             | 57 +++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 59 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index 7760c6d344a3..1375ee3f03aa 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -199,11 +199,11 @@ struct module_use {
 	struct module *source, *target;
 };
 
-enum module_state
-{
-	MODULE_STATE_LIVE,
-	MODULE_STATE_COMING,
-	MODULE_STATE_GOING,
+enum module_state {
+	MODULE_STATE_LIVE,	/* Normal state. */
+	MODULE_STATE_COMING,	/* Full formed, running module_init. */
+	MODULE_STATE_GOING,	/* Going away. */
+	MODULE_STATE_UNFORMED,	/* Still setting it up. */
 };
 
 /**
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 4d5f8d5612f3..8875254120b6 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1970,6 +1970,8 @@ static int kdb_lsmod(int argc, const char **argv)
 
 	kdb_printf("Module                  Size  modstruct     Used by\n");
 	list_for_each_entry(mod, kdb_modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 
 		kdb_printf("%-20s%8u  0x%p ", mod->name,
 			   mod->core_size, (void *)mod);
diff --git a/kernel/module.c b/kernel/module.c
index 41bc1189b061..c3a2ee8e3679 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -188,6 +188,7 @@ struct load_info {
    ongoing or failed initialization etc. */
 static inline int strong_try_module_get(struct module *mod)
 {
+	BUG_ON(mod && mod->state == MODULE_STATE_UNFORMED);
 	if (mod && mod->state == MODULE_STATE_COMING)
 		return -EBUSY;
 	if (try_module_get(mod))
@@ -343,6 +344,9 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
 #endif
 		};
 
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
+
 		if (each_symbol_in_section(arr, ARRAY_SIZE(arr), mod, fn, data))
 			return true;
 	}
@@ -450,16 +454,24 @@ const struct kernel_symbol *find_symbol(const char *name,
 EXPORT_SYMBOL_GPL(find_symbol);
 
 /* Search for module by name: must hold module_mutex. */
-struct module *find_module(const char *name)
+static struct module *find_module_all(const char *name,
+				      bool even_unformed)
 {
 	struct module *mod;
 
 	list_for_each_entry(mod, &modules, list) {
+		if (!even_unformed && mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		if (strcmp(mod->name, name) == 0)
 			return mod;
 	}
 	return NULL;
 }
+
+struct module *find_module(const char *name)
+{
+	return find_module_all(name, false);
+}
 EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
@@ -525,6 +537,8 @@ bool is_module_percpu_address(unsigned long addr)
 	preempt_disable();
 
 	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		if (!mod->percpu_size)
 			continue;
 		for_each_possible_cpu(cpu) {
@@ -1048,6 +1062,8 @@ static ssize_t show_initstate(struct module_attribute *mattr,
 	case MODULE_STATE_GOING:
 		state = "going";
 		break;
+	default:
+		BUG();
 	}
 	return sprintf(buffer, "%s\n", state);
 }
@@ -1786,6 +1802,8 @@ void set_all_modules_text_rw(void)
 
 	mutex_lock(&module_mutex);
 	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		if ((mod->module_core) && (mod->core_text_size)) {
 			set_page_attributes(mod->module_core,
 						mod->module_core + mod->core_text_size,
@@ -1807,6 +1825,8 @@ void set_all_modules_text_ro(void)
 
 	mutex_lock(&module_mutex);
 	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		if ((mod->module_core) && (mod->core_text_size)) {
 			set_page_attributes(mod->module_core,
 						mod->module_core + mod->core_text_size,
@@ -2998,7 +3018,8 @@ static bool finished_loading(const char *name)
 
 	mutex_lock(&module_mutex);
 	mod = find_module(name);
-	ret = !mod || mod->state != MODULE_STATE_COMING;
+	ret = !mod || mod->state == MODULE_STATE_LIVE
+		|| mod->state == MODULE_STATE_GOING;
 	mutex_unlock(&module_mutex);
 
 	return ret;
@@ -3361,6 +3382,8 @@ const char *module_address_lookup(unsigned long addr,
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		if (within_module_init(addr, mod) ||
 		    within_module_core(addr, mod)) {
 			if (modname)
@@ -3384,6 +3407,8 @@ int lookup_module_symbol_name(unsigned long addr, char *symname)
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		if (within_module_init(addr, mod) ||
 		    within_module_core(addr, mod)) {
 			const char *sym;
@@ -3408,6 +3433,8 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size,
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		if (within_module_init(addr, mod) ||
 		    within_module_core(addr, mod)) {
 			const char *sym;
@@ -3435,6 +3462,8 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		if (symnum < mod->num_symtab) {
 			*value = mod->symtab[symnum].st_value;
 			*type = mod->symtab[symnum].st_info;
@@ -3477,9 +3506,12 @@ unsigned long module_kallsyms_lookup_name(const char *name)
 			ret = mod_find_symname(mod, colon+1);
 		*colon = ':';
 	} else {
-		list_for_each_entry_rcu(mod, &modules, list)
+		list_for_each_entry_rcu(mod, &modules, list) {
+			if (mod->state == MODULE_STATE_UNFORMED)
+				continue;
 			if ((ret = mod_find_symname(mod, name)) != 0)
 				break;
+		}
 	}
 	preempt_enable();
 	return ret;
@@ -3494,6 +3526,8 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
 	int ret;
 
 	list_for_each_entry(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		for (i = 0; i < mod->num_symtab; i++) {
 			ret = fn(data, mod->strtab + mod->symtab[i].st_name,
 				 mod, mod->symtab[i].st_value);
@@ -3509,6 +3543,7 @@ static char *module_flags(struct module *mod, char *buf)
 {
 	int bx = 0;
 
+	BUG_ON(mod->state == MODULE_STATE_UNFORMED);
 	if (mod->taints ||
 	    mod->state == MODULE_STATE_GOING ||
 	    mod->state == MODULE_STATE_COMING) {
@@ -3550,6 +3585,10 @@ static int m_show(struct seq_file *m, void *p)
 	struct module *mod = list_entry(p, struct module, list);
 	char buf[8];
 
+	/* We always ignore unformed modules. */
+	if (mod->state == MODULE_STATE_UNFORMED)
+		return 0;
+
 	seq_printf(m, "%s %u",
 		   mod->name, mod->init_size + mod->core_size);
 	print_unload_info(m, mod);
@@ -3610,6 +3649,8 @@ const struct exception_table_entry *search_module_extables(unsigned long addr)
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		if (mod->num_exentries == 0)
 			continue;
 
@@ -3658,10 +3699,13 @@ struct module *__module_address(unsigned long addr)
 	if (addr < module_addr_min || addr > module_addr_max)
 		return NULL;
 
-	list_for_each_entry_rcu(mod, &modules, list)
+	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		if (within_module_core(addr, mod)
 		    || within_module_init(addr, mod))
 			return mod;
+	}
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(__module_address);
@@ -3714,8 +3758,11 @@ void print_modules(void)
 	printk(KERN_DEFAULT "Modules linked in:");
 	/* Most callers should already have preempt disabled, but make sure */
 	preempt_disable();
-	list_for_each_entry_rcu(mod, &modules, list)
+	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
 		printk(" %s%s", mod->name, module_flags(mod, buf));
+	}
 	preempt_enable();
 	if (last_unloaded_module[0])
 		printk(" [last unloaded: %s]", last_unloaded_module);
-- 
cgit v1.2.3-55-g7522


From 1e47ee8367babe6a5e8adf44a714c7086657b87e Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Thu, 10 Jan 2013 16:12:01 +0100
Subject: netfilter: nf_conntrack: fix BUG_ON while removing nf_conntrack with
 netns

canqun zhang reported that we're hitting BUG_ON in the
nf_conntrack_destroy path when calling kfree_skb while
rmmod'ing the nf_conntrack module.

Currently, the nf_ct_destroy hook is being set to NULL in the
destroy path of conntrack.init_net. However, this is a problem
since init_net may be destroyed before any other existing netns
(we cannot assume any specific ordering while releasing existing
netns according to what I read in recent emails).

Thanks to Gao feng for initial patch to address this issue.

Reported-by: canqun zhang <canqunzhang@gmail.com>
Acked-by: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_core.h | 2 ++
 net/netfilter/nf_conntrack_core.c         | 9 +++++----
 net/netfilter/nf_conntrack_standalone.c   | 1 +
 3 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index d8f5b9f52169..e98aeb3da033 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -31,6 +31,8 @@ extern void nf_conntrack_cleanup(struct net *net);
 extern int nf_conntrack_proto_init(struct net *net);
 extern void nf_conntrack_proto_fini(struct net *net);
 
+extern void nf_conntrack_cleanup_end(void);
+
 extern bool
 nf_ct_get_tuple(const struct sk_buff *skb,
 		unsigned int nhoff,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 016d95ead930..e4a0c4fb3a7c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1376,11 +1376,12 @@ void nf_conntrack_cleanup(struct net *net)
 	synchronize_net();
 	nf_conntrack_proto_fini(net);
 	nf_conntrack_cleanup_net(net);
+}
 
-	if (net_eq(net, &init_net)) {
-		RCU_INIT_POINTER(nf_ct_destroy, NULL);
-		nf_conntrack_cleanup_init_net();
-	}
+void nf_conntrack_cleanup_end(void)
+{
+	RCU_INIT_POINTER(nf_ct_destroy, NULL);
+	nf_conntrack_cleanup_init_net();
 }
 
 void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 363285d544a1..e7185c684816 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -575,6 +575,7 @@ static int __init nf_conntrack_standalone_init(void)
 static void __exit nf_conntrack_standalone_fini(void)
 {
 	unregister_pernet_subsys(&nf_conntrack_net_ops);
+	nf_conntrack_cleanup_end();
 }
 
 module_init(nf_conntrack_standalone_init);
-- 
cgit v1.2.3-55-g7522


From 803739d25c2343da6d2f95eebdcbc08bf67097d4 Mon Sep 17 00:00:00 2001
From: Shane Huang
Date: Mon, 17 Dec 2012 23:18:59 +0800
Subject: [libata] replace sata_settings with devslp_timing

NCQ capability was used to check availability of SATA Settings page
from Identify Device Data Log, which contains DevSlp timing variables.
It does not work on some HDDs and leads to error messages.

IDENTIFY word 78 bit 5(Hardware Feature Control) can't work either
because it is only the sufficient condition of Identify Device data
log, not the necessary condition.

This patch replaced ata_device->sata_settings with ->devslp_timing
to only save DevSlp timing variables(8 bytes), instead of the whole
SATA Settings page(512 bytes).

Addresses https://bugzilla.kernel.org/show_bug.cgi?id=51881

Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Shane Huang <shane.huang@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/libahci.c     |  6 +++---
 drivers/ata/libata-core.c | 22 +++++++++++++---------
 include/linux/ata.h       |  8 +++++---
 include/linux/libata.h    |  4 ++--
 4 files changed, 23 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 320712a7b9ea..6cd7805e47ca 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1951,13 +1951,13 @@ static void ahci_set_aggressive_devslp(struct ata_port *ap, bool sleep)
 	/* Use the nominal value 10 ms if the read MDAT is zero,
 	 * the nominal value of DETO is 20 ms.
 	 */
-	if (dev->sata_settings[ATA_LOG_DEVSLP_VALID] &
+	if (dev->devslp_timing[ATA_LOG_DEVSLP_VALID] &
 	    ATA_LOG_DEVSLP_VALID_MASK) {
-		mdat = dev->sata_settings[ATA_LOG_DEVSLP_MDAT] &
+		mdat = dev->devslp_timing[ATA_LOG_DEVSLP_MDAT] &
 		       ATA_LOG_DEVSLP_MDAT_MASK;
 		if (!mdat)
 			mdat = 10;
-		deto = dev->sata_settings[ATA_LOG_DEVSLP_DETO];
+		deto = dev->devslp_timing[ATA_LOG_DEVSLP_DETO];
 		if (!deto)
 			deto = 20;
 	} else {
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 9e8b99af400d..46cd3f4c6aaa 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2325,24 +2325,28 @@ int ata_dev_configure(struct ata_device *dev)
 			}
 		}
 
-		/* check and mark DevSlp capability */
-		if (ata_id_has_devslp(dev->id))
-			dev->flags |= ATA_DFLAG_DEVSLP;
-
-		/* Obtain SATA Settings page from Identify Device Data Log,
-		 * which contains DevSlp timing variables etc.
-		 * Exclude old devices with ata_id_has_ncq()
+		/* Check and mark DevSlp capability. Get DevSlp timing variables
+		 * from SATA Settings page of Identify Device Data Log.
 		 */
-		if (ata_id_has_ncq(dev->id)) {
+		if (ata_id_has_devslp(dev->id)) {
+			u8 sata_setting[ATA_SECT_SIZE];
+			int i, j;
+
+			dev->flags |= ATA_DFLAG_DEVSLP;
 			err_mask = ata_read_log_page(dev,
 						     ATA_LOG_SATA_ID_DEV_DATA,
 						     ATA_LOG_SATA_SETTINGS,
-						     dev->sata_settings,
+						     sata_setting,
 						     1);
 			if (err_mask)
 				ata_dev_dbg(dev,
 					    "failed to get Identify Device Data, Emask 0x%x\n",
 					    err_mask);
+			else
+				for (i = 0; i < ATA_LOG_DEVSLP_SIZE; i++) {
+					j = ATA_LOG_DEVSLP_OFFSET + i;
+					dev->devslp_timing[i] = sata_setting[j];
+				}
 		}
 
 		dev->cdb_len = 16;
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 408da9502177..8f7a3d68371a 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -297,10 +297,12 @@ enum {
 	ATA_LOG_SATA_NCQ	= 0x10,
 	ATA_LOG_SATA_ID_DEV_DATA  = 0x30,
 	ATA_LOG_SATA_SETTINGS	  = 0x08,
-	ATA_LOG_DEVSLP_MDAT	  = 0x30,
+	ATA_LOG_DEVSLP_OFFSET	  = 0x30,
+	ATA_LOG_DEVSLP_SIZE	  = 0x08,
+	ATA_LOG_DEVSLP_MDAT	  = 0x00,
 	ATA_LOG_DEVSLP_MDAT_MASK  = 0x1F,
-	ATA_LOG_DEVSLP_DETO	  = 0x31,
-	ATA_LOG_DEVSLP_VALID	  = 0x37,
+	ATA_LOG_DEVSLP_DETO	  = 0x01,
+	ATA_LOG_DEVSLP_VALID	  = 0x07,
 	ATA_LOG_DEVSLP_VALID_MASK = 0x80,
 
 	/* READ/WRITE LONG (obsolete) */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 83ba0ab2c915..649e5f86b5f0 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -652,8 +652,8 @@ struct ata_device {
 		u32		gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */
 	};
 
-	/* Identify Device Data Log (30h), SATA Settings (page 08h) */
-	u8			sata_settings[ATA_SECT_SIZE];
+	/* DEVSLP Timing Variables from Identify Device Data Log */
+	u8			devslp_timing[ATA_LOG_DEVSLP_SIZE];
 
 	/* error history */
 	int			spdn_cnt;
-- 
cgit v1.2.3-55-g7522


From 5dbbaf2de89613d19a9286d4db0a535ca2735d26 Mon Sep 17 00:00:00 2001
From: Paul Moore
Date: Mon, 14 Jan 2013 07:12:19 +0000
Subject: tun: fix LSM/SELinux labeling of tun/tap devices

This patch corrects some problems with LSM/SELinux that were introduced
with the multiqueue patchset.  The problem stems from the fact that the
multiqueue work changed the relationship between the tun device and its
associated socket; before the socket persisted for the life of the
device, however after the multiqueue changes the socket only persisted
for the life of the userspace connection (fd open).  For non-persistent
devices this is not an issue, but for persistent devices this can cause
the tun device to lose its SELinux label.

We correct this problem by adding an opaque LSM security blob to the
tun device struct which allows us to have the LSM security state, e.g.
SELinux labeling information, persist for the lifetime of the tun
device.  In the process we tweak the LSM hooks to work with this new
approach to TUN device/socket labeling and introduce a new LSM hook,
security_tun_dev_attach_queue(), to approve requests to attach to a
TUN queue via TUNSETQUEUE.

The SELinux code has been adjusted to match the new LSM hooks, the
other LSMs do not make use of the LSM TUN controls.  This patch makes
use of the recently added "tun_socket:attach_queue" permission to
restrict access to the TUNSETQUEUE operation.  On older SELinux
policies which do not define the "tun_socket:attach_queue" permission
the access control decision for TUNSETQUEUE will be handled according
to the SELinux policy's unknown permission setting.

Signed-off-by: Paul Moore <pmoore@redhat.com>
Acked-by: Eric Paris <eparis@parisplace.org>
Tested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c                 | 23 +++++++++++----
 include/linux/security.h          | 59 ++++++++++++++++++++++++++++++---------
 security/capability.c             | 24 ++++++++++++++--
 security/security.c               | 28 +++++++++++++++----
 security/selinux/hooks.c          | 50 +++++++++++++++++++++++++--------
 security/selinux/include/objsec.h |  4 +++
 6 files changed, 151 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index af372d0957fe..c81680dc10eb 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -185,6 +185,7 @@ struct tun_struct {
 	unsigned long ageing_time;
 	unsigned int numdisabled;
 	struct list_head disabled;
+	void *security;
 };
 
 static inline u32 tun_hashfn(u32 rxhash)
@@ -490,6 +491,10 @@ static int tun_attach(struct tun_struct *tun, struct file *file)
 	struct tun_file *tfile = file->private_data;
 	int err;
 
+	err = security_tun_dev_attach(tfile->socket.sk, tun->security);
+	if (err < 0)
+		goto out;
+
 	err = -EINVAL;
 	if (rtnl_dereference(tfile->tun))
 		goto out;
@@ -1373,6 +1378,7 @@ static void tun_free_netdev(struct net_device *dev)
 
 	BUG_ON(!(list_empty(&tun->disabled)));
 	tun_flow_uninit(tun);
+	security_tun_dev_free_security(tun->security);
 	free_netdev(dev);
 }
 
@@ -1562,7 +1568,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		if (tun_not_capable(tun))
 			return -EPERM;
-		err = security_tun_dev_attach(tfile->socket.sk);
+		err = security_tun_dev_open(tun->security);
 		if (err < 0)
 			return err;
 
@@ -1619,7 +1625,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		spin_lock_init(&tun->lock);
 
-		security_tun_dev_post_create(&tfile->sk);
+		err = security_tun_dev_alloc_security(&tun->security);
+		if (err < 0)
+			goto err_free_dev;
 
 		tun_net_init(dev);
 
@@ -1789,10 +1797,14 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
 
 	if (ifr->ifr_flags & IFF_ATTACH_QUEUE) {
 		tun = tfile->detached;
-		if (!tun)
+		if (!tun) {
 			ret = -EINVAL;
-		else
-			ret = tun_attach(tun, file);
+			goto unlock;
+		}
+		ret = security_tun_dev_attach_queue(tun->security);
+		if (ret < 0)
+			goto unlock;
+		ret = tun_attach(tun, file);
 	} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
 		tun = rtnl_dereference(tfile->tun);
 		if (!tun || !(tun->flags & TUN_TAP_MQ))
@@ -1802,6 +1814,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
 	} else
 		ret = -EINVAL;
 
+unlock:
 	rtnl_unlock();
 	return ret;
 }
diff --git a/include/linux/security.h b/include/linux/security.h
index 0f6afc657f77..eee7478cda70 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -989,17 +989,29 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	tells the LSM to decrement the number of secmark labeling rules loaded
  * @req_classify_flow:
  *	Sets the flow's sid to the openreq sid.
+ * @tun_dev_alloc_security:
+ *	This hook allows a module to allocate a security structure for a TUN
+ *	device.
+ *	@security pointer to a security structure pointer.
+ *	Returns a zero on success, negative values on failure.
+ * @tun_dev_free_security:
+ *	This hook allows a module to free the security structure for a TUN
+ *	device.
+ *	@security pointer to the TUN device's security structure
  * @tun_dev_create:
  *	Check permissions prior to creating a new TUN device.
- * @tun_dev_post_create:
- *	This hook allows a module to update or allocate a per-socket security
- *	structure.
- *	@sk contains the newly created sock structure.
+ * @tun_dev_attach_queue:
+ *	Check permissions prior to attaching to a TUN device queue.
+ *	@security pointer to the TUN device's security structure.
  * @tun_dev_attach:
- *	Check permissions prior to attaching to a persistent TUN device.  This
- *	hook can also be used by the module to update any security state
+ *	This hook can be used by the module to update any security state
  *	associated with the TUN device's sock structure.
  *	@sk contains the existing sock structure.
+ *	@security pointer to the TUN device's security structure.
+ * @tun_dev_open:
+ *	This hook can be used by the module to update any security state
+ *	associated with the TUN device's security structure.
+ *	@security pointer to the TUN devices's security structure.
  *
  * Security hooks for XFRM operations.
  *
@@ -1620,9 +1632,12 @@ struct security_operations {
 	void (*secmark_refcount_inc) (void);
 	void (*secmark_refcount_dec) (void);
 	void (*req_classify_flow) (const struct request_sock *req, struct flowi *fl);
-	int (*tun_dev_create)(void);
-	void (*tun_dev_post_create)(struct sock *sk);
-	int (*tun_dev_attach)(struct sock *sk);
+	int (*tun_dev_alloc_security) (void **security);
+	void (*tun_dev_free_security) (void *security);
+	int (*tun_dev_create) (void);
+	int (*tun_dev_attach_queue) (void *security);
+	int (*tun_dev_attach) (struct sock *sk, void *security);
+	int (*tun_dev_open) (void *security);
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
@@ -2566,9 +2581,12 @@ void security_inet_conn_established(struct sock *sk,
 int security_secmark_relabel_packet(u32 secid);
 void security_secmark_refcount_inc(void);
 void security_secmark_refcount_dec(void);
+int security_tun_dev_alloc_security(void **security);
+void security_tun_dev_free_security(void *security);
 int security_tun_dev_create(void);
-void security_tun_dev_post_create(struct sock *sk);
-int security_tun_dev_attach(struct sock *sk);
+int security_tun_dev_attach_queue(void *security);
+int security_tun_dev_attach(struct sock *sk, void *security);
+int security_tun_dev_open(void *security);
 
 #else	/* CONFIG_SECURITY_NETWORK */
 static inline int security_unix_stream_connect(struct sock *sock,
@@ -2733,16 +2751,31 @@ static inline void security_secmark_refcount_dec(void)
 {
 }
 
+static inline int security_tun_dev_alloc_security(void **security)
+{
+	return 0;
+}
+
+static inline void security_tun_dev_free_security(void *security)
+{
+}
+
 static inline int security_tun_dev_create(void)
 {
 	return 0;
 }
 
-static inline void security_tun_dev_post_create(struct sock *sk)
+static inline int security_tun_dev_attach_queue(void *security)
+{
+	return 0;
+}
+
+static inline int security_tun_dev_attach(struct sock *sk, void *security)
 {
+	return 0;
 }
 
-static inline int security_tun_dev_attach(struct sock *sk)
+static inline int security_tun_dev_open(void *security)
 {
 	return 0;
 }
diff --git a/security/capability.c b/security/capability.c
index 0fe5a026aef8..579775088967 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -709,16 +709,31 @@ static void cap_req_classify_flow(const struct request_sock *req,
 {
 }
 
+static int cap_tun_dev_alloc_security(void **security)
+{
+	return 0;
+}
+
+static void cap_tun_dev_free_security(void *security)
+{
+}
+
 static int cap_tun_dev_create(void)
 {
 	return 0;
 }
 
-static void cap_tun_dev_post_create(struct sock *sk)
+static int cap_tun_dev_attach_queue(void *security)
+{
+	return 0;
+}
+
+static int cap_tun_dev_attach(struct sock *sk, void *security)
 {
+	return 0;
 }
 
-static int cap_tun_dev_attach(struct sock *sk)
+static int cap_tun_dev_open(void *security)
 {
 	return 0;
 }
@@ -1050,8 +1065,11 @@ void __init security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, secmark_refcount_inc);
 	set_to_cap_if_null(ops, secmark_refcount_dec);
 	set_to_cap_if_null(ops, req_classify_flow);
+	set_to_cap_if_null(ops, tun_dev_alloc_security);
+	set_to_cap_if_null(ops, tun_dev_free_security);
 	set_to_cap_if_null(ops, tun_dev_create);
-	set_to_cap_if_null(ops, tun_dev_post_create);
+	set_to_cap_if_null(ops, tun_dev_open);
+	set_to_cap_if_null(ops, tun_dev_attach_queue);
 	set_to_cap_if_null(ops, tun_dev_attach);
 #endif	/* CONFIG_SECURITY_NETWORK */
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
diff --git a/security/security.c b/security/security.c
index daa97f4ac9d1..7b88c6aeaed4 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1254,24 +1254,42 @@ void security_secmark_refcount_dec(void)
 }
 EXPORT_SYMBOL(security_secmark_refcount_dec);
 
+int security_tun_dev_alloc_security(void **security)
+{
+	return security_ops->tun_dev_alloc_security(security);
+}
+EXPORT_SYMBOL(security_tun_dev_alloc_security);
+
+void security_tun_dev_free_security(void *security)
+{
+	security_ops->tun_dev_free_security(security);
+}
+EXPORT_SYMBOL(security_tun_dev_free_security);
+
 int security_tun_dev_create(void)
 {
 	return security_ops->tun_dev_create();
 }
 EXPORT_SYMBOL(security_tun_dev_create);
 
-void security_tun_dev_post_create(struct sock *sk)
+int security_tun_dev_attach_queue(void *security)
 {
-	return security_ops->tun_dev_post_create(sk);
+	return security_ops->tun_dev_attach_queue(security);
 }
-EXPORT_SYMBOL(security_tun_dev_post_create);
+EXPORT_SYMBOL(security_tun_dev_attach_queue);
 
-int security_tun_dev_attach(struct sock *sk)
+int security_tun_dev_attach(struct sock *sk, void *security)
 {
-	return security_ops->tun_dev_attach(sk);
+	return security_ops->tun_dev_attach(sk, security);
 }
 EXPORT_SYMBOL(security_tun_dev_attach);
 
+int security_tun_dev_open(void *security)
+{
+	return security_ops->tun_dev_open(security);
+}
+EXPORT_SYMBOL(security_tun_dev_open);
+
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 61a53367d029..ef26e9611ffb 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4399,6 +4399,24 @@ static void selinux_req_classify_flow(const struct request_sock *req,
 	fl->flowi_secid = req->secid;
 }
 
+static int selinux_tun_dev_alloc_security(void **security)
+{
+	struct tun_security_struct *tunsec;
+
+	tunsec = kzalloc(sizeof(*tunsec), GFP_KERNEL);
+	if (!tunsec)
+		return -ENOMEM;
+	tunsec->sid = current_sid();
+
+	*security = tunsec;
+	return 0;
+}
+
+static void selinux_tun_dev_free_security(void *security)
+{
+	kfree(security);
+}
+
 static int selinux_tun_dev_create(void)
 {
 	u32 sid = current_sid();
@@ -4414,8 +4432,17 @@ static int selinux_tun_dev_create(void)
 			    NULL);
 }
 
-static void selinux_tun_dev_post_create(struct sock *sk)
+static int selinux_tun_dev_attach_queue(void *security)
 {
+	struct tun_security_struct *tunsec = security;
+
+	return avc_has_perm(current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET,
+			    TUN_SOCKET__ATTACH_QUEUE, NULL);
+}
+
+static int selinux_tun_dev_attach(struct sock *sk, void *security)
+{
+	struct tun_security_struct *tunsec = security;
 	struct sk_security_struct *sksec = sk->sk_security;
 
 	/* we don't currently perform any NetLabel based labeling here and it
@@ -4425,20 +4452,19 @@ static void selinux_tun_dev_post_create(struct sock *sk)
 	 * cause confusion to the TUN user that had no idea network labeling
 	 * protocols were being used */
 
-	/* see the comments in selinux_tun_dev_create() about why we don't use
-	 * the sockcreate SID here */
-
-	sksec->sid = current_sid();
+	sksec->sid = tunsec->sid;
 	sksec->sclass = SECCLASS_TUN_SOCKET;
+
+	return 0;
 }
 
-static int selinux_tun_dev_attach(struct sock *sk)
+static int selinux_tun_dev_open(void *security)
 {
-	struct sk_security_struct *sksec = sk->sk_security;
+	struct tun_security_struct *tunsec = security;
 	u32 sid = current_sid();
 	int err;
 
-	err = avc_has_perm(sid, sksec->sid, SECCLASS_TUN_SOCKET,
+	err = avc_has_perm(sid, tunsec->sid, SECCLASS_TUN_SOCKET,
 			   TUN_SOCKET__RELABELFROM, NULL);
 	if (err)
 		return err;
@@ -4446,8 +4472,7 @@ static int selinux_tun_dev_attach(struct sock *sk)
 			   TUN_SOCKET__RELABELTO, NULL);
 	if (err)
 		return err;
-
-	sksec->sid = sid;
+	tunsec->sid = sid;
 
 	return 0;
 }
@@ -5642,9 +5667,12 @@ static struct security_operations selinux_ops = {
 	.secmark_refcount_inc =		selinux_secmark_refcount_inc,
 	.secmark_refcount_dec =		selinux_secmark_refcount_dec,
 	.req_classify_flow =		selinux_req_classify_flow,
+	.tun_dev_alloc_security =	selinux_tun_dev_alloc_security,
+	.tun_dev_free_security =	selinux_tun_dev_free_security,
 	.tun_dev_create =		selinux_tun_dev_create,
-	.tun_dev_post_create = 		selinux_tun_dev_post_create,
+	.tun_dev_attach_queue =		selinux_tun_dev_attach_queue,
 	.tun_dev_attach =		selinux_tun_dev_attach,
+	.tun_dev_open =			selinux_tun_dev_open,
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 	.xfrm_policy_alloc_security =	selinux_xfrm_policy_alloc,
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index 26c7eee1c309..aa47bcabb5f6 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -110,6 +110,10 @@ struct sk_security_struct {
 	u16 sclass;			/* sock security class */
 };
 
+struct tun_security_struct {
+	u32 sid;			/* SID for the tun device sockets */
+};
+
 struct key_security_struct {
 	u32 sid;	/* SID of key */
 };
-- 
cgit v1.2.3-55-g7522


From 8aef33a7cf40ca9da188e8578b2abe7267a38c52 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano
Date: Tue, 15 Jan 2013 14:18:04 +0100
Subject: cpuidle: remove the power_specified field in the driver

We realized that the power usage field is never filled and when it
is filled for tegra, the power_specified flag is not set causing all
of these values to be reset when the driver is initialized with
set_power_state().

However, the power_specified flag can be simply removed under the
assumption that the states are always backward sorted, which is the
case with the current code.

This change allows the menu governor select function and the
cpuidle_play_dead() to be simplified.  Moreover, the
set_power_states() function can removed as it does not make sense
any more.

Drop the power_specified flag from struct cpuidle_driver and make
the related changes as described above.

As a consequence, this also fixes the bug where on the dynamic
C-states system, the power fields are not initialized.

[rjw: Changelog]
References: https://bugzilla.kernel.org/show_bug.cgi?id=42870
References: https://bugzilla.kernel.org/show_bug.cgi?id=43349
References: https://lkml.org/lkml/2012/10/16/518
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpuidle/cpuidle.c        | 17 ++++-------------
 drivers/cpuidle/driver.c         | 25 -------------------------
 drivers/cpuidle/governors/menu.c |  8 ++------
 include/linux/cpuidle.h          |  2 +-
 4 files changed, 7 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index fb4a7dd57f94..e1f6860e069c 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -69,24 +69,15 @@ int cpuidle_play_dead(void)
 {
 	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
-	int i, dead_state = -1;
-	int power_usage = INT_MAX;
+	int i;
 
 	if (!drv)
 		return -ENODEV;
 
 	/* Find lowest-power state that supports long-term idle */
-	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
-		struct cpuidle_state *s = &drv->states[i];
-
-		if (s->power_usage < power_usage && s->enter_dead) {
-			power_usage = s->power_usage;
-			dead_state = i;
-		}
-	}
-
-	if (dead_state != -1)
-		return drv->states[dead_state].enter_dead(dev, dead_state);
+	for (i = drv->state_count - 1; i >= CPUIDLE_DRIVER_STATE_START; i--)
+		if (drv->states[i].enter_dead)
+			return drv->states[i].enter_dead(dev, i);
 
 	return -ENODEV;
 }
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index c2b281afe0ed..422c7b69ba7c 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -19,34 +19,9 @@ DEFINE_SPINLOCK(cpuidle_driver_lock);
 static void __cpuidle_set_cpu_driver(struct cpuidle_driver *drv, int cpu);
 static struct cpuidle_driver * __cpuidle_get_cpu_driver(int cpu);
 
-static void set_power_states(struct cpuidle_driver *drv)
-{
-	int i;
-
-	/*
-	 * cpuidle driver should set the drv->power_specified bit
-	 * before registering if the driver provides
-	 * power_usage numbers.
-	 *
-	 * If power_specified is not set,
-	 * we fill in power_usage with decreasing values as the
-	 * cpuidle code has an implicit assumption that state Cn
-	 * uses less power than C(n-1).
-	 *
-	 * With CONFIG_ARCH_HAS_CPU_RELAX, C0 is already assigned
-	 * an power value of -1.  So we use -2, -3, etc, for other
-	 * c-states.
-	 */
-	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++)
-		drv->states[i].power_usage = -1 - i;
-}
-
 static void __cpuidle_driver_init(struct cpuidle_driver *drv)
 {
 	drv->refcnt = 0;
-
-	if (!drv->power_specified)
-		set_power_states(drv);
 }
 
 static int __cpuidle_register_driver(struct cpuidle_driver *drv, int cpu)
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 20ea33afdda1..fe343a06b7da 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -312,7 +312,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct menu_device *data = &__get_cpu_var(menu_devices);
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
-	int power_usage = INT_MAX;
 	int i;
 	int multiplier;
 	struct timespec t;
@@ -383,11 +382,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		if (s->exit_latency * multiplier > data->predicted_us)
 			continue;
 
-		if (s->power_usage < power_usage) {
-			power_usage = s->power_usage;
-			data->last_state_idx = i;
-			data->exit_us = s->exit_latency;
-		}
+		data->last_state_idx = i;
+		data->exit_us = s->exit_latency;
 	}
 
 	/* not deepest C-state chosen for low predicted residency */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 3711b34dc4f9..24cd1037b6d6 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -126,9 +126,9 @@ struct cpuidle_driver {
 	struct module 		*owner;
 	int                     refcnt;
 
-	unsigned int		power_specified:1;
 	/* set to 1 to use the core cpuidle time keeping (for all states). */
 	unsigned int		en_core_tk_irqen:1;
+	/* states array must be ordered in decreasing power consumption */
 	struct cpuidle_state	states[CPUIDLE_STATE_MAX];
 	int			state_count;
 	int			safe_state_index;
-- 
cgit v1.2.3-55-g7522


From 774a1221e862b343388347bac9b318767336b20b Mon Sep 17 00:00:00 2001
From: Tejun Heo
Date: Tue, 15 Jan 2013 18:52:51 -0800
Subject: module, async: async_synchronize_full() on module init iff async is
 used

If the default iosched is built as module, the kernel may deadlock
while trying to load the iosched module on device probe if the probing
was running off async.  This is because async_synchronize_full() at
the end of module init ends up waiting for the async job which
initiated the module loading.

 async A				modprobe

 1. finds a device
 2. registers the block device
 3. request_module(default iosched)
					4. modprobe in userland
					5. load and init module
					6. async_synchronize_full()

Async A waits for modprobe to finish in request_module() and modprobe
waits for async A to finish in async_synchronize_full().

Because there's no easy to track dependency once control goes out to
userland, implementing properly nested flushing is difficult.  For
now, make module init perform async_synchronize_full() iff module init
has queued async jobs as suggested by Linus.

This avoids the described deadlock because iosched module doesn't use
async and thus wouldn't invoke async_synchronize_full().  This is
hacky and incomplete.  It will deadlock if async module loading nests;
however, this works around the known problem case and seems to be the
best of bad options.

For more details, please refer to the following thread.

  http://thread.gmane.org/gmane.linux.kernel/1420814

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Alex Riesen <raa.lkml@gmail.com>
Tested-by: Ming Lei <ming.lei@canonical.com>
Tested-by: Alex Riesen <raa.lkml@gmail.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h |  1 +
 kernel/async.c        |  3 +++
 kernel/module.c       | 27 +++++++++++++++++++++++++--
 3 files changed, 29 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 206bb089c06b..6fc8f45de4e9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1810,6 +1810,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_MEMALLOC	0x00000800	/* Allocating memory */
 #define PF_NPROC_EXCEEDED 0x00001000	/* set_user noticed that RLIMIT_NPROC was exceeded */
 #define PF_USED_MATH	0x00002000	/* if unset the fpu must be initialized before use */
+#define PF_USED_ASYNC	0x00004000	/* used async_schedule*(), used by module init */
 #define PF_NOFREEZE	0x00008000	/* this thread should not be frozen */
 #define PF_FROZEN	0x00010000	/* frozen for system suspend */
 #define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
diff --git a/kernel/async.c b/kernel/async.c
index 9d3118384858..a1d585c351d6 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -196,6 +196,9 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct a
 	atomic_inc(&entry_count);
 	spin_unlock_irqrestore(&async_lock, flags);
 
+	/* mark that this task has queued an async job, used by module init */
+	current->flags |= PF_USED_ASYNC;
+
 	/* schedule for execution */
 	queue_work(system_unbound_wq, &entry->work);
 
diff --git a/kernel/module.c b/kernel/module.c
index 250092c1d57d..b10b048367e1 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3013,6 +3013,12 @@ static int do_init_module(struct module *mod)
 {
 	int ret = 0;
 
+	/*
+	 * We want to find out whether @mod uses async during init.  Clear
+	 * PF_USED_ASYNC.  async_schedule*() will set it.
+	 */
+	current->flags &= ~PF_USED_ASYNC;
+
 	blocking_notifier_call_chain(&module_notify_list,
 			MODULE_STATE_COMING, mod);
 
@@ -3058,8 +3064,25 @@ static int do_init_module(struct module *mod)
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_LIVE, mod);
 
-	/* We need to finish all async code before the module init sequence is done */
-	async_synchronize_full();
+	/*
+	 * We need to finish all async code before the module init sequence
+	 * is done.  This has potential to deadlock.  For example, a newly
+	 * detected block device can trigger request_module() of the
+	 * default iosched from async probing task.  Once userland helper
+	 * reaches here, async_synchronize_full() will wait on the async
+	 * task waiting on request_module() and deadlock.
+	 *
+	 * This deadlock is avoided by perfomring async_synchronize_full()
+	 * iff module init queued any async jobs.  This isn't a full
+	 * solution as it will deadlock the same if module loading from
+	 * async jobs nests more than once; however, due to the various
+	 * constraints, this hack seems to be the best option for now.
+	 * Please refer to the following thread for details.
+	 *
+	 * http://thread.gmane.org/gmane.linux.kernel/1420814
+	 */
+	if (current->flags & PF_USED_ASYNC)
+		async_synchronize_full();
 
 	mutex_lock(&module_mutex);
 	/* Drop initial reference. */
-- 
cgit v1.2.3-55-g7522


From e65b9ad222c280c031bc8d3642cc38dd3026fe06 Mon Sep 17 00:00:00 2001
From: Jiri Kosina
Date: Tue, 15 Jan 2013 20:12:37 +0100
Subject: lockdep, rwsem: fix down_write_nest_lock() if
 !CONFIG_DEBUG_LOCK_ALLOC

Commit 1b963c81b145 ("lockdep, rwsem: provide down_write_nest_lock()")
contains a bug in a codepath when CONFIG_DEBUG_LOCK_ALLOC is disabled,
which causes down_read() to be called instead of down_write() by mistake
on such configurations.  Fix that.

Reported-and-tested-by: Andrew Clayton <andrew@digital-domain.net>
Reported-and-tested-by: Zlatko Calusic <zlatko.calusic@iskon.hr>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/rwsem.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 413cc11e414a..8da67d625e13 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -135,7 +135,7 @@ do {								\
 
 #else
 # define down_read_nested(sem, subclass)		down_read(sem)
-# define down_write_nest_lock(sem, nest_lock)	down_read(sem)
+# define down_write_nest_lock(sem, nest_lock)	down_write(sem)
 # define down_write_nested(sem, subclass)	down_write(sem)
 #endif
 
-- 
cgit v1.2.3-55-g7522


From ebebd49a8eab5e9aa1b1f8f1614ccc3c2120f886 Mon Sep 17 00:00:00 2001
From: Stephen Hurd
Date: Thu, 17 Jan 2013 14:14:53 -0800
Subject: 8250/16?50: Add support for Broadcom TruManage redirected serial port

Add support for the UART device present in Broadcom TruManage capable
NetXtreme chips (ie: 5761m 5762, and 5725).

This implementation has a hidden transmit FIFO, so running in single-byte
interrupt mode results in too many interrupts.  The UART_CAP_HFIFO
capability was added to track this.  It continues to reload the THR as long
as the THRE and TSRE bits are set in the LSR up to a specified limit (1024
is used here).

Signed-off-by: Stephen Hurd <shurd@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250.c     | 11 +++++++++++
 drivers/tty/serial/8250/8250.h     |  1 +
 drivers/tty/serial/8250/8250_pci.c | 38 ++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/serial_core.h   |  3 ++-
 4 files changed, 52 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250.c b/drivers/tty/serial/8250/8250.c
index d085e3a8ec06..f9320437a649 100644
--- a/drivers/tty/serial/8250/8250.c
+++ b/drivers/tty/serial/8250/8250.c
@@ -300,6 +300,12 @@ static const struct serial8250_config uart_config[] = {
 				  UART_FCR_R_TRIG_00 | UART_FCR_T_TRIG_00,
 		.flags		= UART_CAP_FIFO,
 	},
+	[PORT_BRCM_TRUMANAGE] = {
+		.name		= "TruManage",
+		.fifo_size	= 1,
+		.tx_loadsz	= 1024,
+		.flags		= UART_CAP_HFIFO,
+	},
 	[PORT_8250_CIR] = {
 		.name		= "CIR port"
 	}
@@ -1490,6 +1496,11 @@ void serial8250_tx_chars(struct uart_8250_port *up)
 		port->icount.tx++;
 		if (uart_circ_empty(xmit))
 			break;
+		if (up->capabilities & UART_CAP_HFIFO) {
+			if ((serial_port_in(port, UART_LSR) & BOTH_EMPTY) !=
+			    BOTH_EMPTY)
+				break;
+		}
 	} while (--count > 0);
 
 	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h
index 3b4ea84898c2..12caa1292b75 100644
--- a/drivers/tty/serial/8250/8250.h
+++ b/drivers/tty/serial/8250/8250.h
@@ -40,6 +40,7 @@ struct serial8250_config {
 #define UART_CAP_AFE	(1 << 11)	/* MCR-based hw flow control */
 #define UART_CAP_UUE	(1 << 12)	/* UART needs IER bit 6 set (Xscale) */
 #define UART_CAP_RTOIE	(1 << 13)	/* UART needs IER bit 4 set (Xscale, Tegra) */
+#define UART_CAP_HFIFO	(1 << 14)	/* UART has a "hidden" FIFO */
 
 #define UART_BUG_QUOT	(1 << 0)	/* UART has buggy quot LSB */
 #define UART_BUG_TXEN	(1 << 1)	/* UART has buggy TX IIR status */
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 8a2c3d934187..a27a98e1b066 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1085,6 +1085,18 @@ pci_omegapci_setup(struct serial_private *priv,
 	return setup_port(priv, port, 2, idx * 8, 0);
 }
 
+static int
+pci_brcm_trumanage_setup(struct serial_private *priv,
+			 const struct pciserial_board *board,
+			 struct uart_8250_port *port, int idx)
+{
+	int ret = pci_default_setup(priv, board, port, idx);
+
+	port->port.type = PORT_BRCM_TRUMANAGE;
+	port->port.flags = (port->port.flags | UPF_FIXED_PORT | UPF_FIXED_TYPE);
+	return ret;
+}
+
 static int skip_tx_en_setup(struct serial_private *priv,
 			const struct pciserial_board *board,
 			struct uart_8250_port *port, int idx)
@@ -1304,6 +1316,7 @@ pci_wch_ch353_setup(struct serial_private *priv,
 #define PCI_DEVICE_ID_COMMTECH_4224PCIE	0x0020
 #define PCI_DEVICE_ID_COMMTECH_4228PCIE	0x0021
 #define PCI_DEVICE_ID_COMMTECH_4222PCIE	0x0022
+#define PCI_DEVICE_ID_BROADCOM_TRUMANAGE 0x160a
 
 
 /* Unknown vendors/cards - this should not be in linux/pci_ids.h */
@@ -1953,6 +1966,17 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = {
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_xr17v35x_setup,
 	},
+	/*
+	 * Broadcom TruManage (NetXtreme)
+	 */
+	{
+		.vendor		= PCI_VENDOR_ID_BROADCOM,
+		.device		= PCI_DEVICE_ID_BROADCOM_TRUMANAGE,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_brcm_trumanage_setup,
+	},
+
 	/*
 	 * Default "match everything" terminator entry
 	 */
@@ -2148,6 +2172,7 @@ enum pci_board_num_t {
 	pbn_ce4100_1_115200,
 	pbn_omegapci,
 	pbn_NETMOS9900_2s_115200,
+	pbn_brcm_trumanage,
 };
 
 /*
@@ -2892,6 +2917,12 @@ static struct pciserial_board pci_boards[] = {
 		.num_ports	= 2,
 		.base_baud	= 115200,
 	},
+	[pbn_brcm_trumanage] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 1,
+		.reg_shift	= 2,
+		.base_baud	= 115200,
+	},
 };
 
 static const struct pci_device_id blacklist[] = {
@@ -4470,6 +4501,13 @@ static struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 		pbn_omegapci },
 
+	/*
+	 * Broadcom TruManage
+	 */
+	{	PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_BROADCOM_TRUMANAGE,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_brcm_trumanage },
+
 	/*
 	 * AgeStar as-prs2-009
 	 */
diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h
index 78f99d97475b..2c6c85f18ea0 100644
--- a/include/uapi/linux/serial_core.h
+++ b/include/uapi/linux/serial_core.h
@@ -50,7 +50,8 @@
 #define PORT_LPC3220	22	/* NXP LPC32xx SoC "Standard" UART */
 #define PORT_8250_CIR	23	/* CIR infrared port, has its own driver */
 #define PORT_XR17V35X	24	/* Exar XR17V35x UARTs */
-#define PORT_MAX_8250	24	/* max port ID */
+#define PORT_BRCM_TRUMANAGE	24
+#define PORT_MAX_8250	25	/* max port ID */
 
 /*
  * ARM specific type numbers.  These are not currently guaranteed
-- 
cgit v1.2.3-55-g7522


From 2f91ec8cc456d6e57db3ebced34a9e96a356168f Mon Sep 17 00:00:00 2001
From: Kirill A. Shutemov
Date: Wed, 26 Dec 2012 03:19:55 +0300
Subject: asm-generic, mm: pgtable: convert my_zero_pfn() to macros to fix
 build

Commit 816422ad7647 ("asm-generic, mm: pgtable: consolidate zero page
helpers") broke the compile on MIPS if SPARSEMEM is enabled.  We get
this:

  In file included from arch/mips/include/asm/pgtable.h:552,
                   from include/linux/mm.h:44,
                   from arch/mips/kernel/asm-offsets.c:14:
  include/asm-generic/pgtable.h: In function 'my_zero_pfn':
  include/asm-generic/pgtable.h:466: error: implicit declaration of function 'page_to_section'
  In file included from arch/mips/kernel/asm-offsets.c:14:
  include/linux/mm.h: At top level:
  include/linux/mm.h:738: error: conflicting types for 'page_to_section'
  include/asm-generic/pgtable.h:466: note: previous implicit declaration of 'page_to_section' was here

Due header files inter-dependencies, the only way I see to fix it is
convert my_zero_pfn() for __HAVE_COLOR_ZERO_PAGE to macros.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Tested-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Acked-by: David Daney <david.daney@cavium.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/pgtable.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 701beab27aab..5cf680a98f9b 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -461,10 +461,8 @@ static inline int is_zero_pfn(unsigned long pfn)
 	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
 }
 
-static inline unsigned long my_zero_pfn(unsigned long addr)
-{
-	return page_to_pfn(ZERO_PAGE(addr));
-}
+#define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
+
 #else
 static inline int is_zero_pfn(unsigned long pfn)
 {
-- 
cgit v1.2.3-55-g7522


From edea0d03ee5f0ae0051b6adb6681ebdf976b1ca4 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov
Date: Sun, 20 Jan 2013 20:25:47 +0100
Subject: ia64: kill thread_matches(), unexport ptrace_check_attach()

The ia64 function "thread_matches()" has no users since commit
e868a55c2a8c ("[IA64] remove find_thread_for_addr()").  Remove it.

This allows us to make ptrace_check_attach() static to kernel/ptrace.c,
which is good since we'll need to change the semantics of it and fix up
all the callers.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/kernel/ptrace.c | 27 ---------------------------
 include/linux/ptrace.h    |  1 -
 kernel/ptrace.c           |  2 +-
 3 files changed, 1 insertion(+), 29 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 4265ff64219b..b7a5fffe0924 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -672,33 +672,6 @@ ptrace_attach_sync_user_rbs (struct task_struct *child)
 	read_unlock(&tasklist_lock);
 }
 
-static inline int
-thread_matches (struct task_struct *thread, unsigned long addr)
-{
-	unsigned long thread_rbs_end;
-	struct pt_regs *thread_regs;
-
-	if (ptrace_check_attach(thread, 0) < 0)
-		/*
-		 * If the thread is not in an attachable state, we'll
-		 * ignore it.  The net effect is that if ADDR happens
-		 * to overlap with the portion of the thread's
-		 * register backing store that is currently residing
-		 * on the thread's kernel stack, then ptrace() may end
-		 * up accessing a stale value.  But if the thread
-		 * isn't stopped, that's a problem anyhow, so we're
-		 * doing as well as we can...
-		 */
-		return 0;
-
-	thread_regs = task_pt_regs(thread);
-	thread_rbs_end = ia64_get_user_rbs_end(thread, thread_regs, NULL);
-	if (!on_kernel_rbs(addr, thread_regs->ar_bspstore, thread_rbs_end))
-		return 0;
-
-	return 1;	/* looks like we've got a winner */
-}
-
 /*
  * Write f32-f127 back to task->thread.fph if it has been modified.
  */
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 1693775ecfe8..89573a33ab3c 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -45,7 +45,6 @@ extern long arch_ptrace(struct task_struct *child, long request,
 extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len);
 extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len);
 extern void ptrace_disable(struct task_struct *);
-extern int ptrace_check_attach(struct task_struct *task, bool ignore_state);
 extern int ptrace_request(struct task_struct *child, long request,
 			  unsigned long addr, unsigned long data);
 extern void ptrace_notify(int exit_code);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1599157336a6..612a56126851 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -139,7 +139,7 @@ void __ptrace_unlink(struct task_struct *child)
  * RETURNS:
  * 0 on success, -ESRCH if %child is not ready.
  */
-int ptrace_check_attach(struct task_struct *child, bool ignore_state)
+static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 {
 	int ret = -ESRCH;
 
-- 
cgit v1.2.3-55-g7522


From 8141ed9fcedb278f4a3a78680591bef1e55f75fb Mon Sep 17 00:00:00 2001
From: Steffen Klassert
Date: Mon, 21 Jan 2013 02:00:03 +0000
Subject: ipv4: Add a socket release callback for datagram sockets

This implements a socket release callback function to check
if the socket cached route got invalid during the time
we owned the socket. The function is used from udp, raw
and ping sockets.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h    |  2 ++
 net/ipv4/datagram.c | 25 +++++++++++++++++++++++++
 net/ipv4/ping.c     |  1 +
 net/ipv4/raw.c      |  1 +
 net/ipv4/udp.c      |  1 +
 5 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index 0707fb9551aa..a68f838a132c 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -143,6 +143,8 @@ static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
 extern int		ip4_datagram_connect(struct sock *sk, 
 					     struct sockaddr *uaddr, int addr_len);
 
+extern void ip4_datagram_release_cb(struct sock *sk);
+
 struct ip_reply_arg {
 	struct kvec iov[1];   
 	int	    flags;
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 424fafbc8cb0..b28e863fe0a7 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -85,3 +85,28 @@ out:
 	return err;
 }
 EXPORT_SYMBOL(ip4_datagram_connect);
+
+void ip4_datagram_release_cb(struct sock *sk)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct ip_options_rcu *inet_opt;
+	__be32 daddr = inet->inet_daddr;
+	struct flowi4 fl4;
+	struct rtable *rt;
+
+	if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0))
+		return;
+
+	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
+	if (inet_opt && inet_opt->opt.srr)
+		daddr = inet_opt->opt.faddr;
+	rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr,
+				   inet->inet_saddr, inet->inet_dport,
+				   inet->inet_sport, sk->sk_protocol,
+				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
+	if (!IS_ERR(rt))
+		__sk_dst_set(sk, &rt->dst);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 8f3d05424a3e..6f9c07268cf6 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -738,6 +738,7 @@ struct proto ping_prot = {
 	.recvmsg =	ping_recvmsg,
 	.bind =		ping_bind,
 	.backlog_rcv =	ping_queue_rcv_skb,
+	.release_cb =	ip4_datagram_release_cb,
 	.hash =		ping_v4_hash,
 	.unhash =	ping_v4_unhash,
 	.get_port =	ping_v4_get_port,
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 73d1e4df4bf6..6f08991409c3 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -894,6 +894,7 @@ struct proto raw_prot = {
 	.recvmsg	   = raw_recvmsg,
 	.bind		   = raw_bind,
 	.backlog_rcv	   = raw_rcv_skb,
+	.release_cb	   = ip4_datagram_release_cb,
 	.hash		   = raw_hash_sk,
 	.unhash		   = raw_unhash_sk,
 	.obj_size	   = sizeof(struct raw_sock),
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 79c8dbe59b54..1f4d405eafba 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1952,6 +1952,7 @@ struct proto udp_prot = {
 	.recvmsg	   = udp_recvmsg,
 	.sendpage	   = udp_sendpage,
 	.backlog_rcv	   = __udp_queue_rcv_skb,
+	.release_cb	   = ip4_datagram_release_cb,
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
 	.rehash		   = udp_v4_rehash,
-- 
cgit v1.2.3-55-g7522


From 6509141f9c2ba74df6cc72ec35cd1865276ae3a4 Mon Sep 17 00:00:00 2001
From: Wei Shuai
Date: Mon, 21 Jan 2013 06:00:31 +0000
Subject: usbnet: add new flag FLAG_NOARP for usb net devices

We do have some USB net devices, which cannot do ARP.
so we can introduce a new flag FLAG_NOARP, then client drivers
can easily handle this kind of devices

Signed-off-by: Wei Shuai <cpuwolf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c   | 4 ++++
 include/linux/usb/usbnet.h | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 3d4bf01641b4..f34b2ebee815 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1448,6 +1448,10 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 		if ((dev->driver_info->flags & FLAG_WWAN) != 0)
 			strcpy(net->name, "wwan%d");
 
+		/* devices that cannot do ARP */
+		if ((dev->driver_info->flags & FLAG_NOARP) != 0)
+			net->flags |= IFF_NOARP;
+
 		/* maybe the remote can't receive an Ethernet MTU */
 		if (net->mtu > (dev->hard_mtu - net->hard_header_len))
 			net->mtu = dev->hard_mtu - net->hard_header_len;
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index bd45eb7bedc8..5de7a220e986 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -100,6 +100,7 @@ struct driver_info {
 #define FLAG_LINK_INTR	0x0800		/* updates link (carrier) status */
 
 #define FLAG_POINTTOPOINT 0x1000	/* possibly use "usb%d" names */
+#define FLAG_NOARP	0x2000		/* device can't do ARP */
 
 /*
  * Indicates to usbnet, that USB driver accumulates multiple IP packets.
-- 
cgit v1.2.3-55-g7522


From 00441b5e6b98ad6a50b5cb7f88d473e3ea1e0d75 Mon Sep 17 00:00:00 2001
From: Lee Jones
Date: Wed, 9 Jan 2013 10:06:03 +0000
Subject: mfd: Fix compile errors and warnings when !CONFIG_AB8500_BM

drivers/mfd/ab8500-core.c:1015:21: error: ‘ab8500_bm_data’ undeclared here

include/linux/mfd/abx500/ab8500-bm.h:445:13: warning: ‘ab8500_fg_reinit’ defined but not used
include/linux/mfd/abx500/ab8500-bm.h:448:13: warning: ‘ab8500_charger_usb_state_changed’ defined but not used
include/linux/mfd/abx500/ab8500-bm.h:451:29: warning: ‘ab8500_btemp_get’ defined but not used
include/linux/mfd/abx500/ab8500-bm.h:455:12: warning: ‘ab8500_btemp_get_batctrl_temp’ defined but not used
include/linux/mfd/abx500/ab8500-bm.h:463:12: warning: ‘ab8500_fg_inst_curr_blocking’ defined but not used
include/linux/mfd/abx500/ab8500-bm.h:442:12: warning: ‘ab8500_fg_inst_curr_done’ defined but not used
include/linux/mfd/abx500/ab8500-bm.h:447:26: warning: ‘ab8500_fg_get’ defined but not used

Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/ab8500-core.c            |  1 +
 include/linux/mfd/abx500.h           |  2 --
 include/linux/mfd/abx500/ab8500-bm.h | 29 ++++-------------------------
 3 files changed, 5 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index e1650badd106..4778bb124efe 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -19,6 +19,7 @@
 #include <linux/mfd/core.h>
 #include <linux/mfd/abx500.h>
 #include <linux/mfd/abx500/ab8500.h>
+#include <linux/mfd/abx500/ab8500-bm.h>
 #include <linux/mfd/dbx500-prcmu.h>
 #include <linux/regulator/ab8500.h>
 #include <linux/of.h>
diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h
index 2138bd33021a..e53dcfeaee69 100644
--- a/include/linux/mfd/abx500.h
+++ b/include/linux/mfd/abx500.h
@@ -272,8 +272,6 @@ struct abx500_bm_data {
 	const struct abx500_fg_parameters *fg_params;
 };
 
-extern struct abx500_bm_data ab8500_bm_data;
-
 enum {
 	NTC_EXTERNAL = 0,
 	NTC_INTERNAL,
diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h
index 44310c98ee6e..9bd037df97d9 100644
--- a/include/linux/mfd/abx500/ab8500-bm.h
+++ b/include/linux/mfd/abx500/ab8500-bm.h
@@ -422,7 +422,10 @@ struct ab8500_chargalg_platform_data {
 struct ab8500_btemp;
 struct ab8500_gpadc;
 struct ab8500_fg;
+
 #ifdef CONFIG_AB8500_BM
+extern struct abx500_bm_data ab8500_bm_data;
+
 void ab8500_fg_reinit(void);
 void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA);
 struct ab8500_btemp *ab8500_btemp_get(void);
@@ -434,31 +437,7 @@ int ab8500_fg_inst_curr_finalize(struct ab8500_fg *di, int *res);
 int ab8500_fg_inst_curr_done(struct ab8500_fg *di);
 
 #else
-int ab8500_fg_inst_curr_done(struct ab8500_fg *di)
-{
-}
-static void ab8500_fg_reinit(void)
-{
-}
-static void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA)
-{
-}
-static struct ab8500_btemp *ab8500_btemp_get(void)
-{
-	return NULL;
-}
-static int ab8500_btemp_get_batctrl_temp(struct ab8500_btemp *btemp)
-{
-	return 0;
-}
-struct ab8500_fg *ab8500_fg_get(void)
-{
-	return NULL;
-}
-static int ab8500_fg_inst_curr_blocking(struct ab8500_fg *dev)
-{
-	return -ENODEV;
-}
+static struct abx500_bm_data ab8500_bm_data;
 
 static inline int ab8500_fg_inst_curr_start(struct ab8500_fg *di)
 {
-- 
cgit v1.2.3-55-g7522


From 910ffdb18a6408e14febbb6e4b6840fd2c928c82 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov
Date: Mon, 21 Jan 2013 20:47:41 +0100
Subject: ptrace: introduce signal_wake_up_state() and ptrace_signal_wake_up()

Cleanup and preparation for the next change.

signal_wake_up(resume => true) is overused. None of ptrace/jctl callers
actually want to wakeup a TASK_WAKEKILL task, but they can't specify the
necessary mask.

Turn signal_wake_up() into signal_wake_up_state(state), reintroduce
signal_wake_up() as a trivial helper, and add ptrace_signal_wake_up()
which adds __TASK_TRACED.

This way ptrace_signal_wake_up() can work "inside" ptrace_request()
even if the tracee doesn't have the TASK_WAKEKILL bit set.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h | 11 ++++++++++-
 kernel/ptrace.c       |  8 ++++----
 kernel/signal.c       | 14 ++++----------
 3 files changed, 18 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6fc8f45de4e9..d2112477ff5e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2714,7 +2714,16 @@ static inline void thread_group_cputime_init(struct signal_struct *sig)
 extern void recalc_sigpending_and_wake(struct task_struct *t);
 extern void recalc_sigpending(void);
 
-extern void signal_wake_up(struct task_struct *t, int resume_stopped);
+extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
+
+static inline void signal_wake_up(struct task_struct *t, bool resume)
+{
+	signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
+}
+static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
+{
+	signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
+}
 
 /*
  * Wrappers for p->thread_info->cpu access. No-op on UP.
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 612a56126851..62f7c2774b16 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -117,7 +117,7 @@ void __ptrace_unlink(struct task_struct *child)
 	 * TASK_KILLABLE sleeps.
 	 */
 	if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child))
-		signal_wake_up(child, task_is_traced(child));
+		ptrace_signal_wake_up(child, true);
 
 	spin_unlock(&child->sighand->siglock);
 }
@@ -317,7 +317,7 @@ static int ptrace_attach(struct task_struct *task, long request,
 	 */
 	if (task_is_stopped(task) &&
 	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING))
-		signal_wake_up(task, 1);
+		signal_wake_up_state(task, __TASK_STOPPED);
 
 	spin_unlock(&task->sighand->siglock);
 
@@ -737,7 +737,7 @@ int ptrace_request(struct task_struct *child, long request,
 		 * tracee into STOP.
 		 */
 		if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP)))
-			signal_wake_up(child, child->jobctl & JOBCTL_LISTENING);
+			ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING);
 
 		unlock_task_sighand(child, &flags);
 		ret = 0;
@@ -763,7 +763,7 @@ int ptrace_request(struct task_struct *child, long request,
 			 * start of this trap and now.  Trigger re-trap.
 			 */
 			if (child->jobctl & JOBCTL_TRAP_NOTIFY)
-				signal_wake_up(child, true);
+				ptrace_signal_wake_up(child, true);
 			ret = 0;
 		}
 		unlock_task_sighand(child, &flags);
diff --git a/kernel/signal.c b/kernel/signal.c
index 53cd5c4d1172..6e97aa6fa32c 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -680,23 +680,17 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
  * No need to set need_resched since signal event passing
  * goes through ->blocked
  */
-void signal_wake_up(struct task_struct *t, int resume)
+void signal_wake_up_state(struct task_struct *t, unsigned int state)
 {
-	unsigned int mask;
-
 	set_tsk_thread_flag(t, TIF_SIGPENDING);
-
 	/*
-	 * For SIGKILL, we want to wake it up in the stopped/traced/killable
+	 * TASK_WAKEKILL also means wake it up in the stopped/traced/killable
 	 * case. We don't check t->state here because there is a race with it
 	 * executing another processor and just now entering stopped state.
 	 * By using wake_up_state, we ensure the process will wake up and
 	 * handle its death signal.
 	 */
-	mask = TASK_INTERRUPTIBLE;
-	if (resume)
-		mask |= TASK_WAKEKILL;
-	if (!wake_up_state(t, mask))
+	if (!wake_up_state(t, state | TASK_INTERRUPTIBLE))
 		kick_process(t);
 }
 
@@ -844,7 +838,7 @@ static void ptrace_trap_notify(struct task_struct *t)
 	assert_spin_locked(&t->sighand->siglock);
 
 	task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY);
-	signal_wake_up(t, t->jobctl & JOBCTL_LISTENING);
+	ptrace_signal_wake_up(t, t->jobctl & JOBCTL_LISTENING);
 }
 
 /*
-- 
cgit v1.2.3-55-g7522


From 54a3ac0c9e5b7213daa358ce74d154352657353a Mon Sep 17 00:00:00 2001
From: Lan Tianyu
Date: Thu, 24 Jan 2013 10:31:28 +0800
Subject: usb: Using correct way to clear usb3.0 device's remote wakeup
 feature.

Usb3.0 device defines function remote wakeup which is only for interface
recipient rather than device recipient. This is different with usb2.0 device's
remote wakeup feature which is defined for device recipient. According usb3.0
spec 9.4.5, the function remote wakeup can be modified by the SetFeature()
requests using the FUNCTION_SUSPEND feature selector. This patch is to use
correct way to disable usb3.0 device's function remote wakeup after suspend
error and resuming.

This should be backported to kernels as old as 3.4, that contain the
commit 623bef9e03a60adc623b09673297ca7a1cdfb367 "USB/xhci: Enable remote
wakeup for USB3 devices."

Signed-off-by: Lan Tianyu <tianyu.lan@intel.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Cc: stable@vger.kernel.org
---
 drivers/usb/core/hub.c       | 70 ++++++++++++++++++++++++++++++++------------
 include/uapi/linux/usb/ch9.h |  6 ++++
 2 files changed, 58 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 957ed2c41482..cbf7168e3ce7 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2838,6 +2838,23 @@ void usb_enable_ltm(struct usb_device *udev)
 EXPORT_SYMBOL_GPL(usb_enable_ltm);
 
 #ifdef	CONFIG_USB_SUSPEND
+/*
+ * usb_disable_function_remotewakeup - disable usb3.0
+ * device's function remote wakeup
+ * @udev: target device
+ *
+ * Assume there's only one function on the USB 3.0
+ * device and disable remote wake for the first
+ * interface. FIXME if the interface association
+ * descriptor shows there's more than one function.
+ */
+static int usb_disable_function_remotewakeup(struct usb_device *udev)
+{
+	return usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
+				USB_REQ_CLEAR_FEATURE, USB_RECIP_INTERFACE,
+				USB_INTRF_FUNC_SUSPEND,	0, NULL, 0,
+				USB_CTRL_SET_TIMEOUT);
+}
 
 /*
  * usb_port_suspend - suspend a usb device's upstream port
@@ -2955,12 +2972,19 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
 		dev_dbg(hub->intfdev, "can't suspend port %d, status %d\n",
 				port1, status);
 		/* paranoia:  "should not happen" */
-		if (udev->do_remote_wakeup)
-			(void) usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
-				USB_REQ_CLEAR_FEATURE, USB_RECIP_DEVICE,
-				USB_DEVICE_REMOTE_WAKEUP, 0,
-				NULL, 0,
-				USB_CTRL_SET_TIMEOUT);
+		if (udev->do_remote_wakeup) {
+			if (!hub_is_superspeed(hub->hdev)) {
+				(void) usb_control_msg(udev,
+						usb_sndctrlpipe(udev, 0),
+						USB_REQ_CLEAR_FEATURE,
+						USB_RECIP_DEVICE,
+						USB_DEVICE_REMOTE_WAKEUP, 0,
+						NULL, 0,
+						USB_CTRL_SET_TIMEOUT);
+			} else
+				(void) usb_disable_function_remotewakeup(udev);
+
+		}
 
 		/* Try to enable USB2 hardware LPM again */
 		if (udev->usb2_hw_lpm_capable == 1)
@@ -3052,20 +3076,30 @@ static int finish_port_resume(struct usb_device *udev)
 	 * udev->reset_resume
 	 */
 	} else if (udev->actconfig && !udev->reset_resume) {
-		le16_to_cpus(&devstatus);
-		if (devstatus & (1 << USB_DEVICE_REMOTE_WAKEUP)) {
-			status = usb_control_msg(udev,
-					usb_sndctrlpipe(udev, 0),
-					USB_REQ_CLEAR_FEATURE,
+		if (!hub_is_superspeed(udev->parent)) {
+			le16_to_cpus(&devstatus);
+			if (devstatus & (1 << USB_DEVICE_REMOTE_WAKEUP))
+				status = usb_control_msg(udev,
+						usb_sndctrlpipe(udev, 0),
+						USB_REQ_CLEAR_FEATURE,
 						USB_RECIP_DEVICE,
-					USB_DEVICE_REMOTE_WAKEUP, 0,
-					NULL, 0,
-					USB_CTRL_SET_TIMEOUT);
-			if (status)
-				dev_dbg(&udev->dev,
-					"disable remote wakeup, status %d\n",
-					status);
+						USB_DEVICE_REMOTE_WAKEUP, 0,
+						NULL, 0,
+						USB_CTRL_SET_TIMEOUT);
+		} else {
+			status = usb_get_status(udev, USB_RECIP_INTERFACE, 0,
+					&devstatus);
+			le16_to_cpus(&devstatus);
+			if (!status && devstatus & (USB_INTRF_STAT_FUNC_RW_CAP
+					| USB_INTRF_STAT_FUNC_RW))
+				status =
+					usb_disable_function_remotewakeup(udev);
 		}
+
+		if (status)
+			dev_dbg(&udev->dev,
+				"disable remote wakeup, status %d\n",
+				status);
 		status = 0;
 	}
 	return status;
diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h
index 50598472dc41..f738e25377ff 100644
--- a/include/uapi/linux/usb/ch9.h
+++ b/include/uapi/linux/usb/ch9.h
@@ -152,6 +152,12 @@
 #define USB_INTRF_FUNC_SUSPEND_LP	(1 << (8 + 0))
 #define USB_INTRF_FUNC_SUSPEND_RW	(1 << (8 + 1))
 
+/*
+ * Interface status, Figure 9-5 USB 3.0 spec
+ */
+#define USB_INTRF_STAT_FUNC_RW_CAP     1
+#define USB_INTRF_STAT_FUNC_RW         2
+
 #define USB_ENDPOINT_HALT		0	/* IN/OUT will STALL */
 
 /* Bit array elements as returned by the USB_REQ_GET_STATUS request. */
-- 
cgit v1.2.3-55-g7522


From da0aa7169b97d90f4af39a9dc84d58bbe19d7e78 Mon Sep 17 00:00:00 2001
From: Alan Stern
Date: Fri, 25 Jan 2013 17:09:42 -0500
Subject: USB: add usb_hcd_{start,end}_port_resume

This patch (as1649) adds a mechanism for host controller drivers to
inform usbcore when they have begun or ended resume signalling on a
particular root-hub port.  The core will then make sure that the root
hub does not get runtime-suspended while the port resume is going on.

Since commit 596d789a211d134dc5f94d1e5957248c204ef850 (USB: set hub's
default autosuspend delay as 0), the system tries to suspend hubs
whenever they aren't in use.  While a root-hub port is being resumed,
the root hub does not appear to be in use.  Attempted runtime suspends
fail because of the ongoing port resume, but the PM core just keeps on
trying over and over again.  We want to prevent this wasteful effort.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Tested-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c  | 44 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/usb.h     |  2 ++
 include/linux/usb/hcd.h |  3 +++
 3 files changed, 49 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 4225d5e72131..8e64adf8e4d5 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -39,6 +39,7 @@
 #include <asm/unaligned.h>
 #include <linux/platform_device.h>
 #include <linux/workqueue.h>
+#include <linux/pm_runtime.h>
 
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
@@ -1025,6 +1026,49 @@ static int register_root_hub(struct usb_hcd *hcd)
 	return retval;
 }
 
+/*
+ * usb_hcd_start_port_resume - a root-hub port is sending a resume signal
+ * @bus: the bus which the root hub belongs to
+ * @portnum: the port which is being resumed
+ *
+ * HCDs should call this function when they know that a resume signal is
+ * being sent to a root-hub port.  The root hub will be prevented from
+ * going into autosuspend until usb_hcd_end_port_resume() is called.
+ *
+ * The bus's private lock must be held by the caller.
+ */
+void usb_hcd_start_port_resume(struct usb_bus *bus, int portnum)
+{
+	unsigned bit = 1 << portnum;
+
+	if (!(bus->resuming_ports & bit)) {
+		bus->resuming_ports |= bit;
+		pm_runtime_get_noresume(&bus->root_hub->dev);
+	}
+}
+EXPORT_SYMBOL_GPL(usb_hcd_start_port_resume);
+
+/*
+ * usb_hcd_end_port_resume - a root-hub port has stopped sending a resume signal
+ * @bus: the bus which the root hub belongs to
+ * @portnum: the port which is being resumed
+ *
+ * HCDs should call this function when they know that a resume signal has
+ * stopped being sent to a root-hub port.  The root hub will be allowed to
+ * autosuspend again.
+ *
+ * The bus's private lock must be held by the caller.
+ */
+void usb_hcd_end_port_resume(struct usb_bus *bus, int portnum)
+{
+	unsigned bit = 1 << portnum;
+
+	if (bus->resuming_ports & bit) {
+		bus->resuming_ports &= ~bit;
+		pm_runtime_put_noidle(&bus->root_hub->dev);
+	}
+}
+EXPORT_SYMBOL_GPL(usb_hcd_end_port_resume);
 
 /*-------------------------------------------------------------------------*/
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 689b14b26c8d..4d22d0f6167a 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -357,6 +357,8 @@ struct usb_bus {
 	int bandwidth_int_reqs;		/* number of Interrupt requests */
 	int bandwidth_isoc_reqs;	/* number of Isoc. requests */
 
+	unsigned resuming_ports;	/* bit array: resuming root-hub ports */
+
 #if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE)
 	struct mon_bus *mon_bus;	/* non-null when associated */
 	int monitored;			/* non-zero when monitored */
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 608050b2545f..0a78df5f6cfd 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -430,6 +430,9 @@ extern void usb_hcd_poll_rh_status(struct usb_hcd *hcd);
 extern void usb_wakeup_notification(struct usb_device *hdev,
 		unsigned int portnum);
 
+extern void usb_hcd_start_port_resume(struct usb_bus *bus, int portnum);
+extern void usb_hcd_end_port_resume(struct usb_bus *bus, int portnum);
+
 /* The D0/D1 toggle bits ... USE WITH CAUTION (they're almost hcd-internal) */
 #define usb_gettoggle(dev, ep, out) (((dev)->toggle[out] >> (ep)) & 1)
 #define	usb_dotoggle(dev, ep, out)  ((dev)->toggle[out] ^= (1 << (ep)))
-- 
cgit v1.2.3-55-g7522


From d817ac4e181710cd02b582b759d3123ad2cfa8d8 Mon Sep 17 00:00:00 2001
From: Wei WANG
Date: Wed, 23 Jan 2013 09:51:04 +0800
Subject: mfd: rtsx: Add output voltage switch hook

Different card reader has different method to switch output voltage,
add this callback to let the card reader implement its individual switch
function.
This is needed as rtl8411 has a specific switch output voltage procedure.

Signed-off-by: Wei WANG <wei_wang@realsil.com.cn>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/rtl8411.c        | 16 ++++++++++++++++
 drivers/mfd/rts5209.c        | 20 ++++++++++++++++++++
 drivers/mfd/rts5229.c        | 20 ++++++++++++++++++++
 drivers/mfd/rtsx_pcr.c       |  9 +++++++++
 include/linux/mfd/rtsx_pci.h | 24 ++++++++++++++++++++----
 5 files changed, 85 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/rtl8411.c b/drivers/mfd/rtl8411.c
index 89f046ca9e41..5058ba8dec3b 100644
--- a/drivers/mfd/rtl8411.c
+++ b/drivers/mfd/rtl8411.c
@@ -112,6 +112,21 @@ static int rtl8411_card_power_off(struct rtsx_pcr *pcr, int card)
 			BPP_LDO_POWB, BPP_LDO_SUSPEND);
 }
 
+static int rtl8411_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	u8 mask, val;
+
+	mask = (BPP_REG_TUNED18 << BPP_TUNED18_SHIFT_8411) | BPP_PAD_MASK;
+	if (voltage == OUTPUT_3V3)
+		val = (BPP_ASIC_3V3 << BPP_TUNED18_SHIFT_8411) | BPP_PAD_3V3;
+	else if (voltage == OUTPUT_1V8)
+		val = (BPP_ASIC_1V8 << BPP_TUNED18_SHIFT_8411) | BPP_PAD_1V8;
+	else
+		return -EINVAL;
+
+	return rtsx_pci_write_register(pcr, LDO_CTL, mask, val);
+}
+
 static unsigned int rtl8411_cd_deglitch(struct rtsx_pcr *pcr)
 {
 	unsigned int card_exist;
@@ -172,6 +187,7 @@ static const struct pcr_ops rtl8411_pcr_ops = {
 	.disable_auto_blink = rtl8411_disable_auto_blink,
 	.card_power_on = rtl8411_card_power_on,
 	.card_power_off = rtl8411_card_power_off,
+	.switch_output_voltage = rtl8411_switch_output_voltage,
 	.cd_deglitch = rtl8411_cd_deglitch,
 };
 
diff --git a/drivers/mfd/rts5209.c b/drivers/mfd/rts5209.c
index 283a4f148084..ba74de8a7c24 100644
--- a/drivers/mfd/rts5209.c
+++ b/drivers/mfd/rts5209.c
@@ -144,6 +144,25 @@ static int rts5209_card_power_off(struct rtsx_pcr *pcr, int card)
 	return rtsx_pci_send_cmd(pcr, 100);
 }
 
+static int rts5209_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	int err;
+
+	if (voltage == OUTPUT_3V3) {
+		err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4FC0 | 0x24);
+		if (err < 0)
+			return err;
+	} else if (voltage == OUTPUT_1V8) {
+		err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4C40 | 0x24);
+		if (err < 0)
+			return err;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pcr_ops rts5209_pcr_ops = {
 	.extra_init_hw = rts5209_extra_init_hw,
 	.optimize_phy = rts5209_optimize_phy,
@@ -153,6 +172,7 @@ static const struct pcr_ops rts5209_pcr_ops = {
 	.disable_auto_blink = rts5209_disable_auto_blink,
 	.card_power_on = rts5209_card_power_on,
 	.card_power_off = rts5209_card_power_off,
+	.switch_output_voltage = rts5209_switch_output_voltage,
 	.cd_deglitch = NULL,
 };
 
diff --git a/drivers/mfd/rts5229.c b/drivers/mfd/rts5229.c
index b9dbab266fda..ec1747adf5d3 100644
--- a/drivers/mfd/rts5229.c
+++ b/drivers/mfd/rts5229.c
@@ -114,6 +114,25 @@ static int rts5229_card_power_off(struct rtsx_pcr *pcr, int card)
 	return rtsx_pci_send_cmd(pcr, 100);
 }
 
+static int rts5229_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	int err;
+
+	if (voltage == OUTPUT_3V3) {
+		err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4FC0 | 0x24);
+		if (err < 0)
+			return err;
+	} else if (voltage == OUTPUT_1V8) {
+		err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4C40 | 0x24);
+		if (err < 0)
+			return err;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pcr_ops rts5229_pcr_ops = {
 	.extra_init_hw = rts5229_extra_init_hw,
 	.optimize_phy = rts5229_optimize_phy,
@@ -123,6 +142,7 @@ static const struct pcr_ops rts5229_pcr_ops = {
 	.disable_auto_blink = rts5229_disable_auto_blink,
 	.card_power_on = rts5229_card_power_on,
 	.card_power_off = rts5229_card_power_off,
+	.switch_output_voltage = rts5229_switch_output_voltage,
 	.cd_deglitch = NULL,
 };
 
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index 7a7b0bda4618..f4e02d089271 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -703,6 +703,15 @@ int rtsx_pci_card_power_off(struct rtsx_pcr *pcr, int card)
 }
 EXPORT_SYMBOL_GPL(rtsx_pci_card_power_off);
 
+int rtsx_pci_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	if (pcr->ops->switch_output_voltage)
+		return pcr->ops->switch_output_voltage(pcr, voltage);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_switch_output_voltage);
+
 unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr)
 {
 	unsigned int val;
diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
index 060b721fcbfb..271b6e5654af 100644
--- a/include/linux/mfd/rtsx_pci.h
+++ b/include/linux/mfd/rtsx_pci.h
@@ -158,10 +158,9 @@
 #define SG_TRANS_DATA		(0x02 << 4)
 #define SG_LINK_DESC		(0x03 << 4)
 
-/* SD bank voltage */
-#define SD_IO_3V3		0
-#define SD_IO_1V8		1
-
+/* Output voltage */
+#define OUTPUT_3V3		0
+#define OUTPUT_1V8		1
 
 /* Card Clock Enable Register */
 #define SD_CLK_EN			0x04
@@ -201,6 +200,20 @@
 #define CHANGE_CLK			0x01
 
 /* LDO_CTL */
+#define BPP_ASIC_1V7			0x00
+#define BPP_ASIC_1V8			0x01
+#define BPP_ASIC_1V9			0x02
+#define BPP_ASIC_2V0			0x03
+#define BPP_ASIC_2V7			0x04
+#define BPP_ASIC_2V8			0x05
+#define BPP_ASIC_3V2			0x06
+#define BPP_ASIC_3V3			0x07
+#define BPP_REG_TUNED18			0x07
+#define BPP_TUNED18_SHIFT_8402		5
+#define BPP_TUNED18_SHIFT_8411		4
+#define BPP_PAD_MASK			0x04
+#define BPP_PAD_3V3			0x04
+#define BPP_PAD_1V8			0x00
 #define BPP_LDO_POWB			0x03
 #define BPP_LDO_ON			0x00
 #define BPP_LDO_SUSPEND			0x02
@@ -688,6 +701,8 @@ struct pcr_ops {
 	int		(*disable_auto_blink)(struct rtsx_pcr *pcr);
 	int		(*card_power_on)(struct rtsx_pcr *pcr, int card);
 	int		(*card_power_off)(struct rtsx_pcr *pcr, int card);
+	int		(*switch_output_voltage)(struct rtsx_pcr *pcr,
+						u8 voltage);
 	unsigned int	(*cd_deglitch)(struct rtsx_pcr *pcr);
 };
 
@@ -783,6 +798,7 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
 		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk);
 int rtsx_pci_card_power_on(struct rtsx_pcr *pcr, int card);
 int rtsx_pci_card_power_off(struct rtsx_pcr *pcr, int card);
+int rtsx_pci_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage);
 unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr);
 void rtsx_pci_complete_unfinished_transfer(struct rtsx_pcr *pcr);
 
-- 
cgit v1.2.3-55-g7522


From ab4e8f8b7bdfeff0c961fdbbdacb262d68f094c0 Mon Sep 17 00:00:00 2001
From: Wei WANG
Date: Wed, 23 Jan 2013 09:51:06 +0800
Subject: mfd: rtsx: Add clock divider hook

Add callback function conv_clk_and_div_n to convert between SSC clock
and its divider N.
For rtl8411, the formula to calculate SSC clock divider N is different
with the other card reader models.

Signed-off-by: Wei WANG <wei_wang@realsil.com.cn>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/rtl8411.c           | 13 +++++++++++++
 drivers/mfd/rts5209.c           |  1 +
 drivers/mfd/rts5229.c           |  1 +
 drivers/mfd/rtsx_pcr.c          | 14 ++++++++++++--
 include/linux/mfd/rtsx_common.h |  3 +++
 include/linux/mfd/rtsx_pci.h    |  1 +
 6 files changed, 31 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/rtl8411.c b/drivers/mfd/rtl8411.c
index 5058ba8dec3b..3d3b4addf81a 100644
--- a/drivers/mfd/rtl8411.c
+++ b/drivers/mfd/rtl8411.c
@@ -178,6 +178,18 @@ static unsigned int rtl8411_cd_deglitch(struct rtsx_pcr *pcr)
 	return card_exist;
 }
 
+static int rtl8411_conv_clk_and_div_n(int input, int dir)
+{
+	int output;
+
+	if (dir == CLK_TO_DIV_N)
+		output = input * 4 / 5 - 2;
+	else
+		output = (input + 2) * 5 / 4;
+
+	return output;
+}
+
 static const struct pcr_ops rtl8411_pcr_ops = {
 	.extra_init_hw = rtl8411_extra_init_hw,
 	.optimize_phy = NULL,
@@ -189,6 +201,7 @@ static const struct pcr_ops rtl8411_pcr_ops = {
 	.card_power_off = rtl8411_card_power_off,
 	.switch_output_voltage = rtl8411_switch_output_voltage,
 	.cd_deglitch = rtl8411_cd_deglitch,
+	.conv_clk_and_div_n = rtl8411_conv_clk_and_div_n,
 };
 
 /* SD Pull Control Enable:
diff --git a/drivers/mfd/rts5209.c b/drivers/mfd/rts5209.c
index ba74de8a7c24..98fe0f39463e 100644
--- a/drivers/mfd/rts5209.c
+++ b/drivers/mfd/rts5209.c
@@ -174,6 +174,7 @@ static const struct pcr_ops rts5209_pcr_ops = {
 	.card_power_off = rts5209_card_power_off,
 	.switch_output_voltage = rts5209_switch_output_voltage,
 	.cd_deglitch = NULL,
+	.conv_clk_and_div_n = NULL,
 };
 
 /* SD Pull Control Enable:
diff --git a/drivers/mfd/rts5229.c b/drivers/mfd/rts5229.c
index ec1747adf5d3..29d889cbb9c5 100644
--- a/drivers/mfd/rts5229.c
+++ b/drivers/mfd/rts5229.c
@@ -144,6 +144,7 @@ static const struct pcr_ops rts5229_pcr_ops = {
 	.card_power_off = rts5229_card_power_off,
 	.switch_output_voltage = rts5229_switch_output_voltage,
 	.cd_deglitch = NULL,
+	.conv_clk_and_div_n = NULL,
 };
 
 /* SD Pull Control Enable:
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index f4e02d089271..910200e10fa0 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -630,7 +630,10 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
 	if (clk == pcr->cur_clock)
 		return 0;
 
-	N = (u8)(clk - 2);
+	if (pcr->ops->conv_clk_and_div_n)
+		N = (u8)pcr->ops->conv_clk_and_div_n(clk, CLK_TO_DIV_N);
+	else
+		N = (u8)(clk - 2);
 	if ((clk <= 2) || (N > max_N))
 		return -EINVAL;
 
@@ -641,7 +644,14 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
 	/* Make sure that the SSC clock div_n is equal or greater than min_N */
 	div = CLK_DIV_1;
 	while ((N < min_N) && (div < max_div)) {
-		N = (N + 2) * 2 - 2;
+		if (pcr->ops->conv_clk_and_div_n) {
+			int dbl_clk = pcr->ops->conv_clk_and_div_n(N,
+					DIV_N_TO_CLK) * 2;
+			N = (u8)pcr->ops->conv_clk_and_div_n(dbl_clk,
+					CLK_TO_DIV_N);
+		} else {
+			N = (N + 2) * 2 - 2;
+		}
 		div++;
 	}
 	dev_dbg(&(pcr->pci->dev), "N = %d, div = %d\n", N, div);
diff --git a/include/linux/mfd/rtsx_common.h b/include/linux/mfd/rtsx_common.h
index a8d393e3066b..2b13970596f5 100644
--- a/include/linux/mfd/rtsx_common.h
+++ b/include/linux/mfd/rtsx_common.h
@@ -38,6 +38,9 @@
 #define RTSX_SD_CARD			0
 #define RTSX_MS_CARD			1
 
+#define CLK_TO_DIV_N			0
+#define DIV_N_TO_CLK			1
+
 struct platform_device;
 
 struct rtsx_slot {
diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
index 271b6e5654af..4b117a3f54d4 100644
--- a/include/linux/mfd/rtsx_pci.h
+++ b/include/linux/mfd/rtsx_pci.h
@@ -704,6 +704,7 @@ struct pcr_ops {
 	int		(*switch_output_voltage)(struct rtsx_pcr *pcr,
 						u8 voltage);
 	unsigned int	(*cd_deglitch)(struct rtsx_pcr *pcr);
+	int		(*conv_clk_and_div_n)(int clk, int dir);
 };
 
 enum PDEV_STAT  {PDEV_STAT_IDLE, PDEV_STAT_RUN};
-- 
cgit v1.2.3-55-g7522


From 0a8c290ac58a86d5e1f2193abcd4d74ec075e20c Mon Sep 17 00:00:00 2001
From: Ashish Jangam
Date: Fri, 25 Jan 2013 14:03:49 +0530
Subject: mfd: da9052/53 lockup fix

An issue has been reported where the PMIC either locks up or fails to
respond following a system Reset. This could result in a second write
in which the bus writes the current content of the write buffer to address
of the last I2C access.

The failure case is where this unwanted write transfers incorrect data to
a critical register.

This patch fixes this issue to by following any read or write with a dummy read
to a safe register address. A safe register address is one where the contents
will not affect the operation of the system.

Signed-off-by: Ashish Jangam <ashish.jangam@kpitcummins.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/da9052-i2c.c          | 61 ++++++++++++++++++++++++++++++++++++
 include/linux/mfd/da9052/da9052.h | 66 ++++++++++++++++++++++++++++++++++++---
 include/linux/mfd/da9052/reg.h    |  3 ++
 3 files changed, 126 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c
index ac74a4d1daea..885e56780358 100644
--- a/drivers/mfd/da9052-i2c.c
+++ b/drivers/mfd/da9052-i2c.c
@@ -27,6 +27,66 @@
 #include <linux/of_device.h>
 #endif
 
+/* I2C safe register check */
+static inline bool i2c_safe_reg(unsigned char reg)
+{
+	switch (reg) {
+	case DA9052_STATUS_A_REG:
+	case DA9052_STATUS_B_REG:
+	case DA9052_STATUS_C_REG:
+	case DA9052_STATUS_D_REG:
+	case DA9052_ADC_RES_L_REG:
+	case DA9052_ADC_RES_H_REG:
+	case DA9052_VDD_RES_REG:
+	case DA9052_ICHG_AV_REG:
+	case DA9052_TBAT_RES_REG:
+	case DA9052_ADCIN4_RES_REG:
+	case DA9052_ADCIN5_RES_REG:
+	case DA9052_ADCIN6_RES_REG:
+	case DA9052_TJUNC_RES_REG:
+	case DA9052_TSI_X_MSB_REG:
+	case DA9052_TSI_Y_MSB_REG:
+	case DA9052_TSI_LSB_REG:
+	case DA9052_TSI_Z_MSB_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/*
+ * There is an issue with DA9052 and DA9053_AA/BA/BB PMIC where the PMIC
+ * gets lockup up or fails to respond following a system reset.
+ * This fix is to follow any read or write with a dummy read to a safe
+ * register.
+ */
+int da9052_i2c_fix(struct da9052 *da9052, unsigned char reg)
+{
+	int val;
+
+	switch (da9052->chip_id) {
+	case DA9052:
+	case DA9053_AA:
+	case DA9053_BA:
+	case DA9053_BB:
+		/* A dummy read to a safe register address. */
+	if (!i2c_safe_reg(reg))
+			return regmap_read(da9052->regmap,
+					   DA9052_PARK_REGISTER,
+					   &val);
+		break;
+	default:
+		/*
+		 * For other chips parking of I2C register
+		 * to a safe place is not required.
+		 */
+		break;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(da9052_i2c_fix);
+
 static int da9052_i2c_enable_multiwrite(struct da9052 *da9052)
 {
 	int reg_val, ret;
@@ -83,6 +143,7 @@ static int da9052_i2c_probe(struct i2c_client *client,
 
 	da9052->dev = &client->dev;
 	da9052->chip_irq = client->irq;
+	da9052->fix_io = da9052_i2c_fix;
 
 	i2c_set_clientdata(client, da9052);
 
diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index 86dd93de6ff2..786d02eb79d2 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -99,6 +99,9 @@ struct da9052 {
 	u8 chip_id;
 
 	int chip_irq;
+
+	/* SOC I/O transfer related fixes for DA9052/53 */
+	int (*fix_io) (struct da9052 *da9052, unsigned char reg);
 };
 
 /* ADC API */
@@ -113,32 +116,87 @@ static inline int da9052_reg_read(struct da9052 *da9052, unsigned char reg)
 	ret = regmap_read(da9052->regmap, reg, &val);
 	if (ret < 0)
 		return ret;
+
+	if (da9052->fix_io) {
+		ret = da9052->fix_io(da9052, reg);
+		if (ret < 0)
+			return ret;
+	}
+
 	return val;
 }
 
 static inline int da9052_reg_write(struct da9052 *da9052, unsigned char reg,
 				    unsigned char val)
 {
-	return regmap_write(da9052->regmap, reg, val);
+	int ret;
+
+	ret = regmap_write(da9052->regmap, reg, val);
+	if (ret < 0)
+		return ret;
+
+	if (da9052->fix_io) {
+		ret = da9052->fix_io(da9052, reg);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
 }
 
 static inline int da9052_group_read(struct da9052 *da9052, unsigned char reg,
 				     unsigned reg_cnt, unsigned char *val)
 {
-	return regmap_bulk_read(da9052->regmap, reg, val, reg_cnt);
+	int ret;
+
+	ret = regmap_bulk_read(da9052->regmap, reg, val, reg_cnt);
+	if (ret < 0)
+		return ret;
+
+	if (da9052->fix_io) {
+		ret = da9052->fix_io(da9052, reg);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
 }
 
 static inline int da9052_group_write(struct da9052 *da9052, unsigned char reg,
 				      unsigned reg_cnt, unsigned char *val)
 {
-	return regmap_raw_write(da9052->regmap, reg, val, reg_cnt);
+	int ret;
+
+	ret = regmap_raw_write(da9052->regmap, reg, val, reg_cnt);
+	if (ret < 0)
+		return ret;
+
+	if (da9052->fix_io) {
+		ret = da9052->fix_io(da9052, reg);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
 }
 
 static inline int da9052_reg_update(struct da9052 *da9052, unsigned char reg,
 				     unsigned char bit_mask,
 				     unsigned char reg_val)
 {
-	return regmap_update_bits(da9052->regmap, reg, bit_mask, reg_val);
+	int ret;
+
+	ret = regmap_update_bits(da9052->regmap, reg, bit_mask, reg_val);
+	if (ret < 0)
+		return ret;
+
+	if (da9052->fix_io) {
+		ret = da9052->fix_io(da9052, reg);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
 }
 
 int da9052_device_init(struct da9052 *da9052, u8 chip_id);
diff --git a/include/linux/mfd/da9052/reg.h b/include/linux/mfd/da9052/reg.h
index b97f7309d7f6..c4dd3a8add21 100644
--- a/include/linux/mfd/da9052/reg.h
+++ b/include/linux/mfd/da9052/reg.h
@@ -34,6 +34,9 @@
 #define DA9052_STATUS_C_REG		3
 #define DA9052_STATUS_D_REG		4
 
+/* PARK REGISTER */
+#define DA9052_PARK_REGISTER		DA9052_STATUS_D_REG
+
 /* EVENT REGISTERS */
 #define DA9052_EVENT_A_REG		5
 #define DA9052_EVENT_B_REG		6
-- 
cgit v1.2.3-55-g7522


From 83e68189745ad931c2afd45d8ee3303929233e7f Mon Sep 17 00:00:00 2001
From: Matt Fleming
Date: Wed, 14 Nov 2012 09:42:35 +0000
Subject: efi: Make 'efi_enabled' a function to query EFI facilities

Originally 'efi_enabled' indicated whether a kernel was booted from
EFI firmware. Over time its semantics have changed, and it now
indicates whether or not we are booted on an EFI machine with
bit-native firmware, e.g. 64-bit kernel with 64-bit firmware.

The immediate motivation for this patch is the bug report at,

    https://bugs.launchpad.net/ubuntu-cdimage/+bug/1040557

which details how running a platform driver on an EFI machine that is
designed to run under BIOS can cause the machine to become
bricked. Also, the following report,

    https://bugzilla.kernel.org/show_bug.cgi?id=47121

details how running said driver can also cause Machine Check
Exceptions. Drivers need a new means of detecting whether they're
running on an EFI machine, as sadly the expression,

    if (!efi_enabled)

hasn't been a sufficient condition for quite some time.

Users actually want to query 'efi_enabled' for different reasons -
what they really want access to is the list of available EFI
facilities.

For instance, the x86 reboot code needs to know whether it can invoke
the ResetSystem() function provided by the EFI runtime services, while
the ACPI OSL code wants to know whether the EFI config tables were
mapped successfully. There are also checks in some of the platform
driver code to simply see if they're running on an EFI machine (which
would make it a bad idea to do BIOS-y things).

This patch is a prereq for the samsung-laptop fix patch.

Cc: David Airlie <airlied@linux.ie>
Cc: Corentin Chary <corentincj@iksaif.net>
Cc: Matthew Garrett <mjg59@srcf.ucam.org>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Olof Johansson <olof@lixom.net>
Cc: Peter Jones <pjones@redhat.com>
Cc: Colin Ian King <colin.king@canonical.com>
Cc: Steve Langasek <steve.langasek@canonical.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Konrad Rzeszutek Wilk <konrad@kernel.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: <stable@vger.kernel.org>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/x86/include/asm/efi.h             |  1 +
 arch/x86/kernel/reboot.c               |  2 +-
 arch/x86/kernel/setup.c                | 28 ++++++++---------
 arch/x86/platform/efi/efi.c            | 57 ++++++++++++++++++++--------------
 drivers/acpi/osl.c                     |  2 +-
 drivers/firmware/dmi_scan.c            |  2 +-
 drivers/firmware/efivars.c             |  4 +--
 drivers/firmware/iscsi_ibft_find.c     |  2 +-
 drivers/gpu/drm/radeon/radeon_device.c |  3 +-
 drivers/platform/x86/ibm_rtl.c         |  2 +-
 drivers/scsi/isci/init.c               |  2 +-
 include/linux/efi.h                    | 24 ++++++++++----
 init/main.c                            |  4 +--
 13 files changed, 79 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 6e8fdf5ad113..28677c55113f 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -94,6 +94,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
+extern unsigned long x86_efi_facility;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 4e8ba39eaf0f..76fa1e9a2b39 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -584,7 +584,7 @@ static void native_machine_emergency_restart(void)
 			break;
 
 		case BOOT_EFI:
-			if (efi_enabled)
+			if (efi_enabled(EFI_RUNTIME_SERVICES))
 				efi.reset_system(reboot_mode ?
 						 EFI_RESET_WARM :
 						 EFI_RESET_COLD,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 00f6c1472b85..8b24289cc10c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -807,15 +807,15 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL32", 4)) {
-		efi_enabled = 1;
-		efi_64bit = false;
+		set_bit(EFI_BOOT, &x86_efi_facility);
 	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL64", 4)) {
-		efi_enabled = 1;
-		efi_64bit = true;
+		set_bit(EFI_BOOT, &x86_efi_facility);
+		set_bit(EFI_64BIT, &x86_efi_facility);
 	}
-	if (efi_enabled && efi_memblock_x86_reserve_range())
-		efi_enabled = 0;
+
+	if (efi_enabled(EFI_BOOT))
+		efi_memblock_x86_reserve_range();
 #endif
 
 	x86_init.oem.arch_setup();
@@ -888,7 +888,7 @@ void __init setup_arch(char **cmdline_p)
 
 	finish_e820_parsing();
 
-	if (efi_enabled)
+	if (efi_enabled(EFI_BOOT))
 		efi_init();
 
 	dmi_scan_machine();
@@ -971,7 +971,7 @@ void __init setup_arch(char **cmdline_p)
 	 * The EFI specification says that boot service code won't be called
 	 * after ExitBootServices(). This is, in fact, a lie.
 	 */
-	if (efi_enabled)
+	if (efi_enabled(EFI_MEMMAP))
 		efi_reserve_boot_services();
 
 	/* preallocate 4k for mptable mpc */
@@ -1114,7 +1114,7 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
-	if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
+	if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
 		conswitchp = &vga_con;
 #elif defined(CONFIG_DUMMY_CONSOLE)
 	conswitchp = &dummy_con;
@@ -1131,14 +1131,14 @@ void __init setup_arch(char **cmdline_p)
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
-	/* Once setup is done above, disable efi_enabled on mismatched
-	 * firmware/kernel archtectures since there is no support for
-	 * runtime services.
+	/* Once setup is done above, unmap the EFI memory map on
+	 * mismatched firmware/kernel archtectures since there is no
+	 * support for runtime services.
 	 */
-	if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) {
+	if (efi_enabled(EFI_BOOT) &&
+	    IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) {
 		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
 		efi_unmap_memmap();
-		efi_enabled = 0;
 	}
 #endif
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index ad4439145f85..5426e482db6e 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -51,9 +51,6 @@
 
 #define EFI_DEBUG	1
 
-int efi_enabled;
-EXPORT_SYMBOL(efi_enabled);
-
 struct efi __read_mostly efi = {
 	.mps        = EFI_INVALID_TABLE_ADDR,
 	.acpi       = EFI_INVALID_TABLE_ADDR,
@@ -69,19 +66,28 @@ EXPORT_SYMBOL(efi);
 
 struct efi_memory_map memmap;
 
-bool efi_64bit;
-
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
 static inline bool efi_is_native(void)
 {
-	return IS_ENABLED(CONFIG_X86_64) == efi_64bit;
+	return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
+}
+
+unsigned long x86_efi_facility;
+
+/*
+ * Returns 1 if 'facility' is enabled, 0 otherwise.
+ */
+int efi_enabled(int facility)
+{
+	return test_bit(facility, &x86_efi_facility) != 0;
 }
+EXPORT_SYMBOL(efi_enabled);
 
 static int __init setup_noefi(char *arg)
 {
-	efi_enabled = 0;
+	clear_bit(EFI_BOOT, &x86_efi_facility);
 	return 0;
 }
 early_param("noefi", setup_noefi);
@@ -426,6 +432,7 @@ void __init efi_reserve_boot_services(void)
 
 void __init efi_unmap_memmap(void)
 {
+	clear_bit(EFI_MEMMAP, &x86_efi_facility);
 	if (memmap.map) {
 		early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
 		memmap.map = NULL;
@@ -460,7 +467,7 @@ void __init efi_free_boot_services(void)
 
 static int __init efi_systab_init(void *phys)
 {
-	if (efi_64bit) {
+	if (efi_enabled(EFI_64BIT)) {
 		efi_system_table_64_t *systab64;
 		u64 tmp = 0;
 
@@ -552,7 +559,7 @@ static int __init efi_config_init(u64 tables, int nr_tables)
 	void *config_tables, *tablep;
 	int i, sz;
 
-	if (efi_64bit)
+	if (efi_enabled(EFI_64BIT))
 		sz = sizeof(efi_config_table_64_t);
 	else
 		sz = sizeof(efi_config_table_32_t);
@@ -572,7 +579,7 @@ static int __init efi_config_init(u64 tables, int nr_tables)
 		efi_guid_t guid;
 		unsigned long table;
 
-		if (efi_64bit) {
+		if (efi_enabled(EFI_64BIT)) {
 			u64 table64;
 			guid = ((efi_config_table_64_t *)tablep)->guid;
 			table64 = ((efi_config_table_64_t *)tablep)->table;
@@ -684,7 +691,6 @@ void __init efi_init(void)
 	if (boot_params.efi_info.efi_systab_hi ||
 	    boot_params.efi_info.efi_memmap_hi) {
 		pr_info("Table located above 4GB, disabling EFI.\n");
-		efi_enabled = 0;
 		return;
 	}
 	efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
@@ -694,10 +700,10 @@ void __init efi_init(void)
 			  ((__u64)boot_params.efi_info.efi_systab_hi<<32));
 #endif
 
-	if (efi_systab_init(efi_phys.systab)) {
-		efi_enabled = 0;
+	if (efi_systab_init(efi_phys.systab))
 		return;
-	}
+
+	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
 
 	/*
 	 * Show what we know for posterity
@@ -715,10 +721,10 @@ void __init efi_init(void)
 		efi.systab->hdr.revision >> 16,
 		efi.systab->hdr.revision & 0xffff, vendor);
 
-	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables)) {
-		efi_enabled = 0;
+	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables))
 		return;
-	}
+
+	set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
 
 	/*
 	 * Note: We currently don't support runtime services on an EFI
@@ -727,15 +733,17 @@ void __init efi_init(void)
 
 	if (!efi_is_native())
 		pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
-	else if (efi_runtime_init()) {
-		efi_enabled = 0;
-		return;
+	else {
+		if (efi_runtime_init())
+			return;
+		set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
 	}
 
-	if (efi_memmap_init()) {
-		efi_enabled = 0;
+	if (efi_memmap_init())
 		return;
-	}
+
+	set_bit(EFI_MEMMAP, &x86_efi_facility);
+
 #ifdef CONFIG_X86_32
 	if (efi_is_native()) {
 		x86_platform.get_wallclock = efi_get_time;
@@ -969,6 +977,9 @@ u32 efi_mem_type(unsigned long phys_addr)
 	efi_memory_desc_t *md;
 	void *p;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return 0;
+
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
 		if ((md->phys_addr <= phys_addr) &&
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 3ff267861541..bd22f8667eed 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -250,7 +250,7 @@ acpi_physical_address __init acpi_os_get_root_pointer(void)
 		return acpi_rsdp;
 #endif
 
-	if (efi_enabled) {
+	if (efi_enabled(EFI_CONFIG_TABLES)) {
 		if (efi.acpi20 != EFI_INVALID_TABLE_ADDR)
 			return efi.acpi20;
 		else if (efi.acpi != EFI_INVALID_TABLE_ADDR)
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index fd3ae6290d71..982f1f5f5742 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -471,7 +471,7 @@ void __init dmi_scan_machine(void)
 	char __iomem *p, *q;
 	int rc;
 
-	if (efi_enabled) {
+	if (efi_enabled(EFI_CONFIG_TABLES)) {
 		if (efi.smbios == EFI_INVALID_TABLE_ADDR)
 			goto error;
 
diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index 7b1c37497c9a..1065119dff92 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -1782,7 +1782,7 @@ efivars_init(void)
 	printk(KERN_INFO "EFI Variables Facility v%s %s\n", EFIVARS_VERSION,
 	       EFIVARS_DATE);
 
-	if (!efi_enabled)
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
 		return 0;
 
 	/* For now we'll register the efi directory at /sys/firmware/efi */
@@ -1822,7 +1822,7 @@ err_put:
 static void __exit
 efivars_exit(void)
 {
-	if (efi_enabled) {
+	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
 		unregister_efivars(&__efivars);
 		kobject_put(efi_kobj);
 	}
diff --git a/drivers/firmware/iscsi_ibft_find.c b/drivers/firmware/iscsi_ibft_find.c
index 4da4eb9ae926..2224f1dc074b 100644
--- a/drivers/firmware/iscsi_ibft_find.c
+++ b/drivers/firmware/iscsi_ibft_find.c
@@ -99,7 +99,7 @@ unsigned long __init find_ibft_region(unsigned long *sizep)
 	/* iBFT 1.03 section 1.4.3.1 mandates that UEFI machines will
 	 * only use ACPI for this */
 
-	if (!efi_enabled)
+	if (!efi_enabled(EFI_BOOT))
 		find_ibft_in_mem();
 
 	if (ibft_addr) {
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index edfc54e41842..0d6562bb0c93 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -429,7 +429,8 @@ bool radeon_card_posted(struct radeon_device *rdev)
 {
 	uint32_t reg;
 
-	if (efi_enabled && rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE)
+	if (efi_enabled(EFI_BOOT) &&
+	    rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE)
 		return false;
 
 	/* first check CRTCs */
diff --git a/drivers/platform/x86/ibm_rtl.c b/drivers/platform/x86/ibm_rtl.c
index 7481146a5b47..97c2be195efc 100644
--- a/drivers/platform/x86/ibm_rtl.c
+++ b/drivers/platform/x86/ibm_rtl.c
@@ -244,7 +244,7 @@ static int __init ibm_rtl_init(void) {
 	if (force)
 		pr_warn("module loaded by force\n");
 	/* first ensure that we are running on IBM HW */
-	else if (efi_enabled || !dmi_check_system(ibm_rtl_dmi_table))
+	else if (efi_enabled(EFI_BOOT) || !dmi_check_system(ibm_rtl_dmi_table))
 		return -ENODEV;
 
 	/* Get the address for the Extended BIOS Data Area */
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index d73fdcfeb45a..2839baa82a5a 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -633,7 +633,7 @@ static int isci_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 	pci_set_drvdata(pdev, pci_info);
 
-	if (efi_enabled)
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		orom = isci_get_efi_var(pdev);
 
 	if (!orom)
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 8b84916dc671..7a9498ab3c2d 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -618,18 +618,30 @@ extern int __init efi_setup_pcdp_console(char *);
 #endif
 
 /*
- * We play games with efi_enabled so that the compiler will, if possible, remove
- * EFI-related code altogether.
+ * We play games with efi_enabled so that the compiler will, if
+ * possible, remove EFI-related code altogether.
  */
+#define EFI_BOOT		0	/* Were we booted from EFI? */
+#define EFI_SYSTEM_TABLES	1	/* Can we use EFI system tables? */
+#define EFI_CONFIG_TABLES	2	/* Can we use EFI config tables? */
+#define EFI_RUNTIME_SERVICES	3	/* Can we use runtime services? */
+#define EFI_MEMMAP		4	/* Can we use EFI memory map? */
+#define EFI_64BIT		5	/* Is the firmware 64-bit? */
+
 #ifdef CONFIG_EFI
 # ifdef CONFIG_X86
-   extern int efi_enabled;
-   extern bool efi_64bit;
+extern int efi_enabled(int facility);
 # else
-#  define efi_enabled 1
+static inline int efi_enabled(int facility)
+{
+	return 1;
+}
 # endif
 #else
-# define efi_enabled 0
+static inline int efi_enabled(int facility)
+{
+	return 0;
+}
 #endif
 
 /*
diff --git a/init/main.c b/init/main.c
index 85d69dffe864..cd30179c86bd 100644
--- a/init/main.c
+++ b/init/main.c
@@ -604,7 +604,7 @@ asmlinkage void __init start_kernel(void)
 	pidmap_init();
 	anon_vma_init();
 #ifdef CONFIG_X86
-	if (efi_enabled)
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
 #endif
 	thread_info_cache_init();
@@ -632,7 +632,7 @@ asmlinkage void __init start_kernel(void)
 	acpi_early_init(); /* before LAPIC and SMP init */
 	sfi_init_late();
 
-	if (efi_enabled) {
+	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
 		efi_late_init();
 		efi_free_boot_services();
 	}
-- 
cgit v1.2.3-55-g7522


From 70c37bf97f2a91accba76080db69144f3b69f736 Mon Sep 17 00:00:00 2001
From: Bjørn Mork
Date: Mon, 28 Jan 2013 23:51:28 +0000
Subject: net: usbnet: prevent buggy devices from killing us

A device sending 0 length frames as fast as it can has been
observed killing the host system due to the resulting memory
pressure.

Temporarily disable RX skb allocation and URB submission when
the current error ratio is high, preventing us from trying to
allocate an infinite number of skbs.  Reenable as soon as we
are finished processing the done queue, allowing the device
to continue working after short error bursts.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-by: Oliver Neukum <oneukum@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c   | 25 +++++++++++++++++++++++++
 include/linux/usb/usbnet.h |  2 ++
 2 files changed, 27 insertions(+)

(limited to 'include')

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index f34b2ebee815..977837725726 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -380,6 +380,12 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
 	unsigned long		lockflags;
 	size_t			size = dev->rx_urb_size;
 
+	/* prevent rx skb allocation when error ratio is high */
+	if (test_bit(EVENT_RX_KILL, &dev->flags)) {
+		usb_free_urb(urb);
+		return -ENOLINK;
+	}
+
 	skb = __netdev_alloc_skb_ip_align(dev->net, size, flags);
 	if (!skb) {
 		netif_dbg(dev, rx_err, dev->net, "no rx skb\n");
@@ -539,6 +545,17 @@ block:
 		break;
 	}
 
+	/* stop rx if packet error rate is high */
+	if (++dev->pkt_cnt > 30) {
+		dev->pkt_cnt = 0;
+		dev->pkt_err = 0;
+	} else {
+		if (state == rx_cleanup)
+			dev->pkt_err++;
+		if (dev->pkt_err > 20)
+			set_bit(EVENT_RX_KILL, &dev->flags);
+	}
+
 	state = defer_bh(dev, skb, &dev->rxq, state);
 
 	if (urb) {
@@ -791,6 +808,11 @@ int usbnet_open (struct net_device *net)
 		   (dev->driver_info->flags & FLAG_FRAMING_AX) ? "ASIX" :
 		   "simple");
 
+	/* reset rx error state */
+	dev->pkt_cnt = 0;
+	dev->pkt_err = 0;
+	clear_bit(EVENT_RX_KILL, &dev->flags);
+
 	// delay posting reads until we're fully open
 	tasklet_schedule (&dev->bh);
 	if (info->manage_power) {
@@ -1254,6 +1276,9 @@ static void usbnet_bh (unsigned long param)
 		}
 	}
 
+	/* restart RX again after disabling due to high error rate */
+	clear_bit(EVENT_RX_KILL, &dev->flags);
+
 	// waiting for all pending urbs to complete?
 	if (dev->wait) {
 		if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) {
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 5de7a220e986..0de078d4cdb9 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -33,6 +33,7 @@ struct usbnet {
 	wait_queue_head_t	*wait;
 	struct mutex		phy_mutex;
 	unsigned char		suspend_count;
+	unsigned char		pkt_cnt, pkt_err;
 
 	/* i/o info: pipes etc */
 	unsigned		in, out;
@@ -70,6 +71,7 @@ struct usbnet {
 #		define EVENT_DEV_OPEN	7
 #		define EVENT_DEVICE_REPORT_IDLE	8
 #		define EVENT_NO_RUNTIME_PM	9
+#		define EVENT_RX_KILL	10
 };
 
 static inline struct usb_driver *driver_of(struct usb_interface *intf)
-- 
cgit v1.2.3-55-g7522


From 73df66f8b1926c59cbc83000af6bf37ecc5509dd Mon Sep 17 00:00:00 2001
From: Tom Parkin
Date: Thu, 31 Jan 2013 01:02:24 +0000
Subject: ipv6: rename datagram_send_ctl and datagram_recv_ctl

The datagram_*_ctl functions in net/ipv6/datagram.c are IPv6-specific.  Since
datagram_send_ctl is publicly exported it should be appropriately named to
reflect the fact that it's for IPv6 only.

Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/transp_v6.h  | 22 +++++++++++-----------
 net/ipv6/datagram.c      | 15 ++++++++-------
 net/ipv6/ip6_flowlabel.c |  4 ++--
 net/ipv6/ipv6_sockglue.c |  6 +++---
 net/ipv6/raw.c           |  6 +++---
 net/ipv6/udp.c           |  6 +++---
 net/l2tp/l2tp_ip6.c      |  4 ++--
 net/sunrpc/svcsock.c     |  2 +-
 8 files changed, 33 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index 498433dd067d..938b7fd11204 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -34,17 +34,17 @@ extern int				udpv6_connect(struct sock *sk,
 						      struct sockaddr *uaddr,
 						      int addr_len);
 
-extern int			datagram_recv_ctl(struct sock *sk,
-						  struct msghdr *msg,
-						  struct sk_buff *skb);
-
-extern int			datagram_send_ctl(struct net *net,
-						  struct sock *sk,
-						  struct msghdr *msg,
-						  struct flowi6 *fl6,
-						  struct ipv6_txoptions *opt,
-						  int *hlimit, int *tclass,
-						  int *dontfrag);
+extern int			ip6_datagram_recv_ctl(struct sock *sk,
+						      struct msghdr *msg,
+						      struct sk_buff *skb);
+
+extern int			ip6_datagram_send_ctl(struct net *net,
+						      struct sock *sk,
+						      struct msghdr *msg,
+						      struct flowi6 *fl6,
+						      struct ipv6_txoptions *opt,
+						      int *hlimit, int *tclass,
+						      int *dontfrag);
 
 #define		LOOPBACK4_IPV6		cpu_to_be32(0x7f000006)
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 8edf2601065a..06fd2730838b 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -380,7 +380,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			sin->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (np->rxopt.all)
-				datagram_recv_ctl(sk, msg, skb);
+				ip6_datagram_recv_ctl(sk, msg, skb);
 			if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
 				sin->sin6_scope_id = IP6CB(skb)->iif;
 		} else {
@@ -468,7 +468,8 @@ out:
 }
 
 
-int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
+int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
+			  struct sk_buff *skb)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet6_skb_parm *opt = IP6CB(skb);
@@ -598,10 +599,10 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
 	return 0;
 }
 
-int datagram_send_ctl(struct net *net, struct sock *sk,
-		      struct msghdr *msg, struct flowi6 *fl6,
-		      struct ipv6_txoptions *opt,
-		      int *hlimit, int *tclass, int *dontfrag)
+int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
+			  struct msghdr *msg, struct flowi6 *fl6,
+			  struct ipv6_txoptions *opt,
+			  int *hlimit, int *tclass, int *dontfrag)
 {
 	struct in6_pktinfo *src_info;
 	struct cmsghdr *cmsg;
@@ -871,4 +872,4 @@ int datagram_send_ctl(struct net *net, struct sock *sk,
 exit_f:
 	return err;
 }
-EXPORT_SYMBOL_GPL(datagram_send_ctl);
+EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl);
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 29124b7a04c8..d6de4b447250 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -365,8 +365,8 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 		msg.msg_control = (void*)(fl->opt+1);
 		memset(&flowi6, 0, sizeof(flowi6));
 
-		err = datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt, &junk,
-					&junk, &junk);
+		err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt,
+					    &junk, &junk, &junk);
 		if (err)
 			goto done;
 		err = -EINVAL;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index ee94d31c9d4d..d1e2e8ef29c5 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -476,8 +476,8 @@ sticky_done:
 		msg.msg_controllen = optlen;
 		msg.msg_control = (void*)(opt+1);
 
-		retv = datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, &junk,
-					 &junk);
+		retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk,
+					     &junk, &junk);
 		if (retv)
 			goto done;
 update:
@@ -1002,7 +1002,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		release_sock(sk);
 
 		if (skb) {
-			int err = datagram_recv_ctl(sk, &msg, skb);
+			int err = ip6_datagram_recv_ctl(sk, &msg, skb);
 			kfree_skb(skb);
 			if (err)
 				return err;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 6cd29b1e8b92..70fa81449997 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -507,7 +507,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (np->rxopt.all)
-		datagram_recv_ctl(sk, msg, skb);
+		ip6_datagram_recv_ctl(sk, msg, skb);
 
 	err = copied;
 	if (flags & MSG_TRUNC)
@@ -822,8 +822,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(struct ipv6_txoptions);
 
-		err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
-					&hlimit, &tclass, &dontfrag);
+		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
+					    &hlimit, &tclass, &dontfrag);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index dfaa29b8b293..fb083295ff0b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -443,7 +443,7 @@ try_again:
 			ip_cmsg_recv(msg, skb);
 	} else {
 		if (np->rxopt.all)
-			datagram_recv_ctl(sk, msg, skb);
+			ip6_datagram_recv_ctl(sk, msg, skb);
 	}
 
 	err = copied;
@@ -1153,8 +1153,8 @@ do_udp_sendmsg:
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(*opt);
 
-		err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
-					&hlimit, &tclass, &dontfrag);
+		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
+					    &hlimit, &tclass, &dontfrag);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 927547171bc7..2316947ee772 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -554,8 +554,8 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(struct ipv6_txoptions);
 
-		err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
-					&hlimit, &tclass, &dontfrag);
+		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
+					    &hlimit, &tclass, &dontfrag);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 0a148c9d2a5c..0f679df7d072 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -465,7 +465,7 @@ static int svc_udp_get_dest_address4(struct svc_rqst *rqstp,
 }
 
 /*
- * See net/ipv6/datagram.c : datagram_recv_ctl
+ * See net/ipv6/datagram.c : ip6_datagram_recv_ctl
  */
 static int svc_udp_get_dest_address6(struct svc_rqst *rqstp,
 				     struct cmsghdr *cmh)
-- 
cgit v1.2.3-55-g7522


From 631b0cfdbd801ceae8762e8d287f15da26792ebe Mon Sep 17 00:00:00 2001
From: Yuanhan Liu
Date: Mon, 4 Feb 2013 14:28:48 -0800
Subject: mm: fix wrong comments about anon_vma lock

We use rwsem since commit 5a505085f043 ("mm/rmap: Convert the struct
anon_vma::mutex to an rwsem").  And most of comments are converted to
the new rwsem lock; while just 2 more missed from:

	 $ git grep 'anon_vma->mutex'

Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmu_notifier.h | 2 +-
 mm/mmap.c                    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index bc823c4c028b..deca87452528 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -151,7 +151,7 @@ struct mmu_notifier_ops {
  * Therefore notifier chains can only be traversed when either
  *
  * 1. mmap_sem is held.
- * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->mutex).
+ * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->rwsem).
  * 3. No other concurrent thread can access the list (release)
  */
 struct mmu_notifier {
diff --git a/mm/mmap.c b/mm/mmap.c
index 35730ee9d515..d1e4124f3d0e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2943,7 +2943,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
  * vma in this mm is backed by the same anon_vma or address_space.
  *
  * We can take all the locks in random order because the VM code
- * taking i_mmap_mutex or anon_vma->mutex outside the mmap_sem never
+ * taking i_mmap_mutex or anon_vma->rwsem outside the mmap_sem never
  * takes more than one of them in a row. Secondly we're protected
  * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
  *
-- 
cgit v1.2.3-55-g7522


From 91c777d86752b00bb3a1d8efa3d8f7e1264f38a9 Mon Sep 17 00:00:00 2001
From: Glauber Costa
Date: Mon, 4 Feb 2013 14:28:49 -0800
Subject: memcg: fix typo in kmemcg cache walk macro

The macro for_each_memcg_cache_index contains a silly yet potentially
deadly mistake.  Although the macro parameter is _idx, the loop tests
are done over i, not _idx.

This hasn't generated any problems so far, because all users use i as a
loop index.  However, while playing with an extension of the code I
ended using another loop index and the compiler was quick to complain.

Unfortunately, this is not the kind of thing that testing reveals =(

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 0108a56f814e..28bd5fa2ff2e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -429,7 +429,7 @@ extern int memcg_limited_groups_array_size;
  * the slab_mutex must be held when looping through those caches
  */
 #define for_each_memcg_cache_index(_idx)	\
-	for ((_idx) = 0; i < memcg_limited_groups_array_size; (_idx)++)
+	for ((_idx) = 0; (_idx) < memcg_limited_groups_array_size; (_idx)++)
 
 static inline bool memcg_kmem_enabled(void)
 {
-- 
cgit v1.2.3-55-g7522


From 9c79330d930b5774aed8eb323daebecedce2e245 Mon Sep 17 00:00:00 2001
From: Lucas Stach
Date: Thu, 7 Feb 2013 16:18:39 +0000
Subject: net: usb: fix regression from FLAG_NOARP code

In commit 6509141f9c2ba74df6cc72ec35cd1865276ae3a4 ("usbnet: add new
flag FLAG_NOARP for usb net devices"), the newly added flag NOARP was
using an already defined value, which broke drivers using flag
MULTI_PACKET.

Signed-off-by: Lucas Stach <dev@lynxeye.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/usb/usbnet.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 0de078d4cdb9..0e5ac93bab10 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -102,7 +102,6 @@ struct driver_info {
 #define FLAG_LINK_INTR	0x0800		/* updates link (carrier) status */
 
 #define FLAG_POINTTOPOINT 0x1000	/* possibly use "usb%d" names */
-#define FLAG_NOARP	0x2000		/* device can't do ARP */
 
 /*
  * Indicates to usbnet, that USB driver accumulates multiple IP packets.
@@ -110,6 +109,7 @@ struct driver_info {
  */
 #define FLAG_MULTI_PACKET	0x2000
 #define FLAG_RX_ASSEMBLE	0x4000	/* rx packets may span >1 frames */
+#define FLAG_NOARP		0x8000	/* device can't do ARP */
 
 	/* init device ... can sleep, or cause probe() failure */
 	int	(*bind)(struct usbnet *, struct usb_interface *);
-- 
cgit v1.2.3-55-g7522